OpenCloudOS-Kernel/include/linux/ftrace.h

909 lines
29 KiB
C
Raw Normal View History

/*
* Ftrace header. For implementation details beyond the random comments
* scattered below, see: Documentation/trace/ftrace-design.txt
*/
#ifndef _LINUX_FTRACE_H
#define _LINUX_FTRACE_H
#include <linux/trace_clock.h>
#include <linux/kallsyms.h>
#include <linux/linkage.h>
ftrace: graph of a single function This patch adds the file: /debugfs/tracing/set_graph_function which can be used along with the function graph tracer. When this file is empty, the function graph tracer will act as usual. When the file has a function in it, the function graph tracer will only trace that function. For example: # echo blk_unplug > /debugfs/tracing/set_graph_function # cat /debugfs/tracing/trace [...] ------------------------------------------ | 2) make-19003 => kjournald-2219 ------------------------------------------ 2) | blk_unplug() { 2) | dm_unplug_all() { 2) | dm_get_table() { 2) 1.381 us | _read_lock(); 2) 0.911 us | dm_table_get(); 2) 1. 76 us | _read_unlock(); 2) + 12.912 us | } 2) | dm_table_unplug_all() { 2) | blk_unplug() { 2) 0.778 us | generic_unplug_device(); 2) 2.409 us | } 2) 5.992 us | } 2) 0.813 us | dm_table_put(); 2) + 29. 90 us | } 2) + 34.532 us | } You can add up to 32 functions into this file. Currently we limit it to 32, but this may change with later improvements. To add another function, use the append '>>': # echo sys_read >> /debugfs/tracing/set_graph_function # cat /debugfs/tracing/set_graph_function blk_unplug sys_read Using the '>' will clear out the function and write anew: # echo sys_write > /debug/tracing/set_graph_function # cat /debug/tracing/set_graph_function sys_write Note, if you have function graph running while doing this, the small time between clearing it and updating it will cause the graph to record all functions. This should not be an issue because after it sets the filter, only those functions will be recorded from then on. If you need to only record a particular function then set this file first before starting the function graph tracer. In the future this side effect may be corrected. The set_graph_function file is similar to the set_ftrace_filter but it does not take wild cards nor does it allow for more than one function to be set with a single write. There is no technical reason why this is the case, I just do not have the time yet to implement that. Note, dynamic ftrace must be enabled for this to appear because it uses the dynamic ftrace records to match the name to the mcount call sites. Signed-off-by: Steven Rostedt <srostedt@redhat.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2008-12-04 04:36:57 +08:00
#include <linux/bitops.h>
#include <linux/ptrace.h>
#include <linux/ktime.h>
#include <linux/sched.h>
#include <linux/types.h>
#include <linux/init.h>
#include <linux/fs.h>
#include <asm/ftrace.h>
/*
* If the arch supports passing the variable contents of
* function_trace_op as the third parameter back from the
* mcount call, then the arch should define this as 1.
*/
#ifndef ARCH_SUPPORTS_FTRACE_OPS
#define ARCH_SUPPORTS_FTRACE_OPS 0
#endif
/*
* If the arch's mcount caller does not support all of ftrace's
* features, then it must call an indirect function that
* does. Or at least does enough to prevent any unwelcomed side effects.
*/
#if !ARCH_SUPPORTS_FTRACE_OPS
# define FTRACE_FORCE_LIST_FUNC 1
#else
# define FTRACE_FORCE_LIST_FUNC 0
#endif
/* Main tracing buffer and events set up */
#ifdef CONFIG_TRACING
void trace_init(void);
#else
static inline void trace_init(void) { }
#endif
struct module;
struct ftrace_hash;
#ifdef CONFIG_FUNCTION_TRACER
extern int ftrace_enabled;
extern int
ftrace_enable_sysctl(struct ctl_table *table, int write,
void __user *buffer, size_t *lenp,
loff_t *ppos);
struct ftrace_ops;
typedef void (*ftrace_func_t)(unsigned long ip, unsigned long parent_ip,
struct ftrace_ops *op, struct pt_regs *regs);
ftrace_func_t ftrace_ops_get_func(struct ftrace_ops *ops);
/*
* FTRACE_OPS_FL_* bits denote the state of ftrace_ops struct and are
* set in the flags member.
* CONTROL, SAVE_REGS, SAVE_REGS_IF_SUPPORTED, RECURSION_SAFE, STUB and
* IPMODIFY are a kind of attribute flags which can be set only before
* registering the ftrace_ops, and can not be modified while registered.
* Changing those attribute flags after regsitering ftrace_ops will
* cause unexpected results.
*
* ENABLED - set/unset when ftrace_ops is registered/unregistered
* DYNAMIC - set when ftrace_ops is registered to denote dynamically
* allocated ftrace_ops which need special care
* CONTROL - set manualy by ftrace_ops user to denote the ftrace_ops
* could be controled by following calls:
* ftrace_function_local_enable
* ftrace_function_local_disable
ftrace/x86: Add separate function to save regs Add a way to have different functions calling different trampolines. If a ftrace_ops wants regs saved on the return, then have only the functions with ops registered to save regs. Functions registered by other ops would not be affected, unless the functions overlap. If one ftrace_ops registered functions A, B and C and another ops registered fucntions to save regs on A, and D, then only functions A and D would be saving regs. Function B and C would work as normal. Although A is registered by both ops: normal and saves regs; this is fine as saving the regs is needed to satisfy one of the ops that calls it but the regs are ignored by the other ops function. x86_64 implements the full regs saving, and i386 just passes a NULL for regs to satisfy the ftrace_ops passing. Where an arch must supply both regs and ftrace_ops parameters, even if regs is just NULL. It is OK for an arch to pass NULL regs. All function trace users that require regs passing must add the flag FTRACE_OPS_FL_SAVE_REGS when registering the ftrace_ops. If the arch does not support saving regs then the ftrace_ops will fail to register. The flag FTRACE_OPS_FL_SAVE_REGS_IF_SUPPORTED may be set that will prevent the ftrace_ops from failing to register. In this case, the handler may either check if regs is not NULL or check if ARCH_SUPPORTS_FTRACE_SAVE_REGS. If the arch supports passing regs it will set this macro and pass regs for ops that request them. All other archs will just pass NULL. Link: Link: http://lkml.kernel.org/r/20120711195745.107705970@goodmis.org Cc: Alexander van Heukelum <heukelum@fastmail.fm> Reviewed-by: Masami Hiramatsu <masami.hiramatsu.pt@hitachi.com> Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
2012-05-01 04:20:23 +08:00
* SAVE_REGS - The ftrace_ops wants regs saved at each function called
* and passed to the callback. If this flag is set, but the
* architecture does not support passing regs
* (CONFIG_DYNAMIC_FTRACE_WITH_REGS is not defined), then the
ftrace/x86: Add separate function to save regs Add a way to have different functions calling different trampolines. If a ftrace_ops wants regs saved on the return, then have only the functions with ops registered to save regs. Functions registered by other ops would not be affected, unless the functions overlap. If one ftrace_ops registered functions A, B and C and another ops registered fucntions to save regs on A, and D, then only functions A and D would be saving regs. Function B and C would work as normal. Although A is registered by both ops: normal and saves regs; this is fine as saving the regs is needed to satisfy one of the ops that calls it but the regs are ignored by the other ops function. x86_64 implements the full regs saving, and i386 just passes a NULL for regs to satisfy the ftrace_ops passing. Where an arch must supply both regs and ftrace_ops parameters, even if regs is just NULL. It is OK for an arch to pass NULL regs. All function trace users that require regs passing must add the flag FTRACE_OPS_FL_SAVE_REGS when registering the ftrace_ops. If the arch does not support saving regs then the ftrace_ops will fail to register. The flag FTRACE_OPS_FL_SAVE_REGS_IF_SUPPORTED may be set that will prevent the ftrace_ops from failing to register. In this case, the handler may either check if regs is not NULL or check if ARCH_SUPPORTS_FTRACE_SAVE_REGS. If the arch supports passing regs it will set this macro and pass regs for ops that request them. All other archs will just pass NULL. Link: Link: http://lkml.kernel.org/r/20120711195745.107705970@goodmis.org Cc: Alexander van Heukelum <heukelum@fastmail.fm> Reviewed-by: Masami Hiramatsu <masami.hiramatsu.pt@hitachi.com> Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
2012-05-01 04:20:23 +08:00
* ftrace_ops will fail to register, unless the next flag
* is set.
* SAVE_REGS_IF_SUPPORTED - This is the same as SAVE_REGS, but if the
* handler can handle an arch that does not save regs
* (the handler tests if regs == NULL), then it can set
* this flag instead. It will not fail registering the ftrace_ops
* but, the regs field will be NULL if the arch does not support
* passing regs to the handler.
* Note, if this flag is set, the SAVE_REGS flag will automatically
* get set upon registering the ftrace_ops, if the arch supports it.
* RECURSION_SAFE - The ftrace_ops can set this to tell the ftrace infrastructure
* that the call back has its own recursion protection. If it does
* not set this, then the ftrace infrastructure will add recursion
* protection for the caller.
ftrace: Do not call stub functions in control loop The function tracing control loop used by perf spits out a warning if the called function is not a control function. This is because the control function references a per cpu allocated data structure on struct ftrace_ops that is not allocated for other types of functions. commit 0a016409e42 "ftrace: Optimize the function tracer list loop" Had an optimization done to all function tracing loops to optimize for a single registered ops. Unfortunately, this allows for a slight race when tracing starts or ends, where the stub function might be called after the current registered ops is removed. In this case we get the following dump: root# perf stat -e ftrace:function sleep 1 [ 74.339105] WARNING: at include/linux/ftrace.h:209 ftrace_ops_control_func+0xde/0xf0() [ 74.349522] Hardware name: PRIMERGY RX200 S6 [ 74.357149] Modules linked in: sg igb iTCO_wdt ptp pps_core iTCO_vendor_support i7core_edac dca lpc_ich i2c_i801 coretemp edac_core crc32c_intel mfd_core ghash_clmulni_intel dm_multipath acpi_power_meter pcspk r microcode vhost_net tun macvtap macvlan nfsd kvm_intel kvm auth_rpcgss nfs_acl lockd sunrpc uinput xfs libcrc32c sd_mod crc_t10dif sr_mod cdrom mgag200 i2c_algo_bit drm_kms_helper ttm qla2xxx mptsas ahci drm li bahci scsi_transport_sas mptscsih libata scsi_transport_fc i2c_core mptbase scsi_tgt dm_mirror dm_region_hash dm_log dm_mod [ 74.446233] Pid: 1377, comm: perf Tainted: G W 3.9.0-rc1 #1 [ 74.453458] Call Trace: [ 74.456233] [<ffffffff81062e3f>] warn_slowpath_common+0x7f/0xc0 [ 74.462997] [<ffffffff810fbc60>] ? rcu_note_context_switch+0xa0/0xa0 [ 74.470272] [<ffffffff811041a2>] ? __unregister_ftrace_function+0xa2/0x1a0 [ 74.478117] [<ffffffff81062e9a>] warn_slowpath_null+0x1a/0x20 [ 74.484681] [<ffffffff81102ede>] ftrace_ops_control_func+0xde/0xf0 [ 74.491760] [<ffffffff8162f400>] ftrace_call+0x5/0x2f [ 74.497511] [<ffffffff8162f400>] ? ftrace_call+0x5/0x2f [ 74.503486] [<ffffffff8162f400>] ? ftrace_call+0x5/0x2f [ 74.509500] [<ffffffff810fbc65>] ? synchronize_sched+0x5/0x50 [ 74.516088] [<ffffffff816254d5>] ? _cond_resched+0x5/0x40 [ 74.522268] [<ffffffff810fbc65>] ? synchronize_sched+0x5/0x50 [ 74.528837] [<ffffffff811041a2>] ? __unregister_ftrace_function+0xa2/0x1a0 [ 74.536696] [<ffffffff816254d5>] ? _cond_resched+0x5/0x40 [ 74.542878] [<ffffffff8162402d>] ? mutex_lock+0x1d/0x50 [ 74.548869] [<ffffffff81105c67>] unregister_ftrace_function+0x27/0x50 [ 74.556243] [<ffffffff8111eadf>] perf_ftrace_event_register+0x9f/0x140 [ 74.563709] [<ffffffff816254d5>] ? _cond_resched+0x5/0x40 [ 74.569887] [<ffffffff8162402d>] ? mutex_lock+0x1d/0x50 [ 74.575898] [<ffffffff8111e94e>] perf_trace_destroy+0x2e/0x50 [ 74.582505] [<ffffffff81127ba9>] tp_perf_event_destroy+0x9/0x10 [ 74.589298] [<ffffffff811295d0>] free_event+0x70/0x1a0 [ 74.595208] [<ffffffff8112a579>] perf_event_release_kernel+0x69/0xa0 [ 74.602460] [<ffffffff816254d5>] ? _cond_resched+0x5/0x40 [ 74.608667] [<ffffffff8112a640>] put_event+0x90/0xc0 [ 74.614373] [<ffffffff8112a740>] perf_release+0x10/0x20 [ 74.620367] [<ffffffff811a3044>] __fput+0xf4/0x280 [ 74.625894] [<ffffffff811a31de>] ____fput+0xe/0x10 [ 74.631387] [<ffffffff81083697>] task_work_run+0xa7/0xe0 [ 74.637452] [<ffffffff81014981>] do_notify_resume+0x71/0xb0 [ 74.643843] [<ffffffff8162fa92>] int_signal+0x12/0x17 To fix this a new ftrace_ops flag is added that denotes the ftrace_list_end ftrace_ops stub as just that, a stub. This flag is now checked in the control loop and the function is not called if the flag is set. Thanks to Jovi for not just reporting the bug, but also pointing out where the bug was in the code. Link: http://lkml.kernel.org/r/514A8855.7090402@redhat.com Link: http://lkml.kernel.org/r/1364377499-1900-15-git-send-email-jovi.zhangwei@huawei.com Tested-by: WANG Chao <chaowang@redhat.com> Reported-by: WANG Chao <chaowang@redhat.com> Reported-by: zhangwei(Jovi) <jovi.zhangwei@huawei.com> Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
2013-03-27 21:31:28 +08:00
* STUB - The ftrace_ops is just a place holder.
ftrace, kprobes: Fix a deadlock on ftrace_regex_lock Fix a deadlock on ftrace_regex_lock which happens when setting an enable_event trigger on dynamic kprobe event as below. ---- sh-2.05b# echo p vfs_symlink > kprobe_events sh-2.05b# echo vfs_symlink:enable_event:kprobes:p_vfs_symlink_0 > set_ftrace_filter ============================================= [ INFO: possible recursive locking detected ] 3.9.0+ #35 Not tainted --------------------------------------------- sh/72 is trying to acquire lock: (ftrace_regex_lock){+.+.+.}, at: [<ffffffff810ba6c1>] ftrace_set_hash+0x81/0x1f0 but task is already holding lock: (ftrace_regex_lock){+.+.+.}, at: [<ffffffff810b7cbd>] ftrace_regex_write.isra.29.part.30+0x3d/0x220 other info that might help us debug this: Possible unsafe locking scenario: CPU0 ---- lock(ftrace_regex_lock); lock(ftrace_regex_lock); *** DEADLOCK *** ---- To fix that, this introduces a finer regex_lock for each ftrace_ops. ftrace_regex_lock is too big of a lock which protects all filter/notrace_hash operations, but it doesn't need to be a global lock after supporting multiple ftrace_ops because each ftrace_ops has its own filter/notrace_hash. Link: http://lkml.kernel.org/r/20130509054417.30398.84254.stgit@mhiramat-M0-7522 Cc: Srikar Dronamraju <srikar@linux.vnet.ibm.com> Cc: Oleg Nesterov <oleg@redhat.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Ingo Molnar <mingo@redhat.com> Cc: Tom Zanussi <tom.zanussi@intel.com> Signed-off-by: Masami Hiramatsu <masami.hiramatsu.pt@hitachi.com> [ Added initialization flag and automate mutex initialization for non ftrace.c ftrace_probes. ] Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
2013-05-09 13:44:17 +08:00
* INITIALIZED - The ftrace_ops has already been initialized (first use time
* register_ftrace_function() is called, it will initialized the ops)
* DELETED - The ops are being deleted, do not let them be registered again.
* ADDING - The ops is in the process of being added.
* REMOVING - The ops is in the process of being removed.
* MODIFYING - The ops is in the process of changing its filter functions.
ftrace/x86: Add dynamic allocated trampoline for ftrace_ops The current method of handling multiple function callbacks is to register a list function callback that calls all the other callbacks based on their hash tables and compare it to the function that the callback was called on. But this is very inefficient. For example, if you are tracing all functions in the kernel and then add a kprobe to a function such that the kprobe uses ftrace, the mcount trampoline will switch from calling the function trace callback to calling the list callback that will iterate over all registered ftrace_ops (in this case, the function tracer and the kprobes callback). That means for every function being traced it checks the hash of the ftrace_ops for function tracing and kprobes, even though the kprobes is only set at a single function. The kprobes ftrace_ops is checked for every function being traced! Instead of calling the list function for functions that are only being traced by a single callback, we can call a dynamically allocated trampoline that calls the callback directly. The function graph tracer already uses a direct call trampoline when it is being traced by itself but it is not dynamically allocated. It's trampoline is static in the kernel core. The infrastructure that called the function graph trampoline can also be used to call a dynamically allocated one. For now, only ftrace_ops that are not dynamically allocated can have a trampoline. That is, users such as function tracer or stack tracer. kprobes and perf allocate their ftrace_ops, and until there's a safe way to free the trampoline, it can not be used. The dynamically allocated ftrace_ops may, although, use the trampoline if the kernel is not compiled with CONFIG_PREEMPT. But that will come later. Tested-by: Masami Hiramatsu <masami.hiramatsu.pt@hitachi.com> Tested-by: Jiri Kosina <jkosina@suse.cz> Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
2014-07-03 11:23:31 +08:00
* ALLOC_TRAMP - A dynamic trampoline was allocated by the core code.
* The arch specific code sets this flag when it allocated a
* trampoline. This lets the arch know that it can update the
* trampoline in case the callback function changes.
* The ftrace_ops trampoline can be set by the ftrace users, and
* in such cases the arch must not modify it. Only the arch ftrace
* core code should set this flag.
* IPMODIFY - The ops can modify the IP register. This can only be set with
* SAVE_REGS. If another ops with this flag set is already registered
* for any of the functions that this ops will be registered for, then
* this ops will fail to register or set_filter_ip.
* PID - Is affected by set_ftrace_pid (allows filtering on those pids)
*/
enum {
ftrace/x86: Add separate function to save regs Add a way to have different functions calling different trampolines. If a ftrace_ops wants regs saved on the return, then have only the functions with ops registered to save regs. Functions registered by other ops would not be affected, unless the functions overlap. If one ftrace_ops registered functions A, B and C and another ops registered fucntions to save regs on A, and D, then only functions A and D would be saving regs. Function B and C would work as normal. Although A is registered by both ops: normal and saves regs; this is fine as saving the regs is needed to satisfy one of the ops that calls it but the regs are ignored by the other ops function. x86_64 implements the full regs saving, and i386 just passes a NULL for regs to satisfy the ftrace_ops passing. Where an arch must supply both regs and ftrace_ops parameters, even if regs is just NULL. It is OK for an arch to pass NULL regs. All function trace users that require regs passing must add the flag FTRACE_OPS_FL_SAVE_REGS when registering the ftrace_ops. If the arch does not support saving regs then the ftrace_ops will fail to register. The flag FTRACE_OPS_FL_SAVE_REGS_IF_SUPPORTED may be set that will prevent the ftrace_ops from failing to register. In this case, the handler may either check if regs is not NULL or check if ARCH_SUPPORTS_FTRACE_SAVE_REGS. If the arch supports passing regs it will set this macro and pass regs for ops that request them. All other archs will just pass NULL. Link: Link: http://lkml.kernel.org/r/20120711195745.107705970@goodmis.org Cc: Alexander van Heukelum <heukelum@fastmail.fm> Reviewed-by: Masami Hiramatsu <masami.hiramatsu.pt@hitachi.com> Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
2012-05-01 04:20:23 +08:00
FTRACE_OPS_FL_ENABLED = 1 << 0,
FTRACE_OPS_FL_DYNAMIC = 1 << 1,
FTRACE_OPS_FL_CONTROL = 1 << 2,
FTRACE_OPS_FL_SAVE_REGS = 1 << 3,
FTRACE_OPS_FL_SAVE_REGS_IF_SUPPORTED = 1 << 4,
FTRACE_OPS_FL_RECURSION_SAFE = 1 << 5,
FTRACE_OPS_FL_STUB = 1 << 6,
FTRACE_OPS_FL_INITIALIZED = 1 << 7,
FTRACE_OPS_FL_DELETED = 1 << 8,
FTRACE_OPS_FL_ADDING = 1 << 9,
FTRACE_OPS_FL_REMOVING = 1 << 10,
FTRACE_OPS_FL_MODIFYING = 1 << 11,
ftrace/x86: Add dynamic allocated trampoline for ftrace_ops The current method of handling multiple function callbacks is to register a list function callback that calls all the other callbacks based on their hash tables and compare it to the function that the callback was called on. But this is very inefficient. For example, if you are tracing all functions in the kernel and then add a kprobe to a function such that the kprobe uses ftrace, the mcount trampoline will switch from calling the function trace callback to calling the list callback that will iterate over all registered ftrace_ops (in this case, the function tracer and the kprobes callback). That means for every function being traced it checks the hash of the ftrace_ops for function tracing and kprobes, even though the kprobes is only set at a single function. The kprobes ftrace_ops is checked for every function being traced! Instead of calling the list function for functions that are only being traced by a single callback, we can call a dynamically allocated trampoline that calls the callback directly. The function graph tracer already uses a direct call trampoline when it is being traced by itself but it is not dynamically allocated. It's trampoline is static in the kernel core. The infrastructure that called the function graph trampoline can also be used to call a dynamically allocated one. For now, only ftrace_ops that are not dynamically allocated can have a trampoline. That is, users such as function tracer or stack tracer. kprobes and perf allocate their ftrace_ops, and until there's a safe way to free the trampoline, it can not be used. The dynamically allocated ftrace_ops may, although, use the trampoline if the kernel is not compiled with CONFIG_PREEMPT. But that will come later. Tested-by: Masami Hiramatsu <masami.hiramatsu.pt@hitachi.com> Tested-by: Jiri Kosina <jkosina@suse.cz> Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
2014-07-03 11:23:31 +08:00
FTRACE_OPS_FL_ALLOC_TRAMP = 1 << 12,
FTRACE_OPS_FL_IPMODIFY = 1 << 13,
FTRACE_OPS_FL_PID = 1 << 14,
};
ftrace: Allow ftrace_ops to use the hashes from other ops Currently the top level debug file system function tracer shares its ftrace_ops with the function graph tracer. This was thought to be fine because the tracers are not used together, as one can only enable function or function_graph tracer in the current_tracer file. But that assumption proved to be incorrect. The function profiler can use the function graph tracer when function tracing is enabled. Since all function graph users uses the function tracing ftrace_ops this causes a conflict and when a user enables both function profiling as well as the function tracer it will crash ftrace and disable it. The quick solution so far is to move them as separate ftrace_ops like it was earlier. The problem though is to synchronize the functions that are traced because both function and function_graph tracer are limited by the selections made in the set_ftrace_filter and set_ftrace_notrace files. To handle this, a new structure is made called ftrace_ops_hash. This structure will now hold the filter_hash and notrace_hash, and the ftrace_ops will point to this structure. That will allow two ftrace_ops to share the same hashes. Since most ftrace_ops do not share the hashes, and to keep allocation simple, the ftrace_ops structure will include both a pointer to the ftrace_ops_hash called func_hash, as well as the structure itself, called local_hash. When the ops are registered, the func_hash pointer will be initialized to point to the local_hash within the ftrace_ops structure. Some of the ftrace internal ftrace_ops will be initialized statically. This will allow for the function and function_graph tracer to have separate ops but still share the same hash tables that determine what functions they trace. Cc: stable@vger.kernel.org # 3.16 (apply after 3.17-rc4 is out) Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
2014-08-16 05:23:02 +08:00
#ifdef CONFIG_DYNAMIC_FTRACE
/* The hash used to know what functions callbacks trace */
struct ftrace_ops_hash {
struct ftrace_hash *notrace_hash;
struct ftrace_hash *filter_hash;
struct mutex regex_lock;
};
#endif
/*
* Note, ftrace_ops can be referenced outside of RCU protection.
* (Although, for perf, the control ops prevent that). If ftrace_ops is
* allocated and not part of kernel core data, the unregistering of it will
* perform a scheduling on all CPUs to make sure that there are no more users.
* Depending on the load of the system that may take a bit of time.
*
* Any private data added must also take care not to be freed and if private
* data is added to a ftrace_ops that is in core code, the user of the
* ftrace_ops must perform a schedule_on_each_cpu() before freeing it.
*/
struct ftrace_ops {
ftrace_func_t func;
struct ftrace_ops *next;
unsigned long flags;
void *private;
ftrace_func_t saved_func;
ftrace: Optimize function graph to be called directly Function graph tracing is a bit different than the function tracers, as it is processed after either the ftrace_caller or ftrace_regs_caller and we only have one place to modify the jump to ftrace_graph_caller, the jump needs to happen after the restore of registeres. The function graph tracer is dependent on the function tracer, where even if the function graph tracing is going on by itself, the save and restore of registers is still done for function tracing regardless of if function tracing is happening, before it calls the function graph code. If there's no function tracing happening, it is possible to just call the function graph tracer directly, and avoid the wasted effort to save and restore regs for function tracing. This requires adding new flags to the dyn_ftrace records: FTRACE_FL_TRAMP FTRACE_FL_TRAMP_EN The first is set if the count for the record is one, and the ftrace_ops associated to that record has its own trampoline. That way the mcount code can call that trampoline directly. In the future, trampolines can be added to arbitrary ftrace_ops, where you can have two or more ftrace_ops registered to ftrace (like kprobes and perf) and if they are not tracing the same functions, then instead of doing a loop to check all registered ftrace_ops against their hashes, just call the ftrace_ops trampoline directly, which would call the registered ftrace_ops function directly. Without this patch perf showed: 0.05% hackbench [kernel.kallsyms] [k] ftrace_caller 0.05% hackbench [kernel.kallsyms] [k] arch_local_irq_save 0.05% hackbench [kernel.kallsyms] [k] native_sched_clock 0.04% hackbench [kernel.kallsyms] [k] __buffer_unlock_commit 0.04% hackbench [kernel.kallsyms] [k] preempt_trace 0.04% hackbench [kernel.kallsyms] [k] prepare_ftrace_return 0.04% hackbench [kernel.kallsyms] [k] __this_cpu_preempt_check 0.04% hackbench [kernel.kallsyms] [k] ftrace_graph_caller See that the ftrace_caller took up more time than the ftrace_graph_caller did. With this patch: 0.05% hackbench [kernel.kallsyms] [k] __buffer_unlock_commit 0.04% hackbench [kernel.kallsyms] [k] call_filter_check_discard 0.04% hackbench [kernel.kallsyms] [k] ftrace_graph_caller 0.04% hackbench [kernel.kallsyms] [k] sched_clock The ftrace_caller is no where to be found and ftrace_graph_caller still takes up the same percentage. Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
2014-05-07 09:56:17 +08:00
int __percpu *disabled;
#ifdef CONFIG_DYNAMIC_FTRACE
int nr_trampolines;
ftrace: Allow ftrace_ops to use the hashes from other ops Currently the top level debug file system function tracer shares its ftrace_ops with the function graph tracer. This was thought to be fine because the tracers are not used together, as one can only enable function or function_graph tracer in the current_tracer file. But that assumption proved to be incorrect. The function profiler can use the function graph tracer when function tracing is enabled. Since all function graph users uses the function tracing ftrace_ops this causes a conflict and when a user enables both function profiling as well as the function tracer it will crash ftrace and disable it. The quick solution so far is to move them as separate ftrace_ops like it was earlier. The problem though is to synchronize the functions that are traced because both function and function_graph tracer are limited by the selections made in the set_ftrace_filter and set_ftrace_notrace files. To handle this, a new structure is made called ftrace_ops_hash. This structure will now hold the filter_hash and notrace_hash, and the ftrace_ops will point to this structure. That will allow two ftrace_ops to share the same hashes. Since most ftrace_ops do not share the hashes, and to keep allocation simple, the ftrace_ops structure will include both a pointer to the ftrace_ops_hash called func_hash, as well as the structure itself, called local_hash. When the ops are registered, the func_hash pointer will be initialized to point to the local_hash within the ftrace_ops structure. Some of the ftrace internal ftrace_ops will be initialized statically. This will allow for the function and function_graph tracer to have separate ops but still share the same hash tables that determine what functions they trace. Cc: stable@vger.kernel.org # 3.16 (apply after 3.17-rc4 is out) Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
2014-08-16 05:23:02 +08:00
struct ftrace_ops_hash local_hash;
struct ftrace_ops_hash *func_hash;
ftrace: Replace tramp_hash with old_*_hash to save space Allowing function callbacks to declare their own trampolines requires that each ftrace_ops that has a trampoline must have some sort of accounting that keeps track of which ops has a trampoline attached to a record. The easy way to solve this was to add a "tramp_hash" that created a hash entry for every function that a ops uses with a trampoline. But since we can have literally tens of thousands of functions being traced, that means we need tens of thousands of descriptors to map the ops to the function in the hash. This is quite expensive and can cause enabling and disabling the function graph tracer to take some time to start and stop. It can take up to several seconds to disable or enable all functions in the function graph tracer for this reason. The better approach albeit more complex, is to keep track of how ops are being enabled and disabled, and use that along with the counting of the number of ops attached to records, to determive what ops has a trampoline attached to a record at enabling and disabling of tracing. To do this, the tramp_hash has been replaced with an old_filter_hash and old_notrace_hash, which get the copy of the ops filter_hash and notrace_hash respectively. The old hashes is kept until the ops has been modified or removed and the old hashes are used with the logic of the accounting to determine the ops that have the trampoline of a record. The reason this has less of a footprint is due to the trick that an "empty" hash in the filter_hash means "all functions" and an empty hash in the notrace hash means "no functions" in the hash. This is much more efficienct, doesn't have the delay, and takes up much less memory, as we do not need to map all the functions but just figure out which functions are mapped at the time it is enabled or disabled. Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
2014-07-25 00:25:47 +08:00
struct ftrace_ops_hash old_hash;
ftrace: Optimize function graph to be called directly Function graph tracing is a bit different than the function tracers, as it is processed after either the ftrace_caller or ftrace_regs_caller and we only have one place to modify the jump to ftrace_graph_caller, the jump needs to happen after the restore of registeres. The function graph tracer is dependent on the function tracer, where even if the function graph tracing is going on by itself, the save and restore of registers is still done for function tracing regardless of if function tracing is happening, before it calls the function graph code. If there's no function tracing happening, it is possible to just call the function graph tracer directly, and avoid the wasted effort to save and restore regs for function tracing. This requires adding new flags to the dyn_ftrace records: FTRACE_FL_TRAMP FTRACE_FL_TRAMP_EN The first is set if the count for the record is one, and the ftrace_ops associated to that record has its own trampoline. That way the mcount code can call that trampoline directly. In the future, trampolines can be added to arbitrary ftrace_ops, where you can have two or more ftrace_ops registered to ftrace (like kprobes and perf) and if they are not tracing the same functions, then instead of doing a loop to check all registered ftrace_ops against their hashes, just call the ftrace_ops trampoline directly, which would call the registered ftrace_ops function directly. Without this patch perf showed: 0.05% hackbench [kernel.kallsyms] [k] ftrace_caller 0.05% hackbench [kernel.kallsyms] [k] arch_local_irq_save 0.05% hackbench [kernel.kallsyms] [k] native_sched_clock 0.04% hackbench [kernel.kallsyms] [k] __buffer_unlock_commit 0.04% hackbench [kernel.kallsyms] [k] preempt_trace 0.04% hackbench [kernel.kallsyms] [k] prepare_ftrace_return 0.04% hackbench [kernel.kallsyms] [k] __this_cpu_preempt_check 0.04% hackbench [kernel.kallsyms] [k] ftrace_graph_caller See that the ftrace_caller took up more time than the ftrace_graph_caller did. With this patch: 0.05% hackbench [kernel.kallsyms] [k] __buffer_unlock_commit 0.04% hackbench [kernel.kallsyms] [k] call_filter_check_discard 0.04% hackbench [kernel.kallsyms] [k] ftrace_graph_caller 0.04% hackbench [kernel.kallsyms] [k] sched_clock The ftrace_caller is no where to be found and ftrace_graph_caller still takes up the same percentage. Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
2014-05-07 09:56:17 +08:00
unsigned long trampoline;
unsigned long trampoline_size;
#endif
};
tracing/function-return-tracer: support for dynamic ftrace on function return tracer This patch adds the support for dynamic tracing on the function return tracer. The whole difference with normal dynamic function tracing is that we don't need to hook on a particular callback. The only pro that we want is to nop or set dynamically the calls to ftrace_caller (which is ftrace_return_caller here). Some security checks ensure that we are not trying to launch dynamic tracing for return tracing while normal function tracing is already running. An example of trace with getnstimeofday set as a filter: ktime_get_ts+0x22/0x50 -> getnstimeofday (2283 ns) ktime_get_ts+0x22/0x50 -> getnstimeofday (1396 ns) ktime_get_ts+0x22/0x50 -> getnstimeofday (1382 ns) ktime_get_ts+0x22/0x50 -> getnstimeofday (1825 ns) ktime_get_ts+0x22/0x50 -> getnstimeofday (1426 ns) ktime_get_ts+0x22/0x50 -> getnstimeofday (1464 ns) ktime_get_ts+0x22/0x50 -> getnstimeofday (1524 ns) ktime_get_ts+0x22/0x50 -> getnstimeofday (1382 ns) ktime_get_ts+0x22/0x50 -> getnstimeofday (1382 ns) ktime_get_ts+0x22/0x50 -> getnstimeofday (1434 ns) ktime_get_ts+0x22/0x50 -> getnstimeofday (1464 ns) ktime_get_ts+0x22/0x50 -> getnstimeofday (1502 ns) ktime_get_ts+0x22/0x50 -> getnstimeofday (1404 ns) ktime_get_ts+0x22/0x50 -> getnstimeofday (1397 ns) ktime_get_ts+0x22/0x50 -> getnstimeofday (1051 ns) ktime_get_ts+0x22/0x50 -> getnstimeofday (1314 ns) ktime_get_ts+0x22/0x50 -> getnstimeofday (1344 ns) ktime_get_ts+0x22/0x50 -> getnstimeofday (1163 ns) ktime_get_ts+0x22/0x50 -> getnstimeofday (1390 ns) ktime_get_ts+0x22/0x50 -> getnstimeofday (1374 ns) Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2008-11-16 13:02:06 +08:00
/*
* Type of the current tracing.
*/
enum ftrace_tracing_type_t {
FTRACE_TYPE_ENTER = 0, /* Hook the call of the function */
FTRACE_TYPE_RETURN, /* Hook the return of the function */
};
/* Current tracing type, default is FTRACE_TYPE_ENTER */
extern enum ftrace_tracing_type_t ftrace_tracing_type;
/*
* The ftrace_ops must be a static and should also
* be read_mostly. These functions do modify read_mostly variables
* so use them sparely. Never free an ftrace_op or modify the
* next pointer after it has been registered. Even after unregistering
* it, the next pointer may still be used internally.
*/
int register_ftrace_function(struct ftrace_ops *ops);
int unregister_ftrace_function(struct ftrace_ops *ops);
void clear_ftrace_function(void);
/**
* ftrace_function_local_enable - enable controlled ftrace_ops on current cpu
*
* This function enables tracing on current cpu by decreasing
* the per cpu control variable.
* It must be called with preemption disabled and only on ftrace_ops
* registered with FTRACE_OPS_FL_CONTROL. If called without preemption
* disabled, this_cpu_ptr will complain when CONFIG_DEBUG_PREEMPT is enabled.
*/
static inline void ftrace_function_local_enable(struct ftrace_ops *ops)
{
if (WARN_ON_ONCE(!(ops->flags & FTRACE_OPS_FL_CONTROL)))
return;
(*this_cpu_ptr(ops->disabled))--;
}
/**
* ftrace_function_local_disable - enable controlled ftrace_ops on current cpu
*
* This function enables tracing on current cpu by decreasing
* the per cpu control variable.
* It must be called with preemption disabled and only on ftrace_ops
* registered with FTRACE_OPS_FL_CONTROL. If called without preemption
* disabled, this_cpu_ptr will complain when CONFIG_DEBUG_PREEMPT is enabled.
*/
static inline void ftrace_function_local_disable(struct ftrace_ops *ops)
{
if (WARN_ON_ONCE(!(ops->flags & FTRACE_OPS_FL_CONTROL)))
return;
(*this_cpu_ptr(ops->disabled))++;
}
/**
* ftrace_function_local_disabled - returns ftrace_ops disabled value
* on current cpu
*
* This function returns value of ftrace_ops::disabled on current cpu.
* It must be called with preemption disabled and only on ftrace_ops
* registered with FTRACE_OPS_FL_CONTROL. If called without preemption
* disabled, this_cpu_ptr will complain when CONFIG_DEBUG_PREEMPT is enabled.
*/
static inline int ftrace_function_local_disabled(struct ftrace_ops *ops)
{
WARN_ON_ONCE(!(ops->flags & FTRACE_OPS_FL_CONTROL));
return *this_cpu_ptr(ops->disabled);
}
extern void ftrace_stub(unsigned long a0, unsigned long a1,
struct ftrace_ops *op, struct pt_regs *regs);
#else /* !CONFIG_FUNCTION_TRACER */
/*
* (un)register_ftrace_function must be a macro since the ops parameter
* must not be evaluated.
*/
#define register_ftrace_function(ops) ({ 0; })
#define unregister_ftrace_function(ops) ({ 0; })
static inline int ftrace_nr_registered_ops(void)
{
return 0;
}
static inline void clear_ftrace_function(void) { }
static inline void ftrace_kill(void) { }
#endif /* CONFIG_FUNCTION_TRACER */
ftrace: tracer for scheduler wakeup latency This patch adds the tracer that tracks the wakeup latency of the highest priority waking task. "wakeup" is added to /debugfs/tracing/available_tracers Also added to /debugfs/tracing tracing_max_latency holds the current max latency for the wakeup wakeup_thresh if set to other than zero, a log will be recorded for every wakeup that takes longer than the number entered in here (usecs for all counters) (deletes previous trace) Examples: (with ftrace_enabled = 0) ============ preemption latency trace v1.1.5 on 2.6.24-rc8 Signed-off-by: Ingo Molnar <mingo@elte.hu> -------------------------------------------------------------------- latency: 26 us, #2/2, CPU#1 | (M:rt VP:0, KP:0, SP:0 HP:0 #P:2) ----------------- | task: migration/0-3 (uid:0 nice:-5 policy:1 rt_prio:99) ----------------- _------=> CPU# / _-----=> irqs-off | / _----=> need-resched || / _---=> hardirq/softirq ||| / _--=> preempt-depth |||| / ||||| delay cmd pid ||||| time | caller \ / ||||| \ | / quilt-8551 0d..3 0us+: wake_up_process+0x15/0x17 <ffffffff80233e80> (sched_exec+0xc9/0x100 <ffffffff80235343>) quilt-8551 0d..4 26us : sched_switch_callback+0x73/0x81 <ffffffff80338d2f> (schedule+0x483/0x6d5 <ffffffff8048b3ee>) vim:ft=help ============ (with ftrace_enabled = 1) ============ preemption latency trace v1.1.5 on 2.6.24-rc8 -------------------------------------------------------------------- latency: 36 us, #45/45, CPU#0 | (M:rt VP:0, KP:0, SP:0 HP:0 #P:2) ----------------- | task: migration/1-5 (uid:0 nice:-5 policy:1 rt_prio:99) ----------------- _------=> CPU# / _-----=> irqs-off | / _----=> need-resched || / _---=> hardirq/softirq ||| / _--=> preempt-depth |||| / ||||| delay cmd pid ||||| time | caller \ / ||||| \ | / bash-10653 1d..3 0us : wake_up_process+0x15/0x17 <ffffffff80233e80> (sched_exec+0xc9/0x100 <ffffffff80235343>) bash-10653 1d..3 1us : try_to_wake_up+0x271/0x2e7 <ffffffff80233dcf> (sub_preempt_count+0xc/0x7a <ffffffff8023309e>) bash-10653 1d..2 2us : try_to_wake_up+0x296/0x2e7 <ffffffff80233df4> (update_rq_clock+0x9/0x20 <ffffffff802303f3>) bash-10653 1d..2 2us : update_rq_clock+0x1e/0x20 <ffffffff80230408> (__update_rq_clock+0xc/0x90 <ffffffff80230366>) bash-10653 1d..2 3us : __update_rq_clock+0x1b/0x90 <ffffffff80230375> (sched_clock+0x9/0x29 <ffffffff80214529>) bash-10653 1d..2 4us : try_to_wake_up+0x2a6/0x2e7 <ffffffff80233e04> (activate_task+0xc/0x3f <ffffffff8022ffca>) bash-10653 1d..2 4us : activate_task+0x2d/0x3f <ffffffff8022ffeb> (enqueue_task+0xe/0x66 <ffffffff8022ff66>) bash-10653 1d..2 5us : enqueue_task+0x5b/0x66 <ffffffff8022ffb3> (enqueue_task_rt+0x9/0x3c <ffffffff80233351>) bash-10653 1d..2 6us : try_to_wake_up+0x2ba/0x2e7 <ffffffff80233e18> (check_preempt_wakeup+0x12/0x99 <ffffffff80234f84>) [...] bash-10653 1d..5 33us : tracing_record_cmdline+0xcf/0xd4 <ffffffff80338aad> (_spin_unlock+0x9/0x33 <ffffffff8048d3ec>) bash-10653 1d..5 34us : _spin_unlock+0x19/0x33 <ffffffff8048d3fc> (sub_preempt_count+0xc/0x7a <ffffffff8023309e>) bash-10653 1d..4 35us : wakeup_sched_switch+0x65/0x2ff <ffffffff80339f66> (_spin_lock_irqsave+0xc/0xa9 <ffffffff8048d08b>) bash-10653 1d..4 35us : _spin_lock_irqsave+0x19/0xa9 <ffffffff8048d098> (add_preempt_count+0xe/0x77 <ffffffff8023311a>) bash-10653 1d..4 36us : sched_switch_callback+0x73/0x81 <ffffffff80338d2f> (schedule+0x483/0x6d5 <ffffffff8048b3ee>) vim:ft=help ============ The [...] was added here to not waste your email box space. Signed-off-by: Steven Rostedt <srostedt@redhat.com> Signed-off-by: Ingo Molnar <mingo@elte.hu> Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
2008-05-13 03:20:42 +08:00
#ifdef CONFIG_STACK_TRACER
extern int stack_tracer_enabled;
int
stack_trace_sysctl(struct ctl_table *table, int write,
void __user *buffer, size_t *lenp,
loff_t *ppos);
#endif
struct ftrace_func_command {
struct list_head list;
char *name;
ftrace: Fix regression of :mod:module function enabling The new code that allows different utilities to pick and choose what functions they trace broke the :mod: hook that allows users to trace only functions of a particular module. The reason is that the :mod: hook bypasses the hash that is setup to allow individual users to trace their own functions and uses the global hash directly. But if the global hash has not been set up, it will cause a bug: echo '*:mod:radeon' > /sys/kernel/debug/set_ftrace_filter produces: [drm:drm_mode_getfb] *ERROR* invalid framebuffer id [drm:radeon_crtc_page_flip] *ERROR* failed to reserve new rbo buffer before flip BUG: unable to handle kernel paging request at ffffffff8160ec90 IP: [<ffffffff810d9136>] add_hash_entry+0x66/0xd0 PGD 1a05067 PUD 1a09063 PMD 80000000016001e1 Oops: 0003 [#1] SMP Jul 7 04:02:28 phyllis kernel: [55303.858604] CPU 1 Modules linked in: cryptd aes_x86_64 aes_generic binfmt_misc rfcomm bnep ip6table_filter hid radeon r8169 ahci libahci mii ttm drm_kms_helper drm video i2c_algo_bit intel_agp intel_gtt Pid: 10344, comm: bash Tainted: G WC 3.0.0-rc5 #1 Dell Inc. Inspiron N5010/0YXXJJ RIP: 0010:[<ffffffff810d9136>] [<ffffffff810d9136>] add_hash_entry+0x66/0xd0 RSP: 0018:ffff88003a96bda8 EFLAGS: 00010246 RAX: ffff8801301735c0 RBX: ffffffff8160ec80 RCX: 0000000000306ee0 RDX: 0000000000000000 RSI: 0000000000000000 RDI: ffff880137c92940 RBP: ffff88003a96bdb8 R08: ffff880137c95680 R09: 0000000000000000 R10: 0000000000000001 R11: 0000000000000000 R12: ffffffff81c9df78 R13: ffff8801153d1000 R14: 0000000000000000 R15: 0000000000000000 FS: 00007f329c18a700(0000) GS:ffff880137c80000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: ffffffff8160ec90 CR3: 000000003002b000 CR4: 00000000000006e0 DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 DR3: 0000000000000000 DR6: 00000000ffff0ff0 DR7: 0000000000000400 Process bash (pid: 10344, threadinfo ffff88003a96a000, task ffff88012fcfc470) Stack: 0000000000000fd0 00000000000000fc ffff88003a96be38 ffffffff810d92f5 ffff88011c4c4e00 ffff880000000000 000000000b69f4d0 ffffffff8160ec80 ffff8800300e6f06 0000000081130295 0000000000000282 ffff8800300e6f00 Call Trace: [<ffffffff810d92f5>] match_records+0x155/0x1b0 [<ffffffff810d940c>] ftrace_mod_callback+0xbc/0x100 [<ffffffff810dafdf>] ftrace_regex_write+0x16f/0x210 [<ffffffff810db09f>] ftrace_filter_write+0xf/0x20 [<ffffffff81166e48>] vfs_write+0xc8/0x190 [<ffffffff81167001>] sys_write+0x51/0x90 [<ffffffff815c7e02>] system_call_fastpath+0x16/0x1b Code: 48 8b 33 31 d2 48 85 f6 75 33 49 89 d4 4c 03 63 08 49 8b 14 24 48 85 d2 48 89 10 74 04 48 89 42 08 49 89 04 24 4c 89 60 08 31 d2 RIP [<ffffffff810d9136>] add_hash_entry+0x66/0xd0 RSP <ffff88003a96bda8> CR2: ffffffff8160ec90 ---[ end trace a5d031828efdd88e ]--- Reported-by: Brian Marete <marete@toshnix.com> Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
2011-07-07 23:09:22 +08:00
int (*func)(struct ftrace_hash *hash,
char *func, char *cmd,
char *params, int enable);
};
ftrace: dynamic enabling/disabling of function calls This patch adds a feature to dynamically replace the ftrace code with the jmps to allow a kernel with ftrace configured to run as fast as it can without it configured. The way this works, is on bootup (if ftrace is enabled), a ftrace function is registered to record the instruction pointer of all places that call the function. Later, if there's still any code to patch, a kthread is awoken (rate limited to at most once a second) that performs a stop_machine, and replaces all the code that was called with a jmp over the call to ftrace. It only replaces what was found the previous time. Typically the system reaches equilibrium quickly after bootup and there's no code patching needed at all. e.g. call ftrace /* 5 bytes */ is replaced with jmp 3f /* jmp is 2 bytes and we jump 3 forward */ 3: When we want to enable ftrace for function tracing, the IP recording is removed, and stop_machine is called again to replace all the locations of that were recorded back to the call of ftrace. When it is disabled, we replace the code back to the jmp. Allocation is done by the kthread. If the ftrace recording function is called, and we don't have any record slots available, then we simply skip that call. Once a second a new page (if needed) is allocated for recording new ftrace function calls. A large batch is allocated at boot up to get most of the calls there. Because we do this via stop_machine, we don't have to worry about another CPU executing a ftrace call as we modify it. But we do need to worry about NMI's so all functions that might be called via nmi must be annotated with notrace_nmi. When this code is configured in, the NMI code will not call notrace. Signed-off-by: Steven Rostedt <srostedt@redhat.com> Signed-off-by: Ingo Molnar <mingo@elte.hu> Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
2008-05-13 03:20:42 +08:00
#ifdef CONFIG_DYNAMIC_FTRACE
ftrace: pass module struct to arch dynamic ftrace functions Impact: allow archs more flexibility on dynamic ftrace implementations Dynamic ftrace has largly been developed on x86. Since x86 does not have the same limitations as other architectures, the ftrace interaction between the generic code and the architecture specific code was not flexible enough to handle some of the issues that other architectures have. Most notably, module trampolines. Due to the limited branch distance that archs make in calling kernel core code from modules, the module load code must create a trampoline to jump to what will make the larger jump into core kernel code. The problem arises when this happens to a call to mcount. Ftrace checks all code before modifying it and makes sure the current code is what it expects. Right now, there is not enough information to handle modifying module trampolines. This patch changes the API between generic dynamic ftrace code and the arch dependent code. There is now two functions for modifying code: ftrace_make_nop(mod, rec, addr) - convert the code at rec->ip into a nop, where the original text is calling addr. (mod is the module struct if called by module init) ftrace_make_caller(rec, addr) - convert the code rec->ip that should be a nop into a caller to addr. The record "rec" now has a new field called "arch" where the architecture can add any special attributes to each call site record. Signed-off-by: Steven Rostedt <srostedt@redhat.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2008-11-15 08:21:19 +08:00
int ftrace_arch_code_modify_prepare(void);
int ftrace_arch_code_modify_post_process(void);
struct dyn_ftrace;
void ftrace_bug(int err, struct dyn_ftrace *rec);
struct seq_file;
struct ftrace_probe_ops {
ftrace: trace different functions with a different tracer Impact: new feature Currently, the function tracer only gives you an ability to hook a tracer to all functions being traced. The dynamic function trace allows you to pick and choose which of those functions will be traced, but all functions being traced will call all tracers that registered with the function tracer. This patch adds a new feature that allows a tracer to hook to specific functions, even when all functions are being traced. It allows for different functions to call different tracer hooks. The way this is accomplished is by a special function that will hook to the function tracer and will set up a hash table knowing which tracer hook to call with which function. This is the most general and easiest method to accomplish this. Later, an arch may choose to supply their own method in changing the mcount call of a function to call a different tracer. But that will be an exercise for the future. To register a function: struct ftrace_hook_ops { void (*func)(unsigned long ip, unsigned long parent_ip, void **data); int (*callback)(unsigned long ip, void **data); void (*free)(void **data); }; int register_ftrace_function_hook(char *glob, struct ftrace_hook_ops *ops, void *data); glob is a simple glob to search for the functions to hook. ops is a pointer to the operations (listed below) data is the default data to be passed to the hook functions when traced ops: func is the hook function to call when the functions are traced callback is a callback function that is called when setting up the hash. That is, if the tracer needs to do something special for each function, that is being traced, and wants to give each function its own data. The address of the entry data is passed to this callback, so that the callback may wish to update the entry to whatever it would like. free is a callback for when the entry is freed. In case the tracer allocated any data, it is give the chance to free it. To unregister we have three functions: void unregister_ftrace_function_hook(char *glob, struct ftrace_hook_ops *ops, void *data) This will unregister all hooks that match glob, point to ops, and have its data matching data. (note, if glob is NULL, blank or '*', all functions will be tested). void unregister_ftrace_function_hook_func(char *glob, struct ftrace_hook_ops *ops) This will unregister all functions matching glob that has an entry pointing to ops. void unregister_ftrace_function_hook_all(char *glob) This simply unregisters all funcs. Signed-off-by: Steven Rostedt <srostedt@redhat.com>
2009-02-15 04:29:06 +08:00
void (*func)(unsigned long ip,
unsigned long parent_ip,
void **data);
int (*init)(struct ftrace_probe_ops *ops,
unsigned long ip, void **data);
void (*free)(struct ftrace_probe_ops *ops,
unsigned long ip, void **data);
int (*print)(struct seq_file *m,
unsigned long ip,
struct ftrace_probe_ops *ops,
void *data);
ftrace: trace different functions with a different tracer Impact: new feature Currently, the function tracer only gives you an ability to hook a tracer to all functions being traced. The dynamic function trace allows you to pick and choose which of those functions will be traced, but all functions being traced will call all tracers that registered with the function tracer. This patch adds a new feature that allows a tracer to hook to specific functions, even when all functions are being traced. It allows for different functions to call different tracer hooks. The way this is accomplished is by a special function that will hook to the function tracer and will set up a hash table knowing which tracer hook to call with which function. This is the most general and easiest method to accomplish this. Later, an arch may choose to supply their own method in changing the mcount call of a function to call a different tracer. But that will be an exercise for the future. To register a function: struct ftrace_hook_ops { void (*func)(unsigned long ip, unsigned long parent_ip, void **data); int (*callback)(unsigned long ip, void **data); void (*free)(void **data); }; int register_ftrace_function_hook(char *glob, struct ftrace_hook_ops *ops, void *data); glob is a simple glob to search for the functions to hook. ops is a pointer to the operations (listed below) data is the default data to be passed to the hook functions when traced ops: func is the hook function to call when the functions are traced callback is a callback function that is called when setting up the hash. That is, if the tracer needs to do something special for each function, that is being traced, and wants to give each function its own data. The address of the entry data is passed to this callback, so that the callback may wish to update the entry to whatever it would like. free is a callback for when the entry is freed. In case the tracer allocated any data, it is give the chance to free it. To unregister we have three functions: void unregister_ftrace_function_hook(char *glob, struct ftrace_hook_ops *ops, void *data) This will unregister all hooks that match glob, point to ops, and have its data matching data. (note, if glob is NULL, blank or '*', all functions will be tested). void unregister_ftrace_function_hook_func(char *glob, struct ftrace_hook_ops *ops) This will unregister all functions matching glob that has an entry pointing to ops. void unregister_ftrace_function_hook_all(char *glob) This simply unregisters all funcs. Signed-off-by: Steven Rostedt <srostedt@redhat.com>
2009-02-15 04:29:06 +08:00
};
extern int
register_ftrace_function_probe(char *glob, struct ftrace_probe_ops *ops,
ftrace: trace different functions with a different tracer Impact: new feature Currently, the function tracer only gives you an ability to hook a tracer to all functions being traced. The dynamic function trace allows you to pick and choose which of those functions will be traced, but all functions being traced will call all tracers that registered with the function tracer. This patch adds a new feature that allows a tracer to hook to specific functions, even when all functions are being traced. It allows for different functions to call different tracer hooks. The way this is accomplished is by a special function that will hook to the function tracer and will set up a hash table knowing which tracer hook to call with which function. This is the most general and easiest method to accomplish this. Later, an arch may choose to supply their own method in changing the mcount call of a function to call a different tracer. But that will be an exercise for the future. To register a function: struct ftrace_hook_ops { void (*func)(unsigned long ip, unsigned long parent_ip, void **data); int (*callback)(unsigned long ip, void **data); void (*free)(void **data); }; int register_ftrace_function_hook(char *glob, struct ftrace_hook_ops *ops, void *data); glob is a simple glob to search for the functions to hook. ops is a pointer to the operations (listed below) data is the default data to be passed to the hook functions when traced ops: func is the hook function to call when the functions are traced callback is a callback function that is called when setting up the hash. That is, if the tracer needs to do something special for each function, that is being traced, and wants to give each function its own data. The address of the entry data is passed to this callback, so that the callback may wish to update the entry to whatever it would like. free is a callback for when the entry is freed. In case the tracer allocated any data, it is give the chance to free it. To unregister we have three functions: void unregister_ftrace_function_hook(char *glob, struct ftrace_hook_ops *ops, void *data) This will unregister all hooks that match glob, point to ops, and have its data matching data. (note, if glob is NULL, blank or '*', all functions will be tested). void unregister_ftrace_function_hook_func(char *glob, struct ftrace_hook_ops *ops) This will unregister all functions matching glob that has an entry pointing to ops. void unregister_ftrace_function_hook_all(char *glob) This simply unregisters all funcs. Signed-off-by: Steven Rostedt <srostedt@redhat.com>
2009-02-15 04:29:06 +08:00
void *data);
extern void
unregister_ftrace_function_probe(char *glob, struct ftrace_probe_ops *ops,
ftrace: trace different functions with a different tracer Impact: new feature Currently, the function tracer only gives you an ability to hook a tracer to all functions being traced. The dynamic function trace allows you to pick and choose which of those functions will be traced, but all functions being traced will call all tracers that registered with the function tracer. This patch adds a new feature that allows a tracer to hook to specific functions, even when all functions are being traced. It allows for different functions to call different tracer hooks. The way this is accomplished is by a special function that will hook to the function tracer and will set up a hash table knowing which tracer hook to call with which function. This is the most general and easiest method to accomplish this. Later, an arch may choose to supply their own method in changing the mcount call of a function to call a different tracer. But that will be an exercise for the future. To register a function: struct ftrace_hook_ops { void (*func)(unsigned long ip, unsigned long parent_ip, void **data); int (*callback)(unsigned long ip, void **data); void (*free)(void **data); }; int register_ftrace_function_hook(char *glob, struct ftrace_hook_ops *ops, void *data); glob is a simple glob to search for the functions to hook. ops is a pointer to the operations (listed below) data is the default data to be passed to the hook functions when traced ops: func is the hook function to call when the functions are traced callback is a callback function that is called when setting up the hash. That is, if the tracer needs to do something special for each function, that is being traced, and wants to give each function its own data. The address of the entry data is passed to this callback, so that the callback may wish to update the entry to whatever it would like. free is a callback for when the entry is freed. In case the tracer allocated any data, it is give the chance to free it. To unregister we have three functions: void unregister_ftrace_function_hook(char *glob, struct ftrace_hook_ops *ops, void *data) This will unregister all hooks that match glob, point to ops, and have its data matching data. (note, if glob is NULL, blank or '*', all functions will be tested). void unregister_ftrace_function_hook_func(char *glob, struct ftrace_hook_ops *ops) This will unregister all functions matching glob that has an entry pointing to ops. void unregister_ftrace_function_hook_all(char *glob) This simply unregisters all funcs. Signed-off-by: Steven Rostedt <srostedt@redhat.com>
2009-02-15 04:29:06 +08:00
void *data);
extern void
unregister_ftrace_function_probe_func(char *glob, struct ftrace_probe_ops *ops);
extern void unregister_ftrace_function_probe_all(char *glob);
ftrace: trace different functions with a different tracer Impact: new feature Currently, the function tracer only gives you an ability to hook a tracer to all functions being traced. The dynamic function trace allows you to pick and choose which of those functions will be traced, but all functions being traced will call all tracers that registered with the function tracer. This patch adds a new feature that allows a tracer to hook to specific functions, even when all functions are being traced. It allows for different functions to call different tracer hooks. The way this is accomplished is by a special function that will hook to the function tracer and will set up a hash table knowing which tracer hook to call with which function. This is the most general and easiest method to accomplish this. Later, an arch may choose to supply their own method in changing the mcount call of a function to call a different tracer. But that will be an exercise for the future. To register a function: struct ftrace_hook_ops { void (*func)(unsigned long ip, unsigned long parent_ip, void **data); int (*callback)(unsigned long ip, void **data); void (*free)(void **data); }; int register_ftrace_function_hook(char *glob, struct ftrace_hook_ops *ops, void *data); glob is a simple glob to search for the functions to hook. ops is a pointer to the operations (listed below) data is the default data to be passed to the hook functions when traced ops: func is the hook function to call when the functions are traced callback is a callback function that is called when setting up the hash. That is, if the tracer needs to do something special for each function, that is being traced, and wants to give each function its own data. The address of the entry data is passed to this callback, so that the callback may wish to update the entry to whatever it would like. free is a callback for when the entry is freed. In case the tracer allocated any data, it is give the chance to free it. To unregister we have three functions: void unregister_ftrace_function_hook(char *glob, struct ftrace_hook_ops *ops, void *data) This will unregister all hooks that match glob, point to ops, and have its data matching data. (note, if glob is NULL, blank or '*', all functions will be tested). void unregister_ftrace_function_hook_func(char *glob, struct ftrace_hook_ops *ops) This will unregister all functions matching glob that has an entry pointing to ops. void unregister_ftrace_function_hook_all(char *glob) This simply unregisters all funcs. Signed-off-by: Steven Rostedt <srostedt@redhat.com>
2009-02-15 04:29:06 +08:00
extern int ftrace_text_reserved(const void *start, const void *end);
extern int ftrace_nr_registered_ops(void);
bool is_ftrace_trampoline(unsigned long addr);
ftrace/x86: Add separate function to save regs Add a way to have different functions calling different trampolines. If a ftrace_ops wants regs saved on the return, then have only the functions with ops registered to save regs. Functions registered by other ops would not be affected, unless the functions overlap. If one ftrace_ops registered functions A, B and C and another ops registered fucntions to save regs on A, and D, then only functions A and D would be saving regs. Function B and C would work as normal. Although A is registered by both ops: normal and saves regs; this is fine as saving the regs is needed to satisfy one of the ops that calls it but the regs are ignored by the other ops function. x86_64 implements the full regs saving, and i386 just passes a NULL for regs to satisfy the ftrace_ops passing. Where an arch must supply both regs and ftrace_ops parameters, even if regs is just NULL. It is OK for an arch to pass NULL regs. All function trace users that require regs passing must add the flag FTRACE_OPS_FL_SAVE_REGS when registering the ftrace_ops. If the arch does not support saving regs then the ftrace_ops will fail to register. The flag FTRACE_OPS_FL_SAVE_REGS_IF_SUPPORTED may be set that will prevent the ftrace_ops from failing to register. In this case, the handler may either check if regs is not NULL or check if ARCH_SUPPORTS_FTRACE_SAVE_REGS. If the arch supports passing regs it will set this macro and pass regs for ops that request them. All other archs will just pass NULL. Link: Link: http://lkml.kernel.org/r/20120711195745.107705970@goodmis.org Cc: Alexander van Heukelum <heukelum@fastmail.fm> Reviewed-by: Masami Hiramatsu <masami.hiramatsu.pt@hitachi.com> Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
2012-05-01 04:20:23 +08:00
/*
* The dyn_ftrace record's flags field is split into two parts.
* the first part which is '0-FTRACE_REF_MAX' is a counter of
* the number of callbacks that have registered the function that
* the dyn_ftrace descriptor represents.
*
* The second part is a mask:
* ENABLED - the function is being traced
* REGS - the record wants the function to save regs
* REGS_EN - the function is set up to save regs.
* IPMODIFY - the record allows for the IP address to be changed.
ftrace/x86: Add separate function to save regs Add a way to have different functions calling different trampolines. If a ftrace_ops wants regs saved on the return, then have only the functions with ops registered to save regs. Functions registered by other ops would not be affected, unless the functions overlap. If one ftrace_ops registered functions A, B and C and another ops registered fucntions to save regs on A, and D, then only functions A and D would be saving regs. Function B and C would work as normal. Although A is registered by both ops: normal and saves regs; this is fine as saving the regs is needed to satisfy one of the ops that calls it but the regs are ignored by the other ops function. x86_64 implements the full regs saving, and i386 just passes a NULL for regs to satisfy the ftrace_ops passing. Where an arch must supply both regs and ftrace_ops parameters, even if regs is just NULL. It is OK for an arch to pass NULL regs. All function trace users that require regs passing must add the flag FTRACE_OPS_FL_SAVE_REGS when registering the ftrace_ops. If the arch does not support saving regs then the ftrace_ops will fail to register. The flag FTRACE_OPS_FL_SAVE_REGS_IF_SUPPORTED may be set that will prevent the ftrace_ops from failing to register. In this case, the handler may either check if regs is not NULL or check if ARCH_SUPPORTS_FTRACE_SAVE_REGS. If the arch supports passing regs it will set this macro and pass regs for ops that request them. All other archs will just pass NULL. Link: Link: http://lkml.kernel.org/r/20120711195745.107705970@goodmis.org Cc: Alexander van Heukelum <heukelum@fastmail.fm> Reviewed-by: Masami Hiramatsu <masami.hiramatsu.pt@hitachi.com> Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
2012-05-01 04:20:23 +08:00
*
* When a new ftrace_ops is registered and wants a function to save
* pt_regs, the rec->flag REGS is set. When the function has been
* set up to save regs, the REG_EN flag is set. Once a function
* starts saving regs it will do so until all ftrace_ops are removed
* from tracing that function.
*/
enum {
ftrace: Optimize function graph to be called directly Function graph tracing is a bit different than the function tracers, as it is processed after either the ftrace_caller or ftrace_regs_caller and we only have one place to modify the jump to ftrace_graph_caller, the jump needs to happen after the restore of registeres. The function graph tracer is dependent on the function tracer, where even if the function graph tracing is going on by itself, the save and restore of registers is still done for function tracing regardless of if function tracing is happening, before it calls the function graph code. If there's no function tracing happening, it is possible to just call the function graph tracer directly, and avoid the wasted effort to save and restore regs for function tracing. This requires adding new flags to the dyn_ftrace records: FTRACE_FL_TRAMP FTRACE_FL_TRAMP_EN The first is set if the count for the record is one, and the ftrace_ops associated to that record has its own trampoline. That way the mcount code can call that trampoline directly. In the future, trampolines can be added to arbitrary ftrace_ops, where you can have two or more ftrace_ops registered to ftrace (like kprobes and perf) and if they are not tracing the same functions, then instead of doing a loop to check all registered ftrace_ops against their hashes, just call the ftrace_ops trampoline directly, which would call the registered ftrace_ops function directly. Without this patch perf showed: 0.05% hackbench [kernel.kallsyms] [k] ftrace_caller 0.05% hackbench [kernel.kallsyms] [k] arch_local_irq_save 0.05% hackbench [kernel.kallsyms] [k] native_sched_clock 0.04% hackbench [kernel.kallsyms] [k] __buffer_unlock_commit 0.04% hackbench [kernel.kallsyms] [k] preempt_trace 0.04% hackbench [kernel.kallsyms] [k] prepare_ftrace_return 0.04% hackbench [kernel.kallsyms] [k] __this_cpu_preempt_check 0.04% hackbench [kernel.kallsyms] [k] ftrace_graph_caller See that the ftrace_caller took up more time than the ftrace_graph_caller did. With this patch: 0.05% hackbench [kernel.kallsyms] [k] __buffer_unlock_commit 0.04% hackbench [kernel.kallsyms] [k] call_filter_check_discard 0.04% hackbench [kernel.kallsyms] [k] ftrace_graph_caller 0.04% hackbench [kernel.kallsyms] [k] sched_clock The ftrace_caller is no where to be found and ftrace_graph_caller still takes up the same percentage. Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
2014-05-07 09:56:17 +08:00
FTRACE_FL_ENABLED = (1UL << 31),
ftrace/x86: Add separate function to save regs Add a way to have different functions calling different trampolines. If a ftrace_ops wants regs saved on the return, then have only the functions with ops registered to save regs. Functions registered by other ops would not be affected, unless the functions overlap. If one ftrace_ops registered functions A, B and C and another ops registered fucntions to save regs on A, and D, then only functions A and D would be saving regs. Function B and C would work as normal. Although A is registered by both ops: normal and saves regs; this is fine as saving the regs is needed to satisfy one of the ops that calls it but the regs are ignored by the other ops function. x86_64 implements the full regs saving, and i386 just passes a NULL for regs to satisfy the ftrace_ops passing. Where an arch must supply both regs and ftrace_ops parameters, even if regs is just NULL. It is OK for an arch to pass NULL regs. All function trace users that require regs passing must add the flag FTRACE_OPS_FL_SAVE_REGS when registering the ftrace_ops. If the arch does not support saving regs then the ftrace_ops will fail to register. The flag FTRACE_OPS_FL_SAVE_REGS_IF_SUPPORTED may be set that will prevent the ftrace_ops from failing to register. In this case, the handler may either check if regs is not NULL or check if ARCH_SUPPORTS_FTRACE_SAVE_REGS. If the arch supports passing regs it will set this macro and pass regs for ops that request them. All other archs will just pass NULL. Link: Link: http://lkml.kernel.org/r/20120711195745.107705970@goodmis.org Cc: Alexander van Heukelum <heukelum@fastmail.fm> Reviewed-by: Masami Hiramatsu <masami.hiramatsu.pt@hitachi.com> Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
2012-05-01 04:20:23 +08:00
FTRACE_FL_REGS = (1UL << 30),
ftrace: Optimize function graph to be called directly Function graph tracing is a bit different than the function tracers, as it is processed after either the ftrace_caller or ftrace_regs_caller and we only have one place to modify the jump to ftrace_graph_caller, the jump needs to happen after the restore of registeres. The function graph tracer is dependent on the function tracer, where even if the function graph tracing is going on by itself, the save and restore of registers is still done for function tracing regardless of if function tracing is happening, before it calls the function graph code. If there's no function tracing happening, it is possible to just call the function graph tracer directly, and avoid the wasted effort to save and restore regs for function tracing. This requires adding new flags to the dyn_ftrace records: FTRACE_FL_TRAMP FTRACE_FL_TRAMP_EN The first is set if the count for the record is one, and the ftrace_ops associated to that record has its own trampoline. That way the mcount code can call that trampoline directly. In the future, trampolines can be added to arbitrary ftrace_ops, where you can have two or more ftrace_ops registered to ftrace (like kprobes and perf) and if they are not tracing the same functions, then instead of doing a loop to check all registered ftrace_ops against their hashes, just call the ftrace_ops trampoline directly, which would call the registered ftrace_ops function directly. Without this patch perf showed: 0.05% hackbench [kernel.kallsyms] [k] ftrace_caller 0.05% hackbench [kernel.kallsyms] [k] arch_local_irq_save 0.05% hackbench [kernel.kallsyms] [k] native_sched_clock 0.04% hackbench [kernel.kallsyms] [k] __buffer_unlock_commit 0.04% hackbench [kernel.kallsyms] [k] preempt_trace 0.04% hackbench [kernel.kallsyms] [k] prepare_ftrace_return 0.04% hackbench [kernel.kallsyms] [k] __this_cpu_preempt_check 0.04% hackbench [kernel.kallsyms] [k] ftrace_graph_caller See that the ftrace_caller took up more time than the ftrace_graph_caller did. With this patch: 0.05% hackbench [kernel.kallsyms] [k] __buffer_unlock_commit 0.04% hackbench [kernel.kallsyms] [k] call_filter_check_discard 0.04% hackbench [kernel.kallsyms] [k] ftrace_graph_caller 0.04% hackbench [kernel.kallsyms] [k] sched_clock The ftrace_caller is no where to be found and ftrace_graph_caller still takes up the same percentage. Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
2014-05-07 09:56:17 +08:00
FTRACE_FL_REGS_EN = (1UL << 29),
FTRACE_FL_TRAMP = (1UL << 28),
FTRACE_FL_TRAMP_EN = (1UL << 27),
FTRACE_FL_IPMODIFY = (1UL << 26),
};
#define FTRACE_REF_MAX_SHIFT 26
#define FTRACE_FL_BITS 6
#define FTRACE_FL_MASKED_BITS ((1UL << FTRACE_FL_BITS) - 1)
#define FTRACE_FL_MASK (FTRACE_FL_MASKED_BITS << FTRACE_REF_MAX_SHIFT)
#define FTRACE_REF_MAX ((1UL << FTRACE_REF_MAX_SHIFT) - 1)
#define ftrace_rec_count(rec) ((rec)->flags & ~FTRACE_FL_MASK)
ftrace: dynamic enabling/disabling of function calls This patch adds a feature to dynamically replace the ftrace code with the jmps to allow a kernel with ftrace configured to run as fast as it can without it configured. The way this works, is on bootup (if ftrace is enabled), a ftrace function is registered to record the instruction pointer of all places that call the function. Later, if there's still any code to patch, a kthread is awoken (rate limited to at most once a second) that performs a stop_machine, and replaces all the code that was called with a jmp over the call to ftrace. It only replaces what was found the previous time. Typically the system reaches equilibrium quickly after bootup and there's no code patching needed at all. e.g. call ftrace /* 5 bytes */ is replaced with jmp 3f /* jmp is 2 bytes and we jump 3 forward */ 3: When we want to enable ftrace for function tracing, the IP recording is removed, and stop_machine is called again to replace all the locations of that were recorded back to the call of ftrace. When it is disabled, we replace the code back to the jmp. Allocation is done by the kthread. If the ftrace recording function is called, and we don't have any record slots available, then we simply skip that call. Once a second a new page (if needed) is allocated for recording new ftrace function calls. A large batch is allocated at boot up to get most of the calls there. Because we do this via stop_machine, we don't have to worry about another CPU executing a ftrace call as we modify it. But we do need to worry about NMI's so all functions that might be called via nmi must be annotated with notrace_nmi. When this code is configured in, the NMI code will not call notrace. Signed-off-by: Steven Rostedt <srostedt@redhat.com> Signed-off-by: Ingo Molnar <mingo@elte.hu> Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
2008-05-13 03:20:42 +08:00
struct dyn_ftrace {
unsigned long ip; /* address of mcount call-site */
unsigned long flags;
struct dyn_arch_ftrace arch;
ftrace: dynamic enabling/disabling of function calls This patch adds a feature to dynamically replace the ftrace code with the jmps to allow a kernel with ftrace configured to run as fast as it can without it configured. The way this works, is on bootup (if ftrace is enabled), a ftrace function is registered to record the instruction pointer of all places that call the function. Later, if there's still any code to patch, a kthread is awoken (rate limited to at most once a second) that performs a stop_machine, and replaces all the code that was called with a jmp over the call to ftrace. It only replaces what was found the previous time. Typically the system reaches equilibrium quickly after bootup and there's no code patching needed at all. e.g. call ftrace /* 5 bytes */ is replaced with jmp 3f /* jmp is 2 bytes and we jump 3 forward */ 3: When we want to enable ftrace for function tracing, the IP recording is removed, and stop_machine is called again to replace all the locations of that were recorded back to the call of ftrace. When it is disabled, we replace the code back to the jmp. Allocation is done by the kthread. If the ftrace recording function is called, and we don't have any record slots available, then we simply skip that call. Once a second a new page (if needed) is allocated for recording new ftrace function calls. A large batch is allocated at boot up to get most of the calls there. Because we do this via stop_machine, we don't have to worry about another CPU executing a ftrace call as we modify it. But we do need to worry about NMI's so all functions that might be called via nmi must be annotated with notrace_nmi. When this code is configured in, the NMI code will not call notrace. Signed-off-by: Steven Rostedt <srostedt@redhat.com> Signed-off-by: Ingo Molnar <mingo@elte.hu> Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
2008-05-13 03:20:42 +08:00
};
int ftrace_force_update(void);
int ftrace_set_filter_ip(struct ftrace_ops *ops, unsigned long ip,
int remove, int reset);
int ftrace_set_filter(struct ftrace_ops *ops, unsigned char *buf,
int len, int reset);
int ftrace_set_notrace(struct ftrace_ops *ops, unsigned char *buf,
int len, int reset);
void ftrace_set_global_filter(unsigned char *buf, int len, int reset);
void ftrace_set_global_notrace(unsigned char *buf, int len, int reset);
ftrace, perf: Add filter support for function trace event Adding support to filter function trace event via perf interface. It is now possible to use filter interface in the perf tool like: perf record -e ftrace:function --filter="(ip == mm_*)" ls The filter syntax is restricted to the the 'ip' field only, and following operators are accepted '==' '!=' '||', ending up with the filter strings like: ip == f1[, ]f2 ... || ip != f3[, ]f4 ... with comma ',' or space ' ' as a function separator. If the space ' ' is used as a separator, the right side of the assignment needs to be enclosed in double quotes '"', e.g.: perf record -e ftrace:function --filter '(ip == do_execve,sys_*,ext*)' ls perf record -e ftrace:function --filter '(ip == "do_execve,sys_*,ext*")' ls perf record -e ftrace:function --filter '(ip == "do_execve sys_* ext*")' ls The '==' operator adds trace filter with same effect as would be added via set_ftrace_filter file. The '!=' operator adds trace filter with same effect as would be added via set_ftrace_notrace file. The right side of the '!=', '==' operators is list of functions or regexp. to be added to filter separated by space. The '||' operator is used for connecting multiple filter definitions together. It is possible to have more than one '==' and '!=' operators within one filter string. Link: http://lkml.kernel.org/r/1329317514-8131-8-git-send-email-jolsa@redhat.com Signed-off-by: Jiri Olsa <jolsa@redhat.com> Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
2012-02-15 22:51:54 +08:00
void ftrace_free_filter(struct ftrace_ops *ops);
int register_ftrace_command(struct ftrace_func_command *cmd);
int unregister_ftrace_command(struct ftrace_func_command *cmd);
enum {
FTRACE_UPDATE_CALLS = (1 << 0),
FTRACE_DISABLE_CALLS = (1 << 1),
FTRACE_UPDATE_TRACE_FUNC = (1 << 2),
FTRACE_START_FUNC_RET = (1 << 3),
FTRACE_STOP_FUNC_RET = (1 << 4),
};
ftrace/x86: Add separate function to save regs Add a way to have different functions calling different trampolines. If a ftrace_ops wants regs saved on the return, then have only the functions with ops registered to save regs. Functions registered by other ops would not be affected, unless the functions overlap. If one ftrace_ops registered functions A, B and C and another ops registered fucntions to save regs on A, and D, then only functions A and D would be saving regs. Function B and C would work as normal. Although A is registered by both ops: normal and saves regs; this is fine as saving the regs is needed to satisfy one of the ops that calls it but the regs are ignored by the other ops function. x86_64 implements the full regs saving, and i386 just passes a NULL for regs to satisfy the ftrace_ops passing. Where an arch must supply both regs and ftrace_ops parameters, even if regs is just NULL. It is OK for an arch to pass NULL regs. All function trace users that require regs passing must add the flag FTRACE_OPS_FL_SAVE_REGS when registering the ftrace_ops. If the arch does not support saving regs then the ftrace_ops will fail to register. The flag FTRACE_OPS_FL_SAVE_REGS_IF_SUPPORTED may be set that will prevent the ftrace_ops from failing to register. In this case, the handler may either check if regs is not NULL or check if ARCH_SUPPORTS_FTRACE_SAVE_REGS. If the arch supports passing regs it will set this macro and pass regs for ops that request them. All other archs will just pass NULL. Link: Link: http://lkml.kernel.org/r/20120711195745.107705970@goodmis.org Cc: Alexander van Heukelum <heukelum@fastmail.fm> Reviewed-by: Masami Hiramatsu <masami.hiramatsu.pt@hitachi.com> Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
2012-05-01 04:20:23 +08:00
/*
* The FTRACE_UPDATE_* enum is used to pass information back
* from the ftrace_update_record() and ftrace_test_record()
* functions. These are called by the code update routines
* to find out what is to be done for a given function.
*
* IGNORE - The function is already what we want it to be
* MAKE_CALL - Start tracing the function
* MODIFY_CALL - Stop saving regs for the function
* MAKE_NOP - Stop tracing the function
*/
enum {
FTRACE_UPDATE_IGNORE,
FTRACE_UPDATE_MAKE_CALL,
ftrace/x86: Add separate function to save regs Add a way to have different functions calling different trampolines. If a ftrace_ops wants regs saved on the return, then have only the functions with ops registered to save regs. Functions registered by other ops would not be affected, unless the functions overlap. If one ftrace_ops registered functions A, B and C and another ops registered fucntions to save regs on A, and D, then only functions A and D would be saving regs. Function B and C would work as normal. Although A is registered by both ops: normal and saves regs; this is fine as saving the regs is needed to satisfy one of the ops that calls it but the regs are ignored by the other ops function. x86_64 implements the full regs saving, and i386 just passes a NULL for regs to satisfy the ftrace_ops passing. Where an arch must supply both regs and ftrace_ops parameters, even if regs is just NULL. It is OK for an arch to pass NULL regs. All function trace users that require regs passing must add the flag FTRACE_OPS_FL_SAVE_REGS when registering the ftrace_ops. If the arch does not support saving regs then the ftrace_ops will fail to register. The flag FTRACE_OPS_FL_SAVE_REGS_IF_SUPPORTED may be set that will prevent the ftrace_ops from failing to register. In this case, the handler may either check if regs is not NULL or check if ARCH_SUPPORTS_FTRACE_SAVE_REGS. If the arch supports passing regs it will set this macro and pass regs for ops that request them. All other archs will just pass NULL. Link: Link: http://lkml.kernel.org/r/20120711195745.107705970@goodmis.org Cc: Alexander van Heukelum <heukelum@fastmail.fm> Reviewed-by: Masami Hiramatsu <masami.hiramatsu.pt@hitachi.com> Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
2012-05-01 04:20:23 +08:00
FTRACE_UPDATE_MODIFY_CALL,
FTRACE_UPDATE_MAKE_NOP,
};
enum {
FTRACE_ITER_FILTER = (1 << 0),
FTRACE_ITER_NOTRACE = (1 << 1),
FTRACE_ITER_PRINTALL = (1 << 2),
FTRACE_ITER_DO_HASH = (1 << 3),
FTRACE_ITER_HASH = (1 << 4),
FTRACE_ITER_ENABLED = (1 << 5),
};
void arch_ftrace_update_code(int command);
struct ftrace_rec_iter;
struct ftrace_rec_iter *ftrace_rec_iter_start(void);
struct ftrace_rec_iter *ftrace_rec_iter_next(struct ftrace_rec_iter *iter);
struct dyn_ftrace *ftrace_rec_iter_record(struct ftrace_rec_iter *iter);
#define for_ftrace_rec_iter(iter) \
for (iter = ftrace_rec_iter_start(); \
iter; \
iter = ftrace_rec_iter_next(iter))
int ftrace_update_record(struct dyn_ftrace *rec, int enable);
int ftrace_test_record(struct dyn_ftrace *rec, int enable);
void ftrace_run_stop_machine(int command);
unsigned long ftrace_location(unsigned long ip);
unsigned long ftrace_get_addr_new(struct dyn_ftrace *rec);
unsigned long ftrace_get_addr_curr(struct dyn_ftrace *rec);
extern ftrace_func_t ftrace_trace_function;
int ftrace_regex_open(struct ftrace_ops *ops, int flag,
struct inode *inode, struct file *file);
ssize_t ftrace_filter_write(struct file *file, const char __user *ubuf,
size_t cnt, loff_t *ppos);
ssize_t ftrace_notrace_write(struct file *file, const char __user *ubuf,
size_t cnt, loff_t *ppos);
int ftrace_regex_release(struct inode *inode, struct file *file);
void __init
ftrace_set_early_filter(struct ftrace_ops *ops, char *buf, int enable);
ftrace: dynamic enabling/disabling of function calls This patch adds a feature to dynamically replace the ftrace code with the jmps to allow a kernel with ftrace configured to run as fast as it can without it configured. The way this works, is on bootup (if ftrace is enabled), a ftrace function is registered to record the instruction pointer of all places that call the function. Later, if there's still any code to patch, a kthread is awoken (rate limited to at most once a second) that performs a stop_machine, and replaces all the code that was called with a jmp over the call to ftrace. It only replaces what was found the previous time. Typically the system reaches equilibrium quickly after bootup and there's no code patching needed at all. e.g. call ftrace /* 5 bytes */ is replaced with jmp 3f /* jmp is 2 bytes and we jump 3 forward */ 3: When we want to enable ftrace for function tracing, the IP recording is removed, and stop_machine is called again to replace all the locations of that were recorded back to the call of ftrace. When it is disabled, we replace the code back to the jmp. Allocation is done by the kthread. If the ftrace recording function is called, and we don't have any record slots available, then we simply skip that call. Once a second a new page (if needed) is allocated for recording new ftrace function calls. A large batch is allocated at boot up to get most of the calls there. Because we do this via stop_machine, we don't have to worry about another CPU executing a ftrace call as we modify it. But we do need to worry about NMI's so all functions that might be called via nmi must be annotated with notrace_nmi. When this code is configured in, the NMI code will not call notrace. Signed-off-by: Steven Rostedt <srostedt@redhat.com> Signed-off-by: Ingo Molnar <mingo@elte.hu> Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
2008-05-13 03:20:42 +08:00
/* defined in arch */
extern int ftrace_ip_converted(unsigned long ip);
extern int ftrace_dyn_arch_init(void);
extern void ftrace_replace_code(int enable);
extern int ftrace_update_ftrace_func(ftrace_func_t func);
extern void ftrace_caller(void);
ftrace/x86: Add separate function to save regs Add a way to have different functions calling different trampolines. If a ftrace_ops wants regs saved on the return, then have only the functions with ops registered to save regs. Functions registered by other ops would not be affected, unless the functions overlap. If one ftrace_ops registered functions A, B and C and another ops registered fucntions to save regs on A, and D, then only functions A and D would be saving regs. Function B and C would work as normal. Although A is registered by both ops: normal and saves regs; this is fine as saving the regs is needed to satisfy one of the ops that calls it but the regs are ignored by the other ops function. x86_64 implements the full regs saving, and i386 just passes a NULL for regs to satisfy the ftrace_ops passing. Where an arch must supply both regs and ftrace_ops parameters, even if regs is just NULL. It is OK for an arch to pass NULL regs. All function trace users that require regs passing must add the flag FTRACE_OPS_FL_SAVE_REGS when registering the ftrace_ops. If the arch does not support saving regs then the ftrace_ops will fail to register. The flag FTRACE_OPS_FL_SAVE_REGS_IF_SUPPORTED may be set that will prevent the ftrace_ops from failing to register. In this case, the handler may either check if regs is not NULL or check if ARCH_SUPPORTS_FTRACE_SAVE_REGS. If the arch supports passing regs it will set this macro and pass regs for ops that request them. All other archs will just pass NULL. Link: Link: http://lkml.kernel.org/r/20120711195745.107705970@goodmis.org Cc: Alexander van Heukelum <heukelum@fastmail.fm> Reviewed-by: Masami Hiramatsu <masami.hiramatsu.pt@hitachi.com> Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
2012-05-01 04:20:23 +08:00
extern void ftrace_regs_caller(void);
extern void ftrace_call(void);
ftrace/x86: Add separate function to save regs Add a way to have different functions calling different trampolines. If a ftrace_ops wants regs saved on the return, then have only the functions with ops registered to save regs. Functions registered by other ops would not be affected, unless the functions overlap. If one ftrace_ops registered functions A, B and C and another ops registered fucntions to save regs on A, and D, then only functions A and D would be saving regs. Function B and C would work as normal. Although A is registered by both ops: normal and saves regs; this is fine as saving the regs is needed to satisfy one of the ops that calls it but the regs are ignored by the other ops function. x86_64 implements the full regs saving, and i386 just passes a NULL for regs to satisfy the ftrace_ops passing. Where an arch must supply both regs and ftrace_ops parameters, even if regs is just NULL. It is OK for an arch to pass NULL regs. All function trace users that require regs passing must add the flag FTRACE_OPS_FL_SAVE_REGS when registering the ftrace_ops. If the arch does not support saving regs then the ftrace_ops will fail to register. The flag FTRACE_OPS_FL_SAVE_REGS_IF_SUPPORTED may be set that will prevent the ftrace_ops from failing to register. In this case, the handler may either check if regs is not NULL or check if ARCH_SUPPORTS_FTRACE_SAVE_REGS. If the arch supports passing regs it will set this macro and pass regs for ops that request them. All other archs will just pass NULL. Link: Link: http://lkml.kernel.org/r/20120711195745.107705970@goodmis.org Cc: Alexander van Heukelum <heukelum@fastmail.fm> Reviewed-by: Masami Hiramatsu <masami.hiramatsu.pt@hitachi.com> Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
2012-05-01 04:20:23 +08:00
extern void ftrace_regs_call(void);
extern void mcount_call(void);
void ftrace_modify_all_code(int command);
#ifndef FTRACE_ADDR
#define FTRACE_ADDR ((unsigned long)ftrace_caller)
#endif
ftrace/x86: Add separate function to save regs Add a way to have different functions calling different trampolines. If a ftrace_ops wants regs saved on the return, then have only the functions with ops registered to save regs. Functions registered by other ops would not be affected, unless the functions overlap. If one ftrace_ops registered functions A, B and C and another ops registered fucntions to save regs on A, and D, then only functions A and D would be saving regs. Function B and C would work as normal. Although A is registered by both ops: normal and saves regs; this is fine as saving the regs is needed to satisfy one of the ops that calls it but the regs are ignored by the other ops function. x86_64 implements the full regs saving, and i386 just passes a NULL for regs to satisfy the ftrace_ops passing. Where an arch must supply both regs and ftrace_ops parameters, even if regs is just NULL. It is OK for an arch to pass NULL regs. All function trace users that require regs passing must add the flag FTRACE_OPS_FL_SAVE_REGS when registering the ftrace_ops. If the arch does not support saving regs then the ftrace_ops will fail to register. The flag FTRACE_OPS_FL_SAVE_REGS_IF_SUPPORTED may be set that will prevent the ftrace_ops from failing to register. In this case, the handler may either check if regs is not NULL or check if ARCH_SUPPORTS_FTRACE_SAVE_REGS. If the arch supports passing regs it will set this macro and pass regs for ops that request them. All other archs will just pass NULL. Link: Link: http://lkml.kernel.org/r/20120711195745.107705970@goodmis.org Cc: Alexander van Heukelum <heukelum@fastmail.fm> Reviewed-by: Masami Hiramatsu <masami.hiramatsu.pt@hitachi.com> Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
2012-05-01 04:20:23 +08:00
ftrace: Optimize function graph to be called directly Function graph tracing is a bit different than the function tracers, as it is processed after either the ftrace_caller or ftrace_regs_caller and we only have one place to modify the jump to ftrace_graph_caller, the jump needs to happen after the restore of registeres. The function graph tracer is dependent on the function tracer, where even if the function graph tracing is going on by itself, the save and restore of registers is still done for function tracing regardless of if function tracing is happening, before it calls the function graph code. If there's no function tracing happening, it is possible to just call the function graph tracer directly, and avoid the wasted effort to save and restore regs for function tracing. This requires adding new flags to the dyn_ftrace records: FTRACE_FL_TRAMP FTRACE_FL_TRAMP_EN The first is set if the count for the record is one, and the ftrace_ops associated to that record has its own trampoline. That way the mcount code can call that trampoline directly. In the future, trampolines can be added to arbitrary ftrace_ops, where you can have two or more ftrace_ops registered to ftrace (like kprobes and perf) and if they are not tracing the same functions, then instead of doing a loop to check all registered ftrace_ops against their hashes, just call the ftrace_ops trampoline directly, which would call the registered ftrace_ops function directly. Without this patch perf showed: 0.05% hackbench [kernel.kallsyms] [k] ftrace_caller 0.05% hackbench [kernel.kallsyms] [k] arch_local_irq_save 0.05% hackbench [kernel.kallsyms] [k] native_sched_clock 0.04% hackbench [kernel.kallsyms] [k] __buffer_unlock_commit 0.04% hackbench [kernel.kallsyms] [k] preempt_trace 0.04% hackbench [kernel.kallsyms] [k] prepare_ftrace_return 0.04% hackbench [kernel.kallsyms] [k] __this_cpu_preempt_check 0.04% hackbench [kernel.kallsyms] [k] ftrace_graph_caller See that the ftrace_caller took up more time than the ftrace_graph_caller did. With this patch: 0.05% hackbench [kernel.kallsyms] [k] __buffer_unlock_commit 0.04% hackbench [kernel.kallsyms] [k] call_filter_check_discard 0.04% hackbench [kernel.kallsyms] [k] ftrace_graph_caller 0.04% hackbench [kernel.kallsyms] [k] sched_clock The ftrace_caller is no where to be found and ftrace_graph_caller still takes up the same percentage. Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
2014-05-07 09:56:17 +08:00
#ifndef FTRACE_GRAPH_ADDR
#define FTRACE_GRAPH_ADDR ((unsigned long)ftrace_graph_caller)
#endif
ftrace/x86: Add separate function to save regs Add a way to have different functions calling different trampolines. If a ftrace_ops wants regs saved on the return, then have only the functions with ops registered to save regs. Functions registered by other ops would not be affected, unless the functions overlap. If one ftrace_ops registered functions A, B and C and another ops registered fucntions to save regs on A, and D, then only functions A and D would be saving regs. Function B and C would work as normal. Although A is registered by both ops: normal and saves regs; this is fine as saving the regs is needed to satisfy one of the ops that calls it but the regs are ignored by the other ops function. x86_64 implements the full regs saving, and i386 just passes a NULL for regs to satisfy the ftrace_ops passing. Where an arch must supply both regs and ftrace_ops parameters, even if regs is just NULL. It is OK for an arch to pass NULL regs. All function trace users that require regs passing must add the flag FTRACE_OPS_FL_SAVE_REGS when registering the ftrace_ops. If the arch does not support saving regs then the ftrace_ops will fail to register. The flag FTRACE_OPS_FL_SAVE_REGS_IF_SUPPORTED may be set that will prevent the ftrace_ops from failing to register. In this case, the handler may either check if regs is not NULL or check if ARCH_SUPPORTS_FTRACE_SAVE_REGS. If the arch supports passing regs it will set this macro and pass regs for ops that request them. All other archs will just pass NULL. Link: Link: http://lkml.kernel.org/r/20120711195745.107705970@goodmis.org Cc: Alexander van Heukelum <heukelum@fastmail.fm> Reviewed-by: Masami Hiramatsu <masami.hiramatsu.pt@hitachi.com> Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
2012-05-01 04:20:23 +08:00
#ifndef FTRACE_REGS_ADDR
#ifdef CONFIG_DYNAMIC_FTRACE_WITH_REGS
ftrace/x86: Add separate function to save regs Add a way to have different functions calling different trampolines. If a ftrace_ops wants regs saved on the return, then have only the functions with ops registered to save regs. Functions registered by other ops would not be affected, unless the functions overlap. If one ftrace_ops registered functions A, B and C and another ops registered fucntions to save regs on A, and D, then only functions A and D would be saving regs. Function B and C would work as normal. Although A is registered by both ops: normal and saves regs; this is fine as saving the regs is needed to satisfy one of the ops that calls it but the regs are ignored by the other ops function. x86_64 implements the full regs saving, and i386 just passes a NULL for regs to satisfy the ftrace_ops passing. Where an arch must supply both regs and ftrace_ops parameters, even if regs is just NULL. It is OK for an arch to pass NULL regs. All function trace users that require regs passing must add the flag FTRACE_OPS_FL_SAVE_REGS when registering the ftrace_ops. If the arch does not support saving regs then the ftrace_ops will fail to register. The flag FTRACE_OPS_FL_SAVE_REGS_IF_SUPPORTED may be set that will prevent the ftrace_ops from failing to register. In this case, the handler may either check if regs is not NULL or check if ARCH_SUPPORTS_FTRACE_SAVE_REGS. If the arch supports passing regs it will set this macro and pass regs for ops that request them. All other archs will just pass NULL. Link: Link: http://lkml.kernel.org/r/20120711195745.107705970@goodmis.org Cc: Alexander van Heukelum <heukelum@fastmail.fm> Reviewed-by: Masami Hiramatsu <masami.hiramatsu.pt@hitachi.com> Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
2012-05-01 04:20:23 +08:00
# define FTRACE_REGS_ADDR ((unsigned long)ftrace_regs_caller)
#else
# define FTRACE_REGS_ADDR FTRACE_ADDR
#endif
#endif
/*
* If an arch would like functions that are only traced
* by the function graph tracer to jump directly to its own
* trampoline, then they can define FTRACE_GRAPH_TRAMP_ADDR
* to be that address to jump to.
*/
#ifndef FTRACE_GRAPH_TRAMP_ADDR
#define FTRACE_GRAPH_TRAMP_ADDR ((unsigned long) 0)
#endif
#ifdef CONFIG_FUNCTION_GRAPH_TRACER
extern void ftrace_graph_caller(void);
extern int ftrace_enable_ftrace_graph_caller(void);
extern int ftrace_disable_ftrace_graph_caller(void);
#else
static inline int ftrace_enable_ftrace_graph_caller(void) { return 0; }
static inline int ftrace_disable_ftrace_graph_caller(void) { return 0; }
tracing/function-return-tracer: support for dynamic ftrace on function return tracer This patch adds the support for dynamic tracing on the function return tracer. The whole difference with normal dynamic function tracing is that we don't need to hook on a particular callback. The only pro that we want is to nop or set dynamically the calls to ftrace_caller (which is ftrace_return_caller here). Some security checks ensure that we are not trying to launch dynamic tracing for return tracing while normal function tracing is already running. An example of trace with getnstimeofday set as a filter: ktime_get_ts+0x22/0x50 -> getnstimeofday (2283 ns) ktime_get_ts+0x22/0x50 -> getnstimeofday (1396 ns) ktime_get_ts+0x22/0x50 -> getnstimeofday (1382 ns) ktime_get_ts+0x22/0x50 -> getnstimeofday (1825 ns) ktime_get_ts+0x22/0x50 -> getnstimeofday (1426 ns) ktime_get_ts+0x22/0x50 -> getnstimeofday (1464 ns) ktime_get_ts+0x22/0x50 -> getnstimeofday (1524 ns) ktime_get_ts+0x22/0x50 -> getnstimeofday (1382 ns) ktime_get_ts+0x22/0x50 -> getnstimeofday (1382 ns) ktime_get_ts+0x22/0x50 -> getnstimeofday (1434 ns) ktime_get_ts+0x22/0x50 -> getnstimeofday (1464 ns) ktime_get_ts+0x22/0x50 -> getnstimeofday (1502 ns) ktime_get_ts+0x22/0x50 -> getnstimeofday (1404 ns) ktime_get_ts+0x22/0x50 -> getnstimeofday (1397 ns) ktime_get_ts+0x22/0x50 -> getnstimeofday (1051 ns) ktime_get_ts+0x22/0x50 -> getnstimeofday (1314 ns) ktime_get_ts+0x22/0x50 -> getnstimeofday (1344 ns) ktime_get_ts+0x22/0x50 -> getnstimeofday (1163 ns) ktime_get_ts+0x22/0x50 -> getnstimeofday (1390 ns) ktime_get_ts+0x22/0x50 -> getnstimeofday (1374 ns) Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2008-11-16 13:02:06 +08:00
#endif
ftrace: user update and disable dynamic ftrace daemon In dynamic ftrace, the mcount function starts off pointing to a stub function that just returns. On start up, the call to the stub is modified to point to a "record_ip" function. The job of the record_ip function is to add the function to a pre-allocated hash list. If the function is already there, it simply is ignored, otherwise it is added to the list. Later, a ftraced daemon wakes up and calls kstop_machine if any functions have been recorded, and changes the calls to the recorded functions to a simple nop. If no functions were recorded, the daemon goes back to sleep. The daemon wakes up once a second to see if it needs to update any newly recorded functions into nops. Usually it does not, but if a lot of code has been executed for the first time in the kernel, the ftraced daemon will call kstop_machine to update those into nops. The problem currently is that there's no way to stop the daemon from doing this, and it can cause unneeded latencies (800us which for some is bothersome). This patch adds a new file /debugfs/tracing/ftraced_enabled. If the daemon is active, reading this will return "enabled\n" and "disabled\n" when the daemon is not running. To disable the daemon, the user can echo "0" or "disable" into this file, and "1" or "enable" to re-enable the daemon. Since the daemon is used to convert the functions into nops to increase the performance of the system, I also added that anytime something is written into the ftraced_enabled file, kstop_machine will run if there are new functions that have been detected that need to be converted. This way the user can disable the daemon but still be able to control the conversion of the mcount calls to nops by simply, "echo 0 > /debugfs/tracing/ftraced_enabled" when they need to do more conversions. To see the number of converted functions: "cat /debugfs/tracing/dyn_ftrace_total_info" Signed-off-by: Steven Rostedt <srostedt@redhat.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2008-05-28 08:48:37 +08:00
ftrace: pass module struct to arch dynamic ftrace functions Impact: allow archs more flexibility on dynamic ftrace implementations Dynamic ftrace has largly been developed on x86. Since x86 does not have the same limitations as other architectures, the ftrace interaction between the generic code and the architecture specific code was not flexible enough to handle some of the issues that other architectures have. Most notably, module trampolines. Due to the limited branch distance that archs make in calling kernel core code from modules, the module load code must create a trampoline to jump to what will make the larger jump into core kernel code. The problem arises when this happens to a call to mcount. Ftrace checks all code before modifying it and makes sure the current code is what it expects. Right now, there is not enough information to handle modifying module trampolines. This patch changes the API between generic dynamic ftrace code and the arch dependent code. There is now two functions for modifying code: ftrace_make_nop(mod, rec, addr) - convert the code at rec->ip into a nop, where the original text is calling addr. (mod is the module struct if called by module init) ftrace_make_caller(rec, addr) - convert the code rec->ip that should be a nop into a caller to addr. The record "rec" now has a new field called "arch" where the architecture can add any special attributes to each call site record. Signed-off-by: Steven Rostedt <srostedt@redhat.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2008-11-15 08:21:19 +08:00
/**
* ftrace_make_nop - convert code into nop
ftrace: pass module struct to arch dynamic ftrace functions Impact: allow archs more flexibility on dynamic ftrace implementations Dynamic ftrace has largly been developed on x86. Since x86 does not have the same limitations as other architectures, the ftrace interaction between the generic code and the architecture specific code was not flexible enough to handle some of the issues that other architectures have. Most notably, module trampolines. Due to the limited branch distance that archs make in calling kernel core code from modules, the module load code must create a trampoline to jump to what will make the larger jump into core kernel code. The problem arises when this happens to a call to mcount. Ftrace checks all code before modifying it and makes sure the current code is what it expects. Right now, there is not enough information to handle modifying module trampolines. This patch changes the API between generic dynamic ftrace code and the arch dependent code. There is now two functions for modifying code: ftrace_make_nop(mod, rec, addr) - convert the code at rec->ip into a nop, where the original text is calling addr. (mod is the module struct if called by module init) ftrace_make_caller(rec, addr) - convert the code rec->ip that should be a nop into a caller to addr. The record "rec" now has a new field called "arch" where the architecture can add any special attributes to each call site record. Signed-off-by: Steven Rostedt <srostedt@redhat.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2008-11-15 08:21:19 +08:00
* @mod: module structure if called by module load initialization
* @rec: the mcount call site record
* @addr: the address that the call site should be calling
*
* This is a very sensitive operation and great care needs
* to be taken by the arch. The operation should carefully
* read the location, check to see if what is read is indeed
* what we expect it to be, and then on success of the compare,
* it should write to the location.
*
* The code segment at @rec->ip should be a caller to @addr
*
* Return must be:
* 0 on success
* -EFAULT on error reading the location
* -EINVAL on a failed compare of the contents
* -EPERM on error writing to the location
* Any other value will be considered a failure.
*/
extern int ftrace_make_nop(struct module *mod,
struct dyn_ftrace *rec, unsigned long addr);
/**
ftrace: pass module struct to arch dynamic ftrace functions Impact: allow archs more flexibility on dynamic ftrace implementations Dynamic ftrace has largly been developed on x86. Since x86 does not have the same limitations as other architectures, the ftrace interaction between the generic code and the architecture specific code was not flexible enough to handle some of the issues that other architectures have. Most notably, module trampolines. Due to the limited branch distance that archs make in calling kernel core code from modules, the module load code must create a trampoline to jump to what will make the larger jump into core kernel code. The problem arises when this happens to a call to mcount. Ftrace checks all code before modifying it and makes sure the current code is what it expects. Right now, there is not enough information to handle modifying module trampolines. This patch changes the API between generic dynamic ftrace code and the arch dependent code. There is now two functions for modifying code: ftrace_make_nop(mod, rec, addr) - convert the code at rec->ip into a nop, where the original text is calling addr. (mod is the module struct if called by module init) ftrace_make_caller(rec, addr) - convert the code rec->ip that should be a nop into a caller to addr. The record "rec" now has a new field called "arch" where the architecture can add any special attributes to each call site record. Signed-off-by: Steven Rostedt <srostedt@redhat.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2008-11-15 08:21:19 +08:00
* ftrace_make_call - convert a nop call site into a call to addr
* @rec: the mcount call site record
* @addr: the address that the call site should call
*
* This is a very sensitive operation and great care needs
* to be taken by the arch. The operation should carefully
* read the location, check to see if what is read is indeed
* what we expect it to be, and then on success of the compare,
* it should write to the location.
*
ftrace: pass module struct to arch dynamic ftrace functions Impact: allow archs more flexibility on dynamic ftrace implementations Dynamic ftrace has largly been developed on x86. Since x86 does not have the same limitations as other architectures, the ftrace interaction between the generic code and the architecture specific code was not flexible enough to handle some of the issues that other architectures have. Most notably, module trampolines. Due to the limited branch distance that archs make in calling kernel core code from modules, the module load code must create a trampoline to jump to what will make the larger jump into core kernel code. The problem arises when this happens to a call to mcount. Ftrace checks all code before modifying it and makes sure the current code is what it expects. Right now, there is not enough information to handle modifying module trampolines. This patch changes the API between generic dynamic ftrace code and the arch dependent code. There is now two functions for modifying code: ftrace_make_nop(mod, rec, addr) - convert the code at rec->ip into a nop, where the original text is calling addr. (mod is the module struct if called by module init) ftrace_make_caller(rec, addr) - convert the code rec->ip that should be a nop into a caller to addr. The record "rec" now has a new field called "arch" where the architecture can add any special attributes to each call site record. Signed-off-by: Steven Rostedt <srostedt@redhat.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2008-11-15 08:21:19 +08:00
* The code segment at @rec->ip should be a nop
*
* Return must be:
* 0 on success
* -EFAULT on error reading the location
* -EINVAL on a failed compare of the contents
* -EPERM on error writing to the location
* Any other value will be considered a failure.
*/
ftrace: pass module struct to arch dynamic ftrace functions Impact: allow archs more flexibility on dynamic ftrace implementations Dynamic ftrace has largly been developed on x86. Since x86 does not have the same limitations as other architectures, the ftrace interaction between the generic code and the architecture specific code was not flexible enough to handle some of the issues that other architectures have. Most notably, module trampolines. Due to the limited branch distance that archs make in calling kernel core code from modules, the module load code must create a trampoline to jump to what will make the larger jump into core kernel code. The problem arises when this happens to a call to mcount. Ftrace checks all code before modifying it and makes sure the current code is what it expects. Right now, there is not enough information to handle modifying module trampolines. This patch changes the API between generic dynamic ftrace code and the arch dependent code. There is now two functions for modifying code: ftrace_make_nop(mod, rec, addr) - convert the code at rec->ip into a nop, where the original text is calling addr. (mod is the module struct if called by module init) ftrace_make_caller(rec, addr) - convert the code rec->ip that should be a nop into a caller to addr. The record "rec" now has a new field called "arch" where the architecture can add any special attributes to each call site record. Signed-off-by: Steven Rostedt <srostedt@redhat.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2008-11-15 08:21:19 +08:00
extern int ftrace_make_call(struct dyn_ftrace *rec, unsigned long addr);
#ifdef CONFIG_DYNAMIC_FTRACE_WITH_REGS
ftrace/x86: Add separate function to save regs Add a way to have different functions calling different trampolines. If a ftrace_ops wants regs saved on the return, then have only the functions with ops registered to save regs. Functions registered by other ops would not be affected, unless the functions overlap. If one ftrace_ops registered functions A, B and C and another ops registered fucntions to save regs on A, and D, then only functions A and D would be saving regs. Function B and C would work as normal. Although A is registered by both ops: normal and saves regs; this is fine as saving the regs is needed to satisfy one of the ops that calls it but the regs are ignored by the other ops function. x86_64 implements the full regs saving, and i386 just passes a NULL for regs to satisfy the ftrace_ops passing. Where an arch must supply both regs and ftrace_ops parameters, even if regs is just NULL. It is OK for an arch to pass NULL regs. All function trace users that require regs passing must add the flag FTRACE_OPS_FL_SAVE_REGS when registering the ftrace_ops. If the arch does not support saving regs then the ftrace_ops will fail to register. The flag FTRACE_OPS_FL_SAVE_REGS_IF_SUPPORTED may be set that will prevent the ftrace_ops from failing to register. In this case, the handler may either check if regs is not NULL or check if ARCH_SUPPORTS_FTRACE_SAVE_REGS. If the arch supports passing regs it will set this macro and pass regs for ops that request them. All other archs will just pass NULL. Link: Link: http://lkml.kernel.org/r/20120711195745.107705970@goodmis.org Cc: Alexander van Heukelum <heukelum@fastmail.fm> Reviewed-by: Masami Hiramatsu <masami.hiramatsu.pt@hitachi.com> Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
2012-05-01 04:20:23 +08:00
/**
* ftrace_modify_call - convert from one addr to another (no nop)
* @rec: the mcount call site record
* @old_addr: the address expected to be currently called to
* @addr: the address to change to
*
* This is a very sensitive operation and great care needs
* to be taken by the arch. The operation should carefully
* read the location, check to see if what is read is indeed
* what we expect it to be, and then on success of the compare,
* it should write to the location.
*
* The code segment at @rec->ip should be a caller to @old_addr
*
* Return must be:
* 0 on success
* -EFAULT on error reading the location
* -EINVAL on a failed compare of the contents
* -EPERM on error writing to the location
* Any other value will be considered a failure.
*/
extern int ftrace_modify_call(struct dyn_ftrace *rec, unsigned long old_addr,
unsigned long addr);
#else
/* Should never be called */
static inline int ftrace_modify_call(struct dyn_ftrace *rec, unsigned long old_addr,
unsigned long addr)
{
return -EINVAL;
}
#endif
ftrace: pass module struct to arch dynamic ftrace functions Impact: allow archs more flexibility on dynamic ftrace implementations Dynamic ftrace has largly been developed on x86. Since x86 does not have the same limitations as other architectures, the ftrace interaction between the generic code and the architecture specific code was not flexible enough to handle some of the issues that other architectures have. Most notably, module trampolines. Due to the limited branch distance that archs make in calling kernel core code from modules, the module load code must create a trampoline to jump to what will make the larger jump into core kernel code. The problem arises when this happens to a call to mcount. Ftrace checks all code before modifying it and makes sure the current code is what it expects. Right now, there is not enough information to handle modifying module trampolines. This patch changes the API between generic dynamic ftrace code and the arch dependent code. There is now two functions for modifying code: ftrace_make_nop(mod, rec, addr) - convert the code at rec->ip into a nop, where the original text is calling addr. (mod is the module struct if called by module init) ftrace_make_caller(rec, addr) - convert the code rec->ip that should be a nop into a caller to addr. The record "rec" now has a new field called "arch" where the architecture can add any special attributes to each call site record. Signed-off-by: Steven Rostedt <srostedt@redhat.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2008-11-15 08:21:19 +08:00
/* May be defined in arch */
extern int ftrace_arch_read_dyn_info(char *buf, int size);
extern int skip_trace(unsigned long ip);
ftrace/module: Hardcode ftrace_module_init() call into load_module() A race exists between module loading and enabling of function tracer. CPU 1 CPU 2 ----- ----- load_module() module->state = MODULE_STATE_COMING register_ftrace_function() mutex_lock(&ftrace_lock); ftrace_startup() update_ftrace_function(); ftrace_arch_code_modify_prepare() set_all_module_text_rw(); <enables-ftrace> ftrace_arch_code_modify_post_process() set_all_module_text_ro(); [ here all module text is set to RO, including the module that is loading!! ] blocking_notifier_call_chain(MODULE_STATE_COMING); ftrace_init_module() [ tries to modify code, but it's RO, and fails! ftrace_bug() is called] When this race happens, ftrace_bug() will produces a nasty warning and all of the function tracing features will be disabled until reboot. The simple solution is to treate module load the same way the core kernel is treated at boot. To hardcode the ftrace function modification of converting calls to mcount into nops. This is done in init/main.c there's no reason it could not be done in load_module(). This gives a better control of the changes and doesn't tie the state of the module to its notifiers as much. Ftrace is special, it needs to be treated as such. The reason this would work, is that the ftrace_module_init() would be called while the module is in MODULE_STATE_UNFORMED, which is ignored by the set_all_module_text_ro() call. Link: http://lkml.kernel.org/r/1395637826-3312-1-git-send-email-indou.takao@jp.fujitsu.com Reported-by: Takao Indoh <indou.takao@jp.fujitsu.com> Acked-by: Rusty Russell <rusty@rustcorp.com.au> Cc: stable@vger.kernel.org # 2.6.38+ Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
2014-04-24 22:40:12 +08:00
extern void ftrace_module_init(struct module *mod);
extern void ftrace_disable_daemon(void);
extern void ftrace_enable_daemon(void);
#else /* CONFIG_DYNAMIC_FTRACE */
static inline int skip_trace(unsigned long ip) { return 0; }
static inline int ftrace_force_update(void) { return 0; }
static inline void ftrace_disable_daemon(void) { }
static inline void ftrace_enable_daemon(void) { }
static inline void ftrace_release_mod(struct module *mod) {}
ftrace/module: Hardcode ftrace_module_init() call into load_module() A race exists between module loading and enabling of function tracer. CPU 1 CPU 2 ----- ----- load_module() module->state = MODULE_STATE_COMING register_ftrace_function() mutex_lock(&ftrace_lock); ftrace_startup() update_ftrace_function(); ftrace_arch_code_modify_prepare() set_all_module_text_rw(); <enables-ftrace> ftrace_arch_code_modify_post_process() set_all_module_text_ro(); [ here all module text is set to RO, including the module that is loading!! ] blocking_notifier_call_chain(MODULE_STATE_COMING); ftrace_init_module() [ tries to modify code, but it's RO, and fails! ftrace_bug() is called] When this race happens, ftrace_bug() will produces a nasty warning and all of the function tracing features will be disabled until reboot. The simple solution is to treate module load the same way the core kernel is treated at boot. To hardcode the ftrace function modification of converting calls to mcount into nops. This is done in init/main.c there's no reason it could not be done in load_module(). This gives a better control of the changes and doesn't tie the state of the module to its notifiers as much. Ftrace is special, it needs to be treated as such. The reason this would work, is that the ftrace_module_init() would be called while the module is in MODULE_STATE_UNFORMED, which is ignored by the set_all_module_text_ro() call. Link: http://lkml.kernel.org/r/1395637826-3312-1-git-send-email-indou.takao@jp.fujitsu.com Reported-by: Takao Indoh <indou.takao@jp.fujitsu.com> Acked-by: Rusty Russell <rusty@rustcorp.com.au> Cc: stable@vger.kernel.org # 2.6.38+ Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
2014-04-24 22:40:12 +08:00
static inline void ftrace_module_init(struct module *mod) {}
static inline __init int register_ftrace_command(struct ftrace_func_command *cmd)
{
return -EINVAL;
}
static inline __init int unregister_ftrace_command(char *cmd_name)
{
return -EINVAL;
}
static inline int ftrace_text_reserved(const void *start, const void *end)
{
return 0;
}
static inline unsigned long ftrace_location(unsigned long ip)
{
return 0;
}
/*
* Again users of functions that have ftrace_ops may not
* have them defined when ftrace is not enabled, but these
* functions may still be called. Use a macro instead of inline.
*/
#define ftrace_regex_open(ops, flag, inod, file) ({ -ENODEV; })
#define ftrace_set_early_filter(ops, buf, enable) do { } while (0)
#define ftrace_set_filter_ip(ops, ip, remove, reset) ({ -ENODEV; })
ftrace, perf: Add filter support for function trace event Adding support to filter function trace event via perf interface. It is now possible to use filter interface in the perf tool like: perf record -e ftrace:function --filter="(ip == mm_*)" ls The filter syntax is restricted to the the 'ip' field only, and following operators are accepted '==' '!=' '||', ending up with the filter strings like: ip == f1[, ]f2 ... || ip != f3[, ]f4 ... with comma ',' or space ' ' as a function separator. If the space ' ' is used as a separator, the right side of the assignment needs to be enclosed in double quotes '"', e.g.: perf record -e ftrace:function --filter '(ip == do_execve,sys_*,ext*)' ls perf record -e ftrace:function --filter '(ip == "do_execve,sys_*,ext*")' ls perf record -e ftrace:function --filter '(ip == "do_execve sys_* ext*")' ls The '==' operator adds trace filter with same effect as would be added via set_ftrace_filter file. The '!=' operator adds trace filter with same effect as would be added via set_ftrace_notrace file. The right side of the '!=', '==' operators is list of functions or regexp. to be added to filter separated by space. The '||' operator is used for connecting multiple filter definitions together. It is possible to have more than one '==' and '!=' operators within one filter string. Link: http://lkml.kernel.org/r/1329317514-8131-8-git-send-email-jolsa@redhat.com Signed-off-by: Jiri Olsa <jolsa@redhat.com> Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
2012-02-15 22:51:54 +08:00
#define ftrace_set_filter(ops, buf, len, reset) ({ -ENODEV; })
#define ftrace_set_notrace(ops, buf, len, reset) ({ -ENODEV; })
#define ftrace_free_filter(ops) do { } while (0)
static inline ssize_t ftrace_filter_write(struct file *file, const char __user *ubuf,
size_t cnt, loff_t *ppos) { return -ENODEV; }
static inline ssize_t ftrace_notrace_write(struct file *file, const char __user *ubuf,
size_t cnt, loff_t *ppos) { return -ENODEV; }
static inline int
ftrace_regex_release(struct inode *inode, struct file *file) { return -ENODEV; }
static inline bool is_ftrace_trampoline(unsigned long addr)
{
return false;
}
#endif /* CONFIG_DYNAMIC_FTRACE */
ftrace: tracer for scheduler wakeup latency This patch adds the tracer that tracks the wakeup latency of the highest priority waking task. "wakeup" is added to /debugfs/tracing/available_tracers Also added to /debugfs/tracing tracing_max_latency holds the current max latency for the wakeup wakeup_thresh if set to other than zero, a log will be recorded for every wakeup that takes longer than the number entered in here (usecs for all counters) (deletes previous trace) Examples: (with ftrace_enabled = 0) ============ preemption latency trace v1.1.5 on 2.6.24-rc8 Signed-off-by: Ingo Molnar <mingo@elte.hu> -------------------------------------------------------------------- latency: 26 us, #2/2, CPU#1 | (M:rt VP:0, KP:0, SP:0 HP:0 #P:2) ----------------- | task: migration/0-3 (uid:0 nice:-5 policy:1 rt_prio:99) ----------------- _------=> CPU# / _-----=> irqs-off | / _----=> need-resched || / _---=> hardirq/softirq ||| / _--=> preempt-depth |||| / ||||| delay cmd pid ||||| time | caller \ / ||||| \ | / quilt-8551 0d..3 0us+: wake_up_process+0x15/0x17 <ffffffff80233e80> (sched_exec+0xc9/0x100 <ffffffff80235343>) quilt-8551 0d..4 26us : sched_switch_callback+0x73/0x81 <ffffffff80338d2f> (schedule+0x483/0x6d5 <ffffffff8048b3ee>) vim:ft=help ============ (with ftrace_enabled = 1) ============ preemption latency trace v1.1.5 on 2.6.24-rc8 -------------------------------------------------------------------- latency: 36 us, #45/45, CPU#0 | (M:rt VP:0, KP:0, SP:0 HP:0 #P:2) ----------------- | task: migration/1-5 (uid:0 nice:-5 policy:1 rt_prio:99) ----------------- _------=> CPU# / _-----=> irqs-off | / _----=> need-resched || / _---=> hardirq/softirq ||| / _--=> preempt-depth |||| / ||||| delay cmd pid ||||| time | caller \ / ||||| \ | / bash-10653 1d..3 0us : wake_up_process+0x15/0x17 <ffffffff80233e80> (sched_exec+0xc9/0x100 <ffffffff80235343>) bash-10653 1d..3 1us : try_to_wake_up+0x271/0x2e7 <ffffffff80233dcf> (sub_preempt_count+0xc/0x7a <ffffffff8023309e>) bash-10653 1d..2 2us : try_to_wake_up+0x296/0x2e7 <ffffffff80233df4> (update_rq_clock+0x9/0x20 <ffffffff802303f3>) bash-10653 1d..2 2us : update_rq_clock+0x1e/0x20 <ffffffff80230408> (__update_rq_clock+0xc/0x90 <ffffffff80230366>) bash-10653 1d..2 3us : __update_rq_clock+0x1b/0x90 <ffffffff80230375> (sched_clock+0x9/0x29 <ffffffff80214529>) bash-10653 1d..2 4us : try_to_wake_up+0x2a6/0x2e7 <ffffffff80233e04> (activate_task+0xc/0x3f <ffffffff8022ffca>) bash-10653 1d..2 4us : activate_task+0x2d/0x3f <ffffffff8022ffeb> (enqueue_task+0xe/0x66 <ffffffff8022ff66>) bash-10653 1d..2 5us : enqueue_task+0x5b/0x66 <ffffffff8022ffb3> (enqueue_task_rt+0x9/0x3c <ffffffff80233351>) bash-10653 1d..2 6us : try_to_wake_up+0x2ba/0x2e7 <ffffffff80233e18> (check_preempt_wakeup+0x12/0x99 <ffffffff80234f84>) [...] bash-10653 1d..5 33us : tracing_record_cmdline+0xcf/0xd4 <ffffffff80338aad> (_spin_unlock+0x9/0x33 <ffffffff8048d3ec>) bash-10653 1d..5 34us : _spin_unlock+0x19/0x33 <ffffffff8048d3fc> (sub_preempt_count+0xc/0x7a <ffffffff8023309e>) bash-10653 1d..4 35us : wakeup_sched_switch+0x65/0x2ff <ffffffff80339f66> (_spin_lock_irqsave+0xc/0xa9 <ffffffff8048d08b>) bash-10653 1d..4 35us : _spin_lock_irqsave+0x19/0xa9 <ffffffff8048d098> (add_preempt_count+0xe/0x77 <ffffffff8023311a>) bash-10653 1d..4 36us : sched_switch_callback+0x73/0x81 <ffffffff80338d2f> (schedule+0x483/0x6d5 <ffffffff8048b3ee>) vim:ft=help ============ The [...] was added here to not waste your email box space. Signed-off-by: Steven Rostedt <srostedt@redhat.com> Signed-off-by: Ingo Molnar <mingo@elte.hu> Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
2008-05-13 03:20:42 +08:00
/* totally disable ftrace - can not re-enable after this */
void ftrace_kill(void);
static inline void tracer_disable(void)
{
#ifdef CONFIG_FUNCTION_TRACER
ftrace_enabled = 0;
#endif
}
/*
* Ftrace disable/restore without lock. Some synchronization mechanism
* must be used to prevent ftrace_enabled to be changed between
* disable/restore.
*/
static inline int __ftrace_enabled_save(void)
{
#ifdef CONFIG_FUNCTION_TRACER
int saved_ftrace_enabled = ftrace_enabled;
ftrace_enabled = 0;
return saved_ftrace_enabled;
#else
return 0;
#endif
}
static inline void __ftrace_enabled_restore(int enabled)
{
#ifdef CONFIG_FUNCTION_TRACER
ftrace_enabled = enabled;
#endif
}
/* All archs should have this, but we define it for consistency */
#ifndef ftrace_return_address0
# define ftrace_return_address0 __builtin_return_address(0)
#endif
/* Archs may use other ways for ADDR1 and beyond */
#ifndef ftrace_return_address
# ifdef CONFIG_FRAME_POINTER
# define ftrace_return_address(n) __builtin_return_address(n)
# else
# define ftrace_return_address(n) 0UL
# endif
#endif
#define CALLER_ADDR0 ((unsigned long)ftrace_return_address0)
#define CALLER_ADDR1 ((unsigned long)ftrace_return_address(1))
#define CALLER_ADDR2 ((unsigned long)ftrace_return_address(2))
#define CALLER_ADDR3 ((unsigned long)ftrace_return_address(3))
#define CALLER_ADDR4 ((unsigned long)ftrace_return_address(4))
#define CALLER_ADDR5 ((unsigned long)ftrace_return_address(5))
#define CALLER_ADDR6 ((unsigned long)ftrace_return_address(6))
ftrace: tracer for scheduler wakeup latency This patch adds the tracer that tracks the wakeup latency of the highest priority waking task. "wakeup" is added to /debugfs/tracing/available_tracers Also added to /debugfs/tracing tracing_max_latency holds the current max latency for the wakeup wakeup_thresh if set to other than zero, a log will be recorded for every wakeup that takes longer than the number entered in here (usecs for all counters) (deletes previous trace) Examples: (with ftrace_enabled = 0) ============ preemption latency trace v1.1.5 on 2.6.24-rc8 Signed-off-by: Ingo Molnar <mingo@elte.hu> -------------------------------------------------------------------- latency: 26 us, #2/2, CPU#1 | (M:rt VP:0, KP:0, SP:0 HP:0 #P:2) ----------------- | task: migration/0-3 (uid:0 nice:-5 policy:1 rt_prio:99) ----------------- _------=> CPU# / _-----=> irqs-off | / _----=> need-resched || / _---=> hardirq/softirq ||| / _--=> preempt-depth |||| / ||||| delay cmd pid ||||| time | caller \ / ||||| \ | / quilt-8551 0d..3 0us+: wake_up_process+0x15/0x17 <ffffffff80233e80> (sched_exec+0xc9/0x100 <ffffffff80235343>) quilt-8551 0d..4 26us : sched_switch_callback+0x73/0x81 <ffffffff80338d2f> (schedule+0x483/0x6d5 <ffffffff8048b3ee>) vim:ft=help ============ (with ftrace_enabled = 1) ============ preemption latency trace v1.1.5 on 2.6.24-rc8 -------------------------------------------------------------------- latency: 36 us, #45/45, CPU#0 | (M:rt VP:0, KP:0, SP:0 HP:0 #P:2) ----------------- | task: migration/1-5 (uid:0 nice:-5 policy:1 rt_prio:99) ----------------- _------=> CPU# / _-----=> irqs-off | / _----=> need-resched || / _---=> hardirq/softirq ||| / _--=> preempt-depth |||| / ||||| delay cmd pid ||||| time | caller \ / ||||| \ | / bash-10653 1d..3 0us : wake_up_process+0x15/0x17 <ffffffff80233e80> (sched_exec+0xc9/0x100 <ffffffff80235343>) bash-10653 1d..3 1us : try_to_wake_up+0x271/0x2e7 <ffffffff80233dcf> (sub_preempt_count+0xc/0x7a <ffffffff8023309e>) bash-10653 1d..2 2us : try_to_wake_up+0x296/0x2e7 <ffffffff80233df4> (update_rq_clock+0x9/0x20 <ffffffff802303f3>) bash-10653 1d..2 2us : update_rq_clock+0x1e/0x20 <ffffffff80230408> (__update_rq_clock+0xc/0x90 <ffffffff80230366>) bash-10653 1d..2 3us : __update_rq_clock+0x1b/0x90 <ffffffff80230375> (sched_clock+0x9/0x29 <ffffffff80214529>) bash-10653 1d..2 4us : try_to_wake_up+0x2a6/0x2e7 <ffffffff80233e04> (activate_task+0xc/0x3f <ffffffff8022ffca>) bash-10653 1d..2 4us : activate_task+0x2d/0x3f <ffffffff8022ffeb> (enqueue_task+0xe/0x66 <ffffffff8022ff66>) bash-10653 1d..2 5us : enqueue_task+0x5b/0x66 <ffffffff8022ffb3> (enqueue_task_rt+0x9/0x3c <ffffffff80233351>) bash-10653 1d..2 6us : try_to_wake_up+0x2ba/0x2e7 <ffffffff80233e18> (check_preempt_wakeup+0x12/0x99 <ffffffff80234f84>) [...] bash-10653 1d..5 33us : tracing_record_cmdline+0xcf/0xd4 <ffffffff80338aad> (_spin_unlock+0x9/0x33 <ffffffff8048d3ec>) bash-10653 1d..5 34us : _spin_unlock+0x19/0x33 <ffffffff8048d3fc> (sub_preempt_count+0xc/0x7a <ffffffff8023309e>) bash-10653 1d..4 35us : wakeup_sched_switch+0x65/0x2ff <ffffffff80339f66> (_spin_lock_irqsave+0xc/0xa9 <ffffffff8048d08b>) bash-10653 1d..4 35us : _spin_lock_irqsave+0x19/0xa9 <ffffffff8048d098> (add_preempt_count+0xe/0x77 <ffffffff8023311a>) bash-10653 1d..4 36us : sched_switch_callback+0x73/0x81 <ffffffff80338d2f> (schedule+0x483/0x6d5 <ffffffff8048b3ee>) vim:ft=help ============ The [...] was added here to not waste your email box space. Signed-off-by: Steven Rostedt <srostedt@redhat.com> Signed-off-by: Ingo Molnar <mingo@elte.hu> Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
2008-05-13 03:20:42 +08:00
ftrace: trace irq disabled critical timings This patch adds latency tracing for critical timings (how long interrupts are disabled for). "irqsoff" is added to /debugfs/tracing/available_tracers Note: tracing_max_latency also holds the max latency for irqsoff (in usecs). (default to large number so one must start latency tracing) tracing_thresh threshold (in usecs) to always print out if irqs off is detected to be longer than stated here. If irq_thresh is non-zero, then max_irq_latency is ignored. Here's an example of a trace with ftrace_enabled = 0 ======= preemption latency trace v1.1.5 on 2.6.24-rc7 Signed-off-by: Ingo Molnar <mingo@elte.hu> -------------------------------------------------------------------- latency: 100 us, #3/3, CPU#1 | (M:rt VP:0, KP:0, SP:0 HP:0 #P:2) ----------------- | task: swapper-0 (uid:0 nice:0 policy:0 rt_prio:0) ----------------- => started at: _spin_lock_irqsave+0x2a/0xb7 => ended at: _spin_unlock_irqrestore+0x32/0x5f _------=> CPU# / _-----=> irqs-off | / _----=> need-resched || / _---=> hardirq/softirq ||| / _--=> preempt-depth |||| / ||||| delay cmd pid ||||| time | caller \ / ||||| \ | / swapper-0 1d.s3 0us+: _spin_lock_irqsave+0x2a/0xb7 (e1000_update_stats+0x47/0x64c [e1000]) swapper-0 1d.s3 100us : _spin_unlock_irqrestore+0x32/0x5f (e1000_update_stats+0x641/0x64c [e1000]) swapper-0 1d.s3 100us : trace_hardirqs_on_caller+0x75/0x89 (_spin_unlock_irqrestore+0x32/0x5f) vim:ft=help ======= And this is a trace with ftrace_enabled == 1 ======= preemption latency trace v1.1.5 on 2.6.24-rc7 -------------------------------------------------------------------- latency: 102 us, #12/12, CPU#1 | (M:rt VP:0, KP:0, SP:0 HP:0 #P:2) ----------------- | task: swapper-0 (uid:0 nice:0 policy:0 rt_prio:0) ----------------- => started at: _spin_lock_irqsave+0x2a/0xb7 => ended at: _spin_unlock_irqrestore+0x32/0x5f _------=> CPU# / _-----=> irqs-off | / _----=> need-resched || / _---=> hardirq/softirq ||| / _--=> preempt-depth |||| / ||||| delay cmd pid ||||| time | caller \ / ||||| \ | / swapper-0 1dNs3 0us+: _spin_lock_irqsave+0x2a/0xb7 (e1000_update_stats+0x47/0x64c [e1000]) swapper-0 1dNs3 46us : e1000_read_phy_reg+0x16/0x225 [e1000] (e1000_update_stats+0x5e2/0x64c [e1000]) swapper-0 1dNs3 46us : e1000_swfw_sync_acquire+0x10/0x99 [e1000] (e1000_read_phy_reg+0x49/0x225 [e1000]) swapper-0 1dNs3 46us : e1000_get_hw_eeprom_semaphore+0x12/0xa6 [e1000] (e1000_swfw_sync_acquire+0x36/0x99 [e1000]) swapper-0 1dNs3 47us : __const_udelay+0x9/0x47 (e1000_read_phy_reg+0x116/0x225 [e1000]) swapper-0 1dNs3 47us+: __delay+0x9/0x50 (__const_udelay+0x45/0x47) swapper-0 1dNs3 97us : preempt_schedule+0xc/0x84 (__delay+0x4e/0x50) swapper-0 1dNs3 98us : e1000_swfw_sync_release+0xc/0x55 [e1000] (e1000_read_phy_reg+0x211/0x225 [e1000]) swapper-0 1dNs3 99us+: e1000_put_hw_eeprom_semaphore+0x9/0x35 [e1000] (e1000_swfw_sync_release+0x50/0x55 [e1000]) swapper-0 1dNs3 101us : _spin_unlock_irqrestore+0xe/0x5f (e1000_update_stats+0x641/0x64c [e1000]) swapper-0 1dNs3 102us : _spin_unlock_irqrestore+0x32/0x5f (e1000_update_stats+0x641/0x64c [e1000]) swapper-0 1dNs3 102us : trace_hardirqs_on_caller+0x75/0x89 (_spin_unlock_irqrestore+0x32/0x5f) vim:ft=help ======= Signed-off-by: Steven Rostedt <srostedt@redhat.com> Signed-off-by: Ingo Molnar <mingo@elte.hu> Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
2008-05-13 03:20:42 +08:00
#ifdef CONFIG_IRQSOFF_TRACER
extern void time_hardirqs_on(unsigned long a0, unsigned long a1);
extern void time_hardirqs_off(unsigned long a0, unsigned long a1);
ftrace: trace irq disabled critical timings This patch adds latency tracing for critical timings (how long interrupts are disabled for). "irqsoff" is added to /debugfs/tracing/available_tracers Note: tracing_max_latency also holds the max latency for irqsoff (in usecs). (default to large number so one must start latency tracing) tracing_thresh threshold (in usecs) to always print out if irqs off is detected to be longer than stated here. If irq_thresh is non-zero, then max_irq_latency is ignored. Here's an example of a trace with ftrace_enabled = 0 ======= preemption latency trace v1.1.5 on 2.6.24-rc7 Signed-off-by: Ingo Molnar <mingo@elte.hu> -------------------------------------------------------------------- latency: 100 us, #3/3, CPU#1 | (M:rt VP:0, KP:0, SP:0 HP:0 #P:2) ----------------- | task: swapper-0 (uid:0 nice:0 policy:0 rt_prio:0) ----------------- => started at: _spin_lock_irqsave+0x2a/0xb7 => ended at: _spin_unlock_irqrestore+0x32/0x5f _------=> CPU# / _-----=> irqs-off | / _----=> need-resched || / _---=> hardirq/softirq ||| / _--=> preempt-depth |||| / ||||| delay cmd pid ||||| time | caller \ / ||||| \ | / swapper-0 1d.s3 0us+: _spin_lock_irqsave+0x2a/0xb7 (e1000_update_stats+0x47/0x64c [e1000]) swapper-0 1d.s3 100us : _spin_unlock_irqrestore+0x32/0x5f (e1000_update_stats+0x641/0x64c [e1000]) swapper-0 1d.s3 100us : trace_hardirqs_on_caller+0x75/0x89 (_spin_unlock_irqrestore+0x32/0x5f) vim:ft=help ======= And this is a trace with ftrace_enabled == 1 ======= preemption latency trace v1.1.5 on 2.6.24-rc7 -------------------------------------------------------------------- latency: 102 us, #12/12, CPU#1 | (M:rt VP:0, KP:0, SP:0 HP:0 #P:2) ----------------- | task: swapper-0 (uid:0 nice:0 policy:0 rt_prio:0) ----------------- => started at: _spin_lock_irqsave+0x2a/0xb7 => ended at: _spin_unlock_irqrestore+0x32/0x5f _------=> CPU# / _-----=> irqs-off | / _----=> need-resched || / _---=> hardirq/softirq ||| / _--=> preempt-depth |||| / ||||| delay cmd pid ||||| time | caller \ / ||||| \ | / swapper-0 1dNs3 0us+: _spin_lock_irqsave+0x2a/0xb7 (e1000_update_stats+0x47/0x64c [e1000]) swapper-0 1dNs3 46us : e1000_read_phy_reg+0x16/0x225 [e1000] (e1000_update_stats+0x5e2/0x64c [e1000]) swapper-0 1dNs3 46us : e1000_swfw_sync_acquire+0x10/0x99 [e1000] (e1000_read_phy_reg+0x49/0x225 [e1000]) swapper-0 1dNs3 46us : e1000_get_hw_eeprom_semaphore+0x12/0xa6 [e1000] (e1000_swfw_sync_acquire+0x36/0x99 [e1000]) swapper-0 1dNs3 47us : __const_udelay+0x9/0x47 (e1000_read_phy_reg+0x116/0x225 [e1000]) swapper-0 1dNs3 47us+: __delay+0x9/0x50 (__const_udelay+0x45/0x47) swapper-0 1dNs3 97us : preempt_schedule+0xc/0x84 (__delay+0x4e/0x50) swapper-0 1dNs3 98us : e1000_swfw_sync_release+0xc/0x55 [e1000] (e1000_read_phy_reg+0x211/0x225 [e1000]) swapper-0 1dNs3 99us+: e1000_put_hw_eeprom_semaphore+0x9/0x35 [e1000] (e1000_swfw_sync_release+0x50/0x55 [e1000]) swapper-0 1dNs3 101us : _spin_unlock_irqrestore+0xe/0x5f (e1000_update_stats+0x641/0x64c [e1000]) swapper-0 1dNs3 102us : _spin_unlock_irqrestore+0x32/0x5f (e1000_update_stats+0x641/0x64c [e1000]) swapper-0 1dNs3 102us : trace_hardirqs_on_caller+0x75/0x89 (_spin_unlock_irqrestore+0x32/0x5f) vim:ft=help ======= Signed-off-by: Steven Rostedt <srostedt@redhat.com> Signed-off-by: Ingo Molnar <mingo@elte.hu> Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
2008-05-13 03:20:42 +08:00
#else
static inline void time_hardirqs_on(unsigned long a0, unsigned long a1) { }
static inline void time_hardirqs_off(unsigned long a0, unsigned long a1) { }
ftrace: trace irq disabled critical timings This patch adds latency tracing for critical timings (how long interrupts are disabled for). "irqsoff" is added to /debugfs/tracing/available_tracers Note: tracing_max_latency also holds the max latency for irqsoff (in usecs). (default to large number so one must start latency tracing) tracing_thresh threshold (in usecs) to always print out if irqs off is detected to be longer than stated here. If irq_thresh is non-zero, then max_irq_latency is ignored. Here's an example of a trace with ftrace_enabled = 0 ======= preemption latency trace v1.1.5 on 2.6.24-rc7 Signed-off-by: Ingo Molnar <mingo@elte.hu> -------------------------------------------------------------------- latency: 100 us, #3/3, CPU#1 | (M:rt VP:0, KP:0, SP:0 HP:0 #P:2) ----------------- | task: swapper-0 (uid:0 nice:0 policy:0 rt_prio:0) ----------------- => started at: _spin_lock_irqsave+0x2a/0xb7 => ended at: _spin_unlock_irqrestore+0x32/0x5f _------=> CPU# / _-----=> irqs-off | / _----=> need-resched || / _---=> hardirq/softirq ||| / _--=> preempt-depth |||| / ||||| delay cmd pid ||||| time | caller \ / ||||| \ | / swapper-0 1d.s3 0us+: _spin_lock_irqsave+0x2a/0xb7 (e1000_update_stats+0x47/0x64c [e1000]) swapper-0 1d.s3 100us : _spin_unlock_irqrestore+0x32/0x5f (e1000_update_stats+0x641/0x64c [e1000]) swapper-0 1d.s3 100us : trace_hardirqs_on_caller+0x75/0x89 (_spin_unlock_irqrestore+0x32/0x5f) vim:ft=help ======= And this is a trace with ftrace_enabled == 1 ======= preemption latency trace v1.1.5 on 2.6.24-rc7 -------------------------------------------------------------------- latency: 102 us, #12/12, CPU#1 | (M:rt VP:0, KP:0, SP:0 HP:0 #P:2) ----------------- | task: swapper-0 (uid:0 nice:0 policy:0 rt_prio:0) ----------------- => started at: _spin_lock_irqsave+0x2a/0xb7 => ended at: _spin_unlock_irqrestore+0x32/0x5f _------=> CPU# / _-----=> irqs-off | / _----=> need-resched || / _---=> hardirq/softirq ||| / _--=> preempt-depth |||| / ||||| delay cmd pid ||||| time | caller \ / ||||| \ | / swapper-0 1dNs3 0us+: _spin_lock_irqsave+0x2a/0xb7 (e1000_update_stats+0x47/0x64c [e1000]) swapper-0 1dNs3 46us : e1000_read_phy_reg+0x16/0x225 [e1000] (e1000_update_stats+0x5e2/0x64c [e1000]) swapper-0 1dNs3 46us : e1000_swfw_sync_acquire+0x10/0x99 [e1000] (e1000_read_phy_reg+0x49/0x225 [e1000]) swapper-0 1dNs3 46us : e1000_get_hw_eeprom_semaphore+0x12/0xa6 [e1000] (e1000_swfw_sync_acquire+0x36/0x99 [e1000]) swapper-0 1dNs3 47us : __const_udelay+0x9/0x47 (e1000_read_phy_reg+0x116/0x225 [e1000]) swapper-0 1dNs3 47us+: __delay+0x9/0x50 (__const_udelay+0x45/0x47) swapper-0 1dNs3 97us : preempt_schedule+0xc/0x84 (__delay+0x4e/0x50) swapper-0 1dNs3 98us : e1000_swfw_sync_release+0xc/0x55 [e1000] (e1000_read_phy_reg+0x211/0x225 [e1000]) swapper-0 1dNs3 99us+: e1000_put_hw_eeprom_semaphore+0x9/0x35 [e1000] (e1000_swfw_sync_release+0x50/0x55 [e1000]) swapper-0 1dNs3 101us : _spin_unlock_irqrestore+0xe/0x5f (e1000_update_stats+0x641/0x64c [e1000]) swapper-0 1dNs3 102us : _spin_unlock_irqrestore+0x32/0x5f (e1000_update_stats+0x641/0x64c [e1000]) swapper-0 1dNs3 102us : trace_hardirqs_on_caller+0x75/0x89 (_spin_unlock_irqrestore+0x32/0x5f) vim:ft=help ======= Signed-off-by: Steven Rostedt <srostedt@redhat.com> Signed-off-by: Ingo Molnar <mingo@elte.hu> Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
2008-05-13 03:20:42 +08:00
#endif
#ifdef CONFIG_PREEMPT_TRACER
extern void trace_preempt_on(unsigned long a0, unsigned long a1);
extern void trace_preempt_off(unsigned long a0, unsigned long a1);
#else
/*
* Use defines instead of static inlines because some arches will make code out
* of the CALLER_ADDR, when we really want these to be a real nop.
*/
# define trace_preempt_on(a0, a1) do { } while (0)
# define trace_preempt_off(a0, a1) do { } while (0)
#endif
#ifdef CONFIG_FTRACE_MCOUNT_RECORD
extern void ftrace_init(void);
#else
static inline void ftrace_init(void) { }
#endif
tracing/function-return-tracer: set a more human readable output Impact: feature This patch sets a C-like output for the function graph tracing. For this aim, we now call two handler for each function: one on the entry and one other on return. This way we can draw a well-ordered call stack. The pid of the previous trace is loosely stored to be compared against the one of the current trace to see if there were a context switch. Without this little feature, the call tree would seem broken at some locations. We could use the sched_tracer to capture these sched_events but this way of processing is much more simpler. 2 spaces have been chosen for indentation to fit the screen while deep calls. The time of execution in nanosecs is printed just after closed braces, it seems more easy this way to find the corresponding function. If the time was printed as a first column, it would be not so easy to find the corresponding function if it is called on a deep depth. I plan to output the return value but on 32 bits CPU, the return value can be 32 or 64, and its difficult to guess on which case we are. I don't know what would be the better solution on X86-32: only print eax (low-part) or even edx (high-part). Actually it's thee same problem when a function return a 8 bits value, the high part of eax could contain junk values... Here is an example of trace: sys_read() { fget_light() { } 526 vfs_read() { rw_verify_area() { security_file_permission() { cap_file_permission() { } 519 } 1564 } 2640 do_sync_read() { pipe_read() { __might_sleep() { } 511 pipe_wait() { prepare_to_wait() { } 760 deactivate_task() { dequeue_task() { dequeue_task_fair() { dequeue_entity() { update_curr() { update_min_vruntime() { } 504 } 1587 clear_buddies() { } 512 add_cfs_task_weight() { } 519 update_min_vruntime() { } 511 } 5602 dequeue_entity() { update_curr() { update_min_vruntime() { } 496 } 1631 clear_buddies() { } 496 update_min_vruntime() { } 527 } 4580 hrtick_update() { hrtick_start_fair() { } 488 } 1489 } 13700 } 14949 } 16016 msecs_to_jiffies() { } 496 put_prev_task_fair() { } 504 pick_next_task_fair() { } 489 pick_next_task_rt() { } 496 pick_next_task_fair() { } 489 pick_next_task_idle() { } 489 ------------8<---------- thread 4 ------------8<---------- finish_task_switch() { } 1203 do_softirq() { __do_softirq() { __local_bh_disable() { } 669 rcu_process_callbacks() { __rcu_process_callbacks() { cpu_quiet() { rcu_start_batch() { } 503 } 1647 } 3128 __rcu_process_callbacks() { } 542 } 5362 _local_bh_enable() { } 587 } 8880 } 9986 kthread_should_stop() { } 669 deactivate_task() { dequeue_task() { dequeue_task_fair() { dequeue_entity() { update_curr() { calc_delta_mine() { } 511 update_min_vruntime() { } 511 } 2813 Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Acked-by: Steven Rostedt <rostedt@goodmis.org> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2008-11-26 07:57:25 +08:00
/*
* Structure that defines an entry function trace.
*/
struct ftrace_graph_ent {
unsigned long func; /* Current function */
int depth;
};
/*
* Structure that defines a return function trace.
*/
struct ftrace_graph_ret {
unsigned long func; /* Current function */
unsigned long long calltime;
unsigned long long rettime;
tracing/function-return-tracer: add the overrun field Impact: help to find the better depth of trace We decided to arbitrary define the depth of function return trace as "20". Perhaps this is not enough. To help finding an optimal depth, we measure now the overrun: the number of functions that have been missed for the current thread. By default this is not displayed, we have to do set a particular flag on the return tracer: echo overrun > /debug/tracing/trace_options And the overrun will be printed on the right. As the trace shows below, the current 20 depth is not enough. update_wall_time+0x37f/0x8c0 -> update_xtime_cache (345 ns) (Overruns: 2838) update_wall_time+0x384/0x8c0 -> clocksource_get_next (1141 ns) (Overruns: 2838) do_timer+0x23/0x100 -> update_wall_time (3882 ns) (Overruns: 2838) tick_do_update_jiffies64+0xbf/0x160 -> do_timer (5339 ns) (Overruns: 2838) tick_sched_timer+0x6a/0xf0 -> tick_do_update_jiffies64 (7209 ns) (Overruns: 2838) vgacon_set_cursor_size+0x98/0x120 -> native_io_delay (2613 ns) (Overruns: 274) vgacon_cursor+0x16e/0x1d0 -> vgacon_set_cursor_size (33151 ns) (Overruns: 274) set_cursor+0x5f/0x80 -> vgacon_cursor (36432 ns) (Overruns: 274) con_flush_chars+0x34/0x40 -> set_cursor (38790 ns) (Overruns: 274) release_console_sem+0x1ec/0x230 -> up (721 ns) (Overruns: 274) release_console_sem+0x225/0x230 -> wake_up_klogd (316 ns) (Overruns: 274) con_flush_chars+0x39/0x40 -> release_console_sem (2996 ns) (Overruns: 274) con_write+0x22/0x30 -> con_flush_chars (46067 ns) (Overruns: 274) n_tty_write+0x1cc/0x360 -> con_write (292670 ns) (Overruns: 274) smp_apic_timer_interrupt+0x2a/0x90 -> native_apic_mem_write (330 ns) (Overruns: 274) irq_enter+0x17/0x70 -> idle_cpu (413 ns) (Overruns: 274) smp_apic_timer_interrupt+0x2f/0x90 -> irq_enter (1525 ns) (Overruns: 274) ktime_get_ts+0x40/0x70 -> getnstimeofday (465 ns) (Overruns: 274) ktime_get_ts+0x60/0x70 -> set_normalized_timespec (436 ns) (Overruns: 274) ktime_get+0x16/0x30 -> ktime_get_ts (2501 ns) (Overruns: 274) hrtimer_interrupt+0x77/0x1a0 -> ktime_get (3439 ns) (Overruns: 274) Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Acked-by: Steven Rostedt <rostedt@goodmis.org> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2008-11-17 10:22:41 +08:00
/* Number of functions that overran the depth limit for current task */
unsigned long overrun;
tracing/function-return-tracer: set a more human readable output Impact: feature This patch sets a C-like output for the function graph tracing. For this aim, we now call two handler for each function: one on the entry and one other on return. This way we can draw a well-ordered call stack. The pid of the previous trace is loosely stored to be compared against the one of the current trace to see if there were a context switch. Without this little feature, the call tree would seem broken at some locations. We could use the sched_tracer to capture these sched_events but this way of processing is much more simpler. 2 spaces have been chosen for indentation to fit the screen while deep calls. The time of execution in nanosecs is printed just after closed braces, it seems more easy this way to find the corresponding function. If the time was printed as a first column, it would be not so easy to find the corresponding function if it is called on a deep depth. I plan to output the return value but on 32 bits CPU, the return value can be 32 or 64, and its difficult to guess on which case we are. I don't know what would be the better solution on X86-32: only print eax (low-part) or even edx (high-part). Actually it's thee same problem when a function return a 8 bits value, the high part of eax could contain junk values... Here is an example of trace: sys_read() { fget_light() { } 526 vfs_read() { rw_verify_area() { security_file_permission() { cap_file_permission() { } 519 } 1564 } 2640 do_sync_read() { pipe_read() { __might_sleep() { } 511 pipe_wait() { prepare_to_wait() { } 760 deactivate_task() { dequeue_task() { dequeue_task_fair() { dequeue_entity() { update_curr() { update_min_vruntime() { } 504 } 1587 clear_buddies() { } 512 add_cfs_task_weight() { } 519 update_min_vruntime() { } 511 } 5602 dequeue_entity() { update_curr() { update_min_vruntime() { } 496 } 1631 clear_buddies() { } 496 update_min_vruntime() { } 527 } 4580 hrtick_update() { hrtick_start_fair() { } 488 } 1489 } 13700 } 14949 } 16016 msecs_to_jiffies() { } 496 put_prev_task_fair() { } 504 pick_next_task_fair() { } 489 pick_next_task_rt() { } 496 pick_next_task_fair() { } 489 pick_next_task_idle() { } 489 ------------8<---------- thread 4 ------------8<---------- finish_task_switch() { } 1203 do_softirq() { __do_softirq() { __local_bh_disable() { } 669 rcu_process_callbacks() { __rcu_process_callbacks() { cpu_quiet() { rcu_start_batch() { } 503 } 1647 } 3128 __rcu_process_callbacks() { } 542 } 5362 _local_bh_enable() { } 587 } 8880 } 9986 kthread_should_stop() { } 669 deactivate_task() { dequeue_task() { dequeue_task_fair() { dequeue_entity() { update_curr() { calc_delta_mine() { } 511 update_min_vruntime() { } 511 } 2813 Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Acked-by: Steven Rostedt <rostedt@goodmis.org> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2008-11-26 07:57:25 +08:00
int depth;
};
/* Type of the callback handlers for tracing function graph*/
typedef void (*trace_func_graph_ret_t)(struct ftrace_graph_ret *); /* return */
typedef int (*trace_func_graph_ent_t)(struct ftrace_graph_ent *); /* entry */
#ifdef CONFIG_FUNCTION_GRAPH_TRACER
/* for init task */
#define INIT_FTRACE_GRAPH .ret_stack = NULL,
/*
* Stack of return addresses for functions
* of a thread.
* Used in struct thread_info
*/
struct ftrace_ret_stack {
unsigned long ret;
unsigned long func;
unsigned long long calltime;
unsigned long long subtime;
function-graph: add stack frame test In case gcc does something funny with the stack frames, or the return from function code, we would like to detect that. An arch may implement passing of a variable that is unique to the function and can be saved on entering a function and can be tested when exiting the function. Usually the frame pointer can be used for this purpose. This patch also implements this for x86. Where it passes in the stack frame of the parent function, and will test that frame on exit. There was a case in x86_32 with optimize for size (-Os) where, for a few functions, gcc would align the stack frame and place a copy of the return address into it. The function graph tracer modified the copy and not the actual return address. On return from the funtion, it did not go to the tracer hook, but returned to the parent. This broke the function graph tracer, because the return of the parent (where gcc did not do this funky manipulation) returned to the location that the child function was suppose to. This caused strange kernel crashes. This test detected the problem and pointed out where the issue was. This modifies the parameters of one of the functions that the arch specific code calls, so it includes changes to arch code to accommodate the new prototype. Note, I notice that the parsic arch implements its own push_return_trace. This is now a generic function and the ftrace_push_return_trace should be used instead. This patch does not touch that code. Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org> Cc: Paul Mackerras <paulus@samba.org> Cc: Heiko Carstens <heiko.carstens@de.ibm.com> Cc: Martin Schwidefsky <schwidefsky@de.ibm.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Helge Deller <deller@gmx.de> Cc: Kyle McMartin <kyle@mcmartin.ca> Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
2009-06-19 00:45:08 +08:00
unsigned long fp;
};
/*
* Primary handler of a function return.
* It relays on ftrace_return_to_handler.
* Defined in entry_32/64.S
*/
extern void return_to_handler(void);
extern int
function-graph: add stack frame test In case gcc does something funny with the stack frames, or the return from function code, we would like to detect that. An arch may implement passing of a variable that is unique to the function and can be saved on entering a function and can be tested when exiting the function. Usually the frame pointer can be used for this purpose. This patch also implements this for x86. Where it passes in the stack frame of the parent function, and will test that frame on exit. There was a case in x86_32 with optimize for size (-Os) where, for a few functions, gcc would align the stack frame and place a copy of the return address into it. The function graph tracer modified the copy and not the actual return address. On return from the funtion, it did not go to the tracer hook, but returned to the parent. This broke the function graph tracer, because the return of the parent (where gcc did not do this funky manipulation) returned to the location that the child function was suppose to. This caused strange kernel crashes. This test detected the problem and pointed out where the issue was. This modifies the parameters of one of the functions that the arch specific code calls, so it includes changes to arch code to accommodate the new prototype. Note, I notice that the parsic arch implements its own push_return_trace. This is now a generic function and the ftrace_push_return_trace should be used instead. This patch does not touch that code. Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org> Cc: Paul Mackerras <paulus@samba.org> Cc: Heiko Carstens <heiko.carstens@de.ibm.com> Cc: Martin Schwidefsky <schwidefsky@de.ibm.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Helge Deller <deller@gmx.de> Cc: Kyle McMartin <kyle@mcmartin.ca> Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
2009-06-19 00:45:08 +08:00
ftrace_push_return_trace(unsigned long ret, unsigned long func, int *depth,
unsigned long frame_pointer);
/*
* Sometimes we don't want to trace a function with the function
* graph tracer but we want them to keep traced by the usual function
* tracer if the function graph tracer is not configured.
*/
#define __notrace_funcgraph notrace
/*
* We want to which function is an entrypoint of a hardirq.
* That will help us to put a signal on output.
*/
#define __irq_entry __attribute__((__section__(".irqentry.text")))
/* Limits of hardirq entrypoints */
extern char __irqentry_text_start[];
extern char __irqentry_text_end[];
ftrace: Add set_graph_notrace filter The set_graph_notrace filter is analogous to set_ftrace_notrace and can be used for eliminating uninteresting part of function graph trace output. It also works with set_graph_function nicely. # cd /sys/kernel/debug/tracing/ # echo do_page_fault > set_graph_function # perf ftrace live true 2) | do_page_fault() { 2) | __do_page_fault() { 2) 0.381 us | down_read_trylock(); 2) 0.055 us | __might_sleep(); 2) 0.696 us | find_vma(); 2) | handle_mm_fault() { 2) | handle_pte_fault() { 2) | __do_fault() { 2) | filemap_fault() { 2) | find_get_page() { 2) 0.033 us | __rcu_read_lock(); 2) 0.035 us | __rcu_read_unlock(); 2) 1.696 us | } 2) 0.031 us | __might_sleep(); 2) 2.831 us | } 2) | _raw_spin_lock() { 2) 0.046 us | add_preempt_count(); 2) 0.841 us | } 2) 0.033 us | page_add_file_rmap(); 2) | _raw_spin_unlock() { 2) 0.057 us | sub_preempt_count(); 2) 0.568 us | } 2) | unlock_page() { 2) 0.084 us | page_waitqueue(); 2) 0.126 us | __wake_up_bit(); 2) 1.117 us | } 2) 7.729 us | } 2) 8.397 us | } 2) 8.956 us | } 2) 0.085 us | up_read(); 2) + 12.745 us | } 2) + 13.401 us | } ... # echo handle_mm_fault > set_graph_notrace # perf ftrace live true 1) | do_page_fault() { 1) | __do_page_fault() { 1) 0.205 us | down_read_trylock(); 1) 0.041 us | __might_sleep(); 1) 0.344 us | find_vma(); 1) 0.069 us | up_read(); 1) 4.692 us | } 1) 5.311 us | } ... Link: http://lkml.kernel.org/r/1381739066-7531-5-git-send-email-namhyung@kernel.org Signed-off-by: Namhyung Kim <namhyung@kernel.org> Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
2013-10-14 16:24:26 +08:00
#define FTRACE_NOTRACE_DEPTH 65536
#define FTRACE_RETFUNC_DEPTH 50
#define FTRACE_RETSTACK_ALLOC_SIZE 32
tracing/function-return-tracer: set a more human readable output Impact: feature This patch sets a C-like output for the function graph tracing. For this aim, we now call two handler for each function: one on the entry and one other on return. This way we can draw a well-ordered call stack. The pid of the previous trace is loosely stored to be compared against the one of the current trace to see if there were a context switch. Without this little feature, the call tree would seem broken at some locations. We could use the sched_tracer to capture these sched_events but this way of processing is much more simpler. 2 spaces have been chosen for indentation to fit the screen while deep calls. The time of execution in nanosecs is printed just after closed braces, it seems more easy this way to find the corresponding function. If the time was printed as a first column, it would be not so easy to find the corresponding function if it is called on a deep depth. I plan to output the return value but on 32 bits CPU, the return value can be 32 or 64, and its difficult to guess on which case we are. I don't know what would be the better solution on X86-32: only print eax (low-part) or even edx (high-part). Actually it's thee same problem when a function return a 8 bits value, the high part of eax could contain junk values... Here is an example of trace: sys_read() { fget_light() { } 526 vfs_read() { rw_verify_area() { security_file_permission() { cap_file_permission() { } 519 } 1564 } 2640 do_sync_read() { pipe_read() { __might_sleep() { } 511 pipe_wait() { prepare_to_wait() { } 760 deactivate_task() { dequeue_task() { dequeue_task_fair() { dequeue_entity() { update_curr() { update_min_vruntime() { } 504 } 1587 clear_buddies() { } 512 add_cfs_task_weight() { } 519 update_min_vruntime() { } 511 } 5602 dequeue_entity() { update_curr() { update_min_vruntime() { } 496 } 1631 clear_buddies() { } 496 update_min_vruntime() { } 527 } 4580 hrtick_update() { hrtick_start_fair() { } 488 } 1489 } 13700 } 14949 } 16016 msecs_to_jiffies() { } 496 put_prev_task_fair() { } 504 pick_next_task_fair() { } 489 pick_next_task_rt() { } 496 pick_next_task_fair() { } 489 pick_next_task_idle() { } 489 ------------8<---------- thread 4 ------------8<---------- finish_task_switch() { } 1203 do_softirq() { __do_softirq() { __local_bh_disable() { } 669 rcu_process_callbacks() { __rcu_process_callbacks() { cpu_quiet() { rcu_start_batch() { } 503 } 1647 } 3128 __rcu_process_callbacks() { } 542 } 5362 _local_bh_enable() { } 587 } 8880 } 9986 kthread_should_stop() { } 669 deactivate_task() { dequeue_task() { dequeue_task_fair() { dequeue_entity() { update_curr() { calc_delta_mine() { } 511 update_min_vruntime() { } 511 } 2813 Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Acked-by: Steven Rostedt <rostedt@goodmis.org> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2008-11-26 07:57:25 +08:00
extern int register_ftrace_graph(trace_func_graph_ret_t retfunc,
trace_func_graph_ent_t entryfunc);
extern bool ftrace_graph_is_dead(void);
extern void ftrace_graph_stop(void);
tracing/function-return-tracer: set a more human readable output Impact: feature This patch sets a C-like output for the function graph tracing. For this aim, we now call two handler for each function: one on the entry and one other on return. This way we can draw a well-ordered call stack. The pid of the previous trace is loosely stored to be compared against the one of the current trace to see if there were a context switch. Without this little feature, the call tree would seem broken at some locations. We could use the sched_tracer to capture these sched_events but this way of processing is much more simpler. 2 spaces have been chosen for indentation to fit the screen while deep calls. The time of execution in nanosecs is printed just after closed braces, it seems more easy this way to find the corresponding function. If the time was printed as a first column, it would be not so easy to find the corresponding function if it is called on a deep depth. I plan to output the return value but on 32 bits CPU, the return value can be 32 or 64, and its difficult to guess on which case we are. I don't know what would be the better solution on X86-32: only print eax (low-part) or even edx (high-part). Actually it's thee same problem when a function return a 8 bits value, the high part of eax could contain junk values... Here is an example of trace: sys_read() { fget_light() { } 526 vfs_read() { rw_verify_area() { security_file_permission() { cap_file_permission() { } 519 } 1564 } 2640 do_sync_read() { pipe_read() { __might_sleep() { } 511 pipe_wait() { prepare_to_wait() { } 760 deactivate_task() { dequeue_task() { dequeue_task_fair() { dequeue_entity() { update_curr() { update_min_vruntime() { } 504 } 1587 clear_buddies() { } 512 add_cfs_task_weight() { } 519 update_min_vruntime() { } 511 } 5602 dequeue_entity() { update_curr() { update_min_vruntime() { } 496 } 1631 clear_buddies() { } 496 update_min_vruntime() { } 527 } 4580 hrtick_update() { hrtick_start_fair() { } 488 } 1489 } 13700 } 14949 } 16016 msecs_to_jiffies() { } 496 put_prev_task_fair() { } 504 pick_next_task_fair() { } 489 pick_next_task_rt() { } 496 pick_next_task_fair() { } 489 pick_next_task_idle() { } 489 ------------8<---------- thread 4 ------------8<---------- finish_task_switch() { } 1203 do_softirq() { __do_softirq() { __local_bh_disable() { } 669 rcu_process_callbacks() { __rcu_process_callbacks() { cpu_quiet() { rcu_start_batch() { } 503 } 1647 } 3128 __rcu_process_callbacks() { } 542 } 5362 _local_bh_enable() { } 587 } 8880 } 9986 kthread_should_stop() { } 669 deactivate_task() { dequeue_task() { dequeue_task_fair() { dequeue_entity() { update_curr() { calc_delta_mine() { } 511 update_min_vruntime() { } 511 } 2813 Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Acked-by: Steven Rostedt <rostedt@goodmis.org> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2008-11-26 07:57:25 +08:00
/* The current handlers in use */
extern trace_func_graph_ret_t ftrace_graph_return;
extern trace_func_graph_ent_t ftrace_graph_entry;
extern void unregister_ftrace_graph(void);
extern void ftrace_graph_init_task(struct task_struct *t);
extern void ftrace_graph_exit_task(struct task_struct *t);
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 <benh@kernel.crashing.org> Suggested-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Stable Tree <stable@kernel.org> Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
2011-02-11 10:26:13 +08:00
extern void ftrace_graph_init_idle_task(struct task_struct *t, int cpu);
static inline int task_curr_ret_stack(struct task_struct *t)
{
return t->curr_ret_stack;
}
static inline void pause_graph_tracing(void)
{
atomic_inc(&current->tracing_graph_pause);
}
static inline void unpause_graph_tracing(void)
{
atomic_dec(&current->tracing_graph_pause);
}
#else /* !CONFIG_FUNCTION_GRAPH_TRACER */
#define __notrace_funcgraph
#define __irq_entry
#define INIT_FTRACE_GRAPH
static inline void ftrace_graph_init_task(struct task_struct *t) { }
static inline void ftrace_graph_exit_task(struct task_struct *t) { }
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 <benh@kernel.crashing.org> Suggested-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Stable Tree <stable@kernel.org> Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
2011-02-11 10:26:13 +08:00
static inline void ftrace_graph_init_idle_task(struct task_struct *t, int cpu) { }
static inline int register_ftrace_graph(trace_func_graph_ret_t retfunc,
trace_func_graph_ent_t entryfunc)
{
return -1;
}
static inline void unregister_ftrace_graph(void) { }
static inline int task_curr_ret_stack(struct task_struct *tsk)
{
return -1;
}
static inline void pause_graph_tracing(void) { }
static inline void unpause_graph_tracing(void) { }
#endif /* CONFIG_FUNCTION_GRAPH_TRACER */
ftrace: graph of a single function This patch adds the file: /debugfs/tracing/set_graph_function which can be used along with the function graph tracer. When this file is empty, the function graph tracer will act as usual. When the file has a function in it, the function graph tracer will only trace that function. For example: # echo blk_unplug > /debugfs/tracing/set_graph_function # cat /debugfs/tracing/trace [...] ------------------------------------------ | 2) make-19003 => kjournald-2219 ------------------------------------------ 2) | blk_unplug() { 2) | dm_unplug_all() { 2) | dm_get_table() { 2) 1.381 us | _read_lock(); 2) 0.911 us | dm_table_get(); 2) 1. 76 us | _read_unlock(); 2) + 12.912 us | } 2) | dm_table_unplug_all() { 2) | blk_unplug() { 2) 0.778 us | generic_unplug_device(); 2) 2.409 us | } 2) 5.992 us | } 2) 0.813 us | dm_table_put(); 2) + 29. 90 us | } 2) + 34.532 us | } You can add up to 32 functions into this file. Currently we limit it to 32, but this may change with later improvements. To add another function, use the append '>>': # echo sys_read >> /debugfs/tracing/set_graph_function # cat /debugfs/tracing/set_graph_function blk_unplug sys_read Using the '>' will clear out the function and write anew: # echo sys_write > /debug/tracing/set_graph_function # cat /debug/tracing/set_graph_function sys_write Note, if you have function graph running while doing this, the small time between clearing it and updating it will cause the graph to record all functions. This should not be an issue because after it sets the filter, only those functions will be recorded from then on. If you need to only record a particular function then set this file first before starting the function graph tracer. In the future this side effect may be corrected. The set_graph_function file is similar to the set_ftrace_filter but it does not take wild cards nor does it allow for more than one function to be set with a single write. There is no technical reason why this is the case, I just do not have the time yet to implement that. Note, dynamic ftrace must be enabled for this to appear because it uses the dynamic ftrace records to match the name to the mcount call sites. Signed-off-by: Steven Rostedt <srostedt@redhat.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2008-12-04 04:36:57 +08:00
#ifdef CONFIG_TRACING
/* flags for current->trace */
enum {
TSK_TRACE_FL_TRACE_BIT = 0,
TSK_TRACE_FL_GRAPH_BIT = 1,
};
enum {
TSK_TRACE_FL_TRACE = 1 << TSK_TRACE_FL_TRACE_BIT,
TSK_TRACE_FL_GRAPH = 1 << TSK_TRACE_FL_GRAPH_BIT,
};
static inline void set_tsk_trace_trace(struct task_struct *tsk)
{
set_bit(TSK_TRACE_FL_TRACE_BIT, &tsk->trace);
}
static inline void clear_tsk_trace_trace(struct task_struct *tsk)
{
clear_bit(TSK_TRACE_FL_TRACE_BIT, &tsk->trace);
}
static inline int test_tsk_trace_trace(struct task_struct *tsk)
{
return tsk->trace & TSK_TRACE_FL_TRACE;
}
static inline void set_tsk_trace_graph(struct task_struct *tsk)
{
set_bit(TSK_TRACE_FL_GRAPH_BIT, &tsk->trace);
}
static inline void clear_tsk_trace_graph(struct task_struct *tsk)
{
clear_bit(TSK_TRACE_FL_GRAPH_BIT, &tsk->trace);
}
static inline int test_tsk_trace_graph(struct task_struct *tsk)
{
return tsk->trace & TSK_TRACE_FL_GRAPH;
}
enum ftrace_dump_mode;
extern enum ftrace_dump_mode ftrace_dump_on_oops;
extern int tracepoint_printk;
extern void disable_trace_on_warning(void);
extern int __disable_trace_on_warning;
#ifdef CONFIG_PREEMPT
#define INIT_TRACE_RECURSION .trace_recursion = 0,
#endif
#else /* CONFIG_TRACING */
static inline void disable_trace_on_warning(void) { }
ftrace: graph of a single function This patch adds the file: /debugfs/tracing/set_graph_function which can be used along with the function graph tracer. When this file is empty, the function graph tracer will act as usual. When the file has a function in it, the function graph tracer will only trace that function. For example: # echo blk_unplug > /debugfs/tracing/set_graph_function # cat /debugfs/tracing/trace [...] ------------------------------------------ | 2) make-19003 => kjournald-2219 ------------------------------------------ 2) | blk_unplug() { 2) | dm_unplug_all() { 2) | dm_get_table() { 2) 1.381 us | _read_lock(); 2) 0.911 us | dm_table_get(); 2) 1. 76 us | _read_unlock(); 2) + 12.912 us | } 2) | dm_table_unplug_all() { 2) | blk_unplug() { 2) 0.778 us | generic_unplug_device(); 2) 2.409 us | } 2) 5.992 us | } 2) 0.813 us | dm_table_put(); 2) + 29. 90 us | } 2) + 34.532 us | } You can add up to 32 functions into this file. Currently we limit it to 32, but this may change with later improvements. To add another function, use the append '>>': # echo sys_read >> /debugfs/tracing/set_graph_function # cat /debugfs/tracing/set_graph_function blk_unplug sys_read Using the '>' will clear out the function and write anew: # echo sys_write > /debug/tracing/set_graph_function # cat /debug/tracing/set_graph_function sys_write Note, if you have function graph running while doing this, the small time between clearing it and updating it will cause the graph to record all functions. This should not be an issue because after it sets the filter, only those functions will be recorded from then on. If you need to only record a particular function then set this file first before starting the function graph tracer. In the future this side effect may be corrected. The set_graph_function file is similar to the set_ftrace_filter but it does not take wild cards nor does it allow for more than one function to be set with a single write. There is no technical reason why this is the case, I just do not have the time yet to implement that. Note, dynamic ftrace must be enabled for this to appear because it uses the dynamic ftrace records to match the name to the mcount call sites. Signed-off-by: Steven Rostedt <srostedt@redhat.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2008-12-04 04:36:57 +08:00
#endif /* CONFIG_TRACING */
#ifndef INIT_TRACE_RECURSION
#define INIT_TRACE_RECURSION
#endif
#ifdef CONFIG_FTRACE_SYSCALLS
unsigned long arch_syscall_addr(int nr);
#endif /* CONFIG_FTRACE_SYSCALLS */
#endif /* _LINUX_FTRACE_H */