Linux Kernel Markers
Subsystems (19)
cover Linux Kernel Markers
Hi Andrew,
Here is the latest version of the Linux Kernel Markers. I removed superfluous features that brought more complexity than needed.
It applies to 2.6.22-rc6-mm1.
It depends on the Immediate Values.
Mathieu
Signature · 3 lines
Mathieu Desnoyers Computer Engineering Ph.D. Student, Ecole Polytechnique de Montreal OpenPGP key fingerprint: 8CD5 52C3 8E3C 4140 715F BA06 3F25 A8FE 3BAE 9A68
PATCH 1/4 Linux Kernel Markers, architecture independent code.
The marker activation functions sits in kernel/marker.c. A hash table is used to keep track of the registered probes and armed markers, so the markers within a newly loaded module that should be active can be activated at module load time.
marker_query has been removed. marker_get_first, marker_get_next and marker_release should be used as iterators on the markers.
---
include/asm-generic/vmlinux.lds.h | 11 include/linux/marker.h | 136 ++++++++ include/linux/module.h | 5 kernel/marker.c | 636 ++++++++++++++++++++++++++++++++++++++ kernel/module.c | 19 + 5 files changed, 806 insertions(+), 1 deletion(-)
include/asm-generic/vmlinux.lds.h +10 -1
@@ -12,7 +12,11 @@/* .data section */ #define DATA_DATA \ *(.data) \ - *(.data.init.refok) + *(.data.init.refok) \ + . = ALIGN(8); \ + VMLINUX_SYMBOL(__start___markers) = .; \ + *(__markers) \ + VMLINUX_SYMBOL(__stop___markers) = .;#define RO_DATA (align) \ . = ALIGN((align)); \
@@ -129,6 +133,11 @@ VMLINUX_SYMBOL(__stop___immediate) = .; \ } \ \ +/* Markers: strings */ \ + __markers_strings : AT(ADDR(__markers_strings) - LOAD_OFFSET) { \ + *(__markers_strings) \ + } \ + \/* Kernel symbol table: strings */ \ __ksymtab_strings : AT(ADDR(__ksymtab_strings) - LOAD_OFFSET) { \ *(__ksymtab_strings) \
include/linux/marker.h new file +136 -0
136 lines not on this page · raw message
include/linux/module.h +5 -0
@@ -16,6 +16,7 @@#include <linux/kobject.h> #include <linux/moduleparam.h> #include <linux/immediate.h> +#include <linux/marker.h> #include <asm/local.h> #include <asm/module.h>
@@ -380,6 +381,10 @@const struct __immediate *immediate;unsigned int num_immediate;#endif +#ifdef CONFIG_MARKERS +struct __mark_marker *markers; +unsigned int num_markers; +#endif };#ifndef MODULE_ARCH_INIT #define MODULE_ARCH_INIT {}
kernel/module.c +19 -0
@@ -1625,6 +1625,8 @@unsigned int unusedgplindex;unsigned int unusedgplcrcindex;unsigned int immediateindex =0 ; +unsigned int markersindex =0 ; +unsigned int markersstringsindex =0 ;struct module *mod;long err =0 ;void *percpu =NULL , *ptr =NULL ;/* Stops spurious gcc warning */
@@ -1724,6 +1726,10 @@#ifdef CONFIG_IMMEDIATE immediateindex =find_sec (hdr, sechdrs, secstrings,"__immediate" );#endif +#ifdef CONFIG_MARKERS + markersindex =find_sec (hdr, sechdrs, secstrings,"__markers" ); + markersstringsindex =find_sec (hdr, sechdrs, secstrings,"__markers_strings" ); +#endif /* Don't keep modinfo section */ sechdrs[infoindex].sh_flags &= ~(unsigned long )SHF_ALLOC ;
@@ -1883,6 +1889,10 @@ sechdrs[immediateindex].sh_size / sizeof(*mod->immediate); }#endif +if (markersindex) + sechdrs[markersindex].sh_flags |=SHF_ALLOC ; +if (markersstringsindex) + sechdrs[markersstringsindex].sh_flags |=SHF_ALLOC ; mod->unused_syms = (void *)sechdrs[unusedindex].sh_addr;if (unusedcrcindex)
@@ -1924,6 +1934,13 @@if (err <0 ) goto cleanup; } +#ifdef CONFIG_MARKERS +if (markersindex) { + mod->markers = (void *)sechdrs[markersindex].sh_addr; + mod->num_markers = + sechdrs[markersindex].sh_size /sizeof (*mod->markers); + } +#endif /* Find duplicate symbols */ err =verify_export_symbols (mod);
@@ -1948,6 +1965,8 @@ }#endif +module_marker_update (mod); +module_immediate_setup (mod); err =module_finalize (hdr, sechdrs, mod);
kernel/marker.c new file +636 -0
636 lines not on this page · raw message
Signature · 3 lines
Mathieu Desnoyers Computer Engineering Ph.D. Student, Ecole Polytechnique de Montreal OpenPGP key fingerprint: 8CD5 52C3 8E3C 4140 715F BA06 3F25 A8FE 3BAE 9A68
PATCH 1/1 Linux Kernel Markers - Architecture Independent Code Deferred Sync
Linux Kernel Markers - Architecture Independent Code Deferred Sync
Upon marker probe_unregister, we delay call to synchronize_sched() to accelerate mass unregistration (only when there is no more reference to a give module do we call synchronize_sched()). However, we need to make sure every critical region have ended before we re-arm a marker that has been unregistered and then registered back with a different probe data.
--- kernel/marker.c | 22 ++++++++++++++++++++-- 1 file changed, 20 insertions(+), 2 deletions(-)
kernel/marker.c +20 -2
@@ -30,11 +30,21 @@ extern struct __mark_marker __stop___mar/* * module_mutex nests inside markers_mutex. Markers mutex protects the builtin -* and module markers, and the hash table. +* and module markers, the hash table and deferred_sync. */ DEFINE_MUTEX (markers_mutex);/* +* Marker deferred synchronization. +* Upon marker probe_unregister, we delay call to synchronize_sched() to +* accelerate mass unregistration (only when there is no more reference to a +* give module do we call synchronize_sched()). However, we need to make sure +* every critical region have ended before we re-arm a marker that has been +* unregistered and then registered back with a different probe data. +*/ +static int deferred_sync; + +/* * Marker hash table, containing the active markers. * Protected by module_mutex. */
@@ -303,8 +313,10 @@ static inline void __marker_update_probe __stop___markers, probe_module, &refcount);/* Markers in modules. */ __marker_update_probes_modules (probe_module, &refcount); -if (probe_module && refcount ==0 ) +if (probe_module && refcount ==0 ) {synchronize_sched (); + deferred_sync =0 ; + } }#ifdef CONFIG_MODULES
@@ -353,6 +365,10 @@ int marker_probe_register(const char *na ret = -EBUSY ; goto end; } +if (deferred_sync) { +synchronize_sched (); + deferred_sync =0 ; + } ret =_add_marker (name, format, probe, pdata);if (ret) goto end;
@@ -384,6 +400,7 @@ void *marker_probe_unregister(const char/* In what module is the probe handler ? */ probe_module =__module_text_address ((unsigned long )entry->probe); pdata =_remove_marker (name); + deferred_sync =1 ;_marker_update_probes (probe_module); end:mutex_unlock (&markers_mutex);
@@ -425,6 +442,7 @@ iter_end:/* In what module is the probe handler ? */ probe_module =__module_text_address ((unsigned long )entry->probe); pdata =_remove_marker (entry->name); + deferred_sync =1 ;_marker_update_probes (probe_module); end:mutex_unlock (&markers_mutex);
Signature · 3 lines
Mathieu Desnoyers Computer Engineering Ph.D. Student, Ecole Polytechnique de Montreal OpenPGP key fingerprint: 8CD5 52C3 8E3C 4140 715F BA06 3F25 A8FE 3BAE 9A68
PATCH 1/1 Linux Kernel Markers - Architecture Independent Code - kerneldoc
Linux Kernel Markers - Architecture Independent Code - kerneldoc
Add kerneldoc to Linux Kernel Markers API.
--- include/linux/marker.h | 108 ++++++++++++++++++++++++++++++++++++++++++++----- 1 file changed, 99 insertions(+), 9 deletions(-)
include/linux/marker.h +99 -9
@@ -20,6 +20,15 @@struct module ;struct __mark_marker ; +/** +* marker_probe_func - Type of a marker probe function +* @mdata: pointer of type struct __mark_marker +* @fmt: format string +* @...: variable argument list +* +* Type of marker probe functions. They receive the mdata and need to parse the +* format string to recover the variable argument list. +*/ typedef void marker_probe_func (const struct __mark_marker *mdata,const char *fmt, ...);
@@ -88,18 +97,36 @@ extern void module_marker_update(structstatic inline void module_marker_update (struct module *mod) { }#endif /* CONFIG_MARKERS */ -/* Marker with default behavior */ +/** +* trace_mark - Marker using code patching +* @name: marker name, not quoted. +* @format: format string +* @args...: variable argument list +* +* Places a marker using optimized code patching technique (immediate_if ()) +* to be enabled. +*/ #define trace_mark(name, format, args...) \ __trace_mark(0, name, format, ## args) -/* -* Map to the generic marker. Should be used for markers in __init and __exit -* functions and in lockdep code. + +/** +* _trace_mark - Marker using variable read +* @name: marker name, not quoted. +* @format: format string +* @args...: variable argument list +* +* Places a marker using a standard memory read (_immediate_if ()) to be +* enabled. Should be used for markers in __init and __exit functions and in +* lockdep code. */ #define _trace_mark(name, format, args...) \ __trace_mark(1, name, format, ## args)#define MARK_MAX_FORMAT_LEN 1024 -/* Pass this as a format string for a marker with no argument */ + +/** +* MARK_NOARGS - Format string for a marker with no argument. +*/ #define MARK_NOARGS " "/* To be used for string format validity checking with gcc */
@@ -109,27 +136,90 @@ static inline void __mark_check_format(cextern marker_probe_func __mark_empty_function; -/* -* Connect a probe to a markers. +/** +* marker_probe_register - Connect a probe to a marker +* @name: marker name +* @format: format string +* @probe: probe handler +* @pdata: probe private data +* * pdata must be a valid allocated memory address, or NULL. +* Returns 0 if ok, error value on error. */ extern int marker_probe_register (const char *name,const char *format,marker_probe_func *probe,void *pdata); -/* +/** +* marker_probe_unregister - Disconnect a probe from a marker +* @name: marker name +* * Returns the pdata given to marker_probe_register. */ extern void *marker_probe_unregister (const char *name); -/* + +/** +* marker_probe_unregister - Disconnect a probe from a marker +* @pdata: probe private data +* * Unregister a marker by providing the registered pdata. +* Returns the pdata given to marker_probe_register. */ extern void *marker_probe_unregister_pdata (void *pdata); +/** +* marker_arm - Arm a marker +* @name: marker name +* +* Activate a marker. It keeps a reference count of the number of +* arming/disarming done. +* Returns 0 if ok, error value on error. +*/ extern int marker_arm (const char *name); + +/** +* marker_disarm - Disarm a marker +* @name: marker name +* +* Disarm a marker. It keeps a reference count of the number of arming/disarming +* done. +* Returns 0 if ok, error value on error. +*/ extern int marker_disarm (const char *name); + +/** +* marker_get_first - Get first marker to start iteration +* +* Get the first marker found in the kernel. It should have a matching +* marker_release. +*/ extern struct __mark_marker *marker_get_first (void ); + +/** +* marker_get_next - Get next marker of an iteration +* @iter: previous marker +* +* Get the next marker found in the kernel. It should get its previous marker +* from either marker_get_first() or marker_get_next(). +*/ extern struct __mark_marker *marker_get_next (struct __mark_marker *iter); + +/** +* marker_release - Release the marker iterator +* @iter: previous marker +* +* Release the ressources held to insure iterator validity. +*/ extern void marker_release (struct __mark_marker *iter); + +/** +* marker_get_pdata - Get a marker's probe private data +* @name: marker name +* +* Returns the pdata pointer, or an ERR_PTR. +* The pdata pointer should _only_ be dereferenced if the caller is the owner of +* the data, or its content could vanish. This is mostly used to confirm that a +* caller is the owner of a registered probe. +*/ extern void *marker_get_pdata (const char *name);#endif /* __KERNEL__ */
Signature · 3 lines
Mathieu Desnoyers Computer Engineering Ph.D. Student, Ecole Polytechnique de Montreal OpenPGP key fingerprint: 8CD5 52C3 8E3C 4140 715F BA06 3F25 A8FE 3BAE 9A68
Re: [PATCH] Linux Kernel Markers - Architecture Independent Code - kerneldoc
Please drop, will be replaced by linux-kernel-markers-architecture-independent-code-kerneldoc-implementation.patch
Quoted 171 lines · * Mathieu Desnoyers ([email protected]) wrote:
Linux Kernel Markers - Architecture Independent Code - kerneldoc
Add kerneldoc to Linux Kernel Markers API.
Signed-off-by Mathieu Desnoyers <[email protected]>--- include/linux/marker.h | 108 ++++++++++++++++++++++++++++++++++++++++++++----- 1 file changed, 99 insertions(+), 9 deletions(-)Index:
linux-2.6-lttng/include/linux/marker.h
===================================================================include/linux/marker.h +99
-9@@ -20,6 +20,15 @@struct module ;struct __mark_marker ; +/** +* marker_probe_func - Type of a marker probe function +* @mdata: pointer of type struct __mark_marker +* @fmt: format string +* @...: variable argument list +* +* Type of marker probe functions. They receive the mdata and need to parse the +* format string to recover the variable argument list. +*/ typedef void marker_probe_func (const struct __mark_marker *mdata,const char *fmt, ...);@@ -88,18 +97,36 @@ extern void module_marker_update(structstatic inline void module_marker_update (struct module *mod) { }#endif /* CONFIG_MARKERS */ -/* Marker with default behavior */ +/** +* trace_mark - Marker using code patching +* @name: marker name, not quoted. +* @format: format string +* @args...: variable argument list +* +* Places a marker using optimized code patching technique (immediate_if ()) +* to be enabled. +*/ #define trace_mark(name, format, args...) \ __trace_mark(0, name, format, ## args) -/* -* Map to the generic marker. Should be used for markers in __init and __exit -* functions and in lockdep code. + +/** +* _trace_mark - Marker using variable read +* @name: marker name, not quoted. +* @format: format string +* @args...: variable argument list +* +* Places a marker using a standard memory read (_immediate_if ()) to be +* enabled. Should be used for markers in __init and __exit functions and in +* lockdep code. */ #define _trace_mark(name, format, args...) \ __trace_mark(1, name, format, ## args)#define MARK_MAX_FORMAT_LEN 1024 -/* Pass this as a format string for a marker with no argument */ + +/** +* MARK_NOARGS - Format string for a marker with no argument. +*/ #define MARK_NOARGS " "/* To be used for string format validity checking with gcc */ @@ -109,27 +136,90 @@ static inline void __mark_check_format(cextern marker_probe_func __mark_empty_function; -/* -* Connect a probe to a markers. +/** +* marker_probe_register - Connect a probe to a marker +* @name: marker name +* @format: format string +* @probe: probe handler +* @pdata: probe private data +* * pdata must be a valid allocated memory address, or NULL. +* Returns 0 if ok, error value on error. */ extern int marker_probe_register (const char *name,const char *format,marker_probe_func *probe,void *pdata); -/* +/** +* marker_probe_unregister - Disconnect a probe from a marker +* @name: marker name +* * Returns the pdata given to marker_probe_register. */ extern void *marker_probe_unregister (const char *name); -/* + +/** +* marker_probe_unregister - Disconnect a probe from a marker +* @pdata: probe private data +* * Unregister a marker by providing the registered pdata. +* Returns the pdata given to marker_probe_register. */ extern void *marker_probe_unregister_pdata (void *pdata); +/** +* marker_arm - Arm a marker +* @name: marker name +* +* Activate a marker. It keeps a reference count of the number of +* arming/disarming done. +* Returns 0 if ok, error value on error. +*/ extern int marker_arm (const char *name); + +/** +* marker_disarm - Disarm a marker +* @name: marker name +* +* Disarm a marker. It keeps a reference count of the number of arming/disarming +* done. +* Returns 0 if ok, error value on error. +*/ extern int marker_disarm (const char *name); + +/** +* marker_get_first - Get first marker to start iteration +* +* Get the first marker found in the kernel. It should have a matching +* marker_release. +*/ extern struct __mark_marker *marker_get_first (void ); + +/** +* marker_get_next - Get next marker of an iteration +* @iter: previous marker +* +* Get the next marker found in the kernel. It should get its previous marker +* from either marker_get_first() or marker_get_next(). +*/ extern struct __mark_marker *marker_get_next (struct __mark_marker *iter); + +/** +* marker_release - Release the marker iterator +* @iter: previous marker +* +* Release the ressources held to insure iterator validity. +*/ extern void marker_release (struct __mark_marker *iter); + +/** +* marker_get_pdata - Get a marker's probe private data +* @name: marker name +* +* Returns the pdata pointer, or an ERR_PTR. +* The pdata pointer should _only_ be dereferenced if the caller is the owner of +* the data, or its content could vanish. This is mostly used to confirm that a +* caller is the owner of a registered probe. +*/ extern void *marker_get_pdata (const char *name);#endif /* __KERNEL__ */ Signature · 3 lines
Mathieu Desnoyers Computer Engineering Ph.D. Student, Ecole Polytechnique de Montreal OpenPGP key fingerprint: 8CD5 52C3 8E3C 4140 715F BA06 3F25 A8FE 3BAE 9A68
Signature · 3 lines
Mathieu Desnoyers Computer Engineering Ph.D. Student, Ecole Polytechnique de Montreal OpenPGP key fingerprint: 8CD5 52C3 8E3C 4140 715F BA06 3F25 A8FE 3BAE 9A68
PATCH 1/1 Linux Kernel Markers - Architecture Independent Code Remove ifdef KERNEL
In reply to Mathieu DesnoyersLinux Kernel Markers - Architecture Independent Code Remove ifdef kernel
Remove #ifdef __KERNEL__ in marker.h.
--- include/linux/marker.h | 3 --- 1 file changed, 3 deletions(-)
include/linux/marker.h +0 -3
@@ -12,8 +12,6 @@* See the file COPYING for more details. */ -#ifdef __KERNEL__ -#include <linux/immediate.h> #include <linux/types.h>
@@ -132,5 +130,4 @@ extern struct __mark_marker *marker_get_extern void marker_release (struct __mark_marker *iter);extern void *marker_get_pdata (const char *name); -#endif /* __KERNEL__ */ #endif
Signature · 3 lines
Mathieu Desnoyers Computer Engineering Ph.D. Student, Ecole Polytechnique de Montreal OpenPGP key fingerprint: 8CD5 52C3 8E3C 4140 715F BA06 3F25 A8FE 3BAE 9A68
PATCH 1/1 Linux Kernel Markers - Architecture Independent Code - kerneldoc for implementation
Linux Kernel Markers - Architecture Independent Code - kerneldoc for implementation
Add kerneldoc to Linux Kernel Markers API.
It applies after:
"linux-kernel-markers-architecture-independent-code-remove-ifdef-kernel.patch"
--- include/linux/marker.h | 37 +++++++++++++--- kernel/marker.c | 113 ++++++++++++++++++++++++++++++++++--------------- 2 files changed, 112 insertions(+), 38 deletions(-)
include/linux/marker.h +32 -5
@@ -18,6 +18,15 @@struct module ;struct __mark_marker ; +/** +* marker_probe_func - Type of a marker probe function +* @mdata: pointer of type struct __mark_marker +* @fmt: format string +* @...: variable argument list +* +* Type of marker probe functions. They receive the mdata and need to parse the +* format string to recover the variable argument list. +*/ typedef void marker_probe_func (const struct __mark_marker *mdata,const char *fmt, ...);
@@ -86,18 +95,36 @@ extern void module_marker_update(structstatic inline void module_marker_update (struct module *mod) { }#endif /* CONFIG_MARKERS */ -/* Marker with default behavior */ +/** +* trace_mark - Marker using code patching +* @name: marker name, not quoted. +* @format: format string +* @args...: variable argument list +* +* Places a marker using optimized code patching technique (immediate_if ()) +* to be enabled. +*/ #define trace_mark(name, format, args...) \ __trace_mark(0, name, format, ## args) -/* -* Map to the generic marker. Should be used for markers in __init and __exit -* functions and in lockdep code. + +/** +* _trace_mark - Marker using variable read +* @name: marker name, not quoted. +* @format: format string +* @args...: variable argument list +* +* Places a marker using a standard memory read (_immediate_if ()) to be +* enabled. Should be used for markers in __init and __exit functions and in +* lockdep code. */ #define _trace_mark(name, format, args...) \ __trace_mark(1, name, format, ## args)#define MARK_MAX_FORMAT_LEN 1024 -/* Pass this as a format string for a marker with no argument */ + +/** +* MARK_NOARGS - Format string for a marker with no argument. +*/ #define MARK_NOARGS " "/* To be used for string format validity checking with gcc */
kernel/marker.c +80 -33
204 lines not on this page · raw message
Signature · 3 lines
Mathieu Desnoyers Computer Engineering Ph.D. Student, Ecole Polytechnique de Montreal OpenPGP key fingerprint: 8CD5 52C3 8E3C 4140 715F BA06 3F25 A8FE 3BAE 9A68
Re: [PATCH] Linux Kernel Markers - Architecture Independent Code - kerneldoc for implementation
Please drop: it came from the wrong email. I will resend.
Quoted 301 lines · * Mathieu Desnoyers ([email protected]) wrote:
Linux Kernel Markers - Architecture Independent Code - kerneldoc for implementation
Add kerneldoc to Linux Kernel Markers API.
It applies after:
"linux-kernel-markers-architecture-independent-code-remove-ifdef-kernel.patch"Signed-off-by Mathieu Desnoyers <[email protected]>--- include/linux/marker.h | 37 +++++++++++++--- kernel/marker.c | 113 ++++++++++++++++++++++++++++++++++--------------- 2 files changed, 112 insertions(+), 38 deletions(-)Index:
linux-2.6-lttng/include/linux/marker.h
===================================================================include/linux/marker.h +32
-5@@ -18,6 +18,15 @@struct module ;struct __mark_marker ; +/** +* marker_probe_func - Type of a marker probe function +* @mdata: pointer of type struct __mark_marker +* @fmt: format string +* @...: variable argument list +* +* Type of marker probe functions. They receive the mdata and need to parse the +* format string to recover the variable argument list. +*/ typedef void marker_probe_func (const struct __mark_marker *mdata,const char *fmt, ...);@@ -86,18 +95,36 @@ extern void module_marker_update(structstatic inline void module_marker_update (struct module *mod) { }#endif /* CONFIG_MARKERS */ -/* Marker with default behavior */ +/** +* trace_mark - Marker using code patching +* @name: marker name, not quoted. +* @format: format string +* @args...: variable argument list +* +* Places a marker using optimized code patching technique (immediate_if ()) +* to be enabled. +*/ #define trace_mark(name, format, args...) \ __trace_mark(0, name, format, ## args) -/* -* Map to the generic marker. Should be used for markers in __init and __exit -* functions and in lockdep code. + +/** +* _trace_mark - Marker using variable read +* @name: marker name, not quoted. +* @format: format string +* @args...: variable argument list +* +* Places a marker using a standard memory read (_immediate_if ()) to be +* enabled. Should be used for markers in __init and __exit functions and in +* lockdep code. */ #define _trace_mark(name, format, args...) \ __trace_mark(1, name, format, ## args)#define MARK_MAX_FORMAT_LEN 1024 -/* Pass this as a format string for a marker with no argument */ + +/** +* MARK_NOARGS - Format string for a marker with no argument. +*/ #define MARK_NOARGS " "/* To be used for string format validity checking with gcc */ Index:
linux-2.6-lttng/kernel/marker.c
===================================================================kernel/marker.c +80
-33@@ -62,7 +62,12 @@ struct marker_entry {static struct hlist_head marker_table[MARKER_TABLE_SIZE ]; -/* +/** +* __mark_empty_function - Empty probe callback +* @mdata: pointer of type const struct __mark_marker +* @fmt: format string +* @...: variable argument list +* * Empty callback provided as a probe to the markers. By providing this to a * disabled marker, we makes sure the execution flow is always valid even * though the function pointer change and the marker enabling are two distinct @@ -199,7 +204,9 @@ static int _marker_set_format(struct marreturn 0 ; } -/* Sets the probe callback corresponding to one marker. */ +/* +* Sets the probe callback corresponding to one marker. +*/ static int _set_marker (struct marker_entry **entry,struct __mark_marker *elem) {@@ -320,11 +327,13 @@ static inline void __marker_update_probe }#ifdef CONFIG_MODULES -/* +/** +* module_marker_update - Update module's markers +* @mod: pointer of type struct module identifying the target module +* * Setup the marker according to the data present in the marker hash table -* upon module load. If an error occur during the set probe range, -* refuse to load the module. Must be called with module_mutex held. -* Since the probe_module parameter is NULL, it is safe for refcount to be NULL. +* upon module load. Must be called with module_mutex held. Since the +* probe_module parameter is NULL, it is safe for refcount to be NULL. */ void module_marker_update (struct module *mod) {@@ -334,7 +343,8 @@ void module_marker_update(struct module }/* -* Update the system wide probes, with modules. */ +* Update the system wide probes, with modules. +*/ static inline void _marker_update_probes (struct module *probe_module) {mutex_lock (&module_mutex);@@ -342,16 +352,24 @@ static inline void _marker_update_probes mutex_unlock(&module_mutex); }#else -/* Update the system wide probes, without modules. */ +/* +* Update the system wide probes, without modules. +*/ static inline void _marker_update_probes (struct module *probe_module) {__marker_update_probes (probe_module); }#endif -/* -* Register a probe : set the callback for each marker. -* Markers must be disarmed to be registered. +/** +* marker_probe_register - Connect a probe to a marker +* @name: marker name +* @format: format string +* @probe: probe handler +* @pdata: probe private data +* +* pdata must be a valid allocated memory address, or NULL. +* Returns 0 if ok, error value on error. */ int marker_probe_register (const char *name,const char *format,marker_probe_func *probe,void *pdata)@@ -379,10 +397,11 @@ end: }EXPORT_SYMBOL_GPL (marker_probe_register); -/* -* Unregister a probe : unset the callback for each marker. -* returns the pdata if ok. -* else, returns a ERR_PTR(). +/** +* marker_probe_unregister - Disconnect a probe from a marker +* @name: marker name +* +* Returns the pdata given to marker_probe_register, or an ERR_PTR(). */ void *marker_probe_unregister (const char *name) {@@ -408,11 +427,12 @@ end: }EXPORT_SYMBOL_GPL (marker_probe_unregister); -/* -* Unregister a probe by pdata : unset the callback for each marker. -* Markers must be disarmed to be unregistered. -* returns the pdata if ok. -* else, returns a ERR_PTR(). +/** +* marker_probe_unregister - Disconnect a probe from a marker +* @pdata: probe private data +* +* Unregister a marker by providing the registered pdata. +* Returns the pdata given to marker_probe_register, or an ERR_PTR(). */ void *marker_probe_unregister_pdata (void *pdata) {@@ -450,9 +470,13 @@ end: }EXPORT_SYMBOL_GPL (marker_probe_unregister_pdata); -/* -* Arm the probe : arm the immediate values. -* A probe must have been previously registered. +/** +* marker_arm - Arm a marker +* @name: marker name +* +* Activate a marker. It keeps a reference count of the number of +* arming/disarming done. +* Returns 0 if ok, error value on error. */ int marker_arm (const char *name) {@@ -477,9 +501,13 @@ end: }EXPORT_SYMBOL_GPL (marker_arm); -/* -* Disarm the probe : disarm the immediate and set the empty callback for each -* marker. +/** +* marker_disarm - Disarm a marker +* @name: marker name +* +* Disarm a marker. It keeps a reference count of the number of arming/disarming +* done. +* Returns 0 if ok, error value on error. */ int marker_disarm (const char *name) {@@ -510,6 +538,15 @@ end: }EXPORT_SYMBOL_GPL (marker_disarm); +/** +* marker_get_pdata - Get a marker's probe private data +* @name: marker name +* +* Returns the pdata pointer, or an ERR_PTR. +* The pdata pointer should _only_ be dereferenced if the caller is the owner of +* the data, or its content could vanish. This is mostly used to confirm that a +* caller is the owner of a registered probe. +*/ void *marker_get_pdata (const char *name) {struct hlist_head *head;@@ -530,7 +567,6 @@ void *marker_get_pdata(const char *name) }EXPORT_SYMBOL_GPL (marker_get_pdata); -/* * No markers are added to the core marker section, no lock needed. * Must be called with modules mutex held for modules markers. @@ -609,11 +645,12 @@ static inline int marker_get_next_module }#endif -/* -* Only need to increment the module use count. -* We allow modification of markers beneath us, since we only want to output -* their information. -* Returns NULL when it reaches the last marker. +/** +* marker_get_next - Get next marker of an iteration +* @iter: previous marker +* +* Get the next marker found in the kernel. It should get its previous marker +* from either marker_get_first() or marker_get_next(). */ struct __mark_marker *marker_get_next (struct __mark_marker *cur) {@@ -635,13 +672,23 @@ end: }EXPORT_SYMBOL_GPL (marker_get_next); +/** +* marker_get_first - Get first marker to start iteration +* +* Get the first marker found in the kernel. It should have a matching +* marker_release. +*/ struct __mark_marker *marker_get_first (void ) {return marker_get_next (NULL ); }EXPORT_SYMBOL_GPL (marker_get_first); -/* +/** +* marker_release - Release the marker iterator +* @iter: previous marker +* +* Release the ressources held to insure iterator validity. * FIXME: suboptimal * Gets the markers until the end, so no module refcount is held when the * function ends. Signature · 4 lines
-- Mathieu Desnoyers Computer Engineering Ph.D. Student, Ecole Polytechnique de Montreal OpenPGP key fingerprint: 8CD5 52C3 8E3C 4140 715F BA06 3F25 A8FE 3BAE 9A68
Signature · 3 lines
Mathieu Desnoyers Computer Engineering Ph.D. Student, Ecole Polytechnique de Montreal OpenPGP key fingerprint: 8CD5 52C3 8E3C 4140 715F BA06 3F25 A8FE 3BAE 9A68
PATCH 1/1 Linux Kernel Markers - Architecture Independent Code - kerneldoc for implementation
In reply to Mathieu DesnoyersLinux Kernel Markers - Architecture Independent Code - kerneldoc for implementation
Add kerneldoc to Linux Kernel Markers API.
It applies after "linux-kernel-markers-architecture-independent-code-remove-ifdef-kernel.patch"
--- include/linux/marker.h | 37 +++++++++++++--- kernel/marker.c | 113 ++++++++++++++++++++++++++++++++++--------------- 2 files changed, 112 insertions(+), 38 deletions(-)
include/linux/marker.h +32 -5
@@ -18,6 +18,15 @@struct module ;struct __mark_marker ; +/** +* marker_probe_func - Type of a marker probe function +* @mdata: pointer of type struct __mark_marker +* @fmt: format string +* @...: variable argument list +* +* Type of marker probe functions. They receive the mdata and need to parse the +* format string to recover the variable argument list. +*/ typedef void marker_probe_func (const struct __mark_marker *mdata,const char *fmt, ...);
@@ -86,18 +95,36 @@ extern void module_marker_update(structstatic inline void module_marker_update (struct module *mod) { }#endif /* CONFIG_MARKERS */ -/* Marker with default behavior */ +/** +* trace_mark - Marker using code patching +* @name: marker name, not quoted. +* @format: format string +* @args...: variable argument list +* +* Places a marker using optimized code patching technique (immediate_if ()) +* to be enabled. +*/ #define trace_mark(name, format, args...) \ __trace_mark(0, name, format, ## args) -/* -* Map to the generic marker. Should be used for markers in __init and __exit -* functions and in lockdep code. + +/** +* _trace_mark - Marker using variable read +* @name: marker name, not quoted. +* @format: format string +* @args...: variable argument list +* +* Places a marker using a standard memory read (_immediate_if ()) to be +* enabled. Should be used for markers in __init and __exit functions and in +* lockdep code. */ #define _trace_mark(name, format, args...) \ __trace_mark(1, name, format, ## args)#define MARK_MAX_FORMAT_LEN 1024 -/* Pass this as a format string for a marker with no argument */ + +/** +* MARK_NOARGS - Format string for a marker with no argument. +*/ #define MARK_NOARGS " "/* To be used for string format validity checking with gcc */
kernel/marker.c +80 -33
204 lines not on this page · raw message
Signature · 3 lines
Mathieu Desnoyers Computer Engineering Ph.D. Student, Ecole Polytechnique de Montreal OpenPGP key fingerprint: 8CD5 52C3 8E3C 4140 715F BA06 3F25 A8FE 3BAE 9A68
PATCH 2/4 Linux Kernel Markers - Add kconfig menus for the marker code
In reply to Mathieu DesnoyersWith the increasing complexity of today's user-space application and the wide deployment of SMP systems, the users need an increasing understanding of the behavior and performance of a system across multiple processes/different execution contexts/multiple CPUs. In applications such as large clusters (Google, IBM), video acquisition (Autodesk), embedded real-time systems (Wind River, Monta Vista, Sony) or sysadmin/programmer-type tasks (SystemTAP from Redhat), a tool that permits tracing of kernel-user space interaction becomes necessary.
Usage of such tools have been made to successfully pinpoint problems such as:
latency issues in a user-space video acquisition application, slowdown problems in large clusters due to a switch to a different filesystems with a different cache size, abnormal Linux scheduler latency (just to name a few that I have personally investigated).
The currently existing solutions does not give a system-wide overview of what
- and when - things are happening on the system. Ptracing a program works with few processes, but quickly becomes useless when it comes to keeping track of many processes.
Bugs occuring because of bad interaction of such complex systems can be very hard to find due to the fact that they occur rarely (sometimes once a week on hundreds of machines). One can therefore only hope at having the best conditions to statistically reproduce the bug while extracting information from the system. Some bugs have been successfully found at Google using their ktrace tracer only because they could enable it on production machines and therefore recreate the same context where the bug happened.
Therefore, it makes sense to offer an instrumentation set of the most relevant events occurring in the Linux that can have the smallest performance cost possible when not active while not requiring a reboot of a production system to activate. This is essentially what the markers are providing.
Since we cannot limit the growth of the Linux kernel, nor can we pre-determine each and every "interesting" instrumentation within each subsystem and driver, it is sensible to let this task to the persons who knows the best their code. Adding instrumentation should therefore be as easy as adding and maintaining a "printk" in the kernel code from the developer's point of view.
Towards a complete tracing mechanism in the Linux kernel, the markers are only one step forward. The following step is to connect probes to those markers that will record the tracing information in buffers exported to user-space, organized in timestamped "events". Probe callbacks are responsible for serializing the information passed as parameter to the markers (described by the format string) into the events. A control mechanism to activate/stop the tracing is required, as well as a daemon that maps the buffers to write them to disk or send them through the network.
Keeping track of the events also requires a centralized infrastructure : the idea is to assign a unique ID to each event so they can be later recognized in the trace. Keeping in mind that recording the complete instrumentation site name string for each event would be more that inefficient, assigning a numeric unique identifier makes sense.
Finally, support for gathering events coming from user-space, with a minimal performance impact, is very useful to see the interaction between the system's execution contexts.
The last steps are currently implemented in Linux Trace Toolkit Next Generation (LTTng).
The SystemTAP project could clearly benefit from such an infrastructure for tracing. In addition, they would be providing support for dynamic addition of kernel probes through breakpoints/jumps when possible, with the associated restrictions (accessing local variables, reentrancy, speed).
This marker infrastructure is a hook-callback mechanism. It is meant to have an impact as low as possible on the system performances when no callback (probe) is connected so markers (hooks) can be compiled into a production kernel without noticeable slowdown.
Why use the markers instead of kprobes?
The rationale behind this mechanism the following :
1 - It makes sense to have instrumentation (for tracing, profiling)
within the kernel source tree so that it can follow its evolution. Other options, such as kprobes, imply maintaining an external set of instrumentation that must be adapted to each kernel version. Although it may make sense for distributions, it is not well suited for kernel developers, since they rarely work on a major distribution image.
2 - kprobes, although being a very good attempt at providing a dynamic
hooking mechanism that has no impact when disabled, suffers from important limitations :
a - It cannot access local variables of a function at a particular
point within its body that will be consistent thorough the kernel versions without involving a lot of recurrent hair-pulling.
b - Kprobes is slow, since it involves going though a trap each time
a probe site is executed. Even though the djprobes project made a good effort to make things faster, it cannot currently instrument fully-preemptible kernels and does not solve (1), (2a) and (2c).
c - On the reentrancy side, going though a trap (thus playing with
interrupt enable/disable) and taking spinlocks are not suited to some code paths, i.e. :
kernel/lockdep.c, printk (within the lockdep_on()/lockdep_off()). It must be understood that some code paths interesting for instrumentation often present a particular reentrancy challenge.
Some more details :
The probe callback connection to its markers is done dynamically. A predicted branch (see the immediate values infrastructure) is used to skip the hook stack setup and function call when the marker is "disabled" (no probe is connected). Further optimizations can be implemented for each architecture to make this branch faster.
Instrumentation of a subsystem becomes therefore a straightforward task. One has to add instrumentation within the key locations of the kernel code in the following form :
trace_mark(subsystem_event, "%d %p", myint, myptr);
Jim Keniston <[email protected]> adds:
kprobes remains a vital foundation for SystemTap. But markers are attactive as an alternate source of trace/debug info. Here's why:
1. Markers will live in the kernel and presumably be kept up to date by the maintainers of the enclosing code. We have a growing set of tapsets (probe libraries), each of which "knows" the source code for a certain area of the kernel. Whenever the underlying kernel code changes (e.g., a function or one of its args disappears or is renamed), there's a chance that the tapset will become invalid until we bring it back in sync with the kernel. As you can imagine, maintaining tapsets separate from the kernel source is a maintenance headache. Markers could mitigate this.
2. Because the kernel code is highly optimized, the kernel's dwarf info doesn't always accurately reflect which variables have which values on which lines (sometimes even upon entry to a function). A marker is a way to ensure that values of interest are available to SystemTap at marked points.
3. Sometimes the overhead of a kprobe probepoint is too much (either in terms of time or locking) for the particular hotspot we want to probe.
In OLS2006 proceedings, vol. 1
http://www.linuxsymposium.org/2006/linuxsymposium_procv1.pdf
Frank C. Eigler, from SystemTAP, presents its "static probing markers" (pp. 261-268) in his paper "Problem Solving With Systemtap".
He explains the advantages :
"In exchange for this effort, systemtap marker-based probes are faster and
more precise than kprobes. The better precision comes from not having to covet the compiler's favours. Such fickle favours include retaining clean boundaries in the instruction stream between interesting statements, and precisely describing positions of variables in the stack frame. Since markers don't rely on debugging information, neither favour is required, and the compiler can channel its charms into unabated optimization. The speed advantage comes from using direct call instructions rather than int 3 breakpoints to dispatch to the systemtap handlers. We will see below just how big a difference this makes."
He does a comparison of his "simple" marker solution with kprobes (his simple solution looks like my generic markers, but with a major race condition). I also posted numbers about the markers performance impact a few months ago in the initial thread. I can dig into my emails to find them for you if you consider it important for the Changelog.
He concludes with :
"To the extent that is true, we propose that these groups consider using a
shared pool of static markers as the basic kernel-side instrumentation mechanism. If they prove to have as low dormant cost and as high active performance as initial experience suggests, perhaps this could motivate the various tracing efforts and kernel subsystem developers to finally join forces. Let's designate standard trace/probe points once and for all. Tracing backends can attach to these markers the same way systemtap would. There would be no need for them to maintain kernel patches any more. Let's think about it."
This patch:
Add Kconfig menus for the marker code.
---
arch/alpha/Kconfig | 2 ++ arch/arm/Kconfig | 2 ++ arch/arm26/Kconfig | 2 ++ arch/avr32/Kconfig.debug | 7 +++++++ arch/cris/Kconfig | 2 ++ arch/frv/Kconfig | 2 ++ arch/h8300/Kconfig | 2 ++ arch/i386/Kconfig | 2 ++ arch/ia64/Kconfig | 2 ++ arch/m32r/Kconfig | 2 ++ arch/m68k/Kconfig | 2 ++ arch/m68knommu/Kconfig | 2 ++ arch/mips/Kconfig | 2 ++ arch/parisc/Kconfig | 2 ++ arch/powerpc/Kconfig | 2 ++ arch/ppc/Kconfig | 2 ++ arch/s390/Kconfig | 2 ++ arch/sh/Kconfig | 2 ++ arch/sh64/Kconfig | 2 ++ arch/sparc/Kconfig | 2 ++ arch/sparc64/Kconfig | 2 ++ arch/um/Kconfig | 2 ++ arch/v850/Kconfig | 2 ++ arch/x86_64/Kconfig | 2 ++ arch/xtensa/Kconfig | 2 ++ kernel/Kconfig.marker | 7 +++++++ kernel/Makefile | 1 + 27 files changed, 63 insertions(+)
arch/alpha/Kconfig +2 -0
@@ -657,6 +657,8 @@ source "kernel/Kconfig.immediate" +source "kernel/Kconfig.marker" + endmenu source "arch/alpha/Kconfig.debug"
arch/arm/Kconfig +2 -0
@@ -1050,6 +1050,8 @@ source "kernel/Kconfig.immediate" +source "kernel/Kconfig.marker" + endmenu source "arch/arm/Kconfig.debug"
arch/arm26/Kconfig +2 -0
@@ -248,6 +248,8 @@ source "kernel/Kconfig.immediate" +source "kernel/Kconfig.marker" + endmenu source "arch/arm26/Kconfig.debug"
arch/cris/Kconfig +2 -0
@@ -202,6 +202,8 @@ source "kernel/Kconfig.immediate" +source "kernel/Kconfig.marker" + endmenu source "arch/cris/Kconfig.debug"
arch/frv/Kconfig +2 -0
@@ -379,6 +379,8 @@ source "kernel/Kconfig.immediate" +source "kernel/Kconfig.marker" + endmenu source "arch/frv/Kconfig.debug"
arch/h8300/Kconfig +2 -0
@@ -227,6 +227,8 @@ source "kernel/Kconfig.immediate" +source "kernel/Kconfig.marker" + endmenu source "arch/h8300/Kconfig.debug"
arch/i386/Kconfig +2 -0
@@ -1251,6 +1251,8 @@ source "kernel/Kconfig.immediate" +source "kernel/Kconfig.marker" + endif # INSTRUMENTATION source "arch/i386/Kconfig.debug"
arch/ia64/Kconfig +2 -0
@@ -596,6 +596,8 @@ source "kernel/Kconfig.immediate" +source "kernel/Kconfig.marker" + endmenu source "arch/ia64/Kconfig.debug"
arch/m32r/Kconfig +2 -0
@@ -412,6 +412,8 @@ source "kernel/Kconfig.immediate" +source "kernel/Kconfig.marker" + endmenu source "arch/m32r/Kconfig.debug"
arch/m68k/Kconfig +2 -0
@@ -680,6 +680,8 @@ source "kernel/Kconfig.immediate" +source "kernel/Kconfig.marker" + endmenu source "arch/m68k/Kconfig.debug"
arch/m68knommu/Kconfig +2 -0
@@ -672,6 +672,8 @@ source "kernel/Kconfig.immediate" +source "kernel/Kconfig.marker" + endmenu source "arch/m68knommu/Kconfig.debug"
arch/mips/Kconfig +2 -0
@@ -1950,6 +1950,8 @@ source "kernel/Kconfig.immediate" +source "kernel/Kconfig.marker" + endmenu source "arch/mips/Kconfig.debug"
arch/parisc/Kconfig +2 -0
@@ -273,6 +273,8 @@ source "kernel/Kconfig.immediate" +source "kernel/Kconfig.marker" + endmenu source "arch/parisc/Kconfig.debug"
arch/powerpc/Kconfig +2 -0
@@ -658,6 +658,8 @@ source "kernel/Kconfig.immediate" +source "kernel/Kconfig.marker" + endmenu source "arch/powerpc/Kconfig.debug"
arch/ppc/Kconfig +2 -0
@@ -1457,6 +1457,8 @@ source "kernel/Kconfig.immediate" +source "kernel/Kconfig.marker" + endmenu source "arch/ppc/Kconfig.debug"
arch/s390/Kconfig +2 -0
@@ -549,6 +549,8 @@ source "kernel/Kconfig.immediate" +source "kernel/Kconfig.marker" + endmenu source "arch/s390/Kconfig.debug"
arch/sh/Kconfig +2 -0
@@ -725,6 +725,8 @@ source "kernel/Kconfig.immediate" +source "kernel/Kconfig.marker" + endmenu source "arch/sh/Kconfig.debug"
arch/sh64/Kconfig +2 -0
@@ -288,6 +288,8 @@ source "kernel/Kconfig.immediate" +source "kernel/Kconfig.marker" + endmenu source "arch/sh64/Kconfig.debug"
arch/sparc/Kconfig +2 -0
@@ -315,6 +315,8 @@ source "kernel/Kconfig.immediate" +source "kernel/Kconfig.marker" + endmenu source "arch/sparc/Kconfig.debug"
arch/sparc64/Kconfig +2 -0
@@ -454,6 +454,8 @@ source "kernel/Kconfig.immediate" +source "kernel/Kconfig.marker" + endmenu source "arch/sparc64/Kconfig.debug"
arch/um/Kconfig +2 -0
@@ -339,6 +339,8 @@ source "kernel/Kconfig.immediate" +source "kernel/Kconfig.marker" + endmenu source "arch/um/Kconfig.debug"
arch/v850/Kconfig +2 -0
@@ -335,6 +335,8 @@ source "kernel/Kconfig.immediate" +source "kernel/Kconfig.marker" + endmenu source "arch/v850/Kconfig.debug"
arch/x86_64/Kconfig +2 -0
@@ -845,6 +845,8 @@ source "kernel/Kconfig.immediate" +source "kernel/Kconfig.marker" + endmenu source "arch/x86_64/Kconfig.debug"
arch/xtensa/Kconfig +2 -0
@@ -255,6 +255,8 @@ source "kernel/Kconfig.immediate" +source "kernel/Kconfig.marker" + endmenu source "arch/xtensa/Kconfig.debug"
kernel/Kconfig.marker new file +7 -0
@@ -0,0 +1,7 @@ +# Code markers configuration + +config MARKERS + bool "Activate markers" + help + Place an empty function call at each marker site. Can be + dynamically changed for a probe function.
arch/avr32/Kconfig.debug +7 -0
@@ -9,6 +9,9 @@ menu "Instrumentation Support" depends on EXPERIMENTAL +menu "Instrumentation Support" + depends on EXPERIMENTAL + config KPROBES bool "Kprobes" depends on DEBUG_KERNEL
@@ -21,6 +24,10 @@ source "kernel/Kconfig.immediate" +source "kernel/Kconfig.marker" + +endmenu + endmenu endmenu
kernel/Makefile +1 -0
@@ -59,6 +59,7 @@ obj-$(CONFIG_TASK_DELAY_ACCT) += delayacct.o obj-$(CONFIG_TASKSTATS) += taskstats.o tsacct.o obj-$(CONFIG_IMMEDIATE) += immediate.o +obj-$(CONFIG_MARKERS) += marker.o ifneq ($(CONFIG_SCHED_NO_NO_OMIT_FRAME_POINTER),y) # According to Alan Modra <[email protected]>, the -fno-omit-frame-pointer is
Signature · 3 lines
Mathieu Desnoyers Computer Engineering Ph.D. Student, Ecole Polytechnique de Montreal OpenPGP key fingerprint: 8CD5 52C3 8E3C 4140 715F BA06 3F25 A8FE 3BAE 9A68
PATCH 3/4 Linux Kernel Markers - Documentation
In reply to Mathieu DesnoyersHere is some documentation explaining what is/how to use the Linux Kernel Markers.
---
Documentation/marker.txt | 244 +++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 244 insertions(+)
Documentation/marker.txt new file +244 -0
@@ -0,0 +1,244 @@ + Using the Linux Kernel Markers + + Mathieu Desnoyers + + +This document introduces Linux Kernel Markers and their use. It provides +examples of how to insert markers in the kernel and connect probe functions to +them and provides some examples of probe functions. + + +* Purpose of markers + +A marker placed in your code provides a hook to call a function (probe) that +you can provide at runtime. A marker can be "on" (a probe is connected to it) +or "off" (no probe is attached). When a marker is "off" it has no +effect. When a marker is "on", the function you provide is called each +time the marker is executed, in the execution context of the +caller. When the function provided ends its execution, it returns to the +caller (continuing from the marker site). + +You can put markers at important locations in the code. Markers are +lightweight hooks that can pass an arbitrary number of parameters, +described in a printk-like format string, to the attached probe function. + +They can be used for tracing and performance accounting. + + +* Usage + +In order to use the macro trace_mark, you should include linux/marker.h. + +#include <linux/marker.h> + +Add, in your code : + +trace_mark(subsystem_event, "%d %s", someint, somestring); +Where : +- subsystem_event is an identifier unique to your event + - subsystem is the name of your subsystem. + - event is the name of the event to mark. +- "%d %s" is the formatted string for the serializer. +- someint is an integer. +- somestring is a char pointer. + +Connecting a function (probe) to a marker is done by providing a probe +(function to call) for the specific marker through marker_probe_register() and +can be activated by calling marker_arm(). Marker disactivation can be done by +calling marker_disarm() as many times as marker_arm() has been called. Removing +a probe is done through marker_probe_unregister(); it will disarm the probe and +make sure there is no caller left using the probe when it returns. Probe removal +is preempt-safe because preemption is disabled around the probe call. See the +"Probe example" section below for a sample probe module. + +The marker mechanism supports inserting multiple instances of the same marker. +Markers can be put in inline functions, inlined static functions, and +unrolled loops. + + +* Optimization for a given architecture + +One can implement optimized markers for a given architecture by replacing +asm-$ARCH/marker.h. + +To force use of a non-optimized version of the markers, _trace_mark() should be +used. It takes the same parameters as the normal markers, but it does not use +the immediate values based on code patching. + + +* Probe example + +You can build the kernel modules, probe-example.ko and marker-example.ko, +using the following Makefile: +------------------------------ CUT ------------------------------------- +obj-m := probe-example.o marker-example.o +KDIR := /lib/modules/$(shell uname -r)/build +PWD := $(shell pwd) +default: + $(MAKE) -C $(KDIR) SUBDIRS=$(PWD) modules +clean: + rm -f *.mod.c *.ko *.o +------------------------------ CUT ------------------------------------- +/* probe-example.c + * + * Connects two functions to marker call sites. + * + * (C) Copyright 2007 Mathieu Desnoyers <[email protected]> + * + * This file is released under the GPLv2. + * See the file COPYING for more details. + */ + +#include <linux/sched.h> +#include <linux/kernel.h> +#include <linux/module.h> +#include <linux/marker.h> +#include <asm/atomic.h> + +struct probe_data { + const char *name; + const char *format; + marker_probe_func *probe_func; +}; + +void probe_subsystem_event(const struct __mark_marker *mdata, + const char *format, ...) +{ + va_list ap; + /* Declare args */ + unsigned int value; + const char *mystr; + + /* Assign args */ + va_start(ap, format); + value = va_arg(ap, typeof(value)); + mystr = va_arg(ap, typeof(mystr)); + + /* Call printk */ + printk("Value %u, string %s\n", value, mystr); + + /* or count, check rights, serialize data in a buffer */ + + va_end(ap); +} + +atomic_t eventb_count = ATOMIC_INIT(0); + +void probe_subsystem_eventb(const struct __mark_marker *mdata, + const char *format, ...) +{ + /* Increment counter */ + atomic_inc(&eventb_count); +} + +static struct probe_data probe_array[] = +{ + { .name = "subsystem_event", + .format = "%d %s", + .probe_func = probe_subsystem_event }, + { .name = "subsystem_eventb", + .format = MARK_NOARGS, + .probe_func = probe_subsystem_eventb }, +}; + +static int __init probe_init(void) +{ + int result; + int i; + + for (i = 0; i < ARRAY_SIZE(probe_array); i++) { + result = marker_probe_register(probe_array[i].name, + probe_array[i].format, + probe_array[i].probe_func, &probe_array[i]); + if (result) + printk(KERN_INFO "Unable to register probe %s\n", + probe_array[i].name); + result = marker_arm(probe_array[i].name); + if (result) + printk(KERN_INFO "Unable to arm probe %s\n", + probe_array[i].name); + } + return 0; +} + +static void __exit probe_fini(void) +{ + int i; + + for (i = 0; i < ARRAY_SIZE(probe_array); i++) { + marker_probe_unregister(probe_array[i].name); + } + printk("Number of event b : %u\n", atomic_read(&eventb_count)); +} + +module_init(probe_init); +module_exit(probe_fini); + +MODULE_LICENSE("GPL"); +MODULE_AUTHOR("Mathieu Desnoyers"); +MODULE_DESCRIPTION("SUBSYSTEM Probe"); +------------------------------ CUT ------------------------------------- +/* marker-example.c + * + * Executes a marker when /proc/marker-example is opened. + * + * (C) Copyright 2007 Mathieu Desnoyers <[email protected]> + * + * This file is released under the GPLv2. + * See the file COPYING for more details. + */ + +#include <linux/module.h> +#include <linux/marker.h> +#include <linux/sched.h> +#include <linux/proc_fs.h> + +struct proc_dir_entry *pentry_example = NULL; + +static int my_open(struct inode *inode, struct file *file) +{ + int i; + + trace_mark(subsystem_event, "%d %s", 123, "example string"); + for (i=0; i<10; i++) { + trace_mark(subsystem_eventb, MARK_NOARGS); + } + return -EPERM; +} + +static struct file_operations mark_ops = { + .open = my_open, +}; + +static int example_init(void) +{ + printk(KERN_ALERT "example init\n"); + pentry_example = create_proc_entry("marker-example", 0444, NULL); + if (pentry_example) + pentry_example->proc_fops = &mark_ops; + else + return -EPERM; + return 0; +} + +static void example_exit(void) +{ + printk(KERN_ALERT "example exit\n"); + remove_proc_entry("marker-example", NULL); +} + +module_init(example_init) +module_exit(example_exit) + +MODULE_LICENSE("GPL"); +MODULE_AUTHOR("Mathieu Desnoyers"); +MODULE_DESCRIPTION("Linux Trace Toolkit example"); +------------------------------ CUT ------------------------------------- +Sequence of operations : (as root) +make +insmod marker-example.ko (insmod order is not important) +insmod probe-example.ko +cat /proc/marker-example (returns an expected error) +rmmod marker-example probe-example +dmesg +------------------------------ CUT -------------------------------------
Signature · 3 lines
Mathieu Desnoyers Computer Engineering Ph.D. Student, Ecole Polytechnique de Montreal OpenPGP key fingerprint: 8CD5 52C3 8E3C 4140 715F BA06 3F25 A8FE 3BAE 9A68
PATCH 4/4 Port of blktrace to the Linux Kernel Markers.
In reply to Mathieu DesnoyersHere is the first stage of a port of blktrace to the Linux Kernel Markers. The advantage of this port is that it minimizes the impact on the running when blktrace is not active.
A few remarks : this patch has the positive effect of removing some code from the block io tracing hot paths, minimizing the i-cache impact in a system where the io tracing is compiled in but inactive.
It also moves the blk tracing code from a header (and therefore from the body of the instrumented functions) to a separate C file.
There, as soon as one device has to be traced, all devices have to execute the tracing function call when they pass by the instrumentation site. This is slower than the previous inline function which tested the condition quickly.
It does not make the code smaller, since I left all the specialized tracing functions for requests, bio, generic, remap, which would go away once a generic infrastructure is in place to serialize the information passed to the marker. This is mostly why I consider it as a step towards the full improvements that could bring the markers.
---
block/Kconfig | 1 block/blktrace.c | 342 ++++++++++++++++++++++++++++++++++++++++++- block/elevator.c | 6 block/ll_rw_blk.c | 28 +-- drivers/block/cciss.c | 4 drivers/md/dm.c | 14 - fs/bio.c | 6 include/linux/blktrace_api.h | 146 +----------------- mm/bounce.c | 4 mm/highmem.c | 2 10 files changed, 385 insertions(+), 168 deletions(-)
block/elevator.c +3 -3
@@ -32,7 +32,7 @@#include <linux/init.h> #include <linux/compiler.h> #include <linux/delay.h> -#include <linux/blktrace_api.h> +#include <linux/marker.h> #include <linux/hash.h> #include <asm/uaccess.h>
@@ -547,7 +547,7 @@unsigned ordseq;int unplug_it =1 ; -blk_add_trace_rq (q, rq,BLK_TA_INSERT ); +trace_mark (blk_request_insert,"%p %p" , q, rq); rq->q = q;
@@ -726,7 +726,7 @@* not be passed by new incoming requests */ rq->cmd_flags |=REQ_STARTED ; -blk_add_trace_rq (q, rq,BLK_TA_ISSUE ); +trace_mark (blk_request_issue,"%p %p" , q, rq); }if (!q->boundary_rq || q->boundary_rq == rq) {
block/ll_rw_blk.c +15 -13
@@ -28,6 +28,7 @@#include <linux/task_io_accounting_ops.h> #include <linux/interrupt.h> #include <linux/cpu.h> +#include <linux/marker.h> #include <linux/blktrace_api.h> #include <linux/fault-inject.h>
@@ -1551,7 +1552,7 @@if (!test_and_set_bit (QUEUE_FLAG_PLUGGED , &q->queue_flags)) {mod_timer (&q->unplug_timer, jiffies + q->unplug_delay); -blk_add_trace_generic (q,NULL ,0 ,BLK_TA_PLUG ); +trace_mark (blk_plug_device,"%p %p %d" , q,NULL ,0 ); } }
@@ -1617,7 +1618,7 @@* devices don't necessarily have an ->unplug_fn defined */ if (q->unplug_fn) { -blk_add_trace_pdu_int (q,BLK_TA_UNPLUG_IO ,NULL , +trace_mark (blk_pdu_unplug_io,"%p %p %d" , q,NULL , q->rq.count[READ ] + q->rq.count[WRITE ]); q->unplug_fn (q);
@@ -1628,7 +1629,7 @@ {request_queue_t *q =container_of (work, request_queue_t, unplug_work); -blk_add_trace_pdu_int (q,BLK_TA_UNPLUG_IO ,NULL , +trace_mark (blk_pdu_unplug_io,"%p %p %d" , q,NULL , q->rq.count[READ ] + q->rq.count[WRITE ]); q->unplug_fn (q);
@@ -1638,7 +1639,7 @@ {request_queue_t *q = (request_queue_t *)data; -blk_add_trace_pdu_int (q,BLK_TA_UNPLUG_TIMER ,NULL , +trace_mark (blk_pdu_unplug_timer,"%p %p %d" , q,NULL , q->rq.count[READ ] + q->rq.count[WRITE ]);kblockd_schedule_work (&q->unplug_work);
@@ -2150,7 +2151,7 @@rq_init (q, rq); -blk_add_trace_generic (q, bio, rw,BLK_TA_GETRQ ); +trace_mark (blk_get_request,"%p %p %d" , q, bio, rw); out:return rq; }
@@ -2180,7 +2181,7 @@if (!rq) {struct io_context *ioc; -blk_add_trace_generic (q, bio, rw,BLK_TA_SLEEPRQ ); +trace_mark (blk_sleep_request,"%p %p %d" , q, bio, rw);__generic_unplug_device (q);spin_unlock_irq (q->queue_lock);
@@ -2254,7 +2255,7 @@*/ void blk_requeue_request (request_queue_t *q,struct request *rq) { -blk_add_trace_rq (q, rq,BLK_TA_REQUEUE ); +trace_mark (blk_requeue,"%p %p" , q, rq);if (blk_rq_tagged (rq))blk_queue_end_tag (q, rq);
@@ -2940,7 +2941,7 @@if (!ll_back_merge_fn (q, req, bio))break ; -blk_add_trace_bio (q, bio,BLK_TA_BACKMERGE ); +trace_mark (blk_bio_backmerge,"%p %p" , q, bio); req->biotail->bi_next = bio; req->biotail = bio;
@@ -2957,7 +2958,7 @@if (!ll_front_merge_fn (q, req, bio))break ; -blk_add_trace_bio (q, bio,BLK_TA_FRONTMERGE ); +trace_mark (blk_bio_frontmerge,"%p %p" , q, bio); bio->bi_next = req->bio; req->bio = bio;
@@ -3187,10 +3188,11 @@blk_partition_remap (bio);if (old_sector !=-1 ) -blk_add_trace_remap (q, bio, old_dev, bio->bi_sector, - old_sector); +trace_mark (blk_remap,"%p %p %llu %llu %llu" , + q, bio, (u64 )old_dev, + (u64 )bio->bi_sector, (u64 )old_sector); -blk_add_trace_bio (q, bio,BLK_TA_QUEUE ); +trace_mark (blk_bio_queue,"%p %p" , q, bio); old_sector = bio->bi_sector; old_dev = bio->bi_bdev->bd_dev;
@@ -3383,7 +3385,7 @@int total_bytes, bio_nbytes, error, next_idx =0 ;struct bio *bio; -blk_add_trace_rq (req->q, req,BLK_TA_COMPLETE ); +trace_mark (blk_request_complete,"%p %p" , req->q, req);/* * extend uptodate bool to allow < 0 value to be direct io error
block/Kconfig +1 -0
@@ -32,6 +32,7 @@ depends on SYSFS select RELAY select DEBUG_FS + select MARKERS help Say Y here, if you want to be able to trace the block layer actions on a given queue. Tracing allows you to see any traffic happening
block/blktrace.c +340 -2
379 lines not on this page · raw message
include/linux/blktrace_api.h +11 -135
166 lines not on this page · raw message
mm/bounce.c +2 -2
@@ -13,7 +13,7 @@#include <linux/init.h> #include <linux/hash.h> #include <linux/highmem.h> -#include <linux/blktrace_api.h> +#include <linux/marker.h> #include <asm/tlbflush.h> #define POOL_SIZE 64
@@ -237,7 +237,7 @@if (!bio)return ; -blk_add_trace_bio (q, *bio_orig,BLK_TA_BOUNCE ); +trace_mark (blk_bio_bounce,"%p %p" , q, *bio_orig);/* * at least one page was bounced, fill in possible non-highmem
mm/highmem.c +1 -1
@@ -26,7 +26,7 @@#include <linux/init.h> #include <linux/hash.h> #include <linux/highmem.h> -#include <linux/blktrace_api.h> +#include <linux/marker.h> #include <asm/tlbflush.h> /*
fs/bio.c +3 -3
@@ -25,7 +25,7 @@#include <linux/module.h> #include <linux/mempool.h> #include <linux/workqueue.h> -#include <linux/blktrace_api.h> +#include <linux/marker.h> #include <scsi/sg.h> /* for struct sg_iovec */ #define BIO_POOL_SIZE 2
@@ -1081,8 +1081,8 @@if (!bp)return bp; -blk_add_trace_pdu_int (bdev_get_queue (bi->bi_bdev),BLK_TA_SPLIT , bi, - bi->bi_sector + first_sectors); +trace_mark (blk_pdu_split,"%p %p %llu" ,bdev_get_queue (bi->bi_bdev), bi, + (u64 )bi->bi_sector + first_sectors);BUG_ON (bi->bi_vcnt !=1 );BUG_ON (bi->bi_idx !=0 );
drivers/block/cciss.c +2 -2
@@ -37,7 +37,7 @@#include <linux/hdreg.h> #include <linux/spinlock.h> #include <linux/compat.h> -#include <linux/blktrace_api.h> +#include <linux/marker.h> #include <asm/uaccess.h> #include <asm/io.h>
@@ -2502,7 +2502,7 @@ } cmd->rq->data_len =0 ; cmd->rq->completion_data = cmd; -blk_add_trace_rq (cmd->rq->q, cmd->rq,BLK_TA_COMPLETE ); +trace_mark (blk_request_complete,"%p %p" , cmd->rq->q, cmd->rq);blk_complete_request (cmd->rq); }
drivers/md/dm.c +7 -7
@@ -20,7 +20,7 @@#include <linux/slab.h> #include <linux/idr.h> #include <linux/hdreg.h> -#include <linux/blktrace_api.h> +#include <linux/marker.h> #include <linux/smp_lock.h> #define DM_MSG_PREFIX "core"
@@ -489,8 +489,8 @@wake_up (&io->md->wait);if (io->error !=DM_ENDIO_REQUEUE ) { -blk_add_trace_bio (io->md->queue, io->bio, -BLK_TA_COMPLETE ); +trace_mark (blk_request_complete,"%p %p" , + io->md->queue, io->bio);bio_endio (io->bio, io->bio->bi_size, io->error); }
@@ -586,10 +586,10 @@ r = ti->type->map (ti, clone, &tio->info);if (r ==DM_MAPIO_REMAPPED ) {/* the bio has been remapped so dispatch it */ - -blk_add_trace_remap (bdev_get_queue (clone->bi_bdev), clone, - tio->io->bio->bi_bdev->bd_dev, sector, - clone->bi_sector); +trace_mark (blk_remap,"%p %p %llu %llu %llu" , +bdev_get_queue (clone->bi_bdev), clone, + (u64 )tio->io->bio->bi_bdev->bd_dev, (u64 )sector, + (u64 )clone->bi_sector);generic_make_request (clone); }else if (r <0 || r ==DM_MAPIO_REQUEUE ) {
Signature · 3 lines
Mathieu Desnoyers Computer Engineering Ph.D. Student, Ecole Polytechnique de Montreal OpenPGP key fingerprint: 8CD5 52C3 8E3C 4140 715F BA06 3F25 A8FE 3BAE 9A68