From c1504e5102384762bd06b068e9928b624a8a88c6 Mon Sep 17 00:00:00 2001 From: Ajay Kaher Date: Fri, 28 Jul 2023 23:50:46 +0530 Subject: eventfs: Implement eventfs dir creation functions Add eventfs_file structure which will hold the properties of the eventfs files and directories. Add following functions to create the directories in eventfs: eventfs_create_events_dir() will create the top level "events" directory within the tracefs file system. eventfs_add_subsystem_dir() creates an eventfs_file descriptor with the given name of the subsystem. eventfs_add_dir() creates an eventfs_file descriptor with the given name of the directory and attached to a eventfs_file of a subsystem. Add tracefs_inode structure to hold the inodes, flags and pointers to private data used by eventfs. Link: https://lkml.kernel.org/r/1690568452-46553-5-git-send-email-akaher@vmware.com Signed-off-by: Ajay Kaher Co-developed-by: Steven Rostedt (VMware) Signed-off-by: Steven Rostedt (VMware) Tested-by: Ching-lin Yu Reported-by: kernel test robot Closes: https://lore.kernel.org/oe-lkp/202305051619.9a469a9a-yujie.liu@intel.com Signed-off-by: Steven Rostedt (Google) --- include/linux/tracefs.h | 11 +++++++++++ 1 file changed, 11 insertions(+) (limited to 'include/linux') diff --git a/include/linux/tracefs.h b/include/linux/tracefs.h index 99912445974c..432e5e6f7901 100644 --- a/include/linux/tracefs.h +++ b/include/linux/tracefs.h @@ -21,6 +21,17 @@ struct file_operations; #ifdef CONFIG_TRACING +struct eventfs_file; + +struct dentry *eventfs_create_events_dir(const char *name, + struct dentry *parent); + +struct eventfs_file *eventfs_add_subsystem_dir(const char *name, + struct dentry *parent); + +struct eventfs_file *eventfs_add_dir(const char *name, + struct eventfs_file *ef_parent); + struct dentry *tracefs_create_file(const char *name, umode_t mode, struct dentry *parent, void *data, const struct file_operations *fops); -- cgit v1.3 From 88f349b4a83aab6a0fabd4230a1b6796f26bc546 Mon Sep 17 00:00:00 2001 From: Ajay Kaher Date: Fri, 28 Jul 2023 23:50:47 +0530 Subject: eventfs: Implement eventfs file add functions Add the following functions to add files to evenfs: eventfs_add_events_file() to add the data needed to create a specific file located at the top level events directory. The dentry/inode will be created when the events directory is scanned. eventfs_add_file() to add the data needed for files within the directories below the top level events directory. The dentry/inode of the file will be created when the directory that the file is in is scanned. Link: https://lkml.kernel.org/r/1690568452-46553-6-git-send-email-akaher@vmware.com Signed-off-by: Ajay Kaher Co-developed-by: Steven Rostedt (VMware) Signed-off-by: Steven Rostedt (VMware) Tested-by: Ching-lin Yu Reported-by: kernel test robot Closes: https://lore.kernel.org/oe-lkp/202305051619.9a469a9a-yujie.liu@intel.com Signed-off-by: Steven Rostedt (Google) --- fs/tracefs/event_inode.c | 86 ++++++++++++++++++++++++++++++++++++++++++++++++ include/linux/tracefs.h | 8 +++++ 2 files changed, 94 insertions(+) (limited to 'include/linux') diff --git a/fs/tracefs/event_inode.c b/fs/tracefs/event_inode.c index 8f334b122e46..9e4843be9dc9 100644 --- a/fs/tracefs/event_inode.c +++ b/fs/tracefs/event_inode.c @@ -209,3 +209,89 @@ struct eventfs_file *eventfs_add_dir(const char *name, mutex_unlock(&eventfs_mutex); return ef; } + +/** + * eventfs_add_events_file - add the data needed to create a file for later reference + * @name: the name of the file to create. + * @mode: the permission that the file should have. + * @parent: parent dentry for this file. + * @data: something that the caller will want to get to later on. + * @fop: struct file_operations that should be used for this file. + * + * This function is used to add the information needed to create a + * dentry/inode within the top level events directory. The file created + * will have the @mode permissions. The @data will be used to fill the + * inode.i_private when the open() call is done. The dentry and inodes are + * all created when they are referenced, and removed when they are no + * longer referenced. + */ +int eventfs_add_events_file(const char *name, umode_t mode, + struct dentry *parent, void *data, + const struct file_operations *fop) +{ + struct tracefs_inode *ti; + struct eventfs_inode *ei; + struct eventfs_file *ef; + + if (!parent) + return -EINVAL; + + if (!(mode & S_IFMT)) + mode |= S_IFREG; + + if (!parent->d_inode) + return -EINVAL; + + ti = get_tracefs(parent->d_inode); + if (!(ti->flags & TRACEFS_EVENT_INODE)) + return -EINVAL; + + ei = ti->private; + ef = eventfs_prepare_ef(name, mode, fop, NULL, data); + + if (IS_ERR(ef)) + return -ENOMEM; + + mutex_lock(&eventfs_mutex); + list_add_tail(&ef->list, &ei->e_top_files); + mutex_unlock(&eventfs_mutex); + return 0; +} + +/** + * eventfs_add_file - add eventfs file to list to create later + * @name: the name of the file to create. + * @mode: the permission that the file should have. + * @ef_parent: parent eventfs_file for this file. + * @data: something that the caller will want to get to later on. + * @fop: struct file_operations that should be used for this file. + * + * This function is used to add the information needed to create a + * file within a subdirectory of the events directory. The file created + * will have the @mode permissions. The @data will be used to fill the + * inode.i_private when the open() call is done. The dentry and inodes are + * all created when they are referenced, and removed when they are no + * longer referenced. + */ +int eventfs_add_file(const char *name, umode_t mode, + struct eventfs_file *ef_parent, + void *data, + const struct file_operations *fop) +{ + struct eventfs_file *ef; + + if (!ef_parent) + return -EINVAL; + + if (!(mode & S_IFMT)) + mode |= S_IFREG; + + ef = eventfs_prepare_ef(name, mode, fop, NULL, data); + if (IS_ERR(ef)) + return -ENOMEM; + + mutex_lock(&eventfs_mutex); + list_add_tail(&ef->list, &ef_parent->ei->e_top_files); + mutex_unlock(&eventfs_mutex); + return 0; +} diff --git a/include/linux/tracefs.h b/include/linux/tracefs.h index 432e5e6f7901..54c9cbd0389b 100644 --- a/include/linux/tracefs.h +++ b/include/linux/tracefs.h @@ -32,6 +32,14 @@ struct eventfs_file *eventfs_add_subsystem_dir(const char *name, struct eventfs_file *eventfs_add_dir(const char *name, struct eventfs_file *ef_parent); +int eventfs_add_file(const char *name, umode_t mode, + struct eventfs_file *ef_parent, void *data, + const struct file_operations *fops); + +int eventfs_add_events_file(const char *name, umode_t mode, + struct dentry *parent, void *data, + const struct file_operations *fops); + struct dentry *tracefs_create_file(const char *name, umode_t mode, struct dentry *parent, void *data, const struct file_operations *fops); -- cgit v1.3 From 5bdcd5f5331a276a3ddf1fba8605986d0d15298a Mon Sep 17 00:00:00 2001 From: Ajay Kaher Date: Fri, 28 Jul 2023 23:50:50 +0530 Subject: eventfs: Implement removal of meta data from eventfs When events are removed from tracefs, the eventfs must be aware of this. The eventfs_remove() removes the meta data from eventfs so that it will no longer create the files associated with that event. When an instance is removed from tracefs, eventfs_remove_events_dir() will remove and clean up the entire "events" directory. The helper function eventfs_remove_rec() is used to clean up and free the associated data from eventfs for both of the added functions. SRCU is used to protect the lists of meta data stored in the eventfs. The eventfs_mutex is used to protect the content of the items in the list. As lookups may be happening as deletions of events are made, the freeing of dentry/inodes and relative information is done after the SRCU grace period has passed. Link: https://lkml.kernel.org/r/1690568452-46553-9-git-send-email-akaher@vmware.com Signed-off-by: Ajay Kaher Co-developed-by: Steven Rostedt (VMware) Signed-off-by: Steven Rostedt (VMware) Tested-by: Ching-lin Yu Reported-by: kernel test robot Closes: https://lore.kernel.org/oe-kbuild-all/202305030611.Kas747Ev-lkp@intel.com/ Signed-off-by: Steven Rostedt (Google) --- fs/tracefs/event_inode.c | 143 +++++++++++++++++++++++++++++++++++++++++++++++ include/linux/tracefs.h | 4 ++ 2 files changed, 147 insertions(+) (limited to 'include/linux') diff --git a/fs/tracefs/event_inode.c b/fs/tracefs/event_inode.c index 5240bd2c81e7..da8d2e73cc47 100644 --- a/fs/tracefs/event_inode.c +++ b/fs/tracefs/event_inode.c @@ -198,6 +198,14 @@ void eventfs_set_ef_status_free(struct dentry *dentry) if (!ef) goto out; + /* + * If ef was freed, then the LSB bit is set for d_fsdata. + * But this should not happen, as it should still have a + * ref count that prevents it. Warn in case it does. + */ + if (WARN_ON_ONCE((unsigned long)ef & 1)) + goto out; + dentry->d_fsdata = NULL; ef->dentry = NULL; out: @@ -656,3 +664,138 @@ int eventfs_add_file(const char *name, umode_t mode, mutex_unlock(&eventfs_mutex); return 0; } + +static void free_ef(struct rcu_head *head) +{ + struct eventfs_file *ef = container_of(head, struct eventfs_file, rcu); + + kfree(ef->name); + kfree(ef->ei); + kfree(ef); +} + +/** + * eventfs_remove_rec - remove eventfs dir or file from list + * @ef: eventfs_file to be removed. + * @head: to create list of eventfs_file to be deleted + * @level: to check recursion depth + * + * The helper function eventfs_remove_rec() is used to clean up and free the + * associated data from eventfs for both of the added functions. + */ +static void eventfs_remove_rec(struct eventfs_file *ef, struct list_head *head, int level) +{ + struct eventfs_file *ef_child; + + if (!ef) + return; + /* + * Check recursion depth. It should never be greater than 3: + * 0 - events/ + * 1 - events/group/ + * 2 - events/group/event/ + * 3 - events/group/event/file + */ + if (WARN_ON_ONCE(level > 3)) + return; + + if (ef->ei) { + /* search for nested folders or files */ + list_for_each_entry_srcu(ef_child, &ef->ei->e_top_files, list, + lockdep_is_held(&eventfs_mutex)) { + eventfs_remove_rec(ef_child, head, level + 1); + } + } + + list_del_rcu(&ef->list); + list_add_tail(&ef->del_list, head); +} + +/** + * eventfs_remove - remove eventfs dir or file from list + * @ef: eventfs_file to be removed. + * + * This function acquire the eventfs_mutex lock and call eventfs_remove_rec() + */ +void eventfs_remove(struct eventfs_file *ef) +{ + struct eventfs_file *tmp; + LIST_HEAD(ef_del_list); + struct dentry *dentry_list = NULL; + struct dentry *dentry; + + if (!ef) + return; + + mutex_lock(&eventfs_mutex); + eventfs_remove_rec(ef, &ef_del_list, 0); + list_for_each_entry_safe(ef, tmp, &ef_del_list, del_list) { + if (ef->dentry) { + unsigned long ptr = (unsigned long)dentry_list; + + /* Keep the dentry from being freed yet */ + dget(ef->dentry); + + /* + * Paranoid: The dget() above should prevent the dentry + * from being freed and calling eventfs_set_ef_status_free(). + * But just in case, set the link list LSB pointer to 1 + * and have eventfs_set_ef_status_free() check that to + * make sure that if it does happen, it will not think + * the d_fsdata is an event_file. + * + * For this to work, no event_file should be allocated + * on a odd space, as the ef should always be allocated + * to be at least word aligned. Check for that too. + */ + WARN_ON_ONCE(ptr & 1); + + ef->dentry->d_fsdata = (void *)(ptr | 1); + dentry_list = ef->dentry; + ef->dentry = NULL; + } + call_srcu(&eventfs_srcu, &ef->rcu, free_ef); + } + mutex_unlock(&eventfs_mutex); + + while (dentry_list) { + unsigned long ptr; + + dentry = dentry_list; + ptr = (unsigned long)dentry->d_fsdata & ~1UL; + dentry_list = (struct dentry *)ptr; + dentry->d_fsdata = NULL; + d_invalidate(dentry); + mutex_lock(&eventfs_mutex); + /* dentry should now have at least a single reference */ + WARN_ONCE((int)d_count(dentry) < 1, + "dentry %p less than one reference (%d) after invalidate\n", + dentry, d_count(dentry)); + mutex_unlock(&eventfs_mutex); + dput(dentry); + } +} + +/** + * eventfs_remove_events_dir - remove eventfs dir or file from list + * @dentry: events's dentry to be removed. + * + * This function remove events main directory + */ +void eventfs_remove_events_dir(struct dentry *dentry) +{ + struct tracefs_inode *ti; + struct eventfs_inode *ei; + + if (!dentry || !dentry->d_inode) + return; + + ti = get_tracefs(dentry->d_inode); + if (!ti || !(ti->flags & TRACEFS_EVENT_INODE)) + return; + + ei = ti->private; + d_invalidate(dentry); + dput(dentry); + kfree(ei); +} diff --git a/include/linux/tracefs.h b/include/linux/tracefs.h index 54c9cbd0389b..009072792fa3 100644 --- a/include/linux/tracefs.h +++ b/include/linux/tracefs.h @@ -40,6 +40,10 @@ int eventfs_add_events_file(const char *name, umode_t mode, struct dentry *parent, void *data, const struct file_operations *fops); +void eventfs_remove(struct eventfs_file *ef); + +void eventfs_remove_events_dir(struct dentry *dentry); + struct dentry *tracefs_create_file(const char *name, umode_t mode, struct dentry *parent, void *data, const struct file_operations *fops); -- cgit v1.3 From 27152bceea1df27ffebb12ac9cd9adbf2c4c3f35 Mon Sep 17 00:00:00 2001 From: Ajay Kaher Date: Fri, 28 Jul 2023 23:50:51 +0530 Subject: eventfs: Move tracing/events to eventfs Up until now, /sys/kernel/tracing/events was no different than any other part of tracefs. The files and directories within the events directory was created when the tracefs was mounted, and also created for the instances in /sys/kernel/tracing/instances//events. Most of these files and directories will never be referenced. Since there are thousands of these files and directories they spend their time wasting precious memory resources. Move the "events" directory to the new eventfs. The eventfs will take the meta data of the events that they represent and store that. When the files in the events directory are referenced, the dentry and inodes to represent them are then created. When the files are no longer referenced, they are freed. This saves the precious memory resources that were wasted on these seldom referenced dentries and inodes. Running the following: ~# cat /proc/meminfo /proc/slabinfo > before.out ~# mkdir /sys/kernel/tracing/instances/foo ~# cat /proc/meminfo /proc/slabinfo > after.out to test the changes produces the following deltas: Before this change: Before after deltas for meminfo: MemFree: -32260 MemAvailable: -21496 KReclaimable: 21528 Slab: 22440 SReclaimable: 21528 SUnreclaim: 912 VmallocUsed: 16 Before after deltas for slabinfo: : [ * = ] tracefs_inode_cache: 14472 [* 1184 = 17134848] buffer_head: 24 [* 168 = 4032] hmem_inode_cache: 28 [* 1480 = 41440] dentry: 14450 [* 312 = 4508400] lsm_inode_cache: 14453 [* 32 = 462496] vma_lock: 11 [* 152 = 1672] vm_area_struct: 2 [* 184 = 368] trace_event_file: 1748 [* 88 = 153824] kmalloc-256: 1072 [* 256 = 274432] kmalloc-64: 2842 [* 64 = 181888] Total slab additions in size: 22,763,400 bytes With this change: Before after deltas for meminfo: MemFree: -12600 MemAvailable: -12580 Cached: 24 Active: 12 Inactive: 68 Inactive(anon): 48 Active(file): 12 Inactive(file): 20 Dirty: -4 AnonPages: 68 KReclaimable: 12 Slab: 1856 SReclaimable: 12 SUnreclaim: 1844 KernelStack: 16 PageTables: 36 VmallocUsed: 16 Before after deltas for slabinfo: : [ * = ] tracefs_inode_cache: 108 [* 1184 = 127872] buffer_head: 24 [* 168 = 4032] hmem_inode_cache: 18 [* 1480 = 26640] dentry: 127 [* 312 = 39624] lsm_inode_cache: 152 [* 32 = 4864] vma_lock: 67 [* 152 = 10184] vm_area_struct: -12 [* 184 = -2208] trace_event_file: 1764 [* 96 = 169344] kmalloc-96: 14322 [* 96 = 1374912] kmalloc-64: 2814 [* 64 = 180096] kmalloc-32: 1103 [* 32 = 35296] kmalloc-16: 2308 [* 16 = 36928] kmalloc-8: 12800 [* 8 = 102400] Total slab additions in size: 2,109,984 bytes Which is a savings of 20,653,416 bytes (20 MB) per tracing instance. Link: https://lkml.kernel.org/r/1690568452-46553-10-git-send-email-akaher@vmware.com Signed-off-by: Ajay Kaher Co-developed-by: Steven Rostedt (VMware) Signed-off-by: Steven Rostedt (VMware) Tested-by: Ching-lin Yu Signed-off-by: Steven Rostedt (Google) --- fs/tracefs/inode.c | 18 ++++++++++++ include/linux/trace_events.h | 1 + kernel/trace/trace.h | 2 +- kernel/trace/trace_events.c | 65 ++++++++++++++++++++++---------------------- 4 files changed, 53 insertions(+), 33 deletions(-) (limited to 'include/linux') diff --git a/fs/tracefs/inode.c b/fs/tracefs/inode.c index d9273066f25f..bb6de89eb446 100644 --- a/fs/tracefs/inode.c +++ b/fs/tracefs/inode.c @@ -374,6 +374,23 @@ static const struct super_operations tracefs_super_operations = { .show_options = tracefs_show_options, }; +static void tracefs_dentry_iput(struct dentry *dentry, struct inode *inode) +{ + struct tracefs_inode *ti; + + if (!dentry || !inode) + return; + + ti = get_tracefs(inode); + if (ti && ti->flags & TRACEFS_EVENT_INODE) + eventfs_set_ef_status_free(dentry); + iput(inode); +} + +static const struct dentry_operations tracefs_dentry_operations = { + .d_iput = tracefs_dentry_iput, +}; + static int trace_fill_super(struct super_block *sb, void *data, int silent) { static const struct tree_descr trace_files[] = {{""}}; @@ -396,6 +413,7 @@ static int trace_fill_super(struct super_block *sb, void *data, int silent) goto fail; sb->s_op = &tracefs_super_operations; + sb->s_d_op = &tracefs_dentry_operations; tracefs_apply_options(sb, false); diff --git a/include/linux/trace_events.h b/include/linux/trace_events.h index 3930e676436c..c17623c78029 100644 --- a/include/linux/trace_events.h +++ b/include/linux/trace_events.h @@ -638,6 +638,7 @@ struct trace_event_file { struct list_head list; struct trace_event_call *event_call; struct event_filter __rcu *filter; + struct eventfs_file *ef; struct dentry *dir; struct trace_array *tr; struct trace_subsystem_dir *system; diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h index ba7ababb8308..5b1f9e24764a 100644 --- a/kernel/trace/trace.h +++ b/kernel/trace/trace.h @@ -1334,7 +1334,7 @@ struct trace_subsystem_dir { struct list_head list; struct event_subsystem *subsystem; struct trace_array *tr; - struct dentry *entry; + struct eventfs_file *ef; int ref_count; int nr_events; }; diff --git a/kernel/trace/trace_events.c b/kernel/trace/trace_events.c index 3ecc41f6acd9..ed367d713be0 100644 --- a/kernel/trace/trace_events.c +++ b/kernel/trace/trace_events.c @@ -984,7 +984,7 @@ static void remove_subsystem(struct trace_subsystem_dir *dir) return; if (!--dir->nr_events) { - tracefs_remove(dir->entry); + eventfs_remove(dir->ef); list_del(&dir->list); __put_system_dir(dir); } @@ -1005,7 +1005,7 @@ static void remove_event_file_dir(struct trace_event_file *file) tracefs_remove(dir); } - + eventfs_remove(file->ef); list_del(&file->list); remove_subsystem(file->system); free_event_filter(file->filter); @@ -2291,13 +2291,13 @@ create_new_subsystem(const char *name) return NULL; } -static struct dentry * +static struct eventfs_file * event_subsystem_dir(struct trace_array *tr, const char *name, struct trace_event_file *file, struct dentry *parent) { struct event_subsystem *system, *iter; struct trace_subsystem_dir *dir; - struct dentry *entry; + int res; /* First see if we did not already create this dir */ list_for_each_entry(dir, &tr->systems, list) { @@ -2305,7 +2305,7 @@ event_subsystem_dir(struct trace_array *tr, const char *name, if (strcmp(system->name, name) == 0) { dir->nr_events++; file->system = dir; - return dir->entry; + return dir->ef; } } @@ -2329,8 +2329,8 @@ event_subsystem_dir(struct trace_array *tr, const char *name, } else __get_system(system); - dir->entry = tracefs_create_dir(name, parent); - if (!dir->entry) { + dir->ef = eventfs_add_subsystem_dir(name, parent); + if (IS_ERR(dir->ef)) { pr_warn("Failed to create system directory %s\n", name); __put_system(system); goto out_free; @@ -2345,22 +2345,22 @@ event_subsystem_dir(struct trace_array *tr, const char *name, /* the ftrace system is special, do not create enable or filter files */ if (strcmp(name, "ftrace") != 0) { - entry = tracefs_create_file("filter", TRACE_MODE_WRITE, - dir->entry, dir, + res = eventfs_add_file("filter", TRACE_MODE_WRITE, + dir->ef, dir, &ftrace_subsystem_filter_fops); - if (!entry) { + if (res) { kfree(system->filter); system->filter = NULL; pr_warn("Could not create tracefs '%s/filter' entry\n", name); } - trace_create_file("enable", TRACE_MODE_WRITE, dir->entry, dir, + eventfs_add_file("enable", TRACE_MODE_WRITE, dir->ef, dir, &ftrace_system_enable_fops); } list_add(&dir->list, &tr->systems); - return dir->entry; + return dir->ef; out_free: kfree(dir); @@ -2413,8 +2413,8 @@ static int event_create_dir(struct dentry *parent, struct trace_event_file *file) { struct trace_event_call *call = file->event_call; + struct eventfs_file *ef_subsystem = NULL; struct trace_array *tr = file->tr; - struct dentry *d_events; const char *name; int ret; @@ -2426,24 +2426,24 @@ event_create_dir(struct dentry *parent, struct trace_event_file *file) if (WARN_ON_ONCE(strcmp(call->class->system, TRACE_SYSTEM) == 0)) return -ENODEV; - d_events = event_subsystem_dir(tr, call->class->system, file, parent); - if (!d_events) + ef_subsystem = event_subsystem_dir(tr, call->class->system, file, parent); + if (!ef_subsystem) return -ENOMEM; name = trace_event_name(call); - file->dir = tracefs_create_dir(name, d_events); - if (!file->dir) { + file->ef = eventfs_add_dir(name, ef_subsystem); + if (IS_ERR(file->ef)) { pr_warn("Could not create tracefs '%s' directory\n", name); return -1; } if (call->class->reg && !(call->flags & TRACE_EVENT_FL_IGNORE_ENABLE)) - trace_create_file("enable", TRACE_MODE_WRITE, file->dir, file, + eventfs_add_file("enable", TRACE_MODE_WRITE, file->ef, file, &ftrace_enable_fops); #ifdef CONFIG_PERF_EVENTS if (call->event.type && call->class->reg) - trace_create_file("id", TRACE_MODE_READ, file->dir, + eventfs_add_file("id", TRACE_MODE_READ, file->ef, (void *)(long)call->event.type, &ftrace_event_id_fops); #endif @@ -2459,27 +2459,27 @@ event_create_dir(struct dentry *parent, struct trace_event_file *file) * triggers or filters. */ if (!(call->flags & TRACE_EVENT_FL_IGNORE_ENABLE)) { - trace_create_file("filter", TRACE_MODE_WRITE, file->dir, + eventfs_add_file("filter", TRACE_MODE_WRITE, file->ef, file, &ftrace_event_filter_fops); - trace_create_file("trigger", TRACE_MODE_WRITE, file->dir, + eventfs_add_file("trigger", TRACE_MODE_WRITE, file->ef, file, &event_trigger_fops); } #ifdef CONFIG_HIST_TRIGGERS - trace_create_file("hist", TRACE_MODE_READ, file->dir, file, + eventfs_add_file("hist", TRACE_MODE_READ, file->ef, file, &event_hist_fops); #endif #ifdef CONFIG_HIST_TRIGGERS_DEBUG - trace_create_file("hist_debug", TRACE_MODE_READ, file->dir, file, + eventfs_add_file("hist_debug", TRACE_MODE_READ, file->ef, file, &event_hist_debug_fops); #endif - trace_create_file("format", TRACE_MODE_READ, file->dir, call, + eventfs_add_file("format", TRACE_MODE_READ, file->ef, call, &ftrace_event_format_fops); #ifdef CONFIG_TRACE_EVENT_INJECT if (call->event.type && call->class->reg) - trace_create_file("inject", 0200, file->dir, file, + eventfs_add_file("inject", 0200, file->ef, file, &event_inject_fops); #endif @@ -3632,21 +3632,22 @@ create_event_toplevel_files(struct dentry *parent, struct trace_array *tr) { struct dentry *d_events; struct dentry *entry; + int error = 0; entry = trace_create_file("set_event", TRACE_MODE_WRITE, parent, tr, &ftrace_set_event_fops); if (!entry) return -ENOMEM; - d_events = tracefs_create_dir("events", parent); - if (!d_events) { + d_events = eventfs_create_events_dir("events", parent); + if (IS_ERR(d_events)) { pr_warn("Could not create tracefs 'events' directory\n"); return -ENOMEM; } - entry = trace_create_file("enable", TRACE_MODE_WRITE, d_events, + error = eventfs_add_events_file("enable", TRACE_MODE_WRITE, d_events, tr, &ftrace_tr_enable_fops); - if (!entry) + if (error) return -ENOMEM; /* There are not as crucial, just warn if they are not created */ @@ -3659,11 +3660,11 @@ create_event_toplevel_files(struct dentry *parent, struct trace_array *tr) &ftrace_set_event_notrace_pid_fops); /* ring buffer internal formats */ - trace_create_file("header_page", TRACE_MODE_READ, d_events, + eventfs_add_events_file("header_page", TRACE_MODE_READ, d_events, ring_buffer_print_page_header, &ftrace_show_header_fops); - trace_create_file("header_event", TRACE_MODE_READ, d_events, + eventfs_add_events_file("header_event", TRACE_MODE_READ, d_events, ring_buffer_print_entry_header, &ftrace_show_header_fops); @@ -3751,7 +3752,7 @@ int event_trace_del_tracer(struct trace_array *tr) down_write(&trace_event_sem); __trace_remove_event_dirs(tr); - tracefs_remove(tr->event_dir); + eventfs_remove_events_dir(tr->event_dir); up_write(&trace_event_sem); tr->event_dir = NULL; -- cgit v1.3 From 39f7c41c908bc82947ce47cdd021520ff486c53f Mon Sep 17 00:00:00 2001 From: Valentin Schneider Date: Fri, 7 Jul 2023 18:21:48 +0100 Subject: tracing/filters: Enable filtering a cpumask field by another cpumask The recently introduced ipi_send_cpumask trace event contains a cpumask field, but it currently cannot be used in filter expressions. Make event filtering aware of cpumask fields, and allow these to be filtered by a user-provided cpumask. The user-provided cpumask is to be given in cpulist format and wrapped as: "CPUS{$cpulist}". The use of curly braces instead of parentheses is to prevent predicate_parse() from parsing the contents of CPUS{...} as a full-fledged predicate subexpression. This enables e.g.: $ trace-cmd record -e 'ipi_send_cpumask' -f 'cpumask & CPUS{2,4,6,8-32}' Link: https://lkml.kernel.org/r/20230707172155.70873-3-vschneid@redhat.com Cc: Masami Hiramatsu Cc: Jonathan Corbet Cc: Juri Lelli Cc: Daniel Bristot de Oliveira Cc: Marcelo Tosatti Cc: Leonardo Bras Cc: Frederic Weisbecker Signed-off-by: Valentin Schneider Signed-off-by: Steven Rostedt (Google) --- include/linux/trace_events.h | 1 + kernel/trace/trace_events_filter.c | 97 +++++++++++++++++++++++++++++++++++++- 2 files changed, 96 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/trace_events.h b/include/linux/trace_events.h index c17623c78029..1600aeb8e1a3 100644 --- a/include/linux/trace_events.h +++ b/include/linux/trace_events.h @@ -808,6 +808,7 @@ enum { FILTER_RDYN_STRING, FILTER_PTR_STRING, FILTER_TRACE_FN, + FILTER_CPUMASK, FILTER_COMM, FILTER_CPU, FILTER_STACKTRACE, diff --git a/kernel/trace/trace_events_filter.c b/kernel/trace/trace_events_filter.c index 91fc9990107f..cb1863dfa280 100644 --- a/kernel/trace/trace_events_filter.c +++ b/kernel/trace/trace_events_filter.c @@ -64,6 +64,7 @@ enum filter_pred_fn { FILTER_PRED_FN_PCHAR_USER, FILTER_PRED_FN_PCHAR, FILTER_PRED_FN_CPU, + FILTER_PRED_FN_CPUMASK, FILTER_PRED_FN_FUNCTION, FILTER_PRED_FN_, FILTER_PRED_TEST_VISITED, @@ -71,6 +72,7 @@ enum filter_pred_fn { struct filter_pred { struct regex *regex; + struct cpumask *mask; unsigned short *ops; struct ftrace_event_field *field; u64 val; @@ -94,6 +96,8 @@ struct filter_pred { C(TOO_MANY_OPEN, "Too many '('"), \ C(TOO_MANY_CLOSE, "Too few '('"), \ C(MISSING_QUOTE, "Missing matching quote"), \ + C(MISSING_BRACE_OPEN, "Missing '{'"), \ + C(MISSING_BRACE_CLOSE, "Missing '}'"), \ C(OPERAND_TOO_LONG, "Operand too long"), \ C(EXPECT_STRING, "Expecting string field"), \ C(EXPECT_DIGIT, "Expecting numeric field"), \ @@ -103,6 +107,7 @@ struct filter_pred { C(BAD_SUBSYS_FILTER, "Couldn't find or set field in one of a subsystem's events"), \ C(TOO_MANY_PREDS, "Too many terms in predicate expression"), \ C(INVALID_FILTER, "Meaningless filter expression"), \ + C(INVALID_CPULIST, "Invalid cpulist"), \ C(IP_FIELD_ONLY, "Only 'ip' field is supported for function trace"), \ C(INVALID_VALUE, "Invalid value (did you forget quotes)?"), \ C(NO_FUNCTION, "Function not found"), \ @@ -190,6 +195,7 @@ static void free_predicate(struct filter_pred *pred) { if (pred) { kfree(pred->regex); + kfree(pred->mask); kfree(pred); } } @@ -877,6 +883,26 @@ static int filter_pred_cpu(struct filter_pred *pred, void *event) } } +/* Filter predicate for cpumask field vs user-provided cpumask */ +static int filter_pred_cpumask(struct filter_pred *pred, void *event) +{ + u32 item = *(u32 *)(event + pred->offset); + int loc = item & 0xffff; + const struct cpumask *mask = (event + loc); + const struct cpumask *cmp = pred->mask; + + switch (pred->op) { + case OP_EQ: + return cpumask_equal(mask, cmp); + case OP_NE: + return !cpumask_equal(mask, cmp); + case OP_BAND: + return cpumask_intersects(mask, cmp); + default: + return 0; + } +} + /* Filter predicate for COMM. */ static int filter_pred_comm(struct filter_pred *pred, void *event) { @@ -1244,8 +1270,12 @@ static void filter_free_subsystem_filters(struct trace_subsystem_dir *dir, int filter_assign_type(const char *type) { - if (strstr(type, "__data_loc") && strstr(type, "char")) - return FILTER_DYN_STRING; + if (strstr(type, "__data_loc")) { + if (strstr(type, "char")) + return FILTER_DYN_STRING; + if (strstr(type, "cpumask_t")) + return FILTER_CPUMASK; + } if (strstr(type, "__rel_loc") && strstr(type, "char")) return FILTER_RDYN_STRING; @@ -1357,6 +1387,8 @@ static int filter_pred_fn_call(struct filter_pred *pred, void *event) return filter_pred_pchar(pred, event); case FILTER_PRED_FN_CPU: return filter_pred_cpu(pred, event); + case FILTER_PRED_FN_CPUMASK: + return filter_pred_cpumask(pred, event); case FILTER_PRED_FN_FUNCTION: return filter_pred_function(pred, event); case FILTER_PRED_TEST_VISITED: @@ -1568,6 +1600,67 @@ static int parse_pred(const char *str, void *data, strncpy(pred->regex->pattern, str + s, len); pred->regex->pattern[len] = 0; + } else if (!strncmp(str + i, "CPUS", 4)) { + unsigned int maskstart; + char *tmp; + + switch (field->filter_type) { + case FILTER_CPUMASK: + break; + default: + parse_error(pe, FILT_ERR_ILLEGAL_FIELD_OP, pos + i); + goto err_free; + } + + switch (op) { + case OP_EQ: + case OP_NE: + case OP_BAND: + break; + default: + parse_error(pe, FILT_ERR_ILLEGAL_FIELD_OP, pos + i); + goto err_free; + } + + /* Skip CPUS */ + i += 4; + if (str[i++] != '{') { + parse_error(pe, FILT_ERR_MISSING_BRACE_OPEN, pos + i); + goto err_free; + } + maskstart = i; + + /* Walk the cpulist until closing } */ + for (; str[i] && str[i] != '}'; i++); + if (str[i] != '}') { + parse_error(pe, FILT_ERR_MISSING_BRACE_CLOSE, pos + i); + goto err_free; + } + + if (maskstart == i) { + parse_error(pe, FILT_ERR_INVALID_CPULIST, pos + i); + goto err_free; + } + + /* Copy the cpulist between { and } */ + tmp = kmalloc((i - maskstart) + 1, GFP_KERNEL); + strscpy(tmp, str + maskstart, (i - maskstart) + 1); + + pred->mask = kzalloc(cpumask_size(), GFP_KERNEL); + if (!pred->mask) + goto err_mem; + + /* Now parse it */ + if (cpulist_parse(tmp, pred->mask)) { + parse_error(pe, FILT_ERR_INVALID_CPULIST, pos + i); + goto err_free; + } + + /* Move along */ + i++; + if (field->filter_type == FILTER_CPUMASK) + pred->fn_num = FILTER_PRED_FN_CPUMASK; + /* This is either a string, or an integer */ } else if (str[i] == '\'' || str[i] == '"') { char q = str[i]; -- cgit v1.3 From c8f05f2f41d7e4950d6767e6ebe9fba3dcaf45ff Mon Sep 17 00:00:00 2001 From: Zhang Zekun Date: Fri, 4 Aug 2023 09:36:36 +0800 Subject: ftrace: Remove empty declaration ftrace_enable_daemon() and ftrace_disable_daemon() The definition of ftrace_enable_daemon() and ftrace_disable_daemon() has been removed since commit cb7be3b2fc2c ("ftrace: remove daemon"), remain the declarations in the header files, so remove it. Link: https://lore.kernel.org/linux-trace-kernel/20230804013636.115940-1-zhangzekun11@huawei.com Cc: Cc: Signed-off-by: Zhang Zekun Signed-off-by: Steven Rostedt (Google) --- include/linux/ftrace.h | 5 ----- 1 file changed, 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ftrace.h b/include/linux/ftrace.h index aad9cf8876b5..e8921871ef9a 100644 --- a/include/linux/ftrace.h +++ b/include/linux/ftrace.h @@ -862,13 +862,8 @@ extern int skip_trace(unsigned long ip); extern void ftrace_module_init(struct module *mod); extern void ftrace_module_enable(struct module *mod); extern void ftrace_release_mod(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 void ftrace_disable_daemon(void) { } -static inline void ftrace_enable_daemon(void) { } static inline void ftrace_module_init(struct module *mod) { } static inline void ftrace_module_enable(struct module *mod) { } static inline void ftrace_release_mod(struct module *mod) { } -- cgit v1.3