From 6ad51ada17ed80c9a5f205b4c01c424cac8b0d46 Mon Sep 17 00:00:00 2001 From: "Masami Hiramatsu (Google)" Date: Mon, 20 Apr 2026 23:00:48 +0900 Subject: tracing/fprobe: Reject registration of a registered fprobe before init Reject registration of a registered fprobe which is on the fprobe hash table before initializing fprobe. The add_fprobe_hash() checks this re-register fprobe, but since fprobe_init() clears hlist_array field, it is too late to check it. It has to check the re-registration before touncing fprobe. Link: https://lore.kernel.org/all/177669364845.132053.18375367916162315835.stgit@mhiramat.tok.corp.google.com/ Fixes: 4346ba160409 ("fprobe: Rewrite fprobe on function-graph tracer") Cc: stable@vger.kernel.org Signed-off-by: Masami Hiramatsu (Google) --- kernel/trace/fprobe.c | 21 ++++++++++----------- 1 file changed, 10 insertions(+), 11 deletions(-) diff --git a/kernel/trace/fprobe.c b/kernel/trace/fprobe.c index 56d145017902..af9ba7250874 100644 --- a/kernel/trace/fprobe.c +++ b/kernel/trace/fprobe.c @@ -4,6 +4,7 @@ */ #define pr_fmt(fmt) "fprobe: " fmt +#include #include #include #include @@ -107,7 +108,7 @@ static bool delete_fprobe_node(struct fprobe_hlist_node *node) } /* Check existence of the fprobe */ -static bool is_fprobe_still_exist(struct fprobe *fp) +static bool fprobe_registered(struct fprobe *fp) { struct hlist_head *head; struct fprobe_hlist *fph; @@ -120,7 +121,7 @@ static bool is_fprobe_still_exist(struct fprobe *fp) } return false; } -NOKPROBE_SYMBOL(is_fprobe_still_exist); +NOKPROBE_SYMBOL(fprobe_registered); static int add_fprobe_hash(struct fprobe *fp) { @@ -132,9 +133,6 @@ static int add_fprobe_hash(struct fprobe *fp) if (WARN_ON_ONCE(!fph)) return -EINVAL; - if (is_fprobe_still_exist(fp)) - return -EEXIST; - head = &fprobe_table[hash_ptr(fp, FPROBE_HASH_BITS)]; hlist_add_head_rcu(&fp->hlist_array->hlist, head); return 0; @@ -149,7 +147,7 @@ static int del_fprobe_hash(struct fprobe *fp) if (WARN_ON_ONCE(!fph)) return -EINVAL; - if (!is_fprobe_still_exist(fp)) + if (!fprobe_registered(fp)) return -ENOENT; fph->fp = NULL; @@ -480,7 +478,7 @@ static void fprobe_return(struct ftrace_graph_ret *trace, if (!fp) break; curr += FPROBE_HEADER_SIZE_IN_LONG; - if (is_fprobe_still_exist(fp) && !fprobe_disabled(fp)) { + if (fprobe_registered(fp) && !fprobe_disabled(fp)) { if (WARN_ON_ONCE(curr + size > size_words)) break; fp->exit_handler(fp, trace->func, ret_ip, fregs, @@ -839,12 +837,14 @@ int register_fprobe_ips(struct fprobe *fp, unsigned long *addrs, int num) struct fprobe_hlist *hlist_array; int ret, i; + guard(mutex)(&fprobe_mutex); + if (fprobe_registered(fp)) + return -EEXIST; + ret = fprobe_init(fp, addrs, num); if (ret) return ret; - mutex_lock(&fprobe_mutex); - hlist_array = fp->hlist_array; if (fprobe_is_ftrace(fp)) ret = fprobe_ftrace_add_ips(addrs, num); @@ -864,7 +864,6 @@ int register_fprobe_ips(struct fprobe *fp, unsigned long *addrs, int num) delete_fprobe_node(&hlist_array->array[i]); } } - mutex_unlock(&fprobe_mutex); if (ret) fprobe_fail_cleanup(fp); @@ -926,7 +925,7 @@ int unregister_fprobe(struct fprobe *fp) int ret = 0, i, count; mutex_lock(&fprobe_mutex); - if (!fp || !is_fprobe_still_exist(fp)) { + if (!fp || !fprobe_registered(fp)) { ret = -EINVAL; goto out; } -- cgit v1.2.3 From 1aec9e5c3e31ce1e28f914427fb7f90b91d310df Mon Sep 17 00:00:00 2001 From: "Masami Hiramatsu (Google)" Date: Mon, 20 Apr 2026 23:00:56 +0900 Subject: tracing/fprobe: Unregister fprobe even if memory allocation fails unregister_fprobe() can fail under memory pressure because of memory allocation failure, but this maybe called from module unloading, and usually there is no way to retry it. Moreover. trace_fprobe does not check the return value. To fix this problem, unregister fprobe and fprobe_hash_node even if working memory allocation fails. Anyway, if the last fprobe is removed, the filter will be freed. Link: https://lore.kernel.org/all/177669365629.132053.8433032896213721288.stgit@mhiramat.tok.corp.google.com/ Fixes: 4346ba160409 ("fprobe: Rewrite fprobe on function-graph tracer") Cc: stable@vger.kernel.org Signed-off-by: Masami Hiramatsu (Google) --- kernel/trace/fprobe.c | 25 +++++++++++++++---------- 1 file changed, 15 insertions(+), 10 deletions(-) diff --git a/kernel/trace/fprobe.c b/kernel/trace/fprobe.c index af9ba7250874..a2b659006e0e 100644 --- a/kernel/trace/fprobe.c +++ b/kernel/trace/fprobe.c @@ -324,9 +324,10 @@ static void fprobe_ftrace_remove_ips(unsigned long *addrs, int num) lockdep_assert_held(&fprobe_mutex); fprobe_ftrace_active--; - if (!fprobe_ftrace_active) + if (!fprobe_ftrace_active) { unregister_ftrace_function(&fprobe_ftrace_ops); - if (num) + ftrace_free_filter(&fprobe_ftrace_ops); + } else if (num) ftrace_set_filter_ips(&fprobe_ftrace_ops, addrs, num, 1, 0); } @@ -525,10 +526,10 @@ static void fprobe_graph_remove_ips(unsigned long *addrs, int num) fprobe_graph_active--; /* Q: should we unregister it ? */ - if (!fprobe_graph_active) + if (!fprobe_graph_active) { unregister_ftrace_graph(&fprobe_graph_ops); - - if (num) + ftrace_free_filter(&fprobe_graph_ops.ops); + } else if (num) ftrace_set_filter_ips(&fprobe_graph_ops.ops, addrs, num, 1, 0); } @@ -932,15 +933,19 @@ int unregister_fprobe(struct fprobe *fp) hlist_array = fp->hlist_array; addrs = kcalloc(hlist_array->size, sizeof(unsigned long), GFP_KERNEL); - if (!addrs) { - ret = -ENOMEM; /* TODO: Fallback to one-by-one loop */ - goto out; - } + /* + * This will remove fprobe_hash_node from the hash table even if + * memory allocation fails. However, ftrace_ops will not be updated. + * Anyway, when the last fprobe is unregistered, ftrace_ops is also + * unregistered. + */ + if (!addrs) + pr_warn("Failed to allocate working array. ftrace_ops may not sync.\n"); /* Remove non-synonim ips from table and hash */ count = 0; for (i = 0; i < hlist_array->size; i++) { - if (!delete_fprobe_node(&hlist_array->array[i])) + if (!delete_fprobe_node(&hlist_array->array[i]) && addrs) addrs[count++] = hlist_array->array[i].addr; } del_fprobe_hash(fp); -- cgit v1.2.3 From 845947aca6814f5723ed65e556eb5ee09493f05b Mon Sep 17 00:00:00 2001 From: "Masami Hiramatsu (Google)" Date: Mon, 20 Apr 2026 23:01:04 +0900 Subject: tracing/fprobe: Remove fprobe from hash in failure path When register_fprobe_ips() fails, it tries to remove a list of fprobe_hash_node from fprobe_ip_table, but it missed to remove fprobe itself from fprobe_table. Moreover, when removing the fprobe_hash_node which is added to rhltable once, it must use kfree_rcu() after removing from rhltable. To fix these issues, this reuses unregister_fprobe() internal code to rollback the half-way registered fprobe. Link: https://lore.kernel.org/all/177669366417.132053.17874946321744910456.stgit@mhiramat.tok.corp.google.com/ Fixes: 4346ba160409 ("fprobe: Rewrite fprobe on function-graph tracer") Cc: stable@vger.kernel.org Signed-off-by: Masami Hiramatsu (Google) --- kernel/trace/fprobe.c | 90 +++++++++++++++++++++++++++------------------------ 1 file changed, 47 insertions(+), 43 deletions(-) diff --git a/kernel/trace/fprobe.c b/kernel/trace/fprobe.c index a2b659006e0e..621477ad0947 100644 --- a/kernel/trace/fprobe.c +++ b/kernel/trace/fprobe.c @@ -79,20 +79,27 @@ static const struct rhashtable_params fprobe_rht_params = { }; /* Node insertion and deletion requires the fprobe_mutex */ -static int insert_fprobe_node(struct fprobe_hlist_node *node) +static int insert_fprobe_node(struct fprobe_hlist_node *node, struct fprobe *fp) { + int ret; + lockdep_assert_held(&fprobe_mutex); - return rhltable_insert(&fprobe_ip_table, &node->hlist, fprobe_rht_params); + ret = rhltable_insert(&fprobe_ip_table, &node->hlist, fprobe_rht_params); + /* Set the fprobe pointer if insertion was successful. */ + if (!ret) + WRITE_ONCE(node->fp, fp); + return ret; } /* Return true if there are synonims */ static bool delete_fprobe_node(struct fprobe_hlist_node *node) { - lockdep_assert_held(&fprobe_mutex); bool ret; - /* Avoid double deleting */ + lockdep_assert_held(&fprobe_mutex); + + /* Avoid double deleting and non-inserted nodes */ if (READ_ONCE(node->fp) != NULL) { WRITE_ONCE(node->fp, NULL); rhltable_remove(&fprobe_ip_table, &node->hlist, @@ -756,7 +763,6 @@ static int fprobe_init(struct fprobe *fp, unsigned long *addrs, int num) fp->hlist_array = hlist_array; hlist_array->fp = fp; for (i = 0; i < num; i++) { - hlist_array->array[i].fp = fp; addr = ftrace_location(addrs[i]); if (!addr) { fprobe_fail_cleanup(fp); @@ -820,6 +826,8 @@ int register_fprobe(struct fprobe *fp, const char *filter, const char *notfilter } EXPORT_SYMBOL_GPL(register_fprobe); +static int unregister_fprobe_nolock(struct fprobe *fp); + /** * register_fprobe_ips() - Register fprobe to ftrace by address. * @fp: A fprobe data structure to be registered. @@ -846,28 +854,25 @@ int register_fprobe_ips(struct fprobe *fp, unsigned long *addrs, int num) if (ret) return ret; - hlist_array = fp->hlist_array; if (fprobe_is_ftrace(fp)) ret = fprobe_ftrace_add_ips(addrs, num); else ret = fprobe_graph_add_ips(addrs, num); - - if (!ret) { - add_fprobe_hash(fp); - for (i = 0; i < hlist_array->size; i++) { - ret = insert_fprobe_node(&hlist_array->array[i]); - if (ret) - break; - } - /* fallback on insert error */ - if (ret) { - for (i--; i >= 0; i--) - delete_fprobe_node(&hlist_array->array[i]); - } + if (ret) { + fprobe_fail_cleanup(fp); + return ret; } - if (ret) - fprobe_fail_cleanup(fp); + hlist_array = fp->hlist_array; + ret = add_fprobe_hash(fp); + for (i = 0; i < hlist_array->size && !ret; i++) + ret = insert_fprobe_node(&hlist_array->array[i], fp); + + if (ret) { + unregister_fprobe_nolock(fp); + /* In error case, wait for clean up safely. */ + synchronize_rcu(); + } return ret; } @@ -911,27 +916,12 @@ bool fprobe_is_registered(struct fprobe *fp) return true; } -/** - * unregister_fprobe() - Unregister fprobe. - * @fp: A fprobe data structure to be unregistered. - * - * Unregister fprobe (and remove ftrace hooks from the function entries). - * - * Return 0 if @fp is unregistered successfully, -errno if not. - */ -int unregister_fprobe(struct fprobe *fp) +static int unregister_fprobe_nolock(struct fprobe *fp) { - struct fprobe_hlist *hlist_array; + struct fprobe_hlist *hlist_array = fp->hlist_array; unsigned long *addrs = NULL; - int ret = 0, i, count; + int i, count; - mutex_lock(&fprobe_mutex); - if (!fp || !fprobe_registered(fp)) { - ret = -EINVAL; - goto out; - } - - hlist_array = fp->hlist_array; addrs = kcalloc(hlist_array->size, sizeof(unsigned long), GFP_KERNEL); /* * This will remove fprobe_hash_node from the hash table even if @@ -957,12 +947,26 @@ int unregister_fprobe(struct fprobe *fp) kfree_rcu(hlist_array, rcu); fp->hlist_array = NULL; + kfree(addrs); -out: - mutex_unlock(&fprobe_mutex); + return 0; +} - kfree(addrs); - return ret; +/** + * unregister_fprobe() - Unregister fprobe. + * @fp: A fprobe data structure to be unregistered. + * + * Unregister fprobe (and remove ftrace hooks from the function entries). + * + * Return 0 if @fp is unregistered successfully, -errno if not. + */ +int unregister_fprobe(struct fprobe *fp) +{ + guard(mutex)(&fprobe_mutex); + if (!fp || !fprobe_registered(fp)) + return -EINVAL; + + return unregister_fprobe_nolock(fp); } EXPORT_SYMBOL_GPL(unregister_fprobe); -- cgit v1.2.3 From aa72812b49104bb5a38272fc9541feb62ca6fd32 Mon Sep 17 00:00:00 2001 From: "Masami Hiramatsu (Google)" Date: Mon, 20 Apr 2026 23:01:12 +0900 Subject: tracing/fprobe: Avoid kcalloc() in rcu_read_lock section fprobe_remove_node_in_module() is called under RCU read locked, but this invokes kcalloc() if there are more than 8 fprobes installed on the module. Sashiko warns it because kcalloc() can sleep [1]. [1] https://sashiko.dev/#/patchset/177552432201.853249.5125045538812833325.stgit%40mhiramat.tok.corp.google.com To fix this issue, expand the batch size to 128 and do not expand the fprobe_addr_list, but just cancel walking on fprobe_ip_table, update fgraph/ftrace_ops and retry the loop again. Link: https://lore.kernel.org/all/177669367206.132053.1493637946869032744.stgit@mhiramat.tok.corp.google.com/ Fixes: 0de4c70d04a4 ("tracing: fprobe: use rhltable for fprobe_ip_table") Cc: stable@vger.kernel.org Signed-off-by: Masami Hiramatsu (Google) --- kernel/trace/fprobe.c | 92 +++++++++++++++++++++++++-------------------------- 1 file changed, 45 insertions(+), 47 deletions(-) diff --git a/kernel/trace/fprobe.c b/kernel/trace/fprobe.c index 621477ad0947..9b913facfd36 100644 --- a/kernel/trace/fprobe.c +++ b/kernel/trace/fprobe.c @@ -344,11 +344,10 @@ static bool fprobe_is_ftrace(struct fprobe *fp) } #ifdef CONFIG_MODULES -static void fprobe_set_ips(unsigned long *ips, unsigned int cnt, int remove, - int reset) +static void fprobe_remove_ips(unsigned long *ips, unsigned int cnt) { - ftrace_set_filter_ips(&fprobe_graph_ops.ops, ips, cnt, remove, reset); - ftrace_set_filter_ips(&fprobe_ftrace_ops, ips, cnt, remove, reset); + ftrace_set_filter_ips(&fprobe_graph_ops.ops, ips, cnt, 1, 0); + ftrace_set_filter_ips(&fprobe_ftrace_ops, ips, cnt, 1, 0); } #endif #else @@ -367,10 +366,9 @@ static bool fprobe_is_ftrace(struct fprobe *fp) } #ifdef CONFIG_MODULES -static void fprobe_set_ips(unsigned long *ips, unsigned int cnt, int remove, - int reset) +static void fprobe_remove_ips(unsigned long *ips, unsigned int cnt) { - ftrace_set_filter_ips(&fprobe_graph_ops.ops, ips, cnt, remove, reset); + ftrace_set_filter_ips(&fprobe_graph_ops.ops, ips, cnt, 1, 0); } #endif #endif /* !CONFIG_DYNAMIC_FTRACE_WITH_ARGS && !CONFIG_DYNAMIC_FTRACE_WITH_REGS */ @@ -542,7 +540,7 @@ static void fprobe_graph_remove_ips(unsigned long *addrs, int num) #ifdef CONFIG_MODULES -#define FPROBE_IPS_BATCH_INIT 8 +#define FPROBE_IPS_BATCH_INIT 128 /* instruction pointer address list */ struct fprobe_addr_list { int index; @@ -550,45 +548,24 @@ struct fprobe_addr_list { unsigned long *addrs; }; -static int fprobe_addr_list_add(struct fprobe_addr_list *alist, unsigned long addr) +static int fprobe_remove_node_in_module(struct module *mod, struct fprobe_hlist_node *node, + struct fprobe_addr_list *alist) { - unsigned long *addrs; - - /* Previously we failed to expand the list. */ - if (alist->index == alist->size) - return -ENOSPC; - - alist->addrs[alist->index++] = addr; - if (alist->index < alist->size) + if (!within_module(node->addr, mod)) return 0; - /* Expand the address list */ - addrs = kcalloc(alist->size * 2, sizeof(*addrs), GFP_KERNEL); - if (!addrs) - return -ENOMEM; - - memcpy(addrs, alist->addrs, alist->size * sizeof(*addrs)); - alist->size *= 2; - kfree(alist->addrs); - alist->addrs = addrs; + if (delete_fprobe_node(node)) + return 0; + /* If no address list is available, we can't track this address. */ + if (!alist->addrs) + return 0; + alist->addrs[alist->index++] = node->addr; + if (alist->index == alist->size) + return -ENOSPC; return 0; } -static void fprobe_remove_node_in_module(struct module *mod, struct fprobe_hlist_node *node, - struct fprobe_addr_list *alist) -{ - if (!within_module(node->addr, mod)) - return; - if (delete_fprobe_node(node)) - return; - /* - * If failed to update alist, just continue to update hlist. - * Therefore, at list user handler will not hit anymore. - */ - fprobe_addr_list_add(alist, node->addr); -} - /* Handle module unloading to manage fprobe_ip_table. */ static int fprobe_module_callback(struct notifier_block *nb, unsigned long val, void *data) @@ -597,29 +574,50 @@ static int fprobe_module_callback(struct notifier_block *nb, struct fprobe_hlist_node *node; struct rhashtable_iter iter; struct module *mod = data; + bool retry; if (val != MODULE_STATE_GOING) return NOTIFY_DONE; alist.addrs = kcalloc(alist.size, sizeof(*alist.addrs), GFP_KERNEL); - /* If failed to alloc memory, we can not remove ips from hash. */ - if (!alist.addrs) - return NOTIFY_DONE; + /* + * If failed to alloc memory, ftrace_ops will not be able to remove ips from + * hash, but we can still remove nodes from fprobe_ip_table, so we can avoid + * the potential wrong callback. So just print a warning here and try to + * continue without address list. + */ + WARN_ONCE(!alist.addrs, + "Failed to allocate memory for fprobe_addr_list, ftrace_ops will not be updated"); mutex_lock(&fprobe_mutex); +again: + retry = false; + alist.index = 0; rhltable_walk_enter(&fprobe_ip_table, &iter); do { rhashtable_walk_start(&iter); while ((node = rhashtable_walk_next(&iter)) && !IS_ERR(node)) - fprobe_remove_node_in_module(mod, node, &alist); + if (fprobe_remove_node_in_module(mod, node, &alist) < 0) { + retry = true; + break; + } rhashtable_walk_stop(&iter); - } while (node == ERR_PTR(-EAGAIN)); + } while (node == ERR_PTR(-EAGAIN) && !retry); rhashtable_walk_exit(&iter); + /* Remove any ips from hash table(s) */ + if (alist.index > 0) { + fprobe_remove_ips(alist.addrs, alist.index); + /* + * If we break rhashtable walk loop except for -EAGAIN, we need + * to restart looping from start for safety. Anyway, this is + * not a hotpath. + */ + if (retry) + goto again; + } - if (alist.index > 0) - fprobe_set_ips(alist.addrs, alist.index, 1, 0); mutex_unlock(&fprobe_mutex); kfree(alist.addrs); -- cgit v1.2.3 From 0ac0058a74ac5765c7ce09ea630f4fdeaf4d80fa Mon Sep 17 00:00:00 2001 From: "Masami Hiramatsu (Google)" Date: Mon, 20 Apr 2026 23:01:20 +0900 Subject: tracing/fprobe: Check the same type fprobe on table as the unregistered one Commit 2c67dc457bc6 ("tracing: fprobe: optimization for entry only case") introduced a different ftrace_ops for entry-only fprobes. However, when unregistering an fprobe, the kernel only checks if another fprobe exists at the same address, without checking which type of fprobe it is. If different fprobes are registered at the same address, the same address will be registered in both fgraph_ops and ftrace_ops, but only one of them will be deleted when unregistering. (the one removed first will not be deleted from the ops). This results in junk entries remaining in either fgraph_ops or ftrace_ops. For example: ======= cd /sys/kernel/tracing # 'Add entry and exit events on the same place' echo 'f:event1 vfs_read' >> dynamic_events echo 'f:event2 vfs_read%return' >> dynamic_events # 'Enable both of them' echo 1 > events/fprobes/enable cat enabled_functions vfs_read (2) ->arch_ftrace_ops_list_func+0x0/0x210 # 'Disable and remove exit event' echo 0 > events/fprobes/event2/enable echo -:event2 >> dynamic_events # 'Disable and remove all events' echo 0 > events/fprobes/enable echo > dynamic_events # 'Add another event' echo 'f:event3 vfs_open%return' > dynamic_events cat dynamic_events f:fprobes/event3 vfs_open%return echo 1 > events/fprobes/enable cat enabled_functions vfs_open (1) tramp: 0xffffffffa0001000 (ftrace_graph_func+0x0/0x60) ->ftrace_graph_func+0x0/0x60 subops: {ent:fprobe_fgraph_entry+0x0/0x620 ret:fprobe_return+0x0/0x150} vfs_read (1) tramp: 0xffffffffa0001000 (ftrace_graph_func+0x0/0x60) ->ftrace_graph_func+0x0/0x60 subops: {ent:fprobe_fgraph_entry+0x0/0x620 ret:fprobe_return+0x0/0x150} ======= As you can see, an entry for the vfs_read remains. To fix this issue, when unregistering, the kernel should also check if there is the same type of fprobes still exist at the same address, and if not, delete its entry from either fgraph_ops or ftrace_ops. Link: https://lore.kernel.org/all/177669367993.132053.10553046138528674802.stgit@mhiramat.tok.corp.google.com/ Fixes: 2c67dc457bc6 ("tracing: fprobe: optimization for entry only case") Cc: stable@vger.kernel.org Signed-off-by: Masami Hiramatsu (Google) --- kernel/trace/fprobe.c | 82 ++++++++++++++++++++++++++++++++++++++++----------- 1 file changed, 65 insertions(+), 17 deletions(-) diff --git a/kernel/trace/fprobe.c b/kernel/trace/fprobe.c index 9b913facfd36..d0a68a2c5eaf 100644 --- a/kernel/trace/fprobe.c +++ b/kernel/trace/fprobe.c @@ -92,11 +92,8 @@ static int insert_fprobe_node(struct fprobe_hlist_node *node, struct fprobe *fp) return ret; } -/* Return true if there are synonims */ -static bool delete_fprobe_node(struct fprobe_hlist_node *node) +static void delete_fprobe_node(struct fprobe_hlist_node *node) { - bool ret; - lockdep_assert_held(&fprobe_mutex); /* Avoid double deleting and non-inserted nodes */ @@ -105,13 +102,6 @@ static bool delete_fprobe_node(struct fprobe_hlist_node *node) rhltable_remove(&fprobe_ip_table, &node->hlist, fprobe_rht_params); } - - rcu_read_lock(); - ret = !!rhltable_lookup(&fprobe_ip_table, &node->addr, - fprobe_rht_params); - rcu_read_unlock(); - - return ret; } /* Check existence of the fprobe */ @@ -343,6 +333,32 @@ static bool fprobe_is_ftrace(struct fprobe *fp) return !fp->exit_handler; } +static bool fprobe_exists_on_hash(unsigned long ip, bool ftrace) +{ + struct rhlist_head *head, *pos; + struct fprobe_hlist_node *node; + struct fprobe *fp; + + guard(rcu)(); + head = rhltable_lookup(&fprobe_ip_table, &ip, + fprobe_rht_params); + if (!head) + return false; + /* We have to check the same type on the list. */ + rhl_for_each_entry_rcu(node, pos, head, hlist) { + if (node->addr != ip) + break; + fp = READ_ONCE(node->fp); + if (likely(fp)) { + if ((!ftrace && fp->exit_handler) || + (ftrace && !fp->exit_handler)) + return true; + } + } + + return false; +} + #ifdef CONFIG_MODULES static void fprobe_remove_ips(unsigned long *ips, unsigned int cnt) { @@ -365,6 +381,29 @@ static bool fprobe_is_ftrace(struct fprobe *fp) return false; } +static bool fprobe_exists_on_hash(unsigned long ip, bool ftrace __maybe_unused) +{ + struct rhlist_head *head, *pos; + struct fprobe_hlist_node *node; + struct fprobe *fp; + + guard(rcu)(); + head = rhltable_lookup(&fprobe_ip_table, &ip, + fprobe_rht_params); + if (!head) + return false; + /* We only need to check fp is there. */ + rhl_for_each_entry_rcu(node, pos, head, hlist) { + if (node->addr != ip) + break; + fp = READ_ONCE(node->fp); + if (likely(fp)) + return true; + } + + return false; +} + #ifdef CONFIG_MODULES static void fprobe_remove_ips(unsigned long *ips, unsigned int cnt) { @@ -551,18 +590,25 @@ struct fprobe_addr_list { static int fprobe_remove_node_in_module(struct module *mod, struct fprobe_hlist_node *node, struct fprobe_addr_list *alist) { + lockdep_assert_in_rcu_read_lock(); + if (!within_module(node->addr, mod)) return 0; - if (delete_fprobe_node(node)) - return 0; + delete_fprobe_node(node); /* If no address list is available, we can't track this address. */ if (!alist->addrs) return 0; + /* + * Don't care the type here, because all fprobes on the same + * address must be removed eventually. + */ + if (!rhltable_lookup(&fprobe_ip_table, &node->addr, fprobe_rht_params)) { + alist->addrs[alist->index++] = node->addr; + if (alist->index == alist->size) + return -ENOSPC; + } - alist->addrs[alist->index++] = node->addr; - if (alist->index == alist->size) - return -ENOSPC; return 0; } @@ -933,7 +979,9 @@ static int unregister_fprobe_nolock(struct fprobe *fp) /* Remove non-synonim ips from table and hash */ count = 0; for (i = 0; i < hlist_array->size; i++) { - if (!delete_fprobe_node(&hlist_array->array[i]) && addrs) + delete_fprobe_node(&hlist_array->array[i]); + if (addrs && !fprobe_exists_on_hash(hlist_array->array[i].addr, + fprobe_is_ftrace(fp))) addrs[count++] = hlist_array->array[i].addr; } del_fprobe_hash(fp); -- cgit v1.2.3 From 476c5bbae65c9ab60b61fca9abd72df75a077183 Mon Sep 17 00:00:00 2001 From: "Masami Hiramatsu (Google)" Date: Mon, 20 Apr 2026 23:01:27 +0900 Subject: tracing/fprobe: Fix to unregister ftrace_ops if it is empty on module unloading Fix fprobe to unregister ftrace_ops if corresponding type of fprobe does not exist on the fprobe_ip_table and it is expected to be empty when unloading modules. Since ftrace thinks that the empty hash means everything to be traced, if we set fprobes only on the unloaded module, all functions are traced unexpectedly after unloading module. e.g. # modprobe xt_LOG.ko # echo 'f:test log_tg*' > dynamic_events # echo 1 > events/fprobes/test/enable # cat enabled_functions log_tg [xt_LOG] (1) tramp: 0xffffffffa0004000 (fprobe_ftrace_entry+0x0/0x490) ->fprobe_ftrace_entry+0x0/0x490 log_tg_check [xt_LOG] (1) tramp: 0xffffffffa0004000 (fprobe_ftrace_entry+0x0/0x490) ->fprobe_ftrace_entry+0x0/0x490 log_tg_destroy [xt_LOG] (1) tramp: 0xffffffffa0004000 (fprobe_ftrace_entry+0x0/0x490) ->fprobe_ftrace_entry+0x0/0x490 # rmmod xt_LOG # wc -l enabled_functions 34085 enabled_functions Link: https://lore.kernel.org/all/177669368776.132053.10042301916765771279.stgit@mhiramat.tok.corp.google.com/ Signed-off-by: Masami Hiramatsu (Google) --- kernel/trace/fprobe.c | 224 +++++++++++++++++++++++++++++++++++--------------- 1 file changed, 159 insertions(+), 65 deletions(-) diff --git a/kernel/trace/fprobe.c b/kernel/trace/fprobe.c index d0a68a2c5eaf..cc49ebd2a773 100644 --- a/kernel/trace/fprobe.c +++ b/kernel/trace/fprobe.c @@ -79,7 +79,7 @@ static const struct rhashtable_params fprobe_rht_params = { }; /* Node insertion and deletion requires the fprobe_mutex */ -static int insert_fprobe_node(struct fprobe_hlist_node *node, struct fprobe *fp) +static int __insert_fprobe_node(struct fprobe_hlist_node *node, struct fprobe *fp) { int ret; @@ -92,7 +92,7 @@ static int insert_fprobe_node(struct fprobe_hlist_node *node, struct fprobe *fp) return ret; } -static void delete_fprobe_node(struct fprobe_hlist_node *node) +static void __delete_fprobe_node(struct fprobe_hlist_node *node) { lockdep_assert_held(&fprobe_mutex); @@ -250,7 +250,65 @@ static inline int __fprobe_kprobe_handler(unsigned long ip, unsigned long parent return ret; } +static int fprobe_fgraph_entry(struct ftrace_graph_ent *trace, struct fgraph_ops *gops, + struct ftrace_regs *fregs); +static void fprobe_return(struct ftrace_graph_ret *trace, + struct fgraph_ops *gops, + struct ftrace_regs *fregs); + +static struct fgraph_ops fprobe_graph_ops = { + .entryfunc = fprobe_fgraph_entry, + .retfunc = fprobe_return, +}; +/* Number of fgraph fprobe nodes */ +static int nr_fgraph_fprobes; +/* Is fprobe_graph_ops registered? */ +static bool fprobe_graph_registered; + +/* Add @addrs to the ftrace filter and register fgraph if needed. */ +static int fprobe_graph_add_ips(unsigned long *addrs, int num) +{ + int ret; + + lockdep_assert_held(&fprobe_mutex); + + ret = ftrace_set_filter_ips(&fprobe_graph_ops.ops, addrs, num, 0, 0); + if (ret) + return ret; + + if (!fprobe_graph_registered) { + ret = register_ftrace_graph(&fprobe_graph_ops); + if (WARN_ON_ONCE(ret)) { + ftrace_free_filter(&fprobe_graph_ops.ops); + return ret; + } + fprobe_graph_registered = true; + } + return 0; +} + +static void __fprobe_graph_unregister(void) +{ + if (fprobe_graph_registered) { + unregister_ftrace_graph(&fprobe_graph_ops); + ftrace_free_filter(&fprobe_graph_ops.ops); + fprobe_graph_registered = false; + } +} + +/* Remove @addrs from the ftrace filter and unregister fgraph if possible. */ +static void fprobe_graph_remove_ips(unsigned long *addrs, int num) +{ + lockdep_assert_held(&fprobe_mutex); + + if (!nr_fgraph_fprobes) + __fprobe_graph_unregister(); + else if (num) + ftrace_set_filter_ips(&fprobe_graph_ops.ops, addrs, num, 1, 0); +} + #if defined(CONFIG_DYNAMIC_FTRACE_WITH_ARGS) || defined(CONFIG_DYNAMIC_FTRACE_WITH_REGS) + /* ftrace_ops callback, this processes fprobes which have only entry_handler. */ static void fprobe_ftrace_entry(unsigned long ip, unsigned long parent_ip, struct ftrace_ops *ops, struct ftrace_regs *fregs) @@ -293,7 +351,10 @@ static struct ftrace_ops fprobe_ftrace_ops = { .func = fprobe_ftrace_entry, .flags = FTRACE_OPS_FL_SAVE_ARGS, }; -static int fprobe_ftrace_active; +/* Number of ftrace fprobe nodes */ +static int nr_ftrace_fprobes; +/* Is fprobe_ftrace_ops registered? */ +static bool fprobe_ftrace_registered; static int fprobe_ftrace_add_ips(unsigned long *addrs, int num) { @@ -305,26 +366,33 @@ static int fprobe_ftrace_add_ips(unsigned long *addrs, int num) if (ret) return ret; - if (!fprobe_ftrace_active) { + if (!fprobe_ftrace_registered) { ret = register_ftrace_function(&fprobe_ftrace_ops); if (ret) { ftrace_free_filter(&fprobe_ftrace_ops); return ret; } + fprobe_ftrace_registered = true; } - fprobe_ftrace_active++; return 0; } +static void __fprobe_ftrace_unregister(void) +{ + if (fprobe_ftrace_registered) { + unregister_ftrace_function(&fprobe_ftrace_ops); + ftrace_free_filter(&fprobe_ftrace_ops); + fprobe_ftrace_registered = false; + } +} + static void fprobe_ftrace_remove_ips(unsigned long *addrs, int num) { lockdep_assert_held(&fprobe_mutex); - fprobe_ftrace_active--; - if (!fprobe_ftrace_active) { - unregister_ftrace_function(&fprobe_ftrace_ops); - ftrace_free_filter(&fprobe_ftrace_ops); - } else if (num) + if (!nr_ftrace_fprobes) + __fprobe_ftrace_unregister(); + else if (num) ftrace_set_filter_ips(&fprobe_ftrace_ops, addrs, num, 1, 0); } @@ -333,6 +401,40 @@ static bool fprobe_is_ftrace(struct fprobe *fp) return !fp->exit_handler; } +/* Node insertion and deletion requires the fprobe_mutex */ +static int insert_fprobe_node(struct fprobe_hlist_node *node, struct fprobe *fp) +{ + int ret; + + lockdep_assert_held(&fprobe_mutex); + + ret = __insert_fprobe_node(node, fp); + if (!ret) { + if (fprobe_is_ftrace(fp)) + nr_ftrace_fprobes++; + else + nr_fgraph_fprobes++; + } + + return ret; +} + +static void delete_fprobe_node(struct fprobe_hlist_node *node) +{ + struct fprobe *fp; + + lockdep_assert_held(&fprobe_mutex); + + fp = READ_ONCE(node->fp); + if (fp) { + if (fprobe_is_ftrace(fp)) + nr_ftrace_fprobes--; + else + nr_fgraph_fprobes--; + } + __delete_fprobe_node(node); +} + static bool fprobe_exists_on_hash(unsigned long ip, bool ftrace) { struct rhlist_head *head, *pos; @@ -362,8 +464,15 @@ static bool fprobe_exists_on_hash(unsigned long ip, bool ftrace) #ifdef CONFIG_MODULES static void fprobe_remove_ips(unsigned long *ips, unsigned int cnt) { - ftrace_set_filter_ips(&fprobe_graph_ops.ops, ips, cnt, 1, 0); - ftrace_set_filter_ips(&fprobe_ftrace_ops, ips, cnt, 1, 0); + if (!nr_fgraph_fprobes) + __fprobe_graph_unregister(); + else if (cnt) + ftrace_set_filter_ips(&fprobe_graph_ops.ops, ips, cnt, 1, 0); + + if (!nr_ftrace_fprobes) + __fprobe_ftrace_unregister(); + else if (cnt) + ftrace_set_filter_ips(&fprobe_ftrace_ops, ips, cnt, 1, 0); } #endif #else @@ -381,6 +490,32 @@ static bool fprobe_is_ftrace(struct fprobe *fp) return false; } +/* Node insertion and deletion requires the fprobe_mutex */ +static int insert_fprobe_node(struct fprobe_hlist_node *node, struct fprobe *fp) +{ + int ret; + + lockdep_assert_held(&fprobe_mutex); + + ret = __insert_fprobe_node(node, fp); + if (!ret) + nr_fgraph_fprobes++; + + return ret; +} + +static void delete_fprobe_node(struct fprobe_hlist_node *node) +{ + struct fprobe *fp; + + lockdep_assert_held(&fprobe_mutex); + + fp = READ_ONCE(node->fp); + if (fp) + nr_fgraph_fprobes--; + __delete_fprobe_node(node); +} + static bool fprobe_exists_on_hash(unsigned long ip, bool ftrace __maybe_unused) { struct rhlist_head *head, *pos; @@ -407,7 +542,10 @@ static bool fprobe_exists_on_hash(unsigned long ip, bool ftrace __maybe_unused) #ifdef CONFIG_MODULES static void fprobe_remove_ips(unsigned long *ips, unsigned int cnt) { - ftrace_set_filter_ips(&fprobe_graph_ops.ops, ips, cnt, 1, 0); + if (!nr_fgraph_fprobes) + __fprobe_graph_unregister(); + else if (cnt) + ftrace_set_filter_ips(&fprobe_graph_ops.ops, ips, cnt, 1, 0); } #endif #endif /* !CONFIG_DYNAMIC_FTRACE_WITH_ARGS && !CONFIG_DYNAMIC_FTRACE_WITH_REGS */ @@ -535,48 +673,6 @@ static void fprobe_return(struct ftrace_graph_ret *trace, } NOKPROBE_SYMBOL(fprobe_return); -static struct fgraph_ops fprobe_graph_ops = { - .entryfunc = fprobe_fgraph_entry, - .retfunc = fprobe_return, -}; -static int fprobe_graph_active; - -/* Add @addrs to the ftrace filter and register fgraph if needed. */ -static int fprobe_graph_add_ips(unsigned long *addrs, int num) -{ - int ret; - - lockdep_assert_held(&fprobe_mutex); - - ret = ftrace_set_filter_ips(&fprobe_graph_ops.ops, addrs, num, 0, 0); - if (ret) - return ret; - - if (!fprobe_graph_active) { - ret = register_ftrace_graph(&fprobe_graph_ops); - if (WARN_ON_ONCE(ret)) { - ftrace_free_filter(&fprobe_graph_ops.ops); - return ret; - } - } - fprobe_graph_active++; - return 0; -} - -/* Remove @addrs from the ftrace filter and unregister fgraph if possible. */ -static void fprobe_graph_remove_ips(unsigned long *addrs, int num) -{ - lockdep_assert_held(&fprobe_mutex); - - fprobe_graph_active--; - /* Q: should we unregister it ? */ - if (!fprobe_graph_active) { - unregister_ftrace_graph(&fprobe_graph_ops); - ftrace_free_filter(&fprobe_graph_ops.ops); - } else if (num) - ftrace_set_filter_ips(&fprobe_graph_ops.ops, addrs, num, 1, 0); -} - #ifdef CONFIG_MODULES #define FPROBE_IPS_BATCH_INIT 128 @@ -653,16 +749,14 @@ again: } while (node == ERR_PTR(-EAGAIN) && !retry); rhashtable_walk_exit(&iter); /* Remove any ips from hash table(s) */ - if (alist.index > 0) { - fprobe_remove_ips(alist.addrs, alist.index); - /* - * If we break rhashtable walk loop except for -EAGAIN, we need - * to restart looping from start for safety. Anyway, this is - * not a hotpath. - */ - if (retry) - goto again; - } + fprobe_remove_ips(alist.addrs, alist.index); + /* + * If we break rhashtable walk loop except for -EAGAIN, we need + * to restart looping from start for safety. Anyway, this is + * not a hotpath. + */ + if (retry) + goto again; mutex_unlock(&fprobe_mutex); -- cgit v1.2.3 From 132001e9f90e577d002e0ba613205340c579921f Mon Sep 17 00:00:00 2001 From: "Masami Hiramatsu (Google)" Date: Mon, 20 Apr 2026 23:01:35 +0900 Subject: selftests/ftrace: Add a testcase for fprobe events on module Add a testcase for fprobe events on module, which unloads a kernel module on which fprobe events are probing and ensure the ftrace hash map is cleared correctly. Link: https://lore.kernel.org/all/177669369564.132053.623527664540176496.stgit@mhiramat.tok.corp.google.com/ Signed-off-by: Masami Hiramatsu (Google) --- .../test.d/dynevent/add_remove_fprobe_module.tc | 87 ++++++++++++++++++++++ 1 file changed, 87 insertions(+) create mode 100644 tools/testing/selftests/ftrace/test.d/dynevent/add_remove_fprobe_module.tc diff --git a/tools/testing/selftests/ftrace/test.d/dynevent/add_remove_fprobe_module.tc b/tools/testing/selftests/ftrace/test.d/dynevent/add_remove_fprobe_module.tc new file mode 100644 index 000000000000..2915206777b6 --- /dev/null +++ b/tools/testing/selftests/ftrace/test.d/dynevent/add_remove_fprobe_module.tc @@ -0,0 +1,87 @@ +#!/bin/sh +# SPDX-License-Identifier: GPL-2.0 +# description: Generic dynamic event - add/remove fprobe events on module +# requires: dynamic_events "f[:[/][]] [%return] []":README enabled_functions + +rmmod trace-events-sample ||: +if ! modprobe trace-events-sample ; then + echo "No trace-events sample module - please make CONFIG_SAMPLE_TRACE_EVENTS=m" + exit_unresolved; +fi +trap "lsmod | grep -q trace_events_sample && rmmod trace-events-sample" EXIT + +echo 0 > events/enable +echo > dynamic_events + +FUNC1='foo_bar*' +FUNC2='vfs_read' + +:;: "Add an event on the test module" ;: +echo "f:test1 $FUNC1" >> dynamic_events +echo 1 > events/fprobes/test1/enable + +:;: "Ensure it is enabled" ;: +funcs=`cat enabled_functions | wc -l` +test $funcs -ne 0 + +:;: "Check the enabled_functions is cleared on unloading" ;: +rmmod trace-events-sample +funcs=`cat enabled_functions | wc -l` +test $funcs -eq 0 + +:;: "Check it is kept clean" ;: +modprobe trace-events-sample +echo 1 > events/fprobes/test1/enable || echo "OK" +funcs=`cat enabled_functions | wc -l` +test $funcs -eq 0 + +:;: "Add another event not on the test module" ;: +echo "f:test2 $FUNC2" >> dynamic_events +echo 1 > events/fprobes/test2/enable + +:;: "Ensure it is enabled" ;: +ofuncs=`cat enabled_functions | wc -l` +test $ofuncs -ne 0 + +:;: "Disable and remove the first event" +echo 0 > events/fprobes/test1/enable +echo "-:fprobes/test1" >> dynamic_events +funcs=`cat enabled_functions | wc -l` +test $ofuncs -eq $funcs + +:;: "Disable and remove other events" ;: +echo 0 > events/fprobes/enable +echo > dynamic_events +funcs=`cat enabled_functions | wc -l` +test $funcs -eq 0 + +rmmod trace-events-sample + +:;: "Add events on kernel and test module" ;: +modprobe trace-events-sample +echo "f:test1 $FUNC1" >> dynamic_events +echo 1 > events/fprobes/test1/enable +echo "f:test2 $FUNC2" >> dynamic_events +echo 1 > events/fprobes/test2/enable +ofuncs=`cat enabled_functions | wc -l` +test $ofuncs -ne 0 + +:;: "Unload module (ftrace entry should be removed)" ;: +rmmod trace-events-sample +funcs=`cat enabled_functions | wc -l` +test $funcs -ne 0 +test $ofuncs -ne $funcs + +:;: "Disable and remove core-kernel fprobe event" ;: +echo 0 > events/fprobes/test2/enable +echo "-:fprobes/test2" >> dynamic_events + +:;: "Ensure ftrace is disabled." ;: +funcs=`cat enabled_functions | wc -l` +test $funcs -eq 0 + +echo 0 > events/fprobes/enable +echo > dynamic_events + +trap "" EXIT +clear_trace -- cgit v1.2.3 From 453553e1ed53ca364454e155ba33e110d02c75cd Mon Sep 17 00:00:00 2001 From: "Masami Hiramatsu (Google)" Date: Mon, 20 Apr 2026 23:01:43 +0900 Subject: selftests/ftrace: Add a testcase for multiple fprobe events Add a testcase for multiple fprobe events on the same function so that it clears ftrace hash map correctly when removing the events. Link: https://lore.kernel.org/all/177669370353.132053.16801520791509406141.stgit@mhiramat.tok.corp.google.com/ Signed-off-by: Masami Hiramatsu (Google) --- .../test.d/dynevent/add_remove_multiple_fprobe.tc | 69 ++++++++++++++++++++++ 1 file changed, 69 insertions(+) create mode 100644 tools/testing/selftests/ftrace/test.d/dynevent/add_remove_multiple_fprobe.tc diff --git a/tools/testing/selftests/ftrace/test.d/dynevent/add_remove_multiple_fprobe.tc b/tools/testing/selftests/ftrace/test.d/dynevent/add_remove_multiple_fprobe.tc new file mode 100644 index 000000000000..f2cbf2ffd29b --- /dev/null +++ b/tools/testing/selftests/ftrace/test.d/dynevent/add_remove_multiple_fprobe.tc @@ -0,0 +1,69 @@ +#!/bin/sh +# SPDX-License-Identifier: GPL-2.0 +# description: Generic dynamic event - add/remove multiple fprobe events on the same function +# requires: dynamic_events "f[:[/][]] [%return] []":README enabled_functions + +echo 0 > events/enable +echo > dynamic_events + +PLACE=vfs_read +PLACE2=vfs_open + +:;: 'Ensure no other ftrace user' ;: +test `cat enabled_functions | wc -l` -eq 0 || exit_unresolved + +:;: 'Test case 1: leave entry event' ;: +:;: 'Add entry and exit events on the same place' ;: +echo "f:event1 ${PLACE}" >> dynamic_events +echo "f:event2 ${PLACE}%return" >> dynamic_events + +:;: 'Enable both of them' ;: +echo 1 > events/fprobes/enable +test `cat enabled_functions | wc -l` -eq 1 + +:;: 'Disable and remove exit event' ;: +echo 0 > events/fprobes/event2/enable +echo -:event2 >> dynamic_events + +:;: 'Disable and remove all events' ;: +echo 0 > events/fprobes/enable +echo > dynamic_events + +:;: 'Add another event' ;: +echo "f:event3 ${PLACE2}%return" > dynamic_events +echo 1 > events/fprobes/enable +test `cat enabled_functions | wc -l` -eq 1 + +:;: 'No other ftrace user' ;: +echo 0 > events/fprobes/enable +echo > dynamic_events +test `cat enabled_functions | wc -l` -eq 0 + +:;: 'Test case 2: leave exit event' ;: +:;: 'Add entry and exit events on the same place' ;: +echo "f:event1 ${PLACE}" >> dynamic_events +echo "f:event2 ${PLACE}%return" >> dynamic_events + +:;: 'Enable both of them' ;: +echo 1 > events/fprobes/enable +test `cat enabled_functions | wc -l` -eq 1 + +:;: 'Disable and remove entry event' ;: +echo 0 > events/fprobes/event1/enable +echo -:event1 >> dynamic_events + +:;: 'Disable and remove all events' ;: +echo 0 > events/fprobes/enable +echo > dynamic_events + +:;: 'Add another event' ;: +echo "f:event3 ${PLACE2}" > dynamic_events +echo 1 > events/fprobes/enable +test `cat enabled_functions | wc -l` -eq 1 + +:;: 'No other ftrace user' ;: +echo 0 > events/fprobes/enable +echo > dynamic_events +test `cat enabled_functions | wc -l` -eq 0 + +clear_trace -- cgit v1.2.3