From nobody Mon Jun 15 13:42:43 2026 Received: from smtp.kernel.org (aws-us-west-2-korg-mail-1.web.codeaurora.org [10.30.226.201]) (using TLSv1.2 with cipher ECDHE-RSA-AES256-GCM-SHA384 (256/256 bits)) (No client certificate requested) by smtp.subspace.kernel.org (Postfix) with ESMTPS id CA4D53E314F; Fri, 10 Apr 2026 17:11:43 +0000 (UTC) Authentication-Results: smtp.subspace.kernel.org; arc=none smtp.client-ip=10.30.226.201 ARC-Seal: i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1775841103; cv=none; b=UEBZZcEZYeNFkEY233UNq4XxR2YWK3EU3oCOqAJyh2gYFpg+3DVq4MG6qG7R6KfOo1RhEQKPTpzZRGvq8PMF39npTmlw3/xSqa0ZxFBXIltyW7OBH5fymElEZ5fIGAYQtdMgb3PoOrqTfx8eLEIq+fbidQ7T5ygliOZ+uWY/5rs= ARC-Message-Signature: i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1775841103; c=relaxed/simple; bh=lAG3bww15i7ITAMim36ZtF0uvho3IT70zGWNBF/aj30=; h=From:To:Cc:Subject:Date:Message-ID:In-Reply-To:References: MIME-Version:Content-Type; b=bdhLdEosq2YlRnCquqKpZ6EEwl3PFEQWugt/UbV1KNxNKaj8QvJwx97dCVtf00c08sjsiqo+HUqQE5nI0UmMeoFyoBmjH9DbK7FyU7+PNfrEmM6YwE7UwcrCXPq6dSlsGAb7emsrZ51t+uVmi7+Zgya4Doa4wp2EcOf2Z53jQJw= ARC-Authentication-Results: i=1; smtp.subspace.kernel.org; dkim=pass (2048-bit key) header.d=kernel.org header.i=@kernel.org header.b=jrrPX5f2; arc=none smtp.client-ip=10.30.226.201 Authentication-Results: smtp.subspace.kernel.org; dkim=pass (2048-bit key) header.d=kernel.org header.i=@kernel.org header.b="jrrPX5f2" Received: by smtp.kernel.org (Postfix) with ESMTPSA id 5F3B7C19421; Fri, 10 Apr 2026 17:11:41 +0000 (UTC) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/simple; d=kernel.org; s=k20201202; t=1775841103; bh=lAG3bww15i7ITAMim36ZtF0uvho3IT70zGWNBF/aj30=; h=From:To:Cc:Subject:Date:In-Reply-To:References:From; b=jrrPX5f2kbAcmD8qQaLX65jkoZ9QT9NkP78T/ah+dEq+bYuNi2ae4F4SkRTX1yUHl JpTlSyAqGdoycrEyWZQJNYQQGQOAGIEfvexh7tzpB+FdW0lTvTiSCh5xFhUKJnyl6Z itDOmsKXdJkjup2l/njIokaMJrT++KnwOFlwVKCLuS2eh4hJYe5r28LU9o/i2Wa2ri HqtH1QSmONzc3e7/nqtMjHEA/vfJ62cU4/wACJGeJgfBD90kWP8eICr3Ex9G8zpMr2 e966aSZh2/C8BI3+FrKP9VmhLEzVn0c2dxGWsGfqx0Zo181evLNKVyrzaINtqYUFEv b++WH9J19YWkw== From: "Masami Hiramatsu (Google)" To: Steven Rostedt , Masami Hiramatsu Cc: Menglong Dong , Mathieu Desnoyers , jiang.biao@linux.dev, linux-kernel@vger.kernel.org, linux-trace-kernel@vger.kernel.org Subject: [PATCH v4 1/3] tracing/fprobe: Remove fprobe from hash in failure path Date: Sat, 11 Apr 2026 02:11:38 +0900 Message-ID: <177584109879.388483.14499258580060375437.stgit@devnote2> X-Mailer: git-send-email 2.43.0 In-Reply-To: <177584108931.388483.11311214679686745474.stgit@devnote2> References: <177584108931.388483.11311214679686745474.stgit@devnote2> User-Agent: StGit/0.19 Precedence: bulk X-Mailing-List: linux-kernel@vger.kernel.org List-Id: List-Subscribe: List-Unsubscribe: MIME-Version: 1.0 Content-Type: text/plain; charset="utf-8" Content-Transfer-Encoding: quoted-printable From: Masami Hiramatsu (Google) 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. Fixes: 4346ba160409 ("fprobe: Rewrite fprobe on function-graph tracer") Signed-off-by: Masami Hiramatsu (Google) --- Changes in v4: - Remove short-cut case because we always need to upadte ftrace_ops. - Use guard(mutex) in register_fprobe_ips() to unlock it correctly. - Remove redundant !ret check in register_fprobe_ips(). - Do not set hlist_array->size in failure case, instead, hlist_array->array[i].fp is set only when insertion is succeeded. Changes in v3: - Newly added. --- kernel/trace/fprobe.c | 95 +++++++++++++++++++++++++--------------------= ---- 1 file changed, 48 insertions(+), 47 deletions(-) diff --git a/kernel/trace/fprobe.c b/kernel/trace/fprobe.c index dcadf1d23b8a..a7c0d5f9016b 100644 --- a/kernel/trace/fprobe.c +++ b/kernel/trace/fprobe.c @@ -4,6 +4,7 @@ */ #define pr_fmt(fmt) "fprobe: " fmt =20 +#include #include #include #include @@ -78,20 +79,27 @@ static const struct rhashtable_params fprobe_rht_params= =3D { }; =20 /* 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 fprob= e *fp) { + int ret; + lockdep_assert_held(&fprobe_mutex); =20 - return rhltable_insert(&fprobe_ip_table, &node->hlist, fprobe_rht_params); + ret =3D 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; } =20 /* Return true if there are synonims */ static bool delete_fprobe_node(struct fprobe_hlist_node *node) { - lockdep_assert_held(&fprobe_mutex); bool ret; =20 - /* Avoid double deleting */ + lockdep_assert_held(&fprobe_mutex); + + /* Avoid double deleting and non-inserted nodes */ if (READ_ONCE(node->fp) !=3D NULL) { WRITE_ONCE(node->fp, NULL); rhltable_remove(&fprobe_ip_table, &node->hlist, @@ -759,7 +767,6 @@ static int fprobe_init(struct fprobe *fp, unsigned long= *addrs, int num) fp->hlist_array =3D hlist_array; hlist_array->fp =3D fp; for (i =3D 0; i < num; i++) { - hlist_array->array[i].fp =3D fp; addr =3D ftrace_location(addrs[i]); if (!addr) { fprobe_fail_cleanup(fp); @@ -823,6 +830,8 @@ int register_fprobe(struct fprobe *fp, const char *filt= er, const char *notfilter } EXPORT_SYMBOL_GPL(register_fprobe); =20 +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. @@ -845,31 +854,26 @@ int register_fprobe_ips(struct fprobe *fp, unsigned l= ong *addrs, int num) if (ret) return ret; =20 - mutex_lock(&fprobe_mutex); + guard(mutex)(&fprobe_mutex); =20 - hlist_array =3D fp->hlist_array; if (fprobe_is_ftrace(fp)) ret =3D fprobe_ftrace_add_ips(addrs, num); else ret =3D fprobe_graph_add_ips(addrs, num); + if (ret) { + fprobe_fail_cleanup(fp); + return ret; + } =20 - if (!ret) { - add_fprobe_hash(fp); - for (i =3D 0; i < hlist_array->size; i++) { - ret =3D insert_fprobe_node(&hlist_array->array[i]); - if (ret) - break; - } - /* fallback on insert error */ + hlist_array =3D fp->hlist_array; + add_fprobe_hash(fp); + for (i =3D 0; i < hlist_array->size; i++) { + ret =3D insert_fprobe_node(&hlist_array->array[i], fp); if (ret) { - for (i--; i >=3D 0; i--) - delete_fprobe_node(&hlist_array->array[i]); + unregister_fprobe_nolock(fp); + break; } } - mutex_unlock(&fprobe_mutex); - - if (ret) - fprobe_fail_cleanup(fp); =20 return ret; } @@ -913,32 +917,15 @@ bool fprobe_is_registered(struct fprobe *fp) return true; } =20 -/** - * 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 =3D fp->hlist_array; unsigned long *addrs =3D NULL; - int ret =3D 0, i, count; + int i, count; =20 - mutex_lock(&fprobe_mutex); - if (!fp || !is_fprobe_still_exist(fp)) { - ret =3D -EINVAL; - goto out; - } - - hlist_array =3D fp->hlist_array; addrs =3D kcalloc(hlist_array->size, sizeof(unsigned long), GFP_KERNEL); - if (!addrs) { - ret =3D -ENOMEM; /* TODO: Fallback to one-by-one loop */ - goto out; - } + if (!addrs) + return -ENOMEM; /* TODO: Fallback to one-by-one loop */ =20 /* Remove non-synonim ips from table and hash */ count =3D 0; @@ -955,12 +942,26 @@ int unregister_fprobe(struct fprobe *fp) =20 kfree_rcu(hlist_array, rcu); fp->hlist_array =3D NULL; + kfree(addrs); =20 -out: - mutex_unlock(&fprobe_mutex); + return 0; +} =20 - 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 || !is_fprobe_still_exist(fp)) + return -EINVAL; + + return unregister_fprobe_nolock(fp); } EXPORT_SYMBOL_GPL(unregister_fprobe); From nobody Mon Jun 15 13:42:43 2026 Received: from smtp.kernel.org (aws-us-west-2-korg-mail-1.web.codeaurora.org [10.30.226.201]) (using TLSv1.2 with cipher ECDHE-RSA-AES256-GCM-SHA384 (256/256 bits)) (No client certificate requested) by smtp.subspace.kernel.org (Postfix) with ESMTPS id EED9D3E277C; Fri, 10 Apr 2026 17:11:53 +0000 (UTC) Authentication-Results: smtp.subspace.kernel.org; arc=none smtp.client-ip=10.30.226.201 ARC-Seal: i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1775841114; cv=none; b=KL9Sx23khPPPgUtkHOW679W3QTEHSw022L06nehrWE9L/yjK+yGWoxYTIqkMJPTLarovKAGuDGiHuyoY0XRdfrf0zPGKe9RQAu8REa1aXzCcWXkYGyWKEJbyKWm5wpm4jlCCj0Ooq13HcR9ZFWDOGdC6iVJx22bWXleBZKbU0hA= ARC-Message-Signature: i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1775841114; c=relaxed/simple; bh=sMvywU0Ew7ALrP1iCBRTav3iZxiHo74useCiIoc4G+I=; h=From:To:Cc:Subject:Date:Message-ID:In-Reply-To:References: MIME-Version:Content-Type; b=ZRQQQmnIwrNwHxBaiRyhppU3LoAgM4UkcKiOnTftQg9I/2AHOLgTv8zekbF+O2/1pAwoDXxgclfofTuUzs8+FRo3vpLWPfc3eL33oby/dCV75D3Lrc3yK3ejXvZwKLKnyffjy+XTdwBr/Bob0nyAI/PeemRPk6OEgE1uLiy88IY= ARC-Authentication-Results: i=1; smtp.subspace.kernel.org; dkim=pass (2048-bit key) header.d=kernel.org header.i=@kernel.org header.b=tndNPwGo; arc=none smtp.client-ip=10.30.226.201 Authentication-Results: smtp.subspace.kernel.org; dkim=pass (2048-bit key) header.d=kernel.org header.i=@kernel.org header.b="tndNPwGo" Received: by smtp.kernel.org (Postfix) with ESMTPSA id 809FAC19421; Fri, 10 Apr 2026 17:11:51 +0000 (UTC) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/simple; d=kernel.org; s=k20201202; t=1775841113; bh=sMvywU0Ew7ALrP1iCBRTav3iZxiHo74useCiIoc4G+I=; h=From:To:Cc:Subject:Date:In-Reply-To:References:From; b=tndNPwGo1qcWy5sEAW4z99Ud7+CB942OcnuRGRAOMjhnJRbRrNbQXR/RiJhVpSewP ezFbl8liTWpcghDbNccC4M18EY6qsTKACUn0MxN4RczYGwzvyGSUjnnr+VRVixDi5g fAksKx9h0UVNYQ7GDBw0GhVkg/ds+NgGFMvG7bv28Wg7gwIcpM3O6NcGeUe//lJlAB Oo9X/9JubCQlztVcTpB84ODkUm4Q15rTXofEqh3v9SSubhtpgZMj9F/VF9euGfiYY1 jfEOc584pNqomnUlZQ8BBDWzjPG8k0KkhLvH8zc6U25FyqN4U+7zaAyqPNhzq+ALZi sVF3tOhYxDXoA== From: "Masami Hiramatsu (Google)" To: Steven Rostedt , Masami Hiramatsu Cc: Menglong Dong , Mathieu Desnoyers , jiang.biao@linux.dev, linux-kernel@vger.kernel.org, linux-trace-kernel@vger.kernel.org Subject: [PATCH v4 2/3] tracing/fprobe: Avoid kcalloc() in rcu_read_lock section Date: Sat, 11 Apr 2026 02:11:48 +0900 Message-ID: <177584110853.388483.637011075513179835.stgit@devnote2> X-Mailer: git-send-email 2.43.0 In-Reply-To: <177584108931.388483.11311214679686745474.stgit@devnote2> References: <177584108931.388483.11311214679686745474.stgit@devnote2> User-Agent: StGit/0.19 Precedence: bulk X-Mailing-List: linux-kernel@vger.kernel.org List-Id: List-Subscribe: List-Unsubscribe: MIME-Version: 1.0 Content-Type: text/plain; charset="utf-8" Content-Transfer-Encoding: quoted-printable From: Masami Hiramatsu (Google) 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. Fixes: 0de4c70d04a4 ("tracing: fprobe: use rhltable for fprobe_ip_table") Cc: stable@vger.kernel.org Signed-off-by: Masami Hiramatsu (Google) --- Changes in v4: - fix a build error typo in case of CONFIG_DYNAMIC_FTRACE=3Dn. Changes in v3: - Retry inside rhltable_walk_enter/exit(). - Rename fprobe_set_ips() to fprobe_remove_ips(). - Rename 'retry' label to 'again'. --- kernel/trace/fprobe.c | 75 ++++++++++++++++++++-------------------------= ---- 1 file changed, 30 insertions(+), 45 deletions(-) diff --git a/kernel/trace/fprobe.c b/kernel/trace/fprobe.c index a7c0d5f9016b..799332f865f8 100644 --- a/kernel/trace/fprobe.c +++ b/kernel/trace/fprobe.c @@ -346,11 +346,10 @@ static bool fprobe_is_ftrace(struct fprobe *fp) } =20 #ifdef CONFIG_MODULES -static void fprobe_set_ips(unsigned long *ips, unsigned int cnt, int remov= e, - 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 @@ -369,10 +368,9 @@ static bool fprobe_is_ftrace(struct fprobe *fp) } =20 #ifdef CONFIG_MODULES -static void fprobe_set_ips(unsigned long *ips, unsigned int cnt, int remov= e, - 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 */ @@ -546,7 +544,7 @@ static void fprobe_graph_remove_ips(unsigned long *addr= s, int num) =20 #ifdef CONFIG_MODULES =20 -#define FPROBE_IPS_BATCH_INIT 8 +#define FPROBE_IPS_BATCH_INIT 128 /* instruction pointer address list */ struct fprobe_addr_list { int index; @@ -554,45 +552,21 @@ struct fprobe_addr_list { unsigned long *addrs; }; =20 -static int fprobe_addr_list_add(struct fprobe_addr_list *alist, unsigned l= ong 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 =3D=3D alist->size) - return -ENOSPC; - - alist->addrs[alist->index++] =3D addr; - if (alist->index < alist->size) + if (!within_module(node->addr, mod)) return 0; =20 - /* Expand the address list */ - addrs =3D kcalloc(alist->size * 2, sizeof(*addrs), GFP_KERNEL); - if (!addrs) - return -ENOMEM; - - memcpy(addrs, alist->addrs, alist->size * sizeof(*addrs)); - alist->size *=3D 2; - kfree(alist->addrs); - alist->addrs =3D addrs; + if (delete_fprobe_node(node)) + return 0; =20 + alist->addrs[alist->index++] =3D node->addr; + if (alist->index =3D=3D alist->size) + return -ENOSPC; return 0; } =20 -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) @@ -601,6 +575,7 @@ static int fprobe_module_callback(struct notifier_block= *nb, struct fprobe_hlist_node *node; struct rhashtable_iter iter; struct module *mod =3D data; + bool retry; =20 if (val !=3D MODULE_STATE_GOING) return NOTIFY_DONE; @@ -612,18 +587,28 @@ static int fprobe_module_callback(struct notifier_blo= ck *nb, =20 mutex_lock(&fprobe_mutex); rhltable_walk_enter(&fprobe_ip_table, &iter); +again: + retry =3D false; + alist.index =3D 0; do { rhashtable_walk_start(&iter); =20 while ((node =3D 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 =3D true; + break; + } =20 rhashtable_walk_stop(&iter); - } while (node =3D=3D ERR_PTR(-EAGAIN)); - rhashtable_walk_exit(&iter); + } while (node =3D=3D ERR_PTR(-EAGAIN) && !retry); + /* Remove any ips from hash table(s) */ + if (alist.index > 0) { + fprobe_remove_ips(alist.addrs, alist.index); + if (retry) + goto again; + } =20 - if (alist.index > 0) - fprobe_set_ips(alist.addrs, alist.index, 1, 0); + rhashtable_walk_exit(&iter); mutex_unlock(&fprobe_mutex); =20 kfree(alist.addrs); From nobody Mon Jun 15 13:42:43 2026 Received: from smtp.kernel.org (aws-us-west-2-korg-mail-1.web.codeaurora.org [10.30.226.201]) (using TLSv1.2 with cipher ECDHE-RSA-AES256-GCM-SHA384 (256/256 bits)) (No client certificate requested) by smtp.subspace.kernel.org (Postfix) with ESMTPS id A5DEB3E314F; Fri, 10 Apr 2026 17:12:03 +0000 (UTC) Authentication-Results: smtp.subspace.kernel.org; arc=none smtp.client-ip=10.30.226.201 ARC-Seal: i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1775841123; cv=none; b=b/i8w1AnD58d560638ltxuGF7mTLEmyZ2OiX5VzRVhn5OqH080Xr792xW+dmeg3Q/zrExJ/RnZxUg9AkjSyNtxVxXKgRgmCv4NrUsui6KX3ESKlTfYGTw3+tu5bVg9HKNbMhsJVEbNlYQMb7412HEaRXZ49D95rAGCKX529KXGs= ARC-Message-Signature: i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1775841123; c=relaxed/simple; bh=HGnNaiPjP8ZtBLC/bBwOU7J5HGe5OgE6j20D6I08n2M=; h=From:To:Cc:Subject:Date:Message-ID:In-Reply-To:References: MIME-Version:Content-Type; b=Z4rey8TToIUCUuMxz6JNV682bMctcsdKqG8pXBsXe6alZxqre8GVrBel3xii4CGld8mtM2IQr92jNhVd2xDiQZz/T1ccyEaUsh6+MXaVs5tQMQYn/C5hZqjSue+D4H267zrwbXxlcepwh/98uufboHOW3zvHDcC52+jhRvT16Ac= ARC-Authentication-Results: i=1; smtp.subspace.kernel.org; dkim=pass (2048-bit key) header.d=kernel.org header.i=@kernel.org header.b=OgEB4D03; arc=none smtp.client-ip=10.30.226.201 Authentication-Results: smtp.subspace.kernel.org; dkim=pass (2048-bit key) header.d=kernel.org header.i=@kernel.org header.b="OgEB4D03" Received: by smtp.kernel.org (Postfix) with ESMTPSA id 57EACC19421; Fri, 10 Apr 2026 17:12:01 +0000 (UTC) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/simple; d=kernel.org; s=k20201202; t=1775841123; bh=HGnNaiPjP8ZtBLC/bBwOU7J5HGe5OgE6j20D6I08n2M=; h=From:To:Cc:Subject:Date:In-Reply-To:References:From; b=OgEB4D03+wU5IhYnWVws37+TmUNnXzQYuHTMbYHOSQQmS8X2cII8ANJ7fDK/H/D1Q a9zor+d35SkO1cUd0DaAr+5nUJnz0uNBGne1uKMJblHg9M8xaG+M3gk7JBdlHUAgdr m7PJvPcbxJ2J4WKgZdBTGbTD+d8pZwA/4L2ECA0lc6rzno16HyR8g3mCN4LRQYO9r5 AERWwkUnRptGTZljlbsi63Z6Ck4FtARMcYiNy1q7cTc3Wo/teLZb5CLxvPZDGV7yfM HYFNwecFxf+Uo0WHRSCXi2Y3akaJT8in00rwCDyjyQtXQtK8pX8H4edB5wVfsQyrDB o1ww141P0IULQ== From: "Masami Hiramatsu (Google)" To: Steven Rostedt , Masami Hiramatsu Cc: Menglong Dong , Mathieu Desnoyers , jiang.biao@linux.dev, linux-kernel@vger.kernel.org, linux-trace-kernel@vger.kernel.org Subject: [PATCH v4 3/3] tracing/fprobe: Check the same type fprobe on table as the unregistered one Date: Sat, 11 Apr 2026 02:11:58 +0900 Message-ID: <177584111887.388483.3432533037945624434.stgit@devnote2> X-Mailer: git-send-email 2.43.0 In-Reply-To: <177584108931.388483.11311214679686745474.stgit@devnote2> References: <177584108931.388483.11311214679686745474.stgit@devnote2> User-Agent: StGit/0.19 Precedence: bulk X-Mailing-List: linux-kernel@vger.kernel.org List-Id: List-Subscribe: List-Unsubscribe: MIME-Version: 1.0 Content-Type: text/plain; charset="utf-8" Content-Transfer-Encoding: quoted-printable From: Masami Hiramatsu (Google) 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: =3D=3D=3D=3D=3D=3D=3D 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+0x0/0x= 60) ->ftrace_graph_func+0x0/0x60 subops: {ent:fprobe_fgraph_entry+0x0/0x= 620 ret:fprobe_return+0x0/0x150} vfs_read (1) tramp: 0xffffffffa0001000 (ftrace_graph_func+0x0/0x= 60) ->ftrace_graph_func+0x0/0x60 subops: {ent:fprobe_fgraph_entry+0x0/0x= 620 ret:fprobe_return+0x0/0x150} =3D=3D=3D=3D=3D=3D=3D 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. 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 799332f865f8..2cac2252f78f 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; } =20 -/* 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); =20 /* Avoid double deleting and non-inserted nodes */ @@ -105,13 +102,6 @@ static bool delete_fprobe_node(struct fprobe_hlist_nod= e *node) rhltable_remove(&fprobe_ip_table, &node->hlist, fprobe_rht_params); } - - rcu_read_lock(); - ret =3D !!rhltable_lookup(&fprobe_ip_table, &node->addr, - fprobe_rht_params); - rcu_read_unlock(); - - return ret; } =20 /* Check existence of the fprobe */ @@ -345,6 +335,32 @@ static bool fprobe_is_ftrace(struct fprobe *fp) return !fp->exit_handler; } =20 +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 =3D 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 !=3D ip) + break; + fp =3D 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) { @@ -367,6 +383,29 @@ static bool fprobe_is_ftrace(struct fprobe *fp) return false; } =20 +static bool fprobe_exists_on_hash(unsigned long ip, bool ftrace __maybe_un= used) +{ + struct rhlist_head *head, *pos; + struct fprobe_hlist_node *node; + struct fprobe *fp; + + guard(rcu)(); + head =3D 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 !=3D ip) + break; + fp =3D 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) { @@ -555,15 +594,22 @@ 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; =20 - if (delete_fprobe_node(node)) - return 0; + delete_fprobe_node(node); + /* + * 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++] =3D node->addr; + if (alist->index =3D=3D alist->size) + return -ENOSPC; + } =20 - alist->addrs[alist->index++] =3D node->addr; - if (alist->index =3D=3D alist->size) - return -ENOSPC; return 0; } =20 @@ -915,7 +961,9 @@ static int unregister_fprobe_nolock(struct fprobe *fp) /* Remove non-synonim ips from table and hash */ count =3D 0; for (i =3D 0; i < hlist_array->size; i++) { - if (!delete_fprobe_node(&hlist_array->array[i])) + delete_fprobe_node(&hlist_array->array[i]); + if (!fprobe_exists_on_hash(hlist_array->array[i].addr, + fprobe_is_ftrace(fp))) addrs[count++] =3D hlist_array->array[i].addr; } del_fprobe_hash(fp);