From nobody Sat Feb 7 18:16:04 2026 Received: from out-173.mta1.migadu.com (out-173.mta1.migadu.com [95.215.58.173]) (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 4BE8533033B for ; Tue, 21 Oct 2025 16:07:17 +0000 (UTC) Authentication-Results: smtp.subspace.kernel.org; arc=none smtp.client-ip=95.215.58.173 ARC-Seal: i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1761062839; cv=none; b=jyzHon6w6X9PsDIL+zDaJ1wBB8UeU9h/8SUI0OoA2wn6kt61yl0MqzqsgyR9vDcCRtrs3yLi4/fAlIpMbWiurJFaUqGGO714QXaOEMaBKxmjxF2taHyre1TeyDfuEC8WBt2W/pdten+6bX3Q74y+AanEjVobwn0Atizsi4iUV0w= ARC-Message-Signature: i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1761062839; c=relaxed/simple; bh=/BfyvLc3alET4VUbm8IcEp9DdnDvoMNBCmAfIzP2ToM=; h=From:To:Cc:Subject:Date:Message-ID:In-Reply-To:References: MIME-Version; b=eYhc8Z5MzNFupFg21UGjLPX95V/Rk84Q+V15PcWijSwxt9Q/iN8QS1XCxvf8UeLk7qTaooXwjSldGLs3J1RgaWy0rvtrmwuwZQvuUBMeRWr41NcqL4/EEkR2yKw6r7hopDRC5IAX9XJSArlyvuCDZ3nD4E2cNWsCArQz/GByv48= ARC-Authentication-Results: i=1; smtp.subspace.kernel.org; dmarc=pass (p=none dis=none) header.from=linux.dev; spf=pass smtp.mailfrom=linux.dev; dkim=pass (1024-bit key) header.d=linux.dev header.i=@linux.dev header.b=wpw5QU7a; arc=none smtp.client-ip=95.215.58.173 Authentication-Results: smtp.subspace.kernel.org; dmarc=pass (p=none dis=none) header.from=linux.dev Authentication-Results: smtp.subspace.kernel.org; spf=pass smtp.mailfrom=linux.dev Authentication-Results: smtp.subspace.kernel.org; dkim=pass (1024-bit key) header.d=linux.dev header.i=@linux.dev header.b="wpw5QU7a" X-Report-Abuse: Please report any abuse attempt to abuse@migadu.com and include these headers. DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=linux.dev; s=key1; t=1761062825; h=from:from:reply-to:subject:subject:date:date:message-id:message-id: to:to:cc:cc:mime-version:mime-version: content-transfer-encoding:content-transfer-encoding: in-reply-to:in-reply-to:references:references; bh=Rx3Mu1f9RcQnyEwI6I+qDuteJEIdnrA8Zyt1Wu+roas=; b=wpw5QU7auhont3DE94eD3Lc/11dQx6XQgINlzNT2fQuKRzmQkAY1bUpygOG4ZtrQBYc9xu YVl4vuej6mk500AhDWlE0ZWlSa7ta8Hfc6u3sqQLjV0eRzcLpkspva2uby0Sig9fyIv79c B+genqXj8jZcr4WG5/WssaeBTSBhdvU= From: Tao Chen To: peterz@infradead.org, mingo@redhat.com, acme@kernel.org, namhyung@kernel.org, mark.rutland@arm.com, alexander.shishkin@linux.intel.com, jolsa@kernel.org, irogers@google.com, adrian.hunter@intel.com, kan.liang@linux.intel.com, song@kernel.org, ast@kernel.org, daniel@iogearbox.net, andrii@kernel.org, martin.lau@linux.dev, eddyz87@gmail.com, yonghong.song@linux.dev, john.fastabend@gmail.com, kpsingh@kernel.org, sdf@fomichev.me, haoluo@google.com Cc: linux-perf-users@vger.kernel.org, linux-kernel@vger.kernel.org, bpf@vger.kernel.org, Tao Chen Subject: [PATCH bpf-next v4 1/2] perf: Use extern perf_callchain_entry for get_perf_callchain Date: Wed, 22 Oct 2025 00:06:32 +0800 Message-ID: <20251021160633.3046301-2-chen.dylane@linux.dev> In-Reply-To: <20251021160633.3046301-1-chen.dylane@linux.dev> References: <20251021160633.3046301-1-chen.dylane@linux.dev> Precedence: bulk X-Mailing-List: linux-kernel@vger.kernel.org List-Id: List-Subscribe: List-Unsubscribe: MIME-Version: 1.0 Content-Transfer-Encoding: quoted-printable X-Migadu-Flow: FLOW_OUT Content-Type: text/plain; charset="utf-8" From bpf stack map, we want to use our own buffers to avoid unnecessary copy, so let us pass it directly. BPF will use this in the next patch. Signed-off-by: Tao Chen --- include/linux/perf_event.h | 4 ++-- kernel/bpf/stackmap.c | 4 ++-- kernel/events/callchain.c | 13 +++++++++---- kernel/events/core.c | 2 +- 4 files changed, 14 insertions(+), 9 deletions(-) diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h index fd1d91017b9..b144da7d803 100644 --- a/include/linux/perf_event.h +++ b/include/linux/perf_event.h @@ -1719,8 +1719,8 @@ DECLARE_PER_CPU(struct perf_callchain_entry, perf_cal= lchain_entry); extern void perf_callchain_user(struct perf_callchain_entry_ctx *entry, st= ruct pt_regs *regs); extern void perf_callchain_kernel(struct perf_callchain_entry_ctx *entry, = struct pt_regs *regs); extern struct perf_callchain_entry * -get_perf_callchain(struct pt_regs *regs, bool kernel, bool user, - u32 max_stack, bool crosstask, bool add_mark); +get_perf_callchain(struct pt_regs *regs, struct perf_callchain_entry *exte= rnal_entry, + bool kernel, bool user, u32 max_stack, bool crosstask, bool add_mark); extern int get_callchain_buffers(int max_stack); extern void put_callchain_buffers(void); extern struct perf_callchain_entry *get_callchain_entry(int *rctx); diff --git a/kernel/bpf/stackmap.c b/kernel/bpf/stackmap.c index 4d53cdd1374..94e46b7f340 100644 --- a/kernel/bpf/stackmap.c +++ b/kernel/bpf/stackmap.c @@ -314,7 +314,7 @@ BPF_CALL_3(bpf_get_stackid, struct pt_regs *, regs, str= uct bpf_map *, map, if (max_depth > sysctl_perf_event_max_stack) max_depth =3D sysctl_perf_event_max_stack; =20 - trace =3D get_perf_callchain(regs, kernel, user, max_depth, + trace =3D get_perf_callchain(regs, NULL, kernel, user, max_depth, false, false); =20 if (unlikely(!trace)) @@ -451,7 +451,7 @@ static long __bpf_get_stack(struct pt_regs *regs, struc= t task_struct *task, else if (kernel && task) trace =3D get_callchain_entry_for_task(task, max_depth); else - trace =3D get_perf_callchain(regs, kernel, user, max_depth, + trace =3D get_perf_callchain(regs, NULL, kernel, user, max_depth, crosstask, false); =20 if (unlikely(!trace) || trace->nr < skip) { diff --git a/kernel/events/callchain.c b/kernel/events/callchain.c index 808c0d7a31f..851e8f9d026 100644 --- a/kernel/events/callchain.c +++ b/kernel/events/callchain.c @@ -217,8 +217,8 @@ static void fixup_uretprobe_trampoline_entries(struct p= erf_callchain_entry *entr } =20 struct perf_callchain_entry * -get_perf_callchain(struct pt_regs *regs, bool kernel, bool user, - u32 max_stack, bool crosstask, bool add_mark) +get_perf_callchain(struct pt_regs *regs, struct perf_callchain_entry *exte= rnal_entry, + bool kernel, bool user, u32 max_stack, bool crosstask, bool add_mark) { struct perf_callchain_entry *entry; struct perf_callchain_entry_ctx ctx; @@ -228,7 +228,11 @@ get_perf_callchain(struct pt_regs *regs, bool kernel, = bool user, if (crosstask && user && !kernel) return NULL; =20 - entry =3D get_callchain_entry(&rctx); + if (external_entry) + entry =3D external_entry; + else + entry =3D get_callchain_entry(&rctx); + if (!entry) return NULL; =20 @@ -260,7 +264,8 @@ get_perf_callchain(struct pt_regs *regs, bool kernel, b= ool user, } =20 exit_put: - put_callchain_entry(rctx); + if (!external_entry) + put_callchain_entry(rctx); =20 return entry; } diff --git a/kernel/events/core.c b/kernel/events/core.c index 7541f6f85fc..5d8e146003a 100644 --- a/kernel/events/core.c +++ b/kernel/events/core.c @@ -8217,7 +8217,7 @@ perf_callchain(struct perf_event *event, struct pt_re= gs *regs) if (!kernel && !user) return &__empty_callchain; =20 - callchain =3D get_perf_callchain(regs, kernel, user, + callchain =3D get_perf_callchain(regs, NULL, kernel, user, max_stack, crosstask, true); return callchain ?: &__empty_callchain; } --=20 2.48.1 From nobody Sat Feb 7 18:16:04 2026 Received: from out-180.mta0.migadu.com (out-180.mta0.migadu.com [91.218.175.180]) (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 817B233033B; Tue, 21 Oct 2025 16:07:22 +0000 (UTC) Authentication-Results: smtp.subspace.kernel.org; arc=none smtp.client-ip=91.218.175.180 ARC-Seal: i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1761062845; cv=none; b=agcXU1Kts1p+GoqnZUSeNLkycprOTlmfe15z8ZfnLaAwVLptfgJfqVqquttQ6ikCZXVfexOibqUMDn1dY9UeakQMwKKgo8R9aCL0iSVTJncIBhDWKCjV92df5i5h9TnGd4Fn435N2kiuka1jzmwk0F0pNqIPRhzylUYaBxde6sY= ARC-Message-Signature: i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1761062845; c=relaxed/simple; bh=iY9Yb0Gn2Gx4LmXHIlKFgLujqTljqZiHXTOJwPqFXek=; h=From:To:Cc:Subject:Date:Message-ID:In-Reply-To:References: MIME-Version; b=YAx5H0usOuh+IwNGmOiPbHEqF4pCeWZDJLSTND9IX9lHjTbuMxQ2Zs8oIF4m4JTDP3NIub9+mFXZIR1i8Ylr4c3vIu3p2hkJLMsDhLKStL9fjAs9Y5bqNp69cN2vbDKcSYGxYUd3nIlKgULlLkuyGU3FC+9CBX6Tn8rEyEP+hFQ= ARC-Authentication-Results: i=1; smtp.subspace.kernel.org; dmarc=pass (p=none dis=none) header.from=linux.dev; spf=pass smtp.mailfrom=linux.dev; dkim=pass (1024-bit key) header.d=linux.dev header.i=@linux.dev header.b=w5uYFMHO; arc=none smtp.client-ip=91.218.175.180 Authentication-Results: smtp.subspace.kernel.org; dmarc=pass (p=none dis=none) header.from=linux.dev Authentication-Results: smtp.subspace.kernel.org; spf=pass smtp.mailfrom=linux.dev Authentication-Results: smtp.subspace.kernel.org; dkim=pass (1024-bit key) header.d=linux.dev header.i=@linux.dev header.b="w5uYFMHO" X-Report-Abuse: Please report any abuse attempt to abuse@migadu.com and include these headers. DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=linux.dev; s=key1; t=1761062840; h=from:from:reply-to:subject:subject:date:date:message-id:message-id: to:to:cc:cc:mime-version:mime-version: content-transfer-encoding:content-transfer-encoding: in-reply-to:in-reply-to:references:references; bh=f/ceOYFMHO8rupmeTuNBdZk0i8ibDpq4hA/Mx8osgH0=; b=w5uYFMHOTKmlHbxaOYhCWyqkI8cAKAvY99nTXx8aZW5iJ/KTAY7VpzsqKirs4UX3yWYWkp K0sWgibi7IsLsDTyKluOg0gORACCMrBNTFlgnSsG9dYOH/TpfW4h7awVXUQTSqBHE4FVtM oksRDUvsZfQBNN0QrhyDiDi47xSoDp8= From: Tao Chen To: peterz@infradead.org, mingo@redhat.com, acme@kernel.org, namhyung@kernel.org, mark.rutland@arm.com, alexander.shishkin@linux.intel.com, jolsa@kernel.org, irogers@google.com, adrian.hunter@intel.com, kan.liang@linux.intel.com, song@kernel.org, ast@kernel.org, daniel@iogearbox.net, andrii@kernel.org, martin.lau@linux.dev, eddyz87@gmail.com, yonghong.song@linux.dev, john.fastabend@gmail.com, kpsingh@kernel.org, sdf@fomichev.me, haoluo@google.com Cc: linux-perf-users@vger.kernel.org, linux-kernel@vger.kernel.org, bpf@vger.kernel.org, Tao Chen Subject: [PATCH bpf-next v4 2/2] bpf: Use per-cpu BPF callchain entry to save callchain Date: Wed, 22 Oct 2025 00:06:33 +0800 Message-ID: <20251021160633.3046301-3-chen.dylane@linux.dev> In-Reply-To: <20251021160633.3046301-1-chen.dylane@linux.dev> References: <20251021160633.3046301-1-chen.dylane@linux.dev> Precedence: bulk X-Mailing-List: linux-kernel@vger.kernel.org List-Id: List-Subscribe: List-Unsubscribe: MIME-Version: 1.0 Content-Transfer-Encoding: quoted-printable X-Migadu-Flow: FLOW_OUT Content-Type: text/plain; charset="utf-8" As Alexei noted, get_perf_callchain() return values may be reused if a task is preempted after the BPF program enters migrate disable mode. Drawing on the per-cpu design of bpf_bprintf_buffers, per-cpu BPF callchain entry is used here. Signed-off-by: Tao Chen --- kernel/bpf/stackmap.c | 98 ++++++++++++++++++++++++++++++++----------- 1 file changed, 73 insertions(+), 25 deletions(-) diff --git a/kernel/bpf/stackmap.c b/kernel/bpf/stackmap.c index 94e46b7f340..97028d39df1 100644 --- a/kernel/bpf/stackmap.c +++ b/kernel/bpf/stackmap.c @@ -31,6 +31,52 @@ struct bpf_stack_map { struct stack_map_bucket *buckets[] __counted_by(n_buckets); }; =20 +struct bpf_perf_callchain_entry { + u64 nr; + u64 ip[PERF_MAX_STACK_DEPTH]; +}; + +#define MAX_PERF_CALLCHAIN_PREEMPT 3 +static DEFINE_PER_CPU(struct bpf_perf_callchain_entry[MAX_PERF_CALLCHAIN_P= REEMPT], + bpf_perf_callchain_entries); +static DEFINE_PER_CPU(int, bpf_perf_callchain_preempt_cnt); + +static int bpf_get_perf_callchain_or_entry(struct perf_callchain_entry **e= ntry, + struct pt_regs *regs, bool kernel, + bool user, u32 max_stack, bool crosstack, + bool add_mark, bool get_callchain) +{ + struct bpf_perf_callchain_entry *bpf_entry; + struct perf_callchain_entry *perf_entry; + int preempt_cnt; + + preempt_cnt =3D this_cpu_inc_return(bpf_perf_callchain_preempt_cnt); + if (WARN_ON_ONCE(preempt_cnt > MAX_PERF_CALLCHAIN_PREEMPT)) { + this_cpu_dec(bpf_perf_callchain_preempt_cnt); + return -EBUSY; + } + + bpf_entry =3D this_cpu_ptr(&bpf_perf_callchain_entries[preempt_cnt - 1]); + if (!get_callchain) { + *entry =3D (struct perf_callchain_entry *)bpf_entry; + return 0; + } + + perf_entry =3D get_perf_callchain(regs, (struct perf_callchain_entry *)bp= f_entry, + kernel, user, max_stack, + crosstack, add_mark); + *entry =3D perf_entry; + + return 0; +} + +static void bpf_put_perf_callchain(void) +{ + if (WARN_ON_ONCE(this_cpu_read(bpf_perf_callchain_preempt_cnt) =3D=3D 0)) + return; + this_cpu_dec(bpf_perf_callchain_preempt_cnt); +} + static inline bool stack_map_use_build_id(struct bpf_map *map) { return (map->map_flags & BPF_F_STACK_BUILD_ID); @@ -192,11 +238,11 @@ get_callchain_entry_for_task(struct task_struct *task= , u32 max_depth) { #ifdef CONFIG_STACKTRACE struct perf_callchain_entry *entry; - int rctx; - - entry =3D get_callchain_entry(&rctx); + int ret; =20 - if (!entry) + ret =3D bpf_get_perf_callchain_or_entry(&entry, NULL, false, false, 0, fa= lse, false, + false); + if (ret) return NULL; =20 entry->nr =3D stack_trace_save_tsk(task, (unsigned long *)entry->ip, @@ -216,8 +262,6 @@ get_callchain_entry_for_task(struct task_struct *task, = u32 max_depth) to[i] =3D (u64)(from[i]); } =20 - put_callchain_entry(rctx); - return entry; #else /* CONFIG_STACKTRACE */ return NULL; @@ -305,6 +349,7 @@ BPF_CALL_3(bpf_get_stackid, struct pt_regs *, regs, str= uct bpf_map *, map, bool user =3D flags & BPF_F_USER_STACK; struct perf_callchain_entry *trace; bool kernel =3D !user; + int err; =20 if (unlikely(flags & ~(BPF_F_SKIP_FIELD_MASK | BPF_F_USER_STACK | BPF_F_FAST_STACK_CMP | BPF_F_REUSE_STACKID))) @@ -314,14 +359,15 @@ BPF_CALL_3(bpf_get_stackid, struct pt_regs *, regs, s= truct bpf_map *, map, if (max_depth > sysctl_perf_event_max_stack) max_depth =3D sysctl_perf_event_max_stack; =20 - trace =3D get_perf_callchain(regs, NULL, kernel, user, max_depth, - false, false); + err =3D bpf_get_perf_callchain_or_entry(&trace, regs, kernel, user, max_d= epth, + false, false, true); + if (err) + return err; =20 - if (unlikely(!trace)) - /* couldn't fetch the stack trace */ - return -EFAULT; + err =3D __bpf_get_stackid(map, trace, flags); + bpf_put_perf_callchain(); =20 - return __bpf_get_stackid(map, trace, flags); + return err; } =20 const struct bpf_func_proto bpf_get_stackid_proto =3D { @@ -443,20 +489,23 @@ static long __bpf_get_stack(struct pt_regs *regs, str= uct task_struct *task, if (sysctl_perf_event_max_stack < max_depth) max_depth =3D sysctl_perf_event_max_stack; =20 - if (may_fault) - rcu_read_lock(); /* need RCU for perf's callchain below */ - if (trace_in) trace =3D trace_in; - else if (kernel && task) + else if (kernel && task) { trace =3D get_callchain_entry_for_task(task, max_depth); - else - trace =3D get_perf_callchain(regs, NULL, kernel, user, max_depth, - crosstask, false); + } else { + err =3D bpf_get_perf_callchain_or_entry(&trace, regs, kernel, user, max_= depth, + false, false, true); + if (err) + return err; + } + + if (unlikely(!trace)) + goto err_fault; =20 - if (unlikely(!trace) || trace->nr < skip) { - if (may_fault) - rcu_read_unlock(); + if (trace->nr < skip) { + if (!trace_in) + bpf_put_perf_callchain(); goto err_fault; } =20 @@ -475,9 +524,8 @@ static long __bpf_get_stack(struct pt_regs *regs, struc= t task_struct *task, memcpy(buf, ips, copy_len); } =20 - /* trace/ips should not be dereferenced after this point */ - if (may_fault) - rcu_read_unlock(); + if (!trace_in) + bpf_put_perf_callchain(); =20 if (user_build_id) stack_map_get_build_id_offset(buf, trace_nr, user, may_fault); --=20 2.48.1