From nobody Fri Dec 19 15:40:15 2025 Received: from out-173.mta0.migadu.com (out-173.mta0.migadu.com [91.218.175.173]) (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 3E9E82C15BA for ; Mon, 13 Oct 2025 17:48:18 +0000 (UTC) Authentication-Results: smtp.subspace.kernel.org; arc=none smtp.client-ip=91.218.175.173 ARC-Seal: i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1760377700; cv=none; b=tPTHchsuDy1DEqFX1CxYH0ms0WTH9knxSxIed4/NVlNHLxtHXX22iuqKImDBJZQztI8RqS3H/hGsIcgbUp+8hsPx+c2MJycKhHboI1jem4bbjcJw+klvd+WiQBWfu1ed6Ypvr7nDrlnBPCny/tAvylfXlRLWzmeKjbIkDgfLx3s= ARC-Message-Signature: i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1760377700; c=relaxed/simple; bh=U0voQM2oYnf6STeO6/rk9aLxKnrO1RiaTGJ/8zUau1w=; h=From:To:Cc:Subject:Date:Message-ID:In-Reply-To:References: MIME-Version; b=S7G4cxLDl+I96aEHqzzN5RjLmwUt9xaQhRtYBXXf6JycGnRHhQrdVzdv3e0A1V0ipBFG9yi971g7Pyi1T6RenjP0OE7aS4wd5SeVQ9LZcDtoM0UnaOiGU3waKKUGx+ZOgGbGv1+kd6RiP6w9WJm+0db1bjlDo7A8Sl/Sa391lAw= 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=dqog44Hl; arc=none smtp.client-ip=91.218.175.173 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="dqog44Hl" 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=1760377696; 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=GFSgpLJ9oy5bTPXjycAjjR+uiZnaDlBjDtnbne3KHWA=; b=dqog44HlD/xi4SmzgPayoGAyNglOXEbXHUVvDjSrKnNlF3zG9OY+/PnBjRu+tI5R08bv9L 9qo8QWSiIBxn8QVr5br7rI2wp/EfK/WDxBe87TvPgk/V9vehAAux3m0Izgp2PxAQJgot8B Aw2WZP8/zaM7h7tp6DhqHswK/xTC768= 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 RFC 1/2] perf: Use extern perf_callchain_entry for get_perf_callchain Date: Tue, 14 Oct 2025 01:47:20 +0800 Message-ID: <20251013174721.2681091-2-chen.dylane@linux.dev> In-Reply-To: <20251013174721.2681091-1-chen.dylane@linux.dev> References: <20251013174721.2681091-1-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 cop= y, so let us pass it directly. Signed-off-by: Tao Chen --- include/linux/perf_event.h | 5 +++-- kernel/bpf/stackmap.c | 4 ++-- kernel/events/callchain.c | 18 ++++++++++++------ kernel/events/core.c | 2 +- 4 files changed, 18 insertions(+), 11 deletions(-) diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h index ec9d9602568..ca69ad2723c 100644 --- a/include/linux/perf_event.h +++ b/include/linux/perf_event.h @@ -1719,8 +1719,9 @@ 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, u32 init_nr, bool kernel, bool us= er, - u32 max_stack, bool crosstask, bool add_mark); +get_perf_callchain(struct pt_regs *regs, struct perf_callchain_entry *exte= rnal_entry, + u32 init_nr, 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 2e182a3ac4c..e6e40f22826 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, 0, kernel, user, max_depth, + trace =3D get_perf_callchain(regs, NULL, 0, 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, 0, kernel, user, max_depth, + trace =3D get_perf_callchain(regs, NULL, 0, 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 6c83ad674d0..fe5d2d58deb 100644 --- a/kernel/events/callchain.c +++ b/kernel/events/callchain.c @@ -217,16 +217,21 @@ static void fixup_uretprobe_trampoline_entries(struct= perf_callchain_entry *entr } =20 struct perf_callchain_entry * -get_perf_callchain(struct pt_regs *regs, u32 init_nr, bool kernel, bool us= er, - u32 max_stack, bool crosstask, bool add_mark) +get_perf_callchain(struct pt_regs *regs, struct perf_callchain_entry *exte= rnal_entry, + u32 init_nr, bool kernel, bool user, u32 max_stack, bool crosstask, + bool add_mark) { struct perf_callchain_entry *entry; struct perf_callchain_entry_ctx ctx; int rctx, start_entry_idx; =20 - entry =3D get_callchain_entry(&rctx); - if (!entry) - return NULL; + if (external_entry) { + entry =3D external_entry; + } else { + entry =3D get_callchain_entry(&rctx); + if (!entry) + return NULL; + } =20 ctx.entry =3D entry; ctx.max_stack =3D max_stack; @@ -262,7 +267,8 @@ get_perf_callchain(struct pt_regs *regs, u32 init_nr, b= ool kernel, bool 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 1d354778dcd..08ce44db18f 100644 --- a/kernel/events/core.c +++ b/kernel/events/core.c @@ -8204,7 +8204,7 @@ perf_callchain(struct perf_event *event, struct pt_re= gs *regs) if (!kernel && !user) return &__empty_callchain; =20 - callchain =3D get_perf_callchain(regs, 0, kernel, user, + callchain =3D get_perf_callchain(regs, NULL, 0, kernel, user, max_stack, crosstask, true); return callchain ?: &__empty_callchain; } --=20 2.48.1 From nobody Fri Dec 19 15:40:15 2025 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 4F0E12C21D8 for ; Mon, 13 Oct 2025 17:48:35 +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=1760377718; cv=none; b=RXx0K5VOEK7U3GhERPUBzXT56pSyEZOgrrCLxkmYt3un0Fp7N8/7C6HvCsZqyUFBmr5JPUIvQqB8uaFCbFZ0luG2oJivAk8mILrXOh+TsPmSiy6l3V/vvk4hPiA6TgQ+KNI16CiAA2Kkh1oOOjLpCYQSZL7d4Fcubo/5Yq7XAOs= ARC-Message-Signature: i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1760377718; c=relaxed/simple; bh=JZ3RCEqrx9zVV7MZr9JKbsHGFEy/s3pgNDFLa15OMyk=; h=From:To:Cc:Subject:Date:Message-ID:In-Reply-To:References: MIME-Version; b=KI8G87+MnM7aw1mzGMPw/DX8AjShhsfbNDEGR7zFhgzqJ2zRNnOhZJC4RuzmQf2CJOroX7zr8NYcVx52MKihUidwtEBUe6WhwHBCu2ENJj6d9wr5WEhim6Ni8OnXh3WUtNvgEUqHfvfznuhYkj9AEAGEboCsr8btsCBm5UMsMus= 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=vLiNPVXC; 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="vLiNPVXC" 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=1760377713; 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=7WmnP6ICbEec27+qyu/CiHrrXy+wQUjaQxBTOOdzmdE=; b=vLiNPVXCYKIdbovrJm/KfG9lusZ7EzIPIrmZDWtPqLWh1Mf3MhswaTlD6Yxu4nUtuu2AGZ 4+Xm0sq5jF8eDtmDopOviMJJgttQsxs2qzVEauY3O71Kg4Sp+w+BV8p4Oz1++JDINztbTk FzaGCHEmIxGUjFlv9RP+nJb66DmOivM= 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 RFC 2/2] bpf: Pass external callchain entry to get_perf_callchain Date: Tue, 14 Oct 2025 01:47:21 +0800 Message-ID: <20251013174721.2681091-3-chen.dylane@linux.dev> In-Reply-To: <20251013174721.2681091-1-chen.dylane@linux.dev> References: <20251013174721.2681091-1-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_perf_callchain_entries, stack-allocated memory of bpf_perf_callchain_entry is used here. Signed-off-by: Tao Chen --- kernel/bpf/stackmap.c | 19 +++++++++++-------- 1 file changed, 11 insertions(+), 8 deletions(-) diff --git a/kernel/bpf/stackmap.c b/kernel/bpf/stackmap.c index e6e40f22826..1a51a2ea159 100644 --- a/kernel/bpf/stackmap.c +++ b/kernel/bpf/stackmap.c @@ -31,6 +31,11 @@ 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]; +}; + static inline bool stack_map_use_build_id(struct bpf_map *map) { return (map->map_flags & BPF_F_STACK_BUILD_ID); @@ -305,6 +310,7 @@ 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; + struct bpf_perf_callchain_entry entry =3D { 0 }; =20 if (unlikely(flags & ~(BPF_F_SKIP_FIELD_MASK | BPF_F_USER_STACK | BPF_F_FAST_STACK_CMP | BPF_F_REUSE_STACKID))) @@ -314,12 +320,8 @@ BPF_CALL_3(bpf_get_stackid, struct pt_regs *, regs, st= ruct 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, 0, kernel, user, max_depth, - false, false); - - if (unlikely(!trace)) - /* couldn't fetch the stack trace */ - return -EFAULT; + trace =3D get_perf_callchain(regs, (struct perf_callchain_entry *)&entry,= 0, + kernel, user, max_depth, false, false); =20 return __bpf_get_stackid(map, trace, flags); } @@ -412,6 +414,7 @@ static long __bpf_get_stack(struct pt_regs *regs, struc= t task_struct *task, u32 skip =3D flags & BPF_F_SKIP_FIELD_MASK; bool user =3D flags & BPF_F_USER_STACK; struct perf_callchain_entry *trace; + struct bpf_perf_callchain_entry entry =3D { 0 }; bool kernel =3D !user; int err =3D -EINVAL; u64 *ips; @@ -451,8 +454,8 @@ 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, NULL, 0, kernel, user, max_depth, - crosstask, false); + trace =3D get_perf_callchain(regs, (struct perf_callchain_entry *)&entry= , 0, + kernel, user, max_depth, crosstask, false); =20 if (unlikely(!trace) || trace->nr < skip) { if (may_fault) --=20 2.48.1