From nobody Mon Jun 15 07:41:59 2026 Received: from out-180.mta1.migadu.com (out-180.mta1.migadu.com [95.215.58.180]) (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 ED16F23AE62 for ; Thu, 9 Apr 2026 01:06:25 +0000 (UTC) Authentication-Results: smtp.subspace.kernel.org; arc=none smtp.client-ip=95.215.58.180 ARC-Seal: i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1775696787; cv=none; b=N8Pu2S5uhDB44vjbln6+AFlkWdw7jN04zQKBdVLYIlXeudo7A1/UhpEXCM1BVZVwkTid6fZUKCwZK1VKwYKjmj8py2jOQjYD0tAdfViy71bscqaARxzzBJmwfUwjw+2dWXrYWBaDq0a63u/647kbF/IlitcFw4bq42S8ax+O3cs= ARC-Message-Signature: i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1775696787; c=relaxed/simple; bh=iczHXna4L7grqbUgBt6rxCfU6rJknMojicr/70GykkU=; h=From:To:Cc:Subject:Date:Message-ID:In-Reply-To:References: MIME-Version; b=Zen9tImEDhFYn6N2J6f/3holAs27gkpN9IGLlqgsuElMptP3TgRoJlww+A7PjTdCy43tGJ60JNmBTMpreerh7bddS3GTNf4SFH6934iiJdeirH1/VbkBwLf8kQZk3smSEsKcGWkwazB6LJ2f8p62x+C5S99yN5t8H1qqvrzslSc= 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=Nzy+Vs1u; arc=none smtp.client-ip=95.215.58.180 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="Nzy+Vs1u" 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=1775696784; 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=T/Jsa74Va1s1Nkqgt9Gzuyp9emVzAprYCwqK0vMSfQo=; b=Nzy+Vs1uJn7v6TQR2nqBXukjlVTDTvOg6392fHX5wlNKvBpvUbS2zWBe4n/QnFi7ttXVrF 7ibcY537CnlUM5LiZ/aaoLnR8OzFuyDXU+lOxiX1gBtKDbwlRv9+FzVdm/R4jKfay/CRA8 fKLEkHSADDVPw+USG2N+hjj0kBT6e30= From: Ihor Solodrai To: Alexei Starovoitov , Andrii Nakryiko , Daniel Borkmann , Song Liu Cc: Puranjay Mohan , Shakeel Butt , bpf@vger.kernel.org, linux-kernel@vger.kernel.org, kernel-team@meta.com Subject: [PATCH bpf v2 1/2] bpf: Factor out stack_map_build_id_set_ip() in stackmap.c Date: Wed, 8 Apr 2026 18:06:03 -0700 Message-ID: <20260409010604.1439087-2-ihor.solodrai@linux.dev> In-Reply-To: <20260409010604.1439087-1-ihor.solodrai@linux.dev> References: <20260409010604.1439087-1-ihor.solodrai@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" Factor out a small helper from stack_map_get_build_id_offset() in preparation for adding a sleepable build ID resolution path. No functional changes. Signed-off-by: Ihor Solodrai Acked-by: Mykyta Yatsenko --- kernel/bpf/stackmap.c | 21 ++++++++++++--------- 1 file changed, 12 insertions(+), 9 deletions(-) diff --git a/kernel/bpf/stackmap.c b/kernel/bpf/stackmap.c index da3d328f5c15..4ef0fd06cea5 100644 --- a/kernel/bpf/stackmap.c +++ b/kernel/bpf/stackmap.c @@ -152,6 +152,12 @@ static int fetch_build_id(struct vm_area_struct *vma, = unsigned char *build_id, b : build_id_parse_nofault(vma, build_id, NULL); } =20 +static inline void stack_map_build_id_set_ip(struct bpf_stack_build_id *id) +{ + id->status =3D BPF_STACK_BUILD_ID_IP; + memset(id->build_id, 0, BUILD_ID_SIZE_MAX); +} + /* * Expects all id_offs[i].ip values to be set to correct initial IPs. * They will be subsequently: @@ -165,23 +171,21 @@ static int fetch_build_id(struct vm_area_struct *vma,= unsigned char *build_id, b static void stack_map_get_build_id_offset(struct bpf_stack_build_id *id_of= fs, u32 trace_nr, bool user, bool may_fault) { - int i; struct mmap_unlock_irq_work *work =3D NULL; bool irq_work_busy =3D bpf_mmap_unlock_get_irq_work(&work); + bool has_user_ctx =3D user && current && current->mm; struct vm_area_struct *vma, *prev_vma =3D NULL; const char *prev_build_id; + int i; =20 /* If the irq_work is in use, fall back to report ips. Same * fallback is used for kernel stack (!user) on a stackmap with * build_id. */ - if (!user || !current || !current->mm || irq_work_busy || - !mmap_read_trylock(current->mm)) { + if (!has_user_ctx || irq_work_busy || !mmap_read_trylock(current->mm)) { /* cannot access current->mm, fall back to ips */ - for (i =3D 0; i < trace_nr; i++) { - id_offs[i].status =3D BPF_STACK_BUILD_ID_IP; - memset(id_offs[i].build_id, 0, BUILD_ID_SIZE_MAX); - } + for (i =3D 0; i < trace_nr; i++) + stack_map_build_id_set_ip(&id_offs[i]); return; } =20 @@ -196,8 +200,7 @@ static void stack_map_get_build_id_offset(struct bpf_st= ack_build_id *id_offs, vma =3D find_vma(current->mm, ip); if (!vma || fetch_build_id(vma, id_offs[i].build_id, may_fault)) { /* per entry fall back to ips */ - id_offs[i].status =3D BPF_STACK_BUILD_ID_IP; - memset(id_offs[i].build_id, 0, BUILD_ID_SIZE_MAX); + stack_map_build_id_set_ip(&id_offs[i]); continue; } build_id_valid: --=20 2.53.0 From nobody Mon Jun 15 07:41:59 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 95FA525FA05; Thu, 9 Apr 2026 01:06:28 +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=1775696790; cv=none; b=SboE9FinmUw1ueVfxwC8tUwwNxZOg+bp5n6Xgnuq/jryiKcExFKRs9eqTKMQe+L8mAep/fTL4UgbgqNAM50pI4MuEVDUQ7LJFH0r1rQEArhoFLbU9YqlsIXi1ZoqtveJpxV1rzGAiWZZpFzRr+IC3EZYp86pNic7s40l3/zSixM= ARC-Message-Signature: i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1775696790; c=relaxed/simple; bh=YoMlvFba6n5/TgRdOdFDioLwnYXuIDfqAfrrOTk8jS0=; h=From:To:Cc:Subject:Date:Message-ID:In-Reply-To:References: MIME-Version; b=ZFS3/LtyH4VXaeaUFs0m700eKwRDGvsqSB4UCth23GWhdNU0ixBNl5wH8OwlrRj0EaljnelHbnursso/jwraAEouAjRZVIZgaqxVukRkM7uoSwC/3I9QLvCLx8d/oHYa7rDAqFDZk4soOQp41pcw1s1pZm/6vSviWjD/L5HXqY8= 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=bMAmlJSO; 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="bMAmlJSO" 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=1775696786; 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=qfpLRZHC4aPh0em6KEZ82mZi2AP3rltdS+lguz0C2Hs=; b=bMAmlJSOcsXMIL4ukV4smv/Q5hbI7LR1l3WiOzNGcd7bEOSWklYHg+NmgJSwvTLUPD7GFG GpGZPqXgYNfpZSNUhZ208tDFu1DPSkbDM/x70fg5Thsk/DV3GW9WeYcFB5+G2AFMi3hHUG QiD114lOfWsFcPrSGeXmHjqPcCS2fZU= From: Ihor Solodrai To: Alexei Starovoitov , Andrii Nakryiko , Daniel Borkmann , Song Liu Cc: Puranjay Mohan , Shakeel Butt , bpf@vger.kernel.org, linux-kernel@vger.kernel.org, kernel-team@meta.com Subject: [PATCH bpf v2 2/2] bpf: Avoid faultable build ID reads under mm locks Date: Wed, 8 Apr 2026 18:06:04 -0700 Message-ID: <20260409010604.1439087-3-ihor.solodrai@linux.dev> In-Reply-To: <20260409010604.1439087-1-ihor.solodrai@linux.dev> References: <20260409010604.1439087-1-ihor.solodrai@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" Sleepable build ID parsing can block in __kernel_read() [1], so the stackmap sleepable path must not call it while holding mmap_lock or a per-VMA read lock. The issue and the fix are conceptually similar to a recent procfs patch [2]. Resolve each covered VMA with a stable read-side reference, preferring lock_vma_under_rcu() and falling back to mmap_read_lock() only long enough to acquire the VMA read lock. Take a reference to the backing file, drop the VMA lock, and then parse the build ID through (sleepable) build_id_parse_file(). [1]: https://lore.kernel.org/all/20251218005818.614819-1-shakeel.butt@linux= .dev/ [2]: https://lore.kernel.org/all/20260128183232.2854138-1-andrii@kernel.org/ Fixes: 777a8560fd29 ("lib/buildid: use __kernel_read() for sleepable contex= t") Assisted-by: Codex:gpt-5.4 Suggested-by: Puranjay Mohan Signed-off-by: Ihor Solodrai --- kernel/bpf/stackmap.c | 139 ++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 139 insertions(+) diff --git a/kernel/bpf/stackmap.c b/kernel/bpf/stackmap.c index 4ef0fd06cea5..de3d89e20a1e 100644 --- a/kernel/bpf/stackmap.c +++ b/kernel/bpf/stackmap.c @@ -9,6 +9,7 @@ #include #include #include +#include #include "percpu_freelist.h" #include "mmap_unlock_work.h" =20 @@ -158,6 +159,139 @@ static inline void stack_map_build_id_set_ip(struct b= pf_stack_build_id *id) memset(id->build_id, 0, BUILD_ID_SIZE_MAX); } =20 +enum stack_map_vma_lock_state { + STACK_MAP_LOCKED_NONE =3D 0, + STACK_MAP_LOCKED_VMA, + STACK_MAP_LOCKED_MMAP, +}; + +struct stack_map_vma_lock { + enum stack_map_vma_lock_state state; + struct vm_area_struct *vma; + struct mm_struct *mm; +}; + +static struct vm_area_struct *stack_map_lock_vma(struct stack_map_vma_lock= *lock, unsigned long ip) +{ + struct mm_struct *mm =3D lock->mm; + struct vm_area_struct *vma; + + if (WARN_ON_ONCE(!mm)) + return NULL; + + vma =3D lock_vma_under_rcu(mm, ip); + if (vma) + goto vma_locked; + + if (!mmap_read_trylock(mm)) + return NULL; + + vma =3D vma_lookup(mm, ip); + if (!vma) { + mmap_read_unlock(mm); + return NULL; + } + +#ifdef CONFIG_PER_VMA_LOCK + if (!vma_start_read_locked(vma)) { + mmap_read_unlock(mm); + return NULL; + } + mmap_read_unlock(mm); +#else + lock->state =3D STACK_MAP_LOCKED_MMAP; + lock->vma =3D vma; + return vma; +#endif + +vma_locked: + lock->state =3D STACK_MAP_LOCKED_VMA; + lock->vma =3D vma; + return vma; +} + +static void stack_map_unlock_vma(struct stack_map_vma_lock *lock) +{ + struct vm_area_struct *vma =3D lock->vma; + struct mm_struct *mm =3D lock->mm; + + switch (lock->state) { + case STACK_MAP_LOCKED_VMA: + if (WARN_ON_ONCE(!vma)) + break; + vma_end_read(vma); + break; + case STACK_MAP_LOCKED_MMAP: + if (WARN_ON_ONCE(!mm)) + break; + mmap_read_unlock(mm); + break; + default: + break; + } + + lock->state =3D STACK_MAP_LOCKED_NONE; + lock->vma =3D NULL; +} + +static void stack_map_get_build_id_offset_sleepable(struct bpf_stack_build= _id *id_offs, + u32 trace_nr) +{ + struct mm_struct *mm =3D current->mm; + struct stack_map_vma_lock lock =3D { + .state =3D STACK_MAP_LOCKED_NONE, + .vma =3D NULL, + .mm =3D mm, + }; + struct file *file, *prev_file =3D NULL; + unsigned long vm_pgoff, vm_start; + struct vm_area_struct *vma; + const char *prev_build_id; + u64 ip; + + for (u32 i =3D 0; i < trace_nr; i++) { + ip =3D READ_ONCE(id_offs[i].ip); + vma =3D stack_map_lock_vma(&lock, ip); + if (!vma || !vma->vm_file) { + stack_map_build_id_set_ip(&id_offs[i]); + stack_map_unlock_vma(&lock); + continue; + } + + file =3D vma->vm_file; + vm_pgoff =3D vma->vm_pgoff; + vm_start =3D vma->vm_start; + + if (file =3D=3D prev_file) { + memcpy(id_offs[i].build_id, prev_build_id, BUILD_ID_SIZE_MAX); + stack_map_unlock_vma(&lock); + goto build_id_valid; + } + + file =3D get_file(file); + stack_map_unlock_vma(&lock); + + /* build_id_parse_file() may block on filesystem reads */ + if (build_id_parse_file(file, id_offs[i].build_id, NULL)) { + stack_map_build_id_set_ip(&id_offs[i]); + fput(file); + continue; + } + + if (prev_file) + fput(prev_file); + prev_file =3D file; + prev_build_id =3D id_offs[i].build_id; + +build_id_valid: + id_offs[i].offset =3D (vm_pgoff << PAGE_SHIFT) + ip - vm_start; + id_offs[i].status =3D BPF_STACK_BUILD_ID_VALID; + } + + if (prev_file) + fput(prev_file); +} + /* * Expects all id_offs[i].ip values to be set to correct initial IPs. * They will be subsequently: @@ -178,6 +312,11 @@ static void stack_map_get_build_id_offset(struct bpf_s= tack_build_id *id_offs, const char *prev_build_id; int i; =20 + if (may_fault && has_user_ctx) { + stack_map_get_build_id_offset_sleepable(id_offs, trace_nr); + return; + } + /* If the irq_work is in use, fall back to report ips. Same * fallback is used for kernel stack (!user) on a stackmap with * build_id. --=20 2.53.0