From nobody Wed Dec 17 00:33:29 2025 Received: from mail-yb1-f201.google.com (mail-yb1-f201.google.com [209.85.219.201]) (using TLSv1.2 with cipher ECDHE-RSA-AES128-GCM-SHA256 (128/128 bits)) (No client certificate requested) by smtp.subspace.kernel.org (Postfix) with ESMTPS id D923918E1A for ; Mon, 15 Jan 2024 18:38:43 +0000 (UTC) Authentication-Results: smtp.subspace.kernel.org; dmarc=pass (p=reject dis=none) header.from=google.com Authentication-Results: smtp.subspace.kernel.org; spf=pass smtp.mailfrom=flex--surenb.bounces.google.com Authentication-Results: smtp.subspace.kernel.org; dkim=pass (2048-bit key) header.d=google.com header.i=@google.com header.b="p74byPgz" Received: by mail-yb1-f201.google.com with SMTP id 3f1490d57ef6-dbeba57a668so12636044276.3 for ; Mon, 15 Jan 2024 10:38:43 -0800 (PST) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=google.com; s=20230601; t=1705343923; x=1705948723; darn=vger.kernel.org; h=cc:to:from:subject:message-id:references:mime-version:in-reply-to :date:from:to:cc:subject:date:message-id:reply-to; bh=oLlMsVPwk9YFRfJ1xkZa3gURgHKOqqqaOLfJjGTa1Bw=; b=p74byPgz+dtfmyc2Mci897DKkR+m9CFVuXWEUMpI/9zbFHW+i3VJk1TmMonhR67NQP EA3jqiVrcAUnodwE/e/sqHUNWr+8WZsjqqeZOfBLV9leh4Aoh5Vp65L5mRtPZkCnd2Vr qQ/pRb9jy+L2tq5pwDaluDl4vsiGbEENgKDSH4n7nb4mOwgFnXU94kqMCKxOz1rZTqcI X6FhfuCQtAGWTby0uPZuFGwf89jUk45W7ycUVKanPQPlKF94By7TIN3VUaNqk6i02VRa M/kILqSzbLDbqWYkd//QJ+WFzzQzGuwqpoCQDaN/OtlvO3FaTf6sRR+8yRceHP4tEAH/ FWOQ== X-Google-DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=1e100.net; s=20230601; t=1705343923; x=1705948723; h=cc:to:from:subject:message-id:references:mime-version:in-reply-to :date:x-gm-message-state:from:to:cc:subject:date:message-id:reply-to; bh=oLlMsVPwk9YFRfJ1xkZa3gURgHKOqqqaOLfJjGTa1Bw=; b=LEPoTjuyY8o1LSlpxprMT+praWACv8/MiLDWFUQqNTmr3NdynYbQZHmJfzo/W0h5GW ETzF8NXN9FI0+erBUIgEeUW9BoJo2hyNPrX7wgbN9UIvJM1t+agiyWEIKborHxsSv+5H nshYY8S/wqEMNalS2kNdUZeFNNcYSle9jsgHJ2ByRoA13hjr9SFlAnaJ0Fr0sXQviyIk HLrcVJlwZVtmHNnODTEk9lrC4S5Ci8UICWzWdQ8AlbW6tVAp8aFDEvddxPPWcBz9WXsr RZo9TwxFPDkjI8M+qfWG/SfnCPcns9cUHCU/T0ZHhkYggABr4ghLNmE+ItC9kof6iwgc 51vw== X-Gm-Message-State: AOJu0YwY6ksmRUdB9Y1koPu/X0MOegZ3oLQTazGahwsfNJ7cP2EoJSaW e0XKrw1wpSatmVpP5m2Ebj9bgiGFfVUyziN8SQ== X-Google-Smtp-Source: AGHT+IETYM+vP+GcA1bz5ffGAn7xpFLG8rQcpZyAKLVas4y2HqU4DVH4yHlOoP/EqERN0tEXwr857q4NqX0= X-Received: from surenb-desktop.mtv.corp.google.com ([2620:15c:211:201:3af2:e48e:2785:270]) (user=surenb job=sendgmr) by 2002:a25:a292:0:b0:dc1:f71f:a0ad with SMTP id c18-20020a25a292000000b00dc1f71fa0admr1244231ybi.13.1705343922947; Mon, 15 Jan 2024 10:38:42 -0800 (PST) Date: Mon, 15 Jan 2024 10:38:34 -0800 In-Reply-To: <20240115183837.205694-1-surenb@google.com> Precedence: bulk X-Mailing-List: linux-kernel@vger.kernel.org List-Id: List-Subscribe: List-Unsubscribe: Mime-Version: 1.0 References: <20240115183837.205694-1-surenb@google.com> X-Mailer: git-send-email 2.43.0.381.gb435a96ce8-goog Message-ID: <20240115183837.205694-2-surenb@google.com> Subject: [RFC 1/3] mm: make vm_area_struct anon_name field RCU-safe From: Suren Baghdasaryan To: akpm@linux-foundation.org Cc: viro@zeniv.linux.org.uk, brauner@kernel.org, jack@suse.cz, dchinner@redhat.com, casey@schaufler-ca.com, ben.wolsieffer@hefring.com, paulmck@kernel.org, david@redhat.com, avagin@google.com, usama.anjum@collabora.com, peterx@redhat.com, hughd@google.com, ryan.roberts@arm.com, wangkefeng.wang@huawei.com, Liam.Howlett@Oracle.com, yuzhao@google.com, axelrasmussen@google.com, lstoakes@gmail.com, talumbau@google.com, willy@infradead.org, vbabka@suse.cz, mgorman@techsingularity.net, jhubbard@nvidia.com, vishal.moola@gmail.com, mathieu.desnoyers@efficios.com, dhowells@redhat.com, jgg@ziepe.ca, sidhartha.kumar@oracle.com, andriy.shevchenko@linux.intel.com, yangxingui@huawei.com, keescook@chromium.org, linux-kernel@vger.kernel.org, linux-fsdevel@vger.kernel.org, linux-mm@kvack.org, kernel-team@android.com, surenb@google.com Content-Transfer-Encoding: quoted-printable Content-Type: text/plain; charset="utf-8" For lockless /proc/pid/maps reading we have to ensure all the fields used when generating the output are RCU-safe. The only pointer fields in vm_area_struct which are used to generate that file's output are vm_file and anon_name. vm_file is RCU-safe but anon_name is not. Make anon_name RCU-safe as well. Signed-off-by: Suren Baghdasaryan --- include/linux/mm_inline.h | 10 +++++++++- include/linux/mm_types.h | 3 ++- mm/madvise.c | 30 ++++++++++++++++++++++++++---- 3 files changed, 37 insertions(+), 6 deletions(-) diff --git a/include/linux/mm_inline.h b/include/linux/mm_inline.h index f4fe593c1400..bbdb0ca857f1 100644 --- a/include/linux/mm_inline.h +++ b/include/linux/mm_inline.h @@ -389,7 +389,7 @@ static inline void dup_anon_vma_name(struct vm_area_str= uct *orig_vma, struct anon_vma_name *anon_name =3D anon_vma_name(orig_vma); =20 if (anon_name) - new_vma->anon_name =3D anon_vma_name_reuse(anon_name); + rcu_assign_pointer(new_vma->anon_name, anon_vma_name_reuse(anon_name)); } =20 static inline void free_anon_vma_name(struct vm_area_struct *vma) @@ -411,6 +411,8 @@ static inline bool anon_vma_name_eq(struct anon_vma_nam= e *anon_name1, !strcmp(anon_name1->name, anon_name2->name); } =20 +struct anon_vma_name *anon_vma_name_get_rcu(struct vm_area_struct *vma); + #else /* CONFIG_ANON_VMA_NAME */ static inline void anon_vma_name_get(struct anon_vma_name *anon_name) {} static inline void anon_vma_name_put(struct anon_vma_name *anon_name) {} @@ -424,6 +426,12 @@ static inline bool anon_vma_name_eq(struct anon_vma_na= me *anon_name1, return true; } =20 +static inline +struct anon_vma_name *anon_vma_name_get_rcu(struct vm_area_struct *vma) +{ + return NULL; +} + #endif /* CONFIG_ANON_VMA_NAME */ =20 static inline void init_tlb_flush_pending(struct mm_struct *mm) diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h index b2d3a88a34d1..1f0a30c00795 100644 --- a/include/linux/mm_types.h +++ b/include/linux/mm_types.h @@ -545,6 +545,7 @@ struct vm_userfaultfd_ctx {}; =20 struct anon_vma_name { struct kref kref; + struct rcu_head rcu; /* The name needs to be at the end because it is dynamically sized. */ char name[]; }; @@ -699,7 +700,7 @@ struct vm_area_struct { * terminated string containing the name given to the vma, or NULL if * unnamed. Serialized by mmap_lock. Use anon_vma_name to access. */ - struct anon_vma_name *anon_name; + struct anon_vma_name __rcu *anon_name; #endif #ifdef CONFIG_SWAP atomic_long_t swap_readahead_info; diff --git a/mm/madvise.c b/mm/madvise.c index 912155a94ed5..0f222d464254 100644 --- a/mm/madvise.c +++ b/mm/madvise.c @@ -88,14 +88,15 @@ void anon_vma_name_free(struct kref *kref) { struct anon_vma_name *anon_name =3D container_of(kref, struct anon_vma_name, kref); - kfree(anon_name); + kfree_rcu(anon_name, rcu); } =20 struct anon_vma_name *anon_vma_name(struct vm_area_struct *vma) { mmap_assert_locked(vma->vm_mm); =20 - return vma->anon_name; + return rcu_dereference_protected(vma->anon_name, + rwsem_is_locked(&vma->vm_mm->mmap_lock)); } =20 /* mmap_lock should be write-locked */ @@ -105,7 +106,7 @@ static int replace_anon_vma_name(struct vm_area_struct = *vma, struct anon_vma_name *orig_name =3D anon_vma_name(vma); =20 if (!anon_name) { - vma->anon_name =3D NULL; + rcu_assign_pointer(vma->anon_name, NULL); anon_vma_name_put(orig_name); return 0; } @@ -113,11 +114,32 @@ static int replace_anon_vma_name(struct vm_area_struc= t *vma, if (anon_vma_name_eq(orig_name, anon_name)) return 0; =20 - vma->anon_name =3D anon_vma_name_reuse(anon_name); + rcu_assign_pointer(vma->anon_name, anon_vma_name_reuse(anon_name)); anon_vma_name_put(orig_name); =20 return 0; } + +/* + * Returned anon_vma_name is stable due to elevated refcount but not guara= nteed + * to be assigned to the original VMA after the call. + */ +struct anon_vma_name *anon_vma_name_get_rcu(struct vm_area_struct *vma) +{ + struct anon_vma_name __rcu *anon_name; + + WARN_ON_ONCE(!rcu_read_lock_held()); + + anon_name =3D rcu_dereference(vma->anon_name); + if (!anon_name) + return NULL; + + if (unlikely(!kref_get_unless_zero(&anon_name->kref))) + return NULL; + + return anon_name; +} + #else /* CONFIG_ANON_VMA_NAME */ static int replace_anon_vma_name(struct vm_area_struct *vma, struct anon_vma_name *anon_name) --=20 2.43.0.381.gb435a96ce8-goog