From patchwork Mon Jan 22 07:13:22 2024 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Suren Baghdasaryan X-Patchwork-Id: 13524874 Received: from mail-yw1-f201.google.com (mail-yw1-f201.google.com [209.85.128.201]) (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 A6881FBE1 for ; Mon, 22 Jan 2024 07:13:29 +0000 (UTC) Authentication-Results: smtp.subspace.kernel.org; arc=none smtp.client-ip=209.85.128.201 ARC-Seal: i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1705907611; cv=none; b=V/Tyu+s7tLedbn4c1B6MSr7F/5btlW50xfYEbfg6H0MnCHs7vTSOY4asSGWa3KVliu3snX6ZG6Lo9FutNM67Ej3KYaWGL/heDhyQNpVYLxLxsiCQd9DYATfxDNfyKiAkR4hUF5ny1X5SZGNjtO3kSsFvCTbKNqCYZMDLtxqf9Oo= ARC-Message-Signature: i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1705907611; c=relaxed/simple; bh=6Lrv5xwMfaDaPsl1VCKPLCnIY6z/5ht1dxDtK8LPTm4=; h=Date:Mime-Version:Message-ID:Subject:From:To:Cc:Content-Type; b=V9wsm3ztT9VWNqCjDNnus0HI32D6SbMDbj7T2N23snCHTD0FAPKOQKNajl0rnoagpZN1DmYSqps4LbM73GOUoZOpePJhVDV83BG6kssf1xAml3TUWb9FHtW2JWeQZs8IqoHoveKOpo0fkRTtJjnkr9CorbffkzlFDURbYvR05SU= ARC-Authentication-Results: i=1; smtp.subspace.kernel.org; dmarc=pass (p=reject dis=none) header.from=google.com; spf=pass smtp.mailfrom=flex--surenb.bounces.google.com; dkim=pass (2048-bit key) header.d=google.com header.i=@google.com header.b=UsWEKk8r; arc=none smtp.client-ip=209.85.128.201 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="UsWEKk8r" Received: by mail-yw1-f201.google.com with SMTP id 00721157ae682-5f38d676cecso43397347b3.0 for ; Sun, 21 Jan 2024 23:13:29 -0800 (PST) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=google.com; s=20230601; t=1705907608; x=1706512408; darn=vger.kernel.org; h=cc:to:from:subject:message-id:mime-version:date:from:to:cc:subject :date:message-id:reply-to; bh=oXyU4pkvCRYAyA2TUvsUC8dh5sAPzBBH4qagn6tOpF0=; b=UsWEKk8rXs+hKbDWocKQBdrDKXKhfh7jxYSGJNpmt/g5n6Ib5Uh7cFCdtwF1uBsKIo 6bV0X98CVkYYVLY2A8uEkBhzAv5kYDxH8nsK+7P9lARMQCWcL7k4auaMiQ0OacLPjz8J 22aphKXRcuApyh1s4BwTpO8M++11answPeB7Z4GtcZP+d1V+0X+EfzxgcfhAzKXC7hxA lNlWWZp0M+PPptivUqVxF8iO+FulNtCQyaQO9LtolBByrN9Z+w9YkmQX+JaTn9O7VOAk IPNA3xX69jCFo65s2A7SJ9YqakfeYuAO2S3UNxVv3zeckadO/eSh7ZZ3CXtmsRdaqwlQ p5oQ== X-Google-DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=1e100.net; s=20230601; t=1705907608; x=1706512408; h=cc:to:from:subject:message-id:mime-version:date:x-gm-message-state :from:to:cc:subject:date:message-id:reply-to; bh=oXyU4pkvCRYAyA2TUvsUC8dh5sAPzBBH4qagn6tOpF0=; b=RU/Jpfw87vKaJOhuz05Bqx/lINjzsGl5CoNZCubGNyvYkvsqnOmp/XvpDVXGDkAVz+ WjfNnqxFAHCoU4bys4HrLVT2zFv6RUKjisp7SPKVpeuvhT1FXkP+2NPKliwkpC85w4T5 B5zlgn/7QCHYSaIq6XgJAbAdPRC3DLDmeq+NTrlpvRsscpBZ3nVrt4ubduDnvILAlgtV 8zewiWbzLA5t2Jl5IcdE9eeOL32n4/3qmLPU4QuEc0CaKjV0M/SaciSrTj/IkvunHcqR eXNDS5MWNV7DisDEmsaoVFM2RG/uJCakzigQ3hY9QOfFAx8ISOTTosszByTivi2/vq/j VVrg== X-Gm-Message-State: AOJu0YwiLEpPX5iTgqNKtZc3ezHz5iDwNlucJEmRkteuv5Yhwuup4MN9 4BSufOOYMd01ejxG9L7bNh9ks4wL4mBjnQSOlQQ3AU6uZ6sPoXQkzxnlBmLWWMB0yBIIcojo95e g9Q== X-Google-Smtp-Source: AGHT+IG8d1Gn9VWPvChN4p2/RHkaCghVVAROZ7VOgDGN0KGJpb0phlIzNaSwlCWzvJeInLF/vdqx3fCBkG0= X-Received: from surenb-desktop.mtv.corp.google.com ([2620:15c:211:201:4979:1d79:d572:5708]) (user=surenb job=sendgmr) by 2002:a25:e90c:0:b0:dbe:49ca:eb03 with SMTP id n12-20020a25e90c000000b00dbe49caeb03mr1889847ybd.5.1705907608657; Sun, 21 Jan 2024 23:13:28 -0800 (PST) Date: Sun, 21 Jan 2024 23:13:22 -0800 Precedence: bulk X-Mailing-List: linux-fsdevel@vger.kernel.org List-Id: List-Subscribe: List-Unsubscribe: Mime-Version: 1.0 X-Mailer: git-send-email 2.43.0.429.g432eaa2c6b-goog Message-ID: <20240122071324.2099712-1-surenb@google.com> Subject: [PATCH 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 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_struct *orig_vma, struct anon_vma_name *anon_name = anon_vma_name(orig_vma); if (anon_name) - new_vma->anon_name = anon_vma_name_reuse(anon_name); + rcu_assign_pointer(new_vma->anon_name, anon_vma_name_reuse(anon_name)); } 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_name *anon_name1, !strcmp(anon_name1->name, anon_name2->name); } +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_name *anon_name1, return true; } +static inline +struct anon_vma_name *anon_vma_name_get_rcu(struct vm_area_struct *vma) +{ + return NULL; +} + #endif /* CONFIG_ANON_VMA_NAME */ 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 8b611e13153e..bbe1223cd992 100644 --- a/include/linux/mm_types.h +++ b/include/linux/mm_types.h @@ -545,6 +545,7 @@ struct vm_userfaultfd_ctx {}; 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 = container_of(kref, struct anon_vma_name, kref); - kfree(anon_name); + kfree_rcu(anon_name, rcu); } struct anon_vma_name *anon_vma_name(struct vm_area_struct *vma) { mmap_assert_locked(vma->vm_mm); - return vma->anon_name; + return rcu_dereference_protected(vma->anon_name, + rwsem_is_locked(&vma->vm_mm->mmap_lock)); } /* 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 = anon_vma_name(vma); if (!anon_name) { - vma->anon_name = 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_struct *vma, if (anon_vma_name_eq(orig_name, anon_name)) return 0; - vma->anon_name = anon_vma_name_reuse(anon_name); + rcu_assign_pointer(vma->anon_name, anon_vma_name_reuse(anon_name)); anon_vma_name_put(orig_name); return 0; } + +/* + * Returned anon_vma_name is stable due to elevated refcount but not guaranteed + * 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 = 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) From patchwork Mon Jan 22 07:13:23 2024 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Suren Baghdasaryan X-Patchwork-Id: 13524875 Received: from mail-yw1-f202.google.com (mail-yw1-f202.google.com [209.85.128.202]) (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 01E5CFC14 for ; Mon, 22 Jan 2024 07:13:31 +0000 (UTC) Authentication-Results: smtp.subspace.kernel.org; arc=none smtp.client-ip=209.85.128.202 ARC-Seal: i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1705907613; cv=none; b=TQM+FXv0EAVpwC6iihJMw51oaaKFsEG/OGQOqYKK8mZcQDQwOY4tGia0htsRIbgvVLRhmGEZeQIeyffCI/WV/bAk9YZZPjzc2urkdNPKgegL74TcWj2zeMbHlYw1JGDEpIJFsMyRfr4toGTg6Ay25rtzaOvrsp9dm0UT0lYG2jU= ARC-Message-Signature: i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1705907613; c=relaxed/simple; bh=VSmKcMfyN3MYuxa3M+8VItvp5qj4UNGBOJKK9wA9Qlk=; h=Date:In-Reply-To:Mime-Version:References:Message-ID:Subject:From: To:Cc:Content-Type; b=j7w6jifAVUBVd5IhEXvWps/flGdIUoX8fHsKfUy2u6xWZzUtFjUuPWPJGB0RVw7yi1p9NNgFGMdeDWzBK6M0b2eM3P2NEnTpErSgILc7zvfrC1JC2yELxezrppvuKGq5T2FmxN8anh4vzgYeTF0ADmaB8A4xTzJrVn/yJLAhKR8= ARC-Authentication-Results: i=1; smtp.subspace.kernel.org; dmarc=pass (p=reject dis=none) header.from=google.com; spf=pass smtp.mailfrom=flex--surenb.bounces.google.com; dkim=pass (2048-bit key) header.d=google.com header.i=@google.com header.b=1V6naVaZ; arc=none smtp.client-ip=209.85.128.202 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="1V6naVaZ" Received: by mail-yw1-f202.google.com with SMTP id 00721157ae682-5ff85fabbecso36887477b3.3 for ; Sun, 21 Jan 2024 23:13:31 -0800 (PST) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=google.com; s=20230601; t=1705907611; x=1706512411; 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=OLp6U6EsMSw583KQsA7U2jc3UsvPAv4xgtxefIxudO0=; b=1V6naVaZaSLjwy19DLCWrHyiuJ3nL9dOJ2i1WamO/OYHbln+7XGcnJa7FVhJZ1en2P hidngHBf6X4ak8lqqu/DpCUgRfjMX1rt2/n8kga7qyAjzfLtYy4HV57HOZXl5t8FujMG 7T47ry/neXetIKOdV59cMb7XDRgiLgR/wKqvpYiFeeWEGNiORBCsSS7D7fTdtW9Mf7QB JBfd1mE6W3oj3lDr7pFP5m72VsT3R9TXsmPynxDOj2Zl/On92L+Ig8wZnVj8XYJyF5aS xK1OIUYq2gRcrqpC4bBRb+fU19EAH+vMP4qmnNrJKmYEu3C0S90dRleNPT8J3yZe1ZuC FKuQ== X-Google-DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=1e100.net; s=20230601; t=1705907611; x=1706512411; 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=OLp6U6EsMSw583KQsA7U2jc3UsvPAv4xgtxefIxudO0=; b=Xiw1NkqF17THbRoWIUs2LrxNfkmCJzja9velcX6F85mzZbEuFO0n7j0J0szilEfNZF ia8elMsRKFs82DwdErlMrTLh0dKL/AwDauhc1SDzVW9zH9B0hI2uAVfF7mhYyk3wuCBT PJS6M/7aTmpHDRhC5+PHIdsyyt8ySLJ8tF/NDvUspGMGaOjchBPg4d3qoB0R0KaFxjju 0M8Xzg37gDX93oBtCBB8HnDePseXVqkNhfEJN3ViVvhZqelhR/DwmmbOJPoG/1OK8PmJ Wo6NjLzmY6Cjb01kGfY6yQd72NuRgoX3qBSMIit6ZH4G+IFizLG8QWDpS7x9qgnoNGVr dd+w== X-Gm-Message-State: AOJu0YwLuRG+82KajncHXLYUxbvO9j/meJzvlic1086RaHMGs3x4ZXKj MoFQtYwgfWw/r6M47fcNmEMoPx+Nihp9YmBux4j3uZxt0hRp3z4zGdS8oYPgmzFiPyVP91OoBrl x8w== X-Google-Smtp-Source: AGHT+IFDFx+rU5MMV2joyEArNdxSbn9+Uqv0sdgUNYpKz6Fm9lpqOqNw6v9H//7PI5LcIGO1EwFhJ6qHlkY= X-Received: from surenb-desktop.mtv.corp.google.com ([2620:15c:211:201:4979:1d79:d572:5708]) (user=surenb job=sendgmr) by 2002:a81:a096:0:b0:5e6:27ee:67fb with SMTP id x144-20020a81a096000000b005e627ee67fbmr1310854ywg.4.1705907611085; Sun, 21 Jan 2024 23:13:31 -0800 (PST) Date: Sun, 21 Jan 2024 23:13:23 -0800 In-Reply-To: <20240122071324.2099712-1-surenb@google.com> Precedence: bulk X-Mailing-List: linux-fsdevel@vger.kernel.org List-Id: List-Subscribe: List-Unsubscribe: Mime-Version: 1.0 References: <20240122071324.2099712-1-surenb@google.com> X-Mailer: git-send-email 2.43.0.429.g432eaa2c6b-goog Message-ID: <20240122071324.2099712-2-surenb@google.com> Subject: [PATCH 2/3] mm: add mm_struct sequence number to detect write locks 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 Provide a way for lockless mm_struct users to detect whether mm might have been changed since some specific point in time. The API provided allows the user to record a counter when it starts using the mm and later use that counter to check if anyone write-locked mmap_lock since the counter was recorded. Recording the counter value should be done while holding mmap_lock at least for reading to prevent the counter from concurrent changes. Every time mmap_lock is write-locked mm_struct updates its mm_wr_seq counter so that checks against counters recorded before that would fail, indicating a possibility of mm being modified. Signed-off-by: Suren Baghdasaryan --- include/linux/mm_types.h | 2 ++ include/linux/mmap_lock.h | 22 ++++++++++++++++++++++ 2 files changed, 24 insertions(+) diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h index bbe1223cd992..e749f7f09314 100644 --- a/include/linux/mm_types.h +++ b/include/linux/mm_types.h @@ -846,6 +846,8 @@ struct mm_struct { */ int mm_lock_seq; #endif + /* Counter incremented each time mm gets write-locked */ + unsigned long mm_wr_seq; unsigned long hiwater_rss; /* High-watermark of RSS usage */ diff --git a/include/linux/mmap_lock.h b/include/linux/mmap_lock.h index 8d38dcb6d044..0197079cb6fe 100644 --- a/include/linux/mmap_lock.h +++ b/include/linux/mmap_lock.h @@ -106,6 +106,8 @@ static inline void mmap_write_lock(struct mm_struct *mm) { __mmap_lock_trace_start_locking(mm, true); down_write(&mm->mmap_lock); + /* Pairs with ACQUIRE semantics in mmap_write_seq_read */ + smp_store_release(&mm->mm_wr_seq, mm->mm_wr_seq + 1); __mmap_lock_trace_acquire_returned(mm, true, true); } @@ -113,6 +115,8 @@ static inline void mmap_write_lock_nested(struct mm_struct *mm, int subclass) { __mmap_lock_trace_start_locking(mm, true); down_write_nested(&mm->mmap_lock, subclass); + /* Pairs with ACQUIRE semantics in mmap_write_seq_read */ + smp_store_release(&mm->mm_wr_seq, mm->mm_wr_seq + 1); __mmap_lock_trace_acquire_returned(mm, true, true); } @@ -122,6 +126,10 @@ static inline int mmap_write_lock_killable(struct mm_struct *mm) __mmap_lock_trace_start_locking(mm, true); ret = down_write_killable(&mm->mmap_lock); + if (!ret) { + /* Pairs with ACQUIRE semantics in mmap_write_seq_read */ + smp_store_release(&mm->mm_wr_seq, mm->mm_wr_seq + 1); + } __mmap_lock_trace_acquire_returned(mm, true, ret == 0); return ret; } @@ -140,6 +148,20 @@ static inline void mmap_write_downgrade(struct mm_struct *mm) downgrade_write(&mm->mmap_lock); } +static inline unsigned long mmap_write_seq_read(struct mm_struct *mm) +{ + /* Pairs with RELEASE semantics in mmap_write_lock */ + return smp_load_acquire(&mm->mm_wr_seq); +} + +static inline void mmap_write_seq_record(struct mm_struct *mm, + unsigned long *mm_wr_seq) +{ + mmap_assert_locked(mm); + /* Nobody can concurrently modify since we hold the mmap_lock */ + *mm_wr_seq = mm->mm_wr_seq; +} + static inline void mmap_read_lock(struct mm_struct *mm) { __mmap_lock_trace_start_locking(mm, false); From patchwork Mon Jan 22 07:13:24 2024 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Suren Baghdasaryan X-Patchwork-Id: 13524876 Received: from mail-yw1-f201.google.com (mail-yw1-f201.google.com [209.85.128.201]) (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 34B4B111B4 for ; Mon, 22 Jan 2024 07:13:34 +0000 (UTC) Authentication-Results: smtp.subspace.kernel.org; arc=none smtp.client-ip=209.85.128.201 ARC-Seal: i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1705907615; cv=none; b=qP17LnchqeX5bvGHBweZLoMftL1QX3cki1JeQaZqbrHEQtYoO6x6PqIQcUu55q2lI2Kpj7s21qBJCARyaPS31PvdT1HzPgu8Q308lIPXqep8t9ZxAyWNagENI200h+Z2CLFp7+pr/HYZ5/xo063I6pzPoLItYcZ78K1HT8cNgC0= ARC-Message-Signature: i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1705907615; c=relaxed/simple; bh=Q4c5kAQB/tihMQ4sonqfCtbk7g6WtRsFX1gU0E6agKU=; h=Date:In-Reply-To:Mime-Version:References:Message-ID:Subject:From: To:Cc:Content-Type; b=OZQiWHa4LCfoeA8Lmv5Q8iJUtLUHcUXzE+3XVBZxtcXbZHI48ngtLvMjWpT6TQWuoP2EvHlXSCl6lQtKhEWg+eyCEQtYSFhewGdrFA6gkx6k5pPgG8E7O1zQ7HcDMaU8iY0k+8NcRHiTRfc28YB0CGt0hbwEnyqoPSeLxz/2ocQ= ARC-Authentication-Results: i=1; smtp.subspace.kernel.org; dmarc=pass (p=reject dis=none) header.from=google.com; spf=pass smtp.mailfrom=flex--surenb.bounces.google.com; dkim=pass (2048-bit key) header.d=google.com header.i=@google.com header.b=Nv+KkvTo; arc=none smtp.client-ip=209.85.128.201 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="Nv+KkvTo" Received: by mail-yw1-f201.google.com with SMTP id 00721157ae682-6000bbc9c8cso3391967b3.1 for ; Sun, 21 Jan 2024 23:13:34 -0800 (PST) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=google.com; s=20230601; t=1705907613; x=1706512413; 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=pm6LGPn0g5uP1lRXkRkuwE07r5wy4EXy2R/IId+4s5Y=; b=Nv+KkvToXtL3NAC2LApO/y0zwVfomGjye0FD+j0U5teteYMGoGEa4/oaLHhUK6eBn0 bXPvDUHjwoGKWAZhCowMrIonl7J+yUwsyTEhHy6RDtD7SG0LWVOXlHzRyK9niqdw/Pw7 kpOzkGY+YkktZHQr/dr9ptU05NY/zvxr+Z+3G0seLVaT6QYjNU3HGzE2UJoSO4C/q5J2 TivSWrMUfRUh7MmnE0XacQi8X1svM4kWG+/4Xi13TOZaF3PRwy5yDW9miv+8uYyn92Wt pV0FQSv3KsdThEEWfYaQwD6Cs/lx9wtxaF8FTAyAfAz4J55yZ/KGwnKE07rAn7C2ScJA dp0A== X-Google-DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=1e100.net; s=20230601; t=1705907613; x=1706512413; 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=pm6LGPn0g5uP1lRXkRkuwE07r5wy4EXy2R/IId+4s5Y=; b=lFXiIaUS4MNeeSwo/LUO6IYjt23GuxzRAcYa5DMSNGeiG8qDune8qYajsc3HkGonNR JhirApW8FbkOzveV97JSgg0MCUYoI3l8IWL3/sN7KzDvJhKA7WrzrMts9Q1hHsj9uwGu Q+bRJNMv2lkDgg0QNBk0r90Uxi9oLxRZBn+oaBIYjavN1Zm8LLRiJF694QeaH/r2DETm JgId/LNZDFhLIMsig+Atg543HNJEs4YgI2qD7EGq5RwcggyuNhxxnSKU84hvVCCgWSiz bep4bCCHN5DOUKgY/9Xfq9/+clJgpkosIjyiobtckgJG9aI0YDx+agqGizJhyyOgzXlE 9Z7A== X-Gm-Message-State: AOJu0YyEzNsLREOJPscgNYJdlCHeJx4yof8nc/1ihhH+36bo+KKXtfDe n/S5zBjW3P31/6VwapG1dP59NpyaI1cDcdto1WUaoexZLT9S51ffGfiOKMs/bTSEP3uBsPzixco N+w== X-Google-Smtp-Source: AGHT+IH/iYjVx28BB70L/Axhud1gI/xXkTJNuH9QVTuj4mqjLNYD8CKXEzHkMSgNYwCDkSwAyquSZSHHvqg= X-Received: from surenb-desktop.mtv.corp.google.com ([2620:15c:211:201:4979:1d79:d572:5708]) (user=surenb job=sendgmr) by 2002:a81:9847:0:b0:5e7:12cc:a60f with SMTP id p68-20020a819847000000b005e712cca60fmr1362943ywg.6.1705907613421; Sun, 21 Jan 2024 23:13:33 -0800 (PST) Date: Sun, 21 Jan 2024 23:13:24 -0800 In-Reply-To: <20240122071324.2099712-1-surenb@google.com> Precedence: bulk X-Mailing-List: linux-fsdevel@vger.kernel.org List-Id: List-Subscribe: List-Unsubscribe: Mime-Version: 1.0 References: <20240122071324.2099712-1-surenb@google.com> X-Mailer: git-send-email 2.43.0.429.g432eaa2c6b-goog Message-ID: <20240122071324.2099712-3-surenb@google.com> Subject: [PATCH 3/3] mm/maps: read proc/pid/maps under RCU 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 With maple_tree supporting vma tree traversal under RCU and per-vma locks making vma access RCU-safe, /proc/pid/maps can be read under RCU and without the need to read-lock mmap_lock. However vma content can change from under us, therefore we make a copy of the vma and we pin pointer fields used when generating the output (currently only vm_file and anon_name). Afterwards we check for concurrent address space modifications, wait for them to end and retry. That last check is needed to avoid possibility of missing a vma during concurrent maple_tree node replacement, which might report a NULL when a vma is replaced with another one. While we take the mmap_lock for reading during such contention, we do that momentarily only to record new mm_wr_seq counter. This change is designed to reduce mmap_lock contention and prevent a process reading /proc/pid/maps files (often a low priority task, such as monitoring/data collection services) from blocking address space updates. Note that this change has a userspace visible disadvantage: it allows for sub-page data tearing as opposed to the previous mechanism where data tearing could happen only between pages of generated output data. Since current userspace considers data tearing between pages to be acceptable, we assume is will be able to handle sub-page data tearing as well. Signed-off-by: Suren Baghdasaryan --- fs/proc/internal.h | 2 + fs/proc/task_mmu.c | 114 ++++++++++++++++++++++++++++++++++++++++++--- 2 files changed, 109 insertions(+), 7 deletions(-) diff --git a/fs/proc/internal.h b/fs/proc/internal.h index a71ac5379584..e0247225bb68 100644 --- a/fs/proc/internal.h +++ b/fs/proc/internal.h @@ -290,6 +290,8 @@ struct proc_maps_private { struct task_struct *task; struct mm_struct *mm; struct vma_iterator iter; + unsigned long mm_wr_seq; + struct vm_area_struct vma_copy; #ifdef CONFIG_NUMA struct mempolicy *task_mempolicy; #endif diff --git a/fs/proc/task_mmu.c b/fs/proc/task_mmu.c index 3f78ebbb795f..3886d04afc01 100644 --- a/fs/proc/task_mmu.c +++ b/fs/proc/task_mmu.c @@ -126,11 +126,96 @@ static void release_task_mempolicy(struct proc_maps_private *priv) } #endif -static struct vm_area_struct *proc_get_vma(struct proc_maps_private *priv, - loff_t *ppos) +#ifdef CONFIG_PER_VMA_LOCK + +static const struct seq_operations proc_pid_maps_op; +/* + * Take VMA snapshot and pin vm_file and anon_name as they are used by + * show_map_vma. + */ +static int get_vma_snapshow(struct proc_maps_private *priv, struct vm_area_struct *vma) { + struct vm_area_struct *copy = &priv->vma_copy; + int ret = -EAGAIN; + + memcpy(copy, vma, sizeof(*vma)); + if (copy->vm_file && !get_file_rcu(©->vm_file)) + goto out; + + if (copy->anon_name && !anon_vma_name_get_rcu(copy)) + goto put_file; + + if (priv->mm_wr_seq == mmap_write_seq_read(priv->mm)) + return 0; + + /* Address space got modified, vma might be stale. Wait and retry. */ + rcu_read_unlock(); + ret = mmap_read_lock_killable(priv->mm); + mmap_write_seq_record(priv->mm, &priv->mm_wr_seq); + mmap_read_unlock(priv->mm); + rcu_read_lock(); + + if (!ret) + ret = -EAGAIN; /* no other errors, ok to retry */ + + if (copy->anon_name) + anon_vma_name_put(copy->anon_name); +put_file: + if (copy->vm_file) + fput(copy->vm_file); +out: + return ret; +} + +static void put_vma_snapshot(struct proc_maps_private *priv) +{ + struct vm_area_struct *vma = &priv->vma_copy; + + if (vma->anon_name) + anon_vma_name_put(vma->anon_name); + if (vma->vm_file) + fput(vma->vm_file); +} + +static inline bool needs_mmap_lock(struct seq_file *m) +{ + /* + * smaps and numa_maps perform page table walk, therefore require + * mmap_lock but maps can be read under RCU. + */ + return m->op != &proc_pid_maps_op; +} + +#else /* CONFIG_PER_VMA_LOCK */ + +/* Without per-vma locks VMA access is not RCU-safe */ +static inline bool needs_mmap_lock(struct seq_file *m) { return true; } + +#endif /* CONFIG_PER_VMA_LOCK */ + +static struct vm_area_struct *proc_get_vma(struct seq_file *m, loff_t *ppos) +{ + struct proc_maps_private *priv = m->private; struct vm_area_struct *vma = vma_next(&priv->iter); +#ifdef CONFIG_PER_VMA_LOCK + if (vma && !needs_mmap_lock(m)) { + int ret; + + put_vma_snapshot(priv); + while ((ret = get_vma_snapshow(priv, vma)) == -EAGAIN) { + /* lookup the vma at the last position again */ + vma_iter_init(&priv->iter, priv->mm, *ppos); + vma = vma_next(&priv->iter); + } + + if (ret) { + put_vma_snapshot(priv); + return NULL; + } + vma = &priv->vma_copy; + } +#endif if (vma) { *ppos = vma->vm_start; } else { @@ -169,12 +254,20 @@ static void *m_start(struct seq_file *m, loff_t *ppos) return ERR_PTR(-EINTR); } + /* Drop mmap_lock if possible */ + if (!needs_mmap_lock(m)) { + mmap_write_seq_record(priv->mm, &priv->mm_wr_seq); + mmap_read_unlock(priv->mm); + rcu_read_lock(); + memset(&priv->vma_copy, 0, sizeof(priv->vma_copy)); + } + vma_iter_init(&priv->iter, mm, last_addr); hold_task_mempolicy(priv); if (last_addr == -2UL) return get_gate_vma(mm); - return proc_get_vma(priv, ppos); + return proc_get_vma(m, ppos); } static void *m_next(struct seq_file *m, void *v, loff_t *ppos) @@ -183,7 +276,7 @@ static void *m_next(struct seq_file *m, void *v, loff_t *ppos) *ppos = -1UL; return NULL; } - return proc_get_vma(m->private, ppos); + return proc_get_vma(m, ppos); } static void m_stop(struct seq_file *m, void *v) @@ -195,7 +288,10 @@ static void m_stop(struct seq_file *m, void *v) return; release_task_mempolicy(priv); - mmap_read_unlock(mm); + if (needs_mmap_lock(m)) + mmap_read_unlock(mm); + else + rcu_read_unlock(); mmput(mm); put_task_struct(priv->task); priv->task = NULL; @@ -283,8 +379,10 @@ show_map_vma(struct seq_file *m, struct vm_area_struct *vma) start = vma->vm_start; end = vma->vm_end; show_vma_header_prefix(m, start, end, flags, pgoff, dev, ino); - if (mm) - anon_name = anon_vma_name(vma); + if (mm) { + anon_name = needs_mmap_lock(m) ? anon_vma_name(vma) : + anon_vma_name_get_rcu(vma); + } /* * Print the dentry name for named mappings, and a @@ -338,6 +436,8 @@ show_map_vma(struct seq_file *m, struct vm_area_struct *vma) seq_puts(m, name); } seq_putc(m, '\n'); + if (anon_name && !needs_mmap_lock(m)) + anon_vma_name_put(anon_name); } static int show_map(struct seq_file *m, void *v)