- Linux-stable-mirror - lists.linaro.org

FAILED: patch "[PATCH] io_uring: fix cancellation taking mutex while" failed to apply to 5.10-stable tree

by gregkh＠linuxfoundation.org

The patch below does not apply to the 5.10-stable tree. If someone wants it applied there, or to any other stable or longterm tree, then please email the backport, including the original git commit id to <stable(a)vger.kernel.org>. thanks, greg k-h ------------------ original commit in Linus's tree ------------------ >From ca70f00bed6cb255b7a9b91aa18a2717c9217f70 Mon Sep 17 00:00:00 2001 From: Pavel Begunkov <asml.silence(a)gmail.com> Date: Tue, 26 Jan 2021 15:28:27 +0000 Subject: [PATCH] io_uring: fix cancellation taking mutex while TASK_UNINTERRUPTIBLE do not call blocking ops when !TASK_RUNNING; state=2 set at [<00000000ced9dbfc>] prepare_to_wait+0x1f4/0x3b0 kernel/sched/wait.c:262 WARNING: CPU: 1 PID: 19888 at kernel/sched/core.c:7853 __might_sleep+0xed/0x100 kernel/sched/core.c:7848 RIP: 0010:__might_sleep+0xed/0x100 kernel/sched/core.c:7848 Call Trace: __mutex_lock_common+0xc4/0x2ef0 kernel/locking/mutex.c:935 __mutex_lock kernel/locking/mutex.c:1103 [inline] mutex_lock_nested+0x1a/0x20 kernel/locking/mutex.c:1118 io_wq_submit_work+0x39a/0x720 fs/io_uring.c:6411 io_run_cancel fs/io-wq.c:856 [inline] io_wqe_cancel_pending_work fs/io-wq.c:990 [inline] io_wq_cancel_cb+0x614/0xcb0 fs/io-wq.c:1027 io_uring_cancel_files fs/io_uring.c:8874 [inline] io_uring_cancel_task_requests fs/io_uring.c:8952 [inline] __io_uring_files_cancel+0x115d/0x19e0 fs/io_uring.c:9038 io_uring_files_cancel include/linux/io_uring.h:51 [inline] do_exit+0x2e6/0x2490 kernel/exit.c:780 do_group_exit+0x168/0x2d0 kernel/exit.c:922 get_signal+0x16b5/0x2030 kernel/signal.c:2770 arch_do_signal_or_restart+0x8e/0x6a0 arch/x86/kernel/signal.c:811 handle_signal_work kernel/entry/common.c:147 [inline] exit_to_user_mode_loop kernel/entry/common.c:171 [inline] exit_to_user_mode_prepare+0xac/0x1e0 kernel/entry/common.c:201 __syscall_exit_to_user_mode_work kernel/entry/common.c:291 [inline] syscall_exit_to_user_mode+0x48/0x190 kernel/entry/common.c:302 entry_SYSCALL_64_after_hwframe+0x44/0xa9 Rewrite io_uring_cancel_files() to mimic __io_uring_task_cancel()'s counting scheme, so it does all the heavy work before setting TASK_UNINTERRUPTIBLE. Cc: stable(a)vger.kernel.org # 5.9+ Reported-by: syzbot+f655445043a26a7cfab8(a)syzkaller.appspotmail.com Signed-off-by: Pavel Begunkov <asml.silence(a)gmail.com> [axboe: fix inverted task check] Signed-off-by: Jens Axboe <axboe(a)kernel.dk> diff --git a/fs/io_uring.c b/fs/io_uring.c index 09aada153a71..bb0270eeb8cb 100644 --- a/fs/io_uring.c +++ b/fs/io_uring.c @@ -8873,30 +8873,31 @@ static void io_cancel_defer_files(struct io_ring_ctx *ctx, } } +static int io_uring_count_inflight(struct io_ring_ctx *ctx, + struct task_struct *task, + struct files_struct *files) +{ + struct io_kiocb *req; + int cnt = 0; + + spin_lock_irq(&ctx->inflight_lock); + list_for_each_entry(req, &ctx->inflight_list, inflight_entry) + cnt += io_match_task(req, task, files); + spin_unlock_irq(&ctx->inflight_lock); + return cnt; +} + static void io_uring_cancel_files(struct io_ring_ctx *ctx, struct task_struct *task, struct files_struct *files) { while (!list_empty_careful(&ctx->inflight_list)) { struct io_task_cancel cancel = { .task = task, .files = files }; - struct io_kiocb *req; DEFINE_WAIT(wait); - bool found = false; - - spin_lock_irq(&ctx->inflight_lock); - list_for_each_entry(req, &ctx->inflight_list, inflight_entry) { - if (!io_match_task(req, task, files)) - continue; - found = true; - break; - } - if (found) - prepare_to_wait(&task->io_uring->wait, &wait, - TASK_UNINTERRUPTIBLE); - spin_unlock_irq(&ctx->inflight_lock); + int inflight; - /* We need to keep going until we don't find a matching req */ - if (!found) + inflight = io_uring_count_inflight(ctx, task, files); + if (!inflight) break; io_wq_cancel_cb(ctx->io_wq, io_cancel_task_cb, &cancel, true); @@ -8905,7 +8906,11 @@ static void io_uring_cancel_files(struct io_ring_ctx *ctx, io_cqring_overflow_flush(ctx, true, task, files); /* cancellations _may_ trigger task work */ io_run_task_work(); - schedule(); + + prepare_to_wait(&task->io_uring->wait, &wait, + TASK_UNINTERRUPTIBLE); + if (inflight == io_uring_count_inflight(ctx, task, files)) + schedule(); finish_wait(&task->io_uring->wait, &wait); } }

4 years, 6 months

1
0
0 0

FAILED: patch "[PATCH] io_uring: fix __io_uring_files_cancel() with" failed to apply to 5.10-stable tree

by gregkh＠linuxfoundation.org

The patch below does not apply to the 5.10-stable tree. If someone wants it applied there, or to any other stable or longterm tree, then please email the backport, including the original git commit id to <stable(a)vger.kernel.org>. thanks, greg k-h ------------------ original commit in Linus's tree ------------------ >From a1bb3cd58913338e1b627ea6b8c03c2ae82d293f Mon Sep 17 00:00:00 2001 From: Pavel Begunkov <asml.silence(a)gmail.com> Date: Tue, 26 Jan 2021 15:28:26 +0000 Subject: [PATCH] io_uring: fix __io_uring_files_cancel() with TASK_UNINTERRUPTIBLE If the tctx inflight number haven't changed because of cancellation, __io_uring_task_cancel() will continue leaving the task in TASK_UNINTERRUPTIBLE state, that's not expected by __io_uring_files_cancel(). Ensure we always call finish_wait() before retrying. Cc: stable(a)vger.kernel.org # 5.9+ Signed-off-by: Pavel Begunkov <asml.silence(a)gmail.com> Signed-off-by: Jens Axboe <axboe(a)kernel.dk> diff --git a/fs/io_uring.c b/fs/io_uring.c index 2166c469789d..09aada153a71 100644 --- a/fs/io_uring.c +++ b/fs/io_uring.c @@ -9124,16 +9124,15 @@ void __io_uring_task_cancel(void) prepare_to_wait(&tctx->wait, &wait, TASK_UNINTERRUPTIBLE); /* - * If we've seen completions, retry. This avoids a race where - * a completion comes in before we did prepare_to_wait(). + * If we've seen completions, retry without waiting. This + * avoids a race where a completion comes in before we did + * prepare_to_wait(). */ - if (inflight != tctx_inflight(tctx)) - continue; - schedule(); + if (inflight == tctx_inflight(tctx)) + schedule(); finish_wait(&tctx->wait, &wait); } while (1); - finish_wait(&tctx->wait, &wait); atomic_dec(&tctx->in_idle); io_uring_remove_task_files(tctx);

4 years, 6 months

1
0
0 0

FAILED: patch "[PATCH] io_uring: if we see flush on exit, cancel related tasks" failed to apply to 5.10-stable tree

by gregkh＠linuxfoundation.org

The patch below does not apply to the 5.10-stable tree. If someone wants it applied there, or to any other stable or longterm tree, then please email the backport, including the original git commit id to <stable(a)vger.kernel.org>. thanks, greg k-h ------------------ original commit in Linus's tree ------------------ >From 84965ff8a84f0368b154c9b367b62e59c1193f30 Mon Sep 17 00:00:00 2001 From: Jens Axboe <axboe(a)kernel.dk> Date: Sat, 23 Jan 2021 15:51:11 -0700 Subject: [PATCH] io_uring: if we see flush on exit, cancel related tasks Ensure we match tasks that belong to a dead or dying task as well, as we need to reap those in addition to those belonging to the exiting task. Cc: stable(a)vger.kernel.org # 5.9+ Reported-by: Josef Grieb <josef.grieb(a)gmail.com> Signed-off-by: Jens Axboe <axboe(a)kernel.dk> diff --git a/fs/io_uring.c b/fs/io_uring.c index c07913ec0cca..695fe00bafdc 100644 --- a/fs/io_uring.c +++ b/fs/io_uring.c @@ -1069,8 +1069,12 @@ static bool io_match_task(struct io_kiocb *head, { struct io_kiocb *req; - if (task && head->task != task) + if (task && head->task != task) { + /* in terms of cancelation, always match if req task is dead */ + if (head->task->flags & PF_EXITING) + return true; return false; + } if (!files) return true; @@ -9136,6 +9140,9 @@ static int io_uring_flush(struct file *file, void *data) struct io_uring_task *tctx = current->io_uring; struct io_ring_ctx *ctx = file->private_data; + if (fatal_signal_pending(current) || (current->flags & PF_EXITING)) + io_uring_cancel_task_requests(ctx, NULL); + if (!tctx) return 0;

4 years, 6 months

1
0
0 0

FAILED: patch "[PATCH] io_uring: if we see flush on exit, cancel related tasks" failed to apply to 5.10-stable tree

by gregkh＠linuxfoundation.org

The patch below does not apply to the 5.10-stable tree. If someone wants it applied there, or to any other stable or longterm tree, then please email the backport, including the original git commit id to <stable(a)vger.kernel.org>. thanks, greg k-h ------------------ original commit in Linus's tree ------------------ >From 84965ff8a84f0368b154c9b367b62e59c1193f30 Mon Sep 17 00:00:00 2001 From: Jens Axboe <axboe(a)kernel.dk> Date: Sat, 23 Jan 2021 15:51:11 -0700 Subject: [PATCH] io_uring: if we see flush on exit, cancel related tasks Ensure we match tasks that belong to a dead or dying task as well, as we need to reap those in addition to those belonging to the exiting task. Cc: stable(a)vger.kernel.org # 5.9+ Reported-by: Josef Grieb <josef.grieb(a)gmail.com> Signed-off-by: Jens Axboe <axboe(a)kernel.dk> diff --git a/fs/io_uring.c b/fs/io_uring.c index c07913ec0cca..695fe00bafdc 100644 --- a/fs/io_uring.c +++ b/fs/io_uring.c @@ -1069,8 +1069,12 @@ static bool io_match_task(struct io_kiocb *head, { struct io_kiocb *req; - if (task && head->task != task) + if (task && head->task != task) { + /* in terms of cancelation, always match if req task is dead */ + if (head->task->flags & PF_EXITING) + return true; return false; + } if (!files) return true; @@ -9136,6 +9140,9 @@ static int io_uring_flush(struct file *file, void *data) struct io_uring_task *tctx = current->io_uring; struct io_ring_ctx *ctx = file->private_data; + if (fatal_signal_pending(current) || (current->flags & PF_EXITING)) + io_uring_cancel_task_requests(ctx, NULL); + if (!tctx) return 0;

4 years, 6 months

1
0
0 0

FAILED: patch "[PATCH] KVM: Forbid the use of tagged userspace addresses for" failed to apply to 4.9-stable tree

by gregkh＠linuxfoundation.org

The patch below does not apply to the 4.9-stable tree. If someone wants it applied there, or to any other stable or longterm tree, then please email the backport, including the original git commit id to <stable(a)vger.kernel.org>. thanks, greg k-h ------------------ original commit in Linus's tree ------------------ >From 139bc8a6146d92822c866cf2fd410159c56b3648 Mon Sep 17 00:00:00 2001 From: Marc Zyngier <maz(a)kernel.org> Date: Thu, 21 Jan 2021 12:08:15 +0000 Subject: [PATCH] KVM: Forbid the use of tagged userspace addresses for memslots The use of a tagged address could be pretty confusing for the whole memslot infrastructure as well as the MMU notifiers. Forbid it altogether, as it never quite worked the first place. Cc: stable(a)vger.kernel.org Reported-by: Rick Edgecombe <rick.p.edgecombe(a)intel.com> Reviewed-by: Catalin Marinas <catalin.marinas(a)arm.com> Signed-off-by: Marc Zyngier <maz(a)kernel.org> diff --git a/Documentation/virt/kvm/api.rst b/Documentation/virt/kvm/api.rst index 4e5316ed10e9..c347b7083abf 100644 --- a/Documentation/virt/kvm/api.rst +++ b/Documentation/virt/kvm/api.rst @@ -1269,6 +1269,9 @@ field userspace_addr, which must point at user addressable memory for the entire memory slot size. Any object may back this memory, including anonymous memory, ordinary files, and hugetlbfs. +On architectures that support a form of address tagging, userspace_addr must +be an untagged address. + It is recommended that the lower 21 bits of guest_phys_addr and userspace_addr be identical. This allows large pages in the guest to be backed by large pages in the host. diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c index 2541a17ff1c4..a9abaf5f8e53 100644 --- a/virt/kvm/kvm_main.c +++ b/virt/kvm/kvm_main.c @@ -1290,6 +1290,7 @@ int __kvm_set_memory_region(struct kvm *kvm, return -EINVAL; /* We can read the guest memory with __xxx_user() later on. */ if ((mem->userspace_addr & (PAGE_SIZE - 1)) || + (mem->userspace_addr != untagged_addr(mem->userspace_addr)) || !access_ok((void __user *)(unsigned long)mem->userspace_addr, mem->memory_size)) return -EINVAL;

4 years, 6 months

1
0
0 0

FAILED: patch "[PATCH] KVM: Forbid the use of tagged userspace addresses for" failed to apply to 4.19-stable tree

by gregkh＠linuxfoundation.org

The patch below does not apply to the 4.19-stable tree. If someone wants it applied there, or to any other stable or longterm tree, then please email the backport, including the original git commit id to <stable(a)vger.kernel.org>. thanks, greg k-h ------------------ original commit in Linus's tree ------------------ >From 139bc8a6146d92822c866cf2fd410159c56b3648 Mon Sep 17 00:00:00 2001 From: Marc Zyngier <maz(a)kernel.org> Date: Thu, 21 Jan 2021 12:08:15 +0000 Subject: [PATCH] KVM: Forbid the use of tagged userspace addresses for memslots The use of a tagged address could be pretty confusing for the whole memslot infrastructure as well as the MMU notifiers. Forbid it altogether, as it never quite worked the first place. Cc: stable(a)vger.kernel.org Reported-by: Rick Edgecombe <rick.p.edgecombe(a)intel.com> Reviewed-by: Catalin Marinas <catalin.marinas(a)arm.com> Signed-off-by: Marc Zyngier <maz(a)kernel.org> diff --git a/Documentation/virt/kvm/api.rst b/Documentation/virt/kvm/api.rst index 4e5316ed10e9..c347b7083abf 100644 --- a/Documentation/virt/kvm/api.rst +++ b/Documentation/virt/kvm/api.rst @@ -1269,6 +1269,9 @@ field userspace_addr, which must point at user addressable memory for the entire memory slot size. Any object may back this memory, including anonymous memory, ordinary files, and hugetlbfs. +On architectures that support a form of address tagging, userspace_addr must +be an untagged address. + It is recommended that the lower 21 bits of guest_phys_addr and userspace_addr be identical. This allows large pages in the guest to be backed by large pages in the host. diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c index 2541a17ff1c4..a9abaf5f8e53 100644 --- a/virt/kvm/kvm_main.c +++ b/virt/kvm/kvm_main.c @@ -1290,6 +1290,7 @@ int __kvm_set_memory_region(struct kvm *kvm, return -EINVAL; /* We can read the guest memory with __xxx_user() later on. */ if ((mem->userspace_addr & (PAGE_SIZE - 1)) || + (mem->userspace_addr != untagged_addr(mem->userspace_addr)) || !access_ok((void __user *)(unsigned long)mem->userspace_addr, mem->memory_size)) return -EINVAL;

4 years, 6 months

1
0
0 0

FAILED: patch "[PATCH] KVM: Forbid the use of tagged userspace addresses for" failed to apply to 4.4-stable tree

by gregkh＠linuxfoundation.org

The patch below does not apply to the 4.4-stable tree. If someone wants it applied there, or to any other stable or longterm tree, then please email the backport, including the original git commit id to <stable(a)vger.kernel.org>. thanks, greg k-h ------------------ original commit in Linus's tree ------------------ >From 139bc8a6146d92822c866cf2fd410159c56b3648 Mon Sep 17 00:00:00 2001 From: Marc Zyngier <maz(a)kernel.org> Date: Thu, 21 Jan 2021 12:08:15 +0000 Subject: [PATCH] KVM: Forbid the use of tagged userspace addresses for memslots The use of a tagged address could be pretty confusing for the whole memslot infrastructure as well as the MMU notifiers. Forbid it altogether, as it never quite worked the first place. Cc: stable(a)vger.kernel.org Reported-by: Rick Edgecombe <rick.p.edgecombe(a)intel.com> Reviewed-by: Catalin Marinas <catalin.marinas(a)arm.com> Signed-off-by: Marc Zyngier <maz(a)kernel.org> diff --git a/Documentation/virt/kvm/api.rst b/Documentation/virt/kvm/api.rst index 4e5316ed10e9..c347b7083abf 100644 --- a/Documentation/virt/kvm/api.rst +++ b/Documentation/virt/kvm/api.rst @@ -1269,6 +1269,9 @@ field userspace_addr, which must point at user addressable memory for the entire memory slot size. Any object may back this memory, including anonymous memory, ordinary files, and hugetlbfs. +On architectures that support a form of address tagging, userspace_addr must +be an untagged address. + It is recommended that the lower 21 bits of guest_phys_addr and userspace_addr be identical. This allows large pages in the guest to be backed by large pages in the host. diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c index 2541a17ff1c4..a9abaf5f8e53 100644 --- a/virt/kvm/kvm_main.c +++ b/virt/kvm/kvm_main.c @@ -1290,6 +1290,7 @@ int __kvm_set_memory_region(struct kvm *kvm, return -EINVAL; /* We can read the guest memory with __xxx_user() later on. */ if ((mem->userspace_addr & (PAGE_SIZE - 1)) || + (mem->userspace_addr != untagged_addr(mem->userspace_addr)) || !access_ok((void __user *)(unsigned long)mem->userspace_addr, mem->memory_size)) return -EINVAL;

4 years, 6 months

1
0
0 0

FAILED: patch "[PATCH] KVM: Forbid the use of tagged userspace addresses for" failed to apply to 4.14-stable tree

by gregkh＠linuxfoundation.org

The patch below does not apply to the 4.14-stable tree. If someone wants it applied there, or to any other stable or longterm tree, then please email the backport, including the original git commit id to <stable(a)vger.kernel.org>. thanks, greg k-h ------------------ original commit in Linus's tree ------------------ >From 139bc8a6146d92822c866cf2fd410159c56b3648 Mon Sep 17 00:00:00 2001 From: Marc Zyngier <maz(a)kernel.org> Date: Thu, 21 Jan 2021 12:08:15 +0000 Subject: [PATCH] KVM: Forbid the use of tagged userspace addresses for memslots The use of a tagged address could be pretty confusing for the whole memslot infrastructure as well as the MMU notifiers. Forbid it altogether, as it never quite worked the first place. Cc: stable(a)vger.kernel.org Reported-by: Rick Edgecombe <rick.p.edgecombe(a)intel.com> Reviewed-by: Catalin Marinas <catalin.marinas(a)arm.com> Signed-off-by: Marc Zyngier <maz(a)kernel.org> diff --git a/Documentation/virt/kvm/api.rst b/Documentation/virt/kvm/api.rst index 4e5316ed10e9..c347b7083abf 100644 --- a/Documentation/virt/kvm/api.rst +++ b/Documentation/virt/kvm/api.rst @@ -1269,6 +1269,9 @@ field userspace_addr, which must point at user addressable memory for the entire memory slot size. Any object may back this memory, including anonymous memory, ordinary files, and hugetlbfs. +On architectures that support a form of address tagging, userspace_addr must +be an untagged address. + It is recommended that the lower 21 bits of guest_phys_addr and userspace_addr be identical. This allows large pages in the guest to be backed by large pages in the host. diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c index 2541a17ff1c4..a9abaf5f8e53 100644 --- a/virt/kvm/kvm_main.c +++ b/virt/kvm/kvm_main.c @@ -1290,6 +1290,7 @@ int __kvm_set_memory_region(struct kvm *kvm, return -EINVAL; /* We can read the guest memory with __xxx_user() later on. */ if ((mem->userspace_addr & (PAGE_SIZE - 1)) || + (mem->userspace_addr != untagged_addr(mem->userspace_addr)) || !access_ok((void __user *)(unsigned long)mem->userspace_addr, mem->memory_size)) return -EINVAL;

4 years, 6 months

1
0
0 0

FAILED: patch "[PATCH] btrfs: fix possible free space tree corruption with online" failed to apply to 4.9-stable tree

by gregkh＠linuxfoundation.org

The patch below does not apply to the 4.9-stable tree. If someone wants it applied there, or to any other stable or longterm tree, then please email the backport, including the original git commit id to <stable(a)vger.kernel.org>. thanks, greg k-h ------------------ original commit in Linus's tree ------------------ >From 2f96e40212d435b328459ba6b3956395eed8fa9f Mon Sep 17 00:00:00 2001 From: Josef Bacik <josef(a)toxicpanda.com> Date: Fri, 15 Jan 2021 16:26:17 -0500 Subject: [PATCH] btrfs: fix possible free space tree corruption with online conversion While running btrfs/011 in a loop I would often ASSERT() while trying to add a new free space entry that already existed, or get an EEXIST while adding a new block to the extent tree, which is another indication of double allocation. This occurs because when we do the free space tree population, we create the new root and then populate the tree and commit the transaction. The problem is when you create a new root, the root node and commit root node are the same. During this initial transaction commit we will run all of the delayed refs that were paused during the free space tree generation, and thus begin to cache block groups. While caching block groups the caching thread will be reading from the main root for the free space tree, so as we make allocations we'll be changing the free space tree, which can cause us to add the same range twice which results in either the ASSERT(ret != -EEXIST); in __btrfs_add_free_space, or in a variety of different errors when running delayed refs because of a double allocation. Fix this by marking the fs_info as unsafe to load the free space tree, and fall back on the old slow method. We could be smarter than this, for example caching the block group while we're populating the free space tree, but since this is a serious problem I've opted for the simplest solution. CC: stable(a)vger.kernel.org # 4.9+ Fixes: a5ed91828518 ("Btrfs: implement the free space B-tree") Reviewed-by: Filipe Manana <fdmanana(a)suse.com> Signed-off-by: Josef Bacik <josef(a)toxicpanda.com> Signed-off-by: David Sterba <dsterba(a)suse.com> diff --git a/fs/btrfs/block-group.c b/fs/btrfs/block-group.c index 0886e81e5540..48ebc106a606 100644 --- a/fs/btrfs/block-group.c +++ b/fs/btrfs/block-group.c @@ -673,7 +673,15 @@ static noinline void caching_thread(struct btrfs_work *work) wake_up(&caching_ctl->wait); } - if (btrfs_fs_compat_ro(fs_info, FREE_SPACE_TREE)) + /* + * If we are in the transaction that populated the free space tree we + * can't actually cache from the free space tree as our commit root and + * real root are the same, so we could change the contents of the blocks + * while caching. Instead do the slow caching in this case, and after + * the transaction has committed we will be safe. + */ + if (btrfs_fs_compat_ro(fs_info, FREE_SPACE_TREE) && + !(test_bit(BTRFS_FS_FREE_SPACE_TREE_UNTRUSTED, &fs_info->flags))) ret = load_free_space_tree(caching_ctl); else ret = load_extent_tree_free(caching_ctl); diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h index 0225c5208f44..47ca8edafb5e 100644 --- a/fs/btrfs/ctree.h +++ b/fs/btrfs/ctree.h @@ -564,6 +564,9 @@ enum { /* Indicate that we need to cleanup space cache v1 */ BTRFS_FS_CLEANUP_SPACE_CACHE_V1, + + /* Indicate that we can't trust the free space tree for caching yet */ + BTRFS_FS_FREE_SPACE_TREE_UNTRUSTED, }; /* diff --git a/fs/btrfs/free-space-tree.c b/fs/btrfs/free-space-tree.c index e33a65bd9a0c..a33bca94d133 100644 --- a/fs/btrfs/free-space-tree.c +++ b/fs/btrfs/free-space-tree.c @@ -1150,6 +1150,7 @@ int btrfs_create_free_space_tree(struct btrfs_fs_info *fs_info) return PTR_ERR(trans); set_bit(BTRFS_FS_CREATING_FREE_SPACE_TREE, &fs_info->flags); + set_bit(BTRFS_FS_FREE_SPACE_TREE_UNTRUSTED, &fs_info->flags); free_space_root = btrfs_create_tree(trans, BTRFS_FREE_SPACE_TREE_OBJECTID); if (IS_ERR(free_space_root)) { @@ -1171,11 +1172,18 @@ int btrfs_create_free_space_tree(struct btrfs_fs_info *fs_info) btrfs_set_fs_compat_ro(fs_info, FREE_SPACE_TREE); btrfs_set_fs_compat_ro(fs_info, FREE_SPACE_TREE_VALID); clear_bit(BTRFS_FS_CREATING_FREE_SPACE_TREE, &fs_info->flags); + ret = btrfs_commit_transaction(trans); - return btrfs_commit_transaction(trans); + /* + * Now that we've committed the transaction any reading of our commit + * root will be safe, so we can cache from the free space tree now. + */ + clear_bit(BTRFS_FS_FREE_SPACE_TREE_UNTRUSTED, &fs_info->flags); + return ret; abort: clear_bit(BTRFS_FS_CREATING_FREE_SPACE_TREE, &fs_info->flags); + clear_bit(BTRFS_FS_FREE_SPACE_TREE_UNTRUSTED, &fs_info->flags); btrfs_abort_transaction(trans, ret); btrfs_end_transaction(trans); return ret;

4 years, 6 months

1
0
0 0

FAILED: patch "[PATCH] btrfs: fix possible free space tree corruption with online" failed to apply to 4.14-stable tree

by gregkh＠linuxfoundation.org

The patch below does not apply to the 4.14-stable tree. If someone wants it applied there, or to any other stable or longterm tree, then please email the backport, including the original git commit id to <stable(a)vger.kernel.org>. thanks, greg k-h ------------------ original commit in Linus's tree ------------------ >From 2f96e40212d435b328459ba6b3956395eed8fa9f Mon Sep 17 00:00:00 2001 From: Josef Bacik <josef(a)toxicpanda.com> Date: Fri, 15 Jan 2021 16:26:17 -0500 Subject: [PATCH] btrfs: fix possible free space tree corruption with online conversion While running btrfs/011 in a loop I would often ASSERT() while trying to add a new free space entry that already existed, or get an EEXIST while adding a new block to the extent tree, which is another indication of double allocation. This occurs because when we do the free space tree population, we create the new root and then populate the tree and commit the transaction. The problem is when you create a new root, the root node and commit root node are the same. During this initial transaction commit we will run all of the delayed refs that were paused during the free space tree generation, and thus begin to cache block groups. While caching block groups the caching thread will be reading from the main root for the free space tree, so as we make allocations we'll be changing the free space tree, which can cause us to add the same range twice which results in either the ASSERT(ret != -EEXIST); in __btrfs_add_free_space, or in a variety of different errors when running delayed refs because of a double allocation. Fix this by marking the fs_info as unsafe to load the free space tree, and fall back on the old slow method. We could be smarter than this, for example caching the block group while we're populating the free space tree, but since this is a serious problem I've opted for the simplest solution. CC: stable(a)vger.kernel.org # 4.9+ Fixes: a5ed91828518 ("Btrfs: implement the free space B-tree") Reviewed-by: Filipe Manana <fdmanana(a)suse.com> Signed-off-by: Josef Bacik <josef(a)toxicpanda.com> Signed-off-by: David Sterba <dsterba(a)suse.com> diff --git a/fs/btrfs/block-group.c b/fs/btrfs/block-group.c index 0886e81e5540..48ebc106a606 100644 --- a/fs/btrfs/block-group.c +++ b/fs/btrfs/block-group.c @@ -673,7 +673,15 @@ static noinline void caching_thread(struct btrfs_work *work) wake_up(&caching_ctl->wait); } - if (btrfs_fs_compat_ro(fs_info, FREE_SPACE_TREE)) + /* + * If we are in the transaction that populated the free space tree we + * can't actually cache from the free space tree as our commit root and + * real root are the same, so we could change the contents of the blocks + * while caching. Instead do the slow caching in this case, and after + * the transaction has committed we will be safe. + */ + if (btrfs_fs_compat_ro(fs_info, FREE_SPACE_TREE) && + !(test_bit(BTRFS_FS_FREE_SPACE_TREE_UNTRUSTED, &fs_info->flags))) ret = load_free_space_tree(caching_ctl); else ret = load_extent_tree_free(caching_ctl); diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h index 0225c5208f44..47ca8edafb5e 100644 --- a/fs/btrfs/ctree.h +++ b/fs/btrfs/ctree.h @@ -564,6 +564,9 @@ enum { /* Indicate that we need to cleanup space cache v1 */ BTRFS_FS_CLEANUP_SPACE_CACHE_V1, + + /* Indicate that we can't trust the free space tree for caching yet */ + BTRFS_FS_FREE_SPACE_TREE_UNTRUSTED, }; /* diff --git a/fs/btrfs/free-space-tree.c b/fs/btrfs/free-space-tree.c index e33a65bd9a0c..a33bca94d133 100644 --- a/fs/btrfs/free-space-tree.c +++ b/fs/btrfs/free-space-tree.c @@ -1150,6 +1150,7 @@ int btrfs_create_free_space_tree(struct btrfs_fs_info *fs_info) return PTR_ERR(trans); set_bit(BTRFS_FS_CREATING_FREE_SPACE_TREE, &fs_info->flags); + set_bit(BTRFS_FS_FREE_SPACE_TREE_UNTRUSTED, &fs_info->flags); free_space_root = btrfs_create_tree(trans, BTRFS_FREE_SPACE_TREE_OBJECTID); if (IS_ERR(free_space_root)) { @@ -1171,11 +1172,18 @@ int btrfs_create_free_space_tree(struct btrfs_fs_info *fs_info) btrfs_set_fs_compat_ro(fs_info, FREE_SPACE_TREE); btrfs_set_fs_compat_ro(fs_info, FREE_SPACE_TREE_VALID); clear_bit(BTRFS_FS_CREATING_FREE_SPACE_TREE, &fs_info->flags); + ret = btrfs_commit_transaction(trans); - return btrfs_commit_transaction(trans); + /* + * Now that we've committed the transaction any reading of our commit + * root will be safe, so we can cache from the free space tree now. + */ + clear_bit(BTRFS_FS_FREE_SPACE_TREE_UNTRUSTED, &fs_info->flags); + return ret; abort: clear_bit(BTRFS_FS_CREATING_FREE_SPACE_TREE, &fs_info->flags); + clear_bit(BTRFS_FS_FREE_SPACE_TREE_UNTRUSTED, &fs_info->flags); btrfs_abort_transaction(trans, ret); btrfs_end_transaction(trans); return ret;

4 years, 6 months

1
0
0 0

2025

2024

2023

2022

2021

2020

2019

2018

2017

Linux-stable-mirror