From: Pavel Begunkov asml.silence@gmail.com

[ Upstream commit 08d23634643c239ddae706758f54d3a8e0c24962 ]

Add io_match_task() that matches both task and files.

Signed-off-by: Pavel Begunkov asml.silence@gmail.com Signed-off-by: Jens Axboe axboe@kernel.dk Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- fs/io_uring.c | 63 +++++++++++++++++++++++++++++----------------------------- 1 file changed, 32 insertions(+), 31 deletions(-)

--- a/fs/io_uring.c +++ b/fs/io_uring.c @@ -997,6 +997,36 @@ static inline void io_clean_op(struct io __io_clean_op(req); }

+static inline bool __io_match_files(struct io_kiocb *req, + struct files_struct *files) +{ + return ((req->flags & REQ_F_WORK_INITIALIZED) && + (req->work.flags & IO_WQ_WORK_FILES)) && + req->work.identity->files == files; +} + +static bool io_match_task(struct io_kiocb *head, + struct task_struct *task, + struct files_struct *files) +{ + struct io_kiocb *link; + + if (task && head->task != task) + return false; + if (!files) + return true; + if (__io_match_files(head, files)) + return true; + if (head->flags & REQ_F_LINK_HEAD) { + list_for_each_entry(link, &head->link_list, link_list) { + if (__io_match_files(link, files)) + return true; + } + } + return false; +} + + static void io_sq_thread_drop_mm(void) { struct mm_struct *mm = current->mm; @@ -1612,32 +1642,6 @@ static void io_cqring_mark_overflow(stru } }

-static inline bool __io_match_files(struct io_kiocb *req, - struct files_struct *files) -{ - return ((req->flags & REQ_F_WORK_INITIALIZED) && - (req->work.flags & IO_WQ_WORK_FILES)) && - req->work.identity->files == files; -} - -static bool io_match_files(struct io_kiocb *req, - struct files_struct *files) -{ - struct io_kiocb *link; - - if (!files) - return true; - if (__io_match_files(req, files)) - return true; - if (req->flags & REQ_F_LINK_HEAD) { - list_for_each_entry(link, &req->link_list, link_list) { - if (__io_match_files(link, files)) - return true; - } - } - return false; -} - /* Returns true if there are no backlogged entries after the flush */ static bool __io_cqring_overflow_flush(struct io_ring_ctx *ctx, bool force, struct task_struct *tsk, @@ -1659,9 +1663,7 @@ static bool __io_cqring_overflow_flush(s

cqe = NULL; list_for_each_entry_safe(req, tmp, &ctx->cq_overflow_list, compl.list) { - if (tsk && req->task != tsk) - continue; - if (!io_match_files(req, files)) + if (!io_match_task(req, tsk, files)) continue;

cqe = io_get_cqring(ctx); @@ -8635,8 +8637,7 @@ static void io_cancel_defer_files(struct

spin_lock_irq(&ctx->completion_lock); list_for_each_entry_reverse(de, &ctx->defer_list, list) { - if (io_task_match(de->req, task) && - io_match_files(de->req, files)) { + if (io_match_task(de->req, task, files)) { list_cut_position(&list, &ctx->defer_list, &de->list); break; }

From: Pavel Begunkov asml.silence@gmail.com

[ Upstream commit 6b81928d4ca8668513251f9c04cdcb9d38ef51c7 ]

Make io_poll_remove_all() and io_kill_timeouts() to match against files as well. A preparation patch, effectively not used by now.

Signed-off-by: Pavel Begunkov asml.silence@gmail.com Signed-off-by: Jens Axboe axboe@kernel.dk Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- fs/io_uring.c | 18 ++++++++++-------- 1 file changed, 10 insertions(+), 8 deletions(-)

--- a/fs/io_uring.c +++ b/fs/io_uring.c @@ -1508,14 +1508,15 @@ static bool io_task_match(struct io_kioc /* * Returns true if we found and killed one or more timeouts */ -static bool io_kill_timeouts(struct io_ring_ctx *ctx, struct task_struct *tsk) +static bool io_kill_timeouts(struct io_ring_ctx *ctx, struct task_struct *tsk, + struct files_struct *files) { struct io_kiocb *req, *tmp; int canceled = 0;

spin_lock_irq(&ctx->completion_lock); list_for_each_entry_safe(req, tmp, &ctx->timeout_list, timeout.list) { - if (io_task_match(req, tsk)) { + if (io_match_task(req, tsk, files)) { io_kill_timeout(req); canceled++; } @@ -5312,7 +5313,8 @@ static bool io_poll_remove_one(struct io /* * Returns true if we found and killed one or more poll requests */ -static bool io_poll_remove_all(struct io_ring_ctx *ctx, struct task_struct *tsk) +static bool io_poll_remove_all(struct io_ring_ctx *ctx, struct task_struct *tsk, + struct files_struct *files) { struct hlist_node *tmp; struct io_kiocb *req; @@ -5324,7 +5326,7 @@ static bool io_poll_remove_all(struct io

list = &ctx->cancel_hash[i]; hlist_for_each_entry_safe(req, tmp, list, hash_node) { - if (io_task_match(req, tsk)) + if (io_match_task(req, tsk, files)) posted += io_poll_remove_one(req); } } @@ -8485,8 +8487,8 @@ static void io_ring_ctx_wait_and_kill(st __io_cqring_overflow_flush(ctx, true, NULL, NULL); mutex_unlock(&ctx->uring_lock);

- io_kill_timeouts(ctx, NULL); - io_poll_remove_all(ctx, NULL); + io_kill_timeouts(ctx, NULL, NULL); + io_poll_remove_all(ctx, NULL, NULL);

if (ctx->io_wq) io_wq_cancel_cb(ctx->io_wq, io_cancel_ctx_cb, ctx, true); @@ -8721,8 +8723,8 @@ static void __io_uring_cancel_task_reque } }

- ret |= io_poll_remove_all(ctx, task); - ret |= io_kill_timeouts(ctx, task); + ret |= io_poll_remove_all(ctx, task, NULL); + ret |= io_kill_timeouts(ctx, task, NULL); if (!ret) break; io_run_task_work();

From: Pavel Begunkov asml.silence@gmail.com

[ Upstream commit bee749b187ac57d1faf00b2ab356ff322230fce8 ]

io_uring_cancel_files()'s task check condition mistakenly got flipped.

1. There can't be a request in the inflight list without IO_WQ_WORK_FILES, kill this check to keep the whole condition simpler. 2. Also, don't call the function for files==NULL to not do such a check, all that staff is already handled well by its counter part, __io_uring_cancel_task_requests().

With that just flip the task check.

Also, it iowq-cancels all request of current task there, don't forget to set right ->files into struct io_task_cancel.

Fixes: c1973b38bf639 ("io_uring: cancel only requests of current task") Reported-by: syzbot+c0d52d0b3c0c3ffb9525@syzkaller.appspotmail.com Signed-off-by: Pavel Begunkov asml.silence@gmail.com Signed-off-by: Jens Axboe axboe@kernel.dk Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- fs/io_uring.c | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-)

--- a/fs/io_uring.c +++ b/fs/io_uring.c @@ -8571,15 +8571,14 @@ static void io_uring_cancel_files(struct struct files_struct *files) { while (!list_empty_careful(&ctx->inflight_list)) { - struct io_task_cancel cancel = { .task = task, .files = NULL, }; + 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 (req->task == task && - (req->work.flags & IO_WQ_WORK_FILES) && + if (req->task != task || req->work.identity->files != files) continue; found = true; @@ -8665,10 +8664,11 @@ static void io_uring_cancel_task_request

io_cancel_defer_files(ctx, task, files); io_cqring_overflow_flush(ctx, true, task, files); - io_uring_cancel_files(ctx, task, files);

if (!files) __io_uring_cancel_task_requests(ctx, task); + else + io_uring_cancel_files(ctx, task, files);

if ((ctx->flags & IORING_SETUP_SQPOLL) && ctx->sq_data) { atomic_dec(&task->io_uring->in_idle);

From: Jens Axboe axboe@kernel.dk

[ Upstream commit 84965ff8a84f0368b154c9b367b62e59c1193f30 ]

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@vger.kernel.org # 5.9+ Reported-by: Josef Grieb josef.grieb@gmail.com Signed-off-by: Jens Axboe axboe@kernel.dk Signed-off-by: Pavel Begunkov asml.silence@gmail.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- fs/io_uring.c | 9 ++++++++- 1 file changed, 8 insertions(+), 1 deletion(-)

--- a/fs/io_uring.c +++ b/fs/io_uring.c @@ -1014,8 +1014,12 @@ static bool io_match_task(struct io_kioc { struct io_kiocb *link;

- 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; if (__io_match_files(head, files)) @@ -8844,6 +8848,9 @@ static int io_uring_flush(struct file *f 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;

From: Pavel Begunkov asml.silence@gmail.com

[ Upstream commit c98de08c990e190fc7cc3aaf8079b4a0674c6425 ]

As tasks now cancel only theirs requests, and inflight_wait is awaited only in io_uring_cancel_files(), which should be called with ->in_idle set, instead of keeping a separate inflight_wait use tctx->wait.

That will add some spurious wakeups but actually is safer from point of not hanging the task.

e.g. task1 | IRQ | *start* io_complete_rw_common(link) | link: req1 -> req2 -> req3(with files) *cancel_files() | io_wq_cancel(), etc. | | put_req(link), adds to io-wq req2 schedule() |

So, task1 will never try to cancel req2 or req3. If req2 is long-standing (e.g. read(empty_pipe)), this may hang.

Signed-off-by: Pavel Begunkov asml.silence@gmail.com Signed-off-by: Jens Axboe axboe@kernel.dk Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- fs/io_uring.c | 13 ++++++------- 1 file changed, 6 insertions(+), 7 deletions(-)

--- a/fs/io_uring.c +++ b/fs/io_uring.c @@ -286,7 +286,6 @@ struct io_ring_ctx { struct list_head timeout_list; struct list_head cq_overflow_list;

- wait_queue_head_t inflight_wait; struct io_uring_sqe *sq_sqes; } ____cacheline_aligned_in_smp;

@@ -1220,7 +1219,6 @@ static struct io_ring_ctx *io_ring_ctx_a INIT_LIST_HEAD(&ctx->iopoll_list); INIT_LIST_HEAD(&ctx->defer_list); INIT_LIST_HEAD(&ctx->timeout_list); - init_waitqueue_head(&ctx->inflight_wait); spin_lock_init(&ctx->inflight_lock); INIT_LIST_HEAD(&ctx->inflight_list); INIT_DELAYED_WORK(&ctx->file_put_work, io_file_put_work); @@ -5894,6 +5892,7 @@ static int io_req_defer(struct io_kiocb static void io_req_drop_files(struct io_kiocb *req) { struct io_ring_ctx *ctx = req->ctx; + struct io_uring_task *tctx = req->task->io_uring; unsigned long flags;

if (req->work.flags & IO_WQ_WORK_FILES) { @@ -5905,8 +5904,8 @@ static void io_req_drop_files(struct io_ spin_unlock_irqrestore(&ctx->inflight_lock, flags); req->flags &= ~REQ_F_INFLIGHT; req->work.flags &= ~IO_WQ_WORK_FILES; - if (waitqueue_active(&ctx->inflight_wait)) - wake_up(&ctx->inflight_wait); + if (atomic_read(&tctx->in_idle)) + wake_up(&tctx->wait); }

static void __io_clean_op(struct io_kiocb *req) @@ -8605,8 +8604,8 @@ static void io_uring_cancel_files(struct break; } if (found) - prepare_to_wait(&ctx->inflight_wait, &wait, - TASK_UNINTERRUPTIBLE); + prepare_to_wait(&task->io_uring->wait, &wait, + TASK_UNINTERRUPTIBLE); spin_unlock_irq(&ctx->inflight_lock);

/* We need to keep going until we don't find a matching req */ @@ -8619,7 +8618,7 @@ static void io_uring_cancel_files(struct /* cancellations _may_ trigger task work */ io_run_task_work(); schedule(); - finish_wait(&ctx->inflight_wait, &wait); + finish_wait(&task->io_uring->wait, &wait); } }

From: Hao Xu haoxu@linux.alibaba.com

[ Upstream commit 6195ba09822c87cad09189bbf550d0fbe714687a ]

Abaci reported the follow warning:

[ 27.073425] do not call blocking ops when !TASK_RUNNING; state=1 set at [] prepare_to_wait_exclusive+0x3a/0xc0 [ 27.075805] WARNING: CPU: 0 PID: 951 at kernel/sched/core.c:7853 __might_sleep+0x80/0xa0 [ 27.077604] Modules linked in: [ 27.078379] CPU: 0 PID: 951 Comm: a.out Not tainted 5.11.0-rc3+ #1 [ 27.079637] Hardware name: Red Hat KVM, BIOS 0.5.1 01/01/2011 [ 27.080852] RIP: 0010:__might_sleep+0x80/0xa0 [ 27.081835] Code: 65 48 8b 04 25 80 71 01 00 48 8b 90 c0 15 00 00 48 8b 70 18 48 c7 c7 08 39 95 82 c6 05 f9 5f de 08 01 48 89 d1 e8 00 c6 fa ff 0b eb bf 41 0f b6 f5 48 c7 c7 40 23 c9 82 e8 f3 48 ec 00 eb a7 [ 27.084521] RSP: 0018:ffffc90000fe3ce8 EFLAGS: 00010286 [ 27.085350] RAX: 0000000000000000 RBX: ffffffff82956083 RCX: 0000000000000000 [ 27.086348] RDX: ffff8881057a0000 RSI: ffffffff8118cc9e RDI: ffff88813bc28570 [ 27.087598] RBP: 00000000000003a7 R08: 0000000000000001 R09: 0000000000000001 [ 27.088819] R10: ffffc90000fe3e00 R11: 00000000fffef9f0 R12: 0000000000000000 [ 27.089819] R13: 0000000000000000 R14: ffff88810576eb80 R15: ffff88810576e800 [ 27.091058] FS: 00007f7b144cf740(0000) GS:ffff88813bc00000(0000) knlGS:0000000000000000 [ 27.092775] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [ 27.093796] CR2: 00000000022da7b8 CR3: 000000010b928002 CR4: 00000000003706f0 [ 27.094778] DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 [ 27.095780] DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 [ 27.097011] Call Trace: [ 27.097685] __mutex_lock+0x5d/0xa30 [ 27.098565] ? prepare_to_wait_exclusive+0x71/0xc0 [ 27.099412] ? io_cqring_overflow_flush.part.101+0x6d/0x70 [ 27.100441] ? lockdep_hardirqs_on_prepare+0xe9/0x1c0 [ 27.101537] ? _raw_spin_unlock_irqrestore+0x2d/0x40 [ 27.102656] ? trace_hardirqs_on+0x46/0x110 [ 27.103459] ? io_cqring_overflow_flush.part.101+0x6d/0x70 [ 27.104317] io_cqring_overflow_flush.part.101+0x6d/0x70 [ 27.105113] io_cqring_wait+0x36e/0x4d0 [ 27.105770] ? find_held_lock+0x28/0xb0 [ 27.106370] ? io_uring_remove_task_files+0xa0/0xa0 [ 27.107076] __x64_sys_io_uring_enter+0x4fb/0x640 [ 27.107801] ? rcu_read_lock_sched_held+0x59/0xa0 [ 27.108562] ? lockdep_hardirqs_on_prepare+0xe9/0x1c0 [ 27.109684] ? syscall_enter_from_user_mode+0x26/0x70 [ 27.110731] do_syscall_64+0x2d/0x40 [ 27.111296] entry_SYSCALL_64_after_hwframe+0x44/0xa9 [ 27.112056] RIP: 0033:0x7f7b13dc8239 [ 27.112663] Code: 01 00 48 81 c4 80 00 00 00 e9 f1 fe ff ff 0f 1f 00 48 89 f8 48 89 f7 48 89 d6 48 89 ca 4d 89 c2 4d 89 c8 4c 8b 4c 24 08 0f 05 3d 01 f0 ff ff 73 01 c3 48 8b 0d 27 ec 2c 00 f7 d8 64 89 01 48 [ 27.115113] RSP: 002b:00007ffd6d7f5c88 EFLAGS: 00000286 ORIG_RAX: 00000000000001aa [ 27.116562] RAX: ffffffffffffffda RBX: 0000000000000000 RCX: 00007f7b13dc8239 [ 27.117961] RDX: 000000000000478e RSI: 0000000000000000 RDI: 0000000000000003 [ 27.118925] RBP: 00007ffd6d7f5cb0 R08: 0000000020000040 R09: 0000000000000008 [ 27.119773] R10: 0000000000000001 R11: 0000000000000286 R12: 0000000000400480 [ 27.120614] R13: 00007ffd6d7f5d90 R14: 0000000000000000 R15: 0000000000000000 [ 27.121490] irq event stamp: 5635 [ 27.121946] hardirqs last enabled at (5643): [] console_unlock+0x5c4/0x740 [ 27.123476] hardirqs last disabled at (5652): [] console_unlock+0x4e7/0x740 [ 27.125192] softirqs last enabled at (5272): [] __do_softirq+0x3c5/0x5aa [ 27.126430] softirqs last disabled at (5267): [] asm_call_irq_on_stack+0xf/0x20 [ 27.127634] ---[ end trace 289d7e28fa60f928 ]---

This is caused by calling io_cqring_overflow_flush() which may sleep after calling prepare_to_wait_exclusive() which set task state to TASK_INTERRUPTIBLE

Reported-by: Abaci abaci@linux.alibaba.com Fixes: 6c503150ae33 ("io_uring: patch up IOPOLL overflow_flush sync") Reviewed-by: Pavel Begunkov asml.silence@gmail.com Signed-off-by: Hao Xu haoxu@linux.alibaba.com Signed-off-by: Jens Axboe axboe@kernel.dk Signed-off-by: Pavel Begunkov asml.silence@gmail.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- fs/io_uring.c | 8 ++++++-- 1 file changed, 6 insertions(+), 2 deletions(-)

--- a/fs/io_uring.c +++ b/fs/io_uring.c @@ -7000,14 +7000,18 @@ static int io_cqring_wait(struct io_ring TASK_INTERRUPTIBLE); /* make sure we run task_work before checking for signals */ ret = io_run_task_work_sig(); - if (ret > 0) + if (ret > 0) { + finish_wait(&ctx->wait, &iowq.wq); continue; + } else if (ret < 0) break; if (io_should_wake(&iowq)) break; - if (test_bit(0, &ctx->cq_check_overflow)) + if (test_bit(0, &ctx->cq_check_overflow)) { + finish_wait(&ctx->wait, &iowq.wq); continue; + } schedule(); } while (1); finish_wait(&ctx->wait, &iowq.wq);

From: Pavel Begunkov asml.silence@gmail.com

[ Upstream commit 70b2c60d3797bffe182dddb9bb55975b9be5889a ]

WARNING: CPU: 0 PID: 21359 at fs/io_uring.c:9042 io_uring_cancel_task_requests+0xe55/0x10c0 fs/io_uring.c:9042 Call Trace: io_uring_flush+0x47b/0x6e0 fs/io_uring.c:9227 filp_close+0xb4/0x170 fs/open.c:1295 close_files fs/file.c:403 [inline] put_files_struct fs/file.c:418 [inline] put_files_struct+0x1cc/0x350 fs/file.c:415 exit_files+0x7e/0xa0 fs/file.c:435 do_exit+0xc22/0x2ae0 kernel/exit.c:820 do_group_exit+0x125/0x310 kernel/exit.c:922 get_signal+0x427/0x20f0 kernel/signal.c:2773 arch_do_signal_or_restart+0x2a8/0x1eb0 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+0x148/0x250 kernel/entry/common.c:201 __syscall_exit_to_user_mode_work kernel/entry/common.c:291 [inline] syscall_exit_to_user_mode+0x19/0x50 kernel/entry/common.c:302 entry_SYSCALL_64_after_hwframe+0x44/0xa9

Now io_uring_cancel_task_requests() can be called not through file notes but directly, remove a WARN_ONCE() there that give us false positives. That check is not very important and we catch it in other places.

Fixes: 84965ff8a84f0 ("io_uring: if we see flush on exit, cancel related tasks") Cc: stable@vger.kernel.org # 5.9+ Reported-by: syzbot+3e3d9bd0c6ce9efbc3ef@syzkaller.appspotmail.com Signed-off-by: Pavel Begunkov asml.silence@gmail.com Signed-off-by: Jens Axboe axboe@kernel.dk Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- fs/io_uring.c | 2 -- 1 file changed, 2 deletions(-)

--- a/fs/io_uring.c +++ b/fs/io_uring.c @@ -8683,8 +8683,6 @@ static void io_uring_cancel_task_request struct task_struct *task = current;

if ((ctx->flags & IORING_SETUP_SQPOLL) && ctx->sq_data) { - /* for SQPOLL only sqo_task has task notes */ - WARN_ON_ONCE(ctx->sqo_task != current); io_disable_sqo_submit(ctx); task = ctx->sq_data->thread; atomic_inc(&task->io_uring->in_idle);

From: Pavel Begunkov asml.silence@gmail.com

[ Upstream commit aec18a57edad562d620f7d19016de1fc0cc2208c ]

Since SQPOLL task can be shared and so task_work entries can be a mix of them, we need to drop mm and files before trying to issue next request.

Cc: stable@vger.kernel.org # 5.10+ Signed-off-by: Pavel Begunkov asml.silence@gmail.com Signed-off-by: Jens Axboe axboe@kernel.dk Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- fs/io_uring.c | 3 +++ 1 file changed, 3 insertions(+)

--- a/fs/io_uring.c +++ b/fs/io_uring.c @@ -2084,6 +2084,9 @@ static void __io_req_task_submit(struct else __io_req_task_cancel(req, -EFAULT); mutex_unlock(&ctx->uring_lock); + + if (ctx->flags & IORING_SETUP_SQPOLL) + io_sq_thread_drop_mm(); }

static void io_req_task_submit(struct callback_head *cb)

From: Raoni Fassina Firmino raoni@linux.ibm.com

commit 24321ac668e452a4942598533d267805f291fdc9 upstream.

Commit 0138ba5783ae ("powerpc/64/signal: Balance return predictor stack in signal trampoline") changed __kernel_sigtramp_rt64() VDSO and trampoline code, and introduced a regression in the way glibc's backtrace()[1] detects the signal-handler stack frame. Apart from the practical implications, __kernel_sigtramp_rt64() was a VDSO function with the semantics that it is a function you can call from userspace to end a signal handling. Now this semantics are no longer valid.

I believe the aforementioned change affects all releases since 5.9.

This patch tries to fix both the semantics and practical aspect of __kernel_sigtramp_rt64() returning it to the previous code, whilst keeping the intended behaviour of 0138ba5783ae by adding a new symbol to serve as the jump target from the kernel to the trampoline. Now the trampoline has two parts, a new entry point and the old return point.

[1] https://lists.ozlabs.org/pipermail/linuxppc-dev/2021-January/223194.html

Fixes: 0138ba5783ae ("powerpc/64/signal: Balance return predictor stack in signal trampoline") Cc: stable@vger.kernel.org # v5.9+ Signed-off-by: Raoni Fassina Firmino raoni@linux.ibm.com Acked-by: Nicholas Piggin npiggin@gmail.com [mpe: Minor tweaks to change log formatting, add stable tag] Signed-off-by: Michael Ellerman mpe@ellerman.id.au Link: https://lore.kernel.org/r/20210201200505.iz46ubcizipnkcxe@work-tp Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org

--- arch/powerpc/kernel/vdso.c | 2 +- arch/powerpc/kernel/vdso64/sigtramp.S | 11 ++++++++++- arch/powerpc/kernel/vdso64/vdso64.lds.S | 1 + 3 files changed, 12 insertions(+), 2 deletions(-)

--- a/arch/powerpc/kernel/vdso.c +++ b/arch/powerpc/kernel/vdso.c @@ -475,7 +475,7 @@ static __init void vdso_setup_trampoline */

#ifdef CONFIG_PPC64 - vdso64_rt_sigtramp = find_function64(v64, "__kernel_sigtramp_rt64"); + vdso64_rt_sigtramp = find_function64(v64, "__kernel_start_sigtramp_rt64"); #endif vdso32_sigtramp = find_function32(v32, "__kernel_sigtramp32"); vdso32_rt_sigtramp = find_function32(v32, "__kernel_sigtramp_rt32"); --- a/arch/powerpc/kernel/vdso64/sigtramp.S +++ b/arch/powerpc/kernel/vdso64/sigtramp.S @@ -15,11 +15,20 @@

.text

+/* + * __kernel_start_sigtramp_rt64 and __kernel_sigtramp_rt64 together + * are one function split in two parts. The kernel jumps to the former + * and the signal handler indirectly (by blr) returns to the latter. + * __kernel_sigtramp_rt64 needs to point to the return address so + * glibc can correctly identify the trampoline stack frame. + */ .balign 8 .balign IFETCH_ALIGN_BYTES -V_FUNCTION_BEGIN(__kernel_sigtramp_rt64) +V_FUNCTION_BEGIN(__kernel_start_sigtramp_rt64) .Lsigrt_start: bctrl /* call the handler */ +V_FUNCTION_END(__kernel_start_sigtramp_rt64) +V_FUNCTION_BEGIN(__kernel_sigtramp_rt64) addi r1, r1, __SIGNAL_FRAMESIZE li r0,__NR_rt_sigreturn sc --- a/arch/powerpc/kernel/vdso64/vdso64.lds.S +++ b/arch/powerpc/kernel/vdso64/vdso64.lds.S @@ -150,6 +150,7 @@ VERSION __kernel_get_tbfreq; __kernel_sync_dicache; __kernel_sync_dicache_p5; + __kernel_start_sigtramp_rt64; __kernel_sigtramp_rt64; __kernel_getcpu; __kernel_time;

From: David Collins collinsd@codeaurora.org

[ Upstream commit eaa7995c529b54d68d97a30f6344cc6ca2f214a7 ]

The final step in regulator_register() is to call regulator_resolve_supply() for each registered regulator (including the one in the process of being registered). The regulator_resolve_supply() function first checks if rdev->supply is NULL, then it performs various steps to try to find the supply. If successful, rdev->supply is set inside of set_supply().

This procedure can encounter a race condition if two concurrent tasks call regulator_register() near to each other on separate CPUs and one of the regulators has rdev->supply_name specified. There is currently nothing guaranteeing atomicity between the rdev->supply check and set steps. Thus, both tasks can observe rdev->supply==NULL in their regulator_resolve_supply() calls. This then results in both creating a struct regulator for the supply. One ends up actually stored in rdev->supply and the other is lost (though still present in the supply's consumer_list).

Here is a kernel log snippet showing the issue:

[ 12.421768] gpu_cc_gx_gdsc: supplied by pm8350_s5_level [ 12.425854] gpu_cc_gx_gdsc: supplied by pm8350_s5_level [ 12.429064] debugfs: Directory 'regulator.4-SUPPLY' with parent '17a00000.rsc:rpmh-regulator-gfxlvl-pm8350_s5_level' already present!

Avoid this race condition by holding the rdev->mutex lock inside of regulator_resolve_supply() while checking and setting rdev->supply.

Signed-off-by: David Collins collinsd@codeaurora.org Link: https://lore.kernel.org/r/1610068562-4410-1-git-send-email-collinsd@codeauro... Signed-off-by: Mark Brown broonie@kernel.org Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/regulator/core.c | 39 ++++++++++++++++++++++++++++----------- 1 file changed, 28 insertions(+), 11 deletions(-)

diff --git a/drivers/regulator/core.c b/drivers/regulator/core.c index 42bbd99a36acf..2c31f04ff950f 100644 --- a/drivers/regulator/core.c +++ b/drivers/regulator/core.c @@ -1813,23 +1813,34 @@ static int regulator_resolve_supply(struct regulator_dev *rdev) { struct regulator_dev *r; struct device *dev = rdev->dev.parent; - int ret; + int ret = 0;

/* No supply to resolve? */ if (!rdev->supply_name) return 0;

- /* Supply already resolved? */ + /* Supply already resolved? (fast-path without locking contention) */ if (rdev->supply) return 0;

+ /* + * Recheck rdev->supply with rdev->mutex lock held to avoid a race + * between rdev->supply null check and setting rdev->supply in + * set_supply() from concurrent tasks. + */ + regulator_lock(rdev); + + /* Supply just resolved by a concurrent task? */ + if (rdev->supply) + goto out; + r = regulator_dev_lookup(dev, rdev->supply_name); if (IS_ERR(r)) { ret = PTR_ERR(r);

/* Did the lookup explicitly defer for us? */ if (ret == -EPROBE_DEFER) - return ret; + goto out;

if (have_full_constraints()) { r = dummy_regulator_rdev; @@ -1837,15 +1848,18 @@ static int regulator_resolve_supply(struct regulator_dev *rdev) } else { dev_err(dev, "Failed to resolve %s-supply for %s\n", rdev->supply_name, rdev->desc->name); - return -EPROBE_DEFER; + ret = -EPROBE_DEFER; + goto out; } }

if (r == rdev) { dev_err(dev, "Supply for %s (%s) resolved to itself\n", rdev->desc->name, rdev->supply_name); - if (!have_full_constraints()) - return -EINVAL; + if (!have_full_constraints()) { + ret = -EINVAL; + goto out; + } r = dummy_regulator_rdev; get_device(&r->dev); } @@ -1859,7 +1873,8 @@ static int regulator_resolve_supply(struct regulator_dev *rdev) if (r->dev.parent && r->dev.parent != rdev->dev.parent) { if (!device_is_bound(r->dev.parent)) { put_device(&r->dev); - return -EPROBE_DEFER; + ret = -EPROBE_DEFER; + goto out; } }

@@ -1867,13 +1882,13 @@ static int regulator_resolve_supply(struct regulator_dev *rdev) ret = regulator_resolve_supply(r); if (ret < 0) { put_device(&r->dev); - return ret; + goto out; }

ret = set_supply(rdev, r); if (ret < 0) { put_device(&r->dev); - return ret; + goto out; }

/* @@ -1886,11 +1901,13 @@ static int regulator_resolve_supply(struct regulator_dev *rdev) if (ret < 0) { _regulator_put(rdev->supply); rdev->supply = NULL; - return ret; + goto out; } }

- return 0; +out: + regulator_unlock(rdev); + return ret; }

/* Internal regulator request function */

From: Ben Skeggs bskeggs@redhat.com

[ Upstream commit d502297008142645edf5c791af424ed321e5da84 ]

Reported-by: Lyude Paul lyude@redhat.com Signed-off-by: Ben Skeggs bskeggs@redhat.com Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/gpu/drm/nouveau/include/nvif/push.h | 216 ++++++++++---------- 1 file changed, 108 insertions(+), 108 deletions(-)

diff --git a/drivers/gpu/drm/nouveau/include/nvif/push.h b/drivers/gpu/drm/nouveau/include/nvif/push.h index 168d7694ede5c..6d3a8a3d2087b 100644 --- a/drivers/gpu/drm/nouveau/include/nvif/push.h +++ b/drivers/gpu/drm/nouveau/include/nvif/push.h @@ -123,131 +123,131 @@ PUSH_KICK(struct nvif_push *push) } while(0) #endif

-#define PUSH_1(X,f,ds,n,c,o,p,s,mA,dA) do { \ - PUSH_##o##_HDR((p), s, mA, (c)+(n)); \ - PUSH_##f(X, (p), X##mA, 1, o, (dA), ds, ""); \ +#define PUSH_1(X,f,ds,n,o,p,s,mA,dA) do { \ + PUSH_##o##_HDR((p), s, mA, (ds)+(n)); \ + PUSH_##f(X, (p), X##mA, 1, o, (dA), ds, ""); \ } while(0) -#define PUSH_2(X,f,ds,n,c,o,p,s,mB,dB,mA,dA,a...) do { \ - PUSH_ASSERT((mB) - (mA) == (1?PUSH_##o##_INC), "mthd1"); \ - PUSH_1(X, DATA_, 1, ds, (c)+(n), o, (p), s, X##mA, (dA), ##a); \ - PUSH_##f(X, (p), X##mB, 0, o, (dB), ds, ""); \ +#define PUSH_2(X,f,ds,n,o,p,s,mB,dB,mA,dA,a...) do { \ + PUSH_ASSERT((mB) - (mA) == (1?PUSH_##o##_INC), "mthd1"); \ + PUSH_1(X, DATA_, 1, (ds) + (n), o, (p), s, X##mA, (dA), ##a); \ + PUSH_##f(X, (p), X##mB, 0, o, (dB), ds, ""); \ } while(0) -#define PUSH_3(X,f,ds,n,c,o,p,s,mB,dB,mA,dA,a...) do { \ - PUSH_ASSERT((mB) - (mA) == (0?PUSH_##o##_INC), "mthd2"); \ - PUSH_2(X, DATA_, 1, ds, (c)+(n), o, (p), s, X##mA, (dA), ##a); \ - PUSH_##f(X, (p), X##mB, 0, o, (dB), ds, ""); \ +#define PUSH_3(X,f,ds,n,o,p,s,mB,dB,mA,dA,a...) do { \ + PUSH_ASSERT((mB) - (mA) == (0?PUSH_##o##_INC), "mthd2"); \ + PUSH_2(X, DATA_, 1, (ds) + (n), o, (p), s, X##mA, (dA), ##a); \ + PUSH_##f(X, (p), X##mB, 0, o, (dB), ds, ""); \ } while(0) -#define PUSH_4(X,f,ds,n,c,o,p,s,mB,dB,mA,dA,a...) do { \ - PUSH_ASSERT((mB) - (mA) == (0?PUSH_##o##_INC), "mthd3"); \ - PUSH_3(X, DATA_, 1, ds, (c)+(n), o, (p), s, X##mA, (dA), ##a); \ - PUSH_##f(X, (p), X##mB, 0, o, (dB), ds, ""); \ +#define PUSH_4(X,f,ds,n,o,p,s,mB,dB,mA,dA,a...) do { \ + PUSH_ASSERT((mB) - (mA) == (0?PUSH_##o##_INC), "mthd3"); \ + PUSH_3(X, DATA_, 1, (ds) + (n), o, (p), s, X##mA, (dA), ##a); \ + PUSH_##f(X, (p), X##mB, 0, o, (dB), ds, ""); \ } while(0) -#define PUSH_5(X,f,ds,n,c,o,p,s,mB,dB,mA,dA,a...) do { \ - PUSH_ASSERT((mB) - (mA) == (0?PUSH_##o##_INC), "mthd4"); \ - PUSH_4(X, DATA_, 1, ds, (c)+(n), o, (p), s, X##mA, (dA), ##a); \ - PUSH_##f(X, (p), X##mB, 0, o, (dB), ds, ""); \ +#define PUSH_5(X,f,ds,n,o,p,s,mB,dB,mA,dA,a...) do { \ + PUSH_ASSERT((mB) - (mA) == (0?PUSH_##o##_INC), "mthd4"); \ + PUSH_4(X, DATA_, 1, (ds) + (n), o, (p), s, X##mA, (dA), ##a); \ + PUSH_##f(X, (p), X##mB, 0, o, (dB), ds, ""); \ } while(0) -#define PUSH_6(X,f,ds,n,c,o,p,s,mB,dB,mA,dA,a...) do { \ - PUSH_ASSERT((mB) - (mA) == (0?PUSH_##o##_INC), "mthd5"); \ - PUSH_5(X, DATA_, 1, ds, (c)+(n), o, (p), s, X##mA, (dA), ##a); \ - PUSH_##f(X, (p), X##mB, 0, o, (dB), ds, ""); \ +#define PUSH_6(X,f,ds,n,o,p,s,mB,dB,mA,dA,a...) do { \ + PUSH_ASSERT((mB) - (mA) == (0?PUSH_##o##_INC), "mthd5"); \ + PUSH_5(X, DATA_, 1, (ds) + (n), o, (p), s, X##mA, (dA), ##a); \ + PUSH_##f(X, (p), X##mB, 0, o, (dB), ds, ""); \ } while(0) -#define PUSH_7(X,f,ds,n,c,o,p,s,mB,dB,mA,dA,a...) do { \ - PUSH_ASSERT((mB) - (mA) == (0?PUSH_##o##_INC), "mthd6"); \ - PUSH_6(X, DATA_, 1, ds, (c)+(n), o, (p), s, X##mA, (dA), ##a); \ - PUSH_##f(X, (p), X##mB, 0, o, (dB), ds, ""); \ +#define PUSH_7(X,f,ds,n,o,p,s,mB,dB,mA,dA,a...) do { \ + PUSH_ASSERT((mB) - (mA) == (0?PUSH_##o##_INC), "mthd6"); \ + PUSH_6(X, DATA_, 1, (ds) + (n), o, (p), s, X##mA, (dA), ##a); \ + PUSH_##f(X, (p), X##mB, 0, o, (dB), ds, ""); \ } while(0) -#define PUSH_8(X,f,ds,n,c,o,p,s,mB,dB,mA,dA,a...) do { \ - PUSH_ASSERT((mB) - (mA) == (0?PUSH_##o##_INC), "mthd7"); \ - PUSH_7(X, DATA_, 1, ds, (c)+(n), o, (p), s, X##mA, (dA), ##a); \ - PUSH_##f(X, (p), X##mB, 0, o, (dB), ds, ""); \ +#define PUSH_8(X,f,ds,n,o,p,s,mB,dB,mA,dA,a...) do { \ + PUSH_ASSERT((mB) - (mA) == (0?PUSH_##o##_INC), "mthd7"); \ + PUSH_7(X, DATA_, 1, (ds) + (n), o, (p), s, X##mA, (dA), ##a); \ + PUSH_##f(X, (p), X##mB, 0, o, (dB), ds, ""); \ } while(0) -#define PUSH_9(X,f,ds,n,c,o,p,s,mB,dB,mA,dA,a...) do { \ - PUSH_ASSERT((mB) - (mA) == (0?PUSH_##o##_INC), "mthd8"); \ - PUSH_8(X, DATA_, 1, ds, (c)+(n), o, (p), s, X##mA, (dA), ##a); \ - PUSH_##f(X, (p), X##mB, 0, o, (dB), ds, ""); \ +#define PUSH_9(X,f,ds,n,o,p,s,mB,dB,mA,dA,a...) do { \ + PUSH_ASSERT((mB) - (mA) == (0?PUSH_##o##_INC), "mthd8"); \ + PUSH_8(X, DATA_, 1, (ds) + (n), o, (p), s, X##mA, (dA), ##a); \ + PUSH_##f(X, (p), X##mB, 0, o, (dB), ds, ""); \ } while(0) -#define PUSH_10(X,f,ds,n,c,o,p,s,mB,dB,mA,dA,a...) do { \ - PUSH_ASSERT((mB) - (mA) == (0?PUSH_##o##_INC), "mthd9"); \ - PUSH_9(X, DATA_, 1, ds, (c)+(n), o, (p), s, X##mA, (dA), ##a); \ - PUSH_##f(X, (p), X##mB, 0, o, (dB), ds, ""); \ +#define PUSH_10(X,f,ds,n,o,p,s,mB,dB,mA,dA,a...) do { \ + PUSH_ASSERT((mB) - (mA) == (0?PUSH_##o##_INC), "mthd9"); \ + PUSH_9(X, DATA_, 1, (ds) + (n), o, (p), s, X##mA, (dA), ##a); \ + PUSH_##f(X, (p), X##mB, 0, o, (dB), ds, ""); \ } while(0)

-#define PUSH_1D(X,o,p,s,mA,dA) \ - PUSH_1(X, DATA_, 1, 1, 0, o, (p), s, X##mA, (dA)) -#define PUSH_2D(X,o,p,s,mA,dA,mB,dB) \ - PUSH_2(X, DATA_, 1, 1, 0, o, (p), s, X##mB, (dB), \ - X##mA, (dA)) -#define PUSH_3D(X,o,p,s,mA,dA,mB,dB,mC,dC) \ - PUSH_3(X, DATA_, 1, 1, 0, o, (p), s, X##mC, (dC), \ - X##mB, (dB), \ - X##mA, (dA)) -#define PUSH_4D(X,o,p,s,mA,dA,mB,dB,mC,dC,mD,dD) \ - PUSH_4(X, DATA_, 1, 1, 0, o, (p), s, X##mD, (dD), \ - X##mC, (dC), \ - X##mB, (dB), \ - X##mA, (dA)) -#define PUSH_5D(X,o,p,s,mA,dA,mB,dB,mC,dC,mD,dD,mE,dE) \ - PUSH_5(X, DATA_, 1, 1, 0, o, (p), s, X##mE, (dE), \ - X##mD, (dD), \ - X##mC, (dC), \ - X##mB, (dB), \ - X##mA, (dA)) +#define PUSH_1D(X,o,p,s,mA,dA) \ + PUSH_1(X, DATA_, 1, 0, o, (p), s, X##mA, (dA)) +#define PUSH_2D(X,o,p,s,mA,dA,mB,dB) \ + PUSH_2(X, DATA_, 1, 0, o, (p), s, X##mB, (dB), \ + X##mA, (dA)) +#define PUSH_3D(X,o,p,s,mA,dA,mB,dB,mC,dC) \ + PUSH_3(X, DATA_, 1, 0, o, (p), s, X##mC, (dC), \ + X##mB, (dB), \ + X##mA, (dA)) +#define PUSH_4D(X,o,p,s,mA,dA,mB,dB,mC,dC,mD,dD) \ + PUSH_4(X, DATA_, 1, 0, o, (p), s, X##mD, (dD), \ + X##mC, (dC), \ + X##mB, (dB), \ + X##mA, (dA)) +#define PUSH_5D(X,o,p,s,mA,dA,mB,dB,mC,dC,mD,dD,mE,dE) \ + PUSH_5(X, DATA_, 1, 0, o, (p), s, X##mE, (dE), \ + X##mD, (dD), \ + X##mC, (dC), \ + X##mB, (dB), \ + X##mA, (dA)) #define PUSH_6D(X,o,p,s,mA,dA,mB,dB,mC,dC,mD,dD,mE,dE,mF,dF) \ - PUSH_6(X, DATA_, 1, 1, 0, o, (p), s, X##mF, (dF), \ - X##mE, (dE), \ - X##mD, (dD), \ - X##mC, (dC), \ - X##mB, (dB), \ - X##mA, (dA)) + PUSH_6(X, DATA_, 1, 0, o, (p), s, X##mF, (dF), \ + X##mE, (dE), \ + X##mD, (dD), \ + X##mC, (dC), \ + X##mB, (dB), \ + X##mA, (dA)) #define PUSH_7D(X,o,p,s,mA,dA,mB,dB,mC,dC,mD,dD,mE,dE,mF,dF,mG,dG) \ - PUSH_7(X, DATA_, 1, 1, 0, o, (p), s, X##mG, (dG), \ - X##mF, (dF), \ - X##mE, (dE), \ - X##mD, (dD), \ - X##mC, (dC), \ - X##mB, (dB), \ - X##mA, (dA)) + PUSH_7(X, DATA_, 1, 0, o, (p), s, X##mG, (dG), \ + X##mF, (dF), \ + X##mE, (dE), \ + X##mD, (dD), \ + X##mC, (dC), \ + X##mB, (dB), \ + X##mA, (dA)) #define PUSH_8D(X,o,p,s,mA,dA,mB,dB,mC,dC,mD,dD,mE,dE,mF,dF,mG,dG,mH,dH) \ - PUSH_8(X, DATA_, 1, 1, 0, o, (p), s, X##mH, (dH), \ - X##mG, (dG), \ - X##mF, (dF), \ - X##mE, (dE), \ - X##mD, (dD), \ - X##mC, (dC), \ - X##mB, (dB), \ - X##mA, (dA)) + PUSH_8(X, DATA_, 1, 0, o, (p), s, X##mH, (dH), \ + X##mG, (dG), \ + X##mF, (dF), \ + X##mE, (dE), \ + X##mD, (dD), \ + X##mC, (dC), \ + X##mB, (dB), \ + X##mA, (dA)) #define PUSH_9D(X,o,p,s,mA,dA,mB,dB,mC,dC,mD,dD,mE,dE,mF,dF,mG,dG,mH,dH,mI,dI) \ - PUSH_9(X, DATA_, 1, 1, 0, o, (p), s, X##mI, (dI), \ - X##mH, (dH), \ - X##mG, (dG), \ - X##mF, (dF), \ - X##mE, (dE), \ - X##mD, (dD), \ - X##mC, (dC), \ - X##mB, (dB), \ - X##mA, (dA)) + PUSH_9(X, DATA_, 1, 0, o, (p), s, X##mI, (dI), \ + X##mH, (dH), \ + X##mG, (dG), \ + X##mF, (dF), \ + X##mE, (dE), \ + X##mD, (dD), \ + X##mC, (dC), \ + X##mB, (dB), \ + X##mA, (dA)) #define PUSH_10D(X,o,p,s,mA,dA,mB,dB,mC,dC,mD,dD,mE,dE,mF,dF,mG,dG,mH,dH,mI,dI,mJ,dJ) \ - PUSH_10(X, DATA_, 1, 1, 0, o, (p), s, X##mJ, (dJ), \ - X##mI, (dI), \ - X##mH, (dH), \ - X##mG, (dG), \ - X##mF, (dF), \ - X##mE, (dE), \ - X##mD, (dD), \ - X##mC, (dC), \ - X##mB, (dB), \ - X##mA, (dA)) + PUSH_10(X, DATA_, 1, 0, o, (p), s, X##mJ, (dJ), \ + X##mI, (dI), \ + X##mH, (dH), \ + X##mG, (dG), \ + X##mF, (dF), \ + X##mE, (dE), \ + X##mD, (dD), \ + X##mC, (dC), \ + X##mB, (dB), \ + X##mA, (dA))

-#define PUSH_1P(X,o,p,s,mA,dp,ds) \ - PUSH_1(X, DATAp, ds, ds, 0, o, (p), s, X##mA, (dp)) -#define PUSH_2P(X,o,p,s,mA,dA,mB,dp,ds) \ - PUSH_2(X, DATAp, ds, ds, 0, o, (p), s, X##mB, (dp), \ - X##mA, (dA)) -#define PUSH_3P(X,o,p,s,mA,dA,mB,dB,mC,dp,ds) \ - PUSH_3(X, DATAp, ds, ds, 0, o, (p), s, X##mC, (dp), \ - X##mB, (dB), \ - X##mA, (dA)) +#define PUSH_1P(X,o,p,s,mA,dp,ds) \ + PUSH_1(X, DATAp, ds, 0, o, (p), s, X##mA, (dp)) +#define PUSH_2P(X,o,p,s,mA,dA,mB,dp,ds) \ + PUSH_2(X, DATAp, ds, 0, o, (p), s, X##mB, (dp), \ + X##mA, (dA)) +#define PUSH_3P(X,o,p,s,mA,dA,mB,dB,mC,dp,ds) \ + PUSH_3(X, DATAp, ds, 0, o, (p), s, X##mC, (dp), \ + X##mB, (dB), \ + X##mA, (dA))

#define PUSH_(A,B,C,D,E,F,G,H,I,J,K,L,M,N,O,P,Q,R,S,T,U,V,W,X,IMPL,...) IMPL #define PUSH(A...) PUSH_(A, PUSH_10P, PUSH_10D, \

From: Ricardo Ribalda ribalda@chromium.org

[ Upstream commit 1d8fe0648e118fd495a2cb393a34eb8d428e7808 ]

Clear struct snd_ctl_elem_value before calling ->put() to avoid any data leak.

Signed-off-by: Ricardo Ribalda ribalda@chromium.org Reviewed-by: Cezary Rojewski cezary.rojewski@intel.com Reviewed-by: Andy Shevchenko andriy.shevchenko@linux.intel.com Link: https://lore.kernel.org/r/20210121171644.131059-2-ribalda@chromium.org Signed-off-by: Mark Brown broonie@kernel.org Signed-off-by: Sasha Levin sashal@kernel.org --- sound/soc/intel/skylake/skl-topology.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/sound/soc/intel/skylake/skl-topology.c b/sound/soc/intel/skylake/skl-topology.c index d699e61eca3d0..0955cbb4e9187 100644 --- a/sound/soc/intel/skylake/skl-topology.c +++ b/sound/soc/intel/skylake/skl-topology.c @@ -3632,7 +3632,7 @@ static void skl_tplg_complete(struct snd_soc_component *component) sprintf(chan_text, "c%d", mach->mach_params.dmic_num);

for (i = 0; i < se->items; i++) { - struct snd_ctl_elem_value val; + struct snd_ctl_elem_value val = {};

if (strstr(texts[i], chan_text)) { val.value.enumerated.item[0] = i;

From: Trond Myklebust trond.myklebust@hammerspace.com

[ Upstream commit 08bd8dbe88825760e953759d7ec212903a026c75 ]

If the server returns a new stateid that does not match the one in our cache, then try to return the one we hold instead of just invalidating it on the client side. This ensures that both client and server will agree that the stateid is invalid.

Signed-off-by: Trond Myklebust trond.myklebust@hammerspace.com Signed-off-by: Sasha Levin sashal@kernel.org --- fs/nfs/pnfs.c | 8 +++++++- 1 file changed, 7 insertions(+), 1 deletion(-)

diff --git a/fs/nfs/pnfs.c b/fs/nfs/pnfs.c index cbadcf6ca4da2..2b98286376d40 100644 --- a/fs/nfs/pnfs.c +++ b/fs/nfs/pnfs.c @@ -2402,7 +2402,13 @@ pnfs_layout_process(struct nfs4_layoutget *lgp) * We got an entirely new state ID. Mark all segments for the * inode invalid, and retry the layoutget */ - pnfs_mark_layout_stateid_invalid(lo, &free_me); + struct pnfs_layout_range range = { + .iomode = IOMODE_ANY, + .length = NFS4_MAX_UINT64, + }; + pnfs_set_plh_return_info(lo, IOMODE_ANY, 0); + pnfs_mark_matching_lsegs_return(lo, &lo->plh_return_segs, + &range, 0); goto out_forget; }

From: Bard Liao bard.liao@intel.com

[ Upstream commit c5b5ff607d6fe5f4284acabd07066f96ecf96ac4 ]

Adding PCI id for TGL-H. Like for other TGL platforms, SOF is used if Soundwire codecs or PCH-DMIC is detected.

Signed-off-by: Bard Liao bard.liao@intel.com Reviewed-by: Xiuli Pan xiuli.pan@intel.com Reviewed-by: Libin Yang libin.yang@intel.com Signed-off-by: Kai Vehmanen kai.vehmanen@linux.intel.com Link: https://lore.kernel.org/r/20210125083051.828205-1-kai.vehmanen@linux.intel.c... Signed-off-by: Takashi Iwai tiwai@suse.de Signed-off-by: Sasha Levin sashal@kernel.org --- sound/hda/intel-dsp-config.c | 4 ++++ 1 file changed, 4 insertions(+)

diff --git a/sound/hda/intel-dsp-config.c b/sound/hda/intel-dsp-config.c index 1c5114dedda92..fe49e9a97f0ec 100644 --- a/sound/hda/intel-dsp-config.c +++ b/sound/hda/intel-dsp-config.c @@ -306,6 +306,10 @@ static const struct config_entry config_table[] = { .flags = FLAG_SOF | FLAG_SOF_ONLY_IF_DMIC_OR_SOUNDWIRE, .device = 0xa0c8, }, + { + .flags = FLAG_SOF | FLAG_SOF_ONLY_IF_DMIC_OR_SOUNDWIRE, + .device = 0x43c8, + }, #endif

/* Elkhart Lake */

From: Libin Yang libin.yang@intel.com

[ Upstream commit 9ad9bc59dde106e56dd59ce2bec7c1b08e1f0eb4 ]

Add flag "SOF_RT711_JD_SRC_JD2", flag "SOF_RT715_DAI_ID_FIX" and "SOF_SDW_FOUR_SPK" to the Dell TGL-H based SKU "0A5E".

Signed-off-by: Libin Yang libin.yang@intel.com Co-developed-by: Hui Wang hui.wang@canonical.com Signed-off-by: Hui Wang hui.wang@canonical.com Reviewed-by: Bard Liao bard.liao@intel.com Reviewed-by: Pierre-Louis Bossart pierre-louis.bossart@linux.intel.com Signed-off-by: Kai Vehmanen kai.vehmanen@linux.intel.com Link: https://lore.kernel.org/r/20210125081117.814488-1-kai.vehmanen@linux.intel.c... Signed-off-by: Mark Brown broonie@kernel.org Signed-off-by: Sasha Levin sashal@kernel.org --- sound/soc/intel/boards/sof_sdw.c | 10 ++++++++++ 1 file changed, 10 insertions(+)

diff --git a/sound/soc/intel/boards/sof_sdw.c b/sound/soc/intel/boards/sof_sdw.c index b29946eb43551..a8d43c87cb5a2 100644 --- a/sound/soc/intel/boards/sof_sdw.c +++ b/sound/soc/intel/boards/sof_sdw.c @@ -57,6 +57,16 @@ static const struct dmi_system_id sof_sdw_quirk_table[] = { .driver_data = (void *)(SOF_RT711_JD_SRC_JD2 | SOF_RT715_DAI_ID_FIX), }, + { + .callback = sof_sdw_quirk_cb, + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc"), + DMI_EXACT_MATCH(DMI_PRODUCT_SKU, "0A5E") + }, + .driver_data = (void *)(SOF_RT711_JD_SRC_JD2 | + SOF_RT715_DAI_ID_FIX | + SOF_SDW_FOUR_SPK), + }, { .callback = sof_sdw_quirk_cb, .matches = {

From: Johannes Berg johannes.berg@intel.com

[ Upstream commit 5c56d862c749669d45c256f581eac4244be00d4d ]

We need to take the mutex to call iwl_mvm_get_sync_time(), do it.

Signed-off-by: Johannes Berg johannes.berg@intel.com Signed-off-by: Luca Coelho luciano.coelho@intel.com Signed-off-by: Kalle Valo kvalo@codeaurora.org Link: https://lore.kernel.org/r/iwlwifi.20210115130252.4bb5ccf881a6.I62973cbb081e8... Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/net/wireless/intel/iwlwifi/mvm/debugfs-vif.c | 3 +++ 1 file changed, 3 insertions(+)

diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/debugfs-vif.c b/drivers/net/wireless/intel/iwlwifi/mvm/debugfs-vif.c index f043eefabb4ec..7b1d2dac6ceb8 100644 --- a/drivers/net/wireless/intel/iwlwifi/mvm/debugfs-vif.c +++ b/drivers/net/wireless/intel/iwlwifi/mvm/debugfs-vif.c @@ -514,7 +514,10 @@ static ssize_t iwl_dbgfs_os_device_timediff_read(struct file *file, const size_t bufsz = sizeof(buf); int pos = 0;

+ mutex_lock(&mvm->mutex); iwl_mvm_get_sync_time(mvm, &curr_gp2, &curr_os); + mutex_unlock(&mvm->mutex); + do_div(curr_os, NSEC_PER_USEC); diff = curr_os - curr_gp2; pos += scnprintf(buf + pos, bufsz - pos, "diff=%lld\n", diff);

From: Johannes Berg johannes.berg@intel.com

[ Upstream commit 2d6bc752cc2806366d9a4fd577b3f6c1f7a7e04e ]

If the image loader allocation fails, we leak all the previously allocated memory. Fix this.

Signed-off-by: Johannes Berg johannes.berg@intel.com Signed-off-by: Luca Coelho luciano.coelho@intel.com Signed-off-by: Kalle Valo kvalo@codeaurora.org Link: https://lore.kernel.org/r/iwlwifi.20210115130252.97172cbaa67c.I3473233d0ad01... Signed-off-by: Sasha Levin sashal@kernel.org --- .../net/wireless/intel/iwlwifi/pcie/ctxt-info-gen3.c | 11 +++++++++-- 1 file changed, 9 insertions(+), 2 deletions(-)

diff --git a/drivers/net/wireless/intel/iwlwifi/pcie/ctxt-info-gen3.c b/drivers/net/wireless/intel/iwlwifi/pcie/ctxt-info-gen3.c index d719e433a59bf..2d43899fbdd7a 100644 --- a/drivers/net/wireless/intel/iwlwifi/pcie/ctxt-info-gen3.c +++ b/drivers/net/wireless/intel/iwlwifi/pcie/ctxt-info-gen3.c @@ -245,8 +245,10 @@ int iwl_pcie_ctxt_info_gen3_init(struct iwl_trans *trans, /* Allocate IML */ iml_img = dma_alloc_coherent(trans->dev, trans->iml_len, &trans_pcie->iml_dma_addr, GFP_KERNEL); - if (!iml_img) - return -ENOMEM; + if (!iml_img) { + ret = -ENOMEM; + goto err_free_ctxt_info; + }

memcpy(iml_img, trans->iml, trans->iml_len);

@@ -284,6 +286,11 @@ int iwl_pcie_ctxt_info_gen3_init(struct iwl_trans *trans,

return 0;

+err_free_ctxt_info: + dma_free_coherent(trans->dev, sizeof(*trans_pcie->ctxt_info_gen3), + trans_pcie->ctxt_info_gen3, + trans_pcie->ctxt_info_dma_addr); + trans_pcie->ctxt_info_gen3 = NULL; err_free_prph_info: dma_free_coherent(trans->dev, sizeof(*prph_info),

From: Luca Coelho luciano.coelho@intel.com

[ Upstream commit 16062c12edb8ed2dfb15e6a914ff4edf858ab9e0 ]

Until now we have been relying on matching the PCI ID and subsystem device ID in order to recognize Qu devices with Hr2. Add rules to match these devices, so that we don't have to add a new rule for every new ID we get.

Signed-off-by: Luca Coelho luciano.coelho@intel.com Signed-off-by: Kalle Valo kvalo@codeaurora.org Link: https://lore.kernel.org/r/iwlwifi.20210122144849.591ce253ddd8.Ia4b9cc2c53562... Signed-off-by: Sasha Levin sashal@kernel.org --- .../net/wireless/intel/iwlwifi/cfg/22000.c | 25 +++++++++++++++++++ .../net/wireless/intel/iwlwifi/iwl-config.h | 3 +++ drivers/net/wireless/intel/iwlwifi/pcie/drv.c | 10 ++++++++ 3 files changed, 38 insertions(+)

diff --git a/drivers/net/wireless/intel/iwlwifi/cfg/22000.c b/drivers/net/wireless/intel/iwlwifi/cfg/22000.c index d2bbe6a735142..92c50efd48fc3 100644 --- a/drivers/net/wireless/intel/iwlwifi/cfg/22000.c +++ b/drivers/net/wireless/intel/iwlwifi/cfg/22000.c @@ -358,6 +358,7 @@ const struct iwl_cfg_trans_params iwl_ma_trans_cfg = { const char iwl_ax101_name[] = "Intel(R) Wi-Fi 6 AX101"; const char iwl_ax200_name[] = "Intel(R) Wi-Fi 6 AX200 160MHz"; const char iwl_ax201_name[] = "Intel(R) Wi-Fi 6 AX201 160MHz"; +const char iwl_ax203_name[] = "Intel(R) Wi-Fi 6 AX203"; const char iwl_ax211_name[] = "Intel(R) Wi-Fi 6 AX211 160MHz"; const char iwl_ax411_name[] = "Intel(R) Wi-Fi 6 AX411 160MHz"; const char iwl_ma_name[] = "Intel(R) Wi-Fi 6"; @@ -384,6 +385,18 @@ const struct iwl_cfg iwl_qu_b0_hr1_b0 = { .num_rbds = IWL_NUM_RBDS_22000_HE, };

+const struct iwl_cfg iwl_qu_b0_hr_b0 = { + .fw_name_pre = IWL_QU_B_HR_B_FW_PRE, + IWL_DEVICE_22500, + /* + * This device doesn't support receiving BlockAck with a large bitmap + * so we need to restrict the size of transmitted aggregation to the + * HT size; mac80211 would otherwise pick the HE max (256) by default. + */ + .max_tx_agg_size = IEEE80211_MAX_AMPDU_BUF_HT, + .num_rbds = IWL_NUM_RBDS_22000_HE, +}; + const struct iwl_cfg iwl_ax201_cfg_qu_hr = { .name = "Intel(R) Wi-Fi 6 AX201 160MHz", .fw_name_pre = IWL_QU_B_HR_B_FW_PRE, @@ -410,6 +423,18 @@ const struct iwl_cfg iwl_qu_c0_hr1_b0 = { .num_rbds = IWL_NUM_RBDS_22000_HE, };

+const struct iwl_cfg iwl_qu_c0_hr_b0 = { + .fw_name_pre = IWL_QU_C_HR_B_FW_PRE, + IWL_DEVICE_22500, + /* + * This device doesn't support receiving BlockAck with a large bitmap + * so we need to restrict the size of transmitted aggregation to the + * HT size; mac80211 would otherwise pick the HE max (256) by default. + */ + .max_tx_agg_size = IEEE80211_MAX_AMPDU_BUF_HT, + .num_rbds = IWL_NUM_RBDS_22000_HE, +}; + const struct iwl_cfg iwl_ax201_cfg_qu_c0_hr_b0 = { .name = "Intel(R) Wi-Fi 6 AX201 160MHz", .fw_name_pre = IWL_QU_C_HR_B_FW_PRE, diff --git a/drivers/net/wireless/intel/iwlwifi/iwl-config.h b/drivers/net/wireless/intel/iwlwifi/iwl-config.h index e82e3fc963be2..9b91aa9b2e7f1 100644 --- a/drivers/net/wireless/intel/iwlwifi/iwl-config.h +++ b/drivers/net/wireless/intel/iwlwifi/iwl-config.h @@ -544,6 +544,7 @@ extern const char iwl9260_killer_1550_name[]; extern const char iwl9560_killer_1550i_name[]; extern const char iwl9560_killer_1550s_name[]; extern const char iwl_ax200_name[]; +extern const char iwl_ax203_name[]; extern const char iwl_ax201_name[]; extern const char iwl_ax101_name[]; extern const char iwl_ax200_killer_1650w_name[]; @@ -627,6 +628,8 @@ extern const struct iwl_cfg iwl9560_2ac_cfg_soc; extern const struct iwl_cfg iwl_qu_b0_hr1_b0; extern const struct iwl_cfg iwl_qu_c0_hr1_b0; extern const struct iwl_cfg iwl_quz_a0_hr1_b0; +extern const struct iwl_cfg iwl_qu_b0_hr_b0; +extern const struct iwl_cfg iwl_qu_c0_hr_b0; extern const struct iwl_cfg iwl_ax200_cfg_cc; extern const struct iwl_cfg iwl_ax201_cfg_qu_hr; extern const struct iwl_cfg iwl_ax201_cfg_qu_hr; diff --git a/drivers/net/wireless/intel/iwlwifi/pcie/drv.c b/drivers/net/wireless/intel/iwlwifi/pcie/drv.c index 7b5ece380fbfb..2823a1e81656d 100644 --- a/drivers/net/wireless/intel/iwlwifi/pcie/drv.c +++ b/drivers/net/wireless/intel/iwlwifi/pcie/drv.c @@ -966,6 +966,11 @@ static const struct iwl_dev_info iwl_dev_info_table[] = { IWL_CFG_RF_TYPE_HR1, IWL_CFG_ANY, IWL_CFG_ANY, IWL_CFG_ANY, iwl_qu_b0_hr1_b0, iwl_ax101_name), + _IWL_DEV_INFO(IWL_CFG_ANY, IWL_CFG_ANY, + IWL_CFG_MAC_TYPE_QU, SILICON_C_STEP, + IWL_CFG_RF_TYPE_HR2, IWL_CFG_ANY, + IWL_CFG_ANY, IWL_CFG_ANY, + iwl_qu_b0_hr_b0, iwl_ax203_name),

/* Qu C step */ _IWL_DEV_INFO(IWL_CFG_ANY, IWL_CFG_ANY, @@ -973,6 +978,11 @@ static const struct iwl_dev_info iwl_dev_info_table[] = { IWL_CFG_RF_TYPE_HR1, IWL_CFG_ANY, IWL_CFG_ANY, IWL_CFG_ANY, iwl_qu_c0_hr1_b0, iwl_ax101_name), + _IWL_DEV_INFO(IWL_CFG_ANY, IWL_CFG_ANY, + IWL_CFG_MAC_TYPE_QU, SILICON_C_STEP, + IWL_CFG_RF_TYPE_HR2, IWL_CFG_ANY, + IWL_CFG_ANY, IWL_CFG_ANY, + iwl_qu_c0_hr_b0, iwl_ax203_name),

/* QuZ */ _IWL_DEV_INFO(IWL_CFG_ANY, IWL_CFG_ANY,

From: Johannes Berg johannes.berg@intel.com

[ Upstream commit 0bed6a2a14afaae240cc431e49c260568488b51c ]

If we find an entry without an SKB, we currently continue, but that will just result in an infinite loop since we won't increment the read pointer, and will try the same thing over and over again. Fix this.

Signed-off-by: Johannes Berg johannes.berg@intel.com Signed-off-by: Luca Coelho luciano.coelho@intel.com Signed-off-by: Kalle Valo kvalo@codeaurora.org Link: https://lore.kernel.org/r/iwlwifi.20210122144849.abe2dedcc3ac.Ia6b03f9eeb617... Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/net/wireless/intel/iwlwifi/queue/tx.c | 6 ++---- 1 file changed, 2 insertions(+), 4 deletions(-)

diff --git a/drivers/net/wireless/intel/iwlwifi/queue/tx.c b/drivers/net/wireless/intel/iwlwifi/queue/tx.c index af0b27a68d84d..9181221a2434d 100644 --- a/drivers/net/wireless/intel/iwlwifi/queue/tx.c +++ b/drivers/net/wireless/intel/iwlwifi/queue/tx.c @@ -887,10 +887,8 @@ void iwl_txq_gen2_unmap(struct iwl_trans *trans, int txq_id) int idx = iwl_txq_get_cmd_index(txq, txq->read_ptr); struct sk_buff *skb = txq->entries[idx].skb;

- if (WARN_ON_ONCE(!skb)) - continue; - - iwl_txq_free_tso_page(trans, skb); + if (!WARN_ON_ONCE(!skb)) + iwl_txq_free_tso_page(trans, skb); } iwl_txq_gen2_free_tfd(trans, txq); txq->read_ptr = iwl_txq_inc_wrap(trans, txq->read_ptr);

From: Dave Wysochanski dwysocha@redhat.com

[ Upstream commit e4a7d1f7707eb44fd953a31dd59eff82009d879c ]

When handling an auth_gss downcall, it's possible to get 0-length opaque object for the acceptor. In the case of a 0-length XDR object, make sure simple_get_netobj() fills in dest->data = NULL, and does not continue to kmemdup() which will set dest->data = ZERO_SIZE_PTR for the acceptor.

The trace event code can handle NULL but not ZERO_SIZE_PTR for a string, and so without this patch the rpcgss_context trace event will crash the kernel as follows:

[ 162.887992] BUG: kernel NULL pointer dereference, address: 0000000000000010 [ 162.898693] #PF: supervisor read access in kernel mode [ 162.900830] #PF: error_code(0x0000) - not-present page [ 162.902940] PGD 0 P4D 0 [ 162.904027] Oops: 0000 [#1] SMP PTI [ 162.905493] CPU: 4 PID: 4321 Comm: rpc.gssd Kdump: loaded Not tainted 5.10.0 #133 [ 162.908548] Hardware name: Red Hat KVM, BIOS 0.5.1 01/01/2011 [ 162.910978] RIP: 0010:strlen+0x0/0x20 [ 162.912505] Code: 48 89 f9 74 09 48 83 c1 01 80 39 00 75 f7 31 d2 44 0f b6 04 16 44 88 04 11 48 83 c2 01 45 84 c0 75 ee c3 0f 1f 80 00 00 00 00 <80> 3f 00 74 10 48 89 f8 48 83 c0 01 80 38 00 75 f7 48 29 f8 c3 31 [ 162.920101] RSP: 0018:ffffaec900c77d90 EFLAGS: 00010202 [ 162.922263] RAX: 0000000000000000 RBX: 0000000000000000 RCX: 00000000fffde697 [ 162.925158] RDX: 000000000000002f RSI: 0000000000000080 RDI: 0000000000000010 [ 162.928073] RBP: 0000000000000010 R08: 0000000000000e10 R09: 0000000000000000 [ 162.930976] R10: ffff8e698a590cb8 R11: 0000000000000001 R12: 0000000000000e10 [ 162.933883] R13: 00000000fffde697 R14: 000000010034d517 R15: 0000000000070028 [ 162.936777] FS: 00007f1e1eb93700(0000) GS:ffff8e6ab7d00000(0000) knlGS:0000000000000000 [ 162.940067] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [ 162.942417] CR2: 0000000000000010 CR3: 0000000104eba000 CR4: 00000000000406e0 [ 162.945300] Call Trace: [ 162.946428] trace_event_raw_event_rpcgss_context+0x84/0x140 [auth_rpcgss] [ 162.949308] ? __kmalloc_track_caller+0x35/0x5a0 [ 162.951224] ? gss_pipe_downcall+0x3a3/0x6a0 [auth_rpcgss] [ 162.953484] gss_pipe_downcall+0x585/0x6a0 [auth_rpcgss] [ 162.955953] rpc_pipe_write+0x58/0x70 [sunrpc] [ 162.957849] vfs_write+0xcb/0x2c0 [ 162.959264] ksys_write+0x68/0xe0 [ 162.960706] do_syscall_64+0x33/0x40 [ 162.962238] entry_SYSCALL_64_after_hwframe+0x44/0xa9 [ 162.964346] RIP: 0033:0x7f1e1f1e57df

Signed-off-by: Dave Wysochanski dwysocha@redhat.com Signed-off-by: Trond Myklebust trond.myklebust@hammerspace.com Signed-off-by: Sasha Levin sashal@kernel.org --- net/sunrpc/auth_gss/auth_gss_internal.h | 9 ++++++--- 1 file changed, 6 insertions(+), 3 deletions(-)

diff --git a/net/sunrpc/auth_gss/auth_gss_internal.h b/net/sunrpc/auth_gss/auth_gss_internal.h index c5603242b54bf..f6d9631bd9d00 100644 --- a/net/sunrpc/auth_gss/auth_gss_internal.h +++ b/net/sunrpc/auth_gss/auth_gss_internal.h @@ -34,9 +34,12 @@ simple_get_netobj(const void *p, const void *end, struct xdr_netobj *dest) q = (const void *)((const char *)p + len); if (unlikely(q > end || q < p)) return ERR_PTR(-EFAULT); - dest->data = kmemdup(p, len, GFP_NOFS); - if (unlikely(dest->data == NULL)) - return ERR_PTR(-ENOMEM); + if (len) { + dest->data = kmemdup(p, len, GFP_NOFS); + if (unlikely(dest->data == NULL)) + return ERR_PTR(-ENOMEM); + } else + dest->data = NULL; dest->len = len; return q; }

From: Baolin Wang baolin.wang@linux.alibaba.com

[ Upstream commit 6c635caef410aa757befbd8857c1eadde5cc22ed ]

On !PREEMPT kernel, we can get below softlockup when doing stress testing with creating and destroying block cgroup repeatly. The reason is it may take a long time to acquire the queue's lock in the loop of blkcg_destroy_blkgs(), or the system can accumulate a huge number of blkgs in pathological cases. We can add a need_resched() check on each loop and release locks and do cond_resched() if true to avoid this issue, since the blkcg_destroy_blkgs() is not called from atomic contexts.

[ 4757.010308] watchdog: BUG: soft lockup - CPU#11 stuck for 94s! [ 4757.010698] Call trace: [ 4757.010700]  blkcg_destroy_blkgs+0x68/0x150 [ 4757.010701]  cgwb_release_workfn+0x104/0x158 [ 4757.010702]  process_one_work+0x1bc/0x3f0 [ 4757.010704]  worker_thread+0x164/0x468 [ 4757.010705]  kthread+0x108/0x138

Suggested-by: Tejun Heo tj@kernel.org Signed-off-by: Baolin Wang baolin.wang@linux.alibaba.com Signed-off-by: Jens Axboe axboe@kernel.dk Signed-off-by: Sasha Levin sashal@kernel.org --- block/blk-cgroup.c | 18 +++++++++++++----- 1 file changed, 13 insertions(+), 5 deletions(-)

diff --git a/block/blk-cgroup.c b/block/blk-cgroup.c index 54fbe1e80cc41..f13688c4b9317 100644 --- a/block/blk-cgroup.c +++ b/block/blk-cgroup.c @@ -1017,6 +1017,8 @@ static void blkcg_css_offline(struct cgroup_subsys_state *css) */ void blkcg_destroy_blkgs(struct blkcg *blkcg) { + might_sleep(); + spin_lock_irq(&blkcg->lock);

while (!hlist_empty(&blkcg->blkg_list)) { @@ -1024,14 +1026,20 @@ void blkcg_destroy_blkgs(struct blkcg *blkcg) struct blkcg_gq, blkcg_node); struct request_queue *q = blkg->q;

- if (spin_trylock(&q->queue_lock)) { - blkg_destroy(blkg); - spin_unlock(&q->queue_lock); - } else { + if (need_resched() || !spin_trylock(&q->queue_lock)) { + /* + * Given that the system can accumulate a huge number + * of blkgs in pathological cases, check to see if we + * need to rescheduling to avoid softlockup. + */ spin_unlock_irq(&blkcg->lock); - cpu_relax(); + cond_resched(); spin_lock_irq(&blkcg->lock); + continue; } + + blkg_destroy(blkg); + spin_unlock(&q->queue_lock); }

spin_unlock_irq(&blkcg->lock);

From: Daniel Borkmann daniel@iogearbox.net

commit fd675184fc7abfd1e1c52d23e8e900676b5a1c1a upstream.

Anatoly has been fuzzing with kBdysch harness and reported a hang in one of the outcomes:

func#0 @0 0: R1=ctx(id=0,off=0,imm=0) R10=fp0 0: (b7) r0 = 808464450 1: R0_w=invP808464450 R1=ctx(id=0,off=0,imm=0) R10=fp0 1: (b4) w4 = 808464432 2: R0_w=invP808464450 R1=ctx(id=0,off=0,imm=0) R4_w=invP808464432 R10=fp0 2: (9c) w4 %= w0 3: R0_w=invP808464450 R1=ctx(id=0,off=0,imm=0) R4_w=invP(id=0,umax_value=4294967295,var_off=(0x0; 0xffffffff)) R10=fp0 3: (66) if w4 s> 0x30303030 goto pc+0 R0_w=invP808464450 R1=ctx(id=0,off=0,imm=0) R4_w=invP(id=0,umax_value=4294967295,var_off=(0x0; 0xffffffff),s32_max_value=808464432) R10=fp0 4: R0_w=invP808464450 R1=ctx(id=0,off=0,imm=0) R4_w=invP(id=0,umax_value=4294967295,var_off=(0x0; 0xffffffff),s32_max_value=808464432) R10=fp0 4: (7f) r0 >>= r0 5: R0_w=invP(id=0) R1=ctx(id=0,off=0,imm=0) R4_w=invP(id=0,umax_value=4294967295,var_off=(0x0; 0xffffffff),s32_max_value=808464432) R10=fp0 5: (9c) w4 %= w0 6: R0_w=invP(id=0) R1=ctx(id=0,off=0,imm=0) R4_w=invP(id=0) R10=fp0 6: (66) if w0 s> 0x3030 goto pc+0 R0_w=invP(id=0,s32_max_value=12336) R1=ctx(id=0,off=0,imm=0) R4_w=invP(id=0) R10=fp0 7: R0=invP(id=0,s32_max_value=12336) R1=ctx(id=0,off=0,imm=0) R4=invP(id=0) R10=fp0 7: (d6) if w0 s<= 0x303030 goto pc+1 9: R0=invP(id=0,s32_max_value=12336) R1=ctx(id=0,off=0,imm=0) R4=invP(id=0) R10=fp0 9: (95) exit propagating r0

from 6 to 7: safe 4: R0_w=invP808464450 R1=ctx(id=0,off=0,imm=0) R4_w=invP(id=0,umin_value=808464433,umax_value=2147483647,var_off=(0x0; 0x7fffffff)) R10=fp0 4: (7f) r0 >>= r0 5: R0_w=invP(id=0) R1=ctx(id=0,off=0,imm=0) R4_w=invP(id=0,umin_value=808464433,umax_value=2147483647,var_off=(0x0; 0x7fffffff)) R10=fp0 5: (9c) w4 %= w0 6: R0_w=invP(id=0) R1=ctx(id=0,off=0,imm=0) R4_w=invP(id=0) R10=fp0 6: (66) if w0 s> 0x3030 goto pc+0 R0_w=invP(id=0,s32_max_value=12336) R1=ctx(id=0,off=0,imm=0) R4_w=invP(id=0) R10=fp0 propagating r0 7: safe propagating r0

from 6 to 7: safe processed 15 insns (limit 1000000) max_states_per_insn 0 total_states 1 peak_states 1 mark_read 1

The underlying program was xlated as follows:

# bpftool p d x i 10 0: (b7) r0 = 808464450 1: (b4) w4 = 808464432 2: (bc) w0 = w0 3: (15) if r0 == 0x0 goto pc+1 4: (9c) w4 %= w0 5: (66) if w4 s> 0x30303030 goto pc+0 6: (7f) r0 >>= r0 7: (bc) w0 = w0 8: (15) if r0 == 0x0 goto pc+1 9: (9c) w4 %= w0 10: (66) if w0 s> 0x3030 goto pc+0 11: (d6) if w0 s<= 0x303030 goto pc+1 12: (05) goto pc-1 13: (95) exit

The verifier rewrote original instructions it recognized as dead code with 'goto pc-1', but reality differs from verifier simulation in that we are actually able to trigger a hang due to hitting the 'goto pc-1' instructions.

Taking a closer look at the verifier analysis, the reason is that it misjudges its pruning decision at the first 'from 6 to 7: safe' occasion. What happens is that while both old/cur registers are marked as precise, they get misjudged for the jmp32 case as range_within() yields true, meaning that the prior verification path with a wider register bound could be verified successfully and therefore the current path with a narrower register bound is deemed safe as well whereas in reality it's not. R0 old/cur path's bounds compare as follows:

old: smin_value=0x8000000000000000,smax_value=0x7fffffffffffffff,umin_value=0x0,umax_value=0xffffffffffffffff,var_off=(0x0; 0xffffffffffffffff) cur: smin_value=0x8000000000000000,smax_value=0x7fffffff7fffffff,umin_value=0x0,umax_value=0xffffffff7fffffff,var_off=(0x0; 0xffffffff7fffffff)

old: s32_min_value=0x80000000,s32_max_value=0x00003030,u32_min_value=0x00000000,u32_max_value=0xffffffff cur: s32_min_value=0x00003031,s32_max_value=0x7fffffff,u32_min_value=0x00003031,u32_max_value=0x7fffffff

The 64 bit bounds generally look okay and while the information that got propagated from 32 to 64 bit looks correct as well, it's not precise enough for judging a conditional jmp32. Given the latter only operates on subregisters we also need to take these into account as well for a range_within() probe in order to be able to prune paths. Extending the range_within() constraint to both bounds will be able to tell us that the old signed 32 bit bounds are not wider than the cur signed 32 bit bounds.

With the fix in place, the program will now verify the 'goto' branch case as it should have been:

[...] 6: R0_w=invP(id=0) R1=ctx(id=0,off=0,imm=0) R4_w=invP(id=0) R10=fp0 6: (66) if w0 s> 0x3030 goto pc+0 R0_w=invP(id=0,s32_max_value=12336) R1=ctx(id=0,off=0,imm=0) R4_w=invP(id=0) R10=fp0 7: R0=invP(id=0,s32_max_value=12336) R1=ctx(id=0,off=0,imm=0) R4=invP(id=0) R10=fp0 7: (d6) if w0 s<= 0x303030 goto pc+1 9: R0=invP(id=0,s32_max_value=12336) R1=ctx(id=0,off=0,imm=0) R4=invP(id=0) R10=fp0 9: (95) exit

7: R0_w=invP(id=0,smax_value=9223372034707292159,umax_value=18446744071562067967,var_off=(0x0; 0xffffffff7fffffff),s32_min_value=12337,u32_min_value=12337,u32_max_value=2147483647) R1=ctx(id=0,off=0,imm=0) R4_w=invP(id=0) R10=fp0 7: (d6) if w0 s<= 0x303030 goto pc+1 R0_w=invP(id=0,smax_value=9223372034707292159,umax_value=18446744071562067967,var_off=(0x0; 0xffffffff7fffffff),s32_min_value=3158065,u32_min_value=3158065,u32_max_value=2147483647) R1=ctx(id=0,off=0,imm=0) R4_w=invP(id=0) R10=fp0 8: R0_w=invP(id=0,smax_value=9223372034707292159,umax_value=18446744071562067967,var_off=(0x0; 0xffffffff7fffffff),s32_min_value=3158065,u32_min_value=3158065,u32_max_value=2147483647) R1=ctx(id=0,off=0,imm=0) R4_w=invP(id=0) R10=fp0 8: (30) r0 = *(u8 *)skb[808464432] BPF_LD_[ABS|IND] uses reserved fields processed 11 insns (limit 1000000) max_states_per_insn 1 total_states 1 peak_states 1 mark_read 1

The bug is quite subtle in the sense that when verifier would determine that a given branch is dead code, it would (here: wrongly) remove these instructions from the program and hard-wire the taken branch for privileged programs instead of the 'goto pc-1' rewrites which will cause hard to debug problems.

Fixes: 3f50f132d840 ("bpf: Verifier, do explicit ALU32 bounds tracking") Reported-by: Anatoly Trosinenko anatoly.trosinenko@gmail.com Signed-off-by: Daniel Borkmann daniel@iogearbox.net Reviewed-by: John Fastabend john.fastabend@gmail.com Acked-by: Alexei Starovoitov ast@kernel.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- kernel/bpf/verifier.c | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-)

--- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -8465,7 +8465,11 @@ static bool range_within(struct bpf_reg_ return old->umin_value <= cur->umin_value && old->umax_value >= cur->umax_value && old->smin_value <= cur->smin_value && - old->smax_value >= cur->smax_value; + old->smax_value >= cur->smax_value && + old->u32_min_value <= cur->u32_min_value && + old->u32_max_value >= cur->u32_max_value && + old->s32_min_value <= cur->s32_min_value && + old->s32_max_value >= cur->s32_max_value; }

/* Maximum number of register states that can exist at once */

From: Daniel Borkmann daniel@iogearbox.net

commit ee114dd64c0071500345439fc79dd5e0f9d106ed upstream.

Fix incorrect is_branch{32,64}_taken() analysis for the jsgt case. The return code for both will tell the caller whether a given conditional jump is taken or not, e.g. 1 means branch will be taken [for the involved registers] and the goto target will be executed, 0 means branch will not be taken and instead we fall-through to the next insn, and last but not least a -1 denotes that it is not known at verification time whether a branch will be taken or not. Now while the jsgt has the branch-taken case correct with reg->s32_min_value > sval, the branch-not-taken case is off-by-one when testing for reg->s32_max_value < sval since the branch will also be taken for reg->s32_max_value == sval. The jgt branch analysis, for example, gets this right.

Fixes: 3f50f132d840 ("bpf: Verifier, do explicit ALU32 bounds tracking") Fixes: 4f7b3e82589e ("bpf: improve verifier branch analysis") Signed-off-by: Daniel Borkmann daniel@iogearbox.net Reviewed-by: John Fastabend john.fastabend@gmail.com Acked-by: Alexei Starovoitov ast@kernel.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- kernel/bpf/verifier.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-)

--- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -6822,7 +6822,7 @@ static int is_branch32_taken(struct bpf_ case BPF_JSGT: if (reg->s32_min_value > sval) return 1; - else if (reg->s32_max_value < sval) + else if (reg->s32_max_value <= sval) return 0; break; case BPF_JLT: @@ -6895,7 +6895,7 @@ static int is_branch64_taken(struct bpf_ case BPF_JSGT: if (reg->smin_value > sval) return 1; - else if (reg->smax_value < sval) + else if (reg->smax_value <= sval) return 0; break; case BPF_JLT:

From: Ville Syrjälä ville.syrjala@linux.intel.com

commit eaf5bfe37db871031232d2bf2535b6ca92afbad8 upstream.

In thunderbolt mode the PHY is owned by the thunderbolt controller. We are not supposed to touch it. So skip the vswing programming as well (we already skipped the other steps not applicable to TBT).

Touching this stuff could supposedly interfere with the PHY programming done by the thunderbolt controller.

Cc: stable@vger.kernel.org Signed-off-by: Ville Syrjälä ville.syrjala@linux.intel.com Link: https://patchwork.freedesktop.org/patch/msgid/20210128155948.13678-1-ville.s... Reviewed-by: Imre Deak imre.deak@intel.com (cherry picked from commit f8c6b615b921d8a1bcd74870f9105e62b0bceff3) Signed-off-by: Jani Nikula jani.nikula@intel.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- drivers/gpu/drm/i915/display/intel_ddi.c | 6 ++++++ 1 file changed, 6 insertions(+)

--- a/drivers/gpu/drm/i915/display/intel_ddi.c +++ b/drivers/gpu/drm/i915/display/intel_ddi.c @@ -2597,6 +2597,9 @@ static void icl_mg_phy_ddi_vswing_sequen u32 n_entries, val; int ln, rate = 0;

+ if (enc_to_dig_port(encoder)->tc_mode == TC_PORT_TBT_ALT) + return; + if (type != INTEL_OUTPUT_HDMI) { struct intel_dp *intel_dp = enc_to_intel_dp(encoder);

@@ -2741,6 +2744,9 @@ tgl_dkl_phy_ddi_vswing_sequence(struct i u32 n_entries, val, ln, dpcnt_mask, dpcnt_val; int rate = 0;

+ if (enc_to_dig_port(encoder)->tc_mode == TC_PORT_TBT_ALT) + return; + if (type != INTEL_OUTPUT_HDMI) { struct intel_dp *intel_dp = enc_to_intel_dp(encoder);

From: Johannes Weiner hannes@cmpxchg.org

commit e82553c10b0899994153f9bf0af333c0a1550fd7 upstream.

This reverts commit 536d3bf261a2fc3b05b3e91e7eef7383443015cf, as it can cause writers to memory.high to get stuck in the kernel forever, performing page reclaim and consuming excessive amounts of CPU cycles.

Before the patch, a write to memory.high would first put the new limit in place for the workload, and then reclaim the requested delta. After the patch, the kernel tries to reclaim the delta before putting the new limit into place, in order to not overwhelm the workload with a sudden, large excess over the limit. However, if reclaim is actively racing with new allocations from the uncurbed workload, it can keep the write() working inside the kernel indefinitely.

This is causing problems in Facebook production. A privileged system-level daemon that adjusts memory.high for various workloads running on a host can get unexpectedly stuck in the kernel and essentially turn into a sort of involuntary kswapd for one of the workloads. We've observed that daemon busy-spin in a write() for minutes at a time, neglecting its other duties on the system, and expending privileged system resources on behalf of a workload.

To remedy this, we have first considered changing the reclaim logic to break out after a couple of loops - whether the workload has converged to the new limit or not - and bound the write() call this way. However, the root cause that inspired the sequence change in the first place has been fixed through other means, and so a revert back to the proven limit-setting sequence, also used by memory.max, is preferable.

The sequence was changed to avoid extreme latencies in the workload when the limit was lowered: the sudden, large excess created by the limit lowering would erroneously trigger the penalty sleeping code that is meant to throttle excessive growth from below. Allocating threads could end up sleeping long after the write() had already reclaimed the delta for which they were being punished.

However, erroneous throttling also caused problems in other scenarios at around the same time. This resulted in commit b3ff92916af3 ("mm, memcg: reclaim more aggressively before high allocator throttling"), included in the same release as the offending commit. When allocating threads now encounter large excess caused by a racing write() to memory.high, instead of entering punitive sleeps, they will simply be tasked with helping reclaim down the excess, and will be held no longer than it takes to accomplish that. This is in line with regular limit enforcement - i.e. if the workload allocates up against or over an otherwise unchanged limit from below.

With the patch breaking userspace, and the root cause addressed by other means already, revert it again.

Link: https://lkml.kernel.org/r/20210122184341.292461-1-hannes@cmpxchg.org Fixes: 536d3bf261a2 ("mm: memcontrol: avoid workload stalls when lowering memory.high") Signed-off-by: Johannes Weiner hannes@cmpxchg.org Reported-by: Tejun Heo tj@kernel.org Acked-by: Chris Down chris@chrisdown.name Acked-by: Michal Hocko mhocko@suse.com Cc: Roman Gushchin guro@fb.com Cc: Shakeel Butt shakeelb@google.com Cc: Michal Koutný mkoutny@suse.com Cc: stable@vger.kernel.org [5.8+] Signed-off-by: Andrew Morton akpm@linux-foundation.org Signed-off-by: Linus Torvalds torvalds@linux-foundation.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- mm/memcontrol.c | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-)

--- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -6320,6 +6320,8 @@ static ssize_t memory_high_write(struct if (err) return err;

+ page_counter_set_high(&memcg->memory, high); + for (;;) { unsigned long nr_pages = page_counter_read(&memcg->memory); unsigned long reclaimed; @@ -6343,10 +6345,7 @@ static ssize_t memory_high_write(struct break; }

- page_counter_set_high(&memcg->memory, high); - memcg_wb_domain_size_changed(memcg); - return nbytes; }

From: Phillip Lougher phillip@squashfs.org.uk

commit f37aa4c7366e23f91b81d00bafd6a7ab54e4a381 upstream.

Sysbot has reported a number of "slab-out-of-bounds reads" and "use-after-free read" errors which has been identified as being caused by a corrupted index value read from the inode. This could be because the metadata block is uncompressed, or because the "compression" bit has been corrupted (turning a compressed block into an uncompressed block).

This patch adds additional sanity checks to detect this, and the following corruption.

1. It checks against corruption of the ids count. This can either lead to a larger table to be read, or a smaller than expected table to be read.

In the case of a too large ids count, this would often have been trapped by the existing sanity checks, but this patch introduces a more exact check, which can identify too small values.

2. It checks the contents of the index table for corruption.

Link: https://lkml.kernel.org/r/20210204130249.4495-3-phillip@squashfs.org.uk Signed-off-by: Phillip Lougher phillip@squashfs.org.uk Reported-by: syzbot+b06d57ba83f604522af2@syzkaller.appspotmail.com Reported-by: syzbot+c021ba012da41ee9807c@syzkaller.appspotmail.com Reported-by: syzbot+5024636e8b5fd19f0f19@syzkaller.appspotmail.com Reported-by: syzbot+bcbc661df46657d0fa4f@syzkaller.appspotmail.com Cc: stable@vger.kernel.org Signed-off-by: Andrew Morton akpm@linux-foundation.org Signed-off-by: Linus Torvalds torvalds@linux-foundation.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- fs/squashfs/id.c | 40 ++++++++++++++++++++++++++++++++-------- fs/squashfs/squashfs_fs_sb.h | 1 + fs/squashfs/super.c | 6 +++--- fs/squashfs/xattr.h | 10 +++++++++- 4 files changed, 45 insertions(+), 12 deletions(-)

--- a/fs/squashfs/id.c +++ b/fs/squashfs/id.c @@ -35,10 +35,15 @@ int squashfs_get_id(struct super_block * struct squashfs_sb_info *msblk = sb->s_fs_info; int block = SQUASHFS_ID_BLOCK(index); int offset = SQUASHFS_ID_BLOCK_OFFSET(index); - u64 start_block = le64_to_cpu(msblk->id_table[block]); + u64 start_block; __le32 disk_id; int err;

+ if (index >= msblk->ids) + return -EINVAL; + + start_block = le64_to_cpu(msblk->id_table[block]); + err = squashfs_read_metadata(sb, &disk_id, &start_block, &offset, sizeof(disk_id)); if (err < 0) @@ -56,7 +61,10 @@ __le64 *squashfs_read_id_index_table(str u64 id_table_start, u64 next_table, unsigned short no_ids) { unsigned int length = SQUASHFS_ID_BLOCK_BYTES(no_ids); + unsigned int indexes = SQUASHFS_ID_BLOCKS(no_ids); + int n; __le64 *table; + u64 start, end;

TRACE("In read_id_index_table, length %d\n", length);

@@ -67,20 +75,36 @@ __le64 *squashfs_read_id_index_table(str return ERR_PTR(-EINVAL);

/* - * length bytes should not extend into the next table - this check - * also traps instances where id_table_start is incorrectly larger - * than the next table start + * The computed size of the index table (length bytes) should exactly + * match the table start and end points */ - if (id_table_start + length > next_table) + if (length != (next_table - id_table_start)) return ERR_PTR(-EINVAL);

table = squashfs_read_table(sb, id_table_start, length); + if (IS_ERR(table)) + return table;

/* - * table[0] points to the first id lookup table metadata block, this - * should be less than id_table_start + * table[0], table[1], ... table[indexes - 1] store the locations + * of the compressed id blocks. Each entry should be less than + * the next (i.e. table[0] < table[1]), and the difference between them + * should be SQUASHFS_METADATA_SIZE or less. table[indexes - 1] + * should be less than id_table_start, and again the difference + * should be SQUASHFS_METADATA_SIZE or less */ - if (!IS_ERR(table) && le64_to_cpu(table[0]) >= id_table_start) { + for (n = 0; n < (indexes - 1); n++) { + start = le64_to_cpu(table[n]); + end = le64_to_cpu(table[n + 1]); + + if (start >= end || (end - start) > SQUASHFS_METADATA_SIZE) { + kfree(table); + return ERR_PTR(-EINVAL); + } + } + + start = le64_to_cpu(table[indexes - 1]); + if (start >= id_table_start || (id_table_start - start) > SQUASHFS_METADATA_SIZE) { kfree(table); return ERR_PTR(-EINVAL); } --- a/fs/squashfs/squashfs_fs_sb.h +++ b/fs/squashfs/squashfs_fs_sb.h @@ -64,5 +64,6 @@ struct squashfs_sb_info { unsigned int inodes; unsigned int fragments; int xattr_ids; + unsigned int ids; }; #endif --- a/fs/squashfs/super.c +++ b/fs/squashfs/super.c @@ -166,6 +166,7 @@ static int squashfs_fill_super(struct su msblk->directory_table = le64_to_cpu(sblk->directory_table_start); msblk->inodes = le32_to_cpu(sblk->inodes); msblk->fragments = le32_to_cpu(sblk->fragments); + msblk->ids = le16_to_cpu(sblk->no_ids); flags = le16_to_cpu(sblk->flags);

TRACE("Found valid superblock on %pg\n", sb->s_bdev); @@ -177,7 +178,7 @@ static int squashfs_fill_super(struct su TRACE("Block size %d\n", msblk->block_size); TRACE("Number of inodes %d\n", msblk->inodes); TRACE("Number of fragments %d\n", msblk->fragments); - TRACE("Number of ids %d\n", le16_to_cpu(sblk->no_ids)); + TRACE("Number of ids %d\n", msblk->ids); TRACE("sblk->inode_table_start %llx\n", msblk->inode_table); TRACE("sblk->directory_table_start %llx\n", msblk->directory_table); TRACE("sblk->fragment_table_start %llx\n", @@ -236,8 +237,7 @@ static int squashfs_fill_super(struct su allocate_id_index_table: /* Allocate and read id index table */ msblk->id_table = squashfs_read_id_index_table(sb, - le64_to_cpu(sblk->id_table_start), next_table, - le16_to_cpu(sblk->no_ids)); + le64_to_cpu(sblk->id_table_start), next_table, msblk->ids); if (IS_ERR(msblk->id_table)) { errorf(fc, "unable to read id index table"); err = PTR_ERR(msblk->id_table); --- a/fs/squashfs/xattr.h +++ b/fs/squashfs/xattr.h @@ -17,8 +17,16 @@ extern int squashfs_xattr_lookup(struct static inline __le64 *squashfs_read_xattr_id_table(struct super_block *sb, u64 start, u64 *xattr_table_start, int *xattr_ids) { + struct squashfs_xattr_id_table *id_table; + + id_table = squashfs_read_table(sb, start, sizeof(*id_table)); + if (IS_ERR(id_table)) + return (__le64 *) id_table; + + *xattr_table_start = le64_to_cpu(id_table->xattr_table_start); + kfree(id_table); + ERROR("Xattrs in filesystem, these will be ignored\n"); - *xattr_table_start = start; return ERR_PTR(-ENOTSUPP); }

From: Phillip Lougher phillip@squashfs.org.uk

commit 506220d2ba21791314af569211ffd8870b8208fa upstream.

Sysbot has reported a warning where a kmalloc() attempt exceeds the maximum limit. This has been identified as corruption of the xattr_ids count when reading the xattr id lookup table.

This patch adds a number of additional sanity checks to detect this corruption and others.

1. It checks for a corrupted xattr index read from the inode. This could be because the metadata block is uncompressed, or because the "compression" bit has been corrupted (turning a compressed block into an uncompressed block). This would cause an out of bounds read.

2. It checks against corruption of the xattr_ids count. This can either lead to the above kmalloc failure, or a smaller than expected table to be read.

3. It checks the contents of the index table for corruption.

[phillip@squashfs.org.uk: fix checkpatch issue] Link: https://lkml.kernel.org/r/270245655.754655.1612770082682@webmail.123-reg.co....

Link: https://lkml.kernel.org/r/20210204130249.4495-5-phillip@squashfs.org.uk Signed-off-by: Phillip Lougher phillip@squashfs.org.uk Reported-by: syzbot+2ccea6339d368360800d@syzkaller.appspotmail.com Cc: stable@vger.kernel.org Signed-off-by: Andrew Morton akpm@linux-foundation.org Signed-off-by: Linus Torvalds torvalds@linux-foundation.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- fs/squashfs/xattr_id.c | 66 ++++++++++++++++++++++++++++++++++++++++++------- 1 file changed, 57 insertions(+), 9 deletions(-)

--- a/fs/squashfs/xattr_id.c +++ b/fs/squashfs/xattr_id.c @@ -31,10 +31,15 @@ int squashfs_xattr_lookup(struct super_b struct squashfs_sb_info *msblk = sb->s_fs_info; int block = SQUASHFS_XATTR_BLOCK(index); int offset = SQUASHFS_XATTR_BLOCK_OFFSET(index); - u64 start_block = le64_to_cpu(msblk->xattr_id_table[block]); + u64 start_block; struct squashfs_xattr_id id; int err;

+ if (index >= msblk->xattr_ids) + return -EINVAL; + + start_block = le64_to_cpu(msblk->xattr_id_table[block]); + err = squashfs_read_metadata(sb, &id, &start_block, &offset, sizeof(id)); if (err < 0) @@ -50,13 +55,17 @@ int squashfs_xattr_lookup(struct super_b /* * Read uncompressed xattr id lookup table indexes from disk into memory */ -__le64 *squashfs_read_xattr_id_table(struct super_block *sb, u64 start, +__le64 *squashfs_read_xattr_id_table(struct super_block *sb, u64 table_start, u64 *xattr_table_start, int *xattr_ids) { - unsigned int len; + struct squashfs_sb_info *msblk = sb->s_fs_info; + unsigned int len, indexes; struct squashfs_xattr_id_table *id_table; + __le64 *table; + u64 start, end; + int n;

- id_table = squashfs_read_table(sb, start, sizeof(*id_table)); + id_table = squashfs_read_table(sb, table_start, sizeof(*id_table)); if (IS_ERR(id_table)) return (__le64 *) id_table;

@@ -70,13 +79,52 @@ __le64 *squashfs_read_xattr_id_table(str if (*xattr_ids == 0) return ERR_PTR(-EINVAL);

- /* xattr_table should be less than start */ - if (*xattr_table_start >= start) + len = SQUASHFS_XATTR_BLOCK_BYTES(*xattr_ids); + indexes = SQUASHFS_XATTR_BLOCKS(*xattr_ids); + + /* + * The computed size of the index table (len bytes) should exactly + * match the table start and end points + */ + start = table_start + sizeof(*id_table); + end = msblk->bytes_used; + + if (len != (end - start)) return ERR_PTR(-EINVAL);

- len = SQUASHFS_XATTR_BLOCK_BYTES(*xattr_ids); + table = squashfs_read_table(sb, start, len); + if (IS_ERR(table)) + return table; + + /* table[0], table[1], ... table[indexes - 1] store the locations + * of the compressed xattr id blocks. Each entry should be less than + * the next (i.e. table[0] < table[1]), and the difference between them + * should be SQUASHFS_METADATA_SIZE or less. table[indexes - 1] + * should be less than table_start, and again the difference + * shouls be SQUASHFS_METADATA_SIZE or less. + * + * Finally xattr_table_start should be less than table[0]. + */ + for (n = 0; n < (indexes - 1); n++) { + start = le64_to_cpu(table[n]); + end = le64_to_cpu(table[n + 1]); + + if (start >= end || (end - start) > SQUASHFS_METADATA_SIZE) { + kfree(table); + return ERR_PTR(-EINVAL); + } + } + + start = le64_to_cpu(table[indexes - 1]); + if (start >= table_start || (table_start - start) > SQUASHFS_METADATA_SIZE) { + kfree(table); + return ERR_PTR(-EINVAL); + }

- TRACE("In read_xattr_index_table, length %d\n", len); + if (*xattr_table_start >= le64_to_cpu(table[0])) { + kfree(table); + return ERR_PTR(-EINVAL); + }

- return squashfs_read_table(sb, start + sizeof(*id_table), len); + return table; }