Merge tag 'for-linus-2019-10-18' of git://git.kernel.dk/linux-block

Pull block fixes from Jens Axboe:

 - NVMe pull request from Keith that address deadlocks, double resets,
   memory leaks, and other regression.

 - Fixup elv_support_iosched() for bio based devices (Damien)

 - Fixup for the ahci PCS quirk (Dan)

 - Socket O_NONBLOCK handling fix for io_uring (me)

 - Timeout sequence io_uring fixes (yangerkun)

 - MD warning fix for parameter default_layout (Song)

 - blkcg activation fixes (Tejun)

 - blk-rq-qos node deletion fix (Tejun)

* tag 'for-linus-2019-10-18' of git://git.kernel.dk/linux-block:
  nvme-pci: Set the prp2 correctly when using more than 4k page
  io_uring: fix logic error in io_timeout
  io_uring: fix up O_NONBLOCK handling for sockets
  md/raid0: fix warning message for parameter default_layout
  libata/ahci: Fix PCS quirk application
  blk-rq-qos: fix first node deletion of rq_qos_del()
  blkcg: Fix multiple bugs in blkcg_activate_policy()
  io_uring: consider the overflow of sequence for timeout req
  nvme-tcp: fix possible leakage during error flow
  nvmet-loop: fix possible leakage during error flow
  block: Fix elv_support_iosched()
  nvme-tcp: Initialize sk->sk_ll_usec only with NET_RX_BUSY_POLL
  nvme: Wait for reset state when required
  nvme: Prevent resets during paused controller state
  nvme: Restart request timers in resetting state
  nvme: Remove ADMIN_ONLY state
  nvme-pci: Free tagset if no IO queues
  nvme: retain split access workaround for capability reads
  nvme: fix possible deadlock when nvme_update_formats fails

1 files changed, 60 insertions, 24 deletions

diff --git a/fs/io_uring.c b/fs/io_uring.c
index 76fdbe84aff5..67dbe0201e0d 100644
--- a/fs/io_uring.c
+++ b/fs/io_uring.c
@@ -322,6 +322,8 @@ struct io_kiocb {
 #define REQ_F_FAIL_LINK		256	/* fail rest of links */
 #define REQ_F_SHADOW_DRAIN	512	/* link-drain shadow req */
 #define REQ_F_TIMEOUT		1024	/* timeout request */
+#define REQ_F_ISREG		2048	/* regular file */
+#define REQ_F_MUST_PUNT		4096	/* must be punted even for NONBLOCK */
 	u64			user_data;
 	u32			result;
 	u32			sequence;
@@ -914,26 +916,26 @@ static int io_iopoll_check(struct io_ring_ctx *ctx, unsigned *nr_events,
 	return ret;
 }
 
-static void kiocb_end_write(struct kiocb *kiocb)
+static void kiocb_end_write(struct io_kiocb *req)
 {
-	if (kiocb->ki_flags & IOCB_WRITE) {
-		struct inode *inode = file_inode(kiocb->ki_filp);
+	/*
+	 * Tell lockdep we inherited freeze protection from submission
+	 * thread.
+	 */
+	if (req->flags & REQ_F_ISREG) {
+		struct inode *inode = file_inode(req->file);
 
-		/*
-		 * Tell lockdep we inherited freeze protection from submission
-		 * thread.
-		 */
-		if (S_ISREG(inode->i_mode))
-			__sb_writers_acquired(inode->i_sb, SB_FREEZE_WRITE);
-		file_end_write(kiocb->ki_filp);
+		__sb_writers_acquired(inode->i_sb, SB_FREEZE_WRITE);
 	}
+	file_end_write(req->file);
 }
 
 static void io_complete_rw(struct kiocb *kiocb, long res, long res2)
 {
 	struct io_kiocb *req = container_of(kiocb, struct io_kiocb, rw);
 
-	kiocb_end_write(kiocb);
+	if (kiocb->ki_flags & IOCB_WRITE)
+		kiocb_end_write(req);
 
 	if ((req->flags & REQ_F_LINK) && res != req->result)
 		req->flags |= REQ_F_FAIL_LINK;
@@ -945,7 +947,8 @@ static void io_complete_rw_iopoll(struct kiocb *kiocb, long res, long res2)
 {
 	struct io_kiocb *req = container_of(kiocb, struct io_kiocb, rw);
 
-	kiocb_end_write(kiocb);
+	if (kiocb->ki_flags & IOCB_WRITE)
+		kiocb_end_write(req);
 
 	if ((req->flags & REQ_F_LINK) && res != req->result)
 		req->flags |= REQ_F_FAIL_LINK;
@@ -1059,8 +1062,17 @@ static int io_prep_rw(struct io_kiocb *req, const struct sqe_submit *s,
 	if (!req->file)
 		return -EBADF;
 
-	if (force_nonblock && !io_file_supports_async(req->file))
-		force_nonblock = false;
+	if (S_ISREG(file_inode(req->file)->i_mode))
+		req->flags |= REQ_F_ISREG;
+
+	/*
+	 * If the file doesn't support async, mark it as REQ_F_MUST_PUNT so
+	 * we know to async punt it even if it was opened O_NONBLOCK
+	 */
+	if (force_nonblock && !io_file_supports_async(req->file)) {
+		req->flags |= REQ_F_MUST_PUNT;
+		return -EAGAIN;
+	}
 
 	kiocb->ki_pos = READ_ONCE(sqe->off);
 	kiocb->ki_flags = iocb_flags(kiocb->ki_filp);
@@ -1081,7 +1093,8 @@ static int io_prep_rw(struct io_kiocb *req, const struct sqe_submit *s,
 		return ret;
 
 	/* don't allow async punt if RWF_NOWAIT was requested */
-	if (kiocb->ki_flags & IOCB_NOWAIT)
+	if ((kiocb->ki_flags & IOCB_NOWAIT) ||
+	    (req->file->f_flags & O_NONBLOCK))
 		req->flags |= REQ_F_NOWAIT;
 
 	if (force_nonblock)
@@ -1382,7 +1395,9 @@ static int io_read(struct io_kiocb *req, const struct sqe_submit *s,
 		 * need async punt anyway, so it's more efficient to do it
 		 * here.
 		 */
-		if (force_nonblock && ret2 > 0 && ret2 < read_size)
+		if (force_nonblock && !(req->flags & REQ_F_NOWAIT) &&
+		    (req->flags & REQ_F_ISREG) &&
+		    ret2 > 0 && ret2 < read_size)
 			ret2 = -EAGAIN;
 		/* Catch -EAGAIN return for forced non-blocking submission */
 		if (!force_nonblock || ret2 != -EAGAIN) {
@@ -1447,7 +1462,7 @@ static int io_write(struct io_kiocb *req, const struct sqe_submit *s,
 		 * released so that it doesn't complain about the held lock when
 		 * we return to userspace.
 		 */
-		if (S_ISREG(file_inode(file)->i_mode)) {
+		if (req->flags & REQ_F_ISREG) {
 			__sb_start_write(file_inode(file)->i_sb,
 						SB_FREEZE_WRITE, true);
 			__sb_writers_release(file_inode(file)->i_sb,
@@ -1884,7 +1899,7 @@ static enum hrtimer_restart io_timeout_fn(struct hrtimer *timer)
 
 static int io_timeout(struct io_kiocb *req, const struct io_uring_sqe *sqe)
 {
-	unsigned count, req_dist, tail_index;
+	unsigned count;
 	struct io_ring_ctx *ctx = req->ctx;
 	struct list_head *entry;
 	struct timespec64 ts;
@@ -1907,21 +1922,36 @@ static int io_timeout(struct io_kiocb *req, const struct io_uring_sqe *sqe)
 		count = 1;
 
 	req->sequence = ctx->cached_sq_head + count - 1;
+	/* reuse it to store the count */
+	req->submit.sequence = count;
 	req->flags |= REQ_F_TIMEOUT;
 
 	/*
 	 * Insertion sort, ensuring the first entry in the list is always
 	 * the one we need first.
 	 */
-	tail_index = ctx->cached_cq_tail - ctx->rings->sq_dropped;
-	req_dist = req->sequence - tail_index;
 	spin_lock_irq(&ctx->completion_lock);
 	list_for_each_prev(entry, &ctx->timeout_list) {
 		struct io_kiocb *nxt = list_entry(entry, struct io_kiocb, list);
-		unsigned dist;
+		unsigned nxt_sq_head;
+		long long tmp, tmp_nxt;
 
-		dist = nxt->sequence - tail_index;
-		if (req_dist >= dist)
+		/*
+		 * Since cached_sq_head + count - 1 can overflow, use type long
+		 * long to store it.
+		 */
+		tmp = (long long)ctx->cached_sq_head + count - 1;
+		nxt_sq_head = nxt->sequence - nxt->submit.sequence + 1;
+		tmp_nxt = (long long)nxt_sq_head + nxt->submit.sequence - 1;
+
+		/*
+		 * cached_sq_head may overflow, and it will never overflow twice
+		 * once there is some timeout req still be valid.
+		 */
+		if (ctx->cached_sq_head < nxt_sq_head)
+			tmp += UINT_MAX;
+
+		if (tmp >= tmp_nxt)
 			break;
 	}
 	list_add(&req->list, entry);
@@ -2267,7 +2297,13 @@ static int __io_queue_sqe(struct io_ring_ctx *ctx, struct io_kiocb *req,
 	int ret;
 
 	ret = __io_submit_sqe(ctx, req, s, force_nonblock);
-	if (ret == -EAGAIN && !(req->flags & REQ_F_NOWAIT)) {
+
+	/*
+	 * We async punt it if the file wasn't marked NOWAIT, or if the file
+	 * doesn't support non-blocking read/write attempts
+	 */
+	if (ret == -EAGAIN && (!(req->flags & REQ_F_NOWAIT) ||
+	    (req->flags & REQ_F_MUST_PUNT))) {
 		struct io_uring_sqe *sqe_copy;
 
 		sqe_copy = kmemdup(s->sqe, sizeof(*sqe_copy), GFP_KERNEL);