Merge tag 'for-4.21/block-20181221' of git://git.kernel.dk/linux-block

Pull block updates from Jens Axboe:
 "This is the main pull request for block/storage for 4.21.

  Larger than usual, it was a busy round with lots of goodies queued up.
  Most notable is the removal of the old IO stack, which has been a long
  time coming. No new features for a while, everything coming in this
  week has all been fixes for things that were previously merged.

  This contains:

   - Use atomic counters instead of semaphores for mtip32xx (Arnd)

   - Cleanup of the mtip32xx request setup (Christoph)

   - Fix for circular locking dependency in loop (Jan, Tetsuo)

   - bcache (Coly, Guoju, Shenghui)
      * Optimizations for writeback caching
      * Various fixes and improvements

   - nvme (Chaitanya, Christoph, Sagi, Jay, me, Keith)
      * host and target support for NVMe over TCP
      * Error log page support
      * Support for separate read/write/poll queues
      * Much improved polling
      * discard OOM fallback
      * Tracepoint improvements

   - lightnvm (Hans, Hua, Igor, Matias, Javier)
      * Igor added packed metadata to pblk. Now drives without metadata
        per LBA can be used as well.
      * Fix from Geert on uninitialized value on chunk metadata reads.
      * Fixes from Hans and Javier to pblk recovery and write path.
      * Fix from Hua Su to fix a race condition in the pblk recovery
        code.
      * Scan optimization added to pblk recovery from Zhoujie.
      * Small geometry cleanup from me.

   - Conversion of the last few drivers that used the legacy path to
     blk-mq (me)

   - Removal of legacy IO path in SCSI (me, Christoph)

   - Removal of legacy IO stack and schedulers (me)

   - Support for much better polling, now without interrupts at all.
     blk-mq adds support for multiple queue maps, which enables us to
     have a map per type. This in turn enables nvme to have separate
     completion queues for polling, which can then be interrupt-less.
     Also means we're ready for async polled IO, which is hopefully
     coming in the next release.

   - Killing of (now) unused block exports (Christoph)

   - Unification of the blk-rq-qos and blk-wbt wait handling (Josef)

   - Support for zoned testing with null_blk (Masato)

   - sx8 conversion to per-host tag sets (Christoph)

   - IO priority improvements (Damien)

   - mq-deadline zoned fix (Damien)

   - Ref count blkcg series (Dennis)

   - Lots of blk-mq improvements and speedups (me)

   - sbitmap scalability improvements (me)

   - Make core inflight IO accounting per-cpu (Mikulas)

   - Export timeout setting in sysfs (Weiping)

   - Cleanup the direct issue path (Jianchao)

   - Export blk-wbt internals in block debugfs for easier debugging
     (Ming)

   - Lots of other fixes and improvements"

* tag 'for-4.21/block-20181221' of git://git.kernel.dk/linux-block: (364 commits)
  kyber: use sbitmap add_wait_queue/list_del wait helpers
  sbitmap: add helpers for add/del wait queue handling
  block: save irq state in blkg_lookup_create()
  dm: don't reuse bio for flushes
  nvme-pci: trace SQ status on completions
  nvme-rdma: implement polling queue map
  nvme-fabrics: allow user to pass in nr_poll_queues
  nvme-fabrics: allow nvmf_connect_io_queue to poll
  nvme-core: optionally poll sync commands
  block: make request_to_qc_t public
  nvme-tcp: fix spelling mistake "attepmpt" -> "attempt"
  nvme-tcp: fix endianess annotations
  nvmet-tcp: fix endianess annotations
  nvme-pci: refactor nvme_poll_irqdisable to make sparse happy
  nvme-pci: only set nr_maps to 2 if poll queues are supported
  nvmet: use a macro for default error location
  nvmet: fix comparison of a u16 with -1
  blk-mq: enable IO poll if .nr_queues of type poll > 0
  blk-mq: change blk_mq_queue_busy() to blk_mq_queue_inflight()
  blk-mq: skip zero-queue maps in blk_mq_map_swqueue
  ...

1 files changed, 104 insertions, 61 deletions

diff --git a/drivers/nvme/target/io-cmd-file.c b/drivers/nvme/target/io-cmd-file.c
index 01feebec29ea..517522305e5c 100644
--- a/drivers/nvme/target/io-cmd-file.c
+++ b/drivers/nvme/target/io-cmd-file.c
@@ -83,17 +83,16 @@ static void nvmet_file_init_bvec(struct bio_vec *bv, struct sg_page_iter *iter)
 }
 
 static ssize_t nvmet_file_submit_bvec(struct nvmet_req *req, loff_t pos,
-		unsigned long nr_segs, size_t count)
+		unsigned long nr_segs, size_t count, int ki_flags)
 {
 	struct kiocb *iocb = &req->f.iocb;
 	ssize_t (*call_iter)(struct kiocb *iocb, struct iov_iter *iter);
 	struct iov_iter iter;
-	int ki_flags = 0, rw;
-	ssize_t ret;
+	int rw;
 
 	if (req->cmd->rw.opcode == nvme_cmd_write) {
 		if (req->cmd->rw.control & cpu_to_le16(NVME_RW_FUA))
-			ki_flags = IOCB_DSYNC;
+			ki_flags |= IOCB_DSYNC;
 		call_iter = req->ns->file->f_op->write_iter;
 		rw = WRITE;
 	} else {
@@ -107,17 +106,13 @@ static ssize_t nvmet_file_submit_bvec(struct nvmet_req *req, loff_t pos,
 	iocb->ki_filp = req->ns->file;
 	iocb->ki_flags = ki_flags | iocb_flags(req->ns->file);
 
-	ret = call_iter(iocb, &iter);
-
-	if (ret != -EIOCBQUEUED && iocb->ki_complete)
-		iocb->ki_complete(iocb, ret, 0);
-
-	return ret;
+	return call_iter(iocb, &iter);
 }
 
 static void nvmet_file_io_done(struct kiocb *iocb, long ret, long ret2)
 {
 	struct nvmet_req *req = container_of(iocb, struct nvmet_req, f.iocb);
+	u16 status = NVME_SC_SUCCESS;
 
 	if (req->f.bvec != req->inline_bvec) {
 		if (likely(req->f.mpool_alloc == false))
@@ -126,11 +121,12 @@ static void nvmet_file_io_done(struct kiocb *iocb, long ret, long ret2)
 			mempool_free(req->f.bvec, req->ns->bvec_pool);
 	}
 
-	nvmet_req_complete(req, ret != req->data_len ?
-			NVME_SC_INTERNAL | NVME_SC_DNR : 0);
+	if (unlikely(ret != req->data_len))
+		status = errno_to_nvme_status(req, ret);
+	nvmet_req_complete(req, status);
 }
 
-static void nvmet_file_execute_rw(struct nvmet_req *req)
+static bool nvmet_file_execute_io(struct nvmet_req *req, int ki_flags)
 {
 	ssize_t nr_bvec = DIV_ROUND_UP(req->data_len, PAGE_SIZE);
 	struct sg_page_iter sg_pg_iter;
@@ -140,30 +136,14 @@ static void nvmet_file_execute_rw(struct nvmet_req *req)
 	ssize_t ret = 0;
 	loff_t pos;
 
-	if (!req->sg_cnt || !nr_bvec) {
-		nvmet_req_complete(req, 0);
-		return;
-	}
+
+	if (req->f.mpool_alloc && nr_bvec > NVMET_MAX_MPOOL_BVEC)
+		is_sync = true;
 
 	pos = le64_to_cpu(req->cmd->rw.slba) << req->ns->blksize_shift;
 	if (unlikely(pos + req->data_len > req->ns->size)) {
-		nvmet_req_complete(req, NVME_SC_LBA_RANGE | NVME_SC_DNR);
-		return;
-	}
-
-	if (nr_bvec > NVMET_MAX_INLINE_BIOVEC)
-		req->f.bvec = kmalloc_array(nr_bvec, sizeof(struct bio_vec),
-				GFP_KERNEL);
-	else
-		req->f.bvec = req->inline_bvec;
-
-	req->f.mpool_alloc = false;
-	if (unlikely(!req->f.bvec)) {
-		/* fallback under memory pressure */
-		req->f.bvec = mempool_alloc(req->ns->bvec_pool, GFP_KERNEL);
-		req->f.mpool_alloc = true;
-		if (nr_bvec > NVMET_MAX_MPOOL_BVEC)
-			is_sync = true;
+		nvmet_req_complete(req, errno_to_nvme_status(req, -ENOSPC));
+		return true;
 	}
 
 	memset(&req->f.iocb, 0, sizeof(struct kiocb));
@@ -177,9 +157,10 @@ static void nvmet_file_execute_rw(struct nvmet_req *req)
 
 		if (unlikely(is_sync) &&
 		    (nr_bvec - 1 == 0 || bv_cnt == NVMET_MAX_MPOOL_BVEC)) {
-			ret = nvmet_file_submit_bvec(req, pos, bv_cnt, len);
+			ret = nvmet_file_submit_bvec(req, pos, bv_cnt, len, 0);
 			if (ret < 0)
-				goto out;
+				goto complete;
+
 			pos += len;
 			bv_cnt = 0;
 			len = 0;
@@ -187,35 +168,95 @@ static void nvmet_file_execute_rw(struct nvmet_req *req)
 		nr_bvec--;
 	}
 
-	if (WARN_ON_ONCE(total_len != req->data_len))
+	if (WARN_ON_ONCE(total_len != req->data_len)) {
 		ret = -EIO;
-out:
-	if (unlikely(is_sync || ret)) {
-		nvmet_file_io_done(&req->f.iocb, ret < 0 ? ret : total_len, 0);
-		return;
+		goto complete;
+	}
+
+	if (unlikely(is_sync)) {
+		ret = total_len;
+		goto complete;
 	}
-	req->f.iocb.ki_complete = nvmet_file_io_done;
-	nvmet_file_submit_bvec(req, pos, bv_cnt, total_len);
+
+	/*
+	 * A NULL ki_complete ask for synchronous execution, which we want
+	 * for the IOCB_NOWAIT case.
+	 */
+	if (!(ki_flags & IOCB_NOWAIT))
+		req->f.iocb.ki_complete = nvmet_file_io_done;
+
+	ret = nvmet_file_submit_bvec(req, pos, bv_cnt, total_len, ki_flags);
+
+	switch (ret) {
+	case -EIOCBQUEUED:
+		return true;
+	case -EAGAIN:
+		if (WARN_ON_ONCE(!(ki_flags & IOCB_NOWAIT)))
+			goto complete;
+		return false;
+	case -EOPNOTSUPP:
+		/*
+		 * For file systems returning error -EOPNOTSUPP, handle
+		 * IOCB_NOWAIT error case separately and retry without
+		 * IOCB_NOWAIT.
+		 */
+		if ((ki_flags & IOCB_NOWAIT))
+			return false;
+		break;
+	}
+
+complete:
+	nvmet_file_io_done(&req->f.iocb, ret, 0);
+	return true;
 }
 
 static void nvmet_file_buffered_io_work(struct work_struct *w)
 {
 	struct nvmet_req *req = container_of(w, struct nvmet_req, f.work);
 
-	nvmet_file_execute_rw(req);
+	nvmet_file_execute_io(req, 0);
 }
 
-static void nvmet_file_execute_rw_buffered_io(struct nvmet_req *req)
+static void nvmet_file_submit_buffered_io(struct nvmet_req *req)
 {
 	INIT_WORK(&req->f.work, nvmet_file_buffered_io_work);
 	queue_work(buffered_io_wq, &req->f.work);
 }
 
+static void nvmet_file_execute_rw(struct nvmet_req *req)
+{
+	ssize_t nr_bvec = DIV_ROUND_UP(req->data_len, PAGE_SIZE);
+
+	if (!req->sg_cnt || !nr_bvec) {
+		nvmet_req_complete(req, 0);
+		return;
+	}
+
+	if (nr_bvec > NVMET_MAX_INLINE_BIOVEC)
+		req->f.bvec = kmalloc_array(nr_bvec, sizeof(struct bio_vec),
+				GFP_KERNEL);
+	else
+		req->f.bvec = req->inline_bvec;
+
+	if (unlikely(!req->f.bvec)) {
+		/* fallback under memory pressure */
+		req->f.bvec = mempool_alloc(req->ns->bvec_pool, GFP_KERNEL);
+		req->f.mpool_alloc = true;
+	} else
+		req->f.mpool_alloc = false;
+
+	if (req->ns->buffered_io) {
+		if (likely(!req->f.mpool_alloc) &&
+				nvmet_file_execute_io(req, IOCB_NOWAIT))
+			return;
+		nvmet_file_submit_buffered_io(req);
+	} else
+		nvmet_file_execute_io(req, 0);
+}
+
 u16 nvmet_file_flush(struct nvmet_req *req)
 {
-	if (vfs_fsync(req->ns->file, 1) < 0)
-		return NVME_SC_INTERNAL | NVME_SC_DNR;
-	return 0;
+	return errno_to_nvme_status(req, vfs_fsync(req->ns->file, 1));
 }
 
 static void nvmet_file_flush_work(struct work_struct *w)
@@ -236,30 +277,34 @@ static void nvmet_file_execute_discard(struct nvmet_req *req)
 	int mode = FALLOC_FL_PUNCH_HOLE | FALLOC_FL_KEEP_SIZE;
 	struct nvme_dsm_range range;
 	loff_t offset, len;
-	u16 ret;
+	u16 status = 0;
+	int ret;
 	int i;
 
 	for (i = 0; i <= le32_to_cpu(req->cmd->dsm.nr); i++) {
-		ret = nvmet_copy_from_sgl(req, i * sizeof(range), &range,
+		status = nvmet_copy_from_sgl(req, i * sizeof(range), &range,
 					sizeof(range));
-		if (ret)
+		if (status)
 			break;
 
 		offset = le64_to_cpu(range.slba) << req->ns->blksize_shift;
 		len = le32_to_cpu(range.nlb);
 		len <<= req->ns->blksize_shift;
 		if (offset + len > req->ns->size) {
-			ret = NVME_SC_LBA_RANGE | NVME_SC_DNR;
+			req->error_slba = le64_to_cpu(range.slba);
+			status = errno_to_nvme_status(req, -ENOSPC);
 			break;
 		}
 
-		if (vfs_fallocate(req->ns->file, mode, offset, len)) {
-			ret = NVME_SC_INTERNAL | NVME_SC_DNR;
+		ret = vfs_fallocate(req->ns->file, mode, offset, len);
+		if (ret) {
+			req->error_slba = le64_to_cpu(range.slba);
+			status = errno_to_nvme_status(req, ret);
 			break;
 		}
 	}
 
-	nvmet_req_complete(req, ret);
+	nvmet_req_complete(req, status);
 }
 
 static void nvmet_file_dsm_work(struct work_struct *w)
@@ -299,12 +344,12 @@ static void nvmet_file_write_zeroes_work(struct work_struct *w)
 			req->ns->blksize_shift);
 
 	if (unlikely(offset + len > req->ns->size)) {
-		nvmet_req_complete(req, NVME_SC_LBA_RANGE | NVME_SC_DNR);
+		nvmet_req_complete(req, errno_to_nvme_status(req, -ENOSPC));
 		return;
 	}
 
 	ret = vfs_fallocate(req->ns->file, mode, offset, len);
-	nvmet_req_complete(req, ret < 0 ? NVME_SC_INTERNAL | NVME_SC_DNR : 0);
+	nvmet_req_complete(req, ret < 0 ? errno_to_nvme_status(req, ret) : 0);
 }
 
 static void nvmet_file_execute_write_zeroes(struct nvmet_req *req)
@@ -320,10 +365,7 @@ u16 nvmet_file_parse_io_cmd(struct nvmet_req *req)
 	switch (cmd->common.opcode) {
 	case nvme_cmd_read:
 	case nvme_cmd_write:
-		if (req->ns->buffered_io)
-			req->execute = nvmet_file_execute_rw_buffered_io;
-		else
-			req->execute = nvmet_file_execute_rw;
+		req->execute = nvmet_file_execute_rw;
 		req->data_len = nvmet_rw_len(req);
 		return 0;
 	case nvme_cmd_flush:
@@ -342,6 +384,7 @@ u16 nvmet_file_parse_io_cmd(struct nvmet_req *req)
 	default:
 		pr_err("unhandled cmd for file ns %d on qid %d\n",
 				cmd->common.opcode, req->sq->qid);
+		req->error_loc = offsetof(struct nvme_common_command, opcode);
 		return NVME_SC_INVALID_OPCODE | NVME_SC_DNR;
 	}
 }