Merge tag 'for-linus-20190715' of git://git.kernel.dk/linux-block

Pull more block updates from Jens Axboe:
 "A later pull request with some followup items. I had some vacation
  coming up to the merge window, so certain things items were delayed a
  bit. This pull request also contains fixes that came in within the
  last few days of the merge window, which I didn't want to push right
  before sending you a pull request.

  This contains:

   - NVMe pull request, mostly fixes, but also a few minor items on the
     feature side that were timing constrained (Christoph et al)

   - Report zones fixes (Damien)

   - Removal of dead code (Damien)

   - Turn on cgroup psi memstall (Josef)

   - block cgroup MAINTAINERS entry (Konstantin)

   - Flush init fix (Josef)

   - blk-throttle low iops timing fix (Konstantin)

   - nbd resize fixes (Mike)

   - nbd 0 blocksize crash fix (Xiubo)

   - block integrity error leak fix (Wenwen)

   - blk-cgroup writeback and priority inheritance fixes (Tejun)"

* tag 'for-linus-20190715' of git://git.kernel.dk/linux-block: (42 commits)
  MAINTAINERS: add entry for block io cgroup
  null_blk: fixup ->report_zones() for !CONFIG_BLK_DEV_ZONED
  block: Limit zone array allocation size
  sd_zbc: Fix report zones buffer allocation
  block: Kill gfp_t argument of blkdev_report_zones()
  block: Allow mapping of vmalloc-ed buffers
  block/bio-integrity: fix a memory leak bug
  nvme: fix NULL deref for fabrics options
  nbd: add netlink reconfigure resize support
  nbd: fix crash when the blksize is zero
  block: Disable write plugging for zoned block devices
  block: Fix elevator name declaration
  block: Remove unused definitions
  nvme: fix regression upon hot device removal and insertion
  blk-throttle: fix zero wait time for iops throttled group
  block: Fix potential overflow in blk_report_zones()
  blkcg: implement REQ_CGROUP_PUNT
  blkcg, writeback: Implement wbc_blkcg_css()
  blkcg, writeback: Add wbc->no_cgroup_owner
  blkcg, writeback: Rename wbc_account_io() to wbc_account_cgroup_owner()
  ...

2 files changed, 77 insertions, 34 deletions

diff --git a/drivers/scsi/sd.h b/drivers/scsi/sd.h
index 5796ace76225..38c50946fc42 100644
--- a/drivers/scsi/sd.h
+++ b/drivers/scsi/sd.h
@@ -213,8 +213,7 @@ extern blk_status_t sd_zbc_setup_reset_cmnd(struct scsi_cmnd *cmd);
 extern void sd_zbc_complete(struct scsi_cmnd *cmd, unsigned int good_bytes,
 			    struct scsi_sense_hdr *sshdr);
 extern int sd_zbc_report_zones(struct gendisk *disk, sector_t sector,
-			       struct blk_zone *zones, unsigned int *nr_zones,
-			       gfp_t gfp_mask);
+			       struct blk_zone *zones, unsigned int *nr_zones);
 
 #else /* CONFIG_BLK_DEV_ZONED */
 
diff --git a/drivers/scsi/sd_zbc.c b/drivers/scsi/sd_zbc.c
index 7334024b64f1..db16c19e05c4 100644
--- a/drivers/scsi/sd_zbc.c
+++ b/drivers/scsi/sd_zbc.c
@@ -9,6 +9,8 @@
  */
 
 #include <linux/blkdev.h>
+#include <linux/vmalloc.h>
+#include <linux/sched/mm.h>
 
 #include <asm/unaligned.h>
 
@@ -50,7 +52,7 @@ static void sd_zbc_parse_report(struct scsi_disk *sdkp, u8 *buf,
 /**
  * sd_zbc_do_report_zones - Issue a REPORT ZONES scsi command.
  * @sdkp: The target disk
- * @buf: Buffer to use for the reply
+ * @buf: vmalloc-ed buffer to use for the reply
  * @buflen: the buffer size
  * @lba: Start LBA of the report
  * @partial: Do partial report
@@ -79,7 +81,6 @@ static int sd_zbc_do_report_zones(struct scsi_disk *sdkp, unsigned char *buf,
 	put_unaligned_be32(buflen, &cmd[10]);
 	if (partial)
 		cmd[14] = ZBC_REPORT_ZONE_PARTIAL;
-	memset(buf, 0, buflen);
 
 	result = scsi_execute_req(sdp, cmd, DMA_FROM_DEVICE,
 				  buf, buflen, &sshdr,
@@ -103,45 +104,83 @@ static int sd_zbc_do_report_zones(struct scsi_disk *sdkp, unsigned char *buf,
 	return 0;
 }
 
+/*
+ * Maximum number of zones to get with one report zones command.
+ */
+#define SD_ZBC_REPORT_MAX_ZONES		8192U
+
+/**
+ * Allocate a buffer for report zones reply.
+ * @sdkp: The target disk
+ * @nr_zones: Maximum number of zones to report
+ * @buflen: Size of the buffer allocated
+ *
+ * Try to allocate a reply buffer for the number of requested zones.
+ * The size of the buffer allocated may be smaller than requested to
+ * satify the device constraint (max_hw_sectors, max_segments, etc).
+ *
+ * Return the address of the allocated buffer and update @buflen with
+ * the size of the allocated buffer.
+ */
+static void *sd_zbc_alloc_report_buffer(struct scsi_disk *sdkp,
+					unsigned int nr_zones, size_t *buflen)
+{
+	struct request_queue *q = sdkp->disk->queue;
+	size_t bufsize;
+	void *buf;
+
+	/*
+	 * Report zone buffer size should be at most 64B times the number of
+	 * zones requested plus the 64B reply header, but should be at least
+	 * SECTOR_SIZE for ATA devices.
+	 * Make sure that this size does not exceed the hardware capabilities.
+	 * Furthermore, since the report zone command cannot be split, make
+	 * sure that the allocated buffer can always be mapped by limiting the
+	 * number of pages allocated to the HBA max segments limit.
+	 */
+	nr_zones = min(nr_zones, SD_ZBC_REPORT_MAX_ZONES);
+	bufsize = roundup((nr_zones + 1) * 64, 512);
+	bufsize = min_t(size_t, bufsize,
+			queue_max_hw_sectors(q) << SECTOR_SHIFT);
+	bufsize = min_t(size_t, bufsize, queue_max_segments(q) << PAGE_SHIFT);
+
+	buf = vzalloc(bufsize);
+	if (buf)
+		*buflen = bufsize;
+
+	return buf;
+}
+
 /**
  * sd_zbc_report_zones - Disk report zones operation.
  * @disk: The target disk
  * @sector: Start 512B sector of the report
  * @zones: Array of zone descriptors
  * @nr_zones: Number of descriptors in the array
- * @gfp_mask: Memory allocation mask
  *
  * Execute a report zones command on the target disk.
  */
 int sd_zbc_report_zones(struct gendisk *disk, sector_t sector,
-			struct blk_zone *zones, unsigned int *nr_zones,
-			gfp_t gfp_mask)
+			struct blk_zone *zones, unsigned int *nr_zones)
 {
 	struct scsi_disk *sdkp = scsi_disk(disk);
-	unsigned int i, buflen, nrz = *nr_zones;
+	unsigned int i, nrz = *nr_zones;
 	unsigned char *buf;
-	size_t offset = 0;
+	size_t buflen = 0, offset = 0;
 	int ret = 0;
 
 	if (!sd_is_zoned(sdkp))
 		/* Not a zoned device */
 		return -EOPNOTSUPP;
 
-	/*
-	 * Get a reply buffer for the number of requested zones plus a header,
-	 * without exceeding the device maximum command size. For ATA disks,
-	 * buffers must be aligned to 512B.
-	 */
-	buflen = min(queue_max_hw_sectors(disk->queue) << 9,
-		     roundup((nrz + 1) * 64, 512));
-	buf = kmalloc(buflen, gfp_mask);
+	buf = sd_zbc_alloc_report_buffer(sdkp, nrz, &buflen);
 	if (!buf)
 		return -ENOMEM;
 
 	ret = sd_zbc_do_report_zones(sdkp, buf, buflen,
 			sectors_to_logical(sdkp->device, sector), true);
 	if (ret)
-		goto out_free_buf;
+		goto out;
 
 	nrz = min(nrz, get_unaligned_be32(&buf[0]) / 64);
 	for (i = 0; i < nrz; i++) {
@@ -152,8 +191,8 @@ int sd_zbc_report_zones(struct gendisk *disk, sector_t sector,
 
 	*nr_zones = nrz;
 
-out_free_buf:
-	kfree(buf);
+out:
+	kvfree(buf);
 
 	return ret;
 }
@@ -287,8 +326,6 @@ static int sd_zbc_check_zoned_characteristics(struct scsi_disk *sdkp,
 	return 0;
 }
 
-#define SD_ZBC_BUF_SIZE 131072U
-
 /**
  * sd_zbc_check_zones - Check the device capacity and zone sizes
  * @sdkp: Target disk
@@ -304,22 +341,28 @@ static int sd_zbc_check_zoned_characteristics(struct scsi_disk *sdkp,
  */
 static int sd_zbc_check_zones(struct scsi_disk *sdkp, u32 *zblocks)
 {
+	size_t bufsize, buflen;
+	unsigned int noio_flag;
 	u64 zone_blocks = 0;
 	sector_t max_lba, block = 0;
 	unsigned char *buf;
 	unsigned char *rec;
-	unsigned int buf_len;
-	unsigned int list_length;
 	int ret;
 	u8 same;
 
+	/* Do all memory allocations as if GFP_NOIO was specified */
+	noio_flag = memalloc_noio_save();
+
 	/* Get a buffer */
-	buf = kmalloc(SD_ZBC_BUF_SIZE, GFP_KERNEL);
-	if (!buf)
-		return -ENOMEM;
+	buf = sd_zbc_alloc_report_buffer(sdkp, SD_ZBC_REPORT_MAX_ZONES,
+					 &bufsize);
+	if (!buf) {
+		ret = -ENOMEM;
+		goto out;
+	}
 
 	/* Do a report zone to get max_lba and the same field */
-	ret = sd_zbc_do_report_zones(sdkp, buf, SD_ZBC_BUF_SIZE, 0, false);
+	ret = sd_zbc_do_report_zones(sdkp, buf, bufsize, 0, false);
 	if (ret)
 		goto out_free;
 
@@ -355,12 +398,12 @@ static int sd_zbc_check_zones(struct scsi_disk *sdkp, u32 *zblocks)
 	do {
 
 		/* Parse REPORT ZONES header */
-		list_length = get_unaligned_be32(&buf[0]) + 64;
+		buflen = min_t(size_t, get_unaligned_be32(&buf[0]) + 64,
+			       bufsize);
 		rec = buf + 64;
-		buf_len = min(list_length, SD_ZBC_BUF_SIZE);
 
 		/* Parse zone descriptors */
-		while (rec < buf + buf_len) {
+		while (rec < buf + buflen) {
 			u64 this_zone_blocks = get_unaligned_be64(&rec[8]);
 
 			if (zone_blocks == 0) {
@@ -376,8 +419,8 @@ static int sd_zbc_check_zones(struct scsi_disk *sdkp, u32 *zblocks)
 		}
 
 		if (block < sdkp->capacity) {
-			ret = sd_zbc_do_report_zones(sdkp, buf, SD_ZBC_BUF_SIZE,
-						     block, true);
+			ret = sd_zbc_do_report_zones(sdkp, buf, bufsize, block,
+						     true);
 			if (ret)
 				goto out_free;
 		}
@@ -408,7 +451,8 @@ out:
 	}
 
 out_free:
-	kfree(buf);
+	memalloc_noio_restore(noio_flag);
+	kvfree(buf);
 
 	return ret;
 }