1 files changed, 157 insertions, 27 deletions

diff --git a/kernel/drivers/scsi/sd.c b/kernel/drivers/scsi/sd.c
index 11ea52b2c..bb669d32c 100644
--- a/kernel/drivers/scsi/sd.c
+++ b/kernel/drivers/scsi/sd.c
@@ -51,6 +51,7 @@
 #include <linux/async.h>
 #include <linux/slab.h>
 #include <linux/pm_runtime.h>
+#include <linux/pr.h>
 #include <asm/uaccess.h>
 #include <asm/unaligned.h>
 
@@ -204,6 +205,7 @@ cache_type_store(struct device *dev, struct device_attribute *attr,
 	buffer_data[2] &= ~0x05;
 	buffer_data[2] |= wce << 2 | rcd;
 	sp = buffer_data[0] & 0x80 ? 1 : 0;
+	buffer_data[0] &= ~0x80;
 
 	if (scsi_mode_select(sdp, 1, sp, 8, buffer_data, len, SD_TIMEOUT,
 			     SD_MAX_RETRIES, &data, &sshdr)) {
@@ -636,18 +638,31 @@ static void sd_config_discard(struct scsi_disk *sdkp, unsigned int mode)
 	unsigned int max_blocks = 0;
 
 	q->limits.discard_zeroes_data = 0;
-	q->limits.discard_alignment = sdkp->unmap_alignment *
-		logical_block_size;
-	q->limits.discard_granularity =
-		max(sdkp->physical_block_size,
-		    sdkp->unmap_granularity * logical_block_size);
+
+	/*
+	 * When LBPRZ is reported, discard alignment and granularity
+	 * must be fixed to the logical block size. Otherwise the block
+	 * layer will drop misaligned portions of the request which can
+	 * lead to data corruption. If LBPRZ is not set, we honor the
+	 * device preference.
+	 */
+	if (sdkp->lbprz) {
+		q->limits.discard_alignment = 0;
+		q->limits.discard_granularity = 1;
+	} else {
+		q->limits.discard_alignment = sdkp->unmap_alignment *
+			logical_block_size;
+		q->limits.discard_granularity =
+			max(sdkp->physical_block_size,
+			    sdkp->unmap_granularity * logical_block_size);
+	}
 
 	sdkp->provisioning_mode = mode;
 
 	switch (mode) {
 
 	case SD_LBP_DISABLE:
-		q->limits.max_discard_sectors = 0;
+		blk_queue_max_discard_sectors(q, 0);
 		queue_flag_clear_unlocked(QUEUE_FLAG_DISCARD, q);
 		return;
 
@@ -675,7 +690,7 @@ static void sd_config_discard(struct scsi_disk *sdkp, unsigned int mode)
 		break;
 	}
 
-	q->limits.max_discard_sectors = max_blocks * (logical_block_size >> 9);
+	blk_queue_max_discard_sectors(q, max_blocks * (logical_block_size >> 9));
 	queue_flag_set_unlocked(QUEUE_FLAG_DISCARD, q);
 }
 
@@ -1535,6 +1550,100 @@ static int sd_compat_ioctl(struct block_device *bdev, fmode_t mode,
 }
 #endif
 
+static char sd_pr_type(enum pr_type type)
+{
+	switch (type) {
+	case PR_WRITE_EXCLUSIVE:
+		return 0x01;
+	case PR_EXCLUSIVE_ACCESS:
+		return 0x03;
+	case PR_WRITE_EXCLUSIVE_REG_ONLY:
+		return 0x05;
+	case PR_EXCLUSIVE_ACCESS_REG_ONLY:
+		return 0x06;
+	case PR_WRITE_EXCLUSIVE_ALL_REGS:
+		return 0x07;
+	case PR_EXCLUSIVE_ACCESS_ALL_REGS:
+		return 0x08;
+	default:
+		return 0;
+	}
+};
+
+static int sd_pr_command(struct block_device *bdev, u8 sa,
+		u64 key, u64 sa_key, u8 type, u8 flags)
+{
+	struct scsi_device *sdev = scsi_disk(bdev->bd_disk)->device;
+	struct scsi_sense_hdr sshdr;
+	int result;
+	u8 cmd[16] = { 0, };
+	u8 data[24] = { 0, };
+
+	cmd[0] = PERSISTENT_RESERVE_OUT;
+	cmd[1] = sa;
+	cmd[2] = type;
+	put_unaligned_be32(sizeof(data), &cmd[5]);
+
+	put_unaligned_be64(key, &data[0]);
+	put_unaligned_be64(sa_key, &data[8]);
+	data[20] = flags;
+
+	result = scsi_execute_req(sdev, cmd, DMA_TO_DEVICE, &data, sizeof(data),
+			&sshdr, SD_TIMEOUT, SD_MAX_RETRIES, NULL);
+
+	if ((driver_byte(result) & DRIVER_SENSE) &&
+	    (scsi_sense_valid(&sshdr))) {
+		sdev_printk(KERN_INFO, sdev, "PR command failed: %d\n", result);
+		scsi_print_sense_hdr(sdev, NULL, &sshdr);
+	}
+
+	return result;
+}
+
+static int sd_pr_register(struct block_device *bdev, u64 old_key, u64 new_key,
+		u32 flags)
+{
+	if (flags & ~PR_FL_IGNORE_KEY)
+		return -EOPNOTSUPP;
+	return sd_pr_command(bdev, (flags & PR_FL_IGNORE_KEY) ? 0x06 : 0x00,
+			old_key, new_key, 0,
+			(1 << 0) /* APTPL */ |
+			(1 << 2) /* ALL_TG_PT */);
+}
+
+static int sd_pr_reserve(struct block_device *bdev, u64 key, enum pr_type type,
+		u32 flags)
+{
+	if (flags)
+		return -EOPNOTSUPP;
+	return sd_pr_command(bdev, 0x01, key, 0, sd_pr_type(type), 0);
+}
+
+static int sd_pr_release(struct block_device *bdev, u64 key, enum pr_type type)
+{
+	return sd_pr_command(bdev, 0x02, key, 0, sd_pr_type(type), 0);
+}
+
+static int sd_pr_preempt(struct block_device *bdev, u64 old_key, u64 new_key,
+		enum pr_type type, bool abort)
+{
+	return sd_pr_command(bdev, abort ? 0x05 : 0x04, old_key, new_key,
+			     sd_pr_type(type), 0);
+}
+
+static int sd_pr_clear(struct block_device *bdev, u64 key)
+{
+	return sd_pr_command(bdev, 0x03, key, 0, 0, 0);
+}
+
+static const struct pr_ops sd_pr_ops = {
+	.pr_register	= sd_pr_register,
+	.pr_reserve	= sd_pr_reserve,
+	.pr_release	= sd_pr_release,
+	.pr_preempt	= sd_pr_preempt,
+	.pr_clear	= sd_pr_clear,
+};
+
 static const struct block_device_operations sd_fops = {
 	.owner			= THIS_MODULE,
 	.open			= sd_open,
@@ -1547,6 +1656,7 @@ static const struct block_device_operations sd_fops = {
 	.check_events		= sd_check_events,
 	.revalidate_disk	= sd_revalidate_disk,
 	.unlock_native_capacity	= sd_unlock_native_capacity,
+	.pr_ops			= &sd_pr_ops,
 };
 
 /**
@@ -2224,11 +2334,8 @@ got_data:
 		}
 	}
 
-	if (sdkp->capacity > 0xffffffff) {
+	if (sdkp->capacity > 0xffffffff)
 		sdp->use_16_for_rw = 1;
-		sdkp->max_xfer_blocks = SD_MAX_XFER_BLOCKS;
-	} else
-		sdkp->max_xfer_blocks = SD_DEF_XFER_BLOCKS;
 
 	/* Rescale capacity to 512-byte units */
 	if (sector_size == 4096)
@@ -2545,7 +2652,6 @@ static void sd_read_block_limits(struct scsi_disk *sdkp)
 {
 	unsigned int sector_sz = sdkp->device->sector_size;
 	const int vpd_len = 64;
-	u32 max_xfer_length;
 	unsigned char *buffer = kmalloc(vpd_len, GFP_KERNEL);
 
 	if (!buffer ||
@@ -2553,14 +2659,11 @@ static void sd_read_block_limits(struct scsi_disk *sdkp)
 	    scsi_get_vpd_page(sdkp->device, 0xb0, buffer, vpd_len))
 		goto out;
 
-	max_xfer_length = get_unaligned_be32(&buffer[8]);
-	if (max_xfer_length)
-		sdkp->max_xfer_blocks = max_xfer_length;
-
 	blk_queue_io_min(sdkp->disk->queue,
 			 get_unaligned_be16(&buffer[6]) * sector_sz);
-	blk_queue_io_opt(sdkp->disk->queue,
-			 get_unaligned_be32(&buffer[12]) * sector_sz);
+
+	sdkp->max_xfer_blocks = get_unaligned_be32(&buffer[8]);
+	sdkp->opt_xfer_blocks = get_unaligned_be32(&buffer[12]);
 
 	if (buffer[3] == 0x3c) {
 		unsigned int lba_count, desc_count;
@@ -2709,6 +2812,11 @@ static int sd_try_extended_inquiry(struct scsi_device *sdp)
 	return 0;
 }
 
+static inline u32 logical_to_sectors(struct scsi_device *sdev, u32 blocks)
+{
+	return blocks << (ilog2(sdev->sector_size) - 9);
+}
+
 /**
  *	sd_revalidate_disk - called the first time a new disk is seen,
  *	performs disk spin up, read_capacity, etc.
@@ -2718,8 +2826,9 @@ static int sd_revalidate_disk(struct gendisk *disk)
 {
 	struct scsi_disk *sdkp = scsi_disk(disk);
 	struct scsi_device *sdp = sdkp->device;
+	struct request_queue *q = sdkp->disk->queue;
 	unsigned char *buffer;
-	unsigned int max_xfer;
+	unsigned int dev_max, rw_max;
 
 	SCSI_LOG_HLQUEUE(3, sd_printk(KERN_INFO, sdkp,
 				      "sd_revalidate_disk\n"));
@@ -2767,11 +2876,29 @@ static int sd_revalidate_disk(struct gendisk *disk)
 	 */
 	sd_set_flush_flag(sdkp);
 
-	max_xfer = sdkp->max_xfer_blocks;
-	max_xfer <<= ilog2(sdp->sector_size) - 9;
+	/* Initial block count limit based on CDB TRANSFER LENGTH field size. */
+	dev_max = sdp->use_16_for_rw ? SD_MAX_XFER_BLOCKS : SD_DEF_XFER_BLOCKS;
+
+	/* Some devices report a maximum block count for READ/WRITE requests. */
+	dev_max = min_not_zero(dev_max, sdkp->max_xfer_blocks);
+	q->limits.max_dev_sectors = logical_to_sectors(sdp, dev_max);
 
-	sdkp->disk->queue->limits.max_sectors =
-		min_not_zero(queue_max_hw_sectors(sdkp->disk->queue), max_xfer);
+	/*
+	 * Use the device's preferred I/O size for reads and writes
+	 * unless the reported value is unreasonably small, large, or
+	 * garbage.
+	 */
+	if (sdkp->opt_xfer_blocks &&
+	    sdkp->opt_xfer_blocks <= dev_max &&
+	    sdkp->opt_xfer_blocks <= SD_DEF_XFER_BLOCKS &&
+	    sdkp->opt_xfer_blocks * sdp->sector_size >= PAGE_CACHE_SIZE)
+		rw_max = q->limits.io_opt =
+			sdkp->opt_xfer_blocks * sdp->sector_size;
+	else
+		rw_max = BLK_DEF_MAX_SECTORS;
+
+	/* Combine with controller limits */
+	q->limits.max_sectors = min(rw_max, queue_max_hw_sectors(q));
 
 	set_capacity(disk, sdkp->capacity);
 	sd_config_write_same(sdkp);
@@ -2988,7 +3115,8 @@ static int sd_probe(struct device *dev)
 	sdkp->dev.class = &sd_disk_class;
 	dev_set_name(&sdkp->dev, "%s", dev_name(dev));
 
-	if (device_add(&sdkp->dev))
+	error = device_add(&sdkp->dev);
+	if (error)
 		goto out_free_index;
 
 	get_device(dev);
@@ -3067,7 +3195,6 @@ static void scsi_disk_release(struct device *dev)
 	ida_remove(&sd_index_ida, sdkp->index);
 	spin_unlock(&sd_index_lock);
 
-	blk_integrity_unregister(disk);
 	disk->private_data = NULL;
 	put_disk(disk);
 	put_device(&sdkp->device->sdev_gendev);
@@ -3141,8 +3268,8 @@ static int sd_suspend_common(struct device *dev, bool ignore_stop_errors)
 	struct scsi_disk *sdkp = dev_get_drvdata(dev);
 	int ret = 0;
 
-	if (!sdkp)
-		return 0;	/* this can happen */
+	if (!sdkp)	/* E.g.: runtime suspend following sd_remove() */
+		return 0;
 
 	if (sdkp->WCE && sdkp->media_present) {
 		sd_printk(KERN_NOTICE, sdkp, "Synchronizing SCSI cache\n");
@@ -3181,6 +3308,9 @@ static int sd_resume(struct device *dev)
 {
 	struct scsi_disk *sdkp = dev_get_drvdata(dev);
 
+	if (!sdkp)	/* E.g.: runtime resume at the start of sd_probe() */
+		return 0;
+
 	if (!sdkp->device->manage_start_stop)
 		return 0;