From: Swarna Prabhu <sw.prabhu6@gmail.com>

The WRITE SAME(16) and WRITE SAME(10) scsi commands uses
a page from a dedicated mempool('sd_page_pool') for its
payload. This pool was initialized to allocate single
pages, which was sufficient as long as the device sector
size did not exceed the PAGE_SIZE.

Given that block layer now supports block size upto
64K ie beyond PAGE_SIZE, initialize large page pool in
'sd_probe()' if a higher sector device is attached ensuring
atomicity. Adapt 'sd_set_special_bvec()' to use large page
pool when a higher sector size device is attached.

With the above fix, enable sector sizes > PAGE_SIZE in
scsi sd driver.

Cc: stable@vger.kernel.org
Signed-off-by: Swarna Prabhu <s.prabhu@samsung.com>
Co-developed-by: Pankaj Raghav <p.raghav@samsung.com>
Signed-off-by: Pankaj Raghav <p.raghav@samsung.com>
---
 drivers/scsi/sd.c | 79 ++++++++++++++++++++++++++++++++++++++++-------
 1 file changed, 67 insertions(+), 12 deletions(-)

diff --git a/drivers/scsi/sd.c b/drivers/scsi/sd.c
index f50b92e63201..0e0c5dd1c668 100644
--- a/drivers/scsi/sd.c
+++ b/drivers/scsi/sd.c
@@ -112,8 +112,11 @@ static void sd_shutdown(struct device *);
 static void scsi_disk_release(struct device *cdev);
 
 static DEFINE_IDA(sd_index_ida);
+static DEFINE_MUTEX(sd_mutex_lock);
 
 static mempool_t *sd_page_pool;
+static mempool_t *sd_large_page_pool;
+static atomic_t sd_large_page_pool_users = ATOMIC_INIT(0);
 static struct lock_class_key sd_bio_compl_lkclass;
 
 static const char *sd_cache_types[] = {
@@ -922,14 +925,27 @@ static void sd_config_discard(struct scsi_disk *sdkp, struct queue_limits *lim,
 		(logical_block_size >> SECTOR_SHIFT);
 }
 
-static void *sd_set_special_bvec(struct request *rq, unsigned int data_len)
+static void *sd_set_special_bvec(struct scsi_cmnd *cmd, unsigned int data_len)
 {
 	struct page *page;
+	struct request *rq = scsi_cmd_to_rq(cmd);
+	struct scsi_device *sdp = cmd->device;
+	unsigned sector_size = sdp->sector_size;
+	unsigned int nr_pages = DIV_ROUND_UP(sector_size, PAGE_SIZE);
+	int n = 0;
 
-	page = mempool_alloc(sd_page_pool, GFP_ATOMIC);
+	if (sector_size > PAGE_SIZE)
+		page = mempool_alloc(sd_large_page_pool, GFP_ATOMIC);
+	else
+		page = mempool_alloc(sd_page_pool, GFP_ATOMIC);
 	if (!page)
 		return NULL;
-	clear_highpage(page);
+
+	do {
+		clear_highpage(page + n);
+		n++;
+	} while (n < nr_pages);
+
 	bvec_set_page(&rq->special_vec, page, data_len, 0);
 	rq->rq_flags |= RQF_SPECIAL_PAYLOAD;
 	return bvec_virt(&rq->special_vec);
@@ -945,7 +961,7 @@ static blk_status_t sd_setup_unmap_cmnd(struct scsi_cmnd *cmd)
 	unsigned int data_len = 24;
 	char *buf;
 
-	buf = sd_set_special_bvec(rq, data_len);
+	buf = sd_set_special_bvec(cmd, data_len);
 	if (!buf)
 		return BLK_STS_RESOURCE;
 
@@ -1034,7 +1050,7 @@ static blk_status_t sd_setup_write_same16_cmnd(struct scsi_cmnd *cmd,
 	u32 nr_blocks = sectors_to_logical(sdp, blk_rq_sectors(rq));
 	u32 data_len = sdp->sector_size;
 
-	if (!sd_set_special_bvec(rq, data_len))
+	if (!sd_set_special_bvec(cmd, data_len))
 		return BLK_STS_RESOURCE;
 
 	cmd->cmd_len = 16;
@@ -1061,7 +1077,7 @@ static blk_status_t sd_setup_write_same10_cmnd(struct scsi_cmnd *cmd,
 	u32 nr_blocks = sectors_to_logical(sdp, blk_rq_sectors(rq));
 	u32 data_len = sdp->sector_size;
 
-	if (!sd_set_special_bvec(rq, data_len))
+	if (!sd_set_special_bvec(cmd, data_len))
 		return BLK_STS_RESOURCE;
 
 	cmd->cmd_len = 10;
@@ -1507,9 +1523,15 @@ static blk_status_t sd_init_command(struct scsi_cmnd *cmd)
 static void sd_uninit_command(struct scsi_cmnd *SCpnt)
 {
 	struct request *rq = scsi_cmd_to_rq(SCpnt);
+	struct scsi_device *sdp = SCpnt->device;
+	unsigned sector_size = sdp->sector_size;
 
-	if (rq->rq_flags & RQF_SPECIAL_PAYLOAD)
-		mempool_free(rq->special_vec.bv_page, sd_page_pool);
+	if (rq->rq_flags & RQF_SPECIAL_PAYLOAD) {
+		if (sector_size > PAGE_SIZE)
+			mempool_free(rq->special_vec.bv_page, sd_large_page_pool);
+		else
+			mempool_free(rq->special_vec.bv_page, sd_page_pool);
+	}
 }
 
 static bool sd_need_revalidate(struct gendisk *disk, struct scsi_disk *sdkp)
@@ -2920,10 +2942,7 @@ sd_read_capacity(struct scsi_disk *sdkp, struct queue_limits *lim,
 			  "assuming 512.\n");
 	}
 
-	if (sector_size != 512 &&
-	    sector_size != 1024 &&
-	    sector_size != 2048 &&
-	    sector_size != 4096) {
+	if (blk_validate_block_size(sector_size)) {
 		sd_printk(KERN_NOTICE, sdkp, "Unsupported sector size %d.\n",
 			  sector_size);
 		/*
@@ -4044,6 +4063,21 @@ static int sd_probe(struct device *dev)
 	sdkp->max_medium_access_timeouts = SD_MAX_MEDIUM_TIMEOUTS;
 
 	sd_revalidate_disk(gd);
+	if (sdp->sector_size > PAGE_SIZE) {
+		mutex_lock(&sd_mutex_lock);
+		if (!sd_large_page_pool) {
+			sd_large_page_pool = mempool_create_page_pool(
+					SD_MEMPOOL_SIZE, get_order(BLK_MAX_BLOCK_SIZE));
+			if (!sd_large_page_pool) {
+				printk(KERN_ERR "sd: can't create large page mempool\n");
+				error = -ENOMEM;
+				mutex_unlock(&sd_mutex_lock);
+				goto out_free_index;
+			}
+		}
+		atomic_inc(&sd_large_page_pool_users);
+		mutex_unlock(&sd_mutex_lock);
+	}
 
 	if (sdp->removable) {
 		gd->flags |= GENHD_FL_REMOVABLE;
@@ -4061,6 +4095,14 @@ static int sd_probe(struct device *dev)
 	if (error) {
 		device_unregister(&sdkp->disk_dev);
 		put_disk(gd);
+		if (sdp->sector_size > PAGE_SIZE) {
+			mutex_lock(&sd_mutex_lock);
+			if (atomic_dec_and_test(&sd_large_page_pool_users)) {
+				mempool_destroy(sd_large_page_pool);
+				sd_large_page_pool = NULL;
+			}
+			mutex_unlock(&sd_mutex_lock);
+		}
 		goto out;
 	}
 
@@ -4101,6 +4143,7 @@ static int sd_probe(struct device *dev)
 static int sd_remove(struct device *dev)
 {
 	struct scsi_disk *sdkp = dev_get_drvdata(dev);
+	struct scsi_device *sdp = sdkp->device;
 
 	scsi_autopm_get_device(sdkp->device);
 
@@ -4110,6 +4153,16 @@ static int sd_remove(struct device *dev)
 		sd_shutdown(dev);
 
 	put_disk(sdkp->disk);
+
+	if (sdp->sector_size > PAGE_SIZE) {
+		mutex_lock(&sd_mutex_lock);
+		if (atomic_dec_and_test(&sd_large_page_pool_users)) {
+			mempool_destroy(sd_large_page_pool);
+			sd_large_page_pool = NULL;
+		}
+		mutex_unlock(&sd_mutex_lock);
+	}
+
 	return 0;
 }
 
@@ -4446,6 +4499,8 @@ static void __exit exit_sd(void)
 
 	scsi_unregister_driver(&sd_template.gendrv);
 	mempool_destroy(sd_page_pool);
+	if (sd_large_page_pool)
+		mempool_destroy(sd_large_page_pool);
 
 	class_unregister(&sd_disk_class);
 
-- 
2.39.5

On 2/11/26 10:50, sw.prabhu6@gmail.com wrote:
> From: Swarna Prabhu <sw.prabhu6@gmail.com>
> 
> The WRITE SAME(16) and WRITE SAME(10) scsi commands uses
> a page from a dedicated mempool('sd_page_pool') for its
> payload. This pool was initialized to allocate single
> pages, which was sufficient as long as the device sector
> size did not exceed the PAGE_SIZE.
> 
> Given that block layer now supports block size upto
> 64K ie beyond PAGE_SIZE, initialize large page pool in
> 'sd_probe()' if a higher sector device is attached ensuring
> atomicity. Adapt 'sd_set_special_bvec()' to use large page
> pool when a higher sector size device is attached.
> 
> With the above fix, enable sector sizes > PAGE_SIZE in
> scsi sd driver.

This is not a fix (as in a bug fix) but rather a new feature.

> Cc: stable@vger.kernel.org

Why ? Before this patch, scsi allows only up to 4K sector size, which is not >
PAGE_SIZE.

> Signed-off-by: Swarna Prabhu <s.prabhu@samsung.com>
> Co-developed-by: Pankaj Raghav <p.raghav@samsung.com>
> Signed-off-by: Pankaj Raghav <p.raghav@samsung.com>
> ---
>  drivers/scsi/sd.c | 79 ++++++++++++++++++++++++++++++++++++++++-------
>  1 file changed, 67 insertions(+), 12 deletions(-)
> 
> diff --git a/drivers/scsi/sd.c b/drivers/scsi/sd.c
> index f50b92e63201..0e0c5dd1c668 100644
> --- a/drivers/scsi/sd.c
> +++ b/drivers/scsi/sd.c
> @@ -112,8 +112,11 @@ static void sd_shutdown(struct device *);
>  static void scsi_disk_release(struct device *cdev);
>  
>  static DEFINE_IDA(sd_index_ida);
> +static DEFINE_MUTEX(sd_mutex_lock);
>  
>  static mempool_t *sd_page_pool;
> +static mempool_t *sd_large_page_pool;
> +static atomic_t sd_large_page_pool_users = ATOMIC_INIT(0);
>  static struct lock_class_key sd_bio_compl_lkclass;
>  
>  static const char *sd_cache_types[] = {
> @@ -922,14 +925,27 @@ static void sd_config_discard(struct scsi_disk *sdkp, struct queue_limits *lim,
>  		(logical_block_size >> SECTOR_SHIFT);
>  }
>  
> -static void *sd_set_special_bvec(struct request *rq, unsigned int data_len)
> +static void *sd_set_special_bvec(struct scsi_cmnd *cmd, unsigned int data_len)
>  {
>  	struct page *page;
> +	struct request *rq = scsi_cmd_to_rq(cmd);
> +	struct scsi_device *sdp = cmd->device;
> +	unsigned sector_size = sdp->sector_size;
> +	unsigned int nr_pages = DIV_ROUND_UP(sector_size, PAGE_SIZE);
> +	int n = 0;
>  
> -	page = mempool_alloc(sd_page_pool, GFP_ATOMIC);
> +	if (sector_size > PAGE_SIZE)
> +		page = mempool_alloc(sd_large_page_pool, GFP_ATOMIC);
> +	else
> +		page = mempool_alloc(sd_page_pool, GFP_ATOMIC);
>  	if (!page)
>  		return NULL;
> -	clear_highpage(page);
> +
> +	do {
> +		clear_highpage(page + n);
> +		n++;
> +	} while (n < nr_pages);

A for loop would be a lot cleaner and simpler.

> +
>  	bvec_set_page(&rq->special_vec, page, data_len, 0);
>  	rq->rq_flags |= RQF_SPECIAL_PAYLOAD;
>  	return bvec_virt(&rq->special_vec);
> @@ -945,7 +961,7 @@ static blk_status_t sd_setup_unmap_cmnd(struct scsi_cmnd *cmd)
>  	unsigned int data_len = 24;
>  	char *buf;
>  
> -	buf = sd_set_special_bvec(rq, data_len);
> +	buf = sd_set_special_bvec(cmd, data_len);
>  	if (!buf)
>  		return BLK_STS_RESOURCE;
>  
> @@ -1034,7 +1050,7 @@ static blk_status_t sd_setup_write_same16_cmnd(struct scsi_cmnd *cmd,
>  	u32 nr_blocks = sectors_to_logical(sdp, blk_rq_sectors(rq));
>  	u32 data_len = sdp->sector_size;
>  
> -	if (!sd_set_special_bvec(rq, data_len))
> +	if (!sd_set_special_bvec(cmd, data_len))
>  		return BLK_STS_RESOURCE;
>  
>  	cmd->cmd_len = 16;
> @@ -1061,7 +1077,7 @@ static blk_status_t sd_setup_write_same10_cmnd(struct scsi_cmnd *cmd,
>  	u32 nr_blocks = sectors_to_logical(sdp, blk_rq_sectors(rq));
>  	u32 data_len = sdp->sector_size;
>  
> -	if (!sd_set_special_bvec(rq, data_len))
> +	if (!sd_set_special_bvec(cmd, data_len))
>  		return BLK_STS_RESOURCE;
>  
>  	cmd->cmd_len = 10;
> @@ -1507,9 +1523,15 @@ static blk_status_t sd_init_command(struct scsi_cmnd *cmd)
>  static void sd_uninit_command(struct scsi_cmnd *SCpnt)
>  {
>  	struct request *rq = scsi_cmd_to_rq(SCpnt);
> +	struct scsi_device *sdp = SCpnt->device;
> +	unsigned sector_size = sdp->sector_size;
>  
> -	if (rq->rq_flags & RQF_SPECIAL_PAYLOAD)
> -		mempool_free(rq->special_vec.bv_page, sd_page_pool);
> +	if (rq->rq_flags & RQF_SPECIAL_PAYLOAD) {
> +		if (sector_size > PAGE_SIZE)
> +			mempool_free(rq->special_vec.bv_page, sd_large_page_pool);
> +		else
> +			mempool_free(rq->special_vec.bv_page, sd_page_pool);
> +	}
>  }
>  
>  static bool sd_need_revalidate(struct gendisk *disk, struct scsi_disk *sdkp)
> @@ -2920,10 +2942,7 @@ sd_read_capacity(struct scsi_disk *sdkp, struct queue_limits *lim,
>  			  "assuming 512.\n");
>  	}
>  
> -	if (sector_size != 512 &&
> -	    sector_size != 1024 &&
> -	    sector_size != 2048 &&
> -	    sector_size != 4096) {
> +	if (blk_validate_block_size(sector_size)) {
>  		sd_printk(KERN_NOTICE, sdkp, "Unsupported sector size %d.\n",
>  			  sector_size);
>  		/*
> @@ -4044,6 +4063,21 @@ static int sd_probe(struct device *dev)
>  	sdkp->max_medium_access_timeouts = SD_MAX_MEDIUM_TIMEOUTS;
>  
>  	sd_revalidate_disk(gd);
> +	if (sdp->sector_size > PAGE_SIZE) {
> +		mutex_lock(&sd_mutex_lock);
> +		if (!sd_large_page_pool) {
> +			sd_large_page_pool = mempool_create_page_pool(
> +					SD_MEMPOOL_SIZE, get_order(BLK_MAX_BLOCK_SIZE));
> +			if (!sd_large_page_pool) {
> +				printk(KERN_ERR "sd: can't create large page mempool\n");
> +				error = -ENOMEM;
> +				mutex_unlock(&sd_mutex_lock);
> +				goto out_free_index;
> +			}
> +		}
> +		atomic_inc(&sd_large_page_pool_users);
> +		mutex_unlock(&sd_mutex_lock);
> +	}

It would be a lot nicer to have this defined as a helper function that goes
together with a pool destroy function (see below).

>  
>  	if (sdp->removable) {
>  		gd->flags |= GENHD_FL_REMOVABLE;
> @@ -4061,6 +4095,14 @@ static int sd_probe(struct device *dev)
>  	if (error) {
>  		device_unregister(&sdkp->disk_dev);
>  		put_disk(gd);
> +		if (sdp->sector_size > PAGE_SIZE) {
> +			mutex_lock(&sd_mutex_lock);
> +			if (atomic_dec_and_test(&sd_large_page_pool_users)) {
> +				mempool_destroy(sd_large_page_pool);
> +				sd_large_page_pool = NULL;
> +			}
> +			mutex_unlock(&sd_mutex_lock);
> +		}

This hunk is repeated twice. Make this a helper please.

>  		goto out;
>  	}
>  
> @@ -4101,6 +4143,7 @@ static int sd_probe(struct device *dev)
>  static int sd_remove(struct device *dev)
>  {
>  	struct scsi_disk *sdkp = dev_get_drvdata(dev);
> +	struct scsi_device *sdp = sdkp->device;
>  
>  	scsi_autopm_get_device(sdkp->device);
>  
> @@ -4110,6 +4153,16 @@ static int sd_remove(struct device *dev)
>  		sd_shutdown(dev);
>  
>  	put_disk(sdkp->disk);
> +
> +	if (sdp->sector_size > PAGE_SIZE) {
> +		mutex_lock(&sd_mutex_lock);
> +		if (atomic_dec_and_test(&sd_large_page_pool_users)) {
> +			mempool_destroy(sd_large_page_pool);
> +			sd_large_page_pool = NULL;
> +		}
> +		mutex_unlock(&sd_mutex_lock);
> +	}
> +
>  	return 0;
>  }
>  
> @@ -4446,6 +4499,8 @@ static void __exit exit_sd(void)
>  
>  	scsi_unregister_driver(&sd_template.gendrv);
>  	mempool_destroy(sd_page_pool);
> +	if (sd_large_page_pool)
> +		mempool_destroy(sd_large_page_pool);
>  
>  	class_unregister(&sd_disk_class);
>  


-- 
Damien Le Moal
Western Digital Research