@@ -45,6 +45,8 @@
*/
#define SCSI_INLINE_PROT_SG_CNT 1
+#define SCSI_INLINE_SG_CNT 2
+
static struct kmem_cache *scsi_sdb_cache;
static struct kmem_cache *scsi_sense_cache;
static struct kmem_cache *scsi_sense_isadma_cache;
@@ -573,10 +575,18 @@ static inline struct scatterlist *scsi_prot_inline_sg(struct scsi_cmnd *cmd)
return (struct scatterlist *)(cmd->prot_sdb + 1);
}
+static inline struct scatterlist *scsi_inline_sg(struct scsi_cmnd *cmd)
+{
+ return (struct scatterlist *)((void *)cmd +
+ sizeof(struct scsi_cmnd) +
+ cmd->device->host->hostt->cmd_size);
+}
+
static void scsi_mq_free_sgtables(struct scsi_cmnd *cmd)
{
- if (cmd->sdb.table.nents)
- sg_free_table_chained(&cmd->sdb.table, true);
+ if (cmd->sdb.table.nents && cmd->sdb.table.sgl !=
+ scsi_inline_sg(cmd))
+ sg_free_table_chained(&cmd->sdb.table, false);
if (scsi_prot_sg_count(cmd) && cmd->prot_sdb->table.sgl !=
scsi_prot_inline_sg(cmd))
sg_free_table_chained(&cmd->prot_sdb->table, false);
@@ -1008,12 +1018,17 @@ static blk_status_t scsi_init_sgtable(struct request *req,
struct scsi_data_buffer *sdb)
{
int count;
+ unsigned nr_segs = blk_rq_nr_phys_segments(req);
/*
* If sg table allocation fails, requeue request later.
*/
- if (unlikely(sg_alloc_table_chained(&sdb->table,
- blk_rq_nr_phys_segments(req), sdb->table.sgl)))
+ if (nr_segs <= SCSI_INLINE_SG_CNT) {
+ scsi_init_inline_sg_table(&sdb->table, scsi_inline_sg(
+ blk_mq_rq_to_pdu(req)),
+ SCSI_INLINE_SG_CNT);
+ } else if (unlikely(sg_alloc_table_chained(&sdb->table, nr_segs,
+ NULL)))
return BLK_STS_RESOURCE;
/*
@@ -1581,9 +1596,9 @@ static int scsi_dispatch_cmd(struct scsi_cmnd *cmd)
}
/* Size in bytes of the sg-list stored in the scsi-mq command-private data. */
-static unsigned int scsi_mq_sgl_size(struct Scsi_Host *shost)
+static unsigned int scsi_mq_inline_sgl_size(struct Scsi_Host *shost)
{
- return min_t(unsigned int, shost->sg_tablesize, SG_CHUNK_SIZE) *
+ return min_t(unsigned int, shost->sg_tablesize, SCSI_INLINE_SG_CNT) *
sizeof(struct scatterlist);
}
@@ -1592,7 +1607,6 @@ static blk_status_t scsi_mq_prep_fn(struct request *req)
struct scsi_cmnd *cmd = blk_mq_rq_to_pdu(req);
struct scsi_device *sdev = req->q->queuedata;
struct Scsi_Host *shost = sdev->host;
- struct scatterlist *sg;
scsi_init_command(sdev, cmd);
@@ -1600,9 +1614,6 @@ static blk_status_t scsi_mq_prep_fn(struct request *req)
cmd->tag = req->tag;
cmd->prot_op = SCSI_PROT_NORMAL;
- sg = (void *)cmd + sizeof(struct scsi_cmnd) + shost->hostt->cmd_size;
- cmd->sdb.table.sgl = sg;
-
if (scsi_host_get_prot(shost))
memset(cmd->prot_sdb, 0, sizeof(struct scsi_data_buffer));
@@ -1769,7 +1780,7 @@ static int scsi_mq_init_request(struct blk_mq_tag_set *set, struct request *rq,
if (scsi_host_get_prot(shost)) {
sg = (void *)cmd + sizeof(struct scsi_cmnd) +
shost->hostt->cmd_size;
- cmd->prot_sdb = (void *)sg + scsi_mq_sgl_size(shost);
+ cmd->prot_sdb = (void *)sg + scsi_mq_inline_sgl_size(shost);
}
return 0;
@@ -1863,7 +1874,7 @@ int scsi_mq_setup_tags(struct Scsi_Host *shost)
{
unsigned int cmd_size, sgl_size;
- sgl_size = scsi_mq_sgl_size(shost);
+ sgl_size = scsi_mq_inline_sgl_size(shost);
cmd_size = sizeof(struct scsi_cmnd) + shost->hostt->cmd_size + sgl_size;
if (scsi_host_get_prot(shost))
cmd_size += sizeof(struct scsi_data_buffer) +
Now scsi_mq_setup_tags() pre-allocates a big buffer for IO sg list, and the buffer size is scsi_mq_sgl_size() which depends on smaller value between shost->sg_tablesize and SG_CHUNK_SIZE. Modern HBA's DMA is often capable of deadling with very big segment number, so scsi_mq_sgl_size() is often big. Suppose the max sg number of SG_CHUNK_SIZE is taken, scsi_mq_sgl_size() will be 4KB. Then if one HBA has lots of queues, and each hw queue's depth is high, pre-allocation for sg list can consume huge memory. For example of lpfc, nr_hw_queues can be 70, each queue's depth can be 3781, so the pre-allocation for data sg list is 70*3781*2k =517MB for single HBA. There is Red Hat internal report that scsi_debug based tests can't be run any more since legacy io path is killed because too big pre-allocation. So switch to runtime allocation for sg list, meantime pre-allocate 2 inline sg entries. This way has been applied to NVMe PCI for a while, so it should be fine for SCSI too. Also runtime sg entries allocation has verified and run always in the original legacy io path. Not see performance effect in my big BS test on scsi_debug. Cc: Christoph Hellwig <hch@lst.de> Cc: Bart Van Assche <bvanassche@acm.org> Cc: Ewan D. Milne <emilne@redhat.com> Cc: Hannes Reinecke <hare@suse.com> Signed-off-by: Ming Lei <ming.lei@redhat.com> --- drivers/scsi/scsi_lib.c | 35 +++++++++++++++++++++++------------ 1 file changed, 23 insertions(+), 12 deletions(-)