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 capabilty 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
big, the whole 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 can be 70*3781*2k
=517MB for single HBA.
Also there is Red Hat internal reprot that scsi_debug based tests can't
be run any more since legacy io path is killed because too big
pre-allocation.
This patch switchs to runtime allocation for sg list, meantime
pre-allocate 2 inline sg entries. This way has been applied to
NVMe for a while, so it should be fine for SCSI too.
Cc: Christoph Hellwig <hch@xxxxxx>
Cc: Bart Van Assche <bvanassche@xxxxxxx>
Cc: Ewan D. Milne <emilne@xxxxxxxxxx>
Cc: Hannes Reinecke <hare@xxxxxxxx>
Signed-off-by: Ming Lei <ming.lei@xxxxxxxxxx>
---
drivers/scsi/scsi_lib.c | 30 ++++++++++++++++++++++--------
1 file changed, 22 insertions(+), 8 deletions(-)
diff --git a/drivers/scsi/scsi_lib.c b/drivers/scsi/scsi_lib.c
index bdcf40851356..4fff95b14c91 100644
--- a/drivers/scsi/scsi_lib.c
+++ b/drivers/scsi/scsi_lib.c
@@ -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;
@@ -568,10 +570,18 @@ static inline bool scsi_prot_use_inline_sg(struct scsi_cmnd *cmd)
(struct scatterlist *)(cmd->prot_sdb + 1);
}
+static bool scsi_use_inline_sg(struct scsi_cmnd *cmd)
+{
+ struct scatterlist *sg = (void *)cmd + sizeof(struct scsi_cmnd) +
+ cmd->device->host->hostt->cmd_size;
+
+ return cmd->sdb.table.sgl == sg;
+}
+
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 && !scsi_use_inline_sg(cmd))
+ sg_free_table_chained(&cmd->sdb.table, false);
if (scsi_prot_sg_count(cmd) && !scsi_prot_use_inline_sg(cmd))
sg_free_table_chained(&cmd->prot_sdb->table, false);
}
@@ -1002,12 +1012,16 @@ 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)
+ sdb->table.nents = sdb->table.orig_nents =
+ SCSI_INLINE_SG_CNT;
+ else if (unlikely(sg_alloc_table_chained(&sdb->table, nr_segs,
+ NULL)))
return BLK_STS_RESOURCE;
/*
@@ -1574,9 +1588,9 @@ 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);
}
@@ -1766,7 +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;
@@ -1860,7 +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) +
--
2.9.5
