[12/17] nvme: enable bio-cache for fixed-buffer passthru

Commit Message

Kanchan Joshi March 8, 2022, 3:21 p.m. UTC

Since we do submission/completion in task, we can have this up.
Add a bio-set for nvme as we need that for bio-cache.

Signed-off-by: Kanchan Joshi <[e-mail]>
---
 block/blk-map.c           | 4 ++--
 drivers/nvme/host/core.c  | 9 +++++++++
 drivers/nvme/host/ioctl.c | 2 +-
 drivers/nvme/host/nvme.h  | 1 +
 include/linux/blk-mq.h    | 3 ++-
 5 files changed, 15 insertions(+), 4 deletions(-)

Comments

Christoph Hellwig March 11, 2022, 6:48 a.m. UTC | #1

On Tue, Mar 08, 2022 at 08:51:00PM +0530, Kanchan Joshi wrote:
> Since we do submission/completion in task, we can have this up.
> Add a bio-set for nvme as we need that for bio-cache.

Well, passthrough I/O should just use kmalloced bios anyway, as there
is no need for the mempool to start with.  Take a look at the existing
code in blk-map.c.

Kanchan Joshi March 14, 2022, 6:18 p.m. UTC | #2

On Fri, Mar 11, 2022 at 12:18 PM Christoph Hellwig <[e-mail]> wrote:
>
> On Tue, Mar 08, 2022 at 08:51:00PM +0530, Kanchan Joshi wrote:
> > Since we do submission/completion in task, we can have this up.
> > Add a bio-set for nvme as we need that for bio-cache.
>
> Well, passthrough I/O should just use kmalloced bios anyway, as there
> is no need for the mempool to start with.  Take a look at the existing
> code in blk-map.c.

Yes, the only reason to switch from kmalloc to bio-set was being able
to use bio-cache.
Towards the goal of matching peak perf of io_uring's block io path.
Is it too bad to go down this route; Is there any different way to
enable bio-cache for passthru.

Christoph Hellwig March 15, 2022, 8:57 a.m. UTC | #3

On Mon, Mar 14, 2022 at 11:48:43PM +0530, Kanchan Joshi wrote:
> Yes, the only reason to switch from kmalloc to bio-set was being able
> to use bio-cache.
> Towards the goal of matching peak perf of io_uring's block io path.
> Is it too bad to go down this route; Is there any different way to
> enable bio-cache for passthru.

How does this actually make a difference vs say a slab cache?  Slab/slub
seems to be very fine tuned for these kinds of patters using per-cpu
caches.

Patch

diff --git a/block/blk-map.c b/block/blk-map.c
index 027e8216e313..c39917f0eb78 100644
--- a/block/blk-map.c
+++ b/block/blk-map.c
@@ -580,7 +580,7 @@  EXPORT_SYMBOL(blk_rq_map_user);
 
 /* Unlike blk_rq_map_user () this is only for fixed-buffer async passthrough. */
 int blk_rq_map_user_fixedb(struct request_queue *q, struct request *rq,
-		     u64 ubuf, unsigned long len, gfp_t gfp_mask,
+		     u64 ubuf, unsigned long len, struct bio_set *bs,
 		     struct io_uring_cmd *ioucmd)
 {
 	struct iov_iter iter;
@@ -604,7 +604,7 @@  int blk_rq_map_user_fixedb(struct request_queue *q, struct request *rq,
 	if (nr_segs > queue_max_segments(q))
 		return -EINVAL;
 	/* no iovecs to alloc, as we already have a BVEC iterator */
-	bio = bio_alloc(gfp_mask, 0);
+	bio = bio_from_cache(0, bs);
 	if (!bio)
 		return -ENOMEM;
 
diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c
index 3fe8f5901cd9..4a385001f124 100644
--- a/drivers/nvme/host/core.c
+++ b/drivers/nvme/host/core.c
@@ -30,6 +30,9 @@ 
 
 #define NVME_MINORS		(1U << MINORBITS)
 
+#define NVME_BIO_POOL_SZ	(4)
+struct bio_set nvme_bio_pool;
+
 unsigned int admin_timeout = 60;
 module_param(admin_timeout, uint, 0644);
 MODULE_PARM_DESC(admin_timeout, "timeout in seconds for admin commands");
@@ -4797,6 +4800,11 @@  static int __init nvme_core_init(void)
 		goto unregister_generic_ns;
 	}
 
+	result = bioset_init(&nvme_bio_pool, NVME_BIO_POOL_SZ, 0,
+			BIOSET_NEED_BVECS | BIOSET_PERCPU_CACHE);
+	if (result < 0)
+		goto unregister_generic_ns;
+
 	return 0;
 
 unregister_generic_ns:
@@ -4819,6 +4827,7 @@  static int __init nvme_core_init(void)
 
 static void __exit nvme_core_exit(void)
 {
+	bioset_exit(&nvme_bio_pool);
 	class_destroy(nvme_ns_chr_class);
 	class_destroy(nvme_subsys_class);
 	class_destroy(nvme_class);
diff --git a/drivers/nvme/host/ioctl.c b/drivers/nvme/host/ioctl.c
index 91d893eedc82..a4cde210aab9 100644
--- a/drivers/nvme/host/ioctl.c
+++ b/drivers/nvme/host/ioctl.c
@@ -159,7 +159,7 @@  static int nvme_submit_user_cmd(struct request_queue *q,
 	if (ubuffer && bufflen) {
 		if (likely(nvme_is_fixedb_passthru(ioucmd)))
 			ret = blk_rq_map_user_fixedb(q, req, ubuffer, bufflen,
-					GFP_KERNEL, ioucmd);
+					&nvme_bio_pool, ioucmd);
 		else
 			ret = blk_rq_map_user(q, req, NULL, nvme_to_user_ptr(ubuffer),
 					bufflen, GFP_KERNEL);
diff --git a/drivers/nvme/host/nvme.h b/drivers/nvme/host/nvme.h
index e6a30543d7c8..9a3e5093dedc 100644
--- a/drivers/nvme/host/nvme.h
+++ b/drivers/nvme/host/nvme.h
@@ -47,6 +47,7 @@  extern unsigned int admin_timeout;
 extern struct workqueue_struct *nvme_wq;
 extern struct workqueue_struct *nvme_reset_wq;
 extern struct workqueue_struct *nvme_delete_wq;
+extern struct bio_set nvme_bio_pool;
 
 /*
  * List of workarounds for devices that required behavior not specified in
diff --git a/include/linux/blk-mq.h b/include/linux/blk-mq.h
index 48bcfd194bdc..5f21f71b2529 100644
--- a/include/linux/blk-mq.h
+++ b/include/linux/blk-mq.h
@@ -967,7 +967,8 @@  struct rq_map_data {
 int blk_rq_map_user(struct request_queue *, struct request *,
 		struct rq_map_data *, void __user *, unsigned long, gfp_t);
 int blk_rq_map_user_fixedb(struct request_queue *, struct request *,
-		     u64 ubuf, unsigned long, gfp_t,  struct io_uring_cmd *);
+		     u64 ubuf, unsigned long, struct bio_set *,
+		     struct io_uring_cmd *);
 int blk_rq_map_user_iov(struct request_queue *, struct request *,
 		struct rq_map_data *, const struct iov_iter *, gfp_t);
 int blk_rq_unmap_user(struct bio *);