Commit 7fbc78e3 authored by Linus Torvalds's avatar Linus Torvalds

Merge tag 'for-linus-20190524' of git://git.kernel.dk/linux-block

Pull block fixes from Jens Axboe:

 - NVMe pull request from Keith, with fixes from a few folks.

 - bio and sbitmap before atomic barrier fixes (Andrea)

 - Hang fix for blk-mq freeze and unfreeze (Bob)

 - Single segment count regression fix (Christoph)

 - AoE now has a new maintainer

 - tools/io_uring/ Makefile fix, and sync with liburing (me)

* tag 'for-linus-20190524' of git://git.kernel.dk/linux-block: (23 commits)
  tools/io_uring: sync with liburing
  tools/io_uring: fix Makefile for pthread library link
  blk-mq: fix hang caused by freeze/unfreeze sequence
  block: remove the bi_seg_{front,back}_size fields in struct bio
  block: remove the segment size check in bio_will_gap
  block: force an unlimited segment size on queues with a virt boundary
  block: don't decrement nr_phys_segments for physically contigous segments
  sbitmap: fix improper use of smp_mb__before_atomic()
  bio: fix improper use of smp_mb__before_atomic()
  aoe: list new maintainer for aoe driver
  nvme-pci: use blk-mq mapping for unmanaged irqs
  nvme: update MAINTAINERS
  nvme: copy MTFA field from identify controller
  nvme: fix memory leak for power latency tolerance
  nvme: release namespace SRCU protection before performing controller ioctls
  nvme: merge nvme_ns_ioctl into nvme_ioctl
  nvme: remove the ifdef around nvme_nvm_ioctl
  nvme: fix srcu locking on error return in nvme_get_ns_from_disk
  nvme: Fix known effects
  nvme-pci: Sync queues on reset
  ...
parents 7f8b40e3 096c7a6d
......@@ -2627,7 +2627,7 @@ F: Documentation/devicetree/bindings/eeprom/at24.txt
F: drivers/misc/eeprom/at24.c
ATA OVER ETHERNET (AOE) DRIVER
M: "Ed L. Cashin" <ed.cashin@acm.org>
M: "Justin Sanders" <justin@coraid.com>
W: http://www.openaoe.org/
S: Supported
F: Documentation/aoe/
......@@ -11226,7 +11226,7 @@ F: drivers/video/fbdev/riva/
F: drivers/video/fbdev/nvidia/
NVM EXPRESS DRIVER
M: Keith Busch <keith.busch@intel.com>
M: Keith Busch <kbusch@kernel.org>
M: Jens Axboe <axboe@fb.com>
M: Christoph Hellwig <hch@lst.de>
M: Sagi Grimberg <sagi@grimberg.me>
......
......@@ -413,7 +413,7 @@ int blk_queue_enter(struct request_queue *q, blk_mq_req_flags_t flags)
smp_rmb();
wait_event(q->mq_freeze_wq,
(atomic_read(&q->mq_freeze_depth) == 0 &&
(!q->mq_freeze_depth &&
(pm || (blk_pm_request_resume(q),
!blk_queue_pm_only(q)))) ||
blk_queue_dying(q));
......@@ -503,6 +503,7 @@ struct request_queue *blk_alloc_queue_node(gfp_t gfp_mask, int node_id)
spin_lock_init(&q->queue_lock);
init_waitqueue_head(&q->mq_freeze_wq);
mutex_init(&q->mq_freeze_lock);
/*
* Init percpu_ref in atomic mode so that it's faster to shutdown.
......
......@@ -12,23 +12,6 @@
#include "blk.h"
/*
* Check if the two bvecs from two bios can be merged to one segment. If yes,
* no need to check gap between the two bios since the 1st bio and the 1st bvec
* in the 2nd bio can be handled in one segment.
*/
static inline bool bios_segs_mergeable(struct request_queue *q,
struct bio *prev, struct bio_vec *prev_last_bv,
struct bio_vec *next_first_bv)
{
if (!biovec_phys_mergeable(q, prev_last_bv, next_first_bv))
return false;
if (prev->bi_seg_back_size + next_first_bv->bv_len >
queue_max_segment_size(q))
return false;
return true;
}
static inline bool bio_will_gap(struct request_queue *q,
struct request *prev_rq, struct bio *prev, struct bio *next)
{
......@@ -60,7 +43,7 @@ static inline bool bio_will_gap(struct request_queue *q,
*/
bio_get_last_bvec(prev, &pb);
bio_get_first_bvec(next, &nb);
if (bios_segs_mergeable(q, prev, &pb, &nb))
if (biovec_phys_mergeable(q, &pb, &nb))
return false;
return __bvec_gap_to_prev(q, &pb, nb.bv_offset);
}
......@@ -179,8 +162,7 @@ static unsigned get_max_segment_size(struct request_queue *q,
* variables.
*/
static bool bvec_split_segs(struct request_queue *q, struct bio_vec *bv,
unsigned *nsegs, unsigned *last_seg_size,
unsigned *front_seg_size, unsigned *sectors, unsigned max_segs)
unsigned *nsegs, unsigned *sectors, unsigned max_segs)
{
unsigned len = bv->bv_len;
unsigned total_len = 0;
......@@ -202,28 +184,12 @@ static bool bvec_split_segs(struct request_queue *q, struct bio_vec *bv,
break;
}
if (!new_nsegs)
return !!len;
/* update front segment size */
if (!*nsegs) {
unsigned first_seg_size;
if (new_nsegs == 1)
first_seg_size = get_max_segment_size(q, bv->bv_offset);
else
first_seg_size = queue_max_segment_size(q);
if (*front_seg_size < first_seg_size)
*front_seg_size = first_seg_size;
if (new_nsegs) {
*nsegs += new_nsegs;
if (sectors)
*sectors += total_len >> 9;
}
/* update other varibles */
*last_seg_size = seg_size;
*nsegs += new_nsegs;
if (sectors)
*sectors += total_len >> 9;
/* split in the middle of the bvec if len != 0 */
return !!len;
}
......@@ -235,8 +201,7 @@ static struct bio *blk_bio_segment_split(struct request_queue *q,
{
struct bio_vec bv, bvprv, *bvprvp = NULL;
struct bvec_iter iter;
unsigned seg_size = 0, nsegs = 0, sectors = 0;
unsigned front_seg_size = bio->bi_seg_front_size;
unsigned nsegs = 0, sectors = 0;
bool do_split = true;
struct bio *new = NULL;
const unsigned max_sectors = get_max_io_size(q, bio);
......@@ -260,8 +225,6 @@ static struct bio *blk_bio_segment_split(struct request_queue *q,
/* split in the middle of bvec */
bv.bv_len = (max_sectors - sectors) << 9;
bvec_split_segs(q, &bv, &nsegs,
&seg_size,
&front_seg_size,
&sectors, max_segs);
}
goto split;
......@@ -275,12 +238,9 @@ static struct bio *blk_bio_segment_split(struct request_queue *q,
if (bv.bv_offset + bv.bv_len <= PAGE_SIZE) {
nsegs++;
seg_size = bv.bv_len;
sectors += bv.bv_len >> 9;
if (nsegs == 1 && seg_size > front_seg_size)
front_seg_size = seg_size;
} else if (bvec_split_segs(q, &bv, &nsegs, &seg_size,
&front_seg_size, &sectors, max_segs)) {
} else if (bvec_split_segs(q, &bv, &nsegs, &sectors,
max_segs)) {
goto split;
}
}
......@@ -295,10 +255,6 @@ static struct bio *blk_bio_segment_split(struct request_queue *q,
bio = new;
}
bio->bi_seg_front_size = front_seg_size;
if (seg_size > bio->bi_seg_back_size)
bio->bi_seg_back_size = seg_size;
return do_split ? new : NULL;
}
......@@ -353,18 +309,13 @@ EXPORT_SYMBOL(blk_queue_split);
static unsigned int __blk_recalc_rq_segments(struct request_queue *q,
struct bio *bio)
{
struct bio_vec uninitialized_var(bv), bvprv = { NULL };
unsigned int seg_size, nr_phys_segs;
unsigned front_seg_size;
struct bio *fbio, *bbio;
unsigned int nr_phys_segs = 0;
struct bvec_iter iter;
bool new_bio = false;
struct bio_vec bv;
if (!bio)
return 0;
front_seg_size = bio->bi_seg_front_size;
switch (bio_op(bio)) {
case REQ_OP_DISCARD:
case REQ_OP_SECURE_ERASE:
......@@ -374,42 +325,11 @@ static unsigned int __blk_recalc_rq_segments(struct request_queue *q,
return 1;
}
fbio = bio;
seg_size = 0;
nr_phys_segs = 0;
for_each_bio(bio) {
bio_for_each_bvec(bv, bio, iter) {
if (new_bio) {
if (seg_size + bv.bv_len
> queue_max_segment_size(q))
goto new_segment;
if (!biovec_phys_mergeable(q, &bvprv, &bv))
goto new_segment;
seg_size += bv.bv_len;
if (nr_phys_segs == 1 && seg_size >
front_seg_size)
front_seg_size = seg_size;
continue;
}
new_segment:
bvec_split_segs(q, &bv, &nr_phys_segs, &seg_size,
&front_seg_size, NULL, UINT_MAX);
new_bio = false;
}
bbio = bio;
if (likely(bio->bi_iter.bi_size)) {
bvprv = bv;
new_bio = true;
}
bio_for_each_bvec(bv, bio, iter)
bvec_split_segs(q, &bv, &nr_phys_segs, NULL, UINT_MAX);
}
fbio->bi_seg_front_size = front_seg_size;
if (seg_size > bbio->bi_seg_back_size)
bbio->bi_seg_back_size = seg_size;
return nr_phys_segs;
}
......@@ -429,24 +349,6 @@ void blk_recount_segments(struct request_queue *q, struct bio *bio)
bio_set_flag(bio, BIO_SEG_VALID);
}
static int blk_phys_contig_segment(struct request_queue *q, struct bio *bio,
struct bio *nxt)
{
struct bio_vec end_bv = { NULL }, nxt_bv;
if (bio->bi_seg_back_size + nxt->bi_seg_front_size >
queue_max_segment_size(q))
return 0;
if (!bio_has_data(bio))
return 1;
bio_get_last_bvec(bio, &end_bv);
bio_get_first_bvec(nxt, &nxt_bv);
return biovec_phys_mergeable(q, &end_bv, &nxt_bv);
}
static inline struct scatterlist *blk_next_sg(struct scatterlist **sg,
struct scatterlist *sglist)
{
......@@ -706,8 +608,6 @@ static int ll_merge_requests_fn(struct request_queue *q, struct request *req,
struct request *next)
{
int total_phys_segments;
unsigned int seg_size =
req->biotail->bi_seg_back_size + next->bio->bi_seg_front_size;
if (req_gap_back_merge(req, next->bio))
return 0;
......@@ -720,14 +620,6 @@ static int ll_merge_requests_fn(struct request_queue *q, struct request *req,
return 0;
total_phys_segments = req->nr_phys_segments + next->nr_phys_segments;
if (blk_phys_contig_segment(q, req->biotail, next->bio)) {
if (req->nr_phys_segments == 1)
req->bio->bi_seg_front_size = seg_size;
if (next->nr_phys_segments == 1)
next->biotail->bi_seg_back_size = seg_size;
total_phys_segments--;
}
if (total_phys_segments > queue_max_segments(q))
return 0;
......
......@@ -144,13 +144,14 @@ void blk_mq_in_flight_rw(struct request_queue *q, struct hd_struct *part,
void blk_freeze_queue_start(struct request_queue *q)
{
int freeze_depth;
freeze_depth = atomic_inc_return(&q->mq_freeze_depth);
if (freeze_depth == 1) {
mutex_lock(&q->mq_freeze_lock);
if (++q->mq_freeze_depth == 1) {
percpu_ref_kill(&q->q_usage_counter);
mutex_unlock(&q->mq_freeze_lock);
if (queue_is_mq(q))
blk_mq_run_hw_queues(q, false);
} else {
mutex_unlock(&q->mq_freeze_lock);
}
}
EXPORT_SYMBOL_GPL(blk_freeze_queue_start);
......@@ -199,14 +200,14 @@ EXPORT_SYMBOL_GPL(blk_mq_freeze_queue);
void blk_mq_unfreeze_queue(struct request_queue *q)
{
int freeze_depth;
freeze_depth = atomic_dec_return(&q->mq_freeze_depth);
WARN_ON_ONCE(freeze_depth < 0);
if (!freeze_depth) {
mutex_lock(&q->mq_freeze_lock);
q->mq_freeze_depth--;
WARN_ON_ONCE(q->mq_freeze_depth < 0);
if (!q->mq_freeze_depth) {
percpu_ref_resurrect(&q->q_usage_counter);
wake_up_all(&q->mq_freeze_wq);
}
mutex_unlock(&q->mq_freeze_lock);
}
EXPORT_SYMBOL_GPL(blk_mq_unfreeze_queue);
......
......@@ -310,6 +310,9 @@ void blk_queue_max_segment_size(struct request_queue *q, unsigned int max_size)
__func__, max_size);
}
/* see blk_queue_virt_boundary() for the explanation */
WARN_ON_ONCE(q->limits.virt_boundary_mask);
q->limits.max_segment_size = max_size;
}
EXPORT_SYMBOL(blk_queue_max_segment_size);
......@@ -742,6 +745,14 @@ EXPORT_SYMBOL(blk_queue_segment_boundary);
void blk_queue_virt_boundary(struct request_queue *q, unsigned long mask)
{
q->limits.virt_boundary_mask = mask;
/*
* Devices that require a virtual boundary do not support scatter/gather
* I/O natively, but instead require a descriptor list entry for each
* page (which might not be idential to the Linux PAGE_SIZE). Because
* of that they are not limited by our notion of "segment size".
*/
q->limits.max_segment_size = UINT_MAX;
}
EXPORT_SYMBOL(blk_queue_virt_boundary);
......
......@@ -1257,9 +1257,9 @@ static u32 nvme_passthru_start(struct nvme_ctrl *ctrl, struct nvme_ns *ns,
return 0;
}
effects |= nvme_known_admin_effects(opcode);
if (ctrl->effects)
effects = le32_to_cpu(ctrl->effects->acs[opcode]);
effects |= nvme_known_admin_effects(opcode);
/*
* For simplicity, IO to all namespaces is quiesced even if the command
......@@ -1361,9 +1361,14 @@ static struct nvme_ns *nvme_get_ns_from_disk(struct gendisk *disk,
{
#ifdef CONFIG_NVME_MULTIPATH
if (disk->fops == &nvme_ns_head_ops) {
struct nvme_ns *ns;
*head = disk->private_data;
*srcu_idx = srcu_read_lock(&(*head)->srcu);
return nvme_find_path(*head);
ns = nvme_find_path(*head);
if (!ns)
srcu_read_unlock(&(*head)->srcu, *srcu_idx);
return ns;
}
#endif
*head = NULL;
......@@ -1377,42 +1382,56 @@ static void nvme_put_ns_from_disk(struct nvme_ns_head *head, int idx)
srcu_read_unlock(&head->srcu, idx);
}
static int nvme_ns_ioctl(struct nvme_ns *ns, unsigned cmd, unsigned long arg)
static int nvme_ioctl(struct block_device *bdev, fmode_t mode,
unsigned int cmd, unsigned long arg)
{
struct nvme_ns_head *head = NULL;
void __user *argp = (void __user *)arg;
struct nvme_ns *ns;
int srcu_idx, ret;
ns = nvme_get_ns_from_disk(bdev->bd_disk, &head, &srcu_idx);
if (unlikely(!ns))
return -EWOULDBLOCK;
/*
* Handle ioctls that apply to the controller instead of the namespace
* seperately and drop the ns SRCU reference early. This avoids a
* deadlock when deleting namespaces using the passthrough interface.
*/
if (cmd == NVME_IOCTL_ADMIN_CMD || is_sed_ioctl(cmd)) {
struct nvme_ctrl *ctrl = ns->ctrl;
nvme_get_ctrl(ns->ctrl);
nvme_put_ns_from_disk(head, srcu_idx);
if (cmd == NVME_IOCTL_ADMIN_CMD)
ret = nvme_user_cmd(ctrl, NULL, argp);
else
ret = sed_ioctl(ctrl->opal_dev, cmd, argp);
nvme_put_ctrl(ctrl);
return ret;
}
switch (cmd) {
case NVME_IOCTL_ID:
force_successful_syscall_return();
return ns->head->ns_id;
case NVME_IOCTL_ADMIN_CMD:
return nvme_user_cmd(ns->ctrl, NULL, (void __user *)arg);
ret = ns->head->ns_id;
break;
case NVME_IOCTL_IO_CMD:
return nvme_user_cmd(ns->ctrl, ns, (void __user *)arg);
ret = nvme_user_cmd(ns->ctrl, ns, argp);
break;
case NVME_IOCTL_SUBMIT_IO:
return nvme_submit_io(ns, (void __user *)arg);
ret = nvme_submit_io(ns, argp);
break;
default:
#ifdef CONFIG_NVM
if (ns->ndev)
return nvme_nvm_ioctl(ns, cmd, arg);
#endif
if (is_sed_ioctl(cmd))
return sed_ioctl(ns->ctrl->opal_dev, cmd,
(void __user *) arg);
return -ENOTTY;
ret = nvme_nvm_ioctl(ns, cmd, arg);
else
ret = -ENOTTY;
}
}
static int nvme_ioctl(struct block_device *bdev, fmode_t mode,
unsigned int cmd, unsigned long arg)
{
struct nvme_ns_head *head = NULL;
struct nvme_ns *ns;
int srcu_idx, ret;
ns = nvme_get_ns_from_disk(bdev->bd_disk, &head, &srcu_idx);
if (unlikely(!ns))
ret = -EWOULDBLOCK;
else
ret = nvme_ns_ioctl(ns, cmd, arg);
nvme_put_ns_from_disk(head, srcu_idx);
return ret;
}
......@@ -2557,6 +2576,7 @@ int nvme_init_identify(struct nvme_ctrl *ctrl)
ctrl->oacs = le16_to_cpu(id->oacs);
ctrl->oncs = le16_to_cpu(id->oncs);
ctrl->mtfa = le16_to_cpu(id->mtfa);
ctrl->oaes = le32_to_cpu(id->oaes);
atomic_set(&ctrl->abort_limit, id->acl + 1);
ctrl->vwc = id->vwc;
......@@ -3681,6 +3701,7 @@ EXPORT_SYMBOL_GPL(nvme_start_ctrl);
void nvme_uninit_ctrl(struct nvme_ctrl *ctrl)
{
dev_pm_qos_hide_latency_tolerance(ctrl->device);
cdev_device_del(&ctrl->cdev, ctrl->device);
}
EXPORT_SYMBOL_GPL(nvme_uninit_ctrl);
......@@ -3880,6 +3901,18 @@ void nvme_start_queues(struct nvme_ctrl *ctrl)
}
EXPORT_SYMBOL_GPL(nvme_start_queues);
void nvme_sync_queues(struct nvme_ctrl *ctrl)
{
struct nvme_ns *ns;
down_read(&ctrl->namespaces_rwsem);
list_for_each_entry(ns, &ctrl->namespaces, list)
blk_sync_queue(ns->queue);
up_read(&ctrl->namespaces_rwsem);
}
EXPORT_SYMBOL_GPL(nvme_sync_queues);
/*
* Check we didn't inadvertently grow the command structure sizes:
*/
......
......@@ -441,6 +441,7 @@ void nvme_complete_async_event(struct nvme_ctrl *ctrl, __le16 status,
void nvme_stop_queues(struct nvme_ctrl *ctrl);
void nvme_start_queues(struct nvme_ctrl *ctrl);
void nvme_kill_queues(struct nvme_ctrl *ctrl);
void nvme_sync_queues(struct nvme_ctrl *ctrl);
void nvme_unfreeze(struct nvme_ctrl *ctrl);
void nvme_wait_freeze(struct nvme_ctrl *ctrl);
void nvme_wait_freeze_timeout(struct nvme_ctrl *ctrl, long timeout);
......
......@@ -464,7 +464,7 @@ static int nvme_pci_map_queues(struct blk_mq_tag_set *set)
* affinity), so use the regular blk-mq cpu mapping
*/
map->queue_offset = qoff;
if (i != HCTX_TYPE_POLL)
if (i != HCTX_TYPE_POLL && offset)
blk_mq_pci_map_queues(map, to_pci_dev(dev->dev), offset);
else
blk_mq_map_queues(map);
......@@ -1257,7 +1257,6 @@ static enum blk_eh_timer_return nvme_timeout(struct request *req, bool reserved)
struct nvme_dev *dev = nvmeq->dev;
struct request *abort_req;
struct nvme_command cmd;
bool shutdown = false;
u32 csts = readl(dev->bar + NVME_REG_CSTS);
/* If PCI error recovery process is happening, we cannot reset or
......@@ -1294,17 +1293,18 @@ static enum blk_eh_timer_return nvme_timeout(struct request *req, bool reserved)
* shutdown, so we return BLK_EH_DONE.
*/
switch (dev->ctrl.state) {
case NVME_CTRL_DELETING:
shutdown = true;
/* fall through */
case NVME_CTRL_CONNECTING:
case NVME_CTRL_RESETTING:
nvme_change_ctrl_state(&dev->ctrl, NVME_CTRL_DELETING);
/* fall through */
case NVME_CTRL_DELETING:
dev_warn_ratelimited(dev->ctrl.device,
"I/O %d QID %d timeout, disable controller\n",
req->tag, nvmeq->qid);
nvme_dev_disable(dev, shutdown);
nvme_dev_disable(dev, true);
nvme_req(req)->flags |= NVME_REQ_CANCELLED;
return BLK_EH_DONE;
case NVME_CTRL_RESETTING:
return BLK_EH_RESET_TIMER;
default:
break;
}
......@@ -2376,7 +2376,7 @@ static void nvme_pci_disable(struct nvme_dev *dev)
static void nvme_dev_disable(struct nvme_dev *dev, bool shutdown)
{
bool dead = true;
bool dead = true, freeze = false;
struct pci_dev *pdev = to_pci_dev(dev->dev);
mutex_lock(&dev->shutdown_lock);
......@@ -2384,8 +2384,10 @@ static void nvme_dev_disable(struct nvme_dev *dev, bool shutdown)
u32 csts = readl(dev->bar + NVME_REG_CSTS);
if (dev->ctrl.state == NVME_CTRL_LIVE ||
dev->ctrl.state == NVME_CTRL_RESETTING)
dev->ctrl.state == NVME_CTRL_RESETTING) {
freeze = true;
nvme_start_freeze(&dev->ctrl);
}
dead = !!((csts & NVME_CSTS_CFS) || !(csts & NVME_CSTS_RDY) ||
pdev->error_state != pci_channel_io_normal);
}
......@@ -2394,10 +2396,8 @@ static void nvme_dev_disable(struct nvme_dev *dev, bool shutdown)
* Give the controller a chance to complete all entered requests if
* doing a safe shutdown.
*/
if (!dead) {
if (shutdown)
nvme_wait_freeze_timeout(&dev->ctrl, NVME_IO_TIMEOUT);
}
if (!dead && shutdown && freeze)
nvme_wait_freeze_timeout(&dev->ctrl, NVME_IO_TIMEOUT);
nvme_stop_queues(&dev->ctrl);
......@@ -2492,6 +2492,7 @@ static void nvme_reset_work(struct work_struct *work)
*/
if (dev->ctrl.ctrl_config & NVME_CC_ENABLE)
nvme_dev_disable(dev, false);
nvme_sync_queues(&dev->ctrl);
mutex_lock(&dev->shutdown_lock);
result = nvme_pci_enable(dev);
......
......@@ -210,7 +210,7 @@ static inline void bio_cnt_set(struct bio *bio, unsigned int count)
{
if (count != 1) {
bio->bi_flags |= (1 << BIO_REFFED);
smp_mb__before_atomic();
smp_mb();
}
atomic_set(&bio->__bi_cnt, count);
}
......
......@@ -159,13 +159,6 @@ struct bio {
*/
unsigned int bi_phys_segments;
/*
* To keep track of the max segment size, we account for the
* sizes of the first and last mergeable segments in this bio.
*/
unsigned int bi_seg_front_size;
unsigned int bi_seg_back_size;
struct bvec_iter bi_iter;
atomic_t __bi_remaining;
......
......@@ -542,7 +542,7 @@ struct request_queue {
struct list_head unused_hctx_list;
spinlock_t unused_hctx_lock;
atomic_t mq_freeze_depth;
int mq_freeze_depth;
#if defined(CONFIG_BLK_DEV_BSG)
struct bsg_class_device bsg_dev;
......@@ -554,6 +554,11 @@ struct request_queue {
#endif
struct rcu_head rcu_head;
wait_queue_head_t mq_freeze_wq;
/*
* Protect concurrent access to q_usage_counter by
* percpu_ref_kill() and percpu_ref_reinit().
*/
struct mutex mq_freeze_lock;
struct percpu_ref q_usage_counter;
struct blk_mq_tag_set *tag_set;
......
......@@ -435,7 +435,7 @@ static void sbitmap_queue_update_wake_batch(struct sbitmap_queue *sbq,
* to ensure that the batch size is updated before the wait
* counts.
*/
smp_mb__before_atomic();
smp_mb();
for (i = 0; i < SBQ_WAIT_QUEUES; i++)
atomic_set(&sbq->ws[i].wait_cnt, 1);
}
......
......@@ -8,7 +8,7 @@ all: io_uring-cp io_uring-bench
$(CC) $(CFLAGS) -o $@ $^
io_uring-bench: syscall.o io_uring-bench.o
$(CC) $(CFLAGS) $(LDLIBS) -o $@ $^
$(CC) $(CFLAGS) -o $@ $^ $(LDLIBS)
io_uring-cp: setup.o syscall.o queue.o
......
......@@ -13,6 +13,7 @@
#include <assert.h>
#include <errno.h>
#include <inttypes.h>
#include <sys/types.h>
#include <sys/stat.h>
#include <sys/ioctl.h>
......@@ -85,11 +86,16 @@ static int queue_read(struct io_uring *ring, off_t size, off_t offset)
struct io_uring_sqe *sqe;
struct io_data *data;
data = malloc(size + sizeof(*data));
if (!data)
return 1;
sqe = io_uring_get_sqe(ring);
if (!sqe)
if (!sqe) {
free(data);
return 1;
}
data = malloc(size + sizeof(*data));
data->read = 1;
data->offset = data->first_offset = offset;
......@@ -166,22 +172,23 @@ static int copy_file(struct io_uring *ring, off_t insize)
struct io_data *data;
if (!got_comp) {
ret = io_uring_wait_completion(ring, &cqe);
ret = io_uring_wait_cqe(ring, &cqe);
got_comp = 1;
} else
ret = io_uring_get_completion(ring, &cqe);
ret = io_uring_peek_cqe(ring, &cqe);
if (ret < 0) {
fprintf(stderr, "io_uring_get_completion: %s\n",
fprintf(stderr, "io_uring_peek_cqe: %s\n",
strerror(-ret));
return 1;
}
if (!cqe)
break;
data = (struct io_data *) (uintptr_t) cqe->user_data;
data = io_uring_cqe_get_data(cqe);
if (cqe->res < 0) {
if (cqe->res == -EAGAIN) {
queue_prepped(ring, data);
io_uring_cqe_seen(ring, cqe);
continue;
}
fprintf(stderr, "cqe failed: %s\n",
......@@ -193,6 +200,7 @@ static int copy_file(struct io_uring *ring, off_t insize)
data->iov.iov_len -= cqe->res;
data->offset += cqe->res;
queue_prepped(ring, data);
io_uring_cqe_seen(ring, cqe);
continue;
}
......@@ -209,6 +217,7 @@ static int copy_file(struct io_uring *ring, off_t insize)
free(data);
writes--;
}
io_uring_cqe_seen(ring, cqe);
}
}
......
#ifndef LIB_URING_H
#define LIB_URING_H
#ifdef __cplusplus
extern "C" {
#endif
#include <sys/uio.h>
#include <signal.h>
#include <string.h>
#include "../../include/uapi/linux/io_uring.h"
#include <inttypes.h>
#include "barrier.h"
/*
* Library interface to io_uring
......@@ -46,7 +52,7 @@ struct io_uring {
* System calls
*/
extern int io_uring_setup(unsigned entries, struct io_uring_params *p);
extern int io_uring_enter(unsigned fd, unsigned to_submit,
extern int io_uring_enter(int fd, unsigned to_submit,
unsigned min_complete, unsigned flags, sigset_t *sig);
extern int io_uring_register(int fd, unsigned int opcode, void *arg,
unsigned int nr_args);
......@@ -59,13 +65,32 @@ extern int io_uring_queue_init(unsigned entries, struct io_uring *ring,
extern int io_uring_queue_mmap(int fd, struct io_uring_params *p,
struct io_uring *ring);
extern void io_uring_queue_exit(struct io_uring *ring);
extern int io_uring_get_completion(struct io_uring *ring,
extern int io_uring_peek_cqe(struct io_uring *ring,
struct io_uring_cqe **cqe_ptr);
extern int io_uring_wait_completion(struct io_uring *ring,
extern int io_uring_wait_cqe(struct io_uring *ring,
struct io_uring_cqe **cqe_ptr);
extern int io_uring_submit(struct io_uring *ring);
extern struct io_uring_sqe *io_uring_get_sqe(struct io_uring *ring);
/*
* Must be called after io_uring_{peek,wait}_cqe() after the cqe has
* been processed by the application.
*/
static inline void io_uring_cqe_seen(struct io_uring *ring,
struct io_uring_cqe *cqe)
{
if (cqe) {
struct io_uring_cq *cq = &ring->cq;
(*cq->khead)++;
/*
* Ensure that the kernel sees our new head, the kernel has
* the matching read barrier.
*/
write_barrier();
}
}
/*
* Command prep helpers
*/
......@@ -74,8 +99,14 @@ static inline void io_uring_sqe_set_data(struct io_uring_sqe *sqe, void *data)
sqe->user_data = (unsigned long) data;
}
static inline void *io_uring_cqe_get_data(struct io_uring_cqe *cqe)
{
return (void *) (uintptr_t) cqe->user_data;
}
static inline void io_uring_prep_rw(int op, struct io_uring_sqe *sqe, int fd,
void *addr, unsigned len, off_t offset)
const void *addr, unsigned len,
off_t offset)
{
memset(sqe, 0, sizeof(*sqe));
sqe->opcode = op;
......@@ -86,8 +117,8 @@ static inline void io_uring_prep_rw(int op, struct io_uring_sqe *sqe, int fd,
}
static inline void io_uring_prep_readv(struct io_uring_sqe *sqe, int fd,
struct iovec *iovecs, unsigned nr_vecs,
off_t offset)
const struct iovec *iovecs,
unsigned nr_vecs, off_t offset)
{
io_uring_prep_rw(IORING_OP_READV, sqe, fd, iovecs, nr_vecs, offset);
}
......@@ -100,14 +131,14 @@ static inline void io_uring_prep_read_fixed(struct io_uring_sqe *sqe, int fd,
}
static inline void io_uring_prep_writev(struct io_uring_sqe *sqe, int fd,
struct iovec *iovecs, unsigned nr_vecs,
off_t offset)
const struct iovec *iovecs,
unsigned nr_vecs, off_t offset)
{
io_uring_prep_rw(IORING_OP_WRITEV, sqe, fd, iovecs, nr_vecs, offset);
}
static inline void io_uring_prep_write_fixed(struct io_uring_sqe *sqe, int fd,
void *buf, unsigned nbytes,
const void *buf, unsigned nbytes,
off_t offset)
{
io_uring_prep_rw(IORING_OP_WRITE_FIXED, sqe, fd, buf, nbytes, offset);
......@@ -131,13 +162,22 @@ static inline void io_uring_prep_poll_remove(struct io_uring_sqe *sqe,
}
static inline void io_uring_prep_fsync(struct io_uring_sqe *sqe, int fd,
int datasync)
unsigned fsync_flags)
{
memset(sqe, 0, sizeof(*sqe));
sqe->opcode = IORING_OP_FSYNC;
sqe->fd = fd;
if (datasync)
sqe->fsync_flags = IORING_FSYNC_DATASYNC;
sqe->fsync_flags = fsync_flags;
}
static inline void io_uring_prep_nop(struct io_uring_sqe *sqe)
{
memset(sqe, 0, sizeof(*sqe));
sqe->opcode = IORING_OP_NOP;
}
#ifdef __cplusplus
}
#endif
#endif
......@@ -8,8 +8,8 @@
#include "liburing.h"
#include "barrier.h"
static int __io_uring_get_completion(struct io_uring *ring,
struct io_uring_cqe **cqe_ptr, int wait)
static int __io_uring_get_cqe(struct io_uring *ring,
struct io_uring_cqe **cqe_ptr, int wait)
{
struct io_uring_cq *cq = &ring->cq;
const unsigned mask = *cq->kring_mask;
......@@ -39,34 +39,25 @@ static int __io_uring_get_completion(struct io_uring *ring,
return -errno;
} while (1);
if (*cqe_ptr) {
*cq->khead = head + 1;
/*
* Ensure that the kernel sees our new head, the kernel has
* the matching read barrier.
*/
write_barrier();
}
return 0;
}
/*
* Return an IO completion, if one is readily available
* Return an IO completion, if one is readily available. Returns 0 with
* cqe_ptr filled in on success, -errno on failure.
*/
int io_uring_get_completion(struct io_uring *ring,
struct io_uring_cqe **cqe_ptr)
int io_uring_peek_cqe(struct io_uring *ring, struct io_uring_cqe **cqe_ptr)
{
return __io_uring_get_completion(ring, cqe_ptr, 0);
return __io_uring_get_cqe(ring, cqe_ptr, 0);
}
/*
* Return an IO completion, waiting for it if necessary
* Return an IO completion, waiting for it if necessary. Returns 0 with
* cqe_ptr filled in on success, -errno on failure.
*/
int io_uring_wait_completion(struct io_uring *ring,
struct io_uring_cqe **cqe_ptr)
int io_uring_wait_cqe(struct io_uring *ring, struct io_uring_cqe **cqe_ptr)
{
return __io_uring_get_completion(ring, cqe_ptr, 1);
return __io_uring_get_cqe(ring, cqe_ptr, 1);
}
/*
......@@ -78,7 +69,7 @@ int io_uring_submit(struct io_uring *ring)
{
struct io_uring_sq *sq = &ring->sq;
const unsigned mask = *sq->kring_mask;
unsigned ktail, ktail_next, submitted;
unsigned ktail, ktail_next, submitted, to_submit;
int ret;
/*
......@@ -100,7 +91,8 @@ int io_uring_submit(struct io_uring *ring)
*/
submitted = 0;
ktail = ktail_next = *sq->ktail;
while (sq->sqe_head < sq->sqe_tail) {
to_submit = sq->sqe_tail - sq->sqe_head;
while (to_submit--) {
ktail_next++;
read_barrier();
......@@ -136,7 +128,7 @@ int io_uring_submit(struct io_uring *ring)
if (ret < 0)
return -errno;
return 0;
return ret;
}
/*
......
......@@ -27,7 +27,7 @@ static int io_uring_mmap(int fd, struct io_uring_params *p,
sq->kdropped = ptr + p->sq_off.dropped;
sq->array = ptr + p->sq_off.array;
size = p->sq_entries * sizeof(struct io_uring_sqe),
size = p->sq_entries * sizeof(struct io_uring_sqe);
sq->sqes = mmap(0, size, PROT_READ | PROT_WRITE,
MAP_SHARED | MAP_POPULATE, fd,
IORING_OFF_SQES);
......@@ -79,7 +79,7 @@ int io_uring_queue_mmap(int fd, struct io_uring_params *p, struct io_uring *ring
int io_uring_queue_init(unsigned entries, struct io_uring *ring, unsigned flags)
{
struct io_uring_params p;
int fd;
int fd, ret;
memset(&p, 0, sizeof(p));
p.flags = flags;
......@@ -88,7 +88,11 @@ int io_uring_queue_init(unsigned entries, struct io_uring *ring, unsigned flags)
if (fd < 0)
return fd;
return io_uring_queue_mmap(fd, &p, ring);
ret = io_uring_queue_mmap(fd, &p, ring);
if (ret)
close(fd);
return ret;
}
void io_uring_queue_exit(struct io_uring *ring)
......
......@@ -7,34 +7,46 @@
#include <signal.h>
#include "liburing.h"
#if defined(__x86_64) || defined(__i386__)
#ifndef __NR_sys_io_uring_setup
#define __NR_sys_io_uring_setup 425
#endif
#ifndef __NR_sys_io_uring_enter
#define __NR_sys_io_uring_enter 426
#endif
#ifndef __NR_sys_io_uring_register
#define __NR_sys_io_uring_register 427
#endif
#else
#error "Arch not supported yet"
#ifdef __alpha__
/*
* alpha is the only exception, all other architectures
* have common numbers for new system calls.
*/
# ifndef __NR_io_uring_setup
# define __NR_io_uring_setup 535
# endif
# ifndef __NR_io_uring_enter
# define __NR_io_uring_enter 536
# endif
# ifndef __NR_io_uring_register
# define __NR_io_uring_register 537
# endif
#else /* !__alpha__ */
# ifndef __NR_io_uring_setup
# define __NR_io_uring_setup 425
# endif
# ifndef __NR_io_uring_enter
# define __NR_io_uring_enter 426
# endif
# ifndef __NR_io_uring_register
# define __NR_io_uring_register 427
# endif
#endif
int io_uring_register(int fd, unsigned int opcode, void *arg,
unsigned int nr_args)
{
return syscall(__NR_sys_io_uring_register, fd, opcode, arg, nr_args);
return syscall(__NR_io_uring_register, fd, opcode, arg, nr_args);
}
int io_uring_setup(unsigned entries, struct io_uring_params *p)
int io_uring_setup(unsigned int entries, struct io_uring_params *p)
{
return syscall(__NR_sys_io_uring_setup, entries, p);
return syscall(__NR_io_uring_setup, entries, p);
}
int io_uring_enter(unsigned fd, unsigned to_submit, unsigned min_complete,
unsigned flags, sigset_t *sig)
int io_uring_enter(int fd, unsigned int to_submit, unsigned int min_complete,
unsigned int flags, sigset_t *sig)
{
return syscall(__NR_sys_io_uring_enter, fd, to_submit, min_complete,
return syscall(__NR_io_uring_enter, fd, to_submit, min_complete,
flags, sig, _NSIG / 8);
}
Markdown is supported
0%
or
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment