Stop using the .bdrv_co_io_plug() API because it is not multi-queue

block layer friendly. Use the new blk_io_plug_call() API to batch I/O

submission instead.

Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com>

Reviewed-by: Eric Blake <eblake@redhat.com>

Reviewed-by: Stefano Garzarella <sgarzare@redhat.com>

Acked-by: Kevin Wolf <kwolf@redhat.com>

Message-id: 20230530180959.1108766-3-stefanha@redhat.com

Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com>

---

block/nvme.c | 44 ++++++++++++--------------------------------

block/trace-events | 1 -

2 files changed, 12 insertions(+), 33 deletions(-)

diff --git a/block/nvme.c b/block/nvme.c

index XXXXXXX..XXXXXXX 100644

--- a/block/nvme.c

+++ b/block/nvme.c

@@ -XXX,XX +XXX,XX @@

#include "qemu/vfio-helpers.h"

#include "block/block-io.h"

#include "block/block_int.h"

+#include "sysemu/block-backend.h"

#include "sysemu/replay.h"

#include "trace.h"

@@ -XXX,XX +XXX,XX @@ struct BDRVNVMeState {

int blkshift;

uint64_t max_transfer;

- bool plugged;

bool supports_write_zeroes;

bool supports_discard;

@@ -XXX,XX +XXX,XX @@ static void nvme_kick(NVMeQueuePair *q)

{

BDRVNVMeState *s = q->s;

- if (s->plugged || !q->need_kick) {

+ if (!q->need_kick) {

return;

}

trace_nvme_kick(s, q->index);

@@ -XXX,XX +XXX,XX @@ static bool nvme_process_completion(NVMeQueuePair *q)

NvmeCqe *c;

trace_nvme_process_completion(s, q->index, q->inflight);

- if (s->plugged) {

- trace_nvme_process_completion_queue_plugged(s, q->index);

- return false;

- }

/*

* Support re-entrancy when a request cb() function invokes aio_poll().

@@ -XXX,XX +XXX,XX @@ static void nvme_trace_command(const NvmeCmd *cmd)

}

}

+static void nvme_unplug_fn(void *opaque)

+{

+ NVMeQueuePair *q = opaque;

+

+ QEMU_LOCK_GUARD(&q->lock);

+ nvme_kick(q);

+ nvme_process_completion(q);

+}

+

static void nvme_submit_command(NVMeQueuePair *q, NVMeRequest *req,

NvmeCmd *cmd, BlockCompletionFunc cb,

void *opaque)

@@ -XXX,XX +XXX,XX @@ static void nvme_submit_command(NVMeQueuePair *q, NVMeRequest *req,

q->sq.tail * NVME_SQ_ENTRY_BYTES, cmd, sizeof(*cmd));

q->sq.tail = (q->sq.tail + 1) % NVME_QUEUE_SIZE;

q->need_kick++;

- nvme_kick(q);

- nvme_process_completion(q);

+ blk_io_plug_call(nvme_unplug_fn, q);

qemu_mutex_unlock(&q->lock);

}

@@ -XXX,XX +XXX,XX @@ static void nvme_attach_aio_context(BlockDriverState *bs,

}

}

-static void coroutine_fn nvme_co_io_plug(BlockDriverState *bs)

-{

- BDRVNVMeState *s = bs->opaque;

- assert(!s->plugged);

- s->plugged = true;

-}

-

-static void coroutine_fn nvme_co_io_unplug(BlockDriverState *bs)

-{

- BDRVNVMeState *s = bs->opaque;

- assert(s->plugged);

- s->plugged = false;

- for (unsigned i = INDEX_IO(0); i < s->queue_count; i++) {

- NVMeQueuePair *q = s->queues[i];

- qemu_mutex_lock(&q->lock);

- nvme_kick(q);

- nvme_process_completion(q);

- qemu_mutex_unlock(&q->lock);

- }

-}

-

static bool nvme_register_buf(BlockDriverState *bs, void *host, size_t size,

Error **errp)

{

@@ -XXX,XX +XXX,XX @@ static BlockDriver bdrv_nvme = {

.bdrv_detach_aio_context = nvme_detach_aio_context,

.bdrv_attach_aio_context = nvme_attach_aio_context,

- .bdrv_co_io_plug = nvme_co_io_plug,

- .bdrv_co_io_unplug = nvme_co_io_unplug,

-

.bdrv_register_buf = nvme_register_buf,

.bdrv_unregister_buf = nvme_unregister_buf,

};

diff --git a/block/trace-events b/block/trace-events

index XXXXXXX..XXXXXXX 100644

--- a/block/trace-events

+++ b/block/trace-events

@@ -XXX,XX +XXX,XX @@ nvme_kick(void *s, unsigned q_index) "s %p q #%u"

nvme_dma_flush_queue_wait(void *s) "s %p"

nvme_error(int cmd_specific, int sq_head, int sqid, int cid, int status) "cmd_specific %d sq_head %d sqid %d cid %d status 0x%x"

nvme_process_completion(void *s, unsigned q_index, int inflight) "s %p q #%u inflight %d"

-nvme_process_completion_queue_plugged(void *s, unsigned q_index) "s %p q #%u"

nvme_complete_command(void *s, unsigned q_index, int cid) "s %p q #%u cid %d"

nvme_submit_command(void *s, unsigned q_index, int cid) "s %p q #%u cid %d"

nvme_submit_command_raw(int c0, int c1, int c2, int c3, int c4, int c5, int c6, int c7) "%02x %02x %02x %02x %02x %02x %02x %02x"

--

2.40.1

Stop using the .bdrv_co_io_plug() API because it is not multi-queue

block layer friendly. Use the new blk_io_plug_call() API to batch I/O

submission instead.

Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com>

Reviewed-by: Eric Blake <eblake@redhat.com>

Reviewed-by: Stefano Garzarella <sgarzare@redhat.com>

Acked-by: Kevin Wolf <kwolf@redhat.com>

Message-id: 20230530180959.1108766-4-stefanha@redhat.com

Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com>

---

block/blkio.c | 43 ++++++++++++++++++++++++-------------------

1 file changed, 24 insertions(+), 19 deletions(-)

diff --git a/block/blkio.c b/block/blkio.c

index XXXXXXX..XXXXXXX 100644

--- a/block/blkio.c

+++ b/block/blkio.c

@@ -XXX,XX +XXX,XX @@

#include "qemu/error-report.h"

#include "qapi/qmp/qdict.h"

#include "qemu/module.h"

+#include "sysemu/block-backend.h"

#include "exec/memory.h" /* for ram_block_discard_disable() */

#include "block/block-io.h"

@@ -XXX,XX +XXX,XX @@ static void blkio_detach_aio_context(BlockDriverState *bs)

NULL, NULL, NULL);

}

-/* Call with s->blkio_lock held to submit I/O after enqueuing a new request */

-static void blkio_submit_io(BlockDriverState *bs)

+/*

+ * Called by blk_io_unplug() or immediately if not plugged. Called without

+ * blkio_lock.

+ */

+static void blkio_unplug_fn(void *opaque)

{

- if (qatomic_read(&bs->io_plugged) == 0) {

- BDRVBlkioState *s = bs->opaque;

+ BDRVBlkioState *s = opaque;

+ WITH_QEMU_LOCK_GUARD(&s->blkio_lock) {

blkioq_do_io(s->blkioq, NULL, 0, 0, NULL);

}

}

+/*

+ * Schedule I/O submission after enqueuing a new request. Called without

+ * blkio_lock.

+ */

+static void blkio_submit_io(BlockDriverState *bs)

+{

+ BDRVBlkioState *s = bs->opaque;

+

+ blk_io_plug_call(blkio_unplug_fn, s);

+}

+

static int coroutine_fn

blkio_co_pdiscard(BlockDriverState *bs, int64_t offset, int64_t bytes)

{

@@ -XXX,XX +XXX,XX @@ blkio_co_pdiscard(BlockDriverState *bs, int64_t offset, int64_t bytes)

WITH_QEMU_LOCK_GUARD(&s->blkio_lock) {

blkioq_discard(s->blkioq, offset, bytes, &cod, 0);

- blkio_submit_io(bs);

}

+ blkio_submit_io(bs);

qemu_coroutine_yield();

return cod.ret;

}

@@ -XXX,XX +XXX,XX @@ blkio_co_preadv(BlockDriverState *bs, int64_t offset, int64_t bytes,

WITH_QEMU_LOCK_GUARD(&s->blkio_lock) {

blkioq_readv(s->blkioq, offset, iov, iovcnt, &cod, 0);

- blkio_submit_io(bs);

}

+ blkio_submit_io(bs);

qemu_coroutine_yield();

if (use_bounce_buffer) {

@@ -XXX,XX +XXX,XX @@ static int coroutine_fn blkio_co_pwritev(BlockDriverState *bs, int64_t offset,

WITH_QEMU_LOCK_GUARD(&s->blkio_lock) {

blkioq_writev(s->blkioq, offset, iov, iovcnt, &cod, blkio_flags);

- blkio_submit_io(bs);

}

+ blkio_submit_io(bs);

qemu_coroutine_yield();

if (use_bounce_buffer) {

@@ -XXX,XX +XXX,XX @@ static int coroutine_fn blkio_co_flush(BlockDriverState *bs)

WITH_QEMU_LOCK_GUARD(&s->blkio_lock) {

blkioq_flush(s->blkioq, &cod, 0);

- blkio_submit_io(bs);

}

+ blkio_submit_io(bs);

qemu_coroutine_yield();

return cod.ret;

}

@@ -XXX,XX +XXX,XX @@ static int coroutine_fn blkio_co_pwrite_zeroes(BlockDriverState *bs,

WITH_QEMU_LOCK_GUARD(&s->blkio_lock) {

blkioq_write_zeroes(s->blkioq, offset, bytes, &cod, blkio_flags);

- blkio_submit_io(bs);

}

+ blkio_submit_io(bs);

qemu_coroutine_yield();

return cod.ret;

}

-static void coroutine_fn blkio_co_io_unplug(BlockDriverState *bs)

-{

- BDRVBlkioState *s = bs->opaque;

-

- WITH_QEMU_LOCK_GUARD(&s->blkio_lock) {

- blkio_submit_io(bs);

- }

-}

-

typedef enum {

BMRR_OK,

BMRR_SKIP,

@@ -XXX,XX +XXX,XX @@ static void blkio_refresh_limits(BlockDriverState *bs, Error **errp)

.bdrv_co_pwritev = blkio_co_pwritev, \

.bdrv_co_flush_to_disk = blkio_co_flush, \

.bdrv_co_pwrite_zeroes = blkio_co_pwrite_zeroes, \

- .bdrv_co_io_unplug = blkio_co_io_unplug, \

.bdrv_refresh_limits = blkio_refresh_limits, \

.bdrv_register_buf = blkio_register_buf, \

.bdrv_unregister_buf = blkio_unregister_buf, \

--

2.40.1

Stop using the .bdrv_co_io_plug() API because it is not multi-queue

block layer friendly. Use the new blk_io_plug_call() API to batch I/O

submission instead.

Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com>

Reviewed-by: Eric Blake <eblake@redhat.com>

Reviewed-by: Stefano Garzarella <sgarzare@redhat.com>

Acked-by: Kevin Wolf <kwolf@redhat.com>

Message-id: 20230530180959.1108766-5-stefanha@redhat.com

Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com>

---

include/block/raw-aio.h | 7 -------

block/file-posix.c | 10 ----------

block/io_uring.c | 44 ++++++++++++++++-------------------------

block/trace-events | 5 ++---

4 files changed, 19 insertions(+), 47 deletions(-)

diff --git a/include/block/raw-aio.h b/include/block/raw-aio.h

index XXXXXXX..XXXXXXX 100644

--- a/include/block/raw-aio.h

+++ b/include/block/raw-aio.h

@@ -XXX,XX +XXX,XX @@ int coroutine_fn luring_co_submit(BlockDriverState *bs, int fd, uint64_t offset,

QEMUIOVector *qiov, int type);

void luring_detach_aio_context(LuringState *s, AioContext *old_context);

void luring_attach_aio_context(LuringState *s, AioContext *new_context);

-

-/*

- * luring_io_plug/unplug work in the thread's current AioContext, therefore the

- * caller must ensure that they are paired in the same IOThread.

- */

-void luring_io_plug(void);

-void luring_io_unplug(void);

#endif

#ifdef _WIN32

diff --git a/block/file-posix.c b/block/file-posix.c

index XXXXXXX..XXXXXXX 100644

--- a/block/file-posix.c

+++ b/block/file-posix.c

@@ -XXX,XX +XXX,XX @@ static void coroutine_fn raw_co_io_plug(BlockDriverState *bs)

laio_io_plug();

}

#endif

-#ifdef CONFIG_LINUX_IO_URING

- if (s->use_linux_io_uring) {

- luring_io_plug();

- }

-#endif

}

static void coroutine_fn raw_co_io_unplug(BlockDriverState *bs)

@@ -XXX,XX +XXX,XX @@ static void coroutine_fn raw_co_io_unplug(BlockDriverState *bs)

laio_io_unplug(s->aio_max_batch);

}

#endif

-#ifdef CONFIG_LINUX_IO_URING

- if (s->use_linux_io_uring) {

- luring_io_unplug();

- }

-#endif

}

static int coroutine_fn raw_co_flush_to_disk(BlockDriverState *bs)

diff --git a/block/io_uring.c b/block/io_uring.c

index XXXXXXX..XXXXXXX 100644

--- a/block/io_uring.c

+++ b/block/io_uring.c

@@ -XXX,XX +XXX,XX @@

#include "block/raw-aio.h"

#include "qemu/coroutine.h"

#include "qapi/error.h"

+#include "sysemu/block-backend.h"

#include "trace.h"

/* Only used for assertions. */

@@ -XXX,XX +XXX,XX @@ typedef struct LuringAIOCB {

} LuringAIOCB;

typedef struct LuringQueue {

- int plugged;

unsigned int in_queue;

unsigned int in_flight;

bool blocked;

@@ -XXX,XX +XXX,XX @@ static void luring_process_completions_and_submit(LuringState *s)

{

luring_process_completions(s);

- if (!s->io_q.plugged && s->io_q.in_queue > 0) {

+ if (s->io_q.in_queue > 0) {

ioq_submit(s);

}

}

@@ -XXX,XX +XXX,XX @@ static void qemu_luring_poll_ready(void *opaque)

static void ioq_init(LuringQueue *io_q)

{

QSIMPLEQ_INIT(&io_q->submit_queue);

- io_q->plugged = 0;

io_q->in_queue = 0;

io_q->in_flight = 0;

io_q->blocked = false;

}

-void luring_io_plug(void)

+static void luring_unplug_fn(void *opaque)

{

- AioContext *ctx = qemu_get_current_aio_context();

- LuringState *s = aio_get_linux_io_uring(ctx);

- trace_luring_io_plug(s);

- s->io_q.plugged++;

-}

-

-void luring_io_unplug(void)

-{

- AioContext *ctx = qemu_get_current_aio_context();

- LuringState *s = aio_get_linux_io_uring(ctx);

- assert(s->io_q.plugged);

- trace_luring_io_unplug(s, s->io_q.blocked, s->io_q.plugged,

- s->io_q.in_queue, s->io_q.in_flight);

- if (--s->io_q.plugged == 0 &&

- !s->io_q.blocked && s->io_q.in_queue > 0) {

+ LuringState *s = opaque;

+ trace_luring_unplug_fn(s, s->io_q.blocked, s->io_q.in_queue,

+ s->io_q.in_flight);

+ if (!s->io_q.blocked && s->io_q.in_queue > 0) {

ioq_submit(s);

}

}

@@ -XXX,XX +XXX,XX @@ static int luring_do_submit(int fd, LuringAIOCB *luringcb, LuringState *s,

QSIMPLEQ_INSERT_TAIL(&s->io_q.submit_queue, luringcb, next);

s->io_q.in_queue++;

- trace_luring_do_submit(s, s->io_q.blocked, s->io_q.plugged,

- s->io_q.in_queue, s->io_q.in_flight);

- if (!s->io_q.blocked &&

- (!s->io_q.plugged ||

- s->io_q.in_flight + s->io_q.in_queue >= MAX_ENTRIES)) {

- ret = ioq_submit(s);

- trace_luring_do_submit_done(s, ret);

- return ret;

+ trace_luring_do_submit(s, s->io_q.blocked, s->io_q.in_queue,

+ s->io_q.in_flight);

+ if (!s->io_q.blocked) {

+ if (s->io_q.in_flight + s->io_q.in_queue >= MAX_ENTRIES) {

+ ret = ioq_submit(s);

+ trace_luring_do_submit_done(s, ret);

+ return ret;

+ }

+

+ blk_io_plug_call(luring_unplug_fn, s);

}

return 0;

}

diff --git a/block/trace-events b/block/trace-events

index XXXXXXX..XXXXXXX 100644

--- a/block/trace-events

+++ b/block/trace-events

@@ -XXX,XX +XXX,XX @@ file_paio_submit(void *acb, void *opaque, int64_t offset, int count, int type) "

# io_uring.c

luring_init_state(void *s, size_t size) "s %p size %zu"

luring_cleanup_state(void *s) "%p freed"

-luring_io_plug(void *s) "LuringState %p plug"

-luring_io_unplug(void *s, int blocked, int plugged, int queued, int inflight) "LuringState %p blocked %d plugged %d queued %d inflight %d"

-luring_do_submit(void *s, int blocked, int plugged, int queued, int inflight) "LuringState %p blocked %d plugged %d queued %d inflight %d"

+luring_unplug_fn(void *s, int blocked, int queued, int inflight) "LuringState %p blocked %d queued %d inflight %d"

+luring_do_submit(void *s, int blocked, int queued, int inflight) "LuringState %p blocked %d queued %d inflight %d"

luring_do_submit_done(void *s, int ret) "LuringState %p submitted to kernel %d"

luring_co_submit(void *bs, void *s, void *luringcb, int fd, uint64_t offset, size_t nbytes, int type) "bs %p s %p luringcb %p fd %d offset %" PRId64 " nbytes %zd type %d"

luring_process_completion(void *s, void *aiocb, int ret) "LuringState %p luringcb %p ret %d"

--

2.40.1

No block driver implements .bdrv_co_io_plug() anymore. Get rid of the

function pointers.

Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com>

Reviewed-by: Eric Blake <eblake@redhat.com>

Reviewed-by: Stefano Garzarella <sgarzare@redhat.com>

Acked-by: Kevin Wolf <kwolf@redhat.com>

Message-id: 20230530180959.1108766-7-stefanha@redhat.com

Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com>

---

include/block/block-io.h | 3 ---

include/block/block_int-common.h | 11 ----------

block/io.c | 37 --------------------------------

3 files changed, 51 deletions(-)

diff --git a/include/block/block-io.h b/include/block/block-io.h

index XXXXXXX..XXXXXXX 100644

--- a/include/block/block-io.h

+++ b/include/block/block-io.h

@@ -XXX,XX +XXX,XX @@ void coroutine_fn bdrv_co_leave(BlockDriverState *bs, AioContext *old_ctx);

AioContext *child_of_bds_get_parent_aio_context(BdrvChild *c);

-void coroutine_fn GRAPH_RDLOCK bdrv_co_io_plug(BlockDriverState *bs);

-void coroutine_fn GRAPH_RDLOCK bdrv_co_io_unplug(BlockDriverState *bs);

-

bool coroutine_fn GRAPH_RDLOCK

bdrv_co_can_store_new_dirty_bitmap(BlockDriverState *bs, const char *name,

uint32_t granularity, Error **errp);

diff --git a/include/block/block_int-common.h b/include/block/block_int-common.h

index XXXXXXX..XXXXXXX 100644

--- a/include/block/block_int-common.h

+++ b/include/block/block_int-common.h

@@ -XXX,XX +XXX,XX @@ struct BlockDriver {

void coroutine_fn GRAPH_RDLOCK_PTR (*bdrv_co_debug_event)(

BlockDriverState *bs, BlkdebugEvent event);

- /* io queue for linux-aio */

- void coroutine_fn GRAPH_RDLOCK_PTR (*bdrv_co_io_plug)(BlockDriverState *bs);

- void coroutine_fn GRAPH_RDLOCK_PTR (*bdrv_co_io_unplug)(

- BlockDriverState *bs);

-

bool (*bdrv_supports_persistent_dirty_bitmap)(BlockDriverState *bs);

bool coroutine_fn GRAPH_RDLOCK_PTR (*bdrv_co_can_store_new_dirty_bitmap)(

@@ -XXX,XX +XXX,XX @@ struct BlockDriverState {

unsigned int in_flight;

unsigned int serialising_in_flight;

- /*

- * counter for nested bdrv_io_plug.

- * Accessed with atomic ops.

- */

- unsigned io_plugged;

-

/* do we need to tell the quest if we have a volatile write cache? */

int enable_write_cache;

diff --git a/block/io.c b/block/io.c

index XXXXXXX..XXXXXXX 100644

--- a/block/io.c

+++ b/block/io.c

@@ -XXX,XX +XXX,XX @@ void *qemu_try_blockalign0(BlockDriverState *bs, size_t size)

return mem;

}

-void coroutine_fn bdrv_co_io_plug(BlockDriverState *bs)

-{

- BdrvChild *child;

- IO_CODE();

- assert_bdrv_graph_readable();

-

- QLIST_FOREACH(child, &bs->children, next) {

- bdrv_co_io_plug(child->bs);

- }

-

- if (qatomic_fetch_inc(&bs->io_plugged) == 0) {

- BlockDriver *drv = bs->drv;

- if (drv && drv->bdrv_co_io_plug) {

- drv->bdrv_co_io_plug(bs);

- }

- }

-}

-

-void coroutine_fn bdrv_co_io_unplug(BlockDriverState *bs)

-{

- BdrvChild *child;

- IO_CODE();

- assert_bdrv_graph_readable();

-

- assert(bs->io_plugged);

- if (qatomic_fetch_dec(&bs->io_plugged) == 1) {

- BlockDriver *drv = bs->drv;

- if (drv && drv->bdrv_co_io_unplug) {

- drv->bdrv_co_io_unplug(bs);

- }

- }

-

- QLIST_FOREACH(child, &bs->children, next) {

- bdrv_co_io_unplug(child->bs);

- }

-}

-

/* Helper that undoes bdrv_register_buf() when it fails partway through */

static void GRAPH_RDLOCK

bdrv_register_buf_rollback(BlockDriverState *bs, void *host, size_t size,

--

2.40.1

From: Stefano Garzarella <sgarzare@redhat.com>

The virtio-blk-vhost-vdpa driver in libblkio 1.3.0 supports the fd

passing through the new 'fd' property.

Since now we are using qemu_open() on '@path' if the virtio-blk driver

supports the fd passing, let's announce it.

In this way, the management layer can pass the file descriptor of an

already opened vhost-vdpa character device. This is useful especially

when the device can only be accessed with certain privileges.

Add the '@fdset' feature only when the virtio-blk-vhost-vdpa driver

in libblkio supports it.

Suggested-by: Markus Armbruster <armbru@redhat.com>

Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com>

Signed-off-by: Stefano Garzarella <sgarzare@redhat.com>

Message-id: 20230530071941.8954-3-sgarzare@redhat.com

Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com>

---