The following changes since commit c6a5fc2ac76c5ab709896ee1b0edd33685a67ed1:

decodetree: Add --output-null for meson testing (2023-05-31 19:56:42 -0700)

https://gitlab.com/stefanha/qemu.git tags/block-pull-request

for you to fetch changes up to 98b126f5e3228a346c774e569e26689943b401dd:

qapi: add '@fdset' feature for BlockdevOptionsVirtioBlkVhostVdpa (2023-06-01 11:08:21 -0400)

- Stefano Garzarella's blkio block driver 'fd' parameter

- My thread-local blk_io_plug() series

Stefan Hajnoczi (6):

block: add blk_io_plug_call() API

block/nvme: convert to blk_io_plug_call() API

block/blkio: convert to blk_io_plug_call() API

block/io_uring: convert to blk_io_plug_call() API

block/linux-aio: convert to blk_io_plug_call() API

block: remove bdrv_co_io_plug() API

Stefano Garzarella (2):

block/blkio: use qemu_open() to support fd passing for virtio-blk

qapi: add '@fdset' feature for BlockdevOptionsVirtioBlkVhostVdpa

MAINTAINERS | 1 +

qapi/block-core.json | 6 ++

meson.build | 4 +

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

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

include/block/raw-aio.h | 14 ---

include/sysemu/block-backend-io.h | 13 +--

block/blkio.c | 96 ++++++++++++------

block/block-backend.c | 22 -----

block/file-posix.c | 38 -------

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

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

block/linux-aio.c | 41 +++-----

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

block/plug.c | 159 ++++++++++++++++++++++++++++++

hw/block/dataplane/xen-block.c | 8 +-

hw/block/virtio-blk.c | 4 +-

hw/scsi/virtio-scsi.c | 6 +-

block/meson.build | 1 +

block/trace-events | 6 +-

20 files changed, 293 insertions(+), 265 deletions(-)

create mode 100644 block/plug.c

2.40.1

Introduce a new API for thread-local blk_io_plug() that does not

traverse the block graph. The goal is to make blk_io_plug() multi-queue

friendly.

Instead of having block drivers track whether or not we're in a plugged

section, provide an API that allows them to defer a function call until

we're unplugged: blk_io_plug_call(fn, opaque). If blk_io_plug_call() is

called multiple times with the same fn/opaque pair, then fn() is only

called once at the end of the function - resulting in batching.

This patch introduces the API and changes blk_io_plug()/blk_io_unplug().

blk_io_plug()/blk_io_unplug() no longer require a BlockBackend argument

because the plug state is now thread-local.

Later patches convert block drivers to blk_io_plug_call() and then we

can finally remove .bdrv_co_io_plug() once all block drivers have been

converted.

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: 20230530180959.1108766-2-stefanha@redhat.com

MAINTAINERS | 1 +

include/sysemu/block-backend-io.h | 13 +--

block/block-backend.c | 22 -----

block/plug.c | 159 ++++++++++++++++++++++++++++++

hw/block/dataplane/xen-block.c | 8 +-

hw/block/virtio-blk.c | 4 +-

hw/scsi/virtio-scsi.c | 6 +-

block/meson.build | 1 +

8 files changed, 173 insertions(+), 41 deletions(-)

create mode 100644 block/plug.c

@@ -XXX,XX +XXX,XX @@ F: util/aio-*.c

F: util/aio-*.h

F: util/fdmon-*.c

F: block/io.c

+F: block/plug.c

F: migration/block*

F: include/block/aio.h

F: include/block/aio-wait.h

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

index XXXXXXX..XXXXXXX 100644

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

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

@@ -XXX,XX +XXX,XX @@ void blk_iostatus_set_err(BlockBackend *blk, int error);

int blk_get_max_iov(BlockBackend *blk);

int blk_get_max_hw_iov(BlockBackend *blk);

-/*

- * blk_io_plug/unplug are thread-local operations. This means that multiple

- * IOThreads can simultaneously call plug/unplug, but the caller must ensure

- * that each unplug() is called in the same IOThread of the matching plug().

- */

-void coroutine_fn blk_co_io_plug(BlockBackend *blk);

-void co_wrapper blk_io_plug(BlockBackend *blk);

-

-void coroutine_fn blk_co_io_unplug(BlockBackend *blk);

-void co_wrapper blk_io_unplug(BlockBackend *blk);

+void blk_io_plug(void);

+void blk_io_unplug(void);

+void blk_io_plug_call(void (*fn)(void *), void *opaque);

AioContext *blk_get_aio_context(BlockBackend *blk);

BlockAcctStats *blk_get_stats(BlockBackend *blk);

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

index XXXXXXX..XXXXXXX 100644

--- a/block/block-backend.c

+++ b/block/block-backend.c

@@ -XXX,XX +XXX,XX @@ void blk_add_insert_bs_notifier(BlockBackend *blk, Notifier *notify)

notifier_list_add(&blk->insert_bs_notifiers, notify);

}

-void coroutine_fn blk_co_io_plug(BlockBackend *blk)

-{

- BlockDriverState *bs = blk_bs(blk);

- IO_CODE();

- GRAPH_RDLOCK_GUARD();

-

- if (bs) {

- bdrv_co_io_plug(bs);

- }

-}

-

-void coroutine_fn blk_co_io_unplug(BlockBackend *blk)

-{

- BlockDriverState *bs = blk_bs(blk);

- IO_CODE();

- GRAPH_RDLOCK_GUARD();

-

- if (bs) {

- bdrv_co_io_unplug(bs);

- }

-}

-

BlockAcctStats *blk_get_stats(BlockBackend *blk)

{

IO_CODE();

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

+++ b/block/plug.c

+/* SPDX-License-Identifier: GPL-2.0-or-later */

+ * Block I/O plugging

+ *

+ * Copyright Red Hat.

+ *

+ * This API defers a function call within a blk_io_plug()/blk_io_unplug()

+ * section, allowing multiple calls to batch up. This is a performance

+ * optimization that is used in the block layer to submit several I/O requests

+ * at once instead of individually:

+ *

+ * blk_io_plug(); <-- start of plugged region

+ * ...

+ * blk_io_plug_call(my_func, my_obj); <-- deferred my_func(my_obj) call

+ * blk_io_plug_call(my_func, my_obj); <-- another

+ * blk_io_plug_call(my_func, my_obj); <-- another

+ * ...

+ * blk_io_unplug(); <-- end of plugged region, my_func(my_obj) is called once

+ *

+ * This code is actually generic and not tied to the block layer. If another

+ * subsystem needs this functionality, it could be renamed.

+#include "qemu/coroutine-tls.h"

+#include "qemu/notify.h"

+#include "qemu/thread.h"

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

+

+/* A function call that has been deferred until unplug() */

+typedef struct {

+ void (*fn)(void *);

+ void *opaque;

+} UnplugFn;

+

+/* Per-thread state */

+typedef struct {

+ unsigned count; /* how many times has plug() been called? */

+ GArray *unplug_fns; /* functions to call at unplug time */

+} Plug;

+

+/* Use get_ptr_plug() to fetch this thread-local value */

+QEMU_DEFINE_STATIC_CO_TLS(Plug, plug);

+

+/* Called at thread cleanup time */

+static void blk_io_plug_atexit(Notifier *n, void *value)

+ Plug *plug = get_ptr_plug();

+ g_array_free(plug->unplug_fns, TRUE);

+/* This won't involve coroutines, so use __thread */

+static __thread Notifier blk_io_plug_atexit_notifier;

+

+/**

+ * blk_io_plug_call:

+ * @fn: a function pointer to be invoked

+ * @opaque: a user-defined argument to @fn()

+ *

+ * Call @fn(@opaque) immediately if not within a blk_io_plug()/blk_io_unplug()

+ * section.

+ *

+ * Otherwise defer the call until the end of the outermost

+ * blk_io_plug()/blk_io_unplug() section in this thread. If the same

+ * @fn/@opaque pair has already been deferred, it will only be called once upon

+ * blk_io_unplug() so that accumulated calls are batched into a single call.

+ *

+ * The caller must ensure that @opaque is not freed before @fn() is invoked.

+ */

+void blk_io_plug_call(void (*fn)(void *), void *opaque)

+ Plug *plug = get_ptr_plug();

+

+ /* Call immediately if we're not plugged */

+ if (plug->count == 0) {

+ fn(opaque);

+ return;

+ }

+

+ GArray *array = plug->unplug_fns;

+ if (!array) {

+ array = g_array_new(FALSE, FALSE, sizeof(UnplugFn));

+ plug->unplug_fns = array;

+ blk_io_plug_atexit_notifier.notify = blk_io_plug_atexit;

+ qemu_thread_atexit_add(&blk_io_plug_atexit_notifier);

+ }

+

+ UnplugFn *fns = (UnplugFn *)array->data;

+ UnplugFn new_fn = {

+ .fn = fn,

+ .opaque = opaque,

+ };

+

+ /*

+ * There won't be many, so do a linear search. If this becomes a bottleneck

+ * then a binary search (glib 2.62+) or different data structure could be

+ * used.

+ */

+ for (guint i = 0; i < array->len; i++) {

+ if (memcmp(&fns[i], &new_fn, sizeof(new_fn)) == 0) {

+ return; /* already exists */

+ }

+ }

+

+ g_array_append_val(array, new_fn);

+/**

+ * blk_io_plug: Defer blk_io_plug_call() functions until blk_io_unplug()

+ *

+ * blk_io_plug/unplug are thread-local operations. This means that multiple

+ * threads can simultaneously call plug/unplug, but the caller must ensure that

+ * each unplug() is called in the same thread of the matching plug().

+ *

+ * Nesting is supported. blk_io_plug_call() functions are only called at the

+ * outermost blk_io_unplug().

+ */

+void blk_io_plug(void)

+ Plug *plug = get_ptr_plug();

+

+ assert(plug->count < UINT32_MAX);

+

+ plug->count++;

+/**

+ * blk_io_unplug: Run any pending blk_io_plug_call() functions

+ *

+ * There must have been a matching blk_io_plug() call in the same thread prior

+ * to this blk_io_unplug() call.

+ */

+void blk_io_unplug(void)

+ Plug *plug = get_ptr_plug();

+

+ assert(plug->count > 0);

+

+ if (--plug->count > 0) {

+ return;

+ }

+

+ GArray *array = plug->unplug_fns;

+ if (!array) {

+ return;

+ }

+

+ UnplugFn *fns = (UnplugFn *)array->data;

+

+ for (guint i = 0; i < array->len; i++) {

+ fns[i].fn(fns[i].opaque);

+ }

+

+ /*

+ * This resets the array without freeing memory so that appending is cheap

+ * in the future.

+ */

+ g_array_set_size(array, 0);

diff --git a/hw/block/dataplane/xen-block.c b/hw/block/dataplane/xen-block.c

index XXXXXXX..XXXXXXX 100644

--- a/hw/block/dataplane/xen-block.c

+++ b/hw/block/dataplane/xen-block.c

@@ -XXX,XX +XXX,XX @@ static bool xen_block_handle_requests(XenBlockDataPlane *dataplane)

* is below us.

*/

if (inflight_atstart > IO_PLUG_THRESHOLD) {

- blk_io_plug(dataplane->blk);

+ blk_io_plug();

}

while (rc != rp) {

/* pull request from ring */

@@ -XXX,XX +XXX,XX @@ static bool xen_block_handle_requests(XenBlockDataPlane *dataplane)

if (inflight_atstart > IO_PLUG_THRESHOLD &&

batched >= inflight_atstart) {

- blk_io_unplug(dataplane->blk);

+ blk_io_unplug();

}

xen_block_do_aio(request);

if (inflight_atstart > IO_PLUG_THRESHOLD) {

if (batched >= inflight_atstart) {

- blk_io_plug(dataplane->blk);

+ blk_io_plug();

batched = 0;

} else {

batched++;

@@ -XXX,XX +XXX,XX @@ static bool xen_block_handle_requests(XenBlockDataPlane *dataplane)

}

}

if (inflight_atstart > IO_PLUG_THRESHOLD) {

- blk_io_unplug(dataplane->blk);

+ blk_io_unplug();

}

return done_something;

diff --git a/hw/block/virtio-blk.c b/hw/block/virtio-blk.c

index XXXXXXX..XXXXXXX 100644

--- a/hw/block/virtio-blk.c

+++ b/hw/block/virtio-blk.c

@@ -XXX,XX +XXX,XX @@ void virtio_blk_handle_vq(VirtIOBlock *s, VirtQueue *vq)

bool suppress_notifications = virtio_queue_get_notification(vq);

aio_context_acquire(blk_get_aio_context(s->blk));

- blk_io_plug(s->blk);

+ blk_io_plug();

do {

if (suppress_notifications) {

@@ -XXX,XX +XXX,XX @@ void virtio_blk_handle_vq(VirtIOBlock *s, VirtQueue *vq)

virtio_blk_submit_multireq(s, &mrb);

}

- blk_io_unplug(s->blk);

+ blk_io_unplug();

aio_context_release(blk_get_aio_context(s->blk));

}

diff --git a/hw/scsi/virtio-scsi.c b/hw/scsi/virtio-scsi.c

index XXXXXXX..XXXXXXX 100644

--- a/hw/scsi/virtio-scsi.c

+++ b/hw/scsi/virtio-scsi.c

@@ -XXX,XX +XXX,XX @@ static int virtio_scsi_handle_cmd_req_prepare(VirtIOSCSI *s, VirtIOSCSIReq *req)

return -ENOBUFS;

}

scsi_req_ref(req->sreq);

- blk_io_plug(d->conf.blk);

+ blk_io_plug();

object_unref(OBJECT(d));

return 0;

}

@@ -XXX,XX +XXX,XX @@ static void virtio_scsi_handle_cmd_req_submit(VirtIOSCSI *s, VirtIOSCSIReq *req)

if (scsi_req_enqueue(sreq)) {

scsi_req_continue(sreq);

}

- blk_io_unplug(sreq->dev->conf.blk);

+ blk_io_unplug();

scsi_req_unref(sreq);

}

@@ -XXX,XX +XXX,XX @@ static void virtio_scsi_handle_cmd_vq(VirtIOSCSI *s, VirtQueue *vq)

while (!QTAILQ_EMPTY(&reqs)) {

req = QTAILQ_FIRST(&reqs);

QTAILQ_REMOVE(&reqs, req, next);

- blk_io_unplug(req->sreq->dev->conf.blk);

+ blk_io_unplug();

scsi_req_unref(req->sreq);

virtqueue_detach_element(req->vq, &req->elem, 0);

virtio_scsi_free_req(req);

diff --git a/block/meson.build b/block/meson.build

index XXXXXXX..XXXXXXX 100644

--- a/block/meson.build

+++ b/block/meson.build

@@ -XXX,XX +XXX,XX @@ block_ss.add(files(

'mirror.c',

'nbd.c',

'null.c',

+ 'plug.c',

'qapi.c',

'qcow2-bitmap.c',

'qcow2-cache.c',

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.

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

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

--- 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.

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

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

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

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

--- 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)