The following changes since commit 171199f56f5f9bdf1e5d670d09ef1351d8f01bae:

Merge remote-tracking branch 'remotes/alistair/tags/pull-riscv-to-apply-20200619-3' into staging (2020-06-22 14:45:25 +0100)

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

for you to fetch changes up to 7838c67f22a81fcf669785cd6c0876438422071a:

block/nvme: support nested aio_poll() (2020-06-23 15:46:08 +0100)

Daniele Buono (4):

coroutine: support SafeStack in ucontext backend

coroutine: add check for SafeStack in sigaltstack

configure: add flags to support SafeStack

check-block: enable iotests with SafeStack

Stefan Hajnoczi (8):

minikconf: explicitly set encoding to UTF-8

block/nvme: poll queues without q->lock

block/nvme: drop tautologous assertion

block/nvme: don't access CQE after moving cq.head

block/nvme: switch to a NVMeRequest freelist

block/nvme: clarify that free_req_queue is protected by q->lock

block/nvme: keep BDRVNVMeState pointer in NVMeQueuePair

block/nvme: support nested aio_poll()

configure | 73 ++++++++++++

include/qemu/coroutine_int.h | 5 +

block/nvme.c | 220 +++++++++++++++++++++++++----------

util/coroutine-sigaltstack.c | 4 +

util/coroutine-ucontext.c | 28 +++++

block/trace-events | 2 +-

scripts/minikconf.py | 6 +-

tests/check-block.sh | 12 +-

8 files changed, 284 insertions(+), 66 deletions(-)

2.26.2

QEMU block drivers are supposed to support aio_poll() from I/O

completion callback functions. This means completion processing must be

re-entrant.

The standard approach is to schedule a BH during completion processing

and cancel it at the end of processing. If aio_poll() is invoked by a

callback function then the BH will run. The BH continues the suspended

completion processing.

All of this means that request A's cb() can synchronously wait for

request B to complete. Previously the nvme block driver would hang

because it didn't process completions from nested aio_poll().

Reviewed-by: Sergio Lopez <slp@redhat.com>

Message-id: 20200617132201.1832152-8-stefanha@redhat.com

block/nvme.c | 67 ++++++++++++++++++++++++++++++++++++++++------

block/trace-events | 2 +-

2 files changed, 60 insertions(+), 9 deletions(-)

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

--- a/block/nvme.c

+++ b/block/nvme.c

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

int cq_phase;

int free_req_head;

NVMeRequest reqs[NVME_NUM_REQS];

- bool busy;

int need_kick;

int inflight;

+ /* Thread-safe, no lock necessary */

+ QEMUBH *completion_bh;

} NVMeQueuePair;

/* Memory mapped registers */

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

#define NVME_BLOCK_OPT_DEVICE "device"

#define NVME_BLOCK_OPT_NAMESPACE "namespace"

+static void nvme_process_completion_bh(void *opaque);

static QemuOptsList runtime_opts = {

.name = "nvme",

.head = QTAILQ_HEAD_INITIALIZER(runtime_opts.head),

@@ -XXX,XX +XXX,XX @@ static void nvme_init_queue(BlockDriverState *bs, NVMeQueue *q,

static void nvme_free_queue_pair(NVMeQueuePair *q)

{

+ if (q->completion_bh) {

+ qemu_bh_delete(q->completion_bh);

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

+ * Pending completions must be visible to aio_poll() so that a cb()

+ * function can wait for the completion of another request.

+ *

+ * The aio_poll() loop will execute our BH and we'll resume completion

+ * processing there.

+ qemu_bh_schedule(q->completion_bh);

assert(q->inflight >= 0);

while (q->inflight) {

int ret;

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

assert(req.cb);

nvme_put_free_req_locked(q, preq);

preq->cb = preq->opaque = NULL;

- qemu_mutex_unlock(&q->lock);

- req.cb(req.opaque, ret);

- qemu_mutex_lock(&q->lock);

q->inflight--;

+ qemu_mutex_unlock(&q->lock);

+ req.cb(req.opaque, ret);

+ qemu_mutex_lock(&q->lock);

progress = true;

}

if (progress) {

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

*q->cq.doorbell = cpu_to_le32(q->cq.head);

nvme_wake_free_req_locked(q);

}

- q->busy = false;

+

+ qemu_bh_cancel(q->completion_bh);

+

return progress;

}

+static void nvme_process_completion_bh(void *opaque)

+{

+ NVMeQueuePair *q = opaque;

+ * We're being invoked because a nvme_process_completion() cb() function

+ * called aio_poll(). The callback may be waiting for further completions

+ * so notify the device that it has space to fill in more completions now.

+ smp_mb_release();

+ *q->cq.doorbell = cpu_to_le32(q->cq.head);

+ nvme_wake_free_req_locked(q);

+ nvme_process_completion(q);

+}

+

static void nvme_trace_command(const NvmeCmd *cmd)

{

int i;

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

{

BDRVNVMeState *s = bs->opaque;

+ for (int i = 0; i < s->nr_queues; i++) {

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

+

+ qemu_bh_delete(q->completion_bh);

+ q->completion_bh = NULL;

+ }

+

aio_set_event_notifier(bdrv_get_aio_context(bs), &s->irq_notifier,

false, NULL, NULL);