Block and testing patches

- Paolo's AIO fixes.
 - VMDK streamOptimized corner case fix
 - VM testing improvment on -cpu
 -----BEGIN PGP SIGNATURE-----
 
 iQFEBAABCAAuFiEEUAN8t5cGD3bwIa1WyjViTGqRccYFAluq9NAQHGZhbXpAcmVk
 aGF0LmNvbQAKCRDKNWJMapFxxm6mB/0XBuWySxCchAZDmkdcIqosrO7XZ6dKFpvW
 3uegPH3gUCpH6tw1YtigQSS+Se7tdnrUkOA5/5yOt8v2h9+6ORbIEYkkjGFpsPAL
 jITjIGSxXb2yjR0Ss+zKoR4tFQGYEVRmQSGZ8UHYiDVFHU0FbcwNkagHIyluoRuF
 +IspfB7bMXqrZ1qCCWROQDy7Cd2TJDeZ+jUtoiOACh7kyq5Q+PcVoeyeKKk1berH
 Kv8ZhdOk2t/te/CSaCpUTe5zYv3QI1tjcU1D6huYAkT9M8/3SasOeXHBNNG9zLE+
 zAtNKufd+VQoG7l24AfcPaUVqJlQ4GRDXFdumcgW3zA2Qf5CGyN7
 =pEHW
 -----END PGP SIGNATURE-----

Merge remote-tracking branch 'remotes/famz/tags/staging-pull-request' into staging

Block and testing patches

- Paolo's AIO fixes.
- VMDK streamOptimized corner case fix
- VM testing improvment on -cpu

# gpg: Signature made Wed 26 Sep 2018 03:54:08 BST
# gpg:                using RSA key CA35624C6A9171C6
# gpg: Good signature from "Fam Zheng <famz@redhat.com>"
# Primary key fingerprint: 5003 7CB7 9706 0F76 F021  AD56 CA35 624C 6A91 71C6

* remotes/famz/tags/staging-pull-request:
  vmdk: align end of file to a sector boundary
  tests/vm: Use -cpu max rather than -cpu host
  aio-posix: do skip system call if ctx->notifier polling succeeds
  aio-posix: compute timeout before polling
  aio-posix: fix concurrent access to poll_disable_cnt

Signed-off-by: Peter Maydell <peter.maydell@linaro.org>

block/vmdk.c

@@ -1698,6 +1698,27 @@ static int coroutine_fn
 vmdk_co_pwritev_compressed(BlockDriverState *bs, uint64_t offset,
                            uint64_t bytes, QEMUIOVector *qiov)
 {
+    if (bytes == 0) {
+        /* The caller will write bytes 0 to signal EOF.
+         * When receive it, we align EOF to a sector boundary. */
+        BDRVVmdkState *s = bs->opaque;
+        int i, ret;
+        int64_t length;
+
+        for (i = 0; i < s->num_extents; i++) {
+            length = bdrv_getlength(s->extents[i].file->bs);
+            if (length < 0) {
+                return length;
+            }
+            length = QEMU_ALIGN_UP(length, BDRV_SECTOR_SIZE);
+            ret = bdrv_truncate(s->extents[i].file, length,
+                                PREALLOC_MODE_OFF, NULL);
+            if (ret < 0) {
+                return ret;
+            }
+        }
+        return 0;
+    }
     return vmdk_co_pwritev(bs, offset, bytes, qiov, 0);
 }
 

tests/vm/basevm.py

@@ -65,6 +65,7 @@ class BaseVM(object):
             self._stdout = self._devnull
         self._args = [ \
             "-nodefaults", "-m", "4G",
+            "-cpu", "max",
             "-netdev", "user,id=vnet,hostfwd=:127.0.0.1:0-:22",
             "-device", "virtio-net-pci,netdev=vnet",
             "-vnc", "127.0.0.1:0,to=20",
@@ -72,11 +73,9 @@ class BaseVM(object):
         if vcpus:
             self._args += ["-smp", str(vcpus)]
         if os.access("/dev/kvm", os.R_OK | os.W_OK):
-            self._args += ["-cpu", "host"]
             self._args += ["-enable-kvm"]
         else:
             logging.info("KVM not available, not using -enable-kvm")
-            self._args += ["-cpu", "max"]
         self._data_args = []
 
     def _download_with_cache(self, url, sha256sum=None):

util/aio-posix.c

@@ -211,6 +211,7 @@ void aio_set_fd_handler(AioContext *ctx,
     AioHandler *node;
     bool is_new = false;
     bool deleted = false;
+    int poll_disable_change;
 
     qemu_lockcnt_lock(&ctx->list_lock);
 
@@ -244,11 +245,9 @@ void aio_set_fd_handler(AioContext *ctx,
             QLIST_REMOVE(node, node);
             deleted = true;
         }
-
+        poll_disable_change = -!node->io_poll;
-        if (!node->io_poll) {
-            ctx->poll_disable_cnt--;
-        }
     } else {
+        poll_disable_change = !io_poll - (node && !node->io_poll);
         if (node == NULL) {
             /* Alloc and insert if it's not already there */
             node = g_new0(AioHandler, 1);
@@ -257,10 +256,6 @@ void aio_set_fd_handler(AioContext *ctx,
 
             g_source_add_poll(&ctx->source, &node->pfd);
             is_new = true;
-
-            ctx->poll_disable_cnt += !io_poll;
-        } else {
-            ctx->poll_disable_cnt += !io_poll - !node->io_poll;
         }
 
         /* Update handler with latest information */
@@ -274,6 +269,15 @@ void aio_set_fd_handler(AioContext *ctx,
         node->pfd.events |= (io_write ? G_IO_OUT | G_IO_ERR : 0);
     }
 
+    /* No need to order poll_disable_cnt writes against other updates;
+     * the counter is only used to avoid wasting time and latency on
+     * iterated polling when the system call will be ultimately necessary.
+     * Changing handlers is a rare event, and a little wasted polling until
+     * the aio_notify below is not an issue.
+     */
+    atomic_set(&ctx->poll_disable_cnt,
+               atomic_read(&ctx->poll_disable_cnt) + poll_disable_change);
+
     aio_epoll_update(ctx, node, is_new);
     qemu_lockcnt_unlock(&ctx->list_lock);
     aio_notify(ctx);
@@ -486,7 +490,7 @@ static void add_pollfd(AioHandler *node)
     npfd++;
 }
 
-static bool run_poll_handlers_once(AioContext *ctx)
+static bool run_poll_handlers_once(AioContext *ctx, int64_t *timeout)
 {
     bool progress = false;
     AioHandler *node;
@@ -494,9 +498,11 @@ static bool run_poll_handlers_once(AioContext *ctx)
     QLIST_FOREACH_RCU(node, &ctx->aio_handlers, node) {
         if (!node->deleted && node->io_poll &&
             aio_node_check(ctx, node->is_external) &&
-            node->io_poll(node->opaque) &&
+            node->io_poll(node->opaque)) {
-            node->opaque != &ctx->notifier) {
+            *timeout = 0;
-            progress = true;
+            if (node->opaque != &ctx->notifier) {
+                progress = true;
+            }
         }
 
         /* Caller handles freeing deleted nodes.  Don't do it here. */
@@ -518,31 +524,38 @@ static bool run_poll_handlers_once(AioContext *ctx)
  *
  * Returns: true if progress was made, false otherwise
  */
-static bool run_poll_handlers(AioContext *ctx, int64_t max_ns)
+static bool run_poll_handlers(AioContext *ctx, int64_t max_ns, int64_t *timeout)
 {
     bool progress;
-    int64_t end_time;
+    int64_t start_time, elapsed_time;
 
     assert(ctx->notify_me);
     assert(qemu_lockcnt_count(&ctx->list_lock) > 0);
-    assert(ctx->poll_disable_cnt == 0);
 
-    trace_run_poll_handlers_begin(ctx, max_ns);
+    trace_run_poll_handlers_begin(ctx, max_ns, *timeout);
-
-    end_time = qemu_clock_get_ns(QEMU_CLOCK_REALTIME) + max_ns;
 
+    start_time = qemu_clock_get_ns(QEMU_CLOCK_REALTIME);
     do {
-        progress = run_poll_handlers_once(ctx);
+        progress = run_poll_handlers_once(ctx, timeout);
-    } while (!progress && qemu_clock_get_ns(QEMU_CLOCK_REALTIME) < end_time);
+        elapsed_time = qemu_clock_get_ns(QEMU_CLOCK_REALTIME) - start_time;
+    } while (!progress && elapsed_time < max_ns
+             && !atomic_read(&ctx->poll_disable_cnt));
 
-    trace_run_poll_handlers_end(ctx, progress);
+    /* If time has passed with no successful polling, adjust *timeout to
+     * keep the same ending time.
+     */
+    if (*timeout != -1) {
+        *timeout -= MIN(*timeout, elapsed_time);
+    }
 
+    trace_run_poll_handlers_end(ctx, progress, *timeout);
     return progress;
 }
 
 /* try_poll_mode:
  * @ctx: the AioContext
- * @blocking: busy polling is only attempted when blocking is true
+ * @timeout: timeout for blocking wait, computed by the caller and updated if
+ *    polling succeeds.
  *
  * ctx->notify_me must be non-zero so this function can detect aio_notify().
  *
@@ -550,19 +563,16 @@ static bool run_poll_handlers(AioContext *ctx, int64_t max_ns)
  *
  * Returns: true if progress was made, false otherwise
  */
-static bool try_poll_mode(AioContext *ctx, bool blocking)
+static bool try_poll_mode(AioContext *ctx, int64_t *timeout)
 {
-    if (blocking && ctx->poll_max_ns && ctx->poll_disable_cnt == 0) {
+    /* See qemu_soonest_timeout() uint64_t hack */
-        /* See qemu_soonest_timeout() uint64_t hack */
+    int64_t max_ns = MIN((uint64_t)*timeout, (uint64_t)ctx->poll_ns);
-        int64_t max_ns = MIN((uint64_t)aio_compute_timeout(ctx),
-                             (uint64_t)ctx->poll_ns);
 
-        if (max_ns) {
+    if (max_ns && !atomic_read(&ctx->poll_disable_cnt)) {
-            poll_set_started(ctx, true);
+        poll_set_started(ctx, true);
 
-            if (run_poll_handlers(ctx, max_ns)) {
+        if (run_poll_handlers(ctx, max_ns, timeout)) {
-                return true;
+            return true;
-            }
         }
     }
 
@@ -571,7 +581,7 @@ static bool try_poll_mode(AioContext *ctx, bool blocking)
     /* Even if we don't run busy polling, try polling once in case it can make
      * progress and the caller will be able to avoid ppoll(2)/epoll_wait(2).
      */
-    return run_poll_handlers_once(ctx);
+    return run_poll_handlers_once(ctx, timeout);
 }
 
 bool aio_poll(AioContext *ctx, bool blocking)
@@ -601,8 +611,14 @@ bool aio_poll(AioContext *ctx, bool blocking)
         start = qemu_clock_get_ns(QEMU_CLOCK_REALTIME);
     }
 
-    progress = try_poll_mode(ctx, blocking);
+    timeout = blocking ? aio_compute_timeout(ctx) : 0;
-    if (!progress) {
+    progress = try_poll_mode(ctx, &timeout);
+    assert(!(timeout && progress));
+
+    /* If polling is allowed, non-blocking aio_poll does not need the
+     * system call---a single round of run_poll_handlers_once suffices.
+     */
+    if (timeout || atomic_read(&ctx->poll_disable_cnt)) {
         assert(npfd == 0);
 
         /* fill pollfds */
@@ -616,8 +632,6 @@ bool aio_poll(AioContext *ctx, bool blocking)
             }
         }
 
-        timeout = blocking ? aio_compute_timeout(ctx) : 0;
-
         /* wait until next event */
         if (aio_epoll_check_poll(ctx, pollfds, npfd, timeout)) {
             AioHandler epoll_handler;

util/trace-events

@@ -1,8 +1,8 @@
 # See docs/devel/tracing.txt for syntax documentation.
 
 # util/aio-posix.c
-run_poll_handlers_begin(void *ctx, int64_t max_ns) "ctx %p max_ns %"PRId64
+run_poll_handlers_begin(void *ctx, int64_t max_ns, int64_t timeout) "ctx %p max_ns %"PRId64 " timeout %"PRId64
-run_poll_handlers_end(void *ctx, bool progress) "ctx %p progress %d"
+run_poll_handlers_end(void *ctx, bool progress, int64_t timeout) "ctx %p progress %d new timeout %"PRId64
 poll_shrink(void *ctx, int64_t old, int64_t new) "ctx %p old %"PRId64" new %"PRId64
 poll_grow(void *ctx, int64_t old, int64_t new) "ctx %p old %"PRId64" new %"PRId64