Merge remote-tracking branch 'remotes/kevin/tags/for-upstream' into staging

Block patches

# gpg: Signature made Tue Apr 28 15:35:05 2015 BST using RSA key ID C88F2FD6
# gpg: Good signature from "Kevin Wolf <kwolf@redhat.com>"

* remotes/kevin/tags/for-upstream: (76 commits)
  block: move I/O request processing to block/io.c
  block: extract bdrv_setup_io_funcs()
  block: add bdrv_set_dirty()/bdrv_reset_dirty() to block_int.h
  block: replace bdrv_states iteration with bdrv_next()
  vmdk: Widen before shifting 32 bit header field
  block/dmg: make it modular
  block/mirror: Always call block_job_sleep_ns()
  iotests: add incremental backup granularity tests
  iotests: add incremental backup failure recovery test
  iotests: add simple incremental backup case
  iotests: add QMP event waiting queue
  iotests: add invalid input incremental backup tests
  hbitmap: truncate tests
  block: Resize bitmaps on bdrv_truncate
  block: Ensure consistent bitmap function prototypes
  block: add BdrvDirtyBitmap documentation
  qmp: Add dirty bitmap status field in query-block
  qmp: add block-dirty-bitmap-clear
  qmp: Add support of "dirty-bitmap" sync mode for drive-backup
  block: Add bitmap successors
  ...

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

1 files changed, 66 insertions, 21 deletions

diff --git a/aio-posix.c b/aio-posix.c
index cbd4c3438c..4abec38866 100644
--- a/aio-posix.c
+++ b/aio-posix.c
@@ -24,7 +24,6 @@ struct AioHandler
     IOHandler *io_read;
     IOHandler *io_write;
     int deleted;
-    int pollfds_idx;
     void *opaque;
     QLIST_ENTRY(AioHandler) node;
 };
@@ -83,7 +82,6 @@ void aio_set_fd_handler(AioContext *ctx,
         node->io_read = io_read;
         node->io_write = io_write;
         node->opaque = opaque;
-        node->pollfds_idx = -1;
 
         node->pfd.events = (io_read ? G_IO_IN | G_IO_HUP | G_IO_ERR : 0);
         node->pfd.events |= (io_write ? G_IO_OUT | G_IO_ERR : 0);
@@ -186,13 +184,61 @@ bool aio_dispatch(AioContext *ctx)
     return progress;
 }
 
+/* These thread-local variables are used only in a small part of aio_poll
+ * around the call to the poll() system call.  In particular they are not
+ * used while aio_poll is performing callbacks, which makes it much easier
+ * to think about reentrancy!
+ *
+ * Stack-allocated arrays would be perfect but they have size limitations;
+ * heap allocation is expensive enough that we want to reuse arrays across
+ * calls to aio_poll().  And because poll() has to be called without holding
+ * any lock, the arrays cannot be stored in AioContext.  Thread-local data
+ * has none of the disadvantages of these three options.
+ */
+static __thread GPollFD *pollfds;
+static __thread AioHandler **nodes;
+static __thread unsigned npfd, nalloc;
+static __thread Notifier pollfds_cleanup_notifier;
+
+static void pollfds_cleanup(Notifier *n, void *unused)
+{
+    g_assert(npfd == 0);
+    g_free(pollfds);
+    g_free(nodes);
+    nalloc = 0;
+}
+
+static void add_pollfd(AioHandler *node)
+{
+    if (npfd == nalloc) {
+        if (nalloc == 0) {
+            pollfds_cleanup_notifier.notify = pollfds_cleanup;
+            qemu_thread_atexit_add(&pollfds_cleanup_notifier);
+            nalloc = 8;
+        } else {
+            g_assert(nalloc <= INT_MAX);
+            nalloc *= 2;
+        }
+        pollfds = g_renew(GPollFD, pollfds, nalloc);
+        nodes = g_renew(AioHandler *, nodes, nalloc);
+    }
+    nodes[npfd] = node;
+    pollfds[npfd] = (GPollFD) {
+        .fd = node->pfd.fd,
+        .events = node->pfd.events,
+    };
+    npfd++;
+}
+
 bool aio_poll(AioContext *ctx, bool blocking)
 {
     AioHandler *node;
     bool was_dispatching;
-    int ret;
+    int i, ret;
     bool progress;
+    int64_t timeout;
 
+    aio_context_acquire(ctx);
     was_dispatching = ctx->dispatching;
     progress = false;
 
@@ -210,39 +256,36 @@ bool aio_poll(AioContext *ctx, bool blocking)
 
     ctx->walking_handlers++;
 
-    g_array_set_size(ctx->pollfds, 0);
+    assert(npfd == 0);
 
     /* fill pollfds */
     QLIST_FOREACH(node, &ctx->aio_handlers, node) {
-        node->pollfds_idx = -1;
         if (!node->deleted && node->pfd.events) {
-            GPollFD pfd = {
-                .fd = node->pfd.fd,
-                .events = node->pfd.events,
-            };
-            node->pollfds_idx = ctx->pollfds->len;
-            g_array_append_val(ctx->pollfds, pfd);
+            add_pollfd(node);
         }
     }
 
-    ctx->walking_handlers--;
+    timeout = blocking ? aio_compute_timeout(ctx) : 0;
 
     /* wait until next event */
-    ret = qemu_poll_ns((GPollFD *)ctx->pollfds->data,
-                         ctx->pollfds->len,
-                         blocking ? aio_compute_timeout(ctx) : 0);
+    if (timeout) {
+        aio_context_release(ctx);
+    }
+    ret = qemu_poll_ns((GPollFD *)pollfds, npfd, timeout);
+    if (timeout) {
+        aio_context_acquire(ctx);
+    }
 
     /* if we have any readable fds, dispatch event */
     if (ret > 0) {
-        QLIST_FOREACH(node, &ctx->aio_handlers, node) {
-            if (node->pollfds_idx != -1) {
-                GPollFD *pfd = &g_array_index(ctx->pollfds, GPollFD,
-                                              node->pollfds_idx);
-                node->pfd.revents = pfd->revents;
-            }
+        for (i = 0; i < npfd; i++) {
+            nodes[i]->pfd.revents = pollfds[i].revents;
         }
     }
 
+    npfd = 0;
+    ctx->walking_handlers--;
+
     /* Run dispatch even if there were no readable fds to run timers */
     aio_set_dispatching(ctx, true);
     if (aio_dispatch(ctx)) {
@@ -250,5 +293,7 @@ bool aio_poll(AioContext *ctx, bool blocking)
     }
 
     aio_set_dispatching(ctx, was_dispatching);
+    aio_context_release(ctx);
+
     return progress;
 }