Merge remote-tracking branch 'remotes/maxreitz/tags/pull-block-2017-03-27' into staging

Block patches for 2.9-rc2.

# gpg: Signature made Mon 27 Mar 2017 16:47:54 BST
# gpg:                using RSA key 0xF407DB0061D5CF40
# gpg: Good signature from "Max Reitz <mreitz@redhat.com>"
# Primary key fingerprint: 91BE B60A 30DB 3E88 57D1  1829 F407 DB00 61D5 CF40

* remotes/maxreitz/tags/pull-block-2017-03-27:
  block/file-posix.c: Fix unused variable warning on OpenBSD
  file-posix: Make bdrv_flush() failure permanent without O_DIRECT
  nbd-client: fix handling of hungup connections
  qemu-img: print short help on getopt failure
  qemu-img: fix switch indentation in img_amend()
  qemu-img: show help for invalid global options

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

2 files changed, 42 insertions, 20 deletions

diff --git a/block/file-posix.c b/block/file-posix.c
index 53febd3767..0841a08785 100644
--- a/block/file-posix.c
+++ b/block/file-posix.c
@@ -144,6 +144,7 @@ typedef struct BDRVRawState {
     bool has_write_zeroes:1;
     bool discard_zeroes:1;
     bool use_linux_aio:1;
+    bool page_cache_inconsistent:1;
     bool has_fallocate;
     bool needs_alignment;
 } BDRVRawState;
@@ -219,28 +220,28 @@ static int probe_logical_blocksize(int fd, unsigned int *sector_size_p)
 {
     unsigned int sector_size;
     bool success = false;
+    int i;
 
     errno = ENOTSUP;
-
-    /* Try a few ioctls to get the right size */
+    static const unsigned long ioctl_list[] = {
 #ifdef BLKSSZGET
-    if (ioctl(fd, BLKSSZGET, &sector_size) >= 0) {
-        *sector_size_p = sector_size;
-        success = true;
-    }
+        BLKSSZGET,
 #endif
 #ifdef DKIOCGETBLOCKSIZE
-    if (ioctl(fd, DKIOCGETBLOCKSIZE, &sector_size) >= 0) {
-        *sector_size_p = sector_size;
-        success = true;
-    }
+        DKIOCGETBLOCKSIZE,
 #endif
 #ifdef DIOCGSECTORSIZE
-    if (ioctl(fd, DIOCGSECTORSIZE, &sector_size) >= 0) {
-        *sector_size_p = sector_size;
-        success = true;
-    }
+        DIOCGSECTORSIZE,
 #endif
+    };
+
+    /* Try a few ioctls to get the right size */
+    for (i = 0; i < (int)ARRAY_SIZE(ioctl_list); i++) {
+        if (ioctl(fd, ioctl_list[i], &sector_size) >= 0) {
+            *sector_size_p = sector_size;
+            success = true;
+        }
+    }
 
     return success ? 0 : -errno;
 }
@@ -824,10 +825,31 @@ static ssize_t handle_aiocb_ioctl(RawPosixAIOData *aiocb)
 
 static ssize_t handle_aiocb_flush(RawPosixAIOData *aiocb)
 {
+    BDRVRawState *s = aiocb->bs->opaque;
     int ret;
 
+    if (s->page_cache_inconsistent) {
+        return -EIO;
+    }
+
     ret = qemu_fdatasync(aiocb->aio_fildes);
     if (ret == -1) {
+        /* There is no clear definition of the semantics of a failing fsync(),
+         * so we may have to assume the worst. The sad truth is that this
+         * assumption is correct for Linux. Some pages are now probably marked
+         * clean in the page cache even though they are inconsistent with the
+         * on-disk contents. The next fdatasync() call would succeed, but no
+         * further writeback attempt will be made. We can't get back to a state
+         * in which we know what is on disk (we would have to rewrite
+         * everything that was touched since the last fdatasync() at least), so
+         * make bdrv_flush() fail permanently. Given that the behaviour isn't
+         * really defined, I have little hope that other OSes are doing better.
+         *
+         * Obviously, this doesn't affect O_DIRECT, which bypasses the page
+         * cache. */
+        if ((s->open_flags & O_DIRECT) == 0) {
+            s->page_cache_inconsistent = true;
+        }
         return -errno;
     }
     return 0;
diff --git a/block/nbd-client.c b/block/nbd-client.c
index 0dc12c2d67..1e2952fdae 100644
--- a/block/nbd-client.c
+++ b/block/nbd-client.c
@@ -33,17 +33,15 @@
 #define HANDLE_TO_INDEX(bs, handle) ((handle) ^ ((uint64_t)(intptr_t)bs))
 #define INDEX_TO_HANDLE(bs, index)  ((index)  ^ ((uint64_t)(intptr_t)bs))
 
-static void nbd_recv_coroutines_enter_all(BlockDriverState *bs)
+static void nbd_recv_coroutines_enter_all(NBDClientSession *s)
 {
-    NBDClientSession *s = nbd_get_client_session(bs);
     int i;
 
     for (i = 0; i < MAX_NBD_REQUESTS; i++) {
         if (s->recv_coroutine[i]) {
-            qemu_coroutine_enter(s->recv_coroutine[i]);
+            aio_co_wake(s->recv_coroutine[i]);
         }
     }
-    BDRV_POLL_WHILE(bs, s->read_reply_co);
 }
 
 static void nbd_teardown_connection(BlockDriverState *bs)
@@ -58,7 +56,7 @@ static void nbd_teardown_connection(BlockDriverState *bs)
     qio_channel_shutdown(client->ioc,
                          QIO_CHANNEL_SHUTDOWN_BOTH,
                          NULL);
-    nbd_recv_coroutines_enter_all(bs);
+    BDRV_POLL_WHILE(bs, client->read_reply_co);
 
     nbd_client_detach_aio_context(bs);
     object_unref(OBJECT(client->sioc));
@@ -76,7 +74,7 @@ static coroutine_fn void nbd_read_reply_entry(void *opaque)
     for (;;) {
         assert(s->reply.handle == 0);
         ret = nbd_receive_reply(s->ioc, &s->reply);
-        if (ret < 0) {
+        if (ret <= 0) {
             break;
         }
 
@@ -103,6 +101,8 @@ static coroutine_fn void nbd_read_reply_entry(void *opaque)
         aio_co_wake(s->recv_coroutine[i]);
         qemu_coroutine_yield();
     }
+
+    nbd_recv_coroutines_enter_all(s);
     s->read_reply_co = NULL;
 }