Merge remote-tracking branch 'remotes/cody/tags/block-pull-request' i…

…nto staging

# gpg: Signature made Fri 25 Sep 2015 16:47:31 BST using RSA key ID C0DE3057
# gpg: Good signature from "Jeffrey Cody <jcody@redhat.com>"
# gpg:                 aka "Jeffrey Cody <jeff@codyprime.org>"
# gpg:                 aka "Jeffrey Cody <codyprime@gmail.com>"

* remotes/cody/tags/block-pull-request:
  sheepdog: refine discard support
  sheepdog: use per AIOCB dirty indexes for non overlapping requests
  Backup: don't do copy-on-read in before_write_notifier
  block: Introduce a new API bdrv_co_no_copy_on_readv()
  sheepdog: add reopen support
  block/nfs: cache allocated filesize for read-only files
  block/nfs: fix calculation of allocated file size

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

block/backup.c

@@ -89,7 +89,8 @@ static void cow_request_end(CowRequest *req)
 
 static int coroutine_fn backup_do_cow(BlockDriverState *bs,
                                       int64_t sector_num, int nb_sectors,
-                                      bool *error_is_read)
+                                      bool *error_is_read,
+                                      bool is_write_notifier)
 {
     BackupBlockJob *job = (BackupBlockJob *)bs->job;
     CowRequest cow_request;
@@ -129,8 +130,14 @@ static int coroutine_fn backup_do_cow(BlockDriverState *bs,
         iov.iov_len = n * BDRV_SECTOR_SIZE;
         qemu_iovec_init_external(&bounce_qiov, &iov, 1);
 
-        ret = bdrv_co_readv(bs, start * BACKUP_SECTORS_PER_CLUSTER, n,
-                            &bounce_qiov);
+        if (is_write_notifier) {
+            ret = bdrv_co_no_copy_on_readv(bs,
+                                           start * BACKUP_SECTORS_PER_CLUSTER,
+                                           n, &bounce_qiov);
+        } else {
+            ret = bdrv_co_readv(bs, start * BACKUP_SECTORS_PER_CLUSTER, n,
+                                &bounce_qiov);
+        }
         if (ret < 0) {
             trace_backup_do_cow_read_fail(job, start, ret);
             if (error_is_read) {
@@ -190,7 +197,7 @@ static int coroutine_fn backup_before_write_notify(
     assert((req->offset & (BDRV_SECTOR_SIZE - 1)) == 0);
     assert((req->bytes & (BDRV_SECTOR_SIZE - 1)) == 0);
 
-    return backup_do_cow(req->bs, sector_num, nb_sectors, NULL);
+    return backup_do_cow(req->bs, sector_num, nb_sectors, NULL, true);
 }
 
 static void backup_set_speed(BlockJob *job, int64_t speed, Error **errp)
@@ -303,7 +310,8 @@ static int coroutine_fn backup_run_incremental(BackupBlockJob *job)
                     return ret;
                 }
                 ret = backup_do_cow(bs, cluster * BACKUP_SECTORS_PER_CLUSTER,
-                                    BACKUP_SECTORS_PER_CLUSTER, &error_is_read);
+                                    BACKUP_SECTORS_PER_CLUSTER, &error_is_read,
+                                    false);
                 if ((ret < 0) &&
                     backup_error_action(job, error_is_read, -ret) ==
                     BLOCK_ERROR_ACTION_REPORT) {
@@ -408,7 +416,7 @@ static void coroutine_fn backup_run(void *opaque)
             }
             /* FULL sync mode we copy the whole drive. */
             ret = backup_do_cow(bs, start * BACKUP_SECTORS_PER_CLUSTER,
-                    BACKUP_SECTORS_PER_CLUSTER, &error_is_read);
+                    BACKUP_SECTORS_PER_CLUSTER, &error_is_read, false);
             if (ret < 0) {
                 /* Depending on error action, fail now or retry cluster */
                 BlockErrorAction action =

block/io.c

@@ -932,7 +932,8 @@ static int coroutine_fn bdrv_co_do_preadv(BlockDriverState *bs,
         return ret;
     }
 
-    if (bs->copy_on_read) {
+    /* Don't do copy-on-read if we read data before write operation */
+    if (bs->copy_on_read && !(flags & BDRV_REQ_NO_COPY_ON_READ)) {
         flags |= BDRV_REQ_COPY_ON_READ;
     }
 
@@ -1001,6 +1002,15 @@ int coroutine_fn bdrv_co_readv(BlockDriverState *bs, int64_t sector_num,
     return bdrv_co_do_readv(bs, sector_num, nb_sectors, qiov, 0);
 }
 
+int coroutine_fn bdrv_co_no_copy_on_readv(BlockDriverState *bs,
+    int64_t sector_num, int nb_sectors, QEMUIOVector *qiov)
+{
+    trace_bdrv_co_no_copy_on_readv(bs, sector_num, nb_sectors);
+
+    return bdrv_co_do_readv(bs, sector_num, nb_sectors, qiov,
+                            BDRV_REQ_NO_COPY_ON_READ);
+}
+
 int coroutine_fn bdrv_co_copy_on_readv(BlockDriverState *bs,
     int64_t sector_num, int nb_sectors, QEMUIOVector *qiov)
 {

block/nfs.c

@@ -43,6 +43,7 @@ typedef struct NFSClient {
     int events;
     bool has_zero_init;
     AioContext *aio_context;
+    blkcnt_t st_blocks;
 } NFSClient;
 
 typedef struct NFSRPC {
@@ -374,6 +375,7 @@ static int64_t nfs_client_open(NFSClient *client, const char *filename,
     }
 
     ret = DIV_ROUND_UP(st.st_size, BDRV_SECTOR_SIZE);
+    client->st_blocks = st.st_blocks;
     client->has_zero_init = S_ISREG(st.st_mode);
     goto out;
 fail:
@@ -464,6 +466,11 @@ static int64_t nfs_get_allocated_file_size(BlockDriverState *bs)
     NFSRPC task = {0};
     struct stat st;
 
+    if (bdrv_is_read_only(bs) &&
+        !(bs->open_flags & BDRV_O_NOCACHE)) {
+        return client->st_blocks * 512;
+    }
+
     task.st = &st;
     if (nfs_fstat_async(client->context, client->fh, nfs_co_generic_cb,
                         &task) != 0) {
@@ -475,7 +482,7 @@ static int64_t nfs_get_allocated_file_size(BlockDriverState *bs)
         aio_poll(client->aio_context, true);
     }
 
-    return (task.ret < 0 ? task.ret : st.st_blocks * st.st_blksize);
+    return (task.ret < 0 ? task.ret : st.st_blocks * 512);
 }
 
 static int nfs_file_truncate(BlockDriverState *bs, int64_t offset)
@@ -484,6 +491,34 @@ static int nfs_file_truncate(BlockDriverState *bs, int64_t offset)
     return nfs_ftruncate(client->context, client->fh, offset);
 }
 
+/* Note that this will not re-establish a connection with the NFS server
+ * - it is effectively a NOP.  */
+static int nfs_reopen_prepare(BDRVReopenState *state,
+                              BlockReopenQueue *queue, Error **errp)
+{
+    NFSClient *client = state->bs->opaque;
+    struct stat st;
+    int ret = 0;
+
+    if (state->flags & BDRV_O_RDWR && bdrv_is_read_only(state->bs)) {
+        error_setg(errp, "Cannot open a read-only mount as read-write");
+        return -EACCES;
+    }
+
+    /* Update cache for read-only reopens */
+    if (!(state->flags & BDRV_O_RDWR)) {
+        ret = nfs_fstat(client->context, client->fh, &st);
+        if (ret < 0) {
+            error_setg(errp, "Failed to fstat file: %s",
+                       nfs_get_error(client->context));
+            return ret;
+        }
+        client->st_blocks = st.st_blocks;
+    }
+
+    return 0;
+}
+
 static BlockDriver bdrv_nfs = {
     .format_name                    = "nfs",
     .protocol_name                  = "nfs",
@@ -499,6 +534,7 @@ static BlockDriver bdrv_nfs = {
     .bdrv_file_open                 = nfs_file_open,
     .bdrv_close                     = nfs_file_close,
     .bdrv_create                    = nfs_file_create,
+    .bdrv_reopen_prepare            = nfs_reopen_prepare,
 
     .bdrv_co_readv                  = nfs_co_readv,
     .bdrv_co_writev                 = nfs_co_writev,