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

Block layer patches

# gpg: Signature made Tue 05 Jul 2016 16:46:14 BST
# gpg:                using RSA key 0x7F09B272C88F2FD6
# gpg: Good signature from "Kevin Wolf <kwolf@redhat.com>"
# Primary key fingerprint: DC3D EB15 9A9A F95D 3D74  56FE 7F09 B272 C88F 2FD6

* remotes/kevin/tags/for-upstream: (43 commits)
  block/qcow2: Don't use cpu_to_*w()
  block: Convert bdrv_co_preadv/pwritev to BdrvChild
  block: Convert bdrv_prwv_co() to BdrvChild
  block: Convert bdrv_pwrite_zeroes() to BdrvChild
  block: Convert bdrv_pwrite(v/_sync) to BdrvChild
  block: Convert bdrv_pread(v) to BdrvChild
  block: Convert bdrv_write() to BdrvChild
  block: Convert bdrv_read() to BdrvChild
  block: Use BlockBackend for I/O in bdrv_commit()
  block: Move bdrv_commit() to block/commit.c
  block: Convert bdrv_co_do_readv/writev to BdrvChild
  block: Convert bdrv_aio_writev() to BdrvChild
  block: Convert bdrv_aio_readv() to BdrvChild
  block: Convert bdrv_co_writev() to BdrvChild
  block: Convert bdrv_co_readv() to BdrvChild
  vhdx: Some more BlockBackend use in vhdx_create()
  blkreplay: Convert to byte-based I/O
  vvfat: Use BdrvChild for s->qcow
  block/qdev: Fix NULL access when using BB twice
  block: fix return code for partial write for Linux AIO
  ...

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

4 files changed, 66 insertions, 48 deletions

diff --git a/include/block/block.h b/include/block/block.h
index 733a8ec2ec..616d8b9f12 100644
--- a/include/block/block.h
+++ b/include/block/block.h
@@ -226,33 +226,31 @@ int bdrv_reopen_prepare(BDRVReopenState *reopen_state,
                         BlockReopenQueue *queue, Error **errp);
 void bdrv_reopen_commit(BDRVReopenState *reopen_state);
 void bdrv_reopen_abort(BDRVReopenState *reopen_state);
-int bdrv_read(BlockDriverState *bs, int64_t sector_num,
+int bdrv_read(BdrvChild *child, int64_t sector_num,
               uint8_t *buf, int nb_sectors);
-int bdrv_write(BlockDriverState *bs, int64_t sector_num,
+int bdrv_write(BdrvChild *child, int64_t sector_num,
                const uint8_t *buf, int nb_sectors);
-int bdrv_pwrite_zeroes(BlockDriverState *bs, int64_t offset,
+int bdrv_pwrite_zeroes(BdrvChild *child, int64_t offset,
                        int count, BdrvRequestFlags flags);
-int bdrv_make_zero(BlockDriverState *bs, BdrvRequestFlags flags);
-int bdrv_pread(BlockDriverState *bs, int64_t offset,
-               void *buf, int count);
-int bdrv_preadv(BlockDriverState *bs, int64_t offset, QEMUIOVector *qiov);
-int bdrv_pwrite(BlockDriverState *bs, int64_t offset,
-                const void *buf, int count);
-int bdrv_pwritev(BlockDriverState *bs, int64_t offset, QEMUIOVector *qiov);
-int bdrv_pwrite_sync(BlockDriverState *bs, int64_t offset,
-    const void *buf, int count);
-int coroutine_fn bdrv_co_readv(BlockDriverState *bs, int64_t sector_num,
-    int nb_sectors, QEMUIOVector *qiov);
-int coroutine_fn bdrv_co_writev(BlockDriverState *bs, int64_t sector_num,
-    int nb_sectors, QEMUIOVector *qiov);
+int bdrv_make_zero(BdrvChild *child, BdrvRequestFlags flags);
+int bdrv_pread(BdrvChild *child, int64_t offset, void *buf, int bytes);
+int bdrv_preadv(BdrvChild *child, int64_t offset, QEMUIOVector *qiov);
+int bdrv_pwrite(BdrvChild *child, int64_t offset, const void *buf, int bytes);
+int bdrv_pwritev(BdrvChild *child, int64_t offset, QEMUIOVector *qiov);
+int bdrv_pwrite_sync(BdrvChild *child, int64_t offset,
+                     const void *buf, int count);
+int coroutine_fn bdrv_co_readv(BdrvChild *child, int64_t sector_num,
+                               int nb_sectors, QEMUIOVector *qiov);
+int coroutine_fn bdrv_co_writev(BdrvChild *child, int64_t sector_num,
+                               int nb_sectors, QEMUIOVector *qiov);
 /*
  * Efficiently zero a region of the disk image.  Note that this is a regular
  * I/O request like read or write and should have a reasonable size.  This
  * function is not suitable for zeroing the entire image in a single request
  * because it may allocate memory for the entire region.
  */
-int coroutine_fn bdrv_co_pwrite_zeroes(BlockDriverState *bs, int64_t offset,
-    int count, BdrvRequestFlags flags);
+int coroutine_fn bdrv_co_pwrite_zeroes(BdrvChild *child, int64_t offset,
+                                       int count, BdrvRequestFlags flags);
 BlockDriverState *bdrv_find_backing_image(BlockDriverState *bs,
     const char *backing_file);
 int bdrv_get_backing_file_depth(BlockDriverState *bs);
@@ -310,10 +308,10 @@ BlockDriverState *check_to_replace_node(BlockDriverState *parent_bs,
                                         const char *node_name, Error **errp);
 
 /* async block I/O */
-BlockAIOCB *bdrv_aio_readv(BlockDriverState *bs, int64_t sector_num,
+BlockAIOCB *bdrv_aio_readv(BdrvChild *child, int64_t sector_num,
                            QEMUIOVector *iov, int nb_sectors,
                            BlockCompletionFunc *cb, void *opaque);
-BlockAIOCB *bdrv_aio_writev(BlockDriverState *bs, int64_t sector_num,
+BlockAIOCB *bdrv_aio_writev(BdrvChild *child, int64_t sector_num,
                             QEMUIOVector *iov, int nb_sectors,
                             BlockCompletionFunc *cb, void *opaque);
 BlockAIOCB *bdrv_aio_flush(BlockDriverState *bs,
@@ -362,8 +360,8 @@ int bdrv_is_allocated(BlockDriverState *bs, int64_t sector_num, int nb_sectors,
 int bdrv_is_allocated_above(BlockDriverState *top, BlockDriverState *base,
                             int64_t sector_num, int nb_sectors, int *pnum);
 
-int bdrv_is_read_only(BlockDriverState *bs);
-int bdrv_is_sg(BlockDriverState *bs);
+bool bdrv_is_read_only(BlockDriverState *bs);
+bool bdrv_is_sg(BlockDriverState *bs);
 bool bdrv_is_inserted(BlockDriverState *bs);
 int bdrv_media_changed(BlockDriverState *bs);
 void bdrv_lock_medium(BlockDriverState *bs, bool locked);
@@ -390,8 +388,8 @@ BlockDriverState *bdrv_first(BdrvNextIterator *it);
 BlockDriverState *bdrv_next(BdrvNextIterator *it);
 
 BlockDriverState *bdrv_next_monitor_owned(BlockDriverState *bs);
-int bdrv_is_encrypted(BlockDriverState *bs);
-int bdrv_key_required(BlockDriverState *bs);
+bool bdrv_is_encrypted(BlockDriverState *bs);
+bool bdrv_key_required(BlockDriverState *bs);
 int bdrv_set_key(BlockDriverState *bs, const char *key);
 void bdrv_add_key(BlockDriverState *bs, const char *key, Error **errp);
 int bdrv_query_missing_keys(void);
diff --git a/include/block/block_int.h b/include/block/block_int.h
index 205715600b..47b9aac71b 100644
--- a/include/block/block_int.h
+++ b/include/block/block_int.h
@@ -324,30 +324,48 @@ struct BlockDriver {
 };
 
 typedef struct BlockLimits {
-    /* maximum number of sectors that can be discarded at once */
-    int max_discard;
-
-    /* optimal alignment for discard requests in sectors */
-    int64_t discard_alignment;
+    /* Alignment requirement, in bytes, for offset/length of I/O
+     * requests. Must be a power of 2 less than INT_MAX; defaults to
+     * 1 for drivers with modern byte interfaces, and to 512
+     * otherwise. */
+    uint32_t request_alignment;
+
+    /* maximum number of bytes that can be discarded at once (since it
+     * is signed, it must be < 2G, if set), should be multiple of
+     * pdiscard_alignment, but need not be power of 2. May be 0 if no
+     * inherent 32-bit limit */
+    int32_t max_pdiscard;
+
+    /* optimal alignment for discard requests in bytes, must be power
+     * of 2, less than max_pdiscard if that is set, and multiple of
+     * bl.request_alignment. May be 0 if bl.request_alignment is good
+     * enough */
+    uint32_t pdiscard_alignment;
 
     /* maximum number of bytes that can zeroized at once (since it is
-     * signed, it must be < 2G, if set) */
+     * signed, it must be < 2G, if set), should be multiple of
+     * pwrite_zeroes_alignment. May be 0 if no inherent 32-bit limit */
     int32_t max_pwrite_zeroes;
 
     /* optimal alignment for write zeroes requests in bytes, must be
-     * power of 2, and less than max_pwrite_zeroes if that is set */
+     * power of 2, less than max_pwrite_zeroes if that is set, and
+     * multiple of bl.request_alignment. May be 0 if
+     * bl.request_alignment is good enough */
     uint32_t pwrite_zeroes_alignment;
 
-    /* optimal transfer length in sectors */
-    int opt_transfer_length;
+    /* optimal transfer length in bytes (must be power of 2, and
+     * multiple of bl.request_alignment), or 0 if no preferred size */
+    uint32_t opt_transfer;
 
-    /* maximal transfer length in sectors */
-    int max_transfer_length;
+    /* maximal transfer length in bytes (need not be power of 2, but
+     * should be multiple of opt_transfer), or 0 for no 32-bit limit.
+     * For now, anything larger than INT_MAX is clamped down. */
+    uint32_t max_transfer;
 
-    /* memory alignment so that no bounce buffer is needed */
+    /* memory alignment, in bytes so that no bounce buffer is needed */
     size_t min_mem_alignment;
 
-    /* memory alignment for bounce buffer */
+    /* memory alignment, in bytes, for bounce buffer */
     size_t opt_mem_alignment;
 
     /* maximum number of iovec elements */
@@ -411,14 +429,15 @@ struct BdrvChild {
 struct BlockDriverState {
     int64_t total_sectors; /* if we are reading a disk image, give its
                               size in sectors */
-    int read_only; /* if true, the media is read only */
     int open_flags; /* flags used to open the file, re-used for re-open */
-    int encrypted; /* if true, the media is encrypted */
-    int valid_key; /* if true, a valid encryption key has been set */
-    int sg;        /* if true, the device is a /dev/sg* */
-    int copy_on_read; /* if true, copy read backing sectors into image
+    bool read_only; /* if true, the media is read only */
+    bool encrypted; /* if true, the media is encrypted */
+    bool valid_key; /* if true, a valid encryption key has been set */
+    bool sg;        /* if true, the device is a /dev/sg* */
+    bool probed;    /* if true, format was probed rather than specified */
+
+    int copy_on_read; /* if nonzero, copy read backing sectors into image.
                          note this is a reference count */
-    bool probed;
 
     BlockDriver *drv; /* NULL means no media */
     void *opaque;
@@ -453,8 +472,6 @@ struct BlockDriverState {
     /* I/O Limits */
     BlockLimits bl;
 
-    /* Alignment requirement for offset/length of I/O requests */
-    unsigned int request_alignment;
     /* Flags honored during pwrite (so far: BDRV_REQ_FUA) */
     unsigned int supported_write_flags;
     /* Flags honored during pwrite_zeroes (so far: BDRV_REQ_FUA,
@@ -546,10 +563,10 @@ extern BlockDriver bdrv_qcow2;
  */
 void bdrv_setup_io_funcs(BlockDriver *bdrv);
 
-int coroutine_fn bdrv_co_preadv(BlockDriverState *bs,
+int coroutine_fn bdrv_co_preadv(BdrvChild *child,
     int64_t offset, unsigned int bytes, QEMUIOVector *qiov,
     BdrvRequestFlags flags);
-int coroutine_fn bdrv_co_pwritev(BlockDriverState *bs,
+int coroutine_fn bdrv_co_pwritev(BdrvChild *child,
     int64_t offset, unsigned int bytes, QEMUIOVector *qiov,
     BdrvRequestFlags flags);
 
diff --git a/include/block/nbd.h b/include/block/nbd.h
index df1f804338..eeda3ebdf7 100644
--- a/include/block/nbd.h
+++ b/include/block/nbd.h
@@ -77,6 +77,8 @@ enum {
 
 /* Maximum size of a single READ/WRITE data buffer */
 #define NBD_MAX_BUFFER_SIZE (32 * 1024 * 1024)
+#define NBD_MAX_SECTORS (NBD_MAX_BUFFER_SIZE / BDRV_SECTOR_SIZE)
+
 /* Maximum size of an export name. The NBD spec requires 256 and
  * suggests that servers support up to 4096, but we stick to only the
  * required size so that we can stack-allocate the names, and because
diff --git a/include/sysemu/block-backend.h b/include/sysemu/block-backend.h
index c04af8ea46..3c3e82f05d 100644
--- a/include/sysemu/block-backend.h
+++ b/include/sysemu/block-backend.h
@@ -124,6 +124,7 @@ int blk_pwrite_zeroes(BlockBackend *blk, int64_t offset,
 BlockAIOCB *blk_aio_pwrite_zeroes(BlockBackend *blk, int64_t offset,
                                   int count, BdrvRequestFlags flags,
                                   BlockCompletionFunc *cb, void *opaque);
+int blk_make_zero(BlockBackend *blk, BdrvRequestFlags flags);
 int blk_pread(BlockBackend *blk, int64_t offset, void *buf, int count);
 int blk_pwrite(BlockBackend *blk, int64_t offset, const void *buf, int count,
                BdrvRequestFlags flags);
@@ -170,7 +171,7 @@ bool blk_is_available(BlockBackend *blk);
 void blk_lock_medium(BlockBackend *blk, bool locked);
 void blk_eject(BlockBackend *blk, bool eject_flag);
 int blk_get_flags(BlockBackend *blk);
-int blk_get_max_transfer_length(BlockBackend *blk);
+uint32_t blk_get_max_transfer(BlockBackend *blk);
 int blk_get_max_iov(BlockBackend *blk);
 void blk_set_guest_block_size(BlockBackend *blk, int align);
 void *blk_try_blockalign(BlockBackend *blk, size_t size);