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

Block layer patches

# gpg: Signature made Thu 11 May 2017 10:31:37 AM EDT
# 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

* kwolf/tags/for-upstream: (58 commits)
  MAINTAINERS: Add qemu-progress to the block layer
  qcow2: Discard/zero clusters by byte count
  qcow2: Assert that cluster operations are aligned
  qcow2: Optimize write zero of unaligned tail cluster
  iotests: Add test 179 to cover write zeroes with unmap
  iotests: Improve _filter_qemu_img_map
  qcow2: Optimize zero_single_l2() to minimize L2 churn
  qcow2: Make distinction between zero cluster types obvious
  qcow2: Name typedef for cluster type
  qcow2: Correctly report status of preallocated zero clusters
  block: Update comments on BDRV_BLOCK_* meanings
  qcow2: Use consistent switch indentation
  qcow2: Nicer variable names in qcow2_update_snapshot_refcount()
  tests: Add coverage for recent block geometry fixes
  blkdebug: Add ability to override unmap geometries
  blkdebug: Simplify override logic
  blkdebug: Add pass-through write_zero and discard support
  blkdebug: Refactor error injection
  blkdebug: Sanity check block layer guarantees
  qemu-io: Switch 'map' output to byte-based reporting
  ...

Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com>

3 files changed, 40 insertions, 18 deletions

diff --git a/include/block/block.h b/include/block/block.h
index 862eb56fc7..9b355e92d8 100644
--- a/include/block/block.h
+++ b/include/block/block.h
@@ -109,6 +109,7 @@ typedef struct HDGeometry {
 #define BDRV_OPT_CACHE_NO_FLUSH "cache.no-flush"
 #define BDRV_OPT_READ_ONLY      "read-only"
 #define BDRV_OPT_DISCARD        "discard"
+#define BDRV_OPT_FORCE_SHARE    "force-share"
 
 
 #define BDRV_SECTOR_BITS   9
@@ -120,29 +121,32 @@ typedef struct HDGeometry {
 #define BDRV_REQUEST_MAX_BYTES (BDRV_REQUEST_MAX_SECTORS << BDRV_SECTOR_BITS)
 
 /*
- * Allocation status flags
- * BDRV_BLOCK_DATA: data is read from a file returned by bdrv_get_block_status.
- * BDRV_BLOCK_ZERO: sectors read as zero
- * BDRV_BLOCK_OFFSET_VALID: sector stored as raw data in a file returned by
- *                          bdrv_get_block_status.
+ * Allocation status flags for bdrv_get_block_status() and friends.
+ *
+ * Public flags:
+ * BDRV_BLOCK_DATA: allocation for data at offset is tied to this layer
+ * BDRV_BLOCK_ZERO: offset reads as zero
+ * BDRV_BLOCK_OFFSET_VALID: an associated offset exists for accessing raw data
  * BDRV_BLOCK_ALLOCATED: the content of the block is determined by this
- *                       layer (as opposed to the backing file)
- * BDRV_BLOCK_RAW: used internally to indicate that the request
- *                 was answered by the raw driver and that one
- *                 should look in bs->file directly.
+ *                       layer (short for DATA || ZERO), set by block layer
  *
- * If BDRV_BLOCK_OFFSET_VALID is set, bits 9-62 represent the offset in
- * bs->file where sector data can be read from as raw data.
+ * Internal flag:
+ * BDRV_BLOCK_RAW: used internally to indicate that the request was
+ *                 answered by a passthrough driver such as raw and that the
+ *                 block layer should recompute the answer from bs->file.
  *
- * DATA == 0 && ZERO == 0 means that data is read from backing_hd if present.
+ * If BDRV_BLOCK_OFFSET_VALID is set, bits 9-62 (BDRV_BLOCK_OFFSET_MASK)
+ * represent the offset in the returned BDS that is allocated for the
+ * corresponding raw data; however, whether that offset actually contains
+ * data also depends on BDRV_BLOCK_DATA and BDRV_BLOCK_ZERO, as follows:
  *
  * DATA ZERO OFFSET_VALID
- *  t    t        t       sectors read as zero, bs->file is zero at offset
- *  t    f        t       sectors read as valid from bs->file at offset
- *  f    t        t       sectors preallocated, read as zero, bs->file not
+ *  t    t        t       sectors read as zero, returned file is zero at offset
+ *  t    f        t       sectors read as valid from file at offset
+ *  f    t        t       sectors preallocated, read as zero, returned file not
  *                        necessarily zero at offset
  *  f    f        t       sectors preallocated but read from backing_hd,
- *                        bs->file contains garbage at offset
+ *                        returned file contains garbage at offset
  *  t    t        f       sectors preallocated, read as zero, unknown offset
  *  t    f        f       sectors read from unknown file or offset
  *  f    t        f       not allocated or unknown offset, read as zero
@@ -224,6 +228,8 @@ enum {
     BLK_PERM_ALL                = 0x1f,
 };
 
+char *bdrv_perm_names(uint64_t perm);
+
 /* disk I/O throttling */
 void bdrv_init(void);
 void bdrv_init_with_whitelist(void);
@@ -366,8 +372,6 @@ void bdrv_invalidate_cache(BlockDriverState *bs, Error **errp);
 void bdrv_invalidate_cache_all(Error **errp);
 int bdrv_inactivate_all(void);
 
-void blk_resume_after_migration(Error **errp);
-
 /* Ensure contents are flushed to disk.  */
 int bdrv_flush(BlockDriverState *bs);
 int coroutine_fn bdrv_co_flush(BlockDriverState *bs);
@@ -434,6 +438,7 @@ int bdrv_is_allocated_above(BlockDriverState *top, BlockDriverState *base,
                             int64_t sector_num, int nb_sectors, int *pnum);
 
 bool bdrv_is_read_only(BlockDriverState *bs);
+bool bdrv_is_writable(BlockDriverState *bs);
 int bdrv_can_set_read_only(BlockDriverState *bs, bool read_only, Error **errp);
 int bdrv_set_read_only(BlockDriverState *bs, bool read_only, Error **errp);
 bool bdrv_is_sg(BlockDriverState *bs);
diff --git a/include/block/block_int.h b/include/block/block_int.h
index 87739405d5..8d3724cce6 100644
--- a/include/block/block_int.h
+++ b/include/block/block_int.h
@@ -165,6 +165,13 @@ struct BlockDriver {
         int64_t offset, int count, BdrvRequestFlags flags);
     int coroutine_fn (*bdrv_co_pdiscard)(BlockDriverState *bs,
         int64_t offset, int count);
+
+    /*
+     * Building block for bdrv_block_status[_above]. The driver should
+     * answer only according to the current layer, and should not
+     * set BDRV_BLOCK_ALLOCATED, but may set BDRV_BLOCK_RAW.  See block.h
+     * for the meaning of _DATA, _ZERO, and _OFFSET_VALID.
+     */
     int64_t coroutine_fn (*bdrv_co_get_block_status)(BlockDriverState *bs,
         int64_t sector_num, int nb_sectors, int *pnum,
         BlockDriverState **file);
@@ -473,6 +480,12 @@ struct BdrvChildRole {
     void (*drained_begin)(BdrvChild *child);
     void (*drained_end)(BdrvChild *child);
 
+    /* Notifies the parent that the child has been activated/inactivated (e.g.
+     * when migration is completing) and it can start/stop requesting
+     * permissions and doing I/O on it. */
+    void (*activate)(BdrvChild *child, Error **errp);
+    int (*inactivate)(BdrvChild *child);
+
     void (*attach)(BdrvChild *child);
     void (*detach)(BdrvChild *child);
 };
@@ -518,6 +531,7 @@ struct BlockDriverState {
     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 */
+    bool force_share; /* if true, always allow all shared permissions */
 
     BlockDriver *drv; /* NULL means no media */
     void *opaque;
diff --git a/include/qemu/osdep.h b/include/qemu/osdep.h
index 122ff06ff6..1c9f5e260c 100644
--- a/include/qemu/osdep.h
+++ b/include/qemu/osdep.h
@@ -341,6 +341,9 @@ int qemu_close(int fd);
 #ifndef _WIN32
 int qemu_dup(int fd);
 #endif
+int qemu_lock_fd(int fd, int64_t start, int64_t len, bool exclusive);
+int qemu_unlock_fd(int fd, int64_t start, int64_t len);
+int qemu_lock_fd_test(int fd, int64_t start, int64_t len, bool exclusive);
 
 #if defined(__HAIKU__) && defined(__i386__)
 #define FMT_pid "%ld"