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

Block layer patches:

- Switch AIO/callback based block drivers to a byte-based interface
- Block jobs: Expose error string via query-block-jobs
- Block job cleanups and fixes
- hmp: Allow using a qdev id in block_set_io_throttle

# gpg: Signature made Tue 15 May 2018 16:33:10 BST
# gpg:                using RSA key 7F09B272C88F2FD6
# 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: (37 commits)
  iotests: Add test for -U/force-share conflicts
  qemu-img: Use only string options in img_open_opts
  qemu-io: Use purely string blockdev options
  block: Document BDRV_REQ_WRITE_UNCHANGED support
  qemu-img: Check post-truncation size
  iotests: Add test for COR across nodes
  iotests: Copy 197 for COR filter driver
  iotests: Clean up wrap image in 197
  block: Support BDRV_REQ_WRITE_UNCHANGED in filters
  block/quorum: Support BDRV_REQ_WRITE_UNCHANGED
  block: Set BDRV_REQ_WRITE_UNCHANGED for COR writes
  block: Add BDRV_REQ_WRITE_UNCHANGED flag
  block: BLK_PERM_WRITE includes ..._UNCHANGED
  block: Add COR filter driver
  iotests: Skip 181 and 201 without userfaultfd
  iotests: Add failure matching to common.qemu
  docs: Document the new default sizes of the qcow2 caches
  qcow2: Give the refcount cache the minimum possible size by default
  specs/qcow2: Clarify that compressed clusters have the COPIED bit reset
  Fix error message about compressed clusters with OFLAG_COPIED
  ...

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

5 files changed, 69 insertions, 13 deletions

diff --git a/include/block/block.h b/include/block/block.h
index cdec3639a3..3894edda9d 100644
--- a/include/block/block.h
+++ b/include/block/block.h
@@ -54,8 +54,12 @@ typedef enum {
     BDRV_REQ_FUA                = 0x10,
     BDRV_REQ_WRITE_COMPRESSED   = 0x20,
 
+    /* Signifies that this write request will not change the visible disk
+     * content. */
+    BDRV_REQ_WRITE_UNCHANGED    = 0x40,
+
     /* Mask of valid flags */
-    BDRV_REQ_MASK               = 0x3f,
+    BDRV_REQ_MASK               = 0x7f,
 } BdrvRequestFlags;
 
 typedef struct BlockSizes {
@@ -205,6 +209,9 @@ enum {
      * This permission (which is weaker than BLK_PERM_WRITE) is both enough and
      * required for writes to the block node when the caller promises that
      * the visible disk content doesn't change.
+     *
+     * As the BLK_PERM_WRITE permission is strictly stronger, either is
+     * sufficient to perform an unchanging write.
      */
     BLK_PERM_WRITE_UNCHANGED    = 0x04,
 
diff --git a/include/block/block_int.h b/include/block/block_int.h
index c4dd1d4bb8..76b589da57 100644
--- a/include/block/block_int.h
+++ b/include/block/block_int.h
@@ -141,11 +141,11 @@ struct BlockDriver {
     void (*bdrv_refresh_filename)(BlockDriverState *bs, QDict *options);
 
     /* aio */
-    BlockAIOCB *(*bdrv_aio_readv)(BlockDriverState *bs,
-        int64_t sector_num, QEMUIOVector *qiov, int nb_sectors,
+    BlockAIOCB *(*bdrv_aio_preadv)(BlockDriverState *bs,
+        uint64_t offset, uint64_t bytes, QEMUIOVector *qiov, int flags,
         BlockCompletionFunc *cb, void *opaque);
-    BlockAIOCB *(*bdrv_aio_writev)(BlockDriverState *bs,
-        int64_t sector_num, QEMUIOVector *qiov, int nb_sectors,
+    BlockAIOCB *(*bdrv_aio_pwritev)(BlockDriverState *bs,
+        uint64_t offset, uint64_t bytes, QEMUIOVector *qiov, int flags,
         BlockCompletionFunc *cb, void *opaque);
     BlockAIOCB *(*bdrv_aio_flush)(BlockDriverState *bs,
         BlockCompletionFunc *cb, void *opaque);
@@ -174,8 +174,6 @@ struct BlockDriver {
     int coroutine_fn (*bdrv_co_preadv)(BlockDriverState *bs,
         uint64_t offset, uint64_t bytes, QEMUIOVector *qiov, int flags);
     int coroutine_fn (*bdrv_co_writev)(BlockDriverState *bs,
-        int64_t sector_num, int nb_sectors, QEMUIOVector *qiov);
-    int coroutine_fn (*bdrv_co_writev_flags)(BlockDriverState *bs,
         int64_t sector_num, int nb_sectors, QEMUIOVector *qiov, int flags);
     /**
      * @offset: position in bytes to write at
@@ -658,10 +656,24 @@ struct BlockDriverState {
     /* I/O Limits */
     BlockLimits bl;
 
-    /* Flags honored during pwrite (so far: BDRV_REQ_FUA) */
+    /* Flags honored during pwrite (so far: BDRV_REQ_FUA,
+     * BDRV_REQ_WRITE_UNCHANGED).
+     * If a driver does not support BDRV_REQ_WRITE_UNCHANGED, those
+     * writes will be issued as normal writes without the flag set.
+     * This is important to note for drivers that do not explicitly
+     * request a WRITE permission for their children and instead take
+     * the same permissions as their parent did (this is commonly what
+     * block filters do).  Such drivers have to be aware that the
+     * parent may have taken a WRITE_UNCHANGED permission only and is
+     * issuing such requests.  Drivers either must make sure that
+     * these requests do not result in plain WRITE accesses (usually
+     * by supporting BDRV_REQ_WRITE_UNCHANGED, and then forwarding
+     * every incoming write request as-is, including potentially that
+     * flag), or they have to explicitly take the WRITE permission for
+     * their children. */
     unsigned int supported_write_flags;
     /* Flags honored during pwrite_zeroes (so far: BDRV_REQ_FUA,
-     * BDRV_REQ_MAY_UNMAP) */
+     * BDRV_REQ_MAY_UNMAP, BDRV_REQ_WRITE_UNCHANGED) */
     unsigned int supported_zero_flags;
 
     /* the following member gives a name to every node on the bs graph. */
diff --git a/include/block/blockjob.h b/include/block/blockjob.h
index fc645dac68..0f56f723de 100644
--- a/include/block/blockjob.h
+++ b/include/block/blockjob.h
@@ -27,6 +27,9 @@
 #define BLOCKJOB_H
 
 #include "block/block.h"
+#include "qemu/ratelimit.h"
+
+#define BLOCK_JOB_SLICE_TIME 100000000ULL /* ns */
 
 typedef struct BlockJobDriver BlockJobDriver;
 typedef struct BlockJobTxn BlockJobTxn;
@@ -118,6 +121,9 @@ typedef struct BlockJob {
     /** Speed that was set with @block_job_set_speed.  */
     int64_t speed;
 
+    /** Rate limiting data structure for implementing @speed. */
+    RateLimit limit;
+
     /** The completion function that will be called when the job completes.  */
     BlockCompletionFunc *cb;
 
@@ -278,6 +284,25 @@ void block_job_finalize(BlockJob *job, Error **errp);
 void block_job_dismiss(BlockJob **job, Error **errp);
 
 /**
+ * block_job_progress_update:
+ * @job: The job that has made progress
+ * @done: How much progress the job made
+ *
+ * Updates the progress counter of the job.
+ */
+void block_job_progress_update(BlockJob *job, uint64_t done);
+
+/**
+ * block_job_progress_set_remaining:
+ * @job: The job whose expected progress end value is set
+ * @remaining: Expected end value of the progress counter of the job
+ *
+ * Sets the expected end value of the progress counter of a job so that a
+ * completion percentage can be calculated when the progress is updated.
+ */
+void block_job_progress_set_remaining(BlockJob *job, uint64_t remaining);
+
+/**
  * block_job_query:
  * @job: The job to get information about.
  *
@@ -427,4 +452,11 @@ void block_job_txn_add_job(BlockJobTxn *txn, BlockJob *job);
  */
 bool block_job_is_internal(BlockJob *job);
 
+/**
+ * block_job_driver:
+ *
+ * Returns the driver associated with a block job.
+ */
+const BlockJobDriver *block_job_driver(BlockJob *job);
+
 #endif
diff --git a/include/block/blockjob_int.h b/include/block/blockjob_int.h
index d5a515de9b..62ec964d09 100644
--- a/include/block/blockjob_int.h
+++ b/include/block/blockjob_int.h
@@ -41,9 +41,6 @@ struct BlockJobDriver {
     /** String describing the operation, part of query-block-jobs QMP API */
     BlockJobType job_type;
 
-    /** Optional callback for job types that support setting a speed limit */
-    void (*set_speed)(BlockJob *job, int64_t speed, Error **errp);
-
     /** Mandatory: Entrypoint for the Coroutine. */
     CoroutineEntry *start;
 
@@ -169,6 +166,14 @@ void block_job_sleep_ns(BlockJob *job, int64_t ns);
 void block_job_yield(BlockJob *job);
 
 /**
+ * block_job_ratelimit_get_delay:
+ *
+ * Calculate and return delay for the next request in ns. See the documentation
+ * of ratelimit_calculate_delay() for details.
+ */
+int64_t block_job_ratelimit_get_delay(BlockJob *job, uint64_t n);
+
+/**
  * block_job_early_fail:
  * @bs: The block device.
  *
diff --git a/include/block/raw-aio.h b/include/block/raw-aio.h
index a4cdbbf1b7..9e47b8a629 100644
--- a/include/block/raw-aio.h
+++ b/include/block/raw-aio.h
@@ -57,7 +57,7 @@ void win32_aio_cleanup(QEMUWin32AIOState *aio);
 int win32_aio_attach(QEMUWin32AIOState *aio, HANDLE hfile);
 BlockAIOCB *win32_aio_submit(BlockDriverState *bs,
         QEMUWin32AIOState *aio, HANDLE hfile,
-        int64_t sector_num, QEMUIOVector *qiov, int nb_sectors,
+        uint64_t offset, uint64_t bytes, QEMUIOVector *qiov,
         BlockCompletionFunc *cb, void *opaque, int type);
 void win32_aio_detach_aio_context(QEMUWin32AIOState *aio,
                                   AioContext *old_context);