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

Block layer patches for 2.8.0-rc1

# gpg: Signature made Tue 22 Nov 2016 03:55:38 PM GMT
# 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:
  block: Pass unaligned discard requests to drivers
  block: Return -ENOTSUP rather than assert on unaligned discards
  block: Let write zeroes fallback work even with small max_transfer
  qcow2: Inform block layer about discard boundaries

Message-id: 1479830693-26676-1-git-send-email-kwolf@redhat.com
Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com>

4 files changed, 52 insertions, 21 deletions

diff --git a/block/io.c b/block/io.c
index aa532a5c1f..4f005623f7 100644
--- a/block/io.c
+++ b/block/io.c
@@ -1214,6 +1214,8 @@ static int coroutine_fn bdrv_co_do_pwrite_zeroes(BlockDriverState *bs,
     int max_write_zeroes = MIN_NON_ZERO(bs->bl.max_pwrite_zeroes, INT_MAX);
     int alignment = MAX(bs->bl.pwrite_zeroes_alignment,
                         bs->bl.request_alignment);
+    int max_transfer = MIN_NON_ZERO(bs->bl.max_transfer,
+                                    MAX_WRITE_ZEROES_BOUNCE_BUFFER);
 
     assert(alignment % bs->bl.request_alignment == 0);
     head = offset % alignment;
@@ -1229,9 +1231,12 @@ static int coroutine_fn bdrv_co_do_pwrite_zeroes(BlockDriverState *bs,
          * boundaries.
          */
         if (head) {
-            /* Make a small request up to the first aligned sector.  */
-            num = MIN(count, alignment - head);
-            head = 0;
+            /* Make a small request up to the first aligned sector. For
+             * convenience, limit this request to max_transfer even if
+             * we don't need to fall back to writes.  */
+            num = MIN(MIN(count, max_transfer), alignment - head);
+            head = (head + num) % alignment;
+            assert(num < max_write_zeroes);
         } else if (tail && num > alignment) {
             /* Shorten the request to the last aligned sector.  */
             num -= tail;
@@ -1257,8 +1262,6 @@ static int coroutine_fn bdrv_co_do_pwrite_zeroes(BlockDriverState *bs,
 
         if (ret == -ENOTSUP) {
             /* Fall back to bounce buffer if write zeroes is unsupported */
-            int max_transfer = MIN_NON_ZERO(bs->bl.max_transfer,
-                                            MAX_WRITE_ZEROES_BOUNCE_BUFFER);
             BdrvRequestFlags write_flags = flags & ~BDRV_REQ_ZERO_WRITE;
 
             if ((flags & BDRV_REQ_FUA) &&
@@ -2421,7 +2424,7 @@ int coroutine_fn bdrv_co_pdiscard(BlockDriverState *bs, int64_t offset,
 {
     BdrvTrackedRequest req;
     int max_pdiscard, ret;
-    int head, align;
+    int head, tail, align;
 
     if (!bs->drv) {
         return -ENOMEDIUM;
@@ -2444,19 +2447,15 @@ int coroutine_fn bdrv_co_pdiscard(BlockDriverState *bs, int64_t offset,
         return 0;
     }
 
-    /* Discard is advisory, so ignore any unaligned head or tail */
+    /* Discard is advisory, but some devices track and coalesce
+     * unaligned requests, so we must pass everything down rather than
+     * round here.  Still, most devices will just silently ignore
+     * unaligned requests (by returning -ENOTSUP), so we must fragment
+     * the request accordingly.  */
     align = MAX(bs->bl.pdiscard_alignment, bs->bl.request_alignment);
     assert(align % bs->bl.request_alignment == 0);
     head = offset % align;
-    if (head) {
-        head = MIN(count, align - head);
-        count -= head;
-        offset += head;
-    }
-    count = QEMU_ALIGN_DOWN(count, align);
-    if (!count) {
-        return 0;
-    }
+    tail = (offset + count) % align;
 
     bdrv_inc_in_flight(bs);
     tracked_request_begin(&req, bs, offset, count, BDRV_TRACKED_DISCARD);
@@ -2468,11 +2467,34 @@ int coroutine_fn bdrv_co_pdiscard(BlockDriverState *bs, int64_t offset,
 
     max_pdiscard = QEMU_ALIGN_DOWN(MIN_NON_ZERO(bs->bl.max_pdiscard, INT_MAX),
                                    align);
-    assert(max_pdiscard);
+    assert(max_pdiscard >= bs->bl.request_alignment);
 
     while (count > 0) {
         int ret;
-        int num = MIN(count, max_pdiscard);
+        int num = count;
+
+        if (head) {
+            /* Make small requests to get to alignment boundaries. */
+            num = MIN(count, align - head);
+            if (!QEMU_IS_ALIGNED(num, bs->bl.request_alignment)) {
+                num %= bs->bl.request_alignment;
+            }
+            head = (head + num) % align;
+            assert(num < max_pdiscard);
+        } else if (tail) {
+            if (num > align) {
+                /* Shorten the request to the last aligned cluster.  */
+                num -= tail;
+            } else if (!QEMU_IS_ALIGNED(tail, bs->bl.request_alignment) &&
+                       tail > bs->bl.request_alignment) {
+                tail %= bs->bl.request_alignment;
+                num -= tail;
+            }
+        }
+        /* limit request size */
+        if (num > max_pdiscard) {
+            num = max_pdiscard;
+        }
 
         if (bs->drv->bdrv_co_pdiscard) {
             ret = bs->drv->bdrv_co_pdiscard(bs, offset, num);
diff --git a/block/iscsi.c b/block/iscsi.c
index 71bd523df5..0960929d57 100644
--- a/block/iscsi.c
+++ b/block/iscsi.c
@@ -1083,7 +1083,9 @@ coroutine_fn iscsi_co_pdiscard(BlockDriverState *bs, int64_t offset, int count)
     struct IscsiTask iTask;
     struct unmap_list list;
 
-    assert(is_byte_request_lun_aligned(offset, count, iscsilun));
+    if (!is_byte_request_lun_aligned(offset, count, iscsilun)) {
+        return -ENOTSUP;
+    }
 
     if (!iscsilun->lbp.lbpu) {
         /* UNMAP is not supported by the target */
diff --git a/block/qcow2.c b/block/qcow2.c
index 6d5689a23c..7cfcd8412c 100644
--- a/block/qcow2.c
+++ b/block/qcow2.c
@@ -1206,6 +1206,7 @@ static void qcow2_refresh_limits(BlockDriverState *bs, Error **errp)
         bs->bl.request_alignment = BDRV_SECTOR_SIZE;
     }
     bs->bl.pwrite_zeroes_alignment = s->cluster_size;
+    bs->bl.pdiscard_alignment = s->cluster_size;
 }
 
 static int qcow2_set_key(BlockDriverState *bs, const char *key)
@@ -2490,6 +2491,11 @@ static coroutine_fn int qcow2_co_pdiscard(BlockDriverState *bs,
     int ret;
     BDRVQcow2State *s = bs->opaque;
 
+    if (!QEMU_IS_ALIGNED(offset | count, s->cluster_size)) {
+        assert(count < s->cluster_size);
+        return -ENOTSUP;
+    }
+
     qemu_co_mutex_lock(&s->lock);
     ret = qcow2_discard_clusters(bs, offset, count >> BDRV_SECTOR_BITS,
                                  QCOW2_DISCARD_REQUEST, false);
diff --git a/block/sheepdog.c b/block/sheepdog.c
index 1fb917343a..4c9af89180 100644
--- a/block/sheepdog.c
+++ b/block/sheepdog.c
@@ -2829,8 +2829,9 @@ static coroutine_fn int sd_co_pdiscard(BlockDriverState *bs, int64_t offset,
     iov.iov_len = sizeof(zero);
     discard_iov.iov = &iov;
     discard_iov.niov = 1;
-    assert((offset & (BDRV_SECTOR_SIZE - 1)) == 0);
-    assert((count & (BDRV_SECTOR_SIZE - 1)) == 0);
+    if (!QEMU_IS_ALIGNED(offset | count, BDRV_SECTOR_SIZE)) {
+        return -ENOTSUP;
+    }
     acb = sd_aio_setup(bs, &discard_iov, offset >> BDRV_SECTOR_BITS,
                        count >> BDRV_SECTOR_BITS);
     acb->aiocb_type = AIOCB_DISCARD_OBJ;