Skip to contentSkip to conversation

drop unallocated_blocks_are_zero

PATCH Applied Vladimir Sementsov-Ogievskiy 2 participants 15 messages May 28, 2020 – Jul 6, 2020 Block layer

lore
Share & tools
lore
#0 lore raw

v3 cover drop unallocated_blocks_are_zero

This is first step to block-status refactoring, and solves most simple problem mentioned in my investigation of block-status described in the thread "backing chain & block status & filters":
https://lists.gnu.org/archive/html/qemu-devel/2020-04/msg04706.html

The whole series is reviewed, let's proceed with it please!

v3: rebase on master
02: grammar fix in commit msg, add Eric's r-b
03,04,09: add Eric's r-b
10: add my r-b

Eric Blake (1):
qed: Simplify backing reads

Vladimir Sementsov-Ogievskiy (9):
qemu-img: convert: don't use unallocated_blocks_are_zero
block: inline bdrv_unallocated_blocks_are_zero() block/vdi: return ZERO block-status when appropriate block/vpc: return ZERO block-status when appropriate block/crypto: drop unallocated_blocks_are_zero block/iscsi: drop unallocated_blocks_are_zero block/file-posix: drop unallocated_blocks_are_zero block/vhdx: drop unallocated_blocks_are_zero
block: drop unallocated_blocks_are_zero

 block/qed.h               |  1 -
 include/block/block.h     |  6 ----
 include/block/block_int.h | 12 +++++++-
 block.c                   | 15 ---------
 block/crypto.c            |  1 -
 block/file-posix.c        |  3 --
 block/io.c                |  8 ++---
 block/iscsi.c             |  1 -
 block/qcow2.c             |  1 -
 block/qed.c               | 65 ++++-----------------------------------
 block/vdi.c               |  3 +-
 block/vhdx.c              |  3 --
 block/vpc.c               |  3 +-
 qemu-img.c                |  4 +--
 14 files changed, 24 insertions(+), 102 deletions(-)
Signature · 1 line
2.18.0
#1 lore raw

PATCH v3 1/10 qemu-img: convert: don't use unallocated_blocks_are_zero

qemu-img convert wants to distinguish ZERO which comes from short backing files. unallocated_blocks_are_zero field of bdi is unrelated:
space after EOF is always considered to be zero anyway. So, just make post_backing_zero true in case of short backing file.

---
 qemu-img.c | 4 +---
 1 file changed, 1 insertion(+), 3 deletions(-)
qemu-img.c +1 -3
index 2d30682f12..9fcfafe470 100644
@@ -1660,7 +1660,6 @@ typedef struct ImgConvertState {
     BlockBackend *target;
     bool has_zero_init;
     bool compressed;
-    bool unallocated_blocks_are_zero;
     bool target_is_new;
     bool target_has_backing;
     int64_t target_backing_sectors; /* negative if unknown */
@@ -1705,7 +1704,7 @@ static int convert_iteration_sectors(ImgConvertState *s, int64_t sector_num)
 
     if (s->target_backing_sectors >= 0) {
         if (sector_num >= s->target_backing_sectors) {
-            post_backing_zero = s->unallocated_blocks_are_zero;
+            post_backing_zero = true;
         } else if (sector_num + n > s->target_backing_sectors) {
             /* Split requests around target_backing_sectors (because
              * starting from there, zeros are handled differently) */
@@ -2610,7 +2609,6 @@ static int img_convert(int argc, char **argv)
     } else {
         s.compressed = s.compressed || bdi.needs_compressed_writes;
         s.cluster_sectors = bdi.cluster_size / BDRV_SECTOR_SIZE;
-        s.unallocated_blocks_are_zero = bdi.unallocated_blocks_are_zero;
     }
 
     ret = convert_do_copy(&s);
Signature · 1 line
2.18.0
#2 lore raw

PATCH v3 2/10 block: inline bdrv_unallocated_blocks_are_zero()

In reply to Vladimir Sementsov-Ogievskiy

The function has only one user: bdrv_co_block_status(). Inline it to simplify reviewing of the following patches, which will finally drop unallocated_blocks_are_zero field too.

---
 include/block/block.h |  1 -
 block.c               | 15 ---------------
 block/io.c            | 11 ++++++++---
 3 files changed, 8 insertions(+), 19 deletions(-)
include/block/block.h +0 -1
index 25e299605e..68699ebbfa 100644
@@ -488,7 +488,6 @@ int bdrv_pdiscard(BdrvChild *child, int64_t offset, int64_t bytes);
 int bdrv_co_pdiscard(BdrvChild *child, int64_t offset, int64_t bytes);
 int bdrv_has_zero_init_1(BlockDriverState *bs);
 int bdrv_has_zero_init(BlockDriverState *bs);
-bool bdrv_unallocated_blocks_are_zero(BlockDriverState *bs);
 bool bdrv_can_write_zeroes_with_unmap(BlockDriverState *bs);
 int bdrv_block_status(BlockDriverState *bs, int64_t offset,
                       int64_t bytes, int64_t *pnum, int64_t *map,
block.c +0 -15
index 8416376c9b..34adf1298f 100644
@@ -5408,21 +5408,6 @@ int bdrv_has_zero_init(BlockDriverState *bs)
     return 0;
 }
 
-bool bdrv_unallocated_blocks_are_zero(BlockDriverState *bs)
-{
-    BlockDriverInfo bdi;
-
-    if (bs->backing) {
-        return false;
-    }
-
-    if (bdrv_get_info(bs, &bdi) == 0) {
-        return bdi.unallocated_blocks_are_zero;
-    }
-
-    return false;
-}
-
 bool bdrv_can_write_zeroes_with_unmap(BlockDriverState *bs)
 {
     if (!(bs->open_flags & BDRV_O_UNMAP)) {
block/io.c +8 -3
index 121ce17a49..6f9507f718 100644
@@ -2387,15 +2387,20 @@ static int coroutine_fn bdrv_co_block_status(BlockDriverState *bs,
     if (ret & (BDRV_BLOCK_DATA | BDRV_BLOCK_ZERO)) {
         ret |= BDRV_BLOCK_ALLOCATED;
     } else if (want_zero) {
-        if (bdrv_unallocated_blocks_are_zero(bs)) {
-            ret |= BDRV_BLOCK_ZERO;
-        } else if (bs->backing) {
+        if (bs->backing) {
             BlockDriverState *bs2 = bs->backing->bs;
             int64_t size2 = bdrv_getlength(bs2);
 
             if (size2 >= 0 && offset >= size2) {
                 ret |= BDRV_BLOCK_ZERO;
             }
+        } else {
+            BlockDriverInfo bdi;
+            int ret2 = bdrv_get_info(bs, &bdi);
+
+            if (ret2 == 0 && bdi.unallocated_blocks_are_zero) {
+                ret |= BDRV_BLOCK_ZERO;
+            }
         }
     }
 
Signature · 1 line
2.18.0
#3 lore raw

PATCH v3 3/10 block/vdi: return ZERO block-status when appropriate

In reply to Vladimir Sementsov-Ogievskiy

In case of !VDI_IS_ALLOCATED[], we do zero out the corresponding chunk of qiov. So, this should be reported as ZERO.

Note that this changes visible output of "qemu-img map --output=json" and "qemu-io -c map" commands. For qemu-img map, the change is obvious:
we just mark as zero what is really zero. For qemu-io it's less
obvious: what was unallocated now is allocated.

There is an inconsistency in understanding of unallocated regions in
Qemu: backing-supporting format-drivers return 0 block-status to report go-to-backing logic for this area. Some protocol-drivers (iscsi) return 0 to report fs-unallocated-non-zero status (i.e., don't occupy space on disk, read result is undefined).

BDRV_BLOCK_ALLOCATED is defined as something more close to go-to-backing logic. Still it is calculated as ZERO | DATA, so 0 from iscsi is treated as unallocated. It doesn't influence backing-chain behavior, as iscsi can't have backing file. But it does influence "qemu-io -c map".

We should solve this inconsistency at some future point. Now, let's just make backing-not-supporting format drivers (vdi at this patch and vpc with the following) to behave more like backing-supporting drivers and not report 0 block-status. More over, returning ZERO status is absolutely valid thing, and again, corresponds to how the other format-drivers (backing-supporting) work.

After block-status update, it never reports 0, so setting unallocated_blocks_are_zero doesn't make sense (as the only user of it is bdrv_co_block_status and it checks unallocated_blocks_are_zero only for unallocated areas). Drop it.

---
 block/vdi.c | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)
block/vdi.c +1 -2
index 2f506a01ba..c4527a9d8c 100644
@@ -334,7 +334,6 @@ static int vdi_get_info(BlockDriverState *bs, BlockDriverInfo *bdi)
     logout("\n");
     bdi->cluster_size = s->block_size;
     bdi->vm_state_offset = 0;
-    bdi->unallocated_blocks_are_zero = true;
     return 0;
 }
 
@@ -536,7 +535,7 @@ static int coroutine_fn vdi_co_block_status(BlockDriverState *bs,
     *pnum = MIN(s->block_size - index_in_block, bytes);
     result = VDI_IS_ALLOCATED(bmap_entry);
     if (!result) {
-        return 0;
+        return BDRV_BLOCK_ZERO;
     }
 
     *map = s->header.offset_data + (uint64_t)bmap_entry * s->block_size +
Signature · 1 line
2.18.0
#4 lore raw

PATCH v3 4/10 block/vpc: return ZERO block-status when appropriate

In reply to Vladimir Sementsov-Ogievskiy

In case when get_image_offset() returns -1, we do zero out the corresponding chunk of qiov. So, this should be reported as ZERO.

Note that this changes visible output of "qemu-img map --output=json" and "qemu-io -c map" commands. For qemu-img map, the change is obvious:
we just mark as zero what is really zero. For qemu-io it's less
obvious: what was unallocated now is allocated.

There is an inconsistency in understanding of unallocated regions in
Qemu: backing-supporting format-drivers return 0 block-status to report go-to-backing logic for this area. Some protocol-drivers (iscsi) return 0 to report fs-unallocated-non-zero status (i.e., don't occupy space on disk, read result is undefined).

BDRV_BLOCK_ALLOCATED is defined as something more close to go-to-backing logic. Still it is calculated as ZERO | DATA, so 0 from iscsi is treated as unallocated. It doesn't influence backing-chain behavior, as iscsi can't have backing file. But it does influence "qemu-io -c map".

We should solve this inconsistency at some future point. Now, let's just make backing-not-supporting format drivers (vdi in the previous patch and vpc now) to behave more like backing-supporting drivers and not report 0 block-status. More over, returning ZERO status is absolutely valid thing, and again, corresponds to how the other format-drivers (backing-supporting) work.

After block-status update, it never reports 0, so setting unallocated_blocks_are_zero doesn't make sense (as the only user of it is bdrv_co_block_status and it checks unallocated_blocks_are_zero only for unallocated areas). Drop it.

---
 block/vpc.c | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)
block/vpc.c +1 -2
index c055591641..01fcd37e3c 100644
@@ -606,7 +606,6 @@ static int vpc_get_info(BlockDriverState *bs, BlockDriverInfo *bdi)
         bdi->cluster_size = s->block_size;
     }
 
-    bdi->unallocated_blocks_are_zero = true;
     return 0;
 }
 
@@ -745,7 +744,7 @@ static int coroutine_fn vpc_co_block_status(BlockDriverState *bs,
     image_offset = get_image_offset(bs, offset, false, NULL);
     allocated = (image_offset != -1);
     *pnum = 0;
-    ret = 0;
+    ret = BDRV_BLOCK_ZERO;
 
     do {
         /* All sectors in a block are contiguous (without using the bitmap) */
Signature · 1 line
2.18.0
#5 lore raw

Re: [PATCH v3 04/10] block/vpc: return ZERO block-status when appropriate

Quoted 32 lines · Vladimir Sementsov-Ogievskiy

In case when get_image_offset() returns -1, we do zero out the corresponding chunk of qiov. So, this should be reported as ZERO.

Note that this changes visible output of "qemu-img map --output=json" and "qemu-io -c map" commands. For qemu-img map, the change is obvious:
we just mark as zero what is really zero. For qemu-io it's less
obvious: what was unallocated now is allocated.

There is an inconsistency in understanding of unallocated regions in
Qemu: backing-supporting format-drivers return 0 block-status to report go-to-backing logic for this area. Some protocol-drivers (iscsi) return 0 to report fs-unallocated-non-zero status (i.e., don't occupy space on disk, read result is undefined).

BDRV_BLOCK_ALLOCATED is defined as something more close to go-to-backing logic. Still it is calculated as ZERO | DATA, so 0 from iscsi is treated as unallocated. It doesn't influence backing-chain behavior, as iscsi can't have backing file. But it does influence "qemu-io -c map".

We should solve this inconsistency at some future point. Now, let's just make backing-not-supporting format drivers (vdi in the previous patch and vpc now) to behave more like backing-supporting drivers and not report 0 block-status. More over, returning ZERO status is absolutely valid thing, and again, corresponds to how the other format-drivers (backing-supporting) work.

After block-status update, it never reports 0, so setting unallocated_blocks_are_zero doesn't make sense (as the only user of it is bdrv_co_block_status and it checks unallocated_blocks_are_zero only for unallocated areas). Drop it.

Quoted 5 lines
---
 block/vpc.c | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

This breaks iotest 146, I’m afraid. Now everything is reported as allocated, which is of course what we kind of want, but I suppose it renders the test a bit useless.

It seems to me like the best thing to do would be to replace the “qemu-io -o $opts -c map” calls by
“qemu-img map --output=json --image-opts $opts”, so that we get “zero: true” instead of “not allocated” in the output.

A bit of a problem with that approach are the “allocated” entries, because those are split into 2 MB chunks, so the output gets long. But, well.

I’ve attached a diff to that effect. Would you be OK with squashing that in?

Max

tests/qemu-iotests/146 +45 -15
index 2e43abddfc..ddc3c1fd80 100755
@@ -51,19 +51,25 @@ echo === Testing VPC Autodetect ===
 echo
 _use_sample_img virtualpc-dynamic.vhd.bz2
 
-${QEMU_IO} -c "open -o driver=vpc ${TEST_IMG}" -c 'map'
+$QEMU_IMG map --output=json --image-opts \
+    "driver=vpc,file.filename=$TEST_IMG" \
+    | _filter_qemu_img_map
 
 echo
 echo === Testing VPC with current_size force ===
 echo
 
-${QEMU_IO} -c "open -o driver=vpc,force_size_calc=current_size ${TEST_IMG}" -c 'map'
+$QEMU_IMG map --output=json --image-opts \
+    "driver=vpc,force_size_calc=current_size,file.filename=$TEST_IMG" \
+    | _filter_qemu_img_map
 
 echo
 echo === Testing VPC with chs force ===
 echo
 
-${QEMU_IO} -c "open -o driver=vpc,force_size_calc=chs ${TEST_IMG}" -c 'map'
+$QEMU_IMG map --output=json --image-opts \
+    "driver=vpc,force_size_calc=chs,file.filename=$TEST_IMG" \
+    | _filter_qemu_img_map
 
 _cleanup_test_img
 
@@ -72,19 +78,25 @@ echo === Testing Hyper-V Autodetect ===
 echo
 _use_sample_img hyperv2012r2-dynamic.vhd.bz2
 
-${QEMU_IO} -c "open -o driver=vpc ${TEST_IMG}" -c 'map'
+$QEMU_IMG map --output=json --image-opts \
+    "driver=vpc,file.filename=$TEST_IMG" \
+    | _filter_qemu_img_map
 
 echo
 echo === Testing Hyper-V with current_size force ===
 echo
 
-${QEMU_IO} -c "open -o driver=vpc,force_size_calc=current_size ${TEST_IMG}" -c 'map'
+$QEMU_IMG map --output=json --image-opts \
+    "driver=vpc,force_size_calc=current_size,file.filename=$TEST_IMG" \
+    | _filter_qemu_img_map
 
 echo
 echo === Testing Hyper-V with chs force ===
 echo
 
-${QEMU_IO} -c "open -o driver=vpc,force_size_calc=chs ${TEST_IMG}" -c 'map'
+$QEMU_IMG map --output=json --image-opts \
+    "driver=vpc,force_size_calc=chs,file.filename=$TEST_IMG" \
+    | _filter_qemu_img_map
 
 _cleanup_test_img
 
@@ -93,19 +105,25 @@ echo === Testing d2v Autodetect ===
 echo
 _use_sample_img d2v-zerofilled.vhd.bz2
 
-${QEMU_IO} -c "open -o driver=vpc ${TEST_IMG}" -c 'map'
+$QEMU_IMG map --output=json --image-opts \
+    "driver=vpc,file.filename=$TEST_IMG" \
+    | _filter_qemu_img_map
 
 echo
 echo === Testing d2v with current_size force ===
 echo
 
-${QEMU_IO} -c "open -o driver=vpc,force_size_calc=current_size ${TEST_IMG}" -c 'map'
+$QEMU_IMG map --output=json --image-opts \
+    "driver=vpc,force_size_calc=current_size,file.filename=$TEST_IMG" \
+    | _filter_qemu_img_map
 
 echo
 echo === Testing d2v with chs force ===
 echo
 
-${QEMU_IO} -c "open -o driver=vpc,force_size_calc=chs ${TEST_IMG}" -c 'map'
+$QEMU_IMG map --output=json --image-opts \
+    "driver=vpc,force_size_calc=chs,file.filename=$TEST_IMG" \
+    | _filter_qemu_img_map
 
 _cleanup_test_img
 
@@ -121,19 +139,25 @@ echo
 echo === Read created image, default opts ====
 echo
 
-${QEMU_IO} -c "open -o driver=vpc ${TEST_IMG}" -c 'map'
+$QEMU_IMG map --output=json --image-opts \
+    "driver=vpc,file.filename=$TEST_IMG" \
+    | _filter_qemu_img_map
 
 echo
 echo === Read created image, force_size_calc=chs ====
 echo
 
-${QEMU_IO} -c "open -o driver=vpc,force_size_calc=chs ${TEST_IMG}" -c 'map'
+$QEMU_IMG map --output=json --image-opts \
+    "driver=vpc,force_size_calc=chs,file.filename=$TEST_IMG" \
+    | _filter_qemu_img_map
 
 echo
 echo === Read created image, force_size_calc=current_size ====
 echo
 
-${QEMU_IO} -c "open -o driver=vpc,force_size_calc=current_size ${TEST_IMG}" -c 'map'
+$QEMU_IMG map --output=json --image-opts \
+    "driver=vpc,force_size_calc=current_size,file.filename=$TEST_IMG" \
+    | _filter_qemu_img_map
 
 echo
 echo === Testing Image create, force_size ===
@@ -145,19 +169,25 @@ echo
 echo === Read created image, default opts ====
 echo
 
-${QEMU_IO} -c "open -o driver=vpc ${TEST_IMG}" -c 'map'
+$QEMU_IMG map --output=json --image-opts \
+    "driver=vpc,file.filename=$TEST_IMG" \
+    | _filter_qemu_img_map
 
 echo
 echo === Read created image, force_size_calc=chs ====
 echo
 
-${QEMU_IO} -c "open -o driver=vpc,force_size_calc=chs ${TEST_IMG}" -c 'map'
+$QEMU_IMG map --output=json --image-opts \
+    "driver=vpc,force_size_calc=chs,file.filename=$TEST_IMG" \
+    | _filter_qemu_img_map
 
 echo
 echo === Read created image, force_size_calc=current_size ====
 echo
 
-${QEMU_IO} -c "open -o driver=vpc,force_size_calc=current_size ${TEST_IMG}" -c 'map'
+$QEMU_IMG map --output=json --image-opts \
+    "driver=vpc,force_size_calc=current_size,file.filename=$TEST_IMG" \
+    | _filter_qemu_img_map
 
 echo "*** done"
 rm -f $seq.full
tests/qemu-iotests/146.out +390 -15

457 lines not on this page · raw message

#6 lore raw

Re: [PATCH v3 04/10] block/vpc: return ZERO block-status when appropriate

Quoted 48 lines · Max Reitz
Quoted 32 lines · Vladimir Sementsov-Ogievskiy

In case when get_image_offset() returns -1, we do zero out the corresponding chunk of qiov. So, this should be reported as ZERO.

Note that this changes visible output of "qemu-img map --output=json" and "qemu-io -c map" commands. For qemu-img map, the change is obvious:
we just mark as zero what is really zero. For qemu-io it's less
obvious: what was unallocated now is allocated.

There is an inconsistency in understanding of unallocated regions in
Qemu: backing-supporting format-drivers return 0 block-status to report go-to-backing logic for this area. Some protocol-drivers (iscsi) return 0 to report fs-unallocated-non-zero status (i.e., don't occupy space on disk, read result is undefined).

BDRV_BLOCK_ALLOCATED is defined as something more close to go-to-backing logic. Still it is calculated as ZERO | DATA, so 0 from iscsi is treated as unallocated. It doesn't influence backing-chain behavior, as iscsi can't have backing file. But it does influence "qemu-io -c map".

We should solve this inconsistency at some future point. Now, let's just make backing-not-supporting format drivers (vdi in the previous patch and vpc now) to behave more like backing-supporting drivers and not report 0 block-status. More over, returning ZERO status is absolutely valid thing, and again, corresponds to how the other format-drivers (backing-supporting) work.

After block-status update, it never reports 0, so setting unallocated_blocks_are_zero doesn't make sense (as the only user of it is bdrv_co_block_status and it checks unallocated_blocks_are_zero only for unallocated areas). Drop it.

Quoted 5 lines
---
  block/vpc.c | 3 +--
  1 file changed, 1 insertion(+), 2 deletions(-)

This breaks iotest 146, I’m afraid. Now everything is reported as allocated, which is of course what we kind of want, but I suppose it renders the test a bit useless.

It seems to me like the best thing to do would be to replace the “qemu-io -o $opts -c map” calls by
“qemu-img map --output=json --image-opts $opts”, so that we get “zero: true” instead of “not allocated” in the output.

Quoted 6 lines

A bit of a problem with that approach are the “allocated” entries, because those are split into 2 MB chunks, so the output gets long. But, well.

I’ve attached a diff to that effect. Would you be OK with squashing that in?

Yes, this looks reasonable, thanks a lot!

Signature · 2 lines
Best regards,
Vladimir
#7 lore raw

PATCH v3 5/10 block/crypto: drop unallocated_blocks_are_zero

In reply to Vladimir Sementsov-Ogievskiy

It's false by default, no needs to set it. We are going to drop this variable at all, so drop it now here, it doesn't hurt.

---
 block/crypto.c | 1 -
 1 file changed, 1 deletion(-)
block/crypto.c +0 -1
index b216e12c31..6d930e2d54 100644
@@ -710,7 +710,6 @@ static int block_crypto_get_info_luks(BlockDriverState *bs,
         return ret;
     }
 
-    bdi->unallocated_blocks_are_zero = false;
     bdi->cluster_size = subbdi.cluster_size;
 
     return 0;
Signature · 1 line
2.18.0
#8 lore raw

PATCH v3 6/10 block/iscsi: drop unallocated_blocks_are_zero

In reply to Vladimir Sementsov-Ogievskiy

We set bdi->unallocated_blocks_are_zero = iscsilun->lbprz, but iscsi_co_block_status doesn't return 0 in case of iscsilun->lbprz, it returns ZERO when appropriate. So actually unallocated_blocks_are_zero is useless (it doesn't affect the only user of the field:
bdrv_co_block_status()). Drop it now.

---
 block/iscsi.c | 1 -
 1 file changed, 1 deletion(-)
block/iscsi.c +0 -1
index a8b76979d8..767e3e75fd 100644
@@ -2163,7 +2163,6 @@ static int coroutine_fn iscsi_co_truncate(BlockDriverState *bs, int64_t offset,
 static int iscsi_get_info(BlockDriverState *bs, BlockDriverInfo *bdi)
 {
     IscsiLun *iscsilun = bs->opaque;
-    bdi->unallocated_blocks_are_zero = iscsilun->lbprz;
     bdi->cluster_size = iscsilun->cluster_size;
     return 0;
 }
Signature · 1 line
2.18.0
#9 lore raw

PATCH v3 7/10 block/file-posix: drop unallocated_blocks_are_zero

In reply to Vladimir Sementsov-Ogievskiy

raw_co_block_status() in block/file-posix.c never returns 0, so unallocated_blocks_are_zero is useless (it doesn't affect the only user of the field: bdrv_co_block_status()). Drop it.

---
 block/file-posix.c | 3 ---
 1 file changed, 3 deletions(-)
block/file-posix.c +0 -3
index 3ab8f5a0fa..d86ea57769 100644
@@ -2878,9 +2878,6 @@ static int coroutine_fn raw_co_pwrite_zeroes(
 
 static int raw_get_info(BlockDriverState *bs, BlockDriverInfo *bdi)
 {
-    BDRVRawState *s = bs->opaque;
-
-    bdi->unallocated_blocks_are_zero = s->discard_zeroes;
     return 0;
 }
 
Signature · 1 line
2.18.0
#10 lore raw

PATCH v3 8/10 block/vhdx: drop unallocated_blocks_are_zero

In reply to Vladimir Sementsov-Ogievskiy

vhdx doesn't have .bdrv_co_block_status handler, so DATA|ALLOCATED is always assumed for it in bdrv_co_block_status(). unallocated_blocks_are_zero is useless (it doesn't affect the only user of the field: bdrv_co_block_status()), drop it.

---
 block/vhdx.c | 3 ---
 1 file changed, 3 deletions(-)
block/vhdx.c +0 -3
index fa9e544a5e..645dc4b4f4 100644
@@ -1164,9 +1164,6 @@ static int vhdx_get_info(BlockDriverState *bs, BlockDriverInfo *bdi)
 
     bdi->cluster_size = s->block_size;
 
-    bdi->unallocated_blocks_are_zero =
-        (s->params.data_bits & VHDX_PARAMS_HAS_PARENT) == 0;
-
     return 0;
 }
 
Signature · 1 line
2.18.0
#11 lore raw

PATCH v3 9/10 block: drop unallocated_blocks_are_zero

In reply to Vladimir Sementsov-Ogievskiy

Currently this field only set by qed and qcow2. But in fact, all backing-supporting formats (parallels, qcow, qcow2, qed, vmdk) share these semantics: on unallocated blocks, if there is no backing file they just memset the buffer with zeroes.

So, document this behavior for .supports_backing and drop .unallocated_blocks_are_zero

---
 include/block/block.h     |  5 -----
 include/block/block_int.h | 12 +++++++++++-
 block/io.c                |  9 ++-------
 block/qcow2.c             |  1 -
 block/qed.c               |  1 -
 5 files changed, 13 insertions(+), 15 deletions(-)
include/block/block.h +0 -5
index 68699ebbfa..ceb9defb58 100644
@@ -21,11 +21,6 @@ typedef struct BlockDriverInfo {
     /* offset at which the VM state can be saved (0 if not possible) */
     int64_t vm_state_offset;
     bool is_dirty;
-    /*
-     * True if unallocated blocks read back as zeroes. This is equivalent
-     * to the LBPRZ flag in the SCSI logical block provisioning page.
-     */
-    bool unallocated_blocks_are_zero;
     /*
      * True if this block driver only supports compressed writes
      */
include/block/block_int.h +11 -1
index 791de6a59c..faeeef1706 100644
@@ -123,7 +123,17 @@ struct BlockDriver {
      */
     bool bdrv_needs_filename;
 
-    /* Set if a driver can support backing files */
+    /*
+     * Set if a driver can support backing files. This also implies the
+     * following semantics:
+     *
+     *  - Return status 0 of .bdrv_co_block_status means that corresponding
+     *    blocks are not allocated in this layer of backing-chain
+     *  - For such (unallocated) blocks, read will:
+     *    - fill buffer with zeros if there is no backing file
+     *    - read from the backing file otherwise, where the block layer
+     *      takes care of reading zeros beyond EOF if backing file is short
+     */
     bool supports_backing;
 
     /* For handling image reopen for split or non-split files */
block/io.c +2 -7
index 6f9507f718..ddcd533c5d 100644
@@ -2386,7 +2386,7 @@ static int coroutine_fn bdrv_co_block_status(BlockDriverState *bs,
 
     if (ret & (BDRV_BLOCK_DATA | BDRV_BLOCK_ZERO)) {
         ret |= BDRV_BLOCK_ALLOCATED;
-    } else if (want_zero) {
+    } else if (want_zero && bs->drv->supports_backing) {
         if (bs->backing) {
             BlockDriverState *bs2 = bs->backing->bs;
             int64_t size2 = bdrv_getlength(bs2);
@@ -2395,12 +2395,7 @@ static int coroutine_fn bdrv_co_block_status(BlockDriverState *bs,
                 ret |= BDRV_BLOCK_ZERO;
             }
         } else {
-            BlockDriverInfo bdi;
-            int ret2 = bdrv_get_info(bs, &bdi);
-
-            if (ret2 == 0 && bdi.unallocated_blocks_are_zero) {
-                ret |= BDRV_BLOCK_ZERO;
-            }
+            ret |= BDRV_BLOCK_ZERO;
         }
     }
 
block/qcow2.c +0 -1
index dfab8d2f6c..72ed3bf305 100644
@@ -4973,7 +4973,6 @@ err:
 static int qcow2_get_info(BlockDriverState *bs, BlockDriverInfo *bdi)
 {
     BDRVQcow2State *s = bs->opaque;
-    bdi->unallocated_blocks_are_zero = true;
     bdi->cluster_size = s->cluster_size;
     bdi->vm_state_offset = qcow2_vm_state_offset(s);
     return 0;
block/qed.c +0 -1
index c0c65015c7..a2dd952699 100644
@@ -1514,7 +1514,6 @@ static int bdrv_qed_get_info(BlockDriverState *bs, BlockDriverInfo *bdi)
     memset(bdi, 0, sizeof(*bdi));
     bdi->cluster_size = s->header.cluster_size;
     bdi->is_dirty = s->header.features & QED_F_NEED_CHECK;
-    bdi->unallocated_blocks_are_zero = true;
     return 0;
 }
 
Signature · 1 line
2.18.0
#12 lore raw

PATCH v3 10/10 qed: Simplify backing reads

In reply to Vladimir Sementsov-Ogievskiy

From: Eric Blake <[email protected]>

The other four drivers that support backing files (qcow, qcow2, parallels, vmdk) all rely on the block layer to populate zeroes when reading beyond EOF of a short backing file. We can simplify the qed code by doing likewise.

---
 block/qed.h |  1 -
 block/qed.c | 64 +++++------------------------------------------------
 2 files changed, 6 insertions(+), 59 deletions(-)
block/qed.h +0 -1
index 42c115d822..3d12bf78d4 100644
@@ -140,7 +140,6 @@ typedef struct QEDAIOCB {
 
     /* Current cluster scatter-gather list */
     QEMUIOVector cur_qiov;
-    QEMUIOVector *backing_qiov;
     uint64_t cur_pos;               /* position on block device, in bytes */
     uint64_t cur_cluster;           /* cluster offset in image file */
     unsigned int cur_nclusters;     /* number of clusters being accessed */
block/qed.c +6 -58

102 lines not on this page · raw message

Signature · 1 line
2.18.0
Applied
#13 lore raw
In reply to Vladimir Sementsov-Ogievskiy
Quoted 11 lines · Vladimir Sementsov-Ogievskiy

This is first step to block-status refactoring, and solves most simple problem mentioned in my investigation of block-status described in the thread "backing chain & block status & filters":
https://lists.gnu.org/archive/html/qemu-devel/2020-04/msg04706.html

The whole series is reviewed, let's proceed with it please!

v3: rebase on master
02: grammar fix in commit msg, add Eric's r-b
03,04,09: add Eric's r-b
10: add my r-b

Thanks, applied to my block branch:

https://git.xanclic.moe/XanClic/qemu/commits/branch/block

#14 lore raw
Quoted 8 lines · Max Reitz
Quoted 7 lines · Vladimir Sementsov-Ogievskiy

This is first step to block-status refactoring, and solves most simple problem mentioned in my investigation of block-status described in the thread "backing chain & block status & filters":

   https://lists.gnu.org/archive/html/qemu-devel/2020-04/msg04706.html

The whole series is reviewed, let's proceed with it please!

Quoted 9 lines
Quoted 4 lines

v3: rebase on master
02: grammar fix in commit msg, add Eric's r-b
03,04,09: add Eric's r-b
10: add my r-b

Thanks, applied to my block branch:

https://git.xanclic.moe/XanClic/qemu/commits/branch/block

Thanks!

Signature · 2 lines
Best regards,
Vladimir