From 4704bbaba38bfeb1710b109f0b4b32a839b24734 Mon Sep 17 00:00:00 2001

From: Maxim Levitsky <mlevitsk@redhat.com>

Date: Wed, 5 Jun 2019 13:57:00 +0200

Subject: [PATCH 12/23] file-posix: Fix write_zeroes with unmap on block

 devices

RH-Author: Maxim Levitsky <mlevitsk@redhat.com>

Message-id: <20190605135705.24526-5-mlevitsk@redhat.com>

Patchwork-id: 88562

O-Subject: [RHEL-7.7 qemu-kvm-rhev PATCH 4/9] file-posix: Fix write_zeroes with unmap on block devices

Bugzilla: 1648622

RH-Acked-by: Max Reitz <mreitz@redhat.com>

RH-Acked-by: Stefan Hajnoczi <stefanha@redhat.com>

RH-Acked-by: John Snow <jsnow@redhat.com>

From: Kevin Wolf <kwolf@redhat.com>

The BLKDISCARD ioctl doesn't guarantee that the discarded blocks read as

all-zero afterwards, so don't try to abuse it for zero writing. We try

to only use this if BLKDISCARDZEROES tells us that it is safe, but this

is unreliable on older kernels and a constant 0 in newer kernels. In

other words, this code path is never actually used with newer kernels,

so we don't even try to unmap while writing zeros.

This patch removes the abuse of discard for writing zeroes from

file-posix and instead adds a new function that uses interfaces that are

actually meant to deallocate and zero out at the same time. Only if

those fail, it falls back to zeroing out without unmap. We never fall

back to a discard operation any more that may or may not result in

zeros.

Signed-off-by: Kevin Wolf <kwolf@redhat.com>

Fixes: https://bugzilla.redhat.com/show_bug.cgi?id=1648622

Signed-off-by: Maxim Levitsky <mlevitsk@redhat.com>

(Cherry picked from 34fa110e424e9a6a9b7e0274c3d4bfee766eb7ed)

Signed-off-by: Miroslav Rezanina <mrezanin@redhat.com>

---

 block/file-posix.c | 59 ++++++++++++++++++++++++++++++++++++++++--------------

 1 file changed, 44 insertions(+), 15 deletions(-)

diff --git a/block/file-posix.c b/block/file-posix.c

index 518f16b..5b93d06 100644

--- a/block/file-posix.c

+++ b/block/file-posix.c

@@ -632,7 +632,7 @@ static int raw_open_common(BlockDriverState *bs, QDict *options,

     }

 #endif

-    bs->supported_zero_flags = s->discard_zeroes ? BDRV_REQ_MAY_UNMAP : 0;

+    bs->supported_zero_flags = BDRV_REQ_MAY_UNMAP;

     ret = 0;

 fail:

     if (filename && (bdrv_flags & BDRV_O_TEMPORARY)) {

@@ -1530,6 +1530,35 @@ static ssize_t handle_aiocb_write_zeroes(RawPosixAIOData *aiocb)

     return -ENOTSUP;

 }

+static ssize_t handle_aiocb_write_zeroes_unmap(RawPosixAIOData *aiocb)

+{

+    BDRVRawState *s G_GNUC_UNUSED = aiocb->bs->opaque;

+    int ret;

+

+    /* First try to write zeros and unmap at the same time */

+

+#ifdef CONFIG_FALLOCATE_PUNCH_HOLE

+    ret = do_fallocate(s->fd, FALLOC_FL_PUNCH_HOLE | FALLOC_FL_KEEP_SIZE,

+                       aiocb->aio_offset, aiocb->aio_nbytes);

+    if (ret != -ENOTSUP) {

+        return ret;

+    }

+#endif

+

+#ifdef CONFIG_XFS

+    if (s->is_xfs) {

+        /* xfs_discard() guarantees that the discarded area reads as all-zero

+         * afterwards, so we can use it here. */

+        return xfs_discard(s, aiocb->aio_offset, aiocb->aio_nbytes);

+    }

+#endif

+

+    /* If we couldn't manage to unmap while guaranteed that the area reads as

+     * all-zero afterwards, just write zeroes without unmapping */

+    ret = handle_aiocb_write_zeroes(aiocb);

+    return ret;

+}

+

 #ifndef HAVE_COPY_FILE_RANGE

 static off_t copy_file_range(int in_fd, off_t *in_off, int out_fd,

                              off_t *out_off, size_t len, unsigned int flags)

@@ -1770,6 +1799,9 @@ static int aio_worker(void *arg)

     case QEMU_AIO_WRITE_ZEROES:

         ret = handle_aiocb_write_zeroes(aiocb);

         break;

+    case QEMU_AIO_WRITE_ZEROES | QEMU_AIO_DISCARD:

+        ret = handle_aiocb_write_zeroes_unmap(aiocb);

+        break;

     case QEMU_AIO_COPY_RANGE:

         ret = handle_aiocb_copy_range(aiocb);

         break;

@@ -2488,15 +2520,13 @@ static int coroutine_fn raw_co_pwrite_zeroes(

     int bytes, BdrvRequestFlags flags)

 {

     BDRVRawState *s = bs->opaque;

+    int operation = QEMU_AIO_WRITE_ZEROES;

-    if (!(flags & BDRV_REQ_MAY_UNMAP)) {

-        return paio_submit_co(bs, s->fd, offset, NULL, bytes,

-                              QEMU_AIO_WRITE_ZEROES);

-    } else if (s->discard_zeroes) {

-        return paio_submit_co(bs, s->fd, offset, NULL, bytes,

-                              QEMU_AIO_DISCARD);

+    if (flags & BDRV_REQ_MAY_UNMAP) {

+        operation |= QEMU_AIO_DISCARD;

     }

-    return -ENOTSUP;

+

+    return paio_submit_co(bs, s->fd, offset, NULL, bytes, operation);

 }

 static int raw_get_info(BlockDriverState *bs, BlockDriverInfo *bdi)

@@ -3061,20 +3091,19 @@ static coroutine_fn int hdev_co_pwrite_zeroes(BlockDriverState *bs,

     int64_t offset, int bytes, BdrvRequestFlags flags)

 {

     BDRVRawState *s = bs->opaque;

+    int operation = QEMU_AIO_WRITE_ZEROES | QEMU_AIO_BLKDEV;

     int rc;

     rc = fd_open(bs);

     if (rc < 0) {

         return rc;

     }

-    if (!(flags & BDRV_REQ_MAY_UNMAP)) {

-        return paio_submit_co(bs, s->fd, offset, NULL, bytes,

-                              QEMU_AIO_WRITE_ZEROES|QEMU_AIO_BLKDEV);

-    } else if (s->discard_zeroes) {

-        return paio_submit_co(bs, s->fd, offset, NULL, bytes,

-                              QEMU_AIO_DISCARD|QEMU_AIO_BLKDEV);

+

+    if (flags & BDRV_REQ_MAY_UNMAP) {

+        operation |= QEMU_AIO_DISCARD;

     }

-    return -ENOTSUP;

+

+    return paio_submit_co(bs, s->fd, offset, NULL, bytes, operation);

 }

 static int coroutine_fn hdev_co_create_opts(const char *filename, QemuOpts *opts,

-- 

1.8.3.1