Commit 1ab8f867 authored by Peter Maydell's avatar Peter Maydell

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

Block patches for 2.2.0-rc2

# gpg: Signature made Tue 18 Nov 2014 11:32:55 GMT using RSA key ID C88F2FD6
# gpg: Good signature from "Kevin Wolf <kwolf@redhat.com>"

* remotes/kevin/tags/for-upstream:
  block/raw-posix: Catch fsync() errors
  block/raw-posix: Only sync after successful preallocation
  block/raw-posix: Fix preallocating write() loop
  raw-posix: The SEEK_HOLE code is flawed, rewrite it
  raw-posix: SEEK_HOLE suffices, get rid of FIEMAP
  raw-posix: Fix comment for raw_co_get_block_status()
Signed-off-by: default avatarPeter Maydell <peter.maydell@linaro.org>
parents ea5b201a 098ffa66
......@@ -60,9 +60,6 @@
#define FS_NOCOW_FL 0x00800000 /* Do not cow file */
#endif
#endif
#ifdef CONFIG_FIEMAP
#include <linux/fiemap.h>
#endif
#ifdef CONFIG_FALLOCATE_PUNCH_HOLE
#include <linux/falloc.h>
#endif
......@@ -151,9 +148,6 @@ typedef struct BDRVRawState {
bool has_write_zeroes:1;
bool discard_zeroes:1;
bool needs_alignment;
#ifdef CONFIG_FIEMAP
bool skip_fiemap;
#endif
} BDRVRawState;
typedef struct BDRVRawReopenState {
......@@ -1457,9 +1451,16 @@ static int raw_create(const char *filename, QemuOpts *opts, Error **errp)
"Could not write to the new file");
break;
}
left -= num;
left -= result;
}
if (result >= 0) {
result = fsync(fd);
if (result < 0) {
result = -errno;
error_setg_errno(errp, -result,
"Could not flush new file to disk");
}
}
fsync(fd);
g_free(buf);
break;
}
......@@ -1481,83 +1482,93 @@ out:
return result;
}
static int try_fiemap(BlockDriverState *bs, off_t start, off_t *data,
off_t *hole, int nb_sectors)
/*
* Find allocation range in @bs around offset @start.
* May change underlying file descriptor's file offset.
* If @start is not in a hole, store @start in @data, and the
* beginning of the next hole in @hole, and return 0.
* If @start is in a non-trailing hole, store @start in @hole and the
* beginning of the next non-hole in @data, and return 0.
* If @start is in a trailing hole or beyond EOF, return -ENXIO.
* If we can't find out, return a negative errno other than -ENXIO.
*/
static int find_allocation(BlockDriverState *bs, off_t start,
off_t *data, off_t *hole)
{
#ifdef CONFIG_FIEMAP
#if defined SEEK_HOLE && defined SEEK_DATA
BDRVRawState *s = bs->opaque;
int ret = 0;
struct {
struct fiemap fm;
struct fiemap_extent fe;
} f;
off_t offs;
if (s->skip_fiemap) {
return -ENOTSUP;
}
f.fm.fm_start = start;
f.fm.fm_length = (int64_t)nb_sectors * BDRV_SECTOR_SIZE;
f.fm.fm_flags = FIEMAP_FLAG_SYNC;
f.fm.fm_extent_count = 1;
f.fm.fm_reserved = 0;
if (ioctl(s->fd, FS_IOC_FIEMAP, &f) == -1) {
s->skip_fiemap = true;
return -errno;
/*
* SEEK_DATA cases:
* D1. offs == start: start is in data
* D2. offs > start: start is in a hole, next data at offs
* D3. offs < 0, errno = ENXIO: either start is in a trailing hole
* or start is beyond EOF
* If the latter happens, the file has been truncated behind
* our back since we opened it. All bets are off then.
* Treating like a trailing hole is simplest.
* D4. offs < 0, errno != ENXIO: we learned nothing
*/
offs = lseek(s->fd, start, SEEK_DATA);
if (offs < 0) {
return -errno; /* D3 or D4 */
}
assert(offs >= start);
if (f.fm.fm_mapped_extents == 0) {
/* No extents found, data is beyond f.fm.fm_start + f.fm.fm_length.
* f.fm.fm_start + f.fm.fm_length must be clamped to the file size!
*/
off_t length = lseek(s->fd, 0, SEEK_END);
*hole = f.fm.fm_start;
*data = MIN(f.fm.fm_start + f.fm.fm_length, length);
} else {
*data = f.fe.fe_logical;
*hole = f.fe.fe_logical + f.fe.fe_length;
if (f.fe.fe_flags & FIEMAP_EXTENT_UNWRITTEN) {
ret |= BDRV_BLOCK_ZERO;
}
if (offs > start) {
/* D2: in hole, next data at offs */
*hole = start;
*data = offs;
return 0;
}
return ret;
#else
return -ENOTSUP;
#endif
}
static int try_seek_hole(BlockDriverState *bs, off_t start, off_t *data,
off_t *hole)
{
#if defined SEEK_HOLE && defined SEEK_DATA
BDRVRawState *s = bs->opaque;
/* D1: in data, end not yet known */
*hole = lseek(s->fd, start, SEEK_HOLE);
if (*hole == -1) {
return -errno;
/*
* SEEK_HOLE cases:
* H1. offs == start: start is in a hole
* If this happens here, a hole has been dug behind our back
* since the previous lseek().
* H2. offs > start: either start is in data, next hole at offs,
* or start is in trailing hole, EOF at offs
* Linux treats trailing holes like any other hole: offs ==
* start. Solaris seeks to EOF instead: offs > start (blech).
* If that happens here, a hole has been dug behind our back
* since the previous lseek().
* H3. offs < 0, errno = ENXIO: start is beyond EOF
* If this happens, the file has been truncated behind our
* back since we opened it. Treat it like a trailing hole.
* H4. offs < 0, errno != ENXIO: we learned nothing
* Pretend we know nothing at all, i.e. "forget" about D1.
*/
offs = lseek(s->fd, start, SEEK_HOLE);
if (offs < 0) {
return -errno; /* D1 and (H3 or H4) */
}
assert(offs >= start);
if (*hole > start) {
if (offs > start) {
/*
* D1 and H2: either in data, next hole at offs, or it was in
* data but is now in a trailing hole. In the latter case,
* all bets are off. Treating it as if it there was data all
* the way to EOF is safe, so simply do that.
*/
*data = start;
} else {
/* On a hole. We need another syscall to find its end. */
*data = lseek(s->fd, start, SEEK_DATA);
if (*data == -1) {
*data = lseek(s->fd, 0, SEEK_END);
}
*hole = offs;
return 0;
}
return 0;
/* D1 and H1 */
return -EBUSY;
#else
return -ENOTSUP;
#endif
}
/*
* Returns true iff the specified sector is present in the disk image. Drivers
* not implementing the functionality are assumed to not support backing files,
* hence all their sectors are reported as allocated.
* Returns the allocation status of the specified sectors.
*
* If 'sector_num' is beyond the end of the disk image the return value is 0
* and 'pnum' is set to 0.
......@@ -1593,28 +1604,26 @@ static int64_t coroutine_fn raw_co_get_block_status(BlockDriverState *bs,
nb_sectors = DIV_ROUND_UP(total_size - start, BDRV_SECTOR_SIZE);
}
ret = try_seek_hole(bs, start, &data, &hole);
if (ret < 0) {
ret = try_fiemap(bs, start, &data, &hole, nb_sectors);
if (ret < 0) {
/* Assume everything is allocated. */
data = 0;
hole = start + nb_sectors * BDRV_SECTOR_SIZE;
ret = 0;
}
}
assert(ret >= 0);
if (data <= start) {
ret = find_allocation(bs, start, &data, &hole);
if (ret == -ENXIO) {
/* Trailing hole */
*pnum = nb_sectors;
ret = BDRV_BLOCK_ZERO;
} else if (ret < 0) {
/* No info available, so pretend there are no holes */
*pnum = nb_sectors;
ret = BDRV_BLOCK_DATA;
} else if (data == start) {
/* On a data extent, compute sectors to the end of the extent. */
*pnum = MIN(nb_sectors, (hole - start) / BDRV_SECTOR_SIZE);
return ret | BDRV_BLOCK_DATA | BDRV_BLOCK_OFFSET_VALID | start;
ret = BDRV_BLOCK_DATA;
} else {
/* On a hole, compute sectors to the beginning of the next extent. */
assert(hole == start);
*pnum = MIN(nb_sectors, (data - start) / BDRV_SECTOR_SIZE);
return ret | BDRV_BLOCK_ZERO | BDRV_BLOCK_OFFSET_VALID | start;
ret = BDRV_BLOCK_ZERO;
}
return ret | BDRV_BLOCK_OFFSET_VALID | start;
}
static coroutine_fn BlockAIOCB *raw_aio_discard(BlockDriverState *bs,
......
Markdown is supported
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment