diff options
| -rw-r--r-- | block/file-posix.c | 67 | ||||
| -rw-r--r-- | block/io.c | 35 | ||||
| -rw-r--r-- | include/block/block_int-common.h | 4 | ||||
| -rw-r--r-- | qemu-img.c | 2 |
4 files changed, 79 insertions, 29 deletions
diff --git a/block/file-posix.c b/block/file-posix.c index 56d1972d15..0d6e12f880 100644 --- a/block/file-posix.c +++ b/block/file-posix.c @@ -1276,10 +1276,10 @@ static int get_sysfs_zoned_model(struct stat *st, BlockZoneModel *zoned) } #endif /* defined(CONFIG_BLKZONED) */ +#ifdef CONFIG_LINUX /* * Get a sysfs attribute value as a long integer. */ -#ifdef CONFIG_LINUX static long get_sysfs_long_val(struct stat *st, const char *attribute) { g_autofree char *str = NULL; @@ -1299,6 +1299,30 @@ static long get_sysfs_long_val(struct stat *st, const char *attribute) } return ret; } + +/* + * Get a sysfs attribute value as a uint32_t. + */ +static int get_sysfs_u32_val(struct stat *st, const char *attribute, + uint32_t *u32) +{ + g_autofree char *str = NULL; + const char *end; + unsigned int val; + int ret; + + ret = get_sysfs_str_val(st, attribute, &str); + if (ret < 0) { + return ret; + } + + /* The file is ended with '\n', pass 'end' to accept that. */ + ret = qemu_strtoui(str, &end, 10, &val); + if (ret == 0 && end && *end == '\0') { + *u32 = val; + } + return ret; +} #endif static int hdev_get_max_segments(int fd, struct stat *st) @@ -1318,6 +1342,23 @@ static int hdev_get_max_segments(int fd, struct stat *st) #endif } +/* + * Fills in *dalign with the discard alignment and returns 0 on success, + * -errno otherwise. + */ +static int hdev_get_pdiscard_alignment(struct stat *st, uint32_t *dalign) +{ +#ifdef CONFIG_LINUX + /* + * Note that Linux "discard_granularity" is QEMU "discard_alignment". Linux + * "discard_alignment" is something else. + */ + return get_sysfs_u32_val(st, "discard_granularity", dalign); +#else + return -ENOTSUP; +#endif +} + #if defined(CONFIG_BLKZONED) /* * If the reset_all flag is true, then the wps of zone whose state is @@ -1527,6 +1568,30 @@ static void raw_refresh_limits(BlockDriverState *bs, Error **errp) } } + if (S_ISBLK(st.st_mode)) { + uint32_t dalign = 0; + int ret; + + ret = hdev_get_pdiscard_alignment(&st, &dalign); + if (ret == 0) { + uint32_t ralign = bs->bl.request_alignment; + + /* Probably never happens, but handle it just in case */ + if (dalign < ralign && (ralign % dalign == 0)) { + dalign = ralign; + } + + /* The block layer requires a multiple of request_alignment */ + if (dalign % ralign != 0) { + error_setg(errp, "Invalid pdiscard_alignment limit %u is not a " + "multiple of request_alignment %u", dalign, ralign); + return; + } + + bs->bl.pdiscard_alignment = dalign; + } + } + raw_refresh_zoned_limits(bs, &st, errp); } diff --git a/block/io.c b/block/io.c index 1ba8d1aeea..6d98b0abb9 100644 --- a/block/io.c +++ b/block/io.c @@ -3102,18 +3102,19 @@ int coroutine_fn bdrv_co_pdiscard(BdrvChild *child, int64_t offset, return 0; } - if (!bs->drv->bdrv_co_pdiscard && !bs->drv->bdrv_aio_pdiscard) { + if (!bs->drv->bdrv_co_pdiscard) { return 0; } /* Invalidate the cached block-status data range if this discard overlaps */ bdrv_bsc_invalidate_range(bs, offset, bytes); - /* Discard is advisory, but some devices track and coalesce + /* + * 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. */ + * round here. Still, most devices reject unaligned requests with + * -EINVAL or -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; @@ -3161,27 +3162,15 @@ int coroutine_fn bdrv_co_pdiscard(BdrvChild *child, int64_t offset, ret = -ENOMEDIUM; goto out; } - if (bs->drv->bdrv_co_pdiscard) { - ret = bs->drv->bdrv_co_pdiscard(bs, offset, num); - } else { - BlockAIOCB *acb; - CoroutineIOCompletion co = { - .coroutine = qemu_coroutine_self(), - }; - - acb = bs->drv->bdrv_aio_pdiscard(bs, offset, num, - bdrv_co_io_em_complete, &co); - if (acb == NULL) { - ret = -EIO; - goto out; + + ret = bs->drv->bdrv_co_pdiscard(bs, offset, num); + if (ret && ret != -ENOTSUP) { + if (ret == -EINVAL && (offset % align != 0 || num % align != 0)) { + /* Silently skip rejected unaligned head/tail requests */ } else { - qemu_coroutine_yield(); - ret = co.ret; + goto out; /* bail out */ } } - if (ret && ret != -ENOTSUP) { - goto out; - } offset += num; bytes -= num; diff --git a/include/block/block_int-common.h b/include/block/block_int-common.h index ebb4e56a50..0d8187f656 100644 --- a/include/block/block_int-common.h +++ b/include/block/block_int-common.h @@ -506,10 +506,6 @@ struct BlockDriver { BlockAIOCB * GRAPH_RDLOCK_PTR (*bdrv_aio_flush)( BlockDriverState *bs, BlockCompletionFunc *cb, void *opaque); - BlockAIOCB * GRAPH_RDLOCK_PTR (*bdrv_aio_pdiscard)( - BlockDriverState *bs, int64_t offset, int bytes, - BlockCompletionFunc *cb, void *opaque); - int coroutine_fn GRAPH_RDLOCK_PTR (*bdrv_co_readv)(BlockDriverState *bs, int64_t sector_num, int nb_sectors, QEMUIOVector *qiov); diff --git a/qemu-img.c b/qemu-img.c index 2044c22a4c..76ac5d3028 100644 --- a/qemu-img.c +++ b/qemu-img.c @@ -4571,7 +4571,7 @@ static int img_bench(int argc, char **argv) { unsigned long res; - if (qemu_strtoul(optarg, NULL, 0, &res) < 0 || res > INT_MAX) { + if (qemu_strtoul(optarg, NULL, 0, &res) <= 0 || res > INT_MAX) { error_report("Invalid queue depth specified"); return 1; } |