block: introduce zone append write for zoned devices

A zone append command is a write operation that specifies the first
logical block of a zone as the write position. When writing to a zoned
block device using zone append, the byte offset of the call may point at
any position within the zone to which the data is being appended. Upon
completion the device will respond with the position where the data has
been written in the zone.

Signed-off-by: Sam Li <faithilikerun@gmail.com>
Reviewed-by: Dmitry Fomichev <dmitry.fomichev@wdc.com>
Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com>
Message-id: 20230508051510.177850-3-faithilikerun@gmail.com
Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com>

1 files changed, 51 insertions, 7 deletions

diff --git a/block/file-posix.c b/block/file-posix.c
index 56f5751..179263f 100644
--- a/block/file-posix.c
+++ b/block/file-posix.c
@@ -160,6 +160,7 @@ typedef struct BDRVRawState {
     bool has_write_zeroes:1;
     bool use_linux_aio:1;
     bool use_linux_io_uring:1;
+    int64_t *offset; /* offset of zone append operation */
     int page_cache_inconsistent; /* errno from fdatasync failure */
     bool has_fallocate;
     bool needs_alignment;
@@ -1698,7 +1699,7 @@ static ssize_t handle_aiocb_rw_vector(RawPosixAIOData *aiocb)
     ssize_t len;
 
     len = RETRY_ON_EINTR(
-        (aiocb->aio_type & QEMU_AIO_WRITE) ?
+        (aiocb->aio_type & (QEMU_AIO_WRITE | QEMU_AIO_ZONE_APPEND)) ?
             qemu_pwritev(aiocb->aio_fildes,
                            aiocb->io.iov,
                            aiocb->io.niov,
@@ -1727,7 +1728,7 @@ static ssize_t handle_aiocb_rw_linear(RawPosixAIOData *aiocb, char *buf)
     ssize_t len;
 
     while (offset < aiocb->aio_nbytes) {
-        if (aiocb->aio_type & QEMU_AIO_WRITE) {
+        if (aiocb->aio_type & (QEMU_AIO_WRITE | QEMU_AIO_ZONE_APPEND)) {
             len = pwrite(aiocb->aio_fildes,
                          (const char *)buf + offset,
                          aiocb->aio_nbytes - offset,
@@ -1820,7 +1821,7 @@ static int handle_aiocb_rw(void *opaque)
     }
 
     nbytes = handle_aiocb_rw_linear(aiocb, buf);
-    if (!(aiocb->aio_type & QEMU_AIO_WRITE)) {
+    if (!(aiocb->aio_type & (QEMU_AIO_WRITE | QEMU_AIO_ZONE_APPEND))) {
         char *p = buf;
         size_t count = aiocb->aio_nbytes, copy;
         int i;
@@ -2453,8 +2454,12 @@ static int coroutine_fn raw_co_prw(BlockDriverState *bs, uint64_t offset,
     if (fd_open(bs) < 0)
         return -EIO;
 #if defined(CONFIG_BLKZONED)
-    if (type & QEMU_AIO_WRITE && bs->wps) {
+    if ((type & (QEMU_AIO_WRITE | QEMU_AIO_ZONE_APPEND)) && bs->wps) {
         qemu_co_mutex_lock(&bs->wps->colock);
+        if (type & QEMU_AIO_ZONE_APPEND && bs->bl.zone_size) {
+            int index = offset / bs->bl.zone_size;
+            offset = bs->wps->wp[index];
+        }
     }
 #endif
 
@@ -2502,9 +2507,13 @@ out:
 {
     BlockZoneWps *wps = bs->wps;
     if (ret == 0) {
-        if (type & QEMU_AIO_WRITE && wps && bs->bl.zone_size) {
+        if ((type & (QEMU_AIO_WRITE | QEMU_AIO_ZONE_APPEND))
+            && wps && bs->bl.zone_size) {
             uint64_t *wp = &wps->wp[offset / bs->bl.zone_size];
             if (!BDRV_ZT_IS_CONV(*wp)) {
+                if (type & QEMU_AIO_ZONE_APPEND) {
+                    *s->offset = *wp;
+                }
                 /* Advance the wp if needed */
                 if (offset + bytes > *wp) {
                     *wp = offset + bytes;
@@ -2512,12 +2521,12 @@ out:
             }
         }
     } else {
-        if (type & QEMU_AIO_WRITE) {
+        if (type & (QEMU_AIO_WRITE | QEMU_AIO_ZONE_APPEND)) {
             update_zones_wp(bs, s->fd, 0, 1);
         }
     }
 
-    if (type & QEMU_AIO_WRITE && wps) {
+    if ((type & (QEMU_AIO_WRITE | QEMU_AIO_ZONE_APPEND)) && wps) {
         qemu_co_mutex_unlock(&wps->colock);
     }
 }
@@ -3515,6 +3524,40 @@ static int coroutine_fn raw_co_zone_mgmt(BlockDriverState *bs, BlockZoneOp op,
 }
 #endif
 
+#if defined(CONFIG_BLKZONED)
+static int coroutine_fn raw_co_zone_append(BlockDriverState *bs,
+                                           int64_t *offset,
+                                           QEMUIOVector *qiov,
+                                           BdrvRequestFlags flags) {
+    assert(flags == 0);
+    int64_t zone_size_mask = bs->bl.zone_size - 1;
+    int64_t iov_len = 0;
+    int64_t len = 0;
+    BDRVRawState *s = bs->opaque;
+    s->offset = offset;
+
+    if (*offset & zone_size_mask) {
+        error_report("sector offset %" PRId64 " is not aligned to zone size "
+                     "%" PRId32 "", *offset / 512, bs->bl.zone_size / 512);
+        return -EINVAL;
+    }
+
+    int64_t wg = bs->bl.write_granularity;
+    int64_t wg_mask = wg - 1;
+    for (int i = 0; i < qiov->niov; i++) {
+        iov_len = qiov->iov[i].iov_len;
+        if (iov_len & wg_mask) {
+            error_report("len of IOVector[%d] %" PRId64 " is not aligned to "
+                         "block size %" PRId64 "", i, iov_len, wg);
+            return -EINVAL;
+        }
+        len += iov_len;
+    }
+
+    return raw_co_prw(bs, *offset, len, qiov, QEMU_AIO_ZONE_APPEND);
+}
+#endif
+
 static coroutine_fn int
 raw_do_pdiscard(BlockDriverState *bs, int64_t offset, int64_t bytes,
                 bool blkdev)
@@ -4276,6 +4319,7 @@ static BlockDriver bdrv_host_device = {
     /* zone management operations */
     .bdrv_co_zone_report = raw_co_zone_report,
     .bdrv_co_zone_mgmt = raw_co_zone_mgmt,
+    .bdrv_co_zone_append = raw_co_zone_append,
 #endif
 };