[Qemu-block] block: split large discard requests from block frontend

Commit Message

Olaf Hering Nov. 17, 2016, 4:27 p.m. UTC

On Thu, Nov 17, Olaf Hering wrote:

> Looking at current master, BLKIF_OP_DISCARD is indeed broken. The values
> passed from the guest are u64 and get stashed into signed values. I will
> add a loop to repeatedly call blk_aio_pdiscard with small chunks of
> BDRV_REQUEST_MAX_SECTORS.

I have not compile tested the change below, but thats the way how I
would deal with it:



Olaf

Patch

diff --git a/hw/block/xen_disk.c b/hw/block/xen_disk.c
index 3a7dc19..5962c4b 100644
--- a/hw/block/xen_disk.c
+++ b/hw/block/xen_disk.c
@@ -660,6 +660,38 @@  static void qemu_aio_complete(void *opaque, int ret)
     qemu_bh_schedule(ioreq->blkdev->bh);
 }
 
+static bool blk_split_discard(struct ioreq *ioreq, blkif_sector_t sector_number, uint64_t nr_sectors)
+{
+    struct XenBlkDev *blkdev = ioreq->blkdev;
+    int64_t byte_offset;
+    int bytes;
+    uint64_t byte_limit = INT64_MAX + INT_MAX;
+    uint64_t sec_start = sector_number;
+    uint64_t sec_count = nr_sectors;
+    uint64_t byte_remaining;
+    uint64_t limit = BDRV_REQUEST_MAX_SECTORS << BDRV_SECTOR_BITS;
+
+    /* Wrap around? */
+    if ((sec_start + sec_count) < sec_count)
+        return false;
+    /* Overflowing byte limit? */
+    if ((sec_start + sec_count) > (byte_limit >> BDRV_SECTOR_BITS))
+        return false;
+
+    byte_offset = sec_start << BDRV_SECTOR_BITS;
+    byte_remaining = sec_count << BDRV_SECTOR_BITS;
+    do {
+        bytes = byte_remaining > limit ? limit : byte_remaining;
+        ioreq->aio_inflight++;
+        blk_aio_pdiscard(blkdev->blk, byte_offset, bytes,
+                         qemu_aio_complete, ioreq);
+        byte_remaining -= bytes;
+        byte_offset += bytes;
+    } while (byte_remaining > 0);
+
+    return true;
+}
+
 static int ioreq_runio_qemu_aio(struct ioreq *ioreq)
 {
     struct XenBlkDev *blkdev = ioreq->blkdev;
@@ -708,12 +740,9 @@  static int ioreq_runio_qemu_aio(struct ioreq *ioreq)
         break;
     case BLKIF_OP_DISCARD:
     {
-        struct blkif_request_discard *discard_req = (void *)&ioreq->req;
-        ioreq->aio_inflight++;
-        blk_aio_pdiscard(blkdev->blk,
-                         discard_req->sector_number << BDRV_SECTOR_BITS,
-                         discard_req->nr_sectors << BDRV_SECTOR_BITS,
-                         qemu_aio_complete, ioreq);
+        struct blkif_request_discard *req = (void *)&ioreq->req;
+        if (blk_split_discard(ioreq, req->sector_number, req->nr_sectors))
+            goto err;
         break;
     }
     default: