On Thu, May 10, 2018 at 03:34:50PM +0800, Jason Wang wrote:
On 2018å05æ10æ 15:32, Jason Wang wrote:Nice catch! Thanks a lot!
On 2018å04æ25æ 13:15, Tiwei Bie wrote:next_avail should be 6 here.
+ÂÂÂ /* We're using some buffers from the free list. */During testing zerocopy (out of order completion), I found driver may
+ÂÂÂ vq->vq.num_free -= descs_used;
+
+ÂÂÂ /* Update free pointer */
+ÂÂÂ if (indirect) {
+ÂÂÂÂÂÂÂ n = head + 1;
+ÂÂÂÂÂÂÂ if (n >= vq->vring_packed.num) {
+ÂÂÂÂÂÂÂÂÂÂÂ n = 0;
+ÂÂÂÂÂÂÂÂÂÂÂ vq->wrap_counter ^= 1;
+ÂÂÂÂÂÂÂ }
+ÂÂÂÂÂÂÂ vq->next_avail_idx = n;
+ÂÂÂ } else
+ÂÂÂÂÂÂÂ vq->next_avail_idx = i;
submit two identical buffer id to vhost. So the above code may not work
well.
Consider the case that driver adds 3 buffer and virtqueue size is 8.
a) id = 0,count = 2,next_avail = 2
b) id = 2,count = 4,next_avail = 2
c) id = 4,count = 2,next_avail = 0id should be 6 here.
Thanks
if packet b is done before packet a, driver may think buffer id 0 is
available and try to use it if even if the real buffer 0 was not done.
Thanks
I'll implement an ID allocator.
Best regards,
Tiwei Bie