From: Christoph Hellwig Date: Sat, 18 Jul 2009 03:47:45 +0000 (-0600) Subject: virtio_blk: don't bounce highmem requests X-Git-Tag: v2.6.31-rc4~33^2~3 X-Git-Url: https://openfabrics.org/gitweb/?a=commitdiff_plain;h=4eff3cae9c9809720c636e64bc72f212258e0bd5;p=~shefty%2Frdma-dev.git virtio_blk: don't bounce highmem requests By default a block driver bounces highmem requests, but virtio-blk is perfectly fine with any request that fit into it's 64 bit addressing scheme, mapped in the kernel virtual space or not. Besides improving performance on highmem systems this also makes the reproducible oops in __bounce_end_io go away (but hiding the real cause). Signed-off-by: Christoph Hellwig Signed-off-by: Rusty Russell --- diff --git a/drivers/block/virtio_blk.c b/drivers/block/virtio_blk.c index 43db3ea15b5..4c47859ad8b 100644 --- a/drivers/block/virtio_blk.c +++ b/drivers/block/virtio_blk.c @@ -360,6 +360,9 @@ static int __devinit virtblk_probe(struct virtio_device *vdev) blk_queue_max_phys_segments(vblk->disk->queue, vblk->sg_elems-2); blk_queue_max_hw_segments(vblk->disk->queue, vblk->sg_elems-2); + /* No need to bounce any requests */ + blk_queue_bounce_limit(vblk->disk->queue, BLK_BOUNCE_ANY); + /* No real sector limit. */ blk_queue_max_sectors(vblk->disk->queue, -1U);