virtio_ring currently sends the device (usually a hypervisor)
physical addresses of its I/O buffers. This is okay when DMA
addresses and physical addresses are the same thing, but this isn't
always the case. For example, this never works on Xen guests, and
it is likely to fail if a physical "virtio" device ever ends up
behind an IOMMU or swiotlb.
The immediate use case for me is to enable virtio on Xen guests.
For that to work, we need vring to support DMA address translation
as well as a corresponding change to virtio_pci or to another
driver.
Signed-off-by: Andy Lutomirski <luto@kernel.org>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
This adds micro-benchmarks useful for tuning virtio ring layouts.
Three layouts are currently implemented:
- virtio 0.9 compatible one
- an experimental extension bypassing the ring index, polling ring
itself instead
- an experimental extension bypassing avail and used ring completely
Typical use:
sh run-on-all.sh perf stat -r 10 --log-fd 1 -- ./ring
It doesn't depend on the kernel directly, but it's handy
to have as much virtio stuff as possible in one tree.
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
commit cf561f0d2e ("virtio: introduce
virtio_is_little_endian() helper") changed byteswap logic to
skip feature bit checks for LE platforms, but didn't
update tools/virtio, so vring_bench started failing.
Update the copy under tools/virtio/ (TODO: find a way to avoid this code
duplication).
Cc: Greg Kurz <gkurz@linux.vnet.ibm.com>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
Change u32 to u64, and use BIT_ULL and 1ULL everywhere.
Note: transports are unchanged, and only set low 32 bit.
This guarantees that no transport sets e.g. VERSION_1
by mistake without proper support.
Based on patch by Rusty.
Signed-off-by: Rusty Russell <rusty@rustcorp.com.au>
Signed-off-by: Cornelia Huck <cornelia.huck@de.ibm.com>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
Reviewed-by: David Hildenbrand <dahi@linux.vnet.ibm.com>
Reviewed-by: Cornelia Huck <cornelia.huck@de.ibm.com>
It seemed like a good idea to use bitmap for features
in struct virtio_device, but it's actually a pain,
and seems to become even more painful when we get more
than 32 feature bits. Just change it to a u32 for now.
Based on patch by Rusty.
Suggested-by: David Hildenbrand <dahi@linux.vnet.ibm.com>
Signed-off-by: Rusty Russell <rusty@rustcorp.com.au>
Signed-off-by: Cornelia Huck <cornelia.huck@de.ibm.com>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
Reviewed-by: Cornelia Huck <cornelia.huck@de.ibm.com>
Fixes the following build failure:
cc -g -O2 -Wall -I. -I ../../usr/include/ -Wno-pointer-sign
-fno-strict-overflow -fno-strict-aliasing -fno-common -MMD
-U_FORTIFY_SOURCE -c -o virtio_test.o virtio_test.c
virtio_test.c: In function ‘run_test’:
virtio_test.c:176:7: error: expected ‘)’ before ‘r’
r = -1;
^
Fixes: 53c18c9906 (virtio_test: verify if virtqueue_kick() succeeded)
Cc: Heinz Graalfs <graalfs@linux.vnet.ibm.com>
Signed-off-by: Joel Stanley <joel@jms.id.au>
Acked-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: Rusty Russell <rusty@rustcorp.com.au>
In commit bb478d8b16 virtio_ring: plug kmemleak false positive,
kmemleak_ignore was introduced. This broke compilation of virtio_test:
cc -g -O2 -Wall -I. -I ../../usr/include/ -Wno-pointer-sign
-fno-strict-overflow -fno-strict-aliasing -fno-common -MMD
-U_FORTIFY_SOURCE -c -o virtio_ring.o ../../drivers/virtio/virtio_ring.c
../../drivers/virtio/virtio_ring.c: In function ‘vring_add_indirect’:
../../drivers/virtio/virtio_ring.c:177:2: warning: implicit declaration
of function ‘kmemleak_ignore’ [-Wimplicit-function-declaration]
kmemleak_ignore(desc);
^
cc virtio_test.o virtio_ring.o -o virtio_test
virtio_ring.o: In function `vring_add_indirect':
tools/virtio/../../drivers/virtio/virtio_ring.c:177:
undefined reference to `kmemleak_ignore'
Add a dummy header for tools/virtio, and add #incldue <linux/kmemleak.h>
to drivers/virtio/virtio_ring.c so it is picked up by the userspace
tools.
Signed-off-by: Joel Stanley <joel@jms.id.au>
Signed-off-by: Rusty Russell <rusty@rustcorp.com.au>
The virtio headers have changed recently:
5b1bf7cb67 virtio_ring: let virtqueue_{kick()/notify()} return a bool
46f9c2b925 virtio_ring: change host notification API
Update the internal copies to fix the build of virtio_test:
cc -g -O2 -Wall -I. -I ../../usr/include/ -Wno-pointer-sign
-fno-strict-overflow -fno-strict-aliasing -fno-common -MMD -U_FORTIFY_SOURCE
-c -o virtio_test.o virtio_test.c
In file included from virtio_test.c:15:0:
./linux/virtio.h:76:19: error: conflicting types for ‘vring_new_virtqueue’
struct virtqueue *vring_new_virtqueue(unsigned int index,
^
In file included from ./linux/virtio_ring.h:1:0,
from ../../usr/include/linux/vhost.h:17,
from virtio_test.c:14:
./linux/../../../include/linux/virtio_ring.h:68:19: note: previous
declaration of ‘vring_new_virtqueue’ was here
struct virtqueue *vring_new_virtqueue(unsigned int index,
virtio_test.c: In function ‘vq_info_add’:
virtio_test.c:103:12: warning: passing argument 7 of ‘vring_new_virtqueue’
from incompatible pointer type [enabled by default]
vq_notify, vq_callback, "test");
^
In file included from virtio_test.c:15:0:
./linux/virtio.h:76:19: note: expected ‘void (*)(struct virtqueue *)’ but
argument is of type ‘_Bool (*)(struct virtqueue *)’
struct virtqueue *vring_new_virtqueue(unsigned int index,
^
Signed-off-by: Joel Stanley <joel@jms.id.au>
Signed-off-by: Rusty Russell <rusty@rustcorp.com.au>
Verify if a host kick succeeded by checking return value of virtqueue_kick().
Signed-off-by: Heinz Graalfs <graalfs@linux.vnet.ibm.com>
Signed-off-by: Rusty Russell <rusty@rustcorp.com.au>
Currently a host kick error is silently ignored and not reflected in
the virtqueue of a particular virtio device.
Changing the notify API for guest->host notification seems to be one
prerequisite in order to be able to handle such errors in the context
where the kick is triggered.
This patch changes the notify API. The notify function must return a
bool return value. It returns false if the host notification failed.
Signed-off-by: Heinz Graalfs <graalfs@linux.vnet.ibm.com>
Signed-off-by: Rusty Russell <rusty@rustcorp.com.au>
