Signed-off-by: Michael S. Tsirkin <mst@redhat.com>

Signed-off-by: Michael S. Tsirkin <mst@redhat.com>

Seems to mostly be a positive.
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>

Missed one place where vringh_test used
long to pass features. Fix it up to u64.
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>

Include missing virtio_config.h
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>

As usual, add more stubs to fix test build after main
codebase changes.
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>

virtio 1.0 spec says:

Drivers MUST NOT assume reads from fields greater than 32 bits wide are
atomic, nor are reads from multiple fields: drivers SHOULD read device
configuration space fields like so:
	u32 before, after;
	do {
		before = get_config_generation(device);
		// read config entry/entries.
		after = get_config_generation(device);
	} while (after != before);

Do exactly this, for transports that support it.
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>

Add macro to disable all legacy register defines.
Helpful to make sure legacy macros don't leak
through into modern code.
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>

It turns out this make everything easier.
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>

Legacy drivers use virtio_pci_common.h too, we should not
define VIRTIO_PCI_NO_LEGACY there.
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>

virtio_cread_bytes is implemented incorrectly in case length happens to
be 2,4 or 8 bytes: transports and devices will assume it's an integer
value that has to be converted to LE format.

Let's just do multiple 1-byte reads: this also makes life easier
for transports who only need to implement 1,2,4 and 8 byte reads.
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>

virtio 1.0 devices require that drivers set VIRTIO_CONFIG_S_FEATURES_OK
after finalizing features.
virtio core missed doing this on restore, fix it up.
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
Reviewed-by: Cornelia Huck <cornelia.huck@de.ibm.com>

We previously tried to use device even if finalize_features failed, but
that's wrong since driver and device are now out of sync.

Fail probe if we detect failures during finalize_features.
Signed-off-by: Cornelia Huck <cornelia.huck@de.ibm.com>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>

We never negotiate revision > 1, but just to
make this code more likely to work when we do,
require VERSION_1 with any revision >= 1.
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
Acked-by: Cornelia Huck <cornelia.huck@de.ibm.com>

kbuild does not seem to like it when we name source
files same as the module.
Let's rename virtio_pci -> virtio_pci_common,
and get rid of #include-ing c files.
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>

There's been a lot of changes since 2007.
List main authors, add Red Hat copyright.
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>

Move everything dealing with legacy devices out to virtio_pci_legacy.c.
Expose common code APIs in virtio_pci.h
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>

config vector setup is version specific, do it indirectly.
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>

VQ setup is mostly version-specific, add another level of indirection to
split the version-independent code out.
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>

VQ deletion is mostly version-specific, add another level of indirection
to split the version-independent code out.
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>

slightly reduce the amount of pointer chasing this needs to do.
More importantly, this will easily generalize to virtio 1.0.
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>

We don't need to go from vq to vq info on
data path, so using direct vq->priv pointer for that
seems like a waste.

Let's build an array of vq infos, then we can use vq->index
for that lookup.
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>

should be

struct foo {
}

not

struct foo
{
}
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>

Use isr field instead of direct access to ioaddr.
This way generalizes easily to virtio 1.0.
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>

legacy_only flag is now unused, drop it from core.
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
Acked-by: Cornelia Huck <cornelia.huck@de.ibm.com>

we have blacklisted balloon in core, no need
for a driver flag.
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
Acked-by: Cornelia Huck <cornelia.huck@de.ibm.com>

What does it mean if rev 1 device does not set
VIRTIO_F_VERSION_1? E.g. is it native endian?

Let's not even try to drive such devices:
fail attempts to finalize features.
virtio core will detect this and bail out.
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>

This will make it easy for transports to validate features and return
failure.
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>

Legacy balloon device doesn't pretend to support revision 1 or 64 bit
features.

But just in case someone implements a broken one that does, let's not
even try to drive legacy only devices using revision 1, and let's not
give them a chance to say they support VIRTIO_F_VERSION_1 by not reading
or writing high feature bits.
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
Reviewed-by: Cornelia Huck <cornelia.huck@de.ibm.com>

transports need to be able to detect legacy-only
devices (ATM balloon only) to use legacy path
to drive them.

Add a core API to do just that.
The implementation just blacklists balloon:
not too pretty, but let's not over-engineer.
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
Acked-by: Cornelia Huck <cornelia.huck@de.ibm.com>

CHECK drivers/char/virtio_console.c
drivers/char/virtio_console.c:687:36: warning: incorrect type in
	argument 1 (different address spaces)
drivers/char/virtio_console.c:687:36:    expected void [noderef]
	<asn:1>*to
drivers/char/virtio_console.c:687:36:    got char *out_buf
drivers/char/virtio_console.c:790:35: warning: incorrect type in
	argument 2 (different address spaces)
drivers/char/virtio_console.c:790:35:    expected char *out_buf
drivers/char/virtio_console.c:790:35:    got char [noderef]
	<asn:1>*ubuf

fill_readbuf is reused with both kernel and userspace pointers,
depending on value of to_user flag.

Tag address parameter as __user, and cast to/from regular pointer type
when we know it's safe.
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>

Signed-off-by: Jason Wang <jasowang@redhat.com>
Acked-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>

Core activates this bit automatically now,
drop it from drivers that set it explicitly.
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>

Activate VIRTIO_F_VERSION_1 automatically unless legacy_only
is set.
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>

We have no plans to support virtio 1.0 in balloon driver.  Add an
explicit flag to mark it legacy only.

This will be used by follow-up patches.
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>

Pretty straight-forward, just use accessors for all fields.
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>

This merely fixes sparse warnings, without actually
adding support for the new APIs.

Still working out the best way to enable the new
functionality.
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>

Include all endian conversions as required by virtio 1.0.
Don't set virtio 1.0 yet, since that requires ANY_LAYOUT
which we don't yet support.
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
Acked-by: Paolo Bonzini <pbonzini@redhat.com>

Replace uXX by __uXX and _packed by __attribute((packed))
as seems to be the norm for userspace headers.
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
Acked-by: Paolo Bonzini <pbonzini@redhat.com>

Guests need to use virtio scsi API, so export it to uapi,
nice to e.g. qemu and will help us remember this file
affects ABI.
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
Acked-by: Paolo Bonzini <pbonzini@redhat.com>