* [PATCH v7 07/46] virtio: add virtio 1.0 feature bit
[not found] <1417359787-10138-1-git-send-email-mst@redhat.com>
@ 2014-11-30 15:09 ` Michael S. Tsirkin
2014-11-30 15:09 ` [PATCH v7 08/46] virtio: memory access APIs Michael S. Tsirkin
` (6 subsequent siblings)
7 siblings, 0 replies; 26+ messages in thread
From: Michael S. Tsirkin @ 2014-11-30 15:09 UTC (permalink / raw)
To: linux-kernel
Cc: thuth, rusty, linux-api, virtualization, dahi, pbonzini,
David Miller
Based on original patches by Rusty Russell, Thomas Huth
and Cornelia Huck.
Note: at this time, we do not negotiate this feature bit
in core, drivers have to declare VERSION_1 support explicitly.
For this reason we treat this bit as a device bit
and not as a transport bit for now.
After all drivers are converted, we will be able to
move VERSION_1 to core and drop it from all drivers.
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
Reviewed-by: Cornelia Huck <cornelia.huck@de.ibm.com>
---
include/uapi/linux/virtio_config.h | 3 +++
1 file changed, 3 insertions(+)
diff --git a/include/uapi/linux/virtio_config.h b/include/uapi/linux/virtio_config.h
index 3ce768c..80e7381 100644
--- a/include/uapi/linux/virtio_config.h
+++ b/include/uapi/linux/virtio_config.h
@@ -54,4 +54,7 @@
/* Can the device handle any descriptor layout? */
#define VIRTIO_F_ANY_LAYOUT 27
+/* v1.0 compliant. */
+#define VIRTIO_F_VERSION_1 32
+
#endif /* _UAPI_LINUX_VIRTIO_CONFIG_H */
--
MST
^ permalink raw reply related [flat|nested] 26+ messages in thread* [PATCH v7 08/46] virtio: memory access APIs
[not found] <1417359787-10138-1-git-send-email-mst@redhat.com>
2014-11-30 15:09 ` [PATCH v7 07/46] virtio: add virtio 1.0 feature bit Michael S. Tsirkin
@ 2014-11-30 15:09 ` Michael S. Tsirkin
2014-12-01 9:56 ` Cornelia Huck
2014-11-30 15:10 ` [PATCH v7 12/46] virtio: set FEATURES_OK Michael S. Tsirkin
` (5 subsequent siblings)
7 siblings, 1 reply; 26+ messages in thread
From: Michael S. Tsirkin @ 2014-11-30 15:09 UTC (permalink / raw)
To: linux-kernel
Cc: Bjarke Istrup Pedersen, thuth, Anup Patel, rusty,
Greg Kroah-Hartman, David Drysdale, dahi, Ashwin Chaugule,
Sakari Ailus, linux-api, pbonzini, Andy Grover, virtualization,
David Miller, Alexei Starovoitov
virtio 1.0 makes all memory structures LE, so
we need APIs to conditionally do a byteswap on BE
architectures.
To make it easier to check code statically,
add virtio specific types for multi-byte integers
in memory.
Add low level wrappers that do a byteswap conditionally, these will be
useful e.g. for vhost. Add high level wrappers that
query device endian-ness and act accordingly.
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
---
include/linux/virtio_byteorder.h | 59 +++++++++++++++++++++++++++++++++++++++
include/linux/virtio_config.h | 32 +++++++++++++++++++++
include/uapi/linux/virtio_ring.h | 45 ++++++++++++++---------------
include/uapi/linux/virtio_types.h | 46 ++++++++++++++++++++++++++++++
include/uapi/linux/Kbuild | 1 +
5 files changed, 161 insertions(+), 22 deletions(-)
create mode 100644 include/linux/virtio_byteorder.h
create mode 100644 include/uapi/linux/virtio_types.h
diff --git a/include/linux/virtio_byteorder.h b/include/linux/virtio_byteorder.h
new file mode 100644
index 0000000..51865d0
--- /dev/null
+++ b/include/linux/virtio_byteorder.h
@@ -0,0 +1,59 @@
+#ifndef _LINUX_VIRTIO_BYTEORDER_H
+#define _LINUX_VIRTIO_BYTEORDER_H
+#include <linux/types.h>
+#include <uapi/linux/virtio_types.h>
+
+/*
+ * Low-level memory accessors for handling virtio in modern little endian and in
+ * compatibility native endian format.
+ */
+
+static inline u16 __virtio16_to_cpu(bool little_endian, __virtio16 val)
+{
+ if (little_endian)
+ return le16_to_cpu((__force __le16)val);
+ else
+ return (__force u16)val;
+}
+
+static inline __virtio16 __cpu_to_virtio16(bool little_endian, u16 val)
+{
+ if (little_endian)
+ return (__force __virtio16)cpu_to_le16(val);
+ else
+ return (__force __virtio16)val;
+}
+
+static inline u32 __virtio32_to_cpu(bool little_endian, __virtio32 val)
+{
+ if (little_endian)
+ return le32_to_cpu((__force __le32)val);
+ else
+ return (__force u32)val;
+}
+
+static inline __virtio32 __cpu_to_virtio32(bool little_endian, u32 val)
+{
+ if (little_endian)
+ return (__force __virtio32)cpu_to_le32(val);
+ else
+ return (__force __virtio32)val;
+}
+
+static inline u64 __virtio64_to_cpu(bool little_endian, __virtio64 val)
+{
+ if (little_endian)
+ return le64_to_cpu((__force __le64)val);
+ else
+ return (__force u64)val;
+}
+
+static inline __virtio64 __cpu_to_virtio64(bool little_endian, u64 val)
+{
+ if (little_endian)
+ return (__force __virtio64)cpu_to_le64(val);
+ else
+ return (__force __virtio64)val;
+}
+
+#endif /* _LINUX_VIRTIO_BYTEORDER */
diff --git a/include/linux/virtio_config.h b/include/linux/virtio_config.h
index f517884..02f0acb 100644
--- a/include/linux/virtio_config.h
+++ b/include/linux/virtio_config.h
@@ -4,6 +4,7 @@
#include <linux/err.h>
#include <linux/bug.h>
#include <linux/virtio.h>
+#include <linux/virtio_byteorder.h>
#include <uapi/linux/virtio_config.h>
/**
@@ -199,6 +200,37 @@ int virtqueue_set_affinity(struct virtqueue *vq, int cpu)
return 0;
}
+/* Memory accessors */
+static inline u16 virtio16_to_cpu(struct virtio_device *vdev, __virtio16 val)
+{
+ return __virtio16_to_cpu(virtio_has_feature(vdev, VIRTIO_F_VERSION_1), val);
+}
+
+static inline __virtio16 cpu_to_virtio16(struct virtio_device *vdev, u16 val)
+{
+ return __cpu_to_virtio16(virtio_has_feature(vdev, VIRTIO_F_VERSION_1), val);
+}
+
+static inline u32 virtio32_to_cpu(struct virtio_device *vdev, __virtio32 val)
+{
+ return __virtio32_to_cpu(virtio_has_feature(vdev, VIRTIO_F_VERSION_1), val);
+}
+
+static inline __virtio32 cpu_to_virtio32(struct virtio_device *vdev, u32 val)
+{
+ return __cpu_to_virtio32(virtio_has_feature(vdev, VIRTIO_F_VERSION_1), val);
+}
+
+static inline u64 virtio64_to_cpu(struct virtio_device *vdev, __virtio64 val)
+{
+ return __virtio64_to_cpu(virtio_has_feature(vdev, VIRTIO_F_VERSION_1), val);
+}
+
+static inline __virtio64 cpu_to_virtio64(struct virtio_device *vdev, u64 val)
+{
+ return __cpu_to_virtio64(virtio_has_feature(vdev, VIRTIO_F_VERSION_1), val);
+}
+
/* Config space accessors. */
#define virtio_cread(vdev, structname, member, ptr) \
do { \
diff --git a/include/uapi/linux/virtio_ring.h b/include/uapi/linux/virtio_ring.h
index a99f9b7..61c818a 100644
--- a/include/uapi/linux/virtio_ring.h
+++ b/include/uapi/linux/virtio_ring.h
@@ -32,6 +32,7 @@
*
* Copyright Rusty Russell IBM Corporation 2007. */
#include <linux/types.h>
+#include <linux/virtio_types.h>
/* This marks a buffer as continuing via the next field. */
#define VRING_DESC_F_NEXT 1
@@ -61,32 +62,32 @@
/* Virtio ring descriptors: 16 bytes. These can chain together via "next". */
struct vring_desc {
/* Address (guest-physical). */
- __u64 addr;
+ __virtio64 addr;
/* Length. */
- __u32 len;
+ __virtio32 len;
/* The flags as indicated above. */
- __u16 flags;
+ __virtio16 flags;
/* We chain unused descriptors via this, too */
- __u16 next;
+ __virtio16 next;
};
struct vring_avail {
- __u16 flags;
- __u16 idx;
- __u16 ring[];
+ __virtio16 flags;
+ __virtio16 idx;
+ __virtio16 ring[];
};
/* u32 is used here for ids for padding reasons. */
struct vring_used_elem {
/* Index of start of used descriptor chain. */
- __u32 id;
+ __virtio32 id;
/* Total length of the descriptor chain which was used (written to) */
- __u32 len;
+ __virtio32 len;
};
struct vring_used {
- __u16 flags;
- __u16 idx;
+ __virtio16 flags;
+ __virtio16 idx;
struct vring_used_elem ring[];
};
@@ -109,25 +110,25 @@ struct vring {
* struct vring_desc desc[num];
*
* // A ring of available descriptor heads with free-running index.
- * __u16 avail_flags;
- * __u16 avail_idx;
- * __u16 available[num];
- * __u16 used_event_idx;
+ * __virtio16 avail_flags;
+ * __virtio16 avail_idx;
+ * __virtio16 available[num];
+ * __virtio16 used_event_idx;
*
* // Padding to the next align boundary.
* char pad[];
*
* // A ring of used descriptor heads with free-running index.
- * __u16 used_flags;
- * __u16 used_idx;
+ * __virtio16 used_flags;
+ * __virtio16 used_idx;
* struct vring_used_elem used[num];
- * __u16 avail_event_idx;
+ * __virtio16 avail_event_idx;
* };
*/
/* We publish the used event index at the end of the available ring, and vice
* versa. They are at the end for backwards compatibility. */
#define vring_used_event(vr) ((vr)->avail->ring[(vr)->num])
-#define vring_avail_event(vr) (*(__u16 *)&(vr)->used->ring[(vr)->num])
+#define vring_avail_event(vr) (*(__virtio16 *)&(vr)->used->ring[(vr)->num])
static inline void vring_init(struct vring *vr, unsigned int num, void *p,
unsigned long align)
@@ -135,15 +136,15 @@ static inline void vring_init(struct vring *vr, unsigned int num, void *p,
vr->num = num;
vr->desc = p;
vr->avail = p + num*sizeof(struct vring_desc);
- vr->used = (void *)(((unsigned long)&vr->avail->ring[num] + sizeof(__u16)
+ vr->used = (void *)(((unsigned long)&vr->avail->ring[num] + sizeof(__virtio16)
+ align-1) & ~(align - 1));
}
static inline unsigned vring_size(unsigned int num, unsigned long align)
{
- return ((sizeof(struct vring_desc) * num + sizeof(__u16) * (3 + num)
+ return ((sizeof(struct vring_desc) * num + sizeof(__virtio16) * (3 + num)
+ align - 1) & ~(align - 1))
- + sizeof(__u16) * 3 + sizeof(struct vring_used_elem) * num;
+ + sizeof(__virtio16) * 3 + sizeof(struct vring_used_elem) * num;
}
/* The following is used with USED_EVENT_IDX and AVAIL_EVENT_IDX */
diff --git a/include/uapi/linux/virtio_types.h b/include/uapi/linux/virtio_types.h
new file mode 100644
index 0000000..e845e8c
--- /dev/null
+++ b/include/uapi/linux/virtio_types.h
@@ -0,0 +1,46 @@
+#ifndef _UAPI_LINUX_VIRTIO_TYPES_H
+#define _UAPI_LINUX_VIRTIO_TYPES_H
+/* Type definitions for virtio implementations.
+ *
+ * This header is BSD licensed so anyone can use the definitions to implement
+ * compatible drivers/servers.
+ *
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted provided that the following conditions
+ * are met:
+ * 1. Redistributions of source code must retain the above copyright
+ * notice, this list of conditions and the following disclaimer.
+ * 2. Redistributions in binary form must reproduce the above copyright
+ * notice, this list of conditions and the following disclaimer in the
+ * documentation and/or other materials provided with the distribution.
+ * 3. Neither the name of IBM nor the names of its contributors
+ * may be used to endorse or promote products derived from this software
+ * without specific prior written permission.
+ * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS ``AS IS'' AND
+ * ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
+ * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
+ * ARE DISCLAIMED. IN NO EVENT SHALL IBM OR CONTRIBUTORS BE LIABLE
+ * FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
+ * DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS
+ * OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION)
+ * HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT
+ * LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY
+ * OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF
+ * SUCH DAMAGE.
+ *
+ * Copyright (C) 2014 Red Hat, Inc.
+ * Author: Michael S. Tsirkin <mst@redhat.com>
+ */
+#include <linux/types.h>
+
+/*
+ * __virtio{16,32,64} have the following meaning:
+ * - __u{16,32,64} for virtio devices in legacy mode, accessed in native endian
+ * - __le{16,32,64} for standard-compliant virtio devices
+ */
+
+typedef __u16 __bitwise__ __virtio16;
+typedef __u32 __bitwise__ __virtio32;
+typedef __u64 __bitwise__ __virtio64;
+
+#endif /* _UAPI_LINUX_VIRTIO_TYPES_H */
diff --git a/include/uapi/linux/Kbuild b/include/uapi/linux/Kbuild
index 4c94f31..44a5581 100644
--- a/include/uapi/linux/Kbuild
+++ b/include/uapi/linux/Kbuild
@@ -423,6 +423,7 @@ header-y += virtio_blk.h
header-y += virtio_config.h
header-y += virtio_console.h
header-y += virtio_ids.h
+header-y += virtio_types.h
header-y += virtio_net.h
header-y += virtio_pci.h
header-y += virtio_ring.h
--
MST
^ permalink raw reply related [flat|nested] 26+ messages in thread* Re: [PATCH v7 08/46] virtio: memory access APIs
2014-11-30 15:09 ` [PATCH v7 08/46] virtio: memory access APIs Michael S. Tsirkin
@ 2014-12-01 9:56 ` Cornelia Huck
0 siblings, 0 replies; 26+ messages in thread
From: Cornelia Huck @ 2014-12-01 9:56 UTC (permalink / raw)
To: Michael S. Tsirkin
Cc: Bjarke Istrup Pedersen, thuth, Anup Patel, rusty,
Greg Kroah-Hartman, linux-kernel, David Drysdale, dahi,
Ashwin Chaugule, Sakari Ailus, linux-api, pbonzini, Andy Grover,
virtualization, David Miller, Alexei Starovoitov
On Sun, 30 Nov 2014 17:09:50 +0200
"Michael S. Tsirkin" <mst@redhat.com> wrote:
> virtio 1.0 makes all memory structures LE, so
> we need APIs to conditionally do a byteswap on BE
> architectures.
>
> To make it easier to check code statically,
> add virtio specific types for multi-byte integers
> in memory.
>
> Add low level wrappers that do a byteswap conditionally, these will be
> useful e.g. for vhost. Add high level wrappers that
> query device endian-ness and act accordingly.
>
> Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
> ---
> include/linux/virtio_byteorder.h | 59 +++++++++++++++++++++++++++++++++++++++
> include/linux/virtio_config.h | 32 +++++++++++++++++++++
> include/uapi/linux/virtio_ring.h | 45 ++++++++++++++---------------
> include/uapi/linux/virtio_types.h | 46 ++++++++++++++++++++++++++++++
> include/uapi/linux/Kbuild | 1 +
> 5 files changed, 161 insertions(+), 22 deletions(-)
> create mode 100644 include/linux/virtio_byteorder.h
> create mode 100644 include/uapi/linux/virtio_types.h
Reviewed-by: Cornelia Huck <cornelia.huck@de.ibm.com>
^ permalink raw reply [flat|nested] 26+ messages in thread
* [PATCH v7 12/46] virtio: set FEATURES_OK
[not found] <1417359787-10138-1-git-send-email-mst@redhat.com>
2014-11-30 15:09 ` [PATCH v7 07/46] virtio: add virtio 1.0 feature bit Michael S. Tsirkin
2014-11-30 15:09 ` [PATCH v7 08/46] virtio: memory access APIs Michael S. Tsirkin
@ 2014-11-30 15:10 ` Michael S. Tsirkin
[not found] ` <1417359787-10138-13-git-send-email-mst-H+wXaHxf7aLQT0dZR+AlfA@public.gmane.org>
2014-11-30 15:10 ` [PATCH v7 15/46] virtio_net: v1.0 endianness Michael S. Tsirkin
` (4 subsequent siblings)
7 siblings, 1 reply; 26+ messages in thread
From: Michael S. Tsirkin @ 2014-11-30 15:10 UTC (permalink / raw)
To: linux-kernel
Cc: thuth, rusty, linux-api, virtualization, dahi, pbonzini,
David Miller
set FEATURES_OK as per virtio 1.0 spec
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
---
include/uapi/linux/virtio_config.h | 2 ++
drivers/virtio/virtio.c | 29 ++++++++++++++++++++++-------
2 files changed, 24 insertions(+), 7 deletions(-)
diff --git a/include/uapi/linux/virtio_config.h b/include/uapi/linux/virtio_config.h
index 80e7381..4d05671 100644
--- a/include/uapi/linux/virtio_config.h
+++ b/include/uapi/linux/virtio_config.h
@@ -38,6 +38,8 @@
#define VIRTIO_CONFIG_S_DRIVER 2
/* Driver has used its parts of the config, and is happy */
#define VIRTIO_CONFIG_S_DRIVER_OK 4
+/* Driver has finished configuring features */
+#define VIRTIO_CONFIG_S_FEATURES_OK 8
/* We've given up on this device. */
#define VIRTIO_CONFIG_S_FAILED 0x80
diff --git a/drivers/virtio/virtio.c b/drivers/virtio/virtio.c
index 746d350..9248125 100644
--- a/drivers/virtio/virtio.c
+++ b/drivers/virtio/virtio.c
@@ -160,6 +160,7 @@ static int virtio_dev_probe(struct device *_d)
struct virtio_device *dev = dev_to_virtio(_d);
struct virtio_driver *drv = drv_to_virtio(dev->dev.driver);
u64 device_features;
+ unsigned status;
/* We have a driver! */
add_status(dev, VIRTIO_CONFIG_S_DRIVER);
@@ -183,18 +184,32 @@ static int virtio_dev_probe(struct device *_d)
dev->config->finalize_features(dev);
+ if (virtio_has_feature(dev, VIRTIO_F_VERSION_1)) {
+ add_status(dev, VIRTIO_CONFIG_S_FEATURES_OK);
+ status = dev->config->get_status(dev);
+ if (!(status & VIRTIO_CONFIG_S_FEATURES_OK)) {
+ dev_err(_d, "virtio: device refuses features: %x\n",
+ status);
+ err = -ENODEV;
+ goto err;
+ }
+ }
+
err = drv->probe(dev);
if (err)
- add_status(dev, VIRTIO_CONFIG_S_FAILED);
- else {
- add_status(dev, VIRTIO_CONFIG_S_DRIVER_OK);
- if (drv->scan)
- drv->scan(dev);
+ goto err;
- virtio_config_enable(dev);
- }
+ add_status(dev, VIRTIO_CONFIG_S_DRIVER_OK);
+ if (drv->scan)
+ drv->scan(dev);
+
+ virtio_config_enable(dev);
+ return 0;
+err:
+ add_status(dev, VIRTIO_CONFIG_S_FAILED);
return err;
+
}
static int virtio_dev_remove(struct device *_d)
--
MST
^ permalink raw reply related [flat|nested] 26+ messages in thread* [PATCH v7 15/46] virtio_net: v1.0 endianness
[not found] <1417359787-10138-1-git-send-email-mst@redhat.com>
` (2 preceding siblings ...)
2014-11-30 15:10 ` [PATCH v7 12/46] virtio: set FEATURES_OK Michael S. Tsirkin
@ 2014-11-30 15:10 ` Michael S. Tsirkin
2014-11-30 15:10 ` [PATCH v7 16/46] virtio_blk: v1.0 support Michael S. Tsirkin
` (3 subsequent siblings)
7 siblings, 0 replies; 26+ messages in thread
From: Michael S. Tsirkin @ 2014-11-30 15:10 UTC (permalink / raw)
To: linux-kernel
Cc: David Miller, cornelia.huck, rusty, nab, pbonzini, thuth, dahi,
Rusty Russell, virtualization, netdev, linux-api
Based on patches by Rusty Russell, Cornelia Huck.
Note: more code changes are needed for 1.0 support
(due to different header size).
So we don't advertize support for 1.0 yet.
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>
---
include/uapi/linux/virtio_net.h | 15 ++++++++-------
drivers/net/virtio_net.c | 33 ++++++++++++++++++++-------------
2 files changed, 28 insertions(+), 20 deletions(-)
diff --git a/include/uapi/linux/virtio_net.h b/include/uapi/linux/virtio_net.h
index 172a7f0..b5f1677 100644
--- a/include/uapi/linux/virtio_net.h
+++ b/include/uapi/linux/virtio_net.h
@@ -28,6 +28,7 @@
#include <linux/types.h>
#include <linux/virtio_ids.h>
#include <linux/virtio_config.h>
+#include <linux/virtio_types.h>
#include <linux/if_ether.h>
/* The feature bitmap for virtio net */
@@ -84,17 +85,17 @@ struct virtio_net_hdr {
#define VIRTIO_NET_HDR_GSO_TCPV6 4 // GSO frame, IPv6 TCP
#define VIRTIO_NET_HDR_GSO_ECN 0x80 // TCP has ECN set
__u8 gso_type;
- __u16 hdr_len; /* Ethernet + IP + tcp/udp hdrs */
- __u16 gso_size; /* Bytes to append to hdr_len per frame */
- __u16 csum_start; /* Position to start checksumming from */
- __u16 csum_offset; /* Offset after that to place checksum */
+ __virtio16 hdr_len; /* Ethernet + IP + tcp/udp hdrs */
+ __virtio16 gso_size; /* Bytes to append to hdr_len per frame */
+ __virtio16 csum_start; /* Position to start checksumming from */
+ __virtio16 csum_offset; /* Offset after that to place checksum */
};
/* This is the version of the header to use when the MRG_RXBUF
* feature has been negotiated. */
struct virtio_net_hdr_mrg_rxbuf {
struct virtio_net_hdr hdr;
- __u16 num_buffers; /* Number of merged rx buffers */
+ __virtio16 num_buffers; /* Number of merged rx buffers */
};
/*
@@ -149,7 +150,7 @@ typedef __u8 virtio_net_ctrl_ack;
* VIRTIO_NET_F_CTRL_MAC_ADDR feature is available.
*/
struct virtio_net_ctrl_mac {
- __u32 entries;
+ __virtio32 entries;
__u8 macs[][ETH_ALEN];
} __attribute__((packed));
@@ -193,7 +194,7 @@ struct virtio_net_ctrl_mac {
* specified.
*/
struct virtio_net_ctrl_mq {
- __u16 virtqueue_pairs;
+ __virtio16 virtqueue_pairs;
};
#define VIRTIO_NET_CTRL_MQ 4
diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c
index b0bc8ea..c07e030 100644
--- a/drivers/net/virtio_net.c
+++ b/drivers/net/virtio_net.c
@@ -347,13 +347,14 @@ err:
}
static struct sk_buff *receive_mergeable(struct net_device *dev,
+ struct virtnet_info *vi,
struct receive_queue *rq,
unsigned long ctx,
unsigned int len)
{
void *buf = mergeable_ctx_to_buf_address(ctx);
struct skb_vnet_hdr *hdr = buf;
- int num_buf = hdr->mhdr.num_buffers;
+ u16 num_buf = virtio16_to_cpu(rq->vq->vdev, hdr->mhdr.num_buffers);
struct page *page = virt_to_head_page(buf);
int offset = buf - page_address(page);
unsigned int truesize = max(len, mergeable_ctx_to_buf_truesize(ctx));
@@ -369,7 +370,9 @@ static struct sk_buff *receive_mergeable(struct net_device *dev,
ctx = (unsigned long)virtqueue_get_buf(rq->vq, &len);
if (unlikely(!ctx)) {
pr_debug("%s: rx error: %d buffers out of %d missing\n",
- dev->name, num_buf, hdr->mhdr.num_buffers);
+ dev->name, num_buf,
+ virtio16_to_cpu(rq->vq->vdev,
+ hdr->mhdr.num_buffers));
dev->stats.rx_length_errors++;
goto err_buf;
}
@@ -454,7 +457,7 @@ static void receive_buf(struct receive_queue *rq, void *buf, unsigned int len)
}
if (vi->mergeable_rx_bufs)
- skb = receive_mergeable(dev, rq, (unsigned long)buf, len);
+ skb = receive_mergeable(dev, vi, rq, (unsigned long)buf, len);
else if (vi->big_packets)
skb = receive_big(dev, rq, buf, len);
else
@@ -473,8 +476,8 @@ static void receive_buf(struct receive_queue *rq, void *buf, unsigned int len)
if (hdr->hdr.flags & VIRTIO_NET_HDR_F_NEEDS_CSUM) {
pr_debug("Needs csum!\n");
if (!skb_partial_csum_set(skb,
- hdr->hdr.csum_start,
- hdr->hdr.csum_offset))
+ virtio16_to_cpu(vi->vdev, hdr->hdr.csum_start),
+ virtio16_to_cpu(vi->vdev, hdr->hdr.csum_offset)))
goto frame_err;
} else if (hdr->hdr.flags & VIRTIO_NET_HDR_F_DATA_VALID) {
skb->ip_summed = CHECKSUM_UNNECESSARY;
@@ -514,7 +517,8 @@ static void receive_buf(struct receive_queue *rq, void *buf, unsigned int len)
if (hdr->hdr.gso_type & VIRTIO_NET_HDR_GSO_ECN)
skb_shinfo(skb)->gso_type |= SKB_GSO_TCP_ECN;
- skb_shinfo(skb)->gso_size = hdr->hdr.gso_size;
+ skb_shinfo(skb)->gso_size = virtio16_to_cpu(vi->vdev,
+ hdr->hdr.gso_size);
if (skb_shinfo(skb)->gso_size == 0) {
net_warn_ratelimited("%s: zero gso size.\n", dev->name);
goto frame_err;
@@ -876,16 +880,19 @@ static int xmit_skb(struct send_queue *sq, struct sk_buff *skb)
if (skb->ip_summed == CHECKSUM_PARTIAL) {
hdr->hdr.flags = VIRTIO_NET_HDR_F_NEEDS_CSUM;
- hdr->hdr.csum_start = skb_checksum_start_offset(skb);
- hdr->hdr.csum_offset = skb->csum_offset;
+ hdr->hdr.csum_start = cpu_to_virtio16(vi->vdev,
+ skb_checksum_start_offset(skb));
+ hdr->hdr.csum_offset = cpu_to_virtio16(vi->vdev,
+ skb->csum_offset);
} else {
hdr->hdr.flags = 0;
hdr->hdr.csum_offset = hdr->hdr.csum_start = 0;
}
if (skb_is_gso(skb)) {
- hdr->hdr.hdr_len = skb_headlen(skb);
- hdr->hdr.gso_size = skb_shinfo(skb)->gso_size;
+ hdr->hdr.hdr_len = cpu_to_virtio16(vi->vdev, skb_headlen(skb));
+ hdr->hdr.gso_size = cpu_to_virtio16(vi->vdev,
+ skb_shinfo(skb)->gso_size);
if (skb_shinfo(skb)->gso_type & SKB_GSO_TCPV4)
hdr->hdr.gso_type = VIRTIO_NET_HDR_GSO_TCPV4;
else if (skb_shinfo(skb)->gso_type & SKB_GSO_TCPV6)
@@ -1112,7 +1119,7 @@ static int virtnet_set_queues(struct virtnet_info *vi, u16 queue_pairs)
if (!vi->has_cvq || !virtio_has_feature(vi->vdev, VIRTIO_NET_F_MQ))
return 0;
- s.virtqueue_pairs = queue_pairs;
+ s.virtqueue_pairs = cpu_to_virtio16(vi->vdev, queue_pairs);
sg_init_one(&sg, &s, sizeof(s));
if (!virtnet_send_command(vi, VIRTIO_NET_CTRL_MQ,
@@ -1189,7 +1196,7 @@ static void virtnet_set_rx_mode(struct net_device *dev)
sg_init_table(sg, 2);
/* Store the unicast list and count in the front of the buffer */
- mac_data->entries = uc_count;
+ mac_data->entries = cpu_to_virtio32(vi->vdev, uc_count);
i = 0;
netdev_for_each_uc_addr(ha, dev)
memcpy(&mac_data->macs[i++][0], ha->addr, ETH_ALEN);
@@ -1200,7 +1207,7 @@ static void virtnet_set_rx_mode(struct net_device *dev)
/* multicast list and count fill the end */
mac_data = (void *)&mac_data->macs[uc_count][0];
- mac_data->entries = mc_count;
+ mac_data->entries = cpu_to_virtio32(vi->vdev, mc_count);
i = 0;
netdev_for_each_mc_addr(ha, dev)
memcpy(&mac_data->macs[i++][0], ha->addr, ETH_ALEN);
--
MST
^ permalink raw reply related [flat|nested] 26+ messages in thread* [PATCH v7 16/46] virtio_blk: v1.0 support
[not found] <1417359787-10138-1-git-send-email-mst@redhat.com>
` (3 preceding siblings ...)
2014-11-30 15:10 ` [PATCH v7 15/46] virtio_net: v1.0 endianness Michael S. Tsirkin
@ 2014-11-30 15:10 ` Michael S. Tsirkin
2014-12-01 8:16 ` David Hildenbrand
2014-11-30 15:12 ` [PATCH v7 37/46] tun: move internal flag defines out of uapi Michael S. Tsirkin
` (2 subsequent siblings)
7 siblings, 1 reply; 26+ messages in thread
From: Michael S. Tsirkin @ 2014-11-30 15:10 UTC (permalink / raw)
To: linux-kernel
Cc: thuth, rusty, linux-api, virtualization, dahi, pbonzini,
David Miller
Based on patch by Cornelia Huck.
Note: for consistency, and to avoid sparse errors,
convert all fields, even those no longer in use
for virtio v1.0.
Signed-off-by: Cornelia Huck <cornelia.huck@de.ibm.com>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
---
include/uapi/linux/virtio_blk.h | 15 ++++-----
drivers/block/virtio_blk.c | 70 ++++++++++++++++++++++++-----------------
2 files changed, 49 insertions(+), 36 deletions(-)
diff --git a/include/uapi/linux/virtio_blk.h b/include/uapi/linux/virtio_blk.h
index 9ad67b2..247c8ba 100644
--- a/include/uapi/linux/virtio_blk.h
+++ b/include/uapi/linux/virtio_blk.h
@@ -28,6 +28,7 @@
#include <linux/types.h>
#include <linux/virtio_ids.h>
#include <linux/virtio_config.h>
+#include <linux/virtio_types.h>
/* Feature bits */
#define VIRTIO_BLK_F_BARRIER 0 /* Does host support barriers? */
@@ -114,18 +115,18 @@ struct virtio_blk_config {
/* This is the first element of the read scatter-gather list. */
struct virtio_blk_outhdr {
/* VIRTIO_BLK_T* */
- __u32 type;
+ __virtio32 type;
/* io priority. */
- __u32 ioprio;
+ __virtio32 ioprio;
/* Sector (ie. 512 byte offset) */
- __u64 sector;
+ __virtio64 sector;
};
struct virtio_scsi_inhdr {
- __u32 errors;
- __u32 data_len;
- __u32 sense_len;
- __u32 residual;
+ __virtio32 errors;
+ __virtio32 data_len;
+ __virtio32 sense_len;
+ __virtio32 residual;
};
/* And this is the final byte of the write scatter-gather list. */
diff --git a/drivers/block/virtio_blk.c b/drivers/block/virtio_blk.c
index c6a27d5..f601f16 100644
--- a/drivers/block/virtio_blk.c
+++ b/drivers/block/virtio_blk.c
@@ -80,7 +80,7 @@ static int __virtblk_add_req(struct virtqueue *vq,
{
struct scatterlist hdr, status, cmd, sense, inhdr, *sgs[6];
unsigned int num_out = 0, num_in = 0;
- int type = vbr->out_hdr.type & ~VIRTIO_BLK_T_OUT;
+ __virtio32 type = vbr->out_hdr.type & ~cpu_to_virtio32(vq->vdev, VIRTIO_BLK_T_OUT);
sg_init_one(&hdr, &vbr->out_hdr, sizeof(vbr->out_hdr));
sgs[num_out++] = &hdr;
@@ -91,19 +91,19 @@ static int __virtblk_add_req(struct virtqueue *vq,
* block, and before the normal inhdr we put the sense data and the
* inhdr with additional status information.
*/
- if (type == VIRTIO_BLK_T_SCSI_CMD) {
+ if (type == cpu_to_virtio32(vq->vdev, VIRTIO_BLK_T_SCSI_CMD)) {
sg_init_one(&cmd, vbr->req->cmd, vbr->req->cmd_len);
sgs[num_out++] = &cmd;
}
if (have_data) {
- if (vbr->out_hdr.type & VIRTIO_BLK_T_OUT)
+ if (vbr->out_hdr.type & cpu_to_virtio32(vq->vdev, VIRTIO_BLK_T_OUT))
sgs[num_out++] = data_sg;
else
sgs[num_out + num_in++] = data_sg;
}
- if (type == VIRTIO_BLK_T_SCSI_CMD) {
+ if (type == cpu_to_virtio32(vq->vdev, VIRTIO_BLK_T_SCSI_CMD)) {
sg_init_one(&sense, vbr->req->sense, SCSI_SENSE_BUFFERSIZE);
sgs[num_out + num_in++] = &sense;
sg_init_one(&inhdr, &vbr->in_hdr, sizeof(vbr->in_hdr));
@@ -119,12 +119,13 @@ static int __virtblk_add_req(struct virtqueue *vq,
static inline void virtblk_request_done(struct request *req)
{
struct virtblk_req *vbr = blk_mq_rq_to_pdu(req);
+ struct virtio_blk *vblk = req->q->queuedata;
int error = virtblk_result(vbr);
if (req->cmd_type == REQ_TYPE_BLOCK_PC) {
- req->resid_len = vbr->in_hdr.residual;
- req->sense_len = vbr->in_hdr.sense_len;
- req->errors = vbr->in_hdr.errors;
+ req->resid_len = virtio32_to_cpu(vblk->vdev, vbr->in_hdr.residual);
+ req->sense_len = virtio32_to_cpu(vblk->vdev, vbr->in_hdr.sense_len);
+ req->errors = virtio32_to_cpu(vblk->vdev, vbr->in_hdr.errors);
} else if (req->cmd_type == REQ_TYPE_SPECIAL) {
req->errors = (error != 0);
}
@@ -173,25 +174,25 @@ static int virtio_queue_rq(struct blk_mq_hw_ctx *hctx, struct request *req,
vbr->req = req;
if (req->cmd_flags & REQ_FLUSH) {
- vbr->out_hdr.type = VIRTIO_BLK_T_FLUSH;
+ vbr->out_hdr.type = cpu_to_virtio32(vblk->vdev, VIRTIO_BLK_T_FLUSH);
vbr->out_hdr.sector = 0;
- vbr->out_hdr.ioprio = req_get_ioprio(vbr->req);
+ vbr->out_hdr.ioprio = cpu_to_virtio32(vblk->vdev, req_get_ioprio(vbr->req));
} else {
switch (req->cmd_type) {
case REQ_TYPE_FS:
vbr->out_hdr.type = 0;
- vbr->out_hdr.sector = blk_rq_pos(vbr->req);
- vbr->out_hdr.ioprio = req_get_ioprio(vbr->req);
+ vbr->out_hdr.sector = cpu_to_virtio64(vblk->vdev, blk_rq_pos(vbr->req));
+ vbr->out_hdr.ioprio = cpu_to_virtio32(vblk->vdev, req_get_ioprio(vbr->req));
break;
case REQ_TYPE_BLOCK_PC:
- vbr->out_hdr.type = VIRTIO_BLK_T_SCSI_CMD;
+ vbr->out_hdr.type = cpu_to_virtio32(vblk->vdev, VIRTIO_BLK_T_SCSI_CMD);
vbr->out_hdr.sector = 0;
- vbr->out_hdr.ioprio = req_get_ioprio(vbr->req);
+ vbr->out_hdr.ioprio = cpu_to_virtio32(vblk->vdev, req_get_ioprio(vbr->req));
break;
case REQ_TYPE_SPECIAL:
- vbr->out_hdr.type = VIRTIO_BLK_T_GET_ID;
+ vbr->out_hdr.type = cpu_to_virtio32(vblk->vdev, VIRTIO_BLK_T_GET_ID);
vbr->out_hdr.sector = 0;
- vbr->out_hdr.ioprio = req_get_ioprio(vbr->req);
+ vbr->out_hdr.ioprio = cpu_to_virtio32(vblk->vdev, req_get_ioprio(vbr->req));
break;
default:
/* We don't put anything else in the queue. */
@@ -204,9 +205,9 @@ static int virtio_queue_rq(struct blk_mq_hw_ctx *hctx, struct request *req,
num = blk_rq_map_sg(hctx->queue, vbr->req, vbr->sg);
if (num) {
if (rq_data_dir(vbr->req) == WRITE)
- vbr->out_hdr.type |= VIRTIO_BLK_T_OUT;
+ vbr->out_hdr.type |= cpu_to_virtio32(vblk->vdev, VIRTIO_BLK_T_OUT);
else
- vbr->out_hdr.type |= VIRTIO_BLK_T_IN;
+ vbr->out_hdr.type |= cpu_to_virtio32(vblk->vdev, VIRTIO_BLK_T_IN);
}
spin_lock_irqsave(&vblk->vqs[qid].lock, flags);
@@ -476,7 +477,8 @@ static int virtblk_get_cache_mode(struct virtio_device *vdev)
struct virtio_blk_config, wce,
&writeback);
if (err)
- writeback = virtio_has_feature(vdev, VIRTIO_BLK_F_WCE);
+ writeback = virtio_has_feature(vdev, VIRTIO_BLK_F_WCE) ||
+ virtio_has_feature(vdev, VIRTIO_F_VERSION_1);
return writeback;
}
@@ -821,25 +823,35 @@ static const struct virtio_device_id id_table[] = {
{ 0 },
};
-static unsigned int features[] = {
+static unsigned int features_legacy[] = {
VIRTIO_BLK_F_SEG_MAX, VIRTIO_BLK_F_SIZE_MAX, VIRTIO_BLK_F_GEOMETRY,
VIRTIO_BLK_F_RO, VIRTIO_BLK_F_BLK_SIZE, VIRTIO_BLK_F_SCSI,
VIRTIO_BLK_F_WCE, VIRTIO_BLK_F_TOPOLOGY, VIRTIO_BLK_F_CONFIG_WCE,
VIRTIO_BLK_F_MQ,
+}
+;
+static unsigned int features[] = {
+ VIRTIO_BLK_F_SEG_MAX, VIRTIO_BLK_F_SIZE_MAX, VIRTIO_BLK_F_GEOMETRY,
+ VIRTIO_BLK_F_RO, VIRTIO_BLK_F_BLK_SIZE,
+ VIRTIO_BLK_F_TOPOLOGY,
+ VIRTIO_BLK_F_MQ,
+ VIRTIO_F_VERSION_1,
};
static struct virtio_driver virtio_blk = {
- .feature_table = features,
- .feature_table_size = ARRAY_SIZE(features),
- .driver.name = KBUILD_MODNAME,
- .driver.owner = THIS_MODULE,
- .id_table = id_table,
- .probe = virtblk_probe,
- .remove = virtblk_remove,
- .config_changed = virtblk_config_changed,
+ .feature_table = features,
+ .feature_table_size = ARRAY_SIZE(features),
+ .feature_table_legacy = features_legacy,
+ .feature_table_size_legacy = ARRAY_SIZE(features_legacy),
+ .driver.name = KBUILD_MODNAME,
+ .driver.owner = THIS_MODULE,
+ .id_table = id_table,
+ .probe = virtblk_probe,
+ .remove = virtblk_remove,
+ .config_changed = virtblk_config_changed,
#ifdef CONFIG_PM_SLEEP
- .freeze = virtblk_freeze,
- .restore = virtblk_restore,
+ .freeze = virtblk_freeze,
+ .restore = virtblk_restore,
#endif
};
--
MST
^ permalink raw reply related [flat|nested] 26+ messages in thread* Re: [PATCH v7 16/46] virtio_blk: v1.0 support
2014-11-30 15:10 ` [PATCH v7 16/46] virtio_blk: v1.0 support Michael S. Tsirkin
@ 2014-12-01 8:16 ` David Hildenbrand
2014-12-01 9:26 ` Michael S. Tsirkin
2014-12-01 9:28 ` Michael S. Tsirkin
0 siblings, 2 replies; 26+ messages in thread
From: David Hildenbrand @ 2014-12-01 8:16 UTC (permalink / raw)
To: Michael S. Tsirkin
Cc: thuth, rusty, linux-api, linux-kernel, virtualization, pbonzini,
David Miller
> Based on patch by Cornelia Huck.
>
> Note: for consistency, and to avoid sparse errors,
> convert all fields, even those no longer in use
> for virtio v1.0.
>
> Signed-off-by: Cornelia Huck <cornelia.huck@de.ibm.com>
> Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
...
>
> -static unsigned int features[] = {
> +static unsigned int features_legacy[] = {
> VIRTIO_BLK_F_SEG_MAX, VIRTIO_BLK_F_SIZE_MAX, VIRTIO_BLK_F_GEOMETRY,
> VIRTIO_BLK_F_RO, VIRTIO_BLK_F_BLK_SIZE, VIRTIO_BLK_F_SCSI,
> VIRTIO_BLK_F_WCE, VIRTIO_BLK_F_TOPOLOGY, VIRTIO_BLK_F_CONFIG_WCE,
> VIRTIO_BLK_F_MQ,
> +}
> +;
> +static unsigned int features[] = {
> + VIRTIO_BLK_F_SEG_MAX, VIRTIO_BLK_F_SIZE_MAX, VIRTIO_BLK_F_GEOMETRY,
> + VIRTIO_BLK_F_RO, VIRTIO_BLK_F_BLK_SIZE,
> + VIRTIO_BLK_F_TOPOLOGY,
> + VIRTIO_BLK_F_MQ,
> + VIRTIO_F_VERSION_1,
We can fit this into less lines, like done for features_legacy.
I was asking myself if we could do the conversion of the statical values
somehow upfront, to reduce the patch size and avoid cpu_to_virtio.* at those
places.
Otherwise looks good to me.
^ permalink raw reply [flat|nested] 26+ messages in thread* Re: [PATCH v7 16/46] virtio_blk: v1.0 support
2014-12-01 8:16 ` David Hildenbrand
@ 2014-12-01 9:26 ` Michael S. Tsirkin
2014-12-01 11:33 ` Cornelia Huck
2014-12-01 9:28 ` Michael S. Tsirkin
1 sibling, 1 reply; 26+ messages in thread
From: Michael S. Tsirkin @ 2014-12-01 9:26 UTC (permalink / raw)
To: David Hildenbrand
Cc: thuth, rusty, linux-api, linux-kernel, virtualization, pbonzini,
David Miller
On Mon, Dec 01, 2014 at 09:16:41AM +0100, David Hildenbrand wrote:
> > Based on patch by Cornelia Huck.
> >
> > Note: for consistency, and to avoid sparse errors,
> > convert all fields, even those no longer in use
> > for virtio v1.0.
> >
> > Signed-off-by: Cornelia Huck <cornelia.huck@de.ibm.com>
> > Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
> ...
> >
> > -static unsigned int features[] = {
> > +static unsigned int features_legacy[] = {
> > VIRTIO_BLK_F_SEG_MAX, VIRTIO_BLK_F_SIZE_MAX, VIRTIO_BLK_F_GEOMETRY,
> > VIRTIO_BLK_F_RO, VIRTIO_BLK_F_BLK_SIZE, VIRTIO_BLK_F_SCSI,
> > VIRTIO_BLK_F_WCE, VIRTIO_BLK_F_TOPOLOGY, VIRTIO_BLK_F_CONFIG_WCE,
> > VIRTIO_BLK_F_MQ,
> > +}
> > +;
> > +static unsigned int features[] = {
> > + VIRTIO_BLK_F_SEG_MAX, VIRTIO_BLK_F_SIZE_MAX, VIRTIO_BLK_F_GEOMETRY,
> > + VIRTIO_BLK_F_RO, VIRTIO_BLK_F_BLK_SIZE,
> > + VIRTIO_BLK_F_TOPOLOGY,
> > + VIRTIO_BLK_F_MQ,
> > + VIRTIO_F_VERSION_1,
>
> We can fit this into less lines, like done for features_legacy.
>
> I was asking myself if we could do the conversion of the statical values
> somehow upfront, to reduce the patch size and avoid cpu_to_virtio.* at those
> places.
>
> Otherwise looks good to me.
>
I don't see how we can reduce the patch size.
For BE architectures it's dynamic, so at best the values
will become macros/incline functions taking a flag.
For some places on data path, it might be worth it
to cache the correct value e.g. as part of device
structure. This replaces a branch with a memory load,
so the gain would have to be measured, best done
separately?
--
MST
^ permalink raw reply [flat|nested] 26+ messages in thread* Re: [PATCH v7 16/46] virtio_blk: v1.0 support
2014-12-01 9:26 ` Michael S. Tsirkin
@ 2014-12-01 11:33 ` Cornelia Huck
2014-12-01 11:46 ` Michael S. Tsirkin
0 siblings, 1 reply; 26+ messages in thread
From: Cornelia Huck @ 2014-12-01 11:33 UTC (permalink / raw)
To: Michael S. Tsirkin
Cc: thuth, rusty, linux-api, linux-kernel, virtualization,
David Hildenbrand, pbonzini, David Miller
On Mon, 1 Dec 2014 11:26:58 +0200
"Michael S. Tsirkin" <mst@redhat.com> wrote:
> For some places on data path, it might be worth it
> to cache the correct value e.g. as part of device
> structure. This replaces a branch with a memory load,
> so the gain would have to be measured, best done
> separately?
I think we'll want to do some measuring once the basic structure is
in place anyway. We should make sure that e.g. s390 only takes minor
hit due to all that swapping that is needed for standard-compliant
devices. Caching the value might certainly help in some paths.
^ permalink raw reply [flat|nested] 26+ messages in thread
* Re: [PATCH v7 16/46] virtio_blk: v1.0 support
2014-12-01 11:33 ` Cornelia Huck
@ 2014-12-01 11:46 ` Michael S. Tsirkin
2014-12-01 12:02 ` Cornelia Huck
0 siblings, 1 reply; 26+ messages in thread
From: Michael S. Tsirkin @ 2014-12-01 11:46 UTC (permalink / raw)
To: Cornelia Huck
Cc: thuth, rusty, linux-api, linux-kernel, virtualization,
David Hildenbrand, pbonzini, David Miller
On Mon, Dec 01, 2014 at 12:33:15PM +0100, Cornelia Huck wrote:
> On Mon, 1 Dec 2014 11:26:58 +0200
> "Michael S. Tsirkin" <mst@redhat.com> wrote:
>
> > For some places on data path, it might be worth it
> > to cache the correct value e.g. as part of device
> > structure. This replaces a branch with a memory load,
> > so the gain would have to be measured, best done
> > separately?
>
> I think we'll want to do some measuring once the basic structure is
> in place anyway.
What's meant by in place here?
> We should make sure that e.g. s390 only takes minor
> hit due to all that swapping that is needed for standard-compliant
> devices. Caching the value might certainly help in some paths.
Well, this is queued in linux-next for 3.19, so
now's the time to do it :)
^ permalink raw reply [flat|nested] 26+ messages in thread
* Re: [PATCH v7 16/46] virtio_blk: v1.0 support
2014-12-01 11:46 ` Michael S. Tsirkin
@ 2014-12-01 12:02 ` Cornelia Huck
2014-12-01 12:19 ` Michael S. Tsirkin
2014-12-01 12:34 ` Michael S. Tsirkin
0 siblings, 2 replies; 26+ messages in thread
From: Cornelia Huck @ 2014-12-01 12:02 UTC (permalink / raw)
To: Michael S. Tsirkin
Cc: thuth, rusty, linux-api, linux-kernel, virtualization,
David Hildenbrand, pbonzini, David Miller
On Mon, 1 Dec 2014 13:46:45 +0200
"Michael S. Tsirkin" <mst@redhat.com> wrote:
> On Mon, Dec 01, 2014 at 12:33:15PM +0100, Cornelia Huck wrote:
> > On Mon, 1 Dec 2014 11:26:58 +0200
> > "Michael S. Tsirkin" <mst@redhat.com> wrote:
> >
> > > For some places on data path, it might be worth it
> > > to cache the correct value e.g. as part of device
> > > structure. This replaces a branch with a memory load,
> > > so the gain would have to be measured, best done
> > > separately?
> >
> > I think we'll want to do some measuring once the basic structure is
> > in place anyway.
>
> What's meant by in place here?
That this patchset is ready :)
>
> > We should make sure that e.g. s390 only takes minor
> > hit due to all that swapping that is needed for standard-compliant
> > devices. Caching the value might certainly help in some paths.
>
> Well, this is queued in linux-next for 3.19, so
> now's the time to do it :)
So much to do, so little time...
I'm still feeling a bit uncomfortable with some of the changes
(virtio-scsi etc.) as I have not been able to test them yet (as there's
no converted qemu for these yet). The virtio-net and virtio-blk changes
seem sane, though, and virtio-ccw should be fine as well.
OTOH, it's not like we're introducing new external interfaces, so later
rework should be fine.
^ permalink raw reply [flat|nested] 26+ messages in thread
* Re: [PATCH v7 16/46] virtio_blk: v1.0 support
2014-12-01 12:02 ` Cornelia Huck
@ 2014-12-01 12:19 ` Michael S. Tsirkin
2014-12-01 12:34 ` Michael S. Tsirkin
1 sibling, 0 replies; 26+ messages in thread
From: Michael S. Tsirkin @ 2014-12-01 12:19 UTC (permalink / raw)
To: Cornelia Huck
Cc: thuth, rusty, linux-api, linux-kernel, virtualization,
David Hildenbrand, pbonzini, David Miller
On Mon, Dec 01, 2014 at 01:02:58PM +0100, Cornelia Huck wrote:
> On Mon, 1 Dec 2014 13:46:45 +0200
> "Michael S. Tsirkin" <mst@redhat.com> wrote:
>
> > On Mon, Dec 01, 2014 at 12:33:15PM +0100, Cornelia Huck wrote:
> > > On Mon, 1 Dec 2014 11:26:58 +0200
> > > "Michael S. Tsirkin" <mst@redhat.com> wrote:
> > >
> > > > For some places on data path, it might be worth it
> > > > to cache the correct value e.g. as part of device
> > > > structure. This replaces a branch with a memory load,
> > > > so the gain would have to be measured, best done
> > > > separately?
> > >
> > > I think we'll want to do some measuring once the basic structure is
> > > in place anyway.
> >
> > What's meant by in place here?
>
> That this patchset is ready :)
>
> >
> > > We should make sure that e.g. s390 only takes minor
> > > hit due to all that swapping that is needed for standard-compliant
> > > devices. Caching the value might certainly help in some paths.
> >
> > Well, this is queued in linux-next for 3.19, so
> > now's the time to do it :)
>
> So much to do, so little time...
>
> I'm still feeling a bit uncomfortable with some of the changes
> (virtio-scsi etc.) as I have not been able to test them yet (as there's
> no converted qemu for these yet). The virtio-net and virtio-blk changes
> seem sane, though, and virtio-ccw should be fine as well.
>
> OTOH, it's not like we're introducing new external interfaces, so later
> rework should be fine.
Right. I'll send a revision with virtio console and the rest of devices
shortly.
^ permalink raw reply [flat|nested] 26+ messages in thread
* Re: [PATCH v7 16/46] virtio_blk: v1.0 support
2014-12-01 12:02 ` Cornelia Huck
2014-12-01 12:19 ` Michael S. Tsirkin
@ 2014-12-01 12:34 ` Michael S. Tsirkin
[not found] ` <20141201123455.GA17958-H+wXaHxf7aLQT0dZR+AlfA@public.gmane.org>
1 sibling, 1 reply; 26+ messages in thread
From: Michael S. Tsirkin @ 2014-12-01 12:34 UTC (permalink / raw)
To: Cornelia Huck
Cc: thuth, rusty, linux-api, linux-kernel, virtualization,
David Hildenbrand, pbonzini, David Miller
On Mon, Dec 01, 2014 at 01:02:58PM +0100, Cornelia Huck wrote:
> On Mon, 1 Dec 2014 13:46:45 +0200
> "Michael S. Tsirkin" <mst@redhat.com> wrote:
>
> > On Mon, Dec 01, 2014 at 12:33:15PM +0100, Cornelia Huck wrote:
> > > On Mon, 1 Dec 2014 11:26:58 +0200
> > > "Michael S. Tsirkin" <mst@redhat.com> wrote:
> > >
> > > > For some places on data path, it might be worth it
> > > > to cache the correct value e.g. as part of device
> > > > structure. This replaces a branch with a memory load,
> > > > so the gain would have to be measured, best done
> > > > separately?
> > >
> > > I think we'll want to do some measuring once the basic structure is
> > > in place anyway.
> >
> > What's meant by in place here?
>
> That this patchset is ready :)
Also it's ready to the level where benchmarking is possible, right? I
don't think you should wait until we finish polishing up commit
messages.
> >
> > > We should make sure that e.g. s390 only takes minor
> > > hit due to all that swapping that is needed for standard-compliant
> > > devices. Caching the value might certainly help in some paths.
> >
> > Well, this is queued in linux-next for 3.19, so
> > now's the time to do it :)
>
> So much to do, so little time...
>
> I'm still feeling a bit uncomfortable with some of the changes
> (virtio-scsi etc.) as I have not been able to test them yet (as there's
> no converted qemu for these yet). The virtio-net and virtio-blk changes
> seem sane, though, and virtio-ccw should be fine as well.
>
> OTOH, it's not like we're introducing new external interfaces, so later
> rework should be fine.
^ permalink raw reply [flat|nested] 26+ messages in thread
* Re: [PATCH v7 16/46] virtio_blk: v1.0 support
2014-12-01 8:16 ` David Hildenbrand
2014-12-01 9:26 ` Michael S. Tsirkin
@ 2014-12-01 9:28 ` Michael S. Tsirkin
[not found] ` <20141201092850.GD15607-H+wXaHxf7aLQT0dZR+AlfA@public.gmane.org>
1 sibling, 1 reply; 26+ messages in thread
From: Michael S. Tsirkin @ 2014-12-01 9:28 UTC (permalink / raw)
To: David Hildenbrand
Cc: thuth, rusty, linux-api, linux-kernel, virtualization, pbonzini,
David Miller
On Mon, Dec 01, 2014 at 09:16:41AM +0100, David Hildenbrand wrote:
> > Based on patch by Cornelia Huck.
> >
> > Note: for consistency, and to avoid sparse errors,
> > convert all fields, even those no longer in use
> > for virtio v1.0.
> >
> > Signed-off-by: Cornelia Huck <cornelia.huck@de.ibm.com>
> > Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
> ...
> >
> > -static unsigned int features[] = {
> > +static unsigned int features_legacy[] = {
> > VIRTIO_BLK_F_SEG_MAX, VIRTIO_BLK_F_SIZE_MAX, VIRTIO_BLK_F_GEOMETRY,
> > VIRTIO_BLK_F_RO, VIRTIO_BLK_F_BLK_SIZE, VIRTIO_BLK_F_SCSI,
> > VIRTIO_BLK_F_WCE, VIRTIO_BLK_F_TOPOLOGY, VIRTIO_BLK_F_CONFIG_WCE,
> > VIRTIO_BLK_F_MQ,
> > +}
> > +;
> > +static unsigned int features[] = {
> > + VIRTIO_BLK_F_SEG_MAX, VIRTIO_BLK_F_SIZE_MAX, VIRTIO_BLK_F_GEOMETRY,
> > + VIRTIO_BLK_F_RO, VIRTIO_BLK_F_BLK_SIZE,
> > + VIRTIO_BLK_F_TOPOLOGY,
> > + VIRTIO_BLK_F_MQ,
> > + VIRTIO_F_VERSION_1,
>
> We can fit this into less lines, like done for features_legacy.
Wrt packing code more tightly, I did it like this to
make it easier to compare the arrays.
Each flag is on the same line in original and new array.
> I was asking myself if we could do the conversion of the statical values
> somehow upfront, to reduce the patch size and avoid cpu_to_virtio.* at those
> places.
>
> Otherwise looks good to me.
>
^ permalink raw reply [flat|nested] 26+ messages in thread
* [PATCH v7 37/46] tun: move internal flag defines out of uapi
[not found] <1417359787-10138-1-git-send-email-mst@redhat.com>
` (4 preceding siblings ...)
2014-11-30 15:10 ` [PATCH v7 16/46] virtio_blk: v1.0 support Michael S. Tsirkin
@ 2014-11-30 15:12 ` Michael S. Tsirkin
2014-11-30 15:12 ` [PATCH v7 39/46] tun: add VNET_LE flag Michael S. Tsirkin
2014-11-30 15:12 ` [PATCH v7 44/46] virtio_scsi: export to userspace Michael S. Tsirkin
7 siblings, 0 replies; 26+ messages in thread
From: Michael S. Tsirkin @ 2014-11-30 15:12 UTC (permalink / raw)
To: linux-kernel
Cc: David Miller, cornelia.huck, rusty, nab, pbonzini, thuth, dahi,
Jason Wang, Zhi Yong Wu, Herbert Xu, Tom Herbert, Ben Hutchings,
Masatake YAMATO, Xi Wang, netdev, linux-api
TUN_ flags are internal and never exposed
to userspace. Any application using it is almost
certainly buggy.
Move them out to tun.c.
Note: we remove these completely in follow-up patches,
this code movement is split out for ease of review.
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
---
include/uapi/linux/if_tun.h | 16 ++--------
drivers/net/tun.c | 72 +++++++++++++--------------------------------
2 files changed, 24 insertions(+), 64 deletions(-)
diff --git a/include/uapi/linux/if_tun.h b/include/uapi/linux/if_tun.h
index e9502dd..277a260 100644
--- a/include/uapi/linux/if_tun.h
+++ b/include/uapi/linux/if_tun.h
@@ -22,21 +22,11 @@
/* Read queue size */
#define TUN_READQ_SIZE 500
-
-/* TUN device flags */
-#define TUN_TUN_DEV 0x0001
-#define TUN_TAP_DEV 0x0002
+/* TUN device type flags: deprecated. Use IFF_TUN/IFF_TAP instead. */
+#define TUN_TUN_DEV IFF_TUN
+#define TUN_TAP_DEV IFF_TAP
#define TUN_TYPE_MASK 0x000f
-#define TUN_FASYNC 0x0010
-#define TUN_NOCHECKSUM 0x0020
-#define TUN_NO_PI 0x0040
-/* This flag has no real effect */
-#define TUN_ONE_QUEUE 0x0080
-#define TUN_PERSIST 0x0100
-#define TUN_VNET_HDR 0x0200
-#define TUN_TAP_MQ 0x0400
-
/* Ioctl defines */
#define TUNSETNOCSUM _IOW('T', 200, int)
#define TUNSETDEBUG _IOW('T', 201, int)
diff --git a/drivers/net/tun.c b/drivers/net/tun.c
index 9dd3746..b4e4ca0 100644
--- a/drivers/net/tun.c
+++ b/drivers/net/tun.c
@@ -103,6 +103,21 @@ do { \
} while (0)
#endif
+/* TUN device flags */
+
+/* IFF_ATTACH_QUEUE is never stored in device flags,
+ * overload it to mean fasync when stored there.
+ */
+#define TUN_FASYNC IFF_ATTACH_QUEUE
+#define TUN_NO_PI IFF_NO_PI
+/* This flag has no real effect */
+#define TUN_ONE_QUEUE IFF_ONE_QUEUE
+#define TUN_PERSIST IFF_PERSIST
+#define TUN_VNET_HDR IFF_VNET_HDR
+#define TUN_TAP_MQ IFF_MULTI_QUEUE
+
+#define TUN_FEATURES (IFF_NO_PI | IFF_ONE_QUEUE | IFF_VNET_HDR | \
+ IFF_MULTI_QUEUE)
#define GOODCOPY_LEN 128
#define FLT_EXACT_COUNT 8
@@ -1521,32 +1536,7 @@ static struct proto tun_proto = {
static int tun_flags(struct tun_struct *tun)
{
- int flags = 0;
-
- if (tun->flags & TUN_TUN_DEV)
- flags |= IFF_TUN;
- else
- flags |= IFF_TAP;
-
- if (tun->flags & TUN_NO_PI)
- flags |= IFF_NO_PI;
-
- /* This flag has no real effect. We track the value for backwards
- * compatibility.
- */
- if (tun->flags & TUN_ONE_QUEUE)
- flags |= IFF_ONE_QUEUE;
-
- if (tun->flags & TUN_VNET_HDR)
- flags |= IFF_VNET_HDR;
-
- if (tun->flags & TUN_TAP_MQ)
- flags |= IFF_MULTI_QUEUE;
-
- if (tun->flags & TUN_PERSIST)
- flags |= IFF_PERSIST;
-
- return flags;
+ return tun->flags & (TUN_FEATURES | IFF_PERSIST | IFF_TUN | IFF_TAP);
}
static ssize_t tun_show_flags(struct device *dev, struct device_attribute *attr,
@@ -1706,28 +1696,8 @@ static int tun_set_iff(struct net *net, struct file *file, struct ifreq *ifr)
tun_debug(KERN_INFO, tun, "tun_set_iff\n");
- if (ifr->ifr_flags & IFF_NO_PI)
- tun->flags |= TUN_NO_PI;
- else
- tun->flags &= ~TUN_NO_PI;
-
- /* This flag has no real effect. We track the value for backwards
- * compatibility.
- */
- if (ifr->ifr_flags & IFF_ONE_QUEUE)
- tun->flags |= TUN_ONE_QUEUE;
- else
- tun->flags &= ~TUN_ONE_QUEUE;
-
- if (ifr->ifr_flags & IFF_VNET_HDR)
- tun->flags |= TUN_VNET_HDR;
- else
- tun->flags &= ~TUN_VNET_HDR;
-
- if (ifr->ifr_flags & IFF_MULTI_QUEUE)
- tun->flags |= TUN_TAP_MQ;
- else
- tun->flags &= ~TUN_TAP_MQ;
+ tun->flags = (tun->flags & ~TUN_FEATURES) |
+ (ifr->ifr_flags & TUN_FEATURES);
/* Make sure persistent devices do not get stuck in
* xoff state.
@@ -1890,9 +1860,9 @@ static long __tun_chr_ioctl(struct file *file, unsigned int cmd,
if (cmd == TUNGETFEATURES) {
/* Currently this just means: "what IFF flags are valid?".
* This is needed because we never checked for invalid flags on
- * TUNSETIFF. */
- return put_user(IFF_TUN | IFF_TAP | IFF_NO_PI | IFF_ONE_QUEUE |
- IFF_VNET_HDR | IFF_MULTI_QUEUE,
+ * TUNSETIFF.
+ */
+ return put_user(IFF_TUN | IFF_TAP | TUN_FEATURES,
(unsigned int __user*)argp);
} else if (cmd == TUNSETQUEUE)
return tun_set_queue(file, &ifr);
--
MST
^ permalink raw reply related [flat|nested] 26+ messages in thread* [PATCH v7 39/46] tun: add VNET_LE flag
[not found] <1417359787-10138-1-git-send-email-mst@redhat.com>
` (5 preceding siblings ...)
2014-11-30 15:12 ` [PATCH v7 37/46] tun: move internal flag defines out of uapi Michael S. Tsirkin
@ 2014-11-30 15:12 ` Michael S. Tsirkin
2014-11-30 15:12 ` [PATCH v7 44/46] virtio_scsi: export to userspace Michael S. Tsirkin
7 siblings, 0 replies; 26+ messages in thread
From: Michael S. Tsirkin @ 2014-11-30 15:12 UTC (permalink / raw)
To: linux-kernel
Cc: David Miller, cornelia.huck, rusty, nab, pbonzini, thuth, dahi,
netdev, linux-api
virtio 1.0 modified virtio net header format,
making all fields little endian.
Users can tweak header format before submitting it to tun,
but this means more data copies where none were necessary.
And if the iovec is in RO memory, this means we might
need to split iovec also means we might in theory overflow
iovec max size.
This patch adds a simpler way for applications to handle this,
using new "little endian" flag in tun.
As a result, tun simply byte-swaps header fields as appropriate.
This is a NOP on LE architectures.
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
---
include/uapi/linux/if_tun.h | 1 +
1 file changed, 1 insertion(+)
diff --git a/include/uapi/linux/if_tun.h b/include/uapi/linux/if_tun.h
index 277a260..18b2403 100644
--- a/include/uapi/linux/if_tun.h
+++ b/include/uapi/linux/if_tun.h
@@ -57,6 +57,7 @@
#define IFF_ONE_QUEUE 0x2000
#define IFF_VNET_HDR 0x4000
#define IFF_TUN_EXCL 0x8000
+#define IFF_VNET_LE 0x10000
#define IFF_MULTI_QUEUE 0x0100
#define IFF_ATTACH_QUEUE 0x0200
#define IFF_DETACH_QUEUE 0x0400
--
MST
^ permalink raw reply related [flat|nested] 26+ messages in thread* [PATCH v7 44/46] virtio_scsi: export to userspace
[not found] <1417359787-10138-1-git-send-email-mst@redhat.com>
` (6 preceding siblings ...)
2014-11-30 15:12 ` [PATCH v7 39/46] tun: add VNET_LE flag Michael S. Tsirkin
@ 2014-11-30 15:12 ` Michael S. Tsirkin
[not found] ` <1417359787-10138-45-git-send-email-mst-H+wXaHxf7aLQT0dZR+AlfA@public.gmane.org>
7 siblings, 1 reply; 26+ messages in thread
From: Michael S. Tsirkin @ 2014-11-30 15:12 UTC (permalink / raw)
To: linux-kernel
Cc: David Miller, cornelia.huck, rusty, nab, pbonzini, thuth, dahi,
Rusty Russell, Greg Kroah-Hartman, Alexei Starovoitov,
Lad, Prabhakar, Bjarke Istrup Pedersen, Andy Grover,
stephen hemminger, Sakari Ailus, Anup Patel, linux-api,
virtualization
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>
---
include/uapi/linux/virtio_scsi.h | 74 ++++++++++++++++++++--------------------
include/uapi/linux/Kbuild | 1 +
2 files changed, 38 insertions(+), 37 deletions(-)
diff --git a/include/uapi/linux/virtio_scsi.h b/include/uapi/linux/virtio_scsi.h
index af44864..42b9370 100644
--- a/include/uapi/linux/virtio_scsi.h
+++ b/include/uapi/linux/virtio_scsi.h
@@ -34,78 +34,78 @@
/* SCSI command request, followed by data-out */
struct virtio_scsi_cmd_req {
- u8 lun[8]; /* Logical Unit Number */
+ __u8 lun[8]; /* Logical Unit Number */
__virtio64 tag; /* Command identifier */
- u8 task_attr; /* Task attribute */
- u8 prio; /* SAM command priority field */
- u8 crn;
- u8 cdb[VIRTIO_SCSI_CDB_SIZE];
-} __packed;
+ __u8 task_attr; /* Task attribute */
+ __u8 prio; /* SAM command priority field */
+ __u8 crn;
+ __u8 cdb[VIRTIO_SCSI_CDB_SIZE];
+} __attribute__((packed));
/* SCSI command request, followed by protection information */
struct virtio_scsi_cmd_req_pi {
- u8 lun[8]; /* Logical Unit Number */
+ __u8 lun[8]; /* Logical Unit Number */
__virtio64 tag; /* Command identifier */
- u8 task_attr; /* Task attribute */
- u8 prio; /* SAM command priority field */
- u8 crn;
+ __u8 task_attr; /* Task attribute */
+ __u8 prio; /* SAM command priority field */
+ __u8 crn;
__virtio32 pi_bytesout; /* DataOUT PI Number of bytes */
__virtio32 pi_bytesin; /* DataIN PI Number of bytes */
- u8 cdb[VIRTIO_SCSI_CDB_SIZE];
-} __packed;
+ __u8 cdb[VIRTIO_SCSI_CDB_SIZE];
+} __attribute__((packed));
/* Response, followed by sense data and data-in */
struct virtio_scsi_cmd_resp {
__virtio32 sense_len; /* Sense data length */
__virtio32 resid; /* Residual bytes in data buffer */
__virtio16 status_qualifier; /* Status qualifier */
- u8 status; /* Command completion status */
- u8 response; /* Response values */
- u8 sense[VIRTIO_SCSI_SENSE_SIZE];
-} __packed;
+ __u8 status; /* Command completion status */
+ __u8 response; /* Response values */
+ __u8 sense[VIRTIO_SCSI_SENSE_SIZE];
+} __attribute__((packed));
/* Task Management Request */
struct virtio_scsi_ctrl_tmf_req {
__virtio32 type;
__virtio32 subtype;
- u8 lun[8];
+ __u8 lun[8];
__virtio64 tag;
-} __packed;
+} __attribute__((packed));
struct virtio_scsi_ctrl_tmf_resp {
- u8 response;
-} __packed;
+ __u8 response;
+} __attribute__((packed));
/* Asynchronous notification query/subscription */
struct virtio_scsi_ctrl_an_req {
__virtio32 type;
- u8 lun[8];
+ __u8 lun[8];
__virtio32 event_requested;
-} __packed;
+} __attribute__((packed));
struct virtio_scsi_ctrl_an_resp {
__virtio32 event_actual;
- u8 response;
-} __packed;
+ __u8 response;
+} __attribute__((packed));
struct virtio_scsi_event {
__virtio32 event;
- u8 lun[8];
+ __u8 lun[8];
__virtio32 reason;
-} __packed;
+} __attribute__((packed));
struct virtio_scsi_config {
- u32 num_queues;
- u32 seg_max;
- u32 max_sectors;
- u32 cmd_per_lun;
- u32 event_info_size;
- u32 sense_size;
- u32 cdb_size;
- u16 max_channel;
- u16 max_target;
- u32 max_lun;
-} __packed;
+ __u32 num_queues;
+ __u32 seg_max;
+ __u32 max_sectors;
+ __u32 cmd_per_lun;
+ __u32 event_info_size;
+ __u32 sense_size;
+ __u32 cdb_size;
+ __u16 max_channel;
+ __u16 max_target;
+ __u32 max_lun;
+} __attribute__((packed));
/* Feature Bits */
#define VIRTIO_SCSI_F_INOUT 0
diff --git a/include/uapi/linux/Kbuild b/include/uapi/linux/Kbuild
index 44a5581..e61947c 100644
--- a/include/uapi/linux/Kbuild
+++ b/include/uapi/linux/Kbuild
@@ -428,6 +428,7 @@ header-y += virtio_net.h
header-y += virtio_pci.h
header-y += virtio_ring.h
header-y += virtio_rng.h
+header-y += virtio_scsi.h
header=y += vm_sockets.h
header-y += vt.h
header-y += wait.h
--
MST
^ permalink raw reply related [flat|nested] 26+ messages in thread