[PATCH RFC v3 01/16] virtio: memory access APIs

[PATCH RFC v3 01/16] virtio: memory access APIs

[Michael S. Tsirkin]

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 will (in the
future) query device endian-ness and act accordingly.

At the moment, stub them out and assume native endian-ness everywhere.

Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
---
 include/linux/virtio_byteorder.h | 29 ++++++++++++++++++++++++
 include/linux/virtio_config.h    | 16 +++++++++++++
 include/uapi/linux/virtio_ring.h | 49 ++++++++++++++++++++--------------------
 include/uapi/linux/Kbuild        |  1 +
 4 files changed, 71 insertions(+), 24 deletions(-)
 create mode 100644 include/linux/virtio_byteorder.h

diff --git a/include/linux/virtio_byteorder.h b/include/linux/virtio_byteorder.h
new file mode 100644
index 0000000..7afdd8a
--- /dev/null
+++ b/include/linux/virtio_byteorder.h
@@ -0,0 +1,29 @@
+#ifndef _LINUX_VIRTIO_BYTEORDER_H
+#define _LINUX_VIRTIO_BYTEORDER_H
+#include <linux/types.h>
+#include <uapi/linux/virtio_types.h>
+
+/* Memory accessors for handling virtio in modern little endian and in
+ * compatibility big endian format. */
+
+#define __DEFINE_VIRTIO_XX_TO_CPU(bits) \
+static inline u##bits __virtio##bits##_to_cpu(bool little_endian, __virtio##bits val) \
+{ \
+	if (little_endian) \
+		return le##bits##_to_cpu((__force __le##bits)val); \
+	else \
+		return (__force u##bits)val; \
+} \
+static inline __virtio##bits __cpu_to_virtio##bits(bool little_endian, u##bits val) \
+{ \
+	if (little_endian) \
+		return (__force __virtio##bits)cpu_to_le##bits(val); \
+	else \
+		return val; \
+}
+
+__DEFINE_VIRTIO_XX_TO_CPU(16)
+__DEFINE_VIRTIO_XX_TO_CPU(32)
+__DEFINE_VIRTIO_XX_TO_CPU(64)
+
+#endif /* _LINUX_VIRTIO_BYTEORDER */
diff --git a/include/linux/virtio_config.h b/include/linux/virtio_config.h
index 7f4ef66..d38d3c2 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>
 
 /**
@@ -152,6 +153,21 @@ int virtqueue_set_affinity(struct virtqueue *vq, int cpu)
 	return 0;
 }
 
+/* Memory accessors */
+#define DEFINE_VIRTIO_XX_TO_CPU(bits) \
+static inline u##bits virtio##bits##_to_cpu(struct virtio_device *vdev, __virtio##bits val) \
+{ \
+	return __virtio##bits##_to_cpu(false, val); \
+} \
+static inline __virtio##bits cpu_to_virtio##bits(struct virtio_device *vdev, u##bits val) \
+{ \
+	return __cpu_to_virtio##bits(false, val); \
+}
+
+DEFINE_VIRTIO_XX_TO_CPU(16)
+DEFINE_VIRTIO_XX_TO_CPU(32)
+DEFINE_VIRTIO_XX_TO_CPU(64)
+
 /* 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..6c00632 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)
@@ -135,29 +136,29 @@ 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 */
 /* Assuming a given event_idx value from the other size, if
  * we have just incremented index from old to new_idx,
  * should we trigger an event? */
-static inline int vring_need_event(__u16 event_idx, __u16 new_idx, __u16 old)
+static inline int vring_need_event(__virtio16 event_idx, __virtio16 new_idx, __virtio16 old)
 {
 	/* Note: Xen has similar logic for notification hold-off
 	 * in include/xen/interface/io/ring.h with req_event and req_prod
 	 * corresponding to event_idx + 1 and new_idx respectively.
 	 * Note also that req_event and req_prod in Xen start at 1,
 	 * event indexes in virtio start at 0. */
-	return (__u16)(new_idx - event_idx - 1) < (__u16)(new_idx - old);
+	return (__virtio16)(new_idx - event_idx - 1) < (__virtio16)(new_idx - old);
 }
 
 #endif /* _UAPI_LINUX_VIRTIO_RING_H */
diff --git a/include/uapi/linux/Kbuild b/include/uapi/linux/Kbuild
index 6cad974..39c161a 100644
--- a/include/uapi/linux/Kbuild
+++ b/include/uapi/linux/Kbuild
@@ -419,6 +419,7 @@ 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

[PATCH RFC v3 05/16] virtio: add virtio 1.0 feature bit

[Michael S. Tsirkin]

Based on original patches by Rusty Russell, Thomas Huth
and Cornelia Huck.

Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
---
 include/uapi/linux/virtio_config.h | 7 +++++--
 drivers/virtio/virtio_ring.c       | 2 ++
 2 files changed, 7 insertions(+), 2 deletions(-)

diff --git a/include/uapi/linux/virtio_config.h b/include/uapi/linux/virtio_config.h
index 3ce768c..f3fe33a 100644
--- a/include/uapi/linux/virtio_config.h
+++ b/include/uapi/linux/virtio_config.h
@@ -41,11 +41,11 @@
 /* We've given up on this device. */
 #define VIRTIO_CONFIG_S_FAILED		0x80
 
-/* Some virtio feature bits (currently bits 28 through 31) are reserved for the
+/* Some virtio feature bits (currently bits 28 through 32) are reserved for the
  * transport being used (eg. virtio_ring), the rest are per-device feature
  * bits. */
 #define VIRTIO_TRANSPORT_F_START	28
-#define VIRTIO_TRANSPORT_F_END		32
+#define VIRTIO_TRANSPORT_F_END		33
 
 /* Do we get callbacks when the ring is completely used, even if we've
  * suppressed them? */
@@ -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 */
diff --git a/drivers/virtio/virtio_ring.c b/drivers/virtio/virtio_ring.c
index b311fa7..9f5dfe3 100644
--- a/drivers/virtio/virtio_ring.c
+++ b/drivers/virtio/virtio_ring.c
@@ -780,6 +780,8 @@ void vring_transport_features(struct virtio_device *vdev)
 			break;
 		case VIRTIO_RING_F_EVENT_IDX:
 			break;
+		case VIRTIO_F_VERSION_1:
+			break;
 		default:
 			/* We don't understand this bit. */
 			vdev->features &= ~(1ULL << i);
-- 
MST

[PATCH RFC v3 09/16] virtio: set FEATURES_OK

[Michael S. Tsirkin]

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 f3fe33a..a6d0cde 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 d213567..a3df817 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)) {
+			printk(KERN_ERR "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

[PATCH RFC v3 15/16] virtio_net: fix types for in memory structures

[Michael S. Tsirkin]

Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
---
 include/uapi/linux/virtio_net.h | 15 ++++++++-------
 1 file changed, 8 insertions(+), 7 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
-- 
MST

[PATCH RFC v3 16/16] virtio_blk: fix types for in memory structures

[Michael S. Tsirkin]

Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
---
 include/uapi/linux/virtio_blk.h | 15 ++++++++-------
 1 file changed, 8 insertions(+), 7 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. */
-- 
MST

Re: [PATCH RFC v3 01/16] virtio: memory access APIs

[Cornelia Huck]

On Wed, 22 Oct 2014 21:44:08 +0300
"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 will (in the
> future) query device endian-ness and act accordingly.
> 
> At the moment, stub them out and assume native endian-ness everywhere.
> 
> Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
> ---
>  include/linux/virtio_byteorder.h | 29 ++++++++++++++++++++++++
>  include/linux/virtio_config.h    | 16 +++++++++++++
>  include/uapi/linux/virtio_ring.h | 49 ++++++++++++++++++++--------------------
>  include/uapi/linux/Kbuild        |  1 +
>  4 files changed, 71 insertions(+), 24 deletions(-)
>  create mode 100644 include/linux/virtio_byteorder.h
> 
> diff --git a/include/linux/virtio_byteorder.h b/include/linux/virtio_byteorder.h
> new file mode 100644
> index 0000000..7afdd8a
> --- /dev/null
> +++ b/include/linux/virtio_byteorder.h
> @@ -0,0 +1,29 @@
> +#ifndef _LINUX_VIRTIO_BYTEORDER_H
> +#define _LINUX_VIRTIO_BYTEORDER_H
> +#include <linux/types.h>
> +#include <uapi/linux/virtio_types.h>
> +
> +/* Memory accessors for handling virtio in modern little endian and in
> + * compatibility big endian format. */

s/big/native/

> +
> +#define __DEFINE_VIRTIO_XX_TO_CPU(bits) \
> +static inline u##bits __virtio##bits##_to_cpu(bool little_endian, __virtio##bits val) \
> +{ \
> +	if (little_endian) \
> +		return le##bits##_to_cpu((__force __le##bits)val); \
> +	else \
> +		return (__force u##bits)val; \
> +} \
> +static inline __virtio##bits __cpu_to_virtio##bits(bool little_endian, u##bits val) \
> +{ \
> +	if (little_endian) \
> +		return (__force __virtio##bits)cpu_to_le##bits(val); \
> +	else \
> +		return val; \
> +}
> +
> +__DEFINE_VIRTIO_XX_TO_CPU(16)
> +__DEFINE_VIRTIO_XX_TO_CPU(32)
> +__DEFINE_VIRTIO_XX_TO_CPU(64)

...although I'm still not too happy with macro-generated helpers.

> +
> +#endif /* _LINUX_VIRTIO_BYTEORDER */

> diff --git a/include/uapi/linux/virtio_ring.h b/include/uapi/linux/virtio_ring.h
> index a99f9b7..6c00632 100644
> --- a/include/uapi/linux/virtio_ring.h
> +++ b/include/uapi/linux/virtio_ring.h

> @@ -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;
>  };

I think all of these __virtio types need an explanation somewhere as to
what they mean, e.g.:

/*
 * __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
 */

Re: [PATCH RFC v3 01/16] virtio: memory access APIs

[Michael S. Tsirkin]

On Thu, Oct 23, 2014 at 09:54:05AM +0200, Cornelia Huck wrote:
> On Wed, 22 Oct 2014 21:44:08 +0300
> "Michael S. Tsirkin" <mst-H+wXaHxf7aLQT0dZR+AlfA@public.gmane.org> 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 will (in the
> > future) query device endian-ness and act accordingly.
> > 
> > At the moment, stub them out and assume native endian-ness everywhere.
> > 
> > Signed-off-by: Michael S. Tsirkin <mst-H+wXaHxf7aLQT0dZR+AlfA@public.gmane.org>
> > ---
> >  include/linux/virtio_byteorder.h | 29 ++++++++++++++++++++++++
> >  include/linux/virtio_config.h    | 16 +++++++++++++
> >  include/uapi/linux/virtio_ring.h | 49 ++++++++++++++++++++--------------------
> >  include/uapi/linux/Kbuild        |  1 +
> >  4 files changed, 71 insertions(+), 24 deletions(-)
> >  create mode 100644 include/linux/virtio_byteorder.h
> > 
> > diff --git a/include/linux/virtio_byteorder.h b/include/linux/virtio_byteorder.h
> > new file mode 100644
> > index 0000000..7afdd8a
> > --- /dev/null
> > +++ b/include/linux/virtio_byteorder.h
> > @@ -0,0 +1,29 @@
> > +#ifndef _LINUX_VIRTIO_BYTEORDER_H
> > +#define _LINUX_VIRTIO_BYTEORDER_H
> > +#include <linux/types.h>
> > +#include <uapi/linux/virtio_types.h>
> > +
> > +/* Memory accessors for handling virtio in modern little endian and in
> > + * compatibility big endian format. */
> 
> s/big/native/

Thanks.

> > +
> > +#define __DEFINE_VIRTIO_XX_TO_CPU(bits) \
> > +static inline u##bits __virtio##bits##_to_cpu(bool little_endian, __virtio##bits val) \
> > +{ \
> > +	if (little_endian) \
> > +		return le##bits##_to_cpu((__force __le##bits)val); \
> > +	else \
> > +		return (__force u##bits)val; \
> > +} \
> > +static inline __virtio##bits __cpu_to_virtio##bits(bool little_endian, u##bits val) \
> > +{ \
> > +	if (little_endian) \
> > +		return (__force __virtio##bits)cpu_to_le##bits(val); \
> > +	else \
> > +		return val; \
> > +}
> > +
> > +__DEFINE_VIRTIO_XX_TO_CPU(16)
> > +__DEFINE_VIRTIO_XX_TO_CPU(32)
> > +__DEFINE_VIRTIO_XX_TO_CPU(64)
> 
> ...although I'm still not too happy with macro-generated helpers.

I'm fine with open-coding them.

> > +
> > +#endif /* _LINUX_VIRTIO_BYTEORDER */
> 
> > diff --git a/include/uapi/linux/virtio_ring.h b/include/uapi/linux/virtio_ring.h
> > index a99f9b7..6c00632 100644
> > --- a/include/uapi/linux/virtio_ring.h
> > +++ b/include/uapi/linux/virtio_ring.h
> 
> > @@ -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;
> >  };
> 
> I think all of these __virtio types need an explanation somewhere as to
> what they mean, e.g.:
> 
> /*
>  * __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
>  */

Will do.

-- 
MST

Re: [PATCH RFC v3 05/16] virtio: add virtio 1.0 feature bit

[Cornelia Huck]

On Wed, 22 Oct 2014 21:44:31 +0300
"Michael S. Tsirkin" <mst@redhat.com> wrote:

> Based on original patches by Rusty Russell, Thomas Huth
> and Cornelia Huck.
> 
> Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
> ---
>  include/uapi/linux/virtio_config.h | 7 +++++--
>  drivers/virtio/virtio_ring.c       | 2 ++
>  2 files changed, 7 insertions(+), 2 deletions(-)

Reviewed-by: Cornelia Huck <cornelia.huck@de.ibm.com>

Re: [PATCH RFC v3 09/16] virtio: set FEATURES_OK

[Cornelia Huck]

On Wed, 22 Oct 2014 21:44:44 +0300
"Michael S. Tsirkin" <mst-H+wXaHxf7aLQT0dZR+AlfA@public.gmane.org> wrote:

> set FEATURES_OK as per virtio 1.0 spec
> 
> Signed-off-by: Michael S. Tsirkin <mst-H+wXaHxf7aLQT0dZR+AlfA@public.gmane.org>
> ---
>  include/uapi/linux/virtio_config.h |  2 ++
>  drivers/virtio/virtio.c            | 29 ++++++++++++++++++++++-------
>  2 files changed, 24 insertions(+), 7 deletions(-)
> 

>  	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)) {
> +			printk(KERN_ERR "virtio: device refuses features: %x\n",
> +			       status);
> +			err = -ENODEV;
> +			goto err;
> +		}
> +	}
> +

Ugh, I just realize that virtio-ccw has a problem with that mechanism :(

Up to now, the driver only propagated status to the device: For
virtio-ccw, this was easily implemented via a ccw that transmitted
"status" to the device. However, the "read back status" part now
actually requires that the driver can get "status" from the device, or
has a comparable way to find out that the device won't accept the
status it tried to write.

I can think of two solutions:

(1) Introduce a new ccw that actually reads the device status.
(2) Make the WRITE_STATUS ccw fail (with a unit check) if the driver
    sets FEATURES_OK after it tried to set features the device won't
    accept.

(1) is probably more generic, while (2) is more straightforward to
implement.

Good thing we actually try to finally implement this, I did not notice
this problem during the review :(

Re: [PATCH RFC v3 09/16] virtio: set FEATURES_OK

[Michael S. Tsirkin]

On Thu, Oct 23, 2014 at 02:28:08PM +0200, Cornelia Huck wrote:
> On Wed, 22 Oct 2014 21:44:44 +0300
> "Michael S. Tsirkin" <mst@redhat.com> wrote:
> 
> > 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(-)
> > 
> 
> >  	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)) {
> > +			printk(KERN_ERR "virtio: device refuses features: %x\n",
> > +			       status);
> > +			err = -ENODEV;
> > +			goto err;
> > +		}
> > +	}
> > +
> 
> Ugh, I just realize that virtio-ccw has a problem with that mechanism :(
> 
> Up to now, the driver only propagated status to the device: For
> virtio-ccw, this was easily implemented via a ccw that transmitted
> "status" to the device. However, the "read back status" part now
> actually requires that the driver can get "status" from the device, or
> has a comparable way to find out that the device won't accept the
> status it tried to write.

Ugh, it actually caches the status in the transport :(


> I can think of two solutions:
> 
> (1) Introduce a new ccw that actually reads the device status.
> (2) Make the WRITE_STATUS ccw fail (with a unit check) if the driver
>     sets FEATURES_OK after it tried to set features the device won't
>     accept.
> 
> (1) is probably more generic, while (2) is more straightforward to
> implement.
> 
> Good thing we actually try to finally implement this,

> I did not notice
> this problem during the review :(

Well, it's a nuisance, but the spec is out.
It seems to me a new command would be a substantive change so we can't
do this in errata.

Option (2) would require two statements for drivers and devices,
but since it's clearly the case for correct drivers/devices
that command does not fail, it follows that this
is not a substantive change so it can be fixed
in an errata.

So the new command would have to be optional, please open
two issues in the TC: one documenting that driver must check
WRITE_STATUS and device can fail WRITE_STATUS, and another
for adding READ_STATUS (which will have to wait until
the next CS).


-- 
MST

Re: [PATCH RFC v3 09/16] virtio: set FEATURES_OK

[Cornelia Huck]

On Thu, 23 Oct 2014 15:51:39 +0300
"Michael S. Tsirkin" <mst@redhat.com> wrote:

> On Thu, Oct 23, 2014 at 02:28:08PM +0200, Cornelia Huck wrote:
> > On Wed, 22 Oct 2014 21:44:44 +0300
> > "Michael S. Tsirkin" <mst@redhat.com> wrote:
> > 
> > > 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(-)
> > > 
> > 
> > >  	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)) {
> > > +			printk(KERN_ERR "virtio: device refuses features: %x\n",
> > > +			       status);
> > > +			err = -ENODEV;
> > > +			goto err;
> > > +		}
> > > +	}
> > > +
> > 
> > Ugh, I just realize that virtio-ccw has a problem with that mechanism :(
> > 
> > Up to now, the driver only propagated status to the device: For
> > virtio-ccw, this was easily implemented via a ccw that transmitted
> > "status" to the device. However, the "read back status" part now
> > actually requires that the driver can get "status" from the device, or
> > has a comparable way to find out that the device won't accept the
> > status it tried to write.
> 
> Ugh, it actually caches the status in the transport :(

Well, it worked as long as this was unidirectional...

> 
> 
> > I can think of two solutions:
> > 
> > (1) Introduce a new ccw that actually reads the device status.
> > (2) Make the WRITE_STATUS ccw fail (with a unit check) if the driver
> >     sets FEATURES_OK after it tried to set features the device won't
> >     accept.
> > 
> > (1) is probably more generic, while (2) is more straightforward to
> > implement.
> > 
> > Good thing we actually try to finally implement this,
> 
> > I did not notice
> > this problem during the review :(
> 
> Well, it's a nuisance, but the spec is out.
> It seems to me a new command would be a substantive change so we can't
> do this in errata.
> 
> Option (2) would require two statements for drivers and devices,
> but since it's clearly the case for correct drivers/devices
> that command does not fail, it follows that this
> is not a substantive change so it can be fixed
> in an errata.

It only adds a new failure case, so it's not really magic, agreed.

> 
> So the new command would have to be optional, 

I think a new command should be tied to a new virtio-ccw revision.

> please open
> two issues in the TC: one documenting that driver must check
> WRITE_STATUS and device can fail WRITE_STATUS, and another
> for adding READ_STATUS (which will have to wait until
> the next CS).

I think I need to contemplate that a bit more. The problem with a new
READ_STATUS is that it is, by nature, an asynchronous command (as all
ccw commands are - the Linux guest driver uses a simple wrapper that
makes it appear synchronous). This means, for example, that every
status update now involves two channel programs instead of one, and
that reading e.g. the status sysfs attribute in Linux now triggers
channel I/O, which means several exits (at least ssch, interrupt
injection, tsch; probably more depending on what the guest does)...

Re: [PATCH RFC v3 09/16] virtio: set FEATURES_OK

[Michael S. Tsirkin]

On Thu, Oct 23, 2014 at 03:30:06PM +0200, Cornelia Huck wrote:
> On Thu, 23 Oct 2014 15:51:39 +0300
> "Michael S. Tsirkin" <mst@redhat.com> wrote:
> 
> > On Thu, Oct 23, 2014 at 02:28:08PM +0200, Cornelia Huck wrote:
> > > On Wed, 22 Oct 2014 21:44:44 +0300
> > > "Michael S. Tsirkin" <mst@redhat.com> wrote:
> > > 
> > > > 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(-)
> > > > 
> > > 
> > > >  	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)) {
> > > > +			printk(KERN_ERR "virtio: device refuses features: %x\n",
> > > > +			       status);
> > > > +			err = -ENODEV;
> > > > +			goto err;
> > > > +		}
> > > > +	}
> > > > +
> > > 
> > > Ugh, I just realize that virtio-ccw has a problem with that mechanism :(
> > > 
> > > Up to now, the driver only propagated status to the device: For
> > > virtio-ccw, this was easily implemented via a ccw that transmitted
> > > "status" to the device. However, the "read back status" part now
> > > actually requires that the driver can get "status" from the device, or
> > > has a comparable way to find out that the device won't accept the
> > > status it tried to write.
> > 
> > Ugh, it actually caches the status in the transport :(
> 
> Well, it worked as long as this was unidirectional...
> 
> > 
> > 
> > > I can think of two solutions:
> > > 
> > > (1) Introduce a new ccw that actually reads the device status.
> > > (2) Make the WRITE_STATUS ccw fail (with a unit check) if the driver
> > >     sets FEATURES_OK after it tried to set features the device won't
> > >     accept.
> > > 
> > > (1) is probably more generic, while (2) is more straightforward to
> > > implement.
> > > 
> > > Good thing we actually try to finally implement this,
> > 
> > > I did not notice
> > > this problem during the review :(
> > 
> > Well, it's a nuisance, but the spec is out.
> > It seems to me a new command would be a substantive change so we can't
> > do this in errata.
> > 
> > Option (2) would require two statements for drivers and devices,
> > but since it's clearly the case for correct drivers/devices
> > that command does not fail, it follows that this
> > is not a substantive change so it can be fixed
> > in an errata.
> 
> It only adds a new failure case, so it's not really magic, agreed.
> 
> > 
> > So the new command would have to be optional, 
> 
> I think a new command should be tied to a new virtio-ccw revision.

Or a feature bit.

> > please open
> > two issues in the TC: one documenting that driver must check
> > WRITE_STATUS and device can fail WRITE_STATUS, and another
> > for adding READ_STATUS (which will have to wait until
> > the next CS).
> 
> I think I need to contemplate that a bit more. The problem with a new
> READ_STATUS is that it is, by nature, an asynchronous command (as all
> ccw commands are - the Linux guest driver uses a simple wrapper that
> makes it appear synchronous). This means, for example, that every
> status update now involves two channel programs instead of one, and
> that reading e.g. the status sysfs attribute in Linux now triggers
> channel I/O, which means several exits (at least ssch, interrupt
> injection, tsch; probably more depending on what the guest does)...

Well it seems more robust than just caching it within guest.
Anyway, let's start with issue tracker, it does not force any specific
solution.

-- 
MST