[PATCH v2 12/23] vfio-user: region read/write

[John Johnson]

Add support for posted writes on remote devices

Signed-off-by: Elena Ufimtseva <elena.ufimtseva@oracle.com>
Signed-off-by: John G Johnson <john.g.johnson@oracle.com>
Signed-off-by: Jagannathan Raman <jag.raman@oracle.com>
---
 hw/vfio/user-protocol.h       |  12 +++++
 hw/vfio/user.h                |   1 +
 include/hw/vfio/vfio-common.h |   3 +-
 hw/vfio/common.c              |  23 ++++++---
 hw/vfio/pci.c                 |   5 +-
 hw/vfio/user-pci.c            |   5 ++
 hw/vfio/user.c                | 112 ++++++++++++++++++++++++++++++++++++++++++
 hw/vfio/trace-events          |   1 +
 8 files changed, 154 insertions(+), 8 deletions(-)

diff --git a/hw/vfio/user-protocol.h b/hw/vfio/user-protocol.h
index 6f70a48..6987435 100644
--- a/hw/vfio/user-protocol.h
+++ b/hw/vfio/user-protocol.h
@@ -139,4 +139,16 @@ typedef struct {
     uint64_t offset;
 } VFIOUserRegionInfo;
 
+/*
+ * VFIO_USER_REGION_READ
+ * VFIO_USER_REGION_WRITE
+ */
+typedef struct {
+    VFIOUserHdr hdr;
+    uint64_t offset;
+    uint32_t region;
+    uint32_t count;
+    char data[];
+} VFIOUserRegionRW;
+
 #endif /* VFIO_USER_PROTOCOL_H */
diff --git a/hw/vfio/user.h b/hw/vfio/user.h
index e6485dc..3012a86 100644
--- a/hw/vfio/user.h
+++ b/hw/vfio/user.h
@@ -84,6 +84,7 @@ typedef struct VFIOUserProxy {
 /* VFIOProxy flags */
 #define VFIO_PROXY_CLIENT        0x1
 #define VFIO_PROXY_FORCE_QUEUED  0x4
+#define VFIO_PROXY_NO_POST       0x8
 
 VFIOUserProxy *vfio_user_connect_dev(SocketAddress *addr, Error **errp);
 void vfio_user_disconnect(VFIOUserProxy *proxy);
diff --git a/include/hw/vfio/vfio-common.h b/include/hw/vfio/vfio-common.h
index 9fb4c80..bbc4b15 100644
--- a/include/hw/vfio/vfio-common.h
+++ b/include/hw/vfio/vfio-common.h
@@ -57,6 +57,7 @@ typedef struct VFIORegion {
     VFIOMmap *mmaps;
     uint8_t nr; /* cache the region number for debug */
     int fd; /* fd to mmap() region */
+    bool post_wr; /* writes can be posted */
 } VFIORegion;
 
 typedef struct VFIOMigration {
@@ -180,7 +181,7 @@ struct VFIODeviceIO {
     int (*region_read)(VFIODevice *vdev, uint8_t nr, off_t off, uint32_t size,
                        void *data);
     int (*region_write)(VFIODevice *vdev, uint8_t nr, off_t off, uint32_t size,
-                        void *data);
+                        void *data, bool post);
 };
 
 struct VFIOContainerIO {
diff --git a/hw/vfio/common.c b/hw/vfio/common.c
index d26b325..de64e53 100644
--- a/hw/vfio/common.c
+++ b/hw/vfio/common.c
@@ -215,6 +215,7 @@ void vfio_region_write(void *opaque, hwaddr addr,
         uint32_t dword;
         uint64_t qword;
     } buf;
+    bool post = region->post_wr;
     int ret;
 
     switch (size) {
@@ -235,12 +236,19 @@ void vfio_region_write(void *opaque, hwaddr addr,
         break;
     }
 
-    ret = vbasedev->io->region_write(vbasedev, region->nr, addr, size, &buf);
+    /* read-after-write hazard if guest can directly access region */
+    if (region->nr_mmaps) {
+        post = false;
+    }
+    ret = vbasedev->io->region_write(vbasedev, region->nr, addr, size, &buf,
+                                     post);
     if (ret != size) {
+        const char *err = ret < 0 ? strerror(-ret) : "short write";
+
         error_report("%s(%s:region%d+0x%"HWADDR_PRIx", 0x%"PRIx64
-                     ",%d) failed: %m",
+                     ",%d) failed: %s",
                      __func__, vbasedev->name, region->nr,
-                     addr, data, size);
+                     addr, data, size, err);
     }
     trace_vfio_region_write(vbasedev->name, region->nr, addr, data, size);
 
@@ -271,9 +279,11 @@ uint64_t vfio_region_read(void *opaque,
 
     ret = vbasedev->io->region_read(vbasedev, region->nr, addr, size, &buf);
     if (ret != size) {
-        error_report("%s(%s:region%d+0x%"HWADDR_PRIx", %d) failed: %m",
+        const char *err = ret < 0 ? strerror(-ret) : "short read";
+
+        error_report("%s(%s:region%d+0x%"HWADDR_PRIx", %d) failed: %s",
                      __func__, vbasedev->name, region->nr,
-                     addr, size);
+                     addr, size, err);
         return (uint64_t)-1;
     }
 
@@ -1584,6 +1594,7 @@ int vfio_region_setup(Object *obj, VFIODevice *vbasedev, 
VFIORegion *region,
     region->size = info->size;
     region->fd_offset = info->offset;
     region->nr = index;
+    region->post_wr = false;
     if (vbasedev->regfds != NULL) {
         region->fd = vbasedev->regfds[index];
     } else {
@@ -2711,7 +2722,7 @@ static int vfio_io_region_read(VFIODevice *vbasedev, 
uint8_t index, off_t off,
 }
 
 static int vfio_io_region_write(VFIODevice *vbasedev, uint8_t index, off_t off,
-                                uint32_t size, void *data)
+                                uint32_t size, void *data, bool post)
 {
     struct vfio_region_info *info = vbasedev->regions[index];
     int ret;
diff --git a/hw/vfio/pci.c b/hw/vfio/pci.c
index 935d247..be714b7 100644
--- a/hw/vfio/pci.c
+++ b/hw/vfio/pci.c
@@ -49,7 +49,7 @@
                                  (off), (size), (data)))
 #define VDEV_CONFIG_WRITE(vbasedev, off, size, data) \
     ((vbasedev)->io->region_write((vbasedev), VFIO_PCI_CONFIG_REGION_INDEX, \
-                                  (off), (size), (data)))
+                                  (off), (size), (data), false))
 
 #define TYPE_VFIO_PCI_NOHOTPLUG "vfio-pci-nohotplug"
 
@@ -1702,6 +1702,9 @@ static void vfio_bar_prepare(VFIOPCIDevice *vdev, int nr)
     bar->type = pci_bar & (bar->ioport ? ~PCI_BASE_ADDRESS_IO_MASK :
                                          ~PCI_BASE_ADDRESS_MEM_MASK);
     bar->size = bar->region.size;
+
+    /* IO regions are sync, memory can be async */
+    bar->region.post_wr = (bar->ioport == 0);
 }
 
 static void vfio_bars_prepare(VFIOPCIDevice *vdev)
diff --git a/hw/vfio/user-pci.c b/hw/vfio/user-pci.c
index 09c6c98..900ab5f 100644
--- a/hw/vfio/user-pci.c
+++ b/hw/vfio/user-pci.c
@@ -41,6 +41,7 @@ struct VFIOUserPCIDevice {
     VFIOPCIDevice device;
     char *sock_name;
     bool send_queued;   /* all sends are queued */
+    bool no_post;       /* all regions write are sync */
 };
 
 /*
@@ -105,6 +106,9 @@ static void vfio_user_pci_realize(PCIDevice *pdev, Error 
**errp)
     if (udev->send_queued) {
         proxy->flags |= VFIO_PROXY_FORCE_QUEUED;
     }
+    if (udev->no_post) {
+        proxy->flags |= VFIO_PROXY_NO_POST;
+    }
 
     vfio_user_validate_version(proxy, &err);
     if (err != NULL) {
@@ -145,6 +149,7 @@ static void vfio_user_instance_finalize(Object *obj)
 static Property vfio_user_pci_dev_properties[] = {
     DEFINE_PROP_STRING("socket", VFIOUserPCIDevice, sock_name),
     DEFINE_PROP_BOOL("x-send-queued", VFIOUserPCIDevice, send_queued, false),
+    DEFINE_PROP_BOOL("x-no-posted-writes", VFIOUserPCIDevice, no_post, false),
     DEFINE_PROP_END_OF_LIST(),
 };
 
diff --git a/hw/vfio/user.c b/hw/vfio/user.c
index a05ba80..389c807 100644
--- a/hw/vfio/user.c
+++ b/hw/vfio/user.c
@@ -58,6 +58,8 @@ static void vfio_user_cb(void *opaque);
 
 static void vfio_user_request(void *opaque);
 static int vfio_user_send_queued(VFIOUserProxy *proxy, VFIOUserMsg *msg);
+static void vfio_user_send_async(VFIOUserProxy *proxy, VFIOUserHdr *hdr,
+                                 VFIOUserFDs *fds);
 static void vfio_user_send_wait(VFIOUserProxy *proxy, VFIOUserHdr *hdr,
                                 VFIOUserFDs *fds, int rsize, bool nobql);
 static void vfio_user_request_msg(VFIOUserHdr *hdr, uint16_t cmd,
@@ -631,6 +633,33 @@ static int vfio_user_send_queued(VFIOUserProxy *proxy, 
VFIOUserMsg *msg)
     return 0;
 }
 
+/*
+ * async send - msg can be queued, but will be freed when sent
+ */
+static void vfio_user_send_async(VFIOUserProxy *proxy, VFIOUserHdr *hdr,
+                                 VFIOUserFDs *fds)
+{
+    VFIOUserMsg *msg;
+    int ret;
+
+    if (!(hdr->flags & (VFIO_USER_NO_REPLY | VFIO_USER_REPLY))) {
+        error_printf("vfio_user_send_async on sync message\n");
+        return;
+    }
+
+    QEMU_LOCK_GUARD(&proxy->lock);
+
+    msg = vfio_user_getmsg(proxy, hdr, fds);
+    msg->id = hdr->id;
+    msg->rsize = 0;
+    msg->type = VFIO_MSG_ASYNC;
+
+    ret = vfio_user_send_queued(proxy, msg);
+    if (ret < 0) {
+        vfio_user_recycle(proxy, msg);
+    }
+}
+
 static void vfio_user_send_wait(VFIOUserProxy *proxy, VFIOUserHdr *hdr,
                                 VFIOUserFDs *fds, int rsize, bool nobql)
 {
@@ -1179,6 +1208,73 @@ static int vfio_user_get_region_info(VFIOUserProxy 
*proxy,
     return 0;
 }
 
+static int vfio_user_region_read(VFIOUserProxy *proxy, uint8_t index,
+                                 off_t offset, uint32_t count, void *data)
+{
+    g_autofree VFIOUserRegionRW *msgp = NULL;
+    int size = sizeof(*msgp) + count;
+
+    if (count > proxy->max_xfer_size) {
+        return -EINVAL;
+    }
+
+    msgp = g_malloc0(size);
+    vfio_user_request_msg(&msgp->hdr, VFIO_USER_REGION_READ, sizeof(*msgp), 0);
+    msgp->offset = offset;
+    msgp->region = index;
+    msgp->count = count;
+    trace_vfio_user_region_rw(msgp->region, msgp->offset, msgp->count);
+
+    vfio_user_send_wait(proxy, &msgp->hdr, NULL, size, false);
+    if (msgp->hdr.flags & VFIO_USER_ERROR) {
+        return -msgp->hdr.error_reply;
+    } else if (msgp->count > count) {
+        return -E2BIG;
+    } else {
+        memcpy(data, &msgp->data, msgp->count);
+    }
+
+    return msgp->count;
+}
+
+static int vfio_user_region_write(VFIOUserProxy *proxy, uint8_t index,
+                                  off_t offset, uint32_t count, void *data,
+                                  bool post)
+{
+    VFIOUserRegionRW *msgp = NULL;
+    int flags = post ? VFIO_USER_NO_REPLY : 0;
+    int size = sizeof(*msgp) + count;
+    int ret;
+
+    if (count > proxy->max_xfer_size) {
+        return -EINVAL;
+    }
+
+    msgp = g_malloc0(size);
+    vfio_user_request_msg(&msgp->hdr, VFIO_USER_REGION_WRITE, size, flags);
+    msgp->offset = offset;
+    msgp->region = index;
+    msgp->count = count;
+    memcpy(&msgp->data, data, count);
+    trace_vfio_user_region_rw(msgp->region, msgp->offset, msgp->count);
+
+    /* async send will free msg after it's sent */
+    if (post && !(proxy->flags & VFIO_PROXY_NO_POST)) {
+        vfio_user_send_async(proxy, &msgp->hdr, NULL);
+        return count;
+    }
+
+    vfio_user_send_wait(proxy, &msgp->hdr, NULL, 0, false);
+    if (msgp->hdr.flags & VFIO_USER_ERROR) {
+        ret = -msgp->hdr.error_reply;
+    } else {
+        ret = count;
+    }
+
+    g_free(msgp);
+    return ret;
+}
+
 
 /*
  * Socket-based io_ops
@@ -1208,6 +1304,22 @@ static int vfio_user_io_get_region_info(VFIODevice 
*vbasedev,
     return 0;
 }
 
+static int vfio_user_io_region_read(VFIODevice *vbasedev, uint8_t index,
+                                    off_t off, uint32_t size, void *data)
+{
+    return vfio_user_region_read(vbasedev->proxy, index, off, size, data);
+}
+
+static int vfio_user_io_region_write(VFIODevice *vbasedev, uint8_t index,
+                                     off_t off, unsigned size, void *data,
+                                     bool post)
+{
+    return vfio_user_region_write(vbasedev->proxy, index, off, size, data,
+                                  post);
+}
+
 VFIODeviceIO vfio_dev_io_sock = {
     .get_region_info = vfio_user_io_get_region_info,
+    .region_read = vfio_user_io_region_read,
+    .region_write = vfio_user_io_region_write,
 };
diff --git a/hw/vfio/trace-events b/hw/vfio/trace-events
index 939113a..1f3688f 100644
--- a/hw/vfio/trace-events
+++ b/hw/vfio/trace-events
@@ -175,3 +175,4 @@ vfio_user_send_write(uint16_t id, int wrote) " id 0x%x 
wrote 0x%x"
 vfio_user_version(uint16_t major, uint16_t minor, const char *caps) " major %d 
minor %d caps: %s"
 vfio_user_get_info(uint32_t nregions, uint32_t nirqs) " #regions %d #irqs %d"
 vfio_user_get_region_info(uint32_t index, uint32_t flags, uint64_t size) " 
index %d flags 0x%x size 0x%"PRIx64
+vfio_user_region_rw(uint32_t region, uint64_t off, uint32_t count) " region %d 
offset 0x%"PRIx64" count %d"
-- 
1.9.4