[dpdk-dev] [PATCH 08/12] vhost: send userfault range addresses back to qemu

[Maxime Coquelin]

Signed-off-by: Dr. David Alan Gilbert <dgilb...@redhat.com>
Signed-off-by: Maxime Coquelin <maxime.coque...@redhat.com>
---
 lib/librte_vhost/vhost_user.c | 52 ++++++++++++++++++++++++++++++++---
 1 file changed, 48 insertions(+), 4 deletions(-)

diff --git a/lib/librte_vhost/vhost_user.c b/lib/librte_vhost/vhost_user.c
index 37b5edcd7..766df7a58 100644
--- a/lib/librte_vhost/vhost_user.c
+++ b/lib/librte_vhost/vhost_user.c
@@ -77,6 +77,11 @@ static const char *vhost_message_str[VHOST_USER_MAX] = {
        [VHOST_USER_POSTCOPY_LISTEN]  = "VHOST_USER_POSTCOPY_LISTEN",
 };
 
+static int
+send_vhost_reply(int sockfd, struct VhostUserMsg *msg);
+static int
+read_vhost_message(int sockfd, struct VhostUserMsg *msg);
+
 static uint64_t
 get_blk_size(int fd)
 {
@@ -786,7 +791,8 @@ vhost_memory_changed(struct VhostUserMemory *new,
 }
 
 static int
-vhost_user_set_mem_table(struct virtio_net **pdev, struct VhostUserMsg *pmsg)
+vhost_user_set_mem_table(struct virtio_net **pdev, struct VhostUserMsg *pmsg,
+                       int main_fd)
 {
        struct virtio_net *dev = *pdev;
        struct VhostUserMemory *memory = &pmsg->payload.memory;
@@ -930,10 +936,48 @@ vhost_user_set_mem_table(struct virtio_net **pdev, struct 
VhostUserMsg *pmsg)
                        mmap_offset);
 
                if (dev->postcopy_listening) {
+                       /*
+                        * We haven't a better way right now than sharing
+                        * DPDK's virtual address with Qemu, so that Qemu can
+                        * retreive the region offset when handling userfaults.
+                        */
+                       memory->regions[i].userspace_addr =
+                               reg->host_user_addr;
+               }
+       }
+       if (dev->postcopy_listening) {
+               /* Send the addresses back to qemu */
+               pmsg->fd_num = 0;
+               send_vhost_reply(main_fd, pmsg);
+
+               /* Wait for qemu to acknolwedge it's got the addresses
+                * we've got to wait before we're allowed to generate faults.
+                */
+               VhostUserMsg ack_msg;
+               if (read_vhost_message(main_fd, &ack_msg) <= 0) {
+                       RTE_LOG(ERR, VHOST_CONFIG,
+                                       "Failed to read qemu ack on postcopy 
set-mem-table\n");
+                       goto err_mmap;
+               }
+               if (ack_msg.request.master != VHOST_USER_SET_MEM_TABLE) {
+                       RTE_LOG(ERR, VHOST_CONFIG,
+                                       "Bad qemu ack on postcopy set-mem-table 
(%d)\n",
+                                       ack_msg.request.master);
+                       goto err_mmap;
+               }
+
+               /* Now userfault register and we can use the memory */
+               for (i = 0; i < memory->nregions; i++) {
+                       reg = &dev->mem->regions[i];
                        struct uffdio_register reg_struct;
 
-                       reg_struct.range.start = (uint64_t)(uintptr_t)mmap_addr;
-                       reg_struct.range.len = mmap_size;
+                       /*
+                        * Let's register all the mmap'ed area to ensure
+                        * alignement on page boundary.
+                        */
+                       reg_struct.range.start =
+                               (uint64_t)(uintptr_t)reg->mmap_addr;
+                       reg_struct.range.len = reg->mmap_size;
                        reg_struct.mode = UFFDIO_REGISTER_MODE_MISSING;
 
                        if (ioctl(dev->postcopy_ufd, UFFDIO_REGISTER,
@@ -1750,7 +1794,7 @@ vhost_user_msg_handler(int vid, int fd)
                break;
 
        case VHOST_USER_SET_MEM_TABLE:
-               ret = vhost_user_set_mem_table(&dev, &msg);
+               ret = vhost_user_set_mem_table(&dev, &msg, fd);
                break;
 
        case VHOST_USER_SET_LOG_BASE:
-- 
2.17.1