From c62b91e5804e7d2b1e8e253fc4031b4ea67a11f7 Mon Sep 17 00:00:00 2001 From: Marc-André Lureau Date: Fri, 9 Oct 2015 17:17:29 +0200 Subject: vhost-user: document migration log MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Signed-off-by: Marc-André Lureau Reviewed-by: Michael S. Tsirkin Signed-off-by: Michael S. Tsirkin Tested-by: Thibaut Collet --- docs/specs/vhost-user.txt | 48 +++++++++++++++++++++++++++++++++++++++++++++-- 1 file changed, 46 insertions(+), 2 deletions(-) (limited to 'docs/specs') diff --git a/docs/specs/vhost-user.txt b/docs/specs/vhost-user.txt index 4eadad1d6b..e0292a0e65 100644 --- a/docs/specs/vhost-user.txt +++ b/docs/specs/vhost-user.txt @@ -115,11 +115,13 @@ the ones that do: * VHOST_GET_FEATURES * VHOST_GET_PROTOCOL_FEATURES * VHOST_GET_VRING_BASE + * VHOST_SET_LOG_BASE (if VHOST_USER_PROTOCOL_F_LOG_SHMFD) There are several messages that the master sends with file descriptors passed in the ancillary data: * VHOST_SET_MEM_TABLE + * VHOST_SET_LOG_BASE (if VHOST_USER_PROTOCOL_F_LOG_SHMFD) * VHOST_SET_LOG_FD * VHOST_SET_VRING_KICK * VHOST_SET_VRING_CALL @@ -140,8 +142,7 @@ Multiple queue support Multiple queue is treated as a protocol extension, hence the slave has to implement protocol features first. The multiple queues feature is supported -only when the protocol feature VHOST_USER_PROTOCOL_F_MQ (bit 0) is set: -#define VHOST_USER_PROTOCOL_F_MQ 0 +only when the protocol feature VHOST_USER_PROTOCOL_F_MQ (bit 0) is set. The max number of queues the slave supports can be queried with message VHOST_USER_GET_PROTOCOL_FEATURES. Master should stop when the number of @@ -152,6 +153,48 @@ queue in the sent message to identify a specified queue. One queue pair is enabled initially. More queues are enabled dynamically, by sending message VHOST_USER_SET_VRING_ENABLE. +Migration +--------- + +During live migration, the master may need to track the modifications +the slave makes to the memory mapped regions. The client should mark +the dirty pages in a log. Once it complies to this logging, it may +declare the VHOST_F_LOG_ALL vhost feature. + +All the modifications to memory pointed by vring "descriptor" should +be marked. Modifications to "used" vring should be marked if +VHOST_VRING_F_LOG is part of ring's features. + +Dirty pages are of size: +#define VHOST_LOG_PAGE 0x1000 + +The log memory fd is provided in the ancillary data of +VHOST_USER_SET_LOG_BASE message when the slave has +VHOST_USER_PROTOCOL_F_LOG_SHMFD protocol feature. + +The size of the log may be computed by using all the known guest +addresses. The log covers from address 0 to the maximum of guest +regions. In pseudo-code, to mark page at "addr" as dirty: + +page = addr / VHOST_LOG_PAGE +log[page / 8] |= 1 << page % 8 + +Use atomic operations, as the log may be concurrently manipulated. + +VHOST_USER_SET_LOG_FD is an optional message with an eventfd in +ancillary data, it may be used to inform the master that the log has +been modified. + +Once the source has finished migration, VHOST_USER_RESET_OWNER message +will be sent by the source. No further update must be done before the +destination takes over with new regions & rings. + +Protocol features +----------------- + +#define VHOST_USER_PROTOCOL_F_MQ 0 +#define VHOST_USER_PROTOCOL_F_LOG_SHMFD 1 + Message types ------------- @@ -236,6 +279,7 @@ Message types Id: 6 Equivalent ioctl: VHOST_SET_LOG_BASE Master payload: u64 + Slave payload: N/A Sets the logging base address. -- cgit 1.4.1 From 3e866365e1eb6bcfa2d01c21debb05b9e47a47f7 Mon Sep 17 00:00:00 2001 From: Thibaut Collet Date: Fri, 9 Oct 2015 17:17:32 +0200 Subject: vhost user: add rarp sending after live migration for legacy guest MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit A new vhost user message is added to allow QEMU to ask to vhost user backend to broadcast a fake RARP after live migration for guest without GUEST_ANNOUNCE capability. This new message is sent only if the backend supports the new VHOST_USER_PROTOCOL_F_RARP protocol feature. The payload of this new message is the MAC address of the guest (not known by the backend). The MAC address is copied in the first 6 bytes of a u64 to avoid to create a new payload message type. This new message has no equivalent ioctl so a new callback is added in the userOps structure to send the request. Upon reception of this new message the vhost user backend must generate and broadcast a fake RARP request to notify the migration is terminated. Signed-off-by: Thibaut Collet [Rebased and fixed checkpatch errors - Marc-André] Signed-off-by: Marc-André Lureau Reviewed-by: Michael S. Tsirkin Signed-off-by: Michael S. Tsirkin Tested-by: Thibaut Collet --- docs/specs/vhost-user.txt | 15 +++++++++++++++ hw/net/vhost_net.c | 17 +++++++++++++++++ hw/virtio/vhost-user.c | 32 +++++++++++++++++++++++++++++++- include/hw/virtio/vhost-backend.h | 3 +++ include/net/vhost_net.h | 1 + net/vhost-user.c | 24 ++++++++++++++++++++++-- 6 files changed, 89 insertions(+), 3 deletions(-) (limited to 'docs/specs') diff --git a/docs/specs/vhost-user.txt b/docs/specs/vhost-user.txt index e0292a0e65..e0d71e27e6 100644 --- a/docs/specs/vhost-user.txt +++ b/docs/specs/vhost-user.txt @@ -194,6 +194,7 @@ Protocol features #define VHOST_USER_PROTOCOL_F_MQ 0 #define VHOST_USER_PROTOCOL_F_LOG_SHMFD 1 +#define VHOST_USER_PROTOCOL_F_RARP 2 Message types ------------- @@ -381,3 +382,17 @@ Message types Master payload: vring state description Signal slave to enable or disable corresponding vring. + + * VHOST_USER_SEND_RARP + + Id: 19 + Equivalent ioctl: N/A + Master payload: u64 + + Ask vhost user backend to broadcast a fake RARP to notify the migration + is terminated for guest that does not support GUEST_ANNOUNCE. + Only legal if feature bit VHOST_USER_F_PROTOCOL_FEATURES is present in + VHOST_USER_GET_FEATURES and protocol feature bit VHOST_USER_PROTOCOL_F_RARP + is present in VHOST_USER_GET_PROTOCOL_FEATURES. + The first 6 bytes of the payload contain the mac address of the guest to + allow the vhost user backend to construct and broadcast the fake RARP. diff --git a/hw/net/vhost_net.c b/hw/net/vhost_net.c index 840f443065..d91b7b155e 100644 --- a/hw/net/vhost_net.c +++ b/hw/net/vhost_net.c @@ -388,6 +388,18 @@ void vhost_net_cleanup(struct vhost_net *net) g_free(net); } +int vhost_net_notify_migration_done(struct vhost_net *net, char* mac_addr) +{ + const VhostOps *vhost_ops = net->dev.vhost_ops; + int r = -1; + + if (vhost_ops->vhost_migration_done) { + r = vhost_ops->vhost_migration_done(&net->dev, mac_addr); + } + + return r; +} + bool vhost_net_virtqueue_pending(VHostNetState *net, int idx) { return vhost_virtqueue_pending(&net->dev, idx); @@ -479,6 +491,11 @@ void vhost_net_virtqueue_mask(VHostNetState *net, VirtIODevice *dev, { } +int vhost_net_notify_migration_done(struct vhost_net *net, char* mac_addr) +{ + return -1; +} + VHostNetState *get_vhost_net(NetClientState *nc) { return 0; diff --git a/hw/virtio/vhost-user.c b/hw/virtio/vhost-user.c index 16d8e80a2a..d804c5f565 100644 --- a/hw/virtio/vhost-user.c +++ b/hw/virtio/vhost-user.c @@ -10,6 +10,7 @@ #include "hw/virtio/vhost.h" #include "hw/virtio/vhost-backend.h" +#include "hw/virtio/virtio-net.h" #include "sysemu/char.h" #include "sysemu/kvm.h" #include "qemu/error-report.h" @@ -27,9 +28,10 @@ #define VHOST_MEMORY_MAX_NREGIONS 8 #define VHOST_USER_F_PROTOCOL_FEATURES 30 -#define VHOST_USER_PROTOCOL_FEATURE_MASK 0x3ULL +#define VHOST_USER_PROTOCOL_FEATURE_MASK 0x7ULL #define VHOST_USER_PROTOCOL_F_MQ 0 #define VHOST_USER_PROTOCOL_F_LOG_SHMFD 1 +#define VHOST_USER_PROTOCOL_F_RARP 2 typedef enum VhostUserRequest { VHOST_USER_NONE = 0, @@ -51,6 +53,7 @@ typedef enum VhostUserRequest { VHOST_USER_SET_PROTOCOL_FEATURES = 16, VHOST_USER_GET_QUEUE_NUM = 17, VHOST_USER_SET_VRING_ENABLE = 18, + VHOST_USER_SEND_RARP = 19, VHOST_USER_MAX } VhostUserRequest; @@ -566,6 +569,32 @@ static bool vhost_user_requires_shm_log(struct vhost_dev *dev) VHOST_USER_PROTOCOL_F_LOG_SHMFD); } +static int vhost_user_migration_done(struct vhost_dev *dev, char* mac_addr) +{ + VhostUserMsg msg = { 0 }; + int err; + + assert(dev->vhost_ops->backend_type == VHOST_BACKEND_TYPE_USER); + + /* If guest supports GUEST_ANNOUNCE do nothing */ + if (virtio_has_feature(dev->acked_features, VIRTIO_NET_F_GUEST_ANNOUNCE)) { + return 0; + } + + /* if backend supports VHOST_USER_PROTOCOL_F_RARP ask it to send the RARP */ + if (virtio_has_feature(dev->protocol_features, + VHOST_USER_PROTOCOL_F_RARP)) { + msg.request = VHOST_USER_SEND_RARP; + msg.flags = VHOST_USER_VERSION; + memcpy((char *)&msg.u64, mac_addr, 6); + msg.size = sizeof(m.u64); + + err = vhost_user_write(dev, &msg, NULL, 0); + return err; + } + return -1; +} + const VhostOps user_ops = { .backend_type = VHOST_BACKEND_TYPE_USER, .vhost_backend_init = vhost_user_init, @@ -587,4 +616,5 @@ const VhostOps user_ops = { .vhost_get_vq_index = vhost_user_get_vq_index, .vhost_set_vring_enable = vhost_user_set_vring_enable, .vhost_requires_shm_log = vhost_user_requires_shm_log, + .vhost_migration_done = vhost_user_migration_done, }; diff --git a/include/hw/virtio/vhost-backend.h b/include/hw/virtio/vhost-backend.h index ad1948101d..c59cc81915 100644 --- a/include/hw/virtio/vhost-backend.h +++ b/include/hw/virtio/vhost-backend.h @@ -68,6 +68,8 @@ typedef int (*vhost_get_vq_index_op)(struct vhost_dev *dev, int idx); typedef int (*vhost_set_vring_enable_op)(struct vhost_dev *dev, int enable); typedef bool (*vhost_requires_shm_log_op)(struct vhost_dev *dev); +typedef int (*vhost_migration_done_op)(struct vhost_dev *dev, + char *mac_addr); typedef struct VhostOps { VhostBackendType backend_type; @@ -94,6 +96,7 @@ typedef struct VhostOps { vhost_get_vq_index_op vhost_get_vq_index; vhost_set_vring_enable_op vhost_set_vring_enable; vhost_requires_shm_log_op vhost_requires_shm_log; + vhost_migration_done_op vhost_migration_done; } VhostOps; extern const VhostOps user_ops; diff --git a/include/net/vhost_net.h b/include/net/vhost_net.h index 0188c4d02d..3389b410d8 100644 --- a/include/net/vhost_net.h +++ b/include/net/vhost_net.h @@ -27,6 +27,7 @@ void vhost_net_ack_features(VHostNetState *net, uint64_t features); bool vhost_net_virtqueue_pending(VHostNetState *net, int n); void vhost_net_virtqueue_mask(VHostNetState *net, VirtIODevice *dev, int idx, bool mask); +int vhost_net_notify_migration_done(VHostNetState *net, char* mac_addr); VHostNetState *get_vhost_net(NetClientState *nc); int vhost_set_vring_enable(NetClientState * nc, int enable); diff --git a/net/vhost-user.c b/net/vhost-user.c index b067524f2b..17b5c2a722 100644 --- a/net/vhost-user.c +++ b/net/vhost-user.c @@ -106,9 +106,29 @@ err: static ssize_t vhost_user_receive(NetClientState *nc, const uint8_t *buf, size_t size) { - /* Discard the request that is received and managed by backend - * by an other way. + /* In case of RARP (message size is 60) notify backup to send a fake RARP. + This fake RARP will be sent by backend only for guest + without GUEST_ANNOUNCE capability. */ + if (size == 60) { + VhostUserState *s = DO_UPCAST(VhostUserState, nc, nc); + int r; + static int display_rarp_failure = 1; + char mac_addr[6]; + + /* extract guest mac address from the RARP message */ + memcpy(mac_addr, &buf[6], 6); + + r = vhost_net_notify_migration_done(s->vhost_net, mac_addr); + + if ((r != 0) && (display_rarp_failure)) { + fprintf(stderr, + "Vhost user backend fails to broadcast fake RARP\n"); + fflush(stderr); + display_rarp_failure = 0; + } + } + return size; } -- cgit 1.4.1