diff options
-rw-r--r-- | drivers/misc/vmw_vmci/vmci_driver.c | 67 | ||||
-rw-r--r-- | drivers/misc/vmw_vmci/vmci_driver.h | 2 | ||||
-rw-r--r-- | drivers/misc/vmw_vmci/vmci_guest.c | 2 | ||||
-rw-r--r-- | drivers/misc/vmw_vmci/vmci_host.c | 7 | ||||
-rw-r--r-- | drivers/vhost/vsock.c | 102 | ||||
-rw-r--r-- | include/linux/virtio_vsock.h | 18 | ||||
-rw-r--r-- | include/linux/vm_sockets.h | 15 | ||||
-rw-r--r-- | include/linux/vmw_vmci_api.h | 2 | ||||
-rw-r--r-- | include/net/af_vsock.h | 45 | ||||
-rw-r--r-- | include/net/vsock_addr.h | 2 | ||||
-rw-r--r-- | net/vmw_vsock/af_vsock.c | 382 | ||||
-rw-r--r-- | net/vmw_vsock/hyperv_transport.c | 70 | ||||
-rw-r--r-- | net/vmw_vsock/virtio_transport.c | 177 | ||||
-rw-r--r-- | net/vmw_vsock/virtio_transport_common.c | 166 | ||||
-rw-r--r-- | net/vmw_vsock/vmci_transport.c | 140 | ||||
-rw-r--r-- | net/vmw_vsock/vmci_transport.h | 3 | ||||
-rw-r--r-- | net/vmw_vsock/vmci_transport_notify.h | 1 |
17 files changed, 679 insertions, 522 deletions
diff --git a/drivers/misc/vmw_vmci/vmci_driver.c b/drivers/misc/vmw_vmci/vmci_driver.c index 819e35995d32..95fed4664a2d 100644 --- a/drivers/misc/vmw_vmci/vmci_driver.c +++ b/drivers/misc/vmw_vmci/vmci_driver.c @@ -28,6 +28,10 @@ MODULE_PARM_DESC(disable_guest, static bool vmci_guest_personality_initialized; static bool vmci_host_personality_initialized; +static DEFINE_MUTEX(vmci_vsock_mutex); /* protects vmci_vsock_transport_cb */ +static vmci_vsock_cb vmci_vsock_transport_cb; +bool vmci_vsock_cb_host_called; + /* * vmci_get_context_id() - Gets the current context ID. * @@ -45,6 +49,69 @@ u32 vmci_get_context_id(void) } EXPORT_SYMBOL_GPL(vmci_get_context_id); +/* + * vmci_register_vsock_callback() - Register the VSOCK vmci_transport callback. + * + * The callback will be called when the first host or guest becomes active, + * or if they are already active when this function is called. + * To unregister the callback, call this function with NULL parameter. + * + * Returns 0 on success. -EBUSY if a callback is already registered. + */ +int vmci_register_vsock_callback(vmci_vsock_cb callback) +{ + int err = 0; + + mutex_lock(&vmci_vsock_mutex); + + if (vmci_vsock_transport_cb && callback) { + err = -EBUSY; + goto out; + } + + vmci_vsock_transport_cb = callback; + + if (!vmci_vsock_transport_cb) { + vmci_vsock_cb_host_called = false; + goto out; + } + + if (vmci_guest_code_active()) + vmci_vsock_transport_cb(false); + + if (vmci_host_users() > 0) { + vmci_vsock_cb_host_called = true; + vmci_vsock_transport_cb(true); + } + +out: + mutex_unlock(&vmci_vsock_mutex); + return err; +} +EXPORT_SYMBOL_GPL(vmci_register_vsock_callback); + +void vmci_call_vsock_callback(bool is_host) +{ + mutex_lock(&vmci_vsock_mutex); + + if (!vmci_vsock_transport_cb) + goto out; + + /* In the host, this function could be called multiple times, + * but we want to register it only once. + */ + if (is_host) { + if (vmci_vsock_cb_host_called) + goto out; + + vmci_vsock_cb_host_called = true; + } + + vmci_vsock_transport_cb(is_host); +out: + mutex_unlock(&vmci_vsock_mutex); +} + static int __init vmci_drv_init(void) { int vmci_err; diff --git a/drivers/misc/vmw_vmci/vmci_driver.h b/drivers/misc/vmw_vmci/vmci_driver.h index aab81b67670c..990682480bf6 100644 --- a/drivers/misc/vmw_vmci/vmci_driver.h +++ b/drivers/misc/vmw_vmci/vmci_driver.h @@ -36,10 +36,12 @@ extern struct pci_dev *vmci_pdev; u32 vmci_get_context_id(void); int vmci_send_datagram(struct vmci_datagram *dg); +void vmci_call_vsock_callback(bool is_host); int vmci_host_init(void); void vmci_host_exit(void); bool vmci_host_code_active(void); +int vmci_host_users(void); int vmci_guest_init(void); void vmci_guest_exit(void); diff --git a/drivers/misc/vmw_vmci/vmci_guest.c b/drivers/misc/vmw_vmci/vmci_guest.c index 7a84a48c75da..cc8eeb361fcd 100644 --- a/drivers/misc/vmw_vmci/vmci_guest.c +++ b/drivers/misc/vmw_vmci/vmci_guest.c @@ -637,6 +637,8 @@ static int vmci_guest_probe_device(struct pci_dev *pdev, vmci_dev->iobase + VMCI_CONTROL_ADDR); pci_set_drvdata(pdev, vmci_dev); + + vmci_call_vsock_callback(false); return 0; err_free_irq: diff --git a/drivers/misc/vmw_vmci/vmci_host.c b/drivers/misc/vmw_vmci/vmci_host.c index 833e2bd248a5..ff3c396146ff 100644 --- a/drivers/misc/vmw_vmci/vmci_host.c +++ b/drivers/misc/vmw_vmci/vmci_host.c @@ -108,6 +108,11 @@ bool vmci_host_code_active(void) atomic_read(&vmci_host_active_users) > 0); } +int vmci_host_users(void) +{ + return atomic_read(&vmci_host_active_users); +} + /* * Called on open of /dev/vmci. */ @@ -338,6 +343,8 @@ static int vmci_host_do_init_context(struct vmci_host_dev *vmci_host_dev, vmci_host_dev->ct_type = VMCIOBJ_CONTEXT; atomic_inc(&vmci_host_active_users); + vmci_call_vsock_callback(true); + retval = 0; out: diff --git a/drivers/vhost/vsock.c b/drivers/vhost/vsock.c index 9f57736fe15e..dde392b91bb3 100644 --- a/drivers/vhost/vsock.c +++ b/drivers/vhost/vsock.c @@ -384,6 +384,49 @@ static bool vhost_vsock_more_replies(struct vhost_vsock *vsock) return val < vq->num; } +static struct virtio_transport vhost_transport = { + .transport = { + .module = THIS_MODULE, + + .get_local_cid = vhost_transport_get_local_cid, + + .init = virtio_transport_do_socket_init, + .destruct = virtio_transport_destruct, + .release = virtio_transport_release, + .connect = virtio_transport_connect, + .shutdown = virtio_transport_shutdown, + .cancel_pkt = vhost_transport_cancel_pkt, + + .dgram_enqueue = virtio_transport_dgram_enqueue, + .dgram_dequeue = virtio_transport_dgram_dequeue, + .dgram_bind = virtio_transport_dgram_bind, + .dgram_allow = virtio_transport_dgram_allow, + + .stream_enqueue = virtio_transport_stream_enqueue, + .stream_dequeue = virtio_transport_stream_dequeue, + .stream_has_data = virtio_transport_stream_has_data, + .stream_has_space = virtio_transport_stream_has_space, + .stream_rcvhiwat = virtio_transport_stream_rcvhiwat, + .stream_is_active = virtio_transport_stream_is_active, + .stream_allow = virtio_transport_stream_allow, + + .notify_poll_in = virtio_transport_notify_poll_in, + .notify_poll_out = virtio_transport_notify_poll_out, + .notify_recv_init = virtio_transport_notify_recv_init, + .notify_recv_pre_block = virtio_transport_notify_recv_pre_block, + .notify_recv_pre_dequeue = virtio_transport_notify_recv_pre_dequeue, + .notify_recv_post_dequeue = virtio_transport_notify_recv_post_dequeue, + .notify_send_init = virtio_transport_notify_send_init, + .notify_send_pre_block = virtio_transport_notify_send_pre_block, + .notify_send_pre_enqueue = virtio_transport_notify_send_pre_enqueue, + .notify_send_post_enqueue = virtio_transport_notify_send_post_enqueue, + .notify_buffer_size = virtio_transport_notify_buffer_size, + + }, + + .send_pkt = vhost_transport_send_pkt, +}; + static void vhost_vsock_handle_tx_kick(struct vhost_work *work) { struct vhost_virtqueue *vq = container_of(work, struct vhost_virtqueue, @@ -438,7 +481,7 @@ static void vhost_vsock_handle_tx_kick(struct vhost_work *work) /* Only accept correctly addressed packets */ if (le64_to_cpu(pkt->hdr.src_cid) == vsock->guest_cid) - virtio_transport_recv_pkt(pkt); + virtio_transport_recv_pkt(&vhost_transport, pkt); else virtio_transport_free_pkt(pkt); @@ -675,6 +718,12 @@ static int vhost_vsock_set_cid(struct vhost_vsock *vsock, u64 guest_cid) if (guest_cid > U32_MAX) return -EINVAL; + /* Refuse if CID is assigned to the guest->host transport (i.e. nested + * VM), to make the loopback work. + */ + if (vsock_find_cid(guest_cid)) + return -EADDRINUSE; + /* Refuse if CID is already in use */ mutex_lock(&vhost_vsock_mutex); other = vhost_vsock_get(guest_cid); @@ -786,57 +835,12 @@ static struct miscdevice vhost_vsock_misc = { .fops = &vhost_vsock_fops, }; -static struct virtio_transport vhost_transport = { - .transport = { - .get_local_cid = vhost_transport_get_local_cid, - - .init = virtio_transport_do_socket_init, - .destruct = virtio_transport_destruct, - .release = virtio_transport_release, - .connect = virtio_transport_connect, - .shutdown = virtio_transport_shutdown, - .cancel_pkt = vhost_transport_cancel_pkt, - - .dgram_enqueue = virtio_transport_dgram_enqueue, - .dgram_dequeue = virtio_transport_dgram_dequeue, - .dgram_bind = virtio_transport_dgram_bind, - .dgram_allow = virtio_transport_dgram_allow, - - .stream_enqueue = virtio_transport_stream_enqueue, - .stream_dequeue = virtio_transport_stream_dequeue, - .stream_has_data = virtio_transport_stream_has_data, - .stream_has_space = virtio_transport_stream_has_space, - .stream_rcvhiwat = virtio_transport_stream_rcvhiwat, - .stream_is_active = virtio_transport_stream_is_active, - .stream_allow = virtio_transport_stream_allow, - - .notify_poll_in = virtio_transport_notify_poll_in, - .notify_poll_out = virtio_transport_notify_poll_out, - .notify_recv_init = virtio_transport_notify_recv_init, - .notify_recv_pre_block = virtio_transport_notify_recv_pre_block, - .notify_recv_pre_dequeue = virtio_transport_notify_recv_pre_dequeue, - .notify_recv_post_dequeue = virtio_transport_notify_recv_post_dequeue, - .notify_send_init = virtio_transport_notify_send_init, - .notify_send_pre_block = virtio_transport_notify_send_pre_block, - .notify_send_pre_enqueue = virtio_transport_notify_send_pre_enqueue, - .notify_send_post_enqueue = virtio_transport_notify_send_post_enqueue, - - .set_buffer_size = virtio_transport_set_buffer_size, - .set_min_buffer_size = virtio_transport_set_min_buffer_size, - .set_max_buffer_size = virtio_transport_set_max_buffer_size, - .get_buffer_size = virtio_transport_get_buffer_size, - .get_min_buffer_size = virtio_transport_get_min_buffer_size, - .get_max_buffer_size = virtio_transport_get_max_buffer_size, - }, - - .send_pkt = vhost_transport_send_pkt, -}; - static int __init vhost_vsock_init(void) { int ret; - ret = vsock_core_init(&vhost_transport.transport); + ret = vsock_core_register(&vhost_transport.transport, + VSOCK_TRANSPORT_F_H2G); if (ret < 0) return ret; return misc_register(&vhost_vsock_misc); @@ -845,7 +849,7 @@ static int __init vhost_vsock_init(void) static void __exit vhost_vsock_exit(void) { misc_deregister(&vhost_vsock_misc); - vsock_core_exit(); + vsock_core_unregister(&vhost_transport.transport); }; module_init(vhost_vsock_init); diff --git a/include/linux/virtio_vsock.h b/include/linux/virtio_vsock.h index 07875ccc7bb5..71c81e0dc8f2 100644 --- a/include/linux/virtio_vsock.h +++ b/include/linux/virtio_vsock.h @@ -7,9 +7,6 @@ #include <net/sock.h> #include <net/af_vsock.h> -#define VIRTIO_VSOCK_DEFAULT_MIN_BUF_SIZE 128 -#define VIRTIO_VSOCK_DEFAULT_BUF_SIZE (1024 * 256) -#define VIRTIO_VSOCK_DEFAULT_MAX_BUF_SIZE (1024 * 256) #define VIRTIO_VSOCK_DEFAULT_RX_BUF_SIZE (1024 * 4) #define VIRTIO_VSOCK_MAX_BUF_SIZE 0xFFFFFFFFUL #define VIRTIO_VSOCK_MAX_PKT_BUF_SIZE (1024 * 64) @@ -25,11 +22,6 @@ enum { struct virtio_vsock_sock { struct vsock_sock *vsk; - /* Protected by lock_sock(sk_vsock(trans->vsk)) */ - u32 buf_size; - u32 buf_size_min; - u32 buf_size_max; - spinlock_t tx_lock; spinlock_t rx_lock; @@ -92,12 +84,6 @@ s64 virtio_transport_stream_has_space(struct vsock_sock *vsk); int virtio_transport_do_socket_init(struct vsock_sock *vsk, struct vsock_sock *psk); -u64 virtio_transport_get_buffer_size(struct vsock_sock *vsk); -u64 virtio_transport_get_min_buffer_size(struct vsock_sock *vsk); -u64 virtio_transport_get_max_buffer_size(struct vsock_sock *vsk); -void virtio_transport_set_buffer_size(struct vsock_sock *vsk, u64 val); -void virtio_transport_set_min_buffer_size(struct vsock_sock *vsk, u64 val); -void virtio_transport_set_max_buffer_size(struct vsock_sock *vs, u64 val); int virtio_transport_notify_poll_in(struct vsock_sock *vsk, size_t target, @@ -124,6 +110,7 @@ int virtio_transport_notify_send_pre_enqueue(struct vsock_sock *vsk, struct vsock_transport_send_notify_data *data); int virtio_transport_notify_send_post_enqueue(struct vsock_sock *vsk, ssize_t written, struct vsock_transport_send_notify_data *data); +void virtio_transport_notify_buffer_size(struct vsock_sock *vsk, u64 *val); u64 virtio_transport_stream_rcvhiwat(struct vsock_sock *vsk); bool virtio_transport_stream_is_active(struct vsock_sock *vsk); @@ -150,7 +137,8 @@ virtio_transport_dgram_enqueue(struct vsock_sock *vsk, void virtio_transport_destruct(struct vsock_sock *vsk); -void virtio_transport_recv_pkt(struct virtio_vsock_pkt *pkt); +void virtio_transport_recv_pkt(struct virtio_transport *t, + struct virtio_vsock_pkt *pkt); void virtio_transport_free_pkt(struct virtio_vsock_pkt *pkt); void virtio_transport_inc_tx_pkt(struct virtio_vsock_sock *vvs, struct virtio_vsock_pkt *pkt); u32 virtio_transport_get_credit(struct virtio_vsock_sock *vvs, u32 wanted); diff --git a/include/linux/vm_sockets.h b/include/linux/vm_sockets.h deleted file mode 100644 index 33f1a2ecd905..000000000000 --- a/include/linux/vm_sockets.h +++ /dev/null @@ -1,15 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0-only */ -/* - * VMware vSockets Driver - * - * Copyright (C) 2007-2013 VMware, Inc. All rights reserved. - */ - -#ifndef _VM_SOCKETS_H -#define _VM_SOCKETS_H - -#include <uapi/linux/vm_sockets.h> - -int vm_sockets_get_local_cid(void); - -#endif /* _VM_SOCKETS_H */ diff --git a/include/linux/vmw_vmci_api.h b/include/linux/vmw_vmci_api.h index acd9fafe4fc6..f28907345c80 100644 --- a/include/linux/vmw_vmci_api.h +++ b/include/linux/vmw_vmci_api.h @@ -19,6 +19,7 @@ struct msghdr; typedef void (vmci_device_shutdown_fn) (void *device_registration, void *user_data); +typedef void (*vmci_vsock_cb) (bool is_host); int vmci_datagram_create_handle(u32 resource_id, u32 flags, vmci_datagram_recv_cb recv_cb, @@ -37,6 +38,7 @@ int vmci_doorbell_destroy(struct vmci_handle handle); int vmci_doorbell_notify(struct vmci_handle handle, u32 priv_flags); u32 vmci_get_context_id(void); bool vmci_is_context_owner(u32 context_id, kuid_t uid); +int vmci_register_vsock_callback(vmci_vsock_cb callback); int vmci_event_subscribe(u32 event, vmci_event_cb callback, void *callback_data, diff --git a/include/net/af_vsock.h b/include/net/af_vsock.h index 80ea0f93d3f7..4206dc6d813f 100644 --- a/include/net/af_vsock.h +++ b/include/net/af_vsock.h @@ -10,7 +10,7 @@ #include <linux/kernel.h> #include <linux/workqueue.h> -#include <linux/vm_sockets.h> +#include <uapi/linux/vm_sockets.h> #include "vsock_addr.h" @@ -27,6 +27,7 @@ extern spinlock_t vsock_table_lock; struct vsock_sock { /* sk must be the first member. */ struct sock sk; + const struct vsock_transport *transport; struct sockaddr_vm local_addr; struct sockaddr_vm remote_addr; /* Links for the global tables of bound and connected sockets. */ @@ -64,16 +65,18 @@ struct vsock_sock { bool sent_request; bool ignore_connecting_rst; + /* Protected by lock_sock(sk) */ + u64 buffer_size; + u64 buffer_min_size; + u64 buffer_max_size; + /* Private to transport. */ void *trans; }; s64 vsock_stream_has_data(struct vsock_sock *vsk); s64 vsock_stream_has_space(struct vsock_sock *vsk); -struct sock *__vsock_create(struct net *net, - struct socket *sock, - struct sock *parent, - gfp_t priority, unsigned short type, int kern); +struct sock *vsock_create_connected(struct sock *parent); /**** TRANSPORT ****/ @@ -88,7 +91,17 @@ struct vsock_transport_send_notify_data { u64 data2; /* Transport-defined. */ }; +/* Transport features flags */ +/* Transport provides host->guest communication */ +#define VSOCK_TRANSPORT_F_H2G 0x00000001 +/* Transport provides guest->host communication */ +#define VSOCK_TRANSPORT_F_G2H 0x00000002 +/* Transport provides DGRAM communication */ +#define VSOCK_TRANSPORT_F_DGRAM 0x00000004 + struct vsock_transport { + struct module *module; + /* Initialize/tear-down socket. */ int (*init)(struct vsock_sock *, struct vsock_sock *); void (*destruct)(struct vsock_sock *); @@ -139,33 +152,23 @@ struct vsock_transport { struct vsock_transport_send_notify_data *); int (*notify_send_post_enqueue)(struct vsock_sock *, ssize_t, struct vsock_transport_send_notify_data *); + /* sk_lock held by the caller */ + void (*notify_buffer_size)(struct vsock_sock *, u64 *); /* Shutdown. */ int (*shutdown)(struct vsock_sock *, int); - /* Buffer sizes. */ - void (*set_buffer_size)(struct vsock_sock *, u64); - void (*set_min_buffer_size)(struct vsock_sock *, u64); - void (*set_max_buffer_size)(struct vsock_sock *, u64); - u64 (*get_buffer_size)(struct vsock_sock *); - u64 (*get_min_buffer_size)(struct vsock_sock *); - u64 (*get_max_buffer_size)(struct vsock_sock *); - /* Addressing. */ u32 (*get_local_cid)(void); }; /**** CORE ****/ -int __vsock_core_init(const struct vsock_transport *t, struct module *owner); -static inline int vsock_core_init(const struct vsock_transport *t) -{ - return __vsock_core_init(t, THIS_MODULE); -} -void vsock_core_exit(void); +int vsock_core_register(const struct vsock_transport *t, int features); +void vsock_core_unregister(const struct vsock_transport *t); /* The transport may downcast this to access transport-specific functions */ -const struct vsock_transport *vsock_core_get_transport(void); +const struct vsock_transport *vsock_core_get_transport(struct vsock_sock *vsk); /**** UTILS ****/ @@ -193,6 +196,8 @@ struct sock *vsock_find_connected_socket(struct sockaddr_vm *src, struct sockaddr_vm *dst); void vsock_remove_sock(struct vsock_sock *vsk); void vsock_for_each_connected_socket(void (*fn)(struct sock *sk)); +int vsock_assign_transport(struct vsock_sock *vsk, struct vsock_sock *psk); +bool vsock_find_cid(unsigned int cid); /**** TAP ****/ diff --git a/include/net/vsock_addr.h b/include/net/vsock_addr.h index 57d2db5c4bdf..cf8cc140d68d 100644 --- a/include/net/vsock_addr.h +++ b/include/net/vsock_addr.h @@ -8,7 +8,7 @@ #ifndef _VSOCK_ADDR_H_ #define _VSOCK_ADDR_H_ -#include <linux/vm_sockets.h> +#include <uapi/linux/vm_sockets.h> void vsock_addr_init(struct sockaddr_vm *addr, u32 cid, u32 port); int vsock_addr_validate(const struct sockaddr_vm *addr); diff --git a/net/vmw_vsock/af_vsock.c b/net/vmw_vsock/af_vsock.c index 1f4fde4711b6..cc8659838bf2 100644 --- a/net/vmw_vsock/af_vsock.c +++ b/net/vmw_vsock/af_vsock.c @@ -126,19 +126,18 @@ static struct proto vsock_proto = { */ #define VSOCK_DEFAULT_CONNECT_TIMEOUT (2 * HZ) -static const struct vsock_transport *transport; +#define VSOCK_DEFAULT_BUFFER_SIZE (1024 * 256) +#define VSOCK_DEFAULT_BUFFER_MAX_SIZE (1024 * 256) +#define VSOCK_DEFAULT_BUFFER_MIN_SIZE 128 + +/* Transport used for host->guest communication */ +static const struct vsock_transport *transport_h2g; +/* Transport used for guest->host communication */ +static const struct vsock_transport *transport_g2h; +/* Transport used for DGRAM communication */ +static const struct vsock_transport *transport_dgram; static DEFINE_MUTEX(vsock_register_mutex); -/**** EXPORTS ****/ - -/* Get the ID of the local context. This is transport dependent. */ - -int vm_sockets_get_local_cid(void) -{ - return transport->get_local_cid(); -} -EXPORT_SYMBOL_GPL(vm_sockets_get_local_cid); - /**** UTILS ****/ /* Each bound VSocket is stored in the bind hash table and each connected @@ -188,7 +187,7 @@ static int vsock_auto_bind(struct vsock_sock *vsk) return __vsock_bind(sk, &local_addr); } -static int __init vsock_init_tables(void) +static void vsock_init_tables(void) { int i; @@ -197,7 +196,6 @@ static int __init vsock_init_tables(void) for (i = 0; i < ARRAY_SIZE(vsock_connected_table); i++) INIT_LIST_HEAD(&vsock_connected_table[i]); - return 0; } static void __vsock_insert_bound(struct list_head *list, @@ -230,9 +228,15 @@ static struct sock *__vsock_find_bound_socket(struct sockaddr_vm *addr) { struct vsock_sock *vsk; - list_for_each_entry(vsk, vsock_bound_sockets(addr), bound_table) - if (addr->svm_port == vsk->local_addr.svm_port) + list_for_each_entry(vsk, vsock_bound_sockets(addr), bound_table) { + if (vsock_addr_equals_addr(addr, &vsk->local_addr)) + return sk_vsock(vsk); + + if (addr->svm_port == vsk->local_addr.svm_port && + (vsk->local_addr.svm_cid == VMADDR_CID_ANY || + addr->svm_cid == VMADDR_CID_ANY)) return sk_vsock(vsk); + } return NULL; } @@ -382,6 +386,81 @@ void vsock_enqueue_accept(struct sock *listener, struct sock *connected) } EXPORT_SYMBOL_GPL(vsock_enqueue_accept); +static void vsock_deassign_transport(struct vsock_sock *vsk) +{ + if (!vsk->transport) + return; + + vsk->transport->destruct(vsk); + module_put(vsk->transport->module); + vsk->transport = NULL; +} + +/* Assign a transport to a socket and call the .init transport callback. + * + * Note: for stream socket this must be called when vsk->remote_addr is set + * (e.g. during the connect() or when a connection request on a listener + * socket is received). + * The vsk->remote_addr is used to decide which transport to use: + * - remote CID <= VMADDR_CID_HOST will use guest->host transport; + * - remote CID == local_cid (guest->host transport) will use guest->host + * transport for loopback (host->guest transports don't support loopback); + * - remote CID > VMADDR_CID_HOST will use host->guest transport; + */ +int vsock_assign_transport(struct vsock_sock *vsk, struct vsock_sock *psk) +{ + const struct vsock_transport *new_transport; + struct sock *sk = sk_vsock(vsk); + unsigned int remote_cid = vsk->remote_addr.svm_cid; + + switch (sk->sk_type) { + case SOCK_DGRAM: + new_transport = transport_dgram; + break; + case SOCK_STREAM: + if (remote_cid <= VMADDR_CID_HOST || + (transport_g2h && + remote_cid == transport_g2h->get_local_cid())) + new_transport = transport_g2h; + else + new_transport = transport_h2g; + break; + default: + return -ESOCKTNOSUPPORT; + } + + if (vsk->transport) { + if (vsk->transport == new_transport) + return 0; + + vsk->transport->release(vsk); + vsock_deassign_transport(vsk); + } + + /* We increase the module refcnt to prevent the transport unloading + * while there are open sockets assigned to it. + */ + if (!new_transport || !try_module_get(new_transport->module)) + return -ENODEV; + + vsk->transport = new_transport; + + return vsk->transport->init(vsk, psk); +} +EXPORT_SYMBOL_GPL(vsock_assign_transport); + +bool vsock_find_cid(unsigned int cid) +{ + if (transport_g2h && cid == transport_g2h->get_local_cid()) + return true; + + if (transport_h2g && cid == VMADDR_CID_HOST) + return true; + + return false; +} +EXPORT_SYMBOL_GPL(vsock_find_cid); + static struct sock *vsock_dequeue_accept(struct sock *listener) { struct vsock_sock *vlistener; @@ -418,7 +497,12 @@ static bool vsock_is_pending(struct sock *sk) static int vsock_send_shutdown(struct sock *sk, int mode) { - return transport->shutdown(vsock_sk(sk), mode); + struct vsock_sock *vsk = vsock_sk(sk); + + if (!vsk->transport) + return -ENODEV; + + return vsk->transport->shutdown(vsk, mode); } static void vsock_pending_work(struct work_struct *work) @@ -528,13 +612,12 @@ static int __vsock_bind_stream(struct vsock_sock *vsk, static int __vsock_bind_dgram(struct vsock_sock *vsk, struct sockaddr_vm *addr) { - return transport->dgram_bind(vsk, addr); + return vsk->transport->dgram_bind(vsk, addr); } static int __vsock_bind(struct sock *sk, struct sockaddr_vm *addr) { struct vsock_sock *vsk = vsock_sk(sk); - u32 cid; int retval; /* First ensure this socket isn't already bound. */ @@ -544,10 +627,9 @@ static int __vsock_bind(struct sock *sk, struct sockaddr_vm *addr) /* Now bind to the provided address or select appropriate values if * none are provided (VMADDR_CID_ANY and VMADDR_PORT_ANY). Note that * like AF_INET prevents binding to a non-local IP address (in most - * cases), we only allow binding to the local CID. + * cases), we only allow binding to a local CID. */ - cid = transport->get_local_cid(); - if (addr->svm_cid != cid && addr->svm_cid != VMADDR_CID_ANY) + if (addr->svm_cid != VMADDR_CID_ANY && !vsock_find_cid(addr->svm_cid)) return -EADDRNOTAVAIL; switch (sk->sk_socket->type) { @@ -571,12 +653,12 @@ static int __vsock_bind(struct sock *sk, struct sockaddr_vm *addr) static void vsock_connect_timeout(struct work_struct *work); -struct sock *__vsock_create(struct net *net, - struct socket *sock, - struct sock *parent, - gfp_t priority, - unsigned short type, - int kern) +static struct sock *__vsock_create(struct net *net, + struct socket *sock, + struct sock *parent, + gfp_t priority, + unsigned short type, + int kern) { struct sock *sk; struct vsock_sock *psk; @@ -620,23 +702,20 @@ struct sock *__vsock_create(struct net *net, vsk->trusted = psk->trusted; vsk->owner = get_cred(psk->owner); vsk->connect_timeout = psk->connect_timeout; + vsk->buffer_size = psk->buffer_size; + vsk->buffer_min_size = psk->buffer_min_size; + vsk->buffer_max_size = psk->buffer_max_size; } else { vsk->trusted = capable(CAP_NET_ADMIN); vsk->owner = get_current_cred(); vsk->connect_timeout = VSOCK_DEFAULT_CONNECT_TIMEOUT; + vsk->buffer_size = VSOCK_DEFAULT_BUFFER_SIZE; + vsk->buffer_min_size = VSOCK_DEFAULT_BUFFER_MIN_SIZE; + vsk->buffer_max_size = VSOCK_DEFAULT_BUFFER_MAX_SIZE; } - if (transport->init(vsk, psk) < 0) { - sk_free(sk); - return NULL; - } - - if (sock) - vsock_insert_unbound(vsk); - return sk; } -EXPORT_SYMBOL_GPL(__vsock_create); static void __vsock_release(struct sock *sk, int level) { @@ -650,7 +729,10 @@ static void __vsock_release(struct sock *sk, int level) /* The release call is supposed to use lock_sock_nested() * rather than lock_sock(), if a sock lock should be acquired. */ - transport->release(vsk); + if (vsk->transport) + vsk->transport->release(vsk); + else if (sk->sk_type == SOCK_STREAM) + vsock_remove_sock(vsk); /* When "level" is SINGLE_DEPTH_NESTING, use the nested * version to avoid the warning "possible recursive locking @@ -678,7 +760,7 @@ static void vsock_sk_destruct(struct sock *sk) { struct vsock_sock *vsk = vsock_sk(sk); - transport->destruct(vsk); + vsock_deassign_transport(vsk); /* When clearing these addresses, there's no need to set the family and * possibly register the address family with the kernel. @@ -700,15 +782,22 @@ static int vsock_queue_rcv_skb(struct sock *sk, struct sk_buff *skb) return err; } +struct sock *vsock_create_connected(struct sock *parent) +{ + return __vsock_create(sock_net(parent), NULL, parent, GFP_KERNEL, + parent->sk_type, 0); +} +EXPORT_SYMBOL_GPL(vsock_create_connected); + s64 vsock_stream_has_data(struct vsock_sock *vsk) { - return transport->stream_has_data(vsk); + return vsk->transport->stream_has_data(vsk); } EXPORT_SYMBOL_GPL(vsock_stream_has_data); s64 vsock_stream_has_space(struct vsock_sock *vsk) { - return transport->stream_has_space(vsk); + return vsk->transport->stream_has_space(vsk); } EXPORT_SYMBOL_GPL(vsock_stream_has_space); @@ -877,6 +966,7 @@ static __poll_t vsock_poll(struct file *file, struct socket *sock, mask |= EPOLLOUT | EPOLLWRNORM | EPOLLWRBAND; } else if (sock->type == SOCK_STREAM) { + const struct vsock_transport *transport = vsk->transport; lock_sock(sk); /* Listening sockets that have connections in their accept @@ -887,7 +977,7 @@ static __poll_t vsock_poll(struct file *file, struct socket *sock, mask |= EPOLLIN | EPOLLRDNORM; /* If there is something in the queue then we can read. */ - if (transport->stream_is_active(vsk) && + if (transport && transport->stream_is_active(vsk) && !(sk->sk_shutdown & RCV_SHUTDOWN)) { bool data_ready_now = false; int ret = transport->notify_poll_in( @@ -952,6 +1042,7 @@ static int vsock_dgram_sendmsg(struct socket *sock, struct msghdr *msg, struct sock *sk; struct vsock_sock *vsk; struct sockaddr_vm *remote_addr; + const struct vsock_transport *transport; if (msg->msg_flags & MSG_OOB) return -EOPNOTSUPP; @@ -960,6 +1051,7 @@ static int vsock_dgram_sendmsg(struct socket *sock, struct msghdr *msg, err = 0; sk = sock->sk; vsk = vsock_sk(sk); + transport = vsk->transport; lock_sock(sk); @@ -1044,8 +1136,8 @@ static int vsock_dgram_connect(struct socket *sock, if (err) goto out; - if (!transport->dgram_allow(remote_addr->svm_cid, - remote_addr->svm_port)) { + if (!vsk->transport->dgram_allow(remote_addr->svm_cid, + remote_addr->svm_port)) { err = -EINVAL; goto out; } @@ -1061,7 +1153,9 @@ out: static int vsock_dgram_recvmsg(struct socket *sock, struct msghdr *msg, size_t len, int flags) { - return transport->dgram_dequeue(vsock_sk(sock->sk), msg, len, flags); + struct vsock_sock *vsk = vsock_sk(sock->sk); + + return vsk->transport->dgram_dequeue(vsk, msg, len, flags); } static const struct proto_ops vsock_dgram_ops = { @@ -1087,6 +1181,8 @@ static const struct proto_ops vsock_dgram_ops = { static int vsock_transport_cancel_pkt(struct vsock_sock *vsk) { + const struct vsock_transport *transport = vsk->transport; + if (!transport->cancel_pkt) return -EOPNOTSUPP; @@ -1123,6 +1219,7 @@ static int vsock_stream_connect(struct socket *sock, struct sockaddr *addr, int err; struct sock *sk; struct vsock_sock *vsk; + const struct vsock_transport *transport; struct sockaddr_vm *remote_addr; long timeout; DEFINE_WAIT(wait); @@ -1157,19 +1254,26 @@ static int vsock_stream_connect(struct socket *sock, struct sockaddr *addr, goto out; } + /* Set the remote address that we are connecting to. */ + memcpy(&vsk->remote_addr, remote_addr, + sizeof(vsk->remote_addr)); + + err = vsock_assign_transport(vsk, NULL); + if (err) + goto out; + + transport = vsk->transport; + /* The hypervisor and well-known contexts do not have socket * endpoints. */ - if (!transport->stream_allow(remote_addr->svm_cid, + if (!transport || + !transport->stream_allow(remote_addr->svm_cid, remote_addr->svm_port)) { err = -ENETUNREACH; goto out; } - /* Set the remote address that we are connecting to. */ - memcpy(&vsk->remote_addr, remote_addr, - sizeof(vsk->remote_addr)); - err = vsock_auto_bind(vsk); if (err) goto out; @@ -1364,6 +1468,23 @@ out: return err; } +static void vsock_update_buffer_size(struct vsock_sock *vsk, + const struct vsock_transport *transport, + u64 val) +{ + if (val > vsk->buffer_max_size) + val = vsk->buffer_max_size; + + if (val < vsk->buffer_min_size) + val = vsk->buffer_min_size; + + if (val != vsk->buffer_size && + transport && transport->notify_buffer_size) + transport->notify_buffer_size(vsk, &val); + |