This changes the checkpoint/restart procedure for sockets a bit. The socket file header is now checkpointed separately from the socket itself, which allows us to checkpoint a socket without arriving at it from a file descriptor. Thus, most sockets will be checkpointed as a result of processing the file table, calling sock_file_checkpoint(fd), which in turn calls checkpoint_obj(socket).
However, we may arrive at some sockets while checkpointing other objects, such as the other end of an AF_UNIX socket with buffers in flight. This patch just opens that door, which is utilized by the next patch. Changes in v2: - If we attempt to checkpoint an orphan socket, create a struct socket to adopt it for the purposes of the checkpoint Signed-off-by: Dan Smith <[email protected]> --- checkpoint/objhash.c | 2 + include/linux/checkpoint_hdr.h | 6 +- include/linux/net.h | 4 +- include/net/af_unix.h | 4 +- include/net/sock.h | 2 + net/checkpoint.c | 153 +++++++++++++++++++++++++++++++--------- net/unix/checkpoint.c | 11 ++-- 7 files changed, 136 insertions(+), 46 deletions(-) diff --git a/checkpoint/objhash.c b/checkpoint/objhash.c index a9a10d1..a410346 100644 --- a/checkpoint/objhash.c +++ b/checkpoint/objhash.c @@ -381,6 +381,8 @@ static struct ckpt_obj_ops ckpt_obj_ops[] = { .obj_type = CKPT_OBJ_SOCK, .ref_drop = obj_sock_drop, .ref_grab = obj_sock_grab, + .checkpoint = checkpoint_sock, + .restore = restore_sock, }, }; diff --git a/include/linux/checkpoint_hdr.h b/include/linux/checkpoint_hdr.h index 06bc6e2..b75562c 100644 --- a/include/linux/checkpoint_hdr.h +++ b/include/linux/checkpoint_hdr.h @@ -70,6 +70,7 @@ enum { CKPT_HDR_USER, CKPT_HDR_GROUPINFO, CKPT_HDR_TASK_CREDS, + CKPT_HDR_SOCKET, /* 201-299: reserved for arch-dependent */ @@ -368,7 +369,8 @@ struct ckpt_hdr_file_pipe { } __attribute__((aligned(8))); /* socket */ -struct ckpt_socket { +struct ckpt_hdr_socket { + struct ckpt_hdr h; struct { /* struct socket */ __u64 flags; __u8 state; @@ -428,7 +430,7 @@ struct ckpt_hdr_socket_unix { struct ckpt_hdr_file_socket { struct ckpt_hdr_file common; - struct ckpt_socket socket; + __s32 sock_objref; } __attribute__((aligned(8))); struct ckpt_hdr_utsns { diff --git a/include/linux/net.h b/include/linux/net.h index 27187a4..96c7e22 100644 --- a/include/linux/net.h +++ b/include/linux/net.h @@ -148,7 +148,7 @@ struct msghdr; struct module; struct ckpt_ctx; -struct ckpt_socket; +struct ckpt_hdr_socket; struct proto_ops { int family; @@ -197,7 +197,7 @@ struct proto_ops { int (*checkpoint)(struct ckpt_ctx *ctx, struct socket *sock); int (*restore)(struct ckpt_ctx *ctx, struct socket *sock, - struct ckpt_socket *h); + struct ckpt_hdr_socket *h); }; struct net_proto_family { diff --git a/include/net/af_unix.h b/include/net/af_unix.h index 1a1fd20..61f666b 100644 --- a/include/net/af_unix.h +++ b/include/net/af_unix.h @@ -71,10 +71,10 @@ static inline void unix_sysctl_unregister(struct net *net) {} #ifdef CONFIG_CHECKPOINT struct ckpt_ctx; -struct ckpt_socket; +struct ckpt_hdr_socket; extern int unix_checkpoint(struct ckpt_ctx *ctx, struct socket *sock); extern int unix_restore(struct ckpt_ctx *ctx, struct socket *sock, - struct ckpt_socket *h); + struct ckpt_hdr_socket *h); #else #define unix_checkpoint NULL #define unix_restore NULL diff --git a/include/net/sock.h b/include/net/sock.h index 8e3b050..0db1ca3 100644 --- a/include/net/sock.h +++ b/include/net/sock.h @@ -1644,6 +1644,8 @@ extern __u32 sysctl_rmem_default; /* Checkpoint/Restart Functions */ struct ckpt_ctx; struct ckpt_hdr_file; +extern int checkpoint_sock(struct ckpt_ctx *ctx, void *ptr); +extern void *restore_sock(struct ckpt_ctx *ctx); extern int sock_file_checkpoint(struct ckpt_ctx *ctx, struct file *file); extern struct file *sock_file_restore(struct ckpt_ctx *ctx, struct ckpt_hdr_file *h); diff --git a/net/checkpoint.c b/net/checkpoint.c index 2541e81..d52389a 100644 --- a/net/checkpoint.c +++ b/net/checkpoint.c @@ -166,7 +166,7 @@ int ckpt_sock_getnames(struct ckpt_ctx *ctx, struct socket *sock, return 0; } -static int sock_cptrst_verify(struct ckpt_socket *h) +static int sock_cptrst_verify(struct ckpt_hdr_socket *h) { uint8_t userlocks_mask = SOCK_SNDBUF_LOCK | SOCK_RCVBUF_LOCK | SOCK_BINDADDR_LOCK | SOCK_BINDPORT_LOCK; @@ -204,7 +204,7 @@ static int sock_cptrst_opt(int op, struct socket *sock, sock_cptrst_opt(op, sk->sk_socket, name, (char *)opt, sizeof(*opt)) static int sock_cptrst_bufopts(int op, struct sock *sk, - struct ckpt_socket *h) + struct ckpt_hdr_socket *h) { if (CKPT_COPY_SOPT(op, sk, SO_RCVBUF, &h->sock.rcvbuf)) @@ -270,7 +270,7 @@ static int sock_restore_flag(struct socket *sock, static int sock_restore_flags(struct socket *sock, - struct ckpt_socket *h) + struct ckpt_hdr_socket *h) { int ret; int i; @@ -309,6 +309,9 @@ static int sock_restore_flags(struct socket *sock, return -ENOSYS; } + if (test_and_clear_bit(SOCK_DEAD, &sk_flags)) + sock_flag(sock->sk, SOCK_DEAD); + /* Anything that is still set in the flags that isn't part of * our protocol's default set, indicates an error */ @@ -339,7 +342,7 @@ static int sock_copy_timeval(int op, struct sock *sk, } static int sock_cptrst(struct ckpt_ctx *ctx, struct sock *sk, - struct ckpt_socket *h, int op) + struct ckpt_hdr_socket *h, int op) { if (sk->sk_socket) { CKPT_COPY(op, h->socket.state, sk->sk_socket->state); @@ -428,31 +431,26 @@ static int sock_cptrst(struct ckpt_ctx *ctx, struct sock *sk, return 0; } -int sock_file_checkpoint(struct ckpt_ctx *ctx, struct file *file) +static int __do_sock_checkpoint(struct ckpt_ctx *ctx, struct sock *sk) { - struct ckpt_hdr_file_socket *h; - struct socket *sock = file->private_data; - struct sock *sk = sock->sk; int ret; + struct socket *sock = sk->sk_socket; + struct ckpt_hdr_socket *h; if (!sock->ops->checkpoint) { ckpt_write_err(ctx, "socket (proto_ops: %pS)", sock->ops); return -ENOSYS; } - h = ckpt_hdr_get_type(ctx, sizeof(*h), CKPT_HDR_FILE); + h = ckpt_hdr_get_type(ctx, sizeof(*h), CKPT_HDR_SOCKET); if (!h) return -ENOMEM; - h->common.f_type = CKPT_FILE_SOCKET; - /* part I: common to all sockets */ - ret = sock_cptrst(ctx, sk, &h->socket, CKPT_CPT); - if (ret < 0) - goto out; - ret = checkpoint_file_common(ctx, file, &h->common); + ret = sock_cptrst(ctx, sk, h, CKPT_CPT); if (ret < 0) goto out; + ret = ckpt_write_obj(ctx, (struct ckpt_hdr *) h); if (ret < 0) goto out; @@ -463,12 +461,71 @@ int sock_file_checkpoint(struct ckpt_ctx *ctx, struct file *file) goto out; /* part III: socket buffers */ - if (sk->sk_state != TCP_LISTEN) { + if ((sk->sk_state != TCP_LISTEN) && (!sock_flag(sk, SOCK_DEAD))) { ret = sock_write_buffers(ctx, &sk->sk_receive_queue); if (ret) goto out; ret = sock_write_buffers(ctx, &sk->sk_write_queue); } + + out: + ckpt_hdr_put(ctx, h); + + return ret; +} + +static int do_sock_checkpoint(struct ckpt_ctx *ctx, struct sock *sk) +{ + struct socket *sock; + int ret; + + if (sk->sk_socket) + return __do_sock_checkpoint(ctx, sk); + + /* Temporarily adopt this orphan socket */ + ret = sock_create(sk->sk_family, sk->sk_type, 0, &sock); + if (ret < 0) + return ret; + sock_graft(sk, sock); + + ret = __do_sock_checkpoint(ctx, sk); + + sock_orphan(sk); + sock->sk = NULL; + sock_release(sock); + + return ret; +} + +int checkpoint_sock(struct ckpt_ctx *ctx, void *ptr) +{ + return do_sock_checkpoint(ctx, (struct sock *)ptr); +} + +int sock_file_checkpoint(struct ckpt_ctx *ctx, struct file *file) +{ + struct ckpt_hdr_file_socket *h; + struct socket *sock = file->private_data; + struct sock *sk = sock->sk; + int ret; + + h = ckpt_hdr_get_type(ctx, sizeof(*h), CKPT_HDR_FILE); + if (!h) + return -ENOMEM; + + h->common.f_type = CKPT_FILE_SOCKET; + + h->sock_objref = checkpoint_obj(ctx, sk, CKPT_OBJ_SOCK); + if (h->sock_objref < 0) { + ret = h->sock_objref; + goto out; + } + + ret = checkpoint_file_common(ctx, file, &h->common); + if (ret < 0) + goto out; + + ret = ckpt_write_obj(ctx, (struct ckpt_hdr *) h); out: ckpt_hdr_put(ctx, h); return ret; @@ -525,27 +582,31 @@ static struct file *sock_alloc_attach_fd(struct socket *sock) file = ERR_PTR(err); } + /* Since objhash assumes the initial reference for a socket, + * we bump it here for this descriptor, unlike other places in the + * socket code which assume the descriptor is the owner. + */ + sock_hold(sock->sk); + return file; } -struct file *sock_file_restore(struct ckpt_ctx *ctx, struct ckpt_hdr_file *ptr) +struct sock *do_sock_restore(struct ckpt_ctx *ctx) { - struct ckpt_hdr_file_socket *hh = (struct ckpt_hdr_file_socket *) ptr; - struct ckpt_socket *h = &hh->socket; + struct ckpt_hdr_socket *h; struct socket *sock; - struct file *file; int ret; - if (ptr->h.type != CKPT_HDR_FILE || - ptr->h.len != sizeof(*hh) || ptr->f_type != CKPT_FILE_SOCKET) - return ERR_PTR(-EINVAL); + h = ckpt_read_obj_type(ctx, sizeof(*h), CKPT_HDR_SOCKET); + if (IS_ERR(h)) + return ERR_PTR(PTR_ERR(h)); /* silently clear flags, e.g. SOCK_NONBLOCK or SOCK_CLOEXEC */ h->sock.type &= SOCK_TYPE_MASK; ret = sock_create(h->sock_common.family, h->sock.type, 0, &sock); if (ret < 0) - return ERR_PTR(ret); + goto err; if (!sock->ops->restore) { ckpt_debug("proto_ops lacks checkpoint: %pS\n", sock->ops); @@ -566,21 +627,45 @@ struct file *sock_file_restore(struct ckpt_ctx *ctx, struct ckpt_hdr_file *ptr) if (ret < 0) goto err; - file = sock_alloc_attach_fd(sock); - if (IS_ERR(file)) { - ret = PTR_ERR(file); - goto err; - } + ckpt_hdr_put(ctx, h); + + return sock->sk; + err: + ckpt_hdr_put(ctx, h); + sock_release(sock); + + return ERR_PTR(ret); +} + +void *restore_sock(struct ckpt_ctx *ctx) +{ + return do_sock_restore(ctx); +} + +struct file *sock_file_restore(struct ckpt_ctx *ctx, struct ckpt_hdr_file *ptr) +{ + struct ckpt_hdr_file_socket *h = (struct ckpt_hdr_file_socket *)ptr; + struct sock *sk; + struct file *file; + int ret; + + if (ptr->h.type != CKPT_HDR_FILE || ptr->f_type != CKPT_FILE_SOCKET) + return ERR_PTR(-EINVAL); + + sk = ckpt_obj_fetch(ctx, h->sock_objref, CKPT_OBJ_SOCK); + if (IS_ERR(sk)) + return ERR_PTR(PTR_ERR(sk)); + + file = sock_alloc_attach_fd(sk->sk_socket); + if (IS_ERR(file)) + return file; ret = restore_file_common(ctx, file, ptr); if (ret < 0) { fput(file); - file = ERR_PTR(ret); + return ERR_PTR(ret); } - return file; - err: - sock_release(sock); - return ERR_PTR(ret); + return file; } diff --git a/net/unix/checkpoint.c b/net/unix/checkpoint.c index 08e664b..395f6fd 100644 --- a/net/unix/checkpoint.c +++ b/net/unix/checkpoint.c @@ -57,7 +57,6 @@ static int unix_write_cwd(struct ckpt_ctx *ctx, int unix_checkpoint(struct ckpt_ctx *ctx, struct socket *sock) { struct unix_sock *sk = unix_sk(sock->sk); - struct unix_sock *pr = unix_sk(sk->peer); struct ckpt_hdr_socket_unix *un; int new; int ret = -ENOMEM; @@ -86,7 +85,7 @@ int unix_checkpoint(struct ckpt_ctx *ctx, struct socket *sock) goto out; if (sk->peer) - un->peer = ckpt_obj_lookup_add(ctx, pr, CKPT_OBJ_SOCK, &new); + un->peer = checkpoint_obj(ctx, sk->peer, CKPT_OBJ_SOCK); else un->peer = 0; @@ -237,7 +236,7 @@ static int unix_join(struct ckpt_ctx *ctx, } static int unix_restore_connected(struct ckpt_ctx *ctx, - struct ckpt_socket *h, + struct ckpt_hdr_socket *h, struct ckpt_hdr_socket_unix *un, struct socket *sock) { @@ -423,7 +422,7 @@ static int unix_fakebind(struct socket *sock, return 0; } -static int unix_restore_bind(struct ckpt_socket *h, +static int unix_restore_bind(struct ckpt_hdr_socket *h, struct ckpt_hdr_socket_unix *un, struct socket *sock, const char *path) @@ -440,7 +439,7 @@ static int unix_restore_bind(struct ckpt_socket *h, } /* Some easy pre-flight checks before we get underway */ -static int unix_precheck(struct socket *sock, struct ckpt_socket *h) +static int unix_precheck(struct socket *sock, struct ckpt_hdr_socket *h) { struct net *net = sock_net(sock->sk); @@ -471,7 +470,7 @@ static int unix_precheck(struct socket *sock, struct ckpt_socket *h) } int unix_restore(struct ckpt_ctx *ctx, struct socket *sock, - struct ckpt_socket *h) + struct ckpt_hdr_socket *h) { struct ckpt_hdr_socket_unix *un; -- 1.6.2.5 _______________________________________________ Containers mailing list [email protected] https://lists.linux-foundation.org/mailman/listinfo/containers _______________________________________________ Devel mailing list [email protected] https://openvz.org/mailman/listinfo/devel
