diff --git a/fs/ceph/dir.c b/fs/ceph/dir.c index f0aef787a1026cb96587054d19bc01c6eaf2e03b..099a58615b90f73e29368ffba4793e5a17cb66ae 100644 --- a/fs/ceph/dir.c +++ b/fs/ceph/dir.c @@ -60,7 +60,6 @@ int ceph_init_dentry(struct dentry *dentry) } di->dentry = dentry; di->lease_session = NULL; - di->parent_inode = igrab(dentry->d_parent->d_inode); dentry->d_fsdata = di; dentry->d_time = jiffies; ceph_dentry_lru_add(dentry); @@ -410,7 +409,7 @@ static int ceph_readdir(struct file *filp, void *dirent, filldir_t filldir) spin_lock(&inode->i_lock); if (ci->i_release_count == fi->dir_release_count) { dout(" marking %p complete\n", inode); - ci->i_ceph_flags |= CEPH_I_COMPLETE; + /* ci->i_ceph_flags |= CEPH_I_COMPLETE; */ ci->i_max_offset = filp->f_pos; } spin_unlock(&inode->i_lock); @@ -497,6 +496,7 @@ struct dentry *ceph_finish_lookup(struct ceph_mds_request *req, /* .snap dir? */ if (err == -ENOENT && + ceph_snap(parent) == CEPH_NOSNAP && strcmp(dentry->d_name.name, fsc->mount_options->snapdir_name) == 0) { struct inode *inode = ceph_get_snapdir(parent); @@ -1030,28 +1030,8 @@ static int ceph_d_revalidate(struct dentry *dentry, struct nameidata *nd) static void ceph_dentry_release(struct dentry *dentry) { struct ceph_dentry_info *di = ceph_dentry(dentry); - struct inode *parent_inode = NULL; - u64 snapid = CEPH_NOSNAP; - if (!IS_ROOT(dentry)) { - parent_inode = di->parent_inode; - if (parent_inode) - snapid = ceph_snap(parent_inode); - } - dout("dentry_release %p parent %p\n", dentry, parent_inode); - if (parent_inode && snapid != CEPH_SNAPDIR) { - struct ceph_inode_info *ci = ceph_inode(parent_inode); - - spin_lock(&parent_inode->i_lock); - if (ci->i_shared_gen == di->lease_shared_gen || - snapid <= CEPH_MAXSNAP) { - dout(" clearing %p complete (d_release)\n", - parent_inode); - ci->i_ceph_flags &= ~CEPH_I_COMPLETE; - ci->i_release_count++; - } - spin_unlock(&parent_inode->i_lock); - } + dout("dentry_release %p\n", dentry); if (di) { ceph_dentry_lru_del(dentry); if (di->lease_session) @@ -1059,8 +1039,6 @@ static void ceph_dentry_release(struct dentry *dentry) kmem_cache_free(ceph_dentry_cachep, di); dentry->d_fsdata = NULL; } - if (parent_inode) - iput(parent_inode); } static int ceph_snapdir_d_revalidate(struct dentry *dentry, diff --git a/fs/ceph/inode.c b/fs/ceph/inode.c index 5625463aa4796f3df3678dd29ed1bfb1135a32af..193bfa5e9cbd7943bcb2a8124b5fa9ed6717cac4 100644 --- a/fs/ceph/inode.c +++ b/fs/ceph/inode.c @@ -707,7 +707,7 @@ static int fill_inode(struct inode *inode, (issued & CEPH_CAP_FILE_EXCL) == 0 && (ci->i_ceph_flags & CEPH_I_COMPLETE) == 0) { dout(" marking %p complete (empty)\n", inode); - ci->i_ceph_flags |= CEPH_I_COMPLETE; + /* ci->i_ceph_flags |= CEPH_I_COMPLETE; */ ci->i_max_offset = 2; } break; diff --git a/fs/ceph/super.h b/fs/ceph/super.h index 88fcaa21b801a8c10ba2be23c41967b95ddfcef6..20b907d76ae2f1be3b9e5ef4859bb1866b833c8a 100644 --- a/fs/ceph/super.h +++ b/fs/ceph/super.h @@ -207,7 +207,6 @@ struct ceph_dentry_info { struct dentry *dentry; u64 time; u64 offset; - struct inode *parent_inode; }; struct ceph_inode_xattrs_info { diff --git a/include/linux/ceph/messenger.h b/include/linux/ceph/messenger.h index c3011beac30d18023ba8a7a8d8305050cb6a37df..31d91a64838be0326ee3d8d76032f67181008dbc 100644 --- a/include/linux/ceph/messenger.h +++ b/include/linux/ceph/messenger.h @@ -123,6 +123,7 @@ struct ceph_msg_pos { #define SOCK_CLOSED 11 /* socket state changed to closed */ #define OPENING 13 /* open connection w/ (possibly new) peer */ #define DEAD 14 /* dead, about to kfree */ +#define BACKOFF 15 /* * A single connection with another host. @@ -160,7 +161,6 @@ struct ceph_connection { struct list_head out_queue; struct list_head out_sent; /* sending or sent but unacked */ u64 out_seq; /* last message queued for send */ - bool out_keepalive_pending; u64 in_seq, in_seq_acked; /* last message received, acked */ diff --git a/net/ceph/messenger.c b/net/ceph/messenger.c index 35b36b86d762892a118b7e34e88b654979db30a1..05f357828a2fb8de1bb2be9f4103c90058484259 100644 --- a/net/ceph/messenger.c +++ b/net/ceph/messenger.c @@ -336,7 +336,6 @@ static void reset_connection(struct ceph_connection *con) ceph_msg_put(con->out_msg); con->out_msg = NULL; } - con->out_keepalive_pending = false; con->in_seq = 0; con->in_seq_acked = 0; } @@ -1248,8 +1247,6 @@ static int process_connect(struct ceph_connection *con) con->auth_retry); if (con->auth_retry == 2) { con->error_msg = "connect authorization failure"; - reset_connection(con); - set_bit(CLOSED, &con->state); return -1; } con->auth_retry = 1; @@ -1715,14 +1712,6 @@ static int try_write(struct ceph_connection *con) /* open the socket first? */ if (con->sock == NULL) { - /* - * if we were STANDBY and are reconnecting _this_ - * connection, bump connect_seq now. Always bump - * global_seq. - */ - if (test_and_clear_bit(STANDBY, &con->state)) - con->connect_seq++; - prepare_write_banner(msgr, con); prepare_write_connect(msgr, con, 1); prepare_read_banner(con); @@ -1951,7 +1940,24 @@ static void con_work(struct work_struct *work) work.work); mutex_lock(&con->mutex); + if (test_and_clear_bit(BACKOFF, &con->state)) { + dout("con_work %p backing off\n", con); + if (queue_delayed_work(ceph_msgr_wq, &con->work, + round_jiffies_relative(con->delay))) { + dout("con_work %p backoff %lu\n", con, con->delay); + mutex_unlock(&con->mutex); + return; + } else { + con->ops->put(con); + dout("con_work %p FAILED to back off %lu\n", con, + con->delay); + } + } + if (test_bit(STANDBY, &con->state)) { + dout("con_work %p STANDBY\n", con); + goto done; + } if (test_bit(CLOSED, &con->state)) { /* e.g. if we are replaced */ dout("con_work CLOSED\n"); con_close_socket(con); @@ -2008,10 +2014,12 @@ static void ceph_fault(struct ceph_connection *con) /* Requeue anything that hasn't been acked */ list_splice_init(&con->out_sent, &con->out_queue); - /* If there are no messages in the queue, place the connection - * in a STANDBY state (i.e., don't try to reconnect just yet). */ - if (list_empty(&con->out_queue) && !con->out_keepalive_pending) { - dout("fault setting STANDBY\n"); + /* If there are no messages queued or keepalive pending, place + * the connection in a STANDBY state */ + if (list_empty(&con->out_queue) && + !test_bit(KEEPALIVE_PENDING, &con->state)) { + dout("fault %p setting STANDBY clearing WRITE_PENDING\n", con); + clear_bit(WRITE_PENDING, &con->state); set_bit(STANDBY, &con->state); } else { /* retry after a delay. */ @@ -2019,11 +2027,24 @@ static void ceph_fault(struct ceph_connection *con) con->delay = BASE_DELAY_INTERVAL; else if (con->delay < MAX_DELAY_INTERVAL) con->delay *= 2; - dout("fault queueing %p delay %lu\n", con, con->delay); con->ops->get(con); if (queue_delayed_work(ceph_msgr_wq, &con->work, - round_jiffies_relative(con->delay)) == 0) + round_jiffies_relative(con->delay))) { + dout("fault queued %p delay %lu\n", con, con->delay); + } else { con->ops->put(con); + dout("fault failed to queue %p delay %lu, backoff\n", + con, con->delay); + /* + * In many cases we see a socket state change + * while con_work is running and end up + * queuing (non-delayed) work, such that we + * can't backoff with a delay. Set a flag so + * that when con_work restarts we schedule the + * delay then. + */ + set_bit(BACKOFF, &con->state); + } } out_unlock: @@ -2094,6 +2115,19 @@ void ceph_messenger_destroy(struct ceph_messenger *msgr) } EXPORT_SYMBOL(ceph_messenger_destroy); +static void clear_standby(struct ceph_connection *con) +{ + /* come back from STANDBY? */ + if (test_and_clear_bit(STANDBY, &con->state)) { + mutex_lock(&con->mutex); + dout("clear_standby %p and ++connect_seq\n", con); + con->connect_seq++; + WARN_ON(test_bit(WRITE_PENDING, &con->state)); + WARN_ON(test_bit(KEEPALIVE_PENDING, &con->state)); + mutex_unlock(&con->mutex); + } +} + /* * Queue up an outgoing message on the given connection. */ @@ -2126,6 +2160,7 @@ void ceph_con_send(struct ceph_connection *con, struct ceph_msg *msg) /* if there wasn't anything waiting to send before, queue * new work */ + clear_standby(con); if (test_and_set_bit(WRITE_PENDING, &con->state) == 0) queue_con(con); } @@ -2191,6 +2226,8 @@ void ceph_con_revoke_message(struct ceph_connection *con, struct ceph_msg *msg) */ void ceph_con_keepalive(struct ceph_connection *con) { + dout("con_keepalive %p\n", con); + clear_standby(con); if (test_and_set_bit(KEEPALIVE_PENDING, &con->state) == 0 && test_and_set_bit(WRITE_PENDING, &con->state) == 0) queue_con(con); diff --git a/net/ceph/pagevec.c b/net/ceph/pagevec.c index 1a040e64c69f23545f98e282bae934b3ed33baa9..cd9c21df87d172fa0c7bfe1af7ee289ab5dd0494 100644 --- a/net/ceph/pagevec.c +++ b/net/ceph/pagevec.c @@ -16,22 +16,30 @@ struct page **ceph_get_direct_page_vector(const char __user *data, int num_pages, bool write_page) { struct page **pages; - int rc; + int got = 0; + int rc = 0; pages = kmalloc(sizeof(*pages) * num_pages, GFP_NOFS); if (!pages) return ERR_PTR(-ENOMEM); down_read(¤t->mm->mmap_sem); - rc = get_user_pages(current, current->mm, (unsigned long)data, - num_pages, write_page, 0, pages, NULL); + while (got < num_pages) { + rc = get_user_pages(current, current->mm, + (unsigned long)data + ((unsigned long)got * PAGE_SIZE), + num_pages - got, write_page, 0, pages + got, NULL); + if (rc < 0) + break; + BUG_ON(rc == 0); + got += rc; + } up_read(¤t->mm->mmap_sem); - if (rc < num_pages) + if (rc < 0) goto fail; return pages; fail: - ceph_put_page_vector(pages, rc > 0 ? rc : 0, false); + ceph_put_page_vector(pages, got, false); return ERR_PTR(rc); } EXPORT_SYMBOL(ceph_get_direct_page_vector);