diff options
Diffstat (limited to 'net')
70 files changed, 1129 insertions, 415 deletions
diff --git a/net/9p/client.c b/net/9p/client.c index b433aff5ff13..21e6df1cc70f 100644 --- a/net/9p/client.c +++ b/net/9p/client.c @@ -190,7 +190,9 @@ static int parse_opts(char *opts, struct p9_client *clnt) p9_debug(P9_DEBUG_ERROR, "problem allocating copy of trans arg\n"); goto free_and_return; - } + } + + v9fs_put_trans(clnt->trans_mod); clnt->trans_mod = v9fs_get_trans_by_name(s); if (clnt->trans_mod == NULL) { pr_info("Could not find request transport: %s\n", @@ -226,6 +228,7 @@ static int parse_opts(char *opts, struct p9_client *clnt) } free_and_return: + v9fs_put_trans(clnt->trans_mod); kfree(tmp_options); return ret; } @@ -769,7 +772,7 @@ p9_client_rpc(struct p9_client *c, int8_t type, const char *fmt, ...) if (err < 0) { if (err != -ERESTARTSYS && err != -EFAULT) c->status = Disconnected; - goto reterr; + goto recalc_sigpending; } again: /* Wait for the response */ @@ -804,6 +807,7 @@ again: if (req->status == REQ_STATUS_RCVD) err = 0; } +recalc_sigpending: if (sigpending) { spin_lock_irqsave(¤t->sighand->siglock, flags); recalc_sigpending(); @@ -867,7 +871,7 @@ static struct p9_req_t *p9_client_zc_rpc(struct p9_client *c, int8_t type, if (err == -EIO) c->status = Disconnected; if (err != -ERESTARTSYS) - goto reterr; + goto recalc_sigpending; } if (req->status == REQ_STATUS_ERROR) { p9_debug(P9_DEBUG_ERROR, "req_status error %d\n", req->t_err); @@ -885,6 +889,7 @@ static struct p9_req_t *p9_client_zc_rpc(struct p9_client *c, int8_t type, if (req->status == REQ_STATUS_RCVD) err = 0; } +recalc_sigpending: if (sigpending) { spin_lock_irqsave(¤t->sighand->siglock, flags); recalc_sigpending(); diff --git a/net/bluetooth/hci_conn.c b/net/bluetooth/hci_conn.c index a9682534c377..45ff5dc124cc 100644 --- a/net/bluetooth/hci_conn.c +++ b/net/bluetooth/hci_conn.c @@ -749,18 +749,31 @@ static bool conn_use_rpa(struct hci_conn *conn) } static void hci_req_add_le_create_conn(struct hci_request *req, - struct hci_conn *conn) + struct hci_conn *conn, + bdaddr_t *direct_rpa) { struct hci_cp_le_create_conn cp; struct hci_dev *hdev = conn->hdev; u8 own_addr_type; - /* Update random address, but set require_privacy to false so - * that we never connect with an non-resolvable address. + /* If direct address was provided we use it instead of current + * address. */ - if (hci_update_random_address(req, false, conn_use_rpa(conn), - &own_addr_type)) - return; + if (direct_rpa) { + if (bacmp(&req->hdev->random_addr, direct_rpa)) + hci_req_add(req, HCI_OP_LE_SET_RANDOM_ADDR, 6, + direct_rpa); + + /* direct address is always RPA */ + own_addr_type = ADDR_LE_DEV_RANDOM; + } else { + /* Update random address, but set require_privacy to false so + * that we never connect with an non-resolvable address. + */ + if (hci_update_random_address(req, false, conn_use_rpa(conn), + &own_addr_type)) + return; + } memset(&cp, 0, sizeof(cp)); @@ -825,7 +838,7 @@ static void hci_req_directed_advertising(struct hci_request *req, struct hci_conn *hci_connect_le(struct hci_dev *hdev, bdaddr_t *dst, u8 dst_type, u8 sec_level, u16 conn_timeout, - u8 role) + u8 role, bdaddr_t *direct_rpa) { struct hci_conn_params *params; struct hci_conn *conn; @@ -940,7 +953,7 @@ struct hci_conn *hci_connect_le(struct hci_dev *hdev, bdaddr_t *dst, hci_dev_set_flag(hdev, HCI_LE_SCAN_INTERRUPTED); } - hci_req_add_le_create_conn(&req, conn); + hci_req_add_le_create_conn(&req, conn, direct_rpa); create_conn: err = hci_req_run(&req, create_le_conn_complete); diff --git a/net/bluetooth/hci_event.c b/net/bluetooth/hci_event.c index cd3bbb766c24..139707cd9d35 100644 --- a/net/bluetooth/hci_event.c +++ b/net/bluetooth/hci_event.c @@ -4648,7 +4648,8 @@ static void hci_le_conn_update_complete_evt(struct hci_dev *hdev, /* This function requires the caller holds hdev->lock */ static struct hci_conn *check_pending_le_conn(struct hci_dev *hdev, bdaddr_t *addr, - u8 addr_type, u8 adv_type) + u8 addr_type, u8 adv_type, + bdaddr_t *direct_rpa) { struct hci_conn *conn; struct hci_conn_params *params; @@ -4699,7 +4700,8 @@ static struct hci_conn *check_pending_le_conn(struct hci_dev *hdev, } conn = hci_connect_le(hdev, addr, addr_type, BT_SECURITY_LOW, - HCI_LE_AUTOCONN_TIMEOUT, HCI_ROLE_MASTER); + HCI_LE_AUTOCONN_TIMEOUT, HCI_ROLE_MASTER, + direct_rpa); if (!IS_ERR(conn)) { /* If HCI_AUTO_CONN_EXPLICIT is set, conn is already owned * by higher layer that tried to connect, if no then @@ -4808,8 +4810,13 @@ static void process_adv_report(struct hci_dev *hdev, u8 type, bdaddr_t *bdaddr, bdaddr_type = irk->addr_type; } - /* Check if we have been requested to connect to this device */ - conn = check_pending_le_conn(hdev, bdaddr, bdaddr_type, type); + /* Check if we have been requested to connect to this device. + * + * direct_addr is set only for directed advertising reports (it is NULL + * for advertising reports) and is already verified to be RPA above. + */ + conn = check_pending_le_conn(hdev, bdaddr, bdaddr_type, type, + direct_addr); if (conn && type == LE_ADV_IND) { /* Store report for later inclusion by * mgmt_device_connected diff --git a/net/bluetooth/l2cap_core.c b/net/bluetooth/l2cap_core.c index fc6615d59165..9b7907ebfa01 100644 --- a/net/bluetooth/l2cap_core.c +++ b/net/bluetooth/l2cap_core.c @@ -7156,7 +7156,7 @@ int l2cap_chan_connect(struct l2cap_chan *chan, __le16 psm, u16 cid, hcon = hci_connect_le(hdev, dst, dst_type, chan->sec_level, HCI_LE_CONN_TIMEOUT, - HCI_ROLE_SLAVE); + HCI_ROLE_SLAVE, NULL); else hcon = hci_connect_le_scan(hdev, dst, dst_type, chan->sec_level, diff --git a/net/ceph/Makefile b/net/ceph/Makefile index b4bded4b5396..12bf49772d24 100644 --- a/net/ceph/Makefile +++ b/net/ceph/Makefile @@ -8,6 +8,7 @@ libceph-y := ceph_common.o messenger.o msgpool.o buffer.o pagelist.o \ mon_client.o \ cls_lock_client.o \ osd_client.o osdmap.o crush/crush.o crush/mapper.o crush/hash.o \ + striper.o \ debugfs.o \ auth.o auth_none.o \ crypto.o armor.o \ diff --git a/net/ceph/ceph_common.c b/net/ceph/ceph_common.c index 4adf07826f4a..584fdbef2088 100644 --- a/net/ceph/ceph_common.c +++ b/net/ceph/ceph_common.c @@ -72,6 +72,7 @@ const char *ceph_msg_type_name(int type) case CEPH_MSG_MON_GET_VERSION: return "mon_get_version"; case CEPH_MSG_MON_GET_VERSION_REPLY: return "mon_get_version_reply"; case CEPH_MSG_MDS_MAP: return "mds_map"; + case CEPH_MSG_FS_MAP_USER: return "fs_map_user"; case CEPH_MSG_CLIENT_SESSION: return "client_session"; case CEPH_MSG_CLIENT_RECONNECT: return "client_reconnect"; case CEPH_MSG_CLIENT_REQUEST: return "client_request"; @@ -79,8 +80,13 @@ const char *ceph_msg_type_name(int type) case CEPH_MSG_CLIENT_REPLY: return "client_reply"; case CEPH_MSG_CLIENT_CAPS: return "client_caps"; case CEPH_MSG_CLIENT_CAPRELEASE: return "client_cap_release"; + case CEPH_MSG_CLIENT_QUOTA: return "client_quota"; case CEPH_MSG_CLIENT_SNAP: return "client_snap"; case CEPH_MSG_CLIENT_LEASE: return "client_lease"; + case CEPH_MSG_POOLOP_REPLY: return "poolop_reply"; + case CEPH_MSG_POOLOP: return "poolop"; + case CEPH_MSG_MON_COMMAND: return "mon_command"; + case CEPH_MSG_MON_COMMAND_ACK: return "mon_command_ack"; case CEPH_MSG_OSD_MAP: return "osd_map"; case CEPH_MSG_OSD_OP: return "osd_op"; case CEPH_MSG_OSD_OPREPLY: return "osd_opreply"; @@ -217,7 +223,7 @@ static int parse_fsid(const char *str, struct ceph_fsid *fsid) if (i == 16) err = 0; - dout("parse_fsid ret %d got fsid %pU", err, fsid); + dout("parse_fsid ret %d got fsid %pU\n", err, fsid); return err; } diff --git a/net/ceph/crypto.c b/net/ceph/crypto.c index bf9d079cbafd..02172c408ff2 100644 --- a/net/ceph/crypto.c +++ b/net/ceph/crypto.c @@ -347,10 +347,12 @@ struct key_type key_type_ceph = { .destroy = ceph_key_destroy, }; -int ceph_crypto_init(void) { +int __init ceph_crypto_init(void) +{ return register_key_type(&key_type_ceph); } -void ceph_crypto_shutdown(void) { +void ceph_crypto_shutdown(void) +{ unregister_key_type(&key_type_ceph); } diff --git a/net/ceph/debugfs.c b/net/ceph/debugfs.c index 1eef6806aa1a..02952605d121 100644 --- a/net/ceph/debugfs.c +++ b/net/ceph/debugfs.c @@ -389,7 +389,7 @@ CEPH_DEFINE_SHOW_FUNC(monc_show) CEPH_DEFINE_SHOW_FUNC(osdc_show) CEPH_DEFINE_SHOW_FUNC(client_options_show) -int ceph_debugfs_init(void) +int __init ceph_debugfs_init(void) { ceph_debugfs_dir = debugfs_create_dir("ceph", NULL); if (!ceph_debugfs_dir) @@ -418,7 +418,7 @@ int ceph_debugfs_client_init(struct ceph_client *client) goto out; client->monc.debugfs_file = debugfs_create_file("monc", - 0600, + 0400, client->debugfs_dir, client, &monc_show_fops); @@ -426,7 +426,7 @@ int ceph_debugfs_client_init(struct ceph_client *client) goto out; client->osdc.debugfs_file = debugfs_create_file("osdc", - 0600, + 0400, client->debugfs_dir, client, &osdc_show_fops); @@ -434,7 +434,7 @@ int ceph_debugfs_client_init(struct ceph_client *client) goto out; client->debugfs_monmap = debugfs_create_file("monmap", - 0600, + 0400, client->debugfs_dir, client, &monmap_show_fops); @@ -442,7 +442,7 @@ int ceph_debugfs_client_init(struct ceph_client *client) goto out; client->debugfs_osdmap = debugfs_create_file("osdmap", - 0600, + 0400, client->debugfs_dir, client, &osdmap_show_fops); @@ -450,7 +450,7 @@ int ceph_debugfs_client_init(struct ceph_client *client) goto out; client->debugfs_options = debugfs_create_file("client_options", - 0600, + 0400, client->debugfs_dir, client, &client_options_show_fops); @@ -477,7 +477,7 @@ void ceph_debugfs_client_cleanup(struct ceph_client *client) #else /* CONFIG_DEBUG_FS */ -int ceph_debugfs_init(void) +int __init ceph_debugfs_init(void) { return 0; } @@ -496,6 +496,3 @@ void ceph_debugfs_client_cleanup(struct ceph_client *client) } #endif /* CONFIG_DEBUG_FS */ - -EXPORT_SYMBOL(ceph_debugfs_init); -EXPORT_SYMBOL(ceph_debugfs_cleanup); diff --git a/net/ceph/messenger.c b/net/ceph/messenger.c index 8a4d3758030b..fcb40c12b1f8 100644 --- a/net/ceph/messenger.c +++ b/net/ceph/messenger.c @@ -277,7 +277,7 @@ static void _ceph_msgr_exit(void) ceph_msgr_slab_exit(); } -int ceph_msgr_init(void) +int __init ceph_msgr_init(void) { if (ceph_msgr_slab_init()) return -ENOMEM; @@ -299,7 +299,6 @@ int ceph_msgr_init(void) return -ENOMEM; } -EXPORT_SYMBOL(ceph_msgr_init); void ceph_msgr_exit(void) { @@ -307,7 +306,6 @@ void ceph_msgr_exit(void) _ceph_msgr_exit(); } -EXPORT_SYMBOL(ceph_msgr_exit); void ceph_msgr_flush(void) { @@ -839,93 +837,112 @@ static void ceph_msg_data_bio_cursor_init(struct ceph_msg_data_cursor *cursor, size_t length) { struct ceph_msg_data *data = cursor->data; - struct bio *bio; + struct ceph_bio_iter *it = &cursor->bio_iter; - BUG_ON(data->type != CEPH_MSG_DATA_BIO); + cursor->resid = min_t(size_t, length, data->bio_length); + *it = data->bio_pos; + if (cursor->resid < it->iter.bi_size) + it->iter.bi_size = cursor->resid; - bio = data->bio; - BUG_ON(!bio); - - cursor->resid = min(length, data->bio_length); - cursor->bio = bio; - cursor->bvec_iter = bio->bi_iter; - cursor->last_piece = - cursor->resid <= bio_iter_len(bio, cursor->bvec_iter); + BUG_ON(cursor->resid < bio_iter_len(it->bio, it->iter)); + cursor->last_piece = cursor->resid == bio_iter_len(it->bio, it->iter); } static struct page *ceph_msg_data_bio_next(struct ceph_msg_data_cursor *cursor, size_t *page_offset, size_t *length) { - struct ceph_msg_data *data = cursor->data; - struct bio *bio; - struct bio_vec bio_vec; - - BUG_ON(data->type != CEPH_MSG_DATA_BIO); - - bio = cursor->bio; - BUG_ON(!bio); - - bio_vec = bio_iter_iovec(bio, cursor->bvec_iter); - - *page_offset = (size_t) bio_vec.bv_offset; - BUG_ON(*page_offset >= PAGE_SIZE); - if (cursor->last_piece) /* pagelist offset is always 0 */ - *length = cursor->resid; - else - *length = (size_t) bio_vec.bv_len; - BUG_ON(*length > cursor->resid); - BUG_ON(*page_offset + *length > PAGE_SIZE); + struct bio_vec bv = bio_iter_iovec(cursor->bio_iter.bio, + cursor->bio_iter.iter); - return bio_vec.bv_page; + *page_offset = bv.bv_offset; + *length = bv.bv_len; + return bv.bv_page; } static bool ceph_msg_data_bio_advance(struct ceph_msg_data_cursor *cursor, size_t bytes) { - struct bio *bio; - struct bio_vec bio_vec; + struct ceph_bio_iter *it = &cursor->bio_iter; - BUG_ON(cursor->data->type != CEPH_MSG_DATA_BIO); + BUG_ON(bytes > cursor->resid); + BUG_ON(bytes > bio_iter_len(it->bio, it->iter)); + cursor->resid -= bytes; + bio_advance_iter(it->bio, &it->iter, bytes); - bio = cursor->bio; - BUG_ON(!bio); + if (!cursor->resid) { + BUG_ON(!cursor->last_piece); + return false; /* no more data */ + } - bio_vec = bio_iter_iovec(bio, cursor->bvec_iter); + if (!bytes || (it->iter.bi_size && it->iter.bi_bvec_done)) + return false; /* more bytes to process in this segment */ - /* Advance the cursor offset */ + if (!it->iter.bi_size) { + it->bio = it->bio->bi_next; + it->iter = it->bio->bi_iter; + if (cursor->resid < it->iter.bi_size) + it->iter.bi_size = cursor->resid; + } - BUG_ON(cursor->resid < bytes); - cursor->resid -= bytes; + BUG_ON(cursor->last_piece); + BUG_ON(cursor->resid < bio_iter_len(it->bio, it->iter)); + cursor->last_piece = cursor->resid == bio_iter_len(it->bio, it->iter); + return true; +} +#endif /* CONFIG_BLOCK */ - bio_advance_iter(bio, &cursor->bvec_iter, bytes); +static void ceph_msg_data_bvecs_cursor_init(struct ceph_msg_data_cursor *cursor, + size_t length) +{ + struct ceph_msg_data *data = cursor->data; + struct bio_vec *bvecs = data->bvec_pos.bvecs; - if (bytes < bio_vec.bv_len) - return false; /* more bytes to process in this segment */ + cursor->resid = min_t(size_t, length, data->bvec_pos.iter.bi_size); + cursor->bvec_iter = data->bvec_pos.iter; + cursor->bvec_iter.bi_size = cursor->resid; - /* Move on to the next segment, and possibly the next bio */ + BUG_ON(cursor->resid < bvec_iter_len(bvecs, cursor->bvec_iter)); + cursor->last_piece = + cursor->resid == bvec_iter_len(bvecs, cursor->bvec_iter); +} - if (!cursor->bvec_iter.bi_size) { - bio = bio->bi_next; - cursor->bio = bio; - if (bio) - cursor->bvec_iter = bio->bi_iter; - else - memset(&cursor->bvec_iter, 0, - sizeof(cursor->bvec_iter)); - } +static struct page *ceph_msg_data_bvecs_next(struct ceph_msg_data_cursor *cursor, + size_t *page_offset, + size_t *length) +{ + struct bio_vec bv = bvec_iter_bvec(cursor->data->bvec_pos.bvecs, + cursor->bvec_iter); + + *page_offset = bv.bv_offset; + *length = bv.bv_len; + return bv.bv_page; +} + +static bool ceph_msg_data_bvecs_advance(struct ceph_msg_data_cursor *cursor, + size_t bytes) +{ + struct bio_vec *bvecs = cursor->data->bvec_pos.bvecs; + + BUG_ON(bytes > cursor->resid); + BUG_ON(bytes > bvec_iter_len(bvecs, cursor->bvec_iter)); + cursor->resid -= bytes; + bvec_iter_advance(bvecs, &cursor->bvec_iter, bytes); - if (!cursor->last_piece) { - BUG_ON(!cursor->resid); - BUG_ON(!bio); - /* A short read is OK, so use <= rather than == */ - if (cursor->resid <= bio_iter_len(bio, cursor->bvec_iter)) - cursor->last_piece = true; + if (!cursor->resid) { + BUG_ON(!cursor->last_piece); + return false; /* no more data */ } + if (!bytes || cursor->bvec_iter.bi_bvec_done) + return false; /* more bytes to process in this segment */ + + BUG_ON(cursor->last_piece); + BUG_ON(cursor->resid < bvec_iter_len(bvecs, cursor->bvec_iter)); + cursor->last_piece = + cursor->resid == bvec_iter_len(bvecs, cursor->bvec_iter); return true; } -#endif /* CONFIG_BLOCK */ /* * For a page array, a piece comes from the first page in the array @@ -1110,6 +1127,9 @@ static void __ceph_msg_data_cursor_init(struct ceph_msg_data_cursor *cursor) ceph_msg_data_bio_cursor_init(cursor, length); break; #endif /* CONFIG_BLOCK */ + case CEPH_MSG_DATA_BVECS: + ceph_msg_data_bvecs_cursor_init(cursor, length); + break; case CEPH_MSG_DATA_NONE: default: /* BUG(); */ @@ -1158,14 +1178,19 @@ static struct page *ceph_msg_data_next(struct ceph_msg_data_cursor *cursor, page = ceph_msg_data_bio_next(cursor, page_offset, length); break; #endif /* CONFIG_BLOCK */ + case CEPH_MSG_DATA_BVECS: + page = ceph_msg_data_bvecs_next(cursor, page_offset, length); + break; case CEPH_MSG_DATA_NONE: default: page = NULL; break; } + BUG_ON(!page); BUG_ON(*page_offset + *length > PAGE_SIZE); BUG_ON(!*length); + BUG_ON(*length > cursor->resid); if (last_piece) *last_piece = cursor->last_piece; @@ -1194,6 +1219,9 @@ static void ceph_msg_data_advance(struct ceph_msg_data_cursor *cursor, new_piece = ceph_msg_data_bio_advance(cursor, bytes); break; #endif /* CONFIG_BLOCK */ + case CEPH_MSG_DATA_BVECS: + new_piece = ceph_msg_data_bvecs_advance(cursor, bytes); + break; case CEPH_MSG_DATA_NONE: default: BUG(); @@ -1575,13 +1603,18 @@ static int write_partial_message_data(struct ceph_connection *con) * been revoked, so use the zero page. */ crc = do_datacrc ? le32_to_cpu(msg->footer.data_crc) : 0; - while (cursor->resid) { + while (cursor->total_resid) { struct page *page; size_t page_offset; size_t length; bool last_piece; int ret; + if (!cursor->resid) { + ceph_msg_data_advance(cursor, 0); + continue; + } + page = ceph_msg_data_next(cursor, &page_offset, &length, &last_piece); ret = ceph_tcp_sendpage(con->sock, page, page_offset, @@ -2297,7 +2330,12 @@ static int read_partial_msg_data(struct ceph_connection *con) if (do_datacrc) crc = con->in_data_crc; - while (cursor->resid) { + while (cursor->total_resid) { + if (!cursor->resid) { + ceph_msg_data_advance(cursor, 0); + continue; + } + page = ceph_msg_data_next(cursor, &page_offset, &length, NULL); ret = ceph_tcp_recvpage(con->sock, page, page_offset, length); if (ret <= 0) { @@ -3262,16 +3300,14 @@ void ceph_msg_data_add_pagelist(struct ceph_msg *msg, EXPORT_SYMBOL(ceph_msg_data_add_pagelist); #ifdef CONFIG_BLOCK -void ceph_msg_data_add_bio(struct ceph_msg *msg, struct bio *bio, - size_t length) +void ceph_msg_data_add_bio(struct ceph_msg *msg, struct ceph_bio_iter *bio_pos, + u32 length) { struct ceph_msg_data *data; - BUG_ON(!bio); - data = ceph_msg_data_create(CEPH_MSG_DATA_BIO); BUG_ON(!data); - data->bio = bio; + data->bio_pos = *bio_pos; data->bio_length = length; list_add_tail(&data->links, &msg->data); @@ -3280,6 +3316,20 @@ void ceph_msg_data_add_bio(struct ceph_msg *msg, struct bio *bio, EXPORT_SYMBOL(ceph_msg_data_add_bio); #endif /* CONFIG_BLOCK */ +void ceph_msg_data_add_bvecs(struct ceph_msg *msg, + struct ceph_bvec_iter *bvec_pos) +{ + struct ceph_msg_data *data; + + data = ceph_msg_data_create(CEPH_MSG_DATA_BVECS); + BUG_ON(!data); + data->bvec_pos = *bvec_pos; + + list_add_tail(&data->links, &msg->data); + msg->data_length += bvec_pos->iter.bi_size; +} +EXPORT_SYMBOL(ceph_msg_data_add_bvecs); + /* * construct a new message with given type, size * the new msg has a ref count of 1. diff --git a/net/ceph/mon_client.c b/net/ceph/mon_client.c index 1547107f4854..b3dac24412d3 100644 --- a/net/ceph/mon_client.c +++ b/net/ceph/mon_client.c @@ -60,7 +60,7 @@ struct ceph_monmap *ceph_monmap_decode(void *p, void *end) num_mon = ceph_decode_32(&p); ceph_decode_need(&p, end, num_mon*sizeof(m->mon_inst[0]), bad); - if (num_mon >= CEPH_MAX_MON) + if (num_mon > CEPH_MAX_MON) goto bad; m = kmalloc(sizeof(*m) + sizeof(m->mon_inst[0])*num_mon, GFP_NOFS); if (m == NULL) diff --git a/net/ceph/osd_client.c b/net/ceph/osd_client.c index 2814dba5902d..ea2a6c9fb7ce 100644 --- a/net/ceph/osd_client.c +++ b/net/ceph/osd_client.c @@ -20,6 +20,7 @@ #include <linux/ceph/decode.h> #include <linux/ceph/auth.h> #include <linux/ceph/pagelist.h> +#include <linux/ceph/striper.h> #define OSD_OPREPLY_FRONT_LEN 512 @@ -103,13 +104,12 @@ static int calc_layout(struct ceph_file_layout *layout, u64 off, u64 *plen, u64 *objnum, u64 *objoff, u64 *objlen) { u64 orig_len = *plen; - int r; + u32 xlen; /* object extent? */ - r = ceph_calc_file_object_mapping(layout, off, orig_len, objnum, - objoff, objlen); - if (r < 0) - return r; + ceph_calc_file_object_mapping(layout, off, orig_len, objnum, + objoff, &xlen); + *objlen = xlen; if (*objlen < orig_len) { *plen = *objlen; dout(" skipping last %llu, final file extent %llu~%llu\n", @@ -117,7 +117,6 @@ static int calc_layout(struct ceph_file_layout *layout, u64 off, u64 *plen, } dout("calc_layout objnum=%llx %llu~%llu\n", *objnum, *objoff, *objlen); - return 0; } @@ -148,14 +147,22 @@ static void ceph_osd_data_pagelist_init(struct ceph_osd_data *osd_data, #ifdef CONFIG_BLOCK static void ceph_osd_data_bio_init(struct ceph_osd_data *osd_data, - struct bio *bio, size_t bio_length) + struct ceph_bio_iter *bio_pos, + u32 bio_length) { osd_data->type = CEPH_OSD_DATA_TYPE_BIO; - osd_data->bio = bio; + osd_data->bio_pos = *bio_pos; osd_data->bio_length = bio_length; } #endif /* CONFIG_BLOCK */ +static void ceph_osd_data_bvecs_init(struct ceph_osd_data *osd_data, + struct ceph_bvec_iter *bvec_pos) +{ + osd_data->type = CEPH_OSD_DATA_TYPE_BVECS; + osd_data->bvec_pos = *bvec_pos; +} + #define osd_req_op_data(oreq, whch, typ, fld) \ ({ \ struct ceph_osd_request *__oreq = (oreq); \ @@ -218,16 +225,29 @@ EXPORT_SYMBOL(osd_req_op_extent_osd_data_pagelist); #ifdef CONFIG_BLOCK void osd_req_op_extent_osd_data_bio(struct ceph_osd_request *osd_req, - unsigned int which, struct bio *bio, size_t bio_length) + unsigned int which, + struct ceph_bio_iter *bio_pos, + u32 bio_length) { struct ceph_osd_data *osd_data; osd_data = osd_req_op_data(osd_req, which, extent, osd_data); - ceph_osd_data_bio_init(osd_data, bio, bio_length); + ceph_osd_data_bio_init(osd_data, bio_pos, bio_length); } EXPORT_SYMBOL(osd_req_op_extent_osd_data_bio); #endif /* CONFIG_BLOCK */ +void osd_req_op_extent_osd_data_bvec_pos(struct ceph_osd_request *osd_req, + unsigned int which, + struct ceph_bvec_iter *bvec_pos) +{ + struct ceph_osd_data *osd_data; + + osd_data = osd_req_op_data(osd_req, which, extent, osd_data); + ceph_osd_data_bvecs_init(osd_data, bvec_pos); +} +EXPORT_SYMBOL(osd_req_op_extent_osd_data_bvec_pos); + static void osd_req_op_cls_request_info_pagelist( struct ceph_osd_request *osd_req, unsigned int which, struct ceph_pagelist *pagelist) @@ -265,6 +285,23 @@ void osd_req_op_cls_request_data_pages(struct ceph_osd_request *osd_req, } EXPORT_SYMBOL(osd_req_op_cls_request_data_pages); +void osd_req_op_cls_request_data_bvecs(struct ceph_osd_request *osd_req, + unsigned int which, + struct bio_vec *bvecs, u32 bytes) +{ + struct ceph_osd_data *osd_data; + struct ceph_bvec_iter it = { + .bvecs = bvecs, + .iter = { .bi_size = bytes }, + }; + + osd_data = osd_req_op_data(osd_req, which, cls, request_data); + ceph_osd_data_bvecs_init(osd_data, &it); + osd_req->r_ops[which].cls.indata_len += bytes; + osd_req->r_ops[which].indata_len += bytes; +} +EXPORT_SYMBOL(osd_req_op_cls_request_data_bvecs); + void osd_req_op_cls_response_data_pages(struct ceph_osd_request *osd_req, unsigned int which, struct page **pages, u64 length, u32 alignment, bool pages_from_pool, bool own_pages) @@ -290,6 +327,8 @@ static u64 ceph_osd_data_length(struct ceph_osd_data *osd_data) case CEPH_OSD_DATA_TYPE_BIO: return (u64)osd_data->bio_length; #endif /* CONFIG_BLOCK */ + case CEPH_OSD_DATA_TYPE_BVECS: + return osd_data->bvec_pos.iter.bi_size; default: WARN(true, "unrecognized data type %d\n", (int)osd_data->type); return 0; @@ -828,8 +867,10 @@ static void ceph_osdc_msg_data_add(struct ceph_msg *msg, ceph_msg_data_add_pagelist(msg, osd_data->pagelist); #ifdef CONFIG_BLOCK } else if (osd_data->type == CEPH_OSD_DATA_TYPE_BIO) { - ceph_msg_data_add_bio(msg, osd_data->bio, length); + ceph_msg_data_add_bio(msg, &osd_data->bio_pos, length); #endif + } else if (osd_data->type == CEPH_OSD_DATA_TYPE_BVECS) { + ceph_msg_data_add_bvecs(msg, &osd_data->bvec_pos); } else { BUG_ON(osd_data->type != CEPH_OSD_DATA_TYPE_NONE); } @@ -5065,7 +5106,7 @@ int ceph_osdc_writepages(struct ceph_osd_client *osdc, struct ceph_vino vino, } EXPORT_SYMBOL(ceph_osdc_writepages); -int ceph_osdc_setup(void) +int __init ceph_osdc_setup(void) { size_t size = sizeof(struct ceph_osd_request) + CEPH_OSD_SLAB_OPS * sizeof(struct ceph_osd_req_op); @@ -5076,7 +5117,6 @@ int ceph_osdc_setup(void) return ceph_osd_request_cache ? 0 : -ENOMEM; } -EXPORT_SYMBOL(ceph_osdc_setup); void ceph_osdc_cleanup(void) { @@ -5084,7 +5124,6 @@ void ceph_osdc_cleanup(void) kmem_cache_destroy(ceph_osd_request_cache); ceph_osd_request_cache = NULL; } -EXPORT_SYMBOL(ceph_osdc_cleanup); /* * handle incoming message diff --git a/net/ceph/osdmap.c b/net/ceph/osdmap.c index 0da27c66349a..9645ffd6acfb 100644 --- a/net/ceph/osdmap.c +++ b/net/ceph/osdmap.c @@ -4,7 +4,6 @@ #include <linux/module.h> #include <linux/slab.h> -#include <asm/div64.h> #include <linux/ceph/libceph.h> #include <linux/ceph/osdmap.h> @@ -2141,76 +2140,6 @@ bool ceph_osds_changed(const struct ceph_osds *old_acting, } /* - * calculate file layout from given offset, length. - * fill in correct oid, logical length, and object extent - * offset, length. - * - * for now, we write only a single su, until we can - * pass a stride back to the caller. - */ -int ceph_calc_file_object_mapping(struct ceph_file_layout *layout, - u64 off, u64 len, - u64 *ono, - u64 *oxoff, u64 *oxlen) -{ - u32 osize = layout->object_size; - u32 su = layout->stripe_unit; - u32 sc = layout->stripe_count; - u32 bl, stripeno, stripepos, objsetno; - u32 su_per_object; - u64 t, su_offset; - - dout("mapping %llu~%llu osize %u fl_su %u\n", off, len, - osize, su); - if (su == 0 || sc == 0) - goto invalid; - su_per_object = osize / su; - if (su_per_object == 0) - goto invalid; - dout("osize %u / su %u = su_per_object %u\n", osize, su, - su_per_object); - - if ((su & ~PAGE_MASK) != 0) - goto invalid; - - /* bl = *off / su; */ - t = off; - do_div(t, su); - bl = t; - dout("off %llu / su %u = bl %u\n", off, su, bl); - - stripeno = bl / sc; - stripepos = bl % sc; - objsetno = stripeno / su_per_object; - - *ono = objsetno * sc + stripepos; - dout("objset %u * sc %u = ono %u\n", objsetno, sc, (unsigned int)*ono); - - /* *oxoff = *off % layout->fl_stripe_unit; # offset in su */ - t = off; - su_offset = do_div(t, su); - *oxoff = su_offset + (stripeno % su_per_object) * su; - - /* - * Calculate the length of the extent being written to the selected - * object. This is the minimum of the full length requested (len) or - * the remainder of the current stripe being written to. - */ - *oxlen = min_t(u64, len, su - su_offset); - - dout(" obj extent %llu~%llu\n", *oxoff, *oxlen); - return 0; - -invalid: - dout(" invalid layout\n"); - *ono = 0; - *oxoff = 0; - *oxlen = 0; - return -EINVAL; -} -EXPORT_SYMBOL(ceph_calc_file_object_mapping); - -/* * Map an object into a PG. * * Should only be called with target_oid and target_oloc (as opposed to diff --git a/net/ceph/striper.c b/net/ceph/striper.c new file mode 100644 index 000000000000..c36462dc86b7 --- /dev/null +++ b/net/ceph/striper.c @@ -0,0 +1,261 @@ +/* SPDX-License-Identifier: GPL-2.0 */ + +#include <linux/ceph/ceph_debug.h> + +#include <linux/math64.h> +#include <linux/slab.h> + +#include <linux/ceph/striper.h> +#include <linux/ceph/types.h> + +/* + * Map a file extent to a stripe unit within an object. + * Fill in objno, offset into object, and object extent length (i.e. the + * number of bytes mapped, less than or equal to @l->stripe_unit). + * + * Example for stripe_count = 3, stripes_per_object = 4: + * + * blockno | 0 3 6 9 | 1 4 7 10 | 2 5 8 11 | 12 15 18 21 | 13 16 19 + * stripeno | 0 1 2 3 | 0 1 2 3 | 0 1 2 3 | 4 5 6 7 | 4 5 6 + * stripepos | 0 | 1 | 2 | 0 | 1 + * objno | 0 | 1 | 2 | 3 | 4 + * objsetno | 0 | 1 + */ +void ceph_calc_file_object_mapping(struct ceph_file_layout *l, + u64 off, u64 len, + u64 *objno, u64 *objoff, u32 *xlen) +{ + u32 stripes_per_object = l->object_size / l->stripe_unit; + u64 blockno; /* which su in the file (i.e. globally) */ + u32 blockoff; /* offset into su */ + u64 stripeno; /* which stripe */ + u32 stripepos; /* which su in the stripe, + which object in the object set */ + u64 objsetno; /* which object set */ + u32 objsetpos; /* which stripe in the object set */ + + blockno = div_u64_rem(off, l->stripe_unit, &blockoff); + stripeno = div_u64_rem(blockno, l->stripe_count, &stripepos); + objsetno = div_u64_rem(stripeno, stripes_per_object, &objsetpos); + + *objno = objsetno * l->stripe_count + stripepos; + *objoff = objsetpos * l->stripe_unit + blockoff; + *xlen = min_t(u64, len, l->stripe_unit - blockoff); +} +EXPORT_SYMBOL(ceph_calc_file_object_mapping); + +/* + * Return the last extent with given objno (@object_extents is sorted + * by objno). If not found, return NULL and set @add_pos so that the + * new extent can be added with list_add(add_pos, new_ex). + */ +static struct ceph_object_extent * +lookup_last(struct list_head *object_extents, u64 objno, + struct list_head **add_pos) +{ + struct list_head *pos; + + list_for_each_prev(pos, object_extents) { + struct ceph_object_extent *ex = + list_entry(pos, typeof(*ex), oe_item); + + if (ex->oe_objno == objno) + return ex; + + if (ex->oe_objno < objno) + break; + } + + *add_pos = pos; + return NULL; +} + +static struct ceph_object_extent * +lookup_containing(struct list_head *object_extents, u64 objno, + u64 objoff, u32 xlen) +{ + struct ceph_object_extent *ex; + + list_for_each_entry(ex, object_extents, oe_item) { + if (ex->oe_objno == objno && + ex->oe_off <= objoff && + ex->oe_off + ex->oe_len >= objoff + xlen) /* paranoia */ + return ex; + + if (ex->oe_objno > objno) + break; + } + + return NULL; +} + +/* + * Map a file extent to a sorted list of object extents. + * + * We want only one (or as few as possible) object extents per object. + * Adjacent object extents will be merged together, each returned object + * extent may reverse map to multiple different file extents. + * + * Call @alloc_fn for each new object extent and @action_fn for each + * mapped stripe unit, whether it was merged into an already allocated + * object extent or started a new object extent. + * + * Newly allocated object extents are added to @object_extents. + * To keep @object_extents sorted, successive calls to this function + * must map successive file extents (i.e. the list of file extents that + * are mapped using the same @object_extents must be sorted). + * + * The caller is responsible for @object_extents. + */ +int ceph_file_to_extents(struct ceph_file_layout *l, u64 off, u64 len, + struct list_head *object_extents, + struct ceph_object_extent *alloc_fn(void *arg), + void *alloc_arg, + ceph_object_extent_fn_t action_fn, + void *action_arg) +{ + struct ceph_object_extent *last_ex, *ex; + + while (len) { + struct list_head *add_pos = NULL; + u64 objno, objoff; + u32 xlen; + + ceph_calc_file_object_mapping(l, off, len, &objno, &objoff, + &xlen); + + last_ex = lookup_last(object_extents, objno, &add_pos); + if (!last_ex || last_ex->oe_off + last_ex->oe_len != objoff) { + ex = alloc_fn(alloc_arg); + if (!ex) + return -ENOMEM; + + ex->oe_objno = objno; + ex->oe_off = objoff; + ex->oe_len = xlen; + if (action_fn) + action_fn(ex, xlen, action_arg); + + if (!last_ex) + list_add(&ex->oe_item, add_pos); + else + list_add(&ex->oe_item, &last_ex->oe_item); + } else { + last_ex->oe_len += xlen; + if (action_fn) + action_fn(last_ex, xlen, action_arg); + } + + off += xlen; + len -= xlen; + } + + for (last_ex = list_first_entry(object_extents, typeof(*ex), oe_item), + ex = list_next_entry(last_ex, oe_item); + &ex->oe_item != object_extents; + last_ex = ex, ex = list_next_entry(ex, oe_item)) { + if (last_ex->oe_objno > ex->oe_objno || + (last_ex->oe_objno == ex->oe_objno && + last_ex->oe_off + last_ex->oe_len >= ex->oe_off)) { + WARN(1, "%s: object_extents list not sorted!\n", + __func__); + return -EINVAL; + } + } + + return 0; +} +EXPORT_SYMBOL(ceph_file_to_extents); + +/* + * A stripped down, non-allocating version of ceph_file_to_extents(), + * for when @object_extents is already populated. + */ +int ceph_iterate_extents(struct ceph_file_layout *l, u64 off, u64 len, + struct list_head *object_extents, + ceph_object_extent_fn_t action_fn, + void *action_arg) +{ + while (len) { + struct ceph_object_extent *ex; + u64 objno, objoff; + u32 xlen; + + ceph_calc_file_object_mapping(l, off, len, &objno, &objoff, + &xlen); + + ex = lookup_containing(object_extents, objno, objoff, xlen); + if (!ex) { + WARN(1, "%s: objno %llu %llu~%u not found!\n", + __func__, objno, objoff, xlen); + return -EINVAL; + } + + action_fn(ex, xlen, action_arg); + + off += xlen; + len -= xlen; + } + + return 0; +} +EXPORT_SYMBOL(ceph_iterate_extents); + +/* + * Reverse map an object extent to a sorted list of file extents. + * + * On success, the caller is responsible for: + * + * kfree(file_extents) + */ +int ceph_extent_to_file(struct ceph_file_layout *l, + u64 objno, u64 objoff, u64 objlen, + struct ceph_file_extent **file_extents, + u32 *num_file_extents) +{ + u32 stripes_per_object = l->object_size / l->stripe_unit; + u64 blockno; /* which su */ + u32 blockoff; /* offset into su */ + u64 stripeno; /* which stripe */ + u32 stripepos; /* which su in the stripe, + which object in the object set */ + u64 objsetno; /* which object set */ + u32 i = 0; + + if (!objlen) { + *file_extents = NULL; + *num_file_extents = 0; + return 0; + } + + *num_file_extents = DIV_ROUND_UP_ULL(objoff + objlen, l->stripe_unit) - + DIV_ROUND_DOWN_ULL(objoff, l->stripe_unit); + *file_extents = kmalloc_array(*num_file_extents, sizeof(**file_extents), + GFP_NOIO); + if (!*file_extents) + return -ENOMEM; + + div_u64_rem(objoff, l->stripe_unit, &blockoff); + while (objlen) { + u64 off, len; + + objsetno = div_u64_rem(objno, l->stripe_count, &stripepos); + stripeno = div_u64(objoff, l->stripe_unit) + + objsetno * stripes_per_object; + blockno = stripeno * l->stripe_count + stripepos; + off = blockno * l->stripe_unit + blockoff; + len = min_t(u64, objlen, l->stripe_unit - blockoff); + + (*file_extents)[i].fe_off = off; + (*file_extents)[i].fe_len = len; + + blockoff = 0; + objoff += len; + objlen -= len; + i++; + } + + BUG_ON(i != *num_file_extents); + return 0; +} +EXPORT_SYMBOL(ceph_extent_to_file); diff --git a/net/core/dev.c b/net/core/dev.c index 9b04a9fd1dfd..969462ebb296 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -1027,7 +1027,7 @@ bool dev_valid_name(const char *name) { if (*name == '\0') return false; - if (strlen(name) >= IFNAMSIZ) + if (strnlen(name, IFNAMSIZ) == IFNAMSIZ) return false; if (!strcmp(name, ".") || !strcmp(name, "..")) return false; diff --git a/net/core/dev_addr_lists.c b/net/core/dev_addr_lists.c index c0548d268e1a..e3e6a3e2ca22 100644 --- a/net/core/dev_addr_lists.c +++ b/net/core/dev_addr_lists.c @@ -57,8 +57,8 @@ static int __hw_addr_add_ex(struct netdev_hw_addr_list *list, return -EINVAL; list_for_each_entry(ha, &list->list, list) { - if (!memcmp(ha->addr, addr, addr_len) && - ha->type == addr_type) { + if (ha->type == addr_type && + !memcmp(ha->addr, addr, addr_len)) { if (global) { /* check if addr is already used as global */ if (ha->global_use) diff --git a/net/core/devlink.c b/net/core/devlink.c index 9236e421bd62..ad1317376798 100644 --- a/net/core/devlink.c +++ b/net/core/devlink.c @@ -2405,6 +2405,16 @@ devlink_resource_size_params_put(struct devlink_resource *resource, return 0; } +static int devlink_resource_occ_put(struct devlink_resource *resource, + struct sk_buff *skb) +{ + if (!resource->occ_get) + return 0; + return nla_put_u64_64bit(skb, DEVLINK_ATTR_RESOURCE_OCC, + resource->occ_get(resource->occ_get_priv), + DEVLINK_ATTR_PAD); +} + static int devlink_resource_put(struct devlink *devlink, struct sk_buff *skb, struct devlink_resource *resource) { @@ -2425,11 +2435,8 @@ static int devlink_resource_put(struct devlink *devlink, struct sk_buff *skb, if (resource->size != resource->size_new) nla_put_u64_64bit(skb, DEVLINK_ATTR_RESOURCE_SIZE_NEW, resource->size_new, DEVLINK_ATTR_PAD); - if (resource->resource_ops && resource->resource_ops->occ_get) - if (nla_put_u64_64bit(skb, DEVLINK_ATTR_RESOURCE_OCC, - resource->resource_ops->occ_get(devlink), - DEVLINK_ATTR_PAD)) - goto nla_put_failure; + if (devlink_resource_occ_put(resource, skb)) + goto nla_put_failure; if (devlink_resource_size_params_put(resource, skb)) goto nla_put_failure; if (list_empty(&resource->resource_list)) @@ -3162,15 +3169,13 @@ EXPORT_SYMBOL_GPL(devlink_dpipe_table_unregister); * @resource_id: resource's id * @parent_reosurce_id: resource's parent id * @size params: size parameters - * @resource_ops: resource ops */ int devlink_resource_register(struct devlink *devlink, const char *resource_name, u64 resource_size, u64 resource_id, u64 parent_resource_id, - const struct devlink_resource_size_params *size_params, - const struct devlink_resource_ops *resource_ops) + const struct devlink_resource_size_params *size_params) { struct devlink_resource *resource; struct list_head *resource_list; @@ -3213,7 +3218,6 @@ int devlink_resource_register(struct devlink *devlink, resource->size = resource_size; resource->size_new = resource_size; resource->id = resource_id; - resource->resource_ops = resource_ops; resource->size_valid = true; memcpy(&resource->size_params, size_params, sizeof(resource->size_params)); @@ -3315,6 +3319,58 @@ out: } EXPORT_SYMBOL_GPL(devlink_dpipe_table_resource_set); +/** + * devlink_resource_occ_get_register - register occupancy getter + * + * @devlink: devlink + * @resource_id: resource id + * @occ_get: occupancy getter callback + * @occ_get_priv: occupancy getter callback priv + */ +void devlink_resource_occ_get_register(struct devlink *devlink, + u64 resource_id, + devlink_resource_occ_get_t *occ_get, + void *occ_get_priv) +{ + struct devlink_resource *resource; + + mutex_lock(&devlink->lock); + resource = devlink_resource_find(devlink, NULL, resource_id); + if (WARN_ON(!resource)) + goto out; + WARN_ON(resource->occ_get); + + resource->occ_get = occ_get; + resource->occ_get_priv = occ_get_priv; +out: + mutex_unlock(&devlink->lock); +} +EXPORT_SYMBOL_GPL(devlink_resource_occ_get_register); + +/** + * devlink_resource_occ_get_unregister - unregister occupancy getter + * + * @devlink: devlink + * @resource_id: resource id + */ +void devlink_resource_occ_get_unregister(struct devlink *devlink, + u64 resource_id) +{ + struct devlink_resource *resource; + + mutex_lock(&devlink->lock); + resource = devlink_resource_find(devlink, NULL, resource_id); + if (WARN_ON(!resource)) + goto out; + WARN_ON(!resource->occ_get); + + resource->occ_get = NULL; + resource->occ_get_priv = NULL; +out: + mutex_unlock(&devlink->lock); +} +EXPORT_SYMBOL_GPL(devlink_resource_occ_get_unregister); + static int __init devlink_module_init(void) { return genl_register_family(&devlink_nl_family); diff --git a/net/core/skbuff.c b/net/core/skbuff.c index 1bca1e0fc8f7..345b51837ca8 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -857,6 +857,7 @@ static struct sk_buff *__skb_clone(struct sk_buff *n, struct sk_buff *skb) n->hdr_len = skb->nohdr ? skb_headroom(skb) : skb->hdr_len; n->cloned = 1; n->nohdr = 0; + n->peeked = 0; n->destructor = NULL; C(tail); C(end); diff --git a/net/core/sysctl_net_core.c b/net/core/sysctl_net_core.c index b3b609f0eeb5..b1a2c5e38530 100644 --- a/net/core/sysctl_net_core.c +++ b/net/core/sysctl_net_core.c @@ -15,7 +15,6 @@ #include <linux/vmalloc.h> #include <linux/init.h> #include <linux/slab.h> -#include <linux/kmemleak.h> #include <net/ip.h> #include <net/sock.h> diff --git a/net/core/utils.c b/net/core/utils.c index 93066bd0305a..d47863b07a60 100644 --- a/net/core/utils.c +++ b/net/core/utils.c @@ -403,6 +403,29 @@ int inet_pton_with_scope(struct net *net, __kernel_sa_family_t af, } EXPORT_SYMBOL(inet_pton_with_scope); +bool inet_addr_is_any(struct sockaddr *addr) +{ + if (addr->sa_family == AF_INET6) { + struct sockaddr_in6 *in6 = (struct sockaddr_in6 *)addr; + const struct sockaddr_in6 in6_any = + { .sin6_addr = IN6ADDR_ANY_INIT }; + + if (!memcmp(in6->sin6_addr.s6_addr, + in6_any.sin6_addr.s6_addr, 16)) + return true; + } else if (addr->sa_family == AF_INET) { + struct sockaddr_in *in = (struct sockaddr_in *)addr; + + if (in->sin_addr.s_addr == htonl(INADDR_ANY)) + return true; + } else { + pr_warn("unexpected address family %u\n", addr->sa_family); + } + + return false; +} +EXPORT_SYMBOL(inet_addr_is_any); + void inet_proto_csum_replace4(__sum16 *sum, struct sk_buff *skb, __be32 from, __be32 to, bool pseudohdr) { diff --git a/net/dccp/ipv4.c b/net/dccp/ipv4.c index e65fcb45c3f6..b08feb219b44 100644 --- a/net/dccp/ipv4.c +++ b/net/dccp/ipv4.c @@ -614,6 +614,7 @@ int dccp_v4_conn_request(struct sock *sk, struct sk_buff *skb) ireq = inet_rsk(req); sk_rcv_saddr_set(req_to_sk(req), ip_hdr(skb)->daddr); sk_daddr_set(req_to_sk(req), ip_hdr(skb)->saddr); + ireq->ir_mark = inet_request_mark(sk, skb); ireq->ireq_family = AF_INET; ireq->ir_iif = sk->sk_bound_dev_if; diff --git a/net/dccp/ipv6.c b/net/dccp/ipv6.c index 5df7857fc0f3..6344f1b18a6a 100644 --- a/net/dccp/ipv6.c +++ b/net/dccp/ipv6.c @@ -351,6 +351,7 @@ static int dccp_v6_conn_request(struct sock *sk, struct sk_buff *skb) ireq->ir_v6_rmt_addr = ipv6_hdr(skb)->saddr; ireq->ir_v6_loc_addr = ipv6_hdr(skb)->daddr; ireq->ireq_family = AF_INET6; + ireq->ir_mark = inet_request_mark(sk, skb); if (ipv6_opt_accepted(sk, skb, IP6CB(skb)) || np->rxopt.bits.rxinfo || np->rxopt.bits.rxoinfo || diff --git a/net/dsa/dsa_priv.h b/net/dsa/dsa_priv.h index 70de7895e5b8..053731473c99 100644 --- a/net/dsa/dsa_priv.h +++ b/net/dsa/dsa_priv.h @@ -126,6 +126,7 @@ static inline struct net_device *dsa_master_find_slave(struct net_device *dev, struct dsa_port *cpu_dp = dev->dsa_ptr; struct dsa_switch_tree *dst = cpu_dp->dst; struct dsa_switch *ds; + struct dsa_port *slave_port; if (device < 0 || device >= DSA_MAX_SWITCHES) return NULL; @@ -137,7 +138,12 @@ static inline struct net_device *dsa_master_find_slave(struct net_device *dev, if (port < 0 || port >= ds->num_ports) return NULL; - return ds->ports[port].slave; + slave_port = &ds->ports[port]; + + if (unlikely(slave_port->type != DSA_PORT_TYPE_USER)) + return NULL; + + return slave_port->slave; } /* port.c */ diff --git a/net/ieee802154/6lowpan/reassembly.c b/net/ieee802154/6lowpan/reassembly.c index 44f148a6bb57..1790b65944b3 100644 --- a/net/ieee802154/6lowpan/reassembly.c +++ b/net/ieee802154/6lowpan/reassembly.c @@ -411,7 +411,6 @@ err: } #ifdef CONFIG_SYSCTL -static long zero; static struct ctl_table lowpan_frags_ns_ctl_table[] = { { @@ -428,7 +427,6 @@ static struct ctl_table lowpan_frags_ns_ctl_table[] = { .maxlen = sizeof(unsigned long), .mode = 0644, .proc_handler = proc_doulongvec_minmax, - .extra1 = &zero, .extra2 = &init_net.ieee802154_lowpan.frags.high_thresh }, { diff --git a/net/ipv4/arp.c b/net/ipv4/arp.c index be4c595edccb..bf6c2d4d4fdc 100644 --- a/net/ipv4/arp.c +++ b/net/ipv4/arp.c @@ -437,7 +437,7 @@ static int arp_filter(__be32 sip, __be32 tip, struct net_device *dev) /*unsigned long now; */ struct net *net = dev_net(dev); - rt = ip_route_output(net, sip, tip, 0, 0); + rt = ip_route_output(net, sip, tip, 0, l3mdev_master_ifindex_rcu(dev)); if (IS_ERR(rt)) return 1; if (rt->dst.dev != dev) { diff --git a/net/ipv4/inet_timewait_sock.c b/net/ipv4/inet_timewait_sock.c index c3ea4906d237..88c5069b5d20 100644 --- a/net/ipv4/inet_timewait_sock.c +++ b/net/ipv4/inet_timewait_sock.c @@ -178,6 +178,7 @@ struct inet_timewait_sock *inet_twsk_alloc(const struct sock *sk, tw->tw_dport = inet->inet_dport; tw->tw_family = sk->sk_family; tw->tw_reuse = sk->sk_reuse; + tw->tw_reuseport = sk->sk_reuseport; tw->tw_hash = sk->sk_hash; tw->tw_ipv6only = 0; tw->tw_transparent = inet->transparent; diff --git a/net/ipv4/inetpeer.c b/net/ipv4/inetpeer.c index 1f04bd91fc2e..d757b9642d0d 100644 --- a/net/ipv4/inetpeer.c +++ b/net/ipv4/inetpeer.c @@ -211,6 +211,7 @@ struct inet_peer *inet_getpeer(struct inet_peer_base *base, p = kmem_cache_alloc(peer_cachep, GFP_ATOMIC); if (p) { p->daddr = *daddr; + p->dtime = (__u32)jiffies; refcount_set(&p->refcnt, 2); atomic_set(&p->rid, 0); p->metrics[RTAX_LOCK-1] = INETPEER_METRICS_NEW; diff --git a/net/ipv4/ip_fragment.c b/net/ipv4/ip_fragment.c index 994fa70a910f..8e9528ebaa8e 100644 --- a/net/ipv4/ip_fragment.c +++ b/net/ipv4/ip_fragment.c @@ -667,7 +667,7 @@ struct sk_buff *ip_check_defrag(struct net *net, struct sk_buff *skb, u32 user) EXPORT_SYMBOL(ip_check_defrag); #ifdef CONFIG_SYSCTL -static long zero; +static int dist_min; static struct ctl_table ip4_frags_ns_ctl_table[] = { { @@ -684,7 +684,6 @@ static struct ctl_table ip4_frags_ns_ctl_table[] = { .maxlen = sizeof(unsigned long), .mode = 0644, .proc_handler = proc_doulongvec_minmax, - .extra1 = &zero, .extra2 = &init_net.ipv4.frags.high_thresh }, { @@ -700,7 +699,7 @@ static struct ctl_table ip4_frags_ns_ctl_table[] = { .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec_minmax, - .extra1 = &zero + .extra1 = &dist_min, }, { } }; diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c index 94cacae76aca..4c11b810a447 100644 --- a/net/ipv4/ip_output.c +++ b/net/ipv4/ip_output.c @@ -1090,7 +1090,8 @@ alloc_new_skb: length -= copy; } - refcount_add(wmem_alloc_delta, &sk->sk_wmem_alloc); + if (wmem_alloc_delta) + refcount_add(wmem_alloc_delta, &sk->sk_wmem_alloc); return 0; error_efault: diff --git a/net/ipv4/ip_tunnel.c b/net/ipv4/ip_tunnel.c index de6d94482fe7..6b0e362cc99b 100644 --- a/net/ipv4/ip_tunnel.c +++ b/net/ipv4/ip_tunnel.c @@ -253,13 +253,14 @@ static struct net_device *__ip_tunnel_create(struct net *net, struct net_device *dev; char name[IFNAMSIZ]; - if (parms->name[0]) + err = -E2BIG; + if (parms->name[0]) { + if (!dev_valid_name(parms->name)) + goto failed; strlcpy(name, parms->name, IFNAMSIZ); - else { - if (strlen(ops->kind) > (IFNAMSIZ - 3)) { - err = -E2BIG; + } else { + if (strlen(ops->kind) > (IFNAMSIZ - 3)) goto failed; - } strlcpy(name, ops->kind, IFNAMSIZ); strncat(name, "%d", 2); } diff --git a/net/ipv4/route.c b/net/ipv4/route.c index 8322e479f299..ccb25d80f679 100644 --- a/net/ipv4/route.c +++ b/net/ipv4/route.c @@ -108,7 +108,6 @@ #include <net/rtnetlink.h> #ifdef CONFIG_SYSCTL #include <linux/sysctl.h> -#include <linux/kmemleak.h> #endif #include <net/secure_seq.h> #include <net/ip_tunnels.h> @@ -2297,13 +2296,14 @@ struct rtable *ip_route_output_key_hash(struct net *net, struct flowi4 *fl4, const struct sk_buff *skb) { __u8 tos = RT_FL_TOS(fl4); - struct fib_result res; + struct fib_result res = { + .type = RTN_UNSPEC, + .fi = NULL, + .table = NULL, + .tclassid = 0, + }; struct rtable *rth; - res.tclassid = 0; - res.fi = NULL; - res.table = NULL; - fl4->flowi4_iif = LOOPBACK_IFINDEX; fl4->flowi4_tos = tos & IPTOS_RT_MASK; fl4->flowi4_scope = ((tos & RTO_ONLINK) ? diff --git a/net/ipv6/datagram.c b/net/ipv6/datagram.c index 88bc2ef7c7a8..a02ad100f0d7 100644 --- a/net/ipv6/datagram.c +++ b/net/ipv6/datagram.c @@ -106,14 +106,7 @@ int ip6_datagram_dst_update(struct sock *sk, bool fix_sk_saddr) } } - ip6_dst_store(sk, dst, - ipv6_addr_equal(&fl6.daddr, &sk->sk_v6_daddr) ? - &sk->sk_v6_daddr : NULL, -#ifdef CONFIG_IPV6_SUBTREES - ipv6_addr_equal(&fl6.saddr, &np->saddr) ? - &np->saddr : -#endif - NULL); + ip6_sk_dst_store_flow(sk, dst, &fl6); out: fl6_sock_release(flowlabel); diff --git a/net/ipv6/ip6_gre.c b/net/ipv6/ip6_gre.c index f8a103bdbd60..69727bc168cb 100644 --- a/net/ipv6/ip6_gre.c +++ b/net/ipv6/ip6_gre.c @@ -335,11 +335,13 @@ static struct ip6_tnl *ip6gre_tunnel_locate(struct net *net, if (t || !create) return t; - if (parms->name[0]) + if (parms->name[0]) { + if (!dev_valid_name(parms->name)) + return NULL; strlcpy(name, parms->name, IFNAMSIZ); - else + } else { strcpy(name, "ip6gre%d"); - + } dev = alloc_netdev(sizeof(*t), name, NET_NAME_UNKNOWN, ip6gre_tunnel_setup); if (!dev) diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c index e6eaa4dd9f60..2e891d2c30ef 100644 --- a/net/ipv6/ip6_output.c +++ b/net/ipv6/ip6_output.c @@ -375,6 +375,11 @@ static int ip6_forward_proxy_check(struct sk_buff *skb) static inline int ip6_forward_finish(struct net *net, struct sock *sk, struct sk_buff *skb) { + struct dst_entry *dst = skb_dst(skb); + + __IP6_INC_STATS(net, ip6_dst_idev(dst), IPSTATS_MIB_OUTFORWDATAGRAMS); + __IP6_ADD_STATS(net, ip6_dst_idev(dst), IPSTATS_MIB_OUTOCTETS, skb->len); + return dst_output(net, sk, skb); } @@ -569,8 +574,6 @@ int ip6_forward(struct sk_buff *skb) hdr->hop_limit--; - __IP6_INC_STATS(net, ip6_dst_idev(dst), IPSTATS_MIB_OUTFORWDATAGRAMS); - __IP6_ADD_STATS(net, ip6_dst_idev(dst), IPSTATS_MIB_OUTOCTETS, skb->len); return NF_HOOK(NFPROTO_IPV6, NF_INET_FORWARD, net, NULL, skb, skb->dev, dst->dev, ip6_forward_finish); @@ -1105,23 +1108,32 @@ EXPORT_SYMBOL_GPL(ip6_dst_lookup_flow); * @sk: socket which provides the dst cache and route info * @fl6: flow to lookup * @final_dst: final destination address for ipsec lookup + * @connected: whether @sk is connected or not * * This function performs a route lookup on the given flow with the * possibility of using the cached route in the socket if it is valid. * It will take the socket dst lock when operating on the dst cache. * As a result, this function can only be used in process context. * + * In addition, for a connected socket, cache the dst in the socket + * if the current cache is not valid. + * * It returns a valid dst pointer on success, or a pointer encoded * error code. */ struct dst_entry *ip6_sk_dst_lookup_flow(struct sock *sk, struct flowi6 *fl6, - const struct in6_addr *final_dst) + const struct in6_addr *final_dst, + bool connected) { struct dst_entry *dst = sk_dst_check(sk, inet6_sk(sk)->dst_cookie); dst = ip6_sk_dst_check(sk, dst, fl6); - if (!dst) - dst = ip6_dst_lookup_flow(sk, fl6, final_dst); + if (dst) + return dst; + + dst = ip6_dst_lookup_flow(sk, fl6, final_dst); + if (connected && !IS_ERR(dst)) + ip6_sk_dst_store_flow(sk, dst_clone(dst), fl6); return dst; } @@ -1536,7 +1548,8 @@ alloc_new_skb: length -= copy; } - refcount_add(wmem_alloc_delta, &sk->sk_wmem_alloc); + if (wmem_alloc_delta) + refcount_add(wmem_alloc_delta, &sk->sk_wmem_alloc); return 0; error_efault: diff --git a/net/ipv6/ip6_tunnel.c b/net/ipv6/ip6_tunnel.c index df4c29f7d59f..da66aaac51ce 100644 --- a/net/ipv6/ip6_tunnel.c +++ b/net/ipv6/ip6_tunnel.c @@ -297,13 +297,16 @@ static struct ip6_tnl *ip6_tnl_create(struct net *net, struct __ip6_tnl_parm *p) struct net_device *dev; struct ip6_tnl *t; char name[IFNAMSIZ]; - int err = -ENOMEM; + int err = -E2BIG; - if (p->name[0]) + if (p->name[0]) { + if (!dev_valid_name(p->name)) + goto failed; strlcpy(name, p->name, IFNAMSIZ); - else + } else { sprintf(name, "ip6tnl%%d"); - + } + err = -ENOMEM; dev = alloc_netdev(sizeof(*t), name, NET_NAME_UNKNOWN, ip6_tnl_dev_setup); if (!dev) diff --git a/net/ipv6/ip6_vti.c b/net/ipv6/ip6_vti.c index 6ebb2e8777f4..c214ffec02f0 100644 --- a/net/ipv6/ip6_vti.c +++ b/net/ipv6/ip6_vti.c @@ -212,10 +212,13 @@ static struct ip6_tnl *vti6_tnl_create(struct net *net, struct __ip6_tnl_parm *p char name[IFNAMSIZ]; int err; - if (p->name[0]) + if (p->name[0]) { + if (!dev_valid_name(p->name)) + goto failed; strlcpy(name, p->name, IFNAMSIZ); - else + } else { sprintf(name, "ip6_vti%%d"); + } dev = alloc_netdev(sizeof(*t), name, NET_NAME_UNKNOWN, vti6_dev_setup); if (!dev) diff --git a/net/ipv6/netfilter/nf_conntrack_reasm.c b/net/ipv6/netfilter/nf_conntrack_reasm.c index 3622aac343ae..5e0332014c17 100644 --- a/net/ipv6/netfilter/nf_conntrack_reasm.c +++ b/net/ipv6/netfilter/nf_conntrack_reasm.c @@ -55,7 +55,6 @@ static const char nf_frags_cache_name[] = "nf-frags"; static struct inet_frags nf_frags; #ifdef CONFIG_SYSCTL -static long zero; static struct ctl_table nf_ct_frag6_sysctl_table[] = { { @@ -71,7 +70,6 @@ static struct ctl_table nf_ct_frag6_sysctl_table[] = { .maxlen = sizeof(unsigned long), .mode = 0644, .proc_handler = proc_doulongvec_minmax, - .extra1 = &zero, .extra2 = &init_net.nf_frag.frags.high_thresh }, { diff --git a/net/ipv6/ping.c b/net/ipv6/ping.c index d12c55dad7d1..746eeae7f581 100644 --- a/net/ipv6/ping.c +++ b/net/ipv6/ping.c @@ -121,7 +121,7 @@ static int ping_v6_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) ipc6.tclass = np->tclass; fl6.flowlabel = ip6_make_flowinfo(ipc6.tclass, fl6.flowlabel); - dst = ip6_sk_dst_lookup_flow(sk, &fl6, daddr); + dst = ip6_sk_dst_lookup_flow(sk, &fl6, daddr, false); if (IS_ERR(dst)) return PTR_ERR(dst); rt = (struct rt6_info *) dst; diff --git a/net/ipv6/reassembly.c b/net/ipv6/reassembly.c index 70e4a578b2fb..4979610287e2 100644 --- a/net/ipv6/reassembly.c +++ b/net/ipv6/reassembly.c @@ -548,7 +548,6 @@ static const struct inet6_protocol frag_protocol = { }; #ifdef CONFIG_SYSCTL -static int zero; static struct ctl_table ip6_frags_ns_ctl_table[] = { { @@ -565,7 +564,6 @@ static struct ctl_table ip6_frags_ns_ctl_table[] = { .maxlen = sizeof(unsigned long), .mode = 0644, .proc_handler = proc_doulongvec_minmax, - .extra1 = &zero, .extra2 = &init_net.ipv6.frags.high_thresh }, { diff --git a/net/ipv6/route.c b/net/ipv6/route.c index f239f91d2efb..49b954d6d0fa 100644 --- a/net/ipv6/route.c +++ b/net/ipv6/route.c @@ -2229,6 +2229,23 @@ void ip6_sk_update_pmtu(struct sk_buff *skb, struct sock *sk, __be32 mtu) } EXPORT_SYMBOL_GPL(ip6_sk_update_pmtu); +void ip6_sk_dst_store_flow(struct sock *sk, struct dst_entry *dst, + const struct flowi6 *fl6) +{ +#ifdef CONFIG_IPV6_SUBTREES + struct ipv6_pinfo *np = inet6_sk(sk); +#endif + + ip6_dst_store(sk, dst, + ipv6_addr_equal(&fl6->daddr, &sk->sk_v6_daddr) ? + &sk->sk_v6_daddr : NULL, +#ifdef CONFIG_IPV6_SUBTREES + ipv6_addr_equal(&fl6->saddr, &np->saddr) ? + &np->saddr : +#endif + NULL); +} + /* Handle redirects */ struct ip6rd_flowi { struct flowi6 fl6; diff --git a/net/ipv6/sit.c b/net/ipv6/sit.c index 1522bcfd253f..2afce37a7177 100644 --- a/net/ipv6/sit.c +++ b/net/ipv6/sit.c @@ -250,11 +250,13 @@ static struct ip_tunnel *ipip6_tunnel_locate(struct net *net, if (!create) goto failed; - if (parms->name[0]) + if (parms->name[0]) { + if (!dev_valid_name(parms->name)) + goto failed; strlcpy(name, parms->name, IFNAMSIZ); - else + } else { strcpy(name, "sit%d"); - + } dev = alloc_netdev(sizeof(*t), name, NET_NAME_UNKNOWN, ipip6_tunnel_setup); if (!dev) diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c index 6861ed479469..4ec76a87aeb8 100644 --- a/net/ipv6/udp.c +++ b/net/ipv6/udp.c @@ -1116,10 +1116,10 @@ int udpv6_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) struct dst_entry *dst; struct ipcm6_cookie ipc6; int addr_len = msg->msg_namelen; + bool connected = false; int ulen = len; int corkreq = up->corkflag || msg->msg_flags&MSG_MORE; int err; - int connected = 0; int is_udplite = IS_UDPLITE(sk); int (*getfrag)(void *, char *, int, int, int, struct sk_buff *); struct sockcm_cookie sockc; @@ -1241,7 +1241,7 @@ do_udp_sendmsg: fl6.fl6_dport = inet->inet_dport; daddr = &sk->sk_v6_daddr; fl6.flowlabel = np->flow_label; - connected = 1; + connected = true; } if (!fl6.flowi6_oif) @@ -1271,7 +1271,7 @@ do_udp_sendmsg: } if (!(opt->opt_nflen|opt->opt_flen)) opt = NULL; - connected = 0; + connected = false; } if (!opt) { opt = txopt_get(np); @@ -1293,11 +1293,11 @@ do_udp_sendmsg: final_p = fl6_update_dst(&fl6, opt, &final); if (final_p) - connected = 0; + connected = false; if (!fl6.flowi6_oif && ipv6_addr_is_multicast(&fl6.daddr)) { fl6.flowi6_oif = np->mcast_oif; - connected = 0; + connected = false; } else if (!fl6.flowi6_oif) fl6.flowi6_oif = np->ucast_oif; @@ -1308,7 +1308,7 @@ do_udp_sendmsg: fl6.flowlabel = ip6_make_flowinfo(ipc6.tclass, fl6.flowlabel); - dst = ip6_sk_dst_lookup_flow(sk, &fl6, final_p); + dst = ip6_sk_dst_lookup_flow(sk, &fl6, final_p, connected); if (IS_ERR(dst)) { err = PTR_ERR(dst); dst = NULL; @@ -1333,7 +1333,7 @@ back_from_confirm: err = PTR_ERR(skb); if (!IS_ERR_OR_NULL(skb)) err = udp_v6_send_skb(skb, &fl6); - goto release_dst; + goto out; } lock_sock(sk); @@ -1367,23 +1367,6 @@ do_append_data: err = np->recverr ? net_xmit_errno(err) : 0; release_sock(sk); -release_dst: - if (dst) { - if (connected) { - ip6_dst_store(sk, dst, - ipv6_addr_equal(&fl6.daddr, &sk->sk_v6_daddr) ? - &sk->sk_v6_daddr : NULL, -#ifdef CONFIG_IPV6_SUBTREES - ipv6_addr_equal(&fl6.saddr, &np->saddr) ? - &np->saddr : -#endif - NULL); - } else { - dst_release(dst); - } - dst = NULL; - } - out: dst_release(dst); fl6_sock_release(flowlabel); diff --git a/net/netlabel/netlabel_unlabeled.c b/net/netlabel/netlabel_unlabeled.c index 22dc1b9d6362..c070dfc0190a 100644 --- a/net/netlabel/netlabel_unlabeled.c +++ b/net/netlabel/netlabel_unlabeled.c @@ -1472,6 +1472,16 @@ int netlbl_unlabel_getattr(const struct sk_buff *skb, iface = rcu_dereference(netlbl_unlhsh_def); if (iface == NULL || !iface->valid) goto unlabel_getattr_nolabel; + +#if IS_ENABLED(CONFIG_IPV6) + /* When resolving a fallback label, check the sk_buff version as + * it is possible (e.g. SCTP) to have family = PF_INET6 while + * receiving ip_hdr(skb)->version = 4. + */ + if (family == PF_INET6 && ip_hdr(skb)->version == 4) + family = PF_INET; +#endif /* IPv6 */ + switch (family) { case PF_INET: { struct iphdr *hdr4; diff --git a/net/netlink/af_netlink.c b/net/netlink/af_netlink.c index fa556fdef57d..55342c4d5cec 100644 --- a/net/netlink/af_netlink.c +++ b/net/netlink/af_netlink.c @@ -1844,6 +1844,8 @@ static int netlink_sendmsg(struct socket *sock, struct msghdr *msg, size_t len) if (msg->msg_namelen) { err = -EINVAL; + if (msg->msg_namelen < sizeof(struct sockaddr_nl)) + goto out; if (addr->nl_family != AF_NETLINK) goto out; dst_portid = addr->nl_pid; diff --git a/net/rxrpc/input.c b/net/rxrpc/input.c index 21800e6f5019..0410d2277ca2 100644 --- a/net/rxrpc/input.c +++ b/net/rxrpc/input.c @@ -1200,6 +1200,12 @@ void rxrpc_data_ready(struct sock *udp_sk) !rxrpc_validate_jumbo(skb)) goto bad_message; break; + + /* Packet types 9-11 should just be ignored. */ + case RXRPC_PACKET_TYPE_PARAMS: + case RXRPC_PACKET_TYPE_10: + case RXRPC_PACKET_TYPE_11: + goto discard; } rcu_read_lock(); diff --git a/net/rxrpc/protocol.h b/net/rxrpc/protocol.h index 4bddcf3face3..93da73bf7098 100644 --- a/net/rxrpc/protocol.h +++ b/net/rxrpc/protocol.h @@ -46,6 +46,9 @@ struct rxrpc_wire_header { #define RXRPC_PACKET_TYPE_CHALLENGE 6 /* connection security challenge (SRVR->CLNT) */ #define RXRPC_PACKET_TYPE_RESPONSE 7 /* connection secutity response (CLNT->SRVR) */ #define RXRPC_PACKET_TYPE_DEBUG 8 /* debug info request */ +#define RXRPC_PACKET_TYPE_PARAMS 9 /* Parameter negotiation (unspec'd, ignore) */ +#define RXRPC_PACKET_TYPE_10 10 /* Ignored */ +#define RXRPC_PACKET_TYPE_11 11 /* Ignored */ #define RXRPC_PACKET_TYPE_VERSION 13 /* version string request */ #define RXRPC_N_PACKET_TYPES 14 /* number of packet types (incl type 0) */ @@ -78,6 +81,9 @@ struct rxrpc_wire_header { (1 << RXRPC_PACKET_TYPE_CHALLENGE) | \ (1 << RXRPC_PACKET_TYPE_RESPONSE) | \ /*(1 << RXRPC_PACKET_TYPE_DEBUG) | */ \ + (1 << RXRPC_PACKET_TYPE_PARAMS) | \ + (1 << RXRPC_PACKET_TYPE_10) | \ + (1 << RXRPC_PACKET_TYPE_11) | \ (1 << RXRPC_PACKET_TYPE_VERSION)) /*****************************************************************************/ diff --git a/net/sched/act_bpf.c b/net/sched/act_bpf.c index 9092531d45d8..18089c02e557 100644 --- a/net/sched/act_bpf.c +++ b/net/sched/act_bpf.c @@ -248,10 +248,14 @@ static int tcf_bpf_init_from_efd(struct nlattr **tb, struct tcf_bpf_cfg *cfg) static void tcf_bpf_cfg_cleanup(const struct tcf_bpf_cfg *cfg) { - if (cfg->is_ebpf) - bpf_prog_put(cfg->filter); - else - bpf_prog_destroy(cfg->filter); + struct bpf_prog *filter = cfg->filter; + + if (filter) { + if (cfg->is_ebpf) + bpf_prog_put(filter); + else + bpf_prog_destroy(filter); + } kfree(cfg->bpf_ops); kfree(cfg->bpf_name); diff --git a/net/sched/cls_u32.c b/net/sched/cls_u32.c index ed8b6a24b9e9..bac47b5d18fd 100644 --- a/net/sched/cls_u32.c +++ b/net/sched/cls_u32.c @@ -489,6 +489,7 @@ static int u32_delete_key(struct tcf_proto *tp, struct tc_u_knode *key) RCU_INIT_POINTER(*kp, key->next); tcf_unbind_filter(tp, &key->res); + idr_remove(&ht->handle_idr, key->handle); tcf_exts_get_net(&key->exts); call_rcu(&key->rcu, u32_delete_key_freepf_rcu); return 0; diff --git a/net/sctp/chunk.c b/net/sctp/chunk.c index f889a84f264d..be296d633e95 100644 --- a/net/sctp/chunk.c +++ b/net/sctp/chunk.c @@ -172,6 +172,8 @@ struct sctp_datamsg *sctp_datamsg_from_user(struct sctp_association *asoc, struct list_head *pos, *temp; struct sctp_chunk *chunk; struct sctp_datamsg *msg; + struct sctp_sock *sp; + struct sctp_af *af; int err; msg = sctp_datamsg_new(GFP_KERNEL); @@ -190,9 +192,11 @@ struct sctp_datamsg *sctp_datamsg_from_user(struct sctp_association *asoc, /* This is the biggest possible DATA chunk that can fit into * the packet */ - max_data = asoc->pathmtu - - sctp_sk(asoc->base.sk)->pf->af->net_header_len - - sizeof(struct sctphdr) - sctp_datachk_len(&asoc->stream); + sp = sctp_sk(asoc->base.sk); + af = sp->pf->af; + max_data = asoc->pathmtu - af->net_header_len - + sizeof(struct sctphdr) - sctp_datachk_len(&asoc->stream) - + af->ip_options_len(asoc->base.sk); max_data = SCTP_TRUNC4(max_data); /* If the the peer requested that we authenticate DATA chunks diff --git a/net/sctp/ipv6.c b/net/sctp/ipv6.c index 0d873c58e516..31083b5035ec 100644 --- a/net/sctp/ipv6.c +++ b/net/sctp/ipv6.c @@ -427,6 +427,41 @@ static void sctp_v6_copy_addrlist(struct list_head *addrlist, rcu_read_unlock(); } +/* Copy over any ip options */ +static void sctp_v6_copy_ip_options(struct sock *sk, struct sock *newsk) +{ + struct ipv6_pinfo *newnp, *np = inet6_sk(sk); + struct ipv6_txoptions *opt; + + newnp = inet6_sk(newsk); + + rcu_read_lock(); + opt = rcu_dereference(np->opt); + if (opt) { + opt = ipv6_dup_options(newsk, opt); + if (!opt) + pr_err("%s: Failed to copy ip options\n", __func__); + } + RCU_INIT_POINTER(newnp->opt, opt); + rcu_read_unlock(); +} + +/* Account for the IP options */ +static int sctp_v6_ip_options_len(struct sock *sk) +{ + struct ipv6_pinfo *np = inet6_sk(sk); + struct ipv6_txoptions *opt; + int len = 0; + + rcu_read_lock(); + opt = rcu_dereference(np->opt); + if (opt) + len = opt->opt_flen + opt->opt_nflen; + + rcu_read_unlock(); + return len; +} + /* Initialize a sockaddr_storage from in incoming skb. */ static void sctp_v6_from_skb(union sctp_addr *addr, struct sk_buff *skb, int is_saddr) @@ -666,7 +701,6 @@ static struct sock *sctp_v6_create_accept_sk(struct sock *sk, struct sock *newsk; struct ipv6_pinfo *newnp, *np = inet6_sk(sk); struct sctp6_sock *newsctp6sk; - struct ipv6_txoptions *opt; newsk = sk_alloc(sock_net(sk), PF_INET6, GFP_KERNEL, sk->sk_prot, kern); if (!newsk) @@ -689,12 +723,7 @@ static struct sock *sctp_v6_create_accept_sk(struct sock *sk, newnp->ipv6_ac_list = NULL; newnp->ipv6_fl_list = NULL; - rcu_read_lock(); - opt = rcu_dereference(np->opt); - if (opt) - opt = ipv6_dup_options(newsk, opt); - RCU_INIT_POINTER(newnp->opt, opt); - rcu_read_unlock(); + sctp_v6_copy_ip_options(sk, newsk); /* Initialize sk's sport, dport, rcv_saddr and daddr for getsockname() * and getpeername(). @@ -728,8 +757,10 @@ static int sctp_v6_addr_to_user(struct sctp_sock *sp, union sctp_addr *addr) sctp_v6_map_v4(addr); } - if (addr->sa.sa_family == AF_INET) + if (addr->sa.sa_family == AF_INET) { + memset(addr->v4.sin_zero, 0, sizeof(addr->v4.sin_zero)); return sizeof(struct sockaddr_in); + } return sizeof(struct sockaddr_in6); } @@ -1041,6 +1072,7 @@ static struct sctp_af sctp_af_inet6 = { .ecn_capable = sctp_v6_ecn_capable, .net_header_len = sizeof(struct ipv6hdr), .sockaddr_len = sizeof(struct sockaddr_in6), + .ip_options_len = sctp_v6_ip_options_len, #ifdef CONFIG_COMPAT .compat_setsockopt = compat_ipv6_setsockopt, .compat_getsockopt = compat_ipv6_getsockopt, @@ -1059,6 +1091,7 @@ static struct sctp_pf sctp_pf_inet6 = { .addr_to_user = sctp_v6_addr_to_user, .to_sk_saddr = sctp_v6_to_sk_saddr, .to_sk_daddr = sctp_v6_to_sk_daddr, + .copy_ip_options = sctp_v6_copy_ip_options, .af = &sctp_af_inet6, }; diff --git a/net/sctp/output.c b/net/sctp/output.c index d6e1c90cc09a..690d8557bb7b 100644 --- a/net/sctp/output.c +++ b/net/sctp/output.c @@ -69,7 +69,11 @@ static enum sctp_xmit sctp_packet_will_fit(struct sctp_packet *packet, static void sctp_packet_reset(struct sctp_packet *packet) { + /* sctp_packet_transmit() relies on this to reset size to the + * current overhead after sending packets. + */ packet->size = packet->overhead; + packet->has_cookie_echo = 0; packet->has_sack = 0; packet->has_data = 0; @@ -87,6 +91,7 @@ void sctp_packet_config(struct sctp_packet *packet, __u32 vtag, struct sctp_transport *tp = packet->transport; struct sctp_association *asoc = tp->asoc; struct sock *sk; + size_t overhead = sizeof(struct ipv6hdr) + sizeof(struct sctphdr); pr_debug("%s: packet:%p vtag:0x%x\n", __func__, packet, vtag); packet->vtag = vtag; @@ -95,10 +100,22 @@ void sctp_packet_config(struct sctp_packet *packet, __u32 vtag, if (!sctp_packet_empty(packet)) return; - /* set packet max_size with pathmtu */ + /* set packet max_size with pathmtu, then calculate overhead */ packet->max_size = tp->pathmtu; - if (!asoc) + if (asoc) { + struct sctp_sock *sp = sctp_sk(asoc->base.sk); + struct sctp_af *af = sp->pf->af; + + overhead = af->net_header_len + + af->ip_options_len(asoc->base.sk); + overhead += sizeof(struct sctphdr); + packet->overhead = overhead; + packet->size = overhead; + } else { + packet->overhead = overhead; + packet->size = overhead; return; + } /* update dst or transport pathmtu if in need */ sk = asoc->base.sk; @@ -140,23 +157,14 @@ void sctp_packet_init(struct sctp_packet *packet, struct sctp_transport *transport, __u16 sport, __u16 dport) { - struct sctp_association *asoc = transport->asoc; - size_t overhead; - pr_debug("%s: packet:%p transport:%p\n", __func__, packet, transport); packet->transport = transport; packet->source_port = sport; packet->destination_port = dport; INIT_LIST_HEAD(&packet->chunk_list); - if (asoc) { - struct sctp_sock *sp = sctp_sk(asoc->base.sk); - overhead = sp->pf->af->net_header_len; - } else { - overhead = sizeof(struct ipv6hdr); - } - overhead += sizeof(struct sctphdr); - packet->overhead = overhead; + /* The overhead will be calculated by sctp_packet_config() */ + packet->overhead = 0; sctp_packet_reset(packet); packet->vtag = 0; } diff --git a/net/sctp/protocol.c b/net/sctp/protocol.c index a24cde236330..d685f8456762 100644 --- a/net/sctp/protocol.c +++ b/net/sctp/protocol.c @@ -187,6 +187,45 @@ int sctp_copy_local_addr_list(struct net *net, struct sctp_bind_addr *bp, return error; } +/* Copy over any ip options */ +static void sctp_v4_copy_ip_options(struct sock *sk, struct sock *newsk) +{ + struct inet_sock *newinet, *inet = inet_sk(sk); + struct ip_options_rcu *inet_opt, *newopt = NULL; + + newinet = inet_sk(newsk); + + rcu_read_lock(); + inet_opt = rcu_dereference(inet->inet_opt); + if (inet_opt) { + newopt = sock_kmalloc(newsk, sizeof(*inet_opt) + + inet_opt->opt.optlen, GFP_ATOMIC); + if (newopt) + memcpy(newopt, inet_opt, sizeof(*inet_opt) + + inet_opt->opt.optlen); + else + pr_err("%s: Failed to copy ip options\n", __func__); + } + RCU_INIT_POINTER(newinet->inet_opt, newopt); + rcu_read_unlock(); +} + +/* Account for the IP options */ +static int sctp_v4_ip_options_len(struct sock *sk) +{ + struct inet_sock *inet = inet_sk(sk); + struct ip_options_rcu *inet_opt; + int len = 0; + + rcu_read_lock(); + inet_opt = rcu_dereference(inet->inet_opt); + if (inet_opt) + len = inet_opt->opt.optlen; + + rcu_read_unlock(); + return len; +} + /* Initialize a sctp_addr from in incoming skb. */ static void sctp_v4_from_skb(union sctp_addr *addr, struct sk_buff *skb, int is_saddr) @@ -538,6 +577,8 @@ static struct sock *sctp_v4_create_accept_sk(struct sock *sk, sctp_copy_sock(newsk, sk, asoc); sock_reset_flag(newsk, SOCK_ZAPPED); + sctp_v4_copy_ip_options(sk, newsk); + newinet = inet_sk(newsk); newinet->inet_daddr = asoc->peer.primary_addr.v4.sin_addr.s_addr; @@ -956,6 +997,7 @@ static struct sctp_pf sctp_pf_inet = { .addr_to_user = sctp_v4_addr_to_user, .to_sk_saddr = sctp_v4_to_sk_saddr, .to_sk_daddr = sctp_v4_to_sk_daddr, + .copy_ip_options = sctp_v4_copy_ip_options, .af = &sctp_af_inet }; @@ -1040,6 +1082,7 @@ static struct sctp_af sctp_af_inet = { .ecn_capable = sctp_v4_ecn_capable, .net_header_len = sizeof(struct iphdr), .sockaddr_len = sizeof(struct sockaddr_in), + .ip_options_len = sctp_v4_ip_options_len, #ifdef CONFIG_COMPAT .compat_setsockopt = compat_ip_setsockopt, .compat_getsockopt = compat_ip_getsockopt, diff --git a/net/sctp/sm_make_chunk.c b/net/sctp/sm_make_chunk.c index cc20bc39ee7c..5a4fb1dc8400 100644 --- a/net/sctp/sm_make_chunk.c +++ b/net/sctp/sm_make_chunk.c @@ -3098,6 +3098,12 @@ static __be16 sctp_process_asconf_param(struct sctp_association *asoc, if (af->is_any(&addr)) memcpy(&addr, &asconf->source, sizeof(addr)); + if (security_sctp_bind_connect(asoc->ep->base.sk, + SCTP_PARAM_ADD_IP, + (struct sockaddr *)&addr, + af->sockaddr_len)) + return SCTP_ERROR_REQ_REFUSED; + /* ADDIP 4.3 D9) If an endpoint receives an ADD IP address * request and does not have the local resources to add this * new address to the association, it MUST return an Error @@ -3164,6 +3170,12 @@ static __be16 sctp_process_asconf_param(struct sctp_association *asoc, if (af->is_any(&addr)) memcpy(&addr.v4, sctp_source(asconf), sizeof(addr)); + if (security_sctp_bind_connect(asoc->ep->base.sk, + SCTP_PARAM_SET_PRIMARY, + (struct sockaddr *)&addr, + af->sockaddr_len)) + return SCTP_ERROR_REQ_REFUSED; + peer = sctp_assoc_lookup_paddr(asoc, &addr); if (!peer) return SCTP_ERROR_DNS_FAILED; diff --git a/net/sctp/sm_statefuns.c b/net/sctp/sm_statefuns.c index cc56a67dbb4d..dd0594a10961 100644 --- a/net/sctp/sm_statefuns.c +++ b/net/sctp/sm_statefuns.c @@ -321,6 +321,11 @@ enum sctp_disposition sctp_sf_do_5_1B_init(struct net *net, struct sctp_packet *packet; int len; + /* Update socket peer label if first association. */ + if (security_sctp_assoc_request((struct sctp_endpoint *)ep, + chunk->skb)) + return sctp_sf_pdiscard(net, ep, asoc, type, arg, commands); + /* 6.10 Bundling * An endpoint MUST NOT bundle INIT, INIT ACK or * SHUTDOWN COMPLETE with any other chunks. @@ -922,6 +927,9 @@ enum sctp_disposition sctp_sf_do_5_1E_ca(struct net *net, */ sctp_add_cmd_sf(commands, SCTP_CMD_INIT_COUNTER_RESET, SCTP_NULL()); + /* Set peer label for connection. */ + security_inet_conn_established(ep->base.sk, chunk->skb); + /* RFC 2960 5.1 Normal Establishment of an Association * * E) Upon reception of the COOKIE ACK, endpoint "A" will move @@ -1459,6 +1467,11 @@ static enum sctp_disposition sctp_sf_do_unexpected_init( struct sctp_packet *packet; int len; + /* Update socket peer label if first association. */ + if (security_sctp_assoc_request((struct sctp_endpoint *)ep, + chunk->skb)) + return sctp_sf_pdiscard(net, ep, asoc, type, arg, commands); + /* 6.10 Bundling * An endpoint MUST NOT bundle INIT, INIT ACK or * SHUTDOWN COMPLETE with any other chunks. @@ -2145,6 +2158,11 @@ enum sctp_disposition sctp_sf_do_5_2_4_dupcook( } } + /* Update socket peer label if first association. */ + if (security_sctp_assoc_request((struct sctp_endpoint *)ep, + chunk->skb)) + return sctp_sf_pdiscard(net, ep, asoc, type, arg, commands); + /* Set temp so that it won't be added into hashtable */ new_asoc->temp = 1; diff --git a/net/sctp/socket.c b/net/sctp/socket.c index 7a10ae3c3d82..80835ac26d2c 100644 --- a/net/sctp/socket.c +++ b/net/sctp/socket.c @@ -357,11 +357,14 @@ static struct sctp_af *sctp_sockaddr_af(struct sctp_sock *opt, if (!opt->pf->af_supported(addr->sa.sa_family, opt)) return NULL; - /* V4 mapped address are really of AF_INET family */ - if (addr->sa.sa_family == AF_INET6 && - ipv6_addr_v4mapped(&addr->v6.sin6_addr) && - !opt->pf->af_supported(AF_INET, opt)) - return NULL; + if (addr->sa.sa_family == AF_INET6) { + if (len < SIN6_LEN_RFC2133) + return NULL; + /* V4 mapped address are really of AF_INET family */ + if (ipv6_addr_v4mapped(&addr->v6.sin6_addr) && + !opt->pf->af_supported(AF_INET, opt)) + return NULL; + } /* If we get this far, af is valid. */ af = sctp_get_af_specific(addr->sa.sa_family); @@ -1046,6 +1049,12 @@ static int sctp_setsockopt_bindx(struct sock *sk, /* Do the work. */ switch (op) { case SCTP_BINDX_ADD_ADDR: + /* Allow security module to validate bindx addresses. */ + err = security_sctp_bind_connect(sk, SCTP_SOCKOPT_BINDX_ADD, + (struct sockaddr *)kaddrs, + addrs_size); + if (err) + goto out; err = sctp_bindx_add(sk, kaddrs, addrcnt); if (err) goto out; @@ -1255,6 +1264,7 @@ static int __sctp_connect(struct sock *sk, if (assoc_id) *assoc_id = asoc->assoc_id; + err = sctp_wait_for_connect(asoc, &timeo); /* Note: the asoc may be freed after the return of * sctp_wait_for_connect. @@ -1350,7 +1360,16 @@ static int __sctp_setsockopt_connectx(struct sock *sk, if (unlikely(IS_ERR(kaddrs))) return PTR_ERR(kaddrs); + /* Allow security module to validate connectx addresses. */ + err = security_sctp_bind_connect(sk, SCTP_SOCKOPT_CONNECTX, + (struct sockaddr *)kaddrs, + addrs_size); + if (err) + goto out_free; + err = __sctp_connect(sk, kaddrs, addrs_size, assoc_id); + +out_free: kvfree(kaddrs); return err; @@ -1680,6 +1699,7 @@ static int sctp_sendmsg_new_asoc(struct sock *sk, __u16 sflags, struct sctp_association *asoc; enum sctp_scope scope; struct cmsghdr *cmsg; + struct sctp_af *af; int err; *tp = NULL; @@ -1705,6 +1725,21 @@ static int sctp_sendmsg_new_asoc(struct sock *sk, __u16 sflags, scope = sctp_scope(daddr); + /* Label connection socket for first association 1-to-many + * style for client sequence socket()->sendmsg(). This + * needs to be done before sctp_assoc_add_peer() as that will + * set up the initial packet that needs to account for any + * security ip options (CIPSO/CALIPSO) added to the packet. + */ + af = sctp_get_af_specific(daddr->sa.sa_family); + if (!af) + return -EINVAL; + err = security_sctp_bind_connect(sk, SCTP_SENDMSG_CONNECT, + (struct sockaddr *)daddr, + af->sockaddr_len); + if (err < 0) + return err; + asoc = sctp_association_new(ep, sk, scope, GFP_KERNEL); if (!asoc) return -ENOMEM; @@ -2932,6 +2967,8 @@ static int sctp_setsockopt_primary_addr(struct sock *sk, char __user *optval, { struct sctp_prim prim; struct sctp_transport *trans; + struct sctp_af *af; + int err; if (optlen != sizeof(struct sctp_prim)) return -EINVAL; @@ -2939,6 +2976,17 @@ static int sctp_setsockopt_primary_addr(struct sock *sk, char __user *optval, if (copy_from_user(&prim, optval, sizeof(struct sctp_prim))) return -EFAULT; + /* Allow security module to validate address but need address len. */ + af = sctp_get_af_specific(prim.ssp_addr.ss_family); + if (!af) + return -EINVAL; + + err = security_sctp_bind_connect(sk, SCTP_PRIMARY_ADDR, + (struct sockaddr *)&prim.ssp_addr, + af->sockaddr_len); + if (err) + return err; + trans = sctp_addr_id2transport(sk, &prim.ssp_addr, prim.ssp_assoc_id); if (!trans) return -EINVAL; @@ -3161,6 +3209,7 @@ static int sctp_setsockopt_mappedv4(struct sock *sk, char __user *optval, unsign static int sctp_setsockopt_maxseg(struct sock *sk, char __user *optval, unsigned int optlen) { struct sctp_sock *sp = sctp_sk(sk); + struct sctp_af *af = sp->pf->af; struct sctp_assoc_value params; struct sctp_association *asoc; int val; @@ -3185,7 +3234,8 @@ static int sctp_setsockopt_maxseg(struct sock *sk, char __user *optval, unsigned if (val) { int min_len, max_len; - min_len = SCTP_DEFAULT_MINSEGMENT - sp->pf->af->net_header_len; + min_len = SCTP_DEFAULT_MINSEGMENT - af->net_header_len; + min_len -= af->ip_options_len(sk); min_len -= sizeof(struct sctphdr) + sizeof(struct sctp_data_chunk); @@ -3198,7 +3248,8 @@ static int sctp_setsockopt_maxseg(struct sock *sk, char __user *optval, unsigned asoc = sctp_id2assoc(sk, params.assoc_id); if (asoc) { if (val == 0) { - val = asoc->pathmtu - sp->pf->af->net_header_len; + val = asoc->pathmtu - af->net_header_len; + val -= af->ip_options_len(sk); val -= sizeof(struct sctphdr) + sctp_datachk_len(&asoc->stream); } @@ -3267,6 +3318,13 @@ static int sctp_setsockopt_peer_primary_addr(struct sock *sk, char __user *optva if (!sctp_assoc_lookup_laddr(asoc, (union sctp_addr *)&prim.sspp_addr)) return -EADDRNOTAVAIL; + /* Allow security module to validate address. */ + err = security_sctp_bind_connect(sk, SCTP_SET_PEER_PRIMARY_ADDR, + (struct sockaddr *)&prim.sspp_addr, + af->sockaddr_len); + if (err) + return err; + /* Create an ASCONF chunk with SET_PRIMARY parameter */ chunk = sctp_make_asconf_set_prim(asoc, (union sctp_addr *)&prim.sspp_addr); @@ -5140,9 +5198,11 @@ int sctp_do_peeloff(struct sock *sk, sctp_assoc_t id, struct socket **sockp) sctp_copy_sock(sock->sk, sk, asoc); /* Make peeled-off sockets more like 1-1 accepted sockets. - * Set the daddr and initialize id to something more random + * Set the daddr and initialize id to something more random and also + * copy over any ip options. */ sp->pf->to_sk_daddr(&asoc->peer.primary_addr, sk); + sp->pf->copy_ip_options(sk, sock->sk); /* Populate the fields of the newsk from the oldsk and migrate the * asoc to the newsk. @@ -8465,6 +8525,8 @@ void sctp_copy_sock(struct sock *newsk, struct sock *sk, { struct inet_sock *inet = inet_sk(sk); struct inet_sock *newinet; + struct sctp_sock *sp = sctp_sk(sk); + struct sctp_endpoint *ep = sp->ep; newsk->sk_type = sk->sk_type; newsk->sk_bound_dev_if = sk->sk_bound_dev_if; @@ -8507,7 +8569,10 @@ void sctp_copy_sock(struct sock *newsk, struct sock *sk, if (newsk->sk_flags & SK_FLAGS_TIMESTAMP) net_enable_timestamp(); - security_sk_clone(sk, newsk); + /* Set newsk security attributes from orginal sk and connection + * security attribute from ep. + */ + security_sctp_sk_clone(ep, sk, newsk); } static inline void sctp_copy_descendant(struct sock *sk_to, diff --git a/net/socket.c b/net/socket.c index 54dcb43e25a1..f10f1d947c78 100644 --- a/net/socket.c +++ b/net/socket.c @@ -1536,7 +1536,7 @@ SYSCALL_DEFINE2(listen, int, fd, int, backlog) * * 1003.1g adds the ability to recvmsg() to query connection pending * status to recvmsg. We need to add that support in a way thats - * clean when we restucture accept also. + * clean when we restructure accept also. */ int __sys_accept4(int fd, struct sockaddr __user *upeer_sockaddr, diff --git a/net/sunrpc/auth_gss/gss_krb5_crypto.c b/net/sunrpc/auth_gss/gss_krb5_crypto.c index 12649c9fedab..8654494b4d0a 100644 --- a/net/sunrpc/auth_gss/gss_krb5_crypto.c +++ b/net/sunrpc/auth_gss/gss_krb5_crypto.c @@ -237,9 +237,6 @@ make_checksum_hmac_md5(struct krb5_ctx *kctx, char *header, int hdrlen, ahash_request_set_callback(req, CRYPTO_TFM_REQ_MAY_SLEEP, NULL, NULL); - err = crypto_ahash_init(req); - if (err) - goto out; err = crypto_ahash_setkey(hmac_md5, cksumkey, kctx->gk5e->keylength); if (err) goto out; diff --git a/net/sunrpc/auth_gss/gss_krb5_seal.c b/net/sunrpc/auth_gss/gss_krb5_seal.c index 1d74d653e6c0..94a2b3f082a8 100644 --- a/net/sunrpc/auth_gss/gss_krb5_seal.c +++ b/net/sunrpc/auth_gss/gss_krb5_seal.c @@ -177,6 +177,7 @@ gss_get_mic_v2(struct krb5_ctx *ctx, struct xdr_buf *text, u64 seq_send; u8 *cksumkey; unsigned int cksum_usage; + __be64 seq_send_be64; dprintk("RPC: %s\n", __func__); @@ -187,7 +188,9 @@ gss_get_mic_v2(struct krb5_ctx *ctx, struct xdr_buf *text, spin_lock(&krb5_seq_lock); seq_send = ctx->seq_send64++; spin_unlock(&krb5_seq_lock); - *((__be64 *)(krb5_hdr + 8)) = cpu_to_be64(seq_send); + + seq_send_be64 = cpu_to_be64(seq_send); + memcpy(krb5_hdr + 8, (char *) &seq_send_be64, 8); if (ctx->initiate) { cksumkey = ctx->initiator_sign; diff --git a/net/sunrpc/auth_gss/gss_krb5_unseal.c b/net/sunrpc/auth_gss/gss_krb5_unseal.c index dcf9515d9aef..b601a73cc9db 100644 --- a/net/sunrpc/auth_gss/gss_krb5_unseal.c +++ b/net/sunrpc/auth_gss/gss_krb5_unseal.c @@ -155,10 +155,12 @@ gss_verify_mic_v2(struct krb5_ctx *ctx, u8 flags; int i; unsigned int cksum_usage; + __be16 be16_ptr; dprintk("RPC: %s\n", __func__); - if (be16_to_cpu(*((__be16 *)ptr)) != KG2_TOK_MIC) + memcpy(&be16_ptr, (char *) ptr, 2); + if (be16_to_cpu(be16_ptr) != KG2_TOK_MIC) return GSS_S_DEFECTIVE_TOKEN; flags = ptr[2]; diff --git a/net/sunrpc/cache.c b/net/sunrpc/cache.c index c536cc24b3d1..cdda4744c9b1 100644 --- a/net/sunrpc/cache.c +++ b/net/sunrpc/cache.c @@ -1450,8 +1450,8 @@ static ssize_t write_flush(struct file *file, const char __user *buf, struct cache_detail *cd) { char tbuf[20]; - char *bp, *ep; - time_t then, now; + char *ep; + time_t now; if (*ppos || count > sizeof(tbuf)-1) return -EINVAL; @@ -1461,24 +1461,24 @@ static ssize_t write_flush(struct file *file, const char __user *buf, simple_strtoul(tbuf, &ep, 0); if (*ep && *ep != '\n') return -EINVAL; + /* Note that while we check that 'buf' holds a valid number, + * we always ignore the value and just flush everything. + * Making use of the number leads to races. + */ - bp = tbuf; - then = get_expiry(&bp); now = seconds_since_boot(); - cd->nextcheck = now; - /* Can only set flush_time to 1 second beyond "now", or - * possibly 1 second beyond flushtime. This is because - * flush_time never goes backwards so it mustn't get too far - * ahead of time. + /* Always flush everything, so behave like cache_purge() + * Do this by advancing flush_time to the current time, + * or by one second if it has already reached the current time. + * Newly added cache entries will always have ->last_refresh greater + * that ->flush_time, so they don't get flushed prematurely. */ - if (then >= now) { - /* Want to flush everything, so behave like cache_purge() */ - if (cd->flush_time >= now) - now = cd->flush_time + 1; - then = now; - } - cd->flush_time = then; + if (cd->flush_time >= now) + now = cd->flush_time + 1; + + cd->flush_time = now; + cd->nextcheck = now; cache_flush(); *ppos += count; diff --git a/net/sunrpc/svc.c b/net/sunrpc/svc.c index 387cc4add6f6..30a4226baf03 100644 --- a/net/sunrpc/svc.c +++ b/net/sunrpc/svc.c @@ -1255,6 +1255,7 @@ svc_process_common(struct svc_rqst *rqstp, struct kvec *argv, struct kvec *resv) /* Syntactic check complete */ serv->sv_stats->rpccnt++; + trace_svc_process(rqstp, progp->pg_name); /* Build the reply header. */ statp = resv->iov_base +resv->iov_len; @@ -1431,14 +1432,10 @@ svc_process(struct svc_rqst *rqstp) } /* Returns 1 for send, 0 for drop */ - if (likely(svc_process_common(rqstp, argv, resv))) { - int ret = svc_send(rqstp); + if (likely(svc_process_common(rqstp, argv, resv))) + return svc_send(rqstp); - trace_svc_process(rqstp, ret); - return ret; - } out_drop: - trace_svc_process(rqstp, 0); svc_drop(rqstp); return 0; } @@ -1536,3 +1533,112 @@ u32 svc_max_payload(const struct svc_rqst *rqstp) return max; } EXPORT_SYMBOL_GPL(svc_max_payload); + +/** + * svc_fill_write_vector - Construct data argument for VFS write call + * @rqstp: svc_rqst to operate on + * @first: buffer containing first section of write payload + * @total: total number of bytes of write payload + * + * Returns the number of elements populated in the data argument array. + */ +unsigned int svc_fill_write_vector(struct svc_rqst *rqstp, struct kvec *first, + size_t total) +{ + struct kvec *vec = rqstp->rq_vec; + struct page **pages; + unsigned int i; + + /* Some types of transport can present the write payload + * entirely in rq_arg.pages. In this case, @first is empty. + */ + i = 0; + if (first->iov_len) { + vec[i].iov_base = first->iov_base; + vec[i].iov_len = min_t(size_t, total, first->iov_len); + total -= vec[i].iov_len; + ++i; + } + + WARN_ON_ONCE(rqstp->rq_arg.page_base != 0); + pages = rqstp->rq_arg.pages; + while (total) { + vec[i].iov_base = page_address(*pages); + vec[i].iov_len = min_t(size_t, total, PAGE_SIZE); + total -= vec[i].iov_len; + ++i; + + ++pages; + } + + WARN_ON_ONCE(i > ARRAY_SIZE(rqstp->rq_vec)); + return i; +} +EXPORT_SYMBOL_GPL(svc_fill_write_vector); + +/** + * svc_fill_symlink_pathname - Construct pathname argument for VFS symlink call + * @rqstp: svc_rqst to operate on + * @first: buffer containing first section of pathname + * @total: total length of the pathname argument + * + * Returns pointer to a NUL-terminated string, or an ERR_PTR. The buffer is + * released automatically when @rqstp is recycled. + */ +char *svc_fill_symlink_pathname(struct svc_rqst *rqstp, struct kvec *first, + size_t total) +{ + struct xdr_buf *arg = &rqstp->rq_arg; + struct page **pages; + char *result; + + /* VFS API demands a NUL-terminated pathname. This function + * uses a page from @rqstp as the pathname buffer, to enable + * direct placement. Thus the total buffer size is PAGE_SIZE. + * Space in this buffer for NUL-termination requires that we + * cap the size of the returned symlink pathname just a + * little early. + */ + if (total > PAGE_SIZE - 1) + return ERR_PTR(-ENAMETOOLONG); + + /* Some types of transport can present the pathname entirely + * in rq_arg.pages. If not, then copy the pathname into one + * page. + */ + pages = arg->pages; + WARN_ON_ONCE(arg->page_base != 0); + if (first->iov_base == 0) { + result = page_address(*pages); + result[total] = '\0'; + } else { + size_t len, remaining; + char *dst; + + result = page_address(*(rqstp->rq_next_page++)); + dst = result; + remaining = total; + + len = min_t(size_t, total, first->iov_len); + memcpy(dst, first->iov_base, len); + dst += len; + remaining -= len; + + /* No more than one page left */ + if (remaining) { + len = min_t(size_t, remaining, PAGE_SIZE); + memcpy(dst, page_address(*pages), len); + dst += len; + } + + *dst = '\0'; + } + + /* Sanity check: we don't allow the pathname argument to + * contain a NUL byte. + */ + if (strlen(result) != total) + return ERR_PTR(-EINVAL); + return result; +} +EXPORT_SYMBOL_GPL(svc_fill_symlink_pathname); diff --git a/net/sunrpc/svc_xprt.c b/net/sunrpc/svc_xprt.c index f9307bd6644b..5185efb9027b 100644 --- a/net/sunrpc/svc_xprt.c +++ b/net/sunrpc/svc_xprt.c @@ -173,6 +173,7 @@ void svc_xprt_init(struct net *net, struct svc_xprt_class *xcl, set_bit(XPT_BUSY, &xprt->xpt_flags); rpc_init_wait_queue(&xprt->xpt_bc_pending, "xpt_bc_pending"); xprt->xpt_net = get_net(net); + strcpy(xprt->xpt_remotebuf, "uninitialized"); } EXPORT_SYMBOL_GPL(svc_xprt_init); @@ -382,25 +383,21 @@ void svc_xprt_do_enqueue(struct svc_xprt *xprt) int cpu; if (!svc_xprt_has_something_to_do(xprt)) - goto out; + return; /* Mark transport as busy. It will remain in this state until * the provider calls svc_xprt_received. We update XPT_BUSY * atomically because it also guards against trying to enqueue * the transport twice. */ - if (test_and_set_bit(XPT_BUSY, &xprt->xpt_flags)) { - /* Don't enqueue transport while already enqueued */ - dprintk("svc: transport %p busy, not enqueued\n", xprt); - goto out; - } + if (test_and_set_bit(XPT_BUSY, &xprt->xpt_flags)) + return; cpu = get_cpu(); pool = svc_pool_for_cpu(xprt->xpt_server, cpu); atomic_long_inc(&pool->sp_stats.packets); - dprintk("svc: transport %p put into queue\n", xprt); spin_lock_bh(&pool->sp_lock); list_add_tail(&xprt->xpt_ready, &pool->sp_sockets); pool->sp_stats.sockets_queued++; @@ -412,6 +409,7 @@ void svc_xprt_do_enqueue(struct svc_xprt *xprt) if (test_and_set_bit(RQ_BUSY, &rqstp->rq_flags)) continue; atomic_long_inc(&pool->sp_stats.threads_woken); + rqstp->rq_qtime = ktime_get(); wake_up_process(rqstp->rq_task); goto out_unlock; } @@ -420,7 +418,6 @@ void svc_xprt_do_enqueue(struct svc_xprt *xprt) out_unlock: rcu_read_unlock(); put_cpu(); -out: trace_svc_xprt_do_enqueue(xprt, rqstp); } EXPORT_SYMBOL_GPL(svc_xprt_do_enqueue); @@ -454,13 +451,9 @@ static struct svc_xprt *svc_xprt_dequeue(struct svc_pool *pool) struct svc_xprt, xpt_ready); list_del_init(&xprt->xpt_ready); svc_xprt_get(xprt); - - dprintk("svc: transport %p dequeued, inuse=%d\n", - xprt, kref_read(&xprt->xpt_ref)); } spin_unlock_bh(&pool->sp_lock); out: - trace_svc_xprt_dequeue(xprt); return xprt; } @@ -492,7 +485,7 @@ static void svc_xprt_release(struct svc_rqst *rqstp) { struct svc_xprt *xprt = rqstp->rq_xprt; - rqstp->rq_xprt->xpt_ops->xpo_release_rqst(rqstp); + xprt->xpt_ops->xpo_release_rqst(rqstp); kfree(rqstp->rq_deferred); rqstp->rq_deferred = NULL; @@ -538,7 +531,6 @@ void svc_wake_up(struct svc_serv *serv) if (test_bit(RQ_BUSY, &rqstp->rq_flags)) continue; rcu_read_unlock(); - dprintk("svc: daemon %p woken up.\n", rqstp); wake_up_process(rqstp->rq_task); trace_svc_wake_up(rqstp->rq_task->pid); return; @@ -734,6 +726,7 @@ out_found: rqstp->rq_chandle.thread_wait = 5*HZ; else rqstp->rq_chandle.thread_wait = 1*HZ; + trace_svc_xprt_dequeue(rqstp); return rqstp->rq_xprt; } @@ -789,7 +782,7 @@ static int svc_handle_xprt(struct svc_rqst *rqstp, struct svc_xprt *xprt) len = svc_deferred_recv(rqstp); else len = xprt->xpt_ops->xpo_recvfrom(rqstp); - dprintk("svc: got len=%d\n", len); + rqstp->rq_stime = ktime_get(); rqstp->rq_reserved = serv->sv_max_mesg; atomic_add(rqstp->rq_reserved, &xprt->xpt_reserved); } @@ -844,10 +837,7 @@ int svc_recv(struct svc_rqst *rqstp, long timeout) clear_bit(XPT_OLD, &xprt->xpt_flags); - if (xprt->xpt_ops->xpo_secure_port(rqstp)) - set_bit(RQ_SECURE, &rqstp->rq_flags); - else - clear_bit(RQ_SECURE, &rqstp->rq_flags); + xprt->xpt_ops->xpo_secure_port(rqstp); rqstp->rq_chandle.defer = svc_defer; rqstp->rq_xid = svc_getu32(&rqstp->rq_arg.head[0]); @@ -859,7 +849,6 @@ out_release: rqstp->rq_res.len = 0; svc_xprt_release(rqstp); out: - trace_svc_recv(rqstp, err); return err; } EXPORT_SYMBOL_GPL(svc_recv); @@ -889,7 +878,7 @@ int svc_send(struct svc_rqst *rqstp) goto out; /* release the receive skb before sending the reply */ - rqstp->rq_xprt->xpt_ops->xpo_release_rqst(rqstp); + xprt->xpt_ops->xpo_release_rqst(rqstp); /* calculate over-all length */ xb = &rqstp->rq_res; @@ -899,6 +888,7 @@ int svc_send(struct svc_rqst *rqstp) /* Grab mutex to serialize outgoing data. */ mutex_lock(&xprt->xpt_mutex); + trace_svc_stats_latency(rqstp); if (test_bit(XPT_DEAD, &xprt->xpt_flags) || test_bit(XPT_CLOSE, &xprt->xpt_flags)) len = -ENOTCONN; @@ -906,12 +896,12 @@ int svc_send(struct svc_rqst *rqstp) len = xprt->xpt_ops->xpo_sendto(rqstp); mutex_unlock(&xprt->xpt_mutex); rpc_wake_up(&xprt->xpt_bc_pending); + trace_svc_send(rqstp, len); svc_xprt_release(rqstp); if (len == -ECONNREFUSED || len == -ENOTCONN || len == -EAGAIN) len = 0; out: - trace_svc_send(rqstp, len); return len; } diff --git a/net/sunrpc/svcsock.c b/net/sunrpc/svcsock.c index 08cd951aaeea..5445145e639c 100644 --- a/net/sunrpc/svcsock.c +++ b/net/sunrpc/svcsock.c @@ -391,9 +391,12 @@ static void svc_sock_setbufsize(struct socket *sock, unsigned int snd, release_sock(sock->sk); } -static int svc_sock_secure_port(struct svc_rqst *rqstp) +static void svc_sock_secure_port(struct svc_rqst *rqstp) { - return svc_port_is_privileged(svc_addr(rqstp)); + if (svc_port_is_privileged(svc_addr(rqstp))) + set_bit(RQ_SECURE, &rqstp->rq_flags); + else + clear_bit(RQ_SECURE, &rqstp->rq_flags); } /* @@ -1309,6 +1312,7 @@ static void svc_tcp_init(struct svc_sock *svsk, struct svc_serv *serv) set_bit(XPT_CONG_CTRL, &svsk->sk_xprt.xpt_flags); if (sk->sk_state == TCP_LISTEN) { dprintk("setting up TCP socket for listening\n"); + strcpy(svsk->sk_xprt.xpt_remotebuf, "listener"); set_bit(XPT_LISTENER, &svsk->sk_xprt.xpt_flags); sk->sk_data_ready = svc_tcp_listen_data_ready; set_bit(XPT_CONN, &svsk->sk_xprt.xpt_flags); diff --git a/net/sunrpc/xprtrdma/svc_rdma.c b/net/sunrpc/xprtrdma/svc_rdma.c index a4a8f6989ee7..dd8a431dc2ae 100644 --- a/net/sunrpc/xprtrdma/svc_rdma.c +++ b/net/sunrpc/xprtrdma/svc_rdma.c @@ -51,9 +51,9 @@ #define RPCDBG_FACILITY RPCDBG_SVCXPRT /* RPC/RDMA parameters */ -unsigned int svcrdma_ord = RPCRDMA_ORD; +unsigned int svcrdma_ord = 16; /* historical default */ static unsigned int min_ord = 1; -static unsigned int max_ord = 4096; +static unsigned int max_ord = 255; unsigned int svcrdma_max_requests = RPCRDMA_MAX_REQUESTS; unsigned int svcrdma_max_bc_requests = RPCRDMA_MAX_BC_REQUESTS; static unsigned int min_max_requests = 4; diff --git a/net/sunrpc/xprtrdma/svc_rdma_recvfrom.c b/net/sunrpc/xprtrdma/svc_rdma_recvfrom.c index 19e9c6b33042..3d45015dca97 100644 --- a/net/sunrpc/xprtrdma/svc_rdma_recvfrom.c +++ b/net/sunrpc/xprtrdma/svc_rdma_recvfrom.c @@ -110,15 +110,16 @@ * the RDMA_RECV completion. The SGL should contain full pages up until the * last one. */ -static void rdma_build_arg_xdr(struct svc_rqst *rqstp, - struct svc_rdma_op_ctxt *ctxt, - u32 byte_count) +static void svc_rdma_build_arg_xdr(struct svc_rqst *rqstp, + struct svc_rdma_op_ctxt *ctxt) { struct page *page; - u32 bc; int sge_no; + u32 len; - /* Swap the page in the SGE with the page in argpages */ + /* The reply path assumes the Call's transport header resides + * in rqstp->rq_pages[0]. + */ page = ctxt->pages[0]; put_page(rqstp->rq_pages[0]); rqstp->rq_pages[0] = page; @@ -126,35 +127,35 @@ static void rdma_build_arg_xdr(struct svc_rqst *rqstp, /* Set up the XDR head */ rqstp->rq_arg.head[0].iov_base = page_address(page); rqstp->rq_arg.head[0].iov_len = - min_t(size_t, byte_count, ctxt->sge[0].length); - rqstp->rq_arg.len = byte_count; - rqstp->rq_arg.buflen = byte_count; + min_t(size_t, ctxt->byte_len, ctxt->sge[0].length); + rqstp->rq_arg.len = ctxt->byte_len; + rqstp->rq_arg.buflen = ctxt->byte_len; /* Compute bytes past head in the SGL */ - bc = byte_count - rqstp->rq_arg.head[0].iov_len; + len = ctxt->byte_len - rqstp->rq_arg.head[0].iov_len; /* If data remains, store it in the pagelist */ - rqstp->rq_arg.page_len = bc; + rqstp->rq_arg.page_len = len; rqstp->rq_arg.page_base = 0; sge_no = 1; - while (bc && sge_no < ctxt->count) { + while (len && sge_no < ctxt->count) { page = ctxt->pages[sge_no]; put_page(rqstp->rq_pages[sge_no]); rqstp->rq_pages[sge_no] = page; - bc -= min_t(u32, bc, ctxt->sge[sge_no].length); + len -= min_t(u32, len, ctxt->sge[sge_no].length); sge_no++; } rqstp->rq_respages = &rqstp->rq_pages[sge_no]; rqstp->rq_next_page = rqstp->rq_respages + 1; /* If not all pages were used from the SGL, free the remaining ones */ - bc = sge_no; + len = sge_no; while (sge_no < ctxt->count) { page = ctxt->pages[sge_no++]; put_page(page); } - ctxt->count = bc; + ctxt->count = len; /* Set up tail */ rqstp->rq_arg.tail[0].iov_base = NULL; @@ -534,10 +535,8 @@ int svc_rdma_recvfrom(struct svc_rqst *rqstp) ctxt, rdma_xprt, rqstp); atomic_inc(&rdma_stat_recv); - /* Build up the XDR from the receive buffers. */ - rdma_build_arg_xdr(rqstp, ctxt, ctxt->byte_len); + svc_rdma_build_arg_xdr(rqstp, ctxt); - /* Decode the RDMA header. */ p = (__be32 *)rqstp->rq_arg.head[0].iov_base; ret = svc_rdma_xdr_decode_req(&rqstp->rq_arg); if (ret < 0) diff --git a/net/sunrpc/xprtrdma/svc_rdma_transport.c b/net/sunrpc/xprtrdma/svc_rdma_transport.c index 9ad12a215b51..96cc8f6597d3 100644 --- a/net/sunrpc/xprtrdma/svc_rdma_transport.c +++ b/net/sunrpc/xprtrdma/svc_rdma_transport.c @@ -69,7 +69,7 @@ static void svc_rdma_release_rqst(struct svc_rqst *); static void svc_rdma_detach(struct svc_xprt *xprt); static void svc_rdma_free(struct svc_xprt *xprt); static int svc_rdma_has_wspace(struct svc_xprt *xprt); -static int svc_rdma_secure_port(struct svc_rqst *); +static void svc_rdma_secure_port(struct svc_rqst *); static void svc_rdma_kill_temp_xprt(struct svc_xprt *); static const struct svc_xprt_ops svc_rdma_ops = { @@ -330,9 +330,9 @@ static void svc_rdma_wc_receive(struct ib_cq *cq, struct ib_wc *wc) flushed: if (wc->status != IB_WC_WR_FLUSH_ERR) - pr_warn("svcrdma: receive: %s (%u/0x%x)\n", - ib_wc_status_msg(wc->status), - wc->status, wc->vendor_err); + pr_err("svcrdma: Recv: %s (%u/0x%x)\n", + ib_wc_status_msg(wc->status), + wc->status, wc->vendor_err); set_bit(XPT_CLOSE, &xprt->sc_xprt.xpt_flags); svc_rdma_put_context(ctxt, 1); @@ -401,8 +401,10 @@ static struct svcxprt_rdma *rdma_create_xprt(struct svc_serv *serv, */ set_bit(XPT_CONG_CTRL, &cma_xprt->sc_xprt.xpt_flags); - if (listener) + if (listener) { + strcpy(cma_xprt->sc_xprt.xpt_remotebuf, "listener"); set_bit(XPT_LISTENER, &cma_xprt->sc_xprt.xpt_flags); + } return cma_xprt; } @@ -762,13 +764,6 @@ static struct svc_xprt *svc_rdma_accept(struct svc_xprt *xprt) if (!svc_rdma_prealloc_ctxts(newxprt)) goto errout; - /* - * Limit ORD based on client limit, local device limit, and - * configured svcrdma limit. - */ - newxprt->sc_ord = min_t(size_t, dev->attrs.max_qp_rd_atom, newxprt->sc_ord); - newxprt->sc_ord = min_t(size_t, svcrdma_ord, newxprt->sc_ord); - newxprt->sc_pd = ib_alloc_pd(dev, 0); if (IS_ERR(newxprt->sc_pd)) { dprintk("svcrdma: error creating PD for connect request\n"); @@ -843,15 +838,18 @@ static struct svc_xprt *svc_rdma_accept(struct svc_xprt *xprt) set_bit(RDMAXPRT_CONN_PENDING, &newxprt->sc_flags); memset(&conn_param, 0, sizeof conn_param); conn_param.responder_resources = 0; - conn_param.initiator_depth = newxprt->sc_ord; + conn_param.initiator_depth = min_t(int, newxprt->sc_ord, + dev->attrs.max_qp_init_rd_atom); + if (!conn_param.initiator_depth) { + dprintk("svcrdma: invalid ORD setting\n"); + ret = -EINVAL; + goto errout; + } conn_param.private_data = &pmsg; conn_param.private_data_len = sizeof(pmsg); ret = rdma_accept(newxprt->sc_cm_id, &conn_param); - if (ret) { - dprintk("svcrdma: failed to accept new connection, ret=%d\n", - ret); + if (ret) goto errout; - } dprintk("svcrdma: new connection %p accepted:\n", newxprt); sap = (struct sockaddr *)&newxprt->sc_cm_id->route.addr.src_addr; @@ -862,7 +860,7 @@ static struct svc_xprt *svc_rdma_accept(struct svc_xprt *xprt) dprintk(" sq_depth : %d\n", newxprt->sc_sq_depth); dprintk(" rdma_rw_ctxs : %d\n", ctxts); dprintk(" max_requests : %d\n", newxprt->sc_max_requests); - dprintk(" ord : %d\n", newxprt->sc_ord); + dprintk(" ord : %d\n", conn_param.initiator_depth); return &newxprt->sc_xprt; @@ -992,9 +990,9 @@ static int svc_rdma_has_wspace(struct svc_xprt *xprt) return 1; } -static int svc_rdma_secure_port(struct svc_rqst *rqstp) +static void svc_rdma_secure_port(struct svc_rqst *rqstp) { - return 1; + set_bit(RQ_SECURE, &rqstp->rq_flags); } static void svc_rdma_kill_temp_xprt(struct svc_xprt *xprt) diff --git a/net/tipc/diag.c b/net/tipc/diag.c index 46d9cd62f781..aaabb0b776dd 100644 --- a/net/tipc/diag.c +++ b/net/tipc/diag.c @@ -59,7 +59,7 @@ static int __tipc_add_sock_diag(struct sk_buff *skb, if (!nlh) return -EMSGSIZE; - err = tipc_sk_fill_sock_diag(skb, tsk, req->tidiag_states, + err = tipc_sk_fill_sock_diag(skb, cb, tsk, req->tidiag_states, __tipc_diag_gen_cookie); if (err) return err; diff --git a/net/tipc/socket.c b/net/tipc/socket.c index 3e5eba30865e..1fd1c8b5ce03 100644 --- a/net/tipc/socket.c +++ b/net/tipc/socket.c @@ -3257,8 +3257,8 @@ out: } EXPORT_SYMBOL(tipc_nl_sk_walk); -int tipc_sk_fill_sock_diag(struct sk_buff *skb, struct tipc_sock *tsk, - u32 sk_filter_state, +int tipc_sk_fill_sock_diag(struct sk_buff *skb, struct netlink_callback *cb, + struct tipc_sock *tsk, u32 sk_filter_state, u64 (*tipc_diag_gen_cookie)(struct sock *sk)) { struct sock *sk = &tsk->sk; @@ -3280,7 +3280,8 @@ int tipc_sk_fill_sock_diag(struct sk_buff *skb, struct tipc_sock *tsk, nla_put_u32(skb, TIPC_NLA_SOCK_TIPC_STATE, (u32)sk->sk_state) || nla_put_u32(skb, TIPC_NLA_SOCK_INO, sock_i_ino(sk)) || nla_put_u32(skb, TIPC_NLA_SOCK_UID, - from_kuid_munged(sk_user_ns(sk), sock_i_uid(sk))) || + from_kuid_munged(sk_user_ns(NETLINK_CB(cb->skb).sk), + sock_i_uid(sk))) || nla_put_u64_64bit(skb, TIPC_NLA_SOCK_COOKIE, tipc_diag_gen_cookie(sk), TIPC_NLA_SOCK_PAD)) diff --git a/net/tipc/socket.h b/net/tipc/socket.h index aae3fd4cd06c..aff9b2ae5a1f 100644 --- a/net/tipc/socket.h +++ b/net/tipc/socket.h @@ -61,8 +61,8 @@ int tipc_sk_rht_init(struct net *net); void tipc_sk_rht_destroy(struct net *net); int tipc_nl_sk_dump(struct sk_buff *skb, struct netlink_callback *cb); int tipc_nl_publ_dump(struct sk_buff *skb, struct netlink_callback *cb); -int tipc_sk_fill_sock_diag(struct sk_buff *skb, struct tipc_sock *tsk, - u32 sk_filter_state, +int tipc_sk_fill_sock_diag(struct sk_buff *skb, struct netlink_callback *cb, + struct tipc_sock *tsk, u32 sk_filter_state, u64 (*tipc_diag_gen_cookie)(struct sock *sk)); int tipc_nl_sk_walk(struct sk_buff *skb, struct netlink_callback *cb, int (*skb_handler)(struct sk_buff *skb, diff --git a/net/tipc/subscr.c b/net/tipc/subscr.c index 6925a989569b..b7d80bc5f4ab 100644 --- a/net/tipc/subscr.c +++ b/net/tipc/subscr.c @@ -145,6 +145,8 @@ struct tipc_subscription *tipc_sub_subscribe(struct net *net, pr_warn("Subscription rejected, no memory\n"); return NULL; } + INIT_LIST_HEAD(&sub->service_list); + INIT_LIST_HEAD(&sub->sub_list); sub->net = net; sub->conid = conid; sub->inactive = false; diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c index aded82da1aea..68bb70a62afe 100644 --- a/net/unix/af_unix.c +++ b/net/unix/af_unix.c @@ -745,14 +745,6 @@ static struct proto unix_proto = { .obj_size = sizeof(struct unix_sock), }; -/* - * AF_UNIX sockets do not interact with hardware, hence they - * dont trigger interrupts - so it's safe for them to have - * bh-unsafe locking for their sk_receive_queue.lock. Split off - * this special lock-class by reinitializing the spinlock key: - */ -static struct lock_class_key af_unix_sk_receive_queue_lock_key; - static struct sock *unix_create1(struct net *net, struct socket *sock, int kern) { struct sock *sk = NULL; @@ -767,8 +759,6 @@ static struct sock *unix_create1(struct net *net, struct socket *sock, int kern) goto out; sock_init_data(sock, sk); - lockdep_set_class(&sk->sk_receive_queue.lock, - &af_unix_sk_receive_queue_lock_key); sk->sk_allocation = GFP_KERNEL_ACCOUNT; sk->sk_write_space = unix_write_space; |
