diff options
Diffstat (limited to 'net')
90 files changed, 1005 insertions, 466 deletions
diff --git a/net/bluetooth/rfcomm/core.c b/net/bluetooth/rfcomm/core.c index af73bc3acb40..410dd5e76c41 100644 --- a/net/bluetooth/rfcomm/core.c +++ b/net/bluetooth/rfcomm/core.c @@ -101,11 +101,11 @@ static struct rfcomm_session *rfcomm_session_del(struct rfcomm_session *s); #define __get_rpn_stop_bits(line) (((line) >> 2) & 0x1) #define __get_rpn_parity(line) (((line) >> 3) & 0x7) +static DECLARE_WAIT_QUEUE_HEAD(rfcomm_wq); + static void rfcomm_schedule(void) { - if (!rfcomm_thread) - return; - wake_up_process(rfcomm_thread); + wake_up_all(&rfcomm_wq); } /* ---- RFCOMM FCS computation ---- */ @@ -2086,24 +2086,22 @@ static void rfcomm_kill_listener(void) static int rfcomm_run(void *unused) { + DEFINE_WAIT_FUNC(wait, woken_wake_function); BT_DBG(""); set_user_nice(current, -10); rfcomm_add_listener(BDADDR_ANY); - while (1) { - set_current_state(TASK_INTERRUPTIBLE); - - if (kthread_should_stop()) - break; + add_wait_queue(&rfcomm_wq, &wait); + while (!kthread_should_stop()) { /* Process stuff */ rfcomm_process_sessions(); - schedule(); + wait_woken(&wait, TASK_INTERRUPTIBLE, MAX_SCHEDULE_TIMEOUT); } - __set_current_state(TASK_RUNNING); + remove_wait_queue(&rfcomm_wq, &wait); rfcomm_kill_listener(); diff --git a/net/bridge/br_multicast.c b/net/bridge/br_multicast.c index 648d79ccf462..c465876c7861 100644 --- a/net/bridge/br_multicast.c +++ b/net/bridge/br_multicast.c @@ -813,10 +813,9 @@ static void __br_multicast_send_query(struct net_bridge *br, return; if (port) { - __skb_push(skb, sizeof(struct ethhdr)); skb->dev = port->dev; NF_HOOK(NFPROTO_BRIDGE, NF_BR_LOCAL_OUT, skb, NULL, skb->dev, - dev_queue_xmit); + br_dev_queue_push_xmit); } else { br_multicast_select_own_querier(br, ip, skb); netif_rx(skb); diff --git a/net/bridge/br_netlink.c b/net/bridge/br_netlink.c index 2ff9706647f2..e5ec470b851f 100644 --- a/net/bridge/br_netlink.c +++ b/net/bridge/br_netlink.c @@ -280,6 +280,7 @@ static const struct nla_policy br_port_policy[IFLA_BRPORT_MAX + 1] = { [IFLA_BRPORT_MODE] = { .type = NLA_U8 }, [IFLA_BRPORT_GUARD] = { .type = NLA_U8 }, [IFLA_BRPORT_PROTECT] = { .type = NLA_U8 }, + [IFLA_BRPORT_FAST_LEAVE]= { .type = NLA_U8 }, [IFLA_BRPORT_LEARNING] = { .type = NLA_U8 }, [IFLA_BRPORT_UNICAST_FLOOD] = { .type = NLA_U8 }, }; diff --git a/net/bridge/netfilter/nft_reject_bridge.c b/net/bridge/netfilter/nft_reject_bridge.c index 654c9018e3e7..48da2c54a69e 100644 --- a/net/bridge/netfilter/nft_reject_bridge.c +++ b/net/bridge/netfilter/nft_reject_bridge.c @@ -18,6 +18,7 @@ #include <net/netfilter/ipv6/nf_reject.h> #include <linux/ip.h> #include <net/ip.h> +#include <net/ip6_checksum.h> #include <linux/netfilter_bridge.h> #include "../br_private.h" diff --git a/net/ceph/crypto.c b/net/ceph/crypto.c index 62fc5e7a9acf..790fe89d90c0 100644 --- a/net/ceph/crypto.c +++ b/net/ceph/crypto.c @@ -90,11 +90,82 @@ static struct crypto_blkcipher *ceph_crypto_alloc_cipher(void) static const u8 *aes_iv = (u8 *)CEPH_AES_IV; +/* + * Should be used for buffers allocated with ceph_kvmalloc(). + * Currently these are encrypt out-buffer (ceph_buffer) and decrypt + * in-buffer (msg front). + * + * Dispose of @sgt with teardown_sgtable(). + * + * @prealloc_sg is to avoid memory allocation inside sg_alloc_table() + * in cases where a single sg is sufficient. No attempt to reduce the + * number of sgs by squeezing physically contiguous pages together is + * made though, for simplicity. + */ +static int setup_sgtable(struct sg_table *sgt, struct scatterlist *prealloc_sg, + const void *buf, unsigned int buf_len) +{ + struct scatterlist *sg; + const bool is_vmalloc = is_vmalloc_addr(buf); + unsigned int off = offset_in_page(buf); + unsigned int chunk_cnt = 1; + unsigned int chunk_len = PAGE_ALIGN(off + buf_len); + int i; + int ret; + + if (buf_len == 0) { + memset(sgt, 0, sizeof(*sgt)); + return -EINVAL; + } + + if (is_vmalloc) { + chunk_cnt = chunk_len >> PAGE_SHIFT; + chunk_len = PAGE_SIZE; + } + + if (chunk_cnt > 1) { + ret = sg_alloc_table(sgt, chunk_cnt, GFP_NOFS); + if (ret) + return ret; + } else { + WARN_ON(chunk_cnt != 1); + sg_init_table(prealloc_sg, 1); + sgt->sgl = prealloc_sg; + sgt->nents = sgt->orig_nents = 1; + } + + for_each_sg(sgt->sgl, sg, sgt->orig_nents, i) { + struct page *page; + unsigned int len = min(chunk_len - off, buf_len); + + if (is_vmalloc) + page = vmalloc_to_page(buf); + else + page = virt_to_page(buf); + + sg_set_page(sg, page, len, off); + + off = 0; + buf += len; + buf_len -= len; + } + WARN_ON(buf_len != 0); + + return 0; +} + +static void teardown_sgtable(struct sg_table *sgt) +{ + if (sgt->orig_nents > 1) + sg_free_table(sgt); +} + static int ceph_aes_encrypt(const void *key, int key_len, void *dst, size_t *dst_len, const void *src, size_t src_len) { - struct scatterlist sg_in[2], sg_out[1]; + struct scatterlist sg_in[2], prealloc_sg; + struct sg_table sg_out; struct crypto_blkcipher *tfm = ceph_crypto_alloc_cipher(); struct blkcipher_desc desc = { .tfm = tfm, .flags = 0 }; int ret; @@ -110,16 +181,18 @@ static int ceph_aes_encrypt(const void *key, int key_len, *dst_len = src_len + zero_padding; - crypto_blkcipher_setkey((void *)tfm, key, key_len); sg_init_table(sg_in, 2); sg_set_buf(&sg_in[0], src, src_len); sg_set_buf(&sg_in[1], pad, zero_padding); - sg_init_table(sg_out, 1); - sg_set_buf(sg_out, dst, *dst_len); + ret = setup_sgtable(&sg_out, &prealloc_sg, dst, *dst_len); + if (ret) + goto out_tfm; + + crypto_blkcipher_setkey((void *)tfm, key, key_len); iv = crypto_blkcipher_crt(tfm)->iv; ivsize = crypto_blkcipher_ivsize(tfm); - memcpy(iv, aes_iv, ivsize); + /* print_hex_dump(KERN_ERR, "enc key: ", DUMP_PREFIX_NONE, 16, 1, key, key_len, 1); @@ -128,16 +201,22 @@ static int ceph_aes_encrypt(const void *key, int key_len, print_hex_dump(KERN_ERR, "enc pad: ", DUMP_PREFIX_NONE, 16, 1, pad, zero_padding, 1); */ - ret = crypto_blkcipher_encrypt(&desc, sg_out, sg_in, + ret = crypto_blkcipher_encrypt(&desc, sg_out.sgl, sg_in, src_len + zero_padding); - crypto_free_blkcipher(tfm); - if (ret < 0) + if (ret < 0) { pr_err("ceph_aes_crypt failed %d\n", ret); + goto out_sg; + } /* print_hex_dump(KERN_ERR, "enc out: ", DUMP_PREFIX_NONE, 16, 1, dst, *dst_len, 1); */ - return 0; + +out_sg: + teardown_sgtable(&sg_out); +out_tfm: + crypto_free_blkcipher(tfm); + return ret; } static int ceph_aes_encrypt2(const void *key, int key_len, void *dst, @@ -145,7 +224,8 @@ static int ceph_aes_encrypt2(const void *key, int key_len, void *dst, const void *src1, size_t src1_len, const void *src2, size_t src2_len) { - struct scatterlist sg_in[3], sg_out[1]; + struct scatterlist sg_in[3], prealloc_sg; + struct sg_table sg_out; struct crypto_blkcipher *tfm = ceph_crypto_alloc_cipher(); struct blkcipher_desc desc = { .tfm = tfm, .flags = 0 }; int ret; @@ -161,17 +241,19 @@ static int ceph_aes_encrypt2(const void *key, int key_len, void *dst, *dst_len = src1_len + src2_len + zero_padding; - crypto_blkcipher_setkey((void *)tfm, key, key_len); sg_init_table(sg_in, 3); sg_set_buf(&sg_in[0], src1, src1_len); sg_set_buf(&sg_in[1], src2, src2_len); sg_set_buf(&sg_in[2], pad, zero_padding); - sg_init_table(sg_out, 1); - sg_set_buf(sg_out, dst, *dst_len); + ret = setup_sgtable(&sg_out, &prealloc_sg, dst, *dst_len); + if (ret) + goto out_tfm; + + crypto_blkcipher_setkey((void *)tfm, key, key_len); iv = crypto_blkcipher_crt(tfm)->iv; ivsize = crypto_blkcipher_ivsize(tfm); - memcpy(iv, aes_iv, ivsize); + /* print_hex_dump(KERN_ERR, "enc key: ", DUMP_PREFIX_NONE, 16, 1, key, key_len, 1); @@ -182,23 +264,30 @@ static int ceph_aes_encrypt2(const void *key, int key_len, void *dst, print_hex_dump(KERN_ERR, "enc pad: ", DUMP_PREFIX_NONE, 16, 1, pad, zero_padding, 1); */ - ret = crypto_blkcipher_encrypt(&desc, sg_out, sg_in, + ret = crypto_blkcipher_encrypt(&desc, sg_out.sgl, sg_in, src1_len + src2_len + zero_padding); - crypto_free_blkcipher(tfm); - if (ret < 0) + if (ret < 0) { pr_err("ceph_aes_crypt2 failed %d\n", ret); + goto out_sg; + } /* print_hex_dump(KERN_ERR, "enc out: ", DUMP_PREFIX_NONE, 16, 1, dst, *dst_len, 1); */ - return 0; + +out_sg: + teardown_sgtable(&sg_out); +out_tfm: + crypto_free_blkcipher(tfm); + return ret; } static int ceph_aes_decrypt(const void *key, int key_len, void *dst, size_t *dst_len, const void *src, size_t src_len) { - struct scatterlist sg_in[1], sg_out[2]; + struct sg_table sg_in; + struct scatterlist sg_out[2], prealloc_sg; struct crypto_blkcipher *tfm = ceph_crypto_alloc_cipher(); struct blkcipher_desc desc = { .tfm = tfm }; char pad[16]; @@ -210,16 +299,16 @@ static int ceph_aes_decrypt(const void *key, int key_len, if (IS_ERR(tfm)) return PTR_ERR(tfm); - crypto_blkcipher_setkey((void *)tfm, key, key_len); - sg_init_table(sg_in, 1); sg_init_table(sg_out, 2); - sg_set_buf(sg_in, src, src_len); sg_set_buf(&sg_out[0], dst, *dst_len); sg_set_buf(&sg_out[1], pad, sizeof(pad)); + ret = setup_sgtable(&sg_in, &prealloc_sg, src, src_len); + if (ret) + goto out_tfm; + crypto_blkcipher_setkey((void *)tfm, key, key_len); iv = crypto_blkcipher_crt(tfm)->iv; ivsize = crypto_blkcipher_ivsize(tfm); - memcpy(iv, aes_iv, ivsize); /* @@ -228,12 +317,10 @@ static int ceph_aes_decrypt(const void *key, int key_len, print_hex_dump(KERN_ERR, "dec in: ", DUMP_PREFIX_NONE, 16, 1, src, src_len, 1); */ - - ret = crypto_blkcipher_decrypt(&desc, sg_out, sg_in, src_len); - crypto_free_blkcipher(tfm); + ret = crypto_blkcipher_decrypt(&desc, sg_out, sg_in.sgl, src_len); if (ret < 0) { pr_err("ceph_aes_decrypt failed %d\n", ret); - return ret; + goto out_sg; } if (src_len <= *dst_len) @@ -251,7 +338,12 @@ static int ceph_aes_decrypt(const void *key, int key_len, print_hex_dump(KERN_ERR, "dec out: ", DUMP_PREFIX_NONE, 16, 1, dst, *dst_len, 1); */ - return 0; + +out_sg: + teardown_sgtable(&sg_in); +out_tfm: + crypto_free_blkcipher(tfm); + return ret; } static int ceph_aes_decrypt2(const void *key, int key_len, @@ -259,7 +351,8 @@ static int ceph_aes_decrypt2(const void *key, int key_len, void *dst2, size_t *dst2_len, const void *src, size_t src_len) { - struct scatterlist sg_in[1], sg_out[3]; + struct sg_table sg_in; + struct scatterlist sg_out[3], prealloc_sg; struct crypto_blkcipher *tfm = ceph_crypto_alloc_cipher(); struct blkcipher_desc desc = { .tfm = tfm }; char pad[16]; @@ -271,17 +364,17 @@ static int ceph_aes_decrypt2(const void *key, int key_len, if (IS_ERR(tfm)) return PTR_ERR(tfm); - sg_init_table(sg_in, 1); - sg_set_buf(sg_in, src, src_len); sg_init_table(sg_out, 3); sg_set_buf(&sg_out[0], dst1, *dst1_len); sg_set_buf(&sg_out[1], dst2, *dst2_len); sg_set_buf(&sg_out[2], pad, sizeof(pad)); + ret = setup_sgtable(&sg_in, &prealloc_sg, src, src_len); + if (ret) + goto out_tfm; crypto_blkcipher_setkey((void *)tfm, key, key_len); iv = crypto_blkcipher_crt(tfm)->iv; ivsize = crypto_blkcipher_ivsize(tfm); - memcpy(iv, aes_iv, ivsize); /* @@ -290,12 +383,10 @@ static int ceph_aes_decrypt2(const void *key, int key_len, print_hex_dump(KERN_ERR, "dec in: ", DUMP_PREFIX_NONE, 16, 1, src, src_len, 1); */ - - ret = crypto_blkcipher_decrypt(&desc, sg_out, sg_in, src_len); - crypto_free_blkcipher(tfm); + ret = crypto_blkcipher_decrypt(&desc, sg_out, sg_in.sgl, src_len); if (ret < 0) { pr_err("ceph_aes_decrypt failed %d\n", ret); - return ret; + goto out_sg; } if (src_len <= *dst1_len) @@ -325,7 +416,11 @@ static int ceph_aes_decrypt2(const void *key, int key_len, dst2, *dst2_len, 1); */ - return 0; +out_sg: + teardown_sgtable(&sg_in); +out_tfm: + crypto_free_blkcipher(tfm); + return ret; } diff --git a/net/ceph/osd_client.c b/net/ceph/osd_client.c index f3fc54eac09d..6f164289bde8 100644 --- a/net/ceph/osd_client.c +++ b/net/ceph/osd_client.c @@ -1007,8 +1007,8 @@ static void put_osd(struct ceph_osd *osd) static void __remove_osd(struct ceph_osd_client *osdc, struct ceph_osd *osd) { dout("__remove_osd %p\n", osd); - BUG_ON(!list_empty(&osd->o_requests)); - BUG_ON(!list_empty(&osd->o_linger_requests)); + WARN_ON(!list_empty(&osd->o_requests)); + WARN_ON(!list_empty(&osd->o_linger_requests)); rb_erase(&osd->o_node, &osdc->osds); list_del_init(&osd->o_osd_lru); @@ -1254,6 +1254,8 @@ static void __unregister_linger_request(struct ceph_osd_client *osdc, if (list_empty(&req->r_osd_item)) req->r_osd = NULL; } + + list_del_init(&req->r_req_lru_item); /* can be on notarget */ ceph_osdc_put_request(req); } @@ -1395,6 +1397,7 @@ static int __map_request(struct ceph_osd_client *osdc, if (req->r_osd) { __cancel_request(req); list_del_init(&req->r_osd_item); + list_del_init(&req->r_linger_osd_item); req->r_osd = NULL; } diff --git a/net/core/dev.c b/net/core/dev.c index 945bbd001359..3acff0974560 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -7200,11 +7200,10 @@ static void __net_exit rtnl_lock_unregistering(struct list_head *net_list) */ struct net *net; bool unregistering; - DEFINE_WAIT(wait); + DEFINE_WAIT_FUNC(wait, woken_wake_function); + add_wait_queue(&netdev_unregistering_wq, &wait); for (;;) { - prepare_to_wait(&netdev_unregistering_wq, &wait, - TASK_UNINTERRUPTIBLE); unregistering = false; rtnl_lock(); list_for_each_entry(net, net_list, exit_list) { @@ -7216,9 +7215,10 @@ static void __net_exit rtnl_lock_unregistering(struct list_head *net_list) if (!unregistering) break; __rtnl_unlock(); - schedule(); + + wait_woken(&wait, TASK_UNINTERRUPTIBLE, MAX_SCHEDULE_TIMEOUT); } - finish_wait(&netdev_unregistering_wq, &wait); + remove_wait_queue(&netdev_unregistering_wq, &wait); } static void __net_exit default_device_exit_batch(struct list_head *net_list) diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c index a6882686ca3a..88e8de3b59b0 100644 --- a/net/core/rtnetlink.c +++ b/net/core/rtnetlink.c @@ -365,11 +365,10 @@ static void rtnl_lock_unregistering_all(void) { struct net *net; bool unregistering; - DEFINE_WAIT(wait); + DEFINE_WAIT_FUNC(wait, woken_wake_function); + add_wait_queue(&netdev_unregistering_wq, &wait); for (;;) { - prepare_to_wait(&netdev_unregistering_wq, &wait, - TASK_UNINTERRUPTIBLE); unregistering = false; rtnl_lock(); for_each_net(net) { @@ -381,9 +380,10 @@ static void rtnl_lock_unregistering_all(void) if (!unregistering) break; __rtnl_unlock(); - schedule(); + + wait_woken(&wait, TASK_UNINTERRUPTIBLE, MAX_SCHEDULE_TIMEOUT); } - finish_wait(&netdev_unregistering_wq, &wait); + remove_wait_queue(&netdev_unregistering_wq, &wait); } /** @@ -1498,6 +1498,7 @@ static int do_setlink(const struct sk_buff *skb, goto errout; } if (!netlink_ns_capable(skb, net->user_ns, CAP_NET_ADMIN)) { + put_net(net); err = -EPERM; goto errout; } @@ -2685,13 +2686,20 @@ static int rtnl_bridge_getlink(struct sk_buff *skb, struct netlink_callback *cb) int idx = 0; u32 portid = NETLINK_CB(cb->skb).portid; u32 seq = cb->nlh->nlmsg_seq; - struct nlattr *extfilt; u32 filter_mask = 0; - extfilt = nlmsg_find_attr(cb->nlh, sizeof(struct ifinfomsg), - IFLA_EXT_MASK); - if (extfilt) - filter_mask = nla_get_u32(extfilt); + if (nlmsg_len(cb->nlh) > sizeof(struct ifinfomsg)) { + struct nlattr *extfilt; + + extfilt = nlmsg_find_attr(cb->nlh, sizeof(struct ifinfomsg), + IFLA_EXT_MASK); + if (extfilt) { + if (nla_len(extfilt) < sizeof(filter_mask)) + return -EINVAL; + + filter_mask = nla_get_u32(extfilt); + } + } rcu_read_lock(); for_each_netdev_rcu(net, dev) { @@ -2798,6 +2806,9 @@ static int rtnl_bridge_setlink(struct sk_buff *skb, struct nlmsghdr *nlh) if (br_spec) { nla_for_each_nested(attr, br_spec, rem) { if (nla_type(attr) == IFLA_BRIDGE_FLAGS) { + if (nla_len(attr) < sizeof(flags)) + return -EINVAL; + have_flags = true; flags = nla_get_u16(attr); break; @@ -2868,6 +2879,9 @@ static int rtnl_bridge_dellink(struct sk_buff *skb, struct nlmsghdr *nlh) if (br_spec) { nla_for_each_nested(attr, br_spec, rem) { if (nla_type(attr) == IFLA_BRIDGE_FLAGS) { + if (nla_len(attr) < sizeof(flags)) + return -EINVAL; + have_flags = true; flags = nla_get_u16(attr); break; diff --git a/net/core/skbuff.c b/net/core/skbuff.c index c16615bfb61e..32e31c299631 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -552,20 +552,13 @@ static void kfree_skbmem(struct sk_buff *skb) case SKB_FCLONE_CLONE: fclones = container_of(skb, struct sk_buff_fclones, skb2); - /* Warning : We must perform the atomic_dec_and_test() before - * setting skb->fclone back to SKB_FCLONE_FREE, otherwise - * skb_clone() could set clone_ref to 2 before our decrement. - * Anyway, if we are going to free the structure, no need to - * rewrite skb->fclone. + /* The clone portion is available for + * fast-cloning again. */ - if (atomic_dec_and_test(&fclones->fclone_ref)) { + skb->fclone = SKB_FCLONE_FREE; + + if (atomic_dec_and_test(&fclones->fclone_ref)) kmem_cache_free(skbuff_fclone_cache, fclones); - } else { - /* The clone portion is available for - * fast-cloning again. - */ - skb->fclone = SKB_FCLONE_FREE; - } break; } } @@ -887,11 +880,7 @@ struct sk_buff *skb_clone(struct sk_buff *skb, gfp_t gfp_mask) if (skb->fclone == SKB_FCLONE_ORIG && n->fclone == SKB_FCLONE_FREE) { n->fclone = SKB_FCLONE_CLONE; - /* As our fastclone was free, clone_ref must be 1 at this point. - * We could use atomic_inc() here, but it is faster - * to set the final value. - */ - atomic_set(&fclones->fclone_ref, 2); + atomic_inc(&fclones->fclone_ref); } else { if (skb_pfmemalloc(skb)) gfp_mask |= __GFP_MEMALLOC; diff --git a/net/dcb/dcbnl.c b/net/dcb/dcbnl.c index ca11d283bbeb..93ea80196f0e 100644 --- a/net/dcb/dcbnl.c +++ b/net/dcb/dcbnl.c @@ -1080,13 +1080,13 @@ static int dcbnl_ieee_fill(struct sk_buff *skb, struct net_device *netdev) if (!app) return -EMSGSIZE; - spin_lock(&dcb_lock); + spin_lock_bh(&dcb_lock); list_for_each_entry(itr, &dcb_app_list, list) { if (itr->ifindex == netdev->ifindex) { err = nla_put(skb, DCB_ATTR_IEEE_APP, sizeof(itr->app), &itr->app); if (err) { - spin_unlock(&dcb_lock); + spin_unlock_bh(&dcb_lock); return -EMSGSIZE; } } @@ -1097,7 +1097,7 @@ static int dcbnl_ieee_fill(struct sk_buff *skb, struct net_device *netdev) else dcbx = -EOPNOTSUPP; - spin_unlock(&dcb_lock); + spin_unlock_bh(&dcb_lock); nla_nest_end(skb, app); /* get peer info if available */ @@ -1234,7 +1234,7 @@ static int dcbnl_cee_fill(struct sk_buff *skb, struct net_device *netdev) } /* local app */ - spin_lock(&dcb_lock); + spin_lock_bh(&dcb_lock); app = nla_nest_start(skb, DCB_ATTR_CEE_APP_TABLE); if (!app) goto dcb_unlock; @@ -1271,7 +1271,7 @@ static int dcbnl_cee_fill(struct sk_buff *skb, struct net_device *netdev) else dcbx = -EOPNOTSUPP; - spin_unlock(&dcb_lock); + spin_unlock_bh(&dcb_lock); /* features flags */ if (ops->getfeatcfg) { @@ -1326,7 +1326,7 @@ static int dcbnl_cee_fill(struct sk_buff *skb, struct net_device *netdev) return 0; dcb_unlock: - spin_unlock(&dcb_lock); + spin_unlock_bh(&dcb_lock); nla_put_failure: return err; } @@ -1762,10 +1762,10 @@ u8 dcb_getapp(struct net_device *dev, struct dcb_app *app) struct dcb_app_type *itr; u8 prio = 0; - spin_lock(&dcb_lock); + spin_lock_bh(&dcb_lock); if ((itr = dcb_app_lookup(app, dev->ifindex, 0))) prio = itr->app.priority; - spin_unlock(&dcb_lock); + spin_unlock_bh(&dcb_lock); return prio; } @@ -1789,7 +1789,7 @@ int dcb_setapp(struct net_device *dev, struct dcb_app *new) if (dev->dcbnl_ops->getdcbx) event.dcbx = dev->dcbnl_ops->getdcbx(dev); - spin_lock(&dcb_lock); + spin_lock_bh(&dcb_lock); /* Search for existing match and replace */ if ((itr = dcb_app_lookup(new, dev->ifindex, 0))) { if (new->priority) @@ -1804,7 +1804,7 @@ int dcb_setapp(struct net_device *dev, struct dcb_app *new) if (new->priority) err = dcb_app_add(new, dev->ifindex); out: - spin_unlock(&dcb_lock); + spin_unlock_bh(&dcb_lock); if (!err) call_dcbevent_notifiers(DCB_APP_EVENT, &event); return err; @@ -1823,10 +1823,10 @@ u8 dcb_ieee_getapp_mask(struct net_device *dev, struct dcb_app *app) struct dcb_app_type *itr; u8 prio = 0; - spin_lock(&dcb_lock); + spin_lock_bh(&dcb_lock); if ((itr = dcb_app_lookup(app, dev->ifindex, 0))) prio |= 1 << itr->app.priority; - spin_unlock(&dcb_lock); + spin_unlock_bh(&dcb_lock); return prio; } @@ -1850,7 +1850,7 @@ int dcb_ieee_setapp(struct net_device *dev, struct dcb_app *new) if (dev->dcbnl_ops->getdcbx) event.dcbx = dev->dcbnl_ops->getdcbx(dev); - spin_lock(&dcb_lock); + spin_lock_bh(&dcb_lock); /* Search for existing match and abort if found */ if (dcb_app_lookup(new, dev->ifindex, new->priority)) { err = -EEXIST; @@ -1859,7 +1859,7 @@ int dcb_ieee_setapp(struct net_device *dev, struct dcb_app *new) err = dcb_app_add(new, dev->ifindex); out: - spin_unlock(&dcb_lock); + spin_unlock_bh(&dcb_lock); if (!err) call_dcbevent_notifiers(DCB_APP_EVENT, &event); return err; @@ -1882,7 +1882,7 @@ int dcb_ieee_delapp(struct net_device *dev, struct dcb_app *del) if (dev->dcbnl_ops->getdcbx) event.dcbx = dev->dcbnl_ops->getdcbx(dev); - spin_lock(&dcb_lock); + spin_lock_bh(&dcb_lock); /* Search for existing match and remove it. */ if ((itr = dcb_app_lookup(del, dev->ifindex, del->priority))) { list_del(&itr->list); @@ -1890,7 +1890,7 @@ int dcb_ieee_delapp(struct net_device *dev, struct dcb_app *del) err = 0; } - spin_unlock(&dcb_lock); + spin_unlock_bh(&dcb_lock); if (!err) call_dcbevent_notifiers(DCB_APP_EVENT, &event); return err; @@ -1902,12 +1902,12 @@ static void dcb_flushapp(void) struct dcb_app_type *app; struct dcb_app_type *tmp; - spin_lock(&dcb_lock); + spin_lock_bh(&dcb_lock); list_for_each_entry_safe(app, tmp, &dcb_app_list, list) { list_del(&app->list); kfree(app); } - spin_unlock(&dcb_lock); + spin_unlock_bh(&dcb_lock); } static int __init dcbnl_init(void) diff --git a/net/dsa/slave.c b/net/dsa/slave.c index 6d1817449c36..ab03e00ffe8f 100644 --- a/net/dsa/slave.c +++ b/net/dsa/slave.c @@ -489,11 +489,14 @@ static void dsa_slave_phy_setup(struct dsa_slave_priv *p, /* We could not connect to a designated PHY, so use the switch internal * MDIO bus instead */ - if (!p->phy) + if (!p->phy) { p->phy = ds->slave_mii_bus->phy_map[p->port]; - else + phy_connect_direct(slave_dev, p->phy, dsa_slave_adjust_link, + p->phy_interface); + } else { pr_info("attached PHY at address %d [%s]\n", p->phy->addr, p->phy->drv->name); + } } int dsa_slave_suspend(struct net_device *slave_dev) diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c index 8b7fe5b03906..e67da4e6c324 100644 --- a/net/ipv4/af_inet.c +++ b/net/ipv4/af_inet.c @@ -1386,6 +1386,17 @@ out: return pp; } +int inet_recv_error(struct sock *sk, struct msghdr *msg, int len, int *addr_len) +{ + if (sk->sk_family == AF_INET) + return ip_recv_error(sk, msg, len, addr_len); +#if IS_ENABLED(CONFIG_IPV6) + if (sk->sk_family == AF_INET6) + return pingv6_ops.ipv6_recv_error(sk, msg, len, addr_len); +#endif + return -EINVAL; +} + static int inet_gro_complete(struct sk_buff *skb, int nhoff) { __be16 newlen = htons(skb->len - nhoff); diff --git a/net/ipv4/fib_rules.c b/net/ipv4/fib_rules.c index f2e15738534d..8f7bd56955b0 100644 --- a/net/ipv4/fib_rules.c +++ b/net/ipv4/fib_rules.c @@ -62,6 +62,10 @@ int __fib_lookup(struct net *net, struct flowi4 *flp, struct fib_result *res) else res->tclassid = 0; #endif + + if (err == -ESRCH) + err = -ENETUNREACH; + return err; } EXPORT_SYMBOL_GPL(__fib_lookup); diff --git a/net/ipv4/fou.c b/net/ipv4/fou.c index 32e78924e246..606c520ffd5a 100644 --- a/net/ipv4/fou.c +++ b/net/ipv4/fou.c @@ -133,6 +133,8 @@ static int fou_gro_complete(struct sk_buff *skb, int nhoff) int err = -ENOSYS; const struct net_offload **offloads; + udp_tunnel_gro_complete(skb, nhoff); + rcu_read_lock(); offloads = NAPI_GRO_CB(skb)->is_ipv6 ? inet6_offloads : inet_offloads; ops = rcu_dereference(offloads[proto]); diff --git a/net/ipv4/geneve.c b/net/ipv4/geneve.c index 065cd94c640c..dedb21e99914 100644 --- a/net/ipv4/geneve.c +++ b/net/ipv4/geneve.c @@ -144,6 +144,8 @@ int geneve_xmit_skb(struct geneve_sock *gs, struct rtable *rt, gnvh = (struct genevehdr *)__skb_push(skb, sizeof(*gnvh) + opt_len); geneve_build_header(gnvh, tun_flags, vni, opt_len, opt); + skb_set_inner_protocol(skb, htons(ETH_P_TEB)); + return udp_tunnel_xmit_skb(gs->sock, rt, skb, src, dst, tos, ttl, df, src_port, dst_port, xnet); } @@ -364,6 +366,7 @@ late_initcall(geneve_init_module); static void __exit geneve_cleanup_module(void) { destroy_workqueue(geneve_wq); + unregister_pernet_subsys(&geneve_net_ops); } module_exit(geneve_cleanup_module); diff --git a/net/ipv4/igmp.c b/net/ipv4/igmp.c index fb70e3ecc3e4..bb15d0e03d4f 100644 --- a/net/ipv4/igmp.c +++ b/net/ipv4/igmp.c @@ -318,9 +318,7 @@ igmp_scount(struct ip_mc_list *pmc, int type, int gdeleted, int sdeleted) return scount; } -#define igmp_skb_size(skb) (*(unsigned int *)((skb)->cb)) - -static struct sk_buff *igmpv3_newpack(struct net_device *dev, int size) +static struct sk_buff *igmpv3_newpack(struct net_device *dev, unsigned int mtu) { struct sk_buff *skb; struct rtable *rt; @@ -330,6 +328,7 @@ static struct sk_buff *igmpv3_newpack(struct net_device *dev, int size) struct flowi4 fl4; int hlen = LL_RESERVED_SPACE(dev); int tlen = dev->needed_tailroom; + unsigned int size = mtu; while (1) { skb = alloc_skb(size + hlen + tlen, @@ -341,7 +340,6 @@ static struct sk_buff *igmpv3_newpack(struct net_device *dev, int size) return NULL; } skb->priority = TC_PRIO_CONTROL; - igmp_skb_size(skb) = size; rt = ip_route_output_ports(net, &fl4, NULL, IGMPV3_ALL_MCR, 0, 0, 0, @@ -354,6 +352,8 @@ static struct sk_buff *igmpv3_newpack(struct net_device *dev, int size) skb_dst_set(skb, &rt->dst); skb->dev = dev; + skb->reserved_tailroom = skb_end_offset(skb) - + min(mtu, skb_end_offset(skb)); skb_reserve(skb, hlen); skb_reset_network_header(skb); @@ -423,8 +423,7 @@ static struct sk_buff *add_grhead(struct sk_buff *skb, struct ip_mc_list *pmc, return skb; } -#define AVAILABLE(skb) ((skb) ? ((skb)->dev ? igmp_skb_size(skb) - (skb)->len : \ - skb_tailroom(skb)) : 0) +#define AVAILABLE(skb) ((skb) ? skb_availroom(skb) : 0) static struct sk_buff *add_grec(struct sk_buff *skb, struct ip_mc_list *pmc, int type, int gdeleted, int sdeleted) diff --git a/net/ipv4/ip_sockglue.c b/net/ipv4/ip_sockglue.c index c373a9ad4555..9daf2177dc00 100644 --- a/net/ipv4/ip_sockglue.c +++ b/net/ipv4/ip_sockglue.c @@ -195,7 +195,7 @@ int ip_cmsg_send(struct net *net, struct msghdr *msg, struct ipcm_cookie *ipc, for (cmsg = CMSG_FIRSTHDR(msg); cmsg; cmsg = CMSG_NXTHDR(msg, cmsg)) { if (!CMSG_OK(msg, cmsg)) return -EINVAL; -#if defined(CONFIG_IPV6) +#if IS_ENABLED(CONFIG_IPV6) if (allow_ipv6 && cmsg->cmsg_level == SOL_IPV6 && cmsg->cmsg_type == IPV6_PKTINFO) { diff --git a/net/ipv4/ip_vti.c b/net/ipv4/ip_vti.c index 3e861011e4a3..1a7e979e80ba 100644 --- a/net/ipv4/ip_vti.c +++ b/net/ipv4/ip_vti.c @@ -528,6 +528,7 @@ static struct rtnl_link_ops vti_link_ops __read_mostly = { .validate = vti_tunnel_validate, .newlink = vti_newlink, .changelink = vti_changelink, + .dellink = ip_tunnel_dellink, .get_size = vti_get_size, .fill_info = vti_fill_info, }; diff --git a/net/ipv4/netfilter/nft_masq_ipv4.c b/net/ipv4/netfilter/nft_masq_ipv4.c index c1023c445920..665de06561cd 100644 --- a/net/ipv4/netfilter/nft_masq_ipv4.c +++ b/net/ipv4/netfilter/nft_masq_ipv4.c @@ -24,6 +24,7 @@ static void nft_masq_ipv4_eval(const struct nft_expr *expr, struct nf_nat_range range; unsigned int verdict; + memset(&range, 0, sizeof(range)); range.flags = priv->flags; verdict = nf_nat_masquerade_ipv4(pkt->skb, pkt->ops->hooknum, diff --git a/net/ipv4/ping.c b/net/ipv4/ping.c index 57f7c9804139..5d740cccf69e 100644 --- a/net/ipv4/ping.c +++ b/net/ipv4/ping.c @@ -217,6 +217,8 @@ static struct sock *ping_lookup(struct net *net, struct sk_buff *skb, u16 ident) &ipv6_hdr(skb)->daddr)) continue; #endif + } else { + continue; } if (sk->sk_bound_dev_if && sk->sk_bound_dev_if != dif) @@ -853,16 +855,8 @@ int ping_recvmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg, if (flags & MSG_OOB) goto out; - if (flags & MSG_ERRQUEUE) { - if (family == AF_INET) { - return ip_recv_error(sk, msg, len, addr_len); -#if IS_ENABLED(CONFIG_IPV6) - } else if (family == AF_INET6) { - return pingv6_ops.ipv6_recv_error(sk, msg, len, - addr_len); -#endif - } - } + if (flags & MSG_ERRQUEUE) + return inet_recv_error(sk, msg, len, addr_len); skb = skb_recv_datagram(sk, flags, noblock, &err); if (!skb) diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index 39ec0c379545..38c2bcb8dd5d 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -1598,7 +1598,7 @@ int tcp_recvmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg, u32 urg_hole = 0; if (unlikely(flags & MSG_ERRQUEUE)) - return ip_recv_error(sk, msg, len, addr_len); + return inet_recv_error(sk, msg, len, addr_len); if (sk_can_busy_loop(sk) && skb_queue_empty(&sk->sk_receive_queue) && (sk->sk_state == TCP_ESTABLISHED)) diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index a12b455928e5..d107ee246a1d 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -2315,6 +2315,35 @@ static inline bool tcp_packet_delayed(const struct tcp_sock *tp) /* Undo procedures. */ +/* We can clear retrans_stamp when there are no retransmissions in the + * window. It would seem that it is trivially available for us in + * tp->retrans_out, however, that kind of assumptions doesn't consider + * what will happen if errors occur when sending retransmission for the + * second time. ...It could the that such segment has only + * TCPCB_EVER_RETRANS set at the present time. It seems that checking + * the head skb is enough except for some reneging corner cases that + * are not worth the effort. + * + * Main reason for all this complexity is the fact that connection dying + * time now depends on the validity of the retrans_stamp, in particular, + * that successive retransmissions of a segment must not advance + * retrans_stamp under any conditions. + */ +static bool tcp_any_retrans_done(const struct sock *sk) +{ + const struct tcp_sock *tp = tcp_sk(sk); + struct sk_buff *skb; + + if (tp->retrans_out) + return true; + + skb = tcp_write_queue_head(sk); + if (unlikely(skb && TCP_SKB_CB(skb)->sacked & TCPCB_EVER_RETRANS)) + return true; + + return false; +} + #if FASTRETRANS_DEBUG > 1 static void DBGUNDO(struct sock *sk, const char *msg) { @@ -2410,6 +2439,8 @@ static bool tcp_try_undo_recovery(struct sock *sk) * is ACKed. For Reno it is MUST to prevent false * fast retransmits (RFC2582). SACK TCP is safe. */ tcp_moderate_cwnd(tp); + if (!tcp_any_retrans_done(sk)) + tp->retrans_stamp = 0; return true; } tcp_set_ca_state(sk, TCP_CA_Open); @@ -2430,35 +2461,6 @@ static bool tcp_try_undo_dsack(struct sock *sk) return false; } -/* We can clear retrans_stamp when there are no retransmissions in the - * window. It would seem that it is trivially available for us in - * tp->retrans_out, however, that kind of assumptions doesn't consider - * what will happen if errors occur when sending retransmission for the - * second time. ...It could the that such segment has only - * TCPCB_EVER_RETRANS set at the present time. It seems that checking - * the head skb is enough except for some reneging corner cases that - * are not worth the effort. - * - * Main reason for all this complexity is the fact that connection dying - * time now depends on the validity of the retrans_stamp, in particular, - * that successive retransmissions of a segment must not advance - * retrans_stamp under any conditions. - */ -static bool tcp_any_retrans_done(const struct sock *sk) -{ - const struct tcp_sock *tp = tcp_sk(sk); - struct sk_buff *skb; - - if (tp->retrans_out) - return true; - - skb = tcp_write_queue_head(sk); - if (unlikely(skb && TCP_SKB_CB(skb)->sacked & TCPCB_EVER_RETRANS)) - return true; - - return false; -} - /* Undo during loss recovery after partial ACK or using F-RTO. */ static bool tcp_try_undo_loss(struct sock *sk, bool frto_undo) { @@ -5229,7 +5231,7 @@ slow_path: if (len < (th->doff << 2) || tcp_checksum_complete_user(sk, skb)) goto csum_error; - if (!th->ack && !th->rst) + if (!th->ack && !th->rst && !th->syn) goto discard; /* @@ -5648,7 +5650,7 @@ int tcp_rcv_state_process(struct sock *sk, struct sk_buff *skb, goto discard; } - if (!th->ack && !th->rst) + if (!th->ack && !th->rst && !th->syn) goto discard; if (!tcp_validate_incoming(sk, skb, th, 0)) diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index 9c7d7621466b..147be2024290 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -598,7 +598,10 @@ static void tcp_v4_send_reset(struct sock *sk, struct sk_buff *skb) if (th->rst) return; - if (skb_rtable(skb)->rt_type != RTN_LOCAL) + /* If sk not NULL, it means we did a successful lookup and incoming + * route had to be correct. prequeue might have dropped our dst. + */ + if (!sk && skb_rtable(skb)->rt_type != RTN_LOCAL) return; /* Swap the send and the receive. */ diff --git a/net/ipv6/ip6_gre.c b/net/ipv6/ip6_gre.c index 12c3c8ef3849..0e32d2e1bdbf 100644 --- a/net/ipv6/ip6_gre.c +++ b/net/ipv6/ip6_gre.c @@ -502,11 +502,11 @@ static int ip6gre_rcv(struct sk_buff *skb) skb->protocol = gre_proto; /* WCCP version 1 and 2 protocol decoding. - * - Change protocol to IP + * - Change protocol to IPv6 * - When dealing with WCCPv2, Skip extra 4 bytes in GRE header */ if (flags == 0 && gre_proto == htons(ETH_P_WCCP)) { - skb->protocol = htons(ETH_P_IP); + skb->protocol = htons(ETH_P_IPV6); if ((*(h + offset) & 0xF0) != 0x40) offset += 4; } @@ -961,8 +961,6 @@ static void ip6gre_tnl_link_config(struct ip6_tnl *t, int set_mtu) else dev->flags &= ~IFF_POINTOPOINT; - dev->iflink = p->link; - /* Precalculate GRE options length */ if (t->parms.o_flags&(GRE_CSUM|GRE_KEY|GRE_SEQ)) { if (t->parms.o_flags&GRE_CSUM) @@ -1272,6 +1270,7 @@ static int ip6gre_tunnel_init(struct net_device *dev) u64_stats_init(&ip6gre_tunnel_stats->syncp); } + dev->iflink = tunnel->parms.link; return 0; } @@ -1481,6 +1480,8 @@ static int ip6gre_tap_init(struct net_device *dev) if (!dev->tstats) return -ENOMEM; + dev->iflink = tunnel->parms.link; + return 0; } diff --git a/net/ipv6/ip6_offload.c b/net/ipv6/ip6_offload.c index a071563a7e6e..01e12d0d8fcc 100644 --- a/net/ipv6/ip6_offload.c +++ b/net/ipv6/ip6_offload.c @@ -69,7 +69,8 @@ static struct sk_buff *ipv6_gso_segment(struct sk_buff *skb, int nhoff; if (unlikely(skb_shinfo(skb)->gso_type & - ~(SKB_GSO_UDP | + ~(SKB_GSO_TCPV4 | + SKB_GSO_UDP | SKB_GSO_DODGY | SKB_GSO_TCP_ECN | SKB_GSO_GRE | diff --git a/net/ipv6/ip6_tunnel.c b/net/ipv6/ip6_tunnel.c index 9409887fb664..9cb94cfa0ae7 100644 --- a/net/ipv6/ip6_tunnel.c +++ b/net/ipv6/ip6_tunnel.c @@ -272,9 +272,6 @@ static int ip6_tnl_create2(struct net_device *dev) int err; t = netdev_priv(dev); - err = ip6_tnl_dev_init(dev); - if (err < 0) - goto out; err = register_netdevice(dev); if (err < 0) @@ -1462,6 +1459,7 @@ ip6_tnl_change_mtu(struct net_device *dev, int new_mtu) static const struct net_device_ops ip6_tnl_netdev_ops = { + .ndo_init = ip6_tnl_dev_init, .ndo_uninit = ip6_tnl_dev_uninit, .ndo_start_xmit = ip6_tnl_xmit, .ndo_do_ioctl = ip6_tnl_ioctl, @@ -1546,16 +1544,10 @@ static int __net_init ip6_fb_tnl_dev_init(struct net_device *dev) struct ip6_tnl *t = netdev_priv(dev); struct net *net = dev_net(dev); struct ip6_tnl_net *ip6n = net_generic(net, ip6_tnl_net_id); - int err = ip6_tnl_dev_init_gen(dev); - - if (err) - return err; t->parms.proto = IPPROTO_IPV6; dev_hold(dev); - ip6_tnl_link_config(t); - rcu_assign_pointer(ip6n->tnls_wc[0], t); return 0; } diff --git a/net/ipv6/ip6_udp_tunnel.c b/net/ipv6/ip6_udp_tunnel.c index b04ed72c4542..8db6c98fe218 100644 --- a/net/ipv6/ip6_udp_tunnel.c +++ b/net/ipv6/ip6_udp_tunnel.c @@ -79,15 +79,13 @@ int udp_tunnel6_xmit_skb(struct socket *sock, struct dst_entry *dst, uh->source = src_port; uh->len = htons(skb->len); - uh->check = 0; memset(&(IPCB(skb)->opt), 0, sizeof(IPCB(skb)->opt)); IPCB(skb)->flags &= ~(IPSKB_XFRM_TUNNEL_SIZE | IPSKB_XFRM_TRANSFORMED | IPSKB_REROUTED); skb_dst_set(skb, dst); - udp6_set_csum(udp_get_no_check6_tx(sk), skb, &inet6_sk(sk)->saddr, - &sk->sk_v6_daddr, skb->len); + udp6_set_csum(udp_get_no_check6_tx(sk), skb, saddr, daddr, skb->len); __skb_push(skb, sizeof(*ip6h)); skb_reset_network_header(skb); diff --git a/net/ipv6/ip6_vti.c b/net/ipv6/ip6_vti.c index d440bb585524..bcda14de7f84 100644 --- a/net/ipv6/ip6_vti.c +++ b/net/ipv6/ip6_vti.c @@ -172,10 +172,6 @@ static int vti6_tnl_create2(struct net_device *dev) struct vti6_net *ip6n = net_generic(net, vti6_net_id); int err; - err = vti6_dev_init(dev); - if (err < 0) - goto out; - err = register_netdevice(dev); if (err < 0) goto out; @@ -783,6 +779,7 @@ static int vti6_change_mtu(struct net_device *dev, int new_mtu) } static const struct net_device_ops vti6_netdev_ops = { + .ndo_init = vti6_dev_init, .ndo_uninit = vti6_dev_uninit, .ndo_start_xmit = vti6_tnl_xmit, .ndo_do_ioctl = vti6_ioctl, @@ -852,16 +849,10 @@ static int __net_init vti6_fb_tnl_dev_init(struct net_device *dev) struct ip6_tnl *t = netdev_priv(dev); struct net *net = dev_net(dev); struct vti6_net *ip6n = net_generic(net, vti6_net_id); - int err = vti6_dev_init_gen(dev); - - if (err) - return err; t->parms.proto = IPPROTO_IPV6; dev_hold(dev); - vti6_link_config(t); - rcu_assign_pointer(ip6n->tnls_wc[0], t); return 0; } @@ -914,6 +905,15 @@ static int vti6_newlink(struct net *src_net, struct net_device *dev, return vti6_tnl_create2(dev); } +static void vti6_dellink(struct net_device *dev, struct list_head *head) +{ + struct net *net = dev_net(dev); + struct vti6_net *ip6n = net_generic(net, vti6_net_id); + + if (dev != ip6n->fb_tnl_dev) + unregister_netdevice_queue(dev, head); +} + static int vti6_changelink(struct net_device *dev, struct nlattr *tb[], struct nlattr *data[]) { @@ -989,6 +989,7 @@ static struct rtnl_link_ops vti6_link_ops __read_mostly = { .setup = vti6_dev_setup, .validate = vti6_validate, .newlink = vti6_newlink, + .dellink = vti6_dellink, .changelink = vti6_changelink, .get_size = vti6_get_size, .fill_info = vti6_fill_info, @@ -1029,6 +1030,7 @@ static int __net_init vti6_init_net(struct net *net) if (!ip6n->fb_tnl_dev) goto err_alloc_dev; dev_net_set(ip6n->fb_tnl_dev, net); + ip6n->fb_tnl_dev->rtnl_link_ops = &vti6_link_ops; err = vti6_fb_tnl_dev_init(ip6n->fb_tnl_dev); if (err < 0) diff --git a/net/ipv6/ip6mr.c b/net/ipv6/ip6mr.c index 0171f08325c3..1a01d79b8698 100644 --- a/net/ipv6/ip6mr.c +++ b/net/ipv6/ip6mr.c @@ -1439,6 +1439,10 @@ reg_pernet_fail: void ip6_mr_cleanup(void) { + rtnl_unregister(RTNL_FAMILY_IP6MR, RTM_GETROUTE); +#ifdef CONFIG_IPV6_PIMSM_V2 + inet6_del_protocol(&pim6_protocol, IPPROTO_PIM); +#endif unregister_netdevice_notifier(&ip6_mr_notifier); unregister_pernet_subsys(&ip6mr_net_ops); kmem_cache_destroy(mrt_cachep); diff --git a/net/ipv6/mcast.c b/net/ipv6/mcast.c index 9648de2b6745..ed2c4e400b46 100644 --- a/net/ipv6/mcast.c +++ b/net/ipv6/mcast.c @@ -1550,7 +1550,7 @@ static void ip6_mc_hdr(struct sock *sk, struct sk_buff *skb, hdr->daddr = *daddr; } -static struct sk_buff *mld_newpack(struct inet6_dev *idev, int size) +static struct sk_buff *mld_newpack(struct inet6_dev *idev, unsigned int mtu) { struct net_device *dev = idev->dev; struct net *net = dev_net(dev); @@ -1561,13 +1561,13 @@ static struct sk_buff *mld_newpack(struct inet6_dev *idev, int size) const struct in6_addr *saddr; int hlen = LL_RESERVED_SPACE(dev); int tlen = dev->needed_tailroom; + unsigned int size = mtu + hlen + tlen; int err; u8 ra[8] = { IPPROTO_ICMPV6, 0, IPV6_TLV_ROUTERALERT, 2, 0, 0, IPV6_TLV_PADN, 0 }; /* we assume size > sizeof(ra) here */ - size += hlen + tlen; /* limit our allocations to order-0 page */ size = min_t(int, size, SKB_MAX_ORDER(0, 0)); skb = sock_alloc_send_skb(sk, size, 1, &err); @@ -1576,6 +1576,8 @@ static struct sk_buff *mld_newpack(struct inet6_dev *idev, int size) return NULL; skb->priority = TC_PRIO_CONTROL; + skb->reserved_tailroom = skb_end_offset(skb) - + min(mtu, skb_end_offset(skb)); skb_reserve(skb, hlen); if (__ipv6_get_lladdr(idev, &addr_buf, IFA_F_TENTATIVE)) { @@ -1690,8 +1692,7 @@ static struct sk_buff *add_grhead(struct sk_buff *skb, struct ifmcaddr6 *pmc, return skb; } -#define AVAILABLE(skb) ((skb) ? ((skb)->dev ? (skb)->dev->mtu - (skb)->len : \ - skb_tailroom(skb)) : 0) +#define AVAILABLE(skb) ((skb) ? skb_availroom(skb) : 0) static struct sk_buff *add_grec(struct sk_buff *skb, struct ifmcaddr6 *pmc, int type, int gdeleted, int sdeleted, int crsend) diff --git a/net/ipv6/netfilter/nft_masq_ipv6.c b/net/ipv6/netfilter/nft_masq_ipv6.c index 8a7ac685076d..529c119cbb14 100644 --- a/net/ipv6/netfilter/nft_masq_ipv6.c +++ b/net/ipv6/netfilter/nft_masq_ipv6.c @@ -25,6 +25,7 @@ static void nft_masq_ipv6_eval(const struct nft_expr *expr, struct nf_nat_range range; unsigned int verdict; + memset(&range, 0, sizeof(range)); range.flags = priv->flags; verdict = nf_nat_masquerade_ipv6(pkt->skb, &range, pkt->out); diff --git a/net/ipv6/sit.c b/net/ipv6/sit.c index 58e5b4710127..a24557a1c1d8 100644 --- a/net/ipv6/sit.c +++ b/net/ipv6/sit.c @@ -195,10 +195,8 @@ static int ipip6_tunnel_create(struct net_device *dev) struct sit_net *sitn = net_generic(net, sit_net_id); int err; - err = ipip6_tunnel_init(dev); - if (err < 0) - goto out; - ipip6_tunnel_clone_6rd(dev, sitn); + memcpy(dev->dev_addr, &t->parms.iph.saddr, 4); + memcpy(dev->broadcast, &t->parms.iph.daddr, 4); if ((__force u16)t->parms.i_flags & SIT_ISATAP) dev->priv_flags |= IFF_ISATAP; @@ -207,7 +205,8 @@ static int ipip6_tunnel_create(struct net_device *dev) if (err < 0) goto out; - strcpy(t->parms.name, dev->name); + ipip6_tunnel_clone_6rd(dev, sitn); + dev->rtnl_link_ops = &sit_link_ops; dev_hold(dev); @@ -1330,6 +1329,7 @@ static int ipip6_tunnel_change_mtu(struct net_device *dev, int new_mtu) } static const struct net_device_ops ipip6_netdev_ops = { + .ndo_init = ipip6_tunnel_init, .ndo_uninit = ipip6_tunnel_uninit, .ndo_start_xmit = sit_tunnel_xmit, .ndo_do_ioctl = ipip6_tunnel_ioctl, @@ -1378,9 +1378,7 @@ static int ipip6_tunnel_init(struct net_device *dev) tunnel->dev = dev; tunnel->net = dev_net(dev); - - memcpy(dev->dev_addr, &tunnel->parms.iph.saddr, 4); - memcpy(dev->broadcast, &tunnel->parms.iph.daddr, 4); + strcpy(tunnel->parms.name, dev->name); ipip6_tunnel_bind_dev(dev); dev->tstats = netdev_alloc_pcpu_stats(struct pcpu_sw_netstats); @@ -1405,7 +1403,6 @@ static int __net_init ipip6_fb_tunnel_init(struct net_device *dev) tunnel->dev = dev; tunnel->net = dev_net(dev); - strcpy(tunnel->parms.name, dev->name); iph->version = 4; iph->protocol = IPPROTO_IPV6; diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c index ace29b60813c..dc495ae2ead0 100644 --- a/net/ipv6/tcp_ipv6.c +++ b/net/ipv6/tcp_ipv6.c @@ -903,7 +903,10 @@ static void tcp_v6_send_reset(struct sock *sk, struct sk_buff *skb) if (th->rst) return; - if (!ipv6_unicast_destination(skb)) + /* If sk not NULL, it means we did a successful lookup and incoming + * route had to be correct. prequeue might have dropped our dst. + */ + if (!sk && !ipv6_unicast_destination(skb)) return; #ifdef CONFIG_TCP_MD5SIG diff --git a/net/ipx/af_ipx.c b/net/ipx/af_ipx.c index 91729b807c7d..1b095ca37aa4 100644 --- a/net/ipx/af_ipx.c +++ b/net/ipx/af_ipx.c @@ -1764,6 +1764,7 @@ static int ipx_recvmsg(struct kiocb *iocb, struct socket *sock, struct ipxhdr *ipx = NULL; struct sk_buff *skb; int copied, rc; + bool locked = true; lock_sock(sk); /* put the autobinding in */ @@ -1790,6 +1791,8 @@ static int ipx_recvmsg(struct kiocb *iocb, struct socket *sock, if (sock_flag(sk, SOCK_ZAPPED)) goto out; + release_sock(sk); + locked = false; skb = skb_recv_datagram(sk, flags & ~MSG_DONTWAIT, flags & MSG_DONTWAIT, &rc); if (!skb) { @@ -1826,7 +1829,8 @@ static int ipx_recvmsg(struct kiocb *iocb, struct socket *sock, out_free: skb_free_datagram(sk, skb); out: - release_sock(sk); + if (locked) + release_sock(sk); return rc; } diff --git a/net/mac80211/aes_ccm.c b/net/mac80211/aes_ccm.c index ec24378caaaf..09d9caaec591 100644 --- a/net/mac80211/aes_ccm.c +++ b/net/mac80211/aes_ccm.c @@ -53,6 +53,9 @@ int ieee80211_aes_ccm_decrypt(struct crypto_aead *tfm, u8 *b_0, u8 *aad, __aligned(__alignof__(struct aead_request)); struct aead_request *aead_req = (void *) aead_req_data; + if (data_len == 0) + return -EINVAL; + memset(aead_req, 0, sizeof(aead_req_data)); sg_init_one(&pt, data, data_len); diff --git a/net/mac80211/ibss.c b/net/mac80211/ibss.c index 56b53571c807..509bc157ce55 100644 --- a/net/mac80211/ibss.c +++ b/net/mac80211/ibss.c @@ -805,7 +805,7 @@ ieee80211_ibss_process_chanswitch(struct ieee80211_sub_if_data *sdata, memset(¶ms, 0, sizeof(params)); memset(&csa_ie, 0, sizeof(csa_ie)); - err = ieee80211_parse_ch_switch_ie(sdata, elems, beacon, + err = ieee80211_parse_ch_switch_ie(sdata, elems, ifibss->chandef.chan->band, sta_flags, ifibss->bssid, &csa_ie); /* can't switch to destination channel, fail */ diff --git a/net/mac80211/ieee80211_i.h b/net/mac80211/ieee80211_i.h index c2aaec4dfcf0..8c68da30595d 100644 --- a/net/mac80211/ieee80211_i.h +++ b/net/mac80211/ieee80211_i.h @@ -1642,7 +1642,6 @@ void ieee80211_process_measurement_req(struct ieee80211_sub_if_data *sdata, * ieee80211_parse_ch_switch_ie - parses channel switch IEs * @sdata: the sdata of the interface which has received the frame * @elems: parsed 802.11 elements received with the frame - * @beacon: indicates if the frame was a beacon or probe response * @current_band: indicates the current band * @sta_flags: contains information about own capabilities and restrictions * to decide which channel switch announcements can be accepted. Only the @@ -1656,7 +1655,7 @@ void ieee80211_process_measurement_req(struct ieee80211_sub_if_data *sdata, * Return: 0 on success, <0 on error and >0 if there is nothing to parse. */ int ieee80211_parse_ch_switch_ie(struct ieee80211_sub_if_data *sdata, - struct ieee802_11_elems *elems, bool beacon, + struct ieee802_11_elems *elems, enum ieee80211_band current_band, u32 sta_flags, u8 *bssid, struct ieee80211_csa_ie *csa_ie); diff --git a/net/mac80211/iface.c b/net/mac80211/iface.c index af237223a8cd..653f5eb07a27 100644 --- a/net/mac80211/iface.c +++ b/net/mac80211/iface.c @@ -766,10 +766,12 @@ static void ieee80211_do_stop(struct ieee80211_sub_if_data *sdata, int i, flushed; struct ps_data *ps; struct cfg80211_chan_def chandef; + bool cancel_scan; clear_bit(SDATA_STATE_RUNNING, &sdata->state); - if (rcu_access_pointer(local->scan_sdata) == sdata) + cancel_scan = rcu_access_pointer(local->scan_sdata) == sdata; + if (cancel_scan) ieee80211_scan_cancel(local); /* @@ -898,6 +900,8 @@ static void ieee80211_do_stop(struct ieee80211_sub_if_data *sdata, list_del(&sdata->u.vlan.list); mutex_unlock(&local->mtx); RCU_INIT_POINTER(sdata->vif.chanctx_conf, NULL); + /* see comment in the default case below */ + ieee80211_free_keys(sdata, true); /* no need to tell driver */ break; case NL80211_IFTYPE_MONITOR: @@ -923,17 +927,16 @@ static void ieee80211_do_stop(struct ieee80211_sub_if_data *sdata, /* * When we get here, the interface is marked down. * Free the remaining keys, if there are any - * (shouldn't be, except maybe in WDS mode?) + * (which can happen in AP mode if userspace sets + * keys before the interface is operating, and maybe + * also in WDS mode) * * Force the key freeing to always synchronize_net() * to wait for the RX path in case it is using this - * interface enqueuing frames * at this very time on + * interface enqueuing frames at this very time on * another CPU. */ ieee80211_free_keys(sdata, true); - - /* fall through */ - case NL80211_IFTYPE_AP: skb_queue_purge(&sdata->skb_queue); } @@ -991,6 +994,9 @@ static void ieee80211_do_stop(struct ieee80211_sub_if_data *sdata, ieee80211_recalc_ps(local, -1); + if (cancel_scan) + flush_delayed_work(&local->scan_work); + if (local->open_count == 0) { ieee80211_stop_device(local); diff --git a/net/mac80211/mesh.c b/net/mac80211/mesh.c index e9f99c1e3fad..0c8b2a77d312 100644 --- a/net/mac80211/mesh.c +++ b/net/mac80211/mesh.c @@ -874,7 +874,7 @@ ieee80211_mesh_process_chnswitch(struct ieee80211_sub_if_data *sdata, memset(¶ms, 0, sizeof(params)); memset(&csa_ie, 0, sizeof(csa_ie)); - err = ieee80211_parse_ch_switch_ie(sdata, elems, beacon, band, + err = ieee80211_parse_ch_switch_ie(sdata, elems, band, sta_flags, sdata->vif.addr, &csa_ie); if (err < 0) diff --git a/net/mac80211/mlme.c b/net/mac80211/mlme.c index 2de88704278b..93af0f1c9d99 100644 --- a/net/mac80211/mlme.c +++ b/net/mac80211/mlme.c @@ -1072,7 +1072,7 @@ ieee80211_sta_process_chanswitch(struct ieee80211_sub_if_data *sdata, current_band = cbss->channel->band; memset(&csa_ie, 0, sizeof(csa_ie)); - res = ieee80211_parse_ch_switch_ie(sdata, elems, beacon, current_band, + res = ieee80211_parse_ch_switch_ie(sdata, elems, current_band, ifmgd->flags, ifmgd->associated->bssid, &csa_ie); if (res < 0) @@ -1168,7 +1168,8 @@ ieee80211_sta_process_chanswitch(struct ieee80211_sub_if_data *sdata, ieee80211_queue_work(&local->hw, &ifmgd->chswitch_work); else mod_timer(&ifmgd->chswitch_timer, - TU_TO_EXP_TIME(csa_ie.count * cbss->beacon_interval)); + TU_TO_EXP_TIME((csa_ie.count - 1) * + cbss->beacon_interval)); } static bool diff --git a/net/mac80211/rc80211_minstrel_ht.c b/net/mac80211/rc80211_minstrel_ht.c index df90ce2db00c..408fd8ab4eef 100644 --- a/net/mac80211/rc80211_minstrel_ht.c +++ b/net/mac80211/rc80211_minstrel_ht.c @@ -252,19 +252,16 @@ minstrel_ht_sort_best_tp_rates(struct minstrel_ht_sta *mi, u8 index, cur_thr = mi->groups[cur_group].rates[cur_idx].cur_tp; cur_prob = mi->groups[cur_group].rates[cur_idx].probability; - tmp_group = tp_list[j - 1] / MCS_GROUP_RATES; - tmp_idx = tp_list[j - 1] % MCS_GROUP_RATES; - tmp_thr = mi->groups[tmp_group].rates[tmp_idx].cur_tp; - tmp_prob = mi->groups[tmp_group].rates[tmp_idx].probability; - - while (j > 0 && (cur_thr > tmp_thr || - (cur_thr == tmp_thr && cur_prob > tmp_prob))) { - j--; + do { tmp_group = tp_list[j - 1] / MCS_GROUP_RATES; tmp_idx = tp_list[j - 1] % MCS_GROUP_RATES; tmp_thr = mi->groups[tmp_group].rates[tmp_idx].cur_tp; tmp_prob = mi->groups[tmp_group].rates[tmp_idx].probability; - } + if (cur_thr < tmp_thr || + (cur_thr == tmp_thr && cur_prob <= tmp_prob)) + break; + j--; + } while (j > 0); if (j < MAX_THR_RATES - 1) { memmove(&tp_list[j + 1], &tp_list[j], (sizeof(*tp_list) * diff --git a/net/mac80211/rx.c b/net/mac80211/rx.c index b04ca4049c95..a37f9af634cb 100644 --- a/net/mac80211/rx.c +++ b/net/mac80211/rx.c @@ -1678,11 +1678,14 @@ ieee80211_rx_h_defragment(struct ieee80211_rx_data *rx) sc = le16_to_cpu(hdr->seq_ctrl); frag = sc & IEEE80211_SCTL_FRAG; - if (likely((!ieee80211_has_morefrags(fc) && frag == 0) || - is_multicast_ether_addr(hdr->addr1))) { - /* not fragmented */ + if (likely(!ieee80211_has_morefrags(fc) && frag == 0)) + goto out; + + if (is_multicast_ether_addr(hdr->addr1)) { + rx->local->dot11MulticastReceivedFrameCount++; goto out; } + I802_DEBUG_INC(rx->local->rx_handlers_fragments); if (skb_linearize(rx->skb)) @@ -1775,10 +1778,7 @@ ieee80211_rx_h_defragment(struct ieee80211_rx_data *rx) out: if (rx->sta) rx->sta->rx_packets++; - if (is_multicast_ether_addr(hdr->addr1)) - rx->local->dot11MulticastReceivedFrameCount++; - else - ieee80211_led_rx(rx->local); + ieee80211_led_rx(rx->local); return RX_CONTINUE; } diff --git a/net/mac80211/spectmgmt.c b/net/mac80211/spectmgmt.c index 6ab009070084..efeba56c913b 100644 --- a/net/mac80211/spectmgmt.c +++ b/net/mac80211/spectmgmt.c @@ -22,7 +22,7 @@ #include "wme.h" int ieee80211_parse_ch_switch_ie(struct ieee80211_sub_if_data *sdata, - struct ieee802_11_elems *elems, bool beacon, + struct ieee802_11_elems *elems, enum ieee80211_band current_band, u32 sta_flags, u8 *bssid, struct ieee80211_csa_ie *csa_ie) @@ -91,19 +91,13 @@ int ieee80211_parse_ch_switch_ie(struct ieee80211_sub_if_data *sdata, return -EINVAL; } - if (!beacon && sec_chan_offs) { + if (sec_chan_offs) { secondary_channel_offset = sec_chan_offs->sec_chan_offs; - } else if (beacon && ht_oper) { - secondary_channel_offset = - ht_oper->ht_param & IEEE80211_HT_PARAM_CHA_SEC_OFFSET; } else if (!(sta_flags & IEEE80211_STA_DISABLE_HT)) { - /* If it's not a beacon, HT is enabled and the IE not present, - * it's 20 MHz, 802.11-2012 8.5.2.6: - * This element [the Secondary Channel Offset Element] is - * present when switching to a 40 MHz channel. It may be - * present when switching to a 20 MHz channel (in which - * case the secondary channel offset is set to SCN). - */ + /* If the secondary channel offset IE is not present, + * we can't know what's the post-CSA offset, so the + * best we can do is use 20MHz. + */ secondary_channel_offset = IEEE80211_HT_PARAM_CHA_SEC_NONE; } diff --git a/net/netfilter/ipset/ip_set_core.c b/net/netfilter/ipset/ip_set_core.c index 86f9d76b1464..d259da3ce67a 100644 --- a/net/netfilter/ipset/ip_set_core.c +++ b/net/netfilter/ipset/ip_set_core.c @@ -1863,6 +1863,12 @@ ip_set_sockfn_get(struct sock *sk, int optval, void __user *user, int *len) if (*op < IP_SET_OP_VERSION) { /* Check the version at the beginning of operations */ struct ip_set_req_version *req_version = data; + + if (*len < sizeof(struct ip_set_req_version)) { + ret = -EINVAL; + goto done; + } + if (req_version->version != IPSET_PROTOCOL) { ret = -EPROTO; goto done; diff --git a/net/netfilter/ipvs/ip_vs_xmit.c b/net/netfilter/ipvs/ip_vs_xmit.c index 437a3663ad03..bd90bf8107da 100644 --- a/net/netfilter/ipvs/ip_vs_xmit.c +++ b/net/netfilter/ipvs/ip_vs_xmit.c @@ -846,6 +846,8 @@ ip_vs_prepare_tunneled_skb(struct sk_buff *skb, int skb_af, new_skb = skb_realloc_headroom(skb, max_headroom); if (!new_skb) goto error; + if (skb->sk) + skb_set_owner_w(new_skb, skb->sk); consume_skb(skb); skb = new_skb; } diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c index 11ab4b078f3b..66e8425dbfe7 100644 --- a/net/netfilter/nf_tables_api.c +++ b/net/netfilter/nf_tables_api.c @@ -3484,13 +3484,8 @@ static void nft_chain_commit_update(struct nft_trans *trans) } } -/* Schedule objects for release via rcu to make sure no packets are accesing - * removed rules. - */ -static void nf_tables_commit_release_rcu(struct rcu_head *rt) +static void nf_tables_commit_release(struct nft_trans *trans) { - struct nft_trans *trans = container_of(rt, struct nft_trans, rcu_head); - switch (trans->msg_type) { case NFT_MSG_DELTABLE: nf_tables_table_destroy(&trans->ctx); @@ -3612,10 +3607,11 @@ static int nf_tables_commit(struct sk_buff *skb) } } + synchronize_rcu(); + list_for_each_entry_safe(trans, next, &net->nft.commit_list, list) { list_del(&trans->list); - trans->ctx.nla = NULL; - call_rcu(&trans->rcu_head, nf_tables_commit_release_rcu); + nf_tables_commit_release(trans); } nf_tables_gen_notify(net, skb, NFT_MSG_NEWGEN); @@ -3623,13 +3619,8 @@ static int nf_tables_commit(struct sk_buff *skb) return 0; } -/* Schedule objects for release via rcu to make sure no packets are accesing - * aborted rules. - */ -static void nf_tables_abort_release_rcu(struct rcu_head *rt) +static void nf_tables_abort_release(struct nft_trans *trans) { - struct nft_trans *trans = container_of(rt, struct nft_trans, rcu_head); - switch (trans->msg_type) { case NFT_MSG_NEWTABLE: nf_tables_table_destroy(&trans->ctx); @@ -3725,11 +3716,12 @@ static int nf_tables_abort(struct sk_buff *skb) } } + synchronize_rcu(); + list_for_each_entry_safe_reverse(trans, next, &net->nft.commit_list, list) { list_del(&trans->list); - trans->ctx.nla = NULL; - call_rcu(&trans->rcu_head, nf_tables_abort_release_rcu); + nf_tables_abort_release(trans); } return 0; diff --git a/net/netfilter/nfnetlink.c b/net/netfilter/nfnetlink.c index 6c5a915cfa75..13c2e17bbe27 100644 --- a/net/netfilter/nfnetlink.c +++ b/net/netfilter/nfnetlink.c @@ -47,6 +47,8 @@ static const int nfnl_group2type[NFNLGRP_MAX+1] = { [NFNLGRP_CONNTRACK_EXP_NEW] = NFNL_SUBSYS_CTNETLINK_EXP, [NFNLGRP_CONNTRACK_EXP_UPDATE] = NFNL_SUBSYS_CTNETLINK_EXP, [NFNLGRP_CONNTRACK_EXP_DESTROY] = NFNL_SUBSYS_CTNETLINK_EXP, + [NFNLGRP_NFTABLES] = NFNL_SUBSYS_NFTABLES, + [NFNLGRP_ACCT_QUOTA] = NFNL_SUBSYS_ACCT, }; void nfnl_lock(__u8 subsys_id) @@ -464,7 +466,12 @@ static void nfnetlink_rcv(struct sk_buff *skb) static int nfnetlink_bind(int group) { const struct nfnetlink_subsystem *ss; - int type = nfnl_group2type[group]; + int type; + + if (group <= NFNLGRP_NONE || group > NFNLGRP_MAX) + return -EINVAL; + + type = nfnl_group2type[group]; rcu_read_lock(); ss = nfnetlink_get_subsys(type); @@ -514,6 +521,9 @@ static int __init nfnetlink_init(void) { int i; + for (i = NFNLGRP_NONE + 1; i <= NFNLGRP_MAX; i++) + BUG_ON(nfnl_group2type[i] == NFNL_SUBSYS_NONE); + for (i=0; i<NFNL_SUBSYS_COUNT; i++) mutex_init(&table[i].mutex); diff --git a/net/netfilter/nft_compat.c b/net/netfilter/nft_compat.c index 9d6d6f60a80f..265e190f2218 100644 --- a/net/netfilter/nft_compat.c +++ b/net/netfilter/nft_compat.c @@ -21,45 +21,17 @@ #include <linux/netfilter_ipv6/ip6_tables.h> #include <net/netfilter/nf_tables.h> -static const struct { - const char *name; - u8 type; -} table_to_chaintype[] = { - { "filter", NFT_CHAIN_T_DEFAULT }, - { "raw", NFT_CHAIN_T_DEFAULT }, - { "security", NFT_CHAIN_T_DEFAULT }, - { "mangle", NFT_CHAIN_T_ROUTE }, - { "nat", NFT_CHAIN_T_NAT }, - { }, -}; - -static int nft_compat_table_to_chaintype(const char *table) -{ - int i; - - for (i = 0; table_to_chaintype[i].name != NULL; i++) { - if (strcmp(table_to_chaintype[i].name, table) == 0) - return table_to_chaintype[i].type; - } - - return -1; -} - static int nft_compat_chain_validate_dependency(const char *tablename, const struct nft_chain *chain) { - enum nft_chain_type type; const struct nft_base_chain *basechain; if (!tablename || !(chain->flags & NFT_BASE_CHAIN)) return 0; - type = nft_compat_table_to_chaintype(tablename); - if (type < 0) - return -EINVAL; - basechain = nft_base_chain(chain); - if (basechain->type->type != type) + if (strcmp(tablename, "nat") == 0 && + basechain->type->type != NFT_CHAIN_T_NAT) return -EINVAL; return 0; @@ -117,7 +89,7 @@ nft_target_set_tgchk_param(struct xt_tgchk_param *par, struct xt_target *target, void *info, union nft_entry *entry, u8 proto, bool inv) { - par->net = &init_net; + par->net = ctx->net; par->table = ctx->table->name; switch (ctx->afi->family) { case AF_INET: @@ -324,7 +296,7 @@ nft_match_set_mtchk_param(struct xt_mtchk_param *par, const struct nft_ctx *ctx, struct xt_match *match, void *info, union nft_entry *entry, u8 proto, bool inv) { - par->net = &init_net; + par->net = ctx->net; par->table = ctx->table->name; switch (ctx->afi->family) { case AF_INET: @@ -374,7 +346,7 @@ nft_match_init(const struct nft_ctx *ctx, const struct nft_expr *expr, union nft_entry e = {}; int ret; - ret = nft_compat_chain_validate_dependency(match->name, ctx->chain); + ret = nft_compat_chain_validate_dependency(match->table, ctx->chain); if (ret < 0) goto err; @@ -448,7 +420,7 @@ static int nft_match_validate(const struct nft_ctx *ctx, if (!(hook_mask & match->hooks)) return -EINVAL; - ret = nft_compat_chain_validate_dependency(match->name, + ret = nft_compat_chain_validate_dependency(match->table, ctx->chain); if (ret < 0) return ret; diff --git a/net/netlink/af_netlink.c b/net/netlink/af_netlink.c index f1de72de273e..0007b8180397 100644 --- a/net/netlink/af_netlink.c +++ b/net/netlink/af_netlink.c @@ -1440,7 +1440,7 @@ static void netlink_unbind(int group, long unsigned int groups, return; for (undo = 0; undo < group; undo++) - if (test_bit(group, &groups)) + if (test_bit(undo, &groups)) nlk->netlink_unbind(undo); } @@ -1492,7 +1492,7 @@ static int netlink_bind(struct socket *sock, struct sockaddr *addr, netlink_insert(sk, net, nladdr->nl_pid) : netlink_autobind(sock); if (err) { - netlink_unbind(nlk->ngroups - 1, groups, nlk); + netlink_unbind(nlk->ngroups, groups, nlk); return err; } } @@ -2509,6 +2509,7 @@ __netlink_kernel_create(struct net *net, int unit, struct module *module, nl_table[unit].module = module; if (cfg) { nl_table[unit].bind = cfg->bind; + nl_table[unit].unbind = cfg->unbind; nl_table[unit].flags = cfg->flags; if (cfg->compare) nl_table[unit].compare = cfg->compare; diff --git a/net/openvswitch/actions.c b/net/openvswitch/actions.c index 006886dbee36..8c4229b11c34 100644 --- a/net/openvswitch/actions.c +++ b/net/openvswitch/actions.c @@ -246,11 +246,11 @@ static void update_ipv6_checksum(struct sk_buff *skb, u8 l4_proto, { int transport_len = skb->len - skb_transport_offset(skb); - if (l4_proto == IPPROTO_TCP) { + if (l4_proto == NEXTHDR_TCP) { if (likely(transport_len >= sizeof(struct tcphdr))) inet_proto_csum_replace16(&tcp_hdr(skb)->check, skb, addr, new_addr, 1); - } else if (l4_proto == IPPROTO_UDP) { + } else if (l4_proto == NEXTHDR_UDP) { if (likely(transport_len >= sizeof(struct udphdr))) { struct udphdr *uh = udp_hdr(skb); @@ -261,6 +261,10 @@ static void update_ipv6_checksum(struct sk_buff *skb, u8 l4_proto, uh->check = CSUM_MANGLED_0; } } + } else if (l4_proto == NEXTHDR_ICMP) { + if (likely(transport_len >= sizeof(struct icmp6hdr))) + inet_proto_csum_replace16(&icmp6_hdr(skb)->icmp6_cksum, + skb, addr, new_addr, 1); } } @@ -722,8 +726,6 @@ static int do_execute_actions(struct datapath *dp, struct sk_buff *skb, case OVS_ACTION_ATTR_SAMPLE: err = sample(dp, skb, key, a); - if (unlikely(err)) /* skb already freed. */ - return err; break; } diff --git a/net/openvswitch/datapath.c b/net/openvswitch/datapath.c index e6d7255183eb..f9e556b56086 100644 --- a/net/openvswitch/datapath.c +++ b/net/openvswitch/datapath.c @@ -1265,7 +1265,7 @@ static size_t ovs_dp_cmd_msg_size(void) return msgsize; } -/* Called with ovs_mutex or RCU read lock. */ +/* Called with ovs_mutex. */ static int ovs_dp_cmd_fill_info(struct datapath *dp, struct sk_buff *skb, u32 portid, u32 seq, u32 flags, u8 cmd) { @@ -1555,7 +1555,7 @@ static int ovs_dp_cmd_get(struct sk_buff *skb, struct genl_info *info) if (!reply) return -ENOMEM; - rcu_read_lock(); + ovs_lock(); dp = lookup_datapath(sock_net(skb->sk), info->userhdr, info->attrs); if (IS_ERR(dp)) { err = PTR_ERR(dp); @@ -1564,12 +1564,12 @@ static int ovs_dp_cmd_get(struct sk_buff *skb, struct genl_info *info) err = ovs_dp_cmd_fill_info(dp, reply, info->snd_portid, info->snd_seq, 0, OVS_DP_CMD_NEW); BUG_ON(err < 0); - rcu_read_unlock(); + ovs_unlock(); return genlmsg_reply(reply, info); err_unlock_free: - rcu_read_unlock(); + ovs_unlock(); kfree_skb(reply); return err; } @@ -1581,8 +1581,8 @@ static int ovs_dp_cmd_dump(struct sk_buff *skb, struct netlink_callback *cb) int skip = cb->args[0]; int i = 0; - rcu_read_lock(); - list_for_each_entry_rcu(dp, &ovs_net->dps, list_node) { + ovs_lock(); + list_for_each_entry(dp, &ovs_net->dps, list_node) { if (i >= skip && ovs_dp_cmd_fill_info(dp, skb, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, NLM_F_MULTI, @@ -1590,7 +1590,7 @@ static int ovs_dp_cmd_dump(struct sk_buff *skb, struct netlink_callback *cb) break; i++; } - rcu_read_unlock(); + ovs_unlock(); cb->args[0] = i; diff --git a/net/openvswitch/flow_netlink.c b/net/openvswitch/flow_netlink.c index 939bcb32100f..089b195c064a 100644 --- a/net/openvswitch/flow_netlink.c +++ b/net/openvswitch/flow_netlink.c @@ -145,7 +145,7 @@ static bool match_validate(const struct sw_flow_match *match, if (match->key->eth.type == htons(ETH_P_ARP) || match->key->eth.type == htons(ETH_P_RARP)) { key_expected |= 1 << OVS_KEY_ATTR_ARP; - if (match->mask && (match->mask->key.eth.type == htons(0xffff))) + if (match->mask && (match->mask->key.tp.src == htons(0xff))) mask_allowed |= 1 << OVS_KEY_ATTR_ARP; } @@ -689,6 +689,13 @@ static int ovs_key_from_nlattrs(struct sw_flow_match *match, u64 attrs, ipv6_key->ipv6_frag, OVS_FRAG_TYPE_MAX); return -EINVAL; } + + if (!is_mask && ipv6_key->ipv6_label & htonl(0xFFF00000)) { + OVS_NLERR("IPv6 flow label %x is out of range (max=%x).\n", + ntohl(ipv6_key->ipv6_label), (1 << 20) - 1); + return -EINVAL; + } + SW_FLOW_KEY_PUT(match, ipv6.label, ipv6_key->ipv6_label, is_mask); SW_FLOW_KEY_PUT(match, ip.proto, diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c index 87d20f48ff06..07c04a841ba0 100644 --- a/net/packet/af_packet.c +++ b/net/packet/af_packet.c @@ -378,7 +378,7 @@ static void unregister_prot_hook(struct sock *sk, bool sync) __unregister_prot_hook(sk, sync); } -static inline __pure struct page *pgv_to_page(void *addr) +static inline struct page * __pure pgv_to_page(void *addr) { if (is_vmalloc_addr(addr)) return vmalloc_to_page(addr); diff --git a/net/sctp/auth.c b/net/sctp/auth.c index 0e8529113dc5..fb7976aee61c 100644 --- a/net/sctp/auth.c +++ b/net/sctp/auth.c @@ -862,8 +862,6 @@ int sctp_auth_set_key(struct sctp_endpoint *ep, list_add(&cur_key->key_list, sh_keys); cur_key->key = key; - sctp_auth_key_hold(key); - return 0; nomem: if (!replace) diff --git a/net/sctp/sm_make_chunk.c b/net/sctp/sm_make_chunk.c index ab734be8cb20..9f32741abb1c 100644 --- a/net/sctp/sm_make_chunk.c +++ b/net/sctp/sm_make_chunk.c @@ -2609,6 +2609,9 @@ do_addr_param: addr_param = param.v + sizeof(sctp_addip_param_t); af = sctp_get_af_specific(param_type2af(param.p->type)); + if (af == NULL) + break; + af->from_addr_param(&addr, addr_param, htons(asoc->peer.port), 0); diff --git a/net/sunrpc/Kconfig b/net/sunrpc/Kconfig index 0754d0f466d2..fb78117b896c 100644 --- a/net/sunrpc/Kconfig +++ b/net/sunrpc/Kconfig @@ -35,6 +35,7 @@ config RPCSEC_GSS_KRB5 config SUNRPC_DEBUG bool "RPC: Enable dprintk debugging" depends on SUNRPC && SYSCTL + select DEBUG_FS help This option enables a sysctl-based debugging interface that is be used by the 'rpcdebug' utility to turn on or off diff --git a/net/sunrpc/Makefile b/net/sunrpc/Makefile index e5a7a1cac8f3..15e6f6c23c5d 100644 --- a/net/sunrpc/Makefile +++ b/net/sunrpc/Makefile @@ -14,6 +14,7 @@ sunrpc-y := clnt.o xprt.o socklib.o xprtsock.o sched.o \ addr.o rpcb_clnt.o timer.o xdr.o \ sunrpc_syms.o cache.o rpc_pipe.o \ svc_xprt.o +sunrpc-$(CONFIG_SUNRPC_DEBUG) += debugfs.o sunrpc-$(CONFIG_SUNRPC_BACKCHANNEL) += backchannel_rqst.o bc_svc.o sunrpc-$(CONFIG_PROC_FS) += stats.o sunrpc-$(CONFIG_SYSCTL) += sysctl.o diff --git a/net/sunrpc/auth.c b/net/sunrpc/auth.c index 383eb919ac0b..47f38be4155f 100644 --- a/net/sunrpc/auth.c +++ b/net/sunrpc/auth.c @@ -16,7 +16,7 @@ #include <linux/sunrpc/gss_api.h> #include <linux/spinlock.h> -#ifdef RPC_DEBUG +#if IS_ENABLED(CONFIG_SUNRPC_DEBUG) # define RPCDBG_FACILITY RPCDBG_AUTH #endif @@ -646,7 +646,7 @@ rpcauth_init_cred(struct rpc_cred *cred, const struct auth_cred *acred, cred->cr_auth = auth; cred->cr_ops = ops; cred->cr_expire = jiffies; -#ifdef RPC_DEBUG +#if IS_ENABLED(CONFIG_SUNRPC_DEBUG) cred->cr_magic = RPCAUTH_CRED_MAGIC; #endif cred->cr_uid = acred->uid; diff --git a/net/sunrpc/auth_generic.c b/net/sunrpc/auth_generic.c index 6f6b829c9e8e..41248b1820c7 100644 --- a/net/sunrpc/auth_generic.c +++ b/net/sunrpc/auth_generic.c @@ -14,7 +14,7 @@ #include <linux/sunrpc/debug.h> #include <linux/sunrpc/sched.h> -#ifdef RPC_DEBUG +#if IS_ENABLED(CONFIG_SUNRPC_DEBUG) # define RPCDBG_FACILITY RPCDBG_AUTH #endif diff --git a/net/sunrpc/auth_gss/auth_gss.c b/net/sunrpc/auth_gss/auth_gss.c index afb292cd797d..dace13d7638e 100644 --- a/net/sunrpc/auth_gss/auth_gss.c +++ b/net/sunrpc/auth_gss/auth_gss.c @@ -66,7 +66,7 @@ static unsigned int gss_expired_cred_retry_delay = GSS_RETRY_EXPIRED; #define GSS_KEY_EXPIRE_TIMEO 240 static unsigned int gss_key_expire_timeo = GSS_KEY_EXPIRE_TIMEO; -#ifdef RPC_DEBUG +#if IS_ENABLED(CONFIG_SUNRPC_DEBUG) # define RPCDBG_FACILITY RPCDBG_AUTH #endif @@ -1353,6 +1353,7 @@ gss_stringify_acceptor(struct rpc_cred *cred) char *string = NULL; struct gss_cred *gss_cred = container_of(cred, struct gss_cred, gc_base); struct gss_cl_ctx *ctx; + unsigned int len; struct xdr_netobj *acceptor; rcu_read_lock(); @@ -1360,15 +1361,39 @@ gss_stringify_acceptor(struct rpc_cred *cred) if (!ctx) goto out; - acceptor = &ctx->gc_acceptor; + len = ctx->gc_acceptor.len; + rcu_read_unlock(); /* no point if there's no string */ - if (!acceptor->len) - goto out; - - string = kmalloc(acceptor->len + 1, GFP_KERNEL); + if (!len) + return NULL; +realloc: + string = kmalloc(len + 1, GFP_KERNEL); if (!string) + return NULL; + + rcu_read_lock(); + ctx = rcu_dereference(gss_cred->gc_ctx); + + /* did the ctx disappear or was it replaced by one with no acceptor? */ + if (!ctx || !ctx->gc_acceptor.len) { + kfree(string); + string = NULL; goto out; + } + + acceptor = &ctx->gc_acceptor; + + /* + * Did we find a new acceptor that's longer than the original? Allocate + * a longer buffer and try again. + */ + if (len < acceptor->len) { + len = acceptor->len; + rcu_read_unlock(); + kfree(string); + goto realloc; + } memcpy(string, acceptor->data, acceptor->len); string[acceptor->len] = '\0'; diff --git a/net/sunrpc/auth_gss/gss_generic_token.c b/net/sunrpc/auth_gss/gss_generic_token.c index c586e92bcf76..254defe446a7 100644 --- a/net/sunrpc/auth_gss/gss_generic_token.c +++ b/net/sunrpc/auth_gss/gss_generic_token.c @@ -38,7 +38,7 @@ #include <linux/sunrpc/gss_asn1.h> -#ifdef RPC_DEBUG +#if IS_ENABLED(CONFIG_SUNRPC_DEBUG) # define RPCDBG_FACILITY RPCDBG_AUTH #endif diff --git a/net/sunrpc/auth_gss/gss_krb5_crypto.c b/net/sunrpc/auth_gss/gss_krb5_crypto.c index f5ed9f6ece06..b5408e8a37f2 100644 --- a/net/sunrpc/auth_gss/gss_krb5_crypto.c +++ b/net/sunrpc/auth_gss/gss_krb5_crypto.c @@ -45,7 +45,7 @@ #include <linux/sunrpc/gss_krb5.h> #include <linux/sunrpc/xdr.h> -#ifdef RPC_DEBUG +#if IS_ENABLED(CONFIG_SUNRPC_DEBUG) # define RPCDBG_FACILITY RPCDBG_AUTH #endif diff --git a/net/sunrpc/auth_gss/gss_krb5_keys.c b/net/sunrpc/auth_gss/gss_krb5_keys.c index 24589bd2a4b6..234fa8d0fd9b 100644 --- a/net/sunrpc/auth_gss/gss_krb5_keys.c +++ b/net/sunrpc/auth_gss/gss_krb5_keys.c @@ -61,7 +61,7 @@ #include <linux/sunrpc/xdr.h> #include <linux/lcm.h> -#ifdef RPC_DEBUG +#if IS_ENABLED(CONFIG_SUNRPC_DEBUG) # define RPCDBG_FACILITY RPCDBG_AUTH #endif diff --git a/net/sunrpc/auth_gss/gss_krb5_mech.c b/net/sunrpc/auth_gss/gss_krb5_mech.c index 0d3c158ef8fa..28db442a0034 100644 --- a/net/sunrpc/auth_gss/gss_krb5_mech.c +++ b/net/sunrpc/auth_gss/gss_krb5_mech.c @@ -45,7 +45,7 @@ #include <linux/crypto.h> #include <linux/sunrpc/gss_krb5_enctypes.h> -#ifdef RPC_DEBUG +#if IS_ENABLED(CONFIG_SUNRPC_DEBUG) # define RPCDBG_FACILITY RPCDBG_AUTH #endif diff --git a/net/sunrpc/auth_gss/gss_krb5_seal.c b/net/sunrpc/auth_gss/gss_krb5_seal.c index 42768e5c3994..1d74d653e6c0 100644 --- a/net/sunrpc/auth_gss/gss_krb5_seal.c +++ b/net/sunrpc/auth_gss/gss_krb5_seal.c @@ -64,7 +64,7 @@ #include <linux/random.h> #include <linux/crypto.h> -#ifdef RPC_DEBUG +#if IS_ENABLED(CONFIG_SUNRPC_DEBUG) # define RPCDBG_FACILITY RPCDBG_AUTH #endif diff --git a/net/sunrpc/auth_gss/gss_krb5_seqnum.c b/net/sunrpc/auth_gss/gss_krb5_seqnum.c index 62ac90c62cb1..20d55c793eb6 100644 --- a/net/sunrpc/auth_gss/gss_krb5_seqnum.c +++ b/net/sunrpc/auth_gss/gss_krb5_seqnum.c @@ -35,7 +35,7 @@ #include <linux/sunrpc/gss_krb5.h> #include <linux/crypto.h> -#ifdef RPC_DEBUG +#if IS_ENABLED(CONFIG_SUNRPC_DEBUG) # define RPCDBG_FACILITY RPCDBG_AUTH #endif diff --git a/net/sunrpc/auth_gss/gss_krb5_unseal.c b/net/sunrpc/auth_gss/gss_krb5_unseal.c index 6c981ddc19f8..dcf9515d9aef 100644 --- a/net/sunrpc/auth_gss/gss_krb5_unseal.c +++ b/net/sunrpc/auth_gss/gss_krb5_unseal.c @@ -62,7 +62,7 @@ #include <linux/sunrpc/gss_krb5.h> #include <linux/crypto.h> -#ifdef RPC_DEBUG +#if IS_ENABLED(CONFIG_SUNRPC_DEBUG) # define RPCDBG_FACILITY RPCDBG_AUTH #endif diff --git a/net/sunrpc/auth_gss/gss_krb5_wrap.c b/net/sunrpc/auth_gss/gss_krb5_wrap.c index 4b614c604fe0..ca7e92a32f84 100644 --- a/net/sunrpc/auth_gss/gss_krb5_wrap.c +++ b/net/sunrpc/auth_gss/gss_krb5_wrap.c @@ -35,7 +35,7 @@ #include <linux/pagemap.h> #include <linux/crypto.h> -#ifdef RPC_DEBUG +#if IS_ENABLED(CONFIG_SUNRPC_DEBUG) # define RPCDBG_FACILITY RPCDBG_AUTH #endif diff --git a/net/sunrpc/auth_gss/gss_mech_switch.c b/net/sunrpc/auth_gss/gss_mech_switch.c index 92d5ab99fbf3..7063d856a598 100644 --- a/net/sunrpc/auth_gss/gss_mech_switch.c +++ b/net/sunrpc/auth_gss/gss_mech_switch.c @@ -46,7 +46,7 @@ #include <linux/sunrpc/gss_api.h> #include <linux/sunrpc/clnt.h> -#ifdef RPC_DEBUG +#if IS_ENABLED(CONFIG_SUNRPC_DEBUG) # define RPCDBG_FACILITY RPCDBG_AUTH #endif diff --git a/net/sunrpc/auth_gss/gss_rpc_xdr.h b/net/sunrpc/auth_gss/gss_rpc_xdr.h index 685a688f3d8a..9d88c6239f01 100644 --- a/net/sunrpc/auth_gss/gss_rpc_xdr.h +++ b/net/sunrpc/auth_gss/gss_rpc_xdr.h @@ -25,7 +25,7 @@ #include <linux/sunrpc/clnt.h> #include <linux/sunrpc/xprtsock.h> -#ifdef RPC_DEBUG +#if IS_ENABLED(CONFIG_SUNRPC_DEBUG) # define RPCDBG_FACILITY RPCDBG_AUTH #endif diff --git a/net/sunrpc/auth_gss/svcauth_gss.c b/net/sunrpc/auth_gss/svcauth_gss.c index c548ab213f76..de856ddf5fed 100644 --- a/net/sunrpc/auth_gss/svcauth_gss.c +++ b/net/sunrpc/auth_gss/svcauth_gss.c @@ -51,7 +51,7 @@ #include "gss_rpc_upcall.h" -#ifdef RPC_DEBUG +#if IS_ENABLED(CONFIG_SUNRPC_DEBUG) # define RPCDBG_FACILITY RPCDBG_AUTH #endif diff --git a/net/sunrpc/auth_null.c b/net/sunrpc/auth_null.c index 712c123e04e9..c2a2b584a056 100644 --- a/net/sunrpc/auth_null.c +++ b/net/sunrpc/auth_null.c @@ -10,7 +10,7 @@ #include <linux/module.h> #include <linux/sunrpc/clnt.h> -#ifdef RPC_DEBUG +#if IS_ENABLED(CONFIG_SUNRPC_DEBUG) # define RPCDBG_FACILITY RPCDBG_AUTH #endif @@ -138,7 +138,7 @@ struct rpc_cred null_cred = { .cr_ops = &null_credops, .cr_count = ATOMIC_INIT(1), .cr_flags = 1UL << RPCAUTH_CRED_UPTODATE, -#ifdef RPC_DEBUG +#if IS_ENABLED(CONFIG_SUNRPC_DEBUG) .cr_magic = RPCAUTH_CRED_MAGIC, #endif }; diff --git a/net/sunrpc/auth_unix.c b/net/sunrpc/auth_unix.c index d5d692366294..4feda2d0a833 100644 --- a/net/sunrpc/auth_unix.c +++ b/net/sunrpc/auth_unix.c @@ -25,7 +25,7 @@ struct unx_cred { #define UNX_WRITESLACK (21 + (UNX_MAXNODENAME >> 2)) -#ifdef RPC_DEBUG +#if IS_ENABLED(CONFIG_SUNRPC_DEBUG) # define RPCDBG_FACILITY RPCDBG_AUTH #endif diff --git a/net/sunrpc/backchannel_rqst.c b/net/sunrpc/backchannel_rqst.c index 9761a0da964d..651f49ab601f 100644 --- a/net/sunrpc/backchannel_rqst.c +++ b/net/sunrpc/backchannel_rqst.c @@ -27,7 +27,7 @@ SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE. #include <linux/export.h> #include <linux/sunrpc/bc_xprt.h> -#ifdef RPC_DEBUG +#if IS_ENABLED(CONFIG_SUNRPC_DEBUG) #define RPCDBG_FACILITY RPCDBG_TRANS #endif diff --git a/net/sunrpc/clnt.c b/net/sunrpc/clnt.c index 9acd6ce88db7..05da12a33945 100644 --- a/net/sunrpc/clnt.c +++ b/net/sunrpc/clnt.c @@ -42,7 +42,7 @@ #include "sunrpc.h" #include "netns.h" -#ifdef RPC_DEBUG +#if IS_ENABLED(CONFIG_SUNRPC_DEBUG) # define RPCDBG_FACILITY RPCDBG_CALL #endif @@ -305,6 +305,10 @@ static int rpc_client_register(struct rpc_clnt *clnt, struct super_block *pipefs_sb; int err; + err = rpc_clnt_debugfs_register(clnt); + if (err) + return err; + pipefs_sb = rpc_get_sb_net(net); if (pipefs_sb) { err = rpc_setup_pipedir(pipefs_sb, clnt); @@ -331,6 +335,7 @@ err_auth: out: if (pipefs_sb) rpc_put_sb_net(net); + rpc_clnt_debugfs_unregister(clnt); return err; } @@ -670,6 +675,7 @@ int rpc_switch_client_transport(struct rpc_clnt *clnt, rpc_unregister_client(clnt); __rpc_clnt_remove_pipedir(clnt); + rpc_clnt_debugfs_unregister(clnt); /* * A new transport was created. "clnt" therefore @@ -771,6 +777,7 @@ rpc_free_client(struct rpc_clnt *clnt) rcu_dereference(clnt->cl_xprt)->servername); if (clnt->cl_parent != clnt) parent = clnt->cl_parent; + rpc_clnt_debugfs_unregister(clnt); rpc_clnt_remove_pipedir(clnt); rpc_unregister_client(clnt); rpc_free_iostats(clnt->cl_metrics); @@ -1396,8 +1403,9 @@ rpc_restart_call(struct rpc_task *task) } EXPORT_SYMBOL_GPL(rpc_restart_call); -#ifdef RPC_DEBUG -static const char *rpc_proc_name(const struct rpc_task *task) +#if IS_ENABLED(CONFIG_SUNRPC_DEBUG) +const char +*rpc_proc_name(const struct rpc_task *task) { const struct rpc_procinfo *proc = task->tk_msg.rpc_proc; @@ -2421,7 +2429,7 @@ struct rpc_task *rpc_call_null(struct rpc_clnt *clnt, struct rpc_cred *cred, int } EXPORT_SYMBOL_GPL(rpc_call_null); -#ifdef RPC_DEBUG +#if IS_ENABLED(CONFIG_SUNRPC_DEBUG) static void rpc_show_header(void) { printk(KERN_INFO "-pid- flgs status -client- --rqstp- " diff --git a/net/sunrpc/debugfs.c b/net/sunrpc/debugfs.c new file mode 100644 index 000000000000..e811f390f9f6 --- /dev/null +++ b/net/sunrpc/debugfs.c @@ -0,0 +1,292 @@ +/** + * debugfs interface for sunrpc + * + * (c) 2014 Jeff Layton <jlayton@primarydata.com> + */ + +#include <linux/debugfs.h> +#include <linux/sunrpc/sched.h> +#include <linux/sunrpc/clnt.h> +#include "netns.h" + +static struct dentry *topdir; +static struct dentry *rpc_clnt_dir; +static struct dentry *rpc_xprt_dir; + +struct rpc_clnt_iter { + struct rpc_clnt *clnt; + loff_t pos; +}; + +static int +tasks_show(struct seq_file *f, void *v) +{ + u32 xid = 0; + struct rpc_task *task = v; + struct rpc_clnt *clnt = task->tk_client; + const char *rpc_waitq = "none"; + + if (RPC_IS_QUEUED(task)) + rpc_waitq = rpc_qname(task->tk_waitqueue); + + if (task->tk_rqstp) + xid = be32_to_cpu(task->tk_rqstp->rq_xid); + + seq_printf(f, "%5u %04x %6d 0x%x 0x%x %8ld %ps %sv%u %s a:%ps q:%s\n", + task->tk_pid, task->tk_flags, task->tk_status, + clnt->cl_clid, xid, task->tk_timeout, task->tk_ops, + clnt->cl_program->name, clnt->cl_vers, rpc_proc_name(task), + task->tk_action, rpc_waitq); + return 0; +} + +static void * +tasks_start(struct seq_file *f, loff_t *ppos) + __acquires(&clnt->cl_lock) +{ + struct rpc_clnt_iter *iter = f->private; + loff_t pos = *ppos; + struct rpc_clnt *clnt = iter->clnt; + struct rpc_task *task; + + iter->pos = pos + 1; + spin_lock(&clnt->cl_lock); + list_for_each_entry(task, &clnt->cl_tasks, tk_task) + if (pos-- == 0) + return task; + return NULL; +} + +static void * +tasks_next(struct seq_file *f, void *v, loff_t *pos) +{ + struct rpc_clnt_iter *iter = f->private; + struct rpc_clnt *clnt = iter->clnt; + struct rpc_task *task = v; + struct list_head *next = task->tk_task.next; + + ++iter->pos; + ++*pos; + + /* If there's another task on list, return it */ + if (next == &clnt->cl_tasks) + return NULL; + return list_entry(next, struct rpc_task, tk_task); +} + +static void +tasks_stop(struct seq_file *f, void *v) + __releases(&clnt->cl_lock) +{ + struct rpc_clnt_iter *iter = f->private; + struct rpc_clnt *clnt = iter->clnt; + + spin_unlock(&clnt->cl_lock); +} + +static const struct seq_operations tasks_seq_operations = { + .start = tasks_start, + .next = tasks_next, + .stop = tasks_stop, + .show = tasks_show, +}; + +static int tasks_open(struct inode *inode, struct file *filp) +{ + int ret = seq_open_private(filp, &tasks_seq_operations, + sizeof(struct rpc_clnt_iter)); + + if (!ret) { + struct seq_file *seq = filp->private_data; + struct rpc_clnt_iter *iter = seq->private; + + iter->clnt = inode->i_private; + + if (!atomic_inc_not_zero(&iter->clnt->cl_count)) { + seq_release_private(inode, filp); + ret = -EINVAL; + } + } + + return ret; +} + +static int +tasks_release(struct inode *inode, struct file *filp) +{ + struct seq_file *seq = filp->private_data; + struct rpc_clnt_iter *iter = seq->private; + + rpc_release_client(iter->clnt); + return seq_release_private(inode, filp); +} + +static const struct file_operations tasks_fops = { + .owner = THIS_MODULE, + .open = tasks_open, + .read = seq_read, + .llseek = seq_lseek, + .release = tasks_release, +}; + +int +rpc_clnt_debugfs_register(struct rpc_clnt *clnt) +{ + int len, err; + char name[24]; /* enough for "../../rpc_xprt/ + 8 hex digits + NULL */ + + /* Already registered? */ + if (clnt->cl_debugfs) + return 0; + + len = snprintf(name, sizeof(name), "%x", clnt->cl_clid); + if (len >= sizeof(name)) + return -EINVAL; + + /* make the per-client dir */ + clnt->cl_debugfs = debugfs_create_dir(name, rpc_clnt_dir); + if (!clnt->cl_debugfs) + return -ENOMEM; + + /* make tasks file */ + err = -ENOMEM; + if (!debugfs_create_file("tasks", S_IFREG | S_IRUSR, clnt->cl_debugfs, + clnt, &tasks_fops)) + goto out_err; + + err = -EINVAL; + rcu_read_lock(); + len = snprintf(name, sizeof(name), "../../rpc_xprt/%s", + rcu_dereference(clnt->cl_xprt)->debugfs->d_name.name); + rcu_read_unlock(); + if (len >= sizeof(name)) + goto out_err; + + err = -ENOMEM; + if (!debugfs_create_symlink("xprt", clnt->cl_debugfs, name)) + goto out_err; + + return 0; +out_err: + debugfs_remove_recursive(clnt->cl_debugfs); + clnt->cl_debugfs = NULL; + return err; +} + +void +rpc_clnt_debugfs_unregister(struct rpc_clnt *clnt) +{ + debugfs_remove_recursive(clnt->cl_debugfs); + clnt->cl_debugfs = NULL; +} + +static int +xprt_info_show(struct seq_file *f, void *v) +{ + struct rpc_xprt *xprt = f->private; + + seq_printf(f, "netid: %s\n", xprt->address_strings[RPC_DISPLAY_NETID]); + seq_printf(f, "addr: %s\n", xprt->address_strings[RPC_DISPLAY_ADDR]); + seq_printf(f, "port: %s\n", xprt->address_strings[RPC_DISPLAY_PORT]); + seq_printf(f, "state: 0x%lx\n", xprt->state); + return 0; +} + +static int +xprt_info_open(struct inode *inode, struct file *filp) +{ + int ret; + struct rpc_xprt *xprt = inode->i_private; + + ret = single_open(filp, xprt_info_show, xprt); + + if (!ret) { + if (!xprt_get(xprt)) { + single_release(inode, filp); + ret = -EINVAL; + } + } + return ret; +} + +static int +xprt_info_release(struct inode *inode, struct file *filp) +{ + struct rpc_xprt *xprt = inode->i_private; + + xprt_put(xprt); + return single_release(inode, filp); +} + +static const struct file_operations xprt_info_fops = { + .owner = THIS_MODULE, + .open = xprt_info_open, + .read = seq_read, + .llseek = seq_lseek, + .release = xprt_info_release, +}; + +int +rpc_xprt_debugfs_register(struct rpc_xprt *xprt) +{ + int len, id; + static atomic_t cur_id; + char name[9]; /* 8 hex digits + NULL term */ + + id = (unsigned int)atomic_inc_return(&cur_id); + + len = snprintf(name, sizeof(name), "%x", id); + if (len >= sizeof(name)) + return -EINVAL; + + /* make the per-client dir */ + xprt->debugfs = debugfs_create_dir(name, rpc_xprt_dir); + if (!xprt->debugfs) + return -ENOMEM; + + /* make tasks file */ + if (!debugfs_create_file("info", S_IFREG | S_IRUSR, xprt->debugfs, + xprt, &xprt_info_fops)) { + debugfs_remove_recursive(xprt->debugfs); + xprt->debugfs = NULL; + return -ENOMEM; + } + + return 0; +} + +void +rpc_xprt_debugfs_unregister(struct rpc_xprt *xprt) +{ + debugfs_remove_recursive(xprt->debugfs); + xprt->debugfs = NULL; +} + +void __exit +sunrpc_debugfs_exit(void) +{ + debugfs_remove_recursive(topdir); +} + +int __init +sunrpc_debugfs_init(void) +{ + topdir = debugfs_create_dir("sunrpc", NULL); + if (!topdir) + goto out; + + rpc_clnt_dir = debugfs_create_dir("rpc_clnt", topdir); + if (!rpc_clnt_dir) + goto out_remove; + + rpc_xprt_dir = debugfs_create_dir("rpc_xprt", topdir); + if (!rpc_xprt_dir) + goto out_remove; + + return 0; +out_remove: + debugfs_remove_recursive(topdir); + topdir = NULL; +out: + return -ENOMEM; +} diff --git a/net/sunrpc/rpcb_clnt.c b/net/sunrpc/rpcb_clnt.c index 1891a1022c17..05202012bcfc 100644 --- a/net/sunrpc/rpcb_clnt.c +++ b/net/sunrpc/rpcb_clnt.c @@ -32,7 +32,7 @@ #include "netns.h" -#ifdef RPC_DEBUG +#if IS_ENABLED(CONFIG_SUNRPC_DEBUG) # define RPCDBG_FACILITY RPCDBG_BIND #endif diff --git a/net/sunrpc/sched.c b/net/sunrpc/sched.c index fe3441abdbe5..d20f2329eea3 100644 --- a/net/sunrpc/sched.c +++ b/net/sunrpc/sched.c @@ -24,7 +24,7 @@ #include "sunrpc.h" -#ifdef RPC_DEBUG +#if IS_ENABLED(CONFIG_SUNRPC_DEBUG) #define RPCDBG_FACILITY RPCDBG_SCHED #endif @@ -258,7 +258,7 @@ static int rpc_wait_bit_killable(struct wait_bit_key *key) return 0; } -#if defined(RPC_DEBUG) || defined(RPC_TRACEPOINTS) +#if IS_ENABLED(CONFIG_SUNRPC_DEBUG) || IS_ENABLED(CONFIG_TRACEPOINTS) static void rpc_task_set_debuginfo(struct rpc_task *task) { static atomic_t rpc_pid; diff --git a/net/sunrpc/stats.c b/net/sunrpc/stats.c index 54530490944e..9711a155bc50 100644 --- a/net/sunrpc/stats.c +++ b/net/sunrpc/stats.c @@ -116,7 +116,15 @@ EXPORT_SYMBOL_GPL(svc_seq_show); */ struct rpc_iostats *rpc_alloc_iostats(struct rpc_clnt *clnt) { - return kcalloc(clnt->cl_maxproc, sizeof(struct rpc_iostats), GFP_KERNEL); + struct rpc_iostats *stats; + int i; + + stats = kcalloc(clnt->cl_maxproc, sizeof(*stats), GFP_KERNEL); + if (stats) { + for (i = 0; i < clnt->cl_maxproc; i++) + spin_lock_init(&stats[i].om_lock); + } + return stats; } EXPORT_SYMBOL_GPL(rpc_alloc_iostats); @@ -135,20 +143,21 @@ EXPORT_SYMBOL_GPL(rpc_free_iostats); * rpc_count_iostats - tally up per-task stats * @task: completed rpc_task * @stats: array of stat structures - * - * Relies on the caller for serialization. */ void rpc_count_iostats(const struct rpc_task *task, struct rpc_iostats *stats) { struct rpc_rqst *req = task->tk_rqstp; struct rpc_iostats *op_metrics; - ktime_t delta; + ktime_t delta, now; if (!stats || !req) return; + now = ktime_get(); op_metrics = &stats[task->tk_msg.rpc_proc->p_statidx]; + spin_lock(&op_metrics->om_lock); + op_metrics->om_ops++; op_metrics->om_ntrans += req->rq_ntrans; op_metrics->om_timeouts += task->tk_timeouts; @@ -161,8 +170,10 @@ void rpc_count_iostats(const struct rpc_task *task, struct rpc_iostats *stats) op_metrics->om_rtt = ktime_add(op_metrics->om_rtt, req->rq_rtt); - delta = ktime_sub(ktime_get(), task->tk_start); + delta = ktime_sub(now, task->tk_start); op_metrics->om_execute = ktime_add(op_metrics->om_execute, delta); + + spin_unlock(&op_metrics->om_lock); } EXPORT_SYMBOL_GPL(rpc_count_iostats); diff --git a/net/sunrpc/sunrpc_syms.c b/net/sunrpc/sunrpc_syms.c index cd30120de9e4..e37fbed87956 100644 --- a/net/sunrpc/sunrpc_syms.c +++ b/net/sunrpc/sunrpc_syms.c @@ -97,13 +97,20 @@ init_sunrpc(void) err = register_rpc_pipefs(); if (err) goto out4; -#ifdef RPC_DEBUG + + err = sunrpc_debugfs_init(); + if (err) + goto out5; + +#if IS_ENABLED(CONFIG_SUNRPC_DEBUG) rpc_register_sysctl(); #endif svc_init_xprt_sock(); /* svc sock transport */ init_socket_xprt(); /* clnt sock transport */ return 0; +out5: + unregister_rpc_pipefs(); out4: unregister_pernet_subsys(&sunrpc_net_ops); out3: @@ -120,10 +127,11 @@ cleanup_sunrpc(void) rpcauth_remove_module(); cleanup_socket_xprt(); svc_cleanup_xprt_sock(); + sunrpc_debugfs_exit(); unregister_rpc_pipefs(); rpc_destroy_mempool(); unregister_pernet_subsys(&sunrpc_net_ops); -#ifdef RPC_DEBUG +#if IS_ENABLED(CONFIG_SUNRPC_DEBUG) rpc_unregister_sysctl(); #endif rcu_barrier(); /* Wait for completion of call_rcu()'s */ diff --git a/net/sunrpc/svc.c b/net/sunrpc/svc.c index ca8a7958f4e6..2783fd80c229 100644 --- a/net/sunrpc/svc.c +++ b/net/sunrpc/svc.c @@ -28,6 +28,8 @@ #include <linux/sunrpc/clnt.h> #include <linux/sunrpc/bc_xprt.h> +#include <trace/events/sunrpc.h> + #define RPCDBG_FACILITY RPCDBG_SVCDSP static void svc_unregister(const struct svc_serv *serv, struct net *net); @@ -1040,7 +1042,7 @@ static void svc_unregister(const struct svc_serv *serv, struct net *net) /* * dprintk the given error with the address of the client that caused it. */ -#ifdef RPC_DEBUG +#if IS_ENABLED(CONFIG_SUNRPC_DEBUG) static __printf(2, 3) void svc_printk(struct svc_rqst *rqstp, const char *fmt, ...) { @@ -1314,24 +1316,25 @@ svc_process(struct svc_rqst *rqstp) rqstp->rq_res.tail[0].iov_base = NULL; rqstp->rq_res.tail[0].iov_len = 0; - rqstp->rq_xid = svc_getu32(argv); - dir = svc_getnl(argv); if (dir != 0) { /* direction != CALL */ svc_printk(rqstp, "bad direction %d, dropping request\n", dir); serv->sv_stats->rpcbadfmt++; - svc_drop(rqstp); - return 0; + goto out_drop; } /* Returns 1 for send, 0 for drop */ - if (svc_process_common(rqstp, argv, resv)) - return svc_send(rqstp); - else { - svc_drop(rqstp); - return 0; + if (likely(svc_process_common(rqstp, argv, resv))) { + int ret = svc_send(rqstp); + + trace_svc_process(rqstp, ret); + return ret; } +out_drop: + trace_svc_process(rqstp, 0); + svc_drop(rqstp); + return 0; } #if defined(CONFIG_SUNRPC_BACKCHANNEL) diff --git a/net/sunrpc/svc_xprt.c b/net/sunrpc/svc_xprt.c index c179ca2a5aa4..bbb3b044b877 100644 --- a/net/sunrpc/svc_xprt.c +++ b/net/sunrpc/svc_xprt.c @@ -15,6 +15,7 @@ #include <linux/sunrpc/svcsock.h> #include <linux/sunrpc/xprt.h> #include <linux/module.h> +#include <trace/events/sunrpc.h> #define RPCDBG_FACILITY RPCDBG_SVCXPRT @@ -773,35 +774,43 @@ int svc_recv(struct svc_rqst *rqstp, long timeout) err = svc_alloc_arg(rqstp); if (err) - return err; + goto out; try_to_freeze(); cond_resched(); + err = -EINTR; if (signalled() || kthread_should_stop()) - return -EINTR; + goto out; xprt = svc_get_next_xprt(rqstp, timeout); - if (IS_ERR(xprt)) - return PTR_ERR(xprt); + if (IS_ERR(xprt)) { + err = PTR_ERR(xprt); + goto out; + } len = svc_handle_xprt(rqstp, xprt); /* No data, incomplete (TCP) read, or accept() */ + err = -EAGAIN; if (len <= 0) - goto out; + goto out_release; clear_bit(XPT_OLD, &xprt->xpt_flags); rqstp->rq_secure = xprt->xpt_ops->xpo_secure_port(rqstp); rqstp->rq_chandle.defer = svc_defer; + rqstp->rq_xid = svc_getu32(&rqstp->rq_arg.head[0]); if (serv->sv_stats) serv->sv_stats->netcnt++; + trace_svc_recv(rqstp, len); return len; -out: +out_release: rqstp->rq_res.len = 0; svc_xprt_release(rqstp); - return -EAGAIN; +out: + trace_svc_recv(rqstp, err); + return err; } EXPORT_SYMBOL_GPL(svc_recv); @@ -821,12 +830,12 @@ EXPORT_SYMBOL_GPL(svc_drop); int svc_send(struct svc_rqst *rqstp) { struct svc_xprt *xprt; - int len; + int len = -EFAULT; struct xdr_buf *xb; xprt = rqstp->rq_xprt; if (!xprt) - return -EFAULT; + goto out; /* release the receive skb before sending the reply */ rqstp->rq_xprt->xpt_ops->xpo_release_rqst(rqstp); @@ -849,7 +858,9 @@ int svc_send(struct svc_rqst *rqstp) svc_xprt_release(rqstp); if (len == -ECONNREFUSED || len == -ENOTCONN || len == -EAGAIN) - return 0; + len = 0; +out: + trace_svc_send(rqstp, len); return len; } diff --git a/net/sunrpc/svcsock.c b/net/sunrpc/svcsock.c index 3f959c681885..f9c052d508f0 100644 --- a/net/sunrpc/svcsock.c +++ b/net/sunrpc/svcsock.c @@ -1019,17 +1019,12 @@ static int receive_cb_reply(struct svc_sock *svsk, struct svc_rqst *rqstp) xid = *p++; calldir = *p; - if (bc_xprt) - req = xprt_lookup_rqst(bc_xprt, xid); - - if (!req) { - printk(KERN_NOTICE - "%s: Got unrecognized reply: " - "calldir 0x%x xpt_bc_xprt %p xid %08x\n", - __func__, ntohl(calldir), - bc_xprt, ntohl(xid)); + if (!bc_xprt) return -EAGAIN; - } + spin_lock_bh(&bc_xprt->transport_lock); + req = xprt_lookup_rqst(bc_xprt, xid); + if (!req) + goto unlock_notfound; memcpy(&req->rq_private_buf, &req->rq_rcv_buf, sizeof(struct xdr_buf)); /* @@ -1040,11 +1035,21 @@ static int receive_cb_reply(struct svc_sock *svsk, struct svc_rqst *rqstp) dst = &req->rq_private_buf.head[0]; src = &rqstp->rq_arg.head[0]; if (dst->iov_len < src->iov_len) - return -EAGAIN; /* whatever; just giving up. */ + goto unlock_eagain; /* whatever; just giving up. */ memcpy(dst->iov_base, src->iov_base, src->iov_len); xprt_complete_rqst(req->rq_task, rqstp->rq_arg.len); rqstp->rq_arg.len = 0; + spin_unlock_bh(&bc_xprt->transport_lock); return 0; +unlock_notfound: + printk(KERN_NOTICE + "%s: Got unrecognized reply: " + "calldir 0x%x xpt_bc_xprt %p xid %08x\n", + __func__, ntohl(calldir), + bc_xprt, ntohl(xid)); +unlock_eagain: + spin_unlock_bh(&bc_xprt->transport_lock); + return -EAGAIN; } static int copy_pages_to_kvecs(struct kvec *vec, struct page **pages, int len) diff --git a/net/sunrpc/sysctl.c b/net/sunrpc/sysctl.c index c99c58e2ee66..887f0183b4c6 100644 --- a/net/sunrpc/sysctl.c +++ b/net/sunrpc/sysctl.c @@ -37,7 +37,7 @@ EXPORT_SYMBOL_GPL(nfsd_debug); unsigned int nlm_debug; EXPORT_SYMBOL_GPL(nlm_debug); -#ifdef RPC_DEBUG +#if IS_ENABLED(CONFIG_SUNRPC_DEBUG) static struct ctl_table_header *sunrpc_table_header; static struct ctl_table sunrpc_table[]; diff --git a/net/sunrpc/xprt.c b/net/sunrpc/xprt.c index 56e4e150e80e..ebbefad21a37 100644 --- a/net/sunrpc/xprt.c +++ b/net/sunrpc/xprt.c @@ -49,13 +49,15 @@ #include <linux/sunrpc/metrics.h> #include <linux/sunrpc/bc_xprt.h> +#include <trace/events/sunrpc.h> + #include "sunrpc.h" /* * Local variables */ -#ifdef RPC_DEBUG +#if IS_ENABLED(CONFIG_SUNRPC_DEBUG) # define RPCDBG_FACILITY RPCDBG_XPRT #endif @@ -772,11 +774,14 @@ struct rpc_rqst *xprt_lookup_rqst(struct rpc_xprt *xprt, __be32 xid) struct rpc_rqst *entry; list_for_each_entry(entry, &xprt->recv, rq_list) - if (entry->rq_xid == xid) + if (entry->rq_xid == xid) { + trace_xprt_lookup_rqst(xprt, xid, 0); return entry; + } dprintk("RPC: xprt_lookup_rqst did not find xid %08x\n", ntohl(xid)); + trace_xprt_lookup_rqst(xprt, xid, -ENOENT); xprt->stat.bad_xids++; return NULL; } @@ -810,6 +815,7 @@ void xprt_complete_rqst(struct rpc_task *task, int copied) dprintk("RPC: %5u xid %08x complete (%d bytes received)\n", task->tk_pid, ntohl(req->rq_xid), copied); + trace_xprt_complete_rqst(xprt, req->rq_xid, copied); xprt->stat.recvs++; req->rq_rtt = ktime_sub(ktime_get(), req->rq_xtime); @@ -926,6 +932,7 @@ void xprt_transmit(struct rpc_task *task) req->rq_xtime = ktime_get(); status = xprt->ops->send_request(task); + trace_xprt_transmit(xprt, req->rq_xid, status); if (status != 0) { task->tk_status = status; return; @@ -1296,6 +1303,7 @@ static void xprt_init(struct rpc_xprt *xprt, struct net *net) */ struct rpc_xprt *xprt_create_transport(struct xprt_create *args) { + int err; struct rpc_xprt *xprt; struct xprt_class *t; @@ -1336,6 +1344,12 @@ found: return ERR_PTR(-ENOMEM); } + err = rpc_xprt_debugfs_register(xprt); + if (err) { + xprt_destroy(xprt); + return ERR_PTR(err); + } + dprintk("RPC: created transport %p with %u slots\n", xprt, xprt->max_reqs); out: @@ -1352,6 +1366,7 @@ static void xprt_destroy(struct rpc_xprt *xprt) dprintk("RPC: destroying transport %p\n", xprt); del_timer_sync(&xprt->timer); + rpc_xprt_debugfs_unregister(xprt); rpc_destroy_wait_queue(&xprt->binding); rpc_destroy_wait_queue(&xprt->pending); rpc_destroy_wait_queue(&xprt->sending); diff --git a/net/sunrpc/xprtrdma/rpc_rdma.c b/net/sunrpc/xprtrdma/rpc_rdma.c index 6166c985fe24..df01d124936c 100644 --- a/net/sunrpc/xprtrdma/rpc_rdma.c +++ b/net/sunrpc/xprtrdma/rpc_rdma.c @@ -49,11 +49,11 @@ #include <linux/highmem.h> -#ifdef RPC_DEBUG +#if IS_ENABLED(CONFIG_SUNRPC_DEBUG) # define RPCDBG_FACILITY RPCDBG_TRANS #endif -#ifdef RPC_DEBUG +#if IS_ENABLED(CONFIG_SUNRPC_DEBUG) static const char transfertypes[][12] = { "pure inline", /* no chunks */ " read chunk", /* some argument via rdma read */ diff --git a/net/sunrpc/xprtrdma/transport.c b/net/sunrpc/xprtrdma/transport.c index 6a4615dd0261..bbd6155d3e34 100644 --- a/net/sunrpc/xprtrdma/transport.c +++ b/net/sunrpc/xprtrdma/transport.c @@ -55,7 +55,7 @@ #include "xprt_rdma.h" -#ifdef RPC_DEBUG +#if IS_ENABLED(CONFIG_SUNRPC_DEBUG) # define RPCDBG_FACILITY RPCDBG_TRANS #endif @@ -73,9 +73,9 @@ static unsigned int xprt_rdma_max_inline_read = RPCRDMA_DEF_INLINE; static unsigned int xprt_rdma_max_inline_write = RPCRDMA_DEF_INLINE; static unsigned int xprt_rdma_inline_write_padding; static unsigned int xprt_rdma_memreg_strategy = RPCRDMA_FRMR; - int xprt_rdma_pad_optimize = 0; + int xprt_rdma_pad_optimize = 1; -#ifdef RPC_DEBUG +#if IS_ENABLED(CONFIG_SUNRPC_DEBUG) static unsigned int min_slot_table_size = RPCRDMA_MIN_SLOT_TABLE; static unsigned int max_slot_table_size = RPCRDMA_MAX_SLOT_TABLE; @@ -599,7 +599,7 @@ xprt_rdma_send_request(struct rpc_task *task) if (req->rl_niovs == 0) rc = rpcrdma_marshal_req(rqst); - else if (r_xprt->rx_ia.ri_memreg_strategy == RPCRDMA_FRMR) + else if (r_xprt->rx_ia.ri_memreg_strategy != RPCRDMA_ALLPHYSICAL) rc = rpcrdma_marshal_chunks(rqst, 0); if (rc < 0) goto failed_marshal; @@ -705,7 +705,7 @@ static void __exit xprt_rdma_cleanup(void) int rc; dprintk("RPCRDMA Module Removed, deregister RPC RDMA transport\n"); -#ifdef RPC_DEBUG +#if IS_ENABLED(CONFIG_SUNRPC_DEBUG) if (sunrpc_table_header) { unregister_sysctl_table(sunrpc_table_header); sunrpc_table_header = NULL; @@ -736,7 +736,7 @@ static int __init xprt_rdma_init(void) dprintk("\tPadding %d\n\tMemreg %d\n", xprt_rdma_inline_write_padding, xprt_rdma_memreg_strategy); -#ifdef RPC_DEBUG +#if IS_ENABLED(CONFIG_SUNRPC_DEBUG) if (!sunrpc_table_header) sunrpc_table_header = register_sysctl_table(sunrpc_table); #endif diff --git a/net/sunrpc/xprtrdma/verbs.c b/net/sunrpc/xprtrdma/verbs.c index 61c41298b4ea..c98e40643910 100644 --- a/net/sunrpc/xprtrdma/verbs.c +++ b/net/sunrpc/xprtrdma/verbs.c @@ -57,11 +57,12 @@ * Globals/Macros */ -#ifdef RPC_DEBUG +#if IS_ENABLED(CONFIG_SUNRPC_DEBUG) # define RPCDBG_FACILITY RPCDBG_TRANS #endif static void rpcrdma_reset_frmrs(struct rpcrdma_ia *); +static void rpcrdma_reset_fmrs(struct rpcrdma_ia *); /* * internal functions @@ -105,13 +106,51 @@ rpcrdma_run_tasklet(unsigned long data) static DECLARE_TASKLET(rpcrdma_tasklet_g, rpcrdma_run_tasklet, 0UL); +static const char * const async_event[] = { + "CQ error", + "QP fatal error", + "QP request error", + "QP access error", + "communication established", + "send queue drained", + "path migration successful", + "path mig error", + "device fatal error", + "port active", + "port error", + "LID change", + "P_key change", + "SM change", + "SRQ error", + "SRQ limit reached", + "last WQE reached", + "client reregister", + "GID change", +}; + +#define ASYNC_MSG(status) \ + ((status) < ARRAY_SIZE(async_event) ? \ + async_event[(status)] : "unknown async error") + +static void +rpcrdma_schedule_tasklet(struct list_head *sched_list) +{ + unsigned long flags; + + spin_lock_irqsave(&rpcrdma_tk_lock_g, flags); + list_splice_tail(sched_list, &rpcrdma_tasklets_g); + spin_unlock_irqrestore(&rpcrdma_tk_lock_g, flags); + tasklet_schedule(&rpcrdma_tasklet_g); +} + static void rpcrdma_qp_async_error_upcall(struct ib_event *event, void *context) { struct rpcrdma_ep *ep = context; - dprintk("RPC: %s: QP error %X on device %s ep %p\n", - __func__, event->event, event->device->name, context); + pr_err("RPC: %s: %s on device %s ep %p\n", + __func__, ASYNC_MSG(event->event), + event->device->name, context); if (ep->rep_connected == 1) { ep->rep_connected = -EIO; ep->rep_func(ep); @@ -124,8 +163,9 @@ rpcrdma_cq_async_error_upcall(struct ib_event *event, void *context) { struct rpcrdma_ep *ep = context; - dprintk("RPC: %s: CQ error %X on device %s ep %p\n", - __func__, event->event, event->device->name, context); + pr_err("RPC: %s: %s on device %s ep %p\n", + __func__, ASYNC_MSG(event->event), + event->device->name, context); if (ep->rep_connected == 1) { ep->rep_connected = -EIO; ep->rep_func(ep); @@ -243,7 +283,6 @@ rpcrdma_recvcq_poll(struct ib_cq *cq, struct rpcrdma_ep *ep) struct list_head sched_list; struct ib_wc *wcs; int budget, count, rc; - unsigned long flags; INIT_LIST_HEAD(&sched_list); budget = RPCRDMA_WC_BUDGET / RPCRDMA_POLLSIZE; @@ -261,10 +300,7 @@ rpcrdma_recvcq_poll(struct ib_cq *cq, struct rpcrdma_ep *ep) rc = 0; out_schedule: - spin_lock_irqsave(&rpcrdma_tk_lock_g, flags); - list_splice_tail(&sched_list, &rpcrdma_tasklets_g); - spin_unlock_irqrestore(&rpcrdma_tk_lock_g, flags); - tasklet_schedule(&rpcrdma_tasklet_g); + rpcrdma_schedule_tasklet(&sched_list); return rc; } @@ -309,11 +345,18 @@ rpcrdma_recvcq_upcall(struct ib_cq *cq, void *cq_context) static void rpcrdma_flush_cqs(struct rpcrdma_ep *ep) { - rpcrdma_recvcq_upcall(ep->rep_attr.recv_cq, ep); - rpcrdma_sendcq_upcall(ep->rep_attr.send_cq, ep); + struct ib_wc wc; + LIST_HEAD(sched_list); + + while (ib_poll_cq(ep->rep_attr.recv_cq, 1, &wc) > 0) + rpcrdma_recvcq_process_wc(&wc, &sched_list); + if (!list_empty(&sched_list)) + rpcrdma_schedule_tasklet(&sched_list); + while (ib_poll_cq(ep->rep_attr.send_cq, 1, &wc) > 0) + rpcrdma_sendcq_process_wc(&wc); } -#ifdef RPC_DEBUG +#if IS_ENABLED(CONFIG_SUNRPC_DEBUG) static const char * const conn[] = { "address resolved", "address error", @@ -344,7 +387,7 @@ rpcrdma_conn_upcall(struct rdma_cm_id *id, struct rdma_cm_event *event) struct rpcrdma_xprt *xprt = id->context; struct rpcrdma_ia *ia = &xprt->rx_ia; struct rpcrdma_ep *ep = &xprt->rx_ep; -#ifdef RPC_DEBUG +#if IS_ENABLED(CONFIG_SUNRPC_DEBUG) struct sockaddr_in *addr = (struct sockaddr_in *) &ep->rep_remote_addr; #endif struct ib_qp_attr attr; @@ -408,7 +451,7 @@ connected: break; } -#ifdef RPC_DEBUG +#if IS_ENABLED(CONFIG_SUNRPC_DEBUG) if (connstate == 1) { int ird = attr.max_dest_rd_atomic; int tird = ep->rep_remote_cma.responder_resources; @@ -733,7 +776,9 @@ rpcrdma_ep_create(struct rpcrdma_ep *ep, struct rpcrdma_ia *ia, /* set trigger for requesting send completion */ ep->rep_cqinit = ep->rep_attr.cap.max_send_wr/2 - 1; - if (ep->rep_cqinit <= 2) + if (ep->rep_cqinit > RPCRDMA_MAX_UNSIGNALED_SENDS) + ep->rep_cqinit = RPCRDMA_MAX_UNSIGNALED_SENDS; + else if (ep->rep_cqinit <= 2) ep->rep_cqinit = 0; INIT_CQCOUNT(ep); ep->rep_ia = ia; @@ -866,8 +911,19 @@ retry: rpcrdma_ep_disconnect(ep, ia); rpcrdma_flush_cqs(ep); - if (ia->ri_memreg_strategy == RPCRDMA_FRMR) + switch (ia->ri_memreg_strategy) { + case RPCRDMA_FRMR: rpcrdma_reset_frmrs(ia); + break; + case RPCRDMA_MTHCAFMR: + rpcrdma_reset_fmrs(ia); + break; + case RPCRDMA_ALLPHYSICAL: + break; + default: + rc = -EIO; + goto out; + } xprt = container_of(ia, struct rpcrdma_xprt, rx_ia); id = rpcrdma_create_id(xprt, ia, @@ -1287,6 +1343,34 @@ rpcrdma_buffer_destroy(struct rpcrdma_buffer *buf) kfree(buf->rb_pool); } +/* After a disconnect, unmap all FMRs. + * + * This is invoked only in the transport connect worker in order + * to serialize with rpcrdma_register_fmr_external(). + */ +static void +rpcrdma_reset_fmrs(struct rpcrdma_ia *ia) +{ + struct rpcrdma_xprt *r_xprt = + container_of(ia, struct rpcrdma_xprt, rx_ia); + struct rpcrdma_buffer *buf = &r_xprt->rx_buf; + struct list_head *pos; + struct rpcrdma_mw *r; + LIST_HEAD(l); + int rc; + + list_for_each(pos, &buf->rb_all) { + r = list_entry(pos, struct rpcrdma_mw, mw_all); + + INIT_LIST_HEAD(&l); + list_add(&r->r.fmr->list, &l); + rc = ib_unmap_fmr(&l); + if (rc) + dprintk("RPC: %s: ib_unmap_fmr failed %i\n", + __func__, rc); + } +} + /* After a disconnect, a flushed FAST_REG_MR can leave an FRMR in * an unusable state. Find FRMRs in this state and dereg / reg * each. FRMRs that are VALID and attached to an rpcrdma_req are @@ -1918,10 +2002,10 @@ rpcrdma_register_external(struct rpcrdma_mr_seg *seg, break; default: - return -1; + return -EIO; } if (rc) - return -1; + return rc; return nsegs; } diff --git a/net/sunrpc/xprtrdma/xprt_rdma.h b/net/sunrpc/xprtrdma/xprt_rdma.h index ac7fc9a31342..b799041b75bf 100644 --- a/net/sunrpc/xprtrdma/xprt_rdma.h +++ b/net/sunrpc/xprtrdma/xprt_rdma.h @@ -97,6 +97,12 @@ struct rpcrdma_ep { struct ib_wc rep_recv_wcs[RPCRDMA_POLLSIZE]; }; +/* + * Force a signaled SEND Work Request every so often, + * in case the provider needs to do some housekeeping. + */ +#define RPCRDMA_MAX_UNSIGNALED_SENDS (32) + #define INIT_CQCOUNT(ep) atomic_set(&(ep)->rep_cqcount, (ep)->rep_cqinit) #define DECR_CQCOUNT(ep) atomic_sub_return(1, &(ep)->rep_cqcount) diff --git a/net/sunrpc/xprtsock.c b/net/sunrpc/xprtsock.c index 3b305ab17afe..87ce7e8bb8dc 100644 --- a/net/sunrpc/xprtsock.c +++ b/net/sunrpc/xprtsock.c @@ -75,7 +75,7 @@ static unsigned int xs_tcp_fin_timeout __read_mostly = XS_TCP_LINGER_TO; * someone else's file names! */ -#ifdef RPC_DEBUG +#if IS_ENABLED(CONFIG_SUNRPC_DEBUG) static unsigned int min_slot_table_size = RPC_MIN_SLOT_TABLE; static unsigned int max_slot_table_size = RPC_MAX_SLOT_TABLE; @@ -186,7 +186,7 @@ static struct ctl_table sunrpc_table[] = { */ #define XS_IDLE_DISC_TO (5U * 60 * HZ) -#ifdef RPC_DEBUG +#if IS_ENABLED(CONFIG_SUNRPC_DEBUG) # undef RPC_DEBUG_DATA # define RPCDBG_FACILITY RPCDBG_TRANS #endif @@ -216,65 +216,6 @@ static inline void xs_pktdump(char *msg, u32 *packet, unsigned int count) } #endif -struct sock_xprt { - struct rpc_xprt xprt; - - /* - * Network layer - */ - struct socket * sock; - struct sock * inet; - - /* - * State of TCP reply receive - */ - __be32 tcp_fraghdr, - tcp_xid, - tcp_calldir; - - u32 tcp_offset, - tcp_reclen; - - unsigned long tcp_copied, - tcp_flags; - - /* - * Connection of transports - */ - struct delayed_work connect_worker; - struct sockaddr_storage srcaddr; - unsigned short srcport; - - /* - * UDP socket buffer size parameters - */ - size_t rcvsize, - sndsize; - - /* - * Saved socket callback addresses - */ - void (*old_data_ready)(struct sock *); - void (*old_state_change)(struct sock *); - void (*old_write_space)(struct sock *); - void (*old_error_report)(struct sock *); -}; - -/* - * TCP receive state flags - */ -#define TCP_RCV_LAST_FRAG (1UL << 0) -#define TCP_RCV_COPY_FRAGHDR (1UL << 1) -#define TCP_RCV_COPY_XID (1UL << 2) -#define TCP_RCV_COPY_DATA (1UL << 3) -#define TCP_RCV_READ_CALLDIR (1UL << 4) -#define TCP_RCV_COPY_CALLDIR (1UL << 5) - -/* - * TCP RPC flags - */ -#define TCP_RPC_REPLY (1UL << 6) - static inline struct rpc_xprt *xprt_from_sock(struct sock *sk) { return (struct rpc_xprt *) sk->sk_user_data; @@ -1415,6 +1356,7 @@ static int xs_tcp_data_recv(read_descriptor_t *rd_desc, struct sk_buff *skb, uns dprintk("RPC: xs_tcp_data_recv started\n"); do { + trace_xs_tcp_data_recv(transport); /* Read in a new fragment marker if necessary */ /* Can we ever really expect to get completely empty fragments? */ if (transport->tcp_flags & TCP_RCV_COPY_FRAGHDR) { @@ -1439,6 +1381,7 @@ static int xs_tcp_data_recv(read_descriptor_t *rd_desc, struct sk_buff *skb, uns /* Skip over any trailing bytes on short reads */ xs_tcp_read_discard(transport, &desc); } while (desc.count); + trace_xs_tcp_data_recv(transport); dprintk("RPC: xs_tcp_data_recv done\n"); return len - desc.count; } @@ -1454,12 +1397,15 @@ static void xs_tcp_data_ready(struct sock *sk) struct rpc_xprt *xprt; read_descriptor_t rd_desc; int read; + unsigned long total = 0; dprintk("RPC: xs_tcp_data_ready...\n"); read_lock_bh(&sk->sk_callback_lock); - if (!(xprt = xprt_from_sock(sk))) + if (!(xprt = xprt_from_sock(sk))) { + read = 0; goto out; + } /* Any data means we had a useful conversation, so * the we don't need to delay the next reconnect */ @@ -1471,8 +1417,11 @@ static void xs_tcp_data_ready(struct sock *sk) do { rd_desc.count = 65536; read = tcp_read_sock(sk, &rd_desc, xs_tcp_data_recv); + if (read > 0) + total += read; } while (read > 0); out: + trace_xs_tcp_data_ready(xprt, read, total); read_unlock_bh(&sk->sk_callback_lock); } @@ -3042,7 +2991,7 @@ static struct xprt_class xs_bc_tcp_transport = { */ int init_socket_xprt(void) { -#ifdef RPC_DEBUG +#if IS_ENABLED(CONFIG_SUNRPC_DEBUG) if (!sunrpc_table_header) sunrpc_table_header = register_sysctl_table(sunrpc_table); #endif @@ -3061,7 +3010,7 @@ int init_socket_xprt(void) */ void cleanup_socket_xprt(void) { -#ifdef RPC_DEBUG +#if IS_ENABLED(CONFIG_SUNRPC_DEBUG) if (sunrpc_table_header) { unregister_sysctl_table(sunrpc_table_header); sunrpc_table_header = NULL; |