From 9446b87addd90a067b21c726aedd3c42694c1780 Mon Sep 17 00:00:00 2001 From: Ying Xue Date: Fri, 18 Oct 2013 07:23:15 +0200 Subject: tipc: remove iovec length parameter from all sending functions tipc_msg_build() now copies message data from iovec to skb_buff using memcpy_fromiovecend(), which doesn't need to be passed the iovec length to perform the copying. So we remove the parameter indicating iovec length in all functions where TIPC messages are built and sent. Signed-off-by: Ying Xue Reviewed-by: Paul Gortmaker Signed-off-by: Jon Maloy Signed-off-by: David S. Miller --- net/tipc/link.c | 25 ++++++++++--------------- 1 file changed, 10 insertions(+), 15 deletions(-) (limited to 'net/tipc/link.c') diff --git a/net/tipc/link.c b/net/tipc/link.c index 0cc3d9015c5d..b02a6dc4efe4 100644 --- a/net/tipc/link.c +++ b/net/tipc/link.c @@ -97,8 +97,7 @@ static int link_recv_changeover_msg(struct tipc_link **l_ptr, static void link_set_supervision_props(struct tipc_link *l_ptr, u32 tolerance); static int link_send_sections_long(struct tipc_port *sender, struct iovec const *msg_sect, - u32 num_sect, unsigned int total_len, - u32 destnode); + unsigned int len, u32 destnode); static void link_state_event(struct tipc_link *l_ptr, u32 event); static void link_reset_statistics(struct tipc_link *l_ptr); static void link_print(struct tipc_link *l_ptr, const char *str); @@ -1065,8 +1064,7 @@ static int link_send_buf_fast(struct tipc_link *l_ptr, struct sk_buff *buf, */ int tipc_link_send_sections_fast(struct tipc_port *sender, struct iovec const *msg_sect, - const u32 num_sect, unsigned int total_len, - u32 destaddr) + unsigned int len, u32 destaddr) { struct tipc_msg *hdr = &sender->phdr; struct tipc_link *l_ptr; @@ -1080,8 +1078,7 @@ again: * Try building message using port's max_pkt hint. * (Must not hold any locks while building message.) */ - res = tipc_msg_build(hdr, msg_sect, num_sect, total_len, - sender->max_pkt, &buf); + res = tipc_msg_build(hdr, msg_sect, len, sender->max_pkt, &buf); /* Exit if build request was invalid */ if (unlikely(res < 0)) return res; @@ -1121,8 +1118,7 @@ exit: if ((msg_hdr_sz(hdr) + res) <= sender->max_pkt) goto again; - return link_send_sections_long(sender, msg_sect, - num_sect, total_len, + return link_send_sections_long(sender, msg_sect, len, destaddr); } tipc_node_unlock(node); @@ -1133,8 +1129,8 @@ exit: if (buf) return tipc_reject_msg(buf, TIPC_ERR_NO_NODE); if (res >= 0) - return tipc_port_reject_sections(sender, hdr, msg_sect, num_sect, - total_len, TIPC_ERR_NO_NODE); + return tipc_port_reject_sections(sender, hdr, msg_sect, + len, TIPC_ERR_NO_NODE); return res; } @@ -1154,13 +1150,12 @@ exit: */ static int link_send_sections_long(struct tipc_port *sender, struct iovec const *msg_sect, - u32 num_sect, unsigned int total_len, - u32 destaddr) + unsigned int len, u32 destaddr) { struct tipc_link *l_ptr; struct tipc_node *node; struct tipc_msg *hdr = &sender->phdr; - u32 dsz = total_len; + u32 dsz = len; u32 max_pkt, fragm_sz, rest; struct tipc_msg fragm_hdr; struct sk_buff *buf, *buf_chain, *prev; @@ -1283,8 +1278,8 @@ reject: buf = buf_chain->next; kfree_skb(buf_chain); } - return tipc_port_reject_sections(sender, hdr, msg_sect, num_sect, - total_len, TIPC_ERR_NO_NODE); + return tipc_port_reject_sections(sender, hdr, msg_sect, + len, TIPC_ERR_NO_NODE); } /* Append chain of fragments to send queue & send them */ -- cgit v1.2.3-55-g7522 From 4068243208d605b046479e25c253379069a05fed Mon Sep 17 00:00:00 2001 From: Ying Xue Date: Fri, 18 Oct 2013 07:23:16 +0200 Subject: tipc: silence sparse warnings Eliminate below sparse warnings: net/tipc/link.c:1210:37: warning: cast removes address space of expression net/tipc/link.c:1218:59: warning: incorrect type in argument 2 (different address spaces) net/tipc/link.c:1218:59: expected void const [noderef] *from net/tipc/link.c:1218:59: got unsigned char const [usertype] *[assigned] sect_crs net/tipc/socket.c:341:49: warning: Using plain integer as NULL pointer net/tipc/socket.c:1371:36: warning: Using plain integer as NULL pointer net/tipc/socket.c:1694:57: warning: Using plain integer as NULL pointer Signed-off-by: Ying Xue Signed-off-by: Andreas Bofjäll Reviewed-by: Paul Gortmaker Signed-off-by: Jon Maloy Signed-off-by: David S. Miller --- net/tipc/link.c | 4 ++-- net/tipc/socket.c | 6 +++--- 2 files changed, 5 insertions(+), 5 deletions(-) (limited to 'net/tipc/link.c') diff --git a/net/tipc/link.c b/net/tipc/link.c index b02a6dc4efe4..be73a1fa7c65 100644 --- a/net/tipc/link.c +++ b/net/tipc/link.c @@ -1160,7 +1160,7 @@ static int link_send_sections_long(struct tipc_port *sender, struct tipc_msg fragm_hdr; struct sk_buff *buf, *buf_chain, *prev; u32 fragm_crs, fragm_rest, hsz, sect_rest; - const unchar *sect_crs; + const unchar __user *sect_crs; int curr_sect; u32 fragm_no; int res = 0; @@ -1202,7 +1202,7 @@ again: if (!sect_rest) { sect_rest = msg_sect[++curr_sect].iov_len; - sect_crs = (const unchar *)msg_sect[curr_sect].iov_base; + sect_crs = msg_sect[curr_sect].iov_base; } if (sect_rest < fragm_rest) diff --git a/net/tipc/socket.c b/net/tipc/socket.c index d224382d8270..3906527259d1 100644 --- a/net/tipc/socket.c +++ b/net/tipc/socket.c @@ -338,7 +338,7 @@ static int release(struct socket *sock) buf = __skb_dequeue(&sk->sk_receive_queue); if (buf == NULL) break; - if (TIPC_SKB_CB(buf)->handle != 0) + if (TIPC_SKB_CB(buf)->handle != NULL) kfree_skb(buf); else { if ((sock->state == SS_CONNECTING) || @@ -1364,7 +1364,7 @@ static u32 filter_rcv(struct sock *sk, struct sk_buff *buf) return TIPC_ERR_OVERLOAD; /* Enqueue message */ - TIPC_SKB_CB(buf)->handle = 0; + TIPC_SKB_CB(buf)->handle = NULL; __skb_queue_tail(&sk->sk_receive_queue, buf); skb_set_owner_r(buf, sk); @@ -1687,7 +1687,7 @@ restart: /* Disconnect and send a 'FIN+' or 'FIN-' message to peer */ buf = __skb_dequeue(&sk->sk_receive_queue); if (buf) { - if (TIPC_SKB_CB(buf)->handle != 0) { + if (TIPC_SKB_CB(buf)->handle != NULL) { kfree_skb(buf); goto restart; } -- cgit v1.2.3-55-g7522 From 636c0371a737c27510df867161fb8100c2f086bd Mon Sep 17 00:00:00 2001 From: Ying Xue Date: Fri, 18 Oct 2013 07:23:20 +0200 Subject: tipc: correct return value of link_cmd_set_value routine link_cmd_set_value() takes commands for link, bearer and media related configuration. Genereally the function returns 0 when a command is recognized, and -EINVAL when it is not. However, in the switch for link related commands it returns 0 even when the command is unrecognized. This will sometimes make it look as if a failed configuration command has been successful, but has otherwise no negative effects. We remove this anomaly by returning -EINVAL even for link commands. We also rework all three switches to make them conforming to common kernel coding style. Signed-off-by: Ying Xue Reviewed-by: Paul Gortmaker Signed-off-by: Jon Maloy Signed-off-by: David S. Miller --- net/tipc/link.c | 28 +++++++++++++++++++--------- 1 file changed, 19 insertions(+), 9 deletions(-) (limited to 'net/tipc/link.c') diff --git a/net/tipc/link.c b/net/tipc/link.c index be73a1fa7c65..223bbc87e451 100644 --- a/net/tipc/link.c +++ b/net/tipc/link.c @@ -2641,6 +2641,7 @@ static int link_cmd_set_value(const char *name, u32 new_value, u16 cmd) struct tipc_link *l_ptr; struct tipc_bearer *b_ptr; struct tipc_media *m_ptr; + int res = 0; l_ptr = link_find_link(name, &node); if (l_ptr) { @@ -2663,9 +2664,12 @@ static int link_cmd_set_value(const char *name, u32 new_value, u16 cmd) case TIPC_CMD_SET_LINK_WINDOW: tipc_link_set_queue_limits(l_ptr, new_value); break; + default: + res = -EINVAL; + break; } tipc_node_unlock(node); - return 0; + return res; } b_ptr = tipc_bearer_find(name); @@ -2673,15 +2677,18 @@ static int link_cmd_set_value(const char *name, u32 new_value, u16 cmd) switch (cmd) { case TIPC_CMD_SET_LINK_TOL: b_ptr->tolerance = new_value; - return 0; + break; case TIPC_CMD_SET_LINK_PRI: b_ptr->priority = new_value; - return 0; + break; case TIPC_CMD_SET_LINK_WINDOW: b_ptr->window = new_value; - return 0; + break; + default: + res = -EINVAL; + break; } - return -EINVAL; + return res; } m_ptr = tipc_media_find(name); @@ -2690,15 +2697,18 @@ static int link_cmd_set_value(const char *name, u32 new_value, u16 cmd) switch (cmd) { case TIPC_CMD_SET_LINK_TOL: m_ptr->tolerance = new_value; - return 0; + break; case TIPC_CMD_SET_LINK_PRI: m_ptr->priority = new_value; - return 0; + break; case TIPC_CMD_SET_LINK_WINDOW: m_ptr->window = new_value; - return 0; + break; + default: + res = -EINVAL; + break; } - return -EINVAL; + return res; } struct sk_buff *tipc_link_cmd_config(const void *req_tlv_area, int req_tlv_space, -- cgit v1.2.3-55-g7522 From bbfbe47cc99ce093708aaf28b7f2c08d28045c67 Mon Sep 17 00:00:00 2001 From: Erik Hugne Date: Fri, 18 Oct 2013 07:23:21 +0200 Subject: tipc: simplify the link lookup routine When checking statistics or changing parameters on a link, the link_find_link function is used to locate the link with a given name. The complex method of deconstructing the name into local and remote address/interface is error prone and may fail if the interface names contains special characters. We change the lookup method to iterate over the list of nodes and compare the link names. Signed-off-by: Erik Hugne Reviewed-by: Paul Gortmaker Signed-off-by: Jon Maloy Signed-off-by: David S. Miller --- net/tipc/link.c | 110 +++++++------------------------------------------------- 1 file changed, 13 insertions(+), 97 deletions(-) (limited to 'net/tipc/link.c') diff --git a/net/tipc/link.c b/net/tipc/link.c index 223bbc87e451..e8153f64d2d6 100644 --- a/net/tipc/link.c +++ b/net/tipc/link.c @@ -75,20 +75,6 @@ static const char *link_unk_evt = "Unknown link event "; */ #define START_CHANGEOVER 100000u -/** - * struct tipc_link_name - deconstructed link name - * @addr_local: network address of node at this end - * @if_local: name of interface at this end - * @addr_peer: network address of node at far end - * @if_peer: name of interface at far end - */ -struct tipc_link_name { - u32 addr_local; - char if_local[TIPC_MAX_IF_NAME]; - u32 addr_peer; - char if_peer[TIPC_MAX_IF_NAME]; -}; - static void link_handle_out_of_seq_msg(struct tipc_link *l_ptr, struct sk_buff *buf); static void link_recv_proto_msg(struct tipc_link *l_ptr, struct sk_buff *buf); @@ -159,72 +145,6 @@ int tipc_link_is_active(struct tipc_link *l_ptr) (l_ptr->owner->active_links[1] == l_ptr); } -/** - * link_name_validate - validate & (optionally) deconstruct tipc_link name - * @name: ptr to link name string - * @name_parts: ptr to area for link name components (or NULL if not needed) - * - * Returns 1 if link name is valid, otherwise 0. - */ -static int link_name_validate(const char *name, - struct tipc_link_name *name_parts) -{ - char name_copy[TIPC_MAX_LINK_NAME]; - char *addr_local; - char *if_local; - char *addr_peer; - char *if_peer; - char dummy; - u32 z_local, c_local, n_local; - u32 z_peer, c_peer, n_peer; - u32 if_local_len; - u32 if_peer_len; - - /* copy link name & ensure length is OK */ - name_copy[TIPC_MAX_LINK_NAME - 1] = 0; - /* need above in case non-Posix strncpy() doesn't pad with nulls */ - strncpy(name_copy, name, TIPC_MAX_LINK_NAME); - if (name_copy[TIPC_MAX_LINK_NAME - 1] != 0) - return 0; - - /* ensure all component parts of link name are present */ - addr_local = name_copy; - if_local = strchr(addr_local, ':'); - if (if_local == NULL) - return 0; - *(if_local++) = 0; - addr_peer = strchr(if_local, '-'); - if (addr_peer == NULL) - return 0; - *(addr_peer++) = 0; - if_local_len = addr_peer - if_local; - if_peer = strchr(addr_peer, ':'); - if (if_peer == NULL) - return 0; - *(if_peer++) = 0; - if_peer_len = strlen(if_peer) + 1; - - /* validate component parts of link name */ - if ((sscanf(addr_local, "%u.%u.%u%c", - &z_local, &c_local, &n_local, &dummy) != 3) || - (sscanf(addr_peer, "%u.%u.%u%c", - &z_peer, &c_peer, &n_peer, &dummy) != 3) || - (z_local > 255) || (c_local > 4095) || (n_local > 4095) || - (z_peer > 255) || (c_peer > 4095) || (n_peer > 4095) || - (if_local_len <= 1) || (if_local_len > TIPC_MAX_IF_NAME) || - (if_peer_len <= 1) || (if_peer_len > TIPC_MAX_IF_NAME)) - return 0; - - /* return link name components, if necessary */ - if (name_parts) { - name_parts->addr_local = tipc_addr(z_local, c_local, n_local); - strcpy(name_parts->if_local, if_local); - name_parts->addr_peer = tipc_addr(z_peer, c_peer, n_peer); - strcpy(name_parts->if_peer, if_peer); - } - return 1; -} - /** * link_timeout - handle expiration of link timer * @l_ptr: pointer to link @@ -2580,25 +2500,21 @@ void tipc_link_set_queue_limits(struct tipc_link *l_ptr, u32 window) static struct tipc_link *link_find_link(const char *name, struct tipc_node **node) { - struct tipc_link_name link_name_parts; - struct tipc_bearer *b_ptr; struct tipc_link *l_ptr; + struct tipc_node *n_ptr; + int i; - if (!link_name_validate(name, &link_name_parts)) - return NULL; - - b_ptr = tipc_bearer_find_interface(link_name_parts.if_local); - if (!b_ptr) - return NULL; - - *node = tipc_node_find(link_name_parts.addr_peer); - if (!*node) - return NULL; - - l_ptr = (*node)->links[b_ptr->identity]; - if (!l_ptr || strcmp(l_ptr->name, name)) - return NULL; - + list_for_each_entry(n_ptr, &tipc_node_list, list) { + for (i = 0; i < MAX_BEARERS; i++) { + l_ptr = n_ptr->links[i]; + if (l_ptr && !strcmp(l_ptr->name, name)) + goto found; + } + } + l_ptr = NULL; + n_ptr = NULL; +found: + *node = n_ptr; return l_ptr; } -- cgit v1.2.3-55-g7522 From 3af390e2c5fd8a8cab6d123c18fcd3e1a65b43c6 Mon Sep 17 00:00:00 2001 From: Ying Xue Date: Wed, 30 Oct 2013 11:26:57 +0800 Subject: tipc: remove two indentation levels in tipc_recv_msg routine The message dispatching part of tipc_recv_msg() is wrapped layers of while/if/if/switch, causing out-of-control indentation and does not look very good. We reduce two indentation levels by separating the message dispatching from the blocks that checks link state and sequence numbers, allowing longer function and arg names to be consistently indented without wrapping. Additionally we also rename "cont" label to "discard" and add one new label called "unlock_discard" to make code clearer. In all, these are cosmetic changes that do not alter the operation of TIPC in any way. Signed-off-by: Ying Xue Reviewed-by: Erik Hugne Cc: David Laight Cc: Andreas Bofjäll Signed-off-by: David S. Miller --- net/tipc/link.c | 173 +++++++++++++++++++++++++++----------------------------- 1 file changed, 84 insertions(+), 89 deletions(-) (limited to 'net/tipc/link.c') diff --git a/net/tipc/link.c b/net/tipc/link.c index e8153f64d2d6..54163f91b8ae 100644 --- a/net/tipc/link.c +++ b/net/tipc/link.c @@ -1507,15 +1507,15 @@ void tipc_recv_msg(struct sk_buff *head, struct tipc_bearer *b_ptr) /* Ensure bearer is still enabled */ if (unlikely(!b_ptr->active)) - goto cont; + goto discard; /* Ensure message is well-formed */ if (unlikely(!link_recv_buf_validate(buf))) - goto cont; + goto discard; /* Ensure message data is a single contiguous unit */ if (unlikely(skb_linearize(buf))) - goto cont; + goto discard; /* Handle arrival of a non-unicast link message */ msg = buf_msg(buf); @@ -1531,20 +1531,18 @@ void tipc_recv_msg(struct sk_buff *head, struct tipc_bearer *b_ptr) /* Discard unicast link messages destined for another node */ if (unlikely(!msg_short(msg) && (msg_destnode(msg) != tipc_own_addr))) - goto cont; + goto discard; /* Locate neighboring node that sent message */ n_ptr = tipc_node_find(msg_prevnode(msg)); if (unlikely(!n_ptr)) - goto cont; + goto discard; tipc_node_lock(n_ptr); /* Locate unicast link endpoint that should handle message */ l_ptr = n_ptr->links[b_ptr->identity]; - if (unlikely(!l_ptr)) { - tipc_node_unlock(n_ptr); - goto cont; - } + if (unlikely(!l_ptr)) + goto unlock_discard; /* Verify that communication with node is currently allowed */ if ((n_ptr->block_setup & WAIT_PEER_DOWN) && @@ -1554,10 +1552,8 @@ void tipc_recv_msg(struct sk_buff *head, struct tipc_bearer *b_ptr) !msg_redundant_link(msg)) n_ptr->block_setup &= ~WAIT_PEER_DOWN; - if (n_ptr->block_setup) { - tipc_node_unlock(n_ptr); - goto cont; - } + if (n_ptr->block_setup) + goto unlock_discard; /* Validate message sequence number info */ seq_no = msg_seqno(msg); @@ -1593,98 +1589,97 @@ void tipc_recv_msg(struct sk_buff *head, struct tipc_bearer *b_ptr) /* Now (finally!) process the incoming message */ protocol_check: - if (likely(link_working_working(l_ptr))) { - if (likely(seq_no == mod(l_ptr->next_in_no))) { - l_ptr->next_in_no++; - if (unlikely(l_ptr->oldest_deferred_in)) - head = link_insert_deferred_queue(l_ptr, - head); -deliver: - if (likely(msg_isdata(msg))) { - tipc_node_unlock(n_ptr); - tipc_port_recv_msg(buf); - continue; - } - switch (msg_user(msg)) { - int ret; - case MSG_BUNDLER: - l_ptr->stats.recv_bundles++; - l_ptr->stats.recv_bundled += - msg_msgcnt(msg); - tipc_node_unlock(n_ptr); - tipc_link_recv_bundle(buf); - continue; - case NAME_DISTRIBUTOR: - n_ptr->bclink.recv_permitted = true; - tipc_node_unlock(n_ptr); - tipc_named_recv(buf); - continue; - case BCAST_PROTOCOL: - tipc_link_recv_sync(n_ptr, buf); - tipc_node_unlock(n_ptr); - continue; - case CONN_MANAGER: - tipc_node_unlock(n_ptr); - tipc_port_recv_proto_msg(buf); - continue; - case MSG_FRAGMENTER: - l_ptr->stats.recv_fragments++; - ret = tipc_link_recv_fragment( - &l_ptr->defragm_buf, - &buf, &msg); - if (ret == 1) { - l_ptr->stats.recv_fragmented++; - goto deliver; - } - if (ret == -1) - l_ptr->next_in_no--; - break; - case CHANGEOVER_PROTOCOL: - type = msg_type(msg); - if (link_recv_changeover_msg(&l_ptr, - &buf)) { - msg = buf_msg(buf); - seq_no = msg_seqno(msg); - if (type == ORIGINAL_MSG) - goto deliver; - goto protocol_check; - } - break; - default: - kfree_skb(buf); - buf = NULL; - break; - } + if (unlikely(!link_working_working(l_ptr))) { + if (msg_user(msg) == LINK_PROTOCOL) { + link_recv_proto_msg(l_ptr, buf); + head = link_insert_deferred_queue(l_ptr, head); + tipc_node_unlock(n_ptr); + continue; + } + + /* Traffic message. Conditionally activate link */ + link_state_event(l_ptr, TRAFFIC_MSG_EVT); + + if (link_working_working(l_ptr)) { + /* Re-insert buffer in front of queue */ + buf->next = head; + head = buf; tipc_node_unlock(n_ptr); - tipc_net_route_msg(buf); continue; } + goto unlock_discard; + } + + /* Link is now in state WORKING_WORKING */ + if (unlikely(seq_no != mod(l_ptr->next_in_no))) { link_handle_out_of_seq_msg(l_ptr, buf); head = link_insert_deferred_queue(l_ptr, head); tipc_node_unlock(n_ptr); continue; } - - /* Link is not in state WORKING_WORKING */ - if (msg_user(msg) == LINK_PROTOCOL) { - link_recv_proto_msg(l_ptr, buf); + l_ptr->next_in_no++; + if (unlikely(l_ptr->oldest_deferred_in)) head = link_insert_deferred_queue(l_ptr, head); +deliver: + if (likely(msg_isdata(msg))) { tipc_node_unlock(n_ptr); + tipc_port_recv_msg(buf); continue; } - - /* Traffic message. Conditionally activate link */ - link_state_event(l_ptr, TRAFFIC_MSG_EVT); - - if (link_working_working(l_ptr)) { - /* Re-insert buffer in front of queue */ - buf->next = head; - head = buf; + switch (msg_user(msg)) { + int ret; + case MSG_BUNDLER: + l_ptr->stats.recv_bundles++; + l_ptr->stats.recv_bundled += msg_msgcnt(msg); + tipc_node_unlock(n_ptr); + tipc_link_recv_bundle(buf); + continue; + case NAME_DISTRIBUTOR: + n_ptr->bclink.recv_permitted = true; + tipc_node_unlock(n_ptr); + tipc_named_recv(buf); + continue; + case BCAST_PROTOCOL: + tipc_link_recv_sync(n_ptr, buf); tipc_node_unlock(n_ptr); continue; + case CONN_MANAGER: + tipc_node_unlock(n_ptr); + tipc_port_recv_proto_msg(buf); + continue; + case MSG_FRAGMENTER: + l_ptr->stats.recv_fragments++; + ret = tipc_link_recv_fragment(&l_ptr->defragm_buf, + &buf, &msg); + if (ret == 1) { + l_ptr->stats.recv_fragmented++; + goto deliver; + } + if (ret == -1) + l_ptr->next_in_no--; + break; + case CHANGEOVER_PROTOCOL: + type = msg_type(msg); + if (link_recv_changeover_msg(&l_ptr, &buf)) { + msg = buf_msg(buf); + seq_no = msg_seqno(msg); + if (type == ORIGINAL_MSG) + goto deliver; + goto protocol_check; + } + break; + default: + kfree_skb(buf); + buf = NULL; + break; } tipc_node_unlock(n_ptr); -cont: + tipc_net_route_msg(buf); + continue; +unlock_discard: + + tipc_node_unlock(n_ptr); +discard: kfree_skb(buf); } read_unlock_bh(&tipc_net_lock); -- cgit v1.2.3-55-g7522 From 528f6f4bf372511ebf6004eed822de8f749b5930 Mon Sep 17 00:00:00 2001 From: Erik Hugne Date: Wed, 6 Nov 2013 09:28:05 +0100 Subject: tipc: don't reroute message fragments When a message fragment is received in a broadcast or unicast link, the reception code will append the fragment payload to a big reassembly buffer through a call to the function tipc_recv_fragm(). However, after the return of that call, the logics goes on and passes the fragment buffer to the function tipc_net_route_msg(), which will simply drop it. This behavior is a remnant from the now obsolete multi-cluster functionality, and has no relevance in the current code base. Although currently harmless, this unnecessary call would be fatal after applying the next patch in this series, which introduces a completely new reassembly algorithm. So we change the code to eliminate the redundant call. Signed-off-by: Erik Hugne Reviewed-by: Paul Gortmaker Signed-off-by: Jon Maloy Signed-off-by: David S. Miller --- net/tipc/bcast.c | 6 ++++-- net/tipc/link.c | 3 ++- 2 files changed, 6 insertions(+), 3 deletions(-) (limited to 'net/tipc/link.c') diff --git a/net/tipc/bcast.c b/net/tipc/bcast.c index 716de1ac6cb5..766a6eb4a88f 100644 --- a/net/tipc/bcast.c +++ b/net/tipc/bcast.c @@ -487,11 +487,13 @@ receive: spin_lock_bh(&bc_lock); bclink_accept_pkt(node, seqno); bcl->stats.recv_fragments++; - if (ret > 0) + if (ret > 0) { bcl->stats.recv_fragmented++; + spin_unlock_bh(&bc_lock); + goto receive; + } spin_unlock_bh(&bc_lock); tipc_node_unlock(node); - tipc_net_route_msg(buf); } else if (msg_user(msg) == NAME_DISTRIBUTOR) { spin_lock_bh(&bc_lock); bclink_accept_pkt(node, seqno); diff --git a/net/tipc/link.c b/net/tipc/link.c index 54163f91b8ae..ada8cadf5af8 100644 --- a/net/tipc/link.c +++ b/net/tipc/link.c @@ -1657,7 +1657,8 @@ deliver: } if (ret == -1) l_ptr->next_in_no--; - break; + tipc_node_unlock(n_ptr); + continue; case CHANGEOVER_PROTOCOL: type = msg_type(msg); if (link_recv_changeover_msg(&l_ptr, &buf)) { -- cgit v1.2.3-55-g7522 From 40ba3cdf542a469aaa9083fa041656e59b109b90 Mon Sep 17 00:00:00 2001 From: Erik Hugne Date: Wed, 6 Nov 2013 09:28:06 +0100 Subject: tipc: message reassembly using fragment chain When the first fragment of a long data data message is received on a link, a reassembly buffer large enough to hold the data from this and all subsequent fragments of the message is allocated. The payload of each new fragment is copied into this buffer upon arrival. When the last fragment is received, the reassembled message is delivered upwards to the port/socket layer. Not only is this an inefficient approach, but it may also cause bursts of reassembly failures in low memory situations. since we may fail to allocate the necessary large buffer in the first place. Furthermore, after 100 subsequent such failures the link will be reset, something that in reality aggravates the situation. To remedy this problem, this patch introduces a different approach. Instead of allocating a big reassembly buffer, we now append the arriving fragments to a reassembly chain on the link, and deliver the whole chain up to the socket layer once the last fragment has been received. This is safe because the retransmission layer of a TIPC link always delivers packets in strict uninterrupted order, to the reassembly layer as to all other upper layers. Hence there can never be more than one fragment chain pending reassembly at any given time in a link, and we can trust (but still verify) that the fragments will be chained up in the correct order. Signed-off-by: Erik Hugne Reviewed-by: Paul Gortmaker Signed-off-by: Jon Maloy Signed-off-by: David S. Miller --- net/tipc/bcast.c | 12 +++-- net/tipc/link.c | 159 +++++++++++++++---------------------------------------- net/tipc/link.h | 20 ++++--- net/tipc/msg.h | 12 ----- net/tipc/node.c | 7 +-- net/tipc/node.h | 6 ++- 6 files changed, 74 insertions(+), 142 deletions(-) (limited to 'net/tipc/link.c') diff --git a/net/tipc/bcast.c b/net/tipc/bcast.c index 766a6eb4a88f..0d4402587fdf 100644 --- a/net/tipc/bcast.c +++ b/net/tipc/bcast.c @@ -480,15 +480,19 @@ receive: tipc_node_unlock(node); tipc_link_recv_bundle(buf); } else if (msg_user(msg) == MSG_FRAGMENTER) { - int ret = tipc_link_recv_fragment(&node->bclink.defragm, - &buf, &msg); - if (ret < 0) + int ret; + ret = tipc_link_recv_fragment(&node->bclink.reasm_head, + &node->bclink.reasm_tail, + &buf); + if (ret == LINK_REASM_ERROR) goto unlock; spin_lock_bh(&bc_lock); bclink_accept_pkt(node, seqno); bcl->stats.recv_fragments++; - if (ret > 0) { + if (ret == LINK_REASM_COMPLETE) { bcl->stats.recv_fragmented++; + /* Point msg to inner header */ + msg = buf_msg(buf); spin_unlock_bh(&bc_lock); goto receive; } diff --git a/net/tipc/link.c b/net/tipc/link.c index ada8cadf5af8..a63646e6c2cf 100644 --- a/net/tipc/link.c +++ b/net/tipc/link.c @@ -404,15 +404,9 @@ static void link_release_outqueue(struct tipc_link *l_ptr) */ void tipc_link_reset_fragments(struct tipc_link *l_ptr) { - struct sk_buff *buf = l_ptr->defragm_buf; - struct sk_buff *next; - - while (buf) { - next = buf->next; - kfree_skb(buf); - buf = next; - } - l_ptr->defragm_buf = NULL; + kfree_skb(l_ptr->reasm_head); + l_ptr->reasm_head = NULL; + l_ptr->reasm_tail = NULL; } /** @@ -1649,13 +1643,15 @@ deliver: continue; case MSG_FRAGMENTER: l_ptr->stats.recv_fragments++; - ret = tipc_link_recv_fragment(&l_ptr->defragm_buf, - &buf, &msg); - if (ret == 1) { + ret = tipc_link_recv_fragment(&l_ptr->reasm_head, + &l_ptr->reasm_tail, + &buf); + if (ret == LINK_REASM_COMPLETE) { l_ptr->stats.recv_fragmented++; + msg = buf_msg(buf); goto deliver; } - if (ret == -1) + if (ret == LINK_REASM_ERROR) l_ptr->next_in_no--; tipc_node_unlock(n_ptr); continue; @@ -2342,115 +2338,48 @@ static int link_send_long_buf(struct tipc_link *l_ptr, struct sk_buff *buf) return dsz; } -/* - * A pending message being re-assembled must store certain values - * to handle subsequent fragments correctly. The following functions - * help storing these values in unused, available fields in the - * pending message. This makes dynamic memory allocation unnecessary. - */ -static void set_long_msg_seqno(struct sk_buff *buf, u32 seqno) -{ - msg_set_seqno(buf_msg(buf), seqno); -} - -static u32 get_fragm_size(struct sk_buff *buf) -{ - return msg_ack(buf_msg(buf)); -} - -static void set_fragm_size(struct sk_buff *buf, u32 sz) -{ - msg_set_ack(buf_msg(buf), sz); -} - -static u32 get_expected_frags(struct sk_buff *buf) -{ - return msg_bcast_ack(buf_msg(buf)); -} - -static void set_expected_frags(struct sk_buff *buf, u32 exp) -{ - msg_set_bcast_ack(buf_msg(buf), exp); -} - /* * tipc_link_recv_fragment(): Called with node lock on. Returns * the reassembled buffer if message is complete. */ -int tipc_link_recv_fragment(struct sk_buff **pending, struct sk_buff **fb, - struct tipc_msg **m) -{ - struct sk_buff *prev = NULL; - struct sk_buff *fbuf = *fb; - struct tipc_msg *fragm = buf_msg(fbuf); - struct sk_buff *pbuf = *pending; - u32 long_msg_seq_no = msg_long_msgno(fragm); - - *fb = NULL; - - /* Is there an incomplete message waiting for this fragment? */ - while (pbuf && ((buf_seqno(pbuf) != long_msg_seq_no) || - (msg_orignode(fragm) != msg_orignode(buf_msg(pbuf))))) { - prev = pbuf; - pbuf = pbuf->next; - } - - if (!pbuf && (msg_type(fragm) == FIRST_FRAGMENT)) { - struct tipc_msg *imsg = (struct tipc_msg *)msg_data(fragm); - u32 msg_sz = msg_size(imsg); - u32 fragm_sz = msg_data_sz(fragm); - u32 exp_fragm_cnt; - u32 max = TIPC_MAX_USER_MSG_SIZE + NAMED_H_SIZE; - - if (msg_type(imsg) == TIPC_MCAST_MSG) - max = TIPC_MAX_USER_MSG_SIZE + MCAST_H_SIZE; - if (fragm_sz == 0 || msg_size(imsg) > max) { - kfree_skb(fbuf); - return 0; - } - exp_fragm_cnt = msg_sz / fragm_sz + !!(msg_sz % fragm_sz); - pbuf = tipc_buf_acquire(msg_size(imsg)); - if (pbuf != NULL) { - pbuf->next = *pending; - *pending = pbuf; - skb_copy_to_linear_data(pbuf, imsg, - msg_data_sz(fragm)); - /* Prepare buffer for subsequent fragments. */ - set_long_msg_seqno(pbuf, long_msg_seq_no); - set_fragm_size(pbuf, fragm_sz); - set_expected_frags(pbuf, exp_fragm_cnt - 1); - } else { - pr_debug("Link unable to reassemble fragmented message\n"); - kfree_skb(fbuf); - return -1; - } - kfree_skb(fbuf); - return 0; - } else if (pbuf && (msg_type(fragm) != FIRST_FRAGMENT)) { - u32 dsz = msg_data_sz(fragm); - u32 fsz = get_fragm_size(pbuf); - u32 crs = ((msg_fragm_no(fragm) - 1) * fsz); - u32 exp_frags = get_expected_frags(pbuf) - 1; - skb_copy_to_linear_data_offset(pbuf, crs, - msg_data(fragm), dsz); - kfree_skb(fbuf); - - /* Is message complete? */ - if (exp_frags == 0) { - if (prev) - prev->next = pbuf->next; - else - *pending = pbuf->next; - msg_reset_reroute_cnt(buf_msg(pbuf)); - *fb = pbuf; - *m = buf_msg(pbuf); - return 1; - } - set_expected_frags(pbuf, exp_frags); +int tipc_link_recv_fragment(struct sk_buff **head, struct sk_buff **tail, + struct sk_buff **fbuf) +{ + struct sk_buff *frag = *fbuf; + struct tipc_msg *msg = buf_msg(frag); + u32 fragid = msg_type(msg); + bool headstolen; + int delta; + + skb_pull(frag, msg_hdr_sz(msg)); + if (fragid == FIRST_FRAGMENT) { + if (*head || skb_unclone(frag, GFP_ATOMIC)) + goto out_free; + *head = frag; + skb_frag_list_init(*head); return 0; + } else if (skb_try_coalesce(*head, frag, &headstolen, &delta)) { + kfree_skb_partial(frag, headstolen); + } else { + if (!*head) + goto out_free; + if (!skb_has_frag_list(*head)) + skb_shinfo(*head)->frag_list = frag; + else + (*tail)->next = frag; + *tail = frag; + (*head)->truesize += frag->truesize; + } + if (fragid == LAST_FRAGMENT) { + *fbuf = *head; + *tail = *head = NULL; + return LINK_REASM_COMPLETE; } - kfree_skb(fbuf); return 0; +out_free: + pr_warn_ratelimited("Link unable to reassemble fragmented message\n"); + kfree_skb(*fbuf); + return LINK_REASM_ERROR; } static void link_set_supervision_props(struct tipc_link *l_ptr, u32 tolerance) diff --git a/net/tipc/link.h b/net/tipc/link.h index 55cf8554a08b..8a6c1026644d 100644 --- a/net/tipc/link.h +++ b/net/tipc/link.h @@ -40,6 +40,12 @@ #include "msg.h" #include "node.h" +/* + * Link reassembly status codes + */ +#define LINK_REASM_ERROR -1 +#define LINK_REASM_COMPLETE 1 + /* * Out-of-range value for link sequence numbers */ @@ -134,7 +140,8 @@ struct tipc_stats { * @next_out: ptr to first unsent outbound message in queue * @waiting_ports: linked list of ports waiting for link congestion to abate * @long_msg_seq_no: next identifier to use for outbound fragmented messages - * @defragm_buf: list of partially reassembled inbound message fragments + * @reasm_head: list head of partially reassembled inbound message fragments + * @reasm_tail: last fragment received * @stats: collects statistics regarding link activity */ struct tipc_link { @@ -196,9 +203,10 @@ struct tipc_link { struct sk_buff *next_out; struct list_head waiting_ports; - /* Fragmentation/defragmentation */ + /* Fragmentation/reassembly */ u32 long_msg_seq_no; - struct sk_buff *defragm_buf; + struct sk_buff *reasm_head; + struct sk_buff *reasm_tail; /* Statistics */ struct tipc_stats stats; @@ -229,9 +237,9 @@ int tipc_link_send_sections_fast(struct tipc_port *sender, struct iovec const *msg_sect, unsigned int len, u32 destnode); void tipc_link_recv_bundle(struct sk_buff *buf); -int tipc_link_recv_fragment(struct sk_buff **pending, - struct sk_buff **fb, - struct tipc_msg **msg); +int tipc_link_recv_fragment(struct sk_buff **reasm_head, + struct sk_buff **reasm_tail, + struct sk_buff **fbuf); void tipc_link_send_proto_msg(struct tipc_link *l_ptr, u32 msg_typ, int prob, u32 gap, u32 tolerance, u32 priority, u32 acked_mtu); diff --git a/net/tipc/msg.h b/net/tipc/msg.h index 559b73a9bf35..76d1269b9443 100644 --- a/net/tipc/msg.h +++ b/net/tipc/msg.h @@ -554,12 +554,6 @@ static inline void msg_set_last_bcast(struct tipc_msg *m, u32 n) msg_set_bits(m, 4, 16, 0xffff, n); } - -static inline u32 msg_fragm_no(struct tipc_msg *m) -{ - return msg_bits(m, 4, 16, 0xffff); -} - static inline void msg_set_fragm_no(struct tipc_msg *m, u32 n) { msg_set_bits(m, 4, 16, 0xffff, n); @@ -576,12 +570,6 @@ static inline void msg_set_next_sent(struct tipc_msg *m, u32 n) msg_set_bits(m, 4, 0, 0xffff, n); } - -static inline u32 msg_long_msgno(struct tipc_msg *m) -{ - return msg_bits(m, 4, 0, 0xffff); -} - static inline void msg_set_long_msgno(struct tipc_msg *m, u32 n) { msg_set_bits(m, 4, 0, 0xffff, n); diff --git a/net/tipc/node.c b/net/tipc/node.c index 6e6c434872e8..25100c0a6fe8 100644 --- a/net/tipc/node.c +++ b/net/tipc/node.c @@ -298,9 +298,10 @@ static void node_lost_contact(struct tipc_node *n_ptr) } n_ptr->bclink.deferred_size = 0; - if (n_ptr->bclink.defragm) { - kfree_skb(n_ptr->bclink.defragm); - n_ptr->bclink.defragm = NULL; + if (n_ptr->bclink.reasm_head) { + kfree_skb(n_ptr->bclink.reasm_head); + n_ptr->bclink.reasm_head = NULL; + n_ptr->bclink.reasm_tail = NULL; } tipc_bclink_remove_node(n_ptr->addr); diff --git a/net/tipc/node.h b/net/tipc/node.h index 3c189b35b102..e5e96c04e167 100644 --- a/net/tipc/node.h +++ b/net/tipc/node.h @@ -74,7 +74,8 @@ * @deferred_size: number of OOS b'cast messages in deferred queue * @deferred_head: oldest OOS b'cast message received from node * @deferred_tail: newest OOS b'cast message received from node - * @defragm: list of partially reassembled b'cast message fragments from node + * @reasm_head: broadcast reassembly queue head from node + * @reasm_tail: last broadcast fragment received from node * @recv_permitted: true if node is allowed to receive b'cast messages */ struct tipc_node { @@ -98,7 +99,8 @@ struct tipc_node { u32 deferred_size; struct sk_buff *deferred_head; struct sk_buff *deferred_tail; - struct sk_buff *defragm; + struct sk_buff *reasm_head; + struct sk_buff *reasm_tail; bool recv_permitted; } bclink; }; -- cgit v1.2.3-55-g7522 From a715b49e79b0924863ff1424f9823cc1b5972322 Mon Sep 17 00:00:00 2001 From: Erik Hugne Date: Wed, 6 Nov 2013 09:28:07 +0100 Subject: tipc: reassembly failures should cause link reset If appending a received fragment to the pending fragment chain in a unicast link fails, the current code tries to force a retransmission of the fragment by decrementing the 'next received sequence number' field in the link. This is done under the assumption that the failure is caused by an out-of-memory situation, an assumption that does not hold true after the previous patch in this series. A failure to append a fragment can now only be caused by a protocol violation by the sending peer, and it must hence be assumed that it is either malicious or buggy. Either way, the correct behavior is now to reset the link instead of trying to revert its sequence number. So, this is what we do in this commit. Signed-off-by: Erik Hugne Reviewed-by: Paul Gortmaker Signed-off-by: Jon Maloy Signed-off-by: David S. Miller --- net/tipc/link.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'net/tipc/link.c') diff --git a/net/tipc/link.c b/net/tipc/link.c index a63646e6c2cf..cf465d66ccde 100644 --- a/net/tipc/link.c +++ b/net/tipc/link.c @@ -1652,7 +1652,7 @@ deliver: goto deliver; } if (ret == LINK_REASM_ERROR) - l_ptr->next_in_no--; + tipc_link_reset(l_ptr); tipc_node_unlock(n_ptr); continue; case CHANGEOVER_PROTOCOL: -- cgit v1.2.3-55-g7522