diff options
| author | Linus Torvalds <torvalds@linux-foundation.org> | 2014-08-06 09:38:14 -0700 |
|---|---|---|
| committer | Linus Torvalds <torvalds@linux-foundation.org> | 2014-08-06 09:38:14 -0700 |
| commit | ae045e2455429c418a418a3376301a9e5753a0a8 (patch) | |
| tree | b445bdeecd3f38aa0d0a29c9585cee49e4ccb0f1 /net | |
| parent | f4f142ed4ef835709c7e6d12eaca10d190bcebed (diff) | |
| parent | d247b6ab3ce6dd43665780865ec5fa145d9ab6bd (diff) | |
| download | lwn-ae045e2455429c418a418a3376301a9e5753a0a8.tar.gz lwn-ae045e2455429c418a418a3376301a9e5753a0a8.zip | |
Merge git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next
Pull networking updates from David Miller:
"Highlights:
1) Steady transitioning of the BPF instructure to a generic spot so
all kernel subsystems can make use of it, from Alexei Starovoitov.
2) SFC driver supports busy polling, from Alexandre Rames.
3) Take advantage of hash table in UDP multicast delivery, from David
Held.
4) Lighten locking, in particular by getting rid of the LRU lists, in
inet frag handling. From Florian Westphal.
5) Add support for various RFC6458 control messages in SCTP, from
Geir Ola Vaagland.
6) Allow to filter bridge forwarding database dumps by device, from
Jamal Hadi Salim.
7) virtio-net also now supports busy polling, from Jason Wang.
8) Some low level optimization tweaks in pktgen from Jesper Dangaard
Brouer.
9) Add support for ipv6 address generation modes, so that userland
can have some input into the process. From Jiri Pirko.
10) Consolidate common TCP connection request code in ipv4 and ipv6,
from Octavian Purdila.
11) New ARP packet logger in netfilter, from Pablo Neira Ayuso.
12) Generic resizable RCU hash table, with intial users in netlink and
nftables. From Thomas Graf.
13) Maintain a name assignment type so that userspace can see where a
network device name came from (enumerated by kernel, assigned
explicitly by userspace, etc.) From Tom Gundersen.
14) Automatic flow label generation on transmit in ipv6, from Tom
Herbert.
15) New packet timestamping facilities from Willem de Bruijn, meant to
assist in measuring latencies going into/out-of the packet
scheduler, latency from TCP data transmission to ACK, etc"
* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next: (1536 commits)
cxgb4 : Disable recursive mailbox commands when enabling vi
net: reduce USB network driver config options.
tg3: Modify tg3_tso_bug() to handle multiple TX rings
amd-xgbe: Perform phy connect/disconnect at dev open/stop
amd-xgbe: Use dma_set_mask_and_coherent to set DMA mask
net: sun4i-emac: fix memory leak on bad packet
sctp: fix possible seqlock seadlock in sctp_packet_transmit()
Revert "net: phy: Set the driver when registering an MDIO bus device"
cxgb4vf: Turn off SGE RX/TX Callback Timers and interrupts in PCI shutdown routine
team: Simplify return path of team_newlink
bridge: Update outdated comment on promiscuous mode
net-timestamp: ACK timestamp for bytestreams
net-timestamp: TCP timestamping
net-timestamp: SCHED timestamp on entering packet scheduler
net-timestamp: add key to disambiguate concurrent datagrams
net-timestamp: move timestamp flags out of sk_flags
net-timestamp: extend SCM_TIMESTAMPING ancillary data struct
cxgb4i : Move stray CPL definitions to cxgb4 driver
tcp: reduce spurious retransmits due to transient SACK reneging
qlcnic: Initialize dcbnl_ops before register_netdev
...
Diffstat (limited to 'net')
321 files changed, 14000 insertions, 11796 deletions
diff --git a/net/6lowpan/Kconfig b/net/6lowpan/Kconfig new file mode 100644 index 000000000000..028a5c6d1f61 --- /dev/null +++ b/net/6lowpan/Kconfig @@ -0,0 +1,6 @@ +config 6LOWPAN + bool "6LoWPAN Support" + depends on IPV6 + ---help--- + This enables IPv6 over Low power Wireless Personal Area Network - + "6LoWPAN" which is supported by IEEE 802.15.4 or Bluetooth stacks. diff --git a/net/6lowpan/Makefile b/net/6lowpan/Makefile new file mode 100644 index 000000000000..415886bb456a --- /dev/null +++ b/net/6lowpan/Makefile @@ -0,0 +1,3 @@ +obj-$(CONFIG_6LOWPAN) := 6lowpan.o + +6lowpan-y := iphc.o diff --git a/net/ieee802154/6lowpan_iphc.c b/net/6lowpan/iphc.c index 211b5686d719..142eef55c9e2 100644 --- a/net/ieee802154/6lowpan_iphc.c +++ b/net/6lowpan/iphc.c @@ -3,8 +3,7 @@ * written by Alexander Smirnov <alex.bluesman.smirnov@gmail.com> */ -/* - * Based on patches from Jon Smirl <jonsmirl@gmail.com> +/* Based on patches from Jon Smirl <jonsmirl@gmail.com> * Copyright (c) 2011 Jon Smirl <jonsmirl@gmail.com> * * This program is free software; you can redistribute it and/or modify @@ -58,16 +57,15 @@ #include <net/ipv6.h> #include <net/af_ieee802154.h> -/* - * Uncompress address function for source and +/* Uncompress address function for source and * destination address(non-multicast). * * address_mode is sam value or dam value. */ static int uncompress_addr(struct sk_buff *skb, - struct in6_addr *ipaddr, const u8 address_mode, - const u8 *lladdr, const u8 addr_type, - const u8 addr_len) + struct in6_addr *ipaddr, const u8 address_mode, + const u8 *lladdr, const u8 addr_type, + const u8 addr_len) { bool fail; @@ -140,13 +138,12 @@ static int uncompress_addr(struct sk_buff *skb, return 0; } -/* - * Uncompress address function for source context +/* Uncompress address function for source context * based address(non-multicast). */ static int uncompress_context_based_src_addr(struct sk_buff *skb, - struct in6_addr *ipaddr, - const u8 sam) + struct in6_addr *ipaddr, + const u8 sam) { switch (sam) { case LOWPAN_IPHC_ADDR_00: @@ -175,13 +172,13 @@ static int uncompress_context_based_src_addr(struct sk_buff *skb, } static int skb_deliver(struct sk_buff *skb, struct ipv6hdr *hdr, - struct net_device *dev, skb_delivery_cb deliver_skb) + struct net_device *dev, skb_delivery_cb deliver_skb) { struct sk_buff *new; int stat; new = skb_copy_expand(skb, sizeof(struct ipv6hdr), skb_tailroom(skb), - GFP_ATOMIC); + GFP_ATOMIC); kfree_skb(skb); if (!new) @@ -196,7 +193,7 @@ static int skb_deliver(struct sk_buff *skb, struct ipv6hdr *hdr, new->dev = dev; raw_dump_table(__func__, "raw skb data dump before receiving", - new->data, new->len); + new->data, new->len); stat = deliver_skb(new, dev); @@ -208,10 +205,9 @@ static int skb_deliver(struct sk_buff *skb, struct ipv6hdr *hdr, /* Uncompress function for multicast destination address, * when M bit is set. */ -static int -lowpan_uncompress_multicast_daddr(struct sk_buff *skb, - struct in6_addr *ipaddr, - const u8 dam) +static int lowpan_uncompress_multicast_daddr(struct sk_buff *skb, + struct in6_addr *ipaddr, + const u8 dam) { bool fail; @@ -257,41 +253,41 @@ lowpan_uncompress_multicast_daddr(struct sk_buff *skb, } raw_dump_inline(NULL, "Reconstructed ipv6 multicast addr is", - ipaddr->s6_addr, 16); + ipaddr->s6_addr, 16); return 0; } -static int -uncompress_udp_header(struct sk_buff *skb, struct udphdr *uh) +static int uncompress_udp_header(struct sk_buff *skb, struct udphdr *uh) { bool fail; u8 tmp = 0, val = 0; - if (!uh) - goto err; - - fail = lowpan_fetch_skb(skb, &tmp, 1); + fail = lowpan_fetch_skb(skb, &tmp, sizeof(tmp)); if ((tmp & LOWPAN_NHC_UDP_MASK) == LOWPAN_NHC_UDP_ID) { pr_debug("UDP header uncompression\n"); switch (tmp & LOWPAN_NHC_UDP_CS_P_11) { case LOWPAN_NHC_UDP_CS_P_00: - fail |= lowpan_fetch_skb(skb, &uh->source, 2); - fail |= lowpan_fetch_skb(skb, &uh->dest, 2); + fail |= lowpan_fetch_skb(skb, &uh->source, + sizeof(uh->source)); + fail |= lowpan_fetch_skb(skb, &uh->dest, + sizeof(uh->dest)); break; case LOWPAN_NHC_UDP_CS_P_01: - fail |= lowpan_fetch_skb(skb, &uh->source, 2); - fail |= lowpan_fetch_skb(skb, &val, 1); + fail |= lowpan_fetch_skb(skb, &uh->source, + sizeof(uh->source)); + fail |= lowpan_fetch_skb(skb, &val, sizeof(val)); uh->dest = htons(val + LOWPAN_NHC_UDP_8BIT_PORT); break; case LOWPAN_NHC_UDP_CS_P_10: - fail |= lowpan_fetch_skb(skb, &val, 1); + fail |= lowpan_fetch_skb(skb, &val, sizeof(val)); uh->source = htons(val + LOWPAN_NHC_UDP_8BIT_PORT); - fail |= lowpan_fetch_skb(skb, &uh->dest, 2); + fail |= lowpan_fetch_skb(skb, &uh->dest, + sizeof(uh->dest)); break; case LOWPAN_NHC_UDP_CS_P_11: - fail |= lowpan_fetch_skb(skb, &val, 1); + fail |= lowpan_fetch_skb(skb, &val, sizeof(val)); uh->source = htons(LOWPAN_NHC_UDP_4BIT_PORT + (val >> 4)); uh->dest = htons(LOWPAN_NHC_UDP_4BIT_PORT + @@ -300,7 +296,6 @@ uncompress_udp_header(struct sk_buff *skb, struct udphdr *uh) default: pr_debug("ERROR: unknown UDP format\n"); goto err; - break; } pr_debug("uncompressed UDP ports: src = %d, dst = %d\n", @@ -311,11 +306,11 @@ uncompress_udp_header(struct sk_buff *skb, struct udphdr *uh) pr_debug_ratelimited("checksum elided currently not supported\n"); goto err; } else { - fail |= lowpan_fetch_skb(skb, &uh->check, 2); + fail |= lowpan_fetch_skb(skb, &uh->check, + sizeof(uh->check)); } - /* - * UDP lenght needs to be infered from the lower layers + /* UDP length needs to be infered from the lower layers * here, we obtain the hint from the remaining size of the * frame */ @@ -338,21 +333,21 @@ err: static const u8 lowpan_ttl_values[] = { 0, 1, 64, 255 }; int lowpan_process_data(struct sk_buff *skb, struct net_device *dev, - const u8 *saddr, const u8 saddr_type, const u8 saddr_len, - const u8 *daddr, const u8 daddr_type, const u8 daddr_len, - u8 iphc0, u8 iphc1, skb_delivery_cb deliver_skb) + const u8 *saddr, const u8 saddr_type, const u8 saddr_len, + const u8 *daddr, const u8 daddr_type, const u8 daddr_len, + u8 iphc0, u8 iphc1, skb_delivery_cb deliver_skb) { struct ipv6hdr hdr = {}; u8 tmp, num_context = 0; int err; raw_dump_table(__func__, "raw skb data dump uncompressed", - skb->data, skb->len); + skb->data, skb->len); /* another if the CID flag is set */ if (iphc1 & LOWPAN_IPHC_CID) { pr_debug("CID flag is set, increase header with one\n"); - if (lowpan_fetch_skb_u8(skb, &num_context)) + if (lowpan_fetch_skb(skb, &num_context, sizeof(num_context))) goto drop; } @@ -360,12 +355,11 @@ int lowpan_process_data(struct sk_buff *skb, struct net_device *dev, /* Traffic Class and Flow Label */ switch ((iphc0 & LOWPAN_IPHC_TF) >> 3) { - /* - * Traffic Class and FLow Label carried in-line + /* Traffic Class and FLow Label carried in-line * ECN + DSCP + 4-bit Pad + Flow Label (4 bytes) */ case 0: /* 00b */ - if (lowpan_fetch_skb_u8(skb, &tmp)) + if (lowpan_fetch_skb(skb, &tmp, sizeof(tmp))) goto drop; memcpy(&hdr.flow_lbl, &skb->data[0], 3); @@ -374,23 +368,21 @@ int lowpan_process_data(struct sk_buff *skb, struct net_device *dev, hdr.flow_lbl[0] = ((tmp >> 2) & 0x30) | (tmp << 6) | (hdr.flow_lbl[0] & 0x0f); break; - /* - * Traffic class carried in-line + /* Traffic class carried in-line * ECN + DSCP (1 byte), Flow Label is elided */ case 2: /* 10b */ - if (lowpan_fetch_skb_u8(skb, &tmp)) + if (lowpan_fetch_skb(skb, &tmp, sizeof(tmp))) goto drop; hdr.priority = ((tmp >> 2) & 0x0f); hdr.flow_lbl[0] = ((tmp << 6) & 0xC0) | ((tmp >> 2) & 0x30); break; - /* - * Flow Label carried in-line + /* Flow Label carried in-line * ECN + 2-bit Pad + Flow Label (3 bytes), DSCP is elided */ case 1: /* 01b */ - if (lowpan_fetch_skb_u8(skb, &tmp)) + if (lowpan_fetch_skb(skb, &tmp, sizeof(tmp))) goto drop; hdr.flow_lbl[0] = (skb->data[0] & 0x0F) | ((tmp >> 2) & 0x30); @@ -407,7 +399,7 @@ int lowpan_process_data(struct sk_buff *skb, struct net_device *dev, /* Next Header */ if ((iphc0 & LOWPAN_IPHC_NH_C) == 0) { /* Next header is carried inline */ - if (lowpan_fetch_skb_u8(skb, &(hdr.nexthdr))) + if (lowpan_fetch_skb(skb, &hdr.nexthdr, sizeof(hdr.nexthdr))) goto drop; pr_debug("NH flag is set, next header carried inline: %02x\n", @@ -415,10 +407,11 @@ int lowpan_process_data(struct sk_buff *skb, struct net_device *dev, } /* Hop Limit */ - if ((iphc0 & 0x03) != LOWPAN_IPHC_TTL_I) + if ((iphc0 & 0x03) != LOWPAN_IPHC_TTL_I) { hdr.hop_limit = lowpan_ttl_values[iphc0 & 0x03]; - else { - if (lowpan_fetch_skb_u8(skb, &(hdr.hop_limit))) + } else { + if (lowpan_fetch_skb(skb, &hdr.hop_limit, + sizeof(hdr.hop_limit))) goto drop; } @@ -428,13 +421,12 @@ int lowpan_process_data(struct sk_buff *skb, struct net_device *dev, if (iphc1 & LOWPAN_IPHC_SAC) { /* Source address context based uncompression */ pr_debug("SAC bit is set. Handle context based source address.\n"); - err = uncompress_context_based_src_addr( - skb, &hdr.saddr, tmp); + err = uncompress_context_based_src_addr(skb, &hdr.saddr, tmp); } else { /* Source address uncompression */ pr_debug("source address stateless compression\n"); err = uncompress_addr(skb, &hdr.saddr, tmp, saddr, - saddr_type, saddr_len); + saddr_type, saddr_len); } /* Check on error of previous branch */ @@ -450,16 +442,17 @@ int lowpan_process_data(struct sk_buff *skb, struct net_device *dev, pr_debug("dest: context-based mcast compression\n"); /* TODO: implement this */ } else { - err = lowpan_uncompress_multicast_daddr( - skb, &hdr.daddr, tmp); + err = lowpan_uncompress_multicast_daddr(skb, &hdr.daddr, + tmp); + if (err) goto drop; } } else { err = uncompress_addr(skb, &hdr.daddr, tmp, daddr, - daddr_type, daddr_len); + daddr_type, daddr_len); pr_debug("dest: stateless compression mode %d dest %pI6c\n", - tmp, &hdr.daddr); + tmp, &hdr.daddr); if (err) goto drop; } @@ -468,11 +461,11 @@ int lowpan_process_data(struct sk_buff *skb, struct net_device *dev, if (iphc0 & LOWPAN_IPHC_NH_C) { struct udphdr uh; struct sk_buff *new; + if (uncompress_udp_header(skb, &uh)) goto drop; - /* - * replace the compressed UDP head by the uncompressed UDP + /* replace the compressed UDP head by the uncompressed UDP * header */ new = skb_copy_expand(skb, sizeof(struct udphdr), @@ -489,7 +482,7 @@ int lowpan_process_data(struct sk_buff *skb, struct net_device *dev, skb_copy_to_linear_data(skb, &uh, sizeof(struct udphdr)); raw_dump_table(__func__, "raw UDP header dump", - (u8 *)&uh, sizeof(uh)); + (u8 *)&uh, sizeof(uh)); hdr.nexthdr = UIP_PROTO_UDP; } @@ -504,8 +497,7 @@ int lowpan_process_data(struct sk_buff *skb, struct net_device *dev, hdr.version, ntohs(hdr.payload_len), hdr.nexthdr, hdr.hop_limit, &hdr.daddr); - raw_dump_table(__func__, "raw header dump", (u8 *)&hdr, - sizeof(hdr)); + raw_dump_table(__func__, "raw header dump", (u8 *)&hdr, sizeof(hdr)); return skb_deliver(skb, &hdr, dev, deliver_skb); @@ -515,9 +507,9 @@ drop: } EXPORT_SYMBOL_GPL(lowpan_process_data); -static u8 lowpan_compress_addr_64(u8 **hc06_ptr, u8 shift, - const struct in6_addr *ipaddr, - const unsigned char *lladdr) +static u8 lowpan_compress_addr_64(u8 **hc_ptr, u8 shift, + const struct in6_addr *ipaddr, + const unsigned char *lladdr) { u8 val = 0; @@ -526,24 +518,22 @@ static u8 lowpan_compress_addr_64(u8 **hc06_ptr, u8 shift, pr_debug("address compression 0 bits\n"); } else if (lowpan_is_iid_16_bit_compressable(ipaddr)) { /* compress IID to 16 bits xxxx::XXXX */ - memcpy(*hc06_ptr, &ipaddr->s6_addr16[7], 2); - *hc06_ptr += 2; + lowpan_push_hc_data(hc_ptr, &ipaddr->s6_addr16[7], 2); val = 2; /* 16-bits */ raw_dump_inline(NULL, "Compressed ipv6 addr is (16 bits)", - *hc06_ptr - 2, 2); + *hc_ptr - 2, 2); } else { /* do not compress IID => xxxx::IID */ - memcpy(*hc06_ptr, &ipaddr->s6_addr16[4], 8); - *hc06_ptr += 8; + lowpan_push_hc_data(hc_ptr, &ipaddr->s6_addr16[4], 8); val = 1; /* 64-bits */ raw_dump_inline(NULL, "Compressed ipv6 addr is (64 bits)", - *hc06_ptr - 8, 8); + *hc_ptr - 8, 8); } return rol8(val, shift); } -static void compress_udp_header(u8 **hc06_ptr, struct sk_buff *skb) +static void compress_udp_header(u8 **hc_ptr, struct sk_buff *skb) { struct udphdr *uh = udp_hdr(skb); u8 tmp; @@ -555,75 +545,75 @@ static void compress_udp_header(u8 **hc06_ptr, struct sk_buff *skb) pr_debug("UDP header: both ports compression to 4 bits\n"); /* compression value */ tmp = LOWPAN_NHC_UDP_CS_P_11; - lowpan_push_hc_data(hc06_ptr, &tmp, sizeof(tmp)); + lowpan_push_hc_data(hc_ptr, &tmp, sizeof(tmp)); /* source and destination port */ tmp = ntohs(uh->dest) - LOWPAN_NHC_UDP_4BIT_PORT + ((ntohs(uh->source) - LOWPAN_NHC_UDP_4BIT_PORT) << 4); - lowpan_push_hc_data(hc06_ptr, &tmp, sizeof(tmp)); + lowpan_push_hc_data(hc_ptr, &tmp, sizeof(tmp)); } else if ((ntohs(uh->dest) & LOWPAN_NHC_UDP_8BIT_MASK) == LOWPAN_NHC_UDP_8BIT_PORT) { pr_debug("UDP header: remove 8 bits of dest\n"); /* compression value */ tmp = LOWPAN_NHC_UDP_CS_P_01; - lowpan_push_hc_data(hc06_ptr, &tmp, sizeof(tmp)); + lowpan_push_hc_data(hc_ptr, &tmp, sizeof(tmp)); /* source port */ - lowpan_push_hc_data(hc06_ptr, &uh->source, sizeof(uh->source)); + lowpan_push_hc_data(hc_ptr, &uh->source, sizeof(uh->source)); /* destination port */ tmp = ntohs(uh->dest) - LOWPAN_NHC_UDP_8BIT_PORT; - lowpan_push_hc_data(hc06_ptr, &tmp, sizeof(tmp)); + lowpan_push_hc_data(hc_ptr, &tmp, sizeof(tmp)); } else if ((ntohs(uh->source) & LOWPAN_NHC_UDP_8BIT_MASK) == LOWPAN_NHC_UDP_8BIT_PORT) { pr_debug("UDP header: remove 8 bits of source\n"); /* compression value */ tmp = LOWPAN_NHC_UDP_CS_P_10; - lowpan_push_hc_data(hc06_ptr, &tmp, sizeof(tmp)); + lowpan_push_hc_data(hc_ptr, &tmp, sizeof(tmp)); /* source port */ tmp = ntohs(uh->source) - LOWPAN_NHC_UDP_8BIT_PORT; - lowpan_push_hc_data(hc06_ptr, &tmp, sizeof(tmp)); + lowpan_push_hc_data(hc_ptr, &tmp, sizeof(tmp)); /* destination port */ - lowpan_push_hc_data(hc06_ptr, &uh->dest, sizeof(uh->dest)); + lowpan_push_hc_data(hc_ptr, &uh->dest, sizeof(uh->dest)); } else { pr_debug("UDP header: can't compress\n"); /* compression value */ tmp = LOWPAN_NHC_UDP_CS_P_00; - lowpan_push_hc_data(hc06_ptr, &tmp, sizeof(tmp)); + lowpan_push_hc_data(hc_ptr, &tmp, sizeof(tmp)); /* source port */ - lowpan_push_hc_data(hc06_ptr, &uh->source, sizeof(uh->source)); + lowpan_push_hc_data(hc_ptr, &uh->source, sizeof(uh->source)); /* destination port */ - lowpan_push_hc_data(hc06_ptr, &uh->dest, sizeof(uh->dest)); + lowpan_push_hc_data(hc_ptr, &uh->dest, sizeof(uh->dest)); } /* checksum is always inline */ - lowpan_push_hc_data(hc06_ptr, &uh->check, sizeof(uh->check)); + lowpan_push_hc_data(hc_ptr, &uh->check, sizeof(uh->check)); /* skip the UDP header */ skb_pull(skb, sizeof(struct udphdr)); } int lowpan_header_compress(struct sk_buff *skb, struct net_device *dev, - unsigned short type, const void *_daddr, - const void *_saddr, unsigned int len) + unsigned short type, const void *_daddr, + const void *_saddr, unsigned int len) { - u8 tmp, iphc0, iphc1, *hc06_ptr; + u8 tmp, iphc0, iphc1, *hc_ptr; struct ipv6hdr *hdr; u8 head[100] = {}; + int addr_type; if (type != ETH_P_IPV6) return -EINVAL; hdr = ipv6_hdr(skb); - hc06_ptr = head + 2; + hc_ptr = head + 2; pr_debug("IPv6 header dump:\n\tversion = %d\n\tlength = %d\n" "\tnexthdr = 0x%02x\n\thop_lim = %d\n\tdest = %pI6c\n", - hdr->version, ntohs(hdr->payload_len), hdr->nexthdr, - hdr->hop_limit, &hdr->daddr); + hdr->version, ntohs(hdr->payload_len), hdr->nexthdr, + hdr->hop_limit, &hdr->daddr); raw_dump_table(__func__, "raw skb network header dump", - skb_network_header(skb), sizeof(struct ipv6hdr)); + skb_network_header(skb), sizeof(struct ipv6hdr)); - /* - * As we copy some bit-length fields, in the IPHC encoding bytes, + /* As we copy some bit-length fields, in the IPHC encoding bytes, * we sometimes use |= * If the field is 0, and the current bit value in memory is 1, * this does not work. We therefore reset the IPHC encoding here @@ -638,49 +628,47 @@ int lowpan_header_compress(struct sk_buff *skb, struct net_device *dev, raw_dump_inline(__func__, "daddr", (unsigned char *)_daddr, IEEE802154_ADDR_LEN); - raw_dump_table(__func__, - "sending raw skb network uncompressed packet", - skb->data, skb->len); + raw_dump_table(__func__, "sending raw skb network uncompressed packet", + skb->data, skb->len); - /* - * Traffic class, flow label + /* Traffic class, flow label * If flow label is 0, compress it. If traffic class is 0, compress it * We have to process both in the same time as the offset of traffic * class depends on the presence of version and flow label */ - /* hc06 format of TC is ECN | DSCP , original one is DSCP | ECN */ + /* hc format of TC is ECN | DSCP , original one is DSCP | ECN */ tmp = (hdr->priority << 4) | (hdr->flow_lbl[0] >> 4); tmp = ((tmp & 0x03) << 6) | (tmp >> 2); if (((hdr->flow_lbl[0] & 0x0F) == 0) && - (hdr->flow_lbl[1] == 0) && (hdr->flow_lbl[2] == 0)) { + (hdr->flow_lbl[1] == 0) && (hdr->flow_lbl[2] == 0)) { /* flow label can be compressed */ iphc0 |= LOWPAN_IPHC_FL_C; if ((hdr->priority == 0) && - ((hdr->flow_lbl[0] & 0xF0) == 0)) { + ((hdr->flow_lbl[0] & 0xF0) == 0)) { /* compress (elide) all */ iphc0 |= LOWPAN_IPHC_TC_C; } else { /* compress only the flow label */ - *hc06_ptr = tmp; - hc06_ptr += 1; + *hc_ptr = tmp; + hc_ptr += 1; } } else { /* Flow label cannot be compressed */ if ((hdr->priority == 0) && - ((hdr->flow_lbl[0] & 0xF0) == 0)) { + ((hdr->flow_lbl[0] & 0xF0) == 0)) { /* compress only traffic class */ iphc0 |= LOWPAN_IPHC_TC_C; - *hc06_ptr = (tmp & 0xc0) | (hdr->flow_lbl[0] & 0x0F); - memcpy(hc06_ptr + 1, &hdr->flow_lbl[1], 2); - hc06_ptr += 3; + *hc_ptr = (tmp & 0xc0) | (hdr->flow_lbl[0] & 0x0F); + memcpy(hc_ptr + 1, &hdr->flow_lbl[1], 2); + hc_ptr += 3; } else { /* compress nothing */ - memcpy(hc06_ptr, hdr, 4); + memcpy(hc_ptr, hdr, 4); /* replace the top byte with new ECN | DSCP format */ - *hc06_ptr = tmp; - hc06_ptr += 4; + *hc_ptr = tmp; + hc_ptr += 4; } } @@ -690,13 +678,11 @@ int lowpan_header_compress(struct sk_buff *skb, struct net_device *dev, if (hdr->nexthdr == UIP_PROTO_UDP) iphc0 |= LOWPAN_IPHC_NH_C; - if ((iphc0 & LOWPAN_IPHC_NH_C) == 0) { - *hc06_ptr = hdr->nexthdr; - hc06_ptr += 1; - } + if ((iphc0 & LOWPAN_IPHC_NH_C) == 0) + lowpan_push_hc_data(&hc_ptr, &hdr->nexthdr, + sizeof(hdr->nexthdr)); - /* - * Hop limit + /* Hop limit * if 1: compress, encoding is 01 * if 64: compress, encoding is 10 * if 255: compress, encoding is 11 @@ -713,87 +699,89 @@ int lowpan_header_compress(struct sk_buff *skb, struct net_device *dev, iphc0 |= LOWPAN_IPHC_TTL_255; break; default: - *hc06_ptr = hdr->hop_limit; - hc06_ptr += 1; - break; + lowpan_push_hc_data(&hc_ptr, &hdr->hop_limit, + sizeof(hdr->hop_limit)); } + addr_type = ipv6_addr_type(&hdr->saddr); /* source address compression */ - if (is_addr_unspecified(&hdr->saddr)) { + if (addr_type == IPV6_ADDR_ANY) { pr_debug("source address is unspecified, setting SAC\n"); iphc1 |= LOWPAN_IPHC_SAC; - /* TODO: context lookup */ - } else if (is_addr_link_local(&hdr->saddr)) { - iphc1 |= lowpan_compress_addr_64(&hc06_ptr, - LOWPAN_IPHC_SAM_BIT, &hdr->saddr, _saddr); - pr_debug("source address unicast link-local %pI6c " - "iphc1 0x%02x\n", &hdr->saddr, iphc1); } else { - pr_debug("send the full source address\n"); - memcpy(hc06_ptr, &hdr->saddr.s6_addr16[0], 16); - hc06_ptr += 16; + if (addr_type & IPV6_ADDR_LINKLOCAL) { + iphc1 |= lowpan_compress_addr_64(&hc_ptr, + LOWPAN_IPHC_SAM_BIT, + &hdr->saddr, _saddr); + pr_debug("source address unicast link-local %pI6c iphc1 0x%02x\n", + &hdr->saddr, iphc1); + } else { + pr_debug("send the full source address\n"); + lowpan_push_hc_data(&hc_ptr, hdr->saddr.s6_addr, 16); + } } + addr_type = ipv6_addr_type(&hdr->daddr); /* destination address compression */ - if (is_addr_mcast(&hdr->daddr)) { + if (addr_type & IPV6_ADDR_MULTICAST) { pr_debug("destination address is multicast: "); iphc1 |= LOWPAN_IPHC_M; if (lowpan_is_mcast_addr_compressable8(&hdr->daddr)) { pr_debug("compressed to 1 octet\n"); iphc1 |= LOWPAN_IPHC_DAM_11; /* use last byte */ - *hc06_ptr = hdr->daddr.s6_addr[15]; - hc06_ptr += 1; + lowpan_push_hc_data(&hc_ptr, + &hdr->daddr.s6_addr[15], 1); } else if (lowpan_is_mcast_addr_compressable32(&hdr->daddr)) { pr_debug("compressed to 4 octets\n"); iphc1 |= LOWPAN_IPHC_DAM_10; /* second byte + the last three */ - *hc06_ptr = hdr->daddr.s6_addr[1]; - memcpy(hc06_ptr + 1, &hdr->daddr.s6_addr[13], 3); - hc06_ptr += 4; + lowpan_push_hc_data(&hc_ptr, + &hdr->daddr.s6_addr[1], 1); + lowpan_push_hc_data(&hc_ptr, + &hdr->daddr.s6_addr[13], 3); } else if (lowpan_is_mcast_addr_compressable48(&hdr->daddr)) { pr_debug("compressed to 6 octets\n"); iphc1 |= LOWPAN_IPHC_DAM_01; /* second byte + the last five */ - *hc06_ptr = hdr->daddr.s6_addr[1]; - memcpy(hc06_ptr + 1, &hdr->daddr.s6_addr[11], 5); - hc06_ptr += 6; + lowpan_push_hc_data(&hc_ptr, + &hdr->daddr.s6_addr[1], 1); + lowpan_push_hc_data(&hc_ptr, + &hdr->daddr.s6_addr[11], 5); } else { pr_debug("using full address\n"); iphc1 |= LOWPAN_IPHC_DAM_00; - memcpy(hc06_ptr, &hdr->daddr.s6_addr[0], 16); - hc06_ptr += 16; + lowpan_push_hc_data(&hc_ptr, hdr->daddr.s6_addr, 16); } } else { - /* TODO: context lookup */ - if (is_addr_link_local(&hdr->daddr)) { - iphc1 |= lowpan_compress_addr_64(&hc06_ptr, + if (addr_type & IPV6_ADDR_LINKLOCAL) { + /* TODO: context lookup */ + iphc1 |= lowpan_compress_addr_64(&hc_ptr, LOWPAN_IPHC_DAM_BIT, &hdr->daddr, _daddr); pr_debug("dest address unicast link-local %pI6c " - "iphc1 0x%02x\n", &hdr->daddr, iphc1); + "iphc1 0x%02x\n", &hdr->daddr, iphc1); } else { pr_debug("dest address unicast %pI6c\n", &hdr->daddr); - memcpy(hc06_ptr, &hdr->daddr.s6_addr16[0], 16); - hc06_ptr += 16; + lowpan_push_hc_data(&hc_ptr, hdr->daddr.s6_addr, 16); } } /* UDP header compression */ if (hdr->nexthdr == UIP_PROTO_UDP) - compress_udp_header(&hc06_ptr, skb); + compress_udp_header(&hc_ptr, skb); head[0] = iphc0; head[1] = iphc1; skb_pull(skb, sizeof(struct ipv6hdr)); skb_reset_transport_header(skb); - memcpy(skb_push(skb, hc06_ptr - head), head, hc06_ptr - head); + memcpy(skb_push(skb, hc_ptr - head), head, hc_ptr - head); skb_reset_network_header(skb); - pr_debug("header len %d skb %u\n", (int)(hc06_ptr - head), skb->len); + pr_debug("header len %d skb %u\n", (int)(hc_ptr - head), skb->len); raw_dump_table(__func__, "raw skb data dump compressed", - skb->data, skb->len); + skb->data, skb->len); return 0; } EXPORT_SYMBOL_GPL(lowpan_header_compress); diff --git a/net/802/fc.c b/net/802/fc.c index 05eea6b98bb8..7c174b6750cd 100644 --- a/net/802/fc.c +++ b/net/802/fc.c @@ -126,6 +126,6 @@ static void fc_setup(struct net_device *dev) */ struct net_device *alloc_fcdev(int sizeof_priv) { - return alloc_netdev(sizeof_priv, "fc%d", fc_setup); + return alloc_netdev(sizeof_priv, "fc%d", NET_NAME_UNKNOWN, fc_setup); } EXPORT_SYMBOL(alloc_fcdev); diff --git a/net/802/fddi.c b/net/802/fddi.c index 9cda40661e0d..59e7346f1193 100644 --- a/net/802/fddi.c +++ b/net/802/fddi.c @@ -207,7 +207,8 @@ static void fddi_setup(struct net_device *dev) */ struct net_device *alloc_fddidev(int sizeof_priv) { - return alloc_netdev(sizeof_priv, "fddi%d", fddi_setup); + return alloc_netdev(sizeof_priv, "fddi%d", NET_NAME_UNKNOWN, + fddi_setup); } EXPORT_SYMBOL(alloc_fddidev); diff --git a/net/802/hippi.c b/net/802/hippi.c index 5ff2a718ddca..2e03f8259dd5 100644 --- a/net/802/hippi.c +++ b/net/802/hippi.c @@ -228,7 +228,8 @@ static void hippi_setup(struct net_device *dev) struct net_device *alloc_hippi_dev(int sizeof_priv) { - return alloc_netdev(sizeof_priv, "hip%d", hippi_setup); + return alloc_netdev(sizeof_priv, "hip%d", NET_NAME_UNKNOWN, + hippi_setup); } EXPORT_SYMBOL(alloc_hippi_dev); diff --git a/net/8021q/vlan.c b/net/8021q/vlan.c index 44ebd5c2cd4a..64c6bed4a3d3 100644 --- a/net/8021q/vlan.c +++ b/net/8021q/vlan.c @@ -250,7 +250,8 @@ static int register_vlan_device(struct net_device *real_dev, u16 vlan_id) snprintf(name, IFNAMSIZ, "vlan%.4i", vlan_id); } - new_dev = alloc_netdev(sizeof(struct vlan_dev_priv), name, vlan_setup); + new_dev = alloc_netdev(sizeof(struct vlan_dev_priv), name, + NET_NAME_UNKNOWN, vlan_setup); if (new_dev == NULL) return -ENOBUFS; @@ -324,23 +325,24 @@ static void vlan_transfer_features(struct net_device *dev, netdev_update_features(vlandev); } -static void __vlan_device_event(struct net_device *dev, unsigned long event) +static int __vlan_device_event(struct net_device *dev, unsigned long event) { + int err = 0; + switch (event) { case NETDEV_CHANGENAME: vlan_proc_rem_dev(dev); - if (vlan_proc_add_dev(dev) < 0) - pr_warn("failed to change proc name for %s\n", - dev->name); + err = vlan_proc_add_dev(dev); break; case NETDEV_REGISTER: - if (vlan_proc_add_dev(dev) < 0) - pr_warn("failed to add proc entry for %s\n", dev->name); + err = vlan_proc_add_dev(dev); break; case NETDEV_UNREGISTER: vlan_proc_rem_dev(dev); break; } + + return err; } static int vlan_device_event(struct notifier_block *unused, unsigned long event, @@ -355,8 +357,12 @@ static int vlan_device_event(struct notifier_block *unused, unsigned long event, bool last = false; LIST_HEAD(list); - if (is_vlan_dev(dev)) - __vlan_device_event(dev, event); + if (is_vlan_dev(dev)) { + int err = __vlan_device_event(dev, event); + + if (err) + return notifier_from_errno(err); + } if ((event == NETDEV_UP) && (dev->features & NETIF_F_HW_VLAN_CTAG_FILTER)) { diff --git a/net/8021q/vlan_dev.c b/net/8021q/vlan_dev.c index dd11f612e03e..35a6b6b15e8a 100644 --- a/net/8021q/vlan_dev.c +++ b/net/8021q/vlan_dev.c @@ -385,6 +385,8 @@ static int vlan_dev_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd) case SIOCGMIIPHY: case SIOCGMIIREG: case SIOCSMIIREG: + case SIOCSHWTSTAMP: + case SIOCGHWTSTAMP: if (netif_device_present(real_dev) && ops->ndo_do_ioctl) err = ops->ndo_do_ioctl(real_dev, &ifrr, cmd); break; diff --git a/net/8021q/vlanproc.c b/net/8021q/vlanproc.c index 1d0e89213a28..ae63cf72a953 100644 --- a/net/8021q/vlanproc.c +++ b/net/8021q/vlanproc.c @@ -171,6 +171,8 @@ int vlan_proc_add_dev(struct net_device *vlandev) struct vlan_dev_priv *vlan = vlan_dev_priv(vlandev); struct vlan_net *vn = net_generic(dev_net(vlandev), vlan_net_id); + if (!strcmp(vlandev->name, name_conf)) + return -EINVAL; vlan->dent = proc_create_data(vlandev->name, S_IFREG|S_IRUSR|S_IWUSR, vn->proc_vlan_dir, &vlandev_fops, vlandev); diff --git a/net/9p/client.c b/net/9p/client.c index 0004cbaac4a4..e86a9bea1d16 100644 --- a/net/9p/client.c +++ b/net/9p/client.c @@ -959,7 +959,6 @@ static int p9_client_version(struct p9_client *c) break; default: return -EINVAL; - break; } if (IS_ERR(req)) diff --git a/net/Kconfig b/net/Kconfig index d92afe4204d9..4051fdfa4367 100644 --- a/net/Kconfig +++ b/net/Kconfig @@ -214,6 +214,7 @@ source "drivers/net/appletalk/Kconfig" source "net/x25/Kconfig" source "net/lapb/Kconfig" source "net/phonet/Kconfig" +source "net/6lowpan/Kconfig" source "net/ieee802154/Kconfig" source "net/mac802154/Kconfig" source "net/sched/Kconfig" diff --git a/net/Makefile b/net/Makefile index cbbbe6d657ca..7ed1970074b0 100644 --- a/net/Makefile +++ b/net/Makefile @@ -57,7 +57,8 @@ obj-$(CONFIG_CAIF) += caif/ ifneq ($(CONFIG_DCB),) obj-y += dcb/ endif -obj-y += ieee802154/ +obj-$(CONFIG_6LOWPAN) += 6lowpan/ +obj-$(CONFIG_IEEE802154) += ieee802154/ obj-$(CONFIG_MAC802154) += mac802154/ ifeq ($(CONFIG_NET),y) diff --git a/net/appletalk/ddp.c b/net/appletalk/ddp.c index bfcf6be1d665..c00897f65a31 100644 --- a/net/appletalk/ddp.c +++ b/net/appletalk/ddp.c @@ -1805,7 +1805,7 @@ static int atalk_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg) long amount = 0; if (skb) - amount = skb->len - sizeof(struct ddpehdr); + amount = skb->len - sizeof(struct ddpehdr); rc = put_user(amount, (int __user *)argp); break; } diff --git a/net/appletalk/dev.c b/net/appletalk/dev.c index 6c8016f61866..e4158b8b926d 100644 --- a/net/appletalk/dev.c +++ b/net/appletalk/dev.c @@ -39,6 +39,7 @@ static void ltalk_setup(struct net_device *dev) struct net_device *alloc_ltalkdev(int sizeof_priv) { - return alloc_netdev(sizeof_priv, "lt%d", ltalk_setup); + return alloc_netdev(sizeof_priv, "lt%d", NET_NAME_UNKNOWN, + ltalk_setup); } EXPORT_SYMBOL(alloc_ltalkdev); diff --git a/net/atm/br2684.c b/net/atm/br2684.c index 403e71fa88fe..cc78538d163b 100644 --- a/net/atm/br2684.c +++ b/net/atm/br2684.c @@ -682,8 +682,8 @@ static int br2684_create(void __user *arg) netdev = alloc_netdev(sizeof(struct br2684_dev), ni.ifname[0] ? ni.ifname : "nas%d", - (payload == p_routed) ? - br2684_setup_routed : br2684_setup); + NET_NAME_UNKNOWN, + (payload == p_routed) ? br2684_setup_routed : br2684_setup); if (!netdev) return -ENOMEM; diff --git a/net/atm/clip.c b/net/atm/clip.c index ba291ce4bdff..46339040fef0 100644 --- a/net/atm/clip.c +++ b/net/atm/clip.c @@ -520,7 +520,8 @@ static int clip_create(int number) if (PRIV(dev)->number >= number) number = PRIV(dev)->number + 1; } - dev = alloc_netdev(sizeof(struct clip_priv), "", clip_setup); + dev = alloc_netdev(sizeof(struct clip_priv), "", NET_NAME_UNKNOWN, + clip_setup); if (!dev) return -ENOMEM; clip_priv = PRIV(dev); diff --git a/net/batman-adv/bat_iv_ogm.c b/net/batman-adv/bat_iv_ogm.c index f04224c32005..1e8053976e83 100644 --- a/net/batman-adv/bat_iv_ogm.c +++ b/net/batman-adv/bat_iv_ogm.c @@ -108,14 +108,15 @@ static int batadv_iv_ogm_orig_add_if(struct batadv_orig_node *orig_node, int max_if_num) { void *data_ptr; - size_t data_size, old_size; + size_t old_size; int ret = -ENOMEM; spin_lock_bh(&orig_node->bat_iv.ogm_cnt_lock); - data_size = max_if_num * sizeof(unsigned long) * BATADV_NUM_WORDS; old_size = (max_if_num - 1) * sizeof(unsigned long) * BATADV_NUM_WORDS; - data_ptr = kmalloc(data_size, GFP_ATOMIC); + data_ptr = kmalloc_array(max_if_num, + BATADV_NUM_WORDS * sizeof(unsigned long), + GFP_ATOMIC); if (!data_ptr) goto unlock; @@ -123,7 +124,7 @@ static int batadv_iv_ogm_orig_add_if(struct batadv_orig_node *orig_node, kfree(orig_node->bat_iv.bcast_own); orig_node->bat_iv.bcast_own = data_ptr; - data_ptr = kmalloc(max_if_num * sizeof(uint8_t), GFP_ATOMIC); + data_ptr = kmalloc_array(max_if_num, sizeof(uint8_t), GFP_ATOMIC); if (!data_ptr) { kfree(orig_node->bat_iv.bcast_own); goto unlock; @@ -164,7 +165,7 @@ static int batadv_iv_ogm_orig_del_if(struct batadv_orig_node *orig_node, goto free_bcast_own; chunk_size = sizeof(unsigned long) * BATADV_NUM_WORDS; - data_ptr = kmalloc(max_if_num * chunk_size, GFP_ATOMIC); + data_ptr = kmalloc_array(max_if_num, chunk_size, GFP_ATOMIC); if (!data_ptr) goto unlock; @@ -183,7 +184,7 @@ free_bcast_own: if (max_if_num == 0) goto free_own_sum; - data_ptr = kmalloc(max_if_num * sizeof(uint8_t), GFP_ATOMIC); + data_ptr = kmalloc_array(max_if_num, sizeof(uint8_t), GFP_ATOMIC); if (!data_ptr) { kfree(orig_node->bat_iv.bcast_own); goto unlock; diff --git a/net/batman-adv/distributed-arp-table.c b/net/batman-adv/distributed-arp-table.c index f2c066b21716..b5981113c9a7 100644 --- a/net/batman-adv/distributed-arp-table.c +++ b/net/batman-adv/distributed-arp-table.c @@ -537,7 +537,8 @@ batadv_dat_select_candidates(struct batadv_priv *bat_priv, __be32 ip_dst) if (!bat_priv->orig_hash) return NULL; - res = kmalloc(BATADV_DAT_CANDIDATES_NUM * sizeof(*res), GFP_ATOMIC); + res = kmalloc_array(BATADV_DAT_CANDIDATES_NUM, sizeof(*res), + GFP_ATOMIC); if (!res) return NULL; diff --git a/net/batman-adv/fragmentation.c b/net/batman-adv/fragmentation.c index f14e54a05691..022d18ab27a6 100644 --- a/net/batman-adv/fragmentation.c +++ b/net/batman-adv/fragmentation.c @@ -128,6 +128,7 @@ static bool batadv_frag_insert_packet(struct batadv_orig_node *orig_node, { struct batadv_frag_table_entry *chain; struct batadv_frag_list_entry *frag_entry_new = NULL, *frag_entry_curr; + struct batadv_frag_list_entry *frag_entry_last = NULL; struct batadv_frag_packet *frag_packet; uint8_t bucket; uint16_t seqno, hdr_size = sizeof(struct batadv_frag_packet); @@ -180,11 +181,14 @@ static bool batadv_frag_insert_packet(struct batadv_orig_node *orig_node, ret = true; goto out; } + + /* store current entry because it could be the last in list */ + frag_entry_last = frag_entry_curr; } - /* Reached the end of the list, so insert after 'frag_entry_curr'. */ - if (likely(frag_entry_curr)) { - hlist_add_after(&frag_entry_curr->list, &frag_entry_new->list); + /* Reached the end of the list, so insert after 'frag_entry_last'. */ + if (likely(frag_entry_last)) { + hlist_add_after(&frag_entry_last->list, &frag_entry_new->list); chain->size += skb->len - hdr_size; chain->timestamp = jiffies; ret = true; diff --git a/net/batman-adv/hash.c b/net/batman-adv/hash.c index 63bdf7e94f1e..7c1c63080e20 100644 --- a/net/batman-adv/hash.c +++ b/net/batman-adv/hash.c @@ -46,12 +46,12 @@ struct batadv_hashtable *batadv_hash_new(uint32_t size) if (!hash) return NULL; - hash->table = kmalloc(sizeof(*hash->table) * size, GFP_ATOMIC); + hash->table = kmalloc_array(size, sizeof(*hash->table), GFP_ATOMIC); if (!hash->table) goto free_hash; - hash->list_locks = kmalloc(sizeof(*hash->list_locks) * size, - GFP_ATOMIC); + hash->list_locks = kmalloc_array(size, sizeof(*hash->list_locks), + GFP_ATOMIC); if (!hash->list_locks) goto free_table; diff --git a/net/batman-adv/main.h b/net/batman-adv/main.h index 118b990bae25..a1fcd884f0b1 100644 --- a/net/batman-adv/main.h +++ b/net/batman-adv/main.h @@ -24,7 +24,7 @@ #define BATADV_DRIVER_DEVICE "batman-adv" #ifndef BATADV_SOURCE_VERSION -#define BATADV_SOURCE_VERSION "2014.3.0" +#define BATADV_SOURCE_VERSION "2014.4.0" #endif /* B.A.T.M.A.N. parameters */ @@ -238,21 +238,29 @@ enum batadv_dbg_level { int batadv_debug_log(struct batadv_priv *bat_priv, const char *fmt, ...) __printf(2, 3); -#define batadv_dbg(type, bat_priv, fmt, arg...) \ +/* possibly ratelimited debug output */ +#define _batadv_dbg(type, bat_priv, ratelimited, fmt, arg...) \ do { \ - if (atomic_read(&bat_priv->log_level) & type) \ + if (atomic_read(&bat_priv->log_level) & type && \ + (!ratelimited || net_ratelimit())) \ batadv_debug_log(bat_priv, fmt, ## arg);\ } \ while (0) #else /* !CONFIG_BATMAN_ADV_DEBUG */ -__printf(3, 4) -static inline void batadv_dbg(int type __always_unused, - struct batadv_priv *bat_priv __always_unused, - const char *fmt __always_unused, ...) +__printf(4, 5) +static inline void _batadv_dbg(int type __always_unused, + struct batadv_priv *bat_priv __always_unused, + int ratelimited __always_unused, + const char *fmt __always_unused, ...) { } #endif +#define batadv_dbg(type, bat_priv, arg...) \ + _batadv_dbg(type, bat_priv, 0, ## arg) +#define batadv_dbg_ratelimited(type, bat_priv, arg...) \ + _batadv_dbg(type, bat_priv, 1, ## arg) + #define batadv_info(net_dev, fmt, arg...) \ do { \ struct net_device *_netdev = (net_dev); \ diff --git a/net/batman-adv/routing.c b/net/batman-adv/routing.c index 35141534938e..35f76f2f7824 100644 --- a/net/batman-adv/routing.c +++ b/net/batman-adv/routing.c @@ -706,11 +706,11 @@ static int batadv_check_unicast_ttvn(struct batadv_priv *bat_priv, if (batadv_tt_local_client_is_roaming(bat_priv, ethhdr->h_dest, vid)) { if (batadv_reroute_unicast_packet(bat_priv, unicast_packet, ethhdr->h_dest, vid)) - net_ratelimited_function(batadv_dbg, BATADV_DBG_TT, - bat_priv, - "Rerouting unicast packet to %pM (dst=%pM): Local Roaming\n", - unicast_packet->dest, - ethhdr->h_dest); + batadv_dbg_ratelimited(BATADV_DBG_TT, + bat_priv, + "Rerouting unicast packet to %pM (dst=%pM): Local Roaming\n", + unicast_packet->dest, + ethhdr->h_dest); /* at this point the mesh destination should have been * substituted with the originator address found in the global * table. If not, let the packet go untouched anyway because @@ -752,10 +752,10 @@ static int batadv_check_unicast_ttvn(struct batadv_priv *bat_priv, */ if (batadv_reroute_unicast_packet(bat_priv, unicast_packet, ethhdr->h_dest, vid)) { - net_ratelimited_function(batadv_dbg, BATADV_DBG_TT, bat_priv, - "Rerouting unicast packet to %pM (dst=%pM): TTVN mismatch old_ttvn=%u new_ttvn=%u\n", - unicast_packet->dest, ethhdr->h_dest, - old_ttvn, curr_ttvn); + batadv_dbg_ratelimited(BATADV_DBG_TT, bat_priv, + "Rerouting unicast packet to %pM (dst=%pM): TTVN mismatch old_ttvn=%u new_ttvn=%u\n", + unicast_packet->dest, ethhdr->h_dest, + old_ttvn, curr_ttvn); return 1; } diff --git a/net/batman-adv/soft-interface.c b/net/batman-adv/soft-interface.c index cbd677f48c00..5467955eb27c 100644 --- a/net/batman-adv/soft-interface.c +++ b/net/batman-adv/soft-interface.c @@ -751,7 +751,7 @@ static int batadv_softif_init_late(struct net_device *dev) atomic_set(&bat_priv->gw.bandwidth_down, 100); atomic_set(&bat_priv->gw.bandwidth_up, 20); atomic_set(&bat_priv->orig_interval, 1000); - atomic_set(&bat_priv->hop_penalty, 15); + atomic_set(&bat_priv->hop_penalty, 30); #ifdef CONFIG_BATMAN_ADV_DEBUG atomic_set(&bat_priv->log_level, 0); #endif @@ -927,7 +927,7 @@ struct net_device *batadv_softif_create(const char *name) int ret; soft_iface = alloc_netdev(sizeof(struct batadv_priv), name, - batadv_softif_init_early); + NET_NAME_UNKNOWN, batadv_softif_init_early); if (!soft_iface) return NULL; diff --git a/net/batman-adv/sysfs.c b/net/batman-adv/sysfs.c index fc47baa888c5..f40cb0436eba 100644 --- a/net/batman-adv/sysfs.c +++ b/net/batman-adv/sysfs.c @@ -900,32 +900,24 @@ int batadv_throw_uevent(struct batadv_priv *bat_priv, enum batadv_uev_type type, bat_kobj = &bat_priv->soft_iface->dev.kobj; - uevent_env[0] = kmalloc(strlen(BATADV_UEV_TYPE_VAR) + - strlen(batadv_uev_type_str[type]) + 1, - GFP_ATOMIC); + uevent_env[0] = kasprintf(GFP_ATOMIC, + "%s%s", BATADV_UEV_TYPE_VAR, + batadv_uev_type_str[type]); if (!uevent_env[0]) goto out; - sprintf(uevent_env[0], "%s%s", BATADV_UEV_TYPE_VAR, - batadv_uev_type_str[type]); - - uevent_env[1] = kmalloc(strlen(BATADV_UEV_ACTION_VAR) + - strlen(batadv_uev_action_str[action]) + 1, - GFP_ATOMIC); + uevent_env[1] = kasprintf(GFP_ATOMIC, + "%s%s", BATADV_UEV_ACTION_VAR, + batadv_uev_action_str[action]); if (!uevent_env[1]) goto out; - sprintf(uevent_env[1], "%s%s", BATADV_UEV_ACTION_VAR, - batadv_uev_action_str[action]); - /* If the event is DEL, ignore the data field */ if (action != BATADV_UEV_DEL) { - uevent_env[2] = kmalloc(strlen(BATADV_UEV_DATA_VAR) + - strlen(data) + 1, GFP_ATOMIC); + uevent_env[2] = kasprintf(GFP_ATOMIC, + "%s%s", BATADV_UEV_DATA_VAR, data); if (!uevent_env[2]) goto out; - - sprintf(uevent_env[2], "%s%s", BATADV_UEV_DATA_VAR, data); } ret = kobject_uevent_env(bat_kobj, KOBJ_CHANGE, uevent_env); diff --git a/net/bluetooth/6lowpan.c b/net/bluetooth/6lowpan.c index 8796ffa08b43..206b65ccd5b8 100644 --- a/net/bluetooth/6lowpan.c +++ b/net/bluetooth/6lowpan.c @@ -1,5 +1,5 @@ /* - Copyright (c) 2013 Intel Corp. + Copyright (c) 2013-2014 Intel Corp. This program is free software; you can redistribute it and/or modify it under the terms of the GNU General Public License version 2 and @@ -14,6 +14,8 @@ #include <linux/if_arp.h> #include <linux/netdevice.h> #include <linux/etherdevice.h> +#include <linux/module.h> +#include <linux/debugfs.h> #include <net/ipv6.h> #include <net/ip6_route.h> @@ -25,16 +27,20 @@ #include <net/bluetooth/hci_core.h> #include <net/bluetooth/l2cap.h> -#include "6lowpan.h" - #include <net/6lowpan.h> /* for the compression support */ +#define VERSION "0.1" + +static struct dentry *lowpan_psm_debugfs; +static struct dentry *lowpan_control_debugfs; + #define IFACE_NAME_TEMPLATE "bt%d" #define EUI64_ADDR_LEN 8 struct skb_cb { struct in6_addr addr; - struct l2cap_conn *conn; + struct l2cap_chan *chan; + int status; }; #define lowpan_cb(skb) ((struct skb_cb *)((skb)->cb)) @@ -48,9 +54,19 @@ struct skb_cb { static LIST_HEAD(bt_6lowpan_devices); static DEFINE_RWLOCK(devices_lock); +/* If psm is set to 0 (default value), then 6lowpan is disabled. + * Other values are used to indicate a Protocol Service Multiplexer + * value for 6lowpan. + */ +static u16 psm_6lowpan; + +/* We are listening incoming connections via this channel + */ +static struct l2cap_chan *listen_chan; + struct lowpan_peer { struct list_head list; - struct l2cap_conn *conn; + struct l2cap_chan *chan; /* peer addresses in various formats */ unsigned char eui64_addr[EUI64_ADDR_LEN]; @@ -84,6 +100,8 @@ static inline bool peer_del(struct lowpan_dev *dev, struct lowpan_peer *peer) { list_del(&peer->list); + module_put(THIS_MODULE); + if (atomic_dec_and_test(&dev->peer_count)) { BT_DBG("last peer"); return true; @@ -101,13 +119,26 @@ static inline struct lowpan_peer *peer_lookup_ba(struct lowpan_dev *dev, ba, type); list_for_each_entry_safe(peer, tmp, &dev->peers, list) { - BT_DBG("addr %pMR type %d", - &peer->conn->hcon->dst, peer->conn->hcon->dst_type); + BT_DBG("dst addr %pMR dst type %d", + &peer->chan->dst, peer->chan->dst_type); - if (bacmp(&peer->conn->hcon->dst, ba)) + if (bacmp(&peer->chan->dst, ba)) continue; - if (type == peer->conn->hcon->dst_type) + if (type == peer->chan->dst_type) + return peer; + } + + return NULL; +} + +static inline struct lowpan_peer *peer_lookup_chan(struct lowpan_dev *dev, + struct l2cap_chan *chan) +{ + struct lowpan_peer *peer, *tmp; + + list_for_each_entry_safe(peer, tmp, &dev->peers, list) { + if (peer->chan == chan) return peer; } @@ -120,7 +151,7 @@ static inline struct lowpan_peer *peer_lookup_conn(struct lowpan_dev *dev, struct lowpan_peer *peer, *tmp; list_for_each_entry_safe(peer, tmp, &dev->peers, list) { - if (peer->conn == conn) + if (peer->chan->conn == conn) return peer; } @@ -176,16 +207,16 @@ static int give_skb_to_upper(struct sk_buff *skb, struct net_device *dev) return -ENOMEM; ret = netif_rx(skb_cp); - - BT_DBG("receive skb %d", ret); - if (ret < 0) + if (ret < 0) { + BT_DBG("receive skb %d", ret); return NET_RX_DROP; + } return ret; } static int process_data(struct sk_buff *skb, struct net_device *netdev, - struct l2cap_conn *conn) + struct l2cap_chan *chan) { const u8 *saddr, *daddr; u8 iphc0, iphc1; @@ -196,7 +227,7 @@ static int process_data(struct sk_buff *skb, struct net_device *netdev, dev = lowpan_dev(netdev); read_lock_irqsave(&devices_lock, flags); - peer = peer_lookup_conn(dev, conn); + peer = peer_lookup_chan(dev, chan); read_unlock_irqrestore(&devices_lock, flags); if (!peer) goto drop; @@ -225,7 +256,7 @@ drop: } static int recv_pkt(struct sk_buff *skb, struct net_device *dev, - struct l2cap_conn *conn) + struct l2cap_chan *chan) { struct sk_buff *local_skb; int ret; @@ -269,7 +300,7 @@ static int recv_pkt(struct sk_buff *skb, struct net_device *dev, if (!local_skb) goto drop; - ret = process_data(local_skb, dev, conn); + ret = process_data(local_skb, dev, chan); if (ret != NET_RX_SUCCESS) goto drop; @@ -286,147 +317,39 @@ static int recv_pkt(struct sk_buff *skb, struct net_device *dev, return NET_RX_SUCCESS; drop: + dev->stats.rx_dropped++; kfree_skb(skb); return NET_RX_DROP; } /* Packet from BT LE device */ -int bt_6lowpan_recv(struct l2cap_conn *conn, struct sk_buff *skb) +static int chan_recv_cb(struct l2cap_chan *chan, struct sk_buff *skb) { struct lowpan_dev *dev; struct lowpan_peer *peer; int err; - peer = lookup_peer(conn); + peer = lookup_peer(chan->conn); if (!peer) return -ENOENT; - dev = lookup_dev(conn); + dev = lookup_dev(chan->conn); if (!dev || !dev->netdev) return -ENOENT; - err = recv_pkt(skb, dev->netdev, conn); - BT_DBG("recv pkt %d", err); - - return err; -} - -static inline int skbuff_copy(void *msg, int len, int count, int mtu, - struct sk_buff *skb, struct net_device *dev) -{ - struct sk_buff **frag; - int sent = 0; - - memcpy(skb_put(skb, count), msg, count); - - sent += count; - msg += count; - len -= count; - - dev->stats.tx_bytes += count; - dev->stats.tx_packets++; - - raw_dump_table(__func__, "Sending", skb->data, skb->len); - - /* Continuation fragments (no L2CAP header) */ - frag = &skb_shinfo(skb)->frag_list; - while (len > 0) { - struct sk_buff *tmp; - - count = min_t(unsigned int, mtu, len); - - tmp = bt_skb_alloc(count, GFP_ATOMIC); - if (!tmp) - return -ENOMEM; - - *frag = tmp; - - memcpy(skb_put(*frag, count), msg, count); - - raw_dump_table(__func__, "Sending fragment", - (*frag)->data, count); - - (*frag)->priority = skb->priority; - - sent += count; - msg += count; - len -= count; - - skb->len += (*frag)->len; - skb->data_len += (*frag)->len; - - frag = &(*frag)->next; - - dev->stats.tx_bytes += count; - dev->stats.tx_packets++; + err = recv_pkt(skb, dev->netdev, chan); + if (err) { + BT_DBG("recv pkt %d", err); + err = -EAGAIN; } - return sent; -} - -static struct sk_buff *create_pdu(struct l2cap_conn *conn, void *msg, - size_t len, u32 priority, - struct net_device *dev) -{ - struct sk_buff *skb; - int err, count; - struct l2cap_hdr *lh; - - /* FIXME: This mtu check should be not needed and atm is only used for - * testing purposes - */ - if (conn->mtu > (L2CAP_LE_MIN_MTU + L2CAP_HDR_SIZE)) - conn->mtu = L2CAP_LE_MIN_MTU + L2CAP_HDR_SIZE; - - count = min_t(unsigned int, (conn->mtu - L2CAP_HDR_SIZE), len); - - BT_DBG("conn %p len %zu mtu %d count %d", conn, len, conn->mtu, count); - - skb = bt_skb_alloc(count + L2CAP_HDR_SIZE, GFP_ATOMIC); - if (!skb) - return ERR_PTR(-ENOMEM); - - skb->priority = priority; - - lh = (struct l2cap_hdr *)skb_put(skb, L2CAP_HDR_SIZE); - lh->cid = cpu_to_le16(L2CAP_FC_6LOWPAN); - lh->len = cpu_to_le16(len); - - err = skbuff_copy(msg, len, count, conn->mtu, skb, dev); - if (unlikely(err < 0)) { - kfree_skb(skb); - BT_DBG("skbuff copy %d failed", err); - return ERR_PTR(err); - } - - return skb; -} - -static int conn_send(struct l2cap_conn *conn, - void *msg, size_t len, u32 priority, - struct net_device *dev) -{ - struct sk_buff *skb; - - skb = create_pdu(conn, msg, len, priority, dev); - if (IS_ERR(skb)) - return -EINVAL; - - BT_DBG("conn %p skb %p len %d priority %u", conn, skb, skb->len, - skb->priority); - - hci_send_acl(conn->hchan, skb, ACL_START); - - return 0; + return err; } static u8 get_addr_type_from_eui64(u8 byte) { - /* Is universal(0) or local(1) bit, */ - if (byte & 0x02) - return ADDR_LE_DEV_RANDOM; - - return ADDR_LE_DEV_PUBLIC; + /* Is universal(0) or local(1) bit */ + return ((byte & 0x02) ? BDADDR_LE_RANDOM : BDADDR_LE_PUBLIC); } static void copy_to_bdaddr(struct in6_addr *ip6_daddr, bdaddr_t *addr) @@ -475,7 +398,7 @@ static int header_create(struct sk_buff *skb, struct net_device *netdev, if (ipv6_addr_is_multicast(&hdr->daddr)) { memcpy(&lowpan_cb(skb)->addr, &hdr->daddr, sizeof(struct in6_addr)); - lowpan_cb(skb)->conn = NULL; + lowpan_cb(skb)->chan = NULL; } else { unsigned long flags; @@ -484,9 +407,8 @@ static int header_create(struct sk_buff *skb, struct net_device *netdev, */ convert_dest_bdaddr(&hdr->daddr, &addr, &addr_type); - BT_DBG("dest addr %pMR type %s IP %pI6c", &addr, - addr_type == ADDR_LE_DEV_PUBLIC ? "PUBLIC" : "RANDOM", - &hdr->daddr); + BT_DBG("dest addr %pMR type %d IP %pI6c", &addr, + addr_type, &hdr->daddr); read_lock_irqsave(&devices_lock, flags); peer = peer_lookup_ba(dev, &addr, addr_type); @@ -501,7 +423,7 @@ static int header_create(struct sk_buff *skb, struct net_device *netdev, memcpy(&lowpan_cb(skb)->addr, &hdr->daddr, sizeof(struct in6_addr)); - lowpan_cb(skb)->conn = peer->conn; + lowpan_cb(skb)->chan = peer->chan; } saddr = dev->netdev->dev_addr; @@ -510,14 +432,42 @@ static int header_create(struct sk_buff *skb, struct net_device *netdev, } /* Packet to BT LE device */ -static int send_pkt(struct l2cap_conn *conn, const void *saddr, - const void *daddr, struct sk_buff *skb, +static int send_pkt(struct l2cap_chan *chan, struct sk_buff *skb, struct net_device *netdev) { - raw_dump_table(__func__, "raw skb data dump before fragmentation", - skb->data, skb->len); + struct msghdr msg; + struct kvec iv; + int err; + + /* Remember the skb so that we can send EAGAIN to the caller if + * we run out of credits. + */ + chan->data = skb; + + memset(&msg, 0, sizeof(msg)); + msg.msg_iov = (struct iovec *) &iv; + msg.msg_iovlen = 1; + iv.iov_base = skb->data; + iv.iov_len = skb->len; + + err = l2cap_chan_send(chan, &msg, skb->len); + if (err > 0) { + netdev->stats.tx_bytes += err; + netdev->stats.tx_packets++; + return 0; + } + + if (!err) + err = lowpan_cb(skb)->status; - return conn_send(conn, skb->data, skb->len, 0, netdev); + if (err < 0) { + if (err == -EAGAIN) + netdev->stats.tx_dropped++; + else + netdev->stats.tx_errors++; + } + + return err; } static void send_mcast_pkt(struct sk_buff *skb, struct net_device *netdev) @@ -540,8 +490,7 @@ static void send_mcast_pkt(struct sk_buff *skb, struct net_device *netdev) list_for_each_entry_safe(pentry, ptmp, &dev->peers, list) { local_skb = skb_clone(skb, GFP_ATOMIC); - send_pkt(pentry->conn, netdev->dev_addr, - pentry->eui64_addr, local_skb, netdev); + send_pkt(pentry->chan, local_skb, netdev); kfree_skb(local_skb); } @@ -553,7 +502,6 @@ static void send_mcast_pkt(struct sk_buff *skb, struct net_device *netdev) static netdev_tx_t bt_xmit(struct sk_buff *skb, struct net_device *netdev) { int err = 0; - unsigned char *eui64_addr; struct lowpan_dev *dev; struct lowpan_peer *peer; bdaddr_t addr; @@ -568,21 +516,20 @@ static netdev_tx_t bt_xmit(struct sk_buff *skb, struct net_device *netdev) unsigned long flags; convert_dest_bdaddr(&lowpan_cb(skb)->addr, &addr, &addr_type); - eui64_addr = lowpan_cb(skb)->addr.s6_addr + 8; dev = lowpan_dev(netdev); read_lock_irqsave(&devices_lock, flags); peer = peer_lookup_ba(dev, &addr, addr_type); read_unlock_irqrestore(&devices_lock, flags); - BT_DBG("xmit %s to %pMR type %s IP %pI6c peer %p", - netdev->name, &addr, - addr_type == ADDR_LE_DEV_PUBLIC ? "PUBLIC" : "RANDOM", + BT_DBG("xmit %s to %pMR type %d IP %pI6c peer %p", + netdev->name, &addr, addr_type, &lowpan_cb(skb)->addr, peer); - if (peer && peer->conn) - err = send_pkt(peer->conn, netdev->dev_addr, - eui64_addr, skb, netdev); + if (peer && peer->chan) + err = send_pkt(peer->chan, skb, netdev); + else + err = -ENOENT; } dev_kfree_skb(skb); @@ -634,7 +581,7 @@ static void set_addr(u8 *eui, u8 *addr, u8 addr_type) eui[7] = addr[0]; /* Universal/local bit set, BT 6lowpan draft ch. 3.2.1 */ - if (addr_type == ADDR_LE_DEV_PUBLIC) + if (addr_type == BDADDR_LE_PUBLIC) eui[0] &= ~0x02; else eui[0] |= 0x02; @@ -660,6 +607,17 @@ static void ifup(struct net_device *netdev) rtnl_unlock(); } +static void ifdown(struct net_device *netdev) +{ + int err; + + rtnl_lock(); + err = dev_close(netdev); + if (err < 0) + BT_INFO("iface %s cannot be closed (%d)", netdev->name, err); + rtnl_unlock(); +} + static void do_notify_peers(struct work_struct *work) { struct lowpan_dev *dev = container_of(work, struct lowpan_dev, @@ -673,26 +631,64 @@ static bool is_bt_6lowpan(struct hci_conn *hcon) if (hcon->type != LE_LINK) return false; - return test_bit(HCI_CONN_6LOWPAN, &hcon->flags); + if (!psm_6lowpan) + return false; + + return true; +} + +static struct l2cap_chan *chan_create(void) +{ + struct l2cap_chan *chan; + + chan = l2cap_chan_create(); + if (!chan) + return NULL; + + l2cap_chan_set_defaults(chan); + + chan->chan_type = L2CAP_CHAN_CONN_ORIENTED; + chan->mode = L2CAP_MODE_LE_FLOWCTL; + chan->omtu = 65535; + chan->imtu = chan->omtu; + + return chan; } -static int add_peer_conn(struct l2cap_conn *conn, struct lowpan_dev *dev) +static struct l2cap_chan *chan_open(struct l2cap_chan *pchan) +{ + struct l2cap_chan *chan; + + chan = chan_create(); + if (!chan) + return NULL; + + chan->remote_mps = chan->omtu; + chan->mps = chan->omtu; + + chan->state = BT_CONNECTED; + + return chan; +} + +static struct l2cap_chan *add_peer_chan(struct l2cap_chan *chan, + struct lowpan_dev *dev) { struct lowpan_peer *peer; unsigned long flags; peer = kzalloc(sizeof(*peer), GFP_ATOMIC); if (!peer) - return -ENOMEM; + return NULL; - peer->conn = conn; + peer->chan = chan; memset(&peer->peer_addr, 0, sizeof(struct in6_addr)); /* RFC 2464 ch. 5 */ peer->peer_addr.s6_addr[0] = 0xFE; peer->peer_addr.s6_addr[1] = 0x80; - set_addr((u8 *)&peer->peer_addr.s6_addr + 8, conn->hcon->dst.b, - conn->hcon->dst_type); + set_addr((u8 *)&peer->peer_addr.s6_addr + 8, chan->dst.b, + chan->dst_type); memcpy(&peer->eui64_addr, (u8 *)&peer->peer_addr.s6_addr + 8, EUI64_ADDR_LEN); @@ -706,40 +702,24 @@ static int add_peer_conn(struct l2cap_conn *conn, struct lowpan_dev *dev) INIT_DELAYED_WORK(&dev->notify_peers, do_notify_peers); schedule_delayed_work(&dev->notify_peers, msecs_to_jiffies(100)); - return 0; + return peer->chan; } -/* This gets called when BT LE 6LoWPAN device is connected. We then - * create network device that acts as a proxy between BT LE device - * and kernel network stack. - */ -int bt_6lowpan_add_conn(struct l2cap_conn *conn) +static int setup_netdev(struct l2cap_chan *chan, struct lowpan_dev **dev) { - struct lowpan_peer *peer = NULL; - struct lowpan_dev *dev; struct net_device *netdev; int err = 0; unsigned long flags; - if (!is_bt_6lowpan(conn->hcon)) - return 0; - - peer = lookup_peer(conn); - if (peer) - return -EEXIST; - - dev = lookup_dev(conn); - if (dev) - return add_peer_conn(conn, dev); - - netdev = alloc_netdev(sizeof(*dev), IFACE_NAME_TEMPLATE, netdev_setup); + netdev = alloc_netdev(sizeof(struct lowpan_dev), IFACE_NAME_TEMPLATE, + NET_NAME_UNKNOWN, netdev_setup); if (!netdev) return -ENOMEM; - set_dev_addr(netdev, &conn->hcon->src, conn->hcon->src_type); + set_dev_addr(netdev, &chan->src, chan->src_type); netdev->netdev_ops = &netdev_ops; - SET_NETDEV_DEV(netdev, &conn->hcon->dev); + SET_NETDEV_DEV(netdev, &chan->conn->hcon->dev); SET_NETDEV_DEVTYPE(netdev, &bt_type); err = register_netdev(netdev); @@ -749,28 +729,61 @@ int bt_6lowpan_add_conn(struct l2cap_conn *conn) goto out; } - BT_DBG("ifindex %d peer bdaddr %pMR my addr %pMR", - netdev->ifindex, &conn->hcon->dst, &conn->hcon->src); + BT_DBG("ifindex %d peer bdaddr %pMR type %d my addr %pMR type %d", + netdev->ifindex, &chan->dst, chan->dst_type, + &chan->src, chan->src_type); set_bit(__LINK_STATE_PRESENT, &netdev->state); - dev = netdev_priv(netdev); - dev->netdev = netdev; - dev->hdev = conn->hcon->hdev; - INIT_LIST_HEAD(&dev->peers); + *dev = netdev_priv(netdev); + (*dev)->netdev = netdev; + (*dev)->hdev = chan->conn->hcon->hdev; + INIT_LIST_HEAD(&(*dev)->peers); write_lock_irqsave(&devices_lock, flags); - INIT_LIST_HEAD(&dev->list); - list_add(&dev->list, &bt_6lowpan_devices); + INIT_LIST_HEAD(&(*dev)->list); + list_add(&(*dev)->list, &bt_6lowpan_devices); write_unlock_irqrestore(&devices_lock, flags); - ifup(netdev); - - return add_peer_conn(conn, dev); + return 0; out: return err; } +static inline void chan_ready_cb(struct l2cap_chan *chan) +{ + struct lowpan_dev *dev; + + dev = lookup_dev(chan->conn); + + BT_DBG("chan %p conn %p dev %p", chan, chan->conn, dev); + + if (!dev) { + if (setup_netdev(chan, &dev) < 0) { + l2cap_chan_del(chan, -ENOENT); + return; + } + } + + if (!try_module_get(THIS_MODULE)) + return; + + add_peer_chan(chan, dev); + ifup(dev->netdev); +} + +static inline struct l2cap_chan *chan_new_conn_cb(struct l2cap_chan *chan) +{ + struct l2cap_chan *pchan; + + pchan = chan_open(chan); + pchan->ops = chan->ops; + + BT_DBG("chan %p pchan %p", chan, pchan); + + return pchan; +} + static void delete_netdev(struct work_struct *work) { struct lowpan_dev *entry = container_of(work, struct lowpan_dev, @@ -781,26 +794,43 @@ static void delete_netdev(struct work_struct *work) /* The entry pointer is deleted in device_event() */ } -int bt_6lowpan_del_conn(struct l2cap_conn *conn) +static void chan_close_cb(struct l2cap_chan *chan) { struct lowpan_dev *entry, *tmp; struct lowpan_dev *dev = NULL; struct lowpan_peer *peer; int err = -ENOENT; unsigned long flags; - bool last = false; + bool last = false, removed = true; - if (!conn || !is_bt_6lowpan(conn->hcon)) - return 0; + BT_DBG("chan %p conn %p", chan, chan->conn); + + if (chan->conn && chan->conn->hcon) { + if (!is_bt_6lowpan(chan->conn->hcon)) + return; + + /* If conn is set, then the netdev is also there and we should + * not remove it. + */ + removed = false; + } write_lock_irqsave(&devices_lock, flags); list_for_each_entry_safe(entry, tmp, &bt_6lowpan_devices, list) { dev = lowpan_dev(entry->netdev); - peer = peer_lookup_conn(dev, conn); + peer = peer_lookup_chan(dev, chan); if (peer) { last = peer_del(dev, peer); err = 0; + + BT_DBG("dev %p removing %speer %p", dev, + last ? "last " : "1 ", peer); + BT_DBG("chan %p orig refcnt %d", chan, + atomic_read(&chan->kref.refcount)); + + l2cap_chan_put(chan); + kfree(peer); break; } } @@ -810,18 +840,402 @@ int bt_6lowpan_del_conn(struct l2cap_conn *conn) cancel_delayed_work_sync(&dev->notify_peers); - /* bt_6lowpan_del_conn() is called with hci dev lock held which - * means that we must delete the netdevice in worker thread. - */ - INIT_WORK(&entry->delete_netdev, delete_netdev); - schedule_work(&entry->delete_netdev); + ifdown(dev->netdev); + + if (!removed) { + INIT_WORK(&entry->delete_netdev, delete_netdev); + schedule_work(&entry->delete_netdev); + } } else { write_unlock_irqrestore(&devices_lock, flags); } + return; +} + +static void chan_state_change_cb(struct l2cap_chan *chan, int state, int err) +{ + BT_DBG("chan %p conn %p state %s err %d", chan, chan->conn, + state_to_string(state), err); +} + +static struct sk_buff *chan_alloc_skb_cb(struct l2cap_chan *chan, + unsigned long hdr_len, + unsigned long len, int nb) +{ + /* Note that we must allocate using GFP_ATOMIC here as + * this function is called originally from netdev hard xmit + * function in atomic context. + */ + return bt_skb_alloc(hdr_len + len, GFP_ATOMIC); +} + +static void chan_suspend_cb(struct l2cap_chan *chan) +{ + struct sk_buff *skb = chan->data; + + BT_DBG("chan %p conn %p skb %p", chan, chan->conn, skb); + + lowpan_cb(skb)->status = -EAGAIN; +} + +static void chan_resume_cb(struct l2cap_chan *chan) +{ + struct sk_buff *skb = chan->data; + + BT_DBG("chan %p conn %p skb %p", chan, chan->conn, skb); + + lowpan_cb(skb)->status = 0; +} + +static long chan_get_sndtimeo_cb(struct l2cap_chan *chan) +{ + return msecs_to_jiffies(1000); +} + +static const struct l2cap_ops bt_6lowpan_chan_ops = { + .name = "L2CAP 6LoWPAN channel", + .new_connection = chan_new_conn_cb, + .recv = chan_recv_cb, + .close = chan_close_cb, + .state_change = chan_state_change_cb, + .ready = chan_ready_cb, + .resume = chan_resume_cb, + .suspend = chan_suspend_cb, + .get_sndtimeo = chan_get_sndtimeo_cb, + .alloc_skb = chan_alloc_skb_cb, + .memcpy_fromiovec = l2cap_chan_no_memcpy_fromiovec, + + .teardown = l2cap_chan_no_teardown, + .defer = l2cap_chan_no_defer, + .set_shutdown = l2cap_chan_no_set_shutdown, +}; + +static inline __u8 bdaddr_type(__u8 type) +{ + if (type == ADDR_LE_DEV_PUBLIC) + return BDADDR_LE_PUBLIC; + else + return BDADDR_LE_RANDOM; +} + +static struct l2cap_chan *chan_get(void) +{ + struct l2cap_chan *pchan; + + pchan = chan_create(); + if (!pchan) + return NULL; + + pchan->ops = &bt_6lowpan_chan_ops; + + return pchan; +} + +static int bt_6lowpan_connect(bdaddr_t *addr, u8 dst_type) +{ + struct l2cap_chan *pchan; + int err; + + pchan = chan_get(); + if (!pchan) + return -EINVAL; + + err = l2cap_chan_connect(pchan, cpu_to_le16(psm_6lowpan), 0, + addr, dst_type); + + BT_DBG("chan %p err %d", pchan, err); + if (err < 0) + l2cap_chan_put(pchan); + return err; } +static int bt_6lowpan_disconnect(struct l2cap_conn *conn, u8 dst_type) +{ + struct lowpan_peer *peer; + + BT_DBG("conn %p dst type %d", conn, dst_type); + + peer = lookup_peer(conn); + if (!peer) + return -ENOENT; + + BT_DBG("peer %p chan %p", peer, peer->chan); + + l2cap_chan_close(peer->chan, ENOENT); + + return 0; +} + +static struct l2cap_chan *bt_6lowpan_listen(void) +{ + bdaddr_t *addr = BDADDR_ANY; + struct l2cap_chan *pchan; + int err; + + if (psm_6lowpan == 0) + return NULL; + + pchan = chan_get(); + if (!pchan) + return NULL; + + pchan->state = BT_LISTEN; + pchan->src_type = BDADDR_LE_PUBLIC; + + BT_DBG("psm 0x%04x chan %p src type %d", psm_6lowpan, pchan, + pchan->src_type); + + err = l2cap_add_psm(pchan, addr, cpu_to_le16(psm_6lowpan)); + if (err) { + l2cap_chan_put(pchan); + BT_ERR("psm cannot be added err %d", err); + return NULL; + } + + return pchan; +} + +static int get_l2cap_conn(char *buf, bdaddr_t *addr, u8 *addr_type, + struct l2cap_conn **conn) +{ + struct hci_conn *hcon; + struct hci_dev *hdev; + bdaddr_t *src = BDADDR_ANY; + int n; + + n = sscanf(buf, "%hhx:%hhx:%hhx:%hhx:%hhx:%hhx %hhu", + &addr->b[5], &addr->b[4], &addr->b[3], + &addr->b[2], &addr->b[1], &addr->b[0], + addr_type); + + if (n < 7) + return -EINVAL; + + hdev = hci_get_route(addr, src); + if (!hdev) + return -ENOENT; + + hci_dev_lock(hdev); + hcon = hci_conn_hash_lookup_ba(hdev, LE_LINK, addr); + hci_dev_unlock(hdev); + + if (!hcon) + return -ENOENT; + + *conn = (struct l2cap_conn *)hcon->l2cap_data; + + BT_DBG("conn %p dst %pMR type %d", *conn, &hcon->dst, hcon->dst_type); + + return 0; +} + +static void disconnect_all_peers(void) +{ + struct lowpan_dev *entry, *tmp_dev; + struct lowpan_peer *peer, *tmp_peer, *new_peer; + struct list_head peers; + unsigned long flags; + + INIT_LIST_HEAD(&peers); + + /* We make a separate list of peers as the close_cb() will + * modify the device peers list so it is better not to mess + * with the same list at the same time. + */ + + read_lock_irqsave(&devices_lock, flags); + + list_for_each_entry_safe(entry, tmp_dev, &bt_6lowpan_devices, list) { + list_for_each_entry_safe(peer, tmp_peer, &entry->peers, list) { + new_peer = kmalloc(sizeof(*new_peer), GFP_ATOMIC); + if (!new_peer) + break; + + new_peer->chan = peer->chan; + INIT_LIST_HEAD(&new_peer->list); + + list_add(&new_peer->list, &peers); + } + } + + read_unlock_irqrestore(&devices_lock, flags); + + list_for_each_entry_safe(peer, tmp_peer, &peers, list) { + l2cap_chan_close(peer->chan, ENOENT); + kfree(peer); + } +} + +static int lowpan_psm_set(void *data, u64 val) +{ + u16 psm; + + psm = val; + if (psm == 0 || psm_6lowpan != psm) + /* Disconnect existing connections if 6lowpan is + * disabled (psm = 0), or if psm changes. + */ + disconnect_all_peers(); + + psm_6lowpan = psm; + + if (listen_chan) { + l2cap_chan_close(listen_chan, 0); + l2cap_chan_put(listen_chan); + } + + listen_chan = bt_6lowpan_listen(); + + return 0; +} + +static int lowpan_psm_get(void *data, u64 *val) +{ + *val = psm_6lowpan; + return 0; +} + +DEFINE_SIMPLE_ATTRIBUTE(lowpan_psm_fops, lowpan_psm_get, + lowpan_psm_set, "%llu\n"); + +static ssize_t lowpan_control_write(struct file *fp, + const char __user *user_buffer, + size_t count, + loff_t *position) +{ + char buf[32]; + size_t buf_size = min(count, sizeof(buf) - 1); + int ret; + bdaddr_t addr; + u8 addr_type; + struct l2cap_conn *conn = NULL; + + if (copy_from_user(buf, user_buffer, buf_size)) + return -EFAULT; + + buf[buf_size] = '\0'; + + if (memcmp(buf, "connect ", 8) == 0) { + ret = get_l2cap_conn(&buf[8], &addr, &addr_type, &conn); + if (ret == -EINVAL) + return ret; + + if (listen_chan) { + l2cap_chan_close(listen_chan, 0); + l2cap_chan_put(listen_chan); + listen_chan = NULL; + } + + if (conn) { + struct lowpan_peer *peer; + + if (!is_bt_6lowpan(conn->hcon)) + return -EINVAL; + + peer = lookup_peer(conn); + if (peer) { + BT_DBG("6LoWPAN connection already exists"); + return -EALREADY; + } + + BT_DBG("conn %p dst %pMR type %d user %d", conn, + &conn->hcon->dst, conn->hcon->dst_type, + addr_type); + } + + ret = bt_6lowpan_connect(&addr, addr_type); + if (ret < 0) + return ret; + + return count; + } + + if (memcmp(buf, "disconnect ", 11) == 0) { + ret = get_l2cap_conn(&buf[11], &addr, &addr_type, &conn); + if (ret < 0) + return ret; + + ret = bt_6lowpan_disconnect(conn, addr_type); + if (ret < 0) + return ret; + + return count; + } + + return count; +} + +static int lowpan_control_show(struct seq_file *f, void *ptr) +{ + struct lowpan_dev *entry, *tmp_dev; + struct lowpan_peer *peer, *tmp_peer; + unsigned long flags; + + read_lock_irqsave(&devices_lock, flags); + + list_for_each_entry_safe(entry, tmp_dev, &bt_6lowpan_devices, list) { + list_for_each_entry_safe(peer, tmp_peer, &entry->peers, list) + seq_printf(f, "%pMR (type %u)\n", + &peer->chan->dst, peer->chan->dst_type); + } + + read_unlock_irqrestore(&devices_lock, flags); + + return 0; +} + +static int lowpan_control_open(struct inode *inode, struct file *file) +{ + return single_open(file, lowpan_control_show, inode->i_private); +} + +static const struct file_operations lowpan_control_fops = { + .open = lowpan_control_open, + .read = seq_read, + .write = lowpan_control_write, + .llseek = seq_lseek, + .release = single_release, +}; + +static void disconnect_devices(void) +{ + struct lowpan_dev *entry, *tmp, *new_dev; + struct list_head devices; + unsigned long flags; + + INIT_LIST_HEAD(&devices); + + /* We make a separate list of devices because the unregister_netdev() + * will call device_event() which will also want to modify the same + * devices list. + */ + + read_lock_irqsave(&devices_lock, flags); + + list_for_each_entry_safe(entry, tmp, &bt_6lowpan_devices, list) { + new_dev = kmalloc(sizeof(*new_dev), GFP_ATOMIC); + if (!new_dev) + break; + + new_dev->netdev = entry->netdev; + INIT_LIST_HEAD(&new_dev->list); + + list_add(&new_dev->list, &devices); + } + + read_unlock_irqrestore(&devices_lock, flags); + + list_for_each_entry_safe(entry, tmp, &devices, list) { + ifdown(entry->netdev); + BT_DBG("Unregistering netdev %s %p", + entry->netdev->name, entry->netdev); + unregister_netdev(entry->netdev); + kfree(entry); + } +} + static int device_event(struct notifier_block *unused, unsigned long event, void *ptr) { @@ -838,6 +1252,8 @@ static int device_event(struct notifier_block *unused, list_for_each_entry_safe(entry, tmp, &bt_6lowpan_devices, list) { if (entry->netdev == netdev) { + BT_DBG("Unregistered netdev %s %p", + netdev->name, netdev); list_del(&entry->list); kfree(entry); break; @@ -854,12 +1270,37 @@ static struct notifier_block bt_6lowpan_dev_notifier = { .notifier_call = device_event, }; -int bt_6lowpan_init(void) +static int __init bt_6lowpan_init(void) { + lowpan_psm_debugfs = debugfs_create_file("6lowpan_psm", 0644, + bt_debugfs, NULL, + &lowpan_psm_fops); + lowpan_control_debugfs = debugfs_create_file("6lowpan_control", 0644, + bt_debugfs, NULL, + &lowpan_control_fops); + return register_netdevice_notifier(&bt_6lowpan_dev_notifier); } -void bt_6lowpan_cleanup(void) +static void __exit bt_6lowpan_exit(void) { + debugfs_remove(lowpan_psm_debugfs); + debugfs_remove(lowpan_control_debugfs); + + if (listen_chan) { + l2cap_chan_close(listen_chan, 0); + l2cap_chan_put(listen_chan); + } + + disconnect_devices(); + unregister_netdevice_notifier(&bt_6lowpan_dev_notifier); } + +module_init(bt_6lowpan_init); +module_exit(bt_6lowpan_exit); + +MODULE_AUTHOR("Jukka Rissanen <jukka.rissanen@linux.intel.com>"); +MODULE_DESCRIPTION("Bluetooth 6LoWPAN"); +MODULE_VERSION(VERSION); +MODULE_LICENSE("GPL"); diff --git a/net/bluetooth/6lowpan.h b/net/bluetooth/6lowpan.h deleted file mode 100644 index 5d281f1eaf55..000000000000 --- a/net/bluetooth/6lowpan.h +++ /dev/null @@ -1,47 +0,0 @@ -/* - Copyright (c) 2013 Intel Corp. - - This program is free software; you can redistribute it and/or modify - it under the terms of the GNU General Public License version 2 and - only version 2 as published by the Free Software Foundation. - - This program is distributed in the hope that it will be useful, - but WITHOUT ANY WARRANTY; without even the implied warranty of - MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - GNU General Public License for more details. -*/ - -#ifndef __6LOWPAN_H -#define __6LOWPAN_H - -#include <linux/errno.h> -#include <linux/skbuff.h> -#include <net/bluetooth/l2cap.h> - -#if IS_ENABLED(CONFIG_BT_6LOWPAN) -int bt_6lowpan_recv(struct l2cap_conn *conn, struct sk_buff *skb); -int bt_6lowpan_add_conn(struct l2cap_conn *conn); -int bt_6lowpan_del_conn(struct l2cap_conn *conn); -int bt_6lowpan_init(void); -void bt_6lowpan_cleanup(void); -#else -static int bt_6lowpan_recv(struct l2cap_conn *conn, struct sk_buff *skb) -{ - return -EOPNOTSUPP; -} -static int bt_6lowpan_add_conn(struct l2cap_conn *conn) -{ - return -EOPNOTSUPP; -} -int bt_6lowpan_del_conn(struct l2cap_conn *conn) -{ - return -EOPNOTSUPP; -} -static int bt_6lowpan_init(void) -{ - return -EOPNOTSUPP; -} -static void bt_6lowpan_cleanup(void) { } -#endif - -#endif /* __6LOWPAN_H */ diff --git a/net/bluetooth/Kconfig b/net/bluetooth/Kconfig index 06ec14499ca1..600fb29288f4 100644 --- a/net/bluetooth/Kconfig +++ b/net/bluetooth/Kconfig @@ -6,7 +6,6 @@ menuconfig BT tristate "Bluetooth subsystem support" depends on NET && !S390 depends on RFKILL || !RFKILL - select 6LOWPAN_IPHC if BT_6LOWPAN select CRC16 select CRYPTO select CRYPTO_BLKCIPHER @@ -41,10 +40,10 @@ menuconfig BT more information, see <http://www.bluez.org/>. config BT_6LOWPAN - bool "Bluetooth 6LoWPAN support" - depends on BT && IPV6 + tristate "Bluetooth 6LoWPAN support" + depends on BT && 6LOWPAN help - IPv6 compression over Bluetooth. + IPv6 compression over Bluetooth Low Energy. source "net/bluetooth/rfcomm/Kconfig" diff --git a/net/bluetooth/Makefile b/net/bluetooth/Makefile index ca51246b1016..886e9aa3ecf1 100644 --- a/net/bluetooth/Makefile +++ b/net/bluetooth/Makefile @@ -7,10 +7,12 @@ obj-$(CONFIG_BT_RFCOMM) += rfcomm/ obj-$(CONFIG_BT_BNEP) += bnep/ obj-$(CONFIG_BT_CMTP) += cmtp/ obj-$(CONFIG_BT_HIDP) += hidp/ +obj-$(CONFIG_BT_6LOWPAN) += bluetooth_6lowpan.o + +bluetooth_6lowpan-y := 6lowpan.o bluetooth-y := af_bluetooth.o hci_core.o hci_conn.o hci_event.o mgmt.o \ hci_sock.o hci_sysfs.o l2cap_core.o l2cap_sock.o smp.o sco.o lib.o \ a2mp.o amp.o -bluetooth-$(CONFIG_BT_6LOWPAN) += 6lowpan.o subdir-ccflags-y += -D__CHECK_ENDIAN__ diff --git a/net/bluetooth/a2mp.c b/net/bluetooth/a2mp.c index 9514cc9e850c..5dcade511fdb 100644 --- a/net/bluetooth/a2mp.c +++ b/net/bluetooth/a2mp.c @@ -63,7 +63,7 @@ void a2mp_send(struct amp_mgr *mgr, u8 code, u8 ident, u16 len, void *data) msg.msg_iov = (struct iovec *) &iv; msg.msg_iovlen = 1; - l2cap_chan_send(chan, &msg, total_len, 0); + l2cap_chan_send(chan, &msg, total_len); kfree(cmd); } @@ -693,18 +693,19 @@ static void a2mp_chan_state_change_cb(struct l2cap_chan *chan, int state, } static struct sk_buff *a2mp_chan_alloc_skb_cb(struct l2cap_chan *chan, + unsigned long hdr_len, unsigned long len, int nb) { struct sk_buff *skb; - skb = bt_skb_alloc(len, GFP_KERNEL); + skb = bt_skb_alloc(hdr_len + len, GFP_KERNEL); if (!skb) return ERR_PTR(-ENOMEM); return skb; } -static struct l2cap_ops a2mp_chan_ops = { +static const struct l2cap_ops a2mp_chan_ops = { .name = "L2CAP A2MP channel", .recv = a2mp_chan_recv_cb, .close = a2mp_chan_close_cb, @@ -719,6 +720,7 @@ static struct l2cap_ops a2mp_chan_ops = { .resume = l2cap_chan_no_resume, .set_shutdown = l2cap_chan_no_set_shutdown, .get_sndtimeo = l2cap_chan_no_get_sndtimeo, + .memcpy_fromiovec = l2cap_chan_no_memcpy_fromiovec, }; static struct l2cap_chan *a2mp_chan_open(struct l2cap_conn *conn, bool locked) diff --git a/net/bluetooth/af_bluetooth.c b/net/bluetooth/af_bluetooth.c index 2021c481cdb6..4dca0299ed96 100644 --- a/net/bluetooth/af_bluetooth.c +++ b/net/bluetooth/af_bluetooth.c @@ -639,7 +639,7 @@ static int bt_seq_show(struct seq_file *seq, void *v) return 0; } -static struct seq_operations bt_seq_ops = { +static const struct seq_operations bt_seq_ops = { .start = bt_seq_start, .next = bt_seq_next, .stop = bt_seq_stop, diff --git a/net/bluetooth/amp.c b/net/bluetooth/amp.c index bb39509b3f06..016cdb66df6c 100644 --- a/net/bluetooth/amp.c +++ b/net/bluetooth/amp.c @@ -113,8 +113,9 @@ struct hci_conn *phylink_add(struct hci_dev *hdev, struct amp_mgr *mgr, { bdaddr_t *dst = &mgr->l2cap_conn->hcon->dst; struct hci_conn *hcon; + u8 role = out ? HCI_ROLE_MASTER : HCI_ROLE_SLAVE; - hcon = hci_conn_add(hdev, AMP_LINK, dst); + hcon = hci_conn_add(hdev, AMP_LINK, dst, role); if (!hcon) return NULL; @@ -125,7 +126,6 @@ struct hci_conn *phylink_add(struct hci_dev *hdev, struct amp_mgr *mgr, hcon->handle = __next_handle(mgr); hcon->remote_id = remote_id; hcon->amp_mgr = amp_mgr_get(mgr); - hcon->out = out; return hcon; } @@ -133,8 +133,8 @@ struct hci_conn *phylink_add(struct hci_dev *hdev, struct amp_mgr *mgr, /* AMP crypto key generation interface */ static int hmac_sha256(u8 *key, u8 ksize, char *plaintext, u8 psize, u8 *output) { - int ret = 0; struct crypto_shash *tfm; + int ret; if (!ksize) return -EINVAL; diff --git a/net/bluetooth/bnep/core.c b/net/bluetooth/bnep/core.c index a841d3e776c5..85bcc21e84d2 100644 --- a/net/bluetooth/bnep/core.c +++ b/net/bluetooth/bnep/core.c @@ -538,8 +538,9 @@ int bnep_add_connection(struct bnep_connadd_req *req, struct socket *sock) /* session struct allocated as private part of net_device */ dev = alloc_netdev(sizeof(struct bnep_session), - (*req->device) ? req->device : "bnep%d", - bnep_net_setup); + (*req->device) ? req->device : "bnep%d", + NET_NAME_UNKNOWN, + bnep_net_setup); if (!dev) return -ENOMEM; diff --git a/net/bluetooth/cmtp/capi.c b/net/bluetooth/cmtp/capi.c index cd75e4d64b90..1ca8a87a0787 100644 --- a/net/bluetooth/cmtp/capi.c +++ b/net/bluetooth/cmtp/capi.c @@ -362,12 +362,6 @@ void cmtp_recv_capimsg(struct cmtp_session *session, struct sk_buff *skb) CAPIMSG_SETCONTROL(skb->data, contr); } - if (!ctrl) { - BT_ERR("Can't find controller %d for message", session->num); - kfree_skb(skb); - return; - } - capi_ctr_handle_message(ctrl, appl, skb); } diff --git a/net/bluetooth/hci_conn.c b/net/bluetooth/hci_conn.c index a7a27bc2c0b1..b50dabb3f86a 100644 --- a/net/bluetooth/hci_conn.c +++ b/net/bluetooth/hci_conn.c @@ -66,8 +66,7 @@ static void hci_acl_create_connection(struct hci_conn *conn) conn->state = BT_CONNECT; conn->out = true; - - conn->link_mode = HCI_LM_MASTER; + conn->role = HCI_ROLE_MASTER; conn->attempt++; @@ -136,7 +135,7 @@ void hci_disconnect(struct hci_conn *conn, __u8 reason) hci_send_cmd(conn->hdev, HCI_OP_DISCONNECT, sizeof(cp), &cp); } -static void hci_amp_disconn(struct hci_conn *conn, __u8 reason) +static void hci_amp_disconn(struct hci_conn *conn) { struct hci_cp_disconn_phy_link cp; @@ -145,7 +144,7 @@ static void hci_amp_disconn(struct hci_conn *conn, __u8 reason) conn->state = BT_DISCONN; cp.phy_handle = HCI_PHY_HANDLE(conn->handle); - cp.reason = reason; + cp.reason = hci_proto_disconn_ind(conn); hci_send_cmd(conn->hdev, HCI_OP_DISCONN_PHY_LINK, sizeof(cp), &cp); } @@ -213,14 +212,26 @@ bool hci_setup_sync(struct hci_conn *conn, __u16 handle) return true; } -void hci_le_conn_update(struct hci_conn *conn, u16 min, u16 max, - u16 latency, u16 to_multiplier) +u8 hci_le_conn_update(struct hci_conn *conn, u16 min, u16 max, u16 latency, + u16 to_multiplier) { - struct hci_cp_le_conn_update cp; struct hci_dev *hdev = conn->hdev; + struct hci_conn_params *params; + struct hci_cp_le_conn_update cp; - memset(&cp, 0, sizeof(cp)); + hci_dev_lock(hdev); + params = hci_conn_params_lookup(hdev, &conn->dst, conn->dst_type); + if (params) { + params->conn_min_interval = min; + params->conn_max_interval = max; + params->conn_latency = latency; + params->supervision_timeout = to_multiplier; + } + + hci_dev_unlock(hdev); + + memset(&cp, 0, sizeof(cp)); cp.handle = cpu_to_le16(conn->handle); cp.conn_interval_min = cpu_to_le16(min); cp.conn_interval_max = cpu_to_le16(max); @@ -230,6 +241,11 @@ void hci_le_conn_update(struct hci_conn *conn, u16 min, u16 max, cp.max_ce_len = cpu_to_le16(0x0000); hci_send_cmd(hdev, HCI_OP_LE_CONN_UPDATE, sizeof(cp), &cp); + + if (params) + return 0x01; + + return 0x00; } void hci_le_start_enc(struct hci_conn *conn, __le16 ediv, __le64 rand, @@ -271,20 +287,6 @@ void hci_sco_setup(struct hci_conn *conn, __u8 status) } } -static void hci_conn_disconnect(struct hci_conn *conn) -{ - __u8 reason = hci_proto_disconn_ind(conn); - - switch (conn->type) { - case AMP_LINK: - hci_amp_disconn(conn, reason); - break; - default: - hci_disconnect(conn, reason); - break; - } -} - static void hci_conn_timeout(struct work_struct *work) { struct hci_conn *conn = container_of(work, struct hci_conn, @@ -319,7 +321,31 @@ static void hci_conn_timeout(struct work_struct *work) break; case BT_CONFIG: case BT_CONNECTED: - hci_conn_disconnect(conn); + if (conn->type == AMP_LINK) { + hci_amp_disconn(conn); + } else { + __u8 reason = hci_proto_disconn_ind(conn); + + /* When we are master of an established connection + * and it enters the disconnect timeout, then go + * ahead and try to read the current clock offset. + * + * Processing of the result is done within the + * event handling and hci_clock_offset_evt function. + */ + if (conn->type == ACL_LINK && + conn->role == HCI_ROLE_MASTER) { + struct hci_dev *hdev = conn->hdev; + struct hci_cp_read_clock_offset cp; + + cp.handle = cpu_to_le16(conn->handle); + + hci_send_cmd(hdev, HCI_OP_READ_CLOCK_OFFSET, + sizeof(cp), &cp); + } + + hci_disconnect(conn, reason); + } break; default: conn->state = BT_CLOSED; @@ -336,9 +362,6 @@ static void hci_conn_idle(struct work_struct *work) BT_DBG("hcon %p mode %d", conn, conn->mode); - if (test_bit(HCI_RAW, &hdev->flags)) - return; - if (!lmp_sniff_capable(hdev) || !lmp_sniff_capable(conn)) return; @@ -398,13 +421,14 @@ static void le_conn_timeout(struct work_struct *work) hci_le_create_connection_cancel(conn); } -struct hci_conn *hci_conn_add(struct hci_dev *hdev, int type, bdaddr_t *dst) +struct hci_conn *hci_conn_add(struct hci_dev *hdev, int type, bdaddr_t *dst, + u8 role) { struct hci_conn *conn; BT_DBG("%s dst %pMR", hdev->name, dst); - conn = kzalloc(sizeof(struct hci_conn), GFP_KERNEL); + conn = kzalloc(sizeof(*conn), GFP_KERNEL); if (!conn) return NULL; @@ -412,6 +436,7 @@ struct hci_conn *hci_conn_add(struct hci_dev *hdev, int type, bdaddr_t *dst) bacpy(&conn->src, &hdev->bdaddr); conn->hdev = hdev; conn->type = type; + conn->role = role; conn->mode = HCI_CM_ACTIVE; conn->state = BT_OPEN; conn->auth_type = HCI_AT_GENERAL_BONDING; @@ -424,6 +449,9 @@ struct hci_conn *hci_conn_add(struct hci_dev *hdev, int type, bdaddr_t *dst) set_bit(HCI_CONN_POWER_SAVE, &conn->flags); conn->disc_timeout = HCI_DISCONN_TIMEOUT; + if (conn->role == HCI_ROLE_MASTER) + conn->out = true; + switch (type) { case ACL_LINK: conn->pkt_type = hdev->pkt_type & ACL_PTYPE_MASK; @@ -529,7 +557,6 @@ struct hci_dev *hci_get_route(bdaddr_t *dst, bdaddr_t *src) list_for_each_entry(d, &hci_dev_list, list) { if (!test_bit(HCI_UP, &d->flags) || - test_bit(HCI_RAW, &d->flags) || test_bit(HCI_USER_CHANNEL, &d->dev_flags) || d->dev_type != HCI_BREDR) continue; @@ -627,7 +654,8 @@ static void hci_req_add_le_create_conn(struct hci_request *req, cp.own_address_type = own_addr_type; cp.conn_interval_min = cpu_to_le16(conn->le_conn_min_interval); cp.conn_interval_max = cpu_to_le16(conn->le_conn_max_interval); - cp.supervision_timeout = cpu_to_le16(0x002a); + cp.conn_latency = cpu_to_le16(conn->le_conn_latency); + cp.supervision_timeout = cpu_to_le16(conn->le_supv_timeout); cp.min_ce_len = cpu_to_le16(0x0000); cp.max_ce_len = cpu_to_le16(0x0000); @@ -644,15 +672,12 @@ static void hci_req_directed_advertising(struct hci_request *req, u8 own_addr_type; u8 enable; - enable = 0x00; - hci_req_add(req, HCI_OP_LE_SET_ADV_ENABLE, sizeof(enable), &enable); - - /* Clear the HCI_ADVERTISING bit temporarily so that the + /* Clear the HCI_LE_ADV bit temporarily so that the * hci_update_random_address knows that it's safe to go ahead * and write a new random address. The flag will be set back on * as soon as the SET_ADV_ENABLE HCI command completes. */ - clear_bit(HCI_ADVERTISING, &hdev->dev_flags); + clear_bit(HCI_LE_ADV, &hdev->dev_flags); /* Set require_privacy to false so that the remote device has a * chance of identifying us. @@ -676,7 +701,8 @@ static void hci_req_directed_advertising(struct hci_request *req, } struct hci_conn *hci_connect_le(struct hci_dev *hdev, bdaddr_t *dst, - u8 dst_type, u8 sec_level, u8 auth_type) + u8 dst_type, u8 sec_level, u16 conn_timeout, + u8 role) { struct hci_conn_params *params; struct hci_conn *conn; @@ -696,7 +722,6 @@ struct hci_conn *hci_connect_le(struct hci_dev *hdev, bdaddr_t *dst, conn = hci_conn_hash_lookup_ba(hdev, LE_LINK, dst); if (conn) { conn->pending_sec_level = sec_level; - conn->auth_type = auth_type; goto done; } @@ -726,32 +751,56 @@ struct hci_conn *hci_connect_le(struct hci_dev *hdev, bdaddr_t *dst, dst_type = ADDR_LE_DEV_RANDOM; } - conn = hci_conn_add(hdev, LE_LINK, dst); + conn = hci_conn_add(hdev, LE_LINK, dst, role); if (!conn) return ERR_PTR(-ENOMEM); conn->dst_type = dst_type; conn->sec_level = BT_SECURITY_LOW; conn->pending_sec_level = sec_level; - conn->auth_type = auth_type; + conn->conn_timeout = conn_timeout; hci_req_init(&req, hdev); - if (test_bit(HCI_ADVERTISING, &hdev->dev_flags)) { + /* Disable advertising if we're active. For master role + * connections most controllers will refuse to connect if + * advertising is enabled, and for slave role connections we + * anyway have to disable it in order to start directed + * advertising. + */ + if (test_bit(HCI_LE_ADV, &hdev->dev_flags)) { + u8 enable = 0x00; + hci_req_add(&req, HCI_OP_LE_SET_ADV_ENABLE, sizeof(enable), + &enable); + } + + /* If requested to connect as slave use directed advertising */ + if (conn->role == HCI_ROLE_SLAVE) { + /* If we're active scanning most controllers are unable + * to initiate advertising. Simply reject the attempt. + */ + if (test_bit(HCI_LE_SCAN, &hdev->dev_flags) && + hdev->le_scan_type == LE_SCAN_ACTIVE) { + skb_queue_purge(&req.cmd_q); + hci_conn_del(conn); + return ERR_PTR(-EBUSY); + } + hci_req_directed_advertising(&req, conn); goto create_conn; } - conn->out = true; - conn->link_mode |= HCI_LM_MASTER; - params = hci_conn_params_lookup(hdev, &conn->dst, conn->dst_type); if (params) { conn->le_conn_min_interval = params->conn_min_interval; conn->le_conn_max_interval = params->conn_max_interval; + conn->le_conn_latency = params->conn_latency; + conn->le_supv_timeout = params->supervision_timeout; } else { conn->le_conn_min_interval = hdev->le_conn_min_interval; conn->le_conn_max_interval = hdev->le_conn_max_interval; + conn->le_conn_latency = hdev->le_conn_latency; + conn->le_supv_timeout = hdev->le_supv_timeout; } /* If controller is scanning, we stop it since some controllers are @@ -785,11 +834,11 @@ struct hci_conn *hci_connect_acl(struct hci_dev *hdev, bdaddr_t *dst, struct hci_conn *acl; if (!test_bit(HCI_BREDR_ENABLED, &hdev->dev_flags)) - return ERR_PTR(-ENOTSUPP); + return ERR_PTR(-EOPNOTSUPP); acl = hci_conn_hash_lookup_ba(hdev, ACL_LINK, dst); if (!acl) { - acl = hci_conn_add(hdev, ACL_LINK, dst); + acl = hci_conn_add(hdev, ACL_LINK, dst, HCI_ROLE_MASTER); if (!acl) return ERR_PTR(-ENOMEM); } @@ -818,7 +867,7 @@ struct hci_conn *hci_connect_sco(struct hci_dev *hdev, int type, bdaddr_t *dst, sco = hci_conn_hash_lookup_ba(hdev, type, dst); if (!sco) { - sco = hci_conn_add(hdev, type, dst); + sco = hci_conn_add(hdev, type, dst, HCI_ROLE_MASTER); if (!sco) { hci_conn_drop(acl); return ERR_PTR(-ENOMEM); @@ -865,7 +914,8 @@ int hci_conn_check_link_mode(struct hci_conn *conn) return 0; } - if (hci_conn_ssp_enabled(conn) && !(conn->link_mode & HCI_LM_ENCRYPT)) + if (hci_conn_ssp_enabled(conn) && + !test_bit(HCI_CONN_ENCRYPT, &conn->flags)) return 0; return 1; @@ -881,7 +931,7 @@ static int hci_conn_auth(struct hci_conn *conn, __u8 sec_level, __u8 auth_type) if (sec_level > conn->sec_level) conn->pending_sec_level = sec_level; - else if (conn->link_mode & HCI_LM_AUTH) + else if (test_bit(HCI_CONN_AUTH, &conn->flags)) return 1; /* Make sure we preserve an existing MITM requirement*/ @@ -899,7 +949,7 @@ static int hci_conn_auth(struct hci_conn *conn, __u8 sec_level, __u8 auth_type) /* If we're already encrypted set the REAUTH_PEND flag, * otherwise set the ENCRYPT_PEND. */ - if (conn->link_mode & HCI_LM_ENCRYPT) + if (test_bit(HCI_CONN_ENCRYPT, &conn->flags)) set_bit(HCI_CONN_REAUTH_PEND, &conn->flags); else set_bit(HCI_CONN_ENCRYPT_PEND, &conn->flags); @@ -923,7 +973,8 @@ static void hci_conn_encrypt(struct hci_conn *conn) } /* Enable security */ -int hci_conn_security(struct hci_conn *conn, __u8 sec_level, __u8 auth_type) +int hci_conn_security(struct hci_conn *conn, __u8 sec_level, __u8 auth_type, + bool initiator) { BT_DBG("hcon %p", conn); @@ -940,7 +991,7 @@ int hci_conn_security(struct hci_conn *conn, __u8 sec_level, __u8 auth_type) return 1; /* For other security levels we need the link key. */ - if (!(conn->link_mode & HCI_LM_AUTH)) + if (!test_bit(HCI_CONN_AUTH, &conn->flags)) goto auth; /* An authenticated FIPS approved combination key has sufficient @@ -976,11 +1027,14 @@ auth: if (test_bit(HCI_CONN_ENCRYPT_PEND, &conn->flags)) return 0; + if (initiator) + set_bit(HCI_CONN_AUTH_INITIATOR, &conn->flags); + if (!hci_conn_auth(conn, sec_level, auth_type)) return 0; encrypt: - if (conn->link_mode & HCI_LM_ENCRYPT) + if (test_bit(HCI_CONN_ENCRYPT, &conn->flags)) return 1; hci_conn_encrypt(conn); @@ -1027,7 +1081,7 @@ int hci_conn_switch_role(struct hci_conn *conn, __u8 role) { BT_DBG("hcon %p", conn); - if (!role && conn->link_mode & HCI_LM_MASTER) + if (role == conn->role) return 1; if (!test_and_set_bit(HCI_CONN_RSWITCH_PEND, &conn->flags)) { @@ -1048,9 +1102,6 @@ void hci_conn_enter_active_mode(struct hci_conn *conn, __u8 force_active) BT_DBG("hcon %p mode %d", conn, conn->mode); - if (test_bit(HCI_RAW, &hdev->flags)) - return; - if (conn->mode != HCI_CM_SNIFF) goto timer; @@ -1101,6 +1152,28 @@ void hci_conn_check_pending(struct hci_dev *hdev) hci_dev_unlock(hdev); } +static u32 get_link_mode(struct hci_conn *conn) +{ + u32 link_mode = 0; + + if (conn->role == HCI_ROLE_MASTER) + link_mode |= HCI_LM_MASTER; + + if (test_bit(HCI_CONN_ENCRYPT, &conn->flags)) + link_mode |= HCI_LM_ENCRYPT; + + if (test_bit(HCI_CONN_AUTH, &conn->flags)) + link_mode |= HCI_LM_AUTH; + + if (test_bit(HCI_CONN_SECURE, &conn->flags)) + link_mode |= HCI_LM_SECURE; + + if (test_bit(HCI_CONN_FIPS, &conn->flags)) + link_mode |= HCI_LM_FIPS; + + return link_mode; +} + int hci_get_conn_list(void __user *arg) { struct hci_conn *c; @@ -1136,7 +1209,7 @@ int hci_get_conn_list(void __user *arg) (ci + n)->type = c->type; (ci + n)->out = c->out; (ci + n)->state = c->state; - (ci + n)->link_mode = c->link_mode; + (ci + n)->link_mode = get_link_mode(c); if (++n >= req.conn_num) break; } @@ -1172,7 +1245,7 @@ int hci_get_conn_info(struct hci_dev *hdev, void __user *arg) ci.type = conn->type; ci.out = conn->out; ci.state = conn->state; - ci.link_mode = conn->link_mode; + ci.link_mode = get_link_mode(conn); } hci_dev_unlock(hdev); @@ -1209,7 +1282,7 @@ struct hci_chan *hci_chan_create(struct hci_conn *conn) BT_DBG("%s hcon %p", hdev->name, conn); - chan = kzalloc(sizeof(struct hci_chan), GFP_KERNEL); + chan = kzalloc(sizeof(*chan), GFP_KERNEL); if (!chan) return NULL; diff --git a/net/bluetooth/hci_core.c b/net/bluetooth/hci_core.c index e090bffe1bf8..c32d361c0cf7 100644 --- a/net/bluetooth/hci_core.c +++ b/net/bluetooth/hci_core.c @@ -35,6 +35,7 @@ #include <net/bluetooth/bluetooth.h> #include <net/bluetooth/hci_core.h> #include <net/bluetooth/l2cap.h> +#include <net/bluetooth/mgmt.h> #include "smp.h" @@ -53,6 +54,15 @@ DEFINE_RWLOCK(hci_cb_list_lock); /* HCI ID Numbering */ static DEFINE_IDA(hci_index_ida); +/* ----- HCI requests ----- */ + +#define HCI_REQ_DONE 0 +#define HCI_REQ_PEND 1 +#define HCI_REQ_CANCELED 2 + +#define hci_req_lock(d) mutex_lock(&d->req_lock) +#define hci_req_unlock(d) mutex_unlock(&d->req_lock) + /* ---- HCI notifications ---- */ static void hci_notify(struct hci_dev *hdev, int event) @@ -68,7 +78,7 @@ static ssize_t dut_mode_read(struct file *file, char __user *user_buf, struct hci_dev *hdev = file->private_data; char buf[3]; - buf[0] = test_bit(HCI_DUT_MODE, &hdev->dev_flags) ? 'Y': 'N'; + buf[0] = test_bit(HCI_DUT_MODE, &hdev->dbg_flags) ? 'Y': 'N'; buf[1] = '\n'; buf[2] = '\0'; return simple_read_from_buffer(user_buf, count, ppos, buf, 2); @@ -94,7 +104,7 @@ static ssize_t dut_mode_write(struct file *file, const char __user *user_buf, if (strtobool(buf, &enable)) return -EINVAL; - if (enable == test_bit(HCI_DUT_MODE, &hdev->dev_flags)) + if (enable == test_bit(HCI_DUT_MODE, &hdev->dbg_flags)) return -EALREADY; hci_req_lock(hdev); @@ -115,7 +125,7 @@ static ssize_t dut_mode_write(struct file *file, const char __user *user_buf, if (err < 0) return err; - change_bit(HCI_DUT_MODE, &hdev->dev_flags); + change_bit(HCI_DUT_MODE, &hdev->dbg_flags); return count; } @@ -190,6 +200,31 @@ static const struct file_operations blacklist_fops = { .release = single_release, }; +static int whitelist_show(struct seq_file *f, void *p) +{ + struct hci_dev *hdev = f->private; + struct bdaddr_list *b; + + hci_dev_lock(hdev); + list_for_each_entry(b, &hdev->whitelist, list) + seq_printf(f, "%pMR (type %u)\n", &b->bdaddr, b->bdaddr_type); + hci_dev_unlock(hdev); + + return 0; +} + +static int whitelist_open(struct inode *inode, struct file *file) +{ + return single_open(file, whitelist_show, inode->i_private); +} + +static const struct file_operations whitelist_fops = { + .open = whitelist_open, + .read = seq_read, + .llseek = seq_lseek, + .release = single_release, +}; + static int uuids_show(struct seq_file *f, void *p) { struct hci_dev *hdev = f->private; @@ -352,62 +387,13 @@ static int auto_accept_delay_get(void *data, u64 *val) DEFINE_SIMPLE_ATTRIBUTE(auto_accept_delay_fops, auto_accept_delay_get, auto_accept_delay_set, "%llu\n"); -static int ssp_debug_mode_set(void *data, u64 val) -{ - struct hci_dev *hdev = data; - struct sk_buff *skb; - __u8 mode; - int err; - - if (val != 0 && val != 1) - return -EINVAL; - - if (!test_bit(HCI_UP, &hdev->flags)) - return -ENETDOWN; - - hci_req_lock(hdev); - mode = val; - skb = __hci_cmd_sync(hdev, HCI_OP_WRITE_SSP_DEBUG_MODE, sizeof(mode), - &mode, HCI_CMD_TIMEOUT); - hci_req_unlock(hdev); - - if (IS_ERR(skb)) - return PTR_ERR(skb); - - err = -bt_to_errno(skb->data[0]); - kfree_skb(skb); - - if (err < 0) - return err; - - hci_dev_lock(hdev); - hdev->ssp_debug_mode = val; - hci_dev_unlock(hdev); - - return 0; -} - -static int ssp_debug_mode_get(void *data, u64 *val) -{ - struct hci_dev *hdev = data; - - hci_dev_lock(hdev); - *val = hdev->ssp_debug_mode; - hci_dev_unlock(hdev); - - return 0; -} - -DEFINE_SIMPLE_ATTRIBUTE(ssp_debug_mode_fops, ssp_debug_mode_get, - ssp_debug_mode_set, "%llu\n"); - static ssize_t force_sc_support_read(struct file *file, char __user *user_buf, size_t count, loff_t *ppos) { struct hci_dev *hdev = file->private_data; char buf[3]; - buf[0] = test_bit(HCI_FORCE_SC, &hdev->dev_flags) ? 'Y': 'N'; + buf[0] = test_bit(HCI_FORCE_SC, &hdev->dbg_flags) ? 'Y': 'N'; buf[1] = '\n'; buf[2] = '\0'; return simple_read_from_buffer(user_buf, count, ppos, buf, 2); @@ -432,10 +418,10 @@ static ssize_t force_sc_support_write(struct file *file, if (strtobool(buf, &enable)) return -EINVAL; - if (enable == test_bit(HCI_FORCE_SC, &hdev->dev_flags)) + if (enable == test_bit(HCI_FORCE_SC, &hdev->dbg_flags)) return -EALREADY; - change_bit(HCI_FORCE_SC, &hdev->dev_flags); + change_bit(HCI_FORCE_SC, &hdev->dbg_flags); return count; } @@ -719,7 +705,7 @@ static ssize_t force_static_address_read(struct file *file, struct hci_dev *hdev = file->private_data; char buf[3]; - buf[0] = test_bit(HCI_FORCE_STATIC_ADDR, &hdev->dev_flags) ? 'Y': 'N'; + buf[0] = test_bit(HCI_FORCE_STATIC_ADDR, &hdev->dbg_flags) ? 'Y': 'N'; buf[1] = '\n'; buf[2] = '\0'; return simple_read_from_buffer(user_buf, count, ppos, buf, 2); @@ -744,10 +730,10 @@ static ssize_t force_static_address_write(struct file *file, if (strtobool(buf, &enable)) return -EINVAL; - if (enable == test_bit(HCI_FORCE_STATIC_ADDR, &hdev->dev_flags)) + if (enable == test_bit(HCI_FORCE_STATIC_ADDR, &hdev->dbg_flags)) return -EALREADY; - change_bit(HCI_FORCE_STATIC_ADDR, &hdev->dev_flags); + change_bit(HCI_FORCE_STATIC_ADDR, &hdev->dbg_flags); return count; } @@ -900,177 +886,169 @@ static int conn_max_interval_get(void *data, u64 *val) DEFINE_SIMPLE_ATTRIBUTE(conn_max_interval_fops, conn_max_interval_get, conn_max_interval_set, "%llu\n"); -static int adv_channel_map_set(void *data, u64 val) +static int conn_latency_set(void *data, u64 val) { struct hci_dev *hdev = data; - if (val < 0x01 || val > 0x07) + if (val > 0x01f3) return -EINVAL; hci_dev_lock(hdev); - hdev->le_adv_channel_map = val; + hdev->le_conn_latency = val; hci_dev_unlock(hdev); return 0; } -static int adv_channel_map_get(void *data, u64 *val) +static int conn_latency_get(void *data, u64 *val) { struct hci_dev *hdev = data; hci_dev_lock(hdev); - *val = hdev->le_adv_channel_map; + *val = hdev->le_conn_latency; hci_dev_unlock(hdev); return 0; } -DEFINE_SIMPLE_ATTRIBUTE(adv_channel_map_fops, adv_channel_map_get, - adv_channel_map_set, "%llu\n"); +DEFINE_SIMPLE_ATTRIBUTE(conn_latency_fops, conn_latency_get, + conn_latency_set, "%llu\n"); -static ssize_t lowpan_read(struct file *file, char __user *user_buf, - size_t count, loff_t *ppos) +static int supervision_timeout_set(void *data, u64 val) { - struct hci_dev *hdev = file->private_data; - char buf[3]; + struct hci_dev *hdev = data; - buf[0] = test_bit(HCI_6LOWPAN_ENABLED, &hdev->dev_flags) ? 'Y' : 'N'; - buf[1] = '\n'; - buf[2] = '\0'; - return simple_read_from_buffer(user_buf, count, ppos, buf, 2); + if (val < 0x000a || val > 0x0c80) + return -EINVAL; + + hci_dev_lock(hdev); + hdev->le_supv_timeout = val; + hci_dev_unlock(hdev); + + return 0; } -static ssize_t lowpan_write(struct file *fp, const char __user *user_buffer, - size_t count, loff_t *position) +static int supervision_timeout_get(void *data, u64 *val) { - struct hci_dev *hdev = fp->private_data; - bool enable; - char buf[32]; - size_t buf_size = min(count, (sizeof(buf)-1)); + struct hci_dev *hdev = data; - if (copy_from_user(buf, user_buffer, buf_size)) - return -EFAULT; + hci_dev_lock(hdev); + *val = hdev->le_supv_timeout; + hci_dev_unlock(hdev); - buf[buf_size] = '\0'; + return 0; +} - if (strtobool(buf, &enable) < 0) - return -EINVAL; +DEFINE_SIMPLE_ATTRIBUTE(supervision_timeout_fops, supervision_timeout_get, + supervision_timeout_set, "%llu\n"); - if (enable == test_bit(HCI_6LOWPAN_ENABLED, &hdev->dev_flags)) - return -EALREADY; +static int adv_channel_map_set(void *data, u64 val) +{ + struct hci_dev *hdev = data; - change_bit(HCI_6LOWPAN_ENABLED, &hdev->dev_flags); + if (val < 0x01 || val > 0x07) + return -EINVAL; - return count; -} + hci_dev_lock(hdev); + hdev->le_adv_channel_map = val; + hci_dev_unlock(hdev); -static const struct file_operations lowpan_debugfs_fops = { - .open = simple_open, - .read = lowpan_read, - .write = lowpan_write, - .llseek = default_llseek, -}; + return 0; +} -static int le_auto_conn_show(struct seq_file *sf, void *ptr) +static int adv_channel_map_get(void *data, u64 *val) { - struct hci_dev *hdev = sf->private; - struct hci_conn_params *p; + struct hci_dev *hdev = data; hci_dev_lock(hdev); + *val = hdev->le_adv_channel_map; + hci_dev_unlock(hdev); - list_for_each_entry(p, &hdev->le_conn_params, list) { - seq_printf(sf, "%pMR %u %u\n", &p->addr, p->addr_type, - p->auto_connect); - } + return 0; +} +DEFINE_SIMPLE_ATTRIBUTE(adv_channel_map_fops, adv_channel_map_get, + adv_channel_map_set, "%llu\n"); + +static int adv_min_interval_set(void *data, u64 val) +{ + struct hci_dev *hdev = data; + + if (val < 0x0020 || val > 0x4000 || val > hdev->le_adv_max_interval) + return -EINVAL; + + hci_dev_lock(hdev); + hdev->le_adv_min_interval = val; hci_dev_unlock(hdev); return 0; } -static int le_auto_conn_open(struct inode *inode, struct file *file) +static int adv_min_interval_get(void *data, u64 *val) { - return single_open(file, le_auto_conn_show, inode->i_private); + struct hci_dev *hdev = data; + + hci_dev_lock(hdev); + *val = hdev->le_adv_min_interval; + hci_dev_unlock(hdev); + + return 0; } -static ssize_t le_auto_conn_write(struct file *file, const char __user *data, - size_t count, loff_t *offset) +DEFINE_SIMPLE_ATTRIBUTE(adv_min_interval_fops, adv_min_interval_get, + adv_min_interval_set, "%llu\n"); + +static int adv_max_interval_set(void *data, u64 val) { - struct seq_file *sf = file->private_data; - struct hci_dev *hdev = sf->private; - u8 auto_connect = 0; - bdaddr_t addr; - u8 addr_type; - char *buf; - int err = 0; - int n; + struct hci_dev *hdev = data; - /* Don't allow partial write */ - if (*offset != 0) + if (val < 0x0020 || val > 0x4000 || val < hdev->le_adv_min_interval) return -EINVAL; - if (count < 3) - return -EINVAL; + hci_dev_lock(hdev); + hdev->le_adv_max_interval = val; + hci_dev_unlock(hdev); - buf = memdup_user(data, count); - if (IS_ERR(buf)) - return PTR_ERR(buf); + return 0; +} - if (memcmp(buf, "add", 3) == 0) { - n = sscanf(&buf[4], "%hhx:%hhx:%hhx:%hhx:%hhx:%hhx %hhu %hhu", - &addr.b[5], &addr.b[4], &addr.b[3], &addr.b[2], - &addr.b[1], &addr.b[0], &addr_type, - &auto_connect); +static int adv_max_interval_get(void *data, u64 *val) +{ + struct hci_dev *hdev = data; - if (n < 7) { - err = -EINVAL; - goto done; - } + hci_dev_lock(hdev); + *val = hdev->le_adv_max_interval; + hci_dev_unlock(hdev); - hci_dev_lock(hdev); - err = hci_conn_params_add(hdev, &addr, addr_type, auto_connect, - hdev->le_conn_min_interval, - hdev->le_conn_max_interval); - hci_dev_unlock(hdev); + return 0; +} - if (err) - goto done; - } else if (memcmp(buf, "del", 3) == 0) { - n = sscanf(&buf[4], "%hhx:%hhx:%hhx:%hhx:%hhx:%hhx %hhu", - &addr.b[5], &addr.b[4], &addr.b[3], &addr.b[2], - &addr.b[1], &addr.b[0], &addr_type); +DEFINE_SIMPLE_ATTRIBUTE(adv_max_interval_fops, adv_max_interval_get, + adv_max_interval_set, "%llu\n"); - if (n < 7) { - err = -EINVAL; - goto done; - } +static int device_list_show(struct seq_file *f, void *ptr) +{ + struct hci_dev *hdev = f->private; + struct hci_conn_params *p; - hci_dev_lock(hdev); - hci_conn_params_del(hdev, &addr, addr_type); - hci_dev_unlock(hdev); - } else if (memcmp(buf, "clr", 3) == 0) { - hci_dev_lock(hdev); - hci_conn_params_clear(hdev); - hci_pend_le_conns_clear(hdev); - hci_update_background_scan(hdev); - hci_dev_unlock(hdev); - } else { - err = -EINVAL; + hci_dev_lock(hdev); + list_for_each_entry(p, &hdev->le_conn_params, list) { + seq_printf(f, "%pMR %u %u\n", &p->addr, p->addr_type, + p->auto_connect); } + hci_dev_unlock(hdev); -done: - kfree(buf); + return 0; +} - if (err) - return err; - else - return count; +static int device_list_open(struct inode *inode, struct file *file) +{ + return single_open(file, device_list_show, inode->i_private); } -static const struct file_operations le_auto_conn_fops = { - .open = le_auto_conn_open, +static const struct file_operations device_list_fops = { + .open = device_list_open, .read = seq_read, - .write = le_auto_conn_write, .llseek = seq_lseek, .release = single_release, }; @@ -1426,9 +1404,6 @@ static void le_setup(struct hci_request *req) /* Read LE Supported States */ hci_req_add(req, HCI_OP_LE_READ_SUPPORTED_STATES, 0, NULL); - /* Read LE Advertising Channel TX Power */ - hci_req_add(req, HCI_OP_LE_READ_ADV_TX_POWER, 0, NULL); - /* Read LE White List Size */ hci_req_add(req, HCI_OP_LE_READ_WHITE_LIST_SIZE, 0, NULL); @@ -1503,14 +1478,17 @@ static void hci_setup_event_mask(struct hci_request *req) /* Use a different default for LE-only devices */ memset(events, 0, sizeof(events)); events[0] |= 0x10; /* Disconnection Complete */ - events[0] |= 0x80; /* Encryption Change */ events[1] |= 0x08; /* Read Remote Version Information Complete */ events[1] |= 0x20; /* Command Complete */ events[1] |= 0x40; /* Command Status */ events[1] |= 0x80; /* Hardware Error */ events[2] |= 0x04; /* Number of Completed Packets */ events[3] |= 0x02; /* Data Buffer Overflow */ - events[5] |= 0x80; /* Encryption Key Refresh Complete */ + + if (hdev->le_features[0] & HCI_LE_ENCRYPTION) { + events[0] |= 0x80; /* Encryption Change */ + events[5] |= 0x80; /* Encryption Key Refresh Complete */ + } } if (lmp_inq_rssi_capable(hdev)) @@ -1549,13 +1527,6 @@ static void hci_setup_event_mask(struct hci_request *req) events[7] |= 0x20; /* LE Meta-Event */ hci_req_add(req, HCI_OP_SET_EVENT_MASK, sizeof(events), events); - - if (lmp_le_capable(hdev)) { - memset(events, 0, sizeof(events)); - events[0] = 0x1f; - hci_req_add(req, HCI_OP_LE_SET_EVENT_MASK, - sizeof(events), events); - } } static void hci_init2_req(struct hci_request *req, unsigned long opt) @@ -1570,8 +1541,6 @@ static void hci_init2_req(struct hci_request *req, unsigned long opt) if (lmp_le_capable(hdev)) le_setup(req); - hci_setup_event_mask(req); - /* AVM Berlin (31), aka "BlueFRITZ!", doesn't support the read * local supported commands HCI command. */ @@ -1654,7 +1623,7 @@ static void hci_set_le_support(struct hci_request *req) if (test_bit(HCI_LE_ENABLED, &hdev->dev_flags)) { cp.le = 0x01; - cp.simul = lmp_le_br_capable(hdev); + cp.simul = 0x00; } if (cp.le != lmp_host_le_capable(hdev)) @@ -1688,7 +1657,7 @@ static void hci_set_event_mask_page_2(struct hci_request *req) } /* Enable Authenticated Payload Timeout Expired event if supported */ - if (lmp_ping_capable(hdev)) + if (lmp_ping_capable(hdev) || hdev->le_features[0] & HCI_LE_PING) events[2] |= 0x80; hci_req_add(req, HCI_OP_SET_EVENT_MASK_PAGE_2, sizeof(events), events); @@ -1699,6 +1668,8 @@ static void hci_init3_req(struct hci_request *req, unsigned long opt) struct hci_dev *hdev = req->hdev; u8 p; + hci_setup_event_mask(req); + /* Some Broadcom based Bluetooth controllers do not support the * Delete Stored Link Key command. They are clearly indicating its * absence in the bit mask of supported commands. @@ -1725,8 +1696,33 @@ static void hci_init3_req(struct hci_request *req, unsigned long opt) if (hdev->commands[5] & 0x10) hci_setup_link_policy(req); - if (lmp_le_capable(hdev)) + if (lmp_le_capable(hdev)) { + u8 events[8]; + + memset(events, 0, sizeof(events)); + events[0] = 0x0f; + + if (hdev->le_features[0] & HCI_LE_ENCRYPTION) + events[0] |= 0x10; /* LE Long Term Key Request */ + + /* If controller supports the Connection Parameters Request + * Link Layer Procedure, enable the corresponding event. + */ + if (hdev->le_features[0] & HCI_LE_CONN_PARAM_REQ_PROC) + events[0] |= 0x20; /* LE Remote Connection + * Parameter Request + */ + + hci_req_add(req, HCI_OP_LE_SET_EVENT_MASK, sizeof(events), + events); + + if (hdev->commands[25] & 0x40) { + /* Read LE Advertising Channel TX Power */ + hci_req_add(req, HCI_OP_LE_READ_ADV_TX_POWER, 0, NULL); + } + hci_set_le_support(req); + } /* Read features beyond page 1 if available */ for (p = 2; p < HCI_MAX_PAGES && p <= hdev->max_page; p++) { @@ -1746,13 +1742,21 @@ static void hci_init4_req(struct hci_request *req, unsigned long opt) if (hdev->commands[22] & 0x04) hci_set_event_mask_page_2(req); + /* Read local codec list if the HCI command is supported */ + if (hdev->commands[29] & 0x20) + hci_req_add(req, HCI_OP_READ_LOCAL_CODECS, 0, NULL); + + /* Get MWS transport configuration if the HCI command is supported */ + if (hdev->commands[30] & 0x08) + hci_req_add(req, HCI_OP_GET_MWS_TRANSPORT_CONFIG, 0, NULL); + /* Check for Synchronization Train support */ if (lmp_sync_train_capable(hdev)) hci_req_add(req, HCI_OP_READ_SYNC_TRAIN_PARAMS, 0, NULL); /* Enable Secure Connections if supported and configured */ if ((lmp_sc_capable(hdev) || - test_bit(HCI_FORCE_SC, &hdev->dev_flags)) && + test_bit(HCI_FORCE_SC, &hdev->dbg_flags)) && test_bit(HCI_SC_ENABLED, &hdev->dev_flags)) { u8 support = 0x01; hci_req_add(req, HCI_OP_WRITE_SC_SUPPORT, @@ -1809,6 +1813,8 @@ static int __hci_init(struct hci_dev *hdev) debugfs_create_u16("hci_revision", 0444, hdev->debugfs, &hdev->hci_rev); debugfs_create_file("blacklist", 0444, hdev->debugfs, hdev, &blacklist_fops); + debugfs_create_file("whitelist", 0444, hdev->debugfs, hdev, + &whitelist_fops); debugfs_create_file("uuids", 0444, hdev->debugfs, hdev, &uuids_fops); debugfs_create_file("conn_info_min_age", 0644, hdev->debugfs, hdev, @@ -1830,8 +1836,6 @@ static int __hci_init(struct hci_dev *hdev) if (lmp_ssp_capable(hdev)) { debugfs_create_file("auto_accept_delay", 0644, hdev->debugfs, hdev, &auto_accept_delay_fops); - debugfs_create_file("ssp_debug_mode", 0644, hdev->debugfs, - hdev, &ssp_debug_mode_fops); debugfs_create_file("force_sc_support", 0644, hdev->debugfs, hdev, &force_sc_support_fops); debugfs_create_file("sc_only_mode", 0444, hdev->debugfs, @@ -1879,12 +1883,18 @@ static int __hci_init(struct hci_dev *hdev) hdev, &conn_min_interval_fops); debugfs_create_file("conn_max_interval", 0644, hdev->debugfs, hdev, &conn_max_interval_fops); + debugfs_create_file("conn_latency", 0644, hdev->debugfs, + hdev, &conn_latency_fops); + debugfs_create_file("supervision_timeout", 0644, hdev->debugfs, + hdev, &supervision_timeout_fops); debugfs_create_file("adv_channel_map", 0644, hdev->debugfs, hdev, &adv_channel_map_fops); - debugfs_create_file("6lowpan", 0644, hdev->debugfs, hdev, - &lowpan_debugfs_fops); - debugfs_create_file("le_auto_conn", 0644, hdev->debugfs, hdev, - &le_auto_conn_fops); + debugfs_create_file("adv_min_interval", 0644, hdev->debugfs, + hdev, &adv_min_interval_fops); + debugfs_create_file("adv_max_interval", 0644, hdev->debugfs, + hdev, &adv_max_interval_fops); + debugfs_create_file("device_list", 0444, hdev->debugfs, hdev, + &device_list_fops); debugfs_create_u16("discov_interleaved_timeout", 0644, hdev->debugfs, &hdev->discov_interleaved_timeout); @@ -1893,6 +1903,38 @@ static int __hci_init(struct hci_dev *hdev) return 0; } +static void hci_init0_req(struct hci_request *req, unsigned long opt) +{ + struct hci_dev *hdev = req->hdev; + + BT_DBG("%s %ld", hdev->name, opt); + + /* Reset */ + if (!test_bit(HCI_QUIRK_RESET_ON_CLOSE, &hdev->quirks)) + hci_reset_req(req, 0); + + /* Read Local Version */ + hci_req_add(req, HCI_OP_READ_LOCAL_VERSION, 0, NULL); + + /* Read BD Address */ + if (hdev->set_bdaddr) + hci_req_add(req, HCI_OP_READ_BD_ADDR, 0, NULL); +} + +static int __hci_unconf_init(struct hci_dev *hdev) +{ + int err; + + if (test_bit(HCI_QUIRK_RAW_DEVICE, &hdev->quirks)) + return 0; + + err = __hci_req_sync(hdev, hci_init0_req, 0, HCI_INIT_TIMEOUT); + if (err < 0) + return err; + + return 0; +} + static void hci_scan_req(struct hci_request *req, unsigned long opt) { __u8 scan = opt; @@ -1973,16 +2015,20 @@ bool hci_discovery_active(struct hci_dev *hdev) void hci_discovery_set_state(struct hci_dev *hdev, int state) { + int old_state = hdev->discovery.state; + BT_DBG("%s state %u -> %u", hdev->name, hdev->discovery.state, state); - if (hdev->discovery.state == state) + if (old_state == state) return; + hdev->discovery.state = state; + switch (state) { case DISCOVERY_STOPPED: hci_update_background_scan(hdev); - if (hdev->discovery.state != DISCOVERY_STARTING) + if (old_state != DISCOVERY_STARTING) mgmt_discovering(hdev, 0); break; case DISCOVERY_STARTING: @@ -1995,8 +2041,6 @@ void hci_discovery_set_state(struct hci_dev *hdev, int state) case DISCOVERY_STOPPING: break; } - - hdev->discovery.state = state; } void hci_inquiry_cache_flush(struct hci_dev *hdev) @@ -2083,22 +2127,24 @@ void hci_inquiry_cache_update_resolve(struct hci_dev *hdev, list_add(&ie->list, pos); } -bool hci_inquiry_cache_update(struct hci_dev *hdev, struct inquiry_data *data, - bool name_known, bool *ssp) +u32 hci_inquiry_cache_update(struct hci_dev *hdev, struct inquiry_data *data, + bool name_known) { struct discovery_state *cache = &hdev->discovery; struct inquiry_entry *ie; + u32 flags = 0; BT_DBG("cache %p, %pMR", cache, &data->bdaddr); hci_remove_remote_oob_data(hdev, &data->bdaddr); - *ssp = data->ssp_mode; + if (!data->ssp_mode) + flags |= MGMT_DEV_FOUND_LEGACY_PAIRING; ie = hci_inquiry_cache_lookup(hdev, &data->bdaddr); if (ie) { - if (ie->data.ssp_mode) - *ssp = true; + if (!ie->data.ssp_mode) + flags |= MGMT_DEV_FOUND_LEGACY_PAIRING; if (ie->name_state == NAME_NEEDED && data->rssi != ie->data.rssi) { @@ -2110,9 +2156,11 @@ bool hci_inquiry_cache_update(struct hci_dev *hdev, struct inquiry_data *data, } /* Entry not in the cache. Add new one. */ - ie = kzalloc(sizeof(struct inquiry_entry), GFP_ATOMIC); - if (!ie) - return false; + ie = kzalloc(sizeof(*ie), GFP_KERNEL); + if (!ie) { + flags |= MGMT_DEV_FOUND_CONFIRM_NAME; + goto done; + } list_add(&ie->all, &cache->all); @@ -2135,9 +2183,10 @@ update: cache->timestamp = jiffies; if (ie->name_state == NAME_NOT_KNOWN) - return false; + flags |= MGMT_DEV_FOUND_CONFIRM_NAME; - return true; +done: + return flags; } static int inquiry_cache_dump(struct hci_dev *hdev, int num, __u8 *buf) @@ -2207,6 +2256,11 @@ int hci_inquiry(void __user *arg) goto done; } + if (test_bit(HCI_UNCONFIGURED, &hdev->dev_flags)) { + err = -EOPNOTSUPP; + goto done; + } + if (hdev->dev_type != HCI_BREDR) { err = -EOPNOTSUPP; goto done; @@ -2289,7 +2343,8 @@ static int hci_dev_do_open(struct hci_dev *hdev) goto done; } - if (!test_bit(HCI_SETUP, &hdev->dev_flags)) { + if (!test_bit(HCI_SETUP, &hdev->dev_flags) && + !test_bit(HCI_CONFIG, &hdev->dev_flags)) { /* Check for rfkill but allow the HCI setup stage to * proceed (which in itself doesn't cause any RF activity). */ @@ -2332,14 +2387,47 @@ static int hci_dev_do_open(struct hci_dev *hdev) atomic_set(&hdev->cmd_cnt, 1); set_bit(HCI_INIT, &hdev->flags); - if (hdev->setup && test_bit(HCI_SETUP, &hdev->dev_flags)) - ret = hdev->setup(hdev); + if (test_bit(HCI_SETUP, &hdev->dev_flags)) { + if (hdev->setup) + ret = hdev->setup(hdev); - if (!ret) { - if (test_bit(HCI_QUIRK_RAW_DEVICE, &hdev->quirks)) - set_bit(HCI_RAW, &hdev->flags); + /* The transport driver can set these quirks before + * creating the HCI device or in its setup callback. + * + * In case any of them is set, the controller has to + * start up as unconfigured. + */ + if (test_bit(HCI_QUIRK_EXTERNAL_CONFIG, &hdev->quirks) || + test_bit(HCI_QUIRK_INVALID_BDADDR, &hdev->quirks)) + set_bit(HCI_UNCONFIGURED, &hdev->dev_flags); + + /* For an unconfigured controller it is required to + * read at least the version information provided by + * the Read Local Version Information command. + * + * If the set_bdaddr driver callback is provided, then + * also the original Bluetooth public device address + * will be read using the Read BD Address command. + */ + if (test_bit(HCI_UNCONFIGURED, &hdev->dev_flags)) + ret = __hci_unconf_init(hdev); + } - if (!test_bit(HCI_RAW, &hdev->flags) && + if (test_bit(HCI_CONFIG, &hdev->dev_flags)) { + /* If public address change is configured, ensure that + * the address gets programmed. If the driver does not + * support changing the public address, fail the power + * on procedure. + */ + if (bacmp(&hdev->public_addr, BDADDR_ANY) && + hdev->set_bdaddr) + ret = hdev->set_bdaddr(hdev, &hdev->public_addr); + else + ret = -EADDRNOTAVAIL; + } + + if (!ret) { + if (!test_bit(HCI_UNCONFIGURED, &hdev->dev_flags) && !test_bit(HCI_USER_CHANNEL, &hdev->dev_flags)) ret = __hci_init(hdev); } @@ -2352,6 +2440,8 @@ static int hci_dev_do_open(struct hci_dev *hdev) set_bit(HCI_UP, &hdev->flags); hci_notify(hdev, HCI_DEV_UP); if (!test_bit(HCI_SETUP, &hdev->dev_flags) && + !test_bit(HCI_CONFIG, &hdev->dev_flags) && + !test_bit(HCI_UNCONFIGURED, &hdev->dev_flags) && !test_bit(HCI_USER_CHANNEL, &hdev->dev_flags) && hdev->dev_type == HCI_BREDR) { hci_dev_lock(hdev); @@ -2376,7 +2466,7 @@ static int hci_dev_do_open(struct hci_dev *hdev) } hdev->close(hdev); - hdev->flags = 0; + hdev->flags &= BIT(HCI_RAW); } done: @@ -2395,6 +2485,21 @@ int hci_dev_open(__u16 dev) if (!hdev) return -ENODEV; + /* Devices that are marked as unconfigured can only be powered + * up as user channel. Trying to bring them up as normal devices + * will result into a failure. Only user channel operation is + * possible. + * + * When this function is called for a user channel, the flag + * HCI_USER_CHANNEL will be set first before attempting to + * open the device. + */ + if (test_bit(HCI_UNCONFIGURED, &hdev->dev_flags) && + !test_bit(HCI_USER_CHANNEL, &hdev->dev_flags)) { + err = -EOPNOTSUPP; + goto done; + } + /* We need to ensure that no other power on/off work is pending * before proceeding to call hci_dev_do_open. This is * particularly important if the setup procedure has not yet @@ -2409,13 +2514,34 @@ int hci_dev_open(__u16 dev) */ flush_workqueue(hdev->req_workqueue); + /* For controllers not using the management interface and that + * are brought up using legacy ioctl, set the HCI_BONDABLE bit + * so that pairing works for them. Once the management interface + * is in use this bit will be cleared again and userspace has + * to explicitly enable it. + */ + if (!test_bit(HCI_USER_CHANNEL, &hdev->dev_flags) && + !test_bit(HCI_MGMT, &hdev->dev_flags)) + set_bit(HCI_BONDABLE, &hdev->dev_flags); + err = hci_dev_do_open(hdev); +done: hci_dev_put(hdev); - return err; } +/* This function requires the caller holds hdev->lock */ +static void hci_pend_le_actions_clear(struct hci_dev *hdev) +{ + struct hci_conn_params *p; + + list_for_each_entry(p, &hdev->le_conn_params, list) + list_del_init(&p->action); + + BT_DBG("All LE pending actions cleared"); +} + static int hci_dev_do_close(struct hci_dev *hdev) { BT_DBG("%s %p", hdev->name, hdev); @@ -2426,7 +2552,7 @@ static int hci_dev_do_close(struct hci_dev *hdev) hci_req_lock(hdev); if (!test_and_clear_bit(HCI_UP, &hdev->flags)) { - del_timer_sync(&hdev->cmd_timer); + cancel_delayed_work_sync(&hdev->cmd_timer); hci_req_unlock(hdev); return 0; } @@ -2453,7 +2579,7 @@ static int hci_dev_do_close(struct hci_dev *hdev) hci_dev_lock(hdev); hci_inquiry_cache_flush(hdev); hci_conn_hash_flush(hdev); - hci_pend_le_conns_clear(hdev); + hci_pend_le_actions_clear(hdev); hci_dev_unlock(hdev); hci_notify(hdev, HCI_DEV_DOWN); @@ -2464,8 +2590,8 @@ static int hci_dev_do_close(struct hci_dev *hdev) /* Reset device */ skb_queue_purge(&hdev->cmd_q); atomic_set(&hdev->cmd_cnt, 1); - if (!test_bit(HCI_RAW, &hdev->flags) && - !test_bit(HCI_AUTO_OFF, &hdev->dev_flags) && + if (!test_bit(HCI_AUTO_OFF, &hdev->dev_flags) && + !test_bit(HCI_UNCONFIGURED, &hdev->dev_flags) && test_bit(HCI_QUIRK_RESET_ON_CLOSE, &hdev->quirks)) { set_bit(HCI_INIT, &hdev->flags); __hci_req_sync(hdev, hci_reset_req, 0, HCI_CMD_TIMEOUT); @@ -2482,7 +2608,7 @@ static int hci_dev_do_close(struct hci_dev *hdev) /* Drop last sent command */ if (hdev->sent_cmd) { - del_timer_sync(&hdev->cmd_timer); + cancel_delayed_work_sync(&hdev->cmd_timer); kfree_skb(hdev->sent_cmd); hdev->sent_cmd = NULL; } @@ -2495,7 +2621,7 @@ static int hci_dev_do_close(struct hci_dev *hdev) hdev->close(hdev); /* Clear flags */ - hdev->flags = 0; + hdev->flags &= BIT(HCI_RAW); hdev->dev_flags &= ~HCI_PERSISTENT_MASK; if (!test_and_clear_bit(HCI_AUTO_OFF, &hdev->dev_flags)) { @@ -2564,6 +2690,11 @@ int hci_dev_reset(__u16 dev) goto done; } + if (test_bit(HCI_UNCONFIGURED, &hdev->dev_flags)) { + ret = -EOPNOTSUPP; + goto done; + } + /* Drop queues */ skb_queue_purge(&hdev->rx_q); skb_queue_purge(&hdev->cmd_q); @@ -2579,8 +2710,7 @@ int hci_dev_reset(__u16 dev) atomic_set(&hdev->cmd_cnt, 1); hdev->acl_cnt = 0; hdev->sco_cnt = 0; hdev->le_cnt = 0; - if (!test_bit(HCI_RAW, &hdev->flags)) - ret = __hci_req_sync(hdev, hci_reset_req, 0, HCI_INIT_TIMEOUT); + ret = __hci_req_sync(hdev, hci_reset_req, 0, HCI_INIT_TIMEOUT); done: hci_req_unlock(hdev); @@ -2602,6 +2732,11 @@ int hci_dev_reset_stat(__u16 dev) goto done; } + if (test_bit(HCI_UNCONFIGURED, &hdev->dev_flags)) { + ret = -EOPNOTSUPP; + goto done; + } + memset(&hdev->stat, 0, sizeof(struct hci_dev_stats)); done: @@ -2609,6 +2744,42 @@ done: return ret; } +static void hci_update_scan_state(struct hci_dev *hdev, u8 scan) +{ + bool conn_changed, discov_changed; + + BT_DBG("%s scan 0x%02x", hdev->name, scan); + + if ((scan & SCAN_PAGE)) + conn_changed = !test_and_set_bit(HCI_CONNECTABLE, + &hdev->dev_flags); + else + conn_changed = test_and_clear_bit(HCI_CONNECTABLE, + &hdev->dev_flags); + + if ((scan & SCAN_INQUIRY)) { + discov_changed = !test_and_set_bit(HCI_DISCOVERABLE, + &hdev->dev_flags); + } else { + clear_bit(HCI_LIMITED_DISCOVERABLE, &hdev->dev_flags); + discov_changed = test_and_clear_bit(HCI_DISCOVERABLE, + &hdev->dev_flags); + } + + if (!test_bit(HCI_MGMT, &hdev->dev_flags)) + return; + + if (conn_changed || discov_changed) { + /* In case this was disabled through mgmt */ + set_bit(HCI_BREDR_ENABLED, &hdev->dev_flags); + + if (test_bit(HCI_LE_ENABLED, &hdev->dev_flags)) + mgmt_update_adv_data(hdev); + + mgmt_new_settings(hdev); + } +} + int hci_dev_cmd(unsigned int cmd, void __user *arg) { struct hci_dev *hdev; @@ -2627,6 +2798,11 @@ int hci_dev_cmd(unsigned int cmd, void __user *arg) goto done; } + if (test_bit(HCI_UNCONFIGURED, &hdev->dev_flags)) { + err = -EOPNOTSUPP; + goto done; + } + if (hdev->dev_type != HCI_BREDR) { err = -EOPNOTSUPP; goto done; @@ -2664,6 +2840,12 @@ int hci_dev_cmd(unsigned int cmd, void __user *arg) case HCISETSCAN: err = hci_req_sync(hdev, hci_scan_req, dr.dev_opt, HCI_INIT_TIMEOUT); + + /* Ensure that the connectable and discoverable states + * get correctly modified as this was a non-mgmt change. + */ + if (!err) + hci_update_scan_state(hdev, dr.dev_opt); break; case HCISETLINKPOL: @@ -2724,14 +2906,17 @@ int hci_get_dev_list(void __user *arg) read_lock(&hci_dev_list_lock); list_for_each_entry(hdev, &hci_dev_list, list) { - if (test_and_clear_bit(HCI_AUTO_OFF, &hdev->dev_flags)) - cancel_delayed_work(&hdev->power_off); + unsigned long flags = hdev->flags; - if (!test_bit(HCI_MGMT, &hdev->dev_flags)) - set_bit(HCI_PAIRABLE, &hdev->dev_flags); + /* When the auto-off is configured it means the transport + * is running, but in that case still indicate that the + * device is actually down. + */ + if (test_bit(HCI_AUTO_OFF, &hdev->dev_flags)) + flags &= ~BIT(HCI_UP); (dr + n)->dev_id = hdev->id; - (dr + n)->dev_opt = hdev->flags; + (dr + n)->dev_opt = flags; if (++n >= dev_num) break; @@ -2751,6 +2936,7 @@ int hci_get_dev_info(void __user *arg) { struct hci_dev *hdev; struct hci_dev_info di; + unsigned long flags; int err = 0; if (copy_from_user(&di, arg, sizeof(di))) @@ -2760,16 +2946,19 @@ int hci_get_dev_info(void __user *arg) if (!hdev) return -ENODEV; - if (test_and_clear_bit(HCI_AUTO_OFF, &hdev->dev_flags)) - cancel_delayed_work_sync(&hdev->power_off); - - if (!test_bit(HCI_MGMT, &hdev->dev_flags)) - set_bit(HCI_PAIRABLE, &hdev->dev_flags); + /* When the auto-off is configured it means the transport + * is running, but in that case still indicate that the + * device is actually down. + */ + if (test_bit(HCI_AUTO_OFF, &hdev->dev_flags)) + flags = hdev->flags & ~BIT(HCI_UP); + else + flags = hdev->flags; strcpy(di.name, hdev->name); di.bdaddr = hdev->bdaddr; di.type = (hdev->bus & 0x0f) | ((hdev->dev_type & 0x03) << 4); - di.flags = hdev->flags; + di.flags = flags; di.pkt_type = hdev->pkt_type; if (lmp_bredr_capable(hdev)) { di.acl_mtu = hdev->acl_mtu; @@ -2809,7 +2998,8 @@ static int hci_rfkill_set_block(void *data, bool blocked) if (blocked) { set_bit(HCI_RFKILLED, &hdev->dev_flags); - if (!test_bit(HCI_SETUP, &hdev->dev_flags)) + if (!test_bit(HCI_SETUP, &hdev->dev_flags) && + !test_bit(HCI_CONFIG, &hdev->dev_flags)) hci_dev_do_close(hdev); } else { clear_bit(HCI_RFKILLED, &hdev->dev_flags); @@ -2840,6 +3030,7 @@ static void hci_power_on(struct work_struct *work) * valid, it is important to turn the device back off. */ if (test_bit(HCI_RFKILLED, &hdev->dev_flags) || + test_bit(HCI_UNCONFIGURED, &hdev->dev_flags) || (hdev->dev_type == HCI_BREDR && !bacmp(&hdev->bdaddr, BDADDR_ANY) && !bacmp(&hdev->static_addr, BDADDR_ANY))) { @@ -2850,8 +3041,34 @@ static void hci_power_on(struct work_struct *work) HCI_AUTO_OFF_TIMEOUT); } - if (test_and_clear_bit(HCI_SETUP, &hdev->dev_flags)) + if (test_and_clear_bit(HCI_SETUP, &hdev->dev_flags)) { + /* For unconfigured devices, set the HCI_RAW flag + * so that userspace can easily identify them. + */ + if (test_bit(HCI_UNCONFIGURED, &hdev->dev_flags)) + set_bit(HCI_RAW, &hdev->flags); + + /* For fully configured devices, this will send + * the Index Added event. For unconfigured devices, + * it will send Unconfigued Index Added event. + * + * Devices with HCI_QUIRK_RAW_DEVICE are ignored + * and no event will be send. + */ mgmt_index_added(hdev); + } else if (test_and_clear_bit(HCI_CONFIG, &hdev->dev_flags)) { + /* When the controller is now configured, then it + * is important to clear the HCI_RAW flag. + */ + if (!test_bit(HCI_UNCONFIGURED, &hdev->dev_flags)) + clear_bit(HCI_RAW, &hdev->flags); + + /* Powering on the controller with HCI_CONFIG set only + * happens with the transition from unconfigured to + * configured. This will send the Index Added event. + */ + mgmt_index_added(hdev); + } } static void hci_power_off(struct work_struct *work) @@ -2966,16 +3183,16 @@ static bool hci_persistent_key(struct hci_dev *hdev, struct hci_conn *conn, return false; } -static bool ltk_type_master(u8 type) +static u8 ltk_role(u8 type) { - if (type == HCI_SMP_STK || type == HCI_SMP_LTK) - return true; + if (type == SMP_LTK) + return HCI_ROLE_MASTER; - return false; + return HCI_ROLE_SLAVE; } struct smp_ltk *hci_find_ltk(struct hci_dev *hdev, __le16 ediv, __le64 rand, - bool master) + u8 role) { struct smp_ltk *k; @@ -2983,7 +3200,7 @@ struct smp_ltk *hci_find_ltk(struct hci_dev *hdev, __le16 ediv, __le64 rand, if (k->ediv != ediv || k->rand != rand) continue; - if (ltk_type_master(k->type) != master) + if (ltk_role(k->type) != role) continue; return k; @@ -2993,14 +3210,14 @@ struct smp_ltk *hci_find_ltk(struct hci_dev *hdev, __le16 ediv, __le64 rand, } struct smp_ltk *hci_find_ltk_by_addr(struct hci_dev *hdev, bdaddr_t *bdaddr, - u8 addr_type, bool master) + u8 addr_type, u8 role) { struct smp_ltk *k; list_for_each_entry(k, &hdev->long_term_keys, list) if (addr_type == k->bdaddr_type && bacmp(bdaddr, &k->bdaddr) == 0 && - ltk_type_master(k->type) == master) + ltk_role(k->type) == role) return k; return NULL; @@ -3043,12 +3260,12 @@ struct smp_irk *hci_find_irk_by_addr(struct hci_dev *hdev, bdaddr_t *bdaddr, return NULL; } -int hci_add_link_key(struct hci_dev *hdev, struct hci_conn *conn, int new_key, - bdaddr_t *bdaddr, u8 *val, u8 type, u8 pin_len) +struct link_key *hci_add_link_key(struct hci_dev *hdev, struct hci_conn *conn, + bdaddr_t *bdaddr, u8 *val, u8 type, + u8 pin_len, bool *persistent) { struct link_key *key, *old_key; u8 old_key_type; - bool persistent; old_key = hci_find_link_key(hdev, bdaddr); if (old_key) { @@ -3058,7 +3275,7 @@ int hci_add_link_key(struct hci_dev *hdev, struct hci_conn *conn, int new_key, old_key_type = conn ? conn->key_type : 0xff; key = kzalloc(sizeof(*key), GFP_KERNEL); if (!key) - return -ENOMEM; + return NULL; list_add(&key->list, &hdev->link_keys); } @@ -3083,17 +3300,11 @@ int hci_add_link_key(struct hci_dev *hdev, struct hci_conn *conn, int new_key, else key->type = type; - if (!new_key) - return 0; - - persistent = hci_persistent_key(hdev, conn, type, old_key_type); - - mgmt_new_link_key(hdev, key, persistent); + if (persistent) + *persistent = hci_persistent_key(hdev, conn, type, + old_key_type); - if (conn) - conn->flush_key = !persistent; - - return 0; + return key; } struct smp_ltk *hci_add_ltk(struct hci_dev *hdev, bdaddr_t *bdaddr, @@ -3101,9 +3312,9 @@ struct smp_ltk *hci_add_ltk(struct hci_dev *hdev, bdaddr_t *bdaddr, u8 tk[16], u8 enc_size, __le16 ediv, __le64 rand) { struct smp_ltk *key, *old_key; - bool master = ltk_type_master(type); + u8 role = ltk_role(type); - old_key = hci_find_ltk_by_addr(hdev, bdaddr, addr_type, master); + old_key = hci_find_ltk_by_addr(hdev, bdaddr, addr_type, role); if (old_key) key = old_key; else { @@ -3199,9 +3410,10 @@ void hci_remove_irk(struct hci_dev *hdev, bdaddr_t *bdaddr, u8 addr_type) } /* HCI command timer function */ -static void hci_cmd_timeout(unsigned long arg) +static void hci_cmd_timeout(struct work_struct *work) { - struct hci_dev *hdev = (void *) arg; + struct hci_dev *hdev = container_of(work, struct hci_dev, + cmd_timer.work); if (hdev->sent_cmd) { struct hci_command_hdr *sent = (void *) hdev->sent_cmd->data; @@ -3307,12 +3519,12 @@ int hci_add_remote_oob_ext_data(struct hci_dev *hdev, bdaddr_t *bdaddr, return 0; } -struct bdaddr_list *hci_blacklist_lookup(struct hci_dev *hdev, +struct bdaddr_list *hci_bdaddr_list_lookup(struct list_head *bdaddr_list, bdaddr_t *bdaddr, u8 type) { struct bdaddr_list *b; - list_for_each_entry(b, &hdev->blacklist, list) { + list_for_each_entry(b, bdaddr_list, list) { if (!bacmp(&b->bdaddr, bdaddr) && b->bdaddr_type == type) return b; } @@ -3320,11 +3532,11 @@ struct bdaddr_list *hci_blacklist_lookup(struct hci_dev *hdev, return NULL; } -static void hci_blacklist_clear(struct hci_dev *hdev) +void hci_bdaddr_list_clear(struct list_head *bdaddr_list) { struct list_head *p, *n; - list_for_each_safe(p, n, &hdev->blacklist) { + list_for_each_safe(p, n, bdaddr_list) { struct bdaddr_list *b = list_entry(p, struct bdaddr_list, list); list_del(p); @@ -3332,99 +3544,38 @@ static void hci_blacklist_clear(struct hci_dev *hdev) } } -int hci_blacklist_add(struct hci_dev *hdev, bdaddr_t *bdaddr, u8 type) +int hci_bdaddr_list_add(struct list_head *list, bdaddr_t *bdaddr, u8 type) { struct bdaddr_list *entry; if (!bacmp(bdaddr, BDADDR_ANY)) return -EBADF; - if (hci_blacklist_lookup(hdev, bdaddr, type)) + if (hci_bdaddr_list_lookup(list, bdaddr, type)) return -EEXIST; - entry = kzalloc(sizeof(struct bdaddr_list), GFP_KERNEL); + entry = kzalloc(sizeof(*entry), GFP_KERNEL); if (!entry) return -ENOMEM; bacpy(&entry->bdaddr, bdaddr); entry->bdaddr_type = type; - list_add(&entry->list, &hdev->blacklist); + list_add(&entry->list, list); - return mgmt_device_blocked(hdev, bdaddr, type); + return 0; } -int hci_blacklist_del(struct hci_dev *hdev, bdaddr_t *bdaddr, u8 type) +int hci_bdaddr_list_del(struct list_head *list, bdaddr_t *bdaddr, u8 type) { struct bdaddr_list *entry; if (!bacmp(bdaddr, BDADDR_ANY)) { - hci_blacklist_clear(hdev); + hci_bdaddr_list_clear(list); return 0; } - entry = hci_blacklist_lookup(hdev, bdaddr, type); - if (!entry) - return -ENOENT; - - list_del(&entry->list); - kfree(entry); - - return mgmt_device_unblocked(hdev, bdaddr, type); -} - -struct bdaddr_list *hci_white_list_lookup(struct hci_dev *hdev, - bdaddr_t *bdaddr, u8 type) -{ - struct bdaddr_list *b; - - list_for_each_entry(b, &hdev->le_white_list, list) { - if (!bacmp(&b->bdaddr, bdaddr) && b->bdaddr_type == type) - return b; - } - - return NULL; -} - -void hci_white_list_clear(struct hci_dev *hdev) -{ - struct list_head *p, *n; - - list_for_each_safe(p, n, &hdev->le_white_list) { - struct bdaddr_list *b = list_entry(p, struct bdaddr_list, list); - - list_del(p); - kfree(b); - } -} - -int hci_white_list_add(struct hci_dev *hdev, bdaddr_t *bdaddr, u8 type) -{ - struct bdaddr_list *entry; - - if (!bacmp(bdaddr, BDADDR_ANY)) - return -EBADF; - - entry = kzalloc(sizeof(struct bdaddr_list), GFP_KERNEL); - if (!entry) - return -ENOMEM; - - bacpy(&entry->bdaddr, bdaddr); - entry->bdaddr_type = type; - - list_add(&entry->list, &hdev->le_white_list); - - return 0; -} - -int hci_white_list_del(struct hci_dev *hdev, bdaddr_t *bdaddr, u8 type) -{ - struct bdaddr_list *entry; - - if (!bacmp(bdaddr, BDADDR_ANY)) - return -EBADF; - - entry = hci_white_list_lookup(hdev, bdaddr, type); + entry = hci_bdaddr_list_lookup(list, bdaddr, type); if (!entry) return -ENOENT; @@ -3440,6 +3591,10 @@ struct hci_conn_params *hci_conn_params_lookup(struct hci_dev *hdev, { struct hci_conn_params *params; + /* The conn params list only contains identity addresses */ + if (!hci_is_identity_address(addr, addr_type)) + return NULL; + list_for_each_entry(params, &hdev->le_conn_params, list) { if (bacmp(¶ms->addr, addr) == 0 && params->addr_type == addr_type) { @@ -3467,62 +3622,98 @@ static bool is_connected(struct hci_dev *hdev, bdaddr_t *addr, u8 type) return true; } -static bool is_identity_address(bdaddr_t *addr, u8 addr_type) +/* This function requires the caller holds hdev->lock */ +struct hci_conn_params *hci_pend_le_action_lookup(struct list_head *list, + bdaddr_t *addr, u8 addr_type) { - if (addr_type == ADDR_LE_DEV_PUBLIC) - return true; + struct hci_conn_params *param; - /* Check for Random Static address type */ - if ((addr->b[5] & 0xc0) == 0xc0) - return true; + /* The list only contains identity addresses */ + if (!hci_is_identity_address(addr, addr_type)) + return NULL; - return false; + list_for_each_entry(param, list, action) { + if (bacmp(¶m->addr, addr) == 0 && + param->addr_type == addr_type) + return param; + } + + return NULL; } /* This function requires the caller holds hdev->lock */ -int hci_conn_params_add(struct hci_dev *hdev, bdaddr_t *addr, u8 addr_type, - u8 auto_connect, u16 conn_min_interval, - u16 conn_max_interval) +struct hci_conn_params *hci_conn_params_add(struct hci_dev *hdev, + bdaddr_t *addr, u8 addr_type) { struct hci_conn_params *params; - if (!is_identity_address(addr, addr_type)) - return -EINVAL; + if (!hci_is_identity_address(addr, addr_type)) + return NULL; params = hci_conn_params_lookup(hdev, addr, addr_type); if (params) - goto update; + return params; params = kzalloc(sizeof(*params), GFP_KERNEL); if (!params) { BT_ERR("Out of memory"); - return -ENOMEM; + return NULL; } bacpy(¶ms->addr, addr); params->addr_type = addr_type; list_add(¶ms->list, &hdev->le_conn_params); + INIT_LIST_HEAD(¶ms->action); -update: - params->conn_min_interval = conn_min_interval; - params->conn_max_interval = conn_max_interval; - params->auto_connect = auto_connect; + params->conn_min_interval = hdev->le_conn_min_interval; + params->conn_max_interval = hdev->le_conn_max_interval; + params->conn_latency = hdev->le_conn_latency; + params->supervision_timeout = hdev->le_supv_timeout; + params->auto_connect = HCI_AUTO_CONN_DISABLED; + + BT_DBG("addr %pMR (type %u)", addr, addr_type); + + return params; +} + +/* This function requires the caller holds hdev->lock */ +int hci_conn_params_set(struct hci_dev *hdev, bdaddr_t *addr, u8 addr_type, + u8 auto_connect) +{ + struct hci_conn_params *params; + + params = hci_conn_params_add(hdev, addr, addr_type); + if (!params) + return -EIO; + + if (params->auto_connect == auto_connect) + return 0; + + list_del_init(¶ms->action); switch (auto_connect) { case HCI_AUTO_CONN_DISABLED: case HCI_AUTO_CONN_LINK_LOSS: - hci_pend_le_conn_del(hdev, addr, addr_type); + hci_update_background_scan(hdev); + break; + case HCI_AUTO_CONN_REPORT: + list_add(¶ms->action, &hdev->pend_le_reports); + hci_update_background_scan(hdev); break; + case HCI_AUTO_CONN_DIRECT: case HCI_AUTO_CONN_ALWAYS: - if (!is_connected(hdev, addr, addr_type)) - hci_pend_le_conn_add(hdev, addr, addr_type); + if (!is_connected(hdev, addr, addr_type)) { + list_add(¶ms->action, &hdev->pend_le_conns); + hci_update_background_scan(hdev); + } break; } - BT_DBG("addr %pMR (type %u) auto_connect %u conn_min_interval 0x%.4x " - "conn_max_interval 0x%.4x", addr, addr_type, auto_connect, - conn_min_interval, conn_max_interval); + params->auto_connect = auto_connect; + + BT_DBG("addr %pMR (type %u) auto_connect %u", addr, addr_type, + auto_connect); return 0; } @@ -3536,97 +3727,44 @@ void hci_conn_params_del(struct hci_dev *hdev, bdaddr_t *addr, u8 addr_type) if (!params) return; - hci_pend_le_conn_del(hdev, addr, addr_type); - + list_del(¶ms->action); list_del(¶ms->list); kfree(params); + hci_update_background_scan(hdev); + BT_DBG("addr %pMR (type %u)", addr, addr_type); } /* This function requires the caller holds hdev->lock */ -void hci_conn_params_clear(struct hci_dev *hdev) +void hci_conn_params_clear_disabled(struct hci_dev *hdev) { struct hci_conn_params *params, *tmp; list_for_each_entry_safe(params, tmp, &hdev->le_conn_params, list) { + if (params->auto_connect != HCI_AUTO_CONN_DISABLED) + continue; list_del(¶ms->list); kfree(params); } - BT_DBG("All LE connection parameters were removed"); + BT_DBG("All LE disabled connection parameters were removed"); } /* This function requires the caller holds hdev->lock */ -struct bdaddr_list *hci_pend_le_conn_lookup(struct hci_dev *hdev, - bdaddr_t *addr, u8 addr_type) +void hci_conn_params_clear_all(struct hci_dev *hdev) { - struct bdaddr_list *entry; - - list_for_each_entry(entry, &hdev->pend_le_conns, list) { - if (bacmp(&entry->bdaddr, addr) == 0 && - entry->bdaddr_type == addr_type) - return entry; - } - - return NULL; -} - -/* This function requires the caller holds hdev->lock */ -void hci_pend_le_conn_add(struct hci_dev *hdev, bdaddr_t *addr, u8 addr_type) -{ - struct bdaddr_list *entry; - - entry = hci_pend_le_conn_lookup(hdev, addr, addr_type); - if (entry) - goto done; + struct hci_conn_params *params, *tmp; - entry = kzalloc(sizeof(*entry), GFP_KERNEL); - if (!entry) { - BT_ERR("Out of memory"); - return; + list_for_each_entry_safe(params, tmp, &hdev->le_conn_params, list) { + list_del(¶ms->action); + list_del(¶ms->list); + kfree(params); } - bacpy(&entry->bdaddr, addr); - entry->bdaddr_type = addr_type; - - list_add(&entry->list, &hdev->pend_le_conns); - - BT_DBG("addr %pMR (type %u)", addr, addr_type); - -done: hci_update_background_scan(hdev); -} - -/* This function requires the caller holds hdev->lock */ -void hci_pend_le_conn_del(struct hci_dev *hdev, bdaddr_t *addr, u8 addr_type) -{ - struct bdaddr_list *entry; - - entry = hci_pend_le_conn_lookup(hdev, addr, addr_type); - if (!entry) - goto done; - list_del(&entry->list); - kfree(entry); - - BT_DBG("addr %pMR (type %u)", addr, addr_type); - -done: - hci_update_background_scan(hdev); -} - -/* This function requires the caller holds hdev->lock */ -void hci_pend_le_conns_clear(struct hci_dev *hdev) -{ - struct bdaddr_list *entry, *tmp; - - list_for_each_entry_safe(entry, tmp, &hdev->pend_le_conns, list) { - list_del(&entry->list); - kfree(entry); - } - - BT_DBG("All LE pending connections cleared"); + BT_DBG("All LE connection parameters were removed"); } static void inquiry_complete(struct hci_dev *hdev, u8 status) @@ -3716,7 +3854,7 @@ static void set_random_addr(struct hci_request *req, bdaddr_t *rpa) * In this kind of scenario skip the update and let the random * address be updated at the next cycle. */ - if (test_bit(HCI_ADVERTISING, &hdev->dev_flags) || + if (test_bit(HCI_LE_ADV, &hdev->dev_flags) || hci_conn_hash_lookup_state(hdev, LE_LINK, BT_CONNECT)) { BT_DBG("Deferring random address update"); return; @@ -3778,7 +3916,7 @@ int hci_update_random_address(struct hci_request *req, bool require_privacy, * the HCI command if the current random address is already the * static one. */ - if (test_bit(HCI_FORCE_STATIC_ADDR, &hdev->dev_flags) || + if (test_bit(HCI_FORCE_STATIC_ADDR, &hdev->dbg_flags) || !bacmp(&hdev->bdaddr, BDADDR_ANY)) { *own_addr_type = ADDR_LE_DEV_RANDOM; if (bacmp(&hdev->static_addr, &hdev->random_addr)) @@ -3807,7 +3945,7 @@ int hci_update_random_address(struct hci_request *req, bool require_privacy, void hci_copy_identity_address(struct hci_dev *hdev, bdaddr_t *bdaddr, u8 *bdaddr_type) { - if (test_bit(HCI_FORCE_STATIC_ADDR, &hdev->dev_flags) || + if (test_bit(HCI_FORCE_STATIC_ADDR, &hdev->dbg_flags) || !bacmp(&hdev->bdaddr, BDADDR_ANY)) { bacpy(bdaddr, &hdev->static_addr); *bdaddr_type = ADDR_LE_DEV_RANDOM; @@ -3822,7 +3960,7 @@ struct hci_dev *hci_alloc_dev(void) { struct hci_dev *hdev; - hdev = kzalloc(sizeof(struct hci_dev), GFP_KERNEL); + hdev = kzalloc(sizeof(*hdev), GFP_KERNEL); if (!hdev) return NULL; @@ -3831,6 +3969,7 @@ struct hci_dev *hci_alloc_dev(void) hdev->link_mode = (HCI_LM_ACCEPT); hdev->num_iac = 0x01; /* One IAC support is mandatory */ hdev->io_capability = 0x03; /* No Input No Output */ + hdev->manufacturer = 0xffff; /* Default to internal use */ hdev->inq_tx_power = HCI_TX_POWER_INVALID; hdev->adv_tx_power = HCI_TX_POWER_INVALID; @@ -3838,10 +3977,14 @@ struct hci_dev *hci_alloc_dev(void) hdev->sniff_min_interval = 80; hdev->le_adv_channel_map = 0x07; + hdev->le_adv_min_interval = 0x0800; + hdev->le_adv_max_interval = 0x0800; hdev->le_scan_interval = 0x0060; hdev->le_scan_window = 0x0030; hdev->le_conn_min_interval = 0x0028; hdev->le_conn_max_interval = 0x0038; + hdev->le_conn_latency = 0x0000; + hdev->le_supv_timeout = 0x002a; hdev->rpa_timeout = HCI_DEFAULT_RPA_TIMEOUT; hdev->discov_interleaved_timeout = DISCOV_INTERLEAVED_TIMEOUT; @@ -3853,6 +3996,7 @@ struct hci_dev *hci_alloc_dev(void) INIT_LIST_HEAD(&hdev->mgmt_pending); INIT_LIST_HEAD(&hdev->blacklist); + INIT_LIST_HEAD(&hdev->whitelist); INIT_LIST_HEAD(&hdev->uuids); INIT_LIST_HEAD(&hdev->link_keys); INIT_LIST_HEAD(&hdev->long_term_keys); @@ -3861,6 +4005,7 @@ struct hci_dev *hci_alloc_dev(void) INIT_LIST_HEAD(&hdev->le_white_list); INIT_LIST_HEAD(&hdev->le_conn_params); INIT_LIST_HEAD(&hdev->pend_le_conns); + INIT_LIST_HEAD(&hdev->pend_le_reports); INIT_LIST_HEAD(&hdev->conn_hash.list); INIT_WORK(&hdev->rx_work, hci_rx_work); @@ -3878,7 +4023,7 @@ struct hci_dev *hci_alloc_dev(void) init_waitqueue_head(&hdev->req_wait_q); - setup_timer(&hdev->cmd_timer, hci_cmd_timeout, (unsigned long) hdev); + INIT_DELAYED_WORK(&hdev->cmd_timer, hci_cmd_timeout); hci_init_sysfs(hdev); discovery_init(hdev); @@ -3900,7 +4045,7 @@ int hci_register_dev(struct hci_dev *hdev) { int id, error; - if (!hdev->open || !hdev->close) + if (!hdev->open || !hdev->close || !hdev->send) return -EINVAL; /* Do not allow HCI_AMP devices to register at index 0, @@ -3985,6 +4130,12 @@ int hci_register_dev(struct hci_dev *hdev) list_add(&hdev->list, &hci_dev_list); write_unlock(&hci_dev_list_lock); + /* Devices that are marked for raw-only usage are unconfigured + * and should not be included in normal operation. + */ + if (test_bit(HCI_QUIRK_RAW_DEVICE, &hdev->quirks)) + set_bit(HCI_UNCONFIGURED, &hdev->dev_flags); + hci_notify(hdev, HCI_DEV_REG); hci_dev_hold(hdev); @@ -4027,7 +4178,8 @@ void hci_unregister_dev(struct hci_dev *hdev) cancel_work_sync(&hdev->power_on); if (!test_bit(HCI_INIT, &hdev->flags) && - !test_bit(HCI_SETUP, &hdev->dev_flags)) { + !test_bit(HCI_SETUP, &hdev->dev_flags) && + !test_bit(HCI_CONFIG, &hdev->dev_flags)) { hci_dev_lock(hdev); mgmt_index_removed(hdev); hci_dev_unlock(hdev); @@ -4055,15 +4207,15 @@ void hci_unregister_dev(struct hci_dev *hdev) destroy_workqueue(hdev->req_workqueue); hci_dev_lock(hdev); - hci_blacklist_clear(hdev); + hci_bdaddr_list_clear(&hdev->blacklist); + hci_bdaddr_list_clear(&hdev->whitelist); hci_uuids_clear(hdev); hci_link_keys_clear(hdev); hci_smp_ltks_clear(hdev); hci_smp_irks_clear(hdev); hci_remote_oob_data_clear(hdev); - hci_white_list_clear(hdev); - hci_conn_params_clear(hdev); - hci_pend_le_conns_clear(hdev); + hci_bdaddr_list_clear(&hdev->le_white_list); + hci_conn_params_clear_all(hdev); hci_dev_unlock(hdev); hci_dev_put(hdev); @@ -4301,6 +4453,8 @@ EXPORT_SYMBOL(hci_unregister_cb); static void hci_send_frame(struct hci_dev *hdev, struct sk_buff *skb) { + int err; + BT_DBG("%s type %d len %d", hdev->name, bt_cb(skb)->pkt_type, skb->len); /* Time stamp */ @@ -4317,8 +4471,11 @@ static void hci_send_frame(struct hci_dev *hdev, struct sk_buff *skb) /* Get rid of skb owner, prior to sending to the driver. */ skb_orphan(skb); - if (hdev->send(hdev, skb) < 0) - BT_ERR("%s sending frame failed", hdev->name); + err = hdev->send(hdev, skb); + if (err < 0) { + BT_ERR("%s sending frame failed (%d)", hdev->name, err); + kfree_skb(skb); + } } void hci_req_init(struct hci_request *req, struct hci_dev *hdev) @@ -4360,6 +4517,11 @@ int hci_req_run(struct hci_request *req, hci_req_complete_t complete) return 0; } +bool hci_req_pending(struct hci_dev *hdev) +{ + return (hdev->req_status == HCI_REQ_PEND); +} + static struct sk_buff *hci_prepare_cmd(struct hci_dev *hdev, u16 opcode, u32 plen, const void *param) { @@ -4792,7 +4954,7 @@ static inline int __get_blocks(struct hci_dev *hdev, struct sk_buff *skb) static void __check_timeout(struct hci_dev *hdev, unsigned int cnt) { - if (!test_bit(HCI_RAW, &hdev->flags)) { + if (!test_bit(HCI_UNCONFIGURED, &hdev->dev_flags)) { /* ACL tx timeout must be longer than maximum * link supervision timeout (40.9 seconds) */ if (!cnt && time_after(jiffies, hdev->acl_last_tx + @@ -4975,7 +5137,7 @@ static void hci_sched_le(struct hci_dev *hdev) if (!hci_conn_num(hdev, LE_LINK)) return; - if (!test_bit(HCI_RAW, &hdev->flags)) { + if (!test_bit(HCI_UNCONFIGURED, &hdev->dev_flags)) { /* LE tx timeout must be longer than maximum * link supervision timeout (40.9 seconds) */ if (!hdev->le_cnt && hdev->le_pkts && @@ -5220,8 +5382,7 @@ static void hci_rx_work(struct work_struct *work) hci_send_to_sock(hdev, skb); } - if (test_bit(HCI_RAW, &hdev->flags) || - test_bit(HCI_USER_CHANNEL, &hdev->dev_flags)) { + if (test_bit(HCI_USER_CHANNEL, &hdev->dev_flags)) { kfree_skb(skb); continue; } @@ -5281,10 +5442,10 @@ static void hci_cmd_work(struct work_struct *work) atomic_dec(&hdev->cmd_cnt); hci_send_frame(hdev, skb); if (test_bit(HCI_RESET, &hdev->flags)) - del_timer(&hdev->cmd_timer); + cancel_delayed_work(&hdev->cmd_timer); else - mod_timer(&hdev->cmd_timer, - jiffies + HCI_CMD_TIMEOUT); + schedule_delayed_work(&hdev->cmd_timer, + HCI_CMD_TIMEOUT); } else { skb_queue_head(&hdev->cmd_q, skb); queue_work(hdev->workqueue, &hdev->cmd_work); @@ -5301,26 +5462,135 @@ void hci_req_add_le_scan_disable(struct hci_request *req) hci_req_add(req, HCI_OP_LE_SET_SCAN_ENABLE, sizeof(cp), &cp); } +static void add_to_white_list(struct hci_request *req, + struct hci_conn_params *params) +{ + struct hci_cp_le_add_to_white_list cp; + + cp.bdaddr_type = params->addr_type; + bacpy(&cp.bdaddr, ¶ms->addr); + + hci_req_add(req, HCI_OP_LE_ADD_TO_WHITE_LIST, sizeof(cp), &cp); +} + +static u8 update_white_list(struct hci_request *req) +{ + struct hci_dev *hdev = req->hdev; + struct hci_conn_params *params; + struct bdaddr_list *b; + uint8_t white_list_entries = 0; + + /* Go through the current white list programmed into the + * controller one by one and check if that address is still + * in the list of pending connections or list of devices to + * report. If not present in either list, then queue the + * command to remove it from the controller. + */ + list_for_each_entry(b, &hdev->le_white_list, list) { + struct hci_cp_le_del_from_white_list cp; + + if (hci_pend_le_action_lookup(&hdev->pend_le_conns, + &b->bdaddr, b->bdaddr_type) || + hci_pend_le_action_lookup(&hdev->pend_le_reports, + &b->bdaddr, b->bdaddr_type)) { + white_list_entries++; + continue; + } + + cp.bdaddr_type = b->bdaddr_type; + bacpy(&cp.bdaddr, &b->bdaddr); + + hci_req_add(req, HCI_OP_LE_DEL_FROM_WHITE_LIST, + sizeof(cp), &cp); + } + + /* Since all no longer valid white list entries have been + * removed, walk through the list of pending connections + * and ensure that any new device gets programmed into + * the controller. + * + * If the list of the devices is larger than the list of + * available white list entries in the controller, then + * just abort and return filer policy value to not use the + * white list. + */ + list_for_each_entry(params, &hdev->pend_le_conns, action) { + if (hci_bdaddr_list_lookup(&hdev->le_white_list, + ¶ms->addr, params->addr_type)) + continue; + + if (white_list_entries >= hdev->le_white_list_size) { + /* Select filter policy to accept all advertising */ + return 0x00; + } + + if (hci_find_irk_by_addr(hdev, ¶ms->addr, + params->addr_type)) { + /* White list can not be used with RPAs */ + return 0x00; + } + + white_list_entries++; + add_to_white_list(req, params); + } + + /* After adding all new pending connections, walk through + * the list of pending reports and also add these to the + * white list if there is still space. + */ + list_for_each_entry(params, &hdev->pend_le_reports, action) { + if (hci_bdaddr_list_lookup(&hdev->le_white_list, + ¶ms->addr, params->addr_type)) + continue; + + if (white_list_entries >= hdev->le_white_list_size) { + /* Select filter policy to accept all advertising */ + return 0x00; + } + + if (hci_find_irk_by_addr(hdev, ¶ms->addr, + params->addr_type)) { + /* White list can not be used with RPAs */ + return 0x00; + } + + white_list_entries++; + add_to_white_list(req, params); + } + + /* Select filter policy to use white list */ + return 0x01; +} + void hci_req_add_le_passive_scan(struct hci_request *req) { struct hci_cp_le_set_scan_param param_cp; struct hci_cp_le_set_scan_enable enable_cp; struct hci_dev *hdev = req->hdev; u8 own_addr_type; + u8 filter_policy; - /* Set require_privacy to true to avoid identification from - * unknown peer devices. Since this is passive scanning, no - * SCAN_REQ using the local identity should be sent. Mandating - * privacy is just an extra precaution. + /* Set require_privacy to false since no SCAN_REQ are send + * during passive scanning. Not using an unresolvable address + * here is important so that peer devices using direct + * advertising with our address will be correctly reported + * by the controller. */ - if (hci_update_random_address(req, true, &own_addr_type)) + if (hci_update_random_address(req, false, &own_addr_type)) return; + /* Adding or removing entries from the white list must + * happen before enabling scanning. The controller does + * not allow white list modification while scanning. + */ + filter_policy = update_white_list(req); + memset(¶m_cp, 0, sizeof(param_cp)); param_cp.type = LE_SCAN_PASSIVE; param_cp.interval = cpu_to_le16(hdev->le_scan_interval); param_cp.window = cpu_to_le16(hdev->le_scan_window); param_cp.own_address_type = own_addr_type; + param_cp.filter_policy = filter_policy; hci_req_add(req, HCI_OP_LE_SET_SCAN_PARAM, sizeof(param_cp), ¶m_cp); @@ -5350,11 +5620,29 @@ void hci_update_background_scan(struct hci_dev *hdev) struct hci_conn *conn; int err; + if (!test_bit(HCI_UP, &hdev->flags) || + test_bit(HCI_INIT, &hdev->flags) || + test_bit(HCI_SETUP, &hdev->dev_flags) || + test_bit(HCI_CONFIG, &hdev->dev_flags) || + test_bit(HCI_AUTO_OFF, &hdev->dev_flags) || + test_bit(HCI_UNREGISTER, &hdev->dev_flags)) + return; + + /* No point in doing scanning if LE support hasn't been enabled */ + if (!test_bit(HCI_LE_ENABLED, &hdev->dev_flags)) + return; + + /* If discovery is active don't interfere with it */ + if (hdev->discovery.state != DISCOVERY_STOPPED) + return; + hci_req_init(&req, hdev); - if (list_empty(&hdev->pend_le_conns)) { - /* If there is no pending LE connections, we should stop - * the background scanning. + if (list_empty(&hdev->pend_le_conns) && + list_empty(&hdev->pend_le_reports)) { + /* If there is no pending LE connections or devices + * to be scanned for, we should stop the background + * scanning. */ /* If controller is not scanning we are done. */ diff --git a/net/bluetooth/hci_event.c b/net/bluetooth/hci_event.c index 640c54ec1bd2..be35598984d9 100644 --- a/net/bluetooth/hci_event.c +++ b/net/bluetooth/hci_event.c @@ -32,6 +32,7 @@ #include "a2mp.h" #include "amp.h" +#include "smp.h" /* Handle HCI Event packets */ @@ -100,12 +101,8 @@ static void hci_cc_role_discovery(struct hci_dev *hdev, struct sk_buff *skb) hci_dev_lock(hdev); conn = hci_conn_hash_lookup_handle(hdev, __le16_to_cpu(rp->handle)); - if (conn) { - if (rp->role) - conn->link_mode &= ~HCI_LM_MASTER; - else - conn->link_mode |= HCI_LM_MASTER; - } + if (conn) + conn->role = rp->role; hci_dev_unlock(hdev); } @@ -174,12 +171,14 @@ static void hci_cc_write_def_link_policy(struct hci_dev *hdev, BT_DBG("%s status 0x%2.2x", hdev->name, status); + if (status) + return; + sent = hci_sent_cmd_data(hdev, HCI_OP_WRITE_DEF_LINK_POLICY); if (!sent) return; - if (!status) - hdev->link_policy = get_unaligned_le16(sent); + hdev->link_policy = get_unaligned_le16(sent); } static void hci_cc_reset(struct hci_dev *hdev, struct sk_buff *skb) @@ -269,28 +268,30 @@ static void hci_cc_write_auth_enable(struct hci_dev *hdev, struct sk_buff *skb) static void hci_cc_write_encrypt_mode(struct hci_dev *hdev, struct sk_buff *skb) { __u8 status = *((__u8 *) skb->data); + __u8 param; void *sent; BT_DBG("%s status 0x%2.2x", hdev->name, status); + if (status) + return; + sent = hci_sent_cmd_data(hdev, HCI_OP_WRITE_ENCRYPT_MODE); if (!sent) return; - if (!status) { - __u8 param = *((__u8 *) sent); + param = *((__u8 *) sent); - if (param) - set_bit(HCI_ENCRYPT, &hdev->flags); - else - clear_bit(HCI_ENCRYPT, &hdev->flags); - } + if (param) + set_bit(HCI_ENCRYPT, &hdev->flags); + else + clear_bit(HCI_ENCRYPT, &hdev->flags); } static void hci_cc_write_scan_enable(struct hci_dev *hdev, struct sk_buff *skb) { - __u8 param, status = *((__u8 *) skb->data); - int old_pscan, old_iscan; + __u8 status = *((__u8 *) skb->data); + __u8 param; void *sent; BT_DBG("%s status 0x%2.2x", hdev->name, status); @@ -304,32 +305,19 @@ static void hci_cc_write_scan_enable(struct hci_dev *hdev, struct sk_buff *skb) hci_dev_lock(hdev); if (status) { - mgmt_write_scan_failed(hdev, param, status); hdev->discov_timeout = 0; goto done; } - /* We need to ensure that we set this back on if someone changed - * the scan mode through a raw HCI socket. - */ - set_bit(HCI_BREDR_ENABLED, &hdev->dev_flags); - - old_pscan = test_and_clear_bit(HCI_PSCAN, &hdev->flags); - old_iscan = test_and_clear_bit(HCI_ISCAN, &hdev->flags); - - if (param & SCAN_INQUIRY) { + if (param & SCAN_INQUIRY) set_bit(HCI_ISCAN, &hdev->flags); - if (!old_iscan) - mgmt_discoverable(hdev, 1); - } else if (old_iscan) - mgmt_discoverable(hdev, 0); + else + clear_bit(HCI_ISCAN, &hdev->flags); - if (param & SCAN_PAGE) { + if (param & SCAN_PAGE) set_bit(HCI_PSCAN, &hdev->flags); - if (!old_pscan) - mgmt_connectable(hdev, 1); - } else if (old_pscan) - mgmt_connectable(hdev, 0); + else + clear_bit(HCI_PSCAN, &hdev->flags); done: hci_dev_unlock(hdev); @@ -601,8 +589,10 @@ static void hci_cc_read_flow_control_mode(struct hci_dev *hdev, BT_DBG("%s status 0x%2.2x", hdev->name, rp->status); - if (!rp->status) - hdev->flow_ctl_mode = rp->mode; + if (rp->status) + return; + + hdev->flow_ctl_mode = rp->mode; } static void hci_cc_read_buffer_size(struct hci_dev *hdev, struct sk_buff *skb) @@ -637,8 +627,14 @@ static void hci_cc_read_bd_addr(struct hci_dev *hdev, struct sk_buff *skb) BT_DBG("%s status 0x%2.2x", hdev->name, rp->status); - if (!rp->status) + if (rp->status) + return; + + if (test_bit(HCI_INIT, &hdev->flags)) bacpy(&hdev->bdaddr, &rp->bdaddr); + + if (test_bit(HCI_SETUP, &hdev->dev_flags)) + bacpy(&hdev->setup_addr, &rp->bdaddr); } static void hci_cc_read_page_scan_activity(struct hci_dev *hdev, @@ -648,7 +644,10 @@ static void hci_cc_read_page_scan_activity(struct hci_dev *hdev, BT_DBG("%s status 0x%2.2x", hdev->name, rp->status); - if (test_bit(HCI_INIT, &hdev->flags) && !rp->status) { + if (rp->status) + return; + + if (test_bit(HCI_INIT, &hdev->flags)) { hdev->page_scan_interval = __le16_to_cpu(rp->interval); hdev->page_scan_window = __le16_to_cpu(rp->window); } @@ -680,7 +679,10 @@ static void hci_cc_read_page_scan_type(struct hci_dev *hdev, BT_DBG("%s status 0x%2.2x", hdev->name, rp->status); - if (test_bit(HCI_INIT, &hdev->flags) && !rp->status) + if (rp->status) + return; + + if (test_bit(HCI_INIT, &hdev->flags)) hdev->page_scan_type = rp->type; } @@ -720,6 +722,41 @@ static void hci_cc_read_data_block_size(struct hci_dev *hdev, hdev->block_cnt, hdev->block_len); } +static void hci_cc_read_clock(struct hci_dev *hdev, struct sk_buff *skb) +{ + struct hci_rp_read_clock *rp = (void *) skb->data; + struct hci_cp_read_clock *cp; + struct hci_conn *conn; + + BT_DBG("%s", hdev->name); + + if (skb->len < sizeof(*rp)) + return; + + if (rp->status) + return; + + hci_dev_lock(hdev); + + cp = hci_sent_cmd_data(hdev, HCI_OP_READ_CLOCK); + if (!cp) + goto unlock; + + if (cp->which == 0x00) { + hdev->clock = le32_to_cpu(rp->clock); + goto unlock; + } + + conn = hci_conn_hash_lookup_handle(hdev, __le16_to_cpu(rp->handle)); + if (conn) { + conn->clock = le32_to_cpu(rp->clock); + conn->clock_accuracy = le16_to_cpu(rp->accuracy); + } + +unlock: + hci_dev_unlock(hdev); +} + static void hci_cc_read_local_amp_info(struct hci_dev *hdev, struct sk_buff *skb) { @@ -789,8 +826,10 @@ static void hci_cc_read_inq_rsp_tx_power(struct hci_dev *hdev, BT_DBG("%s status 0x%2.2x", hdev->name, rp->status); - if (!rp->status) - hdev->inq_tx_power = rp->tx_power; + if (rp->status) + return; + + hdev->inq_tx_power = rp->tx_power; } static void hci_cc_pin_code_reply(struct hci_dev *hdev, struct sk_buff *skb) @@ -861,8 +900,10 @@ static void hci_cc_le_read_local_features(struct hci_dev *hdev, BT_DBG("%s status 0x%2.2x", hdev->name, rp->status); - if (!rp->status) - memcpy(hdev->le_features, rp->features, 8); + if (rp->status) + return; + + memcpy(hdev->le_features, rp->features, 8); } static void hci_cc_le_read_adv_tx_power(struct hci_dev *hdev, @@ -872,8 +913,10 @@ static void hci_cc_le_read_adv_tx_power(struct hci_dev *hdev, BT_DBG("%s status 0x%2.2x", hdev->name, rp->status); - if (!rp->status) - hdev->adv_tx_power = rp->tx_power; + if (rp->status) + return; + + hdev->adv_tx_power = rp->tx_power; } static void hci_cc_user_confirm_reply(struct hci_dev *hdev, struct sk_buff *skb) @@ -973,14 +1016,16 @@ static void hci_cc_le_set_random_addr(struct hci_dev *hdev, struct sk_buff *skb) BT_DBG("%s status 0x%2.2x", hdev->name, status); + if (status) + return; + sent = hci_sent_cmd_data(hdev, HCI_OP_LE_SET_RANDOM_ADDR); if (!sent) return; hci_dev_lock(hdev); - if (!status) - bacpy(&hdev->random_addr, sent); + bacpy(&hdev->random_addr, sent); hci_dev_unlock(hdev); } @@ -991,11 +1036,11 @@ static void hci_cc_le_set_adv_enable(struct hci_dev *hdev, struct sk_buff *skb) BT_DBG("%s status 0x%2.2x", hdev->name, status); - sent = hci_sent_cmd_data(hdev, HCI_OP_LE_SET_ADV_ENABLE); - if (!sent) + if (status) return; - if (status) + sent = hci_sent_cmd_data(hdev, HCI_OP_LE_SET_ADV_ENABLE); + if (!sent) return; hci_dev_lock(hdev); @@ -1006,15 +1051,17 @@ static void hci_cc_le_set_adv_enable(struct hci_dev *hdev, struct sk_buff *skb) if (*sent) { struct hci_conn *conn; + set_bit(HCI_LE_ADV, &hdev->dev_flags); + conn = hci_conn_hash_lookup_state(hdev, LE_LINK, BT_CONNECT); if (conn) queue_delayed_work(hdev->workqueue, &conn->le_conn_timeout, - HCI_LE_CONN_TIMEOUT); + conn->conn_timeout); + } else { + clear_bit(HCI_LE_ADV, &hdev->dev_flags); } - mgmt_advertising(hdev, *sent); - hci_dev_unlock(hdev); } @@ -1025,14 +1072,16 @@ static void hci_cc_le_set_scan_param(struct hci_dev *hdev, struct sk_buff *skb) BT_DBG("%s status 0x%2.2x", hdev->name, status); + if (status) + return; + cp = hci_sent_cmd_data(hdev, HCI_OP_LE_SET_SCAN_PARAM); if (!cp) return; hci_dev_lock(hdev); - if (!status) - hdev->le_scan_type = cp->type; + hdev->le_scan_type = cp->type; hci_dev_unlock(hdev); } @@ -1053,13 +1102,15 @@ static void clear_pending_adv_report(struct hci_dev *hdev) } static void store_pending_adv_report(struct hci_dev *hdev, bdaddr_t *bdaddr, - u8 bdaddr_type, s8 rssi, u8 *data, u8 len) + u8 bdaddr_type, s8 rssi, u32 flags, + u8 *data, u8 len) { struct discovery_state *d = &hdev->discovery; bacpy(&d->last_adv_addr, bdaddr); d->last_adv_addr_type = bdaddr_type; d->last_adv_rssi = rssi; + d->last_adv_flags = flags; memcpy(d->last_adv_data, data, len); d->last_adv_data_len = len; } @@ -1072,11 +1123,11 @@ static void hci_cc_le_set_scan_enable(struct hci_dev *hdev, BT_DBG("%s status 0x%2.2x", hdev->name, status); - cp = hci_sent_cmd_data(hdev, HCI_OP_LE_SET_SCAN_ENABLE); - if (!cp) + if (status) return; - if (status) + cp = hci_sent_cmd_data(hdev, HCI_OP_LE_SET_SCAN_ENABLE); + if (!cp) return; switch (cp->enable) { @@ -1096,7 +1147,7 @@ static void hci_cc_le_set_scan_enable(struct hci_dev *hdev, mgmt_device_found(hdev, &d->last_adv_addr, LE_LINK, d->last_adv_addr_type, NULL, - d->last_adv_rssi, 0, 1, + d->last_adv_rssi, d->last_adv_flags, d->last_adv_data, d->last_adv_data_len, NULL, 0); } @@ -1107,13 +1158,21 @@ static void hci_cc_le_set_scan_enable(struct hci_dev *hdev, cancel_delayed_work(&hdev->le_scan_disable); clear_bit(HCI_LE_SCAN, &hdev->dev_flags); + /* The HCI_LE_SCAN_INTERRUPTED flag indicates that we * interrupted scanning due to a connect request. Mark - * therefore discovery as stopped. + * therefore discovery as stopped. If this was not + * because of a connect request advertising might have + * been disabled because of active scanning, so + * re-enable it again if necessary. */ if (test_and_clear_bit(HCI_LE_SCAN_INTERRUPTED, &hdev->dev_flags)) hci_discovery_set_state(hdev, DISCOVERY_STOPPED); + else if (!test_bit(HCI_LE_ADV, &hdev->dev_flags) && + hdev->discovery.state == DISCOVERY_FINDING) + mgmt_reenable_advertising(hdev); + break; default: @@ -1129,8 +1188,10 @@ static void hci_cc_le_read_white_list_size(struct hci_dev *hdev, BT_DBG("%s status 0x%2.2x size %u", hdev->name, rp->status, rp->size); - if (!rp->status) - hdev->le_white_list_size = rp->size; + if (rp->status) + return; + + hdev->le_white_list_size = rp->size; } static void hci_cc_le_clear_white_list(struct hci_dev *hdev, @@ -1140,8 +1201,10 @@ static void hci_cc_le_clear_white_list(struct hci_dev *hdev, BT_DBG("%s status 0x%2.2x", hdev->name, status); - if (!status) - hci_white_list_clear(hdev); + if (status) + return; + + hci_bdaddr_list_clear(&hdev->le_white_list); } static void hci_cc_le_add_to_white_list(struct hci_dev *hdev, @@ -1152,12 +1215,15 @@ static void hci_cc_le_add_to_white_list(struct hci_dev *hdev, BT_DBG("%s status 0x%2.2x", hdev->name, status); + if (status) + return; + sent = hci_sent_cmd_data(hdev, HCI_OP_LE_ADD_TO_WHITE_LIST); if (!sent) return; - if (!status) - hci_white_list_add(hdev, &sent->bdaddr, sent->bdaddr_type); + hci_bdaddr_list_add(&hdev->le_white_list, &sent->bdaddr, + sent->bdaddr_type); } static void hci_cc_le_del_from_white_list(struct hci_dev *hdev, @@ -1168,12 +1234,15 @@ static void hci_cc_le_del_from_white_list(struct hci_dev *hdev, BT_DBG("%s status 0x%2.2x", hdev->name, status); + if (status) + return; + sent = hci_sent_cmd_data(hdev, HCI_OP_LE_DEL_FROM_WHITE_LIST); if (!sent) return; - if (!status) - hci_white_list_del(hdev, &sent->bdaddr, sent->bdaddr_type); + hci_bdaddr_list_del(&hdev->le_white_list, &sent->bdaddr, + sent->bdaddr_type); } static void hci_cc_le_read_supported_states(struct hci_dev *hdev, @@ -1183,8 +1252,10 @@ static void hci_cc_le_read_supported_states(struct hci_dev *hdev, BT_DBG("%s status 0x%2.2x", hdev->name, rp->status); - if (!rp->status) - memcpy(hdev->le_states, rp->le_states, 8); + if (rp->status) + return; + + memcpy(hdev->le_states, rp->le_states, 8); } static void hci_cc_write_le_host_supported(struct hci_dev *hdev, @@ -1195,25 +1266,26 @@ static void hci_cc_write_le_host_supported(struct hci_dev *hdev, BT_DBG("%s status 0x%2.2x", hdev->name, status); + if (status) + return; + sent = hci_sent_cmd_data(hdev, HCI_OP_WRITE_LE_HOST_SUPPORTED); if (!sent) return; - if (!status) { - if (sent->le) { - hdev->features[1][0] |= LMP_HOST_LE; - set_bit(HCI_LE_ENABLED, &hdev->dev_flags); - } else { - hdev->features[1][0] &= ~LMP_HOST_LE; - clear_bit(HCI_LE_ENABLED, &hdev->dev_flags); - clear_bit(HCI_ADVERTISING, &hdev->dev_flags); - } - - if (sent->simul) - hdev->features[1][0] |= LMP_HOST_LE_BREDR; - else - hdev->features[1][0] &= ~LMP_HOST_LE_BREDR; + if (sent->le) { + hdev->features[1][0] |= LMP_HOST_LE; + set_bit(HCI_LE_ENABLED, &hdev->dev_flags); + } else { + hdev->features[1][0] &= ~LMP_HOST_LE; + clear_bit(HCI_LE_ENABLED, &hdev->dev_flags); + clear_bit(HCI_ADVERTISING, &hdev->dev_flags); } + + if (sent->simul) + hdev->features[1][0] |= LMP_HOST_LE_BREDR; + else + hdev->features[1][0] &= ~LMP_HOST_LE_BREDR; } static void hci_cc_set_adv_param(struct hci_dev *hdev, struct sk_buff *skb) @@ -1342,11 +1414,9 @@ static void hci_cs_create_conn(struct hci_dev *hdev, __u8 status) } } else { if (!conn) { - conn = hci_conn_add(hdev, ACL_LINK, &cp->bdaddr); - if (conn) { - conn->out = true; - conn->link_mode |= HCI_LM_MASTER; - } else + conn = hci_conn_add(hdev, ACL_LINK, &cp->bdaddr, + HCI_ROLE_MASTER); + if (!conn) BT_ERR("No memory for new connection"); } } @@ -1575,6 +1645,8 @@ static void hci_cs_remote_name_req(struct hci_dev *hdev, __u8 status) if (!test_and_set_bit(HCI_CONN_AUTH_PEND, &conn->flags)) { struct hci_cp_auth_requested auth_cp; + set_bit(HCI_CONN_AUTH_INITIATOR, &conn->flags); + auth_cp.handle = __cpu_to_le16(conn->handle); hci_send_cmd(hdev, HCI_OP_AUTH_REQUESTED, sizeof(auth_cp), &auth_cp); @@ -1835,7 +1907,7 @@ static void hci_cs_le_create_conn(struct hci_dev *hdev, u8 status) if (cp->filter_policy == HCI_LE_USE_PEER_ADDR) queue_delayed_work(conn->hdev->workqueue, &conn->le_conn_timeout, - HCI_LE_CONN_TIMEOUT); + conn->conn_timeout); unlock: hci_dev_unlock(hdev); @@ -1929,7 +2001,7 @@ static void hci_inquiry_result_evt(struct hci_dev *hdev, struct sk_buff *skb) hci_dev_lock(hdev); for (; num_rsp; num_rsp--, info++) { - bool name_known, ssp; + u32 flags; bacpy(&data.bdaddr, &info->bdaddr); data.pscan_rep_mode = info->pscan_rep_mode; @@ -1940,10 +2012,10 @@ static void hci_inquiry_result_evt(struct hci_dev *hdev, struct sk_buff *skb) data.rssi = 0x00; data.ssp_mode = 0x00; - name_known = hci_inquiry_cache_update(hdev, &data, false, &ssp); + flags = hci_inquiry_cache_update(hdev, &data, false); + mgmt_device_found(hdev, &info->bdaddr, ACL_LINK, 0x00, - info->dev_class, 0, !name_known, ssp, NULL, - 0, NULL, 0); + info->dev_class, 0, flags, NULL, 0, NULL, 0); } hci_dev_unlock(hdev); @@ -1988,10 +2060,10 @@ static void hci_conn_complete_evt(struct hci_dev *hdev, struct sk_buff *skb) hci_conn_add_sysfs(conn); if (test_bit(HCI_AUTH, &hdev->flags)) - conn->link_mode |= HCI_LM_AUTH; + set_bit(HCI_CONN_AUTH, &conn->flags); if (test_bit(HCI_ENCRYPT, &hdev->flags)) - conn->link_mode |= HCI_LM_ENCRYPT; + set_bit(HCI_CONN_ENCRYPT, &conn->flags); /* Get remote features */ if (conn->type == ACL_LINK) { @@ -2031,10 +2103,21 @@ unlock: hci_conn_check_pending(hdev); } +static void hci_reject_conn(struct hci_dev *hdev, bdaddr_t *bdaddr) +{ + struct hci_cp_reject_conn_req cp; + + bacpy(&cp.bdaddr, bdaddr); + cp.reason = HCI_ERROR_REJ_BAD_ADDR; + hci_send_cmd(hdev, HCI_OP_REJECT_CONN_REQ, sizeof(cp), &cp); +} + static void hci_conn_request_evt(struct hci_dev *hdev, struct sk_buff *skb) { struct hci_ev_conn_request *ev = (void *) skb->data; int mask = hdev->link_mode; + struct inquiry_entry *ie; + struct hci_conn *conn; __u8 flags = 0; BT_DBG("%s bdaddr %pMR type 0x%x", hdev->name, &ev->bdaddr, @@ -2043,73 +2126,79 @@ static void hci_conn_request_evt(struct hci_dev *hdev, struct sk_buff *skb) mask |= hci_proto_connect_ind(hdev, &ev->bdaddr, ev->link_type, &flags); - if ((mask & HCI_LM_ACCEPT) && - !hci_blacklist_lookup(hdev, &ev->bdaddr, BDADDR_BREDR)) { - /* Connection accepted */ - struct inquiry_entry *ie; - struct hci_conn *conn; + if (!(mask & HCI_LM_ACCEPT)) { + hci_reject_conn(hdev, &ev->bdaddr); + return; + } - hci_dev_lock(hdev); + if (hci_bdaddr_list_lookup(&hdev->blacklist, &ev->bdaddr, + BDADDR_BREDR)) { + hci_reject_conn(hdev, &ev->bdaddr); + return; + } - ie = hci_inquiry_cache_lookup(hdev, &ev->bdaddr); - if (ie) - memcpy(ie->data.dev_class, ev->dev_class, 3); + if (!test_bit(HCI_CONNECTABLE, &hdev->dev_flags) && + !hci_bdaddr_list_lookup(&hdev->whitelist, &ev->bdaddr, + BDADDR_BREDR)) { + hci_reject_conn(hdev, &ev->bdaddr); + return; + } + + /* Connection accepted */ - conn = hci_conn_hash_lookup_ba(hdev, ev->link_type, - &ev->bdaddr); + hci_dev_lock(hdev); + + ie = hci_inquiry_cache_lookup(hdev, &ev->bdaddr); + if (ie) + memcpy(ie->data.dev_class, ev->dev_class, 3); + + conn = hci_conn_hash_lookup_ba(hdev, ev->link_type, + &ev->bdaddr); + if (!conn) { + conn = hci_conn_add(hdev, ev->link_type, &ev->bdaddr, + HCI_ROLE_SLAVE); if (!conn) { - conn = hci_conn_add(hdev, ev->link_type, &ev->bdaddr); - if (!conn) { - BT_ERR("No memory for new connection"); - hci_dev_unlock(hdev); - return; - } + BT_ERR("No memory for new connection"); + hci_dev_unlock(hdev); + return; } + } - memcpy(conn->dev_class, ev->dev_class, 3); + memcpy(conn->dev_class, ev->dev_class, 3); - hci_dev_unlock(hdev); + hci_dev_unlock(hdev); - if (ev->link_type == ACL_LINK || - (!(flags & HCI_PROTO_DEFER) && !lmp_esco_capable(hdev))) { - struct hci_cp_accept_conn_req cp; - conn->state = BT_CONNECT; + if (ev->link_type == ACL_LINK || + (!(flags & HCI_PROTO_DEFER) && !lmp_esco_capable(hdev))) { + struct hci_cp_accept_conn_req cp; + conn->state = BT_CONNECT; - bacpy(&cp.bdaddr, &ev->bdaddr); + bacpy(&cp.bdaddr, &ev->bdaddr); - if (lmp_rswitch_capable(hdev) && (mask & HCI_LM_MASTER)) - cp.role = 0x00; /* Become master */ - else - cp.role = 0x01; /* Remain slave */ + if (lmp_rswitch_capable(hdev) && (mask & HCI_LM_MASTER)) + cp.role = 0x00; /* Become master */ + else + cp.role = 0x01; /* Remain slave */ - hci_send_cmd(hdev, HCI_OP_ACCEPT_CONN_REQ, sizeof(cp), - &cp); - } else if (!(flags & HCI_PROTO_DEFER)) { - struct hci_cp_accept_sync_conn_req cp; - conn->state = BT_CONNECT; + hci_send_cmd(hdev, HCI_OP_ACCEPT_CONN_REQ, sizeof(cp), &cp); + } else if (!(flags & HCI_PROTO_DEFER)) { + struct hci_cp_accept_sync_conn_req cp; + conn->state = BT_CONNECT; - bacpy(&cp.bdaddr, &ev->bdaddr); - cp.pkt_type = cpu_to_le16(conn->pkt_type); + bacpy(&cp.bdaddr, &ev->bdaddr); + cp.pkt_type = cpu_to_le16(conn->pkt_type); - cp.tx_bandwidth = cpu_to_le32(0x00001f40); - cp.rx_bandwidth = cpu_to_le32(0x00001f40); - cp.max_latency = cpu_to_le16(0xffff); - cp.content_format = cpu_to_le16(hdev->voice_setting); - cp.retrans_effort = 0xff; + cp.tx_bandwidth = cpu_to_le32(0x00001f40); + cp.rx_bandwidth = cpu_to_le32(0x00001f40); + cp.max_latency = cpu_to_le16(0xffff); + cp.content_format = cpu_to_le16(hdev->voice_setting); + cp.retrans_effort = 0xff; - hci_send_cmd(hdev, HCI_OP_ACCEPT_SYNC_CONN_REQ, - sizeof(cp), &cp); - } else { - conn->state = BT_CONNECT2; - hci_proto_connect_cfm(conn, 0); - } + hci_send_cmd(hdev, HCI_OP_ACCEPT_SYNC_CONN_REQ, sizeof(cp), + &cp); } else { - /* Connection rejected */ - struct hci_cp_reject_conn_req cp; - - bacpy(&cp.bdaddr, &ev->bdaddr); - cp.reason = HCI_ERROR_REJ_BAD_ADDR; - hci_send_cmd(hdev, HCI_OP_REJECT_CONN_REQ, sizeof(cp), &cp); + conn->state = BT_CONNECT2; + hci_proto_connect_cfm(conn, 0); } } @@ -2158,7 +2247,8 @@ static void hci_disconn_complete_evt(struct hci_dev *hdev, struct sk_buff *skb) mgmt_device_disconnected(hdev, &conn->dst, conn->type, conn->dst_type, reason, mgmt_connected); - if (conn->type == ACL_LINK && conn->flush_key) + if (conn->type == ACL_LINK && + test_bit(HCI_CONN_FLUSH_KEY, &conn->flags)) hci_remove_link_key(hdev, &conn->dst); params = hci_conn_params_lookup(hdev, &conn->dst, conn->dst_type); @@ -2169,8 +2259,11 @@ static void hci_disconn_complete_evt(struct hci_dev *hdev, struct sk_buff *skb) break; /* Fall through */ + case HCI_AUTO_CONN_DIRECT: case HCI_AUTO_CONN_ALWAYS: - hci_pend_le_conn_add(hdev, &conn->dst, conn->dst_type); + list_del_init(¶ms->action); + list_add(¶ms->action, &hdev->pend_le_conns); + hci_update_background_scan(hdev); break; default: @@ -2218,7 +2311,7 @@ static void hci_auth_complete_evt(struct hci_dev *hdev, struct sk_buff *skb) test_bit(HCI_CONN_REAUTH_PEND, &conn->flags)) { BT_INFO("re-auth of legacy device is not possible."); } else { - conn->link_mode |= HCI_LM_AUTH; + set_bit(HCI_CONN_AUTH, &conn->flags); conn->sec_level = conn->pending_sec_level; } } else { @@ -2297,6 +2390,9 @@ check_auth: if (!test_and_set_bit(HCI_CONN_AUTH_PEND, &conn->flags)) { struct hci_cp_auth_requested cp; + + set_bit(HCI_CONN_AUTH_INITIATOR, &conn->flags); + cp.handle = __cpu_to_le16(conn->handle); hci_send_cmd(hdev, HCI_OP_AUTH_REQUESTED, sizeof(cp), &cp); } @@ -2321,19 +2417,19 @@ static void hci_encrypt_change_evt(struct hci_dev *hdev, struct sk_buff *skb) if (!ev->status) { if (ev->encrypt) { /* Encryption implies authentication */ - conn->link_mode |= HCI_LM_AUTH; - conn->link_mode |= HCI_LM_ENCRYPT; + set_bit(HCI_CONN_AUTH, &conn->flags); + set_bit(HCI_CONN_ENCRYPT, &conn->flags); conn->sec_level = conn->pending_sec_level; /* P-256 authentication key implies FIPS */ if (conn->key_type == HCI_LK_AUTH_COMBINATION_P256) - conn->link_mode |= HCI_LM_FIPS; + set_bit(HCI_CONN_FIPS, &conn->flags); if ((conn->type == ACL_LINK && ev->encrypt == 0x02) || conn->type == LE_LINK) set_bit(HCI_CONN_AES_CCM, &conn->flags); } else { - conn->link_mode &= ~HCI_LM_ENCRYPT; + clear_bit(HCI_CONN_ENCRYPT, &conn->flags); clear_bit(HCI_CONN_AES_CCM, &conn->flags); } } @@ -2384,7 +2480,7 @@ static void hci_change_link_key_complete_evt(struct hci_dev *hdev, conn = hci_conn_hash_lookup_handle(hdev, __le16_to_cpu(ev->handle)); if (conn) { if (!ev->status) - conn->link_mode |= HCI_LM_SECURE; + set_bit(HCI_CONN_SECURE, &conn->flags); clear_bit(HCI_CONN_AUTH_PEND, &conn->flags); @@ -2595,6 +2691,10 @@ static void hci_cmd_complete_evt(struct hci_dev *hdev, struct sk_buff *skb) hci_cc_read_local_amp_info(hdev, skb); break; + case HCI_OP_READ_CLOCK: + hci_cc_read_clock(hdev, skb); + break; + case HCI_OP_READ_LOCAL_AMP_ASSOC: hci_cc_read_local_amp_assoc(hdev, skb); break; @@ -2709,7 +2809,7 @@ static void hci_cmd_complete_evt(struct hci_dev *hdev, struct sk_buff *skb) } if (opcode != HCI_OP_NOP) - del_timer(&hdev->cmd_timer); + cancel_delayed_work(&hdev->cmd_timer); hci_req_cmd_complete(hdev, opcode, status); @@ -2800,7 +2900,7 @@ static void hci_cmd_status_evt(struct hci_dev *hdev, struct sk_buff *skb) } if (opcode != HCI_OP_NOP) - del_timer(&hdev->cmd_timer); + cancel_delayed_work(&hdev->cmd_timer); if (ev->status || (hdev->sent_cmd && !bt_cb(hdev->sent_cmd)->req.event)) @@ -2824,12 +2924,8 @@ static void hci_role_change_evt(struct hci_dev *hdev, struct sk_buff *skb) conn = hci_conn_hash_lookup_ba(hdev, ACL_LINK, &ev->bdaddr); if (conn) { - if (!ev->status) { - if (ev->role) - conn->link_mode &= ~HCI_LM_MASTER; - else - conn->link_mode |= HCI_LM_MASTER; - } + if (!ev->status) + conn->role = ev->role; clear_bit(HCI_CONN_RSWITCH_PEND, &conn->flags); @@ -3023,10 +3119,11 @@ static void hci_pin_code_request_evt(struct hci_dev *hdev, struct sk_buff *skb) hci_conn_drop(conn); } - if (!test_bit(HCI_PAIRABLE, &hdev->dev_flags)) + if (!test_bit(HCI_BONDABLE, &hdev->dev_flags) && + !test_bit(HCI_CONN_AUTH_INITIATOR, &conn->flags)) { hci_send_cmd(hdev, HCI_OP_PIN_CODE_NEG_REPLY, sizeof(ev->bdaddr), &ev->bdaddr); - else if (test_bit(HCI_MGMT, &hdev->dev_flags)) { + } else if (test_bit(HCI_MGMT, &hdev->dev_flags)) { u8 secure; if (conn->pending_sec_level == BT_SECURITY_HIGH) @@ -3065,12 +3162,6 @@ static void hci_link_key_request_evt(struct hci_dev *hdev, struct sk_buff *skb) BT_DBG("%s found key type %u for %pMR", hdev->name, key->type, &ev->bdaddr); - if (!test_bit(HCI_DEBUG_KEYS, &hdev->dev_flags) && - key->type == HCI_LK_DEBUG_COMBINATION) { - BT_DBG("%s ignoring debug key", hdev->name); - goto not_found; - } - conn = hci_conn_hash_lookup_ba(hdev, ACL_LINK, &ev->bdaddr); if (conn) { if ((key->type == HCI_LK_UNAUTH_COMBINATION_P192 || @@ -3110,6 +3201,8 @@ static void hci_link_key_notify_evt(struct hci_dev *hdev, struct sk_buff *skb) { struct hci_ev_link_key_notify *ev = (void *) skb->data; struct hci_conn *conn; + struct link_key *key; + bool persistent; u8 pin_len = 0; BT_DBG("%s", hdev->name); @@ -3128,10 +3221,33 @@ static void hci_link_key_notify_evt(struct hci_dev *hdev, struct sk_buff *skb) hci_conn_drop(conn); } - if (test_bit(HCI_MGMT, &hdev->dev_flags)) - hci_add_link_key(hdev, conn, 1, &ev->bdaddr, ev->link_key, - ev->key_type, pin_len); + if (!test_bit(HCI_MGMT, &hdev->dev_flags)) + goto unlock; + + key = hci_add_link_key(hdev, conn, &ev->bdaddr, ev->link_key, + ev->key_type, pin_len, &persistent); + if (!key) + goto unlock; + + mgmt_new_link_key(hdev, key, persistent); + + /* Keep debug keys around only if the HCI_KEEP_DEBUG_KEYS flag + * is set. If it's not set simply remove the key from the kernel + * list (we've still notified user space about it but with + * store_hint being 0). + */ + if (key->type == HCI_LK_DEBUG_COMBINATION && + !test_bit(HCI_KEEP_DEBUG_KEYS, &hdev->dev_flags)) { + list_del(&key->list); + kfree(key); + } else if (conn) { + if (persistent) + clear_bit(HCI_CONN_FLUSH_KEY, &conn->flags); + else + set_bit(HCI_CONN_FLUSH_KEY, &conn->flags); + } +unlock: hci_dev_unlock(hdev); } @@ -3197,7 +3313,6 @@ static void hci_inquiry_result_with_rssi_evt(struct hci_dev *hdev, { struct inquiry_data data; int num_rsp = *((__u8 *) skb->data); - bool name_known, ssp; BT_DBG("%s num_rsp %d", hdev->name, num_rsp); @@ -3214,6 +3329,8 @@ static void hci_inquiry_result_with_rssi_evt(struct hci_dev *hdev, info = (void *) (skb->data + 1); for (; num_rsp; num_rsp--, info++) { + u32 flags; + bacpy(&data.bdaddr, &info->bdaddr); data.pscan_rep_mode = info->pscan_rep_mode; data.pscan_period_mode = info->pscan_period_mode; @@ -3223,16 +3340,18 @@ static void hci_inquiry_result_with_rssi_evt(struct hci_dev *hdev, data.rssi = info->rssi; data.ssp_mode = 0x00; - name_known = hci_inquiry_cache_update(hdev, &data, - false, &ssp); + flags = hci_inquiry_cache_update(hdev, &data, false); + mgmt_device_found(hdev, &info->bdaddr, ACL_LINK, 0x00, info->dev_class, info->rssi, - !name_known, ssp, NULL, 0, NULL, 0); + flags, NULL, 0, NULL, 0); } } else { struct inquiry_info_with_rssi *info = (void *) (skb->data + 1); for (; num_rsp; num_rsp--, info++) { + u32 flags; + bacpy(&data.bdaddr, &info->bdaddr); data.pscan_rep_mode = info->pscan_rep_mode; data.pscan_period_mode = info->pscan_period_mode; @@ -3241,11 +3360,12 @@ static void hci_inquiry_result_with_rssi_evt(struct hci_dev *hdev, data.clock_offset = info->clock_offset; data.rssi = info->rssi; data.ssp_mode = 0x00; - name_known = hci_inquiry_cache_update(hdev, &data, - false, &ssp); + + flags = hci_inquiry_cache_update(hdev, &data, false); + mgmt_device_found(hdev, &info->bdaddr, ACL_LINK, 0x00, info->dev_class, info->rssi, - !name_known, ssp, NULL, 0, NULL, 0); + flags, NULL, 0, NULL, 0); } } @@ -3348,6 +3468,7 @@ static void hci_sync_conn_complete_evt(struct hci_dev *hdev, hci_conn_add_sysfs(conn); break; + case 0x10: /* Connection Accept Timeout */ case 0x0d: /* Connection Rejected due to Limited Resources */ case 0x11: /* Unsupported Feature or Parameter Value */ case 0x1c: /* SCO interval rejected */ @@ -3411,7 +3532,8 @@ static void hci_extended_inquiry_result_evt(struct hci_dev *hdev, hci_dev_lock(hdev); for (; num_rsp; num_rsp--, info++) { - bool name_known, ssp; + u32 flags; + bool name_known; bacpy(&data.bdaddr, &info->bdaddr); data.pscan_rep_mode = info->pscan_rep_mode; @@ -3429,12 +3551,13 @@ static void hci_extended_inquiry_result_evt(struct hci_dev *hdev, else name_known = true; - name_known = hci_inquiry_cache_update(hdev, &data, name_known, - &ssp); + flags = hci_inquiry_cache_update(hdev, &data, name_known); + eir_len = eir_get_length(info->data, sizeof(info->data)); + mgmt_device_found(hdev, &info->bdaddr, ACL_LINK, 0x00, - info->dev_class, info->rssi, !name_known, - ssp, info->data, eir_len, NULL, 0); + info->dev_class, info->rssi, + flags, info->data, eir_len, NULL, 0); } hci_dev_unlock(hdev); @@ -3526,7 +3649,11 @@ static void hci_io_capa_request_evt(struct hci_dev *hdev, struct sk_buff *skb) if (!test_bit(HCI_MGMT, &hdev->dev_flags)) goto unlock; - if (test_bit(HCI_PAIRABLE, &hdev->dev_flags) || + /* Allow pairing if we're pairable, the initiators of the + * pairing or if the remote is not requesting bonding. + */ + if (test_bit(HCI_BONDABLE, &hdev->dev_flags) || + test_bit(HCI_CONN_AUTH_INITIATOR, &conn->flags) || (conn->remote_auth & ~0x01) == HCI_AT_NO_BONDING) { struct hci_cp_io_capability_reply cp; @@ -3538,23 +3665,24 @@ static void hci_io_capa_request_evt(struct hci_dev *hdev, struct sk_buff *skb) /* If we are initiators, there is no remote information yet */ if (conn->remote_auth == 0xff) { - cp.authentication = conn->auth_type; - /* Request MITM protection if our IO caps allow it * except for the no-bonding case. - * conn->auth_type is not updated here since - * that might cause the user confirmation to be - * rejected in case the remote doesn't have the - * IO capabilities for MITM. */ if (conn->io_capability != HCI_IO_NO_INPUT_OUTPUT && - cp.authentication != HCI_AT_NO_BONDING) - cp.authentication |= 0x01; + conn->auth_type != HCI_AT_NO_BONDING) + conn->auth_type |= 0x01; } else { conn->auth_type = hci_get_auth_req(conn); - cp.authentication = conn->auth_type; } + /* If we're not bondable, force one of the non-bondable + * authentication requirement values. + */ + if (!test_bit(HCI_BONDABLE, &hdev->dev_flags)) + conn->auth_type &= HCI_AT_NO_BONDING_MITM; + + cp.authentication = conn->auth_type; + if (hci_find_remote_oob_data(hdev, &conn->dst) && (conn->out || test_bit(HCI_CONN_REMOTE_OOB, &conn->flags))) cp.oob_data = 0x01; @@ -3621,9 +3749,12 @@ static void hci_user_confirm_request_evt(struct hci_dev *hdev, rem_mitm = (conn->remote_auth & 0x01); /* If we require MITM but the remote device can't provide that - * (it has NoInputNoOutput) then reject the confirmation request + * (it has NoInputNoOutput) then reject the confirmation + * request. We check the security level here since it doesn't + * necessarily match conn->auth_type. */ - if (loc_mitm && conn->remote_cap == HCI_IO_NO_INPUT_OUTPUT) { + if (conn->pending_sec_level > BT_SECURITY_MEDIUM && + conn->remote_cap == HCI_IO_NO_INPUT_OUTPUT) { BT_DBG("Rejecting request: remote device can't provide MITM"); hci_send_cmd(hdev, HCI_OP_USER_CONFIRM_NEG_REPLY, sizeof(ev->bdaddr), &ev->bdaddr); @@ -3637,9 +3768,11 @@ static void hci_user_confirm_request_evt(struct hci_dev *hdev, /* If we're not the initiators request authorization to * proceed from user space (mgmt_user_confirm with * confirm_hint set to 1). The exception is if neither - * side had MITM in which case we do auto-accept. + * side had MITM or if the local IO capability is + * NoInputNoOutput, in which case we do auto-accept */ if (!test_bit(HCI_CONN_AUTH_PEND, &conn->flags) && + conn->io_capability != HCI_IO_NO_INPUT_OUTPUT && (loc_mitm || rem_mitm)) { BT_DBG("Confirming auto-accept as acceptor"); confirm_hint = 1; @@ -3753,6 +3886,9 @@ static void hci_simple_pair_complete_evt(struct hci_dev *hdev, if (!conn) goto unlock; + /* Reset the authentication requirement to unknown */ + conn->remote_auth = 0xff; + /* To avoid duplicate auth_failed events to user space we check * the HCI_CONN_AUTH_PEND flag which will be set if we * initiated the authentication. A traditional auth_complete @@ -3967,16 +4103,23 @@ static void hci_disconn_phylink_complete_evt(struct hci_dev *hdev, static void hci_le_conn_complete_evt(struct hci_dev *hdev, struct sk_buff *skb) { struct hci_ev_le_conn_complete *ev = (void *) skb->data; + struct hci_conn_params *params; struct hci_conn *conn; struct smp_irk *irk; + u8 addr_type; BT_DBG("%s status 0x%2.2x", hdev->name, ev->status); hci_dev_lock(hdev); + /* All controllers implicitly stop advertising in the event of a + * connection, so ensure that the state bit is cleared. + */ + clear_bit(HCI_LE_ADV, &hdev->dev_flags); + conn = hci_conn_hash_lookup_state(hdev, LE_LINK, BT_CONNECT); if (!conn) { - conn = hci_conn_add(hdev, LE_LINK, &ev->bdaddr); + conn = hci_conn_add(hdev, LE_LINK, &ev->bdaddr, ev->role); if (!conn) { BT_ERR("No memory for new connection"); goto unlock; @@ -3984,11 +4127,6 @@ static void hci_le_conn_complete_evt(struct hci_dev *hdev, struct sk_buff *skb) conn->dst_type = ev->bdaddr_type; - if (ev->role == LE_CONN_ROLE_MASTER) { - conn->out = true; - conn->link_mode |= HCI_LM_MASTER; - } - /* If we didn't have a hci_conn object previously * but we're in master role this must be something * initiated using a white list. Since white list based @@ -4025,6 +4163,14 @@ static void hci_le_conn_complete_evt(struct hci_dev *hdev, struct sk_buff *skb) conn->init_addr_type = ev->bdaddr_type; bacpy(&conn->init_addr, &ev->bdaddr); + + /* For incoming connections, set the default minimum + * and maximum connection interval. They will be used + * to check if the parameters are in range and if not + * trigger the connection update procedure. + */ + conn->le_conn_min_interval = hdev->le_conn_min_interval; + conn->le_conn_max_interval = hdev->le_conn_max_interval; } /* Lookup the identity address from the stored connection @@ -4042,11 +4188,22 @@ static void hci_le_conn_complete_evt(struct hci_dev *hdev, struct sk_buff *skb) conn->dst_type = irk->addr_type; } + if (conn->dst_type == ADDR_LE_DEV_PUBLIC) + addr_type = BDADDR_LE_PUBLIC; + else + addr_type = BDADDR_LE_RANDOM; + if (ev->status) { hci_le_conn_failed(conn, ev->status); goto unlock; } + /* Drop the connection if the device is blocked */ + if (hci_bdaddr_list_lookup(&hdev->blacklist, &conn->dst, addr_type)) { + hci_conn_drop(conn); + goto unlock; + } + if (!test_and_set_bit(HCI_CONN_MGMT_CONNECTED, &conn->flags)) mgmt_device_connected(hdev, &conn->dst, conn->type, conn->dst_type, 0, NULL, 0, NULL); @@ -4055,40 +4212,98 @@ static void hci_le_conn_complete_evt(struct hci_dev *hdev, struct sk_buff *skb) conn->handle = __le16_to_cpu(ev->handle); conn->state = BT_CONNECTED; - if (test_bit(HCI_6LOWPAN_ENABLED, &hdev->dev_flags)) - set_bit(HCI_CONN_6LOWPAN, &conn->flags); + conn->le_conn_interval = le16_to_cpu(ev->interval); + conn->le_conn_latency = le16_to_cpu(ev->latency); + conn->le_supv_timeout = le16_to_cpu(ev->supervision_timeout); hci_conn_add_sysfs(conn); hci_proto_connect_cfm(conn, ev->status); - hci_pend_le_conn_del(hdev, &conn->dst, conn->dst_type); + params = hci_conn_params_lookup(hdev, &conn->dst, conn->dst_type); + if (params) + list_del_init(¶ms->action); unlock: + hci_update_background_scan(hdev); + hci_dev_unlock(hdev); +} + +static void hci_le_conn_update_complete_evt(struct hci_dev *hdev, + struct sk_buff *skb) +{ + struct hci_ev_le_conn_update_complete *ev = (void *) skb->data; + struct hci_conn *conn; + + BT_DBG("%s status 0x%2.2x", hdev->name, ev->status); + + if (ev->status) + return; + + hci_dev_lock(hdev); + + conn = hci_conn_hash_lookup_handle(hdev, __le16_to_cpu(ev->handle)); + if (conn) { + conn->le_conn_interval = le16_to_cpu(ev->interval); + conn->le_conn_latency = le16_to_cpu(ev->latency); + conn->le_supv_timeout = le16_to_cpu(ev->supervision_timeout); + } + hci_dev_unlock(hdev); } /* This function requires the caller holds hdev->lock */ static void check_pending_le_conn(struct hci_dev *hdev, bdaddr_t *addr, - u8 addr_type) + u8 addr_type, u8 adv_type) { struct hci_conn *conn; - struct smp_irk *irk; + struct hci_conn_params *params; + + /* If the event is not connectable don't proceed further */ + if (adv_type != LE_ADV_IND && adv_type != LE_ADV_DIRECT_IND) + return; - /* If this is a resolvable address, we should resolve it and then - * update address and address type variables. + /* Ignore if the device is blocked */ + if (hci_bdaddr_list_lookup(&hdev->blacklist, addr, addr_type)) + return; + + /* Most controller will fail if we try to create new connections + * while we have an existing one in slave role. */ - irk = hci_get_irk(hdev, addr, addr_type); - if (irk) { - addr = &irk->bdaddr; - addr_type = irk->addr_type; - } + if (hdev->conn_hash.le_num_slave > 0) + return; - if (!hci_pend_le_conn_lookup(hdev, addr, addr_type)) + /* If we're not connectable only connect devices that we have in + * our pend_le_conns list. + */ + params = hci_pend_le_action_lookup(&hdev->pend_le_conns, + addr, addr_type); + if (!params) return; + switch (params->auto_connect) { + case HCI_AUTO_CONN_DIRECT: + /* Only devices advertising with ADV_DIRECT_IND are + * triggering a connection attempt. This is allowing + * incoming connections from slave devices. + */ + if (adv_type != LE_ADV_DIRECT_IND) + return; + break; + case HCI_AUTO_CONN_ALWAYS: + /* Devices advertising with ADV_IND or ADV_DIRECT_IND + * are triggering a connection attempt. This means + * that incoming connectioms from slave device are + * accepted and also outgoing connections to slave + * devices are established when found. + */ + break; + default: + return; + } + conn = hci_connect_le(hdev, addr, addr_type, BT_SECURITY_LOW, - HCI_AT_NO_BONDING); + HCI_LE_AUTOCONN_TIMEOUT, HCI_ROLE_MASTER); if (!IS_ERR(conn)) return; @@ -4109,15 +4324,62 @@ static void process_adv_report(struct hci_dev *hdev, u8 type, bdaddr_t *bdaddr, u8 bdaddr_type, s8 rssi, u8 *data, u8 len) { struct discovery_state *d = &hdev->discovery; + struct smp_irk *irk; bool match; + u32 flags; + + /* Check if we need to convert to identity address */ + irk = hci_get_irk(hdev, bdaddr, bdaddr_type); + if (irk) { + bdaddr = &irk->bdaddr; + bdaddr_type = irk->addr_type; + } - /* Passive scanning shouldn't trigger any device found events */ + /* Check if we have been requested to connect to this device */ + check_pending_le_conn(hdev, bdaddr, bdaddr_type, type); + + /* Passive scanning shouldn't trigger any device found events, + * except for devices marked as CONN_REPORT for which we do send + * device found events. + */ if (hdev->le_scan_type == LE_SCAN_PASSIVE) { - if (type == LE_ADV_IND || type == LE_ADV_DIRECT_IND) - check_pending_le_conn(hdev, bdaddr, bdaddr_type); + if (type == LE_ADV_DIRECT_IND) + return; + + if (!hci_pend_le_action_lookup(&hdev->pend_le_reports, + bdaddr, bdaddr_type)) + return; + + if (type == LE_ADV_NONCONN_IND || type == LE_ADV_SCAN_IND) + flags = MGMT_DEV_FOUND_NOT_CONNECTABLE; + else + flags = 0; + mgmt_device_found(hdev, bdaddr, LE_LINK, bdaddr_type, NULL, + rssi, flags, data, len, NULL, 0); return; } + /* When receiving non-connectable or scannable undirected + * advertising reports, this means that the remote device is + * not connectable and then clearly indicate this in the + * device found event. + * + * When receiving a scan response, then there is no way to + * know if the remote device is connectable or not. However + * since scan responses are merged with a previously seen + * advertising report, the flags field from that report + * will be used. + * + * In the really unlikely case that a controller get confused + * and just sends a scan response event, then it is marked as + * not connectable as well. + */ + if (type == LE_ADV_NONCONN_IND || type == LE_ADV_SCAN_IND || + type == LE_ADV_SCAN_RSP) + flags = MGMT_DEV_FOUND_NOT_CONNECTABLE; + else + flags = 0; + /* If there's nothing pending either store the data from this * event or send an immediate device found event if the data * should not be stored for later. @@ -4128,12 +4390,12 @@ static void process_adv_report(struct hci_dev *hdev, u8 type, bdaddr_t *bdaddr, */ if (type == LE_ADV_IND || type == LE_ADV_SCAN_IND) { store_pending_adv_report(hdev, bdaddr, bdaddr_type, - rssi, data, len); + rssi, flags, data, len); return; } mgmt_device_found(hdev, bdaddr, LE_LINK, bdaddr_type, NULL, - rssi, 0, 1, data, len, NULL, 0); + rssi, flags, data, len, NULL, 0); return; } @@ -4150,7 +4412,7 @@ static void process_adv_report(struct hci_dev *hdev, u8 type, bdaddr_t *bdaddr, if (!match) mgmt_device_found(hdev, &d->last_adv_addr, LE_LINK, d->last_adv_addr_type, NULL, - d->last_adv_rssi, 0, 1, + d->last_adv_rssi, d->last_adv_flags, d->last_adv_data, d->last_adv_data_len, NULL, 0); @@ -4159,7 +4421,7 @@ static void process_adv_report(struct hci_dev *hdev, u8 type, bdaddr_t *bdaddr, */ if (type == LE_ADV_IND || type == LE_ADV_SCAN_IND) { store_pending_adv_report(hdev, bdaddr, bdaddr_type, - rssi, data, len); + rssi, flags, data, len); return; } @@ -4168,7 +4430,7 @@ static void process_adv_report(struct hci_dev *hdev, u8 type, bdaddr_t *bdaddr, */ clear_pending_adv_report(hdev); mgmt_device_found(hdev, bdaddr, LE_LINK, bdaddr_type, NULL, - rssi, 0, 1, data, len, NULL, 0); + rssi, flags, data, len, NULL, 0); return; } @@ -4177,8 +4439,8 @@ static void process_adv_report(struct hci_dev *hdev, u8 type, bdaddr_t *bdaddr, * sending a merged device found event. */ mgmt_device_found(hdev, &d->last_adv_addr, LE_LINK, - d->last_adv_addr_type, NULL, rssi, 0, 1, data, len, - d->last_adv_data, d->last_adv_data_len); + d->last_adv_addr_type, NULL, rssi, d->last_adv_flags, + d->last_adv_data, d->last_adv_data_len, data, len); clear_pending_adv_report(hdev); } @@ -4219,7 +4481,7 @@ static void hci_le_ltk_request_evt(struct hci_dev *hdev, struct sk_buff *skb) if (conn == NULL) goto not_found; - ltk = hci_find_ltk(hdev, ev->ediv, ev->rand, conn->out); + ltk = hci_find_ltk(hdev, ev->ediv, ev->rand, conn->role); if (ltk == NULL) goto not_found; @@ -4241,9 +4503,12 @@ static void hci_le_ltk_request_evt(struct hci_dev *hdev, struct sk_buff *skb) * distribute the keys. Later, security can be re-established * using a distributed LTK. */ - if (ltk->type == HCI_SMP_STK_SLAVE) { + if (ltk->type == SMP_STK) { + set_bit(HCI_CONN_STK_ENCRYPT, &conn->flags); list_del(<k->list); kfree(ltk); + } else { + clear_bit(HCI_CONN_STK_ENCRYPT, &conn->flags); } hci_dev_unlock(hdev); @@ -4256,6 +4521,76 @@ not_found: hci_dev_unlock(hdev); } +static void send_conn_param_neg_reply(struct hci_dev *hdev, u16 handle, + u8 reason) +{ + struct hci_cp_le_conn_param_req_neg_reply cp; + + cp.handle = cpu_to_le16(handle); + cp.reason = reason; + + hci_send_cmd(hdev, HCI_OP_LE_CONN_PARAM_REQ_NEG_REPLY, sizeof(cp), + &cp); +} + +static void hci_le_remote_conn_param_req_evt(struct hci_dev *hdev, + struct sk_buff *skb) +{ + struct hci_ev_le_remote_conn_param_req *ev = (void *) skb->data; + struct hci_cp_le_conn_param_req_reply cp; + struct hci_conn *hcon; + u16 handle, min, max, latency, timeout; + + handle = le16_to_cpu(ev->handle); + min = le16_to_cpu(ev->interval_min); + max = le16_to_cpu(ev->interval_max); + latency = le16_to_cpu(ev->latency); + timeout = le16_to_cpu(ev->timeout); + + hcon = hci_conn_hash_lookup_handle(hdev, handle); + if (!hcon || hcon->state != BT_CONNECTED) + return send_conn_param_neg_reply(hdev, handle, + HCI_ERROR_UNKNOWN_CONN_ID); + + if (hci_check_conn_params(min, max, latency, timeout)) + return send_conn_param_neg_reply(hdev, handle, + HCI_ERROR_INVALID_LL_PARAMS); + + if (hcon->role == HCI_ROLE_MASTER) { + struct hci_conn_params *params; + u8 store_hint; + + hci_dev_lock(hdev); + + params = hci_conn_params_lookup(hdev, &hcon->dst, + hcon->dst_type); + if (params) { + params->conn_min_interval = min; + params->conn_max_interval = max; + params->conn_latency = latency; + params->supervision_timeout = timeout; + store_hint = 0x01; + } else{ + store_hint = 0x00; + } + + hci_dev_unlock(hdev); + + mgmt_new_conn_param(hdev, &hcon->dst, hcon->dst_type, + store_hint, min, max, latency, timeout); + } + + cp.handle = ev->handle; + cp.interval_min = ev->interval_min; + cp.interval_max = ev->interval_max; + cp.latency = ev->latency; + cp.timeout = ev->timeout; + cp.min_ce_len = 0; + cp.max_ce_len = 0; + + hci_send_cmd(hdev, HCI_OP_LE_CONN_PARAM_REQ_REPLY, sizeof(cp), &cp); +} + static void hci_le_meta_evt(struct hci_dev *hdev, struct sk_buff *skb) { struct hci_ev_le_meta *le_ev = (void *) skb->data; @@ -4267,6 +4602,10 @@ static void hci_le_meta_evt(struct hci_dev *hdev, struct sk_buff *skb) hci_le_conn_complete_evt(hdev, skb); break; + case HCI_EV_LE_CONN_UPDATE_COMPLETE: + hci_le_conn_update_complete_evt(hdev, skb); + break; + case HCI_EV_LE_ADVERTISING_REPORT: hci_le_adv_report_evt(hdev, skb); break; @@ -4275,6 +4614,10 @@ static void hci_le_meta_evt(struct hci_dev *hdev, struct sk_buff *skb) hci_le_ltk_request_evt(hdev, skb); break; + case HCI_EV_LE_REMOTE_CONN_PARAM_REQ: + hci_le_remote_conn_param_req_evt(hdev, skb); + break; + default: break; } @@ -4306,7 +4649,7 @@ void hci_event_packet(struct hci_dev *hdev, struct sk_buff *skb) /* Received events are (currently) only needed when a request is * ongoing so avoid unnecessary memory allocation. */ - if (hdev->req_status == HCI_REQ_PEND) { + if (hci_req_pending(hdev)) { kfree_skb(hdev->recv_evt); hdev->recv_evt = skb_clone(skb, GFP_KERNEL); } diff --git a/net/bluetooth/hci_sock.c b/net/bluetooth/hci_sock.c index 80d25c150a65..115f149362ba 100644 --- a/net/bluetooth/hci_sock.c +++ b/net/bluetooth/hci_sock.c @@ -35,13 +35,32 @@ static atomic_t monitor_promisc = ATOMIC_INIT(0); /* ----- HCI socket interface ----- */ +/* Socket info */ +#define hci_pi(sk) ((struct hci_pinfo *) sk) + +struct hci_pinfo { + struct bt_sock bt; + struct hci_dev *hdev; + struct hci_filter filter; + __u32 cmsg_mask; + unsigned short channel; +}; + static inline int hci_test_bit(int nr, void *addr) { return *((__u32 *) addr + (nr >> 5)) & ((__u32) 1 << (nr & 31)); } /* Security filter */ -static struct hci_sec_filter hci_sec_filter = { +#define HCI_SFLT_MAX_OGF 5 + +struct hci_sec_filter { + __u32 type_mask; + __u32 event_mask[2]; + __u32 ocf_mask[HCI_SFLT_MAX_OGF + 1][4]; +}; + +static const struct hci_sec_filter hci_sec_filter = { /* Packet types */ 0x10, /* Events */ @@ -481,7 +500,7 @@ static int hci_sock_blacklist_add(struct hci_dev *hdev, void __user *arg) hci_dev_lock(hdev); - err = hci_blacklist_add(hdev, &bdaddr, BDADDR_BREDR); + err = hci_bdaddr_list_add(&hdev->blacklist, &bdaddr, BDADDR_BREDR); hci_dev_unlock(hdev); @@ -498,7 +517,7 @@ static int hci_sock_blacklist_del(struct hci_dev *hdev, void __user *arg) hci_dev_lock(hdev); - err = hci_blacklist_del(hdev, &bdaddr, BDADDR_BREDR); + err = hci_bdaddr_list_del(&hdev->blacklist, &bdaddr, BDADDR_BREDR); hci_dev_unlock(hdev); @@ -517,6 +536,9 @@ static int hci_sock_bound_ioctl(struct sock *sk, unsigned int cmd, if (test_bit(HCI_USER_CHANNEL, &hdev->dev_flags)) return -EBUSY; + if (test_bit(HCI_UNCONFIGURED, &hdev->dev_flags)) + return -EOPNOTSUPP; + if (hdev->dev_type != HCI_BREDR) return -EOPNOTSUPP; @@ -690,7 +712,8 @@ static int hci_sock_bind(struct socket *sock, struct sockaddr *addr, if (test_bit(HCI_UP, &hdev->flags) || test_bit(HCI_INIT, &hdev->flags) || - test_bit(HCI_SETUP, &hdev->dev_flags)) { + test_bit(HCI_SETUP, &hdev->dev_flags) || + test_bit(HCI_CONFIG, &hdev->dev_flags)) { err = -EBUSY; hci_dev_put(hdev); goto done; @@ -960,7 +983,7 @@ static int hci_sock_sendmsg(struct kiocb *iocb, struct socket *sock, goto drop; } - if (test_bit(HCI_RAW, &hdev->flags) || (ogf == 0x3f)) { + if (ogf == 0x3f) { skb_queue_tail(&hdev->raw_q, skb); queue_work(hdev->workqueue, &hdev->tx_work); } else { diff --git a/net/bluetooth/hidp/core.c b/net/bluetooth/hidp/core.c index 8181ea4bc2f2..6c7ecf116e74 100644 --- a/net/bluetooth/hidp/core.c +++ b/net/bluetooth/hidp/core.c @@ -154,7 +154,7 @@ static int hidp_input_event(struct input_dev *dev, unsigned int type, (!!test_bit(LED_COMPOSE, dev->led) << 3) | (!!test_bit(LED_SCROLLL, dev->led) << 2) | (!!test_bit(LED_CAPSL, dev->led) << 1) | - (!!test_bit(LED_NUML, dev->led)); + (!!test_bit(LED_NUML, dev->led) << 0); if (session->leds == newleds) return 0; diff --git a/net/bluetooth/l2cap_core.c b/net/bluetooth/l2cap_core.c index 323f23cd2c37..46547b920f88 100644 --- a/net/bluetooth/l2cap_core.c +++ b/net/bluetooth/l2cap_core.c @@ -40,14 +40,13 @@ #include "smp.h" #include "a2mp.h" #include "amp.h" -#include "6lowpan.h" #define LE_FLOWCTL_MAX_CREDITS 65535 bool disable_ertm; static u32 l2cap_feat_mask = L2CAP_FEAT_FIXED_CHAN | L2CAP_FEAT_UCD; -static u8 l2cap_fixed_chan[8] = { L2CAP_FC_L2CAP | L2CAP_FC_CONNLESS, }; +static u8 l2cap_fixed_chan[8] = { L2CAP_FC_SIG_BREDR | L2CAP_FC_CONNLESS, }; static LIST_HEAD(chan_list); static DEFINE_RWLOCK(chan_list_lock); @@ -205,6 +204,7 @@ done: write_unlock(&chan_list_lock); return err; } +EXPORT_SYMBOL_GPL(l2cap_add_psm); int l2cap_add_scid(struct l2cap_chan *chan, __u16 scid) { @@ -437,6 +437,7 @@ struct l2cap_chan *l2cap_chan_create(void) return chan; } +EXPORT_SYMBOL_GPL(l2cap_chan_create); static void l2cap_chan_destroy(struct kref *kref) { @@ -464,6 +465,7 @@ void l2cap_chan_put(struct l2cap_chan *c) kref_put(&c->kref, l2cap_chan_destroy); } +EXPORT_SYMBOL_GPL(l2cap_chan_put); void l2cap_chan_set_defaults(struct l2cap_chan *chan) { @@ -482,6 +484,7 @@ void l2cap_chan_set_defaults(struct l2cap_chan *chan) set_bit(FLAG_FORCE_ACTIVE, &chan->flags); } +EXPORT_SYMBOL_GPL(l2cap_chan_set_defaults); static void l2cap_le_flowctl_init(struct l2cap_chan *chan) { @@ -614,6 +617,7 @@ void l2cap_chan_del(struct l2cap_chan *chan, int err) return; } +EXPORT_SYMBOL_GPL(l2cap_chan_del); void l2cap_conn_update_id_addr(struct hci_conn *hcon) { @@ -717,6 +721,7 @@ void l2cap_chan_close(struct l2cap_chan *chan, int reason) break; } } +EXPORT_SYMBOL(l2cap_chan_close); static inline u8 l2cap_get_auth_type(struct l2cap_chan *chan) { @@ -770,7 +775,7 @@ static inline u8 l2cap_get_auth_type(struct l2cap_chan *chan) } /* Service level security */ -int l2cap_chan_check_security(struct l2cap_chan *chan) +int l2cap_chan_check_security(struct l2cap_chan *chan, bool initiator) { struct l2cap_conn *conn = chan->conn; __u8 auth_type; @@ -780,7 +785,8 @@ int l2cap_chan_check_security(struct l2cap_chan *chan) auth_type = l2cap_get_auth_type(chan); - return hci_conn_security(conn->hcon, chan->sec_level, auth_type); + return hci_conn_security(conn->hcon, chan->sec_level, auth_type, + initiator); } static u8 l2cap_get_ident(struct l2cap_conn *conn) @@ -793,14 +799,14 @@ static u8 l2cap_get_ident(struct l2cap_conn *conn) * 200 - 254 are used by utilities like l2ping, etc. */ - spin_lock(&conn->lock); + mutex_lock(&conn->ident_lock); if (++conn->tx_ident > 128) conn->tx_ident = 1; id = conn->tx_ident; - spin_unlock(&conn->lock); + mutex_unlock(&conn->ident_lock); return id; } @@ -1273,7 +1279,7 @@ static void l2cap_do_start(struct l2cap_chan *chan) if (!(conn->info_state & L2CAP_INFO_FEAT_MASK_REQ_DONE)) return; - if (l2cap_chan_check_security(chan) && + if (l2cap_chan_check_security(chan, true) && __l2cap_no_conn_pending(chan)) { l2cap_start_connection(chan); } @@ -1352,7 +1358,7 @@ static void l2cap_conn_start(struct l2cap_conn *conn) } if (chan->state == BT_CONNECT) { - if (!l2cap_chan_check_security(chan) || + if (!l2cap_chan_check_security(chan, true) || !__l2cap_no_conn_pending(chan)) { l2cap_chan_unlock(chan); continue; @@ -1374,7 +1380,7 @@ static void l2cap_conn_start(struct l2cap_conn *conn) rsp.scid = cpu_to_le16(chan->dcid); rsp.dcid = cpu_to_le16(chan->scid); - if (l2cap_chan_check_security(chan)) { + if (l2cap_chan_check_security(chan, false)) { if (test_bit(FLAG_DEFER_SETUP, &chan->flags)) { rsp.result = cpu_to_le16(L2CAP_CR_PEND); rsp.status = cpu_to_le16(L2CAP_CS_AUTHOR_PEND); @@ -1455,13 +1461,12 @@ static struct l2cap_chan *l2cap_global_chan_by_scid(int state, u16 cid, static void l2cap_le_conn_ready(struct l2cap_conn *conn) { struct hci_conn *hcon = conn->hcon; + struct hci_dev *hdev = hcon->hdev; struct l2cap_chan *chan, *pchan; u8 dst_type; BT_DBG(""); - bt_6lowpan_add_conn(conn); - /* Check if we have socket listening on cid */ pchan = l2cap_global_chan_by_scid(BT_LISTEN, L2CAP_CID_ATT, &hcon->src, &hcon->dst); @@ -1475,9 +1480,28 @@ static void l2cap_le_conn_ready(struct l2cap_conn *conn) dst_type = bdaddr_type(hcon, hcon->dst_type); /* If device is blocked, do not create a channel for it */ - if (hci_blacklist_lookup(hcon->hdev, &hcon->dst, dst_type)) + if (hci_bdaddr_list_lookup(&hdev->blacklist, &hcon->dst, dst_type)) return; + /* For LE slave connections, make sure the connection interval + * is in the range of the minium and maximum interval that has + * been configured for this connection. If not, then trigger + * the connection update procedure. + */ + if (hcon->role == HCI_ROLE_SLAVE && + (hcon->le_conn_interval < hcon->le_conn_min_interval || + hcon->le_conn_interval > hcon->le_conn_max_interval)) { + struct l2cap_conn_param_update_req req; + + req.min = cpu_to_le16(hcon->le_conn_min_interval); + req.max = cpu_to_le16(hcon->le_conn_max_interval); + req.latency = cpu_to_le16(hcon->le_conn_latency); + req.to_multiplier = cpu_to_le16(hcon->le_supv_timeout); + + l2cap_send_cmd(conn, l2cap_get_ident(conn), + L2CAP_CONN_PARAM_UPDATE_REQ, sizeof(req), &req); + } + l2cap_chan_lock(pchan); chan = pchan->ops->new_connection(pchan); @@ -2118,7 +2142,8 @@ static inline int l2cap_skbuff_fromiovec(struct l2cap_chan *chan, struct sk_buff **frag; int sent = 0; - if (memcpy_fromiovec(skb_put(skb, count), msg->msg_iov, count)) + if (chan->ops->memcpy_fromiovec(chan, skb_put(skb, count), + msg->msg_iov, count)) return -EFAULT; sent += count; @@ -2131,18 +2156,17 @@ static inline int l2cap_skbuff_fromiovec(struct l2cap_chan *chan, count = min_t(unsigned int, conn->mtu, len); - tmp = chan->ops->alloc_skb(chan, count, + tmp = chan->ops->alloc_skb(chan, 0, count, msg->msg_flags & MSG_DONTWAIT); if (IS_ERR(tmp)) return PTR_ERR(tmp); *frag = tmp; - if (memcpy_fromiovec(skb_put(*frag, count), msg->msg_iov, count)) + if (chan->ops->memcpy_fromiovec(chan, skb_put(*frag, count), + msg->msg_iov, count)) return -EFAULT; - (*frag)->priority = skb->priority; - sent += count; len -= count; @@ -2156,26 +2180,23 @@ static inline int l2cap_skbuff_fromiovec(struct l2cap_chan *chan, } static struct sk_buff *l2cap_create_connless_pdu(struct l2cap_chan *chan, - struct msghdr *msg, size_t len, - u32 priority) + struct msghdr *msg, size_t len) { struct l2cap_conn *conn = chan->conn; struct sk_buff *skb; int err, count, hlen = L2CAP_HDR_SIZE + L2CAP_PSMLEN_SIZE; struct l2cap_hdr *lh; - BT_DBG("chan %p psm 0x%2.2x len %zu priority %u", chan, - __le16_to_cpu(chan->psm), len, priority); + BT_DBG("chan %p psm 0x%2.2x len %zu", chan, + __le16_to_cpu(chan->psm), len); count = min_t(unsigned int, (conn->mtu - hlen), len); - skb = chan->ops->alloc_skb(chan, count + hlen, + skb = chan->ops->alloc_skb(chan, hlen, count, msg->msg_flags & MSG_DONTWAIT); if (IS_ERR(skb)) return skb; - skb->priority = priority; - /* Create L2CAP header */ lh = (struct l2cap_hdr *) skb_put(skb, L2CAP_HDR_SIZE); lh->cid = cpu_to_le16(chan->dcid); @@ -2191,8 +2212,7 @@ static struct sk_buff *l2cap_create_connless_pdu(struct l2cap_chan *chan, } static struct sk_buff *l2cap_create_basic_pdu(struct l2cap_chan *chan, - struct msghdr *msg, size_t len, - u32 priority) + struct msghdr *msg, size_t len) { struct l2cap_conn *conn = chan->conn; struct sk_buff *skb; @@ -2203,13 +2223,11 @@ static struct sk_buff *l2cap_create_basic_pdu(struct l2cap_chan *chan, count = min_t(unsigned int, (conn->mtu - L2CAP_HDR_SIZE), len); - skb = chan->ops->alloc_skb(chan, count + L2CAP_HDR_SIZE, + skb = chan->ops->alloc_skb(chan, L2CAP_HDR_SIZE, count, msg->msg_flags & MSG_DONTWAIT); if (IS_ERR(skb)) return skb; - skb->priority = priority; - /* Create L2CAP header */ lh = (struct l2cap_hdr *) skb_put(skb, L2CAP_HDR_SIZE); lh->cid = cpu_to_le16(chan->dcid); @@ -2247,7 +2265,7 @@ static struct sk_buff *l2cap_create_iframe_pdu(struct l2cap_chan *chan, count = min_t(unsigned int, (conn->mtu - hlen), len); - skb = chan->ops->alloc_skb(chan, count + hlen, + skb = chan->ops->alloc_skb(chan, hlen, count, msg->msg_flags & MSG_DONTWAIT); if (IS_ERR(skb)) return skb; @@ -2368,7 +2386,7 @@ static struct sk_buff *l2cap_create_le_flowctl_pdu(struct l2cap_chan *chan, count = min_t(unsigned int, (conn->mtu - hlen), len); - skb = chan->ops->alloc_skb(chan, count + hlen, + skb = chan->ops->alloc_skb(chan, hlen, count, msg->msg_flags & MSG_DONTWAIT); if (IS_ERR(skb)) return skb; @@ -2430,8 +2448,7 @@ static int l2cap_segment_le_sdu(struct l2cap_chan *chan, return 0; } -int l2cap_chan_send(struct l2cap_chan *chan, struct msghdr *msg, size_t len, - u32 priority) +int l2cap_chan_send(struct l2cap_chan *chan, struct msghdr *msg, size_t len) { struct sk_buff *skb; int err; @@ -2442,7 +2459,7 @@ int l2cap_chan_send(struct l2cap_chan *chan, struct msghdr *msg, size_t len, /* Connectionless channel */ if (chan->chan_type == L2CAP_CHAN_CONN_LESS) { - skb = l2cap_create_connless_pdu(chan, msg, len, priority); + skb = l2cap_create_connless_pdu(chan, msg, len); if (IS_ERR(skb)) return PTR_ERR(skb); @@ -2499,7 +2516,7 @@ int l2cap_chan_send(struct l2cap_chan *chan, struct msghdr *msg, size_t len, return -EMSGSIZE; /* Create a basic PDU */ - skb = l2cap_create_basic_pdu(chan, msg, len, priority); + skb = l2cap_create_basic_pdu(chan, msg, len); if (IS_ERR(skb)) return PTR_ERR(skb); @@ -2562,6 +2579,7 @@ int l2cap_chan_send(struct l2cap_chan *chan, struct msghdr *msg, size_t len, return err; } +EXPORT_SYMBOL_GPL(l2cap_chan_send); static void l2cap_send_srej(struct l2cap_chan *chan, u16 txseq) { @@ -3217,6 +3235,9 @@ done: switch (chan->mode) { case L2CAP_MODE_BASIC: + if (disable_ertm) + break; + if (!(chan->conn->feat_mask & L2CAP_FEAT_ERTM) && !(chan->conn->feat_mask & L2CAP_FEAT_STREAMING)) break; @@ -3829,7 +3850,7 @@ static struct l2cap_chan *l2cap_connect(struct l2cap_conn *conn, chan->ident = cmd->ident; if (conn->info_state & L2CAP_INFO_FEAT_MASK_REQ_DONE) { - if (l2cap_chan_check_security(chan)) { + if (l2cap_chan_check_security(chan, false)) { if (test_bit(FLAG_DEFER_SETUP, &chan->flags)) { l2cap_state_change(chan, BT_CONNECT2); result = L2CAP_CR_PEND; @@ -5197,27 +5218,6 @@ static inline int l2cap_move_channel_confirm_rsp(struct l2cap_conn *conn, return 0; } -static inline int l2cap_check_conn_param(u16 min, u16 max, u16 latency, - u16 to_multiplier) -{ - u16 max_latency; - - if (min > max || min < 6 || max > 3200) - return -EINVAL; - - if (to_multiplier < 10 || to_multiplier > 3200) - return -EINVAL; - - if (max >= to_multiplier * 8) - return -EINVAL; - - max_latency = (to_multiplier * 8 / max) - 1; - if (latency > 499 || latency > max_latency) - return -EINVAL; - - return 0; -} - static inline int l2cap_conn_param_update_req(struct l2cap_conn *conn, struct l2cap_cmd_hdr *cmd, u16 cmd_len, u8 *data) @@ -5228,7 +5228,7 @@ static inline int l2cap_conn_param_update_req(struct l2cap_conn *conn, u16 min, max, latency, to_multiplier; int err; - if (!(hcon->link_mode & HCI_LM_MASTER)) + if (hcon->role != HCI_ROLE_MASTER) return -EINVAL; if (cmd_len != sizeof(struct l2cap_conn_param_update_req)) @@ -5245,7 +5245,7 @@ static inline int l2cap_conn_param_update_req(struct l2cap_conn *conn, memset(&rsp, 0, sizeof(rsp)); - err = l2cap_check_conn_param(min, max, latency, to_multiplier); + err = hci_check_conn_params(min, max, latency, to_multiplier); if (err) rsp.result = cpu_to_le16(L2CAP_CONN_PARAM_REJECTED); else @@ -5254,8 +5254,16 @@ static inline int l2cap_conn_param_update_req(struct l2cap_conn *conn, l2cap_send_cmd(conn, cmd->ident, L2CAP_CONN_PARAM_UPDATE_RSP, sizeof(rsp), &rsp); - if (!err) - hci_le_conn_update(hcon, min, max, latency, to_multiplier); + if (!err) { + u8 store_hint; + + store_hint = hci_le_conn_update(hcon, min, max, latency, + to_multiplier); + mgmt_new_conn_param(hcon->hdev, &hcon->dst, hcon->dst_type, + store_hint, min, max, latency, + to_multiplier); + + } return 0; } @@ -6879,9 +6887,6 @@ static void l2cap_att_channel(struct l2cap_conn *conn, BT_DBG("chan %p, len %d", chan, skb->len); - if (hci_blacklist_lookup(hcon->hdev, &hcon->dst, hcon->dst_type)) - goto drop; - if (chan->imtu < skb->len) goto drop; @@ -6914,6 +6919,16 @@ static void l2cap_recv_frame(struct l2cap_conn *conn, struct sk_buff *skb) return; } + /* Since we can't actively block incoming LE connections we must + * at least ensure that we ignore incoming data from them. + */ + if (hcon->type == LE_LINK && + hci_bdaddr_list_lookup(&hcon->hdev->blacklist, &hcon->dst, + bdaddr_type(hcon, hcon->dst_type))) { + kfree_skb(skb); + return; + } + BT_DBG("len %d, cid 0x%4.4x", len, cid); switch (cid) { @@ -6940,10 +6955,6 @@ static void l2cap_recv_frame(struct l2cap_conn *conn, struct sk_buff *skb) l2cap_conn_del(conn->hcon, EACCES); break; - case L2CAP_FC_6LOWPAN: - bt_6lowpan_recv(conn, skb); - break; - default: l2cap_data_channel(conn, cid, skb); break; @@ -6974,7 +6985,7 @@ static struct l2cap_conn *l2cap_conn_add(struct hci_conn *hcon) if (!hchan) return NULL; - conn = kzalloc(sizeof(struct l2cap_conn), GFP_KERNEL); + conn = kzalloc(sizeof(*conn), GFP_KERNEL); if (!conn) { hci_chan_del(hchan); return NULL; @@ -7006,7 +7017,7 @@ static struct l2cap_conn *l2cap_conn_add(struct hci_conn *hcon) conn->hs_enabled = test_bit(HCI_HS_ENABLED, &hcon->hdev->dev_flags); - spin_lock_init(&conn->lock); + mutex_init(&conn->ident_lock); mutex_init(&conn->chan_lock); INIT_LIST_HEAD(&conn->chan_l); @@ -7042,7 +7053,6 @@ int l2cap_chan_connect(struct l2cap_chan *chan, __le16 psm, u16 cid, struct l2cap_conn *conn; struct hci_conn *hcon; struct hci_dev *hdev; - __u8 auth_type; int err; BT_DBG("%pMR -> %pMR (type %u) psm 0x%2.2x", &chan->src, dst, @@ -7084,7 +7094,7 @@ int l2cap_chan_connect(struct l2cap_chan *chan, __le16 psm, u16 cid, break; /* fall through */ default: - err = -ENOTSUPP; + err = -EOPNOTSUPP; goto done; } @@ -7118,9 +7128,9 @@ int l2cap_chan_connect(struct l2cap_chan *chan, __le16 psm, u16 cid, chan->psm = psm; chan->dcid = cid; - auth_type = l2cap_get_auth_type(chan); - if (bdaddr_type_is_le(dst_type)) { + u8 role; + /* Convert from L2CAP channel address type to HCI address type */ if (dst_type == BDADDR_LE_PUBLIC) @@ -7128,9 +7138,15 @@ int l2cap_chan_connect(struct l2cap_chan *chan, __le16 psm, u16 cid, else dst_type = ADDR_LE_DEV_RANDOM; + if (test_bit(HCI_ADVERTISING, &hdev->dev_flags)) + role = HCI_ROLE_SLAVE; + else + role = HCI_ROLE_MASTER; + hcon = hci_connect_le(hdev, dst, dst_type, chan->sec_level, - auth_type); + HCI_LE_CONN_TIMEOUT, role); } else { + u8 auth_type = l2cap_get_auth_type(chan); hcon = hci_connect_acl(hdev, dst, chan->sec_level, auth_type); } @@ -7176,7 +7192,7 @@ int l2cap_chan_connect(struct l2cap_chan *chan, __le16 psm, u16 cid, if (hcon->state == BT_CONNECTED) { if (chan->chan_type != L2CAP_CHAN_CONN_ORIENTED) { __clear_chan_timer(chan); - if (l2cap_chan_check_security(chan)) + if (l2cap_chan_check_security(chan, true)) l2cap_state_change(chan, BT_CONNECTED); } else l2cap_do_start(chan); @@ -7190,6 +7206,7 @@ done: hci_dev_put(hdev); return err; } +EXPORT_SYMBOL_GPL(l2cap_chan_connect); /* ---- L2CAP interface with lower layer (HCI) ---- */ @@ -7252,8 +7269,6 @@ void l2cap_disconn_cfm(struct hci_conn *hcon, u8 reason) { BT_DBG("hcon %p reason %d", hcon, reason); - bt_6lowpan_del_conn(hcon->l2cap_data); - l2cap_conn_del(hcon, bt_to_errno(reason)); } @@ -7536,14 +7551,11 @@ int __init l2cap_init(void) debugfs_create_u16("l2cap_le_default_mps", 0644, bt_debugfs, &le_default_mps); - bt_6lowpan_init(); - return 0; } void l2cap_exit(void) { - bt_6lowpan_cleanup(); debugfs_remove(l2cap_debugfs); l2cap_cleanup_sockets(); } diff --git a/net/bluetooth/l2cap_sock.c b/net/bluetooth/l2cap_sock.c index e1378693cc90..1884f72083c2 100644 --- a/net/bluetooth/l2cap_sock.c +++ b/net/bluetooth/l2cap_sock.c @@ -279,7 +279,7 @@ static int l2cap_sock_listen(struct socket *sock, int backlog) break; /* fall through */ default: - err = -ENOTSUPP; + err = -EOPNOTSUPP; goto done; } @@ -361,7 +361,8 @@ static int l2cap_sock_getname(struct socket *sock, struct sockaddr *addr, BT_DBG("sock %p, sk %p", sock, sk); if (peer && sk->sk_state != BT_CONNECTED && - sk->sk_state != BT_CONNECT && sk->sk_state != BT_CONNECT2) + sk->sk_state != BT_CONNECT && sk->sk_state != BT_CONNECT2 && + sk->sk_state != BT_CONFIG) return -ENOTCONN; memset(la, 0, sizeof(struct sockaddr_l2)); @@ -796,7 +797,7 @@ static int l2cap_sock_setsockopt(struct socket *sock, int level, int optname, } else if ((sk->sk_state == BT_CONNECT2 && test_bit(BT_SK_DEFER_SETUP, &bt_sk(sk)->flags)) || sk->sk_state == BT_CONNECTED) { - if (!l2cap_chan_check_security(chan)) + if (!l2cap_chan_check_security(chan, true)) set_bit(BT_SK_SUSPEND, &bt_sk(sk)->flags); else sk->sk_state_change(sk); @@ -964,7 +965,7 @@ static int l2cap_sock_sendmsg(struct kiocb *iocb, struct socket *sock, return err; l2cap_chan_lock(chan); - err = l2cap_chan_send(chan, msg, len, sk->sk_priority); + err = l2cap_chan_send(chan, msg, len); l2cap_chan_unlock(chan); return err; @@ -1111,7 +1112,8 @@ static int l2cap_sock_shutdown(struct socket *sock, int how) l2cap_chan_close(chan, 0); lock_sock(sk); - if (sock_flag(sk, SOCK_LINGER) && sk->sk_lingertime) + if (sock_flag(sk, SOCK_LINGER) && sk->sk_lingertime && + !(current->flags & PF_EXITING)) err = bt_sock_wait_state(sk, BT_CLOSED, sk->sk_lingertime); } @@ -1292,6 +1294,7 @@ static void l2cap_sock_state_change_cb(struct l2cap_chan *chan, int state, } static struct sk_buff *l2cap_sock_alloc_skb_cb(struct l2cap_chan *chan, + unsigned long hdr_len, unsigned long len, int nb) { struct sock *sk = chan->data; @@ -1299,17 +1302,26 @@ static struct sk_buff *l2cap_sock_alloc_skb_cb(struct l2cap_chan *chan, int err; l2cap_chan_unlock(chan); - skb = bt_skb_send_alloc(sk, len, nb, &err); + skb = bt_skb_send_alloc(sk, hdr_len + len, nb, &err); l2cap_chan_lock(chan); if (!skb) return ERR_PTR(err); + skb->priority = sk->sk_priority; + bt_cb(skb)->chan = chan; return skb; } +static int l2cap_sock_memcpy_fromiovec_cb(struct l2cap_chan *chan, + unsigned char *kdata, + struct iovec *iov, int len) +{ + return memcpy_fromiovec(kdata, iov, len); +} + static void l2cap_sock_ready_cb(struct l2cap_chan *chan) { struct sock *sk = chan->data; @@ -1375,20 +1387,21 @@ static void l2cap_sock_suspend_cb(struct l2cap_chan *chan) sk->sk_state_change(sk); } -static struct l2cap_ops l2cap_chan_ops = { - .name = "L2CAP Socket Interface", - .new_connection = l2cap_sock_new_connection_cb, - .recv = l2cap_sock_recv_cb, - .close = l2cap_sock_close_cb, - .teardown = l2cap_sock_teardown_cb, - .state_change = l2cap_sock_state_change_cb, - .ready = l2cap_sock_ready_cb, - .defer = l2cap_sock_defer_cb, - .resume = l2cap_sock_resume_cb, - .suspend = l2cap_sock_suspend_cb, - .set_shutdown = l2cap_sock_set_shutdown_cb, - .get_sndtimeo = l2cap_sock_get_sndtimeo_cb, - .alloc_skb = l2cap_sock_alloc_skb_cb, +static const struct l2cap_ops l2cap_chan_ops = { + .name = "L2CAP Socket Interface", + .new_connection = l2cap_sock_new_connection_cb, + .recv = l2cap_sock_recv_cb, + .close = l2cap_sock_close_cb, + .teardown = l2cap_sock_teardown_cb, + .state_change = l2cap_sock_state_change_cb, + .ready = l2cap_sock_ready_cb, + .defer = l2cap_sock_defer_cb, + .resume = l2cap_sock_resume_cb, + .suspend = l2cap_sock_suspend_cb, + .set_shutdown = l2cap_sock_set_shutdown_cb, + .get_sndtimeo = l2cap_sock_get_sndtimeo_cb, + .alloc_skb = l2cap_sock_alloc_skb_cb, + .memcpy_fromiovec = l2cap_sock_memcpy_fromiovec_cb, }; static void l2cap_sock_destruct(struct sock *sk) diff --git a/net/bluetooth/mgmt.c b/net/bluetooth/mgmt.c index af8e0a6243b7..b8554d429d88 100644 --- a/net/bluetooth/mgmt.c +++ b/net/bluetooth/mgmt.c @@ -35,7 +35,7 @@ #include "smp.h" #define MGMT_VERSION 1 -#define MGMT_REVISION 6 +#define MGMT_REVISION 7 static const u16 mgmt_commands[] = { MGMT_OP_READ_INDEX_LIST, @@ -44,7 +44,7 @@ static const u16 mgmt_commands[] = { MGMT_OP_SET_DISCOVERABLE, MGMT_OP_SET_CONNECTABLE, MGMT_OP_SET_FAST_CONNECTABLE, - MGMT_OP_SET_PAIRABLE, + MGMT_OP_SET_BONDABLE, MGMT_OP_SET_LINK_SECURITY, MGMT_OP_SET_SSP, MGMT_OP_SET_HS, @@ -85,6 +85,14 @@ static const u16 mgmt_commands[] = { MGMT_OP_SET_PRIVACY, MGMT_OP_LOAD_IRKS, MGMT_OP_GET_CONN_INFO, + MGMT_OP_GET_CLOCK_INFO, + MGMT_OP_ADD_DEVICE, + MGMT_OP_REMOVE_DEVICE, + MGMT_OP_LOAD_CONN_PARAM, + MGMT_OP_READ_UNCONF_INDEX_LIST, + MGMT_OP_READ_CONFIG_INFO, + MGMT_OP_SET_EXTERNAL_CONFIG, + MGMT_OP_SET_PUBLIC_ADDRESS, }; static const u16 mgmt_events[] = { @@ -111,6 +119,12 @@ static const u16 mgmt_events[] = { MGMT_EV_PASSKEY_NOTIFY, MGMT_EV_NEW_IRK, MGMT_EV_NEW_CSRK, + MGMT_EV_DEVICE_ADDED, + MGMT_EV_DEVICE_REMOVED, + MGMT_EV_NEW_CONN_PARAM, + MGMT_EV_UNCONF_INDEX_ADDED, + MGMT_EV_UNCONF_INDEX_REMOVED, + MGMT_EV_NEW_CONFIG_OPTIONS, }; #define CACHE_TIMEOUT msecs_to_jiffies(2 * 1000) @@ -200,6 +214,36 @@ static u8 mgmt_status(u8 hci_status) return MGMT_STATUS_FAILED; } +static int mgmt_event(u16 event, struct hci_dev *hdev, void *data, u16 data_len, + struct sock *skip_sk) +{ + struct sk_buff *skb; + struct mgmt_hdr *hdr; + + skb = alloc_skb(sizeof(*hdr) + data_len, GFP_KERNEL); + if (!skb) + return -ENOMEM; + + hdr = (void *) skb_put(skb, sizeof(*hdr)); + hdr->opcode = cpu_to_le16(event); + if (hdev) + hdr->index = cpu_to_le16(hdev->id); + else + hdr->index = cpu_to_le16(MGMT_INDEX_NONE); + hdr->len = cpu_to_le16(data_len); + + if (data) + memcpy(skb_put(skb, data_len), data, data_len); + + /* Time stamp */ + __net_timestamp(skb); + + hci_send_to_control(skb, skip_sk); + kfree_skb(skb); + + return 0; +} + static int cmd_status(struct sock *sk, u16 index, u16 cmd, u8 status) { struct sk_buff *skb; @@ -327,7 +371,8 @@ static int read_index_list(struct sock *sk, struct hci_dev *hdev, void *data, count = 0; list_for_each_entry(d, &hci_dev_list, list) { - if (d->dev_type == HCI_BREDR) + if (d->dev_type == HCI_BREDR && + !test_bit(HCI_UNCONFIGURED, &d->dev_flags)) count++; } @@ -340,13 +385,19 @@ static int read_index_list(struct sock *sk, struct hci_dev *hdev, void *data, count = 0; list_for_each_entry(d, &hci_dev_list, list) { - if (test_bit(HCI_SETUP, &d->dev_flags)) + if (test_bit(HCI_SETUP, &d->dev_flags) || + test_bit(HCI_CONFIG, &d->dev_flags) || + test_bit(HCI_USER_CHANNEL, &d->dev_flags)) continue; - if (test_bit(HCI_USER_CHANNEL, &d->dev_flags)) + /* Devices marked as raw-only are neither configured + * nor unconfigured controllers. + */ + if (test_bit(HCI_QUIRK_RAW_DEVICE, &d->quirks)) continue; - if (d->dev_type == HCI_BREDR) { + if (d->dev_type == HCI_BREDR && + !test_bit(HCI_UNCONFIGURED, &d->dev_flags)) { rp->index[count++] = cpu_to_le16(d->id); BT_DBG("Added hci%u", d->id); } @@ -365,19 +416,151 @@ static int read_index_list(struct sock *sk, struct hci_dev *hdev, void *data, return err; } +static int read_unconf_index_list(struct sock *sk, struct hci_dev *hdev, + void *data, u16 data_len) +{ + struct mgmt_rp_read_unconf_index_list *rp; + struct hci_dev *d; + size_t rp_len; + u16 count; + int err; + + BT_DBG("sock %p", sk); + + read_lock(&hci_dev_list_lock); + + count = 0; + list_for_each_entry(d, &hci_dev_list, list) { + if (d->dev_type == HCI_BREDR && + test_bit(HCI_UNCONFIGURED, &d->dev_flags)) + count++; + } + + rp_len = sizeof(*rp) + (2 * count); + rp = kmalloc(rp_len, GFP_ATOMIC); + if (!rp) { + read_unlock(&hci_dev_list_lock); + return -ENOMEM; + } + + count = 0; + list_for_each_entry(d, &hci_dev_list, list) { + if (test_bit(HCI_SETUP, &d->dev_flags) || + test_bit(HCI_CONFIG, &d->dev_flags) || + test_bit(HCI_USER_CHANNEL, &d->dev_flags)) + continue; + + /* Devices marked as raw-only are neither configured + * nor unconfigured controllers. + */ + if (test_bit(HCI_QUIRK_RAW_DEVICE, &d->quirks)) + continue; + + if (d->dev_type == HCI_BREDR && + test_bit(HCI_UNCONFIGURED, &d->dev_flags)) { + rp->index[count++] = cpu_to_le16(d->id); + BT_DBG("Added hci%u", d->id); + } + } + + rp->num_controllers = cpu_to_le16(count); + rp_len = sizeof(*rp) + (2 * count); + + read_unlock(&hci_dev_list_lock); + + err = cmd_complete(sk, MGMT_INDEX_NONE, MGMT_OP_READ_UNCONF_INDEX_LIST, + 0, rp, rp_len); + + kfree(rp); + + return err; +} + +static bool is_configured(struct hci_dev *hdev) +{ + if (test_bit(HCI_QUIRK_EXTERNAL_CONFIG, &hdev->quirks) && + !test_bit(HCI_EXT_CONFIGURED, &hdev->dev_flags)) + return false; + + if (test_bit(HCI_QUIRK_INVALID_BDADDR, &hdev->quirks) && + !bacmp(&hdev->public_addr, BDADDR_ANY)) + return false; + + return true; +} + +static __le32 get_missing_options(struct hci_dev *hdev) +{ + u32 options = 0; + + if (test_bit(HCI_QUIRK_EXTERNAL_CONFIG, &hdev->quirks) && + !test_bit(HCI_EXT_CONFIGURED, &hdev->dev_flags)) + options |= MGMT_OPTION_EXTERNAL_CONFIG; + + if (test_bit(HCI_QUIRK_INVALID_BDADDR, &hdev->quirks) && + !bacmp(&hdev->public_addr, BDADDR_ANY)) + options |= MGMT_OPTION_PUBLIC_ADDRESS; + + return cpu_to_le32(options); +} + +static int new_options(struct hci_dev *hdev, struct sock *skip) +{ + __le32 options = get_missing_options(hdev); + + return mgmt_event(MGMT_EV_NEW_CONFIG_OPTIONS, hdev, &options, + sizeof(options), skip); +} + +static int send_options_rsp(struct sock *sk, u16 opcode, struct hci_dev *hdev) +{ + __le32 options = get_missing_options(hdev); + + return cmd_complete(sk, hdev->id, opcode, 0, &options, + sizeof(options)); +} + +static int read_config_info(struct sock *sk, struct hci_dev *hdev, + void *data, u16 data_len) +{ + struct mgmt_rp_read_config_info rp; + u32 options = 0; + + BT_DBG("sock %p %s", sk, hdev->name); + + hci_dev_lock(hdev); + + memset(&rp, 0, sizeof(rp)); + rp.manufacturer = cpu_to_le16(hdev->manufacturer); + + if (test_bit(HCI_QUIRK_EXTERNAL_CONFIG, &hdev->quirks)) + options |= MGMT_OPTION_EXTERNAL_CONFIG; + + if (hdev->set_bdaddr) + options |= MGMT_OPTION_PUBLIC_ADDRESS; + + rp.supported_options = cpu_to_le32(options); + rp.missing_options = get_missing_options(hdev); + + hci_dev_unlock(hdev); + + return cmd_complete(sk, hdev->id, MGMT_OP_READ_CONFIG_INFO, 0, &rp, + sizeof(rp)); +} + static u32 get_supported_settings(struct hci_dev *hdev) { u32 settings = 0; settings |= MGMT_SETTING_POWERED; - settings |= MGMT_SETTING_PAIRABLE; + settings |= MGMT_SETTING_BONDABLE; settings |= MGMT_SETTING_DEBUG_KEYS; + settings |= MGMT_SETTING_CONNECTABLE; + settings |= MGMT_SETTING_DISCOVERABLE; if (lmp_bredr_capable(hdev)) { - settings |= MGMT_SETTING_CONNECTABLE; if (hdev->hci_ver >= BLUETOOTH_VER_1_2) settings |= MGMT_SETTING_FAST_CONNECTABLE; - settings |= MGMT_SETTING_DISCOVERABLE; settings |= MGMT_SETTING_BREDR; settings |= MGMT_SETTING_LINK_SECURITY; @@ -387,7 +570,7 @@ static u32 get_supported_settings(struct hci_dev *hdev) } if (lmp_sc_capable(hdev) || - test_bit(HCI_FORCE_SC, &hdev->dev_flags)) + test_bit(HCI_FORCE_SC, &hdev->dbg_flags)) settings |= MGMT_SETTING_SECURE_CONN; } @@ -397,6 +580,10 @@ static u32 get_supported_settings(struct hci_dev *hdev) settings |= MGMT_SETTING_PRIVACY; } + if (test_bit(HCI_QUIRK_EXTERNAL_CONFIG, &hdev->quirks) || + hdev->set_bdaddr) + settings |= MGMT_SETTING_CONFIGURATION; + return settings; } @@ -416,8 +603,8 @@ static u32 get_current_settings(struct hci_dev *hdev) if (test_bit(HCI_DISCOVERABLE, &hdev->dev_flags)) settings |= MGMT_SETTING_DISCOVERABLE; - if (test_bit(HCI_PAIRABLE, &hdev->dev_flags)) - settings |= MGMT_SETTING_PAIRABLE; + if (test_bit(HCI_BONDABLE, &hdev->dev_flags)) + settings |= MGMT_SETTING_BONDABLE; if (test_bit(HCI_BREDR_ENABLED, &hdev->dev_flags)) settings |= MGMT_SETTING_BREDR; @@ -440,7 +627,7 @@ static u32 get_current_settings(struct hci_dev *hdev) if (test_bit(HCI_SC_ENABLED, &hdev->dev_flags)) settings |= MGMT_SETTING_SECURE_CONN; - if (test_bit(HCI_DEBUG_KEYS, &hdev->dev_flags)) + if (test_bit(HCI_KEEP_DEBUG_KEYS, &hdev->dev_flags)) settings |= MGMT_SETTING_DEBUG_KEYS; if (test_bit(HCI_PRIVACY, &hdev->dev_flags)) @@ -571,6 +758,22 @@ static struct pending_cmd *mgmt_pending_find(u16 opcode, struct hci_dev *hdev) return NULL; } +static struct pending_cmd *mgmt_pending_find_data(u16 opcode, + struct hci_dev *hdev, + const void *data) +{ + struct pending_cmd *cmd; + + list_for_each_entry(cmd, &hdev->mgmt_pending, list) { + if (cmd->user_data != data) + continue; + if (cmd->opcode == opcode) + return cmd; + } + + return NULL; +} + static u8 create_scan_rsp_data(struct hci_dev *hdev, u8 *ptr) { u8 ad_len = 0; @@ -703,6 +906,16 @@ static void update_adv_data(struct hci_request *req) hci_req_add(req, HCI_OP_LE_SET_ADV_DATA, sizeof(cp), &cp); } +int mgmt_update_adv_data(struct hci_dev *hdev) +{ + struct hci_request req; + + hci_req_init(&req, hdev); + update_adv_data(&req); + + return hci_req_run(&req, NULL); +} + static void create_eir(struct hci_dev *hdev, u8 *data) { u8 *ptr = data; @@ -836,6 +1049,13 @@ static bool get_connectable(struct hci_dev *hdev) return test_bit(HCI_CONNECTABLE, &hdev->dev_flags); } +static void disable_advertising(struct hci_request *req) +{ + u8 enable = 0x00; + + hci_req_add(req, HCI_OP_LE_SET_ADV_ENABLE, sizeof(enable), &enable); +} + static void enable_advertising(struct hci_request *req) { struct hci_dev *hdev = req->hdev; @@ -843,12 +1063,18 @@ static void enable_advertising(struct hci_request *req) u8 own_addr_type, enable = 0x01; bool connectable; - /* Clear the HCI_ADVERTISING bit temporarily so that the + if (hci_conn_num(hdev, LE_LINK) > 0) + return; + + if (test_bit(HCI_LE_ADV, &hdev->dev_flags)) + disable_advertising(req); + + /* Clear the HCI_LE_ADV bit temporarily so that the * hci_update_random_address knows that it's safe to go ahead * and write a new random address. The flag will be set back on * as soon as the SET_ADV_ENABLE HCI command completes. */ - clear_bit(HCI_ADVERTISING, &hdev->dev_flags); + clear_bit(HCI_LE_ADV, &hdev->dev_flags); connectable = get_connectable(hdev); @@ -860,8 +1086,8 @@ static void enable_advertising(struct hci_request *req) return; memset(&cp, 0, sizeof(cp)); - cp.min_interval = cpu_to_le16(0x0800); - cp.max_interval = cpu_to_le16(0x0800); + cp.min_interval = cpu_to_le16(hdev->le_adv_min_interval); + cp.max_interval = cpu_to_le16(hdev->le_adv_max_interval); cp.type = connectable ? LE_ADV_IND : LE_ADV_NONCONN_IND; cp.own_address_type = own_addr_type; cp.channel_map = hdev->le_adv_channel_map; @@ -871,13 +1097,6 @@ static void enable_advertising(struct hci_request *req) hci_req_add(req, HCI_OP_LE_SET_ADV_ENABLE, sizeof(enable), &enable); } -static void disable_advertising(struct hci_request *req) -{ - u8 enable = 0x00; - - hci_req_add(req, HCI_OP_LE_SET_ADV_ENABLE, sizeof(enable), &enable); -} - static void service_cache_off(struct work_struct *work) { struct hci_dev *hdev = container_of(work, struct hci_dev, @@ -909,19 +1128,14 @@ static void rpa_expired(struct work_struct *work) set_bit(HCI_RPA_EXPIRED, &hdev->dev_flags); - if (!test_bit(HCI_ADVERTISING, &hdev->dev_flags) || - hci_conn_num(hdev, LE_LINK) > 0) + if (!test_bit(HCI_ADVERTISING, &hdev->dev_flags)) return; /* The generation of a new RPA and programming it into the * controller happens in the enable_advertising() function. */ - hci_req_init(&req, hdev); - - disable_advertising(&req); enable_advertising(&req); - hci_req_run(&req, NULL); } @@ -938,7 +1152,7 @@ static void mgmt_init_hdev(struct sock *sk, struct hci_dev *hdev) * for mgmt we require user-space to explicitly enable * it */ - clear_bit(HCI_PAIRABLE, &hdev->dev_flags); + clear_bit(HCI_BONDABLE, &hdev->dev_flags); } static int read_controller_info(struct sock *sk, struct hci_dev *hdev, @@ -984,7 +1198,7 @@ static struct pending_cmd *mgmt_pending_add(struct sock *sk, u16 opcode, { struct pending_cmd *cmd; - cmd = kmalloc(sizeof(*cmd), GFP_KERNEL); + cmd = kzalloc(sizeof(*cmd), GFP_KERNEL); if (!cmd) return NULL; @@ -1047,7 +1261,7 @@ static void clean_up_hci_complete(struct hci_dev *hdev, u8 status) } } -static void hci_stop_discovery(struct hci_request *req) +static bool hci_stop_discovery(struct hci_request *req) { struct hci_dev *hdev = req->hdev; struct hci_cp_remote_name_req_cancel cp; @@ -1062,32 +1276,39 @@ static void hci_stop_discovery(struct hci_request *req) hci_req_add_le_scan_disable(req); } - break; + return true; case DISCOVERY_RESOLVING: e = hci_inquiry_cache_lookup_resolve(hdev, BDADDR_ANY, NAME_PENDING); if (!e) - return; + break; bacpy(&cp.bdaddr, &e->data.bdaddr); hci_req_add(req, HCI_OP_REMOTE_NAME_REQ_CANCEL, sizeof(cp), &cp); - break; + return true; default: /* Passive scanning */ - if (test_bit(HCI_LE_SCAN, &hdev->dev_flags)) + if (test_bit(HCI_LE_SCAN, &hdev->dev_flags)) { hci_req_add_le_scan_disable(req); + return true; + } + break; } + + return false; } static int clean_up_hci_state(struct hci_dev *hdev) { struct hci_request req; struct hci_conn *conn; + bool discov_stopped; + int err; hci_req_init(&req, hdev); @@ -1097,10 +1318,10 @@ static int clean_up_hci_state(struct hci_dev *hdev) hci_req_add(&req, HCI_OP_WRITE_SCAN_ENABLE, 1, &scan); } - if (test_bit(HCI_ADVERTISING, &hdev->dev_flags)) + if (test_bit(HCI_LE_ADV, &hdev->dev_flags)) disable_advertising(&req); - hci_stop_discovery(&req); + discov_stopped = hci_stop_discovery(&req); list_for_each_entry(conn, &hdev->conn_hash.list, list) { struct hci_cp_disconnect dc; @@ -1134,7 +1355,11 @@ static int clean_up_hci_state(struct hci_dev *hdev) } } - return hci_req_run(&req, clean_up_hci_complete); + err = hci_req_run(&req, clean_up_hci_complete); + if (!err && discov_stopped) + hci_discovery_set_state(hdev, DISCOVERY_STOPPING); + + return err; } static int set_powered(struct sock *sk, struct hci_dev *hdev, void *data, @@ -1203,36 +1428,6 @@ failed: return err; } -static int mgmt_event(u16 event, struct hci_dev *hdev, void *data, u16 data_len, - struct sock *skip_sk) -{ - struct sk_buff *skb; - struct mgmt_hdr *hdr; - - skb = alloc_skb(sizeof(*hdr) + data_len, GFP_KERNEL); - if (!skb) - return -ENOMEM; - - hdr = (void *) skb_put(skb, sizeof(*hdr)); - hdr->opcode = cpu_to_le16(event); - if (hdev) - hdr->index = cpu_to_le16(hdev->id); - else - hdr->index = cpu_to_le16(MGMT_INDEX_NONE); - hdr->len = cpu_to_le16(data_len); - - if (data) - memcpy(skb_put(skb, data_len), data, data_len); - - /* Time stamp */ - __net_timestamp(skb); - - hci_send_to_control(skb, skip_sk); - kfree_skb(skb); - - return 0; -} - static int new_settings(struct hci_dev *hdev, struct sock *skip) { __le32 ev; @@ -1242,6 +1437,11 @@ static int new_settings(struct hci_dev *hdev, struct sock *skip) return mgmt_event(MGMT_EV_NEW_SETTINGS, hdev, &ev, sizeof(ev), skip); } +int mgmt_new_settings(struct hci_dev *hdev) +{ + return new_settings(hdev, NULL); +} + struct cmd_lookup { struct sock *sk; struct hci_dev *hdev; @@ -1553,7 +1753,7 @@ static void set_connectable_complete(struct hci_dev *hdev, u8 status) { struct pending_cmd *cmd; struct mgmt_mode *cp; - bool changed; + bool conn_changed, discov_changed; BT_DBG("status 0x%02x", status); @@ -1570,15 +1770,25 @@ static void set_connectable_complete(struct hci_dev *hdev, u8 status) } cp = cmd->param; - if (cp->val) - changed = !test_and_set_bit(HCI_CONNECTABLE, &hdev->dev_flags); - else - changed = test_and_clear_bit(HCI_CONNECTABLE, &hdev->dev_flags); + if (cp->val) { + conn_changed = !test_and_set_bit(HCI_CONNECTABLE, + &hdev->dev_flags); + discov_changed = false; + } else { + conn_changed = test_and_clear_bit(HCI_CONNECTABLE, + &hdev->dev_flags); + discov_changed = test_and_clear_bit(HCI_DISCOVERABLE, + &hdev->dev_flags); + } send_settings_rsp(cmd->sk, MGMT_OP_SET_CONNECTABLE, hdev); - if (changed) + if (conn_changed || discov_changed) { new_settings(hdev, cmd->sk); + if (discov_changed) + mgmt_update_adv_data(hdev); + hci_update_background_scan(hdev); + } remove_cmd: mgmt_pending_remove(cmd); @@ -1607,8 +1817,10 @@ static int set_connectable_update_settings(struct hci_dev *hdev, if (err < 0) return err; - if (changed) + if (changed) { + hci_update_background_scan(hdev); return new_settings(hdev, sk); + } return 0; } @@ -1669,7 +1881,18 @@ static int set_connectable(struct sock *sk, struct hci_dev *hdev, void *data, if (cp->val) { scan = SCAN_PAGE; } else { - scan = 0; + /* If we don't have any whitelist entries just + * disable all scanning. If there are entries + * and we had both page and inquiry scanning + * enabled then fall back to only page scanning. + * Otherwise no changes are needed. + */ + if (list_empty(&hdev->whitelist)) + scan = SCAN_DISABLED; + else if (test_bit(HCI_ISCAN, &hdev->flags)) + scan = SCAN_PAGE; + else + goto no_scan_update; if (test_bit(HCI_ISCAN, &hdev->flags) && hdev->discov_timeout > 0) @@ -1679,6 +1902,7 @@ static int set_connectable(struct sock *sk, struct hci_dev *hdev, void *data, hci_req_add(&req, HCI_OP_WRITE_SCAN_ENABLE, 1, &scan); } +no_scan_update: /* If we're going from non-connectable to connectable or * vice-versa when fast connectable is enabled ensure that fast * connectable gets disabled. write_fast_connectable won't do @@ -1688,11 +1912,9 @@ static int set_connectable(struct sock *sk, struct hci_dev *hdev, void *data, if (cp->val || test_bit(HCI_FAST_CONNECTABLE, &hdev->dev_flags)) write_fast_connectable(&req, false); - if (test_bit(HCI_ADVERTISING, &hdev->dev_flags) && - hci_conn_num(hdev, LE_LINK) == 0) { - disable_advertising(&req); + /* Update the advertising parameters if necessary */ + if (test_bit(HCI_ADVERTISING, &hdev->dev_flags)) enable_advertising(&req); - } err = hci_req_run(&req, set_connectable_complete); if (err < 0) { @@ -1708,7 +1930,7 @@ failed: return err; } -static int set_pairable(struct sock *sk, struct hci_dev *hdev, void *data, +static int set_bondable(struct sock *sk, struct hci_dev *hdev, void *data, u16 len) { struct mgmt_mode *cp = data; @@ -1718,17 +1940,17 @@ static int set_pairable(struct sock *sk, struct hci_dev *hdev, void *data, BT_DBG("request for %s", hdev->name); if (cp->val != 0x00 && cp->val != 0x01) - return cmd_status(sk, hdev->id, MGMT_OP_SET_PAIRABLE, + return cmd_status(sk, hdev->id, MGMT_OP_SET_BONDABLE, MGMT_STATUS_INVALID_PARAMS); hci_dev_lock(hdev); if (cp->val) - changed = !test_and_set_bit(HCI_PAIRABLE, &hdev->dev_flags); + changed = !test_and_set_bit(HCI_BONDABLE, &hdev->dev_flags); else - changed = test_and_clear_bit(HCI_PAIRABLE, &hdev->dev_flags); + changed = test_and_clear_bit(HCI_BONDABLE, &hdev->dev_flags); - err = send_settings_rsp(sk, MGMT_OP_SET_PAIRABLE, hdev); + err = send_settings_rsp(sk, MGMT_OP_SET_BONDABLE, hdev); if (err < 0) goto unlock; @@ -1877,6 +2099,10 @@ static int set_ssp(struct sock *sk, struct hci_dev *hdev, void *data, u16 len) goto failed; } + if (!cp->val && test_bit(HCI_USE_DEBUG_KEYS, &hdev->dev_flags)) + hci_send_cmd(hdev, HCI_OP_WRITE_SSP_DEBUG_MODE, + sizeof(cp->val), &cp->val); + err = hci_send_cmd(hdev, HCI_OP_WRITE_SSP_MODE, 1, &cp->val); if (err < 0) { mgmt_pending_remove(cmd); @@ -1973,6 +2199,8 @@ static void le_enable_complete(struct hci_dev *hdev, u8 status) update_scan_rsp_data(&req); hci_req_run(&req, NULL); + hci_update_background_scan(hdev); + hci_dev_unlock(hdev); } } @@ -2048,9 +2276,9 @@ static int set_le(struct sock *sk, struct hci_dev *hdev, void *data, u16 len) if (val) { hci_cp.le = val; - hci_cp.simul = lmp_le_br_capable(hdev); + hci_cp.simul = 0x00; } else { - if (test_bit(HCI_ADVERTISING, &hdev->dev_flags)) + if (test_bit(HCI_LE_ADV, &hdev->dev_flags)) disable_advertising(&req); } @@ -2373,6 +2601,8 @@ static int load_link_keys(struct sock *sk, struct hci_dev *hdev, void *data, u16 len) { struct mgmt_cp_load_link_keys *cp = data; + const u16 max_key_count = ((U16_MAX - sizeof(*cp)) / + sizeof(struct mgmt_link_key_info)); u16 key_count, expected_len; bool changed; int i; @@ -2384,6 +2614,12 @@ static int load_link_keys(struct sock *sk, struct hci_dev *hdev, void *data, MGMT_STATUS_NOT_SUPPORTED); key_count = __le16_to_cpu(cp->key_count); + if (key_count > max_key_count) { + BT_ERR("load_link_keys: too big key_count value %u", + key_count); + return cmd_status(sk, hdev->id, MGMT_OP_LOAD_LINK_KEYS, + MGMT_STATUS_INVALID_PARAMS); + } expected_len = sizeof(*cp) + key_count * sizeof(struct mgmt_link_key_info); @@ -2414,9 +2650,11 @@ static int load_link_keys(struct sock *sk, struct hci_dev *hdev, void *data, hci_link_keys_clear(hdev); if (cp->debug_keys) - changed = !test_and_set_bit(HCI_DEBUG_KEYS, &hdev->dev_flags); + changed = !test_and_set_bit(HCI_KEEP_DEBUG_KEYS, + &hdev->dev_flags); else - changed = test_and_clear_bit(HCI_DEBUG_KEYS, &hdev->dev_flags); + changed = test_and_clear_bit(HCI_KEEP_DEBUG_KEYS, + &hdev->dev_flags); if (changed) new_settings(hdev, NULL); @@ -2424,8 +2662,14 @@ static int load_link_keys(struct sock *sk, struct hci_dev *hdev, void *data, for (i = 0; i < key_count; i++) { struct mgmt_link_key_info *key = &cp->keys[i]; - hci_add_link_key(hdev, NULL, 0, &key->addr.bdaddr, key->val, - key->type, key->pin_len); + /* Always ignore debug keys and require a new pairing if + * the user wants to use them. + */ + if (key->type == HCI_LK_DEBUG_COMBINATION) + continue; + + hci_add_link_key(hdev, NULL, &key->addr.bdaddr, key->val, + key->type, key->pin_len, NULL); } cmd_complete(sk, hdev->id, MGMT_OP_LOAD_LINK_KEYS, 0, NULL, 0); @@ -2766,6 +3010,10 @@ static int set_io_capability(struct sock *sk, struct hci_dev *hdev, void *data, BT_DBG(""); + if (cp->io_capability > SMP_IO_KEYBOARD_DISPLAY) + return cmd_complete(sk, hdev->id, MGMT_OP_SET_IO_CAPABILITY, + MGMT_STATUS_INVALID_PARAMS, NULL, 0); + hci_dev_lock(hdev); hdev->io_capability = cp->io_capability; @@ -2878,6 +3126,11 @@ static int pair_device(struct sock *sk, struct hci_dev *hdev, void *data, MGMT_STATUS_INVALID_PARAMS, &rp, sizeof(rp)); + if (cp->io_cap > SMP_IO_KEYBOARD_DISPLAY) + return cmd_complete(sk, hdev->id, MGMT_OP_PAIR_DEVICE, + MGMT_STATUS_INVALID_PARAMS, + &rp, sizeof(rp)); + hci_dev_lock(hdev); if (!hdev_is_powered(hdev)) { @@ -2902,8 +3155,20 @@ static int pair_device(struct sock *sk, struct hci_dev *hdev, void *data, else addr_type = ADDR_LE_DEV_RANDOM; + /* When pairing a new device, it is expected to remember + * this device for future connections. Adding the connection + * parameter information ahead of time allows tracking + * of the slave preferred values and will speed up any + * further connection establishment. + * + * If connection parameters already exist, then they + * will be kept and this function does nothing. + */ + hci_conn_params_add(hdev, &cp->addr.bdaddr, addr_type); + conn = hci_connect_le(hdev, &cp->addr.bdaddr, addr_type, - sec_level, auth_type); + sec_level, HCI_LE_CONN_TIMEOUT, + HCI_ROLE_MASTER); } if (IS_ERR(conn)) { @@ -2948,8 +3213,8 @@ static int pair_device(struct sock *sk, struct hci_dev *hdev, void *data, conn->io_capability = cp->io_cap; cmd->user_data = conn; - if (conn->state == BT_CONNECTED && - hci_conn_security(conn, sec_level, auth_type)) + if ((conn->state == BT_CONNECTED || conn->state == BT_CONFIG) && + hci_conn_security(conn, sec_level, auth_type, true)) pairing_complete(cmd, 0); err = 0; @@ -3031,14 +3296,7 @@ static int user_pairing_resp(struct sock *sk, struct hci_dev *hdev, } if (addr->type == BDADDR_LE_PUBLIC || addr->type == BDADDR_LE_RANDOM) { - /* Continue with pairing via SMP. The hdev lock must be - * released as SMP may try to recquire it for crypto - * purposes. - */ - hci_dev_unlock(hdev); err = smp_user_confirm_reply(conn, mgmt_op, passkey); - hci_dev_lock(hdev); - if (!err) err = cmd_complete(sk, hdev->id, mgmt_op, MGMT_STATUS_SUCCESS, addr, @@ -3516,11 +3774,21 @@ static int start_discovery(struct sock *sk, struct hci_dev *hdev, goto failed; } - if (test_bit(HCI_ADVERTISING, &hdev->dev_flags)) { - err = cmd_status(sk, hdev->id, MGMT_OP_START_DISCOVERY, - MGMT_STATUS_REJECTED); - mgmt_pending_remove(cmd); - goto failed; + if (test_bit(HCI_LE_ADV, &hdev->dev_flags)) { + /* Don't let discovery abort an outgoing + * connection attempt that's using directed + * advertising. + */ + if (hci_conn_hash_lookup_state(hdev, LE_LINK, + BT_CONNECT)) { + err = cmd_status(sk, hdev->id, + MGMT_OP_START_DISCOVERY, + MGMT_STATUS_REJECTED); + mgmt_pending_remove(cmd); + goto failed; + } + + disable_advertising(&req); } /* If controller is scanning, it means the background scanning @@ -3723,12 +3991,18 @@ static int block_device(struct sock *sk, struct hci_dev *hdev, void *data, hci_dev_lock(hdev); - err = hci_blacklist_add(hdev, &cp->addr.bdaddr, cp->addr.type); - if (err < 0) + err = hci_bdaddr_list_add(&hdev->blacklist, &cp->addr.bdaddr, + cp->addr.type); + if (err < 0) { status = MGMT_STATUS_FAILED; - else - status = MGMT_STATUS_SUCCESS; + goto done; + } + + mgmt_event(MGMT_EV_DEVICE_BLOCKED, hdev, &cp->addr, sizeof(cp->addr), + sk); + status = MGMT_STATUS_SUCCESS; +done: err = cmd_complete(sk, hdev->id, MGMT_OP_BLOCK_DEVICE, status, &cp->addr, sizeof(cp->addr)); @@ -3753,12 +4027,18 @@ static int unblock_device(struct sock *sk, struct hci_dev *hdev, void *data, hci_dev_lock(hdev); - err = hci_blacklist_del(hdev, &cp->addr.bdaddr, cp->addr.type); - if (err < 0) + err = hci_bdaddr_list_del(&hdev->blacklist, &cp->addr.bdaddr, + cp->addr.type); + if (err < 0) { status = MGMT_STATUS_INVALID_PARAMS; - else - status = MGMT_STATUS_SUCCESS; + goto done; + } + + mgmt_event(MGMT_EV_DEVICE_UNBLOCKED, hdev, &cp->addr, sizeof(cp->addr), + sk); + status = MGMT_STATUS_SUCCESS; +done: err = cmd_complete(sk, hdev->id, MGMT_OP_UNBLOCK_DEVICE, status, &cp->addr, sizeof(cp->addr)); @@ -3813,6 +4093,11 @@ static void set_advertising_complete(struct hci_dev *hdev, u8 status) return; } + if (test_bit(HCI_LE_ADV, &hdev->dev_flags)) + set_bit(HCI_ADVERTISING, &hdev->dev_flags); + else + clear_bit(HCI_ADVERTISING, &hdev->dev_flags); + mgmt_pending_foreach(MGMT_OP_SET_ADVERTISING, hdev, settings_rsp, &match); @@ -3853,7 +4138,9 @@ static int set_advertising(struct sock *sk, struct hci_dev *hdev, void *data, * necessary). */ if (!hdev_is_powered(hdev) || val == enabled || - hci_conn_num(hdev, LE_LINK) > 0) { + hci_conn_num(hdev, LE_LINK) > 0 || + (test_bit(HCI_LE_SCAN, &hdev->dev_flags) && + hdev->le_scan_type == LE_SCAN_ACTIVE)) { bool changed = false; if (val != test_bit(HCI_ADVERTISING, &hdev->dev_flags)) { @@ -4105,7 +4392,8 @@ static void set_bredr_scan(struct hci_request *req) */ write_fast_connectable(req, false); - if (test_bit(HCI_CONNECTABLE, &hdev->dev_flags)) + if (test_bit(HCI_CONNECTABLE, &hdev->dev_flags) || + !list_empty(&hdev->whitelist)) scan |= SCAN_PAGE; if (test_bit(HCI_DISCOVERABLE, &hdev->dev_flags)) scan |= SCAN_INQUIRY; @@ -4219,7 +4507,8 @@ static int set_bredr(struct sock *sk, struct hci_dev *hdev, void *data, u16 len) hci_req_init(&req, hdev); - if (test_bit(HCI_CONNECTABLE, &hdev->dev_flags)) + if (test_bit(HCI_CONNECTABLE, &hdev->dev_flags) || + !list_empty(&hdev->whitelist)) set_bredr_scan(&req); /* Since only the advertising data flags will change, there @@ -4252,7 +4541,7 @@ static int set_secure_conn(struct sock *sk, struct hci_dev *hdev, status); if (!lmp_sc_capable(hdev) && - !test_bit(HCI_FORCE_SC, &hdev->dev_flags)) + !test_bit(HCI_FORCE_SC, &hdev->dbg_flags)) return cmd_status(sk, hdev->id, MGMT_OP_SET_SECURE_CONN, MGMT_STATUS_NOT_SUPPORTED); @@ -4328,21 +4617,37 @@ static int set_debug_keys(struct sock *sk, struct hci_dev *hdev, void *data, u16 len) { struct mgmt_mode *cp = data; - bool changed; + bool changed, use_changed; int err; BT_DBG("request for %s", hdev->name); - if (cp->val != 0x00 && cp->val != 0x01) + if (cp->val != 0x00 && cp->val != 0x01 && cp->val != 0x02) return cmd_status(sk, hdev->id, MGMT_OP_SET_DEBUG_KEYS, MGMT_STATUS_INVALID_PARAMS); hci_dev_lock(hdev); if (cp->val) - changed = !test_and_set_bit(HCI_DEBUG_KEYS, &hdev->dev_flags); + changed = !test_and_set_bit(HCI_KEEP_DEBUG_KEYS, + &hdev->dev_flags); + else + changed = test_and_clear_bit(HCI_KEEP_DEBUG_KEYS, + &hdev->dev_flags); + + if (cp->val == 0x02) + use_changed = !test_and_set_bit(HCI_USE_DEBUG_KEYS, + &hdev->dev_flags); else - changed = test_and_clear_bit(HCI_DEBUG_KEYS, &hdev->dev_flags); + use_changed = test_and_clear_bit(HCI_USE_DEBUG_KEYS, + &hdev->dev_flags); + + if (hdev_is_powered(hdev) && use_changed && + test_bit(HCI_SSP_ENABLED, &hdev->dev_flags)) { + u8 mode = (cp->val == 0x02) ? 0x01 : 0x00; + hci_send_cmd(hdev, HCI_OP_WRITE_SSP_DEBUG_MODE, + sizeof(mode), &mode); + } err = send_settings_rsp(sk, MGMT_OP_SET_DEBUG_KEYS, hdev); if (err < 0) @@ -4426,6 +4731,8 @@ static int load_irks(struct sock *sk, struct hci_dev *hdev, void *cp_data, u16 len) { struct mgmt_cp_load_irks *cp = cp_data; + const u16 max_irk_count = ((U16_MAX - sizeof(*cp)) / + sizeof(struct mgmt_irk_info)); u16 irk_count, expected_len; int i, err; @@ -4436,6 +4743,11 @@ static int load_irks(struct sock *sk, struct hci_dev *hdev, void *cp_data, MGMT_STATUS_NOT_SUPPORTED); irk_count = __le16_to_cpu(cp->irk_count); + if (irk_count > max_irk_count) { + BT_ERR("load_irks: too big irk_count value %u", irk_count); + return cmd_status(sk, hdev->id, MGMT_OP_LOAD_IRKS, + MGMT_STATUS_INVALID_PARAMS); + } expected_len = sizeof(*cp) + irk_count * sizeof(struct mgmt_irk_info); if (expected_len != len) { @@ -4505,6 +4817,8 @@ static int load_long_term_keys(struct sock *sk, struct hci_dev *hdev, void *cp_data, u16 len) { struct mgmt_cp_load_long_term_keys *cp = cp_data; + const u16 max_key_count = ((U16_MAX - sizeof(*cp)) / + sizeof(struct mgmt_ltk_info)); u16 key_count, expected_len; int i, err; @@ -4515,6 +4829,11 @@ static int load_long_term_keys(struct sock *sk, struct hci_dev *hdev, MGMT_STATUS_NOT_SUPPORTED); key_count = __le16_to_cpu(cp->key_count); + if (key_count > max_key_count) { + BT_ERR("load_ltks: too big key_count value %u", key_count); + return cmd_status(sk, hdev->id, MGMT_OP_LOAD_LONG_TERM_KEYS, + MGMT_STATUS_INVALID_PARAMS); + } expected_len = sizeof(*cp) + key_count * sizeof(struct mgmt_ltk_info); @@ -4550,9 +4869,9 @@ static int load_long_term_keys(struct sock *sk, struct hci_dev *hdev, addr_type = ADDR_LE_DEV_RANDOM; if (key->master) - type = HCI_SMP_LTK; + type = SMP_LTK; else - type = HCI_SMP_LTK_SLAVE; + type = SMP_LTK_SLAVE; switch (key->type) { case MGMT_LTK_UNAUTHENTICATED: @@ -4790,6 +5109,561 @@ unlock: return err; } +static void get_clock_info_complete(struct hci_dev *hdev, u8 status) +{ + struct mgmt_cp_get_clock_info *cp; + struct mgmt_rp_get_clock_info rp; + struct hci_cp_read_clock *hci_cp; + struct pending_cmd *cmd; + struct hci_conn *conn; + + BT_DBG("%s status %u", hdev->name, status); + + hci_dev_lock(hdev); + + hci_cp = hci_sent_cmd_data(hdev, HCI_OP_READ_CLOCK); + if (!hci_cp) + goto unlock; + + if (hci_cp->which) { + u16 handle = __le16_to_cpu(hci_cp->handle); + conn = hci_conn_hash_lookup_handle(hdev, handle); + } else { + conn = NULL; + } + + cmd = mgmt_pending_find_data(MGMT_OP_GET_CLOCK_INFO, hdev, conn); + if (!cmd) + goto unlock; + + cp = cmd->param; + + memset(&rp, 0, sizeof(rp)); + memcpy(&rp.addr, &cp->addr, sizeof(rp.addr)); + + if (status) + goto send_rsp; + + rp.local_clock = cpu_to_le32(hdev->clock); + + if (conn) { + rp.piconet_clock = cpu_to_le32(conn->clock); + rp.accuracy = cpu_to_le16(conn->clock_accuracy); + } + +send_rsp: + cmd_complete(cmd->sk, cmd->index, cmd->opcode, mgmt_status(status), + &rp, sizeof(rp)); + mgmt_pending_remove(cmd); + if (conn) + hci_conn_drop(conn); + +unlock: + hci_dev_unlock(hdev); +} + +static int get_clock_info(struct sock *sk, struct hci_dev *hdev, void *data, + u16 len) +{ + struct mgmt_cp_get_clock_info *cp = data; + struct mgmt_rp_get_clock_info rp; + struct hci_cp_read_clock hci_cp; + struct pending_cmd *cmd; + struct hci_request req; + struct hci_conn *conn; + int err; + + BT_DBG("%s", hdev->name); + + memset(&rp, 0, sizeof(rp)); + bacpy(&rp.addr.bdaddr, &cp->addr.bdaddr); + rp.addr.type = cp->addr.type; + + if (cp->addr.type != BDADDR_BREDR) + return cmd_complete(sk, hdev->id, MGMT_OP_GET_CLOCK_INFO, + MGMT_STATUS_INVALID_PARAMS, + &rp, sizeof(rp)); + + hci_dev_lock(hdev); + + if (!hdev_is_powered(hdev)) { + err = cmd_complete(sk, hdev->id, MGMT_OP_GET_CLOCK_INFO, + MGMT_STATUS_NOT_POWERED, &rp, sizeof(rp)); + goto unlock; + } + + if (bacmp(&cp->addr.bdaddr, BDADDR_ANY)) { + conn = hci_conn_hash_lookup_ba(hdev, ACL_LINK, + &cp->addr.bdaddr); + if (!conn || conn->state != BT_CONNECTED) { + err = cmd_complete(sk, hdev->id, + MGMT_OP_GET_CLOCK_INFO, + MGMT_STATUS_NOT_CONNECTED, + &rp, sizeof(rp)); + goto unlock; + } + } else { + conn = NULL; + } + + cmd = mgmt_pending_add(sk, MGMT_OP_GET_CLOCK_INFO, hdev, data, len); + if (!cmd) { + err = -ENOMEM; + goto unlock; + } + + hci_req_init(&req, hdev); + + memset(&hci_cp, 0, sizeof(hci_cp)); + hci_req_add(&req, HCI_OP_READ_CLOCK, sizeof(hci_cp), &hci_cp); + + if (conn) { + hci_conn_hold(conn); + cmd->user_data = conn; + + hci_cp.handle = cpu_to_le16(conn->handle); + hci_cp.which = 0x01; /* Piconet clock */ + hci_req_add(&req, HCI_OP_READ_CLOCK, sizeof(hci_cp), &hci_cp); + } + + err = hci_req_run(&req, get_clock_info_complete); + if (err < 0) + mgmt_pending_remove(cmd); + +unlock: + hci_dev_unlock(hdev); + return err; +} + +/* Helper for Add/Remove Device commands */ +static void update_page_scan(struct hci_dev *hdev, u8 scan) +{ + if (!test_bit(HCI_BREDR_ENABLED, &hdev->dev_flags)) + return; + + if (!hdev_is_powered(hdev)) + return; + + /* If HCI_CONNECTABLE is set then Add/Remove Device should not + * make any changes to page scanning. + */ + if (test_bit(HCI_CONNECTABLE, &hdev->dev_flags)) + return; + + if (test_bit(HCI_DISCOVERABLE, &hdev->dev_flags)) + scan |= SCAN_INQUIRY; + + hci_send_cmd(hdev, HCI_OP_WRITE_SCAN_ENABLE, 1, &scan); +} + +static void device_added(struct sock *sk, struct hci_dev *hdev, + bdaddr_t *bdaddr, u8 type, u8 action) +{ + struct mgmt_ev_device_added ev; + + bacpy(&ev.addr.bdaddr, bdaddr); + ev.addr.type = type; + ev.action = action; + + mgmt_event(MGMT_EV_DEVICE_ADDED, hdev, &ev, sizeof(ev), sk); +} + +static int add_device(struct sock *sk, struct hci_dev *hdev, + void *data, u16 len) +{ + struct mgmt_cp_add_device *cp = data; + u8 auto_conn, addr_type; + int err; + + BT_DBG("%s", hdev->name); + + if (!bdaddr_type_is_valid(cp->addr.type) || + !bacmp(&cp->addr.bdaddr, BDADDR_ANY)) + return cmd_complete(sk, hdev->id, MGMT_OP_ADD_DEVICE, + MGMT_STATUS_INVALID_PARAMS, + &cp->addr, sizeof(cp->addr)); + + if (cp->action != 0x00 && cp->action != 0x01 && cp->action != 0x02) + return cmd_complete(sk, hdev->id, MGMT_OP_ADD_DEVICE, + MGMT_STATUS_INVALID_PARAMS, + &cp->addr, sizeof(cp->addr)); + + hci_dev_lock(hdev); + + if (cp->addr.type == BDADDR_BREDR) { + bool update_scan; + + /* Only incoming connections action is supported for now */ + if (cp->action != 0x01) { + err = cmd_complete(sk, hdev->id, MGMT_OP_ADD_DEVICE, + MGMT_STATUS_INVALID_PARAMS, + &cp->addr, sizeof(cp->addr)); + goto unlock; + } + + update_scan = list_empty(&hdev->whitelist); + + err = hci_bdaddr_list_add(&hdev->whitelist, &cp->addr.bdaddr, + cp->addr.type); + if (err) + goto unlock; + + if (update_scan) + update_page_scan(hdev, SCAN_PAGE); + + goto added; + } + + if (cp->addr.type == BDADDR_LE_PUBLIC) + addr_type = ADDR_LE_DEV_PUBLIC; + else + addr_type = ADDR_LE_DEV_RANDOM; + + if (cp->action == 0x02) + auto_conn = HCI_AUTO_CONN_ALWAYS; + else if (cp->action == 0x01) + auto_conn = HCI_AUTO_CONN_DIRECT; + else + auto_conn = HCI_AUTO_CONN_REPORT; + + /* If the connection parameters don't exist for this device, + * they will be created and configured with defaults. + */ + if (hci_conn_params_set(hdev, &cp->addr.bdaddr, addr_type, + auto_conn) < 0) { + err = cmd_complete(sk, hdev->id, MGMT_OP_ADD_DEVICE, + MGMT_STATUS_FAILED, + &cp->addr, sizeof(cp->addr)); + goto unlock; + } + +added: + device_added(sk, hdev, &cp->addr.bdaddr, cp->addr.type, cp->action); + + err = cmd_complete(sk, hdev->id, MGMT_OP_ADD_DEVICE, + MGMT_STATUS_SUCCESS, &cp->addr, sizeof(cp->addr)); + +unlock: + hci_dev_unlock(hdev); + return err; +} + +static void device_removed(struct sock *sk, struct hci_dev *hdev, + bdaddr_t *bdaddr, u8 type) +{ + struct mgmt_ev_device_removed ev; + + bacpy(&ev.addr.bdaddr, bdaddr); + ev.addr.type = type; + + mgmt_event(MGMT_EV_DEVICE_REMOVED, hdev, &ev, sizeof(ev), sk); +} + +static int remove_device(struct sock *sk, struct hci_dev *hdev, + void *data, u16 len) +{ + struct mgmt_cp_remove_device *cp = data; + int err; + + BT_DBG("%s", hdev->name); + + hci_dev_lock(hdev); + + if (bacmp(&cp->addr.bdaddr, BDADDR_ANY)) { + struct hci_conn_params *params; + u8 addr_type; + + if (!bdaddr_type_is_valid(cp->addr.type)) { + err = cmd_complete(sk, hdev->id, MGMT_OP_REMOVE_DEVICE, + MGMT_STATUS_INVALID_PARAMS, + &cp->addr, sizeof(cp->addr)); + goto unlock; + } + + if (cp->addr.type == BDADDR_BREDR) { + err = hci_bdaddr_list_del(&hdev->whitelist, + &cp->addr.bdaddr, + cp->addr.type); + if (err) { + err = cmd_complete(sk, hdev->id, + MGMT_OP_REMOVE_DEVICE, + MGMT_STATUS_INVALID_PARAMS, + &cp->addr, sizeof(cp->addr)); + goto unlock; + } + + if (list_empty(&hdev->whitelist)) + update_page_scan(hdev, SCAN_DISABLED); + + device_removed(sk, hdev, &cp->addr.bdaddr, + cp->addr.type); + goto complete; + } + + if (cp->addr.type == BDADDR_LE_PUBLIC) + addr_type = ADDR_LE_DEV_PUBLIC; + else + addr_type = ADDR_LE_DEV_RANDOM; + + params = hci_conn_params_lookup(hdev, &cp->addr.bdaddr, + addr_type); + if (!params) { + err = cmd_complete(sk, hdev->id, MGMT_OP_REMOVE_DEVICE, + MGMT_STATUS_INVALID_PARAMS, + &cp->addr, sizeof(cp->addr)); + goto unlock; + } + + if (params->auto_connect == HCI_AUTO_CONN_DISABLED) { + err = cmd_complete(sk, hdev->id, MGMT_OP_REMOVE_DEVICE, + MGMT_STATUS_INVALID_PARAMS, + &cp->addr, sizeof(cp->addr)); + goto unlock; + } + + list_del(¶ms->action); + list_del(¶ms->list); + kfree(params); + hci_update_background_scan(hdev); + + device_removed(sk, hdev, &cp->addr.bdaddr, cp->addr.type); + } else { + struct hci_conn_params *p, *tmp; + struct bdaddr_list *b, *btmp; + + if (cp->addr.type) { + err = cmd_complete(sk, hdev->id, MGMT_OP_REMOVE_DEVICE, + MGMT_STATUS_INVALID_PARAMS, + &cp->addr, sizeof(cp->addr)); + goto unlock; + } + + list_for_each_entry_safe(b, btmp, &hdev->whitelist, list) { + device_removed(sk, hdev, &b->bdaddr, b->bdaddr_type); + list_del(&b->list); + kfree(b); + } + + update_page_scan(hdev, SCAN_DISABLED); + + list_for_each_entry_safe(p, tmp, &hdev->le_conn_params, list) { + if (p->auto_connect == HCI_AUTO_CONN_DISABLED) + continue; + device_removed(sk, hdev, &p->addr, p->addr_type); + list_del(&p->action); + list_del(&p->list); + kfree(p); + } + + BT_DBG("All LE connection parameters were removed"); + + hci_update_background_scan(hdev); + } + +complete: + err = cmd_complete(sk, hdev->id, MGMT_OP_REMOVE_DEVICE, + MGMT_STATUS_SUCCESS, &cp->addr, sizeof(cp->addr)); + +unlock: + hci_dev_unlock(hdev); + return err; +} + +static int load_conn_param(struct sock *sk, struct hci_dev *hdev, void *data, + u16 len) +{ + struct mgmt_cp_load_conn_param *cp = data; + const u16 max_param_count = ((U16_MAX - sizeof(*cp)) / + sizeof(struct mgmt_conn_param)); + u16 param_count, expected_len; + int i; + + if (!lmp_le_capable(hdev)) + return cmd_status(sk, hdev->id, MGMT_OP_LOAD_CONN_PARAM, + MGMT_STATUS_NOT_SUPPORTED); + + param_count = __le16_to_cpu(cp->param_count); + if (param_count > max_param_count) { + BT_ERR("load_conn_param: too big param_count value %u", + param_count); + return cmd_status(sk, hdev->id, MGMT_OP_LOAD_CONN_PARAM, + MGMT_STATUS_INVALID_PARAMS); + } + + expected_len = sizeof(*cp) + param_count * + sizeof(struct mgmt_conn_param); + if (expected_len != len) { + BT_ERR("load_conn_param: expected %u bytes, got %u bytes", + expected_len, len); + return cmd_status(sk, hdev->id, MGMT_OP_LOAD_CONN_PARAM, + MGMT_STATUS_INVALID_PARAMS); + } + + BT_DBG("%s param_count %u", hdev->name, param_count); + + hci_dev_lock(hdev); + + hci_conn_params_clear_disabled(hdev); + + for (i = 0; i < param_count; i++) { + struct mgmt_conn_param *param = &cp->params[i]; + struct hci_conn_params *hci_param; + u16 min, max, latency, timeout; + u8 addr_type; + + BT_DBG("Adding %pMR (type %u)", ¶m->addr.bdaddr, + param->addr.type); + + if (param->addr.type == BDADDR_LE_PUBLIC) { + addr_type = ADDR_LE_DEV_PUBLIC; + } else if (param->addr.type == BDADDR_LE_RANDOM) { + addr_type = ADDR_LE_DEV_RANDOM; + } else { + BT_ERR("Ignoring invalid connection parameters"); + continue; + } + + min = le16_to_cpu(param->min_interval); + max = le16_to_cpu(param->max_interval); + latency = le16_to_cpu(param->latency); + timeout = le16_to_cpu(param->timeout); + + BT_DBG("min 0x%04x max 0x%04x latency 0x%04x timeout 0x%04x", + min, max, latency, timeout); + + if (hci_check_conn_params(min, max, latency, timeout) < 0) { + BT_ERR("Ignoring invalid connection parameters"); + continue; + } + + hci_param = hci_conn_params_add(hdev, ¶m->addr.bdaddr, + addr_type); + if (!hci_param) { + BT_ERR("Failed to add connection parameters"); + continue; + } + + hci_param->conn_min_interval = min; + hci_param->conn_max_interval = max; + hci_param->conn_latency = latency; + hci_param->supervision_timeout = timeout; + } + + hci_dev_unlock(hdev); + + return cmd_complete(sk, hdev->id, MGMT_OP_LOAD_CONN_PARAM, 0, NULL, 0); +} + +static int set_external_config(struct sock *sk, struct hci_dev *hdev, + void *data, u16 len) +{ + struct mgmt_cp_set_external_config *cp = data; + bool changed; + int err; + + BT_DBG("%s", hdev->name); + + if (hdev_is_powered(hdev)) + return cmd_status(sk, hdev->id, MGMT_OP_SET_EXTERNAL_CONFIG, + MGMT_STATUS_REJECTED); + + if (cp->config != 0x00 && cp->config != 0x01) + return cmd_status(sk, hdev->id, MGMT_OP_SET_EXTERNAL_CONFIG, + MGMT_STATUS_INVALID_PARAMS); + + if (!test_bit(HCI_QUIRK_EXTERNAL_CONFIG, &hdev->quirks)) + return cmd_status(sk, hdev->id, MGMT_OP_SET_EXTERNAL_CONFIG, + MGMT_STATUS_NOT_SUPPORTED); + + hci_dev_lock(hdev); + + if (cp->config) + changed = !test_and_set_bit(HCI_EXT_CONFIGURED, + &hdev->dev_flags); + else + changed = test_and_clear_bit(HCI_EXT_CONFIGURED, + &hdev->dev_flags); + + err = send_options_rsp(sk, MGMT_OP_SET_EXTERNAL_CONFIG, hdev); + if (err < 0) + goto unlock; + + if (!changed) + goto unlock; + + err = new_options(hdev, sk); + + if (test_bit(HCI_UNCONFIGURED, &hdev->dev_flags) == is_configured(hdev)) { + mgmt_index_removed(hdev); + + if (test_and_change_bit(HCI_UNCONFIGURED, &hdev->dev_flags)) { + set_bit(HCI_CONFIG, &hdev->dev_flags); + set_bit(HCI_AUTO_OFF, &hdev->dev_flags); + + queue_work(hdev->req_workqueue, &hdev->power_on); + } else { + set_bit(HCI_RAW, &hdev->flags); + mgmt_index_added(hdev); + } + } + +unlock: + hci_dev_unlock(hdev); + return err; +} + +static int set_public_address(struct sock *sk, struct hci_dev *hdev, + void *data, u16 len) +{ + struct mgmt_cp_set_public_address *cp = data; + bool changed; + int err; + + BT_DBG("%s", hdev->name); + + if (hdev_is_powered(hdev)) + return cmd_status(sk, hdev->id, MGMT_OP_SET_PUBLIC_ADDRESS, + MGMT_STATUS_REJECTED); + + if (!bacmp(&cp->bdaddr, BDADDR_ANY)) + return cmd_status(sk, hdev->id, MGMT_OP_SET_PUBLIC_ADDRESS, + MGMT_STATUS_INVALID_PARAMS); + + if (!hdev->set_bdaddr) + return cmd_status(sk, hdev->id, MGMT_OP_SET_PUBLIC_ADDRESS, + MGMT_STATUS_NOT_SUPPORTED); + + hci_dev_lock(hdev); + + changed = !!bacmp(&hdev->public_addr, &cp->bdaddr); + bacpy(&hdev->public_addr, &cp->bdaddr); + + err = send_options_rsp(sk, MGMT_OP_SET_PUBLIC_ADDRESS, hdev); + if (err < 0) + goto unlock; + + if (!changed) + goto unlock; + + if (test_bit(HCI_UNCONFIGURED, &hdev->dev_flags)) + err = new_options(hdev, sk); + + if (is_configured(hdev)) { + mgmt_index_removed(hdev); + + clear_bit(HCI_UNCONFIGURED, &hdev->dev_flags); + + set_bit(HCI_CONFIG, &hdev->dev_flags); + set_bit(HCI_AUTO_OFF, &hdev->dev_flags); + + queue_work(hdev->req_workqueue, &hdev->power_on); + } + +unlock: + hci_dev_unlock(hdev); + return err; +} + static const struct mgmt_handler { int (*func) (struct sock *sk, struct hci_dev *hdev, void *data, u16 data_len); @@ -4805,7 +5679,7 @@ static const struct mgmt_handler { { set_discoverable, false, MGMT_SET_DISCOVERABLE_SIZE }, { set_connectable, false, MGMT_SETTING_SIZE }, { set_fast_connectable, false, MGMT_SETTING_SIZE }, - { set_pairable, false, MGMT_SETTING_SIZE }, + { set_bondable, false, MGMT_SETTING_SIZE }, { set_link_security, false, MGMT_SETTING_SIZE }, { set_ssp, false, MGMT_SETTING_SIZE }, { set_hs, false, MGMT_SETTING_SIZE }, @@ -4846,9 +5720,16 @@ static const struct mgmt_handler { { set_privacy, false, MGMT_SET_PRIVACY_SIZE }, { load_irks, true, MGMT_LOAD_IRKS_SIZE }, { get_conn_info, false, MGMT_GET_CONN_INFO_SIZE }, + { get_clock_info, false, MGMT_GET_CLOCK_INFO_SIZE }, + { add_device, false, MGMT_ADD_DEVICE_SIZE }, + { remove_device, false, MGMT_REMOVE_DEVICE_SIZE }, + { load_conn_param, true, MGMT_LOAD_CONN_PARAM_SIZE }, + { read_unconf_index_list, false, MGMT_READ_UNCONF_INDEX_LIST_SIZE }, + { read_config_info, false, MGMT_READ_CONFIG_INFO_SIZE }, + { set_external_config, false, MGMT_SET_EXTERNAL_CONFIG_SIZE }, + { set_public_address, false, MGMT_SET_PUBLIC_ADDRESS_SIZE }, }; - int mgmt_control(struct sock *sk, struct msghdr *msg, size_t msglen) { void *buf; @@ -4892,11 +5773,21 @@ int mgmt_control(struct sock *sk, struct msghdr *msg, size_t msglen) } if (test_bit(HCI_SETUP, &hdev->dev_flags) || + test_bit(HCI_CONFIG, &hdev->dev_flags) || test_bit(HCI_USER_CHANNEL, &hdev->dev_flags)) { err = cmd_status(sk, index, opcode, MGMT_STATUS_INVALID_INDEX); goto done; } + + if (test_bit(HCI_UNCONFIGURED, &hdev->dev_flags) && + opcode != MGMT_OP_READ_CONFIG_INFO && + opcode != MGMT_OP_SET_EXTERNAL_CONFIG && + opcode != MGMT_OP_SET_PUBLIC_ADDRESS) { + err = cmd_status(sk, index, opcode, + MGMT_STATUS_INVALID_INDEX); + goto done; + } } if (opcode >= ARRAY_SIZE(mgmt_handlers) || @@ -4907,8 +5798,15 @@ int mgmt_control(struct sock *sk, struct msghdr *msg, size_t msglen) goto done; } - if ((hdev && opcode < MGMT_OP_READ_INFO) || - (!hdev && opcode >= MGMT_OP_READ_INFO)) { + if (hdev && (opcode <= MGMT_OP_READ_INDEX_LIST || + opcode == MGMT_OP_READ_UNCONF_INDEX_LIST)) { + err = cmd_status(sk, index, opcode, + MGMT_STATUS_INVALID_INDEX); + goto done; + } + + if (!hdev && (opcode > MGMT_OP_READ_INDEX_LIST && + opcode != MGMT_OP_READ_UNCONF_INDEX_LIST)) { err = cmd_status(sk, index, opcode, MGMT_STATUS_INVALID_INDEX); goto done; @@ -4947,7 +5845,13 @@ void mgmt_index_added(struct hci_dev *hdev) if (hdev->dev_type != HCI_BREDR) return; - mgmt_event(MGMT_EV_INDEX_ADDED, hdev, NULL, 0, NULL); + if (test_bit(HCI_QUIRK_RAW_DEVICE, &hdev->quirks)) + return; + + if (test_bit(HCI_UNCONFIGURED, &hdev->dev_flags)) + mgmt_event(MGMT_EV_UNCONF_INDEX_ADDED, hdev, NULL, 0, NULL); + else + mgmt_event(MGMT_EV_INDEX_ADDED, hdev, NULL, 0, NULL); } void mgmt_index_removed(struct hci_dev *hdev) @@ -4957,20 +5861,42 @@ void mgmt_index_removed(struct hci_dev *hdev) if (hdev->dev_type != HCI_BREDR) return; + if (test_bit(HCI_QUIRK_RAW_DEVICE, &hdev->quirks)) + return; + mgmt_pending_foreach(0, hdev, cmd_status_rsp, &status); - mgmt_event(MGMT_EV_INDEX_REMOVED, hdev, NULL, 0, NULL); + if (test_bit(HCI_UNCONFIGURED, &hdev->dev_flags)) + mgmt_event(MGMT_EV_UNCONF_INDEX_REMOVED, hdev, NULL, 0, NULL); + else + mgmt_event(MGMT_EV_INDEX_REMOVED, hdev, NULL, 0, NULL); } /* This function requires the caller holds hdev->lock */ -static void restart_le_auto_conns(struct hci_dev *hdev) +static void restart_le_actions(struct hci_dev *hdev) { struct hci_conn_params *p; list_for_each_entry(p, &hdev->le_conn_params, list) { - if (p->auto_connect == HCI_AUTO_CONN_ALWAYS) - hci_pend_le_conn_add(hdev, &p->addr, p->addr_type); + /* Needed for AUTO_OFF case where might not "really" + * have been powered off. + */ + list_del_init(&p->action); + + switch (p->auto_connect) { + case HCI_AUTO_CONN_DIRECT: + case HCI_AUTO_CONN_ALWAYS: + list_add(&p->action, &hdev->pend_le_conns); + break; + case HCI_AUTO_CONN_REPORT: + list_add(&p->action, &hdev->pend_le_reports); + break; + default: + break; + } } + + hci_update_background_scan(hdev); } static void powered_complete(struct hci_dev *hdev, u8 status) @@ -4981,7 +5907,7 @@ static void powered_complete(struct hci_dev *hdev, u8 status) hci_dev_lock(hdev); - restart_le_auto_conns(hdev); + restart_le_actions(hdev); mgmt_pending_foreach(MGMT_OP_SET_POWERED, hdev, settings_rsp, &match); @@ -5011,8 +5937,8 @@ static int powered_update_hci(struct hci_dev *hdev) lmp_bredr_capable(hdev)) { struct hci_cp_write_le_host_supported cp; - cp.le = 1; - cp.simul = lmp_le_br_capable(hdev); + cp.le = 0x01; + cp.simul = 0x00; /* Check first if we already have the right * host state (host features set) @@ -5138,92 +6064,6 @@ void mgmt_discoverable_timeout(struct hci_dev *hdev) hci_dev_unlock(hdev); } -void mgmt_discoverable(struct hci_dev *hdev, u8 discoverable) -{ - bool changed; - - /* Nothing needed here if there's a pending command since that - * commands request completion callback takes care of everything - * necessary. - */ - if (mgmt_pending_find(MGMT_OP_SET_DISCOVERABLE, hdev)) - return; - - /* Powering off may clear the scan mode - don't let that interfere */ - if (!discoverable && mgmt_pending_find(MGMT_OP_SET_POWERED, hdev)) - return; - - if (discoverable) { - changed = !test_and_set_bit(HCI_DISCOVERABLE, &hdev->dev_flags); - } else { - clear_bit(HCI_LIMITED_DISCOVERABLE, &hdev->dev_flags); - changed = test_and_clear_bit(HCI_DISCOVERABLE, &hdev->dev_flags); - } - - if (changed) { - struct hci_request req; - - /* In case this change in discoverable was triggered by - * a disabling of connectable there could be a need to - * update the advertising flags. - */ - hci_req_init(&req, hdev); - update_adv_data(&req); - hci_req_run(&req, NULL); - - new_settings(hdev, NULL); - } -} - -void mgmt_connectable(struct hci_dev *hdev, u8 connectable) -{ - bool changed; - - /* Nothing needed here if there's a pending command since that - * commands request completion callback takes care of everything - * necessary. - */ - if (mgmt_pending_find(MGMT_OP_SET_CONNECTABLE, hdev)) - return; - - /* Powering off may clear the scan mode - don't let that interfere */ - if (!connectable && mgmt_pending_find(MGMT_OP_SET_POWERED, hdev)) - return; - - if (connectable) - changed = !test_and_set_bit(HCI_CONNECTABLE, &hdev->dev_flags); - else - changed = test_and_clear_bit(HCI_CONNECTABLE, &hdev->dev_flags); - - if (changed) - new_settings(hdev, NULL); -} - -void mgmt_advertising(struct hci_dev *hdev, u8 advertising) -{ - /* Powering off may stop advertising - don't let that interfere */ - if (!advertising && mgmt_pending_find(MGMT_OP_SET_POWERED, hdev)) - return; - - if (advertising) - set_bit(HCI_ADVERTISING, &hdev->dev_flags); - else - clear_bit(HCI_ADVERTISING, &hdev->dev_flags); -} - -void mgmt_write_scan_failed(struct hci_dev *hdev, u8 scan, u8 status) -{ - u8 mgmt_err = mgmt_status(status); - - if (scan & SCAN_PAGE) - mgmt_pending_foreach(MGMT_OP_SET_CONNECTABLE, hdev, - cmd_status_rsp, &mgmt_err); - - if (scan & SCAN_INQUIRY) - mgmt_pending_foreach(MGMT_OP_SET_DISCOVERABLE, hdev, - cmd_status_rsp, &mgmt_err); -} - void mgmt_new_link_key(struct hci_dev *hdev, struct link_key *key, bool persistent) { @@ -5279,7 +6119,7 @@ void mgmt_new_ltk(struct hci_dev *hdev, struct smp_ltk *key, bool persistent) ev.key.ediv = key->ediv; ev.key.rand = key->rand; - if (key->type == HCI_SMP_LTK) + if (key->type == SMP_LTK) ev.key.master = 1; memcpy(ev.key.val, key->val, sizeof(key->val)); @@ -5347,6 +6187,27 @@ void mgmt_new_csrk(struct hci_dev *hdev, struct smp_csrk *csrk, mgmt_event(MGMT_EV_NEW_CSRK, hdev, &ev, sizeof(ev), NULL); } +void mgmt_new_conn_param(struct hci_dev *hdev, bdaddr_t *bdaddr, + u8 bdaddr_type, u8 store_hint, u16 min_interval, + u16 max_interval, u16 latency, u16 timeout) +{ + struct mgmt_ev_new_conn_param ev; + + if (!hci_is_identity_address(bdaddr, bdaddr_type)) + return; + + memset(&ev, 0, sizeof(ev)); + bacpy(&ev.addr.bdaddr, bdaddr); + ev.addr.type = link_to_bdaddr(LE_LINK, bdaddr_type); + ev.store_hint = store_hint; + ev.min_interval = cpu_to_le16(min_interval); + ev.max_interval = cpu_to_le16(max_interval); + ev.latency = cpu_to_le16(latency); + ev.timeout = cpu_to_le16(timeout); + + mgmt_event(MGMT_EV_NEW_CONN_PARAM, hdev, &ev, sizeof(ev), NULL); +} + static inline u16 eir_append_data(u8 *eir, u16 eir_len, u8 type, u8 *data, u8 data_len) { @@ -5765,10 +6626,14 @@ void mgmt_ssp_enable_complete(struct hci_dev *hdev, u8 enable, u8 status) hci_req_init(&req, hdev); - if (test_bit(HCI_SSP_ENABLED, &hdev->dev_flags)) + if (test_bit(HCI_SSP_ENABLED, &hdev->dev_flags)) { + if (test_bit(HCI_USE_DEBUG_KEYS, &hdev->dev_flags)) + hci_req_add(&req, HCI_OP_WRITE_SSP_DEBUG_MODE, + sizeof(enable), &enable); update_eir(&req); - else + } else { clear_eir(&req); + } hci_req_run(&req, NULL); } @@ -5912,17 +6777,23 @@ void mgmt_read_local_oob_data_complete(struct hci_dev *hdev, u8 *hash192, } void mgmt_device_found(struct hci_dev *hdev, bdaddr_t *bdaddr, u8 link_type, - u8 addr_type, u8 *dev_class, s8 rssi, u8 cfm_name, - u8 ssp, u8 *eir, u16 eir_len, u8 *scan_rsp, - u8 scan_rsp_len) + u8 addr_type, u8 *dev_class, s8 rssi, u32 flags, + u8 *eir, u16 eir_len, u8 *scan_rsp, u8 scan_rsp_len) { char buf[512]; struct mgmt_ev_device_found *ev = (void *) buf; - struct smp_irk *irk; size_t ev_size; - if (!hci_discovery_active(hdev)) - return; + /* Don't send events for a non-kernel initiated discovery. With + * LE one exception is if we have pend_le_reports > 0 in which + * case we're doing passive scanning and want these events. + */ + if (!hci_discovery_active(hdev)) { + if (link_type == ACL_LINK) + return; + if (link_type == LE_LINK && list_empty(&hdev->pend_le_reports)) + return; + } /* Make sure that the buffer is big enough. The 5 extra bytes * are for the potential CoD field. @@ -5932,20 +6803,10 @@ void mgmt_device_found(struct hci_dev *hdev, bdaddr_t *bdaddr, u8 link_type, memset(buf, 0, sizeof(buf)); - irk = hci_get_irk(hdev, bdaddr, addr_type); - if (irk) { - bacpy(&ev->addr.bdaddr, &irk->bdaddr); - ev->addr.type = link_to_bdaddr(link_type, irk->addr_type); - } else { - bacpy(&ev->addr.bdaddr, bdaddr); - ev->addr.type = link_to_bdaddr(link_type, addr_type); - } - + bacpy(&ev->addr.bdaddr, bdaddr); + ev->addr.type = link_to_bdaddr(link_type, addr_type); ev->rssi = rssi; - if (cfm_name) - ev->flags |= cpu_to_le32(MGMT_DEV_FOUND_CONFIRM_NAME); - if (!ssp) - ev->flags |= cpu_to_le32(MGMT_DEV_FOUND_LEGACY_PAIRING); + ev->flags = cpu_to_le32(flags); if (eir_len > 0) memcpy(ev->eir, eir, eir_len); @@ -6013,63 +6874,19 @@ void mgmt_discovering(struct hci_dev *hdev, u8 discovering) mgmt_event(MGMT_EV_DISCOVERING, hdev, &ev, sizeof(ev), NULL); } -int mgmt_device_blocked(struct hci_dev *hdev, bdaddr_t *bdaddr, u8 type) -{ - struct pending_cmd *cmd; - struct mgmt_ev_device_blocked ev; - - cmd = mgmt_pending_find(MGMT_OP_BLOCK_DEVICE, hdev); - - bacpy(&ev.addr.bdaddr, bdaddr); - ev.addr.type = type; - - return mgmt_event(MGMT_EV_DEVICE_BLOCKED, hdev, &ev, sizeof(ev), - cmd ? cmd->sk : NULL); -} - -int mgmt_device_unblocked(struct hci_dev *hdev, bdaddr_t *bdaddr, u8 type) -{ - struct pending_cmd *cmd; - struct mgmt_ev_device_unblocked ev; - - cmd = mgmt_pending_find(MGMT_OP_UNBLOCK_DEVICE, hdev); - - bacpy(&ev.addr.bdaddr, bdaddr); - ev.addr.type = type; - - return mgmt_event(MGMT_EV_DEVICE_UNBLOCKED, hdev, &ev, sizeof(ev), - cmd ? cmd->sk : NULL); -} - static void adv_enable_complete(struct hci_dev *hdev, u8 status) { BT_DBG("%s status %u", hdev->name, status); - - /* Clear the advertising mgmt setting if we failed to re-enable it */ - if (status) { - clear_bit(HCI_ADVERTISING, &hdev->dev_flags); - new_settings(hdev, NULL); - } } void mgmt_reenable_advertising(struct hci_dev *hdev) { struct hci_request req; - if (hci_conn_num(hdev, LE_LINK) > 0) - return; - if (!test_bit(HCI_ADVERTISING, &hdev->dev_flags)) return; hci_req_init(&req, hdev); enable_advertising(&req); - - /* If this fails we have no option but to let user space know - * that we've disabled advertising. - */ - if (hci_req_run(&req, adv_enable_complete) < 0) { - clear_bit(HCI_ADVERTISING, &hdev->dev_flags); - new_settings(hdev, NULL); - } + hci_req_run(&req, adv_enable_complete); } diff --git a/net/bluetooth/rfcomm/core.c b/net/bluetooth/rfcomm/core.c index 754b6fe4f742..af73bc3acb40 100644 --- a/net/bluetooth/rfcomm/core.c +++ b/net/bluetooth/rfcomm/core.c @@ -227,7 +227,8 @@ static int rfcomm_check_security(struct rfcomm_dlc *d) break; } - return hci_conn_security(conn->hcon, d->sec_level, auth_type); + return hci_conn_security(conn->hcon, d->sec_level, auth_type, + d->out); } static void rfcomm_session_timeout(unsigned long arg) @@ -1909,10 +1910,13 @@ static struct rfcomm_session *rfcomm_process_rx(struct rfcomm_session *s) /* Get data directly from socket receive queue without copying it. */ while ((skb = skb_dequeue(&sk->sk_receive_queue))) { skb_orphan(skb); - if (!skb_linearize(skb)) + if (!skb_linearize(skb)) { s = rfcomm_recv_frame(s, skb); - else + if (!s) + break; + } else { kfree_skb(skb); + } } if (s && (sk->sk_state == BT_CLOSED)) diff --git a/net/bluetooth/rfcomm/sock.c b/net/bluetooth/rfcomm/sock.c index c603a5eb4720..8bbbb5ec468c 100644 --- a/net/bluetooth/rfcomm/sock.c +++ b/net/bluetooth/rfcomm/sock.c @@ -918,7 +918,8 @@ static int rfcomm_sock_shutdown(struct socket *sock, int how) sk->sk_shutdown = SHUTDOWN_MASK; __rfcomm_sock_close(sk); - if (sock_flag(sk, SOCK_LINGER) && sk->sk_lingertime) + if (sock_flag(sk, SOCK_LINGER) && sk->sk_lingertime && + !(current->flags & PF_EXITING)) err = bt_sock_wait_state(sk, BT_CLOSED, sk->sk_lingertime); } release_sock(sk); diff --git a/net/bluetooth/sco.c b/net/bluetooth/sco.c index c06dbd3938e8..7ee9e4ab00f8 100644 --- a/net/bluetooth/sco.c +++ b/net/bluetooth/sco.c @@ -40,13 +40,38 @@ static struct bt_sock_list sco_sk_list = { .lock = __RW_LOCK_UNLOCKED(sco_sk_list.lock) }; -static void __sco_chan_add(struct sco_conn *conn, struct sock *sk, struct sock *parent); -static void sco_chan_del(struct sock *sk, int err); +/* ---- SCO connections ---- */ +struct sco_conn { + struct hci_conn *hcon; + + spinlock_t lock; + struct sock *sk; + + unsigned int mtu; +}; + +#define sco_conn_lock(c) spin_lock(&c->lock); +#define sco_conn_unlock(c) spin_unlock(&c->lock); static void sco_sock_close(struct sock *sk); static void sco_sock_kill(struct sock *sk); +/* ----- SCO socket info ----- */ +#define sco_pi(sk) ((struct sco_pinfo *) sk) + +struct sco_pinfo { + struct bt_sock bt; + bdaddr_t src; + bdaddr_t dst; + __u32 flags; + __u16 setting; + struct sco_conn *conn; +}; + /* ---- SCO timers ---- */ +#define SCO_CONN_TIMEOUT (HZ * 40) +#define SCO_DISCONN_TIMEOUT (HZ * 2) + static void sco_sock_timeout(unsigned long arg) { struct sock *sk = (struct sock *) arg; @@ -102,13 +127,31 @@ static struct sco_conn *sco_conn_add(struct hci_conn *hcon) return conn; } -static struct sock *sco_chan_get(struct sco_conn *conn) +/* Delete channel. + * Must be called on the locked socket. */ +static void sco_chan_del(struct sock *sk, int err) { - struct sock *sk = NULL; - sco_conn_lock(conn); - sk = conn->sk; - sco_conn_unlock(conn); - return sk; + struct sco_conn *conn; + + conn = sco_pi(sk)->conn; + + BT_DBG("sk %p, conn %p, err %d", sk, conn, err); + + if (conn) { + sco_conn_lock(conn); + conn->sk = NULL; + sco_pi(sk)->conn = NULL; + sco_conn_unlock(conn); + + if (conn->hcon) + hci_conn_drop(conn->hcon); + } + + sk->sk_state = BT_CLOSED; + sk->sk_err = err; + sk->sk_state_change(sk); + + sock_set_flag(sk, SOCK_ZAPPED); } static int sco_conn_del(struct hci_conn *hcon, int err) @@ -122,7 +165,10 @@ static int sco_conn_del(struct hci_conn *hcon, int err) BT_DBG("hcon %p conn %p, err %d", hcon, conn, err); /* Kill socket */ - sk = sco_chan_get(conn); + sco_conn_lock(conn); + sk = conn->sk; + sco_conn_unlock(conn); + if (sk) { bh_lock_sock(sk); sco_sock_clear_timer(sk); @@ -136,6 +182,17 @@ static int sco_conn_del(struct hci_conn *hcon, int err) return 0; } +static void __sco_chan_add(struct sco_conn *conn, struct sock *sk, struct sock *parent) +{ + BT_DBG("conn %p", conn); + + sco_pi(sk)->conn = conn; + conn->sk = sk; + + if (parent) + bt_accept_enqueue(parent, sk); +} + static int sco_chan_add(struct sco_conn *conn, struct sock *sk, struct sock *parent) { @@ -240,7 +297,11 @@ static int sco_send_frame(struct sock *sk, struct msghdr *msg, int len) static void sco_recv_frame(struct sco_conn *conn, struct sk_buff *skb) { - struct sock *sk = sco_chan_get(conn); + struct sock *sk; + + sco_conn_lock(conn); + sk = conn->sk; + sco_conn_unlock(conn); if (!sk) goto drop; @@ -909,7 +970,8 @@ static int sco_sock_shutdown(struct socket *sock, int how) sco_sock_clear_timer(sk); __sco_sock_close(sk); - if (sock_flag(sk, SOCK_LINGER) && sk->sk_lingertime) + if (sock_flag(sk, SOCK_LINGER) && sk->sk_lingertime && + !(current->flags & PF_EXITING)) err = bt_sock_wait_state(sk, BT_CLOSED, sk->sk_lingertime); } @@ -929,7 +991,8 @@ static int sco_sock_release(struct socket *sock) sco_sock_close(sk); - if (sock_flag(sk, SOCK_LINGER) && sk->sk_lingertime) { + if (sock_flag(sk, SOCK_LINGER) && sk->sk_lingertime && + !(current->flags & PF_EXITING)) { lock_sock(sk); err = bt_sock_wait_state(sk, BT_CLOSED, sk->sk_lingertime); release_sock(sk); @@ -940,44 +1003,6 @@ static int sco_sock_release(struct socket *sock) return err; } -static void __sco_chan_add(struct sco_conn *conn, struct sock *sk, struct sock *parent) -{ - BT_DBG("conn %p", conn); - - sco_pi(sk)->conn = conn; - conn->sk = sk; - - if (parent) - bt_accept_enqueue(parent, sk); -} - -/* Delete channel. - * Must be called on the locked socket. */ -static void sco_chan_del(struct sock *sk, int err) -{ - struct sco_conn *conn; - - conn = sco_pi(sk)->conn; - - BT_DBG("sk %p, conn %p, err %d", sk, conn, err); - - if (conn) { - sco_conn_lock(conn); - conn->sk = NULL; - sco_pi(sk)->conn = NULL; - sco_conn_unlock(conn); - - if (conn->hcon) - hci_conn_drop(conn->hcon); - } - - sk->sk_state = BT_CLOSED; - sk->sk_err = err; - sk->sk_state_change(sk); - - sock_set_flag(sk, SOCK_ZAPPED); -} - static void sco_conn_ready(struct sco_conn *conn) { struct sock *parent; diff --git a/net/bluetooth/smp.c b/net/bluetooth/smp.c index e33a982161c1..fd3294300803 100644 --- a/net/bluetooth/smp.c +++ b/net/bluetooth/smp.c @@ -35,11 +35,13 @@ #define AUTH_REQ_MASK 0x07 -#define SMP_FLAG_TK_VALID 1 -#define SMP_FLAG_CFM_PENDING 2 -#define SMP_FLAG_MITM_AUTH 3 -#define SMP_FLAG_COMPLETE 4 -#define SMP_FLAG_INITIATOR 5 +enum { + SMP_FLAG_TK_VALID, + SMP_FLAG_CFM_PENDING, + SMP_FLAG_MITM_AUTH, + SMP_FLAG_COMPLETE, + SMP_FLAG_INITIATOR, +}; struct smp_chan { struct l2cap_conn *conn; @@ -60,20 +62,16 @@ struct smp_chan { struct smp_ltk *slave_ltk; struct smp_irk *remote_irk; unsigned long flags; + + struct crypto_blkcipher *tfm_aes; }; -static inline void swap128(const u8 src[16], u8 dst[16]) +static inline void swap_buf(const u8 *src, u8 *dst, size_t len) { - int i; - for (i = 0; i < 16; i++) - dst[15 - i] = src[i]; -} + size_t i; -static inline void swap56(const u8 src[7], u8 dst[7]) -{ - int i; - for (i = 0; i < 7; i++) - dst[6 - i] = src[i]; + for (i = 0; i < len; i++) + dst[len - 1 - i] = src[i]; } static int smp_e(struct crypto_blkcipher *tfm, const u8 *k, u8 *r) @@ -92,7 +90,7 @@ static int smp_e(struct crypto_blkcipher *tfm, const u8 *k, u8 *r) desc.flags = 0; /* The most significant octet of key corresponds to k[0] */ - swap128(k, tmp); + swap_buf(k, tmp, 16); err = crypto_blkcipher_setkey(tfm, tmp, 16); if (err) { @@ -101,7 +99,7 @@ static int smp_e(struct crypto_blkcipher *tfm, const u8 *k, u8 *r) } /* Most significant octet of plaintextData corresponds to data[0] */ - swap128(r, data); + swap_buf(r, data, 16); sg_init_one(&sg, data, 16); @@ -110,7 +108,7 @@ static int smp_e(struct crypto_blkcipher *tfm, const u8 *k, u8 *r) BT_ERR("Encrypt data error %d", err); /* Most significant octet of encryptedData corresponds to data[0] */ - swap128(data, r); + swap_buf(data, r, 16); return err; } @@ -174,13 +172,16 @@ int smp_generate_rpa(struct crypto_blkcipher *tfm, u8 irk[16], bdaddr_t *rpa) return 0; } -static int smp_c1(struct crypto_blkcipher *tfm, u8 k[16], u8 r[16], - u8 preq[7], u8 pres[7], u8 _iat, bdaddr_t *ia, - u8 _rat, bdaddr_t *ra, u8 res[16]) +static int smp_c1(struct smp_chan *smp, u8 k[16], u8 r[16], u8 preq[7], + u8 pres[7], u8 _iat, bdaddr_t *ia, u8 _rat, bdaddr_t *ra, + u8 res[16]) { + struct hci_dev *hdev = smp->conn->hcon->hdev; u8 p1[16], p2[16]; int err; + BT_DBG("%s", hdev->name); + memset(p1, 0, 16); /* p1 = pres || preq || _rat || _iat */ @@ -198,7 +199,7 @@ static int smp_c1(struct crypto_blkcipher *tfm, u8 k[16], u8 r[16], u128_xor((u128 *) res, (u128 *) r, (u128 *) p1); /* res = e(k, res) */ - err = smp_e(tfm, k, res); + err = smp_e(smp->tfm_aes, k, res); if (err) { BT_ERR("Encrypt data error"); return err; @@ -208,23 +209,26 @@ static int smp_c1(struct crypto_blkcipher *tfm, u8 k[16], u8 r[16], u128_xor((u128 *) res, (u128 *) res, (u128 *) p2); /* res = e(k, res) */ - err = smp_e(tfm, k, res); + err = smp_e(smp->tfm_aes, k, res); if (err) BT_ERR("Encrypt data error"); return err; } -static int smp_s1(struct crypto_blkcipher *tfm, u8 k[16], u8 r1[16], - u8 r2[16], u8 _r[16]) +static int smp_s1(struct smp_chan *smp, u8 k[16], u8 r1[16], u8 r2[16], + u8 _r[16]) { + struct hci_dev *hdev = smp->conn->hcon->hdev; int err; + BT_DBG("%s", hdev->name); + /* Just least significant octets from r1 and r2 are considered */ memcpy(_r, r2, 8); memcpy(_r + 8, r1, 8); - err = smp_e(tfm, k, _r); + err = smp_e(smp->tfm_aes, k, _r); if (err) BT_ERR("Encrypt data error"); @@ -303,7 +307,7 @@ static void build_pairing_cmd(struct l2cap_conn *conn, struct hci_dev *hdev = hcon->hdev; u8 local_dist = 0, remote_dist = 0; - if (test_bit(HCI_PAIRABLE, &conn->hcon->hdev->dev_flags)) { + if (test_bit(HCI_BONDABLE, &conn->hcon->hdev->dev_flags)) { local_dist = SMP_DIST_ENC_KEY | SMP_DIST_SIGN; remote_dist = SMP_DIST_ENC_KEY | SMP_DIST_SIGN; authreq |= SMP_AUTH_BONDING; @@ -387,10 +391,12 @@ static const u8 gen_method[5][5] = { static u8 get_auth_method(struct smp_chan *smp, u8 local_io, u8 remote_io) { - /* If either side has unknown io_caps, use JUST WORKS */ + /* If either side has unknown io_caps, use JUST_CFM (which gets + * converted later to JUST_WORKS if we're initiators. + */ if (local_io > SMP_IO_KEYBOARD_DISPLAY || remote_io > SMP_IO_KEYBOARD_DISPLAY) - return JUST_WORKS; + return JUST_CFM; return gen_method[remote_io][local_io]; } @@ -410,21 +416,25 @@ static int tk_request(struct l2cap_conn *conn, u8 remote_oob, u8 auth, BT_DBG("tk_request: auth:%d lcl:%d rem:%d", auth, local_io, remote_io); - /* If neither side wants MITM, use JUST WORKS */ - /* Otherwise, look up method from the table */ + /* If neither side wants MITM, either "just" confirm an incoming + * request or use just-works for outgoing ones. The JUST_CFM + * will be converted to JUST_WORKS if necessary later in this + * function. If either side has MITM look up the method from the + * table. + */ if (!(auth & SMP_AUTH_MITM)) - method = JUST_WORKS; + method = JUST_CFM; else method = get_auth_method(smp, local_io, remote_io); - /* If not bonding, don't ask user to confirm a Zero TK */ - if (!(auth & SMP_AUTH_BONDING) && method == JUST_CFM) - method = JUST_WORKS; - /* Don't confirm locally initiated pairing attempts */ if (method == JUST_CFM && test_bit(SMP_FLAG_INITIATOR, &smp->flags)) method = JUST_WORKS; + /* Don't bother user space with no IO capabilities */ + if (method == JUST_CFM && hcon->io_capability == HCI_IO_NO_INPUT_OUTPUT) + method = JUST_WORKS; + /* If Just Works, Continue with Zero TK */ if (method == JUST_WORKS) { set_bit(SMP_FLAG_TK_VALID, &smp->flags); @@ -439,7 +449,7 @@ static int tk_request(struct l2cap_conn *conn, u8 remote_oob, u8 auth, * Confirms and the slave Enters the passkey. */ if (method == OVERLAP) { - if (hcon->link_mode & HCI_LM_MASTER) + if (hcon->role == HCI_ROLE_MASTER) method = CFM_PASSKEY; else method = REQ_PASSKEY; @@ -477,23 +487,15 @@ static int tk_request(struct l2cap_conn *conn, u8 remote_oob, u8 auth, static u8 smp_confirm(struct smp_chan *smp) { struct l2cap_conn *conn = smp->conn; - struct hci_dev *hdev = conn->hcon->hdev; - struct crypto_blkcipher *tfm = hdev->tfm_aes; struct smp_cmd_pairing_confirm cp; int ret; BT_DBG("conn %p", conn); - /* Prevent mutual access to hdev->tfm_aes */ - hci_dev_lock(hdev); - - ret = smp_c1(tfm, smp->tk, smp->prnd, smp->preq, smp->prsp, + ret = smp_c1(smp, smp->tk, smp->prnd, smp->preq, smp->prsp, conn->hcon->init_addr_type, &conn->hcon->init_addr, conn->hcon->resp_addr_type, &conn->hcon->resp_addr, cp.confirm_val); - - hci_dev_unlock(hdev); - if (ret) return SMP_UNSPECIFIED; @@ -508,25 +510,17 @@ static u8 smp_random(struct smp_chan *smp) { struct l2cap_conn *conn = smp->conn; struct hci_conn *hcon = conn->hcon; - struct hci_dev *hdev = hcon->hdev; - struct crypto_blkcipher *tfm = hdev->tfm_aes; u8 confirm[16]; int ret; - if (IS_ERR_OR_NULL(tfm)) + if (IS_ERR_OR_NULL(smp->tfm_aes)) return SMP_UNSPECIFIED; BT_DBG("conn %p %s", conn, conn->hcon->out ? "master" : "slave"); - /* Prevent mutual access to hdev->tfm_aes */ - hci_dev_lock(hdev); - - ret = smp_c1(tfm, smp->tk, smp->rrnd, smp->preq, smp->prsp, + ret = smp_c1(smp, smp->tk, smp->rrnd, smp->preq, smp->prsp, hcon->init_addr_type, &hcon->init_addr, hcon->resp_addr_type, &hcon->resp_addr, confirm); - - hci_dev_unlock(hdev); - if (ret) return SMP_UNSPECIFIED; @@ -540,7 +534,7 @@ static u8 smp_random(struct smp_chan *smp) __le64 rand = 0; __le16 ediv = 0; - smp_s1(tfm, smp->tk, smp->rrnd, smp->prnd, stk); + smp_s1(smp, smp->tk, smp->rrnd, smp->prnd, stk); memset(stk + smp->enc_key_size, 0, SMP_MAX_ENC_KEY_SIZE - smp->enc_key_size); @@ -550,6 +544,7 @@ static u8 smp_random(struct smp_chan *smp) hci_le_start_enc(hcon, ediv, rand, stk); hcon->enc_key_size = smp->enc_key_size; + set_bit(HCI_CONN_STK_ENCRYPT, &hcon->flags); } else { u8 stk[16], auth; __le64 rand = 0; @@ -558,7 +553,7 @@ static u8 smp_random(struct smp_chan *smp) smp_send_cmd(conn, SMP_CMD_PAIRING_RANDOM, sizeof(smp->prnd), smp->prnd); - smp_s1(tfm, smp->tk, smp->prnd, smp->rrnd, stk); + smp_s1(smp, smp->tk, smp->prnd, smp->rrnd, stk); memset(stk + smp->enc_key_size, 0, SMP_MAX_ENC_KEY_SIZE - smp->enc_key_size); @@ -568,9 +563,12 @@ static u8 smp_random(struct smp_chan *smp) else auth = 0; + /* Even though there's no _SLAVE suffix this is the + * slave STK we're adding for later lookup (the master + * STK never needs to be stored). + */ hci_add_ltk(hcon->hdev, &hcon->dst, hcon->dst_type, - HCI_SMP_STK_SLAVE, auth, stk, smp->enc_key_size, - ediv, rand); + SMP_STK, auth, stk, smp->enc_key_size, ediv, rand); } return 0; @@ -581,12 +579,21 @@ static struct smp_chan *smp_chan_create(struct l2cap_conn *conn) struct smp_chan *smp; smp = kzalloc(sizeof(*smp), GFP_ATOMIC); - if (!smp) + if (!smp) { + clear_bit(HCI_CONN_LE_SMP_PEND, &conn->hcon->flags); return NULL; + } + + smp->tfm_aes = crypto_alloc_blkcipher("ecb(aes)", 0, CRYPTO_ALG_ASYNC); + if (IS_ERR(smp->tfm_aes)) { + BT_ERR("Unable to create ECB crypto context"); + kfree(smp); + clear_bit(HCI_CONN_LE_SMP_PEND, &conn->hcon->flags); + return NULL; + } smp->conn = conn; conn->smp_chan = smp; - conn->hcon->smp_conn = conn; hci_conn_hold(conn->hcon); @@ -606,6 +613,8 @@ void smp_chan_destroy(struct l2cap_conn *conn) kfree(smp->csrk); kfree(smp->slave_csrk); + crypto_free_blkcipher(smp->tfm_aes); + /* If pairing failed clean up any keys we might have */ if (!complete) { if (smp->ltk) { @@ -626,19 +635,18 @@ void smp_chan_destroy(struct l2cap_conn *conn) kfree(smp); conn->smp_chan = NULL; - conn->hcon->smp_conn = NULL; hci_conn_drop(conn->hcon); } int smp_user_confirm_reply(struct hci_conn *hcon, u16 mgmt_op, __le32 passkey) { - struct l2cap_conn *conn = hcon->smp_conn; + struct l2cap_conn *conn = hcon->l2cap_data; struct smp_chan *smp; u32 value; BT_DBG(""); - if (!conn) + if (!conn || !test_bit(HCI_CONN_LE_SMP_PEND, &hcon->flags)) return -ENOTCONN; smp = conn->smp_chan; @@ -675,6 +683,7 @@ int smp_user_confirm_reply(struct hci_conn *hcon, u16 mgmt_op, __le32 passkey) static u8 smp_cmd_pairing_req(struct l2cap_conn *conn, struct sk_buff *skb) { struct smp_cmd_pairing rsp, *req = (void *) skb->data; + struct hci_dev *hdev = conn->hcon->hdev; struct smp_chan *smp; u8 key_size, auth, sec_level; int ret; @@ -684,7 +693,7 @@ static u8 smp_cmd_pairing_req(struct l2cap_conn *conn, struct sk_buff *skb) if (skb->len < sizeof(*req)) return SMP_INVALID_PARAMS; - if (conn->hcon->link_mode & HCI_LM_MASTER) + if (conn->hcon->role != HCI_ROLE_SLAVE) return SMP_CMD_NOTSUPP; if (!test_and_set_bit(HCI_CONN_LE_SMP_PEND, &conn->hcon->flags)) @@ -695,6 +704,10 @@ static u8 smp_cmd_pairing_req(struct l2cap_conn *conn, struct sk_buff *skb) if (!smp) return SMP_UNSPECIFIED; + if (!test_bit(HCI_BONDABLE, &hdev->dev_flags) && + (req->auth_req & SMP_AUTH_BONDING)) + return SMP_PAIRING_NOTSUPP; + smp->preq[0] = SMP_CMD_PAIRING_REQ; memcpy(&smp->preq[1], req, sizeof(*req)); skb_pull(skb, sizeof(*req)); @@ -734,8 +747,6 @@ static u8 smp_cmd_pairing_req(struct l2cap_conn *conn, struct sk_buff *skb) if (ret) return SMP_UNSPECIFIED; - clear_bit(SMP_FLAG_INITIATOR, &smp->flags); - return 0; } @@ -751,7 +762,7 @@ static u8 smp_cmd_pairing_rsp(struct l2cap_conn *conn, struct sk_buff *skb) if (skb->len < sizeof(*rsp)) return SMP_INVALID_PARAMS; - if (!(conn->hcon->link_mode & HCI_LM_MASTER)) + if (conn->hcon->role != HCI_ROLE_MASTER) return SMP_CMD_NOTSUPP; skb_pull(skb, sizeof(*rsp)); @@ -839,26 +850,51 @@ static u8 smp_cmd_pairing_random(struct l2cap_conn *conn, struct sk_buff *skb) return smp_random(smp); } -static u8 smp_ltk_encrypt(struct l2cap_conn *conn, u8 sec_level) +static bool smp_ltk_encrypt(struct l2cap_conn *conn, u8 sec_level) { struct smp_ltk *key; struct hci_conn *hcon = conn->hcon; key = hci_find_ltk_by_addr(hcon->hdev, &hcon->dst, hcon->dst_type, - hcon->out); + hcon->role); if (!key) - return 0; + return false; if (sec_level > BT_SECURITY_MEDIUM && !key->authenticated) - return 0; + return false; if (test_and_set_bit(HCI_CONN_ENCRYPT_PEND, &hcon->flags)) - return 1; + return true; hci_le_start_enc(hcon, key->ediv, key->rand, key->val); hcon->enc_key_size = key->enc_size; - return 1; + /* We never store STKs for master role, so clear this flag */ + clear_bit(HCI_CONN_STK_ENCRYPT, &hcon->flags); + + return true; +} + +bool smp_sufficient_security(struct hci_conn *hcon, u8 sec_level) +{ + if (sec_level == BT_SECURITY_LOW) + return true; + + /* If we're encrypted with an STK always claim insufficient + * security. This way we allow the connection to be re-encrypted + * with an LTK, even if the LTK provides the same level of + * security. Only exception is if we don't have an LTK (e.g. + * because of key distribution bits). + */ + if (test_bit(HCI_CONN_STK_ENCRYPT, &hcon->flags) && + hci_find_ltk_by_addr(hcon->hdev, &hcon->dst, hcon->dst_type, + hcon->role)) + return false; + + if (hcon->sec_level >= sec_level) + return true; + + return false; } static u8 smp_cmd_security_req(struct l2cap_conn *conn, struct sk_buff *skb) @@ -874,10 +910,13 @@ static u8 smp_cmd_security_req(struct l2cap_conn *conn, struct sk_buff *skb) if (skb->len < sizeof(*rp)) return SMP_INVALID_PARAMS; - if (!(conn->hcon->link_mode & HCI_LM_MASTER)) + if (hcon->role != HCI_ROLE_MASTER) return SMP_CMD_NOTSUPP; sec_level = authreq_to_seclevel(rp->auth_req); + if (smp_sufficient_security(hcon, sec_level)) + return 0; + if (sec_level > hcon->pending_sec_level) hcon->pending_sec_level = sec_level; @@ -888,6 +927,12 @@ static u8 smp_cmd_security_req(struct l2cap_conn *conn, struct sk_buff *skb) return 0; smp = smp_chan_create(conn); + if (!smp) + return SMP_UNSPECIFIED; + + if (!test_bit(HCI_BONDABLE, &hcon->hdev->dev_flags) && + (rp->auth_req & SMP_AUTH_BONDING)) + return SMP_PAIRING_NOTSUPP; skb_pull(skb, sizeof(*rp)); @@ -899,22 +944,9 @@ static u8 smp_cmd_security_req(struct l2cap_conn *conn, struct sk_buff *skb) smp_send_cmd(conn, SMP_CMD_PAIRING_REQ, sizeof(cp), &cp); - clear_bit(SMP_FLAG_INITIATOR, &smp->flags); - return 0; } -bool smp_sufficient_security(struct hci_conn *hcon, u8 sec_level) -{ - if (sec_level == BT_SECURITY_LOW) - return true; - - if (hcon->sec_level >= sec_level) - return true; - - return false; -} - int smp_conn_security(struct hci_conn *hcon, __u8 sec_level) { struct l2cap_conn *conn = hcon->l2cap_data; @@ -936,7 +968,7 @@ int smp_conn_security(struct hci_conn *hcon, __u8 sec_level) if (sec_level > hcon->pending_sec_level) hcon->pending_sec_level = sec_level; - if (hcon->link_mode & HCI_LM_MASTER) + if (hcon->role == HCI_ROLE_MASTER) if (smp_ltk_encrypt(conn, hcon->pending_sec_level)) return 0; @@ -956,7 +988,7 @@ int smp_conn_security(struct hci_conn *hcon, __u8 sec_level) hcon->pending_sec_level > BT_SECURITY_MEDIUM) authreq |= SMP_AUTH_MITM; - if (hcon->link_mode & HCI_LM_MASTER) { + if (hcon->role == HCI_ROLE_MASTER) { struct smp_cmd_pairing cp; build_pairing_cmd(conn, &cp, NULL, authreq); @@ -1021,7 +1053,7 @@ static int smp_cmd_master_ident(struct l2cap_conn *conn, struct sk_buff *skb) hci_dev_lock(hdev); authenticated = (hcon->sec_level == BT_SECURITY_HIGH); - ltk = hci_add_ltk(hdev, &hcon->dst, hcon->dst_type, HCI_SMP_LTK, + ltk = hci_add_ltk(hdev, &hcon->dst, hcon->dst_type, SMP_LTK, authenticated, smp->tk, smp->enc_key_size, rp->ediv, rp->rand); smp->ltk = ltk; @@ -1075,6 +1107,8 @@ static int smp_cmd_ident_addr_info(struct l2cap_conn *conn, skb_pull(skb, sizeof(*info)); + hci_dev_lock(hcon->hdev); + /* Strictly speaking the Core Specification (4.1) allows sending * an empty address which would force us to rely on just the IRK * as "identity information". However, since such @@ -1084,8 +1118,7 @@ static int smp_cmd_ident_addr_info(struct l2cap_conn *conn, */ if (!bacmp(&info->bdaddr, BDADDR_ANY)) { BT_ERR("Ignoring IRK with no identity address"); - smp_distribute_keys(conn); - return 0; + goto distribute; } bacpy(&smp->id_addr, &info->bdaddr); @@ -1099,8 +1132,11 @@ static int smp_cmd_ident_addr_info(struct l2cap_conn *conn, smp->remote_irk = hci_add_irk(conn->hcon->hdev, &smp->id_addr, smp->id_addr_type, smp->irk, &rpa); +distribute: smp_distribute_keys(conn); + hci_dev_unlock(hcon->hdev); + return 0; } @@ -1156,7 +1192,7 @@ int smp_sig_channel(struct l2cap_conn *conn, struct sk_buff *skb) } if (!test_bit(HCI_LE_ENABLED, &hcon->hdev->dev_flags)) { - err = -ENOTSUPP; + err = -EOPNOTSUPP; reason = SMP_PAIRING_NOTSUPP; goto done; } @@ -1174,7 +1210,7 @@ int smp_sig_channel(struct l2cap_conn *conn, struct sk_buff *skb) !conn->smp_chan) { BT_ERR("Unexpected SMP command 0x%02x. Disconnecting.", code); kfree_skb(skb); - return -ENOTSUPP; + return -EOPNOTSUPP; } switch (code) { @@ -1258,6 +1294,22 @@ static void smp_notify_keys(struct l2cap_conn *conn) bacpy(&hcon->dst, &smp->remote_irk->bdaddr); hcon->dst_type = smp->remote_irk->addr_type; l2cap_conn_update_id_addr(hcon); + + /* When receiving an indentity resolving key for + * a remote device that does not use a resolvable + * private address, just remove the key so that + * it is possible to use the controller white + * list for scanning. + * + * Userspace will have been told to not store + * this key at this point. So it is safe to + * just remove it. + */ + if (!bacmp(&smp->remote_irk->rpa, BDADDR_ANY)) { + list_del(&smp->remote_irk->list); + kfree(smp->remote_irk); + smp->remote_irk = NULL; + } } /* The LTKs and CSRKs should be persistent only if both sides @@ -1337,7 +1389,7 @@ int smp_distribute_keys(struct l2cap_conn *conn) authenticated = hcon->sec_level == BT_SECURITY_HIGH; ltk = hci_add_ltk(hdev, &hcon->dst, hcon->dst_type, - HCI_SMP_LTK_SLAVE, authenticated, enc.ltk, + SMP_LTK_SLAVE, authenticated, enc.ltk, smp->enc_key_size, ediv, rand); smp->slave_ltk = ltk; diff --git a/net/bluetooth/smp.h b/net/bluetooth/smp.h index 5a8dc36460a1..796f4f45f92f 100644 --- a/net/bluetooth/smp.h +++ b/net/bluetooth/smp.h @@ -116,6 +116,13 @@ struct smp_cmd_security_req { #define SMP_MIN_ENC_KEY_SIZE 7 #define SMP_MAX_ENC_KEY_SIZE 16 +/* LTK types used in internal storage (struct smp_ltk) */ +enum { + SMP_STK, + SMP_LTK, + SMP_LTK_SLAVE, +}; + /* SMP Commands */ bool smp_sufficient_security(struct hci_conn *hcon, u8 sec_level); int smp_conn_security(struct hci_conn *hcon, __u8 sec_level); diff --git a/net/bridge/br_fdb.c b/net/bridge/br_fdb.c index b524c36c1273..6f6c95cfe8f2 100644 --- a/net/bridge/br_fdb.c +++ b/net/bridge/br_fdb.c @@ -93,7 +93,7 @@ static void fdb_rcu_free(struct rcu_head *head) static void fdb_add_hw(struct net_bridge *br, const unsigned char *addr) { int err; - struct net_bridge_port *p, *tmp; + struct net_bridge_port *p; ASSERT_RTNL(); @@ -107,11 +107,9 @@ static void fdb_add_hw(struct net_bridge *br, const unsigned char *addr) return; undo: - list_for_each_entry(tmp, &br->port_list, list) { - if (tmp == p) - break; - if (!br_promisc_port(tmp)) - dev_uc_del(tmp->dev, addr); + list_for_each_entry_continue_reverse(p, &br->port_list, list) { + if (!br_promisc_port(p)) + dev_uc_del(p->dev, addr); } } @@ -631,7 +629,7 @@ static int fdb_fill_info(struct sk_buff *skb, const struct net_bridge *br, if (nla_put(skb, NDA_CACHEINFO, sizeof(ci), &ci)) goto nla_put_failure; - if (nla_put(skb, NDA_VLAN, sizeof(u16), &fdb->vlan_id)) + if (fdb->vlan_id && nla_put(skb, NDA_VLAN, sizeof(u16), &fdb->vlan_id)) goto nla_put_failure; return nlmsg_end(skb, nlh); @@ -678,6 +676,7 @@ errout: int br_fdb_dump(struct sk_buff *skb, struct netlink_callback *cb, struct net_device *dev, + struct net_device *filter_dev, int idx) { struct net_bridge *br = netdev_priv(dev); @@ -693,6 +692,19 @@ int br_fdb_dump(struct sk_buff *skb, if (idx < cb->args[0]) goto skip; + if (filter_dev && + (!f->dst || f->dst->dev != filter_dev)) { + if (filter_dev != dev) + goto skip; + /* !f->dst is a speacial case for bridge + * It means the MAC belongs to the bridge + * Therefore need a little more filtering + * we only want to dump the !f->dst case + */ + if (f->dst) + goto skip; + } + if (fdb_fill_info(skb, br, f, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, diff --git a/net/bridge/br_if.c b/net/bridge/br_if.c index 3eca3fdf8fe1..078d336a1f37 100644 --- a/net/bridge/br_if.c +++ b/net/bridge/br_if.c @@ -344,7 +344,7 @@ int br_add_bridge(struct net *net, const char *name) struct net_device *dev; int res; - dev = alloc_netdev(sizeof(struct net_bridge), name, + dev = alloc_netdev(sizeof(struct net_bridge), name, NET_NAME_UNKNOWN, br_dev_setup); if (!dev) diff --git a/net/bridge/br_multicast.c b/net/bridge/br_multicast.c index abfa0b65a111..b4845f4b2bb4 100644 --- a/net/bridge/br_multicast.c +++ b/net/bridge/br_multicast.c @@ -2216,6 +2216,43 @@ unlock: EXPORT_SYMBOL_GPL(br_multicast_list_adjacent); /** + * br_multicast_has_querier_anywhere - Checks for a querier on a bridge + * @dev: The bridge port providing the bridge on which to check for a querier + * @proto: The protocol family to check for: IGMP -> ETH_P_IP, MLD -> ETH_P_IPV6 + * + * Checks whether the given interface has a bridge on top and if so returns + * true if a valid querier exists anywhere on the bridged link layer. + * Otherwise returns false. + */ +bool br_multicast_has_querier_anywhere(struct net_device *dev, int proto) +{ + struct net_bridge *br; + struct net_bridge_port *port; + struct ethhdr eth; + bool ret = false; + + rcu_read_lock(); + if (!br_port_exists(dev)) + goto unlock; + + port = br_port_get_rcu(dev); + if (!port || !port->br) + goto unlock; + + br = port->br; + + memset(ð, 0, sizeof(eth)); + eth.h_proto = htons(proto); + + ret = br_multicast_querier_exists(br, ð); + +unlock: + rcu_read_unlock(); + return ret; +} +EXPORT_SYMBOL_GPL(br_multicast_has_querier_anywhere); + +/** * br_multicast_has_querier_adjacent - Checks for a querier behind a bridge port * @dev: The bridge port adjacent to which to check for a querier * @proto: The protocol family to check for: IGMP -> ETH_P_IP, MLD -> ETH_P_IPV6 diff --git a/net/bridge/br_netlink.c b/net/bridge/br_netlink.c index 26edb518b839..cb5fcf62f663 100644 --- a/net/bridge/br_netlink.c +++ b/net/bridge/br_netlink.c @@ -208,7 +208,6 @@ int br_getlink(struct sk_buff *skb, u32 pid, u32 seq, int err = 0; struct net_bridge_port *port = br_port_get_rtnl(dev); - /* not a bridge port and */ if (!port && !(filter_mask & RTEXT_FILTER_BRVLAN)) goto out; diff --git a/net/bridge/br_private.h b/net/bridge/br_private.h index 23caf5b0309e..62a7fa2e3569 100644 --- a/net/bridge/br_private.h +++ b/net/bridge/br_private.h @@ -399,7 +399,7 @@ int br_fdb_delete(struct ndmsg *ndm, struct nlattr *tb[], int br_fdb_add(struct ndmsg *nlh, struct nlattr *tb[], struct net_device *dev, const unsigned char *addr, u16 nlh_flags); int br_fdb_dump(struct sk_buff *skb, struct netlink_callback *cb, - struct net_device *dev, int idx); + struct net_device *dev, struct net_device *fdev, int idx); int br_fdb_sync_static(struct net_bridge *br, struct net_bridge_port *p); void br_fdb_unsync_static(struct net_bridge *br, struct net_bridge_port *p); diff --git a/net/bridge/br_vlan.c b/net/bridge/br_vlan.c index 2b2774fe0703..febb0f87fa37 100644 --- a/net/bridge/br_vlan.c +++ b/net/bridge/br_vlan.c @@ -55,10 +55,8 @@ static int __vlan_add(struct net_port_vlans *v, u16 vid, u16 flags) if (p) { /* Add VLAN to the device filter if it is supported. - * Stricly speaking, this is not necessary now, since - * devices are made promiscuous by the bridge, but if - * that ever changes this code will allow tagged - * traffic to enter the bridge. + * This ensures tagged traffic enters the bridge when + * promiscuous mode is disabled by br_manage_promisc(). */ err = vlan_vid_add(dev, br->vlan_proto, vid); if (err) diff --git a/net/bridge/netfilter/Kconfig b/net/bridge/netfilter/Kconfig index 629dc77874a9..9cebf47ac840 100644 --- a/net/bridge/netfilter/Kconfig +++ b/net/bridge/netfilter/Kconfig @@ -14,6 +14,15 @@ config NFT_BRIDGE_META help Add support for bridge dedicated meta key. +config NFT_BRIDGE_REJECT + tristate "Netfilter nf_tables bridge reject support" + depends on NFT_REJECT && NFT_REJECT_IPV4 && NFT_REJECT_IPV6 + help + Add support to reject packets. + +config NF_LOG_BRIDGE + tristate "Bridge packet logging" + endif # NF_TABLES_BRIDGE menuconfig BRIDGE_NF_EBTABLES @@ -202,22 +211,6 @@ config BRIDGE_EBT_LOG To compile it as a module, choose M here. If unsure, say N. -config BRIDGE_EBT_ULOG - tristate "ebt: ulog support (OBSOLETE)" - help - This option enables the old bridge-specific "ebt_ulog" implementation - which has been obsoleted by the new "nfnetlink_log" code (see - CONFIG_NETFILTER_NETLINK_LOG). - - This option adds the ulog watcher, that you can use in any rule - in any ebtables table. The packet is passed to a userspace - logging daemon using netlink multicast sockets. This differs - from the log watcher in the sense that the complete packet is - sent to userspace instead of a descriptive text and that - netlink multicast sockets are used instead of the syslog. - - To compile it as a module, choose M here. If unsure, say N. - config BRIDGE_EBT_NFLOG tristate "ebt: nflog support" help diff --git a/net/bridge/netfilter/Makefile b/net/bridge/netfilter/Makefile index 6f2f3943d66f..be4d0cea78ce 100644 --- a/net/bridge/netfilter/Makefile +++ b/net/bridge/netfilter/Makefile @@ -4,6 +4,10 @@ obj-$(CONFIG_NF_TABLES_BRIDGE) += nf_tables_bridge.o obj-$(CONFIG_NFT_BRIDGE_META) += nft_meta_bridge.o +obj-$(CONFIG_NFT_BRIDGE_REJECT) += nft_reject_bridge.o + +# packet logging +obj-$(CONFIG_NF_LOG_BRIDGE) += nf_log_bridge.o obj-$(CONFIG_BRIDGE_NF_EBTABLES) += ebtables.o @@ -33,5 +37,4 @@ obj-$(CONFIG_BRIDGE_EBT_SNAT) += ebt_snat.o # watchers obj-$(CONFIG_BRIDGE_EBT_LOG) += ebt_log.o -obj-$(CONFIG_BRIDGE_EBT_ULOG) += ebt_ulog.o obj-$(CONFIG_BRIDGE_EBT_NFLOG) += ebt_nflog.o diff --git a/net/bridge/netfilter/ebt_log.c b/net/bridge/netfilter/ebt_log.c index 5322a36867a3..17f2e4bc2a29 100644 --- a/net/bridge/netfilter/ebt_log.c +++ b/net/bridge/netfilter/ebt_log.c @@ -186,6 +186,10 @@ ebt_log_tg(struct sk_buff *skb, const struct xt_action_param *par) li.u.log.level = info->loglevel; li.u.log.logflags = info->bitmask; + /* Remember that we have to use ebt_log_packet() not to break backward + * compatibility. We cannot use the default bridge packet logger via + * nf_log_packet() with NFT_LOG_TYPE_LOG here. --Pablo + */ if (info->bitmask & EBT_LOG_NFLOG) nf_log_packet(net, NFPROTO_BRIDGE, par->hooknum, skb, par->in, par->out, &li, "%s", info->prefix); @@ -205,54 +209,13 @@ static struct xt_target ebt_log_tg_reg __read_mostly = { .me = THIS_MODULE, }; -static struct nf_logger ebt_log_logger __read_mostly = { - .name = "ebt_log", - .logfn = &ebt_log_packet, - .me = THIS_MODULE, -}; - -static int __net_init ebt_log_net_init(struct net *net) -{ - nf_log_set(net, NFPROTO_BRIDGE, &ebt_log_logger); - return 0; -} - -static void __net_exit ebt_log_net_fini(struct net *net) -{ - nf_log_unset(net, &ebt_log_logger); -} - -static struct pernet_operations ebt_log_net_ops = { - .init = ebt_log_net_init, - .exit = ebt_log_net_fini, -}; - static int __init ebt_log_init(void) { - int ret; - - ret = register_pernet_subsys(&ebt_log_net_ops); - if (ret < 0) - goto err_pernet; - - ret = xt_register_target(&ebt_log_tg_reg); - if (ret < 0) - goto err_target; - - nf_log_register(NFPROTO_BRIDGE, &ebt_log_logger); - - return ret; - -err_target: - unregister_pernet_subsys(&ebt_log_net_ops); -err_pernet: - return ret; + return xt_register_target(&ebt_log_tg_reg); } static void __exit ebt_log_fini(void) { - unregister_pernet_subsys(&ebt_log_net_ops); - nf_log_unregister(&ebt_log_logger); xt_unregister_target(&ebt_log_tg_reg); } diff --git a/net/bridge/netfilter/ebt_ulog.c b/net/bridge/netfilter/ebt_ulog.c deleted file mode 100644 index 7c470c371e14..000000000000 --- a/net/bridge/netfilter/ebt_ulog.c +++ /dev/null @@ -1,393 +0,0 @@ -/* - * netfilter module for userspace bridged Ethernet frames logging daemons - * - * Authors: - * Bart De Schuymer <bdschuym@pandora.be> - * Harald Welte <laforge@netfilter.org> - * - * November, 2004 - * - * Based on ipt_ULOG.c, which is - * (C) 2000-2002 by Harald Welte <laforge@netfilter.org> - * - * This module accepts two parameters: - * - * nlbufsiz: - * The parameter specifies how big the buffer for each netlink multicast - * group is. e.g. If you say nlbufsiz=8192, up to eight kb of packets will - * get accumulated in the kernel until they are sent to userspace. It is - * NOT possible to allocate more than 128kB, and it is strongly discouraged, - * because atomically allocating 128kB inside the network rx softirq is not - * reliable. Please also keep in mind that this buffer size is allocated for - * each nlgroup you are using, so the total kernel memory usage increases - * by that factor. - * - * flushtimeout: - * Specify, after how many hundredths of a second the queue should be - * flushed even if it is not full yet. - * - */ -#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt -#include <linux/module.h> -#include <linux/slab.h> -#include <linux/spinlock.h> -#include <linux/socket.h> -#include <linux/skbuff.h> -#include <linux/kernel.h> -#include <linux/timer.h> -#include <net/netlink.h> -#include <linux/netdevice.h> -#include <linux/netfilter/x_tables.h> -#include <linux/netfilter_bridge/ebtables.h> -#include <linux/netfilter_bridge/ebt_ulog.h> -#include <net/netfilter/nf_log.h> -#include <net/netns/generic.h> -#include <net/sock.h> -#include "../br_private.h" - -static unsigned int nlbufsiz = NLMSG_GOODSIZE; -module_param(nlbufsiz, uint, 0600); -MODULE_PARM_DESC(nlbufsiz, "netlink buffer size (number of bytes) " - "(defaults to 4096)"); - -static unsigned int flushtimeout = 10; -module_param(flushtimeout, uint, 0600); -MODULE_PARM_DESC(flushtimeout, "buffer flush timeout (hundredths ofa second) " - "(defaults to 10)"); - -typedef struct { - unsigned int qlen; /* number of nlmsgs' in the skb */ - struct nlmsghdr *lastnlh; /* netlink header of last msg in skb */ - struct sk_buff *skb; /* the pre-allocated skb */ - struct timer_list timer; /* the timer function */ - spinlock_t lock; /* the per-queue lock */ -} ebt_ulog_buff_t; - -static int ebt_ulog_net_id __read_mostly; -struct ebt_ulog_net { - unsigned int nlgroup[EBT_ULOG_MAXNLGROUPS]; - ebt_ulog_buff_t ulog_buffers[EBT_ULOG_MAXNLGROUPS]; - struct sock *ebtulognl; -}; - -static struct ebt_ulog_net *ebt_ulog_pernet(struct net *net) -{ - return net_generic(net, ebt_ulog_net_id); -} - -/* send one ulog_buff_t to userspace */ -static void ulog_send(struct ebt_ulog_net *ebt, unsigned int nlgroup) -{ - ebt_ulog_buff_t *ub = &ebt->ulog_buffers[nlgroup]; - - del_timer(&ub->timer); - - if (!ub->skb) - return; - - /* last nlmsg needs NLMSG_DONE */ - if (ub->qlen > 1) - ub->lastnlh->nlmsg_type = NLMSG_DONE; - - NETLINK_CB(ub->skb).dst_group = nlgroup + 1; - netlink_broadcast(ebt->ebtulognl, ub->skb, 0, nlgroup + 1, GFP_ATOMIC); - - ub->qlen = 0; - ub->skb = NULL; -} - -/* timer function to flush queue in flushtimeout time */ -static void ulog_timer(unsigned long data) -{ - struct ebt_ulog_net *ebt = container_of((void *)data, - struct ebt_ulog_net, - nlgroup[*(unsigned int *)data]); - - ebt_ulog_buff_t *ub = &ebt->ulog_buffers[*(unsigned int *)data]; - spin_lock_bh(&ub->lock); - if (ub->skb) - ulog_send(ebt, *(unsigned int *)data); - spin_unlock_bh(&ub->lock); -} - -static struct sk_buff *ulog_alloc_skb(unsigned int size) -{ - struct sk_buff *skb; - unsigned int n; - - n = max(size, nlbufsiz); - skb = alloc_skb(n, GFP_ATOMIC | __GFP_NOWARN); - if (!skb) { - if (n > size) { - /* try to allocate only as much as we need for - * current packet */ - skb = alloc_skb(size, GFP_ATOMIC); - if (!skb) - pr_debug("cannot even allocate buffer of size %ub\n", - size); - } - } - - return skb; -} - -static void ebt_ulog_packet(struct net *net, unsigned int hooknr, - const struct sk_buff *skb, - const struct net_device *in, - const struct net_device *out, - const struct ebt_ulog_info *uloginfo, - const char *prefix) -{ - ebt_ulog_packet_msg_t *pm; - size_t size, copy_len; - struct nlmsghdr *nlh; - struct ebt_ulog_net *ebt = ebt_ulog_pernet(net); - unsigned int group = uloginfo->nlgroup; - ebt_ulog_buff_t *ub = &ebt->ulog_buffers[group]; - spinlock_t *lock = &ub->lock; - ktime_t kt; - - if ((uloginfo->cprange == 0) || - (uloginfo->cprange > skb->len + ETH_HLEN)) - copy_len = skb->len + ETH_HLEN; - else - copy_len = uloginfo->cprange; - - size = nlmsg_total_size(sizeof(*pm) + copy_len); - if (size > nlbufsiz) { - pr_debug("Size %Zd needed, but nlbufsiz=%d\n", size, nlbufsiz); - return; - } - - spin_lock_bh(lock); - - if (!ub->skb) { - if (!(ub->skb = ulog_alloc_skb(size))) - goto unlock; - } else if (size > skb_tailroom(ub->skb)) { - ulog_send(ebt, group); - - if (!(ub->skb = ulog_alloc_skb(size))) - goto unlock; - } - - nlh = nlmsg_put(ub->skb, 0, ub->qlen, 0, - size - NLMSG_ALIGN(sizeof(*nlh)), 0); - if (!nlh) { - kfree_skb(ub->skb); - ub->skb = NULL; - goto unlock; - } - ub->qlen++; - - pm = nlmsg_data(nlh); - memset(pm, 0, sizeof(*pm)); - - /* Fill in the ulog data */ - pm->version = EBT_ULOG_VERSION; - kt = ktime_get_real(); - pm->stamp = ktime_to_timeval(kt); - if (ub->qlen == 1) - ub->skb->tstamp = kt; - pm->data_len = copy_len; - pm->mark = skb->mark; - pm->hook = hooknr; - if (uloginfo->prefix != NULL) - strcpy(pm->prefix, uloginfo->prefix); - - if (in) { - strcpy(pm->physindev, in->name); - /* If in isn't a bridge, then physindev==indev */ - if (br_port_exists(in)) - /* rcu_read_lock()ed by nf_hook_slow */ - strcpy(pm->indev, br_port_get_rcu(in)->br->dev->name); - else - strcpy(pm->indev, in->name); - } - - if (out) { - /* If out exists, then out is a bridge port */ - strcpy(pm->physoutdev, out->name); - /* rcu_read_lock()ed by nf_hook_slow */ - strcpy(pm->outdev, br_port_get_rcu(out)->br->dev->name); - } - - if (skb_copy_bits(skb, -ETH_HLEN, pm->data, copy_len) < 0) - BUG(); - - if (ub->qlen > 1) - ub->lastnlh->nlmsg_flags |= NLM_F_MULTI; - - ub->lastnlh = nlh; - - if (ub->qlen >= uloginfo->qthreshold) - ulog_send(ebt, group); - else if (!timer_pending(&ub->timer)) { - ub->timer.expires = jiffies + flushtimeout * HZ / 100; - add_timer(&ub->timer); - } - -unlock: - spin_unlock_bh(lock); -} - -/* this function is registered with the netfilter core */ -static void ebt_log_packet(struct net *net, u_int8_t pf, unsigned int hooknum, - const struct sk_buff *skb, const struct net_device *in, - const struct net_device *out, const struct nf_loginfo *li, - const char *prefix) -{ - struct ebt_ulog_info loginfo; - - if (!li || li->type != NF_LOG_TYPE_ULOG) { - loginfo.nlgroup = EBT_ULOG_DEFAULT_NLGROUP; - loginfo.cprange = 0; - loginfo.qthreshold = EBT_ULOG_DEFAULT_QTHRESHOLD; - loginfo.prefix[0] = '\0'; - } else { - loginfo.nlgroup = li->u.ulog.group; - loginfo.cprange = li->u.ulog.copy_len; - loginfo.qthreshold = li->u.ulog.qthreshold; - strlcpy(loginfo.prefix, prefix, sizeof(loginfo.prefix)); - } - - ebt_ulog_packet(net, hooknum, skb, in, out, &loginfo, prefix); -} - -static unsigned int -ebt_ulog_tg(struct sk_buff *skb, const struct xt_action_param *par) -{ - struct net *net = dev_net(par->in ? par->in : par->out); - - ebt_ulog_packet(net, par->hooknum, skb, par->in, par->out, - par->targinfo, NULL); - return EBT_CONTINUE; -} - -static int ebt_ulog_tg_check(const struct xt_tgchk_param *par) -{ - struct ebt_ulog_info *uloginfo = par->targinfo; - - if (!par->net->xt.ebt_ulog_warn_deprecated) { - pr_info("ebt_ulog is deprecated and it will be removed soon, " - "use ebt_nflog instead\n"); - par->net->xt.ebt_ulog_warn_deprecated = true; - } - - if (uloginfo->nlgroup > 31) - return -EINVAL; - - uloginfo->prefix[EBT_ULOG_PREFIX_LEN - 1] = '\0'; - - if (uloginfo->qthreshold > EBT_ULOG_MAX_QLEN) - uloginfo->qthreshold = EBT_ULOG_MAX_QLEN; - - return 0; -} - -static struct xt_target ebt_ulog_tg_reg __read_mostly = { - .name = "ulog", - .revision = 0, - .family = NFPROTO_BRIDGE, - .target = ebt_ulog_tg, - .checkentry = ebt_ulog_tg_check, - .targetsize = sizeof(struct ebt_ulog_info), - .me = THIS_MODULE, -}; - -static struct nf_logger ebt_ulog_logger __read_mostly = { - .name = "ebt_ulog", - .logfn = &ebt_log_packet, - .me = THIS_MODULE, -}; - -static int __net_init ebt_ulog_net_init(struct net *net) -{ - int i; - struct ebt_ulog_net *ebt = ebt_ulog_pernet(net); - - struct netlink_kernel_cfg cfg = { - .groups = EBT_ULOG_MAXNLGROUPS, - }; - - /* initialize ulog_buffers */ - for (i = 0; i < EBT_ULOG_MAXNLGROUPS; i++) { - ebt->nlgroup[i] = i; - setup_timer(&ebt->ulog_buffers[i].timer, ulog_timer, - (unsigned long)&ebt->nlgroup[i]); - spin_lock_init(&ebt->ulog_buffers[i].lock); - } - - ebt->ebtulognl = netlink_kernel_create(net, NETLINK_NFLOG, &cfg); - if (!ebt->ebtulognl) - return -ENOMEM; - - nf_log_set(net, NFPROTO_BRIDGE, &ebt_ulog_logger); - return 0; -} - -static void __net_exit ebt_ulog_net_fini(struct net *net) -{ - int i; - struct ebt_ulog_net *ebt = ebt_ulog_pernet(net); - - nf_log_unset(net, &ebt_ulog_logger); - for (i = 0; i < EBT_ULOG_MAXNLGROUPS; i++) { - ebt_ulog_buff_t *ub = &ebt->ulog_buffers[i]; - del_timer(&ub->timer); - - if (ub->skb) { - kfree_skb(ub->skb); - ub->skb = NULL; - } - } - netlink_kernel_release(ebt->ebtulognl); -} - -static struct pernet_operations ebt_ulog_net_ops = { - .init = ebt_ulog_net_init, - .exit = ebt_ulog_net_fini, - .id = &ebt_ulog_net_id, - .size = sizeof(struct ebt_ulog_net), -}; - -static int __init ebt_ulog_init(void) -{ - int ret; - - if (nlbufsiz >= 128*1024) { - pr_warn("Netlink buffer has to be <= 128kB," - "please try a smaller nlbufsiz parameter.\n"); - return -EINVAL; - } - - ret = register_pernet_subsys(&ebt_ulog_net_ops); - if (ret) - goto out_pernet; - - ret = xt_register_target(&ebt_ulog_tg_reg); - if (ret) - goto out_target; - - nf_log_register(NFPROTO_BRIDGE, &ebt_ulog_logger); - - return 0; - -out_target: - unregister_pernet_subsys(&ebt_ulog_net_ops); -out_pernet: - return ret; -} - -static void __exit ebt_ulog_fini(void) -{ - nf_log_unregister(&ebt_ulog_logger); - xt_unregister_target(&ebt_ulog_tg_reg); - unregister_pernet_subsys(&ebt_ulog_net_ops); -} - -module_init(ebt_ulog_init); -module_exit(ebt_ulog_fini); -MODULE_LICENSE("GPL"); -MODULE_AUTHOR("Bart De Schuymer <bdschuym@pandora.be>"); -MODULE_DESCRIPTION("Ebtables: Packet logging to netlink using ULOG"); diff --git a/net/bridge/netfilter/nf_log_bridge.c b/net/bridge/netfilter/nf_log_bridge.c new file mode 100644 index 000000000000..5d9953a90929 --- /dev/null +++ b/net/bridge/netfilter/nf_log_bridge.c @@ -0,0 +1,96 @@ +/* + * (C) 2014 by Pablo Neira Ayuso <pablo@netfilter.org> + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + */ + +#include <linux/module.h> +#include <linux/spinlock.h> +#include <linux/skbuff.h> +#include <linux/if_bridge.h> +#include <linux/ip.h> +#include <net/route.h> + +#include <linux/netfilter.h> +#include <net/netfilter/nf_log.h> + +static void nf_log_bridge_packet(struct net *net, u_int8_t pf, + unsigned int hooknum, + const struct sk_buff *skb, + const struct net_device *in, + const struct net_device *out, + const struct nf_loginfo *loginfo, + const char *prefix) +{ + switch (eth_hdr(skb)->h_proto) { + case htons(ETH_P_IP): + nf_log_packet(net, NFPROTO_IPV4, hooknum, skb, in, out, + loginfo, "%s", prefix); + break; + case htons(ETH_P_IPV6): + nf_log_packet(net, NFPROTO_IPV6, hooknum, skb, in, out, + loginfo, "%s", prefix); + break; + case htons(ETH_P_ARP): + case htons(ETH_P_RARP): + nf_log_packet(net, NFPROTO_ARP, hooknum, skb, in, out, + loginfo, "%s", prefix); + break; + } +} + +static struct nf_logger nf_bridge_logger __read_mostly = { + .name = "nf_log_bridge", + .type = NF_LOG_TYPE_LOG, + .logfn = nf_log_bridge_packet, + .me = THIS_MODULE, +}; + +static int __net_init nf_log_bridge_net_init(struct net *net) +{ + nf_log_set(net, NFPROTO_BRIDGE, &nf_bridge_logger); + return 0; +} + +static void __net_exit nf_log_bridge_net_exit(struct net *net) +{ + nf_log_unset(net, &nf_bridge_logger); +} + +static struct pernet_operations nf_log_bridge_net_ops = { + .init = nf_log_bridge_net_init, + .exit = nf_log_bridge_net_exit, +}; + +static int __init nf_log_bridge_init(void) +{ + int ret; + + /* Request to load the real packet loggers. */ + nf_logger_request_module(NFPROTO_IPV4, NF_LOG_TYPE_LOG); + nf_logger_request_module(NFPROTO_IPV6, NF_LOG_TYPE_LOG); + nf_logger_request_module(NFPROTO_ARP, NF_LOG_TYPE_LOG); + + ret = register_pernet_subsys(&nf_log_bridge_net_ops); + if (ret < 0) + return ret; + + nf_log_register(NFPROTO_BRIDGE, &nf_bridge_logger); + return 0; +} + +static void __exit nf_log_bridge_exit(void) +{ + unregister_pernet_subsys(&nf_log_bridge_net_ops); + nf_log_unregister(&nf_bridge_logger); +} + +module_init(nf_log_bridge_init); +module_exit(nf_log_bridge_exit); + +MODULE_AUTHOR("Pablo Neira Ayuso <pablo@netfilter.org>"); +MODULE_DESCRIPTION("Netfilter bridge packet logging"); +MODULE_LICENSE("GPL"); +MODULE_ALIAS_NF_LOGGER(AF_BRIDGE, 0); diff --git a/net/bridge/netfilter/nft_reject_bridge.c b/net/bridge/netfilter/nft_reject_bridge.c new file mode 100644 index 000000000000..ee3ffe93e14e --- /dev/null +++ b/net/bridge/netfilter/nft_reject_bridge.c @@ -0,0 +1,67 @@ +/* + * Copyright (c) 2014 Pablo Neira Ayuso <pablo@netfilter.org> + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + */ + +#include <linux/kernel.h> +#include <linux/init.h> +#include <linux/module.h> +#include <linux/netlink.h> +#include <linux/netfilter.h> +#include <linux/netfilter/nf_tables.h> +#include <net/netfilter/nf_tables.h> +#include <net/netfilter/nft_reject.h> + +static void nft_reject_bridge_eval(const struct nft_expr *expr, + struct nft_data data[NFT_REG_MAX + 1], + const struct nft_pktinfo *pkt) +{ + switch (eth_hdr(pkt->skb)->h_proto) { + case htons(ETH_P_IP): + return nft_reject_ipv4_eval(expr, data, pkt); + case htons(ETH_P_IPV6): + return nft_reject_ipv6_eval(expr, data, pkt); + default: + /* No explicit way to reject this protocol, drop it. */ + data[NFT_REG_VERDICT].verdict = NF_DROP; + break; + } +} + +static struct nft_expr_type nft_reject_bridge_type; +static const struct nft_expr_ops nft_reject_bridge_ops = { + .type = &nft_reject_bridge_type, + .size = NFT_EXPR_SIZE(sizeof(struct nft_reject)), + .eval = nft_reject_bridge_eval, + .init = nft_reject_init, + .dump = nft_reject_dump, +}; + +static struct nft_expr_type nft_reject_bridge_type __read_mostly = { + .family = NFPROTO_BRIDGE, + .name = "reject", + .ops = &nft_reject_bridge_ops, + .policy = nft_reject_policy, + .maxattr = NFTA_REJECT_MAX, + .owner = THIS_MODULE, +}; + +static int __init nft_reject_bridge_module_init(void) +{ + return nft_register_expr(&nft_reject_bridge_type); +} + +static void __exit nft_reject_bridge_module_exit(void) +{ + nft_unregister_expr(&nft_reject_bridge_type); +} + +module_init(nft_reject_bridge_module_init); +module_exit(nft_reject_bridge_module_exit); + +MODULE_LICENSE("GPL"); +MODULE_AUTHOR("Pablo Neira Ayuso <pablo@netfilter.org>"); +MODULE_ALIAS_NFT_AF_EXPR(AF_BRIDGE, "reject"); diff --git a/net/caif/caif_socket.c b/net/caif/caif_socket.c index e8437094d15f..43f750e88e19 100644 --- a/net/caif/caif_socket.c +++ b/net/caif/caif_socket.c @@ -908,8 +908,7 @@ static int caif_release(struct socket *sock) sock->sk = NULL; WARN_ON(IS_ERR(cf_sk->debugfs_socket_dir)); - if (cf_sk->debugfs_socket_dir != NULL) - debugfs_remove_recursive(cf_sk->debugfs_socket_dir); + debugfs_remove_recursive(cf_sk->debugfs_socket_dir); lock_sock(&(cf_sk->sk)); sk->sk_state = CAIF_DISCONNECTED; diff --git a/net/caif/cfctrl.c b/net/caif/cfctrl.c index 0f455227da83..f5afda1abc76 100644 --- a/net/caif/cfctrl.c +++ b/net/caif/cfctrl.c @@ -547,7 +547,6 @@ static int cfctrl_recv(struct cflayer *layer, struct cfpkt *pkt) default: pr_err("Unrecognized Control Frame\n"); goto error; - break; } ret = 0; error: diff --git a/net/core/dev.c b/net/core/dev.c index 367a586d0c8a..1c15b189c52b 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -132,6 +132,7 @@ #include <linux/hashtable.h> #include <linux/vmalloc.h> #include <linux/if_macvlan.h> +#include <linux/errqueue.h> #include "net-sysfs.h" @@ -1085,6 +1086,7 @@ static int dev_get_valid_name(struct net *net, */ int dev_change_name(struct net_device *dev, const char *newname) { + unsigned char old_assign_type; char oldname[IFNAMSIZ]; int err = 0; int ret; @@ -1112,10 +1114,17 @@ int dev_change_name(struct net_device *dev, const char *newname) return err; } + if (oldname[0] && !strchr(oldname, '%')) + netdev_info(dev, "renamed from %s\n", oldname); + + old_assign_type = dev->name_assign_type; + dev->name_assign_type = NET_NAME_RENAMED; + rollback: ret = device_rename(&dev->dev, dev->name); if (ret) { memcpy(dev->name, oldname, IFNAMSIZ); + dev->name_assign_type = old_assign_type; write_seqcount_end(&devnet_rename_seq); return ret; } @@ -1144,6 +1153,8 @@ rollback: write_seqcount_begin(&devnet_rename_seq); memcpy(dev->name, oldname, IFNAMSIZ); memcpy(oldname, newname, IFNAMSIZ); + dev->name_assign_type = old_assign_type; + old_assign_type = NET_NAME_RENAMED; goto rollback; } else { pr_err("%s: name change rollback failed: %d\n", @@ -2316,7 +2327,7 @@ __be16 skb_network_protocol(struct sk_buff *skb, int *depth) */ if (type == htons(ETH_P_8021Q) || type == htons(ETH_P_8021AD)) { if (vlan_depth) { - if (unlikely(WARN_ON(vlan_depth < VLAN_HLEN))) + if (WARN_ON(vlan_depth < VLAN_HLEN)) return 0; vlan_depth -= VLAN_HLEN; } else { @@ -2414,8 +2425,8 @@ struct sk_buff *__skb_gso_segment(struct sk_buff *skb, skb_warn_bad_offload(skb); - if (skb_header_cloned(skb) && - (err = pskb_expand_head(skb, 0, 0, GFP_ATOMIC))) + err = skb_cow_head(skb, 0); + if (err < 0) return ERR_PTR(err); } @@ -2745,8 +2756,8 @@ static inline int __dev_xmit_skb(struct sk_buff *skb, struct Qdisc *q, /* * Heuristic to force contended enqueues to serialize on a * separate lock before trying to get qdisc main lock. - * This permits __QDISC_STATE_RUNNING owner to get the lock more often - * and dequeue packets faster. + * This permits __QDISC___STATE_RUNNING owner to get the lock more + * often and dequeue packets faster. */ contended = qdisc_is_running(q); if (unlikely(contended)) @@ -2866,6 +2877,9 @@ static int __dev_queue_xmit(struct sk_buff *skb, void *accel_priv) skb_reset_mac_header(skb); + if (unlikely(skb_shinfo(skb)->tx_flags & SKBTX_SCHED_TSTAMP)) + __skb_tstamp_tx(skb, NULL, skb->sk, SCM_TSTAMP_SCHED); + /* Disable soft irqs for various locks below. Also * stops preemption for RCU. */ @@ -5440,13 +5454,9 @@ int __dev_change_flags(struct net_device *dev, unsigned int flags) */ ret = 0; - if ((old_flags ^ flags) & IFF_UP) { /* Bit is different ? */ + if ((old_flags ^ flags) & IFF_UP) ret = ((old_flags & IFF_UP) ? __dev_close : __dev_open)(dev); - if (!ret) - dev_set_rx_mode(dev); - } - if ((flags ^ dev->gflags) & IFF_PROMISC) { int inc = (flags & IFF_PROMISC) ? 1 : -1; unsigned int old_flags = dev->flags; @@ -6446,17 +6456,19 @@ void netdev_freemem(struct net_device *dev) /** * alloc_netdev_mqs - allocate network device - * @sizeof_priv: size of private data to allocate space for - * @name: device name format string - * @setup: callback to initialize device - * @txqs: the number of TX subqueues to allocate - * @rxqs: the number of RX subqueues to allocate + * @sizeof_priv: size of private data to allocate space for + * @name: device name format string + * @name_assign_type: origin of device name + * @setup: callback to initialize device + * @txqs: the number of TX subqueues to allocate + * @rxqs: the number of RX subqueues to allocate * * Allocates a struct net_device with private data area for driver use * and performs basic initialization. Also allocates subqueue structs * for each queue on the device. */ struct net_device *alloc_netdev_mqs(int sizeof_priv, const char *name, + unsigned char name_assign_type, void (*setup)(struct net_device *), unsigned int txqs, unsigned int rxqs) { @@ -6535,6 +6547,7 @@ struct net_device *alloc_netdev_mqs(int sizeof_priv, const char *name, #endif strcpy(dev->name, name); + dev->name_assign_type = name_assign_type; dev->group = INIT_NETDEV_GROUP; if (!dev->ethtool_ops) dev->ethtool_ops = &default_ethtool_ops; @@ -6946,12 +6959,14 @@ static int __netdev_printk(const char *level, const struct net_device *dev, if (dev && dev->dev.parent) { r = dev_printk_emit(level[1] - '0', dev->dev.parent, - "%s %s %s: %pV", + "%s %s %s%s: %pV", dev_driver_string(dev->dev.parent), dev_name(dev->dev.parent), - netdev_name(dev), vaf); + netdev_name(dev), netdev_reg_state(dev), + vaf); } else if (dev) { - r = printk("%s%s: %pV", level, netdev_name(dev), vaf); + r = printk("%s%s%s: %pV", level, netdev_name(dev), + netdev_reg_state(dev), vaf); } else { r = printk("%s(NULL net_device): %pV", level, vaf); } @@ -7103,7 +7118,7 @@ static void __net_exit default_device_exit_batch(struct list_head *net_list) rtnl_lock_unregistering(net_list); list_for_each_entry(net, net_list, exit_list) { for_each_netdev_reverse(net, dev) { - if (dev->rtnl_link_ops) + if (dev->rtnl_link_ops && dev->rtnl_link_ops->dellink) dev->rtnl_link_ops->dellink(dev, &dev_kill_list); else unregister_netdevice_queue(dev, &dev_kill_list); diff --git a/net/core/drop_monitor.c b/net/core/drop_monitor.c index e70301eb7a4a..50f9a9db5792 100644 --- a/net/core/drop_monitor.c +++ b/net/core/drop_monitor.c @@ -289,10 +289,8 @@ static int net_dm_cmd_trace(struct sk_buff *skb, switch (info->genlhdr->cmd) { case NET_DM_CMD_START: return set_all_monitor_traces(TRACE_ON); - break; case NET_DM_CMD_STOP: return set_all_monitor_traces(TRACE_OFF); - break; } return -ENOTSUPP; diff --git a/net/core/filter.c b/net/core/filter.c index 1dbf6462f766..d814b8a89d0f 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -18,7 +18,7 @@ * 2 of the License, or (at your option) any later version. * * Andi Kleen - Fix a few bad bugs and races. - * Kris Katterjohn - Added many additional checks in sk_chk_filter() + * Kris Katterjohn - Added many additional checks in bpf_check_classic() */ #include <linux/module.h> @@ -45,54 +45,6 @@ #include <linux/seccomp.h> #include <linux/if_vlan.h> -/* Registers */ -#define BPF_R0 regs[BPF_REG_0] -#define BPF_R1 regs[BPF_REG_1] -#define BPF_R2 regs[BPF_REG_2] -#define BPF_R3 regs[BPF_REG_3] -#define BPF_R4 regs[BPF_REG_4] -#define BPF_R5 regs[BPF_REG_5] -#define BPF_R6 regs[BPF_REG_6] -#define BPF_R7 regs[BPF_REG_7] -#define BPF_R8 regs[BPF_REG_8] -#define BPF_R9 regs[BPF_REG_9] -#define BPF_R10 regs[BPF_REG_10] - -/* Named registers */ -#define DST regs[insn->dst_reg] -#define SRC regs[insn->src_reg] -#define FP regs[BPF_REG_FP] -#define ARG1 regs[BPF_REG_ARG1] -#define CTX regs[BPF_REG_CTX] -#define IMM insn->imm - -/* No hurry in this branch - * - * Exported for the bpf jit load helper. - */ -void *bpf_internal_load_pointer_neg_helper(const struct sk_buff *skb, int k, unsigned int size) -{ - u8 *ptr = NULL; - - if (k >= SKF_NET_OFF) - ptr = skb_network_header(skb) + k - SKF_NET_OFF; - else if (k >= SKF_LL_OFF) - ptr = skb_mac_header(skb) + k - SKF_LL_OFF; - if (ptr >= skb->head && ptr + size <= skb_tail_pointer(skb)) - return ptr; - - return NULL; -} - -static inline void *load_pointer(const struct sk_buff *skb, int k, - unsigned int size, void *buffer) -{ - if (k >= 0) - return skb_header_pointer(skb, k, size, buffer); - - return bpf_internal_load_pointer_neg_helper(skb, k, size); -} - /** * sk_filter - run a packet through a socket filter * @sk: sock associated with &sk_buff @@ -135,451 +87,6 @@ int sk_filter(struct sock *sk, struct sk_buff *skb) } EXPORT_SYMBOL(sk_filter); -/* Base function for offset calculation. Needs to go into .text section, - * therefore keeping it non-static as well; will also be used by JITs - * anyway later on, so do not let the compiler omit it. - */ -noinline u64 __bpf_call_base(u64 r1, u64 r2, u64 r3, u64 r4, u64 r5) -{ - return 0; -} - -/** - * __sk_run_filter - run a filter on a given context - * @ctx: buffer to run the filter on - * @insn: filter to apply - * - * Decode and apply filter instructions to the skb->data. Return length to - * keep, 0 for none. @ctx is the data we are operating on, @insn is the - * array of filter instructions. - */ -static unsigned int __sk_run_filter(void *ctx, const struct sock_filter_int *insn) -{ - u64 stack[MAX_BPF_STACK / sizeof(u64)]; - u64 regs[MAX_BPF_REG], tmp; - static const void *jumptable[256] = { - [0 ... 255] = &&default_label, - /* Now overwrite non-defaults ... */ - /* 32 bit ALU operations */ - [BPF_ALU | BPF_ADD | BPF_X] = &&ALU_ADD_X, - [BPF_ALU | BPF_ADD | BPF_K] = &&ALU_ADD_K, - [BPF_ALU | BPF_SUB | BPF_X] = &&ALU_SUB_X, - [BPF_ALU | BPF_SUB | BPF_K] = &&ALU_SUB_K, - [BPF_ALU | BPF_AND | BPF_X] = &&ALU_AND_X, - [BPF_ALU | BPF_AND | BPF_K] = &&ALU_AND_K, - [BPF_ALU | BPF_OR | BPF_X] = &&ALU_OR_X, - [BPF_ALU | BPF_OR | BPF_K] = &&ALU_OR_K, - [BPF_ALU | BPF_LSH | BPF_X] = &&ALU_LSH_X, - [BPF_ALU | BPF_LSH | BPF_K] = &&ALU_LSH_K, - [BPF_ALU | BPF_RSH | BPF_X] = &&ALU_RSH_X, - [BPF_ALU | BPF_RSH | BPF_K] = &&ALU_RSH_K, - [BPF_ALU | BPF_XOR | BPF_X] = &&ALU_XOR_X, - [BPF_ALU | BPF_XOR | BPF_K] = &&ALU_XOR_K, - [BPF_ALU | BPF_MUL | BPF_X] = &&ALU_MUL_X, - [BPF_ALU | BPF_MUL | BPF_K] = &&ALU_MUL_K, - [BPF_ALU | BPF_MOV | BPF_X] = &&ALU_MOV_X, - [BPF_ALU | BPF_MOV | BPF_K] = &&ALU_MOV_K, - [BPF_ALU | BPF_DIV | BPF_X] = &&ALU_DIV_X, - [BPF_ALU | BPF_DIV | BPF_K] = &&ALU_DIV_K, - [BPF_ALU | BPF_MOD | BPF_X] = &&ALU_MOD_X, - [BPF_ALU | BPF_MOD | BPF_K] = &&ALU_MOD_K, - [BPF_ALU | BPF_NEG] = &&ALU_NEG, - [BPF_ALU | BPF_END | BPF_TO_BE] = &&ALU_END_TO_BE, - [BPF_ALU | BPF_END | BPF_TO_LE] = &&ALU_END_TO_LE, - /* 64 bit ALU operations */ - [BPF_ALU64 | BPF_ADD | BPF_X] = &&ALU64_ADD_X, - [BPF_ALU64 | BPF_ADD | BPF_K] = &&ALU64_ADD_K, - [BPF_ALU64 | BPF_SUB | BPF_X] = &&ALU64_SUB_X, - [BPF_ALU64 | BPF_SUB | BPF_K] = &&ALU64_SUB_K, - [BPF_ALU64 | BPF_AND | BPF_X] = &&ALU64_AND_X, - [BPF_ALU64 | BPF_AND | BPF_K] = &&ALU64_AND_K, - [BPF_ALU64 | BPF_OR | BPF_X] = &&ALU64_OR_X, - [BPF_ALU64 | BPF_OR | BPF_K] = &&ALU64_OR_K, - [BPF_ALU64 | BPF_LSH | BPF_X] = &&ALU64_LSH_X, - [BPF_ALU64 | BPF_LSH | BPF_K] = &&ALU64_LSH_K, - [BPF_ALU64 | BPF_RSH | BPF_X] = &&ALU64_RSH_X, - [BPF_ALU64 | BPF_RSH | BPF_K] = &&ALU64_RSH_K, - [BPF_ALU64 | BPF_XOR | BPF_X] = &&ALU64_XOR_X, - [BPF_ALU64 | BPF_XOR | BPF_K] = &&ALU64_XOR_K, - [BPF_ALU64 | BPF_MUL | BPF_X] = &&ALU64_MUL_X, - [BPF_ALU64 | BPF_MUL | BPF_K] = &&ALU64_MUL_K, - [BPF_ALU64 | BPF_MOV | BPF_X] = &&ALU64_MOV_X, - [BPF_ALU64 | BPF_MOV | BPF_K] = &&ALU64_MOV_K, - [BPF_ALU64 | BPF_ARSH | BPF_X] = &&ALU64_ARSH_X, - [BPF_ALU64 | BPF_ARSH | BPF_K] = &&ALU64_ARSH_K, - [BPF_ALU64 | BPF_DIV | BPF_X] = &&ALU64_DIV_X, - [BPF_ALU64 | BPF_DIV | BPF_K] = &&ALU64_DIV_K, - [BPF_ALU64 | BPF_MOD | BPF_X] = &&ALU64_MOD_X, - [BPF_ALU64 | BPF_MOD | BPF_K] = &&ALU64_MOD_K, - [BPF_ALU64 | BPF_NEG] = &&ALU64_NEG, - /* Call instruction */ - [BPF_JMP | BPF_CALL] = &&JMP_CALL, - /* Jumps */ - [BPF_JMP | BPF_JA] = &&JMP_JA, - [BPF_JMP | BPF_JEQ | BPF_X] = &&JMP_JEQ_X, - [BPF_JMP | BPF_JEQ | BPF_K] = &&JMP_JEQ_K, - [BPF_JMP | BPF_JNE | BPF_X] = &&JMP_JNE_X, - [BPF_JMP | BPF_JNE | BPF_K] = &&JMP_JNE_K, - [BPF_JMP | BPF_JGT | BPF_X] = &&JMP_JGT_X, - [BPF_JMP | BPF_JGT | BPF_K] = &&JMP_JGT_K, - [BPF_JMP | BPF_JGE | BPF_X] = &&JMP_JGE_X, - [BPF_JMP | BPF_JGE | BPF_K] = &&JMP_JGE_K, - [BPF_JMP | BPF_JSGT | BPF_X] = &&JMP_JSGT_X, - [BPF_JMP | BPF_JSGT | BPF_K] = &&JMP_JSGT_K, - [BPF_JMP | BPF_JSGE | BPF_X] = &&JMP_JSGE_X, - [BPF_JMP | BPF_JSGE | BPF_K] = &&JMP_JSGE_K, - [BPF_JMP | BPF_JSET | BPF_X] = &&JMP_JSET_X, - [BPF_JMP | BPF_JSET | BPF_K] = &&JMP_JSET_K, - /* Program return */ - [BPF_JMP | BPF_EXIT] = &&JMP_EXIT, - /* Store instructions */ - [BPF_STX | BPF_MEM | BPF_B] = &&STX_MEM_B, - [BPF_STX | BPF_MEM | BPF_H] = &&STX_MEM_H, - [BPF_STX | BPF_MEM | BPF_W] = &&STX_MEM_W, - [BPF_STX | BPF_MEM | BPF_DW] = &&STX_MEM_DW, - [BPF_STX | BPF_XADD | BPF_W] = &&STX_XADD_W, - [BPF_STX | BPF_XADD | BPF_DW] = &&STX_XADD_DW, - [BPF_ST | BPF_MEM | BPF_B] = &&ST_MEM_B, - [BPF_ST | BPF_MEM | BPF_H] = &&ST_MEM_H, - [BPF_ST | BPF_MEM | BPF_W] = &&ST_MEM_W, - [BPF_ST | BPF_MEM | BPF_DW] = &&ST_MEM_DW, - /* Load instructions */ - [BPF_LDX | BPF_MEM | BPF_B] = &&LDX_MEM_B, - [BPF_LDX | BPF_MEM | BPF_H] = &&LDX_MEM_H, - [BPF_LDX | BPF_MEM | BPF_W] = &&LDX_MEM_W, - [BPF_LDX | BPF_MEM | BPF_DW] = &&LDX_MEM_DW, - [BPF_LD | BPF_ABS | BPF_W] = &&LD_ABS_W, - [BPF_LD | BPF_ABS | BPF_H] = &&LD_ABS_H, - [BPF_LD | BPF_ABS | BPF_B] = &&LD_ABS_B, - [BPF_LD | BPF_IND | BPF_W] = &&LD_IND_W, - [BPF_LD | BPF_IND | BPF_H] = &&LD_IND_H, - [BPF_LD | BPF_IND | BPF_B] = &&LD_IND_B, - }; - void *ptr; - int off; - -#define CONT ({ insn++; goto select_insn; }) -#define CONT_JMP ({ insn++; goto select_insn; }) - - FP = (u64) (unsigned long) &stack[ARRAY_SIZE(stack)]; - ARG1 = (u64) (unsigned long) ctx; - - /* Registers used in classic BPF programs need to be reset first. */ - regs[BPF_REG_A] = 0; - regs[BPF_REG_X] = 0; - -select_insn: - goto *jumptable[insn->code]; - - /* ALU */ -#define ALU(OPCODE, OP) \ - ALU64_##OPCODE##_X: \ - DST = DST OP SRC; \ - CONT; \ - ALU_##OPCODE##_X: \ - DST = (u32) DST OP (u32) SRC; \ - CONT; \ - ALU64_##OPCODE##_K: \ - DST = DST OP IMM; \ - CONT; \ - ALU_##OPCODE##_K: \ - DST = (u32) DST OP (u32) IMM; \ - CONT; - - ALU(ADD, +) - ALU(SUB, -) - ALU(AND, &) - ALU(OR, |) - ALU(LSH, <<) - ALU(RSH, >>) - ALU(XOR, ^) - ALU(MUL, *) -#undef ALU - ALU_NEG: - DST = (u32) -DST; - CONT; - ALU64_NEG: - DST = -DST; - CONT; - ALU_MOV_X: - DST = (u32) SRC; - CONT; - ALU_MOV_K: - DST = (u32) IMM; - CONT; - ALU64_MOV_X: - DST = SRC; - CONT; - ALU64_MOV_K: - DST = IMM; - CONT; - ALU64_ARSH_X: - (*(s64 *) &DST) >>= SRC; - CONT; - ALU64_ARSH_K: - (*(s64 *) &DST) >>= IMM; - CONT; - ALU64_MOD_X: - if (unlikely(SRC == 0)) - return 0; - tmp = DST; - DST = do_div(tmp, SRC); - CONT; - ALU_MOD_X: - if (unlikely(SRC == 0)) - return 0; - tmp = (u32) DST; - DST = do_div(tmp, (u32) SRC); - CONT; - ALU64_MOD_K: - tmp = DST; - DST = do_div(tmp, IMM); - CONT; - ALU_MOD_K: - tmp = (u32) DST; - DST = do_div(tmp, (u32) IMM); - CONT; - ALU64_DIV_X: - if (unlikely(SRC == 0)) - return 0; - do_div(DST, SRC); - CONT; - ALU_DIV_X: - if (unlikely(SRC == 0)) - return 0; - tmp = (u32) DST; - do_div(tmp, (u32) SRC); - DST = (u32) tmp; - CONT; - ALU64_DIV_K: - do_div(DST, IMM); - CONT; - ALU_DIV_K: - tmp = (u32) DST; - do_div(tmp, (u32) IMM); - DST = (u32) tmp; - CONT; - ALU_END_TO_BE: - switch (IMM) { - case 16: - DST = (__force u16) cpu_to_be16(DST); - break; - case 32: - DST = (__force u32) cpu_to_be32(DST); - break; - case 64: - DST = (__force u64) cpu_to_be64(DST); - break; - } - CONT; - ALU_END_TO_LE: - switch (IMM) { - case 16: - DST = (__force u16) cpu_to_le16(DST); - break; - case 32: - DST = (__force u32) cpu_to_le32(DST); - break; - case 64: - DST = (__force u64) cpu_to_le64(DST); - break; - } - CONT; - - /* CALL */ - JMP_CALL: - /* Function call scratches BPF_R1-BPF_R5 registers, - * preserves BPF_R6-BPF_R9, and stores return value - * into BPF_R0. - */ - BPF_R0 = (__bpf_call_base + insn->imm)(BPF_R1, BPF_R2, BPF_R3, - BPF_R4, BPF_R5); - CONT; - - /* JMP */ - JMP_JA: - insn += insn->off; - CONT; - JMP_JEQ_X: - if (DST == SRC) { - insn += insn->off; - CONT_JMP; - } - CONT; - JMP_JEQ_K: - if (DST == IMM) { - insn += insn->off; - CONT_JMP; - } - CONT; - JMP_JNE_X: - if (DST != SRC) { - insn += insn->off; - CONT_JMP; - } - CONT; - JMP_JNE_K: - if (DST != IMM) { - insn += insn->off; - CONT_JMP; - } - CONT; - JMP_JGT_X: - if (DST > SRC) { - insn += insn->off; - CONT_JMP; - } - CONT; - JMP_JGT_K: - if (DST > IMM) { - insn += insn->off; - CONT_JMP; - } - CONT; - JMP_JGE_X: - if (DST >= SRC) { - insn += insn->off; - CONT_JMP; - } - CONT; - JMP_JGE_K: - if (DST >= IMM) { - insn += insn->off; - CONT_JMP; - } - CONT; - JMP_JSGT_X: - if (((s64) DST) > ((s64) SRC)) { - insn += insn->off; - CONT_JMP; - } - CONT; - JMP_JSGT_K: - if (((s64) DST) > ((s64) IMM)) { - insn += insn->off; - CONT_JMP; - } - CONT; - JMP_JSGE_X: - if (((s64) DST) >= ((s64) SRC)) { - insn += insn->off; - CONT_JMP; - } - CONT; - JMP_JSGE_K: - if (((s64) DST) >= ((s64) IMM)) { - insn += insn->off; - CONT_JMP; - } - CONT; - JMP_JSET_X: - if (DST & SRC) { - insn += insn->off; - CONT_JMP; - } - CONT; - JMP_JSET_K: - if (DST & IMM) { - insn += insn->off; - CONT_JMP; - } - CONT; - JMP_EXIT: - return BPF_R0; - - /* STX and ST and LDX*/ -#define LDST(SIZEOP, SIZE) \ - STX_MEM_##SIZEOP: \ - *(SIZE *)(unsigned long) (DST + insn->off) = SRC; \ - CONT; \ - ST_MEM_##SIZEOP: \ - *(SIZE *)(unsigned long) (DST + insn->off) = IMM; \ - CONT; \ - LDX_MEM_##SIZEOP: \ - DST = *(SIZE *)(unsigned long) (SRC + insn->off); \ - CONT; - - LDST(B, u8) - LDST(H, u16) - LDST(W, u32) - LDST(DW, u64) -#undef LDST - STX_XADD_W: /* lock xadd *(u32 *)(dst_reg + off16) += src_reg */ - atomic_add((u32) SRC, (atomic_t *)(unsigned long) - (DST + insn->off)); - CONT; - STX_XADD_DW: /* lock xadd *(u64 *)(dst_reg + off16) += src_reg */ - atomic64_add((u64) SRC, (atomic64_t *)(unsigned long) - (DST + insn->off)); - CONT; - LD_ABS_W: /* BPF_R0 = ntohl(*(u32 *) (skb->data + imm32)) */ - off = IMM; -load_word: - /* BPF_LD + BPD_ABS and BPF_LD + BPF_IND insns are - * only appearing in the programs where ctx == - * skb. All programs keep 'ctx' in regs[BPF_REG_CTX] - * == BPF_R6, sk_convert_filter() saves it in BPF_R6, - * internal BPF verifier will check that BPF_R6 == - * ctx. - * - * BPF_ABS and BPF_IND are wrappers of function calls, - * so they scratch BPF_R1-BPF_R5 registers, preserve - * BPF_R6-BPF_R9, and store return value into BPF_R0. - * - * Implicit input: - * ctx == skb == BPF_R6 == CTX - * - * Explicit input: - * SRC == any register - * IMM == 32-bit immediate - * - * Output: - * BPF_R0 - 8/16/32-bit skb data converted to cpu endianness - */ - - ptr = load_pointer((struct sk_buff *) (unsigned long) CTX, off, 4, &tmp); - if (likely(ptr != NULL)) { - BPF_R0 = get_unaligned_be32(ptr); - CONT; - } - - return 0; - LD_ABS_H: /* BPF_R0 = ntohs(*(u16 *) (skb->data + imm32)) */ - off = IMM; -load_half: - ptr = load_pointer((struct sk_buff *) (unsigned long) CTX, off, 2, &tmp); - if (likely(ptr != NULL)) { - BPF_R0 = get_unaligned_be16(ptr); - CONT; - } - - return 0; - LD_ABS_B: /* BPF_R0 = *(u8 *) (skb->data + imm32) */ - off = IMM; -load_byte: - ptr = load_pointer((struct sk_buff *) (unsigned long) CTX, off, 1, &tmp); - if (likely(ptr != NULL)) { - BPF_R0 = *(u8 *)ptr; - CONT; - } - - return 0; - LD_IND_W: /* BPF_R0 = ntohl(*(u32 *) (skb->data + src_reg + imm32)) */ - off = IMM + SRC; - goto load_word; - LD_IND_H: /* BPF_R0 = ntohs(*(u16 *) (skb->data + src_reg + imm32)) */ - off = IMM + SRC; - goto load_half; - LD_IND_B: /* BPF_R0 = *(u8 *) (skb->data + src_reg + imm32) */ - off = IMM + SRC; - goto load_byte; - - default_label: - /* If we ever reach this, we have a bug somewhere. */ - WARN_RATELIMIT(1, "unknown opcode %02x\n", insn->code); - return 0; -} - /* Helper to find the offset of pkt_type in sk_buff structure. We want * to make sure its still a 3bit field starting at a byte boundary; * taken from arch/x86/net/bpf_jit_comp.c. @@ -667,9 +174,9 @@ static u64 __get_random_u32(u64 ctx, u64 a, u64 x, u64 r4, u64 r5) } static bool convert_bpf_extensions(struct sock_filter *fp, - struct sock_filter_int **insnp) + struct bpf_insn **insnp) { - struct sock_filter_int *insn = *insnp; + struct bpf_insn *insn = *insnp; switch (fp->k) { case SKF_AD_OFF + SKF_AD_PROTOCOL: @@ -805,7 +312,7 @@ static bool convert_bpf_extensions(struct sock_filter *fp, } /** - * sk_convert_filter - convert filter program + * bpf_convert_filter - convert filter program * @prog: the user passed filter program * @len: the length of the user passed filter program * @new_prog: buffer where converted program will be stored @@ -815,12 +322,12 @@ static bool convert_bpf_extensions(struct sock_filter *fp, * Conversion workflow: * * 1) First pass for calculating the new program length: - * sk_convert_filter(old_prog, old_len, NULL, &new_len) + * bpf_convert_filter(old_prog, old_len, NULL, &new_len) * * 2) 2nd pass to remap in two passes: 1st pass finds new * jump offsets, 2nd pass remapping: - * new_prog = kmalloc(sizeof(struct sock_filter_int) * new_len); - * sk_convert_filter(old_prog, old_len, new_prog, &new_len); + * new_prog = kmalloc(sizeof(struct bpf_insn) * new_len); + * bpf_convert_filter(old_prog, old_len, new_prog, &new_len); * * User BPF's register A is mapped to our BPF register 6, user BPF * register X is mapped to BPF register 7; frame pointer is always @@ -828,11 +335,11 @@ static bool convert_bpf_extensions(struct sock_filter *fp, * for socket filters: ctx == 'struct sk_buff *', for seccomp: * ctx == 'struct seccomp_data *'. */ -int sk_convert_filter(struct sock_filter *prog, int len, - struct sock_filter_int *new_prog, int *new_len) +int bpf_convert_filter(struct sock_filter *prog, int len, + struct bpf_insn *new_prog, int *new_len) { int new_flen = 0, pass = 0, target, i; - struct sock_filter_int *new_insn; + struct bpf_insn *new_insn; struct sock_filter *fp; int *addrs = NULL; u8 bpf_src; @@ -858,8 +365,8 @@ do_pass: new_insn++; for (i = 0; i < len; fp++, i++) { - struct sock_filter_int tmp_insns[6] = { }; - struct sock_filter_int *insn = tmp_insns; + struct bpf_insn tmp_insns[6] = { }; + struct bpf_insn *insn = tmp_insns; if (addrs) addrs[i] = new_insn - new_prog; @@ -1094,7 +601,7 @@ err: * a cell if not previously written, and we check all branches to be sure * a malicious user doesn't try to abuse us. */ -static int check_load_and_stores(struct sock_filter *filter, int flen) +static int check_load_and_stores(const struct sock_filter *filter, int flen) { u16 *masks, memvalid = 0; /* One bit per cell, 16 cells */ int pc, ret = 0; @@ -1214,7 +721,7 @@ static bool chk_code_allowed(u16 code_to_probe) } /** - * sk_chk_filter - verify socket filter code + * bpf_check_classic - verify socket filter code * @filter: filter to verify * @flen: length of filter * @@ -1227,7 +734,7 @@ static bool chk_code_allowed(u16 code_to_probe) * * Returns 0 if the rule set is legal or -EINVAL if not. */ -int sk_chk_filter(struct sock_filter *filter, unsigned int flen) +int bpf_check_classic(const struct sock_filter *filter, unsigned int flen) { bool anc_found; int pc; @@ -1237,7 +744,7 @@ int sk_chk_filter(struct sock_filter *filter, unsigned int flen) /* Check the filter code now */ for (pc = 0; pc < flen; pc++) { - struct sock_filter *ftest = &filter[pc]; + const struct sock_filter *ftest = &filter[pc]; /* May we actually operate on this code? */ if (!chk_code_allowed(ftest->code)) @@ -1301,12 +808,12 @@ int sk_chk_filter(struct sock_filter *filter, unsigned int flen) return -EINVAL; } -EXPORT_SYMBOL(sk_chk_filter); +EXPORT_SYMBOL(bpf_check_classic); -static int sk_store_orig_filter(struct sk_filter *fp, - const struct sock_fprog *fprog) +static int bpf_prog_store_orig_filter(struct bpf_prog *fp, + const struct sock_fprog *fprog) { - unsigned int fsize = sk_filter_proglen(fprog); + unsigned int fsize = bpf_classic_proglen(fprog); struct sock_fprog_kern *fkprog; fp->orig_prog = kmalloc(sizeof(*fkprog), GFP_KERNEL); @@ -1324,7 +831,7 @@ static int sk_store_orig_filter(struct sk_filter *fp, return 0; } -static void sk_release_orig_filter(struct sk_filter *fp) +static void bpf_release_orig_filter(struct bpf_prog *fp) { struct sock_fprog_kern *fprog = fp->orig_prog; @@ -1334,6 +841,18 @@ static void sk_release_orig_filter(struct sk_filter *fp) } } +static void __bpf_prog_release(struct bpf_prog *prog) +{ + bpf_release_orig_filter(prog); + bpf_prog_free(prog); +} + +static void __sk_filter_release(struct sk_filter *fp) +{ + __bpf_prog_release(fp->prog); + kfree(fp); +} + /** * sk_filter_release_rcu - Release a socket filter by rcu_head * @rcu: rcu_head that contains the sk_filter to free @@ -1342,8 +861,7 @@ static void sk_filter_release_rcu(struct rcu_head *rcu) { struct sk_filter *fp = container_of(rcu, struct sk_filter, rcu); - sk_release_orig_filter(fp); - sk_filter_free(fp); + __sk_filter_release(fp); } /** @@ -1360,44 +878,33 @@ static void sk_filter_release(struct sk_filter *fp) void sk_filter_uncharge(struct sock *sk, struct sk_filter *fp) { - atomic_sub(sk_filter_size(fp->len), &sk->sk_omem_alloc); - sk_filter_release(fp); -} + u32 filter_size = bpf_prog_size(fp->prog->len); -void sk_filter_charge(struct sock *sk, struct sk_filter *fp) -{ - atomic_inc(&fp->refcnt); - atomic_add(sk_filter_size(fp->len), &sk->sk_omem_alloc); + atomic_sub(filter_size, &sk->sk_omem_alloc); + sk_filter_release(fp); } -static struct sk_filter *__sk_migrate_realloc(struct sk_filter *fp, - struct sock *sk, - unsigned int len) +/* try to charge the socket memory if there is space available + * return true on success + */ +bool sk_filter_charge(struct sock *sk, struct sk_filter *fp) { - struct sk_filter *fp_new; - - if (sk == NULL) - return krealloc(fp, len, GFP_KERNEL); - - fp_new = sock_kmalloc(sk, len, GFP_KERNEL); - if (fp_new) { - *fp_new = *fp; - /* As we're keeping orig_prog in fp_new along, - * we need to make sure we're not evicting it - * from the old fp. - */ - fp->orig_prog = NULL; - sk_filter_uncharge(sk, fp); + u32 filter_size = bpf_prog_size(fp->prog->len); + + /* same check as in sock_kmalloc() */ + if (filter_size <= sysctl_optmem_max && + atomic_read(&sk->sk_omem_alloc) + filter_size < sysctl_optmem_max) { + atomic_inc(&fp->refcnt); + atomic_add(filter_size, &sk->sk_omem_alloc); + return true; } - - return fp_new; + return false; } -static struct sk_filter *__sk_migrate_filter(struct sk_filter *fp, - struct sock *sk) +static struct bpf_prog *bpf_migrate_filter(struct bpf_prog *fp) { struct sock_filter *old_prog; - struct sk_filter *old_fp; + struct bpf_prog *old_fp; int err, new_len, old_len = fp->len; /* We are free to overwrite insns et al right here as it @@ -1406,7 +913,7 @@ static struct sk_filter *__sk_migrate_filter(struct sk_filter *fp, * representation. */ BUILD_BUG_ON(sizeof(struct sock_filter) != - sizeof(struct sock_filter_int)); + sizeof(struct bpf_insn)); /* Conversion cannot happen on overlapping memory areas, * so we need to keep the user BPF around until the 2nd @@ -1420,13 +927,13 @@ static struct sk_filter *__sk_migrate_filter(struct sk_filter *fp, } /* 1st pass: calculate the new program length. */ - err = sk_convert_filter(old_prog, old_len, NULL, &new_len); + err = bpf_convert_filter(old_prog, old_len, NULL, &new_len); if (err) goto out_err_free; /* Expand fp for appending the new filter representation. */ old_fp = fp; - fp = __sk_migrate_realloc(old_fp, sk, sk_filter_size(new_len)); + fp = krealloc(old_fp, bpf_prog_size(new_len), GFP_KERNEL); if (!fp) { /* The old_fp is still around in case we couldn't * allocate new memory, so uncharge on that one. @@ -1438,17 +945,17 @@ static struct sk_filter *__sk_migrate_filter(struct sk_filter *fp, fp->len = new_len; - /* 2nd pass: remap sock_filter insns into sock_filter_int insns. */ - err = sk_convert_filter(old_prog, old_len, fp->insnsi, &new_len); + /* 2nd pass: remap sock_filter insns into bpf_insn insns. */ + err = bpf_convert_filter(old_prog, old_len, fp->insnsi, &new_len); if (err) - /* 2nd sk_convert_filter() can fail only if it fails + /* 2nd bpf_convert_filter() can fail only if it fails * to allocate memory, remapping must succeed. Note, * that at this time old_fp has already been released - * by __sk_migrate_realloc(). + * by krealloc(). */ goto out_err_free; - sk_filter_select_runtime(fp); + bpf_prog_select_runtime(fp); kfree(old_prog); return fp; @@ -1456,55 +963,20 @@ static struct sk_filter *__sk_migrate_filter(struct sk_filter *fp, out_err_free: kfree(old_prog); out_err: - /* Rollback filter setup. */ - if (sk != NULL) - sk_filter_uncharge(sk, fp); - else - kfree(fp); + __bpf_prog_release(fp); return ERR_PTR(err); } -void __weak bpf_int_jit_compile(struct sk_filter *prog) -{ -} - -/** - * sk_filter_select_runtime - select execution runtime for BPF program - * @fp: sk_filter populated with internal BPF program - * - * try to JIT internal BPF program, if JIT is not available select interpreter - * BPF program will be executed via SK_RUN_FILTER() macro - */ -void sk_filter_select_runtime(struct sk_filter *fp) -{ - fp->bpf_func = (void *) __sk_run_filter; - - /* Probe if internal BPF can be JITed */ - bpf_int_jit_compile(fp); -} -EXPORT_SYMBOL_GPL(sk_filter_select_runtime); - -/* free internal BPF program */ -void sk_filter_free(struct sk_filter *fp) -{ - bpf_jit_free(fp); -} -EXPORT_SYMBOL_GPL(sk_filter_free); - -static struct sk_filter *__sk_prepare_filter(struct sk_filter *fp, - struct sock *sk) +static struct bpf_prog *bpf_prepare_filter(struct bpf_prog *fp) { int err; fp->bpf_func = NULL; fp->jited = 0; - err = sk_chk_filter(fp->insns, fp->len); + err = bpf_check_classic(fp->insns, fp->len); if (err) { - if (sk != NULL) - sk_filter_uncharge(sk, fp); - else - kfree(fp); + __bpf_prog_release(fp); return ERR_PTR(err); } @@ -1517,13 +989,13 @@ static struct sk_filter *__sk_prepare_filter(struct sk_filter *fp, * internal BPF translation for the optimized interpreter. */ if (!fp->jited) - fp = __sk_migrate_filter(fp, sk); + fp = bpf_migrate_filter(fp); return fp; } /** - * sk_unattached_filter_create - create an unattached filter + * bpf_prog_create - create an unattached filter * @pfp: the unattached filter that is created * @fprog: the filter program * @@ -1532,23 +1004,21 @@ static struct sk_filter *__sk_prepare_filter(struct sk_filter *fp, * If an error occurs or there is insufficient memory for the filter * a negative errno code is returned. On success the return is zero. */ -int sk_unattached_filter_create(struct sk_filter **pfp, - struct sock_fprog_kern *fprog) +int bpf_prog_create(struct bpf_prog **pfp, struct sock_fprog_kern *fprog) { - unsigned int fsize = sk_filter_proglen(fprog); - struct sk_filter *fp; + unsigned int fsize = bpf_classic_proglen(fprog); + struct bpf_prog *fp; /* Make sure new filter is there and in the right amounts. */ if (fprog->filter == NULL) return -EINVAL; - fp = kmalloc(sk_filter_size(fprog->len), GFP_KERNEL); + fp = kmalloc(bpf_prog_size(fprog->len), GFP_KERNEL); if (!fp) return -ENOMEM; memcpy(fp->insns, fprog->filter, fsize); - atomic_set(&fp->refcnt, 1); fp->len = fprog->len; /* Since unattached filters are not copied back to user * space through sk_get_filter(), we do not need to hold @@ -1556,23 +1026,23 @@ int sk_unattached_filter_create(struct sk_filter **pfp, */ fp->orig_prog = NULL; - /* __sk_prepare_filter() already takes care of uncharging + /* bpf_prepare_filter() already takes care of freeing * memory in case something goes wrong. */ - fp = __sk_prepare_filter(fp, NULL); + fp = bpf_prepare_filter(fp); if (IS_ERR(fp)) return PTR_ERR(fp); *pfp = fp; return 0; } -EXPORT_SYMBOL_GPL(sk_unattached_filter_create); +EXPORT_SYMBOL_GPL(bpf_prog_create); -void sk_unattached_filter_destroy(struct sk_filter *fp) +void bpf_prog_destroy(struct bpf_prog *fp) { - sk_filter_release(fp); + __bpf_prog_release(fp); } -EXPORT_SYMBOL_GPL(sk_unattached_filter_destroy); +EXPORT_SYMBOL_GPL(bpf_prog_destroy); /** * sk_attach_filter - attach a socket filter @@ -1587,8 +1057,9 @@ EXPORT_SYMBOL_GPL(sk_unattached_filter_destroy); int sk_attach_filter(struct sock_fprog *fprog, struct sock *sk) { struct sk_filter *fp, *old_fp; - unsigned int fsize = sk_filter_proglen(fprog); - unsigned int sk_fsize = sk_filter_size(fprog->len); + unsigned int fsize = bpf_classic_proglen(fprog); + unsigned int bpf_fsize = bpf_prog_size(fprog->len); + struct bpf_prog *prog; int err; if (sock_flag(sk, SOCK_FILTER_LOCKED)) @@ -1598,30 +1069,43 @@ int sk_attach_filter(struct sock_fprog *fprog, struct sock *sk) if (fprog->filter == NULL) return -EINVAL; - fp = sock_kmalloc(sk, sk_fsize, GFP_KERNEL); - if (!fp) + prog = kmalloc(bpf_fsize, GFP_KERNEL); + if (!prog) return -ENOMEM; - if (copy_from_user(fp->insns, fprog->filter, fsize)) { - sock_kfree_s(sk, fp, sk_fsize); + if (copy_from_user(prog->insns, fprog->filter, fsize)) { + kfree(prog); return -EFAULT; } - atomic_set(&fp->refcnt, 1); - fp->len = fprog->len; + prog->len = fprog->len; - err = sk_store_orig_filter(fp, fprog); + err = bpf_prog_store_orig_filter(prog, fprog); if (err) { - sk_filter_uncharge(sk, fp); + kfree(prog); return -ENOMEM; } - /* __sk_prepare_filter() already takes care of uncharging + /* bpf_prepare_filter() already takes care of freeing * memory in case something goes wrong. */ - fp = __sk_prepare_filter(fp, sk); - if (IS_ERR(fp)) - return PTR_ERR(fp); + prog = bpf_prepare_filter(prog); + if (IS_ERR(prog)) + return PTR_ERR(prog); + + fp = kmalloc(sizeof(*fp), GFP_KERNEL); + if (!fp) { + __bpf_prog_release(prog); + return -ENOMEM; + } + fp->prog = prog; + + atomic_set(&fp->refcnt, 0); + + if (!sk_filter_charge(sk, fp)) { + __sk_filter_release(fp); + return -ENOMEM; + } old_fp = rcu_dereference_protected(sk->sk_filter, sock_owned_by_user(sk)); @@ -1670,7 +1154,7 @@ int sk_get_filter(struct sock *sk, struct sock_filter __user *ubuf, /* We're copying the filter that has been originally attached, * so no conversion/decode needed anymore. */ - fprog = filter->orig_prog; + fprog = filter->prog->orig_prog; ret = fprog->len; if (!len) @@ -1682,7 +1166,7 @@ int sk_get_filter(struct sock *sk, struct sock_filter __user *ubuf, goto out; ret = -EFAULT; - if (copy_to_user(ubuf, fprog->filter, sk_filter_proglen(fprog))) + if (copy_to_user(ubuf, fprog->filter, bpf_classic_proglen(fprog))) goto out; /* Instead of bytes, the API requests to return the number diff --git a/net/core/flow_dissector.c b/net/core/flow_dissector.c index 107ed12a5323..5f362c1d0332 100644 --- a/net/core/flow_dissector.c +++ b/net/core/flow_dissector.c @@ -80,6 +80,8 @@ ip: case htons(ETH_P_IPV6): { const struct ipv6hdr *iph; struct ipv6hdr _iph; + __be32 flow_label; + ipv6: iph = skb_header_pointer(skb, nhoff, sizeof(_iph), &_iph); if (!iph) @@ -89,6 +91,21 @@ ipv6: flow->src = (__force __be32)ipv6_addr_hash(&iph->saddr); flow->dst = (__force __be32)ipv6_addr_hash(&iph->daddr); nhoff += sizeof(struct ipv6hdr); + + flow_label = ip6_flowlabel(iph); + if (flow_label) { + /* Awesome, IPv6 packet has a flow label so we can + * use that to represent the ports without any + * further dissection. + */ + flow->n_proto = proto; + flow->ip_proto = ip_proto; + flow->ports = flow_label; + flow->thoff = (u16)nhoff; + + return true; + } + break; } case htons(ETH_P_8021AD): @@ -175,6 +192,7 @@ ipv6: break; } + flow->n_proto = proto; flow->ip_proto = ip_proto; flow->ports = skb_flow_get_ports(skb, nhoff, ip_proto); flow->thoff = (u16) nhoff; @@ -195,12 +213,33 @@ static __always_inline u32 __flow_hash_3words(u32 a, u32 b, u32 c) return jhash_3words(a, b, c, hashrnd); } -static __always_inline u32 __flow_hash_1word(u32 a) +static inline u32 __flow_hash_from_keys(struct flow_keys *keys) { - __flow_hash_secret_init(); - return jhash_1word(a, hashrnd); + u32 hash; + + /* get a consistent hash (same value on both flow directions) */ + if (((__force u32)keys->dst < (__force u32)keys->src) || + (((__force u32)keys->dst == (__force u32)keys->src) && + ((__force u16)keys->port16[1] < (__force u16)keys->port16[0]))) { + swap(keys->dst, keys->src); + swap(keys->port16[0], keys->port16[1]); + } + + hash = __flow_hash_3words((__force u32)keys->dst, + (__force u32)keys->src, + (__force u32)keys->ports); + if (!hash) + hash = 1; + + return hash; } +u32 flow_hash_from_keys(struct flow_keys *keys) +{ + return __flow_hash_from_keys(keys); +} +EXPORT_SYMBOL(flow_hash_from_keys); + /* * __skb_get_hash: calculate a flow hash based on src/dst addresses * and src/dst port numbers. Sets hash in skb to non-zero hash value @@ -210,7 +249,6 @@ static __always_inline u32 __flow_hash_1word(u32 a) void __skb_get_hash(struct sk_buff *skb) { struct flow_keys keys; - u32 hash; if (!skb_flow_dissect(skb, &keys)) return; @@ -218,21 +256,9 @@ void __skb_get_hash(struct sk_buff *skb) if (keys.ports) skb->l4_hash = 1; - /* get a consistent hash (same value on both flow directions) */ - if (((__force u32)keys.dst < (__force u32)keys.src) || - (((__force u32)keys.dst == (__force u32)keys.src) && - ((__force u16)keys.port16[1] < (__force u16)keys.port16[0]))) { - swap(keys.dst, keys.src); - swap(keys.port16[0], keys.port16[1]); - } - - hash = __flow_hash_3words((__force u32)keys.dst, - (__force u32)keys.src, - (__force u32)keys.ports); - if (!hash) - hash = 1; + skb->sw_hash = 1; - skb->hash = hash; + skb->hash = __flow_hash_from_keys(&keys); } EXPORT_SYMBOL(__skb_get_hash); @@ -240,7 +266,7 @@ EXPORT_SYMBOL(__skb_get_hash); * Returns a Tx hash based on the given packet descriptor a Tx queues' number * to be used as a distribution range. */ -u16 __skb_tx_hash(const struct net_device *dev, const struct sk_buff *skb, +u16 __skb_tx_hash(const struct net_device *dev, struct sk_buff *skb, unsigned int num_tx_queues) { u32 hash; @@ -260,13 +286,7 @@ u16 __skb_tx_hash(const struct net_device *dev, const struct sk_buff *skb, qcount = dev->tc_to_txq[tc].count; } - if (skb->sk && skb->sk->sk_hash) - hash = skb->sk->sk_hash; - else - hash = (__force u16) skb->protocol; - hash = __flow_hash_1word(hash); - - return (u16) (((u64) hash * qcount) >> 32) + qoffset; + return (u16) (((u64)skb_get_hash(skb) * qcount) >> 32) + qoffset; } EXPORT_SYMBOL(__skb_tx_hash); @@ -338,17 +358,10 @@ static inline int get_xps_queue(struct net_device *dev, struct sk_buff *skb) if (map) { if (map->len == 1) queue_index = map->queues[0]; - else { - u32 hash; - if (skb->sk && skb->sk->sk_hash) - hash = skb->sk->sk_hash; - else - hash = (__force u16) skb->protocol ^ - skb->hash; - hash = __flow_hash_1word(hash); + else queue_index = map->queues[ - ((u64)hash * map->len) >> 32]; - } + ((u64)skb_get_hash(skb) * map->len) >> 32]; + if (unlikely(queue_index >= dev->real_num_tx_queues)) queue_index = -1; } diff --git a/net/core/net-sysfs.c b/net/core/net-sysfs.c index 1cac29ebb05b..9dd06699b09c 100644 --- a/net/core/net-sysfs.c +++ b/net/core/net-sysfs.c @@ -43,12 +43,12 @@ static ssize_t netdev_show(const struct device *dev, struct device_attribute *attr, char *buf, ssize_t (*format)(const struct net_device *, char *)) { - struct net_device *net = to_net_dev(dev); + struct net_device *ndev = to_net_dev(dev); ssize_t ret = -EINVAL; read_lock(&dev_base_lock); - if (dev_isalive(net)) - ret = (*format)(net, buf); + if (dev_isalive(ndev)) + ret = (*format)(ndev, buf); read_unlock(&dev_base_lock); return ret; @@ -56,9 +56,9 @@ static ssize_t netdev_show(const struct device *dev, /* generate a show function for simple field */ #define NETDEVICE_SHOW(field, format_string) \ -static ssize_t format_##field(const struct net_device *net, char *buf) \ +static ssize_t format_##field(const struct net_device *dev, char *buf) \ { \ - return sprintf(buf, format_string, net->field); \ + return sprintf(buf, format_string, dev->field); \ } \ static ssize_t field##_show(struct device *dev, \ struct device_attribute *attr, char *buf) \ @@ -112,16 +112,35 @@ NETDEVICE_SHOW_RO(ifindex, fmt_dec); NETDEVICE_SHOW_RO(type, fmt_dec); NETDEVICE_SHOW_RO(link_mode, fmt_dec); +static ssize_t format_name_assign_type(const struct net_device *dev, char *buf) +{ + return sprintf(buf, fmt_dec, dev->name_assign_type); +} + +static ssize_t name_assign_type_show(struct device *dev, + struct device_attribute *attr, + char *buf) +{ + struct net_device *ndev = to_net_dev(dev); + ssize_t ret = -EINVAL; + + if (ndev->name_assign_type != NET_NAME_UNKNOWN) + ret = netdev_show(dev, attr, buf, format_name_assign_type); + + return ret; +} +static DEVICE_ATTR_RO(name_assign_type); + /* use same locking rules as GIFHWADDR ioctl's */ static ssize_t address_show(struct device *dev, struct device_attribute *attr, char *buf) { - struct net_device *net = to_net_dev(dev); + struct net_device *ndev = to_net_dev(dev); ssize_t ret = -EINVAL; read_lock(&dev_base_lock); - if (dev_isalive(net)) - ret = sysfs_format_mac(buf, net->dev_addr, net->addr_len); + if (dev_isalive(ndev)) + ret = sysfs_format_mac(buf, ndev->dev_addr, ndev->addr_len); read_unlock(&dev_base_lock); return ret; } @@ -130,18 +149,18 @@ static DEVICE_ATTR_RO(address); static ssize_t broadcast_show(struct device *dev, struct device_attribute *attr, char *buf) { - struct net_device *net = to_net_dev(dev); - if (dev_isalive(net)) - return sysfs_format_mac(buf, net->broadcast, net->addr_len); + struct net_device *ndev = to_net_dev(dev); + if (dev_isalive(ndev)) + return sysfs_format_mac(buf, ndev->broadcast, ndev->addr_len); return -EINVAL; } static DEVICE_ATTR_RO(broadcast); -static int change_carrier(struct net_device *net, unsigned long new_carrier) +static int change_carrier(struct net_device *dev, unsigned long new_carrier) { - if (!netif_running(net)) + if (!netif_running(dev)) return -EINVAL; - return dev_change_carrier(net, (bool) new_carrier); + return dev_change_carrier(dev, (bool) new_carrier); } static ssize_t carrier_store(struct device *dev, struct device_attribute *attr, @@ -265,9 +284,9 @@ static DEVICE_ATTR_RO(carrier_changes); /* read-write attributes */ -static int change_mtu(struct net_device *net, unsigned long new_mtu) +static int change_mtu(struct net_device *dev, unsigned long new_mtu) { - return dev_set_mtu(net, (int) new_mtu); + return dev_set_mtu(dev, (int) new_mtu); } static ssize_t mtu_store(struct device *dev, struct device_attribute *attr, @@ -277,9 +296,9 @@ static ssize_t mtu_store(struct device *dev, struct device_attribute *attr, } NETDEVICE_SHOW_RW(mtu, fmt_dec); -static int change_flags(struct net_device *net, unsigned long new_flags) +static int change_flags(struct net_device *dev, unsigned long new_flags) { - return dev_change_flags(net, (unsigned int) new_flags); + return dev_change_flags(dev, (unsigned int) new_flags); } static ssize_t flags_store(struct device *dev, struct device_attribute *attr, @@ -289,9 +308,9 @@ static ssize_t flags_store(struct device *dev, struct device_attribute *attr, } NETDEVICE_SHOW_RW(flags, fmt_hex); -static int change_tx_queue_len(struct net_device *net, unsigned long new_len) +static int change_tx_queue_len(struct net_device *dev, unsigned long new_len) { - net->tx_queue_len = new_len; + dev->tx_queue_len = new_len; return 0; } @@ -344,9 +363,9 @@ static ssize_t ifalias_show(struct device *dev, } static DEVICE_ATTR_RW(ifalias); -static int change_group(struct net_device *net, unsigned long new_group) +static int change_group(struct net_device *dev, unsigned long new_group) { - dev_set_group(net, (int) new_group); + dev_set_group(dev, (int) new_group); return 0; } @@ -387,6 +406,7 @@ static struct attribute *net_class_attrs[] = { &dev_attr_dev_port.attr, &dev_attr_iflink.attr, &dev_attr_ifindex.attr, + &dev_attr_name_assign_type.attr, &dev_attr_addr_assign_type.attr, &dev_attr_addr_len.attr, &dev_attr_link_mode.attr, @@ -776,20 +796,20 @@ static struct kobj_type rx_queue_ktype = { .namespace = rx_queue_namespace }; -static int rx_queue_add_kobject(struct net_device *net, int index) +static int rx_queue_add_kobject(struct net_device *dev, int index) { - struct netdev_rx_queue *queue = net->_rx + index; + struct netdev_rx_queue *queue = dev->_rx + index; struct kobject *kobj = &queue->kobj; int error = 0; - kobj->kset = net->queues_kset; + kobj->kset = dev->queues_kset; error = kobject_init_and_add(kobj, &rx_queue_ktype, NULL, "rx-%u", index); if (error) goto exit; - if (net->sysfs_rx_queue_group) { - error = sysfs_create_group(kobj, net->sysfs_rx_queue_group); + if (dev->sysfs_rx_queue_group) { + error = sysfs_create_group(kobj, dev->sysfs_rx_queue_group); if (error) goto exit; } @@ -805,18 +825,18 @@ exit: #endif /* CONFIG_SYSFS */ int -net_rx_queue_update_kobjects(struct net_device *net, int old_num, int new_num) +net_rx_queue_update_kobjects(struct net_device *dev, int old_num, int new_num) { #ifdef CONFIG_SYSFS int i; int error = 0; #ifndef CONFIG_RPS - if (!net->sysfs_rx_queue_group) + if (!dev->sysfs_rx_queue_group) return 0; #endif for (i = old_num; i < new_num; i++) { - error = rx_queue_add_kobject(net, i); + error = rx_queue_add_kobject(dev, i); if (error) { new_num = old_num; break; @@ -824,10 +844,10 @@ net_rx_queue_update_kobjects(struct net_device *net, int old_num, int new_num) } while (--i >= new_num) { - if (net->sysfs_rx_queue_group) - sysfs_remove_group(&net->_rx[i].kobj, - net->sysfs_rx_queue_group); - kobject_put(&net->_rx[i].kobj); + if (dev->sysfs_rx_queue_group) + sysfs_remove_group(&dev->_rx[i].kobj, + dev->sysfs_rx_queue_group); + kobject_put(&dev->_rx[i].kobj); } return error; @@ -1135,13 +1155,13 @@ static struct kobj_type netdev_queue_ktype = { .namespace = netdev_queue_namespace, }; -static int netdev_queue_add_kobject(struct net_device *net, int index) +static int netdev_queue_add_kobject(struct net_device *dev, int index) { - struct netdev_queue *queue = net->_tx + index; + struct netdev_queue *queue = dev->_tx + index; struct kobject *kobj = &queue->kobj; int error = 0; - kobj->kset = net->queues_kset; + kobj->kset = dev->queues_kset; error = kobject_init_and_add(kobj, &netdev_queue_ktype, NULL, "tx-%u", index); if (error) @@ -1164,14 +1184,14 @@ exit: #endif /* CONFIG_SYSFS */ int -netdev_queue_update_kobjects(struct net_device *net, int old_num, int new_num) +netdev_queue_update_kobjects(struct net_device *dev, int old_num, int new_num) { #ifdef CONFIG_SYSFS int i; int error = 0; for (i = old_num; i < new_num; i++) { - error = netdev_queue_add_kobject(net, i); + error = netdev_queue_add_kobject(dev, i); if (error) { new_num = old_num; break; @@ -1179,7 +1199,7 @@ netdev_queue_update_kobjects(struct net_device *net, int old_num, int new_num) } while (--i >= new_num) { - struct netdev_queue *queue = net->_tx + i; + struct netdev_queue *queue = dev->_tx + i; #ifdef CONFIG_BQL sysfs_remove_group(&queue->kobj, &dql_group); @@ -1193,25 +1213,25 @@ netdev_queue_update_kobjects(struct net_device *net, int old_num, int new_num) #endif /* CONFIG_SYSFS */ } -static int register_queue_kobjects(struct net_device *net) +static int register_queue_kobjects(struct net_device *dev) { int error = 0, txq = 0, rxq = 0, real_rx = 0, real_tx = 0; #ifdef CONFIG_SYSFS - net->queues_kset = kset_create_and_add("queues", - NULL, &net->dev.kobj); - if (!net->queues_kset) + dev->queues_kset = kset_create_and_add("queues", + NULL, &dev->dev.kobj); + if (!dev->queues_kset) return -ENOMEM; - real_rx = net->real_num_rx_queues; + real_rx = dev->real_num_rx_queues; #endif - real_tx = net->real_num_tx_queues; + real_tx = dev->real_num_tx_queues; - error = net_rx_queue_update_kobjects(net, 0, real_rx); + error = net_rx_queue_update_kobjects(dev, 0, real_rx); if (error) goto error; rxq = real_rx; - error = netdev_queue_update_kobjects(net, 0, real_tx); + error = netdev_queue_update_kobjects(dev, 0, real_tx); if (error) goto error; txq = real_tx; @@ -1219,24 +1239,24 @@ static int register_queue_kobjects(struct net_device *net) return 0; error: - netdev_queue_update_kobjects(net, txq, 0); - net_rx_queue_update_kobjects(net, rxq, 0); + netdev_queue_update_kobjects(dev, txq, 0); + net_rx_queue_update_kobjects(dev, rxq, 0); return error; } -static void remove_queue_kobjects(struct net_device *net) +static void remove_queue_kobjects(struct net_device *dev) { int real_rx = 0, real_tx = 0; #ifdef CONFIG_SYSFS - real_rx = net->real_num_rx_queues; + real_rx = dev->real_num_rx_queues; #endif - real_tx = net->real_num_tx_queues; + real_tx = dev->real_num_tx_queues; - net_rx_queue_update_kobjects(net, real_rx, 0); - netdev_queue_update_kobjects(net, real_tx, 0); + net_rx_queue_update_kobjects(dev, real_rx, 0); + netdev_queue_update_kobjects(dev, real_tx, 0); #ifdef CONFIG_SYSFS - kset_unregister(net->queues_kset); + kset_unregister(dev->queues_kset); #endif } @@ -1329,13 +1349,13 @@ static struct class net_class = { /* Delete sysfs entries but hold kobject reference until after all * netdev references are gone. */ -void netdev_unregister_kobject(struct net_device * net) +void netdev_unregister_kobject(struct net_device *ndev) { - struct device *dev = &(net->dev); + struct device *dev = &(ndev->dev); kobject_get(&dev->kobj); - remove_queue_kobjects(net); + remove_queue_kobjects(ndev); pm_runtime_set_memalloc_noio(dev, false); @@ -1343,18 +1363,18 @@ void netdev_unregister_kobject(struct net_device * net) } /* Create sysfs entries for network device. */ -int netdev_register_kobject(struct net_device *net) +int netdev_register_kobject(struct net_device *ndev) { - struct device *dev = &(net->dev); - const struct attribute_group **groups = net->sysfs_groups; + struct device *dev = &(ndev->dev); + const struct attribute_group **groups = ndev->sysfs_groups; int error = 0; device_initialize(dev); dev->class = &net_class; - dev->platform_data = net; + dev->platform_data = ndev; dev->groups = groups; - dev_set_name(dev, "%s", net->name); + dev_set_name(dev, "%s", ndev->name); #ifdef CONFIG_SYSFS /* Allow for a device specific group */ @@ -1364,10 +1384,10 @@ int netdev_register_kobject(struct net_device *net) *groups++ = &netstat_group; #if IS_ENABLED(CONFIG_WIRELESS_EXT) || IS_ENABLED(CONFIG_CFG80211) - if (net->ieee80211_ptr) + if (ndev->ieee80211_ptr) *groups++ = &wireless_group; #if IS_ENABLED(CONFIG_WIRELESS_EXT) - else if (net->wireless_handlers) + else if (ndev->wireless_handlers) *groups++ = &wireless_group; #endif #endif @@ -1377,7 +1397,7 @@ int netdev_register_kobject(struct net_device *net) if (error) return error; - error = register_queue_kobjects(net); + error = register_queue_kobjects(ndev); if (error) { device_del(dev); return error; diff --git a/net/core/netpoll.c b/net/core/netpoll.c index e33937fb32a0..907fb5e36c02 100644 --- a/net/core/netpoll.c +++ b/net/core/netpoll.c @@ -822,7 +822,8 @@ void __netpoll_cleanup(struct netpoll *np) RCU_INIT_POINTER(np->dev->npinfo, NULL); call_rcu_bh(&npinfo->rcu, rcu_cleanup_netpoll_info); - } + } else + RCU_INIT_POINTER(np->dev->npinfo, NULL); } EXPORT_SYMBOL_GPL(__netpoll_cleanup); diff --git a/net/core/pktgen.c b/net/core/pktgen.c index fc17a9d309ac..8b849ddfef2e 100644 --- a/net/core/pktgen.c +++ b/net/core/pktgen.c @@ -69,8 +69,9 @@ * for running devices in the if_list and sends packets until count is 0 it * also the thread checks the thread->control which is used for inter-process * communication. controlling process "posts" operations to the threads this - * way. The if_lock should be possible to remove when add/rem_device is merged - * into this too. + * way. + * The if_list is RCU protected, and the if_lock remains to protect updating + * of if_list, from "add_device" as it invoked from userspace (via proc write). * * By design there should only be *one* "controlling" process. In practice * multiple write accesses gives unpredictable result. Understood by "write" @@ -208,7 +209,7 @@ #define T_REMDEVALL (1<<2) /* Remove all devs */ #define T_REMDEV (1<<3) /* Remove one dev */ -/* If lock -- can be removed after some work */ +/* If lock -- protects updating of if_list */ #define if_lock(t) spin_lock(&(t->if_lock)); #define if_unlock(t) spin_unlock(&(t->if_lock)); @@ -241,6 +242,7 @@ struct pktgen_dev { struct proc_dir_entry *entry; /* proc file */ struct pktgen_thread *pg_thread;/* the owner */ struct list_head list; /* chaining in the thread's run-queue */ + struct rcu_head rcu; /* freed by RCU */ int running; /* if false, the test will stop */ @@ -802,7 +804,6 @@ static int strn_len(const char __user * user_buffer, unsigned int maxlen) case '\t': case ' ': goto done_str; - break; default: break; } @@ -1737,14 +1738,14 @@ static int pktgen_thread_show(struct seq_file *seq, void *v) seq_puts(seq, "Running: "); - if_lock(t); - list_for_each_entry(pkt_dev, &t->if_list, list) + rcu_read_lock(); + list_for_each_entry_rcu(pkt_dev, &t->if_list, list) if (pkt_dev->running) seq_printf(seq, "%s ", pkt_dev->odevname); seq_puts(seq, "\nStopped: "); - list_for_each_entry(pkt_dev, &t->if_list, list) + list_for_each_entry_rcu(pkt_dev, &t->if_list, list) if (!pkt_dev->running) seq_printf(seq, "%s ", pkt_dev->odevname); @@ -1753,7 +1754,7 @@ static int pktgen_thread_show(struct seq_file *seq, void *v) else seq_puts(seq, "\nResult: NA\n"); - if_unlock(t); + rcu_read_unlock(); return 0; } @@ -1878,10 +1879,8 @@ static struct pktgen_dev *__pktgen_NN_threads(const struct pktgen_net *pn, pkt_dev = pktgen_find_dev(t, ifname, exact); if (pkt_dev) { if (remove) { - if_lock(t); pkt_dev->removal_mark = 1; t->control |= T_REMDEV; - if_unlock(t); } break; } @@ -1931,7 +1930,8 @@ static void pktgen_change_name(const struct pktgen_net *pn, struct net_device *d list_for_each_entry(t, &pn->pktgen_threads, th_list) { struct pktgen_dev *pkt_dev; - list_for_each_entry(pkt_dev, &t->if_list, list) { + rcu_read_lock(); + list_for_each_entry_rcu(pkt_dev, &t->if_list, list) { if (pkt_dev->odev != dev) continue; @@ -1946,6 +1946,7 @@ static void pktgen_change_name(const struct pktgen_net *pn, struct net_device *d dev->name); break; } + rcu_read_unlock(); } } @@ -2997,8 +2998,8 @@ static void pktgen_run(struct pktgen_thread *t) func_enter(); - if_lock(t); - list_for_each_entry(pkt_dev, &t->if_list, list) { + rcu_read_lock(); + list_for_each_entry_rcu(pkt_dev, &t->if_list, list) { /* * setup odev and create initial packet. @@ -3007,18 +3008,18 @@ static void pktgen_run(struct pktgen_thread *t) if (pkt_dev->odev) { pktgen_clear_counters(pkt_dev); - pkt_dev->running = 1; /* Cranke yeself! */ pkt_dev->skb = NULL; pkt_dev->started_at = pkt_dev->next_tx = ktime_get(); set_pkt_overhead(pkt_dev); strcpy(pkt_dev->result, "Starting"); + pkt_dev->running = 1; /* Cranke yeself! */ started++; } else strcpy(pkt_dev->result, "Error starting"); } - if_unlock(t); + rcu_read_unlock(); if (started) t->control &= ~(T_STOP); } @@ -3041,27 +3042,25 @@ static int thread_is_running(const struct pktgen_thread *t) { const struct pktgen_dev *pkt_dev; - list_for_each_entry(pkt_dev, &t->if_list, list) - if (pkt_dev->running) + rcu_read_lock(); + list_for_each_entry_rcu(pkt_dev, &t->if_list, list) + if (pkt_dev->running) { + rcu_read_unlock(); return 1; + } + rcu_read_unlock(); return 0; } static int pktgen_wait_thread_run(struct pktgen_thread *t) { - if_lock(t); - while (thread_is_running(t)) { - if_unlock(t); - msleep_interruptible(100); if (signal_pending(current)) goto signal; - if_lock(t); } - if_unlock(t); return 1; signal: return 0; @@ -3166,10 +3165,10 @@ static int pktgen_stop_device(struct pktgen_dev *pkt_dev) return -EINVAL; } + pkt_dev->running = 0; kfree_skb(pkt_dev->skb); pkt_dev->skb = NULL; pkt_dev->stopped_at = ktime_get(); - pkt_dev->running = 0; show_results(pkt_dev, nr_frags); @@ -3180,9 +3179,8 @@ static struct pktgen_dev *next_to_run(struct pktgen_thread *t) { struct pktgen_dev *pkt_dev, *best = NULL; - if_lock(t); - - list_for_each_entry(pkt_dev, &t->if_list, list) { + rcu_read_lock(); + list_for_each_entry_rcu(pkt_dev, &t->if_list, list) { if (!pkt_dev->running) continue; if (best == NULL) @@ -3190,7 +3188,8 @@ static struct pktgen_dev *next_to_run(struct pktgen_thread *t) else if (ktime_compare(pkt_dev->next_tx, best->next_tx) < 0) best = pkt_dev; } - if_unlock(t); + rcu_read_unlock(); + return best; } @@ -3200,13 +3199,13 @@ static void pktgen_stop(struct pktgen_thread *t) func_enter(); - if_lock(t); + rcu_read_lock(); - list_for_each_entry(pkt_dev, &t->if_list, list) { + list_for_each_entry_rcu(pkt_dev, &t->if_list, list) { pktgen_stop_device(pkt_dev); } - if_unlock(t); + rcu_read_unlock(); } /* @@ -3220,8 +3219,6 @@ static void pktgen_rem_one_if(struct pktgen_thread *t) func_enter(); - if_lock(t); - list_for_each_safe(q, n, &t->if_list) { cur = list_entry(q, struct pktgen_dev, list); @@ -3235,8 +3232,6 @@ static void pktgen_rem_one_if(struct pktgen_thread *t) break; } - - if_unlock(t); } static void pktgen_rem_all_ifs(struct pktgen_thread *t) @@ -3248,8 +3243,6 @@ static void pktgen_rem_all_ifs(struct pktgen_thread *t) /* Remove all devices, free mem */ - if_lock(t); - list_for_each_safe(q, n, &t->if_list) { cur = list_entry(q, struct pktgen_dev, list); @@ -3258,8 +3251,6 @@ static void pktgen_rem_all_ifs(struct pktgen_thread *t) pktgen_remove_device(t, cur); } - - if_unlock(t); } static void pktgen_rem_thread(struct pktgen_thread *t) @@ -3407,10 +3398,10 @@ static int pktgen_thread_worker(void *arg) pr_debug("starting pktgen/%d: pid=%d\n", cpu, task_pid_nr(current)); - set_current_state(TASK_INTERRUPTIBLE); - set_freezable(); + __set_current_state(TASK_RUNNING); + while (!kthread_should_stop()) { pkt_dev = next_to_run(t); @@ -3424,8 +3415,6 @@ static int pktgen_thread_worker(void *arg) continue; } - __set_current_state(TASK_RUNNING); - if (likely(pkt_dev)) { pktgen_xmit(pkt_dev); @@ -3456,9 +3445,8 @@ static int pktgen_thread_worker(void *arg) } try_to_freeze(); - - set_current_state(TASK_INTERRUPTIBLE); } + set_current_state(TASK_INTERRUPTIBLE); pr_debug("%s stopping all device\n", t->tsk->comm); pktgen_stop(t); @@ -3485,8 +3473,8 @@ static struct pktgen_dev *pktgen_find_dev(struct pktgen_thread *t, struct pktgen_dev *p, *pkt_dev = NULL; size_t len = strlen(ifname); - if_lock(t); - list_for_each_entry(p, &t->if_list, list) + rcu_read_lock(); + list_for_each_entry_rcu(p, &t->if_list, list) if (strncmp(p->odevname, ifname, len) == 0) { if (p->odevname[len]) { if (exact || p->odevname[len] != '@') @@ -3496,7 +3484,7 @@ static struct pktgen_dev *pktgen_find_dev(struct pktgen_thread *t, break; } - if_unlock(t); + rcu_read_unlock(); pr_debug("find_dev(%s) returning %p\n", ifname, pkt_dev); return pkt_dev; } @@ -3510,6 +3498,12 @@ static int add_dev_to_thread(struct pktgen_thread *t, { int rv = 0; + /* This function cannot be called concurrently, as its called + * under pktgen_thread_lock mutex, but it can run from + * userspace on another CPU than the kthread. The if_lock() + * is used here to sync with concurrent instances of + * _rem_dev_from_if_list() invoked via kthread, which is also + * updating the if_list */ if_lock(t); if (pkt_dev->pg_thread) { @@ -3518,9 +3512,9 @@ static int add_dev_to_thread(struct pktgen_thread *t, goto out; } - list_add(&pkt_dev->list, &t->if_list); - pkt_dev->pg_thread = t; pkt_dev->running = 0; + pkt_dev->pg_thread = t; + list_add_rcu(&pkt_dev->list, &t->if_list); out: if_unlock(t); @@ -3675,11 +3669,13 @@ static void _rem_dev_from_if_list(struct pktgen_thread *t, struct list_head *q, *n; struct pktgen_dev *p; + if_lock(t); list_for_each_safe(q, n, &t->if_list) { p = list_entry(q, struct pktgen_dev, list); if (p == pkt_dev) - list_del(&p->list); + list_del_rcu(&p->list); } + if_unlock(t); } static int pktgen_remove_device(struct pktgen_thread *t, @@ -3699,20 +3695,22 @@ static int pktgen_remove_device(struct pktgen_thread *t, pkt_dev->odev = NULL; } - /* And update the thread if_list */ - - _rem_dev_from_if_list(t, pkt_dev); - + /* Remove proc before if_list entry, because add_device uses + * list to determine if interface already exist, avoid race + * with proc_create_data() */ if (pkt_dev->entry) proc_remove(pkt_dev->entry); + /* And update the thread if_list */ + _rem_dev_from_if_list(t, pkt_dev); + #ifdef CONFIG_XFRM free_SAs(pkt_dev); #endif vfree(pkt_dev->flows); if (pkt_dev->page) put_page(pkt_dev->page); - kfree(pkt_dev); + kfree_rcu(pkt_dev, rcu); return 0; } @@ -3812,6 +3810,7 @@ static void __exit pg_cleanup(void) { unregister_netdevice_notifier(&pktgen_notifier_block); unregister_pernet_subsys(&pg_net_ops); + /* Don't need rcu_barrier() due to use of kfree_rcu() */ } module_init(pg_init); diff --git a/net/core/ptp_classifier.c b/net/core/ptp_classifier.c index d3027a73fd4b..4eab4a94a59d 100644 --- a/net/core/ptp_classifier.c +++ b/net/core/ptp_classifier.c @@ -52,14 +52,43 @@ * test_8021q: * jneq #0x8100, test_ieee1588 ; ETH_P_8021Q ? * ldh [16] ; load inner type - * jneq #0x88f7, drop_ieee1588 ; ETH_P_1588 ? + * jneq #0x88f7, test_8021q_ipv4 ; ETH_P_1588 ? * ldb [18] ; load payload * and #0x8 ; as we don't have ports here, test * jneq #0x0, drop_ieee1588 ; for PTP_GEN_BIT and drop these * ldh [18] ; reload payload * and #0xf ; mask PTP_CLASS_VMASK - * or #0x40 ; PTP_CLASS_V2_VLAN + * or #0x70 ; PTP_CLASS_VLAN|PTP_CLASS_L2 + * ret a ; return PTP class + * + * ; PTP over UDP over IPv4 over 802.1Q over Ethernet + * test_8021q_ipv4: + * jneq #0x800, test_8021q_ipv6 ; ETH_P_IP ? + * ldb [27] ; load proto + * jneq #17, drop_8021q_ipv4 ; IPPROTO_UDP ? + * ldh [24] ; load frag offset field + * jset #0x1fff, drop_8021q_ipv4; don't allow fragments + * ldxb 4*([18]&0xf) ; load IP header len + * ldh [x + 20] ; load UDP dst port + * jneq #319, drop_8021q_ipv4 ; is port PTP_EV_PORT ? + * ldh [x + 26] ; load payload + * and #0xf ; mask PTP_CLASS_VMASK + * or #0x50 ; PTP_CLASS_VLAN|PTP_CLASS_IPV4 + * ret a ; return PTP class + * drop_8021q_ipv4: ret #0x0 ; PTP_CLASS_NONE + * + * ; PTP over UDP over IPv6 over 802.1Q over Ethernet + * test_8021q_ipv6: + * jneq #0x86dd, drop_8021q_ipv6 ; ETH_P_IPV6 ? + * ldb [24] ; load proto + * jneq #17, drop_8021q_ipv6 ; IPPROTO_UDP ? + * ldh [60] ; load UDP dst port + * jneq #319, drop_8021q_ipv6 ; is port PTP_EV_PORT ? + * ldh [66] ; load payload + * and #0xf ; mask PTP_CLASS_VMASK + * or #0x60 ; PTP_CLASS_VLAN|PTP_CLASS_IPV6 * ret a ; return PTP class + * drop_8021q_ipv6: ret #0x0 ; PTP_CLASS_NONE * * ; PTP over Ethernet * test_ieee1588: @@ -78,11 +107,11 @@ #include <linux/filter.h> #include <linux/ptp_classify.h> -static struct sk_filter *ptp_insns __read_mostly; +static struct bpf_prog *ptp_insns __read_mostly; unsigned int ptp_classify_raw(const struct sk_buff *skb) { - return SK_RUN_FILTER(ptp_insns, skb); + return BPF_PROG_RUN(ptp_insns, skb); } EXPORT_SYMBOL_GPL(ptp_classify_raw); @@ -113,16 +142,39 @@ void __init ptp_classifier_init(void) { 0x44, 0, 0, 0x00000020 }, { 0x16, 0, 0, 0x00000000 }, { 0x06, 0, 0, 0x00000000 }, - { 0x15, 0, 9, 0x00008100 }, + { 0x15, 0, 32, 0x00008100 }, { 0x28, 0, 0, 0x00000010 }, - { 0x15, 0, 15, 0x000088f7 }, + { 0x15, 0, 7, 0x000088f7 }, { 0x30, 0, 0, 0x00000012 }, { 0x54, 0, 0, 0x00000008 }, - { 0x15, 0, 12, 0x00000000 }, + { 0x15, 0, 35, 0x00000000 }, { 0x28, 0, 0, 0x00000012 }, { 0x54, 0, 0, 0x0000000f }, - { 0x44, 0, 0, 0x00000040 }, + { 0x44, 0, 0, 0x00000070 }, + { 0x16, 0, 0, 0x00000000 }, + { 0x15, 0, 12, 0x00000800 }, + { 0x30, 0, 0, 0x0000001b }, + { 0x15, 0, 9, 0x00000011 }, + { 0x28, 0, 0, 0x00000018 }, + { 0x45, 7, 0, 0x00001fff }, + { 0xb1, 0, 0, 0x00000012 }, + { 0x48, 0, 0, 0x00000014 }, + { 0x15, 0, 4, 0x0000013f }, + { 0x48, 0, 0, 0x0000001a }, + { 0x54, 0, 0, 0x0000000f }, + { 0x44, 0, 0, 0x00000050 }, + { 0x16, 0, 0, 0x00000000 }, + { 0x06, 0, 0, 0x00000000 }, + { 0x15, 0, 8, 0x000086dd }, + { 0x30, 0, 0, 0x00000018 }, + { 0x15, 0, 6, 0x00000011 }, + { 0x28, 0, 0, 0x0000003c }, + { 0x15, 0, 4, 0x0000013f }, + { 0x28, 0, 0, 0x00000042 }, + { 0x54, 0, 0, 0x0000000f }, + { 0x44, 0, 0, 0x00000060 }, { 0x16, 0, 0, 0x00000000 }, + { 0x06, 0, 0, 0x00000000 }, { 0x15, 0, 7, 0x000088f7 }, { 0x30, 0, 0, 0x0000000e }, { 0x54, 0, 0, 0x00000008 }, @@ -137,5 +189,5 @@ void __init ptp_classifier_init(void) .len = ARRAY_SIZE(ptp_filter), .filter = ptp_filter, }; - BUG_ON(sk_unattached_filter_create(&ptp_insns, &ptp_prog)); + BUG_ON(bpf_prog_create(&ptp_insns, &ptp_prog)); } diff --git a/net/core/request_sock.c b/net/core/request_sock.c index 467f326126e0..04db318e6218 100644 --- a/net/core/request_sock.c +++ b/net/core/request_sock.c @@ -41,27 +41,27 @@ int reqsk_queue_alloc(struct request_sock_queue *queue, unsigned int nr_table_entries) { size_t lopt_size = sizeof(struct listen_sock); - struct listen_sock *lopt; + struct listen_sock *lopt = NULL; nr_table_entries = min_t(u32, nr_table_entries, sysctl_max_syn_backlog); nr_table_entries = max_t(u32, nr_table_entries, 8); nr_table_entries = roundup_pow_of_two(nr_table_entries + 1); lopt_size += nr_table_entries * sizeof(struct request_sock *); - if (lopt_size > PAGE_SIZE) + + if (lopt_size <= (PAGE_SIZE << PAGE_ALLOC_COSTLY_ORDER)) + lopt = kzalloc(lopt_size, GFP_KERNEL | + __GFP_NOWARN | + __GFP_NORETRY); + if (!lopt) lopt = vzalloc(lopt_size); - else - lopt = kzalloc(lopt_size, GFP_KERNEL); - if (lopt == NULL) + if (!lopt) return -ENOMEM; - for (lopt->max_qlen_log = 3; - (1 << lopt->max_qlen_log) < nr_table_entries; - lopt->max_qlen_log++); - get_random_bytes(&lopt->hash_rnd, sizeof(lopt->hash_rnd)); rwlock_init(&queue->syn_wait_lock); queue->rskq_accept_head = NULL; lopt->nr_table_entries = nr_table_entries; + lopt->max_qlen_log = ilog2(nr_table_entries); write_lock_bh(&queue->syn_wait_lock); queue->listen_opt = lopt; @@ -72,22 +72,8 @@ int reqsk_queue_alloc(struct request_sock_queue *queue, void __reqsk_queue_destroy(struct request_sock_queue *queue) { - struct listen_sock *lopt; - size_t lopt_size; - - /* - * this is an error recovery path only - * no locking needed and the lopt is not NULL - */ - - lopt = queue->listen_opt; - lopt_size = sizeof(struct listen_sock) + - lopt->nr_table_entries * sizeof(struct request_sock *); - - if (lopt_size > PAGE_SIZE) - vfree(lopt); - else - kfree(lopt); + /* This is an error recovery path only, no locking needed */ + kvfree(queue->listen_opt); } static inline struct listen_sock *reqsk_queue_yank_listen_sk( @@ -107,8 +93,6 @@ void reqsk_queue_destroy(struct request_sock_queue *queue) { /* make all the listen_opt local to us */ struct listen_sock *lopt = reqsk_queue_yank_listen_sk(queue); - size_t lopt_size = sizeof(struct listen_sock) + - lopt->nr_table_entries * sizeof(struct request_sock *); if (lopt->qlen != 0) { unsigned int i; @@ -125,10 +109,7 @@ void reqsk_queue_destroy(struct request_sock_queue *queue) } WARN_ON(lopt->qlen != 0); - if (lopt_size > PAGE_SIZE) - vfree(lopt); - else - kfree(lopt); + kvfree(lopt); } /* diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c index 1063996f8317..8d39071f32d7 100644 --- a/net/core/rtnetlink.c +++ b/net/core/rtnetlink.c @@ -299,7 +299,12 @@ int __rtnl_link_register(struct rtnl_link_ops *ops) if (rtnl_link_ops_get(ops->kind)) return -EEXIST; - if (!ops->dellink) + /* The check for setup is here because if ops + * does not have that filled up, it is not possible + * to use the ops for creating device. So do not + * fill up dellink as well. That disables rtnl_dellink. + */ + if (ops->setup && !ops->dellink) ops->dellink = unregister_netdevice_queue; list_add_tail(&ops->list, &link_ops); @@ -1777,7 +1782,7 @@ static int rtnl_dellink(struct sk_buff *skb, struct nlmsghdr *nlh) return -ENODEV; ops = dev->rtnl_link_ops; - if (!ops) + if (!ops || !ops->dellink) return -EOPNOTSUPP; ops->dellink(dev, &list_kill); @@ -1805,7 +1810,8 @@ int rtnl_configure_link(struct net_device *dev, const struct ifinfomsg *ifm) EXPORT_SYMBOL(rtnl_configure_link); struct net_device *rtnl_create_link(struct net *net, - char *ifname, const struct rtnl_link_ops *ops, struct nlattr *tb[]) + char *ifname, unsigned char name_assign_type, + const struct rtnl_link_ops *ops, struct nlattr *tb[]) { int err; struct net_device *dev; @@ -1823,8 +1829,8 @@ struct net_device *rtnl_create_link(struct net *net, num_rx_queues = ops->get_num_rx_queues(); err = -ENOMEM; - dev = alloc_netdev_mqs(ops->priv_size, ifname, ops->setup, - num_tx_queues, num_rx_queues); + dev = alloc_netdev_mqs(ops->priv_size, ifname, name_assign_type, + ops->setup, num_tx_queues, num_rx_queues); if (!dev) goto err; @@ -1889,6 +1895,7 @@ static int rtnl_newlink(struct sk_buff *skb, struct nlmsghdr *nlh) char ifname[IFNAMSIZ]; struct nlattr *tb[IFLA_MAX+1]; struct nlattr *linkinfo[IFLA_INFO_MAX+1]; + unsigned char name_assign_type = NET_NAME_USER; int err; #ifdef CONFIG_MODULES @@ -2038,14 +2045,19 @@ replay: return -EOPNOTSUPP; } - if (!ifname[0]) + if (!ops->setup) + return -EOPNOTSUPP; + + if (!ifname[0]) { snprintf(ifname, IFNAMSIZ, "%s%%d", ops->kind); + name_assign_type = NET_NAME_ENUM; + } dest_net = rtnl_link_get_net(net, tb); if (IS_ERR(dest_net)) return PTR_ERR(dest_net); - dev = rtnl_create_link(dest_net, ifname, ops, tb); + dev = rtnl_create_link(dest_net, ifname, name_assign_type, ops, tb); if (IS_ERR(dev)) { err = PTR_ERR(dev); goto out; @@ -2380,22 +2392,20 @@ int ndo_dflt_fdb_del(struct ndmsg *ndm, struct net_device *dev, const unsigned char *addr) { - int err = -EOPNOTSUPP; + int err = -EINVAL; /* If aging addresses are supported device will need to * implement its own handler for this. */ if (!(ndm->ndm_state & NUD_PERMANENT)) { pr_info("%s: FDB only supports static addresses\n", dev->name); - return -EINVAL; + return err; } if (is_unicast_ether_addr(addr) || is_link_local_ether_addr(addr)) err = dev_uc_del(dev, addr); else if (is_multicast_ether_addr(addr)) err = dev_mc_del(dev, addr); - else - err = -EINVAL; return err; } @@ -2509,6 +2519,7 @@ skip: int ndo_dflt_fdb_dump(struct sk_buff *skb, struct netlink_callback *cb, struct net_device *dev, + struct net_device *filter_dev, int idx) { int err; @@ -2526,28 +2537,72 @@ EXPORT_SYMBOL(ndo_dflt_fdb_dump); static int rtnl_fdb_dump(struct sk_buff *skb, struct netlink_callback *cb) { - int idx = 0; - struct net *net = sock_net(skb->sk); struct net_device *dev; + struct nlattr *tb[IFLA_MAX+1]; + struct net_device *bdev = NULL; + struct net_device *br_dev = NULL; + const struct net_device_ops *ops = NULL; + const struct net_device_ops *cops = NULL; + struct ifinfomsg *ifm = nlmsg_data(cb->nlh); + struct net *net = sock_net(skb->sk); + int brport_idx = 0; + int br_idx = 0; + int idx = 0; - rcu_read_lock(); - for_each_netdev_rcu(net, dev) { - if (dev->priv_flags & IFF_BRIDGE_PORT) { - struct net_device *br_dev; - const struct net_device_ops *ops; + if (nlmsg_parse(cb->nlh, sizeof(struct ifinfomsg), tb, IFLA_MAX, + ifla_policy) == 0) { + if (tb[IFLA_MASTER]) + br_idx = nla_get_u32(tb[IFLA_MASTER]); + } + + brport_idx = ifm->ifi_index; - br_dev = netdev_master_upper_dev_get(dev); - ops = br_dev->netdev_ops; - if (ops->ndo_fdb_dump) - idx = ops->ndo_fdb_dump(skb, cb, dev, idx); + if (br_idx) { + br_dev = __dev_get_by_index(net, br_idx); + if (!br_dev) + return -ENODEV; + + ops = br_dev->netdev_ops; + bdev = br_dev; + } + + for_each_netdev(net, dev) { + if (brport_idx && (dev->ifindex != brport_idx)) + continue; + + if (!br_idx) { /* user did not specify a specific bridge */ + if (dev->priv_flags & IFF_BRIDGE_PORT) { + br_dev = netdev_master_upper_dev_get(dev); + cops = br_dev->netdev_ops; + } + + bdev = dev; + } else { + if (dev != br_dev && + !(dev->priv_flags & IFF_BRIDGE_PORT)) + continue; + + if (br_dev != netdev_master_upper_dev_get(dev) && + !(dev->priv_flags & IFF_EBRIDGE)) + continue; + + bdev = br_dev; + cops = ops; + } + + if (dev->priv_flags & IFF_BRIDGE_PORT) { + if (cops && cops->ndo_fdb_dump) + idx = cops->ndo_fdb_dump(skb, cb, br_dev, dev, + idx); } + idx = ndo_dflt_fdb_dump(skb, cb, dev, NULL, idx); if (dev->netdev_ops->ndo_fdb_dump) - idx = dev->netdev_ops->ndo_fdb_dump(skb, cb, dev, idx); - else - idx = ndo_dflt_fdb_dump(skb, cb, dev, idx); + idx = dev->netdev_ops->ndo_fdb_dump(skb, cb, bdev, dev, + idx); + + cops = NULL; } - rcu_read_unlock(); cb->args[0] = idx; return skb->len; diff --git a/net/core/skbuff.c b/net/core/skbuff.c index c1a33033cbe2..224506a6fa80 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -2976,9 +2976,9 @@ struct sk_buff *skb_segment(struct sk_buff *head_skb, tail = nskb; __copy_skb_header(nskb, head_skb); - nskb->mac_len = head_skb->mac_len; skb_headers_offset_update(nskb, skb_headroom(nskb) - headroom); + skb_reset_mac_len(nskb); skb_copy_from_linear_data_offset(head_skb, -tnl_hlen, nskb->data - tnl_hlen, @@ -3490,10 +3490,10 @@ int sock_queue_err_skb(struct sock *sk, struct sk_buff *skb) } EXPORT_SYMBOL(sock_queue_err_skb); -void skb_tstamp_tx(struct sk_buff *orig_skb, - struct skb_shared_hwtstamps *hwtstamps) +void __skb_tstamp_tx(struct sk_buff *orig_skb, + struct skb_shared_hwtstamps *hwtstamps, + struct sock *sk, int tstype) { - struct sock *sk = orig_skb->sk; struct sock_exterr_skb *serr; struct sk_buff *skb; int err; @@ -3521,12 +3521,26 @@ void skb_tstamp_tx(struct sk_buff *orig_skb, memset(serr, 0, sizeof(*serr)); serr->ee.ee_errno = ENOMSG; serr->ee.ee_origin = SO_EE_ORIGIN_TIMESTAMPING; + serr->ee.ee_info = tstype; + if (sk->sk_tsflags & SOF_TIMESTAMPING_OPT_ID) { + serr->ee.ee_data = skb_shinfo(skb)->tskey; + if (sk->sk_protocol == IPPROTO_TCP) + serr->ee.ee_data -= sk->sk_tskey; + } err = sock_queue_err_skb(sk, skb); if (err) kfree_skb(skb); } +EXPORT_SYMBOL_GPL(__skb_tstamp_tx); + +void skb_tstamp_tx(struct sk_buff *orig_skb, + struct skb_shared_hwtstamps *hwtstamps) +{ + return __skb_tstamp_tx(orig_skb, hwtstamps, orig_skb->sk, + SCM_TSTAMP_SND); +} EXPORT_SYMBOL_GPL(skb_tstamp_tx); void skb_complete_wifi_ack(struct sk_buff *skb, bool acked) diff --git a/net/core/sock.c b/net/core/sock.c index 026e01f70274..2714811afbd8 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -491,7 +491,7 @@ int sk_receive_skb(struct sock *sk, struct sk_buff *skb, const int nested) skb->dev = NULL; - if (sk_rcvqueues_full(sk, skb, sk->sk_rcvbuf)) { + if (sk_rcvqueues_full(sk, sk->sk_rcvbuf)) { atomic_inc(&sk->sk_drops); goto discard_and_relse; } @@ -848,24 +848,25 @@ set_rcvbuf: ret = -EINVAL; break; } - sock_valbool_flag(sk, SOCK_TIMESTAMPING_TX_HARDWARE, - val & SOF_TIMESTAMPING_TX_HARDWARE); - sock_valbool_flag(sk, SOCK_TIMESTAMPING_TX_SOFTWARE, - val & SOF_TIMESTAMPING_TX_SOFTWARE); - sock_valbool_flag(sk, SOCK_TIMESTAMPING_RX_HARDWARE, - val & SOF_TIMESTAMPING_RX_HARDWARE); + if (val & SOF_TIMESTAMPING_OPT_ID && + !(sk->sk_tsflags & SOF_TIMESTAMPING_OPT_ID)) { + if (sk->sk_protocol == IPPROTO_TCP) { + if (sk->sk_state != TCP_ESTABLISHED) { + ret = -EINVAL; + break; + } + sk->sk_tskey = tcp_sk(sk)->snd_una; + } else { + sk->sk_tskey = 0; + } + } + sk->sk_tsflags = val; if (val & SOF_TIMESTAMPING_RX_SOFTWARE) sock_enable_timestamp(sk, SOCK_TIMESTAMPING_RX_SOFTWARE); else sock_disable_timestamp(sk, (1UL << SOCK_TIMESTAMPING_RX_SOFTWARE)); - sock_valbool_flag(sk, SOCK_TIMESTAMPING_SOFTWARE, - val & SOF_TIMESTAMPING_SOFTWARE); - sock_valbool_flag(sk, SOCK_TIMESTAMPING_SYS_HARDWARE, - val & SOF_TIMESTAMPING_SYS_HARDWARE); - sock_valbool_flag(sk, SOCK_TIMESTAMPING_RAW_HARDWARE, - val & SOF_TIMESTAMPING_RAW_HARDWARE); break; case SO_RCVLOWAT: @@ -1091,21 +1092,7 @@ int sock_getsockopt(struct socket *sock, int level, int optname, break; case SO_TIMESTAMPING: - v.val = 0; - if (sock_flag(sk, SOCK_TIMESTAMPING_TX_HARDWARE)) - v.val |= SOF_TIMESTAMPING_TX_HARDWARE; - if (sock_flag(sk, SOCK_TIMESTAMPING_TX_SOFTWARE)) - v.val |= SOF_TIMESTAMPING_TX_SOFTWARE; - if (sock_flag(sk, SOCK_TIMESTAMPING_RX_HARDWARE)) - v.val |= SOF_TIMESTAMPING_RX_HARDWARE; - if (sock_flag(sk, SOCK_TIMESTAMPING_RX_SOFTWARE)) - v.val |= SOF_TIMESTAMPING_RX_SOFTWARE; - if (sock_flag(sk, SOCK_TIMESTAMPING_SOFTWARE)) - v.val |= SOF_TIMESTAMPING_SOFTWARE; - if (sock_flag(sk, SOCK_TIMESTAMPING_SYS_HARDWARE)) - v.val |= SOF_TIMESTAMPING_SYS_HARDWARE; - if (sock_flag(sk, SOCK_TIMESTAMPING_RAW_HARDWARE)) - v.val |= SOF_TIMESTAMPING_RAW_HARDWARE; + v.val = sk->sk_tsflags; break; case SO_RCVTIMEO: @@ -1478,6 +1465,7 @@ static void sk_update_clone(const struct sock *sk, struct sock *newsk) struct sock *sk_clone_lock(const struct sock *sk, const gfp_t priority) { struct sock *newsk; + bool is_charged = true; newsk = sk_prot_alloc(sk->sk_prot, priority, sk->sk_family); if (newsk != NULL) { @@ -1522,9 +1510,13 @@ struct sock *sk_clone_lock(const struct sock *sk, const gfp_t priority) filter = rcu_dereference_protected(newsk->sk_filter, 1); if (filter != NULL) - sk_filter_charge(newsk, filter); + /* though it's an empty new sock, the charging may fail + * if sysctl_optmem_max was changed between creation of + * original socket and cloning + */ + is_charged = sk_filter_charge(newsk, filter); - if (unlikely(xfrm_sk_clone_policy(newsk))) { + if (unlikely(!is_charged || xfrm_sk_clone_policy(newsk))) { /* It is still raw copy of parent, so invalidate * destructor and make plain sk_free() */ newsk->sk_destruct = NULL; diff --git a/net/core/sock_diag.c b/net/core/sock_diag.c index a4216a4c9572..ad704c757bb4 100644 --- a/net/core/sock_diag.c +++ b/net/core/sock_diag.c @@ -68,8 +68,8 @@ int sock_diag_put_filterinfo(bool may_report_filterinfo, struct sock *sk, if (!filter) goto out; - fprog = filter->orig_prog; - flen = sk_filter_proglen(fprog); + fprog = filter->prog->orig_prog; + flen = bpf_classic_proglen(fprog); attr = nla_reserve(skb, attrtype, flen); if (attr == NULL) { diff --git a/net/core/timestamping.c b/net/core/timestamping.c index 6521dfd8b7c8..a8770391ea5b 100644 --- a/net/core/timestamping.c +++ b/net/core/timestamping.c @@ -43,31 +43,22 @@ void skb_clone_tx_timestamp(struct sk_buff *skb) return; type = classify(skb); + if (type == PTP_CLASS_NONE) + return; + + phydev = skb->dev->phydev; + if (likely(phydev->drv->txtstamp)) { + if (!atomic_inc_not_zero(&sk->sk_refcnt)) + return; - switch (type) { - case PTP_CLASS_V1_IPV4: - case PTP_CLASS_V1_IPV6: - case PTP_CLASS_V2_IPV4: - case PTP_CLASS_V2_IPV6: - case PTP_CLASS_V2_L2: - case PTP_CLASS_V2_VLAN: - phydev = skb->dev->phydev; - if (likely(phydev->drv->txtstamp)) { - if (!atomic_inc_not_zero(&sk->sk_refcnt)) - return; - - clone = skb_clone(skb, GFP_ATOMIC); - if (!clone) { - sock_put(sk); - return; - } - - clone->sk = sk; - phydev->drv->txtstamp(phydev, clone, type); + clone = skb_clone(skb, GFP_ATOMIC); + if (!clone) { + sock_put(sk); + return; } - break; - default: - break; + + clone->sk = sk; + phydev->drv->txtstamp(phydev, clone, type); } } EXPORT_SYMBOL_GPL(skb_clone_tx_timestamp); @@ -114,20 +105,12 @@ bool skb_defer_rx_timestamp(struct sk_buff *skb) __skb_pull(skb, ETH_HLEN); - switch (type) { - case PTP_CLASS_V1_IPV4: - case PTP_CLASS_V1_IPV6: - case PTP_CLASS_V2_IPV4: - case PTP_CLASS_V2_IPV6: - case PTP_CLASS_V2_L2: - case PTP_CLASS_V2_VLAN: - phydev = skb->dev->phydev; - if (likely(phydev->drv->rxtstamp)) - return phydev->drv->rxtstamp(phydev, skb, type); - break; - default: - break; - } + if (type == PTP_CLASS_NONE) + return false; + + phydev = skb->dev->phydev; + if (likely(phydev->drv->rxtstamp)) + return phydev->drv->rxtstamp(phydev, skb, type); return false; } diff --git a/net/dcb/dcbnl.c b/net/dcb/dcbnl.c index f8b98d89c285..ca11d283bbeb 100644 --- a/net/dcb/dcbnl.c +++ b/net/dcb/dcbnl.c @@ -471,7 +471,11 @@ static int dcbnl_getapp(struct net_device *netdev, struct nlmsghdr *nlh, id = nla_get_u16(app_tb[DCB_APP_ATTR_ID]); if (netdev->dcbnl_ops->getapp) { - up = netdev->dcbnl_ops->getapp(netdev, idtype, id); + ret = netdev->dcbnl_ops->getapp(netdev, idtype, id); + if (ret < 0) + return ret; + else + up = ret; } else { struct dcb_app app = { .selector = idtype, @@ -538,6 +542,8 @@ static int dcbnl_setapp(struct net_device *netdev, struct nlmsghdr *nlh, if (netdev->dcbnl_ops->setapp) { ret = netdev->dcbnl_ops->setapp(netdev, idtype, id, up); + if (ret < 0) + return ret; } else { struct dcb_app app; app.selector = idtype; @@ -1770,7 +1776,7 @@ EXPORT_SYMBOL(dcb_getapp); * * Priority 0 is an invalid priority in CEE spec. This routine * removes applications from the app list if the priority is - * set to zero. + * set to zero. Priority is expected to be 8-bit 802.1p user priority bitmap */ int dcb_setapp(struct net_device *dev, struct dcb_app *new) { @@ -1831,7 +1837,8 @@ EXPORT_SYMBOL(dcb_ieee_getapp_mask); * * This adds Application data to the list. Multiple application * entries may exists for the same selector and protocol as long - * as the priorities are different. + * as the priorities are different. Priority is expected to be a + * 3-bit unsigned integer */ int dcb_ieee_setapp(struct net_device *dev, struct dcb_app *new) { diff --git a/net/dccp/ipv6.c b/net/dccp/ipv6.c index 4db3c2a1679c..04cb17d4b0ce 100644 --- a/net/dccp/ipv6.c +++ b/net/dccp/ipv6.c @@ -386,7 +386,7 @@ static int dccp_v6_conn_request(struct sock *sk, struct sk_buff *skb) if (sk_acceptq_is_full(sk) && inet_csk_reqsk_queue_young(sk) > 1) goto drop; - req = inet6_reqsk_alloc(&dccp6_request_sock_ops); + req = inet_reqsk_alloc(&dccp6_request_sock_ops); if (req == NULL) goto drop; diff --git a/net/dccp/minisocks.c b/net/dccp/minisocks.c index c69eb9c4fbb8..b50dc436db1f 100644 --- a/net/dccp/minisocks.c +++ b/net/dccp/minisocks.c @@ -55,11 +55,9 @@ void dccp_time_wait(struct sock *sk, int state, int timeo) const int rto = (icsk->icsk_rto << 2) - (icsk->icsk_rto >> 1); #if IS_ENABLED(CONFIG_IPV6) if (tw->tw_family == PF_INET6) { - const struct ipv6_pinfo *np = inet6_sk(sk); - tw->tw_v6_daddr = sk->sk_v6_daddr; tw->tw_v6_rcv_saddr = sk->sk_v6_rcv_saddr; - tw->tw_ipv6only = np->ipv6only; + tw->tw_ipv6only = sk->sk_ipv6only; } #endif /* Linkage updates. */ diff --git a/net/dsa/dsa.c b/net/dsa/dsa.c index 5db37cef50a9..0a49632fac47 100644 --- a/net/dsa/dsa.c +++ b/net/dsa/dsa.c @@ -351,8 +351,7 @@ static void dsa_of_free_platform_data(struct dsa_platform_data *pd) for (i = 0; i < pd->nr_chips; i++) { port_index = 0; while (port_index < DSA_MAX_PORTS) { - if (pd->chip[i].port_names[port_index]) - kfree(pd->chip[i].port_names[port_index]); + kfree(pd->chip[i].port_names[port_index]); port_index++; } kfree(pd->chip[i].rtable); diff --git a/net/dsa/slave.c b/net/dsa/slave.c index 64c5af0a10dd..45a1e34c89e0 100644 --- a/net/dsa/slave.c +++ b/net/dsa/slave.c @@ -340,8 +340,8 @@ dsa_slave_create(struct dsa_switch *ds, struct device *parent, struct dsa_slave_priv *p; int ret; - slave_dev = alloc_netdev(sizeof(struct dsa_slave_priv), - name, ether_setup); + slave_dev = alloc_netdev(sizeof(struct dsa_slave_priv), name, + NET_NAME_UNKNOWN, ether_setup); if (slave_dev == NULL) return slave_dev; diff --git a/net/ethernet/eth.c b/net/ethernet/eth.c index 5dc638cad2e1..f405e0592407 100644 --- a/net/ethernet/eth.c +++ b/net/ethernet/eth.c @@ -390,7 +390,8 @@ EXPORT_SYMBOL(ether_setup); struct net_device *alloc_etherdev_mqs(int sizeof_priv, unsigned int txqs, unsigned int rxqs) { - return alloc_netdev_mqs(sizeof_priv, "eth%d", ether_setup, txqs, rxqs); + return alloc_netdev_mqs(sizeof_priv, "eth%d", NET_NAME_UNKNOWN, + ether_setup, txqs, rxqs); } EXPORT_SYMBOL(alloc_etherdev_mqs); diff --git a/net/hsr/Makefile b/net/hsr/Makefile index b68359f181cc..9ae972a820f4 100644 --- a/net/hsr/Makefile +++ b/net/hsr/Makefile @@ -4,4 +4,5 @@ obj-$(CONFIG_HSR) += hsr.o -hsr-y := hsr_main.o hsr_framereg.o hsr_device.o hsr_netlink.o +hsr-y := hsr_main.o hsr_framereg.o hsr_device.o \ + hsr_netlink.o hsr_slave.o hsr_forward.o diff --git a/net/hsr/hsr_device.c b/net/hsr/hsr_device.c index e5302b7f7ca9..a138d75751df 100644 --- a/net/hsr/hsr_device.c +++ b/net/hsr/hsr_device.c @@ -1,4 +1,4 @@ -/* Copyright 2011-2013 Autronica Fire and Security AS +/* Copyright 2011-2014 Autronica Fire and Security AS * * This program is free software; you can redistribute it and/or modify it * under the terms of the GNU General Public License as published by the Free @@ -6,7 +6,7 @@ * any later version. * * Author(s): - * 2011-2013 Arvid Brodin, arvid.brodin@xdin.com + * 2011-2014 Arvid Brodin, arvid.brodin@alten.se * * This file contains device methods for creating, using and destroying * virtual HSR devices. @@ -15,12 +15,13 @@ #include <linux/netdevice.h> #include <linux/skbuff.h> #include <linux/etherdevice.h> -#include <linux/if_arp.h> #include <linux/rtnetlink.h> #include <linux/pkt_sched.h> #include "hsr_device.h" +#include "hsr_slave.h" #include "hsr_framereg.h" #include "hsr_main.h" +#include "hsr_forward.h" static bool is_admin_up(struct net_device *dev) @@ -45,75 +46,108 @@ static void __hsr_set_operstate(struct net_device *dev, int transition) } } -void hsr_set_operstate(struct net_device *hsr_dev, struct net_device *slave1, - struct net_device *slave2) +static void hsr_set_operstate(struct hsr_port *master, bool has_carrier) { - if (!is_admin_up(hsr_dev)) { - __hsr_set_operstate(hsr_dev, IF_OPER_DOWN); + if (!is_admin_up(master->dev)) { + __hsr_set_operstate(master->dev, IF_OPER_DOWN); return; } - if (is_slave_up(slave1) || is_slave_up(slave2)) - __hsr_set_operstate(hsr_dev, IF_OPER_UP); + if (has_carrier) + __hsr_set_operstate(master->dev, IF_OPER_UP); else - __hsr_set_operstate(hsr_dev, IF_OPER_LOWERLAYERDOWN); + __hsr_set_operstate(master->dev, IF_OPER_LOWERLAYERDOWN); } -void hsr_set_carrier(struct net_device *hsr_dev, struct net_device *slave1, - struct net_device *slave2) +static bool hsr_check_carrier(struct hsr_port *master) { - if (is_slave_up(slave1) || is_slave_up(slave2)) - netif_carrier_on(hsr_dev); + struct hsr_port *port; + bool has_carrier; + + has_carrier = false; + + rcu_read_lock(); + hsr_for_each_port(master->hsr, port) + if ((port->type != HSR_PT_MASTER) && is_slave_up(port->dev)) { + has_carrier = true; + break; + } + rcu_read_unlock(); + + if (has_carrier) + netif_carrier_on(master->dev); else - netif_carrier_off(hsr_dev); + netif_carrier_off(master->dev); + + return has_carrier; } -void hsr_check_announce(struct net_device *hsr_dev, int old_operstate) +static void hsr_check_announce(struct net_device *hsr_dev, + unsigned char old_operstate) { - struct hsr_priv *hsr_priv; + struct hsr_priv *hsr; - hsr_priv = netdev_priv(hsr_dev); + hsr = netdev_priv(hsr_dev); if ((hsr_dev->operstate == IF_OPER_UP) && (old_operstate != IF_OPER_UP)) { /* Went up */ - hsr_priv->announce_count = 0; - hsr_priv->announce_timer.expires = jiffies + + hsr->announce_count = 0; + hsr->announce_timer.expires = jiffies + msecs_to_jiffies(HSR_ANNOUNCE_INTERVAL); - add_timer(&hsr_priv->announce_timer); + add_timer(&hsr->announce_timer); } if ((hsr_dev->operstate != IF_OPER_UP) && (old_operstate == IF_OPER_UP)) /* Went down */ - del_timer(&hsr_priv->announce_timer); + del_timer(&hsr->announce_timer); } - -int hsr_get_max_mtu(struct hsr_priv *hsr_priv) +void hsr_check_carrier_and_operstate(struct hsr_priv *hsr) { - int mtu_max; - - if (hsr_priv->slave[0] && hsr_priv->slave[1]) - mtu_max = min(hsr_priv->slave[0]->mtu, hsr_priv->slave[1]->mtu); - else if (hsr_priv->slave[0]) - mtu_max = hsr_priv->slave[0]->mtu; - else if (hsr_priv->slave[1]) - mtu_max = hsr_priv->slave[1]->mtu; - else - mtu_max = HSR_TAGLEN; + struct hsr_port *master; + unsigned char old_operstate; + bool has_carrier; - return mtu_max - HSR_TAGLEN; + master = hsr_port_get_hsr(hsr, HSR_PT_MASTER); + /* netif_stacked_transfer_operstate() cannot be used here since + * it doesn't set IF_OPER_LOWERLAYERDOWN (?) + */ + old_operstate = master->dev->operstate; + has_carrier = hsr_check_carrier(master); + hsr_set_operstate(master, has_carrier); + hsr_check_announce(master->dev, old_operstate); } +int hsr_get_max_mtu(struct hsr_priv *hsr) +{ + unsigned int mtu_max; + struct hsr_port *port; + + mtu_max = ETH_DATA_LEN; + rcu_read_lock(); + hsr_for_each_port(hsr, port) + if (port->type != HSR_PT_MASTER) + mtu_max = min(port->dev->mtu, mtu_max); + rcu_read_unlock(); + + if (mtu_max < HSR_HLEN) + return 0; + return mtu_max - HSR_HLEN; +} + + static int hsr_dev_change_mtu(struct net_device *dev, int new_mtu) { - struct hsr_priv *hsr_priv; + struct hsr_priv *hsr; + struct hsr_port *master; - hsr_priv = netdev_priv(dev); + hsr = netdev_priv(dev); + master = hsr_port_get_hsr(hsr, HSR_PT_MASTER); - if (new_mtu > hsr_get_max_mtu(hsr_priv)) { - netdev_info(hsr_priv->dev, "A HSR master's MTU cannot be greater than the smallest MTU of its slaves minus the HSR Tag length (%d octets).\n", - HSR_TAGLEN); + if (new_mtu > hsr_get_max_mtu(hsr)) { + netdev_info(master->dev, "A HSR master's MTU cannot be greater than the smallest MTU of its slaves minus the HSR Tag length (%d octets).\n", + HSR_HLEN); return -EINVAL; } @@ -124,164 +158,95 @@ static int hsr_dev_change_mtu(struct net_device *dev, int new_mtu) static int hsr_dev_open(struct net_device *dev) { - struct hsr_priv *hsr_priv; - int i; - char *slave_name; + struct hsr_priv *hsr; + struct hsr_port *port; + char designation; - hsr_priv = netdev_priv(dev); + hsr = netdev_priv(dev); + designation = '\0'; - for (i = 0; i < HSR_MAX_SLAVE; i++) { - if (hsr_priv->slave[i]) - slave_name = hsr_priv->slave[i]->name; - else - slave_name = "null"; - - if (!is_slave_up(hsr_priv->slave[i])) - netdev_warn(dev, "Slave %c (%s) is not up; please bring it up to get a working HSR network\n", - 'A' + i, slave_name); + rcu_read_lock(); + hsr_for_each_port(hsr, port) { + if (port->type == HSR_PT_MASTER) + continue; + switch (port->type) { + case HSR_PT_SLAVE_A: + designation = 'A'; + break; + case HSR_PT_SLAVE_B: + designation = 'B'; + break; + default: + designation = '?'; + } + if (!is_slave_up(port->dev)) + netdev_warn(dev, "Slave %c (%s) is not up; please bring it up to get a fully working HSR network\n", + designation, port->dev->name); } + rcu_read_unlock(); + + if (designation == '\0') + netdev_warn(dev, "No slave devices configured\n"); return 0; } + static int hsr_dev_close(struct net_device *dev) { - /* Nothing to do here. We could try to restore the state of the slaves - * to what they were before being changed by the hsr master dev's state, - * but they might have been changed manually in the mean time too, so - * taking them up or down here might be confusing and is probably not a - * good idea. - */ + /* Nothing to do here. */ return 0; } -static void hsr_fill_tag(struct hsr_ethhdr *hsr_ethhdr, struct hsr_priv *hsr_priv) +static netdev_features_t hsr_features_recompute(struct hsr_priv *hsr, + netdev_features_t features) { - unsigned long irqflags; + netdev_features_t mask; + struct hsr_port *port; - /* IEC 62439-1:2010, p 48, says the 4-bit "path" field can take values - * between 0001-1001 ("ring identifier", for regular HSR frames), - * or 1111 ("HSR management", supervision frames). Unfortunately, the - * spec writers forgot to explain what a "ring identifier" is, or - * how it is used. So we just set this to 0001 for regular frames, - * and 1111 for supervision frames. - */ - set_hsr_tag_path(&hsr_ethhdr->hsr_tag, 0x1); + mask = features; - /* IEC 62439-1:2010, p 12: "The link service data unit in an Ethernet - * frame is the content of the frame located between the Length/Type - * field and the Frame Check Sequence." + /* Mask out all features that, if supported by one device, should be + * enabled for all devices (see NETIF_F_ONE_FOR_ALL). * - * IEC 62439-3, p 48, specifies the "original LPDU" to include the - * original "LT" field (what "LT" means is not explained anywhere as - * far as I can see - perhaps "Length/Type"?). So LSDU_size might - * equal original length + 2. - * Also, the fact that this field is not used anywhere (might be used - * by a RedBox connecting HSR and PRP nets?) means I cannot test its - * correctness. Instead of guessing, I set this to 0 here, to make any - * problems immediately apparent. Anyone using this driver with PRP/HSR - * RedBoxes might need to fix this... + * Anything that's off in mask will not be enabled - so only things + * that were in features originally, and also is in NETIF_F_ONE_FOR_ALL, + * may become enabled. */ - set_hsr_tag_LSDU_size(&hsr_ethhdr->hsr_tag, 0); - - spin_lock_irqsave(&hsr_priv->seqnr_lock, irqflags); - hsr_ethhdr->hsr_tag.sequence_nr = htons(hsr_priv->sequence_nr); - hsr_priv->sequence_nr++; - spin_unlock_irqrestore(&hsr_priv->seqnr_lock, irqflags); + features &= ~NETIF_F_ONE_FOR_ALL; + hsr_for_each_port(hsr, port) + features = netdev_increment_features(features, + port->dev->features, + mask); - hsr_ethhdr->hsr_tag.encap_proto = hsr_ethhdr->ethhdr.h_proto; - - hsr_ethhdr->ethhdr.h_proto = htons(ETH_P_PRP); + return features; } -static int slave_xmit(struct sk_buff *skb, struct hsr_priv *hsr_priv, - enum hsr_dev_idx dev_idx) +static netdev_features_t hsr_fix_features(struct net_device *dev, + netdev_features_t features) { - struct hsr_ethhdr *hsr_ethhdr; - - hsr_ethhdr = (struct hsr_ethhdr *) skb->data; + struct hsr_priv *hsr = netdev_priv(dev); - skb->dev = hsr_priv->slave[dev_idx]; - - hsr_addr_subst_dest(hsr_priv, &hsr_ethhdr->ethhdr, dev_idx); - - /* Address substitution (IEC62439-3 pp 26, 50): replace mac - * address of outgoing frame with that of the outgoing slave's. - */ - ether_addr_copy(hsr_ethhdr->ethhdr.h_source, skb->dev->dev_addr); - - return dev_queue_xmit(skb); + return hsr_features_recompute(hsr, features); } static int hsr_dev_xmit(struct sk_buff *skb, struct net_device *dev) { - struct hsr_priv *hsr_priv; - struct hsr_ethhdr *hsr_ethhdr; - struct sk_buff *skb2; - int res1, res2; - - hsr_priv = netdev_priv(dev); - hsr_ethhdr = (struct hsr_ethhdr *) skb->data; - - if ((skb->protocol != htons(ETH_P_PRP)) || - (hsr_ethhdr->ethhdr.h_proto != htons(ETH_P_PRP))) { - hsr_fill_tag(hsr_ethhdr, hsr_priv); - skb->protocol = htons(ETH_P_PRP); - } - - skb2 = pskb_copy(skb, GFP_ATOMIC); - - res1 = NET_XMIT_DROP; - if (likely(hsr_priv->slave[HSR_DEV_SLAVE_A])) - res1 = slave_xmit(skb, hsr_priv, HSR_DEV_SLAVE_A); + struct hsr_priv *hsr = netdev_priv(dev); + struct hsr_port *master; - res2 = NET_XMIT_DROP; - if (likely(skb2 && hsr_priv->slave[HSR_DEV_SLAVE_B])) - res2 = slave_xmit(skb2, hsr_priv, HSR_DEV_SLAVE_B); - - if (likely(res1 == NET_XMIT_SUCCESS || res1 == NET_XMIT_CN || - res2 == NET_XMIT_SUCCESS || res2 == NET_XMIT_CN)) { - hsr_priv->dev->stats.tx_packets++; - hsr_priv->dev->stats.tx_bytes += skb->len; - } else { - hsr_priv->dev->stats.tx_dropped++; - } + master = hsr_port_get_hsr(hsr, HSR_PT_MASTER); + skb->dev = master->dev; + hsr_forward_skb(skb, master); return NETDEV_TX_OK; } -static int hsr_header_create(struct sk_buff *skb, struct net_device *dev, - unsigned short type, const void *daddr, - const void *saddr, unsigned int len) -{ - int res; - - /* Make room for the HSR tag now. We will fill it in later (in - * hsr_dev_xmit) - */ - if (skb_headroom(skb) < HSR_TAGLEN + ETH_HLEN) - return -ENOBUFS; - skb_push(skb, HSR_TAGLEN); - - /* To allow VLAN/HSR combos we should probably use - * res = dev_hard_header(skb, dev, type, daddr, saddr, len + HSR_TAGLEN); - * here instead. It would require other changes too, though - e.g. - * separate headers for each slave etc... - */ - res = eth_header(skb, dev, type, daddr, saddr, len + HSR_TAGLEN); - if (res <= 0) - return res; - skb_reset_mac_header(skb); - - return res + HSR_TAGLEN; -} - - static const struct header_ops hsr_header_ops = { - .create = hsr_header_create, + .create = eth_header, .parse = eth_header_parse, }; @@ -291,67 +256,63 @@ static const struct header_ops hsr_header_ops = { */ static int hsr_pad(int size) { - const int min_size = ETH_ZLEN - HSR_TAGLEN - ETH_HLEN; + const int min_size = ETH_ZLEN - HSR_HLEN - ETH_HLEN; if (size >= min_size) return size; return min_size; } -static void send_hsr_supervision_frame(struct net_device *hsr_dev, u8 type) +static void send_hsr_supervision_frame(struct hsr_port *master, u8 type) { - struct hsr_priv *hsr_priv; struct sk_buff *skb; int hlen, tlen; struct hsr_sup_tag *hsr_stag; struct hsr_sup_payload *hsr_sp; unsigned long irqflags; - hlen = LL_RESERVED_SPACE(hsr_dev); - tlen = hsr_dev->needed_tailroom; + hlen = LL_RESERVED_SPACE(master->dev); + tlen = master->dev->needed_tailroom; skb = alloc_skb(hsr_pad(sizeof(struct hsr_sup_payload)) + hlen + tlen, GFP_ATOMIC); if (skb == NULL) return; - hsr_priv = netdev_priv(hsr_dev); - skb_reserve(skb, hlen); - skb->dev = hsr_dev; + skb->dev = master->dev; skb->protocol = htons(ETH_P_PRP); skb->priority = TC_PRIO_CONTROL; if (dev_hard_header(skb, skb->dev, ETH_P_PRP, - hsr_priv->sup_multicast_addr, - skb->dev->dev_addr, skb->len) < 0) + master->hsr->sup_multicast_addr, + skb->dev->dev_addr, skb->len) <= 0) goto out; + skb_reset_mac_header(skb); - skb_pull(skb, sizeof(struct ethhdr)); - hsr_stag = (typeof(hsr_stag)) skb->data; + hsr_stag = (typeof(hsr_stag)) skb_put(skb, sizeof(*hsr_stag)); set_hsr_stag_path(hsr_stag, 0xf); set_hsr_stag_HSR_Ver(hsr_stag, 0); - spin_lock_irqsave(&hsr_priv->seqnr_lock, irqflags); - hsr_stag->sequence_nr = htons(hsr_priv->sequence_nr); - hsr_priv->sequence_nr++; - spin_unlock_irqrestore(&hsr_priv->seqnr_lock, irqflags); + spin_lock_irqsave(&master->hsr->seqnr_lock, irqflags); + hsr_stag->sequence_nr = htons(master->hsr->sequence_nr); + master->hsr->sequence_nr++; + spin_unlock_irqrestore(&master->hsr->seqnr_lock, irqflags); hsr_stag->HSR_TLV_Type = type; hsr_stag->HSR_TLV_Length = 12; - skb_push(skb, sizeof(struct ethhdr)); - /* Payload: MacAddressA */ hsr_sp = (typeof(hsr_sp)) skb_put(skb, sizeof(*hsr_sp)); - ether_addr_copy(hsr_sp->MacAddressA, hsr_dev->dev_addr); + ether_addr_copy(hsr_sp->MacAddressA, master->dev->dev_addr); - dev_queue_xmit(skb); + hsr_forward_skb(skb, master); return; out: + WARN_ON_ONCE("HSR: Could not send supervision frame\n"); kfree_skb(skb); } @@ -360,59 +321,32 @@ out: */ static void hsr_announce(unsigned long data) { - struct hsr_priv *hsr_priv; + struct hsr_priv *hsr; + struct hsr_port *master; - hsr_priv = (struct hsr_priv *) data; + hsr = (struct hsr_priv *) data; - if (hsr_priv->announce_count < 3) { - send_hsr_supervision_frame(hsr_priv->dev, HSR_TLV_ANNOUNCE); - hsr_priv->announce_count++; + rcu_read_lock(); + master = hsr_port_get_hsr(hsr, HSR_PT_MASTER); + + if (hsr->announce_count < 3) { + send_hsr_supervision_frame(master, HSR_TLV_ANNOUNCE); + hsr->announce_count++; } else { - send_hsr_supervision_frame(hsr_priv->dev, HSR_TLV_LIFE_CHECK); + send_hsr_supervision_frame(master, HSR_TLV_LIFE_CHECK); } - if (hsr_priv->announce_count < 3) - hsr_priv->announce_timer.expires = jiffies + + if (hsr->announce_count < 3) + hsr->announce_timer.expires = jiffies + msecs_to_jiffies(HSR_ANNOUNCE_INTERVAL); else - hsr_priv->announce_timer.expires = jiffies + + hsr->announce_timer.expires = jiffies + msecs_to_jiffies(HSR_LIFE_CHECK_INTERVAL); - if (is_admin_up(hsr_priv->dev)) - add_timer(&hsr_priv->announce_timer); -} - - -static void restore_slaves(struct net_device *hsr_dev) -{ - struct hsr_priv *hsr_priv; - int i; - int res; - - hsr_priv = netdev_priv(hsr_dev); - - rtnl_lock(); - - /* Restore promiscuity */ - for (i = 0; i < HSR_MAX_SLAVE; i++) { - if (!hsr_priv->slave[i]) - continue; - res = dev_set_promiscuity(hsr_priv->slave[i], -1); - if (res) - netdev_info(hsr_dev, - "Cannot restore slave promiscuity (%s, %d)\n", - hsr_priv->slave[i]->name, res); - } - - rtnl_unlock(); -} - -static void reclaim_hsr_dev(struct rcu_head *rh) -{ - struct hsr_priv *hsr_priv; + if (is_admin_up(master->dev)) + add_timer(&hsr->announce_timer); - hsr_priv = container_of(rh, struct hsr_priv, rcu_head); - free_netdev(hsr_priv->dev); + rcu_read_unlock(); } @@ -421,14 +355,18 @@ static void reclaim_hsr_dev(struct rcu_head *rh) */ static void hsr_dev_destroy(struct net_device *hsr_dev) { - struct hsr_priv *hsr_priv; + struct hsr_priv *hsr; + struct hsr_port *port; - hsr_priv = netdev_priv(hsr_dev); + hsr = netdev_priv(hsr_dev); + hsr_for_each_port(hsr, port) + hsr_del_port(port); - del_timer(&hsr_priv->announce_timer); - unregister_hsr_master(hsr_priv); /* calls list_del_rcu on hsr_priv */ - restore_slaves(hsr_dev); - call_rcu(&hsr_priv->rcu_head, reclaim_hsr_dev); /* reclaim hsr_priv */ + del_timer_sync(&hsr->prune_timer); + del_timer_sync(&hsr->announce_timer); + + synchronize_rcu(); + free_netdev(hsr_dev); } static const struct net_device_ops hsr_device_ops = { @@ -436,62 +374,51 @@ static const struct net_device_ops hsr_device_ops = { .ndo_open = hsr_dev_open, .ndo_stop = hsr_dev_close, .ndo_start_xmit = hsr_dev_xmit, + .ndo_fix_features = hsr_fix_features, }; +static struct device_type hsr_type = { + .name = "hsr", +}; void hsr_dev_setup(struct net_device *dev) { random_ether_addr(dev->dev_addr); ether_setup(dev); - dev->header_ops = &hsr_header_ops; - dev->netdev_ops = &hsr_device_ops; - dev->tx_queue_len = 0; + dev->header_ops = &hsr_header_ops; + dev->netdev_ops = &hsr_device_ops; + SET_NETDEV_DEVTYPE(dev, &hsr_type); + dev->tx_queue_len = 0; dev->destructor = hsr_dev_destroy; + + dev->hw_features = NETIF_F_SG | NETIF_F_FRAGLIST | NETIF_F_HIGHDMA | + NETIF_F_GSO_MASK | NETIF_F_HW_CSUM | + NETIF_F_HW_VLAN_CTAG_TX; + + dev->features = dev->hw_features; + + /* Prevent recursive tx locking */ + dev->features |= NETIF_F_LLTX; + /* VLAN on top of HSR needs testing and probably some work on + * hsr_header_create() etc. + */ + dev->features |= NETIF_F_VLAN_CHALLENGED; + /* Not sure about this. Taken from bridge code. netdev_features.h says + * it means "Does not change network namespaces". + */ + dev->features |= NETIF_F_NETNS_LOCAL; } /* Return true if dev is a HSR master; return false otherwise. */ -bool is_hsr_master(struct net_device *dev) +inline bool is_hsr_master(struct net_device *dev) { return (dev->netdev_ops->ndo_start_xmit == hsr_dev_xmit); } -static int check_slave_ok(struct net_device *dev) -{ - /* Don't allow HSR on non-ethernet like devices */ - if ((dev->flags & IFF_LOOPBACK) || (dev->type != ARPHRD_ETHER) || - (dev->addr_len != ETH_ALEN)) { - netdev_info(dev, "Cannot use loopback or non-ethernet device as HSR slave.\n"); - return -EINVAL; - } - - /* Don't allow enslaving hsr devices */ - if (is_hsr_master(dev)) { - netdev_info(dev, "Cannot create trees of HSR devices.\n"); - return -EINVAL; - } - - if (is_hsr_slave(dev)) { - netdev_info(dev, "This device is already a HSR slave.\n"); - return -EINVAL; - } - - if (dev->priv_flags & IFF_802_1Q_VLAN) { - netdev_info(dev, "HSR on top of VLAN is not yet supported in this driver.\n"); - return -EINVAL; - } - - /* HSR over bonded devices has not been tested, but I'm not sure it - * won't work... - */ - - return 0; -} - - /* Default multicast address for HSR Supervision frames */ static const unsigned char def_multicast_addr[ETH_ALEN] __aligned(2) = { 0x01, 0x15, 0x4e, 0x00, 0x01, 0x00 @@ -500,97 +427,74 @@ static const unsigned char def_multicast_addr[ETH_ALEN] __aligned(2) = { int hsr_dev_finalize(struct net_device *hsr_dev, struct net_device *slave[2], unsigned char multicast_spec) { - struct hsr_priv *hsr_priv; - int i; + struct hsr_priv *hsr; + struct hsr_port *port; int res; - hsr_priv = netdev_priv(hsr_dev); - hsr_priv->dev = hsr_dev; - INIT_LIST_HEAD(&hsr_priv->node_db); - INIT_LIST_HEAD(&hsr_priv->self_node_db); - for (i = 0; i < HSR_MAX_SLAVE; i++) - hsr_priv->slave[i] = slave[i]; - - spin_lock_init(&hsr_priv->seqnr_lock); - /* Overflow soon to find bugs easier: */ - hsr_priv->sequence_nr = USHRT_MAX - 1024; - - init_timer(&hsr_priv->announce_timer); - hsr_priv->announce_timer.function = hsr_announce; - hsr_priv->announce_timer.data = (unsigned long) hsr_priv; + hsr = netdev_priv(hsr_dev); + INIT_LIST_HEAD(&hsr->ports); + INIT_LIST_HEAD(&hsr->node_db); + INIT_LIST_HEAD(&hsr->self_node_db); - ether_addr_copy(hsr_priv->sup_multicast_addr, def_multicast_addr); - hsr_priv->sup_multicast_addr[ETH_ALEN - 1] = multicast_spec; + ether_addr_copy(hsr_dev->dev_addr, slave[0]->dev_addr); -/* FIXME: should I modify the value of these? - * - * - hsr_dev->flags - i.e. - * IFF_MASTER/SLAVE? - * - hsr_dev->priv_flags - i.e. - * IFF_EBRIDGE? - * IFF_TX_SKB_SHARING? - * IFF_HSR_MASTER/SLAVE? - */ + /* Make sure we recognize frames from ourselves in hsr_rcv() */ + res = hsr_create_self_node(&hsr->self_node_db, hsr_dev->dev_addr, + slave[1]->dev_addr); + if (res < 0) + return res; - for (i = 0; i < HSR_MAX_SLAVE; i++) { - res = check_slave_ok(slave[i]); - if (res) - return res; - } + spin_lock_init(&hsr->seqnr_lock); + /* Overflow soon to find bugs easier: */ + hsr->sequence_nr = HSR_SEQNR_START; - hsr_dev->features = slave[0]->features & slave[1]->features; - /* Prevent recursive tx locking */ - hsr_dev->features |= NETIF_F_LLTX; - /* VLAN on top of HSR needs testing and probably some work on - * hsr_header_create() etc. - */ - hsr_dev->features |= NETIF_F_VLAN_CHALLENGED; + init_timer(&hsr->announce_timer); + hsr->announce_timer.function = hsr_announce; + hsr->announce_timer.data = (unsigned long) hsr; - /* Set hsr_dev's MAC address to that of mac_slave1 */ - ether_addr_copy(hsr_dev->dev_addr, hsr_priv->slave[0]->dev_addr); + init_timer(&hsr->prune_timer); + hsr->prune_timer.function = hsr_prune_nodes; + hsr->prune_timer.data = (unsigned long) hsr; - /* Set required header length */ - for (i = 0; i < HSR_MAX_SLAVE; i++) { - if (slave[i]->hard_header_len + HSR_TAGLEN > - hsr_dev->hard_header_len) - hsr_dev->hard_header_len = - slave[i]->hard_header_len + HSR_TAGLEN; - } + ether_addr_copy(hsr->sup_multicast_addr, def_multicast_addr); + hsr->sup_multicast_addr[ETH_ALEN - 1] = multicast_spec; - /* MTU */ - for (i = 0; i < HSR_MAX_SLAVE; i++) - if (slave[i]->mtu - HSR_TAGLEN < hsr_dev->mtu) - hsr_dev->mtu = slave[i]->mtu - HSR_TAGLEN; + /* FIXME: should I modify the value of these? + * + * - hsr_dev->flags - i.e. + * IFF_MASTER/SLAVE? + * - hsr_dev->priv_flags - i.e. + * IFF_EBRIDGE? + * IFF_TX_SKB_SHARING? + * IFF_HSR_MASTER/SLAVE? + */ /* Make sure the 1st call to netif_carrier_on() gets through */ netif_carrier_off(hsr_dev); - /* Promiscuity */ - for (i = 0; i < HSR_MAX_SLAVE; i++) { - res = dev_set_promiscuity(slave[i], 1); - if (res) { - netdev_info(hsr_dev, "Cannot set slave promiscuity (%s, %d)\n", - slave[i]->name, res); - goto fail; - } - } + res = hsr_add_port(hsr, hsr_dev, HSR_PT_MASTER); + if (res) + return res; - /* Make sure we recognize frames from ourselves in hsr_rcv() */ - res = hsr_create_self_node(&hsr_priv->self_node_db, - hsr_dev->dev_addr, - hsr_priv->slave[1]->dev_addr); - if (res < 0) + res = register_netdevice(hsr_dev); + if (res) goto fail; - res = register_netdevice(hsr_dev); + res = hsr_add_port(hsr, slave[0], HSR_PT_SLAVE_A); + if (res) + goto fail; + res = hsr_add_port(hsr, slave[1], HSR_PT_SLAVE_B); if (res) goto fail; - register_hsr_master(hsr_priv); + hsr->prune_timer.expires = jiffies + msecs_to_jiffies(PRUNE_PERIOD); + add_timer(&hsr->prune_timer); return 0; fail: - restore_slaves(hsr_dev); + hsr_for_each_port(hsr, port) + hsr_del_port(port); + return res; } diff --git a/net/hsr/hsr_device.h b/net/hsr/hsr_device.h index 2c7148e73914..108a5d59d2a6 100644 --- a/net/hsr/hsr_device.h +++ b/net/hsr/hsr_device.h @@ -1,4 +1,4 @@ -/* Copyright 2011-2013 Autronica Fire and Security AS +/* Copyright 2011-2014 Autronica Fire and Security AS * * This program is free software; you can redistribute it and/or modify it * under the terms of the GNU General Public License as published by the Free @@ -6,7 +6,7 @@ * any later version. * * Author(s): - * 2011-2013 Arvid Brodin, arvid.brodin@xdin.com + * 2011-2014 Arvid Brodin, arvid.brodin@alten.se */ #ifndef __HSR_DEVICE_H @@ -18,12 +18,8 @@ void hsr_dev_setup(struct net_device *dev); int hsr_dev_finalize(struct net_device *hsr_dev, struct net_device *slave[2], unsigned char multicast_spec); -void hsr_set_operstate(struct net_device *hsr_dev, struct net_device *slave1, - struct net_device *slave2); -void hsr_set_carrier(struct net_device *hsr_dev, struct net_device *slave1, - struct net_device *slave2); -void hsr_check_announce(struct net_device *hsr_dev, int old_operstate); +void hsr_check_carrier_and_operstate(struct hsr_priv *hsr); bool is_hsr_master(struct net_device *dev); -int hsr_get_max_mtu(struct hsr_priv *hsr_priv); +int hsr_get_max_mtu(struct hsr_priv *hsr); #endif /* __HSR_DEVICE_H */ diff --git a/net/hsr/hsr_forward.c b/net/hsr/hsr_forward.c new file mode 100644 index 000000000000..7871ed6d3825 --- /dev/null +++ b/net/hsr/hsr_forward.c @@ -0,0 +1,368 @@ +/* Copyright 2011-2014 Autronica Fire and Security AS + * + * This program is free software; you can redistribute it and/or modify it + * under the terms of the GNU General Public License as published by the Free + * Software Foundation; either version 2 of the License, or (at your option) + * any later version. + * + * Author(s): + * 2011-2014 Arvid Brodin, arvid.brodin@alten.se + */ + +#include "hsr_forward.h" +#include <linux/types.h> +#include <linux/skbuff.h> +#include <linux/etherdevice.h> +#include <linux/if_vlan.h> +#include "hsr_main.h" +#include "hsr_framereg.h" + + +struct hsr_node; + +struct hsr_frame_info { + struct sk_buff *skb_std; + struct sk_buff *skb_hsr; + struct hsr_port *port_rcv; + struct hsr_node *node_src; + u16 sequence_nr; + bool is_supervision; + bool is_vlan; + bool is_local_dest; + bool is_local_exclusive; +}; + + +/* The uses I can see for these HSR supervision frames are: + * 1) Use the frames that are sent after node initialization ("HSR_TLV.Type = + * 22") to reset any sequence_nr counters belonging to that node. Useful if + * the other node's counter has been reset for some reason. + * -- + * Or not - resetting the counter and bridging the frame would create a + * loop, unfortunately. + * + * 2) Use the LifeCheck frames to detect ring breaks. I.e. if no LifeCheck + * frame is received from a particular node, we know something is wrong. + * We just register these (as with normal frames) and throw them away. + * + * 3) Allow different MAC addresses for the two slave interfaces, using the + * MacAddressA field. + */ +static bool is_supervision_frame(struct hsr_priv *hsr, struct sk_buff *skb) +{ + struct hsr_ethhdr_sp *hdr; + + WARN_ON_ONCE(!skb_mac_header_was_set(skb)); + hdr = (struct hsr_ethhdr_sp *) skb_mac_header(skb); + + if (!ether_addr_equal(hdr->ethhdr.h_dest, + hsr->sup_multicast_addr)) + return false; + + if (get_hsr_stag_path(&hdr->hsr_sup) != 0x0f) + return false; + if ((hdr->hsr_sup.HSR_TLV_Type != HSR_TLV_ANNOUNCE) && + (hdr->hsr_sup.HSR_TLV_Type != HSR_TLV_LIFE_CHECK)) + return false; + if (hdr->hsr_sup.HSR_TLV_Length != 12) + return false; + + return true; +} + + +static struct sk_buff *create_stripped_skb(struct sk_buff *skb_in, + struct hsr_frame_info *frame) +{ + struct sk_buff *skb; + int copylen; + unsigned char *dst, *src; + + skb_pull(skb_in, HSR_HLEN); + skb = __pskb_copy(skb_in, skb_headroom(skb_in) - HSR_HLEN, GFP_ATOMIC); + skb_push(skb_in, HSR_HLEN); + if (skb == NULL) + return NULL; + + skb_reset_mac_header(skb); + + if (skb->ip_summed == CHECKSUM_PARTIAL) + skb->csum_start -= HSR_HLEN; + + copylen = 2*ETH_ALEN; + if (frame->is_vlan) + copylen += VLAN_HLEN; + src = skb_mac_header(skb_in); + dst = skb_mac_header(skb); + memcpy(dst, src, copylen); + + skb->protocol = eth_hdr(skb)->h_proto; + return skb; +} + +static struct sk_buff *frame_get_stripped_skb(struct hsr_frame_info *frame, + struct hsr_port *port) +{ + if (!frame->skb_std) + frame->skb_std = create_stripped_skb(frame->skb_hsr, frame); + return skb_clone(frame->skb_std, GFP_ATOMIC); +} + + +static void hsr_fill_tag(struct sk_buff *skb, struct hsr_frame_info *frame, + struct hsr_port *port) +{ + struct hsr_ethhdr *hsr_ethhdr; + int lane_id; + int lsdu_size; + + if (port->type == HSR_PT_SLAVE_A) + lane_id = 0; + else + lane_id = 1; + + lsdu_size = skb->len - 14; + if (frame->is_vlan) + lsdu_size -= 4; + + hsr_ethhdr = (struct hsr_ethhdr *) skb_mac_header(skb); + + set_hsr_tag_path(&hsr_ethhdr->hsr_tag, lane_id); + set_hsr_tag_LSDU_size(&hsr_ethhdr->hsr_tag, lsdu_size); + hsr_ethhdr->hsr_tag.sequence_nr = htons(frame->sequence_nr); + hsr_ethhdr->hsr_tag.encap_proto = hsr_ethhdr->ethhdr.h_proto; + hsr_ethhdr->ethhdr.h_proto = htons(ETH_P_PRP); +} + +static struct sk_buff *create_tagged_skb(struct sk_buff *skb_o, + struct hsr_frame_info *frame, + struct hsr_port *port) +{ + int movelen; + unsigned char *dst, *src; + struct sk_buff *skb; + + /* Create the new skb with enough headroom to fit the HSR tag */ + skb = __pskb_copy(skb_o, skb_headroom(skb_o) + HSR_HLEN, GFP_ATOMIC); + if (skb == NULL) + return NULL; + skb_reset_mac_header(skb); + + if (skb->ip_summed == CHECKSUM_PARTIAL) + skb->csum_start += HSR_HLEN; + + movelen = ETH_HLEN; + if (frame->is_vlan) + movelen += VLAN_HLEN; + + src = skb_mac_header(skb); + dst = skb_push(skb, HSR_HLEN); + memmove(dst, src, movelen); + skb_reset_mac_header(skb); + + hsr_fill_tag(skb, frame, port); + + return skb; +} + +/* If the original frame was an HSR tagged frame, just clone it to be sent + * unchanged. Otherwise, create a private frame especially tagged for 'port'. + */ +static struct sk_buff *frame_get_tagged_skb(struct hsr_frame_info *frame, + struct hsr_port *port) +{ + if (frame->skb_hsr) + return skb_clone(frame->skb_hsr, GFP_ATOMIC); + + if ((port->type != HSR_PT_SLAVE_A) && (port->type != HSR_PT_SLAVE_B)) { + WARN_ONCE(1, "HSR: Bug: trying to create a tagged frame for a non-ring port"); + return NULL; + } + + return create_tagged_skb(frame->skb_std, frame, port); +} + + +static void hsr_deliver_master(struct sk_buff *skb, struct net_device *dev, + struct hsr_node *node_src) +{ + bool was_multicast_frame; + int res; + + was_multicast_frame = (skb->pkt_type == PACKET_MULTICAST); + hsr_addr_subst_source(node_src, skb); + skb_pull(skb, ETH_HLEN); + res = netif_rx(skb); + if (res == NET_RX_DROP) { + dev->stats.rx_dropped++; + } else { + dev->stats.rx_packets++; + dev->stats.rx_bytes += skb->len; + if (was_multicast_frame) + dev->stats.multicast++; + } +} + +static int hsr_xmit(struct sk_buff *skb, struct hsr_port *port, + struct hsr_frame_info *frame) +{ + if (frame->port_rcv->type == HSR_PT_MASTER) { + hsr_addr_subst_dest(frame->node_src, skb, port); + + /* Address substitution (IEC62439-3 pp 26, 50): replace mac + * address of outgoing frame with that of the outgoing slave's. + */ + ether_addr_copy(eth_hdr(skb)->h_source, port->dev->dev_addr); + } + return dev_queue_xmit(skb); +} + + +/* Forward the frame through all devices except: + * - Back through the receiving device + * - If it's a HSR frame: through a device where it has passed before + * - To the local HSR master only if the frame is directly addressed to it, or + * a non-supervision multicast or broadcast frame. + * + * HSR slave devices should insert a HSR tag into the frame, or forward the + * frame unchanged if it's already tagged. Interlink devices should strip HSR + * tags if they're of the non-HSR type (but only after duplicate discard). The + * master device always strips HSR tags. + */ +static void hsr_forward_do(struct hsr_frame_info *frame) +{ + struct hsr_port *port; + struct sk_buff *skb; + + hsr_for_each_port(frame->port_rcv->hsr, port) { + /* Don't send frame back the way it came */ + if (port == frame->port_rcv) + continue; + + /* Don't deliver locally unless we should */ + if ((port->type == HSR_PT_MASTER) && !frame->is_local_dest) + continue; + + /* Deliver frames directly addressed to us to master only */ + if ((port->type != HSR_PT_MASTER) && frame->is_local_exclusive) + continue; + + /* Don't send frame over port where it has been sent before */ + if (hsr_register_frame_out(port, frame->node_src, + frame->sequence_nr)) + continue; + + if (frame->is_supervision && (port->type == HSR_PT_MASTER)) { + hsr_handle_sup_frame(frame->skb_hsr, + frame->node_src, + frame->port_rcv); + continue; + } + + if (port->type != HSR_PT_MASTER) + skb = frame_get_tagged_skb(frame, port); + else + skb = frame_get_stripped_skb(frame, port); + if (skb == NULL) { + /* FIXME: Record the dropped frame? */ + continue; + } + + skb->dev = port->dev; + if (port->type == HSR_PT_MASTER) + hsr_deliver_master(skb, port->dev, frame->node_src); + else + hsr_xmit(skb, port, frame); + } +} + + +static void check_local_dest(struct hsr_priv *hsr, struct sk_buff *skb, + struct hsr_frame_info *frame) +{ + struct net_device *master_dev; + + master_dev = hsr_port_get_hsr(hsr, HSR_PT_MASTER)->dev; + + if (hsr_addr_is_self(hsr, eth_hdr(skb)->h_dest)) { + frame->is_local_exclusive = true; + skb->pkt_type = PACKET_HOST; + } else { + frame->is_local_exclusive = false; + } + + if ((skb->pkt_type == PACKET_HOST) || + (skb->pkt_type == PACKET_MULTICAST) || + (skb->pkt_type == PACKET_BROADCAST)) { + frame->is_local_dest = true; + } else { + frame->is_local_dest = false; + } +} + + +static int hsr_fill_frame_info(struct hsr_frame_info *frame, + struct sk_buff *skb, struct hsr_port *port) +{ + struct ethhdr *ethhdr; + unsigned long irqflags; + + frame->is_supervision = is_supervision_frame(port->hsr, skb); + frame->node_src = hsr_get_node(&port->hsr->node_db, skb, + frame->is_supervision); + if (frame->node_src == NULL) + return -1; /* Unknown node and !is_supervision, or no mem */ + + ethhdr = (struct ethhdr *) skb_mac_header(skb); + frame->is_vlan = false; + if (ethhdr->h_proto == htons(ETH_P_8021Q)) { + frame->is_vlan = true; + /* FIXME: */ + WARN_ONCE(1, "HSR: VLAN not yet supported"); + } + if (ethhdr->h_proto == htons(ETH_P_PRP)) { + frame->skb_std = NULL; + frame->skb_hsr = skb; + frame->sequence_nr = hsr_get_skb_sequence_nr(skb); + } else { + frame->skb_std = skb; + frame->skb_hsr = NULL; + /* Sequence nr for the master node */ + spin_lock_irqsave(&port->hsr->seqnr_lock, irqflags); + frame->sequence_nr = port->hsr->sequence_nr; + port->hsr->sequence_nr++; + spin_unlock_irqrestore(&port->hsr->seqnr_lock, irqflags); + } + + frame->port_rcv = port; + check_local_dest(port->hsr, skb, frame); + + return 0; +} + +/* Must be called holding rcu read lock (because of the port parameter) */ +void hsr_forward_skb(struct sk_buff *skb, struct hsr_port *port) +{ + struct hsr_frame_info frame; + + if (skb_mac_header(skb) != skb->data) { + WARN_ONCE(1, "%s:%d: Malformed frame (port_src %s)\n", + __FILE__, __LINE__, port->dev->name); + goto out_drop; + } + + if (hsr_fill_frame_info(&frame, skb, port) < 0) + goto out_drop; + hsr_register_frame_in(frame.node_src, port, frame.sequence_nr); + hsr_forward_do(&frame); + + if (frame.skb_hsr != NULL) + kfree_skb(frame.skb_hsr); + if (frame.skb_std != NULL) + kfree_skb(frame.skb_std); + return; + +out_drop: + port->dev->stats.tx_dropped++; + kfree_skb(skb); +} diff --git a/net/hsr/hsr_forward.h b/net/hsr/hsr_forward.h new file mode 100644 index 000000000000..5c5bc4b6b75f --- /dev/null +++ b/net/hsr/hsr_forward.h @@ -0,0 +1,20 @@ +/* Copyright 2011-2014 Autronica Fire and Security AS + * + * This program is free software; you can redistribute it and/or modify it + * under the terms of the GNU General Public License as published by the Free + * Software Foundation; either version 2 of the License, or (at your option) + * any later version. + * + * Author(s): + * 2011-2014 Arvid Brodin, arvid.brodin@alten.se + */ + +#ifndef __HSR_FORWARD_H +#define __HSR_FORWARD_H + +#include <linux/netdevice.h> +#include "hsr_main.h" + +void hsr_forward_skb(struct sk_buff *skb, struct hsr_port *port); + +#endif /* __HSR_FORWARD_H */ diff --git a/net/hsr/hsr_framereg.c b/net/hsr/hsr_framereg.c index 83e58449366a..bace124d14ef 100644 --- a/net/hsr/hsr_framereg.c +++ b/net/hsr/hsr_framereg.c @@ -1,4 +1,4 @@ -/* Copyright 2011-2013 Autronica Fire and Security AS +/* Copyright 2011-2014 Autronica Fire and Security AS * * This program is free software; you can redistribute it and/or modify it * under the terms of the GNU General Public License as published by the Free @@ -6,7 +6,7 @@ * any later version. * * Author(s): - * 2011-2013 Arvid Brodin, arvid.brodin@xdin.com + * 2011-2014 Arvid Brodin, arvid.brodin@alten.se * * The HSR spec says never to forward the same frame twice on the same * interface. A frame is identified by its source MAC address and its HSR @@ -23,71 +23,68 @@ #include "hsr_netlink.h" -struct node_entry { - struct list_head mac_list; - unsigned char MacAddressA[ETH_ALEN]; - unsigned char MacAddressB[ETH_ALEN]; - enum hsr_dev_idx AddrB_if; /* The local slave through which AddrB - * frames are received from this node - */ - unsigned long time_in[HSR_MAX_SLAVE]; - bool time_in_stale[HSR_MAX_SLAVE]; - u16 seq_out[HSR_MAX_DEV]; - struct rcu_head rcu_head; +struct hsr_node { + struct list_head mac_list; + unsigned char MacAddressA[ETH_ALEN]; + unsigned char MacAddressB[ETH_ALEN]; + /* Local slave through which AddrB frames are received from this node */ + enum hsr_port_type AddrB_port; + unsigned long time_in[HSR_PT_PORTS]; + bool time_in_stale[HSR_PT_PORTS]; + u16 seq_out[HSR_PT_PORTS]; + struct rcu_head rcu_head; }; -/* TODO: use hash lists for mac addresses (linux/jhash.h)? */ +/* TODO: use hash lists for mac addresses (linux/jhash.h)? */ -/* Search for mac entry. Caller must hold rcu read lock. +/* seq_nr_after(a, b) - return true if a is after (higher in sequence than) b, + * false otherwise. */ -static struct node_entry *find_node_by_AddrA(struct list_head *node_db, - const unsigned char addr[ETH_ALEN]) +static bool seq_nr_after(u16 a, u16 b) { - struct node_entry *node; - - list_for_each_entry_rcu(node, node_db, mac_list) { - if (ether_addr_equal(node->MacAddressA, addr)) - return node; - } + /* Remove inconsistency where + * seq_nr_after(a, b) == seq_nr_before(a, b) + */ + if ((int) b - a == 32768) + return false; - return NULL; + return (((s16) (b - a)) < 0); } +#define seq_nr_before(a, b) seq_nr_after((b), (a)) +#define seq_nr_after_or_eq(a, b) (!seq_nr_before((a), (b))) +#define seq_nr_before_or_eq(a, b) (!seq_nr_after((a), (b))) -/* Search for mac entry. Caller must hold rcu read lock. - */ -static struct node_entry *find_node_by_AddrB(struct list_head *node_db, - const unsigned char addr[ETH_ALEN]) +bool hsr_addr_is_self(struct hsr_priv *hsr, unsigned char *addr) { - struct node_entry *node; + struct hsr_node *node; - list_for_each_entry_rcu(node, node_db, mac_list) { - if (ether_addr_equal(node->MacAddressB, addr)) - return node; + node = list_first_or_null_rcu(&hsr->self_node_db, struct hsr_node, + mac_list); + if (!node) { + WARN_ONCE(1, "HSR: No self node\n"); + return false; } - return NULL; -} + if (ether_addr_equal(addr, node->MacAddressA)) + return true; + if (ether_addr_equal(addr, node->MacAddressB)) + return true; + return false; +} /* Search for mac entry. Caller must hold rcu read lock. */ -struct node_entry *hsr_find_node(struct list_head *node_db, struct sk_buff *skb) +static struct hsr_node *find_node_by_AddrA(struct list_head *node_db, + const unsigned char addr[ETH_ALEN]) { - struct node_entry *node; - struct ethhdr *ethhdr; - - if (!skb_mac_header_was_set(skb)) - return NULL; - - ethhdr = (struct ethhdr *) skb_mac_header(skb); + struct hsr_node *node; list_for_each_entry_rcu(node, node_db, mac_list) { - if (ether_addr_equal(node->MacAddressA, ethhdr->h_source)) - return node; - if (ether_addr_equal(node->MacAddressB, ethhdr->h_source)) + if (ether_addr_equal(node->MacAddressA, addr)) return node; } @@ -102,7 +99,7 @@ int hsr_create_self_node(struct list_head *self_node_db, unsigned char addr_a[ETH_ALEN], unsigned char addr_b[ETH_ALEN]) { - struct node_entry *node, *oldnode; + struct hsr_node *node, *oldnode; node = kmalloc(sizeof(*node), GFP_KERNEL); if (!node) @@ -113,7 +110,7 @@ int hsr_create_self_node(struct list_head *self_node_db, rcu_read_lock(); oldnode = list_first_or_null_rcu(self_node_db, - struct node_entry, mac_list); + struct hsr_node, mac_list); if (oldnode) { list_replace_rcu(&oldnode->mac_list, &node->mac_list); rcu_read_unlock(); @@ -128,135 +125,144 @@ int hsr_create_self_node(struct list_head *self_node_db, } -/* Add/merge node to the database of nodes. 'skb' must contain an HSR - * supervision frame. - * - If the supervision header's MacAddressA field is not yet in the database, - * this frame is from an hitherto unknown node - add it to the database. - * - If the sender's MAC address is not the same as its MacAddressA address, - * the node is using PICS_SUBS (address substitution). Record the sender's - * address as the node's MacAddressB. - * - * This function needs to work even if the sender node has changed one of its - * slaves' MAC addresses. In this case, there are four different cases described - * by (Addr-changed, received-from) pairs as follows. Note that changing the - * SlaveA address is equal to changing the node's own address: - * - * - (AddrB, SlaveB): The new AddrB will be recorded by PICS_SUBS code since - * node == NULL. - * - (AddrB, SlaveA): Will work as usual (the AddrB change won't be detected - * from this frame). - * - * - (AddrA, SlaveB): The old node will be found. We need to detect this and - * remove the node. - * - (AddrA, SlaveA): A new node will be registered (non-PICS_SUBS at first). - * The old one will be pruned after HSR_NODE_FORGET_TIME. - * - * We also need to detect if the sender's SlaveA and SlaveB cables have been - * swapped. +/* Allocate an hsr_node and add it to node_db. 'addr' is the node's AddressA; + * seq_out is used to initialize filtering of outgoing duplicate frames + * originating from the newly added node. */ -struct node_entry *hsr_merge_node(struct hsr_priv *hsr_priv, - struct node_entry *node, - struct sk_buff *skb, - enum hsr_dev_idx dev_idx) +struct hsr_node *hsr_add_node(struct list_head *node_db, unsigned char addr[], + u16 seq_out) { - struct hsr_sup_payload *hsr_sp; - struct hsr_ethhdr_sp *hsr_ethsup; - int i; + struct hsr_node *node; unsigned long now; - - hsr_ethsup = (struct hsr_ethhdr_sp *) skb_mac_header(skb); - hsr_sp = (struct hsr_sup_payload *) skb->data; - - if (node && !ether_addr_equal(node->MacAddressA, hsr_sp->MacAddressA)) { - /* Node has changed its AddrA, frame was received from SlaveB */ - list_del_rcu(&node->mac_list); - kfree_rcu(node, rcu_head); - node = NULL; - } - - if (node && (dev_idx == node->AddrB_if) && - !ether_addr_equal(node->MacAddressB, hsr_ethsup->ethhdr.h_source)) { - /* Cables have been swapped */ - list_del_rcu(&node->mac_list); - kfree_rcu(node, rcu_head); - node = NULL; - } - - if (node && (dev_idx != node->AddrB_if) && - (node->AddrB_if != HSR_DEV_NONE) && - !ether_addr_equal(node->MacAddressA, hsr_ethsup->ethhdr.h_source)) { - /* Cables have been swapped */ - list_del_rcu(&node->mac_list); - kfree_rcu(node, rcu_head); - node = NULL; - } - - if (node) - return node; - - node = find_node_by_AddrA(&hsr_priv->node_db, hsr_sp->MacAddressA); - if (node) { - /* Node is known, but frame was received from an unknown - * address. Node is PICS_SUBS capable; merge its AddrB. - */ - ether_addr_copy(node->MacAddressB, hsr_ethsup->ethhdr.h_source); - node->AddrB_if = dev_idx; - return node; - } + int i; node = kzalloc(sizeof(*node), GFP_ATOMIC); if (!node) return NULL; - ether_addr_copy(node->MacAddressA, hsr_sp->MacAddressA); - ether_addr_copy(node->MacAddressB, hsr_ethsup->ethhdr.h_source); - if (!ether_addr_equal(hsr_sp->MacAddressA, hsr_ethsup->ethhdr.h_source)) - node->AddrB_if = dev_idx; - else - node->AddrB_if = HSR_DEV_NONE; + ether_addr_copy(node->MacAddressA, addr); /* We are only interested in time diffs here, so use current jiffies * as initialization. (0 could trigger an spurious ring error warning). */ now = jiffies; - for (i = 0; i < HSR_MAX_SLAVE; i++) + for (i = 0; i < HSR_PT_PORTS; i++) node->time_in[i] = now; - for (i = 0; i < HSR_MAX_DEV; i++) - node->seq_out[i] = ntohs(hsr_ethsup->hsr_sup.sequence_nr) - 1; + for (i = 0; i < HSR_PT_PORTS; i++) + node->seq_out[i] = seq_out; - list_add_tail_rcu(&node->mac_list, &hsr_priv->node_db); + list_add_tail_rcu(&node->mac_list, node_db); return node; } +/* Get the hsr_node from which 'skb' was sent. + */ +struct hsr_node *hsr_get_node(struct list_head *node_db, struct sk_buff *skb, + bool is_sup) +{ + struct hsr_node *node; + struct ethhdr *ethhdr; + u16 seq_out; + + if (!skb_mac_header_was_set(skb)) + return NULL; + + ethhdr = (struct ethhdr *) skb_mac_header(skb); + + list_for_each_entry_rcu(node, node_db, mac_list) { + if (ether_addr_equal(node->MacAddressA, ethhdr->h_source)) + return node; + if (ether_addr_equal(node->MacAddressB, ethhdr->h_source)) + return node; + } + + if (!is_sup) + return NULL; /* Only supervision frame may create node entry */ + + if (ethhdr->h_proto == htons(ETH_P_PRP)) { + /* Use the existing sequence_nr from the tag as starting point + * for filtering duplicate frames. + */ + seq_out = hsr_get_skb_sequence_nr(skb) - 1; + } else { + WARN_ONCE(1, "%s: Non-HSR frame\n", __func__); + seq_out = 0; + } + + return hsr_add_node(node_db, ethhdr->h_source, seq_out); +} + +/* Use the Supervision frame's info about an eventual MacAddressB for merging + * nodes that has previously had their MacAddressB registered as a separate + * node. + */ +void hsr_handle_sup_frame(struct sk_buff *skb, struct hsr_node *node_curr, + struct hsr_port *port_rcv) +{ + struct hsr_node *node_real; + struct hsr_sup_payload *hsr_sp; + struct list_head *node_db; + int i; + + skb_pull(skb, sizeof(struct hsr_ethhdr_sp)); + hsr_sp = (struct hsr_sup_payload *) skb->data; + + if (ether_addr_equal(eth_hdr(skb)->h_source, hsr_sp->MacAddressA)) + /* Not sent from MacAddressB of a PICS_SUBS capable node */ + goto done; + + /* Merge node_curr (registered on MacAddressB) into node_real */ + node_db = &port_rcv->hsr->node_db; + node_real = find_node_by_AddrA(node_db, hsr_sp->MacAddressA); + if (!node_real) + /* No frame received from AddrA of this node yet */ + node_real = hsr_add_node(node_db, hsr_sp->MacAddressA, + HSR_SEQNR_START - 1); + if (!node_real) + goto done; /* No mem */ + if (node_real == node_curr) + /* Node has already been merged */ + goto done; + + ether_addr_copy(node_real->MacAddressB, eth_hdr(skb)->h_source); + for (i = 0; i < HSR_PT_PORTS; i++) { + if (!node_curr->time_in_stale[i] && + time_after(node_curr->time_in[i], node_real->time_in[i])) { + node_real->time_in[i] = node_curr->time_in[i]; + node_real->time_in_stale[i] = node_curr->time_in_stale[i]; + } + if (seq_nr_after(node_curr->seq_out[i], node_real->seq_out[i])) + node_real->seq_out[i] = node_curr->seq_out[i]; + } + node_real->AddrB_port = port_rcv->type; + + list_del_rcu(&node_curr->mac_list); + kfree_rcu(node_curr, rcu_head); + +done: + skb_push(skb, sizeof(struct hsr_ethhdr_sp)); +} + /* 'skb' is a frame meant for this host, that is to be passed to upper layers. * - * If the frame was sent by a node's B interface, replace the sender + * If the frame was sent by a node's B interface, replace the source * address with that node's "official" address (MacAddressA) so that upper * layers recognize where it came from. */ -void hsr_addr_subst_source(struct hsr_priv *hsr_priv, struct sk_buff *skb) +void hsr_addr_subst_source(struct hsr_node *node, struct sk_buff *skb) { - struct ethhdr *ethhdr; - struct node_entry *node; - if (!skb_mac_header_was_set(skb)) { WARN_ONCE(1, "%s: Mac header not set\n", __func__); return; } - ethhdr = (struct ethhdr *) skb_mac_header(skb); - rcu_read_lock(); - node = find_node_by_AddrB(&hsr_priv->node_db, ethhdr->h_source); - if (node) - ether_addr_copy(ethhdr->h_source, node->MacAddressA); - rcu_read_unlock(); + memcpy(ð_hdr(skb)->h_source, node->MacAddressA, ETH_ALEN); } - /* 'skb' is a frame meant for another host. - * 'hsr_dev_idx' is the HSR index of the outgoing device + * 'port' is the outgoing interface * * Substitute the target (dest) MAC address if necessary, so the it matches the * recipient interface MAC address, regardless of whether that is the @@ -264,47 +270,44 @@ void hsr_addr_subst_source(struct hsr_priv *hsr_priv, struct sk_buff *skb) * This is needed to keep the packets flowing through switches that learn on * which "side" the different interfaces are. */ -void hsr_addr_subst_dest(struct hsr_priv *hsr_priv, struct ethhdr *ethhdr, - enum hsr_dev_idx dev_idx) +void hsr_addr_subst_dest(struct hsr_node *node_src, struct sk_buff *skb, + struct hsr_port *port) { - struct node_entry *node; + struct hsr_node *node_dst; - rcu_read_lock(); - node = find_node_by_AddrA(&hsr_priv->node_db, ethhdr->h_dest); - if (node && (node->AddrB_if == dev_idx)) - ether_addr_copy(ethhdr->h_dest, node->MacAddressB); - rcu_read_unlock(); -} + if (!skb_mac_header_was_set(skb)) { + WARN_ONCE(1, "%s: Mac header not set\n", __func__); + return; + } + if (!is_unicast_ether_addr(eth_hdr(skb)->h_dest)) + return; -/* seq_nr_after(a, b) - return true if a is after (higher in sequence than) b, - * false otherwise. - */ -static bool seq_nr_after(u16 a, u16 b) -{ - /* Remove inconsistency where - * seq_nr_after(a, b) == seq_nr_before(a, b) - */ - if ((int) b - a == 32768) - return false; + node_dst = find_node_by_AddrA(&port->hsr->node_db, eth_hdr(skb)->h_dest); + if (!node_dst) { + WARN_ONCE(1, "%s: Unknown node\n", __func__); + return; + } + if (port->type != node_dst->AddrB_port) + return; - return (((s16) (b - a)) < 0); + ether_addr_copy(eth_hdr(skb)->h_dest, node_dst->MacAddressB); } -#define seq_nr_before(a, b) seq_nr_after((b), (a)) -#define seq_nr_after_or_eq(a, b) (!seq_nr_before((a), (b))) -#define seq_nr_before_or_eq(a, b) (!seq_nr_after((a), (b))) -void hsr_register_frame_in(struct node_entry *node, enum hsr_dev_idx dev_idx) +void hsr_register_frame_in(struct hsr_node *node, struct hsr_port *port, + u16 sequence_nr) { - if ((dev_idx < 0) || (dev_idx >= HSR_MAX_SLAVE)) { - WARN_ONCE(1, "%s: Invalid dev_idx (%d)\n", __func__, dev_idx); + /* Don't register incoming frames without a valid sequence number. This + * ensures entries of restarted nodes gets pruned so that they can + * re-register and resume communications. + */ + if (seq_nr_before(sequence_nr, node->seq_out[port->type])) return; - } - node->time_in[dev_idx] = jiffies; - node->time_in_stale[dev_idx] = false; -} + node->time_in[port->type] = jiffies; + node->time_in_stale[port->type] = false; +} /* 'skb' is a HSR Ethernet frame (with a HSR tag inserted), with a valid * ethhdr->h_source address and skb->mac_header set. @@ -314,102 +317,87 @@ void hsr_register_frame_in(struct node_entry *node, enum hsr_dev_idx dev_idx) * 0 otherwise, or * negative error code on error */ -int hsr_register_frame_out(struct node_entry *node, enum hsr_dev_idx dev_idx, - struct sk_buff *skb) +int hsr_register_frame_out(struct hsr_port *port, struct hsr_node *node, + u16 sequence_nr) { - struct hsr_ethhdr *hsr_ethhdr; - u16 sequence_nr; - - if ((dev_idx < 0) || (dev_idx >= HSR_MAX_DEV)) { - WARN_ONCE(1, "%s: Invalid dev_idx (%d)\n", __func__, dev_idx); - return -EINVAL; - } - if (!skb_mac_header_was_set(skb)) { - WARN_ONCE(1, "%s: Mac header not set\n", __func__); - return -EINVAL; - } - hsr_ethhdr = (struct hsr_ethhdr *) skb_mac_header(skb); - - sequence_nr = ntohs(hsr_ethhdr->hsr_tag.sequence_nr); - if (seq_nr_before_or_eq(sequence_nr, node->seq_out[dev_idx])) + if (seq_nr_before_or_eq(sequence_nr, node->seq_out[port->type])) return 1; - node->seq_out[dev_idx] = sequence_nr; + node->seq_out[port->type] = sequence_nr; return 0; } - -static bool is_late(struct node_entry *node, enum hsr_dev_idx dev_idx) +static struct hsr_port *get_late_port(struct hsr_priv *hsr, + struct hsr_node *node) { - enum hsr_dev_idx other; - - if (node->time_in_stale[dev_idx]) - return true; - - if (dev_idx == HSR_DEV_SLAVE_A) - other = HSR_DEV_SLAVE_B; - else - other = HSR_DEV_SLAVE_A; - - if (node->time_in_stale[other]) - return false; + if (node->time_in_stale[HSR_PT_SLAVE_A]) + return hsr_port_get_hsr(hsr, HSR_PT_SLAVE_A); + if (node->time_in_stale[HSR_PT_SLAVE_B]) + return hsr_port_get_hsr(hsr, HSR_PT_SLAVE_B); + + if (time_after(node->time_in[HSR_PT_SLAVE_B], + node->time_in[HSR_PT_SLAVE_A] + + msecs_to_jiffies(MAX_SLAVE_DIFF))) + return hsr_port_get_hsr(hsr, HSR_PT_SLAVE_A); + if (time_after(node->time_in[HSR_PT_SLAVE_A], + node->time_in[HSR_PT_SLAVE_B] + + msecs_to_jiffies(MAX_SLAVE_DIFF))) + return hsr_port_get_hsr(hsr, HSR_PT_SLAVE_B); - if (time_after(node->time_in[other], node->time_in[dev_idx] + - msecs_to_jiffies(MAX_SLAVE_DIFF))) - return true; - - return false; + return NULL; } /* Remove stale sequence_nr records. Called by timer every * HSR_LIFE_CHECK_INTERVAL (two seconds or so). */ -void hsr_prune_nodes(struct hsr_priv *hsr_priv) +void hsr_prune_nodes(unsigned long data) { - struct node_entry *node; + struct hsr_priv *hsr; + struct hsr_node *node; + struct hsr_port *port; unsigned long timestamp; unsigned long time_a, time_b; + hsr = (struct hsr_priv *) data; + rcu_read_lock(); - list_for_each_entry_rcu(node, &hsr_priv->node_db, mac_list) { + list_for_each_entry_rcu(node, &hsr->node_db, mac_list) { /* Shorthand */ - time_a = node->time_in[HSR_DEV_SLAVE_A]; - time_b = node->time_in[HSR_DEV_SLAVE_B]; + time_a = node->time_in[HSR_PT_SLAVE_A]; + time_b = node->time_in[HSR_PT_SLAVE_B]; /* Check for timestamps old enough to risk wrap-around */ if (time_after(jiffies, time_a + MAX_JIFFY_OFFSET/2)) - node->time_in_stale[HSR_DEV_SLAVE_A] = true; + node->time_in_stale[HSR_PT_SLAVE_A] = true; if (time_after(jiffies, time_b + MAX_JIFFY_OFFSET/2)) - node->time_in_stale[HSR_DEV_SLAVE_B] = true; + node->time_in_stale[HSR_PT_SLAVE_B] = true; /* Get age of newest frame from node. * At least one time_in is OK here; nodes get pruned long * before both time_ins can get stale */ timestamp = time_a; - if (node->time_in_stale[HSR_DEV_SLAVE_A] || - (!node->time_in_stale[HSR_DEV_SLAVE_B] && + if (node->time_in_stale[HSR_PT_SLAVE_A] || + (!node->time_in_stale[HSR_PT_SLAVE_B] && time_after(time_b, time_a))) timestamp = time_b; /* Warn of ring error only as long as we get frames at all */ if (time_is_after_jiffies(timestamp + msecs_to_jiffies(1.5*MAX_SLAVE_DIFF))) { - - if (is_late(node, HSR_DEV_SLAVE_A)) - hsr_nl_ringerror(hsr_priv, node->MacAddressA, - HSR_DEV_SLAVE_A); - else if (is_late(node, HSR_DEV_SLAVE_B)) - hsr_nl_ringerror(hsr_priv, node->MacAddressA, - HSR_DEV_SLAVE_B); + rcu_read_lock(); + port = get_late_port(hsr, node); + if (port != NULL) + hsr_nl_ringerror(hsr, node->MacAddressA, port); + rcu_read_unlock(); } /* Prune old entries */ if (time_is_before_jiffies(timestamp + msecs_to_jiffies(HSR_NODE_FORGET_TIME))) { - hsr_nl_nodedown(hsr_priv, node->MacAddressA); + hsr_nl_nodedown(hsr, node->MacAddressA); list_del_rcu(&node->mac_list); /* Note that we need to free this entry later: */ kfree_rcu(node, rcu_head); @@ -419,21 +407,21 @@ void hsr_prune_nodes(struct hsr_priv *hsr_priv) } -void *hsr_get_next_node(struct hsr_priv *hsr_priv, void *_pos, +void *hsr_get_next_node(struct hsr_priv *hsr, void *_pos, unsigned char addr[ETH_ALEN]) { - struct node_entry *node; + struct hsr_node *node; if (!_pos) { - node = list_first_or_null_rcu(&hsr_priv->node_db, - struct node_entry, mac_list); + node = list_first_or_null_rcu(&hsr->node_db, + struct hsr_node, mac_list); if (node) ether_addr_copy(addr, node->MacAddressA); return node; } node = _pos; - list_for_each_entry_continue_rcu(node, &hsr_priv->node_db, mac_list) { + list_for_each_entry_continue_rcu(node, &hsr->node_db, mac_list) { ether_addr_copy(addr, node->MacAddressA); return node; } @@ -442,7 +430,7 @@ void *hsr_get_next_node(struct hsr_priv *hsr_priv, void *_pos, } -int hsr_get_node_data(struct hsr_priv *hsr_priv, +int hsr_get_node_data(struct hsr_priv *hsr, const unsigned char *addr, unsigned char addr_b[ETH_ALEN], unsigned int *addr_b_ifindex, @@ -451,12 +439,13 @@ int hsr_get_node_data(struct hsr_priv *hsr_priv, int *if2_age, u16 *if2_seq) { - struct node_entry *node; + struct hsr_node *node; + struct hsr_port *port; unsigned long tdiff; rcu_read_lock(); - node = find_node_by_AddrA(&hsr_priv->node_db, addr); + node = find_node_by_AddrA(&hsr->node_db, addr); if (!node) { rcu_read_unlock(); return -ENOENT; /* No such entry */ @@ -464,8 +453,8 @@ int hsr_get_node_data(struct hsr_priv *hsr_priv, ether_addr_copy(addr_b, node->MacAddressB); - tdiff = jiffies - node->time_in[HSR_DEV_SLAVE_A]; - if (node->time_in_stale[HSR_DEV_SLAVE_A]) + tdiff = jiffies - node->time_in[HSR_PT_SLAVE_A]; + if (node->time_in_stale[HSR_PT_SLAVE_A]) *if1_age = INT_MAX; #if HZ <= MSEC_PER_SEC else if (tdiff > msecs_to_jiffies(INT_MAX)) @@ -474,8 +463,8 @@ int hsr_get_node_data(struct hsr_priv *hsr_priv, else *if1_age = jiffies_to_msecs(tdiff); - tdiff = jiffies - node->time_in[HSR_DEV_SLAVE_B]; - if (node->time_in_stale[HSR_DEV_SLAVE_B]) + tdiff = jiffies - node->time_in[HSR_PT_SLAVE_B]; + if (node->time_in_stale[HSR_PT_SLAVE_B]) *if2_age = INT_MAX; #if HZ <= MSEC_PER_SEC else if (tdiff > msecs_to_jiffies(INT_MAX)) @@ -485,13 +474,15 @@ int hsr_get_node_data(struct hsr_priv *hsr_priv, *if2_age = jiffies_to_msecs(tdiff); /* Present sequence numbers as if they were incoming on interface */ - *if1_seq = node->seq_out[HSR_DEV_SLAVE_B]; - *if2_seq = node->seq_out[HSR_DEV_SLAVE_A]; + *if1_seq = node->seq_out[HSR_PT_SLAVE_B]; + *if2_seq = node->seq_out[HSR_PT_SLAVE_A]; - if ((node->AddrB_if != HSR_DEV_NONE) && hsr_priv->slave[node->AddrB_if]) - *addr_b_ifindex = hsr_priv->slave[node->AddrB_if]->ifindex; - else + if (node->AddrB_port != HSR_PT_NONE) { + port = hsr_port_get_hsr(hsr, node->AddrB_port); + *addr_b_ifindex = port->dev->ifindex; + } else { *addr_b_ifindex = -1; + } rcu_read_unlock(); diff --git a/net/hsr/hsr_framereg.h b/net/hsr/hsr_framereg.h index e6c4022030ad..438b40f98f5a 100644 --- a/net/hsr/hsr_framereg.h +++ b/net/hsr/hsr_framereg.h @@ -1,4 +1,4 @@ -/* Copyright 2011-2013 Autronica Fire and Security AS +/* Copyright 2011-2014 Autronica Fire and Security AS * * This program is free software; you can redistribute it and/or modify it * under the terms of the GNU General Public License as published by the Free @@ -6,42 +6,43 @@ * any later version. * * Author(s): - * 2011-2013 Arvid Brodin, arvid.brodin@xdin.com + * 2011-2014 Arvid Brodin, arvid.brodin@alten.se */ -#ifndef _HSR_FRAMEREG_H -#define _HSR_FRAMEREG_H +#ifndef __HSR_FRAMEREG_H +#define __HSR_FRAMEREG_H #include "hsr_main.h" -struct node_entry; +struct hsr_node; -struct node_entry *hsr_find_node(struct list_head *node_db, struct sk_buff *skb); +struct hsr_node *hsr_add_node(struct list_head *node_db, unsigned char addr[], + u16 seq_out); +struct hsr_node *hsr_get_node(struct list_head *node_db, struct sk_buff *skb, + bool is_sup); +void hsr_handle_sup_frame(struct sk_buff *skb, struct hsr_node *node_curr, + struct hsr_port *port); +bool hsr_addr_is_self(struct hsr_priv *hsr, unsigned char *addr); -struct node_entry *hsr_merge_node(struct hsr_priv *hsr_priv, - struct node_entry *node, - struct sk_buff *skb, - enum hsr_dev_idx dev_idx); +void hsr_addr_subst_source(struct hsr_node *node, struct sk_buff *skb); +void hsr_addr_subst_dest(struct hsr_node *node_src, struct sk_buff *skb, + struct hsr_port *port); -void hsr_addr_subst_source(struct hsr_priv *hsr_priv, struct sk_buff *skb); -void hsr_addr_subst_dest(struct hsr_priv *hsr_priv, struct ethhdr *ethhdr, - enum hsr_dev_idx dev_idx); +void hsr_register_frame_in(struct hsr_node *node, struct hsr_port *port, + u16 sequence_nr); +int hsr_register_frame_out(struct hsr_port *port, struct hsr_node *node, + u16 sequence_nr); -void hsr_register_frame_in(struct node_entry *node, enum hsr_dev_idx dev_idx); - -int hsr_register_frame_out(struct node_entry *node, enum hsr_dev_idx dev_idx, - struct sk_buff *skb); - -void hsr_prune_nodes(struct hsr_priv *hsr_priv); +void hsr_prune_nodes(unsigned long data); int hsr_create_self_node(struct list_head *self_node_db, unsigned char addr_a[ETH_ALEN], unsigned char addr_b[ETH_ALEN]); -void *hsr_get_next_node(struct hsr_priv *hsr_priv, void *_pos, +void *hsr_get_next_node(struct hsr_priv *hsr, void *_pos, unsigned char addr[ETH_ALEN]); -int hsr_get_node_data(struct hsr_priv *hsr_priv, +int hsr_get_node_data(struct hsr_priv *hsr, const unsigned char *addr, unsigned char addr_b[ETH_ALEN], unsigned int *addr_b_ifindex, @@ -50,4 +51,4 @@ int hsr_get_node_data(struct hsr_priv *hsr_priv, int *if2_age, u16 *if2_seq); -#endif /* _HSR_FRAMEREG_H */ +#endif /* __HSR_FRAMEREG_H */ diff --git a/net/hsr/hsr_main.c b/net/hsr/hsr_main.c index 3fee5218a691..779d28b65417 100644 --- a/net/hsr/hsr_main.c +++ b/net/hsr/hsr_main.c @@ -1,4 +1,4 @@ -/* Copyright 2011-2013 Autronica Fire and Security AS +/* Copyright 2011-2014 Autronica Fire and Security AS * * This program is free software; you can redistribute it and/or modify it * under the terms of the GNU General Public License as published by the Free @@ -6,11 +6,7 @@ * any later version. * * Author(s): - * 2011-2013 Arvid Brodin, arvid.brodin@xdin.com - * - * In addition to routines for registering and unregistering HSR support, this - * file also contains the receive routine that handles all incoming frames with - * Ethertype (protocol) ETH_P_PRP (HSRv0), and network device event handling. + * 2011-2014 Arvid Brodin, arvid.brodin@alten.se */ #include <linux/netdevice.h> @@ -21,154 +17,71 @@ #include "hsr_device.h" #include "hsr_netlink.h" #include "hsr_framereg.h" - - -/* List of all registered virtual HSR devices */ -static LIST_HEAD(hsr_list); - -void register_hsr_master(struct hsr_priv *hsr_priv) -{ - list_add_tail_rcu(&hsr_priv->hsr_list, &hsr_list); -} - -void unregister_hsr_master(struct hsr_priv *hsr_priv) -{ - struct hsr_priv *hsr_priv_it; - - list_for_each_entry(hsr_priv_it, &hsr_list, hsr_list) - if (hsr_priv_it == hsr_priv) { - list_del_rcu(&hsr_priv_it->hsr_list); - return; - } -} - -bool is_hsr_slave(struct net_device *dev) -{ - struct hsr_priv *hsr_priv_it; - - list_for_each_entry_rcu(hsr_priv_it, &hsr_list, hsr_list) { - if (dev == hsr_priv_it->slave[0]) - return true; - if (dev == hsr_priv_it->slave[1]) - return true; - } - - return false; -} - - -/* If dev is a HSR slave device, return the virtual master device. Return NULL - * otherwise. - */ -static struct hsr_priv *get_hsr_master(struct net_device *dev) -{ - struct hsr_priv *hsr_priv; - - rcu_read_lock(); - list_for_each_entry_rcu(hsr_priv, &hsr_list, hsr_list) - if ((dev == hsr_priv->slave[0]) || - (dev == hsr_priv->slave[1])) { - rcu_read_unlock(); - return hsr_priv; - } - - rcu_read_unlock(); - return NULL; -} - - -/* If dev is a HSR slave device, return the other slave device. Return NULL - * otherwise. - */ -static struct net_device *get_other_slave(struct hsr_priv *hsr_priv, - struct net_device *dev) -{ - if (dev == hsr_priv->slave[0]) - return hsr_priv->slave[1]; - if (dev == hsr_priv->slave[1]) - return hsr_priv->slave[0]; - - return NULL; -} +#include "hsr_slave.h" static int hsr_netdev_notify(struct notifier_block *nb, unsigned long event, void *ptr) { - struct net_device *slave, *other_slave; - struct hsr_priv *hsr_priv; - int old_operstate; + struct net_device *dev; + struct hsr_port *port, *master; + struct hsr_priv *hsr; int mtu_max; int res; - struct net_device *dev; dev = netdev_notifier_info_to_dev(ptr); - - hsr_priv = get_hsr_master(dev); - if (hsr_priv) { - /* dev is a slave device */ - slave = dev; - other_slave = get_other_slave(hsr_priv, slave); - } else { + port = hsr_port_get_rtnl(dev); + if (port == NULL) { if (!is_hsr_master(dev)) - return NOTIFY_DONE; - hsr_priv = netdev_priv(dev); - slave = hsr_priv->slave[0]; - other_slave = hsr_priv->slave[1]; + return NOTIFY_DONE; /* Not an HSR device */ + hsr = netdev_priv(dev); + port = hsr_port_get_hsr(hsr, HSR_PT_MASTER); + } else { + hsr = port->hsr; } switch (event) { case NETDEV_UP: /* Administrative state DOWN */ case NETDEV_DOWN: /* Administrative state UP */ case NETDEV_CHANGE: /* Link (carrier) state changes */ - old_operstate = hsr_priv->dev->operstate; - hsr_set_carrier(hsr_priv->dev, slave, other_slave); - /* netif_stacked_transfer_operstate() cannot be used here since - * it doesn't set IF_OPER_LOWERLAYERDOWN (?) - */ - hsr_set_operstate(hsr_priv->dev, slave, other_slave); - hsr_check_announce(hsr_priv->dev, old_operstate); + hsr_check_carrier_and_operstate(hsr); break; case NETDEV_CHANGEADDR: - - /* This should not happen since there's no ndo_set_mac_address() - * for HSR devices - i.e. not supported. - */ - if (dev == hsr_priv->dev) + if (port->type == HSR_PT_MASTER) { + /* This should not happen since there's no + * ndo_set_mac_address() for HSR devices - i.e. not + * supported. + */ break; + } - if (dev == hsr_priv->slave[0]) - ether_addr_copy(hsr_priv->dev->dev_addr, - hsr_priv->slave[0]->dev_addr); + master = hsr_port_get_hsr(hsr, HSR_PT_MASTER); + + if (port->type == HSR_PT_SLAVE_A) { + ether_addr_copy(master->dev->dev_addr, dev->dev_addr); + call_netdevice_notifiers(NETDEV_CHANGEADDR, master->dev); + } /* Make sure we recognize frames from ourselves in hsr_rcv() */ - res = hsr_create_self_node(&hsr_priv->self_node_db, - hsr_priv->dev->dev_addr, - hsr_priv->slave[1] ? - hsr_priv->slave[1]->dev_addr : - hsr_priv->dev->dev_addr); + port = hsr_port_get_hsr(hsr, HSR_PT_SLAVE_B); + res = hsr_create_self_node(&hsr->self_node_db, + master->dev->dev_addr, + port ? + port->dev->dev_addr : + master->dev->dev_addr); if (res) - netdev_warn(hsr_priv->dev, + netdev_warn(master->dev, "Could not update HSR node address.\n"); - - if (dev == hsr_priv->slave[0]) - call_netdevice_notifiers(NETDEV_CHANGEADDR, hsr_priv->dev); break; case NETDEV_CHANGEMTU: - if (dev == hsr_priv->dev) + if (port->type == HSR_PT_MASTER) break; /* Handled in ndo_change_mtu() */ - mtu_max = hsr_get_max_mtu(hsr_priv); - if (hsr_priv->dev->mtu > mtu_max) - dev_set_mtu(hsr_priv->dev, mtu_max); + mtu_max = hsr_get_max_mtu(port->hsr); + master = hsr_port_get_hsr(port->hsr, HSR_PT_MASTER); + master->dev->mtu = mtu_max; break; case NETDEV_UNREGISTER: - if (dev == hsr_priv->slave[0]) - hsr_priv->slave[0] = NULL; - if (dev == hsr_priv->slave[1]) - hsr_priv->slave[1] = NULL; - - /* There should really be a way to set a new slave device... */ - + hsr_del_port(port); break; case NETDEV_PRE_TYPE_CHANGE: /* HSR works only on Ethernet devices. Refuse slave to change @@ -181,255 +94,16 @@ static int hsr_netdev_notify(struct notifier_block *nb, unsigned long event, } -static struct timer_list prune_timer; - -static void prune_nodes_all(unsigned long data) -{ - struct hsr_priv *hsr_priv; - - rcu_read_lock(); - list_for_each_entry_rcu(hsr_priv, &hsr_list, hsr_list) - hsr_prune_nodes(hsr_priv); - rcu_read_unlock(); - - prune_timer.expires = jiffies + msecs_to_jiffies(PRUNE_PERIOD); - add_timer(&prune_timer); -} - - -static struct sk_buff *hsr_pull_tag(struct sk_buff *skb) +struct hsr_port *hsr_port_get_hsr(struct hsr_priv *hsr, enum hsr_port_type pt) { - struct hsr_tag *hsr_tag; - struct sk_buff *skb2; - - skb2 = skb_share_check(skb, GFP_ATOMIC); - if (unlikely(!skb2)) - goto err_free; - skb = skb2; - - if (unlikely(!pskb_may_pull(skb, HSR_TAGLEN))) - goto err_free; + struct hsr_port *port; - hsr_tag = (struct hsr_tag *) skb->data; - skb->protocol = hsr_tag->encap_proto; - skb_pull(skb, HSR_TAGLEN); - - return skb; - -err_free: - kfree_skb(skb); + hsr_for_each_port(hsr, port) + if (port->type == pt) + return port; return NULL; } - -/* The uses I can see for these HSR supervision frames are: - * 1) Use the frames that are sent after node initialization ("HSR_TLV.Type = - * 22") to reset any sequence_nr counters belonging to that node. Useful if - * the other node's counter has been reset for some reason. - * -- - * Or not - resetting the counter and bridging the frame would create a - * loop, unfortunately. - * - * 2) Use the LifeCheck frames to detect ring breaks. I.e. if no LifeCheck - * frame is received from a particular node, we know something is wrong. - * We just register these (as with normal frames) and throw them away. - * - * 3) Allow different MAC addresses for the two slave interfaces, using the - * MacAddressA field. - */ -static bool is_supervision_frame(struct hsr_priv *hsr_priv, struct sk_buff *skb) -{ - struct hsr_sup_tag *hsr_stag; - - if (!ether_addr_equal(eth_hdr(skb)->h_dest, - hsr_priv->sup_multicast_addr)) - return false; - - hsr_stag = (struct hsr_sup_tag *) skb->data; - if (get_hsr_stag_path(hsr_stag) != 0x0f) - return false; - if ((hsr_stag->HSR_TLV_Type != HSR_TLV_ANNOUNCE) && - (hsr_stag->HSR_TLV_Type != HSR_TLV_LIFE_CHECK)) - return false; - if (hsr_stag->HSR_TLV_Length != 12) - return false; - - return true; -} - - -/* Implementation somewhat according to IEC-62439-3, p. 43 - */ -static int hsr_rcv(struct sk_buff *skb, struct net_device *dev, - struct packet_type *pt, struct net_device *orig_dev) -{ - struct hsr_priv *hsr_priv; - struct net_device *other_slave; - struct node_entry *node; - bool deliver_to_self; - struct sk_buff *skb_deliver; - enum hsr_dev_idx dev_in_idx, dev_other_idx; - bool dup_out; - int ret; - - hsr_priv = get_hsr_master(dev); - - if (!hsr_priv) { - /* Non-HSR-slave device 'dev' is connected to a HSR network */ - kfree_skb(skb); - dev->stats.rx_errors++; - return NET_RX_SUCCESS; - } - - if (dev == hsr_priv->slave[0]) { - dev_in_idx = HSR_DEV_SLAVE_A; - dev_other_idx = HSR_DEV_SLAVE_B; - } else { - dev_in_idx = HSR_DEV_SLAVE_B; - dev_other_idx = HSR_DEV_SLAVE_A; - } - - node = hsr_find_node(&hsr_priv->self_node_db, skb); - if (node) { - /* Always kill frames sent by ourselves */ - kfree_skb(skb); - return NET_RX_SUCCESS; - } - - /* Is this frame a candidate for local reception? */ - deliver_to_self = false; - if ((skb->pkt_type == PACKET_HOST) || - (skb->pkt_type == PACKET_MULTICAST) || - (skb->pkt_type == PACKET_BROADCAST)) - deliver_to_self = true; - else if (ether_addr_equal(eth_hdr(skb)->h_dest, - hsr_priv->dev->dev_addr)) { - skb->pkt_type = PACKET_HOST; - deliver_to_self = true; - } - - - rcu_read_lock(); /* node_db */ - node = hsr_find_node(&hsr_priv->node_db, skb); - - if (is_supervision_frame(hsr_priv, skb)) { - skb_pull(skb, sizeof(struct hsr_sup_tag)); - node = hsr_merge_node(hsr_priv, node, skb, dev_in_idx); - if (!node) { - rcu_read_unlock(); /* node_db */ - kfree_skb(skb); - hsr_priv->dev->stats.rx_dropped++; - return NET_RX_DROP; - } - skb_push(skb, sizeof(struct hsr_sup_tag)); - deliver_to_self = false; - } - - if (!node) { - /* Source node unknown; this might be a HSR frame from - * another net (different multicast address). Ignore it. - */ - rcu_read_unlock(); /* node_db */ - kfree_skb(skb); - return NET_RX_SUCCESS; - } - - /* Register ALL incoming frames as outgoing through the other interface. - * This allows us to register frames as incoming only if they are valid - * for the receiving interface, without using a specific counter for - * incoming frames. - */ - dup_out = hsr_register_frame_out(node, dev_other_idx, skb); - if (!dup_out) - hsr_register_frame_in(node, dev_in_idx); - - /* Forward this frame? */ - if (!dup_out && (skb->pkt_type != PACKET_HOST)) - other_slave = get_other_slave(hsr_priv, dev); - else - other_slave = NULL; - - if (hsr_register_frame_out(node, HSR_DEV_MASTER, skb)) - deliver_to_self = false; - - rcu_read_unlock(); /* node_db */ - - if (!deliver_to_self && !other_slave) { - kfree_skb(skb); - /* Circulated frame; silently remove it. */ - return NET_RX_SUCCESS; - } - - skb_deliver = skb; - if (deliver_to_self && other_slave) { - /* skb_clone() is not enough since we will strip the hsr tag - * and do address substitution below - */ - skb_deliver = pskb_copy(skb, GFP_ATOMIC); - if (!skb_deliver) { - deliver_to_self = false; - hsr_priv->dev->stats.rx_dropped++; - } - } - - if (deliver_to_self) { - bool multicast_frame; - - skb_deliver = hsr_pull_tag(skb_deliver); - if (!skb_deliver) { - hsr_priv->dev->stats.rx_dropped++; - goto forward; - } -#if !defined(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS) - /* Move everything in the header that is after the HSR tag, - * to work around alignment problems caused by the 6-byte HSR - * tag. In practice, this removes/overwrites the HSR tag in - * the header and restores a "standard" packet. - */ - memmove(skb_deliver->data - HSR_TAGLEN, skb_deliver->data, - skb_headlen(skb_deliver)); - - /* Adjust skb members so they correspond with the move above. - * This cannot possibly underflow skb->data since hsr_pull_tag() - * above succeeded. - * At this point in the protocol stack, the transport and - * network headers have not been set yet, and we haven't touched - * the mac header nor the head. So we only need to adjust data - * and tail: - */ - skb_deliver->data -= HSR_TAGLEN; - skb_deliver->tail -= HSR_TAGLEN; -#endif - skb_deliver->dev = hsr_priv->dev; - hsr_addr_subst_source(hsr_priv, skb_deliver); - multicast_frame = (skb_deliver->pkt_type == PACKET_MULTICAST); - ret = netif_rx(skb_deliver); - if (ret == NET_RX_DROP) { - hsr_priv->dev->stats.rx_dropped++; - } else { - hsr_priv->dev->stats.rx_packets++; - hsr_priv->dev->stats.rx_bytes += skb->len; - if (multicast_frame) - hsr_priv->dev->stats.multicast++; - } - } - -forward: - if (other_slave) { - skb_push(skb, ETH_HLEN); - skb->dev = other_slave; - dev_queue_xmit(skb); - } - - return NET_RX_SUCCESS; -} - - -static struct packet_type hsr_pt __read_mostly = { - .type = htons(ETH_P_PRP), - .func = hsr_rcv, -}; - static struct notifier_block hsr_nb = { .notifier_call = hsr_netdev_notify, /* Slave event notifications */ }; @@ -439,18 +113,9 @@ static int __init hsr_init(void) { int res; - BUILD_BUG_ON(sizeof(struct hsr_tag) != HSR_TAGLEN); - - dev_add_pack(&hsr_pt); - - init_timer(&prune_timer); - prune_timer.function = prune_nodes_all; - prune_timer.data = 0; - prune_timer.expires = jiffies + msecs_to_jiffies(PRUNE_PERIOD); - add_timer(&prune_timer); + BUILD_BUG_ON(sizeof(struct hsr_tag) != HSR_HLEN); register_netdevice_notifier(&hsr_nb); - res = hsr_netlink_init(); return res; @@ -459,9 +124,7 @@ static int __init hsr_init(void) static void __exit hsr_exit(void) { unregister_netdevice_notifier(&hsr_nb); - del_timer_sync(&prune_timer); hsr_netlink_exit(); - dev_remove_pack(&hsr_pt); } module_init(hsr_init); diff --git a/net/hsr/hsr_main.h b/net/hsr/hsr_main.h index 56fe060c0ab1..5a9c69962ded 100644 --- a/net/hsr/hsr_main.h +++ b/net/hsr/hsr_main.h @@ -1,4 +1,4 @@ -/* Copyright 2011-2013 Autronica Fire and Security AS +/* Copyright 2011-2014 Autronica Fire and Security AS * * This program is free software; you can redistribute it and/or modify it * under the terms of the GNU General Public License as published by the Free @@ -6,11 +6,11 @@ * any later version. * * Author(s): - * 2011-2013 Arvid Brodin, arvid.brodin@xdin.com + * 2011-2014 Arvid Brodin, arvid.brodin@alten.se */ -#ifndef _HSR_PRIVATE_H -#define _HSR_PRIVATE_H +#ifndef __HSR_PRIVATE_H +#define __HSR_PRIVATE_H #include <linux/netdevice.h> #include <linux/list.h> @@ -29,6 +29,7 @@ * each node differ before we notify of communication problem? */ #define MAX_SLAVE_DIFF 3000 /* ms */ +#define HSR_SEQNR_START (USHRT_MAX - 1024) /* How often shall we check for broken ring and remove node entries older than @@ -46,16 +47,16 @@ * path, LSDU_size, sequence Nr }. But we let eth_header() create { h_dest, * h_source, h_proto = 0x88FB }, and add { path, LSDU_size, sequence Nr, * encapsulated protocol } instead. + * + * Field names as defined in the IEC:2010 standard for HSR. */ -#define HSR_TAGLEN 6 - -/* Field names below as defined in the IEC:2010 standard for HSR. */ struct hsr_tag { __be16 path_and_LSDU_size; __be16 sequence_nr; __be16 encap_proto; } __packed; +#define HSR_HLEN 6 /* The helper functions below assumes that 'path' occupies the 4 most * significant bits of the 16-bit field shared by 'path' and 'LSDU_size' (or @@ -136,31 +137,47 @@ struct hsr_ethhdr_sp { } __packed; -enum hsr_dev_idx { - HSR_DEV_NONE = -1, - HSR_DEV_SLAVE_A = 0, - HSR_DEV_SLAVE_B, - HSR_DEV_MASTER, +enum hsr_port_type { + HSR_PT_NONE = 0, /* Must be 0, used by framereg */ + HSR_PT_SLAVE_A, + HSR_PT_SLAVE_B, + HSR_PT_INTERLINK, + HSR_PT_MASTER, + HSR_PT_PORTS, /* This must be the last item in the enum */ +}; + +struct hsr_port { + struct list_head port_list; + struct net_device *dev; + struct hsr_priv *hsr; + enum hsr_port_type type; }; -#define HSR_MAX_SLAVE (HSR_DEV_SLAVE_B + 1) -#define HSR_MAX_DEV (HSR_DEV_MASTER + 1) struct hsr_priv { - struct list_head hsr_list; /* List of hsr devices */ struct rcu_head rcu_head; - struct net_device *dev; - struct net_device *slave[HSR_MAX_SLAVE]; - struct list_head node_db; /* Other HSR nodes */ + struct list_head ports; + struct list_head node_db; /* Known HSR nodes */ struct list_head self_node_db; /* MACs of slaves */ struct timer_list announce_timer; /* Supervision frame dispatch */ + struct timer_list prune_timer; int announce_count; u16 sequence_nr; spinlock_t seqnr_lock; /* locking for sequence_nr */ unsigned char sup_multicast_addr[ETH_ALEN]; }; -void register_hsr_master(struct hsr_priv *hsr_priv); -void unregister_hsr_master(struct hsr_priv *hsr_priv); -bool is_hsr_slave(struct net_device *dev); +#define hsr_for_each_port(hsr, port) \ + list_for_each_entry_rcu((port), &(hsr)->ports, port_list) + +struct hsr_port *hsr_port_get_hsr(struct hsr_priv *hsr, enum hsr_port_type pt); + +/* Caller must ensure skb is a valid HSR frame */ +static inline u16 hsr_get_skb_sequence_nr(struct sk_buff *skb) +{ + struct hsr_ethhdr *hsr_ethhdr; + + hsr_ethhdr = (struct hsr_ethhdr *) skb_mac_header(skb); + return ntohs(hsr_ethhdr->hsr_tag.sequence_nr); +} -#endif /* _HSR_PRIVATE_H */ +#endif /* __HSR_PRIVATE_H */ diff --git a/net/hsr/hsr_netlink.c b/net/hsr/hsr_netlink.c index 01a5261ac7a5..a2c7e4c0ac1e 100644 --- a/net/hsr/hsr_netlink.c +++ b/net/hsr/hsr_netlink.c @@ -1,4 +1,4 @@ -/* Copyright 2011-2013 Autronica Fire and Security AS +/* Copyright 2011-2014 Autronica Fire and Security AS * * This program is free software; you can redistribute it and/or modify it * under the terms of the GNU General Public License as published by the Free @@ -6,7 +6,7 @@ * any later version. * * Author(s): - * 2011-2013 Arvid Brodin, arvid.brodin@xdin.com + * 2011-2014 Arvid Brodin, arvid.brodin@alten.se * * Routines for handling Netlink messages for HSR. */ @@ -37,13 +37,17 @@ static int hsr_newlink(struct net *src_net, struct net_device *dev, struct net_device *link[2]; unsigned char multicast_spec; + if (!data) { + netdev_info(dev, "HSR: No slave devices specified\n"); + return -EINVAL; + } if (!data[IFLA_HSR_SLAVE1]) { - netdev_info(dev, "IFLA_HSR_SLAVE1 missing!\n"); + netdev_info(dev, "HSR: Slave1 device not specified\n"); return -EINVAL; } link[0] = __dev_get_by_index(src_net, nla_get_u32(data[IFLA_HSR_SLAVE1])); if (!data[IFLA_HSR_SLAVE2]) { - netdev_info(dev, "IFLA_HSR_SLAVE2 missing!\n"); + netdev_info(dev, "HSR: Slave2 device not specified\n"); return -EINVAL; } link[1] = __dev_get_by_index(src_net, nla_get_u32(data[IFLA_HSR_SLAVE2])); @@ -63,21 +67,33 @@ static int hsr_newlink(struct net *src_net, struct net_device *dev, static int hsr_fill_info(struct sk_buff *skb, const struct net_device *dev) { - struct hsr_priv *hsr_priv; + struct hsr_priv *hsr; + struct hsr_port *port; + int res; - hsr_priv = netdev_priv(dev); + hsr = netdev_priv(dev); - if (hsr_priv->slave[0]) - if (nla_put_u32(skb, IFLA_HSR_SLAVE1, hsr_priv->slave[0]->ifindex)) - goto nla_put_failure; + res = 0; - if (hsr_priv->slave[1]) - if (nla_put_u32(skb, IFLA_HSR_SLAVE2, hsr_priv->slave[1]->ifindex)) - goto nla_put_failure; + rcu_read_lock(); + port = hsr_port_get_hsr(hsr, HSR_PT_SLAVE_A); + if (port) + res = nla_put_u32(skb, IFLA_HSR_SLAVE1, port->dev->ifindex); + rcu_read_unlock(); + if (res) + goto nla_put_failure; + + rcu_read_lock(); + port = hsr_port_get_hsr(hsr, HSR_PT_SLAVE_B); + if (port) + res = nla_put_u32(skb, IFLA_HSR_SLAVE2, port->dev->ifindex); + rcu_read_unlock(); + if (res) + goto nla_put_failure; if (nla_put(skb, IFLA_HSR_SUPERVISION_ADDR, ETH_ALEN, - hsr_priv->sup_multicast_addr) || - nla_put_u16(skb, IFLA_HSR_SEQ_NR, hsr_priv->sequence_nr)) + hsr->sup_multicast_addr) || + nla_put_u16(skb, IFLA_HSR_SEQ_NR, hsr->sequence_nr)) goto nla_put_failure; return 0; @@ -128,13 +144,13 @@ static const struct genl_multicast_group hsr_mcgrps[] = { * over one of the slave interfaces. This would indicate an open network ring * (i.e. a link has failed somewhere). */ -void hsr_nl_ringerror(struct hsr_priv *hsr_priv, unsigned char addr[ETH_ALEN], - enum hsr_dev_idx dev_idx) +void hsr_nl_ringerror(struct hsr_priv *hsr, unsigned char addr[ETH_ALEN], + struct hsr_port *port) { struct sk_buff *skb; void *msg_head; + struct hsr_port *master; int res; - int ifindex; skb = genlmsg_new(NLMSG_GOODSIZE, GFP_ATOMIC); if (!skb) @@ -148,11 +164,7 @@ void hsr_nl_ringerror(struct hsr_priv *hsr_priv, unsigned char addr[ETH_ALEN], if (res < 0) goto nla_put_failure; - if (hsr_priv->slave[dev_idx]) - ifindex = hsr_priv->slave[dev_idx]->ifindex; - else - ifindex = -1; - res = nla_put_u32(skb, HSR_A_IFINDEX, ifindex); + res = nla_put_u32(skb, HSR_A_IFINDEX, port->dev->ifindex); if (res < 0) goto nla_put_failure; @@ -165,16 +177,20 @@ nla_put_failure: kfree_skb(skb); fail: - netdev_warn(hsr_priv->dev, "Could not send HSR ring error message\n"); + rcu_read_lock(); + master = hsr_port_get_hsr(hsr, HSR_PT_MASTER); + netdev_warn(master->dev, "Could not send HSR ring error message\n"); + rcu_read_unlock(); } /* This is called when we haven't heard from the node with MAC address addr for * some time (just before the node is removed from the node table/list). */ -void hsr_nl_nodedown(struct hsr_priv *hsr_priv, unsigned char addr[ETH_ALEN]) +void hsr_nl_nodedown(struct hsr_priv *hsr, unsigned char addr[ETH_ALEN]) { struct sk_buff *skb; void *msg_head; + struct hsr_port *master; int res; skb = genlmsg_new(NLMSG_GOODSIZE, GFP_ATOMIC); @@ -199,7 +215,10 @@ nla_put_failure: kfree_skb(skb); fail: - netdev_warn(hsr_priv->dev, "Could not send HSR node down\n"); + rcu_read_lock(); + master = hsr_port_get_hsr(hsr, HSR_PT_MASTER); + netdev_warn(master->dev, "Could not send HSR node down\n"); + rcu_read_unlock(); } @@ -220,7 +239,8 @@ static int hsr_get_node_status(struct sk_buff *skb_in, struct genl_info *info) /* For sending */ struct sk_buff *skb_out; void *msg_head; - struct hsr_priv *hsr_priv; + struct hsr_priv *hsr; + struct hsr_port *port; unsigned char hsr_node_addr_b[ETH_ALEN]; int hsr_node_if1_age; u16 hsr_node_if1_seq; @@ -267,8 +287,8 @@ static int hsr_get_node_status(struct sk_buff *skb_in, struct genl_info *info) if (res < 0) goto nla_put_failure; - hsr_priv = netdev_priv(hsr_dev); - res = hsr_get_node_data(hsr_priv, + hsr = netdev_priv(hsr_dev); + res = hsr_get_node_data(hsr, (unsigned char *) nla_data(info->attrs[HSR_A_NODE_ADDR]), hsr_node_addr_b, &addr_b_ifindex, @@ -301,9 +321,12 @@ static int hsr_get_node_status(struct sk_buff *skb_in, struct genl_info *info) res = nla_put_u16(skb_out, HSR_A_IF1_SEQ, hsr_node_if1_seq); if (res < 0) goto nla_put_failure; - if (hsr_priv->slave[0]) + rcu_read_lock(); + port = hsr_port_get_hsr(hsr, HSR_PT_SLAVE_A); + if (port) res = nla_put_u32(skb_out, HSR_A_IF1_IFINDEX, - hsr_priv->slave[0]->ifindex); + port->dev->ifindex); + rcu_read_unlock(); if (res < 0) goto nla_put_failure; @@ -313,9 +336,14 @@ static int hsr_get_node_status(struct sk_buff *skb_in, struct genl_info *info) res = nla_put_u16(skb_out, HSR_A_IF2_SEQ, hsr_node_if2_seq); if (res < 0) goto nla_put_failure; - if (hsr_priv->slave[1]) + rcu_read_lock(); + port = hsr_port_get_hsr(hsr, HSR_PT_SLAVE_B); + if (port) res = nla_put_u32(skb_out, HSR_A_IF2_IFINDEX, - hsr_priv->slave[1]->ifindex); + port->dev->ifindex); + rcu_read_unlock(); + if (res < 0) + goto nla_put_failure; genlmsg_end(skb_out, msg_head); genlmsg_unicast(genl_info_net(info), skb_out, info->snd_portid); @@ -334,7 +362,7 @@ fail: return res; } -/* Get a list of MacAddressA of all nodes known to this node (other than self). +/* Get a list of MacAddressA of all nodes known to this node (including self). */ static int hsr_get_node_list(struct sk_buff *skb_in, struct genl_info *info) { @@ -345,7 +373,7 @@ static int hsr_get_node_list(struct sk_buff *skb_in, struct genl_info *info) /* For sending */ struct sk_buff *skb_out; void *msg_head; - struct hsr_priv *hsr_priv; + struct hsr_priv *hsr; void *pos; unsigned char addr[ETH_ALEN]; int res; @@ -385,17 +413,17 @@ static int hsr_get_node_list(struct sk_buff *skb_in, struct genl_info *info) if (res < 0) goto nla_put_failure; - hsr_priv = netdev_priv(hsr_dev); + hsr = netdev_priv(hsr_dev); rcu_read_lock(); - pos = hsr_get_next_node(hsr_priv, NULL, addr); + pos = hsr_get_next_node(hsr, NULL, addr); while (pos) { res = nla_put(skb_out, HSR_A_NODE_ADDR, ETH_ALEN, addr); if (res < 0) { rcu_read_unlock(); goto nla_put_failure; } - pos = hsr_get_next_node(hsr_priv, pos, addr); + pos = hsr_get_next_node(hsr, pos, addr); } rcu_read_unlock(); diff --git a/net/hsr/hsr_netlink.h b/net/hsr/hsr_netlink.h index d4579dcc3c7d..3f6b95b5b6b8 100644 --- a/net/hsr/hsr_netlink.h +++ b/net/hsr/hsr_netlink.h @@ -1,4 +1,4 @@ -/* Copyright 2011-2013 Autronica Fire and Security AS +/* Copyright 2011-2014 Autronica Fire and Security AS * * This program is free software; you can redistribute it and/or modify it * under the terms of the GNU General Public License as published by the Free @@ -6,7 +6,7 @@ * any later version. * * Author(s): - * 2011-2013 Arvid Brodin, arvid.brodin@xdin.com + * 2011-2014 Arvid Brodin, arvid.brodin@alten.se */ #ifndef __HSR_NETLINK_H @@ -17,13 +17,14 @@ #include <uapi/linux/hsr_netlink.h> struct hsr_priv; +struct hsr_port; int __init hsr_netlink_init(void); void __exit hsr_netlink_exit(void); -void hsr_nl_ringerror(struct hsr_priv *hsr_priv, unsigned char addr[ETH_ALEN], - int dev_idx); -void hsr_nl_nodedown(struct hsr_priv *hsr_priv, unsigned char addr[ETH_ALEN]); +void hsr_nl_ringerror(struct hsr_priv *hsr, unsigned char addr[ETH_ALEN], + struct hsr_port *port); +void hsr_nl_nodedown(struct hsr_priv *hsr, unsigned char addr[ETH_ALEN]); void hsr_nl_framedrop(int dropcount, int dev_idx); void hsr_nl_linkdown(int dev_idx); diff --git a/net/hsr/hsr_slave.c b/net/hsr/hsr_slave.c new file mode 100644 index 000000000000..a348dcbcd683 --- /dev/null +++ b/net/hsr/hsr_slave.c @@ -0,0 +1,196 @@ +/* Copyright 2011-2014 Autronica Fire and Security AS + * + * This program is free software; you can redistribute it and/or modify it + * under the terms of the GNU General Public License as published by the Free + * Software Foundation; either version 2 of the License, or (at your option) + * any later version. + * + * Author(s): + * 2011-2014 Arvid Brodin, arvid.brodin@alten.se + */ + +#include "hsr_slave.h" +#include <linux/etherdevice.h> +#include <linux/if_arp.h> +#include "hsr_main.h" +#include "hsr_device.h" +#include "hsr_forward.h" +#include "hsr_framereg.h" + + +static rx_handler_result_t hsr_handle_frame(struct sk_buff **pskb) +{ + struct sk_buff *skb = *pskb; + struct hsr_port *port; + + if (!skb_mac_header_was_set(skb)) { + WARN_ONCE(1, "%s: skb invalid", __func__); + return RX_HANDLER_PASS; + } + + rcu_read_lock(); /* hsr->node_db, hsr->ports */ + port = hsr_port_get_rcu(skb->dev); + + if (hsr_addr_is_self(port->hsr, eth_hdr(skb)->h_source)) { + /* Directly kill frames sent by ourselves */ + kfree_skb(skb); + goto finish_consume; + } + + if (eth_hdr(skb)->h_proto != htons(ETH_P_PRP)) + goto finish_pass; + + skb_push(skb, ETH_HLEN); + + hsr_forward_skb(skb, port); + +finish_consume: + rcu_read_unlock(); /* hsr->node_db, hsr->ports */ + return RX_HANDLER_CONSUMED; + +finish_pass: + rcu_read_unlock(); /* hsr->node_db, hsr->ports */ + return RX_HANDLER_PASS; +} + +bool hsr_port_exists(const struct net_device *dev) +{ + return rcu_access_pointer(dev->rx_handler) == hsr_handle_frame; +} + + +static int hsr_check_dev_ok(struct net_device *dev) +{ + /* Don't allow HSR on non-ethernet like devices */ + if ((dev->flags & IFF_LOOPBACK) || (dev->type != ARPHRD_ETHER) || + (dev->addr_len != ETH_ALEN)) { + netdev_info(dev, "Cannot use loopback or non-ethernet device as HSR slave.\n"); + return -EINVAL; + } + + /* Don't allow enslaving hsr devices */ + if (is_hsr_master(dev)) { + netdev_info(dev, "Cannot create trees of HSR devices.\n"); + return -EINVAL; + } + + if (hsr_port_exists(dev)) { + netdev_info(dev, "This device is already a HSR slave.\n"); + return -EINVAL; + } + + if (dev->priv_flags & IFF_802_1Q_VLAN) { + netdev_info(dev, "HSR on top of VLAN is not yet supported in this driver.\n"); + return -EINVAL; + } + + if (dev->priv_flags & IFF_DONT_BRIDGE) { + netdev_info(dev, "This device does not support bridging.\n"); + return -EOPNOTSUPP; + } + + /* HSR over bonded devices has not been tested, but I'm not sure it + * won't work... + */ + + return 0; +} + + +/* Setup device to be added to the HSR bridge. */ +static int hsr_portdev_setup(struct net_device *dev, struct hsr_port *port) +{ + int res; + + dev_hold(dev); + res = dev_set_promiscuity(dev, 1); + if (res) + goto fail_promiscuity; + + /* FIXME: + * What does net device "adjacency" mean? Should we do + * res = netdev_master_upper_dev_link(port->dev, port->hsr->dev); ? + */ + + res = netdev_rx_handler_register(dev, hsr_handle_frame, port); + if (res) + goto fail_rx_handler; + dev_disable_lro(dev); + + return 0; + +fail_rx_handler: + dev_set_promiscuity(dev, -1); +fail_promiscuity: + dev_put(dev); + + return res; +} + +int hsr_add_port(struct hsr_priv *hsr, struct net_device *dev, + enum hsr_port_type type) +{ + struct hsr_port *port, *master; + int res; + + if (type != HSR_PT_MASTER) { + res = hsr_check_dev_ok(dev); + if (res) + return res; + } + + port = hsr_port_get_hsr(hsr, type); + if (port != NULL) + return -EBUSY; /* This port already exists */ + + port = kzalloc(sizeof(*port), GFP_KERNEL); + if (port == NULL) + return -ENOMEM; + + if (type != HSR_PT_MASTER) { + res = hsr_portdev_setup(dev, port); + if (res) + goto fail_dev_setup; + } + + port->hsr = hsr; + port->dev = dev; + port->type = type; + + list_add_tail_rcu(&port->port_list, &hsr->ports); + synchronize_rcu(); + + master = hsr_port_get_hsr(hsr, HSR_PT_MASTER); + netdev_update_features(master->dev); + dev_set_mtu(master->dev, hsr_get_max_mtu(hsr)); + + return 0; + +fail_dev_setup: + kfree(port); + return res; +} + +void hsr_del_port(struct hsr_port *port) +{ + struct hsr_priv *hsr; + struct hsr_port *master; + + hsr = port->hsr; + master = hsr_port_get_hsr(hsr, HSR_PT_MASTER); + list_del_rcu(&port->port_list); + + if (port != master) { + netdev_update_features(master->dev); + dev_set_mtu(master->dev, hsr_get_max_mtu(hsr)); + netdev_rx_handler_unregister(port->dev); + dev_set_promiscuity(port->dev, -1); + } + + /* FIXME? + * netdev_upper_dev_unlink(port->dev, port->hsr->dev); + */ + + synchronize_rcu(); + dev_put(port->dev); +} diff --git a/net/hsr/hsr_slave.h b/net/hsr/hsr_slave.h new file mode 100644 index 000000000000..3ccfbf71c92e --- /dev/null +++ b/net/hsr/hsr_slave.h @@ -0,0 +1,38 @@ +/* Copyright 2011-2014 Autronica Fire and Security AS + * + * This program is free software; you can redistribute it and/or modify it + * under the terms of the GNU General Public License as published by the Free + * Software Foundation; either version 2 of the License, or (at your option) + * any later version. + * + * Author(s): + * 2011-2014 Arvid Brodin, arvid.brodin@alten.se + */ + +#ifndef __HSR_SLAVE_H +#define __HSR_SLAVE_H + +#include <linux/skbuff.h> +#include <linux/netdevice.h> +#include <linux/rtnetlink.h> +#include "hsr_main.h" + +int hsr_add_port(struct hsr_priv *hsr, struct net_device *dev, + enum hsr_port_type pt); +void hsr_del_port(struct hsr_port *port); +bool hsr_port_exists(const struct net_device *dev); + +static inline struct hsr_port *hsr_port_get_rtnl(const struct net_device *dev) +{ + ASSERT_RTNL(); + return hsr_port_exists(dev) ? + rtnl_dereference(dev->rx_handler_data) : NULL; +} + +static inline struct hsr_port *hsr_port_get_rcu(const struct net_device *dev) +{ + return hsr_port_exists(dev) ? + rcu_dereference(dev->rx_handler_data) : NULL; +} + +#endif /* __HSR_SLAVE_H */ diff --git a/net/ieee802154/6lowpan_rtnl.c b/net/ieee802154/6lowpan_rtnl.c index fe6bd7a71081..016b77ee88f0 100644 --- a/net/ieee802154/6lowpan_rtnl.c +++ b/net/ieee802154/6lowpan_rtnl.c @@ -80,14 +80,14 @@ lowpan_dev_info *lowpan_dev_info(const struct net_device *dev) static inline void lowpan_address_flip(u8 *src, u8 *dest) { int i; + for (i = 0; i < IEEE802154_ADDR_LEN; i++) (dest)[IEEE802154_ADDR_LEN - i - 1] = (src)[i]; } -static int lowpan_header_create(struct sk_buff *skb, - struct net_device *dev, - unsigned short type, const void *_daddr, - const void *_saddr, unsigned int len) +static int lowpan_header_create(struct sk_buff *skb, struct net_device *dev, + unsigned short type, const void *_daddr, + const void *_saddr, unsigned int len) { const u8 *saddr = _saddr; const u8 *daddr = _daddr; @@ -144,7 +144,7 @@ static int lowpan_header_create(struct sk_buff *skb, } static int lowpan_give_skb_to_devices(struct sk_buff *skb, - struct net_device *dev) + struct net_device *dev) { struct lowpan_dev_record *entry; struct sk_buff *skb_cp; @@ -368,24 +368,28 @@ static netdev_tx_t lowpan_xmit(struct sk_buff *skb, struct net_device *dev) static struct wpan_phy *lowpan_get_phy(const struct net_device *dev) { struct net_device *real_dev = lowpan_dev_info(dev)->real_dev; + return ieee802154_mlme_ops(real_dev)->get_phy(real_dev); } static __le16 lowpan_get_pan_id(const struct net_device *dev) { struct net_device *real_dev = lowpan_dev_info(dev)->real_dev; + return ieee802154_mlme_ops(real_dev)->get_pan_id(real_dev); } static __le16 lowpan_get_short_addr(const struct net_device *dev) { struct net_device *real_dev = lowpan_dev_info(dev)->real_dev; + return ieee802154_mlme_ops(real_dev)->get_short_addr(real_dev); } static u8 lowpan_get_dsn(const struct net_device *dev) { struct net_device *real_dev = lowpan_dev_info(dev)->real_dev; + return ieee802154_mlme_ops(real_dev)->get_dsn(real_dev); } @@ -454,7 +458,7 @@ static int lowpan_validate(struct nlattr *tb[], struct nlattr *data[]) } static int lowpan_rcv(struct sk_buff *skb, struct net_device *dev, - struct packet_type *pt, struct net_device *orig_dev) + struct packet_type *pt, struct net_device *orig_dev) { struct ieee802154_hdr hdr; int ret; diff --git a/net/ieee802154/Kconfig b/net/ieee802154/Kconfig index 8af1330b3137..c0d4154d144f 100644 --- a/net/ieee802154/Kconfig +++ b/net/ieee802154/Kconfig @@ -12,13 +12,6 @@ config IEEE802154 config IEEE802154_6LOWPAN tristate "6lowpan support over IEEE 802.15.4" - depends on IEEE802154 && IPV6 - select 6LOWPAN_IPHC + depends on IEEE802154 && 6LOWPAN ---help--- IPv6 compression over IEEE 802.15.4. - -config 6LOWPAN_IPHC - tristate - ---help--- - 6lowpan compression code which is shared between IEEE 802.15.4 and Bluetooth - stacks. diff --git a/net/ieee802154/Makefile b/net/ieee802154/Makefile index bf1b51497a41..3914b1ed4274 100644 --- a/net/ieee802154/Makefile +++ b/net/ieee802154/Makefile @@ -1,8 +1,7 @@ obj-$(CONFIG_IEEE802154) += ieee802154.o af_802154.o -obj-$(CONFIG_IEEE802154_6LOWPAN) += 6lowpan.o -obj-$(CONFIG_6LOWPAN_IPHC) += 6lowpan_iphc.o +obj-$(CONFIG_IEEE802154_6LOWPAN) += ieee802154_6lowpan.o -6lowpan-y := 6lowpan_rtnl.o reassembly.o +ieee802154_6lowpan-y := 6lowpan_rtnl.o reassembly.o ieee802154-y := netlink.o nl-mac.o nl-phy.o nl_policy.o wpan-class.o \ header_ops.o af_802154-y := af_ieee802154.o raw.o dgram.o diff --git a/net/ieee802154/af_ieee802154.c b/net/ieee802154/af_ieee802154.c index 351d9a94ec2f..29e0de63001b 100644 --- a/net/ieee802154/af_ieee802154.c +++ b/net/ieee802154/af_ieee802154.c @@ -40,9 +40,7 @@ #include "af802154.h" -/* - * Utility function for families - */ +/* Utility function for families */ struct net_device* ieee802154_get_dev(struct net *net, const struct ieee802154_addr *addr) { @@ -87,8 +85,8 @@ ieee802154_get_dev(struct net *net, const struct ieee802154_addr *addr) rtnl_unlock(); break; default: - pr_warning("Unsupported ieee802154 address type: %d\n", - addr->mode); + pr_warn("Unsupported ieee802154 address type: %d\n", + addr->mode); break; } @@ -106,7 +104,7 @@ static int ieee802154_sock_release(struct socket *sock) return 0; } static int ieee802154_sock_sendmsg(struct kiocb *iocb, struct socket *sock, - struct msghdr *msg, size_t len) + struct msghdr *msg, size_t len) { struct sock *sk = sock->sk; @@ -114,7 +112,7 @@ static int ieee802154_sock_sendmsg(struct kiocb *iocb, struct socket *sock, } static int ieee802154_sock_bind(struct socket *sock, struct sockaddr *uaddr, - int addr_len) + int addr_len) { struct sock *sk = sock->sk; @@ -125,7 +123,7 @@ static int ieee802154_sock_bind(struct socket *sock, struct sockaddr *uaddr, } static int ieee802154_sock_connect(struct socket *sock, struct sockaddr *uaddr, - int addr_len, int flags) + int addr_len, int flags) { struct sock *sk = sock->sk; @@ -139,7 +137,7 @@ static int ieee802154_sock_connect(struct socket *sock, struct sockaddr *uaddr, } static int ieee802154_dev_ioctl(struct sock *sk, struct ifreq __user *arg, - unsigned int cmd) + unsigned int cmd) { struct ifreq ifr; int ret = -ENOIOCTLCMD; @@ -167,7 +165,7 @@ static int ieee802154_dev_ioctl(struct sock *sk, struct ifreq __user *arg, } static int ieee802154_sock_ioctl(struct socket *sock, unsigned int cmd, - unsigned long arg) + unsigned long arg) { struct sock *sk = sock->sk; @@ -238,8 +236,7 @@ static const struct proto_ops ieee802154_dgram_ops = { }; -/* - * Create a socket. Initialise the socket, blank the addresses +/* Create a socket. Initialise the socket, blank the addresses * set the state. */ static int ieee802154_create(struct net *net, struct socket *sock, @@ -301,13 +298,14 @@ static const struct net_proto_family ieee802154_family_ops = { }; static int ieee802154_rcv(struct sk_buff *skb, struct net_device *dev, - struct packet_type *pt, struct net_device *orig_dev) + struct packet_type *pt, struct net_device *orig_dev) { if (!netif_running(dev)) goto drop; pr_debug("got frame, type %d, dev %p\n", dev->type, dev); #ifdef DEBUG - print_hex_dump_bytes("ieee802154_rcv ", DUMP_PREFIX_NONE, skb->data, skb->len); + print_hex_dump_bytes("ieee802154_rcv ", + DUMP_PREFIX_NONE, skb->data, skb->len); #endif if (!net_eq(dev_net(dev), &init_net)) diff --git a/net/ieee802154/dgram.c b/net/ieee802154/dgram.c index 4f0ed8780194..ef2ad8aaef13 100644 --- a/net/ieee802154/dgram.c +++ b/net/ieee802154/dgram.c @@ -149,8 +149,7 @@ static int dgram_ioctl(struct sock *sk, int cmd, unsigned long arg) spin_lock_bh(&sk->sk_receive_queue.lock); skb = skb_peek(&sk->sk_receive_queue); if (skb != NULL) { - /* - * We will only return the amount + /* We will only return the amount * of this packet since that is all * that will be read. */ @@ -161,12 +160,13 @@ static int dgram_ioctl(struct sock *sk, int cmd, unsigned long arg) } } + return -ENOIOCTLCMD; } /* FIXME: autobind */ static int dgram_connect(struct sock *sk, struct sockaddr *uaddr, - int len) + int len) { struct sockaddr_ieee802154 *addr = (struct sockaddr_ieee802154 *)uaddr; struct dgram_sock *ro = dgram_sk(sk); @@ -205,7 +205,7 @@ static int dgram_disconnect(struct sock *sk, int flags) } static int dgram_sendmsg(struct kiocb *iocb, struct sock *sk, - struct msghdr *msg, size_t size) + struct msghdr *msg, size_t size) { struct net_device *dev; unsigned int mtu; @@ -248,8 +248,8 @@ static int dgram_sendmsg(struct kiocb *iocb, struct sock *sk, hlen = LL_RESERVED_SPACE(dev); tlen = dev->needed_tailroom; skb = sock_alloc_send_skb(sk, hlen + tlen + size, - msg->msg_flags & MSG_DONTWAIT, - &err); + msg->msg_flags & MSG_DONTWAIT, + &err); if (!skb) goto out_dev; @@ -262,7 +262,8 @@ static int dgram_sendmsg(struct kiocb *iocb, struct sock *sk, cb->ackreq = ro->want_ack; if (msg->msg_name) { - DECLARE_SOCKADDR(struct sockaddr_ieee802154*, daddr, msg->msg_name); + DECLARE_SOCKADDR(struct sockaddr_ieee802154*, + daddr, msg->msg_name); ieee802154_addr_from_sa(&dst_addr, &daddr->addr); } else { @@ -304,8 +305,8 @@ out: } static int dgram_recvmsg(struct kiocb *iocb, struct sock *sk, - struct msghdr *msg, size_t len, int noblock, int flags, - int *addr_len) + struct msghdr *msg, size_t len, int noblock, + int flags, int *addr_len) { size_t copied = 0; int err = -EOPNOTSUPP; @@ -398,6 +399,7 @@ int ieee802154_dgram_deliver(struct net_device *dev, struct sk_buff *skb) dgram_sk(sk))) { if (prev) { struct sk_buff *clone; + clone = skb_clone(skb, GFP_ATOMIC); if (clone) dgram_rcv_skb(prev, clone); @@ -407,9 +409,9 @@ int ieee802154_dgram_deliver(struct net_device *dev, struct sk_buff *skb) } } - if (prev) + if (prev) { dgram_rcv_skb(prev, skb); - else { + } else { kfree_skb(skb); ret = NET_RX_DROP; } @@ -419,7 +421,7 @@ int ieee802154_dgram_deliver(struct net_device *dev, struct sk_buff *skb) } static int dgram_getsockopt(struct sock *sk, int level, int optname, - char __user *optval, int __user *optlen) + char __user *optval, int __user *optlen) { struct dgram_sock *ro = dgram_sk(sk); @@ -463,7 +465,7 @@ static int dgram_getsockopt(struct sock *sk, int level, int optname, } static int dgram_setsockopt(struct sock *sk, int level, int optname, - char __user *optval, unsigned int optlen) + char __user *optval, unsigned int optlen) { struct dgram_sock *ro = dgram_sk(sk); struct net *net = sock_net(sk); diff --git a/net/ieee802154/ieee802154.h b/net/ieee802154/ieee802154.h index 8b83a231299e..5d352f86979e 100644 --- a/net/ieee802154/ieee802154.h +++ b/net/ieee802154/ieee802154.h @@ -43,7 +43,7 @@ struct genl_info; struct sk_buff *ieee802154_nl_create(int flags, u8 req); int ieee802154_nl_mcast(struct sk_buff *msg, unsigned int group); struct sk_buff *ieee802154_nl_new_reply(struct genl_info *info, - int flags, u8 req); + int flags, u8 req); int ieee802154_nl_reply(struct sk_buff *msg, struct genl_info *info); extern struct genl_family nl802154_family; diff --git a/net/ieee802154/netlink.c b/net/ieee802154/netlink.c index 26efcf4fd2ff..9222966f5e6d 100644 --- a/net/ieee802154/netlink.c +++ b/net/ieee802154/netlink.c @@ -52,7 +52,7 @@ struct sk_buff *ieee802154_nl_create(int flags, u8 req) spin_lock_irqsave(&ieee802154_seq_lock, f); hdr = genlmsg_put(msg, 0, ieee802154_seq_num++, - &nl802154_family, flags, req); + &nl802154_family, flags, req); spin_unlock_irqrestore(&ieee802154_seq_lock, f); if (!hdr) { nlmsg_free(msg); @@ -86,7 +86,7 @@ struct sk_buff *ieee802154_nl_new_reply(struct genl_info *info, return NULL; hdr = genlmsg_put_reply(msg, info, - &nl802154_family, flags, req); + &nl802154_family, flags, req); if (!hdr) { nlmsg_free(msg); return NULL; diff --git a/net/ieee802154/nl-mac.c b/net/ieee802154/nl-mac.c index a3281b8bfd5b..c6bfe22bfa5e 100644 --- a/net/ieee802154/nl-mac.c +++ b/net/ieee802154/nl-mac.c @@ -60,7 +60,8 @@ static __le16 nla_get_shortaddr(const struct nlattr *nla) } int ieee802154_nl_assoc_indic(struct net_device *dev, - struct ieee802154_addr *addr, u8 cap) + struct ieee802154_addr *addr, + u8 cap) { struct sk_buff *msg; @@ -93,7 +94,7 @@ nla_put_failure: EXPORT_SYMBOL(ieee802154_nl_assoc_indic); int ieee802154_nl_assoc_confirm(struct net_device *dev, __le16 short_addr, - u8 status) + u8 status) { struct sk_buff *msg; @@ -119,7 +120,8 @@ nla_put_failure: EXPORT_SYMBOL(ieee802154_nl_assoc_confirm); int ieee802154_nl_disassoc_indic(struct net_device *dev, - struct ieee802154_addr *addr, u8 reason) + struct ieee802154_addr *addr, + u8 reason) { struct sk_buff *msg; @@ -205,8 +207,9 @@ nla_put_failure: EXPORT_SYMBOL(ieee802154_nl_beacon_indic); int ieee802154_nl_scan_confirm(struct net_device *dev, - u8 status, u8 scan_type, u32 unscanned, u8 page, - u8 *edl/* , struct list_head *pan_desc_list */) + u8 status, u8 scan_type, + u32 unscanned, u8 page, + u8 *edl/* , struct list_head *pan_desc_list */) { struct sk_buff *msg; @@ -260,7 +263,7 @@ nla_put_failure: EXPORT_SYMBOL(ieee802154_nl_start_confirm); static int ieee802154_nl_fill_iface(struct sk_buff *msg, u32 portid, - u32 seq, int flags, struct net_device *dev) + u32 seq, int flags, struct net_device *dev) { void *hdr; struct wpan_phy *phy; @@ -270,7 +273,7 @@ static int ieee802154_nl_fill_iface(struct sk_buff *msg, u32 portid, pr_debug("%s\n", __func__); hdr = genlmsg_put(msg, 0, seq, &nl802154_family, flags, - IEEE802154_LIST_IFACE); + IEEE802154_LIST_IFACE); if (!hdr) goto out; @@ -330,14 +333,16 @@ static struct net_device *ieee802154_nl_get_dev(struct genl_info *info) if (info->attrs[IEEE802154_ATTR_DEV_NAME]) { char name[IFNAMSIZ + 1]; + nla_strlcpy(name, info->attrs[IEEE802154_ATTR_DEV_NAME], - sizeof(name)); + sizeof(name)); dev = dev_get_by_name(&init_net, name); - } else if (info->attrs[IEEE802154_ATTR_DEV_INDEX]) + } else if (info->attrs[IEEE802154_ATTR_DEV_INDEX]) { dev = dev_get_by_index(&init_net, nla_get_u32(info->attrs[IEEE802154_ATTR_DEV_INDEX])); - else + } else { return NULL; + } if (!dev) return NULL; @@ -435,7 +440,7 @@ int ieee802154_disassociate_req(struct sk_buff *skb, struct genl_info *info) int ret = -EOPNOTSUPP; if ((!info->attrs[IEEE802154_ATTR_DEST_HW_ADDR] && - !info->attrs[IEEE802154_ATTR_DEST_SHORT_ADDR]) || + !info->attrs[IEEE802154_ATTR_DEST_SHORT_ADDR]) || !info->attrs[IEEE802154_ATTR_REASON]) return -EINVAL; @@ -464,8 +469,7 @@ out: return ret; } -/* - * PANid, channel, beacon_order = 15, superframe_order = 15, +/* PANid, channel, beacon_order = 15, superframe_order = 15, * PAN_coordinator, battery_life_extension = 0, * coord_realignment = 0, security_enable = 0 */ @@ -559,8 +563,8 @@ int ieee802154_scan_req(struct sk_buff *skb, struct genl_info *info) page = 0; - ret = ieee802154_mlme_ops(dev)->scan_req(dev, type, channels, page, - duration); + ret = ieee802154_mlme_ops(dev)->scan_req(dev, type, channels, + page, duration); out: dev_put(dev); @@ -570,7 +574,8 @@ out: int ieee802154_list_iface(struct sk_buff *skb, struct genl_info *info) { /* Request for interface name, index, type, IEEE address, - PAN Id, short address */ + * PAN Id, short address + */ struct sk_buff *msg; struct net_device *dev = NULL; int rc = -ENOBUFS; @@ -586,7 +591,7 @@ int ieee802154_list_iface(struct sk_buff *skb, struct genl_info *info) goto out_dev; rc = ieee802154_nl_fill_iface(msg, info->snd_portid, info->snd_seq, - 0, dev); + 0, dev); if (rc < 0) goto out_free; @@ -598,7 +603,6 @@ out_free: out_dev: dev_put(dev); return rc; - } int ieee802154_dump_iface(struct sk_buff *skb, struct netlink_callback *cb) @@ -616,7 +620,8 @@ int ieee802154_dump_iface(struct sk_buff *skb, struct netlink_callback *cb) goto cont; if (ieee802154_nl_fill_iface(skb, NETLINK_CB(cb->skb).portid, - cb->nlh->nlmsg_seq, NLM_F_MULTI, dev) < 0) + cb->nlh->nlmsg_seq, + NLM_F_MULTI, dev) < 0) break; cont: idx++; @@ -765,6 +770,7 @@ ieee802154_llsec_parse_key_id(struct genl_info *info, case IEEE802154_SCF_KEY_SHORT_INDEX: { u32 source = nla_get_u32(info->attrs[IEEE802154_ATTR_LLSEC_KEY_SOURCE_SHORT]); + desc->short_source = cpu_to_le32(source); break; } @@ -842,7 +848,7 @@ int ieee802154_llsec_getparams(struct sk_buff *skb, struct genl_info *info) goto out_dev; hdr = genlmsg_put(msg, 0, info->snd_seq, &nl802154_family, 0, - IEEE802154_LLSEC_GETPARAMS); + IEEE802154_LLSEC_GETPARAMS); if (!hdr) goto out_free; @@ -946,7 +952,7 @@ struct llsec_dump_data { static int ieee802154_llsec_dump_table(struct sk_buff *skb, struct netlink_callback *cb, - int (*step)(struct llsec_dump_data*)) + int (*step)(struct llsec_dump_data *)) { struct net *net = sock_net(skb->sk); struct net_device *dev; diff --git a/net/ieee802154/nl-phy.c b/net/ieee802154/nl-phy.c index 89b265aea151..972baf83411a 100644 --- a/net/ieee802154/nl-phy.c +++ b/net/ieee802154/nl-phy.c @@ -36,7 +36,7 @@ #include "ieee802154.h" static int ieee802154_nl_fill_phy(struct sk_buff *msg, u32 portid, - u32 seq, int flags, struct wpan_phy *phy) + u32 seq, int flags, struct wpan_phy *phy) { void *hdr; int i, pages = 0; @@ -48,7 +48,7 @@ static int ieee802154_nl_fill_phy(struct sk_buff *msg, u32 portid, return -EMSGSIZE; hdr = genlmsg_put(msg, 0, seq, &nl802154_family, flags, - IEEE802154_LIST_PHY); + IEEE802154_LIST_PHY); if (!hdr) goto out; @@ -80,7 +80,8 @@ out: int ieee802154_list_phy(struct sk_buff *skb, struct genl_info *info) { /* Request for interface name, index, type, IEEE address, - PAN Id, short address */ + * PAN Id, short address + */ struct sk_buff *msg; struct wpan_phy *phy; const char *name; @@ -105,7 +106,7 @@ int ieee802154_list_phy(struct sk_buff *skb, struct genl_info *info) goto out_dev; rc = ieee802154_nl_fill_phy(msg, info->snd_portid, info->snd_seq, - 0, phy); + 0, phy); if (rc < 0) goto out_free; @@ -117,7 +118,6 @@ out_free: out_dev: wpan_phy_put(phy); return rc; - } struct dump_phy_data { @@ -137,10 +137,10 @@ static int ieee802154_dump_phy_iter(struct wpan_phy *phy, void *_data) return 0; rc = ieee802154_nl_fill_phy(data->skb, - NETLINK_CB(data->cb->skb).portid, - data->cb->nlh->nlmsg_seq, - NLM_F_MULTI, - phy); + NETLINK_CB(data->cb->skb).portid, + data->cb->nlh->nlmsg_seq, + NLM_F_MULTI, + phy); if (rc < 0) { data->idx--; @@ -238,10 +238,9 @@ int ieee802154_add_iface(struct sk_buff *skb, struct genl_info *info) addr.sa_family = ARPHRD_IEEE802154; nla_memcpy(&addr.sa_data, info->attrs[IEEE802154_ATTR_HW_ADDR], - IEEE802154_ADDR_LEN); + IEEE802154_ADDR_LEN); - /* - * strangely enough, some callbacks (inetdev_event) from + /* strangely enough, some callbacks (inetdev_event) from * dev_set_mac_address require RTNL_LOCK */ rtnl_lock(); diff --git a/net/ieee802154/raw.c b/net/ieee802154/raw.c index 74d54fae33d7..9d1f64806f02 100644 --- a/net/ieee802154/raw.c +++ b/net/ieee802154/raw.c @@ -96,7 +96,7 @@ out: } static int raw_connect(struct sock *sk, struct sockaddr *uaddr, - int addr_len) + int addr_len) { return -ENOTSUPP; } @@ -106,8 +106,8 @@ static int raw_disconnect(struct sock *sk, int flags) return 0; } -static int raw_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg, - size_t size) +static int raw_sendmsg(struct kiocb *iocb, struct sock *sk, + struct msghdr *msg, size_t size) { struct net_device *dev; unsigned int mtu; @@ -145,7 +145,7 @@ static int raw_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg, hlen = LL_RESERVED_SPACE(dev); tlen = dev->needed_tailroom; skb = sock_alloc_send_skb(sk, hlen + tlen + size, - msg->msg_flags & MSG_DONTWAIT, &err); + msg->msg_flags & MSG_DONTWAIT, &err); if (!skb) goto out_dev; @@ -235,7 +235,6 @@ void ieee802154_raw_deliver(struct net_device *dev, struct sk_buff *skb) bh_lock_sock(sk); if (!sk->sk_bound_dev_if || sk->sk_bound_dev_if == dev->ifindex) { - struct sk_buff *clone; clone = skb_clone(skb, GFP_ATOMIC); @@ -248,13 +247,13 @@ void ieee802154_raw_deliver(struct net_device *dev, struct sk_buff *skb) } static int raw_getsockopt(struct sock *sk, int level, int optname, - char __user *optval, int __user *optlen) + char __user *optval, int __user *optlen) { return -EOPNOTSUPP; } static int raw_setsockopt(struct sock *sk, int level, int optname, - char __user *optval, unsigned int optlen) + char __user *optval, unsigned int optlen) { return -EOPNOTSUPP; } @@ -274,4 +273,3 @@ struct proto ieee802154_raw_prot = { .getsockopt = raw_getsockopt, .setsockopt = raw_setsockopt, }; - diff --git a/net/ieee802154/reassembly.c b/net/ieee802154/reassembly.c index 6f1428c4870b..ffec6ce51005 100644 --- a/net/ieee802154/reassembly.c +++ b/net/ieee802154/reassembly.c @@ -30,6 +30,8 @@ #include "reassembly.h" +static const char lowpan_frags_cache_name[] = "lowpan-frags"; + struct lowpan_frag_info { __be16 d_tag; u16 d_size; @@ -50,29 +52,25 @@ static unsigned int lowpan_hash_frag(__be16 tag, u16 d_size, const struct ieee802154_addr *saddr, const struct ieee802154_addr *daddr) { - u32 c; - net_get_random_once(&lowpan_frags.rnd, sizeof(lowpan_frags.rnd)); - c = jhash_3words(ieee802154_addr_hash(saddr), - ieee802154_addr_hash(daddr), - (__force u32)(tag + (d_size << 16)), - lowpan_frags.rnd); - - return c & (INETFRAGS_HASHSZ - 1); + return jhash_3words(ieee802154_addr_hash(saddr), + ieee802154_addr_hash(daddr), + (__force u32)(tag + (d_size << 16)), + lowpan_frags.rnd); } -static unsigned int lowpan_hashfn(struct inet_frag_queue *q) +static unsigned int lowpan_hashfn(const struct inet_frag_queue *q) { - struct lowpan_frag_queue *fq; + const struct lowpan_frag_queue *fq; fq = container_of(q, struct lowpan_frag_queue, q); return lowpan_hash_frag(fq->tag, fq->d_size, &fq->saddr, &fq->daddr); } -static bool lowpan_frag_match(struct inet_frag_queue *q, void *a) +static bool lowpan_frag_match(const struct inet_frag_queue *q, const void *a) { - struct lowpan_frag_queue *fq; - struct lowpan_create_arg *arg = a; + const struct lowpan_frag_queue *fq; + const struct lowpan_create_arg *arg = a; fq = container_of(q, struct lowpan_frag_queue, q); return fq->tag == arg->tag && fq->d_size == arg->d_size && @@ -80,10 +78,10 @@ static bool lowpan_frag_match(struct inet_frag_queue *q, void *a) ieee802154_addr_equal(&fq->daddr, arg->dst); } -static void lowpan_frag_init(struct inet_frag_queue *q, void *a) +static void lowpan_frag_init(struct inet_frag_queue *q, const void *a) { + const struct lowpan_create_arg *arg = a; struct lowpan_frag_queue *fq; - struct lowpan_create_arg *arg = a; fq = container_of(q, struct lowpan_frag_queue, q); @@ -103,7 +101,7 @@ static void lowpan_frag_expire(unsigned long data) spin_lock(&fq->q.lock); - if (fq->q.last_in & INET_FRAG_COMPLETE) + if (fq->q.flags & INET_FRAG_COMPLETE) goto out; inet_frag_kill(&fq->q, &lowpan_frags); @@ -128,7 +126,6 @@ fq_find(struct net *net, const struct lowpan_frag_info *frag_info, arg.src = src; arg.dst = dst; - read_lock(&lowpan_frags.lock); hash = lowpan_hash_frag(frag_info->d_tag, frag_info->d_size, src, dst); q = inet_frag_find(&ieee802154_lowpan->frags, @@ -147,7 +144,7 @@ static int lowpan_frag_queue(struct lowpan_frag_queue *fq, struct net_device *dev; int end, offset; - if (fq->q.last_in & INET_FRAG_COMPLETE) + if (fq->q.flags & INET_FRAG_COMPLETE) goto err; offset = lowpan_cb(skb)->d_offset << 3; @@ -159,14 +156,14 @@ static int lowpan_frag_queue(struct lowpan_frag_queue *fq, * or have different end, the segment is corrupted. */ if (end < fq->q.len || - ((fq->q.last_in & INET_FRAG_LAST_IN) && end != fq->q.len)) + ((fq->q.flags & INET_FRAG_LAST_IN) && end != fq->q.len)) goto err; - fq->q.last_in |= INET_FRAG_LAST_IN; + fq->q.flags |= INET_FRAG_LAST_IN; fq->q.len = end; } else { if (end > fq->q.len) { /* Some bits beyond end -> corruption. */ - if (fq->q.last_in & INET_FRAG_LAST_IN) + if (fq->q.flags & INET_FRAG_LAST_IN) goto err; fq->q.len = end; } @@ -206,13 +203,13 @@ found: if (frag_type == LOWPAN_DISPATCH_FRAG1) { /* Calculate uncomp. 6lowpan header to estimate full size */ fq->q.meat += lowpan_uncompress_size(skb, NULL); - fq->q.last_in |= INET_FRAG_FIRST_IN; + fq->q.flags |= INET_FRAG_FIRST_IN; } else { fq->q.meat += skb->len; } add_frag_mem_limit(&fq->q, skb->truesize); - if (fq->q.last_in == (INET_FRAG_FIRST_IN | INET_FRAG_LAST_IN) && + if (fq->q.flags == (INET_FRAG_FIRST_IN | INET_FRAG_LAST_IN) && fq->q.meat == fq->q.len) { int res; unsigned long orefdst = skb->_skb_refdst; @@ -223,7 +220,6 @@ found: return res; } - inet_frag_lru_move(&fq->q); return -1; err: kfree_skb(skb); @@ -373,11 +369,10 @@ int lowpan_frag_rcv(struct sk_buff *skb, const u8 frag_type) if (frag_info->d_size > ieee802154_lowpan->max_dsize) goto err; - inet_frag_evictor(&ieee802154_lowpan->frags, &lowpan_frags, false); - fq = fq_find(net, frag_info, &source, &dest); if (fq != NULL) { int ret; + spin_lock(&fq->q.lock); ret = lowpan_frag_queue(fq, skb, frag_type); spin_unlock(&fq->q.lock); @@ -393,20 +388,25 @@ err: EXPORT_SYMBOL(lowpan_frag_rcv); #ifdef CONFIG_SYSCTL +static int zero; + static struct ctl_table lowpan_frags_ns_ctl_table[] = { { .procname = "6lowpanfrag_high_thresh", .data = &init_net.ieee802154_lowpan.frags.high_thresh, .maxlen = sizeof(int), .mode = 0644, - .proc_handler = proc_dointvec + .proc_handler = proc_dointvec_minmax, + .extra1 = &init_net.ieee802154_lowpan.frags.low_thresh }, { .procname = "6lowpanfrag_low_thresh", .data = &init_net.ieee802154_lowpan.frags.low_thresh, .maxlen = sizeof(int), .mode = 0644, - .proc_handler = proc_dointvec + .proc_handler = proc_dointvec_minmax, + .extra1 = &zero, + .extra2 = &init_net.ieee802154_lowpan.frags.high_thresh }, { .procname = "6lowpanfrag_time", @@ -425,10 +425,12 @@ static struct ctl_table lowpan_frags_ns_ctl_table[] = { { } }; +/* secret interval has been deprecated */ +static int lowpan_frags_secret_interval_unused; static struct ctl_table lowpan_frags_ctl_table[] = { { .procname = "6lowpanfrag_secret_interval", - .data = &lowpan_frags.secret_interval, + .data = &lowpan_frags_secret_interval_unused, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec_jiffies, @@ -451,7 +453,10 @@ static int __net_init lowpan_frags_ns_sysctl_register(struct net *net) goto err_alloc; table[0].data = &ieee802154_lowpan->frags.high_thresh; + table[0].extra1 = &ieee802154_lowpan->frags.low_thresh; + table[0].extra2 = &init_net.ieee802154_lowpan.frags.high_thresh; table[1].data = &ieee802154_lowpan->frags.low_thresh; + table[1].extra2 = &ieee802154_lowpan->frags.high_thresh; table[2].data = &ieee802154_lowpan->frags.timeout; table[3].data = &ieee802154_lowpan->max_dsize; @@ -568,8 +573,10 @@ int __init lowpan_net_frag_init(void) lowpan_frags.qsize = sizeof(struct frag_queue); lowpan_frags.match = lowpan_frag_match; lowpan_frags.frag_expire = lowpan_frag_expire; - lowpan_frags.secret_interval = 10 * 60 * HZ; - inet_frags_init(&lowpan_frags); + lowpan_frags.frags_cache_name = lowpan_frags_cache_name; + ret = inet_frags_init(&lowpan_frags); + if (ret) + goto err_pernet; return ret; err_pernet: diff --git a/net/ieee802154/wpan-class.c b/net/ieee802154/wpan-class.c index 8d6f6704da84..4955e0fe5883 100644 --- a/net/ieee802154/wpan-class.c +++ b/net/ieee802154/wpan-class.c @@ -48,7 +48,8 @@ MASTER_SHOW(transmit_power, "%d +- 1 dB"); MASTER_SHOW(cca_mode, "%d"); static ssize_t channels_supported_show(struct device *dev, - struct device_attribute *attr, char *buf) + struct device_attribute *attr, + char *buf) { struct wpan_phy *phy = container_of(dev, struct wpan_phy, dev); int ret; @@ -57,7 +58,7 @@ static ssize_t channels_supported_show(struct device *dev, mutex_lock(&phy->pib_lock); for (i = 0; i < 32; i++) { ret = snprintf(buf + len, PAGE_SIZE - len, - "%#09x\n", phy->channels_supported[i]); + "%#09x\n", phy->channels_supported[i]); if (ret < 0) break; len += ret; @@ -80,6 +81,7 @@ ATTRIBUTE_GROUPS(pmib); static void wpan_phy_release(struct device *d) { struct wpan_phy *phy = container_of(d, struct wpan_phy, dev); + kfree(phy); } @@ -121,11 +123,12 @@ static int wpan_phy_iter(struct device *dev, void *_data) { struct wpan_phy_iter_data *wpid = _data; struct wpan_phy *phy = container_of(dev, struct wpan_phy, dev); + return wpid->fn(phy, wpid->data); } int wpan_phy_for_each(int (*fn)(struct wpan_phy *phy, void *data), - void *data) + void *data) { struct wpan_phy_iter_data wpid = { .fn = fn, @@ -197,6 +200,7 @@ EXPORT_SYMBOL(wpan_phy_free); static int __init wpan_phy_class_init(void) { int rc; + rc = class_register(&wpan_phy_class); if (rc) goto err; diff --git a/net/ipv4/Kconfig b/net/ipv4/Kconfig index 05c57f0fcabe..dbc10d84161f 100644 --- a/net/ipv4/Kconfig +++ b/net/ipv4/Kconfig @@ -307,6 +307,10 @@ config NET_IPVTI the notion of a secure tunnel for IPSEC and then use routing protocol on top. +config NET_UDP_TUNNEL + tristate + default n + config INET_AH tristate "IP: AH transformation" select XFRM_ALGO diff --git a/net/ipv4/Makefile b/net/ipv4/Makefile index f032688d20d3..8ee1cd4053ee 100644 --- a/net/ipv4/Makefile +++ b/net/ipv4/Makefile @@ -22,6 +22,7 @@ obj-$(CONFIG_NET_IPIP) += ipip.o gre-y := gre_demux.o obj-$(CONFIG_NET_IPGRE_DEMUX) += gre.o obj-$(CONFIG_NET_IPGRE) += ip_gre.o +obj-$(CONFIG_NET_UDP_TUNNEL) += udp_tunnel.o obj-$(CONFIG_NET_IPVTI) += ip_vti.o obj-$(CONFIG_SYN_COOKIES) += syncookies.o obj-$(CONFIG_INET_AH) += ah4.o diff --git a/net/ipv4/datagram.c b/net/ipv4/datagram.c index a3095fdefbed..90c0e8386116 100644 --- a/net/ipv4/datagram.c +++ b/net/ipv4/datagram.c @@ -76,6 +76,7 @@ int ip4_datagram_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len) inet->inet_daddr = fl4->daddr; inet->inet_dport = usin->sin_port; sk->sk_state = TCP_ESTABLISHED; + inet_set_txhash(sk); inet->inet_id = jiffies; sk_dst_set(sk, &rt->dst); diff --git a/net/ipv4/devinet.c b/net/ipv4/devinet.c index e9449376b58e..214882e7d6de 100644 --- a/net/ipv4/devinet.c +++ b/net/ipv4/devinet.c @@ -180,11 +180,12 @@ static BLOCKING_NOTIFIER_HEAD(inetaddr_chain); static void inet_del_ifa(struct in_device *in_dev, struct in_ifaddr **ifap, int destroy); #ifdef CONFIG_SYSCTL -static void devinet_sysctl_register(struct in_device *idev); +static int devinet_sysctl_register(struct in_device *idev); static void devinet_sysctl_unregister(struct in_device *idev); #else -static void devinet_sysctl_register(struct in_device *idev) +static int devinet_sysctl_register(struct in_device *idev) { + return 0; } static void devinet_sysctl_unregister(struct in_device *idev) { @@ -232,6 +233,7 @@ EXPORT_SYMBOL(in_dev_finish_destroy); static struct in_device *inetdev_init(struct net_device *dev) { struct in_device *in_dev; + int err = -ENOMEM; ASSERT_RTNL(); @@ -252,7 +254,13 @@ static struct in_device *inetdev_init(struct net_device *dev) /* Account for reference dev->ip_ptr (below) */ in_dev_hold(in_dev); - devinet_sysctl_register(in_dev); + err = devinet_sysctl_register(in_dev); + if (err) { + in_dev->dead = 1; + in_dev_put(in_dev); + in_dev = NULL; + goto out; + } ip_mc_init_dev(in_dev); if (dev->flags & IFF_UP) ip_mc_up(in_dev); @@ -260,7 +268,7 @@ static struct in_device *inetdev_init(struct net_device *dev) /* we can receive as soon as ip_ptr is set -- do this last */ rcu_assign_pointer(dev->ip_ptr, in_dev); out: - return in_dev; + return in_dev ?: ERR_PTR(err); out_kfree: kfree(in_dev); in_dev = NULL; @@ -1347,8 +1355,8 @@ static int inetdev_event(struct notifier_block *this, unsigned long event, if (!in_dev) { if (event == NETDEV_REGISTER) { in_dev = inetdev_init(dev); - if (!in_dev) - return notifier_from_errno(-ENOMEM); + if (IS_ERR(in_dev)) + return notifier_from_errno(PTR_ERR(in_dev)); if (dev->flags & IFF_LOOPBACK) { IN_DEV_CONF_SET(in_dev, NOXFRM, 1); IN_DEV_CONF_SET(in_dev, NOPOLICY, 1); @@ -2182,11 +2190,21 @@ static void __devinet_sysctl_unregister(struct ipv4_devconf *cnf) kfree(t); } -static void devinet_sysctl_register(struct in_device *idev) +static int devinet_sysctl_register(struct in_device *idev) { - neigh_sysctl_register(idev->dev, idev->arp_parms, NULL); - __devinet_sysctl_register(dev_net(idev->dev), idev->dev->name, + int err; + + if (!sysctl_dev_name_is_allowed(idev->dev->name)) + return -EINVAL; + + err = neigh_sysctl_register(idev->dev, idev->arp_parms, NULL); + if (err) + return err; + err = __devinet_sysctl_register(dev_net(idev->dev), idev->dev->name, &idev->cnf); + if (err) + neigh_sysctl_unregister(idev->arp_parms); + return err; } static void devinet_sysctl_unregister(struct in_device *idev) diff --git a/net/ipv4/gre_offload.c b/net/ipv4/gre_offload.c index f0bdd47bbbcb..6556263c8fa5 100644 --- a/net/ipv4/gre_offload.c +++ b/net/ipv4/gre_offload.c @@ -74,7 +74,7 @@ static struct sk_buff *gre_gso_segment(struct sk_buff *skb, /* segment inner packet. */ enc_features = skb->dev->hw_enc_features & netif_skb_features(skb); segs = skb_mac_gso_segment(skb, enc_features); - if (!segs || IS_ERR(segs)) { + if (IS_ERR_OR_NULL(segs)) { skb_gso_error_unwind(skb, protocol, ghl, mac_offset, mac_len); goto out; } diff --git a/net/ipv4/icmp.c b/net/ipv4/icmp.c index 42b7bcf8045b..ea7d4afe8205 100644 --- a/net/ipv4/icmp.c +++ b/net/ipv4/icmp.c @@ -663,16 +663,16 @@ static void icmp_socket_deliver(struct sk_buff *skb, u32 info) /* Checkin full IP header plus 8 bytes of protocol to * avoid additional coding at protocol handlers. */ - if (!pskb_may_pull(skb, iph->ihl * 4 + 8)) + if (!pskb_may_pull(skb, iph->ihl * 4 + 8)) { + ICMP_INC_STATS_BH(dev_net(skb->dev), ICMP_MIB_INERRORS); return; + } raw_icmp_error(skb, protocol, info); - rcu_read_lock(); ipprot = rcu_dereference(inet_protos[protocol]); if (ipprot && ipprot->err_handler) ipprot->err_handler(skb, info); - rcu_read_unlock(); } static bool icmp_tag_validation(int proto) diff --git a/net/ipv4/igmp.c b/net/ipv4/igmp.c index db710b059bab..f10eab462282 100644 --- a/net/ipv4/igmp.c +++ b/net/ipv4/igmp.c @@ -1321,7 +1321,7 @@ void ip_mc_inc_group(struct in_device *in_dev, __be32 addr) atomic_set(&im->refcnt, 1); spin_lock_init(&im->lock); #ifdef CONFIG_IP_MULTICAST - setup_timer(&im->timer, &igmp_timer_expire, (unsigned long)im); + setup_timer(&im->timer, igmp_timer_expire, (unsigned long)im); im->unsolicit_count = IGMP_Unsolicited_Report_Count; #endif diff --git a/net/ipv4/inet_fragment.c b/net/ipv4/inet_fragment.c index 3b01959bf4bb..9eb89f3f0ee4 100644 --- a/net/ipv4/inet_fragment.c +++ b/net/ipv4/inet_fragment.c @@ -25,6 +25,12 @@ #include <net/inet_frag.h> #include <net/inet_ecn.h> +#define INETFRAGS_EVICT_BUCKETS 128 +#define INETFRAGS_EVICT_MAX 512 + +/* don't rebuild inetfrag table with new secret more often than this */ +#define INETFRAGS_MIN_REBUILD_INTERVAL (5 * HZ) + /* Given the OR values of all fragments, apply RFC 3168 5.3 requirements * Value : 0xff if frame should be dropped. * 0 or INET_ECN_CE value, to be ORed in to final iph->tos field @@ -46,24 +52,39 @@ const u8 ip_frag_ecn_table[16] = { }; EXPORT_SYMBOL(ip_frag_ecn_table); -static void inet_frag_secret_rebuild(unsigned long dummy) +static unsigned int +inet_frag_hashfn(const struct inet_frags *f, const struct inet_frag_queue *q) +{ + return f->hashfn(q) & (INETFRAGS_HASHSZ - 1); +} + +static bool inet_frag_may_rebuild(struct inet_frags *f) +{ + return time_after(jiffies, + f->last_rebuild_jiffies + INETFRAGS_MIN_REBUILD_INTERVAL); +} + +static void inet_frag_secret_rebuild(struct inet_frags *f) { - struct inet_frags *f = (struct inet_frags *)dummy; - unsigned long now = jiffies; int i; - /* Per bucket lock NOT needed here, due to write lock protection */ - write_lock(&f->lock); + write_seqlock_bh(&f->rnd_seqlock); + + if (!inet_frag_may_rebuild(f)) + goto out; get_random_bytes(&f->rnd, sizeof(u32)); + for (i = 0; i < INETFRAGS_HASHSZ; i++) { struct inet_frag_bucket *hb; struct inet_frag_queue *q; struct hlist_node *n; hb = &f->hash[i]; + spin_lock(&hb->chain_lock); + hlist_for_each_entry_safe(q, n, &hb->chain, list) { - unsigned int hval = f->hashfn(q); + unsigned int hval = inet_frag_hashfn(f, q); if (hval != i) { struct inet_frag_bucket *hb_dest; @@ -72,76 +93,200 @@ static void inet_frag_secret_rebuild(unsigned long dummy) /* Relink to new hash chain. */ hb_dest = &f->hash[hval]; + + /* This is the only place where we take + * another chain_lock while already holding + * one. As this will not run concurrently, + * we cannot deadlock on hb_dest lock below, if its + * already locked it will be released soon since + * other caller cannot be waiting for hb lock + * that we've taken above. + */ + spin_lock_nested(&hb_dest->chain_lock, + SINGLE_DEPTH_NESTING); hlist_add_head(&q->list, &hb_dest->chain); + spin_unlock(&hb_dest->chain_lock); } } + spin_unlock(&hb->chain_lock); + } + + f->rebuild = false; + f->last_rebuild_jiffies = jiffies; +out: + write_sequnlock_bh(&f->rnd_seqlock); +} + +static bool inet_fragq_should_evict(const struct inet_frag_queue *q) +{ + return q->net->low_thresh == 0 || + frag_mem_limit(q->net) >= q->net->low_thresh; +} + +static unsigned int +inet_evict_bucket(struct inet_frags *f, struct inet_frag_bucket *hb) +{ + struct inet_frag_queue *fq; + struct hlist_node *n; + unsigned int evicted = 0; + HLIST_HEAD(expired); + +evict_again: + spin_lock(&hb->chain_lock); + + hlist_for_each_entry_safe(fq, n, &hb->chain, list) { + if (!inet_fragq_should_evict(fq)) + continue; + + if (!del_timer(&fq->timer)) { + /* q expiring right now thus increment its refcount so + * it won't be freed under us and wait until the timer + * has finished executing then destroy it + */ + atomic_inc(&fq->refcnt); + spin_unlock(&hb->chain_lock); + del_timer_sync(&fq->timer); + WARN_ON(atomic_read(&fq->refcnt) != 1); + inet_frag_put(fq, f); + goto evict_again; + } + + fq->flags |= INET_FRAG_EVICTED; + hlist_del(&fq->list); + hlist_add_head(&fq->list, &expired); + ++evicted; } - write_unlock(&f->lock); - mod_timer(&f->secret_timer, now + f->secret_interval); + spin_unlock(&hb->chain_lock); + + hlist_for_each_entry_safe(fq, n, &expired, list) + f->frag_expire((unsigned long) fq); + + return evicted; } -void inet_frags_init(struct inet_frags *f) +static void inet_frag_worker(struct work_struct *work) +{ + unsigned int budget = INETFRAGS_EVICT_BUCKETS; + unsigned int i, evicted = 0; + struct inet_frags *f; + + f = container_of(work, struct inet_frags, frags_work); + + BUILD_BUG_ON(INETFRAGS_EVICT_BUCKETS >= INETFRAGS_HASHSZ); + + local_bh_disable(); + + for (i = ACCESS_ONCE(f->next_bucket); budget; --budget) { + evicted += inet_evict_bucket(f, &f->hash[i]); + i = (i + 1) & (INETFRAGS_HASHSZ - 1); + if (evicted > INETFRAGS_EVICT_MAX) + break; + } + + f->next_bucket = i; + + local_bh_enable(); + + if (f->rebuild && inet_frag_may_rebuild(f)) + inet_frag_secret_rebuild(f); +} + +static void inet_frag_schedule_worker(struct inet_frags *f) +{ + if (unlikely(!work_pending(&f->frags_work))) + schedule_work(&f->frags_work); +} + +int inet_frags_init(struct inet_frags *f) { int i; + INIT_WORK(&f->frags_work, inet_frag_worker); + for (i = 0; i < INETFRAGS_HASHSZ; i++) { struct inet_frag_bucket *hb = &f->hash[i]; spin_lock_init(&hb->chain_lock); INIT_HLIST_HEAD(&hb->chain); } - rwlock_init(&f->lock); - setup_timer(&f->secret_timer, inet_frag_secret_rebuild, - (unsigned long)f); - f->secret_timer.expires = jiffies + f->secret_interval; - add_timer(&f->secret_timer); + seqlock_init(&f->rnd_seqlock); + f->last_rebuild_jiffies = 0; + f->frags_cachep = kmem_cache_create(f->frags_cache_name, f->qsize, 0, 0, + NULL); + if (!f->frags_cachep) + return -ENOMEM; + + return 0; } EXPORT_SYMBOL(inet_frags_init); void inet_frags_init_net(struct netns_frags *nf) { - nf->nqueues = 0; init_frag_mem_limit(nf); - INIT_LIST_HEAD(&nf->lru_list); - spin_lock_init(&nf->lru_lock); } EXPORT_SYMBOL(inet_frags_init_net); void inet_frags_fini(struct inet_frags *f) { - del_timer(&f->secret_timer); + cancel_work_sync(&f->frags_work); + kmem_cache_destroy(f->frags_cachep); } EXPORT_SYMBOL(inet_frags_fini); void inet_frags_exit_net(struct netns_frags *nf, struct inet_frags *f) { - nf->low_thresh = 0; + unsigned int seq; + int i; + nf->low_thresh = 0; local_bh_disable(); - inet_frag_evictor(nf, f, true); + +evict_again: + seq = read_seqbegin(&f->rnd_seqlock); + + for (i = 0; i < INETFRAGS_HASHSZ ; i++) + inet_evict_bucket(f, &f->hash[i]); + + if (read_seqretry(&f->rnd_seqlock, seq)) + goto evict_again; + local_bh_enable(); percpu_counter_destroy(&nf->mem); } EXPORT_SYMBOL(inet_frags_exit_net); -static inline void fq_unlink(struct inet_frag_queue *fq, struct inet_frags *f) +static struct inet_frag_bucket * +get_frag_bucket_locked(struct inet_frag_queue *fq, struct inet_frags *f) +__acquires(hb->chain_lock) { struct inet_frag_bucket *hb; - unsigned int hash; + unsigned int seq, hash; + + restart: + seq = read_seqbegin(&f->rnd_seqlock); - read_lock(&f->lock); - hash = f->hashfn(fq); + hash = inet_frag_hashfn(f, fq); hb = &f->hash[hash]; spin_lock(&hb->chain_lock); + if (read_seqretry(&f->rnd_seqlock, seq)) { + spin_unlock(&hb->chain_lock); + goto restart; + } + + return hb; +} + +static inline void fq_unlink(struct inet_frag_queue *fq, struct inet_frags *f) +{ + struct inet_frag_bucket *hb; + + hb = get_frag_bucket_locked(fq, f); hlist_del(&fq->list); spin_unlock(&hb->chain_lock); - - read_unlock(&f->lock); - inet_frag_lru_del(fq); } void inet_frag_kill(struct inet_frag_queue *fq, struct inet_frags *f) @@ -149,30 +294,29 @@ void inet_frag_kill(struct inet_frag_queue *fq, struct inet_frags *f) if (del_timer(&fq->timer)) atomic_dec(&fq->refcnt); - if (!(fq->last_in & INET_FRAG_COMPLETE)) { + if (!(fq->flags & INET_FRAG_COMPLETE)) { fq_unlink(fq, f); atomic_dec(&fq->refcnt); - fq->last_in |= INET_FRAG_COMPLETE; + fq->flags |= INET_FRAG_COMPLETE; } } EXPORT_SYMBOL(inet_frag_kill); static inline void frag_kfree_skb(struct netns_frags *nf, struct inet_frags *f, - struct sk_buff *skb) + struct sk_buff *skb) { if (f->skb_free) f->skb_free(skb); kfree_skb(skb); } -void inet_frag_destroy(struct inet_frag_queue *q, struct inet_frags *f, - int *work) +void inet_frag_destroy(struct inet_frag_queue *q, struct inet_frags *f) { struct sk_buff *fp; struct netns_frags *nf; unsigned int sum, sum_truesize = 0; - WARN_ON(!(q->last_in & INET_FRAG_COMPLETE)); + WARN_ON(!(q->flags & INET_FRAG_COMPLETE)); WARN_ON(del_timer(&q->timer) != 0); /* Release all fragment data. */ @@ -186,87 +330,32 @@ void inet_frag_destroy(struct inet_frag_queue *q, struct inet_frags *f, fp = xp; } sum = sum_truesize + f->qsize; - if (work) - *work -= sum; sub_frag_mem_limit(q, sum); if (f->destructor) f->destructor(q); - kfree(q); - + kmem_cache_free(f->frags_cachep, q); } EXPORT_SYMBOL(inet_frag_destroy); -int inet_frag_evictor(struct netns_frags *nf, struct inet_frags *f, bool force) -{ - struct inet_frag_queue *q; - int work, evicted = 0; - - if (!force) { - if (frag_mem_limit(nf) <= nf->high_thresh) - return 0; - } - - work = frag_mem_limit(nf) - nf->low_thresh; - while (work > 0 || force) { - spin_lock(&nf->lru_lock); - - if (list_empty(&nf->lru_list)) { - spin_unlock(&nf->lru_lock); - break; - } - - q = list_first_entry(&nf->lru_list, - struct inet_frag_queue, lru_list); - atomic_inc(&q->refcnt); - /* Remove q from list to avoid several CPUs grabbing it */ - list_del_init(&q->lru_list); - - spin_unlock(&nf->lru_lock); - - spin_lock(&q->lock); - if (!(q->last_in & INET_FRAG_COMPLETE)) - inet_frag_kill(q, f); - spin_unlock(&q->lock); - - if (atomic_dec_and_test(&q->refcnt)) - inet_frag_destroy(q, f, &work); - evicted++; - } - - return evicted; -} -EXPORT_SYMBOL(inet_frag_evictor); - static struct inet_frag_queue *inet_frag_intern(struct netns_frags *nf, - struct inet_frag_queue *qp_in, struct inet_frags *f, - void *arg) + struct inet_frag_queue *qp_in, + struct inet_frags *f, + void *arg) { - struct inet_frag_bucket *hb; + struct inet_frag_bucket *hb = get_frag_bucket_locked(qp_in, f); struct inet_frag_queue *qp; - unsigned int hash; - - read_lock(&f->lock); /* Protects against hash rebuild */ - /* - * While we stayed w/o the lock other CPU could update - * the rnd seed, so we need to re-calculate the hash - * chain. Fortunatelly the qp_in can be used to get one. - */ - hash = f->hashfn(qp_in); - hb = &f->hash[hash]; - spin_lock(&hb->chain_lock); #ifdef CONFIG_SMP /* With SMP race we have to recheck hash table, because - * such entry could be created on other cpu, while we - * released the hash bucket lock. + * such entry could have been created on other cpu before + * we acquired hash bucket lock. */ hlist_for_each_entry(qp, &hb->chain, list) { if (qp->net == nf && f->match(qp, arg)) { atomic_inc(&qp->refcnt); spin_unlock(&hb->chain_lock); - read_unlock(&f->lock); - qp_in->last_in |= INET_FRAG_COMPLETE; + qp_in->flags |= INET_FRAG_COMPLETE; inet_frag_put(qp_in, f); return qp; } @@ -278,19 +367,24 @@ static struct inet_frag_queue *inet_frag_intern(struct netns_frags *nf, atomic_inc(&qp->refcnt); hlist_add_head(&qp->list, &hb->chain); - inet_frag_lru_add(nf, qp); + spin_unlock(&hb->chain_lock); - read_unlock(&f->lock); return qp; } static struct inet_frag_queue *inet_frag_alloc(struct netns_frags *nf, - struct inet_frags *f, void *arg) + struct inet_frags *f, + void *arg) { struct inet_frag_queue *q; - q = kzalloc(f->qsize, GFP_ATOMIC); + if (frag_mem_limit(nf) > nf->high_thresh) { + inet_frag_schedule_worker(f); + return NULL; + } + + q = kmem_cache_zalloc(f->frags_cachep, GFP_ATOMIC); if (q == NULL) return NULL; @@ -301,13 +395,13 @@ static struct inet_frag_queue *inet_frag_alloc(struct netns_frags *nf, setup_timer(&q->timer, f->frag_expire, (unsigned long)q); spin_lock_init(&q->lock); atomic_set(&q->refcnt, 1); - INIT_LIST_HEAD(&q->lru_list); return q; } static struct inet_frag_queue *inet_frag_create(struct netns_frags *nf, - struct inet_frags *f, void *arg) + struct inet_frags *f, + void *arg) { struct inet_frag_queue *q; @@ -319,13 +413,17 @@ static struct inet_frag_queue *inet_frag_create(struct netns_frags *nf, } struct inet_frag_queue *inet_frag_find(struct netns_frags *nf, - struct inet_frags *f, void *key, unsigned int hash) - __releases(&f->lock) + struct inet_frags *f, void *key, + unsigned int hash) { struct inet_frag_bucket *hb; struct inet_frag_queue *q; int depth = 0; + if (frag_mem_limit(nf) > nf->low_thresh) + inet_frag_schedule_worker(f); + + hash &= (INETFRAGS_HASHSZ - 1); hb = &f->hash[hash]; spin_lock(&hb->chain_lock); @@ -333,18 +431,22 @@ struct inet_frag_queue *inet_frag_find(struct netns_frags *nf, if (q->net == nf && f->match(q, key)) { atomic_inc(&q->refcnt); spin_unlock(&hb->chain_lock); - read_unlock(&f->lock); return q; } depth++; } spin_unlock(&hb->chain_lock); - read_unlock(&f->lock); if (depth <= INETFRAGS_MAXDEPTH) return inet_frag_create(nf, f, key); - else - return ERR_PTR(-ENOBUFS); + + if (inet_frag_may_rebuild(f)) { + if (!f->rebuild) + f->rebuild = true; + inet_frag_schedule_worker(f); + } + + return ERR_PTR(-ENOBUFS); } EXPORT_SYMBOL(inet_frag_find); diff --git a/net/ipv4/ip_fragment.c b/net/ipv4/ip_fragment.c index ed32313e307c..15f0e2bad7ad 100644 --- a/net/ipv4/ip_fragment.c +++ b/net/ipv4/ip_fragment.c @@ -55,6 +55,7 @@ */ static int sysctl_ipfrag_max_dist __read_mostly = 64; +static const char ip_frag_cache_name[] = "ip4-frags"; struct ipfrag_skb_cb { @@ -86,11 +87,6 @@ static inline u8 ip4_frag_ecn(u8 tos) static struct inet_frags ip4_frags; -int ip_frag_nqueues(struct net *net) -{ - return net->ipv4.frags.nqueues; -} - int ip_frag_mem(struct net *net) { return sum_frag_mem_limit(&net->ipv4.frags); @@ -109,21 +105,21 @@ static unsigned int ipqhashfn(__be16 id, __be32 saddr, __be32 daddr, u8 prot) net_get_random_once(&ip4_frags.rnd, sizeof(ip4_frags.rnd)); return jhash_3words((__force u32)id << 16 | prot, (__force u32)saddr, (__force u32)daddr, - ip4_frags.rnd) & (INETFRAGS_HASHSZ - 1); + ip4_frags.rnd); } -static unsigned int ip4_hashfn(struct inet_frag_queue *q) +static unsigned int ip4_hashfn(const struct inet_frag_queue *q) { - struct ipq *ipq; + const struct ipq *ipq; ipq = container_of(q, struct ipq, q); return ipqhashfn(ipq->id, ipq->saddr, ipq->daddr, ipq->protocol); } -static bool ip4_frag_match(struct inet_frag_queue *q, void *a) +static bool ip4_frag_match(const struct inet_frag_queue *q, const void *a) { - struct ipq *qp; - struct ip4_create_arg *arg = a; + const struct ipq *qp; + const struct ip4_create_arg *arg = a; qp = container_of(q, struct ipq, q); return qp->id == arg->iph->id && @@ -133,14 +129,14 @@ static bool ip4_frag_match(struct inet_frag_queue *q, void *a) qp->user == arg->user; } -static void ip4_frag_init(struct inet_frag_queue *q, void *a) +static void ip4_frag_init(struct inet_frag_queue *q, const void *a) { struct ipq *qp = container_of(q, struct ipq, q); struct netns_ipv4 *ipv4 = container_of(q->net, struct netns_ipv4, frags); struct net *net = container_of(ipv4, struct net, ipv4); - struct ip4_create_arg *arg = a; + const struct ip4_create_arg *arg = a; qp->protocol = arg->iph->protocol; qp->id = arg->iph->id; @@ -177,18 +173,6 @@ static void ipq_kill(struct ipq *ipq) inet_frag_kill(&ipq->q, &ip4_frags); } -/* Memory limiting on fragments. Evictor trashes the oldest - * fragment queue until we are back under the threshold. - */ -static void ip_evictor(struct net *net) -{ - int evicted; - - evicted = inet_frag_evictor(&net->ipv4.frags, &ip4_frags, false); - if (evicted) - IP_ADD_STATS_BH(net, IPSTATS_MIB_REASMFAILS, evicted); -} - /* * Oops, a fragment queue timed out. Kill it and send an ICMP reply. */ @@ -202,19 +186,22 @@ static void ip_expire(unsigned long arg) spin_lock(&qp->q.lock); - if (qp->q.last_in & INET_FRAG_COMPLETE) + if (qp->q.flags & INET_FRAG_COMPLETE) goto out; ipq_kill(qp); - - IP_INC_STATS_BH(net, IPSTATS_MIB_REASMTIMEOUT); IP_INC_STATS_BH(net, IPSTATS_MIB_REASMFAILS); - if ((qp->q.last_in & INET_FRAG_FIRST_IN) && qp->q.fragments != NULL) { + if (!(qp->q.flags & INET_FRAG_EVICTED)) { struct sk_buff *head = qp->q.fragments; const struct iphdr *iph; int err; + IP_INC_STATS_BH(net, IPSTATS_MIB_REASMTIMEOUT); + + if (!(qp->q.flags & INET_FRAG_FIRST_IN) || !qp->q.fragments) + goto out; + rcu_read_lock(); head->dev = dev_get_by_index_rcu(net, qp->iif); if (!head->dev) @@ -227,8 +214,7 @@ static void ip_expire(unsigned long arg) if (err) goto out_rcu_unlock; - /* - * Only an end host needs to send an ICMP + /* Only an end host needs to send an ICMP * "Fragment Reassembly Timeout" message, per RFC792. */ if (qp->user == IP_DEFRAG_AF_PACKET || @@ -237,7 +223,6 @@ static void ip_expire(unsigned long arg) (skb_rtable(head)->rt_type != RTN_LOCAL))) goto out_rcu_unlock; - /* Send an ICMP "Fragment Reassembly Timeout" message. */ icmp_send(head, ICMP_TIME_EXCEEDED, ICMP_EXC_FRAGTIME, 0); out_rcu_unlock: @@ -260,7 +245,6 @@ static inline struct ipq *ip_find(struct net *net, struct iphdr *iph, u32 user) arg.iph = iph; arg.user = user; - read_lock(&ip4_frags.lock); hash = ipqhashfn(iph->id, iph->saddr, iph->daddr, iph->protocol); q = inet_frag_find(&net->ipv4.frags, &ip4_frags, &arg, hash); @@ -319,7 +303,7 @@ static int ip_frag_reinit(struct ipq *qp) } while (fp); sub_frag_mem_limit(&qp->q, sum_truesize); - qp->q.last_in = 0; + qp->q.flags = 0; qp->q.len = 0; qp->q.meat = 0; qp->q.fragments = NULL; @@ -340,7 +324,7 @@ static int ip_frag_queue(struct ipq *qp, struct sk_buff *skb) int err = -ENOENT; u8 ecn; - if (qp->q.last_in & INET_FRAG_COMPLETE) + if (qp->q.flags & INET_FRAG_COMPLETE) goto err; if (!(IPCB(skb)->flags & IPSKB_FRAG_COMPLETE) && @@ -367,9 +351,9 @@ static int ip_frag_queue(struct ipq *qp, struct sk_buff *skb) * or have different end, the segment is corrupted. */ if (end < qp->q.len || - ((qp->q.last_in & INET_FRAG_LAST_IN) && end != qp->q.len)) + ((qp->q.flags & INET_FRAG_LAST_IN) && end != qp->q.len)) goto err; - qp->q.last_in |= INET_FRAG_LAST_IN; + qp->q.flags |= INET_FRAG_LAST_IN; qp->q.len = end; } else { if (end&7) { @@ -379,7 +363,7 @@ static int ip_frag_queue(struct ipq *qp, struct sk_buff *skb) } if (end > qp->q.len) { /* Some bits beyond end -> corruption. */ - if (qp->q.last_in & INET_FRAG_LAST_IN) + if (qp->q.flags & INET_FRAG_LAST_IN) goto err; qp->q.len = end; } @@ -488,13 +472,13 @@ found: qp->ecn |= ecn; add_frag_mem_limit(&qp->q, skb->truesize); if (offset == 0) - qp->q.last_in |= INET_FRAG_FIRST_IN; + qp->q.flags |= INET_FRAG_FIRST_IN; if (ip_hdr(skb)->frag_off & htons(IP_DF) && skb->len + ihl > qp->q.max_size) qp->q.max_size = skb->len + ihl; - if (qp->q.last_in == (INET_FRAG_FIRST_IN | INET_FRAG_LAST_IN) && + if (qp->q.flags == (INET_FRAG_FIRST_IN | INET_FRAG_LAST_IN) && qp->q.meat == qp->q.len) { unsigned long orefdst = skb->_skb_refdst; @@ -505,7 +489,6 @@ found: } skb_dst_drop(skb); - inet_frag_lru_move(&qp->q); return -EINPROGRESS; err: @@ -655,9 +638,6 @@ int ip_defrag(struct sk_buff *skb, u32 user) net = skb->dev ? dev_net(skb->dev) : dev_net(skb_dst(skb)->dev); IP_INC_STATS_BH(net, IPSTATS_MIB_REASMREQDS); - /* Start by cleaning up the memory. */ - ip_evictor(net); - /* Lookup (or create) queue header */ if ((qp = ip_find(net, ip_hdr(skb), user)) != NULL) { int ret; @@ -721,14 +701,17 @@ static struct ctl_table ip4_frags_ns_ctl_table[] = { .data = &init_net.ipv4.frags.high_thresh, .maxlen = sizeof(int), .mode = 0644, - .proc_handler = proc_dointvec + .proc_handler = proc_dointvec_minmax, + .extra1 = &init_net.ipv4.frags.low_thresh }, { .procname = "ipfrag_low_thresh", .data = &init_net.ipv4.frags.low_thresh, .maxlen = sizeof(int), .mode = 0644, - .proc_handler = proc_dointvec + .proc_handler = proc_dointvec_minmax, + .extra1 = &zero, + .extra2 = &init_net.ipv4.frags.high_thresh }, { .procname = "ipfrag_time", @@ -740,10 +723,12 @@ static struct ctl_table ip4_frags_ns_ctl_table[] = { { } }; +/* secret interval has been deprecated */ +static int ip4_frags_secret_interval_unused; static struct ctl_table ip4_frags_ctl_table[] = { { .procname = "ipfrag_secret_interval", - .data = &ip4_frags.secret_interval, + .data = &ip4_frags_secret_interval_unused, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec_jiffies, @@ -771,7 +756,10 @@ static int __net_init ip4_frags_ns_ctl_register(struct net *net) goto err_alloc; table[0].data = &net->ipv4.frags.high_thresh; + table[0].extra1 = &net->ipv4.frags.low_thresh; + table[0].extra2 = &init_net.ipv4.frags.high_thresh; table[1].data = &net->ipv4.frags.low_thresh; + table[1].extra2 = &net->ipv4.frags.high_thresh; table[2].data = &net->ipv4.frags.timeout; /* Don't export sysctls to unprivileged users */ @@ -873,6 +861,7 @@ void __init ipfrag_init(void) ip4_frags.qsize = sizeof(struct ipq); ip4_frags.match = ip4_frag_match; ip4_frags.frag_expire = ip_expire; - ip4_frags.secret_interval = 10 * 60 * HZ; - inet_frags_init(&ip4_frags); + ip4_frags.frags_cache_name = ip_frag_cache_name; + if (inet_frags_init(&ip4_frags)) + panic("IP: failed to allocate ip4_frags cache\n"); } diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c index 8d3b6b0e9857..215af2b155cb 100644 --- a/net/ipv4/ip_output.c +++ b/net/ipv4/ip_output.c @@ -855,11 +855,15 @@ static int __ip_append_data(struct sock *sk, unsigned int maxfraglen, fragheaderlen, maxnonfragsize; int csummode = CHECKSUM_NONE; struct rtable *rt = (struct rtable *)cork->dst; + u32 tskey = 0; skb = skb_peek_tail(queue); exthdrlen = !skb ? rt->dst.header_len : 0; mtu = cork->fragsize; + if (cork->tx_flags & SKBTX_ANY_SW_TSTAMP && + sk->sk_tsflags & SOF_TIMESTAMPING_OPT_ID) + tskey = sk->sk_tskey++; hh_len = LL_RESERVED_SPACE(rt->dst.dev); @@ -962,10 +966,6 @@ alloc_new_skb: sk->sk_allocation); if (unlikely(skb == NULL)) err = -ENOBUFS; - else - /* only the initial fragment is - time stamped */ - cork->tx_flags = 0; } if (skb == NULL) goto error; @@ -976,7 +976,12 @@ alloc_new_skb: skb->ip_summed = csummode; skb->csum = 0; skb_reserve(skb, hh_len); + + /* only the initial fragment is time stamped */ skb_shinfo(skb)->tx_flags = cork->tx_flags; + cork->tx_flags = 0; + skb_shinfo(skb)->tskey = tskey; + tskey = 0; /* * Find where to start putting bytes. diff --git a/net/ipv4/ip_sockglue.c b/net/ipv4/ip_sockglue.c index 64741b938632..5cb830c78990 100644 --- a/net/ipv4/ip_sockglue.c +++ b/net/ipv4/ip_sockglue.c @@ -1319,7 +1319,7 @@ static int do_ip_getsockopt(struct sock *sk, int level, int optname, if (sk->sk_type != SOCK_STREAM) return -ENOPROTOOPT; - msg.msg_control = optval; + msg.msg_control = (__force void *) optval; msg.msg_controllen = len; msg.msg_flags = flags; diff --git a/net/ipv4/ip_tunnel.c b/net/ipv4/ip_tunnel.c index 6f9de61dce5f..afed1aac2638 100644 --- a/net/ipv4/ip_tunnel.c +++ b/net/ipv4/ip_tunnel.c @@ -69,23 +69,25 @@ static unsigned int ip_tunnel_hash(__be32 key, __be32 remote) } static void __tunnel_dst_set(struct ip_tunnel_dst *idst, - struct dst_entry *dst) + struct dst_entry *dst, __be32 saddr) { struct dst_entry *old_dst; dst_clone(dst); old_dst = xchg((__force struct dst_entry **)&idst->dst, dst); dst_release(old_dst); + idst->saddr = saddr; } -static void tunnel_dst_set(struct ip_tunnel *t, struct dst_entry *dst) +static void tunnel_dst_set(struct ip_tunnel *t, + struct dst_entry *dst, __be32 saddr) { - __tunnel_dst_set(this_cpu_ptr(t->dst_cache), dst); + __tunnel_dst_set(this_cpu_ptr(t->dst_cache), dst, saddr); } static void tunnel_dst_reset(struct ip_tunnel *t) { - tunnel_dst_set(t, NULL); + tunnel_dst_set(t, NULL, 0); } void ip_tunnel_dst_reset_all(struct ip_tunnel *t) @@ -93,20 +95,25 @@ void ip_tunnel_dst_reset_all(struct ip_tunnel *t) int i; for_each_possible_cpu(i) - __tunnel_dst_set(per_cpu_ptr(t->dst_cache, i), NULL); + __tunnel_dst_set(per_cpu_ptr(t->dst_cache, i), NULL, 0); } EXPORT_SYMBOL(ip_tunnel_dst_reset_all); -static struct rtable *tunnel_rtable_get(struct ip_tunnel *t, u32 cookie) +static struct rtable *tunnel_rtable_get(struct ip_tunnel *t, + u32 cookie, __be32 *saddr) { + struct ip_tunnel_dst *idst; struct dst_entry *dst; rcu_read_lock(); - dst = rcu_dereference(this_cpu_ptr(t->dst_cache)->dst); + idst = this_cpu_ptr(t->dst_cache); + dst = rcu_dereference(idst->dst); if (dst && !atomic_inc_not_zero(&dst->__refcnt)) dst = NULL; if (dst) { - if (dst->obsolete && dst->ops->check(dst, cookie) == NULL) { + if (!dst->obsolete || dst->ops->check(dst, cookie)) { + *saddr = idst->saddr; + } else { tunnel_dst_reset(t); dst_release(dst); dst = NULL; @@ -305,7 +312,7 @@ static struct net_device *__ip_tunnel_create(struct net *net, } ASSERT_RTNL(); - dev = alloc_netdev(ops->priv_size, name, ops->setup); + dev = alloc_netdev(ops->priv_size, name, NET_NAME_UNKNOWN, ops->setup); if (!dev) { err = -ENOMEM; goto failed; @@ -367,7 +374,7 @@ static int ip_tunnel_bind_dev(struct net_device *dev) if (!IS_ERR(rt)) { tdev = rt->dst.dev; - tunnel_dst_set(tunnel, &rt->dst); + tunnel_dst_set(tunnel, &rt->dst, fl4.saddr); ip_rt_put(rt); } if (dev->type != ARPHRD_ETHER) @@ -610,7 +617,7 @@ void ip_tunnel_xmit(struct sk_buff *skb, struct net_device *dev, init_tunnel_flow(&fl4, protocol, dst, tnl_params->saddr, tunnel->parms.o_key, RT_TOS(tos), tunnel->parms.link); - rt = connected ? tunnel_rtable_get(tunnel, 0) : NULL; + rt = connected ? tunnel_rtable_get(tunnel, 0, &fl4.saddr) : NULL; if (!rt) { rt = ip_route_output_key(tunnel->net, &fl4); @@ -620,7 +627,7 @@ void ip_tunnel_xmit(struct sk_buff *skb, struct net_device *dev, goto tx_error; } if (connected) - tunnel_dst_set(tunnel, &rt->dst); + tunnel_dst_set(tunnel, &rt->dst, fl4.saddr); } if (rt->dst.dev == dev) { diff --git a/net/ipv4/ip_vti.c b/net/ipv4/ip_vti.c index b8960f3527f3..e453cb724a95 100644 --- a/net/ipv4/ip_vti.c +++ b/net/ipv4/ip_vti.c @@ -534,40 +534,28 @@ static struct rtnl_link_ops vti_link_ops __read_mostly = { static int __init vti_init(void) { + const char *msg; int err; - pr_info("IPv4 over IPSec tunneling driver\n"); + pr_info("IPv4 over IPsec tunneling driver\n"); + msg = "tunnel device"; err = register_pernet_device(&vti_net_ops); if (err < 0) - return err; - err = xfrm4_protocol_register(&vti_esp4_protocol, IPPROTO_ESP); - if (err < 0) { - unregister_pernet_device(&vti_net_ops); - pr_info("vti init: can't register tunnel\n"); - - return err; - } + goto pernet_dev_failed; + msg = "tunnel protocols"; + err = xfrm4_protocol_register(&vti_esp4_protocol, IPPROTO_ESP); + if (err < 0) + goto xfrm_proto_esp_failed; err = xfrm4_protocol_register(&vti_ah4_protocol, IPPROTO_AH); - if (err < 0) { - xfrm4_protocol_deregister(&vti_esp4_protocol, IPPROTO_ESP); - unregister_pernet_device(&vti_net_ops); - pr_info("vti init: can't register tunnel\n"); - - return err; - } - + if (err < 0) + goto xfrm_proto_ah_failed; err = xfrm4_protocol_register(&vti_ipcomp4_protocol, IPPROTO_COMP); - if (err < 0) { - xfrm4_protocol_deregister(&vti_ah4_protocol, IPPROTO_AH); - xfrm4_protocol_deregister(&vti_esp4_protocol, IPPROTO_ESP); - unregister_pernet_device(&vti_net_ops); - pr_info("vti init: can't register tunnel\n"); - - return err; - } + if (err < 0) + goto xfrm_proto_comp_failed; + msg = "netlink interface"; err = rtnl_link_register(&vti_link_ops); if (err < 0) goto rtnl_link_failed; @@ -576,23 +564,23 @@ static int __init vti_init(void) rtnl_link_failed: xfrm4_protocol_deregister(&vti_ipcomp4_protocol, IPPROTO_COMP); +xfrm_proto_comp_failed: xfrm4_protocol_deregister(&vti_ah4_protocol, IPPROTO_AH); +xfrm_proto_ah_failed: xfrm4_protocol_deregister(&vti_esp4_protocol, IPPROTO_ESP); +xfrm_proto_esp_failed: unregister_pernet_device(&vti_net_ops); +pernet_dev_failed: + pr_err("vti init: failed to register %s\n", msg); return err; } static void __exit vti_fini(void) { rtnl_link_unregister(&vti_link_ops); - if (xfrm4_protocol_deregister(&vti_ipcomp4_protocol, IPPROTO_COMP)) - pr_info("vti close: can't deregister tunnel\n"); - if (xfrm4_protocol_deregister(&vti_ah4_protocol, IPPROTO_AH)) - pr_info("vti close: can't deregister tunnel\n"); - if (xfrm4_protocol_deregister(&vti_esp4_protocol, IPPROTO_ESP)) - pr_info("vti close: can't deregister tunnel\n"); - - + xfrm4_protocol_deregister(&vti_ipcomp4_protocol, IPPROTO_COMP); + xfrm4_protocol_deregister(&vti_ah4_protocol, IPPROTO_AH); + xfrm4_protocol_deregister(&vti_esp4_protocol, IPPROTO_ESP); unregister_pernet_device(&vti_net_ops); } diff --git a/net/ipv4/ipconfig.c b/net/ipv4/ipconfig.c index b3e86ea7b71b..5bbef4fdcb43 100644 --- a/net/ipv4/ipconfig.c +++ b/net/ipv4/ipconfig.c @@ -143,8 +143,6 @@ __be32 ic_servaddr = NONE; /* Boot server IP address */ __be32 root_server_addr = NONE; /* Address of NFS server */ u8 root_server_path[256] = { 0, }; /* Path to mount as root */ -__be32 ic_dev_xid; /* Device under configuration */ - /* vendor class identifier */ static char vendor_class_identifier[253] __initdata; @@ -654,6 +652,7 @@ static struct packet_type bootp_packet_type __initdata = { .func = ic_bootp_recv, }; +static __be32 ic_dev_xid; /* Device under configuration */ /* * Initialize DHCP/BOOTP extension fields in the request. @@ -1218,10 +1217,10 @@ static int __init ic_dynamic(void) get_random_bytes(&timeout, sizeof(timeout)); timeout = CONF_BASE_TIMEOUT + (timeout % (unsigned int) CONF_TIMEOUT_RANDOM); for (;;) { +#ifdef IPCONFIG_BOOTP /* Track the device we are configuring */ ic_dev_xid = d->xid; -#ifdef IPCONFIG_BOOTP if (do_bootp && (d->able & IC_BOOTP)) ic_bootp_send_if(d, jiffies - start_jiffies); #endif diff --git a/net/ipv4/ipmr.c b/net/ipv4/ipmr.c index 65bcaa789043..c8034587859d 100644 --- a/net/ipv4/ipmr.c +++ b/net/ipv4/ipmr.c @@ -500,7 +500,7 @@ static struct net_device *ipmr_reg_vif(struct net *net, struct mr_table *mrt) else sprintf(name, "pimreg%u", mrt->id); - dev = alloc_netdev(0, name, reg_vif_setup); + dev = alloc_netdev(0, name, NET_NAME_UNKNOWN, reg_vif_setup); if (dev == NULL) return NULL; diff --git a/net/ipv4/netfilter/Kconfig b/net/ipv4/netfilter/Kconfig index a26ce035e3fa..fb173126f03d 100644 --- a/net/ipv4/netfilter/Kconfig +++ b/net/ipv4/netfilter/Kconfig @@ -36,6 +36,16 @@ config NF_CONNTRACK_PROC_COMPAT If unsure, say Y. +config NF_LOG_ARP + tristate "ARP packet logging" + default m if NETFILTER_ADVANCED=n + select NF_LOG_COMMON + +config NF_LOG_IPV4 + tristate "IPv4 packet logging" + default m if NETFILTER_ADVANCED=n + select NF_LOG_COMMON + config NF_TABLES_IPV4 depends on NF_TABLES tristate "IPv4 nf_tables support" @@ -159,25 +169,6 @@ config IP_NF_TARGET_SYNPROXY To compile it as a module, choose M here. If unsure, say N. -config IP_NF_TARGET_ULOG - tristate "ULOG target support (obsolete)" - default m if NETFILTER_ADVANCED=n - ---help--- - - This option enables the old IPv4-only "ipt_ULOG" implementation - which has been obsoleted by the new "nfnetlink_log" code (see - CONFIG_NETFILTER_NETLINK_LOG). - - This option adds a `ULOG' target, which allows you to create rules in - any iptables table. The packet is passed to a userspace logging - daemon using netlink multicast sockets; unlike the LOG target - which can only be viewed through syslog. - - The appropriate userspace logging daemon (ulogd) may be obtained from - <http://www.netfilter.org/projects/ulogd/index.html> - - To compile it as a module, choose M here. If unsure, say N. - # NAT + specific targets: nf_conntrack config NF_NAT_IPV4 tristate "IPv4 NAT" diff --git a/net/ipv4/netfilter/Makefile b/net/ipv4/netfilter/Makefile index 90b82405331e..33001621465b 100644 --- a/net/ipv4/netfilter/Makefile +++ b/net/ipv4/netfilter/Makefile @@ -19,6 +19,10 @@ obj-$(CONFIG_NF_NAT_IPV4) += nf_nat_ipv4.o # defrag obj-$(CONFIG_NF_DEFRAG_IPV4) += nf_defrag_ipv4.o +# logging +obj-$(CONFIG_NF_LOG_ARP) += nf_log_arp.o +obj-$(CONFIG_NF_LOG_IPV4) += nf_log_ipv4.o + # NAT helpers (nf_conntrack) obj-$(CONFIG_NF_NAT_H323) += nf_nat_h323.o obj-$(CONFIG_NF_NAT_PPTP) += nf_nat_pptp.o @@ -53,7 +57,6 @@ obj-$(CONFIG_IP_NF_TARGET_ECN) += ipt_ECN.o obj-$(CONFIG_IP_NF_TARGET_MASQUERADE) += ipt_MASQUERADE.o obj-$(CONFIG_IP_NF_TARGET_REJECT) += ipt_REJECT.o obj-$(CONFIG_IP_NF_TARGET_SYNPROXY) += ipt_SYNPROXY.o -obj-$(CONFIG_IP_NF_TARGET_ULOG) += ipt_ULOG.o # generic ARP tables obj-$(CONFIG_IP_NF_ARPTABLES) += arp_tables.o diff --git a/net/ipv4/netfilter/ipt_ULOG.c b/net/ipv4/netfilter/ipt_ULOG.c deleted file mode 100644 index 9cb993cd224b..000000000000 --- a/net/ipv4/netfilter/ipt_ULOG.c +++ /dev/null @@ -1,498 +0,0 @@ -/* - * netfilter module for userspace packet logging daemons - * - * (C) 2000-2004 by Harald Welte <laforge@netfilter.org> - * (C) 1999-2001 Paul `Rusty' Russell - * (C) 2002-2004 Netfilter Core Team <coreteam@netfilter.org> - * (C) 2005-2007 Patrick McHardy <kaber@trash.net> - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License version 2 as - * published by the Free Software Foundation. - * - * This module accepts two parameters: - * - * nlbufsiz: - * The parameter specifies how big the buffer for each netlink multicast - * group is. e.g. If you say nlbufsiz=8192, up to eight kb of packets will - * get accumulated in the kernel until they are sent to userspace. It is - * NOT possible to allocate more than 128kB, and it is strongly discouraged, - * because atomically allocating 128kB inside the network rx softirq is not - * reliable. Please also keep in mind that this buffer size is allocated for - * each nlgroup you are using, so the total kernel memory usage increases - * by that factor. - * - * Actually you should use nlbufsiz a bit smaller than PAGE_SIZE, since - * nlbufsiz is used with alloc_skb, which adds another - * sizeof(struct skb_shared_info). Use NLMSG_GOODSIZE instead. - * - * flushtimeout: - * Specify, after how many hundredths of a second the queue should be - * flushed even if it is not full yet. - */ -#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt -#include <linux/module.h> -#include <linux/spinlock.h> -#include <linux/socket.h> -#include <linux/slab.h> -#include <linux/skbuff.h> -#include <linux/kernel.h> -#include <linux/timer.h> -#include <net/netlink.h> -#include <linux/netdevice.h> -#include <linux/mm.h> -#include <linux/moduleparam.h> -#include <linux/netfilter.h> -#include <linux/netfilter/x_tables.h> -#include <linux/netfilter_ipv4/ipt_ULOG.h> -#include <net/netfilter/nf_log.h> -#include <net/netns/generic.h> -#include <net/sock.h> -#include <linux/bitops.h> -#include <asm/unaligned.h> - -MODULE_LICENSE("GPL"); -MODULE_AUTHOR("Harald Welte <laforge@gnumonks.org>"); -MODULE_DESCRIPTION("Xtables: packet logging to netlink using ULOG"); -MODULE_ALIAS_NET_PF_PROTO(PF_NETLINK, NETLINK_NFLOG); - -#define ULOG_NL_EVENT 111 /* Harald's favorite number */ -#define ULOG_MAXNLGROUPS 32 /* numer of nlgroups */ - -static unsigned int nlbufsiz = NLMSG_GOODSIZE; -module_param(nlbufsiz, uint, 0400); -MODULE_PARM_DESC(nlbufsiz, "netlink buffer size"); - -static unsigned int flushtimeout = 10; -module_param(flushtimeout, uint, 0600); -MODULE_PARM_DESC(flushtimeout, "buffer flush timeout (hundredths of a second)"); - -static bool nflog = true; -module_param(nflog, bool, 0400); -MODULE_PARM_DESC(nflog, "register as internal netfilter logging module"); - -/* global data structures */ - -typedef struct { - unsigned int qlen; /* number of nlmsgs' in the skb */ - struct nlmsghdr *lastnlh; /* netlink header of last msg in skb */ - struct sk_buff *skb; /* the pre-allocated skb */ - struct timer_list timer; /* the timer function */ -} ulog_buff_t; - -static int ulog_net_id __read_mostly; -struct ulog_net { - unsigned int nlgroup[ULOG_MAXNLGROUPS]; - ulog_buff_t ulog_buffers[ULOG_MAXNLGROUPS]; - struct sock *nflognl; - spinlock_t lock; -}; - -static struct ulog_net *ulog_pernet(struct net *net) -{ - return net_generic(net, ulog_net_id); -} - -/* send one ulog_buff_t to userspace */ -static void ulog_send(struct ulog_net *ulog, unsigned int nlgroupnum) -{ - ulog_buff_t *ub = &ulog->ulog_buffers[nlgroupnum]; - - pr_debug("ulog_send: timer is deleting\n"); - del_timer(&ub->timer); - - if (!ub->skb) { - pr_debug("ulog_send: nothing to send\n"); - return; - } - - /* last nlmsg needs NLMSG_DONE */ - if (ub->qlen > 1) - ub->lastnlh->nlmsg_type = NLMSG_DONE; - - NETLINK_CB(ub->skb).dst_group = nlgroupnum + 1; - pr_debug("throwing %d packets to netlink group %u\n", - ub->qlen, nlgroupnum + 1); - netlink_broadcast(ulog->nflognl, ub->skb, 0, nlgroupnum + 1, - GFP_ATOMIC); - - ub->qlen = 0; - ub->skb = NULL; - ub->lastnlh = NULL; -} - - -/* timer function to flush queue in flushtimeout time */ -static void ulog_timer(unsigned long data) -{ - unsigned int groupnum = *((unsigned int *)data); - struct ulog_net *ulog = container_of((void *)data, - struct ulog_net, - nlgroup[groupnum]); - pr_debug("timer function called, calling ulog_send\n"); - - /* lock to protect against somebody modifying our structure - * from ipt_ulog_target at the same time */ - spin_lock_bh(&ulog->lock); - ulog_send(ulog, groupnum); - spin_unlock_bh(&ulog->lock); -} - -static struct sk_buff *ulog_alloc_skb(unsigned int size) -{ - struct sk_buff *skb; - unsigned int n; - - /* alloc skb which should be big enough for a whole - * multipart message. WARNING: has to be <= 131000 - * due to slab allocator restrictions */ - - n = max(size, nlbufsiz); - skb = alloc_skb(n, GFP_ATOMIC | __GFP_NOWARN); - if (!skb) { - if (n > size) { - /* try to allocate only as much as we need for - * current packet */ - - skb = alloc_skb(size, GFP_ATOMIC); - if (!skb) - pr_debug("cannot even allocate %ub\n", size); - } - } - - return skb; -} - -static void ipt_ulog_packet(struct net *net, - unsigned int hooknum, - const struct sk_buff *skb, - const struct net_device *in, - const struct net_device *out, - const struct ipt_ulog_info *loginfo, - const char *prefix) -{ - ulog_buff_t *ub; - ulog_packet_msg_t *pm; - size_t size, copy_len; - struct nlmsghdr *nlh; - struct timeval tv; - struct ulog_net *ulog = ulog_pernet(net); - - /* ffs == find first bit set, necessary because userspace - * is already shifting groupnumber, but we need unshifted. - * ffs() returns [1..32], we need [0..31] */ - unsigned int groupnum = ffs(loginfo->nl_group) - 1; - - /* calculate the size of the skb needed */ - if (loginfo->copy_range == 0 || loginfo->copy_range > skb->len) - copy_len = skb->len; - else - copy_len = loginfo->copy_range; - - size = nlmsg_total_size(sizeof(*pm) + copy_len); - - ub = &ulog->ulog_buffers[groupnum]; - - spin_lock_bh(&ulog->lock); - - if (!ub->skb) { - if (!(ub->skb = ulog_alloc_skb(size))) - goto alloc_failure; - } else if (ub->qlen >= loginfo->qthreshold || - size > skb_tailroom(ub->skb)) { - /* either the queue len is too high or we don't have - * enough room in nlskb left. send it to userspace. */ - - ulog_send(ulog, groupnum); - - if (!(ub->skb = ulog_alloc_skb(size))) - goto alloc_failure; - } - - pr_debug("qlen %d, qthreshold %Zu\n", ub->qlen, loginfo->qthreshold); - - nlh = nlmsg_put(ub->skb, 0, ub->qlen, ULOG_NL_EVENT, - sizeof(*pm)+copy_len, 0); - if (!nlh) { - pr_debug("error during nlmsg_put\n"); - goto out_unlock; - } - ub->qlen++; - - pm = nlmsg_data(nlh); - memset(pm, 0, sizeof(*pm)); - - /* We might not have a timestamp, get one */ - if (skb->tstamp.tv64 == 0) - __net_timestamp((struct sk_buff *)skb); - - /* copy hook, prefix, timestamp, payload, etc. */ - pm->data_len = copy_len; - tv = ktime_to_timeval(skb->tstamp); - put_unaligned(tv.tv_sec, &pm->timestamp_sec); - put_unaligned(tv.tv_usec, &pm->timestamp_usec); - put_unaligned(skb->mark, &pm->mark); - pm->hook = hooknum; - if (prefix != NULL) { - strncpy(pm->prefix, prefix, sizeof(pm->prefix) - 1); - pm->prefix[sizeof(pm->prefix) - 1] = '\0'; - } - else if (loginfo->prefix[0] != '\0') - strncpy(pm->prefix, loginfo->prefix, sizeof(pm->prefix)); - - if (in && in->hard_header_len > 0 && - skb->mac_header != skb->network_header && - in->hard_header_len <= ULOG_MAC_LEN) { - memcpy(pm->mac, skb_mac_header(skb), in->hard_header_len); - pm->mac_len = in->hard_header_len; - } else - pm->mac_len = 0; - - if (in) - strncpy(pm->indev_name, in->name, sizeof(pm->indev_name)); - - if (out) - strncpy(pm->outdev_name, out->name, sizeof(pm->outdev_name)); - - /* copy_len <= skb->len, so can't fail. */ - if (skb_copy_bits(skb, 0, pm->payload, copy_len) < 0) - BUG(); - - /* check if we are building multi-part messages */ - if (ub->qlen > 1) - ub->lastnlh->nlmsg_flags |= NLM_F_MULTI; - - ub->lastnlh = nlh; - - /* if timer isn't already running, start it */ - if (!timer_pending(&ub->timer)) { - ub->timer.expires = jiffies + flushtimeout * HZ / 100; - add_timer(&ub->timer); - } - - /* if threshold is reached, send message to userspace */ - if (ub->qlen >= loginfo->qthreshold) { - if (loginfo->qthreshold > 1) - nlh->nlmsg_type = NLMSG_DONE; - ulog_send(ulog, groupnum); - } -out_unlock: - spin_unlock_bh(&ulog->lock); - - return; - -alloc_failure: - pr_debug("Error building netlink message\n"); - spin_unlock_bh(&ulog->lock); -} - -static unsigned int -ulog_tg(struct sk_buff *skb, const struct xt_action_param *par) -{ - struct net *net = dev_net(par->in ? par->in : par->out); - - ipt_ulog_packet(net, par->hooknum, skb, par->in, par->out, - par->targinfo, NULL); - return XT_CONTINUE; -} - -static void ipt_logfn(struct net *net, - u_int8_t pf, - unsigned int hooknum, - const struct sk_buff *skb, - const struct net_device *in, - const struct net_device *out, - const struct nf_loginfo *li, - const char *prefix) -{ - struct ipt_ulog_info loginfo; - - if (!li || li->type != NF_LOG_TYPE_ULOG) { - loginfo.nl_group = ULOG_DEFAULT_NLGROUP; - loginfo.copy_range = 0; - loginfo.qthreshold = ULOG_DEFAULT_QTHRESHOLD; - loginfo.prefix[0] = '\0'; - } else { - loginfo.nl_group = li->u.ulog.group; - loginfo.copy_range = li->u.ulog.copy_len; - loginfo.qthreshold = li->u.ulog.qthreshold; - strlcpy(loginfo.prefix, prefix, sizeof(loginfo.prefix)); - } - - ipt_ulog_packet(net, hooknum, skb, in, out, &loginfo, prefix); -} - -static int ulog_tg_check(const struct xt_tgchk_param *par) -{ - const struct ipt_ulog_info *loginfo = par->targinfo; - - if (!par->net->xt.ulog_warn_deprecated) { - pr_info("ULOG is deprecated and it will be removed soon, " - "use NFLOG instead\n"); - par->net->xt.ulog_warn_deprecated = true; - } - - if (loginfo->prefix[sizeof(loginfo->prefix) - 1] != '\0') { - pr_debug("prefix not null-terminated\n"); - return -EINVAL; - } - if (loginfo->qthreshold > ULOG_MAX_QLEN) { - pr_debug("queue threshold %Zu > MAX_QLEN\n", - loginfo->qthreshold); - return -EINVAL; - } - return 0; -} - -#ifdef CONFIG_COMPAT -struct compat_ipt_ulog_info { - compat_uint_t nl_group; - compat_size_t copy_range; - compat_size_t qthreshold; - char prefix[ULOG_PREFIX_LEN]; -}; - -static void ulog_tg_compat_from_user(void *dst, const void *src) -{ - const struct compat_ipt_ulog_info *cl = src; - struct ipt_ulog_info l = { - .nl_group = cl->nl_group, - .copy_range = cl->copy_range, - .qthreshold = cl->qthreshold, - }; - - memcpy(l.prefix, cl->prefix, sizeof(l.prefix)); - memcpy(dst, &l, sizeof(l)); -} - -static int ulog_tg_compat_to_user(void __user *dst, const void *src) -{ - const struct ipt_ulog_info *l = src; - struct compat_ipt_ulog_info cl = { - .nl_group = l->nl_group, - .copy_range = l->copy_range, - .qthreshold = l->qthreshold, - }; - - memcpy(cl.prefix, l->prefix, sizeof(cl.prefix)); - return copy_to_user(dst, &cl, sizeof(cl)) ? -EFAULT : 0; -} -#endif /* CONFIG_COMPAT */ - -static struct xt_target ulog_tg_reg __read_mostly = { - .name = "ULOG", - .family = NFPROTO_IPV4, - .target = ulog_tg, - .targetsize = sizeof(struct ipt_ulog_info), - .checkentry = ulog_tg_check, -#ifdef CONFIG_COMPAT - .compatsize = sizeof(struct compat_ipt_ulog_info), - .compat_from_user = ulog_tg_compat_from_user, - .compat_to_user = ulog_tg_compat_to_user, -#endif - .me = THIS_MODULE, -}; - -static struct nf_logger ipt_ulog_logger __read_mostly = { - .name = "ipt_ULOG", - .logfn = ipt_logfn, - .me = THIS_MODULE, -}; - -static int __net_init ulog_tg_net_init(struct net *net) -{ - int i; - struct ulog_net *ulog = ulog_pernet(net); - struct netlink_kernel_cfg cfg = { - .groups = ULOG_MAXNLGROUPS, - }; - - spin_lock_init(&ulog->lock); - /* initialize ulog_buffers */ - for (i = 0; i < ULOG_MAXNLGROUPS; i++) { - ulog->nlgroup[i] = i; - setup_timer(&ulog->ulog_buffers[i].timer, ulog_timer, - (unsigned long)&ulog->nlgroup[i]); - } - - ulog->nflognl = netlink_kernel_create(net, NETLINK_NFLOG, &cfg); - if (!ulog->nflognl) - return -ENOMEM; - - if (nflog) - nf_log_set(net, NFPROTO_IPV4, &ipt_ulog_logger); - - return 0; -} - -static void __net_exit ulog_tg_net_exit(struct net *net) -{ - ulog_buff_t *ub; - int i; - struct ulog_net *ulog = ulog_pernet(net); - - if (nflog) - nf_log_unset(net, &ipt_ulog_logger); - - netlink_kernel_release(ulog->nflognl); - - /* remove pending timers and free allocated skb's */ - for (i = 0; i < ULOG_MAXNLGROUPS; i++) { - ub = &ulog->ulog_buffers[i]; - pr_debug("timer is deleting\n"); - del_timer(&ub->timer); - - if (ub->skb) { - kfree_skb(ub->skb); - ub->skb = NULL; - } - } -} - -static struct pernet_operations ulog_tg_net_ops = { - .init = ulog_tg_net_init, - .exit = ulog_tg_net_exit, - .id = &ulog_net_id, - .size = sizeof(struct ulog_net), -}; - -static int __init ulog_tg_init(void) -{ - int ret; - pr_debug("init module\n"); - - if (nlbufsiz > 128*1024) { - pr_warn("Netlink buffer has to be <= 128kB\n"); - return -EINVAL; - } - - ret = register_pernet_subsys(&ulog_tg_net_ops); - if (ret) - goto out_pernet; - - ret = xt_register_target(&ulog_tg_reg); - if (ret < 0) - goto out_target; - - if (nflog) - nf_log_register(NFPROTO_IPV4, &ipt_ulog_logger); - - return 0; - -out_target: - unregister_pernet_subsys(&ulog_tg_net_ops); -out_pernet: - return ret; -} - -static void __exit ulog_tg_exit(void) -{ - pr_debug("cleanup_module\n"); - if (nflog) - nf_log_unregister(&ipt_ulog_logger); - xt_unregister_target(&ulog_tg_reg); - unregister_pernet_subsys(&ulog_tg_net_ops); -} - -module_init(ulog_tg_init); -module_exit(ulog_tg_exit); diff --git a/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4.c b/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4.c index 8127dc802865..a054fe083431 100644 --- a/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4.c +++ b/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4.c @@ -314,7 +314,7 @@ getorigdst(struct sock *sk, int optval, void __user *user, int *len) return -ENOENT; } -#if defined(CONFIG_NF_CT_NETLINK) || defined(CONFIG_NF_CT_NETLINK_MODULE) +#if IS_ENABLED(CONFIG_NF_CT_NETLINK) #include <linux/netfilter/nfnetlink.h> #include <linux/netfilter/nfnetlink_conntrack.h> @@ -358,7 +358,7 @@ static struct nf_sockopt_ops so_getorigdst = { .pf = PF_INET, .get_optmin = SO_ORIGINAL_DST, .get_optmax = SO_ORIGINAL_DST+1, - .get = &getorigdst, + .get = getorigdst, .owner = THIS_MODULE, }; @@ -388,7 +388,7 @@ struct nf_conntrack_l3proto nf_conntrack_l3proto_ipv4 __read_mostly = { .invert_tuple = ipv4_invert_tuple, .print_tuple = ipv4_print_tuple, .get_l4proto = ipv4_get_l4proto, -#if defined(CONFIG_NF_CT_NETLINK) || defined(CONFIG_NF_CT_NETLINK_MODULE) +#if IS_ENABLED(CONFIG_NF_CT_NETLINK) .tuple_to_nlattr = ipv4_tuple_to_nlattr, .nlattr_tuple_size = ipv4_nlattr_tuple_size, .nlattr_to_tuple = ipv4_nlattr_to_tuple, diff --git a/net/ipv4/netfilter/nf_conntrack_proto_icmp.c b/net/ipv4/netfilter/nf_conntrack_proto_icmp.c index a338dad41b7d..b91b2641adda 100644 --- a/net/ipv4/netfilter/nf_conntrack_proto_icmp.c +++ b/net/ipv4/netfilter/nf_conntrack_proto_icmp.c @@ -226,7 +226,7 @@ icmp_error(struct net *net, struct nf_conn *tmpl, return icmp_error_message(net, tmpl, skb, ctinfo, hooknum); } -#if defined(CONFIG_NF_CT_NETLINK) || defined(CONFIG_NF_CT_NETLINK_MODULE) +#if IS_ENABLED(CONFIG_NF_CT_NETLINK) #include <linux/netfilter/nfnetlink.h> #include <linux/netfilter/nfnetlink_conntrack.h> @@ -408,7 +408,7 @@ struct nf_conntrack_l4proto nf_conntrack_l4proto_icmp __read_mostly = .error = icmp_error, .destroy = NULL, .me = NULL, -#if defined(CONFIG_NF_CT_NETLINK) || defined(CONFIG_NF_CT_NETLINK_MODULE) +#if IS_ENABLED(CONFIG_NF_CT_NETLINK) .tuple_to_nlattr = icmp_tuple_to_nlattr, .nlattr_tuple_size = icmp_nlattr_tuple_size, .nlattr_to_tuple = icmp_nlattr_to_tuple, diff --git a/net/ipv4/netfilter/nf_defrag_ipv4.c b/net/ipv4/netfilter/nf_defrag_ipv4.c index b8f6381c7d0b..76bd1aef257f 100644 --- a/net/ipv4/netfilter/nf_defrag_ipv4.c +++ b/net/ipv4/netfilter/nf_defrag_ipv4.c @@ -17,7 +17,7 @@ #include <linux/netfilter_bridge.h> #include <linux/netfilter_ipv4.h> #include <net/netfilter/ipv4/nf_defrag_ipv4.h> -#if defined(CONFIG_NF_CONNTRACK) || defined(CONFIG_NF_CONNTRACK_MODULE) +#if IS_ENABLED(CONFIG_NF_CONNTRACK) #include <net/netfilter/nf_conntrack.h> #endif #include <net/netfilter/nf_conntrack_zones.h> @@ -45,7 +45,7 @@ static enum ip_defrag_users nf_ct_defrag_user(unsigned int hooknum, { u16 zone = NF_CT_DEFAULT_ZONE; -#if defined(CONFIG_NF_CONNTRACK) || defined(CONFIG_NF_CONNTRACK_MODULE) +#if IS_ENABLED(CONFIG_NF_CONNTRACK) if (skb->nfct) zone = nf_ct_zone((struct nf_conn *)skb->nfct); #endif @@ -74,8 +74,8 @@ static unsigned int ipv4_conntrack_defrag(const struct nf_hook_ops *ops, inet->nodefrag) return NF_ACCEPT; -#if defined(CONFIG_NF_CONNTRACK) || defined(CONFIG_NF_CONNTRACK_MODULE) -#if !defined(CONFIG_NF_NAT) && !defined(CONFIG_NF_NAT_MODULE) +#if IS_ENABLED(CONFIG_NF_CONNTRACK) +#if !IS_ENABLED(CONFIG_NF_NAT) /* Previously seen (loopback)? Ignore. Do this before fragment check. */ if (skb->nfct && !nf_ct_is_template((struct nf_conn *)skb->nfct)) diff --git a/net/ipv4/netfilter/nf_log_arp.c b/net/ipv4/netfilter/nf_log_arp.c new file mode 100644 index 000000000000..ccfc78db12ee --- /dev/null +++ b/net/ipv4/netfilter/nf_log_arp.c @@ -0,0 +1,149 @@ +/* + * (C) 2014 by Pablo Neira Ayuso <pablo@netfilter.org> + * + * Based on code from ebt_log from: + * + * Bart De Schuymer <bdschuym@pandora.be> + * Harald Welte <laforge@netfilter.org> + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + */ + +#include <linux/module.h> +#include <linux/spinlock.h> +#include <linux/skbuff.h> +#include <linux/if_arp.h> +#include <linux/ip.h> +#include <net/route.h> + +#include <linux/netfilter.h> +#include <linux/netfilter/xt_LOG.h> +#include <net/netfilter/nf_log.h> + +static struct nf_loginfo default_loginfo = { + .type = NF_LOG_TYPE_LOG, + .u = { + .log = { + .level = 5, + .logflags = NF_LOG_MASK, + }, + }, +}; + +struct arppayload { + unsigned char mac_src[ETH_ALEN]; + unsigned char ip_src[4]; + unsigned char mac_dst[ETH_ALEN]; + unsigned char ip_dst[4]; +}; + +static void dump_arp_packet(struct nf_log_buf *m, + const struct nf_loginfo *info, + const struct sk_buff *skb, unsigned int nhoff) +{ + const struct arphdr *ah; + struct arphdr _arph; + const struct arppayload *ap; + struct arppayload _arpp; + + ah = skb_header_pointer(skb, 0, sizeof(_arph), &_arph); + if (ah == NULL) { + nf_log_buf_add(m, "TRUNCATED"); + return; + } + nf_log_buf_add(m, "ARP HTYPE=%d PTYPE=0x%04x OPCODE=%d", + ntohs(ah->ar_hrd), ntohs(ah->ar_pro), ntohs(ah->ar_op)); + + /* If it's for Ethernet and the lengths are OK, then log the ARP + * payload. + */ + if (ah->ar_hrd != htons(1) || + ah->ar_hln != ETH_ALEN || + ah->ar_pln != sizeof(__be32)) + return; + + ap = skb_header_pointer(skb, sizeof(_arph), sizeof(_arpp), &_arpp); + if (ap == NULL) { + nf_log_buf_add(m, " INCOMPLETE [%Zu bytes]", + skb->len - sizeof(_arph)); + return; + } + nf_log_buf_add(m, " MACSRC=%pM IPSRC=%pI4 MACDST=%pM IPDST=%pI4", + ap->mac_src, ap->ip_src, ap->mac_dst, ap->ip_dst); +} + +void nf_log_arp_packet(struct net *net, u_int8_t pf, + unsigned int hooknum, const struct sk_buff *skb, + const struct net_device *in, + const struct net_device *out, + const struct nf_loginfo *loginfo, + const char *prefix) +{ + struct nf_log_buf *m; + + /* FIXME: Disabled from containers until syslog ns is supported */ + if (!net_eq(net, &init_net)) + return; + + m = nf_log_buf_open(); + + if (!loginfo) + loginfo = &default_loginfo; + + nf_log_dump_packet_common(m, pf, hooknum, skb, in, out, loginfo, + prefix); + dump_arp_packet(m, loginfo, skb, 0); + + nf_log_buf_close(m); +} + +static struct nf_logger nf_arp_logger __read_mostly = { + .name = "nf_log_arp", + .type = NF_LOG_TYPE_LOG, + .logfn = nf_log_arp_packet, + .me = THIS_MODULE, +}; + +static int __net_init nf_log_arp_net_init(struct net *net) +{ + nf_log_set(net, NFPROTO_ARP, &nf_arp_logger); + return 0; +} + +static void __net_exit nf_log_arp_net_exit(struct net *net) +{ + nf_log_unset(net, &nf_arp_logger); +} + +static struct pernet_operations nf_log_arp_net_ops = { + .init = nf_log_arp_net_init, + .exit = nf_log_arp_net_exit, +}; + +static int __init nf_log_arp_init(void) +{ + int ret; + + ret = register_pernet_subsys(&nf_log_arp_net_ops); + if (ret < 0) + return ret; + + nf_log_register(NFPROTO_ARP, &nf_arp_logger); + return 0; +} + +static void __exit nf_log_arp_exit(void) +{ + unregister_pernet_subsys(&nf_log_arp_net_ops); + nf_log_unregister(&nf_arp_logger); +} + +module_init(nf_log_arp_init); +module_exit(nf_log_arp_exit); + +MODULE_AUTHOR("Pablo Neira Ayuso <pablo@netfilter.org>"); +MODULE_DESCRIPTION("Netfilter ARP packet logging"); +MODULE_LICENSE("GPL"); +MODULE_ALIAS_NF_LOGGER(3, 0); diff --git a/net/ipv4/netfilter/nf_log_ipv4.c b/net/ipv4/netfilter/nf_log_ipv4.c new file mode 100644 index 000000000000..078bdca1b607 --- /dev/null +++ b/net/ipv4/netfilter/nf_log_ipv4.c @@ -0,0 +1,385 @@ +/* (C) 1999-2001 Paul `Rusty' Russell + * (C) 2002-2004 Netfilter Core Team <coreteam@netfilter.org> + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + */ + +#include <linux/module.h> +#include <linux/spinlock.h> +#include <linux/skbuff.h> +#include <linux/if_arp.h> +#include <linux/ip.h> +#include <net/ipv6.h> +#include <net/icmp.h> +#include <net/udp.h> +#include <net/tcp.h> +#include <net/route.h> + +#include <linux/netfilter.h> +#include <linux/netfilter/xt_LOG.h> +#include <net/netfilter/nf_log.h> + +static struct nf_loginfo default_loginfo = { + .type = NF_LOG_TYPE_LOG, + .u = { + .log = { + .level = 5, + .logflags = NF_LOG_MASK, + }, + }, +}; + +/* One level of recursion won't kill us */ +static void dump_ipv4_packet(struct nf_log_buf *m, + const struct nf_loginfo *info, + const struct sk_buff *skb, unsigned int iphoff) +{ + struct iphdr _iph; + const struct iphdr *ih; + unsigned int logflags; + + if (info->type == NF_LOG_TYPE_LOG) + logflags = info->u.log.logflags; + else + logflags = NF_LOG_MASK; + + ih = skb_header_pointer(skb, iphoff, sizeof(_iph), &_iph); + if (ih == NULL) { + nf_log_buf_add(m, "TRUNCATED"); + return; + } + + /* Important fields: + * TOS, len, DF/MF, fragment offset, TTL, src, dst, options. */ + /* Max length: 40 "SRC=255.255.255.255 DST=255.255.255.255 " */ + nf_log_buf_add(m, "SRC=%pI4 DST=%pI4 ", &ih->saddr, &ih->daddr); + + /* Max length: 46 "LEN=65535 TOS=0xFF PREC=0xFF TTL=255 ID=65535 " */ + nf_log_buf_add(m, "LEN=%u TOS=0x%02X PREC=0x%02X TTL=%u ID=%u ", + ntohs(ih->tot_len), ih->tos & IPTOS_TOS_MASK, + ih->tos & IPTOS_PREC_MASK, ih->ttl, ntohs(ih->id)); + + /* Max length: 6 "CE DF MF " */ + if (ntohs(ih->frag_off) & IP_CE) + nf_log_buf_add(m, "CE "); + if (ntohs(ih->frag_off) & IP_DF) + nf_log_buf_add(m, "DF "); + if (ntohs(ih->frag_off) & IP_MF) + nf_log_buf_add(m, "MF "); + + /* Max length: 11 "FRAG:65535 " */ + if (ntohs(ih->frag_off) & IP_OFFSET) + nf_log_buf_add(m, "FRAG:%u ", ntohs(ih->frag_off) & IP_OFFSET); + + if ((logflags & XT_LOG_IPOPT) && + ih->ihl * 4 > sizeof(struct iphdr)) { + const unsigned char *op; + unsigned char _opt[4 * 15 - sizeof(struct iphdr)]; + unsigned int i, optsize; + + optsize = ih->ihl * 4 - sizeof(struct iphdr); + op = skb_header_pointer(skb, iphoff+sizeof(_iph), + optsize, _opt); + if (op == NULL) { + nf_log_buf_add(m, "TRUNCATED"); + return; + } + + /* Max length: 127 "OPT (" 15*4*2chars ") " */ + nf_log_buf_add(m, "OPT ("); + for (i = 0; i < optsize; i++) + nf_log_buf_add(m, "%02X", op[i]); + nf_log_buf_add(m, ") "); + } + + switch (ih->protocol) { + case IPPROTO_TCP: + if (nf_log_dump_tcp_header(m, skb, ih->protocol, + ntohs(ih->frag_off) & IP_OFFSET, + iphoff+ih->ihl*4, logflags)) + return; + break; + case IPPROTO_UDP: + case IPPROTO_UDPLITE: + if (nf_log_dump_udp_header(m, skb, ih->protocol, + ntohs(ih->frag_off) & IP_OFFSET, + iphoff+ih->ihl*4)) + return; + break; + case IPPROTO_ICMP: { + struct icmphdr _icmph; + const struct icmphdr *ich; + static const size_t required_len[NR_ICMP_TYPES+1] + = { [ICMP_ECHOREPLY] = 4, + [ICMP_DEST_UNREACH] + = 8 + sizeof(struct iphdr), + [ICMP_SOURCE_QUENCH] + = 8 + sizeof(struct iphdr), + [ICMP_REDIRECT] + = 8 + sizeof(struct iphdr), + [ICMP_ECHO] = 4, + [ICMP_TIME_EXCEEDED] + = 8 + sizeof(struct iphdr), + [ICMP_PARAMETERPROB] + = 8 + sizeof(struct iphdr), + [ICMP_TIMESTAMP] = 20, + [ICMP_TIMESTAMPREPLY] = 20, + [ICMP_ADDRESS] = 12, + [ICMP_ADDRESSREPLY] = 12 }; + + /* Max length: 11 "PROTO=ICMP " */ + nf_log_buf_add(m, "PROTO=ICMP "); + + if (ntohs(ih->frag_off) & IP_OFFSET) + break; + + /* Max length: 25 "INCOMPLETE [65535 bytes] " */ + ich = skb_header_pointer(skb, iphoff + ih->ihl * 4, + sizeof(_icmph), &_icmph); + if (ich == NULL) { + nf_log_buf_add(m, "INCOMPLETE [%u bytes] ", + skb->len - iphoff - ih->ihl*4); + break; + } + + /* Max length: 18 "TYPE=255 CODE=255 " */ + nf_log_buf_add(m, "TYPE=%u CODE=%u ", ich->type, ich->code); + + /* Max length: 25 "INCOMPLETE [65535 bytes] " */ + if (ich->type <= NR_ICMP_TYPES && + required_len[ich->type] && + skb->len-iphoff-ih->ihl*4 < required_len[ich->type]) { + nf_log_buf_add(m, "INCOMPLETE [%u bytes] ", + skb->len - iphoff - ih->ihl*4); + break; + } + + switch (ich->type) { + case ICMP_ECHOREPLY: + case ICMP_ECHO: + /* Max length: 19 "ID=65535 SEQ=65535 " */ + nf_log_buf_add(m, "ID=%u SEQ=%u ", + ntohs(ich->un.echo.id), + ntohs(ich->un.echo.sequence)); + break; + + case ICMP_PARAMETERPROB: + /* Max length: 14 "PARAMETER=255 " */ + nf_log_buf_add(m, "PARAMETER=%u ", + ntohl(ich->un.gateway) >> 24); + break; + case ICMP_REDIRECT: + /* Max length: 24 "GATEWAY=255.255.255.255 " */ + nf_log_buf_add(m, "GATEWAY=%pI4 ", &ich->un.gateway); + /* Fall through */ + case ICMP_DEST_UNREACH: + case ICMP_SOURCE_QUENCH: + case ICMP_TIME_EXCEEDED: + /* Max length: 3+maxlen */ + if (!iphoff) { /* Only recurse once. */ + nf_log_buf_add(m, "["); + dump_ipv4_packet(m, info, skb, + iphoff + ih->ihl*4+sizeof(_icmph)); + nf_log_buf_add(m, "] "); + } + + /* Max length: 10 "MTU=65535 " */ + if (ich->type == ICMP_DEST_UNREACH && + ich->code == ICMP_FRAG_NEEDED) { + nf_log_buf_add(m, "MTU=%u ", + ntohs(ich->un.frag.mtu)); + } + } + break; + } + /* Max Length */ + case IPPROTO_AH: { + struct ip_auth_hdr _ahdr; + const struct ip_auth_hdr *ah; + + if (ntohs(ih->frag_off) & IP_OFFSET) + break; + + /* Max length: 9 "PROTO=AH " */ + nf_log_buf_add(m, "PROTO=AH "); + + /* Max length: 25 "INCOMPLETE [65535 bytes] " */ + ah = skb_header_pointer(skb, iphoff+ih->ihl*4, + sizeof(_ahdr), &_ahdr); + if (ah == NULL) { + nf_log_buf_add(m, "INCOMPLETE [%u bytes] ", + skb->len - iphoff - ih->ihl*4); + break; + } + + /* Length: 15 "SPI=0xF1234567 " */ + nf_log_buf_add(m, "SPI=0x%x ", ntohl(ah->spi)); + break; + } + case IPPROTO_ESP: { + struct ip_esp_hdr _esph; + const struct ip_esp_hdr *eh; + + /* Max length: 10 "PROTO=ESP " */ + nf_log_buf_add(m, "PROTO=ESP "); + + if (ntohs(ih->frag_off) & IP_OFFSET) + break; + + /* Max length: 25 "INCOMPLETE [65535 bytes] " */ + eh = skb_header_pointer(skb, iphoff+ih->ihl*4, + sizeof(_esph), &_esph); + if (eh == NULL) { + nf_log_buf_add(m, "INCOMPLETE [%u bytes] ", + skb->len - iphoff - ih->ihl*4); + break; + } + + /* Length: 15 "SPI=0xF1234567 " */ + nf_log_buf_add(m, "SPI=0x%x ", ntohl(eh->spi)); + break; + } + /* Max length: 10 "PROTO 255 " */ + default: + nf_log_buf_add(m, "PROTO=%u ", ih->protocol); + } + + /* Max length: 15 "UID=4294967295 " */ + if ((logflags & XT_LOG_UID) && !iphoff) + nf_log_dump_sk_uid_gid(m, skb->sk); + + /* Max length: 16 "MARK=0xFFFFFFFF " */ + if (!iphoff && skb->mark) + nf_log_buf_add(m, "MARK=0x%x ", skb->mark); + + /* Proto Max log string length */ + /* IP: 40+46+6+11+127 = 230 */ + /* TCP: 10+max(25,20+30+13+9+32+11+127) = 252 */ + /* UDP: 10+max(25,20) = 35 */ + /* UDPLITE: 14+max(25,20) = 39 */ + /* ICMP: 11+max(25, 18+25+max(19,14,24+3+n+10,3+n+10)) = 91+n */ + /* ESP: 10+max(25)+15 = 50 */ + /* AH: 9+max(25)+15 = 49 */ + /* unknown: 10 */ + + /* (ICMP allows recursion one level deep) */ + /* maxlen = IP + ICMP + IP + max(TCP,UDP,ICMP,unknown) */ + /* maxlen = 230+ 91 + 230 + 252 = 803 */ +} + +static void dump_ipv4_mac_header(struct nf_log_buf *m, + const struct nf_loginfo *info, + const struct sk_buff *skb) +{ + struct net_device *dev = skb->dev; + unsigned int logflags = 0; + + if (info->type == NF_LOG_TYPE_LOG) + logflags = info->u.log.logflags; + + if (!(logflags & XT_LOG_MACDECODE)) + goto fallback; + + switch (dev->type) { + case ARPHRD_ETHER: + nf_log_buf_add(m, "MACSRC=%pM MACDST=%pM MACPROTO=%04x ", + eth_hdr(skb)->h_source, eth_hdr(skb)->h_dest, + ntohs(eth_hdr(skb)->h_proto)); + return; + default: + break; + } + +fallback: + nf_log_buf_add(m, "MAC="); + if (dev->hard_header_len && + skb->mac_header != skb->network_header) { + const unsigned char *p = skb_mac_header(skb); + unsigned int i; + + nf_log_buf_add(m, "%02x", *p++); + for (i = 1; i < dev->hard_header_len; i++, p++) + nf_log_buf_add(m, ":%02x", *p); + } + nf_log_buf_add(m, " "); +} + +static void nf_log_ip_packet(struct net *net, u_int8_t pf, + unsigned int hooknum, const struct sk_buff *skb, + const struct net_device *in, + const struct net_device *out, + const struct nf_loginfo *loginfo, + const char *prefix) +{ + struct nf_log_buf *m; + + /* FIXME: Disabled from containers until syslog ns is supported */ + if (!net_eq(net, &init_net)) + return; + + m = nf_log_buf_open(); + + if (!loginfo) + loginfo = &default_loginfo; + + nf_log_dump_packet_common(m, pf, hooknum, skb, in, + out, loginfo, prefix); + + if (in != NULL) + dump_ipv4_mac_header(m, loginfo, skb); + + dump_ipv4_packet(m, loginfo, skb, 0); + + nf_log_buf_close(m); +} + +static struct nf_logger nf_ip_logger __read_mostly = { + .name = "nf_log_ipv4", + .type = NF_LOG_TYPE_LOG, + .logfn = nf_log_ip_packet, + .me = THIS_MODULE, +}; + +static int __net_init nf_log_ipv4_net_init(struct net *net) +{ + nf_log_set(net, NFPROTO_IPV4, &nf_ip_logger); + return 0; +} + +static void __net_exit nf_log_ipv4_net_exit(struct net *net) +{ + nf_log_unset(net, &nf_ip_logger); +} + +static struct pernet_operations nf_log_ipv4_net_ops = { + .init = nf_log_ipv4_net_init, + .exit = nf_log_ipv4_net_exit, +}; + +static int __init nf_log_ipv4_init(void) +{ + int ret; + + ret = register_pernet_subsys(&nf_log_ipv4_net_ops); + if (ret < 0) + return ret; + + nf_log_register(NFPROTO_IPV4, &nf_ip_logger); + return 0; +} + +static void __exit nf_log_ipv4_exit(void) +{ + unregister_pernet_subsys(&nf_log_ipv4_net_ops); + nf_log_unregister(&nf_ip_logger); +} + +module_init(nf_log_ipv4_init); +module_exit(nf_log_ipv4_exit); + +MODULE_AUTHOR("Netfilter Core Team <coreteam@netfilter.org>"); +MODULE_DESCRIPTION("Netfilter IPv4 packet logging"); +MODULE_LICENSE("GPL"); +MODULE_ALIAS_NF_LOGGER(AF_INET, 0); diff --git a/net/ipv4/netfilter/nf_nat_l3proto_ipv4.c b/net/ipv4/netfilter/nf_nat_l3proto_ipv4.c index d8b2e14efddc..14f5ccd06337 100644 --- a/net/ipv4/netfilter/nf_nat_l3proto_ipv4.c +++ b/net/ipv4/netfilter/nf_nat_l3proto_ipv4.c @@ -154,6 +154,7 @@ static void nf_nat_ipv4_csum_recalc(struct sk_buff *skb, htons(oldlen), htons(datalen), 1); } +#if IS_ENABLED(CONFIG_NF_CT_NETLINK) static int nf_nat_ipv4_nlattr_to_range(struct nlattr *tb[], struct nf_nat_range *range) { @@ -169,6 +170,7 @@ static int nf_nat_ipv4_nlattr_to_range(struct nlattr *tb[], return 0; } +#endif static const struct nf_nat_l3proto nf_nat_l3proto_ipv4 = { .l3proto = NFPROTO_IPV4, @@ -177,7 +179,9 @@ static const struct nf_nat_l3proto nf_nat_l3proto_ipv4 = { .manip_pkt = nf_nat_ipv4_manip_pkt, .csum_update = nf_nat_ipv4_csum_update, .csum_recalc = nf_nat_ipv4_csum_recalc, +#if IS_ENABLED(CONFIG_NF_CT_NETLINK) .nlattr_to_range = nf_nat_ipv4_nlattr_to_range, +#endif #ifdef CONFIG_XFRM .decode_session = nf_nat_ipv4_decode_session, #endif diff --git a/net/ipv4/netfilter/nf_nat_proto_gre.c b/net/ipv4/netfilter/nf_nat_proto_gre.c index 690d890111bb..9414923f1e15 100644 --- a/net/ipv4/netfilter/nf_nat_proto_gre.c +++ b/net/ipv4/netfilter/nf_nat_proto_gre.c @@ -124,7 +124,7 @@ static const struct nf_nat_l4proto gre = { .manip_pkt = gre_manip_pkt, .in_range = nf_nat_l4proto_in_range, .unique_tuple = gre_unique_tuple, -#if defined(CONFIG_NF_CT_NETLINK) || defined(CONFIG_NF_CT_NETLINK_MODULE) +#if IS_ENABLED(CONFIG_NF_CT_NETLINK) .nlattr_to_range = nf_nat_l4proto_nlattr_to_range, #endif }; diff --git a/net/ipv4/netfilter/nf_nat_proto_icmp.c b/net/ipv4/netfilter/nf_nat_proto_icmp.c index eb303471bcf6..4557b4ab8342 100644 --- a/net/ipv4/netfilter/nf_nat_proto_icmp.c +++ b/net/ipv4/netfilter/nf_nat_proto_icmp.c @@ -77,7 +77,7 @@ const struct nf_nat_l4proto nf_nat_l4proto_icmp = { .manip_pkt = icmp_manip_pkt, .in_range = icmp_in_range, .unique_tuple = icmp_unique_tuple, -#if defined(CONFIG_NF_CT_NETLINK) || defined(CONFIG_NF_CT_NETLINK_MODULE) +#if IS_ENABLED(CONFIG_NF_CT_NETLINK) .nlattr_to_range = nf_nat_l4proto_nlattr_to_range, #endif }; diff --git a/net/ipv4/ping.c b/net/ipv4/ping.c index 044a0ddf6a79..a3c59a077a5f 100644 --- a/net/ipv4/ping.c +++ b/net/ipv4/ping.c @@ -911,7 +911,7 @@ int ping_recvmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg, sin6->sin6_flowinfo = ip6_flowinfo(ip6); sin6->sin6_scope_id = ipv6_iface_scope_id(&sin6->sin6_addr, - IP6CB(skb)->iif); + inet6_iif(skb)); *addr_len = sizeof(*sin6); } diff --git a/net/ipv4/proc.c b/net/ipv4/proc.c index ae0af9386f7c..8e3eb39f84e7 100644 --- a/net/ipv4/proc.c +++ b/net/ipv4/proc.c @@ -52,6 +52,7 @@ static int sockstat_seq_show(struct seq_file *seq, void *v) { struct net *net = seq->private; + unsigned int frag_mem; int orphans, sockets; local_bh_disable(); @@ -71,8 +72,8 @@ static int sockstat_seq_show(struct seq_file *seq, void *v) sock_prot_inuse_get(net, &udplite_prot)); seq_printf(seq, "RAW: inuse %d\n", sock_prot_inuse_get(net, &raw_prot)); - seq_printf(seq, "FRAG: inuse %d memory %d\n", - ip_frag_nqueues(net), ip_frag_mem(net)); + frag_mem = ip_frag_mem(net); + seq_printf(seq, "FRAG: inuse %u memory %u\n", !!frag_mem, frag_mem); return 0; } diff --git a/net/ipv4/raw.c b/net/ipv4/raw.c index 2c65160565e1..739db3100c23 100644 --- a/net/ipv4/raw.c +++ b/net/ipv4/raw.c @@ -58,6 +58,7 @@ #include <linux/in_route.h> #include <linux/route.h> #include <linux/skbuff.h> +#include <linux/igmp.h> #include <net/net_namespace.h> #include <net/dst.h> #include <net/sock.h> @@ -174,7 +175,9 @@ static int raw_v4_input(struct sk_buff *skb, const struct iphdr *iph, int hash) while (sk) { delivered = 1; - if (iph->protocol != IPPROTO_ICMP || !icmp_filter(sk, skb)) { + if ((iph->protocol != IPPROTO_ICMP || !icmp_filter(sk, skb)) && + ip_mc_sf_allow(sk, iph->daddr, iph->saddr, + skb->dev->ifindex)) { struct sk_buff *clone = skb_clone(skb, GFP_ATOMIC); /* Not releasing hash table! */ @@ -365,6 +368,8 @@ static int raw_send_hdrinc(struct sock *sk, struct flowi4 *fl4, skb->ip_summed = CHECKSUM_NONE; + sock_tx_timestamp(sk, &skb_shinfo(skb)->tx_flags); + skb->transport_header = skb->network_header; err = -EFAULT; if (memcpy_fromiovecend((void *)iph, from, 0, length)) @@ -606,6 +611,8 @@ back_from_confirm: &rt, msg->msg_flags); else { + sock_tx_timestamp(sk, &ipc.tx_flags); + if (!ipc.addr) ipc.addr = fl4.daddr; lock_sock(sk); diff --git a/net/ipv4/syncookies.c b/net/ipv4/syncookies.c index c86624b36a62..c0c75688896e 100644 --- a/net/ipv4/syncookies.c +++ b/net/ipv4/syncookies.c @@ -170,7 +170,8 @@ u32 __cookie_v4_init_sequence(const struct iphdr *iph, const struct tcphdr *th, } EXPORT_SYMBOL_GPL(__cookie_v4_init_sequence); -__u32 cookie_v4_init_sequence(struct sock *sk, struct sk_buff *skb, __u16 *mssp) +__u32 cookie_v4_init_sequence(struct sock *sk, const struct sk_buff *skb, + __u16 *mssp) { const struct iphdr *iph = ip_hdr(skb); const struct tcphdr *th = tcp_hdr(skb); diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index 9d2118e5fbc7..744af67a5989 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -426,6 +426,15 @@ void tcp_init_sock(struct sock *sk) } EXPORT_SYMBOL(tcp_init_sock); +void tcp_tx_timestamp(struct sock *sk, struct sk_buff *skb) +{ + struct skb_shared_info *shinfo = skb_shinfo(skb); + + sock_tx_timestamp(sk, &shinfo->tx_flags); + if (shinfo->tx_flags & SKBTX_ANY_SW_TSTAMP) + shinfo->tskey = TCP_SKB_CB(skb)->seq + skb->len - 1; +} + /* * Wait for a TCP event. * @@ -523,7 +532,7 @@ unsigned int tcp_poll(struct file *file, struct socket *sock, poll_table *wait) } /* This barrier is coupled with smp_wmb() in tcp_reset() */ smp_rmb(); - if (sk->sk_err) + if (sk->sk_err || !skb_queue_empty(&sk->sk_error_queue)) mask |= POLLERR; return mask; @@ -959,8 +968,10 @@ new_segment: copied += copy; offset += copy; - if (!(size -= copy)) + if (!(size -= copy)) { + tcp_tx_timestamp(sk, skb); goto out; + } if (skb->len < size_goal || (flags & MSG_OOB)) continue; @@ -1252,8 +1263,10 @@ new_segment: from += copy; copied += copy; - if ((seglen -= copy) == 0 && iovlen == 0) + if ((seglen -= copy) == 0 && iovlen == 0) { + tcp_tx_timestamp(sk, skb); goto out; + } if (skb->len < max || (flags & MSG_OOB) || unlikely(tp->repair)) continue; @@ -1617,6 +1630,9 @@ int tcp_recvmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg, struct sk_buff *skb; u32 urg_hole = 0; + if (unlikely(flags & MSG_ERRQUEUE)) + return ip_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)) sk_busy_loop(sk, nonblock); diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index 40639c288dc2..a3d47af01906 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -74,6 +74,7 @@ #include <linux/ipsec.h> #include <asm/unaligned.h> #include <net/netdma.h> +#include <linux/errqueue.h> int sysctl_tcp_timestamps __read_mostly = 1; int sysctl_tcp_window_scaling __read_mostly = 1; @@ -1904,16 +1905,17 @@ void tcp_clear_retrans(struct tcp_sock *tp) tp->sacked_out = 0; } -/* Enter Loss state. If "how" is not zero, forget all SACK information +/* Enter Loss state. If we detect SACK reneging, forget all SACK information * and reset tags completely, otherwise preserve SACKs. If receiver * dropped its ofo queue, we will know this due to reneging detection. */ -void tcp_enter_loss(struct sock *sk, int how) +void tcp_enter_loss(struct sock *sk) { const struct inet_connection_sock *icsk = inet_csk(sk); struct tcp_sock *tp = tcp_sk(sk); struct sk_buff *skb; bool new_recovery = false; + bool is_reneg; /* is receiver reneging on SACKs? */ /* Reduce ssthresh if it has not yet been made inside this window. */ if (icsk->icsk_ca_state <= TCP_CA_Disorder || @@ -1934,7 +1936,11 @@ void tcp_enter_loss(struct sock *sk, int how) tcp_reset_reno_sack(tp); tp->undo_marker = tp->snd_una; - if (how) { + + skb = tcp_write_queue_head(sk); + is_reneg = skb && (TCP_SKB_CB(skb)->sacked & TCPCB_SACKED_ACKED); + if (is_reneg) { + NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_TCPSACKRENEGING); tp->sacked_out = 0; tp->fackets_out = 0; } @@ -1948,7 +1954,7 @@ void tcp_enter_loss(struct sock *sk, int how) tp->undo_marker = 0; TCP_SKB_CB(skb)->sacked &= (~TCPCB_TAGBITS)|TCPCB_SACKED_ACKED; - if (!(TCP_SKB_CB(skb)->sacked&TCPCB_SACKED_ACKED) || how) { + if (!(TCP_SKB_CB(skb)->sacked&TCPCB_SACKED_ACKED) || is_reneg) { TCP_SKB_CB(skb)->sacked &= ~TCPCB_SACKED_ACKED; TCP_SKB_CB(skb)->sacked |= TCPCB_LOST; tp->lost_out += tcp_skb_pcount(skb); @@ -1981,19 +1987,21 @@ void tcp_enter_loss(struct sock *sk, int how) * remembered SACKs do not reflect real state of receiver i.e. * receiver _host_ is heavily congested (or buggy). * - * Do processing similar to RTO timeout. + * To avoid big spurious retransmission bursts due to transient SACK + * scoreboard oddities that look like reneging, we give the receiver a + * little time (max(RTT/2, 10ms)) to send us some more ACKs that will + * restore sanity to the SACK scoreboard. If the apparent reneging + * persists until this RTO then we'll clear the SACK scoreboard. */ static bool tcp_check_sack_reneging(struct sock *sk, int flag) { if (flag & FLAG_SACK_RENEGING) { - struct inet_connection_sock *icsk = inet_csk(sk); - NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_TCPSACKRENEGING); + struct tcp_sock *tp = tcp_sk(sk); + unsigned long delay = max(usecs_to_jiffies(tp->srtt_us >> 4), + msecs_to_jiffies(10)); - tcp_enter_loss(sk, 1); - icsk->icsk_retransmits++; - tcp_retransmit_skb(sk, tcp_write_queue_head(sk)); inet_csk_reset_xmit_timer(sk, ICSK_TIME_RETRANS, - icsk->icsk_rto, TCP_RTO_MAX); + delay, TCP_RTO_MAX); return true; } return false; @@ -2475,7 +2483,7 @@ static bool tcp_try_undo_loss(struct sock *sk, bool frto_undo) * losses and/or application stalls), do not perform any further cwnd * reductions, but instead slow start up to ssthresh. */ -static void tcp_init_cwnd_reduction(struct sock *sk, const bool set_ssthresh) +static void tcp_init_cwnd_reduction(struct sock *sk) { struct tcp_sock *tp = tcp_sk(sk); @@ -2485,8 +2493,7 @@ static void tcp_init_cwnd_reduction(struct sock *sk, const bool set_ssthresh) tp->prior_cwnd = tp->snd_cwnd; tp->prr_delivered = 0; tp->prr_out = 0; - if (set_ssthresh) - tp->snd_ssthresh = inet_csk(sk)->icsk_ca_ops->ssthresh(sk); + tp->snd_ssthresh = inet_csk(sk)->icsk_ca_ops->ssthresh(sk); TCP_ECN_queue_cwr(tp); } @@ -2528,14 +2535,14 @@ static inline void tcp_end_cwnd_reduction(struct sock *sk) } /* Enter CWR state. Disable cwnd undo since congestion is proven with ECN */ -void tcp_enter_cwr(struct sock *sk, const int set_ssthresh) +void tcp_enter_cwr(struct sock *sk) { struct tcp_sock *tp = tcp_sk(sk); tp->prior_ssthresh = 0; if (inet_csk(sk)->icsk_ca_state < TCP_CA_CWR) { tp->undo_marker = 0; - tcp_init_cwnd_reduction(sk, set_ssthresh); + tcp_init_cwnd_reduction(sk); tcp_set_ca_state(sk, TCP_CA_CWR); } } @@ -2564,7 +2571,7 @@ static void tcp_try_to_open(struct sock *sk, int flag, const int prior_unsacked) tp->retrans_stamp = 0; if (flag & FLAG_ECE) - tcp_enter_cwr(sk, 1); + tcp_enter_cwr(sk); if (inet_csk(sk)->icsk_ca_state != TCP_CA_CWR) { tcp_try_keep_open(sk); @@ -2670,7 +2677,7 @@ static void tcp_enter_recovery(struct sock *sk, bool ece_ack) if (inet_csk(sk)->icsk_ca_state < TCP_CA_CWR) { if (!ece_ack) tp->prior_ssthresh = tcp_current_ssthresh(sk); - tcp_init_cwnd_reduction(sk, true); + tcp_init_cwnd_reduction(sk); } tcp_set_ca_state(sk, TCP_CA_Recovery); } @@ -3100,6 +3107,11 @@ static int tcp_clean_rtx_queue(struct sock *sk, int prior_fackets, tp->retrans_stamp = 0; } + if (unlikely(skb_shinfo(skb)->tx_flags & SKBTX_ACK_TSTAMP) && + between(skb_shinfo(skb)->tskey, prior_snd_una, + tp->snd_una + 1)) + __skb_tstamp_tx(skb, NULL, sk, SCM_TSTAMP_ACK); + if (!fully_acked) break; @@ -3346,7 +3358,7 @@ static void tcp_process_tlp_ack(struct sock *sk, u32 ack, int flag) tp->tlp_high_seq = 0; /* Don't reduce cwnd if DSACK arrives for TLP retrans. */ if (!(flag & FLAG_DSACKING_ACK)) { - tcp_init_cwnd_reduction(sk, true); + tcp_init_cwnd_reduction(sk); tcp_set_ca_state(sk, TCP_CA_CWR); tcp_end_cwnd_reduction(sk); tcp_try_keep_open(sk); @@ -5877,3 +5889,153 @@ discard: return 0; } EXPORT_SYMBOL(tcp_rcv_state_process); + +static inline void pr_drop_req(struct request_sock *req, __u16 port, int family) +{ + struct inet_request_sock *ireq = inet_rsk(req); + + if (family == AF_INET) + LIMIT_NETDEBUG(KERN_DEBUG pr_fmt("drop open request from %pI4/%u\n"), + &ireq->ir_rmt_addr, port); +#if IS_ENABLED(CONFIG_IPV6) + else if (family == AF_INET6) + LIMIT_NETDEBUG(KERN_DEBUG pr_fmt("drop open request from %pI6/%u\n"), + &ireq->ir_v6_rmt_addr, port); +#endif +} + +int tcp_conn_request(struct request_sock_ops *rsk_ops, + const struct tcp_request_sock_ops *af_ops, + struct sock *sk, struct sk_buff *skb) +{ + struct tcp_options_received tmp_opt; + struct request_sock *req; + struct tcp_sock *tp = tcp_sk(sk); + struct dst_entry *dst = NULL; + __u32 isn = TCP_SKB_CB(skb)->when; + bool want_cookie = false, fastopen; + struct flowi fl; + struct tcp_fastopen_cookie foc = { .len = -1 }; + int err; + + + /* TW buckets are converted to open requests without + * limitations, they conserve resources and peer is + * evidently real one. + */ + if ((sysctl_tcp_syncookies == 2 || + inet_csk_reqsk_queue_is_full(sk)) && !isn) { + want_cookie = tcp_syn_flood_action(sk, skb, rsk_ops->slab_name); + if (!want_cookie) + goto drop; + } + + + /* Accept backlog is full. If we have already queued enough + * of warm entries in syn queue, drop request. It is better than + * clogging syn queue with openreqs with exponentially increasing + * timeout. + */ + if (sk_acceptq_is_full(sk) && inet_csk_reqsk_queue_young(sk) > 1) { + NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_LISTENOVERFLOWS); + goto drop; + } + + req = inet_reqsk_alloc(rsk_ops); + if (!req) + goto drop; + + tcp_rsk(req)->af_specific = af_ops; + + tcp_clear_options(&tmp_opt); + tmp_opt.mss_clamp = af_ops->mss_clamp; + tmp_opt.user_mss = tp->rx_opt.user_mss; + tcp_parse_options(skb, &tmp_opt, 0, want_cookie ? NULL : &foc); + + if (want_cookie && !tmp_opt.saw_tstamp) + tcp_clear_options(&tmp_opt); + + tmp_opt.tstamp_ok = tmp_opt.saw_tstamp; + tcp_openreq_init(req, &tmp_opt, skb, sk); + + af_ops->init_req(req, sk, skb); + + if (security_inet_conn_request(sk, skb, req)) + goto drop_and_free; + + if (!want_cookie || tmp_opt.tstamp_ok) + TCP_ECN_create_request(req, skb, sock_net(sk)); + + if (want_cookie) { + isn = cookie_init_sequence(af_ops, sk, skb, &req->mss); + req->cookie_ts = tmp_opt.tstamp_ok; + } else if (!isn) { + /* VJ's idea. We save last timestamp seen + * from the destination in peer table, when entering + * state TIME-WAIT, and check against it before + * accepting new connection request. + * + * If "isn" is not zero, this request hit alive + * timewait bucket, so that all the necessary checks + * are made in the function processing timewait state. + */ + if (tmp_opt.saw_tstamp && tcp_death_row.sysctl_tw_recycle) { + bool strict; + + dst = af_ops->route_req(sk, &fl, req, &strict); + if (dst && strict && + !tcp_peer_is_proven(req, dst, true)) { + NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_PAWSPASSIVEREJECTED); + goto drop_and_release; + } + } + /* Kill the following clause, if you dislike this way. */ + else if (!sysctl_tcp_syncookies && + (sysctl_max_syn_backlog - inet_csk_reqsk_queue_len(sk) < + (sysctl_max_syn_backlog >> 2)) && + !tcp_peer_is_proven(req, dst, false)) { + /* Without syncookies last quarter of + * backlog is filled with destinations, + * proven to be alive. + * It means that we continue to communicate + * to destinations, already remembered + * to the moment of synflood. + */ + pr_drop_req(req, ntohs(tcp_hdr(skb)->source), + rsk_ops->family); + goto drop_and_release; + } + + isn = af_ops->init_seq(skb); + } + if (!dst) { + dst = af_ops->route_req(sk, &fl, req, NULL); + if (!dst) + goto drop_and_free; + } + + tcp_rsk(req)->snt_isn = isn; + tcp_openreq_init_rwin(req, sk, dst); + fastopen = !want_cookie && + tcp_try_fastopen(sk, skb, req, &foc, dst); + err = af_ops->send_synack(sk, dst, &fl, req, + skb_get_queue_mapping(skb), &foc); + if (!fastopen) { + if (err || want_cookie) + goto drop_and_free; + + tcp_rsk(req)->listener = NULL; + af_ops->queue_hash_add(sk, req, TCP_TIMEOUT_INIT); + } + + return 0; + +drop_and_release: + dst_release(dst); +drop_and_free: + reqsk_free(req); +drop: + NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_LISTENDROPS); + return 0; +} +EXPORT_SYMBOL(tcp_conn_request); diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index 77cccda1ad0c..992a1f926009 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -99,7 +99,7 @@ static int tcp_v4_md5_hash_hdr(char *md5_hash, const struct tcp_md5sig_key *key, struct inet_hashinfo tcp_hashinfo; EXPORT_SYMBOL(tcp_hashinfo); -static inline __u32 tcp_v4_init_sequence(const struct sk_buff *skb) +static __u32 tcp_v4_init_sequence(const struct sk_buff *skb) { return secure_tcp_sequence_number(ip_hdr(skb)->daddr, ip_hdr(skb)->saddr, @@ -208,6 +208,8 @@ int tcp_v4_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len) inet->inet_dport = usin->sin_port; inet->inet_daddr = daddr; + inet_set_txhash(sk); + inet_csk(sk)->icsk_ext_hdr_len = 0; if (inet_opt) inet_csk(sk)->icsk_ext_hdr_len = inet_opt->opt.optlen; @@ -342,11 +344,6 @@ void tcp_v4_err(struct sk_buff *icmp_skb, u32 info) int err; struct net *net = dev_net(icmp_skb->dev); - if (icmp_skb->len < (iph->ihl << 2) + 8) { - ICMP_INC_STATS_BH(net, ICMP_MIB_INERRORS); - return; - } - sk = inet_lookup(net, &tcp_hashinfo, iph->daddr, th->dest, iph->saddr, th->source, inet_iif(icmp_skb)); if (!sk) { @@ -814,6 +811,7 @@ static void tcp_v4_reqsk_send_ack(struct sock *sk, struct sk_buff *skb, * socket. */ static int tcp_v4_send_synack(struct sock *sk, struct dst_entry *dst, + struct flowi *fl, struct request_sock *req, u16 queue_mapping, struct tcp_fastopen_cookie *foc) @@ -837,24 +835,11 @@ static int tcp_v4_send_synack(struct sock *sk, struct dst_entry *dst, ireq->ir_rmt_addr, ireq->opt); err = net_xmit_eval(err); - if (!tcp_rsk(req)->snt_synack && !err) - tcp_rsk(req)->snt_synack = tcp_time_stamp; } return err; } -static int tcp_v4_rtx_synack(struct sock *sk, struct request_sock *req) -{ - int res = tcp_v4_send_synack(sk, NULL, req, 0, NULL); - - if (!res) { - TCP_INC_STATS_BH(sock_net(sk), TCP_MIB_RETRANSSEGS); - NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_TCPSYNRETRANS); - } - return res; -} - /* * IPv4 request_sock destructor. */ @@ -1064,7 +1049,7 @@ static int tcp_v4_parse_md5_keys(struct sock *sk, char __user *optval, if (sin->sin_family != AF_INET) return -EINVAL; - if (!cmd.tcpm_key || !cmd.tcpm_keylen) + if (!cmd.tcpm_keylen) return tcp_md5_do_del(sk, (union tcp_md5_addr *)&sin->sin_addr.s_addr, AF_INET); @@ -1237,161 +1222,68 @@ static bool tcp_v4_inbound_md5_hash(struct sock *sk, const struct sk_buff *skb) #endif +static void tcp_v4_init_req(struct request_sock *req, struct sock *sk, + struct sk_buff *skb) +{ + struct inet_request_sock *ireq = inet_rsk(req); + + ireq->ir_loc_addr = ip_hdr(skb)->daddr; + ireq->ir_rmt_addr = ip_hdr(skb)->saddr; + ireq->no_srccheck = inet_sk(sk)->transparent; + ireq->opt = tcp_v4_save_options(skb); +} + +static struct dst_entry *tcp_v4_route_req(struct sock *sk, struct flowi *fl, + const struct request_sock *req, + bool *strict) +{ + struct dst_entry *dst = inet_csk_route_req(sk, &fl->u.ip4, req); + + if (strict) { + if (fl->u.ip4.daddr == inet_rsk(req)->ir_rmt_addr) + *strict = true; + else + *strict = false; + } + + return dst; +} + struct request_sock_ops tcp_request_sock_ops __read_mostly = { .family = PF_INET, .obj_size = sizeof(struct tcp_request_sock), - .rtx_syn_ack = tcp_v4_rtx_synack, + .rtx_syn_ack = tcp_rtx_synack, .send_ack = tcp_v4_reqsk_send_ack, .destructor = tcp_v4_reqsk_destructor, .send_reset = tcp_v4_send_reset, .syn_ack_timeout = tcp_syn_ack_timeout, }; -#ifdef CONFIG_TCP_MD5SIG static const struct tcp_request_sock_ops tcp_request_sock_ipv4_ops = { + .mss_clamp = TCP_MSS_DEFAULT, +#ifdef CONFIG_TCP_MD5SIG .md5_lookup = tcp_v4_reqsk_md5_lookup, .calc_md5_hash = tcp_v4_md5_hash_skb, -}; #endif + .init_req = tcp_v4_init_req, +#ifdef CONFIG_SYN_COOKIES + .cookie_init_seq = cookie_v4_init_sequence, +#endif + .route_req = tcp_v4_route_req, + .init_seq = tcp_v4_init_sequence, + .send_synack = tcp_v4_send_synack, + .queue_hash_add = inet_csk_reqsk_queue_hash_add, +}; int tcp_v4_conn_request(struct sock *sk, struct sk_buff *skb) { - struct tcp_options_received tmp_opt; - struct request_sock *req; - struct inet_request_sock *ireq; - struct tcp_sock *tp = tcp_sk(sk); - struct dst_entry *dst = NULL; - __be32 saddr = ip_hdr(skb)->saddr; - __be32 daddr = ip_hdr(skb)->daddr; - __u32 isn = TCP_SKB_CB(skb)->when; - bool want_cookie = false, fastopen; - struct flowi4 fl4; - struct tcp_fastopen_cookie foc = { .len = -1 }; - int err; - /* Never answer to SYNs send to broadcast or multicast */ if (skb_rtable(skb)->rt_flags & (RTCF_BROADCAST | RTCF_MULTICAST)) goto drop; - /* TW buckets are converted to open requests without - * limitations, they conserve resources and peer is - * evidently real one. - */ - if ((sysctl_tcp_syncookies == 2 || - inet_csk_reqsk_queue_is_full(sk)) && !isn) { - want_cookie = tcp_syn_flood_action(sk, skb, "TCP"); - if (!want_cookie) - goto drop; - } - - /* Accept backlog is full. If we have already queued enough - * of warm entries in syn queue, drop request. It is better than - * clogging syn queue with openreqs with exponentially increasing - * timeout. - */ - if (sk_acceptq_is_full(sk) && inet_csk_reqsk_queue_young(sk) > 1) { - NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_LISTENOVERFLOWS); - goto drop; - } - - req = inet_reqsk_alloc(&tcp_request_sock_ops); - if (!req) - goto drop; - -#ifdef CONFIG_TCP_MD5SIG - tcp_rsk(req)->af_specific = &tcp_request_sock_ipv4_ops; -#endif - - tcp_clear_options(&tmp_opt); - tmp_opt.mss_clamp = TCP_MSS_DEFAULT; - tmp_opt.user_mss = tp->rx_opt.user_mss; - tcp_parse_options(skb, &tmp_opt, 0, want_cookie ? NULL : &foc); - - if (want_cookie && !tmp_opt.saw_tstamp) - tcp_clear_options(&tmp_opt); - - tmp_opt.tstamp_ok = tmp_opt.saw_tstamp; - tcp_openreq_init(req, &tmp_opt, skb); - - ireq = inet_rsk(req); - ireq->ir_loc_addr = daddr; - ireq->ir_rmt_addr = saddr; - ireq->no_srccheck = inet_sk(sk)->transparent; - ireq->opt = tcp_v4_save_options(skb); - ireq->ir_mark = inet_request_mark(sk, skb); - - if (security_inet_conn_request(sk, skb, req)) - goto drop_and_free; - - if (!want_cookie || tmp_opt.tstamp_ok) - TCP_ECN_create_request(req, skb, sock_net(sk)); - - if (want_cookie) { - isn = cookie_v4_init_sequence(sk, skb, &req->mss); - req->cookie_ts = tmp_opt.tstamp_ok; - } else if (!isn) { - /* VJ's idea. We save last timestamp seen - * from the destination in peer table, when entering - * state TIME-WAIT, and check against it before - * accepting new connection request. - * - * If "isn" is not zero, this request hit alive - * timewait bucket, so that all the necessary checks - * are made in the function processing timewait state. - */ - if (tmp_opt.saw_tstamp && - tcp_death_row.sysctl_tw_recycle && - (dst = inet_csk_route_req(sk, &fl4, req)) != NULL && - fl4.daddr == saddr) { - if (!tcp_peer_is_proven(req, dst, true)) { - NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_PAWSPASSIVEREJECTED); - goto drop_and_release; - } - } - /* Kill the following clause, if you dislike this way. */ - else if (!sysctl_tcp_syncookies && - (sysctl_max_syn_backlog - inet_csk_reqsk_queue_len(sk) < - (sysctl_max_syn_backlog >> 2)) && - !tcp_peer_is_proven(req, dst, false)) { - /* Without syncookies last quarter of - * backlog is filled with destinations, - * proven to be alive. - * It means that we continue to communicate - * to destinations, already remembered - * to the moment of synflood. - */ - LIMIT_NETDEBUG(KERN_DEBUG pr_fmt("drop open request from %pI4/%u\n"), - &saddr, ntohs(tcp_hdr(skb)->source)); - goto drop_and_release; - } - - isn = tcp_v4_init_sequence(skb); - } - if (!dst && (dst = inet_csk_route_req(sk, &fl4, req)) == NULL) - goto drop_and_free; - - tcp_rsk(req)->snt_isn = isn; - tcp_rsk(req)->snt_synack = tcp_time_stamp; - tcp_openreq_init_rwin(req, sk, dst); - fastopen = !want_cookie && - tcp_try_fastopen(sk, skb, req, &foc, dst); - err = tcp_v4_send_synack(sk, dst, req, - skb_get_queue_mapping(skb), &foc); - if (!fastopen) { - if (err || want_cookie) - goto drop_and_free; - - tcp_rsk(req)->snt_synack = tcp_time_stamp; - tcp_rsk(req)->listener = NULL; - inet_csk_reqsk_queue_hash_add(sk, req, TCP_TIMEOUT_INIT); - } - - return 0; + return tcp_conn_request(&tcp_request_sock_ops, + &tcp_request_sock_ipv4_ops, sk, skb); -drop_and_release: - dst_release(dst); -drop_and_free: - reqsk_free(req); drop: NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_LISTENDROPS); return 0; @@ -1439,6 +1331,7 @@ struct sock *tcp_v4_syn_recv_sock(struct sock *sk, struct sk_buff *skb, newinet->mc_ttl = ip_hdr(skb)->ttl; newinet->rcv_tos = ip_hdr(skb)->tos; inet_csk(newsk)->icsk_ext_hdr_len = 0; + inet_set_txhash(newsk); if (inet_opt) inet_csk(newsk)->icsk_ext_hdr_len = inet_opt->opt.optlen; newinet->inet_id = newtp->write_seq ^ jiffies; diff --git a/net/ipv4/tcp_metrics.c b/net/ipv4/tcp_metrics.c index 4fe041805989..0d54e59b9ea8 100644 --- a/net/ipv4/tcp_metrics.c +++ b/net/ipv4/tcp_metrics.c @@ -1093,7 +1093,6 @@ static const struct genl_ops tcp_metrics_nl_ops[] = { .doit = tcp_metrics_nl_cmd_get, .dumpit = tcp_metrics_nl_dump, .policy = tcp_metrics_nl_policy, - .flags = GENL_ADMIN_PERM, }, { .cmd = TCP_METRICS_CMD_DEL, diff --git a/net/ipv4/tcp_minisocks.c b/net/ipv4/tcp_minisocks.c index e68e0d4af6c9..1649988bd1b6 100644 --- a/net/ipv4/tcp_minisocks.c +++ b/net/ipv4/tcp_minisocks.c @@ -298,7 +298,7 @@ void tcp_time_wait(struct sock *sk, int state, int timeo) tw->tw_v6_rcv_saddr = sk->sk_v6_rcv_saddr; tw->tw_tclass = np->tclass; tw->tw_flowlabel = np->flow_label >> 12; - tw->tw_ipv6only = np->ipv6only; + tw->tw_ipv6only = sk->sk_ipv6only; } #endif diff --git a/net/ipv4/tcp_offload.c b/net/ipv4/tcp_offload.c index 55046ecd083e..f597119fc4e7 100644 --- a/net/ipv4/tcp_offload.c +++ b/net/ipv4/tcp_offload.c @@ -14,6 +14,21 @@ #include <net/tcp.h> #include <net/protocol.h> +void tcp_gso_tstamp(struct sk_buff *skb, unsigned int ts_seq, unsigned int seq, + unsigned int mss) +{ + while (skb) { + if (ts_seq < (__u64) seq + mss) { + skb_shinfo(skb)->tx_flags = SKBTX_SW_TSTAMP; + skb_shinfo(skb)->tskey = ts_seq; + return; + } + + skb = skb->next; + seq += mss; + } +} + struct sk_buff *tcp_gso_segment(struct sk_buff *skb, netdev_features_t features) { @@ -91,6 +106,9 @@ struct sk_buff *tcp_gso_segment(struct sk_buff *skb, th = tcp_hdr(skb); seq = ntohl(th->seq); + if (unlikely(skb_shinfo(gso_skb)->tx_flags & SKBTX_SW_TSTAMP)) + tcp_gso_tstamp(segs, skb_shinfo(gso_skb)->tskey, seq, mss); + newcheck = ~csum_fold((__force __wsum)((__force u32)th->check + (__force u32)delta)); diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c index 179b51e6bda3..8fcfc91964ec 100644 --- a/net/ipv4/tcp_output.c +++ b/net/ipv4/tcp_output.c @@ -916,6 +916,7 @@ static int tcp_transmit_skb(struct sock *sk, struct sk_buff *skb, int clone_it, skb_orphan(skb); skb->sk = sk; skb->destructor = tcp_wfree; + skb_set_hash_from_sk(skb, sk); atomic_add(skb->truesize, &sk->sk_wmem_alloc); /* Build TCP header and checksum it. */ @@ -978,7 +979,7 @@ static int tcp_transmit_skb(struct sock *sk, struct sk_buff *skb, int clone_it, if (likely(err <= 0)) return err; - tcp_enter_cwr(sk, 1); + tcp_enter_cwr(sk); return net_xmit_eval(err); } @@ -3301,3 +3302,18 @@ void tcp_send_probe0(struct sock *sk) TCP_RTO_MAX); } } + +int tcp_rtx_synack(struct sock *sk, struct request_sock *req) +{ + const struct tcp_request_sock_ops *af_ops = tcp_rsk(req)->af_specific; + struct flowi fl; + int res; + + res = af_ops->send_synack(sk, NULL, &fl, req, 0, NULL); + if (!res) { + TCP_INC_STATS_BH(sock_net(sk), TCP_MIB_RETRANSSEGS); + NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_TCPSYNRETRANS); + } + return res; +} +EXPORT_SYMBOL(tcp_rtx_synack); diff --git a/net/ipv4/tcp_timer.c b/net/ipv4/tcp_timer.c index 286227abed10..df90cd1ce37f 100644 --- a/net/ipv4/tcp_timer.c +++ b/net/ipv4/tcp_timer.c @@ -391,7 +391,7 @@ void tcp_retransmit_timer(struct sock *sk) tcp_write_err(sk); goto out; } - tcp_enter_loss(sk, 0); + tcp_enter_loss(sk); tcp_retransmit_skb(sk, tcp_write_queue_head(sk)); __sk_dst_reset(sk); goto out_reset_timer; @@ -422,7 +422,7 @@ void tcp_retransmit_timer(struct sock *sk) NET_INC_STATS_BH(sock_net(sk), mib_idx); } - tcp_enter_loss(sk, 0); + tcp_enter_loss(sk); if (tcp_retransmit_skb(sk, tcp_write_queue_head(sk)) > 0) { /* Retransmission failed because of local congestion, diff --git a/net/ipv4/tcp_vegas.c b/net/ipv4/tcp_vegas.c index 9a5e05f27f4f..b40ad897f945 100644 --- a/net/ipv4/tcp_vegas.c +++ b/net/ipv4/tcp_vegas.c @@ -218,7 +218,8 @@ static void tcp_vegas_cong_avoid(struct sock *sk, u32 ack, u32 acked) * This is: * (actual rate in segments) * baseRTT */ - target_cwnd = tp->snd_cwnd * vegas->baseRTT / rtt; + target_cwnd = (u64)tp->snd_cwnd * vegas->baseRTT; + do_div(target_cwnd, rtt); /* Calculate the difference between the window we had, * and the window we would like to have. This quantity diff --git a/net/ipv4/tcp_veno.c b/net/ipv4/tcp_veno.c index 27b9825753d1..8276977d2c85 100644 --- a/net/ipv4/tcp_veno.c +++ b/net/ipv4/tcp_veno.c @@ -144,7 +144,7 @@ static void tcp_veno_cong_avoid(struct sock *sk, u32 ack, u32 acked) rtt = veno->minrtt; - target_cwnd = (tp->snd_cwnd * veno->basertt); + target_cwnd = (u64)tp->snd_cwnd * veno->basertt; target_cwnd <<= V_PARAM_SHIFT; do_div(target_cwnd, rtt); diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c index 7d5a8661df76..f57c0e4c2326 100644 --- a/net/ipv4/udp.c +++ b/net/ipv4/udp.c @@ -594,27 +594,6 @@ static inline bool __udp_is_mcast_sock(struct net *net, struct sock *sk, return true; } -static inline struct sock *udp_v4_mcast_next(struct net *net, struct sock *sk, - __be16 loc_port, __be32 loc_addr, - __be16 rmt_port, __be32 rmt_addr, - int dif) -{ - struct hlist_nulls_node *node; - struct sock *s = sk; - unsigned short hnum = ntohs(loc_port); - - sk_nulls_for_each_from(s, node) { - if (__udp_is_mcast_sock(net, s, - loc_port, loc_addr, - rmt_port, rmt_addr, - dif, hnum)) - goto found; - } - s = NULL; -found: - return s; -} - /* * This routine is called by the ICMP module when it gets some * sort of error condition. If err < 0 then the socket should @@ -1588,7 +1567,7 @@ int udp_queue_rcv_skb(struct sock *sk, struct sk_buff *skb) goto csum_error; - if (sk_rcvqueues_full(sk, skb, sk->sk_rcvbuf)) { + if (sk_rcvqueues_full(sk, sk->sk_rcvbuf)) { UDP_INC_STATS_BH(sock_net(sk), UDP_MIB_RCVBUFERRORS, is_udplite); goto drop; @@ -1640,6 +1619,8 @@ static void flush_stack(struct sock **stack, unsigned int count, if (skb1 && udp_queue_rcv_skb(sk, skb1) <= 0) skb1 = NULL; + + sock_put(sk); } if (unlikely(skb1)) kfree_skb(skb1); @@ -1668,41 +1649,50 @@ static int __udp4_lib_mcast_deliver(struct net *net, struct sk_buff *skb, struct udp_table *udptable) { struct sock *sk, *stack[256 / sizeof(struct sock *)]; - struct udp_hslot *hslot = udp_hashslot(udptable, net, ntohs(uh->dest)); - int dif; - unsigned int i, count = 0; + struct hlist_nulls_node *node; + unsigned short hnum = ntohs(uh->dest); + struct udp_hslot *hslot = udp_hashslot(udptable, net, hnum); + int dif = skb->dev->ifindex; + unsigned int count = 0, offset = offsetof(typeof(*sk), sk_nulls_node); + unsigned int hash2 = 0, hash2_any = 0, use_hash2 = (hslot->count > 10); + + if (use_hash2) { + hash2_any = udp4_portaddr_hash(net, htonl(INADDR_ANY), hnum) & + udp_table.mask; + hash2 = udp4_portaddr_hash(net, daddr, hnum) & udp_table.mask; +start_lookup: + hslot = &udp_table.hash2[hash2]; + offset = offsetof(typeof(*sk), __sk_common.skc_portaddr_node); + } spin_lock(&hslot->lock); - sk = sk_nulls_head(&hslot->head); - dif = skb->dev->ifindex; - sk = udp_v4_mcast_next(net, sk, uh->dest, daddr, uh->source, saddr, dif); - while (sk) { - stack[count++] = sk; - sk = udp_v4_mcast_next(net, sk_nulls_next(sk), uh->dest, - daddr, uh->source, saddr, dif); - if (unlikely(count == ARRAY_SIZE(stack))) { - if (!sk) - break; - flush_stack(stack, count, skb, ~0); - count = 0; + sk_nulls_for_each_entry_offset(sk, node, &hslot->head, offset) { + if (__udp_is_mcast_sock(net, sk, + uh->dest, daddr, + uh->source, saddr, + dif, hnum)) { + if (unlikely(count == ARRAY_SIZE(stack))) { + flush_stack(stack, count, skb, ~0); + count = 0; + } + stack[count++] = sk; + sock_hold(sk); } } - /* - * before releasing chain lock, we must take a reference on sockets - */ - for (i = 0; i < count; i++) - sock_hold(stack[i]); spin_unlock(&hslot->lock); + /* Also lookup *:port if we are using hash2 and haven't done so yet. */ + if (use_hash2 && hash2 != hash2_any) { + hash2 = hash2_any; + goto start_lookup; + } + /* * do the slow work with no lock held */ if (count) { flush_stack(stack, count, skb, count - 1); - - for (i = 0; i < count; i++) - sock_put(stack[i]); } else { kfree_skb(skb); } @@ -2526,79 +2516,3 @@ void __init udp_init(void) sysctl_udp_rmem_min = SK_MEM_QUANTUM; sysctl_udp_wmem_min = SK_MEM_QUANTUM; } - -struct sk_buff *skb_udp_tunnel_segment(struct sk_buff *skb, - netdev_features_t features) -{ - struct sk_buff *segs = ERR_PTR(-EINVAL); - u16 mac_offset = skb->mac_header; - int mac_len = skb->mac_len; - int tnl_hlen = skb_inner_mac_header(skb) - skb_transport_header(skb); - __be16 protocol = skb->protocol; - netdev_features_t enc_features; - int udp_offset, outer_hlen; - unsigned int oldlen; - bool need_csum; - - oldlen = (u16)~skb->len; - - if (unlikely(!pskb_may_pull(skb, tnl_hlen))) - goto out; - - skb->encapsulation = 0; - __skb_pull(skb, tnl_hlen); - skb_reset_mac_header(skb); - skb_set_network_header(skb, skb_inner_network_offset(skb)); - skb->mac_len = skb_inner_network_offset(skb); - skb->protocol = htons(ETH_P_TEB); - - need_csum = !!(skb_shinfo(skb)->gso_type & SKB_GSO_UDP_TUNNEL_CSUM); - if (need_csum) - skb->encap_hdr_csum = 1; - - /* segment inner packet. */ - enc_features = skb->dev->hw_enc_features & netif_skb_features(skb); - segs = skb_mac_gso_segment(skb, enc_features); - if (!segs || IS_ERR(segs)) { - skb_gso_error_unwind(skb, protocol, tnl_hlen, mac_offset, - mac_len); - goto out; - } - - outer_hlen = skb_tnl_header_len(skb); - udp_offset = outer_hlen - tnl_hlen; - skb = segs; - do { - struct udphdr *uh; - int len; - - skb_reset_inner_headers(skb); - skb->encapsulation = 1; - - skb->mac_len = mac_len; - - skb_push(skb, outer_hlen); - skb_reset_mac_header(skb); - skb_set_network_header(skb, mac_len); - skb_set_transport_header(skb, udp_offset); - len = skb->len - udp_offset; - uh = udp_hdr(skb); - uh->len = htons(len); - - if (need_csum) { - __be32 delta = htonl(oldlen + len); - - uh->check = ~csum_fold((__force __wsum) - ((__force u32)uh->check + - (__force u32)delta)); - uh->check = gso_make_checksum(skb, ~uh->check); - - if (uh->check == 0) - uh->check = CSUM_MANGLED_0; - } - - skb->protocol = protocol; - } while ((skb = skb->next)); -out: - return segs; -} diff --git a/net/ipv4/udp_offload.c b/net/ipv4/udp_offload.c index 546d2d439dda..59035bc3008d 100644 --- a/net/ipv4/udp_offload.c +++ b/net/ipv4/udp_offload.c @@ -47,6 +47,82 @@ static int udp4_ufo_send_check(struct sk_buff *skb) return 0; } +struct sk_buff *skb_udp_tunnel_segment(struct sk_buff *skb, + netdev_features_t features) +{ + struct sk_buff *segs = ERR_PTR(-EINVAL); + u16 mac_offset = skb->mac_header; + int mac_len = skb->mac_len; + int tnl_hlen = skb_inner_mac_header(skb) - skb_transport_header(skb); + __be16 protocol = skb->protocol; + netdev_features_t enc_features; + int udp_offset, outer_hlen; + unsigned int oldlen; + bool need_csum; + + oldlen = (u16)~skb->len; + + if (unlikely(!pskb_may_pull(skb, tnl_hlen))) + goto out; + + skb->encapsulation = 0; + __skb_pull(skb, tnl_hlen); + skb_reset_mac_header(skb); + skb_set_network_header(skb, skb_inner_network_offset(skb)); + skb->mac_len = skb_inner_network_offset(skb); + skb->protocol = htons(ETH_P_TEB); + + need_csum = !!(skb_shinfo(skb)->gso_type & SKB_GSO_UDP_TUNNEL_CSUM); + if (need_csum) + skb->encap_hdr_csum = 1; + + /* segment inner packet. */ + enc_features = skb->dev->hw_enc_features & netif_skb_features(skb); + segs = skb_mac_gso_segment(skb, enc_features); + if (IS_ERR_OR_NULL(segs)) { + skb_gso_error_unwind(skb, protocol, tnl_hlen, mac_offset, + mac_len); + goto out; + } + + outer_hlen = skb_tnl_header_len(skb); + udp_offset = outer_hlen - tnl_hlen; + skb = segs; + do { + struct udphdr *uh; + int len; + + skb_reset_inner_headers(skb); + skb->encapsulation = 1; + + skb->mac_len = mac_len; + + skb_push(skb, outer_hlen); + skb_reset_mac_header(skb); + skb_set_network_header(skb, mac_len); + skb_set_transport_header(skb, udp_offset); + len = skb->len - udp_offset; + uh = udp_hdr(skb); + uh->len = htons(len); + + if (need_csum) { + __be32 delta = htonl(oldlen + len); + + uh->check = ~csum_fold((__force __wsum) + ((__force u32)uh->check + + (__force u32)delta)); + uh->check = gso_make_checksum(skb, ~uh->check); + + if (uh->check == 0) + uh->check = CSUM_MANGLED_0; + } + + skb->protocol = protocol; + } while ((skb = skb->next)); +out: + return segs; +} + static struct sk_buff *udp4_ufo_fragment(struct sk_buff *skb, netdev_features_t features) { diff --git a/net/ipv4/udp_tunnel.c b/net/ipv4/udp_tunnel.c new file mode 100644 index 000000000000..61ec1a65207e --- /dev/null +++ b/net/ipv4/udp_tunnel.c @@ -0,0 +1,100 @@ +#include <linux/module.h> +#include <linux/errno.h> +#include <linux/socket.h> +#include <linux/udp.h> +#include <linux/types.h> +#include <linux/kernel.h> +#include <net/udp.h> +#include <net/udp_tunnel.h> +#include <net/net_namespace.h> + +int udp_sock_create(struct net *net, struct udp_port_cfg *cfg, + struct socket **sockp) +{ + int err = -EINVAL; + struct socket *sock = NULL; + +#if IS_ENABLED(CONFIG_IPV6) + if (cfg->family == AF_INET6) { + struct sockaddr_in6 udp6_addr; + + err = sock_create_kern(AF_INET6, SOCK_DGRAM, 0, &sock); + if (err < 0) + goto error; + + sk_change_net(sock->sk, net); + + udp6_addr.sin6_family = AF_INET6; + memcpy(&udp6_addr.sin6_addr, &cfg->local_ip6, + sizeof(udp6_addr.sin6_addr)); + udp6_addr.sin6_port = cfg->local_udp_port; + err = kernel_bind(sock, (struct sockaddr *)&udp6_addr, + sizeof(udp6_addr)); + if (err < 0) + goto error; + + if (cfg->peer_udp_port) { + udp6_addr.sin6_family = AF_INET6; + memcpy(&udp6_addr.sin6_addr, &cfg->peer_ip6, + sizeof(udp6_addr.sin6_addr)); + udp6_addr.sin6_port = cfg->peer_udp_port; + err = kernel_connect(sock, + (struct sockaddr *)&udp6_addr, + sizeof(udp6_addr), 0); + } + if (err < 0) + goto error; + + udp_set_no_check6_tx(sock->sk, !cfg->use_udp6_tx_checksums); + udp_set_no_check6_rx(sock->sk, !cfg->use_udp6_rx_checksums); + } else +#endif + if (cfg->family == AF_INET) { + struct sockaddr_in udp_addr; + + err = sock_create_kern(AF_INET, SOCK_DGRAM, 0, &sock); + if (err < 0) + goto error; + + sk_change_net(sock->sk, net); + + udp_addr.sin_family = AF_INET; + udp_addr.sin_addr = cfg->local_ip; + udp_addr.sin_port = cfg->local_udp_port; + err = kernel_bind(sock, (struct sockaddr *)&udp_addr, + sizeof(udp_addr)); + if (err < 0) + goto error; + + if (cfg->peer_udp_port) { + udp_addr.sin_family = AF_INET; + udp_addr.sin_addr = cfg->peer_ip; + udp_addr.sin_port = cfg->peer_udp_port; + err = kernel_connect(sock, + (struct sockaddr *)&udp_addr, + sizeof(udp_addr), 0); + if (err < 0) + goto error; + } + + sock->sk->sk_no_check_tx = !cfg->use_udp_checksums; + } else { + return -EPFNOSUPPORT; + } + + + *sockp = sock; + + return 0; + +error: + if (sock) { + kernel_sock_shutdown(sock, SHUT_RDWR); + sk_release_kernel(sock->sk); + } + *sockp = NULL; + return err; +} +EXPORT_SYMBOL(udp_sock_create); + +MODULE_LICENSE("GPL"); diff --git a/net/ipv4/xfrm4_protocol.c b/net/ipv4/xfrm4_protocol.c index a2ce0101eaac..dccefa9d84cf 100644 --- a/net/ipv4/xfrm4_protocol.c +++ b/net/ipv4/xfrm4_protocol.c @@ -124,7 +124,7 @@ static int xfrm4_ah_rcv(struct sk_buff *skb) for_each_protocol_rcu(ah4_handlers, handler) if ((ret = handler->handler(skb)) != -EINVAL) - return ret;; + return ret; icmp_send(skb, ICMP_DEST_UNREACH, ICMP_PORT_UNREACH, 0); diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c index 5667b3003af9..0b239fc1816e 100644 --- a/net/ipv6/addrconf.c +++ b/net/ipv6/addrconf.c @@ -108,11 +108,12 @@ static inline u32 cstamp_delta(unsigned long cstamp) } #ifdef CONFIG_SYSCTL -static void addrconf_sysctl_register(struct inet6_dev *idev); +static int addrconf_sysctl_register(struct inet6_dev *idev); static void addrconf_sysctl_unregister(struct inet6_dev *idev); #else -static inline void addrconf_sysctl_register(struct inet6_dev *idev) +static inline int addrconf_sysctl_register(struct inet6_dev *idev) { + return 0; } static inline void addrconf_sysctl_unregister(struct inet6_dev *idev) @@ -186,6 +187,7 @@ static struct ipv6_devconf ipv6_devconf __read_mostly = { .max_desync_factor = MAX_DESYNC_FACTOR, .max_addresses = IPV6_MAX_ADDRESSES, .accept_ra_defrtr = 1, + .accept_ra_from_local = 0, .accept_ra_pinfo = 1, #ifdef CONFIG_IPV6_ROUTER_PREF .accept_ra_rtr_pref = 1, @@ -222,6 +224,7 @@ static struct ipv6_devconf ipv6_devconf_dflt __read_mostly = { .max_desync_factor = MAX_DESYNC_FACTOR, .max_addresses = IPV6_MAX_ADDRESSES, .accept_ra_defrtr = 1, + .accept_ra_from_local = 0, .accept_ra_pinfo = 1, #ifdef CONFIG_IPV6_ROUTER_PREF .accept_ra_rtr_pref = 1, @@ -308,16 +311,16 @@ err_ip: static struct inet6_dev *ipv6_add_dev(struct net_device *dev) { struct inet6_dev *ndev; + int err = -ENOMEM; ASSERT_RTNL(); if (dev->mtu < IPV6_MIN_MTU) - return NULL; + return ERR_PTR(-EINVAL); ndev = kzalloc(sizeof(struct inet6_dev), GFP_KERNEL); - if (ndev == NULL) - return NULL; + return ERR_PTR(err); rwlock_init(&ndev->lock); ndev->dev = dev; @@ -330,7 +333,7 @@ static struct inet6_dev *ipv6_add_dev(struct net_device *dev) ndev->nd_parms = neigh_parms_alloc(dev, &nd_tbl); if (ndev->nd_parms == NULL) { kfree(ndev); - return NULL; + return ERR_PTR(err); } if (ndev->cnf.forwarding) dev_disable_lro(dev); @@ -344,17 +347,14 @@ static struct inet6_dev *ipv6_add_dev(struct net_device *dev) neigh_parms_release(&nd_tbl, ndev->nd_parms); dev_put(dev); kfree(ndev); - return NULL; + return ERR_PTR(err); } if (snmp6_register_dev(ndev) < 0) { ADBG(KERN_WARNING "%s: cannot create /proc/net/dev_snmp6/%s\n", __func__, dev->name); - neigh_parms_release(&nd_tbl, ndev->nd_parms); - ndev->dead = 1; - in6_dev_finish_destroy(ndev); - return NULL; + goto err_release; } /* One reference from device. We must do this before @@ -392,7 +392,12 @@ static struct inet6_dev *ipv6_add_dev(struct net_device *dev) ipv6_mc_init_dev(ndev); ndev->tstamp = jiffies; - addrconf_sysctl_register(ndev); + err = addrconf_sysctl_register(ndev); + if (err) { + ipv6_mc_destroy_dev(ndev); + del_timer(&ndev->regen_timer); + goto err_release; + } /* protected by rtnl_lock */ rcu_assign_pointer(dev->ip6_ptr, ndev); @@ -407,6 +412,12 @@ static struct inet6_dev *ipv6_add_dev(struct net_device *dev) ipv6_dev_mc_inc(dev, &in6addr_linklocal_allrouters); return ndev; + +err_release: + neigh_parms_release(&nd_tbl, ndev->nd_parms); + ndev->dead = 1; + in6_dev_finish_destroy(ndev); + return ERR_PTR(err); } static struct inet6_dev *ipv6_find_idev(struct net_device *dev) @@ -418,7 +429,7 @@ static struct inet6_dev *ipv6_find_idev(struct net_device *dev) idev = __in6_dev_get(dev); if (!idev) { idev = ipv6_add_dev(dev); - if (!idev) + if (IS_ERR(idev)) return NULL; } @@ -2728,9 +2739,25 @@ static void addrconf_add_linklocal(struct inet6_dev *idev, const struct in6_addr } } +static void addrconf_addr_gen(struct inet6_dev *idev, bool prefix_route) +{ + if (idev->addr_gen_mode == IN6_ADDR_GEN_MODE_EUI64) { + struct in6_addr addr; + + ipv6_addr_set(&addr, htonl(0xFE800000), 0, 0, 0); + /* addrconf_add_linklocal also adds a prefix_route and we + * only need to care about prefix routes if ipv6_generate_eui64 + * couldn't generate one. + */ + if (ipv6_generate_eui64(addr.s6_addr + 8, idev->dev) == 0) + addrconf_add_linklocal(idev, &addr); + else if (prefix_route) + addrconf_prefix_route(&addr, 64, idev->dev, 0, 0); + } +} + static void addrconf_dev_config(struct net_device *dev) { - struct in6_addr addr; struct inet6_dev *idev; ASSERT_RTNL(); @@ -2751,11 +2778,7 @@ static void addrconf_dev_config(struct net_device *dev) if (IS_ERR(idev)) return; - memset(&addr, 0, sizeof(struct in6_addr)); - addr.s6_addr32[0] = htonl(0xFE800000); - - if (ipv6_generate_eui64(addr.s6_addr + 8, dev) == 0) - addrconf_add_linklocal(idev, &addr); + addrconf_addr_gen(idev, false); } #if IS_ENABLED(CONFIG_IPV6_SIT) @@ -2777,11 +2800,7 @@ static void addrconf_sit_config(struct net_device *dev) } if (dev->priv_flags & IFF_ISATAP) { - struct in6_addr addr; - - ipv6_addr_set(&addr, htonl(0xFE800000), 0, 0, 0); - if (!ipv6_generate_eui64(addr.s6_addr + 8, dev)) - addrconf_add_linklocal(idev, &addr); + addrconf_addr_gen(idev, false); return; } @@ -2796,7 +2815,6 @@ static void addrconf_sit_config(struct net_device *dev) static void addrconf_gre_config(struct net_device *dev) { struct inet6_dev *idev; - struct in6_addr addr; ASSERT_RTNL(); @@ -2805,11 +2823,7 @@ static void addrconf_gre_config(struct net_device *dev) return; } - ipv6_addr_set(&addr, htonl(0xFE800000), 0, 0, 0); - if (!ipv6_generate_eui64(addr.s6_addr + 8, dev)) - addrconf_add_linklocal(idev, &addr); - else - addrconf_prefix_route(&addr, 64, dev, 0, 0); + addrconf_addr_gen(idev, true); } #endif @@ -2825,8 +2839,8 @@ static int addrconf_notify(struct notifier_block *this, unsigned long event, case NETDEV_REGISTER: if (!idev && dev->mtu >= IPV6_MIN_MTU) { idev = ipv6_add_dev(dev); - if (!idev) - return notifier_from_errno(-ENOMEM); + if (IS_ERR(idev)) + return notifier_from_errno(PTR_ERR(idev)); } break; @@ -2846,7 +2860,7 @@ static int addrconf_notify(struct notifier_block *this, unsigned long event, if (!idev && dev->mtu >= IPV6_MIN_MTU) idev = ipv6_add_dev(dev); - if (idev) { + if (!IS_ERR_OR_NULL(idev)) { idev->if_flags |= IF_READY; run_pending = 1; } @@ -2889,7 +2903,7 @@ static int addrconf_notify(struct notifier_block *this, unsigned long event, break; } - if (idev) { + if (!IS_ERR_OR_NULL(idev)) { if (run_pending) addrconf_dad_run(idev); @@ -2924,7 +2938,7 @@ static int addrconf_notify(struct notifier_block *this, unsigned long event, if (!idev && dev->mtu >= IPV6_MIN_MTU) { idev = ipv6_add_dev(dev); - if (idev) + if (!IS_ERR(idev)) break; } @@ -2945,10 +2959,14 @@ static int addrconf_notify(struct notifier_block *this, unsigned long event, if (idev) { snmp6_unregister_dev(idev); addrconf_sysctl_unregister(idev); - addrconf_sysctl_register(idev); - err = snmp6_register_dev(idev); + err = addrconf_sysctl_register(idev); if (err) return notifier_from_errno(err); + err = snmp6_register_dev(idev); + if (err) { + addrconf_sysctl_unregister(idev); + return notifier_from_errno(err); + } } break; @@ -4321,6 +4339,7 @@ static inline void ipv6_store_devconf(struct ipv6_devconf *cnf, array[DEVCONF_FORCE_TLLAO] = cnf->force_tllao; array[DEVCONF_NDISC_NOTIFY] = cnf->ndisc_notify; array[DEVCONF_SUPPRESS_FRAG_NDISC] = cnf->suppress_frag_ndisc; + array[DEVCONF_ACCEPT_RA_FROM_LOCAL] = cnf->accept_ra_from_local; } static inline size_t inet6_ifla6_size(void) @@ -4420,6 +4439,10 @@ static int inet6_fill_ifla6_attrs(struct sk_buff *skb, struct inet6_dev *idev) nla = nla_reserve(skb, IFLA_INET6_TOKEN, sizeof(struct in6_addr)); if (nla == NULL) goto nla_put_failure; + + if (nla_put_u8(skb, IFLA_INET6_ADDR_GEN_MODE, idev->addr_gen_mode)) + goto nla_put_failure; + read_lock_bh(&idev->lock); memcpy(nla_data(nla), idev->token.s6_addr, nla_len(nla)); read_unlock_bh(&idev->lock); @@ -4524,8 +4547,21 @@ static int inet6_set_link_af(struct net_device *dev, const struct nlattr *nla) if (nla_parse_nested(tb, IFLA_INET6_MAX, nla, NULL) < 0) BUG(); - if (tb[IFLA_INET6_TOKEN]) + if (tb[IFLA_INET6_TOKEN]) { err = inet6_set_iftoken(idev, nla_data(tb[IFLA_INET6_TOKEN])); + if (err) + return err; + } + + if (tb[IFLA_INET6_ADDR_GEN_MODE]) { + u8 mode = nla_get_u8(tb[IFLA_INET6_ADDR_GEN_MODE]); + + if (mode != IN6_ADDR_GEN_MODE_EUI64 && + mode != IN6_ADDR_GEN_MODE_NONE) + return -EINVAL; + idev->addr_gen_mode = mode; + err = 0; + } return err; } @@ -5168,6 +5204,13 @@ static struct addrconf_sysctl_table .proc_handler = proc_dointvec }, { + .procname = "accept_ra_from_local", + .data = &ipv6_devconf.accept_ra_from_local, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec, + }, + { /* sentinel */ } }, @@ -5218,12 +5261,23 @@ static void __addrconf_sysctl_unregister(struct ipv6_devconf *p) kfree(t); } -static void addrconf_sysctl_register(struct inet6_dev *idev) +static int addrconf_sysctl_register(struct inet6_dev *idev) { - neigh_sysctl_register(idev->dev, idev->nd_parms, - &ndisc_ifinfo_sysctl_change); - __addrconf_sysctl_register(dev_net(idev->dev), idev->dev->name, - idev, &idev->cnf); + int err; + + if (!sysctl_dev_name_is_allowed(idev->dev->name)) + return -EINVAL; + + err = neigh_sysctl_register(idev->dev, idev->nd_parms, + &ndisc_ifinfo_sysctl_change); + if (err) + return err; + err = __addrconf_sysctl_register(dev_net(idev->dev), idev->dev->name, + idev, &idev->cnf); + if (err) + neigh_sysctl_unregister(idev->nd_parms); + + return err; } static void addrconf_sysctl_unregister(struct inet6_dev *idev) @@ -5308,6 +5362,7 @@ static struct rtnl_af_ops inet6_ops = { int __init addrconf_init(void) { + struct inet6_dev *idev; int i, err; err = ipv6_addr_label_init(); @@ -5346,11 +5401,12 @@ int __init addrconf_init(void) * device and it being up should be removed. */ rtnl_lock(); - if (!ipv6_add_dev(init_net.loopback_dev)) - err = -ENOMEM; + idev = ipv6_add_dev(init_net.loopback_dev); rtnl_unlock(); - if (err) + if (IS_ERR(idev)) { + err = PTR_ERR(idev); goto errlo; + } for (i = 0; i < IN6_ADDR_HSIZE; i++) INIT_HLIST_HEAD(&inet6_addr_lst[i]); diff --git a/net/ipv6/af_inet6.c b/net/ipv6/af_inet6.c index 7cb4392690dd..2daa3a133e49 100644 --- a/net/ipv6/af_inet6.c +++ b/net/ipv6/af_inet6.c @@ -197,7 +197,7 @@ lookup_protocol: np->mcast_hops = IPV6_DEFAULT_MCASTHOPS; np->mc_loop = 1; np->pmtudisc = IPV6_PMTUDISC_WANT; - np->ipv6only = net->ipv6.sysctl.bindv6only; + sk->sk_ipv6only = net->ipv6.sysctl.bindv6only; /* Init the ipv4 part of the socket since we can have sockets * using v6 API for ipv4. @@ -294,7 +294,7 @@ int inet6_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len) /* Binding to v4-mapped address on a v6-only socket * makes no sense */ - if (np->ipv6only) { + if (sk->sk_ipv6only) { err = -EINVAL; goto out; } @@ -371,7 +371,7 @@ int inet6_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len) if (addr_type != IPV6_ADDR_ANY) { sk->sk_userlocks |= SOCK_BINDADDR_LOCK; if (addr_type != IPV6_ADDR_MAPPED) - np->ipv6only = 1; + sk->sk_ipv6only = 1; } if (snum) sk->sk_userlocks |= SOCK_BINDPORT_LOCK; @@ -765,6 +765,7 @@ static int __net_init inet6_net_init(struct net *net) net->ipv6.sysctl.bindv6only = 0; net->ipv6.sysctl.icmpv6_time = 1*HZ; net->ipv6.sysctl.flowlabel_consistency = 1; + net->ipv6.sysctl.auto_flowlabels = 0; atomic_set(&net->ipv6.rt_genid, 0); err = ipv6_init_mibs(net); diff --git a/net/ipv6/datagram.c b/net/ipv6/datagram.c index c3bf2d2e519e..2753319524f1 100644 --- a/net/ipv6/datagram.c +++ b/net/ipv6/datagram.c @@ -199,6 +199,7 @@ ipv4_connected: NULL); sk->sk_state = TCP_ESTABLISHED; + ip6_set_txhash(sk); out: fl6_sock_release(flowlabel); return err; diff --git a/net/ipv6/icmp.c b/net/ipv6/icmp.c index f6c84a6eb238..06ba3e58320b 100644 --- a/net/ipv6/icmp.c +++ b/net/ipv6/icmp.c @@ -626,9 +626,10 @@ void icmpv6_notify(struct sk_buff *skb, u8 type, u8 code, __be32 info) int inner_offset; __be16 frag_off; u8 nexthdr; + struct net *net = dev_net(skb->dev); if (!pskb_may_pull(skb, sizeof(struct ipv6hdr))) - return; + goto out; nexthdr = ((struct ipv6hdr *)skb->data)->nexthdr; if (ipv6_ext_hdr(nexthdr)) { @@ -636,14 +637,14 @@ void icmpv6_notify(struct sk_buff *skb, u8 type, u8 code, __be32 info) inner_offset = ipv6_skip_exthdr(skb, sizeof(struct ipv6hdr), &nexthdr, &frag_off); if (inner_offset<0) - return; + goto out; } else { inner_offset = sizeof(struct ipv6hdr); } /* Checkin header including 8 bytes of inner protocol header. */ if (!pskb_may_pull(skb, inner_offset+8)) - return; + goto out; /* BUGGG_FUTURE: we should try to parse exthdrs in this packet. Without this we will not able f.e. to make source routed @@ -652,13 +653,15 @@ void icmpv6_notify(struct sk_buff *skb, u8 type, u8 code, __be32 info) --ANK (980726) */ - rcu_read_lock(); ipprot = rcu_dereference(inet6_protos[nexthdr]); if (ipprot && ipprot->err_handler) ipprot->err_handler(skb, NULL, type, code, inner_offset, info); - rcu_read_unlock(); raw6_icmp_error(skb, nexthdr, type, code, inner_offset, info); + return; + +out: + ICMP6_INC_STATS_BH(net, __in6_dev_get(skb->dev), ICMP6_MIB_INERRORS); } /* diff --git a/net/ipv6/ip6_gre.c b/net/ipv6/ip6_gre.c index 3873181ed856..5f19dfbc4c6a 100644 --- a/net/ipv6/ip6_gre.c +++ b/net/ipv6/ip6_gre.c @@ -322,7 +322,8 @@ static struct ip6_tnl *ip6gre_tunnel_locate(struct net *net, else strcpy(name, "ip6gre%d"); - dev = alloc_netdev(sizeof(*t), name, ip6gre_tunnel_setup); + dev = alloc_netdev(sizeof(*t), name, NET_NAME_UNKNOWN, + ip6gre_tunnel_setup); if (!dev) return NULL; @@ -723,7 +724,8 @@ static netdev_tx_t ip6gre_xmit2(struct sk_buff *skb, * Push down and install the IP header. */ ipv6h = ipv6_hdr(skb); - ip6_flow_hdr(ipv6h, INET_ECN_encapsulate(0, dsfield), fl6->flowlabel); + ip6_flow_hdr(ipv6h, INET_ECN_encapsulate(0, dsfield), + ip6_make_flowlabel(net, skb, fl6->flowlabel, false)); ipv6h->hop_limit = tunnel->parms.hop_limit; ipv6h->nexthdr = proto; ipv6h->saddr = fl6->saddr; @@ -1174,7 +1176,9 @@ static int ip6gre_header(struct sk_buff *skb, struct net_device *dev, struct ipv6hdr *ipv6h = (struct ipv6hdr *)skb_push(skb, t->hlen); __be16 *p = (__be16 *)(ipv6h+1); - ip6_flow_hdr(ipv6h, 0, t->fl.u.ip6.flowlabel); + ip6_flow_hdr(ipv6h, 0, + ip6_make_flowlabel(dev_net(dev), skb, + t->fl.u.ip6.flowlabel, false)); ipv6h->hop_limit = t->parms.hop_limit; ipv6h->nexthdr = NEXTHDR_GRE; ipv6h->saddr = t->parms.laddr; @@ -1323,7 +1327,8 @@ static int __net_init ip6gre_init_net(struct net *net) int err; ign->fb_tunnel_dev = alloc_netdev(sizeof(struct ip6_tnl), "ip6gre0", - ip6gre_tunnel_setup); + NET_NAME_UNKNOWN, + ip6gre_tunnel_setup); if (!ign->fb_tunnel_dev) { err = -ENOMEM; goto err_alloc_dev; diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c index 45702b8cd141..315a55d66079 100644 --- a/net/ipv6/ip6_output.c +++ b/net/ipv6/ip6_output.c @@ -205,7 +205,8 @@ int ip6_xmit(struct sock *sk, struct sk_buff *skb, struct flowi6 *fl6, if (hlimit < 0) hlimit = ip6_dst_hoplimit(dst); - ip6_flow_hdr(hdr, tclass, fl6->flowlabel); + ip6_flow_hdr(hdr, tclass, ip6_make_flowlabel(net, skb, fl6->flowlabel, + np->autoflowlabel)); hdr->payload_len = htons(seg_len); hdr->nexthdr = proto; @@ -802,8 +803,8 @@ slow_path: /* * Copy a block of the IP datagram. */ - if (skb_copy_bits(skb, ptr, skb_transport_header(frag), len)) - BUG(); + BUG_ON(skb_copy_bits(skb, ptr, skb_transport_header(frag), + len)); left -= len; fh->frag_off = htons(offset); @@ -1156,6 +1157,7 @@ int ip6_append_data(struct sock *sk, int getfrag(void *from, char *to, int err; int offset = 0; __u8 tx_flags = 0; + u32 tskey = 0; if (flags&MSG_PROBE) return 0; @@ -1271,9 +1273,12 @@ emsgsize: } } - /* For UDP, check if TX timestamp is enabled */ - if (sk->sk_type == SOCK_DGRAM) + if (sk->sk_type == SOCK_DGRAM || sk->sk_type == SOCK_RAW) { sock_tx_timestamp(sk, &tx_flags); + if (tx_flags & SKBTX_ANY_SW_TSTAMP && + sk->sk_tsflags & SOF_TIMESTAMPING_OPT_ID) + tskey = sk->sk_tskey++; + } /* * Let's try using as much space as possible. @@ -1381,12 +1386,6 @@ alloc_new_skb: sk->sk_allocation); if (unlikely(skb == NULL)) err = -ENOBUFS; - else { - /* Only the initial fragment - * is time stamped. - */ - tx_flags = 0; - } } if (skb == NULL) goto error; @@ -1400,8 +1399,11 @@ alloc_new_skb: skb_reserve(skb, hh_len + sizeof(struct frag_hdr) + dst_exthdrlen); - if (sk->sk_type == SOCK_DGRAM) - skb_shinfo(skb)->tx_flags = tx_flags; + /* Only the initial fragment is time stamped */ + skb_shinfo(skb)->tx_flags = tx_flags; + tx_flags = 0; + skb_shinfo(skb)->tskey = tskey; + tskey = 0; /* * Find where to start putting bytes @@ -1571,7 +1573,9 @@ int ip6_push_pending_frames(struct sock *sk) skb_reset_network_header(skb); hdr = ipv6_hdr(skb); - ip6_flow_hdr(hdr, np->cork.tclass, fl6->flowlabel); + ip6_flow_hdr(hdr, np->cork.tclass, + ip6_make_flowlabel(net, skb, fl6->flowlabel, + np->autoflowlabel)); hdr->hop_limit = np->cork.hop_limit; hdr->nexthdr = proto; hdr->saddr = fl6->saddr; diff --git a/net/ipv6/ip6_tunnel.c b/net/ipv6/ip6_tunnel.c index afa082458360..f9de5a695072 100644 --- a/net/ipv6/ip6_tunnel.c +++ b/net/ipv6/ip6_tunnel.c @@ -315,7 +315,8 @@ static struct ip6_tnl *ip6_tnl_create(struct net *net, struct __ip6_tnl_parm *p) else sprintf(name, "ip6tnl%%d"); - dev = alloc_netdev(sizeof (*t), name, ip6_tnl_dev_setup); + dev = alloc_netdev(sizeof(*t), name, NET_NAME_UNKNOWN, + ip6_tnl_dev_setup); if (dev == NULL) goto failed; @@ -1046,7 +1047,8 @@ static int ip6_tnl_xmit2(struct sk_buff *skb, skb_push(skb, sizeof(struct ipv6hdr)); skb_reset_network_header(skb); ipv6h = ipv6_hdr(skb); - ip6_flow_hdr(ipv6h, INET_ECN_encapsulate(0, dsfield), fl6->flowlabel); + ip6_flow_hdr(ipv6h, INET_ECN_encapsulate(0, dsfield), + ip6_make_flowlabel(net, skb, fl6->flowlabel, false)); ipv6h->hop_limit = t->parms.hop_limit; ipv6h->nexthdr = proto; ipv6h->saddr = fl6->saddr; @@ -1772,7 +1774,7 @@ static int __net_init ip6_tnl_init_net(struct net *net) err = -ENOMEM; ip6n->fb_tnl_dev = alloc_netdev(sizeof(struct ip6_tnl), "ip6tnl0", - ip6_tnl_dev_setup); + NET_NAME_UNKNOWN, ip6_tnl_dev_setup); if (!ip6n->fb_tnl_dev) goto err_alloc_dev; diff --git a/net/ipv6/ip6_vti.c b/net/ipv6/ip6_vti.c index 9aaa6bb229e4..7f52fd9fa7b0 100644 --- a/net/ipv6/ip6_vti.c +++ b/net/ipv6/ip6_vti.c @@ -204,7 +204,7 @@ static struct ip6_tnl *vti6_tnl_create(struct net *net, struct __ip6_tnl_parm *p else sprintf(name, "ip6_vti%%d"); - dev = alloc_netdev(sizeof(*t), name, vti6_dev_setup); + dev = alloc_netdev(sizeof(*t), name, NET_NAME_UNKNOWN, vti6_dev_setup); if (dev == NULL) goto failed; @@ -1020,7 +1020,7 @@ static int __net_init vti6_init_net(struct net *net) err = -ENOMEM; ip6n->fb_tnl_dev = alloc_netdev(sizeof(struct ip6_tnl), "ip6_vti0", - vti6_dev_setup); + NET_NAME_UNKNOWN, vti6_dev_setup); if (!ip6n->fb_tnl_dev) goto err_alloc_dev; @@ -1089,36 +1089,26 @@ static struct xfrm6_protocol vti_ipcomp6_protocol __read_mostly = { **/ static int __init vti6_tunnel_init(void) { - int err; + const char *msg; + int err; + msg = "tunnel device"; err = register_pernet_device(&vti6_net_ops); if (err < 0) - goto out_pernet; + goto pernet_dev_failed; + msg = "tunnel protocols"; err = xfrm6_protocol_register(&vti_esp6_protocol, IPPROTO_ESP); - if (err < 0) { - pr_err("%s: can't register vti6 protocol\n", __func__); - - goto out; - } - + if (err < 0) + goto xfrm_proto_esp_failed; err = xfrm6_protocol_register(&vti_ah6_protocol, IPPROTO_AH); - if (err < 0) { - xfrm6_protocol_deregister(&vti_esp6_protocol, IPPROTO_ESP); - pr_err("%s: can't register vti6 protocol\n", __func__); - - goto out; - } - + if (err < 0) + goto xfrm_proto_ah_failed; err = xfrm6_protocol_register(&vti_ipcomp6_protocol, IPPROTO_COMP); - if (err < 0) { - xfrm6_protocol_deregister(&vti_ah6_protocol, IPPROTO_AH); - xfrm6_protocol_deregister(&vti_esp6_protocol, IPPROTO_ESP); - pr_err("%s: can't register vti6 protocol\n", __func__); - - goto out; - } + if (err < 0) + goto xfrm_proto_comp_failed; + msg = "netlink interface"; err = rtnl_link_register(&vti6_link_ops); if (err < 0) goto rtnl_link_failed; @@ -1127,11 +1117,14 @@ static int __init vti6_tunnel_init(void) rtnl_link_failed: xfrm6_protocol_deregister(&vti_ipcomp6_protocol, IPPROTO_COMP); +xfrm_proto_comp_failed: xfrm6_protocol_deregister(&vti_ah6_protocol, IPPROTO_AH); +xfrm_proto_ah_failed: xfrm6_protocol_deregister(&vti_esp6_protocol, IPPROTO_ESP); -out: +xfrm_proto_esp_failed: unregister_pernet_device(&vti6_net_ops); -out_pernet: +pernet_dev_failed: + pr_err("vti6 init: failed to register %s\n", msg); return err; } @@ -1141,13 +1134,9 @@ out_pernet: static void __exit vti6_tunnel_cleanup(void) { rtnl_link_unregister(&vti6_link_ops); - if (xfrm6_protocol_deregister(&vti_ipcomp6_protocol, IPPROTO_COMP)) - pr_info("%s: can't deregister protocol\n", __func__); - if (xfrm6_protocol_deregister(&vti_ah6_protocol, IPPROTO_AH)) - pr_info("%s: can't deregister protocol\n", __func__); - if (xfrm6_protocol_deregister(&vti_esp6_protocol, IPPROTO_ESP)) - pr_info("%s: can't deregister protocol\n", __func__); - + xfrm6_protocol_deregister(&vti_ipcomp6_protocol, IPPROTO_COMP); + xfrm6_protocol_deregister(&vti_ah6_protocol, IPPROTO_AH); + xfrm6_protocol_deregister(&vti_esp6_protocol, IPPROTO_ESP); unregister_pernet_device(&vti6_net_ops); } diff --git a/net/ipv6/ip6mr.c b/net/ipv6/ip6mr.c index 8250474ab7dc..f9a3fd320d1d 100644 --- a/net/ipv6/ip6mr.c +++ b/net/ipv6/ip6mr.c @@ -744,7 +744,7 @@ static struct net_device *ip6mr_reg_vif(struct net *net, struct mr6_table *mrt) else sprintf(name, "pim6reg%u", mrt->id); - dev = alloc_netdev(0, name, reg_vif_setup); + dev = alloc_netdev(0, name, NET_NAME_UNKNOWN, reg_vif_setup); if (dev == NULL) return NULL; diff --git a/net/ipv6/ipv6_sockglue.c b/net/ipv6/ipv6_sockglue.c index edb58aff4ae7..0c289982796d 100644 --- a/net/ipv6/ipv6_sockglue.c +++ b/net/ipv6/ipv6_sockglue.c @@ -235,7 +235,7 @@ static int do_ipv6_setsockopt(struct sock *sk, int level, int optname, if (optlen < sizeof(int) || inet_sk(sk)->inet_num) goto e_inval; - np->ipv6only = valbool; + sk->sk_ipv6only = valbool; retv = 0; break; @@ -834,6 +834,10 @@ pref_skip_coa: np->dontfrag = valbool; retv = 0; break; + case IPV6_AUTOFLOWLABEL: + np->autoflowlabel = valbool; + retv = 0; + break; } release_sock(sk); @@ -1058,7 +1062,7 @@ static int do_ipv6_getsockopt(struct sock *sk, int level, int optname, } case IPV6_V6ONLY: - val = np->ipv6only; + val = sk->sk_ipv6only; break; case IPV6_RECVPKTINFO: @@ -1158,7 +1162,6 @@ static int do_ipv6_getsockopt(struct sock *sk, int level, int optname, return -EFAULT; return 0; - break; } case IPV6_TRANSPARENT: @@ -1273,6 +1276,10 @@ static int do_ipv6_getsockopt(struct sock *sk, int level, int optname, val = np->dontfrag; break; + case IPV6_AUTOFLOWLABEL: + val = np->autoflowlabel; + break; + default: return -ENOPROTOOPT; } diff --git a/net/ipv6/ndisc.c b/net/ipv6/ndisc.c index ca8d4ea48a5d..339078f95d1b 100644 --- a/net/ipv6/ndisc.c +++ b/net/ipv6/ndisc.c @@ -1070,6 +1070,9 @@ static void ndisc_router_discovery(struct sk_buff *skb) optlen = (skb_tail_pointer(skb) - skb_transport_header(skb)) - sizeof(struct ra_msg); + ND_PRINTK(2, info, + "RA: %s, dev: %s\n", + __func__, skb->dev->name); if (!(ipv6_addr_type(&ipv6_hdr(skb)->saddr) & IPV6_ADDR_LINKLOCAL)) { ND_PRINTK(2, warn, "RA: source address is not link-local\n"); return; @@ -1102,13 +1105,21 @@ static void ndisc_router_discovery(struct sk_buff *skb) return; } - if (!ipv6_accept_ra(in6_dev)) + if (!ipv6_accept_ra(in6_dev)) { + ND_PRINTK(2, info, + "RA: %s, did not accept ra for dev: %s\n", + __func__, skb->dev->name); goto skip_linkparms; + } #ifdef CONFIG_IPV6_NDISC_NODETYPE /* skip link-specific parameters from interior routers */ - if (skb->ndisc_nodetype == NDISC_NODETYPE_NODEFAULT) + if (skb->ndisc_nodetype == NDISC_NODETYPE_NODEFAULT) { + ND_PRINTK(2, info, + "RA: %s, nodetype is NODEFAULT, dev: %s\n", + __func__, skb->dev->name); goto skip_linkparms; + } #endif if (in6_dev->if_flags & IF_RS_SENT) { @@ -1130,11 +1141,24 @@ static void ndisc_router_discovery(struct sk_buff *skb) (ra_msg->icmph.icmp6_addrconf_other ? IF_RA_OTHERCONF : 0); - if (!in6_dev->cnf.accept_ra_defrtr) + if (!in6_dev->cnf.accept_ra_defrtr) { + ND_PRINTK(2, info, + "RA: %s, defrtr is false for dev: %s\n", + __func__, skb->dev->name); goto skip_defrtr; + } - if (ipv6_chk_addr(dev_net(in6_dev->dev), &ipv6_hdr(skb)->saddr, NULL, 0)) + /* Do not accept RA with source-addr found on local machine unless + * accept_ra_from_local is set to true. + */ + if (!in6_dev->cnf.accept_ra_from_local && + ipv6_chk_addr(dev_net(in6_dev->dev), &ipv6_hdr(skb)->saddr, + NULL, 0)) { + ND_PRINTK(2, info, + "RA from local address detected on dev: %s: default router ignored\n", + skb->dev->name); goto skip_defrtr; + } lifetime = ntohs(ra_msg->icmph.icmp6_rt_lifetime); @@ -1163,8 +1187,10 @@ static void ndisc_router_discovery(struct sk_buff *skb) rt = NULL; } + ND_PRINTK(3, info, "RA: rt: %p lifetime: %d, for dev: %s\n", + rt, lifetime, skb->dev->name); if (rt == NULL && lifetime) { - ND_PRINTK(3, dbg, "RA: adding default router\n"); + ND_PRINTK(3, info, "RA: adding default router\n"); rt = rt6_add_dflt_router(&ipv6_hdr(skb)->saddr, skb->dev, pref); if (rt == NULL) { @@ -1260,12 +1286,22 @@ skip_linkparms: NEIGH_UPDATE_F_ISROUTER); } - if (!ipv6_accept_ra(in6_dev)) + if (!ipv6_accept_ra(in6_dev)) { + ND_PRINTK(2, info, + "RA: %s, accept_ra is false for dev: %s\n", + __func__, skb->dev->name); goto out; + } #ifdef CONFIG_IPV6_ROUTE_INFO - if (ipv6_chk_addr(dev_net(in6_dev->dev), &ipv6_hdr(skb)->saddr, NULL, 0)) + if (!in6_dev->cnf.accept_ra_from_local && + ipv6_chk_addr(dev_net(in6_dev->dev), &ipv6_hdr(skb)->saddr, + NULL, 0)) { + ND_PRINTK(2, info, + "RA from local address detected on dev: %s: router info ignored.\n", + skb->dev->name); goto skip_routeinfo; + } if (in6_dev->cnf.accept_ra_rtr_pref && ndopts.nd_opts_ri) { struct nd_opt_hdr *p; @@ -1293,8 +1329,12 @@ skip_routeinfo: #ifdef CONFIG_IPV6_NDISC_NODETYPE /* skip link-specific ndopts from interior routers */ - if (skb->ndisc_nodetype == NDISC_NODETYPE_NODEFAULT) + if (skb->ndisc_nodetype == NDISC_NODETYPE_NODEFAULT) { + ND_PRINTK(2, info, + "RA: %s, nodetype is NODEFAULT (interior routes), dev: %s\n", + __func__, skb->dev->name); goto out; + } #endif if (in6_dev->cnf.accept_ra_pinfo && ndopts.nd_opts_pi) { @@ -1728,7 +1768,7 @@ int __init ndisc_init(void) #ifdef CONFIG_SYSCTL err = neigh_sysctl_register(NULL, &nd_tbl.parms, - &ndisc_ifinfo_sysctl_change); + ndisc_ifinfo_sysctl_change); if (err) goto out_unregister_pernet; out: diff --git a/net/ipv6/netfilter/Kconfig b/net/ipv6/netfilter/Kconfig index 4bff1f297e39..ac93df16f5af 100644 --- a/net/ipv6/netfilter/Kconfig +++ b/net/ipv6/netfilter/Kconfig @@ -55,6 +55,11 @@ config NFT_REJECT_IPV6 default NFT_REJECT tristate +config NF_LOG_IPV6 + tristate "IPv6 packet logging" + depends on NETFILTER_ADVANCED + select NF_LOG_COMMON + config IP6_NF_IPTABLES tristate "IP6 tables support (required for filtering)" depends on INET && IPV6 diff --git a/net/ipv6/netfilter/Makefile b/net/ipv6/netfilter/Makefile index 70d3dd66f2cd..c0b263104ed2 100644 --- a/net/ipv6/netfilter/Makefile +++ b/net/ipv6/netfilter/Makefile @@ -23,6 +23,9 @@ obj-$(CONFIG_NF_NAT_IPV6) += nf_nat_ipv6.o nf_defrag_ipv6-y := nf_defrag_ipv6_hooks.o nf_conntrack_reasm.o obj-$(CONFIG_NF_DEFRAG_IPV6) += nf_defrag_ipv6.o +# logging +obj-$(CONFIG_NF_LOG_IPV6) += nf_log_ipv6.o + # nf_tables obj-$(CONFIG_NF_TABLES_IPV6) += nf_tables_ipv6.o obj-$(CONFIG_NFT_CHAIN_ROUTE_IPV6) += nft_chain_route_ipv6.o diff --git a/net/ipv6/netfilter/ip6t_ipv6header.c b/net/ipv6/netfilter/ip6t_ipv6header.c index 54bd9790603f..8b147440fbdc 100644 --- a/net/ipv6/netfilter/ip6t_ipv6header.c +++ b/net/ipv6/netfilter/ip6t_ipv6header.c @@ -94,7 +94,6 @@ ipv6header_mt6(const struct sk_buff *skb, struct xt_action_param *par) break; default: return false; - break; } nexthdr = hp->nexthdr; diff --git a/net/ipv6/netfilter/nf_conntrack_reasm.c b/net/ipv6/netfilter/nf_conntrack_reasm.c index 0d5279fd852a..6f187c8d8a1b 100644 --- a/net/ipv6/netfilter/nf_conntrack_reasm.c +++ b/net/ipv6/netfilter/nf_conntrack_reasm.c @@ -50,6 +50,7 @@ #include <linux/module.h> #include <net/netfilter/ipv6/nf_defrag_ipv6.h> +static const char nf_frags_cache_name[] = "nf-frags"; struct nf_ct_frag6_skb_cb { @@ -63,6 +64,8 @@ struct nf_ct_frag6_skb_cb static struct inet_frags nf_frags; #ifdef CONFIG_SYSCTL +static int zero; + static struct ctl_table nf_ct_frag6_sysctl_table[] = { { .procname = "nf_conntrack_frag6_timeout", @@ -76,14 +79,17 @@ static struct ctl_table nf_ct_frag6_sysctl_table[] = { .data = &init_net.nf_frag.frags.low_thresh, .maxlen = sizeof(unsigned int), .mode = 0644, - .proc_handler = proc_dointvec, + .proc_handler = proc_dointvec_minmax, + .extra1 = &zero, + .extra2 = &init_net.nf_frag.frags.high_thresh }, { .procname = "nf_conntrack_frag6_high_thresh", .data = &init_net.nf_frag.frags.high_thresh, .maxlen = sizeof(unsigned int), .mode = 0644, - .proc_handler = proc_dointvec, + .proc_handler = proc_dointvec_minmax, + .extra1 = &init_net.nf_frag.frags.low_thresh }, { } }; @@ -102,7 +108,10 @@ static int nf_ct_frag6_sysctl_register(struct net *net) table[0].data = &net->nf_frag.frags.timeout; table[1].data = &net->nf_frag.frags.low_thresh; + table[1].extra2 = &net->nf_frag.frags.high_thresh; table[2].data = &net->nf_frag.frags.high_thresh; + table[2].extra1 = &net->nf_frag.frags.low_thresh; + table[2].extra2 = &init_net.nf_frag.frags.high_thresh; } hdr = register_net_sysctl(net, "net/netfilter", table); @@ -147,16 +156,13 @@ static inline u8 ip6_frag_ecn(const struct ipv6hdr *ipv6h) static unsigned int nf_hash_frag(__be32 id, const struct in6_addr *saddr, const struct in6_addr *daddr) { - u32 c; - net_get_random_once(&nf_frags.rnd, sizeof(nf_frags.rnd)); - c = jhash_3words(ipv6_addr_hash(saddr), ipv6_addr_hash(daddr), - (__force u32)id, nf_frags.rnd); - return c & (INETFRAGS_HASHSZ - 1); + return jhash_3words(ipv6_addr_hash(saddr), ipv6_addr_hash(daddr), + (__force u32)id, nf_frags.rnd); } -static unsigned int nf_hashfn(struct inet_frag_queue *q) +static unsigned int nf_hashfn(const struct inet_frag_queue *q) { const struct frag_queue *nq; @@ -196,7 +202,7 @@ static inline struct frag_queue *fq_find(struct net *net, __be32 id, arg.dst = dst; arg.ecn = ecn; - read_lock_bh(&nf_frags.lock); + local_bh_disable(); hash = nf_hash_frag(id, src, dst); q = inet_frag_find(&net->nf_frag.frags, &nf_frags, &arg, hash); @@ -217,7 +223,7 @@ static int nf_ct_frag6_queue(struct frag_queue *fq, struct sk_buff *skb, int offset, end; u8 ecn; - if (fq->q.last_in & INET_FRAG_COMPLETE) { + if (fq->q.flags & INET_FRAG_COMPLETE) { pr_debug("Already completed\n"); goto err; } @@ -248,11 +254,11 @@ static int nf_ct_frag6_queue(struct frag_queue *fq, struct sk_buff *skb, * or have different end, the segment is corrupted. */ if (end < fq->q.len || - ((fq->q.last_in & INET_FRAG_LAST_IN) && end != fq->q.len)) { + ((fq->q.flags & INET_FRAG_LAST_IN) && end != fq->q.len)) { pr_debug("already received last fragment\n"); goto err; } - fq->q.last_in |= INET_FRAG_LAST_IN; + fq->q.flags |= INET_FRAG_LAST_IN; fq->q.len = end; } else { /* Check if the fragment is rounded to 8 bytes. @@ -267,7 +273,7 @@ static int nf_ct_frag6_queue(struct frag_queue *fq, struct sk_buff *skb, } if (end > fq->q.len) { /* Some bits beyond end -> corruption. */ - if (fq->q.last_in & INET_FRAG_LAST_IN) { + if (fq->q.flags & INET_FRAG_LAST_IN) { pr_debug("last packet already reached.\n"); goto err; } @@ -349,10 +355,9 @@ found: */ if (offset == 0) { fq->nhoffset = nhoff; - fq->q.last_in |= INET_FRAG_FIRST_IN; + fq->q.flags |= INET_FRAG_FIRST_IN; } - inet_frag_lru_move(&fq->q); return 0; discard_fq: @@ -597,10 +602,6 @@ struct sk_buff *nf_ct_frag6_gather(struct sk_buff *skb, u32 user) hdr = ipv6_hdr(clone); fhdr = (struct frag_hdr *)skb_transport_header(clone); - local_bh_disable(); - inet_frag_evictor(&net->nf_frag.frags, &nf_frags, false); - local_bh_enable(); - fq = fq_find(net, fhdr->identification, user, &hdr->saddr, &hdr->daddr, ip6_frag_ecn(hdr)); if (fq == NULL) { @@ -617,7 +618,7 @@ struct sk_buff *nf_ct_frag6_gather(struct sk_buff *skb, u32 user) goto ret_orig; } - if (fq->q.last_in == (INET_FRAG_FIRST_IN | INET_FRAG_LAST_IN) && + if (fq->q.flags == (INET_FRAG_FIRST_IN | INET_FRAG_LAST_IN) && fq->q.meat == fq->q.len) { ret_skb = nf_ct_frag6_reasm(fq, dev); if (ret_skb == NULL) @@ -677,13 +678,15 @@ int nf_ct_frag6_init(void) nf_frags.qsize = sizeof(struct frag_queue); nf_frags.match = ip6_frag_match; nf_frags.frag_expire = nf_ct_frag6_expire; - nf_frags.secret_interval = 10 * 60 * HZ; - inet_frags_init(&nf_frags); - + nf_frags.frags_cache_name = nf_frags_cache_name; + ret = inet_frags_init(&nf_frags); + if (ret) + goto out; ret = register_pernet_subsys(&nf_ct_net_ops); if (ret) inet_frags_fini(&nf_frags); +out: return ret; } diff --git a/net/ipv6/netfilter/nf_log_ipv6.c b/net/ipv6/netfilter/nf_log_ipv6.c new file mode 100644 index 000000000000..7b17a0be93e7 --- /dev/null +++ b/net/ipv6/netfilter/nf_log_ipv6.c @@ -0,0 +1,417 @@ +/* (C) 1999-2001 Paul `Rusty' Russell + * (C) 2002-2004 Netfilter Core Team <coreteam@netfilter.org> + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + */ + +#include <linux/module.h> +#include <linux/spinlock.h> +#include <linux/skbuff.h> +#include <linux/if_arp.h> +#include <linux/ip.h> +#include <net/ipv6.h> +#include <net/icmp.h> +#include <net/udp.h> +#include <net/tcp.h> +#include <net/route.h> + +#include <linux/netfilter.h> +#include <linux/netfilter_ipv6/ip6_tables.h> +#include <linux/netfilter/xt_LOG.h> +#include <net/netfilter/nf_log.h> + +static struct nf_loginfo default_loginfo = { + .type = NF_LOG_TYPE_LOG, + .u = { + .log = { + .level = 5, + .logflags = NF_LOG_MASK, + }, + }, +}; + +/* One level of recursion won't kill us */ +static void dump_ipv6_packet(struct nf_log_buf *m, + const struct nf_loginfo *info, + const struct sk_buff *skb, unsigned int ip6hoff, + int recurse) +{ + u_int8_t currenthdr; + int fragment; + struct ipv6hdr _ip6h; + const struct ipv6hdr *ih; + unsigned int ptr; + unsigned int hdrlen = 0; + unsigned int logflags; + + if (info->type == NF_LOG_TYPE_LOG) + logflags = info->u.log.logflags; + else + logflags = NF_LOG_MASK; + + ih = skb_header_pointer(skb, ip6hoff, sizeof(_ip6h), &_ip6h); + if (ih == NULL) { + nf_log_buf_add(m, "TRUNCATED"); + return; + } + + /* Max length: 88 "SRC=0000.0000.0000.0000.0000.0000.0000.0000 DST=0000.0000.0000.0000.0000.0000.0000.0000 " */ + nf_log_buf_add(m, "SRC=%pI6 DST=%pI6 ", &ih->saddr, &ih->daddr); + + /* Max length: 44 "LEN=65535 TC=255 HOPLIMIT=255 FLOWLBL=FFFFF " */ + nf_log_buf_add(m, "LEN=%Zu TC=%u HOPLIMIT=%u FLOWLBL=%u ", + ntohs(ih->payload_len) + sizeof(struct ipv6hdr), + (ntohl(*(__be32 *)ih) & 0x0ff00000) >> 20, + ih->hop_limit, + (ntohl(*(__be32 *)ih) & 0x000fffff)); + + fragment = 0; + ptr = ip6hoff + sizeof(struct ipv6hdr); + currenthdr = ih->nexthdr; + while (currenthdr != NEXTHDR_NONE && ip6t_ext_hdr(currenthdr)) { + struct ipv6_opt_hdr _hdr; + const struct ipv6_opt_hdr *hp; + + hp = skb_header_pointer(skb, ptr, sizeof(_hdr), &_hdr); + if (hp == NULL) { + nf_log_buf_add(m, "TRUNCATED"); + return; + } + + /* Max length: 48 "OPT (...) " */ + if (logflags & XT_LOG_IPOPT) + nf_log_buf_add(m, "OPT ( "); + + switch (currenthdr) { + case IPPROTO_FRAGMENT: { + struct frag_hdr _fhdr; + const struct frag_hdr *fh; + + nf_log_buf_add(m, "FRAG:"); + fh = skb_header_pointer(skb, ptr, sizeof(_fhdr), + &_fhdr); + if (fh == NULL) { + nf_log_buf_add(m, "TRUNCATED "); + return; + } + + /* Max length: 6 "65535 " */ + nf_log_buf_add(m, "%u ", ntohs(fh->frag_off) & 0xFFF8); + + /* Max length: 11 "INCOMPLETE " */ + if (fh->frag_off & htons(0x0001)) + nf_log_buf_add(m, "INCOMPLETE "); + + nf_log_buf_add(m, "ID:%08x ", + ntohl(fh->identification)); + + if (ntohs(fh->frag_off) & 0xFFF8) + fragment = 1; + + hdrlen = 8; + + break; + } + case IPPROTO_DSTOPTS: + case IPPROTO_ROUTING: + case IPPROTO_HOPOPTS: + if (fragment) { + if (logflags & XT_LOG_IPOPT) + nf_log_buf_add(m, ")"); + return; + } + hdrlen = ipv6_optlen(hp); + break; + /* Max Length */ + case IPPROTO_AH: + if (logflags & XT_LOG_IPOPT) { + struct ip_auth_hdr _ahdr; + const struct ip_auth_hdr *ah; + + /* Max length: 3 "AH " */ + nf_log_buf_add(m, "AH "); + + if (fragment) { + nf_log_buf_add(m, ")"); + return; + } + + ah = skb_header_pointer(skb, ptr, sizeof(_ahdr), + &_ahdr); + if (ah == NULL) { + /* + * Max length: 26 "INCOMPLETE [65535 + * bytes] )" + */ + nf_log_buf_add(m, "INCOMPLETE [%u bytes] )", + skb->len - ptr); + return; + } + + /* Length: 15 "SPI=0xF1234567 */ + nf_log_buf_add(m, "SPI=0x%x ", ntohl(ah->spi)); + + } + + hdrlen = (hp->hdrlen+2)<<2; + break; + case IPPROTO_ESP: + if (logflags & XT_LOG_IPOPT) { + struct ip_esp_hdr _esph; + const struct ip_esp_hdr *eh; + + /* Max length: 4 "ESP " */ + nf_log_buf_add(m, "ESP "); + + if (fragment) { + nf_log_buf_add(m, ")"); + return; + } + + /* + * Max length: 26 "INCOMPLETE [65535 bytes] )" + */ + eh = skb_header_pointer(skb, ptr, sizeof(_esph), + &_esph); + if (eh == NULL) { + nf_log_buf_add(m, "INCOMPLETE [%u bytes] )", + skb->len - ptr); + return; + } + + /* Length: 16 "SPI=0xF1234567 )" */ + nf_log_buf_add(m, "SPI=0x%x )", + ntohl(eh->spi)); + } + return; + default: + /* Max length: 20 "Unknown Ext Hdr 255" */ + nf_log_buf_add(m, "Unknown Ext Hdr %u", currenthdr); + return; + } + if (logflags & XT_LOG_IPOPT) + nf_log_buf_add(m, ") "); + + currenthdr = hp->nexthdr; + ptr += hdrlen; + } + + switch (currenthdr) { + case IPPROTO_TCP: + if (nf_log_dump_tcp_header(m, skb, currenthdr, fragment, + ptr, logflags)) + return; + break; + case IPPROTO_UDP: + case IPPROTO_UDPLITE: + if (nf_log_dump_udp_header(m, skb, currenthdr, fragment, ptr)) + return; + break; + case IPPROTO_ICMPV6: { + struct icmp6hdr _icmp6h; + const struct icmp6hdr *ic; + + /* Max length: 13 "PROTO=ICMPv6 " */ + nf_log_buf_add(m, "PROTO=ICMPv6 "); + + if (fragment) + break; + + /* Max length: 25 "INCOMPLETE [65535 bytes] " */ + ic = skb_header_pointer(skb, ptr, sizeof(_icmp6h), &_icmp6h); + if (ic == NULL) { + nf_log_buf_add(m, "INCOMPLETE [%u bytes] ", + skb->len - ptr); + return; + } + + /* Max length: 18 "TYPE=255 CODE=255 " */ + nf_log_buf_add(m, "TYPE=%u CODE=%u ", + ic->icmp6_type, ic->icmp6_code); + + switch (ic->icmp6_type) { + case ICMPV6_ECHO_REQUEST: + case ICMPV6_ECHO_REPLY: + /* Max length: 19 "ID=65535 SEQ=65535 " */ + nf_log_buf_add(m, "ID=%u SEQ=%u ", + ntohs(ic->icmp6_identifier), + ntohs(ic->icmp6_sequence)); + break; + case ICMPV6_MGM_QUERY: + case ICMPV6_MGM_REPORT: + case ICMPV6_MGM_REDUCTION: + break; + + case ICMPV6_PARAMPROB: + /* Max length: 17 "POINTER=ffffffff " */ + nf_log_buf_add(m, "POINTER=%08x ", + ntohl(ic->icmp6_pointer)); + /* Fall through */ + case ICMPV6_DEST_UNREACH: + case ICMPV6_PKT_TOOBIG: + case ICMPV6_TIME_EXCEED: + /* Max length: 3+maxlen */ + if (recurse) { + nf_log_buf_add(m, "["); + dump_ipv6_packet(m, info, skb, + ptr + sizeof(_icmp6h), 0); + nf_log_buf_add(m, "] "); + } + + /* Max length: 10 "MTU=65535 " */ + if (ic->icmp6_type == ICMPV6_PKT_TOOBIG) { + nf_log_buf_add(m, "MTU=%u ", + ntohl(ic->icmp6_mtu)); + } + } + break; + } + /* Max length: 10 "PROTO=255 " */ + default: + nf_log_buf_add(m, "PROTO=%u ", currenthdr); + } + + /* Max length: 15 "UID=4294967295 " */ + if ((logflags & XT_LOG_UID) && recurse) + nf_log_dump_sk_uid_gid(m, skb->sk); + + /* Max length: 16 "MARK=0xFFFFFFFF " */ + if (recurse && skb->mark) + nf_log_buf_add(m, "MARK=0x%x ", skb->mark); +} + +static void dump_ipv6_mac_header(struct nf_log_buf *m, + const struct nf_loginfo *info, + const struct sk_buff *skb) +{ + struct net_device *dev = skb->dev; + unsigned int logflags = 0; + + if (info->type == NF_LOG_TYPE_LOG) + logflags = info->u.log.logflags; + + if (!(logflags & XT_LOG_MACDECODE)) + goto fallback; + + switch (dev->type) { + case ARPHRD_ETHER: + nf_log_buf_add(m, "MACSRC=%pM MACDST=%pM MACPROTO=%04x ", + eth_hdr(skb)->h_source, eth_hdr(skb)->h_dest, + ntohs(eth_hdr(skb)->h_proto)); + return; + default: + break; + } + +fallback: + nf_log_buf_add(m, "MAC="); + if (dev->hard_header_len && + skb->mac_header != skb->network_header) { + const unsigned char *p = skb_mac_header(skb); + unsigned int len = dev->hard_header_len; + unsigned int i; + + if (dev->type == ARPHRD_SIT) { + p -= ETH_HLEN; + + if (p < skb->head) + p = NULL; + } + + if (p != NULL) { + nf_log_buf_add(m, "%02x", *p++); + for (i = 1; i < len; i++) + nf_log_buf_add(m, ":%02x", *p++); + } + nf_log_buf_add(m, " "); + + if (dev->type == ARPHRD_SIT) { + const struct iphdr *iph = + (struct iphdr *)skb_mac_header(skb); + nf_log_buf_add(m, "TUNNEL=%pI4->%pI4 ", &iph->saddr, + &iph->daddr); + } + } else { + nf_log_buf_add(m, " "); + } +} + +static void nf_log_ip6_packet(struct net *net, u_int8_t pf, + unsigned int hooknum, const struct sk_buff *skb, + const struct net_device *in, + const struct net_device *out, + const struct nf_loginfo *loginfo, + const char *prefix) +{ + struct nf_log_buf *m; + + /* FIXME: Disabled from containers until syslog ns is supported */ + if (!net_eq(net, &init_net)) + return; + + m = nf_log_buf_open(); + + if (!loginfo) + loginfo = &default_loginfo; + + nf_log_dump_packet_common(m, pf, hooknum, skb, in, out, + loginfo, prefix); + + if (in != NULL) + dump_ipv6_mac_header(m, loginfo, skb); + + dump_ipv6_packet(m, loginfo, skb, skb_network_offset(skb), 1); + + nf_log_buf_close(m); +} + +static struct nf_logger nf_ip6_logger __read_mostly = { + .name = "nf_log_ipv6", + .type = NF_LOG_TYPE_LOG, + .logfn = nf_log_ip6_packet, + .me = THIS_MODULE, +}; + +static int __net_init nf_log_ipv6_net_init(struct net *net) +{ + nf_log_set(net, NFPROTO_IPV6, &nf_ip6_logger); + return 0; +} + +static void __net_exit nf_log_ipv6_net_exit(struct net *net) +{ + nf_log_unset(net, &nf_ip6_logger); +} + +static struct pernet_operations nf_log_ipv6_net_ops = { + .init = nf_log_ipv6_net_init, + .exit = nf_log_ipv6_net_exit, +}; + +static int __init nf_log_ipv6_init(void) +{ + int ret; + + ret = register_pernet_subsys(&nf_log_ipv6_net_ops); + if (ret < 0) + return ret; + + nf_log_register(NFPROTO_IPV6, &nf_ip6_logger); + return 0; +} + +static void __exit nf_log_ipv6_exit(void) +{ + unregister_pernet_subsys(&nf_log_ipv6_net_ops); + nf_log_unregister(&nf_ip6_logger); +} + +module_init(nf_log_ipv6_init); +module_exit(nf_log_ipv6_exit); + +MODULE_AUTHOR("Netfilter Core Team <coreteam@netfilter.org>"); +MODULE_DESCRIPTION("Netfilter IPv4 packet logging"); +MODULE_LICENSE("GPL"); +MODULE_ALIAS_NF_LOGGER(AF_INET6, 0); diff --git a/net/ipv6/netfilter/nf_nat_l3proto_ipv6.c b/net/ipv6/netfilter/nf_nat_l3proto_ipv6.c index abfe75a2e316..fc8e49b2ff3e 100644 --- a/net/ipv6/netfilter/nf_nat_l3proto_ipv6.c +++ b/net/ipv6/netfilter/nf_nat_l3proto_ipv6.c @@ -158,6 +158,7 @@ static void nf_nat_ipv6_csum_recalc(struct sk_buff *skb, htons(oldlen), htons(datalen), 1); } +#if IS_ENABLED(CONFIG_NF_CT_NETLINK) static int nf_nat_ipv6_nlattr_to_range(struct nlattr *tb[], struct nf_nat_range *range) { @@ -175,6 +176,7 @@ static int nf_nat_ipv6_nlattr_to_range(struct nlattr *tb[], return 0; } +#endif static const struct nf_nat_l3proto nf_nat_l3proto_ipv6 = { .l3proto = NFPROTO_IPV6, @@ -183,7 +185,9 @@ static const struct nf_nat_l3proto nf_nat_l3proto_ipv6 = { .manip_pkt = nf_nat_ipv6_manip_pkt, .csum_update = nf_nat_ipv6_csum_update, .csum_recalc = nf_nat_ipv6_csum_recalc, +#if IS_ENABLED(CONFIG_NF_CT_NETLINK) .nlattr_to_range = nf_nat_ipv6_nlattr_to_range, +#endif #ifdef CONFIG_XFRM .decode_session = nf_nat_ipv6_decode_session, #endif diff --git a/net/ipv6/proc.c b/net/ipv6/proc.c index 3317440ea341..2d6f860e5c1e 100644 --- a/net/ipv6/proc.c +++ b/net/ipv6/proc.c @@ -33,6 +33,7 @@ static int sockstat6_seq_show(struct seq_file *seq, void *v) { struct net *net = seq->private; + unsigned int frag_mem = ip6_frag_mem(net); seq_printf(seq, "TCP6: inuse %d\n", sock_prot_inuse_get(net, &tcpv6_prot)); @@ -42,8 +43,7 @@ static int sockstat6_seq_show(struct seq_file *seq, void *v) sock_prot_inuse_get(net, &udplitev6_prot)); seq_printf(seq, "RAW6: inuse %d\n", sock_prot_inuse_get(net, &rawv6_prot)); - seq_printf(seq, "FRAG6: inuse %d memory %d\n", - ip6_frag_nqueues(net), ip6_frag_mem(net)); + seq_printf(seq, "FRAG6: inuse %u memory %u\n", !!frag_mem, frag_mem); return 0; } diff --git a/net/ipv6/raw.c b/net/ipv6/raw.c index b2dc60b0c764..39d44226e402 100644 --- a/net/ipv6/raw.c +++ b/net/ipv6/raw.c @@ -176,7 +176,7 @@ static bool ipv6_raw_deliver(struct sk_buff *skb, int nexthdr) goto out; net = dev_net(skb->dev); - sk = __raw_v6_lookup(net, sk, nexthdr, daddr, saddr, IP6CB(skb)->iif); + sk = __raw_v6_lookup(net, sk, nexthdr, daddr, saddr, inet6_iif(skb)); while (sk) { int filtered; @@ -220,7 +220,7 @@ static bool ipv6_raw_deliver(struct sk_buff *skb, int nexthdr) } } sk = __raw_v6_lookup(net, sk_next(sk), nexthdr, daddr, saddr, - IP6CB(skb)->iif); + inet6_iif(skb)); } out: read_unlock(&raw_v6_hashinfo.lock); @@ -375,7 +375,7 @@ void raw6_icmp_error(struct sk_buff *skb, int nexthdr, net = dev_net(skb->dev); while ((sk = __raw_v6_lookup(net, sk, nexthdr, saddr, daddr, - IP6CB(skb)->iif))) { + inet6_iif(skb)))) { rawv6_err(sk, skb, NULL, type, code, inner_offset, info); sk = sk_next(sk); @@ -506,7 +506,7 @@ static int rawv6_recvmsg(struct kiocb *iocb, struct sock *sk, sin6->sin6_addr = ipv6_hdr(skb)->saddr; sin6->sin6_flowinfo = 0; sin6->sin6_scope_id = ipv6_iface_scope_id(&sin6->sin6_addr, - IP6CB(skb)->iif); + inet6_iif(skb)); *addr_len = sizeof(*sin6); } @@ -588,8 +588,7 @@ static int rawv6_push_pending_frames(struct sock *sk, struct flowi6 *fl6, } offset += skb_transport_offset(skb); - if (skb_copy_bits(skb, offset, &csum, 2)) - BUG(); + BUG_ON(skb_copy_bits(skb, offset, &csum, 2)); /* in case cksum was not initialized */ if (unlikely(csum)) @@ -601,8 +600,7 @@ static int rawv6_push_pending_frames(struct sock *sk, struct flowi6 *fl6, if (csum == 0 && fl6->flowi6_proto == IPPROTO_UDP) csum = CSUM_MANGLED_0; - if (skb_store_bits(skb, offset, &csum, 2)) - BUG(); + BUG_ON(skb_store_bits(skb, offset, &csum, 2)); send: err = ip6_push_pending_frames(sk); diff --git a/net/ipv6/reassembly.c b/net/ipv6/reassembly.c index cc85a9ba5010..c6557d9f7808 100644 --- a/net/ipv6/reassembly.c +++ b/net/ipv6/reassembly.c @@ -60,6 +60,8 @@ #include <net/inet_frag.h> #include <net/inet_ecn.h> +static const char ip6_frag_cache_name[] = "ip6-frags"; + struct ip6frag_skb_cb { struct inet6_skb_parm h; @@ -85,27 +87,23 @@ static int ip6_frag_reasm(struct frag_queue *fq, struct sk_buff *prev, static unsigned int inet6_hash_frag(__be32 id, const struct in6_addr *saddr, const struct in6_addr *daddr) { - u32 c; - net_get_random_once(&ip6_frags.rnd, sizeof(ip6_frags.rnd)); - c = jhash_3words(ipv6_addr_hash(saddr), ipv6_addr_hash(daddr), - (__force u32)id, ip6_frags.rnd); - - return c & (INETFRAGS_HASHSZ - 1); + return jhash_3words(ipv6_addr_hash(saddr), ipv6_addr_hash(daddr), + (__force u32)id, ip6_frags.rnd); } -static unsigned int ip6_hashfn(struct inet_frag_queue *q) +static unsigned int ip6_hashfn(const struct inet_frag_queue *q) { - struct frag_queue *fq; + const struct frag_queue *fq; fq = container_of(q, struct frag_queue, q); return inet6_hash_frag(fq->id, &fq->saddr, &fq->daddr); } -bool ip6_frag_match(struct inet_frag_queue *q, void *a) +bool ip6_frag_match(const struct inet_frag_queue *q, const void *a) { - struct frag_queue *fq; - struct ip6_create_arg *arg = a; + const struct frag_queue *fq; + const struct ip6_create_arg *arg = a; fq = container_of(q, struct frag_queue, q); return fq->id == arg->id && @@ -115,10 +113,10 @@ bool ip6_frag_match(struct inet_frag_queue *q, void *a) } EXPORT_SYMBOL(ip6_frag_match); -void ip6_frag_init(struct inet_frag_queue *q, void *a) +void ip6_frag_init(struct inet_frag_queue *q, const void *a) { struct frag_queue *fq = container_of(q, struct frag_queue, q); - struct ip6_create_arg *arg = a; + const struct ip6_create_arg *arg = a; fq->id = arg->id; fq->user = arg->user; @@ -135,7 +133,7 @@ void ip6_expire_frag_queue(struct net *net, struct frag_queue *fq, spin_lock(&fq->q.lock); - if (fq->q.last_in & INET_FRAG_COMPLETE) + if (fq->q.flags & INET_FRAG_COMPLETE) goto out; inet_frag_kill(&fq->q, frags); @@ -145,17 +143,20 @@ void ip6_expire_frag_queue(struct net *net, struct frag_queue *fq, if (!dev) goto out_rcu_unlock; - IP6_INC_STATS_BH(net, __in6_dev_get(dev), IPSTATS_MIB_REASMTIMEOUT); IP6_INC_STATS_BH(net, __in6_dev_get(dev), IPSTATS_MIB_REASMFAILS); + if (fq->q.flags & INET_FRAG_EVICTED) + goto out_rcu_unlock; + + IP6_INC_STATS_BH(net, __in6_dev_get(dev), IPSTATS_MIB_REASMTIMEOUT); + /* Don't send error if the first segment did not arrive. */ - if (!(fq->q.last_in & INET_FRAG_FIRST_IN) || !fq->q.fragments) + if (!(fq->q.flags & INET_FRAG_FIRST_IN) || !fq->q.fragments) goto out_rcu_unlock; - /* - But use as source device on which LAST ARRIVED - segment was received. And do not use fq->dev - pointer directly, device might already disappeared. + /* But use as source device on which LAST ARRIVED + * segment was received. And do not use fq->dev + * pointer directly, device might already disappeared. */ fq->q.fragments->dev = dev; icmpv6_send(fq->q.fragments, ICMPV6_TIME_EXCEED, ICMPV6_EXC_FRAGTIME, 0); @@ -192,7 +193,6 @@ fq_find(struct net *net, __be32 id, const struct in6_addr *src, arg.dst = dst; arg.ecn = ecn; - read_lock(&ip6_frags.lock); hash = inet6_hash_frag(id, src, dst); q = inet_frag_find(&net->ipv6.frags, &ip6_frags, &arg, hash); @@ -212,7 +212,7 @@ static int ip6_frag_queue(struct frag_queue *fq, struct sk_buff *skb, struct net *net = dev_net(skb_dst(skb)->dev); u8 ecn; - if (fq->q.last_in & INET_FRAG_COMPLETE) + if (fq->q.flags & INET_FRAG_COMPLETE) goto err; offset = ntohs(fhdr->frag_off) & ~0x7; @@ -243,9 +243,9 @@ static int ip6_frag_queue(struct frag_queue *fq, struct sk_buff *skb, * or have different end, the segment is corrupted. */ if (end < fq->q.len || - ((fq->q.last_in & INET_FRAG_LAST_IN) && end != fq->q.len)) + ((fq->q.flags & INET_FRAG_LAST_IN) && end != fq->q.len)) goto err; - fq->q.last_in |= INET_FRAG_LAST_IN; + fq->q.flags |= INET_FRAG_LAST_IN; fq->q.len = end; } else { /* Check if the fragment is rounded to 8 bytes. @@ -263,7 +263,7 @@ static int ip6_frag_queue(struct frag_queue *fq, struct sk_buff *skb, } if (end > fq->q.len) { /* Some bits beyond end -> corruption. */ - if (fq->q.last_in & INET_FRAG_LAST_IN) + if (fq->q.flags & INET_FRAG_LAST_IN) goto err; fq->q.len = end; } @@ -338,10 +338,10 @@ found: */ if (offset == 0) { fq->nhoffset = nhoff; - fq->q.last_in |= INET_FRAG_FIRST_IN; + fq->q.flags |= INET_FRAG_FIRST_IN; } - if (fq->q.last_in == (INET_FRAG_FIRST_IN | INET_FRAG_LAST_IN) && + if (fq->q.flags == (INET_FRAG_FIRST_IN | INET_FRAG_LAST_IN) && fq->q.meat == fq->q.len) { int res; unsigned long orefdst = skb->_skb_refdst; @@ -353,14 +353,13 @@ found: } skb_dst_drop(skb); - inet_frag_lru_move(&fq->q); return -1; discard_fq: inet_frag_kill(&fq->q, &ip6_frags); err: - IP6_INC_STATS(net, ip6_dst_idev(skb_dst(skb)), - IPSTATS_MIB_REASMFAILS); + IP6_INC_STATS_BH(net, ip6_dst_idev(skb_dst(skb)), + IPSTATS_MIB_REASMFAILS); kfree_skb(skb); return -1; } @@ -523,7 +522,6 @@ static int ipv6_frag_rcv(struct sk_buff *skb) struct frag_queue *fq; const struct ipv6hdr *hdr = ipv6_hdr(skb); struct net *net = dev_net(skb_dst(skb)->dev); - int evicted; if (IP6CB(skb)->flags & IP6SKB_FRAGMENTED) goto fail_hdr; @@ -552,11 +550,6 @@ static int ipv6_frag_rcv(struct sk_buff *skb) return 1; } - evicted = inet_frag_evictor(&net->ipv6.frags, &ip6_frags, false); - if (evicted) - IP6_ADD_STATS_BH(net, ip6_dst_idev(skb_dst(skb)), - IPSTATS_MIB_REASMFAILS, evicted); - fq = fq_find(net, fhdr->identification, &hdr->saddr, &hdr->daddr, ip6_frag_ecn(hdr)); if (fq != NULL) { @@ -576,7 +569,8 @@ static int ipv6_frag_rcv(struct sk_buff *skb) return -1; fail_hdr: - IP6_INC_STATS(net, ip6_dst_idev(skb_dst(skb)), IPSTATS_MIB_INHDRERRORS); + IP6_INC_STATS_BH(net, ip6_dst_idev(skb_dst(skb)), + IPSTATS_MIB_INHDRERRORS); icmpv6_param_prob(skb, ICMPV6_HDR_FIELD, skb_network_header_len(skb)); return -1; } @@ -588,20 +582,25 @@ static const struct inet6_protocol frag_protocol = }; #ifdef CONFIG_SYSCTL +static int zero; + static struct ctl_table ip6_frags_ns_ctl_table[] = { { .procname = "ip6frag_high_thresh", .data = &init_net.ipv6.frags.high_thresh, .maxlen = sizeof(int), .mode = 0644, - .proc_handler = proc_dointvec + .proc_handler = proc_dointvec_minmax, + .extra1 = &init_net.ipv6.frags.low_thresh }, { .procname = "ip6frag_low_thresh", .data = &init_net.ipv6.frags.low_thresh, .maxlen = sizeof(int), .mode = 0644, - .proc_handler = proc_dointvec + .proc_handler = proc_dointvec_minmax, + .extra1 = &zero, + .extra2 = &init_net.ipv6.frags.high_thresh }, { .procname = "ip6frag_time", @@ -613,10 +612,12 @@ static struct ctl_table ip6_frags_ns_ctl_table[] = { { } }; +/* secret interval has been deprecated */ +static int ip6_frags_secret_interval_unused; static struct ctl_table ip6_frags_ctl_table[] = { { .procname = "ip6frag_secret_interval", - .data = &ip6_frags.secret_interval, + .data = &ip6_frags_secret_interval_unused, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec_jiffies, @@ -636,7 +637,10 @@ static int __net_init ip6_frags_ns_sysctl_register(struct net *net) goto err_alloc; table[0].data = &net->ipv6.frags.high_thresh; + table[0].extra1 = &net->ipv6.frags.low_thresh; + table[0].extra2 = &init_net.ipv6.frags.high_thresh; table[1].data = &net->ipv6.frags.low_thresh; + table[1].extra2 = &net->ipv6.frags.high_thresh; table[2].data = &net->ipv6.frags.timeout; /* Don't export sysctls to unprivileged users */ @@ -746,8 +750,10 @@ int __init ipv6_frag_init(void) ip6_frags.qsize = sizeof(struct frag_queue); ip6_frags.match = ip6_frag_match; ip6_frags.frag_expire = ip6_frag_expire; - ip6_frags.secret_interval = 10 * 60 * HZ; - inet_frags_init(&ip6_frags); + ip6_frags.frags_cache_name = ip6_frag_cache_name; + ret = inet_frags_init(&ip6_frags); + if (ret) + goto err_pernet; out: return ret; diff --git a/net/ipv6/sit.c b/net/ipv6/sit.c index 4f408176dc64..2e9ba035fb5f 100644 --- a/net/ipv6/sit.c +++ b/net/ipv6/sit.c @@ -250,7 +250,8 @@ static struct ip_tunnel *ipip6_tunnel_locate(struct net *net, else strcpy(name, "sit%d"); - dev = alloc_netdev(sizeof(*t), name, ipip6_tunnel_setup); + dev = alloc_netdev(sizeof(*t), name, NET_NAME_UNKNOWN, + ipip6_tunnel_setup); if (dev == NULL) return NULL; @@ -1729,6 +1730,7 @@ static int __net_init sit_init_net(struct net *net) sitn->tunnels[3] = sitn->tunnels_r_l; sitn->fb_tunnel_dev = alloc_netdev(sizeof(struct ip_tunnel), "sit0", + NET_NAME_UNKNOWN, ipip6_tunnel_setup); if (!sitn->fb_tunnel_dev) { err = -ENOMEM; diff --git a/net/ipv6/syncookies.c b/net/ipv6/syncookies.c index a822b880689b..83cea1d39466 100644 --- a/net/ipv6/syncookies.c +++ b/net/ipv6/syncookies.c @@ -187,7 +187,7 @@ struct sock *cookie_v6_check(struct sock *sk, struct sk_buff *skb) goto out; ret = NULL; - req = inet6_reqsk_alloc(&tcp6_request_sock_ops); + req = inet_reqsk_alloc(&tcp6_request_sock_ops); if (!req) goto out; diff --git a/net/ipv6/sysctl_net_ipv6.c b/net/ipv6/sysctl_net_ipv6.c index 058f3eca2e53..0c56c93619e0 100644 --- a/net/ipv6/sysctl_net_ipv6.c +++ b/net/ipv6/sysctl_net_ipv6.c @@ -39,6 +39,13 @@ static struct ctl_table ipv6_table_template[] = { .proc_handler = proc_dointvec }, { + .procname = "auto_flowlabels", + .data = &init_net.ipv6.sysctl.auto_flowlabels, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec + }, + { .procname = "fwmark_reflect", .data = &init_net.ipv6.sysctl.fwmark_reflect, .maxlen = sizeof(int), @@ -74,6 +81,8 @@ static int __net_init ipv6_sysctl_net_init(struct net *net) ipv6_table[0].data = &net->ipv6.sysctl.bindv6only; ipv6_table[1].data = &net->ipv6.sysctl.anycast_src_echo_reply; ipv6_table[2].data = &net->ipv6.sysctl.flowlabel_consistency; + ipv6_table[3].data = &net->ipv6.sysctl.auto_flowlabels; + ipv6_table[4].data = &net->ipv6.sysctl.fwmark_reflect; ipv6_route_table = ipv6_route_sysctl_init(net); if (!ipv6_route_table) diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c index 229239ad96b1..22055b098428 100644 --- a/net/ipv6/tcp_ipv6.c +++ b/net/ipv6/tcp_ipv6.c @@ -198,6 +198,8 @@ static int tcp_v6_connect(struct sock *sk, struct sockaddr *uaddr, sk->sk_v6_daddr = usin->sin6_addr; np->flow_label = fl6.flowlabel; + ip6_set_txhash(sk); + /* * TCP over IPv4 */ @@ -470,13 +472,14 @@ out: static int tcp_v6_send_synack(struct sock *sk, struct dst_entry *dst, - struct flowi6 *fl6, + struct flowi *fl, struct request_sock *req, u16 queue_mapping, struct tcp_fastopen_cookie *foc) { struct inet_request_sock *ireq = inet_rsk(req); struct ipv6_pinfo *np = inet6_sk(sk); + struct flowi6 *fl6 = &fl->u.ip6; struct sk_buff *skb; int err = -ENOMEM; @@ -503,18 +506,6 @@ done: return err; } -static int tcp_v6_rtx_synack(struct sock *sk, struct request_sock *req) -{ - struct flowi6 fl6; - int res; - - res = tcp_v6_send_synack(sk, NULL, &fl6, req, 0, NULL); - if (!res) { - TCP_INC_STATS_BH(sock_net(sk), TCP_MIB_RETRANSSEGS); - NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_TCPSYNRETRANS); - } - return res; -} static void tcp_v6_reqsk_destructor(struct request_sock *req) { @@ -718,22 +709,66 @@ static int tcp_v6_inbound_md5_hash(struct sock *sk, const struct sk_buff *skb) } #endif +static void tcp_v6_init_req(struct request_sock *req, struct sock *sk, + struct sk_buff *skb) +{ + struct inet_request_sock *ireq = inet_rsk(req); + struct ipv6_pinfo *np = inet6_sk(sk); + + ireq->ir_v6_rmt_addr = ipv6_hdr(skb)->saddr; + ireq->ir_v6_loc_addr = ipv6_hdr(skb)->daddr; + + ireq->ir_iif = sk->sk_bound_dev_if; + + /* So that link locals have meaning */ + if (!sk->sk_bound_dev_if && + ipv6_addr_type(&ireq->ir_v6_rmt_addr) & IPV6_ADDR_LINKLOCAL) + ireq->ir_iif = inet6_iif(skb); + + if (!TCP_SKB_CB(skb)->when && + (ipv6_opt_accepted(sk, skb) || np->rxopt.bits.rxinfo || + np->rxopt.bits.rxoinfo || np->rxopt.bits.rxhlim || + np->rxopt.bits.rxohlim || np->repflow)) { + atomic_inc(&skb->users); + ireq->pktopts = skb; + } +} + +static struct dst_entry *tcp_v6_route_req(struct sock *sk, struct flowi *fl, + const struct request_sock *req, + bool *strict) +{ + if (strict) + *strict = true; + return inet6_csk_route_req(sk, &fl->u.ip6, req); +} + struct request_sock_ops tcp6_request_sock_ops __read_mostly = { .family = AF_INET6, .obj_size = sizeof(struct tcp6_request_sock), - .rtx_syn_ack = tcp_v6_rtx_synack, + .rtx_syn_ack = tcp_rtx_synack, .send_ack = tcp_v6_reqsk_send_ack, .destructor = tcp_v6_reqsk_destructor, .send_reset = tcp_v6_send_reset, .syn_ack_timeout = tcp_syn_ack_timeout, }; -#ifdef CONFIG_TCP_MD5SIG static const struct tcp_request_sock_ops tcp_request_sock_ipv6_ops = { + .mss_clamp = IPV6_MIN_MTU - sizeof(struct tcphdr) - + sizeof(struct ipv6hdr), +#ifdef CONFIG_TCP_MD5SIG .md5_lookup = tcp_v6_reqsk_md5_lookup, .calc_md5_hash = tcp_v6_md5_hash_skb, -}; #endif + .init_req = tcp_v6_init_req, +#ifdef CONFIG_SYN_COOKIES + .cookie_init_seq = cookie_v6_init_sequence, +#endif + .route_req = tcp_v6_route_req, + .init_seq = tcp_v6_init_sequence, + .send_synack = tcp_v6_send_synack, + .queue_hash_add = inet6_csk_reqsk_queue_hash_add, +}; static void tcp_v6_send_response(struct sk_buff *skb, u32 seq, u32 ack, u32 win, u32 tsval, u32 tsecr, int oif, @@ -973,153 +1008,17 @@ static struct sock *tcp_v6_hnd_req(struct sock *sk, struct sk_buff *skb) return sk; } -/* FIXME: this is substantially similar to the ipv4 code. - * Can some kind of merge be done? -- erics - */ static int tcp_v6_conn_request(struct sock *sk, struct sk_buff *skb) { - struct tcp_options_received tmp_opt; - struct request_sock *req; - struct inet_request_sock *ireq; - struct ipv6_pinfo *np = inet6_sk(sk); - struct tcp_sock *tp = tcp_sk(sk); - __u32 isn = TCP_SKB_CB(skb)->when; - struct dst_entry *dst = NULL; - struct tcp_fastopen_cookie foc = { .len = -1 }; - bool want_cookie = false, fastopen; - struct flowi6 fl6; - int err; - if (skb->protocol == htons(ETH_P_IP)) return tcp_v4_conn_request(sk, skb); if (!ipv6_unicast_destination(skb)) goto drop; - if ((sysctl_tcp_syncookies == 2 || - inet_csk_reqsk_queue_is_full(sk)) && !isn) { - want_cookie = tcp_syn_flood_action(sk, skb, "TCPv6"); - if (!want_cookie) - goto drop; - } - - if (sk_acceptq_is_full(sk) && inet_csk_reqsk_queue_young(sk) > 1) { - NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_LISTENOVERFLOWS); - goto drop; - } - - req = inet6_reqsk_alloc(&tcp6_request_sock_ops); - if (req == NULL) - goto drop; - -#ifdef CONFIG_TCP_MD5SIG - tcp_rsk(req)->af_specific = &tcp_request_sock_ipv6_ops; -#endif - - tcp_clear_options(&tmp_opt); - tmp_opt.mss_clamp = IPV6_MIN_MTU - sizeof(struct tcphdr) - sizeof(struct ipv6hdr); - tmp_opt.user_mss = tp->rx_opt.user_mss; - tcp_parse_options(skb, &tmp_opt, 0, want_cookie ? NULL : &foc); + return tcp_conn_request(&tcp6_request_sock_ops, + &tcp_request_sock_ipv6_ops, sk, skb); - if (want_cookie && !tmp_opt.saw_tstamp) - tcp_clear_options(&tmp_opt); - - tmp_opt.tstamp_ok = tmp_opt.saw_tstamp; - tcp_openreq_init(req, &tmp_opt, skb); - - ireq = inet_rsk(req); - ireq->ir_v6_rmt_addr = ipv6_hdr(skb)->saddr; - ireq->ir_v6_loc_addr = ipv6_hdr(skb)->daddr; - if (!want_cookie || tmp_opt.tstamp_ok) - TCP_ECN_create_request(req, skb, sock_net(sk)); - - ireq->ir_iif = sk->sk_bound_dev_if; - ireq->ir_mark = inet_request_mark(sk, skb); - - /* So that link locals have meaning */ - if (!sk->sk_bound_dev_if && - ipv6_addr_type(&ireq->ir_v6_rmt_addr) & IPV6_ADDR_LINKLOCAL) - ireq->ir_iif = inet6_iif(skb); - - if (!isn) { - if (ipv6_opt_accepted(sk, skb) || - np->rxopt.bits.rxinfo || np->rxopt.bits.rxoinfo || - np->rxopt.bits.rxhlim || np->rxopt.bits.rxohlim || - np->repflow) { - atomic_inc(&skb->users); - ireq->pktopts = skb; - } - - if (want_cookie) { - isn = cookie_v6_init_sequence(sk, skb, &req->mss); - req->cookie_ts = tmp_opt.tstamp_ok; - goto have_isn; - } - - /* VJ's idea. We save last timestamp seen - * from the destination in peer table, when entering - * state TIME-WAIT, and check against it before - * accepting new connection request. - * - * If "isn" is not zero, this request hit alive - * timewait bucket, so that all the necessary checks - * are made in the function processing timewait state. - */ - if (tmp_opt.saw_tstamp && - tcp_death_row.sysctl_tw_recycle && - (dst = inet6_csk_route_req(sk, &fl6, req)) != NULL) { - if (!tcp_peer_is_proven(req, dst, true)) { - NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_PAWSPASSIVEREJECTED); - goto drop_and_release; - } - } - /* Kill the following clause, if you dislike this way. */ - else if (!sysctl_tcp_syncookies && - (sysctl_max_syn_backlog - inet_csk_reqsk_queue_len(sk) < - (sysctl_max_syn_backlog >> 2)) && - !tcp_peer_is_proven(req, dst, false)) { - /* Without syncookies last quarter of - * backlog is filled with destinations, - * proven to be alive. - * It means that we continue to communicate - * to destinations, already remembered - * to the moment of synflood. - */ - LIMIT_NETDEBUG(KERN_DEBUG "TCP: drop open request from %pI6/%u\n", - &ireq->ir_v6_rmt_addr, ntohs(tcp_hdr(skb)->source)); - goto drop_and_release; - } - - isn = tcp_v6_init_sequence(skb); - } -have_isn: - - if (security_inet_conn_request(sk, skb, req)) - goto drop_and_release; - - if (!dst && (dst = inet6_csk_route_req(sk, &fl6, req)) == NULL) - goto drop_and_free; - - tcp_rsk(req)->snt_isn = isn; - tcp_rsk(req)->snt_synack = tcp_time_stamp; - tcp_openreq_init_rwin(req, sk, dst); - fastopen = !want_cookie && - tcp_try_fastopen(sk, skb, req, &foc, dst); - err = tcp_v6_send_synack(sk, dst, &fl6, req, - skb_get_queue_mapping(skb), &foc); - if (!fastopen) { - if (err || want_cookie) - goto drop_and_free; - - tcp_rsk(req)->listener = NULL; - inet6_csk_reqsk_queue_hash_add(sk, req, TCP_TIMEOUT_INIT); - } - return 0; - -drop_and_release: - dst_release(dst); -drop_and_free: - reqsk_free(req); drop: NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_LISTENDROPS); return 0; /* don't send reset */ @@ -1235,6 +1134,8 @@ static struct sock *tcp_v6_syn_recv_sock(struct sock *sk, struct sk_buff *skb, newsk->sk_v6_rcv_saddr = ireq->ir_v6_loc_addr; newsk->sk_bound_dev_if = ireq->ir_iif; + ip6_set_txhash(newsk); + /* Now IPv6 options... First: no IPv4 options. diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c index 7092ff78fd84..4836af8f582d 100644 --- a/net/ipv6/udp.c +++ b/net/ipv6/udp.c @@ -79,7 +79,6 @@ static unsigned int udp6_ehashfn(struct net *net, int ipv6_rcv_saddr_equal(const struct sock *sk, const struct sock *sk2) { const struct in6_addr *sk2_rcv_saddr6 = inet6_rcv_saddr(sk2); - int sk_ipv6only = ipv6_only_sock(sk); int sk2_ipv6only = inet_v6_ipv6only(sk2); int addr_type = ipv6_addr_type(&sk->sk_v6_rcv_saddr); int addr_type2 = sk2_rcv_saddr6 ? ipv6_addr_type(sk2_rcv_saddr6) : IPV6_ADDR_MAPPED; @@ -95,7 +94,7 @@ int ipv6_rcv_saddr_equal(const struct sock *sk, const struct sock *sk2) return 1; if (addr_type == IPV6_ADDR_ANY && - !(sk_ipv6only && addr_type2 == IPV6_ADDR_MAPPED)) + !(ipv6_only_sock(sk) && addr_type2 == IPV6_ADDR_MAPPED)) return 1; if (sk2_rcv_saddr6 && @@ -473,7 +472,7 @@ try_again: sin6->sin6_addr = ipv6_hdr(skb)->saddr; sin6->sin6_scope_id = ipv6_iface_scope_id(&sin6->sin6_addr, - IP6CB(skb)->iif); + inet6_iif(skb)); } *addr_len = sizeof(*sin6); } @@ -534,11 +533,15 @@ void __udp6_lib_err(struct sk_buff *skb, struct inet6_skb_parm *opt, struct udphdr *uh = (struct udphdr*)(skb->data+offset); struct sock *sk; int err; + struct net *net = dev_net(skb->dev); - sk = __udp6_lib_lookup(dev_net(skb->dev), daddr, uh->dest, + sk = __udp6_lib_lookup(net, daddr, uh->dest, saddr, uh->source, inet6_iif(skb), udptable); - if (sk == NULL) + if (sk == NULL) { + ICMP6_INC_STATS_BH(net, __in6_dev_get(skb->dev), + ICMP6_MIB_INERRORS); return; + } if (type == ICMPV6_PKT_TOOBIG) { if (!ip6_sk_accept_pmtu(sk)) @@ -674,7 +677,7 @@ int udpv6_queue_rcv_skb(struct sock *sk, struct sk_buff *skb) goto csum_error; } - if (sk_rcvqueues_full(sk, skb, sk->sk_rcvbuf)) { + if (sk_rcvqueues_full(sk, sk->sk_rcvbuf)) { UDP6_INC_STATS_BH(sock_net(sk), UDP_MIB_RCVBUFERRORS, is_udplite); goto drop; @@ -703,43 +706,26 @@ drop: return -1; } -static struct sock *udp_v6_mcast_next(struct net *net, struct sock *sk, - __be16 loc_port, const struct in6_addr *loc_addr, - __be16 rmt_port, const struct in6_addr *rmt_addr, - int dif) +static bool __udp_v6_is_mcast_sock(struct net *net, struct sock *sk, + __be16 loc_port, const struct in6_addr *loc_addr, + __be16 rmt_port, const struct in6_addr *rmt_addr, + int dif, unsigned short hnum) { - struct hlist_nulls_node *node; - unsigned short num = ntohs(loc_port); - - sk_nulls_for_each_from(sk, node) { - struct inet_sock *inet = inet_sk(sk); - - if (!net_eq(sock_net(sk), net)) - continue; - - if (udp_sk(sk)->udp_port_hash == num && - sk->sk_family == PF_INET6) { - if (inet->inet_dport) { - if (inet->inet_dport != rmt_port) - continue; - } - if (!ipv6_addr_any(&sk->sk_v6_daddr) && - !ipv6_addr_equal(&sk->sk_v6_daddr, rmt_addr)) - continue; - - if (sk->sk_bound_dev_if && sk->sk_bound_dev_if != dif) - continue; + struct inet_sock *inet = inet_sk(sk); - if (!ipv6_addr_any(&sk->sk_v6_rcv_saddr)) { - if (!ipv6_addr_equal(&sk->sk_v6_rcv_saddr, loc_addr)) - continue; - } - if (!inet6_mc_check(sk, loc_addr, rmt_addr)) - continue; - return sk; - } - } - return NULL; + if (!net_eq(sock_net(sk), net)) + return false; + + if (udp_sk(sk)->udp_port_hash != hnum || + sk->sk_family != PF_INET6 || + (inet->inet_dport && inet->inet_dport != rmt_port) || + (!ipv6_addr_any(&sk->sk_v6_daddr) && + !ipv6_addr_equal(&sk->sk_v6_daddr, rmt_addr)) || + (sk->sk_bound_dev_if && sk->sk_bound_dev_if != dif)) + return false; + if (!inet6_mc_check(sk, loc_addr, rmt_addr)) + return false; + return true; } static void flush_stack(struct sock **stack, unsigned int count, @@ -763,6 +749,7 @@ static void flush_stack(struct sock **stack, unsigned int count, if (skb1 && udpv6_queue_rcv_skb(sk, skb1) <= 0) skb1 = NULL; + sock_put(sk); } if (unlikely(skb1)) kfree_skb(skb1); @@ -788,43 +775,51 @@ static int __udp6_lib_mcast_deliver(struct net *net, struct sk_buff *skb, { struct sock *sk, *stack[256 / sizeof(struct sock *)]; const struct udphdr *uh = udp_hdr(skb); - struct udp_hslot *hslot = udp_hashslot(udptable, net, ntohs(uh->dest)); - int dif; - unsigned int i, count = 0; + struct hlist_nulls_node *node; + unsigned short hnum = ntohs(uh->dest); + struct udp_hslot *hslot = udp_hashslot(udptable, net, hnum); + int dif = inet6_iif(skb); + unsigned int count = 0, offset = offsetof(typeof(*sk), sk_nulls_node); + unsigned int hash2 = 0, hash2_any = 0, use_hash2 = (hslot->count > 10); + + if (use_hash2) { + hash2_any = udp6_portaddr_hash(net, &in6addr_any, hnum) & + udp_table.mask; + hash2 = udp6_portaddr_hash(net, daddr, hnum) & udp_table.mask; +start_lookup: + hslot = &udp_table.hash2[hash2]; + offset = offsetof(typeof(*sk), __sk_common.skc_portaddr_node); + } spin_lock(&hslot->lock); - sk = sk_nulls_head(&hslot->head); - dif = inet6_iif(skb); - sk = udp_v6_mcast_next(net, sk, uh->dest, daddr, uh->source, saddr, dif); - while (sk) { - /* If zero checksum and no_check is not on for - * the socket then skip it. - */ - if (uh->check || udp_sk(sk)->no_check6_rx) + sk_nulls_for_each_entry_offset(sk, node, &hslot->head, offset) { + if (__udp_v6_is_mcast_sock(net, sk, + uh->dest, daddr, + uh->source, saddr, + dif, hnum) && + /* If zero checksum and no_check is not on for + * the socket then skip it. + */ + (uh->check || udp_sk(sk)->no_check6_rx)) { + if (unlikely(count == ARRAY_SIZE(stack))) { + flush_stack(stack, count, skb, ~0); + count = 0; + } stack[count++] = sk; - - sk = udp_v6_mcast_next(net, sk_nulls_next(sk), uh->dest, daddr, - uh->source, saddr, dif); - if (unlikely(count == ARRAY_SIZE(stack))) { - if (!sk) - break; - flush_stack(stack, count, skb, ~0); - count = 0; + sock_hold(sk); } } - /* - * before releasing the lock, we must take reference on sockets - */ - for (i = 0; i < count; i++) - sock_hold(stack[i]); spin_unlock(&hslot->lock); + /* Also lookup *:port if we are using hash2 and haven't done so yet. */ + if (use_hash2 && hash2 != hash2_any) { + hash2 = hash2_any; + goto start_lookup; + } + if (count) { flush_stack(stack, count, skb, count - 1); - - for (i = 0; i < count; i++) - sock_put(stack[i]); } else { kfree_skb(skb); } diff --git a/net/irda/af_irda.c b/net/irda/af_irda.c index 54747c25c86c..92fafd485deb 100644 --- a/net/irda/af_irda.c +++ b/net/irda/af_irda.c @@ -674,7 +674,6 @@ static int irda_discover_daddr_and_lsap_sel(struct irda_sock *self, char *name) self->daddr = DEV_ADDR_ANY; kfree(discoveries); return -EHOSTUNREACH; - break; } } /* Cleanup our copy of the discovery log */ diff --git a/net/irda/irda_device.c b/net/irda/irda_device.c index 365b895da84b..9e0d909390fd 100644 --- a/net/irda/irda_device.c +++ b/net/irda/irda_device.c @@ -293,7 +293,8 @@ static void irda_device_setup(struct net_device *dev) */ struct net_device *alloc_irdadev(int sizeof_priv) { - return alloc_netdev(sizeof_priv, "irda%d", irda_device_setup); + return alloc_netdev(sizeof_priv, "irda%d", NET_NAME_UNKNOWN, + irda_device_setup); } EXPORT_SYMBOL(alloc_irdadev); diff --git a/net/irda/irlan/irlan_common.c b/net/irda/irlan/irlan_common.c index 7ac4d1becbfc..1bc49edf2296 100644 --- a/net/irda/irlan/irlan_common.c +++ b/net/irda/irlan/irlan_common.c @@ -1024,7 +1024,6 @@ static int __irlan_insert_param(struct sk_buff *skb, char *param, int type, default: IRDA_DEBUG(2, "%s(), Unknown parameter type!\n", __func__ ); return 0; - break; } /* Insert at end of sk-buffer */ diff --git a/net/irda/irlan/irlan_eth.c b/net/irda/irlan/irlan_eth.c index ffcec225b5d9..dc13f1a45f2f 100644 --- a/net/irda/irlan/irlan_eth.c +++ b/net/irda/irlan/irlan_eth.c @@ -96,7 +96,7 @@ static void irlan_eth_setup(struct net_device *dev) */ struct net_device *alloc_irlandev(const char *name) { - return alloc_netdev(sizeof(struct irlan_cb), name, + return alloc_netdev(sizeof(struct irlan_cb), name, NET_NAME_UNKNOWN, irlan_eth_setup); } diff --git a/net/irda/irlmp.c b/net/irda/irlmp.c index 98ad6ec4bd3c..a5f28d421ea8 100644 --- a/net/irda/irlmp.c +++ b/net/irda/irlmp.c @@ -1426,7 +1426,8 @@ __u8 *irlmp_hint_to_service(__u8 *hint) if (hint[1] & HINT_TELEPHONY) { IRDA_DEBUG(1, "Telephony "); service[i++] = S_TELEPHONY; - } if (hint[1] & HINT_FILE_SERVER) + } + if (hint[1] & HINT_FILE_SERVER) IRDA_DEBUG(1, "File Server "); if (hint[1] & HINT_COMM) { diff --git a/net/iucv/af_iucv.c b/net/iucv/af_iucv.c index 7a95fa4a3de1..a089b6b91650 100644 --- a/net/iucv/af_iucv.c +++ b/net/iucv/af_iucv.c @@ -1103,7 +1103,6 @@ static int iucv_sock_sendmsg(struct kiocb *iocb, struct socket *sock, default: err = -EINVAL; goto out; - break; } } @@ -1543,7 +1542,8 @@ static int iucv_sock_shutdown(struct socket *sock, int how) sk->sk_shutdown |= how; if (how == RCV_SHUTDOWN || how == SHUTDOWN_MASK) { - if (iucv->transport == AF_IUCV_TRANS_IUCV) { + if ((iucv->transport == AF_IUCV_TRANS_IUCV) && + iucv->path) { err = pr_iucv->path_quiesce(iucv->path, NULL); if (err) err = -ENOTCONN; diff --git a/net/key/af_key.c b/net/key/af_key.c index ba2a2f95911c..1847ec4e3930 100644 --- a/net/key/af_key.c +++ b/net/key/af_key.c @@ -405,7 +405,6 @@ static int verify_address_len(const void *p) * XXX When it can, remove this -EINVAL. -DaveM */ return -EINVAL; - break; } return 0; @@ -536,7 +535,6 @@ pfkey_satype2proto(uint8_t satype) return IPPROTO_ESP; case SADB_X_SATYPE_IPCOMP: return IPPROTO_COMP; - break; default: return 0; } @@ -553,7 +551,6 @@ pfkey_proto2satype(uint16_t proto) return SADB_SATYPE_ESP; case IPPROTO_COMP: return SADB_X_SATYPE_IPCOMP; - break; default: return 0; } diff --git a/net/l2tp/Kconfig b/net/l2tp/Kconfig index adb9843dd7cf..378c73b26093 100644 --- a/net/l2tp/Kconfig +++ b/net/l2tp/Kconfig @@ -6,6 +6,7 @@ menuconfig L2TP tristate "Layer Two Tunneling Protocol (L2TP)" depends on (IPV6 || IPV6=n) depends on INET + select NET_UDP_TUNNEL ---help--- Layer Two Tunneling Protocol diff --git a/net/l2tp/l2tp_core.c b/net/l2tp/l2tp_core.c index bea259043205..1109d3bb8dac 100644 --- a/net/l2tp/l2tp_core.c +++ b/net/l2tp/l2tp_core.c @@ -52,6 +52,7 @@ #include <net/dst.h> #include <net/ip.h> #include <net/udp.h> +#include <net/udp_tunnel.h> #include <net/inet_common.h> #include <net/xfrm.h> #include <net/protocol.h> @@ -1358,81 +1359,46 @@ static int l2tp_tunnel_sock_create(struct net *net, { int err = -EINVAL; struct socket *sock = NULL; - struct sockaddr_in udp_addr = {0}; - struct sockaddr_l2tpip ip_addr = {0}; -#if IS_ENABLED(CONFIG_IPV6) - struct sockaddr_in6 udp6_addr = {0}; - struct sockaddr_l2tpip6 ip6_addr = {0}; -#endif + struct udp_port_cfg udp_conf; switch (cfg->encap) { case L2TP_ENCAPTYPE_UDP: + memset(&udp_conf, 0, sizeof(udp_conf)); + #if IS_ENABLED(CONFIG_IPV6) if (cfg->local_ip6 && cfg->peer_ip6) { - err = sock_create_kern(AF_INET6, SOCK_DGRAM, 0, &sock); - if (err < 0) - goto out; - - sk_change_net(sock->sk, net); - - udp6_addr.sin6_family = AF_INET6; - memcpy(&udp6_addr.sin6_addr, cfg->local_ip6, - sizeof(udp6_addr.sin6_addr)); - udp6_addr.sin6_port = htons(cfg->local_udp_port); - err = kernel_bind(sock, (struct sockaddr *) &udp6_addr, - sizeof(udp6_addr)); - if (err < 0) - goto out; - - udp6_addr.sin6_family = AF_INET6; - memcpy(&udp6_addr.sin6_addr, cfg->peer_ip6, - sizeof(udp6_addr.sin6_addr)); - udp6_addr.sin6_port = htons(cfg->peer_udp_port); - err = kernel_connect(sock, - (struct sockaddr *) &udp6_addr, - sizeof(udp6_addr), 0); - if (err < 0) - goto out; - - if (cfg->udp6_zero_tx_checksums) - udp_set_no_check6_tx(sock->sk, true); - if (cfg->udp6_zero_rx_checksums) - udp_set_no_check6_rx(sock->sk, true); + udp_conf.family = AF_INET6; + memcpy(&udp_conf.local_ip6, cfg->local_ip6, + sizeof(udp_conf.local_ip6)); + memcpy(&udp_conf.peer_ip6, cfg->peer_ip6, + sizeof(udp_conf.peer_ip6)); + udp_conf.use_udp6_tx_checksums = + cfg->udp6_zero_tx_checksums; + udp_conf.use_udp6_rx_checksums = + cfg->udp6_zero_rx_checksums; } else #endif { - err = sock_create_kern(AF_INET, SOCK_DGRAM, 0, &sock); - if (err < 0) - goto out; - - sk_change_net(sock->sk, net); - - udp_addr.sin_family = AF_INET; - udp_addr.sin_addr = cfg->local_ip; - udp_addr.sin_port = htons(cfg->local_udp_port); - err = kernel_bind(sock, (struct sockaddr *) &udp_addr, - sizeof(udp_addr)); - if (err < 0) - goto out; - - udp_addr.sin_family = AF_INET; - udp_addr.sin_addr = cfg->peer_ip; - udp_addr.sin_port = htons(cfg->peer_udp_port); - err = kernel_connect(sock, - (struct sockaddr *) &udp_addr, - sizeof(udp_addr), 0); - if (err < 0) - goto out; + udp_conf.family = AF_INET; + udp_conf.local_ip = cfg->local_ip; + udp_conf.peer_ip = cfg->peer_ip; + udp_conf.use_udp_checksums = cfg->use_udp_checksums; } - if (!cfg->use_udp_checksums) - sock->sk->sk_no_check_tx = 1; + udp_conf.local_udp_port = htons(cfg->local_udp_port); + udp_conf.peer_udp_port = htons(cfg->peer_udp_port); + + err = udp_sock_create(net, &udp_conf, &sock); + if (err < 0) + goto out; break; case L2TP_ENCAPTYPE_IP: #if IS_ENABLED(CONFIG_IPV6) if (cfg->local_ip6 && cfg->peer_ip6) { + struct sockaddr_l2tpip6 ip6_addr = {0}; + err = sock_create_kern(AF_INET6, SOCK_DGRAM, IPPROTO_L2TP, &sock); if (err < 0) @@ -1461,6 +1427,8 @@ static int l2tp_tunnel_sock_create(struct net *net, } else #endif { + struct sockaddr_l2tpip ip_addr = {0}; + err = sock_create_kern(AF_INET, SOCK_DGRAM, IPPROTO_L2TP, &sock); if (err < 0) diff --git a/net/l2tp/l2tp_eth.c b/net/l2tp/l2tp_eth.c index 76125c57ee6d..edb78e69efe4 100644 --- a/net/l2tp/l2tp_eth.c +++ b/net/l2tp/l2tp_eth.c @@ -246,7 +246,8 @@ static int l2tp_eth_create(struct net *net, u32 tunnel_id, u32 session_id, u32 p goto out; } - dev = alloc_netdev(sizeof(*priv), name, l2tp_eth_dev_setup); + dev = alloc_netdev(sizeof(*priv), name, NET_NAME_UNKNOWN, + l2tp_eth_dev_setup); if (!dev) { rc = -ENOMEM; goto out_del_session; diff --git a/net/l2tp/l2tp_ip6.c b/net/l2tp/l2tp_ip6.c index f3f98a156cee..0edb263cc002 100644 --- a/net/l2tp/l2tp_ip6.c +++ b/net/l2tp/l2tp_ip6.c @@ -687,7 +687,7 @@ static int l2tp_ip6_recvmsg(struct kiocb *iocb, struct sock *sk, lsa->l2tp_scope_id = 0; lsa->l2tp_conn_id = 0; if (ipv6_addr_type(&lsa->l2tp_addr) & IPV6_ADDR_LINKLOCAL) - lsa->l2tp_scope_id = IP6CB(skb)->iif; + lsa->l2tp_scope_id = inet6_iif(skb); } if (np->rxopt.all) diff --git a/net/mac80211/Kconfig b/net/mac80211/Kconfig index 97b5dcad5025..aeb6a483b3bc 100644 --- a/net/mac80211/Kconfig +++ b/net/mac80211/Kconfig @@ -19,14 +19,6 @@ if MAC80211 != n config MAC80211_HAS_RC bool -config MAC80211_RC_PID - bool "PID controller based rate control algorithm" if EXPERT - select MAC80211_HAS_RC - ---help--- - This option enables a TX rate control algorithm for - mac80211 that uses a PID controller to select the TX - rate. - config MAC80211_RC_MINSTREL bool "Minstrel" if EXPERT select MAC80211_HAS_RC @@ -51,14 +43,6 @@ choice overridden through the ieee80211_default_rc_algo module parameter if different algorithms are available. -config MAC80211_RC_DEFAULT_PID - bool "PID controller based rate control algorithm" - depends on MAC80211_RC_PID - ---help--- - Select the PID controller based rate control as the - default rate control algorithm. You should choose - this unless you know what you are doing. - config MAC80211_RC_DEFAULT_MINSTREL bool "Minstrel" depends on MAC80211_RC_MINSTREL @@ -72,7 +56,6 @@ config MAC80211_RC_DEFAULT string default "minstrel_ht" if MAC80211_RC_DEFAULT_MINSTREL && MAC80211_RC_MINSTREL_HT default "minstrel" if MAC80211_RC_DEFAULT_MINSTREL - default "pid" if MAC80211_RC_DEFAULT_PID default "" endif diff --git a/net/mac80211/Makefile b/net/mac80211/Makefile index 1e46ffa69167..7273d2796dd1 100644 --- a/net/mac80211/Makefile +++ b/net/mac80211/Makefile @@ -17,6 +17,7 @@ mac80211-y := \ aes_ccm.o \ aes_cmac.o \ cfg.o \ + ethtool.o \ rx.o \ spectmgmt.o \ tx.o \ @@ -47,17 +48,12 @@ mac80211-$(CONFIG_PM) += pm.o CFLAGS_trace.o := -I$(src) -# objects for PID algorithm -rc80211_pid-y := rc80211_pid_algo.o -rc80211_pid-$(CONFIG_MAC80211_DEBUGFS) += rc80211_pid_debugfs.o - rc80211_minstrel-y := rc80211_minstrel.o rc80211_minstrel-$(CONFIG_MAC80211_DEBUGFS) += rc80211_minstrel_debugfs.o rc80211_minstrel_ht-y := rc80211_minstrel_ht.o rc80211_minstrel_ht-$(CONFIG_MAC80211_DEBUGFS) += rc80211_minstrel_ht_debugfs.o -mac80211-$(CONFIG_MAC80211_RC_PID) += $(rc80211_pid-y) mac80211-$(CONFIG_MAC80211_RC_MINSTREL) += $(rc80211_minstrel-y) mac80211-$(CONFIG_MAC80211_RC_MINSTREL_HT) += $(rc80211_minstrel_ht-y) diff --git a/net/mac80211/agg-rx.c b/net/mac80211/agg-rx.c index 31bf2586fb84..f0e84bc48038 100644 --- a/net/mac80211/agg-rx.c +++ b/net/mac80211/agg-rx.c @@ -52,7 +52,7 @@ static void ieee80211_free_tid_rx(struct rcu_head *h) del_timer_sync(&tid_rx->reorder_timer); for (i = 0; i < tid_rx->buf_size; i++) - dev_kfree_skb(tid_rx->reorder_buf[i]); + __skb_queue_purge(&tid_rx->reorder_buf[i]); kfree(tid_rx->reorder_buf); kfree(tid_rx->reorder_time); kfree(tid_rx); @@ -224,28 +224,15 @@ static void ieee80211_send_addba_resp(struct ieee80211_sub_if_data *sdata, u8 *d ieee80211_tx_skb(sdata, skb); } -void ieee80211_process_addba_request(struct ieee80211_local *local, - struct sta_info *sta, - struct ieee80211_mgmt *mgmt, - size_t len) +void __ieee80211_start_rx_ba_session(struct sta_info *sta, + u8 dialog_token, u16 timeout, + u16 start_seq_num, u16 ba_policy, u16 tid, + u16 buf_size, bool tx) { + struct ieee80211_local *local = sta->sdata->local; struct tid_ampdu_rx *tid_agg_rx; - u16 capab, tid, timeout, ba_policy, buf_size, start_seq_num, status; - u8 dialog_token; - int ret = -EOPNOTSUPP; - - /* extract session parameters from addba request frame */ - dialog_token = mgmt->u.action.u.addba_req.dialog_token; - timeout = le16_to_cpu(mgmt->u.action.u.addba_req.timeout); - start_seq_num = - le16_to_cpu(mgmt->u.action.u.addba_req.start_seq_num) >> 4; - - capab = le16_to_cpu(mgmt->u.action.u.addba_req.capab); - ba_policy = (capab & IEEE80211_ADDBA_PARAM_POLICY_MASK) >> 1; - tid = (capab & IEEE80211_ADDBA_PARAM_TID_MASK) >> 2; - buf_size = (capab & IEEE80211_ADDBA_PARAM_BUF_SIZE_MASK) >> 6; - - status = WLAN_STATUS_REQUEST_DECLINED; + int i, ret = -EOPNOTSUPP; + u16 status = WLAN_STATUS_REQUEST_DECLINED; if (test_sta_flag(sta, WLAN_STA_BLOCK_BA)) { ht_dbg(sta->sdata, @@ -264,7 +251,7 @@ void ieee80211_process_addba_request(struct ieee80211_local *local, status = WLAN_STATUS_INVALID_QOS_PARAM; ht_dbg_ratelimited(sta->sdata, "AddBA Req with bad params from %pM on tid %u. policy %d, buffer size %d\n", - mgmt->sa, tid, ba_policy, buf_size); + sta->sta.addr, tid, ba_policy, buf_size); goto end_no_lock; } /* determine default buffer size */ @@ -281,7 +268,7 @@ void ieee80211_process_addba_request(struct ieee80211_local *local, if (sta->ampdu_mlme.tid_rx[tid]) { ht_dbg_ratelimited(sta->sdata, "unexpected AddBA Req from %pM on tid %u\n", - mgmt->sa, tid); + sta->sta.addr, tid); /* delete existing Rx BA session on the same tid */ ___ieee80211_stop_rx_ba_session(sta, tid, WLAN_BACK_RECIPIENT, @@ -308,7 +295,7 @@ void ieee80211_process_addba_request(struct ieee80211_local *local, /* prepare reordering buffer */ tid_agg_rx->reorder_buf = - kcalloc(buf_size, sizeof(struct sk_buff *), GFP_KERNEL); + kcalloc(buf_size, sizeof(struct sk_buff_head), GFP_KERNEL); tid_agg_rx->reorder_time = kcalloc(buf_size, sizeof(unsigned long), GFP_KERNEL); if (!tid_agg_rx->reorder_buf || !tid_agg_rx->reorder_time) { @@ -318,6 +305,9 @@ void ieee80211_process_addba_request(struct ieee80211_local *local, goto end; } + for (i = 0; i < buf_size; i++) + __skb_queue_head_init(&tid_agg_rx->reorder_buf[i]); + ret = drv_ampdu_action(local, sta->sdata, IEEE80211_AMPDU_RX_START, &sta->sta, tid, &start_seq_num, 0); ht_dbg(sta->sdata, "Rx A-MPDU request on %pM tid %d result %d\n", @@ -350,6 +340,74 @@ end: mutex_unlock(&sta->ampdu_mlme.mtx); end_no_lock: - ieee80211_send_addba_resp(sta->sdata, sta->sta.addr, tid, - dialog_token, status, 1, buf_size, timeout); + if (tx) + ieee80211_send_addba_resp(sta->sdata, sta->sta.addr, tid, + dialog_token, status, 1, buf_size, + timeout); +} + +void ieee80211_process_addba_request(struct ieee80211_local *local, + struct sta_info *sta, + struct ieee80211_mgmt *mgmt, + size_t len) +{ + u16 capab, tid, timeout, ba_policy, buf_size, start_seq_num; + u8 dialog_token; + + /* extract session parameters from addba request frame */ + dialog_token = mgmt->u.action.u.addba_req.dialog_token; + timeout = le16_to_cpu(mgmt->u.action.u.addba_req.timeout); + start_seq_num = + le16_to_cpu(mgmt->u.action.u.addba_req.start_seq_num) >> 4; + + capab = le16_to_cpu(mgmt->u.action.u.addba_req.capab); + ba_policy = (capab & IEEE80211_ADDBA_PARAM_POLICY_MASK) >> 1; + tid = (capab & IEEE80211_ADDBA_PARAM_TID_MASK) >> 2; + buf_size = (capab & IEEE80211_ADDBA_PARAM_BUF_SIZE_MASK) >> 6; + + __ieee80211_start_rx_ba_session(sta, dialog_token, timeout, + start_seq_num, ba_policy, tid, + buf_size, true); +} + +void ieee80211_start_rx_ba_session_offl(struct ieee80211_vif *vif, + const u8 *addr, u16 tid) +{ + struct ieee80211_sub_if_data *sdata = vif_to_sdata(vif); + struct ieee80211_local *local = sdata->local; + struct ieee80211_rx_agg *rx_agg; + struct sk_buff *skb = dev_alloc_skb(0); + + if (unlikely(!skb)) + return; + + rx_agg = (struct ieee80211_rx_agg *) &skb->cb; + memcpy(&rx_agg->addr, addr, ETH_ALEN); + rx_agg->tid = tid; + + skb->pkt_type = IEEE80211_SDATA_QUEUE_RX_AGG_START; + skb_queue_tail(&sdata->skb_queue, skb); + ieee80211_queue_work(&local->hw, &sdata->work); +} +EXPORT_SYMBOL(ieee80211_start_rx_ba_session_offl); + +void ieee80211_stop_rx_ba_session_offl(struct ieee80211_vif *vif, + const u8 *addr, u16 tid) +{ + struct ieee80211_sub_if_data *sdata = vif_to_sdata(vif); + struct ieee80211_local *local = sdata->local; + struct ieee80211_rx_agg *rx_agg; + struct sk_buff *skb = dev_alloc_skb(0); + + if (unlikely(!skb)) + return; + + rx_agg = (struct ieee80211_rx_agg *) &skb->cb; + memcpy(&rx_agg->addr, addr, ETH_ALEN); + rx_agg->tid = tid; + + skb->pkt_type = IEEE80211_SDATA_QUEUE_RX_AGG_STOP; + skb_queue_tail(&sdata->skb_queue, skb); + ieee80211_queue_work(&local->hw, &sdata->work); } +EXPORT_SYMBOL(ieee80211_stop_rx_ba_session_offl); diff --git a/net/mac80211/agg-tx.c b/net/mac80211/agg-tx.c index ce9633a3cfb0..d6986f3aa5c4 100644 --- a/net/mac80211/agg-tx.c +++ b/net/mac80211/agg-tx.c @@ -170,10 +170,13 @@ ieee80211_stop_queue_agg(struct ieee80211_sub_if_data *sdata, int tid) { int queue = sdata->vif.hw_queue[ieee80211_ac_from_tid(tid)]; + /* we do refcounting here, so don't use the queue reason refcounting */ + if (atomic_inc_return(&sdata->local->agg_queue_stop[queue]) == 1) ieee80211_stop_queue_by_reason( &sdata->local->hw, queue, - IEEE80211_QUEUE_STOP_REASON_AGGREGATION); + IEEE80211_QUEUE_STOP_REASON_AGGREGATION, + false); __acquire(agg_queue); } @@ -185,7 +188,8 @@ ieee80211_wake_queue_agg(struct ieee80211_sub_if_data *sdata, int tid) if (atomic_dec_return(&sdata->local->agg_queue_stop[queue]) == 0) ieee80211_wake_queue_by_reason( &sdata->local->hw, queue, - IEEE80211_QUEUE_STOP_REASON_AGGREGATION); + IEEE80211_QUEUE_STOP_REASON_AGGREGATION, + false); __release(agg_queue); } diff --git a/net/mac80211/cfg.c b/net/mac80211/cfg.c index 592f4b152ba8..927b4ea0128b 100644 --- a/net/mac80211/cfg.c +++ b/net/mac80211/cfg.c @@ -468,330 +468,6 @@ void sta_set_rate_info_rx(struct sta_info *sta, struct rate_info *rinfo) rinfo->flags |= RATE_INFO_FLAGS_160_MHZ_WIDTH; } -static void sta_set_sinfo(struct sta_info *sta, struct station_info *sinfo) -{ - struct ieee80211_sub_if_data *sdata = sta->sdata; - struct ieee80211_local *local = sdata->local; - struct rate_control_ref *ref = NULL; - struct timespec uptime; - u64 packets = 0; - u32 thr = 0; - int i, ac; - - if (test_sta_flag(sta, WLAN_STA_RATE_CONTROL)) - ref = local->rate_ctrl; - - sinfo->generation = sdata->local->sta_generation; - - sinfo->filled = STATION_INFO_INACTIVE_TIME | - STATION_INFO_RX_BYTES64 | - STATION_INFO_TX_BYTES64 | - STATION_INFO_RX_PACKETS | - STATION_INFO_TX_PACKETS | - STATION_INFO_TX_RETRIES | - STATION_INFO_TX_FAILED | - STATION_INFO_TX_BITRATE | - STATION_INFO_RX_BITRATE | - STATION_INFO_RX_DROP_MISC | - STATION_INFO_BSS_PARAM | - STATION_INFO_CONNECTED_TIME | - STATION_INFO_STA_FLAGS | - STATION_INFO_BEACON_LOSS_COUNT; - - do_posix_clock_monotonic_gettime(&uptime); - sinfo->connected_time = uptime.tv_sec - sta->last_connected; - - sinfo->inactive_time = jiffies_to_msecs(jiffies - sta->last_rx); - sinfo->tx_bytes = 0; - for (ac = 0; ac < IEEE80211_NUM_ACS; ac++) { - sinfo->tx_bytes += sta->tx_bytes[ac]; - packets += sta->tx_packets[ac]; - } - sinfo->tx_packets = packets; - sinfo->rx_bytes = sta->rx_bytes; - sinfo->rx_packets = sta->rx_packets; - sinfo->tx_retries = sta->tx_retry_count; - sinfo->tx_failed = sta->tx_retry_failed; - sinfo->rx_dropped_misc = sta->rx_dropped; - sinfo->beacon_loss_count = sta->beacon_loss_count; - - if ((sta->local->hw.flags & IEEE80211_HW_SIGNAL_DBM) || - (sta->local->hw.flags & IEEE80211_HW_SIGNAL_UNSPEC)) { - sinfo->filled |= STATION_INFO_SIGNAL | STATION_INFO_SIGNAL_AVG; - if (!local->ops->get_rssi || - drv_get_rssi(local, sdata, &sta->sta, &sinfo->signal)) - sinfo->signal = (s8)sta->last_signal; - sinfo->signal_avg = (s8) -ewma_read(&sta->avg_signal); - } - if (sta->chains) { - sinfo->filled |= STATION_INFO_CHAIN_SIGNAL | - STATION_INFO_CHAIN_SIGNAL_AVG; - - sinfo->chains = sta->chains; - for (i = 0; i < ARRAY_SIZE(sinfo->chain_signal); i++) { - sinfo->chain_signal[i] = sta->chain_signal_last[i]; - sinfo->chain_signal_avg[i] = - (s8) -ewma_read(&sta->chain_signal_avg[i]); - } - } - - sta_set_rate_info_tx(sta, &sta->last_tx_rate, &sinfo->txrate); - sta_set_rate_info_rx(sta, &sinfo->rxrate); - - if (ieee80211_vif_is_mesh(&sdata->vif)) { -#ifdef CONFIG_MAC80211_MESH - sinfo->filled |= STATION_INFO_LLID | - STATION_INFO_PLID | - STATION_INFO_PLINK_STATE | - STATION_INFO_LOCAL_PM | - STATION_INFO_PEER_PM | - STATION_INFO_NONPEER_PM; - - sinfo->llid = sta->llid; - sinfo->plid = sta->plid; - sinfo->plink_state = sta->plink_state; - if (test_sta_flag(sta, WLAN_STA_TOFFSET_KNOWN)) { - sinfo->filled |= STATION_INFO_T_OFFSET; - sinfo->t_offset = sta->t_offset; - } - sinfo->local_pm = sta->local_pm; - sinfo->peer_pm = sta->peer_pm; - sinfo->nonpeer_pm = sta->nonpeer_pm; -#endif - } - - sinfo->bss_param.flags = 0; - if (sdata->vif.bss_conf.use_cts_prot) - sinfo->bss_param.flags |= BSS_PARAM_FLAGS_CTS_PROT; - if (sdata->vif.bss_conf.use_short_preamble) - sinfo->bss_param.flags |= BSS_PARAM_FLAGS_SHORT_PREAMBLE; - if (sdata->vif.bss_conf.use_short_slot) - sinfo->bss_param.flags |= BSS_PARAM_FLAGS_SHORT_SLOT_TIME; - sinfo->bss_param.dtim_period = sdata->local->hw.conf.ps_dtim_period; - sinfo->bss_param.beacon_interval = sdata->vif.bss_conf.beacon_int; - - sinfo->sta_flags.set = 0; - sinfo->sta_flags.mask = BIT(NL80211_STA_FLAG_AUTHORIZED) | - BIT(NL80211_STA_FLAG_SHORT_PREAMBLE) | - BIT(NL80211_STA_FLAG_WME) | - BIT(NL80211_STA_FLAG_MFP) | - BIT(NL80211_STA_FLAG_AUTHENTICATED) | - BIT(NL80211_STA_FLAG_ASSOCIATED) | - BIT(NL80211_STA_FLAG_TDLS_PEER); - if (test_sta_flag(sta, WLAN_STA_AUTHORIZED)) - sinfo->sta_flags.set |= BIT(NL80211_STA_FLAG_AUTHORIZED); - if (test_sta_flag(sta, WLAN_STA_SHORT_PREAMBLE)) - sinfo->sta_flags.set |= BIT(NL80211_STA_FLAG_SHORT_PREAMBLE); - if (test_sta_flag(sta, WLAN_STA_WME)) - sinfo->sta_flags.set |= BIT(NL80211_STA_FLAG_WME); - if (test_sta_flag(sta, WLAN_STA_MFP)) - sinfo->sta_flags.set |= BIT(NL80211_STA_FLAG_MFP); - if (test_sta_flag(sta, WLAN_STA_AUTH)) - sinfo->sta_flags.set |= BIT(NL80211_STA_FLAG_AUTHENTICATED); - if (test_sta_flag(sta, WLAN_STA_ASSOC)) - sinfo->sta_flags.set |= BIT(NL80211_STA_FLAG_ASSOCIATED); - if (test_sta_flag(sta, WLAN_STA_TDLS_PEER)) - sinfo->sta_flags.set |= BIT(NL80211_STA_FLAG_TDLS_PEER); - - /* check if the driver has a SW RC implementation */ - if (ref && ref->ops->get_expected_throughput) - thr = ref->ops->get_expected_throughput(sta->rate_ctrl_priv); - else - thr = drv_get_expected_throughput(local, &sta->sta); - - if (thr != 0) { - sinfo->filled |= STATION_INFO_EXPECTED_THROUGHPUT; - sinfo->expected_throughput = thr; - } -} - -static const char ieee80211_gstrings_sta_stats[][ETH_GSTRING_LEN] = { - "rx_packets", "rx_bytes", "wep_weak_iv_count", - "rx_duplicates", "rx_fragments", "rx_dropped", - "tx_packets", "tx_bytes", "tx_fragments", - "tx_filtered", "tx_retry_failed", "tx_retries", - "beacon_loss", "sta_state", "txrate", "rxrate", "signal", - "channel", "noise", "ch_time", "ch_time_busy", - "ch_time_ext_busy", "ch_time_rx", "ch_time_tx" -}; -#define STA_STATS_LEN ARRAY_SIZE(ieee80211_gstrings_sta_stats) - -static int ieee80211_get_et_sset_count(struct wiphy *wiphy, - struct net_device *dev, - int sset) -{ - struct ieee80211_sub_if_data *sdata = IEEE80211_DEV_TO_SUB_IF(dev); - int rv = 0; - - if (sset == ETH_SS_STATS) - rv += STA_STATS_LEN; - - rv += drv_get_et_sset_count(sdata, sset); - - if (rv == 0) - return -EOPNOTSUPP; - return rv; -} - -static void ieee80211_get_et_stats(struct wiphy *wiphy, - struct net_device *dev, - struct ethtool_stats *stats, - u64 *data) -{ - struct ieee80211_sub_if_data *sdata = IEEE80211_DEV_TO_SUB_IF(dev); - struct ieee80211_chanctx_conf *chanctx_conf; - struct ieee80211_channel *channel; - struct sta_info *sta; - struct ieee80211_local *local = sdata->local; - struct station_info sinfo; - struct survey_info survey; - int i, q; -#define STA_STATS_SURVEY_LEN 7 - - memset(data, 0, sizeof(u64) * STA_STATS_LEN); - -#define ADD_STA_STATS(sta) \ - do { \ - data[i++] += sta->rx_packets; \ - data[i++] += sta->rx_bytes; \ - data[i++] += sta->wep_weak_iv_count; \ - data[i++] += sta->num_duplicates; \ - data[i++] += sta->rx_fragments; \ - data[i++] += sta->rx_dropped; \ - \ - data[i++] += sinfo.tx_packets; \ - data[i++] += sinfo.tx_bytes; \ - data[i++] += sta->tx_fragments; \ - data[i++] += sta->tx_filtered_count; \ - data[i++] += sta->tx_retry_failed; \ - data[i++] += sta->tx_retry_count; \ - data[i++] += sta->beacon_loss_count; \ - } while (0) - - /* For Managed stations, find the single station based on BSSID - * and use that. For interface types, iterate through all available - * stations and add stats for any station that is assigned to this - * network device. - */ - - mutex_lock(&local->sta_mtx); - - if (sdata->vif.type == NL80211_IFTYPE_STATION) { - sta = sta_info_get_bss(sdata, sdata->u.mgd.bssid); - - if (!(sta && !WARN_ON(sta->sdata->dev != dev))) - goto do_survey; - - sinfo.filled = 0; - sta_set_sinfo(sta, &sinfo); - - i = 0; - ADD_STA_STATS(sta); - - data[i++] = sta->sta_state; - - - if (sinfo.filled & STATION_INFO_TX_BITRATE) - data[i] = 100000 * - cfg80211_calculate_bitrate(&sinfo.txrate); - i++; - if (sinfo.filled & STATION_INFO_RX_BITRATE) - data[i] = 100000 * - cfg80211_calculate_bitrate(&sinfo.rxrate); - i++; - - if (sinfo.filled & STATION_INFO_SIGNAL_AVG) - data[i] = (u8)sinfo.signal_avg; - i++; - } else { - list_for_each_entry(sta, &local->sta_list, list) { - /* Make sure this station belongs to the proper dev */ - if (sta->sdata->dev != dev) - continue; - - sinfo.filled = 0; - sta_set_sinfo(sta, &sinfo); - i = 0; - ADD_STA_STATS(sta); - } - } - -do_survey: - i = STA_STATS_LEN - STA_STATS_SURVEY_LEN; - /* Get survey stats for current channel */ - survey.filled = 0; - - rcu_read_lock(); - chanctx_conf = rcu_dereference(sdata->vif.chanctx_conf); - if (chanctx_conf) - channel = chanctx_conf->def.chan; - else - channel = NULL; - rcu_read_unlock(); - - if (channel) { - q = 0; - do { - survey.filled = 0; - if (drv_get_survey(local, q, &survey) != 0) { - survey.filled = 0; - break; - } - q++; - } while (channel != survey.channel); - } - - if (survey.filled) - data[i++] = survey.channel->center_freq; - else - data[i++] = 0; - if (survey.filled & SURVEY_INFO_NOISE_DBM) - data[i++] = (u8)survey.noise; - else - data[i++] = -1LL; - if (survey.filled & SURVEY_INFO_CHANNEL_TIME) - data[i++] = survey.channel_time; - else - data[i++] = -1LL; - if (survey.filled & SURVEY_INFO_CHANNEL_TIME_BUSY) - data[i++] = survey.channel_time_busy; - else - data[i++] = -1LL; - if (survey.filled & SURVEY_INFO_CHANNEL_TIME_EXT_BUSY) - data[i++] = survey.channel_time_ext_busy; - else - data[i++] = -1LL; - if (survey.filled & SURVEY_INFO_CHANNEL_TIME_RX) - data[i++] = survey.channel_time_rx; - else - data[i++] = -1LL; - if (survey.filled & SURVEY_INFO_CHANNEL_TIME_TX) - data[i++] = survey.channel_time_tx; - else - data[i++] = -1LL; - - mutex_unlock(&local->sta_mtx); - - if (WARN_ON(i != STA_STATS_LEN)) - return; - - drv_get_et_stats(sdata, stats, &(data[STA_STATS_LEN])); -} - -static void ieee80211_get_et_strings(struct wiphy *wiphy, - struct net_device *dev, - u32 sset, u8 *data) -{ - struct ieee80211_sub_if_data *sdata = IEEE80211_DEV_TO_SUB_IF(dev); - int sz_sta_stats = 0; - - if (sset == ETH_SS_STATS) { - sz_sta_stats = sizeof(ieee80211_gstrings_sta_stats); - memcpy(data, ieee80211_gstrings_sta_stats, sz_sta_stats); - } - drv_get_et_strings(sdata, sset, &(data[sz_sta_stats])); -} - static int ieee80211_dump_station(struct wiphy *wiphy, struct net_device *dev, int idx, u8 *mac, struct station_info *sinfo) { @@ -878,7 +554,8 @@ static int ieee80211_set_monitor_channel(struct wiphy *wiphy, } static int ieee80211_set_probe_resp(struct ieee80211_sub_if_data *sdata, - const u8 *resp, size_t resp_len) + const u8 *resp, size_t resp_len, + const struct ieee80211_csa_settings *csa) { struct probe_resp *new, *old; @@ -894,6 +571,11 @@ static int ieee80211_set_probe_resp(struct ieee80211_sub_if_data *sdata, new->len = resp_len; memcpy(new->data, resp, resp_len); + if (csa) + memcpy(new->csa_counter_offsets, csa->counter_offsets_presp, + csa->n_counter_offsets_presp * + sizeof(new->csa_counter_offsets[0])); + rcu_assign_pointer(sdata->u.ap.probe_resp, new); if (old) kfree_rcu(old, rcu_head); @@ -902,7 +584,8 @@ static int ieee80211_set_probe_resp(struct ieee80211_sub_if_data *sdata, } static int ieee80211_assign_beacon(struct ieee80211_sub_if_data *sdata, - struct cfg80211_beacon_data *params) + struct cfg80211_beacon_data *params, + const struct ieee80211_csa_settings *csa) { struct beacon_data *new, *old; int new_head_len, new_tail_len; @@ -946,6 +629,13 @@ static int ieee80211_assign_beacon(struct ieee80211_sub_if_data *sdata, new->head_len = new_head_len; new->tail_len = new_tail_len; + if (csa) { + new->csa_current_counter = csa->count; + memcpy(new->csa_counter_offsets, csa->counter_offsets_beacon, + csa->n_counter_offsets_beacon * + sizeof(new->csa_counter_offsets[0])); + } + /* copy in head */ if (params->head) memcpy(new->head, params->head, new_head_len); @@ -960,7 +650,7 @@ static int ieee80211_assign_beacon(struct ieee80211_sub_if_data *sdata, memcpy(new->tail, old->tail, new_tail_len); err = ieee80211_set_probe_resp(sdata, params->probe_resp, - params->probe_resp_len); + params->probe_resp_len, csa); if (err < 0) return err; if (err == 0) @@ -1045,7 +735,7 @@ static int ieee80211_start_ap(struct wiphy *wiphy, struct net_device *dev, sdata->vif.bss_conf.p2p_noa_attr.oppps_ctwindow |= IEEE80211_P2P_OPPPS_ENABLE_BIT; - err = ieee80211_assign_beacon(sdata, ¶ms->beacon); + err = ieee80211_assign_beacon(sdata, ¶ms->beacon, NULL); if (err < 0) { ieee80211_vif_release_channel(sdata); return err; @@ -1093,38 +783,13 @@ static int ieee80211_change_beacon(struct wiphy *wiphy, struct net_device *dev, if (!old) return -ENOENT; - err = ieee80211_assign_beacon(sdata, params); + err = ieee80211_assign_beacon(sdata, params, NULL); if (err < 0) return err; ieee80211_bss_info_change_notify(sdata, err); return 0; } -bool ieee80211_csa_needs_block_tx(struct ieee80211_local *local) -{ - struct ieee80211_sub_if_data *sdata; - - lockdep_assert_held(&local->mtx); - - rcu_read_lock(); - list_for_each_entry_rcu(sdata, &local->interfaces, list) { - if (!ieee80211_sdata_running(sdata)) - continue; - - if (!sdata->vif.csa_active) - continue; - - if (!sdata->csa_block_tx) - continue; - - rcu_read_unlock(); - return true; - } - rcu_read_unlock(); - - return false; -} - static int ieee80211_stop_ap(struct wiphy *wiphy, struct net_device *dev) { struct ieee80211_sub_if_data *sdata = IEEE80211_DEV_TO_SUB_IF(dev); @@ -1144,10 +809,12 @@ static int ieee80211_stop_ap(struct wiphy *wiphy, struct net_device *dev) /* abort any running channel switch */ mutex_lock(&local->mtx); sdata->vif.csa_active = false; - if (!ieee80211_csa_needs_block_tx(local)) - ieee80211_wake_queues_by_reason(&local->hw, - IEEE80211_MAX_QUEUE_MAP, - IEEE80211_QUEUE_STOP_REASON_CSA); + if (sdata->csa_block_tx) { + ieee80211_wake_vif_queues(local, sdata, + IEEE80211_QUEUE_STOP_REASON_CSA); + sdata->csa_block_tx = false; + } + mutex_unlock(&local->mtx); kfree(sdata->u.ap.next_beacon); @@ -1330,9 +997,12 @@ static int sta_apply_parameters(struct ieee80211_local *local, } } - ret = sta_apply_auth_flags(local, sta, mask, set); - if (ret) - return ret; + /* auth flags will be set later for TDLS stations */ + if (!test_sta_flag(sta, WLAN_STA_TDLS_PEER)) { + ret = sta_apply_auth_flags(local, sta, mask, set); + if (ret) + return ret; + } if (mask & BIT(NL80211_STA_FLAG_SHORT_PREAMBLE)) { if (set & BIT(NL80211_STA_FLAG_SHORT_PREAMBLE)) @@ -1469,6 +1139,13 @@ static int sta_apply_parameters(struct ieee80211_local *local, #endif } + /* set the STA state after all sta info from usermode has been set */ + if (test_sta_flag(sta, WLAN_STA_TDLS_PEER)) { + ret = sta_apply_auth_flags(local, sta, mask, set); + if (ret) + return ret; + } + return 0; } @@ -3076,7 +2753,8 @@ static int ieee80211_set_after_csa_beacon(struct ieee80211_sub_if_data *sdata, switch (sdata->vif.type) { case NL80211_IFTYPE_AP: - err = ieee80211_assign_beacon(sdata, sdata->u.ap.next_beacon); + err = ieee80211_assign_beacon(sdata, sdata->u.ap.next_beacon, + NULL); kfree(sdata->u.ap.next_beacon); sdata->u.ap.next_beacon = NULL; @@ -3114,17 +2792,35 @@ static int __ieee80211_csa_finalize(struct ieee80211_sub_if_data *sdata) sdata_assert_lock(sdata); lockdep_assert_held(&local->mtx); + lockdep_assert_held(&local->chanctx_mtx); - sdata->radar_required = sdata->csa_radar_required; - err = ieee80211_vif_change_channel(sdata, &changed); - if (err < 0) - return err; + /* + * using reservation isn't immediate as it may be deferred until later + * with multi-vif. once reservation is complete it will re-schedule the + * work with no reserved_chanctx so verify chandef to check if it + * completed successfully + */ - if (!local->use_chanctx) { - local->_oper_chandef = sdata->csa_chandef; - ieee80211_hw_config(local, 0); + if (sdata->reserved_chanctx) { + /* + * with multi-vif csa driver may call ieee80211_csa_finish() + * many times while waiting for other interfaces to use their + * reservations + */ + if (sdata->reserved_ready) + return 0; + + err = ieee80211_vif_use_reserved_context(sdata); + if (err) + return err; + + return 0; } + if (!cfg80211_chandef_identical(&sdata->vif.bss_conf.chandef, + &sdata->csa_chandef)) + return -EINVAL; + sdata->vif.csa_active = false; err = ieee80211_set_after_csa_beacon(sdata, &changed); @@ -3134,10 +2830,11 @@ static int __ieee80211_csa_finalize(struct ieee80211_sub_if_data *sdata) ieee80211_bss_info_change_notify(sdata, changed); cfg80211_ch_switch_notify(sdata->dev, &sdata->csa_chandef); - if (!ieee80211_csa_needs_block_tx(local)) - ieee80211_wake_queues_by_reason(&local->hw, - IEEE80211_MAX_QUEUE_MAP, - IEEE80211_QUEUE_STOP_REASON_CSA); + if (sdata->csa_block_tx) { + ieee80211_wake_vif_queues(local, sdata, + IEEE80211_QUEUE_STOP_REASON_CSA); + sdata->csa_block_tx = false; + } return 0; } @@ -3160,6 +2857,7 @@ void ieee80211_csa_finalize_work(struct work_struct *work) sdata_lock(sdata); mutex_lock(&local->mtx); + mutex_lock(&local->chanctx_mtx); /* AP might have been stopped while waiting for the lock. */ if (!sdata->vif.csa_active) @@ -3171,6 +2869,7 @@ void ieee80211_csa_finalize_work(struct work_struct *work) ieee80211_csa_finalize(sdata); unlock: + mutex_unlock(&local->chanctx_mtx); mutex_unlock(&local->mtx); sdata_unlock(sdata); } @@ -3179,6 +2878,7 @@ static int ieee80211_set_csa_beacon(struct ieee80211_sub_if_data *sdata, struct cfg80211_csa_settings *params, u32 *changed) { + struct ieee80211_csa_settings csa = {}; int err; switch (sdata->vif.type) { @@ -3213,20 +2913,13 @@ static int ieee80211_set_csa_beacon(struct ieee80211_sub_if_data *sdata, IEEE80211_MAX_CSA_COUNTERS_NUM)) return -EINVAL; - /* make sure we don't have garbage in other counters */ - memset(sdata->csa_counter_offset_beacon, 0, - sizeof(sdata->csa_counter_offset_beacon)); - memset(sdata->csa_counter_offset_presp, 0, - sizeof(sdata->csa_counter_offset_presp)); - - memcpy(sdata->csa_counter_offset_beacon, - params->counter_offsets_beacon, - params->n_counter_offsets_beacon * sizeof(u16)); - memcpy(sdata->csa_counter_offset_presp, - params->counter_offsets_presp, - params->n_counter_offsets_presp * sizeof(u16)); + csa.counter_offsets_beacon = params->counter_offsets_beacon; + csa.counter_offsets_presp = params->counter_offsets_presp; + csa.n_counter_offsets_beacon = params->n_counter_offsets_beacon; + csa.n_counter_offsets_presp = params->n_counter_offsets_presp; + csa.count = params->count; - err = ieee80211_assign_beacon(sdata, ¶ms->beacon_csa); + err = ieee80211_assign_beacon(sdata, ¶ms->beacon_csa, &csa); if (err < 0) { kfree(sdata->u.ap.next_beacon); return err; @@ -3322,7 +3015,7 @@ __ieee80211_channel_switch(struct wiphy *wiphy, struct net_device *dev, struct ieee80211_local *local = sdata->local; struct ieee80211_chanctx_conf *conf; struct ieee80211_chanctx *chanctx; - int err, num_chanctx, changed = 0; + int err, changed = 0; sdata_assert_lock(sdata); lockdep_assert_held(&local->mtx); @@ -3337,46 +3030,50 @@ __ieee80211_channel_switch(struct wiphy *wiphy, struct net_device *dev, &sdata->vif.bss_conf.chandef)) return -EINVAL; + /* don't allow another channel switch if one is already active. */ + if (sdata->vif.csa_active) + return -EBUSY; + mutex_lock(&local->chanctx_mtx); conf = rcu_dereference_protected(sdata->vif.chanctx_conf, lockdep_is_held(&local->chanctx_mtx)); if (!conf) { - mutex_unlock(&local->chanctx_mtx); - return -EBUSY; + err = -EBUSY; + goto out; } - /* don't handle for multi-VIF cases */ chanctx = container_of(conf, struct ieee80211_chanctx, conf); - if (ieee80211_chanctx_refcount(local, chanctx) > 1) { - mutex_unlock(&local->chanctx_mtx); - return -EBUSY; + if (!chanctx) { + err = -EBUSY; + goto out; } - num_chanctx = 0; - list_for_each_entry_rcu(chanctx, &local->chanctx_list, list) - num_chanctx++; - mutex_unlock(&local->chanctx_mtx); - if (num_chanctx > 1) - return -EBUSY; + err = ieee80211_vif_reserve_chanctx(sdata, ¶ms->chandef, + chanctx->mode, + params->radar_required); + if (err) + goto out; - /* don't allow another channel switch if one is already active. */ - if (sdata->vif.csa_active) - return -EBUSY; + /* if reservation is invalid then this will fail */ + err = ieee80211_check_combinations(sdata, NULL, chanctx->mode, 0); + if (err) { + ieee80211_vif_unreserve_chanctx(sdata); + goto out; + } err = ieee80211_set_csa_beacon(sdata, params, &changed); - if (err) - return err; + if (err) { + ieee80211_vif_unreserve_chanctx(sdata); + goto out; + } - sdata->csa_radar_required = params->radar_required; sdata->csa_chandef = params->chandef; sdata->csa_block_tx = params->block_tx; - sdata->csa_current_counter = params->count; sdata->vif.csa_active = true; if (sdata->csa_block_tx) - ieee80211_stop_queues_by_reason(&local->hw, - IEEE80211_MAX_QUEUE_MAP, - IEEE80211_QUEUE_STOP_REASON_CSA); + ieee80211_stop_vif_queues(local, sdata, + IEEE80211_QUEUE_STOP_REASON_CSA); if (changed) { ieee80211_bss_info_change_notify(sdata, changed); @@ -3386,7 +3083,9 @@ __ieee80211_channel_switch(struct wiphy *wiphy, struct net_device *dev, ieee80211_csa_finalize(sdata); } - return 0; +out: + mutex_unlock(&local->chanctx_mtx); + return err; } int ieee80211_channel_switch(struct wiphy *wiphy, struct net_device *dev, @@ -3518,10 +3217,23 @@ static int ieee80211_mgmt_tx(struct wiphy *wiphy, struct wireless_dev *wdev, sdata->vif.type == NL80211_IFTYPE_ADHOC) && params->n_csa_offsets) { int i; - u8 c = sdata->csa_current_counter; + struct beacon_data *beacon = NULL; - for (i = 0; i < params->n_csa_offsets; i++) - data[params->csa_offsets[i]] = c; + rcu_read_lock(); + + if (sdata->vif.type == NL80211_IFTYPE_AP) + beacon = rcu_dereference(sdata->u.ap.beacon); + else if (sdata->vif.type == NL80211_IFTYPE_ADHOC) + beacon = rcu_dereference(sdata->u.ibss.presp); + else if (ieee80211_vif_is_mesh(&sdata->vif)) + beacon = rcu_dereference(sdata->u.mesh.beacon); + + if (beacon) + for (i = 0; i < params->n_csa_offsets; i++) + data[params->csa_offsets[i]] = + beacon->csa_current_counter; + + rcu_read_unlock(); } IEEE80211_SKB_CB(skb)->flags = flags; @@ -3601,21 +3313,6 @@ static int ieee80211_get_antenna(struct wiphy *wiphy, u32 *tx_ant, u32 *rx_ant) return drv_get_antenna(local, tx_ant, rx_ant); } -static int ieee80211_set_ringparam(struct wiphy *wiphy, u32 tx, u32 rx) -{ - struct ieee80211_local *local = wiphy_priv(wiphy); - - return drv_set_ringparam(local, tx, rx); -} - -static void ieee80211_get_ringparam(struct wiphy *wiphy, - u32 *tx, u32 *tx_max, u32 *rx, u32 *rx_max) -{ - struct ieee80211_local *local = wiphy_priv(wiphy); - - drv_get_ringparam(local, tx, tx_max, rx, rx_max); -} - static int ieee80211_set_rekey_data(struct wiphy *wiphy, struct net_device *dev, struct cfg80211_gtk_rekey_data *data) @@ -3847,8 +3544,6 @@ const struct cfg80211_ops mac80211_config_ops = { .mgmt_frame_register = ieee80211_mgmt_frame_register, .set_antenna = ieee80211_set_antenna, .get_antenna = ieee80211_get_antenna, - .set_ringparam = ieee80211_set_ringparam, - .get_ringparam = ieee80211_get_ringparam, .set_rekey_data = ieee80211_set_rekey_data, .tdls_oper = ieee80211_tdls_oper, .tdls_mgmt = ieee80211_tdls_mgmt, @@ -3857,9 +3552,6 @@ const struct cfg80211_ops mac80211_config_ops = { #ifdef CONFIG_PM .set_wakeup = ieee80211_set_wakeup, #endif - .get_et_sset_count = ieee80211_get_et_sset_count, - .get_et_stats = ieee80211_get_et_stats, - .get_et_strings = ieee80211_get_et_strings, .get_channel = ieee80211_cfg_get_channel, .start_radar_detection = ieee80211_start_radar_detection, .channel_switch = ieee80211_channel_switch, diff --git a/net/mac80211/chan.c b/net/mac80211/chan.c index a310e33972de..6d537f03c0ba 100644 --- a/net/mac80211/chan.c +++ b/net/mac80211/chan.c @@ -63,6 +63,20 @@ static bool ieee80211_can_create_new_chanctx(struct ieee80211_local *local) return ieee80211_num_chanctx(local) < ieee80211_max_num_channels(local); } +static struct ieee80211_chanctx * +ieee80211_vif_get_chanctx(struct ieee80211_sub_if_data *sdata) +{ + struct ieee80211_local *local __maybe_unused = sdata->local; + struct ieee80211_chanctx_conf *conf; + + conf = rcu_dereference_protected(sdata->vif.chanctx_conf, + lockdep_is_held(&local->chanctx_mtx)); + if (!conf) + return NULL; + + return container_of(conf, struct ieee80211_chanctx, conf); +} + static const struct cfg80211_chan_def * ieee80211_chanctx_reserved_chandef(struct ieee80211_local *local, struct ieee80211_chanctx *ctx, @@ -160,6 +174,9 @@ ieee80211_find_reservation_chanctx(struct ieee80211_local *local, return NULL; list_for_each_entry(ctx, &local->chanctx_list, list) { + if (ctx->replace_state == IEEE80211_CHANCTX_WILL_BE_REPLACED) + continue; + if (ctx->mode == IEEE80211_CHANCTX_EXCLUSIVE) continue; @@ -347,6 +364,9 @@ ieee80211_find_chanctx(struct ieee80211_local *local, list_for_each_entry(ctx, &local->chanctx_list, list) { const struct cfg80211_chan_def *compat; + if (ctx->replace_state != IEEE80211_CHANCTX_REPLACE_NONE) + continue; + if (ctx->mode == IEEE80211_CHANCTX_EXCLUSIVE) continue; @@ -622,6 +642,7 @@ static void __ieee80211_vif_release_channel(struct ieee80211_sub_if_data *sdata) struct ieee80211_local *local = sdata->local; struct ieee80211_chanctx_conf *conf; struct ieee80211_chanctx *ctx; + bool use_reserved_switch = false; lockdep_assert_held(&local->chanctx_mtx); @@ -632,12 +653,23 @@ static void __ieee80211_vif_release_channel(struct ieee80211_sub_if_data *sdata) ctx = container_of(conf, struct ieee80211_chanctx, conf); - if (sdata->reserved_chanctx) + if (sdata->reserved_chanctx) { + if (sdata->reserved_chanctx->replace_state == + IEEE80211_CHANCTX_REPLACES_OTHER && + ieee80211_chanctx_num_reserved(local, + sdata->reserved_chanctx) > 1) + use_reserved_switch = true; + ieee80211_vif_unreserve_chanctx(sdata); + } ieee80211_assign_vif_chanctx(sdata, NULL); if (ieee80211_chanctx_refcount(local, ctx) == 0) ieee80211_free_chanctx(local, ctx); + + /* Unreserving may ready an in-place reservation. */ + if (use_reserved_switch) + ieee80211_vif_use_reserved_switch(local); } void ieee80211_recalc_smps_chanctx(struct ieee80211_local *local, @@ -787,70 +819,6 @@ int ieee80211_vif_use_channel(struct ieee80211_sub_if_data *sdata, return ret; } -static int __ieee80211_vif_change_channel(struct ieee80211_sub_if_data *sdata, - struct ieee80211_chanctx *ctx, - u32 *changed) -{ - struct ieee80211_local *local = sdata->local; - const struct cfg80211_chan_def *chandef = &sdata->csa_chandef; - u32 chanctx_changed = 0; - - if (!cfg80211_chandef_usable(sdata->local->hw.wiphy, chandef, - IEEE80211_CHAN_DISABLED)) - return -EINVAL; - - if (ieee80211_chanctx_refcount(local, ctx) != 1) - return -EINVAL; - - if (sdata->vif.bss_conf.chandef.width != chandef->width) { - chanctx_changed = IEEE80211_CHANCTX_CHANGE_WIDTH; - *changed |= BSS_CHANGED_BANDWIDTH; - } - - sdata->vif.bss_conf.chandef = *chandef; - ctx->conf.def = *chandef; - - chanctx_changed |= IEEE80211_CHANCTX_CHANGE_CHANNEL; - drv_change_chanctx(local, ctx, chanctx_changed); - - ieee80211_recalc_chanctx_chantype(local, ctx); - ieee80211_recalc_smps_chanctx(local, ctx); - ieee80211_recalc_radar_chanctx(local, ctx); - ieee80211_recalc_chanctx_min_def(local, ctx); - - return 0; -} - -int ieee80211_vif_change_channel(struct ieee80211_sub_if_data *sdata, - u32 *changed) -{ - struct ieee80211_local *local = sdata->local; - struct ieee80211_chanctx_conf *conf; - struct ieee80211_chanctx *ctx; - int ret; - - lockdep_assert_held(&local->mtx); - - /* should never be called if not performing a channel switch. */ - if (WARN_ON(!sdata->vif.csa_active)) - return -EINVAL; - - mutex_lock(&local->chanctx_mtx); - conf = rcu_dereference_protected(sdata->vif.chanctx_conf, - lockdep_is_held(&local->chanctx_mtx)); - if (!conf) { - ret = -EINVAL; - goto out; - } - - ctx = container_of(conf, struct ieee80211_chanctx, conf); - - ret = __ieee80211_vif_change_channel(sdata, ctx, changed); - out: - mutex_unlock(&local->chanctx_mtx); - return ret; -} - static void __ieee80211_vif_copy_chanctx_to_vlans(struct ieee80211_sub_if_data *sdata, bool clear) @@ -905,8 +873,25 @@ int ieee80211_vif_unreserve_chanctx(struct ieee80211_sub_if_data *sdata) list_del(&sdata->reserved_chanctx_list); sdata->reserved_chanctx = NULL; - if (ieee80211_chanctx_refcount(sdata->local, ctx) == 0) - ieee80211_free_chanctx(sdata->local, ctx); + if (ieee80211_chanctx_refcount(sdata->local, ctx) == 0) { + if (ctx->replace_state == IEEE80211_CHANCTX_REPLACES_OTHER) { + if (WARN_ON(!ctx->replace_ctx)) + return -EINVAL; + + WARN_ON(ctx->replace_ctx->replace_state != + IEEE80211_CHANCTX_WILL_BE_REPLACED); + WARN_ON(ctx->replace_ctx->replace_ctx != ctx); + + ctx->replace_ctx->replace_ctx = NULL; + ctx->replace_ctx->replace_state = + IEEE80211_CHANCTX_REPLACE_NONE; + + list_del_rcu(&ctx->list); + kfree_rcu(ctx, rcu_head); + } else { + ieee80211_free_chanctx(sdata->local, ctx); + } + } return 0; } @@ -917,40 +902,84 @@ int ieee80211_vif_reserve_chanctx(struct ieee80211_sub_if_data *sdata, bool radar_required) { struct ieee80211_local *local = sdata->local; - struct ieee80211_chanctx_conf *conf; - struct ieee80211_chanctx *new_ctx, *curr_ctx; - int ret = 0; + struct ieee80211_chanctx *new_ctx, *curr_ctx, *ctx; - mutex_lock(&local->chanctx_mtx); - - conf = rcu_dereference_protected(sdata->vif.chanctx_conf, - lockdep_is_held(&local->chanctx_mtx)); - if (!conf) { - ret = -EINVAL; - goto out; - } + lockdep_assert_held(&local->chanctx_mtx); - curr_ctx = container_of(conf, struct ieee80211_chanctx, conf); + curr_ctx = ieee80211_vif_get_chanctx(sdata); + if (curr_ctx && local->use_chanctx && !local->ops->switch_vif_chanctx) + return -ENOTSUPP; new_ctx = ieee80211_find_reservation_chanctx(local, chandef, mode); if (!new_ctx) { - if (ieee80211_chanctx_refcount(local, curr_ctx) == 1 && - (local->hw.flags & IEEE80211_HW_CHANGE_RUNNING_CHANCTX)) { - /* if we're the only users of the chanctx and - * the driver supports changing a running - * context, reserve our current context - */ - new_ctx = curr_ctx; - } else if (ieee80211_can_create_new_chanctx(local)) { - /* create a new context and reserve it */ + if (ieee80211_can_create_new_chanctx(local)) { new_ctx = ieee80211_new_chanctx(local, chandef, mode); - if (IS_ERR(new_ctx)) { - ret = PTR_ERR(new_ctx); - goto out; - } + if (IS_ERR(new_ctx)) + return PTR_ERR(new_ctx); } else { - ret = -EBUSY; - goto out; + if (!curr_ctx || + (curr_ctx->replace_state == + IEEE80211_CHANCTX_WILL_BE_REPLACED) || + !list_empty(&curr_ctx->reserved_vifs)) { + /* + * Another vif already requested this context + * for a reservation. Find another one hoping + * all vifs assigned to it will also switch + * soon enough. + * + * TODO: This needs a little more work as some + * cases (more than 2 chanctx capable devices) + * may fail which could otherwise succeed + * provided some channel context juggling was + * performed. + * + * Consider ctx1..3, vif1..6, each ctx has 2 + * vifs. vif1 and vif2 from ctx1 request new + * different chandefs starting 2 in-place + * reserations with ctx4 and ctx5 replacing + * ctx1 and ctx2 respectively. Next vif5 and + * vif6 from ctx3 reserve ctx4. If vif3 and + * vif4 remain on ctx2 as they are then this + * fails unless `replace_ctx` from ctx5 is + * replaced with ctx3. + */ + list_for_each_entry(ctx, &local->chanctx_list, + list) { + if (ctx->replace_state != + IEEE80211_CHANCTX_REPLACE_NONE) + continue; + + if (!list_empty(&ctx->reserved_vifs)) + continue; + + curr_ctx = ctx; + break; + } + } + + /* + * If that's true then all available contexts already + * have reservations and cannot be used. + */ + if (!curr_ctx || + (curr_ctx->replace_state == + IEEE80211_CHANCTX_WILL_BE_REPLACED) || + !list_empty(&curr_ctx->reserved_vifs)) + return -EBUSY; + + new_ctx = ieee80211_alloc_chanctx(local, chandef, mode); + if (!new_ctx) + return -ENOMEM; + + new_ctx->replace_ctx = curr_ctx; + new_ctx->replace_state = + IEEE80211_CHANCTX_REPLACES_OTHER; + + curr_ctx->replace_ctx = new_ctx; + curr_ctx->replace_state = + IEEE80211_CHANCTX_WILL_BE_REPLACED; + + list_add_rcu(&new_ctx->list, &local->chanctx_list); } } @@ -958,82 +987,601 @@ int ieee80211_vif_reserve_chanctx(struct ieee80211_sub_if_data *sdata, sdata->reserved_chanctx = new_ctx; sdata->reserved_chandef = *chandef; sdata->reserved_radar_required = radar_required; -out: - mutex_unlock(&local->chanctx_mtx); - return ret; + sdata->reserved_ready = false; + + return 0; } -int ieee80211_vif_use_reserved_context(struct ieee80211_sub_if_data *sdata, - u32 *changed) +static void +ieee80211_vif_chanctx_reservation_complete(struct ieee80211_sub_if_data *sdata) { - struct ieee80211_local *local = sdata->local; - struct ieee80211_chanctx *ctx; - struct ieee80211_chanctx *old_ctx; - struct ieee80211_chanctx_conf *conf; - int ret; - u32 tmp_changed = *changed; + switch (sdata->vif.type) { + case NL80211_IFTYPE_ADHOC: + case NL80211_IFTYPE_AP: + case NL80211_IFTYPE_MESH_POINT: + ieee80211_queue_work(&sdata->local->hw, + &sdata->csa_finalize_work); + break; + case NL80211_IFTYPE_STATION: + ieee80211_queue_work(&sdata->local->hw, + &sdata->u.mgd.chswitch_work); + break; + case NL80211_IFTYPE_UNSPECIFIED: + case NL80211_IFTYPE_AP_VLAN: + case NL80211_IFTYPE_WDS: + case NL80211_IFTYPE_MONITOR: + case NL80211_IFTYPE_P2P_CLIENT: + case NL80211_IFTYPE_P2P_GO: + case NL80211_IFTYPE_P2P_DEVICE: + case NUM_NL80211_IFTYPES: + WARN_ON(1); + break; + } +} - /* TODO: need to recheck if the chandef is usable etc.? */ +static int +ieee80211_vif_use_reserved_reassign(struct ieee80211_sub_if_data *sdata) +{ + struct ieee80211_local *local = sdata->local; + struct ieee80211_vif_chanctx_switch vif_chsw[1] = {}; + struct ieee80211_chanctx *old_ctx, *new_ctx; + const struct cfg80211_chan_def *chandef; + u32 changed = 0; + int err; lockdep_assert_held(&local->mtx); + lockdep_assert_held(&local->chanctx_mtx); - mutex_lock(&local->chanctx_mtx); + new_ctx = sdata->reserved_chanctx; + old_ctx = ieee80211_vif_get_chanctx(sdata); - ctx = sdata->reserved_chanctx; - if (WARN_ON(!ctx)) { - ret = -EINVAL; - goto out; - } + if (WARN_ON(!sdata->reserved_ready)) + return -EBUSY; + + if (WARN_ON(!new_ctx)) + return -EINVAL; + + if (WARN_ON(!old_ctx)) + return -EINVAL; + + if (WARN_ON(new_ctx->replace_state == + IEEE80211_CHANCTX_REPLACES_OTHER)) + return -EINVAL; + + chandef = ieee80211_chanctx_non_reserved_chandef(local, new_ctx, + &sdata->reserved_chandef); + if (WARN_ON(!chandef)) + return -EINVAL; + + vif_chsw[0].vif = &sdata->vif; + vif_chsw[0].old_ctx = &old_ctx->conf; + vif_chsw[0].new_ctx = &new_ctx->conf; + + list_del(&sdata->reserved_chanctx_list); + sdata->reserved_chanctx = NULL; + + err = drv_switch_vif_chanctx(local, vif_chsw, 1, + CHANCTX_SWMODE_REASSIGN_VIF); + if (err) { + if (ieee80211_chanctx_refcount(local, new_ctx) == 0) + ieee80211_free_chanctx(local, new_ctx); - conf = rcu_dereference_protected(sdata->vif.chanctx_conf, - lockdep_is_held(&local->chanctx_mtx)); - if (!conf) { - ret = -EINVAL; goto out; } - old_ctx = container_of(conf, struct ieee80211_chanctx, conf); + list_move(&sdata->assigned_chanctx_list, &new_ctx->assigned_vifs); + rcu_assign_pointer(sdata->vif.chanctx_conf, &new_ctx->conf); + + if (sdata->vif.type == NL80211_IFTYPE_AP) + __ieee80211_vif_copy_chanctx_to_vlans(sdata, false); + + if (ieee80211_chanctx_refcount(local, old_ctx) == 0) + ieee80211_free_chanctx(local, old_ctx); if (sdata->vif.bss_conf.chandef.width != sdata->reserved_chandef.width) - tmp_changed |= BSS_CHANGED_BANDWIDTH; + changed = BSS_CHANGED_BANDWIDTH; sdata->vif.bss_conf.chandef = sdata->reserved_chandef; - /* unref our reservation */ - sdata->reserved_chanctx = NULL; - sdata->radar_required = sdata->reserved_radar_required; + if (changed) + ieee80211_bss_info_change_notify(sdata, changed); + +out: + ieee80211_vif_chanctx_reservation_complete(sdata); + return err; +} + +static int +ieee80211_vif_use_reserved_assign(struct ieee80211_sub_if_data *sdata) +{ + struct ieee80211_local *local = sdata->local; + struct ieee80211_chanctx *old_ctx, *new_ctx; + const struct cfg80211_chan_def *chandef; + int err; + + old_ctx = ieee80211_vif_get_chanctx(sdata); + new_ctx = sdata->reserved_chanctx; + + if (WARN_ON(!sdata->reserved_ready)) + return -EINVAL; + + if (WARN_ON(old_ctx)) + return -EINVAL; + + if (WARN_ON(!new_ctx)) + return -EINVAL; + + if (WARN_ON(new_ctx->replace_state == + IEEE80211_CHANCTX_REPLACES_OTHER)) + return -EINVAL; + + chandef = ieee80211_chanctx_non_reserved_chandef(local, new_ctx, + &sdata->reserved_chandef); + if (WARN_ON(!chandef)) + return -EINVAL; + list_del(&sdata->reserved_chanctx_list); + sdata->reserved_chanctx = NULL; - if (old_ctx == ctx) { - /* This is our own context, just change it */ - ret = __ieee80211_vif_change_channel(sdata, old_ctx, - &tmp_changed); - if (ret) - goto out; - } else { - ret = ieee80211_assign_vif_chanctx(sdata, ctx); - if (ieee80211_chanctx_refcount(local, old_ctx) == 0) - ieee80211_free_chanctx(local, old_ctx); - if (ret) { - /* if assign fails refcount stays the same */ - if (ieee80211_chanctx_refcount(local, ctx) == 0) - ieee80211_free_chanctx(local, ctx); + err = ieee80211_assign_vif_chanctx(sdata, new_ctx); + if (err) { + if (ieee80211_chanctx_refcount(local, new_ctx) == 0) + ieee80211_free_chanctx(local, new_ctx); + + goto out; + } + +out: + ieee80211_vif_chanctx_reservation_complete(sdata); + return err; +} + +static bool +ieee80211_vif_has_in_place_reservation(struct ieee80211_sub_if_data *sdata) +{ + struct ieee80211_chanctx *old_ctx, *new_ctx; + + lockdep_assert_held(&sdata->local->chanctx_mtx); + + new_ctx = sdata->reserved_chanctx; + old_ctx = ieee80211_vif_get_chanctx(sdata); + + if (!old_ctx) + return false; + + if (WARN_ON(!new_ctx)) + return false; + + if (old_ctx->replace_state != IEEE80211_CHANCTX_WILL_BE_REPLACED) + return false; + + if (new_ctx->replace_state != IEEE80211_CHANCTX_REPLACES_OTHER) + return false; + + return true; +} + +static int ieee80211_chsw_switch_hwconf(struct ieee80211_local *local, + struct ieee80211_chanctx *new_ctx) +{ + const struct cfg80211_chan_def *chandef; + + lockdep_assert_held(&local->mtx); + lockdep_assert_held(&local->chanctx_mtx); + + chandef = ieee80211_chanctx_reserved_chandef(local, new_ctx, NULL); + if (WARN_ON(!chandef)) + return -EINVAL; + + local->hw.conf.radar_enabled = new_ctx->conf.radar_enabled; + local->_oper_chandef = *chandef; + ieee80211_hw_config(local, 0); + + return 0; +} + +static int ieee80211_chsw_switch_vifs(struct ieee80211_local *local, + int n_vifs) +{ + struct ieee80211_vif_chanctx_switch *vif_chsw; + struct ieee80211_sub_if_data *sdata; + struct ieee80211_chanctx *ctx, *old_ctx; + int i, err; + + lockdep_assert_held(&local->mtx); + lockdep_assert_held(&local->chanctx_mtx); + + vif_chsw = kzalloc(sizeof(vif_chsw[0]) * n_vifs, GFP_KERNEL); + if (!vif_chsw) + return -ENOMEM; + + i = 0; + list_for_each_entry(ctx, &local->chanctx_list, list) { + if (ctx->replace_state != IEEE80211_CHANCTX_REPLACES_OTHER) + continue; + + if (WARN_ON(!ctx->replace_ctx)) { + err = -EINVAL; goto out; } - if (sdata->vif.type == NL80211_IFTYPE_AP) - __ieee80211_vif_copy_chanctx_to_vlans(sdata, false); + list_for_each_entry(sdata, &ctx->reserved_vifs, + reserved_chanctx_list) { + if (!ieee80211_vif_has_in_place_reservation( + sdata)) + continue; + + old_ctx = ieee80211_vif_get_chanctx(sdata); + vif_chsw[i].vif = &sdata->vif; + vif_chsw[i].old_ctx = &old_ctx->conf; + vif_chsw[i].new_ctx = &ctx->conf; + + i++; + } } - *changed = tmp_changed; + err = drv_switch_vif_chanctx(local, vif_chsw, n_vifs, + CHANCTX_SWMODE_SWAP_CONTEXTS); - ieee80211_recalc_chanctx_chantype(local, ctx); - ieee80211_recalc_smps_chanctx(local, ctx); - ieee80211_recalc_radar_chanctx(local, ctx); - ieee80211_recalc_chanctx_min_def(local, ctx); out: - mutex_unlock(&local->chanctx_mtx); - return ret; + kfree(vif_chsw); + return err; +} + +static int ieee80211_chsw_switch_ctxs(struct ieee80211_local *local) +{ + struct ieee80211_chanctx *ctx; + int err; + + lockdep_assert_held(&local->mtx); + lockdep_assert_held(&local->chanctx_mtx); + + list_for_each_entry(ctx, &local->chanctx_list, list) { + if (ctx->replace_state != IEEE80211_CHANCTX_REPLACES_OTHER) + continue; + + if (!list_empty(&ctx->replace_ctx->assigned_vifs)) + continue; + + ieee80211_del_chanctx(local, ctx->replace_ctx); + err = ieee80211_add_chanctx(local, ctx); + if (err) + goto err; + } + + return 0; + +err: + WARN_ON(ieee80211_add_chanctx(local, ctx)); + list_for_each_entry_continue_reverse(ctx, &local->chanctx_list, list) { + if (ctx->replace_state != IEEE80211_CHANCTX_REPLACES_OTHER) + continue; + + if (!list_empty(&ctx->replace_ctx->assigned_vifs)) + continue; + + ieee80211_del_chanctx(local, ctx); + WARN_ON(ieee80211_add_chanctx(local, ctx->replace_ctx)); + } + + return err; +} + +int +ieee80211_vif_use_reserved_switch(struct ieee80211_local *local) +{ + struct ieee80211_sub_if_data *sdata, *sdata_tmp; + struct ieee80211_chanctx *ctx, *ctx_tmp, *old_ctx; + struct ieee80211_chanctx *new_ctx = NULL; + int i, err, n_assigned, n_reserved, n_ready; + int n_ctx = 0, n_vifs_switch = 0, n_vifs_assign = 0, n_vifs_ctxless = 0; + + lockdep_assert_held(&local->mtx); + lockdep_assert_held(&local->chanctx_mtx); + + /* + * If there are 2 independent pairs of channel contexts performing + * cross-switch of their vifs this code will still wait until both are + * ready even though it could be possible to switch one before the + * other is ready. + * + * For practical reasons and code simplicity just do a single huge + * switch. + */ + + /* + * Verify if the reservation is still feasible. + * - if it's not then disconnect + * - if it is but not all vifs necessary are ready then defer + */ + + list_for_each_entry(ctx, &local->chanctx_list, list) { + if (ctx->replace_state != IEEE80211_CHANCTX_REPLACES_OTHER) + continue; + + if (WARN_ON(!ctx->replace_ctx)) { + err = -EINVAL; + goto err; + } + + if (!local->use_chanctx) + new_ctx = ctx; + + n_ctx++; + + n_assigned = 0; + n_reserved = 0; + n_ready = 0; + + list_for_each_entry(sdata, &ctx->replace_ctx->assigned_vifs, + assigned_chanctx_list) { + n_assigned++; + if (sdata->reserved_chanctx) { + n_reserved++; + if (sdata->reserved_ready) + n_ready++; + } + } + + if (n_assigned != n_reserved) { + if (n_ready == n_reserved) { + wiphy_info(local->hw.wiphy, + "channel context reservation cannot be finalized because some interfaces aren't switching\n"); + err = -EBUSY; + goto err; + } + + return -EAGAIN; + } + + ctx->conf.radar_enabled = false; + list_for_each_entry(sdata, &ctx->reserved_vifs, + reserved_chanctx_list) { + if (ieee80211_vif_has_in_place_reservation(sdata) && + !sdata->reserved_ready) + return -EAGAIN; + + old_ctx = ieee80211_vif_get_chanctx(sdata); + if (old_ctx) { + if (old_ctx->replace_state == + IEEE80211_CHANCTX_WILL_BE_REPLACED) + n_vifs_switch++; + else + n_vifs_assign++; + } else { + n_vifs_ctxless++; + } + + if (sdata->reserved_radar_required) + ctx->conf.radar_enabled = true; + } + } + + if (WARN_ON(n_ctx == 0) || + WARN_ON(n_vifs_switch == 0 && + n_vifs_assign == 0 && + n_vifs_ctxless == 0) || + WARN_ON(n_ctx > 1 && !local->use_chanctx) || + WARN_ON(!new_ctx && !local->use_chanctx)) { + err = -EINVAL; + goto err; + } + + /* + * All necessary vifs are ready. Perform the switch now depending on + * reservations and driver capabilities. + */ + + if (local->use_chanctx) { + if (n_vifs_switch > 0) { + err = ieee80211_chsw_switch_vifs(local, n_vifs_switch); + if (err) + goto err; + } + + if (n_vifs_assign > 0 || n_vifs_ctxless > 0) { + err = ieee80211_chsw_switch_ctxs(local); + if (err) + goto err; + } + } else { + err = ieee80211_chsw_switch_hwconf(local, new_ctx); + if (err) + goto err; + } + + /* + * Update all structures, values and pointers to point to new channel + * context(s). + */ + + i = 0; + list_for_each_entry(ctx, &local->chanctx_list, list) { + if (ctx->replace_state != IEEE80211_CHANCTX_REPLACES_OTHER) + continue; + + if (WARN_ON(!ctx->replace_ctx)) { + err = -EINVAL; + goto err; + } + + list_for_each_entry(sdata, &ctx->reserved_vifs, + reserved_chanctx_list) { + u32 changed = 0; + + if (!ieee80211_vif_has_in_place_reservation(sdata)) + continue; + + rcu_assign_pointer(sdata->vif.chanctx_conf, &ctx->conf); + + if (sdata->vif.type == NL80211_IFTYPE_AP) + __ieee80211_vif_copy_chanctx_to_vlans(sdata, + false); + + sdata->radar_required = sdata->reserved_radar_required; + + if (sdata->vif.bss_conf.chandef.width != + sdata->reserved_chandef.width) + changed = BSS_CHANGED_BANDWIDTH; + + sdata->vif.bss_conf.chandef = sdata->reserved_chandef; + if (changed) + ieee80211_bss_info_change_notify(sdata, + changed); + + ieee80211_recalc_txpower(sdata); + } + + ieee80211_recalc_chanctx_chantype(local, ctx); + ieee80211_recalc_smps_chanctx(local, ctx); + ieee80211_recalc_radar_chanctx(local, ctx); + ieee80211_recalc_chanctx_min_def(local, ctx); + + list_for_each_entry_safe(sdata, sdata_tmp, &ctx->reserved_vifs, + reserved_chanctx_list) { + if (ieee80211_vif_get_chanctx(sdata) != ctx) + continue; + + list_del(&sdata->reserved_chanctx_list); + list_move(&sdata->assigned_chanctx_list, + &new_ctx->assigned_vifs); + sdata->reserved_chanctx = NULL; + + ieee80211_vif_chanctx_reservation_complete(sdata); + } + + /* + * This context might have been a dependency for an already + * ready re-assign reservation interface that was deferred. Do + * not propagate error to the caller though. The in-place + * reservation for originally requested interface has already + * succeeded at this point. + */ + list_for_each_entry_safe(sdata, sdata_tmp, &ctx->reserved_vifs, + reserved_chanctx_list) { + if (WARN_ON(ieee80211_vif_has_in_place_reservation( + sdata))) + continue; + + if (WARN_ON(sdata->reserved_chanctx != ctx)) + continue; + + if (!sdata->reserved_ready) + continue; + + if (ieee80211_vif_get_chanctx(sdata)) + err = ieee80211_vif_use_reserved_reassign( + sdata); + else + err = ieee80211_vif_use_reserved_assign(sdata); + + if (err) { + sdata_info(sdata, + "failed to finalize (re-)assign reservation (err=%d)\n", + err); + ieee80211_vif_unreserve_chanctx(sdata); + cfg80211_stop_iface(local->hw.wiphy, + &sdata->wdev, + GFP_KERNEL); + } + } + } + + /* + * Finally free old contexts + */ + + list_for_each_entry_safe(ctx, ctx_tmp, &local->chanctx_list, list) { + if (ctx->replace_state != IEEE80211_CHANCTX_WILL_BE_REPLACED) + continue; + + ctx->replace_ctx->replace_ctx = NULL; + ctx->replace_ctx->replace_state = + IEEE80211_CHANCTX_REPLACE_NONE; + + list_del_rcu(&ctx->list); + kfree_rcu(ctx, rcu_head); + } + + return 0; + +err: + list_for_each_entry(ctx, &local->chanctx_list, list) { + if (ctx->replace_state != IEEE80211_CHANCTX_REPLACES_OTHER) + continue; + + list_for_each_entry_safe(sdata, sdata_tmp, &ctx->reserved_vifs, + reserved_chanctx_list) { + ieee80211_vif_unreserve_chanctx(sdata); + ieee80211_vif_chanctx_reservation_complete(sdata); + } + } + + return err; +} + +int ieee80211_vif_use_reserved_context(struct ieee80211_sub_if_data *sdata) +{ + struct ieee80211_local *local = sdata->local; + struct ieee80211_chanctx *new_ctx; + struct ieee80211_chanctx *old_ctx; + int err; + + lockdep_assert_held(&local->mtx); + lockdep_assert_held(&local->chanctx_mtx); + + new_ctx = sdata->reserved_chanctx; + old_ctx = ieee80211_vif_get_chanctx(sdata); + + if (WARN_ON(!new_ctx)) + return -EINVAL; + + if (WARN_ON(new_ctx->replace_state == + IEEE80211_CHANCTX_WILL_BE_REPLACED)) + return -EINVAL; + + if (WARN_ON(sdata->reserved_ready)) + return -EINVAL; + + sdata->reserved_ready = true; + + if (new_ctx->replace_state == IEEE80211_CHANCTX_REPLACE_NONE) { + if (old_ctx) + err = ieee80211_vif_use_reserved_reassign(sdata); + else + err = ieee80211_vif_use_reserved_assign(sdata); + + if (err) + return err; + } + + /* + * In-place reservation may need to be finalized now either if: + * a) sdata is taking part in the swapping itself and is the last one + * b) sdata has switched with a re-assign reservation to an existing + * context readying in-place switching of old_ctx + * + * In case of (b) do not propagate the error up because the requested + * sdata already switched successfully. Just spill an extra warning. + * The ieee80211_vif_use_reserved_switch() already stops all necessary + * interfaces upon failure. + */ + if ((old_ctx && + old_ctx->replace_state == IEEE80211_CHANCTX_WILL_BE_REPLACED) || + new_ctx->replace_state == IEEE80211_CHANCTX_REPLACES_OTHER) { + err = ieee80211_vif_use_reserved_switch(local); + if (err && err != -EAGAIN) { + if (new_ctx->replace_state == + IEEE80211_CHANCTX_REPLACES_OTHER) + return err; + + wiphy_info(local->hw.wiphy, + "depending in-place reservation failed (err=%d)\n", + err); + } + } + + return 0; } int ieee80211_vif_change_bandwidth(struct ieee80211_sub_if_data *sdata, @@ -1043,6 +1591,7 @@ int ieee80211_vif_change_bandwidth(struct ieee80211_sub_if_data *sdata, struct ieee80211_local *local = sdata->local; struct ieee80211_chanctx_conf *conf; struct ieee80211_chanctx *ctx; + const struct cfg80211_chan_def *compat; int ret; if (!cfg80211_chandef_usable(sdata->local->hw.wiphy, chandef, @@ -1069,11 +1618,33 @@ int ieee80211_vif_change_bandwidth(struct ieee80211_sub_if_data *sdata, } ctx = container_of(conf, struct ieee80211_chanctx, conf); - if (!cfg80211_chandef_compatible(&conf->def, chandef)) { + + compat = cfg80211_chandef_compatible(&conf->def, chandef); + if (!compat) { ret = -EINVAL; goto out; } + switch (ctx->replace_state) { + case IEEE80211_CHANCTX_REPLACE_NONE: + if (!ieee80211_chanctx_reserved_chandef(local, ctx, compat)) { + ret = -EBUSY; + goto out; + } + break; + case IEEE80211_CHANCTX_WILL_BE_REPLACED: + /* TODO: Perhaps the bandwith change could be treated as a + * reservation itself? */ + ret = -EBUSY; + goto out; + case IEEE80211_CHANCTX_REPLACES_OTHER: + /* channel context that is going to replace another channel + * context doesn't really exist and shouldn't be assigned + * anywhere yet */ + WARN_ON(1); + break; + } + sdata->vif.bss_conf.chandef = *chandef; ieee80211_recalc_chanctx_chantype(local, ctx); diff --git a/net/mac80211/debugfs_sta.c b/net/mac80211/debugfs_sta.c index 2ecb4deddb5d..3db96648b45a 100644 --- a/net/mac80211/debugfs_sta.c +++ b/net/mac80211/debugfs_sta.c @@ -124,7 +124,7 @@ static ssize_t sta_connected_time_read(struct file *file, char __user *userbuf, long connected_time_secs; char buf[100]; int res; - do_posix_clock_monotonic_gettime(&uptime); + ktime_get_ts(&uptime); connected_time_secs = uptime.tv_sec - sta->last_connected; time_to_tm(connected_time_secs, 0, &result); result.tm_year -= 70; @@ -587,7 +587,6 @@ void ieee80211_sta_debugfs_add(struct sta_info *sta) DEBUGFS_ADD_COUNTER(tx_filtered, tx_filtered_count); DEBUGFS_ADD_COUNTER(tx_retry_failed, tx_retry_failed); DEBUGFS_ADD_COUNTER(tx_retry_count, tx_retry_count); - DEBUGFS_ADD_COUNTER(wep_weak_iv_count, wep_weak_iv_count); if (sizeof(sta->driver_buffered_tids) == sizeof(u32)) debugfs_create_x32("driver_buffered_tids", 0400, diff --git a/net/mac80211/driver-ops.h b/net/mac80211/driver-ops.h index bd782dcffcc7..11423958116a 100644 --- a/net/mac80211/driver-ops.h +++ b/net/mac80211/driver-ops.h @@ -314,7 +314,7 @@ static inline void drv_update_tkip_key(struct ieee80211_local *local, static inline int drv_hw_scan(struct ieee80211_local *local, struct ieee80211_sub_if_data *sdata, - struct cfg80211_scan_request *req) + struct ieee80211_scan_request *req) { int ret; @@ -346,7 +346,7 @@ static inline int drv_sched_scan_start(struct ieee80211_local *local, struct ieee80211_sub_if_data *sdata, struct cfg80211_sched_scan_request *req, - struct ieee80211_sched_scan_ies *ies) + struct ieee80211_scan_ies *ies) { int ret; @@ -970,6 +970,22 @@ static inline void drv_mgd_prepare_tx(struct ieee80211_local *local, trace_drv_return_void(local); } +static inline void +drv_mgd_protect_tdls_discover(struct ieee80211_local *local, + struct ieee80211_sub_if_data *sdata) +{ + might_sleep(); + + if (!check_sdata_in_driver(sdata)) + return; + WARN_ON_ONCE(sdata->vif.type != NL80211_IFTYPE_STATION); + + trace_drv_mgd_protect_tdls_discover(local, sdata); + if (local->ops->mgd_protect_tdls_discover) + local->ops->mgd_protect_tdls_discover(&local->hw, &sdata->vif); + trace_drv_return_void(local); +} + static inline int drv_add_chanctx(struct ieee80211_local *local, struct ieee80211_chanctx *ctx) { diff --git a/net/mac80211/ethtool.c b/net/mac80211/ethtool.c new file mode 100644 index 000000000000..ebfc8091557b --- /dev/null +++ b/net/mac80211/ethtool.c @@ -0,0 +1,244 @@ +/* + * mac80211 ethtool hooks for cfg80211 + * + * Copied from cfg.c - originally + * Copyright 2006-2010 Johannes Berg <johannes@sipsolutions.net> + * Copyright 2014 Intel Corporation (Author: Johannes Berg) + * + * This file is GPLv2 as found in COPYING. + */ +#include <linux/types.h> +#include <net/cfg80211.h> +#include "ieee80211_i.h" +#include "sta_info.h" +#include "driver-ops.h" + +static int ieee80211_set_ringparam(struct net_device *dev, + struct ethtool_ringparam *rp) +{ + struct ieee80211_local *local = wiphy_priv(dev->ieee80211_ptr->wiphy); + + if (rp->rx_mini_pending != 0 || rp->rx_jumbo_pending != 0) + return -EINVAL; + + return drv_set_ringparam(local, rp->tx_pending, rp->rx_pending); +} + +static void ieee80211_get_ringparam(struct net_device *dev, + struct ethtool_ringparam *rp) +{ + struct ieee80211_local *local = wiphy_priv(dev->ieee80211_ptr->wiphy); + + memset(rp, 0, sizeof(*rp)); + + drv_get_ringparam(local, &rp->tx_pending, &rp->tx_max_pending, + &rp->rx_pending, &rp->rx_max_pending); +} + +static const char ieee80211_gstrings_sta_stats[][ETH_GSTRING_LEN] = { + "rx_packets", "rx_bytes", + "rx_duplicates", "rx_fragments", "rx_dropped", + "tx_packets", "tx_bytes", "tx_fragments", + "tx_filtered", "tx_retry_failed", "tx_retries", + "beacon_loss", "sta_state", "txrate", "rxrate", "signal", + "channel", "noise", "ch_time", "ch_time_busy", + "ch_time_ext_busy", "ch_time_rx", "ch_time_tx" +}; +#define STA_STATS_LEN ARRAY_SIZE(ieee80211_gstrings_sta_stats) + +static int ieee80211_get_sset_count(struct net_device *dev, int sset) +{ + struct ieee80211_sub_if_data *sdata = IEEE80211_DEV_TO_SUB_IF(dev); + int rv = 0; + + if (sset == ETH_SS_STATS) + rv += STA_STATS_LEN; + + rv += drv_get_et_sset_count(sdata, sset); + + if (rv == 0) + return -EOPNOTSUPP; + return rv; +} + +static void ieee80211_get_stats(struct net_device *dev, + struct ethtool_stats *stats, + u64 *data) +{ + struct ieee80211_sub_if_data *sdata = IEEE80211_DEV_TO_SUB_IF(dev); + struct ieee80211_chanctx_conf *chanctx_conf; + struct ieee80211_channel *channel; + struct sta_info *sta; + struct ieee80211_local *local = sdata->local; + struct station_info sinfo; + struct survey_info survey; + int i, q; +#define STA_STATS_SURVEY_LEN 7 + + memset(data, 0, sizeof(u64) * STA_STATS_LEN); + +#define ADD_STA_STATS(sta) \ + do { \ + data[i++] += sta->rx_packets; \ + data[i++] += sta->rx_bytes; \ + data[i++] += sta->num_duplicates; \ + data[i++] += sta->rx_fragments; \ + data[i++] += sta->rx_dropped; \ + \ + data[i++] += sinfo.tx_packets; \ + data[i++] += sinfo.tx_bytes; \ + data[i++] += sta->tx_fragments; \ + data[i++] += sta->tx_filtered_count; \ + data[i++] += sta->tx_retry_failed; \ + data[i++] += sta->tx_retry_count; \ + data[i++] += sta->beacon_loss_count; \ + } while (0) + + /* For Managed stations, find the single station based on BSSID + * and use that. For interface types, iterate through all available + * stations and add stats for any station that is assigned to this + * network device. + */ + + mutex_lock(&local->sta_mtx); + + if (sdata->vif.type == NL80211_IFTYPE_STATION) { + sta = sta_info_get_bss(sdata, sdata->u.mgd.bssid); + + if (!(sta && !WARN_ON(sta->sdata->dev != dev))) + goto do_survey; + + sinfo.filled = 0; + sta_set_sinfo(sta, &sinfo); + + i = 0; + ADD_STA_STATS(sta); + + data[i++] = sta->sta_state; + + + if (sinfo.filled & STATION_INFO_TX_BITRATE) + data[i] = 100000 * + cfg80211_calculate_bitrate(&sinfo.txrate); + i++; + if (sinfo.filled & STATION_INFO_RX_BITRATE) + data[i] = 100000 * + cfg80211_calculate_bitrate(&sinfo.rxrate); + i++; + + if (sinfo.filled & STATION_INFO_SIGNAL_AVG) + data[i] = (u8)sinfo.signal_avg; + i++; + } else { + list_for_each_entry(sta, &local->sta_list, list) { + /* Make sure this station belongs to the proper dev */ + if (sta->sdata->dev != dev) + continue; + + sinfo.filled = 0; + sta_set_sinfo(sta, &sinfo); + i = 0; + ADD_STA_STATS(sta); + } + } + +do_survey: + i = STA_STATS_LEN - STA_STATS_SURVEY_LEN; + /* Get survey stats for current channel */ + survey.filled = 0; + + rcu_read_lock(); + chanctx_conf = rcu_dereference(sdata->vif.chanctx_conf); + if (chanctx_conf) + channel = chanctx_conf->def.chan; + else + channel = NULL; + rcu_read_unlock(); + + if (channel) { + q = 0; + do { + survey.filled = 0; + if (drv_get_survey(local, q, &survey) != 0) { + survey.filled = 0; + break; + } + q++; + } while (channel != survey.channel); + } + + if (survey.filled) + data[i++] = survey.channel->center_freq; + else + data[i++] = 0; + if (survey.filled & SURVEY_INFO_NOISE_DBM) + data[i++] = (u8)survey.noise; + else + data[i++] = -1LL; + if (survey.filled & SURVEY_INFO_CHANNEL_TIME) + data[i++] = survey.channel_time; + else + data[i++] = -1LL; + if (survey.filled & SURVEY_INFO_CHANNEL_TIME_BUSY) + data[i++] = survey.channel_time_busy; + else + data[i++] = -1LL; + if (survey.filled & SURVEY_INFO_CHANNEL_TIME_EXT_BUSY) + data[i++] = survey.channel_time_ext_busy; + else + data[i++] = -1LL; + if (survey.filled & SURVEY_INFO_CHANNEL_TIME_RX) + data[i++] = survey.channel_time_rx; + else + data[i++] = -1LL; + if (survey.filled & SURVEY_INFO_CHANNEL_TIME_TX) + data[i++] = survey.channel_time_tx; + else + data[i++] = -1LL; + + mutex_unlock(&local->sta_mtx); + + if (WARN_ON(i != STA_STATS_LEN)) + return; + + drv_get_et_stats(sdata, stats, &(data[STA_STATS_LEN])); +} + +static void ieee80211_get_strings(struct net_device *dev, u32 sset, u8 *data) +{ + struct ieee80211_sub_if_data *sdata = IEEE80211_DEV_TO_SUB_IF(dev); + int sz_sta_stats = 0; + + if (sset == ETH_SS_STATS) { + sz_sta_stats = sizeof(ieee80211_gstrings_sta_stats); + memcpy(data, ieee80211_gstrings_sta_stats, sz_sta_stats); + } + drv_get_et_strings(sdata, sset, &(data[sz_sta_stats])); +} + +static int ieee80211_get_regs_len(struct net_device *dev) +{ + return 0; +} + +static void ieee80211_get_regs(struct net_device *dev, + struct ethtool_regs *regs, + void *data) +{ + struct wireless_dev *wdev = dev->ieee80211_ptr; + + regs->version = wdev->wiphy->hw_version; + regs->len = 0; +} + +const struct ethtool_ops ieee80211_ethtool_ops = { + .get_drvinfo = cfg80211_get_drvinfo, + .get_regs_len = ieee80211_get_regs_len, + .get_regs = ieee80211_get_regs, + .get_link = ethtool_op_get_link, + .get_ringparam = ieee80211_get_ringparam, + .set_ringparam = ieee80211_set_ringparam, + .get_strings = ieee80211_get_strings, + .get_ethtool_stats = ieee80211_get_stats, + .get_sset_count = ieee80211_get_sset_count, +}; diff --git a/net/mac80211/ht.c b/net/mac80211/ht.c index 15702ff64a4c..ff630be2ca75 100644 --- a/net/mac80211/ht.c +++ b/net/mac80211/ht.c @@ -150,13 +150,12 @@ bool ieee80211_ht_cap_ie_to_sta_ht_cap(struct ieee80211_sub_if_data *sdata, /* * If user has specified capability over-rides, take care - * of that if the station we're setting up is the AP that + * of that if the station we're setting up is the AP or TDLS peer that * we advertised a restricted capability set to. Override * our own capabilities and then use those below. */ - if ((sdata->vif.type == NL80211_IFTYPE_STATION || - sdata->vif.type == NL80211_IFTYPE_ADHOC) && - !test_sta_flag(sta, WLAN_STA_TDLS_PEER)) + if (sdata->vif.type == NL80211_IFTYPE_STATION || + sdata->vif.type == NL80211_IFTYPE_ADHOC) ieee80211_apply_htcap_overrides(sdata, &own_cap); /* @@ -228,6 +227,9 @@ bool ieee80211_ht_cap_ie_to_sta_ht_cap(struct ieee80211_sub_if_data *sdata, if (own_cap.mcs.rx_mask[32/8] & ht_cap_ie->mcs.rx_mask[32/8] & 1) ht_cap.mcs.rx_mask[32/8] |= 1; + /* set Rx highest rate */ + ht_cap.mcs.rx_highest = ht_cap_ie->mcs.rx_highest; + apply: changed = memcmp(&sta->sta.ht_cap, &ht_cap, sizeof(ht_cap)); diff --git a/net/mac80211/ibss.c b/net/mac80211/ibss.c index 18ee0a256b1e..9713dc54ea4b 100644 --- a/net/mac80211/ibss.c +++ b/net/mac80211/ibss.c @@ -143,7 +143,7 @@ ieee80211_ibss_build_presp(struct ieee80211_sub_if_data *sdata, *pos++ = csa_settings->block_tx ? 1 : 0; *pos++ = ieee80211_frequency_to_channel( csa_settings->chandef.chan->center_freq); - sdata->csa_counter_offset_beacon[0] = (pos - presp->head); + presp->csa_counter_offsets[0] = (pos - presp->head); *pos++ = csa_settings->count; } @@ -189,17 +189,8 @@ ieee80211_ibss_build_presp(struct ieee80211_sub_if_data *sdata, chandef, 0); } - if (local->hw.queues >= IEEE80211_NUM_ACS) { - *pos++ = WLAN_EID_VENDOR_SPECIFIC; - *pos++ = 7; /* len */ - *pos++ = 0x00; /* Microsoft OUI 00:50:F2 */ - *pos++ = 0x50; - *pos++ = 0xf2; - *pos++ = 2; /* WME */ - *pos++ = 0; /* WME info */ - *pos++ = 1; /* WME ver */ - *pos++ = 0; /* U-APSD no in use */ - } + if (local->hw.queues >= IEEE80211_NUM_ACS) + pos = ieee80211_add_wmm_info_ie(pos, 0); /* U-APSD not in use */ presp->head_len = pos - presp->head; if (WARN_ON(presp->head_len > frame_len)) diff --git a/net/mac80211/ieee80211_i.h b/net/mac80211/ieee80211_i.h index ac9836e0aab3..ef7a089ac546 100644 --- a/net/mac80211/ieee80211_i.h +++ b/net/mac80211/ieee80211_i.h @@ -229,16 +229,29 @@ struct ieee80211_rx_data { u16 tkip_iv16; }; +struct ieee80211_csa_settings { + const u16 *counter_offsets_beacon; + const u16 *counter_offsets_presp; + + int n_counter_offsets_beacon; + int n_counter_offsets_presp; + + u8 count; +}; + struct beacon_data { u8 *head, *tail; int head_len, tail_len; struct ieee80211_meshconf_ie *meshconf; + u16 csa_counter_offsets[IEEE80211_MAX_CSA_COUNTERS_NUM]; + u8 csa_current_counter; struct rcu_head rcu_head; }; struct probe_resp { struct rcu_head rcu_head; int len; + u16 csa_counter_offsets[IEEE80211_MAX_CSA_COUNTERS_NUM]; u8 data[0]; }; @@ -332,7 +345,6 @@ enum ieee80211_sta_flags { IEEE80211_STA_CONNECTION_POLL = BIT(1), IEEE80211_STA_CONTROL_PORT = BIT(2), IEEE80211_STA_DISABLE_HT = BIT(4), - IEEE80211_STA_CSA_RECEIVED = BIT(5), IEEE80211_STA_MFP_ENABLED = BIT(6), IEEE80211_STA_UAPSD_ENABLED = BIT(7), IEEE80211_STA_NULLFUNC_ACKED = BIT(8), @@ -490,6 +502,9 @@ struct ieee80211_if_managed { struct ieee80211_ht_cap ht_capa_mask; /* Valid parts of ht_capa */ struct ieee80211_vht_cap vht_capa; /* configured VHT overrides */ struct ieee80211_vht_cap vht_capa_mask; /* Valid parts of vht_capa */ + + u8 tdls_peer[ETH_ALEN] __aligned(2); + struct delayed_work tdls_peer_del_work; }; struct ieee80211_if_ibss { @@ -688,6 +703,24 @@ enum ieee80211_chanctx_mode { IEEE80211_CHANCTX_EXCLUSIVE }; +/** + * enum ieee80211_chanctx_replace_state - channel context replacement state + * + * This is used for channel context in-place reservations that require channel + * context switch/swap. + * + * @IEEE80211_CHANCTX_REPLACE_NONE: no replacement is taking place + * @IEEE80211_CHANCTX_WILL_BE_REPLACED: this channel context will be replaced + * by a (not yet registered) channel context pointed by %replace_ctx. + * @IEEE80211_CHANCTX_REPLACES_OTHER: this (not yet registered) channel context + * replaces an existing channel context pointed to by %replace_ctx. + */ +enum ieee80211_chanctx_replace_state { + IEEE80211_CHANCTX_REPLACE_NONE, + IEEE80211_CHANCTX_WILL_BE_REPLACED, + IEEE80211_CHANCTX_REPLACES_OTHER, +}; + struct ieee80211_chanctx { struct list_head list; struct rcu_head rcu_head; @@ -695,6 +728,9 @@ struct ieee80211_chanctx { struct list_head assigned_vifs; struct list_head reserved_vifs; + enum ieee80211_chanctx_replace_state replace_state; + struct ieee80211_chanctx *replace_ctx; + enum ieee80211_chanctx_mode mode; bool driver_present; @@ -754,9 +790,6 @@ struct ieee80211_sub_if_data { struct mac80211_qos_map __rcu *qos_map; struct work_struct csa_finalize_work; - u16 csa_counter_offset_beacon[IEEE80211_MAX_CSA_COUNTERS_NUM]; - u16 csa_counter_offset_presp[IEEE80211_MAX_CSA_COUNTERS_NUM]; - bool csa_radar_required; bool csa_block_tx; /* write-protected by sdata_lock and local->mtx */ struct cfg80211_chan_def csa_chandef; @@ -767,7 +800,7 @@ struct ieee80211_sub_if_data { struct ieee80211_chanctx *reserved_chanctx; struct cfg80211_chan_def reserved_chandef; bool reserved_radar_required; - u8 csa_current_counter; + bool reserved_ready; /* used to reconfigure hardware SM PS */ struct work_struct recalc_smps; @@ -892,10 +925,17 @@ ieee80211_vif_get_shift(struct ieee80211_vif *vif) return shift; } +struct ieee80211_rx_agg { + u8 addr[ETH_ALEN]; + u16 tid; +}; + enum sdata_queue_type { IEEE80211_SDATA_QUEUE_TYPE_FRAME = 0, IEEE80211_SDATA_QUEUE_AGG_START = 1, IEEE80211_SDATA_QUEUE_AGG_STOP = 2, + IEEE80211_SDATA_QUEUE_RX_AGG_START = 3, + IEEE80211_SDATA_QUEUE_RX_AGG_STOP = 4, }; enum { @@ -912,6 +952,9 @@ enum queue_stop_reason { IEEE80211_QUEUE_STOP_REASON_SKB_ADD, IEEE80211_QUEUE_STOP_REASON_OFFCHANNEL, IEEE80211_QUEUE_STOP_REASON_FLUSH, + IEEE80211_QUEUE_STOP_REASON_TDLS_TEARDOWN, + + IEEE80211_QUEUE_STOP_REASONS, }; #ifdef CONFIG_MAC80211_LEDS @@ -1008,6 +1051,7 @@ struct ieee80211_local { struct workqueue_struct *workqueue; unsigned long queue_stop_reasons[IEEE80211_MAX_QUEUES]; + int q_stop_reasons[IEEE80211_MAX_QUEUES][IEEE80211_QUEUE_STOP_REASONS]; /* also used to protect ampdu_ac_queue and amdpu_ac_stop_refcnt */ spinlock_t queue_stop_reason_lock; @@ -1135,7 +1179,8 @@ struct ieee80211_local { unsigned long scanning; struct cfg80211_ssid scan_ssid; struct cfg80211_scan_request *int_scan_req; - struct cfg80211_scan_request *scan_req, *hw_scan_req; + struct cfg80211_scan_request *scan_req; + struct ieee80211_scan_request *hw_scan_req; struct cfg80211_chan_def scan_chandef; enum ieee80211_band hw_scan_band; int scan_channel_idx; @@ -1476,7 +1521,6 @@ void ieee80211_sw_roc_work(struct work_struct *work); void ieee80211_handle_roc_started(struct ieee80211_roc_work *roc); /* channel switch handling */ -bool ieee80211_csa_needs_block_tx(struct ieee80211_local *local); void ieee80211_csa_finalize_work(struct work_struct *work); int ieee80211_channel_switch(struct wiphy *wiphy, struct net_device *dev, struct cfg80211_csa_settings *params); @@ -1540,6 +1584,10 @@ void ___ieee80211_stop_rx_ba_session(struct sta_info *sta, u16 tid, u16 initiator, u16 reason, bool stop); void __ieee80211_stop_rx_ba_session(struct sta_info *sta, u16 tid, u16 initiator, u16 reason, bool stop); +void __ieee80211_start_rx_ba_session(struct sta_info *sta, + u8 dialog_token, u16 timeout, + u16 start_seq_num, u16 ba_policy, u16 tid, + u16 buf_size, bool tx); void ieee80211_sta_tear_down_BA_sessions(struct sta_info *sta, enum ieee80211_agg_stop_reason reason); void ieee80211_process_delba(struct ieee80211_sub_if_data *sdata, @@ -1692,6 +1740,21 @@ static inline void ieee802_11_parse_elems(const u8 *start, size_t len, ieee802_11_parse_elems_crc(start, len, action, elems, 0, 0); } +static inline bool ieee80211_rx_reorder_ready(struct sk_buff_head *frames) +{ + struct sk_buff *tail = skb_peek_tail(frames); + struct ieee80211_rx_status *status; + + if (!tail) + return false; + + status = IEEE80211_SKB_RXCB(tail); + if (status->flag & RX_FLAG_AMSDU_MORE) + return false; + + return true; +} + void ieee80211_dynamic_ps_enable_work(struct work_struct *work); void ieee80211_dynamic_ps_disable_work(struct work_struct *work); void ieee80211_dynamic_ps_timer(unsigned long data); @@ -1705,14 +1768,24 @@ void ieee80211_sta_tx_notify(struct ieee80211_sub_if_data *sdata, void ieee80211_wake_queues_by_reason(struct ieee80211_hw *hw, unsigned long queues, - enum queue_stop_reason reason); + enum queue_stop_reason reason, + bool refcounted); +void ieee80211_stop_vif_queues(struct ieee80211_local *local, + struct ieee80211_sub_if_data *sdata, + enum queue_stop_reason reason); +void ieee80211_wake_vif_queues(struct ieee80211_local *local, + struct ieee80211_sub_if_data *sdata, + enum queue_stop_reason reason); void ieee80211_stop_queues_by_reason(struct ieee80211_hw *hw, unsigned long queues, - enum queue_stop_reason reason); + enum queue_stop_reason reason, + bool refcounted); void ieee80211_wake_queue_by_reason(struct ieee80211_hw *hw, int queue, - enum queue_stop_reason reason); + enum queue_stop_reason reason, + bool refcounted); void ieee80211_stop_queue_by_reason(struct ieee80211_hw *hw, int queue, - enum queue_stop_reason reason); + enum queue_stop_reason reason, + bool refcounted); void ieee80211_propagate_queue_wake(struct ieee80211_local *local, int queue); void ieee80211_add_pending_skb(struct ieee80211_local *local, struct sk_buff *skb); @@ -1730,8 +1803,10 @@ void ieee80211_send_deauth_disassoc(struct ieee80211_sub_if_data *sdata, const u8 *bssid, u16 stype, u16 reason, bool send_frame, u8 *frame_buf); int ieee80211_build_preq_ies(struct ieee80211_local *local, u8 *buffer, - size_t buffer_len, const u8 *ie, size_t ie_len, - enum ieee80211_band band, u32 rate_mask, + size_t buffer_len, + struct ieee80211_scan_ies *ie_desc, + const u8 *ie, size_t ie_len, + u8 bands_used, u32 *rate_masks, struct cfg80211_chan_def *chandef); struct sk_buff *ieee80211_build_probe_req(struct ieee80211_sub_if_data *sdata, u8 *dst, u32 ratemask, @@ -1774,6 +1849,7 @@ int ieee80211_add_srates_ie(struct ieee80211_sub_if_data *sdata, int ieee80211_add_ext_srates_ie(struct ieee80211_sub_if_data *sdata, struct sk_buff *skb, bool need_basic, enum ieee80211_band band); +u8 *ieee80211_add_wmm_info_ie(u8 *buf, u8 qosinfo); /* channel management */ void ieee80211_ht_oper_to_chandef(struct ieee80211_channel *control_chan, @@ -1791,18 +1867,14 @@ ieee80211_vif_reserve_chanctx(struct ieee80211_sub_if_data *sdata, enum ieee80211_chanctx_mode mode, bool radar_required); int __must_check -ieee80211_vif_use_reserved_context(struct ieee80211_sub_if_data *sdata, - u32 *changed); +ieee80211_vif_use_reserved_context(struct ieee80211_sub_if_data *sdata); int ieee80211_vif_unreserve_chanctx(struct ieee80211_sub_if_data *sdata); +int ieee80211_vif_use_reserved_switch(struct ieee80211_local *local); int __must_check ieee80211_vif_change_bandwidth(struct ieee80211_sub_if_data *sdata, const struct cfg80211_chan_def *chandef, u32 *changed); -/* NOTE: only use ieee80211_vif_change_channel() for channel switch */ -int __must_check -ieee80211_vif_change_channel(struct ieee80211_sub_if_data *sdata, - u32 *changed); void ieee80211_vif_release_channel(struct ieee80211_sub_if_data *sdata); void ieee80211_vif_vlan_copy_chanctx(struct ieee80211_sub_if_data *sdata); void ieee80211_vif_copy_chanctx_to_vlans(struct ieee80211_sub_if_data *sdata, @@ -1842,11 +1914,14 @@ int ieee80211_max_num_channels(struct ieee80211_local *local); int ieee80211_tdls_mgmt(struct wiphy *wiphy, struct net_device *dev, const u8 *peer, u8 action_code, u8 dialog_token, u16 status_code, u32 peer_capability, - const u8 *extra_ies, size_t extra_ies_len); + bool initiator, const u8 *extra_ies, + size_t extra_ies_len); int ieee80211_tdls_oper(struct wiphy *wiphy, struct net_device *dev, const u8 *peer, enum nl80211_tdls_operation oper); +extern const struct ethtool_ops ieee80211_ethtool_ops; + #ifdef CONFIG_MAC80211_NOINLINE #define debug_noinline noinline #else @@ -1854,3 +1929,4 @@ int ieee80211_tdls_oper(struct wiphy *wiphy, struct net_device *dev, #endif #endif /* IEEE80211_I_H */ +void ieee80211_tdls_peer_del_work(struct work_struct *wk); diff --git a/net/mac80211/iface.c b/net/mac80211/iface.c index 388b863e821c..01eede7406a5 100644 --- a/net/mac80211/iface.c +++ b/net/mac80211/iface.c @@ -841,10 +841,11 @@ static void ieee80211_do_stop(struct ieee80211_sub_if_data *sdata, sdata_lock(sdata); mutex_lock(&local->mtx); sdata->vif.csa_active = false; - if (!ieee80211_csa_needs_block_tx(local)) - ieee80211_wake_queues_by_reason(&local->hw, - IEEE80211_MAX_QUEUE_MAP, - IEEE80211_QUEUE_STOP_REASON_CSA); + if (sdata->csa_block_tx) { + ieee80211_wake_vif_queues(local, sdata, + IEEE80211_QUEUE_STOP_REASON_CSA); + sdata->csa_block_tx = false; + } mutex_unlock(&local->mtx); sdata_unlock(sdata); @@ -1139,6 +1140,7 @@ static void ieee80211_iface_work(struct work_struct *work) struct sk_buff *skb; struct sta_info *sta; struct ieee80211_ra_tid *ra_tid; + struct ieee80211_rx_agg *rx_agg; if (!ieee80211_sdata_running(sdata)) return; @@ -1166,6 +1168,34 @@ static void ieee80211_iface_work(struct work_struct *work) ra_tid = (void *)&skb->cb; ieee80211_stop_tx_ba_cb(&sdata->vif, ra_tid->ra, ra_tid->tid); + } else if (skb->pkt_type == IEEE80211_SDATA_QUEUE_RX_AGG_START) { + rx_agg = (void *)&skb->cb; + mutex_lock(&local->sta_mtx); + sta = sta_info_get_bss(sdata, rx_agg->addr); + if (sta) { + u16 last_seq; + + last_seq = le16_to_cpu( + sta->last_seq_ctrl[rx_agg->tid]); + + __ieee80211_start_rx_ba_session(sta, + 0, 0, + ieee80211_sn_inc(last_seq), + 1, rx_agg->tid, + IEEE80211_MAX_AMPDU_BUF, + false); + } + mutex_unlock(&local->sta_mtx); + } else if (skb->pkt_type == IEEE80211_SDATA_QUEUE_RX_AGG_STOP) { + rx_agg = (void *)&skb->cb; + mutex_lock(&local->sta_mtx); + sta = sta_info_get_bss(sdata, rx_agg->addr); + if (sta) + __ieee80211_stop_rx_ba_session(sta, + rx_agg->tid, + WLAN_BACK_RECIPIENT, 0, + false); + mutex_unlock(&local->sta_mtx); } else if (ieee80211_is_action(mgmt->frame_control) && mgmt->u.action.category == WLAN_CATEGORY_BACK) { int len = skb->len; @@ -1623,9 +1653,9 @@ int ieee80211_if_add(struct ieee80211_local *local, const char *name, if (local->hw.queues >= IEEE80211_NUM_ACS) txqs = IEEE80211_NUM_ACS; - ndev = alloc_netdev_mqs(sizeof(*sdata) + - local->hw.vif_data_size, - name, ieee80211_if_setup, txqs, 1); + ndev = alloc_netdev_mqs(sizeof(*sdata) + local->hw.vif_data_size, + name, NET_NAME_UNKNOWN, + ieee80211_if_setup, txqs, 1); if (!ndev) return -ENOMEM; dev_net_set(ndev, wiphy_net(local->hw.wiphy)); @@ -1705,6 +1735,8 @@ int ieee80211_if_add(struct ieee80211_local *local, const char *name, ndev->features |= local->hw.netdev_features; + netdev_set_default_ethtool_ops(ndev, &ieee80211_ethtool_ops); + ret = register_netdevice(ndev); if (ret) { free_netdev(ndev); diff --git a/net/mac80211/key.c b/net/mac80211/key.c index 16d97f044a20..d808cff80153 100644 --- a/net/mac80211/key.c +++ b/net/mac80211/key.c @@ -482,9 +482,6 @@ int ieee80211_key_link(struct ieee80211_key *key, int idx, ret; bool pairwise; - if (WARN_ON(!sdata || !key)) - return -EINVAL; - pairwise = key->conf.flags & IEEE80211_KEY_FLAG_PAIRWISE; idx = key->conf.keyidx; key->local = sdata->local; diff --git a/net/mac80211/main.c b/net/mac80211/main.c index d17c26d6e369..e0ab4320a078 100644 --- a/net/mac80211/main.c +++ b/net/mac80211/main.c @@ -272,7 +272,8 @@ void ieee80211_restart_hw(struct ieee80211_hw *hw) /* use this reason, ieee80211_reconfig will unblock it */ ieee80211_stop_queues_by_reason(hw, IEEE80211_MAX_QUEUE_MAP, - IEEE80211_QUEUE_STOP_REASON_SUSPEND); + IEEE80211_QUEUE_STOP_REASON_SUSPEND, + false); /* * Stop all Rx during the reconfig. We don't want state changes @@ -1187,18 +1188,12 @@ static int __init ieee80211_init(void) if (ret) goto err_minstrel; - ret = rc80211_pid_init(); - if (ret) - goto err_pid; - ret = ieee80211_iface_init(); if (ret) goto err_netdev; return 0; err_netdev: - rc80211_pid_exit(); - err_pid: rc80211_minstrel_ht_exit(); err_minstrel: rc80211_minstrel_exit(); @@ -1208,7 +1203,6 @@ static int __init ieee80211_init(void) static void __exit ieee80211_exit(void) { - rc80211_pid_exit(); rc80211_minstrel_ht_exit(); rc80211_minstrel_exit(); diff --git a/net/mac80211/mesh.c b/net/mac80211/mesh.c index 6495a3f0428d..e9f99c1e3fad 100644 --- a/net/mac80211/mesh.c +++ b/net/mac80211/mesh.c @@ -679,7 +679,7 @@ ieee80211_mesh_build_beacon(struct ieee80211_if_mesh *ifmsh) *pos++ = 0x0; *pos++ = ieee80211_frequency_to_channel( csa->settings.chandef.chan->center_freq); - sdata->csa_counter_offset_beacon[0] = hdr_len + 6; + bcn->csa_counter_offsets[0] = hdr_len + 6; *pos++ = csa->settings.count; *pos++ = WLAN_EID_CHAN_SWITCH_PARAM; *pos++ = 6; @@ -1122,7 +1122,7 @@ static int mesh_fwd_csa_frame(struct ieee80211_sub_if_data *sdata, mgmt_fwd = (struct ieee80211_mgmt *) skb_put(skb, len); /* offset_ttl is based on whether the secondary channel - * offset is available or not. Substract 1 from the mesh TTL + * offset is available or not. Subtract 1 from the mesh TTL * and disable the initiator flag before forwarding. */ offset_ttl = (len < 42) ? 7 : 10; diff --git a/net/mac80211/mesh_hwmp.c b/net/mac80211/mesh_hwmp.c index 94758b9c9ed4..214e63b84e5c 100644 --- a/net/mac80211/mesh_hwmp.c +++ b/net/mac80211/mesh_hwmp.c @@ -157,7 +157,6 @@ static int mesh_path_sel_frame_tx(enum mpath_frame_type action, u8 flags, default: kfree_skb(skb); return -ENOTSUPP; - break; } *pos++ = ie_len; *pos++ = flags; diff --git a/net/mac80211/mesh_plink.c b/net/mac80211/mesh_plink.c index e8f60aa2e848..63b874101b27 100644 --- a/net/mac80211/mesh_plink.c +++ b/net/mac80211/mesh_plink.c @@ -551,11 +551,30 @@ static void mesh_plink_timer(unsigned long data) return; spin_lock_bh(&sta->lock); - if (sta->ignore_plink_timer) { - sta->ignore_plink_timer = false; + + /* If a timer fires just before a state transition on another CPU, + * we may have already extended the timeout and changed state by the + * time we've acquired the lock and arrived here. In that case, + * skip this timer and wait for the new one. + */ + if (time_before(jiffies, sta->plink_timer.expires)) { + mpl_dbg(sta->sdata, + "Ignoring timer for %pM in state %s (timer adjusted)", + sta->sta.addr, mplstates[sta->plink_state]); spin_unlock_bh(&sta->lock); return; } + + /* del_timer() and handler may race when entering these states */ + if (sta->plink_state == NL80211_PLINK_LISTEN || + sta->plink_state == NL80211_PLINK_ESTAB) { + mpl_dbg(sta->sdata, + "Ignoring timer for %pM in state %s (timer deleted)", + sta->sta.addr, mplstates[sta->plink_state]); + spin_unlock_bh(&sta->lock); + return; + } + mpl_dbg(sta->sdata, "Mesh plink timer for %pM fired on state %s\n", sta->sta.addr, mplstates[sta->plink_state]); @@ -773,9 +792,7 @@ static u32 mesh_plink_fsm(struct ieee80211_sub_if_data *sdata, break; case CNF_ACPT: sta->plink_state = NL80211_PLINK_CNF_RCVD; - if (!mod_plink_timer(sta, - mshcfg->dot11MeshConfirmTimeout)) - sta->ignore_plink_timer = true; + mod_plink_timer(sta, mshcfg->dot11MeshConfirmTimeout); break; default: break; @@ -834,8 +851,7 @@ static u32 mesh_plink_fsm(struct ieee80211_sub_if_data *sdata, case NL80211_PLINK_HOLDING: switch (event) { case CLS_ACPT: - if (del_timer(&sta->plink_timer)) - sta->ignore_plink_timer = 1; + del_timer(&sta->plink_timer); mesh_plink_fsm_restart(sta); break; case OPN_ACPT: diff --git a/net/mac80211/mlme.c b/net/mac80211/mlme.c index 3345401be1b3..31a8afaf7332 100644 --- a/net/mac80211/mlme.c +++ b/net/mac80211/mlme.c @@ -830,16 +830,7 @@ static void ieee80211_send_assoc(struct ieee80211_sub_if_data *sdata) qos_info = 0; } - pos = skb_put(skb, 9); - *pos++ = WLAN_EID_VENDOR_SPECIFIC; - *pos++ = 7; /* len */ - *pos++ = 0x00; /* Microsoft OUI 00:50:F2 */ - *pos++ = 0x50; - *pos++ = 0xf2; - *pos++ = 2; /* WME */ - *pos++ = 0; /* WME info */ - *pos++ = 1; /* WME ver */ - *pos++ = qos_info; + pos = ieee80211_add_wmm_info_ie(skb_put(skb, 9), qos_info); } /* add any remaining custom (i.e. vendor specific here) IEs */ @@ -940,58 +931,77 @@ static void ieee80211_chswitch_work(struct work_struct *work) container_of(work, struct ieee80211_sub_if_data, u.mgd.chswitch_work); struct ieee80211_local *local = sdata->local; struct ieee80211_if_managed *ifmgd = &sdata->u.mgd; - u32 changed = 0; int ret; if (!ieee80211_sdata_running(sdata)) return; sdata_lock(sdata); + mutex_lock(&local->mtx); + mutex_lock(&local->chanctx_mtx); + if (!ifmgd->associated) goto out; - mutex_lock(&local->mtx); - ret = ieee80211_vif_change_channel(sdata, &changed); - mutex_unlock(&local->mtx); - if (ret) { + if (!sdata->vif.csa_active) + goto out; + + /* + * using reservation isn't immediate as it may be deferred until later + * with multi-vif. once reservation is complete it will re-schedule the + * work with no reserved_chanctx so verify chandef to check if it + * completed successfully + */ + + if (sdata->reserved_chanctx) { + /* + * with multi-vif csa driver may call ieee80211_csa_finish() + * many times while waiting for other interfaces to use their + * reservations + */ + if (sdata->reserved_ready) + goto out; + + ret = ieee80211_vif_use_reserved_context(sdata); + if (ret) { + sdata_info(sdata, + "failed to use reserved channel context, disconnecting (err=%d)\n", + ret); + ieee80211_queue_work(&sdata->local->hw, + &ifmgd->csa_connection_drop_work); + goto out; + } + + goto out; + } + + if (!cfg80211_chandef_identical(&sdata->vif.bss_conf.chandef, + &sdata->csa_chandef)) { sdata_info(sdata, - "vif channel switch failed, disconnecting\n"); + "failed to finalize channel switch, disconnecting\n"); ieee80211_queue_work(&sdata->local->hw, &ifmgd->csa_connection_drop_work); goto out; } - if (!local->use_chanctx) { - local->_oper_chandef = sdata->csa_chandef; - /* Call "hw_config" only if doing sw channel switch. - * Otherwise update the channel directly - */ - if (!local->ops->channel_switch) - ieee80211_hw_config(local, 0); - else - local->hw.conf.chandef = local->_oper_chandef; - } - /* XXX: shouldn't really modify cfg80211-owned data! */ ifmgd->associated->channel = sdata->csa_chandef.chan; - ieee80211_bss_info_change_notify(sdata, changed); - - mutex_lock(&local->mtx); sdata->vif.csa_active = false; - /* XXX: wait for a beacon first? */ - if (!ieee80211_csa_needs_block_tx(local)) - ieee80211_wake_queues_by_reason(&local->hw, - IEEE80211_MAX_QUEUE_MAP, - IEEE80211_QUEUE_STOP_REASON_CSA); - mutex_unlock(&local->mtx); - ifmgd->flags &= ~IEEE80211_STA_CSA_RECEIVED; + /* XXX: wait for a beacon first? */ + if (sdata->csa_block_tx) { + ieee80211_wake_vif_queues(local, sdata, + IEEE80211_QUEUE_STOP_REASON_CSA); + sdata->csa_block_tx = false; + } ieee80211_sta_reset_beacon_monitor(sdata); ieee80211_sta_reset_conn_monitor(sdata); out: + mutex_unlock(&local->chanctx_mtx); + mutex_unlock(&local->mtx); sdata_unlock(sdata); } @@ -1028,6 +1038,7 @@ ieee80211_sta_process_chanswitch(struct ieee80211_sub_if_data *sdata, struct ieee80211_local *local = sdata->local; struct ieee80211_if_managed *ifmgd = &sdata->u.mgd; struct cfg80211_bss *cbss = ifmgd->associated; + struct ieee80211_chanctx_conf *conf; struct ieee80211_chanctx *chanctx; enum ieee80211_band current_band; struct ieee80211_csa_ie csa_ie; @@ -1042,7 +1053,7 @@ ieee80211_sta_process_chanswitch(struct ieee80211_sub_if_data *sdata, return; /* disregard subsequent announcements if we are already processing */ - if (ifmgd->flags & IEEE80211_STA_CSA_RECEIVED) + if (sdata->vif.csa_active) return; current_band = cbss->channel->band; @@ -1069,9 +1080,22 @@ ieee80211_sta_process_chanswitch(struct ieee80211_sub_if_data *sdata, return; } - ifmgd->flags |= IEEE80211_STA_CSA_RECEIVED; - + mutex_lock(&local->mtx); mutex_lock(&local->chanctx_mtx); + conf = rcu_dereference_protected(sdata->vif.chanctx_conf, + lockdep_is_held(&local->chanctx_mtx)); + if (!conf) { + sdata_info(sdata, + "no channel context assigned to vif?, disconnecting\n"); + ieee80211_queue_work(&local->hw, + &ifmgd->csa_connection_drop_work); + mutex_unlock(&local->chanctx_mtx); + mutex_unlock(&local->mtx); + return; + } + + chanctx = container_of(conf, struct ieee80211_chanctx, conf); + if (local->use_chanctx) { u32 num_chanctx = 0; list_for_each_entry(chanctx, &local->chanctx_list, list) @@ -1084,38 +1108,32 @@ ieee80211_sta_process_chanswitch(struct ieee80211_sub_if_data *sdata, ieee80211_queue_work(&local->hw, &ifmgd->csa_connection_drop_work); mutex_unlock(&local->chanctx_mtx); + mutex_unlock(&local->mtx); return; } } - if (WARN_ON(!rcu_access_pointer(sdata->vif.chanctx_conf))) { - ieee80211_queue_work(&local->hw, - &ifmgd->csa_connection_drop_work); - mutex_unlock(&local->chanctx_mtx); - return; - } - chanctx = container_of(rcu_access_pointer(sdata->vif.chanctx_conf), - struct ieee80211_chanctx, conf); - if (ieee80211_chanctx_refcount(local, chanctx) > 1) { + res = ieee80211_vif_reserve_chanctx(sdata, &csa_ie.chandef, + chanctx->mode, false); + if (res) { sdata_info(sdata, - "channel switch with multiple interfaces on the same channel, disconnecting\n"); + "failed to reserve channel context for channel switch, disconnecting (err=%d)\n", + res); ieee80211_queue_work(&local->hw, &ifmgd->csa_connection_drop_work); mutex_unlock(&local->chanctx_mtx); + mutex_unlock(&local->mtx); return; } mutex_unlock(&local->chanctx_mtx); - sdata->csa_chandef = csa_ie.chandef; - - mutex_lock(&local->mtx); sdata->vif.csa_active = true; + sdata->csa_chandef = csa_ie.chandef; sdata->csa_block_tx = csa_ie.mode; if (sdata->csa_block_tx) - ieee80211_stop_queues_by_reason(&local->hw, - IEEE80211_MAX_QUEUE_MAP, - IEEE80211_QUEUE_STOP_REASON_CSA); + ieee80211_stop_vif_queues(local, sdata, + IEEE80211_QUEUE_STOP_REASON_CSA); mutex_unlock(&local->mtx); if (local->ops->channel_switch) { @@ -1385,7 +1403,8 @@ void ieee80211_dynamic_ps_disable_work(struct work_struct *work) ieee80211_wake_queues_by_reason(&local->hw, IEEE80211_MAX_QUEUE_MAP, - IEEE80211_QUEUE_STOP_REASON_PS); + IEEE80211_QUEUE_STOP_REASON_PS, + false); } void ieee80211_dynamic_ps_enable_work(struct work_struct *work) @@ -1830,10 +1849,11 @@ static void ieee80211_set_disassoc(struct ieee80211_sub_if_data *sdata, ieee80211_vif_release_channel(sdata); sdata->vif.csa_active = false; - if (!ieee80211_csa_needs_block_tx(local)) - ieee80211_wake_queues_by_reason(&local->hw, - IEEE80211_MAX_QUEUE_MAP, - IEEE80211_QUEUE_STOP_REASON_CSA); + if (sdata->csa_block_tx) { + ieee80211_wake_vif_queues(local, sdata, + IEEE80211_QUEUE_STOP_REASON_CSA); + sdata->csa_block_tx = false; + } mutex_unlock(&local->mtx); sdata->encrypt_headroom = IEEE80211_ENCRYPT_HEADROOM; @@ -2075,14 +2095,13 @@ static void __ieee80211_disconnect(struct ieee80211_sub_if_data *sdata) ieee80211_set_disassoc(sdata, IEEE80211_STYPE_DEAUTH, WLAN_REASON_DISASSOC_DUE_TO_INACTIVITY, true, frame_buf); - ifmgd->flags &= ~IEEE80211_STA_CSA_RECEIVED; - mutex_lock(&local->mtx); sdata->vif.csa_active = false; - if (!ieee80211_csa_needs_block_tx(local)) - ieee80211_wake_queues_by_reason(&local->hw, - IEEE80211_MAX_QUEUE_MAP, - IEEE80211_QUEUE_STOP_REASON_CSA); + if (sdata->csa_block_tx) { + ieee80211_wake_vif_queues(local, sdata, + IEEE80211_QUEUE_STOP_REASON_CSA); + sdata->csa_block_tx = false; + } mutex_unlock(&local->mtx); cfg80211_tx_mlme_mgmt(sdata->dev, frame_buf, @@ -3688,6 +3707,8 @@ void ieee80211_sta_setup_sdata(struct ieee80211_sub_if_data *sdata) INIT_WORK(&ifmgd->csa_connection_drop_work, ieee80211_csa_connection_drop_work); INIT_WORK(&ifmgd->request_smps_work, ieee80211_request_smps_mgd_work); + INIT_DELAYED_WORK(&ifmgd->tdls_peer_del_work, + ieee80211_tdls_peer_del_work); setup_timer(&ifmgd->timer, ieee80211_sta_timer, (unsigned long) sdata); setup_timer(&ifmgd->bcn_mon_timer, ieee80211_sta_bcn_mon_timer, @@ -4551,6 +4572,7 @@ void ieee80211_mgd_stop(struct ieee80211_sub_if_data *sdata) cancel_work_sync(&ifmgd->request_smps_work); cancel_work_sync(&ifmgd->csa_connection_drop_work); cancel_work_sync(&ifmgd->chswitch_work); + cancel_delayed_work_sync(&ifmgd->tdls_peer_del_work); sdata_lock(sdata); if (ifmgd->assoc_data) { diff --git a/net/mac80211/offchannel.c b/net/mac80211/offchannel.c index 7a17decd27f9..ff20b2ebdb30 100644 --- a/net/mac80211/offchannel.c +++ b/net/mac80211/offchannel.c @@ -119,7 +119,8 @@ void ieee80211_offchannel_stop_vifs(struct ieee80211_local *local) * before sending nullfunc to enable powersave at the AP. */ ieee80211_stop_queues_by_reason(&local->hw, IEEE80211_MAX_QUEUE_MAP, - IEEE80211_QUEUE_STOP_REASON_OFFCHANNEL); + IEEE80211_QUEUE_STOP_REASON_OFFCHANNEL, + false); ieee80211_flush_queues(local, NULL); mutex_lock(&local->iflist_mtx); @@ -182,7 +183,8 @@ void ieee80211_offchannel_return(struct ieee80211_local *local) mutex_unlock(&local->iflist_mtx); ieee80211_wake_queues_by_reason(&local->hw, IEEE80211_MAX_QUEUE_MAP, - IEEE80211_QUEUE_STOP_REASON_OFFCHANNEL); + IEEE80211_QUEUE_STOP_REASON_OFFCHANNEL, + false); } void ieee80211_handle_roc_started(struct ieee80211_roc_work *roc) diff --git a/net/mac80211/pm.c b/net/mac80211/pm.c index d478b880a0af..4c5192e0d66c 100644 --- a/net/mac80211/pm.c +++ b/net/mac80211/pm.c @@ -35,7 +35,8 @@ int __ieee80211_suspend(struct ieee80211_hw *hw, struct cfg80211_wowlan *wowlan) ieee80211_stop_queues_by_reason(hw, IEEE80211_MAX_QUEUE_MAP, - IEEE80211_QUEUE_STOP_REASON_SUSPEND); + IEEE80211_QUEUE_STOP_REASON_SUSPEND, + false); /* flush out all packets */ synchronize_net(); @@ -74,7 +75,8 @@ int __ieee80211_suspend(struct ieee80211_hw *hw, struct cfg80211_wowlan *wowlan) } ieee80211_wake_queues_by_reason(hw, IEEE80211_MAX_QUEUE_MAP, - IEEE80211_QUEUE_STOP_REASON_SUSPEND); + IEEE80211_QUEUE_STOP_REASON_SUSPEND, + false); return err; } else if (err > 0) { WARN_ON(err != 1); diff --git a/net/mac80211/rate.h b/net/mac80211/rate.h index 9aa2a1190a86..18babe302832 100644 --- a/net/mac80211/rate.h +++ b/net/mac80211/rate.h @@ -143,19 +143,6 @@ void rate_control_deinitialize(struct ieee80211_local *local); /* Rate control algorithms */ -#ifdef CONFIG_MAC80211_RC_PID -int rc80211_pid_init(void); -void rc80211_pid_exit(void); -#else -static inline int rc80211_pid_init(void) -{ - return 0; -} -static inline void rc80211_pid_exit(void) -{ -} -#endif - #ifdef CONFIG_MAC80211_RC_MINSTREL int rc80211_minstrel_init(void); void rc80211_minstrel_exit(void); diff --git a/net/mac80211/rc80211_pid.h b/net/mac80211/rc80211_pid.h deleted file mode 100644 index 19111c7bf454..000000000000 --- a/net/mac80211/rc80211_pid.h +++ /dev/null @@ -1,278 +0,0 @@ -/* - * Copyright 2007, Mattias Nissler <mattias.nissler@gmx.de> - * Copyright 2007, Stefano Brivio <stefano.brivio@polimi.it> - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License version 2 as - * published by the Free Software Foundation. - */ - -#ifndef RC80211_PID_H -#define RC80211_PID_H - -/* Sampling period for measuring percentage of failed frames in ms. */ -#define RC_PID_INTERVAL 125 - -/* Exponential averaging smoothness (used for I part of PID controller) */ -#define RC_PID_SMOOTHING_SHIFT 3 -#define RC_PID_SMOOTHING (1 << RC_PID_SMOOTHING_SHIFT) - -/* Sharpening factor (used for D part of PID controller) */ -#define RC_PID_SHARPENING_FACTOR 0 -#define RC_PID_SHARPENING_DURATION 0 - -/* Fixed point arithmetic shifting amount. */ -#define RC_PID_ARITH_SHIFT 8 - -/* Proportional PID component coefficient. */ -#define RC_PID_COEFF_P 15 -/* Integral PID component coefficient. */ -#define RC_PID_COEFF_I 9 -/* Derivative PID component coefficient. */ -#define RC_PID_COEFF_D 15 - -/* Target failed frames rate for the PID controller. NB: This effectively gives - * maximum failed frames percentage we're willing to accept. If the wireless - * link quality is good, the controller will fail to adjust failed frames - * percentage to the target. This is intentional. - */ -#define RC_PID_TARGET_PF 14 - -/* Rate behaviour normalization quantity over time. */ -#define RC_PID_NORM_OFFSET 3 - -/* Push high rates right after loading. */ -#define RC_PID_FAST_START 0 - -/* Arithmetic right shift for positive and negative values for ISO C. */ -#define RC_PID_DO_ARITH_RIGHT_SHIFT(x, y) \ - ((x) < 0 ? -((-(x)) >> (y)) : (x) >> (y)) - -enum rc_pid_event_type { - RC_PID_EVENT_TYPE_TX_STATUS, - RC_PID_EVENT_TYPE_RATE_CHANGE, - RC_PID_EVENT_TYPE_TX_RATE, - RC_PID_EVENT_TYPE_PF_SAMPLE, -}; - -union rc_pid_event_data { - /* RC_PID_EVENT_TX_STATUS */ - struct { - u32 flags; - struct ieee80211_tx_info tx_status; - }; - /* RC_PID_EVENT_TYPE_RATE_CHANGE */ - /* RC_PID_EVENT_TYPE_TX_RATE */ - struct { - int index; - int rate; - }; - /* RC_PID_EVENT_TYPE_PF_SAMPLE */ - struct { - s32 pf_sample; - s32 prop_err; - s32 int_err; - s32 der_err; - }; -}; - -struct rc_pid_event { - /* The time when the event occurred */ - unsigned long timestamp; - - /* Event ID number */ - unsigned int id; - - /* Type of event */ - enum rc_pid_event_type type; - - /* type specific data */ - union rc_pid_event_data data; -}; - -/* Size of the event ring buffer. */ -#define RC_PID_EVENT_RING_SIZE 32 - -struct rc_pid_event_buffer { - /* Counter that generates event IDs */ - unsigned int ev_count; - - /* Ring buffer of events */ - struct rc_pid_event ring[RC_PID_EVENT_RING_SIZE]; - - /* Index to the entry in events_buf to be reused */ - unsigned int next_entry; - - /* Lock that guards against concurrent access to this buffer struct */ - spinlock_t lock; - - /* Wait queue for poll/select and blocking I/O */ - wait_queue_head_t waitqueue; -}; - -struct rc_pid_events_file_info { - /* The event buffer we read */ - struct rc_pid_event_buffer *events; - - /* The entry we have should read next */ - unsigned int next_entry; -}; - -/** - * struct rc_pid_debugfs_entries - tunable parameters - * - * Algorithm parameters, tunable via debugfs. - * @target: target percentage for failed frames - * @sampling_period: error sampling interval in milliseconds - * @coeff_p: absolute value of the proportional coefficient - * @coeff_i: absolute value of the integral coefficient - * @coeff_d: absolute value of the derivative coefficient - * @smoothing_shift: absolute value of the integral smoothing factor (i.e. - * amount of smoothing introduced by the exponential moving average) - * @sharpen_factor: absolute value of the derivative sharpening factor (i.e. - * amount of emphasis given to the derivative term after low activity - * events) - * @sharpen_duration: duration of the sharpening effect after the detected low - * activity event, relative to sampling_period - * @norm_offset: amount of normalization periodically performed on the learnt - * rate behaviour values (lower means we should trust more what we learnt - * about behaviour of rates, higher means we should trust more the natural - * ordering of rates) - */ -struct rc_pid_debugfs_entries { - struct dentry *target; - struct dentry *sampling_period; - struct dentry *coeff_p; - struct dentry *coeff_i; - struct dentry *coeff_d; - struct dentry *smoothing_shift; - struct dentry *sharpen_factor; - struct dentry *sharpen_duration; - struct dentry *norm_offset; -}; - -void rate_control_pid_event_tx_status(struct rc_pid_event_buffer *buf, - struct ieee80211_tx_info *stat); - -void rate_control_pid_event_rate_change(struct rc_pid_event_buffer *buf, - int index, int rate); - -void rate_control_pid_event_tx_rate(struct rc_pid_event_buffer *buf, - int index, int rate); - -void rate_control_pid_event_pf_sample(struct rc_pid_event_buffer *buf, - s32 pf_sample, s32 prop_err, - s32 int_err, s32 der_err); - -void rate_control_pid_add_sta_debugfs(void *priv, void *priv_sta, - struct dentry *dir); - -void rate_control_pid_remove_sta_debugfs(void *priv, void *priv_sta); - -struct rc_pid_sta_info { - unsigned long last_change; - unsigned long last_sample; - - u32 tx_num_failed; - u32 tx_num_xmit; - - int txrate_idx; - - /* Average failed frames percentage error (i.e. actual vs. target - * percentage), scaled by RC_PID_SMOOTHING. This value is computed - * using using an exponential weighted average technique: - * - * (RC_PID_SMOOTHING - 1) * err_avg_old + err - * err_avg = ------------------------------------------ - * RC_PID_SMOOTHING - * - * where err_avg is the new approximation, err_avg_old the previous one - * and err is the error w.r.t. to the current failed frames percentage - * sample. Note that the bigger RC_PID_SMOOTHING the more weight is - * given to the previous estimate, resulting in smoother behavior (i.e. - * corresponding to a longer integration window). - * - * For computation, we actually don't use the above formula, but this - * one: - * - * err_avg_scaled = err_avg_old_scaled - err_avg_old + err - * - * where: - * err_avg_scaled = err * RC_PID_SMOOTHING - * err_avg_old_scaled = err_avg_old * RC_PID_SMOOTHING - * - * This avoids floating point numbers and the per_failed_old value can - * easily be obtained by shifting per_failed_old_scaled right by - * RC_PID_SMOOTHING_SHIFT. - */ - s32 err_avg_sc; - - /* Last framed failes percentage sample. */ - u32 last_pf; - - /* Sharpening needed. */ - u8 sharp_cnt; - -#ifdef CONFIG_MAC80211_DEBUGFS - /* Event buffer */ - struct rc_pid_event_buffer events; - - /* Events debugfs file entry */ - struct dentry *events_entry; -#endif -}; - -/* Algorithm parameters. We keep them on a per-algorithm approach, so they can - * be tuned individually for each interface. - */ -struct rc_pid_rateinfo { - - /* Map sorted rates to rates in ieee80211_hw_mode. */ - int index; - - /* Map rates in ieee80211_hw_mode to sorted rates. */ - int rev_index; - - /* Did we do any measurement on this rate? */ - bool valid; - - /* Comparison with the lowest rate. */ - int diff; -}; - -struct rc_pid_info { - - /* The failed frames percentage target. */ - unsigned int target; - - /* Rate at which failed frames percentage is sampled in 0.001s. */ - unsigned int sampling_period; - - /* P, I and D coefficients. */ - int coeff_p; - int coeff_i; - int coeff_d; - - /* Exponential averaging shift. */ - unsigned int smoothing_shift; - - /* Sharpening factor and duration. */ - unsigned int sharpen_factor; - unsigned int sharpen_duration; - - /* Normalization offset. */ - unsigned int norm_offset; - - /* Rates information. */ - struct rc_pid_rateinfo *rinfo; - - /* Index of the last used rate. */ - int oldrate; - -#ifdef CONFIG_MAC80211_DEBUGFS - /* Debugfs entries created for the parameters above. */ - struct rc_pid_debugfs_entries dentries; -#endif -}; - -#endif /* RC80211_PID_H */ diff --git a/net/mac80211/rc80211_pid_algo.c b/net/mac80211/rc80211_pid_algo.c deleted file mode 100644 index d0da2a70fe68..000000000000 --- a/net/mac80211/rc80211_pid_algo.c +++ /dev/null @@ -1,478 +0,0 @@ -/* - * Copyright 2002-2005, Instant802 Networks, Inc. - * Copyright 2005, Devicescape Software, Inc. - * Copyright 2007, Mattias Nissler <mattias.nissler@gmx.de> - * Copyright 2007-2008, Stefano Brivio <stefano.brivio@polimi.it> - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License version 2 as - * published by the Free Software Foundation. - */ - -#include <linux/netdevice.h> -#include <linux/types.h> -#include <linux/skbuff.h> -#include <linux/debugfs.h> -#include <linux/slab.h> -#include <net/mac80211.h> -#include "rate.h" -#include "mesh.h" -#include "rc80211_pid.h" - - -/* This is an implementation of a TX rate control algorithm that uses a PID - * controller. Given a target failed frames rate, the controller decides about - * TX rate changes to meet the target failed frames rate. - * - * The controller basically computes the following: - * - * adj = CP * err + CI * err_avg + CD * (err - last_err) * (1 + sharpening) - * - * where - * adj adjustment value that is used to switch TX rate (see below) - * err current error: target vs. current failed frames percentage - * last_err last error - * err_avg average (i.e. poor man's integral) of recent errors - * sharpening non-zero when fast response is needed (i.e. right after - * association or no frames sent for a long time), heading - * to zero over time - * CP Proportional coefficient - * CI Integral coefficient - * CD Derivative coefficient - * - * CP, CI, CD are subject to careful tuning. - * - * The integral component uses a exponential moving average approach instead of - * an actual sliding window. The advantage is that we don't need to keep an - * array of the last N error values and computation is easier. - * - * Once we have the adj value, we map it to a rate by means of a learning - * algorithm. This algorithm keeps the state of the percentual failed frames - * difference between rates. The behaviour of the lowest available rate is kept - * as a reference value, and every time we switch between two rates, we compute - * the difference between the failed frames each rate exhibited. By doing so, - * we compare behaviours which different rates exhibited in adjacent timeslices, - * thus the comparison is minimally affected by external conditions. This - * difference gets propagated to the whole set of measurements, so that the - * reference is always the same. Periodically, we normalize this set so that - * recent events weigh the most. By comparing the adj value with this set, we - * avoid pejorative switches to lower rates and allow for switches to higher - * rates if they behaved well. - * - * Note that for the computations we use a fixed-point representation to avoid - * floating point arithmetic. Hence, all values are shifted left by - * RC_PID_ARITH_SHIFT. - */ - - -/* Adjust the rate while ensuring that we won't switch to a lower rate if it - * exhibited a worse failed frames behaviour and we'll choose the highest rate - * whose failed frames behaviour is not worse than the one of the original rate - * target. While at it, check that the new rate is valid. */ -static void rate_control_pid_adjust_rate(struct ieee80211_supported_band *sband, - struct ieee80211_sta *sta, - struct rc_pid_sta_info *spinfo, int adj, - struct rc_pid_rateinfo *rinfo) -{ - int cur_sorted, new_sorted, probe, tmp, n_bitrates, band; - int cur = spinfo->txrate_idx; - - band = sband->band; - n_bitrates = sband->n_bitrates; - - /* Map passed arguments to sorted values. */ - cur_sorted = rinfo[cur].rev_index; - new_sorted = cur_sorted + adj; - - /* Check limits. */ - if (new_sorted < 0) - new_sorted = rinfo[0].rev_index; - else if (new_sorted >= n_bitrates) - new_sorted = rinfo[n_bitrates - 1].rev_index; - - tmp = new_sorted; - - if (adj < 0) { - /* Ensure that the rate decrease isn't disadvantageous. */ - for (probe = cur_sorted; probe >= new_sorted; probe--) - if (rinfo[probe].diff <= rinfo[cur_sorted].diff && - rate_supported(sta, band, rinfo[probe].index)) - tmp = probe; - } else { - /* Look for rate increase with zero (or below) cost. */ - for (probe = new_sorted + 1; probe < n_bitrates; probe++) - if (rinfo[probe].diff <= rinfo[new_sorted].diff && - rate_supported(sta, band, rinfo[probe].index)) - tmp = probe; - } - - /* Fit the rate found to the nearest supported rate. */ - do { - if (rate_supported(sta, band, rinfo[tmp].index)) { - spinfo->txrate_idx = rinfo[tmp].index; - break; - } - if (adj < 0) - tmp--; - else - tmp++; - } while (tmp < n_bitrates && tmp >= 0); - -#ifdef CONFIG_MAC80211_DEBUGFS - rate_control_pid_event_rate_change(&spinfo->events, - spinfo->txrate_idx, - sband->bitrates[spinfo->txrate_idx].bitrate); -#endif -} - -/* Normalize the failed frames per-rate differences. */ -static void rate_control_pid_normalize(struct rc_pid_info *pinfo, int l) -{ - int i, norm_offset = pinfo->norm_offset; - struct rc_pid_rateinfo *r = pinfo->rinfo; - - if (r[0].diff > norm_offset) - r[0].diff -= norm_offset; - else if (r[0].diff < -norm_offset) - r[0].diff += norm_offset; - for (i = 0; i < l - 1; i++) - if (r[i + 1].diff > r[i].diff + norm_offset) - r[i + 1].diff -= norm_offset; - else if (r[i + 1].diff <= r[i].diff) - r[i + 1].diff += norm_offset; -} - -static void rate_control_pid_sample(struct rc_pid_info *pinfo, - struct ieee80211_supported_band *sband, - struct ieee80211_sta *sta, - struct rc_pid_sta_info *spinfo) -{ - struct rc_pid_rateinfo *rinfo = pinfo->rinfo; - u32 pf; - s32 err_avg; - u32 err_prop; - u32 err_int; - u32 err_der; - int adj, i, j, tmp; - unsigned long period; - - /* In case nothing happened during the previous control interval, turn - * the sharpening factor on. */ - period = msecs_to_jiffies(pinfo->sampling_period); - if (jiffies - spinfo->last_sample > 2 * period) - spinfo->sharp_cnt = pinfo->sharpen_duration; - - spinfo->last_sample = jiffies; - - /* This should never happen, but in case, we assume the old sample is - * still a good measurement and copy it. */ - if (unlikely(spinfo->tx_num_xmit == 0)) - pf = spinfo->last_pf; - else - pf = spinfo->tx_num_failed * 100 / spinfo->tx_num_xmit; - - spinfo->tx_num_xmit = 0; - spinfo->tx_num_failed = 0; - - /* If we just switched rate, update the rate behaviour info. */ - if (pinfo->oldrate != spinfo->txrate_idx) { - - i = rinfo[pinfo->oldrate].rev_index; - j = rinfo[spinfo->txrate_idx].rev_index; - - tmp = (pf - spinfo->last_pf); - tmp = RC_PID_DO_ARITH_RIGHT_SHIFT(tmp, RC_PID_ARITH_SHIFT); - - rinfo[j].diff = rinfo[i].diff + tmp; - pinfo->oldrate = spinfo->txrate_idx; - } - rate_control_pid_normalize(pinfo, sband->n_bitrates); - - /* Compute the proportional, integral and derivative errors. */ - err_prop = (pinfo->target - pf) << RC_PID_ARITH_SHIFT; - - err_avg = spinfo->err_avg_sc >> pinfo->smoothing_shift; - spinfo->err_avg_sc = spinfo->err_avg_sc - err_avg + err_prop; - err_int = spinfo->err_avg_sc >> pinfo->smoothing_shift; - - err_der = (pf - spinfo->last_pf) * - (1 + pinfo->sharpen_factor * spinfo->sharp_cnt); - spinfo->last_pf = pf; - if (spinfo->sharp_cnt) - spinfo->sharp_cnt--; - -#ifdef CONFIG_MAC80211_DEBUGFS - rate_control_pid_event_pf_sample(&spinfo->events, pf, err_prop, err_int, - err_der); -#endif - - /* Compute the controller output. */ - adj = (err_prop * pinfo->coeff_p + err_int * pinfo->coeff_i - + err_der * pinfo->coeff_d); - adj = RC_PID_DO_ARITH_RIGHT_SHIFT(adj, 2 * RC_PID_ARITH_SHIFT); - - /* Change rate. */ - if (adj) - rate_control_pid_adjust_rate(sband, sta, spinfo, adj, rinfo); -} - -static void rate_control_pid_tx_status(void *priv, struct ieee80211_supported_band *sband, - struct ieee80211_sta *sta, void *priv_sta, - struct sk_buff *skb) -{ - struct rc_pid_info *pinfo = priv; - struct rc_pid_sta_info *spinfo = priv_sta; - unsigned long period; - struct ieee80211_tx_info *info = IEEE80211_SKB_CB(skb); - - if (!spinfo) - return; - - /* Ignore all frames that were sent with a different rate than the rate - * we currently advise mac80211 to use. */ - if (info->status.rates[0].idx != spinfo->txrate_idx) - return; - - spinfo->tx_num_xmit++; - -#ifdef CONFIG_MAC80211_DEBUGFS - rate_control_pid_event_tx_status(&spinfo->events, info); -#endif - - /* We count frames that totally failed to be transmitted as two bad - * frames, those that made it out but had some retries as one good and - * one bad frame. */ - if (!(info->flags & IEEE80211_TX_STAT_ACK)) { - spinfo->tx_num_failed += 2; - spinfo->tx_num_xmit++; - } else if (info->status.rates[0].count > 1) { - spinfo->tx_num_failed++; - spinfo->tx_num_xmit++; - } - - /* Update PID controller state. */ - period = msecs_to_jiffies(pinfo->sampling_period); - if (time_after(jiffies, spinfo->last_sample + period)) - rate_control_pid_sample(pinfo, sband, sta, spinfo); -} - -static void -rate_control_pid_get_rate(void *priv, struct ieee80211_sta *sta, - void *priv_sta, - struct ieee80211_tx_rate_control *txrc) -{ - struct sk_buff *skb = txrc->skb; - struct ieee80211_supported_band *sband = txrc->sband; - struct ieee80211_tx_info *info = IEEE80211_SKB_CB(skb); - struct rc_pid_sta_info *spinfo = priv_sta; - int rateidx; - - if (txrc->rts) - info->control.rates[0].count = - txrc->hw->conf.long_frame_max_tx_count; - else - info->control.rates[0].count = - txrc->hw->conf.short_frame_max_tx_count; - - /* Send management frames and NO_ACK data using lowest rate. */ - if (rate_control_send_low(sta, priv_sta, txrc)) - return; - - rateidx = spinfo->txrate_idx; - - if (rateidx >= sband->n_bitrates) - rateidx = sband->n_bitrates - 1; - - info->control.rates[0].idx = rateidx; - -#ifdef CONFIG_MAC80211_DEBUGFS - rate_control_pid_event_tx_rate(&spinfo->events, - rateidx, sband->bitrates[rateidx].bitrate); -#endif -} - -static void -rate_control_pid_rate_init(void *priv, struct ieee80211_supported_band *sband, - struct cfg80211_chan_def *chandef, - struct ieee80211_sta *sta, void *priv_sta) -{ - struct rc_pid_sta_info *spinfo = priv_sta; - struct rc_pid_info *pinfo = priv; - struct rc_pid_rateinfo *rinfo = pinfo->rinfo; - int i, j, tmp; - bool s; - - /* TODO: This routine should consider using RSSI from previous packets - * as we need to have IEEE 802.1X auth succeed immediately after assoc.. - * Until that method is implemented, we will use the lowest supported - * rate as a workaround. */ - - /* Sort the rates. This is optimized for the most common case (i.e. - * almost-sorted CCK+OFDM rates). Kind of bubble-sort with reversed - * mapping too. */ - for (i = 0; i < sband->n_bitrates; i++) { - rinfo[i].index = i; - rinfo[i].rev_index = i; - if (RC_PID_FAST_START) - rinfo[i].diff = 0; - else - rinfo[i].diff = i * pinfo->norm_offset; - } - for (i = 1; i < sband->n_bitrates; i++) { - s = false; - for (j = 0; j < sband->n_bitrates - i; j++) - if (unlikely(sband->bitrates[rinfo[j].index].bitrate > - sband->bitrates[rinfo[j + 1].index].bitrate)) { - tmp = rinfo[j].index; - rinfo[j].index = rinfo[j + 1].index; - rinfo[j + 1].index = tmp; - rinfo[rinfo[j].index].rev_index = j; - rinfo[rinfo[j + 1].index].rev_index = j + 1; - s = true; - } - if (!s) - break; - } - - spinfo->txrate_idx = rate_lowest_index(sband, sta); -} - -static void *rate_control_pid_alloc(struct ieee80211_hw *hw, - struct dentry *debugfsdir) -{ - struct rc_pid_info *pinfo; - struct rc_pid_rateinfo *rinfo; - struct ieee80211_supported_band *sband; - int i, max_rates = 0; -#ifdef CONFIG_MAC80211_DEBUGFS - struct rc_pid_debugfs_entries *de; -#endif - - pinfo = kmalloc(sizeof(*pinfo), GFP_ATOMIC); - if (!pinfo) - return NULL; - - for (i = 0; i < IEEE80211_NUM_BANDS; i++) { - sband = hw->wiphy->bands[i]; - if (sband && sband->n_bitrates > max_rates) - max_rates = sband->n_bitrates; - } - - rinfo = kmalloc(sizeof(*rinfo) * max_rates, GFP_ATOMIC); - if (!rinfo) { - kfree(pinfo); - return NULL; - } - - pinfo->target = RC_PID_TARGET_PF; - pinfo->sampling_period = RC_PID_INTERVAL; - pinfo->coeff_p = RC_PID_COEFF_P; - pinfo->coeff_i = RC_PID_COEFF_I; - pinfo->coeff_d = RC_PID_COEFF_D; - pinfo->smoothing_shift = RC_PID_SMOOTHING_SHIFT; - pinfo->sharpen_factor = RC_PID_SHARPENING_FACTOR; - pinfo->sharpen_duration = RC_PID_SHARPENING_DURATION; - pinfo->norm_offset = RC_PID_NORM_OFFSET; - pinfo->rinfo = rinfo; - pinfo->oldrate = 0; - -#ifdef CONFIG_MAC80211_DEBUGFS - de = &pinfo->dentries; - de->target = debugfs_create_u32("target_pf", S_IRUSR | S_IWUSR, - debugfsdir, &pinfo->target); - de->sampling_period = debugfs_create_u32("sampling_period", - S_IRUSR | S_IWUSR, debugfsdir, - &pinfo->sampling_period); - de->coeff_p = debugfs_create_u32("coeff_p", S_IRUSR | S_IWUSR, - debugfsdir, (u32 *)&pinfo->coeff_p); - de->coeff_i = debugfs_create_u32("coeff_i", S_IRUSR | S_IWUSR, - debugfsdir, (u32 *)&pinfo->coeff_i); - de->coeff_d = debugfs_create_u32("coeff_d", S_IRUSR | S_IWUSR, - debugfsdir, (u32 *)&pinfo->coeff_d); - de->smoothing_shift = debugfs_create_u32("smoothing_shift", - S_IRUSR | S_IWUSR, debugfsdir, - &pinfo->smoothing_shift); - de->sharpen_factor = debugfs_create_u32("sharpen_factor", - S_IRUSR | S_IWUSR, debugfsdir, - &pinfo->sharpen_factor); - de->sharpen_duration = debugfs_create_u32("sharpen_duration", - S_IRUSR | S_IWUSR, debugfsdir, - &pinfo->sharpen_duration); - de->norm_offset = debugfs_create_u32("norm_offset", - S_IRUSR | S_IWUSR, debugfsdir, - &pinfo->norm_offset); -#endif - - return pinfo; -} - -static void rate_control_pid_free(void *priv) -{ - struct rc_pid_info *pinfo = priv; -#ifdef CONFIG_MAC80211_DEBUGFS - struct rc_pid_debugfs_entries *de = &pinfo->dentries; - - debugfs_remove(de->norm_offset); - debugfs_remove(de->sharpen_duration); - debugfs_remove(de->sharpen_factor); - debugfs_remove(de->smoothing_shift); - debugfs_remove(de->coeff_d); - debugfs_remove(de->coeff_i); - debugfs_remove(de->coeff_p); - debugfs_remove(de->sampling_period); - debugfs_remove(de->target); -#endif - - kfree(pinfo->rinfo); - kfree(pinfo); -} - -static void *rate_control_pid_alloc_sta(void *priv, struct ieee80211_sta *sta, - gfp_t gfp) -{ - struct rc_pid_sta_info *spinfo; - - spinfo = kzalloc(sizeof(*spinfo), gfp); - if (spinfo == NULL) - return NULL; - - spinfo->last_sample = jiffies; - -#ifdef CONFIG_MAC80211_DEBUGFS - spin_lock_init(&spinfo->events.lock); - init_waitqueue_head(&spinfo->events.waitqueue); -#endif - - return spinfo; -} - -static void rate_control_pid_free_sta(void *priv, struct ieee80211_sta *sta, - void *priv_sta) -{ - kfree(priv_sta); -} - -static const struct rate_control_ops mac80211_rcpid = { - .name = "pid", - .tx_status = rate_control_pid_tx_status, - .get_rate = rate_control_pid_get_rate, - .rate_init = rate_control_pid_rate_init, - .alloc = rate_control_pid_alloc, - .free = rate_control_pid_free, - .alloc_sta = rate_control_pid_alloc_sta, - .free_sta = rate_control_pid_free_sta, -#ifdef CONFIG_MAC80211_DEBUGFS - .add_sta_debugfs = rate_control_pid_add_sta_debugfs, - .remove_sta_debugfs = rate_control_pid_remove_sta_debugfs, -#endif -}; - -int __init rc80211_pid_init(void) -{ - return ieee80211_rate_control_register(&mac80211_rcpid); -} - -void rc80211_pid_exit(void) -{ - ieee80211_rate_control_unregister(&mac80211_rcpid); -} diff --git a/net/mac80211/rc80211_pid_debugfs.c b/net/mac80211/rc80211_pid_debugfs.c deleted file mode 100644 index 6ff134650a84..000000000000 --- a/net/mac80211/rc80211_pid_debugfs.c +++ /dev/null @@ -1,228 +0,0 @@ -/* - * Copyright 2007, Mattias Nissler <mattias.nissler@gmx.de> - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License version 2 as - * published by the Free Software Foundation. - */ - -#include <linux/sched.h> -#include <linux/spinlock.h> -#include <linux/poll.h> -#include <linux/netdevice.h> -#include <linux/types.h> -#include <linux/skbuff.h> -#include <linux/slab.h> -#include <linux/export.h> - -#include <net/mac80211.h> -#include "rate.h" - -#include "rc80211_pid.h" - -static void rate_control_pid_event(struct rc_pid_event_buffer *buf, - enum rc_pid_event_type type, - union rc_pid_event_data *data) -{ - struct rc_pid_event *ev; - unsigned long status; - - spin_lock_irqsave(&buf->lock, status); - ev = &(buf->ring[buf->next_entry]); - buf->next_entry = (buf->next_entry + 1) % RC_PID_EVENT_RING_SIZE; - - ev->timestamp = jiffies; - ev->id = buf->ev_count++; - ev->type = type; - ev->data = *data; - - spin_unlock_irqrestore(&buf->lock, status); - - wake_up_all(&buf->waitqueue); -} - -void rate_control_pid_event_tx_status(struct rc_pid_event_buffer *buf, - struct ieee80211_tx_info *stat) -{ - union rc_pid_event_data evd; - - evd.flags = stat->flags; - memcpy(&evd.tx_status, stat, sizeof(struct ieee80211_tx_info)); - rate_control_pid_event(buf, RC_PID_EVENT_TYPE_TX_STATUS, &evd); -} - -void rate_control_pid_event_rate_change(struct rc_pid_event_buffer *buf, - int index, int rate) -{ - union rc_pid_event_data evd; - - evd.index = index; - evd.rate = rate; - rate_control_pid_event(buf, RC_PID_EVENT_TYPE_RATE_CHANGE, &evd); -} - -void rate_control_pid_event_tx_rate(struct rc_pid_event_buffer *buf, - int index, int rate) -{ - union rc_pid_event_data evd; - - evd.index = index; - evd.rate = rate; - rate_control_pid_event(buf, RC_PID_EVENT_TYPE_TX_RATE, &evd); -} - -void rate_control_pid_event_pf_sample(struct rc_pid_event_buffer *buf, - s32 pf_sample, s32 prop_err, - s32 int_err, s32 der_err) -{ - union rc_pid_event_data evd; - - evd.pf_sample = pf_sample; - evd.prop_err = prop_err; - evd.int_err = int_err; - evd.der_err = der_err; - rate_control_pid_event(buf, RC_PID_EVENT_TYPE_PF_SAMPLE, &evd); -} - -static int rate_control_pid_events_open(struct inode *inode, struct file *file) -{ - struct rc_pid_sta_info *sinfo = inode->i_private; - struct rc_pid_event_buffer *events = &sinfo->events; - struct rc_pid_events_file_info *file_info; - unsigned long status; - - /* Allocate a state struct */ - file_info = kmalloc(sizeof(*file_info), GFP_KERNEL); - if (file_info == NULL) - return -ENOMEM; - - spin_lock_irqsave(&events->lock, status); - - file_info->next_entry = events->next_entry; - file_info->events = events; - - spin_unlock_irqrestore(&events->lock, status); - - file->private_data = file_info; - - return 0; -} - -static int rate_control_pid_events_release(struct inode *inode, - struct file *file) -{ - struct rc_pid_events_file_info *file_info = file->private_data; - - kfree(file_info); - - return 0; -} - -static unsigned int rate_control_pid_events_poll(struct file *file, - poll_table *wait) -{ - struct rc_pid_events_file_info *file_info = file->private_data; - - poll_wait(file, &file_info->events->waitqueue, wait); - - return POLLIN | POLLRDNORM; -} - -#define RC_PID_PRINT_BUF_SIZE 64 - -static ssize_t rate_control_pid_events_read(struct file *file, char __user *buf, - size_t length, loff_t *offset) -{ - struct rc_pid_events_file_info *file_info = file->private_data; - struct rc_pid_event_buffer *events = file_info->events; - struct rc_pid_event *ev; - char pb[RC_PID_PRINT_BUF_SIZE]; - int ret; - int p; - unsigned long status; - - /* Check if there is something to read. */ - if (events->next_entry == file_info->next_entry) { - if (file->f_flags & O_NONBLOCK) - return -EAGAIN; - - /* Wait */ - ret = wait_event_interruptible(events->waitqueue, - events->next_entry != file_info->next_entry); - - if (ret) - return ret; - } - - /* Write out one event per call. I don't care whether it's a little - * inefficient, this is debugging code anyway. */ - spin_lock_irqsave(&events->lock, status); - - /* Get an event */ - ev = &(events->ring[file_info->next_entry]); - file_info->next_entry = (file_info->next_entry + 1) % - RC_PID_EVENT_RING_SIZE; - - /* Print information about the event. Note that userspace needs to - * provide large enough buffers. */ - length = length < RC_PID_PRINT_BUF_SIZE ? - length : RC_PID_PRINT_BUF_SIZE; - p = scnprintf(pb, length, "%u %lu ", ev->id, ev->timestamp); - switch (ev->type) { - case RC_PID_EVENT_TYPE_TX_STATUS: - p += scnprintf(pb + p, length - p, "tx_status %u %u", - !(ev->data.flags & IEEE80211_TX_STAT_ACK), - ev->data.tx_status.status.rates[0].idx); - break; - case RC_PID_EVENT_TYPE_RATE_CHANGE: - p += scnprintf(pb + p, length - p, "rate_change %d %d", - ev->data.index, ev->data.rate); - break; - case RC_PID_EVENT_TYPE_TX_RATE: - p += scnprintf(pb + p, length - p, "tx_rate %d %d", - ev->data.index, ev->data.rate); - break; - case RC_PID_EVENT_TYPE_PF_SAMPLE: - p += scnprintf(pb + p, length - p, - "pf_sample %d %d %d %d", - ev->data.pf_sample, ev->data.prop_err, - ev->data.int_err, ev->data.der_err); - break; - } - p += scnprintf(pb + p, length - p, "\n"); - - spin_unlock_irqrestore(&events->lock, status); - - if (copy_to_user(buf, pb, p)) - return -EFAULT; - - return p; -} - -#undef RC_PID_PRINT_BUF_SIZE - -static const struct file_operations rc_pid_fop_events = { - .owner = THIS_MODULE, - .read = rate_control_pid_events_read, - .poll = rate_control_pid_events_poll, - .open = rate_control_pid_events_open, - .release = rate_control_pid_events_release, - .llseek = noop_llseek, -}; - -void rate_control_pid_add_sta_debugfs(void *priv, void *priv_sta, - struct dentry *dir) -{ - struct rc_pid_sta_info *spinfo = priv_sta; - - spinfo->events_entry = debugfs_create_file("rc_pid_events", S_IRUGO, - dir, spinfo, - &rc_pid_fop_events); -} - -void rate_control_pid_remove_sta_debugfs(void *priv, void *priv_sta) -{ - struct rc_pid_sta_info *spinfo = priv_sta; - - debugfs_remove(spinfo->events_entry); -} diff --git a/net/mac80211/rx.c b/net/mac80211/rx.c index 394e201cde6d..bd2c9b22c945 100644 --- a/net/mac80211/rx.c +++ b/net/mac80211/rx.c @@ -688,20 +688,27 @@ static void ieee80211_release_reorder_frame(struct ieee80211_sub_if_data *sdata, int index, struct sk_buff_head *frames) { - struct sk_buff *skb = tid_agg_rx->reorder_buf[index]; + struct sk_buff_head *skb_list = &tid_agg_rx->reorder_buf[index]; + struct sk_buff *skb; struct ieee80211_rx_status *status; lockdep_assert_held(&tid_agg_rx->reorder_lock); - if (!skb) + if (skb_queue_empty(skb_list)) + goto no_frame; + + if (!ieee80211_rx_reorder_ready(skb_list)) { + __skb_queue_purge(skb_list); goto no_frame; + } - /* release the frame from the reorder ring buffer */ + /* release frames from the reorder ring buffer */ tid_agg_rx->stored_mpdu_num--; - tid_agg_rx->reorder_buf[index] = NULL; - status = IEEE80211_SKB_RXCB(skb); - status->rx_flags |= IEEE80211_RX_DEFERRED_RELEASE; - __skb_queue_tail(frames, skb); + while ((skb = __skb_dequeue(skb_list))) { + status = IEEE80211_SKB_RXCB(skb); + status->rx_flags |= IEEE80211_RX_DEFERRED_RELEASE; + __skb_queue_tail(frames, skb); + } no_frame: tid_agg_rx->head_seq_num = ieee80211_sn_inc(tid_agg_rx->head_seq_num); @@ -738,13 +745,13 @@ static void ieee80211_sta_reorder_release(struct ieee80211_sub_if_data *sdata, struct tid_ampdu_rx *tid_agg_rx, struct sk_buff_head *frames) { - int index, j; + int index, i, j; lockdep_assert_held(&tid_agg_rx->reorder_lock); /* release the buffer until next missing frame */ index = tid_agg_rx->head_seq_num % tid_agg_rx->buf_size; - if (!tid_agg_rx->reorder_buf[index] && + if (!ieee80211_rx_reorder_ready(&tid_agg_rx->reorder_buf[index]) && tid_agg_rx->stored_mpdu_num) { /* * No buffers ready to be released, but check whether any @@ -753,7 +760,8 @@ static void ieee80211_sta_reorder_release(struct ieee80211_sub_if_data *sdata, int skipped = 1; for (j = (index + 1) % tid_agg_rx->buf_size; j != index; j = (j + 1) % tid_agg_rx->buf_size) { - if (!tid_agg_rx->reorder_buf[j]) { + if (!ieee80211_rx_reorder_ready( + &tid_agg_rx->reorder_buf[j])) { skipped++; continue; } @@ -762,6 +770,11 @@ static void ieee80211_sta_reorder_release(struct ieee80211_sub_if_data *sdata, HT_RX_REORDER_BUF_TIMEOUT)) goto set_release_timer; + /* don't leave incomplete A-MSDUs around */ + for (i = (index + 1) % tid_agg_rx->buf_size; i != j; + i = (i + 1) % tid_agg_rx->buf_size) + __skb_queue_purge(&tid_agg_rx->reorder_buf[i]); + ht_dbg_ratelimited(sdata, "release an RX reorder frame due to timeout on earlier frames\n"); ieee80211_release_reorder_frame(sdata, tid_agg_rx, j, @@ -775,7 +788,8 @@ static void ieee80211_sta_reorder_release(struct ieee80211_sub_if_data *sdata, skipped) & IEEE80211_SN_MASK; skipped = 0; } - } else while (tid_agg_rx->reorder_buf[index]) { + } else while (ieee80211_rx_reorder_ready( + &tid_agg_rx->reorder_buf[index])) { ieee80211_release_reorder_frame(sdata, tid_agg_rx, index, frames); index = tid_agg_rx->head_seq_num % tid_agg_rx->buf_size; @@ -786,7 +800,8 @@ static void ieee80211_sta_reorder_release(struct ieee80211_sub_if_data *sdata, for (; j != (index - 1) % tid_agg_rx->buf_size; j = (j + 1) % tid_agg_rx->buf_size) { - if (tid_agg_rx->reorder_buf[j]) + if (ieee80211_rx_reorder_ready( + &tid_agg_rx->reorder_buf[j])) break; } @@ -811,6 +826,7 @@ static bool ieee80211_sta_manage_reorder_buf(struct ieee80211_sub_if_data *sdata struct sk_buff_head *frames) { struct ieee80211_hdr *hdr = (struct ieee80211_hdr *) skb->data; + struct ieee80211_rx_status *status = IEEE80211_SKB_RXCB(skb); u16 sc = le16_to_cpu(hdr->seq_ctrl); u16 mpdu_seq_num = (sc & IEEE80211_SCTL_SEQ) >> 4; u16 head_seq_num, buf_size; @@ -845,7 +861,7 @@ static bool ieee80211_sta_manage_reorder_buf(struct ieee80211_sub_if_data *sdata index = mpdu_seq_num % tid_agg_rx->buf_size; /* check if we already stored this frame */ - if (tid_agg_rx->reorder_buf[index]) { + if (ieee80211_rx_reorder_ready(&tid_agg_rx->reorder_buf[index])) { dev_kfree_skb(skb); goto out; } @@ -858,17 +874,20 @@ static bool ieee80211_sta_manage_reorder_buf(struct ieee80211_sub_if_data *sdata */ if (mpdu_seq_num == tid_agg_rx->head_seq_num && tid_agg_rx->stored_mpdu_num == 0) { - tid_agg_rx->head_seq_num = - ieee80211_sn_inc(tid_agg_rx->head_seq_num); + if (!(status->flag & RX_FLAG_AMSDU_MORE)) + tid_agg_rx->head_seq_num = + ieee80211_sn_inc(tid_agg_rx->head_seq_num); ret = false; goto out; } /* put the frame in the reordering buffer */ - tid_agg_rx->reorder_buf[index] = skb; - tid_agg_rx->reorder_time[index] = jiffies; - tid_agg_rx->stored_mpdu_num++; - ieee80211_sta_reorder_release(sdata, tid_agg_rx, frames); + __skb_queue_tail(&tid_agg_rx->reorder_buf[index], skb); + if (!(status->flag & RX_FLAG_AMSDU_MORE)) { + tid_agg_rx->reorder_time[index] = jiffies; + tid_agg_rx->stored_mpdu_num++; + ieee80211_sta_reorder_release(sdata, tid_agg_rx, frames); + } out: spin_unlock(&tid_agg_rx->reorder_lock); @@ -1107,6 +1126,8 @@ static void sta_ps_end(struct sta_info *sta) return; } + set_sta_flag(sta, WLAN_STA_PS_DELIVER); + clear_sta_flag(sta, WLAN_STA_PS_STA); ieee80211_sta_ps_deliver_wakeup(sta); } @@ -3127,6 +3148,14 @@ static bool prepare_for_handlers(struct ieee80211_rx_data *rx, if (!ieee80211_is_beacon(hdr->frame_control)) return false; status->rx_flags &= ~IEEE80211_RX_RA_MATCH; + } else if (!ieee80211_has_tods(hdr->frame_control)) { + /* ignore data frames to TDLS-peers */ + if (ieee80211_is_data(hdr->frame_control)) + return false; + /* ignore action frames to TDLS-peers */ + if (ieee80211_is_action(hdr->frame_control) && + !ether_addr_equal(bssid, hdr->addr1)) + return false; } break; case NL80211_IFTYPE_WDS: diff --git a/net/mac80211/scan.c b/net/mac80211/scan.c index f40661eb75b5..a0a938145dcc 100644 --- a/net/mac80211/scan.c +++ b/net/mac80211/scan.c @@ -235,38 +235,51 @@ static bool ieee80211_prep_hw_scan(struct ieee80211_local *local) { struct cfg80211_scan_request *req = local->scan_req; struct cfg80211_chan_def chandef; - enum ieee80211_band band; + u8 bands_used = 0; int i, ielen, n_chans; if (test_bit(SCAN_HW_CANCELLED, &local->scanning)) return false; - do { - if (local->hw_scan_band == IEEE80211_NUM_BANDS) - return false; - - band = local->hw_scan_band; - n_chans = 0; + if (local->hw.flags & IEEE80211_SINGLE_HW_SCAN_ON_ALL_BANDS) { for (i = 0; i < req->n_channels; i++) { - if (req->channels[i]->band == band) { - local->hw_scan_req->channels[n_chans] = + local->hw_scan_req->req.channels[i] = req->channels[i]; + bands_used |= BIT(req->channels[i]->band); + } + + n_chans = req->n_channels; + } else { + do { + if (local->hw_scan_band == IEEE80211_NUM_BANDS) + return false; + + n_chans = 0; + + for (i = 0; i < req->n_channels; i++) { + if (req->channels[i]->band != + local->hw_scan_band) + continue; + local->hw_scan_req->req.channels[n_chans] = req->channels[i]; n_chans++; + bands_used |= BIT(req->channels[i]->band); } - } - local->hw_scan_band++; - } while (!n_chans); + local->hw_scan_band++; + } while (!n_chans); + } - local->hw_scan_req->n_channels = n_chans; + local->hw_scan_req->req.n_channels = n_chans; ieee80211_prepare_scan_chandef(&chandef, req->scan_width); - ielen = ieee80211_build_preq_ies(local, (u8 *)local->hw_scan_req->ie, + ielen = ieee80211_build_preq_ies(local, + (u8 *)local->hw_scan_req->req.ie, local->hw_scan_ies_bufsize, - req->ie, req->ie_len, band, - req->rates[band], &chandef); - local->hw_scan_req->ie_len = ielen; - local->hw_scan_req->no_cck = req->no_cck; + &local->hw_scan_req->ies, + req->ie, req->ie_len, + bands_used, req->rates, &chandef); + local->hw_scan_req->req.ie_len = ielen; + local->hw_scan_req->req.no_cck = req->no_cck; return true; } @@ -291,7 +304,9 @@ static void __ieee80211_scan_completed(struct ieee80211_hw *hw, bool aborted) if (WARN_ON(!local->scan_req)) return; - if (hw_scan && !aborted && ieee80211_prep_hw_scan(local)) { + if (hw_scan && !aborted && + !(local->hw.flags & IEEE80211_SINGLE_HW_SCAN_ON_ALL_BANDS) && + ieee80211_prep_hw_scan(local)) { int rc; rc = drv_hw_scan(local, @@ -473,6 +488,21 @@ static int __ieee80211_start_scan(struct ieee80211_sub_if_data *sdata, u8 *ies; local->hw_scan_ies_bufsize = local->scan_ies_len + req->ie_len; + + if (local->hw.flags & IEEE80211_SINGLE_HW_SCAN_ON_ALL_BANDS) { + int i, n_bands = 0; + u8 bands_counted = 0; + + for (i = 0; i < req->n_channels; i++) { + if (bands_counted & BIT(req->channels[i]->band)) + continue; + bands_counted |= BIT(req->channels[i]->band); + n_bands++; + } + + local->hw_scan_ies_bufsize *= n_bands; + } + local->hw_scan_req = kmalloc( sizeof(*local->hw_scan_req) + req->n_channels * sizeof(req->channels[0]) + @@ -480,13 +510,13 @@ static int __ieee80211_start_scan(struct ieee80211_sub_if_data *sdata, if (!local->hw_scan_req) return -ENOMEM; - local->hw_scan_req->ssids = req->ssids; - local->hw_scan_req->n_ssids = req->n_ssids; + local->hw_scan_req->req.ssids = req->ssids; + local->hw_scan_req->req.n_ssids = req->n_ssids; ies = (u8 *)local->hw_scan_req + sizeof(*local->hw_scan_req) + req->n_channels * sizeof(req->channels[0]); - local->hw_scan_req->ie = ies; - local->hw_scan_req->flags = req->flags; + local->hw_scan_req->req.ie = ies; + local->hw_scan_req->req.flags = req->flags; local->hw_scan_band = 0; @@ -973,9 +1003,13 @@ int __ieee80211_request_sched_scan_start(struct ieee80211_sub_if_data *sdata, struct cfg80211_sched_scan_request *req) { struct ieee80211_local *local = sdata->local; - struct ieee80211_sched_scan_ies sched_scan_ies = {}; + struct ieee80211_scan_ies sched_scan_ies = {}; struct cfg80211_chan_def chandef; - int ret, i, iebufsz; + int ret, i, iebufsz, num_bands = 0; + u32 rate_masks[IEEE80211_NUM_BANDS] = {}; + u8 bands_used = 0; + u8 *ie; + size_t len; iebufsz = local->scan_ies_len + req->ie_len; @@ -985,33 +1019,35 @@ int __ieee80211_request_sched_scan_start(struct ieee80211_sub_if_data *sdata, return -ENOTSUPP; for (i = 0; i < IEEE80211_NUM_BANDS; i++) { - if (!local->hw.wiphy->bands[i]) - continue; - - sched_scan_ies.ie[i] = kzalloc(iebufsz, GFP_KERNEL); - if (!sched_scan_ies.ie[i]) { - ret = -ENOMEM; - goto out_free; + if (local->hw.wiphy->bands[i]) { + bands_used |= BIT(i); + rate_masks[i] = (u32) -1; + num_bands++; } + } - ieee80211_prepare_scan_chandef(&chandef, req->scan_width); - - sched_scan_ies.len[i] = - ieee80211_build_preq_ies(local, sched_scan_ies.ie[i], - iebufsz, req->ie, req->ie_len, - i, (u32) -1, &chandef); + ie = kzalloc(num_bands * iebufsz, GFP_KERNEL); + if (!ie) { + ret = -ENOMEM; + goto out; } + ieee80211_prepare_scan_chandef(&chandef, req->scan_width); + + len = ieee80211_build_preq_ies(local, ie, num_bands * iebufsz, + &sched_scan_ies, req->ie, + req->ie_len, bands_used, + rate_masks, &chandef); + ret = drv_sched_scan_start(local, sdata, req, &sched_scan_ies); if (ret == 0) { rcu_assign_pointer(local->sched_scan_sdata, sdata); local->sched_scan_req = req; } -out_free: - while (i > 0) - kfree(sched_scan_ies.ie[--i]); + kfree(ie); +out: if (ret) { /* Clean in case of failure after HW restart or upon resume. */ RCU_INIT_POINTER(local->sched_scan_sdata, NULL); diff --git a/net/mac80211/sta_info.c b/net/mac80211/sta_info.c index a9b46d8ea22f..c6ee2139fbc5 100644 --- a/net/mac80211/sta_info.c +++ b/net/mac80211/sta_info.c @@ -100,7 +100,8 @@ static void __cleanup_single_sta(struct sta_info *sta) struct ps_data *ps; if (test_sta_flag(sta, WLAN_STA_PS_STA) || - test_sta_flag(sta, WLAN_STA_PS_DRIVER)) { + test_sta_flag(sta, WLAN_STA_PS_DRIVER) || + test_sta_flag(sta, WLAN_STA_PS_DELIVER)) { if (sta->sdata->vif.type == NL80211_IFTYPE_AP || sta->sdata->vif.type == NL80211_IFTYPE_AP_VLAN) ps = &sdata->bss->ps; @@ -111,6 +112,7 @@ static void __cleanup_single_sta(struct sta_info *sta) clear_sta_flag(sta, WLAN_STA_PS_STA); clear_sta_flag(sta, WLAN_STA_PS_DRIVER); + clear_sta_flag(sta, WLAN_STA_PS_DELIVER); atomic_dec(&ps->num_sta_ps); sta_info_recalc_tim(sta); @@ -125,7 +127,7 @@ static void __cleanup_single_sta(struct sta_info *sta) if (ieee80211_vif_is_mesh(&sdata->vif)) mesh_sta_cleanup(sta); - cancel_work_sync(&sta->drv_unblock_wk); + cancel_work_sync(&sta->drv_deliver_wk); /* * Destroy aggregation state here. It would be nice to wait for the @@ -253,33 +255,23 @@ static void sta_info_hash_add(struct ieee80211_local *local, rcu_assign_pointer(local->sta_hash[STA_HASH(sta->sta.addr)], sta); } -static void sta_unblock(struct work_struct *wk) +static void sta_deliver_ps_frames(struct work_struct *wk) { struct sta_info *sta; - sta = container_of(wk, struct sta_info, drv_unblock_wk); + sta = container_of(wk, struct sta_info, drv_deliver_wk); if (sta->dead) return; - if (!test_sta_flag(sta, WLAN_STA_PS_STA)) { - local_bh_disable(); + local_bh_disable(); + if (!test_sta_flag(sta, WLAN_STA_PS_STA)) ieee80211_sta_ps_deliver_wakeup(sta); - local_bh_enable(); - } else if (test_and_clear_sta_flag(sta, WLAN_STA_PSPOLL)) { - clear_sta_flag(sta, WLAN_STA_PS_DRIVER); - - local_bh_disable(); + else if (test_and_clear_sta_flag(sta, WLAN_STA_PSPOLL)) ieee80211_sta_ps_deliver_poll_response(sta); - local_bh_enable(); - } else if (test_and_clear_sta_flag(sta, WLAN_STA_UAPSD)) { - clear_sta_flag(sta, WLAN_STA_PS_DRIVER); - - local_bh_disable(); + else if (test_and_clear_sta_flag(sta, WLAN_STA_UAPSD)) ieee80211_sta_ps_deliver_uapsd(sta); - local_bh_enable(); - } else - clear_sta_flag(sta, WLAN_STA_PS_DRIVER); + local_bh_enable(); } static int sta_prepare_rate_control(struct ieee80211_local *local, @@ -341,7 +333,7 @@ struct sta_info *sta_info_alloc(struct ieee80211_sub_if_data *sdata, spin_lock_init(&sta->lock); spin_lock_init(&sta->ps_lock); - INIT_WORK(&sta->drv_unblock_wk, sta_unblock); + INIT_WORK(&sta->drv_deliver_wk, sta_deliver_ps_frames); INIT_WORK(&sta->ampdu_mlme.work, ieee80211_ba_session_work); mutex_init(&sta->ampdu_mlme.mtx); #ifdef CONFIG_MAC80211_MESH @@ -358,7 +350,7 @@ struct sta_info *sta_info_alloc(struct ieee80211_sub_if_data *sdata, sta->sta_state = IEEE80211_STA_NONE; - do_posix_clock_monotonic_gettime(&uptime); + ktime_get_ts(&uptime); sta->last_connected = uptime.tv_sec; ewma_init(&sta->avg_signal, 1024, 8); for (i = 0; i < ARRAY_SIZE(sta->chain_signal_avg); i++) @@ -1141,8 +1133,15 @@ void ieee80211_sta_ps_deliver_wakeup(struct sta_info *sta) } ieee80211_add_pending_skbs(local, &pending); - clear_sta_flag(sta, WLAN_STA_PS_DRIVER); - clear_sta_flag(sta, WLAN_STA_PS_STA); + + /* now we're no longer in the deliver code */ + clear_sta_flag(sta, WLAN_STA_PS_DELIVER); + + /* The station might have polled and then woken up before we responded, + * so clear these flags now to avoid them sticking around. + */ + clear_sta_flag(sta, WLAN_STA_PSPOLL); + clear_sta_flag(sta, WLAN_STA_UAPSD); spin_unlock(&sta->ps_lock); atomic_dec(&ps->num_sta_ps); @@ -1543,10 +1542,26 @@ void ieee80211_sta_block_awake(struct ieee80211_hw *hw, trace_api_sta_block_awake(sta->local, pubsta, block); - if (block) + if (block) { set_sta_flag(sta, WLAN_STA_PS_DRIVER); - else if (test_sta_flag(sta, WLAN_STA_PS_DRIVER)) - ieee80211_queue_work(hw, &sta->drv_unblock_wk); + return; + } + + if (!test_sta_flag(sta, WLAN_STA_PS_DRIVER)) + return; + + if (!test_sta_flag(sta, WLAN_STA_PS_STA)) { + set_sta_flag(sta, WLAN_STA_PS_DELIVER); + clear_sta_flag(sta, WLAN_STA_PS_DRIVER); + ieee80211_queue_work(hw, &sta->drv_deliver_wk); + } else if (test_sta_flag(sta, WLAN_STA_PSPOLL) || + test_sta_flag(sta, WLAN_STA_UAPSD)) { + /* must be asleep in this case */ + clear_sta_flag(sta, WLAN_STA_PS_DRIVER); + ieee80211_queue_work(hw, &sta->drv_deliver_wk); + } else { + clear_sta_flag(sta, WLAN_STA_PS_DRIVER); + } } EXPORT_SYMBOL(ieee80211_sta_block_awake); @@ -1704,3 +1719,140 @@ u8 sta_info_tx_streams(struct sta_info *sta) return ((ht_cap->mcs.tx_params & IEEE80211_HT_MCS_TX_MAX_STREAMS_MASK) >> IEEE80211_HT_MCS_TX_MAX_STREAMS_SHIFT) + 1; } + +void sta_set_sinfo(struct sta_info *sta, struct station_info *sinfo) +{ + struct ieee80211_sub_if_data *sdata = sta->sdata; + struct ieee80211_local *local = sdata->local; + struct rate_control_ref *ref = NULL; + struct timespec uptime; + u64 packets = 0; + u32 thr = 0; + int i, ac; + + if (test_sta_flag(sta, WLAN_STA_RATE_CONTROL)) + ref = local->rate_ctrl; + + sinfo->generation = sdata->local->sta_generation; + + sinfo->filled = STATION_INFO_INACTIVE_TIME | + STATION_INFO_RX_BYTES64 | + STATION_INFO_TX_BYTES64 | + STATION_INFO_RX_PACKETS | + STATION_INFO_TX_PACKETS | + STATION_INFO_TX_RETRIES | + STATION_INFO_TX_FAILED | + STATION_INFO_TX_BITRATE | + STATION_INFO_RX_BITRATE | + STATION_INFO_RX_DROP_MISC | + STATION_INFO_BSS_PARAM | + STATION_INFO_CONNECTED_TIME | + STATION_INFO_STA_FLAGS | + STATION_INFO_BEACON_LOSS_COUNT; + + ktime_get_ts(&uptime); + sinfo->connected_time = uptime.tv_sec - sta->last_connected; + + sinfo->inactive_time = jiffies_to_msecs(jiffies - sta->last_rx); + sinfo->tx_bytes = 0; + for (ac = 0; ac < IEEE80211_NUM_ACS; ac++) { + sinfo->tx_bytes += sta->tx_bytes[ac]; + packets += sta->tx_packets[ac]; + } + sinfo->tx_packets = packets; + sinfo->rx_bytes = sta->rx_bytes; + sinfo->rx_packets = sta->rx_packets; + sinfo->tx_retries = sta->tx_retry_count; + sinfo->tx_failed = sta->tx_retry_failed; + sinfo->rx_dropped_misc = sta->rx_dropped; + sinfo->beacon_loss_count = sta->beacon_loss_count; + + if ((sta->local->hw.flags & IEEE80211_HW_SIGNAL_DBM) || + (sta->local->hw.flags & IEEE80211_HW_SIGNAL_UNSPEC)) { + sinfo->filled |= STATION_INFO_SIGNAL | STATION_INFO_SIGNAL_AVG; + if (!local->ops->get_rssi || + drv_get_rssi(local, sdata, &sta->sta, &sinfo->signal)) + sinfo->signal = (s8)sta->last_signal; + sinfo->signal_avg = (s8) -ewma_read(&sta->avg_signal); + } + if (sta->chains) { + sinfo->filled |= STATION_INFO_CHAIN_SIGNAL | + STATION_INFO_CHAIN_SIGNAL_AVG; + + sinfo->chains = sta->chains; + for (i = 0; i < ARRAY_SIZE(sinfo->chain_signal); i++) { + sinfo->chain_signal[i] = sta->chain_signal_last[i]; + sinfo->chain_signal_avg[i] = + (s8) -ewma_read(&sta->chain_signal_avg[i]); + } + } + + sta_set_rate_info_tx(sta, &sta->last_tx_rate, &sinfo->txrate); + sta_set_rate_info_rx(sta, &sinfo->rxrate); + + if (ieee80211_vif_is_mesh(&sdata->vif)) { +#ifdef CONFIG_MAC80211_MESH + sinfo->filled |= STATION_INFO_LLID | + STATION_INFO_PLID | + STATION_INFO_PLINK_STATE | + STATION_INFO_LOCAL_PM | + STATION_INFO_PEER_PM | + STATION_INFO_NONPEER_PM; + + sinfo->llid = sta->llid; + sinfo->plid = sta->plid; + sinfo->plink_state = sta->plink_state; + if (test_sta_flag(sta, WLAN_STA_TOFFSET_KNOWN)) { + sinfo->filled |= STATION_INFO_T_OFFSET; + sinfo->t_offset = sta->t_offset; + } + sinfo->local_pm = sta->local_pm; + sinfo->peer_pm = sta->peer_pm; + sinfo->nonpeer_pm = sta->nonpeer_pm; +#endif + } + + sinfo->bss_param.flags = 0; + if (sdata->vif.bss_conf.use_cts_prot) + sinfo->bss_param.flags |= BSS_PARAM_FLAGS_CTS_PROT; + if (sdata->vif.bss_conf.use_short_preamble) + sinfo->bss_param.flags |= BSS_PARAM_FLAGS_SHORT_PREAMBLE; + if (sdata->vif.bss_conf.use_short_slot) + sinfo->bss_param.flags |= BSS_PARAM_FLAGS_SHORT_SLOT_TIME; + sinfo->bss_param.dtim_period = sdata->local->hw.conf.ps_dtim_period; + sinfo->bss_param.beacon_interval = sdata->vif.bss_conf.beacon_int; + + sinfo->sta_flags.set = 0; + sinfo->sta_flags.mask = BIT(NL80211_STA_FLAG_AUTHORIZED) | + BIT(NL80211_STA_FLAG_SHORT_PREAMBLE) | + BIT(NL80211_STA_FLAG_WME) | + BIT(NL80211_STA_FLAG_MFP) | + BIT(NL80211_STA_FLAG_AUTHENTICATED) | + BIT(NL80211_STA_FLAG_ASSOCIATED) | + BIT(NL80211_STA_FLAG_TDLS_PEER); + if (test_sta_flag(sta, WLAN_STA_AUTHORIZED)) + sinfo->sta_flags.set |= BIT(NL80211_STA_FLAG_AUTHORIZED); + if (test_sta_flag(sta, WLAN_STA_SHORT_PREAMBLE)) + sinfo->sta_flags.set |= BIT(NL80211_STA_FLAG_SHORT_PREAMBLE); + if (test_sta_flag(sta, WLAN_STA_WME)) + sinfo->sta_flags.set |= BIT(NL80211_STA_FLAG_WME); + if (test_sta_flag(sta, WLAN_STA_MFP)) + sinfo->sta_flags.set |= BIT(NL80211_STA_FLAG_MFP); + if (test_sta_flag(sta, WLAN_STA_AUTH)) + sinfo->sta_flags.set |= BIT(NL80211_STA_FLAG_AUTHENTICATED); + if (test_sta_flag(sta, WLAN_STA_ASSOC)) + sinfo->sta_flags.set |= BIT(NL80211_STA_FLAG_ASSOCIATED); + if (test_sta_flag(sta, WLAN_STA_TDLS_PEER)) + sinfo->sta_flags.set |= BIT(NL80211_STA_FLAG_TDLS_PEER); + + /* check if the driver has a SW RC implementation */ + if (ref && ref->ops->get_expected_throughput) + thr = ref->ops->get_expected_throughput(sta->rate_ctrl_priv); + else + thr = drv_get_expected_throughput(local, &sta->sta); + + if (thr != 0) { + sinfo->filled |= STATION_INFO_EXPECTED_THROUGHPUT; + sinfo->expected_throughput = thr; + } +} diff --git a/net/mac80211/sta_info.h b/net/mac80211/sta_info.h index 4acc5fc402fa..d411bcc8ef08 100644 --- a/net/mac80211/sta_info.h +++ b/net/mac80211/sta_info.h @@ -47,6 +47,8 @@ * @WLAN_STA_TDLS_PEER: Station is a TDLS peer. * @WLAN_STA_TDLS_PEER_AUTH: This TDLS peer is authorized to send direct * packets. This means the link is enabled. + * @WLAN_STA_TDLS_INITIATOR: We are the initiator of the TDLS link with this + * station. * @WLAN_STA_UAPSD: Station requested unscheduled SP while driver was * keeping station in power-save mode, reply when the driver * unblocks the station. @@ -58,6 +60,8 @@ * @WLAN_STA_TOFFSET_KNOWN: toffset calculated for this station is valid. * @WLAN_STA_MPSP_OWNER: local STA is owner of a mesh Peer Service Period. * @WLAN_STA_MPSP_RECIPIENT: local STA is recipient of a MPSP. + * @WLAN_STA_PS_DELIVER: station woke up, but we're still blocking TX + * until pending frames are delivered */ enum ieee80211_sta_info_flags { WLAN_STA_AUTH, @@ -74,6 +78,7 @@ enum ieee80211_sta_info_flags { WLAN_STA_PSPOLL, WLAN_STA_TDLS_PEER, WLAN_STA_TDLS_PEER_AUTH, + WLAN_STA_TDLS_INITIATOR, WLAN_STA_UAPSD, WLAN_STA_SP, WLAN_STA_4ADDR_EVENT, @@ -82,6 +87,7 @@ enum ieee80211_sta_info_flags { WLAN_STA_TOFFSET_KNOWN, WLAN_STA_MPSP_OWNER, WLAN_STA_MPSP_RECIPIENT, + WLAN_STA_PS_DELIVER, }; #define ADDBA_RESP_INTERVAL HZ @@ -149,7 +155,8 @@ struct tid_ampdu_tx { /** * struct tid_ampdu_rx - TID aggregation information (Rx). * - * @reorder_buf: buffer to reorder incoming aggregated MPDUs + * @reorder_buf: buffer to reorder incoming aggregated MPDUs. An MPDU may be an + * A-MSDU with individually reported subframes. * @reorder_time: jiffies when skb was added * @session_timer: check if peer keeps Tx-ing on the TID (by timeout value) * @reorder_timer: releases expired frames from the reorder buffer. @@ -174,7 +181,7 @@ struct tid_ampdu_tx { struct tid_ampdu_rx { struct rcu_head rcu_head; spinlock_t reorder_lock; - struct sk_buff **reorder_buf; + struct sk_buff_head *reorder_buf; unsigned long *reorder_time; struct timer_list session_timer; struct timer_list reorder_timer; @@ -265,7 +272,7 @@ struct ieee80211_tx_latency_stat { * @last_rx_rate_vht_nss: rx status nss of last data packet * @lock: used for locking all fields that require locking, see comments * in the header file. - * @drv_unblock_wk: used for driver PS unblocking + * @drv_deliver_wk: used for delivering frames after driver PS unblocking * @listen_interval: listen interval of this station, when we're acting as AP * @_flags: STA flags, see &enum ieee80211_sta_info_flags, do not use directly * @ps_lock: used for powersave (when mac80211 is the AP) related locking @@ -278,7 +285,6 @@ struct ieee80211_tx_latency_stat { * @driver_buffered_tids: bitmap of TIDs the driver has data buffered on * @rx_packets: Number of MSDUs received from this STA * @rx_bytes: Number of bytes received from this STA - * @wep_weak_iv_count: number of weak WEP IVs received from this station * @last_rx: time (in jiffies) when last frame was received from this STA * @last_connected: time (in seconds) when a station got connected * @num_duplicates: number of duplicate frames received from this STA @@ -303,7 +309,6 @@ struct ieee80211_tx_latency_stat { * @plid: Peer link ID * @reason: Cancel reason on PLINK_HOLDING state * @plink_retries: Retries in establishment - * @ignore_plink_timer: ignore the peer-link timer (used internally) * @plink_state: peer link state * @plink_timeout: timeout of peer link * @plink_timer: peer link watch timer @@ -345,7 +350,7 @@ struct sta_info { void *rate_ctrl_priv; spinlock_t lock; - struct work_struct drv_unblock_wk; + struct work_struct drv_deliver_wk; u16 listen_interval; @@ -367,7 +372,6 @@ struct sta_info { /* Updated from RX path only, no locking requirements */ unsigned long rx_packets; u64 rx_bytes; - unsigned long wep_weak_iv_count; unsigned long last_rx; long last_connected; unsigned long num_duplicates; @@ -418,7 +422,6 @@ struct sta_info { u16 plid; u16 reason; u8 plink_retries; - bool ignore_plink_timer; enum nl80211_plink_state plink_state; u32 plink_timeout; struct timer_list plink_timer; @@ -628,6 +631,8 @@ void sta_set_rate_info_tx(struct sta_info *sta, struct rate_info *rinfo); void sta_set_rate_info_rx(struct sta_info *sta, struct rate_info *rinfo); +void sta_set_sinfo(struct sta_info *sta, struct station_info *sinfo); + void ieee80211_sta_expire(struct ieee80211_sub_if_data *sdata, unsigned long exp_time); u8 sta_info_tx_streams(struct sta_info *sta); diff --git a/net/mac80211/status.c b/net/mac80211/status.c index ba29ebc86141..aa06dcad336e 100644 --- a/net/mac80211/status.c +++ b/net/mac80211/status.c @@ -473,8 +473,6 @@ static void ieee80211_tx_latency_end_msrmnt(struct ieee80211_local *local, struct sta_info *sta, struct ieee80211_hdr *hdr) { - ktime_t skb_dprt; - struct timespec dprt_time; u32 msrmnt; u16 tid; u8 *qc; @@ -506,9 +504,8 @@ static void ieee80211_tx_latency_end_msrmnt(struct ieee80211_local *local, tx_lat = &sta->tx_lat[tid]; - ktime_get_ts(&dprt_time); /* time stamp completion time */ - skb_dprt = ktime_set(dprt_time.tv_sec, dprt_time.tv_nsec); - msrmnt = ktime_to_ms(ktime_sub(skb_dprt, skb_arv)); + /* Calculate the latency */ + msrmnt = ktime_to_ms(ktime_sub(ktime_get(), skb_arv)); if (tx_lat->max < msrmnt) /* update stats */ tx_lat->max = msrmnt; diff --git a/net/mac80211/tdls.c b/net/mac80211/tdls.c index 652813b2d3df..1b21050be174 100644 --- a/net/mac80211/tdls.c +++ b/net/mac80211/tdls.c @@ -8,7 +8,31 @@ */ #include <linux/ieee80211.h> +#include <linux/log2.h> +#include <net/cfg80211.h> #include "ieee80211_i.h" +#include "driver-ops.h" + +/* give usermode some time for retries in setting up the TDLS session */ +#define TDLS_PEER_SETUP_TIMEOUT (15 * HZ) + +void ieee80211_tdls_peer_del_work(struct work_struct *wk) +{ + struct ieee80211_sub_if_data *sdata; + struct ieee80211_local *local; + + sdata = container_of(wk, struct ieee80211_sub_if_data, + u.mgd.tdls_peer_del_work.work); + local = sdata->local; + + mutex_lock(&local->mtx); + if (!is_zero_ether_addr(sdata->u.mgd.tdls_peer)) { + tdls_dbg(sdata, "TDLS del peer %pM\n", sdata->u.mgd.tdls_peer); + sta_info_destroy_addr(sdata, sdata->u.mgd.tdls_peer); + eth_zero_addr(sdata->u.mgd.tdls_peer); + } + mutex_unlock(&local->mtx); +} static void ieee80211_tdls_add_ext_capab(struct sk_buff *skb) { @@ -23,11 +47,16 @@ static void ieee80211_tdls_add_ext_capab(struct sk_buff *skb) *pos++ = WLAN_EXT_CAPA5_TDLS_ENABLED; } -static u16 ieee80211_get_tdls_sta_capab(struct ieee80211_sub_if_data *sdata) +static u16 ieee80211_get_tdls_sta_capab(struct ieee80211_sub_if_data *sdata, + u16 status_code) { struct ieee80211_local *local = sdata->local; u16 capab; + /* The capability will be 0 when sending a failure code */ + if (status_code != 0) + return 0; + capab = 0; if (ieee80211_get_sdata_band(sdata) != IEEE80211_BAND_2GHZ) return capab; @@ -40,19 +69,332 @@ static u16 ieee80211_get_tdls_sta_capab(struct ieee80211_sub_if_data *sdata) return capab; } -static void ieee80211_tdls_add_link_ie(struct sk_buff *skb, const u8 *src_addr, - const u8 *peer, const u8 *bssid) +static void ieee80211_tdls_add_link_ie(struct ieee80211_sub_if_data *sdata, + struct sk_buff *skb, const u8 *peer, + bool initiator) { struct ieee80211_tdls_lnkie *lnkid; + const u8 *init_addr, *rsp_addr; + + if (initiator) { + init_addr = sdata->vif.addr; + rsp_addr = peer; + } else { + init_addr = peer; + rsp_addr = sdata->vif.addr; + } lnkid = (void *)skb_put(skb, sizeof(struct ieee80211_tdls_lnkie)); lnkid->ie_type = WLAN_EID_LINK_ID; lnkid->ie_len = sizeof(struct ieee80211_tdls_lnkie) - 2; - memcpy(lnkid->bssid, bssid, ETH_ALEN); - memcpy(lnkid->init_sta, src_addr, ETH_ALEN); - memcpy(lnkid->resp_sta, peer, ETH_ALEN); + memcpy(lnkid->bssid, sdata->u.mgd.bssid, ETH_ALEN); + memcpy(lnkid->init_sta, init_addr, ETH_ALEN); + memcpy(lnkid->resp_sta, rsp_addr, ETH_ALEN); +} + +/* translate numbering in the WMM parameter IE to the mac80211 notation */ +static enum ieee80211_ac_numbers ieee80211_ac_from_wmm(int ac) +{ + switch (ac) { + default: + WARN_ON_ONCE(1); + case 0: + return IEEE80211_AC_BE; + case 1: + return IEEE80211_AC_BK; + case 2: + return IEEE80211_AC_VI; + case 3: + return IEEE80211_AC_VO; + } +} + +static u8 ieee80211_wmm_aci_aifsn(int aifsn, bool acm, int aci) +{ + u8 ret; + + ret = aifsn & 0x0f; + if (acm) + ret |= 0x10; + ret |= (aci << 5) & 0x60; + return ret; +} + +static u8 ieee80211_wmm_ecw(u16 cw_min, u16 cw_max) +{ + return ((ilog2(cw_min + 1) << 0x0) & 0x0f) | + ((ilog2(cw_max + 1) << 0x4) & 0xf0); +} + +static void ieee80211_tdls_add_wmm_param_ie(struct ieee80211_sub_if_data *sdata, + struct sk_buff *skb) +{ + struct ieee80211_wmm_param_ie *wmm; + struct ieee80211_tx_queue_params *txq; + int i; + + wmm = (void *)skb_put(skb, sizeof(*wmm)); + memset(wmm, 0, sizeof(*wmm)); + + wmm->element_id = WLAN_EID_VENDOR_SPECIFIC; + wmm->len = sizeof(*wmm) - 2; + + wmm->oui[0] = 0x00; /* Microsoft OUI 00:50:F2 */ + wmm->oui[1] = 0x50; + wmm->oui[2] = 0xf2; + wmm->oui_type = 2; /* WME */ + wmm->oui_subtype = 1; /* WME param */ + wmm->version = 1; /* WME ver */ + wmm->qos_info = 0; /* U-APSD not in use */ + + /* + * Use the EDCA parameters defined for the BSS, or default if the AP + * doesn't support it, as mandated by 802.11-2012 section 10.22.4 + */ + for (i = 0; i < IEEE80211_NUM_ACS; i++) { + txq = &sdata->tx_conf[ieee80211_ac_from_wmm(i)]; + wmm->ac[i].aci_aifsn = ieee80211_wmm_aci_aifsn(txq->aifs, + txq->acm, i); + wmm->ac[i].cw = ieee80211_wmm_ecw(txq->cw_min, txq->cw_max); + wmm->ac[i].txop_limit = cpu_to_le16(txq->txop); + } +} + +static void +ieee80211_tdls_add_setup_start_ies(struct ieee80211_sub_if_data *sdata, + struct sk_buff *skb, const u8 *peer, + u8 action_code, bool initiator, + const u8 *extra_ies, size_t extra_ies_len) +{ + enum ieee80211_band band = ieee80211_get_sdata_band(sdata); + struct ieee80211_local *local = sdata->local; + struct ieee80211_supported_band *sband; + struct ieee80211_sta_ht_cap ht_cap; + struct sta_info *sta = NULL; + size_t offset = 0, noffset; + u8 *pos; + + rcu_read_lock(); + + /* we should have the peer STA if we're already responding */ + if (action_code == WLAN_TDLS_SETUP_RESPONSE) { + sta = sta_info_get(sdata, peer); + if (WARN_ON_ONCE(!sta)) { + rcu_read_unlock(); + return; + } + } + + ieee80211_add_srates_ie(sdata, skb, false, band); + ieee80211_add_ext_srates_ie(sdata, skb, false, band); + + /* add any custom IEs that go before Extended Capabilities */ + if (extra_ies_len) { + static const u8 before_ext_cap[] = { + WLAN_EID_SUPP_RATES, + WLAN_EID_COUNTRY, + WLAN_EID_EXT_SUPP_RATES, + WLAN_EID_SUPPORTED_CHANNELS, + WLAN_EID_RSN, + }; + noffset = ieee80211_ie_split(extra_ies, extra_ies_len, + before_ext_cap, + ARRAY_SIZE(before_ext_cap), + offset); + pos = skb_put(skb, noffset - offset); + memcpy(pos, extra_ies + offset, noffset - offset); + offset = noffset; + } + + ieee80211_tdls_add_ext_capab(skb); + + /* add the QoS element if we support it */ + if (local->hw.queues >= IEEE80211_NUM_ACS && + action_code != WLAN_PUB_ACTION_TDLS_DISCOVER_RES) + ieee80211_add_wmm_info_ie(skb_put(skb, 9), 0); /* no U-APSD */ + + /* add any custom IEs that go before HT capabilities */ + if (extra_ies_len) { + static const u8 before_ht_cap[] = { + WLAN_EID_SUPP_RATES, + WLAN_EID_COUNTRY, + WLAN_EID_EXT_SUPP_RATES, + WLAN_EID_SUPPORTED_CHANNELS, + WLAN_EID_RSN, + WLAN_EID_EXT_CAPABILITY, + WLAN_EID_QOS_CAPA, + WLAN_EID_FAST_BSS_TRANSITION, + WLAN_EID_TIMEOUT_INTERVAL, + WLAN_EID_SUPPORTED_REGULATORY_CLASSES, + }; + noffset = ieee80211_ie_split(extra_ies, extra_ies_len, + before_ht_cap, + ARRAY_SIZE(before_ht_cap), + offset); + pos = skb_put(skb, noffset - offset); + memcpy(pos, extra_ies + offset, noffset - offset); + offset = noffset; + } + + /* + * with TDLS we can switch channels, and HT-caps are not necessarily + * the same on all bands. The specification limits the setup to a + * single HT-cap, so use the current band for now. + */ + sband = local->hw.wiphy->bands[band]; + memcpy(&ht_cap, &sband->ht_cap, sizeof(ht_cap)); + if ((action_code == WLAN_TDLS_SETUP_REQUEST || + action_code == WLAN_TDLS_SETUP_RESPONSE) && + ht_cap.ht_supported && (!sta || sta->sta.ht_cap.ht_supported)) { + if (action_code == WLAN_TDLS_SETUP_REQUEST) { + ieee80211_apply_htcap_overrides(sdata, &ht_cap); + + /* disable SMPS in TDLS initiator */ + ht_cap.cap |= (WLAN_HT_CAP_SM_PS_DISABLED + << IEEE80211_HT_CAP_SM_PS_SHIFT); + } else { + /* disable SMPS in TDLS responder */ + sta->sta.ht_cap.cap |= + (WLAN_HT_CAP_SM_PS_DISABLED + << IEEE80211_HT_CAP_SM_PS_SHIFT); + + /* the peer caps are already intersected with our own */ + memcpy(&ht_cap, &sta->sta.ht_cap, sizeof(ht_cap)); + } + + pos = skb_put(skb, sizeof(struct ieee80211_ht_cap) + 2); + ieee80211_ie_build_ht_cap(pos, &ht_cap, ht_cap.cap); + } + + rcu_read_unlock(); + + /* add any remaining IEs */ + if (extra_ies_len) { + noffset = extra_ies_len; + pos = skb_put(skb, noffset - offset); + memcpy(pos, extra_ies + offset, noffset - offset); + } + + ieee80211_tdls_add_link_ie(sdata, skb, peer, initiator); +} + +static void +ieee80211_tdls_add_setup_cfm_ies(struct ieee80211_sub_if_data *sdata, + struct sk_buff *skb, const u8 *peer, + bool initiator, const u8 *extra_ies, + size_t extra_ies_len) +{ + struct ieee80211_local *local = sdata->local; + struct ieee80211_if_managed *ifmgd = &sdata->u.mgd; + size_t offset = 0, noffset; + struct sta_info *sta, *ap_sta; + u8 *pos; + + rcu_read_lock(); + + sta = sta_info_get(sdata, peer); + ap_sta = sta_info_get(sdata, ifmgd->bssid); + if (WARN_ON_ONCE(!sta || !ap_sta)) { + rcu_read_unlock(); + return; + } + + /* add any custom IEs that go before the QoS IE */ + if (extra_ies_len) { + static const u8 before_qos[] = { + WLAN_EID_RSN, + }; + noffset = ieee80211_ie_split(extra_ies, extra_ies_len, + before_qos, + ARRAY_SIZE(before_qos), + offset); + pos = skb_put(skb, noffset - offset); + memcpy(pos, extra_ies + offset, noffset - offset); + offset = noffset; + } + + /* add the QoS param IE if both the peer and we support it */ + if (local->hw.queues >= IEEE80211_NUM_ACS && + test_sta_flag(sta, WLAN_STA_WME)) + ieee80211_tdls_add_wmm_param_ie(sdata, skb); + + /* add any custom IEs that go before HT operation */ + if (extra_ies_len) { + static const u8 before_ht_op[] = { + WLAN_EID_RSN, + WLAN_EID_QOS_CAPA, + WLAN_EID_FAST_BSS_TRANSITION, + WLAN_EID_TIMEOUT_INTERVAL, + }; + noffset = ieee80211_ie_split(extra_ies, extra_ies_len, + before_ht_op, + ARRAY_SIZE(before_ht_op), + offset); + pos = skb_put(skb, noffset - offset); + memcpy(pos, extra_ies + offset, noffset - offset); + offset = noffset; + } + + /* if HT support is only added in TDLS, we need an HT-operation IE */ + if (!ap_sta->sta.ht_cap.ht_supported && sta->sta.ht_cap.ht_supported) { + struct ieee80211_chanctx_conf *chanctx_conf = + rcu_dereference(sdata->vif.chanctx_conf); + if (!WARN_ON(!chanctx_conf)) { + pos = skb_put(skb, 2 + + sizeof(struct ieee80211_ht_operation)); + /* send an empty HT operation IE */ + ieee80211_ie_build_ht_oper(pos, &sta->sta.ht_cap, + &chanctx_conf->def, 0); + } + } + + rcu_read_unlock(); + + /* add any remaining IEs */ + if (extra_ies_len) { + noffset = extra_ies_len; + pos = skb_put(skb, noffset - offset); + memcpy(pos, extra_ies + offset, noffset - offset); + } + + ieee80211_tdls_add_link_ie(sdata, skb, peer, initiator); +} + +static void ieee80211_tdls_add_ies(struct ieee80211_sub_if_data *sdata, + struct sk_buff *skb, const u8 *peer, + u8 action_code, u16 status_code, + bool initiator, const u8 *extra_ies, + size_t extra_ies_len) +{ + switch (action_code) { + case WLAN_TDLS_SETUP_REQUEST: + case WLAN_TDLS_SETUP_RESPONSE: + case WLAN_PUB_ACTION_TDLS_DISCOVER_RES: + if (status_code == 0) + ieee80211_tdls_add_setup_start_ies(sdata, skb, peer, + action_code, + initiator, + extra_ies, + extra_ies_len); + break; + case WLAN_TDLS_SETUP_CONFIRM: + if (status_code == 0) + ieee80211_tdls_add_setup_cfm_ies(sdata, skb, peer, + initiator, extra_ies, + extra_ies_len); + break; + case WLAN_TDLS_TEARDOWN: + case WLAN_TDLS_DISCOVERY_REQUEST: + if (extra_ies_len) + memcpy(skb_put(skb, extra_ies_len), extra_ies, + extra_ies_len); + if (status_code == 0 || action_code == WLAN_TDLS_TEARDOWN) + ieee80211_tdls_add_link_ie(sdata, skb, peer, initiator); + break; + } + } static int @@ -61,7 +403,6 @@ ieee80211_prep_tdls_encap_data(struct wiphy *wiphy, struct net_device *dev, u16 status_code, struct sk_buff *skb) { struct ieee80211_sub_if_data *sdata = IEEE80211_DEV_TO_SUB_IF(dev); - enum ieee80211_band band = ieee80211_get_sdata_band(sdata); struct ieee80211_tdls_data *tf; tf = (void *)skb_put(skb, offsetof(struct ieee80211_tdls_data, u)); @@ -79,11 +420,8 @@ ieee80211_prep_tdls_encap_data(struct wiphy *wiphy, struct net_device *dev, skb_put(skb, sizeof(tf->u.setup_req)); tf->u.setup_req.dialog_token = dialog_token; tf->u.setup_req.capability = - cpu_to_le16(ieee80211_get_tdls_sta_capab(sdata)); - - ieee80211_add_srates_ie(sdata, skb, false, band); - ieee80211_add_ext_srates_ie(sdata, skb, false, band); - ieee80211_tdls_add_ext_capab(skb); + cpu_to_le16(ieee80211_get_tdls_sta_capab(sdata, + status_code)); break; case WLAN_TDLS_SETUP_RESPONSE: tf->category = WLAN_CATEGORY_TDLS; @@ -93,11 +431,8 @@ ieee80211_prep_tdls_encap_data(struct wiphy *wiphy, struct net_device *dev, tf->u.setup_resp.status_code = cpu_to_le16(status_code); tf->u.setup_resp.dialog_token = dialog_token; tf->u.setup_resp.capability = - cpu_to_le16(ieee80211_get_tdls_sta_capab(sdata)); - - ieee80211_add_srates_ie(sdata, skb, false, band); - ieee80211_add_ext_srates_ie(sdata, skb, false, band); - ieee80211_tdls_add_ext_capab(skb); + cpu_to_le16(ieee80211_get_tdls_sta_capab(sdata, + status_code)); break; case WLAN_TDLS_SETUP_CONFIRM: tf->category = WLAN_CATEGORY_TDLS; @@ -134,7 +469,6 @@ ieee80211_prep_tdls_direct(struct wiphy *wiphy, struct net_device *dev, u16 status_code, struct sk_buff *skb) { struct ieee80211_sub_if_data *sdata = IEEE80211_DEV_TO_SUB_IF(dev); - enum ieee80211_band band = ieee80211_get_sdata_band(sdata); struct ieee80211_mgmt *mgmt; mgmt = (void *)skb_put(skb, 24); @@ -155,11 +489,8 @@ ieee80211_prep_tdls_direct(struct wiphy *wiphy, struct net_device *dev, mgmt->u.action.u.tdls_discover_resp.dialog_token = dialog_token; mgmt->u.action.u.tdls_discover_resp.capability = - cpu_to_le16(ieee80211_get_tdls_sta_capab(sdata)); - - ieee80211_add_srates_ie(sdata, skb, false, band); - ieee80211_add_ext_srates_ie(sdata, skb, false, band); - ieee80211_tdls_add_ext_capab(skb); + cpu_to_le16(ieee80211_get_tdls_sta_capab(sdata, + status_code)); break; default: return -EINVAL; @@ -168,33 +499,28 @@ ieee80211_prep_tdls_direct(struct wiphy *wiphy, struct net_device *dev, return 0; } -int ieee80211_tdls_mgmt(struct wiphy *wiphy, struct net_device *dev, - const u8 *peer, u8 action_code, u8 dialog_token, - u16 status_code, u32 peer_capability, - const u8 *extra_ies, size_t extra_ies_len) +static int +ieee80211_tdls_prep_mgmt_packet(struct wiphy *wiphy, struct net_device *dev, + const u8 *peer, u8 action_code, + u8 dialog_token, u16 status_code, + u32 peer_capability, bool initiator, + const u8 *extra_ies, size_t extra_ies_len) { struct ieee80211_sub_if_data *sdata = IEEE80211_DEV_TO_SUB_IF(dev); struct ieee80211_local *local = sdata->local; struct sk_buff *skb = NULL; bool send_direct; + struct sta_info *sta; int ret; - if (!(wiphy->flags & WIPHY_FLAG_SUPPORTS_TDLS)) - return -ENOTSUPP; - - /* make sure we are in managed mode, and associated */ - if (sdata->vif.type != NL80211_IFTYPE_STATION || - !sdata->u.mgd.associated) - return -EINVAL; - - tdls_dbg(sdata, "TDLS mgmt action %d peer %pM\n", - action_code, peer); - skb = dev_alloc_skb(local->hw.extra_tx_headroom + max(sizeof(struct ieee80211_mgmt), sizeof(struct ieee80211_tdls_data)) + 50 + /* supported rates */ 7 + /* ext capab */ + 26 + /* max(WMM-info, WMM-param) */ + 2 + max(sizeof(struct ieee80211_ht_cap), + sizeof(struct ieee80211_ht_operation)) + extra_ies_len + sizeof(struct ieee80211_tdls_lnkie)); if (!skb) @@ -227,30 +553,48 @@ int ieee80211_tdls_mgmt(struct wiphy *wiphy, struct net_device *dev, if (ret < 0) goto fail; - if (extra_ies_len) - memcpy(skb_put(skb, extra_ies_len), extra_ies, extra_ies_len); + rcu_read_lock(); + sta = sta_info_get(sdata, peer); - /* the TDLS link IE is always added last */ + /* infer the initiator if we can, to support old userspace */ switch (action_code) { case WLAN_TDLS_SETUP_REQUEST: + if (sta) + set_sta_flag(sta, WLAN_STA_TDLS_INITIATOR); + /* fall-through */ case WLAN_TDLS_SETUP_CONFIRM: - case WLAN_TDLS_TEARDOWN: case WLAN_TDLS_DISCOVERY_REQUEST: - /* we are the initiator */ - ieee80211_tdls_add_link_ie(skb, sdata->vif.addr, peer, - sdata->u.mgd.bssid); + initiator = true; break; case WLAN_TDLS_SETUP_RESPONSE: + /* + * In some testing scenarios, we send a request and response. + * Make the last packet sent take effect for the initiator + * value. + */ + if (sta) + clear_sta_flag(sta, WLAN_STA_TDLS_INITIATOR); + /* fall-through */ case WLAN_PUB_ACTION_TDLS_DISCOVER_RES: - /* we are the responder */ - ieee80211_tdls_add_link_ie(skb, peer, sdata->vif.addr, - sdata->u.mgd.bssid); + initiator = false; + break; + case WLAN_TDLS_TEARDOWN: + /* any value is ok */ break; default: ret = -ENOTSUPP; - goto fail; + break; } + if (sta && test_sta_flag(sta, WLAN_STA_TDLS_INITIATOR)) + initiator = true; + + rcu_read_unlock(); + if (ret < 0) + goto fail; + + ieee80211_tdls_add_ies(sdata, skb, peer, action_code, status_code, + initiator, extra_ies, extra_ies_len); if (send_direct) { ieee80211_tx_skb(sdata, skb); return 0; @@ -284,11 +628,175 @@ fail: return ret; } +static int +ieee80211_tdls_mgmt_setup(struct wiphy *wiphy, struct net_device *dev, + const u8 *peer, u8 action_code, u8 dialog_token, + u16 status_code, u32 peer_capability, bool initiator, + const u8 *extra_ies, size_t extra_ies_len) +{ + struct ieee80211_sub_if_data *sdata = IEEE80211_DEV_TO_SUB_IF(dev); + struct ieee80211_local *local = sdata->local; + int ret; + + mutex_lock(&local->mtx); + + /* we don't support concurrent TDLS peer setups */ + if (!is_zero_ether_addr(sdata->u.mgd.tdls_peer) && + !ether_addr_equal(sdata->u.mgd.tdls_peer, peer)) { + ret = -EBUSY; + goto exit; + } + + /* + * make sure we have a STA representing the peer so we drop or buffer + * non-TDLS-setup frames to the peer. We can't send other packets + * during setup through the AP path. + * Allow error packets to be sent - sometimes we don't even add a STA + * before failing the setup. + */ + if (status_code == 0) { + rcu_read_lock(); + if (!sta_info_get(sdata, peer)) { + rcu_read_unlock(); + ret = -ENOLINK; + goto exit; + } + rcu_read_unlock(); + } + + ieee80211_flush_queues(local, sdata); + + ret = ieee80211_tdls_prep_mgmt_packet(wiphy, dev, peer, action_code, + dialog_token, status_code, + peer_capability, initiator, + extra_ies, extra_ies_len); + if (ret < 0) + goto exit; + + memcpy(sdata->u.mgd.tdls_peer, peer, ETH_ALEN); + ieee80211_queue_delayed_work(&sdata->local->hw, + &sdata->u.mgd.tdls_peer_del_work, + TDLS_PEER_SETUP_TIMEOUT); + +exit: + mutex_unlock(&local->mtx); + return ret; +} + +static int +ieee80211_tdls_mgmt_teardown(struct wiphy *wiphy, struct net_device *dev, + const u8 *peer, u8 action_code, u8 dialog_token, + u16 status_code, u32 peer_capability, + bool initiator, const u8 *extra_ies, + size_t extra_ies_len) +{ + struct ieee80211_sub_if_data *sdata = IEEE80211_DEV_TO_SUB_IF(dev); + struct ieee80211_local *local = sdata->local; + struct sta_info *sta; + int ret; + + /* + * No packets can be transmitted to the peer via the AP during setup - + * the STA is set as a TDLS peer, but is not authorized. + * During teardown, we prevent direct transmissions by stopping the + * queues and flushing all direct packets. + */ + ieee80211_stop_vif_queues(local, sdata, + IEEE80211_QUEUE_STOP_REASON_TDLS_TEARDOWN); + ieee80211_flush_queues(local, sdata); + + ret = ieee80211_tdls_prep_mgmt_packet(wiphy, dev, peer, action_code, + dialog_token, status_code, + peer_capability, initiator, + extra_ies, extra_ies_len); + if (ret < 0) + sdata_err(sdata, "Failed sending TDLS teardown packet %d\n", + ret); + + /* + * Remove the STA AUTH flag to force further traffic through the AP. If + * the STA was unreachable, it was already removed. + */ + rcu_read_lock(); + sta = sta_info_get(sdata, peer); + if (sta) + clear_sta_flag(sta, WLAN_STA_TDLS_PEER_AUTH); + rcu_read_unlock(); + + ieee80211_wake_vif_queues(local, sdata, + IEEE80211_QUEUE_STOP_REASON_TDLS_TEARDOWN); + + return 0; +} + +int ieee80211_tdls_mgmt(struct wiphy *wiphy, struct net_device *dev, + const u8 *peer, u8 action_code, u8 dialog_token, + u16 status_code, u32 peer_capability, + bool initiator, const u8 *extra_ies, + size_t extra_ies_len) +{ + struct ieee80211_sub_if_data *sdata = IEEE80211_DEV_TO_SUB_IF(dev); + int ret; + + if (!(wiphy->flags & WIPHY_FLAG_SUPPORTS_TDLS)) + return -ENOTSUPP; + + /* make sure we are in managed mode, and associated */ + if (sdata->vif.type != NL80211_IFTYPE_STATION || + !sdata->u.mgd.associated) + return -EINVAL; + + switch (action_code) { + case WLAN_TDLS_SETUP_REQUEST: + case WLAN_TDLS_SETUP_RESPONSE: + ret = ieee80211_tdls_mgmt_setup(wiphy, dev, peer, action_code, + dialog_token, status_code, + peer_capability, initiator, + extra_ies, extra_ies_len); + break; + case WLAN_TDLS_TEARDOWN: + ret = ieee80211_tdls_mgmt_teardown(wiphy, dev, peer, + action_code, dialog_token, + status_code, + peer_capability, initiator, + extra_ies, extra_ies_len); + break; + case WLAN_TDLS_DISCOVERY_REQUEST: + /* + * Protect the discovery so we can hear the TDLS discovery + * response frame. It is transmitted directly and not buffered + * by the AP. + */ + drv_mgd_protect_tdls_discover(sdata->local, sdata); + /* fall-through */ + case WLAN_TDLS_SETUP_CONFIRM: + case WLAN_PUB_ACTION_TDLS_DISCOVER_RES: + /* no special handling */ + ret = ieee80211_tdls_prep_mgmt_packet(wiphy, dev, peer, + action_code, + dialog_token, + status_code, + peer_capability, + initiator, extra_ies, + extra_ies_len); + break; + default: + ret = -EOPNOTSUPP; + break; + } + + tdls_dbg(sdata, "TDLS mgmt action %d peer %pM status %d\n", + action_code, peer, ret); + return ret; +} + int ieee80211_tdls_oper(struct wiphy *wiphy, struct net_device *dev, const u8 *peer, enum nl80211_tdls_operation oper) { struct sta_info *sta; struct ieee80211_sub_if_data *sdata = IEEE80211_DEV_TO_SUB_IF(dev); + struct ieee80211_local *local = sdata->local; + int ret; if (!(wiphy->flags & WIPHY_FLAG_SUPPORTS_TDLS)) return -ENOTSUPP; @@ -296,6 +804,18 @@ int ieee80211_tdls_oper(struct wiphy *wiphy, struct net_device *dev, if (sdata->vif.type != NL80211_IFTYPE_STATION) return -EINVAL; + switch (oper) { + case NL80211_TDLS_ENABLE_LINK: + case NL80211_TDLS_DISABLE_LINK: + break; + case NL80211_TDLS_TEARDOWN: + case NL80211_TDLS_SETUP: + case NL80211_TDLS_DISCOVERY_REQ: + /* We don't support in-driver setup/teardown/discovery */ + return -ENOTSUPP; + } + + mutex_lock(&local->mtx); tdls_dbg(sdata, "TDLS oper %d peer %pM\n", oper, peer); switch (oper) { @@ -304,22 +824,60 @@ int ieee80211_tdls_oper(struct wiphy *wiphy, struct net_device *dev, sta = sta_info_get(sdata, peer); if (!sta) { rcu_read_unlock(); - return -ENOLINK; + ret = -ENOLINK; + break; } set_sta_flag(sta, WLAN_STA_TDLS_PEER_AUTH); rcu_read_unlock(); + + WARN_ON_ONCE(is_zero_ether_addr(sdata->u.mgd.tdls_peer) || + !ether_addr_equal(sdata->u.mgd.tdls_peer, peer)); + ret = 0; break; case NL80211_TDLS_DISABLE_LINK: - return sta_info_destroy_addr(sdata, peer); - case NL80211_TDLS_TEARDOWN: - case NL80211_TDLS_SETUP: - case NL80211_TDLS_DISCOVERY_REQ: - /* We don't support in-driver setup/teardown/discovery */ - return -ENOTSUPP; + /* + * The teardown message in ieee80211_tdls_mgmt_teardown() was + * created while the queues were stopped, so it might still be + * pending. Before flushing the queues we need to be sure the + * message is handled by the tasklet handling pending messages, + * otherwise we might start destroying the station before + * sending the teardown packet. + * Note that this only forces the tasklet to flush pendings - + * not to stop the tasklet from rescheduling itself. + */ + tasklet_kill(&local->tx_pending_tasklet); + /* flush a potentially queued teardown packet */ + ieee80211_flush_queues(local, sdata); + + ret = sta_info_destroy_addr(sdata, peer); + break; default: - return -ENOTSUPP; + ret = -ENOTSUPP; + break; } - return 0; + if (ret == 0 && ether_addr_equal(sdata->u.mgd.tdls_peer, peer)) { + cancel_delayed_work(&sdata->u.mgd.tdls_peer_del_work); + eth_zero_addr(sdata->u.mgd.tdls_peer); + } + + mutex_unlock(&local->mtx); + return ret; +} + +void ieee80211_tdls_oper_request(struct ieee80211_vif *vif, const u8 *peer, + enum nl80211_tdls_operation oper, + u16 reason_code, gfp_t gfp) +{ + struct ieee80211_sub_if_data *sdata = vif_to_sdata(vif); + + if (vif->type != NL80211_IFTYPE_STATION || !vif->bss_conf.assoc) { + sdata_err(sdata, "Discarding TDLS oper %d - not STA or disconnected\n", + oper); + return; + } + + cfg80211_tdls_oper_request(sdata->dev, peer, oper, reason_code, gfp); } +EXPORT_SYMBOL(ieee80211_tdls_oper_request); diff --git a/net/mac80211/trace.h b/net/mac80211/trace.h index cfe1a0688b5c..02ac535d1274 100644 --- a/net/mac80211/trace.h +++ b/net/mac80211/trace.h @@ -1330,6 +1330,13 @@ DEFINE_EVENT(local_sdata_evt, drv_mgd_prepare_tx, TP_ARGS(local, sdata) ); +DEFINE_EVENT(local_sdata_evt, drv_mgd_protect_tdls_discover, + TP_PROTO(struct ieee80211_local *local, + struct ieee80211_sub_if_data *sdata), + + TP_ARGS(local, sdata) +); + DECLARE_EVENT_CLASS(local_chanctx, TP_PROTO(struct ieee80211_local *local, struct ieee80211_chanctx *ctx), diff --git a/net/mac80211/tx.c b/net/mac80211/tx.c index 1a252c606ad0..464106c023d8 100644 --- a/net/mac80211/tx.c +++ b/net/mac80211/tx.c @@ -250,7 +250,8 @@ ieee80211_tx_h_dynamic_ps(struct ieee80211_tx_data *tx) if (local->hw.conf.flags & IEEE80211_CONF_PS) { ieee80211_stop_queues_by_reason(&local->hw, IEEE80211_MAX_QUEUE_MAP, - IEEE80211_QUEUE_STOP_REASON_PS); + IEEE80211_QUEUE_STOP_REASON_PS, + false); ifmgd->flags &= ~IEEE80211_STA_NULLFUNC_ACKED; ieee80211_queue_work(&local->hw, &local->dynamic_ps_disable_work); @@ -473,7 +474,8 @@ ieee80211_tx_h_unicast_ps_buf(struct ieee80211_tx_data *tx) return TX_CONTINUE; if (unlikely((test_sta_flag(sta, WLAN_STA_PS_STA) || - test_sta_flag(sta, WLAN_STA_PS_DRIVER)) && + test_sta_flag(sta, WLAN_STA_PS_DRIVER) || + test_sta_flag(sta, WLAN_STA_PS_DELIVER)) && !(info->flags & IEEE80211_TX_CTL_NO_PS_BUFFER))) { int ac = skb_get_queue_mapping(tx->skb); @@ -496,7 +498,8 @@ ieee80211_tx_h_unicast_ps_buf(struct ieee80211_tx_data *tx) * ahead and Tx the packet. */ if (!test_sta_flag(sta, WLAN_STA_PS_STA) && - !test_sta_flag(sta, WLAN_STA_PS_DRIVER)) { + !test_sta_flag(sta, WLAN_STA_PS_DRIVER) && + !test_sta_flag(sta, WLAN_STA_PS_DELIVER)) { spin_unlock(&sta->ps_lock); return TX_CONTINUE; } @@ -1618,12 +1621,12 @@ netdev_tx_t ieee80211_monitor_start_xmit(struct sk_buff *skb, { struct ieee80211_local *local = wdev_priv(dev->ieee80211_ptr); struct ieee80211_chanctx_conf *chanctx_conf; - struct ieee80211_channel *chan; struct ieee80211_radiotap_header *prthdr = (struct ieee80211_radiotap_header *)skb->data; struct ieee80211_tx_info *info = IEEE80211_SKB_CB(skb); struct ieee80211_hdr *hdr; struct ieee80211_sub_if_data *tmp_sdata, *sdata; + struct cfg80211_chan_def *chandef; u16 len_rthdr; int hdrlen; @@ -1721,9 +1724,9 @@ netdev_tx_t ieee80211_monitor_start_xmit(struct sk_buff *skb, } if (chanctx_conf) - chan = chanctx_conf->def.chan; + chandef = &chanctx_conf->def; else if (!local->use_chanctx) - chan = local->_oper_chandef.chan; + chandef = &local->_oper_chandef; else goto fail_rcu; @@ -1743,10 +1746,11 @@ netdev_tx_t ieee80211_monitor_start_xmit(struct sk_buff *skb, * radar detection by itself. We can do that later by adding a * monitor flag interfaces used for AP support. */ - if ((chan->flags & (IEEE80211_CHAN_NO_IR | IEEE80211_CHAN_RADAR))) + if (!cfg80211_reg_can_beacon(local->hw.wiphy, chandef, + sdata->vif.type)) goto fail_rcu; - ieee80211_xmit(sdata, skb, chan->band); + ieee80211_xmit(sdata, skb, chandef->chan->band); rcu_read_unlock(); return NETDEV_TX_OK; @@ -1767,15 +1771,12 @@ fail: static void ieee80211_tx_latency_start_msrmnt(struct ieee80211_local *local, struct sk_buff *skb) { - struct timespec skb_arv; struct ieee80211_tx_latency_bin_ranges *tx_latency; tx_latency = rcu_dereference(local->tx_latency); if (!tx_latency) return; - - ktime_get_ts(&skb_arv); - skb->tstamp = ktime_set(skb_arv.tv_sec, skb_arv.tv_nsec); + skb->tstamp = ktime_get(); } /** @@ -1810,7 +1811,7 @@ netdev_tx_t ieee80211_subif_start_xmit(struct sk_buff *skb, int nh_pos, h_pos; struct sta_info *sta = NULL; bool wme_sta = false, authorized = false, tdls_auth = false; - bool tdls_direct = false; + bool tdls_peer = false, tdls_setup_frame = false; bool multicast; u32 info_flags = 0; u16 info_id = 0; @@ -1952,34 +1953,35 @@ netdev_tx_t ieee80211_subif_start_xmit(struct sk_buff *skb, #endif case NL80211_IFTYPE_STATION: if (sdata->wdev.wiphy->flags & WIPHY_FLAG_SUPPORTS_TDLS) { - bool tdls_peer = false; - sta = sta_info_get(sdata, skb->data); if (sta) { authorized = test_sta_flag(sta, WLAN_STA_AUTHORIZED); wme_sta = test_sta_flag(sta, WLAN_STA_WME); tdls_peer = test_sta_flag(sta, - WLAN_STA_TDLS_PEER); + WLAN_STA_TDLS_PEER); tdls_auth = test_sta_flag(sta, WLAN_STA_TDLS_PEER_AUTH); } - /* - * If the TDLS link is enabled, send everything - * directly. Otherwise, allow TDLS setup frames - * to be transmitted indirectly. - */ - tdls_direct = tdls_peer && (tdls_auth || - !(ethertype == ETH_P_TDLS && skb->len > 14 && - skb->data[14] == WLAN_TDLS_SNAP_RFTYPE)); + if (tdls_peer) + tdls_setup_frame = + ethertype == ETH_P_TDLS && + skb->len > 14 && + skb->data[14] == WLAN_TDLS_SNAP_RFTYPE; } - if (tdls_direct) { - /* link during setup - throw out frames to peer */ - if (!tdls_auth) - goto fail_rcu; + /* + * TDLS link during setup - throw out frames to peer. We allow + * TDLS-setup frames to unauthorized peers for the special case + * of a link teardown after a TDLS sta is removed due to being + * unreachable. + */ + if (tdls_peer && !tdls_auth && !tdls_setup_frame) + goto fail_rcu; + /* send direct packets to authorized TDLS peers */ + if (tdls_peer && tdls_auth) { /* DA SA BSSID */ memcpy(hdr.addr1, skb->data, ETH_ALEN); memcpy(hdr.addr2, skb->data + ETH_ALEN, ETH_ALEN); @@ -2423,7 +2425,7 @@ static void ieee80211_set_csa(struct ieee80211_sub_if_data *sdata, u8 *beacon_data; size_t beacon_data_len; int i; - u8 count = sdata->csa_current_counter; + u8 count = beacon->csa_current_counter; switch (sdata->vif.type) { case NL80211_IFTYPE_AP: @@ -2442,46 +2444,53 @@ static void ieee80211_set_csa(struct ieee80211_sub_if_data *sdata, return; } + rcu_read_lock(); for (i = 0; i < IEEE80211_MAX_CSA_COUNTERS_NUM; ++i) { - u16 counter_offset_beacon = - sdata->csa_counter_offset_beacon[i]; - u16 counter_offset_presp = sdata->csa_counter_offset_presp[i]; + resp = rcu_dereference(sdata->u.ap.probe_resp); - if (counter_offset_beacon) { - if (WARN_ON(counter_offset_beacon >= beacon_data_len)) - return; - - beacon_data[counter_offset_beacon] = count; - } - - if (sdata->vif.type == NL80211_IFTYPE_AP && - counter_offset_presp) { - rcu_read_lock(); - resp = rcu_dereference(sdata->u.ap.probe_resp); - - /* If nl80211 accepted the offset, this should - * not happen. - */ - if (WARN_ON(!resp)) { + if (beacon->csa_counter_offsets[i]) { + if (WARN_ON_ONCE(beacon->csa_counter_offsets[i] >= + beacon_data_len)) { rcu_read_unlock(); return; } - resp->data[counter_offset_presp] = count; - rcu_read_unlock(); + + beacon_data[beacon->csa_counter_offsets[i]] = count; } + + if (sdata->vif.type == NL80211_IFTYPE_AP && resp) + resp->data[resp->csa_counter_offsets[i]] = count; } + rcu_read_unlock(); } u8 ieee80211_csa_update_counter(struct ieee80211_vif *vif) { struct ieee80211_sub_if_data *sdata = vif_to_sdata(vif); + struct beacon_data *beacon = NULL; + u8 count = 0; + + rcu_read_lock(); - sdata->csa_current_counter--; + if (sdata->vif.type == NL80211_IFTYPE_AP) + beacon = rcu_dereference(sdata->u.ap.beacon); + else if (sdata->vif.type == NL80211_IFTYPE_ADHOC) + beacon = rcu_dereference(sdata->u.ibss.presp); + else if (ieee80211_vif_is_mesh(&sdata->vif)) + beacon = rcu_dereference(sdata->u.mesh.beacon); + + if (!beacon) + goto unlock; + + beacon->csa_current_counter--; /* the counter should never reach 0 */ - WARN_ON(!sdata->csa_current_counter); + WARN_ON_ONCE(!beacon->csa_current_counter); + count = beacon->csa_current_counter; - return sdata->csa_current_counter; +unlock: + rcu_read_unlock(); + return count; } EXPORT_SYMBOL(ieee80211_csa_update_counter); @@ -2491,7 +2500,6 @@ bool ieee80211_csa_is_complete(struct ieee80211_vif *vif) struct beacon_data *beacon = NULL; u8 *beacon_data; size_t beacon_data_len; - int counter_beacon = sdata->csa_counter_offset_beacon[0]; int ret = false; if (!ieee80211_sdata_running(sdata)) @@ -2529,10 +2537,13 @@ bool ieee80211_csa_is_complete(struct ieee80211_vif *vif) goto out; } - if (WARN_ON(counter_beacon > beacon_data_len)) + if (!beacon->csa_counter_offsets[0]) goto out; - if (beacon_data[counter_beacon] == 1) + if (WARN_ON_ONCE(beacon->csa_counter_offsets[0] > beacon_data_len)) + goto out; + + if (beacon_data[beacon->csa_counter_offsets[0]] == 1) ret = true; out: rcu_read_unlock(); @@ -2548,6 +2559,7 @@ __ieee80211_beacon_get(struct ieee80211_hw *hw, bool is_template) { struct ieee80211_local *local = hw_to_local(hw); + struct beacon_data *beacon = NULL; struct sk_buff *skb = NULL; struct ieee80211_tx_info *info; struct ieee80211_sub_if_data *sdata = NULL; @@ -2569,10 +2581,10 @@ __ieee80211_beacon_get(struct ieee80211_hw *hw, if (sdata->vif.type == NL80211_IFTYPE_AP) { struct ieee80211_if_ap *ap = &sdata->u.ap; - struct beacon_data *beacon = rcu_dereference(ap->beacon); + beacon = rcu_dereference(ap->beacon); if (beacon) { - if (sdata->vif.csa_active) { + if (beacon->csa_counter_offsets[0]) { if (!is_template) ieee80211_csa_update_counter(vif); @@ -2613,37 +2625,37 @@ __ieee80211_beacon_get(struct ieee80211_hw *hw, } else if (sdata->vif.type == NL80211_IFTYPE_ADHOC) { struct ieee80211_if_ibss *ifibss = &sdata->u.ibss; struct ieee80211_hdr *hdr; - struct beacon_data *presp = rcu_dereference(ifibss->presp); - if (!presp) + beacon = rcu_dereference(ifibss->presp); + if (!beacon) goto out; - if (sdata->vif.csa_active) { + if (beacon->csa_counter_offsets[0]) { if (!is_template) ieee80211_csa_update_counter(vif); - ieee80211_set_csa(sdata, presp); + ieee80211_set_csa(sdata, beacon); } - skb = dev_alloc_skb(local->tx_headroom + presp->head_len + + skb = dev_alloc_skb(local->tx_headroom + beacon->head_len + local->hw.extra_beacon_tailroom); if (!skb) goto out; skb_reserve(skb, local->tx_headroom); - memcpy(skb_put(skb, presp->head_len), presp->head, - presp->head_len); + memcpy(skb_put(skb, beacon->head_len), beacon->head, + beacon->head_len); hdr = (struct ieee80211_hdr *) skb->data; hdr->frame_control = cpu_to_le16(IEEE80211_FTYPE_MGMT | IEEE80211_STYPE_BEACON); } else if (ieee80211_vif_is_mesh(&sdata->vif)) { struct ieee80211_if_mesh *ifmsh = &sdata->u.mesh; - struct beacon_data *bcn = rcu_dereference(ifmsh->beacon); - if (!bcn) + beacon = rcu_dereference(ifmsh->beacon); + if (!beacon) goto out; - if (sdata->vif.csa_active) { + if (beacon->csa_counter_offsets[0]) { if (!is_template) /* TODO: For mesh csa_counter is in TU, so * decrementing it by one isn't correct, but @@ -2652,40 +2664,42 @@ __ieee80211_beacon_get(struct ieee80211_hw *hw, */ ieee80211_csa_update_counter(vif); - ieee80211_set_csa(sdata, bcn); + ieee80211_set_csa(sdata, beacon); } if (ifmsh->sync_ops) - ifmsh->sync_ops->adjust_tbtt(sdata, bcn); + ifmsh->sync_ops->adjust_tbtt(sdata, beacon); skb = dev_alloc_skb(local->tx_headroom + - bcn->head_len + + beacon->head_len + 256 + /* TIM IE */ - bcn->tail_len + + beacon->tail_len + local->hw.extra_beacon_tailroom); if (!skb) goto out; skb_reserve(skb, local->tx_headroom); - memcpy(skb_put(skb, bcn->head_len), bcn->head, bcn->head_len); + memcpy(skb_put(skb, beacon->head_len), beacon->head, + beacon->head_len); ieee80211_beacon_add_tim(sdata, &ifmsh->ps, skb, is_template); if (offs) { - offs->tim_offset = bcn->head_len; - offs->tim_length = skb->len - bcn->head_len; + offs->tim_offset = beacon->head_len; + offs->tim_length = skb->len - beacon->head_len; } - memcpy(skb_put(skb, bcn->tail_len), bcn->tail, bcn->tail_len); + memcpy(skb_put(skb, beacon->tail_len), beacon->tail, + beacon->tail_len); } else { WARN_ON(1); goto out; } /* CSA offsets */ - if (offs) { + if (offs && beacon) { int i; for (i = 0; i < IEEE80211_MAX_CSA_COUNTERS_NUM; i++) { - u16 csa_off = sdata->csa_counter_offset_beacon[i]; + u16 csa_off = beacon->csa_counter_offsets[i]; if (!csa_off) continue; diff --git a/net/mac80211/util.c b/net/mac80211/util.c index a6cda52ed920..725af7a468d2 100644 --- a/net/mac80211/util.c +++ b/net/mac80211/util.c @@ -317,7 +317,8 @@ void ieee80211_propagate_queue_wake(struct ieee80211_local *local, int queue) } static void __ieee80211_wake_queue(struct ieee80211_hw *hw, int queue, - enum queue_stop_reason reason) + enum queue_stop_reason reason, + bool refcounted) { struct ieee80211_local *local = hw_to_local(hw); @@ -329,7 +330,13 @@ static void __ieee80211_wake_queue(struct ieee80211_hw *hw, int queue, if (!test_bit(reason, &local->queue_stop_reasons[queue])) return; - __clear_bit(reason, &local->queue_stop_reasons[queue]); + if (!refcounted) + local->q_stop_reasons[queue][reason] = 0; + else + local->q_stop_reasons[queue][reason]--; + + if (local->q_stop_reasons[queue][reason] == 0) + __clear_bit(reason, &local->queue_stop_reasons[queue]); if (local->queue_stop_reasons[queue] != 0) /* someone still has this queue stopped */ @@ -344,25 +351,28 @@ static void __ieee80211_wake_queue(struct ieee80211_hw *hw, int queue, } void ieee80211_wake_queue_by_reason(struct ieee80211_hw *hw, int queue, - enum queue_stop_reason reason) + enum queue_stop_reason reason, + bool refcounted) { struct ieee80211_local *local = hw_to_local(hw); unsigned long flags; spin_lock_irqsave(&local->queue_stop_reason_lock, flags); - __ieee80211_wake_queue(hw, queue, reason); + __ieee80211_wake_queue(hw, queue, reason, refcounted); spin_unlock_irqrestore(&local->queue_stop_reason_lock, flags); } void ieee80211_wake_queue(struct ieee80211_hw *hw, int queue) { ieee80211_wake_queue_by_reason(hw, queue, - IEEE80211_QUEUE_STOP_REASON_DRIVER); + IEEE80211_QUEUE_STOP_REASON_DRIVER, + false); } EXPORT_SYMBOL(ieee80211_wake_queue); static void __ieee80211_stop_queue(struct ieee80211_hw *hw, int queue, - enum queue_stop_reason reason) + enum queue_stop_reason reason, + bool refcounted) { struct ieee80211_local *local = hw_to_local(hw); struct ieee80211_sub_if_data *sdata; @@ -373,10 +383,13 @@ static void __ieee80211_stop_queue(struct ieee80211_hw *hw, int queue, if (WARN_ON(queue >= hw->queues)) return; - if (test_bit(reason, &local->queue_stop_reasons[queue])) - return; + if (!refcounted) + local->q_stop_reasons[queue][reason] = 1; + else + local->q_stop_reasons[queue][reason]++; - __set_bit(reason, &local->queue_stop_reasons[queue]); + if (__test_and_set_bit(reason, &local->queue_stop_reasons[queue])) + return; if (local->hw.queues < IEEE80211_NUM_ACS) n_acs = 1; @@ -398,20 +411,22 @@ static void __ieee80211_stop_queue(struct ieee80211_hw *hw, int queue, } void ieee80211_stop_queue_by_reason(struct ieee80211_hw *hw, int queue, - enum queue_stop_reason reason) + enum queue_stop_reason reason, + bool refcounted) { struct ieee80211_local *local = hw_to_local(hw); unsigned long flags; spin_lock_irqsave(&local->queue_stop_reason_lock, flags); - __ieee80211_stop_queue(hw, queue, reason); + __ieee80211_stop_queue(hw, queue, reason, refcounted); spin_unlock_irqrestore(&local->queue_stop_reason_lock, flags); } void ieee80211_stop_queue(struct ieee80211_hw *hw, int queue) { ieee80211_stop_queue_by_reason(hw, queue, - IEEE80211_QUEUE_STOP_REASON_DRIVER); + IEEE80211_QUEUE_STOP_REASON_DRIVER, + false); } EXPORT_SYMBOL(ieee80211_stop_queue); @@ -429,9 +444,11 @@ void ieee80211_add_pending_skb(struct ieee80211_local *local, } spin_lock_irqsave(&local->queue_stop_reason_lock, flags); - __ieee80211_stop_queue(hw, queue, IEEE80211_QUEUE_STOP_REASON_SKB_ADD); + __ieee80211_stop_queue(hw, queue, IEEE80211_QUEUE_STOP_REASON_SKB_ADD, + false); __skb_queue_tail(&local->pending[queue], skb); - __ieee80211_wake_queue(hw, queue, IEEE80211_QUEUE_STOP_REASON_SKB_ADD); + __ieee80211_wake_queue(hw, queue, IEEE80211_QUEUE_STOP_REASON_SKB_ADD, + false); spin_unlock_irqrestore(&local->queue_stop_reason_lock, flags); } @@ -455,20 +472,23 @@ void ieee80211_add_pending_skbs(struct ieee80211_local *local, queue = info->hw_queue; __ieee80211_stop_queue(hw, queue, - IEEE80211_QUEUE_STOP_REASON_SKB_ADD); + IEEE80211_QUEUE_STOP_REASON_SKB_ADD, + false); __skb_queue_tail(&local->pending[queue], skb); } for (i = 0; i < hw->queues; i++) __ieee80211_wake_queue(hw, i, - IEEE80211_QUEUE_STOP_REASON_SKB_ADD); + IEEE80211_QUEUE_STOP_REASON_SKB_ADD, + false); spin_unlock_irqrestore(&local->queue_stop_reason_lock, flags); } void ieee80211_stop_queues_by_reason(struct ieee80211_hw *hw, unsigned long queues, - enum queue_stop_reason reason) + enum queue_stop_reason reason, + bool refcounted) { struct ieee80211_local *local = hw_to_local(hw); unsigned long flags; @@ -477,7 +497,7 @@ void ieee80211_stop_queues_by_reason(struct ieee80211_hw *hw, spin_lock_irqsave(&local->queue_stop_reason_lock, flags); for_each_set_bit(i, &queues, hw->queues) - __ieee80211_stop_queue(hw, i, reason); + __ieee80211_stop_queue(hw, i, reason, refcounted); spin_unlock_irqrestore(&local->queue_stop_reason_lock, flags); } @@ -485,7 +505,8 @@ void ieee80211_stop_queues_by_reason(struct ieee80211_hw *hw, void ieee80211_stop_queues(struct ieee80211_hw *hw) { ieee80211_stop_queues_by_reason(hw, IEEE80211_MAX_QUEUE_MAP, - IEEE80211_QUEUE_STOP_REASON_DRIVER); + IEEE80211_QUEUE_STOP_REASON_DRIVER, + false); } EXPORT_SYMBOL(ieee80211_stop_queues); @@ -508,7 +529,8 @@ EXPORT_SYMBOL(ieee80211_queue_stopped); void ieee80211_wake_queues_by_reason(struct ieee80211_hw *hw, unsigned long queues, - enum queue_stop_reason reason) + enum queue_stop_reason reason, + bool refcounted) { struct ieee80211_local *local = hw_to_local(hw); unsigned long flags; @@ -517,7 +539,7 @@ void ieee80211_wake_queues_by_reason(struct ieee80211_hw *hw, spin_lock_irqsave(&local->queue_stop_reason_lock, flags); for_each_set_bit(i, &queues, hw->queues) - __ieee80211_wake_queue(hw, i, reason); + __ieee80211_wake_queue(hw, i, reason, refcounted); spin_unlock_irqrestore(&local->queue_stop_reason_lock, flags); } @@ -525,17 +547,16 @@ void ieee80211_wake_queues_by_reason(struct ieee80211_hw *hw, void ieee80211_wake_queues(struct ieee80211_hw *hw) { ieee80211_wake_queues_by_reason(hw, IEEE80211_MAX_QUEUE_MAP, - IEEE80211_QUEUE_STOP_REASON_DRIVER); + IEEE80211_QUEUE_STOP_REASON_DRIVER, + false); } EXPORT_SYMBOL(ieee80211_wake_queues); -void ieee80211_flush_queues(struct ieee80211_local *local, - struct ieee80211_sub_if_data *sdata) +static unsigned int +ieee80211_get_vif_queues(struct ieee80211_local *local, + struct ieee80211_sub_if_data *sdata) { - u32 queues; - - if (!local->ops->flush) - return; + unsigned int queues; if (sdata && local->hw.flags & IEEE80211_HW_QUEUE_CONTROL) { int ac; @@ -551,13 +572,46 @@ void ieee80211_flush_queues(struct ieee80211_local *local, queues = BIT(local->hw.queues) - 1; } - ieee80211_stop_queues_by_reason(&local->hw, IEEE80211_MAX_QUEUE_MAP, - IEEE80211_QUEUE_STOP_REASON_FLUSH); + return queues; +} + +void ieee80211_flush_queues(struct ieee80211_local *local, + struct ieee80211_sub_if_data *sdata) +{ + unsigned int queues; + + if (!local->ops->flush) + return; + + queues = ieee80211_get_vif_queues(local, sdata); + + ieee80211_stop_queues_by_reason(&local->hw, queues, + IEEE80211_QUEUE_STOP_REASON_FLUSH, + false); drv_flush(local, sdata, queues, false); - ieee80211_wake_queues_by_reason(&local->hw, IEEE80211_MAX_QUEUE_MAP, - IEEE80211_QUEUE_STOP_REASON_FLUSH); + ieee80211_wake_queues_by_reason(&local->hw, queues, + IEEE80211_QUEUE_STOP_REASON_FLUSH, + false); +} + +void ieee80211_stop_vif_queues(struct ieee80211_local *local, + struct ieee80211_sub_if_data *sdata, + enum queue_stop_reason reason) +{ + ieee80211_stop_queues_by_reason(&local->hw, + ieee80211_get_vif_queues(local, sdata), + reason, true); +} + +void ieee80211_wake_vif_queues(struct ieee80211_local *local, + struct ieee80211_sub_if_data *sdata, + enum queue_stop_reason reason) +{ + ieee80211_wake_queues_by_reason(&local->hw, + ieee80211_get_vif_queues(local, sdata), + reason, true); } static void __iterate_active_interfaces(struct ieee80211_local *local, @@ -1166,14 +1220,17 @@ void ieee80211_send_deauth_disassoc(struct ieee80211_sub_if_data *sdata, } } -int ieee80211_build_preq_ies(struct ieee80211_local *local, u8 *buffer, - size_t buffer_len, const u8 *ie, size_t ie_len, - enum ieee80211_band band, u32 rate_mask, - struct cfg80211_chan_def *chandef) +static int ieee80211_build_preq_ies_band(struct ieee80211_local *local, + u8 *buffer, size_t buffer_len, + const u8 *ie, size_t ie_len, + enum ieee80211_band band, + u32 rate_mask, + struct cfg80211_chan_def *chandef, + size_t *offset) { struct ieee80211_supported_band *sband; u8 *pos = buffer, *end = buffer + buffer_len; - size_t offset = 0, noffset; + size_t noffset; int supp_rates_len, i; u8 rates[32]; int num_rates; @@ -1181,6 +1238,8 @@ int ieee80211_build_preq_ies(struct ieee80211_local *local, u8 *buffer, int shift; u32 rate_flags; + *offset = 0; + sband = local->hw.wiphy->bands[band]; if (WARN_ON_ONCE(!sband)) return 0; @@ -1219,12 +1278,12 @@ int ieee80211_build_preq_ies(struct ieee80211_local *local, u8 *buffer, noffset = ieee80211_ie_split(ie, ie_len, before_extrates, ARRAY_SIZE(before_extrates), - offset); - if (end - pos < noffset - offset) + *offset); + if (end - pos < noffset - *offset) goto out_err; - memcpy(pos, ie + offset, noffset - offset); - pos += noffset - offset; - offset = noffset; + memcpy(pos, ie + *offset, noffset - *offset); + pos += noffset - *offset; + *offset = noffset; } ext_rates_len = num_rates - supp_rates_len; @@ -1258,12 +1317,12 @@ int ieee80211_build_preq_ies(struct ieee80211_local *local, u8 *buffer, }; noffset = ieee80211_ie_split(ie, ie_len, before_ht, ARRAY_SIZE(before_ht), - offset); - if (end - pos < noffset - offset) + *offset); + if (end - pos < noffset - *offset) goto out_err; - memcpy(pos, ie + offset, noffset - offset); - pos += noffset - offset; - offset = noffset; + memcpy(pos, ie + *offset, noffset - *offset); + pos += noffset - *offset; + *offset = noffset; } if (sband->ht_cap.ht_supported) { @@ -1298,12 +1357,12 @@ int ieee80211_build_preq_ies(struct ieee80211_local *local, u8 *buffer, }; noffset = ieee80211_ie_split(ie, ie_len, before_vht, ARRAY_SIZE(before_vht), - offset); - if (end - pos < noffset - offset) + *offset); + if (end - pos < noffset - *offset) goto out_err; - memcpy(pos, ie + offset, noffset - offset); - pos += noffset - offset; - offset = noffset; + memcpy(pos, ie + *offset, noffset - *offset); + pos += noffset - *offset; + *offset = noffset; } if (sband->vht_cap.vht_supported) { @@ -1313,21 +1372,54 @@ int ieee80211_build_preq_ies(struct ieee80211_local *local, u8 *buffer, sband->vht_cap.cap); } - /* add any remaining custom IEs */ - if (ie && ie_len) { - noffset = ie_len; - if (end - pos < noffset - offset) - goto out_err; - memcpy(pos, ie + offset, noffset - offset); - pos += noffset - offset; - } - return pos - buffer; out_err: WARN_ONCE(1, "not enough space for preq IEs\n"); return pos - buffer; } +int ieee80211_build_preq_ies(struct ieee80211_local *local, u8 *buffer, + size_t buffer_len, + struct ieee80211_scan_ies *ie_desc, + const u8 *ie, size_t ie_len, + u8 bands_used, u32 *rate_masks, + struct cfg80211_chan_def *chandef) +{ + size_t pos = 0, old_pos = 0, custom_ie_offset = 0; + int i; + + memset(ie_desc, 0, sizeof(*ie_desc)); + + for (i = 0; i < IEEE80211_NUM_BANDS; i++) { + if (bands_used & BIT(i)) { + pos += ieee80211_build_preq_ies_band(local, + buffer + pos, + buffer_len - pos, + ie, ie_len, i, + rate_masks[i], + chandef, + &custom_ie_offset); + ie_desc->ies[i] = buffer + old_pos; + ie_desc->len[i] = pos - old_pos; + old_pos = pos; + } + } + + /* add any remaining custom IEs */ + if (ie && ie_len) { + if (WARN_ONCE(buffer_len - pos < ie_len - custom_ie_offset, + "not enough space for preq custom IEs\n")) + return pos; + memcpy(buffer + pos, ie + custom_ie_offset, + ie_len - custom_ie_offset); + ie_desc->common_ies = buffer + pos; + ie_desc->common_ie_len = ie_len - custom_ie_offset; + pos += ie_len - custom_ie_offset; + } + + return pos; +}; + struct sk_buff *ieee80211_build_probe_req(struct ieee80211_sub_if_data *sdata, u8 *dst, u32 ratemask, struct ieee80211_channel *chan, @@ -1340,6 +1432,8 @@ struct sk_buff *ieee80211_build_probe_req(struct ieee80211_sub_if_data *sdata, struct sk_buff *skb; struct ieee80211_mgmt *mgmt; int ies_len; + u32 rate_masks[IEEE80211_NUM_BANDS] = {}; + struct ieee80211_scan_ies dummy_ie_desc; /* * Do not send DS Channel parameter for directed probe requests @@ -1357,10 +1451,11 @@ struct sk_buff *ieee80211_build_probe_req(struct ieee80211_sub_if_data *sdata, if (!skb) return NULL; + rate_masks[chan->band] = ratemask; ies_len = ieee80211_build_preq_ies(local, skb_tail_pointer(skb), - skb_tailroom(skb), - ie, ie_len, chan->band, - ratemask, &chandef); + skb_tailroom(skb), &dummy_ie_desc, + ie, ie_len, BIT(chan->band), + rate_masks, &chandef); skb_put(skb, ies_len); if (dst) { @@ -1604,7 +1699,9 @@ int ieee80211_reconfig(struct ieee80211_local *local) if (local->use_chanctx) { mutex_lock(&local->chanctx_mtx); list_for_each_entry(ctx, &local->chanctx_list, list) - WARN_ON(drv_add_chanctx(local, ctx)); + if (ctx->replace_state != + IEEE80211_CHANCTX_REPLACES_OTHER) + WARN_ON(drv_add_chanctx(local, ctx)); mutex_unlock(&local->chanctx_mtx); list_for_each_entry(sdata, &local->interfaces, list) { @@ -1798,7 +1895,8 @@ int ieee80211_reconfig(struct ieee80211_local *local) } ieee80211_wake_queues_by_reason(hw, IEEE80211_MAX_QUEUE_MAP, - IEEE80211_QUEUE_STOP_REASON_SUSPEND); + IEEE80211_QUEUE_STOP_REASON_SUSPEND, + false); /* * Reconfigure sched scan if it was interrupted by FW restart or @@ -2836,6 +2934,35 @@ void ieee80211_recalc_dtim(struct ieee80211_local *local, ps->dtim_count = dtim_count; } +static u8 ieee80211_chanctx_radar_detect(struct ieee80211_local *local, + struct ieee80211_chanctx *ctx) +{ + struct ieee80211_sub_if_data *sdata; + u8 radar_detect = 0; + + lockdep_assert_held(&local->chanctx_mtx); + + if (WARN_ON(ctx->replace_state == IEEE80211_CHANCTX_WILL_BE_REPLACED)) + return 0; + + list_for_each_entry(sdata, &ctx->reserved_vifs, reserved_chanctx_list) + if (sdata->reserved_radar_required) + radar_detect |= BIT(sdata->reserved_chandef.width); + + /* + * An in-place reservation context should not have any assigned vifs + * until it replaces the other context. + */ + WARN_ON(ctx->replace_state == IEEE80211_CHANCTX_REPLACES_OTHER && + !list_empty(&ctx->assigned_vifs)); + + list_for_each_entry(sdata, &ctx->assigned_vifs, assigned_chanctx_list) + if (sdata->radar_required) + radar_detect |= BIT(sdata->vif.bss_conf.chandef.width); + + return radar_detect; +} + int ieee80211_check_combinations(struct ieee80211_sub_if_data *sdata, const struct cfg80211_chan_def *chandef, enum ieee80211_chanctx_mode chanmode, @@ -2877,8 +3004,9 @@ int ieee80211_check_combinations(struct ieee80211_sub_if_data *sdata, num[iftype] = 1; list_for_each_entry(ctx, &local->chanctx_list, list) { - if (ctx->conf.radar_enabled) - radar_detect |= BIT(ctx->conf.def.width); + if (ctx->replace_state == IEEE80211_CHANCTX_WILL_BE_REPLACED) + continue; + radar_detect |= ieee80211_chanctx_radar_detect(local, ctx); if (ctx->mode == IEEE80211_CHANCTX_EXCLUSIVE) { num_different_channels++; continue; @@ -2935,10 +3063,12 @@ int ieee80211_max_num_channels(struct ieee80211_local *local) lockdep_assert_held(&local->chanctx_mtx); list_for_each_entry(ctx, &local->chanctx_list, list) { + if (ctx->replace_state == IEEE80211_CHANCTX_WILL_BE_REPLACED) + continue; + num_different_channels++; - if (ctx->conf.radar_enabled) - radar_detect |= BIT(ctx->conf.def.width); + radar_detect |= ieee80211_chanctx_radar_detect(local, ctx); } list_for_each_entry_rcu(sdata, &local->interfaces, list) @@ -2953,3 +3083,18 @@ int ieee80211_max_num_channels(struct ieee80211_local *local) return max_num_different_channels; } + +u8 *ieee80211_add_wmm_info_ie(u8 *buf, u8 qosinfo) +{ + *buf++ = WLAN_EID_VENDOR_SPECIFIC; + *buf++ = 7; /* len */ + *buf++ = 0x00; /* Microsoft OUI 00:50:F2 */ + *buf++ = 0x50; + *buf++ = 0xf2; + *buf++ = 2; /* WME */ + *buf++ = 0; /* WME info */ + *buf++ = 1; /* WME ver */ + *buf++ = qosinfo; /* U-APSD no in use */ + + return buf; +} diff --git a/net/mac80211/vht.c b/net/mac80211/vht.c index 9265adfdabfc..671ce0d27a80 100644 --- a/net/mac80211/vht.c +++ b/net/mac80211/vht.c @@ -129,6 +129,10 @@ ieee80211_vht_cap_ie_to_sta_vht_cap(struct ieee80211_sub_if_data *sdata, if (!vht_cap_ie || !sband->vht_cap.vht_supported) return; + /* don't support VHT for TDLS peers for now */ + if (test_sta_flag(sta, WLAN_STA_TDLS_PEER)) + return; + /* * A VHT STA must support 40 MHz, but if we verify that here * then we break a few things - some APs (e.g. Netgear R6300v2 diff --git a/net/mac80211/wep.c b/net/mac80211/wep.c index 6ee2b5863572..9181fb6d6437 100644 --- a/net/mac80211/wep.c +++ b/net/mac80211/wep.c @@ -271,22 +271,6 @@ static int ieee80211_wep_decrypt(struct ieee80211_local *local, return ret; } - -static bool ieee80211_wep_is_weak_iv(struct sk_buff *skb, - struct ieee80211_key *key) -{ - struct ieee80211_hdr *hdr = (struct ieee80211_hdr *)skb->data; - unsigned int hdrlen; - u8 *ivpos; - u32 iv; - - hdrlen = ieee80211_hdrlen(hdr->frame_control); - ivpos = skb->data + hdrlen; - iv = (ivpos[0] << 16) | (ivpos[1] << 8) | ivpos[2]; - - return ieee80211_wep_weak_iv(iv, key->conf.keylen); -} - ieee80211_rx_result ieee80211_crypto_wep_decrypt(struct ieee80211_rx_data *rx) { @@ -301,16 +285,12 @@ ieee80211_crypto_wep_decrypt(struct ieee80211_rx_data *rx) if (!(status->flag & RX_FLAG_DECRYPTED)) { if (skb_linearize(rx->skb)) return RX_DROP_UNUSABLE; - if (rx->sta && ieee80211_wep_is_weak_iv(rx->skb, rx->key)) - rx->sta->wep_weak_iv_count++; if (ieee80211_wep_decrypt(rx->local, rx->skb, rx->key)) return RX_DROP_UNUSABLE; } else if (!(status->flag & RX_FLAG_IV_STRIPPED)) { if (!pskb_may_pull(rx->skb, ieee80211_hdrlen(fc) + IEEE80211_WEP_IV_LEN)) return RX_DROP_UNUSABLE; - if (rx->sta && ieee80211_wep_is_weak_iv(rx->skb, rx->key)) - rx->sta->wep_weak_iv_count++; ieee80211_wep_remove_iv(rx->local, rx->skb, rx->key); /* remove ICV */ if (pskb_trim(rx->skb, rx->skb->len - IEEE80211_WEP_ICV_LEN)) diff --git a/net/mac80211/wpa.c b/net/mac80211/wpa.c index 9b3dcc201145..f7d4ca4c46e0 100644 --- a/net/mac80211/wpa.c +++ b/net/mac80211/wpa.c @@ -811,7 +811,7 @@ ieee80211_crypto_hw_encrypt(struct ieee80211_tx_data *tx) ieee80211_rx_result ieee80211_crypto_hw_decrypt(struct ieee80211_rx_data *rx) { - if (rx->sta->cipher_scheme) + if (rx->sta && rx->sta->cipher_scheme) return ieee80211_crypto_cs_decrypt(rx); return RX_DROP_UNUSABLE; diff --git a/net/mac802154/ieee802154_dev.c b/net/mac802154/ieee802154_dev.c index 2cf66d885e68..b36b2b996578 100644 --- a/net/mac802154/ieee802154_dev.c +++ b/net/mac802154/ieee802154_dev.c @@ -143,6 +143,7 @@ static void mac802154_del_iface(struct wpan_phy *phy, struct net_device *dev) { struct mac802154_sub_if_data *sdata; + ASSERT_RTNL(); sdata = netdev_priv(dev); @@ -166,11 +167,13 @@ mac802154_add_iface(struct wpan_phy *phy, const char *name, int type) switch (type) { case IEEE802154_DEV_MONITOR: dev = alloc_netdev(sizeof(struct mac802154_sub_if_data), - name, mac802154_monitor_setup); + name, NET_NAME_UNKNOWN, + mac802154_monitor_setup); break; case IEEE802154_DEV_WPAN: dev = alloc_netdev(sizeof(struct mac802154_sub_if_data), - name, mac802154_wpan_setup); + name, NET_NAME_UNKNOWN, + mac802154_wpan_setup); break; default: dev = NULL; @@ -276,7 +279,8 @@ ieee802154_alloc_device(size_t priv_data_len, struct ieee802154_ops *ops) } priv = wpan_phy_priv(phy); - priv->hw.phy = priv->phy = phy; + priv->phy = phy; + priv->hw.phy = priv->phy; priv->hw.priv = (char *)priv + ALIGN(sizeof(*priv), NETDEV_ALIGN); priv->ops = ops; @@ -302,29 +306,61 @@ EXPORT_SYMBOL(ieee802154_free_device); int ieee802154_register_device(struct ieee802154_dev *dev) { struct mac802154_priv *priv = mac802154_to_priv(dev); - int rc = -ENOMEM; + int rc = -ENOSYS; + + if (dev->flags & IEEE802154_HW_TXPOWER) { + if (!priv->ops->set_txpower) + goto out; + + priv->phy->set_txpower = mac802154_set_txpower; + } + + if (dev->flags & IEEE802154_HW_LBT) { + if (!priv->ops->set_lbt) + goto out; + + priv->phy->set_lbt = mac802154_set_lbt; + } + + if (dev->flags & IEEE802154_HW_CCA_MODE) { + if (!priv->ops->set_cca_mode) + goto out; + + priv->phy->set_cca_mode = mac802154_set_cca_mode; + } + + if (dev->flags & IEEE802154_HW_CCA_ED_LEVEL) { + if (!priv->ops->set_cca_ed_level) + goto out; + + priv->phy->set_cca_ed_level = mac802154_set_cca_ed_level; + } + + if (dev->flags & IEEE802154_HW_CSMA_PARAMS) { + if (!priv->ops->set_csma_params) + goto out; + + priv->phy->set_csma_params = mac802154_set_csma_params; + } + + if (dev->flags & IEEE802154_HW_FRAME_RETRIES) { + if (!priv->ops->set_frame_retries) + goto out; + + priv->phy->set_frame_retries = mac802154_set_frame_retries; + } priv->dev_workqueue = create_singlethread_workqueue(wpan_phy_name(priv->phy)); - if (!priv->dev_workqueue) + if (!priv->dev_workqueue) { + rc = -ENOMEM; goto out; + } wpan_phy_set_dev(priv->phy, priv->hw.parent); priv->phy->add_iface = mac802154_add_iface; priv->phy->del_iface = mac802154_del_iface; - if (priv->ops->set_txpower) - priv->phy->set_txpower = mac802154_set_txpower; - if (priv->ops->set_lbt) - priv->phy->set_lbt = mac802154_set_lbt; - if (priv->ops->set_cca_mode) - priv->phy->set_cca_mode = mac802154_set_cca_mode; - if (priv->ops->set_cca_ed_level) - priv->phy->set_cca_ed_level = mac802154_set_cca_ed_level; - if (priv->ops->set_csma_params) - priv->phy->set_csma_params = mac802154_set_csma_params; - if (priv->ops->set_frame_retries) - priv->phy->set_frame_retries = mac802154_set_frame_retries; rc = wpan_phy_register(priv->phy); if (rc < 0) diff --git a/net/mac802154/llsec.c b/net/mac802154/llsec.c index 1456f73b02b9..457058142098 100644 --- a/net/mac802154/llsec.c +++ b/net/mac802154/llsec.c @@ -538,6 +538,7 @@ static int llsec_recover_addr(struct mac802154_llsec *sec, struct ieee802154_addr *addr) { __le16 caddr = sec->params.coord_shortaddr; + addr->pan_id = sec->params.pan_id; if (caddr == cpu_to_le16(IEEE802154_ADDR_BROADCAST)) { diff --git a/net/mac802154/mib.c b/net/mac802154/mib.c index 15aa2f2b03a7..868a040fd422 100644 --- a/net/mac802154/mib.c +++ b/net/mac802154/mib.c @@ -175,9 +175,9 @@ static void phy_chan_notify(struct work_struct *work) mutex_lock(&priv->hw->phy->pib_lock); res = hw->ops->set_channel(&hw->hw, priv->page, priv->chan); - if (res) + if (res) { pr_debug("set_channel failed\n"); - else { + } else { priv->hw->phy->current_channel = priv->chan; priv->hw->phy->current_page = priv->page; } @@ -210,8 +210,9 @@ void mac802154_dev_set_page_channel(struct net_device *dev, u8 page, u8 chan) INIT_WORK(&work->work, phy_chan_notify); work->dev = dev; queue_work(priv->hw->dev_workqueue, &work->work); - } else + } else { mutex_unlock(&priv->hw->phy->pib_lock); + } } diff --git a/net/mac802154/tx.c b/net/mac802154/tx.c index 6d1647399d4f..8124353646ae 100644 --- a/net/mac802154/tx.c +++ b/net/mac802154/tx.c @@ -98,6 +98,7 @@ netdev_tx_t mac802154_tx(struct mac802154_priv *priv, struct sk_buff *skb, if (!(priv->hw.flags & IEEE802154_HW_OMIT_CKSUM)) { u16 crc = crc_ccitt(0, skb->data, skb->len); u8 *data = skb_put(skb, 2); + data[0] = crc & 0xff; data[1] = crc >> 8; } diff --git a/net/netfilter/Kconfig b/net/netfilter/Kconfig index e9410d17619d..ad751fe2e82b 100644 --- a/net/netfilter/Kconfig +++ b/net/netfilter/Kconfig @@ -46,6 +46,9 @@ config NF_CONNTRACK To compile it as a module, choose M here. If unsure, say N. +config NF_LOG_COMMON + tristate + if NF_CONNTRACK config NF_CONNTRACK_MARK @@ -744,6 +747,7 @@ config NETFILTER_XT_TARGET_LED config NETFILTER_XT_TARGET_LOG tristate "LOG target support" + depends on NF_LOG_IPV4 && NF_LOG_IPV6 default m if NETFILTER_ADVANCED=n help This option adds a `LOG' target, which allows you to create rules in diff --git a/net/netfilter/Makefile b/net/netfilter/Makefile index bffdad774da7..8308624a406a 100644 --- a/net/netfilter/Makefile +++ b/net/netfilter/Makefile @@ -47,6 +47,9 @@ obj-$(CONFIG_NF_CONNTRACK_TFTP) += nf_conntrack_tftp.o nf_nat-y := nf_nat_core.o nf_nat_proto_unknown.o nf_nat_proto_common.o \ nf_nat_proto_udp.o nf_nat_proto_tcp.o nf_nat_helper.o +# generic transport layer logging +obj-$(CONFIG_NF_LOG_COMMON) += nf_log_common.o + obj-$(CONFIG_NF_NAT) += nf_nat.o # NAT protocols (nf_nat) diff --git a/net/netfilter/ipvs/ip_vs_ctl.c b/net/netfilter/ipvs/ip_vs_ctl.c index 581a6584ed0c..8416307fdd1d 100644 --- a/net/netfilter/ipvs/ip_vs_ctl.c +++ b/net/netfilter/ipvs/ip_vs_ctl.c @@ -1807,92 +1807,6 @@ static struct ctl_table vs_vars[] = { .proc_handler = proc_dointvec, }, #endif -#if 0 - { - .procname = "timeout_established", - .data = &vs_timeout_table_dos.timeout[IP_VS_S_ESTABLISHED], - .maxlen = sizeof(int), - .mode = 0644, - .proc_handler = proc_dointvec_jiffies, - }, - { - .procname = "timeout_synsent", - .data = &vs_timeout_table_dos.timeout[IP_VS_S_SYN_SENT], - .maxlen = sizeof(int), - .mode = 0644, - .proc_handler = proc_dointvec_jiffies, - }, - { - .procname = "timeout_synrecv", - .data = &vs_timeout_table_dos.timeout[IP_VS_S_SYN_RECV], - .maxlen = sizeof(int), - .mode = 0644, - .proc_handler = proc_dointvec_jiffies, - }, - { - .procname = "timeout_finwait", - .data = &vs_timeout_table_dos.timeout[IP_VS_S_FIN_WAIT], - .maxlen = sizeof(int), - .mode = 0644, - .proc_handler = proc_dointvec_jiffies, - }, - { - .procname = "timeout_timewait", - .data = &vs_timeout_table_dos.timeout[IP_VS_S_TIME_WAIT], - .maxlen = sizeof(int), - .mode = 0644, - .proc_handler = proc_dointvec_jiffies, - }, - { - .procname = "timeout_close", - .data = &vs_timeout_table_dos.timeout[IP_VS_S_CLOSE], - .maxlen = sizeof(int), - .mode = 0644, - .proc_handler = proc_dointvec_jiffies, - }, - { - .procname = "timeout_closewait", - .data = &vs_timeout_table_dos.timeout[IP_VS_S_CLOSE_WAIT], - .maxlen = sizeof(int), - .mode = 0644, - .proc_handler = proc_dointvec_jiffies, - }, - { - .procname = "timeout_lastack", - .data = &vs_timeout_table_dos.timeout[IP_VS_S_LAST_ACK], - .maxlen = sizeof(int), - .mode = 0644, - .proc_handler = proc_dointvec_jiffies, - }, - { - .procname = "timeout_listen", - .data = &vs_timeout_table_dos.timeout[IP_VS_S_LISTEN], - .maxlen = sizeof(int), - .mode = 0644, - .proc_handler = proc_dointvec_jiffies, - }, - { - .procname = "timeout_synack", - .data = &vs_timeout_table_dos.timeout[IP_VS_S_SYNACK], - .maxlen = sizeof(int), - .mode = 0644, - .proc_handler = proc_dointvec_jiffies, - }, - { - .procname = "timeout_udp", - .data = &vs_timeout_table_dos.timeout[IP_VS_S_UDP], - .maxlen = sizeof(int), - .mode = 0644, - .proc_handler = proc_dointvec_jiffies, - }, - { - .procname = "timeout_icmp", - .data = &vs_timeout_table_dos.timeout[IP_VS_S_ICMP], - .maxlen = sizeof(int), - .mode = 0644, - .proc_handler = proc_dointvec_jiffies, - }, -#endif { } }; diff --git a/net/netfilter/ipvs/ip_vs_sync.c b/net/netfilter/ipvs/ip_vs_sync.c index db801263ee9f..eadffb29dec0 100644 --- a/net/netfilter/ipvs/ip_vs_sync.c +++ b/net/netfilter/ipvs/ip_vs_sync.c @@ -886,8 +886,7 @@ static void ip_vs_proc_conn(struct net *net, struct ip_vs_conn_param *param, cp = ip_vs_conn_new(param, daddr, dport, flags, dest, fwmark); rcu_read_unlock(); if (!cp) { - if (param->pe_data) - kfree(param->pe_data); + kfree(param->pe_data); IP_VS_DBG(2, "BACKUP, add new conn. failed\n"); return; } diff --git a/net/netfilter/ipvs/ip_vs_xmit.c b/net/netfilter/ipvs/ip_vs_xmit.c index 73ba1cc7a88d..6f70bdd3a90a 100644 --- a/net/netfilter/ipvs/ip_vs_xmit.c +++ b/net/netfilter/ipvs/ip_vs_xmit.c @@ -967,8 +967,8 @@ ip_vs_tunnel_xmit_v6(struct sk_buff *skb, struct ip_vs_conn *cp, iph->nexthdr = IPPROTO_IPV6; iph->payload_len = old_iph->payload_len; be16_add_cpu(&iph->payload_len, sizeof(*old_iph)); - iph->priority = old_iph->priority; memset(&iph->flow_lbl, 0, sizeof(iph->flow_lbl)); + ipv6_change_dsfield(iph, 0, ipv6_get_dsfield(old_iph)); iph->daddr = cp->daddr.in6; iph->saddr = saddr; iph->hop_limit = old_iph->hop_limit; diff --git a/net/netfilter/nf_conntrack_core.c b/net/netfilter/nf_conntrack_core.c index 1f4f954c4b47..de88c4ab5146 100644 --- a/net/netfilter/nf_conntrack_core.c +++ b/net/netfilter/nf_conntrack_core.c @@ -352,40 +352,6 @@ static void nf_ct_delete_from_lists(struct nf_conn *ct) local_bh_enable(); } -static void death_by_event(unsigned long ul_conntrack) -{ - struct nf_conn *ct = (void *)ul_conntrack; - struct net *net = nf_ct_net(ct); - struct nf_conntrack_ecache *ecache = nf_ct_ecache_find(ct); - - BUG_ON(ecache == NULL); - - if (nf_conntrack_event(IPCT_DESTROY, ct) < 0) { - /* bad luck, let's retry again */ - ecache->timeout.expires = jiffies + - (prandom_u32() % net->ct.sysctl_events_retry_timeout); - add_timer(&ecache->timeout); - return; - } - /* we've got the event delivered, now it's dying */ - set_bit(IPS_DYING_BIT, &ct->status); - nf_ct_put(ct); -} - -static void nf_ct_dying_timeout(struct nf_conn *ct) -{ - struct net *net = nf_ct_net(ct); - struct nf_conntrack_ecache *ecache = nf_ct_ecache_find(ct); - - BUG_ON(ecache == NULL); - - /* set a new timer to retry event delivery */ - setup_timer(&ecache->timeout, death_by_event, (unsigned long)ct); - ecache->timeout.expires = jiffies + - (prandom_u32() % net->ct.sysctl_events_retry_timeout); - add_timer(&ecache->timeout); -} - bool nf_ct_delete(struct nf_conn *ct, u32 portid, int report) { struct nf_conn_tstamp *tstamp; @@ -394,15 +360,20 @@ bool nf_ct_delete(struct nf_conn *ct, u32 portid, int report) if (tstamp && tstamp->stop == 0) tstamp->stop = ktime_to_ns(ktime_get_real()); - if (!nf_ct_is_dying(ct) && - unlikely(nf_conntrack_event_report(IPCT_DESTROY, ct, - portid, report) < 0)) { + if (nf_ct_is_dying(ct)) + goto delete; + + if (nf_conntrack_event_report(IPCT_DESTROY, ct, + portid, report) < 0) { /* destroy event was not delivered */ nf_ct_delete_from_lists(ct); - nf_ct_dying_timeout(ct); + nf_conntrack_ecache_delayed_work(nf_ct_net(ct)); return false; } + + nf_conntrack_ecache_work(nf_ct_net(ct)); set_bit(IPS_DYING_BIT, &ct->status); + delete: nf_ct_delete_from_lists(ct); nf_ct_put(ct); return true; @@ -1464,26 +1435,6 @@ void nf_conntrack_flush_report(struct net *net, u32 portid, int report) } EXPORT_SYMBOL_GPL(nf_conntrack_flush_report); -static void nf_ct_release_dying_list(struct net *net) -{ - struct nf_conntrack_tuple_hash *h; - struct nf_conn *ct; - struct hlist_nulls_node *n; - int cpu; - - for_each_possible_cpu(cpu) { - struct ct_pcpu *pcpu = per_cpu_ptr(net->ct.pcpu_lists, cpu); - - spin_lock_bh(&pcpu->lock); - hlist_nulls_for_each_entry(h, n, &pcpu->dying, hnnode) { - ct = nf_ct_tuplehash_to_ctrack(h); - /* never fails to remove them, no listeners at this point */ - nf_ct_kill(ct); - } - spin_unlock_bh(&pcpu->lock); - } -} - static int untrack_refs(void) { int cnt = 0, cpu; @@ -1548,7 +1499,6 @@ i_see_dead_people: busy = 0; list_for_each_entry(net, net_exit_list, exit_list) { nf_ct_iterate_cleanup(net, kill_all, NULL, 0, 0); - nf_ct_release_dying_list(net); if (atomic_read(&net->ct.count) != 0) busy = 1; } diff --git a/net/netfilter/nf_conntrack_ecache.c b/net/netfilter/nf_conntrack_ecache.c index 1df176146567..4e78c57b818f 100644 --- a/net/netfilter/nf_conntrack_ecache.c +++ b/net/netfilter/nf_conntrack_ecache.c @@ -29,6 +29,90 @@ static DEFINE_MUTEX(nf_ct_ecache_mutex); +#define ECACHE_RETRY_WAIT (HZ/10) + +enum retry_state { + STATE_CONGESTED, + STATE_RESTART, + STATE_DONE, +}; + +static enum retry_state ecache_work_evict_list(struct ct_pcpu *pcpu) +{ + struct nf_conn *refs[16]; + struct nf_conntrack_tuple_hash *h; + struct hlist_nulls_node *n; + unsigned int evicted = 0; + enum retry_state ret = STATE_DONE; + + spin_lock(&pcpu->lock); + + hlist_nulls_for_each_entry(h, n, &pcpu->dying, hnnode) { + struct nf_conn *ct = nf_ct_tuplehash_to_ctrack(h); + + if (nf_ct_is_dying(ct)) + continue; + + if (nf_conntrack_event(IPCT_DESTROY, ct)) { + ret = STATE_CONGESTED; + break; + } + + /* we've got the event delivered, now it's dying */ + set_bit(IPS_DYING_BIT, &ct->status); + refs[evicted] = ct; + + if (++evicted >= ARRAY_SIZE(refs)) { + ret = STATE_RESTART; + break; + } + } + + spin_unlock(&pcpu->lock); + + /* can't _put while holding lock */ + while (evicted) + nf_ct_put(refs[--evicted]); + + return ret; +} + +static void ecache_work(struct work_struct *work) +{ + struct netns_ct *ctnet = + container_of(work, struct netns_ct, ecache_dwork.work); + int cpu, delay = -1; + struct ct_pcpu *pcpu; + + local_bh_disable(); + + for_each_possible_cpu(cpu) { + enum retry_state ret; + + pcpu = per_cpu_ptr(ctnet->pcpu_lists, cpu); + + ret = ecache_work_evict_list(pcpu); + + switch (ret) { + case STATE_CONGESTED: + delay = ECACHE_RETRY_WAIT; + goto out; + case STATE_RESTART: + delay = 0; + break; + case STATE_DONE: + break; + } + } + + out: + local_bh_enable(); + + ctnet->ecache_dwork_pending = delay > 0; + if (delay >= 0) + schedule_delayed_work(&ctnet->ecache_dwork, delay); +} + /* deliver cached events and clear cache entry - must be called with locally * disabled softirqs */ void nf_ct_deliver_cached_events(struct nf_conn *ct) @@ -157,7 +241,6 @@ EXPORT_SYMBOL_GPL(nf_ct_expect_unregister_notifier); #define NF_CT_EVENTS_DEFAULT 1 static int nf_ct_events __read_mostly = NF_CT_EVENTS_DEFAULT; -static int nf_ct_events_retry_timeout __read_mostly = 15*HZ; #ifdef CONFIG_SYSCTL static struct ctl_table event_sysctl_table[] = { @@ -168,13 +251,6 @@ static struct ctl_table event_sysctl_table[] = { .mode = 0644, .proc_handler = proc_dointvec, }, - { - .procname = "nf_conntrack_events_retry_timeout", - .data = &init_net.ct.sysctl_events_retry_timeout, - .maxlen = sizeof(unsigned int), - .mode = 0644, - .proc_handler = proc_dointvec_jiffies, - }, {} }; #endif /* CONFIG_SYSCTL */ @@ -196,7 +272,6 @@ static int nf_conntrack_event_init_sysctl(struct net *net) goto out; table[0].data = &net->ct.sysctl_events; - table[1].data = &net->ct.sysctl_events_retry_timeout; /* Don't export sysctls to unprivileged users */ if (net->user_ns != &init_user_ns) @@ -238,12 +313,13 @@ static void nf_conntrack_event_fini_sysctl(struct net *net) int nf_conntrack_ecache_pernet_init(struct net *net) { net->ct.sysctl_events = nf_ct_events; - net->ct.sysctl_events_retry_timeout = nf_ct_events_retry_timeout; + INIT_DELAYED_WORK(&net->ct.ecache_dwork, ecache_work); return nf_conntrack_event_init_sysctl(net); } void nf_conntrack_ecache_pernet_fini(struct net *net) { + cancel_delayed_work_sync(&net->ct.ecache_dwork); nf_conntrack_event_fini_sysctl(net); } diff --git a/net/netfilter/nf_conntrack_netlink.c b/net/netfilter/nf_conntrack_netlink.c index 300ed1eec729..355a5c4ef763 100644 --- a/net/netfilter/nf_conntrack_netlink.c +++ b/net/netfilter/nf_conntrack_netlink.c @@ -745,8 +745,7 @@ static int ctnetlink_done(struct netlink_callback *cb) { if (cb->args[1]) nf_ct_put((struct nf_conn *)cb->args[1]); - if (cb->data) - kfree(cb->data); + kfree(cb->data); return 0; } diff --git a/net/netfilter/nf_log.c b/net/netfilter/nf_log.c index 85296d4eac0e..daad6022c689 100644 --- a/net/netfilter/nf_log.c +++ b/net/netfilter/nf_log.c @@ -16,16 +16,22 @@ #define NF_LOG_PREFIXLEN 128 #define NFLOGGER_NAME_LEN 64 -static struct list_head nf_loggers_l[NFPROTO_NUMPROTO] __read_mostly; +static struct nf_logger __rcu *loggers[NFPROTO_NUMPROTO][NF_LOG_TYPE_MAX] __read_mostly; static DEFINE_MUTEX(nf_log_mutex); static struct nf_logger *__find_logger(int pf, const char *str_logger) { - struct nf_logger *t; + struct nf_logger *log; + int i; + + for (i = 0; i < NF_LOG_TYPE_MAX; i++) { + if (loggers[pf][i] == NULL) + continue; - list_for_each_entry(t, &nf_loggers_l[pf], list[pf]) { - if (!strnicmp(str_logger, t->name, strlen(t->name))) - return t; + log = rcu_dereference_protected(loggers[pf][i], + lockdep_is_held(&nf_log_mutex)); + if (!strnicmp(str_logger, log->name, strlen(log->name))) + return log; } return NULL; @@ -73,17 +79,14 @@ int nf_log_register(u_int8_t pf, struct nf_logger *logger) if (pf >= ARRAY_SIZE(init_net.nf.nf_loggers)) return -EINVAL; - for (i = 0; i < ARRAY_SIZE(logger->list); i++) - INIT_LIST_HEAD(&logger->list[i]); - mutex_lock(&nf_log_mutex); if (pf == NFPROTO_UNSPEC) { for (i = NFPROTO_UNSPEC; i < NFPROTO_NUMPROTO; i++) - list_add_tail(&(logger->list[i]), &(nf_loggers_l[i])); + rcu_assign_pointer(loggers[i][logger->type], logger); } else { /* register at end of list to honor first register win */ - list_add_tail(&logger->list[pf], &nf_loggers_l[pf]); + rcu_assign_pointer(loggers[pf][logger->type], logger); } mutex_unlock(&nf_log_mutex); @@ -98,7 +101,7 @@ void nf_log_unregister(struct nf_logger *logger) mutex_lock(&nf_log_mutex); for (i = 0; i < NFPROTO_NUMPROTO; i++) - list_del(&logger->list[i]); + RCU_INIT_POINTER(loggers[i][logger->type], NULL); mutex_unlock(&nf_log_mutex); } EXPORT_SYMBOL(nf_log_unregister); @@ -129,6 +132,48 @@ void nf_log_unbind_pf(struct net *net, u_int8_t pf) } EXPORT_SYMBOL(nf_log_unbind_pf); +void nf_logger_request_module(int pf, enum nf_log_type type) +{ + if (loggers[pf][type] == NULL) + request_module("nf-logger-%u-%u", pf, type); +} +EXPORT_SYMBOL_GPL(nf_logger_request_module); + +int nf_logger_find_get(int pf, enum nf_log_type type) +{ + struct nf_logger *logger; + int ret = -ENOENT; + + logger = loggers[pf][type]; + if (logger == NULL) + request_module("nf-logger-%u-%u", pf, type); + + rcu_read_lock(); + logger = rcu_dereference(loggers[pf][type]); + if (logger == NULL) + goto out; + + if (logger && try_module_get(logger->me)) + ret = 0; +out: + rcu_read_unlock(); + return ret; +} +EXPORT_SYMBOL_GPL(nf_logger_find_get); + +void nf_logger_put(int pf, enum nf_log_type type) +{ + struct nf_logger *logger; + + BUG_ON(loggers[pf][type] == NULL); + + rcu_read_lock(); + logger = rcu_dereference(loggers[pf][type]); + module_put(logger->me); + rcu_read_unlock(); +} +EXPORT_SYMBOL_GPL(nf_logger_put); + void nf_log_packet(struct net *net, u_int8_t pf, unsigned int hooknum, @@ -143,7 +188,11 @@ void nf_log_packet(struct net *net, const struct nf_logger *logger; rcu_read_lock(); - logger = rcu_dereference(net->nf.nf_loggers[pf]); + if (loginfo != NULL) + logger = rcu_dereference(loggers[pf][loginfo->type]); + else + logger = rcu_dereference(net->nf.nf_loggers[pf]); + if (logger) { va_start(args, fmt); vsnprintf(prefix, sizeof(prefix), fmt, args); @@ -154,6 +203,63 @@ void nf_log_packet(struct net *net, } EXPORT_SYMBOL(nf_log_packet); +#define S_SIZE (1024 - (sizeof(unsigned int) + 1)) + +struct nf_log_buf { + unsigned int count; + char buf[S_SIZE + 1]; +}; +static struct nf_log_buf emergency, *emergency_ptr = &emergency; + +__printf(2, 3) int nf_log_buf_add(struct nf_log_buf *m, const char *f, ...) +{ + va_list args; + int len; + + if (likely(m->count < S_SIZE)) { + va_start(args, f); + len = vsnprintf(m->buf + m->count, S_SIZE - m->count, f, args); + va_end(args); + if (likely(m->count + len < S_SIZE)) { + m->count += len; + return 0; + } + } + m->count = S_SIZE; + printk_once(KERN_ERR KBUILD_MODNAME " please increase S_SIZE\n"); + return -1; +} +EXPORT_SYMBOL_GPL(nf_log_buf_add); + +struct nf_log_buf *nf_log_buf_open(void) +{ + struct nf_log_buf *m = kmalloc(sizeof(*m), GFP_ATOMIC); + + if (unlikely(!m)) { + local_bh_disable(); + do { + m = xchg(&emergency_ptr, NULL); + } while (!m); + } + m->count = 0; + return m; +} +EXPORT_SYMBOL_GPL(nf_log_buf_open); + +void nf_log_buf_close(struct nf_log_buf *m) +{ + m->buf[m->count] = 0; + printk("%s\n", m->buf); + + if (likely(m != &emergency)) + kfree(m); + else { + emergency_ptr = m; + local_bh_enable(); + } +} +EXPORT_SYMBOL_GPL(nf_log_buf_close); + #ifdef CONFIG_PROC_FS static void *seq_start(struct seq_file *seq, loff_t *pos) { @@ -188,8 +294,7 @@ static int seq_show(struct seq_file *s, void *v) { loff_t *pos = v; const struct nf_logger *logger; - struct nf_logger *t; - int ret; + int i, ret; struct net *net = seq_file_net(s); logger = rcu_dereference_protected(net->nf.nf_loggers[*pos], @@ -203,11 +308,16 @@ static int seq_show(struct seq_file *s, void *v) if (ret < 0) return ret; - list_for_each_entry(t, &nf_loggers_l[*pos], list[*pos]) { - ret = seq_printf(s, "%s", t->name); + for (i = 0; i < NF_LOG_TYPE_MAX; i++) { + if (loggers[*pos][i] == NULL) + continue; + + logger = rcu_dereference_protected(loggers[*pos][i], + lockdep_is_held(&nf_log_mutex)); + ret = seq_printf(s, "%s", logger->name); if (ret < 0) return ret; - if (&t->list[*pos] != nf_loggers_l[*pos].prev) { + if (i == 0 && loggers[*pos][i + 1] != NULL) { ret = seq_printf(s, ","); if (ret < 0) return ret; @@ -389,14 +499,5 @@ static struct pernet_operations nf_log_net_ops = { int __init netfilter_log_init(void) { - int i, ret; - - ret = register_pernet_subsys(&nf_log_net_ops); - if (ret < 0) - return ret; - - for (i = NFPROTO_UNSPEC; i < NFPROTO_NUMPROTO; i++) - INIT_LIST_HEAD(&(nf_loggers_l[i])); - - return 0; + return register_pernet_subsys(&nf_log_net_ops); } diff --git a/net/netfilter/nf_log_common.c b/net/netfilter/nf_log_common.c new file mode 100644 index 000000000000..eeb8ef4ff1a3 --- /dev/null +++ b/net/netfilter/nf_log_common.c @@ -0,0 +1,187 @@ +/* (C) 1999-2001 Paul `Rusty' Russell + * (C) 2002-2004 Netfilter Core Team <coreteam@netfilter.org> + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + */ + +#include <linux/module.h> +#include <linux/spinlock.h> +#include <linux/skbuff.h> +#include <linux/if_arp.h> +#include <linux/ip.h> +#include <net/icmp.h> +#include <net/udp.h> +#include <net/tcp.h> +#include <net/route.h> + +#include <linux/netfilter.h> +#include <linux/netfilter/xt_LOG.h> +#include <net/netfilter/nf_log.h> + +int nf_log_dump_udp_header(struct nf_log_buf *m, const struct sk_buff *skb, + u8 proto, int fragment, unsigned int offset) +{ + struct udphdr _udph; + const struct udphdr *uh; + + if (proto == IPPROTO_UDP) + /* Max length: 10 "PROTO=UDP " */ + nf_log_buf_add(m, "PROTO=UDP "); + else /* Max length: 14 "PROTO=UDPLITE " */ + nf_log_buf_add(m, "PROTO=UDPLITE "); + + if (fragment) + goto out; + + /* Max length: 25 "INCOMPLETE [65535 bytes] " */ + uh = skb_header_pointer(skb, offset, sizeof(_udph), &_udph); + if (uh == NULL) { + nf_log_buf_add(m, "INCOMPLETE [%u bytes] ", skb->len - offset); + + return 1; + } + + /* Max length: 20 "SPT=65535 DPT=65535 " */ + nf_log_buf_add(m, "SPT=%u DPT=%u LEN=%u ", + ntohs(uh->source), ntohs(uh->dest), ntohs(uh->len)); + +out: + return 0; +} +EXPORT_SYMBOL_GPL(nf_log_dump_udp_header); + +int nf_log_dump_tcp_header(struct nf_log_buf *m, const struct sk_buff *skb, + u8 proto, int fragment, unsigned int offset, + unsigned int logflags) +{ + struct tcphdr _tcph; + const struct tcphdr *th; + + /* Max length: 10 "PROTO=TCP " */ + nf_log_buf_add(m, "PROTO=TCP "); + + if (fragment) + return 0; + + /* Max length: 25 "INCOMPLETE [65535 bytes] " */ + th = skb_header_pointer(skb, offset, sizeof(_tcph), &_tcph); + if (th == NULL) { + nf_log_buf_add(m, "INCOMPLETE [%u bytes] ", skb->len - offset); + return 1; + } + + /* Max length: 20 "SPT=65535 DPT=65535 " */ + nf_log_buf_add(m, "SPT=%u DPT=%u ", + ntohs(th->source), ntohs(th->dest)); + /* Max length: 30 "SEQ=4294967295 ACK=4294967295 " */ + if (logflags & XT_LOG_TCPSEQ) { + nf_log_buf_add(m, "SEQ=%u ACK=%u ", + ntohl(th->seq), ntohl(th->ack_seq)); + } + + /* Max length: 13 "WINDOW=65535 " */ + nf_log_buf_add(m, "WINDOW=%u ", ntohs(th->window)); + /* Max length: 9 "RES=0x3C " */ + nf_log_buf_add(m, "RES=0x%02x ", (u_int8_t)(ntohl(tcp_flag_word(th) & + TCP_RESERVED_BITS) >> 22)); + /* Max length: 32 "CWR ECE URG ACK PSH RST SYN FIN " */ + if (th->cwr) + nf_log_buf_add(m, "CWR "); + if (th->ece) + nf_log_buf_add(m, "ECE "); + if (th->urg) + nf_log_buf_add(m, "URG "); + if (th->ack) + nf_log_buf_add(m, "ACK "); + if (th->psh) + nf_log_buf_add(m, "PSH "); + if (th->rst) + nf_log_buf_add(m, "RST "); + if (th->syn) + nf_log_buf_add(m, "SYN "); + if (th->fin) + nf_log_buf_add(m, "FIN "); + /* Max length: 11 "URGP=65535 " */ + nf_log_buf_add(m, "URGP=%u ", ntohs(th->urg_ptr)); + + if ((logflags & XT_LOG_TCPOPT) && th->doff*4 > sizeof(struct tcphdr)) { + u_int8_t _opt[60 - sizeof(struct tcphdr)]; + const u_int8_t *op; + unsigned int i; + unsigned int optsize = th->doff*4 - sizeof(struct tcphdr); + + op = skb_header_pointer(skb, offset + sizeof(struct tcphdr), + optsize, _opt); + if (op == NULL) { + nf_log_buf_add(m, "OPT (TRUNCATED)"); + return 1; + } + + /* Max length: 127 "OPT (" 15*4*2chars ") " */ + nf_log_buf_add(m, "OPT ("); + for (i = 0; i < optsize; i++) + nf_log_buf_add(m, "%02X", op[i]); + + nf_log_buf_add(m, ") "); + } + + return 0; +} +EXPORT_SYMBOL_GPL(nf_log_dump_tcp_header); + +void nf_log_dump_sk_uid_gid(struct nf_log_buf *m, struct sock *sk) +{ + if (!sk || sk->sk_state == TCP_TIME_WAIT) + return; + + read_lock_bh(&sk->sk_callback_lock); + if (sk->sk_socket && sk->sk_socket->file) { + const struct cred *cred = sk->sk_socket->file->f_cred; + nf_log_buf_add(m, "UID=%u GID=%u ", + from_kuid_munged(&init_user_ns, cred->fsuid), + from_kgid_munged(&init_user_ns, cred->fsgid)); + } + read_unlock_bh(&sk->sk_callback_lock); +} +EXPORT_SYMBOL_GPL(nf_log_dump_sk_uid_gid); + +void +nf_log_dump_packet_common(struct nf_log_buf *m, u_int8_t pf, + unsigned int hooknum, const struct sk_buff *skb, + const struct net_device *in, + const struct net_device *out, + const struct nf_loginfo *loginfo, const char *prefix) +{ + nf_log_buf_add(m, KERN_SOH "%c%sIN=%s OUT=%s ", + '0' + loginfo->u.log.level, prefix, + in ? in->name : "", + out ? out->name : ""); +#ifdef CONFIG_BRIDGE_NETFILTER + if (skb->nf_bridge) { + const struct net_device *physindev; + const struct net_device *physoutdev; + + physindev = skb->nf_bridge->physindev; + if (physindev && in != physindev) + nf_log_buf_add(m, "PHYSIN=%s ", physindev->name); + physoutdev = skb->nf_bridge->physoutdev; + if (physoutdev && out != physoutdev) + nf_log_buf_add(m, "PHYSOUT=%s ", physoutdev->name); + } +#endif +} +EXPORT_SYMBOL_GPL(nf_log_dump_packet_common); + +static int __init nf_log_common_init(void) +{ + return 0; +} + +static void __exit nf_log_common_exit(void) {} + +module_init(nf_log_common_init); +module_exit(nf_log_common_exit); + +MODULE_LICENSE("GPL"); diff --git a/net/netfilter/nf_nat_core.c b/net/netfilter/nf_nat_core.c index a49907b1dabc..552f97cd9fde 100644 --- a/net/netfilter/nf_nat_core.c +++ b/net/netfilter/nf_nat_core.c @@ -710,7 +710,7 @@ static struct nf_ct_ext_type nat_extend __read_mostly = { .flags = NF_CT_EXT_F_PREALLOC, }; -#if defined(CONFIG_NF_CT_NETLINK) || defined(CONFIG_NF_CT_NETLINK_MODULE) +#if IS_ENABLED(CONFIG_NF_CT_NETLINK) #include <linux/netfilter/nfnetlink.h> #include <linux/netfilter/nfnetlink_conntrack.h> diff --git a/net/netfilter/nf_nat_proto_common.c b/net/netfilter/nf_nat_proto_common.c index 83a72a235cae..fbce552a796e 100644 --- a/net/netfilter/nf_nat_proto_common.c +++ b/net/netfilter/nf_nat_proto_common.c @@ -95,7 +95,7 @@ void nf_nat_l4proto_unique_tuple(const struct nf_nat_l3proto *l3proto, } EXPORT_SYMBOL_GPL(nf_nat_l4proto_unique_tuple); -#if defined(CONFIG_NF_CT_NETLINK) || defined(CONFIG_NF_CT_NETLINK_MODULE) +#if IS_ENABLED(CONFIG_NF_CT_NETLINK) int nf_nat_l4proto_nlattr_to_range(struct nlattr *tb[], struct nf_nat_range *range) { diff --git a/net/netfilter/nf_nat_proto_dccp.c b/net/netfilter/nf_nat_proto_dccp.c index c8be2cdac0bf..b8067b53ff3a 100644 --- a/net/netfilter/nf_nat_proto_dccp.c +++ b/net/netfilter/nf_nat_proto_dccp.c @@ -78,7 +78,7 @@ static const struct nf_nat_l4proto nf_nat_l4proto_dccp = { .manip_pkt = dccp_manip_pkt, .in_range = nf_nat_l4proto_in_range, .unique_tuple = dccp_unique_tuple, -#if defined(CONFIG_NF_CT_NETLINK) || defined(CONFIG_NF_CT_NETLINK_MODULE) +#if IS_ENABLED(CONFIG_NF_CT_NETLINK) .nlattr_to_range = nf_nat_l4proto_nlattr_to_range, #endif }; diff --git a/net/netfilter/nf_nat_proto_sctp.c b/net/netfilter/nf_nat_proto_sctp.c index 754536f2c674..cbc7ade1487b 100644 --- a/net/netfilter/nf_nat_proto_sctp.c +++ b/net/netfilter/nf_nat_proto_sctp.c @@ -59,7 +59,7 @@ static const struct nf_nat_l4proto nf_nat_l4proto_sctp = { .manip_pkt = sctp_manip_pkt, .in_range = nf_nat_l4proto_in_range, .unique_tuple = sctp_unique_tuple, -#if defined(CONFIG_NF_CT_NETLINK) || defined(CONFIG_NF_CT_NETLINK_MODULE) +#if IS_ENABLED(CONFIG_NF_CT_NETLINK) .nlattr_to_range = nf_nat_l4proto_nlattr_to_range, #endif }; diff --git a/net/netfilter/nf_nat_proto_tcp.c b/net/netfilter/nf_nat_proto_tcp.c index 83ec8a6e4c36..37f5505f4529 100644 --- a/net/netfilter/nf_nat_proto_tcp.c +++ b/net/netfilter/nf_nat_proto_tcp.c @@ -79,7 +79,7 @@ const struct nf_nat_l4proto nf_nat_l4proto_tcp = { .manip_pkt = tcp_manip_pkt, .in_range = nf_nat_l4proto_in_range, .unique_tuple = tcp_unique_tuple, -#if defined(CONFIG_NF_CT_NETLINK) || defined(CONFIG_NF_CT_NETLINK_MODULE) +#if IS_ENABLED(CONFIG_NF_CT_NETLINK) .nlattr_to_range = nf_nat_l4proto_nlattr_to_range, #endif }; diff --git a/net/netfilter/nf_nat_proto_udp.c b/net/netfilter/nf_nat_proto_udp.c index 7df613fb34a2..b0ede2f0d8bc 100644 --- a/net/netfilter/nf_nat_proto_udp.c +++ b/net/netfilter/nf_nat_proto_udp.c @@ -70,7 +70,7 @@ const struct nf_nat_l4proto nf_nat_l4proto_udp = { .manip_pkt = udp_manip_pkt, .in_range = nf_nat_l4proto_in_range, .unique_tuple = udp_unique_tuple, -#if defined(CONFIG_NF_CT_NETLINK) || defined(CONFIG_NF_CT_NETLINK_MODULE) +#if IS_ENABLED(CONFIG_NF_CT_NETLINK) .nlattr_to_range = nf_nat_l4proto_nlattr_to_range, #endif }; diff --git a/net/netfilter/nf_nat_proto_udplite.c b/net/netfilter/nf_nat_proto_udplite.c index 776a0d1317b1..368f14e01e75 100644 --- a/net/netfilter/nf_nat_proto_udplite.c +++ b/net/netfilter/nf_nat_proto_udplite.c @@ -69,7 +69,7 @@ static const struct nf_nat_l4proto nf_nat_l4proto_udplite = { .manip_pkt = udplite_manip_pkt, .in_range = nf_nat_l4proto_in_range, .unique_tuple = udplite_unique_tuple, -#if defined(CONFIG_NF_CT_NETLINK) || defined(CONFIG_NF_CT_NETLINK_MODULE) +#if IS_ENABLED(CONFIG_NF_CT_NETLINK) .nlattr_to_range = nf_nat_l4proto_nlattr_to_range, #endif }; diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c index 8746ff9a8357..b8035c2d6667 100644 --- a/net/netfilter/nf_tables_api.c +++ b/net/netfilter/nf_tables_api.c @@ -2247,80 +2247,7 @@ err: return err; } -static int nf_tables_dump_sets_table(struct nft_ctx *ctx, struct sk_buff *skb, - struct netlink_callback *cb) -{ - const struct nft_set *set; - unsigned int idx = 0, s_idx = cb->args[0]; - - if (cb->args[1]) - return skb->len; - - rcu_read_lock(); - cb->seq = ctx->net->nft.base_seq; - - list_for_each_entry_rcu(set, &ctx->table->sets, list) { - if (idx < s_idx) - goto cont; - if (nf_tables_fill_set(skb, ctx, set, NFT_MSG_NEWSET, - NLM_F_MULTI) < 0) { - cb->args[0] = idx; - goto done; - } - nl_dump_check_consistent(cb, nlmsg_hdr(skb)); -cont: - idx++; - } - cb->args[1] = 1; -done: - rcu_read_unlock(); - return skb->len; -} - -static int nf_tables_dump_sets_family(struct nft_ctx *ctx, struct sk_buff *skb, - struct netlink_callback *cb) -{ - const struct nft_set *set; - unsigned int idx, s_idx = cb->args[0]; - struct nft_table *table, *cur_table = (struct nft_table *)cb->args[2]; - - if (cb->args[1]) - return skb->len; - - rcu_read_lock(); - cb->seq = ctx->net->nft.base_seq; - - list_for_each_entry_rcu(table, &ctx->afi->tables, list) { - if (cur_table) { - if (cur_table != table) - continue; - - cur_table = NULL; - } - ctx->table = table; - idx = 0; - list_for_each_entry_rcu(set, &ctx->table->sets, list) { - if (idx < s_idx) - goto cont; - if (nf_tables_fill_set(skb, ctx, set, NFT_MSG_NEWSET, - NLM_F_MULTI) < 0) { - cb->args[0] = idx; - cb->args[2] = (unsigned long) table; - goto done; - } - nl_dump_check_consistent(cb, nlmsg_hdr(skb)); -cont: - idx++; - } - } - cb->args[1] = 1; -done: - rcu_read_unlock(); - return skb->len; -} - -static int nf_tables_dump_sets_all(struct nft_ctx *ctx, struct sk_buff *skb, - struct netlink_callback *cb) +static int nf_tables_dump_sets(struct sk_buff *skb, struct netlink_callback *cb) { const struct nft_set *set; unsigned int idx, s_idx = cb->args[0]; @@ -2328,6 +2255,7 @@ static int nf_tables_dump_sets_all(struct nft_ctx *ctx, struct sk_buff *skb, struct nft_table *table, *cur_table = (struct nft_table *)cb->args[2]; struct net *net = sock_net(skb->sk); int cur_family = cb->args[3]; + struct nft_ctx *ctx = cb->data, ctx_set; if (cb->args[1]) return skb->len; @@ -2336,28 +2264,34 @@ static int nf_tables_dump_sets_all(struct nft_ctx *ctx, struct sk_buff *skb, cb->seq = net->nft.base_seq; list_for_each_entry_rcu(afi, &net->nft.af_info, list) { + if (ctx->afi && ctx->afi != afi) + continue; + if (cur_family) { if (afi->family != cur_family) continue; cur_family = 0; } - list_for_each_entry_rcu(table, &afi->tables, list) { + if (ctx->table && ctx->table != table) + continue; + if (cur_table) { if (cur_table != table) continue; cur_table = NULL; } - - ctx->table = table; - ctx->afi = afi; idx = 0; - list_for_each_entry_rcu(set, &ctx->table->sets, list) { + list_for_each_entry_rcu(set, &table->sets, list) { if (idx < s_idx) goto cont; - if (nf_tables_fill_set(skb, ctx, set, + + ctx_set = *ctx; + ctx_set.table = table; + ctx_set.afi = afi; + if (nf_tables_fill_set(skb, &ctx_set, set, NFT_MSG_NEWSET, NLM_F_MULTI) < 0) { cb->args[0] = idx; @@ -2379,31 +2313,10 @@ done: return skb->len; } -static int nf_tables_dump_sets(struct sk_buff *skb, struct netlink_callback *cb) +static int nf_tables_dump_sets_done(struct netlink_callback *cb) { - const struct nfgenmsg *nfmsg = nlmsg_data(cb->nlh); - struct nlattr *nla[NFTA_SET_MAX + 1]; - struct nft_ctx ctx; - int err, ret; - - err = nlmsg_parse(cb->nlh, sizeof(*nfmsg), nla, NFTA_SET_MAX, - nft_set_policy); - if (err < 0) - return err; - - err = nft_ctx_init_from_setattr(&ctx, cb->skb, cb->nlh, (void *)nla); - if (err < 0) - return err; - - if (ctx.table == NULL) { - if (ctx.afi == NULL) - ret = nf_tables_dump_sets_all(&ctx, skb, cb); - else - ret = nf_tables_dump_sets_family(&ctx, skb, cb); - } else - ret = nf_tables_dump_sets_table(&ctx, skb, cb); - - return ret; + kfree(cb->data); + return 0; } #define NFT_SET_INACTIVE (1 << 15) /* Internal set flag */ @@ -2426,7 +2339,17 @@ static int nf_tables_getset(struct sock *nlsk, struct sk_buff *skb, if (nlh->nlmsg_flags & NLM_F_DUMP) { struct netlink_dump_control c = { .dump = nf_tables_dump_sets, + .done = nf_tables_dump_sets_done, }; + struct nft_ctx *ctx_dump; + + ctx_dump = kmalloc(sizeof(*ctx_dump), GFP_KERNEL); + if (ctx_dump == NULL) + return -ENOMEM; + + *ctx_dump = ctx; + c.data = ctx_dump; + return netlink_dump_start(nlsk, skb, nlh, &c); } @@ -3150,6 +3073,9 @@ static int nf_tables_newsetelem(struct sock *nlsk, struct sk_buff *skb, struct nft_ctx ctx; int rem, err = 0; + if (nla[NFTA_SET_ELEM_LIST_ELEMENTS] == NULL) + return -EINVAL; + err = nft_ctx_init_from_elemattr(&ctx, skb, nlh, nla, true); if (err < 0) return err; @@ -3218,6 +3144,7 @@ static int nft_del_setelem(struct nft_ctx *ctx, struct nft_set *set, if (set->flags & NFT_SET_MAP) nft_data_uninit(&elem.data, set->dtype); + return 0; err2: nft_data_uninit(&elem.key, desc.type); err1: @@ -3233,6 +3160,9 @@ static int nf_tables_delsetelem(struct sock *nlsk, struct sk_buff *skb, struct nft_ctx ctx; int rem, err = 0; + if (nla[NFTA_SET_ELEM_LIST_ELEMENTS] == NULL) + return -EINVAL; + err = nft_ctx_init_from_elemattr(&ctx, skb, nlh, nla, false); if (err < 0) return err; diff --git a/net/netfilter/nfnetlink_acct.c b/net/netfilter/nfnetlink_acct.c index 2baa125c2e8d..3ea0eacbd970 100644 --- a/net/netfilter/nfnetlink_acct.c +++ b/net/netfilter/nfnetlink_acct.c @@ -41,6 +41,7 @@ struct nf_acct { }; #define NFACCT_F_QUOTA (NFACCT_F_QUOTA_PKTS | NFACCT_F_QUOTA_BYTES) +#define NFACCT_OVERQUOTA_BIT 2 /* NFACCT_F_OVERQUOTA */ static int nfnl_acct_new(struct sock *nfnl, struct sk_buff *skb, @@ -77,7 +78,8 @@ nfnl_acct_new(struct sock *nfnl, struct sk_buff *skb, smp_mb__before_atomic(); /* reset overquota flag if quota is enabled. */ if ((matching->flags & NFACCT_F_QUOTA)) - clear_bit(NFACCT_F_OVERQUOTA, &matching->flags); + clear_bit(NFACCT_OVERQUOTA_BIT, + &matching->flags); return 0; } return -EBUSY; @@ -129,6 +131,7 @@ nfnl_acct_fill_info(struct sk_buff *skb, u32 portid, u32 seq, u32 type, struct nfgenmsg *nfmsg; unsigned int flags = portid ? NLM_F_MULTI : 0; u64 pkts, bytes; + u32 old_flags; event |= NFNL_SUBSYS_ACCT << 8; nlh = nlmsg_put(skb, portid, seq, event, sizeof(*nfmsg), flags); @@ -143,12 +146,13 @@ nfnl_acct_fill_info(struct sk_buff *skb, u32 portid, u32 seq, u32 type, if (nla_put_string(skb, NFACCT_NAME, acct->name)) goto nla_put_failure; + old_flags = acct->flags; if (type == NFNL_MSG_ACCT_GET_CTRZERO) { pkts = atomic64_xchg(&acct->pkts, 0); bytes = atomic64_xchg(&acct->bytes, 0); smp_mb__before_atomic(); if (acct->flags & NFACCT_F_QUOTA) - clear_bit(NFACCT_F_OVERQUOTA, &acct->flags); + clear_bit(NFACCT_OVERQUOTA_BIT, &acct->flags); } else { pkts = atomic64_read(&acct->pkts); bytes = atomic64_read(&acct->bytes); @@ -160,7 +164,7 @@ nfnl_acct_fill_info(struct sk_buff *skb, u32 portid, u32 seq, u32 type, if (acct->flags & NFACCT_F_QUOTA) { u64 *quota = (u64 *)acct->data; - if (nla_put_be32(skb, NFACCT_FLAGS, htonl(acct->flags)) || + if (nla_put_be32(skb, NFACCT_FLAGS, htonl(old_flags)) || nla_put_be64(skb, NFACCT_QUOTA, cpu_to_be64(*quota))) goto nla_put_failure; } @@ -412,7 +416,7 @@ int nfnl_acct_overquota(const struct sk_buff *skb, struct nf_acct *nfacct) ret = now > *quota; if (now >= *quota && - !test_and_set_bit(NFACCT_F_OVERQUOTA, &nfacct->flags)) { + !test_and_set_bit(NFACCT_OVERQUOTA_BIT, &nfacct->flags)) { nfnl_overquota_report(nfacct); } diff --git a/net/netfilter/nfnetlink_log.c b/net/netfilter/nfnetlink_log.c index d292c8d286eb..a11c5ff2f720 100644 --- a/net/netfilter/nfnetlink_log.c +++ b/net/netfilter/nfnetlink_log.c @@ -773,6 +773,7 @@ nfulnl_recv_unsupp(struct sock *ctnl, struct sk_buff *skb, static struct nf_logger nfulnl_logger __read_mostly = { .name = "nfnetlink_log", + .type = NF_LOG_TYPE_ULOG, .logfn = &nfulnl_log_packet, .me = THIS_MODULE, }; @@ -1105,6 +1106,9 @@ MODULE_DESCRIPTION("netfilter userspace logging"); MODULE_AUTHOR("Harald Welte <laforge@netfilter.org>"); MODULE_LICENSE("GPL"); MODULE_ALIAS_NFNL_SUBSYS(NFNL_SUBSYS_ULOG); +MODULE_ALIAS_NF_LOGGER(AF_INET, 1); +MODULE_ALIAS_NF_LOGGER(AF_INET6, 1); +MODULE_ALIAS_NF_LOGGER(AF_BRIDGE, 1); module_init(nfnetlink_log_init); module_exit(nfnetlink_log_fini); diff --git a/net/netfilter/nft_hash.c b/net/netfilter/nft_hash.c index 4080ed6a072b..28fb8f38e6ba 100644 --- a/net/netfilter/nft_hash.c +++ b/net/netfilter/nft_hash.c @@ -15,209 +15,40 @@ #include <linux/log2.h> #include <linux/jhash.h> #include <linux/netlink.h> -#include <linux/vmalloc.h> +#include <linux/rhashtable.h> #include <linux/netfilter.h> #include <linux/netfilter/nf_tables.h> #include <net/netfilter/nf_tables.h> -#define NFT_HASH_MIN_SIZE 4UL - -struct nft_hash { - struct nft_hash_table __rcu *tbl; -}; - -struct nft_hash_table { - unsigned int size; - struct nft_hash_elem __rcu *buckets[]; -}; +/* We target a hash table size of 4, element hint is 75% of final size */ +#define NFT_HASH_ELEMENT_HINT 3 struct nft_hash_elem { - struct nft_hash_elem __rcu *next; + struct rhash_head node; struct nft_data key; struct nft_data data[]; }; -#define nft_hash_for_each_entry(i, head) \ - for (i = nft_dereference(head); i != NULL; i = nft_dereference(i->next)) -#define nft_hash_for_each_entry_rcu(i, head) \ - for (i = rcu_dereference(head); i != NULL; i = rcu_dereference(i->next)) - -static u32 nft_hash_rnd __read_mostly; -static bool nft_hash_rnd_initted __read_mostly; - -static unsigned int nft_hash_data(const struct nft_data *data, - unsigned int hsize, unsigned int len) -{ - unsigned int h; - - h = jhash(data->data, len, nft_hash_rnd); - return h & (hsize - 1); -} - static bool nft_hash_lookup(const struct nft_set *set, const struct nft_data *key, struct nft_data *data) { - const struct nft_hash *priv = nft_set_priv(set); - const struct nft_hash_table *tbl = rcu_dereference(priv->tbl); + const struct rhashtable *priv = nft_set_priv(set); const struct nft_hash_elem *he; - unsigned int h; - - h = nft_hash_data(key, tbl->size, set->klen); - nft_hash_for_each_entry_rcu(he, tbl->buckets[h]) { - if (nft_data_cmp(&he->key, key, set->klen)) - continue; - if (set->flags & NFT_SET_MAP) - nft_data_copy(data, he->data); - return true; - } - return false; -} - -static void nft_hash_tbl_free(const struct nft_hash_table *tbl) -{ - kvfree(tbl); -} - -static unsigned int nft_hash_tbl_size(unsigned int nelem) -{ - return max(roundup_pow_of_two(nelem * 4 / 3), NFT_HASH_MIN_SIZE); -} - -static struct nft_hash_table *nft_hash_tbl_alloc(unsigned int nbuckets) -{ - struct nft_hash_table *tbl; - size_t size; - - size = sizeof(*tbl) + nbuckets * sizeof(tbl->buckets[0]); - tbl = kzalloc(size, GFP_KERNEL | __GFP_REPEAT | __GFP_NOWARN); - if (tbl == NULL) - tbl = vzalloc(size); - if (tbl == NULL) - return NULL; - tbl->size = nbuckets; - - return tbl; -} - -static void nft_hash_chain_unzip(const struct nft_set *set, - const struct nft_hash_table *ntbl, - struct nft_hash_table *tbl, unsigned int n) -{ - struct nft_hash_elem *he, *last, *next; - unsigned int h; - - he = nft_dereference(tbl->buckets[n]); - if (he == NULL) - return; - h = nft_hash_data(&he->key, ntbl->size, set->klen); - - /* Find last element of first chain hashing to bucket h */ - last = he; - nft_hash_for_each_entry(he, he->next) { - if (nft_hash_data(&he->key, ntbl->size, set->klen) != h) - break; - last = he; - } - - /* Unlink first chain from the old table */ - RCU_INIT_POINTER(tbl->buckets[n], last->next); - /* If end of chain reached, done */ - if (he == NULL) - return; + he = rhashtable_lookup(priv, key); + if (he && set->flags & NFT_SET_MAP) + nft_data_copy(data, he->data); - /* Find first element of second chain hashing to bucket h */ - next = NULL; - nft_hash_for_each_entry(he, he->next) { - if (nft_hash_data(&he->key, ntbl->size, set->klen) != h) - continue; - next = he; - break; - } - - /* Link the two chains */ - RCU_INIT_POINTER(last->next, next); -} - -static int nft_hash_tbl_expand(const struct nft_set *set, struct nft_hash *priv) -{ - struct nft_hash_table *tbl = nft_dereference(priv->tbl), *ntbl; - struct nft_hash_elem *he; - unsigned int i, h; - bool complete; - - ntbl = nft_hash_tbl_alloc(tbl->size * 2); - if (ntbl == NULL) - return -ENOMEM; - - /* Link new table's buckets to first element in the old table - * hashing to the new bucket. - */ - for (i = 0; i < ntbl->size; i++) { - h = i < tbl->size ? i : i - tbl->size; - nft_hash_for_each_entry(he, tbl->buckets[h]) { - if (nft_hash_data(&he->key, ntbl->size, set->klen) != i) - continue; - RCU_INIT_POINTER(ntbl->buckets[i], he); - break; - } - } - - /* Publish new table */ - rcu_assign_pointer(priv->tbl, ntbl); - - /* Unzip interleaved hash chains */ - do { - /* Wait for readers to use new table/unzipped chains */ - synchronize_rcu(); - - complete = true; - for (i = 0; i < tbl->size; i++) { - nft_hash_chain_unzip(set, ntbl, tbl, i); - if (tbl->buckets[i] != NULL) - complete = false; - } - } while (!complete); - - nft_hash_tbl_free(tbl); - return 0; -} - -static int nft_hash_tbl_shrink(const struct nft_set *set, struct nft_hash *priv) -{ - struct nft_hash_table *tbl = nft_dereference(priv->tbl), *ntbl; - struct nft_hash_elem __rcu **pprev; - unsigned int i; - - ntbl = nft_hash_tbl_alloc(tbl->size / 2); - if (ntbl == NULL) - return -ENOMEM; - - for (i = 0; i < ntbl->size; i++) { - ntbl->buckets[i] = tbl->buckets[i]; - - for (pprev = &ntbl->buckets[i]; *pprev != NULL; - pprev = &nft_dereference(*pprev)->next) - ; - RCU_INIT_POINTER(*pprev, tbl->buckets[i + ntbl->size]); - } - - /* Publish new table */ - rcu_assign_pointer(priv->tbl, ntbl); - synchronize_rcu(); - - nft_hash_tbl_free(tbl); - return 0; + return !!he; } static int nft_hash_insert(const struct nft_set *set, const struct nft_set_elem *elem) { - struct nft_hash *priv = nft_set_priv(set); - struct nft_hash_table *tbl = nft_dereference(priv->tbl); + struct rhashtable *priv = nft_set_priv(set); struct nft_hash_elem *he; - unsigned int size, h; + unsigned int size; if (elem->flags != 0) return -EINVAL; @@ -234,13 +65,7 @@ static int nft_hash_insert(const struct nft_set *set, if (set->flags & NFT_SET_MAP) nft_data_copy(he->data, &elem->data); - h = nft_hash_data(&he->key, tbl->size, set->klen); - RCU_INIT_POINTER(he->next, tbl->buckets[h]); - rcu_assign_pointer(tbl->buckets[h], he); - - /* Expand table when exceeding 75% load */ - if (set->nelems + 1 > tbl->size / 4 * 3) - nft_hash_tbl_expand(set, priv); + rhashtable_insert(priv, &he->node, GFP_KERNEL); return 0; } @@ -257,36 +82,31 @@ static void nft_hash_elem_destroy(const struct nft_set *set, static void nft_hash_remove(const struct nft_set *set, const struct nft_set_elem *elem) { - struct nft_hash *priv = nft_set_priv(set); - struct nft_hash_table *tbl = nft_dereference(priv->tbl); - struct nft_hash_elem *he, __rcu **pprev; + struct rhashtable *priv = nft_set_priv(set); + struct rhash_head *he, __rcu **pprev; pprev = elem->cookie; - he = nft_dereference((*pprev)); + he = rht_dereference((*pprev), priv); + + rhashtable_remove_pprev(priv, he, pprev, GFP_KERNEL); - RCU_INIT_POINTER(*pprev, he->next); synchronize_rcu(); kfree(he); - - /* Shrink table beneath 30% load */ - if (set->nelems - 1 < tbl->size * 3 / 10 && - tbl->size > NFT_HASH_MIN_SIZE) - nft_hash_tbl_shrink(set, priv); } static int nft_hash_get(const struct nft_set *set, struct nft_set_elem *elem) { - const struct nft_hash *priv = nft_set_priv(set); - const struct nft_hash_table *tbl = nft_dereference(priv->tbl); - struct nft_hash_elem __rcu * const *pprev; + const struct rhashtable *priv = nft_set_priv(set); + const struct bucket_table *tbl = rht_dereference_rcu(priv->tbl, priv); + struct rhash_head __rcu * const *pprev; struct nft_hash_elem *he; - unsigned int h; + u32 h; - h = nft_hash_data(&elem->key, tbl->size, set->klen); + h = rhashtable_hashfn(priv, &elem->key, set->klen); pprev = &tbl->buckets[h]; - nft_hash_for_each_entry(he, tbl->buckets[h]) { + rht_for_each_entry_rcu(he, tbl->buckets[h], node) { if (nft_data_cmp(&he->key, &elem->key, set->klen)) { - pprev = &he->next; + pprev = &he->node.next; continue; } @@ -302,14 +122,15 @@ static int nft_hash_get(const struct nft_set *set, struct nft_set_elem *elem) static void nft_hash_walk(const struct nft_ctx *ctx, const struct nft_set *set, struct nft_set_iter *iter) { - const struct nft_hash *priv = nft_set_priv(set); - const struct nft_hash_table *tbl = nft_dereference(priv->tbl); + const struct rhashtable *priv = nft_set_priv(set); + const struct bucket_table *tbl; const struct nft_hash_elem *he; struct nft_set_elem elem; unsigned int i; + tbl = rht_dereference_rcu(priv->tbl, priv); for (i = 0; i < tbl->size; i++) { - nft_hash_for_each_entry(he, tbl->buckets[i]) { + rht_for_each_entry_rcu(he, tbl->buckets[i], node) { if (iter->count < iter->skip) goto cont; @@ -329,48 +150,46 @@ cont: static unsigned int nft_hash_privsize(const struct nlattr * const nla[]) { - return sizeof(struct nft_hash); + return sizeof(struct rhashtable); +} + +static int lockdep_nfnl_lock_is_held(void) +{ + return lockdep_nfnl_is_held(NFNL_SUBSYS_NFTABLES); } static int nft_hash_init(const struct nft_set *set, const struct nft_set_desc *desc, const struct nlattr * const tb[]) { - struct nft_hash *priv = nft_set_priv(set); - struct nft_hash_table *tbl; - unsigned int size; + struct rhashtable *priv = nft_set_priv(set); + struct rhashtable_params params = { + .nelem_hint = desc->size ? : NFT_HASH_ELEMENT_HINT, + .head_offset = offsetof(struct nft_hash_elem, node), + .key_offset = offsetof(struct nft_hash_elem, key), + .key_len = set->klen, + .hashfn = jhash, + .grow_decision = rht_grow_above_75, + .shrink_decision = rht_shrink_below_30, + .mutex_is_held = lockdep_nfnl_lock_is_held, + }; - if (unlikely(!nft_hash_rnd_initted)) { - get_random_bytes(&nft_hash_rnd, 4); - nft_hash_rnd_initted = true; - } - - size = NFT_HASH_MIN_SIZE; - if (desc->size) - size = nft_hash_tbl_size(desc->size); - - tbl = nft_hash_tbl_alloc(size); - if (tbl == NULL) - return -ENOMEM; - RCU_INIT_POINTER(priv->tbl, tbl); - return 0; + return rhashtable_init(priv, ¶ms); } static void nft_hash_destroy(const struct nft_set *set) { - const struct nft_hash *priv = nft_set_priv(set); - const struct nft_hash_table *tbl = nft_dereference(priv->tbl); + const struct rhashtable *priv = nft_set_priv(set); + const struct bucket_table *tbl; struct nft_hash_elem *he, *next; unsigned int i; - for (i = 0; i < tbl->size; i++) { - for (he = nft_dereference(tbl->buckets[i]); he != NULL; - he = next) { - next = nft_dereference(he->next); + tbl = rht_dereference(priv->tbl, priv); + for (i = 0; i < tbl->size; i++) + rht_for_each_entry_safe(he, next, tbl->buckets[i], priv, node) nft_hash_elem_destroy(set, he); - } - } - kfree(tbl); + + rhashtable_destroy(priv); } static bool nft_hash_estimate(const struct nft_set_desc *desc, u32 features, @@ -383,8 +202,8 @@ static bool nft_hash_estimate(const struct nft_set_desc *desc, u32 features, esize += FIELD_SIZEOF(struct nft_hash_elem, data[0]); if (desc->size) { - est->size = sizeof(struct nft_hash) + - nft_hash_tbl_size(desc->size) * + est->size = sizeof(struct rhashtable) + + roundup_pow_of_two(desc->size * 4 / 3) * sizeof(struct nft_hash_elem *) + desc->size * esize; } else { diff --git a/net/netfilter/nft_log.c b/net/netfilter/nft_log.c index 10cfb156cdf4..bde05f28cf14 100644 --- a/net/netfilter/nft_log.c +++ b/net/netfilter/nft_log.c @@ -1,5 +1,6 @@ /* * Copyright (c) 2008-2009 Patrick McHardy <kaber@trash.net> + * Copyright (c) 2012-2014 Pablo Neira Ayuso <pablo@netfilter.org> * * This program is free software; you can redistribute it and/or modify * it under the terms of the GNU General Public License version 2 as @@ -41,6 +42,8 @@ static const struct nla_policy nft_log_policy[NFTA_LOG_MAX + 1] = { [NFTA_LOG_PREFIX] = { .type = NLA_STRING }, [NFTA_LOG_SNAPLEN] = { .type = NLA_U32 }, [NFTA_LOG_QTHRESHOLD] = { .type = NLA_U16 }, + [NFTA_LOG_LEVEL] = { .type = NLA_U32 }, + [NFTA_LOG_FLAGS] = { .type = NLA_U32 }, }; static int nft_log_init(const struct nft_ctx *ctx, @@ -50,6 +53,7 @@ static int nft_log_init(const struct nft_ctx *ctx, struct nft_log *priv = nft_expr_priv(expr); struct nf_loginfo *li = &priv->loginfo; const struct nlattr *nla; + int ret; nla = tb[NFTA_LOG_PREFIX]; if (nla != NULL) { @@ -57,30 +61,74 @@ static int nft_log_init(const struct nft_ctx *ctx, if (priv->prefix == NULL) return -ENOMEM; nla_strlcpy(priv->prefix, nla, nla_len(nla) + 1); - } else + } else { priv->prefix = (char *)nft_log_null_prefix; + } - li->type = NF_LOG_TYPE_ULOG; + li->type = NF_LOG_TYPE_LOG; + if (tb[NFTA_LOG_LEVEL] != NULL && + tb[NFTA_LOG_GROUP] != NULL) + return -EINVAL; if (tb[NFTA_LOG_GROUP] != NULL) + li->type = NF_LOG_TYPE_ULOG; + + switch (li->type) { + case NF_LOG_TYPE_LOG: + if (tb[NFTA_LOG_LEVEL] != NULL) { + li->u.log.level = + ntohl(nla_get_be32(tb[NFTA_LOG_LEVEL])); + } else { + li->u.log.level = 4; + } + if (tb[NFTA_LOG_FLAGS] != NULL) { + li->u.log.logflags = + ntohl(nla_get_be32(tb[NFTA_LOG_FLAGS])); + } + break; + case NF_LOG_TYPE_ULOG: li->u.ulog.group = ntohs(nla_get_be16(tb[NFTA_LOG_GROUP])); + if (tb[NFTA_LOG_SNAPLEN] != NULL) { + li->u.ulog.copy_len = + ntohl(nla_get_be32(tb[NFTA_LOG_SNAPLEN])); + } + if (tb[NFTA_LOG_QTHRESHOLD] != NULL) { + li->u.ulog.qthreshold = + ntohs(nla_get_be16(tb[NFTA_LOG_QTHRESHOLD])); + } + break; + } - if (tb[NFTA_LOG_SNAPLEN] != NULL) - li->u.ulog.copy_len = ntohl(nla_get_be32(tb[NFTA_LOG_SNAPLEN])); - if (tb[NFTA_LOG_QTHRESHOLD] != NULL) { - li->u.ulog.qthreshold = - ntohs(nla_get_be16(tb[NFTA_LOG_QTHRESHOLD])); + if (ctx->afi->family == NFPROTO_INET) { + ret = nf_logger_find_get(NFPROTO_IPV4, li->type); + if (ret < 0) + return ret; + + ret = nf_logger_find_get(NFPROTO_IPV6, li->type); + if (ret < 0) { + nf_logger_put(NFPROTO_IPV4, li->type); + return ret; + } + return 0; } - return 0; + return nf_logger_find_get(ctx->afi->family, li->type); } static void nft_log_destroy(const struct nft_ctx *ctx, const struct nft_expr *expr) { struct nft_log *priv = nft_expr_priv(expr); + struct nf_loginfo *li = &priv->loginfo; if (priv->prefix != nft_log_null_prefix) kfree(priv->prefix); + + if (ctx->afi->family == NFPROTO_INET) { + nf_logger_put(NFPROTO_IPV4, li->type); + nf_logger_put(NFPROTO_IPV6, li->type); + } else { + nf_logger_put(ctx->afi->family, li->type); + } } static int nft_log_dump(struct sk_buff *skb, const struct nft_expr *expr) @@ -91,17 +139,33 @@ static int nft_log_dump(struct sk_buff *skb, const struct nft_expr *expr) if (priv->prefix != nft_log_null_prefix) if (nla_put_string(skb, NFTA_LOG_PREFIX, priv->prefix)) goto nla_put_failure; - if (li->u.ulog.group) - if (nla_put_be16(skb, NFTA_LOG_GROUP, htons(li->u.ulog.group))) - goto nla_put_failure; - if (li->u.ulog.copy_len) - if (nla_put_be32(skb, NFTA_LOG_SNAPLEN, - htonl(li->u.ulog.copy_len))) + switch (li->type) { + case NF_LOG_TYPE_LOG: + if (nla_put_be32(skb, NFTA_LOG_LEVEL, htonl(li->u.log.level))) goto nla_put_failure; - if (li->u.ulog.qthreshold) - if (nla_put_be16(skb, NFTA_LOG_QTHRESHOLD, - htons(li->u.ulog.qthreshold))) + + if (li->u.log.logflags) { + if (nla_put_be32(skb, NFTA_LOG_FLAGS, + htonl(li->u.log.logflags))) + goto nla_put_failure; + } + break; + case NF_LOG_TYPE_ULOG: + if (nla_put_be16(skb, NFTA_LOG_GROUP, htons(li->u.ulog.group))) goto nla_put_failure; + + if (li->u.ulog.copy_len) { + if (nla_put_be32(skb, NFTA_LOG_SNAPLEN, + htonl(li->u.ulog.copy_len))) + goto nla_put_failure; + } + if (li->u.ulog.qthreshold) { + if (nla_put_be16(skb, NFTA_LOG_QTHRESHOLD, + htons(li->u.ulog.qthreshold))) + goto nla_put_failure; + } + break; + } return 0; nla_put_failure: diff --git a/net/netfilter/x_tables.c b/net/netfilter/x_tables.c index 227aa11e8409..47b978bc3100 100644 --- a/net/netfilter/x_tables.c +++ b/net/netfilter/x_tables.c @@ -711,28 +711,15 @@ void xt_free_table_info(struct xt_table_info *info) { int cpu; - for_each_possible_cpu(cpu) { - if (info->size <= PAGE_SIZE) - kfree(info->entries[cpu]); - else - vfree(info->entries[cpu]); - } + for_each_possible_cpu(cpu) + kvfree(info->entries[cpu]); if (info->jumpstack != NULL) { - if (sizeof(void *) * info->stacksize > PAGE_SIZE) { - for_each_possible_cpu(cpu) - vfree(info->jumpstack[cpu]); - } else { - for_each_possible_cpu(cpu) - kfree(info->jumpstack[cpu]); - } + for_each_possible_cpu(cpu) + kvfree(info->jumpstack[cpu]); + kvfree(info->jumpstack); } - if (sizeof(void **) * nr_cpu_ids > PAGE_SIZE) - vfree(info->jumpstack); - else - kfree(info->jumpstack); - free_percpu(info->stackptr); kfree(info); diff --git a/net/netfilter/xt_LED.c b/net/netfilter/xt_LED.c index 993de2ba89d3..3ba31c194cce 100644 --- a/net/netfilter/xt_LED.c +++ b/net/netfilter/xt_LED.c @@ -50,11 +50,14 @@ struct xt_led_info_internal { struct timer_list timer; }; +#define XT_LED_BLINK_DELAY 50 /* ms */ + static unsigned int led_tg(struct sk_buff *skb, const struct xt_action_param *par) { const struct xt_led_info *ledinfo = par->targinfo; struct xt_led_info_internal *ledinternal = ledinfo->internal_data; + unsigned long led_delay = XT_LED_BLINK_DELAY; /* * If "always blink" is enabled, and there's still some time until the @@ -62,9 +65,10 @@ led_tg(struct sk_buff *skb, const struct xt_action_param *par) */ if ((ledinfo->delay > 0) && ledinfo->always_blink && timer_pending(&ledinternal->timer)) - led_trigger_event(&ledinternal->netfilter_led_trigger, LED_OFF); - - led_trigger_event(&ledinternal->netfilter_led_trigger, LED_FULL); + led_trigger_blink_oneshot(&ledinternal->netfilter_led_trigger, + &led_delay, &led_delay, 1); + else + led_trigger_event(&ledinternal->netfilter_led_trigger, LED_FULL); /* If there's a positive delay, start/update the timer */ if (ledinfo->delay > 0) { @@ -133,9 +137,7 @@ static int led_tg_check(const struct xt_tgchk_param *par) err = led_trigger_register(&ledinternal->netfilter_led_trigger); if (err) { - pr_warning("led_trigger_register() failed\n"); - if (err == -EEXIST) - pr_warning("Trigger name is already in use.\n"); + pr_err("Trigger name is already in use.\n"); goto exit_alloc; } diff --git a/net/netfilter/xt_LOG.c b/net/netfilter/xt_LOG.c index 5ab24843370a..c13b79440ede 100644 --- a/net/netfilter/xt_LOG.c +++ b/net/netfilter/xt_LOG.c @@ -27,806 +27,6 @@ #include <linux/netfilter/xt_LOG.h> #include <linux/netfilter_ipv6/ip6_tables.h> #include <net/netfilter/nf_log.h> -#include <net/netfilter/xt_log.h> - -static struct nf_loginfo default_loginfo = { - .type = NF_LOG_TYPE_LOG, - .u = { - .log = { - .level = 5, - .logflags = NF_LOG_MASK, - }, - }, -}; - -static int dump_udp_header(struct sbuff *m, const struct sk_buff *skb, - u8 proto, int fragment, unsigned int offset) -{ - struct udphdr _udph; - const struct udphdr *uh; - - if (proto == IPPROTO_UDP) - /* Max length: 10 "PROTO=UDP " */ - sb_add(m, "PROTO=UDP "); - else /* Max length: 14 "PROTO=UDPLITE " */ - sb_add(m, "PROTO=UDPLITE "); - - if (fragment) - goto out; - - /* Max length: 25 "INCOMPLETE [65535 bytes] " */ - uh = skb_header_pointer(skb, offset, sizeof(_udph), &_udph); - if (uh == NULL) { - sb_add(m, "INCOMPLETE [%u bytes] ", skb->len - offset); - - return 1; - } - - /* Max length: 20 "SPT=65535 DPT=65535 " */ - sb_add(m, "SPT=%u DPT=%u LEN=%u ", ntohs(uh->source), ntohs(uh->dest), - ntohs(uh->len)); - -out: - return 0; -} - -static int dump_tcp_header(struct sbuff *m, const struct sk_buff *skb, - u8 proto, int fragment, unsigned int offset, - unsigned int logflags) -{ - struct tcphdr _tcph; - const struct tcphdr *th; - - /* Max length: 10 "PROTO=TCP " */ - sb_add(m, "PROTO=TCP "); - - if (fragment) - return 0; - - /* Max length: 25 "INCOMPLETE [65535 bytes] " */ - th = skb_header_pointer(skb, offset, sizeof(_tcph), &_tcph); - if (th == NULL) { - sb_add(m, "INCOMPLETE [%u bytes] ", skb->len - offset); - return 1; - } - - /* Max length: 20 "SPT=65535 DPT=65535 " */ - sb_add(m, "SPT=%u DPT=%u ", ntohs(th->source), ntohs(th->dest)); - /* Max length: 30 "SEQ=4294967295 ACK=4294967295 " */ - if (logflags & XT_LOG_TCPSEQ) - sb_add(m, "SEQ=%u ACK=%u ", ntohl(th->seq), ntohl(th->ack_seq)); - - /* Max length: 13 "WINDOW=65535 " */ - sb_add(m, "WINDOW=%u ", ntohs(th->window)); - /* Max length: 9 "RES=0x3C " */ - sb_add(m, "RES=0x%02x ", (u_int8_t)(ntohl(tcp_flag_word(th) & - TCP_RESERVED_BITS) >> 22)); - /* Max length: 32 "CWR ECE URG ACK PSH RST SYN FIN " */ - if (th->cwr) - sb_add(m, "CWR "); - if (th->ece) - sb_add(m, "ECE "); - if (th->urg) - sb_add(m, "URG "); - if (th->ack) - sb_add(m, "ACK "); - if (th->psh) - sb_add(m, "PSH "); - if (th->rst) - sb_add(m, "RST "); - if (th->syn) - sb_add(m, "SYN "); - if (th->fin) - sb_add(m, "FIN "); - /* Max length: 11 "URGP=65535 " */ - sb_add(m, "URGP=%u ", ntohs(th->urg_ptr)); - - if ((logflags & XT_LOG_TCPOPT) && th->doff*4 > sizeof(struct tcphdr)) { - u_int8_t _opt[60 - sizeof(struct tcphdr)]; - const u_int8_t *op; - unsigned int i; - unsigned int optsize = th->doff*4 - sizeof(struct tcphdr); - - op = skb_header_pointer(skb, offset + sizeof(struct tcphdr), - optsize, _opt); - if (op == NULL) { - sb_add(m, "OPT (TRUNCATED)"); - return 1; - } - - /* Max length: 127 "OPT (" 15*4*2chars ") " */ - sb_add(m, "OPT ("); - for (i = 0; i < optsize; i++) - sb_add(m, "%02X", op[i]); - - sb_add(m, ") "); - } - - return 0; -} - -static void dump_sk_uid_gid(struct sbuff *m, struct sock *sk) -{ - if (!sk || sk->sk_state == TCP_TIME_WAIT) - return; - - read_lock_bh(&sk->sk_callback_lock); - if (sk->sk_socket && sk->sk_socket->file) { - const struct cred *cred = sk->sk_socket->file->f_cred; - sb_add(m, "UID=%u GID=%u ", - from_kuid_munged(&init_user_ns, cred->fsuid), - from_kgid_munged(&init_user_ns, cred->fsgid)); - } - read_unlock_bh(&sk->sk_callback_lock); -} - -/* One level of recursion won't kill us */ -static void dump_ipv4_packet(struct sbuff *m, - const struct nf_loginfo *info, - const struct sk_buff *skb, - unsigned int iphoff) -{ - struct iphdr _iph; - const struct iphdr *ih; - unsigned int logflags; - - if (info->type == NF_LOG_TYPE_LOG) - logflags = info->u.log.logflags; - else - logflags = NF_LOG_MASK; - - ih = skb_header_pointer(skb, iphoff, sizeof(_iph), &_iph); - if (ih == NULL) { - sb_add(m, "TRUNCATED"); - return; - } - - /* Important fields: - * TOS, len, DF/MF, fragment offset, TTL, src, dst, options. */ - /* Max length: 40 "SRC=255.255.255.255 DST=255.255.255.255 " */ - sb_add(m, "SRC=%pI4 DST=%pI4 ", - &ih->saddr, &ih->daddr); - - /* Max length: 46 "LEN=65535 TOS=0xFF PREC=0xFF TTL=255 ID=65535 " */ - sb_add(m, "LEN=%u TOS=0x%02X PREC=0x%02X TTL=%u ID=%u ", - ntohs(ih->tot_len), ih->tos & IPTOS_TOS_MASK, - ih->tos & IPTOS_PREC_MASK, ih->ttl, ntohs(ih->id)); - - /* Max length: 6 "CE DF MF " */ - if (ntohs(ih->frag_off) & IP_CE) - sb_add(m, "CE "); - if (ntohs(ih->frag_off) & IP_DF) - sb_add(m, "DF "); - if (ntohs(ih->frag_off) & IP_MF) - sb_add(m, "MF "); - - /* Max length: 11 "FRAG:65535 " */ - if (ntohs(ih->frag_off) & IP_OFFSET) - sb_add(m, "FRAG:%u ", ntohs(ih->frag_off) & IP_OFFSET); - - if ((logflags & XT_LOG_IPOPT) && - ih->ihl * 4 > sizeof(struct iphdr)) { - const unsigned char *op; - unsigned char _opt[4 * 15 - sizeof(struct iphdr)]; - unsigned int i, optsize; - - optsize = ih->ihl * 4 - sizeof(struct iphdr); - op = skb_header_pointer(skb, iphoff+sizeof(_iph), - optsize, _opt); - if (op == NULL) { - sb_add(m, "TRUNCATED"); - return; - } - - /* Max length: 127 "OPT (" 15*4*2chars ") " */ - sb_add(m, "OPT ("); - for (i = 0; i < optsize; i++) - sb_add(m, "%02X", op[i]); - sb_add(m, ") "); - } - - switch (ih->protocol) { - case IPPROTO_TCP: - if (dump_tcp_header(m, skb, ih->protocol, - ntohs(ih->frag_off) & IP_OFFSET, - iphoff+ih->ihl*4, logflags)) - return; - break; - case IPPROTO_UDP: - case IPPROTO_UDPLITE: - if (dump_udp_header(m, skb, ih->protocol, - ntohs(ih->frag_off) & IP_OFFSET, - iphoff+ih->ihl*4)) - return; - break; - case IPPROTO_ICMP: { - struct icmphdr _icmph; - const struct icmphdr *ich; - static const size_t required_len[NR_ICMP_TYPES+1] - = { [ICMP_ECHOREPLY] = 4, - [ICMP_DEST_UNREACH] - = 8 + sizeof(struct iphdr), - [ICMP_SOURCE_QUENCH] - = 8 + sizeof(struct iphdr), - [ICMP_REDIRECT] - = 8 + sizeof(struct iphdr), - [ICMP_ECHO] = 4, - [ICMP_TIME_EXCEEDED] - = 8 + sizeof(struct iphdr), - [ICMP_PARAMETERPROB] - = 8 + sizeof(struct iphdr), - [ICMP_TIMESTAMP] = 20, - [ICMP_TIMESTAMPREPLY] = 20, - [ICMP_ADDRESS] = 12, - [ICMP_ADDRESSREPLY] = 12 }; - - /* Max length: 11 "PROTO=ICMP " */ - sb_add(m, "PROTO=ICMP "); - - if (ntohs(ih->frag_off) & IP_OFFSET) - break; - - /* Max length: 25 "INCOMPLETE [65535 bytes] " */ - ich = skb_header_pointer(skb, iphoff + ih->ihl * 4, - sizeof(_icmph), &_icmph); - if (ich == NULL) { - sb_add(m, "INCOMPLETE [%u bytes] ", - skb->len - iphoff - ih->ihl*4); - break; - } - - /* Max length: 18 "TYPE=255 CODE=255 " */ - sb_add(m, "TYPE=%u CODE=%u ", ich->type, ich->code); - - /* Max length: 25 "INCOMPLETE [65535 bytes] " */ - if (ich->type <= NR_ICMP_TYPES && - required_len[ich->type] && - skb->len-iphoff-ih->ihl*4 < required_len[ich->type]) { - sb_add(m, "INCOMPLETE [%u bytes] ", - skb->len - iphoff - ih->ihl*4); - break; - } - - switch (ich->type) { - case ICMP_ECHOREPLY: - case ICMP_ECHO: - /* Max length: 19 "ID=65535 SEQ=65535 " */ - sb_add(m, "ID=%u SEQ=%u ", - ntohs(ich->un.echo.id), - ntohs(ich->un.echo.sequence)); - break; - - case ICMP_PARAMETERPROB: - /* Max length: 14 "PARAMETER=255 " */ - sb_add(m, "PARAMETER=%u ", - ntohl(ich->un.gateway) >> 24); - break; - case ICMP_REDIRECT: - /* Max length: 24 "GATEWAY=255.255.255.255 " */ - sb_add(m, "GATEWAY=%pI4 ", &ich->un.gateway); - /* Fall through */ - case ICMP_DEST_UNREACH: - case ICMP_SOURCE_QUENCH: - case ICMP_TIME_EXCEEDED: - /* Max length: 3+maxlen */ - if (!iphoff) { /* Only recurse once. */ - sb_add(m, "["); - dump_ipv4_packet(m, info, skb, - iphoff + ih->ihl*4+sizeof(_icmph)); - sb_add(m, "] "); - } - - /* Max length: 10 "MTU=65535 " */ - if (ich->type == ICMP_DEST_UNREACH && - ich->code == ICMP_FRAG_NEEDED) - sb_add(m, "MTU=%u ", ntohs(ich->un.frag.mtu)); - } - break; - } - /* Max Length */ - case IPPROTO_AH: { - struct ip_auth_hdr _ahdr; - const struct ip_auth_hdr *ah; - - if (ntohs(ih->frag_off) & IP_OFFSET) - break; - - /* Max length: 9 "PROTO=AH " */ - sb_add(m, "PROTO=AH "); - - /* Max length: 25 "INCOMPLETE [65535 bytes] " */ - ah = skb_header_pointer(skb, iphoff+ih->ihl*4, - sizeof(_ahdr), &_ahdr); - if (ah == NULL) { - sb_add(m, "INCOMPLETE [%u bytes] ", - skb->len - iphoff - ih->ihl*4); - break; - } - - /* Length: 15 "SPI=0xF1234567 " */ - sb_add(m, "SPI=0x%x ", ntohl(ah->spi)); - break; - } - case IPPROTO_ESP: { - struct ip_esp_hdr _esph; - const struct ip_esp_hdr *eh; - - /* Max length: 10 "PROTO=ESP " */ - sb_add(m, "PROTO=ESP "); - - if (ntohs(ih->frag_off) & IP_OFFSET) - break; - - /* Max length: 25 "INCOMPLETE [65535 bytes] " */ - eh = skb_header_pointer(skb, iphoff+ih->ihl*4, - sizeof(_esph), &_esph); - if (eh == NULL) { - sb_add(m, "INCOMPLETE [%u bytes] ", - skb->len - iphoff - ih->ihl*4); - break; - } - - /* Length: 15 "SPI=0xF1234567 " */ - sb_add(m, "SPI=0x%x ", ntohl(eh->spi)); - break; - } - /* Max length: 10 "PROTO 255 " */ - default: - sb_add(m, "PROTO=%u ", ih->protocol); - } - - /* Max length: 15 "UID=4294967295 " */ - if ((logflags & XT_LOG_UID) && !iphoff) - dump_sk_uid_gid(m, skb->sk); - - /* Max length: 16 "MARK=0xFFFFFFFF " */ - if (!iphoff && skb->mark) - sb_add(m, "MARK=0x%x ", skb->mark); - - /* Proto Max log string length */ - /* IP: 40+46+6+11+127 = 230 */ - /* TCP: 10+max(25,20+30+13+9+32+11+127) = 252 */ - /* UDP: 10+max(25,20) = 35 */ - /* UDPLITE: 14+max(25,20) = 39 */ - /* ICMP: 11+max(25, 18+25+max(19,14,24+3+n+10,3+n+10)) = 91+n */ - /* ESP: 10+max(25)+15 = 50 */ - /* AH: 9+max(25)+15 = 49 */ - /* unknown: 10 */ - - /* (ICMP allows recursion one level deep) */ - /* maxlen = IP + ICMP + IP + max(TCP,UDP,ICMP,unknown) */ - /* maxlen = 230+ 91 + 230 + 252 = 803 */ -} - -static void dump_ipv4_mac_header(struct sbuff *m, - const struct nf_loginfo *info, - const struct sk_buff *skb) -{ - struct net_device *dev = skb->dev; - unsigned int logflags = 0; - - if (info->type == NF_LOG_TYPE_LOG) - logflags = info->u.log.logflags; - - if (!(logflags & XT_LOG_MACDECODE)) - goto fallback; - - switch (dev->type) { - case ARPHRD_ETHER: - sb_add(m, "MACSRC=%pM MACDST=%pM MACPROTO=%04x ", - eth_hdr(skb)->h_source, eth_hdr(skb)->h_dest, - ntohs(eth_hdr(skb)->h_proto)); - return; - default: - break; - } - -fallback: - sb_add(m, "MAC="); - if (dev->hard_header_len && - skb->mac_header != skb->network_header) { - const unsigned char *p = skb_mac_header(skb); - unsigned int i; - - sb_add(m, "%02x", *p++); - for (i = 1; i < dev->hard_header_len; i++, p++) - sb_add(m, ":%02x", *p); - } - sb_add(m, " "); -} - -static void -log_packet_common(struct sbuff *m, - u_int8_t pf, - unsigned int hooknum, - const struct sk_buff *skb, - const struct net_device *in, - const struct net_device *out, - const struct nf_loginfo *loginfo, - const char *prefix) -{ - sb_add(m, KERN_SOH "%c%sIN=%s OUT=%s ", - '0' + loginfo->u.log.level, prefix, - in ? in->name : "", - out ? out->name : ""); -#ifdef CONFIG_BRIDGE_NETFILTER - if (skb->nf_bridge) { - const struct net_device *physindev; - const struct net_device *physoutdev; - - physindev = skb->nf_bridge->physindev; - if (physindev && in != physindev) - sb_add(m, "PHYSIN=%s ", physindev->name); - physoutdev = skb->nf_bridge->physoutdev; - if (physoutdev && out != physoutdev) - sb_add(m, "PHYSOUT=%s ", physoutdev->name); - } -#endif -} - - -static void -ipt_log_packet(struct net *net, - u_int8_t pf, - unsigned int hooknum, - const struct sk_buff *skb, - const struct net_device *in, - const struct net_device *out, - const struct nf_loginfo *loginfo, - const char *prefix) -{ - struct sbuff *m; - - /* FIXME: Disabled from containers until syslog ns is supported */ - if (!net_eq(net, &init_net)) - return; - - m = sb_open(); - - if (!loginfo) - loginfo = &default_loginfo; - - log_packet_common(m, pf, hooknum, skb, in, out, loginfo, prefix); - - if (in != NULL) - dump_ipv4_mac_header(m, loginfo, skb); - - dump_ipv4_packet(m, loginfo, skb, 0); - - sb_close(m); -} - -#if IS_ENABLED(CONFIG_IP6_NF_IPTABLES) -/* One level of recursion won't kill us */ -static void dump_ipv6_packet(struct sbuff *m, - const struct nf_loginfo *info, - const struct sk_buff *skb, unsigned int ip6hoff, - int recurse) -{ - u_int8_t currenthdr; - int fragment; - struct ipv6hdr _ip6h; - const struct ipv6hdr *ih; - unsigned int ptr; - unsigned int hdrlen = 0; - unsigned int logflags; - - if (info->type == NF_LOG_TYPE_LOG) - logflags = info->u.log.logflags; - else - logflags = NF_LOG_MASK; - - ih = skb_header_pointer(skb, ip6hoff, sizeof(_ip6h), &_ip6h); - if (ih == NULL) { - sb_add(m, "TRUNCATED"); - return; - } - - /* Max length: 88 "SRC=0000.0000.0000.0000.0000.0000.0000.0000 DST=0000.0000.0000.0000.0000.0000.0000.0000 " */ - sb_add(m, "SRC=%pI6 DST=%pI6 ", &ih->saddr, &ih->daddr); - - /* Max length: 44 "LEN=65535 TC=255 HOPLIMIT=255 FLOWLBL=FFFFF " */ - sb_add(m, "LEN=%Zu TC=%u HOPLIMIT=%u FLOWLBL=%u ", - ntohs(ih->payload_len) + sizeof(struct ipv6hdr), - (ntohl(*(__be32 *)ih) & 0x0ff00000) >> 20, - ih->hop_limit, - (ntohl(*(__be32 *)ih) & 0x000fffff)); - - fragment = 0; - ptr = ip6hoff + sizeof(struct ipv6hdr); - currenthdr = ih->nexthdr; - while (currenthdr != NEXTHDR_NONE && ip6t_ext_hdr(currenthdr)) { - struct ipv6_opt_hdr _hdr; - const struct ipv6_opt_hdr *hp; - - hp = skb_header_pointer(skb, ptr, sizeof(_hdr), &_hdr); - if (hp == NULL) { - sb_add(m, "TRUNCATED"); - return; - } - - /* Max length: 48 "OPT (...) " */ - if (logflags & XT_LOG_IPOPT) - sb_add(m, "OPT ( "); - - switch (currenthdr) { - case IPPROTO_FRAGMENT: { - struct frag_hdr _fhdr; - const struct frag_hdr *fh; - - sb_add(m, "FRAG:"); - fh = skb_header_pointer(skb, ptr, sizeof(_fhdr), - &_fhdr); - if (fh == NULL) { - sb_add(m, "TRUNCATED "); - return; - } - - /* Max length: 6 "65535 " */ - sb_add(m, "%u ", ntohs(fh->frag_off) & 0xFFF8); - - /* Max length: 11 "INCOMPLETE " */ - if (fh->frag_off & htons(0x0001)) - sb_add(m, "INCOMPLETE "); - - sb_add(m, "ID:%08x ", ntohl(fh->identification)); - - if (ntohs(fh->frag_off) & 0xFFF8) - fragment = 1; - - hdrlen = 8; - - break; - } - case IPPROTO_DSTOPTS: - case IPPROTO_ROUTING: - case IPPROTO_HOPOPTS: - if (fragment) { - if (logflags & XT_LOG_IPOPT) - sb_add(m, ")"); - return; - } - hdrlen = ipv6_optlen(hp); - break; - /* Max Length */ - case IPPROTO_AH: - if (logflags & XT_LOG_IPOPT) { - struct ip_auth_hdr _ahdr; - const struct ip_auth_hdr *ah; - - /* Max length: 3 "AH " */ - sb_add(m, "AH "); - - if (fragment) { - sb_add(m, ")"); - return; - } - - ah = skb_header_pointer(skb, ptr, sizeof(_ahdr), - &_ahdr); - if (ah == NULL) { - /* - * Max length: 26 "INCOMPLETE [65535 - * bytes] )" - */ - sb_add(m, "INCOMPLETE [%u bytes] )", - skb->len - ptr); - return; - } - - /* Length: 15 "SPI=0xF1234567 */ - sb_add(m, "SPI=0x%x ", ntohl(ah->spi)); - - } - - hdrlen = (hp->hdrlen+2)<<2; - break; - case IPPROTO_ESP: - if (logflags & XT_LOG_IPOPT) { - struct ip_esp_hdr _esph; - const struct ip_esp_hdr *eh; - - /* Max length: 4 "ESP " */ - sb_add(m, "ESP "); - - if (fragment) { - sb_add(m, ")"); - return; - } - - /* - * Max length: 26 "INCOMPLETE [65535 bytes] )" - */ - eh = skb_header_pointer(skb, ptr, sizeof(_esph), - &_esph); - if (eh == NULL) { - sb_add(m, "INCOMPLETE [%u bytes] )", - skb->len - ptr); - return; - } - - /* Length: 16 "SPI=0xF1234567 )" */ - sb_add(m, "SPI=0x%x )", ntohl(eh->spi)); - - } - return; - default: - /* Max length: 20 "Unknown Ext Hdr 255" */ - sb_add(m, "Unknown Ext Hdr %u", currenthdr); - return; - } - if (logflags & XT_LOG_IPOPT) - sb_add(m, ") "); - - currenthdr = hp->nexthdr; - ptr += hdrlen; - } - - switch (currenthdr) { - case IPPROTO_TCP: - if (dump_tcp_header(m, skb, currenthdr, fragment, ptr, - logflags)) - return; - break; - case IPPROTO_UDP: - case IPPROTO_UDPLITE: - if (dump_udp_header(m, skb, currenthdr, fragment, ptr)) - return; - break; - case IPPROTO_ICMPV6: { - struct icmp6hdr _icmp6h; - const struct icmp6hdr *ic; - - /* Max length: 13 "PROTO=ICMPv6 " */ - sb_add(m, "PROTO=ICMPv6 "); - - if (fragment) - break; - - /* Max length: 25 "INCOMPLETE [65535 bytes] " */ - ic = skb_header_pointer(skb, ptr, sizeof(_icmp6h), &_icmp6h); - if (ic == NULL) { - sb_add(m, "INCOMPLETE [%u bytes] ", skb->len - ptr); - return; - } - - /* Max length: 18 "TYPE=255 CODE=255 " */ - sb_add(m, "TYPE=%u CODE=%u ", ic->icmp6_type, ic->icmp6_code); - - switch (ic->icmp6_type) { - case ICMPV6_ECHO_REQUEST: - case ICMPV6_ECHO_REPLY: - /* Max length: 19 "ID=65535 SEQ=65535 " */ - sb_add(m, "ID=%u SEQ=%u ", - ntohs(ic->icmp6_identifier), - ntohs(ic->icmp6_sequence)); - break; - case ICMPV6_MGM_QUERY: - case ICMPV6_MGM_REPORT: - case ICMPV6_MGM_REDUCTION: - break; - - case ICMPV6_PARAMPROB: - /* Max length: 17 "POINTER=ffffffff " */ - sb_add(m, "POINTER=%08x ", ntohl(ic->icmp6_pointer)); - /* Fall through */ - case ICMPV6_DEST_UNREACH: - case ICMPV6_PKT_TOOBIG: - case ICMPV6_TIME_EXCEED: - /* Max length: 3+maxlen */ - if (recurse) { - sb_add(m, "["); - dump_ipv6_packet(m, info, skb, - ptr + sizeof(_icmp6h), 0); - sb_add(m, "] "); - } - - /* Max length: 10 "MTU=65535 " */ - if (ic->icmp6_type == ICMPV6_PKT_TOOBIG) - sb_add(m, "MTU=%u ", ntohl(ic->icmp6_mtu)); - } - break; - } - /* Max length: 10 "PROTO=255 " */ - default: - sb_add(m, "PROTO=%u ", currenthdr); - } - - /* Max length: 15 "UID=4294967295 " */ - if ((logflags & XT_LOG_UID) && recurse) - dump_sk_uid_gid(m, skb->sk); - - /* Max length: 16 "MARK=0xFFFFFFFF " */ - if (recurse && skb->mark) - sb_add(m, "MARK=0x%x ", skb->mark); -} - -static void dump_ipv6_mac_header(struct sbuff *m, - const struct nf_loginfo *info, - const struct sk_buff *skb) -{ - struct net_device *dev = skb->dev; - unsigned int logflags = 0; - - if (info->type == NF_LOG_TYPE_LOG) - logflags = info->u.log.logflags; - - if (!(logflags & XT_LOG_MACDECODE)) - goto fallback; - - switch (dev->type) { - case ARPHRD_ETHER: - sb_add(m, "MACSRC=%pM MACDST=%pM MACPROTO=%04x ", - eth_hdr(skb)->h_source, eth_hdr(skb)->h_dest, - ntohs(eth_hdr(skb)->h_proto)); - return; - default: - break; - } - -fallback: - sb_add(m, "MAC="); - if (dev->hard_header_len && - skb->mac_header != skb->network_header) { - const unsigned char *p = skb_mac_header(skb); - unsigned int len = dev->hard_header_len; - unsigned int i; - - if (dev->type == ARPHRD_SIT) { - p -= ETH_HLEN; - - if (p < skb->head) - p = NULL; - } - - if (p != NULL) { - sb_add(m, "%02x", *p++); - for (i = 1; i < len; i++) - sb_add(m, ":%02x", *p++); - } - sb_add(m, " "); - - if (dev->type == ARPHRD_SIT) { - const struct iphdr *iph = - (struct iphdr *)skb_mac_header(skb); - sb_add(m, "TUNNEL=%pI4->%pI4 ", &iph->saddr, - &iph->daddr); - } - } else - sb_add(m, " "); -} - -static void -ip6t_log_packet(struct net *net, - u_int8_t pf, - unsigned int hooknum, - const struct sk_buff *skb, - const struct net_device *in, - const struct net_device *out, - const struct nf_loginfo *loginfo, - const char *prefix) -{ - struct sbuff *m; - - /* FIXME: Disabled from containers until syslog ns is supported */ - if (!net_eq(net, &init_net)) - return; - - m = sb_open(); - - if (!loginfo) - loginfo = &default_loginfo; - - log_packet_common(m, pf, hooknum, skb, in, out, loginfo, prefix); - - if (in != NULL) - dump_ipv6_mac_header(m, loginfo, skb); - - dump_ipv6_packet(m, loginfo, skb, skb_network_offset(skb), 1); - - sb_close(m); -} -#endif static unsigned int log_tg(struct sk_buff *skb, const struct xt_action_param *par) @@ -839,17 +39,8 @@ log_tg(struct sk_buff *skb, const struct xt_action_param *par) li.u.log.level = loginfo->level; li.u.log.logflags = loginfo->logflags; - if (par->family == NFPROTO_IPV4) - ipt_log_packet(net, NFPROTO_IPV4, par->hooknum, skb, par->in, - par->out, &li, loginfo->prefix); -#if IS_ENABLED(CONFIG_IP6_NF_IPTABLES) - else if (par->family == NFPROTO_IPV6) - ip6t_log_packet(net, NFPROTO_IPV6, par->hooknum, skb, par->in, - par->out, &li, loginfo->prefix); -#endif - else - WARN_ON_ONCE(1); - + nf_log_packet(net, par->family, par->hooknum, skb, par->in, par->out, + &li, "%s", loginfo->prefix); return XT_CONTINUE; } @@ -870,7 +61,12 @@ static int log_tg_check(const struct xt_tgchk_param *par) return -EINVAL; } - return 0; + return nf_logger_find_get(par->family, NF_LOG_TYPE_LOG); +} + +static void log_tg_destroy(const struct xt_tgdtor_param *par) +{ + nf_logger_put(par->family, NF_LOG_TYPE_LOG); } static struct xt_target log_tg_regs[] __read_mostly = { @@ -880,6 +76,7 @@ static struct xt_target log_tg_regs[] __read_mostly = { .target = log_tg, .targetsize = sizeof(struct xt_log_info), .checkentry = log_tg_check, + .destroy = log_tg_destroy, .me = THIS_MODULE, }, #if IS_ENABLED(CONFIG_IP6_NF_IPTABLES) @@ -889,78 +86,19 @@ static struct xt_target log_tg_regs[] __read_mostly = { .target = log_tg, .targetsize = sizeof(struct xt_log_info), .checkentry = log_tg_check, + .destroy = log_tg_destroy, .me = THIS_MODULE, }, #endif }; -static struct nf_logger ipt_log_logger __read_mostly = { - .name = "ipt_LOG", - .logfn = &ipt_log_packet, - .me = THIS_MODULE, -}; - -#if IS_ENABLED(CONFIG_IP6_NF_IPTABLES) -static struct nf_logger ip6t_log_logger __read_mostly = { - .name = "ip6t_LOG", - .logfn = &ip6t_log_packet, - .me = THIS_MODULE, -}; -#endif - -static int __net_init log_net_init(struct net *net) -{ - nf_log_set(net, NFPROTO_IPV4, &ipt_log_logger); -#if IS_ENABLED(CONFIG_IP6_NF_IPTABLES) - nf_log_set(net, NFPROTO_IPV6, &ip6t_log_logger); -#endif - return 0; -} - -static void __net_exit log_net_exit(struct net *net) -{ - nf_log_unset(net, &ipt_log_logger); -#if IS_ENABLED(CONFIG_IP6_NF_IPTABLES) - nf_log_unset(net, &ip6t_log_logger); -#endif -} - -static struct pernet_operations log_net_ops = { - .init = log_net_init, - .exit = log_net_exit, -}; - static int __init log_tg_init(void) { - int ret; - - ret = register_pernet_subsys(&log_net_ops); - if (ret < 0) - goto err_pernet; - - ret = xt_register_targets(log_tg_regs, ARRAY_SIZE(log_tg_regs)); - if (ret < 0) - goto err_target; - - nf_log_register(NFPROTO_IPV4, &ipt_log_logger); -#if IS_ENABLED(CONFIG_IP6_NF_IPTABLES) - nf_log_register(NFPROTO_IPV6, &ip6t_log_logger); -#endif - return 0; - -err_target: - unregister_pernet_subsys(&log_net_ops); -err_pernet: - return ret; + return xt_register_targets(log_tg_regs, ARRAY_SIZE(log_tg_regs)); } static void __exit log_tg_exit(void) { - unregister_pernet_subsys(&log_net_ops); - nf_log_unregister(&ipt_log_logger); -#if IS_ENABLED(CONFIG_IP6_NF_IPTABLES) - nf_log_unregister(&ip6t_log_logger); -#endif xt_unregister_targets(log_tg_regs, ARRAY_SIZE(log_tg_regs)); } diff --git a/net/netfilter/xt_bpf.c b/net/netfilter/xt_bpf.c index bbffdbdaf603..dffee9d47ec4 100644 --- a/net/netfilter/xt_bpf.c +++ b/net/netfilter/xt_bpf.c @@ -28,7 +28,7 @@ static int bpf_mt_check(const struct xt_mtchk_param *par) program.len = info->bpf_program_num_elem; program.filter = info->bpf_program; - if (sk_unattached_filter_create(&info->filter, &program)) { + if (bpf_prog_create(&info->filter, &program)) { pr_info("bpf: check failed: parse error\n"); return -EINVAL; } @@ -40,13 +40,13 @@ static bool bpf_mt(const struct sk_buff *skb, struct xt_action_param *par) { const struct xt_bpf_info *info = par->matchinfo; - return SK_RUN_FILTER(info->filter, skb); + return BPF_PROG_RUN(info->filter, skb); } static void bpf_mt_destroy(const struct xt_mtdtor_param *par) { const struct xt_bpf_info *info = par->matchinfo; - sk_unattached_filter_destroy(info->filter); + bpf_prog_destroy(info->filter); } static struct xt_match bpf_mt_reg __read_mostly = { diff --git a/net/netfilter/xt_hashlimit.c b/net/netfilter/xt_hashlimit.c index a3910fc2122b..47dc6836830a 100644 --- a/net/netfilter/xt_hashlimit.c +++ b/net/netfilter/xt_hashlimit.c @@ -104,7 +104,7 @@ struct xt_hashlimit_htable { spinlock_t lock; /* lock for list_head */ u_int32_t rnd; /* random seed for hash */ unsigned int count; /* number entries in table */ - struct timer_list timer; /* timer for gc */ + struct delayed_work gc_work; /* seq_file stuff */ struct proc_dir_entry *pde; @@ -213,7 +213,7 @@ dsthash_free(struct xt_hashlimit_htable *ht, struct dsthash_ent *ent) call_rcu_bh(&ent->rcu, dsthash_free_rcu); ht->count--; } -static void htable_gc(unsigned long htlong); +static void htable_gc(struct work_struct *work); static int htable_create(struct net *net, struct xt_hashlimit_mtinfo1 *minfo, u_int8_t family) @@ -273,9 +273,9 @@ static int htable_create(struct net *net, struct xt_hashlimit_mtinfo1 *minfo, } hinfo->net = net; - setup_timer(&hinfo->timer, htable_gc, (unsigned long)hinfo); - hinfo->timer.expires = jiffies + msecs_to_jiffies(hinfo->cfg.gc_interval); - add_timer(&hinfo->timer); + INIT_DEFERRABLE_WORK(&hinfo->gc_work, htable_gc); + queue_delayed_work(system_power_efficient_wq, &hinfo->gc_work, + msecs_to_jiffies(hinfo->cfg.gc_interval)); hlist_add_head(&hinfo->node, &hashlimit_net->htables); @@ -300,29 +300,30 @@ static void htable_selective_cleanup(struct xt_hashlimit_htable *ht, { unsigned int i; - /* lock hash table and iterate over it */ - spin_lock_bh(&ht->lock); for (i = 0; i < ht->cfg.size; i++) { struct dsthash_ent *dh; struct hlist_node *n; + + spin_lock_bh(&ht->lock); hlist_for_each_entry_safe(dh, n, &ht->hash[i], node) { if ((*select)(ht, dh)) dsthash_free(ht, dh); } + spin_unlock_bh(&ht->lock); + cond_resched(); } - spin_unlock_bh(&ht->lock); } -/* hash table garbage collector, run by timer */ -static void htable_gc(unsigned long htlong) +static void htable_gc(struct work_struct *work) { - struct xt_hashlimit_htable *ht = (struct xt_hashlimit_htable *)htlong; + struct xt_hashlimit_htable *ht; + + ht = container_of(work, struct xt_hashlimit_htable, gc_work.work); htable_selective_cleanup(ht, select_gc); - /* re-add the timer accordingly */ - ht->timer.expires = jiffies + msecs_to_jiffies(ht->cfg.gc_interval); - add_timer(&ht->timer); + queue_delayed_work(system_power_efficient_wq, + &ht->gc_work, msecs_to_jiffies(ht->cfg.gc_interval)); } static void htable_remove_proc_entry(struct xt_hashlimit_htable *hinfo) @@ -341,7 +342,7 @@ static void htable_remove_proc_entry(struct xt_hashlimit_htable *hinfo) static void htable_destroy(struct xt_hashlimit_htable *hinfo) { - del_timer_sync(&hinfo->timer); + cancel_delayed_work_sync(&hinfo->gc_work); htable_remove_proc_entry(hinfo); htable_selective_cleanup(hinfo, select_all); kfree(hinfo->name); diff --git a/net/netlabel/netlabel_kapi.c b/net/netlabel/netlabel_kapi.c index 05ea4a4cc0ac..0b4692dd1c5e 100644 --- a/net/netlabel/netlabel_kapi.c +++ b/net/netlabel/netlabel_kapi.c @@ -170,7 +170,6 @@ int netlbl_cfg_unlbl_map_add(const char *domain, #endif /* IPv6 */ default: goto cfg_unlbl_map_add_failure; - break; } entry->def.addrsel = addrmap; diff --git a/net/netlink/af_netlink.c b/net/netlink/af_netlink.c index e6fac7e3db52..479a344563d8 100644 --- a/net/netlink/af_netlink.c +++ b/net/netlink/af_netlink.c @@ -58,7 +58,9 @@ #include <linux/mutex.h> #include <linux/vmalloc.h> #include <linux/if_arp.h> +#include <linux/rhashtable.h> #include <asm/cacheflush.h> +#include <linux/hash.h> #include <net/net_namespace.h> #include <net/sock.h> @@ -100,6 +102,18 @@ static atomic_t nl_table_users = ATOMIC_INIT(0); #define nl_deref_protected(X) rcu_dereference_protected(X, lockdep_is_held(&nl_table_lock)); +/* Protects netlink socket hash table mutations */ +DEFINE_MUTEX(nl_sk_hash_lock); + +static int lockdep_nl_sk_hash_is_held(void) +{ +#ifdef CONFIG_LOCKDEP + return (debug_locks) ? lockdep_is_held(&nl_sk_hash_lock) : 1; +#else + return 1; +#endif +} + static ATOMIC_NOTIFIER_HEAD(netlink_chain); static DEFINE_SPINLOCK(netlink_tap_lock); @@ -110,11 +124,6 @@ static inline u32 netlink_group_mask(u32 group) return group ? 1 << (group - 1) : 0; } -static inline struct hlist_head *nl_portid_hashfn(struct nl_portid_hash *hash, u32 portid) -{ - return &hash->table[jhash_1word(portid, hash->rnd) & hash->mask]; -} - int netlink_add_tap(struct netlink_tap *nt) { if (unlikely(nt->dev->type != ARPHRD_NETLINK)) @@ -170,7 +179,6 @@ EXPORT_SYMBOL_GPL(netlink_remove_tap); static bool netlink_filter_tap(const struct sk_buff *skb) { struct sock *sk = skb->sk; - bool pass = false; /* We take the more conservative approach and * whitelist socket protocols that may pass. @@ -184,11 +192,10 @@ static bool netlink_filter_tap(const struct sk_buff *skb) case NETLINK_FIB_LOOKUP: case NETLINK_NETFILTER: case NETLINK_GENERIC: - pass = true; - break; + return true; } - return pass; + return false; } static int __netlink_deliver_tap_skb(struct sk_buff *skb, @@ -376,7 +383,7 @@ static int netlink_set_ring(struct sock *sk, struct nl_mmap_req *req, if ((int)req->nm_block_size <= 0) return -EINVAL; - if (!IS_ALIGNED(req->nm_block_size, PAGE_SIZE)) + if (!PAGE_ALIGNED(req->nm_block_size)) return -EINVAL; if (req->nm_frame_size < NL_MMAP_HDRLEN) return -EINVAL; @@ -985,105 +992,48 @@ netlink_unlock_table(void) wake_up(&nl_table_wait); } -static bool netlink_compare(struct net *net, struct sock *sk) +struct netlink_compare_arg { - return net_eq(sock_net(sk), net); -} + struct net *net; + u32 portid; +}; -static struct sock *netlink_lookup(struct net *net, int protocol, u32 portid) +static bool netlink_compare(void *ptr, void *arg) { - struct netlink_table *table = &nl_table[protocol]; - struct nl_portid_hash *hash = &table->hash; - struct hlist_head *head; - struct sock *sk; + struct netlink_compare_arg *x = arg; + struct sock *sk = ptr; - read_lock(&nl_table_lock); - head = nl_portid_hashfn(hash, portid); - sk_for_each(sk, head) { - if (table->compare(net, sk) && - (nlk_sk(sk)->portid == portid)) { - sock_hold(sk); - goto found; - } - } - sk = NULL; -found: - read_unlock(&nl_table_lock); - return sk; + return nlk_sk(sk)->portid == x->portid && + net_eq(sock_net(sk), x->net); } -static struct hlist_head *nl_portid_hash_zalloc(size_t size) +static struct sock *__netlink_lookup(struct netlink_table *table, u32 portid, + struct net *net) { - if (size <= PAGE_SIZE) - return kzalloc(size, GFP_ATOMIC); - else - return (struct hlist_head *) - __get_free_pages(GFP_ATOMIC | __GFP_ZERO, - get_order(size)); -} + struct netlink_compare_arg arg = { + .net = net, + .portid = portid, + }; + u32 hash; -static void nl_portid_hash_free(struct hlist_head *table, size_t size) -{ - if (size <= PAGE_SIZE) - kfree(table); - else - free_pages((unsigned long)table, get_order(size)); -} - -static int nl_portid_hash_rehash(struct nl_portid_hash *hash, int grow) -{ - unsigned int omask, mask, shift; - size_t osize, size; - struct hlist_head *otable, *table; - int i; - - omask = mask = hash->mask; - osize = size = (mask + 1) * sizeof(*table); - shift = hash->shift; - - if (grow) { - if (++shift > hash->max_shift) - return 0; - mask = mask * 2 + 1; - size *= 2; - } - - table = nl_portid_hash_zalloc(size); - if (!table) - return 0; - - otable = hash->table; - hash->table = table; - hash->mask = mask; - hash->shift = shift; - get_random_bytes(&hash->rnd, sizeof(hash->rnd)); - - for (i = 0; i <= omask; i++) { - struct sock *sk; - struct hlist_node *tmp; + hash = rhashtable_hashfn(&table->hash, &portid, sizeof(portid)); - sk_for_each_safe(sk, tmp, &otable[i]) - __sk_add_node(sk, nl_portid_hashfn(hash, nlk_sk(sk)->portid)); - } - - nl_portid_hash_free(otable, osize); - hash->rehash_time = jiffies + 10 * 60 * HZ; - return 1; + return rhashtable_lookup_compare(&table->hash, hash, + &netlink_compare, &arg); } -static inline int nl_portid_hash_dilute(struct nl_portid_hash *hash, int len) +static struct sock *netlink_lookup(struct net *net, int protocol, u32 portid) { - int avg = hash->entries >> hash->shift; - - if (unlikely(avg > 1) && nl_portid_hash_rehash(hash, 1)) - return 1; + struct netlink_table *table = &nl_table[protocol]; + struct sock *sk; - if (unlikely(len > avg) && time_after(jiffies, hash->rehash_time)) { - nl_portid_hash_rehash(hash, 0); - return 1; - } + rcu_read_lock(); + sk = __netlink_lookup(table, portid, net); + if (sk) + sock_hold(sk); + rcu_read_unlock(); - return 0; + return sk; } static const struct proto_ops netlink_ops; @@ -1115,22 +1065,10 @@ netlink_update_listeners(struct sock *sk) static int netlink_insert(struct sock *sk, struct net *net, u32 portid) { struct netlink_table *table = &nl_table[sk->sk_protocol]; - struct nl_portid_hash *hash = &table->hash; - struct hlist_head *head; int err = -EADDRINUSE; - struct sock *osk; - int len; - netlink_table_grab(); - head = nl_portid_hashfn(hash, portid); - len = 0; - sk_for_each(osk, head) { - if (table->compare(net, osk) && - (nlk_sk(osk)->portid == portid)) - break; - len++; - } - if (osk) + mutex_lock(&nl_sk_hash_lock); + if (__netlink_lookup(table, portid, net)) goto err; err = -EBUSY; @@ -1138,26 +1076,31 @@ static int netlink_insert(struct sock *sk, struct net *net, u32 portid) goto err; err = -ENOMEM; - if (BITS_PER_LONG > 32 && unlikely(hash->entries >= UINT_MAX)) + if (BITS_PER_LONG > 32 && unlikely(table->hash.nelems >= UINT_MAX)) goto err; - if (len && nl_portid_hash_dilute(hash, len)) - head = nl_portid_hashfn(hash, portid); - hash->entries++; nlk_sk(sk)->portid = portid; - sk_add_node(sk, head); + sock_hold(sk); + rhashtable_insert(&table->hash, &nlk_sk(sk)->node, GFP_KERNEL); err = 0; - err: - netlink_table_ungrab(); + mutex_unlock(&nl_sk_hash_lock); return err; } static void netlink_remove(struct sock *sk) { + struct netlink_table *table; + + mutex_lock(&nl_sk_hash_lock); + table = &nl_table[sk->sk_protocol]; + if (rhashtable_remove(&table->hash, &nlk_sk(sk)->node, GFP_KERNEL)) { + WARN_ON(atomic_read(&sk->sk_refcnt) == 1); + __sock_put(sk); + } + mutex_unlock(&nl_sk_hash_lock); + netlink_table_grab(); - if (sk_del_node_init(sk)) - nl_table[sk->sk_protocol].hash.entries--; if (nlk_sk(sk)->subscriptions) __sk_del_bind_node(sk); netlink_table_ungrab(); @@ -1313,6 +1256,9 @@ static int netlink_release(struct socket *sock) } netlink_table_ungrab(); + /* Wait for readers to complete */ + synchronize_net(); + kfree(nlk->groups); nlk->groups = NULL; @@ -1328,30 +1274,22 @@ static int netlink_autobind(struct socket *sock) struct sock *sk = sock->sk; struct net *net = sock_net(sk); struct netlink_table *table = &nl_table[sk->sk_protocol]; - struct nl_portid_hash *hash = &table->hash; - struct hlist_head *head; - struct sock *osk; s32 portid = task_tgid_vnr(current); int err; static s32 rover = -4097; retry: cond_resched(); - netlink_table_grab(); - head = nl_portid_hashfn(hash, portid); - sk_for_each(osk, head) { - if (!table->compare(net, osk)) - continue; - if (nlk_sk(osk)->portid == portid) { - /* Bind collision, search negative portid values. */ - portid = rover--; - if (rover > -4097) - rover = -4097; - netlink_table_ungrab(); - goto retry; - } + rcu_read_lock(); + if (__netlink_lookup(table, portid, net)) { + /* Bind collision, search negative portid values. */ + portid = rover--; + if (rover > -4097) + rover = -4097; + rcu_read_unlock(); + goto retry; } - netlink_table_ungrab(); + rcu_read_unlock(); err = netlink_insert(sk, net, portid); if (err == -EADDRINUSE) @@ -1961,25 +1899,25 @@ struct netlink_broadcast_data { void *tx_data; }; -static int do_one_broadcast(struct sock *sk, - struct netlink_broadcast_data *p) +static void do_one_broadcast(struct sock *sk, + struct netlink_broadcast_data *p) { struct netlink_sock *nlk = nlk_sk(sk); int val; if (p->exclude_sk == sk) - goto out; + return; if (nlk->portid == p->portid || p->group - 1 >= nlk->ngroups || !test_bit(p->group - 1, nlk->groups)) - goto out; + return; if (!net_eq(sock_net(sk), p->net)) - goto out; + return; if (p->failure) { netlink_overrun(sk); - goto out; + return; } sock_hold(sk); @@ -2017,9 +1955,6 @@ static int do_one_broadcast(struct sock *sk, p->skb2 = NULL; } sock_put(sk); - -out: - return 0; } int netlink_broadcast_filtered(struct sock *ssk, struct sk_buff *skb, u32 portid, @@ -2958,14 +2893,18 @@ static struct sock *netlink_seq_socket_idx(struct seq_file *seq, loff_t pos) { struct nl_seq_iter *iter = seq->private; int i, j; + struct netlink_sock *nlk; struct sock *s; loff_t off = 0; for (i = 0; i < MAX_LINKS; i++) { - struct nl_portid_hash *hash = &nl_table[i].hash; + struct rhashtable *ht = &nl_table[i].hash; + const struct bucket_table *tbl = rht_dereference_rcu(ht->tbl, ht); + + for (j = 0; j < tbl->size; j++) { + rht_for_each_entry_rcu(nlk, tbl->buckets[j], node) { + s = (struct sock *)nlk; - for (j = 0; j <= hash->mask; j++) { - sk_for_each(s, &hash->table[j]) { if (sock_net(s) != seq_file_net(seq)) continue; if (off == pos) { @@ -2981,15 +2920,14 @@ static struct sock *netlink_seq_socket_idx(struct seq_file *seq, loff_t pos) } static void *netlink_seq_start(struct seq_file *seq, loff_t *pos) - __acquires(nl_table_lock) { - read_lock(&nl_table_lock); + rcu_read_lock(); return *pos ? netlink_seq_socket_idx(seq, *pos - 1) : SEQ_START_TOKEN; } static void *netlink_seq_next(struct seq_file *seq, void *v, loff_t *pos) { - struct sock *s; + struct netlink_sock *nlk; struct nl_seq_iter *iter; struct net *net; int i, j; @@ -3001,28 +2939,26 @@ static void *netlink_seq_next(struct seq_file *seq, void *v, loff_t *pos) net = seq_file_net(seq); iter = seq->private; - s = v; - do { - s = sk_next(s); - } while (s && !nl_table[s->sk_protocol].compare(net, s)); - if (s) - return s; + nlk = v; + + rht_for_each_entry_rcu(nlk, nlk->node.next, node) + if (net_eq(sock_net((struct sock *)nlk), net)) + return nlk; i = iter->link; j = iter->hash_idx + 1; do { - struct nl_portid_hash *hash = &nl_table[i].hash; - - for (; j <= hash->mask; j++) { - s = sk_head(&hash->table[j]); + struct rhashtable *ht = &nl_table[i].hash; + const struct bucket_table *tbl = rht_dereference_rcu(ht->tbl, ht); - while (s && !nl_table[s->sk_protocol].compare(net, s)) - s = sk_next(s); - if (s) { - iter->link = i; - iter->hash_idx = j; - return s; + for (; j < tbl->size; j++) { + rht_for_each_entry_rcu(nlk, tbl->buckets[j], node) { + if (net_eq(sock_net((struct sock *)nlk), net)) { + iter->link = i; + iter->hash_idx = j; + return nlk; + } } } @@ -3033,9 +2969,8 @@ static void *netlink_seq_next(struct seq_file *seq, void *v, loff_t *pos) } static void netlink_seq_stop(struct seq_file *seq, void *v) - __releases(nl_table_lock) { - read_unlock(&nl_table_lock); + rcu_read_unlock(); } @@ -3173,9 +3108,17 @@ static struct pernet_operations __net_initdata netlink_net_ops = { static int __init netlink_proto_init(void) { int i; - unsigned long limit; - unsigned int order; int err = proto_register(&netlink_proto, 0); + struct rhashtable_params ht_params = { + .head_offset = offsetof(struct netlink_sock, node), + .key_offset = offsetof(struct netlink_sock, portid), + .key_len = sizeof(u32), /* portid */ + .hashfn = arch_fast_hash, + .max_shift = 16, /* 64K */ + .grow_decision = rht_grow_above_75, + .shrink_decision = rht_shrink_below_30, + .mutex_is_held = lockdep_nl_sk_hash_is_held, + }; if (err != 0) goto out; @@ -3186,32 +3129,13 @@ static int __init netlink_proto_init(void) if (!nl_table) goto panic; - if (totalram_pages >= (128 * 1024)) - limit = totalram_pages >> (21 - PAGE_SHIFT); - else - limit = totalram_pages >> (23 - PAGE_SHIFT); - - order = get_bitmask_order(limit) - 1 + PAGE_SHIFT; - limit = (1UL << order) / sizeof(struct hlist_head); - order = get_bitmask_order(min(limit, (unsigned long)UINT_MAX)) - 1; - for (i = 0; i < MAX_LINKS; i++) { - struct nl_portid_hash *hash = &nl_table[i].hash; - - hash->table = nl_portid_hash_zalloc(1 * sizeof(*hash->table)); - if (!hash->table) { - while (i-- > 0) - nl_portid_hash_free(nl_table[i].hash.table, - 1 * sizeof(*hash->table)); + if (rhashtable_init(&nl_table[i].hash, &ht_params) < 0) { + while (--i > 0) + rhashtable_destroy(&nl_table[i].hash); kfree(nl_table); goto panic; } - hash->max_shift = order; - hash->shift = 0; - hash->mask = 0; - hash->rehash_time = jiffies; - - nl_table[i].compare = netlink_compare; } INIT_LIST_HEAD(&netlink_tap_all); diff --git a/net/netlink/af_netlink.h b/net/netlink/af_netlink.h index 0b59d441f5b6..60f631fb7087 100644 --- a/net/netlink/af_netlink.h +++ b/net/netlink/af_netlink.h @@ -1,6 +1,7 @@ #ifndef _AF_NETLINK_H #define _AF_NETLINK_H +#include <linux/rhashtable.h> #include <net/sock.h> #define NLGRPSZ(x) (ALIGN(x, sizeof(unsigned long) * 8) / 8) @@ -47,6 +48,8 @@ struct netlink_sock { struct netlink_ring tx_ring; atomic_t mapped; #endif /* CONFIG_NETLINK_MMAP */ + + struct rhash_head node; }; static inline struct netlink_sock *nlk_sk(struct sock *sk) @@ -54,21 +57,8 @@ static inline struct netlink_sock *nlk_sk(struct sock *sk) return container_of(sk, struct netlink_sock, sk); } -struct nl_portid_hash { - struct hlist_head *table; - unsigned long rehash_time; - - unsigned int mask; - unsigned int shift; - - unsigned int entries; - unsigned int max_shift; - - u32 rnd; -}; - struct netlink_table { - struct nl_portid_hash hash; + struct rhashtable hash; struct hlist_head mc_list; struct listeners __rcu *listeners; unsigned int flags; diff --git a/net/netlink/diag.c b/net/netlink/diag.c index 1af29624b92f..7301850eb56f 100644 --- a/net/netlink/diag.c +++ b/net/netlink/diag.c @@ -4,6 +4,7 @@ #include <linux/netlink.h> #include <linux/sock_diag.h> #include <linux/netlink_diag.h> +#include <linux/rhashtable.h> #include "af_netlink.h" @@ -101,16 +102,20 @@ static int __netlink_diag_dump(struct sk_buff *skb, struct netlink_callback *cb, int protocol, int s_num) { struct netlink_table *tbl = &nl_table[protocol]; - struct nl_portid_hash *hash = &tbl->hash; + struct rhashtable *ht = &tbl->hash; + const struct bucket_table *htbl = rht_dereference(ht->tbl, ht); struct net *net = sock_net(skb->sk); struct netlink_diag_req *req; + struct netlink_sock *nlsk; struct sock *sk; int ret = 0, num = 0, i; req = nlmsg_data(cb->nlh); - for (i = 0; i <= hash->mask; i++) { - sk_for_each(sk, &hash->table[i]) { + for (i = 0; i < htbl->size; i++) { + rht_for_each_entry(nlsk, htbl->buckets[i], ht, node) { + sk = (struct sock *)nlsk; + if (!net_eq(sock_net(sk), net)) continue; if (num < s_num) { diff --git a/net/netrom/af_netrom.c b/net/netrom/af_netrom.c index ede50d197e10..71cf1bffea06 100644 --- a/net/netrom/af_netrom.c +++ b/net/netrom/af_netrom.c @@ -1418,7 +1418,7 @@ static int __init nr_proto_init(void) struct net_device *dev; sprintf(name, "nr%d", i); - dev = alloc_netdev(0, name, nr_setup); + dev = alloc_netdev(0, name, NET_NAME_UNKNOWN, nr_setup); if (!dev) { printk(KERN_ERR "NET/ROM: nr_proto_init - unable to allocate device structure\n"); goto fail; diff --git a/net/nfc/digital.h b/net/nfc/digital.h index 71ad7eefddd4..3c39c72eb038 100644 --- a/net/nfc/digital.h +++ b/net/nfc/digital.h @@ -29,6 +29,7 @@ #define DIGITAL_CMD_TG_SEND 1 #define DIGITAL_CMD_TG_LISTEN 2 #define DIGITAL_CMD_TG_LISTEN_MDAA 3 +#define DIGITAL_CMD_TG_LISTEN_MD 4 #define DIGITAL_MAX_HEADER_LEN 7 #define DIGITAL_CRC_LEN 2 @@ -121,6 +122,8 @@ int digital_tg_send_dep_res(struct nfc_digital_dev *ddev, struct sk_buff *skb); int digital_tg_listen_nfca(struct nfc_digital_dev *ddev, u8 rf_tech); int digital_tg_listen_nfcf(struct nfc_digital_dev *ddev, u8 rf_tech); +void digital_tg_recv_md_req(struct nfc_digital_dev *ddev, void *arg, + struct sk_buff *resp); typedef u16 (*crc_func_t)(u16, const u8 *, size_t); diff --git a/net/nfc/digital_core.c b/net/nfc/digital_core.c index a6ce3c627e4e..009bcf317101 100644 --- a/net/nfc/digital_core.c +++ b/net/nfc/digital_core.c @@ -201,6 +201,11 @@ static void digital_wq_cmd(struct work_struct *work) digital_send_cmd_complete, cmd); break; + case DIGITAL_CMD_TG_LISTEN_MD: + rc = ddev->ops->tg_listen_md(ddev, cmd->timeout, + digital_send_cmd_complete, cmd); + break; + default: pr_err("Unknown cmd type %d\n", cmd->type); return; @@ -293,12 +298,19 @@ static int digital_tg_listen_mdaa(struct nfc_digital_dev *ddev, u8 rf_tech) 500, digital_tg_recv_atr_req, NULL); } +static int digital_tg_listen_md(struct nfc_digital_dev *ddev, u8 rf_tech) +{ + return digital_send_cmd(ddev, DIGITAL_CMD_TG_LISTEN_MD, NULL, NULL, 500, + digital_tg_recv_md_req, NULL); +} + int digital_target_found(struct nfc_digital_dev *ddev, struct nfc_target *target, u8 protocol) { int rc; u8 framing; u8 rf_tech; + u8 poll_tech_count; int (*check_crc)(struct sk_buff *skb); void (*add_crc)(struct sk_buff *skb); @@ -375,12 +387,16 @@ int digital_target_found(struct nfc_digital_dev *ddev, return rc; target->supported_protocols = (1 << protocol); - rc = nfc_targets_found(ddev->nfc_dev, target, 1); - if (rc) - return rc; + poll_tech_count = ddev->poll_tech_count; ddev->poll_tech_count = 0; + rc = nfc_targets_found(ddev->nfc_dev, target, 1); + if (rc) { + ddev->poll_tech_count = poll_tech_count; + return rc; + } + return 0; } @@ -505,6 +521,9 @@ static int digital_start_poll(struct nfc_dev *nfc_dev, __u32 im_protocols, if (ddev->ops->tg_listen_mdaa) { digital_add_poll_tech(ddev, 0, digital_tg_listen_mdaa); + } else if (ddev->ops->tg_listen_md) { + digital_add_poll_tech(ddev, 0, + digital_tg_listen_md); } else { digital_add_poll_tech(ddev, NFC_DIGITAL_RF_TECH_106A, digital_tg_listen_nfca); @@ -732,7 +751,7 @@ struct nfc_digital_dev *nfc_digital_allocate_device(struct nfc_digital_ops *ops, if (!ops->in_configure_hw || !ops->in_send_cmd || !ops->tg_listen || !ops->tg_configure_hw || !ops->tg_send_cmd || !ops->abort_cmd || - !ops->switch_rf) + !ops->switch_rf || (ops->tg_listen_md && !ops->tg_get_rf_tech)) return NULL; ddev = kzalloc(sizeof(struct nfc_digital_dev), GFP_KERNEL); diff --git a/net/nfc/digital_dep.c b/net/nfc/digital_dep.c index 171cb9949ab5..e1638dab076d 100644 --- a/net/nfc/digital_dep.c +++ b/net/nfc/digital_dep.c @@ -457,12 +457,10 @@ static void digital_tg_recv_dep_req(struct nfc_digital_dev *ddev, void *arg, pr_err("Received a ACK/NACK PDU\n"); rc = -EINVAL; goto exit; - break; case DIGITAL_NFC_DEP_PFB_SUPERVISOR_PDU: pr_err("Received a SUPERVISOR PDU\n"); rc = -EINVAL; goto exit; - break; } skb_pull(resp, size); @@ -673,6 +671,7 @@ void digital_tg_recv_atr_req(struct nfc_digital_dev *ddev, void *arg, int rc; struct digital_atr_req *atr_req; size_t gb_len, min_size; + u8 poll_tech_count; if (IS_ERR(resp)) { rc = PTR_ERR(resp); @@ -730,12 +729,16 @@ void digital_tg_recv_atr_req(struct nfc_digital_dev *ddev, void *arg, goto exit; gb_len = resp->len - sizeof(struct digital_atr_req); + + poll_tech_count = ddev->poll_tech_count; + ddev->poll_tech_count = 0; + rc = nfc_tm_activated(ddev->nfc_dev, NFC_PROTO_NFC_DEP_MASK, NFC_COMM_PASSIVE, atr_req->gb, gb_len); - if (rc) + if (rc) { + ddev->poll_tech_count = poll_tech_count; goto exit; - - ddev->poll_tech_count = 0; + } rc = 0; exit: diff --git a/net/nfc/digital_technology.c b/net/nfc/digital_technology.c index c2c1c0189b7c..fb58ed2dd41d 100644 --- a/net/nfc/digital_technology.c +++ b/net/nfc/digital_technology.c @@ -318,6 +318,8 @@ static void digital_in_recv_sel_res(struct nfc_digital_dev *ddev, void *arg, if (DIGITAL_SEL_RES_IS_T2T(sel_res)) { nfc_proto = NFC_PROTO_MIFARE; + } else if (DIGITAL_SEL_RES_IS_NFC_DEP(sel_res)) { + nfc_proto = NFC_PROTO_NFC_DEP; } else if (DIGITAL_SEL_RES_IS_T4T(sel_res)) { rc = digital_in_send_rats(ddev, target); if (rc) @@ -327,8 +329,6 @@ static void digital_in_recv_sel_res(struct nfc_digital_dev *ddev, void *arg, * done when receiving the ATS */ goto exit_free_skb; - } else if (DIGITAL_SEL_RES_IS_NFC_DEP(sel_res)) { - nfc_proto = NFC_PROTO_NFC_DEP; } else { rc = -EOPNOTSUPP; goto exit; @@ -944,6 +944,13 @@ static int digital_tg_send_sel_res(struct nfc_digital_dev *ddev) if (!DIGITAL_DRV_CAPS_TG_CRC(ddev)) digital_skb_add_crc_a(skb); + rc = digital_tg_configure_hw(ddev, NFC_DIGITAL_CONFIG_FRAMING, + NFC_DIGITAL_FRAMING_NFCA_ANTICOL_COMPLETE); + if (rc) { + kfree_skb(skb); + return rc; + } + rc = digital_tg_send_cmd(ddev, skb, 300, digital_tg_recv_atr_req, NULL); if (rc) @@ -1002,6 +1009,13 @@ static int digital_tg_send_sdd_res(struct nfc_digital_dev *ddev) for (i = 0; i < 4; i++) sdd_res->bcc ^= sdd_res->nfcid1[i]; + rc = digital_tg_configure_hw(ddev, NFC_DIGITAL_CONFIG_FRAMING, + NFC_DIGITAL_FRAMING_NFCA_STANDARD_WITH_CRC_A); + if (rc) { + kfree_skb(skb); + return rc; + } + rc = digital_tg_send_cmd(ddev, skb, 300, digital_tg_recv_sel_req, NULL); if (rc) @@ -1054,6 +1068,13 @@ static int digital_tg_send_sens_res(struct nfc_digital_dev *ddev) sens_res[0] = (DIGITAL_SENS_RES_NFC_DEP >> 8) & 0xFF; sens_res[1] = DIGITAL_SENS_RES_NFC_DEP & 0xFF; + rc = digital_tg_configure_hw(ddev, NFC_DIGITAL_CONFIG_FRAMING, + NFC_DIGITAL_FRAMING_NFCA_STANDARD); + if (rc) { + kfree_skb(skb); + return rc; + } + rc = digital_tg_send_cmd(ddev, skb, 300, digital_tg_recv_sdd_req, NULL); if (rc) @@ -1197,33 +1218,48 @@ exit: dev_kfree_skb(resp); } -int digital_tg_listen_nfca(struct nfc_digital_dev *ddev, u8 rf_tech) +static int digital_tg_config_nfca(struct nfc_digital_dev *ddev) { int rc; - rc = digital_tg_configure_hw(ddev, NFC_DIGITAL_CONFIG_RF_TECH, rf_tech); + rc = digital_tg_configure_hw(ddev, NFC_DIGITAL_CONFIG_RF_TECH, + NFC_DIGITAL_RF_TECH_106A); if (rc) return rc; - rc = digital_tg_configure_hw(ddev, NFC_DIGITAL_CONFIG_FRAMING, - NFC_DIGITAL_FRAMING_NFCA_NFC_DEP); + return digital_tg_configure_hw(ddev, NFC_DIGITAL_CONFIG_FRAMING, + NFC_DIGITAL_FRAMING_NFCA_NFC_DEP); +} + +int digital_tg_listen_nfca(struct nfc_digital_dev *ddev, u8 rf_tech) +{ + int rc; + + rc = digital_tg_config_nfca(ddev); if (rc) return rc; return digital_tg_listen(ddev, 300, digital_tg_recv_sens_req, NULL); } -int digital_tg_listen_nfcf(struct nfc_digital_dev *ddev, u8 rf_tech) +static int digital_tg_config_nfcf(struct nfc_digital_dev *ddev, u8 rf_tech) { int rc; - u8 *nfcid2; rc = digital_tg_configure_hw(ddev, NFC_DIGITAL_CONFIG_RF_TECH, rf_tech); if (rc) return rc; - rc = digital_tg_configure_hw(ddev, NFC_DIGITAL_CONFIG_FRAMING, - NFC_DIGITAL_FRAMING_NFCF_NFC_DEP); + return digital_tg_configure_hw(ddev, NFC_DIGITAL_CONFIG_FRAMING, + NFC_DIGITAL_FRAMING_NFCF_NFC_DEP); +} + +int digital_tg_listen_nfcf(struct nfc_digital_dev *ddev, u8 rf_tech) +{ + int rc; + u8 *nfcid2; + + rc = digital_tg_config_nfcf(ddev, rf_tech); if (rc) return rc; @@ -1237,3 +1273,43 @@ int digital_tg_listen_nfcf(struct nfc_digital_dev *ddev, u8 rf_tech) return digital_tg_listen(ddev, 300, digital_tg_recv_sensf_req, nfcid2); } + +void digital_tg_recv_md_req(struct nfc_digital_dev *ddev, void *arg, + struct sk_buff *resp) +{ + u8 rf_tech; + int rc; + + if (IS_ERR(resp)) { + resp = NULL; + goto exit_free_skb; + } + + rc = ddev->ops->tg_get_rf_tech(ddev, &rf_tech); + if (rc) + goto exit_free_skb; + + switch (rf_tech) { + case NFC_DIGITAL_RF_TECH_106A: + rc = digital_tg_config_nfca(ddev); + if (rc) + goto exit_free_skb; + digital_tg_recv_sens_req(ddev, arg, resp); + break; + case NFC_DIGITAL_RF_TECH_212F: + case NFC_DIGITAL_RF_TECH_424F: + rc = digital_tg_config_nfcf(ddev, rf_tech); + if (rc) + goto exit_free_skb; + digital_tg_recv_sensf_req(ddev, arg, resp); + break; + default: + goto exit_free_skb; + } + + return; + +exit_free_skb: + digital_poll_next_tech(ddev); + dev_kfree_skb(resp); +} diff --git a/net/nfc/hci/core.c b/net/nfc/hci/core.c index 47403705197e..117708263ced 100644 --- a/net/nfc/hci/core.c +++ b/net/nfc/hci/core.c @@ -553,8 +553,11 @@ static void hci_stop_poll(struct nfc_dev *nfc_dev) { struct nfc_hci_dev *hdev = nfc_get_drvdata(nfc_dev); - nfc_hci_send_event(hdev, NFC_HCI_RF_READER_A_GATE, - NFC_HCI_EVT_END_OPERATION, NULL, 0); + if (hdev->ops->stop_poll) + hdev->ops->stop_poll(hdev); + else + nfc_hci_send_event(hdev, NFC_HCI_RF_READER_A_GATE, + NFC_HCI_EVT_END_OPERATION, NULL, 0); } static int hci_dep_link_up(struct nfc_dev *nfc_dev, struct nfc_target *target, diff --git a/net/nfc/nci/ntf.c b/net/nfc/nci/ntf.c index f8f6af231381..df91bb95b12a 100644 --- a/net/nfc/nci/ntf.c +++ b/net/nfc/nci/ntf.c @@ -166,7 +166,9 @@ static int nci_add_new_protocol(struct nci_dev *ndev, struct rf_tech_specific_params_nfcf_poll *nfcf_poll; __u32 protocol; - if (rf_protocol == NCI_RF_PROTOCOL_T2T) + if (rf_protocol == NCI_RF_PROTOCOL_T1T) + protocol = NFC_PROTO_JEWEL_MASK; + else if (rf_protocol == NCI_RF_PROTOCOL_T2T) protocol = NFC_PROTO_MIFARE_MASK; else if (rf_protocol == NCI_RF_PROTOCOL_ISO_DEP) if (rf_tech_and_mode == NCI_NFC_A_PASSIVE_POLL_MODE) diff --git a/net/openvswitch/actions.c b/net/openvswitch/actions.c index e70d8b18e962..fe5cda0deb39 100644 --- a/net/openvswitch/actions.c +++ b/net/openvswitch/actions.c @@ -38,7 +38,7 @@ #include "vport.h" static int do_execute_actions(struct datapath *dp, struct sk_buff *skb, - const struct nlattr *attr, int len, bool keep_skb); + const struct nlattr *attr, int len); static int make_writable(struct sk_buff *skb, int write_len) { @@ -434,11 +434,17 @@ static int output_userspace(struct datapath *dp, struct sk_buff *skb, return ovs_dp_upcall(dp, skb, &upcall); } +static bool last_action(const struct nlattr *a, int rem) +{ + return a->nla_len == rem; +} + static int sample(struct datapath *dp, struct sk_buff *skb, const struct nlattr *attr) { const struct nlattr *acts_list = NULL; const struct nlattr *a; + struct sk_buff *sample_skb; int rem; for (a = nla_data(attr), rem = nla_len(attr); rem > 0; @@ -455,8 +461,34 @@ static int sample(struct datapath *dp, struct sk_buff *skb, } } - return do_execute_actions(dp, skb, nla_data(acts_list), - nla_len(acts_list), true); + rem = nla_len(acts_list); + a = nla_data(acts_list); + + /* Actions list is either empty or only contains a single user-space + * action, the latter being a special case as it is the only known + * usage of the sample action. + * In these special cases don't clone the skb as there are no + * side-effects in the nested actions. + * Otherwise, clone in case the nested actions have side effects. + */ + if (likely(rem == 0 || (nla_type(a) == OVS_ACTION_ATTR_USERSPACE && + last_action(a, rem)))) { + sample_skb = skb; + skb_get(skb); + } else { + sample_skb = skb_clone(skb, GFP_ATOMIC); + if (!sample_skb) /* Skip sample action when out of memory. */ + return 0; + } + + /* Note that do_execute_actions() never consumes skb. + * In the case where skb has been cloned above it is the clone that + * is consumed. Otherwise the skb_get(skb) call prevents + * consumption by do_execute_actions(). Thus, it is safe to simply + * return the error code and let the caller (also + * do_execute_actions()) free skb on error. + */ + return do_execute_actions(dp, sample_skb, a, rem); } static int execute_set_action(struct sk_buff *skb, @@ -507,7 +539,7 @@ static int execute_set_action(struct sk_buff *skb, /* Execute a list of actions against 'skb'. */ static int do_execute_actions(struct datapath *dp, struct sk_buff *skb, - const struct nlattr *attr, int len, bool keep_skb) + const struct nlattr *attr, int len) { /* Every output action needs a separate clone of 'skb', but the common * case is just a single output action, so that doing a clone and @@ -562,12 +594,9 @@ static int do_execute_actions(struct datapath *dp, struct sk_buff *skb, } } - if (prev_port != -1) { - if (keep_skb) - skb = skb_clone(skb, GFP_ATOMIC); - + if (prev_port != -1) do_output(dp, skb, prev_port); - } else if (!keep_skb) + else consume_skb(skb); return 0; @@ -579,6 +608,5 @@ int ovs_execute_actions(struct datapath *dp, struct sk_buff *skb) struct sw_flow_actions *acts = rcu_dereference(OVS_CB(skb)->flow->sf_acts); OVS_CB(skb)->tun_key = NULL; - return do_execute_actions(dp, skb, acts->actions, - acts->actions_len, false); + return do_execute_actions(dp, skb, acts->actions, acts->actions_len); } diff --git a/net/openvswitch/datapath.c b/net/openvswitch/datapath.c index 9db4bf6740d1..7ad3f029baae 100644 --- a/net/openvswitch/datapath.c +++ b/net/openvswitch/datapath.c @@ -66,16 +66,16 @@ static struct genl_family dp_packet_genl_family; static struct genl_family dp_flow_genl_family; static struct genl_family dp_datapath_genl_family; -static struct genl_multicast_group ovs_dp_flow_multicast_group = { - .name = OVS_FLOW_MCGROUP +static const struct genl_multicast_group ovs_dp_flow_multicast_group = { + .name = OVS_FLOW_MCGROUP, }; -static struct genl_multicast_group ovs_dp_datapath_multicast_group = { - .name = OVS_DATAPATH_MCGROUP +static const struct genl_multicast_group ovs_dp_datapath_multicast_group = { + .name = OVS_DATAPATH_MCGROUP, }; -struct genl_multicast_group ovs_dp_vport_multicast_group = { - .name = OVS_VPORT_MCGROUP +static const struct genl_multicast_group ovs_dp_vport_multicast_group = { + .name = OVS_VPORT_MCGROUP, }; /* Check if need to build a reply message. @@ -266,7 +266,7 @@ void ovs_dp_process_received_packet(struct vport *p, struct sk_buff *skb) upcall.cmd = OVS_PACKET_CMD_MISS; upcall.key = &key; upcall.userdata = NULL; - upcall.portid = p->upcall_portid; + upcall.portid = ovs_vport_find_upcall_portid(p, skb); ovs_dp_upcall(dp, skb, &upcall); consume_skb(skb); stats_counter = &stats->n_missed; @@ -464,7 +464,8 @@ static int queue_userspace_packet(struct datapath *dp, struct sk_buff *skb, upcall->dp_ifindex = dp_ifindex; nla = nla_nest_start(user_skb, OVS_PACKET_ATTR_KEY); - ovs_nla_put_flow(upcall_info->key, upcall_info->key, user_skb); + err = ovs_nla_put_flow(upcall_info->key, upcall_info->key, user_skb); + BUG_ON(err); nla_nest_end(user_skb, nla); if (upcall_info->userdata) @@ -780,7 +781,7 @@ static struct sk_buff *ovs_flow_cmd_build_info(const struct sw_flow *flow, skb = ovs_flow_cmd_alloc_info(ovsl_dereference(flow->sf_acts), info, always); - if (!skb || IS_ERR(skb)) + if (IS_ERR_OR_NULL(skb)) return skb; retval = ovs_flow_cmd_fill_info(flow, dp_ifindex, skb, @@ -1189,7 +1190,7 @@ static const struct nla_policy flow_policy[OVS_FLOW_ATTR_MAX + 1] = { [OVS_FLOW_ATTR_CLEAR] = { .type = NLA_FLAG }, }; -static struct genl_ops dp_flow_genl_ops[] = { +static const struct genl_ops dp_flow_genl_ops[] = { { .cmd = OVS_FLOW_CMD_NEW, .flags = GENL_ADMIN_PERM, /* Requires CAP_NET_ADMIN privilege. */ .policy = flow_policy, @@ -1373,7 +1374,7 @@ static int ovs_dp_cmd_new(struct sk_buff *skb, struct genl_info *info) parms.options = NULL; parms.dp = dp; parms.port_no = OVSP_LOCAL; - parms.upcall_portid = nla_get_u32(a[OVS_DP_ATTR_UPCALL_PID]); + parms.upcall_portids = a[OVS_DP_ATTR_UPCALL_PID]; ovs_dp_change(dp, a); @@ -1577,7 +1578,7 @@ static const struct nla_policy datapath_policy[OVS_DP_ATTR_MAX + 1] = { [OVS_DP_ATTR_USER_FEATURES] = { .type = NLA_U32 }, }; -static struct genl_ops dp_datapath_genl_ops[] = { +static const struct genl_ops dp_datapath_genl_ops[] = { { .cmd = OVS_DP_CMD_NEW, .flags = GENL_ADMIN_PERM, /* Requires CAP_NET_ADMIN privilege. */ .policy = datapath_policy, @@ -1632,8 +1633,8 @@ static int ovs_vport_cmd_fill_info(struct vport *vport, struct sk_buff *skb, if (nla_put_u32(skb, OVS_VPORT_ATTR_PORT_NO, vport->port_no) || nla_put_u32(skb, OVS_VPORT_ATTR_TYPE, vport->ops->type) || - nla_put_string(skb, OVS_VPORT_ATTR_NAME, vport->ops->get_name(vport)) || - nla_put_u32(skb, OVS_VPORT_ATTR_UPCALL_PID, vport->upcall_portid)) + nla_put_string(skb, OVS_VPORT_ATTR_NAME, + vport->ops->get_name(vport))) goto nla_put_failure; ovs_vport_get_stats(vport, &vport_stats); @@ -1641,6 +1642,9 @@ static int ovs_vport_cmd_fill_info(struct vport *vport, struct sk_buff *skb, &vport_stats)) goto nla_put_failure; + if (ovs_vport_get_upcall_portids(vport, skb)) + goto nla_put_failure; + err = ovs_vport_get_options(vport, skb); if (err == -EMSGSIZE) goto error; @@ -1762,7 +1766,7 @@ static int ovs_vport_cmd_new(struct sk_buff *skb, struct genl_info *info) parms.options = a[OVS_VPORT_ATTR_OPTIONS]; parms.dp = dp; parms.port_no = port_no; - parms.upcall_portid = nla_get_u32(a[OVS_VPORT_ATTR_UPCALL_PID]); + parms.upcall_portids = a[OVS_VPORT_ATTR_UPCALL_PID]; vport = new_vport(&parms); err = PTR_ERR(vport); @@ -1812,8 +1816,14 @@ static int ovs_vport_cmd_set(struct sk_buff *skb, struct genl_info *info) goto exit_unlock_free; } - if (a[OVS_VPORT_ATTR_UPCALL_PID]) - vport->upcall_portid = nla_get_u32(a[OVS_VPORT_ATTR_UPCALL_PID]); + + if (a[OVS_VPORT_ATTR_UPCALL_PID]) { + struct nlattr *ids = a[OVS_VPORT_ATTR_UPCALL_PID]; + + err = ovs_vport_set_upcall_portids(vport, ids); + if (err) + goto exit_unlock_free; + } err = ovs_vport_cmd_fill_info(vport, reply, info->snd_portid, info->snd_seq, 0, OVS_VPORT_CMD_NEW); @@ -1944,7 +1954,7 @@ static const struct nla_policy vport_policy[OVS_VPORT_ATTR_MAX + 1] = { [OVS_VPORT_ATTR_OPTIONS] = { .type = NLA_NESTED }, }; -static struct genl_ops dp_vport_genl_ops[] = { +static const struct genl_ops dp_vport_genl_ops[] = { { .cmd = OVS_VPORT_CMD_NEW, .flags = GENL_ADMIN_PERM, /* Requires CAP_NET_ADMIN privilege. */ .policy = vport_policy, @@ -2053,10 +2063,14 @@ static int __init dp_init(void) pr_info("Open vSwitch switching datapath\n"); - err = ovs_flow_init(); + err = ovs_internal_dev_rtnl_link_register(); if (err) goto error; + err = ovs_flow_init(); + if (err) + goto error_unreg_rtnl_link; + err = ovs_vport_init(); if (err) goto error_flow_exit; @@ -2083,6 +2097,8 @@ error_vport_exit: ovs_vport_exit(); error_flow_exit: ovs_flow_exit(); +error_unreg_rtnl_link: + ovs_internal_dev_rtnl_link_unregister(); error: return err; } @@ -2095,6 +2111,7 @@ static void dp_cleanup(void) rcu_barrier(); ovs_vport_exit(); ovs_flow_exit(); + ovs_internal_dev_rtnl_link_unregister(); } module_init(dp_init); diff --git a/net/openvswitch/datapath.h b/net/openvswitch/datapath.h index 7ede507500d7..701b5738c38a 100644 --- a/net/openvswitch/datapath.h +++ b/net/openvswitch/datapath.h @@ -144,7 +144,7 @@ int lockdep_ovsl_is_held(void); #define lockdep_ovsl_is_held() 1 #endif -#define ASSERT_OVSL() WARN_ON(unlikely(!lockdep_ovsl_is_held())) +#define ASSERT_OVSL() WARN_ON(!lockdep_ovsl_is_held()) #define ovsl_dereference(p) \ rcu_dereference_protected(p, lockdep_ovsl_is_held()) #define rcu_dereference_ovsl(p) \ diff --git a/net/openvswitch/vport-internal_dev.c b/net/openvswitch/vport-internal_dev.c index 789af9280e77..84516126e5f3 100644 --- a/net/openvswitch/vport-internal_dev.c +++ b/net/openvswitch/vport-internal_dev.c @@ -26,6 +26,7 @@ #include <net/dst.h> #include <net/xfrm.h> +#include <net/rtnetlink.h> #include "datapath.h" #include "vport-internal_dev.h" @@ -121,6 +122,10 @@ static const struct net_device_ops internal_dev_netdev_ops = { .ndo_get_stats64 = internal_dev_get_stats, }; +static struct rtnl_link_ops internal_dev_link_ops __read_mostly = { + .kind = "openvswitch", +}; + static void do_setup(struct net_device *netdev) { ether_setup(netdev); @@ -131,14 +136,18 @@ static void do_setup(struct net_device *netdev) netdev->priv_flags |= IFF_LIVE_ADDR_CHANGE; netdev->destructor = internal_dev_destructor; netdev->ethtool_ops = &internal_dev_ethtool_ops; + netdev->rtnl_link_ops = &internal_dev_link_ops; netdev->tx_queue_len = 0; netdev->features = NETIF_F_LLTX | NETIF_F_SG | NETIF_F_FRAGLIST | - NETIF_F_HIGHDMA | NETIF_F_HW_CSUM | NETIF_F_GSO_SOFTWARE; + NETIF_F_HIGHDMA | NETIF_F_HW_CSUM | + NETIF_F_GSO_SOFTWARE | NETIF_F_GSO_ENCAP_ALL; netdev->vlan_features = netdev->features; + netdev->hw_enc_features = netdev->features; netdev->features |= NETIF_F_HW_VLAN_CTAG_TX; netdev->hw_features = netdev->features & ~NETIF_F_LLTX; + eth_hw_addr_random(netdev); } @@ -159,7 +168,8 @@ static struct vport *internal_dev_create(const struct vport_parms *parms) netdev_vport = netdev_vport_priv(vport); netdev_vport->dev = alloc_netdev(sizeof(struct internal_dev), - parms->name, do_setup); + parms->name, NET_NAME_UNKNOWN, + do_setup); if (!netdev_vport->dev) { err = -ENOMEM; goto error_free_vport; @@ -248,3 +258,13 @@ struct vport *ovs_internal_dev_get_vport(struct net_device *netdev) return internal_dev_priv(netdev)->vport; } + +int ovs_internal_dev_rtnl_link_register(void) +{ + return rtnl_link_register(&internal_dev_link_ops); +} + +void ovs_internal_dev_rtnl_link_unregister(void) +{ + rtnl_link_unregister(&internal_dev_link_ops); +} diff --git a/net/openvswitch/vport-internal_dev.h b/net/openvswitch/vport-internal_dev.h index 9a7d30ecc6a2..1b179a190cff 100644 --- a/net/openvswitch/vport-internal_dev.h +++ b/net/openvswitch/vport-internal_dev.h @@ -24,5 +24,7 @@ int ovs_is_internal_dev(const struct net_device *); struct vport *ovs_internal_dev_get_vport(struct net_device *); +int ovs_internal_dev_rtnl_link_register(void); +void ovs_internal_dev_rtnl_link_unregister(void); #endif /* vport-internal_dev.h */ diff --git a/net/openvswitch/vport-vxlan.c b/net/openvswitch/vport-vxlan.c index 0edbd95c60e7..d8b7e247bebf 100644 --- a/net/openvswitch/vport-vxlan.c +++ b/net/openvswitch/vport-vxlan.c @@ -143,8 +143,6 @@ static int vxlan_tnl_send(struct vport *vport, struct sk_buff *skb) struct rtable *rt; struct flowi4 fl; __be16 src_port; - int port_min; - int port_max; __be16 df; int err; @@ -172,8 +170,7 @@ static int vxlan_tnl_send(struct vport *vport, struct sk_buff *skb) skb->ignore_df = 1; - inet_get_local_port_range(net, &port_min, &port_max); - src_port = vxlan_src_port(port_min, port_max, skb); + src_port = udp_flow_src_port(net, skb, 0, 0, true); err = vxlan_xmit_skb(vxlan_port->vs, rt, skb, fl.saddr, OVS_CB(skb)->tun_key->ipv4_dst, diff --git a/net/openvswitch/vport.c b/net/openvswitch/vport.c index 42c0f4a0b78c..702fb21bfe15 100644 --- a/net/openvswitch/vport.c +++ b/net/openvswitch/vport.c @@ -134,10 +134,12 @@ struct vport *ovs_vport_alloc(int priv_size, const struct vport_ops *ops, vport->dp = parms->dp; vport->port_no = parms->port_no; - vport->upcall_portid = parms->upcall_portid; vport->ops = ops; INIT_HLIST_NODE(&vport->dp_hash_node); + if (ovs_vport_set_upcall_portids(vport, parms->upcall_portids)) + return ERR_PTR(-EINVAL); + vport->percpu_stats = netdev_alloc_pcpu_stats(struct pcpu_sw_netstats); if (!vport->percpu_stats) { kfree(vport); @@ -161,6 +163,10 @@ struct vport *ovs_vport_alloc(int priv_size, const struct vport_ops *ops, */ void ovs_vport_free(struct vport *vport) { + /* vport is freed from RCU callback or error path, Therefore + * it is safe to use raw dereference. + */ + kfree(rcu_dereference_raw(vport->upcall_portids)); free_percpu(vport->percpu_stats); kfree(vport); } @@ -327,6 +333,99 @@ int ovs_vport_get_options(const struct vport *vport, struct sk_buff *skb) } /** + * ovs_vport_set_upcall_portids - set upcall portids of @vport. + * + * @vport: vport to modify. + * @ids: new configuration, an array of port ids. + * + * Sets the vport's upcall_portids to @ids. + * + * Returns 0 if successful, -EINVAL if @ids is zero length or cannot be parsed + * as an array of U32. + * + * Must be called with ovs_mutex. + */ +int ovs_vport_set_upcall_portids(struct vport *vport, struct nlattr *ids) +{ + struct vport_portids *old, *vport_portids; + + if (!nla_len(ids) || nla_len(ids) % sizeof(u32)) + return -EINVAL; + + old = ovsl_dereference(vport->upcall_portids); + + vport_portids = kmalloc(sizeof(*vport_portids) + nla_len(ids), + GFP_KERNEL); + if (!vport_portids) + return -ENOMEM; + + vport_portids->n_ids = nla_len(ids) / sizeof(u32); + vport_portids->rn_ids = reciprocal_value(vport_portids->n_ids); + nla_memcpy(vport_portids->ids, ids, nla_len(ids)); + + rcu_assign_pointer(vport->upcall_portids, vport_portids); + + if (old) + kfree_rcu(old, rcu); + return 0; +} + +/** + * ovs_vport_get_upcall_portids - get the upcall_portids of @vport. + * + * @vport: vport from which to retrieve the portids. + * @skb: sk_buff where portids should be appended. + * + * Retrieves the configuration of the given vport, appending the + * %OVS_VPORT_ATTR_UPCALL_PID attribute which is the array of upcall + * portids to @skb. + * + * Returns 0 if successful, -EMSGSIZE if @skb has insufficient room. + * If an error occurs, @skb is left unmodified. Must be called with + * ovs_mutex or rcu_read_lock. + */ +int ovs_vport_get_upcall_portids(const struct vport *vport, + struct sk_buff *skb) +{ + struct vport_portids *ids; + + ids = rcu_dereference_ovsl(vport->upcall_portids); + + if (vport->dp->user_features & OVS_DP_F_VPORT_PIDS) + return nla_put(skb, OVS_VPORT_ATTR_UPCALL_PID, + ids->n_ids * sizeof(u32), (void *)ids->ids); + else + return nla_put_u32(skb, OVS_VPORT_ATTR_UPCALL_PID, ids->ids[0]); +} + +/** + * ovs_vport_find_upcall_portid - find the upcall portid to send upcall. + * + * @vport: vport from which the missed packet is received. + * @skb: skb that the missed packet was received. + * + * Uses the skb_get_hash() to select the upcall portid to send the + * upcall. + * + * Returns the portid of the target socket. Must be called with rcu_read_lock. + */ +u32 ovs_vport_find_upcall_portid(const struct vport *p, struct sk_buff *skb) +{ + struct vport_portids *ids; + u32 ids_index; + u32 hash; + + ids = rcu_dereference(p->upcall_portids); + + if (ids->n_ids == 1 && ids->ids[0] == 0) + return 0; + + hash = skb_get_hash(skb); + ids_index = hash - ids->n_ids * reciprocal_divide(hash, ids->rn_ids); + return ids->ids[ids_index]; +} + +/** * ovs_vport_receive - pass up received packet to the datapath for processing * * @vport: vport that received the packet diff --git a/net/openvswitch/vport.h b/net/openvswitch/vport.h index 8d721e62f388..35f89d84b45e 100644 --- a/net/openvswitch/vport.h +++ b/net/openvswitch/vport.h @@ -23,6 +23,7 @@ #include <linux/list.h> #include <linux/netlink.h> #include <linux/openvswitch.h> +#include <linux/reciprocal_div.h> #include <linux/skbuff.h> #include <linux/spinlock.h> #include <linux/u64_stats_sync.h> @@ -52,6 +53,10 @@ void ovs_vport_get_stats(struct vport *, struct ovs_vport_stats *); int ovs_vport_set_options(struct vport *, struct nlattr *options); int ovs_vport_get_options(const struct vport *, struct sk_buff *); +int ovs_vport_set_upcall_portids(struct vport *, struct nlattr *pids); +int ovs_vport_get_upcall_portids(const struct vport *, struct sk_buff *); +u32 ovs_vport_find_upcall_portid(const struct vport *, struct sk_buff *); + int ovs_vport_send(struct vport *, struct sk_buff *); /* The following definitions are for implementers of vport devices: */ @@ -62,13 +67,27 @@ struct vport_err_stats { u64 tx_dropped; u64 tx_errors; }; +/** + * struct vport_portids - array of netlink portids of a vport. + * must be protected by rcu. + * @rn_ids: The reciprocal value of @n_ids. + * @rcu: RCU callback head for deferred destruction. + * @n_ids: Size of @ids array. + * @ids: Array storing the Netlink socket pids to be used for packets received + * on this port that miss the flow table. + */ +struct vport_portids { + struct reciprocal_value rn_ids; + struct rcu_head rcu; + u32 n_ids; + u32 ids[]; +}; /** * struct vport - one port within a datapath * @rcu: RCU callback head for deferred destruction. * @dp: Datapath to which this port belongs. - * @upcall_portid: The Netlink port to use for packets received on this port that - * miss the flow table. + * @upcall_portids: RCU protected 'struct vport_portids'. * @port_no: Index into @dp's @ports array. * @hash_node: Element in @dev_table hash table in vport.c. * @dp_hash_node: Element in @datapath->ports hash table in datapath.c. @@ -80,7 +99,7 @@ struct vport_err_stats { struct vport { struct rcu_head rcu; struct datapath *dp; - u32 upcall_portid; + struct vport_portids __rcu *upcall_portids; u16 port_no; struct hlist_node hash_node; @@ -111,7 +130,7 @@ struct vport_parms { /* For ovs_vport_alloc(). */ struct datapath *dp; u16 port_no; - u32 upcall_portid; + struct nlattr *upcall_portids; }; /** diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c index b85c67ccb797..8d9f8042705a 100644 --- a/net/packet/af_packet.c +++ b/net/packet/af_packet.c @@ -441,14 +441,10 @@ static __u32 tpacket_get_timestamp(struct sk_buff *skb, struct timespec *ts, { struct skb_shared_hwtstamps *shhwtstamps = skb_hwtstamps(skb); - if (shhwtstamps) { - if ((flags & SOF_TIMESTAMPING_SYS_HARDWARE) && - ktime_to_timespec_cond(shhwtstamps->syststamp, ts)) - return TP_STATUS_TS_SYS_HARDWARE; - if ((flags & SOF_TIMESTAMPING_RAW_HARDWARE) && - ktime_to_timespec_cond(shhwtstamps->hwtstamp, ts)) - return TP_STATUS_TS_RAW_HARDWARE; - } + if (shhwtstamps && + (flags & SOF_TIMESTAMPING_RAW_HARDWARE) && + ktime_to_timespec_cond(shhwtstamps->hwtstamp, ts)) + return TP_STATUS_TS_RAW_HARDWARE; if (ktime_to_timespec_cond(skb->tstamp, ts)) return TP_STATUS_TS_SOFTWARE; @@ -3071,10 +3067,8 @@ static int packet_dev_mc(struct net_device *dev, struct packet_mclist *i, break; case PACKET_MR_PROMISC: return dev_set_promiscuity(dev, what); - break; case PACKET_MR_ALLMULTI: return dev_set_allmulti(dev, what); - break; case PACKET_MR_UNICAST: if (i->alen != dev->addr_len) return -EINVAL; diff --git a/net/phonet/pep-gprs.c b/net/phonet/pep-gprs.c index 66dc65e7c6a1..e9a83a637185 100644 --- a/net/phonet/pep-gprs.c +++ b/net/phonet/pep-gprs.c @@ -267,7 +267,7 @@ int gprs_attach(struct sock *sk) return -EINVAL; /* need packet boundaries */ /* Create net device */ - dev = alloc_netdev(sizeof(*gp), ifname, gprs_setup); + dev = alloc_netdev(sizeof(*gp), ifname, NET_NAME_UNKNOWN, gprs_setup); if (!dev) return -ENOMEM; gp = netdev_priv(dev); diff --git a/net/rose/af_rose.c b/net/rose/af_rose.c index 8451c8cdc9de..a85c1a086ae4 100644 --- a/net/rose/af_rose.c +++ b/net/rose/af_rose.c @@ -1538,7 +1538,7 @@ static int __init rose_proto_init(void) char name[IFNAMSIZ]; sprintf(name, "rose%d", i); - dev = alloc_netdev(0, name, rose_setup); + dev = alloc_netdev(0, name, NET_NAME_UNKNOWN, rose_setup); if (!dev) { printk(KERN_ERR "ROSE: rose_proto_init - unable to allocate memory\n"); rc = -ENOMEM; diff --git a/net/rxrpc/ar-key.c b/net/rxrpc/ar-key.c index 3907add75932..b45d080e64a7 100644 --- a/net/rxrpc/ar-key.c +++ b/net/rxrpc/ar-key.c @@ -350,7 +350,7 @@ static int rxrpc_krb5_decode_tagged_array(struct krb5_tagged_data **_td, n_elem = ntohl(*xdr++); toklen -= 4; - if (n_elem < 0 || n_elem > max_n_elem) + if (n_elem > max_n_elem) return -EINVAL; *_n_elem = n_elem; if (n_elem > 0) { diff --git a/net/sched/act_mirred.c b/net/sched/act_mirred.c index 4f912c0e225b..eb48306033d9 100644 --- a/net/sched/act_mirred.c +++ b/net/sched/act_mirred.c @@ -218,10 +218,12 @@ static int mirred_device_event(struct notifier_block *unused, if (event == NETDEV_UNREGISTER) list_for_each_entry(m, &mirred_list, tcfm_list) { + spin_lock_bh(&m->tcf_lock); if (m->tcfm_dev == dev) { dev_put(dev); m->tcfm_dev = NULL; } + spin_unlock_bh(&m->tcf_lock); } return NOTIFY_DONE; diff --git a/net/sched/cls_api.c b/net/sched/cls_api.c index 45527e6b52db..c28b0d327b12 100644 --- a/net/sched/cls_api.c +++ b/net/sched/cls_api.c @@ -561,13 +561,14 @@ EXPORT_SYMBOL(tcf_exts_change); int tcf_exts_dump(struct sk_buff *skb, struct tcf_exts *exts) { #ifdef CONFIG_NET_CLS_ACT + struct nlattr *nest; + if (exts->action && !list_empty(&exts->actions)) { /* * again for backward compatible mode - we want * to work with both old and new modes of entering * tc data even if iproute2 was newer - jhs */ - struct nlattr *nest; if (exts->type != TCA_OLD_COMPAT) { nest = nla_nest_start(skb, exts->action); if (nest == NULL) @@ -585,10 +586,14 @@ int tcf_exts_dump(struct sk_buff *skb, struct tcf_exts *exts) nla_nest_end(skb, nest); } } -#endif return 0; -nla_put_failure: __attribute__ ((unused)) + +nla_put_failure: + nla_nest_cancel(skb, nest); return -1; +#else + return 0; +#endif } EXPORT_SYMBOL(tcf_exts_dump); diff --git a/net/sched/cls_bpf.c b/net/sched/cls_bpf.c index 13f64df2c710..0e30d58149da 100644 --- a/net/sched/cls_bpf.c +++ b/net/sched/cls_bpf.c @@ -30,7 +30,7 @@ struct cls_bpf_head { }; struct cls_bpf_prog { - struct sk_filter *filter; + struct bpf_prog *filter; struct sock_filter *bpf_ops; struct tcf_exts exts; struct tcf_result res; @@ -54,7 +54,7 @@ static int cls_bpf_classify(struct sk_buff *skb, const struct tcf_proto *tp, int ret; list_for_each_entry(prog, &head->plist, link) { - int filter_res = SK_RUN_FILTER(prog->filter, skb); + int filter_res = BPF_PROG_RUN(prog->filter, skb); if (filter_res == 0) continue; @@ -92,7 +92,7 @@ static void cls_bpf_delete_prog(struct tcf_proto *tp, struct cls_bpf_prog *prog) tcf_unbind_filter(tp, &prog->res); tcf_exts_destroy(tp, &prog->exts); - sk_unattached_filter_destroy(prog->filter); + bpf_prog_destroy(prog->filter); kfree(prog->bpf_ops); kfree(prog); @@ -161,7 +161,7 @@ static int cls_bpf_modify_existing(struct net *net, struct tcf_proto *tp, struct sock_filter *bpf_ops, *bpf_old; struct tcf_exts exts; struct sock_fprog_kern tmp; - struct sk_filter *fp, *fp_old; + struct bpf_prog *fp, *fp_old; u16 bpf_size, bpf_len; u32 classid; int ret; @@ -193,7 +193,7 @@ static int cls_bpf_modify_existing(struct net *net, struct tcf_proto *tp, tmp.len = bpf_len; tmp.filter = bpf_ops; - ret = sk_unattached_filter_create(&fp, &tmp); + ret = bpf_prog_create(&fp, &tmp); if (ret) goto errout_free; @@ -211,7 +211,7 @@ static int cls_bpf_modify_existing(struct net *net, struct tcf_proto *tp, tcf_exts_change(tp, &prog->exts, &exts); if (fp_old) - sk_unattached_filter_destroy(fp_old); + bpf_prog_destroy(fp_old); if (bpf_old) kfree(bpf_old); diff --git a/net/sched/cls_tcindex.c b/net/sched/cls_tcindex.c index c721cd4a469f..3e9f76413b3b 100644 --- a/net/sched/cls_tcindex.c +++ b/net/sched/cls_tcindex.c @@ -420,7 +420,7 @@ static void tcindex_destroy(struct tcf_proto *tp) pr_debug("tcindex_destroy(tp %p),p %p\n", tp, p); walker.count = 0; walker.skip = 0; - walker.fn = &tcindex_destroy_element; + walker.fn = tcindex_destroy_element; tcindex_walk(tp, &walker); kfree(p->perfect); kfree(p->h); diff --git a/net/sched/em_canid.c b/net/sched/em_canid.c index bfd34e4c1afc..7c292d474f47 100644 --- a/net/sched/em_canid.c +++ b/net/sched/em_canid.c @@ -125,7 +125,6 @@ static int em_canid_change(struct tcf_proto *tp, void *data, int len, { struct can_filter *conf = data; /* Array with rules */ struct canid_match *cm; - struct canid_match *cm_old = (struct canid_match *)m->data; int i; if (!len) @@ -181,12 +180,6 @@ static int em_canid_change(struct tcf_proto *tp, void *data, int len, m->datalen = sizeof(struct canid_match) + len; m->data = (unsigned long)cm; - - if (cm_old != NULL) { - pr_err("canid: Configuring an existing ematch!\n"); - kfree(cm_old); - } - return 0; } diff --git a/net/sched/sch_generic.c b/net/sched/sch_generic.c index e1543b03e39d..fc04fe93c2da 100644 --- a/net/sched/sch_generic.c +++ b/net/sched/sch_generic.c @@ -108,7 +108,7 @@ static inline int handle_dev_cpu_collision(struct sk_buff *skb, /* * Transmit one skb, and handle the return status as required. Holding the - * __QDISC_STATE_RUNNING bit guarantees that only one CPU can execute this + * __QDISC___STATE_RUNNING bit guarantees that only one CPU can execute this * function. * * Returns to the caller: @@ -156,7 +156,7 @@ int sch_direct_xmit(struct sk_buff *skb, struct Qdisc *q, /* * NOTE: Called under qdisc_lock(q) with locally disabled BH. * - * __QDISC_STATE_RUNNING guarantees only one CPU can process + * __QDISC___STATE_RUNNING guarantees only one CPU can process * this qdisc at a time. qdisc_lock(q) serializes queue accesses for * this queue. * diff --git a/net/sched/sch_teql.c b/net/sched/sch_teql.c index 474167162947..bd33793b527e 100644 --- a/net/sched/sch_teql.c +++ b/net/sched/sch_teql.c @@ -485,8 +485,8 @@ static int __init teql_init(void) struct net_device *dev; struct teql_master *master; - dev = alloc_netdev(sizeof(struct teql_master), - "teql%d", teql_master_setup); + dev = alloc_netdev(sizeof(struct teql_master), "teql%d", + NET_NAME_UNKNOWN, teql_master_setup); if (!dev) { err = -ENOMEM; break; diff --git a/net/sctp/Makefile b/net/sctp/Makefile index 5c30b7a873df..3b4ffb021cf1 100644 --- a/net/sctp/Makefile +++ b/net/sctp/Makefile @@ -8,7 +8,7 @@ obj-$(CONFIG_NET_SCTPPROBE) += sctp_probe.o sctp-y := sm_statetable.o sm_statefuns.o sm_sideeffect.o \ protocol.o endpointola.o associola.o \ transport.o chunk.o sm_make_chunk.o ulpevent.o \ - inqueue.o outqueue.o ulpqueue.o command.o \ + inqueue.o outqueue.o ulpqueue.o \ tsnmap.o bind_addr.o socket.o primitive.o \ output.o input.o debug.o ssnmap.o auth.o diff --git a/net/sctp/command.c b/net/sctp/command.c deleted file mode 100644 index dd7375851618..000000000000 --- a/net/sctp/command.c +++ /dev/null @@ -1,68 +0,0 @@ -/* SCTP kernel implementation Copyright (C) 1999-2001 - * Cisco, Motorola, and IBM - * Copyright 2001 La Monte H.P. Yarroll - * - * This file is part of the SCTP kernel implementation - * - * These functions manipulate sctp command sequences. - * - * This SCTP implementation is free software; - * you can redistribute it and/or modify it under the terms of - * the GNU General Public License as published by - * the Free Software Foundation; either version 2, or (at your option) - * any later version. - * - * This SCTP implementation is distributed in the hope that it - * will be useful, but WITHOUT ANY WARRANTY; without even the implied - * ************************ - * warranty of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. - * See the GNU General Public License for more details. - * - * You should have received a copy of the GNU General Public License - * along with GNU CC; see the file COPYING. If not, see - * <http://www.gnu.org/licenses/>. - * - * Please send any bug reports or fixes you make to the - * email address(es): - * lksctp developers <linux-sctp@vger.kernel.org> - * - * Written or modified by: - * La Monte H.P. Yarroll <piggy@acm.org> - * Karl Knutson <karl@athena.chicago.il.us> - */ - -#include <linux/types.h> -#include <net/sctp/sctp.h> -#include <net/sctp/sm.h> - -/* Initialize a block of memory as a command sequence. */ -int sctp_init_cmd_seq(sctp_cmd_seq_t *seq) -{ - memset(seq, 0, sizeof(sctp_cmd_seq_t)); - return 1; /* We always succeed. */ -} - -/* Add a command to a sctp_cmd_seq_t. - * Return 0 if the command sequence is full. - */ -void sctp_add_cmd_sf(sctp_cmd_seq_t *seq, sctp_verb_t verb, sctp_arg_t obj) -{ - BUG_ON(seq->next_free_slot >= SCTP_MAX_NUM_COMMANDS); - - seq->cmds[seq->next_free_slot].verb = verb; - seq->cmds[seq->next_free_slot++].obj = obj; -} - -/* Return the next command structure in a sctp_cmd_seq. - * Returns NULL at the end of the sequence. - */ -sctp_cmd_t *sctp_next_cmd(sctp_cmd_seq_t *seq) -{ - sctp_cmd_t *retval = NULL; - - if (seq->next_cmd < seq->next_free_slot) - retval = &seq->cmds[seq->next_cmd++]; - - return retval; -} - diff --git a/net/sctp/input.c b/net/sctp/input.c index f2e2cbd2d750..c1b991294516 100644 --- a/net/sctp/input.c +++ b/net/sctp/input.c @@ -575,11 +575,6 @@ void sctp_v4_err(struct sk_buff *skb, __u32 info) int err; struct net *net = dev_net(skb->dev); - if (skb->len < ihlen + 8) { - ICMP_INC_STATS_BH(net, ICMP_MIB_INERRORS); - return; - } - /* Fix up skb to look at the embedded net header. */ saveip = skb->network_header; savesctp = skb->transport_header; diff --git a/net/sctp/ipv6.c b/net/sctp/ipv6.c index 1999592ba88c..0e4198ee2370 100644 --- a/net/sctp/ipv6.c +++ b/net/sctp/ipv6.c @@ -434,7 +434,7 @@ static void sctp_v6_from_sk(union sctp_addr *addr, struct sock *sk) /* Initialize sk->sk_rcv_saddr from sctp_addr. */ static void sctp_v6_to_sk_saddr(union sctp_addr *addr, struct sock *sk) { - if (addr->sa.sa_family == AF_INET && sctp_sk(sk)->v4mapped) { + if (addr->sa.sa_family == AF_INET) { sk->sk_v6_rcv_saddr.s6_addr32[0] = 0; sk->sk_v6_rcv_saddr.s6_addr32[1] = 0; sk->sk_v6_rcv_saddr.s6_addr32[2] = htonl(0x0000ffff); @@ -448,7 +448,7 @@ static void sctp_v6_to_sk_saddr(union sctp_addr *addr, struct sock *sk) /* Initialize sk->sk_daddr from sctp_addr. */ static void sctp_v6_to_sk_daddr(union sctp_addr *addr, struct sock *sk) { - if (addr->sa.sa_family == AF_INET && sctp_sk(sk)->v4mapped) { + if (addr->sa.sa_family == AF_INET) { sk->sk_v6_daddr.s6_addr32[0] = 0; sk->sk_v6_daddr.s6_addr32[1] = 0; sk->sk_v6_daddr.s6_addr32[2] = htonl(0x0000ffff); @@ -556,8 +556,6 @@ static int sctp_v6_available(union sctp_addr *addr, struct sctp_sock *sp) if (IPV6_ADDR_ANY == type) return 1; if (type == IPV6_ADDR_MAPPED) { - if (sp && !sp->v4mapped) - return 0; if (sp && ipv6_only_sock(sctp_opt2sk(sp))) return 0; sctp_v6_map_v4(addr); @@ -587,8 +585,6 @@ static int sctp_v6_addr_valid(union sctp_addr *addr, /* Note: This routine is used in input, so v4-mapped-v6 * are disallowed here when there is no sctp_sock. */ - if (!sp || !sp->v4mapped) - return 0; if (sp && ipv6_only_sock(sctp_opt2sk(sp))) return 0; sctp_v6_map_v4(addr); @@ -675,11 +671,23 @@ out: return newsk; } -/* Map v4 address to mapped v6 address */ -static void sctp_v6_addr_v4map(struct sctp_sock *sp, union sctp_addr *addr) +/* Format a sockaddr for return to user space. This makes sure the return is + * AF_INET or AF_INET6 depending on the SCTP_I_WANT_MAPPED_V4_ADDR option. + */ +static int sctp_v6_addr_to_user(struct sctp_sock *sp, union sctp_addr *addr) { - if (sp->v4mapped && AF_INET == addr->sa.sa_family) - sctp_v4_map_v6(addr); + if (sp->v4mapped) { + if (addr->sa.sa_family == AF_INET) + sctp_v4_map_v6(addr); + } else { + if (addr->sa.sa_family == AF_INET6 && + ipv6_addr_v4mapped(&addr->v6.sin6_addr)) + sctp_v6_map_v4(addr); + } + + if (addr->sa.sa_family == AF_INET) + return sizeof(struct sockaddr_in); + return sizeof(struct sockaddr_in6); } /* Where did this skb come from? */ @@ -706,82 +714,68 @@ static void sctp_v6_ecn_capable(struct sock *sk) inet6_sk(sk)->tclass |= INET_ECN_ECT_0; } -/* Initialize a PF_INET6 socket msg_name. */ -static void sctp_inet6_msgname(char *msgname, int *addr_len) -{ - struct sockaddr_in6 *sin6; - - sin6 = (struct sockaddr_in6 *)msgname; - sin6->sin6_family = AF_INET6; - sin6->sin6_flowinfo = 0; - sin6->sin6_scope_id = 0; /*FIXME */ - *addr_len = sizeof(struct sockaddr_in6); -} - /* Initialize a PF_INET msgname from a ulpevent. */ static void sctp_inet6_event_msgname(struct sctp_ulpevent *event, char *msgname, int *addrlen) { - struct sockaddr_in6 *sin6, *sin6from; - - if (msgname) { - union sctp_addr *addr; - struct sctp_association *asoc; - - asoc = event->asoc; - sctp_inet6_msgname(msgname, addrlen); - sin6 = (struct sockaddr_in6 *)msgname; - sin6->sin6_port = htons(asoc->peer.port); - addr = &asoc->peer.primary_addr; + union sctp_addr *addr; + struct sctp_association *asoc; + union sctp_addr *paddr; - /* Note: If we go to a common v6 format, this code - * will change. - */ + if (!msgname) + return; - /* Map ipv4 address into v4-mapped-on-v6 address. */ - if (sctp_sk(asoc->base.sk)->v4mapped && - AF_INET == addr->sa.sa_family) { - sctp_v4_map_v6((union sctp_addr *)sin6); - sin6->sin6_addr.s6_addr32[3] = - addr->v4.sin_addr.s_addr; - return; - } + addr = (union sctp_addr *)msgname; + asoc = event->asoc; + paddr = &asoc->peer.primary_addr; - sin6from = &asoc->peer.primary_addr.v6; - sin6->sin6_addr = sin6from->sin6_addr; - if (ipv6_addr_type(&sin6->sin6_addr) & IPV6_ADDR_LINKLOCAL) - sin6->sin6_scope_id = sin6from->sin6_scope_id; + if (paddr->sa.sa_family == AF_INET) { + addr->v4.sin_family = AF_INET; + addr->v4.sin_port = htons(asoc->peer.port); + addr->v4.sin_addr = paddr->v4.sin_addr; + } else { + addr->v6.sin6_family = AF_INET6; + addr->v6.sin6_flowinfo = 0; + if (ipv6_addr_type(&paddr->v6.sin6_addr) & IPV6_ADDR_LINKLOCAL) + addr->v6.sin6_scope_id = paddr->v6.sin6_scope_id; + else + addr->v6.sin6_scope_id = 0; + addr->v6.sin6_port = htons(asoc->peer.port); + addr->v6.sin6_addr = paddr->v6.sin6_addr; } + + *addrlen = sctp_v6_addr_to_user(sctp_sk(asoc->base.sk), addr); } /* Initialize a msg_name from an inbound skb. */ static void sctp_inet6_skb_msgname(struct sk_buff *skb, char *msgname, int *addr_len) { + union sctp_addr *addr; struct sctphdr *sh; - struct sockaddr_in6 *sin6; - - if (msgname) { - sctp_inet6_msgname(msgname, addr_len); - sin6 = (struct sockaddr_in6 *)msgname; - sh = sctp_hdr(skb); - sin6->sin6_port = sh->source; - - /* Map ipv4 address into v4-mapped-on-v6 address. */ - if (sctp_sk(skb->sk)->v4mapped && - ip_hdr(skb)->version == 4) { - sctp_v4_map_v6((union sctp_addr *)sin6); - sin6->sin6_addr.s6_addr32[3] = ip_hdr(skb)->saddr; - return; - } - /* Otherwise, just copy the v6 address. */ - sin6->sin6_addr = ipv6_hdr(skb)->saddr; - if (ipv6_addr_type(&sin6->sin6_addr) & IPV6_ADDR_LINKLOCAL) { + if (!msgname) + return; + + addr = (union sctp_addr *)msgname; + sh = sctp_hdr(skb); + + if (ip_hdr(skb)->version == 4) { + addr->v4.sin_family = AF_INET; + addr->v4.sin_port = sh->source; + addr->v4.sin_addr.s_addr = ip_hdr(skb)->saddr; + } else { + addr->v6.sin6_family = AF_INET6; + addr->v6.sin6_flowinfo = 0; + addr->v6.sin6_port = sh->source; + addr->v6.sin6_addr = ipv6_hdr(skb)->saddr; + if (ipv6_addr_type(&addr->v6.sin6_addr) & IPV6_ADDR_LINKLOCAL) { struct sctp_ulpevent *ev = sctp_skb2event(skb); - sin6->sin6_scope_id = ev->iif; + addr->v6.sin6_scope_id = ev->iif; } } + + *addr_len = sctp_v6_addr_to_user(sctp_sk(skb->sk), addr); } /* Do we support this AF? */ @@ -857,9 +851,6 @@ static int sctp_inet6_bind_verify(struct sctp_sock *opt, union sctp_addr *addr) return 0; } rcu_read_unlock(); - } else if (type == IPV6_ADDR_MAPPED) { - if (!opt->v4mapped) - return 0; } af = opt->pf->af; @@ -914,6 +905,23 @@ static int sctp_inet6_supported_addrs(const struct sctp_sock *opt, return 1; } +/* Handle SCTP_I_WANT_MAPPED_V4_ADDR for getpeername() and getsockname() */ +static int sctp_getname(struct socket *sock, struct sockaddr *uaddr, + int *uaddr_len, int peer) +{ + int rc; + + rc = inet6_getname(sock, uaddr, uaddr_len, peer); + + if (rc != 0) + return rc; + + *uaddr_len = sctp_v6_addr_to_user(sctp_sk(sock->sk), + (union sctp_addr *)uaddr); + + return rc; +} + static const struct proto_ops inet6_seqpacket_ops = { .family = PF_INET6, .owner = THIS_MODULE, @@ -922,7 +930,7 @@ static const struct proto_ops inet6_seqpacket_ops = { .connect = inet_dgram_connect, .socketpair = sock_no_socketpair, .accept = inet_accept, - .getname = inet6_getname, + .getname = sctp_getname, .poll = sctp_poll, .ioctl = inet6_ioctl, .listen = sctp_inet_listen, @@ -974,8 +982,6 @@ static struct sctp_af sctp_af_inet6 = { .copy_addrlist = sctp_v6_copy_addrlist, .from_skb = sctp_v6_from_skb, .from_sk = sctp_v6_from_sk, - .to_sk_saddr = sctp_v6_to_sk_saddr, - .to_sk_daddr = sctp_v6_to_sk_daddr, .from_addr_param = sctp_v6_from_addr_param, .to_addr_param = sctp_v6_to_addr_param, .cmp_addr = sctp_v6_cmp_addr, @@ -1005,7 +1011,9 @@ static struct sctp_pf sctp_pf_inet6 = { .send_verify = sctp_inet6_send_verify, .supported_addrs = sctp_inet6_supported_addrs, .create_accept_sk = sctp_v6_create_accept_sk, - .addr_v4map = sctp_v6_addr_v4map, + .addr_to_user = sctp_v6_addr_to_user, + .to_sk_saddr = sctp_v6_to_sk_saddr, + .to_sk_daddr = sctp_v6_to_sk_daddr, .af = &sctp_af_inet6, }; diff --git a/net/sctp/output.c b/net/sctp/output.c index 01ab8e0723f0..42dffd428389 100644 --- a/net/sctp/output.c +++ b/net/sctp/output.c @@ -178,7 +178,7 @@ sctp_xmit_t sctp_packet_transmit_chunk(struct sctp_packet *packet, case SCTP_XMIT_RWND_FULL: case SCTP_XMIT_OK: - case SCTP_XMIT_NAGLE_DELAY: + case SCTP_XMIT_DELAY: break; } @@ -599,7 +599,7 @@ out: return err; no_route: kfree_skb(nskb); - IP_INC_STATS_BH(sock_net(asoc->base.sk), IPSTATS_MIB_OUTNOROUTES); + IP_INC_STATS(sock_net(asoc->base.sk), IPSTATS_MIB_OUTNOROUTES); /* FIXME: Returning the 'err' will effect all the associations * associated with a socket, although only one of the paths of the @@ -633,7 +633,6 @@ nomem: static sctp_xmit_t sctp_packet_can_append_data(struct sctp_packet *packet, struct sctp_chunk *chunk) { - sctp_xmit_t retval = SCTP_XMIT_OK; size_t datasize, rwnd, inflight, flight_size; struct sctp_transport *transport = packet->transport; struct sctp_association *asoc = transport->asoc; @@ -658,15 +657,11 @@ static sctp_xmit_t sctp_packet_can_append_data(struct sctp_packet *packet, datasize = sctp_data_size(chunk); - if (datasize > rwnd) { - if (inflight > 0) { - /* We have (at least) one data chunk in flight, - * so we can't fall back to rule 6.1 B). - */ - retval = SCTP_XMIT_RWND_FULL; - goto finish; - } - } + if (datasize > rwnd && inflight > 0) + /* We have (at least) one data chunk in flight, + * so we can't fall back to rule 6.1 B). + */ + return SCTP_XMIT_RWND_FULL; /* RFC 2960 6.1 Transmission of DATA Chunks * @@ -680,36 +675,44 @@ static sctp_xmit_t sctp_packet_can_append_data(struct sctp_packet *packet, * When a Fast Retransmit is being performed the sender SHOULD * ignore the value of cwnd and SHOULD NOT delay retransmission. */ - if (chunk->fast_retransmit != SCTP_NEED_FRTX) - if (flight_size >= transport->cwnd) { - retval = SCTP_XMIT_RWND_FULL; - goto finish; - } + if (chunk->fast_retransmit != SCTP_NEED_FRTX && + flight_size >= transport->cwnd) + return SCTP_XMIT_RWND_FULL; /* Nagle's algorithm to solve small-packet problem: * Inhibit the sending of new chunks when new outgoing data arrives * if any previously transmitted data on the connection remains * unacknowledged. */ - if (!sctp_sk(asoc->base.sk)->nodelay && sctp_packet_empty(packet) && - inflight && sctp_state(asoc, ESTABLISHED)) { - unsigned int max = transport->pathmtu - packet->overhead; - unsigned int len = chunk->skb->len + q->out_qlen; - - /* Check whether this chunk and all the rest of pending - * data will fit or delay in hopes of bundling a full - * sized packet. - * Don't delay large message writes that may have been - * fragmeneted into small peices. - */ - if ((len < max) && chunk->msg->can_delay) { - retval = SCTP_XMIT_NAGLE_DELAY; - goto finish; - } - } -finish: - return retval; + if (sctp_sk(asoc->base.sk)->nodelay) + /* Nagle disabled */ + return SCTP_XMIT_OK; + + if (!sctp_packet_empty(packet)) + /* Append to packet */ + return SCTP_XMIT_OK; + + if (inflight == 0) + /* Nothing unacked */ + return SCTP_XMIT_OK; + + if (!sctp_state(asoc, ESTABLISHED)) + return SCTP_XMIT_OK; + + /* Check whether this chunk and all the rest of pending data will fit + * or delay in hopes of bundling a full sized packet. + */ + if (chunk->skb->len + q->out_qlen >= transport->pathmtu - packet->overhead) + /* Enough data queued to fill a packet */ + return SCTP_XMIT_OK; + + /* Don't delay large message writes that may have been fragmented */ + if (!chunk->msg->can_delay) + return SCTP_XMIT_OK; + + /* Defer until all data acked or packet full */ + return SCTP_XMIT_DELAY; } /* This private function does management things when adding DATA chunk */ diff --git a/net/sctp/outqueue.c b/net/sctp/outqueue.c index 9c77947c0597..7e8f0a117106 100644 --- a/net/sctp/outqueue.c +++ b/net/sctp/outqueue.c @@ -629,7 +629,7 @@ redo: done = 1; break; - case SCTP_XMIT_NAGLE_DELAY: + case SCTP_XMIT_DELAY: /* Send this packet. */ error = sctp_packet_transmit(pkt); @@ -1015,7 +1015,7 @@ static int sctp_outq_flush(struct sctp_outq *q, int rtx_timeout) switch (status) { case SCTP_XMIT_PMTU_FULL: case SCTP_XMIT_RWND_FULL: - case SCTP_XMIT_NAGLE_DELAY: + case SCTP_XMIT_DELAY: /* We could not append this chunk, so put * the chunk back on the output queue. */ @@ -1025,7 +1025,6 @@ static int sctp_outq_flush(struct sctp_outq *q, int rtx_timeout) sctp_outq_head_data(q, chunk); goto sctp_flush_out; - break; case SCTP_XMIT_OK: /* The sender is in the SHUTDOWN-PENDING state, diff --git a/net/sctp/protocol.c b/net/sctp/protocol.c index 6789d785e698..6240834f4b95 100644 --- a/net/sctp/protocol.c +++ b/net/sctp/protocol.c @@ -576,10 +576,10 @@ out: return newsk; } -/* Map address, empty for v4 family */ -static void sctp_v4_addr_v4map(struct sctp_sock *sp, union sctp_addr *addr) +static int sctp_v4_addr_to_user(struct sctp_sock *sp, union sctp_addr *addr) { - /* Empty */ + /* No address mapping for V4 sockets */ + return sizeof(struct sockaddr_in); } /* Dump the v4 addr to the seq file. */ @@ -976,7 +976,9 @@ static struct sctp_pf sctp_pf_inet = { .send_verify = sctp_inet_send_verify, .supported_addrs = sctp_inet_supported_addrs, .create_accept_sk = sctp_v4_create_accept_sk, - .addr_v4map = sctp_v4_addr_v4map, + .addr_to_user = sctp_v4_addr_to_user, + .to_sk_saddr = sctp_v4_to_sk_saddr, + .to_sk_daddr = sctp_v4_to_sk_daddr, .af = &sctp_af_inet }; @@ -1047,8 +1049,6 @@ static struct sctp_af sctp_af_inet = { .copy_addrlist = sctp_v4_copy_addrlist, .from_skb = sctp_v4_from_skb, .from_sk = sctp_v4_from_sk, - .to_sk_saddr = sctp_v4_to_sk_saddr, - .to_sk_daddr = sctp_v4_to_sk_daddr, .from_addr_param = sctp_v4_from_addr_param, .to_addr_param = sctp_v4_to_addr_param, .cmp_addr = sctp_v4_cmp_addr, diff --git a/net/sctp/sm_statefuns.c b/net/sctp/sm_statefuns.c index 5170a1ff95a1..d3f1ea460c50 100644 --- a/net/sctp/sm_statefuns.c +++ b/net/sctp/sm_statefuns.c @@ -4182,7 +4182,6 @@ sctp_disposition_t sctp_sf_unk_chunk(struct net *net, case SCTP_CID_ACTION_DISCARD: /* Discard the packet. */ return sctp_sf_pdiscard(net, ep, asoc, type, arg, commands); - break; case SCTP_CID_ACTION_DISCARD_ERR: /* Generate an ERROR chunk as response. */ hdr = unk_chunk->chunk_hdr; @@ -4198,11 +4197,9 @@ sctp_disposition_t sctp_sf_unk_chunk(struct net *net, /* Discard the packet. */ sctp_sf_pdiscard(net, ep, asoc, type, arg, commands); return SCTP_DISPOSITION_CONSUME; - break; case SCTP_CID_ACTION_SKIP: /* Skip the chunk. */ return SCTP_DISPOSITION_DISCARD; - break; case SCTP_CID_ACTION_SKIP_ERR: /* Generate an ERROR chunk as response. */ hdr = unk_chunk->chunk_hdr; @@ -4216,7 +4213,6 @@ sctp_disposition_t sctp_sf_unk_chunk(struct net *net, } /* Skip the chunk. */ return SCTP_DISPOSITION_CONSUME; - break; default: break; } diff --git a/net/sctp/socket.c b/net/sctp/socket.c index 429899689408..eb71d49e7653 100644 --- a/net/sctp/socket.c +++ b/net/sctp/socket.c @@ -254,7 +254,7 @@ static struct sctp_transport *sctp_addr_id2transport(struct sock *sk, if (id_asoc && (id_asoc != addr_asoc)) return NULL; - sctp_get_pf_specific(sk->sk_family)->addr_v4map(sctp_sk(sk), + sctp_get_pf_specific(sk->sk_family)->addr_to_user(sctp_sk(sk), (union sctp_addr *)addr); return transport; @@ -396,7 +396,7 @@ static int sctp_do_bind(struct sock *sk, union sctp_addr *addr, int len) /* Copy back into socket for getsockname() use. */ if (!ret) { inet_sk(sk)->inet_sport = htons(inet_sk(sk)->inet_num); - af->to_sk_saddr(addr, sk); + sp->pf->to_sk_saddr(addr, sk); } return ret; @@ -1053,7 +1053,6 @@ static int __sctp_connect(struct sock *sk, struct sctp_association *asoc2; struct sctp_transport *transport; union sctp_addr to; - struct sctp_af *af; sctp_scope_t scope; long timeo; int err = 0; @@ -1081,6 +1080,8 @@ static int __sctp_connect(struct sock *sk, /* Walk through the addrs buffer and count the number of addresses. */ addr_buf = kaddrs; while (walk_size < addrs_size) { + struct sctp_af *af; + if (walk_size + sizeof(sa_family_t) > addrs_size) { err = -EINVAL; goto out_free; @@ -1205,8 +1206,7 @@ static int __sctp_connect(struct sock *sk, /* Initialize sk's dport and daddr for getpeername() */ inet_sk(sk)->inet_dport = htons(asoc->peer.port); - af = sctp_get_af_specific(sa_addr->sa.sa_family); - af->to_sk_daddr(sa_addr, sk); + sp->pf->to_sk_daddr(sa_addr, sk); sk->sk_err = 0; /* in-kernel sockets don't generally have a file allocated to them @@ -1602,12 +1602,13 @@ static int sctp_sendmsg(struct kiocb *iocb, struct sock *sk, struct sctp_initmsg *sinit; sctp_assoc_t associd = 0; sctp_cmsgs_t cmsgs = { NULL }; - int err; sctp_scope_t scope; - long timeo; - __u16 sinfo_flags = 0; + bool fill_sinfo_ttl = false; struct sctp_datamsg *datamsg; int msg_flags = msg->msg_flags; + __u16 sinfo_flags = 0; + long timeo; + int err; err = 0; sp = sctp_sk(sk); @@ -1648,10 +1649,21 @@ static int sctp_sendmsg(struct kiocb *iocb, struct sock *sk, msg_name = msg->msg_name; } - sinfo = cmsgs.info; sinit = cmsgs.init; + if (cmsgs.sinfo != NULL) { + memset(&default_sinfo, 0, sizeof(default_sinfo)); + default_sinfo.sinfo_stream = cmsgs.sinfo->snd_sid; + default_sinfo.sinfo_flags = cmsgs.sinfo->snd_flags; + default_sinfo.sinfo_ppid = cmsgs.sinfo->snd_ppid; + default_sinfo.sinfo_context = cmsgs.sinfo->snd_context; + default_sinfo.sinfo_assoc_id = cmsgs.sinfo->snd_assoc_id; - /* Did the user specify SNDRCVINFO? */ + sinfo = &default_sinfo; + fill_sinfo_ttl = true; + } else { + sinfo = cmsgs.srinfo; + } + /* Did the user specify SNDINFO/SNDRCVINFO? */ if (sinfo) { sinfo_flags = sinfo->sinfo_flags; associd = sinfo->sinfo_assoc_id; @@ -1858,8 +1870,8 @@ static int sctp_sendmsg(struct kiocb *iocb, struct sock *sk, pr_debug("%s: we have a valid association\n", __func__); if (!sinfo) { - /* If the user didn't specify SNDRCVINFO, make up one with - * some defaults. + /* If the user didn't specify SNDINFO/SNDRCVINFO, make up + * one with some defaults. */ memset(&default_sinfo, 0, sizeof(default_sinfo)); default_sinfo.sinfo_stream = asoc->default_stream; @@ -1868,7 +1880,13 @@ static int sctp_sendmsg(struct kiocb *iocb, struct sock *sk, default_sinfo.sinfo_context = asoc->default_context; default_sinfo.sinfo_timetolive = asoc->default_timetolive; default_sinfo.sinfo_assoc_id = sctp_assoc2id(asoc); + sinfo = &default_sinfo; + } else if (fill_sinfo_ttl) { + /* In case SNDINFO was specified, we still need to fill + * it with a default ttl from the assoc here. + */ + sinfo->sinfo_timetolive = asoc->default_timetolive; } /* API 7.1.7, the sndbuf size per association bounds the @@ -2042,8 +2060,6 @@ static int sctp_skb_pull(struct sk_buff *skb, int len) * flags - flags sent or received with the user message, see Section * 5 for complete description of the flags. */ -static struct sk_buff *sctp_skb_recv_datagram(struct sock *, int, int, int *); - static int sctp_recvmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg, size_t len, int noblock, int flags, int *addr_len) @@ -2094,9 +2110,16 @@ static int sctp_recvmsg(struct kiocb *iocb, struct sock *sk, sp->pf->skb_msgname(skb, msg->msg_name, addr_len); } + /* Check if we allow SCTP_NXTINFO. */ + if (sp->recvnxtinfo) + sctp_ulpevent_read_nxtinfo(event, msg, sk); + /* Check if we allow SCTP_RCVINFO. */ + if (sp->recvrcvinfo) + sctp_ulpevent_read_rcvinfo(event, msg); /* Check if we allow SCTP_SNDRCVINFO. */ if (sp->subscribe.sctp_data_io_event) sctp_ulpevent_read_sndrcvinfo(event, msg); + #if 0 /* FIXME: we should be calling IP/IPv6 layers. */ if (sk->sk_protinfo.af_inet.cmsg_flags) @@ -2182,8 +2205,13 @@ static int sctp_setsockopt_events(struct sock *sk, char __user *optval, if (copy_from_user(&sctp_sk(sk)->subscribe, optval, optlen)) return -EFAULT; - /* - * At the time when a user app subscribes to SCTP_SENDER_DRY_EVENT, + if (sctp_sk(sk)->subscribe.sctp_data_io_event) + pr_warn_ratelimited(DEPRECATED "%s (pid %d) " + "Requested SCTP_SNDRCVINFO event.\n" + "Use SCTP_RCVINFO through SCTP_RECVRCVINFO option instead.\n", + current->comm, task_pid_nr(current)); + + /* At the time when a user app subscribes to SCTP_SENDER_DRY_EVENT, * if there is no data to be sent or retransmit, the stack will * immediately send up this notification. */ @@ -2747,19 +2775,22 @@ static int sctp_setsockopt_default_send_param(struct sock *sk, char __user *optval, unsigned int optlen) { - struct sctp_sndrcvinfo info; - struct sctp_association *asoc; struct sctp_sock *sp = sctp_sk(sk); + struct sctp_association *asoc; + struct sctp_sndrcvinfo info; - if (optlen != sizeof(struct sctp_sndrcvinfo)) + if (optlen != sizeof(info)) return -EINVAL; if (copy_from_user(&info, optval, optlen)) return -EFAULT; + if (info.sinfo_flags & + ~(SCTP_UNORDERED | SCTP_ADDR_OVER | + SCTP_ABORT | SCTP_EOF)) + return -EINVAL; asoc = sctp_id2assoc(sk, info.sinfo_assoc_id); if (!asoc && info.sinfo_assoc_id && sctp_style(sk, UDP)) return -EINVAL; - if (asoc) { asoc->default_stream = info.sinfo_stream; asoc->default_flags = info.sinfo_flags; @@ -2777,6 +2808,44 @@ static int sctp_setsockopt_default_send_param(struct sock *sk, return 0; } +/* RFC6458, Section 8.1.31. Set/get Default Send Parameters + * (SCTP_DEFAULT_SNDINFO) + */ +static int sctp_setsockopt_default_sndinfo(struct sock *sk, + char __user *optval, + unsigned int optlen) +{ + struct sctp_sock *sp = sctp_sk(sk); + struct sctp_association *asoc; + struct sctp_sndinfo info; + + if (optlen != sizeof(info)) + return -EINVAL; + if (copy_from_user(&info, optval, optlen)) + return -EFAULT; + if (info.snd_flags & + ~(SCTP_UNORDERED | SCTP_ADDR_OVER | + SCTP_ABORT | SCTP_EOF)) + return -EINVAL; + + asoc = sctp_id2assoc(sk, info.snd_assoc_id); + if (!asoc && info.snd_assoc_id && sctp_style(sk, UDP)) + return -EINVAL; + if (asoc) { + asoc->default_stream = info.snd_sid; + asoc->default_flags = info.snd_flags; + asoc->default_ppid = info.snd_ppid; + asoc->default_context = info.snd_context; + } else { + sp->default_stream = info.snd_sid; + sp->default_flags = info.snd_flags; + sp->default_ppid = info.snd_ppid; + sp->default_context = info.snd_context; + } + + return 0; +} + /* 7.1.10 Set Primary Address (SCTP_PRIMARY_ADDR) * * Requests that the local SCTP stack use the enclosed peer address as @@ -3523,7 +3592,6 @@ static int sctp_setsockopt_auto_asconf(struct sock *sk, char __user *optval, return 0; } - /* * SCTP_PEER_ADDR_THLDS * @@ -3574,6 +3642,38 @@ static int sctp_setsockopt_paddr_thresholds(struct sock *sk, return 0; } +static int sctp_setsockopt_recvrcvinfo(struct sock *sk, + char __user *optval, + unsigned int optlen) +{ + int val; + + if (optlen < sizeof(int)) + return -EINVAL; + if (get_user(val, (int __user *) optval)) + return -EFAULT; + + sctp_sk(sk)->recvrcvinfo = (val == 0) ? 0 : 1; + + return 0; +} + +static int sctp_setsockopt_recvnxtinfo(struct sock *sk, + char __user *optval, + unsigned int optlen) +{ + int val; + + if (optlen < sizeof(int)) + return -EINVAL; + if (get_user(val, (int __user *) optval)) + return -EFAULT; + + sctp_sk(sk)->recvnxtinfo = (val == 0) ? 0 : 1; + + return 0; +} + /* API 6.2 setsockopt(), getsockopt() * * Applications use setsockopt() and getsockopt() to set or retrieve @@ -3671,6 +3771,9 @@ static int sctp_setsockopt(struct sock *sk, int level, int optname, retval = sctp_setsockopt_default_send_param(sk, optval, optlen); break; + case SCTP_DEFAULT_SNDINFO: + retval = sctp_setsockopt_default_sndinfo(sk, optval, optlen); + break; case SCTP_PRIMARY_ADDR: retval = sctp_setsockopt_primary_addr(sk, optval, optlen); break; @@ -3725,6 +3828,12 @@ static int sctp_setsockopt(struct sock *sk, int level, int optname, case SCTP_PEER_ADDR_THLDS: retval = sctp_setsockopt_paddr_thresholds(sk, optval, optlen); break; + case SCTP_RECVRCVINFO: + retval = sctp_setsockopt_recvrcvinfo(sk, optval, optlen); + break; + case SCTP_RECVNXTINFO: + retval = sctp_setsockopt_recvnxtinfo(sk, optval, optlen); + break; default: retval = -ENOPROTOOPT; break; @@ -3971,6 +4080,9 @@ static int sctp_init_sock(struct sock *sk) /* Enable Nagle algorithm by default. */ sp->nodelay = 0; + sp->recvrcvinfo = 0; + sp->recvnxtinfo = 0; + /* Enable by default. */ sp->v4mapped = 1; @@ -4143,7 +4255,7 @@ static int sctp_getsockopt_sctp_status(struct sock *sk, int len, memcpy(&status.sstat_primary.spinfo_address, &transport->ipaddr, transport->af_specific->sockaddr_len); /* Map ipv4 address into v4-mapped-on-v6 address. */ - sctp_get_pf_specific(sk->sk_family)->addr_v4map(sctp_sk(sk), + sctp_get_pf_specific(sk->sk_family)->addr_to_user(sctp_sk(sk), (union sctp_addr *)&status.sstat_primary.spinfo_address); status.sstat_primary.spinfo_state = transport->state; status.sstat_primary.spinfo_cwnd = transport->cwnd; @@ -4301,8 +4413,8 @@ static int sctp_getsockopt_autoclose(struct sock *sk, int len, char __user *optv int sctp_do_peeloff(struct sock *sk, sctp_assoc_t id, struct socket **sockp) { struct sctp_association *asoc = sctp_id2assoc(sk, id); + struct sctp_sock *sp = sctp_sk(sk); struct socket *sock; - struct sctp_af *af; int err = 0; if (!asoc) @@ -4324,8 +4436,7 @@ int sctp_do_peeloff(struct sock *sk, sctp_assoc_t id, struct socket **sockp) /* Make peeled-off sockets more like 1-1 accepted sockets. * Set the daddr and initialize id to something more random */ - af = sctp_get_af_specific(asoc->peer.primary_addr.sa.sa_family); - af->to_sk_daddr(&asoc->peer.primary_addr, sk); + sp->pf->to_sk_daddr(&asoc->peer.primary_addr, sk); /* Populate the fields of the newsk from the oldsk and migrate the * asoc to the newsk. @@ -4709,8 +4820,8 @@ static int sctp_getsockopt_peer_addrs(struct sock *sk, int len, list_for_each_entry(from, &asoc->peer.transport_addr_list, transports) { memcpy(&temp, &from->ipaddr, sizeof(temp)); - sctp_get_pf_specific(sk->sk_family)->addr_v4map(sp, &temp); - addrlen = sctp_get_af_specific(temp.sa.sa_family)->sockaddr_len; + addrlen = sctp_get_pf_specific(sk->sk_family) + ->addr_to_user(sp, &temp); if (space_left < addrlen) return -ENOMEM; if (copy_to_user(to, &temp, addrlen)) @@ -4754,9 +4865,9 @@ static int sctp_copy_laddrs(struct sock *sk, __u16 port, void *to, if (!temp.v4.sin_port) temp.v4.sin_port = htons(port); - sctp_get_pf_specific(sk->sk_family)->addr_v4map(sctp_sk(sk), - &temp); - addrlen = sctp_get_af_specific(temp.sa.sa_family)->sockaddr_len; + addrlen = sctp_get_pf_specific(sk->sk_family) + ->addr_to_user(sctp_sk(sk), &temp); + if (space_left < addrlen) { cnt = -ENOMEM; break; @@ -4844,8 +4955,8 @@ static int sctp_getsockopt_local_addrs(struct sock *sk, int len, */ list_for_each_entry(addr, &bp->address_list, list) { memcpy(&temp, &addr->a, sizeof(temp)); - sctp_get_pf_specific(sk->sk_family)->addr_v4map(sp, &temp); - addrlen = sctp_get_af_specific(temp.sa.sa_family)->sockaddr_len; + addrlen = sctp_get_pf_specific(sk->sk_family) + ->addr_to_user(sp, &temp); if (space_left < addrlen) { err = -ENOMEM; /*fixme: right error?*/ goto out; @@ -4904,7 +5015,7 @@ static int sctp_getsockopt_primary_addr(struct sock *sk, int len, memcpy(&prim.ssp_addr, &asoc->peer.primary_path->ipaddr, asoc->peer.primary_path->af_specific->sockaddr_len); - sctp_get_pf_specific(sk->sk_family)->addr_v4map(sp, + sctp_get_pf_specific(sk->sk_family)->addr_to_user(sp, (union sctp_addr *)&prim.ssp_addr); if (put_user(len, optlen)) @@ -4964,14 +5075,14 @@ static int sctp_getsockopt_default_send_param(struct sock *sk, int len, char __user *optval, int __user *optlen) { - struct sctp_sndrcvinfo info; - struct sctp_association *asoc; struct sctp_sock *sp = sctp_sk(sk); + struct sctp_association *asoc; + struct sctp_sndrcvinfo info; - if (len < sizeof(struct sctp_sndrcvinfo)) + if (len < sizeof(info)) return -EINVAL; - len = sizeof(struct sctp_sndrcvinfo); + len = sizeof(info); if (copy_from_user(&info, optval, len)) return -EFAULT; @@ -4979,7 +5090,6 @@ static int sctp_getsockopt_default_send_param(struct sock *sk, asoc = sctp_id2assoc(sk, info.sinfo_assoc_id); if (!asoc && info.sinfo_assoc_id && sctp_style(sk, UDP)) return -EINVAL; - if (asoc) { info.sinfo_stream = asoc->default_stream; info.sinfo_flags = asoc->default_flags; @@ -5002,6 +5112,48 @@ static int sctp_getsockopt_default_send_param(struct sock *sk, return 0; } +/* RFC6458, Section 8.1.31. Set/get Default Send Parameters + * (SCTP_DEFAULT_SNDINFO) + */ +static int sctp_getsockopt_default_sndinfo(struct sock *sk, int len, + char __user *optval, + int __user *optlen) +{ + struct sctp_sock *sp = sctp_sk(sk); + struct sctp_association *asoc; + struct sctp_sndinfo info; + + if (len < sizeof(info)) + return -EINVAL; + + len = sizeof(info); + + if (copy_from_user(&info, optval, len)) + return -EFAULT; + + asoc = sctp_id2assoc(sk, info.snd_assoc_id); + if (!asoc && info.snd_assoc_id && sctp_style(sk, UDP)) + return -EINVAL; + if (asoc) { + info.snd_sid = asoc->default_stream; + info.snd_flags = asoc->default_flags; + info.snd_ppid = asoc->default_ppid; + info.snd_context = asoc->default_context; + } else { + info.snd_sid = sp->default_stream; + info.snd_flags = sp->default_flags; + info.snd_ppid = sp->default_ppid; + info.snd_context = sp->default_context; + } + + if (put_user(len, optlen)) + return -EFAULT; + if (copy_to_user(optval, &info, len)) + return -EFAULT; + + return 0; +} + /* * * 7.1.5 SCTP_NODELAY @@ -5752,6 +5904,46 @@ static int sctp_getsockopt_assoc_stats(struct sock *sk, int len, return 0; } +static int sctp_getsockopt_recvrcvinfo(struct sock *sk, int len, + char __user *optval, + int __user *optlen) +{ + int val = 0; + + if (len < sizeof(int)) + return -EINVAL; + + len = sizeof(int); + if (sctp_sk(sk)->recvrcvinfo) + val = 1; + if (put_user(len, optlen)) + return -EFAULT; + if (copy_to_user(optval, &val, len)) + return -EFAULT; + + return 0; +} + +static int sctp_getsockopt_recvnxtinfo(struct sock *sk, int len, + char __user *optval, + int __user *optlen) +{ + int val = 0; + + if (len < sizeof(int)) + return -EINVAL; + + len = sizeof(int); + if (sctp_sk(sk)->recvnxtinfo) + val = 1; + if (put_user(len, optlen)) + return -EFAULT; + if (copy_to_user(optval, &val, len)) + return -EFAULT; + + return 0; +} + static int sctp_getsockopt(struct sock *sk, int level, int optname, char __user *optval, int __user *optlen) { @@ -5821,6 +6013,10 @@ static int sctp_getsockopt(struct sock *sk, int level, int optname, retval = sctp_getsockopt_default_send_param(sk, len, optval, optlen); break; + case SCTP_DEFAULT_SNDINFO: + retval = sctp_getsockopt_default_sndinfo(sk, len, + optval, optlen); + break; case SCTP_PRIMARY_ADDR: retval = sctp_getsockopt_primary_addr(sk, len, optval, optlen); break; @@ -5895,6 +6091,12 @@ static int sctp_getsockopt(struct sock *sk, int level, int optname, case SCTP_GET_ASSOC_STATS: retval = sctp_getsockopt_assoc_stats(sk, len, optval, optlen); break; + case SCTP_RECVRCVINFO: + retval = sctp_getsockopt_recvrcvinfo(sk, len, optval, optlen); + break; + case SCTP_RECVNXTINFO: + retval = sctp_getsockopt_recvnxtinfo(sk, len, optval, optlen); + break; default: retval = -ENOPROTOOPT; break; @@ -6390,8 +6592,7 @@ static int sctp_msghdr_parse(const struct msghdr *msg, sctp_cmsgs_t *cmsgs) struct cmsghdr *cmsg; struct msghdr *my_msg = (struct msghdr *)msg; - for (cmsg = CMSG_FIRSTHDR(msg); - cmsg != NULL; + for (cmsg = CMSG_FIRSTHDR(msg); cmsg != NULL; cmsg = CMSG_NXTHDR(my_msg, cmsg)) { if (!CMSG_OK(my_msg, cmsg)) return -EINVAL; @@ -6404,7 +6605,7 @@ static int sctp_msghdr_parse(const struct msghdr *msg, sctp_cmsgs_t *cmsgs) switch (cmsg->cmsg_type) { case SCTP_INIT: /* SCTP Socket API Extension - * 5.2.1 SCTP Initiation Structure (SCTP_INIT) + * 5.3.1 SCTP Initiation Structure (SCTP_INIT) * * This cmsghdr structure provides information for * initializing new SCTP associations with sendmsg(). @@ -6416,15 +6617,15 @@ static int sctp_msghdr_parse(const struct msghdr *msg, sctp_cmsgs_t *cmsgs) * ------------ ------------ ---------------------- * IPPROTO_SCTP SCTP_INIT struct sctp_initmsg */ - if (cmsg->cmsg_len != - CMSG_LEN(sizeof(struct sctp_initmsg))) + if (cmsg->cmsg_len != CMSG_LEN(sizeof(struct sctp_initmsg))) return -EINVAL; - cmsgs->init = (struct sctp_initmsg *)CMSG_DATA(cmsg); + + cmsgs->init = CMSG_DATA(cmsg); break; case SCTP_SNDRCV: /* SCTP Socket API Extension - * 5.2.2 SCTP Header Information Structure(SCTP_SNDRCV) + * 5.3.2 SCTP Header Information Structure(SCTP_SNDRCV) * * This cmsghdr structure specifies SCTP options for * sendmsg() and describes SCTP header information @@ -6434,24 +6635,44 @@ static int sctp_msghdr_parse(const struct msghdr *msg, sctp_cmsgs_t *cmsgs) * ------------ ------------ ---------------------- * IPPROTO_SCTP SCTP_SNDRCV struct sctp_sndrcvinfo */ - if (cmsg->cmsg_len != - CMSG_LEN(sizeof(struct sctp_sndrcvinfo))) + if (cmsg->cmsg_len != CMSG_LEN(sizeof(struct sctp_sndrcvinfo))) return -EINVAL; - cmsgs->info = - (struct sctp_sndrcvinfo *)CMSG_DATA(cmsg); + cmsgs->srinfo = CMSG_DATA(cmsg); - /* Minimally, validate the sinfo_flags. */ - if (cmsgs->info->sinfo_flags & + if (cmsgs->srinfo->sinfo_flags & ~(SCTP_UNORDERED | SCTP_ADDR_OVER | SCTP_ABORT | SCTP_EOF)) return -EINVAL; break; + case SCTP_SNDINFO: + /* SCTP Socket API Extension + * 5.3.4 SCTP Send Information Structure (SCTP_SNDINFO) + * + * This cmsghdr structure specifies SCTP options for + * sendmsg(). This structure and SCTP_RCVINFO replaces + * SCTP_SNDRCV which has been deprecated. + * + * cmsg_level cmsg_type cmsg_data[] + * ------------ ------------ --------------------- + * IPPROTO_SCTP SCTP_SNDINFO struct sctp_sndinfo + */ + if (cmsg->cmsg_len != CMSG_LEN(sizeof(struct sctp_sndinfo))) + return -EINVAL; + + cmsgs->sinfo = CMSG_DATA(cmsg); + + if (cmsgs->sinfo->snd_flags & + ~(SCTP_UNORDERED | SCTP_ADDR_OVER | + SCTP_ABORT | SCTP_EOF)) + return -EINVAL; + break; default: return -EINVAL; } } + return 0; } @@ -6518,8 +6739,8 @@ out: * Note: This is pretty much the same routine as in core/datagram.c * with a few changes to make lksctp work. */ -static struct sk_buff *sctp_skb_recv_datagram(struct sock *sk, int flags, - int noblock, int *err) +struct sk_buff *sctp_skb_recv_datagram(struct sock *sk, int flags, + int noblock, int *err) { int error; struct sk_buff *skb; diff --git a/net/sctp/sysctl.c b/net/sctp/sysctl.c index 12c7e01c2677..2e9ada10fd84 100644 --- a/net/sctp/sysctl.c +++ b/net/sctp/sysctl.c @@ -424,8 +424,9 @@ static int proc_sctp_do_alpha_beta(struct ctl_table *ctl, int write, void __user *buffer, size_t *lenp, loff_t *ppos) { - pr_warn_once("Changing rto_alpha or rto_beta may lead to " - "suboptimal rtt/srtt estimations!\n"); + if (write) + pr_warn_once("Changing rto_alpha or rto_beta may lead to " + "suboptimal rtt/srtt estimations!\n"); return proc_dointvec_minmax(ctl, write, buffer, lenp, ppos); } diff --git a/net/sctp/transport.c b/net/sctp/transport.c index 7dd672fa651f..a0a431824f63 100644 --- a/net/sctp/transport.c +++ b/net/sctp/transport.c @@ -289,8 +289,8 @@ void sctp_transport_route(struct sctp_transport *transport, */ if (asoc && (!asoc->peer.primary_path || (transport == asoc->peer.active_path))) - opt->pf->af->to_sk_saddr(&transport->saddr, - asoc->base.sk); + opt->pf->to_sk_saddr(&transport->saddr, + asoc->base.sk); } else transport->pathmtu = SCTP_DEFAULT_MAXSEGMENT; } @@ -594,15 +594,16 @@ void sctp_transport_burst_reset(struct sctp_transport *t) } /* What is the next timeout value for this transport? */ -unsigned long sctp_transport_timeout(struct sctp_transport *t) +unsigned long sctp_transport_timeout(struct sctp_transport *trans) { - unsigned long timeout; - timeout = t->rto + sctp_jitter(t->rto); - if ((t->state != SCTP_UNCONFIRMED) && - (t->state != SCTP_PF)) - timeout += t->hbinterval; - timeout += jiffies; - return timeout; + /* RTO + timer slack +/- 50% of RTO */ + unsigned long timeout = (trans->rto >> 1) + prandom_u32_max(trans->rto); + + if (trans->state != SCTP_UNCONFIRMED && + trans->state != SCTP_PF) + timeout += trans->hbinterval; + + return timeout + jiffies; } /* Reset transport variables to their initial values */ diff --git a/net/sctp/ulpevent.c b/net/sctp/ulpevent.c index b6842fdb53d4..d1e38308f615 100644 --- a/net/sctp/ulpevent.c +++ b/net/sctp/ulpevent.c @@ -341,7 +341,7 @@ struct sctp_ulpevent *sctp_ulpevent_make_peer_addr_change( memcpy(&spc->spc_aaddr, aaddr, sizeof(struct sockaddr_storage)); /* Map ipv4 address into v4-mapped-on-v6 address. */ - sctp_get_pf_specific(asoc->base.sk->sk_family)->addr_v4map( + sctp_get_pf_specific(asoc->base.sk->sk_family)->addr_to_user( sctp_sk(asoc->base.sk), (union sctp_addr *)&spc->spc_aaddr); @@ -886,6 +886,69 @@ void sctp_ulpevent_read_sndrcvinfo(const struct sctp_ulpevent *event, sizeof(sinfo), &sinfo); } +/* RFC6458, Section 5.3.5 SCTP Receive Information Structure + * (SCTP_SNDRCV) + */ +void sctp_ulpevent_read_rcvinfo(const struct sctp_ulpevent *event, + struct msghdr *msghdr) +{ + struct sctp_rcvinfo rinfo; + + if (sctp_ulpevent_is_notification(event)) + return; + + memset(&rinfo, 0, sizeof(struct sctp_rcvinfo)); + rinfo.rcv_sid = event->stream; + rinfo.rcv_ssn = event->ssn; + rinfo.rcv_ppid = event->ppid; + rinfo.rcv_flags = event->flags; + rinfo.rcv_tsn = event->tsn; + rinfo.rcv_cumtsn = event->cumtsn; + rinfo.rcv_assoc_id = sctp_assoc2id(event->asoc); + rinfo.rcv_context = event->asoc->default_rcv_context; + + put_cmsg(msghdr, IPPROTO_SCTP, SCTP_RCVINFO, + sizeof(rinfo), &rinfo); +} + +/* RFC6458, Section 5.3.6. SCTP Next Receive Information Structure + * (SCTP_NXTINFO) + */ +static void __sctp_ulpevent_read_nxtinfo(const struct sctp_ulpevent *event, + struct msghdr *msghdr, + const struct sk_buff *skb) +{ + struct sctp_nxtinfo nxtinfo; + + memset(&nxtinfo, 0, sizeof(nxtinfo)); + nxtinfo.nxt_sid = event->stream; + nxtinfo.nxt_ppid = event->ppid; + nxtinfo.nxt_flags = event->flags; + if (sctp_ulpevent_is_notification(event)) + nxtinfo.nxt_flags |= SCTP_NOTIFICATION; + nxtinfo.nxt_length = skb->len; + nxtinfo.nxt_assoc_id = sctp_assoc2id(event->asoc); + + put_cmsg(msghdr, IPPROTO_SCTP, SCTP_NXTINFO, + sizeof(nxtinfo), &nxtinfo); +} + +void sctp_ulpevent_read_nxtinfo(const struct sctp_ulpevent *event, + struct msghdr *msghdr, + struct sock *sk) +{ + struct sk_buff *skb; + int err; + + skb = sctp_skb_recv_datagram(sk, MSG_PEEK, 1, &err); + if (skb != NULL) { + __sctp_ulpevent_read_nxtinfo(sctp_skb2event(skb), + msghdr, skb); + /* Just release refcount here. */ + kfree_skb(skb); + } +} + /* Do accounting for bytes received and hold a reference to the association * for each skb. */ diff --git a/net/socket.c b/net/socket.c index abf56b2a14f9..ae89569a2db5 100644 --- a/net/socket.c +++ b/net/socket.c @@ -106,6 +106,7 @@ #include <linux/sockios.h> #include <linux/atalk.h> #include <net/busy_poll.h> +#include <linux/errqueue.h> #ifdef CONFIG_NET_RX_BUSY_POLL unsigned int sysctl_net_busy_read __read_mostly; @@ -612,10 +613,15 @@ EXPORT_SYMBOL(sock_release); void sock_tx_timestamp(struct sock *sk, __u8 *tx_flags) { *tx_flags = 0; - if (sock_flag(sk, SOCK_TIMESTAMPING_TX_HARDWARE)) + if (sk->sk_tsflags & SOF_TIMESTAMPING_TX_HARDWARE) *tx_flags |= SKBTX_HW_TSTAMP; - if (sock_flag(sk, SOCK_TIMESTAMPING_TX_SOFTWARE)) + if (sk->sk_tsflags & SOF_TIMESTAMPING_TX_SOFTWARE) *tx_flags |= SKBTX_SW_TSTAMP; + if (sk->sk_tsflags & SOF_TIMESTAMPING_TX_SCHED) + *tx_flags |= SKBTX_SCHED_TSTAMP; + if (sk->sk_tsflags & SOF_TIMESTAMPING_TX_ACK) + *tx_flags |= SKBTX_ACK_TSTAMP; + if (sock_flag(sk, SOCK_WIFI_STATUS)) *tx_flags |= SKBTX_WIFI_STATUS; } @@ -697,7 +703,7 @@ void __sock_recv_timestamp(struct msghdr *msg, struct sock *sk, struct sk_buff *skb) { int need_software_tstamp = sock_flag(sk, SOCK_RCVTSTAMP); - struct timespec ts[3]; + struct scm_timestamping tss; int empty = 1; struct skb_shared_hwtstamps *shhwtstamps = skb_hwtstamps(skb); @@ -714,28 +720,25 @@ void __sock_recv_timestamp(struct msghdr *msg, struct sock *sk, put_cmsg(msg, SOL_SOCKET, SCM_TIMESTAMP, sizeof(tv), &tv); } else { - skb_get_timestampns(skb, &ts[0]); + struct timespec ts; + skb_get_timestampns(skb, &ts); put_cmsg(msg, SOL_SOCKET, SCM_TIMESTAMPNS, - sizeof(ts[0]), &ts[0]); + sizeof(ts), &ts); } } - - memset(ts, 0, sizeof(ts)); - if (sock_flag(sk, SOCK_TIMESTAMPING_SOFTWARE) && - ktime_to_timespec_cond(skb->tstamp, ts + 0)) + memset(&tss, 0, sizeof(tss)); + if ((sk->sk_tsflags & SOF_TIMESTAMPING_SOFTWARE || + skb_shinfo(skb)->tx_flags & SKBTX_ANY_SW_TSTAMP) && + ktime_to_timespec_cond(skb->tstamp, tss.ts + 0)) + empty = 0; + if (shhwtstamps && + (sk->sk_tsflags & SOF_TIMESTAMPING_RAW_HARDWARE) && + ktime_to_timespec_cond(shhwtstamps->hwtstamp, tss.ts + 2)) empty = 0; - if (shhwtstamps) { - if (sock_flag(sk, SOCK_TIMESTAMPING_SYS_HARDWARE) && - ktime_to_timespec_cond(shhwtstamps->syststamp, ts + 1)) - empty = 0; - if (sock_flag(sk, SOCK_TIMESTAMPING_RAW_HARDWARE) && - ktime_to_timespec_cond(shhwtstamps->hwtstamp, ts + 2)) - empty = 0; - } if (!empty) put_cmsg(msg, SOL_SOCKET, - SCM_TIMESTAMPING, sizeof(ts), &ts); + SCM_TIMESTAMPING, sizeof(tss), &tss); } EXPORT_SYMBOL_GPL(__sock_recv_timestamp); diff --git a/net/tipc/bcast.c b/net/tipc/bcast.c index 55c6c9d3e1ce..dd13bfa09333 100644 --- a/net/tipc/bcast.c +++ b/net/tipc/bcast.c @@ -1,7 +1,7 @@ /* * net/tipc/bcast.c: TIPC broadcast code * - * Copyright (c) 2004-2006, Ericsson AB + * Copyright (c) 2004-2006, 2014, Ericsson AB * Copyright (c) 2004, Intel Corporation. * Copyright (c) 2005, 2010-2011, Wind River Systems * All rights reserved. @@ -38,6 +38,8 @@ #include "core.h" #include "link.h" #include "port.h" +#include "socket.h" +#include "msg.h" #include "bcast.h" #include "name_distr.h" @@ -138,6 +140,11 @@ static void tipc_bclink_unlock(void) tipc_link_reset_all(node); } +uint tipc_bclink_get_mtu(void) +{ + return MAX_PKT_DEFAULT_MCAST; +} + void tipc_bclink_set_flags(unsigned int flags) { bclink->flags |= flags; @@ -382,30 +389,50 @@ static void bclink_peek_nack(struct tipc_msg *msg) tipc_node_unlock(n_ptr); } -/* - * tipc_bclink_xmit - broadcast a packet to all nodes in cluster +/* tipc_bclink_xmit - broadcast buffer chain to all nodes in cluster + * and to identified node local sockets + * @buf: chain of buffers containing message + * Consumes the buffer chain, except when returning -ELINKCONG + * Returns 0 if success, otherwise errno: -ELINKCONG,-EHOSTUNREACH,-EMSGSIZE */ int tipc_bclink_xmit(struct sk_buff *buf) { - int res; + int rc = 0; + int bc = 0; + struct sk_buff *clbuf; - tipc_bclink_lock(); - - if (!bclink->bcast_nodes.count) { - res = msg_data_sz(buf_msg(buf)); - kfree_skb(buf); - goto exit; + /* Prepare clone of message for local node */ + clbuf = tipc_msg_reassemble(buf); + if (unlikely(!clbuf)) { + kfree_skb_list(buf); + return -EHOSTUNREACH; } - res = __tipc_link_xmit(bcl, buf); - if (likely(res >= 0)) { - bclink_set_last_sent(); - bcl->stats.queue_sz_counts++; - bcl->stats.accu_queue_sz += bcl->out_queue_size; + /* Broadcast to all other nodes */ + if (likely(bclink)) { + tipc_bclink_lock(); + if (likely(bclink->bcast_nodes.count)) { + rc = __tipc_link_xmit(bcl, buf); + if (likely(!rc)) { + bclink_set_last_sent(); + bcl->stats.queue_sz_counts++; + bcl->stats.accu_queue_sz += bcl->out_queue_size; + } + bc = 1; + } + tipc_bclink_unlock(); } -exit: - tipc_bclink_unlock(); - return res; + + if (unlikely(!bc)) + kfree_skb_list(buf); + + /* Deliver message clone */ + if (likely(!rc)) + tipc_sk_mcast_rcv(clbuf); + else + kfree_skb(clbuf); + + return rc; } /** @@ -443,7 +470,7 @@ void tipc_bclink_rcv(struct sk_buff *buf) struct tipc_node *node; u32 next_in; u32 seqno; - int deferred; + int deferred = 0; /* Screen out unwanted broadcast messages */ @@ -494,7 +521,7 @@ receive: tipc_bclink_unlock(); tipc_node_unlock(node); if (likely(msg_mcast(msg))) - tipc_port_mcast_rcv(buf, NULL); + tipc_sk_mcast_rcv(buf); else kfree_skb(buf); } else if (msg_user(msg) == MSG_BUNDLER) { @@ -573,8 +600,7 @@ receive: node->bclink.deferred_size += deferred; bclink_update_last_sent(node, seqno); buf = NULL; - } else - deferred = 0; + } tipc_bclink_lock(); @@ -611,6 +637,7 @@ static int tipc_bcbearer_send(struct sk_buff *buf, struct tipc_bearer *unused1, struct tipc_media_addr *unused2) { int bp_index; + struct tipc_msg *msg = buf_msg(buf); /* Prepare broadcast link message for reliable transmission, * if first time trying to send it; @@ -618,10 +645,7 @@ static int tipc_bcbearer_send(struct sk_buff *buf, struct tipc_bearer *unused1, * since they are sent in an unreliable manner and don't need it */ if (likely(!msg_non_seq(buf_msg(buf)))) { - struct tipc_msg *msg; - bcbuf_set_acks(buf, bclink->bcast_nodes.count); - msg = buf_msg(buf); msg_set_non_seq(msg, 1); msg_set_mc_netid(msg, tipc_net_id); bcl->stats.sent_info++; @@ -638,12 +662,14 @@ static int tipc_bcbearer_send(struct sk_buff *buf, struct tipc_bearer *unused1, for (bp_index = 0; bp_index < MAX_BEARERS; bp_index++) { struct tipc_bearer *p = bcbearer->bpairs[bp_index].primary; struct tipc_bearer *s = bcbearer->bpairs[bp_index].secondary; - struct tipc_bearer *b = p; + struct tipc_bearer *bp[2] = {p, s}; + struct tipc_bearer *b = bp[msg_link_selector(msg)]; struct sk_buff *tbuf; if (!p) break; /* No more bearers to try */ - + if (!b) + b = p; tipc_nmap_diff(&bcbearer->remains, &b->nodes, &bcbearer->remains_new); if (bcbearer->remains_new.count == bcbearer->remains.count) @@ -660,13 +686,6 @@ static int tipc_bcbearer_send(struct sk_buff *buf, struct tipc_bearer *unused1, tipc_bearer_send(b->identity, tbuf, &b->bcast_addr); kfree_skb(tbuf); /* Bearer keeps a clone */ } - - /* Swap bearers for next packet */ - if (s) { - bcbearer->bpairs[bp_index].primary = s; - bcbearer->bpairs[bp_index].secondary = p; - } - if (bcbearer->remains_new.count == 0) break; /* All targets reached */ diff --git a/net/tipc/bcast.h b/net/tipc/bcast.h index 00330c45df3e..4875d9536aee 100644 --- a/net/tipc/bcast.h +++ b/net/tipc/bcast.h @@ -1,7 +1,7 @@ /* * net/tipc/bcast.h: Include file for TIPC broadcast code * - * Copyright (c) 2003-2006, Ericsson AB + * Copyright (c) 2003-2006, 2014, Ericsson AB * Copyright (c) 2005, 2010-2011, Wind River Systems * All rights reserved. * @@ -89,7 +89,6 @@ void tipc_bclink_add_node(u32 addr); void tipc_bclink_remove_node(u32 addr); struct tipc_node *tipc_bclink_retransmit_to(void); void tipc_bclink_acknowledge(struct tipc_node *n_ptr, u32 acked); -int tipc_bclink_xmit(struct sk_buff *buf); void tipc_bclink_rcv(struct sk_buff *buf); u32 tipc_bclink_get_last_sent(void); u32 tipc_bclink_acks_missing(struct tipc_node *n_ptr); @@ -98,5 +97,7 @@ int tipc_bclink_stats(char *stats_buf, const u32 buf_size); int tipc_bclink_reset_stats(void); int tipc_bclink_set_queue_limits(u32 limit); void tipc_bcbearer_sort(struct tipc_node_map *nm_ptr, u32 node, bool action); +uint tipc_bclink_get_mtu(void); +int tipc_bclink_xmit(struct sk_buff *buf); #endif diff --git a/net/tipc/link.c b/net/tipc/link.c index ad2c57f5868d..fb1485dc6736 100644 --- a/net/tipc/link.c +++ b/net/tipc/link.c @@ -82,15 +82,13 @@ static void tipc_link_proto_rcv(struct tipc_link *l_ptr, struct sk_buff *buf); static int tipc_link_tunnel_rcv(struct tipc_node *n_ptr, struct sk_buff **buf); static void link_set_supervision_props(struct tipc_link *l_ptr, u32 tolerance); -static int tipc_link_iovec_long_xmit(struct tipc_port *sender, - struct iovec const *msg_sect, - 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); -static int tipc_link_frag_xmit(struct tipc_link *l_ptr, struct sk_buff *buf); static void tipc_link_sync_xmit(struct tipc_link *l); static void tipc_link_sync_rcv(struct tipc_node *n, struct sk_buff *buf); +static int tipc_link_input(struct tipc_link *l, struct sk_buff *buf); +static int tipc_link_prepare_input(struct tipc_link *l, struct sk_buff **buf); /* * Simple link routines @@ -335,13 +333,15 @@ void tipc_link_delete_list(unsigned int bearer_id, bool shutting_down) static int link_schedule_port(struct tipc_link *l_ptr, u32 origport, u32 sz) { struct tipc_port *p_ptr; + struct tipc_sock *tsk; spin_lock_bh(&tipc_port_list_lock); p_ptr = tipc_port_lock(origport); if (p_ptr) { if (!list_empty(&p_ptr->wait_list)) goto exit; - p_ptr->congested = 1; + tsk = tipc_port_to_sock(p_ptr); + tsk->link_cong = 1; p_ptr->waiting_pkts = 1 + ((sz - 1) / l_ptr->max_pkt); list_add_tail(&p_ptr->wait_list, &l_ptr->waiting_ports); l_ptr->stats.link_congs++; @@ -355,6 +355,7 @@ exit: void tipc_link_wakeup_ports(struct tipc_link *l_ptr, int all) { struct tipc_port *p_ptr; + struct tipc_sock *tsk; struct tipc_port *temp_p_ptr; int win = l_ptr->queue_limit[0] - l_ptr->out_queue_size; @@ -370,10 +371,11 @@ void tipc_link_wakeup_ports(struct tipc_link *l_ptr, int all) wait_list) { if (win <= 0) break; + tsk = tipc_port_to_sock(p_ptr); list_del_init(&p_ptr->wait_list); spin_lock_bh(p_ptr->lock); - p_ptr->congested = 0; - tipc_port_wakeup(p_ptr); + tsk->link_cong = 0; + tipc_sock_wakeup(tsk); win -= p_ptr->waiting_pkts; spin_unlock_bh(p_ptr->lock); } @@ -676,178 +678,142 @@ static void link_state_event(struct tipc_link *l_ptr, unsigned int event) } } -/* - * link_bundle_buf(): Append contents of a buffer to - * the tail of an existing one. +/* tipc_link_cong: determine return value and how to treat the + * sent buffer during link congestion. + * - For plain, errorless user data messages we keep the buffer and + * return -ELINKONG. + * - For all other messages we discard the buffer and return -EHOSTUNREACH + * - For TIPC internal messages we also reset the link */ -static int link_bundle_buf(struct tipc_link *l_ptr, struct sk_buff *bundler, - struct sk_buff *buf) +static int tipc_link_cong(struct tipc_link *link, struct sk_buff *buf) { - struct tipc_msg *bundler_msg = buf_msg(bundler); struct tipc_msg *msg = buf_msg(buf); - u32 size = msg_size(msg); - u32 bundle_size = msg_size(bundler_msg); - u32 to_pos = align(bundle_size); - u32 pad = to_pos - bundle_size; - - if (msg_user(bundler_msg) != MSG_BUNDLER) - return 0; - if (msg_type(bundler_msg) != OPEN_MSG) - return 0; - if (skb_tailroom(bundler) < (pad + size)) - return 0; - if (l_ptr->max_pkt < (to_pos + size)) - return 0; - - skb_put(bundler, pad + size); - skb_copy_to_linear_data_offset(bundler, to_pos, buf->data, size); - msg_set_size(bundler_msg, to_pos + size); - msg_set_msgcnt(bundler_msg, msg_msgcnt(bundler_msg) + 1); - kfree_skb(buf); - l_ptr->stats.sent_bundled++; - return 1; -} - -static void link_add_to_outqueue(struct tipc_link *l_ptr, - struct sk_buff *buf, - struct tipc_msg *msg) -{ - u32 ack = mod(l_ptr->next_in_no - 1); - u32 seqno = mod(l_ptr->next_out_no++); + uint psz = msg_size(msg); + uint imp = tipc_msg_tot_importance(msg); + u32 oport = msg_tot_origport(msg); - msg_set_word(msg, 2, ((ack << 16) | seqno)); - msg_set_bcast_ack(msg, l_ptr->owner->bclink.last_in); - buf->next = NULL; - if (l_ptr->first_out) { - l_ptr->last_out->next = buf; - l_ptr->last_out = buf; - } else - l_ptr->first_out = l_ptr->last_out = buf; - - l_ptr->out_queue_size++; - if (l_ptr->out_queue_size > l_ptr->stats.max_queue_sz) - l_ptr->stats.max_queue_sz = l_ptr->out_queue_size; -} - -static void link_add_chain_to_outqueue(struct tipc_link *l_ptr, - struct sk_buff *buf_chain, - u32 long_msgno) -{ - struct sk_buff *buf; - struct tipc_msg *msg; - - if (!l_ptr->next_out) - l_ptr->next_out = buf_chain; - while (buf_chain) { - buf = buf_chain; - buf_chain = buf_chain->next; - - msg = buf_msg(buf); - msg_set_long_msgno(msg, long_msgno); - link_add_to_outqueue(l_ptr, buf, msg); + if (likely(imp <= TIPC_CRITICAL_IMPORTANCE)) { + if (!msg_errcode(msg) && !msg_reroute_cnt(msg)) { + link_schedule_port(link, oport, psz); + return -ELINKCONG; + } + } else { + pr_warn("%s<%s>, send queue full", link_rst_msg, link->name); + tipc_link_reset(link); } + kfree_skb_list(buf); + return -EHOSTUNREACH; } -/* - * tipc_link_xmit() is the 'full path' for messages, called from - * inside TIPC when the 'fast path' in tipc_send_xmit - * has failed, and from link_send() +/** + * __tipc_link_xmit(): same as tipc_link_xmit, but destlink is known & locked + * @link: link to use + * @buf: chain of buffers containing message + * Consumes the buffer chain, except when returning -ELINKCONG + * Returns 0 if success, otherwise errno: -ELINKCONG, -EMSGSIZE (plain socket + * user data messages) or -EHOSTUNREACH (all other messages/senders) + * Only the socket functions tipc_send_stream() and tipc_send_packet() need + * to act on the return value, since they may need to do more send attempts. */ -int __tipc_link_xmit(struct tipc_link *l_ptr, struct sk_buff *buf) +int __tipc_link_xmit(struct tipc_link *link, struct sk_buff *buf) { struct tipc_msg *msg = buf_msg(buf); - u32 size = msg_size(msg); - u32 dsz = msg_data_sz(msg); - u32 queue_size = l_ptr->out_queue_size; - u32 imp = tipc_msg_tot_importance(msg); - u32 queue_limit = l_ptr->queue_limit[imp]; - u32 max_packet = l_ptr->max_pkt; - - /* Match msg importance against queue limits: */ - if (unlikely(queue_size >= queue_limit)) { - if (imp <= TIPC_CRITICAL_IMPORTANCE) { - link_schedule_port(l_ptr, msg_origport(msg), size); - kfree_skb(buf); - return -ELINKCONG; - } - kfree_skb(buf); - if (imp > CONN_MANAGER) { - pr_warn("%s<%s>, send queue full", link_rst_msg, - l_ptr->name); - tipc_link_reset(l_ptr); - } - return dsz; + uint psz = msg_size(msg); + uint qsz = link->out_queue_size; + uint sndlim = link->queue_limit[0]; + uint imp = tipc_msg_tot_importance(msg); + uint mtu = link->max_pkt; + uint ack = mod(link->next_in_no - 1); + uint seqno = link->next_out_no; + uint bc_last_in = link->owner->bclink.last_in; + struct tipc_media_addr *addr = &link->media_addr; + struct sk_buff *next = buf->next; + + /* Match queue limits against msg importance: */ + if (unlikely(qsz >= link->queue_limit[imp])) + return tipc_link_cong(link, buf); + + /* Has valid packet limit been used ? */ + if (unlikely(psz > mtu)) { + kfree_skb_list(buf); + return -EMSGSIZE; } - /* Fragmentation needed ? */ - if (size > max_packet) - return tipc_link_frag_xmit(l_ptr, buf); - - /* Packet can be queued or sent. */ - if (likely(!link_congested(l_ptr))) { - link_add_to_outqueue(l_ptr, buf, msg); + /* Prepare each packet for sending, and add to outqueue: */ + while (buf) { + next = buf->next; + msg = buf_msg(buf); + msg_set_word(msg, 2, ((ack << 16) | mod(seqno))); + msg_set_bcast_ack(msg, bc_last_in); + + if (!link->first_out) { + link->first_out = buf; + } else if (qsz < sndlim) { + link->last_out->next = buf; + } else if (tipc_msg_bundle(link->last_out, buf, mtu)) { + link->stats.sent_bundled++; + buf = next; + next = buf->next; + continue; + } else if (tipc_msg_make_bundle(&buf, mtu, link->addr)) { + link->stats.sent_bundled++; + link->stats.sent_bundles++; + link->last_out->next = buf; + if (!link->next_out) + link->next_out = buf; + } else { + link->last_out->next = buf; + if (!link->next_out) + link->next_out = buf; + } - tipc_bearer_send(l_ptr->bearer_id, buf, &l_ptr->media_addr); - l_ptr->unacked_window = 0; - return dsz; - } - /* Congestion: can message be bundled ? */ - if ((msg_user(msg) != CHANGEOVER_PROTOCOL) && - (msg_user(msg) != MSG_FRAGMENTER)) { - - /* Try adding message to an existing bundle */ - if (l_ptr->next_out && - link_bundle_buf(l_ptr, l_ptr->last_out, buf)) - return dsz; - - /* Try creating a new bundle */ - if (size <= max_packet * 2 / 3) { - struct sk_buff *bundler = tipc_buf_acquire(max_packet); - struct tipc_msg bundler_hdr; - - if (bundler) { - tipc_msg_init(&bundler_hdr, MSG_BUNDLER, OPEN_MSG, - INT_H_SIZE, l_ptr->addr); - skb_copy_to_linear_data(bundler, &bundler_hdr, - INT_H_SIZE); - skb_trim(bundler, INT_H_SIZE); - link_bundle_buf(l_ptr, bundler, buf); - buf = bundler; - msg = buf_msg(buf); - l_ptr->stats.sent_bundles++; - } + /* Send packet if possible: */ + if (likely(++qsz <= sndlim)) { + tipc_bearer_send(link->bearer_id, buf, addr); + link->next_out = next; + link->unacked_window = 0; } + seqno++; + link->last_out = buf; + buf = next; } - if (!l_ptr->next_out) - l_ptr->next_out = buf; - link_add_to_outqueue(l_ptr, buf, msg); - return dsz; + link->next_out_no = seqno; + link->out_queue_size = qsz; + return 0; } -/* - * tipc_link_xmit(): same as __tipc_link_xmit(), but the link to use - * has not been selected yet, and the the owner node is not locked - * Called by TIPC internal users, e.g. the name distributor +/** + * tipc_link_xmit() is the general link level function for message sending + * @buf: chain of buffers containing message + * @dsz: amount of user data to be sent + * @dnode: address of destination node + * @selector: a number used for deterministic link selection + * Consumes the buffer chain, except when returning -ELINKCONG + * Returns 0 if success, otherwise errno: -ELINKCONG,-EHOSTUNREACH,-EMSGSIZE */ -int tipc_link_xmit(struct sk_buff *buf, u32 dest, u32 selector) +int tipc_link_xmit(struct sk_buff *buf, u32 dnode, u32 selector) { - struct tipc_link *l_ptr; - struct tipc_node *n_ptr; - int res = -ELINKCONG; + struct tipc_link *link = NULL; + struct tipc_node *node; + int rc = -EHOSTUNREACH; - n_ptr = tipc_node_find(dest); - if (n_ptr) { - tipc_node_lock(n_ptr); - l_ptr = n_ptr->active_links[selector & 1]; - if (l_ptr) - res = __tipc_link_xmit(l_ptr, buf); - else - kfree_skb(buf); - tipc_node_unlock(n_ptr); - } else { - kfree_skb(buf); + node = tipc_node_find(dnode); + if (node) { + tipc_node_lock(node); + link = node->active_links[selector & 1]; + if (link) + rc = __tipc_link_xmit(link, buf); + tipc_node_unlock(node); } - return res; + + if (link) + return rc; + + if (likely(in_own_node(dnode))) + return tipc_sk_rcv(buf); + + kfree_skb_list(buf); + return rc; } /* @@ -858,7 +824,7 @@ int tipc_link_xmit(struct sk_buff *buf, u32 dest, u32 selector) * * Called with node locked */ -static void tipc_link_sync_xmit(struct tipc_link *l) +static void tipc_link_sync_xmit(struct tipc_link *link) { struct sk_buff *buf; struct tipc_msg *msg; @@ -868,10 +834,9 @@ static void tipc_link_sync_xmit(struct tipc_link *l) return; msg = buf_msg(buf); - tipc_msg_init(msg, BCAST_PROTOCOL, STATE_MSG, INT_H_SIZE, l->addr); - msg_set_last_bcast(msg, l->owner->bclink.acked); - link_add_chain_to_outqueue(l, buf, 0); - tipc_link_push_queue(l); + tipc_msg_init(msg, BCAST_PROTOCOL, STATE_MSG, INT_H_SIZE, link->addr); + msg_set_last_bcast(msg, link->owner->bclink.acked); + __tipc_link_xmit(link, buf); } /* @@ -892,293 +857,6 @@ static void tipc_link_sync_rcv(struct tipc_node *n, struct sk_buff *buf) } /* - * tipc_link_names_xmit - send name table entries to new neighbor - * - * Send routine for bulk delivery of name table messages when contact - * with a new neighbor occurs. No link congestion checking is performed - * because name table messages *must* be delivered. The messages must be - * small enough not to require fragmentation. - * Called without any locks held. - */ -void tipc_link_names_xmit(struct list_head *message_list, u32 dest) -{ - struct tipc_node *n_ptr; - struct tipc_link *l_ptr; - struct sk_buff *buf; - struct sk_buff *temp_buf; - - if (list_empty(message_list)) - return; - - n_ptr = tipc_node_find(dest); - if (n_ptr) { - tipc_node_lock(n_ptr); - l_ptr = n_ptr->active_links[0]; - if (l_ptr) { - /* convert circular list to linear list */ - ((struct sk_buff *)message_list->prev)->next = NULL; - link_add_chain_to_outqueue(l_ptr, - (struct sk_buff *)message_list->next, 0); - tipc_link_push_queue(l_ptr); - INIT_LIST_HEAD(message_list); - } - tipc_node_unlock(n_ptr); - } - - /* discard the messages if they couldn't be sent */ - list_for_each_safe(buf, temp_buf, ((struct sk_buff *)message_list)) { - list_del((struct list_head *)buf); - kfree_skb(buf); - } -} - -/* - * tipc_link_xmit_fast: Entry for data messages where the - * destination link is known and the header is complete, - * inclusive total message length. Very time critical. - * Link is locked. Returns user data length. - */ -static int tipc_link_xmit_fast(struct tipc_link *l_ptr, struct sk_buff *buf, - u32 *used_max_pkt) -{ - struct tipc_msg *msg = buf_msg(buf); - int res = msg_data_sz(msg); - - if (likely(!link_congested(l_ptr))) { - if (likely(msg_size(msg) <= l_ptr->max_pkt)) { - link_add_to_outqueue(l_ptr, buf, msg); - tipc_bearer_send(l_ptr->bearer_id, buf, - &l_ptr->media_addr); - l_ptr->unacked_window = 0; - return res; - } - else - *used_max_pkt = l_ptr->max_pkt; - } - return __tipc_link_xmit(l_ptr, buf); /* All other cases */ -} - -/* - * tipc_link_iovec_xmit_fast: Entry for messages where the - * destination processor is known and the header is complete, - * except for total message length. - * Returns user data length or errno. - */ -int tipc_link_iovec_xmit_fast(struct tipc_port *sender, - struct iovec const *msg_sect, - unsigned int len, u32 destaddr) -{ - struct tipc_msg *hdr = &sender->phdr; - struct tipc_link *l_ptr; - struct sk_buff *buf; - struct tipc_node *node; - int res; - u32 selector = msg_origport(hdr) & 1; - -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, len, sender->max_pkt, &buf); - /* Exit if build request was invalid */ - if (unlikely(res < 0)) - return res; - - node = tipc_node_find(destaddr); - if (likely(node)) { - tipc_node_lock(node); - l_ptr = node->active_links[selector]; - if (likely(l_ptr)) { - if (likely(buf)) { - res = tipc_link_xmit_fast(l_ptr, buf, - &sender->max_pkt); -exit: - tipc_node_unlock(node); - return res; - } - - /* Exit if link (or bearer) is congested */ - if (link_congested(l_ptr)) { - res = link_schedule_port(l_ptr, - sender->ref, res); - goto exit; - } - - /* - * Message size exceeds max_pkt hint; update hint, - * then re-try fast path or fragment the message - */ - sender->max_pkt = l_ptr->max_pkt; - tipc_node_unlock(node); - - - if ((msg_hdr_sz(hdr) + res) <= sender->max_pkt) - goto again; - - return tipc_link_iovec_long_xmit(sender, msg_sect, - len, destaddr); - } - tipc_node_unlock(node); - } - - /* Couldn't find a link to the destination node */ - kfree_skb(buf); - tipc_port_iovec_reject(sender, hdr, msg_sect, len, TIPC_ERR_NO_NODE); - return -ENETUNREACH; -} - -/* - * tipc_link_iovec_long_xmit(): Entry for long messages where the - * destination node is known and the header is complete, - * inclusive total message length. - * Link and bearer congestion status have been checked to be ok, - * and are ignored if they change. - * - * Note that fragments do not use the full link MTU so that they won't have - * to undergo refragmentation if link changeover causes them to be sent - * over another link with an additional tunnel header added as prefix. - * (Refragmentation will still occur if the other link has a smaller MTU.) - * - * Returns user data length or errno. - */ -static int tipc_link_iovec_long_xmit(struct tipc_port *sender, - struct iovec const *msg_sect, - unsigned int len, u32 destaddr) -{ - struct tipc_link *l_ptr; - struct tipc_node *node; - struct tipc_msg *hdr = &sender->phdr; - u32 dsz = len; - u32 max_pkt, fragm_sz, rest; - struct tipc_msg fragm_hdr; - struct sk_buff *buf, *buf_chain, *prev; - u32 fragm_crs, fragm_rest, hsz, sect_rest; - const unchar __user *sect_crs; - int curr_sect; - u32 fragm_no; - int res = 0; - -again: - fragm_no = 1; - max_pkt = sender->max_pkt - INT_H_SIZE; - /* leave room for tunnel header in case of link changeover */ - fragm_sz = max_pkt - INT_H_SIZE; - /* leave room for fragmentation header in each fragment */ - rest = dsz; - fragm_crs = 0; - fragm_rest = 0; - sect_rest = 0; - sect_crs = NULL; - curr_sect = -1; - - /* Prepare reusable fragment header */ - tipc_msg_init(&fragm_hdr, MSG_FRAGMENTER, FIRST_FRAGMENT, - INT_H_SIZE, msg_destnode(hdr)); - msg_set_size(&fragm_hdr, max_pkt); - msg_set_fragm_no(&fragm_hdr, 1); - - /* Prepare header of first fragment */ - buf_chain = buf = tipc_buf_acquire(max_pkt); - if (!buf) - return -ENOMEM; - buf->next = NULL; - skb_copy_to_linear_data(buf, &fragm_hdr, INT_H_SIZE); - hsz = msg_hdr_sz(hdr); - skb_copy_to_linear_data_offset(buf, INT_H_SIZE, hdr, hsz); - - /* Chop up message */ - fragm_crs = INT_H_SIZE + hsz; - fragm_rest = fragm_sz - hsz; - - do { /* For all sections */ - u32 sz; - - if (!sect_rest) { - sect_rest = msg_sect[++curr_sect].iov_len; - sect_crs = msg_sect[curr_sect].iov_base; - } - - if (sect_rest < fragm_rest) - sz = sect_rest; - else - sz = fragm_rest; - - if (copy_from_user(buf->data + fragm_crs, sect_crs, sz)) { - res = -EFAULT; -error: - kfree_skb_list(buf_chain); - return res; - } - sect_crs += sz; - sect_rest -= sz; - fragm_crs += sz; - fragm_rest -= sz; - rest -= sz; - - if (!fragm_rest && rest) { - - /* Initiate new fragment: */ - if (rest <= fragm_sz) { - fragm_sz = rest; - msg_set_type(&fragm_hdr, LAST_FRAGMENT); - } else { - msg_set_type(&fragm_hdr, FRAGMENT); - } - msg_set_size(&fragm_hdr, fragm_sz + INT_H_SIZE); - msg_set_fragm_no(&fragm_hdr, ++fragm_no); - prev = buf; - buf = tipc_buf_acquire(fragm_sz + INT_H_SIZE); - if (!buf) { - res = -ENOMEM; - goto error; - } - - buf->next = NULL; - prev->next = buf; - skb_copy_to_linear_data(buf, &fragm_hdr, INT_H_SIZE); - fragm_crs = INT_H_SIZE; - fragm_rest = fragm_sz; - } - } while (rest > 0); - - /* - * Now we have a buffer chain. Select a link and check - * that packet size is still OK - */ - node = tipc_node_find(destaddr); - if (likely(node)) { - tipc_node_lock(node); - l_ptr = node->active_links[sender->ref & 1]; - if (!l_ptr) { - tipc_node_unlock(node); - goto reject; - } - if (l_ptr->max_pkt < max_pkt) { - sender->max_pkt = l_ptr->max_pkt; - tipc_node_unlock(node); - kfree_skb_list(buf_chain); - goto again; - } - } else { -reject: - kfree_skb_list(buf_chain); - tipc_port_iovec_reject(sender, hdr, msg_sect, len, - TIPC_ERR_NO_NODE); - return -ENETUNREACH; - } - - /* Append chain of fragments to send queue & send them */ - l_ptr->long_msg_seq_no++; - link_add_chain_to_outqueue(l_ptr, buf_chain, l_ptr->long_msg_seq_no); - l_ptr->stats.sent_fragments += fragm_no; - l_ptr->stats.sent_fragmented++; - tipc_link_push_queue(l_ptr); - tipc_node_unlock(node); - return dsz; -} - -/* * tipc_link_push_packet: Push one unsent packet to the media */ static u32 tipc_link_push_packet(struct tipc_link *l_ptr) @@ -1238,7 +916,7 @@ static u32 tipc_link_push_packet(struct tipc_link *l_ptr) tipc_bearer_send(l_ptr->bearer_id, buf, &l_ptr->media_addr); if (msg_user(msg) == MSG_BUNDLER) - msg_set_type(msg, CLOSED_MSG); + msg_set_type(msg, BUNDLE_CLOSED); l_ptr->next_out = buf->next; return 0; } @@ -1527,11 +1205,6 @@ void tipc_rcv(struct sk_buff *head, struct tipc_bearer *b_ptr) if (unlikely(!list_empty(&l_ptr->waiting_ports))) tipc_link_wakeup_ports(l_ptr, 0); - if (unlikely(++l_ptr->unacked_window >= TIPC_MIN_LINK_WIN)) { - l_ptr->stats.sent_acks++; - tipc_link_proto_xmit(l_ptr, STATE_MSG, 0, 0, 0, 0, 0); - } - /* Process the incoming packet */ if (unlikely(!link_working_working(l_ptr))) { if (msg_user(msg) == LINK_PROTOCOL) { @@ -1565,57 +1238,19 @@ void tipc_rcv(struct sk_buff *head, struct tipc_bearer *b_ptr) if (unlikely(l_ptr->oldest_deferred_in)) head = link_insert_deferred_queue(l_ptr, head); - /* Deliver packet/message to correct user: */ - if (unlikely(msg_user(msg) == CHANGEOVER_PROTOCOL)) { - if (!tipc_link_tunnel_rcv(n_ptr, &buf)) { - tipc_node_unlock(n_ptr); - continue; - } - msg = buf_msg(buf); - } else if (msg_user(msg) == MSG_FRAGMENTER) { - l_ptr->stats.recv_fragments++; - if (tipc_buf_append(&l_ptr->reasm_buf, &buf)) { - l_ptr->stats.recv_fragmented++; - msg = buf_msg(buf); - } else { - if (!l_ptr->reasm_buf) - tipc_link_reset(l_ptr); - tipc_node_unlock(n_ptr); - continue; - } + if (unlikely(++l_ptr->unacked_window >= TIPC_MIN_LINK_WIN)) { + l_ptr->stats.sent_acks++; + tipc_link_proto_xmit(l_ptr, STATE_MSG, 0, 0, 0, 0, 0); } - switch (msg_user(msg)) { - case TIPC_LOW_IMPORTANCE: - case TIPC_MEDIUM_IMPORTANCE: - case TIPC_HIGH_IMPORTANCE: - case TIPC_CRITICAL_IMPORTANCE: + if (tipc_link_prepare_input(l_ptr, &buf)) { tipc_node_unlock(n_ptr); - tipc_sk_rcv(buf); continue; - case MSG_BUNDLER: - l_ptr->stats.recv_bundles++; - l_ptr->stats.recv_bundled += msg_msgcnt(msg); - tipc_node_unlock(n_ptr); - tipc_link_bundle_rcv(buf); - continue; - case NAME_DISTRIBUTOR: - n_ptr->bclink.recv_permitted = true; - tipc_node_unlock(n_ptr); - tipc_named_rcv(buf); - continue; - case CONN_MANAGER: - tipc_node_unlock(n_ptr); - tipc_port_proto_rcv(buf); - continue; - case BCAST_PROTOCOL: - tipc_link_sync_rcv(n_ptr, buf); - break; - default: - kfree_skb(buf); - break; } tipc_node_unlock(n_ptr); + msg = buf_msg(buf); + if (tipc_link_input(l_ptr, buf) != 0) + goto discard; continue; unlock_discard: tipc_node_unlock(n_ptr); @@ -1625,6 +1260,80 @@ discard: } /** + * tipc_link_prepare_input - process TIPC link messages + * + * returns nonzero if the message was consumed + * + * Node lock must be held + */ +static int tipc_link_prepare_input(struct tipc_link *l, struct sk_buff **buf) +{ + struct tipc_node *n; + struct tipc_msg *msg; + int res = -EINVAL; + + n = l->owner; + msg = buf_msg(*buf); + switch (msg_user(msg)) { + case CHANGEOVER_PROTOCOL: + if (tipc_link_tunnel_rcv(n, buf)) + res = 0; + break; + case MSG_FRAGMENTER: + l->stats.recv_fragments++; + if (tipc_buf_append(&l->reasm_buf, buf)) { + l->stats.recv_fragmented++; + res = 0; + } else if (!l->reasm_buf) { + tipc_link_reset(l); + } + break; + case MSG_BUNDLER: + l->stats.recv_bundles++; + l->stats.recv_bundled += msg_msgcnt(msg); + res = 0; + break; + case NAME_DISTRIBUTOR: + n->bclink.recv_permitted = true; + res = 0; + break; + case BCAST_PROTOCOL: + tipc_link_sync_rcv(n, *buf); + break; + default: + res = 0; + } + return res; +} +/** + * tipc_link_input - Deliver message too higher layers + */ +static int tipc_link_input(struct tipc_link *l, struct sk_buff *buf) +{ + struct tipc_msg *msg = buf_msg(buf); + int res = 0; + + switch (msg_user(msg)) { + case TIPC_LOW_IMPORTANCE: + case TIPC_MEDIUM_IMPORTANCE: + case TIPC_HIGH_IMPORTANCE: + case TIPC_CRITICAL_IMPORTANCE: + case CONN_MANAGER: + tipc_sk_rcv(buf); + break; + case NAME_DISTRIBUTOR: + tipc_named_rcv(buf); + break; + case MSG_BUNDLER: + tipc_link_bundle_rcv(buf); + break; + default: + res = -EINVAL; + } + return res; +} + +/** * tipc_link_defer_pkt - Add out-of-sequence message to deferred reception queue * * Returns increase in queue length (i.e. 0 or 1) @@ -2217,6 +1926,7 @@ void tipc_link_bundle_rcv(struct sk_buff *buf) u32 msgcount = msg_msgcnt(buf_msg(buf)); u32 pos = INT_H_SIZE; struct sk_buff *obuf; + struct tipc_msg *omsg; while (msgcount--) { obuf = buf_extract(buf, pos); @@ -2224,82 +1934,18 @@ void tipc_link_bundle_rcv(struct sk_buff *buf) pr_warn("Link unable to unbundle message(s)\n"); break; } - pos += align(msg_size(buf_msg(obuf))); - tipc_net_route_msg(obuf); - } - kfree_skb(buf); -} - -/* - * Fragmentation/defragmentation: - */ - -/* - * tipc_link_frag_xmit: Entry for buffers needing fragmentation. - * The buffer is complete, inclusive total message length. - * Returns user data length. - */ -static int tipc_link_frag_xmit(struct tipc_link *l_ptr, struct sk_buff *buf) -{ - struct sk_buff *buf_chain = NULL; - struct sk_buff *buf_chain_tail = (struct sk_buff *)&buf_chain; - struct tipc_msg *inmsg = buf_msg(buf); - struct tipc_msg fragm_hdr; - u32 insize = msg_size(inmsg); - u32 dsz = msg_data_sz(inmsg); - unchar *crs = buf->data; - u32 rest = insize; - u32 pack_sz = l_ptr->max_pkt; - u32 fragm_sz = pack_sz - INT_H_SIZE; - u32 fragm_no = 0; - u32 destaddr; - - if (msg_short(inmsg)) - destaddr = l_ptr->addr; - else - destaddr = msg_destnode(inmsg); - - /* Prepare reusable fragment header: */ - tipc_msg_init(&fragm_hdr, MSG_FRAGMENTER, FIRST_FRAGMENT, - INT_H_SIZE, destaddr); - - /* Chop up message: */ - while (rest > 0) { - struct sk_buff *fragm; - - if (rest <= fragm_sz) { - fragm_sz = rest; - msg_set_type(&fragm_hdr, LAST_FRAGMENT); - } - fragm = tipc_buf_acquire(fragm_sz + INT_H_SIZE); - if (fragm == NULL) { - kfree_skb(buf); - kfree_skb_list(buf_chain); - return -ENOMEM; + omsg = buf_msg(obuf); + pos += align(msg_size(omsg)); + if (msg_isdata(omsg) || (msg_user(omsg) == CONN_MANAGER)) { + tipc_sk_rcv(obuf); + } else if (msg_user(omsg) == NAME_DISTRIBUTOR) { + tipc_named_rcv(obuf); + } else { + pr_warn("Illegal bundled msg: %u\n", msg_user(omsg)); + kfree_skb(obuf); } - msg_set_size(&fragm_hdr, fragm_sz + INT_H_SIZE); - fragm_no++; - msg_set_fragm_no(&fragm_hdr, fragm_no); - skb_copy_to_linear_data(fragm, &fragm_hdr, INT_H_SIZE); - skb_copy_to_linear_data_offset(fragm, INT_H_SIZE, crs, - fragm_sz); - buf_chain_tail->next = fragm; - buf_chain_tail = fragm; - - rest -= fragm_sz; - crs += fragm_sz; - msg_set_type(&fragm_hdr, FRAGMENT); } kfree_skb(buf); - - /* Append chain of fragments to send queue & send them */ - l_ptr->long_msg_seq_no++; - link_add_chain_to_outqueue(l_ptr, buf_chain, l_ptr->long_msg_seq_no); - l_ptr->stats.sent_fragments += fragm_no; - l_ptr->stats.sent_fragmented++; - tipc_link_push_queue(l_ptr); - - return dsz; } 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 200d518b218e..782983ccd323 100644 --- a/net/tipc/link.h +++ b/net/tipc/link.h @@ -227,13 +227,8 @@ void tipc_link_reset_all(struct tipc_node *node); void tipc_link_reset(struct tipc_link *l_ptr); void tipc_link_reset_list(unsigned int bearer_id); int tipc_link_xmit(struct sk_buff *buf, u32 dest, u32 selector); -void tipc_link_names_xmit(struct list_head *message_list, u32 dest); -int __tipc_link_xmit(struct tipc_link *l_ptr, struct sk_buff *buf); -int tipc_link_send_buf(struct tipc_link *l_ptr, struct sk_buff *buf); +int __tipc_link_xmit(struct tipc_link *link, struct sk_buff *buf); u32 tipc_link_get_max_pkt(u32 dest, u32 selector); -int tipc_link_iovec_xmit_fast(struct tipc_port *sender, - struct iovec const *msg_sect, - unsigned int len, u32 destnode); void tipc_link_bundle_rcv(struct sk_buff *buf); void tipc_link_proto_xmit(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.c b/net/tipc/msg.c index 0a37a472c29f..9680be6d388a 100644 --- a/net/tipc/msg.c +++ b/net/tipc/msg.c @@ -36,21 +36,16 @@ #include "core.h" #include "msg.h" +#include "addr.h" +#include "name_table.h" -u32 tipc_msg_tot_importance(struct tipc_msg *m) +#define MAX_FORWARD_SIZE 1024 + +static unsigned int align(unsigned int i) { - if (likely(msg_isdata(m))) { - if (likely(msg_orignode(m) == tipc_own_addr)) - return msg_importance(m); - return msg_importance(m) + 4; - } - if ((msg_user(m) == MSG_FRAGMENTER) && - (msg_type(m) == FIRST_FRAGMENT)) - return msg_importance(msg_get_wrapped(m)); - return msg_importance(m); + return (i + 3) & ~3u; } - void tipc_msg_init(struct tipc_msg *m, u32 user, u32 type, u32 hsize, u32 destnode) { @@ -65,41 +60,6 @@ void tipc_msg_init(struct tipc_msg *m, u32 user, u32 type, u32 hsize, msg_set_destnode(m, destnode); } -/** - * tipc_msg_build - create message using specified header and data - * - * Note: Caller must not hold any locks in case copy_from_user() is interrupted! - * - * Returns message data size or errno - */ -int tipc_msg_build(struct tipc_msg *hdr, struct iovec const *msg_sect, - unsigned int len, int max_size, struct sk_buff **buf) -{ - int dsz, sz, hsz; - unsigned char *to; - - dsz = len; - hsz = msg_hdr_sz(hdr); - sz = hsz + dsz; - msg_set_size(hdr, sz); - if (unlikely(sz > max_size)) { - *buf = NULL; - return dsz; - } - - *buf = tipc_buf_acquire(sz); - if (!(*buf)) - return -ENOMEM; - skb_copy_to_linear_data(*buf, hdr, hsz); - to = (*buf)->data + hsz; - if (len && memcpy_fromiovecend(to, msg_sect, 0, dsz)) { - kfree_skb(*buf); - *buf = NULL; - return -EFAULT; - } - return dsz; -} - /* tipc_buf_append(): Append a buffer to the fragment list of another buffer * @*headbuf: in: NULL for first frag, otherwise value returned from prev call * out: set when successful non-complete reassembly, otherwise NULL @@ -112,27 +72,38 @@ int tipc_buf_append(struct sk_buff **headbuf, struct sk_buff **buf) struct sk_buff *head = *headbuf; struct sk_buff *frag = *buf; struct sk_buff *tail; - struct tipc_msg *msg = buf_msg(frag); - u32 fragid = msg_type(msg); - bool headstolen; + struct tipc_msg *msg; + u32 fragid; int delta; + bool headstolen; + if (!frag) + goto err; + + msg = buf_msg(frag); + fragid = msg_type(msg); + frag->next = NULL; skb_pull(frag, msg_hdr_sz(msg)); if (fragid == FIRST_FRAGMENT) { - if (head || skb_unclone(frag, GFP_ATOMIC)) - goto out_free; + if (unlikely(head)) + goto err; + if (unlikely(skb_unclone(frag, GFP_ATOMIC))) + goto err; head = *headbuf = frag; skb_frag_list_init(head); + TIPC_SKB_CB(head)->tail = NULL; *buf = NULL; return 0; } + if (!head) - goto out_free; - tail = TIPC_SKB_CB(head)->tail; + goto err; + if (skb_try_coalesce(head, frag, &headstolen, &delta)) { kfree_skb_partial(frag, headstolen); } else { + tail = TIPC_SKB_CB(head)->tail; if (!skb_has_frag_list(head)) skb_shinfo(head)->frag_list = frag; else @@ -142,6 +113,7 @@ int tipc_buf_append(struct sk_buff **headbuf, struct sk_buff **buf) head->len += frag->len; TIPC_SKB_CB(head)->tail = frag; } + if (fragid == LAST_FRAGMENT) { *buf = head; TIPC_SKB_CB(head)->tail = NULL; @@ -150,10 +122,311 @@ int tipc_buf_append(struct sk_buff **headbuf, struct sk_buff **buf) } *buf = NULL; return 0; -out_free: + +err: pr_warn_ratelimited("Unable to build fragment list\n"); kfree_skb(*buf); kfree_skb(*headbuf); *buf = *headbuf = NULL; return 0; } + + +/** + * tipc_msg_build - create buffer chain containing specified header and data + * @mhdr: Message header, to be prepended to data + * @iov: User data + * @offset: Posision in iov to start copying from + * @dsz: Total length of user data + * @pktmax: Max packet size that can be used + * @chain: Buffer or chain of buffers to be returned to caller + * Returns message data size or errno: -ENOMEM, -EFAULT + */ +int tipc_msg_build(struct tipc_msg *mhdr, struct iovec const *iov, + int offset, int dsz, int pktmax , struct sk_buff **chain) +{ + int mhsz = msg_hdr_sz(mhdr); + int msz = mhsz + dsz; + int pktno = 1; + int pktsz; + int pktrem = pktmax; + int drem = dsz; + struct tipc_msg pkthdr; + struct sk_buff *buf, *prev; + char *pktpos; + int rc; + + msg_set_size(mhdr, msz); + + /* No fragmentation needed? */ + if (likely(msz <= pktmax)) { + buf = tipc_buf_acquire(msz); + *chain = buf; + if (unlikely(!buf)) + return -ENOMEM; + skb_copy_to_linear_data(buf, mhdr, mhsz); + pktpos = buf->data + mhsz; + if (!dsz || !memcpy_fromiovecend(pktpos, iov, offset, dsz)) + return dsz; + rc = -EFAULT; + goto error; + } + + /* Prepare reusable fragment header */ + tipc_msg_init(&pkthdr, MSG_FRAGMENTER, FIRST_FRAGMENT, + INT_H_SIZE, msg_destnode(mhdr)); + msg_set_size(&pkthdr, pktmax); + msg_set_fragm_no(&pkthdr, pktno); + + /* Prepare first fragment */ + *chain = buf = tipc_buf_acquire(pktmax); + if (!buf) + return -ENOMEM; + pktpos = buf->data; + skb_copy_to_linear_data(buf, &pkthdr, INT_H_SIZE); + pktpos += INT_H_SIZE; + pktrem -= INT_H_SIZE; + skb_copy_to_linear_data_offset(buf, INT_H_SIZE, mhdr, mhsz); + pktpos += mhsz; + pktrem -= mhsz; + + do { + if (drem < pktrem) + pktrem = drem; + + if (memcpy_fromiovecend(pktpos, iov, offset, pktrem)) { + rc = -EFAULT; + goto error; + } + drem -= pktrem; + offset += pktrem; + + if (!drem) + break; + + /* Prepare new fragment: */ + if (drem < (pktmax - INT_H_SIZE)) + pktsz = drem + INT_H_SIZE; + else + pktsz = pktmax; + prev = buf; + buf = tipc_buf_acquire(pktsz); + if (!buf) { + rc = -ENOMEM; + goto error; + } + prev->next = buf; + msg_set_type(&pkthdr, FRAGMENT); + msg_set_size(&pkthdr, pktsz); + msg_set_fragm_no(&pkthdr, ++pktno); + skb_copy_to_linear_data(buf, &pkthdr, INT_H_SIZE); + pktpos = buf->data + INT_H_SIZE; + pktrem = pktsz - INT_H_SIZE; + + } while (1); + + msg_set_type(buf_msg(buf), LAST_FRAGMENT); + return dsz; +error: + kfree_skb_list(*chain); + *chain = NULL; + return rc; +} + +/** + * tipc_msg_bundle(): Append contents of a buffer to tail of an existing one + * @bbuf: the existing buffer ("bundle") + * @buf: buffer to be appended + * @mtu: max allowable size for the bundle buffer + * Consumes buffer if successful + * Returns true if bundling could be performed, otherwise false + */ +bool tipc_msg_bundle(struct sk_buff *bbuf, struct sk_buff *buf, u32 mtu) +{ + struct tipc_msg *bmsg = buf_msg(bbuf); + struct tipc_msg *msg = buf_msg(buf); + unsigned int bsz = msg_size(bmsg); + unsigned int msz = msg_size(msg); + u32 start = align(bsz); + u32 max = mtu - INT_H_SIZE; + u32 pad = start - bsz; + + if (likely(msg_user(msg) == MSG_FRAGMENTER)) + return false; + if (unlikely(msg_user(msg) == CHANGEOVER_PROTOCOL)) + return false; + if (unlikely(msg_user(msg) == BCAST_PROTOCOL)) + return false; + if (likely(msg_user(bmsg) != MSG_BUNDLER)) + return false; + if (likely(msg_type(bmsg) != BUNDLE_OPEN)) + return false; + if (unlikely(skb_tailroom(bbuf) < (pad + msz))) + return false; + if (unlikely(max < (start + msz))) + return false; + + skb_put(bbuf, pad + msz); + skb_copy_to_linear_data_offset(bbuf, start, buf->data, msz); + msg_set_size(bmsg, start + msz); + msg_set_msgcnt(bmsg, msg_msgcnt(bmsg) + 1); + bbuf->next = buf->next; + kfree_skb(buf); + return true; +} + +/** + * tipc_msg_make_bundle(): Create bundle buf and append message to its tail + * @buf: buffer to be appended and replaced + * @mtu: max allowable size for the bundle buffer, inclusive header + * @dnode: destination node for message. (Not always present in header) + * Replaces buffer if successful + * Returns true if sucess, otherwise false + */ +bool tipc_msg_make_bundle(struct sk_buff **buf, u32 mtu, u32 dnode) +{ + struct sk_buff *bbuf; + struct tipc_msg *bmsg; + struct tipc_msg *msg = buf_msg(*buf); + u32 msz = msg_size(msg); + u32 max = mtu - INT_H_SIZE; + + if (msg_user(msg) == MSG_FRAGMENTER) + return false; + if (msg_user(msg) == CHANGEOVER_PROTOCOL) + return false; + if (msg_user(msg) == BCAST_PROTOCOL) + return false; + if (msz > (max / 2)) + return false; + + bbuf = tipc_buf_acquire(max); + if (!bbuf) + return false; + + skb_trim(bbuf, INT_H_SIZE); + bmsg = buf_msg(bbuf); + tipc_msg_init(bmsg, MSG_BUNDLER, BUNDLE_OPEN, INT_H_SIZE, dnode); + msg_set_seqno(bmsg, msg_seqno(msg)); + msg_set_ack(bmsg, msg_ack(msg)); + msg_set_bcast_ack(bmsg, msg_bcast_ack(msg)); + bbuf->next = (*buf)->next; + tipc_msg_bundle(bbuf, *buf, mtu); + *buf = bbuf; + return true; +} + +/** + * tipc_msg_reverse(): swap source and destination addresses and add error code + * @buf: buffer containing message to be reversed + * @dnode: return value: node where to send message after reversal + * @err: error code to be set in message + * Consumes buffer if failure + * Returns true if success, otherwise false + */ +bool tipc_msg_reverse(struct sk_buff *buf, u32 *dnode, int err) +{ + struct tipc_msg *msg = buf_msg(buf); + uint imp = msg_importance(msg); + struct tipc_msg ohdr; + uint rdsz = min_t(uint, msg_data_sz(msg), MAX_FORWARD_SIZE); + + if (skb_linearize(buf)) + goto exit; + if (msg_dest_droppable(msg)) + goto exit; + if (msg_errcode(msg)) + goto exit; + + memcpy(&ohdr, msg, msg_hdr_sz(msg)); + imp = min_t(uint, imp + 1, TIPC_CRITICAL_IMPORTANCE); + if (msg_isdata(msg)) + msg_set_importance(msg, imp); + msg_set_errcode(msg, err); + msg_set_origport(msg, msg_destport(&ohdr)); + msg_set_destport(msg, msg_origport(&ohdr)); + msg_set_prevnode(msg, tipc_own_addr); + if (!msg_short(msg)) { + msg_set_orignode(msg, msg_destnode(&ohdr)); + msg_set_destnode(msg, msg_orignode(&ohdr)); + } + msg_set_size(msg, msg_hdr_sz(msg) + rdsz); + skb_trim(buf, msg_size(msg)); + skb_orphan(buf); + *dnode = msg_orignode(&ohdr); + return true; +exit: + kfree_skb(buf); + return false; +} + +/** + * tipc_msg_eval: determine fate of message that found no destination + * @buf: the buffer containing the message. + * @dnode: return value: next-hop node, if message to be forwarded + * @err: error code to use, if message to be rejected + * + * Does not consume buffer + * Returns 0 (TIPC_OK) if message ok and we can try again, -TIPC error + * code if message to be rejected + */ +int tipc_msg_eval(struct sk_buff *buf, u32 *dnode) +{ + struct tipc_msg *msg = buf_msg(buf); + u32 dport; + + if (msg_type(msg) != TIPC_NAMED_MSG) + return -TIPC_ERR_NO_PORT; + if (skb_linearize(buf)) + return -TIPC_ERR_NO_NAME; + if (msg_data_sz(msg) > MAX_FORWARD_SIZE) + return -TIPC_ERR_NO_NAME; + if (msg_reroute_cnt(msg) > 0) + return -TIPC_ERR_NO_NAME; + + *dnode = addr_domain(msg_lookup_scope(msg)); + dport = tipc_nametbl_translate(msg_nametype(msg), + msg_nameinst(msg), + dnode); + if (!dport) + return -TIPC_ERR_NO_NAME; + msg_incr_reroute_cnt(msg); + msg_set_destnode(msg, *dnode); + msg_set_destport(msg, dport); + return TIPC_OK; +} + +/* tipc_msg_reassemble() - clone a buffer chain of fragments and + * reassemble the clones into one message + */ +struct sk_buff *tipc_msg_reassemble(struct sk_buff *chain) +{ + struct sk_buff *buf = chain; + struct sk_buff *frag = buf; + struct sk_buff *head = NULL; + int hdr_sz; + + /* Copy header if single buffer */ + if (!buf->next) { + hdr_sz = skb_headroom(buf) + msg_hdr_sz(buf_msg(buf)); + return __pskb_copy(buf, hdr_sz, GFP_ATOMIC); + } + + /* Clone all fragments and reassemble */ + while (buf) { + frag = skb_clone(buf, GFP_ATOMIC); + if (!frag) + goto error; + frag->next = NULL; + if (tipc_buf_append(&head, &frag)) + break; + if (!head) + goto error; + buf = buf->next; + } + return frag; +error: + pr_warn("Failed do clone local mcast rcv buffer\n"); + kfree_skb(head); + return NULL; +} diff --git a/net/tipc/msg.h b/net/tipc/msg.h index 503511903d1d..462fa194a6af 100644 --- a/net/tipc/msg.h +++ b/net/tipc/msg.h @@ -463,6 +463,11 @@ static inline struct tipc_msg *msg_get_wrapped(struct tipc_msg *m) #define FRAGMENT 1 #define LAST_FRAGMENT 2 +/* Bundling protocol message types + */ +#define BUNDLE_OPEN 0 +#define BUNDLE_CLOSED 1 + /* * Link management protocol message types */ @@ -706,12 +711,36 @@ static inline void msg_set_link_tolerance(struct tipc_msg *m, u32 n) msg_set_bits(m, 9, 0, 0xffff, n); } -u32 tipc_msg_tot_importance(struct tipc_msg *m); +static inline u32 tipc_msg_tot_importance(struct tipc_msg *m) +{ + if ((msg_user(m) == MSG_FRAGMENTER) && (msg_type(m) == FIRST_FRAGMENT)) + return msg_importance(msg_get_wrapped(m)); + return msg_importance(m); +} + +static inline u32 msg_tot_origport(struct tipc_msg *m) +{ + if ((msg_user(m) == MSG_FRAGMENTER) && (msg_type(m) == FIRST_FRAGMENT)) + return msg_origport(msg_get_wrapped(m)); + return msg_origport(m); +} + +bool tipc_msg_reverse(struct sk_buff *buf, u32 *dnode, int err); + +int tipc_msg_eval(struct sk_buff *buf, u32 *dnode); + void tipc_msg_init(struct tipc_msg *m, u32 user, u32 type, u32 hsize, u32 destnode); -int tipc_msg_build(struct tipc_msg *hdr, struct iovec const *msg_sect, - unsigned int len, int max_size, struct sk_buff **buf); int tipc_buf_append(struct sk_buff **headbuf, struct sk_buff **buf); +bool tipc_msg_bundle(struct sk_buff *bbuf, struct sk_buff *buf, u32 mtu); + +bool tipc_msg_make_bundle(struct sk_buff **buf, u32 mtu, u32 dnode); + +int tipc_msg_build(struct tipc_msg *mhdr, struct iovec const *iov, + int offset, int dsz, int mtu , struct sk_buff **chain); + +struct sk_buff *tipc_msg_reassemble(struct sk_buff *chain); + #endif diff --git a/net/tipc/name_distr.c b/net/tipc/name_distr.c index 8ce730984aa1..dcc15bcd5692 100644 --- a/net/tipc/name_distr.c +++ b/net/tipc/name_distr.c @@ -101,24 +101,22 @@ static struct sk_buff *named_prepare_buf(u32 type, u32 size, u32 dest) void named_cluster_distribute(struct sk_buff *buf) { - struct sk_buff *buf_copy; - struct tipc_node *n_ptr; - struct tipc_link *l_ptr; + struct sk_buff *obuf; + struct tipc_node *node; + u32 dnode; rcu_read_lock(); - list_for_each_entry_rcu(n_ptr, &tipc_node_list, list) { - tipc_node_lock(n_ptr); - l_ptr = n_ptr->active_links[n_ptr->addr & 1]; - if (l_ptr) { - buf_copy = skb_copy(buf, GFP_ATOMIC); - if (!buf_copy) { - tipc_node_unlock(n_ptr); - break; - } - msg_set_destnode(buf_msg(buf_copy), n_ptr->addr); - __tipc_link_xmit(l_ptr, buf_copy); - } - tipc_node_unlock(n_ptr); + list_for_each_entry_rcu(node, &tipc_node_list, list) { + dnode = node->addr; + if (in_own_node(dnode)) + continue; + if (!tipc_node_active_links(node)) + continue; + obuf = skb_copy(buf, GFP_ATOMIC); + if (!obuf) + break; + msg_set_destnode(buf_msg(obuf), dnode); + tipc_link_xmit(obuf, dnode, dnode); } rcu_read_unlock(); @@ -175,34 +173,44 @@ struct sk_buff *tipc_named_withdraw(struct publication *publ) return buf; } -/* +/** * named_distribute - prepare name info for bulk distribution to another node + * @msg_list: list of messages (buffers) to be returned from this function + * @dnode: node to be updated + * @pls: linked list of publication items to be packed into buffer chain */ -static void named_distribute(struct list_head *message_list, u32 node, - struct publ_list *pls, u32 max_item_buf) +static void named_distribute(struct list_head *msg_list, u32 dnode, + struct publ_list *pls) { struct publication *publ; struct sk_buff *buf = NULL; struct distr_item *item = NULL; - u32 left = 0; - u32 rest = pls->size * ITEM_SIZE; + uint dsz = pls->size * ITEM_SIZE; + uint msg_dsz = (tipc_node_get_mtu(dnode, 0) / ITEM_SIZE) * ITEM_SIZE; + uint rem = dsz; + uint msg_rem = 0; list_for_each_entry(publ, &pls->list, local_list) { + /* Prepare next buffer: */ if (!buf) { - left = (rest <= max_item_buf) ? rest : max_item_buf; - rest -= left; - buf = named_prepare_buf(PUBLICATION, left, node); + msg_rem = min_t(uint, rem, msg_dsz); + rem -= msg_rem; + buf = named_prepare_buf(PUBLICATION, msg_rem, dnode); if (!buf) { pr_warn("Bulk publication failure\n"); return; } item = (struct distr_item *)msg_data(buf_msg(buf)); } + + /* Pack publication into message: */ publ_to_item(item, publ); item++; - left -= ITEM_SIZE; - if (!left) { - list_add_tail((struct list_head *)buf, message_list); + msg_rem -= ITEM_SIZE; + + /* Append full buffer to list: */ + if (!msg_rem) { + list_add_tail((struct list_head *)buf, msg_list); buf = NULL; } } @@ -211,16 +219,20 @@ static void named_distribute(struct list_head *message_list, u32 node, /** * tipc_named_node_up - tell specified node about all publications by this node */ -void tipc_named_node_up(u32 max_item_buf, u32 node) +void tipc_named_node_up(u32 dnode) { - LIST_HEAD(message_list); + LIST_HEAD(msg_list); + struct sk_buff *buf_chain; read_lock_bh(&tipc_nametbl_lock); - named_distribute(&message_list, node, &publ_cluster, max_item_buf); - named_distribute(&message_list, node, &publ_zone, max_item_buf); + named_distribute(&msg_list, dnode, &publ_cluster); + named_distribute(&msg_list, dnode, &publ_zone); read_unlock_bh(&tipc_nametbl_lock); - tipc_link_names_xmit(&message_list, node); + /* Convert circular list to linear list and send: */ + buf_chain = (struct sk_buff *)msg_list.next; + ((struct sk_buff *)msg_list.prev)->next = NULL; + tipc_link_xmit(buf_chain, dnode, dnode); } /** diff --git a/net/tipc/name_distr.h b/net/tipc/name_distr.h index b2eed4ec1526..8afe32b7fc9a 100644 --- a/net/tipc/name_distr.h +++ b/net/tipc/name_distr.h @@ -70,7 +70,7 @@ struct distr_item { struct sk_buff *tipc_named_publish(struct publication *publ); struct sk_buff *tipc_named_withdraw(struct publication *publ); void named_cluster_distribute(struct sk_buff *buf); -void tipc_named_node_up(u32 max_item_buf, u32 node); +void tipc_named_node_up(u32 dnode); void tipc_named_rcv(struct sk_buff *buf); void tipc_named_reinit(void); diff --git a/net/tipc/net.c b/net/tipc/net.c index f64375e7f99f..7fcc94998fea 100644 --- a/net/tipc/net.c +++ b/net/tipc/net.c @@ -1,7 +1,7 @@ /* * net/tipc/net.c: TIPC network routing code * - * Copyright (c) 1995-2006, Ericsson AB + * Copyright (c) 1995-2006, 2014, Ericsson AB * Copyright (c) 2005, 2010-2011, Wind River Systems * All rights reserved. * @@ -104,67 +104,6 @@ * - A local spin_lock protecting the queue of subscriber events. */ -static void net_route_named_msg(struct sk_buff *buf) -{ - struct tipc_msg *msg = buf_msg(buf); - u32 dnode; - u32 dport; - - if (!msg_named(msg)) { - kfree_skb(buf); - return; - } - - dnode = addr_domain(msg_lookup_scope(msg)); - dport = tipc_nametbl_translate(msg_nametype(msg), msg_nameinst(msg), &dnode); - if (dport) { - msg_set_destnode(msg, dnode); - msg_set_destport(msg, dport); - tipc_net_route_msg(buf); - return; - } - tipc_reject_msg(buf, TIPC_ERR_NO_NAME); -} - -void tipc_net_route_msg(struct sk_buff *buf) -{ - struct tipc_msg *msg; - u32 dnode; - - if (!buf) - return; - msg = buf_msg(buf); - - /* Handle message for this node */ - dnode = msg_short(msg) ? tipc_own_addr : msg_destnode(msg); - if (tipc_in_scope(dnode, tipc_own_addr)) { - if (msg_isdata(msg)) { - if (msg_mcast(msg)) - tipc_port_mcast_rcv(buf, NULL); - else if (msg_destport(msg)) - tipc_sk_rcv(buf); - else - net_route_named_msg(buf); - return; - } - switch (msg_user(msg)) { - case NAME_DISTRIBUTOR: - tipc_named_rcv(buf); - break; - case CONN_MANAGER: - tipc_port_proto_rcv(buf); - break; - default: - kfree_skb(buf); - } - return; - } - - /* Handle message for another node */ - skb_trim(buf, msg_size(msg)); - tipc_link_xmit(buf, dnode, msg_link_selector(msg)); -} - int tipc_net_start(u32 addr) { char addr_string[16]; diff --git a/net/tipc/net.h b/net/tipc/net.h index c6c2b46f7c28..59ef3388be2c 100644 --- a/net/tipc/net.h +++ b/net/tipc/net.h @@ -37,8 +37,6 @@ #ifndef _TIPC_NET_H #define _TIPC_NET_H -void tipc_net_route_msg(struct sk_buff *buf); - int tipc_net_start(u32 addr); void tipc_net_stop(void); diff --git a/net/tipc/node.c b/net/tipc/node.c index 5b44c3041be4..f7069299943f 100644 --- a/net/tipc/node.c +++ b/net/tipc/node.c @@ -1,7 +1,7 @@ /* * net/tipc/node.c: TIPC node management routines * - * Copyright (c) 2000-2006, 2012 Ericsson AB + * Copyright (c) 2000-2006, 2012-2014, Ericsson AB * Copyright (c) 2005-2006, 2010-2014, Wind River Systems * All rights reserved. * @@ -155,21 +155,25 @@ void tipc_node_link_up(struct tipc_node *n_ptr, struct tipc_link *l_ptr) if (!active[0]) { active[0] = active[1] = l_ptr; node_established_contact(n_ptr); - return; + goto exit; } if (l_ptr->priority < active[0]->priority) { pr_info("New link <%s> becomes standby\n", l_ptr->name); - return; + goto exit; } tipc_link_dup_queue_xmit(active[0], l_ptr); if (l_ptr->priority == active[0]->priority) { active[0] = l_ptr; - return; + goto exit; } pr_info("Old link <%s> becomes standby\n", active[0]->name); if (active[1] != active[0]) pr_info("Old link <%s> becomes standby\n", active[1]->name); active[0] = active[1] = l_ptr; +exit: + /* Leave room for changeover header when returning 'mtu' to users: */ + n_ptr->act_mtus[0] = active[0]->max_pkt - INT_H_SIZE; + n_ptr->act_mtus[1] = active[1]->max_pkt - INT_H_SIZE; } /** @@ -229,6 +233,19 @@ void tipc_node_link_down(struct tipc_node *n_ptr, struct tipc_link *l_ptr) tipc_link_failover_send_queue(l_ptr); else node_lost_contact(n_ptr); + + /* Leave room for changeover header when returning 'mtu' to users: */ + if (active[0]) { + n_ptr->act_mtus[0] = active[0]->max_pkt - INT_H_SIZE; + n_ptr->act_mtus[1] = active[1]->max_pkt - INT_H_SIZE; + return; + } + + /* Loopback link went down? No fragmentation needed from now on. */ + if (n_ptr->addr == tipc_own_addr) { + n_ptr->act_mtus[0] = MAX_MSG_SIZE; + n_ptr->act_mtus[1] = MAX_MSG_SIZE; + } } int tipc_node_active_links(struct tipc_node *n_ptr) @@ -457,8 +474,6 @@ int tipc_node_get_linkname(u32 bearer_id, u32 addr, char *linkname, size_t len) void tipc_node_unlock(struct tipc_node *node) { LIST_HEAD(nsub_list); - struct tipc_link *link; - int pkt_sz = 0; u32 addr = 0; if (likely(!node->action_flags)) { @@ -471,18 +486,13 @@ void tipc_node_unlock(struct tipc_node *node) node->action_flags &= ~TIPC_NOTIFY_NODE_DOWN; } if (node->action_flags & TIPC_NOTIFY_NODE_UP) { - link = node->active_links[0]; node->action_flags &= ~TIPC_NOTIFY_NODE_UP; - if (link) { - pkt_sz = ((link->max_pkt - INT_H_SIZE) / ITEM_SIZE) * - ITEM_SIZE; - addr = node->addr; - } + addr = node->addr; } spin_unlock_bh(&node->lock); if (!list_empty(&nsub_list)) tipc_nodesub_notify(&nsub_list); - if (pkt_sz) - tipc_named_node_up(pkt_sz, addr); + if (addr) + tipc_named_node_up(addr); } diff --git a/net/tipc/node.h b/net/tipc/node.h index 9087063793f2..b61716a8218e 100644 --- a/net/tipc/node.h +++ b/net/tipc/node.h @@ -41,6 +41,7 @@ #include "addr.h" #include "net.h" #include "bearer.h" +#include "msg.h" /* * Out-of-range value for node signature @@ -105,6 +106,7 @@ struct tipc_node { spinlock_t lock; struct hlist_node hash; struct tipc_link *active_links[2]; + u32 act_mtus[2]; struct tipc_link *links[MAX_BEARERS]; unsigned int action_flags; struct tipc_node_bclink bclink; @@ -143,4 +145,19 @@ static inline bool tipc_node_blocked(struct tipc_node *node) TIPC_NOTIFY_NODE_DOWN | TIPC_WAIT_OWN_LINKS_DOWN)); } +static inline uint tipc_node_get_mtu(u32 addr, u32 selector) +{ + struct tipc_node *node; + u32 mtu; + + node = tipc_node_find(addr); + + if (likely(node)) + mtu = node->act_mtus[selector & 1]; + else + mtu = MAX_MSG_SIZE; + + return mtu; +} + #endif diff --git a/net/tipc/node_subscr.c b/net/tipc/node_subscr.c index 7c59ab1d6ecb..2d13eea8574a 100644 --- a/net/tipc/node_subscr.c +++ b/net/tipc/node_subscr.c @@ -84,11 +84,13 @@ void tipc_nodesub_unsubscribe(struct tipc_node_subscr *node_sub) void tipc_nodesub_notify(struct list_head *nsub_list) { struct tipc_node_subscr *ns, *safe; + net_ev_handler handle_node_down; list_for_each_entry_safe(ns, safe, nsub_list, nodesub_list) { - if (ns->handle_node_down) { - ns->handle_node_down(ns->usr_handle); + handle_node_down = ns->handle_node_down; + if (handle_node_down) { ns->handle_node_down = NULL; + handle_node_down(ns->usr_handle); } } } diff --git a/net/tipc/port.c b/net/tipc/port.c index 5fd7acce01ea..7e096a5e7701 100644 --- a/net/tipc/port.c +++ b/net/tipc/port.c @@ -42,8 +42,6 @@ /* Connection management: */ #define PROBING_INTERVAL 3600000 /* [ms] => 1 h */ -#define CONFIRMED 0 -#define PROBING 1 #define MAX_REJECT_SIZE 1024 @@ -76,124 +74,6 @@ int tipc_port_peer_msg(struct tipc_port *p_ptr, struct tipc_msg *msg) (!peernode && (orignode == tipc_own_addr)); } -/** - * tipc_port_mcast_xmit - send a multicast message to local and remote - * destinations - */ -int tipc_port_mcast_xmit(struct tipc_port *oport, - struct tipc_name_seq const *seq, - struct iovec const *msg_sect, - unsigned int len) -{ - struct tipc_msg *hdr; - struct sk_buff *buf; - struct sk_buff *ibuf = NULL; - struct tipc_port_list dports = {0, NULL, }; - int ext_targets; - int res; - - /* Create multicast message */ - hdr = &oport->phdr; - msg_set_type(hdr, TIPC_MCAST_MSG); - msg_set_lookup_scope(hdr, TIPC_CLUSTER_SCOPE); - msg_set_destport(hdr, 0); - msg_set_destnode(hdr, 0); - msg_set_nametype(hdr, seq->type); - msg_set_namelower(hdr, seq->lower); - msg_set_nameupper(hdr, seq->upper); - msg_set_hdr_sz(hdr, MCAST_H_SIZE); - res = tipc_msg_build(hdr, msg_sect, len, MAX_MSG_SIZE, &buf); - if (unlikely(!buf)) - return res; - - /* Figure out where to send multicast message */ - ext_targets = tipc_nametbl_mc_translate(seq->type, seq->lower, seq->upper, - TIPC_NODE_SCOPE, &dports); - - /* Send message to destinations (duplicate it only if necessary) */ - if (ext_targets) { - if (dports.count != 0) { - ibuf = skb_copy(buf, GFP_ATOMIC); - if (ibuf == NULL) { - tipc_port_list_free(&dports); - kfree_skb(buf); - return -ENOMEM; - } - } - res = tipc_bclink_xmit(buf); - if ((res < 0) && (dports.count != 0)) - kfree_skb(ibuf); - } else { - ibuf = buf; - } - - if (res >= 0) { - if (ibuf) - tipc_port_mcast_rcv(ibuf, &dports); - } else { - tipc_port_list_free(&dports); - } - return res; -} - -/** - * tipc_port_mcast_rcv - deliver multicast message to all destination ports - * - * If there is no port list, perform a lookup to create one - */ -void tipc_port_mcast_rcv(struct sk_buff *buf, struct tipc_port_list *dp) -{ - struct tipc_msg *msg; - struct tipc_port_list dports = {0, NULL, }; - struct tipc_port_list *item = dp; - int cnt = 0; - - msg = buf_msg(buf); - - /* Create destination port list, if one wasn't supplied */ - if (dp == NULL) { - tipc_nametbl_mc_translate(msg_nametype(msg), - msg_namelower(msg), - msg_nameupper(msg), - TIPC_CLUSTER_SCOPE, - &dports); - item = dp = &dports; - } - - /* Deliver a copy of message to each destination port */ - if (dp->count != 0) { - msg_set_destnode(msg, tipc_own_addr); - if (dp->count == 1) { - msg_set_destport(msg, dp->ports[0]); - tipc_sk_rcv(buf); - tipc_port_list_free(dp); - return; - } - for (; cnt < dp->count; cnt++) { - int index = cnt % PLSIZE; - struct sk_buff *b = skb_clone(buf, GFP_ATOMIC); - - if (b == NULL) { - pr_warn("Unable to deliver multicast message(s)\n"); - goto exit; - } - if ((index == 0) && (cnt != 0)) - item = item->next; - msg_set_destport(buf_msg(b), item->ports[index]); - tipc_sk_rcv(b); - } - } -exit: - kfree_skb(buf); - tipc_port_list_free(dp); -} - - -void tipc_port_wakeup(struct tipc_port *port) -{ - tipc_sock_wakeup(tipc_port_to_sock(port)); -} - /* tipc_port_init - intiate TIPC port and lock it * * Returns obtained reference if initialization is successful, zero otherwise @@ -235,6 +115,8 @@ u32 tipc_port_init(struct tipc_port *p_ptr, void tipc_port_destroy(struct tipc_port *p_ptr) { struct sk_buff *buf = NULL; + struct tipc_msg *msg = NULL; + u32 peer; tipc_withdraw(p_ptr, 0, NULL); @@ -246,14 +128,15 @@ void tipc_port_destroy(struct tipc_port *p_ptr) if (p_ptr->connected) { buf = port_build_peer_abort_msg(p_ptr, TIPC_ERR_NO_PORT); tipc_nodesub_unsubscribe(&p_ptr->subscription); + msg = buf_msg(buf); + peer = msg_destnode(msg); + tipc_link_xmit(buf, peer, msg_link_selector(msg)); } - spin_lock_bh(&tipc_port_list_lock); list_del(&p_ptr->port_list); list_del(&p_ptr->wait_list); spin_unlock_bh(&tipc_port_list_lock); k_term_timer(&p_ptr->timer); - tipc_net_route_msg(buf); } /* @@ -275,100 +158,16 @@ static struct sk_buff *port_build_proto_msg(struct tipc_port *p_ptr, msg_set_destport(msg, tipc_port_peerport(p_ptr)); msg_set_origport(msg, p_ptr->ref); msg_set_msgcnt(msg, ack); + buf->next = NULL; } return buf; } -int tipc_reject_msg(struct sk_buff *buf, u32 err) -{ - struct tipc_msg *msg = buf_msg(buf); - struct sk_buff *rbuf; - struct tipc_msg *rmsg; - int hdr_sz; - u32 imp; - u32 data_sz = msg_data_sz(msg); - u32 src_node; - u32 rmsg_sz; - - /* discard rejected message if it shouldn't be returned to sender */ - if (WARN(!msg_isdata(msg), - "attempt to reject message with user=%u", msg_user(msg))) { - dump_stack(); - goto exit; - } - if (msg_errcode(msg) || msg_dest_droppable(msg)) - goto exit; - - /* - * construct returned message by copying rejected message header and - * data (or subset), then updating header fields that need adjusting - */ - hdr_sz = msg_hdr_sz(msg); - rmsg_sz = hdr_sz + min_t(u32, data_sz, MAX_REJECT_SIZE); - - rbuf = tipc_buf_acquire(rmsg_sz); - if (rbuf == NULL) - goto exit; - - rmsg = buf_msg(rbuf); - skb_copy_to_linear_data(rbuf, msg, rmsg_sz); - - if (msg_connected(rmsg)) { - imp = msg_importance(rmsg); - if (imp < TIPC_CRITICAL_IMPORTANCE) - msg_set_importance(rmsg, ++imp); - } - msg_set_non_seq(rmsg, 0); - msg_set_size(rmsg, rmsg_sz); - msg_set_errcode(rmsg, err); - msg_set_prevnode(rmsg, tipc_own_addr); - msg_swap_words(rmsg, 4, 5); - if (!msg_short(rmsg)) - msg_swap_words(rmsg, 6, 7); - - /* send self-abort message when rejecting on a connected port */ - if (msg_connected(msg)) { - struct tipc_port *p_ptr = tipc_port_lock(msg_destport(msg)); - - if (p_ptr) { - struct sk_buff *abuf = NULL; - - if (p_ptr->connected) - abuf = port_build_self_abort_msg(p_ptr, err); - tipc_port_unlock(p_ptr); - tipc_net_route_msg(abuf); - } - } - - /* send returned message & dispose of rejected message */ - src_node = msg_prevnode(msg); - if (in_own_node(src_node)) - tipc_sk_rcv(rbuf); - else - tipc_link_xmit(rbuf, src_node, msg_link_selector(rmsg)); -exit: - kfree_skb(buf); - return data_sz; -} - -int tipc_port_iovec_reject(struct tipc_port *p_ptr, struct tipc_msg *hdr, - struct iovec const *msg_sect, unsigned int len, - int err) -{ - struct sk_buff *buf; - int res; - - res = tipc_msg_build(hdr, msg_sect, len, MAX_MSG_SIZE, &buf); - if (!buf) - return res; - - return tipc_reject_msg(buf, err); -} - static void port_timeout(unsigned long ref) { struct tipc_port *p_ptr = tipc_port_lock(ref); struct sk_buff *buf = NULL; + struct tipc_msg *msg = NULL; if (!p_ptr) return; @@ -379,15 +178,16 @@ static void port_timeout(unsigned long ref) } /* Last probe answered ? */ - if (p_ptr->probing_state == PROBING) { + if (p_ptr->probing_state == TIPC_CONN_PROBING) { buf = port_build_self_abort_msg(p_ptr, TIPC_ERR_NO_PORT); } else { buf = port_build_proto_msg(p_ptr, CONN_PROBE, 0); - p_ptr->probing_state = PROBING; + p_ptr->probing_state = TIPC_CONN_PROBING; k_start_timer(&p_ptr->timer, p_ptr->probing_interval); } tipc_port_unlock(p_ptr); - tipc_net_route_msg(buf); + msg = buf_msg(buf); + tipc_link_xmit(buf, msg_destnode(msg), msg_link_selector(msg)); } @@ -395,12 +195,14 @@ static void port_handle_node_down(unsigned long ref) { struct tipc_port *p_ptr = tipc_port_lock(ref); struct sk_buff *buf = NULL; + struct tipc_msg *msg = NULL; if (!p_ptr) return; buf = port_build_self_abort_msg(p_ptr, TIPC_ERR_NO_NODE); tipc_port_unlock(p_ptr); - tipc_net_route_msg(buf); + msg = buf_msg(buf); + tipc_link_xmit(buf, msg_destnode(msg), msg_link_selector(msg)); } @@ -412,6 +214,7 @@ static struct sk_buff *port_build_self_abort_msg(struct tipc_port *p_ptr, u32 er struct tipc_msg *msg = buf_msg(buf); msg_swap_words(msg, 4, 5); msg_swap_words(msg, 6, 7); + buf->next = NULL; } return buf; } @@ -436,60 +239,11 @@ static struct sk_buff *port_build_peer_abort_msg(struct tipc_port *p_ptr, u32 er if (imp < TIPC_CRITICAL_IMPORTANCE) msg_set_importance(msg, ++imp); msg_set_errcode(msg, err); + buf->next = NULL; } return buf; } -void tipc_port_proto_rcv(struct sk_buff *buf) -{ - struct tipc_msg *msg = buf_msg(buf); - struct tipc_port *p_ptr; - struct sk_buff *r_buf = NULL; - u32 destport = msg_destport(msg); - int wakeable; - - /* Validate connection */ - p_ptr = tipc_port_lock(destport); - if (!p_ptr || !p_ptr->connected || !tipc_port_peer_msg(p_ptr, msg)) { - r_buf = tipc_buf_acquire(BASIC_H_SIZE); - if (r_buf) { - msg = buf_msg(r_buf); - tipc_msg_init(msg, TIPC_HIGH_IMPORTANCE, TIPC_CONN_MSG, - BASIC_H_SIZE, msg_orignode(msg)); - msg_set_errcode(msg, TIPC_ERR_NO_PORT); - msg_set_origport(msg, destport); - msg_set_destport(msg, msg_origport(msg)); - } - if (p_ptr) - tipc_port_unlock(p_ptr); - goto exit; - } - - /* Process protocol message sent by peer */ - switch (msg_type(msg)) { - case CONN_ACK: - wakeable = tipc_port_congested(p_ptr) && p_ptr->congested; - p_ptr->acked += msg_msgcnt(msg); - if (!tipc_port_congested(p_ptr)) { - p_ptr->congested = 0; - if (wakeable) - tipc_port_wakeup(p_ptr); - } - break; - case CONN_PROBE: - r_buf = port_build_proto_msg(p_ptr, CONN_PROBE_REPLY, 0); - break; - default: - /* CONN_PROBE_REPLY or unrecognized - no action required */ - break; - } - p_ptr->probing_state = CONFIRMED; - tipc_port_unlock(p_ptr); -exit: - tipc_net_route_msg(r_buf); - kfree_skb(buf); -} - static int port_print(struct tipc_port *p_ptr, char *buf, int len, int full_id) { struct publication *publ; @@ -581,16 +335,19 @@ void tipc_acknowledge(u32 ref, u32 ack) { struct tipc_port *p_ptr; struct sk_buff *buf = NULL; + struct tipc_msg *msg; p_ptr = tipc_port_lock(ref); if (!p_ptr) return; - if (p_ptr->connected) { - p_ptr->conn_unacked -= ack; + if (p_ptr->connected) buf = port_build_proto_msg(p_ptr, CONN_ACK, ack); - } + tipc_port_unlock(p_ptr); - tipc_net_route_msg(buf); + if (!buf) + return; + msg = buf_msg(buf); + tipc_link_xmit(buf, msg_destnode(msg), msg_link_selector(msg)); } int tipc_publish(struct tipc_port *p_ptr, unsigned int scope, @@ -689,7 +446,7 @@ int __tipc_port_connect(u32 ref, struct tipc_port *p_ptr, msg_set_hdr_sz(msg, SHORT_H_SIZE); p_ptr->probing_interval = PROBING_INTERVAL; - p_ptr->probing_state = CONFIRMED; + p_ptr->probing_state = TIPC_CONN_OK; p_ptr->connected = 1; k_start_timer(&p_ptr->timer, p_ptr->probing_interval); @@ -698,7 +455,7 @@ int __tipc_port_connect(u32 ref, struct tipc_port *p_ptr, (net_ev_handler)port_handle_node_down); res = 0; exit: - p_ptr->max_pkt = tipc_link_get_max_pkt(peer->node, ref); + p_ptr->max_pkt = tipc_node_get_mtu(peer->node, ref); return res; } @@ -741,6 +498,7 @@ int tipc_port_disconnect(u32 ref) */ int tipc_port_shutdown(u32 ref) { + struct tipc_msg *msg; struct tipc_port *p_ptr; struct sk_buff *buf = NULL; @@ -750,149 +508,7 @@ int tipc_port_shutdown(u32 ref) buf = port_build_peer_abort_msg(p_ptr, TIPC_CONN_SHUTDOWN); tipc_port_unlock(p_ptr); - tipc_net_route_msg(buf); + msg = buf_msg(buf); + tipc_link_xmit(buf, msg_destnode(msg), msg_link_selector(msg)); return tipc_port_disconnect(ref); } - -/* - * tipc_port_iovec_rcv: Concatenate and deliver sectioned - * message for this node. - */ -static int tipc_port_iovec_rcv(struct tipc_port *sender, - struct iovec const *msg_sect, - unsigned int len) -{ - struct sk_buff *buf; - int res; - - res = tipc_msg_build(&sender->phdr, msg_sect, len, MAX_MSG_SIZE, &buf); - if (likely(buf)) - tipc_sk_rcv(buf); - return res; -} - -/** - * tipc_send - send message sections on connection - */ -int tipc_send(struct tipc_port *p_ptr, - struct iovec const *msg_sect, - unsigned int len) -{ - u32 destnode; - int res; - - if (!p_ptr->connected) - return -EINVAL; - - p_ptr->congested = 1; - if (!tipc_port_congested(p_ptr)) { - destnode = tipc_port_peernode(p_ptr); - if (likely(!in_own_node(destnode))) - res = tipc_link_iovec_xmit_fast(p_ptr, msg_sect, len, - destnode); - else - res = tipc_port_iovec_rcv(p_ptr, msg_sect, len); - - if (likely(res != -ELINKCONG)) { - p_ptr->congested = 0; - if (res > 0) - p_ptr->sent++; - return res; - } - } - if (tipc_port_unreliable(p_ptr)) { - p_ptr->congested = 0; - return len; - } - return -ELINKCONG; -} - -/** - * tipc_send2name - send message sections to port name - */ -int tipc_send2name(struct tipc_port *p_ptr, - struct tipc_name const *name, - unsigned int domain, - struct iovec const *msg_sect, - unsigned int len) -{ - struct tipc_msg *msg; - u32 destnode = domain; - u32 destport; - int res; - - if (p_ptr->connected) - return -EINVAL; - - msg = &p_ptr->phdr; - msg_set_type(msg, TIPC_NAMED_MSG); - msg_set_hdr_sz(msg, NAMED_H_SIZE); - msg_set_nametype(msg, name->type); - msg_set_nameinst(msg, name->instance); - msg_set_lookup_scope(msg, tipc_addr_scope(domain)); - destport = tipc_nametbl_translate(name->type, name->instance, &destnode); - msg_set_destnode(msg, destnode); - msg_set_destport(msg, destport); - - if (likely(destport || destnode)) { - if (likely(in_own_node(destnode))) - res = tipc_port_iovec_rcv(p_ptr, msg_sect, len); - else if (tipc_own_addr) - res = tipc_link_iovec_xmit_fast(p_ptr, msg_sect, len, - destnode); - else - res = tipc_port_iovec_reject(p_ptr, msg, msg_sect, - len, TIPC_ERR_NO_NODE); - if (likely(res != -ELINKCONG)) { - if (res > 0) - p_ptr->sent++; - return res; - } - if (tipc_port_unreliable(p_ptr)) - return len; - - return -ELINKCONG; - } - return tipc_port_iovec_reject(p_ptr, msg, msg_sect, len, - TIPC_ERR_NO_NAME); -} - -/** - * tipc_send2port - send message sections to port identity - */ -int tipc_send2port(struct tipc_port *p_ptr, - struct tipc_portid const *dest, - struct iovec const *msg_sect, - unsigned int len) -{ - struct tipc_msg *msg; - int res; - - if (p_ptr->connected) - return -EINVAL; - - msg = &p_ptr->phdr; - msg_set_type(msg, TIPC_DIRECT_MSG); - msg_set_lookup_scope(msg, 0); - msg_set_destnode(msg, dest->node); - msg_set_destport(msg, dest->ref); - msg_set_hdr_sz(msg, BASIC_H_SIZE); - - if (in_own_node(dest->node)) - res = tipc_port_iovec_rcv(p_ptr, msg_sect, len); - else if (tipc_own_addr) - res = tipc_link_iovec_xmit_fast(p_ptr, msg_sect, len, - dest->node); - else - res = tipc_port_iovec_reject(p_ptr, msg, msg_sect, len, - TIPC_ERR_NO_NODE); - if (likely(res != -ELINKCONG)) { - if (res > 0) - p_ptr->sent++; - return res; - } - if (tipc_port_unreliable(p_ptr)) - return len; - - return -ELINKCONG; -} diff --git a/net/tipc/port.h b/net/tipc/port.h index cf4ca5b1d9a4..3f93454592b6 100644 --- a/net/tipc/port.h +++ b/net/tipc/port.h @@ -53,17 +53,13 @@ * @connected: non-zero if port is currently connected to a peer port * @conn_type: TIPC type used when connection was established * @conn_instance: TIPC instance used when connection was established - * @conn_unacked: number of unacknowledged messages received from peer port * @published: non-zero if port has one or more associated names - * @congested: non-zero if cannot send because of link or port congestion * @max_pkt: maximum packet size "hint" used when building messages sent by port * @ref: unique reference to port in TIPC object registry * @phdr: preformatted message header used when sending messages * @port_list: adjacent ports in TIPC's global list of ports * @wait_list: adjacent ports in list of ports waiting on link congestion * @waiting_pkts: - * @sent: # of non-empty messages sent by port - * @acked: # of non-empty message acknowledgements from connected port's peer * @publications: list of publications for port * @pub_count: total # of publications port has made during its lifetime * @probing_state: @@ -76,17 +72,13 @@ struct tipc_port { int connected; u32 conn_type; u32 conn_instance; - u32 conn_unacked; int published; - u32 congested; u32 max_pkt; u32 ref; struct tipc_msg phdr; struct list_head port_list; struct list_head wait_list; u32 waiting_pkts; - u32 sent; - u32 acked; struct list_head publications; u32 pub_count; u32 probing_state; @@ -104,8 +96,6 @@ struct tipc_port_list; u32 tipc_port_init(struct tipc_port *p_ptr, const unsigned int importance); -int tipc_reject_msg(struct sk_buff *buf, u32 err); - void tipc_acknowledge(u32 port_ref, u32 ack); void tipc_port_destroy(struct tipc_port *p_ptr); @@ -122,8 +112,6 @@ int tipc_port_disconnect(u32 portref); int tipc_port_shutdown(u32 ref); -void tipc_port_wakeup(struct tipc_port *port); - /* * The following routines require that the port be locked on entry */ @@ -132,39 +120,7 @@ int __tipc_port_connect(u32 ref, struct tipc_port *p_ptr, struct tipc_portid const *peer); int tipc_port_peer_msg(struct tipc_port *p_ptr, struct tipc_msg *msg); -/* - * TIPC messaging routines - */ - -int tipc_send(struct tipc_port *port, - struct iovec const *msg_sect, - unsigned int len); - -int tipc_send2name(struct tipc_port *port, - struct tipc_name const *name, - u32 domain, - struct iovec const *msg_sect, - unsigned int len); - -int tipc_send2port(struct tipc_port *port, - struct tipc_portid const *dest, - struct iovec const *msg_sect, - unsigned int len); - -int tipc_port_mcast_xmit(struct tipc_port *port, - struct tipc_name_seq const *seq, - struct iovec const *msg, - unsigned int len); - -int tipc_port_iovec_reject(struct tipc_port *p_ptr, - struct tipc_msg *hdr, - struct iovec const *msg_sect, - unsigned int len, - int err); - struct sk_buff *tipc_port_get_ports(void); -void tipc_port_proto_rcv(struct sk_buff *buf); -void tipc_port_mcast_rcv(struct sk_buff *buf, struct tipc_port_list *dp); void tipc_port_reinit(void); /** @@ -185,12 +141,6 @@ static inline void tipc_port_unlock(struct tipc_port *p_ptr) spin_unlock_bh(p_ptr->lock); } -static inline int tipc_port_congested(struct tipc_port *p_ptr) -{ - return ((p_ptr->sent - p_ptr->acked) >= TIPC_FLOWCTRL_WIN); -} - - static inline u32 tipc_port_peernode(struct tipc_port *p_ptr) { return msg_destnode(&p_ptr->phdr); diff --git a/net/tipc/socket.c b/net/tipc/socket.c index ef0475568f9e..7d423ee10897 100644 --- a/net/tipc/socket.c +++ b/net/tipc/socket.c @@ -36,20 +36,23 @@ #include "core.h" #include "port.h" +#include "name_table.h" #include "node.h" - +#include "link.h" #include <linux/export.h> #define SS_LISTENING -1 /* socket is listening */ #define SS_READY -2 /* socket is connectionless */ #define CONN_TIMEOUT_DEFAULT 8000 /* default connect timeout = 8s */ +#define TIPC_FWD_MSG 1 static int tipc_backlog_rcv(struct sock *sk, struct sk_buff *skb); static void tipc_data_ready(struct sock *sk); static void tipc_write_space(struct sock *sk); static int tipc_release(struct socket *sock); static int tipc_accept(struct socket *sock, struct socket *new_sock, int flags); +static int tipc_wait_for_sndmsg(struct socket *sock, long *timeo_p); static const struct proto_ops packet_ops; static const struct proto_ops stream_ops; @@ -123,9 +126,12 @@ static void advance_rx_queue(struct sock *sk) static void reject_rx_queue(struct sock *sk) { struct sk_buff *buf; + u32 dnode; - while ((buf = __skb_dequeue(&sk->sk_receive_queue))) - tipc_reject_msg(buf, TIPC_ERR_NO_PORT); + while ((buf = __skb_dequeue(&sk->sk_receive_queue))) { + if (tipc_msg_reverse(buf, &dnode, TIPC_ERR_NO_PORT)) + tipc_link_xmit(buf, dnode, 0); + } } /** @@ -201,6 +207,7 @@ static int tipc_sk_create(struct net *net, struct socket *sock, sk->sk_data_ready = tipc_data_ready; sk->sk_write_space = tipc_write_space; tsk->conn_timeout = CONN_TIMEOUT_DEFAULT; + tsk->sent_unacked = 0; atomic_set(&tsk->dupl_rcvcnt, 0); tipc_port_unlock(port); @@ -303,6 +310,7 @@ static int tipc_release(struct socket *sock) struct tipc_sock *tsk; struct tipc_port *port; struct sk_buff *buf; + u32 dnode; /* * Exit if socket isn't fully initialized (occurs when a failed accept() @@ -331,7 +339,8 @@ static int tipc_release(struct socket *sock) sock->state = SS_DISCONNECTING; tipc_port_disconnect(port->ref); } - tipc_reject_msg(buf, TIPC_ERR_NO_PORT); + if (tipc_msg_reverse(buf, &dnode, TIPC_ERR_NO_PORT)) + tipc_link_xmit(buf, dnode, 0); } } @@ -504,12 +513,12 @@ static unsigned int tipc_poll(struct file *file, struct socket *sock, switch ((int)sock->state) { case SS_UNCONNECTED: - if (!tsk->port.congested) + if (!tsk->link_cong) mask |= POLLOUT; break; case SS_READY: case SS_CONNECTED: - if (!tsk->port.congested) + if (!tsk->link_cong && !tipc_sk_conn_cong(tsk)) mask |= POLLOUT; /* fall thru' */ case SS_CONNECTING: @@ -526,6 +535,136 @@ static unsigned int tipc_poll(struct file *file, struct socket *sock, } /** + * tipc_sendmcast - send multicast message + * @sock: socket structure + * @seq: destination address + * @iov: message data to send + * @dsz: total length of message data + * @timeo: timeout to wait for wakeup + * + * Called from function tipc_sendmsg(), which has done all sanity checks + * Returns the number of bytes sent on success, or errno + */ +static int tipc_sendmcast(struct socket *sock, struct tipc_name_seq *seq, + struct iovec *iov, size_t dsz, long timeo) +{ + struct sock *sk = sock->sk; + struct tipc_msg *mhdr = &tipc_sk(sk)->port.phdr; + struct sk_buff *buf; + uint mtu; + int rc; + + msg_set_type(mhdr, TIPC_MCAST_MSG); + msg_set_lookup_scope(mhdr, TIPC_CLUSTER_SCOPE); + msg_set_destport(mhdr, 0); + msg_set_destnode(mhdr, 0); + msg_set_nametype(mhdr, seq->type); + msg_set_namelower(mhdr, seq->lower); + msg_set_nameupper(mhdr, seq->upper); + msg_set_hdr_sz(mhdr, MCAST_H_SIZE); + +new_mtu: + mtu = tipc_bclink_get_mtu(); + rc = tipc_msg_build(mhdr, iov, 0, dsz, mtu, &buf); + if (unlikely(rc < 0)) + return rc; + + do { + rc = tipc_bclink_xmit(buf); + if (likely(rc >= 0)) { + rc = dsz; + break; + } + if (rc == -EMSGSIZE) + goto new_mtu; + if (rc != -ELINKCONG) + break; + rc = tipc_wait_for_sndmsg(sock, &timeo); + if (rc) + kfree_skb_list(buf); + } while (!rc); + return rc; +} + +/* tipc_sk_mcast_rcv - Deliver multicast message to all destination sockets + */ +void tipc_sk_mcast_rcv(struct sk_buff *buf) +{ + struct tipc_msg *msg = buf_msg(buf); + struct tipc_port_list dports = {0, NULL, }; + struct tipc_port_list *item; + struct sk_buff *b; + uint i, last, dst = 0; + u32 scope = TIPC_CLUSTER_SCOPE; + + if (in_own_node(msg_orignode(msg))) + scope = TIPC_NODE_SCOPE; + + /* Create destination port list: */ + tipc_nametbl_mc_translate(msg_nametype(msg), + msg_namelower(msg), + msg_nameupper(msg), + scope, + &dports); + last = dports.count; + if (!last) { + kfree_skb(buf); + return; + } + + for (item = &dports; item; item = item->next) { + for (i = 0; i < PLSIZE && ++dst <= last; i++) { + b = (dst != last) ? skb_clone(buf, GFP_ATOMIC) : buf; + if (!b) { + pr_warn("Failed do clone mcast rcv buffer\n"); + continue; + } + msg_set_destport(msg, item->ports[i]); + tipc_sk_rcv(b); + } + } + tipc_port_list_free(&dports); +} + +/** + * tipc_sk_proto_rcv - receive a connection mng protocol message + * @tsk: receiving socket + * @dnode: node to send response message to, if any + * @buf: buffer containing protocol message + * Returns 0 (TIPC_OK) if message was consumed, 1 (TIPC_FWD_MSG) if + * (CONN_PROBE_REPLY) message should be forwarded. + */ +static int tipc_sk_proto_rcv(struct tipc_sock *tsk, u32 *dnode, + struct sk_buff *buf) +{ + struct tipc_msg *msg = buf_msg(buf); + struct tipc_port *port = &tsk->port; + int conn_cong; + + /* Ignore if connection cannot be validated: */ + if (!port->connected || !tipc_port_peer_msg(port, msg)) + goto exit; + + port->probing_state = TIPC_CONN_OK; + + if (msg_type(msg) == CONN_ACK) { + conn_cong = tipc_sk_conn_cong(tsk); + tsk->sent_unacked -= msg_msgcnt(msg); + if (conn_cong) + tipc_sock_wakeup(tsk); + } else if (msg_type(msg) == CONN_PROBE) { + if (!tipc_msg_reverse(buf, dnode, TIPC_OK)) + return TIPC_OK; + msg_set_type(msg, CONN_PROBE_REPLY); + return TIPC_FWD_MSG; + } + /* Do nothing if msg_type() == CONN_PROBE_REPLY */ +exit: + kfree_skb(buf); + return TIPC_OK; +} + +/** * dest_name_check - verify user is permitted to send to specified port name * @dest: destination address * @m: descriptor for message to be sent @@ -539,6 +678,8 @@ static int dest_name_check(struct sockaddr_tipc *dest, struct msghdr *m) { struct tipc_cfg_msg_hdr hdr; + if (unlikely(dest->addrtype == TIPC_ADDR_ID)) + return 0; if (likely(dest->addr.name.name.type >= TIPC_RESERVED_TYPES)) return 0; if (likely(dest->addr.name.name.type == TIPC_TOP_SRV)) @@ -575,19 +716,18 @@ static int tipc_wait_for_sndmsg(struct socket *sock, long *timeo_p) return sock_intr_errno(*timeo_p); prepare_to_wait(sk_sleep(sk), &wait, TASK_INTERRUPTIBLE); - done = sk_wait_event(sk, timeo_p, !tsk->port.congested); + done = sk_wait_event(sk, timeo_p, !tsk->link_cong); finish_wait(sk_sleep(sk), &wait); } while (!done); return 0; } - /** * tipc_sendmsg - send message in connectionless manner * @iocb: if NULL, indicates that socket lock is already held * @sock: socket structure * @m: message to send - * @total_len: length of message + * @dsz: amount of user data to be sent * * Message must have an destination specified explicitly. * Used for SOCK_RDM and SOCK_DGRAM messages, @@ -597,100 +737,123 @@ static int tipc_wait_for_sndmsg(struct socket *sock, long *timeo_p) * Returns the number of bytes sent on success, or errno otherwise */ static int tipc_sendmsg(struct kiocb *iocb, struct socket *sock, - struct msghdr *m, size_t total_len) + struct msghdr *m, size_t dsz) { + DECLARE_SOCKADDR(struct sockaddr_tipc *, dest, m->msg_name); struct sock *sk = sock->sk; struct tipc_sock *tsk = tipc_sk(sk); struct tipc_port *port = &tsk->port; - DECLARE_SOCKADDR(struct sockaddr_tipc *, dest, m->msg_name); - int needs_conn; + struct tipc_msg *mhdr = &port->phdr; + struct iovec *iov = m->msg_iov; + u32 dnode, dport; + struct sk_buff *buf; + struct tipc_name_seq *seq = &dest->addr.nameseq; + u32 mtu; long timeo; - int res = -EINVAL; + int rc = -EINVAL; if (unlikely(!dest)) return -EDESTADDRREQ; + if (unlikely((m->msg_namelen < sizeof(*dest)) || (dest->family != AF_TIPC))) return -EINVAL; - if (total_len > TIPC_MAX_USER_MSG_SIZE) + + if (dsz > TIPC_MAX_USER_MSG_SIZE) return -EMSGSIZE; if (iocb) lock_sock(sk); - needs_conn = (sock->state != SS_READY); - if (unlikely(needs_conn)) { + if (unlikely(sock->state != SS_READY)) { if (sock->state == SS_LISTENING) { - res = -EPIPE; + rc = -EPIPE; goto exit; } if (sock->state != SS_UNCONNECTED) { - res = -EISCONN; + rc = -EISCONN; goto exit; } if (tsk->port.published) { - res = -EOPNOTSUPP; + rc = -EOPNOTSUPP; goto exit; } if (dest->addrtype == TIPC_ADDR_NAME) { tsk->port.conn_type = dest->addr.name.name.type; tsk->port.conn_instance = dest->addr.name.name.instance; } - - /* Abort any pending connection attempts (very unlikely) */ - reject_rx_queue(sk); } + rc = dest_name_check(dest, m); + if (rc) + goto exit; timeo = sock_sndtimeo(sk, m->msg_flags & MSG_DONTWAIT); - do { - if (dest->addrtype == TIPC_ADDR_NAME) { - res = dest_name_check(dest, m); - if (res) - break; - res = tipc_send2name(port, - &dest->addr.name.name, - dest->addr.name.domain, - m->msg_iov, - total_len); - } else if (dest->addrtype == TIPC_ADDR_ID) { - res = tipc_send2port(port, - &dest->addr.id, - m->msg_iov, - total_len); - } else if (dest->addrtype == TIPC_ADDR_MCAST) { - if (needs_conn) { - res = -EOPNOTSUPP; - break; - } - res = dest_name_check(dest, m); - if (res) - break; - res = tipc_port_mcast_xmit(port, - &dest->addr.nameseq, - m->msg_iov, - total_len); + + if (dest->addrtype == TIPC_ADDR_MCAST) { + rc = tipc_sendmcast(sock, seq, iov, dsz, timeo); + goto exit; + } else if (dest->addrtype == TIPC_ADDR_NAME) { + u32 type = dest->addr.name.name.type; + u32 inst = dest->addr.name.name.instance; + u32 domain = dest->addr.name.domain; + + dnode = domain; + msg_set_type(mhdr, TIPC_NAMED_MSG); + msg_set_hdr_sz(mhdr, NAMED_H_SIZE); + msg_set_nametype(mhdr, type); + msg_set_nameinst(mhdr, inst); + msg_set_lookup_scope(mhdr, tipc_addr_scope(domain)); + dport = tipc_nametbl_translate(type, inst, &dnode); + msg_set_destnode(mhdr, dnode); + msg_set_destport(mhdr, dport); + if (unlikely(!dport && !dnode)) { + rc = -EHOSTUNREACH; + goto exit; } - if (likely(res != -ELINKCONG)) { - if (needs_conn && (res >= 0)) + } else if (dest->addrtype == TIPC_ADDR_ID) { + dnode = dest->addr.id.node; + msg_set_type(mhdr, TIPC_DIRECT_MSG); + msg_set_lookup_scope(mhdr, 0); + msg_set_destnode(mhdr, dnode); + msg_set_destport(mhdr, dest->addr.id.ref); + msg_set_hdr_sz(mhdr, BASIC_H_SIZE); + } + +new_mtu: + mtu = tipc_node_get_mtu(dnode, tsk->port.ref); + rc = tipc_msg_build(mhdr, iov, 0, dsz, mtu, &buf); + if (rc < 0) + goto exit; + + do { + rc = tipc_link_xmit(buf, dnode, tsk->port.ref); + if (likely(rc >= 0)) { + if (sock->state != SS_READY) sock->state = SS_CONNECTING; + rc = dsz; break; } - res = tipc_wait_for_sndmsg(sock, &timeo); - if (res) + if (rc == -EMSGSIZE) + goto new_mtu; + + if (rc != -ELINKCONG) break; - } while (1); + rc = tipc_wait_for_sndmsg(sock, &timeo); + if (rc) + kfree_skb_list(buf); + } while (!rc); exit: if (iocb) release_sock(sk); - return res; + + return rc; } static int tipc_wait_for_sndpkt(struct socket *sock, long *timeo_p) { struct sock *sk = sock->sk; struct tipc_sock *tsk = tipc_sk(sk); - struct tipc_port *port = &tsk->port; DEFINE_WAIT(wait); int done; @@ -709,37 +872,49 @@ static int tipc_wait_for_sndpkt(struct socket *sock, long *timeo_p) prepare_to_wait(sk_sleep(sk), &wait, TASK_INTERRUPTIBLE); done = sk_wait_event(sk, timeo_p, - (!port->congested || !port->connected)); + (!tsk->link_cong && + !tipc_sk_conn_cong(tsk)) || + !tsk->port.connected); finish_wait(sk_sleep(sk), &wait); } while (!done); return 0; } /** - * tipc_send_packet - send a connection-oriented message - * @iocb: if NULL, indicates that socket lock is already held + * tipc_send_stream - send stream-oriented data + * @iocb: (unused) * @sock: socket structure - * @m: message to send - * @total_len: length of message + * @m: data to send + * @dsz: total length of data to be transmitted * - * Used for SOCK_SEQPACKET messages and SOCK_STREAM data. + * Used for SOCK_STREAM data. * - * Returns the number of bytes sent on success, or errno otherwise + * Returns the number of bytes sent on success (or partial success), + * or errno if no data sent */ -static int tipc_send_packet(struct kiocb *iocb, struct socket *sock, - struct msghdr *m, size_t total_len) +static int tipc_send_stream(struct kiocb *iocb, struct socket *sock, + struct msghdr *m, size_t dsz) { struct sock *sk = sock->sk; struct tipc_sock *tsk = tipc_sk(sk); + struct tipc_port *port = &tsk->port; + struct tipc_msg *mhdr = &port->phdr; + struct sk_buff *buf; DECLARE_SOCKADDR(struct sockaddr_tipc *, dest, m->msg_name); - int res = -EINVAL; + u32 ref = port->ref; + int rc = -EINVAL; long timeo; + u32 dnode; + uint mtu, send, sent = 0; /* Handle implied connection establishment */ - if (unlikely(dest)) - return tipc_sendmsg(iocb, sock, m, total_len); - - if (total_len > TIPC_MAX_USER_MSG_SIZE) + if (unlikely(dest)) { + rc = tipc_sendmsg(iocb, sock, m, dsz); + if (dsz && (dsz == rc)) + tsk->sent_unacked = 1; + return rc; + } + if (dsz > (uint)INT_MAX) return -EMSGSIZE; if (iocb) @@ -747,123 +922,66 @@ static int tipc_send_packet(struct kiocb *iocb, struct socket *sock, if (unlikely(sock->state != SS_CONNECTED)) { if (sock->state == SS_DISCONNECTING) - res = -EPIPE; + rc = -EPIPE; else - res = -ENOTCONN; + rc = -ENOTCONN; goto exit; } timeo = sock_sndtimeo(sk, m->msg_flags & MSG_DONTWAIT); + dnode = tipc_port_peernode(port); + +next: + mtu = port->max_pkt; + send = min_t(uint, dsz - sent, TIPC_MAX_USER_MSG_SIZE); + rc = tipc_msg_build(mhdr, m->msg_iov, sent, send, mtu, &buf); + if (unlikely(rc < 0)) + goto exit; do { - res = tipc_send(&tsk->port, m->msg_iov, total_len); - if (likely(res != -ELINKCONG)) - break; - res = tipc_wait_for_sndpkt(sock, &timeo); - if (res) - break; - } while (1); + if (likely(!tipc_sk_conn_cong(tsk))) { + rc = tipc_link_xmit(buf, dnode, ref); + if (likely(!rc)) { + tsk->sent_unacked++; + sent += send; + if (sent == dsz) + break; + goto next; + } + if (rc == -EMSGSIZE) { + port->max_pkt = tipc_node_get_mtu(dnode, ref); + goto next; + } + if (rc != -ELINKCONG) + break; + } + rc = tipc_wait_for_sndpkt(sock, &timeo); + if (rc) + kfree_skb_list(buf); + } while (!rc); exit: if (iocb) release_sock(sk); - return res; + return sent ? sent : rc; } /** - * tipc_send_stream - send stream-oriented data - * @iocb: (unused) + * tipc_send_packet - send a connection-oriented message + * @iocb: if NULL, indicates that socket lock is already held * @sock: socket structure - * @m: data to send - * @total_len: total length of data to be sent + * @m: message to send + * @dsz: length of data to be transmitted * - * Used for SOCK_STREAM data. + * Used for SOCK_SEQPACKET messages. * - * Returns the number of bytes sent on success (or partial success), - * or errno if no data sent + * Returns the number of bytes sent on success, or errno otherwise */ -static int tipc_send_stream(struct kiocb *iocb, struct socket *sock, - struct msghdr *m, size_t total_len) +static int tipc_send_packet(struct kiocb *iocb, struct socket *sock, + struct msghdr *m, size_t dsz) { - struct sock *sk = sock->sk; - struct tipc_sock *tsk = tipc_sk(sk); - struct msghdr my_msg; - struct iovec my_iov; - struct iovec *curr_iov; - int curr_iovlen; - char __user *curr_start; - u32 hdr_size; - int curr_left; - int bytes_to_send; - int bytes_sent; - int res; - - lock_sock(sk); - - /* Handle special cases where there is no connection */ - if (unlikely(sock->state != SS_CONNECTED)) { - if (sock->state == SS_UNCONNECTED) - res = tipc_send_packet(NULL, sock, m, total_len); - else - res = sock->state == SS_DISCONNECTING ? -EPIPE : -ENOTCONN; - goto exit; - } - - if (unlikely(m->msg_name)) { - res = -EISCONN; - goto exit; - } - - if (total_len > (unsigned int)INT_MAX) { - res = -EMSGSIZE; - goto exit; - } - - /* - * Send each iovec entry using one or more messages - * - * Note: This algorithm is good for the most likely case - * (i.e. one large iovec entry), but could be improved to pass sets - * of small iovec entries into send_packet(). - */ - curr_iov = m->msg_iov; - curr_iovlen = m->msg_iovlen; - my_msg.msg_iov = &my_iov; - my_msg.msg_iovlen = 1; - my_msg.msg_flags = m->msg_flags; - my_msg.msg_name = NULL; - bytes_sent = 0; - - hdr_size = msg_hdr_sz(&tsk->port.phdr); - - while (curr_iovlen--) { - curr_start = curr_iov->iov_base; - curr_left = curr_iov->iov_len; - - while (curr_left) { - bytes_to_send = tsk->port.max_pkt - hdr_size; - if (bytes_to_send > TIPC_MAX_USER_MSG_SIZE) - bytes_to_send = TIPC_MAX_USER_MSG_SIZE; - if (curr_left < bytes_to_send) - bytes_to_send = curr_left; - my_iov.iov_base = curr_start; - my_iov.iov_len = bytes_to_send; - res = tipc_send_packet(NULL, sock, &my_msg, - bytes_to_send); - if (res < 0) { - if (bytes_sent) - res = bytes_sent; - goto exit; - } - curr_left -= bytes_to_send; - curr_start += bytes_to_send; - bytes_sent += bytes_to_send; - } + if (dsz > TIPC_MAX_USER_MSG_SIZE) + return -EMSGSIZE; - curr_iov++; - } - res = bytes_sent; -exit: - release_sock(sk); - return res; + return tipc_send_stream(iocb, sock, m, dsz); } /** @@ -1104,8 +1222,10 @@ restart: /* Consume received message (optional) */ if (likely(!(flags & MSG_PEEK))) { if ((sock->state != SS_READY) && - (++port->conn_unacked >= TIPC_CONNACK_INTV)) - tipc_acknowledge(port->ref, port->conn_unacked); + (++tsk->rcv_unacked >= TIPC_CONNACK_INTV)) { + tipc_acknowledge(port->ref, tsk->rcv_unacked); + tsk->rcv_unacked = 0; + } advance_rx_queue(sk); } exit: @@ -1213,8 +1333,10 @@ restart: /* Consume received message (optional) */ if (likely(!(flags & MSG_PEEK))) { - if (unlikely(++port->conn_unacked >= TIPC_CONNACK_INTV)) - tipc_acknowledge(port->ref, port->conn_unacked); + if (unlikely(++tsk->rcv_unacked >= TIPC_CONNACK_INTV)) { + tipc_acknowledge(port->ref, tsk->rcv_unacked); + tsk->rcv_unacked = 0; + } advance_rx_queue(sk); } @@ -1269,17 +1391,16 @@ static void tipc_data_ready(struct sock *sk) * @tsk: TIPC socket * @msg: message * - * Returns TIPC error status code and socket error status code - * once it encounters some errors + * Returns 0 (TIPC_OK) if everyting ok, -TIPC_ERR_NO_PORT otherwise */ -static u32 filter_connect(struct tipc_sock *tsk, struct sk_buff **buf) +static int filter_connect(struct tipc_sock *tsk, struct sk_buff **buf) { struct sock *sk = &tsk->sk; struct tipc_port *port = &tsk->port; struct socket *sock = sk->sk_socket; struct tipc_msg *msg = buf_msg(*buf); - u32 retval = TIPC_ERR_NO_PORT; + int retval = -TIPC_ERR_NO_PORT; int res; if (msg_mcast(msg)) @@ -1382,32 +1503,37 @@ static unsigned int rcvbuf_limit(struct sock *sk, struct sk_buff *buf) * * Called with socket lock already taken; port lock may also be taken. * - * Returns TIPC error status code (TIPC_OK if message is not to be rejected) + * Returns 0 (TIPC_OK) if message was consumed, -TIPC error code if message + * to be rejected, 1 (TIPC_FWD_MSG) if (CONN_MANAGER) message to be forwarded */ -static u32 filter_rcv(struct sock *sk, struct sk_buff *buf) +static int filter_rcv(struct sock *sk, struct sk_buff *buf) { struct socket *sock = sk->sk_socket; struct tipc_sock *tsk = tipc_sk(sk); struct tipc_msg *msg = buf_msg(buf); unsigned int limit = rcvbuf_limit(sk, buf); - u32 res = TIPC_OK; + u32 onode; + int rc = TIPC_OK; + + if (unlikely(msg_user(msg) == CONN_MANAGER)) + return tipc_sk_proto_rcv(tsk, &onode, buf); /* Reject message if it is wrong sort of message for socket */ if (msg_type(msg) > TIPC_DIRECT_MSG) - return TIPC_ERR_NO_PORT; + return -TIPC_ERR_NO_PORT; if (sock->state == SS_READY) { if (msg_connected(msg)) - return TIPC_ERR_NO_PORT; + return -TIPC_ERR_NO_PORT; } else { - res = filter_connect(tsk, &buf); - if (res != TIPC_OK || buf == NULL) - return res; + rc = filter_connect(tsk, &buf); + if (rc != TIPC_OK || buf == NULL) + return rc; } /* Reject message if there isn't room to queue it */ if (sk_rmem_alloc_get(sk) + buf->truesize >= limit) - return TIPC_ERR_OVERLOAD; + return -TIPC_ERR_OVERLOAD; /* Enqueue message */ TIPC_SKB_CB(buf)->handle = NULL; @@ -1429,16 +1555,23 @@ static u32 filter_rcv(struct sock *sk, struct sk_buff *buf) */ static int tipc_backlog_rcv(struct sock *sk, struct sk_buff *buf) { - u32 res; + int rc; + u32 onode; struct tipc_sock *tsk = tipc_sk(sk); uint truesize = buf->truesize; - res = filter_rcv(sk, buf); - if (unlikely(res)) - tipc_reject_msg(buf, res); + rc = filter_rcv(sk, buf); - if (atomic_read(&tsk->dupl_rcvcnt) < TIPC_CONN_OVERLOAD_LIMIT) - atomic_add(truesize, &tsk->dupl_rcvcnt); + if (likely(!rc)) { + if (atomic_read(&tsk->dupl_rcvcnt) < TIPC_CONN_OVERLOAD_LIMIT) + atomic_add(truesize, &tsk->dupl_rcvcnt); + return 0; + } + + if ((rc < 0) && !tipc_msg_reverse(buf, &onode, -rc)) + return 0; + + tipc_link_xmit(buf, onode, 0); return 0; } @@ -1455,19 +1588,14 @@ int tipc_sk_rcv(struct sk_buff *buf) struct tipc_port *port; struct sock *sk; u32 dport = msg_destport(buf_msg(buf)); - int err = TIPC_OK; + int rc = TIPC_OK; uint limit; + u32 dnode; - /* Forward unresolved named message */ - if (unlikely(!dport)) { - tipc_net_route_msg(buf); - return 0; - } - - /* Validate destination */ + /* Validate destination and message */ port = tipc_port_lock(dport); if (unlikely(!port)) { - err = TIPC_ERR_NO_PORT; + rc = tipc_msg_eval(buf, &dnode); goto exit; } @@ -1478,23 +1606,25 @@ int tipc_sk_rcv(struct sk_buff *buf) bh_lock_sock(sk); if (!sock_owned_by_user(sk)) { - err = filter_rcv(sk, buf); + rc = filter_rcv(sk, buf); } else { if (sk->sk_backlog.len == 0) atomic_set(&tsk->dupl_rcvcnt, 0); limit = rcvbuf_limit(sk, buf) + atomic_read(&tsk->dupl_rcvcnt); if (sk_add_backlog(sk, buf, limit)) - err = TIPC_ERR_OVERLOAD; + rc = -TIPC_ERR_OVERLOAD; } - bh_unlock_sock(sk); tipc_port_unlock(port); - if (likely(!err)) + if (likely(!rc)) return 0; exit: - tipc_reject_msg(buf, err); - return -EHOSTUNREACH; + if ((rc < 0) && !tipc_msg_reverse(buf, &dnode, -rc)) + return -EHOSTUNREACH; + + tipc_link_xmit(buf, dnode, 0); + return (rc < 0) ? -EHOSTUNREACH : 0; } static int tipc_wait_for_connect(struct socket *sock, long *timeo_p) @@ -1758,6 +1888,7 @@ static int tipc_shutdown(struct socket *sock, int how) struct tipc_sock *tsk = tipc_sk(sk); struct tipc_port *port = &tsk->port; struct sk_buff *buf; + u32 peer; int res; if (how != SHUT_RDWR) @@ -1778,7 +1909,8 @@ restart: goto restart; } tipc_port_disconnect(port->ref); - tipc_reject_msg(buf, TIPC_CONN_SHUTDOWN); + if (tipc_msg_reverse(buf, &peer, TIPC_CONN_SHUTDOWN)) + tipc_link_xmit(buf, peer, 0); } else { tipc_port_shutdown(port->ref); } @@ -1936,7 +2068,7 @@ static int tipc_getsockopt(struct socket *sock, int lvl, int opt, return put_user(sizeof(value), ol); } -int tipc_ioctl(struct socket *sk, unsigned int cmd, unsigned long arg) +static int tipc_ioctl(struct socket *sk, unsigned int cmd, unsigned long arg) { struct tipc_sioc_ln_req lnr; void __user *argp = (void __user *)arg; @@ -1952,7 +2084,6 @@ int tipc_ioctl(struct socket *sk, unsigned int cmd, unsigned long arg) return 0; } return -EADDRNOTAVAIL; - break; default: return -ENOIOCTLCMD; } diff --git a/net/tipc/socket.h b/net/tipc/socket.h index 3afcd2a70b31..43b75b3ceced 100644 --- a/net/tipc/socket.h +++ b/net/tipc/socket.h @@ -38,6 +38,9 @@ #include "port.h" #include <net/sock.h> +#define TIPC_CONN_OK 0 +#define TIPC_CONN_PROBING 1 + /** * struct tipc_sock - TIPC socket structure * @sk: socket - interacts with 'port' and with user via the socket API @@ -45,6 +48,9 @@ * @peer_name: the peer of the connection, if any * @conn_timeout: the time we can wait for an unresponded setup request * @dupl_rcvcnt: number of bytes counted twice, in both backlog and rcv queue + * @link_cong: non-zero if owner must sleep because of link congestion + * @sent_unacked: # messages sent by socket, and not yet acked by peer + * @rcv_unacked: # messages read by user, but not yet acked back to peer */ struct tipc_sock { @@ -52,6 +58,9 @@ struct tipc_sock { struct tipc_port port; unsigned int conn_timeout; atomic_t dupl_rcvcnt; + int link_cong; + uint sent_unacked; + uint rcv_unacked; }; static inline struct tipc_sock *tipc_sk(const struct sock *sk) @@ -69,6 +78,13 @@ static inline void tipc_sock_wakeup(struct tipc_sock *tsk) tsk->sk.sk_write_space(&tsk->sk); } +static inline int tipc_sk_conn_cong(struct tipc_sock *tsk) +{ + return tsk->sent_unacked >= TIPC_FLOWCTRL_WIN; +} + int tipc_sk_rcv(struct sk_buff *buf); +void tipc_sk_mcast_rcv(struct sk_buff *buf); + #endif diff --git a/net/wireless/Kconfig b/net/wireless/Kconfig index 405f3c4cf70c..29c8675f9a11 100644 --- a/net/wireless/Kconfig +++ b/net/wireless/Kconfig @@ -162,6 +162,12 @@ config CFG80211_INTERNAL_REGDB and includes code to query that database. This is an alternative to using CRDA for defining regulatory rules for the kernel. + Using this option requires some parsing of the db.txt at build time, + the parser will be upkept with the latest wireless-regdb updates but + older wireless-regdb formats will be ignored. The parser may later + be replaced to avoid issues with conflicts on versions of + wireless-regdb. + For details see: http://wireless.kernel.org/en/developers/Regulatory diff --git a/net/wireless/core.c b/net/wireless/core.c index a1c40654dd9b..afee5e0455ea 100644 --- a/net/wireless/core.c +++ b/net/wireless/core.c @@ -25,7 +25,6 @@ #include "sysfs.h" #include "debugfs.h" #include "wext-compat.h" -#include "ethtool.h" #include "rdev-ops.h" /* name for sysfs, %d is appended */ @@ -927,8 +926,6 @@ static int cfg80211_netdev_notifier_call(struct notifier_block *nb, /* allow mac80211 to determine the timeout */ wdev->ps_timeout = -1; - netdev_set_default_ethtool_ops(dev, &cfg80211_ethtool_ops); - if ((wdev->iftype == NL80211_IFTYPE_STATION || wdev->iftype == NL80211_IFTYPE_P2P_CLIENT || wdev->iftype == NL80211_IFTYPE_ADHOC) && !wdev->use_4addr) diff --git a/net/wireless/ethtool.c b/net/wireless/ethtool.c index d4860bfc020e..e9e91298c70d 100644 --- a/net/wireless/ethtool.c +++ b/net/wireless/ethtool.c @@ -1,11 +1,9 @@ #include <linux/utsname.h> #include <net/cfg80211.h> #include "core.h" -#include "ethtool.h" #include "rdev-ops.h" -static void cfg80211_get_drvinfo(struct net_device *dev, - struct ethtool_drvinfo *info) +void cfg80211_get_drvinfo(struct net_device *dev, struct ethtool_drvinfo *info) { struct wireless_dev *wdev = dev->ieee80211_ptr; @@ -23,84 +21,4 @@ static void cfg80211_get_drvinfo(struct net_device *dev, strlcpy(info->bus_info, dev_name(wiphy_dev(wdev->wiphy)), sizeof(info->bus_info)); } - -static int cfg80211_get_regs_len(struct net_device *dev) -{ - /* For now, return 0... */ - return 0; -} - -static void cfg80211_get_regs(struct net_device *dev, struct ethtool_regs *regs, - void *data) -{ - struct wireless_dev *wdev = dev->ieee80211_ptr; - - regs->version = wdev->wiphy->hw_version; - regs->len = 0; -} - -static void cfg80211_get_ringparam(struct net_device *dev, - struct ethtool_ringparam *rp) -{ - struct wireless_dev *wdev = dev->ieee80211_ptr; - struct cfg80211_registered_device *rdev = wiphy_to_rdev(wdev->wiphy); - - memset(rp, 0, sizeof(*rp)); - - if (rdev->ops->get_ringparam) - rdev_get_ringparam(rdev, &rp->tx_pending, &rp->tx_max_pending, - &rp->rx_pending, &rp->rx_max_pending); -} - -static int cfg80211_set_ringparam(struct net_device *dev, - struct ethtool_ringparam *rp) -{ - struct wireless_dev *wdev = dev->ieee80211_ptr; - struct cfg80211_registered_device *rdev = wiphy_to_rdev(wdev->wiphy); - - if (rp->rx_mini_pending != 0 || rp->rx_jumbo_pending != 0) - return -EINVAL; - - if (rdev->ops->set_ringparam) - return rdev_set_ringparam(rdev, rp->tx_pending, rp->rx_pending); - - return -ENOTSUPP; -} - -static int cfg80211_get_sset_count(struct net_device *dev, int sset) -{ - struct wireless_dev *wdev = dev->ieee80211_ptr; - struct cfg80211_registered_device *rdev = wiphy_to_rdev(wdev->wiphy); - if (rdev->ops->get_et_sset_count) - return rdev_get_et_sset_count(rdev, dev, sset); - return -EOPNOTSUPP; -} - -static void cfg80211_get_stats(struct net_device *dev, - struct ethtool_stats *stats, u64 *data) -{ - struct wireless_dev *wdev = dev->ieee80211_ptr; - struct cfg80211_registered_device *rdev = wiphy_to_rdev(wdev->wiphy); - if (rdev->ops->get_et_stats) - rdev_get_et_stats(rdev, dev, stats, data); -} - -static void cfg80211_get_strings(struct net_device *dev, u32 sset, u8 *data) -{ - struct wireless_dev *wdev = dev->ieee80211_ptr; - struct cfg80211_registered_device *rdev = wiphy_to_rdev(wdev->wiphy); - if (rdev->ops->get_et_strings) - rdev_get_et_strings(rdev, dev, sset, data); -} - -const struct ethtool_ops cfg80211_ethtool_ops = { - .get_drvinfo = cfg80211_get_drvinfo, - .get_regs_len = cfg80211_get_regs_len, - .get_regs = cfg80211_get_regs, - .get_link = ethtool_op_get_link, - .get_ringparam = cfg80211_get_ringparam, - .set_ringparam = cfg80211_set_ringparam, - .get_strings = cfg80211_get_strings, - .get_ethtool_stats = cfg80211_get_stats, - .get_sset_count = cfg80211_get_sset_count, -}; +EXPORT_SYMBOL(cfg80211_get_drvinfo); diff --git a/net/wireless/ethtool.h b/net/wireless/ethtool.h deleted file mode 100644 index 695ecad20bd6..000000000000 --- a/net/wireless/ethtool.h +++ /dev/null @@ -1,6 +0,0 @@ -#ifndef __CFG80211_ETHTOOL__ -#define __CFG80211_ETHTOOL__ - -extern const struct ethtool_ops cfg80211_ethtool_ops; - -#endif /* __CFG80211_ETHTOOL__ */ diff --git a/net/wireless/genregdb.awk b/net/wireless/genregdb.awk index 40c37fc5b67c..baf2426b555a 100644 --- a/net/wireless/genregdb.awk +++ b/net/wireless/genregdb.awk @@ -51,32 +51,41 @@ function parse_country_head() { function parse_reg_rule() { + flag_starts_at = 7 + start = $1 sub(/\(/, "", start) end = $3 bw = $5 sub(/\),/, "", bw) - gain = $6 - sub(/\(/, "", gain) - sub(/,/, "", gain) - power = $7 - sub(/\)/, "", power) - sub(/,/, "", power) + gain = 0 + power = $6 # power might be in mW... - units = $8 + units = $7 + dfs_cac = 0 + + sub(/\(/, "", power) + sub(/\),/, "", power) + sub(/\),/, "", units) sub(/\)/, "", units) - sub(/,/, "", units) - dfs_cac = $9 + if (units == "mW") { + flag_starts_at = 8 power = 10 * log(power)/log(10) + if ($8 ~ /[[:digit:]]/) { + flag_starts_at = 9 + dfs_cac = $8 + } } else { - dfs_cac = $8 + if ($7 ~ /[[:digit:]]/) { + flag_starts_at = 8 + dfs_cac = $7 + } } - sub(/,/, "", dfs_cac) sub(/\(/, "", dfs_cac) - sub(/\)/, "", dfs_cac) + sub(/\),/, "", dfs_cac) flagstr = "" - for (i=8; i<=NF; i++) + for (i=flag_starts_at; i<=NF; i++) flagstr = flagstr $i split(flagstr, flagarray, ",") flags = "" diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c index 6668daf69326..df7b1332a1ec 100644 --- a/net/wireless/nl80211.c +++ b/net/wireless/nl80211.c @@ -337,6 +337,7 @@ static const struct nla_policy nl80211_policy[NL80211_ATTR_MAX+1] = { [NL80211_ATTR_TDLS_OPERATION] = { .type = NLA_U8 }, [NL80211_ATTR_TDLS_SUPPORT] = { .type = NLA_FLAG }, [NL80211_ATTR_TDLS_EXTERNAL_SETUP] = { .type = NLA_FLAG }, + [NL80211_ATTR_TDLS_INITIATOR] = { .type = NLA_FLAG }, [NL80211_ATTR_DONT_WAIT_FOR_ACK] = { .type = NLA_FLAG }, [NL80211_ATTR_PROBE_RESP] = { .type = NLA_BINARY, .len = IEEE80211_MAX_DATA_LEN }, @@ -3813,7 +3814,8 @@ int cfg80211_check_station_change(struct wiphy *wiphy, { if (params->listen_interval != -1) return -EINVAL; - if (params->aid) + if (params->aid && + !(params->sta_flags_set & BIT(NL80211_STA_FLAG_TDLS_PEER))) return -EINVAL; /* When you run into this, adjust the code below for the new flag */ @@ -6011,17 +6013,6 @@ skip_beacons: params.radar_required = true; } - /* TODO: I left this here for now. With channel switch, the - * verification is a bit more complicated, because we only do - * it later when the channel switch really happens. - */ - err = cfg80211_can_use_iftype_chan(rdev, wdev, wdev->iftype, - params.chandef.chan, - CHAN_MODE_SHARED, - radar_detect_width); - if (err) - return err; - if (info->attrs[NL80211_ATTR_CH_SWITCH_BLOCK_TX]) params.block_tx = true; @@ -7364,6 +7355,7 @@ static int nl80211_tdls_mgmt(struct sk_buff *skb, struct genl_info *info) u32 peer_capability = 0; u16 status_code; u8 *peer; + bool initiator; if (!(rdev->wiphy.flags & WIPHY_FLAG_SUPPORTS_TDLS) || !rdev->ops->tdls_mgmt) @@ -7380,12 +7372,14 @@ static int nl80211_tdls_mgmt(struct sk_buff *skb, struct genl_info *info) action_code = nla_get_u8(info->attrs[NL80211_ATTR_TDLS_ACTION]); status_code = nla_get_u16(info->attrs[NL80211_ATTR_STATUS_CODE]); dialog_token = nla_get_u8(info->attrs[NL80211_ATTR_TDLS_DIALOG_TOKEN]); + initiator = nla_get_flag(info->attrs[NL80211_ATTR_TDLS_INITIATOR]); if (info->attrs[NL80211_ATTR_TDLS_PEER_CAPABILITY]) peer_capability = nla_get_u32(info->attrs[NL80211_ATTR_TDLS_PEER_CAPABILITY]); return rdev_tdls_mgmt(rdev, dev, peer, action_code, dialog_token, status_code, peer_capability, + initiator, nla_data(info->attrs[NL80211_ATTR_IE]), nla_len(info->attrs[NL80211_ATTR_IE])); } diff --git a/net/wireless/rdev-ops.h b/net/wireless/rdev-ops.h index d95bbe348138..56c2240c30ce 100644 --- a/net/wireless/rdev-ops.h +++ b/net/wireless/rdev-ops.h @@ -714,25 +714,6 @@ static inline int rdev_get_antenna(struct cfg80211_registered_device *rdev, return ret; } -static inline int rdev_set_ringparam(struct cfg80211_registered_device *rdev, - u32 tx, u32 rx) -{ - int ret; - trace_rdev_set_ringparam(&rdev->wiphy, tx, rx); - ret = rdev->ops->set_ringparam(&rdev->wiphy, tx, rx); - trace_rdev_return_int(&rdev->wiphy, ret); - return ret; -} - -static inline void rdev_get_ringparam(struct cfg80211_registered_device *rdev, - u32 *tx, u32 *tx_max, u32 *rx, - u32 *rx_max) -{ - trace_rdev_get_ringparam(&rdev->wiphy); - rdev->ops->get_ringparam(&rdev->wiphy, tx, tx_max, rx, rx_max); - trace_rdev_return_void_tx_rx(&rdev->wiphy, *tx, *tx_max, *rx, *rx_max); -} - static inline int rdev_sched_scan_start(struct cfg80211_registered_device *rdev, struct net_device *dev, @@ -770,15 +751,15 @@ static inline int rdev_tdls_mgmt(struct cfg80211_registered_device *rdev, struct net_device *dev, u8 *peer, u8 action_code, u8 dialog_token, u16 status_code, u32 peer_capability, - const u8 *buf, size_t len) + bool initiator, const u8 *buf, size_t len) { int ret; trace_rdev_tdls_mgmt(&rdev->wiphy, dev, peer, action_code, dialog_token, status_code, peer_capability, - buf, len); + initiator, buf, len); ret = rdev->ops->tdls_mgmt(&rdev->wiphy, dev, peer, action_code, dialog_token, status_code, peer_capability, - buf, len); + initiator, buf, len); trace_rdev_return_int(&rdev->wiphy, ret); return ret; } @@ -816,35 +797,6 @@ static inline int rdev_set_noack_map(struct cfg80211_registered_device *rdev, } static inline int -rdev_get_et_sset_count(struct cfg80211_registered_device *rdev, - struct net_device *dev, int sset) -{ - int ret; - trace_rdev_get_et_sset_count(&rdev->wiphy, dev, sset); - ret = rdev->ops->get_et_sset_count(&rdev->wiphy, dev, sset); - trace_rdev_return_int(&rdev->wiphy, ret); - return ret; -} - -static inline void rdev_get_et_stats(struct cfg80211_registered_device *rdev, - struct net_device *dev, - struct ethtool_stats *stats, u64 *data) -{ - trace_rdev_get_et_stats(&rdev->wiphy, dev); - rdev->ops->get_et_stats(&rdev->wiphy, dev, stats, data); - trace_rdev_return_void(&rdev->wiphy); -} - -static inline void rdev_get_et_strings(struct cfg80211_registered_device *rdev, - struct net_device *dev, u32 sset, - u8 *data) -{ - trace_rdev_get_et_strings(&rdev->wiphy, dev, sset); - rdev->ops->get_et_strings(&rdev->wiphy, dev, sset, data); - trace_rdev_return_void(&rdev->wiphy); -} - -static inline int rdev_get_channel(struct cfg80211_registered_device *rdev, struct wireless_dev *wdev, struct cfg80211_chan_def *chandef) diff --git a/net/wireless/trace.h b/net/wireless/trace.h index 7cc887f9da11..0c524cd76c83 100644 --- a/net/wireless/trace.h +++ b/net/wireless/trace.h @@ -298,11 +298,6 @@ DEFINE_EVENT(wiphy_only_evt, rdev_return_void, TP_ARGS(wiphy) ); -DEFINE_EVENT(wiphy_only_evt, rdev_get_ringparam, - TP_PROTO(struct wiphy *wiphy), - TP_ARGS(wiphy) -); - DEFINE_EVENT(wiphy_only_evt, rdev_get_antenna, TP_PROTO(struct wiphy *wiphy), TP_ARGS(wiphy) @@ -580,11 +575,6 @@ DEFINE_EVENT(wiphy_netdev_evt, rdev_stop_ap, TP_ARGS(wiphy, netdev) ); -DEFINE_EVENT(wiphy_netdev_evt, rdev_get_et_stats, - TP_PROTO(struct wiphy *wiphy, struct net_device *netdev), - TP_ARGS(wiphy, netdev) -); - DEFINE_EVENT(wiphy_netdev_evt, rdev_sched_scan_stop, TP_PROTO(struct wiphy *wiphy, struct net_device *netdev), TP_ARGS(wiphy, netdev) @@ -1439,11 +1429,6 @@ DECLARE_EVENT_CLASS(tx_rx_evt, WIPHY_PR_ARG, __entry->tx, __entry->rx) ); -DEFINE_EVENT(tx_rx_evt, rdev_set_ringparam, - TP_PROTO(struct wiphy *wiphy, u32 tx, u32 rx), - TP_ARGS(wiphy, rx, tx) -); - DEFINE_EVENT(tx_rx_evt, rdev_set_antenna, TP_PROTO(struct wiphy *wiphy, u32 tx, u32 rx), TP_ARGS(wiphy, rx, tx) @@ -1469,9 +1454,9 @@ TRACE_EVENT(rdev_tdls_mgmt, TP_PROTO(struct wiphy *wiphy, struct net_device *netdev, u8 *peer, u8 action_code, u8 dialog_token, u16 status_code, u32 peer_capability, - const u8 *buf, size_t len), + bool initiator, const u8 *buf, size_t len), TP_ARGS(wiphy, netdev, peer, action_code, dialog_token, status_code, - peer_capability, buf, len), + peer_capability, initiator, buf, len), TP_STRUCT__entry( WIPHY_ENTRY NETDEV_ENTRY @@ -1480,6 +1465,7 @@ TRACE_EVENT(rdev_tdls_mgmt, __field(u8, dialog_token) __field(u16, status_code) __field(u32, peer_capability) + __field(bool, initiator) __dynamic_array(u8, buf, len) ), TP_fast_assign( @@ -1490,13 +1476,16 @@ TRACE_EVENT(rdev_tdls_mgmt, __entry->dialog_token = dialog_token; __entry->status_code = status_code; __entry->peer_capability = peer_capability; + __entry->initiator = initiator; memcpy(__get_dynamic_array(buf), buf, len); ), TP_printk(WIPHY_PR_FMT ", " NETDEV_PR_FMT ", " MAC_PR_FMT ", action_code: %u, " - "dialog_token: %u, status_code: %u, peer_capability: %u buf: %#.2x ", + "dialog_token: %u, status_code: %u, peer_capability: %u " + "initiator: %s buf: %#.2x ", WIPHY_PR_ARG, NETDEV_PR_ARG, MAC_PR_ARG(peer), __entry->action_code, __entry->dialog_token, __entry->status_code, __entry->peer_capability, + BOOL_TO_STR(__entry->initiator), ((u8 *)__get_dynamic_array(buf))[0]) ); @@ -1725,40 +1714,6 @@ TRACE_EVENT(rdev_set_noack_map, WIPHY_PR_ARG, NETDEV_PR_ARG, __entry->noack_map) ); -TRACE_EVENT(rdev_get_et_sset_count, - TP_PROTO(struct wiphy *wiphy, struct net_device *netdev, int sset), - TP_ARGS(wiphy, netdev, sset), - TP_STRUCT__entry( - WIPHY_ENTRY - NETDEV_ENTRY - __field(int, sset) - ), - TP_fast_assign( - WIPHY_ASSIGN; - NETDEV_ASSIGN; - __entry->sset = sset; - ), - TP_printk(WIPHY_PR_FMT ", " NETDEV_PR_FMT ", sset: %d", - WIPHY_PR_ARG, NETDEV_PR_ARG, __entry->sset) -); - -TRACE_EVENT(rdev_get_et_strings, - TP_PROTO(struct wiphy *wiphy, struct net_device *netdev, u32 sset), - TP_ARGS(wiphy, netdev, sset), - TP_STRUCT__entry( - WIPHY_ENTRY - NETDEV_ENTRY - __field(u32, sset) - ), - TP_fast_assign( - WIPHY_ASSIGN; - NETDEV_ASSIGN; - __entry->sset = sset; - ), - TP_printk(WIPHY_PR_FMT ", " NETDEV_PR_FMT ", sset: %u", - WIPHY_PR_ARG, NETDEV_PR_ARG, __entry->sset) -); - DEFINE_EVENT(wiphy_wdev_evt, rdev_get_channel, TP_PROTO(struct wiphy *wiphy, struct wireless_dev *wdev), TP_ARGS(wiphy, wdev) |