diff options
Diffstat (limited to 'net')
509 files changed, 21510 insertions, 12753 deletions
diff --git a/net/6lowpan/Kconfig b/net/6lowpan/Kconfig index e4a02ef55102..7fa0f382e7d1 100644 --- a/net/6lowpan/Kconfig +++ b/net/6lowpan/Kconfig @@ -1,6 +1,61 @@ -config 6LOWPAN +menuconfig 6LOWPAN tristate "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. + +menuconfig 6LOWPAN_NHC + tristate "Next Header Compression Support" + depends on 6LOWPAN + default y + ---help--- + Support for next header compression. + +if 6LOWPAN_NHC + +config 6LOWPAN_NHC_DEST + tristate "Destination Options Header Support" + default y + ---help--- + 6LoWPAN IPv6 Destination Options Header compression according to + RFC6282. + +config 6LOWPAN_NHC_FRAGMENT + tristate "Fragment Header Support" + default y + ---help--- + 6LoWPAN IPv6 Fragment Header compression according to RFC6282. + +config 6LOWPAN_NHC_HOP + tristate "Hop-by-Hop Options Header Support" + default y + ---help--- + 6LoWPAN IPv6 Hop-by-Hop Options Header compression according to + RFC6282. + +config 6LOWPAN_NHC_IPV6 + tristate "IPv6 Header Support" + default y + ---help--- + 6LoWPAN IPv6 Header compression according to RFC6282. + +config 6LOWPAN_NHC_MOBILITY + tristate "Mobility Header Support" + default y + ---help--- + 6LoWPAN IPv6 Mobility Header compression according to RFC6282. + +config 6LOWPAN_NHC_ROUTING + tristate "Routing Header Support" + default y + ---help--- + 6LoWPAN IPv6 Routing Header compression according to RFC6282. + +config 6LOWPAN_NHC_UDP + tristate "UDP Header Support" + default y + ---help--- + 6LoWPAN IPv6 UDP Header compression according to RFC6282. + +endif diff --git a/net/6lowpan/Makefile b/net/6lowpan/Makefile index 415886bb456a..eb8baa72adc8 100644 --- a/net/6lowpan/Makefile +++ b/net/6lowpan/Makefile @@ -1,3 +1,12 @@ -obj-$(CONFIG_6LOWPAN) := 6lowpan.o +obj-$(CONFIG_6LOWPAN) += 6lowpan.o -6lowpan-y := iphc.o +6lowpan-y := iphc.o nhc.o + +#rfc6282 nhcs +obj-$(CONFIG_6LOWPAN_NHC_DEST) += nhc_dest.o +obj-$(CONFIG_6LOWPAN_NHC_FRAGMENT) += nhc_fragment.o +obj-$(CONFIG_6LOWPAN_NHC_HOP) += nhc_hop.o +obj-$(CONFIG_6LOWPAN_NHC_IPV6) += nhc_ipv6.o +obj-$(CONFIG_6LOWPAN_NHC_MOBILITY) += nhc_mobility.o +obj-$(CONFIG_6LOWPAN_NHC_ROUTING) += nhc_routing.o +obj-$(CONFIG_6LOWPAN_NHC_UDP) += nhc_udp.o diff --git a/net/6lowpan/iphc.c b/net/6lowpan/iphc.c index 32ffec6ef164..94a375c04f21 100644 --- a/net/6lowpan/iphc.c +++ b/net/6lowpan/iphc.c @@ -54,6 +54,8 @@ #include <net/ipv6.h> #include <net/af_ieee802154.h> +#include "nhc.h" + /* Uncompress address function for source and * destination address(non-multicast). * @@ -224,77 +226,6 @@ static int lowpan_uncompress_multicast_daddr(struct sk_buff *skb, return 0; } -static int uncompress_udp_header(struct sk_buff *skb, struct udphdr *uh) -{ - bool fail; - u8 tmp = 0, val = 0; - - 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, - 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, - 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, sizeof(val)); - uh->source = htons(val + LOWPAN_NHC_UDP_8BIT_PORT); - fail |= lowpan_fetch_skb(skb, &uh->dest, - sizeof(uh->dest)); - break; - case LOWPAN_NHC_UDP_CS_P_11: - 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 + - (val & 0x0f)); - break; - default: - pr_debug("ERROR: unknown UDP format\n"); - goto err; - } - - pr_debug("uncompressed UDP ports: src = %d, dst = %d\n", - ntohs(uh->source), ntohs(uh->dest)); - - /* checksum */ - if (tmp & LOWPAN_NHC_UDP_CS_C) { - pr_debug_ratelimited("checksum elided currently not supported\n"); - goto err; - } else { - fail |= lowpan_fetch_skb(skb, &uh->check, - sizeof(uh->check)); - } - - /* UDP length needs to be infered from the lower layers - * here, we obtain the hint from the remaining size of the - * frame - */ - uh->len = htons(skb->len + sizeof(struct udphdr)); - pr_debug("uncompressed UDP length: src = %d", ntohs(uh->len)); - } else { - pr_debug("ERROR: unsupported NH format\n"); - goto err; - } - - if (fail) - goto err; - - return 0; -err: - return -EINVAL; -} - /* TTL uncompression values */ static const u8 lowpan_ttl_values[] = { 0, 1, 64, 255 }; @@ -425,29 +356,11 @@ lowpan_header_decompress(struct sk_buff *skb, struct net_device *dev, return -EINVAL; } - /* UDP data uncompression */ + /* Next header data uncompression */ if (iphc0 & LOWPAN_IPHC_NH_C) { - struct udphdr uh; - const int needed = sizeof(struct udphdr) + sizeof(hdr); - - if (uncompress_udp_header(skb, &uh)) - return -EINVAL; - - /* replace the compressed UDP head by the uncompressed UDP - * header - */ - err = skb_cow(skb, needed); - if (unlikely(err)) + err = lowpan_nhc_do_uncompression(skb, dev, &hdr); + if (err < 0) return err; - - skb_push(skb, sizeof(struct udphdr)); - skb_reset_transport_header(skb); - skb_copy_to_linear_data(skb, &uh, sizeof(struct udphdr)); - - raw_dump_table(__func__, "raw UDP header dump", - (u8 *)&uh, sizeof(uh)); - - hdr.nexthdr = UIP_PROTO_UDP; } else { err = skb_cow(skb, sizeof(hdr)); if (unlikely(err)) @@ -500,71 +413,6 @@ static u8 lowpan_compress_addr_64(u8 **hc_ptr, u8 shift, return rol8(val, shift); } -static void compress_udp_header(u8 **hc_ptr, struct sk_buff *skb) -{ - struct udphdr *uh; - u8 tmp; - - /* In the case of RAW sockets the transport header is not set by - * the ip6 stack so we must set it ourselves - */ - if (skb->transport_header == skb->network_header) - skb_set_transport_header(skb, sizeof(struct ipv6hdr)); - - uh = udp_hdr(skb); - - if (((ntohs(uh->source) & LOWPAN_NHC_UDP_4BIT_MASK) == - LOWPAN_NHC_UDP_4BIT_PORT) && - ((ntohs(uh->dest) & LOWPAN_NHC_UDP_4BIT_MASK) == - LOWPAN_NHC_UDP_4BIT_PORT)) { - pr_debug("UDP header: both ports compression to 4 bits\n"); - /* compression value */ - tmp = LOWPAN_NHC_UDP_CS_P_11; - 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(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(hc_ptr, &tmp, sizeof(tmp)); - /* source port */ - 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(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(hc_ptr, &tmp, sizeof(tmp)); - /* source port */ - tmp = ntohs(uh->source) - LOWPAN_NHC_UDP_8BIT_PORT; - lowpan_push_hc_data(hc_ptr, &tmp, sizeof(tmp)); - /* destination port */ - 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(hc_ptr, &tmp, sizeof(tmp)); - /* source port */ - lowpan_push_hc_data(hc_ptr, &uh->source, sizeof(uh->source)); - /* destination port */ - lowpan_push_hc_data(hc_ptr, &uh->dest, sizeof(uh->dest)); - } - - /* checksum is always inline */ - 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) @@ -572,7 +420,7 @@ int lowpan_header_compress(struct sk_buff *skb, struct net_device *dev, u8 tmp, iphc0, iphc1, *hc_ptr; struct ipv6hdr *hdr; u8 head[100] = {}; - int addr_type; + int ret, addr_type; if (type != ETH_P_IPV6) return -EINVAL; @@ -649,13 +497,12 @@ int lowpan_header_compress(struct sk_buff *skb, struct net_device *dev, /* NOTE: payload length is always compressed */ - /* Next Header is compress if UDP */ - if (hdr->nexthdr == UIP_PROTO_UDP) - iphc0 |= LOWPAN_IPHC_NH_C; - - if ((iphc0 & LOWPAN_IPHC_NH_C) == 0) - lowpan_push_hc_data(&hc_ptr, &hdr->nexthdr, - sizeof(hdr->nexthdr)); + /* Check if we provide the nhc format for nexthdr and compression + * functionality. If not nexthdr is handled inline and not compressed. + */ + ret = lowpan_nhc_check_compression(skb, hdr, &hc_ptr, &iphc0); + if (ret < 0) + return ret; /* Hop limit * if 1: compress, encoding is 01 @@ -741,9 +588,12 @@ int lowpan_header_compress(struct sk_buff *skb, struct net_device *dev, } } - /* UDP header compression */ - if (hdr->nexthdr == UIP_PROTO_UDP) - compress_udp_header(&hc_ptr, skb); + /* next header compression */ + if (iphc0 & LOWPAN_IPHC_NH_C) { + ret = lowpan_nhc_do_compression(skb, hdr, &hc_ptr); + if (ret < 0) + return ret; + } head[0] = iphc0; head[1] = iphc1; @@ -761,4 +611,18 @@ int lowpan_header_compress(struct sk_buff *skb, struct net_device *dev, } EXPORT_SYMBOL_GPL(lowpan_header_compress); +static int __init lowpan_module_init(void) +{ + request_module_nowait("nhc_dest"); + request_module_nowait("nhc_fragment"); + request_module_nowait("nhc_hop"); + request_module_nowait("nhc_ipv6"); + request_module_nowait("nhc_mobility"); + request_module_nowait("nhc_routing"); + request_module_nowait("nhc_udp"); + + return 0; +} +module_init(lowpan_module_init); + MODULE_LICENSE("GPL"); diff --git a/net/6lowpan/nhc.c b/net/6lowpan/nhc.c new file mode 100644 index 000000000000..fd20fc51a7c4 --- /dev/null +++ b/net/6lowpan/nhc.c @@ -0,0 +1,241 @@ +/* + * 6LoWPAN next header compression + * + * + * Authors: + * Alexander Aring <aar@pengutronix.de> + * + * 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. + */ + +#include <linux/netdevice.h> + +#include <net/ipv6.h> + +#include "nhc.h" + +static struct rb_root rb_root = RB_ROOT; +static struct lowpan_nhc *lowpan_nexthdr_nhcs[NEXTHDR_MAX]; +static DEFINE_SPINLOCK(lowpan_nhc_lock); + +static int lowpan_nhc_insert(struct lowpan_nhc *nhc) +{ + struct rb_node **new = &rb_root.rb_node, *parent = NULL; + + /* Figure out where to put new node */ + while (*new) { + struct lowpan_nhc *this = container_of(*new, struct lowpan_nhc, + node); + int result, len_dif, len; + + len_dif = nhc->idlen - this->idlen; + + if (nhc->idlen < this->idlen) + len = nhc->idlen; + else + len = this->idlen; + + result = memcmp(nhc->id, this->id, len); + if (!result) + result = len_dif; + + parent = *new; + if (result < 0) + new = &((*new)->rb_left); + else if (result > 0) + new = &((*new)->rb_right); + else + return -EEXIST; + } + + /* Add new node and rebalance tree. */ + rb_link_node(&nhc->node, parent, new); + rb_insert_color(&nhc->node, &rb_root); + + return 0; +} + +static void lowpan_nhc_remove(struct lowpan_nhc *nhc) +{ + rb_erase(&nhc->node, &rb_root); +} + +static struct lowpan_nhc *lowpan_nhc_by_nhcid(const struct sk_buff *skb) +{ + struct rb_node *node = rb_root.rb_node; + const u8 *nhcid_skb_ptr = skb->data; + + while (node) { + struct lowpan_nhc *nhc = container_of(node, struct lowpan_nhc, + node); + u8 nhcid_skb_ptr_masked[LOWPAN_NHC_MAX_ID_LEN]; + int result, i; + + if (nhcid_skb_ptr + nhc->idlen > skb->data + skb->len) + return NULL; + + /* copy and mask afterwards the nhid value from skb */ + memcpy(nhcid_skb_ptr_masked, nhcid_skb_ptr, nhc->idlen); + for (i = 0; i < nhc->idlen; i++) + nhcid_skb_ptr_masked[i] &= nhc->idmask[i]; + + result = memcmp(nhcid_skb_ptr_masked, nhc->id, nhc->idlen); + if (result < 0) + node = node->rb_left; + else if (result > 0) + node = node->rb_right; + else + return nhc; + } + + return NULL; +} + +int lowpan_nhc_check_compression(struct sk_buff *skb, + const struct ipv6hdr *hdr, u8 **hc_ptr, + u8 *iphc0) +{ + struct lowpan_nhc *nhc; + + spin_lock_bh(&lowpan_nhc_lock); + + nhc = lowpan_nexthdr_nhcs[hdr->nexthdr]; + if (nhc && nhc->compress) + *iphc0 |= LOWPAN_IPHC_NH_C; + else + lowpan_push_hc_data(hc_ptr, &hdr->nexthdr, + sizeof(hdr->nexthdr)); + + spin_unlock_bh(&lowpan_nhc_lock); + + return 0; +} + +int lowpan_nhc_do_compression(struct sk_buff *skb, const struct ipv6hdr *hdr, + u8 **hc_ptr) +{ + int ret; + struct lowpan_nhc *nhc; + + spin_lock_bh(&lowpan_nhc_lock); + + nhc = lowpan_nexthdr_nhcs[hdr->nexthdr]; + /* check if the nhc module was removed in unlocked part. + * TODO: this is a workaround we should prevent unloading + * of nhc modules while unlocked part, this will always drop + * the lowpan packet but it's very unlikely. + * + * Solution isn't easy because we need to decide at + * lowpan_nhc_check_compression if we do a compression or not. + * Because the inline data which is added to skb, we can't move this + * handling. + */ + if (unlikely(!nhc || !nhc->compress)) { + ret = -EINVAL; + goto out; + } + + /* In the case of RAW sockets the transport header is not set by + * the ip6 stack so we must set it ourselves + */ + if (skb->transport_header == skb->network_header) + skb_set_transport_header(skb, sizeof(struct ipv6hdr)); + + ret = nhc->compress(skb, hc_ptr); + if (ret < 0) + goto out; + + /* skip the transport header */ + skb_pull(skb, nhc->nexthdrlen); + +out: + spin_unlock_bh(&lowpan_nhc_lock); + + return ret; +} + +int lowpan_nhc_do_uncompression(struct sk_buff *skb, struct net_device *dev, + struct ipv6hdr *hdr) +{ + struct lowpan_nhc *nhc; + int ret; + + spin_lock_bh(&lowpan_nhc_lock); + + nhc = lowpan_nhc_by_nhcid(skb); + if (nhc) { + if (nhc->uncompress) { + ret = nhc->uncompress(skb, sizeof(struct ipv6hdr) + + nhc->nexthdrlen); + if (ret < 0) { + spin_unlock_bh(&lowpan_nhc_lock); + return ret; + } + } else { + spin_unlock_bh(&lowpan_nhc_lock); + netdev_warn(dev, "received nhc id for %s which is not implemented.\n", + nhc->name); + return -ENOTSUPP; + } + } else { + spin_unlock_bh(&lowpan_nhc_lock); + netdev_warn(dev, "received unknown nhc id which was not found.\n"); + return -ENOENT; + } + + hdr->nexthdr = nhc->nexthdr; + skb_reset_transport_header(skb); + raw_dump_table(__func__, "raw transport header dump", + skb_transport_header(skb), nhc->nexthdrlen); + + spin_unlock_bh(&lowpan_nhc_lock); + + return 0; +} + +int lowpan_nhc_add(struct lowpan_nhc *nhc) +{ + int ret; + + if (!nhc->idlen || !nhc->idsetup) + return -EINVAL; + + WARN_ONCE(nhc->idlen > LOWPAN_NHC_MAX_ID_LEN, + "LOWPAN_NHC_MAX_ID_LEN should be updated to %zd.\n", + nhc->idlen); + + nhc->idsetup(nhc); + + spin_lock_bh(&lowpan_nhc_lock); + + if (lowpan_nexthdr_nhcs[nhc->nexthdr]) { + ret = -EEXIST; + goto out; + } + + ret = lowpan_nhc_insert(nhc); + if (ret < 0) + goto out; + + lowpan_nexthdr_nhcs[nhc->nexthdr] = nhc; +out: + spin_unlock_bh(&lowpan_nhc_lock); + return ret; +} +EXPORT_SYMBOL(lowpan_nhc_add); + +void lowpan_nhc_del(struct lowpan_nhc *nhc) +{ + spin_lock_bh(&lowpan_nhc_lock); + + lowpan_nhc_remove(nhc); + lowpan_nexthdr_nhcs[nhc->nexthdr] = NULL; + + spin_unlock_bh(&lowpan_nhc_lock); + + synchronize_net(); +} +EXPORT_SYMBOL(lowpan_nhc_del); diff --git a/net/6lowpan/nhc.h b/net/6lowpan/nhc.h new file mode 100644 index 000000000000..ed44938eb5de --- /dev/null +++ b/net/6lowpan/nhc.h @@ -0,0 +1,146 @@ +#ifndef __6LOWPAN_NHC_H +#define __6LOWPAN_NHC_H + +#include <linux/skbuff.h> +#include <linux/rbtree.h> +#include <linux/module.h> + +#include <net/6lowpan.h> +#include <net/ipv6.h> + +#define LOWPAN_NHC_MAX_ID_LEN 1 + +/** + * LOWPAN_NHC - helper macro to generate nh id fields and lowpan_nhc struct + * + * @__nhc: variable name of the lowpan_nhc struct. + * @_name: const char * of common header compression name. + * @_nexthdr: ipv6 nexthdr field for the header compression. + * @_nexthdrlen: ipv6 nexthdr len for the reserved space. + * @_idsetup: callback to setup id and mask values. + * @_idlen: len for the next header id and mask, should be always the same. + * @_uncompress: callback for uncompression call. + * @_compress: callback for compression call. + */ +#define LOWPAN_NHC(__nhc, _name, _nexthdr, \ + _hdrlen, _idsetup, _idlen, \ + _uncompress, _compress) \ +static u8 __nhc##_val[_idlen]; \ +static u8 __nhc##_mask[_idlen]; \ +static struct lowpan_nhc __nhc = { \ + .name = _name, \ + .nexthdr = _nexthdr, \ + .nexthdrlen = _hdrlen, \ + .id = __nhc##_val, \ + .idmask = __nhc##_mask, \ + .idlen = _idlen, \ + .idsetup = _idsetup, \ + .uncompress = _uncompress, \ + .compress = _compress, \ +} + +#define module_lowpan_nhc(__nhc) \ +static int __init __nhc##_init(void) \ +{ \ + return lowpan_nhc_add(&(__nhc)); \ +} \ +module_init(__nhc##_init); \ +static void __exit __nhc##_exit(void) \ +{ \ + lowpan_nhc_del(&(__nhc)); \ +} \ +module_exit(__nhc##_exit); + +/** + * struct lowpan_nhc - hold 6lowpan next hdr compression ifnformation + * + * @node: holder for the rbtree. + * @name: name of the specific next header compression + * @nexthdr: next header value of the protocol which should be compressed. + * @nexthdrlen: ipv6 nexthdr len for the reserved space. + * @id: array for nhc id. Note this need to be in network byteorder. + * @mask: array for nhc id mask. Note this need to be in network byteorder. + * @len: the length of the next header id and mask. + * @setup: callback to setup fill the next header id value and mask. + * @compress: callback to do the header compression. + * @uncompress: callback to do the header uncompression. + */ +struct lowpan_nhc { + struct rb_node node; + const char *name; + const u8 nexthdr; + const size_t nexthdrlen; + u8 *id; + u8 *idmask; + const size_t idlen; + + void (*idsetup)(struct lowpan_nhc *nhc); + int (*uncompress)(struct sk_buff *skb, size_t needed); + int (*compress)(struct sk_buff *skb, u8 **hc_ptr); +}; + +/** + * lowpan_nhc_by_nexthdr - return the 6lowpan nhc by ipv6 nexthdr. + * + * @nexthdr: ipv6 nexthdr value. + */ +struct lowpan_nhc *lowpan_nhc_by_nexthdr(u8 nexthdr); + +/** + * lowpan_nhc_check_compression - checks if we support compression format. If + * we support the nhc by nexthdr field, the 6LoWPAN iphc NHC bit will be + * set. If we don't support nexthdr will be added as inline data to the + * 6LoWPAN header. + * + * @skb: skb of 6LoWPAN header to read nhc and replace header. + * @hdr: ipv6hdr to check the nexthdr value + * @hc_ptr: pointer for 6LoWPAN header which should increment at the end of + * replaced header. + * @iphc0: iphc0 pointer to set the 6LoWPAN NHC bit + */ +int lowpan_nhc_check_compression(struct sk_buff *skb, + const struct ipv6hdr *hdr, u8 **hc_ptr, + u8 *iphc0); + +/** + * lowpan_nhc_do_compression - calling compress callback for nhc + * + * @skb: skb of 6LoWPAN header to read nhc and replace header. + * @hdr: ipv6hdr to set the nexthdr value + * @hc_ptr: pointer for 6LoWPAN header which should increment at the end of + * replaced header. + */ +int lowpan_nhc_do_compression(struct sk_buff *skb, const struct ipv6hdr *hdr, + u8 **hc_ptr); + +/** + * lowpan_nhc_do_uncompression - calling uncompress callback for nhc + * + * @nhc: 6LoWPAN nhc context, get by lowpan_nhc_by_ functions. + * @skb: skb of 6LoWPAN header, skb->data should be pointed to nhc id value. + * @dev: netdevice for print logging information. + * @hdr: ipv6hdr for setting nexthdr value. + */ +int lowpan_nhc_do_uncompression(struct sk_buff *skb, struct net_device *dev, + struct ipv6hdr *hdr); + +/** + * lowpan_nhc_add - register a next header compression to framework + * + * @nhc: nhc which should be add. + */ +int lowpan_nhc_add(struct lowpan_nhc *nhc); + +/** + * lowpan_nhc_del - delete a next header compression from framework + * + * @nhc: nhc which should be delete. + */ +void lowpan_nhc_del(struct lowpan_nhc *nhc); + +/** + * lowpan_nhc_init - adding all default nhcs + */ +void lowpan_nhc_init(void); + +#endif /* __6LOWPAN_NHC_H */ diff --git a/net/6lowpan/nhc_dest.c b/net/6lowpan/nhc_dest.c new file mode 100644 index 000000000000..0b292c9646eb --- /dev/null +++ b/net/6lowpan/nhc_dest.c @@ -0,0 +1,28 @@ +/* + * 6LoWPAN IPv6 Destination Options Header compression according to + * RFC6282 + * + * 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. + */ + +#include "nhc.h" + +#define LOWPAN_NHC_DEST_IDLEN 1 +#define LOWPAN_NHC_DEST_ID_0 0xe6 +#define LOWPAN_NHC_DEST_MASK_0 0xfe + +static void dest_nhid_setup(struct lowpan_nhc *nhc) +{ + nhc->id[0] = LOWPAN_NHC_DEST_ID_0; + nhc->idmask[0] = LOWPAN_NHC_DEST_MASK_0; +} + +LOWPAN_NHC(nhc_dest, "RFC6282 Destination Options", NEXTHDR_DEST, 0, + dest_nhid_setup, LOWPAN_NHC_DEST_IDLEN, NULL, NULL); + +module_lowpan_nhc(nhc_dest); +MODULE_DESCRIPTION("6LoWPAN next header RFC6282 Destination Options compression"); +MODULE_LICENSE("GPL"); diff --git a/net/6lowpan/nhc_fragment.c b/net/6lowpan/nhc_fragment.c new file mode 100644 index 000000000000..473dbc58ef84 --- /dev/null +++ b/net/6lowpan/nhc_fragment.c @@ -0,0 +1,27 @@ +/* + * 6LoWPAN IPv6 Fragment Header compression according to RFC6282 + * + * 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. + */ + +#include "nhc.h" + +#define LOWPAN_NHC_FRAGMENT_IDLEN 1 +#define LOWPAN_NHC_FRAGMENT_ID_0 0xe4 +#define LOWPAN_NHC_FRAGMENT_MASK_0 0xfe + +static void fragment_nhid_setup(struct lowpan_nhc *nhc) +{ + nhc->id[0] = LOWPAN_NHC_FRAGMENT_ID_0; + nhc->idmask[0] = LOWPAN_NHC_FRAGMENT_MASK_0; +} + +LOWPAN_NHC(nhc_fragment, "RFC6282 Fragment", NEXTHDR_FRAGMENT, 0, + fragment_nhid_setup, LOWPAN_NHC_FRAGMENT_IDLEN, NULL, NULL); + +module_lowpan_nhc(nhc_fragment); +MODULE_DESCRIPTION("6LoWPAN next header RFC6282 Fragment compression"); +MODULE_LICENSE("GPL"); diff --git a/net/6lowpan/nhc_hop.c b/net/6lowpan/nhc_hop.c new file mode 100644 index 000000000000..1eb66be16f19 --- /dev/null +++ b/net/6lowpan/nhc_hop.c @@ -0,0 +1,27 @@ +/* + * 6LoWPAN IPv6 Hop-by-Hop Options Header compression according to RFC6282 + * + * 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. + */ + +#include "nhc.h" + +#define LOWPAN_NHC_HOP_IDLEN 1 +#define LOWPAN_NHC_HOP_ID_0 0xe0 +#define LOWPAN_NHC_HOP_MASK_0 0xfe + +static void hop_nhid_setup(struct lowpan_nhc *nhc) +{ + nhc->id[0] = LOWPAN_NHC_HOP_ID_0; + nhc->idmask[0] = LOWPAN_NHC_HOP_MASK_0; +} + +LOWPAN_NHC(nhc_hop, "RFC6282 Hop-by-Hop Options", NEXTHDR_HOP, 0, + hop_nhid_setup, LOWPAN_NHC_HOP_IDLEN, NULL, NULL); + +module_lowpan_nhc(nhc_hop); +MODULE_DESCRIPTION("6LoWPAN next header RFC6282 Hop-by-Hop Options compression"); +MODULE_LICENSE("GPL"); diff --git a/net/6lowpan/nhc_ipv6.c b/net/6lowpan/nhc_ipv6.c new file mode 100644 index 000000000000..2313d1600af3 --- /dev/null +++ b/net/6lowpan/nhc_ipv6.c @@ -0,0 +1,27 @@ +/* + * 6LoWPAN IPv6 Header compression according to RFC6282 + * + * 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. + */ + +#include "nhc.h" + +#define LOWPAN_NHC_IPV6_IDLEN 1 +#define LOWPAN_NHC_IPV6_ID_0 0xee +#define LOWPAN_NHC_IPV6_MASK_0 0xfe + +static void ipv6_nhid_setup(struct lowpan_nhc *nhc) +{ + nhc->id[0] = LOWPAN_NHC_IPV6_ID_0; + nhc->idmask[0] = LOWPAN_NHC_IPV6_MASK_0; +} + +LOWPAN_NHC(nhc_ipv6, "RFC6282 IPv6", NEXTHDR_IPV6, 0, ipv6_nhid_setup, + LOWPAN_NHC_IPV6_IDLEN, NULL, NULL); + +module_lowpan_nhc(nhc_ipv6); +MODULE_DESCRIPTION("6LoWPAN next header RFC6282 IPv6 compression"); +MODULE_LICENSE("GPL"); diff --git a/net/6lowpan/nhc_mobility.c b/net/6lowpan/nhc_mobility.c new file mode 100644 index 000000000000..60d3f3886c98 --- /dev/null +++ b/net/6lowpan/nhc_mobility.c @@ -0,0 +1,27 @@ +/* + * 6LoWPAN IPv6 Mobility Header compression according to RFC6282 + * + * 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. + */ + +#include "nhc.h" + +#define LOWPAN_NHC_MOBILITY_IDLEN 1 +#define LOWPAN_NHC_MOBILITY_ID_0 0xe8 +#define LOWPAN_NHC_MOBILITY_MASK_0 0xfe + +static void mobility_nhid_setup(struct lowpan_nhc *nhc) +{ + nhc->id[0] = LOWPAN_NHC_MOBILITY_ID_0; + nhc->idmask[0] = LOWPAN_NHC_MOBILITY_MASK_0; +} + +LOWPAN_NHC(nhc_mobility, "RFC6282 Mobility", NEXTHDR_MOBILITY, 0, + mobility_nhid_setup, LOWPAN_NHC_MOBILITY_IDLEN, NULL, NULL); + +module_lowpan_nhc(nhc_mobility); +MODULE_DESCRIPTION("6LoWPAN next header RFC6282 Mobility compression"); +MODULE_LICENSE("GPL"); diff --git a/net/6lowpan/nhc_routing.c b/net/6lowpan/nhc_routing.c new file mode 100644 index 000000000000..c393280f11c4 --- /dev/null +++ b/net/6lowpan/nhc_routing.c @@ -0,0 +1,27 @@ +/* + * 6LoWPAN IPv6 Routing Header compression according to RFC6282 + * + * 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. + */ + +#include "nhc.h" + +#define LOWPAN_NHC_ROUTING_IDLEN 1 +#define LOWPAN_NHC_ROUTING_ID_0 0xe2 +#define LOWPAN_NHC_ROUTING_MASK_0 0xfe + +static void routing_nhid_setup(struct lowpan_nhc *nhc) +{ + nhc->id[0] = LOWPAN_NHC_ROUTING_ID_0; + nhc->idmask[0] = LOWPAN_NHC_ROUTING_MASK_0; +} + +LOWPAN_NHC(nhc_routing, "RFC6282 Routing", NEXTHDR_ROUTING, 0, + routing_nhid_setup, LOWPAN_NHC_ROUTING_IDLEN, NULL, NULL); + +module_lowpan_nhc(nhc_routing); +MODULE_DESCRIPTION("6LoWPAN next header RFC6282 Routing compression"); +MODULE_LICENSE("GPL"); diff --git a/net/6lowpan/nhc_udp.c b/net/6lowpan/nhc_udp.c new file mode 100644 index 000000000000..c6bcaeb428ae --- /dev/null +++ b/net/6lowpan/nhc_udp.c @@ -0,0 +1,157 @@ +/* + * 6LoWPAN IPv6 UDP compression according to RFC6282 + * + * + * Authors: + * Alexander Aring <aar@pengutronix.de> + * + * Orignal written by: + * Alexander Smirnov <alex.bluesman.smirnov@gmail.com> + * Jon Smirl <jonsmirl@gmail.com> + * + * 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. + */ + +#include "nhc.h" + +#define LOWPAN_NHC_UDP_IDLEN 1 + +static int udp_uncompress(struct sk_buff *skb, size_t needed) +{ + u8 tmp = 0, val = 0; + struct udphdr uh; + bool fail; + int err; + + fail = lowpan_fetch_skb(skb, &tmp, sizeof(tmp)); + + 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, 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, 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, sizeof(val)); + uh.source = htons(val + LOWPAN_NHC_UDP_8BIT_PORT); + fail |= lowpan_fetch_skb(skb, &uh.dest, sizeof(uh.dest)); + break; + case LOWPAN_NHC_UDP_CS_P_11: + 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 + (val & 0x0f)); + break; + default: + BUG(); + } + + pr_debug("uncompressed UDP ports: src = %d, dst = %d\n", + ntohs(uh.source), ntohs(uh.dest)); + + /* checksum */ + if (tmp & LOWPAN_NHC_UDP_CS_C) { + pr_debug_ratelimited("checksum elided currently not supported\n"); + fail = true; + } else { + fail |= lowpan_fetch_skb(skb, &uh.check, sizeof(uh.check)); + } + + if (fail) + return -EINVAL; + + /* UDP length needs to be infered from the lower layers + * here, we obtain the hint from the remaining size of the + * frame + */ + uh.len = htons(skb->len + sizeof(struct udphdr)); + pr_debug("uncompressed UDP length: src = %d", ntohs(uh.len)); + + /* replace the compressed UDP head by the uncompressed UDP + * header + */ + err = skb_cow(skb, needed); + if (unlikely(err)) + return err; + + skb_push(skb, sizeof(struct udphdr)); + skb_copy_to_linear_data(skb, &uh, sizeof(struct udphdr)); + + return 0; +} + +static int udp_compress(struct sk_buff *skb, u8 **hc_ptr) +{ + const struct udphdr *uh = udp_hdr(skb); + u8 tmp; + + if (((ntohs(uh->source) & LOWPAN_NHC_UDP_4BIT_MASK) == + LOWPAN_NHC_UDP_4BIT_PORT) && + ((ntohs(uh->dest) & LOWPAN_NHC_UDP_4BIT_MASK) == + LOWPAN_NHC_UDP_4BIT_PORT)) { + pr_debug("UDP header: both ports compression to 4 bits\n"); + /* compression value */ + tmp = LOWPAN_NHC_UDP_CS_P_11; + 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(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(hc_ptr, &tmp, sizeof(tmp)); + /* source port */ + 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(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(hc_ptr, &tmp, sizeof(tmp)); + /* source port */ + tmp = ntohs(uh->source) - LOWPAN_NHC_UDP_8BIT_PORT; + lowpan_push_hc_data(hc_ptr, &tmp, sizeof(tmp)); + /* destination port */ + 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(hc_ptr, &tmp, sizeof(tmp)); + /* source port */ + lowpan_push_hc_data(hc_ptr, &uh->source, sizeof(uh->source)); + /* destination port */ + lowpan_push_hc_data(hc_ptr, &uh->dest, sizeof(uh->dest)); + } + + /* checksum is always inline */ + lowpan_push_hc_data(hc_ptr, &uh->check, sizeof(uh->check)); + + return 0; +} + +static void udp_nhid_setup(struct lowpan_nhc *nhc) +{ + nhc->id[0] = LOWPAN_NHC_UDP_ID; + nhc->idmask[0] = LOWPAN_NHC_UDP_MASK; +} + +LOWPAN_NHC(nhc_udp, "RFC6282 UDP", NEXTHDR_UDP, sizeof(struct udphdr), + udp_nhid_setup, LOWPAN_NHC_UDP_IDLEN, udp_uncompress, udp_compress); + +module_lowpan_nhc(nhc_udp); +MODULE_DESCRIPTION("6LoWPAN next header RFC6282 UDP compression"); +MODULE_LICENSE("GPL"); diff --git a/net/802/fc.c b/net/802/fc.c index 7c174b6750cd..7b9219022418 100644 --- a/net/802/fc.c +++ b/net/802/fc.c @@ -75,29 +75,8 @@ static int fc_header(struct sk_buff *skb, struct net_device *dev, return -hdr_len; } -/* - * A neighbour discovery of some species (eg arp) has completed. We - * can now send the packet. - */ - -static int fc_rebuild_header(struct sk_buff *skb) -{ -#ifdef CONFIG_INET - struct fch_hdr *fch=(struct fch_hdr *)skb->data; - struct fcllc *fcllc=(struct fcllc *)(skb->data+sizeof(struct fch_hdr)); - if(fcllc->ethertype != htons(ETH_P_IP)) { - printk("fc_rebuild_header: Don't know how to resolve type %04X addresses ?\n", ntohs(fcllc->ethertype)); - return 0; - } - return arp_find(fch->daddr, skb); -#else - return 0; -#endif -} - static const struct header_ops fc_header_ops = { .create = fc_header, - .rebuild = fc_rebuild_header, }; static void fc_setup(struct net_device *dev) diff --git a/net/802/fddi.c b/net/802/fddi.c index 59e7346f1193..7d3a0af954e8 100644 --- a/net/802/fddi.c +++ b/net/802/fddi.c @@ -87,31 +87,6 @@ static int fddi_header(struct sk_buff *skb, struct net_device *dev, return -hl; } - -/* - * Rebuild the FDDI MAC header. This is called after an ARP - * (or in future other address resolution) has completed on - * this sk_buff. We now let ARP fill in the other fields. - */ - -static int fddi_rebuild_header(struct sk_buff *skb) -{ - struct fddihdr *fddi = (struct fddihdr *)skb->data; - -#ifdef CONFIG_INET - if (fddi->hdr.llc_snap.ethertype == htons(ETH_P_IP)) - /* Try to get ARP to resolve the header and fill destination address */ - return arp_find(fddi->daddr, skb); - else -#endif - { - printk("%s: Don't know how to resolve type %04X addresses.\n", - skb->dev->name, ntohs(fddi->hdr.llc_snap.ethertype)); - return 0; - } -} - - /* * Determine the packet's protocol ID and fill in skb fields. * This routine is called before an incoming packet is passed @@ -177,7 +152,6 @@ EXPORT_SYMBOL(fddi_change_mtu); static const struct header_ops fddi_header_ops = { .create = fddi_header, - .rebuild = fddi_rebuild_header, }; diff --git a/net/802/hippi.c b/net/802/hippi.c index 2e03f8259dd5..ade1a52cdcff 100644 --- a/net/802/hippi.c +++ b/net/802/hippi.c @@ -91,33 +91,6 @@ static int hippi_header(struct sk_buff *skb, struct net_device *dev, /* - * Rebuild the HIPPI MAC header. This is called after an ARP has - * completed on this sk_buff. We now let ARP fill in the other fields. - */ - -static int hippi_rebuild_header(struct sk_buff *skb) -{ - struct hippi_hdr *hip = (struct hippi_hdr *)skb->data; - - /* - * Only IP is currently supported - */ - - if(hip->snap.ethertype != htons(ETH_P_IP)) - { - printk(KERN_DEBUG "%s: unable to resolve type %X addresses.\n",skb->dev->name,ntohs(hip->snap.ethertype)); - return 0; - } - - /* - * We don't support dynamic ARP on HIPPI, but we use the ARP - * static ARP tables to hold the I-FIELDs. - */ - return arp_find(hip->le.daddr, skb); -} - - -/* * Determine the packet's protocol ID. */ @@ -186,7 +159,6 @@ EXPORT_SYMBOL(hippi_neigh_setup_dev); static const struct header_ops hippi_header_ops = { .create = hippi_header, - .rebuild = hippi_rebuild_header, }; diff --git a/net/8021q/vlan.c b/net/8021q/vlan.c index 64c6bed4a3d3..98a30a5b8664 100644 --- a/net/8021q/vlan.c +++ b/net/8021q/vlan.c @@ -413,7 +413,10 @@ static int vlan_device_event(struct notifier_block *unused, unsigned long event, vlan_transfer_features(dev, vlandev); break; - case NETDEV_DOWN: + case NETDEV_DOWN: { + struct net_device *tmp; + LIST_HEAD(close_list); + if (dev->features & NETIF_F_HW_VLAN_CTAG_FILTER) vlan_vid_del(dev, htons(ETH_P_8021Q), 0); @@ -425,11 +428,18 @@ static int vlan_device_event(struct notifier_block *unused, unsigned long event, vlan = vlan_dev_priv(vlandev); if (!(vlan->flags & VLAN_FLAG_LOOSE_BINDING)) - dev_change_flags(vlandev, flgs & ~IFF_UP); + list_add(&vlandev->close_list, &close_list); + } + + dev_close_many(&close_list, false); + + list_for_each_entry_safe(vlandev, tmp, &close_list, close_list) { netif_stacked_transfer_operstate(dev, vlandev); + list_del_init(&vlandev->close_list); } + list_del(&close_list); break; - + } case NETDEV_UP: /* Put all VLANs for this dev in the up state too. */ vlan_group_for_each_dev(grp, i, vlandev) { diff --git a/net/8021q/vlan_dev.c b/net/8021q/vlan_dev.c index 118956448cf6..01d7ba840df8 100644 --- a/net/8021q/vlan_dev.c +++ b/net/8021q/vlan_dev.c @@ -37,39 +37,6 @@ #include <linux/netpoll.h> /* - * Rebuild the Ethernet MAC header. This is called after an ARP - * (or in future other address resolution) has completed on this - * sk_buff. We now let ARP fill in the other fields. - * - * This routine CANNOT use cached dst->neigh! - * Really, it is used only when dst->neigh is wrong. - * - * TODO: This needs a checkup, I'm ignorant here. --BLG - */ -static int vlan_dev_rebuild_header(struct sk_buff *skb) -{ - struct net_device *dev = skb->dev; - struct vlan_ethhdr *veth = (struct vlan_ethhdr *)(skb->data); - - switch (veth->h_vlan_encapsulated_proto) { -#ifdef CONFIG_INET - case htons(ETH_P_IP): - - /* TODO: Confirm this will work with VLAN headers... */ - return arp_find(veth->h_dest, skb); -#endif - default: - pr_debug("%s: unable to resolve type %X addresses\n", - dev->name, ntohs(veth->h_vlan_encapsulated_proto)); - - ether_addr_copy(veth->h_source, dev->dev_addr); - break; - } - - return 0; -} - -/* * Create the VLAN header for an arbitrary protocol layer * * saddr=NULL means use device source address @@ -534,7 +501,6 @@ static int vlan_dev_get_lock_subclass(struct net_device *dev) static const struct header_ops vlan_header_ops = { .create = vlan_dev_hard_header, - .rebuild = vlan_dev_rebuild_header, .parse = eth_header_parse, }; @@ -554,7 +520,6 @@ static int vlan_passthru_hard_header(struct sk_buff *skb, struct net_device *dev static const struct header_ops vlan_passthru_header_ops = { .create = vlan_passthru_hard_header, - .rebuild = dev_rebuild_header, .parse = eth_header_parse, }; @@ -573,7 +538,6 @@ static int vlan_dev_init(struct net_device *dev) /* IFF_BROADCAST|IFF_MULTICAST; ??? */ dev->flags = real_dev->flags & ~(IFF_UP | IFF_PROMISC | IFF_ALLMULTI | IFF_MASTER | IFF_SLAVE); - dev->iflink = real_dev->ifindex; dev->state = (real_dev->state & ((1<<__LINK_STATE_NOCARRIER) | (1<<__LINK_STATE_DORMANT))) | (1<<__LINK_STATE_PRESENT); @@ -589,6 +553,7 @@ static int vlan_dev_init(struct net_device *dev) if (dev->features & NETIF_F_VLAN_FEATURES) netdev_warn(real_dev, "VLAN features are set incorrectly. Q-in-Q configurations may not work correctly.\n"); + dev->vlan_features = real_dev->vlan_features & ~NETIF_F_ALL_FCOE; /* ipv6 shared card related stuff */ dev->dev_id = real_dev->dev_id; @@ -767,6 +732,13 @@ static void vlan_dev_netpoll_cleanup(struct net_device *dev) } #endif /* CONFIG_NET_POLL_CONTROLLER */ +static int vlan_dev_get_iflink(const struct net_device *dev) +{ + struct net_device *real_dev = vlan_dev_priv(dev)->real_dev; + + return real_dev->ifindex; +} + static const struct ethtool_ops vlan_ethtool_ops = { .get_settings = vlan_ethtool_get_settings, .get_drvinfo = vlan_ethtool_get_drvinfo, @@ -803,6 +775,7 @@ static const struct net_device_ops vlan_netdev_ops = { #endif .ndo_fix_features = vlan_dev_fix_features, .ndo_get_lock_subclass = vlan_dev_get_lock_subclass, + .ndo_get_iflink = vlan_dev_get_iflink, }; static void vlan_dev_free(struct net_device *dev) @@ -827,5 +800,5 @@ void vlan_setup(struct net_device *dev) dev->destructor = vlan_dev_free; dev->ethtool_ops = &vlan_ethtool_ops; - memset(dev->broadcast, 0, ETH_ALEN); + eth_zero_addr(dev->broadcast); } diff --git a/net/9p/client.c b/net/9p/client.c index e86a9bea1d16..6f4c4c88db84 100644 --- a/net/9p/client.c +++ b/net/9p/client.c @@ -34,6 +34,7 @@ #include <linux/slab.h> #include <linux/sched.h> #include <linux/uaccess.h> +#include <linux/uio.h> #include <net/9p/9p.h> #include <linux/parser.h> #include <net/9p/client.h> @@ -555,7 +556,7 @@ out_err: */ static int p9_check_zc_errors(struct p9_client *c, struct p9_req_t *req, - char *uidata, int in_hdrlen, int kern_buf) + struct iov_iter *uidata, int in_hdrlen) { int err; int ecode; @@ -591,16 +592,11 @@ static int p9_check_zc_errors(struct p9_client *c, struct p9_req_t *req, ename = &req->rc->sdata[req->rc->offset]; if (len > inline_len) { /* We have error in external buffer */ - if (kern_buf) { - memcpy(ename + inline_len, uidata, - len - inline_len); - } else { - err = copy_from_user(ename + inline_len, - uidata, len - inline_len); - if (err) { - err = -EFAULT; - goto out_err; - } + err = copy_from_iter(ename + inline_len, + len - inline_len, uidata); + if (err != len - inline_len) { + err = -EFAULT; + goto out_err; } } ename = NULL; @@ -806,8 +802,8 @@ reterr: * p9_client_zc_rpc - issue a request and wait for a response * @c: client session * @type: type of request - * @uidata: user bffer that should be ued for zero copy read - * @uodata: user buffer that shoud be user for zero copy write + * @uidata: destination for zero copy read + * @uodata: source for zero copy write * @inlen: read buffer size * @olen: write buffer size * @hdrlen: reader header size, This is the size of response protocol data @@ -816,9 +812,10 @@ reterr: * Returns request structure (which client must free using p9_free_req) */ static struct p9_req_t *p9_client_zc_rpc(struct p9_client *c, int8_t type, - char *uidata, char *uodata, + struct iov_iter *uidata, + struct iov_iter *uodata, int inlen, int olen, int in_hdrlen, - int kern_buf, const char *fmt, ...) + const char *fmt, ...) { va_list ap; int sigpending, err; @@ -841,12 +838,8 @@ static struct p9_req_t *p9_client_zc_rpc(struct p9_client *c, int8_t type, } else sigpending = 0; - /* If we are called with KERNEL_DS force kern_buf */ - if (segment_eq(get_fs(), KERNEL_DS)) - kern_buf = 1; - err = c->trans_mod->zc_request(c, req, uidata, uodata, - inlen, olen, in_hdrlen, kern_buf); + inlen, olen, in_hdrlen); if (err < 0) { if (err == -EIO) c->status = Disconnected; @@ -876,7 +869,7 @@ static struct p9_req_t *p9_client_zc_rpc(struct p9_client *c, int8_t type, if (err < 0) goto reterr; - err = p9_check_zc_errors(c, req, uidata, in_hdrlen, kern_buf); + err = p9_check_zc_errors(c, req, uidata, in_hdrlen); trace_9p_client_res(c, type, req->rc->tag, err); if (!err) return req; @@ -1123,6 +1116,7 @@ struct p9_fid *p9_client_attach(struct p9_client *clnt, struct p9_fid *afid, fid = NULL; goto error; } + fid->uid = n_uname; req = p9_client_rpc(clnt, P9_TATTACH, "ddss?u", fid->fid, afid ? afid->fid : P9_NOFID, uname, aname, n_uname); @@ -1541,142 +1535,128 @@ error: EXPORT_SYMBOL(p9_client_unlinkat); int -p9_client_read(struct p9_fid *fid, char *data, char __user *udata, u64 offset, - u32 count) +p9_client_read(struct p9_fid *fid, u64 offset, struct iov_iter *to, int *err) { - char *dataptr; - int kernel_buf = 0; + struct p9_client *clnt = fid->clnt; struct p9_req_t *req; - struct p9_client *clnt; - int err, rsize, non_zc = 0; - + int total = 0; p9_debug(P9_DEBUG_9P, ">>> TREAD fid %d offset %llu %d\n", - fid->fid, (unsigned long long) offset, count); - err = 0; - clnt = fid->clnt; - - rsize = fid->iounit; - if (!rsize || rsize > clnt->msize-P9_IOHDRSZ) - rsize = clnt->msize - P9_IOHDRSZ; - - if (count < rsize) - rsize = count; - - /* Don't bother zerocopy for small IO (< 1024) */ - if (clnt->trans_mod->zc_request && rsize > 1024) { - char *indata; - if (data) { - kernel_buf = 1; - indata = data; - } else - indata = (__force char *)udata; - /* - * response header len is 11 - * PDU Header(7) + IO Size (4) - */ - req = p9_client_zc_rpc(clnt, P9_TREAD, indata, NULL, rsize, 0, - 11, kernel_buf, "dqd", fid->fid, - offset, rsize); - } else { - non_zc = 1; - req = p9_client_rpc(clnt, P9_TREAD, "dqd", fid->fid, offset, - rsize); - } - if (IS_ERR(req)) { - err = PTR_ERR(req); - goto error; - } + fid->fid, (unsigned long long) offset, (int)iov_iter_count(to)); + + while (iov_iter_count(to)) { + int count = iov_iter_count(to); + int rsize, non_zc = 0; + char *dataptr; + + rsize = fid->iounit; + if (!rsize || rsize > clnt->msize-P9_IOHDRSZ) + rsize = clnt->msize - P9_IOHDRSZ; + + if (count < rsize) + rsize = count; + + /* Don't bother zerocopy for small IO (< 1024) */ + if (clnt->trans_mod->zc_request && rsize > 1024) { + /* + * response header len is 11 + * PDU Header(7) + IO Size (4) + */ + req = p9_client_zc_rpc(clnt, P9_TREAD, to, NULL, rsize, + 0, 11, "dqd", fid->fid, + offset, rsize); + } else { + non_zc = 1; + req = p9_client_rpc(clnt, P9_TREAD, "dqd", fid->fid, offset, + rsize); + } + if (IS_ERR(req)) { + *err = PTR_ERR(req); + break; + } - err = p9pdu_readf(req->rc, clnt->proto_version, "D", &count, &dataptr); - if (err) { - trace_9p_protocol_dump(clnt, req->rc); - goto free_and_error; - } + *err = p9pdu_readf(req->rc, clnt->proto_version, + "D", &count, &dataptr); + if (*err) { + trace_9p_protocol_dump(clnt, req->rc); + p9_free_req(clnt, req); + break; + } - p9_debug(P9_DEBUG_9P, "<<< RREAD count %d\n", count); + p9_debug(P9_DEBUG_9P, "<<< RREAD count %d\n", count); + if (!count) { + p9_free_req(clnt, req); + break; + } - if (non_zc) { - if (data) { - memmove(data, dataptr, count); - } else { - err = copy_to_user(udata, dataptr, count); - if (err) { - err = -EFAULT; - goto free_and_error; + if (non_zc) { + int n = copy_to_iter(dataptr, count, to); + total += n; + offset += n; + if (n != count) { + *err = -EFAULT; + p9_free_req(clnt, req); + break; } + } else { + iov_iter_advance(to, count); + total += count; + offset += count; } + p9_free_req(clnt, req); } - p9_free_req(clnt, req); - return count; - -free_and_error: - p9_free_req(clnt, req); -error: - return err; + return total; } EXPORT_SYMBOL(p9_client_read); int -p9_client_write(struct p9_fid *fid, char *data, const char __user *udata, - u64 offset, u32 count) +p9_client_write(struct p9_fid *fid, u64 offset, struct iov_iter *from, int *err) { - int err, rsize; - int kernel_buf = 0; - struct p9_client *clnt; + struct p9_client *clnt = fid->clnt; struct p9_req_t *req; + int total = 0; + + p9_debug(P9_DEBUG_9P, ">>> TWRITE fid %d offset %llu count %zd\n", + fid->fid, (unsigned long long) offset, + iov_iter_count(from)); + + while (iov_iter_count(from)) { + int count = iov_iter_count(from); + int rsize = fid->iounit; + if (!rsize || rsize > clnt->msize-P9_IOHDRSZ) + rsize = clnt->msize - P9_IOHDRSZ; + + if (count < rsize) + rsize = count; + + /* Don't bother zerocopy for small IO (< 1024) */ + if (clnt->trans_mod->zc_request && rsize > 1024) { + req = p9_client_zc_rpc(clnt, P9_TWRITE, NULL, from, 0, + rsize, P9_ZC_HDR_SZ, "dqd", + fid->fid, offset, rsize); + } else { + req = p9_client_rpc(clnt, P9_TWRITE, "dqV", fid->fid, + offset, rsize, from); + } + if (IS_ERR(req)) { + *err = PTR_ERR(req); + break; + } - p9_debug(P9_DEBUG_9P, ">>> TWRITE fid %d offset %llu count %d\n", - fid->fid, (unsigned long long) offset, count); - err = 0; - clnt = fid->clnt; - - rsize = fid->iounit; - if (!rsize || rsize > clnt->msize-P9_IOHDRSZ) - rsize = clnt->msize - P9_IOHDRSZ; + *err = p9pdu_readf(req->rc, clnt->proto_version, "d", &count); + if (*err) { + trace_9p_protocol_dump(clnt, req->rc); + p9_free_req(clnt, req); + } - if (count < rsize) - rsize = count; + p9_debug(P9_DEBUG_9P, "<<< RWRITE count %d\n", count); - /* Don't bother zerocopy for small IO (< 1024) */ - if (clnt->trans_mod->zc_request && rsize > 1024) { - char *odata; - if (data) { - kernel_buf = 1; - odata = data; - } else - odata = (char *)udata; - req = p9_client_zc_rpc(clnt, P9_TWRITE, NULL, odata, 0, rsize, - P9_ZC_HDR_SZ, kernel_buf, "dqd", - fid->fid, offset, rsize); - } else { - if (data) - req = p9_client_rpc(clnt, P9_TWRITE, "dqD", fid->fid, - offset, rsize, data); - else - req = p9_client_rpc(clnt, P9_TWRITE, "dqU", fid->fid, - offset, rsize, udata); - } - if (IS_ERR(req)) { - err = PTR_ERR(req); - goto error; - } - - err = p9pdu_readf(req->rc, clnt->proto_version, "d", &count); - if (err) { - trace_9p_protocol_dump(clnt, req->rc); - goto free_and_error; + p9_free_req(clnt, req); + iov_iter_advance(from, count); + total += count; + offset += count; } - - p9_debug(P9_DEBUG_9P, "<<< RWRITE count %d\n", count); - - p9_free_req(clnt, req); - return count; - -free_and_error: - p9_free_req(clnt, req); -error: - return err; + return total; } EXPORT_SYMBOL(p9_client_write); @@ -2068,6 +2048,10 @@ int p9_client_readdir(struct p9_fid *fid, char *data, u32 count, u64 offset) struct p9_client *clnt; struct p9_req_t *req; char *dataptr; + struct kvec kv = {.iov_base = data, .iov_len = count}; + struct iov_iter to; + + iov_iter_kvec(&to, READ | ITER_KVEC, &kv, 1, count); p9_debug(P9_DEBUG_9P, ">>> TREADDIR fid %d offset %llu count %d\n", fid->fid, (unsigned long long) offset, count); @@ -2088,8 +2072,8 @@ int p9_client_readdir(struct p9_fid *fid, char *data, u32 count, u64 offset) * response header len is 11 * PDU Header(7) + IO Size (4) */ - req = p9_client_zc_rpc(clnt, P9_TREADDIR, data, NULL, rsize, 0, - 11, 1, "dqd", fid->fid, offset, rsize); + req = p9_client_zc_rpc(clnt, P9_TREADDIR, &to, NULL, rsize, 0, + 11, "dqd", fid->fid, offset, rsize); } else { non_zc = 1; req = p9_client_rpc(clnt, P9_TREADDIR, "dqd", fid->fid, diff --git a/net/9p/protocol.c b/net/9p/protocol.c index ab9127ec5b7a..16d287565987 100644 --- a/net/9p/protocol.c +++ b/net/9p/protocol.c @@ -33,6 +33,7 @@ #include <linux/sched.h> #include <linux/stddef.h> #include <linux/types.h> +#include <linux/uio.h> #include <net/9p/9p.h> #include <net/9p/client.h> #include "protocol.h" @@ -69,10 +70,11 @@ static size_t pdu_write(struct p9_fcall *pdu, const void *data, size_t size) } static size_t -pdu_write_u(struct p9_fcall *pdu, const char __user *udata, size_t size) +pdu_write_u(struct p9_fcall *pdu, struct iov_iter *from, size_t size) { size_t len = min(pdu->capacity - pdu->size, size); - if (copy_from_user(&pdu->sdata[pdu->size], udata, len)) + struct iov_iter i = *from; + if (copy_from_iter(&pdu->sdata[pdu->size], len, &i) != len) len = 0; pdu->size += len; @@ -273,7 +275,7 @@ p9pdu_vreadf(struct p9_fcall *pdu, int proto_version, const char *fmt, } break; case 'R':{ - int16_t *nwqid = va_arg(ap, int16_t *); + uint16_t *nwqid = va_arg(ap, uint16_t *); struct p9_qid **wqids = va_arg(ap, struct p9_qid **); @@ -437,23 +439,13 @@ p9pdu_vwritef(struct p9_fcall *pdu, int proto_version, const char *fmt, stbuf->extension, stbuf->n_uid, stbuf->n_gid, stbuf->n_muid); } break; - case 'D':{ + case 'V':{ uint32_t count = va_arg(ap, uint32_t); - const void *data = va_arg(ap, const void *); - - errcode = p9pdu_writef(pdu, proto_version, "d", - count); - if (!errcode && pdu_write(pdu, data, count)) - errcode = -EFAULT; - } - break; - case 'U':{ - int32_t count = va_arg(ap, int32_t); - const char __user *udata = - va_arg(ap, const void __user *); + struct iov_iter *from = + va_arg(ap, struct iov_iter *); errcode = p9pdu_writef(pdu, proto_version, "d", count); - if (!errcode && pdu_write_u(pdu, udata, count)) + if (!errcode && pdu_write_u(pdu, from, count)) errcode = -EFAULT; } break; @@ -479,7 +471,7 @@ p9pdu_vwritef(struct p9_fcall *pdu, int proto_version, const char *fmt, } break; case 'R':{ - int16_t nwqid = va_arg(ap, int); + uint16_t nwqid = va_arg(ap, int); struct p9_qid *wqids = va_arg(ap, struct p9_qid *); diff --git a/net/9p/trans_common.c b/net/9p/trans_common.c index 2ee3879161b1..38aa6345bdfa 100644 --- a/net/9p/trans_common.c +++ b/net/9p/trans_common.c @@ -12,12 +12,8 @@ * */ -#include <linux/slab.h> +#include <linux/mm.h> #include <linux/module.h> -#include <net/9p/9p.h> -#include <net/9p/client.h> -#include <linux/scatterlist.h> -#include "trans_common.h" /** * p9_release_req_pages - Release pages after the transaction. @@ -31,39 +27,3 @@ void p9_release_pages(struct page **pages, int nr_pages) put_page(pages[i]); } EXPORT_SYMBOL(p9_release_pages); - -/** - * p9_nr_pages - Return number of pages needed to accommodate the payload. - */ -int p9_nr_pages(char *data, int len) -{ - unsigned long start_page, end_page; - start_page = (unsigned long)data >> PAGE_SHIFT; - end_page = ((unsigned long)data + len + PAGE_SIZE - 1) >> PAGE_SHIFT; - return end_page - start_page; -} -EXPORT_SYMBOL(p9_nr_pages); - -/** - * payload_gup - Translates user buffer into kernel pages and - * pins them either for read/write through get_user_pages_fast(). - * @req: Request to be sent to server. - * @pdata_off: data offset into the first page after translation (gup). - * @pdata_len: Total length of the IO. gup may not return requested # of pages. - * @nr_pages: number of pages to accommodate the payload - * @rw: Indicates if the pages are for read or write. - */ - -int p9_payload_gup(char *data, int *nr_pages, struct page **pages, int write) -{ - int nr_mapped_pages; - - nr_mapped_pages = get_user_pages_fast((unsigned long)data, - *nr_pages, write, pages); - if (nr_mapped_pages <= 0) - return nr_mapped_pages; - - *nr_pages = nr_mapped_pages; - return 0; -} -EXPORT_SYMBOL(p9_payload_gup); diff --git a/net/9p/trans_common.h b/net/9p/trans_common.h index 173bb550a9eb..c43babb3f635 100644 --- a/net/9p/trans_common.h +++ b/net/9p/trans_common.h @@ -13,5 +13,3 @@ */ void p9_release_pages(struct page **, int); -int p9_payload_gup(char *, int *, struct page **, int); -int p9_nr_pages(char *, int); diff --git a/net/9p/trans_fd.c b/net/9p/trans_fd.c index 80d08f6664cb..bced8c074c12 100644 --- a/net/9p/trans_fd.c +++ b/net/9p/trans_fd.c @@ -734,6 +734,7 @@ static int parse_opts(char *params, struct p9_fd_opts *opts) opts->port = P9_PORT; opts->rfd = ~0; opts->wfd = ~0; + opts->privport = 0; if (!params) return 0; @@ -940,7 +941,7 @@ p9_fd_create_tcp(struct p9_client *client, const char *addr, char *args) sin_server.sin_family = AF_INET; sin_server.sin_addr.s_addr = in_aton(addr); sin_server.sin_port = htons(opts.port); - err = __sock_create(read_pnet(¤t->nsproxy->net_ns), PF_INET, + err = __sock_create(current->nsproxy->net_ns, PF_INET, SOCK_STREAM, IPPROTO_TCP, &csocket, 1); if (err) { pr_err("%s (%d): problem creating socket\n", @@ -988,7 +989,7 @@ p9_fd_create_unix(struct p9_client *client, const char *addr, char *args) sun_server.sun_family = PF_UNIX; strcpy(sun_server.sun_path, addr); - err = __sock_create(read_pnet(¤t->nsproxy->net_ns), PF_UNIX, + err = __sock_create(current->nsproxy->net_ns, PF_UNIX, SOCK_STREAM, 0, &csocket, 1); if (err < 0) { pr_err("%s (%d): problem creating socket\n", @@ -1013,7 +1014,6 @@ p9_fd_create(struct p9_client *client, const char *addr, char *args) { int err; struct p9_fd_opts opts; - struct p9_trans_fd *p; parse_opts(args, &opts); @@ -1026,7 +1026,6 @@ p9_fd_create(struct p9_client *client, const char *addr, char *args) if (err < 0) return err; - p = (struct p9_trans_fd *) client->trans; p9_conn_create(client); return 0; diff --git a/net/9p/trans_rdma.c b/net/9p/trans_rdma.c index 14ad43b5cf89..3533d2a53ab6 100644 --- a/net/9p/trans_rdma.c +++ b/net/9p/trans_rdma.c @@ -139,6 +139,7 @@ struct p9_rdma_opts { int sq_depth; int rq_depth; long timeout; + int privport; }; /* @@ -146,7 +147,10 @@ struct p9_rdma_opts { */ enum { /* Options that take integer arguments */ - Opt_port, Opt_rq_depth, Opt_sq_depth, Opt_timeout, Opt_err, + Opt_port, Opt_rq_depth, Opt_sq_depth, Opt_timeout, + /* Options that take no argument */ + Opt_privport, + Opt_err, }; static match_table_t tokens = { @@ -154,6 +158,7 @@ static match_table_t tokens = { {Opt_sq_depth, "sq=%u"}, {Opt_rq_depth, "rq=%u"}, {Opt_timeout, "timeout=%u"}, + {Opt_privport, "privport"}, {Opt_err, NULL}, }; @@ -175,6 +180,7 @@ static int parse_opts(char *params, struct p9_rdma_opts *opts) opts->sq_depth = P9_RDMA_SQ_DEPTH; opts->rq_depth = P9_RDMA_RQ_DEPTH; opts->timeout = P9_RDMA_TIMEOUT; + opts->privport = 0; if (!params) return 0; @@ -193,13 +199,13 @@ static int parse_opts(char *params, struct p9_rdma_opts *opts) if (!*p) continue; token = match_token(p, tokens, args); - if (token == Opt_err) - continue; - r = match_int(&args[0], &option); - if (r < 0) { - p9_debug(P9_DEBUG_ERROR, - "integer field, but no integer?\n"); - continue; + if ((token != Opt_err) && (token != Opt_privport)) { + r = match_int(&args[0], &option); + if (r < 0) { + p9_debug(P9_DEBUG_ERROR, + "integer field, but no integer?\n"); + continue; + } } switch (token) { case Opt_port: @@ -214,6 +220,9 @@ static int parse_opts(char *params, struct p9_rdma_opts *opts) case Opt_timeout: opts->timeout = option; break; + case Opt_privport: + opts->privport = 1; + break; default: continue; } @@ -607,6 +616,23 @@ static int rdma_cancelled(struct p9_client *client, struct p9_req_t *req) return 0; } +static int p9_rdma_bind_privport(struct p9_trans_rdma *rdma) +{ + struct sockaddr_in cl = { + .sin_family = AF_INET, + .sin_addr.s_addr = htonl(INADDR_ANY), + }; + int port, err = -EINVAL; + + for (port = P9_DEF_MAX_RESVPORT; port >= P9_DEF_MIN_RESVPORT; port--) { + cl.sin_port = htons((ushort)port); + err = rdma_bind_addr(rdma->cm_id, (struct sockaddr *)&cl); + if (err != -EADDRINUSE) + break; + } + return err; +} + /** * trans_create_rdma - Transport method for creating atransport instance * @client: client instance @@ -642,6 +668,16 @@ rdma_create_trans(struct p9_client *client, const char *addr, char *args) /* Associate the client with the transport */ client->trans = rdma; + /* Bind to a privileged port if we need to */ + if (opts.privport) { + err = p9_rdma_bind_privport(rdma); + if (err < 0) { + pr_err("%s (%d): problem binding to privport: %d\n", + __func__, task_pid_nr(current), -err); + goto error; + } + } + /* Resolve the server's address */ rdma->addr.sin_family = AF_INET; rdma->addr.sin_addr.s_addr = in_aton(addr); diff --git a/net/9p/trans_virtio.c b/net/9p/trans_virtio.c index 36a1a739ad68..9dd49ca67dbc 100644 --- a/net/9p/trans_virtio.c +++ b/net/9p/trans_virtio.c @@ -217,15 +217,15 @@ static int p9_virtio_cancel(struct p9_client *client, struct p9_req_t *req) * @start: which segment of the sg_list to start at * @pdata: a list of pages to add into sg. * @nr_pages: number of pages to pack into the scatter/gather list - * @data: data to pack into scatter/gather list + * @offs: amount of data in the beginning of first page _not_ to pack * @count: amount of data to pack into the scatter/gather list */ static int pack_sg_list_p(struct scatterlist *sg, int start, int limit, - struct page **pdata, int nr_pages, char *data, int count) + struct page **pdata, int nr_pages, size_t offs, int count) { int i = 0, s; - int data_off; + int data_off = offs; int index = start; BUG_ON(nr_pages > (limit - start)); @@ -233,16 +233,14 @@ pack_sg_list_p(struct scatterlist *sg, int start, int limit, * if the first page doesn't start at * page boundary find the offset */ - data_off = offset_in_page(data); while (nr_pages) { - s = rest_of_page(data); + s = PAGE_SIZE - data_off; if (s > count) s = count; /* Make sure we don't terminate early. */ sg_unmark_end(&sg[index]); sg_set_page(&sg[index++], pdata[i++], s, data_off); data_off = 0; - data += s; count -= s; nr_pages--; } @@ -314,11 +312,20 @@ req_retry: } static int p9_get_mapped_pages(struct virtio_chan *chan, - struct page **pages, char *data, - int nr_pages, int write, int kern_buf) + struct page ***pages, + struct iov_iter *data, + int count, + size_t *offs, + int *need_drop) { + int nr_pages; int err; - if (!kern_buf) { + + if (!iov_iter_count(data)) + return 0; + + if (!(data->type & ITER_KVEC)) { + int n; /* * We allow only p9_max_pages pinned. We wait for the * Other zc request to finish here @@ -329,26 +336,49 @@ static int p9_get_mapped_pages(struct virtio_chan *chan, if (err == -ERESTARTSYS) return err; } - err = p9_payload_gup(data, &nr_pages, pages, write); - if (err < 0) - return err; + n = iov_iter_get_pages_alloc(data, pages, count, offs); + if (n < 0) + return n; + *need_drop = 1; + nr_pages = DIV_ROUND_UP(n + *offs, PAGE_SIZE); atomic_add(nr_pages, &vp_pinned); + return n; } else { /* kernel buffer, no need to pin pages */ - int s, index = 0; - int count = nr_pages; - while (nr_pages) { - s = rest_of_page(data); - if (is_vmalloc_addr(data)) - pages[index++] = vmalloc_to_page(data); + int index; + size_t len; + void *p; + + /* we'd already checked that it's non-empty */ + while (1) { + len = iov_iter_single_seg_count(data); + if (likely(len)) { + p = data->kvec->iov_base + data->iov_offset; + break; + } + iov_iter_advance(data, 0); + } + if (len > count) + len = count; + + nr_pages = DIV_ROUND_UP((unsigned long)p + len, PAGE_SIZE) - + (unsigned long)p / PAGE_SIZE; + + *pages = kmalloc(sizeof(struct page *) * nr_pages, GFP_NOFS); + if (!*pages) + return -ENOMEM; + + *need_drop = 0; + p -= (*offs = (unsigned long)p % PAGE_SIZE); + for (index = 0; index < nr_pages; index++) { + if (is_vmalloc_addr(p)) + (*pages)[index] = vmalloc_to_page(p); else - pages[index++] = kmap_to_page(data); - data += s; - nr_pages--; + (*pages)[index] = kmap_to_page(p); + p += PAGE_SIZE; } - nr_pages = count; + return len; } - return nr_pages; } /** @@ -364,8 +394,8 @@ static int p9_get_mapped_pages(struct virtio_chan *chan, */ static int p9_virtio_zc_request(struct p9_client *client, struct p9_req_t *req, - char *uidata, char *uodata, int inlen, - int outlen, int in_hdr_len, int kern_buf) + struct iov_iter *uidata, struct iov_iter *uodata, + int inlen, int outlen, int in_hdr_len) { int in, out, err, out_sgs, in_sgs; unsigned long flags; @@ -373,41 +403,32 @@ p9_virtio_zc_request(struct p9_client *client, struct p9_req_t *req, struct page **in_pages = NULL, **out_pages = NULL; struct virtio_chan *chan = client->trans; struct scatterlist *sgs[4]; + size_t offs; + int need_drop = 0; p9_debug(P9_DEBUG_TRANS, "virtio request\n"); if (uodata) { - out_nr_pages = p9_nr_pages(uodata, outlen); - out_pages = kmalloc(sizeof(struct page *) * out_nr_pages, - GFP_NOFS); - if (!out_pages) { - err = -ENOMEM; - goto err_out; + int n = p9_get_mapped_pages(chan, &out_pages, uodata, + outlen, &offs, &need_drop); + if (n < 0) + return n; + out_nr_pages = DIV_ROUND_UP(n + offs, PAGE_SIZE); + if (n != outlen) { + __le32 v = cpu_to_le32(n); + memcpy(&req->tc->sdata[req->tc->size - 4], &v, 4); + outlen = n; } - out_nr_pages = p9_get_mapped_pages(chan, out_pages, uodata, - out_nr_pages, 0, kern_buf); - if (out_nr_pages < 0) { - err = out_nr_pages; - kfree(out_pages); - out_pages = NULL; - goto err_out; - } - } - if (uidata) { - in_nr_pages = p9_nr_pages(uidata, inlen); - in_pages = kmalloc(sizeof(struct page *) * in_nr_pages, - GFP_NOFS); - if (!in_pages) { - err = -ENOMEM; - goto err_out; - } - in_nr_pages = p9_get_mapped_pages(chan, in_pages, uidata, - in_nr_pages, 1, kern_buf); - if (in_nr_pages < 0) { - err = in_nr_pages; - kfree(in_pages); - in_pages = NULL; - goto err_out; + } else if (uidata) { + int n = p9_get_mapped_pages(chan, &in_pages, uidata, + inlen, &offs, &need_drop); + if (n < 0) + return n; + in_nr_pages = DIV_ROUND_UP(n + offs, PAGE_SIZE); + if (n != inlen) { + __le32 v = cpu_to_le32(n); + memcpy(&req->tc->sdata[req->tc->size - 4], &v, 4); + inlen = n; } } req->status = REQ_STATUS_SENT; @@ -426,7 +447,7 @@ req_retry_pinned: if (out_pages) { sgs[out_sgs++] = chan->sg + out; out += pack_sg_list_p(chan->sg, out, VIRTQUEUE_NUM, - out_pages, out_nr_pages, uodata, outlen); + out_pages, out_nr_pages, offs, outlen); } /* @@ -444,7 +465,7 @@ req_retry_pinned: if (in_pages) { sgs[out_sgs + in_sgs++] = chan->sg + out + in; in += pack_sg_list_p(chan->sg, out + in, VIRTQUEUE_NUM, - in_pages, in_nr_pages, uidata, inlen); + in_pages, in_nr_pages, offs, inlen); } BUG_ON(out_sgs + in_sgs > ARRAY_SIZE(sgs)); @@ -478,7 +499,7 @@ req_retry_pinned: * Non kernel buffers are pinned, unpin them */ err_out: - if (!kern_buf) { + if (need_drop) { if (in_pages) { p9_release_pages(in_pages, in_nr_pages); atomic_sub(in_nr_pages, &vp_pinned); @@ -504,7 +525,10 @@ static ssize_t p9_mount_tag_show(struct device *dev, vdev = dev_to_virtio(dev); chan = vdev->priv; - return snprintf(buf, chan->tag_len + 1, "%s", chan->tag); + memcpy(buf, chan->tag, chan->tag_len); + buf[chan->tag_len] = 0; + + return chan->tag_len + 1; } static DEVICE_ATTR(mount_tag, 0444, p9_mount_tag_show, NULL); diff --git a/net/Makefile b/net/Makefile index 38704bdf941a..3995613e5510 100644 --- a/net/Makefile +++ b/net/Makefile @@ -69,7 +69,7 @@ obj-$(CONFIG_BATMAN_ADV) += batman-adv/ obj-$(CONFIG_NFC) += nfc/ obj-$(CONFIG_OPENVSWITCH) += openvswitch/ obj-$(CONFIG_VSOCKETS) += vmw_vsock/ -obj-$(CONFIG_NET_MPLS_GSO) += mpls/ +obj-$(CONFIG_MPLS) += mpls/ obj-$(CONFIG_HSR) += hsr/ ifneq ($(CONFIG_NET_SWITCHDEV),) obj-y += switchdev/ diff --git a/net/appletalk/aarp.c b/net/appletalk/aarp.c index d1c55d8dd0a2..8ad3ec2610b6 100644 --- a/net/appletalk/aarp.c +++ b/net/appletalk/aarp.c @@ -141,7 +141,7 @@ static void __aarp_send_query(struct aarp_entry *a) eah->pa_src_net = sat->s_net; eah->pa_src_node = sat->s_node; - memset(eah->hw_dst, '\0', ETH_ALEN); + eth_zero_addr(eah->hw_dst); eah->pa_dst_zero = 0; eah->pa_dst_net = a->target_addr.s_net; @@ -189,7 +189,7 @@ static void aarp_send_reply(struct net_device *dev, struct atalk_addr *us, eah->pa_src_node = us->s_node; if (!sha) - memset(eah->hw_dst, '\0', ETH_ALEN); + eth_zero_addr(eah->hw_dst); else ether_addr_copy(eah->hw_dst, sha); @@ -239,7 +239,7 @@ static void aarp_send_probe(struct net_device *dev, struct atalk_addr *us) eah->pa_src_net = us->s_net; eah->pa_src_node = us->s_node; - memset(eah->hw_dst, '\0', ETH_ALEN); + eth_zero_addr(eah->hw_dst); eah->pa_dst_zero = 0; eah->pa_dst_net = us->s_net; diff --git a/net/appletalk/ddp.c b/net/appletalk/ddp.c index 0d0766ea5ab1..3b7ad43c7dad 100644 --- a/net/appletalk/ddp.c +++ b/net/appletalk/ddp.c @@ -1559,8 +1559,7 @@ freeit: return 0; } -static int atalk_sendmsg(struct kiocb *iocb, struct socket *sock, struct msghdr *msg, - size_t len) +static int atalk_sendmsg(struct socket *sock, struct msghdr *msg, size_t len) { struct sock *sk = sock->sk; struct atalk_sock *at = at_sk(sk); @@ -1728,8 +1727,8 @@ out: return err ? : len; } -static int atalk_recvmsg(struct kiocb *iocb, struct socket *sock, struct msghdr *msg, - size_t size, int flags) +static int atalk_recvmsg(struct socket *sock, struct msghdr *msg, size_t size, + int flags) { struct sock *sk = sock->sk; struct ddpehdr *ddp; diff --git a/net/atm/common.c b/net/atm/common.c index b84057e41bd6..ed0466637e13 100644 --- a/net/atm/common.c +++ b/net/atm/common.c @@ -523,8 +523,8 @@ int vcc_connect(struct socket *sock, int itf, short vpi, int vci) return 0; } -int vcc_recvmsg(struct kiocb *iocb, struct socket *sock, struct msghdr *msg, - size_t size, int flags) +int vcc_recvmsg(struct socket *sock, struct msghdr *msg, size_t size, + int flags) { struct sock *sk = sock->sk; struct atm_vcc *vcc; @@ -569,8 +569,7 @@ int vcc_recvmsg(struct kiocb *iocb, struct socket *sock, struct msghdr *msg, return copied; } -int vcc_sendmsg(struct kiocb *iocb, struct socket *sock, struct msghdr *m, - size_t size) +int vcc_sendmsg(struct socket *sock, struct msghdr *m, size_t size) { struct sock *sk = sock->sk; DEFINE_WAIT(wait); diff --git a/net/atm/common.h b/net/atm/common.h index cc3c2dae4d79..4d6f5b2068ac 100644 --- a/net/atm/common.h +++ b/net/atm/common.h @@ -13,10 +13,9 @@ int vcc_create(struct net *net, struct socket *sock, int protocol, int family); int vcc_release(struct socket *sock); int vcc_connect(struct socket *sock, int itf, short vpi, int vci); -int vcc_recvmsg(struct kiocb *iocb, struct socket *sock, struct msghdr *msg, - size_t size, int flags); -int vcc_sendmsg(struct kiocb *iocb, struct socket *sock, struct msghdr *m, - size_t total_len); +int vcc_recvmsg(struct socket *sock, struct msghdr *msg, size_t size, + int flags); +int vcc_sendmsg(struct socket *sock, struct msghdr *m, size_t total_len); unsigned int vcc_poll(struct file *file, struct socket *sock, poll_table *wait); int vcc_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg); int vcc_compat_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg); diff --git a/net/atm/lec.c b/net/atm/lec.c index 4b98f897044a..cd3b37989057 100644 --- a/net/atm/lec.c +++ b/net/atm/lec.c @@ -2001,7 +2001,7 @@ lec_vcc_added(struct lec_priv *priv, const struct atmlec_ioc *ioc_data, if (entry == NULL) goto out; memcpy(entry->atm_addr, ioc_data->atm_addr, ATM_ESA_LEN); - memset(entry->mac_addr, 0, ETH_ALEN); + eth_zero_addr(entry->mac_addr); entry->recv_vcc = vcc; entry->old_recv_push = old_push; entry->status = ESI_UNKNOWN; @@ -2086,7 +2086,7 @@ lec_vcc_added(struct lec_priv *priv, const struct atmlec_ioc *ioc_data, entry->vcc = vcc; entry->old_push = old_push; memcpy(entry->atm_addr, ioc_data->atm_addr, ATM_ESA_LEN); - memset(entry->mac_addr, 0, ETH_ALEN); + eth_zero_addr(entry->mac_addr); entry->status = ESI_UNKNOWN; hlist_add_head(&entry->next, &priv->lec_arp_empty_ones); entry->timer.expires = jiffies + priv->vcc_timeout_period; diff --git a/net/atm/mpoa_proc.c b/net/atm/mpoa_proc.c index 5bdd300db0f7..2df34eb5d65f 100644 --- a/net/atm/mpoa_proc.c +++ b/net/atm/mpoa_proc.c @@ -272,7 +272,7 @@ static int parse_qos(const char *buff) qos.rxtp.max_pcr = rx_pcr; qos.rxtp.max_sdu = rx_sdu; qos.aal = ATM_AAL5; - dprintk("parse_qos(): setting qos paramameters to tx=%d,%d rx=%d,%d\n", + dprintk("parse_qos(): setting qos parameters to tx=%d,%d rx=%d,%d\n", qos.txtp.max_pcr, qos.txtp.max_sdu, qos.rxtp.max_pcr, qos.rxtp.max_sdu); diff --git a/net/atm/signaling.c b/net/atm/signaling.c index 523bce72f698..4fd6af47383a 100644 --- a/net/atm/signaling.c +++ b/net/atm/signaling.c @@ -19,36 +19,15 @@ #include "resources.h" #include "signaling.h" -#undef WAIT_FOR_DEMON /* #define this if system calls on SVC sockets - should block until the demon runs. - Danger: may cause nasty hangs if the demon - crashes. */ - struct atm_vcc *sigd = NULL; -#ifdef WAIT_FOR_DEMON -static DECLARE_WAIT_QUEUE_HEAD(sigd_sleep); -#endif static void sigd_put_skb(struct sk_buff *skb) { -#ifdef WAIT_FOR_DEMON - DECLARE_WAITQUEUE(wait, current); - - add_wait_queue(&sigd_sleep, &wait); - while (!sigd) { - set_current_state(TASK_UNINTERRUPTIBLE); - pr_debug("atmsvc: waiting for signaling daemon...\n"); - schedule(); - } - current->state = TASK_RUNNING; - remove_wait_queue(&sigd_sleep, &wait); -#else if (!sigd) { pr_debug("atmsvc: no signaling daemon\n"); kfree_skb(skb); return; } -#endif atm_force_charge(sigd, skb->truesize); skb_queue_tail(&sk_atm(sigd)->sk_receive_queue, skb); sk_atm(sigd)->sk_data_ready(sk_atm(sigd)); @@ -261,8 +240,5 @@ int sigd_attach(struct atm_vcc *vcc) vcc_insert_socket(sk_atm(vcc)); set_bit(ATM_VF_META, &vcc->flags); set_bit(ATM_VF_READY, &vcc->flags); -#ifdef WAIT_FOR_DEMON - wake_up(&sigd_sleep); -#endif return 0; } diff --git a/net/ax25/af_ax25.c b/net/ax25/af_ax25.c index ca049a7c9287..330c1f4a5a0b 100644 --- a/net/ax25/af_ax25.c +++ b/net/ax25/af_ax25.c @@ -1432,8 +1432,7 @@ out: return err; } -static int ax25_sendmsg(struct kiocb *iocb, struct socket *sock, - struct msghdr *msg, size_t len) +static int ax25_sendmsg(struct socket *sock, struct msghdr *msg, size_t len) { DECLARE_SOCKADDR(struct sockaddr_ax25 *, usax, msg->msg_name); struct sock *sk = sock->sk; @@ -1599,8 +1598,8 @@ out: return err; } -static int ax25_recvmsg(struct kiocb *iocb, struct socket *sock, - struct msghdr *msg, size_t size, int flags) +static int ax25_recvmsg(struct socket *sock, struct msghdr *msg, size_t size, + int flags) { struct sock *sk = sock->sk; struct sk_buff *skb; diff --git a/net/ax25/ax25_ip.c b/net/ax25/ax25_ip.c index 67de6b33f2c3..7c646bb2c6f7 100644 --- a/net/ax25/ax25_ip.c +++ b/net/ax25/ax25_ip.c @@ -46,9 +46,9 @@ #ifdef CONFIG_INET -int ax25_hard_header(struct sk_buff *skb, struct net_device *dev, - unsigned short type, const void *daddr, - const void *saddr, unsigned int len) +static int ax25_hard_header(struct sk_buff *skb, struct net_device *dev, + unsigned short type, const void *daddr, + const void *saddr, unsigned int len) { unsigned char *buff; @@ -100,7 +100,7 @@ int ax25_hard_header(struct sk_buff *skb, struct net_device *dev, return -AX25_HEADER_LEN; /* Unfinished header */ } -int ax25_rebuild_header(struct sk_buff *skb) +netdev_tx_t ax25_ip_xmit(struct sk_buff *skb) { struct sk_buff *ourskb; unsigned char *bp = skb->data; @@ -115,9 +115,6 @@ int ax25_rebuild_header(struct sk_buff *skb) dst = (ax25_address *)(bp + 1); src = (ax25_address *)(bp + 8); - if (arp_find(bp + 1, skb)) - return 1; - route = ax25_get_route(dst, NULL); if (route) { digipeat = route->digipeat; @@ -129,6 +126,7 @@ int ax25_rebuild_header(struct sk_buff *skb) dev = skb->dev; if ((ax25_dev = ax25_dev_ax25dev(dev)) == NULL) { + kfree_skb(skb); goto put; } @@ -212,31 +210,29 @@ put: if (route) ax25_put_route(route); - return 1; + return NETDEV_TX_OK; } #else /* INET */ -int ax25_hard_header(struct sk_buff *skb, struct net_device *dev, - unsigned short type, const void *daddr, - const void *saddr, unsigned int len) +static int ax25_hard_header(struct sk_buff *skb, struct net_device *dev, + unsigned short type, const void *daddr, + const void *saddr, unsigned int len) { return -AX25_HEADER_LEN; } -int ax25_rebuild_header(struct sk_buff *skb) +netdev_tx_t ax25_ip_xmit(struct sk_buff *skb) { - return 1; + kfree_skb(skb); + return NETDEV_TX_OK; } - #endif const struct header_ops ax25_header_ops = { .create = ax25_hard_header, - .rebuild = ax25_rebuild_header, }; -EXPORT_SYMBOL(ax25_hard_header); -EXPORT_SYMBOL(ax25_rebuild_header); EXPORT_SYMBOL(ax25_header_ops); +EXPORT_SYMBOL(ax25_ip_xmit); diff --git a/net/batman-adv/gateway_client.c b/net/batman-adv/gateway_client.c index 27649e85f3f6..090828cf1fa7 100644 --- a/net/batman-adv/gateway_client.c +++ b/net/batman-adv/gateway_client.c @@ -592,15 +592,16 @@ static int batadv_write_buffer_text(struct batadv_priv *bat_priv, curr_gw = batadv_gw_get_selected_gw_node(bat_priv); - ret = seq_printf(seq, "%s %pM (%3i) %pM [%10s]: %u.%u/%u.%u MBit\n", - (curr_gw == gw_node ? "=>" : " "), - gw_node->orig_node->orig, - router_ifinfo->bat_iv.tq_avg, router->addr, - router->if_incoming->net_dev->name, - gw_node->bandwidth_down / 10, - gw_node->bandwidth_down % 10, - gw_node->bandwidth_up / 10, - gw_node->bandwidth_up % 10); + seq_printf(seq, "%s %pM (%3i) %pM [%10s]: %u.%u/%u.%u MBit\n", + (curr_gw == gw_node ? "=>" : " "), + gw_node->orig_node->orig, + router_ifinfo->bat_iv.tq_avg, router->addr, + router->if_incoming->net_dev->name, + gw_node->bandwidth_down / 10, + gw_node->bandwidth_down % 10, + gw_node->bandwidth_up / 10, + gw_node->bandwidth_up % 10); + ret = seq_has_overflowed(seq) ? -1 : 0; if (curr_gw) batadv_gw_node_free_ref(curr_gw); diff --git a/net/batman-adv/hard-interface.c b/net/batman-adv/hard-interface.c index fbda6b54baff..baf1f9843f2c 100644 --- a/net/batman-adv/hard-interface.c +++ b/net/batman-adv/hard-interface.c @@ -83,11 +83,12 @@ static bool batadv_is_on_batman_iface(const struct net_device *net_dev) return true; /* no more parents..stop recursion */ - if (net_dev->iflink == 0 || net_dev->iflink == net_dev->ifindex) + if (dev_get_iflink(net_dev) == 0 || + dev_get_iflink(net_dev) == net_dev->ifindex) return false; /* recurse over the parent device */ - parent_dev = __dev_get_by_index(&init_net, net_dev->iflink); + parent_dev = __dev_get_by_index(&init_net, dev_get_iflink(net_dev)); /* if we got a NULL parent_dev there is something broken.. */ if (WARN(!parent_dev, "Cannot find parent device")) return false; diff --git a/net/bluetooth/Kconfig b/net/bluetooth/Kconfig index 7de74635a110..b8c794b87523 100644 --- a/net/bluetooth/Kconfig +++ b/net/bluetooth/Kconfig @@ -91,4 +91,12 @@ config BT_SELFTEST_SMP Run test cases for SMP cryptographic functionality, including both legacy SMP as well as the Secure Connections features. +config BT_DEBUGFS + bool "Export Bluetooth internals in debugfs" + depends on BT && DEBUG_FS + default y + help + Provide extensive information about internal Bluetooth states + in debugfs. + source "drivers/bluetooth/Kconfig" diff --git a/net/bluetooth/Makefile b/net/bluetooth/Makefile index 8e96e3072266..9a8ea232d28f 100644 --- a/net/bluetooth/Makefile +++ b/net/bluetooth/Makefile @@ -13,8 +13,9 @@ 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 ecc.o hci_request.o hci_debugfs.o + a2mp.o amp.o ecc.o hci_request.o mgmt_util.o +bluetooth-$(CONFIG_BT_DEBUGFS) += hci_debugfs.o bluetooth-$(CONFIG_BT_SELFTEST) += selftest.o subdir-ccflags-y += -D__CHECK_ENDIAN__ diff --git a/net/bluetooth/a2mp.c b/net/bluetooth/a2mp.c index cedfbda15dad..5a04eb1a7e57 100644 --- a/net/bluetooth/a2mp.c +++ b/net/bluetooth/a2mp.c @@ -19,9 +19,11 @@ #include "a2mp.h" #include "amp.h" +#define A2MP_FEAT_EXT 0x8000 + /* Global AMP Manager list */ -LIST_HEAD(amp_mgr_list); -DEFINE_MUTEX(amp_mgr_list_lock); +static LIST_HEAD(amp_mgr_list); +static DEFINE_MUTEX(amp_mgr_list_lock); /* A2MP build & send command helper functions */ static struct a2mp_cmd *__a2mp_build(u8 code, u8 ident, u16 len, void *data) @@ -43,7 +45,7 @@ static struct a2mp_cmd *__a2mp_build(u8 code, u8 ident, u16 len, void *data) return cmd; } -void a2mp_send(struct amp_mgr *mgr, u8 code, u8 ident, u16 len, void *data) +static void a2mp_send(struct amp_mgr *mgr, u8 code, u8 ident, u16 len, void *data) { struct l2cap_chan *chan = mgr->a2mp_chan; struct a2mp_cmd *cmd; @@ -67,7 +69,7 @@ void a2mp_send(struct amp_mgr *mgr, u8 code, u8 ident, u16 len, void *data) kfree(cmd); } -u8 __next_ident(struct amp_mgr *mgr) +static u8 __next_ident(struct amp_mgr *mgr) { if (++mgr->ident == 0) mgr->ident = 1; @@ -75,6 +77,23 @@ u8 __next_ident(struct amp_mgr *mgr) return mgr->ident; } +static struct amp_mgr *amp_mgr_lookup_by_state(u8 state) +{ + struct amp_mgr *mgr; + + mutex_lock(&_mgr_list_lock); + list_for_each_entry(mgr, &_mgr_list, list) { + if (test_and_clear_bit(state, &mgr->state)) { + amp_mgr_get(mgr); + mutex_unlock(&_mgr_list_lock); + return mgr; + } + } + mutex_unlock(&_mgr_list_lock); + + return NULL; +} + /* hci_dev_list shall be locked */ static void __a2mp_add_cl(struct amp_mgr *mgr, struct a2mp_cl *cl) { @@ -860,23 +879,6 @@ struct l2cap_chan *a2mp_channel_create(struct l2cap_conn *conn, return mgr->a2mp_chan; } -struct amp_mgr *amp_mgr_lookup_by_state(u8 state) -{ - struct amp_mgr *mgr; - - mutex_lock(&_mgr_list_lock); - list_for_each_entry(mgr, &_mgr_list, list) { - if (test_and_clear_bit(state, &mgr->state)) { - amp_mgr_get(mgr); - mutex_unlock(&_mgr_list_lock); - return mgr; - } - } - mutex_unlock(&_mgr_list_lock); - - return NULL; -} - void a2mp_send_getinfo_rsp(struct hci_dev *hdev) { struct amp_mgr *mgr; diff --git a/net/bluetooth/a2mp.h b/net/bluetooth/a2mp.h index 487b54c1308f..296f665adb09 100644 --- a/net/bluetooth/a2mp.h +++ b/net/bluetooth/a2mp.h @@ -17,8 +17,6 @@ #include <net/bluetooth/l2cap.h> -#define A2MP_FEAT_EXT 0x8000 - enum amp_mgr_state { READ_LOC_AMP_INFO, READ_LOC_AMP_ASSOC, @@ -131,16 +129,10 @@ struct a2mp_physlink_rsp { #define A2MP_STATUS_PHYS_LINK_EXISTS 0x05 #define A2MP_STATUS_SECURITY_VIOLATION 0x06 -extern struct list_head amp_mgr_list; -extern struct mutex amp_mgr_list_lock; - struct amp_mgr *amp_mgr_get(struct amp_mgr *mgr); int amp_mgr_put(struct amp_mgr *mgr); -u8 __next_ident(struct amp_mgr *mgr); struct l2cap_chan *a2mp_channel_create(struct l2cap_conn *conn, struct sk_buff *skb); -struct amp_mgr *amp_mgr_lookup_by_state(u8 state); -void a2mp_send(struct amp_mgr *mgr, u8 code, u8 ident, u16 len, void *data); void a2mp_discover_amp(struct l2cap_chan *chan); void a2mp_send_getinfo_rsp(struct hci_dev *hdev); void a2mp_send_getampassoc_rsp(struct hci_dev *hdev, u8 status); diff --git a/net/bluetooth/af_bluetooth.c b/net/bluetooth/af_bluetooth.c index ce22e0cfa923..70f9d945faf7 100644 --- a/net/bluetooth/af_bluetooth.c +++ b/net/bluetooth/af_bluetooth.c @@ -210,8 +210,8 @@ struct sock *bt_accept_dequeue(struct sock *parent, struct socket *newsock) } EXPORT_SYMBOL(bt_accept_dequeue); -int bt_sock_recvmsg(struct kiocb *iocb, struct socket *sock, - struct msghdr *msg, size_t len, int flags) +int bt_sock_recvmsg(struct socket *sock, struct msghdr *msg, size_t len, + int flags) { int noblock = flags & MSG_DONTWAIT; struct sock *sk = sock->sk; @@ -283,8 +283,8 @@ static long bt_sock_data_wait(struct sock *sk, long timeo) return timeo; } -int bt_sock_stream_recvmsg(struct kiocb *iocb, struct socket *sock, - struct msghdr *msg, size_t size, int flags) +int bt_sock_stream_recvmsg(struct socket *sock, struct msghdr *msg, + size_t size, int flags) { struct sock *sk = sock->sk; int err = 0; @@ -711,10 +711,9 @@ EXPORT_SYMBOL_GPL(bt_debugfs); static int __init bt_init(void) { - struct sk_buff *skb; int err; - BUILD_BUG_ON(sizeof(struct bt_skb_cb) > sizeof(skb->cb)); + sock_skb_cb_check_size(sizeof(struct bt_skb_cb)); BT_INFO("Core ver %s", VERSION); @@ -750,6 +749,13 @@ static int __init bt_init(void) goto sock_err; } + err = mgmt_init(); + if (err < 0) { + sco_exit(); + l2cap_exit(); + goto sock_err; + } + return 0; sock_err: @@ -764,6 +770,8 @@ error: static void __exit bt_exit(void) { + mgmt_exit(); + sco_exit(); l2cap_exit(); diff --git a/net/bluetooth/bnep/bnep.h b/net/bluetooth/bnep/bnep.h index 5a5b16f365e9..40854c99bc1e 100644 --- a/net/bluetooth/bnep/bnep.h +++ b/net/bluetooth/bnep/bnep.h @@ -111,6 +111,10 @@ struct bnep_ext_hdr { #define BNEPCONNDEL _IOW('B', 201, int) #define BNEPGETCONNLIST _IOR('B', 210, int) #define BNEPGETCONNINFO _IOR('B', 211, int) +#define BNEPGETSUPPFEAT _IOR('B', 212, int) + +#define BNEP_SETUP_RESPONSE 0 +#define BNEP_SETUP_RSP_SENT 10 struct bnep_connadd_req { int sock; /* Connected socket */ diff --git a/net/bluetooth/bnep/core.c b/net/bluetooth/bnep/core.c index 05f57e491ccb..1641367e54ca 100644 --- a/net/bluetooth/bnep/core.c +++ b/net/bluetooth/bnep/core.c @@ -231,7 +231,14 @@ static int bnep_rx_control(struct bnep_session *s, void *data, int len) break; case BNEP_SETUP_CONN_REQ: - err = bnep_send_rsp(s, BNEP_SETUP_CONN_RSP, BNEP_CONN_NOT_ALLOWED); + /* Successful response should be sent only once */ + if (test_bit(BNEP_SETUP_RESPONSE, &s->flags) && + !test_and_set_bit(BNEP_SETUP_RSP_SENT, &s->flags)) + err = bnep_send_rsp(s, BNEP_SETUP_CONN_RSP, + BNEP_SUCCESS); + else + err = bnep_send_rsp(s, BNEP_SETUP_CONN_RSP, + BNEP_CONN_NOT_ALLOWED); break; default: { @@ -239,7 +246,7 @@ static int bnep_rx_control(struct bnep_session *s, void *data, int len) pkt[0] = BNEP_CONTROL; pkt[1] = BNEP_CMD_NOT_UNDERSTOOD; pkt[2] = cmd; - bnep_send(s, pkt, sizeof(pkt)); + err = bnep_send(s, pkt, sizeof(pkt)); } break; } @@ -292,29 +299,55 @@ static int bnep_rx_frame(struct bnep_session *s, struct sk_buff *skb) { struct net_device *dev = s->dev; struct sk_buff *nskb; - u8 type; + u8 type, ctrl_type; dev->stats.rx_bytes += skb->len; type = *(u8 *) skb->data; skb_pull(skb, 1); + ctrl_type = *(u8 *)skb->data; if ((type & BNEP_TYPE_MASK) >= sizeof(__bnep_rx_hlen)) goto badframe; if ((type & BNEP_TYPE_MASK) == BNEP_CONTROL) { - bnep_rx_control(s, skb->data, skb->len); - kfree_skb(skb); - return 0; - } + if (bnep_rx_control(s, skb->data, skb->len) < 0) { + dev->stats.tx_errors++; + kfree_skb(skb); + return 0; + } - skb_reset_mac_header(skb); + if (!(type & BNEP_EXT_HEADER)) { + kfree_skb(skb); + return 0; + } - /* Verify and pull out header */ - if (!skb_pull(skb, __bnep_rx_hlen[type & BNEP_TYPE_MASK])) - goto badframe; + /* Verify and pull ctrl message since it's already processed */ + switch (ctrl_type) { + case BNEP_SETUP_CONN_REQ: + /* Pull: ctrl type (1 b), len (1 b), data (len bytes) */ + if (!skb_pull(skb, 2 + *(u8 *)(skb->data + 1) * 2)) + goto badframe; + break; + case BNEP_FILTER_MULTI_ADDR_SET: + case BNEP_FILTER_NET_TYPE_SET: + /* Pull: ctrl type (1 b), len (2 b), data (len bytes) */ + if (!skb_pull(skb, 3 + *(u16 *)(skb->data + 1) * 2)) + goto badframe; + break; + default: + kfree_skb(skb); + return 0; + } + } else { + skb_reset_mac_header(skb); - s->eh.h_proto = get_unaligned((__be16 *) (skb->data - 2)); + /* Verify and pull out header */ + if (!skb_pull(skb, __bnep_rx_hlen[type & BNEP_TYPE_MASK])) + goto badframe; + + s->eh.h_proto = get_unaligned((__be16 *) (skb->data - 2)); + } if (type & BNEP_EXT_HEADER) { if (bnep_rx_extension(s, skb) < 0) @@ -525,6 +558,7 @@ static struct device_type bnep_type = { int bnep_add_connection(struct bnep_connadd_req *req, struct socket *sock) { + u32 valid_flags = BIT(BNEP_SETUP_RESPONSE); struct net_device *dev; struct bnep_session *s, *ss; u8 dst[ETH_ALEN], src[ETH_ALEN]; @@ -535,6 +569,9 @@ int bnep_add_connection(struct bnep_connadd_req *req, struct socket *sock) if (!l2cap_is_socket(sock)) return -EBADFD; + if (req->flags & ~valid_flags) + return -EINVAL; + baswap((void *) dst, &l2cap_pi(sock->sk)->chan->dst); baswap((void *) src, &l2cap_pi(sock->sk)->chan->src); @@ -566,6 +603,7 @@ int bnep_add_connection(struct bnep_connadd_req *req, struct socket *sock) s->sock = sock; s->role = req->role; s->state = BT_CONNECTED; + s->flags = req->flags; s->msg.msg_flags = MSG_NOSIGNAL; @@ -611,11 +649,15 @@ failed: int bnep_del_connection(struct bnep_conndel_req *req) { + u32 valid_flags = 0; struct bnep_session *s; int err = 0; BT_DBG(""); + if (req->flags & ~valid_flags) + return -EINVAL; + down_read(&bnep_session_sem); s = __bnep_get_session(req->dst); @@ -631,10 +673,12 @@ int bnep_del_connection(struct bnep_conndel_req *req) static void __bnep_copy_ci(struct bnep_conninfo *ci, struct bnep_session *s) { + u32 valid_flags = BIT(BNEP_SETUP_RESPONSE); + memset(ci, 0, sizeof(*ci)); memcpy(ci->dst, s->eh.h_source, ETH_ALEN); strcpy(ci->device, s->dev->name); - ci->flags = s->flags; + ci->flags = s->flags & valid_flags; ci->state = s->state; ci->role = s->role; } diff --git a/net/bluetooth/bnep/netdev.c b/net/bluetooth/bnep/netdev.c index 4b488ec26105..6ceb5d36a32b 100644 --- a/net/bluetooth/bnep/netdev.c +++ b/net/bluetooth/bnep/netdev.c @@ -218,7 +218,7 @@ static const struct net_device_ops bnep_netdev_ops = { void bnep_net_setup(struct net_device *dev) { - memset(dev->broadcast, 0xff, ETH_ALEN); + eth_broadcast_addr(dev->broadcast); dev->addr_len = ETH_ALEN; ether_setup(dev); diff --git a/net/bluetooth/bnep/sock.c b/net/bluetooth/bnep/sock.c index 5f051290daba..bde2bdd9e929 100644 --- a/net/bluetooth/bnep/sock.c +++ b/net/bluetooth/bnep/sock.c @@ -57,6 +57,7 @@ static int bnep_sock_ioctl(struct socket *sock, unsigned int cmd, unsigned long struct bnep_conninfo ci; struct socket *nsock; void __user *argp = (void __user *)arg; + __u32 supp_feat = BIT(BNEP_SETUP_RESPONSE); int err; BT_DBG("cmd %x arg %lx", cmd, arg); @@ -120,6 +121,12 @@ static int bnep_sock_ioctl(struct socket *sock, unsigned int cmd, unsigned long return err; + case BNEPGETSUPPFEAT: + if (copy_to_user(argp, &supp_feat, sizeof(supp_feat))) + return -EFAULT; + + return 0; + default: return -EINVAL; } diff --git a/net/bluetooth/cmtp/capi.c b/net/bluetooth/cmtp/capi.c index 75bd2c42e3e7..b0c6c6af76ef 100644 --- a/net/bluetooth/cmtp/capi.c +++ b/net/bluetooth/cmtp/capi.c @@ -333,7 +333,7 @@ void cmtp_recv_capimsg(struct cmtp_session *session, struct sk_buff *skb) return; } - if (session->flags & (1 << CMTP_LOOPBACK)) { + if (session->flags & BIT(CMTP_LOOPBACK)) { kfree_skb(skb); return; } diff --git a/net/bluetooth/cmtp/core.c b/net/bluetooth/cmtp/core.c index 278a194e6af4..298ed37010e6 100644 --- a/net/bluetooth/cmtp/core.c +++ b/net/bluetooth/cmtp/core.c @@ -75,10 +75,11 @@ static void __cmtp_unlink_session(struct cmtp_session *session) static void __cmtp_copy_session(struct cmtp_session *session, struct cmtp_conninfo *ci) { + u32 valid_flags = BIT(CMTP_LOOPBACK); memset(ci, 0, sizeof(*ci)); bacpy(&ci->bdaddr, &session->bdaddr); - ci->flags = session->flags; + ci->flags = session->flags & valid_flags; ci->state = session->state; ci->num = session->num; @@ -313,7 +314,7 @@ static int cmtp_session(void *arg) down_write(&cmtp_session_sem); - if (!(session->flags & (1 << CMTP_LOOPBACK))) + if (!(session->flags & BIT(CMTP_LOOPBACK))) cmtp_detach_device(session); fput(session->sock->file); @@ -329,6 +330,7 @@ static int cmtp_session(void *arg) int cmtp_add_connection(struct cmtp_connadd_req *req, struct socket *sock) { + u32 valid_flags = BIT(CMTP_LOOPBACK); struct cmtp_session *session, *s; int i, err; @@ -337,6 +339,9 @@ int cmtp_add_connection(struct cmtp_connadd_req *req, struct socket *sock) if (!l2cap_is_socket(sock)) return -EBADFD; + if (req->flags & ~valid_flags) + return -EINVAL; + session = kzalloc(sizeof(struct cmtp_session), GFP_KERNEL); if (!session) return -ENOMEM; @@ -385,7 +390,7 @@ int cmtp_add_connection(struct cmtp_connadd_req *req, struct socket *sock) goto unlink; } - if (!(session->flags & (1 << CMTP_LOOPBACK))) { + if (!(session->flags & BIT(CMTP_LOOPBACK))) { err = cmtp_attach_device(session); if (err < 0) { atomic_inc(&session->terminate); @@ -409,11 +414,15 @@ failed: int cmtp_del_connection(struct cmtp_conndel_req *req) { + u32 valid_flags = 0; struct cmtp_session *session; int err = 0; BT_DBG(""); + if (req->flags & ~valid_flags) + return -EINVAL; + down_read(&cmtp_session_sem); session = __cmtp_get_session(&req->bdaddr); diff --git a/net/bluetooth/hci_conn.c b/net/bluetooth/hci_conn.c index c9b8fa544785..ee5e59839b02 100644 --- a/net/bluetooth/hci_conn.c +++ b/net/bluetooth/hci_conn.c @@ -309,7 +309,7 @@ void hci_sco_setup(struct hci_conn *conn, __u8 status) else hci_add_sco(sco, conn->handle); } else { - hci_proto_connect_cfm(sco, status); + hci_connect_cfm(sco, status); hci_conn_del(sco); } } @@ -571,7 +571,7 @@ 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_USER_CHANNEL, &d->dev_flags) || + hci_dev_test_flag(d, HCI_USER_CHANNEL) || d->dev_type != HCI_BREDR) continue; @@ -618,7 +618,7 @@ void hci_le_conn_failed(struct hci_conn *conn, u8 status) mgmt_connect_failed(hdev, &conn->dst, conn->type, conn->dst_type, status); - hci_proto_connect_cfm(conn, status); + hci_connect_cfm(conn, status); hci_conn_del(conn); @@ -700,7 +700,7 @@ static void hci_req_directed_advertising(struct hci_request *req, * 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_LE_ADV, &hdev->dev_flags); + hci_dev_clear_flag(hdev, HCI_LE_ADV); /* Set require_privacy to false so that the remote device has a * chance of identifying us. @@ -733,6 +733,14 @@ struct hci_conn *hci_connect_le(struct hci_dev *hdev, bdaddr_t *dst, struct hci_request req; int err; + /* Let's make sure that le is enabled.*/ + if (!hci_dev_test_flag(hdev, HCI_LE_ENABLED)) { + if (lmp_le_capable(hdev)) + return ERR_PTR(-ECONNREFUSED); + + return ERR_PTR(-EOPNOTSUPP); + } + /* Some devices send ATT messages as soon as the physical link is * established. To be able to handle these ATT messages, the user- * space first establishes the connection and then starts the pairing @@ -791,7 +799,7 @@ struct hci_conn *hci_connect_le(struct hci_dev *hdev, bdaddr_t *dst, * anyway have to disable it in order to start directed * advertising. */ - if (test_bit(HCI_LE_ADV, &hdev->dev_flags)) { + if (hci_dev_test_flag(hdev, HCI_LE_ADV)) { u8 enable = 0x00; hci_req_add(&req, HCI_OP_LE_SET_ADV_ENABLE, sizeof(enable), &enable); @@ -802,7 +810,7 @@ struct hci_conn *hci_connect_le(struct hci_dev *hdev, bdaddr_t *dst, /* 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) && + if (hci_dev_test_flag(hdev, HCI_LE_SCAN) && hdev->le_scan_type == LE_SCAN_ACTIVE) { skb_queue_purge(&req.cmd_q); hci_conn_del(conn); @@ -832,9 +840,9 @@ struct hci_conn *hci_connect_le(struct hci_dev *hdev, bdaddr_t *dst, * handler for scan disabling knows to set the correct discovery * state. */ - if (test_bit(HCI_LE_SCAN, &hdev->dev_flags)) { + if (hci_dev_test_flag(hdev, HCI_LE_SCAN)) { hci_req_add_le_scan_disable(&req); - set_bit(HCI_LE_SCAN_INTERRUPTED, &hdev->dev_flags); + hci_dev_set_flag(hdev, HCI_LE_SCAN_INTERRUPTED); } hci_req_add_le_create_conn(&req, conn); @@ -856,8 +864,12 @@ 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)) + if (!hci_dev_test_flag(hdev, HCI_BREDR_ENABLED)) { + if (lmp_bredr_capable(hdev)) + return ERR_PTR(-ECONNREFUSED); + return ERR_PTR(-EOPNOTSUPP); + } acl = hci_conn_hash_lookup_ba(hdev, ACL_LINK, dst); if (!acl) { @@ -930,7 +942,7 @@ int hci_conn_check_link_mode(struct hci_conn *conn) * Connections is used and the link is encrypted with AES-CCM * using a P-256 authenticated combination key. */ - if (test_bit(HCI_SC_ONLY, &conn->hdev->flags)) { + if (hci_dev_test_flag(conn->hdev, HCI_SC_ONLY)) { if (!hci_conn_sc_enabled(conn) || !test_bit(HCI_CONN_AES_CCM, &conn->flags) || conn->key_type != HCI_LK_AUTH_COMBINATION_P256) @@ -1139,7 +1151,7 @@ void hci_conn_hash_flush(struct hci_dev *hdev) list_for_each_entry_safe(c, n, &h->list, list) { c->state = BT_CLOSED; - hci_proto_disconn_cfm(c, HCI_ERROR_LOCAL_HOST_TERM); + hci_disconn_cfm(c, HCI_ERROR_LOCAL_HOST_TERM); hci_conn_del(c); } } diff --git a/net/bluetooth/hci_core.c b/net/bluetooth/hci_core.c index 3322d3f4c85a..476709bd068a 100644 --- a/net/bluetooth/hci_core.c +++ b/net/bluetooth/hci_core.c @@ -51,7 +51,7 @@ DEFINE_RWLOCK(hci_dev_list_lock); /* HCI callback list */ LIST_HEAD(hci_cb_list); -DEFINE_RWLOCK(hci_cb_list_lock); +DEFINE_MUTEX(hci_cb_list_lock); /* HCI ID Numbering */ static DEFINE_IDA(hci_index_ida); @@ -80,7 +80,7 @@ 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->dbg_flags) ? 'Y': 'N'; + buf[0] = hci_dev_test_flag(hdev, HCI_DUT_MODE) ? 'Y': 'N'; buf[1] = '\n'; buf[2] = '\0'; return simple_read_from_buffer(user_buf, count, ppos, buf, 2); @@ -106,7 +106,7 @@ 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->dbg_flags)) + if (enable == hci_dev_test_flag(hdev, HCI_DUT_MODE)) return -EALREADY; hci_req_lock(hdev); @@ -127,7 +127,7 @@ 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->dbg_flags); + hci_dev_change_flag(hdev, HCI_DUT_MODE); return count; } @@ -141,13 +141,16 @@ static const struct file_operations dut_mode_fops = { /* ---- HCI requests ---- */ -static void hci_req_sync_complete(struct hci_dev *hdev, u8 result, u16 opcode) +static void hci_req_sync_complete(struct hci_dev *hdev, u8 result, u16 opcode, + struct sk_buff *skb) { BT_DBG("%s result 0x%2.2x", hdev->name, result); if (hdev->req_status == HCI_REQ_PEND) { hdev->req_result = result; hdev->req_status = HCI_REQ_DONE; + if (skb) + hdev->req_skb = skb_get(skb); wake_up_interruptible(&hdev->req_wait_q); } } @@ -163,66 +166,12 @@ static void hci_req_cancel(struct hci_dev *hdev, int err) } } -static struct sk_buff *hci_get_cmd_complete(struct hci_dev *hdev, u16 opcode, - u8 event) -{ - struct hci_ev_cmd_complete *ev; - struct hci_event_hdr *hdr; - struct sk_buff *skb; - - hci_dev_lock(hdev); - - skb = hdev->recv_evt; - hdev->recv_evt = NULL; - - hci_dev_unlock(hdev); - - if (!skb) - return ERR_PTR(-ENODATA); - - if (skb->len < sizeof(*hdr)) { - BT_ERR("Too short HCI event"); - goto failed; - } - - hdr = (void *) skb->data; - skb_pull(skb, HCI_EVENT_HDR_SIZE); - - if (event) { - if (hdr->evt != event) - goto failed; - return skb; - } - - if (hdr->evt != HCI_EV_CMD_COMPLETE) { - BT_DBG("Last event is not cmd complete (0x%2.2x)", hdr->evt); - goto failed; - } - - if (skb->len < sizeof(*ev)) { - BT_ERR("Too short cmd_complete event"); - goto failed; - } - - ev = (void *) skb->data; - skb_pull(skb, sizeof(*ev)); - - if (opcode == __le16_to_cpu(ev->opcode)) - return skb; - - BT_DBG("opcode doesn't match (0x%2.2x != 0x%2.2x)", opcode, - __le16_to_cpu(ev->opcode)); - -failed: - kfree_skb(skb); - return ERR_PTR(-ENODATA); -} - struct sk_buff *__hci_cmd_sync_ev(struct hci_dev *hdev, u16 opcode, u32 plen, const void *param, u8 event, u32 timeout) { DECLARE_WAITQUEUE(wait, current); struct hci_request req; + struct sk_buff *skb; int err = 0; BT_DBG("%s", hdev->name); @@ -236,7 +185,7 @@ struct sk_buff *__hci_cmd_sync_ev(struct hci_dev *hdev, u16 opcode, u32 plen, add_wait_queue(&hdev->req_wait_q, &wait); set_current_state(TASK_INTERRUPTIBLE); - err = hci_req_run(&req, hci_req_sync_complete); + err = hci_req_run_skb(&req, hci_req_sync_complete); if (err < 0) { remove_wait_queue(&hdev->req_wait_q, &wait); set_current_state(TASK_RUNNING); @@ -265,13 +214,20 @@ struct sk_buff *__hci_cmd_sync_ev(struct hci_dev *hdev, u16 opcode, u32 plen, } hdev->req_status = hdev->req_result = 0; + skb = hdev->req_skb; + hdev->req_skb = NULL; BT_DBG("%s end: err %d", hdev->name, err); - if (err < 0) + if (err < 0) { + kfree_skb(skb); return ERR_PTR(err); + } + + if (!skb) + return ERR_PTR(-ENODATA); - return hci_get_cmd_complete(hdev, opcode, event); + return skb; } EXPORT_SYMBOL(__hci_cmd_sync_ev); @@ -303,7 +259,7 @@ static int __hci_req_sync(struct hci_dev *hdev, add_wait_queue(&hdev->req_wait_q, &wait); set_current_state(TASK_INTERRUPTIBLE); - err = hci_req_run(&req, hci_req_sync_complete); + err = hci_req_run_skb(&req, hci_req_sync_complete); if (err < 0) { hdev->req_status = 0; @@ -390,7 +346,7 @@ static void bredr_init(struct hci_request *req) hci_req_add(req, HCI_OP_READ_BD_ADDR, 0, NULL); } -static void amp_init(struct hci_request *req) +static void amp_init1(struct hci_request *req) { req->hdev->flow_ctl_mode = HCI_FLOW_CTL_MODE_BLOCK_BASED; @@ -400,9 +356,6 @@ static void amp_init(struct hci_request *req) /* Read Local Supported Commands */ hci_req_add(req, HCI_OP_READ_LOCAL_COMMANDS, 0, NULL); - /* Read Local Supported Features */ - hci_req_add(req, HCI_OP_READ_LOCAL_FEATURES, 0, NULL); - /* Read Local AMP Info */ hci_req_add(req, HCI_OP_READ_LOCAL_AMP_INFO, 0, NULL); @@ -416,6 +369,16 @@ static void amp_init(struct hci_request *req) hci_req_add(req, HCI_OP_READ_LOCATION_DATA, 0, NULL); } +static void amp_init2(struct hci_request *req) +{ + /* Read Local Supported Features. Not all AMP controllers + * support this so it's placed conditionally in the second + * stage init. + */ + if (req->hdev->commands[14] & 0x20) + hci_req_add(req, HCI_OP_READ_LOCAL_FEATURES, 0, NULL); +} + static void hci_init1_req(struct hci_request *req, unsigned long opt) { struct hci_dev *hdev = req->hdev; @@ -432,7 +395,7 @@ static void hci_init1_req(struct hci_request *req, unsigned long opt) break; case HCI_AMP: - amp_init(req); + amp_init1(req); break; default: @@ -494,7 +457,7 @@ static void le_setup(struct hci_request *req) /* LE-only controllers have LE implicitly enabled */ if (!lmp_bredr_capable(hdev)) - set_bit(HCI_LE_ENABLED, &hdev->dev_flags); + hci_dev_set_flag(hdev, HCI_LE_ENABLED); } static void hci_setup_event_mask(struct hci_request *req) @@ -578,10 +541,13 @@ static void hci_init2_req(struct hci_request *req, unsigned long opt) { struct hci_dev *hdev = req->hdev; + if (hdev->dev_type == HCI_AMP) + return amp_init2(req); + if (lmp_bredr_capable(hdev)) bredr_setup(req); else - clear_bit(HCI_BREDR_ENABLED, &hdev->dev_flags); + hci_dev_clear_flag(hdev, HCI_BREDR_ENABLED); if (lmp_le_capable(hdev)) le_setup(req); @@ -607,7 +573,7 @@ static void hci_init2_req(struct hci_request *req, unsigned long opt) */ hdev->max_page = 0x01; - if (test_bit(HCI_SSP_ENABLED, &hdev->dev_flags)) { + if (hci_dev_test_flag(hdev, HCI_SSP_ENABLED)) { u8 mode = 0x01; hci_req_add(req, HCI_OP_WRITE_SSP_MODE, @@ -646,7 +612,7 @@ static void hci_init2_req(struct hci_request *req, unsigned long opt) sizeof(cp), &cp); } - if (test_bit(HCI_LINK_SECURITY, &hdev->dev_flags)) { + if (hci_dev_test_flag(hdev, HCI_LINK_SECURITY)) { u8 enable = 1; hci_req_add(req, HCI_OP_WRITE_AUTH_ENABLE, sizeof(enable), &enable); @@ -683,7 +649,7 @@ static void hci_set_le_support(struct hci_request *req) memset(&cp, 0, sizeof(cp)); - if (test_bit(HCI_LE_ENABLED, &hdev->dev_flags)) { + if (hci_dev_test_flag(hdev, HCI_LE_ENABLED)) { cp.le = 0x01; cp.simul = 0x00; } @@ -871,7 +837,7 @@ static void hci_init4_req(struct hci_request *req, unsigned long opt) hci_req_add(req, HCI_OP_READ_SYNC_TRAIN_PARAMS, 0, NULL); /* Enable Secure Connections if supported and configured */ - if (test_bit(HCI_SSP_ENABLED, &hdev->dev_flags) && + if (hci_dev_test_flag(hdev, HCI_SSP_ENABLED) && bredr_sc_enabled(hdev)) { u8 support = 0x01; @@ -891,22 +857,22 @@ static int __hci_init(struct hci_dev *hdev) /* The Device Under Test (DUT) mode is special and available for * all controller types. So just create it early on. */ - if (test_bit(HCI_SETUP, &hdev->dev_flags)) { + if (hci_dev_test_flag(hdev, HCI_SETUP)) { debugfs_create_file("dut_mode", 0644, hdev->debugfs, hdev, &dut_mode_fops); } + err = __hci_req_sync(hdev, hci_init2_req, 0, HCI_INIT_TIMEOUT); + if (err < 0) + return err; + /* HCI_BREDR covers both single-mode LE, BR/EDR and dual-mode * BR/EDR/LE type controllers. AMP controllers only need the - * first stage init. + * first two stages of init. */ if (hdev->dev_type != HCI_BREDR) return 0; - err = __hci_req_sync(hdev, hci_init2_req, 0, HCI_INIT_TIMEOUT); - if (err < 0) - return err; - err = __hci_req_sync(hdev, hci_init3_req, 0, HCI_INIT_TIMEOUT); if (err < 0) return err; @@ -927,8 +893,8 @@ static int __hci_init(struct hci_dev *hdev) * So only when in setup phase or config phase, create the debugfs * entries and register the SMP channels. */ - if (!test_bit(HCI_SETUP, &hdev->dev_flags) && - !test_bit(HCI_CONFIG, &hdev->dev_flags)) + if (!hci_dev_test_flag(hdev, HCI_SETUP) && + !hci_dev_test_flag(hdev, HCI_CONFIG)) return 0; hci_debugfs_create_common(hdev); @@ -1290,12 +1256,12 @@ int hci_inquiry(void __user *arg) if (!hdev) return -ENODEV; - if (test_bit(HCI_USER_CHANNEL, &hdev->dev_flags)) { + if (hci_dev_test_flag(hdev, HCI_USER_CHANNEL)) { err = -EBUSY; goto done; } - if (test_bit(HCI_UNCONFIGURED, &hdev->dev_flags)) { + if (hci_dev_test_flag(hdev, HCI_UNCONFIGURED)) { err = -EOPNOTSUPP; goto done; } @@ -1305,7 +1271,7 @@ int hci_inquiry(void __user *arg) goto done; } - if (!test_bit(HCI_BREDR_ENABLED, &hdev->dev_flags)) { + if (!hci_dev_test_flag(hdev, HCI_BREDR_ENABLED)) { err = -EOPNOTSUPP; goto done; } @@ -1377,17 +1343,17 @@ static int hci_dev_do_open(struct hci_dev *hdev) hci_req_lock(hdev); - if (test_bit(HCI_UNREGISTER, &hdev->dev_flags)) { + if (hci_dev_test_flag(hdev, HCI_UNREGISTER)) { ret = -ENODEV; goto done; } - if (!test_bit(HCI_SETUP, &hdev->dev_flags) && - !test_bit(HCI_CONFIG, &hdev->dev_flags)) { + if (!hci_dev_test_flag(hdev, HCI_SETUP) && + !hci_dev_test_flag(hdev, HCI_CONFIG)) { /* Check for rfkill but allow the HCI setup stage to * proceed (which in itself doesn't cause any RF activity). */ - if (test_bit(HCI_RFKILLED, &hdev->dev_flags)) { + if (hci_dev_test_flag(hdev, HCI_RFKILLED)) { ret = -ERFKILL; goto done; } @@ -1404,7 +1370,7 @@ static int hci_dev_do_open(struct hci_dev *hdev) * This check is only valid for BR/EDR controllers * since AMP controllers do not have an address. */ - if (!test_bit(HCI_USER_CHANNEL, &hdev->dev_flags) && + if (!hci_dev_test_flag(hdev, HCI_USER_CHANNEL) && hdev->dev_type == HCI_BREDR && !bacmp(&hdev->bdaddr, BDADDR_ANY) && !bacmp(&hdev->static_addr, BDADDR_ANY)) { @@ -1426,7 +1392,7 @@ static int hci_dev_do_open(struct hci_dev *hdev) atomic_set(&hdev->cmd_cnt, 1); set_bit(HCI_INIT, &hdev->flags); - if (test_bit(HCI_SETUP, &hdev->dev_flags)) { + if (hci_dev_test_flag(hdev, HCI_SETUP)) { if (hdev->setup) ret = hdev->setup(hdev); @@ -1438,7 +1404,7 @@ static int hci_dev_do_open(struct hci_dev *hdev) */ if (test_bit(HCI_QUIRK_EXTERNAL_CONFIG, &hdev->quirks) || test_bit(HCI_QUIRK_INVALID_BDADDR, &hdev->quirks)) - set_bit(HCI_UNCONFIGURED, &hdev->dev_flags); + hci_dev_set_flag(hdev, HCI_UNCONFIGURED); /* For an unconfigured controller it is required to * read at least the version information provided by @@ -1448,11 +1414,11 @@ static int hci_dev_do_open(struct hci_dev *hdev) * also the original Bluetooth public device address * will be read using the Read BD Address command. */ - if (test_bit(HCI_UNCONFIGURED, &hdev->dev_flags)) + if (hci_dev_test_flag(hdev, HCI_UNCONFIGURED)) ret = __hci_unconf_init(hdev); } - if (test_bit(HCI_CONFIG, &hdev->dev_flags)) { + if (hci_dev_test_flag(hdev, HCI_CONFIG)) { /* 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 @@ -1466,8 +1432,8 @@ static int hci_dev_do_open(struct hci_dev *hdev) } if (!ret) { - if (!test_bit(HCI_UNCONFIGURED, &hdev->dev_flags) && - !test_bit(HCI_USER_CHANNEL, &hdev->dev_flags)) + if (!hci_dev_test_flag(hdev, HCI_UNCONFIGURED) && + !hci_dev_test_flag(hdev, HCI_USER_CHANNEL)) ret = __hci_init(hdev); } @@ -1475,13 +1441,13 @@ static int hci_dev_do_open(struct hci_dev *hdev) if (!ret) { hci_dev_hold(hdev); - set_bit(HCI_RPA_EXPIRED, &hdev->dev_flags); + hci_dev_set_flag(hdev, HCI_RPA_EXPIRED); 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) && + if (!hci_dev_test_flag(hdev, HCI_SETUP) && + !hci_dev_test_flag(hdev, HCI_CONFIG) && + !hci_dev_test_flag(hdev, HCI_UNCONFIGURED) && + !hci_dev_test_flag(hdev, HCI_USER_CHANNEL) && hdev->dev_type == HCI_BREDR) { hci_dev_lock(hdev); mgmt_powered(hdev, 1); @@ -1533,8 +1499,8 @@ int hci_dev_open(__u16 dev) * 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)) { + if (hci_dev_test_flag(hdev, HCI_UNCONFIGURED) && + !hci_dev_test_flag(hdev, HCI_USER_CHANNEL)) { err = -EOPNOTSUPP; goto done; } @@ -1544,7 +1510,7 @@ int hci_dev_open(__u16 dev) * particularly important if the setup procedure has not yet * completed. */ - if (test_and_clear_bit(HCI_AUTO_OFF, &hdev->dev_flags)) + if (hci_dev_test_and_clear_flag(hdev, HCI_AUTO_OFF)) cancel_delayed_work(&hdev->power_off); /* After this call it is guaranteed that the setup procedure @@ -1559,9 +1525,9 @@ int hci_dev_open(__u16 dev) * 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); + if (!hci_dev_test_flag(hdev, HCI_USER_CHANNEL) && + !hci_dev_test_flag(hdev, HCI_MGMT)) + hci_dev_set_flag(hdev, HCI_BONDABLE); err = hci_dev_do_open(hdev); @@ -1591,6 +1557,12 @@ static int hci_dev_do_close(struct hci_dev *hdev) { BT_DBG("%s %p", hdev->name, hdev); + if (!hci_dev_test_flag(hdev, HCI_UNREGISTER)) { + /* Execute vendor specific shutdown routine */ + if (hdev->shutdown) + hdev->shutdown(hdev); + } + cancel_delayed_work(&hdev->power_off); hci_req_cancel(hdev, ENODEV); @@ -1609,17 +1581,17 @@ static int hci_dev_do_close(struct hci_dev *hdev) if (hdev->discov_timeout > 0) { cancel_delayed_work(&hdev->discov_off); hdev->discov_timeout = 0; - clear_bit(HCI_DISCOVERABLE, &hdev->dev_flags); - clear_bit(HCI_LIMITED_DISCOVERABLE, &hdev->dev_flags); + hci_dev_clear_flag(hdev, HCI_DISCOVERABLE); + hci_dev_clear_flag(hdev, HCI_LIMITED_DISCOVERABLE); } - if (test_and_clear_bit(HCI_SERVICE_CACHE, &hdev->dev_flags)) + if (hci_dev_test_and_clear_flag(hdev, HCI_SERVICE_CACHE)) cancel_delayed_work(&hdev->service_cache); cancel_delayed_work_sync(&hdev->le_scan_disable); cancel_delayed_work_sync(&hdev->le_scan_restart); - if (test_bit(HCI_MGMT, &hdev->dev_flags)) + if (hci_dev_test_flag(hdev, HCI_MGMT)) cancel_delayed_work_sync(&hdev->rpa_expired); /* Avoid potential lockdep warnings from the *_flush() calls by @@ -1631,7 +1603,7 @@ static int hci_dev_do_close(struct hci_dev *hdev) hci_discovery_set_state(hdev, DISCOVERY_STOPPED); - if (!test_and_clear_bit(HCI_AUTO_OFF, &hdev->dev_flags)) { + if (!hci_dev_test_and_clear_flag(hdev, HCI_AUTO_OFF)) { if (hdev->dev_type == HCI_BREDR) mgmt_powered(hdev, 0); } @@ -1651,8 +1623,8 @@ 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_AUTO_OFF, &hdev->dev_flags) && - !test_bit(HCI_UNCONFIGURED, &hdev->dev_flags) && + if (!hci_dev_test_flag(hdev, HCI_AUTO_OFF) && + !hci_dev_test_flag(hdev, HCI_UNCONFIGURED) && 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); @@ -1674,16 +1646,13 @@ static int hci_dev_do_close(struct hci_dev *hdev) hdev->sent_cmd = NULL; } - kfree_skb(hdev->recv_evt); - hdev->recv_evt = NULL; - /* After this point our queues are empty * and no tasks are scheduled. */ hdev->close(hdev); /* Clear flags */ hdev->flags &= BIT(HCI_RAW); - hdev->dev_flags &= ~HCI_PERSISTENT_MASK; + hci_dev_clear_volatile_flags(hdev); /* Controller radio is available but is currently powered down */ hdev->amp_status = AMP_STATUS_POWERED_DOWN; @@ -1707,12 +1676,12 @@ int hci_dev_close(__u16 dev) if (!hdev) return -ENODEV; - if (test_bit(HCI_USER_CHANNEL, &hdev->dev_flags)) { + if (hci_dev_test_flag(hdev, HCI_USER_CHANNEL)) { err = -EBUSY; goto done; } - if (test_and_clear_bit(HCI_AUTO_OFF, &hdev->dev_flags)) + if (hci_dev_test_and_clear_flag(hdev, HCI_AUTO_OFF)) cancel_delayed_work(&hdev->power_off); err = hci_dev_do_close(hdev); @@ -1770,12 +1739,12 @@ int hci_dev_reset(__u16 dev) goto done; } - if (test_bit(HCI_USER_CHANNEL, &hdev->dev_flags)) { + if (hci_dev_test_flag(hdev, HCI_USER_CHANNEL)) { err = -EBUSY; goto done; } - if (test_bit(HCI_UNCONFIGURED, &hdev->dev_flags)) { + if (hci_dev_test_flag(hdev, HCI_UNCONFIGURED)) { err = -EOPNOTSUPP; goto done; } @@ -1796,12 +1765,12 @@ int hci_dev_reset_stat(__u16 dev) if (!hdev) return -ENODEV; - if (test_bit(HCI_USER_CHANNEL, &hdev->dev_flags)) { + if (hci_dev_test_flag(hdev, HCI_USER_CHANNEL)) { ret = -EBUSY; goto done; } - if (test_bit(HCI_UNCONFIGURED, &hdev->dev_flags)) { + if (hci_dev_test_flag(hdev, HCI_UNCONFIGURED)) { ret = -EOPNOTSUPP; goto done; } @@ -1820,29 +1789,29 @@ static void hci_update_scan_state(struct hci_dev *hdev, u8 scan) BT_DBG("%s scan 0x%02x", hdev->name, scan); if ((scan & SCAN_PAGE)) - conn_changed = !test_and_set_bit(HCI_CONNECTABLE, - &hdev->dev_flags); + conn_changed = !hci_dev_test_and_set_flag(hdev, + HCI_CONNECTABLE); else - conn_changed = test_and_clear_bit(HCI_CONNECTABLE, - &hdev->dev_flags); + conn_changed = hci_dev_test_and_clear_flag(hdev, + HCI_CONNECTABLE); if ((scan & SCAN_INQUIRY)) { - discov_changed = !test_and_set_bit(HCI_DISCOVERABLE, - &hdev->dev_flags); + discov_changed = !hci_dev_test_and_set_flag(hdev, + HCI_DISCOVERABLE); } else { - clear_bit(HCI_LIMITED_DISCOVERABLE, &hdev->dev_flags); - discov_changed = test_and_clear_bit(HCI_DISCOVERABLE, - &hdev->dev_flags); + hci_dev_clear_flag(hdev, HCI_LIMITED_DISCOVERABLE); + discov_changed = hci_dev_test_and_clear_flag(hdev, + HCI_DISCOVERABLE); } - if (!test_bit(HCI_MGMT, &hdev->dev_flags)) + if (!hci_dev_test_flag(hdev, HCI_MGMT)) return; if (conn_changed || discov_changed) { /* In case this was disabled through mgmt */ - set_bit(HCI_BREDR_ENABLED, &hdev->dev_flags); + hci_dev_set_flag(hdev, HCI_BREDR_ENABLED); - if (test_bit(HCI_LE_ENABLED, &hdev->dev_flags)) + if (hci_dev_test_flag(hdev, HCI_LE_ENABLED)) mgmt_update_adv_data(hdev); mgmt_new_settings(hdev); @@ -1862,12 +1831,12 @@ int hci_dev_cmd(unsigned int cmd, void __user *arg) if (!hdev) return -ENODEV; - if (test_bit(HCI_USER_CHANNEL, &hdev->dev_flags)) { + if (hci_dev_test_flag(hdev, HCI_USER_CHANNEL)) { err = -EBUSY; goto done; } - if (test_bit(HCI_UNCONFIGURED, &hdev->dev_flags)) { + if (hci_dev_test_flag(hdev, HCI_UNCONFIGURED)) { err = -EOPNOTSUPP; goto done; } @@ -1877,7 +1846,7 @@ int hci_dev_cmd(unsigned int cmd, void __user *arg) goto done; } - if (!test_bit(HCI_BREDR_ENABLED, &hdev->dev_flags)) { + if (!hci_dev_test_flag(hdev, HCI_BREDR_ENABLED)) { err = -EOPNOTSUPP; goto done; } @@ -1981,7 +1950,7 @@ int hci_get_dev_list(void __user *arg) * is running, but in that case still indicate that the * device is actually down. */ - if (test_bit(HCI_AUTO_OFF, &hdev->dev_flags)) + if (hci_dev_test_flag(hdev, HCI_AUTO_OFF)) flags &= ~BIT(HCI_UP); (dr + n)->dev_id = hdev->id; @@ -2019,7 +1988,7 @@ int hci_get_dev_info(void __user *arg) * is running, but in that case still indicate that the * device is actually down. */ - if (test_bit(HCI_AUTO_OFF, &hdev->dev_flags)) + if (hci_dev_test_flag(hdev, HCI_AUTO_OFF)) flags = hdev->flags & ~BIT(HCI_UP); else flags = hdev->flags; @@ -2062,16 +2031,16 @@ static int hci_rfkill_set_block(void *data, bool blocked) BT_DBG("%p name %s blocked %d", hdev, hdev->name, blocked); - if (test_bit(HCI_USER_CHANNEL, &hdev->dev_flags)) + if (hci_dev_test_flag(hdev, HCI_USER_CHANNEL)) return -EBUSY; if (blocked) { - set_bit(HCI_RFKILLED, &hdev->dev_flags); - if (!test_bit(HCI_SETUP, &hdev->dev_flags) && - !test_bit(HCI_CONFIG, &hdev->dev_flags)) + hci_dev_set_flag(hdev, HCI_RFKILLED); + if (!hci_dev_test_flag(hdev, HCI_SETUP) && + !hci_dev_test_flag(hdev, HCI_CONFIG)) hci_dev_do_close(hdev); } else { - clear_bit(HCI_RFKILLED, &hdev->dev_flags); + hci_dev_clear_flag(hdev, HCI_RFKILLED); } return 0; @@ -2100,23 +2069,23 @@ static void hci_power_on(struct work_struct *work) * ignored and they need to be checked now. If they are still * 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) || + if (hci_dev_test_flag(hdev, HCI_RFKILLED) || + hci_dev_test_flag(hdev, HCI_UNCONFIGURED) || (hdev->dev_type == HCI_BREDR && !bacmp(&hdev->bdaddr, BDADDR_ANY) && !bacmp(&hdev->static_addr, BDADDR_ANY))) { - clear_bit(HCI_AUTO_OFF, &hdev->dev_flags); + hci_dev_clear_flag(hdev, HCI_AUTO_OFF); hci_dev_do_close(hdev); - } else if (test_bit(HCI_AUTO_OFF, &hdev->dev_flags)) { + } else if (hci_dev_test_flag(hdev, HCI_AUTO_OFF)) { queue_delayed_work(hdev->req_workqueue, &hdev->power_off, HCI_AUTO_OFF_TIMEOUT); } - if (test_and_clear_bit(HCI_SETUP, &hdev->dev_flags)) { + if (hci_dev_test_and_clear_flag(hdev, HCI_SETUP)) { /* For unconfigured devices, set the HCI_RAW flag * so that userspace can easily identify them. */ - if (test_bit(HCI_UNCONFIGURED, &hdev->dev_flags)) + if (hci_dev_test_flag(hdev, HCI_UNCONFIGURED)) set_bit(HCI_RAW, &hdev->flags); /* For fully configured devices, this will send @@ -2127,11 +2096,11 @@ static void hci_power_on(struct work_struct *work) * and no event will be send. */ mgmt_index_added(hdev); - } else if (test_and_clear_bit(HCI_CONFIG, &hdev->dev_flags)) { + } else if (hci_dev_test_and_clear_flag(hdev, HCI_CONFIG)) { /* When the controller is now configured, then it * is important to clear the HCI_RAW flag. */ - if (!test_bit(HCI_UNCONFIGURED, &hdev->dev_flags)) + if (!hci_dev_test_flag(hdev, HCI_UNCONFIGURED)) clear_bit(HCI_RAW, &hdev->flags); /* Powering on the controller with HCI_CONFIG set only @@ -2500,6 +2469,42 @@ void hci_remove_irk(struct hci_dev *hdev, bdaddr_t *bdaddr, u8 addr_type) } } +bool hci_bdaddr_is_paired(struct hci_dev *hdev, bdaddr_t *bdaddr, u8 type) +{ + struct smp_ltk *k; + struct smp_irk *irk; + u8 addr_type; + + if (type == BDADDR_BREDR) { + if (hci_find_link_key(hdev, bdaddr)) + return true; + return false; + } + + /* Convert to HCI addr type which struct smp_ltk uses */ + if (type == BDADDR_LE_PUBLIC) + addr_type = ADDR_LE_DEV_PUBLIC; + else + addr_type = ADDR_LE_DEV_RANDOM; + + irk = hci_get_irk(hdev, bdaddr, addr_type); + if (irk) { + bdaddr = &irk->bdaddr; + addr_type = irk->addr_type; + } + + rcu_read_lock(); + list_for_each_entry_rcu(k, &hdev->long_term_keys, list) { + if (k->bdaddr_type == addr_type && !bacmp(bdaddr, &k->bdaddr)) { + rcu_read_unlock(); + return true; + } + } + rcu_read_unlock(); + + return false; +} + /* HCI command timer function */ static void hci_cmd_timeout(struct work_struct *work) { @@ -2822,7 +2827,6 @@ static void le_scan_disable_work_complete(struct hci_dev *hdev, u8 status, { /* General inquiry access code (GIAC) */ u8 lap[3] = { 0x33, 0x8b, 0x9e }; - struct hci_request req; struct hci_cp_inquiry cp; int err; @@ -2841,21 +2845,37 @@ static void le_scan_disable_work_complete(struct hci_dev *hdev, u8 status, break; case DISCOV_TYPE_INTERLEAVED: - hci_req_init(&req, hdev); + hci_dev_lock(hdev); - memset(&cp, 0, sizeof(cp)); - memcpy(&cp.lap, lap, sizeof(cp.lap)); - cp.length = DISCOV_INTERLEAVED_INQUIRY_LEN; - hci_req_add(&req, HCI_OP_INQUIRY, sizeof(cp), &cp); + if (test_bit(HCI_QUIRK_SIMULTANEOUS_DISCOVERY, + &hdev->quirks)) { + /* If we were running LE only scan, change discovery + * state. If we were running both LE and BR/EDR inquiry + * simultaneously, and BR/EDR inquiry is already + * finished, stop discovery, otherwise BR/EDR inquiry + * will stop discovery when finished. + */ + if (!test_bit(HCI_INQUIRY, &hdev->flags)) + hci_discovery_set_state(hdev, + DISCOVERY_STOPPED); + } else { + struct hci_request req; - hci_dev_lock(hdev); + hci_inquiry_cache_flush(hdev); - hci_inquiry_cache_flush(hdev); + hci_req_init(&req, hdev); - err = hci_req_run(&req, inquiry_complete); - if (err) { - BT_ERR("Inquiry request failed: err %d", err); - hci_discovery_set_state(hdev, DISCOVERY_STOPPED); + memset(&cp, 0, sizeof(cp)); + memcpy(&cp.lap, lap, sizeof(cp.lap)); + cp.length = DISCOV_INTERLEAVED_INQUIRY_LEN; + hci_req_add(&req, HCI_OP_INQUIRY, sizeof(cp), &cp); + + err = hci_req_run(&req, inquiry_complete); + if (err) { + BT_ERR("Inquiry request failed: err %d", err); + hci_discovery_set_state(hdev, + DISCOVERY_STOPPED); + } } hci_dev_unlock(hdev); @@ -2934,7 +2954,7 @@ static void le_scan_restart_work(struct work_struct *work) BT_DBG("%s", hdev->name); /* If controller is not scanning we are done. */ - if (!test_bit(HCI_LE_SCAN, &hdev->dev_flags)) + if (!hci_dev_test_flag(hdev, HCI_LE_SCAN)) return; hci_req_init(&req, hdev); @@ -2967,9 +2987,9 @@ static void le_scan_restart_work(struct work_struct *work) void hci_copy_identity_address(struct hci_dev *hdev, bdaddr_t *bdaddr, u8 *bdaddr_type) { - if (test_bit(HCI_FORCE_STATIC_ADDR, &hdev->dbg_flags) || + if (hci_dev_test_flag(hdev, HCI_FORCE_STATIC_ADDR) || !bacmp(&hdev->bdaddr, BDADDR_ANY) || - (!test_bit(HCI_BREDR_ENABLED, &hdev->dev_flags) && + (!hci_dev_test_flag(hdev, HCI_BREDR_ENABLED) && bacmp(&hdev->static_addr, BDADDR_ANY))) { bacpy(bdaddr, &hdev->static_addr); *bdaddr_type = ADDR_LE_DEV_RANDOM; @@ -3059,6 +3079,7 @@ struct hci_dev *hci_alloc_dev(void) hci_init_sysfs(hdev); discovery_init(hdev); + adv_info_init(hdev); return hdev; } @@ -3137,16 +3158,16 @@ int hci_register_dev(struct hci_dev *hdev) } if (hdev->rfkill && rfkill_blocked(hdev->rfkill)) - set_bit(HCI_RFKILLED, &hdev->dev_flags); + hci_dev_set_flag(hdev, HCI_RFKILLED); - set_bit(HCI_SETUP, &hdev->dev_flags); - set_bit(HCI_AUTO_OFF, &hdev->dev_flags); + hci_dev_set_flag(hdev, HCI_SETUP); + hci_dev_set_flag(hdev, HCI_AUTO_OFF); if (hdev->dev_type == HCI_BREDR) { /* Assume BR/EDR support until proven otherwise (such as * through reading supported features during init. */ - set_bit(HCI_BREDR_ENABLED, &hdev->dev_flags); + hci_dev_set_flag(hdev, HCI_BREDR_ENABLED); } write_lock(&hci_dev_list_lock); @@ -3157,7 +3178,7 @@ int hci_register_dev(struct hci_dev *hdev) * 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_dev_set_flag(hdev, HCI_UNCONFIGURED); hci_notify(hdev, HCI_DEV_REG); hci_dev_hold(hdev); @@ -3179,11 +3200,11 @@ EXPORT_SYMBOL(hci_register_dev); /* Unregister HCI device */ void hci_unregister_dev(struct hci_dev *hdev) { - int i, id; + int id; BT_DBG("%p name %s bus %d", hdev, hdev->name, hdev->bus); - set_bit(HCI_UNREGISTER, &hdev->dev_flags); + hci_dev_set_flag(hdev, HCI_UNREGISTER); id = hdev->id; @@ -3193,14 +3214,11 @@ void hci_unregister_dev(struct hci_dev *hdev) hci_dev_do_close(hdev); - for (i = 0; i < NUM_REASSEMBLY; i++) - kfree_skb(hdev->reassembly[i]); - cancel_work_sync(&hdev->power_on); if (!test_bit(HCI_INIT, &hdev->flags) && - !test_bit(HCI_SETUP, &hdev->dev_flags) && - !test_bit(HCI_CONFIG, &hdev->dev_flags)) { + !hci_dev_test_flag(hdev, HCI_SETUP) && + !hci_dev_test_flag(hdev, HCI_CONFIG)) { hci_dev_lock(hdev); mgmt_index_removed(hdev); hci_dev_unlock(hdev); @@ -3299,158 +3317,15 @@ int hci_recv_frame(struct hci_dev *hdev, struct sk_buff *skb) } EXPORT_SYMBOL(hci_recv_frame); -static int hci_reassembly(struct hci_dev *hdev, int type, void *data, - int count, __u8 index) -{ - int len = 0; - int hlen = 0; - int remain = count; - struct sk_buff *skb; - struct bt_skb_cb *scb; - - if ((type < HCI_ACLDATA_PKT || type > HCI_EVENT_PKT) || - index >= NUM_REASSEMBLY) - return -EILSEQ; - - skb = hdev->reassembly[index]; - - if (!skb) { - switch (type) { - case HCI_ACLDATA_PKT: - len = HCI_MAX_FRAME_SIZE; - hlen = HCI_ACL_HDR_SIZE; - break; - case HCI_EVENT_PKT: - len = HCI_MAX_EVENT_SIZE; - hlen = HCI_EVENT_HDR_SIZE; - break; - case HCI_SCODATA_PKT: - len = HCI_MAX_SCO_SIZE; - hlen = HCI_SCO_HDR_SIZE; - break; - } - - skb = bt_skb_alloc(len, GFP_ATOMIC); - if (!skb) - return -ENOMEM; - - scb = (void *) skb->cb; - scb->expect = hlen; - scb->pkt_type = type; - - hdev->reassembly[index] = skb; - } - - while (count) { - scb = (void *) skb->cb; - len = min_t(uint, scb->expect, count); - - memcpy(skb_put(skb, len), data, len); - - count -= len; - data += len; - scb->expect -= len; - remain = count; - - switch (type) { - case HCI_EVENT_PKT: - if (skb->len == HCI_EVENT_HDR_SIZE) { - struct hci_event_hdr *h = hci_event_hdr(skb); - scb->expect = h->plen; - - if (skb_tailroom(skb) < scb->expect) { - kfree_skb(skb); - hdev->reassembly[index] = NULL; - return -ENOMEM; - } - } - break; - - case HCI_ACLDATA_PKT: - if (skb->len == HCI_ACL_HDR_SIZE) { - struct hci_acl_hdr *h = hci_acl_hdr(skb); - scb->expect = __le16_to_cpu(h->dlen); - - if (skb_tailroom(skb) < scb->expect) { - kfree_skb(skb); - hdev->reassembly[index] = NULL; - return -ENOMEM; - } - } - break; - - case HCI_SCODATA_PKT: - if (skb->len == HCI_SCO_HDR_SIZE) { - struct hci_sco_hdr *h = hci_sco_hdr(skb); - scb->expect = h->dlen; - - if (skb_tailroom(skb) < scb->expect) { - kfree_skb(skb); - hdev->reassembly[index] = NULL; - return -ENOMEM; - } - } - break; - } - - if (scb->expect == 0) { - /* Complete frame */ - - bt_cb(skb)->pkt_type = type; - hci_recv_frame(hdev, skb); - - hdev->reassembly[index] = NULL; - return remain; - } - } - - return remain; -} - -#define STREAM_REASSEMBLY 0 - -int hci_recv_stream_fragment(struct hci_dev *hdev, void *data, int count) -{ - int type; - int rem = 0; - - while (count) { - struct sk_buff *skb = hdev->reassembly[STREAM_REASSEMBLY]; - - if (!skb) { - struct { char type; } *pkt; - - /* Start of the frame */ - pkt = data; - type = pkt->type; - - data++; - count--; - } else - type = bt_cb(skb)->pkt_type; - - rem = hci_reassembly(hdev, type, data, count, - STREAM_REASSEMBLY); - if (rem < 0) - return rem; - - data += (count - rem); - count = rem; - } - - return rem; -} -EXPORT_SYMBOL(hci_recv_stream_fragment); - /* ---- Interface to upper protocols ---- */ int hci_register_cb(struct hci_cb *cb) { BT_DBG("%p name %s", cb, cb->name); - write_lock(&hci_cb_list_lock); - list_add(&cb->list, &hci_cb_list); - write_unlock(&hci_cb_list_lock); + mutex_lock(&hci_cb_list_lock); + list_add_tail(&cb->list, &hci_cb_list); + mutex_unlock(&hci_cb_list_lock); return 0; } @@ -3460,9 +3335,9 @@ int hci_unregister_cb(struct hci_cb *cb) { BT_DBG("%p name %s", cb, cb->name); - write_lock(&hci_cb_list_lock); + mutex_lock(&hci_cb_list_lock); list_del(&cb->list); - write_unlock(&hci_cb_list_lock); + mutex_unlock(&hci_cb_list_lock); return 0; } @@ -3495,11 +3370,6 @@ static void hci_send_frame(struct hci_dev *hdev, struct sk_buff *skb) } } -bool hci_req_pending(struct hci_dev *hdev) -{ - return (hdev->req_status == HCI_REQ_PEND); -} - /* Send HCI command */ int hci_send_cmd(struct hci_dev *hdev, __u16 opcode, __u32 plen, const void *param) @@ -3874,7 +3744,7 @@ 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_UNCONFIGURED, &hdev->dev_flags)) { + if (!hci_dev_test_flag(hdev, HCI_UNCONFIGURED)) { /* ACL tx timeout must be longer than maximum * link supervision timeout (40.9 seconds) */ if (!cnt && time_after(jiffies, hdev->acl_last_tx + @@ -4057,7 +3927,7 @@ static void hci_sched_le(struct hci_dev *hdev) if (!hci_conn_num(hdev, LE_LINK)) return; - if (!test_bit(HCI_UNCONFIGURED, &hdev->dev_flags)) { + if (!hci_dev_test_flag(hdev, HCI_UNCONFIGURED)) { /* LE tx timeout must be longer than maximum * link supervision timeout (40.9 seconds) */ if (!hdev->le_cnt && hdev->le_pkts && @@ -4105,7 +3975,7 @@ static void hci_tx_work(struct work_struct *work) BT_DBG("%s acl %d sco %d le %d", hdev->name, hdev->acl_cnt, hdev->sco_cnt, hdev->le_cnt); - if (!test_bit(HCI_USER_CHANNEL, &hdev->dev_flags)) { + if (!hci_dev_test_flag(hdev, HCI_USER_CHANNEL)) { /* Schedule queues and send stuff to HCI driver */ hci_sched_acl(hdev); hci_sched_sco(hdev); @@ -4220,9 +4090,10 @@ static void hci_resend_last(struct hci_dev *hdev) queue_work(hdev->workqueue, &hdev->cmd_work); } -void hci_req_cmd_complete(struct hci_dev *hdev, u16 opcode, u8 status) +void hci_req_cmd_complete(struct hci_dev *hdev, u16 opcode, u8 status, + hci_req_complete_t *req_complete, + hci_req_complete_skb_t *req_complete_skb) { - hci_req_complete_t req_complete = NULL; struct sk_buff *skb; unsigned long flags; @@ -4254,18 +4125,14 @@ void hci_req_cmd_complete(struct hci_dev *hdev, u16 opcode, u8 status) * callback would be found in hdev->sent_cmd instead of the * command queue (hdev->cmd_q). */ - if (hdev->sent_cmd) { - req_complete = bt_cb(hdev->sent_cmd)->req.complete; - - if (req_complete) { - /* We must set the complete callback to NULL to - * avoid calling the callback more than once if - * this function gets called again. - */ - bt_cb(hdev->sent_cmd)->req.complete = NULL; + if (bt_cb(hdev->sent_cmd)->req.complete) { + *req_complete = bt_cb(hdev->sent_cmd)->req.complete; + return; + } - goto call_complete; - } + if (bt_cb(hdev->sent_cmd)->req.complete_skb) { + *req_complete_skb = bt_cb(hdev->sent_cmd)->req.complete_skb; + return; } /* Remove all pending commands belonging to this request */ @@ -4276,14 +4143,11 @@ void hci_req_cmd_complete(struct hci_dev *hdev, u16 opcode, u8 status) break; } - req_complete = bt_cb(skb)->req.complete; + *req_complete = bt_cb(skb)->req.complete; + *req_complete_skb = bt_cb(skb)->req.complete_skb; kfree_skb(skb); } spin_unlock_irqrestore(&hdev->cmd_q.lock, flags); - -call_complete: - if (req_complete) - req_complete(hdev, status, status ? opcode : HCI_OP_NOP); } static void hci_rx_work(struct work_struct *work) @@ -4302,7 +4166,7 @@ static void hci_rx_work(struct work_struct *work) hci_send_to_sock(hdev, skb); } - if (test_bit(HCI_USER_CHANNEL, &hdev->dev_flags)) { + if (hci_dev_test_flag(hdev, HCI_USER_CHANNEL)) { kfree_skb(skb); continue; } diff --git a/net/bluetooth/hci_debugfs.c b/net/bluetooth/hci_debugfs.c index 65261e5d4b84..7db4220941cc 100644 --- a/net/bluetooth/hci_debugfs.c +++ b/net/bluetooth/hci_debugfs.c @@ -28,6 +28,54 @@ #include "hci_debugfs.h" +#define DEFINE_QUIRK_ATTRIBUTE(__name, __quirk) \ +static ssize_t __name ## _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(__quirk, &hdev->quirks) ? 'Y' : 'N'; \ + buf[1] = '\n'; \ + buf[2] = '\0'; \ + return simple_read_from_buffer(user_buf, count, ppos, buf, 2); \ +} \ + \ +static ssize_t __name ## _write(struct file *file, \ + const char __user *user_buf, \ + size_t count, loff_t *ppos) \ +{ \ + struct hci_dev *hdev = file->private_data; \ + char buf[32]; \ + size_t buf_size = min(count, (sizeof(buf) - 1)); \ + bool enable; \ + \ + if (test_bit(HCI_UP, &hdev->flags)) \ + return -EBUSY; \ + \ + if (copy_from_user(buf, user_buf, buf_size)) \ + return -EFAULT; \ + \ + buf[buf_size] = '\0'; \ + if (strtobool(buf, &enable)) \ + return -EINVAL; \ + \ + if (enable == test_bit(__quirk, &hdev->quirks)) \ + return -EALREADY; \ + \ + change_bit(__quirk, &hdev->quirks); \ + \ + return count; \ +} \ + \ +static const struct file_operations __name ## _fops = { \ + .open = simple_open, \ + .read = __name ## _read, \ + .write = __name ## _write, \ + .llseek = default_llseek, \ +} \ + static int features_show(struct seq_file *f, void *ptr) { struct hci_dev *hdev = f->private; @@ -66,6 +114,30 @@ static const struct file_operations features_fops = { .release = single_release, }; +static int device_id_show(struct seq_file *f, void *ptr) +{ + struct hci_dev *hdev = f->private; + + hci_dev_lock(hdev); + seq_printf(f, "%4.4x:%4.4x:%4.4x:%4.4x\n", hdev->devid_source, + hdev->devid_vendor, hdev->devid_product, hdev->devid_version); + hci_dev_unlock(hdev); + + return 0; +} + +static int device_id_open(struct inode *inode, struct file *file) +{ + return single_open(file, device_id_show, inode->i_private); +} + +static const struct file_operations device_id_fops = { + .open = device_id_open, + .read = seq_read, + .llseek = seq_lseek, + .release = single_release, +}; + static int device_list_show(struct seq_file *f, void *ptr) { struct hci_dev *hdev = f->private; @@ -166,7 +238,7 @@ static int remote_oob_show(struct seq_file *f, void *ptr) seq_printf(f, "%pMR (type %u) %u %*phN %*phN %*phN %*phN\n", &data->bdaddr, data->bdaddr_type, data->present, 16, data->hash192, 16, data->rand192, - 16, data->hash256, 19, data->rand256); + 16, data->hash256, 16, data->rand256); } hci_dev_unlock(hdev); @@ -247,7 +319,7 @@ static ssize_t use_debug_keys_read(struct file *file, char __user *user_buf, struct hci_dev *hdev = file->private_data; char buf[3]; - buf[0] = test_bit(HCI_USE_DEBUG_KEYS, &hdev->dev_flags) ? 'Y': 'N'; + buf[0] = hci_dev_test_flag(hdev, HCI_USE_DEBUG_KEYS) ? 'Y': 'N'; buf[1] = '\n'; buf[2] = '\0'; return simple_read_from_buffer(user_buf, count, ppos, buf, 2); @@ -265,7 +337,7 @@ static ssize_t sc_only_mode_read(struct file *file, char __user *user_buf, struct hci_dev *hdev = file->private_data; char buf[3]; - buf[0] = test_bit(HCI_SC_ONLY, &hdev->dev_flags) ? 'Y': 'N'; + buf[0] = hci_dev_test_flag(hdev, HCI_SC_ONLY) ? 'Y': 'N'; buf[1] = '\n'; buf[2] = '\0'; return simple_read_from_buffer(user_buf, count, ppos, buf, 2); @@ -287,6 +359,8 @@ void hci_debugfs_create_common(struct hci_dev *hdev) debugfs_create_u16("hci_revision", 0444, hdev->debugfs, &hdev->hci_rev); debugfs_create_u8("hardware_error", 0444, hdev->debugfs, &hdev->hw_error_code); + debugfs_create_file("device_id", 0444, hdev->debugfs, hdev, + &device_id_fops); debugfs_create_file("device_list", 0444, hdev->debugfs, hdev, &device_list_fops); @@ -679,7 +753,7 @@ 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->dbg_flags) ? 'Y': 'N'; + buf[0] = hci_dev_test_flag(hdev, HCI_FORCE_STATIC_ADDR) ? 'Y': 'N'; buf[1] = '\n'; buf[2] = '\0'; return simple_read_from_buffer(user_buf, count, ppos, buf, 2); @@ -704,10 +778,10 @@ 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->dbg_flags)) + if (enable == hci_dev_test_flag(hdev, HCI_FORCE_STATIC_ADDR)) return -EALREADY; - change_bit(HCI_FORCE_STATIC_ADDR, &hdev->dbg_flags); + hci_dev_change_flag(hdev, HCI_FORCE_STATIC_ADDR); return count; } @@ -997,6 +1071,11 @@ static int adv_max_interval_get(void *data, u64 *val) DEFINE_SIMPLE_ATTRIBUTE(adv_max_interval_fops, adv_max_interval_get, adv_max_interval_set, "%llu\n"); +DEFINE_QUIRK_ATTRIBUTE(quirk_strict_duplicate_filter, + HCI_QUIRK_STRICT_DUPLICATE_FILTER); +DEFINE_QUIRK_ATTRIBUTE(quirk_simultaneous_discovery, + HCI_QUIRK_SIMULTANEOUS_DISCOVERY); + void hci_debugfs_create_le(struct hci_dev *hdev) { debugfs_create_file("identity", 0400, hdev->debugfs, hdev, @@ -1041,6 +1120,13 @@ void hci_debugfs_create_le(struct hci_dev *hdev) &adv_max_interval_fops); debugfs_create_u16("discov_interleaved_timeout", 0644, hdev->debugfs, &hdev->discov_interleaved_timeout); + + debugfs_create_file("quirk_strict_duplicate_filter", 0644, + hdev->debugfs, hdev, + &quirk_strict_duplicate_filter_fops); + debugfs_create_file("quirk_simultaneous_discovery", 0644, + hdev->debugfs, hdev, + &quirk_simultaneous_discovery_fops); } void hci_debugfs_create_conn(struct hci_conn *conn) diff --git a/net/bluetooth/hci_debugfs.h b/net/bluetooth/hci_debugfs.h index fb68efe083c5..4444dc8cedc2 100644 --- a/net/bluetooth/hci_debugfs.h +++ b/net/bluetooth/hci_debugfs.h @@ -20,7 +20,29 @@ SOFTWARE IS DISCLAIMED. */ +#if IS_ENABLED(CONFIG_BT_DEBUGFS) + void hci_debugfs_create_common(struct hci_dev *hdev); void hci_debugfs_create_bredr(struct hci_dev *hdev); void hci_debugfs_create_le(struct hci_dev *hdev); void hci_debugfs_create_conn(struct hci_conn *conn); + +#else + +static inline void hci_debugfs_create_common(struct hci_dev *hdev) +{ +} + +static inline void hci_debugfs_create_bredr(struct hci_dev *hdev) +{ +} + +static inline void hci_debugfs_create_le(struct hci_dev *hdev) +{ +} + +static inline void hci_debugfs_create_conn(struct hci_conn *conn) +{ +} + +#endif diff --git a/net/bluetooth/hci_event.c b/net/bluetooth/hci_event.c index a3fb094822b6..7b61be73650f 100644 --- a/net/bluetooth/hci_event.c +++ b/net/bluetooth/hci_event.c @@ -70,7 +70,7 @@ static void hci_cc_periodic_inq(struct hci_dev *hdev, struct sk_buff *skb) if (status) return; - set_bit(HCI_PERIODIC_INQ, &hdev->dev_flags); + hci_dev_set_flag(hdev, HCI_PERIODIC_INQ); } static void hci_cc_exit_periodic_inq(struct hci_dev *hdev, struct sk_buff *skb) @@ -82,7 +82,7 @@ static void hci_cc_exit_periodic_inq(struct hci_dev *hdev, struct sk_buff *skb) if (status) return; - clear_bit(HCI_PERIODIC_INQ, &hdev->dev_flags); + hci_dev_clear_flag(hdev, HCI_PERIODIC_INQ); hci_conn_check_pending(hdev); } @@ -198,7 +198,7 @@ static void hci_cc_reset(struct hci_dev *hdev, struct sk_buff *skb) return; /* Reset all non-persistent flags */ - hdev->dev_flags &= ~HCI_PERSISTENT_MASK; + hci_dev_clear_volatile_flags(hdev); hci_discovery_set_state(hdev, DISCOVERY_STOPPED); @@ -265,7 +265,7 @@ static void hci_cc_write_local_name(struct hci_dev *hdev, struct sk_buff *skb) hci_dev_lock(hdev); - if (test_bit(HCI_MGMT, &hdev->dev_flags)) + if (hci_dev_test_flag(hdev, HCI_MGMT)) mgmt_set_local_name_complete(hdev, sent, status); else if (!status) memcpy(hdev->dev_name, sent, HCI_MAX_NAME_LENGTH); @@ -282,8 +282,8 @@ static void hci_cc_read_local_name(struct hci_dev *hdev, struct sk_buff *skb) if (rp->status) return; - if (test_bit(HCI_SETUP, &hdev->dev_flags) || - test_bit(HCI_CONFIG, &hdev->dev_flags)) + if (hci_dev_test_flag(hdev, HCI_SETUP) || + hci_dev_test_flag(hdev, HCI_CONFIG)) memcpy(hdev->dev_name, rp->name, HCI_MAX_NAME_LENGTH); } @@ -309,7 +309,7 @@ static void hci_cc_write_auth_enable(struct hci_dev *hdev, struct sk_buff *skb) clear_bit(HCI_AUTH, &hdev->flags); } - if (test_bit(HCI_MGMT, &hdev->dev_flags)) + if (hci_dev_test_flag(hdev, HCI_MGMT)) mgmt_auth_enable_complete(hdev, status); hci_dev_unlock(hdev); @@ -404,7 +404,7 @@ static void hci_cc_write_class_of_dev(struct hci_dev *hdev, struct sk_buff *skb) if (status == 0) memcpy(hdev->dev_class, sent, 3); - if (test_bit(HCI_MGMT, &hdev->dev_flags)) + if (hci_dev_test_flag(hdev, HCI_MGMT)) mgmt_set_class_of_dev_complete(hdev, sent, status); hci_dev_unlock(hdev); @@ -497,13 +497,13 @@ static void hci_cc_write_ssp_mode(struct hci_dev *hdev, struct sk_buff *skb) hdev->features[1][0] &= ~LMP_HOST_SSP; } - if (test_bit(HCI_MGMT, &hdev->dev_flags)) + if (hci_dev_test_flag(hdev, HCI_MGMT)) mgmt_ssp_enable_complete(hdev, sent->mode, status); else if (!status) { if (sent->mode) - set_bit(HCI_SSP_ENABLED, &hdev->dev_flags); + hci_dev_set_flag(hdev, HCI_SSP_ENABLED); else - clear_bit(HCI_SSP_ENABLED, &hdev->dev_flags); + hci_dev_clear_flag(hdev, HCI_SSP_ENABLED); } hci_dev_unlock(hdev); @@ -529,11 +529,11 @@ static void hci_cc_write_sc_support(struct hci_dev *hdev, struct sk_buff *skb) hdev->features[1][0] &= ~LMP_HOST_SC; } - if (!test_bit(HCI_MGMT, &hdev->dev_flags) && !status) { + if (!hci_dev_test_flag(hdev, HCI_MGMT) && !status) { if (sent->support) - set_bit(HCI_SC_ENABLED, &hdev->dev_flags); + hci_dev_set_flag(hdev, HCI_SC_ENABLED); else - clear_bit(HCI_SC_ENABLED, &hdev->dev_flags); + hci_dev_clear_flag(hdev, HCI_SC_ENABLED); } hci_dev_unlock(hdev); @@ -548,8 +548,8 @@ static void hci_cc_read_local_version(struct hci_dev *hdev, struct sk_buff *skb) if (rp->status) return; - if (test_bit(HCI_SETUP, &hdev->dev_flags) || - test_bit(HCI_CONFIG, &hdev->dev_flags)) { + if (hci_dev_test_flag(hdev, HCI_SETUP) || + hci_dev_test_flag(hdev, HCI_CONFIG)) { hdev->hci_ver = rp->hci_ver; hdev->hci_rev = __le16_to_cpu(rp->hci_rev); hdev->lmp_ver = rp->lmp_ver; @@ -568,8 +568,8 @@ static void hci_cc_read_local_commands(struct hci_dev *hdev, if (rp->status) return; - if (test_bit(HCI_SETUP, &hdev->dev_flags) || - test_bit(HCI_CONFIG, &hdev->dev_flags)) + if (hci_dev_test_flag(hdev, HCI_SETUP) || + hci_dev_test_flag(hdev, HCI_CONFIG)) memcpy(hdev->commands, rp->commands, sizeof(hdev->commands)); } @@ -691,7 +691,7 @@ static void hci_cc_read_bd_addr(struct hci_dev *hdev, struct sk_buff *skb) if (test_bit(HCI_INIT, &hdev->flags)) bacpy(&hdev->bdaddr, &rp->bdaddr); - if (test_bit(HCI_SETUP, &hdev->dev_flags)) + if (hci_dev_test_flag(hdev, HCI_SETUP)) bacpy(&hdev->setup_addr, &rp->bdaddr); } @@ -900,7 +900,7 @@ static void hci_cc_pin_code_reply(struct hci_dev *hdev, struct sk_buff *skb) hci_dev_lock(hdev); - if (test_bit(HCI_MGMT, &hdev->dev_flags)) + if (hci_dev_test_flag(hdev, HCI_MGMT)) mgmt_pin_code_reply_complete(hdev, &rp->bdaddr, rp->status); if (rp->status) @@ -926,7 +926,7 @@ static void hci_cc_pin_code_neg_reply(struct hci_dev *hdev, struct sk_buff *skb) hci_dev_lock(hdev); - if (test_bit(HCI_MGMT, &hdev->dev_flags)) + if (hci_dev_test_flag(hdev, HCI_MGMT)) mgmt_pin_code_neg_reply_complete(hdev, &rp->bdaddr, rp->status); @@ -985,7 +985,7 @@ static void hci_cc_user_confirm_reply(struct hci_dev *hdev, struct sk_buff *skb) hci_dev_lock(hdev); - if (test_bit(HCI_MGMT, &hdev->dev_flags)) + if (hci_dev_test_flag(hdev, HCI_MGMT)) mgmt_user_confirm_reply_complete(hdev, &rp->bdaddr, ACL_LINK, 0, rp->status); @@ -1001,7 +1001,7 @@ static void hci_cc_user_confirm_neg_reply(struct hci_dev *hdev, hci_dev_lock(hdev); - if (test_bit(HCI_MGMT, &hdev->dev_flags)) + if (hci_dev_test_flag(hdev, HCI_MGMT)) mgmt_user_confirm_neg_reply_complete(hdev, &rp->bdaddr, ACL_LINK, 0, rp->status); @@ -1016,7 +1016,7 @@ static void hci_cc_user_passkey_reply(struct hci_dev *hdev, struct sk_buff *skb) hci_dev_lock(hdev); - if (test_bit(HCI_MGMT, &hdev->dev_flags)) + if (hci_dev_test_flag(hdev, HCI_MGMT)) mgmt_user_passkey_reply_complete(hdev, &rp->bdaddr, ACL_LINK, 0, rp->status); @@ -1032,7 +1032,7 @@ static void hci_cc_user_passkey_neg_reply(struct hci_dev *hdev, hci_dev_lock(hdev); - if (test_bit(HCI_MGMT, &hdev->dev_flags)) + if (hci_dev_test_flag(hdev, HCI_MGMT)) mgmt_user_passkey_neg_reply_complete(hdev, &rp->bdaddr, ACL_LINK, 0, rp->status); @@ -1045,11 +1045,6 @@ static void hci_cc_read_local_oob_data(struct hci_dev *hdev, struct hci_rp_read_local_oob_data *rp = (void *) skb->data; BT_DBG("%s status 0x%2.2x", hdev->name, rp->status); - - hci_dev_lock(hdev); - mgmt_read_local_oob_data_complete(hdev, rp->hash, rp->rand, NULL, NULL, - rp->status); - hci_dev_unlock(hdev); } static void hci_cc_read_local_oob_ext_data(struct hci_dev *hdev, @@ -1058,15 +1053,8 @@ static void hci_cc_read_local_oob_ext_data(struct hci_dev *hdev, struct hci_rp_read_local_oob_ext_data *rp = (void *) skb->data; BT_DBG("%s status 0x%2.2x", hdev->name, rp->status); - - hci_dev_lock(hdev); - mgmt_read_local_oob_data_complete(hdev, rp->hash192, rp->rand192, - rp->hash256, rp->rand256, - rp->status); - hci_dev_unlock(hdev); } - static void hci_cc_le_set_random_addr(struct hci_dev *hdev, struct sk_buff *skb) { __u8 status = *((__u8 *) skb->data); @@ -1109,7 +1097,7 @@ 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); + hci_dev_set_flag(hdev, HCI_LE_ADV); conn = hci_conn_hash_lookup_state(hdev, LE_LINK, BT_CONNECT); if (conn) @@ -1117,7 +1105,7 @@ static void hci_cc_le_set_adv_enable(struct hci_dev *hdev, struct sk_buff *skb) &conn->le_conn_timeout, conn->conn_timeout); } else { - clear_bit(HCI_LE_ADV, &hdev->dev_flags); + hci_dev_clear_flag(hdev, HCI_LE_ADV); } hci_dev_unlock(hdev); @@ -1192,7 +1180,7 @@ static void hci_cc_le_set_scan_enable(struct hci_dev *hdev, switch (cp->enable) { case LE_SCAN_ENABLE: - set_bit(HCI_LE_SCAN, &hdev->dev_flags); + hci_dev_set_flag(hdev, HCI_LE_SCAN); if (hdev->le_scan_type == LE_SCAN_ACTIVE) clear_pending_adv_report(hdev); break; @@ -1217,7 +1205,7 @@ 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); + hci_dev_clear_flag(hdev, HCI_LE_SCAN); /* The HCI_LE_SCAN_INTERRUPTED flag indicates that we * interrupted scanning due to a connect request. Mark @@ -1226,10 +1214,9 @@ static void hci_cc_le_set_scan_enable(struct hci_dev *hdev, * 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)) + if (hci_dev_test_and_clear_flag(hdev, HCI_LE_SCAN_INTERRUPTED)) hci_discovery_set_state(hdev, DISCOVERY_STOPPED); - else if (!test_bit(HCI_LE_ADV, &hdev->dev_flags) && + else if (!hci_dev_test_flag(hdev, HCI_LE_ADV) && hdev->discovery.state == DISCOVERY_FINDING) mgmt_reenable_advertising(hdev); @@ -1388,11 +1375,11 @@ static void hci_cc_write_le_host_supported(struct hci_dev *hdev, if (sent->le) { hdev->features[1][0] |= LMP_HOST_LE; - set_bit(HCI_LE_ENABLED, &hdev->dev_flags); + hci_dev_set_flag(hdev, HCI_LE_ENABLED); } else { hdev->features[1][0] &= ~LMP_HOST_LE; - clear_bit(HCI_LE_ENABLED, &hdev->dev_flags); - clear_bit(HCI_ADVERTISING, &hdev->dev_flags); + hci_dev_clear_flag(hdev, HCI_LE_ENABLED); + hci_dev_clear_flag(hdev, HCI_ADVERTISING); } if (sent->simul) @@ -1537,7 +1524,7 @@ static void hci_cs_create_conn(struct hci_dev *hdev, __u8 status) if (conn && conn->state == BT_CONNECT) { if (status != 0x0c || conn->attempt > 2) { conn->state = BT_CLOSED; - hci_proto_connect_cfm(conn, status); + hci_connect_cfm(conn, status); hci_conn_del(conn); } else conn->state = BT_CONNECT2; @@ -1581,7 +1568,7 @@ static void hci_cs_add_sco(struct hci_dev *hdev, __u8 status) if (sco) { sco->state = BT_CLOSED; - hci_proto_connect_cfm(sco, status); + hci_connect_cfm(sco, status); hci_conn_del(sco); } } @@ -1608,7 +1595,7 @@ static void hci_cs_auth_requested(struct hci_dev *hdev, __u8 status) conn = hci_conn_hash_lookup_handle(hdev, __le16_to_cpu(cp->handle)); if (conn) { if (conn->state == BT_CONFIG) { - hci_proto_connect_cfm(conn, status); + hci_connect_cfm(conn, status); hci_conn_drop(conn); } } @@ -1635,7 +1622,7 @@ static void hci_cs_set_conn_encrypt(struct hci_dev *hdev, __u8 status) conn = hci_conn_hash_lookup_handle(hdev, __le16_to_cpu(cp->handle)); if (conn) { if (conn->state == BT_CONFIG) { - hci_proto_connect_cfm(conn, status); + hci_connect_cfm(conn, status); hci_conn_drop(conn); } } @@ -1769,7 +1756,7 @@ static void hci_cs_remote_name_req(struct hci_dev *hdev, __u8 status) conn = hci_conn_hash_lookup_ba(hdev, ACL_LINK, &cp->bdaddr); - if (test_bit(HCI_MGMT, &hdev->dev_flags)) + if (hci_dev_test_flag(hdev, HCI_MGMT)) hci_check_pending_name(hdev, conn, &cp->bdaddr, NULL, 0); if (!conn) @@ -1811,7 +1798,7 @@ static void hci_cs_read_remote_features(struct hci_dev *hdev, __u8 status) conn = hci_conn_hash_lookup_handle(hdev, __le16_to_cpu(cp->handle)); if (conn) { if (conn->state == BT_CONFIG) { - hci_proto_connect_cfm(conn, status); + hci_connect_cfm(conn, status); hci_conn_drop(conn); } } @@ -1838,7 +1825,7 @@ static void hci_cs_read_remote_ext_features(struct hci_dev *hdev, __u8 status) conn = hci_conn_hash_lookup_handle(hdev, __le16_to_cpu(cp->handle)); if (conn) { if (conn->state == BT_CONFIG) { - hci_proto_connect_cfm(conn, status); + hci_connect_cfm(conn, status); hci_conn_drop(conn); } } @@ -1873,7 +1860,7 @@ static void hci_cs_setup_sync_conn(struct hci_dev *hdev, __u8 status) if (sco) { sco->state = BT_CLOSED; - hci_proto_connect_cfm(sco, status); + hci_connect_cfm(sco, status); hci_conn_del(sco); } } @@ -2049,6 +2036,33 @@ unlock: hci_dev_unlock(hdev); } +static void hci_cs_le_read_remote_features(struct hci_dev *hdev, u8 status) +{ + struct hci_cp_le_read_remote_features *cp; + struct hci_conn *conn; + + BT_DBG("%s status 0x%2.2x", hdev->name, status); + + if (!status) + return; + + cp = hci_sent_cmd_data(hdev, HCI_OP_LE_READ_REMOTE_FEATURES); + if (!cp) + return; + + hci_dev_lock(hdev); + + conn = hci_conn_hash_lookup_handle(hdev, __le16_to_cpu(cp->handle)); + if (conn) { + if (conn->state == BT_CONFIG) { + hci_connect_cfm(conn, status); + hci_conn_drop(conn); + } + } + + hci_dev_unlock(hdev); +} + static void hci_cs_le_start_enc(struct hci_dev *hdev, u8 status) { struct hci_cp_le_start_enc *cp; @@ -2118,7 +2132,7 @@ static void hci_inquiry_complete_evt(struct hci_dev *hdev, struct sk_buff *skb) smp_mb__after_atomic(); /* wake_up_bit advises about this barrier */ wake_up_bit(&hdev->flags, HCI_INQUIRY); - if (!test_bit(HCI_MGMT, &hdev->dev_flags)) + if (!hci_dev_test_flag(hdev, HCI_MGMT)) return; hci_dev_lock(hdev); @@ -2127,7 +2141,16 @@ static void hci_inquiry_complete_evt(struct hci_dev *hdev, struct sk_buff *skb) goto unlock; if (list_empty(&discov->resolve)) { - hci_discovery_set_state(hdev, DISCOVERY_STOPPED); + /* When BR/EDR inquiry is active and no LE scanning is in + * progress, then change discovery state to indicate completion. + * + * When running LE scanning and BR/EDR inquiry simultaneously + * and the LE scan already finished, then change the discovery + * state to indicate completion. + */ + if (!hci_dev_test_flag(hdev, HCI_LE_SCAN) || + !test_bit(HCI_QUIRK_SIMULTANEOUS_DISCOVERY, &hdev->quirks)) + hci_discovery_set_state(hdev, DISCOVERY_STOPPED); goto unlock; } @@ -2136,7 +2159,16 @@ static void hci_inquiry_complete_evt(struct hci_dev *hdev, struct sk_buff *skb) e->name_state = NAME_PENDING; hci_discovery_set_state(hdev, DISCOVERY_RESOLVING); } else { - hci_discovery_set_state(hdev, DISCOVERY_STOPPED); + /* When BR/EDR inquiry is active and no LE scanning is in + * progress, then change discovery state to indicate completion. + * + * When running LE scanning and BR/EDR inquiry simultaneously + * and the LE scan already finished, then change the discovery + * state to indicate completion. + */ + if (!hci_dev_test_flag(hdev, HCI_LE_SCAN) || + !test_bit(HCI_QUIRK_SIMULTANEOUS_DISCOVERY, &hdev->quirks)) + hci_discovery_set_state(hdev, DISCOVERY_STOPPED); } unlock: @@ -2154,7 +2186,7 @@ static void hci_inquiry_result_evt(struct hci_dev *hdev, struct sk_buff *skb) if (!num_rsp) return; - if (test_bit(HCI_PERIODIC_INQ, &hdev->dev_flags)) + if (hci_dev_test_flag(hdev, HCI_PERIODIC_INQ)) return; hci_dev_lock(hdev); @@ -2255,10 +2287,10 @@ static void hci_conn_complete_evt(struct hci_dev *hdev, struct sk_buff *skb) hci_sco_setup(conn, ev->status); if (ev->status) { - hci_proto_connect_cfm(conn, ev->status); + hci_connect_cfm(conn, ev->status); hci_conn_del(conn); } else if (ev->link_type != ACL_LINK) - hci_proto_connect_cfm(conn, ev->status); + hci_connect_cfm(conn, ev->status); unlock: hci_dev_unlock(hdev); @@ -2304,8 +2336,8 @@ static void hci_conn_request_evt(struct hci_dev *hdev, struct sk_buff *skb) * connection. These features are only touched through mgmt so * only do the checks if HCI_MGMT is set. */ - if (test_bit(HCI_MGMT, &hdev->dev_flags) && - !test_bit(HCI_CONNECTABLE, &hdev->dev_flags) && + if (hci_dev_test_flag(hdev, HCI_MGMT) && + !hci_dev_test_flag(hdev, HCI_CONNECTABLE) && !hci_bdaddr_list_lookup(&hdev->whitelist, &ev->bdaddr, BDADDR_BREDR)) { hci_reject_conn(hdev, &ev->bdaddr); @@ -2366,7 +2398,7 @@ static void hci_conn_request_evt(struct hci_dev *hdev, struct sk_buff *skb) &cp); } else { conn->state = BT_CONNECT2; - hci_proto_connect_cfm(conn, 0); + hci_connect_cfm(conn, 0); } } @@ -2444,7 +2476,7 @@ static void hci_disconn_complete_evt(struct hci_dev *hdev, struct sk_buff *skb) type = conn->type; - hci_proto_disconn_cfm(conn, ev->reason); + hci_disconn_cfm(conn, ev->reason); hci_conn_del(conn); /* Re-enable advertising if necessary, since it might @@ -2501,7 +2533,7 @@ static void hci_auth_complete_evt(struct hci_dev *hdev, struct sk_buff *skb) &cp); } else { conn->state = BT_CONNECTED; - hci_proto_connect_cfm(conn, ev->status); + hci_connect_cfm(conn, ev->status); hci_conn_drop(conn); } } else { @@ -2542,7 +2574,7 @@ static void hci_remote_name_evt(struct hci_dev *hdev, struct sk_buff *skb) conn = hci_conn_hash_lookup_ba(hdev, ACL_LINK, &ev->bdaddr); - if (!test_bit(HCI_MGMT, &hdev->dev_flags)) + if (!hci_dev_test_flag(hdev, HCI_MGMT)) goto check_auth; if (ev->status == 0) @@ -2608,7 +2640,7 @@ static void hci_encrypt_change_evt(struct hci_dev *hdev, struct sk_buff *skb) * whenever the encryption procedure fails. */ if (ev->status && conn->type == LE_LINK) - set_bit(HCI_RPA_EXPIRED, &hdev->dev_flags); + hci_dev_set_flag(hdev, HCI_RPA_EXPIRED); clear_bit(HCI_CONN_ENCRYPT_PEND, &conn->flags); @@ -2626,15 +2658,15 @@ static void hci_encrypt_change_evt(struct hci_dev *hdev, struct sk_buff *skb) * connections that are not encrypted with AES-CCM * using a P-256 authenticated combination key. */ - if (test_bit(HCI_SC_ONLY, &hdev->dev_flags) && + if (hci_dev_test_flag(hdev, HCI_SC_ONLY) && (!test_bit(HCI_CONN_AES_CCM, &conn->flags) || conn->key_type != HCI_LK_AUTH_COMBINATION_P256)) { - hci_proto_connect_cfm(conn, HCI_ERROR_AUTH_FAILURE); + hci_connect_cfm(conn, HCI_ERROR_AUTH_FAILURE); hci_conn_drop(conn); goto unlock; } - hci_proto_connect_cfm(conn, ev->status); + hci_connect_cfm(conn, ev->status); hci_conn_drop(conn); } else hci_encrypt_cfm(conn, ev->status, ev->encrypt); @@ -2707,7 +2739,7 @@ static void hci_remote_features_evt(struct hci_dev *hdev, if (!hci_outgoing_auth_needed(hdev, conn)) { conn->state = BT_CONNECTED; - hci_proto_connect_cfm(conn, ev->status); + hci_connect_cfm(conn, ev->status); hci_conn_drop(conn); } @@ -2715,17 +2747,19 @@ unlock: hci_dev_unlock(hdev); } -static void hci_cmd_complete_evt(struct hci_dev *hdev, struct sk_buff *skb) +static void hci_cmd_complete_evt(struct hci_dev *hdev, struct sk_buff *skb, + u16 *opcode, u8 *status, + hci_req_complete_t *req_complete, + hci_req_complete_skb_t *req_complete_skb) { struct hci_ev_cmd_complete *ev = (void *) skb->data; - u8 status = skb->data[sizeof(*ev)]; - __u16 opcode; - skb_pull(skb, sizeof(*ev)); + *opcode = __le16_to_cpu(ev->opcode); + *status = skb->data[sizeof(*ev)]; - opcode = __le16_to_cpu(ev->opcode); + skb_pull(skb, sizeof(*ev)); - switch (opcode) { + switch (*opcode) { case HCI_OP_INQUIRY_CANCEL: hci_cc_inquiry_cancel(hdev, skb); break; @@ -3003,32 +3037,36 @@ static void hci_cmd_complete_evt(struct hci_dev *hdev, struct sk_buff *skb) break; default: - BT_DBG("%s opcode 0x%4.4x", hdev->name, opcode); + BT_DBG("%s opcode 0x%4.4x", hdev->name, *opcode); break; } - if (opcode != HCI_OP_NOP) + if (*opcode != HCI_OP_NOP) cancel_delayed_work(&hdev->cmd_timer); - hci_req_cmd_complete(hdev, opcode, status); - - if (ev->ncmd && !test_bit(HCI_RESET, &hdev->flags)) { + if (ev->ncmd && !test_bit(HCI_RESET, &hdev->flags)) atomic_set(&hdev->cmd_cnt, 1); - if (!skb_queue_empty(&hdev->cmd_q)) - queue_work(hdev->workqueue, &hdev->cmd_work); - } + + hci_req_cmd_complete(hdev, *opcode, *status, req_complete, + req_complete_skb); + + if (atomic_read(&hdev->cmd_cnt) && !skb_queue_empty(&hdev->cmd_q)) + queue_work(hdev->workqueue, &hdev->cmd_work); } -static void hci_cmd_status_evt(struct hci_dev *hdev, struct sk_buff *skb) +static void hci_cmd_status_evt(struct hci_dev *hdev, struct sk_buff *skb, + u16 *opcode, u8 *status, + hci_req_complete_t *req_complete, + hci_req_complete_skb_t *req_complete_skb) { struct hci_ev_cmd_status *ev = (void *) skb->data; - __u16 opcode; skb_pull(skb, sizeof(*ev)); - opcode = __le16_to_cpu(ev->opcode); + *opcode = __le16_to_cpu(ev->opcode); + *status = ev->status; - switch (opcode) { + switch (*opcode) { case HCI_OP_INQUIRY: hci_cs_inquiry(hdev, ev->status); break; @@ -3093,27 +3131,38 @@ static void hci_cmd_status_evt(struct hci_dev *hdev, struct sk_buff *skb) hci_cs_le_create_conn(hdev, ev->status); break; + case HCI_OP_LE_READ_REMOTE_FEATURES: + hci_cs_le_read_remote_features(hdev, ev->status); + break; + case HCI_OP_LE_START_ENC: hci_cs_le_start_enc(hdev, ev->status); break; default: - BT_DBG("%s opcode 0x%4.4x", hdev->name, opcode); + BT_DBG("%s opcode 0x%4.4x", hdev->name, *opcode); break; } - if (opcode != HCI_OP_NOP) + if (*opcode != HCI_OP_NOP) cancel_delayed_work(&hdev->cmd_timer); + if (ev->ncmd && !test_bit(HCI_RESET, &hdev->flags)) + atomic_set(&hdev->cmd_cnt, 1); + + /* Indicate request completion if the command failed. Also, if + * we're not waiting for a special event and we get a success + * command status we should try to flag the request as completed + * (since for this kind of commands there will not be a command + * complete event). + */ if (ev->status || (hdev->sent_cmd && !bt_cb(hdev->sent_cmd)->req.event)) - hci_req_cmd_complete(hdev, opcode, ev->status); + hci_req_cmd_complete(hdev, *opcode, ev->status, req_complete, + req_complete_skb); - if (ev->ncmd && !test_bit(HCI_RESET, &hdev->flags)) { - atomic_set(&hdev->cmd_cnt, 1); - if (!skb_queue_empty(&hdev->cmd_q)) - queue_work(hdev->workqueue, &hdev->cmd_work); - } + if (atomic_read(&hdev->cmd_cnt) && !skb_queue_empty(&hdev->cmd_q)) + queue_work(hdev->workqueue, &hdev->cmd_work); } static void hci_hardware_error_evt(struct hci_dev *hdev, struct sk_buff *skb) @@ -3331,11 +3380,11 @@ static void hci_pin_code_request_evt(struct hci_dev *hdev, struct sk_buff *skb) hci_conn_drop(conn); } - if (!test_bit(HCI_BONDABLE, &hdev->dev_flags) && + if (!hci_dev_test_flag(hdev, HCI_BONDABLE) && !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 (hci_dev_test_flag(hdev, HCI_MGMT)) { u8 secure; if (conn->pending_sec_level == BT_SECURITY_HIGH) @@ -3391,7 +3440,7 @@ static void hci_link_key_request_evt(struct hci_dev *hdev, struct sk_buff *skb) BT_DBG("%s", hdev->name); - if (!test_bit(HCI_MGMT, &hdev->dev_flags)) + if (!hci_dev_test_flag(hdev, HCI_MGMT)) return; hci_dev_lock(hdev); @@ -3465,7 +3514,7 @@ static void hci_link_key_notify_evt(struct hci_dev *hdev, struct sk_buff *skb) set_bit(HCI_CONN_NEW_LINK_KEY, &conn->flags); conn_set_key(conn, ev->key_type, conn->pin_length); - if (!test_bit(HCI_MGMT, &hdev->dev_flags)) + if (!hci_dev_test_flag(hdev, HCI_MGMT)) goto unlock; key = hci_add_link_key(hdev, conn, &ev->bdaddr, ev->link_key, @@ -3487,7 +3536,7 @@ static void hci_link_key_notify_evt(struct hci_dev *hdev, struct sk_buff *skb) * store_hint being 0). */ if (key->type == HCI_LK_DEBUG_COMBINATION && - !test_bit(HCI_KEEP_DEBUG_KEYS, &hdev->dev_flags)) { + !hci_dev_test_flag(hdev, HCI_KEEP_DEBUG_KEYS)) { list_del_rcu(&key->list); kfree_rcu(key, rcu); goto unlock; @@ -3570,7 +3619,7 @@ static void hci_inquiry_result_with_rssi_evt(struct hci_dev *hdev, if (!num_rsp) return; - if (test_bit(HCI_PERIODIC_INQ, &hdev->dev_flags)) + if (hci_dev_test_flag(hdev, HCI_PERIODIC_INQ)) return; hci_dev_lock(hdev); @@ -3679,7 +3728,7 @@ static void hci_remote_ext_features_evt(struct hci_dev *hdev, if (!hci_outgoing_auth_needed(hdev, conn)) { conn->state = BT_CONNECTED; - hci_proto_connect_cfm(conn, ev->status); + hci_connect_cfm(conn, ev->status); hci_conn_drop(conn); } @@ -3738,7 +3787,7 @@ static void hci_sync_conn_complete_evt(struct hci_dev *hdev, break; } - hci_proto_connect_cfm(conn, ev->status); + hci_connect_cfm(conn, ev->status); if (ev->status) hci_conn_del(conn); @@ -3776,7 +3825,7 @@ static void hci_extended_inquiry_result_evt(struct hci_dev *hdev, if (!num_rsp) return; - if (test_bit(HCI_PERIODIC_INQ, &hdev->dev_flags)) + if (hci_dev_test_flag(hdev, HCI_PERIODIC_INQ)) return; hci_dev_lock(hdev); @@ -3794,7 +3843,7 @@ static void hci_extended_inquiry_result_evt(struct hci_dev *hdev, data.rssi = info->rssi; data.ssp_mode = 0x01; - if (test_bit(HCI_MGMT, &hdev->dev_flags)) + if (hci_dev_test_flag(hdev, HCI_MGMT)) name_known = eir_has_data_type(info->data, sizeof(info->data), EIR_NAME_COMPLETE); @@ -3849,7 +3898,7 @@ static void hci_key_refresh_complete_evt(struct hci_dev *hdev, if (!ev->status) conn->state = BT_CONNECTED; - hci_proto_connect_cfm(conn, ev->status); + hci_connect_cfm(conn, ev->status); hci_conn_drop(conn); } else { hci_auth_cfm(conn, ev->status); @@ -3890,41 +3939,37 @@ static u8 bredr_oob_data_present(struct hci_conn *conn) if (!data) return 0x00; - if (conn->out || test_bit(HCI_CONN_REMOTE_OOB, &conn->flags)) { - if (bredr_sc_enabled(hdev)) { - /* When Secure Connections is enabled, then just - * return the present value stored with the OOB - * data. The stored value contains the right present - * information. However it can only be trusted when - * not in Secure Connection Only mode. - */ - if (!test_bit(HCI_SC_ONLY, &hdev->dev_flags)) - return data->present; - - /* When Secure Connections Only mode is enabled, then - * the P-256 values are required. If they are not - * available, then do not declare that OOB data is - * present. - */ - if (!memcmp(data->rand256, ZERO_KEY, 16) || - !memcmp(data->hash256, ZERO_KEY, 16)) - return 0x00; - - return 0x02; - } + if (bredr_sc_enabled(hdev)) { + /* When Secure Connections is enabled, then just + * return the present value stored with the OOB + * data. The stored value contains the right present + * information. However it can only be trusted when + * not in Secure Connection Only mode. + */ + if (!hci_dev_test_flag(hdev, HCI_SC_ONLY)) + return data->present; - /* When Secure Connections is not enabled or actually - * not supported by the hardware, then check that if - * P-192 data values are present. + /* When Secure Connections Only mode is enabled, then + * the P-256 values are required. If they are not + * available, then do not declare that OOB data is + * present. */ - if (!memcmp(data->rand192, ZERO_KEY, 16) || - !memcmp(data->hash192, ZERO_KEY, 16)) + if (!memcmp(data->rand256, ZERO_KEY, 16) || + !memcmp(data->hash256, ZERO_KEY, 16)) return 0x00; - return 0x01; + return 0x02; } - return 0x00; + /* When Secure Connections is not enabled or actually + * not supported by the hardware, then check that if + * P-192 data values are present. + */ + if (!memcmp(data->rand192, ZERO_KEY, 16) || + !memcmp(data->hash192, ZERO_KEY, 16)) + return 0x00; + + return 0x01; } static void hci_io_capa_request_evt(struct hci_dev *hdev, struct sk_buff *skb) @@ -3942,13 +3987,13 @@ static void hci_io_capa_request_evt(struct hci_dev *hdev, struct sk_buff *skb) hci_conn_hold(conn); - if (!test_bit(HCI_MGMT, &hdev->dev_flags)) + if (!hci_dev_test_flag(hdev, HCI_MGMT)) goto unlock; /* 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) || + if (hci_dev_test_flag(hdev, HCI_BONDABLE) || test_bit(HCI_CONN_AUTH_INITIATOR, &conn->flags) || (conn->remote_auth & ~0x01) == HCI_AT_NO_BONDING) { struct hci_cp_io_capability_reply cp; @@ -3974,7 +4019,7 @@ static void hci_io_capa_request_evt(struct hci_dev *hdev, struct sk_buff *skb) /* If we're not bondable, force one of the non-bondable * authentication requirement values. */ - if (!test_bit(HCI_BONDABLE, &hdev->dev_flags)) + if (!hci_dev_test_flag(hdev, HCI_BONDABLE)) conn->auth_type &= HCI_AT_NO_BONDING_MITM; cp.authentication = conn->auth_type; @@ -4011,8 +4056,6 @@ static void hci_io_capa_reply_evt(struct hci_dev *hdev, struct sk_buff *skb) conn->remote_cap = ev->capability; conn->remote_auth = ev->authentication; - if (ev->oob_data) - set_bit(HCI_CONN_REMOTE_OOB, &conn->flags); unlock: hci_dev_unlock(hdev); @@ -4029,7 +4072,7 @@ static void hci_user_confirm_request_evt(struct hci_dev *hdev, hci_dev_lock(hdev); - if (!test_bit(HCI_MGMT, &hdev->dev_flags)) + if (!hci_dev_test_flag(hdev, HCI_MGMT)) goto unlock; conn = hci_conn_hash_lookup_ba(hdev, ACL_LINK, &ev->bdaddr); @@ -4100,7 +4143,7 @@ static void hci_user_passkey_request_evt(struct hci_dev *hdev, BT_DBG("%s", hdev->name); - if (test_bit(HCI_MGMT, &hdev->dev_flags)) + if (hci_dev_test_flag(hdev, HCI_MGMT)) mgmt_user_passkey_request(hdev, &ev->bdaddr, ACL_LINK, 0); } @@ -4119,7 +4162,7 @@ static void hci_user_passkey_notify_evt(struct hci_dev *hdev, conn->passkey_notify = __le32_to_cpu(ev->passkey); conn->passkey_entered = 0; - if (test_bit(HCI_MGMT, &hdev->dev_flags)) + if (hci_dev_test_flag(hdev, HCI_MGMT)) mgmt_user_passkey_notify(hdev, &conn->dst, conn->type, conn->dst_type, conn->passkey_notify, conn->passkey_entered); @@ -4157,7 +4200,7 @@ static void hci_keypress_notify_evt(struct hci_dev *hdev, struct sk_buff *skb) return; } - if (test_bit(HCI_MGMT, &hdev->dev_flags)) + if (hci_dev_test_flag(hdev, HCI_MGMT)) mgmt_user_passkey_notify(hdev, &conn->dst, conn->type, conn->dst_type, conn->passkey_notify, conn->passkey_entered); @@ -4226,7 +4269,7 @@ static void hci_remote_oob_data_request_evt(struct hci_dev *hdev, hci_dev_lock(hdev); - if (!test_bit(HCI_MGMT, &hdev->dev_flags)) + if (!hci_dev_test_flag(hdev, HCI_MGMT)) goto unlock; data = hci_find_remote_oob_data(hdev, &ev->bdaddr, BDADDR_BREDR); @@ -4243,7 +4286,7 @@ static void hci_remote_oob_data_request_evt(struct hci_dev *hdev, struct hci_cp_remote_oob_ext_data_reply cp; bacpy(&cp.bdaddr, &ev->bdaddr); - if (test_bit(HCI_SC_ONLY, &hdev->dev_flags)) { + if (hci_dev_test_flag(hdev, HCI_SC_ONLY)) { memset(cp.hash192, 0, sizeof(cp.hash192)); memset(cp.rand192, 0, sizeof(cp.rand192)); } else { @@ -4409,7 +4452,7 @@ static void hci_le_conn_complete_evt(struct hci_dev *hdev, struct sk_buff *skb) /* 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); + hci_dev_clear_flag(hdev, HCI_LE_ADV); conn = hci_conn_hash_lookup_state(hdev, LE_LINK, BT_CONNECT); if (!conn) { @@ -4432,7 +4475,7 @@ static void hci_le_conn_complete_evt(struct hci_dev *hdev, struct sk_buff *skb) if (conn->out) { conn->resp_addr_type = ev->bdaddr_type; bacpy(&conn->resp_addr, &ev->bdaddr); - if (test_bit(HCI_PRIVACY, &hdev->dev_flags)) { + if (hci_dev_test_flag(hdev, HCI_PRIVACY)) { conn->init_addr_type = ADDR_LE_DEV_RANDOM; bacpy(&conn->init_addr, &hdev->rpa); } else { @@ -4503,7 +4546,7 @@ static void hci_le_conn_complete_evt(struct hci_dev *hdev, struct sk_buff *skb) conn->sec_level = BT_SECURITY_LOW; conn->handle = __le16_to_cpu(ev->handle); - conn->state = BT_CONNECTED; + conn->state = BT_CONFIG; conn->le_conn_interval = le16_to_cpu(ev->interval); conn->le_conn_latency = le16_to_cpu(ev->latency); @@ -4512,7 +4555,33 @@ static void hci_le_conn_complete_evt(struct hci_dev *hdev, struct sk_buff *skb) hci_debugfs_create_conn(conn); hci_conn_add_sysfs(conn); - hci_proto_connect_cfm(conn, ev->status); + if (!ev->status) { + /* The remote features procedure is defined for master + * role only. So only in case of an initiated connection + * request the remote features. + * + * If the local controller supports slave-initiated features + * exchange, then requesting the remote features in slave + * role is possible. Otherwise just transition into the + * connected state without requesting the remote features. + */ + if (conn->out || + (hdev->le_features[0] & HCI_LE_SLAVE_FEATURES)) { + struct hci_cp_le_read_remote_features cp; + + cp.handle = __cpu_to_le16(conn->handle); + + hci_send_cmd(hdev, HCI_OP_LE_READ_REMOTE_FEATURES, + sizeof(cp), &cp); + + hci_conn_hold(conn); + } else { + conn->state = BT_CONNECTED; + hci_connect_cfm(conn, ev->status); + } + } else { + hci_connect_cfm(conn, ev->status); + } params = hci_pend_le_action_lookup(&hdev->pend_le_conns, &conn->dst, conn->dst_type); @@ -4658,7 +4727,7 @@ static void process_adv_report(struct hci_dev *hdev, u8 type, bdaddr_t *bdaddr, /* If the controller is not using resolvable random * addresses, then this report can be ignored. */ - if (!test_bit(HCI_PRIVACY, &hdev->dev_flags)) + if (!hci_dev_test_flag(hdev, HCI_PRIVACY)) return; /* If the local IRK of the controller does not match @@ -4814,6 +4883,48 @@ static void hci_le_adv_report_evt(struct hci_dev *hdev, struct sk_buff *skb) hci_dev_unlock(hdev); } +static void hci_le_remote_feat_complete_evt(struct hci_dev *hdev, + struct sk_buff *skb) +{ + struct hci_ev_le_remote_feat_complete *ev = (void *)skb->data; + struct hci_conn *conn; + + BT_DBG("%s status 0x%2.2x", hdev->name, ev->status); + + hci_dev_lock(hdev); + + conn = hci_conn_hash_lookup_handle(hdev, __le16_to_cpu(ev->handle)); + if (conn) { + if (!ev->status) + memcpy(conn->features[0], ev->features, 8); + + if (conn->state == BT_CONFIG) { + __u8 status; + + /* If the local controller supports slave-initiated + * features exchange, but the remote controller does + * not, then it is possible that the error code 0x1a + * for unsupported remote feature gets returned. + * + * In this specific case, allow the connection to + * transition into connected state and mark it as + * successful. + */ + if ((hdev->le_features[0] & HCI_LE_SLAVE_FEATURES) && + !conn->out && ev->status == 0x1a) + status = 0x00; + else + status = ev->status; + + conn->state = BT_CONNECTED; + hci_connect_cfm(conn, status); + hci_conn_drop(conn); + } + } + + hci_dev_unlock(hdev); +} + static void hci_le_ltk_request_evt(struct hci_dev *hdev, struct sk_buff *skb) { struct hci_ev_le_ltk_req *ev = (void *) skb->data; @@ -4987,6 +5098,10 @@ static void hci_le_meta_evt(struct hci_dev *hdev, struct sk_buff *skb) hci_le_adv_report_evt(hdev, skb); break; + case HCI_EV_LE_REMOTE_FEAT_COMPLETE: + hci_le_remote_feat_complete_evt(hdev, skb); + break; + case HCI_EV_LE_LTK_REQ: hci_le_ltk_request_evt(hdev, skb); break; @@ -5020,32 +5135,79 @@ static void hci_chan_selected_evt(struct hci_dev *hdev, struct sk_buff *skb) amp_read_loc_assoc_final_data(hdev, hcon); } -void hci_event_packet(struct hci_dev *hdev, struct sk_buff *skb) +static bool hci_get_cmd_complete(struct hci_dev *hdev, u16 opcode, + u8 event, struct sk_buff *skb) { - struct hci_event_hdr *hdr = (void *) skb->data; - __u8 event = hdr->evt; + struct hci_ev_cmd_complete *ev; + struct hci_event_hdr *hdr; - hci_dev_lock(hdev); + if (!skb) + return false; - /* Received events are (currently) only needed when a request is - * ongoing so avoid unnecessary memory allocation. - */ - if (hci_req_pending(hdev)) { - kfree_skb(hdev->recv_evt); - hdev->recv_evt = skb_clone(skb, GFP_KERNEL); + if (skb->len < sizeof(*hdr)) { + BT_ERR("Too short HCI event"); + return false; } - hci_dev_unlock(hdev); - + hdr = (void *) skb->data; skb_pull(skb, HCI_EVENT_HDR_SIZE); + if (event) { + if (hdr->evt != event) + return false; + return true; + } + + if (hdr->evt != HCI_EV_CMD_COMPLETE) { + BT_DBG("Last event is not cmd complete (0x%2.2x)", hdr->evt); + return false; + } + + if (skb->len < sizeof(*ev)) { + BT_ERR("Too short cmd_complete event"); + return false; + } + + ev = (void *) skb->data; + skb_pull(skb, sizeof(*ev)); + + if (opcode != __le16_to_cpu(ev->opcode)) { + BT_DBG("opcode doesn't match (0x%2.2x != 0x%2.2x)", opcode, + __le16_to_cpu(ev->opcode)); + return false; + } + + return true; +} + +void hci_event_packet(struct hci_dev *hdev, struct sk_buff *skb) +{ + struct hci_event_hdr *hdr = (void *) skb->data; + hci_req_complete_t req_complete = NULL; + hci_req_complete_skb_t req_complete_skb = NULL; + struct sk_buff *orig_skb = NULL; + u8 status = 0, event = hdr->evt, req_evt = 0; + u16 opcode = HCI_OP_NOP; + if (hdev->sent_cmd && bt_cb(hdev->sent_cmd)->req.event == event) { struct hci_command_hdr *cmd_hdr = (void *) hdev->sent_cmd->data; - u16 opcode = __le16_to_cpu(cmd_hdr->opcode); - - hci_req_cmd_complete(hdev, opcode, 0); + opcode = __le16_to_cpu(cmd_hdr->opcode); + hci_req_cmd_complete(hdev, opcode, status, &req_complete, + &req_complete_skb); + req_evt = event; } + /* If it looks like we might end up having to call + * req_complete_skb, store a pristine copy of the skb since the + * various handlers may modify the original one through + * skb_pull() calls, etc. + */ + if (req_complete_skb || event == HCI_EV_CMD_STATUS || + event == HCI_EV_CMD_COMPLETE) + orig_skb = skb_clone(skb, GFP_KERNEL); + + skb_pull(skb, HCI_EVENT_HDR_SIZE); + switch (event) { case HCI_EV_INQUIRY_COMPLETE: hci_inquiry_complete_evt(hdev, skb); @@ -5088,11 +5250,13 @@ void hci_event_packet(struct hci_dev *hdev, struct sk_buff *skb) break; case HCI_EV_CMD_COMPLETE: - hci_cmd_complete_evt(hdev, skb); + hci_cmd_complete_evt(hdev, skb, &opcode, &status, + &req_complete, &req_complete_skb); break; case HCI_EV_CMD_STATUS: - hci_cmd_status_evt(hdev, skb); + hci_cmd_status_evt(hdev, skb, &opcode, &status, &req_complete, + &req_complete_skb); break; case HCI_EV_HARDWARE_ERROR: @@ -5224,6 +5388,17 @@ void hci_event_packet(struct hci_dev *hdev, struct sk_buff *skb) break; } + if (req_complete) { + req_complete(hdev, status, opcode); + } else if (req_complete_skb) { + if (!hci_get_cmd_complete(hdev, opcode, req_evt, orig_skb)) { + kfree_skb(orig_skb); + orig_skb = NULL; + } + req_complete_skb(hdev, status, opcode, orig_skb); + } + + kfree_skb(orig_skb); kfree_skb(skb); hdev->stat.evt_rx++; } diff --git a/net/bluetooth/hci_request.c b/net/bluetooth/hci_request.c index b59f92c6df0c..d6025d6e6d59 100644 --- a/net/bluetooth/hci_request.c +++ b/net/bluetooth/hci_request.c @@ -34,7 +34,8 @@ void hci_req_init(struct hci_request *req, struct hci_dev *hdev) req->err = 0; } -int hci_req_run(struct hci_request *req, hci_req_complete_t complete) +static int req_run(struct hci_request *req, hci_req_complete_t complete, + hci_req_complete_skb_t complete_skb) { struct hci_dev *hdev = req->hdev; struct sk_buff *skb; @@ -56,6 +57,7 @@ int hci_req_run(struct hci_request *req, hci_req_complete_t complete) skb = skb_peek_tail(&req->cmd_q); bt_cb(skb)->req.complete = complete; + bt_cb(skb)->req.complete_skb = complete_skb; spin_lock_irqsave(&hdev->cmd_q.lock, flags); skb_queue_splice_tail(&req->cmd_q, &hdev->cmd_q); @@ -66,6 +68,16 @@ int hci_req_run(struct hci_request *req, hci_req_complete_t complete) return 0; } +int hci_req_run(struct hci_request *req, hci_req_complete_t complete) +{ + return req_run(req, complete, NULL); +} + +int hci_req_run_skb(struct hci_request *req, hci_req_complete_skb_t complete) +{ + return req_run(req, NULL, complete); +} + struct sk_buff *hci_prepare_cmd(struct hci_dev *hdev, u16 opcode, u32 plen, const void *param) { @@ -270,7 +282,7 @@ void hci_req_add_le_passive_scan(struct hci_request *req) * and 0x01 (whitelist enabled) use the new filter policies * 0x02 (no whitelist) and 0x03 (whitelist enabled). */ - if (test_bit(HCI_PRIVACY, &hdev->dev_flags) && + if (hci_dev_test_flag(hdev, HCI_PRIVACY) && (hdev->le_features[0] & HCI_LE_EXT_SCAN_POLICY)) filter_policy |= 0x02; @@ -304,10 +316,10 @@ 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_LE_ADV, &hdev->dev_flags) || + if (hci_dev_test_flag(hdev, HCI_LE_ADV) || hci_conn_hash_lookup_state(hdev, LE_LINK, BT_CONNECT)) { BT_DBG("Deferring random address update"); - set_bit(HCI_RPA_EXPIRED, &hdev->dev_flags); + hci_dev_set_flag(hdev, HCI_RPA_EXPIRED); return; } @@ -324,12 +336,12 @@ int hci_update_random_address(struct hci_request *req, bool require_privacy, * current RPA has expired or there is something else than * the current RPA in use, then generate a new one. */ - if (test_bit(HCI_PRIVACY, &hdev->dev_flags)) { + if (hci_dev_test_flag(hdev, HCI_PRIVACY)) { int to; *own_addr_type = ADDR_LE_DEV_RANDOM; - if (!test_and_clear_bit(HCI_RPA_EXPIRED, &hdev->dev_flags) && + if (!hci_dev_test_and_clear_flag(hdev, HCI_RPA_EXPIRED) && !bacmp(&hdev->random_addr, &hdev->rpa)) return 0; @@ -383,9 +395,9 @@ int hci_update_random_address(struct hci_request *req, bool require_privacy, * and a static address has been configured, then use that * address instead of the public BR/EDR address. */ - if (test_bit(HCI_FORCE_STATIC_ADDR, &hdev->dbg_flags) || + if (hci_dev_test_flag(hdev, HCI_FORCE_STATIC_ADDR) || !bacmp(&hdev->bdaddr, BDADDR_ANY) || - (!test_bit(HCI_BREDR_ENABLED, &hdev->dev_flags) && + (!hci_dev_test_flag(hdev, HCI_BREDR_ENABLED) && bacmp(&hdev->static_addr, BDADDR_ANY))) { *own_addr_type = ADDR_LE_DEV_RANDOM; if (bacmp(&hdev->static_addr, &hdev->random_addr)) @@ -425,7 +437,7 @@ void __hci_update_page_scan(struct hci_request *req) struct hci_dev *hdev = req->hdev; u8 scan; - if (!test_bit(HCI_BREDR_ENABLED, &hdev->dev_flags)) + if (!hci_dev_test_flag(hdev, HCI_BREDR_ENABLED)) return; if (!hdev_is_powered(hdev)) @@ -434,7 +446,7 @@ void __hci_update_page_scan(struct hci_request *req) if (mgmt_powering_down(hdev)) return; - if (test_bit(HCI_CONNECTABLE, &hdev->dev_flags) || + if (hci_dev_test_flag(hdev, HCI_CONNECTABLE) || disconnected_whitelist_entries(hdev)) scan = SCAN_PAGE; else @@ -443,7 +455,7 @@ void __hci_update_page_scan(struct hci_request *req) if (test_bit(HCI_PSCAN, &hdev->flags) == !!(scan & SCAN_PAGE)) return; - if (test_bit(HCI_DISCOVERABLE, &hdev->dev_flags)) + if (hci_dev_test_flag(hdev, HCI_DISCOVERABLE)) scan |= SCAN_INQUIRY; hci_req_add(req, HCI_OP_WRITE_SCAN_ENABLE, 1, &scan); @@ -471,14 +483,14 @@ void __hci_update_background_scan(struct hci_request *req) 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)) + hci_dev_test_flag(hdev, HCI_SETUP) || + hci_dev_test_flag(hdev, HCI_CONFIG) || + hci_dev_test_flag(hdev, HCI_AUTO_OFF) || + hci_dev_test_flag(hdev, HCI_UNREGISTER)) return; /* No point in doing scanning if LE support hasn't been enabled */ - if (!test_bit(HCI_LE_ENABLED, &hdev->dev_flags)) + if (!hci_dev_test_flag(hdev, HCI_LE_ENABLED)) return; /* If discovery is active don't interfere with it */ @@ -502,7 +514,7 @@ void __hci_update_background_scan(struct hci_request *req) */ /* If controller is not scanning we are done. */ - if (!test_bit(HCI_LE_SCAN, &hdev->dev_flags)) + if (!hci_dev_test_flag(hdev, HCI_LE_SCAN)) return; hci_req_add_le_scan_disable(req); @@ -524,7 +536,7 @@ void __hci_update_background_scan(struct hci_request *req) /* If controller is currently scanning, we stop it to ensure we * don't miss any advertising (due to duplicates filter). */ - if (test_bit(HCI_LE_SCAN, &hdev->dev_flags)) + if (hci_dev_test_flag(hdev, HCI_LE_SCAN)) hci_req_add_le_scan_disable(req); hci_req_add_le_passive_scan(req); diff --git a/net/bluetooth/hci_request.h b/net/bluetooth/hci_request.h index adf074d33544..bf6df92f42db 100644 --- a/net/bluetooth/hci_request.h +++ b/net/bluetooth/hci_request.h @@ -32,11 +32,14 @@ struct hci_request { void hci_req_init(struct hci_request *req, struct hci_dev *hdev); int hci_req_run(struct hci_request *req, hci_req_complete_t complete); +int hci_req_run_skb(struct hci_request *req, hci_req_complete_skb_t complete); void hci_req_add(struct hci_request *req, u16 opcode, u32 plen, const void *param); void hci_req_add_ev(struct hci_request *req, u16 opcode, u32 plen, const void *param, u8 event); -void hci_req_cmd_complete(struct hci_dev *hdev, u16 opcode, u8 status); +void hci_req_cmd_complete(struct hci_dev *hdev, u16 opcode, u8 status, + hci_req_complete_t *req_complete, + hci_req_complete_skb_t *req_complete_skb); struct sk_buff *hci_prepare_cmd(struct hci_dev *hdev, u16 opcode, u32 plen, const void *param); diff --git a/net/bluetooth/hci_sock.c b/net/bluetooth/hci_sock.c index 1d65c5be7c82..56f9edbf3d05 100644 --- a/net/bluetooth/hci_sock.c +++ b/net/bluetooth/hci_sock.c @@ -30,6 +30,12 @@ #include <net/bluetooth/bluetooth.h> #include <net/bluetooth/hci_core.h> #include <net/bluetooth/hci_mon.h> +#include <net/bluetooth/mgmt.h> + +#include "mgmt_util.h" + +static LIST_HEAD(mgmt_chan_list); +static DEFINE_MUTEX(mgmt_chan_list_lock); static atomic_t monitor_promisc = ATOMIC_INIT(0); @@ -44,11 +50,32 @@ struct hci_pinfo { struct hci_filter filter; __u32 cmsg_mask; unsigned short channel; + unsigned long flags; }; -static inline int hci_test_bit(int nr, void *addr) +void hci_sock_set_flag(struct sock *sk, int nr) +{ + set_bit(nr, &hci_pi(sk)->flags); +} + +void hci_sock_clear_flag(struct sock *sk, int nr) { - return *((__u32 *) addr + (nr >> 5)) & ((__u32) 1 << (nr & 31)); + clear_bit(nr, &hci_pi(sk)->flags); +} + +int hci_sock_test_flag(struct sock *sk, int nr) +{ + return test_bit(nr, &hci_pi(sk)->flags); +} + +unsigned short hci_sock_get_channel(struct sock *sk) +{ + return hci_pi(sk)->channel; +} + +static inline int hci_test_bit(int nr, const void *addr) +{ + return *((const __u32 *) addr + (nr >> 5)) & ((__u32) 1 << (nr & 31)); } /* Security filter */ @@ -183,54 +210,31 @@ void hci_send_to_sock(struct hci_dev *hdev, struct sk_buff *skb) kfree_skb(skb_copy); } -/* Send frame to control socket */ -void hci_send_to_control(struct sk_buff *skb, struct sock *skip_sk) +/* Send frame to sockets with specific channel */ +void hci_send_to_channel(unsigned short channel, struct sk_buff *skb, + int flag, struct sock *skip_sk) { struct sock *sk; - BT_DBG("len %d", skb->len); + BT_DBG("channel %u len %d", channel, skb->len); read_lock(&hci_sk_list.lock); sk_for_each(sk, &hci_sk_list.head) { struct sk_buff *nskb; - /* Skip the original socket */ - if (sk == skip_sk) - continue; - - if (sk->sk_state != BT_BOUND) - continue; - - if (hci_pi(sk)->channel != HCI_CHANNEL_CONTROL) + /* Ignore socket without the flag set */ + if (!hci_sock_test_flag(sk, flag)) continue; - nskb = skb_clone(skb, GFP_ATOMIC); - if (!nskb) + /* Skip the original socket */ + if (sk == skip_sk) continue; - if (sock_queue_rcv_skb(sk, nskb)) - kfree_skb(nskb); - } - - read_unlock(&hci_sk_list.lock); -} - -static void queue_monitor_skb(struct sk_buff *skb) -{ - struct sock *sk; - - BT_DBG("len %d", skb->len); - - read_lock(&hci_sk_list.lock); - - sk_for_each(sk, &hci_sk_list.head) { - struct sk_buff *nskb; - if (sk->sk_state != BT_BOUND) continue; - if (hci_pi(sk)->channel != HCI_CHANNEL_MONITOR) + if (hci_pi(sk)->channel != channel) continue; nskb = skb_clone(skb, GFP_ATOMIC); @@ -290,7 +294,8 @@ void hci_send_to_monitor(struct hci_dev *hdev, struct sk_buff *skb) hdr->index = cpu_to_le16(hdev->id); hdr->len = cpu_to_le16(skb->len); - queue_monitor_skb(skb_copy); + hci_send_to_channel(HCI_CHANNEL_MONITOR, skb_copy, + HCI_SOCK_TRUSTED, NULL); kfree_skb(skb_copy); } @@ -397,7 +402,8 @@ void hci_sock_dev_event(struct hci_dev *hdev, int event) skb = create_monitor_event(hdev, event); if (skb) { - queue_monitor_skb(skb); + hci_send_to_channel(HCI_CHANNEL_MONITOR, skb, + HCI_SOCK_TRUSTED, NULL); kfree_skb(skb); } } @@ -428,6 +434,56 @@ void hci_sock_dev_event(struct hci_dev *hdev, int event) } } +static struct hci_mgmt_chan *__hci_mgmt_chan_find(unsigned short channel) +{ + struct hci_mgmt_chan *c; + + list_for_each_entry(c, &mgmt_chan_list, list) { + if (c->channel == channel) + return c; + } + + return NULL; +} + +static struct hci_mgmt_chan *hci_mgmt_chan_find(unsigned short channel) +{ + struct hci_mgmt_chan *c; + + mutex_lock(&mgmt_chan_list_lock); + c = __hci_mgmt_chan_find(channel); + mutex_unlock(&mgmt_chan_list_lock); + + return c; +} + +int hci_mgmt_chan_register(struct hci_mgmt_chan *c) +{ + if (c->channel < HCI_CHANNEL_CONTROL) + return -EINVAL; + + mutex_lock(&mgmt_chan_list_lock); + if (__hci_mgmt_chan_find(c->channel)) { + mutex_unlock(&mgmt_chan_list_lock); + return -EALREADY; + } + + list_add_tail(&c->list, &mgmt_chan_list); + + mutex_unlock(&mgmt_chan_list_lock); + + return 0; +} +EXPORT_SYMBOL(hci_mgmt_chan_register); + +void hci_mgmt_chan_unregister(struct hci_mgmt_chan *c) +{ + mutex_lock(&mgmt_chan_list_lock); + list_del(&c->list); + mutex_unlock(&mgmt_chan_list_lock); +} +EXPORT_SYMBOL(hci_mgmt_chan_unregister); + static int hci_sock_release(struct socket *sock) { struct sock *sk = sock->sk; @@ -448,7 +504,7 @@ static int hci_sock_release(struct socket *sock) if (hdev) { if (hci_pi(sk)->channel == HCI_CHANNEL_USER) { mgmt_index_added(hdev); - clear_bit(HCI_USER_CHANNEL, &hdev->dev_flags); + hci_dev_clear_flag(hdev, HCI_USER_CHANNEL); hci_dev_close(hdev->id); } @@ -508,10 +564,10 @@ static int hci_sock_bound_ioctl(struct sock *sk, unsigned int cmd, if (!hdev) return -EBADFD; - if (test_bit(HCI_USER_CHANNEL, &hdev->dev_flags)) + if (hci_dev_test_flag(hdev, HCI_USER_CHANNEL)) return -EBUSY; - if (test_bit(HCI_UNCONFIGURED, &hdev->dev_flags)) + if (hci_dev_test_flag(hdev, HCI_UNCONFIGURED)) return -EOPNOTSUPP; if (hdev->dev_type != HCI_BREDR) @@ -687,14 +743,14 @@ 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_CONFIG, &hdev->dev_flags)) { + hci_dev_test_flag(hdev, HCI_SETUP) || + hci_dev_test_flag(hdev, HCI_CONFIG)) { err = -EBUSY; hci_dev_put(hdev); goto done; } - if (test_and_set_bit(HCI_USER_CHANNEL, &hdev->dev_flags)) { + if (hci_dev_test_and_set_flag(hdev, HCI_USER_CHANNEL)) { err = -EUSERS; hci_dev_put(hdev); goto done; @@ -704,7 +760,7 @@ static int hci_sock_bind(struct socket *sock, struct sockaddr *addr, err = hci_dev_open(hdev->id); if (err) { - clear_bit(HCI_USER_CHANNEL, &hdev->dev_flags); + hci_dev_clear_flag(hdev, HCI_USER_CHANNEL); mgmt_index_added(hdev); hci_dev_put(hdev); goto done; @@ -715,38 +771,62 @@ static int hci_sock_bind(struct socket *sock, struct sockaddr *addr, hci_pi(sk)->hdev = hdev; break; - case HCI_CHANNEL_CONTROL: + case HCI_CHANNEL_MONITOR: if (haddr.hci_dev != HCI_DEV_NONE) { err = -EINVAL; goto done; } - if (!capable(CAP_NET_ADMIN)) { + if (!capable(CAP_NET_RAW)) { err = -EPERM; goto done; } + /* The monitor interface is restricted to CAP_NET_RAW + * capabilities and with that implicitly trusted. + */ + hci_sock_set_flag(sk, HCI_SOCK_TRUSTED); + + send_monitor_replay(sk); + + atomic_inc(&monitor_promisc); break; - case HCI_CHANNEL_MONITOR: - if (haddr.hci_dev != HCI_DEV_NONE) { + default: + if (!hci_mgmt_chan_find(haddr.hci_channel)) { err = -EINVAL; goto done; } - if (!capable(CAP_NET_RAW)) { - err = -EPERM; + if (haddr.hci_dev != HCI_DEV_NONE) { + err = -EINVAL; goto done; } - send_monitor_replay(sk); - - atomic_inc(&monitor_promisc); + /* Users with CAP_NET_ADMIN capabilities are allowed + * access to all management commands and events. For + * untrusted users the interface is restricted and + * also only untrusted events are sent. + */ + if (capable(CAP_NET_ADMIN)) + hci_sock_set_flag(sk, HCI_SOCK_TRUSTED); + + /* At the moment the index and unconfigured index events + * are enabled unconditionally. Setting them on each + * socket when binding keeps this functionality. They + * however might be cleared later and then sending of these + * events will be disabled, but that is then intentional. + * + * This also enables generic events that are safe to be + * received by untrusted users. Example for such events + * are changes to settings, class of device, name etc. + */ + if (haddr.hci_channel == HCI_CHANNEL_CONTROL) { + hci_sock_set_flag(sk, HCI_MGMT_INDEX_EVENTS); + hci_sock_set_flag(sk, HCI_MGMT_UNCONF_INDEX_EVENTS); + hci_sock_set_flag(sk, HCI_MGMT_GENERIC_EVENTS); + } break; - - default: - err = -EINVAL; - goto done; } @@ -826,8 +906,8 @@ static void hci_sock_cmsg(struct sock *sk, struct msghdr *msg, } } -static int hci_sock_recvmsg(struct kiocb *iocb, struct socket *sock, - struct msghdr *msg, size_t len, int flags) +static int hci_sock_recvmsg(struct socket *sock, struct msghdr *msg, size_t len, + int flags) { int noblock = flags & MSG_DONTWAIT; struct sock *sk = sock->sk; @@ -860,10 +940,13 @@ static int hci_sock_recvmsg(struct kiocb *iocb, struct socket *sock, hci_sock_cmsg(sk, msg, skb); break; case HCI_CHANNEL_USER: - case HCI_CHANNEL_CONTROL: case HCI_CHANNEL_MONITOR: sock_recv_timestamp(msg, sk, skb); break; + default: + if (hci_mgmt_chan_find(hci_pi(sk)->channel)) + sock_recv_timestamp(msg, sk, skb); + break; } skb_free_datagram(sk, skb); @@ -871,10 +954,122 @@ static int hci_sock_recvmsg(struct kiocb *iocb, struct socket *sock, return err ? : copied; } -static int hci_sock_sendmsg(struct kiocb *iocb, struct socket *sock, - struct msghdr *msg, size_t len) +static int hci_mgmt_cmd(struct hci_mgmt_chan *chan, struct sock *sk, + struct msghdr *msg, size_t msglen) +{ + void *buf; + u8 *cp; + struct mgmt_hdr *hdr; + u16 opcode, index, len; + struct hci_dev *hdev = NULL; + const struct hci_mgmt_handler *handler; + bool var_len, no_hdev; + int err; + + BT_DBG("got %zu bytes", msglen); + + if (msglen < sizeof(*hdr)) + return -EINVAL; + + buf = kmalloc(msglen, GFP_KERNEL); + if (!buf) + return -ENOMEM; + + if (memcpy_from_msg(buf, msg, msglen)) { + err = -EFAULT; + goto done; + } + + hdr = buf; + opcode = __le16_to_cpu(hdr->opcode); + index = __le16_to_cpu(hdr->index); + len = __le16_to_cpu(hdr->len); + + if (len != msglen - sizeof(*hdr)) { + err = -EINVAL; + goto done; + } + + if (opcode >= chan->handler_count || + chan->handlers[opcode].func == NULL) { + BT_DBG("Unknown op %u", opcode); + err = mgmt_cmd_status(sk, index, opcode, + MGMT_STATUS_UNKNOWN_COMMAND); + goto done; + } + + handler = &chan->handlers[opcode]; + + if (!hci_sock_test_flag(sk, HCI_SOCK_TRUSTED) && + !(handler->flags & HCI_MGMT_UNTRUSTED)) { + err = mgmt_cmd_status(sk, index, opcode, + MGMT_STATUS_PERMISSION_DENIED); + goto done; + } + + if (index != MGMT_INDEX_NONE) { + hdev = hci_dev_get(index); + if (!hdev) { + err = mgmt_cmd_status(sk, index, opcode, + MGMT_STATUS_INVALID_INDEX); + goto done; + } + + if (hci_dev_test_flag(hdev, HCI_SETUP) || + hci_dev_test_flag(hdev, HCI_CONFIG) || + hci_dev_test_flag(hdev, HCI_USER_CHANNEL)) { + err = mgmt_cmd_status(sk, index, opcode, + MGMT_STATUS_INVALID_INDEX); + goto done; + } + + if (hci_dev_test_flag(hdev, HCI_UNCONFIGURED) && + !(handler->flags & HCI_MGMT_UNCONFIGURED)) { + err = mgmt_cmd_status(sk, index, opcode, + MGMT_STATUS_INVALID_INDEX); + goto done; + } + } + + no_hdev = (handler->flags & HCI_MGMT_NO_HDEV); + if (no_hdev != !hdev) { + err = mgmt_cmd_status(sk, index, opcode, + MGMT_STATUS_INVALID_INDEX); + goto done; + } + + var_len = (handler->flags & HCI_MGMT_VAR_LEN); + if ((var_len && len < handler->data_len) || + (!var_len && len != handler->data_len)) { + err = mgmt_cmd_status(sk, index, opcode, + MGMT_STATUS_INVALID_PARAMS); + goto done; + } + + if (hdev && chan->hdev_init) + chan->hdev_init(sk, hdev); + + cp = buf + sizeof(*hdr); + + err = handler->func(sk, hdev, cp, len); + if (err < 0) + goto done; + + err = msglen; + +done: + if (hdev) + hci_dev_put(hdev); + + kfree(buf); + return err; +} + +static int hci_sock_sendmsg(struct socket *sock, struct msghdr *msg, + size_t len) { struct sock *sk = sock->sk; + struct hci_mgmt_chan *chan; struct hci_dev *hdev; struct sk_buff *skb; int err; @@ -896,14 +1091,18 @@ static int hci_sock_sendmsg(struct kiocb *iocb, struct socket *sock, case HCI_CHANNEL_RAW: case HCI_CHANNEL_USER: break; - case HCI_CHANNEL_CONTROL: - err = mgmt_control(sk, msg, len); - goto done; case HCI_CHANNEL_MONITOR: err = -EOPNOTSUPP; goto done; default: - err = -EINVAL; + mutex_lock(&mgmt_chan_list_lock); + chan = __hci_mgmt_chan_find(hci_pi(sk)->channel); + if (chan) + err = hci_mgmt_cmd(chan, sk, msg, len); + else + err = -EINVAL; + + mutex_unlock(&mgmt_chan_list_lock); goto done; } diff --git a/net/bluetooth/hidp/core.c b/net/bluetooth/hidp/core.c index 07348e142f16..9070dfd6b4ad 100644 --- a/net/bluetooth/hidp/core.c +++ b/net/bluetooth/hidp/core.c @@ -70,10 +70,11 @@ static void hidp_session_terminate(struct hidp_session *s); static void hidp_copy_session(struct hidp_session *session, struct hidp_conninfo *ci) { + u32 valid_flags = 0; memset(ci, 0, sizeof(*ci)); bacpy(&ci->bdaddr, &session->bdaddr); - ci->flags = session->flags; + ci->flags = session->flags & valid_flags; ci->state = BT_CONNECTED; if (session->input) { @@ -907,7 +908,7 @@ static int hidp_session_new(struct hidp_session **out, const bdaddr_t *bdaddr, kref_init(&session->ref); atomic_set(&session->state, HIDP_SESSION_IDLING); init_waitqueue_head(&session->state_queue); - session->flags = req->flags & (1 << HIDP_BLUETOOTH_VENDOR_ID); + session->flags = req->flags & BIT(HIDP_BLUETOOTH_VENDOR_ID); /* connection management */ bacpy(&session->bdaddr, bdaddr); @@ -1312,6 +1313,8 @@ int hidp_connection_add(struct hidp_connadd_req *req, struct socket *ctrl_sock, struct socket *intr_sock) { + u32 valid_flags = BIT(HIDP_VIRTUAL_CABLE_UNPLUG) | + BIT(HIDP_BOOT_PROTOCOL_MODE); struct hidp_session *session; struct l2cap_conn *conn; struct l2cap_chan *chan; @@ -1321,6 +1324,9 @@ int hidp_connection_add(struct hidp_connadd_req *req, if (ret) return ret; + if (req->flags & ~valid_flags) + return -EINVAL; + chan = l2cap_pi(ctrl_sock->sk)->chan; conn = NULL; l2cap_chan_lock(chan); @@ -1351,13 +1357,17 @@ out_conn: int hidp_connection_del(struct hidp_conndel_req *req) { + u32 valid_flags = BIT(HIDP_VIRTUAL_CABLE_UNPLUG); struct hidp_session *session; + if (req->flags & ~valid_flags) + return -EINVAL; + session = hidp_session_find(&req->bdaddr); if (!session) return -ENOENT; - if (req->flags & (1 << HIDP_VIRTUAL_CABLE_UNPLUG)) + if (req->flags & BIT(HIDP_VIRTUAL_CABLE_UNPLUG)) hidp_send_ctrl_message(session, HIDP_TRANS_HID_CONTROL | HIDP_CTRL_VIRTUAL_CABLE_UNPLUG, diff --git a/net/bluetooth/l2cap_core.c b/net/bluetooth/l2cap_core.c index 6ba33f9631e8..dad419782a12 100644 --- a/net/bluetooth/l2cap_core.c +++ b/net/bluetooth/l2cap_core.c @@ -292,7 +292,7 @@ static struct sk_buff *l2cap_ertm_seq_in_queue(struct sk_buff_head *head, struct sk_buff *skb; skb_queue_walk(head, skb) { - if (bt_cb(skb)->control.txseq == seq) + if (bt_cb(skb)->l2cap.txseq == seq) return skb; } @@ -954,11 +954,11 @@ static inline void __unpack_control(struct l2cap_chan *chan, { if (test_bit(FLAG_EXT_CTRL, &chan->flags)) { __unpack_extended_control(get_unaligned_le32(skb->data), - &bt_cb(skb)->control); + &bt_cb(skb)->l2cap); skb_pull(skb, L2CAP_EXT_CTRL_SIZE); } else { __unpack_enhanced_control(get_unaligned_le16(skb->data), - &bt_cb(skb)->control); + &bt_cb(skb)->l2cap); skb_pull(skb, L2CAP_ENH_CTRL_SIZE); } } @@ -1200,8 +1200,8 @@ static void l2cap_move_setup(struct l2cap_chan *chan) chan->retry_count = 0; skb_queue_walk(&chan->tx_q, skb) { - if (bt_cb(skb)->control.retries) - bt_cb(skb)->control.retries = 1; + if (bt_cb(skb)->l2cap.retries) + bt_cb(skb)->l2cap.retries = 1; else break; } @@ -1244,6 +1244,13 @@ static void l2cap_move_done(struct l2cap_chan *chan) static void l2cap_chan_ready(struct l2cap_chan *chan) { + /* The channel may have already been flagged as connected in + * case of receiving data before the L2CAP info req/rsp + * procedure is complete. + */ + if (chan->state == BT_CONNECTED) + return; + /* This clears all conf flags, including CONF_NOT_COMPLETE */ chan->conf_state = 0; __clear_chan_timer(chan); @@ -1839,8 +1846,8 @@ static void l2cap_streaming_send(struct l2cap_chan *chan, skb = skb_dequeue(&chan->tx_q); - bt_cb(skb)->control.retries = 1; - control = &bt_cb(skb)->control; + bt_cb(skb)->l2cap.retries = 1; + control = &bt_cb(skb)->l2cap; control->reqseq = 0; control->txseq = chan->next_tx_seq; @@ -1884,8 +1891,8 @@ static int l2cap_ertm_send(struct l2cap_chan *chan) skb = chan->tx_send_head; - bt_cb(skb)->control.retries = 1; - control = &bt_cb(skb)->control; + bt_cb(skb)->l2cap.retries = 1; + control = &bt_cb(skb)->l2cap; if (test_and_clear_bit(CONN_SEND_FBIT, &chan->conn_state)) control->final = 1; @@ -1956,11 +1963,11 @@ static void l2cap_ertm_resend(struct l2cap_chan *chan) continue; } - bt_cb(skb)->control.retries++; - control = bt_cb(skb)->control; + bt_cb(skb)->l2cap.retries++; + control = bt_cb(skb)->l2cap; if (chan->max_tx != 0 && - bt_cb(skb)->control.retries > chan->max_tx) { + bt_cb(skb)->l2cap.retries > chan->max_tx) { BT_DBG("Retry limit exceeded (%d)", chan->max_tx); l2cap_send_disconn_req(chan, ECONNRESET); l2cap_seq_list_clear(&chan->retrans_list); @@ -2038,7 +2045,7 @@ static void l2cap_retransmit_all(struct l2cap_chan *chan, if (chan->unacked_frames) { skb_queue_walk(&chan->tx_q, skb) { - if (bt_cb(skb)->control.txseq == control->reqseq || + if (bt_cb(skb)->l2cap.txseq == control->reqseq || skb == chan->tx_send_head) break; } @@ -2048,7 +2055,7 @@ static void l2cap_retransmit_all(struct l2cap_chan *chan, break; l2cap_seq_list_append(&chan->retrans_list, - bt_cb(skb)->control.txseq); + bt_cb(skb)->l2cap.txseq); } l2cap_ertm_resend(chan); @@ -2260,8 +2267,8 @@ static struct sk_buff *l2cap_create_iframe_pdu(struct l2cap_chan *chan, return ERR_PTR(err); } - bt_cb(skb)->control.fcs = chan->fcs; - bt_cb(skb)->control.retries = 0; + bt_cb(skb)->l2cap.fcs = chan->fcs; + bt_cb(skb)->l2cap.retries = 0; return skb; } @@ -2314,7 +2321,7 @@ static int l2cap_segment_sdu(struct l2cap_chan *chan, return PTR_ERR(skb); } - bt_cb(skb)->control.sar = sar; + bt_cb(skb)->l2cap.sar = sar; __skb_queue_tail(seg_queue, skb); len -= pdu_len; @@ -2849,7 +2856,7 @@ static void l2cap_raw_recv(struct l2cap_conn *conn, struct sk_buff *skb) continue; /* Don't send frame to the channel it came from */ - if (bt_cb(skb)->chan == chan) + if (bt_cb(skb)->l2cap.chan == chan) continue; nskb = skb_clone(skb, GFP_KERNEL); @@ -3893,7 +3900,7 @@ static int l2cap_connect_req(struct l2cap_conn *conn, return -EPROTO; hci_dev_lock(hdev); - if (test_bit(HCI_MGMT, &hdev->dev_flags) && + if (hci_dev_test_flag(hdev, HCI_MGMT) && !test_and_set_bit(HCI_CONN_MGMT_CONNECTED, &hcon->flags)) mgmt_device_connected(hdev, hcon, 0, NULL, 0); hci_dev_unlock(hdev); @@ -5911,7 +5918,7 @@ static int l2cap_rx_queued_iframes(struct l2cap_chan *chan) skb_unlink(skb, &chan->srej_q); chan->buffer_seq = __next_seq(chan, chan->buffer_seq); - err = l2cap_reassemble_sdu(chan, skb, &bt_cb(skb)->control); + err = l2cap_reassemble_sdu(chan, skb, &bt_cb(skb)->l2cap); if (err) break; } @@ -5945,7 +5952,7 @@ static void l2cap_handle_srej(struct l2cap_chan *chan, return; } - if (chan->max_tx != 0 && bt_cb(skb)->control.retries >= chan->max_tx) { + if (chan->max_tx != 0 && bt_cb(skb)->l2cap.retries >= chan->max_tx) { BT_DBG("Retry limit exceeded (%d)", chan->max_tx); l2cap_send_disconn_req(chan, ECONNRESET); return; @@ -5998,7 +6005,7 @@ static void l2cap_handle_rej(struct l2cap_chan *chan, skb = l2cap_ertm_seq_in_queue(&chan->tx_q, control->reqseq); if (chan->max_tx && skb && - bt_cb(skb)->control.retries >= chan->max_tx) { + bt_cb(skb)->l2cap.retries >= chan->max_tx) { BT_DBG("Retry limit exceeded (%d)", chan->max_tx); l2cap_send_disconn_req(chan, ECONNRESET); return; @@ -6558,7 +6565,7 @@ static int l2cap_stream_rx(struct l2cap_chan *chan, struct l2cap_ctrl *control, static int l2cap_data_rcv(struct l2cap_chan *chan, struct sk_buff *skb) { - struct l2cap_ctrl *control = &bt_cb(skb)->control; + struct l2cap_ctrl *control = &bt_cb(skb)->l2cap; u16 len; u8 event; @@ -6785,6 +6792,13 @@ static void l2cap_data_channel(struct l2cap_conn *conn, u16 cid, BT_DBG("chan %p, len %d", chan, skb->len); + /* If we receive data on a fixed channel before the info req/rsp + * procdure is done simply assume that the channel is supported + * and mark it as ready. + */ + if (chan->chan_type == L2CAP_CHAN_FIXED) + l2cap_chan_ready(chan); + if (chan->state != BT_CONNECTED) goto drop; @@ -6850,8 +6864,8 @@ static void l2cap_conless_channel(struct l2cap_conn *conn, __le16 psm, goto drop; /* Store remote BD_ADDR and PSM for msg_name */ - bacpy(&bt_cb(skb)->bdaddr, &hcon->dst); - bt_cb(skb)->psm = psm; + bacpy(&bt_cb(skb)->l2cap.bdaddr, &hcon->dst); + bt_cb(skb)->l2cap.psm = psm; if (!chan->ops->recv(chan, skb)) { l2cap_chan_put(chan); @@ -6973,12 +6987,12 @@ static struct l2cap_conn *l2cap_conn_add(struct hci_conn *hcon) conn->local_fixed_chan = L2CAP_FC_SIG_BREDR | L2CAP_FC_CONNLESS; if (hcon->type == ACL_LINK && - test_bit(HCI_HS_ENABLED, &hcon->hdev->dev_flags)) + hci_dev_test_flag(hcon->hdev, HCI_HS_ENABLED)) conn->local_fixed_chan |= L2CAP_FC_A2MP; - if (test_bit(HCI_LE_ENABLED, &hcon->hdev->dev_flags) && + if (hci_dev_test_flag(hcon->hdev, HCI_LE_ENABLED) && (bredr_sc_enabled(hcon->hdev) || - test_bit(HCI_FORCE_BREDR_SMP, &hcon->hdev->dbg_flags))) + hci_dev_test_flag(hcon->hdev, HCI_FORCE_BREDR_SMP))) conn->local_fixed_chan |= L2CAP_FC_SMP_BREDR; mutex_init(&conn->ident_lock); @@ -7098,7 +7112,7 @@ 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)) + if (hci_dev_test_flag(hdev, HCI_ADVERTISING)) role = HCI_ROLE_SLAVE; else role = HCI_ROLE_MASTER; @@ -7238,13 +7252,16 @@ static struct l2cap_chan *l2cap_global_fixed_chan(struct l2cap_chan *c, return NULL; } -void l2cap_connect_cfm(struct hci_conn *hcon, u8 status) +static void l2cap_connect_cfm(struct hci_conn *hcon, u8 status) { struct hci_dev *hdev = hcon->hdev; struct l2cap_conn *conn; struct l2cap_chan *pchan; u8 dst_type; + if (hcon->type != ACL_LINK && hcon->type != LE_LINK) + return; + BT_DBG("hcon %p bdaddr %pMR status %d", hcon, &hcon->dst, status); if (status) { @@ -7307,8 +7324,11 @@ int l2cap_disconn_ind(struct hci_conn *hcon) return conn->disc_reason; } -void l2cap_disconn_cfm(struct hci_conn *hcon, u8 reason) +static void l2cap_disconn_cfm(struct hci_conn *hcon, u8 reason) { + if (hcon->type != ACL_LINK && hcon->type != LE_LINK) + return; + BT_DBG("hcon %p reason %d", hcon, reason); l2cap_conn_del(hcon, bt_to_errno(reason)); @@ -7331,13 +7351,13 @@ static inline void l2cap_check_encryption(struct l2cap_chan *chan, u8 encrypt) } } -int l2cap_security_cfm(struct hci_conn *hcon, u8 status, u8 encrypt) +static void l2cap_security_cfm(struct hci_conn *hcon, u8 status, u8 encrypt) { struct l2cap_conn *conn = hcon->l2cap_data; struct l2cap_chan *chan; if (!conn) - return 0; + return; BT_DBG("conn %p status 0x%2.2x encrypt %u", conn, status, encrypt); @@ -7420,8 +7440,6 @@ int l2cap_security_cfm(struct hci_conn *hcon, u8 status, u8 encrypt) } mutex_unlock(&conn->chan_lock); - - return 0; } int l2cap_recv_acldata(struct hci_conn *hcon, struct sk_buff *skb, u16 flags) @@ -7529,6 +7547,13 @@ drop: return 0; } +static struct hci_cb l2cap_cb = { + .name = "L2CAP", + .connect_cfm = l2cap_connect_cfm, + .disconn_cfm = l2cap_disconn_cfm, + .security_cfm = l2cap_security_cfm, +}; + static int l2cap_debugfs_show(struct seq_file *f, void *p) { struct l2cap_chan *c; @@ -7570,6 +7595,8 @@ int __init l2cap_init(void) if (err < 0) return err; + hci_register_cb(&l2cap_cb); + if (IS_ERR_OR_NULL(bt_debugfs)) return 0; @@ -7587,6 +7614,7 @@ int __init l2cap_init(void) void l2cap_exit(void) { debugfs_remove(l2cap_debugfs); + hci_unregister_cb(&l2cap_cb); l2cap_cleanup_sockets(); } diff --git a/net/bluetooth/l2cap_sock.c b/net/bluetooth/l2cap_sock.c index 60694f0f4c73..a7278f05eafb 100644 --- a/net/bluetooth/l2cap_sock.c +++ b/net/bluetooth/l2cap_sock.c @@ -944,8 +944,8 @@ static int l2cap_sock_setsockopt(struct socket *sock, int level, int optname, return err; } -static int l2cap_sock_sendmsg(struct kiocb *iocb, struct socket *sock, - struct msghdr *msg, size_t len) +static int l2cap_sock_sendmsg(struct socket *sock, struct msghdr *msg, + size_t len) { struct sock *sk = sock->sk; struct l2cap_chan *chan = l2cap_pi(sk)->chan; @@ -976,8 +976,8 @@ static int l2cap_sock_sendmsg(struct kiocb *iocb, struct socket *sock, return err; } -static int l2cap_sock_recvmsg(struct kiocb *iocb, struct socket *sock, - struct msghdr *msg, size_t len, int flags) +static int l2cap_sock_recvmsg(struct socket *sock, struct msghdr *msg, + size_t len, int flags) { struct sock *sk = sock->sk; struct l2cap_pinfo *pi = l2cap_pi(sk); @@ -1004,9 +1004,9 @@ static int l2cap_sock_recvmsg(struct kiocb *iocb, struct socket *sock, release_sock(sk); if (sock->type == SOCK_STREAM) - err = bt_sock_stream_recvmsg(iocb, sock, msg, len, flags); + err = bt_sock_stream_recvmsg(sock, msg, len, flags); else - err = bt_sock_recvmsg(iocb, sock, msg, len, flags); + err = bt_sock_recvmsg(sock, msg, len, flags); if (pi->chan->mode != L2CAP_MODE_ERTM) return err; @@ -1330,7 +1330,7 @@ static struct sk_buff *l2cap_sock_alloc_skb_cb(struct l2cap_chan *chan, skb->priority = sk->sk_priority; - bt_cb(skb)->chan = chan; + bt_cb(skb)->l2cap.chan = chan; return skb; } @@ -1444,8 +1444,8 @@ static void l2cap_skb_msg_name(struct sk_buff *skb, void *msg_name, memset(la, 0, sizeof(struct sockaddr_l2)); la->l2_family = AF_BLUETOOTH; - la->l2_psm = bt_cb(skb)->psm; - bacpy(&la->l2_bdaddr, &bt_cb(skb)->bdaddr); + la->l2_psm = bt_cb(skb)->l2cap.psm; + bacpy(&la->l2_bdaddr, &bt_cb(skb)->l2cap.bdaddr); *msg_namelen = sizeof(struct sockaddr_l2); } diff --git a/net/bluetooth/mgmt.c b/net/bluetooth/mgmt.c index 9ec5390c85eb..7fd87e7135b5 100644 --- a/net/bluetooth/mgmt.c +++ b/net/bluetooth/mgmt.c @@ -29,14 +29,16 @@ #include <net/bluetooth/bluetooth.h> #include <net/bluetooth/hci_core.h> +#include <net/bluetooth/hci_sock.h> #include <net/bluetooth/l2cap.h> #include <net/bluetooth/mgmt.h> #include "hci_request.h" #include "smp.h" +#include "mgmt_util.h" #define MGMT_VERSION 1 -#define MGMT_REVISION 8 +#define MGMT_REVISION 9 static const u16 mgmt_commands[] = { MGMT_OP_READ_INDEX_LIST, @@ -95,6 +97,11 @@ static const u16 mgmt_commands[] = { MGMT_OP_SET_EXTERNAL_CONFIG, MGMT_OP_SET_PUBLIC_ADDRESS, MGMT_OP_START_SERVICE_DISCOVERY, + MGMT_OP_READ_LOCAL_OOB_EXT_DATA, + MGMT_OP_READ_EXT_INDEX_LIST, + MGMT_OP_READ_ADV_FEATURES, + MGMT_OP_ADD_ADVERTISING, + MGMT_OP_REMOVE_ADVERTISING, }; static const u16 mgmt_events[] = { @@ -127,6 +134,32 @@ static const u16 mgmt_events[] = { MGMT_EV_UNCONF_INDEX_ADDED, MGMT_EV_UNCONF_INDEX_REMOVED, MGMT_EV_NEW_CONFIG_OPTIONS, + MGMT_EV_EXT_INDEX_ADDED, + MGMT_EV_EXT_INDEX_REMOVED, + MGMT_EV_LOCAL_OOB_DATA_UPDATED, + MGMT_EV_ADVERTISING_ADDED, + MGMT_EV_ADVERTISING_REMOVED, +}; + +static const u16 mgmt_untrusted_commands[] = { + MGMT_OP_READ_INDEX_LIST, + MGMT_OP_READ_INFO, + MGMT_OP_READ_UNCONF_INDEX_LIST, + MGMT_OP_READ_CONFIG_INFO, + MGMT_OP_READ_EXT_INDEX_LIST, +}; + +static const u16 mgmt_untrusted_events[] = { + MGMT_EV_INDEX_ADDED, + MGMT_EV_INDEX_REMOVED, + MGMT_EV_NEW_SETTINGS, + MGMT_EV_CLASS_OF_DEV_CHANGED, + MGMT_EV_LOCAL_NAME_CHANGED, + MGMT_EV_UNCONF_INDEX_ADDED, + MGMT_EV_UNCONF_INDEX_REMOVED, + MGMT_EV_NEW_CONFIG_OPTIONS, + MGMT_EV_EXT_INDEX_ADDED, + MGMT_EV_EXT_INDEX_REMOVED, }; #define CACHE_TIMEOUT msecs_to_jiffies(2 * 1000) @@ -134,17 +167,6 @@ static const u16 mgmt_events[] = { #define ZERO_KEY "\x00\x00\x00\x00\x00\x00\x00\x00" \ "\x00\x00\x00\x00\x00\x00\x00\x00" -struct pending_cmd { - struct list_head list; - u16 opcode; - int index; - void *param; - size_t param_len; - struct sock *sk; - void *user_data; - int (*cmd_complete)(struct pending_cmd *cmd, u8 status); -}; - /* HCI to MGMT error code conversion table */ static u8 mgmt_status_table[] = { MGMT_STATUS_SUCCESS, @@ -218,98 +240,32 @@ 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) +static int mgmt_index_event(u16 event, struct hci_dev *hdev, void *data, + u16 len, int flag) { - 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; + return mgmt_send_event(event, hdev, HCI_CHANNEL_CONTROL, data, len, + flag, NULL); } -static int cmd_status(struct sock *sk, u16 index, u16 cmd, u8 status) +static int mgmt_limited_event(u16 event, struct hci_dev *hdev, void *data, + u16 len, int flag, struct sock *skip_sk) { - struct sk_buff *skb; - struct mgmt_hdr *hdr; - struct mgmt_ev_cmd_status *ev; - int err; - - BT_DBG("sock %p, index %u, cmd %u, status %u", sk, index, cmd, status); - - skb = alloc_skb(sizeof(*hdr) + sizeof(*ev), GFP_KERNEL); - if (!skb) - return -ENOMEM; - - hdr = (void *) skb_put(skb, sizeof(*hdr)); - - hdr->opcode = cpu_to_le16(MGMT_EV_CMD_STATUS); - hdr->index = cpu_to_le16(index); - hdr->len = cpu_to_le16(sizeof(*ev)); - - ev = (void *) skb_put(skb, sizeof(*ev)); - ev->status = status; - ev->opcode = cpu_to_le16(cmd); - - err = sock_queue_rcv_skb(sk, skb); - if (err < 0) - kfree_skb(skb); - - return err; + return mgmt_send_event(event, hdev, HCI_CHANNEL_CONTROL, data, len, + flag, skip_sk); } -static int cmd_complete(struct sock *sk, u16 index, u16 cmd, u8 status, - void *rp, size_t rp_len) +static int mgmt_generic_event(u16 event, struct hci_dev *hdev, void *data, + u16 len, struct sock *skip_sk) { - struct sk_buff *skb; - struct mgmt_hdr *hdr; - struct mgmt_ev_cmd_complete *ev; - int err; - - BT_DBG("sock %p", sk); - - skb = alloc_skb(sizeof(*hdr) + sizeof(*ev) + rp_len, GFP_KERNEL); - if (!skb) - return -ENOMEM; - - hdr = (void *) skb_put(skb, sizeof(*hdr)); - - hdr->opcode = cpu_to_le16(MGMT_EV_CMD_COMPLETE); - hdr->index = cpu_to_le16(index); - hdr->len = cpu_to_le16(sizeof(*ev) + rp_len); - - ev = (void *) skb_put(skb, sizeof(*ev) + rp_len); - ev->opcode = cpu_to_le16(cmd); - ev->status = status; - - if (rp) - memcpy(ev->data, rp, rp_len); - - err = sock_queue_rcv_skb(sk, skb); - if (err < 0) - kfree_skb(skb); + return mgmt_send_event(event, hdev, HCI_CHANNEL_CONTROL, data, len, + HCI_MGMT_GENERIC_EVENTS, skip_sk); +} - return err; +static int mgmt_event(u16 event, struct hci_dev *hdev, void *data, u16 len, + struct sock *skip_sk) +{ + return mgmt_send_event(event, hdev, HCI_CHANNEL_CONTROL, data, len, + HCI_SOCK_TRUSTED, skip_sk); } static int read_version(struct sock *sk, struct hci_dev *hdev, void *data, @@ -322,22 +278,28 @@ static int read_version(struct sock *sk, struct hci_dev *hdev, void *data, rp.version = MGMT_VERSION; rp.revision = cpu_to_le16(MGMT_REVISION); - return cmd_complete(sk, MGMT_INDEX_NONE, MGMT_OP_READ_VERSION, 0, &rp, - sizeof(rp)); + return mgmt_cmd_complete(sk, MGMT_INDEX_NONE, MGMT_OP_READ_VERSION, 0, + &rp, sizeof(rp)); } static int read_commands(struct sock *sk, struct hci_dev *hdev, void *data, u16 data_len) { struct mgmt_rp_read_commands *rp; - const u16 num_commands = ARRAY_SIZE(mgmt_commands); - const u16 num_events = ARRAY_SIZE(mgmt_events); - __le16 *opcode; + u16 num_commands, num_events; size_t rp_size; int i, err; BT_DBG("sock %p", sk); + if (hci_sock_test_flag(sk, HCI_SOCK_TRUSTED)) { + num_commands = ARRAY_SIZE(mgmt_commands); + num_events = ARRAY_SIZE(mgmt_events); + } else { + num_commands = ARRAY_SIZE(mgmt_untrusted_commands); + num_events = ARRAY_SIZE(mgmt_untrusted_events); + } + rp_size = sizeof(*rp) + ((num_commands + num_events) * sizeof(u16)); rp = kmalloc(rp_size, GFP_KERNEL); @@ -347,14 +309,26 @@ static int read_commands(struct sock *sk, struct hci_dev *hdev, void *data, rp->num_commands = cpu_to_le16(num_commands); rp->num_events = cpu_to_le16(num_events); - for (i = 0, opcode = rp->opcodes; i < num_commands; i++, opcode++) - put_unaligned_le16(mgmt_commands[i], opcode); + if (hci_sock_test_flag(sk, HCI_SOCK_TRUSTED)) { + __le16 *opcode = rp->opcodes; + + for (i = 0; i < num_commands; i++, opcode++) + put_unaligned_le16(mgmt_commands[i], opcode); + + for (i = 0; i < num_events; i++, opcode++) + put_unaligned_le16(mgmt_events[i], opcode); + } else { + __le16 *opcode = rp->opcodes; + + for (i = 0; i < num_commands; i++, opcode++) + put_unaligned_le16(mgmt_untrusted_commands[i], opcode); - for (i = 0; i < num_events; i++, opcode++) - put_unaligned_le16(mgmt_events[i], opcode); + for (i = 0; i < num_events; i++, opcode++) + put_unaligned_le16(mgmt_untrusted_events[i], opcode); + } - err = cmd_complete(sk, MGMT_INDEX_NONE, MGMT_OP_READ_COMMANDS, 0, rp, - rp_size); + err = mgmt_cmd_complete(sk, MGMT_INDEX_NONE, MGMT_OP_READ_COMMANDS, 0, + rp, rp_size); kfree(rp); return err; @@ -376,7 +350,7 @@ 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 && - !test_bit(HCI_UNCONFIGURED, &d->dev_flags)) + !hci_dev_test_flag(d, HCI_UNCONFIGURED)) count++; } @@ -389,9 +363,9 @@ 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) || - test_bit(HCI_CONFIG, &d->dev_flags) || - test_bit(HCI_USER_CHANNEL, &d->dev_flags)) + if (hci_dev_test_flag(d, HCI_SETUP) || + hci_dev_test_flag(d, HCI_CONFIG) || + hci_dev_test_flag(d, HCI_USER_CHANNEL)) continue; /* Devices marked as raw-only are neither configured @@ -401,7 +375,7 @@ static int read_index_list(struct sock *sk, struct hci_dev *hdev, void *data, continue; if (d->dev_type == HCI_BREDR && - !test_bit(HCI_UNCONFIGURED, &d->dev_flags)) { + !hci_dev_test_flag(d, HCI_UNCONFIGURED)) { rp->index[count++] = cpu_to_le16(d->id); BT_DBG("Added hci%u", d->id); } @@ -412,8 +386,8 @@ static int read_index_list(struct sock *sk, struct hci_dev *hdev, void *data, read_unlock(&hci_dev_list_lock); - err = cmd_complete(sk, MGMT_INDEX_NONE, MGMT_OP_READ_INDEX_LIST, 0, rp, - rp_len); + err = mgmt_cmd_complete(sk, MGMT_INDEX_NONE, MGMT_OP_READ_INDEX_LIST, + 0, rp, rp_len); kfree(rp); @@ -436,7 +410,7 @@ static int read_unconf_index_list(struct sock *sk, struct hci_dev *hdev, count = 0; list_for_each_entry(d, &hci_dev_list, list) { if (d->dev_type == HCI_BREDR && - test_bit(HCI_UNCONFIGURED, &d->dev_flags)) + hci_dev_test_flag(d, HCI_UNCONFIGURED)) count++; } @@ -449,9 +423,9 @@ static int read_unconf_index_list(struct sock *sk, struct hci_dev *hdev, 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)) + if (hci_dev_test_flag(d, HCI_SETUP) || + hci_dev_test_flag(d, HCI_CONFIG) || + hci_dev_test_flag(d, HCI_USER_CHANNEL)) continue; /* Devices marked as raw-only are neither configured @@ -461,7 +435,7 @@ static int read_unconf_index_list(struct sock *sk, struct hci_dev *hdev, continue; if (d->dev_type == HCI_BREDR && - test_bit(HCI_UNCONFIGURED, &d->dev_flags)) { + hci_dev_test_flag(d, HCI_UNCONFIGURED)) { rp->index[count++] = cpu_to_le16(d->id); BT_DBG("Added hci%u", d->id); } @@ -472,8 +446,84 @@ static int read_unconf_index_list(struct sock *sk, struct hci_dev *hdev, read_unlock(&hci_dev_list_lock); - err = cmd_complete(sk, MGMT_INDEX_NONE, MGMT_OP_READ_UNCONF_INDEX_LIST, - 0, rp, rp_len); + err = mgmt_cmd_complete(sk, MGMT_INDEX_NONE, + MGMT_OP_READ_UNCONF_INDEX_LIST, 0, rp, rp_len); + + kfree(rp); + + return err; +} + +static int read_ext_index_list(struct sock *sk, struct hci_dev *hdev, + void *data, u16 data_len) +{ + struct mgmt_rp_read_ext_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 || d->dev_type == HCI_AMP) + count++; + } + + rp_len = sizeof(*rp) + (sizeof(rp->entry[0]) * 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 (hci_dev_test_flag(d, HCI_SETUP) || + hci_dev_test_flag(d, HCI_CONFIG) || + hci_dev_test_flag(d, HCI_USER_CHANNEL)) + 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) { + if (hci_dev_test_flag(d, HCI_UNCONFIGURED)) + rp->entry[count].type = 0x01; + else + rp->entry[count].type = 0x00; + } else if (d->dev_type == HCI_AMP) { + rp->entry[count].type = 0x02; + } else { + continue; + } + + rp->entry[count].bus = d->bus; + rp->entry[count++].index = cpu_to_le16(d->id); + BT_DBG("Added hci%u", d->id); + } + + rp->num_controllers = cpu_to_le16(count); + rp_len = sizeof(*rp) + (sizeof(rp->entry[0]) * count); + + read_unlock(&hci_dev_list_lock); + + /* If this command is called at least once, then all the + * default index and unconfigured index events are disabled + * and from now on only extended index events are used. + */ + hci_sock_set_flag(sk, HCI_MGMT_EXT_INDEX_EVENTS); + hci_sock_clear_flag(sk, HCI_MGMT_INDEX_EVENTS); + hci_sock_clear_flag(sk, HCI_MGMT_UNCONF_INDEX_EVENTS); + + err = mgmt_cmd_complete(sk, MGMT_INDEX_NONE, + MGMT_OP_READ_EXT_INDEX_LIST, 0, rp, rp_len); kfree(rp); @@ -483,7 +533,7 @@ static int read_unconf_index_list(struct sock *sk, struct hci_dev *hdev, 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)) + !hci_dev_test_flag(hdev, HCI_EXT_CONFIGURED)) return false; if (test_bit(HCI_QUIRK_INVALID_BDADDR, &hdev->quirks) && @@ -498,7 +548,7 @@ 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)) + !hci_dev_test_flag(hdev, HCI_EXT_CONFIGURED)) options |= MGMT_OPTION_EXTERNAL_CONFIG; if (test_bit(HCI_QUIRK_INVALID_BDADDR, &hdev->quirks) && @@ -512,16 +562,16 @@ 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); + return mgmt_generic_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)); + return mgmt_cmd_complete(sk, hdev->id, opcode, 0, &options, + sizeof(options)); } static int read_config_info(struct sock *sk, struct hci_dev *hdev, @@ -548,8 +598,8 @@ static int read_config_info(struct sock *sk, struct hci_dev *hdev, hci_dev_unlock(hdev); - return cmd_complete(sk, hdev->id, MGMT_OP_READ_CONFIG_INFO, 0, &rp, - sizeof(rp)); + return mgmt_cmd_complete(sk, hdev->id, MGMT_OP_READ_CONFIG_INFO, 0, + &rp, sizeof(rp)); } static u32 get_supported_settings(struct hci_dev *hdev) @@ -582,6 +632,7 @@ static u32 get_supported_settings(struct hci_dev *hdev) settings |= MGMT_SETTING_ADVERTISING; settings |= MGMT_SETTING_SECURE_CONN; settings |= MGMT_SETTING_PRIVACY; + settings |= MGMT_SETTING_STATIC_ADDRESS; } if (test_bit(HCI_QUIRK_EXTERNAL_CONFIG, &hdev->quirks) || @@ -598,45 +649,64 @@ static u32 get_current_settings(struct hci_dev *hdev) if (hdev_is_powered(hdev)) settings |= MGMT_SETTING_POWERED; - if (test_bit(HCI_CONNECTABLE, &hdev->dev_flags)) + if (hci_dev_test_flag(hdev, HCI_CONNECTABLE)) settings |= MGMT_SETTING_CONNECTABLE; - if (test_bit(HCI_FAST_CONNECTABLE, &hdev->dev_flags)) + if (hci_dev_test_flag(hdev, HCI_FAST_CONNECTABLE)) settings |= MGMT_SETTING_FAST_CONNECTABLE; - if (test_bit(HCI_DISCOVERABLE, &hdev->dev_flags)) + if (hci_dev_test_flag(hdev, HCI_DISCOVERABLE)) settings |= MGMT_SETTING_DISCOVERABLE; - if (test_bit(HCI_BONDABLE, &hdev->dev_flags)) + if (hci_dev_test_flag(hdev, HCI_BONDABLE)) settings |= MGMT_SETTING_BONDABLE; - if (test_bit(HCI_BREDR_ENABLED, &hdev->dev_flags)) + if (hci_dev_test_flag(hdev, HCI_BREDR_ENABLED)) settings |= MGMT_SETTING_BREDR; - if (test_bit(HCI_LE_ENABLED, &hdev->dev_flags)) + if (hci_dev_test_flag(hdev, HCI_LE_ENABLED)) settings |= MGMT_SETTING_LE; - if (test_bit(HCI_LINK_SECURITY, &hdev->dev_flags)) + if (hci_dev_test_flag(hdev, HCI_LINK_SECURITY)) settings |= MGMT_SETTING_LINK_SECURITY; - if (test_bit(HCI_SSP_ENABLED, &hdev->dev_flags)) + if (hci_dev_test_flag(hdev, HCI_SSP_ENABLED)) settings |= MGMT_SETTING_SSP; - if (test_bit(HCI_HS_ENABLED, &hdev->dev_flags)) + if (hci_dev_test_flag(hdev, HCI_HS_ENABLED)) settings |= MGMT_SETTING_HS; - if (test_bit(HCI_ADVERTISING, &hdev->dev_flags)) + if (hci_dev_test_flag(hdev, HCI_ADVERTISING)) settings |= MGMT_SETTING_ADVERTISING; - if (test_bit(HCI_SC_ENABLED, &hdev->dev_flags)) + if (hci_dev_test_flag(hdev, HCI_SC_ENABLED)) settings |= MGMT_SETTING_SECURE_CONN; - if (test_bit(HCI_KEEP_DEBUG_KEYS, &hdev->dev_flags)) + if (hci_dev_test_flag(hdev, HCI_KEEP_DEBUG_KEYS)) settings |= MGMT_SETTING_DEBUG_KEYS; - if (test_bit(HCI_PRIVACY, &hdev->dev_flags)) + if (hci_dev_test_flag(hdev, HCI_PRIVACY)) settings |= MGMT_SETTING_PRIVACY; + /* The current setting for static address has two purposes. The + * first is to indicate if the static address will be used and + * the second is to indicate if it is actually set. + * + * This means if the static address is not configured, this flag + * will never be set. If the address is configured, then if the + * address is actually used decides if the flag is set or not. + * + * For single mode LE only controllers and dual-mode controllers + * with BR/EDR disabled, the existence of the static address will + * be evaluated. + */ + if (hci_dev_test_flag(hdev, HCI_FORCE_STATIC_ADDR) || + !hci_dev_test_flag(hdev, HCI_BREDR_ENABLED) || + !bacmp(&hdev->bdaddr, BDADDR_ANY)) { + if (bacmp(&hdev->static_addr, BDADDR_ANY)) + settings |= MGMT_SETTING_STATIC_ADDRESS; + } + return settings; } @@ -750,35 +820,19 @@ static u8 *create_uuid128_list(struct hci_dev *hdev, u8 *data, ptrdiff_t len) return ptr; } -static struct pending_cmd *mgmt_pending_find(u16 opcode, struct hci_dev *hdev) +static struct mgmt_pending_cmd *pending_find(u16 opcode, struct hci_dev *hdev) { - struct pending_cmd *cmd; - - list_for_each_entry(cmd, &hdev->mgmt_pending, list) { - if (cmd->opcode == opcode) - return cmd; - } - - return NULL; + return mgmt_pending_find(HCI_CHANNEL_CONTROL, opcode, hdev); } -static struct pending_cmd *mgmt_pending_find_data(u16 opcode, +static struct mgmt_pending_cmd *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; + return mgmt_pending_find_data(HCI_CHANNEL_CONTROL, opcode, hdev, data); } -static u8 create_scan_rsp_data(struct hci_dev *hdev, u8 *ptr) +static u8 create_default_scan_rsp_data(struct hci_dev *hdev, u8 *ptr) { u8 ad_len = 0; size_t name_len; @@ -804,21 +858,36 @@ static u8 create_scan_rsp_data(struct hci_dev *hdev, u8 *ptr) return ad_len; } -static void update_scan_rsp_data(struct hci_request *req) +static u8 create_instance_scan_rsp_data(struct hci_dev *hdev, u8 *ptr) +{ + /* TODO: Set the appropriate entries based on advertising instance flags + * here once flags other than 0 are supported. + */ + memcpy(ptr, hdev->adv_instance.scan_rsp_data, + hdev->adv_instance.scan_rsp_len); + + return hdev->adv_instance.scan_rsp_len; +} + +static void update_scan_rsp_data_for_instance(struct hci_request *req, + u8 instance) { struct hci_dev *hdev = req->hdev; struct hci_cp_le_set_scan_rsp_data cp; u8 len; - if (!test_bit(HCI_LE_ENABLED, &hdev->dev_flags)) + if (!hci_dev_test_flag(hdev, HCI_LE_ENABLED)) return; memset(&cp, 0, sizeof(cp)); - len = create_scan_rsp_data(hdev, cp.data); + if (instance) + len = create_instance_scan_rsp_data(hdev, cp.data); + else + len = create_default_scan_rsp_data(hdev, cp.data); if (hdev->scan_rsp_data_len == len && - memcmp(cp.data, hdev->scan_rsp_data, len) == 0) + !memcmp(cp.data, hdev->scan_rsp_data, len)) return; memcpy(hdev->scan_rsp_data, cp.data, sizeof(cp.data)); @@ -829,14 +898,33 @@ static void update_scan_rsp_data(struct hci_request *req) hci_req_add(req, HCI_OP_LE_SET_SCAN_RSP_DATA, sizeof(cp), &cp); } +static void update_scan_rsp_data(struct hci_request *req) +{ + struct hci_dev *hdev = req->hdev; + u8 instance; + + /* The "Set Advertising" setting supersedes the "Add Advertising" + * setting. Here we set the scan response data based on which + * setting was set. When neither apply, default to the global settings, + * represented by instance "0". + */ + if (hci_dev_test_flag(hdev, HCI_ADVERTISING_INSTANCE) && + !hci_dev_test_flag(hdev, HCI_ADVERTISING)) + instance = 0x01; + else + instance = 0x00; + + update_scan_rsp_data_for_instance(req, instance); +} + static u8 get_adv_discov_flags(struct hci_dev *hdev) { - struct pending_cmd *cmd; + struct mgmt_pending_cmd *cmd; /* If there's a pending mgmt command the flags will not yet have * their final values, so check for this first. */ - cmd = mgmt_pending_find(MGMT_OP_SET_DISCOVERABLE, hdev); + cmd = pending_find(MGMT_OP_SET_DISCOVERABLE, hdev); if (cmd) { struct mgmt_mode *cp = cmd->param; if (cp->val == 0x01) @@ -844,39 +932,131 @@ static u8 get_adv_discov_flags(struct hci_dev *hdev) else if (cp->val == 0x02) return LE_AD_LIMITED; } else { - if (test_bit(HCI_LIMITED_DISCOVERABLE, &hdev->dev_flags)) + if (hci_dev_test_flag(hdev, HCI_LIMITED_DISCOVERABLE)) return LE_AD_LIMITED; - else if (test_bit(HCI_DISCOVERABLE, &hdev->dev_flags)) + else if (hci_dev_test_flag(hdev, HCI_DISCOVERABLE)) return LE_AD_GENERAL; } return 0; } -static u8 create_adv_data(struct hci_dev *hdev, u8 *ptr) +static u8 get_current_adv_instance(struct hci_dev *hdev) +{ + /* The "Set Advertising" setting supersedes the "Add Advertising" + * setting. Here we set the advertising data based on which + * setting was set. When neither apply, default to the global settings, + * represented by instance "0". + */ + if (hci_dev_test_flag(hdev, HCI_ADVERTISING_INSTANCE) && + !hci_dev_test_flag(hdev, HCI_ADVERTISING)) + return 0x01; + + return 0x00; +} + +static bool get_connectable(struct hci_dev *hdev) +{ + struct mgmt_pending_cmd *cmd; + + /* If there's a pending mgmt command the flag will not yet have + * it's final value, so check for this first. + */ + cmd = pending_find(MGMT_OP_SET_CONNECTABLE, hdev); + if (cmd) { + struct mgmt_mode *cp = cmd->param; + + return cp->val; + } + + return hci_dev_test_flag(hdev, HCI_CONNECTABLE); +} + +static u32 get_adv_instance_flags(struct hci_dev *hdev, u8 instance) +{ + u32 flags; + + if (instance > 0x01) + return 0; + + if (instance == 0x01) + return hdev->adv_instance.flags; + + /* Instance 0 always manages the "Tx Power" and "Flags" fields */ + flags = MGMT_ADV_FLAG_TX_POWER | MGMT_ADV_FLAG_MANAGED_FLAGS; + + /* For instance 0, the HCI_ADVERTISING_CONNECTABLE setting corresponds + * to the "connectable" instance flag. + */ + if (hci_dev_test_flag(hdev, HCI_ADVERTISING_CONNECTABLE)) + flags |= MGMT_ADV_FLAG_CONNECTABLE; + + return flags; +} + +static u8 get_adv_instance_scan_rsp_len(struct hci_dev *hdev, u8 instance) +{ + /* Ignore instance 0 and other unsupported instances */ + if (instance != 0x01) + return 0; + + /* TODO: Take into account the "appearance" and "local-name" flags here. + * These are currently being ignored as they are not supported. + */ + return hdev->adv_instance.scan_rsp_len; +} + +static u8 create_instance_adv_data(struct hci_dev *hdev, u8 instance, u8 *ptr) { u8 ad_len = 0, flags = 0; + u32 instance_flags = get_adv_instance_flags(hdev, instance); - flags |= get_adv_discov_flags(hdev); + /* The Add Advertising command allows userspace to set both the general + * and limited discoverable flags. + */ + if (instance_flags & MGMT_ADV_FLAG_DISCOV) + flags |= LE_AD_GENERAL; - if (!test_bit(HCI_BREDR_ENABLED, &hdev->dev_flags)) - flags |= LE_AD_NO_BREDR; + if (instance_flags & MGMT_ADV_FLAG_LIMITED_DISCOV) + flags |= LE_AD_LIMITED; - if (flags) { - BT_DBG("adv flags 0x%02x", flags); + if (flags || (instance_flags & MGMT_ADV_FLAG_MANAGED_FLAGS)) { + /* If a discovery flag wasn't provided, simply use the global + * settings. + */ + if (!flags) + flags |= get_adv_discov_flags(hdev); - ptr[0] = 2; - ptr[1] = EIR_FLAGS; - ptr[2] = flags; + if (!hci_dev_test_flag(hdev, HCI_BREDR_ENABLED)) + flags |= LE_AD_NO_BREDR; - ad_len += 3; - ptr += 3; + /* If flags would still be empty, then there is no need to + * include the "Flags" AD field". + */ + if (flags) { + ptr[0] = 0x02; + ptr[1] = EIR_FLAGS; + ptr[2] = flags; + + ad_len += 3; + ptr += 3; + } } - if (hdev->adv_tx_power != HCI_TX_POWER_INVALID) { - ptr[0] = 2; + if (instance) { + memcpy(ptr, hdev->adv_instance.adv_data, + hdev->adv_instance.adv_data_len); + + ad_len += hdev->adv_instance.adv_data_len; + ptr += hdev->adv_instance.adv_data_len; + } + + /* Provide Tx Power only if we can provide a valid value for it */ + if (hdev->adv_tx_power != HCI_TX_POWER_INVALID && + (instance_flags & MGMT_ADV_FLAG_TX_POWER)) { + ptr[0] = 0x02; ptr[1] = EIR_TX_POWER; - ptr[2] = (u8) hdev->adv_tx_power; + ptr[2] = (u8)hdev->adv_tx_power; ad_len += 3; ptr += 3; @@ -885,19 +1065,20 @@ static u8 create_adv_data(struct hci_dev *hdev, u8 *ptr) return ad_len; } -static void update_adv_data(struct hci_request *req) +static void update_adv_data_for_instance(struct hci_request *req, u8 instance) { struct hci_dev *hdev = req->hdev; struct hci_cp_le_set_adv_data cp; u8 len; - if (!test_bit(HCI_LE_ENABLED, &hdev->dev_flags)) + if (!hci_dev_test_flag(hdev, HCI_LE_ENABLED)) return; memset(&cp, 0, sizeof(cp)); - len = create_adv_data(hdev, cp.data); + len = create_instance_adv_data(hdev, instance, cp.data); + /* There's nothing to do if the data hasn't changed */ if (hdev->adv_data_len == len && memcmp(cp.data, hdev->adv_data, len) == 0) return; @@ -910,6 +1091,14 @@ static void update_adv_data(struct hci_request *req) hci_req_add(req, HCI_OP_LE_SET_ADV_DATA, sizeof(cp), &cp); } +static void update_adv_data(struct hci_request *req) +{ + struct hci_dev *hdev = req->hdev; + u8 instance = get_current_adv_instance(hdev); + + update_adv_data_for_instance(req, instance); +} + int mgmt_update_adv_data(struct hci_dev *hdev) { struct hci_request req; @@ -979,10 +1168,10 @@ static void update_eir(struct hci_request *req) if (!lmp_ext_inq_capable(hdev)) return; - if (!test_bit(HCI_SSP_ENABLED, &hdev->dev_flags)) + if (!hci_dev_test_flag(hdev, HCI_SSP_ENABLED)) return; - if (test_bit(HCI_SERVICE_CACHE, &hdev->dev_flags)) + if (hci_dev_test_flag(hdev, HCI_SERVICE_CACHE)) return; memset(&cp, 0, sizeof(cp)); @@ -1018,17 +1207,17 @@ static void update_class(struct hci_request *req) if (!hdev_is_powered(hdev)) return; - if (!test_bit(HCI_BREDR_ENABLED, &hdev->dev_flags)) + if (!hci_dev_test_flag(hdev, HCI_BREDR_ENABLED)) return; - if (test_bit(HCI_SERVICE_CACHE, &hdev->dev_flags)) + if (hci_dev_test_flag(hdev, HCI_SERVICE_CACHE)) return; cod[0] = hdev->minor_class; cod[1] = hdev->major_class; cod[2] = get_service_classes(hdev); - if (test_bit(HCI_LIMITED_DISCOVERABLE, &hdev->dev_flags)) + if (hci_dev_test_flag(hdev, HCI_LIMITED_DISCOVERABLE)) cod[1] |= 0x20; if (memcmp(cod, hdev->dev_class, 3) == 0) @@ -1037,22 +1226,6 @@ static void update_class(struct hci_request *req) hci_req_add(req, HCI_OP_WRITE_CLASS_OF_DEV, sizeof(cod), cod); } -static bool get_connectable(struct hci_dev *hdev) -{ - struct pending_cmd *cmd; - - /* If there's a pending mgmt command the flag will not yet have - * it's final value, so check for this first. - */ - cmd = mgmt_pending_find(MGMT_OP_SET_CONNECTABLE, hdev); - if (cmd) { - struct mgmt_mode *cp = cmd->param; - return cp->val; - } - - return test_bit(HCI_CONNECTABLE, &hdev->dev_flags); -} - static void disable_advertising(struct hci_request *req) { u8 enable = 0x00; @@ -1066,11 +1239,13 @@ static void enable_advertising(struct hci_request *req) struct hci_cp_le_set_adv_param cp; u8 own_addr_type, enable = 0x01; bool connectable; + u8 instance; + u32 flags; if (hci_conn_num(hdev, LE_LINK) > 0) return; - if (test_bit(HCI_LE_ADV, &hdev->dev_flags)) + if (hci_dev_test_flag(hdev, HCI_LE_ADV)) disable_advertising(req); /* Clear the HCI_LE_ADV bit temporarily so that the @@ -1078,9 +1253,16 @@ static void enable_advertising(struct hci_request *req) * 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_LE_ADV, &hdev->dev_flags); + hci_dev_clear_flag(hdev, HCI_LE_ADV); + + instance = get_current_adv_instance(hdev); + flags = get_adv_instance_flags(hdev, instance); - connectable = get_connectable(hdev); + /* If the "connectable" instance flag was not set, then choose between + * ADV_IND and ADV_NONCONN_IND based on the global connectable setting. + */ + connectable = (flags & MGMT_ADV_FLAG_CONNECTABLE) || + get_connectable(hdev); /* Set require_privacy to true only when non-connectable * advertising is used. In that case it is fine to use a @@ -1092,7 +1274,14 @@ static void enable_advertising(struct hci_request *req) memset(&cp, 0, sizeof(cp)); 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; + + if (connectable) + cp.type = LE_ADV_IND; + else if (get_adv_instance_scan_rsp_len(hdev, instance)) + cp.type = LE_ADV_SCAN_IND; + else + cp.type = LE_ADV_NONCONN_IND; + cp.own_address_type = own_addr_type; cp.channel_map = hdev->le_adv_channel_map; @@ -1107,7 +1296,7 @@ static void service_cache_off(struct work_struct *work) service_cache.work); struct hci_request req; - if (!test_and_clear_bit(HCI_SERVICE_CACHE, &hdev->dev_flags)) + if (!hci_dev_test_and_clear_flag(hdev, HCI_SERVICE_CACHE)) return; hci_req_init(&req, hdev); @@ -1130,9 +1319,9 @@ static void rpa_expired(struct work_struct *work) BT_DBG(""); - set_bit(HCI_RPA_EXPIRED, &hdev->dev_flags); + hci_dev_set_flag(hdev, HCI_RPA_EXPIRED); - if (!test_bit(HCI_ADVERTISING, &hdev->dev_flags)) + if (!hci_dev_test_flag(hdev, HCI_ADVERTISING)) return; /* The generation of a new RPA and programming it into the @@ -1145,7 +1334,7 @@ static void rpa_expired(struct work_struct *work) static void mgmt_init_hdev(struct sock *sk, struct hci_dev *hdev) { - if (test_and_set_bit(HCI_MGMT, &hdev->dev_flags)) + if (hci_dev_test_and_set_flag(hdev, HCI_MGMT)) return; INIT_DELAYED_WORK(&hdev->service_cache, service_cache_off); @@ -1156,7 +1345,7 @@ 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_BONDABLE, &hdev->dev_flags); + hci_dev_clear_flag(hdev, HCI_BONDABLE); } static int read_controller_info(struct sock *sk, struct hci_dev *hdev, @@ -1185,73 +1374,16 @@ static int read_controller_info(struct sock *sk, struct hci_dev *hdev, hci_dev_unlock(hdev); - return cmd_complete(sk, hdev->id, MGMT_OP_READ_INFO, 0, &rp, - sizeof(rp)); -} - -static void mgmt_pending_free(struct pending_cmd *cmd) -{ - sock_put(cmd->sk); - kfree(cmd->param); - kfree(cmd); -} - -static struct pending_cmd *mgmt_pending_add(struct sock *sk, u16 opcode, - struct hci_dev *hdev, void *data, - u16 len) -{ - struct pending_cmd *cmd; - - cmd = kzalloc(sizeof(*cmd), GFP_KERNEL); - if (!cmd) - return NULL; - - cmd->opcode = opcode; - cmd->index = hdev->id; - - cmd->param = kmemdup(data, len, GFP_KERNEL); - if (!cmd->param) { - kfree(cmd); - return NULL; - } - - cmd->param_len = len; - - cmd->sk = sk; - sock_hold(sk); - - list_add(&cmd->list, &hdev->mgmt_pending); - - return cmd; -} - -static void mgmt_pending_foreach(u16 opcode, struct hci_dev *hdev, - void (*cb)(struct pending_cmd *cmd, - void *data), - void *data) -{ - struct pending_cmd *cmd, *tmp; - - list_for_each_entry_safe(cmd, tmp, &hdev->mgmt_pending, list) { - if (opcode > 0 && cmd->opcode != opcode) - continue; - - cb(cmd, data); - } -} - -static void mgmt_pending_remove(struct pending_cmd *cmd) -{ - list_del(&cmd->list); - mgmt_pending_free(cmd); + return mgmt_cmd_complete(sk, hdev->id, MGMT_OP_READ_INFO, 0, &rp, + sizeof(rp)); } static int send_settings_rsp(struct sock *sk, u16 opcode, struct hci_dev *hdev) { __le32 settings = cpu_to_le32(get_current_settings(hdev)); - return cmd_complete(sk, hdev->id, opcode, 0, &settings, - sizeof(settings)); + return mgmt_cmd_complete(sk, hdev->id, opcode, 0, &settings, + sizeof(settings)); } static void clean_up_hci_complete(struct hci_dev *hdev, u8 status, u16 opcode) @@ -1272,9 +1404,10 @@ static bool hci_stop_discovery(struct hci_request *req) switch (hdev->discovery.state) { case DISCOVERY_FINDING: - if (test_bit(HCI_INQUIRY, &hdev->flags)) { + if (test_bit(HCI_INQUIRY, &hdev->flags)) hci_req_add(req, HCI_OP_INQUIRY_CANCEL, 0, NULL); - } else { + + if (hci_dev_test_flag(hdev, HCI_LE_SCAN)) { cancel_delayed_work(&hdev->le_scan_disable); hci_req_add_le_scan_disable(req); } @@ -1295,7 +1428,7 @@ static bool hci_stop_discovery(struct hci_request *req) default: /* Passive scanning */ - if (test_bit(HCI_LE_SCAN, &hdev->dev_flags)) { + if (hci_dev_test_flag(hdev, HCI_LE_SCAN)) { hci_req_add_le_scan_disable(req); return true; } @@ -1306,6 +1439,49 @@ static bool hci_stop_discovery(struct hci_request *req) return false; } +static void advertising_added(struct sock *sk, struct hci_dev *hdev, + u8 instance) +{ + struct mgmt_ev_advertising_added ev; + + ev.instance = instance; + + mgmt_event(MGMT_EV_ADVERTISING_ADDED, hdev, &ev, sizeof(ev), sk); +} + +static void advertising_removed(struct sock *sk, struct hci_dev *hdev, + u8 instance) +{ + struct mgmt_ev_advertising_removed ev; + + ev.instance = instance; + + mgmt_event(MGMT_EV_ADVERTISING_REMOVED, hdev, &ev, sizeof(ev), sk); +} + +static void clear_adv_instance(struct hci_dev *hdev) +{ + struct hci_request req; + + if (!hci_dev_test_flag(hdev, HCI_ADVERTISING_INSTANCE)) + return; + + if (hdev->adv_instance.timeout) + cancel_delayed_work(&hdev->adv_instance.timeout_exp); + + memset(&hdev->adv_instance, 0, sizeof(hdev->adv_instance)); + advertising_removed(NULL, hdev, 1); + hci_dev_clear_flag(hdev, HCI_ADVERTISING_INSTANCE); + + if (!hdev_is_powered(hdev) || + hci_dev_test_flag(hdev, HCI_ADVERTISING)) + return; + + hci_req_init(&req, hdev); + disable_advertising(&req); + hci_req_run(&req, NULL); +} + static int clean_up_hci_state(struct hci_dev *hdev) { struct hci_request req; @@ -1321,7 +1497,10 @@ 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_LE_ADV, &hdev->dev_flags)) + if (hdev->adv_instance.timeout) + clear_adv_instance(hdev); + + if (hci_dev_test_flag(hdev, HCI_LE_ADV)) disable_advertising(&req); discov_stopped = hci_stop_discovery(&req); @@ -1369,24 +1548,24 @@ static int set_powered(struct sock *sk, struct hci_dev *hdev, void *data, u16 len) { struct mgmt_mode *cp = data; - struct pending_cmd *cmd; + struct mgmt_pending_cmd *cmd; int err; BT_DBG("request for %s", hdev->name); if (cp->val != 0x00 && cp->val != 0x01) - return cmd_status(sk, hdev->id, MGMT_OP_SET_POWERED, - MGMT_STATUS_INVALID_PARAMS); + return mgmt_cmd_status(sk, hdev->id, MGMT_OP_SET_POWERED, + MGMT_STATUS_INVALID_PARAMS); hci_dev_lock(hdev); - if (mgmt_pending_find(MGMT_OP_SET_POWERED, hdev)) { - err = cmd_status(sk, hdev->id, MGMT_OP_SET_POWERED, - MGMT_STATUS_BUSY); + if (pending_find(MGMT_OP_SET_POWERED, hdev)) { + err = mgmt_cmd_status(sk, hdev->id, MGMT_OP_SET_POWERED, + MGMT_STATUS_BUSY); goto failed; } - if (test_and_clear_bit(HCI_AUTO_OFF, &hdev->dev_flags)) { + if (hci_dev_test_and_clear_flag(hdev, HCI_AUTO_OFF)) { cancel_delayed_work(&hdev->power_off); if (cp->val) { @@ -1433,11 +1612,10 @@ failed: static int new_settings(struct hci_dev *hdev, struct sock *skip) { - __le32 ev; - - ev = cpu_to_le32(get_current_settings(hdev)); + __le32 ev = cpu_to_le32(get_current_settings(hdev)); - return mgmt_event(MGMT_EV_NEW_SETTINGS, hdev, &ev, sizeof(ev), skip); + return mgmt_generic_event(MGMT_EV_NEW_SETTINGS, hdev, &ev, + sizeof(ev), skip); } int mgmt_new_settings(struct hci_dev *hdev) @@ -1451,7 +1629,7 @@ struct cmd_lookup { u8 mgmt_status; }; -static void settings_rsp(struct pending_cmd *cmd, void *data) +static void settings_rsp(struct mgmt_pending_cmd *cmd, void *data) { struct cmd_lookup *match = data; @@ -1467,15 +1645,15 @@ static void settings_rsp(struct pending_cmd *cmd, void *data) mgmt_pending_free(cmd); } -static void cmd_status_rsp(struct pending_cmd *cmd, void *data) +static void cmd_status_rsp(struct mgmt_pending_cmd *cmd, void *data) { u8 *status = data; - cmd_status(cmd->sk, cmd->index, cmd->opcode, *status); + mgmt_cmd_status(cmd->sk, cmd->index, cmd->opcode, *status); mgmt_pending_remove(cmd); } -static void cmd_complete_rsp(struct pending_cmd *cmd, void *data) +static void cmd_complete_rsp(struct mgmt_pending_cmd *cmd, void *data) { if (cmd->cmd_complete) { u8 *status = data; @@ -1489,23 +1667,23 @@ static void cmd_complete_rsp(struct pending_cmd *cmd, void *data) cmd_status_rsp(cmd, data); } -static int generic_cmd_complete(struct pending_cmd *cmd, u8 status) +static int generic_cmd_complete(struct mgmt_pending_cmd *cmd, u8 status) { - return cmd_complete(cmd->sk, cmd->index, cmd->opcode, status, - cmd->param, cmd->param_len); + return mgmt_cmd_complete(cmd->sk, cmd->index, cmd->opcode, status, + cmd->param, cmd->param_len); } -static int addr_cmd_complete(struct pending_cmd *cmd, u8 status) +static int addr_cmd_complete(struct mgmt_pending_cmd *cmd, u8 status) { - return cmd_complete(cmd->sk, cmd->index, cmd->opcode, status, cmd->param, - sizeof(struct mgmt_addr_info)); + return mgmt_cmd_complete(cmd->sk, cmd->index, cmd->opcode, status, + cmd->param, sizeof(struct mgmt_addr_info)); } static u8 mgmt_bredr_support(struct hci_dev *hdev) { if (!lmp_bredr_capable(hdev)) return MGMT_STATUS_NOT_SUPPORTED; - else if (!test_bit(HCI_BREDR_ENABLED, &hdev->dev_flags)) + else if (!hci_dev_test_flag(hdev, HCI_BREDR_ENABLED)) return MGMT_STATUS_REJECTED; else return MGMT_STATUS_SUCCESS; @@ -1515,7 +1693,7 @@ static u8 mgmt_le_support(struct hci_dev *hdev) { if (!lmp_le_capable(hdev)) return MGMT_STATUS_NOT_SUPPORTED; - else if (!test_bit(HCI_LE_ENABLED, &hdev->dev_flags)) + else if (!hci_dev_test_flag(hdev, HCI_LE_ENABLED)) return MGMT_STATUS_REJECTED; else return MGMT_STATUS_SUCCESS; @@ -1524,7 +1702,7 @@ static u8 mgmt_le_support(struct hci_dev *hdev) static void set_discoverable_complete(struct hci_dev *hdev, u8 status, u16 opcode) { - struct pending_cmd *cmd; + struct mgmt_pending_cmd *cmd; struct mgmt_mode *cp; struct hci_request req; bool changed; @@ -1533,21 +1711,20 @@ static void set_discoverable_complete(struct hci_dev *hdev, u8 status, hci_dev_lock(hdev); - cmd = mgmt_pending_find(MGMT_OP_SET_DISCOVERABLE, hdev); + cmd = pending_find(MGMT_OP_SET_DISCOVERABLE, hdev); if (!cmd) goto unlock; if (status) { u8 mgmt_err = mgmt_status(status); - cmd_status(cmd->sk, cmd->index, cmd->opcode, mgmt_err); - clear_bit(HCI_LIMITED_DISCOVERABLE, &hdev->dev_flags); + mgmt_cmd_status(cmd->sk, cmd->index, cmd->opcode, mgmt_err); + hci_dev_clear_flag(hdev, HCI_LIMITED_DISCOVERABLE); goto remove_cmd; } cp = cmd->param; if (cp->val) { - changed = !test_and_set_bit(HCI_DISCOVERABLE, - &hdev->dev_flags); + changed = !hci_dev_test_and_set_flag(hdev, HCI_DISCOVERABLE); if (hdev->discov_timeout > 0) { int to = msecs_to_jiffies(hdev->discov_timeout * 1000); @@ -1555,8 +1732,7 @@ static void set_discoverable_complete(struct hci_dev *hdev, u8 status, to); } } else { - changed = test_and_clear_bit(HCI_DISCOVERABLE, - &hdev->dev_flags); + changed = hci_dev_test_and_clear_flag(hdev, HCI_DISCOVERABLE); } send_settings_rsp(cmd->sk, MGMT_OP_SET_DISCOVERABLE, hdev); @@ -1585,7 +1761,7 @@ static int set_discoverable(struct sock *sk, struct hci_dev *hdev, void *data, u16 len) { struct mgmt_cp_set_discoverable *cp = data; - struct pending_cmd *cmd; + struct mgmt_pending_cmd *cmd; struct hci_request req; u16 timeout; u8 scan; @@ -1593,14 +1769,14 @@ static int set_discoverable(struct sock *sk, struct hci_dev *hdev, void *data, BT_DBG("request for %s", hdev->name); - if (!test_bit(HCI_LE_ENABLED, &hdev->dev_flags) && - !test_bit(HCI_BREDR_ENABLED, &hdev->dev_flags)) - return cmd_status(sk, hdev->id, MGMT_OP_SET_DISCOVERABLE, - MGMT_STATUS_REJECTED); + if (!hci_dev_test_flag(hdev, HCI_LE_ENABLED) && + !hci_dev_test_flag(hdev, HCI_BREDR_ENABLED)) + return mgmt_cmd_status(sk, hdev->id, MGMT_OP_SET_DISCOVERABLE, + MGMT_STATUS_REJECTED); if (cp->val != 0x00 && cp->val != 0x01 && cp->val != 0x02) - return cmd_status(sk, hdev->id, MGMT_OP_SET_DISCOVERABLE, - MGMT_STATUS_INVALID_PARAMS); + return mgmt_cmd_status(sk, hdev->id, MGMT_OP_SET_DISCOVERABLE, + MGMT_STATUS_INVALID_PARAMS); timeout = __le16_to_cpu(cp->timeout); @@ -1609,27 +1785,27 @@ static int set_discoverable(struct sock *sk, struct hci_dev *hdev, void *data, */ if ((cp->val == 0x00 && timeout > 0) || (cp->val == 0x02 && timeout == 0)) - return cmd_status(sk, hdev->id, MGMT_OP_SET_DISCOVERABLE, - MGMT_STATUS_INVALID_PARAMS); + return mgmt_cmd_status(sk, hdev->id, MGMT_OP_SET_DISCOVERABLE, + MGMT_STATUS_INVALID_PARAMS); hci_dev_lock(hdev); if (!hdev_is_powered(hdev) && timeout > 0) { - err = cmd_status(sk, hdev->id, MGMT_OP_SET_DISCOVERABLE, - MGMT_STATUS_NOT_POWERED); + err = mgmt_cmd_status(sk, hdev->id, MGMT_OP_SET_DISCOVERABLE, + MGMT_STATUS_NOT_POWERED); goto failed; } - if (mgmt_pending_find(MGMT_OP_SET_DISCOVERABLE, hdev) || - mgmt_pending_find(MGMT_OP_SET_CONNECTABLE, hdev)) { - err = cmd_status(sk, hdev->id, MGMT_OP_SET_DISCOVERABLE, - MGMT_STATUS_BUSY); + if (pending_find(MGMT_OP_SET_DISCOVERABLE, hdev) || + pending_find(MGMT_OP_SET_CONNECTABLE, hdev)) { + err = mgmt_cmd_status(sk, hdev->id, MGMT_OP_SET_DISCOVERABLE, + MGMT_STATUS_BUSY); goto failed; } - if (!test_bit(HCI_CONNECTABLE, &hdev->dev_flags)) { - err = cmd_status(sk, hdev->id, MGMT_OP_SET_DISCOVERABLE, - MGMT_STATUS_REJECTED); + if (!hci_dev_test_flag(hdev, HCI_CONNECTABLE)) { + err = mgmt_cmd_status(sk, hdev->id, MGMT_OP_SET_DISCOVERABLE, + MGMT_STATUS_REJECTED); goto failed; } @@ -1640,8 +1816,8 @@ static int set_discoverable(struct sock *sk, struct hci_dev *hdev, void *data, * not a valid operation since it requires a timeout * and so no need to check HCI_LIMITED_DISCOVERABLE. */ - if (!!cp->val != test_bit(HCI_DISCOVERABLE, &hdev->dev_flags)) { - change_bit(HCI_DISCOVERABLE, &hdev->dev_flags); + if (!!cp->val != hci_dev_test_flag(hdev, HCI_DISCOVERABLE)) { + hci_dev_change_flag(hdev, HCI_DISCOVERABLE); changed = true; } @@ -1659,9 +1835,9 @@ static int set_discoverable(struct sock *sk, struct hci_dev *hdev, void *data, * value with the new value. And if only the timeout gets updated, * then no need for any HCI transactions. */ - if (!!cp->val == test_bit(HCI_DISCOVERABLE, &hdev->dev_flags) && - (cp->val == 0x02) == test_bit(HCI_LIMITED_DISCOVERABLE, - &hdev->dev_flags)) { + if (!!cp->val == hci_dev_test_flag(hdev, HCI_DISCOVERABLE) && + (cp->val == 0x02) == hci_dev_test_flag(hdev, + HCI_LIMITED_DISCOVERABLE)) { cancel_delayed_work(&hdev->discov_off); hdev->discov_timeout = timeout; @@ -1690,16 +1866,16 @@ static int set_discoverable(struct sock *sk, struct hci_dev *hdev, void *data, /* Limited discoverable mode */ if (cp->val == 0x02) - set_bit(HCI_LIMITED_DISCOVERABLE, &hdev->dev_flags); + hci_dev_set_flag(hdev, HCI_LIMITED_DISCOVERABLE); else - clear_bit(HCI_LIMITED_DISCOVERABLE, &hdev->dev_flags); + hci_dev_clear_flag(hdev, HCI_LIMITED_DISCOVERABLE); hci_req_init(&req, hdev); /* The procedure for LE-only controllers is much simpler - just * update the advertising data. */ - if (!test_bit(HCI_BREDR_ENABLED, &hdev->dev_flags)) + if (!hci_dev_test_flag(hdev, HCI_BREDR_ENABLED)) goto update_ad; scan = SCAN_PAGE; @@ -1729,7 +1905,7 @@ static int set_discoverable(struct sock *sk, struct hci_dev *hdev, void *data, scan |= SCAN_INQUIRY; } else { - clear_bit(HCI_LIMITED_DISCOVERABLE, &hdev->dev_flags); + hci_dev_clear_flag(hdev, HCI_LIMITED_DISCOVERABLE); } hci_req_add(&req, HCI_OP_WRITE_SCAN_ENABLE, sizeof(scan), &scan); @@ -1752,7 +1928,7 @@ static void write_fast_connectable(struct hci_request *req, bool enable) struct hci_cp_write_page_scan_activity acp; u8 type; - if (!test_bit(HCI_BREDR_ENABLED, &hdev->dev_flags)) + if (!hci_dev_test_flag(hdev, HCI_BREDR_ENABLED)) return; if (hdev->hci_ver < BLUETOOTH_VER_1_2) @@ -1784,7 +1960,7 @@ static void write_fast_connectable(struct hci_request *req, bool enable) static void set_connectable_complete(struct hci_dev *hdev, u8 status, u16 opcode) { - struct pending_cmd *cmd; + struct mgmt_pending_cmd *cmd; struct mgmt_mode *cp; bool conn_changed, discov_changed; @@ -1792,26 +1968,26 @@ static void set_connectable_complete(struct hci_dev *hdev, u8 status, hci_dev_lock(hdev); - cmd = mgmt_pending_find(MGMT_OP_SET_CONNECTABLE, hdev); + cmd = pending_find(MGMT_OP_SET_CONNECTABLE, hdev); if (!cmd) goto unlock; if (status) { u8 mgmt_err = mgmt_status(status); - cmd_status(cmd->sk, cmd->index, cmd->opcode, mgmt_err); + mgmt_cmd_status(cmd->sk, cmd->index, cmd->opcode, mgmt_err); goto remove_cmd; } cp = cmd->param; if (cp->val) { - conn_changed = !test_and_set_bit(HCI_CONNECTABLE, - &hdev->dev_flags); + conn_changed = !hci_dev_test_and_set_flag(hdev, + HCI_CONNECTABLE); 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); + conn_changed = hci_dev_test_and_clear_flag(hdev, + HCI_CONNECTABLE); + discov_changed = hci_dev_test_and_clear_flag(hdev, + HCI_DISCOVERABLE); } send_settings_rsp(cmd->sk, MGMT_OP_SET_CONNECTABLE, hdev); @@ -1837,14 +2013,14 @@ static int set_connectable_update_settings(struct hci_dev *hdev, bool changed = false; int err; - if (!!val != test_bit(HCI_CONNECTABLE, &hdev->dev_flags)) + if (!!val != hci_dev_test_flag(hdev, HCI_CONNECTABLE)) changed = true; if (val) { - set_bit(HCI_CONNECTABLE, &hdev->dev_flags); + hci_dev_set_flag(hdev, HCI_CONNECTABLE); } else { - clear_bit(HCI_CONNECTABLE, &hdev->dev_flags); - clear_bit(HCI_DISCOVERABLE, &hdev->dev_flags); + hci_dev_clear_flag(hdev, HCI_CONNECTABLE); + hci_dev_clear_flag(hdev, HCI_DISCOVERABLE); } err = send_settings_rsp(sk, MGMT_OP_SET_CONNECTABLE, hdev); @@ -1864,21 +2040,21 @@ static int set_connectable(struct sock *sk, struct hci_dev *hdev, void *data, u16 len) { struct mgmt_mode *cp = data; - struct pending_cmd *cmd; + struct mgmt_pending_cmd *cmd; struct hci_request req; u8 scan; int err; BT_DBG("request for %s", hdev->name); - if (!test_bit(HCI_LE_ENABLED, &hdev->dev_flags) && - !test_bit(HCI_BREDR_ENABLED, &hdev->dev_flags)) - return cmd_status(sk, hdev->id, MGMT_OP_SET_CONNECTABLE, - MGMT_STATUS_REJECTED); + if (!hci_dev_test_flag(hdev, HCI_LE_ENABLED) && + !hci_dev_test_flag(hdev, HCI_BREDR_ENABLED)) + return mgmt_cmd_status(sk, hdev->id, MGMT_OP_SET_CONNECTABLE, + MGMT_STATUS_REJECTED); if (cp->val != 0x00 && cp->val != 0x01) - return cmd_status(sk, hdev->id, MGMT_OP_SET_CONNECTABLE, - MGMT_STATUS_INVALID_PARAMS); + return mgmt_cmd_status(sk, hdev->id, MGMT_OP_SET_CONNECTABLE, + MGMT_STATUS_INVALID_PARAMS); hci_dev_lock(hdev); @@ -1887,10 +2063,10 @@ static int set_connectable(struct sock *sk, struct hci_dev *hdev, void *data, goto failed; } - if (mgmt_pending_find(MGMT_OP_SET_DISCOVERABLE, hdev) || - mgmt_pending_find(MGMT_OP_SET_CONNECTABLE, hdev)) { - err = cmd_status(sk, hdev->id, MGMT_OP_SET_CONNECTABLE, - MGMT_STATUS_BUSY); + if (pending_find(MGMT_OP_SET_DISCOVERABLE, hdev) || + pending_find(MGMT_OP_SET_CONNECTABLE, hdev)) { + err = mgmt_cmd_status(sk, hdev->id, MGMT_OP_SET_CONNECTABLE, + MGMT_STATUS_BUSY); goto failed; } @@ -1906,10 +2082,10 @@ static int set_connectable(struct sock *sk, struct hci_dev *hdev, void *data, * by-product of disabling connectable, we need to update the * advertising flags. */ - if (!test_bit(HCI_BREDR_ENABLED, &hdev->dev_flags)) { + if (!hci_dev_test_flag(hdev, HCI_BREDR_ENABLED)) { if (!cp->val) { - clear_bit(HCI_LIMITED_DISCOVERABLE, &hdev->dev_flags); - clear_bit(HCI_DISCOVERABLE, &hdev->dev_flags); + hci_dev_clear_flag(hdev, HCI_LIMITED_DISCOVERABLE); + hci_dev_clear_flag(hdev, HCI_DISCOVERABLE); } update_adv_data(&req); } else if (cp->val != test_bit(HCI_PSCAN, &hdev->flags)) { @@ -1938,17 +2114,9 @@ static int set_connectable(struct sock *sk, struct hci_dev *hdev, void *data, } 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 - * anything if the page scan parameters are already what they - * should be. - */ - if (cp->val || test_bit(HCI_FAST_CONNECTABLE, &hdev->dev_flags)) - write_fast_connectable(&req, false); - /* Update the advertising parameters if necessary */ - if (test_bit(HCI_ADVERTISING, &hdev->dev_flags)) + if (hci_dev_test_flag(hdev, HCI_ADVERTISING) || + hci_dev_test_flag(hdev, HCI_ADVERTISING_INSTANCE)) enable_advertising(&req); err = hci_req_run(&req, set_connectable_complete); @@ -1975,15 +2143,15 @@ static int set_bondable(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_BONDABLE, - MGMT_STATUS_INVALID_PARAMS); + return mgmt_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_BONDABLE, &hdev->dev_flags); + changed = !hci_dev_test_and_set_flag(hdev, HCI_BONDABLE); else - changed = test_and_clear_bit(HCI_BONDABLE, &hdev->dev_flags); + changed = hci_dev_test_and_clear_flag(hdev, HCI_BONDABLE); err = send_settings_rsp(sk, MGMT_OP_SET_BONDABLE, hdev); if (err < 0) @@ -2001,7 +2169,7 @@ static int set_link_security(struct sock *sk, struct hci_dev *hdev, void *data, u16 len) { struct mgmt_mode *cp = data; - struct pending_cmd *cmd; + struct mgmt_pending_cmd *cmd; u8 val, status; int err; @@ -2009,21 +2177,20 @@ static int set_link_security(struct sock *sk, struct hci_dev *hdev, void *data, status = mgmt_bredr_support(hdev); if (status) - return cmd_status(sk, hdev->id, MGMT_OP_SET_LINK_SECURITY, - status); + return mgmt_cmd_status(sk, hdev->id, MGMT_OP_SET_LINK_SECURITY, + status); if (cp->val != 0x00 && cp->val != 0x01) - return cmd_status(sk, hdev->id, MGMT_OP_SET_LINK_SECURITY, - MGMT_STATUS_INVALID_PARAMS); + return mgmt_cmd_status(sk, hdev->id, MGMT_OP_SET_LINK_SECURITY, + MGMT_STATUS_INVALID_PARAMS); hci_dev_lock(hdev); if (!hdev_is_powered(hdev)) { bool changed = false; - if (!!cp->val != test_bit(HCI_LINK_SECURITY, - &hdev->dev_flags)) { - change_bit(HCI_LINK_SECURITY, &hdev->dev_flags); + if (!!cp->val != hci_dev_test_flag(hdev, HCI_LINK_SECURITY)) { + hci_dev_change_flag(hdev, HCI_LINK_SECURITY); changed = true; } @@ -2037,9 +2204,9 @@ static int set_link_security(struct sock *sk, struct hci_dev *hdev, void *data, goto failed; } - if (mgmt_pending_find(MGMT_OP_SET_LINK_SECURITY, hdev)) { - err = cmd_status(sk, hdev->id, MGMT_OP_SET_LINK_SECURITY, - MGMT_STATUS_BUSY); + if (pending_find(MGMT_OP_SET_LINK_SECURITY, hdev)) { + err = mgmt_cmd_status(sk, hdev->id, MGMT_OP_SET_LINK_SECURITY, + MGMT_STATUS_BUSY); goto failed; } @@ -2070,7 +2237,7 @@ failed: static int set_ssp(struct sock *sk, struct hci_dev *hdev, void *data, u16 len) { struct mgmt_mode *cp = data; - struct pending_cmd *cmd; + struct mgmt_pending_cmd *cmd; u8 status; int err; @@ -2078,15 +2245,15 @@ static int set_ssp(struct sock *sk, struct hci_dev *hdev, void *data, u16 len) status = mgmt_bredr_support(hdev); if (status) - return cmd_status(sk, hdev->id, MGMT_OP_SET_SSP, status); + return mgmt_cmd_status(sk, hdev->id, MGMT_OP_SET_SSP, status); if (!lmp_ssp_capable(hdev)) - return cmd_status(sk, hdev->id, MGMT_OP_SET_SSP, - MGMT_STATUS_NOT_SUPPORTED); + return mgmt_cmd_status(sk, hdev->id, MGMT_OP_SET_SSP, + MGMT_STATUS_NOT_SUPPORTED); if (cp->val != 0x00 && cp->val != 0x01) - return cmd_status(sk, hdev->id, MGMT_OP_SET_SSP, - MGMT_STATUS_INVALID_PARAMS); + return mgmt_cmd_status(sk, hdev->id, MGMT_OP_SET_SSP, + MGMT_STATUS_INVALID_PARAMS); hci_dev_lock(hdev); @@ -2094,16 +2261,16 @@ static int set_ssp(struct sock *sk, struct hci_dev *hdev, void *data, u16 len) bool changed; if (cp->val) { - changed = !test_and_set_bit(HCI_SSP_ENABLED, - &hdev->dev_flags); + changed = !hci_dev_test_and_set_flag(hdev, + HCI_SSP_ENABLED); } else { - changed = test_and_clear_bit(HCI_SSP_ENABLED, - &hdev->dev_flags); + changed = hci_dev_test_and_clear_flag(hdev, + HCI_SSP_ENABLED); if (!changed) - changed = test_and_clear_bit(HCI_HS_ENABLED, - &hdev->dev_flags); + changed = hci_dev_test_and_clear_flag(hdev, + HCI_HS_ENABLED); else - clear_bit(HCI_HS_ENABLED, &hdev->dev_flags); + hci_dev_clear_flag(hdev, HCI_HS_ENABLED); } err = send_settings_rsp(sk, MGMT_OP_SET_SSP, hdev); @@ -2116,14 +2283,13 @@ static int set_ssp(struct sock *sk, struct hci_dev *hdev, void *data, u16 len) goto failed; } - if (mgmt_pending_find(MGMT_OP_SET_SSP, hdev) || - mgmt_pending_find(MGMT_OP_SET_HS, hdev)) { - err = cmd_status(sk, hdev->id, MGMT_OP_SET_SSP, - MGMT_STATUS_BUSY); + if (pending_find(MGMT_OP_SET_SSP, hdev)) { + err = mgmt_cmd_status(sk, hdev->id, MGMT_OP_SET_SSP, + MGMT_STATUS_BUSY); goto failed; } - if (!!cp->val == test_bit(HCI_SSP_ENABLED, &hdev->dev_flags)) { + if (!!cp->val == hci_dev_test_flag(hdev, HCI_SSP_ENABLED)) { err = send_settings_rsp(sk, MGMT_OP_SET_SSP, hdev); goto failed; } @@ -2134,7 +2300,7 @@ 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)) + if (!cp->val && hci_dev_test_flag(hdev, HCI_USE_DEBUG_KEYS)) hci_send_cmd(hdev, HCI_OP_WRITE_SSP_DEBUG_MODE, sizeof(cp->val), &cp->val); @@ -2160,32 +2326,38 @@ static int set_hs(struct sock *sk, struct hci_dev *hdev, void *data, u16 len) status = mgmt_bredr_support(hdev); if (status) - return cmd_status(sk, hdev->id, MGMT_OP_SET_HS, status); + return mgmt_cmd_status(sk, hdev->id, MGMT_OP_SET_HS, status); if (!lmp_ssp_capable(hdev)) - return cmd_status(sk, hdev->id, MGMT_OP_SET_HS, - MGMT_STATUS_NOT_SUPPORTED); + return mgmt_cmd_status(sk, hdev->id, MGMT_OP_SET_HS, + MGMT_STATUS_NOT_SUPPORTED); - if (!test_bit(HCI_SSP_ENABLED, &hdev->dev_flags)) - return cmd_status(sk, hdev->id, MGMT_OP_SET_HS, - MGMT_STATUS_REJECTED); + if (!hci_dev_test_flag(hdev, HCI_SSP_ENABLED)) + return mgmt_cmd_status(sk, hdev->id, MGMT_OP_SET_HS, + MGMT_STATUS_REJECTED); if (cp->val != 0x00 && cp->val != 0x01) - return cmd_status(sk, hdev->id, MGMT_OP_SET_HS, - MGMT_STATUS_INVALID_PARAMS); + return mgmt_cmd_status(sk, hdev->id, MGMT_OP_SET_HS, + MGMT_STATUS_INVALID_PARAMS); hci_dev_lock(hdev); + if (pending_find(MGMT_OP_SET_SSP, hdev)) { + err = mgmt_cmd_status(sk, hdev->id, MGMT_OP_SET_HS, + MGMT_STATUS_BUSY); + goto unlock; + } + if (cp->val) { - changed = !test_and_set_bit(HCI_HS_ENABLED, &hdev->dev_flags); + changed = !hci_dev_test_and_set_flag(hdev, HCI_HS_ENABLED); } else { if (hdev_is_powered(hdev)) { - err = cmd_status(sk, hdev->id, MGMT_OP_SET_HS, - MGMT_STATUS_REJECTED); + err = mgmt_cmd_status(sk, hdev->id, MGMT_OP_SET_HS, + MGMT_STATUS_REJECTED); goto unlock; } - changed = test_and_clear_bit(HCI_HS_ENABLED, &hdev->dev_flags); + changed = hci_dev_test_and_clear_flag(hdev, HCI_HS_ENABLED); } err = send_settings_rsp(sk, MGMT_OP_SET_HS, hdev); @@ -2226,7 +2398,7 @@ static void le_enable_complete(struct hci_dev *hdev, u8 status, u16 opcode) * has actually been enabled. During power on, the * update in powered_update_hci will take care of it. */ - if (test_bit(HCI_LE_ENABLED, &hdev->dev_flags)) { + if (hci_dev_test_flag(hdev, HCI_LE_ENABLED)) { struct hci_request req; hci_req_init(&req, hdev); @@ -2244,7 +2416,7 @@ static int set_le(struct sock *sk, struct hci_dev *hdev, void *data, u16 len) { struct mgmt_mode *cp = data; struct hci_cp_write_le_host_supported hci_cp; - struct pending_cmd *cmd; + struct mgmt_pending_cmd *cmd; struct hci_request req; int err; u8 val, enabled; @@ -2252,17 +2424,29 @@ static int set_le(struct sock *sk, struct hci_dev *hdev, void *data, u16 len) BT_DBG("request for %s", hdev->name); if (!lmp_le_capable(hdev)) - return cmd_status(sk, hdev->id, MGMT_OP_SET_LE, - MGMT_STATUS_NOT_SUPPORTED); + return mgmt_cmd_status(sk, hdev->id, MGMT_OP_SET_LE, + MGMT_STATUS_NOT_SUPPORTED); if (cp->val != 0x00 && cp->val != 0x01) - return cmd_status(sk, hdev->id, MGMT_OP_SET_LE, - MGMT_STATUS_INVALID_PARAMS); + return mgmt_cmd_status(sk, hdev->id, MGMT_OP_SET_LE, + MGMT_STATUS_INVALID_PARAMS); + + /* Bluetooth single mode LE only controllers or dual-mode + * controllers configured as LE only devices, do not allow + * switching LE off. These have either LE enabled explicitly + * or BR/EDR has been previously switched off. + * + * When trying to enable an already enabled LE, then gracefully + * send a positive response. Trying to disable it however will + * result into rejection. + */ + if (!hci_dev_test_flag(hdev, HCI_BREDR_ENABLED)) { + if (cp->val == 0x01) + return send_settings_rsp(sk, MGMT_OP_SET_LE, hdev); - /* LE-only devices do not allow toggling LE on/off */ - if (!test_bit(HCI_BREDR_ENABLED, &hdev->dev_flags)) - return cmd_status(sk, hdev->id, MGMT_OP_SET_LE, - MGMT_STATUS_REJECTED); + return mgmt_cmd_status(sk, hdev->id, MGMT_OP_SET_LE, + MGMT_STATUS_REJECTED); + } hci_dev_lock(hdev); @@ -2272,13 +2456,13 @@ static int set_le(struct sock *sk, struct hci_dev *hdev, void *data, u16 len) if (!hdev_is_powered(hdev) || val == enabled) { bool changed = false; - if (val != test_bit(HCI_LE_ENABLED, &hdev->dev_flags)) { - change_bit(HCI_LE_ENABLED, &hdev->dev_flags); + if (val != hci_dev_test_flag(hdev, HCI_LE_ENABLED)) { + hci_dev_change_flag(hdev, HCI_LE_ENABLED); changed = true; } - if (!val && test_bit(HCI_ADVERTISING, &hdev->dev_flags)) { - clear_bit(HCI_ADVERTISING, &hdev->dev_flags); + if (!val && hci_dev_test_flag(hdev, HCI_ADVERTISING)) { + hci_dev_clear_flag(hdev, HCI_ADVERTISING); changed = true; } @@ -2292,10 +2476,10 @@ static int set_le(struct sock *sk, struct hci_dev *hdev, void *data, u16 len) goto unlock; } - if (mgmt_pending_find(MGMT_OP_SET_LE, hdev) || - mgmt_pending_find(MGMT_OP_SET_ADVERTISING, hdev)) { - err = cmd_status(sk, hdev->id, MGMT_OP_SET_LE, - MGMT_STATUS_BUSY); + if (pending_find(MGMT_OP_SET_LE, hdev) || + pending_find(MGMT_OP_SET_ADVERTISING, hdev)) { + err = mgmt_cmd_status(sk, hdev->id, MGMT_OP_SET_LE, + MGMT_STATUS_BUSY); goto unlock; } @@ -2313,7 +2497,7 @@ static int set_le(struct sock *sk, struct hci_dev *hdev, void *data, u16 len) hci_cp.le = val; hci_cp.simul = 0x00; } else { - if (test_bit(HCI_LE_ADV, &hdev->dev_flags)) + if (hci_dev_test_flag(hdev, HCI_LE_ADV)) disable_advertising(&req); } @@ -2337,7 +2521,7 @@ unlock: */ static bool pending_eir_or_class(struct hci_dev *hdev) { - struct pending_cmd *cmd; + struct mgmt_pending_cmd *cmd; list_for_each_entry(cmd, &hdev->mgmt_pending, list) { switch (cmd->opcode) { @@ -2373,16 +2557,16 @@ static u8 get_uuid_size(const u8 *uuid) static void mgmt_class_complete(struct hci_dev *hdev, u16 mgmt_op, u8 status) { - struct pending_cmd *cmd; + struct mgmt_pending_cmd *cmd; hci_dev_lock(hdev); - cmd = mgmt_pending_find(mgmt_op, hdev); + cmd = pending_find(mgmt_op, hdev); if (!cmd) goto unlock; - cmd_complete(cmd->sk, cmd->index, cmd->opcode, mgmt_status(status), - hdev->dev_class, 3); + mgmt_cmd_complete(cmd->sk, cmd->index, cmd->opcode, + mgmt_status(status), hdev->dev_class, 3); mgmt_pending_remove(cmd); @@ -2400,7 +2584,7 @@ static void add_uuid_complete(struct hci_dev *hdev, u8 status, u16 opcode) static int add_uuid(struct sock *sk, struct hci_dev *hdev, void *data, u16 len) { struct mgmt_cp_add_uuid *cp = data; - struct pending_cmd *cmd; + struct mgmt_pending_cmd *cmd; struct hci_request req; struct bt_uuid *uuid; int err; @@ -2410,8 +2594,8 @@ static int add_uuid(struct sock *sk, struct hci_dev *hdev, void *data, u16 len) hci_dev_lock(hdev); if (pending_eir_or_class(hdev)) { - err = cmd_status(sk, hdev->id, MGMT_OP_ADD_UUID, - MGMT_STATUS_BUSY); + err = mgmt_cmd_status(sk, hdev->id, MGMT_OP_ADD_UUID, + MGMT_STATUS_BUSY); goto failed; } @@ -2437,8 +2621,8 @@ static int add_uuid(struct sock *sk, struct hci_dev *hdev, void *data, u16 len) if (err != -ENODATA) goto failed; - err = cmd_complete(sk, hdev->id, MGMT_OP_ADD_UUID, 0, - hdev->dev_class, 3); + err = mgmt_cmd_complete(sk, hdev->id, MGMT_OP_ADD_UUID, 0, + hdev->dev_class, 3); goto failed; } @@ -2460,7 +2644,7 @@ static bool enable_service_cache(struct hci_dev *hdev) if (!hdev_is_powered(hdev)) return false; - if (!test_and_set_bit(HCI_SERVICE_CACHE, &hdev->dev_flags)) { + if (!hci_dev_test_and_set_flag(hdev, HCI_SERVICE_CACHE)) { queue_delayed_work(hdev->workqueue, &hdev->service_cache, CACHE_TIMEOUT); return true; @@ -2480,7 +2664,7 @@ static int remove_uuid(struct sock *sk, struct hci_dev *hdev, void *data, u16 len) { struct mgmt_cp_remove_uuid *cp = data; - struct pending_cmd *cmd; + struct mgmt_pending_cmd *cmd; struct bt_uuid *match, *tmp; u8 bt_uuid_any[] = { 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0 }; struct hci_request req; @@ -2491,8 +2675,8 @@ static int remove_uuid(struct sock *sk, struct hci_dev *hdev, void *data, hci_dev_lock(hdev); if (pending_eir_or_class(hdev)) { - err = cmd_status(sk, hdev->id, MGMT_OP_REMOVE_UUID, - MGMT_STATUS_BUSY); + err = mgmt_cmd_status(sk, hdev->id, MGMT_OP_REMOVE_UUID, + MGMT_STATUS_BUSY); goto unlock; } @@ -2500,8 +2684,9 @@ static int remove_uuid(struct sock *sk, struct hci_dev *hdev, void *data, hci_uuids_clear(hdev); if (enable_service_cache(hdev)) { - err = cmd_complete(sk, hdev->id, MGMT_OP_REMOVE_UUID, - 0, hdev->dev_class, 3); + err = mgmt_cmd_complete(sk, hdev->id, + MGMT_OP_REMOVE_UUID, + 0, hdev->dev_class, 3); goto unlock; } @@ -2520,8 +2705,8 @@ static int remove_uuid(struct sock *sk, struct hci_dev *hdev, void *data, } if (found == 0) { - err = cmd_status(sk, hdev->id, MGMT_OP_REMOVE_UUID, - MGMT_STATUS_INVALID_PARAMS); + err = mgmt_cmd_status(sk, hdev->id, MGMT_OP_REMOVE_UUID, + MGMT_STATUS_INVALID_PARAMS); goto unlock; } @@ -2536,8 +2721,8 @@ update_class: if (err != -ENODATA) goto unlock; - err = cmd_complete(sk, hdev->id, MGMT_OP_REMOVE_UUID, 0, - hdev->dev_class, 3); + err = mgmt_cmd_complete(sk, hdev->id, MGMT_OP_REMOVE_UUID, 0, + hdev->dev_class, 3); goto unlock; } @@ -2565,27 +2750,27 @@ static int set_dev_class(struct sock *sk, struct hci_dev *hdev, void *data, u16 len) { struct mgmt_cp_set_dev_class *cp = data; - struct pending_cmd *cmd; + struct mgmt_pending_cmd *cmd; struct hci_request req; int err; BT_DBG("request for %s", hdev->name); if (!lmp_bredr_capable(hdev)) - return cmd_status(sk, hdev->id, MGMT_OP_SET_DEV_CLASS, - MGMT_STATUS_NOT_SUPPORTED); + return mgmt_cmd_status(sk, hdev->id, MGMT_OP_SET_DEV_CLASS, + MGMT_STATUS_NOT_SUPPORTED); hci_dev_lock(hdev); if (pending_eir_or_class(hdev)) { - err = cmd_status(sk, hdev->id, MGMT_OP_SET_DEV_CLASS, - MGMT_STATUS_BUSY); + err = mgmt_cmd_status(sk, hdev->id, MGMT_OP_SET_DEV_CLASS, + MGMT_STATUS_BUSY); goto unlock; } if ((cp->minor & 0x03) != 0 || (cp->major & 0xe0) != 0) { - err = cmd_status(sk, hdev->id, MGMT_OP_SET_DEV_CLASS, - MGMT_STATUS_INVALID_PARAMS); + err = mgmt_cmd_status(sk, hdev->id, MGMT_OP_SET_DEV_CLASS, + MGMT_STATUS_INVALID_PARAMS); goto unlock; } @@ -2593,14 +2778,14 @@ static int set_dev_class(struct sock *sk, struct hci_dev *hdev, void *data, hdev->minor_class = cp->minor; if (!hdev_is_powered(hdev)) { - err = cmd_complete(sk, hdev->id, MGMT_OP_SET_DEV_CLASS, 0, - hdev->dev_class, 3); + err = mgmt_cmd_complete(sk, hdev->id, MGMT_OP_SET_DEV_CLASS, 0, + hdev->dev_class, 3); goto unlock; } hci_req_init(&req, hdev); - if (test_and_clear_bit(HCI_SERVICE_CACHE, &hdev->dev_flags)) { + if (hci_dev_test_and_clear_flag(hdev, HCI_SERVICE_CACHE)) { hci_dev_unlock(hdev); cancel_delayed_work_sync(&hdev->service_cache); hci_dev_lock(hdev); @@ -2614,8 +2799,8 @@ static int set_dev_class(struct sock *sk, struct hci_dev *hdev, void *data, if (err != -ENODATA) goto unlock; - err = cmd_complete(sk, hdev->id, MGMT_OP_SET_DEV_CLASS, 0, - hdev->dev_class, 3); + err = mgmt_cmd_complete(sk, hdev->id, MGMT_OP_SET_DEV_CLASS, 0, + hdev->dev_class, 3); goto unlock; } @@ -2645,15 +2830,15 @@ static int load_link_keys(struct sock *sk, struct hci_dev *hdev, void *data, BT_DBG("request for %s", hdev->name); if (!lmp_bredr_capable(hdev)) - return cmd_status(sk, hdev->id, MGMT_OP_LOAD_LINK_KEYS, - MGMT_STATUS_NOT_SUPPORTED); + return mgmt_cmd_status(sk, hdev->id, MGMT_OP_LOAD_LINK_KEYS, + 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); + return mgmt_cmd_status(sk, hdev->id, MGMT_OP_LOAD_LINK_KEYS, + MGMT_STATUS_INVALID_PARAMS); } expected_len = sizeof(*cp) + key_count * @@ -2661,13 +2846,13 @@ static int load_link_keys(struct sock *sk, struct hci_dev *hdev, void *data, if (expected_len != len) { BT_ERR("load_link_keys: expected %u bytes, got %u bytes", expected_len, len); - return cmd_status(sk, hdev->id, MGMT_OP_LOAD_LINK_KEYS, - MGMT_STATUS_INVALID_PARAMS); + return mgmt_cmd_status(sk, hdev->id, MGMT_OP_LOAD_LINK_KEYS, + MGMT_STATUS_INVALID_PARAMS); } if (cp->debug_keys != 0x00 && cp->debug_keys != 0x01) - return cmd_status(sk, hdev->id, MGMT_OP_LOAD_LINK_KEYS, - MGMT_STATUS_INVALID_PARAMS); + return mgmt_cmd_status(sk, hdev->id, MGMT_OP_LOAD_LINK_KEYS, + MGMT_STATUS_INVALID_PARAMS); BT_DBG("%s debug_keys %u key_count %u", hdev->name, cp->debug_keys, key_count); @@ -2676,8 +2861,9 @@ static int load_link_keys(struct sock *sk, struct hci_dev *hdev, void *data, struct mgmt_link_key_info *key = &cp->keys[i]; if (key->addr.type != BDADDR_BREDR || key->type > 0x08) - return cmd_status(sk, hdev->id, MGMT_OP_LOAD_LINK_KEYS, - MGMT_STATUS_INVALID_PARAMS); + return mgmt_cmd_status(sk, hdev->id, + MGMT_OP_LOAD_LINK_KEYS, + MGMT_STATUS_INVALID_PARAMS); } hci_dev_lock(hdev); @@ -2685,11 +2871,10 @@ 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_KEEP_DEBUG_KEYS, - &hdev->dev_flags); + changed = !hci_dev_test_and_set_flag(hdev, HCI_KEEP_DEBUG_KEYS); else - changed = test_and_clear_bit(HCI_KEEP_DEBUG_KEYS, - &hdev->dev_flags); + changed = hci_dev_test_and_clear_flag(hdev, + HCI_KEEP_DEBUG_KEYS); if (changed) new_settings(hdev, NULL); @@ -2707,7 +2892,7 @@ static int load_link_keys(struct sock *sk, struct hci_dev *hdev, void *data, key->type, key->pin_len, NULL); } - cmd_complete(sk, hdev->id, MGMT_OP_LOAD_LINK_KEYS, 0, NULL, 0); + mgmt_cmd_complete(sk, hdev->id, MGMT_OP_LOAD_LINK_KEYS, 0, NULL, 0); hci_dev_unlock(hdev); @@ -2732,7 +2917,7 @@ static int unpair_device(struct sock *sk, struct hci_dev *hdev, void *data, struct mgmt_cp_unpair_device *cp = data; struct mgmt_rp_unpair_device rp; struct hci_cp_disconnect dc; - struct pending_cmd *cmd; + struct mgmt_pending_cmd *cmd; struct hci_conn *conn; int err; @@ -2741,20 +2926,21 @@ static int unpair_device(struct sock *sk, struct hci_dev *hdev, void *data, rp.addr.type = cp->addr.type; if (!bdaddr_type_is_valid(cp->addr.type)) - return cmd_complete(sk, hdev->id, MGMT_OP_UNPAIR_DEVICE, - MGMT_STATUS_INVALID_PARAMS, - &rp, sizeof(rp)); + return mgmt_cmd_complete(sk, hdev->id, MGMT_OP_UNPAIR_DEVICE, + MGMT_STATUS_INVALID_PARAMS, + &rp, sizeof(rp)); if (cp->disconnect != 0x00 && cp->disconnect != 0x01) - return cmd_complete(sk, hdev->id, MGMT_OP_UNPAIR_DEVICE, - MGMT_STATUS_INVALID_PARAMS, - &rp, sizeof(rp)); + return mgmt_cmd_complete(sk, hdev->id, MGMT_OP_UNPAIR_DEVICE, + MGMT_STATUS_INVALID_PARAMS, + &rp, sizeof(rp)); hci_dev_lock(hdev); if (!hdev_is_powered(hdev)) { - err = cmd_complete(sk, hdev->id, MGMT_OP_UNPAIR_DEVICE, - MGMT_STATUS_NOT_POWERED, &rp, sizeof(rp)); + err = mgmt_cmd_complete(sk, hdev->id, MGMT_OP_UNPAIR_DEVICE, + MGMT_STATUS_NOT_POWERED, &rp, + sizeof(rp)); goto unlock; } @@ -2804,8 +2990,9 @@ static int unpair_device(struct sock *sk, struct hci_dev *hdev, void *data, } if (err < 0) { - err = cmd_complete(sk, hdev->id, MGMT_OP_UNPAIR_DEVICE, - MGMT_STATUS_NOT_PAIRED, &rp, sizeof(rp)); + err = mgmt_cmd_complete(sk, hdev->id, MGMT_OP_UNPAIR_DEVICE, + MGMT_STATUS_NOT_PAIRED, &rp, + sizeof(rp)); goto unlock; } @@ -2813,8 +3000,8 @@ static int unpair_device(struct sock *sk, struct hci_dev *hdev, void *data, * link is requested. */ if (!conn) { - err = cmd_complete(sk, hdev->id, MGMT_OP_UNPAIR_DEVICE, 0, - &rp, sizeof(rp)); + err = mgmt_cmd_complete(sk, hdev->id, MGMT_OP_UNPAIR_DEVICE, 0, + &rp, sizeof(rp)); device_unpaired(hdev, &cp->addr.bdaddr, cp->addr.type, sk); goto unlock; } @@ -2844,7 +3031,7 @@ static int disconnect(struct sock *sk, struct hci_dev *hdev, void *data, { struct mgmt_cp_disconnect *cp = data; struct mgmt_rp_disconnect rp; - struct pending_cmd *cmd; + struct mgmt_pending_cmd *cmd; struct hci_conn *conn; int err; @@ -2855,21 +3042,22 @@ static int disconnect(struct sock *sk, struct hci_dev *hdev, void *data, rp.addr.type = cp->addr.type; if (!bdaddr_type_is_valid(cp->addr.type)) - return cmd_complete(sk, hdev->id, MGMT_OP_DISCONNECT, - MGMT_STATUS_INVALID_PARAMS, - &rp, sizeof(rp)); + return mgmt_cmd_complete(sk, hdev->id, MGMT_OP_DISCONNECT, + MGMT_STATUS_INVALID_PARAMS, + &rp, sizeof(rp)); hci_dev_lock(hdev); if (!test_bit(HCI_UP, &hdev->flags)) { - err = cmd_complete(sk, hdev->id, MGMT_OP_DISCONNECT, - MGMT_STATUS_NOT_POWERED, &rp, sizeof(rp)); + err = mgmt_cmd_complete(sk, hdev->id, MGMT_OP_DISCONNECT, + MGMT_STATUS_NOT_POWERED, &rp, + sizeof(rp)); goto failed; } - if (mgmt_pending_find(MGMT_OP_DISCONNECT, hdev)) { - err = cmd_complete(sk, hdev->id, MGMT_OP_DISCONNECT, - MGMT_STATUS_BUSY, &rp, sizeof(rp)); + if (pending_find(MGMT_OP_DISCONNECT, hdev)) { + err = mgmt_cmd_complete(sk, hdev->id, MGMT_OP_DISCONNECT, + MGMT_STATUS_BUSY, &rp, sizeof(rp)); goto failed; } @@ -2880,8 +3068,9 @@ static int disconnect(struct sock *sk, struct hci_dev *hdev, void *data, conn = hci_conn_hash_lookup_ba(hdev, LE_LINK, &cp->addr.bdaddr); if (!conn || conn->state == BT_OPEN || conn->state == BT_CLOSED) { - err = cmd_complete(sk, hdev->id, MGMT_OP_DISCONNECT, - MGMT_STATUS_NOT_CONNECTED, &rp, sizeof(rp)); + err = mgmt_cmd_complete(sk, hdev->id, MGMT_OP_DISCONNECT, + MGMT_STATUS_NOT_CONNECTED, &rp, + sizeof(rp)); goto failed; } @@ -2935,8 +3124,8 @@ static int get_connections(struct sock *sk, struct hci_dev *hdev, void *data, hci_dev_lock(hdev); if (!hdev_is_powered(hdev)) { - err = cmd_status(sk, hdev->id, MGMT_OP_GET_CONNECTIONS, - MGMT_STATUS_NOT_POWERED); + err = mgmt_cmd_status(sk, hdev->id, MGMT_OP_GET_CONNECTIONS, + MGMT_STATUS_NOT_POWERED); goto unlock; } @@ -2969,8 +3158,8 @@ static int get_connections(struct sock *sk, struct hci_dev *hdev, void *data, /* Recalculate length in case of filtered SCO connections, etc */ rp_len = sizeof(*rp) + (i * sizeof(struct mgmt_addr_info)); - err = cmd_complete(sk, hdev->id, MGMT_OP_GET_CONNECTIONS, 0, rp, - rp_len); + err = mgmt_cmd_complete(sk, hdev->id, MGMT_OP_GET_CONNECTIONS, 0, rp, + rp_len); kfree(rp); @@ -2982,7 +3171,7 @@ unlock: static int send_pin_code_neg_reply(struct sock *sk, struct hci_dev *hdev, struct mgmt_cp_pin_code_neg_reply *cp) { - struct pending_cmd *cmd; + struct mgmt_pending_cmd *cmd; int err; cmd = mgmt_pending_add(sk, MGMT_OP_PIN_CODE_NEG_REPLY, hdev, cp, @@ -3004,7 +3193,7 @@ static int pin_code_reply(struct sock *sk, struct hci_dev *hdev, void *data, struct hci_conn *conn; struct mgmt_cp_pin_code_reply *cp = data; struct hci_cp_pin_code_reply reply; - struct pending_cmd *cmd; + struct mgmt_pending_cmd *cmd; int err; BT_DBG(""); @@ -3012,15 +3201,15 @@ static int pin_code_reply(struct sock *sk, struct hci_dev *hdev, void *data, hci_dev_lock(hdev); if (!hdev_is_powered(hdev)) { - err = cmd_status(sk, hdev->id, MGMT_OP_PIN_CODE_REPLY, - MGMT_STATUS_NOT_POWERED); + err = mgmt_cmd_status(sk, hdev->id, MGMT_OP_PIN_CODE_REPLY, + MGMT_STATUS_NOT_POWERED); goto failed; } conn = hci_conn_hash_lookup_ba(hdev, ACL_LINK, &cp->addr.bdaddr); if (!conn) { - err = cmd_status(sk, hdev->id, MGMT_OP_PIN_CODE_REPLY, - MGMT_STATUS_NOT_CONNECTED); + err = mgmt_cmd_status(sk, hdev->id, MGMT_OP_PIN_CODE_REPLY, + MGMT_STATUS_NOT_CONNECTED); goto failed; } @@ -3033,8 +3222,8 @@ static int pin_code_reply(struct sock *sk, struct hci_dev *hdev, void *data, err = send_pin_code_neg_reply(sk, hdev, &ncp); if (err >= 0) - err = cmd_status(sk, hdev->id, MGMT_OP_PIN_CODE_REPLY, - MGMT_STATUS_INVALID_PARAMS); + err = mgmt_cmd_status(sk, hdev->id, MGMT_OP_PIN_CODE_REPLY, + MGMT_STATUS_INVALID_PARAMS); goto failed; } @@ -3068,8 +3257,8 @@ 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); + return mgmt_cmd_complete(sk, hdev->id, MGMT_OP_SET_IO_CAPABILITY, + MGMT_STATUS_INVALID_PARAMS, NULL, 0); hci_dev_lock(hdev); @@ -3080,14 +3269,14 @@ static int set_io_capability(struct sock *sk, struct hci_dev *hdev, void *data, hci_dev_unlock(hdev); - return cmd_complete(sk, hdev->id, MGMT_OP_SET_IO_CAPABILITY, 0, NULL, - 0); + return mgmt_cmd_complete(sk, hdev->id, MGMT_OP_SET_IO_CAPABILITY, 0, + NULL, 0); } -static struct pending_cmd *find_pairing(struct hci_conn *conn) +static struct mgmt_pending_cmd *find_pairing(struct hci_conn *conn) { struct hci_dev *hdev = conn->hdev; - struct pending_cmd *cmd; + struct mgmt_pending_cmd *cmd; list_for_each_entry(cmd, &hdev->mgmt_pending, list) { if (cmd->opcode != MGMT_OP_PAIR_DEVICE) @@ -3102,7 +3291,7 @@ static struct pending_cmd *find_pairing(struct hci_conn *conn) return NULL; } -static int pairing_complete(struct pending_cmd *cmd, u8 status) +static int pairing_complete(struct mgmt_pending_cmd *cmd, u8 status) { struct mgmt_rp_pair_device rp; struct hci_conn *conn = cmd->user_data; @@ -3111,8 +3300,8 @@ static int pairing_complete(struct pending_cmd *cmd, u8 status) bacpy(&rp.addr.bdaddr, &conn->dst); rp.addr.type = link_to_bdaddr(conn->type, conn->dst_type); - err = cmd_complete(cmd->sk, cmd->index, MGMT_OP_PAIR_DEVICE, status, - &rp, sizeof(rp)); + err = mgmt_cmd_complete(cmd->sk, cmd->index, MGMT_OP_PAIR_DEVICE, + status, &rp, sizeof(rp)); /* So we don't get further callbacks for this connection */ conn->connect_cfm_cb = NULL; @@ -3134,7 +3323,7 @@ static int pairing_complete(struct pending_cmd *cmd, u8 status) void mgmt_smp_complete(struct hci_conn *conn, bool complete) { u8 status = complete ? MGMT_STATUS_SUCCESS : MGMT_STATUS_FAILED; - struct pending_cmd *cmd; + struct mgmt_pending_cmd *cmd; cmd = find_pairing(conn); if (cmd) { @@ -3145,7 +3334,7 @@ void mgmt_smp_complete(struct hci_conn *conn, bool complete) static void pairing_complete_cb(struct hci_conn *conn, u8 status) { - struct pending_cmd *cmd; + struct mgmt_pending_cmd *cmd; BT_DBG("status %u", status); @@ -3161,7 +3350,7 @@ static void pairing_complete_cb(struct hci_conn *conn, u8 status) static void le_pairing_complete_cb(struct hci_conn *conn, u8 status) { - struct pending_cmd *cmd; + struct mgmt_pending_cmd *cmd; BT_DBG("status %u", status); @@ -3183,7 +3372,7 @@ static int pair_device(struct sock *sk, struct hci_dev *hdev, void *data, { struct mgmt_cp_pair_device *cp = data; struct mgmt_rp_pair_device rp; - struct pending_cmd *cmd; + struct mgmt_pending_cmd *cmd; u8 sec_level, auth_type; struct hci_conn *conn; int err; @@ -3195,20 +3384,28 @@ static int pair_device(struct sock *sk, struct hci_dev *hdev, void *data, rp.addr.type = cp->addr.type; if (!bdaddr_type_is_valid(cp->addr.type)) - return cmd_complete(sk, hdev->id, MGMT_OP_PAIR_DEVICE, - MGMT_STATUS_INVALID_PARAMS, - &rp, sizeof(rp)); + return mgmt_cmd_complete(sk, hdev->id, MGMT_OP_PAIR_DEVICE, + 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)); + return mgmt_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)) { - err = cmd_complete(sk, hdev->id, MGMT_OP_PAIR_DEVICE, - MGMT_STATUS_NOT_POWERED, &rp, sizeof(rp)); + err = mgmt_cmd_complete(sk, hdev->id, MGMT_OP_PAIR_DEVICE, + MGMT_STATUS_NOT_POWERED, &rp, + sizeof(rp)); + goto unlock; + } + + if (hci_bdaddr_is_paired(hdev, &cp->addr.bdaddr, cp->addr.type)) { + err = mgmt_cmd_complete(sk, hdev->id, MGMT_OP_PAIR_DEVICE, + MGMT_STATUS_ALREADY_PAIRED, &rp, + sizeof(rp)); goto unlock; } @@ -3249,19 +3446,22 @@ static int pair_device(struct sock *sk, struct hci_dev *hdev, void *data, if (PTR_ERR(conn) == -EBUSY) status = MGMT_STATUS_BUSY; + else if (PTR_ERR(conn) == -EOPNOTSUPP) + status = MGMT_STATUS_NOT_SUPPORTED; + else if (PTR_ERR(conn) == -ECONNREFUSED) + status = MGMT_STATUS_REJECTED; else status = MGMT_STATUS_CONNECT_FAILED; - err = cmd_complete(sk, hdev->id, MGMT_OP_PAIR_DEVICE, - status, &rp, - sizeof(rp)); + err = mgmt_cmd_complete(sk, hdev->id, MGMT_OP_PAIR_DEVICE, + status, &rp, sizeof(rp)); goto unlock; } if (conn->connect_cfm_cb) { hci_conn_drop(conn); - err = cmd_complete(sk, hdev->id, MGMT_OP_PAIR_DEVICE, - MGMT_STATUS_BUSY, &rp, sizeof(rp)); + err = mgmt_cmd_complete(sk, hdev->id, MGMT_OP_PAIR_DEVICE, + MGMT_STATUS_BUSY, &rp, sizeof(rp)); goto unlock; } @@ -3305,7 +3505,7 @@ static int cancel_pair_device(struct sock *sk, struct hci_dev *hdev, void *data, u16 len) { struct mgmt_addr_info *addr = data; - struct pending_cmd *cmd; + struct mgmt_pending_cmd *cmd; struct hci_conn *conn; int err; @@ -3314,31 +3514,31 @@ static int cancel_pair_device(struct sock *sk, struct hci_dev *hdev, void *data, hci_dev_lock(hdev); if (!hdev_is_powered(hdev)) { - err = cmd_status(sk, hdev->id, MGMT_OP_CANCEL_PAIR_DEVICE, - MGMT_STATUS_NOT_POWERED); + err = mgmt_cmd_status(sk, hdev->id, MGMT_OP_CANCEL_PAIR_DEVICE, + MGMT_STATUS_NOT_POWERED); goto unlock; } - cmd = mgmt_pending_find(MGMT_OP_PAIR_DEVICE, hdev); + cmd = pending_find(MGMT_OP_PAIR_DEVICE, hdev); if (!cmd) { - err = cmd_status(sk, hdev->id, MGMT_OP_CANCEL_PAIR_DEVICE, - MGMT_STATUS_INVALID_PARAMS); + err = mgmt_cmd_status(sk, hdev->id, MGMT_OP_CANCEL_PAIR_DEVICE, + MGMT_STATUS_INVALID_PARAMS); goto unlock; } conn = cmd->user_data; if (bacmp(&addr->bdaddr, &conn->dst) != 0) { - err = cmd_status(sk, hdev->id, MGMT_OP_CANCEL_PAIR_DEVICE, - MGMT_STATUS_INVALID_PARAMS); + err = mgmt_cmd_status(sk, hdev->id, MGMT_OP_CANCEL_PAIR_DEVICE, + MGMT_STATUS_INVALID_PARAMS); goto unlock; } cmd->cmd_complete(cmd, MGMT_STATUS_CANCELLED); mgmt_pending_remove(cmd); - err = cmd_complete(sk, hdev->id, MGMT_OP_CANCEL_PAIR_DEVICE, 0, - addr, sizeof(*addr)); + err = mgmt_cmd_complete(sk, hdev->id, MGMT_OP_CANCEL_PAIR_DEVICE, 0, + addr, sizeof(*addr)); unlock: hci_dev_unlock(hdev); return err; @@ -3348,16 +3548,16 @@ static int user_pairing_resp(struct sock *sk, struct hci_dev *hdev, struct mgmt_addr_info *addr, u16 mgmt_op, u16 hci_op, __le32 passkey) { - struct pending_cmd *cmd; + struct mgmt_pending_cmd *cmd; struct hci_conn *conn; int err; hci_dev_lock(hdev); if (!hdev_is_powered(hdev)) { - err = cmd_complete(sk, hdev->id, mgmt_op, - MGMT_STATUS_NOT_POWERED, addr, - sizeof(*addr)); + err = mgmt_cmd_complete(sk, hdev->id, mgmt_op, + MGMT_STATUS_NOT_POWERED, addr, + sizeof(*addr)); goto done; } @@ -3367,22 +3567,22 @@ static int user_pairing_resp(struct sock *sk, struct hci_dev *hdev, conn = hci_conn_hash_lookup_ba(hdev, LE_LINK, &addr->bdaddr); if (!conn) { - err = cmd_complete(sk, hdev->id, mgmt_op, - MGMT_STATUS_NOT_CONNECTED, addr, - sizeof(*addr)); + err = mgmt_cmd_complete(sk, hdev->id, mgmt_op, + MGMT_STATUS_NOT_CONNECTED, addr, + sizeof(*addr)); goto done; } if (addr->type == BDADDR_LE_PUBLIC || addr->type == BDADDR_LE_RANDOM) { err = smp_user_confirm_reply(conn, mgmt_op, passkey); if (!err) - err = cmd_complete(sk, hdev->id, mgmt_op, - MGMT_STATUS_SUCCESS, addr, - sizeof(*addr)); + err = mgmt_cmd_complete(sk, hdev->id, mgmt_op, + MGMT_STATUS_SUCCESS, addr, + sizeof(*addr)); else - err = cmd_complete(sk, hdev->id, mgmt_op, - MGMT_STATUS_FAILED, addr, - sizeof(*addr)); + err = mgmt_cmd_complete(sk, hdev->id, mgmt_op, + MGMT_STATUS_FAILED, addr, + sizeof(*addr)); goto done; } @@ -3434,8 +3634,8 @@ static int user_confirm_reply(struct sock *sk, struct hci_dev *hdev, void *data, BT_DBG(""); if (len != sizeof(*cp)) - return cmd_status(sk, hdev->id, MGMT_OP_USER_CONFIRM_REPLY, - MGMT_STATUS_INVALID_PARAMS); + return mgmt_cmd_status(sk, hdev->id, MGMT_OP_USER_CONFIRM_REPLY, + MGMT_STATUS_INVALID_PARAMS); return user_pairing_resp(sk, hdev, &cp->addr, MGMT_OP_USER_CONFIRM_REPLY, @@ -3491,24 +3691,24 @@ static void update_name(struct hci_request *req) static void set_name_complete(struct hci_dev *hdev, u8 status, u16 opcode) { struct mgmt_cp_set_local_name *cp; - struct pending_cmd *cmd; + struct mgmt_pending_cmd *cmd; BT_DBG("status 0x%02x", status); hci_dev_lock(hdev); - cmd = mgmt_pending_find(MGMT_OP_SET_LOCAL_NAME, hdev); + cmd = pending_find(MGMT_OP_SET_LOCAL_NAME, hdev); if (!cmd) goto unlock; cp = cmd->param; if (status) - cmd_status(cmd->sk, hdev->id, MGMT_OP_SET_LOCAL_NAME, - mgmt_status(status)); + mgmt_cmd_status(cmd->sk, hdev->id, MGMT_OP_SET_LOCAL_NAME, + mgmt_status(status)); else - cmd_complete(cmd->sk, hdev->id, MGMT_OP_SET_LOCAL_NAME, 0, - cp, sizeof(*cp)); + mgmt_cmd_complete(cmd->sk, hdev->id, MGMT_OP_SET_LOCAL_NAME, 0, + cp, sizeof(*cp)); mgmt_pending_remove(cmd); @@ -3520,7 +3720,7 @@ static int set_local_name(struct sock *sk, struct hci_dev *hdev, void *data, u16 len) { struct mgmt_cp_set_local_name *cp = data; - struct pending_cmd *cmd; + struct mgmt_pending_cmd *cmd; struct hci_request req; int err; @@ -3534,8 +3734,8 @@ static int set_local_name(struct sock *sk, struct hci_dev *hdev, void *data, if (!memcmp(hdev->dev_name, cp->name, sizeof(hdev->dev_name)) && !memcmp(hdev->short_name, cp->short_name, sizeof(hdev->short_name))) { - err = cmd_complete(sk, hdev->id, MGMT_OP_SET_LOCAL_NAME, 0, - data, len); + err = mgmt_cmd_complete(sk, hdev->id, MGMT_OP_SET_LOCAL_NAME, 0, + data, len); goto failed; } @@ -3544,13 +3744,13 @@ static int set_local_name(struct sock *sk, struct hci_dev *hdev, void *data, if (!hdev_is_powered(hdev)) { memcpy(hdev->dev_name, cp->name, sizeof(hdev->dev_name)); - err = cmd_complete(sk, hdev->id, MGMT_OP_SET_LOCAL_NAME, 0, - data, len); + err = mgmt_cmd_complete(sk, hdev->id, MGMT_OP_SET_LOCAL_NAME, 0, + data, len); if (err < 0) goto failed; - err = mgmt_event(MGMT_EV_LOCAL_NAME_CHANGED, hdev, data, len, - sk); + err = mgmt_generic_event(MGMT_EV_LOCAL_NAME_CHANGED, hdev, + data, len, sk); goto failed; } @@ -3585,10 +3785,70 @@ failed: return err; } +static void read_local_oob_data_complete(struct hci_dev *hdev, u8 status, + u16 opcode, struct sk_buff *skb) +{ + struct mgmt_rp_read_local_oob_data mgmt_rp; + size_t rp_size = sizeof(mgmt_rp); + struct mgmt_pending_cmd *cmd; + + BT_DBG("%s status %u", hdev->name, status); + + cmd = pending_find(MGMT_OP_READ_LOCAL_OOB_DATA, hdev); + if (!cmd) + return; + + if (status || !skb) { + mgmt_cmd_status(cmd->sk, hdev->id, MGMT_OP_READ_LOCAL_OOB_DATA, + status ? mgmt_status(status) : MGMT_STATUS_FAILED); + goto remove; + } + + memset(&mgmt_rp, 0, sizeof(mgmt_rp)); + + if (opcode == HCI_OP_READ_LOCAL_OOB_DATA) { + struct hci_rp_read_local_oob_data *rp = (void *) skb->data; + + if (skb->len < sizeof(*rp)) { + mgmt_cmd_status(cmd->sk, hdev->id, + MGMT_OP_READ_LOCAL_OOB_DATA, + MGMT_STATUS_FAILED); + goto remove; + } + + memcpy(mgmt_rp.hash192, rp->hash, sizeof(rp->hash)); + memcpy(mgmt_rp.rand192, rp->rand, sizeof(rp->rand)); + + rp_size -= sizeof(mgmt_rp.hash256) + sizeof(mgmt_rp.rand256); + } else { + struct hci_rp_read_local_oob_ext_data *rp = (void *) skb->data; + + if (skb->len < sizeof(*rp)) { + mgmt_cmd_status(cmd->sk, hdev->id, + MGMT_OP_READ_LOCAL_OOB_DATA, + MGMT_STATUS_FAILED); + goto remove; + } + + memcpy(mgmt_rp.hash192, rp->hash192, sizeof(rp->hash192)); + memcpy(mgmt_rp.rand192, rp->rand192, sizeof(rp->rand192)); + + memcpy(mgmt_rp.hash256, rp->hash256, sizeof(rp->hash256)); + memcpy(mgmt_rp.rand256, rp->rand256, sizeof(rp->rand256)); + } + + mgmt_cmd_complete(cmd->sk, hdev->id, MGMT_OP_READ_LOCAL_OOB_DATA, + MGMT_STATUS_SUCCESS, &mgmt_rp, rp_size); + +remove: + mgmt_pending_remove(cmd); +} + static int read_local_oob_data(struct sock *sk, struct hci_dev *hdev, void *data, u16 data_len) { - struct pending_cmd *cmd; + struct mgmt_pending_cmd *cmd; + struct hci_request req; int err; BT_DBG("%s", hdev->name); @@ -3596,20 +3856,20 @@ static int read_local_oob_data(struct sock *sk, struct hci_dev *hdev, hci_dev_lock(hdev); if (!hdev_is_powered(hdev)) { - err = cmd_status(sk, hdev->id, MGMT_OP_READ_LOCAL_OOB_DATA, - MGMT_STATUS_NOT_POWERED); + err = mgmt_cmd_status(sk, hdev->id, MGMT_OP_READ_LOCAL_OOB_DATA, + MGMT_STATUS_NOT_POWERED); goto unlock; } if (!lmp_ssp_capable(hdev)) { - err = cmd_status(sk, hdev->id, MGMT_OP_READ_LOCAL_OOB_DATA, - MGMT_STATUS_NOT_SUPPORTED); + err = mgmt_cmd_status(sk, hdev->id, MGMT_OP_READ_LOCAL_OOB_DATA, + MGMT_STATUS_NOT_SUPPORTED); goto unlock; } - if (mgmt_pending_find(MGMT_OP_READ_LOCAL_OOB_DATA, hdev)) { - err = cmd_status(sk, hdev->id, MGMT_OP_READ_LOCAL_OOB_DATA, - MGMT_STATUS_BUSY); + if (pending_find(MGMT_OP_READ_LOCAL_OOB_DATA, hdev)) { + err = mgmt_cmd_status(sk, hdev->id, MGMT_OP_READ_LOCAL_OOB_DATA, + MGMT_STATUS_BUSY); goto unlock; } @@ -3619,12 +3879,14 @@ static int read_local_oob_data(struct sock *sk, struct hci_dev *hdev, goto unlock; } + hci_req_init(&req, hdev); + if (bredr_sc_enabled(hdev)) - err = hci_send_cmd(hdev, HCI_OP_READ_LOCAL_OOB_EXT_DATA, - 0, NULL); + hci_req_add(&req, HCI_OP_READ_LOCAL_OOB_EXT_DATA, 0, NULL); else - err = hci_send_cmd(hdev, HCI_OP_READ_LOCAL_OOB_DATA, 0, NULL); + hci_req_add(&req, HCI_OP_READ_LOCAL_OOB_DATA, 0, NULL); + err = hci_req_run_skb(&req, read_local_oob_data_complete); if (err < 0) mgmt_pending_remove(cmd); @@ -3642,9 +3904,10 @@ static int add_remote_oob_data(struct sock *sk, struct hci_dev *hdev, BT_DBG("%s ", hdev->name); if (!bdaddr_type_is_valid(addr->type)) - return cmd_complete(sk, hdev->id, MGMT_OP_ADD_REMOTE_OOB_DATA, - MGMT_STATUS_INVALID_PARAMS, addr, - sizeof(*addr)); + return mgmt_cmd_complete(sk, hdev->id, + MGMT_OP_ADD_REMOTE_OOB_DATA, + MGMT_STATUS_INVALID_PARAMS, + addr, sizeof(*addr)); hci_dev_lock(hdev); @@ -3653,10 +3916,10 @@ static int add_remote_oob_data(struct sock *sk, struct hci_dev *hdev, u8 status; if (cp->addr.type != BDADDR_BREDR) { - err = cmd_complete(sk, hdev->id, - MGMT_OP_ADD_REMOTE_OOB_DATA, - MGMT_STATUS_INVALID_PARAMS, - &cp->addr, sizeof(cp->addr)); + err = mgmt_cmd_complete(sk, hdev->id, + MGMT_OP_ADD_REMOTE_OOB_DATA, + MGMT_STATUS_INVALID_PARAMS, + &cp->addr, sizeof(cp->addr)); goto unlock; } @@ -3668,8 +3931,9 @@ static int add_remote_oob_data(struct sock *sk, struct hci_dev *hdev, else status = MGMT_STATUS_SUCCESS; - err = cmd_complete(sk, hdev->id, MGMT_OP_ADD_REMOTE_OOB_DATA, - status, &cp->addr, sizeof(cp->addr)); + err = mgmt_cmd_complete(sk, hdev->id, + MGMT_OP_ADD_REMOTE_OOB_DATA, status, + &cp->addr, sizeof(cp->addr)); } else if (len == MGMT_ADD_REMOTE_OOB_EXT_DATA_SIZE) { struct mgmt_cp_add_remote_oob_ext_data *cp = data; u8 *rand192, *hash192, *rand256, *hash256; @@ -3681,10 +3945,10 @@ static int add_remote_oob_data(struct sock *sk, struct hci_dev *hdev, */ if (memcmp(cp->rand192, ZERO_KEY, 16) || memcmp(cp->hash192, ZERO_KEY, 16)) { - err = cmd_complete(sk, hdev->id, - MGMT_OP_ADD_REMOTE_OOB_DATA, - MGMT_STATUS_INVALID_PARAMS, - addr, sizeof(*addr)); + err = mgmt_cmd_complete(sk, hdev->id, + MGMT_OP_ADD_REMOTE_OOB_DATA, + MGMT_STATUS_INVALID_PARAMS, + addr, sizeof(*addr)); goto unlock; } @@ -3724,12 +3988,13 @@ static int add_remote_oob_data(struct sock *sk, struct hci_dev *hdev, else status = MGMT_STATUS_SUCCESS; - err = cmd_complete(sk, hdev->id, MGMT_OP_ADD_REMOTE_OOB_DATA, - status, &cp->addr, sizeof(cp->addr)); + err = mgmt_cmd_complete(sk, hdev->id, + MGMT_OP_ADD_REMOTE_OOB_DATA, + status, &cp->addr, sizeof(cp->addr)); } else { BT_ERR("add_remote_oob_data: invalid length of %u bytes", len); - err = cmd_status(sk, hdev->id, MGMT_OP_ADD_REMOTE_OOB_DATA, - MGMT_STATUS_INVALID_PARAMS); + err = mgmt_cmd_status(sk, hdev->id, MGMT_OP_ADD_REMOTE_OOB_DATA, + MGMT_STATUS_INVALID_PARAMS); } unlock: @@ -3747,9 +4012,10 @@ static int remove_remote_oob_data(struct sock *sk, struct hci_dev *hdev, BT_DBG("%s", hdev->name); if (cp->addr.type != BDADDR_BREDR) - return cmd_complete(sk, hdev->id, MGMT_OP_REMOVE_REMOTE_OOB_DATA, - MGMT_STATUS_INVALID_PARAMS, - &cp->addr, sizeof(cp->addr)); + return mgmt_cmd_complete(sk, hdev->id, + MGMT_OP_REMOVE_REMOTE_OOB_DATA, + MGMT_STATUS_INVALID_PARAMS, + &cp->addr, sizeof(cp->addr)); hci_dev_lock(hdev); @@ -3766,100 +4032,136 @@ static int remove_remote_oob_data(struct sock *sk, struct hci_dev *hdev, status = MGMT_STATUS_SUCCESS; done: - err = cmd_complete(sk, hdev->id, MGMT_OP_REMOVE_REMOTE_OOB_DATA, - status, &cp->addr, sizeof(cp->addr)); + err = mgmt_cmd_complete(sk, hdev->id, MGMT_OP_REMOVE_REMOTE_OOB_DATA, + status, &cp->addr, sizeof(cp->addr)); hci_dev_unlock(hdev); return err; } -static bool trigger_discovery(struct hci_request *req, u8 *status) +static bool trigger_bredr_inquiry(struct hci_request *req, u8 *status) { struct hci_dev *hdev = req->hdev; - struct hci_cp_le_set_scan_param param_cp; - struct hci_cp_le_set_scan_enable enable_cp; - struct hci_cp_inquiry inq_cp; + struct hci_cp_inquiry cp; /* General inquiry access code (GIAC) */ u8 lap[3] = { 0x33, 0x8b, 0x9e }; + + *status = mgmt_bredr_support(hdev); + if (*status) + return false; + + if (hci_dev_test_flag(hdev, HCI_INQUIRY)) { + *status = MGMT_STATUS_BUSY; + return false; + } + + hci_inquiry_cache_flush(hdev); + + memset(&cp, 0, sizeof(cp)); + memcpy(&cp.lap, lap, sizeof(cp.lap)); + cp.length = DISCOV_BREDR_INQUIRY_LEN; + + hci_req_add(req, HCI_OP_INQUIRY, sizeof(cp), &cp); + + return true; +} + +static bool trigger_le_scan(struct hci_request *req, u16 interval, u8 *status) +{ + struct hci_dev *hdev = req->hdev; + struct hci_cp_le_set_scan_param param_cp; + struct hci_cp_le_set_scan_enable enable_cp; u8 own_addr_type; int err; - switch (hdev->discovery.type) { - case DISCOV_TYPE_BREDR: - *status = mgmt_bredr_support(hdev); - if (*status) - return false; + *status = mgmt_le_support(hdev); + if (*status) + return false; - if (test_bit(HCI_INQUIRY, &hdev->flags)) { - *status = MGMT_STATUS_BUSY; + if (hci_dev_test_flag(hdev, HCI_LE_ADV)) { + /* 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)) { + *status = MGMT_STATUS_REJECTED; return false; } - hci_inquiry_cache_flush(hdev); + disable_advertising(req); + } - memset(&inq_cp, 0, sizeof(inq_cp)); - memcpy(&inq_cp.lap, lap, sizeof(inq_cp.lap)); - inq_cp.length = DISCOV_BREDR_INQUIRY_LEN; - hci_req_add(req, HCI_OP_INQUIRY, sizeof(inq_cp), &inq_cp); - break; + /* If controller is scanning, it means the background scanning is + * running. Thus, we should temporarily stop it in order to set the + * discovery scanning parameters. + */ + if (hci_dev_test_flag(hdev, HCI_LE_SCAN)) + hci_req_add_le_scan_disable(req); - case DISCOV_TYPE_LE: - case DISCOV_TYPE_INTERLEAVED: - *status = mgmt_le_support(hdev); - if (*status) - return false; + /* All active scans will be done with either a resolvable private + * address (when privacy feature has been enabled) or non-resolvable + * private address. + */ + err = hci_update_random_address(req, true, &own_addr_type); + if (err < 0) { + *status = MGMT_STATUS_FAILED; + return false; + } - if (hdev->discovery.type == DISCOV_TYPE_INTERLEAVED && - !test_bit(HCI_BREDR_ENABLED, &hdev->dev_flags)) { - *status = MGMT_STATUS_NOT_SUPPORTED; + memset(¶m_cp, 0, sizeof(param_cp)); + param_cp.type = LE_SCAN_ACTIVE; + param_cp.interval = cpu_to_le16(interval); + param_cp.window = cpu_to_le16(DISCOV_LE_SCAN_WIN); + param_cp.own_address_type = own_addr_type; + + hci_req_add(req, HCI_OP_LE_SET_SCAN_PARAM, sizeof(param_cp), + ¶m_cp); + + memset(&enable_cp, 0, sizeof(enable_cp)); + enable_cp.enable = LE_SCAN_ENABLE; + enable_cp.filter_dup = LE_SCAN_FILTER_DUP_ENABLE; + + hci_req_add(req, HCI_OP_LE_SET_SCAN_ENABLE, sizeof(enable_cp), + &enable_cp); + + return true; +} + +static bool trigger_discovery(struct hci_request *req, u8 *status) +{ + struct hci_dev *hdev = req->hdev; + + switch (hdev->discovery.type) { + case DISCOV_TYPE_BREDR: + if (!trigger_bredr_inquiry(req, status)) return false; - } + break; - if (test_bit(HCI_LE_ADV, &hdev->dev_flags)) { - /* Don't let discovery abort an outgoing - * connection attempt that's using directed - * advertising. + case DISCOV_TYPE_INTERLEAVED: + if (test_bit(HCI_QUIRK_SIMULTANEOUS_DISCOVERY, + &hdev->quirks)) { + /* During simultaneous discovery, we double LE scan + * interval. We must leave some time for the controller + * to do BR/EDR inquiry. */ - if (hci_conn_hash_lookup_state(hdev, LE_LINK, - BT_CONNECT)) { - *status = MGMT_STATUS_REJECTED; + if (!trigger_le_scan(req, DISCOV_LE_SCAN_INT * 2, + status)) return false; - } - disable_advertising(req); - } - - /* If controller is scanning, it means the background scanning - * is running. Thus, we should temporarily stop it in order to - * set the discovery scanning parameters. - */ - if (test_bit(HCI_LE_SCAN, &hdev->dev_flags)) - hci_req_add_le_scan_disable(req); + if (!trigger_bredr_inquiry(req, status)) + return false; - memset(¶m_cp, 0, sizeof(param_cp)); + return true; + } - /* All active scans will be done with either a resolvable - * private address (when privacy feature has been enabled) - * or non-resolvable private address. - */ - err = hci_update_random_address(req, true, &own_addr_type); - if (err < 0) { - *status = MGMT_STATUS_FAILED; + if (!hci_dev_test_flag(hdev, HCI_BREDR_ENABLED)) { + *status = MGMT_STATUS_NOT_SUPPORTED; return false; } + /* fall through */ - param_cp.type = LE_SCAN_ACTIVE; - param_cp.interval = cpu_to_le16(DISCOV_LE_SCAN_INT); - param_cp.window = cpu_to_le16(DISCOV_LE_SCAN_WIN); - param_cp.own_address_type = own_addr_type; - hci_req_add(req, HCI_OP_LE_SET_SCAN_PARAM, sizeof(param_cp), - ¶m_cp); - - memset(&enable_cp, 0, sizeof(enable_cp)); - enable_cp.enable = LE_SCAN_ENABLE; - enable_cp.filter_dup = LE_SCAN_FILTER_DUP_ENABLE; - hci_req_add(req, HCI_OP_LE_SET_SCAN_ENABLE, sizeof(enable_cp), - &enable_cp); + case DISCOV_TYPE_LE: + if (!trigger_le_scan(req, DISCOV_LE_SCAN_INT, status)) + return false; break; default: @@ -3873,16 +4175,16 @@ static bool trigger_discovery(struct hci_request *req, u8 *status) static void start_discovery_complete(struct hci_dev *hdev, u8 status, u16 opcode) { - struct pending_cmd *cmd; + struct mgmt_pending_cmd *cmd; unsigned long timeout; BT_DBG("status %d", status); hci_dev_lock(hdev); - cmd = mgmt_pending_find(MGMT_OP_START_DISCOVERY, hdev); + cmd = pending_find(MGMT_OP_START_DISCOVERY, hdev); if (!cmd) - cmd = mgmt_pending_find(MGMT_OP_START_SERVICE_DISCOVERY, hdev); + cmd = pending_find(MGMT_OP_START_SERVICE_DISCOVERY, hdev); if (cmd) { cmd->cmd_complete(cmd, mgmt_status(status)); @@ -3904,7 +4206,18 @@ static void start_discovery_complete(struct hci_dev *hdev, u8 status, timeout = msecs_to_jiffies(DISCOV_LE_TIMEOUT); break; case DISCOV_TYPE_INTERLEAVED: - timeout = msecs_to_jiffies(hdev->discov_interleaved_timeout); + /* When running simultaneous discovery, the LE scanning time + * should occupy the whole discovery time sine BR/EDR inquiry + * and LE scanning are scheduled by the controller. + * + * For interleaving discovery in comparison, BR/EDR inquiry + * and LE scanning are done sequentially with separate + * timeouts. + */ + if (test_bit(HCI_QUIRK_SIMULTANEOUS_DISCOVERY, &hdev->quirks)) + timeout = msecs_to_jiffies(DISCOV_LE_TIMEOUT); + else + timeout = msecs_to_jiffies(hdev->discov_interleaved_timeout); break; case DISCOV_TYPE_BREDR: timeout = 0; @@ -3923,8 +4236,7 @@ static void start_discovery_complete(struct hci_dev *hdev, u8 status, */ if (test_bit(HCI_QUIRK_STRICT_DUPLICATE_FILTER, &hdev->quirks) && - (hdev->discovery.uuid_count > 0 || - hdev->discovery.rssi != HCI_RSSI_INVALID)) { + hdev->discovery.result_filtering) { hdev->discovery.scan_start = jiffies; hdev->discovery.scan_duration = timeout; } @@ -3941,7 +4253,7 @@ static int start_discovery(struct sock *sk, struct hci_dev *hdev, void *data, u16 len) { struct mgmt_cp_start_discovery *cp = data; - struct pending_cmd *cmd; + struct mgmt_pending_cmd *cmd; struct hci_request req; u8 status; int err; @@ -3951,17 +4263,17 @@ static int start_discovery(struct sock *sk, struct hci_dev *hdev, hci_dev_lock(hdev); if (!hdev_is_powered(hdev)) { - err = cmd_complete(sk, hdev->id, MGMT_OP_START_DISCOVERY, - MGMT_STATUS_NOT_POWERED, - &cp->type, sizeof(cp->type)); + err = mgmt_cmd_complete(sk, hdev->id, MGMT_OP_START_DISCOVERY, + MGMT_STATUS_NOT_POWERED, + &cp->type, sizeof(cp->type)); goto failed; } if (hdev->discovery.state != DISCOVERY_STOPPED || - test_bit(HCI_PERIODIC_INQ, &hdev->dev_flags)) { - err = cmd_complete(sk, hdev->id, MGMT_OP_START_DISCOVERY, - MGMT_STATUS_BUSY, &cp->type, - sizeof(cp->type)); + hci_dev_test_flag(hdev, HCI_PERIODIC_INQ)) { + err = mgmt_cmd_complete(sk, hdev->id, MGMT_OP_START_DISCOVERY, + MGMT_STATUS_BUSY, &cp->type, + sizeof(cp->type)); goto failed; } @@ -3984,8 +4296,8 @@ static int start_discovery(struct sock *sk, struct hci_dev *hdev, hci_req_init(&req, hdev); if (!trigger_discovery(&req, &status)) { - err = cmd_complete(sk, hdev->id, MGMT_OP_START_DISCOVERY, - status, &cp->type, sizeof(cp->type)); + err = mgmt_cmd_complete(sk, hdev->id, MGMT_OP_START_DISCOVERY, + status, &cp->type, sizeof(cp->type)); mgmt_pending_remove(cmd); goto failed; } @@ -4003,17 +4315,18 @@ failed: return err; } -static int service_discovery_cmd_complete(struct pending_cmd *cmd, u8 status) +static int service_discovery_cmd_complete(struct mgmt_pending_cmd *cmd, + u8 status) { - return cmd_complete(cmd->sk, cmd->index, cmd->opcode, status, - cmd->param, 1); + return mgmt_cmd_complete(cmd->sk, cmd->index, cmd->opcode, status, + cmd->param, 1); } static int start_service_discovery(struct sock *sk, struct hci_dev *hdev, void *data, u16 len) { struct mgmt_cp_start_service_discovery *cp = data; - struct pending_cmd *cmd; + struct mgmt_pending_cmd *cmd; struct hci_request req; const u16 max_uuid_count = ((U16_MAX - sizeof(*cp)) / 16); u16 uuid_count, expected_len; @@ -4025,19 +4338,19 @@ static int start_service_discovery(struct sock *sk, struct hci_dev *hdev, hci_dev_lock(hdev); if (!hdev_is_powered(hdev)) { - err = cmd_complete(sk, hdev->id, - MGMT_OP_START_SERVICE_DISCOVERY, - MGMT_STATUS_NOT_POWERED, - &cp->type, sizeof(cp->type)); + err = mgmt_cmd_complete(sk, hdev->id, + MGMT_OP_START_SERVICE_DISCOVERY, + MGMT_STATUS_NOT_POWERED, + &cp->type, sizeof(cp->type)); goto failed; } if (hdev->discovery.state != DISCOVERY_STOPPED || - test_bit(HCI_PERIODIC_INQ, &hdev->dev_flags)) { - err = cmd_complete(sk, hdev->id, - MGMT_OP_START_SERVICE_DISCOVERY, - MGMT_STATUS_BUSY, &cp->type, - sizeof(cp->type)); + hci_dev_test_flag(hdev, HCI_PERIODIC_INQ)) { + err = mgmt_cmd_complete(sk, hdev->id, + MGMT_OP_START_SERVICE_DISCOVERY, + MGMT_STATUS_BUSY, &cp->type, + sizeof(cp->type)); goto failed; } @@ -4045,10 +4358,10 @@ static int start_service_discovery(struct sock *sk, struct hci_dev *hdev, if (uuid_count > max_uuid_count) { BT_ERR("service_discovery: too big uuid_count value %u", uuid_count); - err = cmd_complete(sk, hdev->id, - MGMT_OP_START_SERVICE_DISCOVERY, - MGMT_STATUS_INVALID_PARAMS, &cp->type, - sizeof(cp->type)); + err = mgmt_cmd_complete(sk, hdev->id, + MGMT_OP_START_SERVICE_DISCOVERY, + MGMT_STATUS_INVALID_PARAMS, &cp->type, + sizeof(cp->type)); goto failed; } @@ -4056,10 +4369,10 @@ static int start_service_discovery(struct sock *sk, struct hci_dev *hdev, if (expected_len != len) { BT_ERR("service_discovery: expected %u bytes, got %u bytes", expected_len, len); - err = cmd_complete(sk, hdev->id, - MGMT_OP_START_SERVICE_DISCOVERY, - MGMT_STATUS_INVALID_PARAMS, &cp->type, - sizeof(cp->type)); + err = mgmt_cmd_complete(sk, hdev->id, + MGMT_OP_START_SERVICE_DISCOVERY, + MGMT_STATUS_INVALID_PARAMS, &cp->type, + sizeof(cp->type)); goto failed; } @@ -4077,6 +4390,7 @@ static int start_service_discovery(struct sock *sk, struct hci_dev *hdev, */ hci_discovery_filter_clear(hdev); + hdev->discovery.result_filtering = true; hdev->discovery.type = cp->type; hdev->discovery.rssi = cp->rssi; hdev->discovery.uuid_count = uuid_count; @@ -4085,10 +4399,10 @@ static int start_service_discovery(struct sock *sk, struct hci_dev *hdev, hdev->discovery.uuids = kmemdup(cp->uuids, uuid_count * 16, GFP_KERNEL); if (!hdev->discovery.uuids) { - err = cmd_complete(sk, hdev->id, - MGMT_OP_START_SERVICE_DISCOVERY, - MGMT_STATUS_FAILED, - &cp->type, sizeof(cp->type)); + err = mgmt_cmd_complete(sk, hdev->id, + MGMT_OP_START_SERVICE_DISCOVERY, + MGMT_STATUS_FAILED, + &cp->type, sizeof(cp->type)); mgmt_pending_remove(cmd); goto failed; } @@ -4097,9 +4411,9 @@ static int start_service_discovery(struct sock *sk, struct hci_dev *hdev, hci_req_init(&req, hdev); if (!trigger_discovery(&req, &status)) { - err = cmd_complete(sk, hdev->id, - MGMT_OP_START_SERVICE_DISCOVERY, - status, &cp->type, sizeof(cp->type)); + err = mgmt_cmd_complete(sk, hdev->id, + MGMT_OP_START_SERVICE_DISCOVERY, + status, &cp->type, sizeof(cp->type)); mgmt_pending_remove(cmd); goto failed; } @@ -4119,13 +4433,13 @@ failed: static void stop_discovery_complete(struct hci_dev *hdev, u8 status, u16 opcode) { - struct pending_cmd *cmd; + struct mgmt_pending_cmd *cmd; BT_DBG("status %d", status); hci_dev_lock(hdev); - cmd = mgmt_pending_find(MGMT_OP_STOP_DISCOVERY, hdev); + cmd = pending_find(MGMT_OP_STOP_DISCOVERY, hdev); if (cmd) { cmd->cmd_complete(cmd, mgmt_status(status)); mgmt_pending_remove(cmd); @@ -4141,7 +4455,7 @@ static int stop_discovery(struct sock *sk, struct hci_dev *hdev, void *data, u16 len) { struct mgmt_cp_stop_discovery *mgmt_cp = data; - struct pending_cmd *cmd; + struct mgmt_pending_cmd *cmd; struct hci_request req; int err; @@ -4150,16 +4464,16 @@ static int stop_discovery(struct sock *sk, struct hci_dev *hdev, void *data, hci_dev_lock(hdev); if (!hci_discovery_active(hdev)) { - err = cmd_complete(sk, hdev->id, MGMT_OP_STOP_DISCOVERY, - MGMT_STATUS_REJECTED, &mgmt_cp->type, - sizeof(mgmt_cp->type)); + err = mgmt_cmd_complete(sk, hdev->id, MGMT_OP_STOP_DISCOVERY, + MGMT_STATUS_REJECTED, &mgmt_cp->type, + sizeof(mgmt_cp->type)); goto unlock; } if (hdev->discovery.type != mgmt_cp->type) { - err = cmd_complete(sk, hdev->id, MGMT_OP_STOP_DISCOVERY, - MGMT_STATUS_INVALID_PARAMS, &mgmt_cp->type, - sizeof(mgmt_cp->type)); + err = mgmt_cmd_complete(sk, hdev->id, MGMT_OP_STOP_DISCOVERY, + MGMT_STATUS_INVALID_PARAMS, + &mgmt_cp->type, sizeof(mgmt_cp->type)); goto unlock; } @@ -4185,8 +4499,8 @@ static int stop_discovery(struct sock *sk, struct hci_dev *hdev, void *data, /* If no HCI commands were sent we're done */ if (err == -ENODATA) { - err = cmd_complete(sk, hdev->id, MGMT_OP_STOP_DISCOVERY, 0, - &mgmt_cp->type, sizeof(mgmt_cp->type)); + err = mgmt_cmd_complete(sk, hdev->id, MGMT_OP_STOP_DISCOVERY, 0, + &mgmt_cp->type, sizeof(mgmt_cp->type)); hci_discovery_set_state(hdev, DISCOVERY_STOPPED); } @@ -4207,17 +4521,17 @@ static int confirm_name(struct sock *sk, struct hci_dev *hdev, void *data, hci_dev_lock(hdev); if (!hci_discovery_active(hdev)) { - err = cmd_complete(sk, hdev->id, MGMT_OP_CONFIRM_NAME, - MGMT_STATUS_FAILED, &cp->addr, - sizeof(cp->addr)); + err = mgmt_cmd_complete(sk, hdev->id, MGMT_OP_CONFIRM_NAME, + MGMT_STATUS_FAILED, &cp->addr, + sizeof(cp->addr)); goto failed; } e = hci_inquiry_cache_lookup_unknown(hdev, &cp->addr.bdaddr); if (!e) { - err = cmd_complete(sk, hdev->id, MGMT_OP_CONFIRM_NAME, - MGMT_STATUS_INVALID_PARAMS, &cp->addr, - sizeof(cp->addr)); + err = mgmt_cmd_complete(sk, hdev->id, MGMT_OP_CONFIRM_NAME, + MGMT_STATUS_INVALID_PARAMS, &cp->addr, + sizeof(cp->addr)); goto failed; } @@ -4229,8 +4543,8 @@ static int confirm_name(struct sock *sk, struct hci_dev *hdev, void *data, hci_inquiry_cache_update_resolve(hdev, e); } - err = cmd_complete(sk, hdev->id, MGMT_OP_CONFIRM_NAME, 0, &cp->addr, - sizeof(cp->addr)); + err = mgmt_cmd_complete(sk, hdev->id, MGMT_OP_CONFIRM_NAME, 0, + &cp->addr, sizeof(cp->addr)); failed: hci_dev_unlock(hdev); @@ -4247,9 +4561,9 @@ static int block_device(struct sock *sk, struct hci_dev *hdev, void *data, BT_DBG("%s", hdev->name); if (!bdaddr_type_is_valid(cp->addr.type)) - return cmd_complete(sk, hdev->id, MGMT_OP_BLOCK_DEVICE, - MGMT_STATUS_INVALID_PARAMS, - &cp->addr, sizeof(cp->addr)); + return mgmt_cmd_complete(sk, hdev->id, MGMT_OP_BLOCK_DEVICE, + MGMT_STATUS_INVALID_PARAMS, + &cp->addr, sizeof(cp->addr)); hci_dev_lock(hdev); @@ -4265,8 +4579,8 @@ static int block_device(struct sock *sk, struct hci_dev *hdev, void *data, status = MGMT_STATUS_SUCCESS; done: - err = cmd_complete(sk, hdev->id, MGMT_OP_BLOCK_DEVICE, status, - &cp->addr, sizeof(cp->addr)); + err = mgmt_cmd_complete(sk, hdev->id, MGMT_OP_BLOCK_DEVICE, status, + &cp->addr, sizeof(cp->addr)); hci_dev_unlock(hdev); @@ -4283,9 +4597,9 @@ static int unblock_device(struct sock *sk, struct hci_dev *hdev, void *data, BT_DBG("%s", hdev->name); if (!bdaddr_type_is_valid(cp->addr.type)) - return cmd_complete(sk, hdev->id, MGMT_OP_UNBLOCK_DEVICE, - MGMT_STATUS_INVALID_PARAMS, - &cp->addr, sizeof(cp->addr)); + return mgmt_cmd_complete(sk, hdev->id, MGMT_OP_UNBLOCK_DEVICE, + MGMT_STATUS_INVALID_PARAMS, + &cp->addr, sizeof(cp->addr)); hci_dev_lock(hdev); @@ -4301,8 +4615,8 @@ static int unblock_device(struct sock *sk, struct hci_dev *hdev, void *data, status = MGMT_STATUS_SUCCESS; done: - err = cmd_complete(sk, hdev->id, MGMT_OP_UNBLOCK_DEVICE, status, - &cp->addr, sizeof(cp->addr)); + err = mgmt_cmd_complete(sk, hdev->id, MGMT_OP_UNBLOCK_DEVICE, status, + &cp->addr, sizeof(cp->addr)); hci_dev_unlock(hdev); @@ -4322,8 +4636,8 @@ static int set_device_id(struct sock *sk, struct hci_dev *hdev, void *data, source = __le16_to_cpu(cp->source); if (source > 0x0002) - return cmd_status(sk, hdev->id, MGMT_OP_SET_DEVICE_ID, - MGMT_STATUS_INVALID_PARAMS); + return mgmt_cmd_status(sk, hdev->id, MGMT_OP_SET_DEVICE_ID, + MGMT_STATUS_INVALID_PARAMS); hci_dev_lock(hdev); @@ -4332,7 +4646,8 @@ static int set_device_id(struct sock *sk, struct hci_dev *hdev, void *data, hdev->devid_product = __le16_to_cpu(cp->product); hdev->devid_version = __le16_to_cpu(cp->version); - err = cmd_complete(sk, hdev->id, MGMT_OP_SET_DEVICE_ID, 0, NULL, 0); + err = mgmt_cmd_complete(sk, hdev->id, MGMT_OP_SET_DEVICE_ID, 0, + NULL, 0); hci_req_init(&req, hdev); update_eir(&req); @@ -4343,10 +4658,17 @@ static int set_device_id(struct sock *sk, struct hci_dev *hdev, void *data, return err; } +static void enable_advertising_instance(struct hci_dev *hdev, u8 status, + u16 opcode) +{ + BT_DBG("status %d", status); +} + static void set_advertising_complete(struct hci_dev *hdev, u8 status, u16 opcode) { struct cmd_lookup match = { NULL, hdev }; + struct hci_request req; hci_dev_lock(hdev); @@ -4358,10 +4680,10 @@ static void set_advertising_complete(struct hci_dev *hdev, u8 status, goto unlock; } - if (test_bit(HCI_LE_ADV, &hdev->dev_flags)) - set_bit(HCI_ADVERTISING, &hdev->dev_flags); + if (hci_dev_test_flag(hdev, HCI_LE_ADV)) + hci_dev_set_flag(hdev, HCI_ADVERTISING); else - clear_bit(HCI_ADVERTISING, &hdev->dev_flags); + hci_dev_clear_flag(hdev, HCI_ADVERTISING); mgmt_pending_foreach(MGMT_OP_SET_ADVERTISING, hdev, settings_rsp, &match); @@ -4371,6 +4693,21 @@ static void set_advertising_complete(struct hci_dev *hdev, u8 status, if (match.sk) sock_put(match.sk); + /* If "Set Advertising" was just disabled and instance advertising was + * set up earlier, then enable the advertising instance. + */ + if (hci_dev_test_flag(hdev, HCI_ADVERTISING) || + !hci_dev_test_flag(hdev, HCI_ADVERTISING_INSTANCE)) + goto unlock; + + hci_req_init(&req, hdev); + + update_adv_data(&req); + enable_advertising(&req); + + if (hci_req_run(&req, enable_advertising_instance) < 0) + BT_ERR("Failed to re-configure advertising"); + unlock: hci_dev_unlock(hdev); } @@ -4379,41 +4716,48 @@ static int set_advertising(struct sock *sk, struct hci_dev *hdev, void *data, u16 len) { struct mgmt_mode *cp = data; - struct pending_cmd *cmd; + struct mgmt_pending_cmd *cmd; struct hci_request req; - u8 val, enabled, status; + u8 val, status; int err; BT_DBG("request for %s", hdev->name); status = mgmt_le_support(hdev); if (status) - return cmd_status(sk, hdev->id, MGMT_OP_SET_ADVERTISING, - status); + return mgmt_cmd_status(sk, hdev->id, MGMT_OP_SET_ADVERTISING, + status); - if (cp->val != 0x00 && cp->val != 0x01) - return cmd_status(sk, hdev->id, MGMT_OP_SET_ADVERTISING, - MGMT_STATUS_INVALID_PARAMS); + if (cp->val != 0x00 && cp->val != 0x01 && cp->val != 0x02) + return mgmt_cmd_status(sk, hdev->id, MGMT_OP_SET_ADVERTISING, + MGMT_STATUS_INVALID_PARAMS); hci_dev_lock(hdev); val = !!cp->val; - enabled = test_bit(HCI_ADVERTISING, &hdev->dev_flags); /* The following conditions are ones which mean that we should * not do any HCI communication but directly send a mgmt * response to user space (after toggling the flag if * necessary). */ - if (!hdev_is_powered(hdev) || val == enabled || + if (!hdev_is_powered(hdev) || + (val == hci_dev_test_flag(hdev, HCI_ADVERTISING) && + (cp->val == 0x02) == hci_dev_test_flag(hdev, HCI_ADVERTISING_CONNECTABLE)) || hci_conn_num(hdev, LE_LINK) > 0 || - (test_bit(HCI_LE_SCAN, &hdev->dev_flags) && + (hci_dev_test_flag(hdev, HCI_LE_SCAN) && hdev->le_scan_type == LE_SCAN_ACTIVE)) { - bool changed = false; + bool changed; - if (val != test_bit(HCI_ADVERTISING, &hdev->dev_flags)) { - change_bit(HCI_ADVERTISING, &hdev->dev_flags); - changed = true; + if (cp->val) { + changed = !hci_dev_test_and_set_flag(hdev, HCI_ADVERTISING); + if (cp->val == 0x02) + hci_dev_set_flag(hdev, HCI_ADVERTISING_CONNECTABLE); + else + hci_dev_clear_flag(hdev, HCI_ADVERTISING_CONNECTABLE); + } else { + changed = hci_dev_test_and_clear_flag(hdev, HCI_ADVERTISING); + hci_dev_clear_flag(hdev, HCI_ADVERTISING_CONNECTABLE); } err = send_settings_rsp(sk, MGMT_OP_SET_ADVERTISING, hdev); @@ -4426,10 +4770,10 @@ static int set_advertising(struct sock *sk, struct hci_dev *hdev, void *data, goto unlock; } - if (mgmt_pending_find(MGMT_OP_SET_ADVERTISING, hdev) || - mgmt_pending_find(MGMT_OP_SET_LE, hdev)) { - err = cmd_status(sk, hdev->id, MGMT_OP_SET_ADVERTISING, - MGMT_STATUS_BUSY); + if (pending_find(MGMT_OP_SET_ADVERTISING, hdev) || + pending_find(MGMT_OP_SET_LE, hdev)) { + err = mgmt_cmd_status(sk, hdev->id, MGMT_OP_SET_ADVERTISING, + MGMT_STATUS_BUSY); goto unlock; } @@ -4441,10 +4785,19 @@ static int set_advertising(struct sock *sk, struct hci_dev *hdev, void *data, hci_req_init(&req, hdev); - if (val) - enable_advertising(&req); + if (cp->val == 0x02) + hci_dev_set_flag(hdev, HCI_ADVERTISING_CONNECTABLE); else + hci_dev_clear_flag(hdev, HCI_ADVERTISING_CONNECTABLE); + + if (val) { + /* Switch to instance "0" for the Set Advertising setting. */ + update_adv_data_for_instance(&req, 0); + update_scan_rsp_data_for_instance(&req, 0); + enable_advertising(&req); + } else { disable_advertising(&req); + } err = hci_req_run(&req, set_advertising_complete); if (err < 0) @@ -4464,34 +4817,38 @@ static int set_static_address(struct sock *sk, struct hci_dev *hdev, BT_DBG("%s", hdev->name); if (!lmp_le_capable(hdev)) - return cmd_status(sk, hdev->id, MGMT_OP_SET_STATIC_ADDRESS, - MGMT_STATUS_NOT_SUPPORTED); + return mgmt_cmd_status(sk, hdev->id, MGMT_OP_SET_STATIC_ADDRESS, + MGMT_STATUS_NOT_SUPPORTED); if (hdev_is_powered(hdev)) - return cmd_status(sk, hdev->id, MGMT_OP_SET_STATIC_ADDRESS, - MGMT_STATUS_REJECTED); + return mgmt_cmd_status(sk, hdev->id, MGMT_OP_SET_STATIC_ADDRESS, + MGMT_STATUS_REJECTED); if (bacmp(&cp->bdaddr, BDADDR_ANY)) { if (!bacmp(&cp->bdaddr, BDADDR_NONE)) - return cmd_status(sk, hdev->id, - MGMT_OP_SET_STATIC_ADDRESS, - MGMT_STATUS_INVALID_PARAMS); + return mgmt_cmd_status(sk, hdev->id, + MGMT_OP_SET_STATIC_ADDRESS, + MGMT_STATUS_INVALID_PARAMS); /* Two most significant bits shall be set */ if ((cp->bdaddr.b[5] & 0xc0) != 0xc0) - return cmd_status(sk, hdev->id, - MGMT_OP_SET_STATIC_ADDRESS, - MGMT_STATUS_INVALID_PARAMS); + return mgmt_cmd_status(sk, hdev->id, + MGMT_OP_SET_STATIC_ADDRESS, + MGMT_STATUS_INVALID_PARAMS); } hci_dev_lock(hdev); bacpy(&hdev->static_addr, &cp->bdaddr); - err = cmd_complete(sk, hdev->id, MGMT_OP_SET_STATIC_ADDRESS, 0, NULL, 0); + err = send_settings_rsp(sk, MGMT_OP_SET_STATIC_ADDRESS, hdev); + if (err < 0) + goto unlock; - hci_dev_unlock(hdev); + err = new_settings(hdev, sk); +unlock: + hci_dev_unlock(hdev); return err; } @@ -4505,36 +4862,37 @@ static int set_scan_params(struct sock *sk, struct hci_dev *hdev, BT_DBG("%s", hdev->name); if (!lmp_le_capable(hdev)) - return cmd_status(sk, hdev->id, MGMT_OP_SET_SCAN_PARAMS, - MGMT_STATUS_NOT_SUPPORTED); + return mgmt_cmd_status(sk, hdev->id, MGMT_OP_SET_SCAN_PARAMS, + MGMT_STATUS_NOT_SUPPORTED); interval = __le16_to_cpu(cp->interval); if (interval < 0x0004 || interval > 0x4000) - return cmd_status(sk, hdev->id, MGMT_OP_SET_SCAN_PARAMS, - MGMT_STATUS_INVALID_PARAMS); + return mgmt_cmd_status(sk, hdev->id, MGMT_OP_SET_SCAN_PARAMS, + MGMT_STATUS_INVALID_PARAMS); window = __le16_to_cpu(cp->window); if (window < 0x0004 || window > 0x4000) - return cmd_status(sk, hdev->id, MGMT_OP_SET_SCAN_PARAMS, - MGMT_STATUS_INVALID_PARAMS); + return mgmt_cmd_status(sk, hdev->id, MGMT_OP_SET_SCAN_PARAMS, + MGMT_STATUS_INVALID_PARAMS); if (window > interval) - return cmd_status(sk, hdev->id, MGMT_OP_SET_SCAN_PARAMS, - MGMT_STATUS_INVALID_PARAMS); + return mgmt_cmd_status(sk, hdev->id, MGMT_OP_SET_SCAN_PARAMS, + MGMT_STATUS_INVALID_PARAMS); hci_dev_lock(hdev); hdev->le_scan_interval = interval; hdev->le_scan_window = window; - err = cmd_complete(sk, hdev->id, MGMT_OP_SET_SCAN_PARAMS, 0, NULL, 0); + err = mgmt_cmd_complete(sk, hdev->id, MGMT_OP_SET_SCAN_PARAMS, 0, + NULL, 0); /* If background scan is running, restart it so new parameters are * loaded. */ - if (test_bit(HCI_LE_SCAN, &hdev->dev_flags) && + if (hci_dev_test_flag(hdev, HCI_LE_SCAN) && hdev->discovery.state == DISCOVERY_STOPPED) { struct hci_request req; @@ -4554,26 +4912,26 @@ static int set_scan_params(struct sock *sk, struct hci_dev *hdev, static void fast_connectable_complete(struct hci_dev *hdev, u8 status, u16 opcode) { - struct pending_cmd *cmd; + struct mgmt_pending_cmd *cmd; BT_DBG("status 0x%02x", status); hci_dev_lock(hdev); - cmd = mgmt_pending_find(MGMT_OP_SET_FAST_CONNECTABLE, hdev); + cmd = pending_find(MGMT_OP_SET_FAST_CONNECTABLE, hdev); if (!cmd) goto unlock; if (status) { - cmd_status(cmd->sk, hdev->id, MGMT_OP_SET_FAST_CONNECTABLE, - mgmt_status(status)); + mgmt_cmd_status(cmd->sk, hdev->id, MGMT_OP_SET_FAST_CONNECTABLE, + mgmt_status(status)); } else { struct mgmt_mode *cp = cmd->param; if (cp->val) - set_bit(HCI_FAST_CONNECTABLE, &hdev->dev_flags); + hci_dev_set_flag(hdev, HCI_FAST_CONNECTABLE); else - clear_bit(HCI_FAST_CONNECTABLE, &hdev->dev_flags); + hci_dev_clear_flag(hdev, HCI_FAST_CONNECTABLE); send_settings_rsp(cmd->sk, MGMT_OP_SET_FAST_CONNECTABLE, hdev); new_settings(hdev, cmd->sk); @@ -4589,40 +4947,40 @@ static int set_fast_connectable(struct sock *sk, struct hci_dev *hdev, void *data, u16 len) { struct mgmt_mode *cp = data; - struct pending_cmd *cmd; + struct mgmt_pending_cmd *cmd; struct hci_request req; int err; BT_DBG("%s", hdev->name); - if (!test_bit(HCI_BREDR_ENABLED, &hdev->dev_flags) || + if (!hci_dev_test_flag(hdev, HCI_BREDR_ENABLED) || hdev->hci_ver < BLUETOOTH_VER_1_2) - return cmd_status(sk, hdev->id, MGMT_OP_SET_FAST_CONNECTABLE, - MGMT_STATUS_NOT_SUPPORTED); + return mgmt_cmd_status(sk, hdev->id, MGMT_OP_SET_FAST_CONNECTABLE, + MGMT_STATUS_NOT_SUPPORTED); if (cp->val != 0x00 && cp->val != 0x01) - return cmd_status(sk, hdev->id, MGMT_OP_SET_FAST_CONNECTABLE, - MGMT_STATUS_INVALID_PARAMS); - - if (!hdev_is_powered(hdev)) - return cmd_status(sk, hdev->id, MGMT_OP_SET_FAST_CONNECTABLE, - MGMT_STATUS_NOT_POWERED); - - if (!test_bit(HCI_CONNECTABLE, &hdev->dev_flags)) - return cmd_status(sk, hdev->id, MGMT_OP_SET_FAST_CONNECTABLE, - MGMT_STATUS_REJECTED); + return mgmt_cmd_status(sk, hdev->id, MGMT_OP_SET_FAST_CONNECTABLE, + MGMT_STATUS_INVALID_PARAMS); hci_dev_lock(hdev); - if (mgmt_pending_find(MGMT_OP_SET_FAST_CONNECTABLE, hdev)) { - err = cmd_status(sk, hdev->id, MGMT_OP_SET_FAST_CONNECTABLE, - MGMT_STATUS_BUSY); + if (pending_find(MGMT_OP_SET_FAST_CONNECTABLE, hdev)) { + err = mgmt_cmd_status(sk, hdev->id, MGMT_OP_SET_FAST_CONNECTABLE, + MGMT_STATUS_BUSY); + goto unlock; + } + + if (!!cp->val == hci_dev_test_flag(hdev, HCI_FAST_CONNECTABLE)) { + err = send_settings_rsp(sk, MGMT_OP_SET_FAST_CONNECTABLE, + hdev); goto unlock; } - if (!!cp->val == test_bit(HCI_FAST_CONNECTABLE, &hdev->dev_flags)) { + if (!hdev_is_powered(hdev)) { + hci_dev_change_flag(hdev, HCI_FAST_CONNECTABLE); err = send_settings_rsp(sk, MGMT_OP_SET_FAST_CONNECTABLE, hdev); + new_settings(hdev, sk); goto unlock; } @@ -4639,8 +4997,8 @@ static int set_fast_connectable(struct sock *sk, struct hci_dev *hdev, err = hci_req_run(&req, fast_connectable_complete); if (err < 0) { - err = cmd_status(sk, hdev->id, MGMT_OP_SET_FAST_CONNECTABLE, - MGMT_STATUS_FAILED); + err = mgmt_cmd_status(sk, hdev->id, MGMT_OP_SET_FAST_CONNECTABLE, + MGMT_STATUS_FAILED); mgmt_pending_remove(cmd); } @@ -4652,13 +5010,13 @@ unlock: static void set_bredr_complete(struct hci_dev *hdev, u8 status, u16 opcode) { - struct pending_cmd *cmd; + struct mgmt_pending_cmd *cmd; BT_DBG("status 0x%02x", status); hci_dev_lock(hdev); - cmd = mgmt_pending_find(MGMT_OP_SET_BREDR, hdev); + cmd = pending_find(MGMT_OP_SET_BREDR, hdev); if (!cmd) goto unlock; @@ -4668,9 +5026,9 @@ static void set_bredr_complete(struct hci_dev *hdev, u8 status, u16 opcode) /* We need to restore the flag if related HCI commands * failed. */ - clear_bit(HCI_BREDR_ENABLED, &hdev->dev_flags); + hci_dev_clear_flag(hdev, HCI_BREDR_ENABLED); - cmd_status(cmd->sk, cmd->index, cmd->opcode, mgmt_err); + mgmt_cmd_status(cmd->sk, cmd->index, cmd->opcode, mgmt_err); } else { send_settings_rsp(cmd->sk, MGMT_OP_SET_BREDR, hdev); new_settings(hdev, cmd->sk); @@ -4685,41 +5043,41 @@ unlock: static int set_bredr(struct sock *sk, struct hci_dev *hdev, void *data, u16 len) { struct mgmt_mode *cp = data; - struct pending_cmd *cmd; + struct mgmt_pending_cmd *cmd; struct hci_request req; int err; BT_DBG("request for %s", hdev->name); if (!lmp_bredr_capable(hdev) || !lmp_le_capable(hdev)) - return cmd_status(sk, hdev->id, MGMT_OP_SET_BREDR, - MGMT_STATUS_NOT_SUPPORTED); + return mgmt_cmd_status(sk, hdev->id, MGMT_OP_SET_BREDR, + MGMT_STATUS_NOT_SUPPORTED); - if (!test_bit(HCI_LE_ENABLED, &hdev->dev_flags)) - return cmd_status(sk, hdev->id, MGMT_OP_SET_BREDR, - MGMT_STATUS_REJECTED); + if (!hci_dev_test_flag(hdev, HCI_LE_ENABLED)) + return mgmt_cmd_status(sk, hdev->id, MGMT_OP_SET_BREDR, + MGMT_STATUS_REJECTED); if (cp->val != 0x00 && cp->val != 0x01) - return cmd_status(sk, hdev->id, MGMT_OP_SET_BREDR, - MGMT_STATUS_INVALID_PARAMS); + return mgmt_cmd_status(sk, hdev->id, MGMT_OP_SET_BREDR, + MGMT_STATUS_INVALID_PARAMS); hci_dev_lock(hdev); - if (cp->val == test_bit(HCI_BREDR_ENABLED, &hdev->dev_flags)) { + if (cp->val == hci_dev_test_flag(hdev, HCI_BREDR_ENABLED)) { err = send_settings_rsp(sk, MGMT_OP_SET_BREDR, hdev); goto unlock; } if (!hdev_is_powered(hdev)) { if (!cp->val) { - clear_bit(HCI_DISCOVERABLE, &hdev->dev_flags); - clear_bit(HCI_SSP_ENABLED, &hdev->dev_flags); - clear_bit(HCI_LINK_SECURITY, &hdev->dev_flags); - clear_bit(HCI_FAST_CONNECTABLE, &hdev->dev_flags); - clear_bit(HCI_HS_ENABLED, &hdev->dev_flags); + hci_dev_clear_flag(hdev, HCI_DISCOVERABLE); + hci_dev_clear_flag(hdev, HCI_SSP_ENABLED); + hci_dev_clear_flag(hdev, HCI_LINK_SECURITY); + hci_dev_clear_flag(hdev, HCI_FAST_CONNECTABLE); + hci_dev_clear_flag(hdev, HCI_HS_ENABLED); } - change_bit(HCI_BREDR_ENABLED, &hdev->dev_flags); + hci_dev_change_flag(hdev, HCI_BREDR_ENABLED); err = send_settings_rsp(sk, MGMT_OP_SET_BREDR, hdev); if (err < 0) @@ -4731,8 +5089,8 @@ static int set_bredr(struct sock *sk, struct hci_dev *hdev, void *data, u16 len) /* Reject disabling when powered on */ if (!cp->val) { - err = cmd_status(sk, hdev->id, MGMT_OP_SET_BREDR, - MGMT_STATUS_REJECTED); + err = mgmt_cmd_status(sk, hdev->id, MGMT_OP_SET_BREDR, + MGMT_STATUS_REJECTED); goto unlock; } else { /* When configuring a dual-mode controller to operate @@ -4749,18 +5107,18 @@ static int set_bredr(struct sock *sk, struct hci_dev *hdev, void *data, u16 len) * switching BR/EDR back on when secure connections has been * enabled is not a supported transaction. */ - if (!test_bit(HCI_BREDR_ENABLED, &hdev->dev_flags) && + if (!hci_dev_test_flag(hdev, HCI_BREDR_ENABLED) && (bacmp(&hdev->static_addr, BDADDR_ANY) || - test_bit(HCI_SC_ENABLED, &hdev->dev_flags))) { - err = cmd_status(sk, hdev->id, MGMT_OP_SET_BREDR, - MGMT_STATUS_REJECTED); + hci_dev_test_flag(hdev, HCI_SC_ENABLED))) { + err = mgmt_cmd_status(sk, hdev->id, MGMT_OP_SET_BREDR, + MGMT_STATUS_REJECTED); goto unlock; } } - if (mgmt_pending_find(MGMT_OP_SET_BREDR, hdev)) { - err = cmd_status(sk, hdev->id, MGMT_OP_SET_BREDR, - MGMT_STATUS_BUSY); + if (pending_find(MGMT_OP_SET_BREDR, hdev)) { + err = mgmt_cmd_status(sk, hdev->id, MGMT_OP_SET_BREDR, + MGMT_STATUS_BUSY); goto unlock; } @@ -4773,7 +5131,7 @@ static int set_bredr(struct sock *sk, struct hci_dev *hdev, void *data, u16 len) /* We need to flip the bit already here so that update_adv_data * generates the correct flags. */ - set_bit(HCI_BREDR_ENABLED, &hdev->dev_flags); + hci_dev_set_flag(hdev, HCI_BREDR_ENABLED); hci_req_init(&req, hdev); @@ -4796,20 +5154,20 @@ unlock: static void sc_enable_complete(struct hci_dev *hdev, u8 status, u16 opcode) { - struct pending_cmd *cmd; + struct mgmt_pending_cmd *cmd; struct mgmt_mode *cp; BT_DBG("%s status %u", hdev->name, status); hci_dev_lock(hdev); - cmd = mgmt_pending_find(MGMT_OP_SET_SECURE_CONN, hdev); + cmd = pending_find(MGMT_OP_SET_SECURE_CONN, hdev); if (!cmd) goto unlock; if (status) { - cmd_status(cmd->sk, cmd->index, cmd->opcode, - mgmt_status(status)); + mgmt_cmd_status(cmd->sk, cmd->index, cmd->opcode, + mgmt_status(status)); goto remove; } @@ -4817,16 +5175,16 @@ static void sc_enable_complete(struct hci_dev *hdev, u8 status, u16 opcode) switch (cp->val) { case 0x00: - clear_bit(HCI_SC_ENABLED, &hdev->dev_flags); - clear_bit(HCI_SC_ONLY, &hdev->dev_flags); + hci_dev_clear_flag(hdev, HCI_SC_ENABLED); + hci_dev_clear_flag(hdev, HCI_SC_ONLY); break; case 0x01: - set_bit(HCI_SC_ENABLED, &hdev->dev_flags); - clear_bit(HCI_SC_ONLY, &hdev->dev_flags); + hci_dev_set_flag(hdev, HCI_SC_ENABLED); + hci_dev_clear_flag(hdev, HCI_SC_ONLY); break; case 0x02: - set_bit(HCI_SC_ENABLED, &hdev->dev_flags); - set_bit(HCI_SC_ONLY, &hdev->dev_flags); + hci_dev_set_flag(hdev, HCI_SC_ENABLED); + hci_dev_set_flag(hdev, HCI_SC_ONLY); break; } @@ -4843,7 +5201,7 @@ static int set_secure_conn(struct sock *sk, struct hci_dev *hdev, void *data, u16 len) { struct mgmt_mode *cp = data; - struct pending_cmd *cmd; + struct mgmt_pending_cmd *cmd; struct hci_request req; u8 val; int err; @@ -4851,37 +5209,37 @@ static int set_secure_conn(struct sock *sk, struct hci_dev *hdev, BT_DBG("request for %s", hdev->name); if (!lmp_sc_capable(hdev) && - !test_bit(HCI_LE_ENABLED, &hdev->dev_flags)) - return cmd_status(sk, hdev->id, MGMT_OP_SET_SECURE_CONN, - MGMT_STATUS_NOT_SUPPORTED); + !hci_dev_test_flag(hdev, HCI_LE_ENABLED)) + return mgmt_cmd_status(sk, hdev->id, MGMT_OP_SET_SECURE_CONN, + MGMT_STATUS_NOT_SUPPORTED); - if (test_bit(HCI_BREDR_ENABLED, &hdev->dev_flags) && + if (hci_dev_test_flag(hdev, HCI_BREDR_ENABLED) && lmp_sc_capable(hdev) && - !test_bit(HCI_SSP_ENABLED, &hdev->dev_flags)) - return cmd_status(sk, hdev->id, MGMT_OP_SET_SECURE_CONN, - MGMT_STATUS_REJECTED); + !hci_dev_test_flag(hdev, HCI_SSP_ENABLED)) + return mgmt_cmd_status(sk, hdev->id, MGMT_OP_SET_SECURE_CONN, + MGMT_STATUS_REJECTED); if (cp->val != 0x00 && cp->val != 0x01 && cp->val != 0x02) - return cmd_status(sk, hdev->id, MGMT_OP_SET_SECURE_CONN, + return mgmt_cmd_status(sk, hdev->id, MGMT_OP_SET_SECURE_CONN, MGMT_STATUS_INVALID_PARAMS); hci_dev_lock(hdev); if (!hdev_is_powered(hdev) || !lmp_sc_capable(hdev) || - !test_bit(HCI_BREDR_ENABLED, &hdev->dev_flags)) { + !hci_dev_test_flag(hdev, HCI_BREDR_ENABLED)) { bool changed; if (cp->val) { - changed = !test_and_set_bit(HCI_SC_ENABLED, - &hdev->dev_flags); + changed = !hci_dev_test_and_set_flag(hdev, + HCI_SC_ENABLED); if (cp->val == 0x02) - set_bit(HCI_SC_ONLY, &hdev->dev_flags); + hci_dev_set_flag(hdev, HCI_SC_ONLY); else - clear_bit(HCI_SC_ONLY, &hdev->dev_flags); + hci_dev_clear_flag(hdev, HCI_SC_ONLY); } else { - changed = test_and_clear_bit(HCI_SC_ENABLED, - &hdev->dev_flags); - clear_bit(HCI_SC_ONLY, &hdev->dev_flags); + changed = hci_dev_test_and_clear_flag(hdev, + HCI_SC_ENABLED); + hci_dev_clear_flag(hdev, HCI_SC_ONLY); } err = send_settings_rsp(sk, MGMT_OP_SET_SECURE_CONN, hdev); @@ -4894,16 +5252,16 @@ static int set_secure_conn(struct sock *sk, struct hci_dev *hdev, goto failed; } - if (mgmt_pending_find(MGMT_OP_SET_SECURE_CONN, hdev)) { - err = cmd_status(sk, hdev->id, MGMT_OP_SET_SECURE_CONN, - MGMT_STATUS_BUSY); + if (pending_find(MGMT_OP_SET_SECURE_CONN, hdev)) { + err = mgmt_cmd_status(sk, hdev->id, MGMT_OP_SET_SECURE_CONN, + MGMT_STATUS_BUSY); goto failed; } val = !!cp->val; - if (val == test_bit(HCI_SC_ENABLED, &hdev->dev_flags) && - (cp->val == 0x02) == test_bit(HCI_SC_ONLY, &hdev->dev_flags)) { + if (val == hci_dev_test_flag(hdev, HCI_SC_ENABLED) && + (cp->val == 0x02) == hci_dev_test_flag(hdev, HCI_SC_ONLY)) { err = send_settings_rsp(sk, MGMT_OP_SET_SECURE_CONN, hdev); goto failed; } @@ -4937,27 +5295,26 @@ static int set_debug_keys(struct sock *sk, struct hci_dev *hdev, BT_DBG("request for %s", hdev->name); 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); + return mgmt_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_KEEP_DEBUG_KEYS, - &hdev->dev_flags); + changed = !hci_dev_test_and_set_flag(hdev, HCI_KEEP_DEBUG_KEYS); else - changed = test_and_clear_bit(HCI_KEEP_DEBUG_KEYS, - &hdev->dev_flags); + changed = hci_dev_test_and_clear_flag(hdev, + HCI_KEEP_DEBUG_KEYS); if (cp->val == 0x02) - use_changed = !test_and_set_bit(HCI_USE_DEBUG_KEYS, - &hdev->dev_flags); + use_changed = !hci_dev_test_and_set_flag(hdev, + HCI_USE_DEBUG_KEYS); else - use_changed = test_and_clear_bit(HCI_USE_DEBUG_KEYS, - &hdev->dev_flags); + use_changed = hci_dev_test_and_clear_flag(hdev, + HCI_USE_DEBUG_KEYS); if (hdev_is_powered(hdev) && use_changed && - test_bit(HCI_SSP_ENABLED, &hdev->dev_flags)) { + hci_dev_test_flag(hdev, HCI_SSP_ENABLED)) { u8 mode = (cp->val == 0x02) ? 0x01 : 0x00; hci_send_cmd(hdev, HCI_OP_WRITE_SSP_DEBUG_MODE, sizeof(mode), &mode); @@ -4985,32 +5342,32 @@ static int set_privacy(struct sock *sk, struct hci_dev *hdev, void *cp_data, BT_DBG("request for %s", hdev->name); if (!lmp_le_capable(hdev)) - return cmd_status(sk, hdev->id, MGMT_OP_SET_PRIVACY, - MGMT_STATUS_NOT_SUPPORTED); + return mgmt_cmd_status(sk, hdev->id, MGMT_OP_SET_PRIVACY, + MGMT_STATUS_NOT_SUPPORTED); if (cp->privacy != 0x00 && cp->privacy != 0x01) - return cmd_status(sk, hdev->id, MGMT_OP_SET_PRIVACY, - MGMT_STATUS_INVALID_PARAMS); + return mgmt_cmd_status(sk, hdev->id, MGMT_OP_SET_PRIVACY, + MGMT_STATUS_INVALID_PARAMS); if (hdev_is_powered(hdev)) - return cmd_status(sk, hdev->id, MGMT_OP_SET_PRIVACY, - MGMT_STATUS_REJECTED); + return mgmt_cmd_status(sk, hdev->id, MGMT_OP_SET_PRIVACY, + MGMT_STATUS_REJECTED); hci_dev_lock(hdev); /* If user space supports this command it is also expected to * handle IRKs. Therefore, set the HCI_RPA_RESOLVING flag. */ - set_bit(HCI_RPA_RESOLVING, &hdev->dev_flags); + hci_dev_set_flag(hdev, HCI_RPA_RESOLVING); if (cp->privacy) { - changed = !test_and_set_bit(HCI_PRIVACY, &hdev->dev_flags); + changed = !hci_dev_test_and_set_flag(hdev, HCI_PRIVACY); memcpy(hdev->irk, cp->irk, sizeof(hdev->irk)); - set_bit(HCI_RPA_EXPIRED, &hdev->dev_flags); + hci_dev_set_flag(hdev, HCI_RPA_EXPIRED); } else { - changed = test_and_clear_bit(HCI_PRIVACY, &hdev->dev_flags); + changed = hci_dev_test_and_clear_flag(hdev, HCI_PRIVACY); memset(hdev->irk, 0, sizeof(hdev->irk)); - clear_bit(HCI_RPA_EXPIRED, &hdev->dev_flags); + hci_dev_clear_flag(hdev, HCI_RPA_EXPIRED); } err = send_settings_rsp(sk, MGMT_OP_SET_PRIVACY, hdev); @@ -5053,22 +5410,22 @@ static int load_irks(struct sock *sk, struct hci_dev *hdev, void *cp_data, BT_DBG("request for %s", hdev->name); if (!lmp_le_capable(hdev)) - return cmd_status(sk, hdev->id, MGMT_OP_LOAD_IRKS, - MGMT_STATUS_NOT_SUPPORTED); + return mgmt_cmd_status(sk, hdev->id, MGMT_OP_LOAD_IRKS, + 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); + return mgmt_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) { BT_ERR("load_irks: expected %u bytes, got %u bytes", expected_len, len); - return cmd_status(sk, hdev->id, MGMT_OP_LOAD_IRKS, - MGMT_STATUS_INVALID_PARAMS); + return mgmt_cmd_status(sk, hdev->id, MGMT_OP_LOAD_IRKS, + MGMT_STATUS_INVALID_PARAMS); } BT_DBG("%s irk_count %u", hdev->name, irk_count); @@ -5077,9 +5434,9 @@ static int load_irks(struct sock *sk, struct hci_dev *hdev, void *cp_data, struct mgmt_irk_info *key = &cp->irks[i]; if (!irk_is_valid(key)) - return cmd_status(sk, hdev->id, - MGMT_OP_LOAD_IRKS, - MGMT_STATUS_INVALID_PARAMS); + return mgmt_cmd_status(sk, hdev->id, + MGMT_OP_LOAD_IRKS, + MGMT_STATUS_INVALID_PARAMS); } hci_dev_lock(hdev); @@ -5099,9 +5456,9 @@ static int load_irks(struct sock *sk, struct hci_dev *hdev, void *cp_data, BDADDR_ANY); } - set_bit(HCI_RPA_RESOLVING, &hdev->dev_flags); + hci_dev_set_flag(hdev, HCI_RPA_RESOLVING); - err = cmd_complete(sk, hdev->id, MGMT_OP_LOAD_IRKS, 0, NULL, 0); + err = mgmt_cmd_complete(sk, hdev->id, MGMT_OP_LOAD_IRKS, 0, NULL, 0); hci_dev_unlock(hdev); @@ -5139,14 +5496,14 @@ static int load_long_term_keys(struct sock *sk, struct hci_dev *hdev, BT_DBG("request for %s", hdev->name); if (!lmp_le_capable(hdev)) - return cmd_status(sk, hdev->id, MGMT_OP_LOAD_LONG_TERM_KEYS, - MGMT_STATUS_NOT_SUPPORTED); + return mgmt_cmd_status(sk, hdev->id, MGMT_OP_LOAD_LONG_TERM_KEYS, + 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); + return mgmt_cmd_status(sk, hdev->id, MGMT_OP_LOAD_LONG_TERM_KEYS, + MGMT_STATUS_INVALID_PARAMS); } expected_len = sizeof(*cp) + key_count * @@ -5154,8 +5511,8 @@ static int load_long_term_keys(struct sock *sk, struct hci_dev *hdev, if (expected_len != len) { BT_ERR("load_keys: expected %u bytes, got %u bytes", expected_len, len); - return cmd_status(sk, hdev->id, MGMT_OP_LOAD_LONG_TERM_KEYS, - MGMT_STATUS_INVALID_PARAMS); + return mgmt_cmd_status(sk, hdev->id, MGMT_OP_LOAD_LONG_TERM_KEYS, + MGMT_STATUS_INVALID_PARAMS); } BT_DBG("%s key_count %u", hdev->name, key_count); @@ -5164,9 +5521,9 @@ static int load_long_term_keys(struct sock *sk, struct hci_dev *hdev, struct mgmt_ltk_info *key = &cp->keys[i]; if (!ltk_is_valid(key)) - return cmd_status(sk, hdev->id, - MGMT_OP_LOAD_LONG_TERM_KEYS, - MGMT_STATUS_INVALID_PARAMS); + return mgmt_cmd_status(sk, hdev->id, + MGMT_OP_LOAD_LONG_TERM_KEYS, + MGMT_STATUS_INVALID_PARAMS); } hci_dev_lock(hdev); @@ -5211,7 +5568,7 @@ static int load_long_term_keys(struct sock *sk, struct hci_dev *hdev, key->rand); } - err = cmd_complete(sk, hdev->id, MGMT_OP_LOAD_LONG_TERM_KEYS, 0, + err = mgmt_cmd_complete(sk, hdev->id, MGMT_OP_LOAD_LONG_TERM_KEYS, 0, NULL, 0); hci_dev_unlock(hdev); @@ -5219,7 +5576,7 @@ static int load_long_term_keys(struct sock *sk, struct hci_dev *hdev, return err; } -static int conn_info_cmd_complete(struct pending_cmd *cmd, u8 status) +static int conn_info_cmd_complete(struct mgmt_pending_cmd *cmd, u8 status) { struct hci_conn *conn = cmd->user_data; struct mgmt_rp_get_conn_info rp; @@ -5237,8 +5594,8 @@ static int conn_info_cmd_complete(struct pending_cmd *cmd, u8 status) rp.max_tx_power = HCI_TX_POWER_INVALID; } - err = cmd_complete(cmd->sk, cmd->index, MGMT_OP_GET_CONN_INFO, status, - &rp, sizeof(rp)); + err = mgmt_cmd_complete(cmd->sk, cmd->index, MGMT_OP_GET_CONN_INFO, + status, &rp, sizeof(rp)); hci_conn_drop(conn); hci_conn_put(conn); @@ -5250,7 +5607,7 @@ static void conn_info_refresh_complete(struct hci_dev *hdev, u8 hci_status, u16 opcode) { struct hci_cp_read_rssi *cp; - struct pending_cmd *cmd; + struct mgmt_pending_cmd *cmd; struct hci_conn *conn; u16 handle; u8 status; @@ -5288,7 +5645,7 @@ static void conn_info_refresh_complete(struct hci_dev *hdev, u8 hci_status, goto unlock; } - cmd = mgmt_pending_find_data(MGMT_OP_GET_CONN_INFO, hdev, conn); + cmd = pending_find_data(MGMT_OP_GET_CONN_INFO, hdev, conn); if (!cmd) goto unlock; @@ -5315,15 +5672,16 @@ static int get_conn_info(struct sock *sk, struct hci_dev *hdev, void *data, rp.addr.type = cp->addr.type; if (!bdaddr_type_is_valid(cp->addr.type)) - return cmd_complete(sk, hdev->id, MGMT_OP_GET_CONN_INFO, - MGMT_STATUS_INVALID_PARAMS, - &rp, sizeof(rp)); + return mgmt_cmd_complete(sk, hdev->id, MGMT_OP_GET_CONN_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_CONN_INFO, - MGMT_STATUS_NOT_POWERED, &rp, sizeof(rp)); + err = mgmt_cmd_complete(sk, hdev->id, MGMT_OP_GET_CONN_INFO, + MGMT_STATUS_NOT_POWERED, &rp, + sizeof(rp)); goto unlock; } @@ -5334,14 +5692,15 @@ static int get_conn_info(struct sock *sk, struct hci_dev *hdev, void *data, conn = hci_conn_hash_lookup_ba(hdev, LE_LINK, &cp->addr.bdaddr); if (!conn || conn->state != BT_CONNECTED) { - err = cmd_complete(sk, hdev->id, MGMT_OP_GET_CONN_INFO, - MGMT_STATUS_NOT_CONNECTED, &rp, sizeof(rp)); + err = mgmt_cmd_complete(sk, hdev->id, MGMT_OP_GET_CONN_INFO, + MGMT_STATUS_NOT_CONNECTED, &rp, + sizeof(rp)); goto unlock; } - if (mgmt_pending_find_data(MGMT_OP_GET_CONN_INFO, hdev, conn)) { - err = cmd_complete(sk, hdev->id, MGMT_OP_GET_CONN_INFO, - MGMT_STATUS_BUSY, &rp, sizeof(rp)); + if (pending_find_data(MGMT_OP_GET_CONN_INFO, hdev, conn)) { + err = mgmt_cmd_complete(sk, hdev->id, MGMT_OP_GET_CONN_INFO, + MGMT_STATUS_BUSY, &rp, sizeof(rp)); goto unlock; } @@ -5361,7 +5720,7 @@ static int get_conn_info(struct sock *sk, struct hci_dev *hdev, void *data, struct hci_request req; struct hci_cp_read_tx_power req_txp_cp; struct hci_cp_read_rssi req_rssi_cp; - struct pending_cmd *cmd; + struct mgmt_pending_cmd *cmd; hci_req_init(&req, hdev); req_rssi_cp.handle = cpu_to_le16(conn->handle); @@ -5409,8 +5768,8 @@ static int get_conn_info(struct sock *sk, struct hci_dev *hdev, void *data, rp.tx_power = conn->tx_power; rp.max_tx_power = conn->max_tx_power; - err = cmd_complete(sk, hdev->id, MGMT_OP_GET_CONN_INFO, - MGMT_STATUS_SUCCESS, &rp, sizeof(rp)); + err = mgmt_cmd_complete(sk, hdev->id, MGMT_OP_GET_CONN_INFO, + MGMT_STATUS_SUCCESS, &rp, sizeof(rp)); } unlock: @@ -5418,7 +5777,7 @@ unlock: return err; } -static int clock_info_cmd_complete(struct pending_cmd *cmd, u8 status) +static int clock_info_cmd_complete(struct mgmt_pending_cmd *cmd, u8 status) { struct hci_conn *conn = cmd->user_data; struct mgmt_rp_get_clock_info rp; @@ -5443,8 +5802,8 @@ static int clock_info_cmd_complete(struct pending_cmd *cmd, u8 status) } complete: - err = cmd_complete(cmd->sk, cmd->index, cmd->opcode, status, &rp, - sizeof(rp)); + err = mgmt_cmd_complete(cmd->sk, cmd->index, cmd->opcode, status, &rp, + sizeof(rp)); if (conn) { hci_conn_drop(conn); @@ -5457,7 +5816,7 @@ complete: static void get_clock_info_complete(struct hci_dev *hdev, u8 status, u16 opcode) { struct hci_cp_read_clock *hci_cp; - struct pending_cmd *cmd; + struct mgmt_pending_cmd *cmd; struct hci_conn *conn; BT_DBG("%s status %u", hdev->name, status); @@ -5475,7 +5834,7 @@ static void get_clock_info_complete(struct hci_dev *hdev, u8 status, u16 opcode) conn = NULL; } - cmd = mgmt_pending_find_data(MGMT_OP_GET_CLOCK_INFO, hdev, conn); + cmd = pending_find_data(MGMT_OP_GET_CLOCK_INFO, hdev, conn); if (!cmd) goto unlock; @@ -5492,7 +5851,7 @@ static int get_clock_info(struct sock *sk, struct hci_dev *hdev, void *data, 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 mgmt_pending_cmd *cmd; struct hci_request req; struct hci_conn *conn; int err; @@ -5504,15 +5863,16 @@ static int get_clock_info(struct sock *sk, struct hci_dev *hdev, void *data, 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)); + return mgmt_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)); + err = mgmt_cmd_complete(sk, hdev->id, MGMT_OP_GET_CLOCK_INFO, + MGMT_STATUS_NOT_POWERED, &rp, + sizeof(rp)); goto unlock; } @@ -5520,10 +5880,10 @@ static int get_clock_info(struct sock *sk, struct hci_dev *hdev, void *data, 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)); + err = mgmt_cmd_complete(sk, hdev->id, + MGMT_OP_GET_CLOCK_INFO, + MGMT_STATUS_NOT_CONNECTED, + &rp, sizeof(rp)); goto unlock; } } else { @@ -5634,13 +5994,13 @@ static void device_added(struct sock *sk, struct hci_dev *hdev, static void add_device_complete(struct hci_dev *hdev, u8 status, u16 opcode) { - struct pending_cmd *cmd; + struct mgmt_pending_cmd *cmd; BT_DBG("status 0x%02x", status); hci_dev_lock(hdev); - cmd = mgmt_pending_find(MGMT_OP_ADD_DEVICE, hdev); + cmd = pending_find(MGMT_OP_ADD_DEVICE, hdev); if (!cmd) goto unlock; @@ -5655,7 +6015,7 @@ static int add_device(struct sock *sk, struct hci_dev *hdev, void *data, u16 len) { struct mgmt_cp_add_device *cp = data; - struct pending_cmd *cmd; + struct mgmt_pending_cmd *cmd; struct hci_request req; u8 auto_conn, addr_type; int err; @@ -5664,14 +6024,14 @@ static int add_device(struct sock *sk, struct hci_dev *hdev, 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)); + return mgmt_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)); + return mgmt_cmd_complete(sk, hdev->id, MGMT_OP_ADD_DEVICE, + MGMT_STATUS_INVALID_PARAMS, + &cp->addr, sizeof(cp->addr)); hci_req_init(&req, hdev); @@ -5757,13 +6117,13 @@ static void device_removed(struct sock *sk, struct hci_dev *hdev, static void remove_device_complete(struct hci_dev *hdev, u8 status, u16 opcode) { - struct pending_cmd *cmd; + struct mgmt_pending_cmd *cmd; BT_DBG("status 0x%02x", status); hci_dev_lock(hdev); - cmd = mgmt_pending_find(MGMT_OP_REMOVE_DEVICE, hdev); + cmd = pending_find(MGMT_OP_REMOVE_DEVICE, hdev); if (!cmd) goto unlock; @@ -5778,7 +6138,7 @@ static int remove_device(struct sock *sk, struct hci_dev *hdev, void *data, u16 len) { struct mgmt_cp_remove_device *cp = data; - struct pending_cmd *cmd; + struct mgmt_pending_cmd *cmd; struct hci_request req; int err; @@ -5911,15 +6271,15 @@ static int load_conn_param(struct sock *sk, struct hci_dev *hdev, void *data, int i; if (!lmp_le_capable(hdev)) - return cmd_status(sk, hdev->id, MGMT_OP_LOAD_CONN_PARAM, - MGMT_STATUS_NOT_SUPPORTED); + return mgmt_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); + return mgmt_cmd_status(sk, hdev->id, MGMT_OP_LOAD_CONN_PARAM, + MGMT_STATUS_INVALID_PARAMS); } expected_len = sizeof(*cp) + param_count * @@ -5927,8 +6287,8 @@ static int load_conn_param(struct sock *sk, struct hci_dev *hdev, void *data, 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); + return mgmt_cmd_status(sk, hdev->id, MGMT_OP_LOAD_CONN_PARAM, + MGMT_STATUS_INVALID_PARAMS); } BT_DBG("%s param_count %u", hdev->name, param_count); @@ -5983,7 +6343,8 @@ static int load_conn_param(struct sock *sk, struct hci_dev *hdev, void *data, hci_dev_unlock(hdev); - return cmd_complete(sk, hdev->id, MGMT_OP_LOAD_CONN_PARAM, 0, NULL, 0); + return mgmt_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, @@ -5996,25 +6357,23 @@ static int set_external_config(struct sock *sk, struct hci_dev *hdev, BT_DBG("%s", hdev->name); if (hdev_is_powered(hdev)) - return cmd_status(sk, hdev->id, MGMT_OP_SET_EXTERNAL_CONFIG, - MGMT_STATUS_REJECTED); + return mgmt_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); + return mgmt_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); + return mgmt_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); + changed = !hci_dev_test_and_set_flag(hdev, HCI_EXT_CONFIGURED); else - changed = test_and_clear_bit(HCI_EXT_CONFIGURED, - &hdev->dev_flags); + changed = hci_dev_test_and_clear_flag(hdev, HCI_EXT_CONFIGURED); err = send_options_rsp(sk, MGMT_OP_SET_EXTERNAL_CONFIG, hdev); if (err < 0) @@ -6025,12 +6384,12 @@ static int set_external_config(struct sock *sk, struct hci_dev *hdev, err = new_options(hdev, sk); - if (test_bit(HCI_UNCONFIGURED, &hdev->dev_flags) == is_configured(hdev)) { + if (hci_dev_test_flag(hdev, HCI_UNCONFIGURED) == 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); + if (hci_dev_test_and_change_flag(hdev, HCI_UNCONFIGURED)) { + hci_dev_set_flag(hdev, HCI_CONFIG); + hci_dev_set_flag(hdev, HCI_AUTO_OFF); queue_work(hdev->req_workqueue, &hdev->power_on); } else { @@ -6054,16 +6413,16 @@ static int set_public_address(struct sock *sk, struct hci_dev *hdev, BT_DBG("%s", hdev->name); if (hdev_is_powered(hdev)) - return cmd_status(sk, hdev->id, MGMT_OP_SET_PUBLIC_ADDRESS, - MGMT_STATUS_REJECTED); + return mgmt_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); + return mgmt_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); + return mgmt_cmd_status(sk, hdev->id, MGMT_OP_SET_PUBLIC_ADDRESS, + MGMT_STATUS_NOT_SUPPORTED); hci_dev_lock(hdev); @@ -6077,16 +6436,16 @@ static int set_public_address(struct sock *sk, struct hci_dev *hdev, if (!changed) goto unlock; - if (test_bit(HCI_UNCONFIGURED, &hdev->dev_flags)) + if (hci_dev_test_flag(hdev, HCI_UNCONFIGURED)) err = new_options(hdev, sk); if (is_configured(hdev)) { mgmt_index_removed(hdev); - clear_bit(HCI_UNCONFIGURED, &hdev->dev_flags); + hci_dev_clear_flag(hdev, HCI_UNCONFIGURED); - set_bit(HCI_CONFIG, &hdev->dev_flags); - set_bit(HCI_AUTO_OFF, &hdev->dev_flags); + hci_dev_set_flag(hdev, HCI_CONFIG); + hci_dev_set_flag(hdev, HCI_AUTO_OFF); queue_work(hdev->req_workqueue, &hdev->power_on); } @@ -6096,213 +6455,852 @@ unlock: return err; } -static const struct mgmt_handler { - int (*func) (struct sock *sk, struct hci_dev *hdev, void *data, - u16 data_len); - bool var_len; - size_t data_len; -} mgmt_handlers[] = { - { NULL }, /* 0x0000 (no command) */ - { read_version, false, MGMT_READ_VERSION_SIZE }, - { read_commands, false, MGMT_READ_COMMANDS_SIZE }, - { read_index_list, false, MGMT_READ_INDEX_LIST_SIZE }, - { read_controller_info, false, MGMT_READ_INFO_SIZE }, - { set_powered, false, MGMT_SETTING_SIZE }, - { set_discoverable, false, MGMT_SET_DISCOVERABLE_SIZE }, - { set_connectable, false, MGMT_SETTING_SIZE }, - { set_fast_connectable, 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 }, - { set_le, false, MGMT_SETTING_SIZE }, - { set_dev_class, false, MGMT_SET_DEV_CLASS_SIZE }, - { set_local_name, false, MGMT_SET_LOCAL_NAME_SIZE }, - { add_uuid, false, MGMT_ADD_UUID_SIZE }, - { remove_uuid, false, MGMT_REMOVE_UUID_SIZE }, - { load_link_keys, true, MGMT_LOAD_LINK_KEYS_SIZE }, - { load_long_term_keys, true, MGMT_LOAD_LONG_TERM_KEYS_SIZE }, - { disconnect, false, MGMT_DISCONNECT_SIZE }, - { get_connections, false, MGMT_GET_CONNECTIONS_SIZE }, - { pin_code_reply, false, MGMT_PIN_CODE_REPLY_SIZE }, - { pin_code_neg_reply, false, MGMT_PIN_CODE_NEG_REPLY_SIZE }, - { set_io_capability, false, MGMT_SET_IO_CAPABILITY_SIZE }, - { pair_device, false, MGMT_PAIR_DEVICE_SIZE }, - { cancel_pair_device, false, MGMT_CANCEL_PAIR_DEVICE_SIZE }, - { unpair_device, false, MGMT_UNPAIR_DEVICE_SIZE }, - { user_confirm_reply, false, MGMT_USER_CONFIRM_REPLY_SIZE }, - { user_confirm_neg_reply, false, MGMT_USER_CONFIRM_NEG_REPLY_SIZE }, - { user_passkey_reply, false, MGMT_USER_PASSKEY_REPLY_SIZE }, - { user_passkey_neg_reply, false, MGMT_USER_PASSKEY_NEG_REPLY_SIZE }, - { read_local_oob_data, false, MGMT_READ_LOCAL_OOB_DATA_SIZE }, - { add_remote_oob_data, true, MGMT_ADD_REMOTE_OOB_DATA_SIZE }, - { remove_remote_oob_data, false, MGMT_REMOVE_REMOTE_OOB_DATA_SIZE }, - { start_discovery, false, MGMT_START_DISCOVERY_SIZE }, - { stop_discovery, false, MGMT_STOP_DISCOVERY_SIZE }, - { confirm_name, false, MGMT_CONFIRM_NAME_SIZE }, - { block_device, false, MGMT_BLOCK_DEVICE_SIZE }, - { unblock_device, false, MGMT_UNBLOCK_DEVICE_SIZE }, - { set_device_id, false, MGMT_SET_DEVICE_ID_SIZE }, - { set_advertising, false, MGMT_SETTING_SIZE }, - { set_bredr, false, MGMT_SETTING_SIZE }, - { set_static_address, false, MGMT_SET_STATIC_ADDRESS_SIZE }, - { set_scan_params, false, MGMT_SET_SCAN_PARAMS_SIZE }, - { set_secure_conn, false, MGMT_SETTING_SIZE }, - { set_debug_keys, false, MGMT_SETTING_SIZE }, - { 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 }, - { start_service_discovery,true, MGMT_START_SERVICE_DISCOVERY_SIZE }, -}; +static inline u16 eir_append_data(u8 *eir, u16 eir_len, u8 type, u8 *data, + u8 data_len) +{ + eir[eir_len++] = sizeof(type) + data_len; + eir[eir_len++] = type; + memcpy(&eir[eir_len], data, data_len); + eir_len += data_len; -int mgmt_control(struct sock *sk, struct msghdr *msg, size_t msglen) + return eir_len; +} + +static void read_local_oob_ext_data_complete(struct hci_dev *hdev, u8 status, + u16 opcode, struct sk_buff *skb) { - void *buf; - u8 *cp; - struct mgmt_hdr *hdr; - u16 opcode, index, len; - struct hci_dev *hdev = NULL; - const struct mgmt_handler *handler; + const struct mgmt_cp_read_local_oob_ext_data *mgmt_cp; + struct mgmt_rp_read_local_oob_ext_data *mgmt_rp; + u8 *h192, *r192, *h256, *r256; + struct mgmt_pending_cmd *cmd; + u16 eir_len; int err; - BT_DBG("got %zu bytes", msglen); + BT_DBG("%s status %u", hdev->name, status); - if (msglen < sizeof(*hdr)) - return -EINVAL; + cmd = pending_find(MGMT_OP_READ_LOCAL_OOB_EXT_DATA, hdev); + if (!cmd) + return; - buf = kmalloc(msglen, GFP_KERNEL); - if (!buf) - return -ENOMEM; + mgmt_cp = cmd->param; + + if (status) { + status = mgmt_status(status); + eir_len = 0; + + h192 = NULL; + r192 = NULL; + h256 = NULL; + r256 = NULL; + } else if (opcode == HCI_OP_READ_LOCAL_OOB_DATA) { + struct hci_rp_read_local_oob_data *rp; + + if (skb->len != sizeof(*rp)) { + status = MGMT_STATUS_FAILED; + eir_len = 0; + } else { + status = MGMT_STATUS_SUCCESS; + rp = (void *)skb->data; - if (memcpy_from_msg(buf, msg, msglen)) { - err = -EFAULT; + eir_len = 5 + 18 + 18; + h192 = rp->hash; + r192 = rp->rand; + h256 = NULL; + r256 = NULL; + } + } else { + struct hci_rp_read_local_oob_ext_data *rp; + + if (skb->len != sizeof(*rp)) { + status = MGMT_STATUS_FAILED; + eir_len = 0; + } else { + status = MGMT_STATUS_SUCCESS; + rp = (void *)skb->data; + + if (hci_dev_test_flag(hdev, HCI_SC_ONLY)) { + eir_len = 5 + 18 + 18; + h192 = NULL; + r192 = NULL; + } else { + eir_len = 5 + 18 + 18 + 18 + 18; + h192 = rp->hash192; + r192 = rp->rand192; + } + + h256 = rp->hash256; + r256 = rp->rand256; + } + } + + mgmt_rp = kmalloc(sizeof(*mgmt_rp) + eir_len, GFP_KERNEL); + if (!mgmt_rp) goto done; + + if (status) + goto send_rsp; + + eir_len = eir_append_data(mgmt_rp->eir, 0, EIR_CLASS_OF_DEV, + hdev->dev_class, 3); + + if (h192 && r192) { + eir_len = eir_append_data(mgmt_rp->eir, eir_len, + EIR_SSP_HASH_C192, h192, 16); + eir_len = eir_append_data(mgmt_rp->eir, eir_len, + EIR_SSP_RAND_R192, r192, 16); + } + + if (h256 && r256) { + eir_len = eir_append_data(mgmt_rp->eir, eir_len, + EIR_SSP_HASH_C256, h256, 16); + eir_len = eir_append_data(mgmt_rp->eir, eir_len, + EIR_SSP_RAND_R256, r256, 16); } - hdr = buf; - opcode = __le16_to_cpu(hdr->opcode); - index = __le16_to_cpu(hdr->index); - len = __le16_to_cpu(hdr->len); +send_rsp: + mgmt_rp->type = mgmt_cp->type; + mgmt_rp->eir_len = cpu_to_le16(eir_len); - if (len != msglen - sizeof(*hdr)) { - err = -EINVAL; + err = mgmt_cmd_complete(cmd->sk, hdev->id, + MGMT_OP_READ_LOCAL_OOB_EXT_DATA, status, + mgmt_rp, sizeof(*mgmt_rp) + eir_len); + if (err < 0 || status) goto done; + + hci_sock_set_flag(cmd->sk, HCI_MGMT_OOB_DATA_EVENTS); + + err = mgmt_limited_event(MGMT_EV_LOCAL_OOB_DATA_UPDATED, hdev, + mgmt_rp, sizeof(*mgmt_rp) + eir_len, + HCI_MGMT_OOB_DATA_EVENTS, cmd->sk); +done: + kfree(mgmt_rp); + mgmt_pending_remove(cmd); +} + +static int read_local_ssp_oob_req(struct hci_dev *hdev, struct sock *sk, + struct mgmt_cp_read_local_oob_ext_data *cp) +{ + struct mgmt_pending_cmd *cmd; + struct hci_request req; + int err; + + cmd = mgmt_pending_add(sk, MGMT_OP_READ_LOCAL_OOB_EXT_DATA, hdev, + cp, sizeof(*cp)); + if (!cmd) + return -ENOMEM; + + hci_req_init(&req, hdev); + + if (bredr_sc_enabled(hdev)) + hci_req_add(&req, HCI_OP_READ_LOCAL_OOB_EXT_DATA, 0, NULL); + else + hci_req_add(&req, HCI_OP_READ_LOCAL_OOB_DATA, 0, NULL); + + err = hci_req_run_skb(&req, read_local_oob_ext_data_complete); + if (err < 0) { + mgmt_pending_remove(cmd); + return err; } - if (index != MGMT_INDEX_NONE) { - hdev = hci_dev_get(index); - if (!hdev) { - err = cmd_status(sk, index, opcode, - MGMT_STATUS_INVALID_INDEX); - goto done; + return 0; +} + +static int read_local_oob_ext_data(struct sock *sk, struct hci_dev *hdev, + void *data, u16 data_len) +{ + struct mgmt_cp_read_local_oob_ext_data *cp = data; + struct mgmt_rp_read_local_oob_ext_data *rp; + size_t rp_len; + u16 eir_len; + u8 status, flags, role, addr[7], hash[16], rand[16]; + int err; + + BT_DBG("%s", hdev->name); + + if (hdev_is_powered(hdev)) { + switch (cp->type) { + case BIT(BDADDR_BREDR): + status = mgmt_bredr_support(hdev); + if (status) + eir_len = 0; + else + eir_len = 5; + break; + case (BIT(BDADDR_LE_PUBLIC) | BIT(BDADDR_LE_RANDOM)): + status = mgmt_le_support(hdev); + if (status) + eir_len = 0; + else + eir_len = 9 + 3 + 18 + 18 + 3; + break; + default: + status = MGMT_STATUS_INVALID_PARAMS; + eir_len = 0; + break; } + } else { + status = MGMT_STATUS_NOT_POWERED; + eir_len = 0; + } - 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; + rp_len = sizeof(*rp) + eir_len; + rp = kmalloc(rp_len, GFP_ATOMIC); + if (!rp) + return -ENOMEM; + + if (status) + goto complete; + + hci_dev_lock(hdev); + + eir_len = 0; + switch (cp->type) { + case BIT(BDADDR_BREDR): + if (hci_dev_test_flag(hdev, HCI_SSP_ENABLED)) { + err = read_local_ssp_oob_req(hdev, sk, cp); + hci_dev_unlock(hdev); + if (!err) + goto done; + + status = MGMT_STATUS_FAILED; + goto complete; + } else { + eir_len = eir_append_data(rp->eir, eir_len, + EIR_CLASS_OF_DEV, + hdev->dev_class, 3); + } + break; + case (BIT(BDADDR_LE_PUBLIC) | BIT(BDADDR_LE_RANDOM)): + if (hci_dev_test_flag(hdev, HCI_SC_ENABLED) && + smp_generate_oob(hdev, hash, rand) < 0) { + hci_dev_unlock(hdev); + status = MGMT_STATUS_FAILED; + goto complete; + } + + /* This should return the active RPA, but since the RPA + * is only programmed on demand, it is really hard to fill + * this in at the moment. For now disallow retrieving + * local out-of-band data when privacy is in use. + * + * Returning the identity address will not help here since + * pairing happens before the identity resolving key is + * known and thus the connection establishment happens + * based on the RPA and not the identity address. + */ + if (hci_dev_test_flag(hdev, HCI_PRIVACY)) { + hci_dev_unlock(hdev); + status = MGMT_STATUS_REJECTED; + goto complete; } - 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 (hci_dev_test_flag(hdev, HCI_FORCE_STATIC_ADDR) || + !bacmp(&hdev->bdaddr, BDADDR_ANY) || + (!hci_dev_test_flag(hdev, HCI_BREDR_ENABLED) && + bacmp(&hdev->static_addr, BDADDR_ANY))) { + memcpy(addr, &hdev->static_addr, 6); + addr[6] = 0x01; + } else { + memcpy(addr, &hdev->bdaddr, 6); + addr[6] = 0x00; + } + + eir_len = eir_append_data(rp->eir, eir_len, EIR_LE_BDADDR, + addr, sizeof(addr)); + + if (hci_dev_test_flag(hdev, HCI_ADVERTISING)) + role = 0x02; + else + role = 0x01; + + eir_len = eir_append_data(rp->eir, eir_len, EIR_LE_ROLE, + &role, sizeof(role)); + + if (hci_dev_test_flag(hdev, HCI_SC_ENABLED)) { + eir_len = eir_append_data(rp->eir, eir_len, + EIR_LE_SC_CONFIRM, + hash, sizeof(hash)); + + eir_len = eir_append_data(rp->eir, eir_len, + EIR_LE_SC_RANDOM, + rand, sizeof(rand)); } + + flags = get_adv_discov_flags(hdev); + + if (!hci_dev_test_flag(hdev, HCI_BREDR_ENABLED)) + flags |= LE_AD_NO_BREDR; + + eir_len = eir_append_data(rp->eir, eir_len, EIR_FLAGS, + &flags, sizeof(flags)); + break; } - if (opcode >= ARRAY_SIZE(mgmt_handlers) || - mgmt_handlers[opcode].func == NULL) { - BT_DBG("Unknown op %u", opcode); - err = cmd_status(sk, index, opcode, - MGMT_STATUS_UNKNOWN_COMMAND); + hci_dev_unlock(hdev); + + hci_sock_set_flag(sk, HCI_MGMT_OOB_DATA_EVENTS); + + status = MGMT_STATUS_SUCCESS; + +complete: + rp->type = cp->type; + rp->eir_len = cpu_to_le16(eir_len); + + err = mgmt_cmd_complete(sk, hdev->id, MGMT_OP_READ_LOCAL_OOB_EXT_DATA, + status, rp, sizeof(*rp) + eir_len); + if (err < 0 || status) goto done; + + err = mgmt_limited_event(MGMT_EV_LOCAL_OOB_DATA_UPDATED, hdev, + rp, sizeof(*rp) + eir_len, + HCI_MGMT_OOB_DATA_EVENTS, sk); + +done: + kfree(rp); + + return err; +} + +static u32 get_supported_adv_flags(struct hci_dev *hdev) +{ + u32 flags = 0; + + flags |= MGMT_ADV_FLAG_CONNECTABLE; + flags |= MGMT_ADV_FLAG_DISCOV; + flags |= MGMT_ADV_FLAG_LIMITED_DISCOV; + flags |= MGMT_ADV_FLAG_MANAGED_FLAGS; + + if (hdev->adv_tx_power != HCI_TX_POWER_INVALID) + flags |= MGMT_ADV_FLAG_TX_POWER; + + return flags; +} + +static int read_adv_features(struct sock *sk, struct hci_dev *hdev, + void *data, u16 data_len) +{ + struct mgmt_rp_read_adv_features *rp; + size_t rp_len; + int err; + bool instance; + u32 supported_flags; + + BT_DBG("%s", hdev->name); + + if (!lmp_le_capable(hdev)) + return mgmt_cmd_status(sk, hdev->id, MGMT_OP_READ_ADV_FEATURES, + MGMT_STATUS_REJECTED); + + hci_dev_lock(hdev); + + rp_len = sizeof(*rp); + + /* Currently only one instance is supported, so just add 1 to the + * response length. + */ + instance = hci_dev_test_flag(hdev, HCI_ADVERTISING_INSTANCE); + if (instance) + rp_len++; + + rp = kmalloc(rp_len, GFP_ATOMIC); + if (!rp) { + hci_dev_unlock(hdev); + return -ENOMEM; } - 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; + supported_flags = get_supported_adv_flags(hdev); + + rp->supported_flags = cpu_to_le32(supported_flags); + rp->max_adv_data_len = HCI_MAX_AD_LENGTH; + rp->max_scan_rsp_len = HCI_MAX_AD_LENGTH; + rp->max_instances = 1; + + /* Currently only one instance is supported, so simply return the + * current instance number. + */ + if (instance) { + rp->num_instances = 1; + rp->instance[0] = 1; + } else { + rp->num_instances = 0; } - 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; + hci_dev_unlock(hdev); + + err = mgmt_cmd_complete(sk, hdev->id, MGMT_OP_READ_ADV_FEATURES, + MGMT_STATUS_SUCCESS, rp, rp_len); + + kfree(rp); + + return err; +} + +static bool tlv_data_is_valid(struct hci_dev *hdev, u32 adv_flags, u8 *data, + u8 len, bool is_adv_data) +{ + u8 max_len = HCI_MAX_AD_LENGTH; + int i, cur_len; + bool flags_managed = false; + bool tx_power_managed = false; + u32 flags_params = MGMT_ADV_FLAG_DISCOV | MGMT_ADV_FLAG_LIMITED_DISCOV | + MGMT_ADV_FLAG_MANAGED_FLAGS; + + if (is_adv_data && (adv_flags & flags_params)) { + flags_managed = true; + max_len -= 3; } - handler = &mgmt_handlers[opcode]; + if (is_adv_data && (adv_flags & MGMT_ADV_FLAG_TX_POWER)) { + tx_power_managed = true; + max_len -= 3; + } - if ((handler->var_len && len < handler->data_len) || - (!handler->var_len && len != handler->data_len)) { - err = cmd_status(sk, index, opcode, - MGMT_STATUS_INVALID_PARAMS); - goto done; + if (len > max_len) + return false; + + /* Make sure that the data is correctly formatted. */ + for (i = 0, cur_len = 0; i < len; i += (cur_len + 1)) { + cur_len = data[i]; + + if (flags_managed && data[i + 1] == EIR_FLAGS) + return false; + + if (tx_power_managed && data[i + 1] == EIR_TX_POWER) + return false; + + /* If the current field length would exceed the total data + * length, then it's invalid. + */ + if (i + cur_len >= len) + return false; } - if (hdev) - mgmt_init_hdev(sk, hdev); + return true; +} + +static void add_advertising_complete(struct hci_dev *hdev, u8 status, + u16 opcode) +{ + struct mgmt_pending_cmd *cmd; + struct mgmt_rp_add_advertising rp; + + BT_DBG("status %d", status); + + hci_dev_lock(hdev); + + cmd = pending_find(MGMT_OP_ADD_ADVERTISING, hdev); + + if (status) { + hci_dev_clear_flag(hdev, HCI_ADVERTISING_INSTANCE); + memset(&hdev->adv_instance, 0, sizeof(hdev->adv_instance)); + advertising_removed(cmd ? cmd->sk : NULL, hdev, 1); + } + + if (!cmd) + goto unlock; - cp = buf + sizeof(*hdr); + rp.instance = 0x01; + + if (status) + mgmt_cmd_status(cmd->sk, cmd->index, cmd->opcode, + mgmt_status(status)); + else + mgmt_cmd_complete(cmd->sk, cmd->index, cmd->opcode, + mgmt_status(status), &rp, sizeof(rp)); + + mgmt_pending_remove(cmd); + +unlock: + hci_dev_unlock(hdev); +} + +static void adv_timeout_expired(struct work_struct *work) +{ + struct hci_dev *hdev = container_of(work, struct hci_dev, + adv_instance.timeout_exp.work); + + hdev->adv_instance.timeout = 0; + + hci_dev_lock(hdev); + clear_adv_instance(hdev); + hci_dev_unlock(hdev); +} + +static int add_advertising(struct sock *sk, struct hci_dev *hdev, + void *data, u16 data_len) +{ + struct mgmt_cp_add_advertising *cp = data; + struct mgmt_rp_add_advertising rp; + u32 flags; + u32 supported_flags; + u8 status; + u16 timeout; + int err; + struct mgmt_pending_cmd *cmd; + struct hci_request req; + + BT_DBG("%s", hdev->name); + + status = mgmt_le_support(hdev); + if (status) + return mgmt_cmd_status(sk, hdev->id, MGMT_OP_ADD_ADVERTISING, + status); - err = handler->func(sk, hdev, cp, len); + flags = __le32_to_cpu(cp->flags); + timeout = __le16_to_cpu(cp->timeout); + + /* The current implementation only supports adding one instance and only + * a subset of the specified flags. + */ + supported_flags = get_supported_adv_flags(hdev); + if (cp->instance != 0x01 || (flags & ~supported_flags)) + return mgmt_cmd_status(sk, hdev->id, MGMT_OP_ADD_ADVERTISING, + MGMT_STATUS_INVALID_PARAMS); + + hci_dev_lock(hdev); + + if (timeout && !hdev_is_powered(hdev)) { + err = mgmt_cmd_status(sk, hdev->id, MGMT_OP_ADD_ADVERTISING, + MGMT_STATUS_REJECTED); + goto unlock; + } + + if (pending_find(MGMT_OP_ADD_ADVERTISING, hdev) || + pending_find(MGMT_OP_REMOVE_ADVERTISING, hdev) || + pending_find(MGMT_OP_SET_LE, hdev)) { + err = mgmt_cmd_status(sk, hdev->id, MGMT_OP_ADD_ADVERTISING, + MGMT_STATUS_BUSY); + goto unlock; + } + + if (!tlv_data_is_valid(hdev, flags, cp->data, cp->adv_data_len, true) || + !tlv_data_is_valid(hdev, flags, cp->data + cp->adv_data_len, + cp->scan_rsp_len, false)) { + err = mgmt_cmd_status(sk, hdev->id, MGMT_OP_ADD_ADVERTISING, + MGMT_STATUS_INVALID_PARAMS); + goto unlock; + } + + INIT_DELAYED_WORK(&hdev->adv_instance.timeout_exp, adv_timeout_expired); + + hdev->adv_instance.flags = flags; + hdev->adv_instance.adv_data_len = cp->adv_data_len; + hdev->adv_instance.scan_rsp_len = cp->scan_rsp_len; + + if (cp->adv_data_len) + memcpy(hdev->adv_instance.adv_data, cp->data, cp->adv_data_len); + + if (cp->scan_rsp_len) + memcpy(hdev->adv_instance.scan_rsp_data, + cp->data + cp->adv_data_len, cp->scan_rsp_len); + + if (hdev->adv_instance.timeout) + cancel_delayed_work(&hdev->adv_instance.timeout_exp); + + hdev->adv_instance.timeout = timeout; + + if (timeout) + queue_delayed_work(hdev->workqueue, + &hdev->adv_instance.timeout_exp, + msecs_to_jiffies(timeout * 1000)); + + if (!hci_dev_test_and_set_flag(hdev, HCI_ADVERTISING_INSTANCE)) + advertising_added(sk, hdev, 1); + + /* If the HCI_ADVERTISING flag is set or the device isn't powered then + * we have no HCI communication to make. Simply return. + */ + if (!hdev_is_powered(hdev) || + hci_dev_test_flag(hdev, HCI_ADVERTISING)) { + rp.instance = 0x01; + err = mgmt_cmd_complete(sk, hdev->id, MGMT_OP_ADD_ADVERTISING, + MGMT_STATUS_SUCCESS, &rp, sizeof(rp)); + goto unlock; + } + + /* We're good to go, update advertising data, parameters, and start + * advertising. + */ + cmd = mgmt_pending_add(sk, MGMT_OP_ADD_ADVERTISING, hdev, data, + data_len); + if (!cmd) { + err = -ENOMEM; + goto unlock; + } + + hci_req_init(&req, hdev); + + update_adv_data(&req); + update_scan_rsp_data(&req); + enable_advertising(&req); + + err = hci_req_run(&req, add_advertising_complete); if (err < 0) - goto done; + mgmt_pending_remove(cmd); + +unlock: + hci_dev_unlock(hdev); - err = msglen; + return err; +} -done: - if (hdev) - hci_dev_put(hdev); +static void remove_advertising_complete(struct hci_dev *hdev, u8 status, + u16 opcode) +{ + struct mgmt_pending_cmd *cmd; + struct mgmt_rp_remove_advertising rp; + + BT_DBG("status %d", status); + + hci_dev_lock(hdev); + + /* A failure status here only means that we failed to disable + * advertising. Otherwise, the advertising instance has been removed, + * so report success. + */ + cmd = pending_find(MGMT_OP_REMOVE_ADVERTISING, hdev); + if (!cmd) + goto unlock; + + rp.instance = 1; + + mgmt_cmd_complete(cmd->sk, cmd->index, cmd->opcode, MGMT_STATUS_SUCCESS, + &rp, sizeof(rp)); + mgmt_pending_remove(cmd); + +unlock: + hci_dev_unlock(hdev); +} + +static int remove_advertising(struct sock *sk, struct hci_dev *hdev, + void *data, u16 data_len) +{ + struct mgmt_cp_remove_advertising *cp = data; + struct mgmt_rp_remove_advertising rp; + int err; + struct mgmt_pending_cmd *cmd; + struct hci_request req; + + BT_DBG("%s", hdev->name); + + /* The current implementation only allows modifying instance no 1. A + * value of 0 indicates that all instances should be cleared. + */ + if (cp->instance > 1) + return mgmt_cmd_status(sk, hdev->id, MGMT_OP_REMOVE_ADVERTISING, + MGMT_STATUS_INVALID_PARAMS); + + hci_dev_lock(hdev); + + if (pending_find(MGMT_OP_ADD_ADVERTISING, hdev) || + pending_find(MGMT_OP_REMOVE_ADVERTISING, hdev) || + pending_find(MGMT_OP_SET_LE, hdev)) { + err = mgmt_cmd_status(sk, hdev->id, MGMT_OP_REMOVE_ADVERTISING, + MGMT_STATUS_BUSY); + goto unlock; + } + + if (!hci_dev_test_flag(hdev, HCI_ADVERTISING_INSTANCE)) { + err = mgmt_cmd_status(sk, hdev->id, MGMT_OP_REMOVE_ADVERTISING, + MGMT_STATUS_INVALID_PARAMS); + goto unlock; + } + + if (hdev->adv_instance.timeout) + cancel_delayed_work(&hdev->adv_instance.timeout_exp); + + memset(&hdev->adv_instance, 0, sizeof(hdev->adv_instance)); + + advertising_removed(sk, hdev, 1); + + hci_dev_clear_flag(hdev, HCI_ADVERTISING_INSTANCE); + + /* If the HCI_ADVERTISING flag is set or the device isn't powered then + * we have no HCI communication to make. Simply return. + */ + if (!hdev_is_powered(hdev) || + hci_dev_test_flag(hdev, HCI_ADVERTISING)) { + rp.instance = 1; + err = mgmt_cmd_complete(sk, hdev->id, + MGMT_OP_REMOVE_ADVERTISING, + MGMT_STATUS_SUCCESS, &rp, sizeof(rp)); + goto unlock; + } + + cmd = mgmt_pending_add(sk, MGMT_OP_REMOVE_ADVERTISING, hdev, data, + data_len); + if (!cmd) { + err = -ENOMEM; + goto unlock; + } + + hci_req_init(&req, hdev); + disable_advertising(&req); + + err = hci_req_run(&req, remove_advertising_complete); + if (err < 0) + mgmt_pending_remove(cmd); + +unlock: + hci_dev_unlock(hdev); - kfree(buf); return err; } +static const struct hci_mgmt_handler mgmt_handlers[] = { + { NULL }, /* 0x0000 (no command) */ + { read_version, MGMT_READ_VERSION_SIZE, + HCI_MGMT_NO_HDEV | + HCI_MGMT_UNTRUSTED }, + { read_commands, MGMT_READ_COMMANDS_SIZE, + HCI_MGMT_NO_HDEV | + HCI_MGMT_UNTRUSTED }, + { read_index_list, MGMT_READ_INDEX_LIST_SIZE, + HCI_MGMT_NO_HDEV | + HCI_MGMT_UNTRUSTED }, + { read_controller_info, MGMT_READ_INFO_SIZE, + HCI_MGMT_UNTRUSTED }, + { set_powered, MGMT_SETTING_SIZE }, + { set_discoverable, MGMT_SET_DISCOVERABLE_SIZE }, + { set_connectable, MGMT_SETTING_SIZE }, + { set_fast_connectable, MGMT_SETTING_SIZE }, + { set_bondable, MGMT_SETTING_SIZE }, + { set_link_security, MGMT_SETTING_SIZE }, + { set_ssp, MGMT_SETTING_SIZE }, + { set_hs, MGMT_SETTING_SIZE }, + { set_le, MGMT_SETTING_SIZE }, + { set_dev_class, MGMT_SET_DEV_CLASS_SIZE }, + { set_local_name, MGMT_SET_LOCAL_NAME_SIZE }, + { add_uuid, MGMT_ADD_UUID_SIZE }, + { remove_uuid, MGMT_REMOVE_UUID_SIZE }, + { load_link_keys, MGMT_LOAD_LINK_KEYS_SIZE, + HCI_MGMT_VAR_LEN }, + { load_long_term_keys, MGMT_LOAD_LONG_TERM_KEYS_SIZE, + HCI_MGMT_VAR_LEN }, + { disconnect, MGMT_DISCONNECT_SIZE }, + { get_connections, MGMT_GET_CONNECTIONS_SIZE }, + { pin_code_reply, MGMT_PIN_CODE_REPLY_SIZE }, + { pin_code_neg_reply, MGMT_PIN_CODE_NEG_REPLY_SIZE }, + { set_io_capability, MGMT_SET_IO_CAPABILITY_SIZE }, + { pair_device, MGMT_PAIR_DEVICE_SIZE }, + { cancel_pair_device, MGMT_CANCEL_PAIR_DEVICE_SIZE }, + { unpair_device, MGMT_UNPAIR_DEVICE_SIZE }, + { user_confirm_reply, MGMT_USER_CONFIRM_REPLY_SIZE }, + { user_confirm_neg_reply, MGMT_USER_CONFIRM_NEG_REPLY_SIZE }, + { user_passkey_reply, MGMT_USER_PASSKEY_REPLY_SIZE }, + { user_passkey_neg_reply, MGMT_USER_PASSKEY_NEG_REPLY_SIZE }, + { read_local_oob_data, MGMT_READ_LOCAL_OOB_DATA_SIZE }, + { add_remote_oob_data, MGMT_ADD_REMOTE_OOB_DATA_SIZE, + HCI_MGMT_VAR_LEN }, + { remove_remote_oob_data, MGMT_REMOVE_REMOTE_OOB_DATA_SIZE }, + { start_discovery, MGMT_START_DISCOVERY_SIZE }, + { stop_discovery, MGMT_STOP_DISCOVERY_SIZE }, + { confirm_name, MGMT_CONFIRM_NAME_SIZE }, + { block_device, MGMT_BLOCK_DEVICE_SIZE }, + { unblock_device, MGMT_UNBLOCK_DEVICE_SIZE }, + { set_device_id, MGMT_SET_DEVICE_ID_SIZE }, + { set_advertising, MGMT_SETTING_SIZE }, + { set_bredr, MGMT_SETTING_SIZE }, + { set_static_address, MGMT_SET_STATIC_ADDRESS_SIZE }, + { set_scan_params, MGMT_SET_SCAN_PARAMS_SIZE }, + { set_secure_conn, MGMT_SETTING_SIZE }, + { set_debug_keys, MGMT_SETTING_SIZE }, + { set_privacy, MGMT_SET_PRIVACY_SIZE }, + { load_irks, MGMT_LOAD_IRKS_SIZE, + HCI_MGMT_VAR_LEN }, + { get_conn_info, MGMT_GET_CONN_INFO_SIZE }, + { get_clock_info, MGMT_GET_CLOCK_INFO_SIZE }, + { add_device, MGMT_ADD_DEVICE_SIZE }, + { remove_device, MGMT_REMOVE_DEVICE_SIZE }, + { load_conn_param, MGMT_LOAD_CONN_PARAM_SIZE, + HCI_MGMT_VAR_LEN }, + { read_unconf_index_list, MGMT_READ_UNCONF_INDEX_LIST_SIZE, + HCI_MGMT_NO_HDEV | + HCI_MGMT_UNTRUSTED }, + { read_config_info, MGMT_READ_CONFIG_INFO_SIZE, + HCI_MGMT_UNCONFIGURED | + HCI_MGMT_UNTRUSTED }, + { set_external_config, MGMT_SET_EXTERNAL_CONFIG_SIZE, + HCI_MGMT_UNCONFIGURED }, + { set_public_address, MGMT_SET_PUBLIC_ADDRESS_SIZE, + HCI_MGMT_UNCONFIGURED }, + { start_service_discovery, MGMT_START_SERVICE_DISCOVERY_SIZE, + HCI_MGMT_VAR_LEN }, + { read_local_oob_ext_data, MGMT_READ_LOCAL_OOB_EXT_DATA_SIZE }, + { read_ext_index_list, MGMT_READ_EXT_INDEX_LIST_SIZE, + HCI_MGMT_NO_HDEV | + HCI_MGMT_UNTRUSTED }, + { read_adv_features, MGMT_READ_ADV_FEATURES_SIZE }, + { add_advertising, MGMT_ADD_ADVERTISING_SIZE, + HCI_MGMT_VAR_LEN }, + { remove_advertising, MGMT_REMOVE_ADVERTISING_SIZE }, +}; + void mgmt_index_added(struct hci_dev *hdev) { - if (hdev->dev_type != HCI_BREDR) - return; + struct mgmt_ev_ext_index ev; 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); + switch (hdev->dev_type) { + case HCI_BREDR: + if (hci_dev_test_flag(hdev, HCI_UNCONFIGURED)) { + mgmt_index_event(MGMT_EV_UNCONF_INDEX_ADDED, hdev, + NULL, 0, HCI_MGMT_UNCONF_INDEX_EVENTS); + ev.type = 0x01; + } else { + mgmt_index_event(MGMT_EV_INDEX_ADDED, hdev, NULL, 0, + HCI_MGMT_INDEX_EVENTS); + ev.type = 0x00; + } + break; + case HCI_AMP: + ev.type = 0x02; + break; + default: + return; + } + + ev.bus = hdev->bus; + + mgmt_index_event(MGMT_EV_EXT_INDEX_ADDED, hdev, &ev, sizeof(ev), + HCI_MGMT_EXT_INDEX_EVENTS); } void mgmt_index_removed(struct hci_dev *hdev) { + struct mgmt_ev_ext_index ev; u8 status = MGMT_STATUS_INVALID_INDEX; - if (hdev->dev_type != HCI_BREDR) + if (test_bit(HCI_QUIRK_RAW_DEVICE, &hdev->quirks)) return; - if (test_bit(HCI_QUIRK_RAW_DEVICE, &hdev->quirks)) + switch (hdev->dev_type) { + case HCI_BREDR: + mgmt_pending_foreach(0, hdev, cmd_complete_rsp, &status); + + if (hci_dev_test_flag(hdev, HCI_UNCONFIGURED)) { + mgmt_index_event(MGMT_EV_UNCONF_INDEX_REMOVED, hdev, + NULL, 0, HCI_MGMT_UNCONF_INDEX_EVENTS); + ev.type = 0x01; + } else { + mgmt_index_event(MGMT_EV_INDEX_REMOVED, hdev, NULL, 0, + HCI_MGMT_INDEX_EVENTS); + ev.type = 0x00; + } + break; + case HCI_AMP: + ev.type = 0x02; + break; + default: return; + } - mgmt_pending_foreach(0, hdev, cmd_complete_rsp, &status); + ev.bus = hdev->bus; - 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); + mgmt_index_event(MGMT_EV_EXT_INDEX_REMOVED, hdev, &ev, sizeof(ev), + HCI_MGMT_EXT_INDEX_EVENTS); } /* This function requires the caller holds hdev->lock */ @@ -6367,7 +7365,7 @@ static int powered_update_hci(struct hci_dev *hdev) hci_req_init(&req, hdev); - if (test_bit(HCI_SSP_ENABLED, &hdev->dev_flags) && + if (hci_dev_test_flag(hdev, HCI_SSP_ENABLED) && !lmp_host_ssp_capable(hdev)) { u8 mode = 0x01; @@ -6381,7 +7379,7 @@ static int powered_update_hci(struct hci_dev *hdev) } } - if (test_bit(HCI_LE_ENABLED, &hdev->dev_flags) && + if (hci_dev_test_flag(hdev, HCI_LE_ENABLED) && lmp_bredr_capable(hdev)) { struct hci_cp_write_le_host_supported cp; @@ -6402,24 +7400,28 @@ static int powered_update_hci(struct hci_dev *hdev) * advertising data. This also applies to the case * where BR/EDR was toggled during the AUTO_OFF phase. */ - if (test_bit(HCI_LE_ENABLED, &hdev->dev_flags)) { + if (hci_dev_test_flag(hdev, HCI_LE_ENABLED)) { update_adv_data(&req); update_scan_rsp_data(&req); } - if (test_bit(HCI_ADVERTISING, &hdev->dev_flags)) + if (hci_dev_test_flag(hdev, HCI_ADVERTISING) || + hci_dev_test_flag(hdev, HCI_ADVERTISING_INSTANCE)) enable_advertising(&req); restart_le_actions(&req); } - link_sec = test_bit(HCI_LINK_SECURITY, &hdev->dev_flags); + link_sec = hci_dev_test_flag(hdev, HCI_LINK_SECURITY); if (link_sec != test_bit(HCI_AUTH, &hdev->flags)) hci_req_add(&req, HCI_OP_WRITE_AUTH_ENABLE, sizeof(link_sec), &link_sec); if (lmp_bredr_capable(hdev)) { - write_fast_connectable(&req, false); + if (hci_dev_test_flag(hdev, HCI_FAST_CONNECTABLE)) + write_fast_connectable(&req, true); + else + write_fast_connectable(&req, false); __hci_update_page_scan(&req); update_class(&req); update_name(&req); @@ -6435,7 +7437,7 @@ int mgmt_powered(struct hci_dev *hdev, u8 powered) u8 status, zero_cod[] = { 0, 0, 0 }; int err; - if (!test_bit(HCI_MGMT, &hdev->dev_flags)) + if (!hci_dev_test_flag(hdev, HCI_MGMT)) return 0; if (powered) { @@ -6456,7 +7458,7 @@ int mgmt_powered(struct hci_dev *hdev, u8 powered) * been triggered, potentially causing misleading DISCONNECTED * status responses. */ - if (test_bit(HCI_UNREGISTER, &hdev->dev_flags)) + if (hci_dev_test_flag(hdev, HCI_UNREGISTER)) status = MGMT_STATUS_INVALID_INDEX; else status = MGMT_STATUS_NOT_POWERED; @@ -6464,8 +7466,8 @@ int mgmt_powered(struct hci_dev *hdev, u8 powered) mgmt_pending_foreach(0, hdev, cmd_complete_rsp, &status); if (memcmp(hdev->dev_class, zero_cod, sizeof(zero_cod)) != 0) - mgmt_event(MGMT_EV_CLASS_OF_DEV_CHANGED, hdev, - zero_cod, sizeof(zero_cod), NULL); + mgmt_generic_event(MGMT_EV_CLASS_OF_DEV_CHANGED, hdev, + zero_cod, sizeof(zero_cod), NULL); new_settings: err = new_settings(hdev, match.sk); @@ -6478,10 +7480,10 @@ new_settings: void mgmt_set_powered_failed(struct hci_dev *hdev, int err) { - struct pending_cmd *cmd; + struct mgmt_pending_cmd *cmd; u8 status; - cmd = mgmt_pending_find(MGMT_OP_SET_POWERED, hdev); + cmd = pending_find(MGMT_OP_SET_POWERED, hdev); if (!cmd) return; @@ -6490,7 +7492,7 @@ void mgmt_set_powered_failed(struct hci_dev *hdev, int err) else status = MGMT_STATUS_FAILED; - cmd_status(cmd->sk, hdev->id, MGMT_OP_SET_POWERED, status); + mgmt_cmd_status(cmd->sk, hdev->id, MGMT_OP_SET_POWERED, status); mgmt_pending_remove(cmd); } @@ -6506,17 +7508,23 @@ void mgmt_discoverable_timeout(struct hci_dev *hdev) * of a timeout triggered from general discoverable, it is * safe to unconditionally clear the flag. */ - clear_bit(HCI_LIMITED_DISCOVERABLE, &hdev->dev_flags); - clear_bit(HCI_DISCOVERABLE, &hdev->dev_flags); + hci_dev_clear_flag(hdev, HCI_LIMITED_DISCOVERABLE); + hci_dev_clear_flag(hdev, HCI_DISCOVERABLE); hci_req_init(&req, hdev); - if (test_bit(HCI_BREDR_ENABLED, &hdev->dev_flags)) { + if (hci_dev_test_flag(hdev, HCI_BREDR_ENABLED)) { u8 scan = SCAN_PAGE; hci_req_add(&req, HCI_OP_WRITE_SCAN_ENABLE, sizeof(scan), &scan); } update_class(&req); - update_adv_data(&req); + + /* Advertising instances don't use the global discoverable setting, so + * only update AD if advertising was enabled using Set Advertising. + */ + if (hci_dev_test_flag(hdev, HCI_ADVERTISING)) + update_adv_data(&req); + hci_req_run(&req, NULL); hdev->discov_timeout = 0; @@ -6654,7 +7662,7 @@ void mgmt_new_csrk(struct hci_dev *hdev, struct smp_csrk *csrk, bacpy(&ev.key.addr.bdaddr, &csrk->bdaddr); ev.key.addr.type = link_to_bdaddr(LE_LINK, csrk->bdaddr_type); - ev.key.master = csrk->master; + ev.key.type = csrk->type; memcpy(ev.key.val, csrk->val, sizeof(csrk->val)); mgmt_event(MGMT_EV_NEW_CSRK, hdev, &ev, sizeof(ev), NULL); @@ -6681,17 +7689,6 @@ void mgmt_new_conn_param(struct hci_dev *hdev, bdaddr_t *bdaddr, 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) -{ - eir[eir_len++] = sizeof(type) + data_len; - eir[eir_len++] = type; - memcpy(&eir[eir_len], data, data_len); - eir_len += data_len; - - return eir_len; -} - void mgmt_device_connected(struct hci_dev *hdev, struct hci_conn *conn, u32 flags, u8 *name, u8 name_len) { @@ -6729,7 +7726,7 @@ void mgmt_device_connected(struct hci_dev *hdev, struct hci_conn *conn, sizeof(*ev) + eir_len, NULL); } -static void disconnect_rsp(struct pending_cmd *cmd, void *data) +static void disconnect_rsp(struct mgmt_pending_cmd *cmd, void *data) { struct sock **sk = data; @@ -6741,7 +7738,7 @@ static void disconnect_rsp(struct pending_cmd *cmd, void *data) mgmt_pending_remove(cmd); } -static void unpair_device_rsp(struct pending_cmd *cmd, void *data) +static void unpair_device_rsp(struct mgmt_pending_cmd *cmd, void *data) { struct hci_dev *hdev = data; struct mgmt_cp_unpair_device *cp = cmd->param; @@ -6754,10 +7751,10 @@ static void unpair_device_rsp(struct pending_cmd *cmd, void *data) bool mgmt_powering_down(struct hci_dev *hdev) { - struct pending_cmd *cmd; + struct mgmt_pending_cmd *cmd; struct mgmt_mode *cp; - cmd = mgmt_pending_find(MGMT_OP_SET_POWERED, hdev); + cmd = pending_find(MGMT_OP_SET_POWERED, hdev); if (!cmd) return false; @@ -6809,12 +7806,12 @@ void mgmt_disconnect_failed(struct hci_dev *hdev, bdaddr_t *bdaddr, { u8 bdaddr_type = link_to_bdaddr(link_type, addr_type); struct mgmt_cp_disconnect *cp; - struct pending_cmd *cmd; + struct mgmt_pending_cmd *cmd; mgmt_pending_foreach(MGMT_OP_UNPAIR_DEVICE, hdev, unpair_device_rsp, hdev); - cmd = mgmt_pending_find(MGMT_OP_DISCONNECT, hdev); + cmd = pending_find(MGMT_OP_DISCONNECT, hdev); if (!cmd) return; @@ -6864,9 +7861,9 @@ void mgmt_pin_code_request(struct hci_dev *hdev, bdaddr_t *bdaddr, u8 secure) void mgmt_pin_code_reply_complete(struct hci_dev *hdev, bdaddr_t *bdaddr, u8 status) { - struct pending_cmd *cmd; + struct mgmt_pending_cmd *cmd; - cmd = mgmt_pending_find(MGMT_OP_PIN_CODE_REPLY, hdev); + cmd = pending_find(MGMT_OP_PIN_CODE_REPLY, hdev); if (!cmd) return; @@ -6877,9 +7874,9 @@ void mgmt_pin_code_reply_complete(struct hci_dev *hdev, bdaddr_t *bdaddr, void mgmt_pin_code_neg_reply_complete(struct hci_dev *hdev, bdaddr_t *bdaddr, u8 status) { - struct pending_cmd *cmd; + struct mgmt_pending_cmd *cmd; - cmd = mgmt_pending_find(MGMT_OP_PIN_CODE_NEG_REPLY, hdev); + cmd = pending_find(MGMT_OP_PIN_CODE_NEG_REPLY, hdev); if (!cmd) return; @@ -6922,9 +7919,9 @@ static int user_pairing_resp_complete(struct hci_dev *hdev, bdaddr_t *bdaddr, u8 link_type, u8 addr_type, u8 status, u8 opcode) { - struct pending_cmd *cmd; + struct mgmt_pending_cmd *cmd; - cmd = mgmt_pending_find(opcode, hdev); + cmd = pending_find(opcode, hdev); if (!cmd) return -ENOENT; @@ -6983,7 +7980,7 @@ int mgmt_user_passkey_notify(struct hci_dev *hdev, bdaddr_t *bdaddr, void mgmt_auth_failed(struct hci_conn *conn, u8 hci_status) { struct mgmt_ev_auth_failed ev; - struct pending_cmd *cmd; + struct mgmt_pending_cmd *cmd; u8 status = mgmt_status(hci_status); bacpy(&ev.addr.bdaddr, &conn->dst); @@ -7014,11 +8011,9 @@ void mgmt_auth_enable_complete(struct hci_dev *hdev, u8 status) } if (test_bit(HCI_AUTH, &hdev->flags)) - changed = !test_and_set_bit(HCI_LINK_SECURITY, - &hdev->dev_flags); + changed = !hci_dev_test_and_set_flag(hdev, HCI_LINK_SECURITY); else - changed = test_and_clear_bit(HCI_LINK_SECURITY, - &hdev->dev_flags); + changed = hci_dev_test_and_clear_flag(hdev, HCI_LINK_SECURITY); mgmt_pending_foreach(MGMT_OP_SET_LINK_SECURITY, hdev, settings_rsp, &match); @@ -7054,9 +8049,9 @@ void mgmt_ssp_enable_complete(struct hci_dev *hdev, u8 enable, u8 status) if (status) { u8 mgmt_err = mgmt_status(status); - if (enable && test_and_clear_bit(HCI_SSP_ENABLED, - &hdev->dev_flags)) { - clear_bit(HCI_HS_ENABLED, &hdev->dev_flags); + if (enable && hci_dev_test_and_clear_flag(hdev, + HCI_SSP_ENABLED)) { + hci_dev_clear_flag(hdev, HCI_HS_ENABLED); new_settings(hdev, NULL); } @@ -7066,14 +8061,14 @@ void mgmt_ssp_enable_complete(struct hci_dev *hdev, u8 enable, u8 status) } if (enable) { - changed = !test_and_set_bit(HCI_SSP_ENABLED, &hdev->dev_flags); + changed = !hci_dev_test_and_set_flag(hdev, HCI_SSP_ENABLED); } else { - changed = test_and_clear_bit(HCI_SSP_ENABLED, &hdev->dev_flags); + changed = hci_dev_test_and_clear_flag(hdev, HCI_SSP_ENABLED); if (!changed) - changed = test_and_clear_bit(HCI_HS_ENABLED, - &hdev->dev_flags); + changed = hci_dev_test_and_clear_flag(hdev, + HCI_HS_ENABLED); else - clear_bit(HCI_HS_ENABLED, &hdev->dev_flags); + hci_dev_clear_flag(hdev, HCI_HS_ENABLED); } mgmt_pending_foreach(MGMT_OP_SET_SSP, hdev, settings_rsp, &match); @@ -7086,8 +8081,8 @@ 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_USE_DEBUG_KEYS, &hdev->dev_flags)) + if (hci_dev_test_flag(hdev, HCI_SSP_ENABLED)) { + if (hci_dev_test_flag(hdev, HCI_USE_DEBUG_KEYS)) hci_req_add(&req, HCI_OP_WRITE_SSP_DEBUG_MODE, sizeof(enable), &enable); update_eir(&req); @@ -7098,7 +8093,7 @@ void mgmt_ssp_enable_complete(struct hci_dev *hdev, u8 enable, u8 status) hci_req_run(&req, NULL); } -static void sk_lookup(struct pending_cmd *cmd, void *data) +static void sk_lookup(struct mgmt_pending_cmd *cmd, void *data) { struct cmd_lookup *match = data; @@ -7118,8 +8113,8 @@ void mgmt_set_class_of_dev_complete(struct hci_dev *hdev, u8 *dev_class, mgmt_pending_foreach(MGMT_OP_REMOVE_UUID, hdev, sk_lookup, &match); if (!status) - mgmt_event(MGMT_EV_CLASS_OF_DEV_CHANGED, hdev, dev_class, 3, - NULL); + mgmt_generic_event(MGMT_EV_CLASS_OF_DEV_CHANGED, hdev, + dev_class, 3, NULL); if (match.sk) sock_put(match.sk); @@ -7128,7 +8123,7 @@ void mgmt_set_class_of_dev_complete(struct hci_dev *hdev, u8 *dev_class, void mgmt_set_local_name_complete(struct hci_dev *hdev, u8 *name, u8 status) { struct mgmt_cp_set_local_name ev; - struct pending_cmd *cmd; + struct mgmt_pending_cmd *cmd; if (status) return; @@ -7137,55 +8132,19 @@ void mgmt_set_local_name_complete(struct hci_dev *hdev, u8 *name, u8 status) memcpy(ev.name, name, HCI_MAX_NAME_LENGTH); memcpy(ev.short_name, hdev->short_name, HCI_MAX_SHORT_NAME_LENGTH); - cmd = mgmt_pending_find(MGMT_OP_SET_LOCAL_NAME, hdev); + cmd = pending_find(MGMT_OP_SET_LOCAL_NAME, hdev); if (!cmd) { memcpy(hdev->dev_name, name, sizeof(hdev->dev_name)); /* If this is a HCI command related to powering on the * HCI dev don't send any mgmt signals. */ - if (mgmt_pending_find(MGMT_OP_SET_POWERED, hdev)) + if (pending_find(MGMT_OP_SET_POWERED, hdev)) return; } - mgmt_event(MGMT_EV_LOCAL_NAME_CHANGED, hdev, &ev, sizeof(ev), - cmd ? cmd->sk : NULL); -} - -void mgmt_read_local_oob_data_complete(struct hci_dev *hdev, u8 *hash192, - u8 *rand192, u8 *hash256, u8 *rand256, - u8 status) -{ - struct pending_cmd *cmd; - - BT_DBG("%s status %u", hdev->name, status); - - cmd = mgmt_pending_find(MGMT_OP_READ_LOCAL_OOB_DATA, hdev); - if (!cmd) - return; - - if (status) { - cmd_status(cmd->sk, hdev->id, MGMT_OP_READ_LOCAL_OOB_DATA, - mgmt_status(status)); - } else { - struct mgmt_rp_read_local_oob_data rp; - size_t rp_size = sizeof(rp); - - memcpy(rp.hash192, hash192, sizeof(rp.hash192)); - memcpy(rp.rand192, rand192, sizeof(rp.rand192)); - - if (bredr_sc_enabled(hdev) && hash256 && rand256) { - memcpy(rp.hash256, hash256, sizeof(rp.hash256)); - memcpy(rp.rand256, rand256, sizeof(rp.rand256)); - } else { - rp_size -= sizeof(rp.hash256) + sizeof(rp.rand256); - } - - cmd_complete(cmd->sk, hdev->id, MGMT_OP_READ_LOCAL_OOB_DATA, 0, - &rp, rp_size); - } - - mgmt_pending_remove(cmd); + mgmt_generic_event(MGMT_EV_LOCAL_NAME_CHANGED, hdev, &ev, sizeof(ev), + cmd ? cmd->sk : NULL); } static inline bool has_uuid(u8 *uuid, u16 uuid_count, u8 (*uuids)[16]) @@ -7258,7 +8217,7 @@ static bool eir_has_uuids(u8 *eir, u16 eir_len, u16 uuid_count, u8 (*uuids)[16]) static void restart_le_scan(struct hci_dev *hdev) { /* If controller is not scanning we are done. */ - if (!test_bit(HCI_LE_SCAN, &hdev->dev_flags)) + if (!hci_dev_test_flag(hdev, HCI_LE_SCAN)) return; if (time_after(jiffies + DISCOV_LE_RESTART_DELAY, @@ -7270,14 +8229,58 @@ static void restart_le_scan(struct hci_dev *hdev) DISCOV_LE_RESTART_DELAY); } +static bool is_filter_match(struct hci_dev *hdev, s8 rssi, u8 *eir, + u16 eir_len, u8 *scan_rsp, u8 scan_rsp_len) +{ + /* If a RSSI threshold has been specified, and + * HCI_QUIRK_STRICT_DUPLICATE_FILTER is not set, then all results with + * a RSSI smaller than the RSSI threshold will be dropped. If the quirk + * is set, let it through for further processing, as we might need to + * restart the scan. + * + * For BR/EDR devices (pre 1.2) providing no RSSI during inquiry, + * the results are also dropped. + */ + if (hdev->discovery.rssi != HCI_RSSI_INVALID && + (rssi == HCI_RSSI_INVALID || + (rssi < hdev->discovery.rssi && + !test_bit(HCI_QUIRK_STRICT_DUPLICATE_FILTER, &hdev->quirks)))) + return false; + + if (hdev->discovery.uuid_count != 0) { + /* If a list of UUIDs is provided in filter, results with no + * matching UUID should be dropped. + */ + if (!eir_has_uuids(eir, eir_len, hdev->discovery.uuid_count, + hdev->discovery.uuids) && + !eir_has_uuids(scan_rsp, scan_rsp_len, + hdev->discovery.uuid_count, + hdev->discovery.uuids)) + return false; + } + + /* If duplicate filtering does not report RSSI changes, then restart + * scanning to ensure updated result with updated RSSI values. + */ + if (test_bit(HCI_QUIRK_STRICT_DUPLICATE_FILTER, &hdev->quirks)) { + restart_le_scan(hdev); + + /* Validate RSSI value against the RSSI threshold once more. */ + if (hdev->discovery.rssi != HCI_RSSI_INVALID && + rssi < hdev->discovery.rssi) + return false; + } + + return true; +} + void mgmt_device_found(struct hci_dev *hdev, bdaddr_t *bdaddr, u8 link_type, 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 mgmt_ev_device_found *ev = (void *)buf; size_t ev_size; - bool match; /* Don't send events for a non-kernel initiated discovery. With * LE one exception is if we have pend_le_reports > 0 in which @@ -7290,21 +8293,12 @@ void mgmt_device_found(struct hci_dev *hdev, bdaddr_t *bdaddr, u8 link_type, return; } - /* When using service discovery with a RSSI threshold, then check - * if such a RSSI threshold is specified. If a RSSI threshold has - * been specified, and HCI_QUIRK_STRICT_DUPLICATE_FILTER is not set, - * then all results with a RSSI smaller than the RSSI threshold will be - * dropped. If the quirk is set, let it through for further processing, - * as we might need to restart the scan. - * - * For BR/EDR devices (pre 1.2) providing no RSSI during inquiry, - * the results are also dropped. - */ - if (hdev->discovery.rssi != HCI_RSSI_INVALID && - (rssi == HCI_RSSI_INVALID || - (rssi < hdev->discovery.rssi && - !test_bit(HCI_QUIRK_STRICT_DUPLICATE_FILTER, &hdev->quirks)))) - return; + if (hdev->discovery.result_filtering) { + /* We are using service discovery */ + if (!is_filter_match(hdev, rssi, eir, eir_len, scan_rsp, + scan_rsp_len)) + return; + } /* Make sure that the buffer is big enough. The 5 extra bytes * are for the potential CoD field. @@ -7331,87 +8325,17 @@ void mgmt_device_found(struct hci_dev *hdev, bdaddr_t *bdaddr, u8 link_type, ev->rssi = rssi; ev->flags = cpu_to_le32(flags); - if (eir_len > 0) { - /* When using service discovery and a list of UUID is - * provided, results with no matching UUID should be - * dropped. In case there is a match the result is - * kept and checking possible scan response data - * will be skipped. - */ - if (hdev->discovery.uuid_count > 0) { - match = eir_has_uuids(eir, eir_len, - hdev->discovery.uuid_count, - hdev->discovery.uuids); - /* If duplicate filtering does not report RSSI changes, - * then restart scanning to ensure updated result with - * updated RSSI values. - */ - if (match && test_bit(HCI_QUIRK_STRICT_DUPLICATE_FILTER, - &hdev->quirks)) - restart_le_scan(hdev); - } else { - match = true; - } - - if (!match && !scan_rsp_len) - return; - + if (eir_len > 0) /* Copy EIR or advertising data into event */ memcpy(ev->eir, eir, eir_len); - } else { - /* When using service discovery and a list of UUID is - * provided, results with empty EIR or advertising data - * should be dropped since they do not match any UUID. - */ - if (hdev->discovery.uuid_count > 0 && !scan_rsp_len) - return; - - match = false; - } if (dev_class && !eir_has_data_type(ev->eir, eir_len, EIR_CLASS_OF_DEV)) eir_len = eir_append_data(ev->eir, eir_len, EIR_CLASS_OF_DEV, dev_class, 3); - if (scan_rsp_len > 0) { - /* When using service discovery and a list of UUID is - * provided, results with no matching UUID should be - * dropped if there is no previous match from the - * advertising data. - */ - if (hdev->discovery.uuid_count > 0) { - if (!match && !eir_has_uuids(scan_rsp, scan_rsp_len, - hdev->discovery.uuid_count, - hdev->discovery.uuids)) - return; - - /* If duplicate filtering does not report RSSI changes, - * then restart scanning to ensure updated result with - * updated RSSI values. - */ - if (test_bit(HCI_QUIRK_STRICT_DUPLICATE_FILTER, - &hdev->quirks)) - restart_le_scan(hdev); - } - + if (scan_rsp_len > 0) /* Append scan response data to event */ memcpy(ev->eir + eir_len, scan_rsp, scan_rsp_len); - } else { - /* When using service discovery and a list of UUID is - * provided, results with empty scan response and no - * previous matched advertising data should be dropped. - */ - if (hdev->discovery.uuid_count > 0 && !match) - return; - } - - /* Validate the reported RSSI value against the RSSI threshold once more - * incase HCI_QUIRK_STRICT_DUPLICATE_FILTER forced a restart of LE - * scanning. - */ - if (hdev->discovery.rssi != HCI_RSSI_INVALID && - rssi < hdev->discovery.rssi) - return; ev->eir_len = cpu_to_le16(eir_len + scan_rsp_len); ev_size = sizeof(*ev) + eir_len + scan_rsp_len; @@ -7464,10 +8388,28 @@ void mgmt_reenable_advertising(struct hci_dev *hdev) { struct hci_request req; - if (!test_bit(HCI_ADVERTISING, &hdev->dev_flags)) + if (!hci_dev_test_flag(hdev, HCI_ADVERTISING) && + !hci_dev_test_flag(hdev, HCI_ADVERTISING_INSTANCE)) return; hci_req_init(&req, hdev); enable_advertising(&req); hci_req_run(&req, adv_enable_complete); } + +static struct hci_mgmt_chan chan = { + .channel = HCI_CHANNEL_CONTROL, + .handler_count = ARRAY_SIZE(mgmt_handlers), + .handlers = mgmt_handlers, + .hdev_init = mgmt_init_hdev, +}; + +int mgmt_init(void) +{ + return hci_mgmt_chan_register(&chan); +} + +void mgmt_exit(void) +{ + hci_mgmt_chan_unregister(&chan); +} diff --git a/net/bluetooth/mgmt_util.c b/net/bluetooth/mgmt_util.c new file mode 100644 index 000000000000..8c30c7eb8bef --- /dev/null +++ b/net/bluetooth/mgmt_util.c @@ -0,0 +1,210 @@ +/* + BlueZ - Bluetooth protocol stack for Linux + + Copyright (C) 2015 Intel Corporation + + 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; + + THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS + OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, + FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT OF THIRD PARTY RIGHTS. + IN NO EVENT SHALL THE COPYRIGHT HOLDER(S) AND AUTHOR(S) BE LIABLE FOR ANY + CLAIM, OR ANY SPECIAL INDIRECT OR CONSEQUENTIAL DAMAGES, OR ANY DAMAGES + WHATSOEVER RESULTING FROM LOSS OF USE, DATA OR PROFITS, WHETHER IN AN + ACTION OF CONTRACT, NEGLIGENCE OR OTHER TORTIOUS ACTION, ARISING OUT OF + OR IN CONNECTION WITH THE USE OR PERFORMANCE OF THIS SOFTWARE. + + ALL LIABILITY, INCLUDING LIABILITY FOR INFRINGEMENT OF ANY PATENTS, + COPYRIGHTS, TRADEMARKS OR OTHER RIGHTS, RELATING TO USE OF THIS + SOFTWARE IS DISCLAIMED. +*/ + +#include <net/bluetooth/bluetooth.h> +#include <net/bluetooth/hci_core.h> +#include <net/bluetooth/mgmt.h> + +#include "mgmt_util.h" + +int mgmt_send_event(u16 event, struct hci_dev *hdev, unsigned short channel, + void *data, u16 data_len, int flag, 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_channel(channel, skb, flag, skip_sk); + kfree_skb(skb); + + return 0; +} + +int mgmt_cmd_status(struct sock *sk, u16 index, u16 cmd, u8 status) +{ + struct sk_buff *skb; + struct mgmt_hdr *hdr; + struct mgmt_ev_cmd_status *ev; + int err; + + BT_DBG("sock %p, index %u, cmd %u, status %u", sk, index, cmd, status); + + skb = alloc_skb(sizeof(*hdr) + sizeof(*ev), GFP_KERNEL); + if (!skb) + return -ENOMEM; + + hdr = (void *) skb_put(skb, sizeof(*hdr)); + + hdr->opcode = cpu_to_le16(MGMT_EV_CMD_STATUS); + hdr->index = cpu_to_le16(index); + hdr->len = cpu_to_le16(sizeof(*ev)); + + ev = (void *) skb_put(skb, sizeof(*ev)); + ev->status = status; + ev->opcode = cpu_to_le16(cmd); + + err = sock_queue_rcv_skb(sk, skb); + if (err < 0) + kfree_skb(skb); + + return err; +} + +int mgmt_cmd_complete(struct sock *sk, u16 index, u16 cmd, u8 status, + void *rp, size_t rp_len) +{ + struct sk_buff *skb; + struct mgmt_hdr *hdr; + struct mgmt_ev_cmd_complete *ev; + int err; + + BT_DBG("sock %p", sk); + + skb = alloc_skb(sizeof(*hdr) + sizeof(*ev) + rp_len, GFP_KERNEL); + if (!skb) + return -ENOMEM; + + hdr = (void *) skb_put(skb, sizeof(*hdr)); + + hdr->opcode = cpu_to_le16(MGMT_EV_CMD_COMPLETE); + hdr->index = cpu_to_le16(index); + hdr->len = cpu_to_le16(sizeof(*ev) + rp_len); + + ev = (void *) skb_put(skb, sizeof(*ev) + rp_len); + ev->opcode = cpu_to_le16(cmd); + ev->status = status; + + if (rp) + memcpy(ev->data, rp, rp_len); + + err = sock_queue_rcv_skb(sk, skb); + if (err < 0) + kfree_skb(skb); + + return err; +} + +struct mgmt_pending_cmd *mgmt_pending_find(unsigned short channel, u16 opcode, + struct hci_dev *hdev) +{ + struct mgmt_pending_cmd *cmd; + + list_for_each_entry(cmd, &hdev->mgmt_pending, list) { + if (hci_sock_get_channel(cmd->sk) != channel) + continue; + if (cmd->opcode == opcode) + return cmd; + } + + return NULL; +} + +struct mgmt_pending_cmd *mgmt_pending_find_data(unsigned short channel, + u16 opcode, + struct hci_dev *hdev, + const void *data) +{ + struct mgmt_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; +} + +void mgmt_pending_foreach(u16 opcode, struct hci_dev *hdev, + void (*cb)(struct mgmt_pending_cmd *cmd, void *data), + void *data) +{ + struct mgmt_pending_cmd *cmd, *tmp; + + list_for_each_entry_safe(cmd, tmp, &hdev->mgmt_pending, list) { + if (opcode > 0 && cmd->opcode != opcode) + continue; + + cb(cmd, data); + } +} + +struct mgmt_pending_cmd *mgmt_pending_add(struct sock *sk, u16 opcode, + struct hci_dev *hdev, + void *data, u16 len) +{ + struct mgmt_pending_cmd *cmd; + + cmd = kzalloc(sizeof(*cmd), GFP_KERNEL); + if (!cmd) + return NULL; + + cmd->opcode = opcode; + cmd->index = hdev->id; + + cmd->param = kmemdup(data, len, GFP_KERNEL); + if (!cmd->param) { + kfree(cmd); + return NULL; + } + + cmd->param_len = len; + + cmd->sk = sk; + sock_hold(sk); + + list_add(&cmd->list, &hdev->mgmt_pending); + + return cmd; +} + +void mgmt_pending_free(struct mgmt_pending_cmd *cmd) +{ + sock_put(cmd->sk); + kfree(cmd->param); + kfree(cmd); +} + +void mgmt_pending_remove(struct mgmt_pending_cmd *cmd) +{ + list_del(&cmd->list); + mgmt_pending_free(cmd); +} diff --git a/net/bluetooth/mgmt_util.h b/net/bluetooth/mgmt_util.h new file mode 100644 index 000000000000..6559f189213c --- /dev/null +++ b/net/bluetooth/mgmt_util.h @@ -0,0 +1,53 @@ +/* + BlueZ - Bluetooth protocol stack for Linux + Copyright (C) 2015 Intel Coropration + + 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; + + THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS + OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, + FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT OF THIRD PARTY RIGHTS. + IN NO EVENT SHALL THE COPYRIGHT HOLDER(S) AND AUTHOR(S) BE LIABLE FOR ANY + CLAIM, OR ANY SPECIAL INDIRECT OR CONSEQUENTIAL DAMAGES, OR ANY DAMAGES + WHATSOEVER RESULTING FROM LOSS OF USE, DATA OR PROFITS, WHETHER IN AN + ACTION OF CONTRACT, NEGLIGENCE OR OTHER TORTIOUS ACTION, ARISING OUT OF + OR IN CONNECTION WITH THE USE OR PERFORMANCE OF THIS SOFTWARE. + + ALL LIABILITY, INCLUDING LIABILITY FOR INFRINGEMENT OF ANY PATENTS, + COPYRIGHTS, TRADEMARKS OR OTHER RIGHTS, RELATING TO USE OF THIS + SOFTWARE IS DISCLAIMED. +*/ + +struct mgmt_pending_cmd { + struct list_head list; + u16 opcode; + int index; + void *param; + size_t param_len; + struct sock *sk; + void *user_data; + int (*cmd_complete)(struct mgmt_pending_cmd *cmd, u8 status); +}; + +int mgmt_send_event(u16 event, struct hci_dev *hdev, unsigned short channel, + void *data, u16 data_len, int flag, struct sock *skip_sk); +int mgmt_cmd_status(struct sock *sk, u16 index, u16 cmd, u8 status); +int mgmt_cmd_complete(struct sock *sk, u16 index, u16 cmd, u8 status, + void *rp, size_t rp_len); + +struct mgmt_pending_cmd *mgmt_pending_find(unsigned short channel, u16 opcode, + struct hci_dev *hdev); +struct mgmt_pending_cmd *mgmt_pending_find_data(unsigned short channel, + u16 opcode, + struct hci_dev *hdev, + const void *data); +void mgmt_pending_foreach(u16 opcode, struct hci_dev *hdev, + void (*cb)(struct mgmt_pending_cmd *cmd, void *data), + void *data); +struct mgmt_pending_cmd *mgmt_pending_add(struct sock *sk, u16 opcode, + struct hci_dev *hdev, + void *data, u16 len); +void mgmt_pending_free(struct mgmt_pending_cmd *cmd); +void mgmt_pending_remove(struct mgmt_pending_cmd *cmd); diff --git a/net/bluetooth/rfcomm/sock.c b/net/bluetooth/rfcomm/sock.c index 3c6d2c8ac1a4..825e8fb5114b 100644 --- a/net/bluetooth/rfcomm/sock.c +++ b/net/bluetooth/rfcomm/sock.c @@ -549,8 +549,8 @@ static int rfcomm_sock_getname(struct socket *sock, struct sockaddr *addr, int * return 0; } -static int rfcomm_sock_sendmsg(struct kiocb *iocb, struct socket *sock, - struct msghdr *msg, size_t len) +static int rfcomm_sock_sendmsg(struct socket *sock, struct msghdr *msg, + size_t len) { struct sock *sk = sock->sk; struct rfcomm_dlc *d = rfcomm_pi(sk)->dlc; @@ -615,8 +615,8 @@ done: return sent; } -static int rfcomm_sock_recvmsg(struct kiocb *iocb, struct socket *sock, - struct msghdr *msg, size_t size, int flags) +static int rfcomm_sock_recvmsg(struct socket *sock, struct msghdr *msg, + size_t size, int flags) { struct sock *sk = sock->sk; struct rfcomm_dlc *d = rfcomm_pi(sk)->dlc; @@ -627,7 +627,7 @@ static int rfcomm_sock_recvmsg(struct kiocb *iocb, struct socket *sock, return 0; } - len = bt_sock_stream_recvmsg(iocb, sock, msg, size, flags); + len = bt_sock_stream_recvmsg(sock, msg, size, flags); lock_sock(sk); if (!(flags & MSG_PEEK) && len > 0) diff --git a/net/bluetooth/sco.c b/net/bluetooth/sco.c index 76321b546e84..4322c833e748 100644 --- a/net/bluetooth/sco.c +++ b/net/bluetooth/sco.c @@ -688,8 +688,8 @@ static int sco_sock_getname(struct socket *sock, struct sockaddr *addr, int *len return 0; } -static int sco_sock_sendmsg(struct kiocb *iocb, struct socket *sock, - struct msghdr *msg, size_t len) +static int sco_sock_sendmsg(struct socket *sock, struct msghdr *msg, + size_t len) { struct sock *sk = sock->sk; int err; @@ -758,8 +758,8 @@ static void sco_conn_defer_accept(struct hci_conn *conn, u16 setting) } } -static int sco_sock_recvmsg(struct kiocb *iocb, struct socket *sock, - struct msghdr *msg, size_t len, int flags) +static int sco_sock_recvmsg(struct socket *sock, struct msghdr *msg, + size_t len, int flags) { struct sock *sk = sock->sk; struct sco_pinfo *pi = sco_pi(sk); @@ -777,7 +777,7 @@ static int sco_sock_recvmsg(struct kiocb *iocb, struct socket *sock, release_sock(sk); - return bt_sock_recvmsg(iocb, sock, msg, len, flags); + return bt_sock_recvmsg(sock, msg, len, flags); } static int sco_sock_setsockopt(struct socket *sock, int level, int optname, char __user *optval, unsigned int optlen) @@ -1083,9 +1083,13 @@ int sco_connect_ind(struct hci_dev *hdev, bdaddr_t *bdaddr, __u8 *flags) return lm; } -void sco_connect_cfm(struct hci_conn *hcon, __u8 status) +static void sco_connect_cfm(struct hci_conn *hcon, __u8 status) { + if (hcon->type != SCO_LINK && hcon->type != ESCO_LINK) + return; + BT_DBG("hcon %p bdaddr %pMR status %d", hcon, &hcon->dst, status); + if (!status) { struct sco_conn *conn; @@ -1096,8 +1100,11 @@ void sco_connect_cfm(struct hci_conn *hcon, __u8 status) sco_conn_del(hcon, bt_to_errno(status)); } -void sco_disconn_cfm(struct hci_conn *hcon, __u8 reason) +static void sco_disconn_cfm(struct hci_conn *hcon, __u8 reason) { + if (hcon->type != SCO_LINK && hcon->type != ESCO_LINK) + return; + BT_DBG("hcon %p reason %d", hcon, reason); sco_conn_del(hcon, bt_to_errno(reason)); @@ -1122,6 +1129,12 @@ drop: return 0; } +static struct hci_cb sco_cb = { + .name = "SCO", + .connect_cfm = sco_connect_cfm, + .disconn_cfm = sco_disconn_cfm, +}; + static int sco_debugfs_show(struct seq_file *f, void *p) { struct sock *sk; @@ -1203,6 +1216,8 @@ int __init sco_init(void) BT_INFO("SCO socket layer initialized"); + hci_register_cb(&sco_cb); + if (IS_ERR_OR_NULL(bt_debugfs)) return 0; @@ -1216,12 +1231,14 @@ error: return err; } -void __exit sco_exit(void) +void sco_exit(void) { bt_procfs_cleanup(&init_net, "sco"); debugfs_remove(sco_debugfs); + hci_unregister_cb(&sco_cb); + bt_sock_unregister(BTPROTO_SCO); proto_unregister(&sco_proto); diff --git a/net/bluetooth/selftest.c b/net/bluetooth/selftest.c index 378f4064952c..dc688f13e496 100644 --- a/net/bluetooth/selftest.c +++ b/net/bluetooth/selftest.c @@ -21,6 +21,8 @@ SOFTWARE IS DISCLAIMED. */ +#include <linux/debugfs.h> + #include <net/bluetooth/bluetooth.h> #include <net/bluetooth/hci_core.h> @@ -154,6 +156,21 @@ static int __init test_ecdh_sample(const u8 priv_a[32], const u8 priv_b[32], return 0; } +static char test_ecdh_buffer[32]; + +static ssize_t test_ecdh_read(struct file *file, char __user *user_buf, + size_t count, loff_t *ppos) +{ + return simple_read_from_buffer(user_buf, count, ppos, test_ecdh_buffer, + strlen(test_ecdh_buffer)); +} + +static const struct file_operations test_ecdh_fops = { + .open = simple_open, + .read = test_ecdh_read, + .llseek = default_llseek, +}; + static int __init test_ecdh(void) { ktime_t calltime, delta, rettime; @@ -165,19 +182,19 @@ static int __init test_ecdh(void) err = test_ecdh_sample(priv_a_1, priv_b_1, pub_a_1, pub_b_1, dhkey_1); if (err) { BT_ERR("ECDH sample 1 failed"); - return err; + goto done; } err = test_ecdh_sample(priv_a_2, priv_b_2, pub_a_2, pub_b_2, dhkey_2); if (err) { BT_ERR("ECDH sample 2 failed"); - return err; + goto done; } err = test_ecdh_sample(priv_a_3, priv_a_3, pub_a_3, pub_a_3, dhkey_3); if (err) { BT_ERR("ECDH sample 3 failed"); - return err; + goto done; } rettime = ktime_get(); @@ -186,7 +203,17 @@ static int __init test_ecdh(void) BT_INFO("ECDH test passed in %llu usecs", duration); - return 0; +done: + if (!err) + snprintf(test_ecdh_buffer, sizeof(test_ecdh_buffer), + "PASS (%llu usecs)\n", duration); + else + snprintf(test_ecdh_buffer, sizeof(test_ecdh_buffer), "FAIL\n"); + + debugfs_create_file("selftest_ecdh", 0444, bt_debugfs, NULL, + &test_ecdh_fops); + + return err; } #else diff --git a/net/bluetooth/smp.c b/net/bluetooth/smp.c index c09a821f381d..1ab3dc9c8f99 100644 --- a/net/bluetooth/smp.c +++ b/net/bluetooth/smp.c @@ -52,7 +52,7 @@ #define SMP_TIMEOUT msecs_to_jiffies(30000) -#define AUTH_REQ_MASK(dev) (test_bit(HCI_SC_ENABLED, &(dev)->dev_flags) ? \ +#define AUTH_REQ_MASK(dev) (hci_dev_test_flag(dev, HCI_SC_ENABLED) ? \ 0x1f : 0x07) #define KEY_DIST_MASK 0x07 @@ -70,7 +70,19 @@ enum { SMP_FLAG_DEBUG_KEY, SMP_FLAG_WAIT_USER, SMP_FLAG_DHKEY_PENDING, - SMP_FLAG_OOB, + SMP_FLAG_REMOTE_OOB, + SMP_FLAG_LOCAL_OOB, +}; + +struct smp_dev { + /* Secure Connections OOB data */ + u8 local_pk[64]; + u8 local_sk[32]; + u8 local_rand[16]; + bool debug_key; + + struct crypto_blkcipher *tfm_aes; + struct crypto_hash *tfm_cmac; }; struct smp_chan { @@ -84,7 +96,8 @@ struct smp_chan { u8 rrnd[16]; /* SMP Pairing Random (remote) */ u8 pcnf[16]; /* SMP Pairing Confirm */ u8 tk[16]; /* SMP Temporary Key */ - u8 rr[16]; + u8 rr[16]; /* Remote OOB ra/rb value */ + u8 lr[16]; /* Local OOB ra/rb value */ u8 enc_key_size; u8 remote_key_dist; bdaddr_t id_addr; @@ -478,18 +491,18 @@ bool smp_irk_matches(struct hci_dev *hdev, const u8 irk[16], const bdaddr_t *bdaddr) { struct l2cap_chan *chan = hdev->smp_data; - struct crypto_blkcipher *tfm; + struct smp_dev *smp; u8 hash[3]; int err; if (!chan || !chan->data) return false; - tfm = chan->data; + smp = chan->data; BT_DBG("RPA %pMR IRK %*phN", bdaddr, 16, irk); - err = smp_ah(tfm, irk, &bdaddr->b[3], hash); + err = smp_ah(smp->tfm_aes, irk, &bdaddr->b[3], hash); if (err) return false; @@ -499,20 +512,20 @@ bool smp_irk_matches(struct hci_dev *hdev, const u8 irk[16], int smp_generate_rpa(struct hci_dev *hdev, const u8 irk[16], bdaddr_t *rpa) { struct l2cap_chan *chan = hdev->smp_data; - struct crypto_blkcipher *tfm; + struct smp_dev *smp; int err; if (!chan || !chan->data) return -EOPNOTSUPP; - tfm = chan->data; + smp = chan->data; get_random_bytes(&rpa->b[3], 3); rpa->b[5] &= 0x3f; /* Clear two most significant bits */ rpa->b[5] |= 0x40; /* Set second most significant bit */ - err = smp_ah(tfm, irk, &rpa->b[3], rpa->b); + err = smp_ah(smp->tfm_aes, irk, &rpa->b[3], rpa->b); if (err < 0) return err; @@ -521,6 +534,53 @@ int smp_generate_rpa(struct hci_dev *hdev, const u8 irk[16], bdaddr_t *rpa) return 0; } +int smp_generate_oob(struct hci_dev *hdev, u8 hash[16], u8 rand[16]) +{ + struct l2cap_chan *chan = hdev->smp_data; + struct smp_dev *smp; + int err; + + if (!chan || !chan->data) + return -EOPNOTSUPP; + + smp = chan->data; + + if (hci_dev_test_flag(hdev, HCI_USE_DEBUG_KEYS)) { + BT_DBG("Using debug keys"); + memcpy(smp->local_pk, debug_pk, 64); + memcpy(smp->local_sk, debug_sk, 32); + smp->debug_key = true; + } else { + while (true) { + /* Generate local key pair for Secure Connections */ + if (!ecc_make_key(smp->local_pk, smp->local_sk)) + return -EIO; + + /* This is unlikely, but we need to check that + * we didn't accidentially generate a debug key. + */ + if (memcmp(smp->local_sk, debug_sk, 32)) + break; + } + smp->debug_key = false; + } + + SMP_DBG("OOB Public Key X: %32phN", smp->local_pk); + SMP_DBG("OOB Public Key Y: %32phN", smp->local_pk + 32); + SMP_DBG("OOB Private Key: %32phN", smp->local_sk); + + get_random_bytes(smp->local_rand, 16); + + err = smp_f4(smp->tfm_cmac, smp->local_pk, smp->local_pk, + smp->local_rand, 0, hash); + if (err < 0) + return err; + + memcpy(rand, smp->local_rand, 16); + + return 0; +} + static void smp_send_cmd(struct l2cap_conn *conn, u8 code, u16 len, void *data) { struct l2cap_chan *chan = conn->smp; @@ -589,7 +649,7 @@ static void build_pairing_cmd(struct l2cap_conn *conn, struct hci_dev *hdev = hcon->hdev; u8 local_dist = 0, remote_dist = 0, oob_flag = SMP_OOB_NOT_PRESENT; - if (test_bit(HCI_BONDABLE, &conn->hcon->hdev->dev_flags)) { + if (hci_dev_test_flag(hdev, HCI_BONDABLE)) { local_dist = SMP_DIST_ENC_KEY | SMP_DIST_SIGN; remote_dist = SMP_DIST_ENC_KEY | SMP_DIST_SIGN; authreq |= SMP_AUTH_BONDING; @@ -597,18 +657,18 @@ static void build_pairing_cmd(struct l2cap_conn *conn, authreq &= ~SMP_AUTH_BONDING; } - if (test_bit(HCI_RPA_RESOLVING, &hdev->dev_flags)) + if (hci_dev_test_flag(hdev, HCI_RPA_RESOLVING)) remote_dist |= SMP_DIST_ID_KEY; - if (test_bit(HCI_PRIVACY, &hdev->dev_flags)) + if (hci_dev_test_flag(hdev, HCI_PRIVACY)) local_dist |= SMP_DIST_ID_KEY; - if (test_bit(HCI_SC_ENABLED, &hdev->dev_flags) && + if (hci_dev_test_flag(hdev, HCI_SC_ENABLED) && (authreq & SMP_AUTH_SC)) { struct oob_data *oob_data; u8 bdaddr_type; - if (test_bit(HCI_SSP_ENABLED, &hdev->dev_flags)) { + if (hci_dev_test_flag(hdev, HCI_SSP_ENABLED)) { local_dist |= SMP_DIST_LINK_KEY; remote_dist |= SMP_DIST_LINK_KEY; } @@ -621,10 +681,12 @@ static void build_pairing_cmd(struct l2cap_conn *conn, oob_data = hci_find_remote_oob_data(hdev, &hcon->dst, bdaddr_type); if (oob_data && oob_data->present) { - set_bit(SMP_FLAG_OOB, &smp->flags); + set_bit(SMP_FLAG_REMOTE_OOB, &smp->flags); oob_flag = SMP_OOB_PRESENT; memcpy(smp->rr, oob_data->rand256, 16); memcpy(smp->pcnf, oob_data->hash256, 16); + SMP_DBG("OOB Remote Confirmation: %16phN", smp->pcnf); + SMP_DBG("OOB Remote Random: %16phN", smp->rr); } } else { @@ -681,9 +743,9 @@ static void smp_chan_destroy(struct l2cap_conn *conn) complete = test_bit(SMP_FLAG_COMPLETE, &smp->flags); mgmt_smp_complete(hcon, complete); - kfree(smp->csrk); - kfree(smp->slave_csrk); - kfree(smp->link_key); + kzfree(smp->csrk); + kzfree(smp->slave_csrk); + kzfree(smp->link_key); crypto_free_blkcipher(smp->tfm_aes); crypto_free_hash(smp->tfm_cmac); @@ -692,7 +754,7 @@ static void smp_chan_destroy(struct l2cap_conn *conn) * support hasn't been explicitly enabled. */ if (smp->ltk && smp->ltk->type == SMP_LTK_P256_DEBUG && - !test_bit(HCI_KEEP_DEBUG_KEYS, &hcon->hdev->dev_flags)) { + !hci_dev_test_flag(hcon->hdev, HCI_KEEP_DEBUG_KEYS)) { list_del_rcu(&smp->ltk->list); kfree_rcu(smp->ltk, rcu); smp->ltk = NULL; @@ -717,7 +779,7 @@ static void smp_chan_destroy(struct l2cap_conn *conn) } chan->data = NULL; - kfree(smp); + kzfree(smp); hci_conn_drop(hcon); } @@ -818,6 +880,12 @@ static int tk_request(struct l2cap_conn *conn, u8 remote_oob, u8 auth, return 0; } + /* If this function is used for SC -> legacy fallback we + * can only recover the just-works case. + */ + if (test_bit(SMP_FLAG_SC, &smp->flags)) + return -EINVAL; + /* Not Just Works/Confirm results in MITM Authentication */ if (smp->method != JUST_CFM) { set_bit(SMP_FLAG_MITM_AUTH, &smp->flags); @@ -1052,7 +1120,7 @@ static void smp_notify_keys(struct l2cap_conn *conn) /* Don't keep debug keys around if the relevant * flag is not set. */ - if (!test_bit(HCI_KEEP_DEBUG_KEYS, &hdev->dev_flags) && + if (!hci_dev_test_flag(hdev, HCI_KEEP_DEBUG_KEYS) && key->type == HCI_LK_DEBUG_COMBINATION) { list_del_rcu(&key->list); kfree_rcu(key, rcu); @@ -1097,13 +1165,13 @@ static void sc_generate_link_key(struct smp_chan *smp) return; if (smp_h6(smp->tfm_cmac, smp->tk, tmp1, smp->link_key)) { - kfree(smp->link_key); + kzfree(smp->link_key); smp->link_key = NULL; return; } if (smp_h6(smp->tfm_cmac, smp->link_key, lebr, smp->link_key)) { - kfree(smp->link_key); + kzfree(smp->link_key); smp->link_key = NULL; return; } @@ -1252,7 +1320,10 @@ static void smp_distribute_keys(struct smp_chan *smp) csrk = kzalloc(sizeof(*csrk), GFP_KERNEL); if (csrk) { - csrk->master = 0x00; + if (hcon->sec_level > BT_SECURITY_MEDIUM) + csrk->type = MGMT_CSRK_LOCAL_AUTHENTICATED; + else + csrk->type = MGMT_CSRK_LOCAL_UNAUTHENTICATED; memcpy(csrk->val, sign.csrk, sizeof(csrk->val)); } smp->slave_csrk = csrk; @@ -1297,7 +1368,7 @@ static struct smp_chan *smp_chan_create(struct l2cap_conn *conn) 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); + kzfree(smp); return NULL; } @@ -1305,7 +1376,7 @@ static struct smp_chan *smp_chan_create(struct l2cap_conn *conn) if (IS_ERR(smp->tfm_cmac)) { BT_ERR("Unable to create CMAC crypto context"); crypto_free_blkcipher(smp->tfm_aes); - kfree(smp); + kzfree(smp); return NULL; } @@ -1601,15 +1672,15 @@ static void build_bredr_pairing_cmd(struct smp_chan *smp, struct hci_dev *hdev = conn->hcon->hdev; u8 local_dist = 0, remote_dist = 0; - if (test_bit(HCI_BONDABLE, &hdev->dev_flags)) { + if (hci_dev_test_flag(hdev, HCI_BONDABLE)) { local_dist = SMP_DIST_ENC_KEY | SMP_DIST_SIGN; remote_dist = SMP_DIST_ENC_KEY | SMP_DIST_SIGN; } - if (test_bit(HCI_RPA_RESOLVING, &hdev->dev_flags)) + if (hci_dev_test_flag(hdev, HCI_RPA_RESOLVING)) remote_dist |= SMP_DIST_ID_KEY; - if (test_bit(HCI_PRIVACY, &hdev->dev_flags)) + if (hci_dev_test_flag(hdev, HCI_PRIVACY)) local_dist |= SMP_DIST_ID_KEY; if (!rsp) { @@ -1661,22 +1732,29 @@ static u8 smp_cmd_pairing_req(struct l2cap_conn *conn, struct sk_buff *skb) /* We didn't start the pairing, so match remote */ auth = req->auth_req & AUTH_REQ_MASK(hdev); - if (!test_bit(HCI_BONDABLE, &hdev->dev_flags) && + if (!hci_dev_test_flag(hdev, HCI_BONDABLE) && (auth & SMP_AUTH_BONDING)) return SMP_PAIRING_NOTSUPP; - if (test_bit(HCI_SC_ONLY, &hdev->dev_flags) && !(auth & SMP_AUTH_SC)) + if (hci_dev_test_flag(hdev, HCI_SC_ONLY) && !(auth & SMP_AUTH_SC)) return SMP_AUTH_REQUIREMENTS; smp->preq[0] = SMP_CMD_PAIRING_REQ; memcpy(&smp->preq[1], req, sizeof(*req)); skb_pull(skb, sizeof(*req)); + /* If the remote side's OOB flag is set it means it has + * successfully received our local OOB data - therefore set the + * flag to indicate that local OOB is in use. + */ + if (req->oob_flag == SMP_OOB_PRESENT) + set_bit(SMP_FLAG_LOCAL_OOB, &smp->flags); + /* SMP over BR/EDR requires special treatment */ if (conn->hcon->type == ACL_LINK) { /* We must have a BR/EDR SC link */ if (!test_bit(HCI_CONN_AES_CCM, &conn->hcon->flags) && - !test_bit(HCI_FORCE_BREDR_SMP, &hdev->dbg_flags)) + !hci_dev_test_flag(hdev, HCI_FORCE_BREDR_SMP)) return SMP_CROSS_TRANSP_NOT_ALLOWED; set_bit(SMP_FLAG_SC, &smp->flags); @@ -1734,14 +1812,19 @@ static u8 smp_cmd_pairing_req(struct l2cap_conn *conn, struct sk_buff *skb) clear_bit(SMP_FLAG_INITIATOR, &smp->flags); + /* Strictly speaking we shouldn't allow Pairing Confirm for the + * SC case, however some implementations incorrectly copy RFU auth + * req bits from our security request, which may create a false + * positive SC enablement. + */ + SMP_ALLOW_CMD(smp, SMP_CMD_PAIRING_CONFIRM); + if (test_bit(SMP_FLAG_SC, &smp->flags)) { SMP_ALLOW_CMD(smp, SMP_CMD_PUBLIC_KEY); /* Clear bits which are generated but not distributed */ smp->remote_key_dist &= ~SMP_SC_NO_DIST; /* Wait for Public Key from Initiating Device */ return 0; - } else { - SMP_ALLOW_CMD(smp, SMP_CMD_PAIRING_CONFIRM); } /* Request setup of TK */ @@ -1758,7 +1841,26 @@ static u8 sc_send_public_key(struct smp_chan *smp) BT_DBG(""); - if (test_bit(HCI_USE_DEBUG_KEYS, &hdev->dev_flags)) { + if (test_bit(SMP_FLAG_LOCAL_OOB, &smp->flags)) { + struct l2cap_chan *chan = hdev->smp_data; + struct smp_dev *smp_dev; + + if (!chan || !chan->data) + return SMP_UNSPECIFIED; + + smp_dev = chan->data; + + memcpy(smp->local_pk, smp_dev->local_pk, 64); + memcpy(smp->local_sk, smp_dev->local_sk, 32); + memcpy(smp->lr, smp_dev->local_rand, 16); + + if (smp_dev->debug_key) + set_bit(SMP_FLAG_DEBUG_KEY, &smp->flags); + + goto done; + } + + if (hci_dev_test_flag(hdev, HCI_USE_DEBUG_KEYS)) { BT_DBG("Using debug keys"); memcpy(smp->local_pk, debug_pk, 64); memcpy(smp->local_sk, debug_sk, 32); @@ -1777,8 +1879,9 @@ static u8 sc_send_public_key(struct smp_chan *smp) } } +done: SMP_DBG("Local Public Key X: %32phN", smp->local_pk); - SMP_DBG("Local Public Key Y: %32phN", &smp->local_pk[32]); + SMP_DBG("Local Public Key Y: %32phN", smp->local_pk + 32); SMP_DBG("Local Private Key: %32phN", smp->local_sk); smp_send_cmd(smp->conn, SMP_CMD_PUBLIC_KEY, 64, smp->local_pk); @@ -1813,9 +1916,16 @@ static u8 smp_cmd_pairing_rsp(struct l2cap_conn *conn, struct sk_buff *skb) auth = rsp->auth_req & AUTH_REQ_MASK(hdev); - if (test_bit(HCI_SC_ONLY, &hdev->dev_flags) && !(auth & SMP_AUTH_SC)) + if (hci_dev_test_flag(hdev, HCI_SC_ONLY) && !(auth & SMP_AUTH_SC)) return SMP_AUTH_REQUIREMENTS; + /* If the remote side's OOB flag is set it means it has + * successfully received our local OOB data - therefore set the + * flag to indicate that local OOB is in use. + */ + if (rsp->oob_flag == SMP_OOB_PRESENT) + set_bit(SMP_FLAG_LOCAL_OOB, &smp->flags); + smp->prsp[0] = SMP_CMD_PAIRING_RSP; memcpy(&smp->prsp[1], rsp, sizeof(*rsp)); @@ -1882,10 +1992,6 @@ static u8 sc_check_confirm(struct smp_chan *smp) BT_DBG(""); - /* Public Key exchange must happen before any other steps */ - if (!test_bit(SMP_FLAG_REMOTE_PK, &smp->flags)) - return SMP_UNSPECIFIED; - if (smp->method == REQ_PASSKEY || smp->method == DSP_PASSKEY) return sc_passkey_round(smp, SMP_CMD_PAIRING_CONFIRM); @@ -1898,6 +2004,47 @@ static u8 sc_check_confirm(struct smp_chan *smp) return 0; } +/* Work-around for some implementations that incorrectly copy RFU bits + * from our security request and thereby create the impression that + * we're doing SC when in fact the remote doesn't support it. + */ +static int fixup_sc_false_positive(struct smp_chan *smp) +{ + struct l2cap_conn *conn = smp->conn; + struct hci_conn *hcon = conn->hcon; + struct hci_dev *hdev = hcon->hdev; + struct smp_cmd_pairing *req, *rsp; + u8 auth; + + /* The issue is only observed when we're in slave role */ + if (hcon->out) + return SMP_UNSPECIFIED; + + if (hci_dev_test_flag(hdev, HCI_SC_ONLY)) { + BT_ERR("Refusing SMP SC -> legacy fallback in SC-only mode"); + return SMP_UNSPECIFIED; + } + + BT_ERR("Trying to fall back to legacy SMP"); + + req = (void *) &smp->preq[1]; + rsp = (void *) &smp->prsp[1]; + + /* Rebuild key dist flags which may have been cleared for SC */ + smp->remote_key_dist = (req->init_key_dist & rsp->resp_key_dist); + + auth = req->auth_req & AUTH_REQ_MASK(hdev); + + if (tk_request(conn, 0, auth, rsp->io_capability, req->io_capability)) { + BT_ERR("Failed to fall back to legacy SMP"); + return SMP_UNSPECIFIED; + } + + clear_bit(SMP_FLAG_SC, &smp->flags); + + return 0; +} + static u8 smp_cmd_pairing_confirm(struct l2cap_conn *conn, struct sk_buff *skb) { struct l2cap_chan *chan = conn->smp; @@ -1911,8 +2058,19 @@ static u8 smp_cmd_pairing_confirm(struct l2cap_conn *conn, struct sk_buff *skb) memcpy(smp->pcnf, skb->data, sizeof(smp->pcnf)); skb_pull(skb, sizeof(smp->pcnf)); - if (test_bit(SMP_FLAG_SC, &smp->flags)) - return sc_check_confirm(smp); + if (test_bit(SMP_FLAG_SC, &smp->flags)) { + int ret; + + /* Public Key exchange must happen before any other steps */ + if (test_bit(SMP_FLAG_REMOTE_PK, &smp->flags)) + return sc_check_confirm(smp); + + BT_ERR("Unexpected SMP Pairing Confirm"); + + ret = fixup_sc_false_positive(smp); + if (ret) + return ret; + } if (conn->hcon->out) { smp_send_cmd(conn, SMP_CMD_PAIRING_RANDOM, sizeof(smp->prnd), @@ -1923,8 +2081,8 @@ static u8 smp_cmd_pairing_confirm(struct l2cap_conn *conn, struct sk_buff *skb) if (test_bit(SMP_FLAG_TK_VALID, &smp->flags)) return smp_confirm(smp); - else - set_bit(SMP_FLAG_CFM_PENDING, &smp->flags); + + set_bit(SMP_FLAG_CFM_PENDING, &smp->flags); return 0; } @@ -2083,7 +2241,7 @@ static u8 smp_cmd_security_req(struct l2cap_conn *conn, struct sk_buff *skb) auth = rp->auth_req & AUTH_REQ_MASK(hdev); - if (test_bit(HCI_SC_ONLY, &hdev->dev_flags) && !(auth & SMP_AUTH_SC)) + if (hci_dev_test_flag(hdev, HCI_SC_ONLY) && !(auth & SMP_AUTH_SC)) return SMP_AUTH_REQUIREMENTS; if (hcon->io_capability == HCI_IO_NO_INPUT_OUTPUT) @@ -2104,7 +2262,7 @@ static u8 smp_cmd_security_req(struct l2cap_conn *conn, struct sk_buff *skb) if (!smp) return SMP_UNSPECIFIED; - if (!test_bit(HCI_BONDABLE, &hcon->hdev->dev_flags) && + if (!hci_dev_test_flag(hdev, HCI_BONDABLE) && (auth & SMP_AUTH_BONDING)) return SMP_PAIRING_NOTSUPP; @@ -2138,7 +2296,7 @@ int smp_conn_security(struct hci_conn *hcon, __u8 sec_level) chan = conn->smp; - if (!test_bit(HCI_LE_ENABLED, &hcon->hdev->dev_flags)) + if (!hci_dev_test_flag(hcon->hdev, HCI_LE_ENABLED)) return 1; if (smp_sufficient_security(hcon, sec_level, SMP_USE_LTK)) @@ -2167,7 +2325,7 @@ int smp_conn_security(struct hci_conn *hcon, __u8 sec_level) authreq = seclevel_to_authreq(sec_level); - if (test_bit(HCI_SC_ENABLED, &hcon->hdev->dev_flags)) + if (hci_dev_test_flag(hcon->hdev, HCI_SC_ENABLED)) authreq |= SMP_AUTH_SC; /* Require MITM if IO Capability allows or the security level @@ -2352,7 +2510,10 @@ static int smp_cmd_sign_info(struct l2cap_conn *conn, struct sk_buff *skb) csrk = kzalloc(sizeof(*csrk), GFP_KERNEL); if (csrk) { - csrk->master = 0x01; + if (conn->hcon->sec_level > BT_SECURITY_MEDIUM) + csrk->type = MGMT_CSRK_REMOTE_AUTHENTICATED; + else + csrk->type = MGMT_CSRK_REMOTE_UNAUTHENTICATED; memcpy(csrk->val, rp->csrk, sizeof(csrk->val)); } smp->csrk = csrk; @@ -2368,7 +2529,8 @@ static u8 sc_select_method(struct smp_chan *smp) struct smp_cmd_pairing *local, *remote; u8 local_mitm, remote_mitm, local_io, remote_io, method; - if (test_bit(SMP_FLAG_OOB, &smp->flags)) + if (test_bit(SMP_FLAG_REMOTE_OOB, &smp->flags) || + test_bit(SMP_FLAG_LOCAL_OOB, &smp->flags)) return REQ_OOB; /* The preq/prsp contain the raw Pairing Request/Response PDUs @@ -2422,6 +2584,16 @@ static int smp_cmd_public_key(struct l2cap_conn *conn, struct sk_buff *skb) memcpy(smp->remote_pk, key, 64); + if (test_bit(SMP_FLAG_REMOTE_OOB, &smp->flags)) { + err = smp_f4(smp->tfm_cmac, smp->remote_pk, smp->remote_pk, + smp->rr, 0, cfm.confirm_val); + if (err) + return SMP_UNSPECIFIED; + + if (memcmp(cfm.confirm_val, smp->pcnf, 16)) + return SMP_CONFIRM_FAILED; + } + /* Non-initiating device sends its public key after receiving * the key from the initiating device. */ @@ -2432,7 +2604,7 @@ static int smp_cmd_public_key(struct l2cap_conn *conn, struct sk_buff *skb) } SMP_DBG("Remote Public Key X: %32phN", smp->remote_pk); - SMP_DBG("Remote Public Key Y: %32phN", &smp->remote_pk[32]); + SMP_DBG("Remote Public Key Y: %32phN", smp->remote_pk + 32); if (!ecdh_shared_secret(smp->remote_pk, smp->local_sk, smp->dhkey)) return SMP_UNSPECIFIED; @@ -2470,14 +2642,6 @@ static int smp_cmd_public_key(struct l2cap_conn *conn, struct sk_buff *skb) } if (smp->method == REQ_OOB) { - err = smp_f4(smp->tfm_cmac, smp->remote_pk, smp->remote_pk, - smp->rr, 0, cfm.confirm_val); - if (err) - return SMP_UNSPECIFIED; - - if (memcmp(cfm.confirm_val, smp->pcnf, 16)) - return SMP_CONFIRM_FAILED; - if (hcon->out) smp_send_cmd(conn, SMP_CMD_PAIRING_RANDOM, sizeof(smp->prnd), smp->prnd); @@ -2550,6 +2714,8 @@ static int smp_cmd_dhkey_check(struct l2cap_conn *conn, struct sk_buff *skb) if (smp->method == REQ_PASSKEY || smp->method == DSP_PASSKEY) put_unaligned_le32(hcon->passkey_notify, r); + else if (smp->method == REQ_OOB) + memcpy(r, smp->lr, 16); err = smp_f6(smp->tfm_cmac, smp->mackey, smp->rrnd, smp->prnd, r, io_cap, remote_addr, local_addr, e); @@ -2600,7 +2766,7 @@ static int smp_sig_channel(struct l2cap_chan *chan, struct sk_buff *skb) if (skb->len < 1) return -EILSEQ; - if (!test_bit(HCI_LE_ENABLED, &hcon->hdev->dev_flags)) { + if (!hci_dev_test_flag(hcon->hdev, HCI_LE_ENABLED)) { reason = SMP_PAIRING_NOTSUPP; goto done; } @@ -2738,16 +2904,16 @@ static void bredr_pairing(struct l2cap_chan *chan) return; /* Secure Connections support must be enabled */ - if (!test_bit(HCI_SC_ENABLED, &hdev->dev_flags)) + if (!hci_dev_test_flag(hdev, HCI_SC_ENABLED)) return; /* BR/EDR must use Secure Connections for SMP */ if (!test_bit(HCI_CONN_AES_CCM, &hcon->flags) && - !test_bit(HCI_FORCE_BREDR_SMP, &hdev->dbg_flags)) + !hci_dev_test_flag(hdev, HCI_FORCE_BREDR_SMP)) return; /* If our LE support is not enabled don't do anything */ - if (!test_bit(HCI_LE_ENABLED, &hdev->dev_flags)) + if (!hci_dev_test_flag(hdev, HCI_LE_ENABLED)) return; /* Don't bother if remote LE support is not enabled */ @@ -2851,7 +3017,7 @@ static struct sk_buff *smp_alloc_skb_cb(struct l2cap_chan *chan, return ERR_PTR(-ENOMEM); skb->priority = HCI_PRIO_MAX; - bt_cb(skb)->chan = chan; + bt_cb(skb)->l2cap.chan = chan; return skb; } @@ -2924,51 +3090,63 @@ static const struct l2cap_ops smp_root_chan_ops = { static struct l2cap_chan *smp_add_cid(struct hci_dev *hdev, u16 cid) { struct l2cap_chan *chan; - struct crypto_blkcipher *tfm_aes; + struct smp_dev *smp; + struct crypto_blkcipher *tfm_aes; + struct crypto_hash *tfm_cmac; if (cid == L2CAP_CID_SMP_BREDR) { - tfm_aes = NULL; + smp = NULL; goto create_chan; } - tfm_aes = crypto_alloc_blkcipher("ecb(aes)", 0, 0); + smp = kzalloc(sizeof(*smp), GFP_KERNEL); + if (!smp) + return ERR_PTR(-ENOMEM); + + tfm_aes = crypto_alloc_blkcipher("ecb(aes)", 0, CRYPTO_ALG_ASYNC); if (IS_ERR(tfm_aes)) { - BT_ERR("Unable to create crypto context"); + BT_ERR("Unable to create ECB crypto context"); + kzfree(smp); return ERR_CAST(tfm_aes); } + tfm_cmac = crypto_alloc_hash("cmac(aes)", 0, CRYPTO_ALG_ASYNC); + if (IS_ERR(tfm_cmac)) { + BT_ERR("Unable to create CMAC crypto context"); + crypto_free_blkcipher(tfm_aes); + kzfree(smp); + return ERR_CAST(tfm_cmac); + } + + smp->tfm_aes = tfm_aes; + smp->tfm_cmac = tfm_cmac; + create_chan: chan = l2cap_chan_create(); if (!chan) { - crypto_free_blkcipher(tfm_aes); + if (smp) { + crypto_free_blkcipher(smp->tfm_aes); + crypto_free_hash(smp->tfm_cmac); + kzfree(smp); + } return ERR_PTR(-ENOMEM); } - chan->data = tfm_aes; + chan->data = smp; l2cap_add_scid(chan, cid); l2cap_chan_set_defaults(chan); if (cid == L2CAP_CID_SMP) { - /* If usage of static address is forced or if the devices - * does not have a public address, then listen on the static - * address. - * - * In case BR/EDR has been disabled on a dual-mode controller - * and a static address has been configued, then listen on - * the static address instead. - */ - if (test_bit(HCI_FORCE_STATIC_ADDR, &hdev->dbg_flags) || - !bacmp(&hdev->bdaddr, BDADDR_ANY) || - (!test_bit(HCI_BREDR_ENABLED, &hdev->dev_flags) && - bacmp(&hdev->static_addr, BDADDR_ANY))) { - bacpy(&chan->src, &hdev->static_addr); - chan->src_type = BDADDR_LE_RANDOM; - } else { - bacpy(&chan->src, &hdev->bdaddr); + u8 bdaddr_type; + + hci_copy_identity_address(hdev, &chan->src, &bdaddr_type); + + if (bdaddr_type == ADDR_LE_DEV_PUBLIC) chan->src_type = BDADDR_LE_PUBLIC; - } + else + chan->src_type = BDADDR_LE_RANDOM; } else { bacpy(&chan->src, &hdev->bdaddr); chan->src_type = BDADDR_BREDR; @@ -2987,14 +3165,18 @@ create_chan: static void smp_del_chan(struct l2cap_chan *chan) { - struct crypto_blkcipher *tfm_aes; + struct smp_dev *smp; BT_DBG("chan %p", chan); - tfm_aes = chan->data; - if (tfm_aes) { + smp = chan->data; + if (smp) { chan->data = NULL; - crypto_free_blkcipher(tfm_aes); + if (smp->tfm_aes) + crypto_free_blkcipher(smp->tfm_aes); + if (smp->tfm_cmac) + crypto_free_hash(smp->tfm_cmac); + kzfree(smp); } l2cap_chan_put(chan); @@ -3007,7 +3189,7 @@ static ssize_t force_bredr_smp_read(struct file *file, struct hci_dev *hdev = file->private_data; char buf[3]; - buf[0] = test_bit(HCI_FORCE_BREDR_SMP, &hdev->dbg_flags) ? 'Y': 'N'; + buf[0] = hci_dev_test_flag(hdev, HCI_FORCE_BREDR_SMP) ? 'Y': 'N'; buf[1] = '\n'; buf[2] = '\0'; return simple_read_from_buffer(user_buf, count, ppos, buf, 2); @@ -3029,7 +3211,7 @@ static ssize_t force_bredr_smp_write(struct file *file, if (strtobool(buf, &enable)) return -EINVAL; - if (enable == test_bit(HCI_FORCE_BREDR_SMP, &hdev->dbg_flags)) + if (enable == hci_dev_test_flag(hdev, HCI_FORCE_BREDR_SMP)) return -EALREADY; if (enable) { @@ -3048,7 +3230,7 @@ static ssize_t force_bredr_smp_write(struct file *file, smp_del_chan(chan); } - change_bit(HCI_FORCE_BREDR_SMP, &hdev->dbg_flags); + hci_dev_change_flag(hdev, HCI_FORCE_BREDR_SMP); return count; } @@ -3367,6 +3549,21 @@ static int __init test_h6(struct crypto_hash *tfm_cmac) return 0; } +static char test_smp_buffer[32]; + +static ssize_t test_smp_read(struct file *file, char __user *user_buf, + size_t count, loff_t *ppos) +{ + return simple_read_from_buffer(user_buf, count, ppos, test_smp_buffer, + strlen(test_smp_buffer)); +} + +static const struct file_operations test_smp_fops = { + .open = simple_open, + .read = test_smp_read, + .llseek = default_llseek, +}; + static int __init run_selftests(struct crypto_blkcipher *tfm_aes, struct crypto_hash *tfm_cmac) { @@ -3379,49 +3576,49 @@ static int __init run_selftests(struct crypto_blkcipher *tfm_aes, err = test_ah(tfm_aes); if (err) { BT_ERR("smp_ah test failed"); - return err; + goto done; } err = test_c1(tfm_aes); if (err) { BT_ERR("smp_c1 test failed"); - return err; + goto done; } err = test_s1(tfm_aes); if (err) { BT_ERR("smp_s1 test failed"); - return err; + goto done; } err = test_f4(tfm_cmac); if (err) { BT_ERR("smp_f4 test failed"); - return err; + goto done; } err = test_f5(tfm_cmac); if (err) { BT_ERR("smp_f5 test failed"); - return err; + goto done; } err = test_f6(tfm_cmac); if (err) { BT_ERR("smp_f6 test failed"); - return err; + goto done; } err = test_g2(tfm_cmac); if (err) { BT_ERR("smp_g2 test failed"); - return err; + goto done; } err = test_h6(tfm_cmac); if (err) { BT_ERR("smp_h6 test failed"); - return err; + goto done; } rettime = ktime_get(); @@ -3430,7 +3627,17 @@ static int __init run_selftests(struct crypto_blkcipher *tfm_aes, BT_INFO("SMP test passed in %llu usecs", duration); - return 0; +done: + if (!err) + snprintf(test_smp_buffer, sizeof(test_smp_buffer), + "PASS (%llu usecs)\n", duration); + else + snprintf(test_smp_buffer, sizeof(test_smp_buffer), "FAIL\n"); + + debugfs_create_file("selftest_smp", 0444, bt_debugfs, NULL, + &test_smp_fops); + + return err; } int __init bt_selftest_smp(void) diff --git a/net/bluetooth/smp.h b/net/bluetooth/smp.h index 60c5b73fcb4b..6cf872563ea7 100644 --- a/net/bluetooth/smp.h +++ b/net/bluetooth/smp.h @@ -188,6 +188,7 @@ int smp_user_confirm_reply(struct hci_conn *conn, u16 mgmt_op, __le32 passkey); bool smp_irk_matches(struct hci_dev *hdev, const u8 irk[16], const bdaddr_t *bdaddr); int smp_generate_rpa(struct hci_dev *hdev, const u8 irk[16], bdaddr_t *rpa); +int smp_generate_oob(struct hci_dev *hdev, u8 hash[16], u8 rand[16]); int smp_register(struct hci_dev *hdev); void smp_unregister(struct hci_dev *hdev); diff --git a/net/bridge/br_device.c b/net/bridge/br_device.c index ffd379db5938..4ff77a16956c 100644 --- a/net/bridge/br_device.c +++ b/net/bridge/br_device.c @@ -25,6 +25,9 @@ #define COMMON_FEATURES (NETIF_F_SG | NETIF_F_FRAGLIST | NETIF_F_HIGHDMA | \ NETIF_F_GSO_MASK | NETIF_F_HW_CSUM) +const struct nf_br_ops __rcu *nf_br_ops __read_mostly; +EXPORT_SYMBOL_GPL(nf_br_ops); + /* net device transmit always called with BH disabled */ netdev_tx_t br_dev_xmit(struct sk_buff *skb, struct net_device *dev) { @@ -33,16 +36,15 @@ netdev_tx_t br_dev_xmit(struct sk_buff *skb, struct net_device *dev) struct net_bridge_fdb_entry *dst; struct net_bridge_mdb_entry *mdst; struct pcpu_sw_netstats *brstats = this_cpu_ptr(br->stats); + const struct nf_br_ops *nf_ops; u16 vid = 0; rcu_read_lock(); -#if IS_ENABLED(CONFIG_BRIDGE_NETFILTER) - if (skb->nf_bridge && (skb->nf_bridge->mask & BRNF_BRIDGED_DNAT)) { - br_nf_pre_routing_finish_bridge_slow(skb); + nf_ops = rcu_dereference(nf_br_ops); + if (nf_ops && nf_ops->br_dev_xmit_hook(skb)) { rcu_read_unlock(); return NETDEV_TX_OK; } -#endif u64_stats_update_begin(&brstats->syncp); brstats->tx_packets++; diff --git a/net/bridge/br_forward.c b/net/bridge/br_forward.c index f96933a823e3..e97572b5d2cc 100644 --- a/net/bridge/br_forward.c +++ b/net/bridge/br_forward.c @@ -35,11 +35,9 @@ static inline int should_deliver(const struct net_bridge_port *p, p->state == BR_STATE_FORWARDING; } -int br_dev_queue_push_xmit(struct sk_buff *skb) +int br_dev_queue_push_xmit(struct sock *sk, struct sk_buff *skb) { - /* ip_fragment doesn't copy the MAC header */ - if (nf_bridge_maybe_copy_header(skb) || - !is_skb_forwardable(skb->dev, skb)) { + if (!is_skb_forwardable(skb->dev, skb)) { kfree_skb(skb); } else { skb_push(skb, ETH_HLEN); @@ -51,9 +49,10 @@ int br_dev_queue_push_xmit(struct sk_buff *skb) } EXPORT_SYMBOL_GPL(br_dev_queue_push_xmit); -int br_forward_finish(struct sk_buff *skb) +int br_forward_finish(struct sock *sk, struct sk_buff *skb) { - return NF_HOOK(NFPROTO_BRIDGE, NF_BR_POST_ROUTING, skb, NULL, skb->dev, + return NF_HOOK(NFPROTO_BRIDGE, NF_BR_POST_ROUTING, sk, skb, + NULL, skb->dev, br_dev_queue_push_xmit); } @@ -77,7 +76,8 @@ static void __br_deliver(const struct net_bridge_port *to, struct sk_buff *skb) return; } - NF_HOOK(NFPROTO_BRIDGE, NF_BR_LOCAL_OUT, skb, NULL, skb->dev, + NF_HOOK(NFPROTO_BRIDGE, NF_BR_LOCAL_OUT, NULL, skb, + NULL, skb->dev, br_forward_finish); } @@ -98,7 +98,8 @@ static void __br_forward(const struct net_bridge_port *to, struct sk_buff *skb) skb->dev = to->dev; skb_forward_csum(skb); - NF_HOOK(NFPROTO_BRIDGE, NF_BR_FORWARD, skb, indev, skb->dev, + NF_HOOK(NFPROTO_BRIDGE, NF_BR_FORWARD, NULL, skb, + indev, skb->dev, br_forward_finish); } @@ -188,6 +189,9 @@ static void br_flood(struct net_bridge *br, struct sk_buff *skb, /* Do not flood to ports that enable proxy ARP */ if (p->flags & BR_PROXYARP) continue; + if ((p->flags & BR_PROXYARP_WIFI) && + BR_INPUT_SKB_CB(skb)->proxyarp_replied) + continue; prev = maybe_deliver(prev, p, skb, __packet_hook); if (IS_ERR(prev)) diff --git a/net/bridge/br_input.c b/net/bridge/br_input.c index e2aa7be3a847..f921a5dce22d 100644 --- a/net/bridge/br_input.c +++ b/net/bridge/br_input.c @@ -55,12 +55,13 @@ static int br_pass_frame_up(struct sk_buff *skb) if (!skb) return NET_RX_DROP; - return NF_HOOK(NFPROTO_BRIDGE, NF_BR_LOCAL_IN, skb, indev, NULL, - netif_receive_skb); + return NF_HOOK(NFPROTO_BRIDGE, NF_BR_LOCAL_IN, NULL, skb, + indev, NULL, + netif_receive_skb_sk); } static void br_do_proxy_arp(struct sk_buff *skb, struct net_bridge *br, - u16 vid) + u16 vid, struct net_bridge_port *p) { struct net_device *dev = br->dev; struct neighbour *n; @@ -68,6 +69,8 @@ static void br_do_proxy_arp(struct sk_buff *skb, struct net_bridge *br, u8 *arpptr, *sha; __be32 sip, tip; + BR_INPUT_SKB_CB(skb)->proxyarp_replied = false; + if (dev->flags & IFF_NOARP) return; @@ -105,16 +108,19 @@ static void br_do_proxy_arp(struct sk_buff *skb, struct net_bridge *br, } f = __br_fdb_get(br, n->ha, vid); - if (f) + if (f && ((p->flags & BR_PROXYARP) || + (f->dst && (f->dst->flags & BR_PROXYARP_WIFI)))) { arp_send(ARPOP_REPLY, ETH_P_ARP, sip, skb->dev, tip, sha, n->ha, sha); + BR_INPUT_SKB_CB(skb)->proxyarp_replied = true; + } neigh_release(n); } } /* note: already called with rcu_read_lock */ -int br_handle_frame_finish(struct sk_buff *skb) +int br_handle_frame_finish(struct sock *sk, struct sk_buff *skb) { const unsigned char *dest = eth_hdr(skb)->h_dest; struct net_bridge_port *p = br_port_get_rcu(skb->dev); @@ -153,12 +159,10 @@ int br_handle_frame_finish(struct sk_buff *skb) dst = NULL; - if (is_broadcast_ether_addr(dest)) { - if (IS_ENABLED(CONFIG_INET) && - p->flags & BR_PROXYARP && - skb->protocol == htons(ETH_P_ARP)) - br_do_proxy_arp(skb, br, vid); + if (IS_ENABLED(CONFIG_INET) && skb->protocol == htons(ETH_P_ARP)) + br_do_proxy_arp(skb, br, vid, p); + if (is_broadcast_ether_addr(dest)) { skb2 = skb; unicast = false; } else if (is_multicast_ether_addr(dest)) { @@ -204,7 +208,7 @@ drop: EXPORT_SYMBOL_GPL(br_handle_frame_finish); /* note: already called with rcu_read_lock */ -static int br_handle_local_finish(struct sk_buff *skb) +static int br_handle_local_finish(struct sock *sk, struct sk_buff *skb) { struct net_bridge_port *p = br_port_get_rcu(skb->dev); u16 vid = 0; @@ -274,8 +278,8 @@ rx_handler_result_t br_handle_frame(struct sk_buff **pskb) } /* Deliver packet to local host only */ - if (NF_HOOK(NFPROTO_BRIDGE, NF_BR_LOCAL_IN, skb, skb->dev, - NULL, br_handle_local_finish)) { + if (NF_HOOK(NFPROTO_BRIDGE, NF_BR_LOCAL_IN, NULL, skb, + skb->dev, NULL, br_handle_local_finish)) { return RX_HANDLER_CONSUMED; /* consumed by filter */ } else { *pskb = skb; @@ -299,7 +303,8 @@ forward: if (ether_addr_equal(p->br->dev->dev_addr, dest)) skb->pkt_type = PACKET_HOST; - NF_HOOK(NFPROTO_BRIDGE, NF_BR_PRE_ROUTING, skb, skb->dev, NULL, + NF_HOOK(NFPROTO_BRIDGE, NF_BR_PRE_ROUTING, NULL, skb, + skb->dev, NULL, br_handle_frame_finish); break; default: diff --git a/net/bridge/br_mdb.c b/net/bridge/br_mdb.c index 409608960899..e29ad70b3000 100644 --- a/net/bridge/br_mdb.c +++ b/net/bridge/br_mdb.c @@ -170,7 +170,7 @@ static int nlmsg_populate_mdb_fill(struct sk_buff *skb, struct br_port_msg *bpm; struct nlattr *nest, *nest2; - nlh = nlmsg_put(skb, pid, seq, type, sizeof(*bpm), NLM_F_MULTI); + nlh = nlmsg_put(skb, pid, seq, type, sizeof(*bpm), 0); if (!nlh) return -EMSGSIZE; diff --git a/net/bridge/br_multicast.c b/net/bridge/br_multicast.c index c465876c7861..4b6722f8f179 100644 --- a/net/bridge/br_multicast.c +++ b/net/bridge/br_multicast.c @@ -814,7 +814,8 @@ static void __br_multicast_send_query(struct net_bridge *br, if (port) { skb->dev = port->dev; - NF_HOOK(NFPROTO_BRIDGE, NF_BR_LOCAL_OUT, skb, NULL, skb->dev, + NF_HOOK(NFPROTO_BRIDGE, NF_BR_LOCAL_OUT, NULL, skb, + NULL, skb->dev, br_dev_queue_push_xmit); } else { br_multicast_select_own_querier(br, ip, skb); diff --git a/net/bridge/br_netfilter.c b/net/bridge/br_netfilter.c index 0ee453fad3de..ab55e2472beb 100644 --- a/net/bridge/br_netfilter.c +++ b/net/bridge/br_netfilter.c @@ -37,17 +37,16 @@ #include <net/route.h> #include <net/netfilter/br_netfilter.h> +#if IS_ENABLED(CONFIG_NF_CONNTRACK) +#include <net/netfilter/nf_conntrack.h> +#endif + #include <asm/uaccess.h> #include "br_private.h" #ifdef CONFIG_SYSCTL #include <linux/sysctl.h> #endif -#define skb_origaddr(skb) (((struct bridge_skb_cb *) \ - (skb->nf_bridge->data))->daddr.ipv4) -#define store_orig_dstaddr(skb) (skb_origaddr(skb) = ip_hdr(skb)->daddr) -#define dnat_took_place(skb) (skb_origaddr(skb) != ip_hdr(skb)->daddr) - #ifdef CONFIG_SYSCTL static struct ctl_table_header *brnf_sysctl_header; static int brnf_call_iptables __read_mostly = 1; @@ -112,6 +111,24 @@ static inline __be16 pppoe_proto(const struct sk_buff *skb) pppoe_proto(skb) == htons(PPP_IPV6) && \ brnf_filter_pppoe_tagged) +/* largest possible L2 header, see br_nf_dev_queue_xmit() */ +#define NF_BRIDGE_MAX_MAC_HEADER_LENGTH (PPPOE_SES_HLEN + ETH_HLEN) + +#if IS_ENABLED(CONFIG_NF_DEFRAG_IPV4) +struct brnf_frag_data { + char mac[NF_BRIDGE_MAX_MAC_HEADER_LENGTH]; + u8 encap_size; + u8 size; +}; + +static DEFINE_PER_CPU(struct brnf_frag_data, brnf_frag_data_storage); +#endif + +static struct nf_bridge_info *nf_bridge_info_get(const struct sk_buff *skb) +{ + return skb->nf_bridge; +} + static inline struct rtable *bridge_parent_rtable(const struct net_device *dev) { struct net_bridge_port *port; @@ -154,6 +171,18 @@ static inline struct nf_bridge_info *nf_bridge_unshare(struct sk_buff *skb) return nf_bridge; } +static unsigned int nf_bridge_encap_header_len(const struct sk_buff *skb) +{ + switch (skb->protocol) { + case __cpu_to_be16(ETH_P_8021Q): + return VLAN_HLEN; + case __cpu_to_be16(ETH_P_PPP_SES): + return PPPOE_SES_HLEN; + default: + return 0; + } +} + static inline void nf_bridge_push_encap_header(struct sk_buff *skb) { unsigned int len = nf_bridge_encap_header_len(skb); @@ -178,14 +207,6 @@ static inline void nf_bridge_pull_encap_header_rcsum(struct sk_buff *skb) skb->network_header += len; } -static inline void nf_bridge_save_header(struct sk_buff *skb) -{ - int header_size = ETH_HLEN + nf_bridge_encap_header_len(skb); - - skb_copy_from_linear_data_offset(skb, -header_size, - skb->nf_bridge->data, header_size); -} - /* When handing a packet over to the IP layer * check whether we have a skb that is in the * expected format @@ -239,17 +260,31 @@ drop: return -1; } +static void nf_bridge_update_protocol(struct sk_buff *skb) +{ + switch (skb->nf_bridge->orig_proto) { + case BRNF_PROTO_8021Q: + skb->protocol = htons(ETH_P_8021Q); + break; + case BRNF_PROTO_PPPOE: + skb->protocol = htons(ETH_P_PPP_SES); + break; + case BRNF_PROTO_UNCHANGED: + break; + } +} + /* PF_BRIDGE/PRE_ROUTING *********************************************/ /* Undo the changes made for ip6tables PREROUTING and continue the * bridge PRE_ROUTING hook. */ -static int br_nf_pre_routing_finish_ipv6(struct sk_buff *skb) +static int br_nf_pre_routing_finish_ipv6(struct sock *sk, struct sk_buff *skb) { - struct nf_bridge_info *nf_bridge = skb->nf_bridge; + struct nf_bridge_info *nf_bridge = nf_bridge_info_get(skb); struct rtable *rt; - if (nf_bridge->mask & BRNF_PKT_TYPE) { + if (nf_bridge->pkt_otherhost) { skb->pkt_type = PACKET_OTHERHOST; - nf_bridge->mask ^= BRNF_PKT_TYPE; + nf_bridge->pkt_otherhost = false; } nf_bridge->mask ^= BRNF_NF_BRIDGE_PREROUTING; @@ -263,7 +298,8 @@ static int br_nf_pre_routing_finish_ipv6(struct sk_buff *skb) skb->dev = nf_bridge->physindev; nf_bridge_update_protocol(skb); nf_bridge_push_encap_header(skb); - NF_HOOK_THRESH(NFPROTO_BRIDGE, NF_BR_PRE_ROUTING, skb, skb->dev, NULL, + NF_HOOK_THRESH(NFPROTO_BRIDGE, NF_BR_PRE_ROUTING, sk, skb, + skb->dev, NULL, br_handle_frame_finish, 1); return 0; @@ -274,9 +310,8 @@ static int br_nf_pre_routing_finish_ipv6(struct sk_buff *skb) * don't, we use the neighbour framework to find out. In both cases, we make * sure that br_handle_frame_finish() is called afterwards. */ -static int br_nf_pre_routing_finish_bridge(struct sk_buff *skb) +static int br_nf_pre_routing_finish_bridge(struct sock *sk, struct sk_buff *skb) { - struct nf_bridge_info *nf_bridge = skb->nf_bridge; struct neighbour *neigh; struct dst_entry *dst; @@ -286,12 +321,13 @@ static int br_nf_pre_routing_finish_bridge(struct sk_buff *skb) dst = skb_dst(skb); neigh = dst_neigh_lookup_skb(dst, skb); if (neigh) { + struct nf_bridge_info *nf_bridge = nf_bridge_info_get(skb); int ret; if (neigh->hh.hh_len) { neigh_hh_bridge(&neigh->hh, skb); skb->dev = nf_bridge->physindev; - ret = br_handle_frame_finish(skb); + ret = br_handle_frame_finish(sk, skb); } else { /* the neighbour function below overwrites the complete * MAC header, so we save the Ethernet source address and @@ -299,7 +335,7 @@ static int br_nf_pre_routing_finish_bridge(struct sk_buff *skb) */ skb_copy_from_linear_data_offset(skb, -(ETH_HLEN-ETH_ALEN), - skb->nf_bridge->data, + nf_bridge->neigh_header, ETH_HLEN-ETH_ALEN); /* tell br_dev_xmit to continue with forwarding */ nf_bridge->mask |= BRNF_BRIDGED_DNAT; @@ -314,6 +350,22 @@ free_skb: return 0; } +static bool dnat_took_place(const struct sk_buff *skb) +{ +#if IS_ENABLED(CONFIG_NF_CONNTRACK) + enum ip_conntrack_info ctinfo; + struct nf_conn *ct; + + ct = nf_ct_get(skb, &ctinfo); + if (!ct || nf_ct_is_untracked(ct)) + return false; + + return test_bit(IPS_DST_NAT_BIT, &ct->status); +#else + return false; +#endif +} + /* This requires some explaining. If DNAT has taken place, * we will need to fix up the destination Ethernet address. * @@ -352,11 +404,11 @@ free_skb: * device, we proceed as if ip_route_input() succeeded. If it differs from the * logical bridge port or if ip_route_output_key() fails we drop the packet. */ -static int br_nf_pre_routing_finish(struct sk_buff *skb) +static int br_nf_pre_routing_finish(struct sock *sk, struct sk_buff *skb) { struct net_device *dev = skb->dev; struct iphdr *iph = ip_hdr(skb); - struct nf_bridge_info *nf_bridge = skb->nf_bridge; + struct nf_bridge_info *nf_bridge = nf_bridge_info_get(skb); struct rtable *rt; int err; int frag_max_size; @@ -364,9 +416,9 @@ static int br_nf_pre_routing_finish(struct sk_buff *skb) frag_max_size = IPCB(skb)->frag_max_size; BR_INPUT_SKB_CB(skb)->frag_max_size = frag_max_size; - if (nf_bridge->mask & BRNF_PKT_TYPE) { + if (nf_bridge->pkt_otherhost) { skb->pkt_type = PACKET_OTHERHOST; - nf_bridge->mask ^= BRNF_PKT_TYPE; + nf_bridge->pkt_otherhost = false; } nf_bridge->mask ^= BRNF_NF_BRIDGE_PREROUTING; if (dnat_took_place(skb)) { @@ -405,7 +457,7 @@ bridged_dnat: nf_bridge_push_encap_header(skb); NF_HOOK_THRESH(NFPROTO_BRIDGE, NF_BR_PRE_ROUTING, - skb, skb->dev, NULL, + sk, skb, skb->dev, NULL, br_nf_pre_routing_finish_bridge, 1); return 0; @@ -425,7 +477,8 @@ bridged_dnat: skb->dev = nf_bridge->physindev; nf_bridge_update_protocol(skb); nf_bridge_push_encap_header(skb); - NF_HOOK_THRESH(NFPROTO_BRIDGE, NF_BR_PRE_ROUTING, skb, skb->dev, NULL, + NF_HOOK_THRESH(NFPROTO_BRIDGE, NF_BR_PRE_ROUTING, sk, skb, + skb->dev, NULL, br_handle_frame_finish, 1); return 0; @@ -448,20 +501,21 @@ static struct net_device *brnf_get_logical_dev(struct sk_buff *skb, const struct /* Some common code for IPv4/IPv6 */ static struct net_device *setup_pre_routing(struct sk_buff *skb) { - struct nf_bridge_info *nf_bridge = skb->nf_bridge; + struct nf_bridge_info *nf_bridge = nf_bridge_info_get(skb); if (skb->pkt_type == PACKET_OTHERHOST) { skb->pkt_type = PACKET_HOST; - nf_bridge->mask |= BRNF_PKT_TYPE; + nf_bridge->pkt_otherhost = true; } nf_bridge->mask |= BRNF_NF_BRIDGE_PREROUTING; nf_bridge->physindev = skb->dev; skb->dev = brnf_get_logical_dev(skb, skb->dev); + if (skb->protocol == htons(ETH_P_8021Q)) - nf_bridge->mask |= BRNF_8021Q; + nf_bridge->orig_proto = BRNF_PROTO_8021Q; else if (skb->protocol == htons(ETH_P_PPP_SES)) - nf_bridge->mask |= BRNF_PPPoE; + nf_bridge->orig_proto = BRNF_PROTO_PPPOE; /* Must drop socket now because of tproxy. */ skb_orphan(skb); @@ -527,9 +581,7 @@ bad: * to ip6tables, which doesn't support NAT, so things are fairly simple. */ static unsigned int br_nf_pre_routing_ipv6(const struct nf_hook_ops *ops, struct sk_buff *skb, - const struct net_device *in, - const struct net_device *out, - int (*okfn)(struct sk_buff *)) + const struct nf_hook_state *state) { const struct ipv6hdr *hdr; u32 pkt_len; @@ -563,7 +615,8 @@ static unsigned int br_nf_pre_routing_ipv6(const struct nf_hook_ops *ops, return NF_DROP; skb->protocol = htons(ETH_P_IPV6); - NF_HOOK(NFPROTO_IPV6, NF_INET_PRE_ROUTING, skb, skb->dev, NULL, + NF_HOOK(NFPROTO_IPV6, NF_INET_PRE_ROUTING, state->sk, skb, + skb->dev, NULL, br_nf_pre_routing_finish_ipv6); return NF_STOLEN; @@ -577,9 +630,7 @@ static unsigned int br_nf_pre_routing_ipv6(const struct nf_hook_ops *ops, * address to be able to detect DNAT afterwards. */ static unsigned int br_nf_pre_routing(const struct nf_hook_ops *ops, struct sk_buff *skb, - const struct net_device *in, - const struct net_device *out, - int (*okfn)(struct sk_buff *)) + const struct nf_hook_state *state) { struct net_bridge_port *p; struct net_bridge *br; @@ -588,7 +639,7 @@ static unsigned int br_nf_pre_routing(const struct nf_hook_ops *ops, if (unlikely(!pskb_may_pull(skb, len))) return NF_DROP; - p = br_port_get_rcu(in); + p = br_port_get_rcu(state->in); if (p == NULL) return NF_DROP; br = p->br; @@ -598,7 +649,7 @@ static unsigned int br_nf_pre_routing(const struct nf_hook_ops *ops, return NF_ACCEPT; nf_bridge_pull_encap_header_rcsum(skb); - return br_nf_pre_routing_ipv6(ops, skb, in, out, okfn); + return br_nf_pre_routing_ipv6(ops, skb, state); } if (!brnf_call_iptables && !br->nf_call_iptables) @@ -617,10 +668,11 @@ static unsigned int br_nf_pre_routing(const struct nf_hook_ops *ops, return NF_DROP; if (!setup_pre_routing(skb)) return NF_DROP; - store_orig_dstaddr(skb); + skb->protocol = htons(ETH_P_IP); - NF_HOOK(NFPROTO_IPV4, NF_INET_PRE_ROUTING, skb, skb->dev, NULL, + NF_HOOK(NFPROTO_IPV4, NF_INET_PRE_ROUTING, state->sk, skb, + skb->dev, NULL, br_nf_pre_routing_finish); return NF_STOLEN; @@ -636,25 +688,30 @@ static unsigned int br_nf_pre_routing(const struct nf_hook_ops *ops, * prevent this from happening. */ static unsigned int br_nf_local_in(const struct nf_hook_ops *ops, struct sk_buff *skb, - const struct net_device *in, - const struct net_device *out, - int (*okfn)(struct sk_buff *)) + const struct nf_hook_state *state) { br_drop_fake_rtable(skb); return NF_ACCEPT; } /* PF_BRIDGE/FORWARD *************************************************/ -static int br_nf_forward_finish(struct sk_buff *skb) +static int br_nf_forward_finish(struct sock *sk, struct sk_buff *skb) { - struct nf_bridge_info *nf_bridge = skb->nf_bridge; + struct nf_bridge_info *nf_bridge = nf_bridge_info_get(skb); struct net_device *in; if (!IS_ARP(skb) && !IS_VLAN_ARP(skb)) { + int frag_max_size; + + if (skb->protocol == htons(ETH_P_IP)) { + frag_max_size = IPCB(skb)->frag_max_size; + BR_INPUT_SKB_CB(skb)->frag_max_size = frag_max_size; + } + in = nf_bridge->physindev; - if (nf_bridge->mask & BRNF_PKT_TYPE) { + if (nf_bridge->pkt_otherhost) { skb->pkt_type = PACKET_OTHERHOST; - nf_bridge->mask ^= BRNF_PKT_TYPE; + nf_bridge->pkt_otherhost = false; } nf_bridge_update_protocol(skb); } else { @@ -662,8 +719,8 @@ static int br_nf_forward_finish(struct sk_buff *skb) } nf_bridge_push_encap_header(skb); - NF_HOOK_THRESH(NFPROTO_BRIDGE, NF_BR_FORWARD, skb, in, - skb->dev, br_forward_finish, 1); + NF_HOOK_THRESH(NFPROTO_BRIDGE, NF_BR_FORWARD, sk, skb, + in, skb->dev, br_forward_finish, 1); return 0; } @@ -675,9 +732,7 @@ static int br_nf_forward_finish(struct sk_buff *skb) * bridge ports. */ static unsigned int br_nf_forward_ip(const struct nf_hook_ops *ops, struct sk_buff *skb, - const struct net_device *in, - const struct net_device *out, - int (*okfn)(struct sk_buff *)) + const struct nf_hook_state *state) { struct nf_bridge_info *nf_bridge; struct net_device *parent; @@ -691,7 +746,11 @@ static unsigned int br_nf_forward_ip(const struct nf_hook_ops *ops, if (!nf_bridge_unshare(skb)) return NF_DROP; - parent = bridge_parent(out); + nf_bridge = nf_bridge_info_get(skb); + if (!nf_bridge) + return NF_DROP; + + parent = bridge_parent(state->out); if (!parent) return NF_DROP; @@ -704,40 +763,42 @@ static unsigned int br_nf_forward_ip(const struct nf_hook_ops *ops, nf_bridge_pull_encap_header(skb); - nf_bridge = skb->nf_bridge; if (skb->pkt_type == PACKET_OTHERHOST) { skb->pkt_type = PACKET_HOST; - nf_bridge->mask |= BRNF_PKT_TYPE; + nf_bridge->pkt_otherhost = true; } - if (pf == NFPROTO_IPV4 && br_parse_ip_options(skb)) - return NF_DROP; + if (pf == NFPROTO_IPV4) { + int frag_max = BR_INPUT_SKB_CB(skb)->frag_max_size; + + if (br_parse_ip_options(skb)) + return NF_DROP; + + IPCB(skb)->frag_max_size = frag_max; + } - /* The physdev module checks on this */ - nf_bridge->mask |= BRNF_BRIDGED; nf_bridge->physoutdev = skb->dev; if (pf == NFPROTO_IPV4) skb->protocol = htons(ETH_P_IP); else skb->protocol = htons(ETH_P_IPV6); - NF_HOOK(pf, NF_INET_FORWARD, skb, brnf_get_logical_dev(skb, in), parent, - br_nf_forward_finish); + NF_HOOK(pf, NF_INET_FORWARD, NULL, skb, + brnf_get_logical_dev(skb, state->in), + parent, br_nf_forward_finish); return NF_STOLEN; } static unsigned int br_nf_forward_arp(const struct nf_hook_ops *ops, struct sk_buff *skb, - const struct net_device *in, - const struct net_device *out, - int (*okfn)(struct sk_buff *)) + const struct nf_hook_state *state) { struct net_bridge_port *p; struct net_bridge *br; struct net_device **d = (struct net_device **)(skb->cb); - p = br_port_get_rcu(out); + p = br_port_get_rcu(state->out); if (p == NULL) return NF_ACCEPT; br = p->br; @@ -756,55 +817,93 @@ static unsigned int br_nf_forward_arp(const struct nf_hook_ops *ops, nf_bridge_push_encap_header(skb); return NF_ACCEPT; } - *d = (struct net_device *)in; - NF_HOOK(NFPROTO_ARP, NF_ARP_FORWARD, skb, (struct net_device *)in, - (struct net_device *)out, br_nf_forward_finish); + *d = state->in; + NF_HOOK(NFPROTO_ARP, NF_ARP_FORWARD, state->sk, skb, + state->in, state->out, br_nf_forward_finish); return NF_STOLEN; } #if IS_ENABLED(CONFIG_NF_DEFRAG_IPV4) -static int br_nf_dev_queue_xmit(struct sk_buff *skb) +static int br_nf_push_frag_xmit(struct sock *sk, struct sk_buff *skb) +{ + struct brnf_frag_data *data; + int err; + + data = this_cpu_ptr(&brnf_frag_data_storage); + err = skb_cow_head(skb, data->size); + + if (err) { + kfree_skb(skb); + return 0; + } + + skb_copy_to_linear_data_offset(skb, -data->size, data->mac, data->size); + __skb_push(skb, data->encap_size); + + return br_dev_queue_push_xmit(sk, skb); +} + +static int br_nf_dev_queue_xmit(struct sock *sk, struct sk_buff *skb) { int ret; int frag_max_size; + unsigned int mtu_reserved; + + if (skb_is_gso(skb) || skb->protocol != htons(ETH_P_IP)) + return br_dev_queue_push_xmit(sk, skb); + mtu_reserved = nf_bridge_mtu_reduction(skb); /* This is wrong! We should preserve the original fragment * boundaries by preserving frag_list rather than refragmenting. */ - if (skb->protocol == htons(ETH_P_IP) && - skb->len + nf_bridge_mtu_reduction(skb) > skb->dev->mtu && - !skb_is_gso(skb)) { + if (skb->len + mtu_reserved > skb->dev->mtu) { + struct brnf_frag_data *data; + frag_max_size = BR_INPUT_SKB_CB(skb)->frag_max_size; if (br_parse_ip_options(skb)) /* Drop invalid packet */ return NF_DROP; IPCB(skb)->frag_max_size = frag_max_size; - ret = ip_fragment(skb, br_dev_queue_push_xmit); - } else - ret = br_dev_queue_push_xmit(skb); + + nf_bridge_update_protocol(skb); + + data = this_cpu_ptr(&brnf_frag_data_storage); + data->encap_size = nf_bridge_encap_header_len(skb); + data->size = ETH_HLEN + data->encap_size; + + skb_copy_from_linear_data_offset(skb, -data->size, data->mac, + data->size); + + ret = ip_fragment(sk, skb, br_nf_push_frag_xmit); + } else { + ret = br_dev_queue_push_xmit(sk, skb); + } return ret; } #else -static int br_nf_dev_queue_xmit(struct sk_buff *skb) +static int br_nf_dev_queue_xmit(struct sock *sk, struct sk_buff *skb) { - return br_dev_queue_push_xmit(skb); + return br_dev_queue_push_xmit(sk, skb); } #endif /* PF_BRIDGE/POST_ROUTING ********************************************/ static unsigned int br_nf_post_routing(const struct nf_hook_ops *ops, struct sk_buff *skb, - const struct net_device *in, - const struct net_device *out, - int (*okfn)(struct sk_buff *)) + const struct nf_hook_state *state) { - struct nf_bridge_info *nf_bridge = skb->nf_bridge; + struct nf_bridge_info *nf_bridge = nf_bridge_info_get(skb); struct net_device *realoutdev = bridge_parent(skb->dev); u_int8_t pf; - if (!nf_bridge || !(nf_bridge->mask & BRNF_BRIDGED)) + /* if nf_bridge is set, but ->physoutdev is NULL, this packet came in + * on a bridge, but was delivered locally and is now being routed: + * + * POST_ROUTING was already invoked from the ip stack. + */ + if (!nf_bridge || !nf_bridge->physoutdev) return NF_ACCEPT; if (!realoutdev) @@ -821,17 +920,17 @@ static unsigned int br_nf_post_routing(const struct nf_hook_ops *ops, * about the value of skb->pkt_type. */ if (skb->pkt_type == PACKET_OTHERHOST) { skb->pkt_type = PACKET_HOST; - nf_bridge->mask |= BRNF_PKT_TYPE; + nf_bridge->pkt_otherhost = true; } nf_bridge_pull_encap_header(skb); - nf_bridge_save_header(skb); if (pf == NFPROTO_IPV4) skb->protocol = htons(ETH_P_IP); else skb->protocol = htons(ETH_P_IPV6); - NF_HOOK(pf, NF_INET_POST_ROUTING, skb, NULL, realoutdev, + NF_HOOK(pf, NF_INET_POST_ROUTING, state->sk, skb, + NULL, realoutdev, br_nf_dev_queue_xmit); return NF_STOLEN; @@ -842,9 +941,7 @@ static unsigned int br_nf_post_routing(const struct nf_hook_ops *ops, * for the second time. */ static unsigned int ip_sabotage_in(const struct nf_hook_ops *ops, struct sk_buff *skb, - const struct net_device *in, - const struct net_device *out, - int (*okfn)(struct sk_buff *)) + const struct nf_hook_state *state) { if (skb->nf_bridge && !(skb->nf_bridge->mask & BRNF_NF_BRIDGE_PREROUTING)) { @@ -854,6 +951,44 @@ static unsigned int ip_sabotage_in(const struct nf_hook_ops *ops, return NF_ACCEPT; } +/* This is called when br_netfilter has called into iptables/netfilter, + * and DNAT has taken place on a bridge-forwarded packet. + * + * neigh->output has created a new MAC header, with local br0 MAC + * as saddr. + * + * This restores the original MAC saddr of the bridged packet + * before invoking bridge forward logic to transmit the packet. + */ +static void br_nf_pre_routing_finish_bridge_slow(struct sk_buff *skb) +{ + struct nf_bridge_info *nf_bridge = nf_bridge_info_get(skb); + + skb_pull(skb, ETH_HLEN); + nf_bridge->mask &= ~BRNF_BRIDGED_DNAT; + + BUILD_BUG_ON(sizeof(nf_bridge->neigh_header) != (ETH_HLEN - ETH_ALEN)); + + skb_copy_to_linear_data_offset(skb, -(ETH_HLEN - ETH_ALEN), + nf_bridge->neigh_header, + ETH_HLEN - ETH_ALEN); + skb->dev = nf_bridge->physindev; + br_handle_frame_finish(NULL, skb); +} + +static int br_nf_dev_xmit(struct sk_buff *skb) +{ + if (skb->nf_bridge && (skb->nf_bridge->mask & BRNF_BRIDGED_DNAT)) { + br_nf_pre_routing_finish_bridge_slow(skb); + return 1; + } + return 0; +} + +static const struct nf_br_ops br_ops = { + .br_dev_xmit_hook = br_nf_dev_xmit, +}; + void br_netfilter_enable(void) { } @@ -991,12 +1126,14 @@ static int __init br_netfilter_init(void) return -ENOMEM; } #endif + RCU_INIT_POINTER(nf_br_ops, &br_ops); printk(KERN_NOTICE "Bridge firewalling registered\n"); return 0; } static void __exit br_netfilter_fini(void) { + RCU_INIT_POINTER(nf_br_ops, NULL); nf_unregister_hooks(br_nf_ops, ARRAY_SIZE(br_nf_ops)); #ifdef CONFIG_SYSCTL unregister_net_sysctl_table(brnf_sysctl_header); diff --git a/net/bridge/br_netlink.c b/net/bridge/br_netlink.c index 4fbcea0e7ecb..4b5c236998ff 100644 --- a/net/bridge/br_netlink.c +++ b/net/bridge/br_netlink.c @@ -22,6 +22,85 @@ #include "br_private.h" #include "br_private_stp.h" +static int br_get_num_vlan_infos(const struct net_port_vlans *pv, + u32 filter_mask) +{ + u16 vid_range_start = 0, vid_range_end = 0; + u16 vid_range_flags = 0; + u16 pvid, vid, flags; + int num_vlans = 0; + + if (filter_mask & RTEXT_FILTER_BRVLAN) + return pv->num_vlans; + + if (!(filter_mask & RTEXT_FILTER_BRVLAN_COMPRESSED)) + return 0; + + /* Count number of vlan info's + */ + pvid = br_get_pvid(pv); + for_each_set_bit(vid, pv->vlan_bitmap, VLAN_N_VID) { + flags = 0; + if (vid == pvid) + flags |= BRIDGE_VLAN_INFO_PVID; + + if (test_bit(vid, pv->untagged_bitmap)) + flags |= BRIDGE_VLAN_INFO_UNTAGGED; + + if (vid_range_start == 0) { + goto initvars; + } else if ((vid - vid_range_end) == 1 && + flags == vid_range_flags) { + vid_range_end = vid; + continue; + } else { + if ((vid_range_end - vid_range_start) > 0) + num_vlans += 2; + else + num_vlans += 1; + } +initvars: + vid_range_start = vid; + vid_range_end = vid; + vid_range_flags = flags; + } + + if (vid_range_start != 0) { + if ((vid_range_end - vid_range_start) > 0) + num_vlans += 2; + else + num_vlans += 1; + } + + return num_vlans; +} + +static size_t br_get_link_af_size_filtered(const struct net_device *dev, + u32 filter_mask) +{ + struct net_port_vlans *pv; + int num_vlan_infos; + + rcu_read_lock(); + if (br_port_exists(dev)) + pv = nbp_get_vlan_info(br_port_get_rcu(dev)); + else if (dev->priv_flags & IFF_EBRIDGE) + pv = br_get_vlan_info((struct net_bridge *)netdev_priv(dev)); + else + pv = NULL; + if (pv) + num_vlan_infos = br_get_num_vlan_infos(pv, filter_mask); + else + num_vlan_infos = 0; + rcu_read_unlock(); + + if (!num_vlan_infos) + return 0; + + /* Each VLAN is returned in bridge_vlan_info along with flags */ + return num_vlan_infos * nla_total_size(sizeof(struct bridge_vlan_info)); +} + static inline size_t br_port_info_size(void) { return nla_total_size(1) /* IFLA_BRPORT_STATE */ @@ -36,7 +115,7 @@ static inline size_t br_port_info_size(void) + 0; } -static inline size_t br_nlmsg_size(void) +static inline size_t br_nlmsg_size(struct net_device *dev, u32 filter_mask) { return NLMSG_ALIGN(sizeof(struct ifinfomsg)) + nla_total_size(IFNAMSIZ) /* IFLA_IFNAME */ @@ -45,7 +124,9 @@ static inline size_t br_nlmsg_size(void) + nla_total_size(4) /* IFLA_MTU */ + nla_total_size(4) /* IFLA_LINK */ + nla_total_size(1) /* IFLA_OPERSTATE */ - + nla_total_size(br_port_info_size()); /* IFLA_PROTINFO */ + + nla_total_size(br_port_info_size()) /* IFLA_PROTINFO */ + + nla_total_size(br_get_link_af_size_filtered(dev, + filter_mask)); /* IFLA_AF_SPEC */ } static int br_port_fill_attrs(struct sk_buff *skb, @@ -62,7 +143,9 @@ static int br_port_fill_attrs(struct sk_buff *skb, nla_put_u8(skb, IFLA_BRPORT_FAST_LEAVE, !!(p->flags & BR_MULTICAST_FAST_LEAVE)) || nla_put_u8(skb, IFLA_BRPORT_LEARNING, !!(p->flags & BR_LEARNING)) || nla_put_u8(skb, IFLA_BRPORT_UNICAST_FLOOD, !!(p->flags & BR_FLOOD)) || - nla_put_u8(skb, IFLA_BRPORT_PROXYARP, !!(p->flags & BR_PROXYARP))) + nla_put_u8(skb, IFLA_BRPORT_PROXYARP, !!(p->flags & BR_PROXYARP)) || + nla_put_u8(skb, IFLA_BRPORT_PROXYARP_WIFI, + !!(p->flags & BR_PROXYARP_WIFI))) return -EMSGSIZE; return 0; @@ -222,8 +305,8 @@ static int br_fill_ifinfo(struct sk_buff *skb, nla_put_u8(skb, IFLA_OPERSTATE, operstate) || (dev->addr_len && nla_put(skb, IFLA_ADDRESS, dev->addr_len, dev->dev_addr)) || - (dev->ifindex != dev->iflink && - nla_put_u32(skb, IFLA_LINK, dev->iflink))) + (dev->ifindex != dev_get_iflink(dev) && + nla_put_u32(skb, IFLA_LINK, dev_get_iflink(dev)))) goto nla_put_failure; if (event == RTM_NEWLINK && port) { @@ -280,6 +363,7 @@ void br_ifinfo_notify(int event, struct net_bridge_port *port) struct net *net; struct sk_buff *skb; int err = -ENOBUFS; + u32 filter = RTEXT_FILTER_BRVLAN_COMPRESSED; if (!port) return; @@ -288,11 +372,11 @@ void br_ifinfo_notify(int event, struct net_bridge_port *port) br_debug(port->br, "port %u(%s) event %d\n", (unsigned int)port->port_no, port->dev->name, event); - skb = nlmsg_new(br_nlmsg_size(), GFP_ATOMIC); + skb = nlmsg_new(br_nlmsg_size(port->dev, filter), GFP_ATOMIC); if (skb == NULL) goto errout; - err = br_fill_ifinfo(skb, port, 0, 0, event, 0, 0, port->dev); + err = br_fill_ifinfo(skb, port, 0, 0, event, 0, filter, port->dev); if (err < 0) { /* -EMSGSIZE implies BUG in br_nlmsg_size() */ WARN_ON(err == -EMSGSIZE); @@ -310,7 +394,7 @@ errout: * Dump information about all ports, in response to GETLINK */ int br_getlink(struct sk_buff *skb, u32 pid, u32 seq, - struct net_device *dev, u32 filter_mask) + struct net_device *dev, u32 filter_mask, int nlflags) { struct net_bridge_port *port = br_port_get_rtnl(dev); @@ -318,7 +402,7 @@ int br_getlink(struct sk_buff *skb, u32 pid, u32 seq, !(filter_mask & RTEXT_FILTER_BRVLAN_COMPRESSED)) return 0; - return br_fill_ifinfo(skb, port, pid, seq, RTM_NEWLINK, NLM_F_MULTI, + return br_fill_ifinfo(skb, port, pid, seq, RTM_NEWLINK, nlflags, filter_mask, dev); } @@ -471,6 +555,7 @@ static int br_setport(struct net_bridge_port *p, struct nlattr *tb[]) br_set_port_flag(p, tb, IFLA_BRPORT_LEARNING, BR_LEARNING); br_set_port_flag(p, tb, IFLA_BRPORT_UNICAST_FLOOD, BR_FLOOD); br_set_port_flag(p, tb, IFLA_BRPORT_PROXYARP, BR_PROXYARP); + br_set_port_flag(p, tb, IFLA_BRPORT_PROXYARP_WIFI, BR_PROXYARP_WIFI); if (tb[IFLA_BRPORT_COST]) { err = br_stp_set_path_cost(p, nla_get_u32(tb[IFLA_BRPORT_COST])); @@ -648,6 +733,9 @@ static const struct nla_policy br_policy[IFLA_BR_MAX + 1] = { [IFLA_BR_FORWARD_DELAY] = { .type = NLA_U32 }, [IFLA_BR_HELLO_TIME] = { .type = NLA_U32 }, [IFLA_BR_MAX_AGE] = { .type = NLA_U32 }, + [IFLA_BR_AGEING_TIME] = { .type = NLA_U32 }, + [IFLA_BR_STP_STATE] = { .type = NLA_U32 }, + [IFLA_BR_PRIORITY] = { .type = NLA_U16 }, }; static int br_changelink(struct net_device *brdev, struct nlattr *tb[], @@ -677,6 +765,24 @@ static int br_changelink(struct net_device *brdev, struct nlattr *tb[], return err; } + if (data[IFLA_BR_AGEING_TIME]) { + u32 ageing_time = nla_get_u32(data[IFLA_BR_AGEING_TIME]); + + br->ageing_time = clock_t_to_jiffies(ageing_time); + } + + if (data[IFLA_BR_STP_STATE]) { + u32 stp_enabled = nla_get_u32(data[IFLA_BR_STP_STATE]); + + br_stp_set_enabled(br, stp_enabled); + } + + if (data[IFLA_BR_PRIORITY]) { + u32 priority = nla_get_u16(data[IFLA_BR_PRIORITY]); + + br_stp_set_bridge_priority(br, priority); + } + return 0; } @@ -685,6 +791,9 @@ static size_t br_get_size(const struct net_device *brdev) return nla_total_size(sizeof(u32)) + /* IFLA_BR_FORWARD_DELAY */ nla_total_size(sizeof(u32)) + /* IFLA_BR_HELLO_TIME */ nla_total_size(sizeof(u32)) + /* IFLA_BR_MAX_AGE */ + nla_total_size(sizeof(u32)) + /* IFLA_BR_AGEING_TIME */ + nla_total_size(sizeof(u32)) + /* IFLA_BR_STP_STATE */ + nla_total_size(sizeof(u16)) + /* IFLA_BR_PRIORITY */ 0; } @@ -694,10 +803,16 @@ static int br_fill_info(struct sk_buff *skb, const struct net_device *brdev) u32 forward_delay = jiffies_to_clock_t(br->forward_delay); u32 hello_time = jiffies_to_clock_t(br->hello_time); u32 age_time = jiffies_to_clock_t(br->max_age); + u32 ageing_time = jiffies_to_clock_t(br->ageing_time); + u32 stp_enabled = br->stp_enabled; + u16 priority = (br->bridge_id.prio[0] << 8) | br->bridge_id.prio[1]; if (nla_put_u32(skb, IFLA_BR_FORWARD_DELAY, forward_delay) || nla_put_u32(skb, IFLA_BR_HELLO_TIME, hello_time) || - nla_put_u32(skb, IFLA_BR_MAX_AGE, age_time)) + nla_put_u32(skb, IFLA_BR_MAX_AGE, age_time) || + nla_put_u32(skb, IFLA_BR_AGEING_TIME, ageing_time) || + nla_put_u32(skb, IFLA_BR_STP_STATE, stp_enabled) || + nla_put_u16(skb, IFLA_BR_PRIORITY, priority)) return -EMSGSIZE; return 0; diff --git a/net/bridge/br_nf_core.c b/net/bridge/br_nf_core.c index 387cb3bd017c..20cbb727df4d 100644 --- a/net/bridge/br_nf_core.c +++ b/net/bridge/br_nf_core.c @@ -54,7 +54,6 @@ static unsigned int fake_mtu(const struct dst_entry *dst) static struct dst_ops fake_dst_ops = { .family = AF_INET, - .protocol = cpu_to_be16(ETH_P_IP), .update_pmtu = fake_update_pmtu, .redirect = fake_redirect, .cow_metrics = fake_cow_metrics, diff --git a/net/bridge/br_private.h b/net/bridge/br_private.h index de0919975a25..3362c29400f1 100644 --- a/net/bridge/br_private.h +++ b/net/bridge/br_private.h @@ -305,6 +305,7 @@ struct br_input_skb_cb { #endif u16 frag_max_size; + bool proxyarp_replied; #ifdef CONFIG_BRIDGE_VLAN_FILTERING bool vlan_filtered; @@ -409,10 +410,10 @@ int br_fdb_external_learn_del(struct net_bridge *br, struct net_bridge_port *p, /* br_forward.c */ void br_deliver(const struct net_bridge_port *to, struct sk_buff *skb); -int br_dev_queue_push_xmit(struct sk_buff *skb); +int br_dev_queue_push_xmit(struct sock *sk, struct sk_buff *skb); void br_forward(const struct net_bridge_port *to, struct sk_buff *skb, struct sk_buff *skb0); -int br_forward_finish(struct sk_buff *skb); +int br_forward_finish(struct sock *sk, struct sk_buff *skb); void br_flood_deliver(struct net_bridge *br, struct sk_buff *skb, bool unicast); void br_flood_forward(struct net_bridge *br, struct sk_buff *skb, struct sk_buff *skb2, bool unicast); @@ -430,7 +431,7 @@ void br_port_flags_change(struct net_bridge_port *port, unsigned long mask); void br_manage_promisc(struct net_bridge *br); /* br_input.c */ -int br_handle_frame_finish(struct sk_buff *skb); +int br_handle_frame_finish(struct sock *sk, struct sk_buff *skb); rx_handler_result_t br_handle_frame(struct sk_buff **pskb); static inline bool br_rx_handler_check_rcu(const struct net_device *dev) @@ -762,6 +763,11 @@ static inline int br_vlan_enabled(struct net_bridge *br) } #endif +struct nf_br_ops { + int (*br_dev_xmit_hook)(struct sk_buff *skb); +}; +extern const struct nf_br_ops __rcu *nf_br_ops; + /* br_netfilter.c */ #if IS_ENABLED(CONFIG_BRIDGE_NETFILTER) int br_nf_core_init(void); @@ -822,7 +828,7 @@ void br_ifinfo_notify(int event, struct net_bridge_port *port); int br_setlink(struct net_device *dev, struct nlmsghdr *nlmsg, u16 flags); int br_dellink(struct net_device *dev, struct nlmsghdr *nlmsg, u16 flags); int br_getlink(struct sk_buff *skb, u32 pid, u32 seq, struct net_device *dev, - u32 filter_mask); + u32 filter_mask, int nlflags); #ifdef CONFIG_SYSFS /* br_sysfs_if.c */ diff --git a/net/bridge/br_stp_bpdu.c b/net/bridge/br_stp_bpdu.c index bdb459d21ad8..534fc4cd263e 100644 --- a/net/bridge/br_stp_bpdu.c +++ b/net/bridge/br_stp_bpdu.c @@ -54,8 +54,9 @@ static void br_send_bpdu(struct net_bridge_port *p, skb_reset_mac_header(skb); - NF_HOOK(NFPROTO_BRIDGE, NF_BR_LOCAL_OUT, skb, NULL, skb->dev, - dev_queue_xmit); + NF_HOOK(NFPROTO_BRIDGE, NF_BR_LOCAL_OUT, NULL, skb, + NULL, skb->dev, + dev_queue_xmit_sk); } static inline void br_set_ticks(unsigned char *dest, int j) diff --git a/net/bridge/br_sysfs_if.c b/net/bridge/br_sysfs_if.c index 2de5d91199e8..4905845a94e9 100644 --- a/net/bridge/br_sysfs_if.c +++ b/net/bridge/br_sysfs_if.c @@ -171,6 +171,7 @@ BRPORT_ATTR_FLAG(root_block, BR_ROOT_BLOCK); BRPORT_ATTR_FLAG(learning, BR_LEARNING); BRPORT_ATTR_FLAG(unicast_flood, BR_FLOOD); BRPORT_ATTR_FLAG(proxyarp, BR_PROXYARP); +BRPORT_ATTR_FLAG(proxyarp_wifi, BR_PROXYARP_WIFI); #ifdef CONFIG_BRIDGE_IGMP_SNOOPING static ssize_t show_multicast_router(struct net_bridge_port *p, char *buf) @@ -215,6 +216,7 @@ static const struct brport_attribute *brport_attrs[] = { &brport_attr_multicast_fast_leave, #endif &brport_attr_proxyarp, + &brport_attr_proxyarp_wifi, NULL }; diff --git a/net/bridge/netfilter/ebtable_filter.c b/net/bridge/netfilter/ebtable_filter.c index ce205aabf9c5..8a3f63b2e807 100644 --- a/net/bridge/netfilter/ebtable_filter.c +++ b/net/bridge/netfilter/ebtable_filter.c @@ -58,20 +58,18 @@ static const struct ebt_table frame_filter = { static unsigned int ebt_in_hook(const struct nf_hook_ops *ops, struct sk_buff *skb, - const struct net_device *in, const struct net_device *out, - int (*okfn)(struct sk_buff *)) + const struct nf_hook_state *state) { - return ebt_do_table(ops->hooknum, skb, in, out, - dev_net(in)->xt.frame_filter); + return ebt_do_table(ops->hooknum, skb, state->in, state->out, + dev_net(state->in)->xt.frame_filter); } static unsigned int ebt_out_hook(const struct nf_hook_ops *ops, struct sk_buff *skb, - const struct net_device *in, const struct net_device *out, - int (*okfn)(struct sk_buff *)) + const struct nf_hook_state *state) { - return ebt_do_table(ops->hooknum, skb, in, out, - dev_net(out)->xt.frame_filter); + return ebt_do_table(ops->hooknum, skb, state->in, state->out, + dev_net(state->out)->xt.frame_filter); } static struct nf_hook_ops ebt_ops_filter[] __read_mostly = { diff --git a/net/bridge/netfilter/ebtable_nat.c b/net/bridge/netfilter/ebtable_nat.c index a0ac2984fb6c..c5ef5b1ab678 100644 --- a/net/bridge/netfilter/ebtable_nat.c +++ b/net/bridge/netfilter/ebtable_nat.c @@ -58,20 +58,18 @@ static struct ebt_table frame_nat = { static unsigned int ebt_nat_in(const struct nf_hook_ops *ops, struct sk_buff *skb, - const struct net_device *in, const struct net_device *out, - int (*okfn)(struct sk_buff *)) + const struct nf_hook_state *state) { - return ebt_do_table(ops->hooknum, skb, in, out, - dev_net(in)->xt.frame_nat); + return ebt_do_table(ops->hooknum, skb, state->in, state->out, + dev_net(state->in)->xt.frame_nat); } static unsigned int ebt_nat_out(const struct nf_hook_ops *ops, struct sk_buff *skb, - const struct net_device *in, const struct net_device *out, - int (*okfn)(struct sk_buff *)) + const struct nf_hook_state *state) { - return ebt_do_table(ops->hooknum, skb, in, out, - dev_net(out)->xt.frame_nat); + return ebt_do_table(ops->hooknum, skb, state->in, state->out, + dev_net(state->out)->xt.frame_nat); } static struct nf_hook_ops ebt_ops_nat[] __read_mostly = { diff --git a/net/bridge/netfilter/nf_tables_bridge.c b/net/bridge/netfilter/nf_tables_bridge.c index 19473a9371b8..a343e62442b1 100644 --- a/net/bridge/netfilter/nf_tables_bridge.c +++ b/net/bridge/netfilter/nf_tables_bridge.c @@ -67,47 +67,43 @@ EXPORT_SYMBOL_GPL(nft_bridge_ip6hdr_validate); static inline void nft_bridge_set_pktinfo_ipv4(struct nft_pktinfo *pkt, const struct nf_hook_ops *ops, struct sk_buff *skb, - const struct net_device *in, - const struct net_device *out) + const struct nf_hook_state *state) { if (nft_bridge_iphdr_validate(skb)) - nft_set_pktinfo_ipv4(pkt, ops, skb, in, out); + nft_set_pktinfo_ipv4(pkt, ops, skb, state); else - nft_set_pktinfo(pkt, ops, skb, in, out); + nft_set_pktinfo(pkt, ops, skb, state); } static inline void nft_bridge_set_pktinfo_ipv6(struct nft_pktinfo *pkt, - const struct nf_hook_ops *ops, - struct sk_buff *skb, - const struct net_device *in, - const struct net_device *out) + const struct nf_hook_ops *ops, + struct sk_buff *skb, + const struct nf_hook_state *state) { #if IS_ENABLED(CONFIG_IPV6) if (nft_bridge_ip6hdr_validate(skb) && - nft_set_pktinfo_ipv6(pkt, ops, skb, in, out) == 0) + nft_set_pktinfo_ipv6(pkt, ops, skb, state) == 0) return; #endif - nft_set_pktinfo(pkt, ops, skb, in, out); + nft_set_pktinfo(pkt, ops, skb, state); } static unsigned int nft_do_chain_bridge(const struct nf_hook_ops *ops, struct sk_buff *skb, - const struct net_device *in, - const struct net_device *out, - int (*okfn)(struct sk_buff *)) + const struct nf_hook_state *state) { struct nft_pktinfo pkt; switch (eth_hdr(skb)->h_proto) { case htons(ETH_P_IP): - nft_bridge_set_pktinfo_ipv4(&pkt, ops, skb, in, out); + nft_bridge_set_pktinfo_ipv4(&pkt, ops, skb, state); break; case htons(ETH_P_IPV6): - nft_bridge_set_pktinfo_ipv6(&pkt, ops, skb, in, out); + nft_bridge_set_pktinfo_ipv6(&pkt, ops, skb, state); break; default: - nft_set_pktinfo(&pkt, ops, skb, in, out); + nft_set_pktinfo(&pkt, ops, skb, state); break; } diff --git a/net/bridge/netfilter/nft_meta_bridge.c b/net/bridge/netfilter/nft_meta_bridge.c index 4f02109d708f..a21269b83f16 100644 --- a/net/bridge/netfilter/nft_meta_bridge.c +++ b/net/bridge/netfilter/nft_meta_bridge.c @@ -19,12 +19,12 @@ #include "../br_private.h" static void nft_meta_bridge_get_eval(const struct nft_expr *expr, - struct nft_data data[NFT_REG_MAX + 1], + struct nft_regs *regs, const struct nft_pktinfo *pkt) { const struct nft_meta *priv = nft_expr_priv(expr); const struct net_device *in = pkt->in, *out = pkt->out; - struct nft_data *dest = &data[priv->dreg]; + u32 *dest = ®s->data[priv->dreg]; const struct net_bridge_port *p; switch (priv->key) { @@ -40,12 +40,12 @@ static void nft_meta_bridge_get_eval(const struct nft_expr *expr, goto out; } - strncpy((char *)dest->data, p->br->dev->name, sizeof(dest->data)); + strncpy((char *)dest, p->br->dev->name, IFNAMSIZ); return; out: - return nft_meta_get_eval(expr, data, pkt); + return nft_meta_get_eval(expr, regs, pkt); err: - data[NFT_REG_VERDICT].verdict = NFT_BREAK; + regs->verdict.code = NFT_BREAK; } static int nft_meta_bridge_get_init(const struct nft_ctx *ctx, @@ -53,27 +53,21 @@ static int nft_meta_bridge_get_init(const struct nft_ctx *ctx, const struct nlattr * const tb[]) { struct nft_meta *priv = nft_expr_priv(expr); - int err; + unsigned int len; priv->key = ntohl(nla_get_be32(tb[NFTA_META_KEY])); switch (priv->key) { case NFT_META_BRI_IIFNAME: case NFT_META_BRI_OIFNAME: + len = IFNAMSIZ; break; default: return nft_meta_get_init(ctx, expr, tb); } - priv->dreg = ntohl(nla_get_be32(tb[NFTA_META_DREG])); - err = nft_validate_output_register(priv->dreg); - if (err < 0) - return err; - - err = nft_validate_data_load(ctx, priv->dreg, NULL, NFT_DATA_VALUE); - if (err < 0) - return err; - - return 0; + priv->dreg = nft_parse_register(tb[NFTA_META_DREG]); + return nft_validate_register_store(ctx, priv->dreg, NULL, + NFT_DATA_VALUE, len); } static struct nft_expr_type nft_meta_bridge_type; diff --git a/net/bridge/netfilter/nft_reject_bridge.c b/net/bridge/netfilter/nft_reject_bridge.c index 3244aead0926..858d848564ee 100644 --- a/net/bridge/netfilter/nft_reject_bridge.c +++ b/net/bridge/netfilter/nft_reject_bridge.c @@ -21,6 +21,7 @@ #include <net/ip.h> #include <net/ip6_checksum.h> #include <linux/netfilter_bridge.h> +#include <linux/netfilter_ipv6.h> #include "../br_private.h" static void nft_reject_br_push_etherhdr(struct sk_buff *oldskb, @@ -36,7 +37,12 @@ static void nft_reject_br_push_etherhdr(struct sk_buff *oldskb, skb_pull(nskb, ETH_HLEN); } -static void nft_reject_br_send_v4_tcp_reset(struct sk_buff *oldskb, int hook) +/* We cannot use oldskb->dev, it can be either bridge device (NF_BRIDGE INPUT) + * or the bridge port (NF_BRIDGE PREROUTING). + */ +static void nft_reject_br_send_v4_tcp_reset(struct sk_buff *oldskb, + const struct net_device *dev, + int hook) { struct sk_buff *nskb; struct iphdr *niph; @@ -65,11 +71,12 @@ static void nft_reject_br_send_v4_tcp_reset(struct sk_buff *oldskb, int hook) nft_reject_br_push_etherhdr(oldskb, nskb); - br_deliver(br_port_get_rcu(oldskb->dev), nskb); + br_deliver(br_port_get_rcu(dev), nskb); } -static void nft_reject_br_send_v4_unreach(struct sk_buff *oldskb, int hook, - u8 code) +static void nft_reject_br_send_v4_unreach(struct sk_buff *oldskb, + const struct net_device *dev, + int hook, u8 code) { struct sk_buff *nskb; struct iphdr *niph; @@ -77,8 +84,9 @@ static void nft_reject_br_send_v4_unreach(struct sk_buff *oldskb, int hook, unsigned int len; void *payload; __wsum csum; + u8 proto; - if (!nft_bridge_iphdr_validate(oldskb)) + if (oldskb->csum_bad || !nft_bridge_iphdr_validate(oldskb)) return; /* IP header checks: fragment. */ @@ -91,7 +99,17 @@ static void nft_reject_br_send_v4_unreach(struct sk_buff *oldskb, int hook, if (!pskb_may_pull(oldskb, len)) return; - if (nf_ip_checksum(oldskb, hook, ip_hdrlen(oldskb), 0)) + if (pskb_trim_rcsum(oldskb, ntohs(ip_hdr(oldskb)->tot_len))) + return; + + if (ip_hdr(oldskb)->protocol == IPPROTO_TCP || + ip_hdr(oldskb)->protocol == IPPROTO_UDP) + proto = ip_hdr(oldskb)->protocol; + else + proto = 0; + + if (!skb_csum_unnecessary(oldskb) && + nf_ip_checksum(oldskb, hook, ip_hdrlen(oldskb), proto)) return; nskb = alloc_skb(sizeof(struct iphdr) + sizeof(struct icmphdr) + @@ -120,11 +138,13 @@ static void nft_reject_br_send_v4_unreach(struct sk_buff *oldskb, int hook, nft_reject_br_push_etherhdr(oldskb, nskb); - br_deliver(br_port_get_rcu(oldskb->dev), nskb); + br_deliver(br_port_get_rcu(dev), nskb); } static void nft_reject_br_send_v6_tcp_reset(struct net *net, - struct sk_buff *oldskb, int hook) + struct sk_buff *oldskb, + const struct net_device *dev, + int hook) { struct sk_buff *nskb; const struct tcphdr *oth; @@ -152,12 +172,37 @@ static void nft_reject_br_send_v6_tcp_reset(struct net *net, nft_reject_br_push_etherhdr(oldskb, nskb); - br_deliver(br_port_get_rcu(oldskb->dev), nskb); + br_deliver(br_port_get_rcu(dev), nskb); +} + +static bool reject6_br_csum_ok(struct sk_buff *skb, int hook) +{ + const struct ipv6hdr *ip6h = ipv6_hdr(skb); + int thoff; + __be16 fo; + u8 proto = ip6h->nexthdr; + + if (skb->csum_bad) + return false; + + if (skb_csum_unnecessary(skb)) + return true; + + if (ip6h->payload_len && + pskb_trim_rcsum(skb, ntohs(ip6h->payload_len) + sizeof(*ip6h))) + return false; + + thoff = ipv6_skip_exthdr(skb, ((u8*)(ip6h+1) - skb->data), &proto, &fo); + if (thoff < 0 || thoff >= skb->len || (fo & htons(~0x7)) != 0) + return false; + + return nf_ip6_checksum(skb, hook, thoff, proto) == 0; } static void nft_reject_br_send_v6_unreach(struct net *net, - struct sk_buff *oldskb, int hook, - u8 code) + struct sk_buff *oldskb, + const struct net_device *dev, + int hook, u8 code) { struct sk_buff *nskb; struct ipv6hdr *nip6h; @@ -176,6 +221,9 @@ static void nft_reject_br_send_v6_unreach(struct net *net, if (!pskb_may_pull(oldskb, len)) return; + if (!reject6_br_csum_ok(oldskb, hook)) + return; + nskb = alloc_skb(sizeof(struct iphdr) + sizeof(struct icmp6hdr) + LL_MAX_HEADER + len, GFP_ATOMIC); if (!nskb) @@ -205,12 +253,12 @@ static void nft_reject_br_send_v6_unreach(struct net *net, nft_reject_br_push_etherhdr(oldskb, nskb); - br_deliver(br_port_get_rcu(oldskb->dev), nskb); + br_deliver(br_port_get_rcu(dev), nskb); } static void nft_reject_bridge_eval(const struct nft_expr *expr, - struct nft_data data[NFT_REG_MAX + 1], - const struct nft_pktinfo *pkt) + struct nft_regs *regs, + const struct nft_pktinfo *pkt) { struct nft_reject *priv = nft_expr_priv(expr); struct net *net = dev_net((pkt->in != NULL) ? pkt->in : pkt->out); @@ -224,16 +272,16 @@ static void nft_reject_bridge_eval(const struct nft_expr *expr, case htons(ETH_P_IP): switch (priv->type) { case NFT_REJECT_ICMP_UNREACH: - nft_reject_br_send_v4_unreach(pkt->skb, + nft_reject_br_send_v4_unreach(pkt->skb, pkt->in, pkt->ops->hooknum, priv->icmp_code); break; case NFT_REJECT_TCP_RST: - nft_reject_br_send_v4_tcp_reset(pkt->skb, + nft_reject_br_send_v4_tcp_reset(pkt->skb, pkt->in, pkt->ops->hooknum); break; case NFT_REJECT_ICMPX_UNREACH: - nft_reject_br_send_v4_unreach(pkt->skb, + nft_reject_br_send_v4_unreach(pkt->skb, pkt->in, pkt->ops->hooknum, nft_reject_icmp_code(priv->icmp_code)); break; @@ -242,16 +290,16 @@ static void nft_reject_bridge_eval(const struct nft_expr *expr, case htons(ETH_P_IPV6): switch (priv->type) { case NFT_REJECT_ICMP_UNREACH: - nft_reject_br_send_v6_unreach(net, pkt->skb, + nft_reject_br_send_v6_unreach(net, pkt->skb, pkt->in, pkt->ops->hooknum, priv->icmp_code); break; case NFT_REJECT_TCP_RST: - nft_reject_br_send_v6_tcp_reset(net, pkt->skb, + nft_reject_br_send_v6_tcp_reset(net, pkt->skb, pkt->in, pkt->ops->hooknum); break; case NFT_REJECT_ICMPX_UNREACH: - nft_reject_br_send_v6_unreach(net, pkt->skb, + nft_reject_br_send_v6_unreach(net, pkt->skb, pkt->in, pkt->ops->hooknum, nft_reject_icmpv6_code(priv->icmp_code)); break; @@ -262,7 +310,7 @@ static void nft_reject_bridge_eval(const struct nft_expr *expr, break; } out: - data[NFT_REG_VERDICT].verdict = NF_DROP; + regs->verdict.code = NF_DROP; } static int nft_reject_bridge_validate(const struct nft_ctx *ctx, @@ -323,6 +371,8 @@ static int nft_reject_bridge_dump(struct sk_buff *skb, if (nla_put_u8(skb, NFTA_REJECT_ICMP_CODE, priv->icmp_code)) goto nla_put_failure; break; + default: + break; } return 0; diff --git a/net/caif/caif_socket.c b/net/caif/caif_socket.c index a6e2da0bc718..4ec0c803aef1 100644 --- a/net/caif/caif_socket.c +++ b/net/caif/caif_socket.c @@ -271,8 +271,8 @@ static void caif_check_flow_release(struct sock *sk) * Copied from unix_dgram_recvmsg, but removed credit checks, * changed locking, address handling and added MSG_TRUNC. */ -static int caif_seqpkt_recvmsg(struct kiocb *iocb, struct socket *sock, - struct msghdr *m, size_t len, int flags) +static int caif_seqpkt_recvmsg(struct socket *sock, struct msghdr *m, + size_t len, int flags) { struct sock *sk = sock->sk; @@ -343,9 +343,8 @@ static long caif_stream_data_wait(struct sock *sk, long timeo) * Copied from unix_stream_recvmsg, but removed credit checks, * changed locking calls, changed address handling. */ -static int caif_stream_recvmsg(struct kiocb *iocb, struct socket *sock, - struct msghdr *msg, size_t size, - int flags) +static int caif_stream_recvmsg(struct socket *sock, struct msghdr *msg, + size_t size, int flags) { struct sock *sk = sock->sk; int copied = 0; @@ -511,8 +510,8 @@ static int transmit_skb(struct sk_buff *skb, struct caifsock *cf_sk, } /* Copied from af_unix:unix_dgram_sendmsg, and adapted to CAIF */ -static int caif_seqpkt_sendmsg(struct kiocb *kiocb, struct socket *sock, - struct msghdr *msg, size_t len) +static int caif_seqpkt_sendmsg(struct socket *sock, struct msghdr *msg, + size_t len) { struct sock *sk = sock->sk; struct caifsock *cf_sk = container_of(sk, struct caifsock, sk); @@ -586,8 +585,8 @@ err: * Changed removed permission handling and added waiting for flow on * and other minor adaptations. */ -static int caif_stream_sendmsg(struct kiocb *kiocb, struct socket *sock, - struct msghdr *msg, size_t len) +static int caif_stream_sendmsg(struct socket *sock, struct msghdr *msg, + size_t len) { struct sock *sk = sock->sk; struct caifsock *cf_sk = container_of(sk, struct caifsock, sk); diff --git a/net/can/bcm.c b/net/can/bcm.c index ee9ffd956552..b523453585be 100644 --- a/net/can/bcm.c +++ b/net/can/bcm.c @@ -328,7 +328,7 @@ static void bcm_send_to_user(struct bcm_op *op, struct bcm_msg_head *head, * containing the interface index. */ - BUILD_BUG_ON(sizeof(skb->cb) < sizeof(struct sockaddr_can)); + sock_skb_cb_check_size(sizeof(struct sockaddr_can)); addr = (struct sockaddr_can *)skb->cb; memset(addr, 0, sizeof(*addr)); addr->can_family = AF_CAN; @@ -1231,8 +1231,7 @@ static int bcm_tx_send(struct msghdr *msg, int ifindex, struct sock *sk) /* * bcm_sendmsg - process BCM commands (opcodes) from the userspace */ -static int bcm_sendmsg(struct kiocb *iocb, struct socket *sock, - struct msghdr *msg, size_t size) +static int bcm_sendmsg(struct socket *sock, struct msghdr *msg, size_t size) { struct sock *sk = sock->sk; struct bcm_sock *bo = bcm_sk(sk); @@ -1535,8 +1534,8 @@ static int bcm_connect(struct socket *sock, struct sockaddr *uaddr, int len, return 0; } -static int bcm_recvmsg(struct kiocb *iocb, struct socket *sock, - struct msghdr *msg, size_t size, int flags) +static int bcm_recvmsg(struct socket *sock, struct msghdr *msg, size_t size, + int flags) { struct sock *sk = sock->sk; struct sk_buff *skb; diff --git a/net/can/raw.c b/net/can/raw.c index 00c13ef23661..31b9748cbb4e 100644 --- a/net/can/raw.c +++ b/net/can/raw.c @@ -74,6 +74,12 @@ MODULE_ALIAS("can-proto-1"); * storing the single filter in dfilter, to avoid using dynamic memory. */ +struct uniqframe { + ktime_t tstamp; + const struct sk_buff *skb; + unsigned int join_rx_count; +}; + struct raw_sock { struct sock sk; int bound; @@ -82,10 +88,12 @@ struct raw_sock { int loopback; int recv_own_msgs; int fd_frames; + int join_filters; int count; /* number of active filters */ struct can_filter dfilter; /* default/single filter */ struct can_filter *filter; /* pointer to filter(s) */ can_err_mask_t err_mask; + struct uniqframe __percpu *uniq; }; /* @@ -95,8 +103,8 @@ struct raw_sock { */ static inline unsigned int *raw_flags(struct sk_buff *skb) { - BUILD_BUG_ON(sizeof(skb->cb) <= (sizeof(struct sockaddr_can) + - sizeof(unsigned int))); + sock_skb_cb_check_size(sizeof(struct sockaddr_can) + + sizeof(unsigned int)); /* return pointer after struct sockaddr_can */ return (unsigned int *)(&((struct sockaddr_can *)skb->cb)[1]); @@ -123,6 +131,26 @@ static void raw_rcv(struct sk_buff *oskb, void *data) if (!ro->fd_frames && oskb->len != CAN_MTU) return; + /* eliminate multiple filter matches for the same skb */ + if (this_cpu_ptr(ro->uniq)->skb == oskb && + ktime_equal(this_cpu_ptr(ro->uniq)->tstamp, oskb->tstamp)) { + if (ro->join_filters) { + this_cpu_inc(ro->uniq->join_rx_count); + /* drop frame until all enabled filters matched */ + if (this_cpu_ptr(ro->uniq)->join_rx_count < ro->count) + return; + } else { + return; + } + } else { + this_cpu_ptr(ro->uniq)->skb = oskb; + this_cpu_ptr(ro->uniq)->tstamp = oskb->tstamp; + this_cpu_ptr(ro->uniq)->join_rx_count = 1; + /* drop first frame to check all enabled filters? */ + if (ro->join_filters && ro->count > 1) + return; + } + /* clone the given skb to be able to enqueue it into the rcv queue */ skb = skb_clone(oskb, GFP_ATOMIC); if (!skb) @@ -135,7 +163,7 @@ static void raw_rcv(struct sk_buff *oskb, void *data) * containing the interface index. */ - BUILD_BUG_ON(sizeof(skb->cb) < sizeof(struct sockaddr_can)); + sock_skb_cb_check_size(sizeof(struct sockaddr_can)); addr = (struct sockaddr_can *)skb->cb; memset(addr, 0, sizeof(*addr)); addr->can_family = AF_CAN; @@ -296,6 +324,12 @@ static int raw_init(struct sock *sk) ro->loopback = 1; ro->recv_own_msgs = 0; ro->fd_frames = 0; + ro->join_filters = 0; + + /* alloc_percpu provides zero'ed memory */ + ro->uniq = alloc_percpu(struct uniqframe); + if (unlikely(!ro->uniq)) + return -ENOMEM; /* set notifier */ ro->notifier.notifier_call = raw_notifier; @@ -339,6 +373,7 @@ static int raw_release(struct socket *sock) ro->ifindex = 0; ro->bound = 0; ro->count = 0; + free_percpu(ro->uniq); sock_orphan(sk); sock->sk = NULL; @@ -583,6 +618,15 @@ static int raw_setsockopt(struct socket *sock, int level, int optname, break; + case CAN_RAW_JOIN_FILTERS: + if (optlen != sizeof(ro->join_filters)) + return -EINVAL; + + if (copy_from_user(&ro->join_filters, optval, optlen)) + return -EFAULT; + + break; + default: return -ENOPROTOOPT; } @@ -647,6 +691,12 @@ static int raw_getsockopt(struct socket *sock, int level, int optname, val = &ro->fd_frames; break; + case CAN_RAW_JOIN_FILTERS: + if (len > sizeof(int)) + len = sizeof(int); + val = &ro->join_filters; + break; + default: return -ENOPROTOOPT; } @@ -658,8 +708,7 @@ static int raw_getsockopt(struct socket *sock, int level, int optname, return 0; } -static int raw_sendmsg(struct kiocb *iocb, struct socket *sock, - struct msghdr *msg, size_t size) +static int raw_sendmsg(struct socket *sock, struct msghdr *msg, size_t size) { struct sock *sk = sock->sk; struct raw_sock *ro = raw_sk(sk); @@ -728,8 +777,8 @@ send_failed: return err; } -static int raw_recvmsg(struct kiocb *iocb, struct socket *sock, - struct msghdr *msg, size_t size, int flags) +static int raw_recvmsg(struct socket *sock, struct msghdr *msg, size_t size, + int flags) { struct sock *sk = sock->sk; struct sk_buff *skb; diff --git a/net/ceph/ceph_common.c b/net/ceph/ceph_common.c index ec565508e904..79e8f71aef5b 100644 --- a/net/ceph/ceph_common.c +++ b/net/ceph/ceph_common.c @@ -490,6 +490,43 @@ out: } EXPORT_SYMBOL(ceph_parse_options); +int ceph_print_client_options(struct seq_file *m, struct ceph_client *client) +{ + struct ceph_options *opt = client->options; + size_t pos = m->count; + + if (opt->name) + seq_printf(m, "name=%s,", opt->name); + if (opt->key) + seq_puts(m, "secret=<hidden>,"); + + if (opt->flags & CEPH_OPT_FSID) + seq_printf(m, "fsid=%pU,", &opt->fsid); + if (opt->flags & CEPH_OPT_NOSHARE) + seq_puts(m, "noshare,"); + if (opt->flags & CEPH_OPT_NOCRC) + seq_puts(m, "nocrc,"); + if (opt->flags & CEPH_OPT_NOMSGAUTH) + seq_puts(m, "nocephx_require_signatures,"); + if ((opt->flags & CEPH_OPT_TCP_NODELAY) == 0) + seq_puts(m, "notcp_nodelay,"); + + if (opt->mount_timeout != CEPH_MOUNT_TIMEOUT_DEFAULT) + seq_printf(m, "mount_timeout=%d,", opt->mount_timeout); + if (opt->osd_idle_ttl != CEPH_OSD_IDLE_TTL_DEFAULT) + seq_printf(m, "osd_idle_ttl=%d,", opt->osd_idle_ttl); + if (opt->osd_keepalive_timeout != CEPH_OSD_KEEPALIVE_DEFAULT) + seq_printf(m, "osdkeepalivetimeout=%d,", + opt->osd_keepalive_timeout); + + /* drop redundant comma */ + if (m->count != pos) + m->count--; + + return 0; +} +EXPORT_SYMBOL(ceph_print_client_options); + u64 ceph_client_id(struct ceph_client *client) { return client->monc.auth->global_id; diff --git a/net/ceph/crush/crush.c b/net/ceph/crush/crush.c index 16bc199d9a62..9d84ce4ea0df 100644 --- a/net/ceph/crush/crush.c +++ b/net/ceph/crush/crush.c @@ -17,6 +17,7 @@ const char *crush_bucket_alg_name(int alg) case CRUSH_BUCKET_LIST: return "list"; case CRUSH_BUCKET_TREE: return "tree"; case CRUSH_BUCKET_STRAW: return "straw"; + case CRUSH_BUCKET_STRAW2: return "straw2"; default: return "unknown"; } } @@ -40,6 +41,8 @@ int crush_get_bucket_item_weight(const struct crush_bucket *b, int p) return ((struct crush_bucket_tree *)b)->node_weights[crush_calc_tree_node(p)]; case CRUSH_BUCKET_STRAW: return ((struct crush_bucket_straw *)b)->item_weights[p]; + case CRUSH_BUCKET_STRAW2: + return ((struct crush_bucket_straw2 *)b)->item_weights[p]; } return 0; } @@ -77,6 +80,14 @@ void crush_destroy_bucket_straw(struct crush_bucket_straw *b) kfree(b); } +void crush_destroy_bucket_straw2(struct crush_bucket_straw2 *b) +{ + kfree(b->item_weights); + kfree(b->h.perm); + kfree(b->h.items); + kfree(b); +} + void crush_destroy_bucket(struct crush_bucket *b) { switch (b->alg) { @@ -92,6 +103,9 @@ void crush_destroy_bucket(struct crush_bucket *b) case CRUSH_BUCKET_STRAW: crush_destroy_bucket_straw((struct crush_bucket_straw *)b); break; + case CRUSH_BUCKET_STRAW2: + crush_destroy_bucket_straw2((struct crush_bucket_straw2 *)b); + break; } } diff --git a/net/ceph/crush/crush_ln_table.h b/net/ceph/crush/crush_ln_table.h new file mode 100644 index 000000000000..6192c7fc958c --- /dev/null +++ b/net/ceph/crush/crush_ln_table.h @@ -0,0 +1,166 @@ +/* + * Ceph - scalable distributed file system + * + * Copyright (C) 2015 Intel Corporation All Rights Reserved + * + * This is free software; you can redistribute it and/or + * modify it under the terms of the GNU Lesser General Public + * License version 2.1, as published by the Free Software + * Foundation. See file COPYING. + * + */ + +#if defined(__linux__) +#include <linux/types.h> +#elif defined(__FreeBSD__) +#include <sys/types.h> +#endif + +#ifndef CEPH_CRUSH_LN_H +#define CEPH_CRUSH_LN_H + + +// RH_LH_tbl[2*k] = 2^48/(1.0+k/128.0) +// RH_LH_tbl[2*k+1] = 2^48*log2(1.0+k/128.0) + +static int64_t __RH_LH_tbl[128*2+2] = { + 0x0001000000000000ll, 0x0000000000000000ll, 0x0000fe03f80fe040ll, 0x000002dfca16dde1ll, + 0x0000fc0fc0fc0fc1ll, 0x000005b9e5a170b4ll, 0x0000fa232cf25214ll, 0x0000088e68ea899all, + 0x0000f83e0f83e0f9ll, 0x00000b5d69bac77ell, 0x0000f6603d980f67ll, 0x00000e26fd5c8555ll, + 0x0000f4898d5f85bcll, 0x000010eb389fa29fll, 0x0000f2b9d6480f2cll, 0x000013aa2fdd27f1ll, + 0x0000f0f0f0f0f0f1ll, 0x00001663f6fac913ll, 0x0000ef2eb71fc435ll, 0x00001918a16e4633ll, + 0x0000ed7303b5cc0fll, 0x00001bc84240adabll, 0x0000ebbdb2a5c162ll, 0x00001e72ec117fa5ll, + 0x0000ea0ea0ea0ea1ll, 0x00002118b119b4f3ll, 0x0000e865ac7b7604ll, 0x000023b9a32eaa56ll, + 0x0000e6c2b4481cd9ll, 0x00002655d3c4f15cll, 0x0000e525982af70dll, 0x000028ed53f307eell, + 0x0000e38e38e38e39ll, 0x00002b803473f7adll, 0x0000e1fc780e1fc8ll, 0x00002e0e85a9de04ll, + 0x0000e070381c0e08ll, 0x0000309857a05e07ll, 0x0000dee95c4ca038ll, 0x0000331dba0efce1ll, + 0x0000dd67c8a60dd7ll, 0x0000359ebc5b69d9ll, 0x0000dbeb61eed19dll, 0x0000381b6d9bb29bll, + 0x0000da740da740dbll, 0x00003a93dc9864b2ll, 0x0000d901b2036407ll, 0x00003d0817ce9cd4ll, + 0x0000d79435e50d7all, 0x00003f782d7204d0ll, 0x0000d62b80d62b81ll, 0x000041e42b6ec0c0ll, + 0x0000d4c77b03531ell, 0x0000444c1f6b4c2dll, 0x0000d3680d3680d4ll, 0x000046b016ca47c1ll, + 0x0000d20d20d20d21ll, 0x000049101eac381cll, 0x0000d0b69fcbd259ll, 0x00004b6c43f1366all, + 0x0000cf6474a8819fll, 0x00004dc4933a9337ll, 0x0000ce168a772509ll, 0x0000501918ec6c11ll, + 0x0000cccccccccccdll, 0x00005269e12f346ell, 0x0000cb8727c065c4ll, 0x000054b6f7f1325all, + 0x0000ca4587e6b750ll, 0x0000570068e7ef5all, 0x0000c907da4e8712ll, 0x000059463f919deell, + 0x0000c7ce0c7ce0c8ll, 0x00005b8887367433ll, 0x0000c6980c6980c7ll, 0x00005dc74ae9fbecll, + 0x0000c565c87b5f9ell, 0x00006002958c5871ll, 0x0000c4372f855d83ll, 0x0000623a71cb82c8ll, + 0x0000c30c30c30c31ll, 0x0000646eea247c5cll, 0x0000c1e4bbd595f7ll, 0x000066a008e4788cll, + 0x0000c0c0c0c0c0c1ll, 0x000068cdd829fd81ll, 0x0000bfa02fe80bfbll, 0x00006af861e5fc7dll, + 0x0000be82fa0be830ll, 0x00006d1fafdce20all, 0x0000bd6910470767ll, 0x00006f43cba79e40ll, + 0x0000bc52640bc527ll, 0x00007164beb4a56dll, 0x0000bb3ee721a54ell, 0x000073829248e961ll, + 0x0000ba2e8ba2e8bbll, 0x0000759d4f80cba8ll, 0x0000b92143fa36f6ll, 0x000077b4ff5108d9ll, + 0x0000b81702e05c0cll, 0x000079c9aa879d53ll, 0x0000b70fbb5a19bfll, 0x00007bdb59cca388ll, + 0x0000b60b60b60b61ll, 0x00007dea15a32c1bll, 0x0000b509e68a9b95ll, 0x00007ff5e66a0ffell, + 0x0000b40b40b40b41ll, 0x000081fed45cbccbll, 0x0000b30f63528918ll, 0x00008404e793fb81ll, + 0x0000b21642c8590cll, 0x000086082806b1d5ll, 0x0000b11fd3b80b12ll, 0x000088089d8a9e47ll, + 0x0000b02c0b02c0b1ll, 0x00008a064fd50f2all, 0x0000af3addc680b0ll, 0x00008c01467b94bbll, + 0x0000ae4c415c9883ll, 0x00008df988f4ae80ll, 0x0000ad602b580ad7ll, 0x00008fef1e987409ll, + 0x0000ac7691840ac8ll, 0x000091e20ea1393ell, 0x0000ab8f69e2835all, 0x000093d2602c2e5fll, + 0x0000aaaaaaaaaaabll, 0x000095c01a39fbd6ll, 0x0000a9c84a47a080ll, 0x000097ab43af59f9ll, + 0x0000a8e83f5717c1ll, 0x00009993e355a4e5ll, 0x0000a80a80a80a81ll, 0x00009b79ffdb6c8bll, + 0x0000a72f0539782all, 0x00009d5d9fd5010bll, 0x0000a655c4392d7cll, 0x00009f3ec9bcfb80ll, + 0x0000a57eb50295fbll, 0x0000a11d83f4c355ll, 0x0000a4a9cf1d9684ll, 0x0000a2f9d4c51039ll, + 0x0000a3d70a3d70a4ll, 0x0000a4d3c25e68dcll, 0x0000a3065e3fae7dll, 0x0000a6ab52d99e76ll, + 0x0000a237c32b16d0ll, 0x0000a8808c384547ll, 0x0000a16b312ea8fdll, 0x0000aa5374652a1cll, + 0x0000a0a0a0a0a0a1ll, 0x0000ac241134c4e9ll, 0x00009fd809fd80a0ll, 0x0000adf26865a8a1ll, + 0x00009f1165e72549ll, 0x0000afbe7fa0f04dll, 0x00009e4cad23dd60ll, 0x0000b1885c7aa982ll, + 0x00009d89d89d89d9ll, 0x0000b35004723c46ll, 0x00009cc8e160c3fcll, 0x0000b5157cf2d078ll, + 0x00009c09c09c09c1ll, 0x0000b6d8cb53b0call, 0x00009b4c6f9ef03bll, 0x0000b899f4d8ab63ll, + 0x00009a90e7d95bc7ll, 0x0000ba58feb2703all, 0x000099d722dabde6ll, 0x0000bc15edfeed32ll, + 0x0000991f1a515886ll, 0x0000bdd0c7c9a817ll, 0x00009868c809868dll, 0x0000bf89910c1678ll, + 0x000097b425ed097cll, 0x0000c1404eadf383ll, 0x000097012e025c05ll, 0x0000c2f5058593d9ll, + 0x0000964fda6c0965ll, 0x0000c4a7ba58377cll, 0x000095a02568095bll, 0x0000c65871da59ddll, + 0x000094f2094f2095ll, 0x0000c80730b00016ll, 0x0000944580944581ll, 0x0000c9b3fb6d0559ll, + 0x0000939a85c4093all, 0x0000cb5ed69565afll, 0x000092f113840498ll, 0x0000cd07c69d8702ll, + 0x0000924924924925ll, 0x0000ceaecfea8085ll, 0x000091a2b3c4d5e7ll, 0x0000d053f6d26089ll, + 0x000090fdbc090fdcll, 0x0000d1f73f9c70c0ll, 0x0000905a38633e07ll, 0x0000d398ae817906ll, + 0x00008fb823ee08fcll, 0x0000d53847ac00a6ll, 0x00008f1779d9fdc4ll, 0x0000d6d60f388e41ll, + 0x00008e78356d1409ll, 0x0000d8720935e643ll, 0x00008dda5202376all, 0x0000da0c39a54804ll, + 0x00008d3dcb08d3ddll, 0x0000dba4a47aa996ll, 0x00008ca29c046515ll, 0x0000dd3b4d9cf24bll, + 0x00008c08c08c08c1ll, 0x0000ded038e633f3ll, 0x00008b70344a139cll, 0x0000e0636a23e2eell, + 0x00008ad8f2fba939ll, 0x0000e1f4e5170d02ll, 0x00008a42f870566all, 0x0000e384ad748f0ell, + 0x000089ae4089ae41ll, 0x0000e512c6e54998ll, 0x0000891ac73ae982ll, 0x0000e69f35065448ll, + 0x0000888888888889ll, 0x0000e829fb693044ll, 0x000087f78087f781ll, 0x0000e9b31d93f98ell, + 0x00008767ab5f34e5ll, 0x0000eb3a9f019750ll, 0x000086d905447a35ll, 0x0000ecc08321eb30ll, + 0x0000864b8a7de6d2ll, 0x0000ee44cd59ffabll, 0x000085bf37612cefll, 0x0000efc781043579ll, + 0x0000853408534086ll, 0x0000f148a170700all, 0x000084a9f9c8084bll, 0x0000f2c831e44116ll, + 0x0000842108421085ll, 0x0000f446359b1353ll, 0x0000839930523fbfll, 0x0000f5c2afc65447ll, + 0x000083126e978d50ll, 0x0000f73da38d9d4all, 0x0000828cbfbeb9a1ll, 0x0000f8b7140edbb1ll, + 0x0000820820820821ll, 0x0000fa2f045e7832ll, 0x000081848da8faf1ll, 0x0000fba577877d7dll, + 0x0000810204081021ll, 0x0000fd1a708bbe11ll, 0x0000808080808081ll, 0x0000fe8df263f957ll, + 0x0000800000000000ll, 0x0000ffff00000000ll, + }; + + + // LL_tbl[k] = 2^48*log2(1.0+k/2^15); +static int64_t __LL_tbl[256] = { + 0x0000000000000000ull, 0x00000002e2a60a00ull, 0x000000070cb64ec5ull, 0x00000009ef50ce67ull, + 0x0000000cd1e588fdull, 0x0000000fb4747e9cull, 0x0000001296fdaf5eull, 0x0000001579811b58ull, + 0x000000185bfec2a1ull, 0x0000001b3e76a552ull, 0x0000001e20e8c380ull, 0x0000002103551d43ull, + 0x00000023e5bbb2b2ull, 0x00000026c81c83e4ull, 0x00000029aa7790f0ull, 0x0000002c8cccd9edull, + 0x0000002f6f1c5ef2ull, 0x0000003251662017ull, 0x0000003533aa1d71ull, 0x0000003815e8571aull, + 0x0000003af820cd26ull, 0x0000003dda537faeull, 0x00000040bc806ec8ull, 0x000000439ea79a8cull, + 0x0000004680c90310ull, 0x0000004962e4a86cull, 0x0000004c44fa8ab6ull, 0x0000004f270aaa06ull, + 0x0000005209150672ull, 0x00000054eb19a013ull, 0x00000057cd1876fdull, 0x0000005aaf118b4aull, + 0x0000005d9104dd0full, 0x0000006072f26c64ull, 0x0000006354da3960ull, 0x0000006636bc441aull, + 0x0000006918988ca8ull, 0x0000006bfa6f1322ull, 0x0000006edc3fd79full, 0x00000071be0ada35ull, + 0x000000749fd01afdull, 0x00000077818f9a0cull, 0x0000007a6349577aull, 0x0000007d44fd535eull, + 0x0000008026ab8dceull, 0x00000083085406e3ull, 0x00000085e9f6beb2ull, 0x00000088cb93b552ull, + 0x0000008bad2aeadcull, 0x0000008e8ebc5f65ull, 0x0000009170481305ull, 0x0000009451ce05d3ull, + 0x00000097334e37e5ull, 0x0000009a14c8a953ull, 0x0000009cf63d5a33ull, 0x0000009fd7ac4a9dull, + 0x000000a2b07f3458ull, 0x000000a59a78ea6aull, 0x000000a87bd699fbull, 0x000000ab5d2e8970ull, + 0x000000ae3e80b8e3ull, 0x000000b11fcd2869ull, 0x000000b40113d818ull, 0x000000b6e254c80aull, + 0x000000b9c38ff853ull, 0x000000bca4c5690cull, 0x000000bf85f51a4aull, 0x000000c2671f0c26ull, + 0x000000c548433eb6ull, 0x000000c82961b211ull, 0x000000cb0a7a664dull, 0x000000cdeb8d5b82ull, + 0x000000d0cc9a91c8ull, 0x000000d3ada20933ull, 0x000000d68ea3c1ddull, 0x000000d96f9fbbdbull, + 0x000000dc5095f744ull, 0x000000df31867430ull, 0x000000e2127132b5ull, 0x000000e4f35632eaull, + 0x000000e7d43574e6ull, 0x000000eab50ef8c1ull, 0x000000ed95e2be90ull, 0x000000f076b0c66cull, + 0x000000f35779106aull, 0x000000f6383b9ca2ull, 0x000000f918f86b2aull, 0x000000fbf9af7c1aull, + 0x000000feda60cf88ull, 0x00000101bb0c658cull, 0x000001049bb23e3cull, 0x000001077c5259afull, + 0x0000010a5cecb7fcull, 0x0000010d3d81593aull, 0x000001101e103d7full, 0x00000112fe9964e4ull, + 0x00000115df1ccf7eull, 0x00000118bf9a7d64ull, 0x0000011ba0126eadull, 0x0000011e8084a371ull, + 0x0000012160f11bc6ull, 0x000001244157d7c3ull, 0x0000012721b8d77full, 0x0000012a02141b10ull, + 0x0000012ce269a28eull, 0x0000012fc2b96e0full, 0x00000132a3037daaull, 0x000001358347d177ull, + 0x000001386386698cull, 0x0000013b43bf45ffull, 0x0000013e23f266e9ull, 0x00000141041fcc5eull, + 0x00000143e4477678ull, 0x00000146c469654bull, 0x00000149a48598f0ull, 0x0000014c849c117cull, + 0x0000014f64accf08ull, 0x0000015244b7d1a9ull, 0x0000015524bd1976ull, 0x0000015804bca687ull, + 0x0000015ae4b678f2ull, 0x0000015dc4aa90ceull, 0x00000160a498ee31ull, 0x0000016384819134ull, + 0x00000166646479ecull, 0x000001694441a870ull, 0x0000016c24191cd7ull, 0x0000016df6ca19bdull, + 0x00000171e3b6d7aaull, 0x00000174c37d1e44ull, 0x00000177a33dab1cull, 0x0000017a82f87e49ull, + 0x0000017d62ad97e2ull, 0x00000180425cf7feull, 0x00000182b07f3458ull, 0x0000018601aa8c19ull, + 0x00000188e148c046ull, 0x0000018bc0e13b52ull, 0x0000018ea073fd52ull, 0x000001918001065dull, + 0x000001945f88568bull, 0x000001973f09edf2ull, 0x0000019a1e85ccaaull, 0x0000019cfdfbf2c8ull, + 0x0000019fdd6c6063ull, 0x000001a2bcd71593ull, 0x000001a59c3c126eull, 0x000001a87b9b570bull, + 0x000001ab5af4e380ull, 0x000001ae3a48b7e5ull, 0x000001b11996d450ull, 0x000001b3f8df38d9ull, + 0x000001b6d821e595ull, 0x000001b9b75eda9bull, 0x000001bc96961803ull, 0x000001bf75c79de3ull, + 0x000001c254f36c51ull, 0x000001c534198365ull, 0x000001c81339e336ull, 0x000001caf2548bd9ull, + 0x000001cdd1697d67ull, 0x000001d0b078b7f5ull, 0x000001d38f823b9aull, 0x000001d66e86086dull, + 0x000001d94d841e86ull, 0x000001dc2c7c7df9ull, 0x000001df0b6f26dfull, 0x000001e1ea5c194eull, + 0x000001e4c943555dull, 0x000001e7a824db23ull, 0x000001ea8700aab5ull, 0x000001ed65d6c42bull, + 0x000001f044a7279dull, 0x000001f32371d51full, 0x000001f60236cccaull, 0x000001f8e0f60eb3ull, + 0x000001fbbfaf9af3ull, 0x000001fe9e63719eull, 0x000002017d1192ccull, 0x000002045bb9fe94ull, + 0x000002073a5cb50dull, 0x00000209c06e6212ull, 0x0000020cf791026aull, 0x0000020fd622997cull, + 0x00000212b07f3458ull, 0x000002159334a8d8ull, 0x0000021871b52150ull, 0x0000021b502fe517ull, + 0x0000021d6a73a78full, 0x000002210d144eeeull, 0x00000223eb7df52cull, 0x00000226c9e1e713ull, + 0x00000229a84024bbull, 0x0000022c23679b4eull, 0x0000022f64eb83a8ull, 0x000002324338a51bull, + 0x00000235218012a9ull, 0x00000237ffc1cc69ull, 0x0000023a2c3b0ea4ull, 0x0000023d13ee805bull, + 0x0000024035e9221full, 0x00000243788faf25ull, 0x0000024656b4e735ull, 0x00000247ed646bfeull, + 0x0000024c12ee3d98ull, 0x0000024ef1025c1aull, 0x00000251cf10c799ull, 0x0000025492644d65ull, + 0x000002578b1c85eeull, 0x0000025a6919d8f0ull, 0x0000025d13ee805bull, 0x0000026025036716ull, + 0x0000026296453882ull, 0x00000265e0d62b53ull, 0x00000268beb701f3ull, 0x0000026b9c92265eull, + 0x0000026d32f798a9ull, 0x00000271583758ebull, 0x000002743601673bull, 0x0000027713c5c3b0ull, + 0x00000279f1846e5full, 0x0000027ccf3d6761ull, 0x0000027e6580aecbull, 0x000002828a9e44b3ull, + 0x0000028568462932ull, 0x00000287bdbf5255ull, 0x0000028b2384de4aull, 0x0000028d13ee805bull, + 0x0000029035e9221full, 0x0000029296453882ull, 0x0000029699bdfb61ull, 0x0000029902a37aabull, + 0x0000029c54b864c9ull, 0x0000029deabd1083ull, 0x000002a20f9c0bb5ull, 0x000002a4c7605d61ull, + 0x000002a7bdbf5255ull, 0x000002a96056dafcull, 0x000002ac3daf14efull, 0x000002af1b019ecaull, + 0x000002b296453882ull, 0x000002b5d022d80full, 0x000002b8fa471cb3ull, 0x000002ba9012e713ull, + 0x000002bd6d4901ccull, 0x000002c04a796cf6ull, 0x000002c327a428a6ull, 0x000002c61a5e8f4cull, + 0x000002c8e1e891f6ull, 0x000002cbbf023fc2ull, 0x000002ce9c163e6eull, 0x000002d179248e13ull, + 0x000002d4562d2ec6ull, 0x000002d73330209dull, 0x000002da102d63b0ull, 0x000002dced24f814ull, +}; + + + + +#endif diff --git a/net/ceph/crush/mapper.c b/net/ceph/crush/mapper.c index a1ef53c04415..5b47736d27d9 100644 --- a/net/ceph/crush/mapper.c +++ b/net/ceph/crush/mapper.c @@ -20,7 +20,7 @@ #include <linux/crush/crush.h> #include <linux/crush/hash.h> -#include <linux/crush/mapper.h> +#include "crush_ln_table.h" /* * Implement the core CRUSH mapping algorithm. @@ -238,6 +238,102 @@ static int bucket_straw_choose(struct crush_bucket_straw *bucket, return bucket->h.items[high]; } +// compute 2^44*log2(input+1) +uint64_t crush_ln(unsigned xin) +{ + unsigned x=xin, x1; + int iexpon, index1, index2; + uint64_t RH, LH, LL, xl64, result; + + x++; + + // normalize input + iexpon = 15; + while(!(x&0x18000)) { x<<=1; iexpon--; } + + index1 = (x>>8)<<1; + // RH ~ 2^56/index1 + RH = __RH_LH_tbl[index1 - 256]; + // LH ~ 2^48 * log2(index1/256) + LH = __RH_LH_tbl[index1 + 1 - 256]; + + // RH*x ~ 2^48 * (2^15 + xf), xf<2^8 + xl64 = (int64_t)x * RH; + xl64 >>= 48; + x1 = xl64; + + result = iexpon; + result <<= (12 + 32); + + index2 = x1 & 0xff; + // LL ~ 2^48*log2(1.0+index2/2^15) + LL = __LL_tbl[index2]; + + LH = LH + LL; + + LH >>= (48-12 - 32); + result += LH; + + return result; +} + + +/* + * straw2 + * + * for reference, see: + * + * http://en.wikipedia.org/wiki/Exponential_distribution#Distribution_of_the_minimum_of_exponential_random_variables + * + */ + +static int bucket_straw2_choose(struct crush_bucket_straw2 *bucket, + int x, int r) +{ + unsigned i, high = 0; + unsigned u; + unsigned w; + __s64 ln, draw, high_draw = 0; + + for (i = 0; i < bucket->h.size; i++) { + w = bucket->item_weights[i]; + if (w) { + u = crush_hash32_3(bucket->h.hash, x, + bucket->h.items[i], r); + u &= 0xffff; + + /* + * for some reason slightly less than 0x10000 produces + * a slightly more accurate distribution... probably a + * rounding effect. + * + * the natural log lookup table maps [0,0xffff] + * (corresponding to real numbers [1/0x10000, 1] to + * [0, 0xffffffffffff] (corresponding to real numbers + * [-11.090355,0]). + */ + ln = crush_ln(u) - 0x1000000000000ll; + + /* + * divide by 16.16 fixed-point weight. note + * that the ln value is negative, so a larger + * weight means a larger (less negative) value + * for draw. + */ + draw = div64_s64(ln, w); + } else { + draw = S64_MIN; + } + + if (i == 0 || draw > high_draw) { + high = i; + high_draw = draw; + } + } + return bucket->h.items[high]; +} + + static int crush_bucket_choose(struct crush_bucket *in, int x, int r) { dprintk(" crush_bucket_choose %d x=%d r=%d\n", in->id, x, r); @@ -255,12 +351,16 @@ static int crush_bucket_choose(struct crush_bucket *in, int x, int r) case CRUSH_BUCKET_STRAW: return bucket_straw_choose((struct crush_bucket_straw *)in, x, r); + case CRUSH_BUCKET_STRAW2: + return bucket_straw2_choose((struct crush_bucket_straw2 *)in, + x, r); default: dprintk("unknown bucket %d alg %d\n", in->id, in->alg); return in->items[0]; } } + /* * true if device is marked "out" (failed, fully offloaded) * of the cluster @@ -290,6 +390,7 @@ static int is_out(const struct crush_map *map, * @type: the type of item to choose * @out: pointer to output vector * @outpos: our position in that vector + * @out_size: size of the out vector * @tries: number of attempts to make * @recurse_tries: number of attempts to have recursive chooseleaf make * @local_retries: localized retries @@ -304,6 +405,7 @@ static int crush_choose_firstn(const struct crush_map *map, const __u32 *weight, int weight_max, int x, int numrep, int type, int *out, int outpos, + int out_size, unsigned int tries, unsigned int recurse_tries, unsigned int local_retries, @@ -322,6 +424,7 @@ static int crush_choose_firstn(const struct crush_map *map, int item = 0; int itemtype; int collide, reject; + int count = out_size; dprintk("CHOOSE%s bucket %d x %d outpos %d numrep %d tries %d recurse_tries %d local_retries %d local_fallback_retries %d parent_r %d\n", recurse_to_leaf ? "_LEAF" : "", @@ -329,7 +432,7 @@ static int crush_choose_firstn(const struct crush_map *map, tries, recurse_tries, local_retries, local_fallback_retries, parent_r); - for (rep = outpos; rep < numrep; rep++) { + for (rep = outpos; rep < numrep && count > 0 ; rep++) { /* keep trying until we get a non-out, non-colliding item */ ftotal = 0; skip_rep = 0; @@ -403,7 +506,7 @@ static int crush_choose_firstn(const struct crush_map *map, map->buckets[-1-item], weight, weight_max, x, outpos+1, 0, - out2, outpos, + out2, outpos, count, recurse_tries, 0, local_retries, local_fallback_retries, @@ -463,6 +566,7 @@ reject: dprintk("CHOOSE got %d\n", item); out[outpos] = item; outpos++; + count--; } dprintk("CHOOSE returns %d\n", outpos); @@ -654,6 +758,7 @@ int crush_do_rule(const struct crush_map *map, __u32 step; int i, j; int numrep; + int out_size; /* * the original choose_total_tries value was off by one (it * counted "retries" and not "tries"). add one. @@ -761,6 +866,7 @@ int crush_do_rule(const struct crush_map *map, x, numrep, curstep->arg2, o+osize, j, + result_max-osize, choose_tries, recurse_tries, choose_local_retries, @@ -770,11 +876,13 @@ int crush_do_rule(const struct crush_map *map, c+osize, 0); } else { + out_size = ((numrep < (result_max-osize)) ? + numrep : (result_max-osize)); crush_choose_indep( map, map->buckets[-1-w[i]], weight, weight_max, - x, numrep, numrep, + x, out_size, numrep, curstep->arg2, o+osize, j, choose_tries, @@ -783,7 +891,7 @@ int crush_do_rule(const struct crush_map *map, recurse_to_leaf, c+osize, 0); - osize += numrep; + osize += out_size; } } diff --git a/net/ceph/debugfs.c b/net/ceph/debugfs.c index 14d9995097cc..593dc2eabcc8 100644 --- a/net/ceph/debugfs.c +++ b/net/ceph/debugfs.c @@ -22,6 +22,7 @@ * .../monmap - current monmap * .../osdc - active osd requests * .../monc - mon client state + * .../client_options - libceph-only (i.e. not rbd or cephfs) options * .../dentry_lru - dump contents of dentry lru * .../caps - expose cap (reservation) stats * .../bdi - symlink to ../../bdi/something @@ -177,10 +178,24 @@ static int osdc_show(struct seq_file *s, void *pp) return 0; } +static int client_options_show(struct seq_file *s, void *p) +{ + struct ceph_client *client = s->private; + int ret; + + ret = ceph_print_client_options(s, client); + if (ret) + return ret; + + seq_putc(s, '\n'); + return 0; +} + CEPH_DEFINE_SHOW_FUNC(monmap_show) CEPH_DEFINE_SHOW_FUNC(osdmap_show) CEPH_DEFINE_SHOW_FUNC(monc_show) CEPH_DEFINE_SHOW_FUNC(osdc_show) +CEPH_DEFINE_SHOW_FUNC(client_options_show) int ceph_debugfs_init(void) { @@ -242,6 +257,14 @@ int ceph_debugfs_client_init(struct ceph_client *client) if (!client->debugfs_osdmap) goto out; + client->debugfs_options = debugfs_create_file("client_options", + 0600, + client->debugfs_dir, + client, + &client_options_show_fops); + if (!client->debugfs_options) + goto out; + return 0; out: @@ -252,6 +275,7 @@ out: void ceph_debugfs_client_cleanup(struct ceph_client *client) { dout("ceph_debugfs_client_cleanup %p\n", client); + debugfs_remove(client->debugfs_options); debugfs_remove(client->debugfs_osdmap); debugfs_remove(client->debugfs_monmap); debugfs_remove(client->osdc.debugfs_file); diff --git a/net/ceph/messenger.c b/net/ceph/messenger.c index a9f4ae45b7fb..967080a9f043 100644 --- a/net/ceph/messenger.c +++ b/net/ceph/messenger.c @@ -505,8 +505,6 @@ static int ceph_tcp_connect(struct ceph_connection *con) pr_err("connect %s error %d\n", ceph_pr_addr(&con->peer_addr.in_addr), ret); sock_release(sock); - con->error_msg = "connect error"; - return ret; } @@ -2145,12 +2143,10 @@ static int process_connect(struct ceph_connection *con) * to WAIT. This shouldn't happen if we are the * client. */ - pr_err("process_connect got WAIT as client\n"); con->error_msg = "protocol error, got WAIT as client"; return -1; default: - pr_err("connect protocol error, will retry\n"); con->error_msg = "protocol error, garbage tag during connect"; return -1; } @@ -2282,8 +2278,7 @@ static int read_partial_message(struct ceph_connection *con) crc = crc32c(0, &con->in_hdr, offsetof(struct ceph_msg_header, crc)); if (cpu_to_le32(crc) != con->in_hdr.crc) { - pr_err("read_partial_message bad hdr " - " crc %u != expected %u\n", + pr_err("read_partial_message bad hdr crc %u != expected %u\n", crc, con->in_hdr.crc); return -EBADMSG; } @@ -2313,7 +2308,7 @@ static int read_partial_message(struct ceph_connection *con) pr_err("read_partial_message bad seq %lld expected %lld\n", seq, con->in_seq + 1); con->error_msg = "bad message sequence # for incoming message"; - return -EBADMSG; + return -EBADE; } /* allocate message? */ @@ -2660,6 +2655,8 @@ more: switch (ret) { case -EBADMSG: con->error_msg = "bad crc"; + /* fall through */ + case -EBADE: ret = -EIO; break; case -EIO: @@ -2838,7 +2835,8 @@ static void con_work(struct work_struct *work) if (ret < 0) { if (ret == -EAGAIN) continue; - con->error_msg = "socket error on read"; + if (!con->error_msg) + con->error_msg = "socket error on read"; fault = true; break; } @@ -2847,7 +2845,8 @@ static void con_work(struct work_struct *work) if (ret < 0) { if (ret == -EAGAIN) continue; - con->error_msg = "socket error on write"; + if (!con->error_msg) + con->error_msg = "socket error on write"; fault = true; } @@ -2869,11 +2868,13 @@ static void con_work(struct work_struct *work) */ static void con_fault(struct ceph_connection *con) { - pr_warn("%s%lld %s %s\n", ENTITY_NAME(con->peer_name), - ceph_pr_addr(&con->peer_addr.in_addr), con->error_msg); dout("fault %p state %lu to peer %s\n", con, con->state, ceph_pr_addr(&con->peer_addr.in_addr)); + pr_warn("%s%lld %s %s\n", ENTITY_NAME(con->peer_name), + ceph_pr_addr(&con->peer_addr.in_addr), con->error_msg); + con->error_msg = NULL; + WARN_ON(con->state != CON_STATE_CONNECTING && con->state != CON_STATE_NEGOTIATING && con->state != CON_STATE_OPEN); @@ -3295,8 +3296,8 @@ static int ceph_con_in_msg_alloc(struct ceph_connection *con, int *skip) */ if (*skip) return 0; - con->error_msg = "error allocating memory for incoming message"; + con->error_msg = "error allocating memory for incoming message"; return -ENOMEM; } memcpy(&con->in_msg->hdr, &con->in_hdr, sizeof(con->in_hdr)); diff --git a/net/ceph/osdmap.c b/net/ceph/osdmap.c index b8c3fde5b04f..15796696d64e 100644 --- a/net/ceph/osdmap.c +++ b/net/ceph/osdmap.c @@ -122,6 +122,22 @@ bad: return -EINVAL; } +static int crush_decode_straw2_bucket(void **p, void *end, + struct crush_bucket_straw2 *b) +{ + int j; + dout("crush_decode_straw2_bucket %p to %p\n", *p, end); + b->item_weights = kcalloc(b->h.size, sizeof(u32), GFP_NOFS); + if (b->item_weights == NULL) + return -ENOMEM; + ceph_decode_need(p, end, b->h.size * sizeof(u32), bad); + for (j = 0; j < b->h.size; j++) + b->item_weights[j] = ceph_decode_32(p); + return 0; +bad: + return -EINVAL; +} + static int skip_name_map(void **p, void *end) { int len; @@ -204,6 +220,9 @@ static struct crush_map *crush_decode(void *pbyval, void *end) case CRUSH_BUCKET_STRAW: size = sizeof(struct crush_bucket_straw); break; + case CRUSH_BUCKET_STRAW2: + size = sizeof(struct crush_bucket_straw2); + break; default: err = -EINVAL; goto bad; @@ -261,6 +280,12 @@ static struct crush_map *crush_decode(void *pbyval, void *end) if (err < 0) goto bad; break; + case CRUSH_BUCKET_STRAW2: + err = crush_decode_straw2_bucket(p, end, + (struct crush_bucket_straw2 *)b); + if (err < 0) + goto bad; + break; } } diff --git a/net/compat.c b/net/compat.c index f7bd286a8280..5cfd26a0006f 100644 --- a/net/compat.c +++ b/net/compat.c @@ -31,10 +31,10 @@ #include <asm/uaccess.h> #include <net/compat.h> -ssize_t get_compat_msghdr(struct msghdr *kmsg, - struct compat_msghdr __user *umsg, - struct sockaddr __user **save_addr, - struct iovec **iov) +int get_compat_msghdr(struct msghdr *kmsg, + struct compat_msghdr __user *umsg, + struct sockaddr __user **save_addr, + struct iovec **iov) { compat_uptr_t uaddr, uiov, tmp3; compat_size_t nr_segs; @@ -79,13 +79,11 @@ ssize_t get_compat_msghdr(struct msghdr *kmsg, if (nr_segs > UIO_MAXIOV) return -EMSGSIZE; - err = compat_rw_copy_check_uvector(save_addr ? READ : WRITE, - compat_ptr(uiov), nr_segs, - UIO_FASTIOV, *iov, iov); - if (err >= 0) - iov_iter_init(&kmsg->msg_iter, save_addr ? READ : WRITE, - *iov, nr_segs, err); - return err; + kmsg->msg_iocb = NULL; + + return compat_import_iovec(save_addr ? READ : WRITE, + compat_ptr(uiov), nr_segs, + UIO_FASTIOV, iov, &kmsg->msg_iter); } /* Bleech... */ @@ -515,25 +513,25 @@ COMPAT_SYSCALL_DEFINE5(getsockopt, int, fd, int, level, int, optname, struct compat_group_req { __u32 gr_interface; struct __kernel_sockaddr_storage gr_group - __attribute__ ((aligned(4))); + __aligned(4); } __packed; struct compat_group_source_req { __u32 gsr_interface; struct __kernel_sockaddr_storage gsr_group - __attribute__ ((aligned(4))); + __aligned(4); struct __kernel_sockaddr_storage gsr_source - __attribute__ ((aligned(4))); + __aligned(4); } __packed; struct compat_group_filter { __u32 gf_interface; struct __kernel_sockaddr_storage gf_group - __attribute__ ((aligned(4))); + __aligned(4); __u32 gf_fmode; __u32 gf_numsrc; struct __kernel_sockaddr_storage gf_slist[1] - __attribute__ ((aligned(4))); + __aligned(4); } __packed; #define __COMPAT_GF0_SIZE (sizeof(struct compat_group_filter) - \ diff --git a/net/core/datagram.c b/net/core/datagram.c index df493d68330c..b80fb91bb3f7 100644 --- a/net/core/datagram.c +++ b/net/core/datagram.c @@ -673,7 +673,7 @@ int skb_copy_and_csum_datagram_msg(struct sk_buff *skb, if (!chunk) return 0; - if (iov_iter_count(&msg->msg_iter) < chunk) { + if (msg_data_left(msg) < chunk) { if (__skb_checksum_complete(skb)) goto csum_error; if (skb_copy_datagram_msg(skb, hlen, msg, chunk)) diff --git a/net/core/dev.c b/net/core/dev.c index 45109b70664e..c7ba0388f1be 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -660,6 +660,27 @@ __setup("netdev=", netdev_boot_setup); *******************************************************************************/ /** + * dev_get_iflink - get 'iflink' value of a interface + * @dev: targeted interface + * + * Indicates the ifindex the interface is linked to. + * Physical interfaces have the same 'ifindex' and 'iflink' values. + */ + +int dev_get_iflink(const struct net_device *dev) +{ + if (dev->netdev_ops && dev->netdev_ops->ndo_get_iflink) + return dev->netdev_ops->ndo_get_iflink(dev); + + /* If dev->rtnl_link_ops is set, it's a virtual interface. */ + if (dev->rtnl_link_ops) + return 0; + + return dev->ifindex; +} +EXPORT_SYMBOL(dev_get_iflink); + +/** * __dev_get_by_name - find a device by its name * @net: the applicable net namespace * @name: name to find @@ -1385,7 +1406,7 @@ static int __dev_close(struct net_device *dev) return retval; } -static int dev_close_many(struct list_head *head) +int dev_close_many(struct list_head *head, bool unlink) { struct net_device *dev, *tmp; @@ -1399,11 +1420,13 @@ static int dev_close_many(struct list_head *head) list_for_each_entry_safe(dev, tmp, head, close_list) { rtmsg_ifinfo(RTM_NEWLINK, dev, IFF_UP|IFF_RUNNING, GFP_KERNEL); call_netdevice_notifiers(NETDEV_DOWN, dev); - list_del_init(&dev->close_list); + if (unlink) + list_del_init(&dev->close_list); } return 0; } +EXPORT_SYMBOL(dev_close_many); /** * dev_close - shutdown an interface. @@ -1420,7 +1443,7 @@ int dev_close(struct net_device *dev) LIST_HEAD(single); list_add(&dev->close_list, &single); - dev_close_many(&single); + dev_close_many(&single, true); list_del(&single); } return 0; @@ -1607,6 +1630,22 @@ int call_netdevice_notifiers(unsigned long val, struct net_device *dev) } EXPORT_SYMBOL(call_netdevice_notifiers); +#ifdef CONFIG_NET_CLS_ACT +static struct static_key ingress_needed __read_mostly; + +void net_inc_ingress_queue(void) +{ + static_key_slow_inc(&ingress_needed); +} +EXPORT_SYMBOL_GPL(net_inc_ingress_queue); + +void net_dec_ingress_queue(void) +{ + static_key_slow_dec(&ingress_needed); +} +EXPORT_SYMBOL_GPL(net_dec_ingress_queue); +#endif + static struct static_key netstamp_needed __read_mostly; #ifdef HAVE_JUMP_LABEL /* We are not allowed to call static_key_slow_dec() from irq context @@ -1694,6 +1733,7 @@ int __dev_forward_skb(struct net_device *dev, struct sk_buff *skb) } skb_scrub_packet(skb, true); + skb->priority = 0; skb->protocol = eth_type_trans(skb, dev); skb_postpull_rcsum(skb, eth_hdr(skb), ETH_HLEN); @@ -1737,7 +1777,8 @@ static inline int deliver_skb(struct sk_buff *skb, static inline void deliver_ptype_list_skb(struct sk_buff *skb, struct packet_type **pt, - struct net_device *dev, __be16 type, + struct net_device *orig_dev, + __be16 type, struct list_head *ptype_list) { struct packet_type *ptype, *pt_prev = *pt; @@ -1746,7 +1787,7 @@ static inline void deliver_ptype_list_skb(struct sk_buff *skb, if (ptype->type != type) continue; if (pt_prev) - deliver_skb(skb, pt_prev, dev); + deliver_skb(skb, pt_prev, orig_dev); pt_prev = ptype; } *pt = pt_prev; @@ -2559,12 +2600,26 @@ static netdev_features_t harmonize_features(struct sk_buff *skb, return features; } +netdev_features_t passthru_features_check(struct sk_buff *skb, + struct net_device *dev, + netdev_features_t features) +{ + return features; +} +EXPORT_SYMBOL(passthru_features_check); + +static netdev_features_t dflt_features_check(const struct sk_buff *skb, + struct net_device *dev, + netdev_features_t features) +{ + return vlan_features_check(skb, features); +} + netdev_features_t netif_skb_features(struct sk_buff *skb) { struct net_device *dev = skb->dev; netdev_features_t features = dev->features; u16 gso_segs = skb_shinfo(skb)->gso_segs; - __be16 protocol = skb->protocol; if (gso_segs > dev->gso_max_segs || gso_segs < dev->gso_min_segs) features &= ~NETIF_F_GSO_MASK; @@ -2576,34 +2631,17 @@ netdev_features_t netif_skb_features(struct sk_buff *skb) if (skb->encapsulation) features &= dev->hw_enc_features; - if (!skb_vlan_tag_present(skb)) { - if (unlikely(protocol == htons(ETH_P_8021Q) || - protocol == htons(ETH_P_8021AD))) { - struct vlan_ethhdr *veh = (struct vlan_ethhdr *)skb->data; - protocol = veh->h_vlan_encapsulated_proto; - } else { - goto finalize; - } - } - - features = netdev_intersect_features(features, - dev->vlan_features | - NETIF_F_HW_VLAN_CTAG_TX | - NETIF_F_HW_VLAN_STAG_TX); - - if (protocol == htons(ETH_P_8021Q) || protocol == htons(ETH_P_8021AD)) + if (skb_vlan_tagged(skb)) features = netdev_intersect_features(features, - NETIF_F_SG | - NETIF_F_HIGHDMA | - NETIF_F_FRAGLIST | - NETIF_F_GEN_CSUM | + dev->vlan_features | NETIF_F_HW_VLAN_CTAG_TX | NETIF_F_HW_VLAN_STAG_TX); -finalize: if (dev->netdev_ops->ndo_features_check) features &= dev->netdev_ops->ndo_features_check(skb, dev, features); + else + features &= dflt_features_check(skb, dev, features); return harmonize_features(skb, features); } @@ -2675,7 +2713,7 @@ static struct sk_buff *validate_xmit_skb(struct sk_buff *skb, struct net_device if (unlikely(!skb)) goto out_null; - if (netif_needs_gso(dev, skb, features)) { + if (netif_needs_gso(skb, features)) { struct sk_buff *segs; segs = skb_gso_segment(skb, features); @@ -2857,7 +2895,7 @@ EXPORT_SYMBOL(xmit_recursion); * dev_loopback_xmit - loop back @skb * @skb: buffer to transmit */ -int dev_loopback_xmit(struct sk_buff *skb) +int dev_loopback_xmit(struct sock *sk, struct sk_buff *skb) { skb_reset_mac_header(skb); __skb_pull(skb, skb_network_offset(skb)); @@ -2995,11 +3033,11 @@ out: return rc; } -int dev_queue_xmit(struct sk_buff *skb) +int dev_queue_xmit_sk(struct sock *sk, struct sk_buff *skb) { return __dev_queue_xmit(skb, NULL); } -EXPORT_SYMBOL(dev_queue_xmit); +EXPORT_SYMBOL(dev_queue_xmit_sk); int dev_queue_xmit_accel(struct sk_buff *skb, void *accel_priv) { @@ -3041,7 +3079,7 @@ static struct rps_dev_flow * set_rps_cpu(struct net_device *dev, struct sk_buff *skb, struct rps_dev_flow *rflow, u16 next_cpu) { - if (next_cpu != RPS_NO_CPU) { + if (next_cpu < nr_cpu_ids) { #ifdef CONFIG_RFS_ACCEL struct netdev_rx_queue *rxqueue; struct rps_dev_flow_table *flow_table; @@ -3146,7 +3184,7 @@ static int get_rps_cpu(struct net_device *dev, struct sk_buff *skb, * If the desired CPU (where last recvmsg was done) is * different from current CPU (one in the rx-queue flow * table entry), switch if one of the following holds: - * - Current CPU is unset (equal to RPS_NO_CPU). + * - Current CPU is unset (>= nr_cpu_ids). * - Current CPU is offline. * - The current CPU's queue tail has advanced beyond the * last packet that was enqueued using this table entry. @@ -3154,14 +3192,14 @@ static int get_rps_cpu(struct net_device *dev, struct sk_buff *skb, * have been dequeued, thus preserving in order delivery. */ if (unlikely(tcpu != next_cpu) && - (tcpu == RPS_NO_CPU || !cpu_online(tcpu) || + (tcpu >= nr_cpu_ids || !cpu_online(tcpu) || ((int)(per_cpu(softnet_data, tcpu).input_queue_head - rflow->last_qtail)) >= 0)) { tcpu = next_cpu; rflow = set_rps_cpu(dev, skb, rflow, next_cpu); } - if (tcpu != RPS_NO_CPU && cpu_online(tcpu)) { + if (tcpu < nr_cpu_ids && cpu_online(tcpu)) { *rflowp = rflow; cpu = tcpu; goto done; @@ -3202,14 +3240,14 @@ bool rps_may_expire_flow(struct net_device *dev, u16 rxq_index, struct rps_dev_flow_table *flow_table; struct rps_dev_flow *rflow; bool expire = true; - int cpu; + unsigned int cpu; rcu_read_lock(); flow_table = rcu_dereference(rxqueue->rps_flow_table); if (flow_table && flow_id <= flow_table->mask) { rflow = &flow_table->flows[flow_id]; cpu = ACCESS_ONCE(rflow->cpu); - if (rflow->filter == filter_id && cpu != RPS_NO_CPU && + if (rflow->filter == filter_id && cpu < nr_cpu_ids && ((int)(per_cpu(softnet_data, cpu).input_queue_head - rflow->last_qtail) < (int)(10 * flow_table->mask))) @@ -3525,7 +3563,7 @@ static inline struct sk_buff *handle_ing(struct sk_buff *skb, struct netdev_queue *rxq = rcu_dereference(skb->dev->ingress_queue); if (!rxq || rcu_access_pointer(rxq->qdisc) == &noop_qdisc) - goto out; + return skb; if (*pt_prev) { *ret = deliver_skb(skb, *pt_prev, orig_dev); @@ -3539,8 +3577,6 @@ static inline struct sk_buff *handle_ing(struct sk_buff *skb, return NULL; } -out: - skb->tc_verd = 0; return skb; } #endif @@ -3676,12 +3712,15 @@ another_round: skip_taps: #ifdef CONFIG_NET_CLS_ACT - skb = handle_ing(skb, &pt_prev, &ret, orig_dev); - if (!skb) - goto unlock; + if (static_key_false(&ingress_needed)) { + skb = handle_ing(skb, &pt_prev, &ret, orig_dev); + if (!skb) + goto unlock; + } + + skb->tc_verd = 0; ncls: #endif - if (pfmemalloc && !skb_pfmemalloc_protocol(skb)) goto drop; @@ -3831,13 +3870,13 @@ static int netif_receive_skb_internal(struct sk_buff *skb) * NET_RX_SUCCESS: no congestion * NET_RX_DROP: packet was dropped */ -int netif_receive_skb(struct sk_buff *skb) +int netif_receive_skb_sk(struct sock *sk, struct sk_buff *skb) { trace_netif_receive_skb_entry(skb); return netif_receive_skb_internal(skb); } -EXPORT_SYMBOL(netif_receive_skb); +EXPORT_SYMBOL(netif_receive_skb_sk); /* Network device is going away, flush any packets still pending * Called with irqs disabled. @@ -5914,6 +5953,24 @@ int dev_get_phys_port_id(struct net_device *dev, EXPORT_SYMBOL(dev_get_phys_port_id); /** + * dev_get_phys_port_name - Get device physical port name + * @dev: device + * @name: port name + * + * Get device physical port name + */ +int dev_get_phys_port_name(struct net_device *dev, + char *name, size_t len) +{ + const struct net_device_ops *ops = dev->netdev_ops; + + if (!ops->ndo_get_phys_port_name) + return -EOPNOTSUPP; + return ops->ndo_get_phys_port_name(dev, name, len); +} +EXPORT_SYMBOL(dev_get_phys_port_name); + +/** * dev_new_index - allocate an ifindex * @net: the applicable net namespace * @@ -5970,7 +6027,7 @@ static void rollback_registered_many(struct list_head *head) /* If device is running, close it first. */ list_for_each_entry(dev, head, unreg_list) list_add_tail(&dev->close_list, &close_head); - dev_close_many(&close_head); + dev_close_many(&close_head, true); list_for_each_entry(dev, head, unreg_list) { /* And unlink it from device chain. */ @@ -6297,8 +6354,6 @@ int register_netdevice(struct net_device *dev) spin_lock_init(&dev->addr_list_lock); netdev_set_addr_lockdep_class(dev); - dev->iflink = -1; - ret = dev_get_valid_name(net, dev, dev->name); if (ret < 0) goto out; @@ -6328,9 +6383,6 @@ int register_netdevice(struct net_device *dev) else if (__dev_get_by_index(net, dev->ifindex)) goto err_uninit; - if (dev->iflink == -1) - dev->iflink = dev->ifindex; - /* Transfer changeable features to wanted_features and enable * software offloads (GSO and GRO). */ @@ -6843,8 +6895,6 @@ void free_netdev(struct net_device *dev) { struct napi_struct *p, *n; - release_net(dev_net(dev)); - netif_free_tx_queues(dev); #ifdef CONFIG_SYSFS kvfree(dev->_rx); @@ -7045,12 +7095,8 @@ int dev_change_net_namespace(struct net_device *dev, struct net *net, const char dev_net_set(dev, net); /* If there is an ifindex conflict assign a new one */ - if (__dev_get_by_index(net, dev->ifindex)) { - int iflink = (dev->iflink == dev->ifindex); + if (__dev_get_by_index(net, dev->ifindex)) dev->ifindex = dev_new_index(net); - if (iflink) - dev->iflink = dev->ifindex; - } /* Send a netdev-add uevent to the new namespace */ kobject_uevent(&dev->dev.kobj, KOBJ_ADD); diff --git a/net/core/ethtool.c b/net/core/ethtool.c index aa378ecef186..1d00b8922902 100644 --- a/net/core/ethtool.c +++ b/net/core/ethtool.c @@ -790,7 +790,7 @@ static noinline_for_stack int ethtool_set_rxfh(struct net_device *dev, if (ops->get_rxfh_indir_size) dev_indir_size = ops->get_rxfh_indir_size(dev); if (ops->get_rxfh_key_size) - dev_key_size = dev->ethtool_ops->get_rxfh_key_size(dev); + dev_key_size = ops->get_rxfh_key_size(dev); if (copy_from_user(&rxfh, useraddr, sizeof(rxfh))) return -EFAULT; diff --git a/net/core/fib_rules.c b/net/core/fib_rules.c index e4fdc9dfb2c7..9a12668f7d62 100644 --- a/net/core/fib_rules.c +++ b/net/core/fib_rules.c @@ -31,7 +31,7 @@ int fib_default_rule_add(struct fib_rules_ops *ops, r->pref = pref; r->table = table; r->flags = flags; - r->fr_net = hold_net(ops->fro_net); + r->fr_net = ops->fro_net; r->suppress_prefixlen = -1; r->suppress_ifgroup = -1; @@ -116,7 +116,6 @@ static int __fib_rules_register(struct fib_rules_ops *ops) if (ops->family == o->family) goto errout; - hold_net(net); list_add_tail_rcu(&ops->list, &net->rules_ops); err = 0; errout: @@ -160,15 +159,6 @@ static void fib_rules_cleanup_ops(struct fib_rules_ops *ops) } } -static void fib_rules_put_rcu(struct rcu_head *head) -{ - struct fib_rules_ops *ops = container_of(head, struct fib_rules_ops, rcu); - struct net *net = ops->fro_net; - - release_net(net); - kfree(ops); -} - void fib_rules_unregister(struct fib_rules_ops *ops) { struct net *net = ops->fro_net; @@ -178,7 +168,7 @@ void fib_rules_unregister(struct fib_rules_ops *ops) spin_unlock(&net->rules_mod_lock); fib_rules_cleanup_ops(ops); - call_rcu(&ops->rcu, fib_rules_put_rcu); + kfree_rcu(ops, rcu); } EXPORT_SYMBOL_GPL(fib_rules_unregister); @@ -303,7 +293,7 @@ static int fib_nl_newrule(struct sk_buff *skb, struct nlmsghdr* nlh) err = -ENOMEM; goto errout; } - rule->fr_net = hold_net(net); + rule->fr_net = net; if (tb[FRA_PRIORITY]) rule->pref = nla_get_u32(tb[FRA_PRIORITY]); @@ -423,7 +413,6 @@ static int fib_nl_newrule(struct sk_buff *skb, struct nlmsghdr* nlh) return 0; errout_free: - release_net(rule->fr_net); kfree(rule); errout: rules_ops_put(ops); @@ -492,6 +481,12 @@ static int fib_nl_delrule(struct sk_buff *skb, struct nlmsghdr* nlh) goto errout; } + if (ops->delete) { + err = ops->delete(rule); + if (err) + goto errout; + } + list_del_rcu(&rule->list); if (rule->action == FR_ACT_GOTO) { @@ -517,8 +512,6 @@ static int fib_nl_delrule(struct sk_buff *skb, struct nlmsghdr* nlh) notify_rule_change(RTM_DELRULE, rule, ops, nlh, NETLINK_CB(skb).portid); - if (ops->delete) - ops->delete(rule); fib_rule_put(rule); flush_route_cache(ops); rules_ops_put(ops); diff --git a/net/core/filter.c b/net/core/filter.c index f6bdc2b1ba01..bf831a85c315 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -150,10 +150,62 @@ static u64 __get_random_u32(u64 ctx, u64 a, u64 x, u64 r4, u64 r5) return prandom_u32(); } +static u32 convert_skb_access(int skb_field, int dst_reg, int src_reg, + struct bpf_insn *insn_buf) +{ + struct bpf_insn *insn = insn_buf; + + switch (skb_field) { + case SKF_AD_MARK: + BUILD_BUG_ON(FIELD_SIZEOF(struct sk_buff, mark) != 4); + + *insn++ = BPF_LDX_MEM(BPF_W, dst_reg, src_reg, + offsetof(struct sk_buff, mark)); + break; + + case SKF_AD_PKTTYPE: + *insn++ = BPF_LDX_MEM(BPF_B, dst_reg, src_reg, PKT_TYPE_OFFSET()); + *insn++ = BPF_ALU32_IMM(BPF_AND, dst_reg, PKT_TYPE_MAX); +#ifdef __BIG_ENDIAN_BITFIELD + *insn++ = BPF_ALU32_IMM(BPF_RSH, dst_reg, 5); +#endif + break; + + case SKF_AD_QUEUE: + BUILD_BUG_ON(FIELD_SIZEOF(struct sk_buff, queue_mapping) != 2); + + *insn++ = BPF_LDX_MEM(BPF_H, dst_reg, src_reg, + offsetof(struct sk_buff, queue_mapping)); + break; + + case SKF_AD_VLAN_TAG: + case SKF_AD_VLAN_TAG_PRESENT: + BUILD_BUG_ON(FIELD_SIZEOF(struct sk_buff, vlan_tci) != 2); + BUILD_BUG_ON(VLAN_TAG_PRESENT != 0x1000); + + /* dst_reg = *(u16 *) (src_reg + offsetof(vlan_tci)) */ + *insn++ = BPF_LDX_MEM(BPF_H, dst_reg, src_reg, + offsetof(struct sk_buff, vlan_tci)); + if (skb_field == SKF_AD_VLAN_TAG) { + *insn++ = BPF_ALU32_IMM(BPF_AND, dst_reg, + ~VLAN_TAG_PRESENT); + } else { + /* dst_reg >>= 12 */ + *insn++ = BPF_ALU32_IMM(BPF_RSH, dst_reg, 12); + /* dst_reg &= 1 */ + *insn++ = BPF_ALU32_IMM(BPF_AND, dst_reg, 1); + } + break; + } + + return insn - insn_buf; +} + static bool convert_bpf_extensions(struct sock_filter *fp, struct bpf_insn **insnp) { struct bpf_insn *insn = *insnp; + u32 cnt; switch (fp->k) { case SKF_AD_OFF + SKF_AD_PROTOCOL: @@ -167,13 +219,8 @@ static bool convert_bpf_extensions(struct sock_filter *fp, break; case SKF_AD_OFF + SKF_AD_PKTTYPE: - *insn++ = BPF_LDX_MEM(BPF_B, BPF_REG_A, BPF_REG_CTX, - PKT_TYPE_OFFSET()); - *insn = BPF_ALU32_IMM(BPF_AND, BPF_REG_A, PKT_TYPE_MAX); -#ifdef __BIG_ENDIAN_BITFIELD - insn++; - *insn = BPF_ALU32_IMM(BPF_RSH, BPF_REG_A, 5); -#endif + cnt = convert_skb_access(SKF_AD_PKTTYPE, BPF_REG_A, BPF_REG_CTX, insn); + insn += cnt - 1; break; case SKF_AD_OFF + SKF_AD_IFINDEX: @@ -197,10 +244,8 @@ static bool convert_bpf_extensions(struct sock_filter *fp, break; case SKF_AD_OFF + SKF_AD_MARK: - BUILD_BUG_ON(FIELD_SIZEOF(struct sk_buff, mark) != 4); - - *insn = BPF_LDX_MEM(BPF_W, BPF_REG_A, BPF_REG_CTX, - offsetof(struct sk_buff, mark)); + cnt = convert_skb_access(SKF_AD_MARK, BPF_REG_A, BPF_REG_CTX, insn); + insn += cnt - 1; break; case SKF_AD_OFF + SKF_AD_RXHASH: @@ -211,29 +256,30 @@ static bool convert_bpf_extensions(struct sock_filter *fp, break; case SKF_AD_OFF + SKF_AD_QUEUE: - BUILD_BUG_ON(FIELD_SIZEOF(struct sk_buff, queue_mapping) != 2); - - *insn = BPF_LDX_MEM(BPF_H, BPF_REG_A, BPF_REG_CTX, - offsetof(struct sk_buff, queue_mapping)); + cnt = convert_skb_access(SKF_AD_QUEUE, BPF_REG_A, BPF_REG_CTX, insn); + insn += cnt - 1; break; case SKF_AD_OFF + SKF_AD_VLAN_TAG: + cnt = convert_skb_access(SKF_AD_VLAN_TAG, + BPF_REG_A, BPF_REG_CTX, insn); + insn += cnt - 1; + break; + case SKF_AD_OFF + SKF_AD_VLAN_TAG_PRESENT: - BUILD_BUG_ON(FIELD_SIZEOF(struct sk_buff, vlan_tci) != 2); - BUILD_BUG_ON(VLAN_TAG_PRESENT != 0x1000); + cnt = convert_skb_access(SKF_AD_VLAN_TAG_PRESENT, + BPF_REG_A, BPF_REG_CTX, insn); + insn += cnt - 1; + break; - /* A = *(u16 *) (CTX + offsetof(vlan_tci)) */ + case SKF_AD_OFF + SKF_AD_VLAN_TPID: + BUILD_BUG_ON(FIELD_SIZEOF(struct sk_buff, vlan_proto) != 2); + + /* A = *(u16 *) (CTX + offsetof(vlan_proto)) */ *insn++ = BPF_LDX_MEM(BPF_H, BPF_REG_A, BPF_REG_CTX, - offsetof(struct sk_buff, vlan_tci)); - if (fp->k == SKF_AD_OFF + SKF_AD_VLAN_TAG) { - *insn = BPF_ALU32_IMM(BPF_AND, BPF_REG_A, - ~VLAN_TAG_PRESENT); - } else { - /* A >>= 12 */ - *insn++ = BPF_ALU32_IMM(BPF_RSH, BPF_REG_A, 12); - /* A &= 1 */ - *insn = BPF_ALU32_IMM(BPF_AND, BPF_REG_A, 1); - } + offsetof(struct sk_buff, vlan_proto)); + /* A = ntohs(A) [emitting a nop or swap16] */ + *insn = BPF_ENDIAN(BPF_FROM_BE, BPF_REG_A, 16); break; case SKF_AD_OFF + SKF_AD_PAY_OFFSET: @@ -814,7 +860,7 @@ static void bpf_release_orig_filter(struct bpf_prog *fp) static void __bpf_prog_release(struct bpf_prog *prog) { - if (prog->aux->prog_type == BPF_PROG_TYPE_SOCKET_FILTER) { + if (prog->type == BPF_PROG_TYPE_SOCKET_FILTER) { bpf_prog_put(prog); } else { bpf_release_orig_filter(prog); @@ -1019,6 +1065,32 @@ void bpf_prog_destroy(struct bpf_prog *fp) } EXPORT_SYMBOL_GPL(bpf_prog_destroy); +static int __sk_attach_prog(struct bpf_prog *prog, struct sock *sk) +{ + struct sk_filter *fp, *old_fp; + + fp = kmalloc(sizeof(*fp), GFP_KERNEL); + if (!fp) + return -ENOMEM; + + fp->prog = prog; + atomic_set(&fp->refcnt, 0); + + if (!sk_filter_charge(sk, fp)) { + kfree(fp); + return -ENOMEM; + } + + old_fp = rcu_dereference_protected(sk->sk_filter, + sock_owned_by_user(sk)); + rcu_assign_pointer(sk->sk_filter, fp); + + if (old_fp) + sk_filter_uncharge(sk, old_fp); + + return 0; +} + /** * sk_attach_filter - attach a socket filter * @fprog: the filter program @@ -1031,7 +1103,6 @@ EXPORT_SYMBOL_GPL(bpf_prog_destroy); */ int sk_attach_filter(struct sock_fprog *fprog, struct sock *sk) { - struct sk_filter *fp, *old_fp; unsigned int fsize = bpf_classic_proglen(fprog); unsigned int bpf_fsize = bpf_prog_size(fprog->len); struct bpf_prog *prog; @@ -1068,36 +1139,20 @@ int sk_attach_filter(struct sock_fprog *fprog, struct sock *sk) if (IS_ERR(prog)) return PTR_ERR(prog); - fp = kmalloc(sizeof(*fp), GFP_KERNEL); - if (!fp) { + err = __sk_attach_prog(prog, sk); + if (err < 0) { __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; + return err; } - old_fp = rcu_dereference_protected(sk->sk_filter, - sock_owned_by_user(sk)); - rcu_assign_pointer(sk->sk_filter, fp); - - if (old_fp) - sk_filter_uncharge(sk, old_fp); - return 0; } EXPORT_SYMBOL_GPL(sk_attach_filter); -#ifdef CONFIG_BPF_SYSCALL int sk_attach_bpf(u32 ufd, struct sock *sk) { - struct sk_filter *fp, *old_fp; struct bpf_prog *prog; + int err; if (sock_flag(sk, SOCK_FILTER_LOCKED)) return -EPERM; @@ -1106,40 +1161,191 @@ int sk_attach_bpf(u32 ufd, struct sock *sk) if (IS_ERR(prog)) return PTR_ERR(prog); - if (prog->aux->prog_type != BPF_PROG_TYPE_SOCKET_FILTER) { - /* valid fd, but invalid program type */ + if (prog->type != BPF_PROG_TYPE_SOCKET_FILTER) { bpf_prog_put(prog); return -EINVAL; } - fp = kmalloc(sizeof(*fp), GFP_KERNEL); - if (!fp) { + err = __sk_attach_prog(prog, sk); + if (err < 0) { bpf_prog_put(prog); - return -ENOMEM; + return err; } - fp->prog = prog; - atomic_set(&fp->refcnt, 0); + return 0; +} - if (!sk_filter_charge(sk, fp)) { - __sk_filter_release(fp); - return -ENOMEM; +/** + * bpf_skb_clone_not_writable - is the header of a clone not writable + * @skb: buffer to check + * @len: length up to which to write, can be negative + * + * Returns true if modifying the header part of the cloned buffer + * does require the data to be copied. I.e. this version works with + * negative lengths needed for eBPF case! + */ +static bool bpf_skb_clone_unwritable(const struct sk_buff *skb, int len) +{ + return skb_header_cloned(skb) || + (int) skb_headroom(skb) + len > skb->hdr_len; +} + +#define BPF_RECOMPUTE_CSUM(flags) ((flags) & 1) + +static u64 bpf_skb_store_bytes(u64 r1, u64 r2, u64 r3, u64 r4, u64 flags) +{ + struct sk_buff *skb = (struct sk_buff *) (long) r1; + int offset = (int) r2; + void *from = (void *) (long) r3; + unsigned int len = (unsigned int) r4; + char buf[16]; + void *ptr; + + /* bpf verifier guarantees that: + * 'from' pointer points to bpf program stack + * 'len' bytes of it were initialized + * 'len' > 0 + * 'skb' is a valid pointer to 'struct sk_buff' + * + * so check for invalid 'offset' and too large 'len' + */ + if (unlikely((u32) offset > 0xffff || len > sizeof(buf))) + return -EFAULT; + + offset -= skb->data - skb_mac_header(skb); + if (unlikely(skb_cloned(skb) && + bpf_skb_clone_unwritable(skb, offset + len))) + return -EFAULT; + + ptr = skb_header_pointer(skb, offset, len, buf); + if (unlikely(!ptr)) + return -EFAULT; + + if (BPF_RECOMPUTE_CSUM(flags)) + skb_postpull_rcsum(skb, ptr, len); + + memcpy(ptr, from, len); + + if (ptr == buf) + /* skb_store_bits cannot return -EFAULT here */ + skb_store_bits(skb, offset, ptr, len); + + if (BPF_RECOMPUTE_CSUM(flags) && skb->ip_summed == CHECKSUM_COMPLETE) + skb->csum = csum_add(skb->csum, csum_partial(ptr, len, 0)); + return 0; +} + +const struct bpf_func_proto bpf_skb_store_bytes_proto = { + .func = bpf_skb_store_bytes, + .gpl_only = false, + .ret_type = RET_INTEGER, + .arg1_type = ARG_PTR_TO_CTX, + .arg2_type = ARG_ANYTHING, + .arg3_type = ARG_PTR_TO_STACK, + .arg4_type = ARG_CONST_STACK_SIZE, + .arg5_type = ARG_ANYTHING, +}; + +#define BPF_HEADER_FIELD_SIZE(flags) ((flags) & 0x0f) +#define BPF_IS_PSEUDO_HEADER(flags) ((flags) & 0x10) + +static u64 bpf_l3_csum_replace(u64 r1, u64 r2, u64 from, u64 to, u64 flags) +{ + struct sk_buff *skb = (struct sk_buff *) (long) r1; + int offset = (int) r2; + __sum16 sum, *ptr; + + if (unlikely((u32) offset > 0xffff)) + return -EFAULT; + + offset -= skb->data - skb_mac_header(skb); + if (unlikely(skb_cloned(skb) && + bpf_skb_clone_unwritable(skb, offset + sizeof(sum)))) + return -EFAULT; + + ptr = skb_header_pointer(skb, offset, sizeof(sum), &sum); + if (unlikely(!ptr)) + return -EFAULT; + + switch (BPF_HEADER_FIELD_SIZE(flags)) { + case 2: + csum_replace2(ptr, from, to); + break; + case 4: + csum_replace4(ptr, from, to); + break; + default: + return -EINVAL; } - old_fp = rcu_dereference_protected(sk->sk_filter, - sock_owned_by_user(sk)); - rcu_assign_pointer(sk->sk_filter, fp); + if (ptr == &sum) + /* skb_store_bits guaranteed to not return -EFAULT here */ + skb_store_bits(skb, offset, ptr, sizeof(sum)); - if (old_fp) - sk_filter_uncharge(sk, old_fp); + return 0; +} + +const struct bpf_func_proto bpf_l3_csum_replace_proto = { + .func = bpf_l3_csum_replace, + .gpl_only = false, + .ret_type = RET_INTEGER, + .arg1_type = ARG_PTR_TO_CTX, + .arg2_type = ARG_ANYTHING, + .arg3_type = ARG_ANYTHING, + .arg4_type = ARG_ANYTHING, + .arg5_type = ARG_ANYTHING, +}; + +static u64 bpf_l4_csum_replace(u64 r1, u64 r2, u64 from, u64 to, u64 flags) +{ + struct sk_buff *skb = (struct sk_buff *) (long) r1; + u32 is_pseudo = BPF_IS_PSEUDO_HEADER(flags); + int offset = (int) r2; + __sum16 sum, *ptr; + + if (unlikely((u32) offset > 0xffff)) + return -EFAULT; + + offset -= skb->data - skb_mac_header(skb); + if (unlikely(skb_cloned(skb) && + bpf_skb_clone_unwritable(skb, offset + sizeof(sum)))) + return -EFAULT; + + ptr = skb_header_pointer(skb, offset, sizeof(sum), &sum); + if (unlikely(!ptr)) + return -EFAULT; + + switch (BPF_HEADER_FIELD_SIZE(flags)) { + case 2: + inet_proto_csum_replace2(ptr, skb, from, to, is_pseudo); + break; + case 4: + inet_proto_csum_replace4(ptr, skb, from, to, is_pseudo); + break; + default: + return -EINVAL; + } + + if (ptr == &sum) + /* skb_store_bits guaranteed to not return -EFAULT here */ + skb_store_bits(skb, offset, ptr, sizeof(sum)); return 0; } -/* allow socket filters to call - * bpf_map_lookup_elem(), bpf_map_update_elem(), bpf_map_delete_elem() - */ -static const struct bpf_func_proto *sock_filter_func_proto(enum bpf_func_id func_id) +const struct bpf_func_proto bpf_l4_csum_replace_proto = { + .func = bpf_l4_csum_replace, + .gpl_only = false, + .ret_type = RET_INTEGER, + .arg1_type = ARG_PTR_TO_CTX, + .arg2_type = ARG_ANYTHING, + .arg3_type = ARG_ANYTHING, + .arg4_type = ARG_ANYTHING, + .arg5_type = ARG_ANYTHING, +}; + +static const struct bpf_func_proto * +sk_filter_func_proto(enum bpf_func_id func_id) { switch (func_id) { case BPF_FUNC_map_lookup_elem: @@ -1148,39 +1354,144 @@ static const struct bpf_func_proto *sock_filter_func_proto(enum bpf_func_id func return &bpf_map_update_elem_proto; case BPF_FUNC_map_delete_elem: return &bpf_map_delete_elem_proto; + case BPF_FUNC_get_prandom_u32: + return &bpf_get_prandom_u32_proto; + case BPF_FUNC_get_smp_processor_id: + return &bpf_get_smp_processor_id_proto; default: return NULL; } } -static bool sock_filter_is_valid_access(int off, int size, enum bpf_access_type type) +static const struct bpf_func_proto * +tc_cls_act_func_proto(enum bpf_func_id func_id) { - /* skb fields cannot be accessed yet */ - return false; + switch (func_id) { + case BPF_FUNC_skb_store_bytes: + return &bpf_skb_store_bytes_proto; + case BPF_FUNC_l3_csum_replace: + return &bpf_l3_csum_replace_proto; + case BPF_FUNC_l4_csum_replace: + return &bpf_l4_csum_replace_proto; + default: + return sk_filter_func_proto(func_id); + } } -static struct bpf_verifier_ops sock_filter_ops = { - .get_func_proto = sock_filter_func_proto, - .is_valid_access = sock_filter_is_valid_access, +static bool sk_filter_is_valid_access(int off, int size, + enum bpf_access_type type) +{ + /* only read is allowed */ + if (type != BPF_READ) + return false; + + /* check bounds */ + if (off < 0 || off >= sizeof(struct __sk_buff)) + return false; + + /* disallow misaligned access */ + if (off % size != 0) + return false; + + /* all __sk_buff fields are __u32 */ + if (size != 4) + return false; + + return true; +} + +static u32 sk_filter_convert_ctx_access(int dst_reg, int src_reg, int ctx_off, + struct bpf_insn *insn_buf) +{ + struct bpf_insn *insn = insn_buf; + + switch (ctx_off) { + case offsetof(struct __sk_buff, len): + BUILD_BUG_ON(FIELD_SIZEOF(struct sk_buff, len) != 4); + + *insn++ = BPF_LDX_MEM(BPF_W, dst_reg, src_reg, + offsetof(struct sk_buff, len)); + break; + + case offsetof(struct __sk_buff, protocol): + BUILD_BUG_ON(FIELD_SIZEOF(struct sk_buff, protocol) != 2); + + *insn++ = BPF_LDX_MEM(BPF_H, dst_reg, src_reg, + offsetof(struct sk_buff, protocol)); + break; + + case offsetof(struct __sk_buff, vlan_proto): + BUILD_BUG_ON(FIELD_SIZEOF(struct sk_buff, vlan_proto) != 2); + + *insn++ = BPF_LDX_MEM(BPF_H, dst_reg, src_reg, + offsetof(struct sk_buff, vlan_proto)); + break; + + case offsetof(struct __sk_buff, priority): + BUILD_BUG_ON(FIELD_SIZEOF(struct sk_buff, priority) != 4); + + *insn++ = BPF_LDX_MEM(BPF_W, dst_reg, src_reg, + offsetof(struct sk_buff, priority)); + break; + + case offsetof(struct __sk_buff, mark): + return convert_skb_access(SKF_AD_MARK, dst_reg, src_reg, insn); + + case offsetof(struct __sk_buff, pkt_type): + return convert_skb_access(SKF_AD_PKTTYPE, dst_reg, src_reg, insn); + + case offsetof(struct __sk_buff, queue_mapping): + return convert_skb_access(SKF_AD_QUEUE, dst_reg, src_reg, insn); + + case offsetof(struct __sk_buff, vlan_present): + return convert_skb_access(SKF_AD_VLAN_TAG_PRESENT, + dst_reg, src_reg, insn); + + case offsetof(struct __sk_buff, vlan_tci): + return convert_skb_access(SKF_AD_VLAN_TAG, + dst_reg, src_reg, insn); + } + + return insn - insn_buf; +} + +static const struct bpf_verifier_ops sk_filter_ops = { + .get_func_proto = sk_filter_func_proto, + .is_valid_access = sk_filter_is_valid_access, + .convert_ctx_access = sk_filter_convert_ctx_access, +}; + +static const struct bpf_verifier_ops tc_cls_act_ops = { + .get_func_proto = tc_cls_act_func_proto, + .is_valid_access = sk_filter_is_valid_access, + .convert_ctx_access = sk_filter_convert_ctx_access, }; -static struct bpf_prog_type_list tl = { - .ops = &sock_filter_ops, +static struct bpf_prog_type_list sk_filter_type __read_mostly = { + .ops = &sk_filter_ops, .type = BPF_PROG_TYPE_SOCKET_FILTER, }; -static int __init register_sock_filter_ops(void) +static struct bpf_prog_type_list sched_cls_type __read_mostly = { + .ops = &tc_cls_act_ops, + .type = BPF_PROG_TYPE_SCHED_CLS, +}; + +static struct bpf_prog_type_list sched_act_type __read_mostly = { + .ops = &tc_cls_act_ops, + .type = BPF_PROG_TYPE_SCHED_ACT, +}; + +static int __init register_sk_filter_ops(void) { - bpf_register_prog_type(&tl); + bpf_register_prog_type(&sk_filter_type); + bpf_register_prog_type(&sched_cls_type); + bpf_register_prog_type(&sched_act_type); + return 0; } -late_initcall(register_sock_filter_ops); -#else -int sk_attach_bpf(u32 ufd, struct sock *sk) -{ - return -EOPNOTSUPP; -} -#endif +late_initcall(register_sk_filter_ops); + int sk_detach_filter(struct sock *sk) { int ret = -ENOENT; diff --git a/net/core/link_watch.c b/net/core/link_watch.c index 49a9e3e06c08..982861607f88 100644 --- a/net/core/link_watch.c +++ b/net/core/link_watch.c @@ -40,7 +40,7 @@ static DEFINE_SPINLOCK(lweventlist_lock); static unsigned char default_operstate(const struct net_device *dev) { if (!netif_carrier_ok(dev)) - return (dev->ifindex != dev->iflink ? + return (dev->ifindex != dev_get_iflink(dev) ? IF_OPER_LOWERLAYERDOWN : IF_OPER_DOWN); if (netif_dormant(dev)) @@ -89,7 +89,7 @@ static bool linkwatch_urgent_event(struct net_device *dev) if (!netif_running(dev)) return false; - if (dev->ifindex != dev->iflink) + if (dev->ifindex != dev_get_iflink(dev)) return true; if (dev->priv_flags & IFF_TEAM_PORT) diff --git a/net/core/neighbour.c b/net/core/neighbour.c index 70fe9e10ac86..3de654256028 100644 --- a/net/core/neighbour.c +++ b/net/core/neighbour.c @@ -397,25 +397,15 @@ struct neighbour *neigh_lookup(struct neigh_table *tbl, const void *pkey, struct net_device *dev) { struct neighbour *n; - int key_len = tbl->key_len; - u32 hash_val; - struct neigh_hash_table *nht; NEIGH_CACHE_STAT_INC(tbl, lookups); rcu_read_lock_bh(); - nht = rcu_dereference_bh(tbl->nht); - hash_val = tbl->hash(pkey, dev, nht->hash_rnd) >> (32 - nht->hash_shift); - - for (n = rcu_dereference_bh(nht->hash_buckets[hash_val]); - n != NULL; - n = rcu_dereference_bh(n->next)) { - if (dev == n->dev && !memcmp(n->primary_key, pkey, key_len)) { - if (!atomic_inc_not_zero(&n->refcnt)) - n = NULL; - NEIGH_CACHE_STAT_INC(tbl, hits); - break; - } + n = __neigh_lookup_noref(tbl, pkey, dev); + if (n) { + if (!atomic_inc_not_zero(&n->refcnt)) + n = NULL; + NEIGH_CACHE_STAT_INC(tbl, hits); } rcu_read_unlock_bh(); @@ -601,7 +591,7 @@ struct pneigh_entry * pneigh_lookup(struct neigh_table *tbl, if (!n) goto out; - write_pnet(&n->net, hold_net(net)); + write_pnet(&n->net, net); memcpy(n->key, pkey, key_len); n->dev = dev; if (dev) @@ -610,7 +600,6 @@ struct pneigh_entry * pneigh_lookup(struct neigh_table *tbl, if (tbl->pconstructor && tbl->pconstructor(n)) { if (dev) dev_put(dev); - release_net(net); kfree(n); n = NULL; goto out; @@ -644,7 +633,6 @@ int pneigh_delete(struct neigh_table *tbl, struct net *net, const void *pkey, tbl->pdestructor(n); if (n->dev) dev_put(n->dev); - release_net(pneigh_net(n)); kfree(n); return 0; } @@ -667,7 +655,6 @@ static int pneigh_ifdown(struct neigh_table *tbl, struct net_device *dev) tbl->pdestructor(n); if (n->dev) dev_put(n->dev); - release_net(pneigh_net(n)); kfree(n); continue; } @@ -830,10 +817,9 @@ out: static __inline__ int neigh_max_probes(struct neighbour *n) { struct neigh_parms *p = n->parms; - int max_probes = NEIGH_VAR(p, UCAST_PROBES) + NEIGH_VAR(p, APP_PROBES); - if (!(n->nud_state & NUD_PROBE)) - max_probes += NEIGH_VAR(p, MCAST_PROBES); - return max_probes; + return NEIGH_VAR(p, UCAST_PROBES) + NEIGH_VAR(p, APP_PROBES) + + (n->nud_state & NUD_PROBE ? NEIGH_VAR(p, MCAST_REPROBES) : + NEIGH_VAR(p, MCAST_PROBES)); } static void neigh_invalidate(struct neighbour *neigh) @@ -1263,10 +1249,10 @@ struct neighbour *neigh_event_ns(struct neigh_table *tbl, EXPORT_SYMBOL(neigh_event_ns); /* called with read_lock_bh(&n->lock); */ -static void neigh_hh_init(struct neighbour *n, struct dst_entry *dst) +static void neigh_hh_init(struct neighbour *n) { - struct net_device *dev = dst->dev; - __be16 prot = dst->ops->protocol; + struct net_device *dev = n->dev; + __be16 prot = n->tbl->protocol; struct hh_cache *hh = &n->hh; write_lock_bh(&n->lock); @@ -1280,43 +1266,19 @@ static void neigh_hh_init(struct neighbour *n, struct dst_entry *dst) write_unlock_bh(&n->lock); } -/* This function can be used in contexts, where only old dev_queue_xmit - * worked, f.e. if you want to override normal output path (eql, shaper), - * but resolution is not made yet. - */ - -int neigh_compat_output(struct neighbour *neigh, struct sk_buff *skb) -{ - struct net_device *dev = skb->dev; - - __skb_pull(skb, skb_network_offset(skb)); - - if (dev_hard_header(skb, dev, ntohs(skb->protocol), NULL, NULL, - skb->len) < 0 && - dev_rebuild_header(skb)) - return 0; - - return dev_queue_xmit(skb); -} -EXPORT_SYMBOL(neigh_compat_output); - /* Slow and careful. */ int neigh_resolve_output(struct neighbour *neigh, struct sk_buff *skb) { - struct dst_entry *dst = skb_dst(skb); int rc = 0; - if (!dst) - goto discard; - if (!neigh_event_send(neigh, skb)) { int err; struct net_device *dev = neigh->dev; unsigned int seq; if (dev->header_ops->cache && !neigh->hh.hh_len) - neigh_hh_init(neigh, dst); + neigh_hh_init(neigh); do { __skb_pull(skb, skb_network_offset(skb)); @@ -1332,8 +1294,6 @@ int neigh_resolve_output(struct neighbour *neigh, struct sk_buff *skb) } out: return rc; -discard: - neigh_dbg(1, "%s: dst=%p neigh=%p\n", __func__, dst, neigh); out_kfree_skb: rc = -EINVAL; kfree_skb(skb); @@ -1464,11 +1424,10 @@ struct neigh_parms *neigh_parms_alloc(struct net_device *dev, neigh_rand_reach_time(NEIGH_VAR(p, BASE_REACHABLE_TIME)); dev_hold(dev); p->dev = dev; - write_pnet(&p->net, hold_net(net)); + write_pnet(&p->net, net); p->sysctl_table = NULL; if (ops->ndo_neigh_setup && ops->ndo_neigh_setup(dev, p)) { - release_net(net); dev_put(dev); kfree(p); return NULL; @@ -1508,7 +1467,6 @@ EXPORT_SYMBOL(neigh_parms_release); static void neigh_parms_destroy(struct neigh_parms *parms) { - release_net(neigh_parms_net(parms)); kfree(parms); } @@ -1783,6 +1741,8 @@ static int neightbl_fill_parms(struct sk_buff *skb, struct neigh_parms *parms) NEIGH_VAR(parms, UCAST_PROBES)) || nla_put_u32(skb, NDTPA_MCAST_PROBES, NEIGH_VAR(parms, MCAST_PROBES)) || + nla_put_u32(skb, NDTPA_MCAST_REPROBES, + NEIGH_VAR(parms, MCAST_REPROBES)) || nla_put_msecs(skb, NDTPA_REACHABLE_TIME, parms->reachable_time) || nla_put_msecs(skb, NDTPA_BASE_REACHABLE_TIME, NEIGH_VAR(parms, BASE_REACHABLE_TIME)) || @@ -1942,6 +1902,7 @@ static const struct nla_policy nl_ntbl_parm_policy[NDTPA_MAX+1] = { [NDTPA_APP_PROBES] = { .type = NLA_U32 }, [NDTPA_UCAST_PROBES] = { .type = NLA_U32 }, [NDTPA_MCAST_PROBES] = { .type = NLA_U32 }, + [NDTPA_MCAST_REPROBES] = { .type = NLA_U32 }, [NDTPA_BASE_REACHABLE_TIME] = { .type = NLA_U64 }, [NDTPA_GC_STALETIME] = { .type = NLA_U64 }, [NDTPA_DELAY_PROBE_TIME] = { .type = NLA_U64 }, @@ -2042,6 +2003,10 @@ static int neightbl_set(struct sk_buff *skb, struct nlmsghdr *nlh) NEIGH_VAR_SET(p, MCAST_PROBES, nla_get_u32(tbp[i])); break; + case NDTPA_MCAST_REPROBES: + NEIGH_VAR_SET(p, MCAST_REPROBES, + nla_get_u32(tbp[i])); + break; case NDTPA_BASE_REACHABLE_TIME: NEIGH_VAR_SET(p, BASE_REACHABLE_TIME, nla_get_msecs(tbp[i])); @@ -2427,6 +2392,40 @@ void __neigh_for_each_release(struct neigh_table *tbl, } EXPORT_SYMBOL(__neigh_for_each_release); +int neigh_xmit(int index, struct net_device *dev, + const void *addr, struct sk_buff *skb) +{ + int err = -EAFNOSUPPORT; + if (likely(index < NEIGH_NR_TABLES)) { + struct neigh_table *tbl; + struct neighbour *neigh; + + tbl = neigh_tables[index]; + if (!tbl) + goto out; + neigh = __neigh_lookup_noref(tbl, addr, dev); + if (!neigh) + neigh = __neigh_create(tbl, addr, dev, false); + err = PTR_ERR(neigh); + if (IS_ERR(neigh)) + goto out_kfree_skb; + err = neigh->output(neigh, skb); + } + else if (index == NEIGH_LINK_TABLE) { + err = dev_hard_header(skb, dev, ntohs(skb->protocol), + addr, NULL, skb->len); + if (err < 0) + goto out_kfree_skb; + err = dev_queue_xmit(skb); + } +out: + return err; +out_kfree_skb: + kfree_skb(skb); + goto out; +} +EXPORT_SYMBOL(neigh_xmit); + #ifdef CONFIG_PROC_FS static struct neighbour *neigh_get_first(struct seq_file *seq) @@ -2994,6 +2993,7 @@ static struct neigh_sysctl_table { NEIGH_SYSCTL_ZERO_INTMAX_ENTRY(MCAST_PROBES, "mcast_solicit"), NEIGH_SYSCTL_ZERO_INTMAX_ENTRY(UCAST_PROBES, "ucast_solicit"), NEIGH_SYSCTL_ZERO_INTMAX_ENTRY(APP_PROBES, "app_solicit"), + NEIGH_SYSCTL_ZERO_INTMAX_ENTRY(MCAST_REPROBES, "mcast_resolicit"), NEIGH_SYSCTL_USERHZ_JIFFIES_ENTRY(RETRANS_TIME, "retrans_time"), NEIGH_SYSCTL_JIFFIES_ENTRY(BASE_REACHABLE_TIME, "base_reachable_time"), NEIGH_SYSCTL_JIFFIES_ENTRY(DELAY_PROBE_TIME, "delay_first_probe_time"), diff --git a/net/core/net-sysfs.c b/net/core/net-sysfs.c index f2aa73bfb0e4..4238d6da5c60 100644 --- a/net/core/net-sysfs.c +++ b/net/core/net-sysfs.c @@ -23,6 +23,7 @@ #include <linux/export.h> #include <linux/jiffies.h> #include <linux/pm_runtime.h> +#include <linux/of.h> #include "net-sysfs.h" @@ -108,11 +109,19 @@ NETDEVICE_SHOW_RO(dev_id, fmt_hex); NETDEVICE_SHOW_RO(dev_port, fmt_dec); NETDEVICE_SHOW_RO(addr_assign_type, fmt_dec); NETDEVICE_SHOW_RO(addr_len, fmt_dec); -NETDEVICE_SHOW_RO(iflink, fmt_dec); NETDEVICE_SHOW_RO(ifindex, fmt_dec); NETDEVICE_SHOW_RO(type, fmt_dec); NETDEVICE_SHOW_RO(link_mode, fmt_dec); +static ssize_t iflink_show(struct device *dev, struct device_attribute *attr, + char *buf) +{ + struct net_device *ndev = to_net_dev(dev); + + return sprintf(buf, fmt_dec, dev_get_iflink(ndev)); +} +static DEVICE_ATTR_RO(iflink); + static ssize_t format_name_assign_type(const struct net_device *dev, char *buf) { return sprintf(buf, fmt_dec, dev->name_assign_type); @@ -417,6 +426,28 @@ static ssize_t phys_port_id_show(struct device *dev, } static DEVICE_ATTR_RO(phys_port_id); +static ssize_t phys_port_name_show(struct device *dev, + struct device_attribute *attr, char *buf) +{ + struct net_device *netdev = to_net_dev(dev); + ssize_t ret = -EINVAL; + + if (!rtnl_trylock()) + return restart_syscall(); + + if (dev_isalive(netdev)) { + char name[IFNAMSIZ]; + + ret = dev_get_phys_port_name(netdev, name, sizeof(name)); + if (!ret) + ret = sprintf(buf, "%s\n", name); + } + rtnl_unlock(); + + return ret; +} +static DEVICE_ATTR_RO(phys_port_name); + static ssize_t phys_switch_id_show(struct device *dev, struct device_attribute *attr, char *buf) { @@ -464,6 +495,7 @@ static struct attribute *net_class_attrs[] = { &dev_attr_tx_queue_len.attr, &dev_attr_gro_flush_timeout.attr, &dev_attr_phys_port_id.attr, + &dev_attr_phys_port_name.attr, &dev_attr_phys_switch_id.attr, NULL, }; @@ -950,6 +982,60 @@ static ssize_t show_trans_timeout(struct netdev_queue *queue, return sprintf(buf, "%lu", trans_timeout); } +#ifdef CONFIG_XPS +static inline unsigned int get_netdev_queue_index(struct netdev_queue *queue) +{ + struct net_device *dev = queue->dev; + int i; + + for (i = 0; i < dev->num_tx_queues; i++) + if (queue == &dev->_tx[i]) + break; + + BUG_ON(i >= dev->num_tx_queues); + + return i; +} + +static ssize_t show_tx_maxrate(struct netdev_queue *queue, + struct netdev_queue_attribute *attribute, + char *buf) +{ + return sprintf(buf, "%lu\n", queue->tx_maxrate); +} + +static ssize_t set_tx_maxrate(struct netdev_queue *queue, + struct netdev_queue_attribute *attribute, + const char *buf, size_t len) +{ + struct net_device *dev = queue->dev; + int err, index = get_netdev_queue_index(queue); + u32 rate = 0; + + err = kstrtou32(buf, 10, &rate); + if (err < 0) + return err; + + if (!rtnl_trylock()) + return restart_syscall(); + + err = -EOPNOTSUPP; + if (dev->netdev_ops->ndo_set_tx_maxrate) + err = dev->netdev_ops->ndo_set_tx_maxrate(dev, index, rate); + + rtnl_unlock(); + if (!err) { + queue->tx_maxrate = rate; + return len; + } + return err; +} + +static struct netdev_queue_attribute queue_tx_maxrate = + __ATTR(tx_maxrate, S_IRUGO | S_IWUSR, + show_tx_maxrate, set_tx_maxrate); +#endif + static struct netdev_queue_attribute queue_trans_timeout = __ATTR(tx_timeout, S_IRUGO, show_trans_timeout, NULL); @@ -1064,18 +1150,6 @@ static struct attribute_group dql_group = { #endif /* CONFIG_BQL */ #ifdef CONFIG_XPS -static unsigned int get_netdev_queue_index(struct netdev_queue *queue) -{ - struct net_device *dev = queue->dev; - unsigned int i; - - i = queue - dev->_tx; - BUG_ON(i >= dev->num_tx_queues); - - return i; -} - - static ssize_t show_xps_map(struct netdev_queue *queue, struct netdev_queue_attribute *attribute, char *buf) { @@ -1152,6 +1226,7 @@ static struct attribute *netdev_queue_default_attrs[] = { &queue_trans_timeout.attr, #ifdef CONFIG_XPS &xps_cpus_attribute.attr, + &queue_tx_maxrate.attr, #endif NULL }; @@ -1374,6 +1449,30 @@ static struct class net_class = { .namespace = net_namespace, }; +#ifdef CONFIG_OF_NET +static int of_dev_node_match(struct device *dev, const void *data) +{ + int ret = 0; + + if (dev->parent) + ret = dev->parent->of_node == data; + + return ret == 0 ? dev->of_node == data : ret; +} + +struct net_device *of_find_net_device_by_node(struct device_node *np) +{ + struct device *dev; + + dev = class_find_device(&net_class, NULL, np, of_dev_node_match); + if (!dev) + return NULL; + + return to_net_dev(dev); +} +EXPORT_SYMBOL(of_find_net_device_by_node); +#endif + /* Delete sysfs entries but hold kobject reference until after all * netdev references are gone. */ diff --git a/net/core/net_namespace.c b/net/core/net_namespace.c index 70d3450588b2..78fc04ad36fc 100644 --- a/net/core/net_namespace.c +++ b/net/core/net_namespace.c @@ -16,7 +16,6 @@ #include <linux/export.h> #include <linux/user_namespace.h> #include <linux/net_namespace.h> -#include <linux/rtnetlink.h> #include <net/sock.h> #include <net/netlink.h> #include <net/net_namespace.h> @@ -148,9 +147,11 @@ static void ops_free_list(const struct pernet_operations *ops, } } +static void rtnl_net_notifyid(struct net *net, struct net *peer, int cmd, + int id); static int alloc_netid(struct net *net, struct net *peer, int reqid) { - int min = 0, max = 0; + int min = 0, max = 0, id; ASSERT_RTNL(); @@ -159,7 +160,11 @@ static int alloc_netid(struct net *net, struct net *peer, int reqid) max = reqid + 1; } - return idr_alloc(&net->netns_ids, peer, min, max, GFP_KERNEL); + id = idr_alloc(&net->netns_ids, peer, min, max, GFP_KERNEL); + if (id >= 0) + rtnl_net_notifyid(net, peer, RTM_NEWNSID, id); + + return id; } /* This function is used by idr_for_each(). If net is equal to peer, the @@ -238,10 +243,6 @@ static __net_init int setup_net(struct net *net, struct user_namespace *user_ns) net->user_ns = user_ns; idr_init(&net->netns_ids); -#ifdef NETNS_REFCNT_DEBUG - atomic_set(&net->use_count, 0); -#endif - list_for_each_entry(ops, &pernet_list, list) { error = ops_init(ops, net); if (error < 0) @@ -296,13 +297,6 @@ out_free: static void net_free(struct net *net) { -#ifdef NETNS_REFCNT_DEBUG - if (unlikely(atomic_read(&net->use_count) != 0)) { - pr_emerg("network namespace not free! Usage: %d\n", - atomic_read(&net->use_count)); - return; - } -#endif kfree(rcu_access_pointer(net->gen)); kmem_cache_free(net_cachep, net); } @@ -370,8 +364,10 @@ static void cleanup_net(struct work_struct *work) for_each_net(tmp) { int id = __peernet2id(tmp, net, false); - if (id >= 0) + if (id >= 0) { + rtnl_net_notifyid(tmp, net, RTM_DELNSID, id); idr_remove(&tmp->netns_ids, id); + } } idr_destroy(&net->netns_ids); @@ -542,7 +538,8 @@ static int rtnl_net_get_size(void) } static int rtnl_net_fill(struct sk_buff *skb, u32 portid, u32 seq, int flags, - int cmd, struct net *net, struct net *peer) + int cmd, struct net *net, struct net *peer, + int nsid) { struct nlmsghdr *nlh; struct rtgenmsg *rth; @@ -557,9 +554,13 @@ static int rtnl_net_fill(struct sk_buff *skb, u32 portid, u32 seq, int flags, rth = nlmsg_data(nlh); rth->rtgen_family = AF_UNSPEC; - id = __peernet2id(net, peer, false); - if (id < 0) - id = NETNSA_NSID_NOT_ASSIGNED; + if (nsid >= 0) { + id = nsid; + } else { + id = __peernet2id(net, peer, false); + if (id < 0) + id = NETNSA_NSID_NOT_ASSIGNED; + } if (nla_put_s32(skb, NETNSA_NSID, id)) goto nla_put_failure; @@ -576,8 +577,8 @@ static int rtnl_net_getid(struct sk_buff *skb, struct nlmsghdr *nlh) struct net *net = sock_net(skb->sk); struct nlattr *tb[NETNSA_MAX + 1]; struct sk_buff *msg; - int err = -ENOBUFS; struct net *peer; + int err; err = nlmsg_parse(nlh, sizeof(struct rtgenmsg), tb, NETNSA_MAX, rtnl_net_policy); @@ -600,7 +601,7 @@ static int rtnl_net_getid(struct sk_buff *skb, struct nlmsghdr *nlh) } err = rtnl_net_fill(msg, NETLINK_CB(skb).portid, nlh->nlmsg_seq, 0, - RTM_GETNSID, net, peer); + RTM_GETNSID, net, peer, -1); if (err < 0) goto err_out; @@ -614,6 +615,75 @@ out: return err; } +struct rtnl_net_dump_cb { + struct net *net; + struct sk_buff *skb; + struct netlink_callback *cb; + int idx; + int s_idx; +}; + +static int rtnl_net_dumpid_one(int id, void *peer, void *data) +{ + struct rtnl_net_dump_cb *net_cb = (struct rtnl_net_dump_cb *)data; + int ret; + + if (net_cb->idx < net_cb->s_idx) + goto cont; + + ret = rtnl_net_fill(net_cb->skb, NETLINK_CB(net_cb->cb->skb).portid, + net_cb->cb->nlh->nlmsg_seq, NLM_F_MULTI, + RTM_NEWNSID, net_cb->net, peer, id); + if (ret < 0) + return ret; + +cont: + net_cb->idx++; + return 0; +} + +static int rtnl_net_dumpid(struct sk_buff *skb, struct netlink_callback *cb) +{ + struct net *net = sock_net(skb->sk); + struct rtnl_net_dump_cb net_cb = { + .net = net, + .skb = skb, + .cb = cb, + .idx = 0, + .s_idx = cb->args[0], + }; + + ASSERT_RTNL(); + + idr_for_each(&net->netns_ids, rtnl_net_dumpid_one, &net_cb); + + cb->args[0] = net_cb.idx; + return skb->len; +} + +static void rtnl_net_notifyid(struct net *net, struct net *peer, int cmd, + int id) +{ + struct sk_buff *msg; + int err = -ENOMEM; + + msg = nlmsg_new(rtnl_net_get_size(), GFP_KERNEL); + if (!msg) + goto out; + + err = rtnl_net_fill(msg, 0, 0, 0, cmd, net, peer, id); + if (err < 0) + goto err_out; + + rtnl_notify(msg, net, 0, RTNLGRP_NSID, NULL, 0); + return; + +err_out: + nlmsg_free(msg); +out: + rtnl_set_sk_err(net, RTNLGRP_NSID, err); +} + static int __init net_ns_init(void) { struct net_generic *ng; @@ -648,7 +718,8 @@ static int __init net_ns_init(void) register_pernet_subsys(&net_ns_ops); rtnl_register(PF_UNSPEC, RTM_NEWNSID, rtnl_net_newid, NULL, NULL); - rtnl_register(PF_UNSPEC, RTM_GETNSID, rtnl_net_getid, NULL, NULL); + rtnl_register(PF_UNSPEC, RTM_GETNSID, rtnl_net_getid, rtnl_net_dumpid, + NULL); return 0; } diff --git a/net/core/request_sock.c b/net/core/request_sock.c index 04db318e6218..87b22c0bc08c 100644 --- a/net/core/request_sock.c +++ b/net/core/request_sock.c @@ -58,14 +58,14 @@ int reqsk_queue_alloc(struct request_sock_queue *queue, return -ENOMEM; get_random_bytes(&lopt->hash_rnd, sizeof(lopt->hash_rnd)); - rwlock_init(&queue->syn_wait_lock); + spin_lock_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); + spin_lock_bh(&queue->syn_wait_lock); queue->listen_opt = lopt; - write_unlock_bh(&queue->syn_wait_lock); + spin_unlock_bh(&queue->syn_wait_lock); return 0; } @@ -81,10 +81,10 @@ static inline struct listen_sock *reqsk_queue_yank_listen_sk( { struct listen_sock *lopt; - write_lock_bh(&queue->syn_wait_lock); + spin_lock_bh(&queue->syn_wait_lock); lopt = queue->listen_opt; queue->listen_opt = NULL; - write_unlock_bh(&queue->syn_wait_lock); + spin_unlock_bh(&queue->syn_wait_lock); return lopt; } @@ -94,21 +94,26 @@ 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); - if (lopt->qlen != 0) { + if (listen_sock_qlen(lopt) != 0) { unsigned int i; for (i = 0; i < lopt->nr_table_entries; i++) { struct request_sock *req; + spin_lock_bh(&queue->syn_wait_lock); while ((req = lopt->syn_table[i]) != NULL) { lopt->syn_table[i] = req->dl_next; - lopt->qlen--; - reqsk_free(req); + atomic_inc(&lopt->qlen_dec); + if (del_timer(&req->rsk_timer)) + reqsk_put(req); + reqsk_put(req); } + spin_unlock_bh(&queue->syn_wait_lock); } } - WARN_ON(lopt->qlen != 0); + if (WARN_ON(listen_sock_qlen(lopt) != 0)) + pr_err("qlen %u\n", listen_sock_qlen(lopt)); kvfree(lopt); } @@ -153,24 +158,22 @@ void reqsk_queue_destroy(struct request_sock_queue *queue) * case might also exist in tcp_v4_hnd_req() that will trigger this locking * order. * - * When a TFO req is created, it needs to sock_hold its listener to prevent - * the latter data structure from going away. - * - * This function also sets "treq->listener" to NULL and unreference listener - * socket. treq->listener is used by the listener so it is protected by the + * This function also sets "treq->tfo_listener" to false. + * treq->tfo_listener is used by the listener so it is protected by the * fastopenq->lock in this function. */ void reqsk_fastopen_remove(struct sock *sk, struct request_sock *req, bool reset) { - struct sock *lsk = tcp_rsk(req)->listener; - struct fastopen_queue *fastopenq = - inet_csk(lsk)->icsk_accept_queue.fastopenq; + struct sock *lsk = req->rsk_listener; + struct fastopen_queue *fastopenq; + + fastopenq = inet_csk(lsk)->icsk_accept_queue.fastopenq; tcp_sk(sk)->fastopen_rsk = NULL; spin_lock_bh(&fastopenq->lock); fastopenq->qlen--; - tcp_rsk(req)->listener = NULL; + tcp_rsk(req)->tfo_listener = false; if (req->sk) /* the child socket hasn't been accepted yet */ goto out; @@ -179,8 +182,7 @@ void reqsk_fastopen_remove(struct sock *sk, struct request_sock *req, * special RST handling below. */ spin_unlock_bh(&fastopenq->lock); - sock_put(lsk); - reqsk_free(req); + reqsk_put(req); return; } /* Wait for 60secs before removing a req that has triggered RST. @@ -190,7 +192,7 @@ void reqsk_fastopen_remove(struct sock *sk, struct request_sock *req, * * For more details see CoNext'11 "TCP Fast Open" paper. */ - req->expires = jiffies + 60*HZ; + req->rsk_timer.expires = jiffies + 60*HZ; if (fastopenq->rskq_rst_head == NULL) fastopenq->rskq_rst_head = req; else @@ -201,5 +203,4 @@ void reqsk_fastopen_remove(struct sock *sk, struct request_sock *req, fastopenq->qlen++; out: spin_unlock_bh(&fastopenq->lock); - sock_put(lsk); } diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c index 7ebed55b5f7d..666e0928ba40 100644 --- a/net/core/rtnetlink.c +++ b/net/core/rtnetlink.c @@ -818,7 +818,8 @@ static inline int rtnl_vfinfo_size(const struct net_device *dev, nla_total_size(sizeof(struct ifla_vf_vlan)) + nla_total_size(sizeof(struct ifla_vf_spoofchk)) + nla_total_size(sizeof(struct ifla_vf_rate)) + - nla_total_size(sizeof(struct ifla_vf_link_state))); + nla_total_size(sizeof(struct ifla_vf_link_state)) + + nla_total_size(sizeof(struct ifla_vf_rss_query_en))); return size; } else return 0; @@ -982,6 +983,24 @@ static int rtnl_phys_port_id_fill(struct sk_buff *skb, struct net_device *dev) return 0; } +static int rtnl_phys_port_name_fill(struct sk_buff *skb, struct net_device *dev) +{ + char name[IFNAMSIZ]; + int err; + + err = dev_get_phys_port_name(dev, name, sizeof(name)); + if (err) { + if (err == -EOPNOTSUPP) + return 0; + return err; + } + + if (nla_put(skb, IFLA_PHYS_PORT_NAME, strlen(name), name)) + return -EMSGSIZE; + + return 0; +} + static int rtnl_phys_switch_id_fill(struct sk_buff *skb, struct net_device *dev) { int err; @@ -1037,8 +1056,8 @@ static int rtnl_fill_ifinfo(struct sk_buff *skb, struct net_device *dev, #ifdef CONFIG_RPS nla_put_u32(skb, IFLA_NUM_RX_QUEUES, dev->num_rx_queues) || #endif - (dev->ifindex != dev->iflink && - nla_put_u32(skb, IFLA_LINK, dev->iflink)) || + (dev->ifindex != dev_get_iflink(dev) && + nla_put_u32(skb, IFLA_LINK, dev_get_iflink(dev))) || (upper_dev && nla_put_u32(skb, IFLA_MASTER, upper_dev->ifindex)) || nla_put_u8(skb, IFLA_CARRIER, netif_carrier_ok(dev)) || @@ -1072,6 +1091,9 @@ static int rtnl_fill_ifinfo(struct sk_buff *skb, struct net_device *dev, if (rtnl_phys_port_id_fill(skb, dev)) goto nla_put_failure; + if (rtnl_phys_port_name_fill(skb, dev)) + goto nla_put_failure; + if (rtnl_phys_switch_id_fill(skb, dev)) goto nla_put_failure; @@ -1111,14 +1133,16 @@ static int rtnl_fill_ifinfo(struct sk_buff *skb, struct net_device *dev, struct ifla_vf_tx_rate vf_tx_rate; struct ifla_vf_spoofchk vf_spoofchk; struct ifla_vf_link_state vf_linkstate; + struct ifla_vf_rss_query_en vf_rss_query_en; /* * Not all SR-IOV capable drivers support the - * spoofcheck query. Preset to -1 so the user - * space tool can detect that the driver didn't - * report anything. + * spoofcheck and "RSS query enable" query. Preset to + * -1 so the user space tool can detect that the driver + * didn't report anything. */ ivi.spoofchk = -1; + ivi.rss_query_en = -1; memset(ivi.mac, 0, sizeof(ivi.mac)); /* The default value for VF link state is "auto" * IFLA_VF_LINK_STATE_AUTO which equals zero @@ -1131,7 +1155,8 @@ static int rtnl_fill_ifinfo(struct sk_buff *skb, struct net_device *dev, vf_rate.vf = vf_tx_rate.vf = vf_spoofchk.vf = - vf_linkstate.vf = ivi.vf; + vf_linkstate.vf = + vf_rss_query_en.vf = ivi.vf; memcpy(vf_mac.mac, ivi.mac, sizeof(ivi.mac)); vf_vlan.vlan = ivi.vlan; @@ -1141,6 +1166,7 @@ static int rtnl_fill_ifinfo(struct sk_buff *skb, struct net_device *dev, vf_rate.max_tx_rate = ivi.max_tx_rate; vf_spoofchk.setting = ivi.spoofchk; vf_linkstate.link_state = ivi.linkstate; + vf_rss_query_en.setting = ivi.rss_query_en; vf = nla_nest_start(skb, IFLA_VF_INFO); if (!vf) { nla_nest_cancel(skb, vfinfo); @@ -1155,7 +1181,10 @@ static int rtnl_fill_ifinfo(struct sk_buff *skb, struct net_device *dev, nla_put(skb, IFLA_VF_SPOOFCHK, sizeof(vf_spoofchk), &vf_spoofchk) || nla_put(skb, IFLA_VF_LINK_STATE, sizeof(vf_linkstate), - &vf_linkstate)) + &vf_linkstate) || + nla_put(skb, IFLA_VF_RSS_QUERY_EN, + sizeof(vf_rss_query_en), + &vf_rss_query_en)) goto nla_put_failure; nla_nest_end(skb, vf); } @@ -1269,6 +1298,7 @@ static const struct nla_policy ifla_vf_policy[IFLA_VF_MAX+1] = { [IFLA_VF_SPOOFCHK] = { .len = sizeof(struct ifla_vf_spoofchk) }, [IFLA_VF_RATE] = { .len = sizeof(struct ifla_vf_rate) }, [IFLA_VF_LINK_STATE] = { .len = sizeof(struct ifla_vf_link_state) }, + [IFLA_VF_RSS_QUERY_EN] = { .len = sizeof(struct ifla_vf_rss_query_en) }, }; static const struct nla_policy ifla_port_policy[IFLA_PORT_MAX+1] = { @@ -1479,6 +1509,17 @@ static int do_setvfinfo(struct net_device *dev, struct nlattr *attr) ivl->link_state); break; } + case IFLA_VF_RSS_QUERY_EN: { + struct ifla_vf_rss_query_en *ivrssq_en; + + ivrssq_en = nla_data(vf); + err = -EOPNOTSUPP; + if (ops->ndo_set_vf_rss_query_en) + err = ops->ndo_set_vf_rss_query_en(dev, + ivrssq_en->vf, + ivrssq_en->setting); + break; + } default: err = -EINVAL; break; @@ -1815,6 +1856,42 @@ errout: return err; } +static int rtnl_group_dellink(const struct net *net, int group) +{ + struct net_device *dev, *aux; + LIST_HEAD(list_kill); + bool found = false; + + if (!group) + return -EPERM; + + for_each_netdev(net, dev) { + if (dev->group == group) { + const struct rtnl_link_ops *ops; + + found = true; + ops = dev->rtnl_link_ops; + if (!ops || !ops->dellink) + return -EOPNOTSUPP; + } + } + + if (!found) + return -ENODEV; + + for_each_netdev_safe(net, dev, aux) { + if (dev->group == group) { + const struct rtnl_link_ops *ops; + + ops = dev->rtnl_link_ops; + ops->dellink(dev, &list_kill); + } + } + unregister_netdevice_many(&list_kill); + + return 0; +} + static int rtnl_dellink(struct sk_buff *skb, struct nlmsghdr *nlh) { struct net *net = sock_net(skb->sk); @@ -1838,6 +1915,8 @@ static int rtnl_dellink(struct sk_buff *skb, struct nlmsghdr *nlh) dev = __dev_get_by_index(net, ifm->ifi_index); else if (tb[IFLA_IFNAME]) dev = __dev_get_by_name(net, ifname); + else if (tb[IFLA_GROUP]) + return rtnl_group_dellink(net, nla_get_u32(tb[IFLA_GROUP])); else return -EINVAL; @@ -1873,7 +1952,7 @@ 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, unsigned char name_assign_type, + const char *ifname, unsigned char name_assign_type, const struct rtnl_link_ops *ops, struct nlattr *tb[]) { int err; @@ -2345,7 +2424,7 @@ EXPORT_SYMBOL(rtmsg_ifinfo); static int nlmsg_populate_fdb_fill(struct sk_buff *skb, struct net_device *dev, - u8 *addr, u32 pid, u32 seq, + u8 *addr, u16 vid, u32 pid, u32 seq, int type, unsigned int flags, int nlflags) { @@ -2367,6 +2446,9 @@ static int nlmsg_populate_fdb_fill(struct sk_buff *skb, if (nla_put(skb, NDA_LLADDR, ETH_ALEN, addr)) goto nla_put_failure; + if (vid) + if (nla_put(skb, NDA_VLAN, sizeof(u16), &vid)) + goto nla_put_failure; nlmsg_end(skb, nlh); return 0; @@ -2381,7 +2463,7 @@ static inline size_t rtnl_fdb_nlmsg_size(void) return NLMSG_ALIGN(sizeof(struct ndmsg)) + nla_total_size(ETH_ALEN); } -static void rtnl_fdb_notify(struct net_device *dev, u8 *addr, int type) +static void rtnl_fdb_notify(struct net_device *dev, u8 *addr, u16 vid, int type) { struct net *net = dev_net(dev); struct sk_buff *skb; @@ -2391,7 +2473,8 @@ static void rtnl_fdb_notify(struct net_device *dev, u8 *addr, int type) if (!skb) goto errout; - err = nlmsg_populate_fdb_fill(skb, dev, addr, 0, 0, type, NTF_SELF, 0); + err = nlmsg_populate_fdb_fill(skb, dev, addr, vid, + 0, 0, type, NTF_SELF, 0); if (err < 0) { kfree_skb(skb); goto errout; @@ -2526,7 +2609,7 @@ static int rtnl_fdb_add(struct sk_buff *skb, struct nlmsghdr *nlh) nlh->nlmsg_flags); if (!err) { - rtnl_fdb_notify(dev, addr, RTM_NEWNEIGH); + rtnl_fdb_notify(dev, addr, vid, RTM_NEWNEIGH); ndm->ndm_flags &= ~NTF_SELF; } } @@ -2627,7 +2710,7 @@ static int rtnl_fdb_del(struct sk_buff *skb, struct nlmsghdr *nlh) err = ndo_dflt_fdb_del(ndm, tb, dev, addr, vid); if (!err) { - rtnl_fdb_notify(dev, addr, RTM_DELNEIGH); + rtnl_fdb_notify(dev, addr, vid, RTM_DELNEIGH); ndm->ndm_flags &= ~NTF_SELF; } } @@ -2652,7 +2735,7 @@ static int nlmsg_populate_fdb(struct sk_buff *skb, if (*idx < cb->args[0]) goto skip; - err = nlmsg_populate_fdb_fill(skb, dev, ha->addr, + err = nlmsg_populate_fdb_fill(skb, dev, ha->addr, 0, portid, seq, RTM_NEWNEIGH, NTF_SELF, NLM_F_MULTI); @@ -2695,7 +2778,6 @@ static int rtnl_fdb_dump(struct sk_buff *skb, struct netlink_callback *cb) { 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; @@ -2719,7 +2801,6 @@ static int rtnl_fdb_dump(struct sk_buff *skb, struct netlink_callback *cb) return -ENODEV; ops = br_dev->netdev_ops; - bdev = br_dev; } for_each_netdev(net, dev) { @@ -2732,7 +2813,6 @@ static int rtnl_fdb_dump(struct sk_buff *skb, struct netlink_callback *cb) cops = br_dev->netdev_ops; } - bdev = dev; } else { if (dev != br_dev && !(dev->priv_flags & IFF_BRIDGE_PORT)) @@ -2742,7 +2822,6 @@ static int rtnl_fdb_dump(struct sk_buff *skb, struct netlink_callback *cb) !(dev->priv_flags & IFF_EBRIDGE)) continue; - bdev = br_dev; cops = ops; } @@ -2775,7 +2854,7 @@ static int brport_nla_put_flag(struct sk_buff *skb, u32 flags, u32 mask, int ndo_dflt_bridge_getlink(struct sk_buff *skb, u32 pid, u32 seq, struct net_device *dev, u16 mode, - u32 flags, u32 mask) + u32 flags, u32 mask, int nlflags) { struct nlmsghdr *nlh; struct ifinfomsg *ifm; @@ -2784,7 +2863,7 @@ int ndo_dflt_bridge_getlink(struct sk_buff *skb, u32 pid, u32 seq, u8 operstate = netif_running(dev) ? dev->operstate : IF_OPER_DOWN; struct net_device *br_dev = netdev_master_upper_dev_get(dev); - nlh = nlmsg_put(skb, pid, seq, RTM_NEWLINK, sizeof(*ifm), NLM_F_MULTI); + nlh = nlmsg_put(skb, pid, seq, RTM_NEWLINK, sizeof(*ifm), nlflags); if (nlh == NULL) return -EMSGSIZE; @@ -2804,8 +2883,8 @@ int ndo_dflt_bridge_getlink(struct sk_buff *skb, u32 pid, u32 seq, nla_put_u32(skb, IFLA_MASTER, br_dev->ifindex)) || (dev->addr_len && nla_put(skb, IFLA_ADDRESS, dev->addr_len, dev->dev_addr)) || - (dev->ifindex != dev->iflink && - nla_put_u32(skb, IFLA_LINK, dev->iflink))) + (dev->ifindex != dev_get_iflink(dev) && + nla_put_u32(skb, IFLA_LINK, dev_get_iflink(dev)))) goto nla_put_failure; br_afspec = nla_nest_start(skb, IFLA_AF_SPEC); @@ -2890,7 +2969,8 @@ static int rtnl_bridge_getlink(struct sk_buff *skb, struct netlink_callback *cb) if (br_dev && br_dev->netdev_ops->ndo_bridge_getlink) { if (idx >= cb->args[0] && br_dev->netdev_ops->ndo_bridge_getlink( - skb, portid, seq, dev, filter_mask) < 0) + skb, portid, seq, dev, filter_mask, + NLM_F_MULTI) < 0) break; idx++; } @@ -2898,7 +2978,8 @@ static int rtnl_bridge_getlink(struct sk_buff *skb, struct netlink_callback *cb) if (ops->ndo_bridge_getlink) { if (idx >= cb->args[0] && ops->ndo_bridge_getlink(skb, portid, seq, dev, - filter_mask) < 0) + filter_mask, + NLM_F_MULTI) < 0) break; idx++; } @@ -2939,7 +3020,7 @@ static int rtnl_bridge_notify(struct net_device *dev) goto errout; } - err = dev->netdev_ops->ndo_bridge_getlink(skb, 0, 0, dev, 0); + err = dev->netdev_ops->ndo_bridge_getlink(skb, 0, 0, dev, 0, 0); if (err < 0) goto errout; diff --git a/net/core/skbuff.c b/net/core/skbuff.c index 8e4ac97c8477..3cfff2a3d651 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -280,13 +280,14 @@ nodata: EXPORT_SYMBOL(__alloc_skb); /** - * build_skb - build a network buffer + * __build_skb - build a network buffer * @data: data buffer provided by caller - * @frag_size: size of fragment, or 0 if head was kmalloced + * @frag_size: size of data, or 0 if head was kmalloced * * Allocate a new &sk_buff. Caller provides space holding head and * skb_shared_info. @data must have been allocated by kmalloc() only if - * @frag_size is 0, otherwise data should come from the page allocator. + * @frag_size is 0, otherwise data should come from the page allocator + * or vmalloc() * The return is the new skb buffer. * On a failure the return is %NULL, and @data is not freed. * Notes : @@ -297,7 +298,7 @@ EXPORT_SYMBOL(__alloc_skb); * before giving packet to stack. * RX rings only contains data buffers, not full skbs. */ -struct sk_buff *build_skb(void *data, unsigned int frag_size) +struct sk_buff *__build_skb(void *data, unsigned int frag_size) { struct skb_shared_info *shinfo; struct sk_buff *skb; @@ -311,7 +312,6 @@ struct sk_buff *build_skb(void *data, unsigned int frag_size) memset(skb, 0, offsetof(struct sk_buff, tail)); skb->truesize = SKB_TRUESIZE(size); - skb->head_frag = frag_size != 0; atomic_set(&skb->users, 1); skb->head = data; skb->data = data; @@ -328,6 +328,23 @@ struct sk_buff *build_skb(void *data, unsigned int frag_size) return skb; } + +/* build_skb() is wrapper over __build_skb(), that specifically + * takes care of skb->head and skb->pfmemalloc + * This means that if @frag_size is not zero, then @data must be backed + * by a page fragment, not kmalloc() or vmalloc() + */ +struct sk_buff *build_skb(void *data, unsigned int frag_size) +{ + struct sk_buff *skb = __build_skb(data, frag_size); + + if (skb && frag_size) { + skb->head_frag = 1; + if (virt_to_head_page(data)->pfmemalloc) + skb->pfmemalloc = 1; + } + return skb; +} EXPORT_SYMBOL(build_skb); struct netdev_alloc_cache { @@ -348,7 +365,8 @@ static struct page *__page_frag_refill(struct netdev_alloc_cache *nc, gfp_t gfp = gfp_mask; if (order) { - gfp_mask |= __GFP_COMP | __GFP_NOWARN | __GFP_NORETRY; + gfp_mask |= __GFP_COMP | __GFP_NOWARN | __GFP_NORETRY | + __GFP_NOMEMALLOC; page = alloc_pages_node(NUMA_NO_NODE, gfp_mask, order); nc->frag.size = PAGE_SIZE << (page ? order : 0); } @@ -2865,7 +2883,6 @@ static void skb_ts_finish(struct ts_config *conf, struct ts_state *state) * @from: search offset * @to: search limit * @config: textsearch configuration - * @state: uninitialized textsearch state variable * * Finds a pattern in the skb data according to the specified * textsearch configuration. Use textsearch_next() to retrieve @@ -2873,17 +2890,17 @@ static void skb_ts_finish(struct ts_config *conf, struct ts_state *state) * to the first occurrence or UINT_MAX if no match was found. */ unsigned int skb_find_text(struct sk_buff *skb, unsigned int from, - unsigned int to, struct ts_config *config, - struct ts_state *state) + unsigned int to, struct ts_config *config) { + struct ts_state state; unsigned int ret; config->get_next_block = skb_ts_get_next_block; config->finish = skb_ts_finish; - skb_prepare_seq_read(skb, from, to, TS_SKB_CB(state)); + skb_prepare_seq_read(skb, from, to, TS_SKB_CB(&state)); - ret = textsearch_find(config, state); + ret = textsearch_find(config, &state); return (ret <= to - from ? ret : UINT_MAX); } EXPORT_SYMBOL(skb_find_text); @@ -3207,10 +3224,9 @@ int skb_gro_receive(struct sk_buff **head, struct sk_buff *skb) struct skb_shared_info *pinfo, *skbinfo = skb_shinfo(skb); unsigned int offset = skb_gro_offset(skb); unsigned int headlen = skb_headlen(skb); - struct sk_buff *nskb, *lp, *p = *head; unsigned int len = skb_gro_len(skb); + struct sk_buff *lp, *p = *head; unsigned int delta_truesize; - unsigned int headroom; if (unlikely(p->len + len >= 65536)) return -E2BIG; @@ -3277,48 +3293,6 @@ int skb_gro_receive(struct sk_buff **head, struct sk_buff *skb) NAPI_GRO_CB(skb)->free = NAPI_GRO_FREE_STOLEN_HEAD; goto done; } - /* switch back to head shinfo */ - pinfo = skb_shinfo(p); - - if (pinfo->frag_list) - goto merge; - if (skb_gro_len(p) != pinfo->gso_size) - return -E2BIG; - - headroom = skb_headroom(p); - nskb = alloc_skb(headroom + skb_gro_offset(p), GFP_ATOMIC); - if (unlikely(!nskb)) - return -ENOMEM; - - __copy_skb_header(nskb, p); - nskb->mac_len = p->mac_len; - - skb_reserve(nskb, headroom); - __skb_put(nskb, skb_gro_offset(p)); - - skb_set_mac_header(nskb, skb_mac_header(p) - p->data); - skb_set_network_header(nskb, skb_network_offset(p)); - skb_set_transport_header(nskb, skb_transport_offset(p)); - - __skb_pull(p, skb_gro_offset(p)); - memcpy(skb_mac_header(nskb), skb_mac_header(p), - p->data - skb_mac_header(p)); - - skb_shinfo(nskb)->frag_list = p; - skb_shinfo(nskb)->gso_size = pinfo->gso_size; - pinfo->gso_size = 0; - __skb_header_release(p); - NAPI_GRO_CB(nskb)->last = p; - - nskb->data_len += p->len; - nskb->truesize += p->truesize; - nskb->len += p->len; - - *head = nskb; - nskb->next = p->next; - p->next = NULL; - - p = nskb; merge: delta_truesize = skb->truesize; @@ -3796,7 +3770,6 @@ void skb_complete_wifi_ack(struct sk_buff *skb, bool acked) } EXPORT_SYMBOL_GPL(skb_complete_wifi_ack); - /** * skb_partial_csum_set - set up and verify partial csum values for packet * @skb: the skb to set @@ -4169,19 +4142,21 @@ EXPORT_SYMBOL(skb_try_coalesce); */ void skb_scrub_packet(struct sk_buff *skb, bool xnet) { - if (xnet) - skb_orphan(skb); skb->tstamp.tv64 = 0; skb->pkt_type = PACKET_HOST; skb->skb_iif = 0; skb->ignore_df = 0; skb_dst_drop(skb); - skb->mark = 0; skb_sender_cpu_clear(skb); - skb_init_secmark(skb); secpath_reset(skb); nf_reset(skb); nf_reset_trace(skb); + + if (!xnet) + return; + + skb_orphan(skb); + skb->mark = 0; } EXPORT_SYMBOL_GPL(skb_scrub_packet); diff --git a/net/core/sock.c b/net/core/sock.c index 71e3e5f1eaa0..e891bcf325ca 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -466,7 +466,7 @@ int sock_queue_rcv_skb(struct sock *sk, struct sk_buff *skb) skb_dst_force(skb); spin_lock_irqsave(&list->lock, flags); - skb->dropcount = atomic_read(&sk->sk_drops); + sock_skb_set_dropcount(sk, skb); __skb_queue_tail(list, skb); spin_unlock_irqrestore(&list->lock, flags); @@ -947,8 +947,6 @@ set_rcvbuf: sk->sk_mark = val; break; - /* We implement the SO_SNDLOWAT etc to - not be settable (1003.1g 5.3) */ case SO_RXQ_OVFL: sock_valbool_flag(sk, SOCK_RXQ_OVFL, valbool); break; @@ -1253,6 +1251,9 @@ int sock_getsockopt(struct socket *sock, int level, int optname, break; default: + /* We implement the SO_SNDLOWAT etc to not be settable + * (1003.1g 7). + */ return -ENOPROTOOPT; } @@ -1473,9 +1474,8 @@ void sk_release_kernel(struct sock *sk) return; sock_hold(sk); - sock_release(sk->sk_socket); - release_net(sock_net(sk)); sock_net_set(sk, get_net(&init_net)); + sock_release(sk->sk_socket); sock_put(sk); } EXPORT_SYMBOL(sk_release_kernel); @@ -1557,6 +1557,7 @@ struct sock *sk_clone_lock(const struct sock *sk, const gfp_t priority) newsk->sk_err = 0; newsk->sk_priority = 0; newsk->sk_incoming_cpu = raw_smp_processor_id(); + atomic64_set(&newsk->sk_cookie, 0); /* * Before updating sk_refcnt, we must commit prior changes to memory * (Documentation/RCU/rculist_nulls.txt for details) @@ -1684,19 +1685,6 @@ void sock_efree(struct sk_buff *skb) } EXPORT_SYMBOL(sock_efree); -#ifdef CONFIG_INET -void sock_edemux(struct sk_buff *skb) -{ - struct sock *sk = skb->sk; - - if (sk->sk_state == TCP_TIME_WAIT) - inet_twsk_put(inet_twsk(sk)); - else - sock_put(sk); -} -EXPORT_SYMBOL(sock_edemux); -#endif - kuid_t sock_i_uid(struct sock *sk) { kuid_t uid; @@ -2186,15 +2174,14 @@ int sock_no_getsockopt(struct socket *sock, int level, int optname, } EXPORT_SYMBOL(sock_no_getsockopt); -int sock_no_sendmsg(struct kiocb *iocb, struct socket *sock, struct msghdr *m, - size_t len) +int sock_no_sendmsg(struct socket *sock, struct msghdr *m, size_t len) { return -EOPNOTSUPP; } EXPORT_SYMBOL(sock_no_sendmsg); -int sock_no_recvmsg(struct kiocb *iocb, struct socket *sock, struct msghdr *m, - size_t len, int flags) +int sock_no_recvmsg(struct socket *sock, struct msghdr *m, size_t len, + int flags) { return -EOPNOTSUPP; } @@ -2566,14 +2553,14 @@ int compat_sock_common_getsockopt(struct socket *sock, int level, int optname, EXPORT_SYMBOL(compat_sock_common_getsockopt); #endif -int sock_common_recvmsg(struct kiocb *iocb, struct socket *sock, - struct msghdr *msg, size_t size, int flags) +int sock_common_recvmsg(struct socket *sock, struct msghdr *msg, size_t size, + int flags) { struct sock *sk = sock->sk; int addr_len = 0; int err; - err = sk->sk_prot->recvmsg(iocb, sk, msg, size, flags & MSG_DONTWAIT, + err = sk->sk_prot->recvmsg(sk, msg, size, flags & MSG_DONTWAIT, flags & ~MSG_DONTWAIT, &addr_len); if (err >= 0) msg->msg_namelen = addr_len; @@ -2750,6 +2737,42 @@ static inline void release_proto_idx(struct proto *prot) } #endif +static void req_prot_cleanup(struct request_sock_ops *rsk_prot) +{ + if (!rsk_prot) + return; + kfree(rsk_prot->slab_name); + rsk_prot->slab_name = NULL; + if (rsk_prot->slab) { + kmem_cache_destroy(rsk_prot->slab); + rsk_prot->slab = NULL; + } +} + +static int req_prot_init(const struct proto *prot) +{ + struct request_sock_ops *rsk_prot = prot->rsk_prot; + + if (!rsk_prot) + return 0; + + rsk_prot->slab_name = kasprintf(GFP_KERNEL, "request_sock_%s", + prot->name); + if (!rsk_prot->slab_name) + return -ENOMEM; + + rsk_prot->slab = kmem_cache_create(rsk_prot->slab_name, + rsk_prot->obj_size, 0, + 0, NULL); + + if (!rsk_prot->slab) { + pr_crit("%s: Can't create request sock SLAB cache!\n", + prot->name); + return -ENOMEM; + } + return 0; +} + int proto_register(struct proto *prot, int alloc_slab) { if (alloc_slab) { @@ -2763,21 +2786,8 @@ int proto_register(struct proto *prot, int alloc_slab) goto out; } - if (prot->rsk_prot != NULL) { - prot->rsk_prot->slab_name = kasprintf(GFP_KERNEL, "request_sock_%s", prot->name); - if (prot->rsk_prot->slab_name == NULL) - goto out_free_sock_slab; - - prot->rsk_prot->slab = kmem_cache_create(prot->rsk_prot->slab_name, - prot->rsk_prot->obj_size, 0, - SLAB_HWCACHE_ALIGN, NULL); - - if (prot->rsk_prot->slab == NULL) { - pr_crit("%s: Can't create request sock SLAB cache!\n", - prot->name); - goto out_free_request_sock_slab_name; - } - } + if (req_prot_init(prot)) + goto out_free_request_sock_slab; if (prot->twsk_prot != NULL) { prot->twsk_prot->twsk_slab_name = kasprintf(GFP_KERNEL, "tw_sock_%s", prot->name); @@ -2789,8 +2799,7 @@ int proto_register(struct proto *prot, int alloc_slab) kmem_cache_create(prot->twsk_prot->twsk_slab_name, prot->twsk_prot->twsk_obj_size, 0, - SLAB_HWCACHE_ALIGN | - prot->slab_flags, + prot->slab_flags, NULL); if (prot->twsk_prot->twsk_slab == NULL) goto out_free_timewait_sock_slab_name; @@ -2806,14 +2815,8 @@ int proto_register(struct proto *prot, int alloc_slab) out_free_timewait_sock_slab_name: kfree(prot->twsk_prot->twsk_slab_name); out_free_request_sock_slab: - if (prot->rsk_prot && prot->rsk_prot->slab) { - kmem_cache_destroy(prot->rsk_prot->slab); - prot->rsk_prot->slab = NULL; - } -out_free_request_sock_slab_name: - if (prot->rsk_prot) - kfree(prot->rsk_prot->slab_name); -out_free_sock_slab: + req_prot_cleanup(prot->rsk_prot); + kmem_cache_destroy(prot->slab); prot->slab = NULL; out: @@ -2833,11 +2836,7 @@ void proto_unregister(struct proto *prot) prot->slab = NULL; } - if (prot->rsk_prot != NULL && prot->rsk_prot->slab != NULL) { - kmem_cache_destroy(prot->rsk_prot->slab); - kfree(prot->rsk_prot->slab_name); - prot->rsk_prot->slab = NULL; - } + req_prot_cleanup(prot->rsk_prot); if (prot->twsk_prot != NULL && prot->twsk_prot->twsk_slab != NULL) { kmem_cache_destroy(prot->twsk_prot->twsk_slab); diff --git a/net/core/sock_diag.c b/net/core/sock_diag.c index ad704c757bb4..74dddf84adcd 100644 --- a/net/core/sock_diag.c +++ b/net/core/sock_diag.c @@ -13,22 +13,39 @@ static const struct sock_diag_handler *sock_diag_handlers[AF_MAX]; static int (*inet_rcv_compat)(struct sk_buff *skb, struct nlmsghdr *nlh); static DEFINE_MUTEX(sock_diag_table_mutex); -int sock_diag_check_cookie(void *sk, __u32 *cookie) +static u64 sock_gen_cookie(struct sock *sk) { - if ((cookie[0] != INET_DIAG_NOCOOKIE || - cookie[1] != INET_DIAG_NOCOOKIE) && - ((u32)(unsigned long)sk != cookie[0] || - (u32)((((unsigned long)sk) >> 31) >> 1) != cookie[1])) - return -ESTALE; - else + while (1) { + u64 res = atomic64_read(&sk->sk_cookie); + + if (res) + return res; + res = atomic64_inc_return(&sock_net(sk)->cookie_gen); + atomic64_cmpxchg(&sk->sk_cookie, 0, res); + } +} + +int sock_diag_check_cookie(struct sock *sk, const __u32 *cookie) +{ + u64 res; + + if (cookie[0] == INET_DIAG_NOCOOKIE && cookie[1] == INET_DIAG_NOCOOKIE) return 0; + + res = sock_gen_cookie(sk); + if ((u32)res != cookie[0] || (u32)(res >> 32) != cookie[1]) + return -ESTALE; + + return 0; } EXPORT_SYMBOL_GPL(sock_diag_check_cookie); -void sock_diag_save_cookie(void *sk, __u32 *cookie) +void sock_diag_save_cookie(struct sock *sk, __u32 *cookie) { - cookie[0] = (u32)(unsigned long)sk; - cookie[1] = (u32)(((unsigned long)sk >> 31) >> 1); + u64 res = sock_gen_cookie(sk); + + cookie[0] = (u32)res; + cookie[1] = (u32)(res >> 32); } EXPORT_SYMBOL_GPL(sock_diag_save_cookie); diff --git a/net/core/sysctl_net_core.c b/net/core/sysctl_net_core.c index 8ce351ffceb1..95b6139d710c 100644 --- a/net/core/sysctl_net_core.c +++ b/net/core/sysctl_net_core.c @@ -24,7 +24,6 @@ static int zero = 0; static int one = 1; -static int ushort_max = USHRT_MAX; static int min_sndbuf = SOCK_MIN_SNDBUF; static int min_rcvbuf = SOCK_MIN_RCVBUF; @@ -403,7 +402,6 @@ static struct ctl_table netns_core_table[] = { .maxlen = sizeof(int), .mode = 0644, .extra1 = &zero, - .extra2 = &ushort_max, .proc_handler = proc_dointvec_minmax }, { } diff --git a/net/dcb/dcbnl.c b/net/dcb/dcbnl.c index 93ea80196f0e..5b21f6f88e97 100644 --- a/net/dcb/dcbnl.c +++ b/net/dcb/dcbnl.c @@ -177,6 +177,8 @@ static const struct nla_policy dcbnl_ieee_policy[DCB_ATTR_IEEE_MAX + 1] = { [DCB_ATTR_IEEE_PFC] = {.len = sizeof(struct ieee_pfc)}, [DCB_ATTR_IEEE_APP_TABLE] = {.type = NLA_NESTED}, [DCB_ATTR_IEEE_MAXRATE] = {.len = sizeof(struct ieee_maxrate)}, + [DCB_ATTR_IEEE_QCN] = {.len = sizeof(struct ieee_qcn)}, + [DCB_ATTR_IEEE_QCN_STATS] = {.len = sizeof(struct ieee_qcn_stats)}, }; static const struct nla_policy dcbnl_ieee_app[DCB_ATTR_IEEE_APP_MAX + 1] = { @@ -1030,7 +1032,7 @@ nla_put_failure: return err; } -/* Handle IEEE 802.1Qaz GET commands. */ +/* Handle IEEE 802.1Qaz/802.1Qau/802.1Qbb GET commands. */ static int dcbnl_ieee_fill(struct sk_buff *skb, struct net_device *netdev) { struct nlattr *ieee, *app; @@ -1067,6 +1069,32 @@ static int dcbnl_ieee_fill(struct sk_buff *skb, struct net_device *netdev) } } + if (ops->ieee_getqcn) { + struct ieee_qcn qcn; + + memset(&qcn, 0, sizeof(qcn)); + err = ops->ieee_getqcn(netdev, &qcn); + if (!err) { + err = nla_put(skb, DCB_ATTR_IEEE_QCN, + sizeof(qcn), &qcn); + if (err) + return -EMSGSIZE; + } + } + + if (ops->ieee_getqcnstats) { + struct ieee_qcn_stats qcn_stats; + + memset(&qcn_stats, 0, sizeof(qcn_stats)); + err = ops->ieee_getqcnstats(netdev, &qcn_stats); + if (!err) { + err = nla_put(skb, DCB_ATTR_IEEE_QCN_STATS, + sizeof(qcn_stats), &qcn_stats); + if (err) + return -EMSGSIZE; + } + } + if (ops->ieee_getpfc) { struct ieee_pfc pfc; memset(&pfc, 0, sizeof(pfc)); @@ -1379,8 +1407,9 @@ int dcbnl_cee_notify(struct net_device *dev, int event, int cmd, } EXPORT_SYMBOL(dcbnl_cee_notify); -/* Handle IEEE 802.1Qaz SET commands. If any requested operation can not - * be completed the entire msg is aborted and error value is returned. +/* Handle IEEE 802.1Qaz/802.1Qau/802.1Qbb SET commands. + * If any requested operation can not be completed + * the entire msg is aborted and error value is returned. * No attempt is made to reconcile the case where only part of the * cmd can be completed. */ @@ -1417,6 +1446,15 @@ static int dcbnl_ieee_set(struct net_device *netdev, struct nlmsghdr *nlh, goto err; } + if (ieee[DCB_ATTR_IEEE_QCN] && ops->ieee_setqcn) { + struct ieee_qcn *qcn = + nla_data(ieee[DCB_ATTR_IEEE_QCN]); + + err = ops->ieee_setqcn(netdev, qcn); + if (err) + goto err; + } + if (ieee[DCB_ATTR_IEEE_PFC] && ops->ieee_setpfc) { struct ieee_pfc *pfc = nla_data(ieee[DCB_ATTR_IEEE_PFC]); err = ops->ieee_setpfc(netdev, pfc); diff --git a/net/dccp/dccp.h b/net/dccp/dccp.h index e4c144fa706f..bebc735f5afc 100644 --- a/net/dccp/dccp.h +++ b/net/dccp/dccp.h @@ -280,8 +280,7 @@ struct sock *dccp_v4_request_recv_sock(struct sock *sk, struct sk_buff *skb, struct request_sock *req, struct dst_entry *dst); struct sock *dccp_check_req(struct sock *sk, struct sk_buff *skb, - struct request_sock *req, - struct request_sock **prev); + struct request_sock *req); int dccp_child_process(struct sock *parent, struct sock *child, struct sk_buff *skb); @@ -310,16 +309,15 @@ int compat_dccp_setsockopt(struct sock *sk, int level, int optname, char __user *optval, unsigned int optlen); #endif int dccp_ioctl(struct sock *sk, int cmd, unsigned long arg); -int dccp_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg, - size_t size); -int dccp_recvmsg(struct kiocb *iocb, struct sock *sk, - struct msghdr *msg, size_t len, int nonblock, int flags, - int *addr_len); +int dccp_sendmsg(struct sock *sk, struct msghdr *msg, size_t size); +int dccp_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, int nonblock, + int flags, int *addr_len); void dccp_shutdown(struct sock *sk, int how); int inet_dccp_listen(struct socket *sock, int backlog); unsigned int dccp_poll(struct file *file, struct socket *sock, poll_table *wait); int dccp_v4_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len); +void dccp_req_err(struct sock *sk, u64 seq); struct sk_buff *dccp_ctl_make_reset(struct sock *sk, struct sk_buff *skb); int dccp_send_reset(struct sock *sk, enum dccp_reset_codes code); diff --git a/net/dccp/diag.c b/net/dccp/diag.c index 028fc43aacbd..5a45f8de5d99 100644 --- a/net/dccp/diag.c +++ b/net/dccp/diag.c @@ -49,13 +49,14 @@ static void dccp_diag_get_info(struct sock *sk, struct inet_diag_msg *r, } static void dccp_diag_dump(struct sk_buff *skb, struct netlink_callback *cb, - struct inet_diag_req_v2 *r, struct nlattr *bc) + const struct inet_diag_req_v2 *r, struct nlattr *bc) { inet_diag_dump_icsk(&dccp_hashinfo, skb, cb, r, bc); } -static int dccp_diag_dump_one(struct sk_buff *in_skb, const struct nlmsghdr *nlh, - struct inet_diag_req_v2 *req) +static int dccp_diag_dump_one(struct sk_buff *in_skb, + const struct nlmsghdr *nlh, + const struct inet_diag_req_v2 *req) { return inet_diag_dump_one_icsk(&dccp_hashinfo, in_skb, nlh, req); } diff --git a/net/dccp/ipv4.c b/net/dccp/ipv4.c index e45b968613a4..ccf4c5629b3c 100644 --- a/net/dccp/ipv4.c +++ b/net/dccp/ipv4.c @@ -89,10 +89,9 @@ int dccp_v4_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len) if (inet->inet_saddr == 0) inet->inet_saddr = fl4->saddr; - inet->inet_rcv_saddr = inet->inet_saddr; - + sk_rcv_saddr_set(sk, inet->inet_saddr); inet->inet_dport = usin->sin_port; - inet->inet_daddr = daddr; + sk_daddr_set(sk, daddr); inet_csk(sk)->icsk_ext_hdr_len = 0; if (inet_opt) @@ -196,6 +195,32 @@ static void dccp_do_redirect(struct sk_buff *skb, struct sock *sk) dst->ops->redirect(dst, sk, skb); } +void dccp_req_err(struct sock *sk, u64 seq) + { + struct request_sock *req = inet_reqsk(sk); + struct net *net = sock_net(sk); + + /* + * ICMPs are not backlogged, hence we cannot get an established + * socket here. + */ + WARN_ON(req->sk); + + if (!between48(seq, dccp_rsk(req)->dreq_iss, dccp_rsk(req)->dreq_gss)) { + NET_INC_STATS_BH(net, LINUX_MIB_OUTOFWINDOWICMPS); + reqsk_put(req); + } else { + /* + * Still in RESPOND, just remove it silently. + * There is no good way to pass the error to the newly + * created socket, and POSIX does not want network + * errors returned from accept(). + */ + inet_csk_reqsk_queue_drop(req->rsk_listener, req); + } +} +EXPORT_SYMBOL(dccp_req_err); + /* * This routine is called by the ICMP module when it gets some sort of error * condition. If err < 0 then the socket should be closed and the error @@ -228,10 +253,11 @@ static void dccp_v4_err(struct sk_buff *skb, u32 info) return; } - sk = inet_lookup(net, &dccp_hashinfo, - iph->daddr, dh->dccph_dport, - iph->saddr, dh->dccph_sport, inet_iif(skb)); - if (sk == NULL) { + sk = __inet_lookup_established(net, &dccp_hashinfo, + iph->daddr, dh->dccph_dport, + iph->saddr, ntohs(dh->dccph_sport), + inet_iif(skb)); + if (!sk) { ICMP_INC_STATS_BH(net, ICMP_MIB_INERRORS); return; } @@ -240,6 +266,9 @@ static void dccp_v4_err(struct sk_buff *skb, u32 info) inet_twsk_put(inet_twsk(sk)); return; } + seq = dccp_hdr_seq(dh); + if (sk->sk_state == DCCP_NEW_SYN_RECV) + return dccp_req_err(sk, seq); bh_lock_sock(sk); /* If too many ICMPs get dropped on busy @@ -252,7 +281,6 @@ static void dccp_v4_err(struct sk_buff *skb, u32 info) goto out; dp = dccp_sk(sk); - seq = dccp_hdr_seq(dh); if ((1 << sk->sk_state) & ~(DCCPF_REQUESTING | DCCPF_LISTEN) && !between48(seq, dp->dccps_awl, dp->dccps_awh)) { NET_INC_STATS_BH(net, LINUX_MIB_OUTOFWINDOWICMPS); @@ -289,35 +317,6 @@ static void dccp_v4_err(struct sk_buff *skb, u32 info) } switch (sk->sk_state) { - struct request_sock *req , **prev; - case DCCP_LISTEN: - if (sock_owned_by_user(sk)) - goto out; - req = inet_csk_search_req(sk, &prev, dh->dccph_dport, - iph->daddr, iph->saddr); - if (!req) - goto out; - - /* - * ICMPs are not backlogged, hence we cannot get an established - * socket here. - */ - WARN_ON(req->sk); - - if (!between48(seq, dccp_rsk(req)->dreq_iss, - dccp_rsk(req)->dreq_gss)) { - NET_INC_STATS_BH(net, LINUX_MIB_OUTOFWINDOWICMPS); - goto out; - } - /* - * Still in RESPOND, just remove it silently. - * There is no good way to pass the error to the newly - * created socket, and POSIX does not want network - * errors returned from accept(). - */ - inet_csk_reqsk_queue_drop(sk, req, prev); - goto out; - case DCCP_REQUESTING: case DCCP_RESPOND: if (!sock_owned_by_user(sk)) { @@ -408,8 +407,8 @@ struct sock *dccp_v4_request_recv_sock(struct sock *sk, struct sk_buff *skb, newinet = inet_sk(newsk); ireq = inet_rsk(req); - newinet->inet_daddr = ireq->ir_rmt_addr; - newinet->inet_rcv_saddr = ireq->ir_loc_addr; + sk_daddr_set(newsk, ireq->ir_rmt_addr); + sk_rcv_saddr_set(newsk, ireq->ir_loc_addr); newinet->inet_saddr = ireq->ir_loc_addr; newinet->inet_opt = ireq->opt; ireq->opt = NULL; @@ -449,14 +448,15 @@ static struct sock *dccp_v4_hnd_req(struct sock *sk, struct sk_buff *skb) const struct dccp_hdr *dh = dccp_hdr(skb); const struct iphdr *iph = ip_hdr(skb); struct sock *nsk; - struct request_sock **prev; /* Find possible connection requests. */ - struct request_sock *req = inet_csk_search_req(sk, &prev, - dh->dccph_sport, + struct request_sock *req = inet_csk_search_req(sk, dh->dccph_sport, iph->saddr, iph->daddr); - if (req != NULL) - return dccp_check_req(sk, skb, req, prev); - + if (req) { + nsk = dccp_check_req(sk, skb, req); + if (!nsk) + reqsk_put(req); + return nsk; + } nsk = inet_lookup_established(sock_net(sk), &dccp_hashinfo, iph->saddr, dh->dccph_sport, iph->daddr, dh->dccph_dport, @@ -575,7 +575,7 @@ static void dccp_v4_reqsk_destructor(struct request_sock *req) kfree(inet_rsk(req)->opt); } -void dccp_syn_ack_timeout(struct sock *sk, struct request_sock *req) +void dccp_syn_ack_timeout(const struct request_sock *req) { } EXPORT_SYMBOL(dccp_syn_ack_timeout); @@ -624,7 +624,7 @@ int dccp_v4_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 = inet_reqsk_alloc(&dccp_request_sock_ops); + req = inet_reqsk_alloc(&dccp_request_sock_ops, sk); if (req == NULL) goto drop; @@ -639,8 +639,10 @@ int dccp_v4_conn_request(struct sock *sk, struct sk_buff *skb) goto drop_and_free; ireq = inet_rsk(req); - ireq->ir_loc_addr = ip_hdr(skb)->daddr; - ireq->ir_rmt_addr = ip_hdr(skb)->saddr; + sk_rcv_saddr_set(req_to_sk(req), ip_hdr(skb)->daddr); + sk_daddr_set(req_to_sk(req), ip_hdr(skb)->saddr); + ireq->ireq_family = AF_INET; + ireq->ir_iif = sk->sk_bound_dev_if; /* * Step 3: Process LISTEN state diff --git a/net/dccp/ipv6.c b/net/dccp/ipv6.c index 6bcaa33cd804..5165571f397a 100644 --- a/net/dccp/ipv6.c +++ b/net/dccp/ipv6.c @@ -40,19 +40,6 @@ static const struct inet_connection_sock_af_ops dccp_ipv6_mapped; static const struct inet_connection_sock_af_ops dccp_ipv6_af_ops; -static void dccp_v6_hash(struct sock *sk) -{ - if (sk->sk_state != DCCP_CLOSED) { - if (inet_csk(sk)->icsk_af_ops == &dccp_ipv6_mapped) { - inet_hash(sk); - return; - } - local_bh_disable(); - __inet6_hash(sk, NULL); - local_bh_enable(); - } -} - /* add pseudo-header to DCCP checksum stored in skb->csum */ static inline __sum16 dccp_v6_csum_finish(struct sk_buff *skb, const struct in6_addr *saddr, @@ -98,11 +85,12 @@ static void dccp_v6_err(struct sk_buff *skb, struct inet6_skb_parm *opt, return; } - sk = inet6_lookup(net, &dccp_hashinfo, - &hdr->daddr, dh->dccph_dport, - &hdr->saddr, dh->dccph_sport, inet6_iif(skb)); + sk = __inet6_lookup_established(net, &dccp_hashinfo, + &hdr->daddr, dh->dccph_dport, + &hdr->saddr, ntohs(dh->dccph_sport), + inet6_iif(skb)); - if (sk == NULL) { + if (!sk) { ICMP6_INC_STATS_BH(net, __in6_dev_get(skb->dev), ICMP6_MIB_INERRORS); return; @@ -112,6 +100,9 @@ static void dccp_v6_err(struct sk_buff *skb, struct inet6_skb_parm *opt, inet_twsk_put(inet_twsk(sk)); return; } + seq = dccp_hdr_seq(dh); + if (sk->sk_state == DCCP_NEW_SYN_RECV) + return dccp_req_err(sk, seq); bh_lock_sock(sk); if (sock_owned_by_user(sk)) @@ -121,7 +112,6 @@ static void dccp_v6_err(struct sk_buff *skb, struct inet6_skb_parm *opt, goto out; dp = dccp_sk(sk); - seq = dccp_hdr_seq(dh); if ((1 << sk->sk_state) & ~(DCCPF_REQUESTING | DCCPF_LISTEN) && !between48(seq, dp->dccps_awl, dp->dccps_awh)) { NET_INC_STATS_BH(net, LINUX_MIB_OUTOFWINDOWICMPS); @@ -162,32 +152,6 @@ static void dccp_v6_err(struct sk_buff *skb, struct inet6_skb_parm *opt, /* Might be for an request_sock */ switch (sk->sk_state) { - struct request_sock *req, **prev; - case DCCP_LISTEN: - if (sock_owned_by_user(sk)) - goto out; - - req = inet6_csk_search_req(sk, &prev, dh->dccph_dport, - &hdr->daddr, &hdr->saddr, - inet6_iif(skb)); - if (req == NULL) - goto out; - - /* - * ICMPs are not backlogged, hence we cannot get an established - * socket here. - */ - WARN_ON(req->sk != NULL); - - if (!between48(seq, dccp_rsk(req)->dreq_iss, - dccp_rsk(req)->dreq_gss)) { - NET_INC_STATS_BH(net, LINUX_MIB_OUTOFWINDOWICMPS); - goto out; - } - - inet_csk_reqsk_queue_drop(sk, req, prev); - goto out; - case DCCP_REQUESTING: case DCCP_RESPOND: /* Cannot happen. It can, it SYNs are crossed. --ANK */ @@ -330,17 +294,17 @@ static struct sock *dccp_v6_hnd_req(struct sock *sk,struct sk_buff *skb) { const struct dccp_hdr *dh = dccp_hdr(skb); const struct ipv6hdr *iph = ipv6_hdr(skb); + struct request_sock *req; struct sock *nsk; - struct request_sock **prev; - /* Find possible connection requests. */ - struct request_sock *req = inet6_csk_search_req(sk, &prev, - dh->dccph_sport, - &iph->saddr, - &iph->daddr, - inet6_iif(skb)); - if (req != NULL) - return dccp_check_req(sk, skb, req, prev); + req = inet6_csk_search_req(sk, dh->dccph_sport, &iph->saddr, + &iph->daddr, inet6_iif(skb)); + if (req) { + nsk = dccp_check_req(sk, skb, req); + if (!nsk) + reqsk_put(req); + return nsk; + } nsk = __inet6_lookup_established(sock_net(sk), &dccp_hashinfo, &iph->saddr, dh->dccph_sport, &iph->daddr, ntohs(dh->dccph_dport), @@ -386,7 +350,7 @@ 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 = inet_reqsk_alloc(&dccp6_request_sock_ops); + req = inet_reqsk_alloc(&dccp6_request_sock_ops, sk); if (req == NULL) goto drop; @@ -403,6 +367,7 @@ static int dccp_v6_conn_request(struct sock *sk, struct sk_buff *skb) ireq = inet_rsk(req); ireq->ir_v6_rmt_addr = ipv6_hdr(skb)->saddr; ireq->ir_v6_loc_addr = ipv6_hdr(skb)->daddr; + ireq->ireq_family = AF_INET6; if (ipv6_opt_accepted(sk, skb, IP6CB(skb)) || np->rxopt.bits.rxinfo || np->rxopt.bits.rxoinfo || @@ -469,11 +434,7 @@ static struct sock *dccp_v6_request_recv_sock(struct sock *sk, memcpy(newnp, np, sizeof(struct ipv6_pinfo)); - ipv6_addr_set_v4mapped(newinet->inet_daddr, &newsk->sk_v6_daddr); - - ipv6_addr_set_v4mapped(newinet->inet_saddr, &newnp->saddr); - - newsk->sk_v6_rcv_saddr = newnp->saddr; + newnp->saddr = newsk->sk_v6_rcv_saddr; inet_csk(newsk)->icsk_af_ops = &dccp_ipv6_mapped; newsk->sk_backlog_rcv = dccp_v4_do_rcv; @@ -591,7 +552,7 @@ static struct sock *dccp_v6_request_recv_sock(struct sock *sk, dccp_done(newsk); goto out; } - __inet6_hash(newsk, NULL); + __inet_hash(newsk, NULL); return newsk; @@ -916,9 +877,7 @@ static int dccp_v6_connect(struct sock *sk, struct sockaddr *uaddr, sk->sk_backlog_rcv = dccp_v6_do_rcv; goto failure; } - ipv6_addr_set_v4mapped(inet->inet_saddr, &np->saddr); - ipv6_addr_set_v4mapped(inet->inet_rcv_saddr, &sk->sk_v6_rcv_saddr); - + np->saddr = sk->sk_v6_rcv_saddr; return err; } @@ -1061,7 +1020,7 @@ static struct proto dccp_v6_prot = { .sendmsg = dccp_sendmsg, .recvmsg = dccp_recvmsg, .backlog_rcv = dccp_v6_do_rcv, - .hash = dccp_v6_hash, + .hash = inet_hash, .unhash = inet_unhash, .accept = inet_csk_accept, .get_port = inet_csk_get_port, diff --git a/net/dccp/minisocks.c b/net/dccp/minisocks.c index b50dc436db1f..30addee2dd03 100644 --- a/net/dccp/minisocks.c +++ b/net/dccp/minisocks.c @@ -27,28 +27,16 @@ struct inet_timewait_death_row dccp_death_row = { .sysctl_max_tw_buckets = NR_FILE * 2, - .period = DCCP_TIMEWAIT_LEN / INET_TWDR_TWKILL_SLOTS, - .death_lock = __SPIN_LOCK_UNLOCKED(dccp_death_row.death_lock), .hashinfo = &dccp_hashinfo, - .tw_timer = TIMER_INITIALIZER(inet_twdr_hangman, 0, - (unsigned long)&dccp_death_row), - .twkill_work = __WORK_INITIALIZER(dccp_death_row.twkill_work, - inet_twdr_twkill_work), -/* Short-time timewait calendar */ - - .twcal_hand = -1, - .twcal_timer = TIMER_INITIALIZER(inet_twdr_twcal_tick, 0, - (unsigned long)&dccp_death_row), }; EXPORT_SYMBOL_GPL(dccp_death_row); void dccp_time_wait(struct sock *sk, int state, int timeo) { - struct inet_timewait_sock *tw = NULL; + struct inet_timewait_sock *tw; - if (dccp_death_row.tw_count < dccp_death_row.sysctl_max_tw_buckets) - tw = inet_twsk_alloc(sk, state); + tw = inet_twsk_alloc(sk, &dccp_death_row, state); if (tw != NULL) { const struct inet_connection_sock *icsk = inet_csk(sk); @@ -71,8 +59,7 @@ void dccp_time_wait(struct sock *sk, int state, int timeo) if (state == DCCP_TIME_WAIT) timeo = DCCP_TIMEWAIT_LEN; - inet_twsk_schedule(tw, &dccp_death_row, timeo, - DCCP_TIMEWAIT_LEN); + inet_twsk_schedule(tw, timeo); inet_twsk_put(tw); } else { /* Sorry, if we're out of memory, just CLOSE this @@ -152,8 +139,7 @@ EXPORT_SYMBOL_GPL(dccp_create_openreq_child); * as an request_sock. */ struct sock *dccp_check_req(struct sock *sk, struct sk_buff *skb, - struct request_sock *req, - struct request_sock **prev) + struct request_sock *req) { struct sock *child = NULL; struct dccp_request_sock *dreq = dccp_rsk(req); @@ -200,8 +186,7 @@ struct sock *dccp_check_req(struct sock *sk, struct sk_buff *skb, if (child == NULL) goto listen_overflow; - inet_csk_reqsk_queue_unlink(sk, req, prev); - inet_csk_reqsk_queue_removed(sk, req); + inet_csk_reqsk_queue_drop(sk, req); inet_csk_reqsk_queue_add(sk, req, child); out: return child; @@ -212,7 +197,7 @@ drop: if (dccp_hdr(skb)->dccph_type != DCCP_PKT_RESET) req->rsk_ops->send_reset(sk, skb); - inet_csk_reqsk_queue_drop(sk, req, prev); + inet_csk_reqsk_queue_drop(sk, req); goto out; } diff --git a/net/dccp/probe.c b/net/dccp/probe.c index 595ddf0459db..d8346d0eadeb 100644 --- a/net/dccp/probe.c +++ b/net/dccp/probe.c @@ -72,8 +72,7 @@ static void printl(const char *fmt, ...) wake_up(&dccpw.wait); } -static int jdccp_sendmsg(struct kiocb *iocb, struct sock *sk, - struct msghdr *msg, size_t size) +static int jdccp_sendmsg(struct sock *sk, struct msghdr *msg, size_t size) { const struct inet_sock *inet = inet_sk(sk); struct ccid3_hc_tx_sock *hc = NULL; diff --git a/net/dccp/proto.c b/net/dccp/proto.c index e171b780b499..52a94016526d 100644 --- a/net/dccp/proto.c +++ b/net/dccp/proto.c @@ -741,8 +741,7 @@ static int dccp_msghdr_parse(struct msghdr *msg, struct sk_buff *skb) return 0; } -int dccp_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg, - size_t len) +int dccp_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) { const struct dccp_sock *dp = dccp_sk(sk); const int flags = msg->msg_flags; @@ -806,8 +805,8 @@ out_discard: EXPORT_SYMBOL_GPL(dccp_sendmsg); -int dccp_recvmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg, - size_t len, int nonblock, int flags, int *addr_len) +int dccp_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, int nonblock, + int flags, int *addr_len) { const struct dccp_hdr *dh; long timeo; diff --git a/net/dccp/timer.c b/net/dccp/timer.c index 1cd46a345cb0..3ef7acef3ce8 100644 --- a/net/dccp/timer.c +++ b/net/dccp/timer.c @@ -161,33 +161,11 @@ out: sock_put(sk); } -/* - * Timer for listening sockets - */ -static void dccp_response_timer(struct sock *sk) -{ - inet_csk_reqsk_queue_prune(sk, TCP_SYNQ_INTERVAL, DCCP_TIMEOUT_INIT, - DCCP_RTO_MAX); -} - static void dccp_keepalive_timer(unsigned long data) { struct sock *sk = (struct sock *)data; - /* Only process if socket is not in use. */ - bh_lock_sock(sk); - if (sock_owned_by_user(sk)) { - /* Try again later. */ - inet_csk_reset_keepalive_timer(sk, HZ / 20); - goto out; - } - - if (sk->sk_state == DCCP_LISTEN) { - dccp_response_timer(sk); - goto out; - } -out: - bh_unlock_sock(sk); + pr_err("dccp should not use a keepalive timer !\n"); sock_put(sk); } diff --git a/net/decnet/af_decnet.c b/net/decnet/af_decnet.c index 810228646de3..754484b3cd0e 100644 --- a/net/decnet/af_decnet.c +++ b/net/decnet/af_decnet.c @@ -1669,8 +1669,8 @@ static int dn_data_ready(struct sock *sk, struct sk_buff_head *q, int flags, int } -static int dn_recvmsg(struct kiocb *iocb, struct socket *sock, - struct msghdr *msg, size_t size, int flags) +static int dn_recvmsg(struct socket *sock, struct msghdr *msg, size_t size, + int flags) { struct sock *sk = sock->sk; struct dn_scp *scp = DN_SK(sk); @@ -1905,8 +1905,7 @@ static inline struct sk_buff *dn_alloc_send_pskb(struct sock *sk, return skb; } -static int dn_sendmsg(struct kiocb *iocb, struct socket *sock, - struct msghdr *msg, size_t size) +static int dn_sendmsg(struct socket *sock, struct msghdr *msg, size_t size) { struct sock *sk = sock->sk; struct dn_scp *scp = DN_SK(sk); diff --git a/net/decnet/dn_neigh.c b/net/decnet/dn_neigh.c index 7ca7c3143da3..4507b188fc51 100644 --- a/net/decnet/dn_neigh.c +++ b/net/decnet/dn_neigh.c @@ -49,41 +49,17 @@ #include <net/dn_route.h> static int dn_neigh_construct(struct neighbour *); -static void dn_long_error_report(struct neighbour *, struct sk_buff *); -static void dn_short_error_report(struct neighbour *, struct sk_buff *); -static int dn_long_output(struct neighbour *, struct sk_buff *); -static int dn_short_output(struct neighbour *, struct sk_buff *); -static int dn_phase3_output(struct neighbour *, struct sk_buff *); - - -/* - * For talking to broadcast devices: Ethernet & PPP - */ -static const struct neigh_ops dn_long_ops = { - .family = AF_DECnet, - .error_report = dn_long_error_report, - .output = dn_long_output, - .connected_output = dn_long_output, -}; +static void dn_neigh_error_report(struct neighbour *, struct sk_buff *); +static int dn_neigh_output(struct neighbour *neigh, struct sk_buff *skb); /* - * For talking to pointopoint and multidrop devices: DDCMP and X.25 + * Operations for adding the link layer header. */ -static const struct neigh_ops dn_short_ops = { +static const struct neigh_ops dn_neigh_ops = { .family = AF_DECnet, - .error_report = dn_short_error_report, - .output = dn_short_output, - .connected_output = dn_short_output, -}; - -/* - * For talking to DECnet phase III nodes - */ -static const struct neigh_ops dn_phase3_ops = { - .family = AF_DECnet, - .error_report = dn_short_error_report, /* Can use short version here */ - .output = dn_phase3_output, - .connected_output = dn_phase3_output, + .error_report = dn_neigh_error_report, + .output = dn_neigh_output, + .connected_output = dn_neigh_output, }; static u32 dn_neigh_hash(const void *pkey, @@ -93,11 +69,18 @@ static u32 dn_neigh_hash(const void *pkey, return jhash_2words(*(__u16 *)pkey, 0, hash_rnd[0]); } +static bool dn_key_eq(const struct neighbour *neigh, const void *pkey) +{ + return neigh_key_eq16(neigh, pkey); +} + struct neigh_table dn_neigh_table = { .family = PF_DECnet, .entry_size = NEIGH_ENTRY_SIZE(sizeof(struct dn_neigh)), .key_len = sizeof(__le16), + .protocol = cpu_to_be16(ETH_P_DNA_RT), .hash = dn_neigh_hash, + .key_eq = dn_key_eq, .constructor = dn_neigh_construct, .id = "dn_neigh_cache", .parms ={ @@ -146,16 +129,9 @@ static int dn_neigh_construct(struct neighbour *neigh) __neigh_parms_put(neigh->parms); neigh->parms = neigh_parms_clone(parms); - - if (dn_db->use_long) - neigh->ops = &dn_long_ops; - else - neigh->ops = &dn_short_ops; rcu_read_unlock(); - if (dn->flags & DN_NDFLAG_P3) - neigh->ops = &dn_phase3_ops; - + neigh->ops = &dn_neigh_ops; neigh->nud_state = NUD_NOARP; neigh->output = neigh->ops->connected_output; @@ -187,24 +163,16 @@ static int dn_neigh_construct(struct neighbour *neigh) return 0; } -static void dn_long_error_report(struct neighbour *neigh, struct sk_buff *skb) -{ - printk(KERN_DEBUG "dn_long_error_report: called\n"); - kfree_skb(skb); -} - - -static void dn_short_error_report(struct neighbour *neigh, struct sk_buff *skb) +static void dn_neigh_error_report(struct neighbour *neigh, struct sk_buff *skb) { - printk(KERN_DEBUG "dn_short_error_report: called\n"); + printk(KERN_DEBUG "dn_neigh_error_report: called\n"); kfree_skb(skb); } -static int dn_neigh_output_packet(struct sk_buff *skb) +static int dn_neigh_output(struct neighbour *neigh, struct sk_buff *skb) { struct dst_entry *dst = skb_dst(skb); struct dn_route *rt = (struct dn_route *)dst; - struct neighbour *neigh = rt->n; struct net_device *dev = neigh->dev; char mac_addr[ETH_ALEN]; unsigned int seq; @@ -226,7 +194,20 @@ static int dn_neigh_output_packet(struct sk_buff *skb) return err; } -static int dn_long_output(struct neighbour *neigh, struct sk_buff *skb) +static int dn_neigh_output_packet(struct sock *sk, struct sk_buff *skb) +{ + struct dst_entry *dst = skb_dst(skb); + struct dn_route *rt = (struct dn_route *)dst; + struct neighbour *neigh = rt->n; + + return neigh->output(neigh, skb); +} + +/* + * For talking to broadcast devices: Ethernet & PPP + */ +static int dn_long_output(struct neighbour *neigh, struct sock *sk, + struct sk_buff *skb) { struct net_device *dev = neigh->dev; int headroom = dev->hard_header_len + sizeof(struct dn_long_packet) + 3; @@ -265,11 +246,15 @@ static int dn_long_output(struct neighbour *neigh, struct sk_buff *skb) skb_reset_network_header(skb); - return NF_HOOK(NFPROTO_DECNET, NF_DN_POST_ROUTING, skb, NULL, - neigh->dev, dn_neigh_output_packet); + return NF_HOOK(NFPROTO_DECNET, NF_DN_POST_ROUTING, sk, skb, + NULL, neigh->dev, dn_neigh_output_packet); } -static int dn_short_output(struct neighbour *neigh, struct sk_buff *skb) +/* + * For talking to pointopoint and multidrop devices: DDCMP and X.25 + */ +static int dn_short_output(struct neighbour *neigh, struct sock *sk, + struct sk_buff *skb) { struct net_device *dev = neigh->dev; int headroom = dev->hard_header_len + sizeof(struct dn_short_packet) + 2; @@ -301,15 +286,17 @@ static int dn_short_output(struct neighbour *neigh, struct sk_buff *skb) skb_reset_network_header(skb); - return NF_HOOK(NFPROTO_DECNET, NF_DN_POST_ROUTING, skb, NULL, - neigh->dev, dn_neigh_output_packet); + return NF_HOOK(NFPROTO_DECNET, NF_DN_POST_ROUTING, sk, skb, + NULL, neigh->dev, dn_neigh_output_packet); } /* - * Phase 3 output is the same is short output, execpt that + * For talking to DECnet phase III nodes + * Phase 3 output is the same as short output, execpt that * it clears the area bits before transmission. */ -static int dn_phase3_output(struct neighbour *neigh, struct sk_buff *skb) +static int dn_phase3_output(struct neighbour *neigh, struct sock *sk, + struct sk_buff *skb) { struct net_device *dev = neigh->dev; int headroom = dev->hard_header_len + sizeof(struct dn_short_packet) + 2; @@ -340,8 +327,34 @@ static int dn_phase3_output(struct neighbour *neigh, struct sk_buff *skb) skb_reset_network_header(skb); - return NF_HOOK(NFPROTO_DECNET, NF_DN_POST_ROUTING, skb, NULL, - neigh->dev, dn_neigh_output_packet); + return NF_HOOK(NFPROTO_DECNET, NF_DN_POST_ROUTING, sk, skb, + NULL, neigh->dev, dn_neigh_output_packet); +} + +int dn_to_neigh_output(struct sock *sk, struct sk_buff *skb) +{ + struct dst_entry *dst = skb_dst(skb); + struct dn_route *rt = (struct dn_route *) dst; + struct neighbour *neigh = rt->n; + struct dn_neigh *dn = (struct dn_neigh *)neigh; + struct dn_dev *dn_db; + bool use_long; + + rcu_read_lock(); + dn_db = rcu_dereference(neigh->dev->dn_ptr); + if (dn_db == NULL) { + rcu_read_unlock(); + return -EINVAL; + } + use_long = dn_db->use_long; + rcu_read_unlock(); + + if (dn->flags & DN_NDFLAG_P3) + return dn_phase3_output(neigh, sk, skb); + if (use_long) + return dn_long_output(neigh, sk, skb); + else + return dn_short_output(neigh, sk, skb); } /* @@ -362,7 +375,7 @@ void dn_neigh_pointopoint_hello(struct sk_buff *skb) /* * Ethernet router hello message received */ -int dn_neigh_router_hello(struct sk_buff *skb) +int dn_neigh_router_hello(struct sock *sk, struct sk_buff *skb) { struct rtnode_hello_message *msg = (struct rtnode_hello_message *)skb->data; @@ -424,7 +437,7 @@ int dn_neigh_router_hello(struct sk_buff *skb) /* * Endnode hello message received */ -int dn_neigh_endnode_hello(struct sk_buff *skb) +int dn_neigh_endnode_hello(struct sock *sk, struct sk_buff *skb) { struct endnode_hello_message *msg = (struct endnode_hello_message *)skb->data; struct neighbour *neigh; diff --git a/net/decnet/dn_nsp_in.c b/net/decnet/dn_nsp_in.c index fe5f01485d33..a321eac9fd0c 100644 --- a/net/decnet/dn_nsp_in.c +++ b/net/decnet/dn_nsp_in.c @@ -714,7 +714,7 @@ out: return ret; } -static int dn_nsp_rx_packet(struct sk_buff *skb) +static int dn_nsp_rx_packet(struct sock *sk2, struct sk_buff *skb) { struct dn_skb_cb *cb = DN_SKB_CB(skb); struct sock *sk = NULL; @@ -814,7 +814,8 @@ free_out: int dn_nsp_rx(struct sk_buff *skb) { - return NF_HOOK(NFPROTO_DECNET, NF_DN_LOCAL_IN, skb, skb->dev, NULL, + return NF_HOOK(NFPROTO_DECNET, NF_DN_LOCAL_IN, NULL, skb, + skb->dev, NULL, dn_nsp_rx_packet); } diff --git a/net/decnet/dn_route.c b/net/decnet/dn_route.c index 3b81092771f8..03227ffd19ce 100644 --- a/net/decnet/dn_route.c +++ b/net/decnet/dn_route.c @@ -136,7 +136,6 @@ int decnet_dst_gc_interval = 2; static struct dst_ops dn_dst_ops = { .family = PF_DECnet, - .protocol = cpu_to_be16(ETH_P_DNA_RT), .gc_thresh = 128, .gc = dn_dst_gc, .check = dn_dst_check, @@ -513,7 +512,7 @@ static int dn_return_long(struct sk_buff *skb) * * Returns: result of input function if route is found, error code otherwise */ -static int dn_route_rx_packet(struct sk_buff *skb) +static int dn_route_rx_packet(struct sock *sk, struct sk_buff *skb) { struct dn_skb_cb *cb; int err; @@ -574,7 +573,8 @@ static int dn_route_rx_long(struct sk_buff *skb) ptr++; cb->hops = *ptr++; /* Visit Count */ - return NF_HOOK(NFPROTO_DECNET, NF_DN_PRE_ROUTING, skb, skb->dev, NULL, + return NF_HOOK(NFPROTO_DECNET, NF_DN_PRE_ROUTING, NULL, skb, + skb->dev, NULL, dn_route_rx_packet); drop_it: @@ -601,7 +601,8 @@ static int dn_route_rx_short(struct sk_buff *skb) ptr += 2; cb->hops = *ptr & 0x3f; - return NF_HOOK(NFPROTO_DECNET, NF_DN_PRE_ROUTING, skb, skb->dev, NULL, + return NF_HOOK(NFPROTO_DECNET, NF_DN_PRE_ROUTING, NULL, skb, + skb->dev, NULL, dn_route_rx_packet); drop_it: @@ -609,7 +610,7 @@ drop_it: return NET_RX_DROP; } -static int dn_route_discard(struct sk_buff *skb) +static int dn_route_discard(struct sock *sk, struct sk_buff *skb) { /* * I know we drop the packet here, but thats considered success in @@ -619,7 +620,7 @@ static int dn_route_discard(struct sk_buff *skb) return NET_RX_SUCCESS; } -static int dn_route_ptp_hello(struct sk_buff *skb) +static int dn_route_ptp_hello(struct sock *sk, struct sk_buff *skb) { dn_dev_hello(skb); dn_neigh_pointopoint_hello(skb); @@ -705,22 +706,22 @@ int dn_route_rcv(struct sk_buff *skb, struct net_device *dev, struct packet_type switch (flags & DN_RT_CNTL_MSK) { case DN_RT_PKT_HELO: return NF_HOOK(NFPROTO_DECNET, NF_DN_HELLO, - skb, skb->dev, NULL, + NULL, skb, skb->dev, NULL, dn_route_ptp_hello); case DN_RT_PKT_L1RT: case DN_RT_PKT_L2RT: return NF_HOOK(NFPROTO_DECNET, NF_DN_ROUTE, - skb, skb->dev, NULL, + NULL, skb, skb->dev, NULL, dn_route_discard); case DN_RT_PKT_ERTH: return NF_HOOK(NFPROTO_DECNET, NF_DN_HELLO, - skb, skb->dev, NULL, + NULL, skb, skb->dev, NULL, dn_neigh_router_hello); case DN_RT_PKT_EEDH: return NF_HOOK(NFPROTO_DECNET, NF_DN_HELLO, - skb, skb->dev, NULL, + NULL, skb, skb->dev, NULL, dn_neigh_endnode_hello); } } else { @@ -743,15 +744,6 @@ out: return NET_RX_DROP; } -static int dn_to_neigh_output(struct sk_buff *skb) -{ - struct dst_entry *dst = skb_dst(skb); - struct dn_route *rt = (struct dn_route *) dst; - struct neighbour *n = rt->n; - - return n->output(n, skb); -} - static int dn_output(struct sock *sk, struct sk_buff *skb) { struct dst_entry *dst = skb_dst(skb); @@ -778,7 +770,8 @@ static int dn_output(struct sock *sk, struct sk_buff *skb) cb->rt_flags |= DN_RT_F_IE; cb->hops = 0; - return NF_HOOK(NFPROTO_DECNET, NF_DN_LOCAL_OUT, skb, NULL, dev, + return NF_HOOK(NFPROTO_DECNET, NF_DN_LOCAL_OUT, sk, skb, + NULL, dev, dn_to_neigh_output); error: @@ -826,7 +819,8 @@ static int dn_forward(struct sk_buff *skb) if (rt->rt_flags & RTCF_DOREDIRECT) cb->rt_flags |= DN_RT_F_IE; - return NF_HOOK(NFPROTO_DECNET, NF_DN_FORWARD, skb, dev, skb->dev, + return NF_HOOK(NFPROTO_DECNET, NF_DN_FORWARD, NULL, skb, + dev, skb->dev, dn_to_neigh_output); drop: diff --git a/net/decnet/netfilter/dn_rtmsg.c b/net/decnet/netfilter/dn_rtmsg.c index e4d9560a910b..af34fc9bdf69 100644 --- a/net/decnet/netfilter/dn_rtmsg.c +++ b/net/decnet/netfilter/dn_rtmsg.c @@ -89,9 +89,7 @@ static void dnrmg_send_peer(struct sk_buff *skb) static unsigned int dnrmg_hook(const struct nf_hook_ops *ops, struct sk_buff *skb, - const struct net_device *in, - const struct net_device *out, - int (*okfn)(struct sk_buff *)) + const struct nf_hook_state *state) { dnrmg_send_peer(skb); return NF_ACCEPT; diff --git a/net/dsa/Kconfig b/net/dsa/Kconfig index 5f8ac404535b..ff7736f7ff42 100644 --- a/net/dsa/Kconfig +++ b/net/dsa/Kconfig @@ -5,9 +5,12 @@ config HAVE_NET_DSA # Drivers must select NET_DSA and the appropriate tagging format config NET_DSA - tristate - depends on HAVE_NET_DSA + tristate "Distributed Switch Architecture" + depends on HAVE_NET_DSA && NET_SWITCHDEV select PHYLIB + ---help--- + Say Y if you want to enable support for the hardware switches supported + by the Distributed Switch Architecture. if NET_DSA diff --git a/net/dsa/dsa.c b/net/dsa/dsa.c index 4dea2e0681d1..e6f6cc3a1bcf 100644 --- a/net/dsa/dsa.c +++ b/net/dsa/dsa.c @@ -20,6 +20,7 @@ #include <linux/of.h> #include <linux/of_mdio.h> #include <linux/of_platform.h> +#include <linux/of_net.h> #include <linux/sysfs.h> #include "dsa_priv.h" @@ -123,7 +124,7 @@ static ssize_t temp1_max_store(struct device *dev, return count; } -static DEVICE_ATTR(temp1_max, S_IRUGO, temp1_max_show, temp1_max_store); +static DEVICE_ATTR_RW(temp1_max); static ssize_t temp1_max_alarm_show(struct device *dev, struct device_attribute *attr, char *buf) @@ -158,8 +159,8 @@ static umode_t dsa_hwmon_attrs_visible(struct kobject *kobj, if (index == 1) { if (!drv->get_temp_limit) mode = 0; - else if (drv->set_temp_limit) - mode |= S_IWUSR; + else if (!drv->set_temp_limit) + mode &= ~S_IWUSR; } else if (index == 2 && !drv->get_temp_alarm) { mode = 0; } @@ -175,43 +176,14 @@ __ATTRIBUTE_GROUPS(dsa_hwmon); #endif /* CONFIG_NET_DSA_HWMON */ /* basic switch operations **************************************************/ -static struct dsa_switch * -dsa_switch_setup(struct dsa_switch_tree *dst, int index, - struct device *parent, struct device *host_dev) +static int dsa_switch_setup_one(struct dsa_switch *ds, struct device *parent) { - struct dsa_chip_data *pd = dst->pd->chip + index; - struct dsa_switch_driver *drv; - struct dsa_switch *ds; - int ret; - char *name; - int i; + struct dsa_switch_driver *drv = ds->drv; + struct dsa_switch_tree *dst = ds->dst; + struct dsa_chip_data *pd = ds->pd; bool valid_name_found = false; - - /* - * Probe for switch model. - */ - drv = dsa_switch_probe(host_dev, pd->sw_addr, &name); - if (drv == NULL) { - netdev_err(dst->master_netdev, "[%d]: could not detect attached switch\n", - index); - return ERR_PTR(-EINVAL); - } - netdev_info(dst->master_netdev, "[%d]: detected a %s switch\n", - index, name); - - - /* - * Allocate and initialise switch state. - */ - ds = kzalloc(sizeof(*ds) + drv->priv_size, GFP_KERNEL); - if (ds == NULL) - return ERR_PTR(-ENOMEM); - - ds->dst = dst; - ds->index = index; - ds->pd = dst->pd->chip + index; - ds->drv = drv; - ds->master_dev = host_dev; + int index = ds->index; + int i, ret; /* * Validate supplied switch configuration. @@ -256,7 +228,7 @@ dsa_switch_setup(struct dsa_switch_tree *dst, int index, * switch. */ if (dst->cpu_switch == index) { - switch (drv->tag_protocol) { + switch (ds->tag_protocol) { #ifdef CONFIG_NET_DSA_TAG_DSA case DSA_TAG_PROTO_DSA: dst->rcv = dsa_netdev_ops.rcv; @@ -284,7 +256,7 @@ dsa_switch_setup(struct dsa_switch_tree *dst, int index, goto out; } - dst->tag_protocol = drv->tag_protocol; + dst->tag_protocol = ds->tag_protocol; } /* @@ -314,19 +286,15 @@ dsa_switch_setup(struct dsa_switch_tree *dst, int index, * Create network devices for physical switch ports. */ for (i = 0; i < DSA_MAX_PORTS; i++) { - struct net_device *slave_dev; - if (!(ds->phys_port_mask & (1 << i))) continue; - slave_dev = dsa_slave_create(ds, parent, i, pd->port_names[i]); - if (slave_dev == NULL) { + ret = dsa_slave_create(ds, parent, i, pd->port_names[i]); + if (ret < 0) { netdev_err(dst->master_netdev, "[%d]: can't create dsa slave device for port %d(%s)\n", index, i, pd->port_names[i]); - continue; + ret = 0; } - - ds->ports[i] = slave_dev; } #ifdef CONFIG_NET_DSA_HWMON @@ -354,13 +322,57 @@ dsa_switch_setup(struct dsa_switch_tree *dst, int index, } #endif /* CONFIG_NET_DSA_HWMON */ - return ds; + return ret; out_free: mdiobus_free(ds->slave_mii_bus); out: kfree(ds); - return ERR_PTR(ret); + return ret; +} + +static struct dsa_switch * +dsa_switch_setup(struct dsa_switch_tree *dst, int index, + struct device *parent, struct device *host_dev) +{ + struct dsa_chip_data *pd = dst->pd->chip + index; + struct dsa_switch_driver *drv; + struct dsa_switch *ds; + int ret; + char *name; + + /* + * Probe for switch model. + */ + drv = dsa_switch_probe(host_dev, pd->sw_addr, &name); + if (drv == NULL) { + netdev_err(dst->master_netdev, "[%d]: could not detect attached switch\n", + index); + return ERR_PTR(-EINVAL); + } + netdev_info(dst->master_netdev, "[%d]: detected a %s switch\n", + index, name); + + + /* + * Allocate and initialise switch state. + */ + ds = kzalloc(sizeof(*ds) + drv->priv_size, GFP_KERNEL); + if (ds == NULL) + return NULL; + + ds->dst = dst; + ds->index = index; + ds->pd = pd; + ds->drv = drv; + ds->tag_protocol = drv->tag_protocol; + ds->master_dev = host_dev; + + ret = dsa_switch_setup_one(ds, parent); + if (ret) + return NULL; + + return ds; } static void dsa_switch_destroy(struct dsa_switch *ds) @@ -378,7 +390,7 @@ static int dsa_switch_suspend(struct dsa_switch *ds) /* Suspend slave network devices */ for (i = 0; i < DSA_MAX_PORTS; i++) { - if (!(ds->phys_port_mask & (1 << i))) + if (!dsa_is_port_initialized(ds, i)) continue; ret = dsa_slave_suspend(ds->ports[i]); @@ -404,7 +416,7 @@ static int dsa_switch_resume(struct dsa_switch *ds) /* Resume slave network devices */ for (i = 0; i < DSA_MAX_PORTS; i++) { - if (!(ds->phys_port_mask & (1 << i))) + if (!dsa_is_port_initialized(ds, i)) continue; ret = dsa_slave_resume(ds->ports[i]); @@ -558,12 +570,12 @@ static void dsa_of_free_platform_data(struct dsa_platform_data *pd) kfree(pd->chip); } -static int dsa_of_probe(struct platform_device *pdev) +static int dsa_of_probe(struct device *dev) { - struct device_node *np = pdev->dev.of_node; + struct device_node *np = dev->of_node; struct device_node *child, *mdio, *ethernet, *port, *link; struct mii_bus *mdio_bus; - struct platform_device *ethernet_dev; + struct net_device *ethernet_dev; struct dsa_platform_data *pd; struct dsa_chip_data *cd; const char *port_name; @@ -578,22 +590,22 @@ static int dsa_of_probe(struct platform_device *pdev) mdio_bus = of_mdio_find_bus(mdio); if (!mdio_bus) - return -EINVAL; + return -EPROBE_DEFER; ethernet = of_parse_phandle(np, "dsa,ethernet", 0); if (!ethernet) return -EINVAL; - ethernet_dev = of_find_device_by_node(ethernet); + ethernet_dev = of_find_net_device_by_node(ethernet); if (!ethernet_dev) - return -ENODEV; + return -EPROBE_DEFER; pd = kzalloc(sizeof(*pd), GFP_KERNEL); if (!pd) return -ENOMEM; - pdev->dev.platform_data = pd; - pd->netdev = ðernet_dev->dev; + dev->platform_data = pd; + pd->of_netdev = ethernet_dev; pd->nr_chips = of_get_available_child_count(np); if (pd->nr_chips > DSA_MAX_SWITCHES) pd->nr_chips = DSA_MAX_SWITCHES; @@ -621,7 +633,7 @@ static int dsa_of_probe(struct platform_device *pdev) if (cd->sw_addr > PHY_MAX_ADDR) continue; - if (!of_property_read_u32(np, "eeprom-length", &eeprom_len)) + if (!of_property_read_u32(child, "eeprom-length", &eeprom_len)) cd->eeprom_len = eeprom_len; for_each_available_child_of_node(child, port) { @@ -665,72 +677,35 @@ out_free_chip: dsa_of_free_platform_data(pd); out_free: kfree(pd); - pdev->dev.platform_data = NULL; + dev->platform_data = NULL; return ret; } -static void dsa_of_remove(struct platform_device *pdev) +static void dsa_of_remove(struct device *dev) { - struct dsa_platform_data *pd = pdev->dev.platform_data; + struct dsa_platform_data *pd = dev->platform_data; - if (!pdev->dev.of_node) + if (!dev->of_node) return; dsa_of_free_platform_data(pd); kfree(pd); } #else -static inline int dsa_of_probe(struct platform_device *pdev) +static inline int dsa_of_probe(struct device *dev) { return 0; } -static inline void dsa_of_remove(struct platform_device *pdev) +static inline void dsa_of_remove(struct device *dev) { } #endif -static int dsa_probe(struct platform_device *pdev) +static void dsa_setup_dst(struct dsa_switch_tree *dst, struct net_device *dev, + struct device *parent, struct dsa_platform_data *pd) { - struct dsa_platform_data *pd = pdev->dev.platform_data; - struct net_device *dev; - struct dsa_switch_tree *dst; - int i, ret; - - pr_notice_once("Distributed Switch Architecture driver version %s\n", - dsa_driver_version); - - if (pdev->dev.of_node) { - ret = dsa_of_probe(pdev); - if (ret) - return ret; - - pd = pdev->dev.platform_data; - } - - if (pd == NULL || pd->netdev == NULL) - return -EINVAL; - - dev = dev_to_net_device(pd->netdev); - if (dev == NULL) { - ret = -EINVAL; - goto out; - } - - if (dev->dsa_ptr != NULL) { - dev_put(dev); - ret = -EEXIST; - goto out; - } - - dst = kzalloc(sizeof(*dst), GFP_KERNEL); - if (dst == NULL) { - dev_put(dev); - ret = -ENOMEM; - goto out; - } - - platform_set_drvdata(pdev, dst); + int i; dst->pd = pd; dst->master_netdev = dev; @@ -740,7 +715,7 @@ static int dsa_probe(struct platform_device *pdev) for (i = 0; i < pd->nr_chips; i++) { struct dsa_switch *ds; - ds = dsa_switch_setup(dst, i, &pdev->dev, pd->chip[i].host_dev); + ds = dsa_switch_setup(dst, i, parent, pd->chip[i].host_dev); if (IS_ERR(ds)) { netdev_err(dev, "[%d]: couldn't create dsa switch instance (error %ld)\n", i, PTR_ERR(ds)); @@ -768,18 +743,67 @@ static int dsa_probe(struct platform_device *pdev) dst->link_poll_timer.expires = round_jiffies(jiffies + HZ); add_timer(&dst->link_poll_timer); } +} + +static int dsa_probe(struct platform_device *pdev) +{ + struct dsa_platform_data *pd = pdev->dev.platform_data; + struct net_device *dev; + struct dsa_switch_tree *dst; + int ret; + + pr_notice_once("Distributed Switch Architecture driver version %s\n", + dsa_driver_version); + + if (pdev->dev.of_node) { + ret = dsa_of_probe(&pdev->dev); + if (ret) + return ret; + + pd = pdev->dev.platform_data; + } + + if (pd == NULL || (pd->netdev == NULL && pd->of_netdev == NULL)) + return -EINVAL; + + if (pd->of_netdev) { + dev = pd->of_netdev; + dev_hold(dev); + } else { + dev = dev_to_net_device(pd->netdev); + } + if (dev == NULL) { + ret = -EPROBE_DEFER; + goto out; + } + + if (dev->dsa_ptr != NULL) { + dev_put(dev); + ret = -EEXIST; + goto out; + } + + dst = kzalloc(sizeof(*dst), GFP_KERNEL); + if (dst == NULL) { + dev_put(dev); + ret = -ENOMEM; + goto out; + } + + platform_set_drvdata(pdev, dst); + + dsa_setup_dst(dst, dev, &pdev->dev, pd); return 0; out: - dsa_of_remove(pdev); + dsa_of_remove(&pdev->dev); return ret; } -static int dsa_remove(struct platform_device *pdev) +static void dsa_remove_dst(struct dsa_switch_tree *dst) { - struct dsa_switch_tree *dst = platform_get_drvdata(pdev); int i; if (dst->link_poll_needed) @@ -793,8 +817,14 @@ static int dsa_remove(struct platform_device *pdev) if (ds != NULL) dsa_switch_destroy(ds); } +} + +static int dsa_remove(struct platform_device *pdev) +{ + struct dsa_switch_tree *dst = platform_get_drvdata(pdev); - dsa_of_remove(pdev); + dsa_remove_dst(dst); + dsa_of_remove(&pdev->dev); return 0; } @@ -821,6 +851,10 @@ static struct packet_type dsa_pack_type __read_mostly = { .func = dsa_switch_rcv, }; +static struct notifier_block dsa_netdevice_nb __read_mostly = { + .notifier_call = dsa_slave_netdevice_event, +}; + #ifdef CONFIG_PM_SLEEP static int dsa_suspend(struct device *d) { @@ -879,6 +913,8 @@ static int __init dsa_init_module(void) { int rc; + register_netdevice_notifier(&dsa_netdevice_nb); + rc = platform_driver_register(&dsa_driver); if (rc) return rc; @@ -891,6 +927,7 @@ module_init(dsa_init_module); static void __exit dsa_cleanup_module(void) { + unregister_netdevice_notifier(&dsa_netdevice_nb); dev_remove_pack(&dsa_pack_type); platform_driver_unregister(&dsa_driver); } diff --git a/net/dsa/dsa_priv.h b/net/dsa/dsa_priv.h index dc9756d3154c..d5f1f9b862ea 100644 --- a/net/dsa/dsa_priv.h +++ b/net/dsa/dsa_priv.h @@ -45,6 +45,8 @@ struct dsa_slave_priv { int old_link; int old_pause; int old_duplex; + + struct net_device *bridge_dev; }; /* dsa.c */ @@ -53,11 +55,12 @@ extern char dsa_driver_version[]; /* slave.c */ extern const struct dsa_device_ops notag_netdev_ops; void dsa_slave_mii_bus_init(struct dsa_switch *ds); -struct net_device *dsa_slave_create(struct dsa_switch *ds, - struct device *parent, - int port, char *name); +int dsa_slave_create(struct dsa_switch *ds, struct device *parent, + int port, char *name); int dsa_slave_suspend(struct net_device *slave_dev); int dsa_slave_resume(struct net_device *slave_dev); +int dsa_slave_netdevice_event(struct notifier_block *unused, + unsigned long event, void *ptr); /* tag_dsa.c */ extern const struct dsa_device_ops dsa_netdev_ops; diff --git a/net/dsa/slave.c b/net/dsa/slave.c index f23deadf42a0..827cda560a55 100644 --- a/net/dsa/slave.c +++ b/net/dsa/slave.c @@ -10,10 +10,14 @@ #include <linux/list.h> #include <linux/etherdevice.h> +#include <linux/netdevice.h> #include <linux/phy.h> #include <linux/phy_fixed.h> #include <linux/of_net.h> #include <linux/of_mdio.h> +#include <net/rtnetlink.h> +#include <net/switchdev.h> +#include <linux/if_bridge.h> #include "dsa_priv.h" /* slave mii_bus handling ***************************************************/ @@ -51,13 +55,16 @@ void dsa_slave_mii_bus_init(struct dsa_switch *ds) /* slave device handling ****************************************************/ -static int dsa_slave_init(struct net_device *dev) +static int dsa_slave_get_iflink(const struct net_device *dev) { struct dsa_slave_priv *p = netdev_priv(dev); - dev->iflink = p->parent->dst->master_netdev->ifindex; + return p->parent->dst->master_netdev->ifindex; +} - return 0; +static inline bool dsa_port_is_bridged(struct dsa_slave_priv *p) +{ + return !!p->bridge_dev; } static int dsa_slave_open(struct net_device *dev) @@ -65,6 +72,8 @@ static int dsa_slave_open(struct net_device *dev) struct dsa_slave_priv *p = netdev_priv(dev); struct net_device *master = p->parent->dst->master_netdev; struct dsa_switch *ds = p->parent; + u8 stp_state = dsa_port_is_bridged(p) ? + BR_STATE_BLOCKING : BR_STATE_FORWARDING; int err; if (!(master->flags & IFF_UP)) @@ -93,6 +102,9 @@ static int dsa_slave_open(struct net_device *dev) goto clear_promisc; } + if (ds->drv->port_stp_update) + ds->drv->port_stp_update(ds, p->port, stp_state); + if (p->phy) phy_start(p->phy); @@ -133,6 +145,9 @@ static int dsa_slave_close(struct net_device *dev) if (ds->drv->port_disable) ds->drv->port_disable(ds, p->port, p->phy); + if (ds->drv->port_stp_update) + ds->drv->port_stp_update(ds, p->port, BR_STATE_DISABLED); + return 0; } @@ -184,6 +199,105 @@ out: return 0; } +static int dsa_slave_fdb_add(struct ndmsg *ndm, struct nlattr *tb[], + struct net_device *dev, + const unsigned char *addr, u16 vid, u16 nlm_flags) +{ + struct dsa_slave_priv *p = netdev_priv(dev); + struct dsa_switch *ds = p->parent; + int ret = -EOPNOTSUPP; + + if (ds->drv->fdb_add) + ret = ds->drv->fdb_add(ds, p->port, addr, vid); + + return ret; +} + +static int dsa_slave_fdb_del(struct ndmsg *ndm, struct nlattr *tb[], + struct net_device *dev, + const unsigned char *addr, u16 vid) +{ + struct dsa_slave_priv *p = netdev_priv(dev); + struct dsa_switch *ds = p->parent; + int ret = -EOPNOTSUPP; + + if (ds->drv->fdb_del) + ret = ds->drv->fdb_del(ds, p->port, addr, vid); + + return ret; +} + +static int dsa_slave_fill_info(struct net_device *dev, struct sk_buff *skb, + const unsigned char *addr, u16 vid, + bool is_static, + u32 portid, u32 seq, int type, + unsigned int flags) +{ + struct nlmsghdr *nlh; + struct ndmsg *ndm; + + nlh = nlmsg_put(skb, portid, seq, type, sizeof(*ndm), flags); + if (!nlh) + return -EMSGSIZE; + + ndm = nlmsg_data(nlh); + ndm->ndm_family = AF_BRIDGE; + ndm->ndm_pad1 = 0; + ndm->ndm_pad2 = 0; + ndm->ndm_flags = NTF_EXT_LEARNED; + ndm->ndm_type = 0; + ndm->ndm_ifindex = dev->ifindex; + ndm->ndm_state = is_static ? NUD_NOARP : NUD_REACHABLE; + + if (nla_put(skb, NDA_LLADDR, ETH_ALEN, addr)) + goto nla_put_failure; + + if (vid && nla_put_u16(skb, NDA_VLAN, vid)) + goto nla_put_failure; + + nlmsg_end(skb, nlh); + return 0; + +nla_put_failure: + nlmsg_cancel(skb, nlh); + return -EMSGSIZE; +} + +/* Dump information about entries, in response to GETNEIGH */ +static int dsa_slave_fdb_dump(struct sk_buff *skb, struct netlink_callback *cb, + struct net_device *dev, + struct net_device *filter_dev, int idx) +{ + struct dsa_slave_priv *p = netdev_priv(dev); + struct dsa_switch *ds = p->parent; + unsigned char addr[ETH_ALEN] = { 0 }; + int ret; + + if (!ds->drv->fdb_getnext) + return -EOPNOTSUPP; + + for (; ; idx++) { + bool is_static; + + ret = ds->drv->fdb_getnext(ds, p->port, addr, &is_static); + if (ret < 0) + break; + + if (idx < cb->args[0]) + continue; + + ret = dsa_slave_fill_info(dev, skb, addr, 0, + is_static, + NETLINK_CB(cb->skb).portid, + cb->nlh->nlmsg_seq, + RTM_NEWNEIGH, NLM_F_MULTI); + if (ret < 0) + break; + } + + return idx; +} + static int dsa_slave_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd) { struct dsa_slave_priv *p = netdev_priv(dev); @@ -194,6 +308,92 @@ static int dsa_slave_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd) return -EOPNOTSUPP; } +/* Return a bitmask of all ports being currently bridged within a given bridge + * device. Note that on leave, the mask will still return the bitmask of ports + * currently bridged, prior to port removal, and this is exactly what we want. + */ +static u32 dsa_slave_br_port_mask(struct dsa_switch *ds, + struct net_device *bridge) +{ + struct dsa_slave_priv *p; + unsigned int port; + u32 mask = 0; + + for (port = 0; port < DSA_MAX_PORTS; port++) { + if (!dsa_is_port_initialized(ds, port)) + continue; + + p = netdev_priv(ds->ports[port]); + + if (ds->ports[port]->priv_flags & IFF_BRIDGE_PORT && + p->bridge_dev == bridge) + mask |= 1 << port; + } + + return mask; +} + +static int dsa_slave_stp_update(struct net_device *dev, u8 state) +{ + struct dsa_slave_priv *p = netdev_priv(dev); + struct dsa_switch *ds = p->parent; + int ret = -EOPNOTSUPP; + + if (ds->drv->port_stp_update) + ret = ds->drv->port_stp_update(ds, p->port, state); + + return ret; +} + +static int dsa_slave_bridge_port_join(struct net_device *dev, + struct net_device *br) +{ + struct dsa_slave_priv *p = netdev_priv(dev); + struct dsa_switch *ds = p->parent; + int ret = -EOPNOTSUPP; + + p->bridge_dev = br; + + if (ds->drv->port_join_bridge) + ret = ds->drv->port_join_bridge(ds, p->port, + dsa_slave_br_port_mask(ds, br)); + + return ret; +} + +static int dsa_slave_bridge_port_leave(struct net_device *dev) +{ + struct dsa_slave_priv *p = netdev_priv(dev); + struct dsa_switch *ds = p->parent; + int ret = -EOPNOTSUPP; + + + if (ds->drv->port_leave_bridge) + ret = ds->drv->port_leave_bridge(ds, p->port, + dsa_slave_br_port_mask(ds, p->bridge_dev)); + + p->bridge_dev = NULL; + + /* Port left the bridge, put in BR_STATE_DISABLED by the bridge layer, + * so allow it to be in BR_STATE_FORWARDING to be kept functional + */ + dsa_slave_stp_update(dev, BR_STATE_FORWARDING); + + return ret; +} + +static int dsa_slave_parent_id_get(struct net_device *dev, + struct netdev_phys_item_id *psid) +{ + struct dsa_slave_priv *p = netdev_priv(dev); + struct dsa_switch *ds = p->parent; + + psid->id_len = sizeof(ds->index); + memcpy(&psid->id, &ds->index, psid->id_len); + + return 0; +} + static netdev_tx_t dsa_slave_xmit(struct sk_buff *skb, struct net_device *dev) { struct dsa_slave_priv *p = netdev_priv(dev); @@ -462,14 +662,22 @@ static const struct ethtool_ops dsa_slave_ethtool_ops = { }; static const struct net_device_ops dsa_slave_netdev_ops = { - .ndo_init = dsa_slave_init, .ndo_open = dsa_slave_open, .ndo_stop = dsa_slave_close, .ndo_start_xmit = dsa_slave_xmit, .ndo_change_rx_flags = dsa_slave_change_rx_flags, .ndo_set_rx_mode = dsa_slave_set_rx_mode, .ndo_set_mac_address = dsa_slave_set_mac_address, + .ndo_fdb_add = dsa_slave_fdb_add, + .ndo_fdb_del = dsa_slave_fdb_del, + .ndo_fdb_dump = dsa_slave_fdb_dump, .ndo_do_ioctl = dsa_slave_ioctl, + .ndo_get_iflink = dsa_slave_get_iflink, +}; + +static const struct swdev_ops dsa_slave_swdev_ops = { + .swdev_parent_id_get = dsa_slave_parent_id_get, + .swdev_port_stp_update = dsa_slave_stp_update, }; static void dsa_slave_adjust_link(struct net_device *dev) @@ -513,6 +721,24 @@ static int dsa_slave_fixed_link_update(struct net_device *dev, } /* slave device setup *******************************************************/ +static int dsa_slave_phy_connect(struct dsa_slave_priv *p, + struct net_device *slave_dev, + int addr) +{ + struct dsa_switch *ds = p->parent; + + p->phy = ds->slave_mii_bus->phy_map[addr]; + if (!p->phy) + return -ENODEV; + + /* Use already configured phy mode */ + p->phy_interface = p->phy->interface; + phy_connect_direct(slave_dev, p->phy, dsa_slave_adjust_link, + p->phy_interface); + + return 0; +} + static int dsa_slave_phy_setup(struct dsa_slave_priv *p, struct net_device *slave_dev) { @@ -546,10 +772,25 @@ static int dsa_slave_phy_setup(struct dsa_slave_priv *p, if (ds->drv->get_phy_flags) phy_flags = ds->drv->get_phy_flags(ds, p->port); - if (phy_dn) - p->phy = of_phy_connect(slave_dev, phy_dn, - dsa_slave_adjust_link, phy_flags, - p->phy_interface); + if (phy_dn) { + ret = of_mdio_parse_addr(&slave_dev->dev, phy_dn); + /* If this PHY address is part of phys_mii_mask, which means + * that we need to divert reads and writes to/from it, then we + * want to bind this device using the slave MII bus created by + * DSA to make that happen. + */ + if (!phy_is_fixed && ret >= 0 && + (ds->phys_mii_mask & (1 << ret))) { + ret = dsa_slave_phy_connect(p, slave_dev, ret); + if (ret) + return ret; + } else { + p->phy = of_phy_connect(slave_dev, phy_dn, + dsa_slave_adjust_link, + phy_flags, + p->phy_interface); + } + } if (p->phy && phy_is_fixed) fixed_phy_set_link_update(p->phy, dsa_slave_fixed_link_update); @@ -558,14 +799,9 @@ static int dsa_slave_phy_setup(struct dsa_slave_priv *p, * MDIO bus instead */ if (!p->phy) { - p->phy = ds->slave_mii_bus->phy_map[p->port]; - if (!p->phy) - return -ENODEV; - - /* Use already configured phy mode */ - p->phy_interface = p->phy->interface; - phy_connect_direct(slave_dev, p->phy, dsa_slave_adjust_link, - p->phy_interface); + ret = dsa_slave_phy_connect(p, slave_dev, p->port); + if (ret) + return ret; } else { netdev_info(slave_dev, "attached PHY at address %d [%s]\n", p->phy->addr, p->phy->drv->name); @@ -605,9 +841,8 @@ int dsa_slave_resume(struct net_device *slave_dev) return 0; } -struct net_device * -dsa_slave_create(struct dsa_switch *ds, struct device *parent, - int port, char *name) +int dsa_slave_create(struct dsa_switch *ds, struct device *parent, + int port, char *name) { struct net_device *master = ds->dst->master_netdev; struct net_device *slave_dev; @@ -617,13 +852,14 @@ dsa_slave_create(struct dsa_switch *ds, struct device *parent, slave_dev = alloc_netdev(sizeof(struct dsa_slave_priv), name, NET_NAME_UNKNOWN, ether_setup); if (slave_dev == NULL) - return slave_dev; + return -ENOMEM; slave_dev->features = master->vlan_features; slave_dev->ethtool_ops = &dsa_slave_ethtool_ops; eth_hw_addr_inherit(slave_dev, master); slave_dev->tx_queue_len = 0; slave_dev->netdev_ops = &dsa_slave_netdev_ops; + slave_dev->swdev_ops = &dsa_slave_swdev_ops; SET_NETDEV_DEV(slave_dev, parent); slave_dev->dev.of_node = ds->pd->port_dn[port]; @@ -667,19 +903,64 @@ dsa_slave_create(struct dsa_switch *ds, struct device *parent, ret = dsa_slave_phy_setup(p, slave_dev); if (ret) { free_netdev(slave_dev); - return NULL; + return ret; } + ds->ports[port] = slave_dev; ret = register_netdev(slave_dev); if (ret) { netdev_err(master, "error %d registering interface %s\n", ret, slave_dev->name); phy_disconnect(p->phy); + ds->ports[port] = NULL; free_netdev(slave_dev); - return NULL; + return ret; } netif_carrier_off(slave_dev); - return slave_dev; + return 0; +} + +static bool dsa_slave_dev_check(struct net_device *dev) +{ + return dev->netdev_ops == &dsa_slave_netdev_ops; +} + +static int dsa_slave_master_changed(struct net_device *dev) +{ + struct net_device *master = netdev_master_upper_dev_get(dev); + struct dsa_slave_priv *p = netdev_priv(dev); + int err = 0; + + if (master && master->rtnl_link_ops && + !strcmp(master->rtnl_link_ops->kind, "bridge")) + err = dsa_slave_bridge_port_join(dev, master); + else if (dsa_port_is_bridged(p)) + err = dsa_slave_bridge_port_leave(dev); + + return err; +} + +int dsa_slave_netdevice_event(struct notifier_block *unused, + unsigned long event, void *ptr) +{ + struct net_device *dev; + int err = 0; + + switch (event) { + case NETDEV_CHANGEUPPER: + dev = netdev_notifier_info_to_dev(ptr); + if (!dsa_slave_dev_check(dev)) + goto out; + + err = dsa_slave_master_changed(dev); + if (err) + netdev_warn(dev, "failed to reflect master change\n"); + + break; + } + +out: + return NOTIFY_DONE; } diff --git a/net/ethernet/eth.c b/net/ethernet/eth.c index 238f38d21641..f3bad41d725f 100644 --- a/net/ethernet/eth.c +++ b/net/ethernet/eth.c @@ -104,7 +104,7 @@ int eth_header(struct sk_buff *skb, struct net_device *dev, */ if (dev->flags & (IFF_LOOPBACK | IFF_NOARP)) { - memset(eth->h_dest, 0, ETH_ALEN); + eth_zero_addr(eth->h_dest); return ETH_HLEN; } @@ -113,39 +113,6 @@ int eth_header(struct sk_buff *skb, struct net_device *dev, EXPORT_SYMBOL(eth_header); /** - * eth_rebuild_header- rebuild the Ethernet MAC header. - * @skb: socket buffer to update - * - * This is called after an ARP or IPV6 ndisc it's resolution on this - * sk_buff. We now let protocol (ARP) fill in the other fields. - * - * This routine CANNOT use cached dst->neigh! - * Really, it is used only when dst->neigh is wrong. - */ -int eth_rebuild_header(struct sk_buff *skb) -{ - struct ethhdr *eth = (struct ethhdr *)skb->data; - struct net_device *dev = skb->dev; - - switch (eth->h_proto) { -#ifdef CONFIG_INET - case htons(ETH_P_IP): - return arp_find(eth->h_dest, skb); -#endif - default: - netdev_dbg(dev, - "%s: unable to resolve type %X addresses.\n", - dev->name, ntohs(eth->h_proto)); - - memcpy(eth->h_source, dev->dev_addr, ETH_ALEN); - break; - } - - return 0; -} -EXPORT_SYMBOL(eth_rebuild_header); - -/** * eth_get_headlen - determine the the length of header for an ethernet frame * @data: pointer to start of frame * @len: total length of frame @@ -369,7 +336,6 @@ EXPORT_SYMBOL(eth_validate_addr); const struct header_ops eth_header_ops ____cacheline_aligned = { .create = eth_header, .parse = eth_header_parse, - .rebuild = eth_rebuild_header, .cache = eth_header_cache, .cache_update = eth_header_cache_update, }; @@ -391,7 +357,7 @@ void ether_setup(struct net_device *dev) dev->flags = IFF_BROADCAST|IFF_MULTICAST; dev->priv_flags |= IFF_TX_SKB_SHARING; - memset(dev->broadcast, 0xFF, ETH_ALEN); + eth_broadcast_addr(dev->broadcast); } EXPORT_SYMBOL(ether_setup); diff --git a/net/ieee802154/6lowpan/core.c b/net/ieee802154/6lowpan/core.c index 055fbb71ba6f..0ae5822ef944 100644 --- a/net/ieee802154/6lowpan/core.c +++ b/net/ieee802154/6lowpan/core.c @@ -113,7 +113,7 @@ static void lowpan_setup(struct net_device *dev) { dev->addr_len = IEEE802154_ADDR_LEN; memset(dev->broadcast, 0xff, IEEE802154_ADDR_LEN); - dev->type = ARPHRD_IEEE802154; + dev->type = ARPHRD_6LOWPAN; /* Frame Control + Sequence Number + Address fields + Security Header */ dev->hard_header_len = 2 + 1 + 20 + 14; dev->needed_tailroom = 2; /* FCS */ @@ -126,6 +126,7 @@ static void lowpan_setup(struct net_device *dev) dev->header_ops = &lowpan_header_ops; dev->ml_priv = &lowpan_mlme; dev->destructor = free_netdev; + dev->features |= NETIF_F_NETNS_LOCAL; } static int lowpan_validate(struct nlattr *tb[], struct nlattr *data[]) @@ -148,10 +149,11 @@ static int lowpan_newlink(struct net *src_net, struct net_device *dev, pr_debug("adding new link\n"); - if (!tb[IFLA_LINK]) + if (!tb[IFLA_LINK] || + !net_eq(dev_net(dev), &init_net)) return -EINVAL; /* find and hold real wpan device */ - real_dev = dev_get_by_index(src_net, nla_get_u32(tb[IFLA_LINK])); + real_dev = dev_get_by_index(dev_net(dev), nla_get_u32(tb[IFLA_LINK])); if (!real_dev) return -ENODEV; if (real_dev->type != ARPHRD_IEEE802154) { diff --git a/net/ieee802154/core.c b/net/ieee802154/core.c index 18bc7e738507..2ee00e8a0308 100644 --- a/net/ieee802154/core.c +++ b/net/ieee802154/core.c @@ -25,6 +25,9 @@ #include "sysfs.h" #include "core.h" +/* name for sysfs, %d is appended */ +#define PHY_NAME "phy" + /* RCU-protected (and RTNL for writers) */ LIST_HEAD(cfg802154_rdev_list); int cfg802154_rdev_list_generation; @@ -122,7 +125,7 @@ wpan_phy_new(const struct cfg802154_ops *ops, size_t priv_size) INIT_LIST_HEAD(&rdev->wpan_dev_list); device_initialize(&rdev->wpan_phy.dev); - dev_set_name(&rdev->wpan_phy.dev, "wpan-phy%d", rdev->wpan_phy_idx); + dev_set_name(&rdev->wpan_phy.dev, PHY_NAME "%d", rdev->wpan_phy_idx); rdev->wpan_phy.dev.class = &wpan_phy_class; rdev->wpan_phy.dev.platform_data = rdev; @@ -225,6 +228,7 @@ static int cfg802154_netdev_notifier_call(struct notifier_block *nb, switch (state) { /* TODO NETDEV_DEVTYPE */ case NETDEV_REGISTER: + dev->features |= NETIF_F_NETNS_LOCAL; wpan_dev->identifier = ++rdev->wpan_dev_id; list_add_rcu(&wpan_dev->list, &rdev->wpan_dev_list); rdev->devlist_generation++; diff --git a/net/ieee802154/nl-mac.c b/net/ieee802154/nl-mac.c index 9105265920fe..2b4955d7aae5 100644 --- a/net/ieee802154/nl-mac.c +++ b/net/ieee802154/nl-mac.c @@ -76,7 +76,6 @@ nla_put_failure: nlmsg_free(msg); return -ENOBUFS; } -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) diff --git a/net/ieee802154/socket.c b/net/ieee802154/socket.c index 2878d8ca6d3b..b60c65f70346 100644 --- a/net/ieee802154/socket.c +++ b/net/ieee802154/socket.c @@ -98,12 +98,12 @@ 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) +static int ieee802154_sock_sendmsg(struct socket *sock, struct msghdr *msg, + size_t len) { struct sock *sk = sock->sk; - return sk->sk_prot->sendmsg(iocb, sk, msg, len); + return sk->sk_prot->sendmsg(sk, msg, len); } static int ieee802154_sock_bind(struct socket *sock, struct sockaddr *uaddr, @@ -255,8 +255,7 @@ 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 sock *sk, struct msghdr *msg, size_t size) { struct net_device *dev; unsigned int mtu; @@ -327,8 +326,8 @@ out: return err; } -static int raw_recvmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg, - size_t len, int noblock, int flags, int *addr_len) +static int raw_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, + int noblock, int flags, int *addr_len) { size_t copied = 0; int err = -EOPNOTSUPP; @@ -615,8 +614,7 @@ static int dgram_disconnect(struct sock *sk, int flags) return 0; } -static int dgram_sendmsg(struct kiocb *iocb, struct sock *sk, - struct msghdr *msg, size_t size) +static int dgram_sendmsg(struct sock *sk, struct msghdr *msg, size_t size) { struct net_device *dev; unsigned int mtu; @@ -715,9 +713,8 @@ out: return err; } -static int dgram_recvmsg(struct kiocb *iocb, struct sock *sk, - struct msghdr *msg, size_t len, int noblock, - int flags, int *addr_len) +static int dgram_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, + int noblock, int flags, int *addr_len) { size_t copied = 0; int err = -EOPNOTSUPP; diff --git a/net/ieee802154/sysfs.c b/net/ieee802154/sysfs.c index dff55c2d87f3..133b4280660c 100644 --- a/net/ieee802154/sysfs.c +++ b/net/ieee802154/sysfs.c @@ -48,49 +48,6 @@ static ssize_t name_show(struct device *dev, } static DEVICE_ATTR_RO(name); -#define MASTER_SHOW_COMPLEX(name, format_string, args...) \ -static ssize_t name ## _show(struct device *dev, \ - struct device_attribute *attr, char *buf) \ -{ \ - struct wpan_phy *phy = container_of(dev, struct wpan_phy, dev); \ - int ret; \ - \ - mutex_lock(&phy->pib_lock); \ - ret = snprintf(buf, PAGE_SIZE, format_string "\n", args); \ - mutex_unlock(&phy->pib_lock); \ - return ret; \ -} \ -static DEVICE_ATTR_RO(name) - -#define MASTER_SHOW(field, format_string) \ - MASTER_SHOW_COMPLEX(field, format_string, phy->field) - -MASTER_SHOW(current_channel, "%d"); -MASTER_SHOW(current_page, "%d"); -MASTER_SHOW(transmit_power, "%d +- 1 dB"); -MASTER_SHOW_COMPLEX(cca_mode, "%d", phy->cca.mode); - -static ssize_t channels_supported_show(struct device *dev, - struct device_attribute *attr, - char *buf) -{ - struct wpan_phy *phy = container_of(dev, struct wpan_phy, dev); - int ret; - int i, len = 0; - - mutex_lock(&phy->pib_lock); - for (i = 0; i < 32; i++) { - ret = snprintf(buf + len, PAGE_SIZE - len, - "%#09x\n", phy->channels_supported[i]); - if (ret < 0) - break; - len += ret; - } - mutex_unlock(&phy->pib_lock); - return len; -} -static DEVICE_ATTR_RO(channels_supported); - static void wpan_phy_release(struct device *dev) { struct cfg802154_registered_device *rdev = dev_to_rdev(dev); @@ -101,12 +58,6 @@ static void wpan_phy_release(struct device *dev) static struct attribute *pmib_attrs[] = { &dev_attr_index.attr, &dev_attr_name.attr, - /* below will be removed soon */ - &dev_attr_current_channel.attr, - &dev_attr_current_page.attr, - &dev_attr_channels_supported.attr, - &dev_attr_transmit_power.attr, - &dev_attr_cca_mode.attr, NULL, }; ATTRIBUTE_GROUPS(pmib); diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c index d2e49baaff63..8b47a4d79d04 100644 --- a/net/ipv4/af_inet.c +++ b/net/ipv4/af_inet.c @@ -217,7 +217,7 @@ int inet_listen(struct socket *sock, int backlog) * shutdown() (rather than close()). */ if ((sysctl_tcp_fastopen & TFO_SERVER_ENABLE) != 0 && - inet_csk(sk)->icsk_accept_queue.fastopenq == NULL) { + !inet_csk(sk)->icsk_accept_queue.fastopenq) { if ((sysctl_tcp_fastopen & TFO_SERVER_WO_SOCKOPT1) != 0) err = fastopen_init_queue(sk, backlog); else if ((sysctl_tcp_fastopen & @@ -314,11 +314,11 @@ lookup_protocol: answer_flags = answer->flags; rcu_read_unlock(); - WARN_ON(answer_prot->slab == NULL); + WARN_ON(!answer_prot->slab); err = -ENOBUFS; sk = sk_alloc(net, PF_INET, GFP_KERNEL, answer_prot); - if (sk == NULL) + if (!sk) goto out; err = 0; @@ -716,8 +716,7 @@ int inet_getname(struct socket *sock, struct sockaddr *uaddr, } EXPORT_SYMBOL(inet_getname); -int inet_sendmsg(struct kiocb *iocb, struct socket *sock, struct msghdr *msg, - size_t size) +int inet_sendmsg(struct socket *sock, struct msghdr *msg, size_t size) { struct sock *sk = sock->sk; @@ -728,7 +727,7 @@ int inet_sendmsg(struct kiocb *iocb, struct socket *sock, struct msghdr *msg, inet_autobind(sk)) return -EAGAIN; - return sk->sk_prot->sendmsg(iocb, sk, msg, size); + return sk->sk_prot->sendmsg(sk, msg, size); } EXPORT_SYMBOL(inet_sendmsg); @@ -750,8 +749,8 @@ ssize_t inet_sendpage(struct socket *sock, struct page *page, int offset, } EXPORT_SYMBOL(inet_sendpage); -int inet_recvmsg(struct kiocb *iocb, struct socket *sock, struct msghdr *msg, - size_t size, int flags) +int inet_recvmsg(struct socket *sock, struct msghdr *msg, size_t size, + int flags) { struct sock *sk = sock->sk; int addr_len = 0; @@ -759,7 +758,7 @@ int inet_recvmsg(struct kiocb *iocb, struct socket *sock, struct msghdr *msg, sock_rps_record_flow(sk); - err = sk->sk_prot->recvmsg(iocb, sk, msg, size, flags & MSG_DONTWAIT, + err = sk->sk_prot->recvmsg(sk, msg, size, flags & MSG_DONTWAIT, flags & ~MSG_DONTWAIT, &addr_len); if (err >= 0) msg->msg_namelen = addr_len; @@ -1270,7 +1269,7 @@ static struct sk_buff *inet_gso_segment(struct sk_buff *skb, if (udpfrag) { iph->id = htons(id); iph->frag_off = htons(offset >> 3); - if (skb->next != NULL) + if (skb->next) iph->frag_off |= htons(IP_MF); offset += skb->len - nhoff - ihl; } else { @@ -1675,7 +1674,7 @@ static int __init inet_init(void) struct list_head *r; int rc = -EINVAL; - BUILD_BUG_ON(sizeof(struct inet_skb_parm) > FIELD_SIZEOF(struct sk_buff, cb)); + sock_skb_cb_check_size(sizeof(struct inet_skb_parm)); rc = proto_register(&tcp_prot, 1); if (rc) diff --git a/net/ipv4/arp.c b/net/ipv4/arp.c index 205e1472aa78..933a92820d26 100644 --- a/net/ipv4/arp.c +++ b/net/ipv4/arp.c @@ -122,6 +122,7 @@ * Interface to generic neighbour cache. */ static u32 arp_hash(const void *pkey, const struct net_device *dev, __u32 *hash_rnd); +static bool arp_key_eq(const struct neighbour *n, const void *pkey); static int arp_constructor(struct neighbour *neigh); static void arp_solicit(struct neighbour *neigh, struct sk_buff *skb); static void arp_error_report(struct neighbour *neigh, struct sk_buff *skb); @@ -149,18 +150,12 @@ static const struct neigh_ops arp_direct_ops = { .connected_output = neigh_direct_output, }; -static const struct neigh_ops arp_broken_ops = { - .family = AF_INET, - .solicit = arp_solicit, - .error_report = arp_error_report, - .output = neigh_compat_output, - .connected_output = neigh_compat_output, -}; - struct neigh_table arp_tbl = { .family = AF_INET, .key_len = 4, + .protocol = cpu_to_be16(ETH_P_IP), .hash = arp_hash, + .key_eq = arp_key_eq, .constructor = arp_constructor, .proxy_redo = parp_redo, .id = "arp_cache", @@ -216,7 +211,12 @@ static u32 arp_hash(const void *pkey, const struct net_device *dev, __u32 *hash_rnd) { - return arp_hashfn(*(u32 *)pkey, dev, *hash_rnd); + return arp_hashfn(pkey, dev, hash_rnd); +} + +static bool arp_key_eq(const struct neighbour *neigh, const void *pkey) +{ + return neigh_key_eq32(neigh, pkey); } static int arp_constructor(struct neighbour *neigh) @@ -228,7 +228,7 @@ static int arp_constructor(struct neighbour *neigh) rcu_read_lock(); in_dev = __in_dev_get_rcu(dev); - if (in_dev == NULL) { + if (!in_dev) { rcu_read_unlock(); return -EINVAL; } @@ -260,35 +260,6 @@ static int arp_constructor(struct neighbour *neigh) in old paradigm. */ -#if 1 - /* So... these "amateur" devices are hopeless. - The only thing, that I can say now: - It is very sad that we need to keep ugly obsolete - code to make them happy. - - They should be moved to more reasonable state, now - they use rebuild_header INSTEAD OF hard_start_xmit!!! - Besides that, they are sort of out of date - (a lot of redundant clones/copies, useless in 2.1), - I wonder why people believe that they work. - */ - switch (dev->type) { - default: - break; - case ARPHRD_ROSE: -#if IS_ENABLED(CONFIG_AX25) - case ARPHRD_AX25: -#if IS_ENABLED(CONFIG_NETROM) - case ARPHRD_NETROM: -#endif - neigh->ops = &arp_broken_ops; - neigh->output = neigh->ops->output; - return 0; -#else - break; -#endif - } -#endif if (neigh->type == RTN_MULTICAST) { neigh->nud_state = NUD_NOARP; arp_mc_map(addr, neigh->ha, dev, 1); @@ -433,71 +404,6 @@ static int arp_filter(__be32 sip, __be32 tip, struct net_device *dev) return flag; } -/* OBSOLETE FUNCTIONS */ - -/* - * Find an arp mapping in the cache. If not found, post a request. - * - * It is very UGLY routine: it DOES NOT use skb->dst->neighbour, - * even if it exists. It is supposed that skb->dev was mangled - * by a virtual device (eql, shaper). Nobody but broken devices - * is allowed to use this function, it is scheduled to be removed. --ANK - */ - -static int arp_set_predefined(int addr_hint, unsigned char *haddr, - __be32 paddr, struct net_device *dev) -{ - switch (addr_hint) { - case RTN_LOCAL: - pr_debug("arp called for own IP address\n"); - memcpy(haddr, dev->dev_addr, dev->addr_len); - return 1; - case RTN_MULTICAST: - arp_mc_map(paddr, haddr, dev, 1); - return 1; - case RTN_BROADCAST: - memcpy(haddr, dev->broadcast, dev->addr_len); - return 1; - } - return 0; -} - - -int arp_find(unsigned char *haddr, struct sk_buff *skb) -{ - struct net_device *dev = skb->dev; - __be32 paddr; - struct neighbour *n; - - if (!skb_dst(skb)) { - pr_debug("arp_find is called with dst==NULL\n"); - kfree_skb(skb); - return 1; - } - - paddr = rt_nexthop(skb_rtable(skb), ip_hdr(skb)->daddr); - if (arp_set_predefined(inet_addr_type(dev_net(dev), paddr), haddr, - paddr, dev)) - return 0; - - n = __neigh_lookup(&arp_tbl, &paddr, dev, 1); - - if (n) { - n->used = jiffies; - if (n->nud_state & NUD_VALID || neigh_event_send(n, skb) == 0) { - neigh_ha_snapshot(haddr, n, dev); - neigh_release(n); - return 0; - } - neigh_release(n); - } else - kfree_skb(skb); - return 1; -} -EXPORT_SYMBOL(arp_find); - -/* END OF OBSOLETE FUNCTIONS */ - /* * Check if we can use proxy ARP for this path */ @@ -569,7 +475,7 @@ static inline int arp_fwd_pvlan(struct in_device *in_dev, */ /* - * Create an arp packet. If (dest_hw == NULL), we create a broadcast + * Create an arp packet. If dest_hw is not set, we create a broadcast * message. */ struct sk_buff *arp_create(int type, int ptype, __be32 dest_ip, @@ -589,7 +495,7 @@ struct sk_buff *arp_create(int type, int ptype, __be32 dest_ip, */ skb = alloc_skb(arp_hdr_len(dev) + hlen + tlen, GFP_ATOMIC); - if (skb == NULL) + if (!skb) return NULL; skb_reserve(skb, hlen); @@ -597,9 +503,9 @@ struct sk_buff *arp_create(int type, int ptype, __be32 dest_ip, arp = (struct arphdr *) skb_put(skb, arp_hdr_len(dev)); skb->dev = dev; skb->protocol = htons(ETH_P_ARP); - if (src_hw == NULL) + if (!src_hw) src_hw = dev->dev_addr; - if (dest_hw == NULL) + if (!dest_hw) dest_hw = dev->broadcast; /* @@ -663,7 +569,7 @@ struct sk_buff *arp_create(int type, int ptype, __be32 dest_ip, break; #endif default: - if (target_hw != NULL) + if (target_hw) memcpy(arp_ptr, target_hw, dev->addr_len); else memset(arp_ptr, 0, dev->addr_len); @@ -685,7 +591,8 @@ EXPORT_SYMBOL(arp_create); void arp_xmit(struct sk_buff *skb) { /* Send it off, maybe filter it using firewalling first. */ - NF_HOOK(NFPROTO_ARP, NF_ARP_OUT, skb, NULL, skb->dev, dev_queue_xmit); + NF_HOOK(NFPROTO_ARP, NF_ARP_OUT, NULL, skb, + NULL, skb->dev, dev_queue_xmit_sk); } EXPORT_SYMBOL(arp_xmit); @@ -708,7 +615,7 @@ void arp_send(int type, int ptype, __be32 dest_ip, skb = arp_create(type, ptype, dest_ip, dev, src_ip, dest_hw, src_hw, target_hw); - if (skb == NULL) + if (!skb) return; arp_xmit(skb); @@ -719,7 +626,7 @@ EXPORT_SYMBOL(arp_send); * Process an arp request. */ -static int arp_process(struct sk_buff *skb) +static int arp_process(struct sock *sk, struct sk_buff *skb) { struct net_device *dev = skb->dev; struct in_device *in_dev = __in_dev_get_rcu(dev); @@ -738,7 +645,7 @@ static int arp_process(struct sk_buff *skb) * is ARP'able. */ - if (in_dev == NULL) + if (!in_dev) goto out; arp = arp_hdr(skb); @@ -902,7 +809,7 @@ static int arp_process(struct sk_buff *skb) is_garp = arp->ar_op == htons(ARPOP_REQUEST) && tip == sip && inet_addr_type(net, sip) == RTN_UNICAST; - if (n == NULL && + if (!n && ((arp->ar_op == htons(ARPOP_REPLY) && inet_addr_type(net, sip) == RTN_UNICAST) || is_garp)) n = __neigh_lookup(&arp_tbl, &sip, dev, 1); @@ -940,7 +847,7 @@ out: static void parp_redo(struct sk_buff *skb) { - arp_process(skb); + arp_process(NULL, skb); } @@ -973,7 +880,8 @@ static int arp_rcv(struct sk_buff *skb, struct net_device *dev, memset(NEIGH_CB(skb), 0, sizeof(struct neighbour_cb)); - return NF_HOOK(NFPROTO_ARP, NF_ARP_IN, skb, dev, NULL, arp_process); + return NF_HOOK(NFPROTO_ARP, NF_ARP_IN, NULL, skb, + dev, NULL, arp_process); consumeskb: consume_skb(skb); @@ -994,7 +902,7 @@ out_of_mem: static int arp_req_set_proxy(struct net *net, struct net_device *dev, int on) { - if (dev == NULL) { + if (!dev) { IPV4_DEVCONF_ALL(net, PROXY_ARP) = on; return 0; } @@ -1020,7 +928,7 @@ static int arp_req_set_public(struct net *net, struct arpreq *r, return -ENODEV; } if (mask) { - if (pneigh_lookup(&arp_tbl, net, &ip, dev, 1) == NULL) + if (!pneigh_lookup(&arp_tbl, net, &ip, dev, 1)) return -ENOBUFS; return 0; } @@ -1041,7 +949,7 @@ static int arp_req_set(struct net *net, struct arpreq *r, ip = ((struct sockaddr_in *)&r->arp_pa)->sin_addr.s_addr; if (r->arp_flags & ATF_PERM) r->arp_flags |= ATF_COM; - if (dev == NULL) { + if (!dev) { struct rtable *rt = ip_route_output(net, ip, 0, RTO_ONLINK, 0); if (IS_ERR(rt)) @@ -1161,7 +1069,7 @@ static int arp_req_delete(struct net *net, struct arpreq *r, return arp_req_delete_public(net, r, dev); ip = ((struct sockaddr_in *)&r->arp_pa)->sin_addr.s_addr; - if (dev == NULL) { + if (!dev) { struct rtable *rt = ip_route_output(net, ip, 0, RTO_ONLINK, 0); if (IS_ERR(rt)) return PTR_ERR(rt); @@ -1210,7 +1118,7 @@ int arp_ioctl(struct net *net, unsigned int cmd, void __user *arg) if (r.arp_dev[0]) { err = -ENODEV; dev = __dev_get_by_name(net, r.arp_dev); - if (dev == NULL) + if (!dev) goto out; /* Mmmm... It is wrong... ARPHRD_NETROM==0 */ diff --git a/net/ipv4/cipso_ipv4.c b/net/ipv4/cipso_ipv4.c index e361ea6f3fc8..bdb2a07ec363 100644 --- a/net/ipv4/cipso_ipv4.c +++ b/net/ipv4/cipso_ipv4.c @@ -255,7 +255,7 @@ static int __init cipso_v4_cache_init(void) cipso_v4_cache = kcalloc(CIPSO_V4_CACHE_BUCKETS, sizeof(struct cipso_v4_map_cache_bkt), GFP_KERNEL); - if (cipso_v4_cache == NULL) + if (!cipso_v4_cache) return -ENOMEM; for (iter = 0; iter < CIPSO_V4_CACHE_BUCKETS; iter++) { @@ -339,7 +339,7 @@ static int cipso_v4_cache_check(const unsigned char *key, secattr->cache = entry->lsm_data; secattr->flags |= NETLBL_SECATTR_CACHE; secattr->type = NETLBL_NLTYPE_CIPSOV4; - if (prev_entry == NULL) { + if (!prev_entry) { spin_unlock_bh(&cipso_v4_cache[bkt].lock); return 0; } @@ -393,10 +393,10 @@ int cipso_v4_cache_add(const unsigned char *cipso_ptr, cipso_ptr_len = cipso_ptr[1]; entry = kzalloc(sizeof(*entry), GFP_ATOMIC); - if (entry == NULL) + if (!entry) return -ENOMEM; entry->key = kmemdup(cipso_ptr, cipso_ptr_len, GFP_ATOMIC); - if (entry->key == NULL) { + if (!entry->key) { ret_val = -ENOMEM; goto cache_add_failure; } @@ -502,7 +502,7 @@ int cipso_v4_doi_add(struct cipso_v4_doi *doi_def, atomic_set(&doi_def->refcount, 1); spin_lock(&cipso_v4_doi_list_lock); - if (cipso_v4_doi_search(doi_def->doi) != NULL) { + if (cipso_v4_doi_search(doi_def->doi)) { spin_unlock(&cipso_v4_doi_list_lock); ret_val = -EEXIST; goto doi_add_return; @@ -513,7 +513,7 @@ int cipso_v4_doi_add(struct cipso_v4_doi *doi_def, doi_add_return: audit_buf = netlbl_audit_start(AUDIT_MAC_CIPSOV4_ADD, audit_info); - if (audit_buf != NULL) { + if (audit_buf) { const char *type_str; switch (doi_type) { case CIPSO_V4_MAP_TRANS: @@ -547,7 +547,7 @@ doi_add_return: */ void cipso_v4_doi_free(struct cipso_v4_doi *doi_def) { - if (doi_def == NULL) + if (!doi_def) return; switch (doi_def->type) { @@ -598,7 +598,7 @@ int cipso_v4_doi_remove(u32 doi, struct netlbl_audit *audit_info) spin_lock(&cipso_v4_doi_list_lock); doi_def = cipso_v4_doi_search(doi); - if (doi_def == NULL) { + if (!doi_def) { spin_unlock(&cipso_v4_doi_list_lock); ret_val = -ENOENT; goto doi_remove_return; @@ -617,7 +617,7 @@ int cipso_v4_doi_remove(u32 doi, struct netlbl_audit *audit_info) doi_remove_return: audit_buf = netlbl_audit_start(AUDIT_MAC_CIPSOV4_DEL, audit_info); - if (audit_buf != NULL) { + if (audit_buf) { audit_log_format(audit_buf, " cipso_doi=%u res=%u", doi, ret_val == 0 ? 1 : 0); @@ -644,7 +644,7 @@ struct cipso_v4_doi *cipso_v4_doi_getdef(u32 doi) rcu_read_lock(); doi_def = cipso_v4_doi_search(doi); - if (doi_def == NULL) + if (!doi_def) goto doi_getdef_return; if (!atomic_inc_not_zero(&doi_def->refcount)) doi_def = NULL; @@ -664,7 +664,7 @@ doi_getdef_return: */ void cipso_v4_doi_putdef(struct cipso_v4_doi *doi_def) { - if (doi_def == NULL) + if (!doi_def) return; if (!atomic_dec_and_test(&doi_def->refcount)) @@ -1642,7 +1642,7 @@ int cipso_v4_validate(const struct sk_buff *skb, unsigned char **option) rcu_read_lock(); doi_def = cipso_v4_doi_search(get_unaligned_be32(&opt[2])); - if (doi_def == NULL) { + if (!doi_def) { err_offset = 2; goto validate_return_locked; } @@ -1736,7 +1736,7 @@ int cipso_v4_validate(const struct sk_buff *skb, unsigned char **option) * not the loopback device drop the packet. Further, * there is no legitimate reason for setting this from * userspace so reject it if skb is NULL. */ - if (skb == NULL || !(skb->dev->flags & IFF_LOOPBACK)) { + if (!skb || !(skb->dev->flags & IFF_LOOPBACK)) { err_offset = opt_iter; goto validate_return_locked; } @@ -1897,7 +1897,7 @@ int cipso_v4_sock_setattr(struct sock *sk, * defined yet but it is not a problem as the only users of these * "lite" PF_INET sockets are functions which do an accept() call * afterwards so we will label the socket as part of the accept(). */ - if (sk == NULL) + if (!sk) return 0; /* We allocate the maximum CIPSO option size here so we are probably @@ -1905,7 +1905,7 @@ int cipso_v4_sock_setattr(struct sock *sk, * on and after all we are only talking about 40 bytes. */ buf_len = CIPSO_V4_OPT_LEN_MAX; buf = kmalloc(buf_len, GFP_ATOMIC); - if (buf == NULL) { + if (!buf) { ret_val = -ENOMEM; goto socket_setattr_failure; } @@ -1921,7 +1921,7 @@ int cipso_v4_sock_setattr(struct sock *sk, * set the IPOPT_CIPSO option. */ opt_len = (buf_len + 3) & ~3; opt = kzalloc(sizeof(*opt) + opt_len, GFP_ATOMIC); - if (opt == NULL) { + if (!opt) { ret_val = -ENOMEM; goto socket_setattr_failure; } @@ -1981,7 +1981,7 @@ int cipso_v4_req_setattr(struct request_sock *req, * on and after all we are only talking about 40 bytes. */ buf_len = CIPSO_V4_OPT_LEN_MAX; buf = kmalloc(buf_len, GFP_ATOMIC); - if (buf == NULL) { + if (!buf) { ret_val = -ENOMEM; goto req_setattr_failure; } @@ -1997,7 +1997,7 @@ int cipso_v4_req_setattr(struct request_sock *req, * set the IPOPT_CIPSO option. */ opt_len = (buf_len + 3) & ~3; opt = kzalloc(sizeof(*opt) + opt_len, GFP_ATOMIC); - if (opt == NULL) { + if (!opt) { ret_val = -ENOMEM; goto req_setattr_failure; } @@ -2102,7 +2102,7 @@ void cipso_v4_sock_delattr(struct sock *sk) sk_inet = inet_sk(sk); opt = rcu_dereference_protected(sk_inet->inet_opt, 1); - if (opt == NULL || opt->opt.cipso == 0) + if (!opt || opt->opt.cipso == 0) return; hdr_delta = cipso_v4_delopt(&sk_inet->inet_opt); @@ -2128,7 +2128,7 @@ void cipso_v4_req_delattr(struct request_sock *req) req_inet = inet_rsk(req); opt = req_inet->opt; - if (opt == NULL || opt->opt.cipso == 0) + if (!opt || opt->opt.cipso == 0) return; cipso_v4_delopt(&req_inet->opt); @@ -2157,7 +2157,7 @@ int cipso_v4_getattr(const unsigned char *cipso, doi = get_unaligned_be32(&cipso[2]); rcu_read_lock(); doi_def = cipso_v4_doi_search(doi); - if (doi_def == NULL) + if (!doi_def) goto getattr_return; /* XXX - This code assumes only one tag per CIPSO option which isn't * really a good assumption to make but since we only support the MAC diff --git a/net/ipv4/devinet.c b/net/ipv4/devinet.c index 3a8985c94581..419d23c53ec7 100644 --- a/net/ipv4/devinet.c +++ b/net/ipv4/devinet.c @@ -107,7 +107,7 @@ static const struct nla_policy ifa_ipv4_policy[IFA_MAX+1] = { static struct hlist_head inet_addr_lst[IN4_ADDR_HSIZE]; -static u32 inet_addr_hash(struct net *net, __be32 addr) +static u32 inet_addr_hash(const struct net *net, __be32 addr) { u32 val = (__force u32) addr ^ net_hash_mix(net); @@ -548,6 +548,26 @@ struct in_ifaddr *inet_ifa_byprefix(struct in_device *in_dev, __be32 prefix, return NULL; } +static int ip_mc_config(struct sock *sk, bool join, const struct in_ifaddr *ifa) +{ + struct ip_mreqn mreq = { + .imr_multiaddr.s_addr = ifa->ifa_address, + .imr_ifindex = ifa->ifa_dev->dev->ifindex, + }; + int ret; + + ASSERT_RTNL(); + + lock_sock(sk); + if (join) + ret = ip_mc_join_group(sk, &mreq); + else + ret = ip_mc_leave_group(sk, &mreq); + release_sock(sk); + + return ret; +} + static int inet_rtm_deladdr(struct sk_buff *skb, struct nlmsghdr *nlh) { struct net *net = sock_net(skb->sk); @@ -565,7 +585,7 @@ static int inet_rtm_deladdr(struct sk_buff *skb, struct nlmsghdr *nlh) ifm = nlmsg_data(nlh); in_dev = inetdev_by_index(net, ifm->ifa_index); - if (in_dev == NULL) { + if (!in_dev) { err = -ENODEV; goto errout; } @@ -573,7 +593,7 @@ static int inet_rtm_deladdr(struct sk_buff *skb, struct nlmsghdr *nlh) for (ifap = &in_dev->ifa_list; (ifa = *ifap) != NULL; ifap = &ifa->ifa_next) { if (tb[IFA_LOCAL] && - ifa->ifa_local != nla_get_be32(tb[IFA_LOCAL])) + ifa->ifa_local != nla_get_in_addr(tb[IFA_LOCAL])) continue; if (tb[IFA_LABEL] && nla_strcmp(tb[IFA_LABEL], ifa->ifa_label)) @@ -581,9 +601,11 @@ static int inet_rtm_deladdr(struct sk_buff *skb, struct nlmsghdr *nlh) if (tb[IFA_ADDRESS] && (ifm->ifa_prefixlen != ifa->ifa_prefixlen || - !inet_ifa_match(nla_get_be32(tb[IFA_ADDRESS]), ifa))) + !inet_ifa_match(nla_get_in_addr(tb[IFA_ADDRESS]), ifa))) continue; + if (ipv4_is_multicast(ifa->ifa_address)) + ip_mc_config(net->ipv4.mc_autojoin_sk, false, ifa); __inet_del_ifa(in_dev, ifap, 1, nlh, NETLINK_CB(skb).portid); return 0; } @@ -733,21 +755,21 @@ static struct in_ifaddr *rtm_to_ifaddr(struct net *net, struct nlmsghdr *nlh, ifm = nlmsg_data(nlh); err = -EINVAL; - if (ifm->ifa_prefixlen > 32 || tb[IFA_LOCAL] == NULL) + if (ifm->ifa_prefixlen > 32 || !tb[IFA_LOCAL]) goto errout; dev = __dev_get_by_index(net, ifm->ifa_index); err = -ENODEV; - if (dev == NULL) + if (!dev) goto errout; in_dev = __in_dev_get_rtnl(dev); err = -ENOBUFS; - if (in_dev == NULL) + if (!in_dev) goto errout; ifa = inet_alloc_ifa(); - if (ifa == NULL) + if (!ifa) /* * A potential indev allocation can be left alive, it stays * assigned to its device and is destroy with it. @@ -758,7 +780,7 @@ static struct in_ifaddr *rtm_to_ifaddr(struct net *net, struct nlmsghdr *nlh, neigh_parms_data_state_setall(in_dev->arp_parms); in_dev_hold(in_dev); - if (tb[IFA_ADDRESS] == NULL) + if (!tb[IFA_ADDRESS]) tb[IFA_ADDRESS] = tb[IFA_LOCAL]; INIT_HLIST_NODE(&ifa->hash); @@ -769,11 +791,11 @@ static struct in_ifaddr *rtm_to_ifaddr(struct net *net, struct nlmsghdr *nlh, ifa->ifa_scope = ifm->ifa_scope; ifa->ifa_dev = in_dev; - ifa->ifa_local = nla_get_be32(tb[IFA_LOCAL]); - ifa->ifa_address = nla_get_be32(tb[IFA_ADDRESS]); + ifa->ifa_local = nla_get_in_addr(tb[IFA_LOCAL]); + ifa->ifa_address = nla_get_in_addr(tb[IFA_ADDRESS]); if (tb[IFA_BROADCAST]) - ifa->ifa_broadcast = nla_get_be32(tb[IFA_BROADCAST]); + ifa->ifa_broadcast = nla_get_in_addr(tb[IFA_BROADCAST]); if (tb[IFA_LABEL]) nla_strlcpy(ifa->ifa_label, tb[IFA_LABEL], IFNAMSIZ); @@ -838,6 +860,15 @@ static int inet_rtm_newaddr(struct sk_buff *skb, struct nlmsghdr *nlh) * userspace already relies on not having to provide this. */ set_ifa_lifetime(ifa, valid_lft, prefered_lft); + if (ifa->ifa_flags & IFA_F_MCAUTOJOIN) { + int ret = ip_mc_config(net->ipv4.mc_autojoin_sk, + true, ifa); + + if (ret < 0) { + inet_free_ifa(ifa); + return ret; + } + } return __inet_insert_ifa(ifa, nlh, NETLINK_CB(skb).portid); } else { inet_free_ifa(ifa); @@ -1259,7 +1290,7 @@ __be32 inet_confirm_addr(struct net *net, struct in_device *in_dev, __be32 addr = 0; struct net_device *dev; - if (in_dev != NULL) + if (in_dev) return confirm_addr_indev(in_dev, dst, local, scope); rcu_read_lock(); @@ -1309,7 +1340,7 @@ static void inetdev_changename(struct net_device *dev, struct in_device *in_dev) if (named++ == 0) goto skip; dot = strchr(old, ':'); - if (dot == NULL) { + if (!dot) { sprintf(old, ":%d", named); dot = old; } @@ -1478,7 +1509,7 @@ static int inet_fill_ifaddr(struct sk_buff *skb, struct in_ifaddr *ifa, u32 preferred, valid; nlh = nlmsg_put(skb, portid, seq, event, sizeof(*ifm), flags); - if (nlh == NULL) + if (!nlh) return -EMSGSIZE; ifm = nlmsg_data(nlh); @@ -1510,11 +1541,11 @@ static int inet_fill_ifaddr(struct sk_buff *skb, struct in_ifaddr *ifa, valid = INFINITY_LIFE_TIME; } if ((ifa->ifa_address && - nla_put_be32(skb, IFA_ADDRESS, ifa->ifa_address)) || + nla_put_in_addr(skb, IFA_ADDRESS, ifa->ifa_address)) || (ifa->ifa_local && - nla_put_be32(skb, IFA_LOCAL, ifa->ifa_local)) || + nla_put_in_addr(skb, IFA_LOCAL, ifa->ifa_local)) || (ifa->ifa_broadcast && - nla_put_be32(skb, IFA_BROADCAST, ifa->ifa_broadcast)) || + nla_put_in_addr(skb, IFA_BROADCAST, ifa->ifa_broadcast)) || (ifa->ifa_label[0] && nla_put_string(skb, IFA_LABEL, ifa->ifa_label)) || nla_put_u32(skb, IFA_FLAGS, ifa->ifa_flags) || @@ -1597,7 +1628,7 @@ static void rtmsg_ifa(int event, struct in_ifaddr *ifa, struct nlmsghdr *nlh, net = dev_net(ifa->ifa_dev->dev); skb = nlmsg_new(inet_nlmsg_size(), GFP_KERNEL); - if (skb == NULL) + if (!skb) goto errout; err = inet_fill_ifaddr(skb, ifa, portid, seq, event, 0); @@ -1634,7 +1665,7 @@ static int inet_fill_link_af(struct sk_buff *skb, const struct net_device *dev) return -ENODATA; nla = nla_reserve(skb, IFLA_INET_CONF, IPV4_DEVCONF_MAX * 4); - if (nla == NULL) + if (!nla) return -EMSGSIZE; for (i = 0; i < IPV4_DEVCONF_MAX; i++) @@ -1723,7 +1754,7 @@ static int inet_netconf_fill_devconf(struct sk_buff *skb, int ifindex, nlh = nlmsg_put(skb, portid, seq, event, sizeof(struct netconfmsg), flags); - if (nlh == NULL) + if (!nlh) return -EMSGSIZE; ncm = nlmsg_data(nlh); @@ -1765,7 +1796,7 @@ void inet_netconf_notify_devconf(struct net *net, int type, int ifindex, int err = -ENOBUFS; skb = nlmsg_new(inet_netconf_msgsize_devconf(type), GFP_ATOMIC); - if (skb == NULL) + if (!skb) goto errout; err = inet_netconf_fill_devconf(skb, ifindex, devconf, 0, 0, @@ -1822,10 +1853,10 @@ static int inet_netconf_get_devconf(struct sk_buff *in_skb, break; default: dev = __dev_get_by_index(net, ifindex); - if (dev == NULL) + if (!dev) goto errout; in_dev = __in_dev_get_rtnl(dev); - if (in_dev == NULL) + if (!in_dev) goto errout; devconf = &in_dev->cnf; break; @@ -1833,7 +1864,7 @@ static int inet_netconf_get_devconf(struct sk_buff *in_skb, err = -ENOBUFS; skb = nlmsg_new(inet_netconf_msgsize_devconf(-1), GFP_ATOMIC); - if (skb == NULL) + if (!skb) goto errout; err = inet_netconf_fill_devconf(skb, ifindex, devconf, @@ -2184,7 +2215,7 @@ static void __devinet_sysctl_unregister(struct ipv4_devconf *cnf) { struct devinet_sysctl_table *t = cnf->sysctl; - if (t == NULL) + if (!t) return; cnf->sysctl = NULL; @@ -2245,16 +2276,16 @@ static __net_init int devinet_init_net(struct net *net) if (!net_eq(net, &init_net)) { all = kmemdup(all, sizeof(ipv4_devconf), GFP_KERNEL); - if (all == NULL) + if (!all) goto err_alloc_all; dflt = kmemdup(dflt, sizeof(ipv4_devconf_dflt), GFP_KERNEL); - if (dflt == NULL) + if (!dflt) goto err_alloc_dflt; #ifdef CONFIG_SYSCTL tbl = kmemdup(tbl, sizeof(ctl_forward_entry), GFP_KERNEL); - if (tbl == NULL) + if (!tbl) goto err_alloc_ctl; tbl[0].data = &all->data[IPV4_DEVCONF_FORWARDING - 1]; @@ -2274,7 +2305,7 @@ static __net_init int devinet_init_net(struct net *net) err = -ENOMEM; forw_hdr = register_net_sysctl(net, "net/ipv4", tbl); - if (forw_hdr == NULL) + if (!forw_hdr) goto err_reg_ctl; net->ipv4.forw_hdr = forw_hdr; #endif diff --git a/net/ipv4/esp4.c b/net/ipv4/esp4.c index 60173d4d3a0e..421a80b09b62 100644 --- a/net/ipv4/esp4.c +++ b/net/ipv4/esp4.c @@ -553,7 +553,7 @@ static int esp_init_authenc(struct xfrm_state *x) int err; err = -EINVAL; - if (x->ealg == NULL) + if (!x->ealg) goto error; err = -ENAMETOOLONG; diff --git a/net/ipv4/fib_frontend.c b/net/ipv4/fib_frontend.c index 23b9b3e86f4c..872494e6e6eb 100644 --- a/net/ipv4/fib_frontend.c +++ b/net/ipv4/fib_frontend.c @@ -52,12 +52,12 @@ static int __net_init fib4_rules_init(struct net *net) { struct fib_table *local_table, *main_table; - local_table = fib_trie_table(RT_TABLE_LOCAL); - if (local_table == NULL) + main_table = fib_trie_table(RT_TABLE_MAIN, NULL); + if (!main_table) return -ENOMEM; - main_table = fib_trie_table(RT_TABLE_MAIN); - if (main_table == NULL) + local_table = fib_trie_table(RT_TABLE_LOCAL, main_table); + if (!local_table) goto fail; hlist_add_head_rcu(&local_table->tb_hlist, @@ -67,14 +67,14 @@ static int __net_init fib4_rules_init(struct net *net) return 0; fail: - fib_free_table(local_table); + fib_free_table(main_table); return -ENOMEM; } #else struct fib_table *fib_new_table(struct net *net, u32 id) { - struct fib_table *tb; + struct fib_table *tb, *alias = NULL; unsigned int h; if (id == 0) @@ -83,23 +83,23 @@ struct fib_table *fib_new_table(struct net *net, u32 id) if (tb) return tb; - tb = fib_trie_table(id); + if (id == RT_TABLE_LOCAL) + alias = fib_new_table(net, RT_TABLE_MAIN); + + tb = fib_trie_table(id, alias); if (!tb) return NULL; switch (id) { case RT_TABLE_LOCAL: - net->ipv4.fib_local = tb; + rcu_assign_pointer(net->ipv4.fib_local, tb); break; - case RT_TABLE_MAIN: - net->ipv4.fib_main = tb; + rcu_assign_pointer(net->ipv4.fib_main, tb); break; - case RT_TABLE_DEFAULT: - net->ipv4.fib_default = tb; + rcu_assign_pointer(net->ipv4.fib_default, tb); break; - default: break; } @@ -129,16 +129,62 @@ struct fib_table *fib_get_table(struct net *net, u32 id) } #endif /* CONFIG_IP_MULTIPLE_TABLES */ +static void fib_replace_table(struct net *net, struct fib_table *old, + struct fib_table *new) +{ +#ifdef CONFIG_IP_MULTIPLE_TABLES + switch (new->tb_id) { + case RT_TABLE_LOCAL: + rcu_assign_pointer(net->ipv4.fib_local, new); + break; + case RT_TABLE_MAIN: + rcu_assign_pointer(net->ipv4.fib_main, new); + break; + case RT_TABLE_DEFAULT: + rcu_assign_pointer(net->ipv4.fib_default, new); + break; + default: + break; + } + +#endif + /* replace the old table in the hlist */ + hlist_replace_rcu(&old->tb_hlist, &new->tb_hlist); +} + +int fib_unmerge(struct net *net) +{ + struct fib_table *old, *new; + + /* attempt to fetch local table if it has been allocated */ + old = fib_get_table(net, RT_TABLE_LOCAL); + if (!old) + return 0; + + new = fib_trie_unmerge(old); + if (!new) + return -ENOMEM; + + /* replace merged table with clean table */ + if (new != old) { + fib_replace_table(net, old, new); + fib_free_table(old); + } + + return 0; +} + static void fib_flush(struct net *net) { int flushed = 0; - struct fib_table *tb; - struct hlist_head *head; unsigned int h; for (h = 0; h < FIB_TABLE_HASHSZ; h++) { - head = &net->ipv4.fib_table_hash[h]; - hlist_for_each_entry(tb, head, tb_hlist) + struct hlist_head *head = &net->ipv4.fib_table_hash[h]; + struct hlist_node *tmp; + struct fib_table *tb; + + hlist_for_each_entry_safe(tb, tmp, head, tb_hlist) flushed += fib_table_flush(tb); } @@ -146,6 +192,19 @@ static void fib_flush(struct net *net) rt_cache_flush(net); } +void fib_flush_external(struct net *net) +{ + struct fib_table *tb; + struct hlist_head *head; + unsigned int h; + + for (h = 0; h < FIB_TABLE_HASHSZ; h++) { + head = &net->ipv4.fib_table_hash[h]; + hlist_for_each_entry(tb, head, tb_hlist) + fib_table_flush_external(tb); + } +} + /* * Find address type as if only "dev" was present in the system. If * on_dev is NULL then all interfaces are taken into consideration. @@ -427,7 +486,7 @@ static int rtentry_to_fib_config(struct net *net, int cmd, struct rtentry *rt, for (ifa = in_dev->ifa_list; ifa; ifa = ifa->ifa_next) if (strcmp(ifa->ifa_label, devname) == 0) break; - if (ifa == NULL) + if (!ifa) return -ENODEV; cfg->fc_prefsrc = ifa->ifa_local; } @@ -455,7 +514,7 @@ static int rtentry_to_fib_config(struct net *net, int cmd, struct rtentry *rt, int len = 0; mx = kzalloc(3 * nla_total_size(4), GFP_KERNEL); - if (mx == NULL) + if (!mx) return -ENOMEM; if (rt->rt_flags & RTF_MTU) @@ -617,7 +676,7 @@ static int inet_rtm_delroute(struct sk_buff *skb, struct nlmsghdr *nlh) goto errout; tb = fib_get_table(net, cfg.fc_table); - if (tb == NULL) { + if (!tb) { err = -ESRCH; goto errout; } @@ -639,7 +698,7 @@ static int inet_rtm_newroute(struct sk_buff *skb, struct nlmsghdr *nlh) goto errout; tb = fib_new_table(net, cfg.fc_table); - if (tb == NULL) { + if (!tb) { err = -ENOBUFS; goto errout; } @@ -665,10 +724,12 @@ static int inet_dump_fib(struct sk_buff *skb, struct netlink_callback *cb) s_h = cb->args[0]; s_e = cb->args[1]; + rcu_read_lock(); + for (h = s_h; h < FIB_TABLE_HASHSZ; h++, s_e = 0) { e = 0; head = &net->ipv4.fib_table_hash[h]; - hlist_for_each_entry(tb, head, tb_hlist) { + hlist_for_each_entry_rcu(tb, head, tb_hlist) { if (e < s_e) goto next; if (dumped) @@ -682,6 +743,8 @@ next: } } out: + rcu_read_unlock(); + cb->args[1] = e; cb->args[0] = h; @@ -716,7 +779,7 @@ static void fib_magic(int cmd, int type, __be32 dst, int dst_len, struct in_ifad else tb = fib_new_table(net, RT_TABLE_LOCAL); - if (tb == NULL) + if (!tb) return; cfg.fc_table = tb->tb_id; @@ -743,7 +806,7 @@ void fib_add_ifaddr(struct in_ifaddr *ifa) if (ifa->ifa_flags & IFA_F_SECONDARY) { prim = inet_ifa_byprefix(in_dev, prefix, mask); - if (prim == NULL) { + if (!prim) { pr_warn("%s: bug: prim == NULL\n", __func__); return; } @@ -797,7 +860,7 @@ void fib_del_ifaddr(struct in_ifaddr *ifa, struct in_ifaddr *iprim) if (ifa->ifa_flags & IFA_F_SECONDARY) { prim = inet_ifa_byprefix(in_dev, any, ifa->ifa_mask); - if (prim == NULL) { + if (!prim) { pr_warn("%s: bug: prim == NULL\n", __func__); return; } @@ -967,7 +1030,7 @@ static void nl_fib_input(struct sk_buff *skb) return; skb = netlink_skb_clone(skb, GFP_KERNEL); - if (skb == NULL) + if (!skb) return; nlh = nlmsg_hdr(skb); @@ -988,7 +1051,7 @@ static int __net_init nl_fib_lookup_init(struct net *net) }; sk = netlink_kernel_create(net, NETLINK_FIB_LOOKUP, &cfg); - if (sk == NULL) + if (!sk) return -EAFNOSUPPORT; net->ipv4.fibnl = sk; return 0; @@ -1026,7 +1089,7 @@ static int fib_inetaddr_event(struct notifier_block *this, unsigned long event, case NETDEV_DOWN: fib_del_ifaddr(ifa, NULL); atomic_inc(&net->ipv4.dev_addr_genid); - if (ifa->ifa_dev->ifa_list == NULL) { + if (!ifa->ifa_dev->ifa_list) { /* Last address was deleted from this interface. * Disable IP. */ @@ -1094,7 +1157,7 @@ static int __net_init ip_fib_net_init(struct net *net) size = max_t(size_t, size, L1_CACHE_BYTES); net->ipv4.fib_table_hash = kzalloc(size, GFP_KERNEL); - if (net->ipv4.fib_table_hash == NULL) + if (!net->ipv4.fib_table_hash) return -ENOMEM; err = fib4_rules_init(net); @@ -1113,20 +1176,25 @@ static void ip_fib_net_exit(struct net *net) rtnl_lock(); #ifdef CONFIG_IP_MULTIPLE_TABLES - fib4_rules_exit(net); + RCU_INIT_POINTER(net->ipv4.fib_local, NULL); + RCU_INIT_POINTER(net->ipv4.fib_main, NULL); + RCU_INIT_POINTER(net->ipv4.fib_default, NULL); #endif for (i = 0; i < FIB_TABLE_HASHSZ; i++) { - struct fib_table *tb; - struct hlist_head *head; + struct hlist_head *head = &net->ipv4.fib_table_hash[i]; struct hlist_node *tmp; + struct fib_table *tb; - head = &net->ipv4.fib_table_hash[i]; hlist_for_each_entry_safe(tb, tmp, head, tb_hlist) { hlist_del(&tb->tb_hlist); fib_table_flush(tb); fib_free_table(tb); } } + +#ifdef CONFIG_IP_MULTIPLE_TABLES + fib4_rules_exit(net); +#endif rtnl_unlock(); kfree(net->ipv4.fib_table_hash); } diff --git a/net/ipv4/fib_lookup.h b/net/ipv4/fib_lookup.h index 825981b1049a..c6211ed60b03 100644 --- a/net/ipv4/fib_lookup.h +++ b/net/ipv4/fib_lookup.h @@ -6,11 +6,13 @@ #include <net/ip_fib.h> struct fib_alias { - struct list_head fa_list; + struct hlist_node fa_list; struct fib_info *fa_info; u8 fa_tos; u8 fa_type; u8 fa_state; + u8 fa_slen; + u32 tb_id; struct rcu_head rcu; }; diff --git a/net/ipv4/fib_rules.c b/net/ipv4/fib_rules.c index d3db718be51d..56151982f74e 100644 --- a/net/ipv4/fib_rules.c +++ b/net/ipv4/fib_rules.c @@ -153,7 +153,7 @@ static struct fib_table *fib_empty_table(struct net *net) u32 id; for (id = 1; id <= RT_TABLE_MAX; id++) - if (fib_get_table(net, id) == NULL) + if (!fib_get_table(net, id)) return fib_new_table(net, id); return NULL; } @@ -174,12 +174,17 @@ static int fib4_rule_configure(struct fib_rule *rule, struct sk_buff *skb, if (frh->tos & ~IPTOS_TOS_MASK) goto errout; + /* split local/main if they are not already split */ + err = fib_unmerge(net); + if (err) + goto errout; + if (rule->table == RT_TABLE_UNSPEC) { if (rule->action == FR_ACT_TO_TBL) { struct fib_table *table; table = fib_empty_table(net); - if (table == NULL) { + if (!table) { err = -ENOBUFS; goto errout; } @@ -189,10 +194,10 @@ static int fib4_rule_configure(struct fib_rule *rule, struct sk_buff *skb, } if (frh->src_len) - rule4->src = nla_get_be32(tb[FRA_SRC]); + rule4->src = nla_get_in_addr(tb[FRA_SRC]); if (frh->dst_len) - rule4->dst = nla_get_be32(tb[FRA_DST]); + rule4->dst = nla_get_in_addr(tb[FRA_DST]); #ifdef CONFIG_IP_ROUTE_CLASSID if (tb[FRA_FLOW]) { @@ -209,21 +214,31 @@ static int fib4_rule_configure(struct fib_rule *rule, struct sk_buff *skb, rule4->tos = frh->tos; net->ipv4.fib_has_custom_rules = true; + fib_flush_external(rule->fr_net); + err = 0; errout: return err; } -static void fib4_rule_delete(struct fib_rule *rule) +static int fib4_rule_delete(struct fib_rule *rule) { struct net *net = rule->fr_net; -#ifdef CONFIG_IP_ROUTE_CLASSID - struct fib4_rule *rule4 = (struct fib4_rule *) rule; + int err; - if (rule4->tclassid) + /* split local/main if they are not already split */ + err = fib_unmerge(net); + if (err) + goto errout; + +#ifdef CONFIG_IP_ROUTE_CLASSID + if (((struct fib4_rule *)rule)->tclassid) net->ipv4.fib_num_tclassid_users--; #endif net->ipv4.fib_has_custom_rules = true; + fib_flush_external(rule->fr_net); +errout: + return err; } static int fib4_rule_compare(struct fib_rule *rule, struct fib_rule_hdr *frh, @@ -245,10 +260,10 @@ static int fib4_rule_compare(struct fib_rule *rule, struct fib_rule_hdr *frh, return 0; #endif - if (frh->src_len && (rule4->src != nla_get_be32(tb[FRA_SRC]))) + if (frh->src_len && (rule4->src != nla_get_in_addr(tb[FRA_SRC]))) return 0; - if (frh->dst_len && (rule4->dst != nla_get_be32(tb[FRA_DST]))) + if (frh->dst_len && (rule4->dst != nla_get_in_addr(tb[FRA_DST]))) return 0; return 1; @@ -264,9 +279,9 @@ static int fib4_rule_fill(struct fib_rule *rule, struct sk_buff *skb, frh->tos = rule4->tos; if ((rule4->dst_len && - nla_put_be32(skb, FRA_DST, rule4->dst)) || + nla_put_in_addr(skb, FRA_DST, rule4->dst)) || (rule4->src_len && - nla_put_be32(skb, FRA_SRC, rule4->src))) + nla_put_in_addr(skb, FRA_SRC, rule4->src))) goto nla_put_failure; #ifdef CONFIG_IP_ROUTE_CLASSID if (rule4->tclassid && diff --git a/net/ipv4/fib_semantics.c b/net/ipv4/fib_semantics.c index 1e2090ea663e..8d695b6659c7 100644 --- a/net/ipv4/fib_semantics.c +++ b/net/ipv4/fib_semantics.c @@ -213,7 +213,6 @@ static void free_fib_info_rcu(struct rcu_head *head) rt_fibinfo_free(&nexthop_nh->nh_rth_input); } endfor_nexthops(fi); - release_net(fi->fib_net); if (fi->fib_metrics != (u32 *) dst_default_metrics) kfree(fi->fib_metrics); kfree(fi); @@ -391,7 +390,7 @@ void rtmsg_fib(int event, __be32 key, struct fib_alias *fa, int err = -ENOBUFS; skb = nlmsg_new(fib_nlmsg_size(fa->fa_info), GFP_KERNEL); - if (skb == NULL) + if (!skb) goto errout; err = fib_dump_info(skb, info->portid, seq, event, tb_id, @@ -469,7 +468,7 @@ static int fib_get_nhs(struct fib_info *fi, struct rtnexthop *rtnh, struct nlattr *nla, *attrs = rtnh_attrs(rtnh); nla = nla_find(attrs, attrlen, RTA_GATEWAY); - nexthop_nh->nh_gw = nla ? nla_get_be32(nla) : 0; + nexthop_nh->nh_gw = nla ? nla_get_in_addr(nla) : 0; #ifdef CONFIG_IP_ROUTE_CLASSID nla = nla_find(attrs, attrlen, RTA_FLOW); nexthop_nh->nh_tclassid = nla ? nla_get_u32(nla) : 0; @@ -504,7 +503,7 @@ int fib_nh_match(struct fib_config *cfg, struct fib_info *fi) } #ifdef CONFIG_IP_ROUTE_MULTIPATH - if (cfg->fc_mp == NULL) + if (!cfg->fc_mp) return 0; rtnh = cfg->fc_mp; @@ -524,7 +523,7 @@ int fib_nh_match(struct fib_config *cfg, struct fib_info *fi) struct nlattr *nla, *attrs = rtnh_attrs(rtnh); nla = nla_find(attrs, attrlen, RTA_GATEWAY); - if (nla && nla_get_be32(nla) != nh->nh_gw) + if (nla && nla_get_in_addr(nla) != nh->nh_gw) return 1; #ifdef CONFIG_IP_ROUTE_CLASSID nla = nla_find(attrs, attrlen, RTA_FLOW); @@ -647,7 +646,7 @@ static int fib_check_nh(struct fib_config *cfg, struct fib_info *fi, rcu_read_lock(); err = -ENODEV; in_dev = inetdev_by_index(net, nh->nh_oif); - if (in_dev == NULL) + if (!in_dev) goto out; err = -ENETDOWN; if (!(in_dev->dev->flags & IFF_UP)) @@ -804,7 +803,7 @@ struct fib_info *fib_create_info(struct fib_config *cfg) } fi = kzalloc(sizeof(*fi)+nhs*sizeof(struct fib_nh), GFP_KERNEL); - if (fi == NULL) + if (!fi) goto failure; fib_info_cnt++; if (cfg->fc_mx) { @@ -814,7 +813,7 @@ struct fib_info *fib_create_info(struct fib_config *cfg) } else fi->fib_metrics = (u32 *) dst_default_metrics; - fi->fib_net = hold_net(net); + fi->fib_net = net; fi->fib_protocol = cfg->fc_protocol; fi->fib_scope = cfg->fc_scope; fi->fib_flags = cfg->fc_flags; @@ -922,7 +921,7 @@ struct fib_info *fib_create_info(struct fib_config *cfg) nh->nh_scope = RT_SCOPE_NOWHERE; nh->nh_dev = dev_get_by_index(net, fi->fib_nh->nh_oif); err = -ENODEV; - if (nh->nh_dev == NULL) + if (!nh->nh_dev) goto failure; } else { change_nexthops(fi) { @@ -996,7 +995,7 @@ int fib_dump_info(struct sk_buff *skb, u32 portid, u32 seq, int event, struct rtmsg *rtm; nlh = nlmsg_put(skb, portid, seq, event, sizeof(*rtm), flags); - if (nlh == NULL) + if (!nlh) return -EMSGSIZE; rtm = nlmsg_data(nlh); @@ -1016,7 +1015,7 @@ int fib_dump_info(struct sk_buff *skb, u32 portid, u32 seq, int event, rtm->rtm_protocol = fi->fib_protocol; if (rtm->rtm_dst_len && - nla_put_be32(skb, RTA_DST, dst)) + nla_put_in_addr(skb, RTA_DST, dst)) goto nla_put_failure; if (fi->fib_priority && nla_put_u32(skb, RTA_PRIORITY, fi->fib_priority)) @@ -1025,11 +1024,11 @@ int fib_dump_info(struct sk_buff *skb, u32 portid, u32 seq, int event, goto nla_put_failure; if (fi->fib_prefsrc && - nla_put_be32(skb, RTA_PREFSRC, fi->fib_prefsrc)) + nla_put_in_addr(skb, RTA_PREFSRC, fi->fib_prefsrc)) goto nla_put_failure; if (fi->fib_nhs == 1) { if (fi->fib_nh->nh_gw && - nla_put_be32(skb, RTA_GATEWAY, fi->fib_nh->nh_gw)) + nla_put_in_addr(skb, RTA_GATEWAY, fi->fib_nh->nh_gw)) goto nla_put_failure; if (fi->fib_nh->nh_oif && nla_put_u32(skb, RTA_OIF, fi->fib_nh->nh_oif)) @@ -1046,12 +1045,12 @@ int fib_dump_info(struct sk_buff *skb, u32 portid, u32 seq, int event, struct nlattr *mp; mp = nla_nest_start(skb, RTA_MULTIPATH); - if (mp == NULL) + if (!mp) goto nla_put_failure; for_nexthops(fi) { rtnh = nla_reserve_nohdr(skb, sizeof(*rtnh)); - if (rtnh == NULL) + if (!rtnh) goto nla_put_failure; rtnh->rtnh_flags = nh->nh_flags & 0xFF; @@ -1059,7 +1058,7 @@ int fib_dump_info(struct sk_buff *skb, u32 portid, u32 seq, int event, rtnh->rtnh_ifindex = nh->nh_oif; if (nh->nh_gw && - nla_put_be32(skb, RTA_GATEWAY, nh->nh_gw)) + nla_put_in_addr(skb, RTA_GATEWAY, nh->nh_gw)) goto nla_put_failure; #ifdef CONFIG_IP_ROUTE_CLASSID if (nh->nh_tclassid && @@ -1094,7 +1093,7 @@ int fib_sync_down_addr(struct net *net, __be32 local) struct hlist_head *head = &fib_info_laddrhash[hash]; struct fib_info *fi; - if (fib_info_laddrhash == NULL || local == 0) + if (!fib_info_laddrhash || local == 0) return 0; hlist_for_each_entry(fi, head, fib_lhash) { @@ -1163,12 +1162,12 @@ int fib_sync_down_dev(struct net_device *dev, int force) void fib_select_default(struct fib_result *res) { struct fib_info *fi = NULL, *last_resort = NULL; - struct list_head *fa_head = res->fa_head; + struct hlist_head *fa_head = res->fa_head; struct fib_table *tb = res->table; int order = -1, last_idx = -1; struct fib_alias *fa; - list_for_each_entry_rcu(fa, fa_head, fa_list) { + hlist_for_each_entry_rcu(fa, fa_head, fa_list) { struct fib_info *next_fi = fa->fa_info; if (next_fi->fib_scope != res->scope || @@ -1183,7 +1182,7 @@ void fib_select_default(struct fib_result *res) fib_alias_accessed(fa); - if (fi == NULL) { + if (!fi) { if (next_fi != res->fi) break; } else if (!fib_detect_death(fi, order, &last_resort, @@ -1196,7 +1195,7 @@ void fib_select_default(struct fib_result *res) order++; } - if (order <= 0 || fi == NULL) { + if (order <= 0 || !fi) { tb->tb_default = -1; goto out; } @@ -1252,7 +1251,7 @@ int fib_sync_up(struct net_device *dev) alive++; continue; } - if (nexthop_nh->nh_dev == NULL || + if (!nexthop_nh->nh_dev || !(nexthop_nh->nh_dev->flags & IFF_UP)) continue; if (nexthop_nh->nh_dev != dev || diff --git a/net/ipv4/fib_trie.c b/net/ipv4/fib_trie.c index 3daf0224ff2e..e13fcc602da2 100644 --- a/net/ipv4/fib_trie.c +++ b/net/ipv4/fib_trie.c @@ -79,6 +79,7 @@ #include <net/tcp.h> #include <net/sock.h> #include <net/ip_fib.h> +#include <net/switchdev.h> #include "fib_lookup.h" #define MAX_STAT_DEPTH 32 @@ -88,38 +89,35 @@ typedef unsigned int t_key; -#define IS_TNODE(n) ((n)->bits) -#define IS_LEAF(n) (!(n)->bits) +#define IS_TRIE(n) ((n)->pos >= KEYLENGTH) +#define IS_TNODE(n) ((n)->bits) +#define IS_LEAF(n) (!(n)->bits) -#define get_index(_key, _kv) (((_key) ^ (_kv)->key) >> (_kv)->pos) - -struct tnode { +struct key_vector { t_key key; - unsigned char bits; /* 2log(KEYLENGTH) bits needed */ unsigned char pos; /* 2log(KEYLENGTH) bits needed */ + unsigned char bits; /* 2log(KEYLENGTH) bits needed */ unsigned char slen; - struct tnode __rcu *parent; - struct rcu_head rcu; union { - /* The fields in this struct are valid if bits > 0 (TNODE) */ - struct { - t_key empty_children; /* KEYLENGTH bits needed */ - t_key full_children; /* KEYLENGTH bits needed */ - struct tnode __rcu *child[0]; - }; - /* This list pointer if valid if bits == 0 (LEAF) */ - struct hlist_head list; + /* This list pointer if valid if (pos | bits) == 0 (LEAF) */ + struct hlist_head leaf; + /* This array is valid if (pos | bits) > 0 (TNODE) */ + struct key_vector __rcu *tnode[0]; }; }; -struct leaf_info { - struct hlist_node hlist; - int plen; - u32 mask_plen; /* ntohl(inet_make_mask(plen)) */ - struct list_head falh; +struct tnode { struct rcu_head rcu; + t_key empty_children; /* KEYLENGTH bits needed */ + t_key full_children; /* KEYLENGTH bits needed */ + struct key_vector __rcu *parent; + struct key_vector kv[1]; +#define tn_bits kv[0].bits }; +#define TNODE_SIZE(n) offsetof(struct tnode, kv[0].tnode[n]) +#define LEAF_SIZE TNODE_SIZE(1) + #ifdef CONFIG_IP_FIB_TRIE_STATS struct trie_use_stats { unsigned int gets; @@ -142,13 +140,13 @@ struct trie_stat { }; struct trie { - struct tnode __rcu *trie; + struct key_vector kv[1]; #ifdef CONFIG_IP_FIB_TRIE_STATS struct trie_use_stats __percpu *stats; #endif }; -static void resize(struct trie *t, struct tnode *tn); +static struct key_vector *resize(struct trie *t, struct key_vector *tn); static size_t tnode_free_size; /* @@ -161,41 +159,46 @@ static const int sync_pages = 128; static struct kmem_cache *fn_alias_kmem __read_mostly; static struct kmem_cache *trie_leaf_kmem __read_mostly; +static inline struct tnode *tn_info(struct key_vector *kv) +{ + return container_of(kv, struct tnode, kv[0]); +} + /* caller must hold RTNL */ -#define node_parent(n) rtnl_dereference((n)->parent) +#define node_parent(tn) rtnl_dereference(tn_info(tn)->parent) +#define get_child(tn, i) rtnl_dereference((tn)->tnode[i]) /* caller must hold RCU read lock or RTNL */ -#define node_parent_rcu(n) rcu_dereference_rtnl((n)->parent) +#define node_parent_rcu(tn) rcu_dereference_rtnl(tn_info(tn)->parent) +#define get_child_rcu(tn, i) rcu_dereference_rtnl((tn)->tnode[i]) /* wrapper for rcu_assign_pointer */ -static inline void node_set_parent(struct tnode *n, struct tnode *tp) +static inline void node_set_parent(struct key_vector *n, struct key_vector *tp) { if (n) - rcu_assign_pointer(n->parent, tp); + rcu_assign_pointer(tn_info(n)->parent, tp); } -#define NODE_INIT_PARENT(n, p) RCU_INIT_POINTER((n)->parent, p) +#define NODE_INIT_PARENT(n, p) RCU_INIT_POINTER(tn_info(n)->parent, p) /* This provides us with the number of children in this node, in the case of a * leaf this will return 0 meaning none of the children are accessible. */ -static inline unsigned long tnode_child_length(const struct tnode *tn) +static inline unsigned long child_length(const struct key_vector *tn) { return (1ul << tn->bits) & ~(1ul); } -/* caller must hold RTNL */ -static inline struct tnode *tnode_get_child(const struct tnode *tn, - unsigned long i) -{ - return rtnl_dereference(tn->child[i]); -} +#define get_cindex(key, kv) (((key) ^ (kv)->key) >> (kv)->pos) -/* caller must hold RCU read lock or RTNL */ -static inline struct tnode *tnode_get_child_rcu(const struct tnode *tn, - unsigned long i) +static inline unsigned long get_index(t_key key, struct key_vector *kv) { - return rcu_dereference_rtnl(tn->child[i]); + unsigned long index = key ^ kv->key; + + if ((BITS_PER_LONG <= KEYLENGTH) && (KEYLENGTH == kv->pos)) + return 0; + + return index >> kv->pos; } /* To understand this stuff, an understanding of keys and all their bits is @@ -274,106 +277,104 @@ static inline void alias_free_mem_rcu(struct fib_alias *fa) } #define TNODE_KMALLOC_MAX \ - ilog2((PAGE_SIZE - sizeof(struct tnode)) / sizeof(struct tnode *)) + ilog2((PAGE_SIZE - TNODE_SIZE(0)) / sizeof(struct key_vector *)) +#define TNODE_VMALLOC_MAX \ + ilog2((SIZE_MAX - TNODE_SIZE(0)) / sizeof(struct key_vector *)) static void __node_free_rcu(struct rcu_head *head) { struct tnode *n = container_of(head, struct tnode, rcu); - if (IS_LEAF(n)) + if (!n->tn_bits) kmem_cache_free(trie_leaf_kmem, n); - else if (n->bits <= TNODE_KMALLOC_MAX) + else if (n->tn_bits <= TNODE_KMALLOC_MAX) kfree(n); else vfree(n); } -#define node_free(n) call_rcu(&n->rcu, __node_free_rcu) +#define node_free(n) call_rcu(&tn_info(n)->rcu, __node_free_rcu) -static inline void free_leaf_info(struct leaf_info *leaf) +static struct tnode *tnode_alloc(int bits) { - kfree_rcu(leaf, rcu); -} + size_t size; + + /* verify bits is within bounds */ + if (bits > TNODE_VMALLOC_MAX) + return NULL; + + /* determine size and verify it is non-zero and didn't overflow */ + size = TNODE_SIZE(1ul << bits); -static struct tnode *tnode_alloc(size_t size) -{ if (size <= PAGE_SIZE) return kzalloc(size, GFP_KERNEL); else return vzalloc(size); } -static inline void empty_child_inc(struct tnode *n) +static inline void empty_child_inc(struct key_vector *n) { - ++n->empty_children ? : ++n->full_children; + ++tn_info(n)->empty_children ? : ++tn_info(n)->full_children; } -static inline void empty_child_dec(struct tnode *n) +static inline void empty_child_dec(struct key_vector *n) { - n->empty_children-- ? : n->full_children--; + tn_info(n)->empty_children-- ? : tn_info(n)->full_children--; } -static struct tnode *leaf_new(t_key key) +static struct key_vector *leaf_new(t_key key, struct fib_alias *fa) { - struct tnode *l = kmem_cache_alloc(trie_leaf_kmem, GFP_KERNEL); - if (l) { - l->parent = NULL; - /* set key and pos to reflect full key value - * any trailing zeros in the key should be ignored - * as the nodes are searched - */ - l->key = key; - l->slen = 0; - l->pos = 0; - /* set bits to 0 indicating we are not a tnode */ - l->bits = 0; + struct tnode *kv = kmem_cache_alloc(trie_leaf_kmem, GFP_KERNEL); + struct key_vector *l = kv->kv; - INIT_HLIST_HEAD(&l->list); - } - return l; -} + if (!kv) + return NULL; -static struct leaf_info *leaf_info_new(int plen) -{ - struct leaf_info *li = kmalloc(sizeof(struct leaf_info), GFP_KERNEL); - if (li) { - li->plen = plen; - li->mask_plen = ntohl(inet_make_mask(plen)); - INIT_LIST_HEAD(&li->falh); - } - return li; + /* initialize key vector */ + l->key = key; + l->pos = 0; + l->bits = 0; + l->slen = fa->fa_slen; + + /* link leaf to fib alias */ + INIT_HLIST_HEAD(&l->leaf); + hlist_add_head(&fa->fa_list, &l->leaf); + + return l; } -static struct tnode *tnode_new(t_key key, int pos, int bits) +static struct key_vector *tnode_new(t_key key, int pos, int bits) { - size_t sz = offsetof(struct tnode, child[1ul << bits]); - struct tnode *tn = tnode_alloc(sz); + struct tnode *tnode = tnode_alloc(bits); unsigned int shift = pos + bits; + struct key_vector *tn = tnode->kv; /* verify bits and pos their msb bits clear and values are valid */ BUG_ON(!bits || (shift > KEYLENGTH)); - if (tn) { - tn->parent = NULL; - tn->slen = pos; - tn->pos = pos; - tn->bits = bits; - tn->key = (shift < KEYLENGTH) ? (key >> shift) << shift : 0; - if (bits == KEYLENGTH) - tn->full_children = 1; - else - tn->empty_children = 1ul << bits; - } + pr_debug("AT %p s=%zu %zu\n", tnode, TNODE_SIZE(0), + sizeof(struct key_vector *) << bits); + + if (!tnode) + return NULL; + + if (bits == KEYLENGTH) + tnode->full_children = 1; + else + tnode->empty_children = 1ul << bits; + + tn->key = (shift < KEYLENGTH) ? (key >> shift) << shift : 0; + tn->pos = pos; + tn->bits = bits; + tn->slen = pos; - pr_debug("AT %p s=%zu %zu\n", tn, sizeof(struct tnode), - sizeof(struct tnode *) << bits); return tn; } /* Check whether a tnode 'n' is "full", i.e. it is an internal node * and no bits are skipped. See discussion in dyntree paper p. 6 */ -static inline int tnode_full(const struct tnode *tn, const struct tnode *n) +static inline int tnode_full(struct key_vector *tn, struct key_vector *n) { return n && ((n->pos + n->bits) == tn->pos) && IS_TNODE(n); } @@ -381,17 +382,18 @@ static inline int tnode_full(const struct tnode *tn, const struct tnode *n) /* Add a child at position i overwriting the old value. * Update the value of full_children and empty_children. */ -static void put_child(struct tnode *tn, unsigned long i, struct tnode *n) +static void put_child(struct key_vector *tn, unsigned long i, + struct key_vector *n) { - struct tnode *chi = tnode_get_child(tn, i); + struct key_vector *chi = get_child(tn, i); int isfull, wasfull; - BUG_ON(i >= tnode_child_length(tn)); + BUG_ON(i >= child_length(tn)); /* update emptyChildren, overflow into fullChildren */ - if (n == NULL && chi != NULL) + if (!n && chi) empty_child_inc(tn); - if (n != NULL && chi == NULL) + if (n && !chi) empty_child_dec(tn); /* update fullChildren */ @@ -399,23 +401,23 @@ static void put_child(struct tnode *tn, unsigned long i, struct tnode *n) isfull = tnode_full(tn, n); if (wasfull && !isfull) - tn->full_children--; + tn_info(tn)->full_children--; else if (!wasfull && isfull) - tn->full_children++; + tn_info(tn)->full_children++; if (n && (tn->slen < n->slen)) tn->slen = n->slen; - rcu_assign_pointer(tn->child[i], n); + rcu_assign_pointer(tn->tnode[i], n); } -static void update_children(struct tnode *tn) +static void update_children(struct key_vector *tn) { unsigned long i; /* update all of the child parent pointers */ - for (i = tnode_child_length(tn); i;) { - struct tnode *inode = tnode_get_child(tn, --i); + for (i = child_length(tn); i;) { + struct key_vector *inode = get_child(tn, --i); if (!inode) continue; @@ -431,36 +433,37 @@ static void update_children(struct tnode *tn) } } -static inline void put_child_root(struct tnode *tp, struct trie *t, - t_key key, struct tnode *n) +static inline void put_child_root(struct key_vector *tp, t_key key, + struct key_vector *n) { - if (tp) - put_child(tp, get_index(key, tp), n); + if (IS_TRIE(tp)) + rcu_assign_pointer(tp->tnode[0], n); else - rcu_assign_pointer(t->trie, n); + put_child(tp, get_index(key, tp), n); } -static inline void tnode_free_init(struct tnode *tn) +static inline void tnode_free_init(struct key_vector *tn) { - tn->rcu.next = NULL; + tn_info(tn)->rcu.next = NULL; } -static inline void tnode_free_append(struct tnode *tn, struct tnode *n) +static inline void tnode_free_append(struct key_vector *tn, + struct key_vector *n) { - n->rcu.next = tn->rcu.next; - tn->rcu.next = &n->rcu; + tn_info(n)->rcu.next = tn_info(tn)->rcu.next; + tn_info(tn)->rcu.next = &tn_info(n)->rcu; } -static void tnode_free(struct tnode *tn) +static void tnode_free(struct key_vector *tn) { - struct callback_head *head = &tn->rcu; + struct callback_head *head = &tn_info(tn)->rcu; while (head) { head = head->next; - tnode_free_size += offsetof(struct tnode, child[1 << tn->bits]); + tnode_free_size += TNODE_SIZE(1ul << tn->bits); node_free(tn); - tn = container_of(head, struct tnode, rcu); + tn = container_of(head, struct tnode, rcu)->kv; } if (tnode_free_size >= PAGE_SIZE * sync_pages) { @@ -469,14 +472,16 @@ static void tnode_free(struct tnode *tn) } } -static void replace(struct trie *t, struct tnode *oldtnode, struct tnode *tn) +static struct key_vector *replace(struct trie *t, + struct key_vector *oldtnode, + struct key_vector *tn) { - struct tnode *tp = node_parent(oldtnode); + struct key_vector *tp = node_parent(oldtnode); unsigned long i; /* setup the parent pointer out of and back into this node */ NODE_INIT_PARENT(tn, tp); - put_child_root(tp, t, tn->key, tn); + put_child_root(tp, tn->key, tn); /* update all of the child parent pointers */ update_children(tn); @@ -485,18 +490,21 @@ static void replace(struct trie *t, struct tnode *oldtnode, struct tnode *tn) tnode_free(oldtnode); /* resize children now that oldtnode is freed */ - for (i = tnode_child_length(tn); i;) { - struct tnode *inode = tnode_get_child(tn, --i); + for (i = child_length(tn); i;) { + struct key_vector *inode = get_child(tn, --i); /* resize child node */ if (tnode_full(tn, inode)) - resize(t, inode); + tn = resize(t, inode); } + + return tp; } -static int inflate(struct trie *t, struct tnode *oldtnode) +static struct key_vector *inflate(struct trie *t, + struct key_vector *oldtnode) { - struct tnode *tn; + struct key_vector *tn; unsigned long i; t_key m; @@ -504,7 +512,7 @@ static int inflate(struct trie *t, struct tnode *oldtnode) tn = tnode_new(oldtnode->key, oldtnode->pos - 1, oldtnode->bits + 1); if (!tn) - return -ENOMEM; + goto notnode; /* prepare oldtnode to be freed */ tnode_free_init(oldtnode); @@ -514,13 +522,13 @@ static int inflate(struct trie *t, struct tnode *oldtnode) * point to existing tnodes and the links between our allocated * nodes. */ - for (i = tnode_child_length(oldtnode), m = 1u << tn->pos; i;) { - struct tnode *inode = tnode_get_child(oldtnode, --i); - struct tnode *node0, *node1; + for (i = child_length(oldtnode), m = 1u << tn->pos; i;) { + struct key_vector *inode = get_child(oldtnode, --i); + struct key_vector *node0, *node1; unsigned long j, k; /* An empty child */ - if (inode == NULL) + if (!inode) continue; /* A leaf or an internal node with skipped bits */ @@ -534,8 +542,8 @@ static int inflate(struct trie *t, struct tnode *oldtnode) /* An internal node with two children */ if (inode->bits == 1) { - put_child(tn, 2 * i + 1, tnode_get_child(inode, 1)); - put_child(tn, 2 * i, tnode_get_child(inode, 0)); + put_child(tn, 2 * i + 1, get_child(inode, 1)); + put_child(tn, 2 * i, get_child(inode, 0)); continue; } @@ -564,11 +572,11 @@ static int inflate(struct trie *t, struct tnode *oldtnode) tnode_free_append(tn, node0); /* populate child pointers in new nodes */ - for (k = tnode_child_length(inode), j = k / 2; j;) { - put_child(node1, --j, tnode_get_child(inode, --k)); - put_child(node0, j, tnode_get_child(inode, j)); - put_child(node1, --j, tnode_get_child(inode, --k)); - put_child(node0, j, tnode_get_child(inode, j)); + for (k = child_length(inode), j = k / 2; j;) { + put_child(node1, --j, get_child(inode, --k)); + put_child(node0, j, get_child(inode, j)); + put_child(node1, --j, get_child(inode, --k)); + put_child(node0, j, get_child(inode, j)); } /* link new nodes to parent */ @@ -581,25 +589,25 @@ static int inflate(struct trie *t, struct tnode *oldtnode) } /* setup the parent pointers into and out of this node */ - replace(t, oldtnode, tn); - - return 0; + return replace(t, oldtnode, tn); nomem: /* all pointers should be clean so we are done */ tnode_free(tn); - return -ENOMEM; +notnode: + return NULL; } -static int halve(struct trie *t, struct tnode *oldtnode) +static struct key_vector *halve(struct trie *t, + struct key_vector *oldtnode) { - struct tnode *tn; + struct key_vector *tn; unsigned long i; pr_debug("In halve\n"); tn = tnode_new(oldtnode->key, oldtnode->pos + 1, oldtnode->bits - 1); if (!tn) - return -ENOMEM; + goto notnode; /* prepare oldtnode to be freed */ tnode_free_init(oldtnode); @@ -609,10 +617,10 @@ static int halve(struct trie *t, struct tnode *oldtnode) * point to existing tnodes and the links between our allocated * nodes. */ - for (i = tnode_child_length(oldtnode); i;) { - struct tnode *node1 = tnode_get_child(oldtnode, --i); - struct tnode *node0 = tnode_get_child(oldtnode, --i); - struct tnode *inode; + for (i = child_length(oldtnode); i;) { + struct key_vector *node1 = get_child(oldtnode, --i); + struct key_vector *node0 = get_child(oldtnode, --i); + struct key_vector *inode; /* At least one of the children is empty */ if (!node1 || !node0) { @@ -622,10 +630,8 @@ static int halve(struct trie *t, struct tnode *oldtnode) /* Two nonempty children */ inode = tnode_new(node0->key, oldtnode->pos, 1); - if (!inode) { - tnode_free(tn); - return -ENOMEM; - } + if (!inode) + goto nomem; tnode_free_append(tn, inode); /* initialize pointers out of node */ @@ -638,30 +644,36 @@ static int halve(struct trie *t, struct tnode *oldtnode) } /* setup the parent pointers into and out of this node */ - replace(t, oldtnode, tn); - - return 0; + return replace(t, oldtnode, tn); +nomem: + /* all pointers should be clean so we are done */ + tnode_free(tn); +notnode: + return NULL; } -static void collapse(struct trie *t, struct tnode *oldtnode) +static struct key_vector *collapse(struct trie *t, + struct key_vector *oldtnode) { - struct tnode *n, *tp; + struct key_vector *n, *tp; unsigned long i; /* scan the tnode looking for that one child that might still exist */ - for (n = NULL, i = tnode_child_length(oldtnode); !n && i;) - n = tnode_get_child(oldtnode, --i); + for (n = NULL, i = child_length(oldtnode); !n && i;) + n = get_child(oldtnode, --i); /* compress one level */ tp = node_parent(oldtnode); - put_child_root(tp, t, oldtnode->key, n); + put_child_root(tp, oldtnode->key, n); node_set_parent(n, tp); /* drop dead node */ node_free(oldtnode); + + return tp; } -static unsigned char update_suffix(struct tnode *tn) +static unsigned char update_suffix(struct key_vector *tn) { unsigned char slen = tn->pos; unsigned long stride, i; @@ -671,8 +683,8 @@ static unsigned char update_suffix(struct tnode *tn) * why we start with a stride of 2 since a stride of 1 would * represent the nodes with suffix length equal to tn->pos */ - for (i = 0, stride = 0x2ul ; i < tnode_child_length(tn); i += stride) { - struct tnode *n = tnode_get_child(tn, i); + for (i = 0, stride = 0x2ul ; i < child_length(tn); i += stride) { + struct key_vector *n = get_child(tn, i); if (!n || (n->slen <= slen)) continue; @@ -704,12 +716,12 @@ static unsigned char update_suffix(struct tnode *tn) * * 'high' in this instance is the variable 'inflate_threshold'. It * is expressed as a percentage, so we multiply it with - * tnode_child_length() and instead of multiplying by 2 (since the + * child_length() and instead of multiplying by 2 (since the * child array will be doubled by inflate()) and multiplying * the left-hand side by 100 (to handle the percentage thing) we * multiply the left-hand side by 50. * - * The left-hand side may look a bit weird: tnode_child_length(tn) + * The left-hand side may look a bit weird: child_length(tn) * - tn->empty_children is of course the number of non-null children * in the current node. tn->full_children is the number of "full" * children, that is non-null tnodes with a skip value of 0. @@ -719,10 +731,10 @@ static unsigned char update_suffix(struct tnode *tn) * A clearer way to write this would be: * * to_be_doubled = tn->full_children; - * not_to_be_doubled = tnode_child_length(tn) - tn->empty_children - + * not_to_be_doubled = child_length(tn) - tn->empty_children - * tn->full_children; * - * new_child_length = tnode_child_length(tn) * 2; + * new_child_length = child_length(tn) * 2; * * new_fill_factor = 100 * (not_to_be_doubled + 2*to_be_doubled) / * new_child_length; @@ -739,57 +751,57 @@ static unsigned char update_suffix(struct tnode *tn) * inflate_threshold * new_child_length * * expand not_to_be_doubled and to_be_doubled, and shorten: - * 100 * (tnode_child_length(tn) - tn->empty_children + + * 100 * (child_length(tn) - tn->empty_children + * tn->full_children) >= inflate_threshold * new_child_length * * expand new_child_length: - * 100 * (tnode_child_length(tn) - tn->empty_children + + * 100 * (child_length(tn) - tn->empty_children + * tn->full_children) >= - * inflate_threshold * tnode_child_length(tn) * 2 + * inflate_threshold * child_length(tn) * 2 * * shorten again: - * 50 * (tn->full_children + tnode_child_length(tn) - + * 50 * (tn->full_children + child_length(tn) - * tn->empty_children) >= inflate_threshold * - * tnode_child_length(tn) + * child_length(tn) * */ -static bool should_inflate(const struct tnode *tp, const struct tnode *tn) +static inline bool should_inflate(struct key_vector *tp, struct key_vector *tn) { - unsigned long used = tnode_child_length(tn); + unsigned long used = child_length(tn); unsigned long threshold = used; /* Keep root node larger */ - threshold *= tp ? inflate_threshold : inflate_threshold_root; - used -= tn->empty_children; - used += tn->full_children; + threshold *= IS_TRIE(tp) ? inflate_threshold_root : inflate_threshold; + used -= tn_info(tn)->empty_children; + used += tn_info(tn)->full_children; /* if bits == KEYLENGTH then pos = 0, and will fail below */ return (used > 1) && tn->pos && ((50 * used) >= threshold); } -static bool should_halve(const struct tnode *tp, const struct tnode *tn) +static inline bool should_halve(struct key_vector *tp, struct key_vector *tn) { - unsigned long used = tnode_child_length(tn); + unsigned long used = child_length(tn); unsigned long threshold = used; /* Keep root node larger */ - threshold *= tp ? halve_threshold : halve_threshold_root; - used -= tn->empty_children; + threshold *= IS_TRIE(tp) ? halve_threshold_root : halve_threshold; + used -= tn_info(tn)->empty_children; /* if bits == KEYLENGTH then used = 100% on wrap, and will fail below */ return (used > 1) && (tn->bits > 1) && ((100 * used) < threshold); } -static bool should_collapse(const struct tnode *tn) +static inline bool should_collapse(struct key_vector *tn) { - unsigned long used = tnode_child_length(tn); + unsigned long used = child_length(tn); - used -= tn->empty_children; + used -= tn_info(tn)->empty_children; /* account for bits == KEYLENGTH case */ - if ((tn->bits == KEYLENGTH) && tn->full_children) + if ((tn->bits == KEYLENGTH) && tn_info(tn)->full_children) used -= KEY_MAX; /* One child or none, time to drop us from the trie */ @@ -797,10 +809,13 @@ static bool should_collapse(const struct tnode *tn) } #define MAX_WORK 10 -static void resize(struct trie *t, struct tnode *tn) +static struct key_vector *resize(struct trie *t, struct key_vector *tn) { - struct tnode *tp = node_parent(tn); - struct tnode __rcu **cptr; +#ifdef CONFIG_IP_FIB_TRIE_STATS + struct trie_use_stats __percpu *stats = t->stats; +#endif + struct key_vector *tp = node_parent(tn); + unsigned long cindex = get_index(tn->key, tp); int max_work = MAX_WORK; pr_debug("In tnode_resize %p inflate_threshold=%d threshold=%d\n", @@ -810,183 +825,128 @@ static void resize(struct trie *t, struct tnode *tn) * doing it ourselves. This way we can let RCU fully do its * thing without us interfering */ - cptr = tp ? &tp->child[get_index(tn->key, tp)] : &t->trie; - BUG_ON(tn != rtnl_dereference(*cptr)); + BUG_ON(tn != get_child(tp, cindex)); /* Double as long as the resulting node has a number of * nonempty nodes that are above the threshold. */ while (should_inflate(tp, tn) && max_work) { - if (inflate(t, tn)) { + tp = inflate(t, tn); + if (!tp) { #ifdef CONFIG_IP_FIB_TRIE_STATS - this_cpu_inc(t->stats->resize_node_skipped); + this_cpu_inc(stats->resize_node_skipped); #endif break; } max_work--; - tn = rtnl_dereference(*cptr); + tn = get_child(tp, cindex); } + /* update parent in case inflate failed */ + tp = node_parent(tn); + /* Return if at least one inflate is run */ if (max_work != MAX_WORK) - return; + return tp; /* Halve as long as the number of empty children in this * node is above threshold. */ while (should_halve(tp, tn) && max_work) { - if (halve(t, tn)) { + tp = halve(t, tn); + if (!tp) { #ifdef CONFIG_IP_FIB_TRIE_STATS - this_cpu_inc(t->stats->resize_node_skipped); + this_cpu_inc(stats->resize_node_skipped); #endif break; } max_work--; - tn = rtnl_dereference(*cptr); + tn = get_child(tp, cindex); } /* Only one child remains */ - if (should_collapse(tn)) { - collapse(t, tn); - return; - } + if (should_collapse(tn)) + return collapse(t, tn); + + /* update parent in case halve failed */ + tp = node_parent(tn); /* Return if at least one deflate was run */ if (max_work != MAX_WORK) - return; + return tp; /* push the suffix length to the parent node */ if (tn->slen > tn->pos) { unsigned char slen = update_suffix(tn); - if (tp && (slen > tp->slen)) + if (slen > tp->slen) tp->slen = slen; } -} - -/* readside must use rcu_read_lock currently dump routines - via get_fa_head and dump */ - -static struct leaf_info *find_leaf_info(struct tnode *l, int plen) -{ - struct hlist_head *head = &l->list; - struct leaf_info *li; - - hlist_for_each_entry_rcu(li, head, hlist) - if (li->plen == plen) - return li; - - return NULL; -} - -static inline struct list_head *get_fa_head(struct tnode *l, int plen) -{ - struct leaf_info *li = find_leaf_info(l, plen); - - if (!li) - return NULL; - return &li->falh; + return tp; } -static void leaf_pull_suffix(struct tnode *l) +static void leaf_pull_suffix(struct key_vector *tp, struct key_vector *l) { - struct tnode *tp = node_parent(l); - - while (tp && (tp->slen > tp->pos) && (tp->slen > l->slen)) { + while ((tp->slen > tp->pos) && (tp->slen > l->slen)) { if (update_suffix(tp) > l->slen) break; tp = node_parent(tp); } } -static void leaf_push_suffix(struct tnode *l) +static void leaf_push_suffix(struct key_vector *tn, struct key_vector *l) { - struct tnode *tn = node_parent(l); - /* if this is a new leaf then tn will be NULL and we can sort * out parent suffix lengths as a part of trie_rebalance */ - while (tn && (tn->slen < l->slen)) { + while (tn->slen < l->slen) { tn->slen = l->slen; tn = node_parent(tn); } } -static void remove_leaf_info(struct tnode *l, struct leaf_info *old) -{ - /* record the location of the previous list_info entry */ - struct hlist_node **pprev = old->hlist.pprev; - struct leaf_info *li = hlist_entry(pprev, typeof(*li), hlist.next); - - /* remove the leaf info from the list */ - hlist_del_rcu(&old->hlist); - - /* only access li if it is pointing at the last valid hlist_node */ - if (hlist_empty(&l->list) || (*pprev)) - return; - - /* update the trie with the latest suffix length */ - l->slen = KEYLENGTH - li->plen; - leaf_pull_suffix(l); -} - -static void insert_leaf_info(struct tnode *l, struct leaf_info *new) +/* rcu_read_lock needs to be hold by caller from readside */ +static struct key_vector *fib_find_node(struct trie *t, + struct key_vector **tp, u32 key) { - struct hlist_head *head = &l->list; - struct leaf_info *li = NULL, *last = NULL; + struct key_vector *pn, *n = t->kv; + unsigned long index = 0; - if (hlist_empty(head)) { - hlist_add_head_rcu(&new->hlist, head); - } else { - hlist_for_each_entry(li, head, hlist) { - if (new->plen > li->plen) - break; - - last = li; - } - if (last) - hlist_add_behind_rcu(&new->hlist, &last->hlist); - else - hlist_add_before_rcu(&new->hlist, &li->hlist); - } - - /* if we added to the tail node then we need to update slen */ - if (l->slen < (KEYLENGTH - new->plen)) { - l->slen = KEYLENGTH - new->plen; - leaf_push_suffix(l); - } -} + do { + pn = n; + n = get_child_rcu(n, index); -/* rcu_read_lock needs to be hold by caller from readside */ -static struct tnode *fib_find_node(struct trie *t, u32 key) -{ - struct tnode *n = rcu_dereference_rtnl(t->trie); + if (!n) + break; - while (n) { - unsigned long index = get_index(key, n); + index = get_cindex(key, n); /* This bit of code is a bit tricky but it combines multiple * checks into a single check. The prefix consists of the * prefix plus zeros for the bits in the cindex. The index * is the difference between the key and this value. From * this we can actually derive several pieces of data. - * if (index & (~0ul << bits)) + * if (index >= (1ul << bits)) * we have a mismatch in skip bits and failed * else * we know the value is cindex + * + * This check is safe even if bits == KEYLENGTH due to the + * fact that we can only allocate a node with 32 bits if a + * long is greater than 32 bits. */ - if (index & (~0ul << n->bits)) - return NULL; - - /* we have found a leaf. Prefixes have already been compared */ - if (IS_LEAF(n)) + if (index >= (1ul << n->bits)) { + n = NULL; break; + } - n = tnode_get_child_rcu(n, index); - } + /* keep searching until we find a perfect match leaf or NULL */ + } while (IS_TNODE(n)); + + *tp = pn; return n; } @@ -994,14 +954,23 @@ static struct tnode *fib_find_node(struct trie *t, u32 key) /* Return the first fib alias matching TOS with * priority less than or equal to PRIO. */ -static struct fib_alias *fib_find_alias(struct list_head *fah, u8 tos, u32 prio) +static struct fib_alias *fib_find_alias(struct hlist_head *fah, u8 slen, + u8 tos, u32 prio, u32 tb_id) { struct fib_alias *fa; if (!fah) return NULL; - list_for_each_entry(fa, fah, fa_list) { + hlist_for_each_entry(fa, fah, fa_list) { + if (fa->fa_slen < slen) + continue; + if (fa->fa_slen != slen) + break; + if (fa->tb_id > tb_id) + continue; + if (fa->tb_id != tb_id) + break; if (fa->fa_tos > tos) continue; if (fa->fa_info->fib_priority >= prio || fa->fa_tos < tos) @@ -1011,77 +980,23 @@ static struct fib_alias *fib_find_alias(struct list_head *fah, u8 tos, u32 prio) return NULL; } -static void trie_rebalance(struct trie *t, struct tnode *tn) +static void trie_rebalance(struct trie *t, struct key_vector *tn) { - struct tnode *tp; - - while ((tp = node_parent(tn)) != NULL) { - resize(t, tn); - tn = tp; - } - - /* Handle last (top) tnode */ - if (IS_TNODE(tn)) - resize(t, tn); + while (!IS_TRIE(tn)) + tn = resize(t, tn); } -/* only used from updater-side */ - -static struct list_head *fib_insert_node(struct trie *t, u32 key, int plen) +static int fib_insert_node(struct trie *t, struct key_vector *tp, + struct fib_alias *new, t_key key) { - struct list_head *fa_head = NULL; - struct tnode *l, *n, *tp = NULL; - struct leaf_info *li; - - li = leaf_info_new(plen); - if (!li) - return NULL; - fa_head = &li->falh; + struct key_vector *n, *l; - n = rtnl_dereference(t->trie); - - /* If we point to NULL, stop. Either the tree is empty and we should - * just put a new leaf in if, or we have reached an empty child slot, - * and we should just put our new leaf in that. - * - * If we hit a node with a key that does't match then we should stop - * and create a new tnode to replace that node and insert ourselves - * and the other node into the new tnode. - */ - while (n) { - unsigned long index = get_index(key, n); - - /* This bit of code is a bit tricky but it combines multiple - * checks into a single check. The prefix consists of the - * prefix plus zeros for the "bits" in the prefix. The index - * is the difference between the key and this value. From - * this we can actually derive several pieces of data. - * if !(index >> bits) - * we know the value is child index - * else - * we have a mismatch in skip bits and failed - */ - if (index >> n->bits) - break; - - /* we have found a leaf. Prefixes have already been compared */ - if (IS_LEAF(n)) { - /* Case 1: n is a leaf, and prefixes match*/ - insert_leaf_info(n, li); - return fa_head; - } - - tp = n; - n = tnode_get_child_rcu(n, index); - } - - l = leaf_new(key); - if (!l) { - free_leaf_info(li); - return NULL; - } + l = leaf_new(key, new); + if (!l) + goto noleaf; - insert_leaf_info(l, li); + /* retrieve child from parent node */ + n = get_child(tp, get_index(key, tp)); /* Case 2: n is a LEAF or a TNODE and the key doesn't match. * @@ -1090,21 +1005,18 @@ static struct list_head *fib_insert_node(struct trie *t, u32 key, int plen) * leaves us in position for handling as case 3 */ if (n) { - struct tnode *tn; + struct key_vector *tn; tn = tnode_new(key, __fls(key ^ n->key), 1); - if (!tn) { - free_leaf_info(li); - node_free(l); - return NULL; - } + if (!tn) + goto notnode; /* initialize routes out of node */ NODE_INIT_PARENT(tn, tp); put_child(tn, get_index(key, tn) ^ 1, n); /* start adding routes into the node */ - put_child_root(tp, t, key, tn); + put_child_root(tp, key, tn); node_set_parent(n, tn); /* parent now has a NULL spot where the leaf can go */ @@ -1112,69 +1024,93 @@ static struct list_head *fib_insert_node(struct trie *t, u32 key, int plen) } /* Case 3: n is NULL, and will just insert a new leaf */ - if (tp) { - NODE_INIT_PARENT(l, tp); - put_child(tp, get_index(key, tp), l); - trie_rebalance(t, tp); + NODE_INIT_PARENT(l, tp); + put_child_root(tp, key, l); + trie_rebalance(t, tp); + + return 0; +notnode: + node_free(l); +noleaf: + return -ENOMEM; +} + +static int fib_insert_alias(struct trie *t, struct key_vector *tp, + struct key_vector *l, struct fib_alias *new, + struct fib_alias *fa, t_key key) +{ + if (!l) + return fib_insert_node(t, tp, new, key); + + if (fa) { + hlist_add_before_rcu(&new->fa_list, &fa->fa_list); } else { - rcu_assign_pointer(t->trie, l); + struct fib_alias *last; + + hlist_for_each_entry(last, &l->leaf, fa_list) { + if (new->fa_slen < last->fa_slen) + break; + if ((new->fa_slen == last->fa_slen) && + (new->tb_id > last->tb_id)) + break; + fa = last; + } + + if (fa) + hlist_add_behind_rcu(&new->fa_list, &fa->fa_list); + else + hlist_add_head_rcu(&new->fa_list, &l->leaf); } - return fa_head; + /* if we added to the tail node then we need to update slen */ + if (l->slen < new->fa_slen) { + l->slen = new->fa_slen; + leaf_push_suffix(tp, l); + } + + return 0; } -/* - * Caller must hold RTNL. - */ +/* Caller must hold RTNL. */ int fib_table_insert(struct fib_table *tb, struct fib_config *cfg) { - struct trie *t = (struct trie *) tb->tb_data; + struct trie *t = (struct trie *)tb->tb_data; struct fib_alias *fa, *new_fa; - struct list_head *fa_head = NULL; + struct key_vector *l, *tp; struct fib_info *fi; - int plen = cfg->fc_dst_len; + u8 plen = cfg->fc_dst_len; + u8 slen = KEYLENGTH - plen; u8 tos = cfg->fc_tos; - u32 key, mask; + u32 key; int err; - struct tnode *l; - if (plen > 32) + if (plen > KEYLENGTH) return -EINVAL; key = ntohl(cfg->fc_dst); pr_debug("Insert table=%u %08x/%d\n", tb->tb_id, key, plen); - mask = ntohl(inet_make_mask(plen)); - - if (key & ~mask) + if ((plen < KEYLENGTH) && (key << plen)) return -EINVAL; - key = key & mask; - fi = fib_create_info(cfg); if (IS_ERR(fi)) { err = PTR_ERR(fi); goto err; } - l = fib_find_node(t, key); - fa = NULL; - - if (l) { - fa_head = get_fa_head(l, plen); - fa = fib_find_alias(fa_head, tos, fi->fib_priority); - } + l = fib_find_node(t, &tp, key); + fa = l ? fib_find_alias(&l->leaf, slen, tos, fi->fib_priority, + tb->tb_id) : NULL; /* Now fa, if non-NULL, points to the first fib alias * with the same keys [prefix,tos,priority], if such key already * exists or to the node before which we will insert new one. * * If fa is NULL, we will need to allocate a new one and - * insert to the head of f. - * - * If f is NULL, no fib node matched the destination key - * and we need to allocate a new one of those as well. + * insert to the tail of the section matching the suffix length + * of the new alias. */ if (fa && fa->fa_tos == tos && @@ -1192,9 +1128,10 @@ int fib_table_insert(struct fib_table *tb, struct fib_config *cfg) */ fa_match = NULL; fa_first = fa; - fa = list_entry(fa->fa_list.prev, struct fib_alias, fa_list); - list_for_each_entry_continue(fa, fa_head, fa_list) { - if (fa->fa_tos != tos) + hlist_for_each_entry_from(fa, fa_list) { + if ((fa->fa_slen != slen) || + (fa->tb_id != tb->tb_id) || + (fa->fa_tos != tos)) break; if (fa->fa_info->fib_priority != fi->fib_priority) break; @@ -1217,7 +1154,7 @@ int fib_table_insert(struct fib_table *tb, struct fib_config *cfg) } err = -ENOBUFS; new_fa = kmem_cache_alloc(fn_alias_kmem, GFP_KERNEL); - if (new_fa == NULL) + if (!new_fa) goto out; fi_drop = fa->fa_info; @@ -1226,8 +1163,21 @@ int fib_table_insert(struct fib_table *tb, struct fib_config *cfg) new_fa->fa_type = cfg->fc_type; state = fa->fa_state; new_fa->fa_state = state & ~FA_S_ACCESSED; + new_fa->fa_slen = fa->fa_slen; + + err = netdev_switch_fib_ipv4_add(key, plen, fi, + new_fa->fa_tos, + cfg->fc_type, + cfg->fc_nlflags, + tb->tb_id); + if (err) { + netdev_switch_fib_ipv4_abort(fi); + kmem_cache_free(fn_alias_kmem, new_fa); + goto out; + } + + hlist_replace_rcu(&fa->fa_list, &new_fa->fa_list); - list_replace_rcu(&fa->fa_list, &new_fa->fa_list); alias_free_mem_rcu(fa); fib_release_info(fi_drop); @@ -1254,37 +1204,42 @@ int fib_table_insert(struct fib_table *tb, struct fib_config *cfg) err = -ENOBUFS; new_fa = kmem_cache_alloc(fn_alias_kmem, GFP_KERNEL); - if (new_fa == NULL) + if (!new_fa) goto out; new_fa->fa_info = fi; new_fa->fa_tos = tos; new_fa->fa_type = cfg->fc_type; new_fa->fa_state = 0; - /* - * Insert new entry to the list. - */ - - if (!fa_head) { - fa_head = fib_insert_node(t, key, plen); - if (unlikely(!fa_head)) { - err = -ENOMEM; - goto out_free_new_fa; - } + new_fa->fa_slen = slen; + new_fa->tb_id = tb->tb_id; + + /* (Optionally) offload fib entry to switch hardware. */ + err = netdev_switch_fib_ipv4_add(key, plen, fi, tos, + cfg->fc_type, + cfg->fc_nlflags, + tb->tb_id); + if (err) { + netdev_switch_fib_ipv4_abort(fi); + goto out_free_new_fa; } + /* Insert new entry to the list. */ + err = fib_insert_alias(t, tp, l, new_fa, fa, key); + if (err) + goto out_sw_fib_del; + if (!plen) tb->tb_num_default++; - list_add_tail_rcu(&new_fa->fa_list, - (fa ? &fa->fa_list : fa_head)); - rt_cache_flush(cfg->fc_nlinfo.nl_net); - rtmsg_fib(RTM_NEWROUTE, htonl(key), new_fa, plen, tb->tb_id, + rtmsg_fib(RTM_NEWROUTE, htonl(key), new_fa, plen, new_fa->tb_id, &cfg->fc_nlinfo, 0); succeeded: return 0; +out_sw_fib_del: + netdev_switch_fib_ipv4_del(key, plen, fi, tos, cfg->fc_type, tb->tb_id); out_free_new_fa: kmem_cache_free(fn_alias_kmem, new_fa); out: @@ -1293,7 +1248,7 @@ err: return err; } -static inline t_key prefix_mismatch(t_key key, struct tnode *n) +static inline t_key prefix_mismatch(t_key key, struct key_vector *n) { t_key prefix = n->key; @@ -1304,16 +1259,20 @@ static inline t_key prefix_mismatch(t_key key, struct tnode *n) int fib_table_lookup(struct fib_table *tb, const struct flowi4 *flp, struct fib_result *res, int fib_flags) { - struct trie *t = (struct trie *)tb->tb_data; + struct trie *t = (struct trie *) tb->tb_data; #ifdef CONFIG_IP_FIB_TRIE_STATS struct trie_use_stats __percpu *stats = t->stats; #endif const t_key key = ntohl(flp->daddr); - struct tnode *n, *pn; - struct leaf_info *li; + struct key_vector *n, *pn; + struct fib_alias *fa; + unsigned long index; t_key cindex; - n = rcu_dereference(t->trie); + pn = t->kv; + cindex = 0; + + n = get_child_rcu(pn, cindex); if (!n) return -EAGAIN; @@ -1321,24 +1280,25 @@ int fib_table_lookup(struct fib_table *tb, const struct flowi4 *flp, this_cpu_inc(stats->gets); #endif - pn = n; - cindex = 0; - /* Step 1: Travel to the longest prefix match in the trie */ for (;;) { - unsigned long index = get_index(key, n); + index = get_cindex(key, n); /* This bit of code is a bit tricky but it combines multiple * checks into a single check. The prefix consists of the * prefix plus zeros for the "bits" in the prefix. The index * is the difference between the key and this value. From * this we can actually derive several pieces of data. - * if (index & (~0ul << bits)) + * if (index >= (1ul << bits)) * we have a mismatch in skip bits and failed * else * we know the value is cindex + * + * This check is safe even if bits == KEYLENGTH due to the + * fact that we can only allocate a node with 32 bits if a + * long is greater than 32 bits. */ - if (index & (~0ul << n->bits)) + if (index >= (1ul << n->bits)) break; /* we have found a leaf. Prefixes have already been compared */ @@ -1353,7 +1313,7 @@ int fib_table_lookup(struct fib_table *tb, const struct flowi4 *flp, cindex = index; } - n = tnode_get_child_rcu(n, index); + n = get_child_rcu(n, index); if (unlikely(!n)) goto backtrace; } @@ -1361,7 +1321,7 @@ int fib_table_lookup(struct fib_table *tb, const struct flowi4 *flp, /* Step 2: Sort out leaves and begin backtracing for longest prefix */ for (;;) { /* record the pointer where our next node pointer is stored */ - struct tnode __rcu **cptr = n->child; + struct key_vector __rcu **cptr = n->tnode; /* This test verifies that none of the bits that differ * between the key and the prefix exist in the region of @@ -1393,13 +1353,17 @@ backtrace: while (!cindex) { t_key pkey = pn->key; - pn = node_parent_rcu(pn); - if (unlikely(!pn)) + /* If we don't have a parent then there is + * nothing for us to do as we do not have any + * further nodes to parse. + */ + if (IS_TRIE(pn)) return -EAGAIN; #ifdef CONFIG_IP_FIB_TRIE_STATS this_cpu_inc(stats->backtrack); #endif /* Get Child's index */ + pn = node_parent_rcu(pn); cindex = get_index(pkey, pn); } @@ -1407,138 +1371,134 @@ backtrace: cindex &= cindex - 1; /* grab pointer for next child node */ - cptr = &pn->child[cindex]; + cptr = &pn->tnode[cindex]; } } found: + /* this line carries forward the xor from earlier in the function */ + index = key ^ n->key; + /* Step 3: Process the leaf, if that fails fall back to backtracing */ - hlist_for_each_entry_rcu(li, &n->list, hlist) { - struct fib_alias *fa; + hlist_for_each_entry_rcu(fa, &n->leaf, fa_list) { + struct fib_info *fi = fa->fa_info; + int nhsel, err; - if ((key ^ n->key) & li->mask_plen) + if ((index >= (1ul << fa->fa_slen)) && + ((BITS_PER_LONG > KEYLENGTH) || (fa->fa_slen != KEYLENGTH))) continue; - - list_for_each_entry_rcu(fa, &li->falh, fa_list) { - struct fib_info *fi = fa->fa_info; - int nhsel, err; - - if (fa->fa_tos && fa->fa_tos != flp->flowi4_tos) - continue; - if (fi->fib_dead) - continue; - if (fa->fa_info->fib_scope < flp->flowi4_scope) - continue; - fib_alias_accessed(fa); - err = fib_props[fa->fa_type].error; - if (unlikely(err < 0)) { + if (fa->fa_tos && fa->fa_tos != flp->flowi4_tos) + continue; + if (fi->fib_dead) + continue; + if (fa->fa_info->fib_scope < flp->flowi4_scope) + continue; + fib_alias_accessed(fa); + err = fib_props[fa->fa_type].error; + if (unlikely(err < 0)) { #ifdef CONFIG_IP_FIB_TRIE_STATS - this_cpu_inc(stats->semantic_match_passed); + this_cpu_inc(stats->semantic_match_passed); #endif - return err; - } - if (fi->fib_flags & RTNH_F_DEAD) + return err; + } + if (fi->fib_flags & RTNH_F_DEAD) + continue; + for (nhsel = 0; nhsel < fi->fib_nhs; nhsel++) { + const struct fib_nh *nh = &fi->fib_nh[nhsel]; + + if (nh->nh_flags & RTNH_F_DEAD) continue; - for (nhsel = 0; nhsel < fi->fib_nhs; nhsel++) { - const struct fib_nh *nh = &fi->fib_nh[nhsel]; - - if (nh->nh_flags & RTNH_F_DEAD) - continue; - if (flp->flowi4_oif && flp->flowi4_oif != nh->nh_oif) - continue; - - if (!(fib_flags & FIB_LOOKUP_NOREF)) - atomic_inc(&fi->fib_clntref); - - res->prefixlen = li->plen; - res->nh_sel = nhsel; - res->type = fa->fa_type; - res->scope = fi->fib_scope; - res->fi = fi; - res->table = tb; - res->fa_head = &li->falh; + if (flp->flowi4_oif && flp->flowi4_oif != nh->nh_oif) + continue; + + if (!(fib_flags & FIB_LOOKUP_NOREF)) + atomic_inc(&fi->fib_clntref); + + res->prefixlen = KEYLENGTH - fa->fa_slen; + res->nh_sel = nhsel; + res->type = fa->fa_type; + res->scope = fi->fib_scope; + res->fi = fi; + res->table = tb; + res->fa_head = &n->leaf; #ifdef CONFIG_IP_FIB_TRIE_STATS - this_cpu_inc(stats->semantic_match_passed); + this_cpu_inc(stats->semantic_match_passed); #endif - return err; - } + return err; } - + } #ifdef CONFIG_IP_FIB_TRIE_STATS - this_cpu_inc(stats->semantic_match_miss); + this_cpu_inc(stats->semantic_match_miss); #endif - } goto backtrace; } EXPORT_SYMBOL_GPL(fib_table_lookup); -/* - * Remove the leaf and return parent. - */ -static void trie_leaf_remove(struct trie *t, struct tnode *l) +static void fib_remove_alias(struct trie *t, struct key_vector *tp, + struct key_vector *l, struct fib_alias *old) { - struct tnode *tp = node_parent(l); + /* record the location of the previous list_info entry */ + struct hlist_node **pprev = old->fa_list.pprev; + struct fib_alias *fa = hlist_entry(pprev, typeof(*fa), fa_list.next); - pr_debug("entering trie_leaf_remove(%p)\n", l); + /* remove the fib_alias from the list */ + hlist_del_rcu(&old->fa_list); - if (tp) { - put_child(tp, get_index(l->key, tp), NULL); + /* if we emptied the list this leaf will be freed and we can sort + * out parent suffix lengths as a part of trie_rebalance + */ + if (hlist_empty(&l->leaf)) { + put_child_root(tp, l->key, NULL); + node_free(l); trie_rebalance(t, tp); - } else { - RCU_INIT_POINTER(t->trie, NULL); + return; } - node_free(l); + /* only access fa if it is pointing at the last valid hlist_node */ + if (*pprev) + return; + + /* update the trie with the latest suffix length */ + l->slen = fa->fa_slen; + leaf_pull_suffix(tp, l); } -/* - * Caller must hold RTNL. - */ +/* Caller must hold RTNL. */ int fib_table_delete(struct fib_table *tb, struct fib_config *cfg) { struct trie *t = (struct trie *) tb->tb_data; - u32 key, mask; - int plen = cfg->fc_dst_len; - u8 tos = cfg->fc_tos; struct fib_alias *fa, *fa_to_delete; - struct list_head *fa_head; - struct tnode *l; - struct leaf_info *li; + struct key_vector *l, *tp; + u8 plen = cfg->fc_dst_len; + u8 slen = KEYLENGTH - plen; + u8 tos = cfg->fc_tos; + u32 key; - if (plen > 32) + if (plen > KEYLENGTH) return -EINVAL; key = ntohl(cfg->fc_dst); - mask = ntohl(inet_make_mask(plen)); - if (key & ~mask) + if ((plen < KEYLENGTH) && (key << plen)) return -EINVAL; - key = key & mask; - l = fib_find_node(t, key); - + l = fib_find_node(t, &tp, key); if (!l) return -ESRCH; - li = find_leaf_info(l, plen); - - if (!li) - return -ESRCH; - - fa_head = &li->falh; - fa = fib_find_alias(fa_head, tos, 0); - + fa = fib_find_alias(&l->leaf, slen, tos, 0, tb->tb_id); if (!fa) return -ESRCH; pr_debug("Deleting %08x/%d tos=%d t=%p\n", key, plen, tos, t); fa_to_delete = NULL; - fa = list_entry(fa->fa_list.prev, struct fib_alias, fa_list); - list_for_each_entry_continue(fa, fa_head, fa_list) { + hlist_for_each_entry_from(fa, fa_list) { struct fib_info *fi = fa->fa_info; - if (fa->fa_tos != tos) + if ((fa->fa_slen != slen) || + (fa->tb_id != tb->tb_id) || + (fa->fa_tos != tos)) break; if ((!cfg->fc_type || fa->fa_type == cfg->fc_type) && @@ -1557,240 +1517,397 @@ int fib_table_delete(struct fib_table *tb, struct fib_config *cfg) if (!fa_to_delete) return -ESRCH; - fa = fa_to_delete; - rtmsg_fib(RTM_DELROUTE, htonl(key), fa, plen, tb->tb_id, - &cfg->fc_nlinfo, 0); + netdev_switch_fib_ipv4_del(key, plen, fa_to_delete->fa_info, tos, + cfg->fc_type, tb->tb_id); - list_del_rcu(&fa->fa_list); + rtmsg_fib(RTM_DELROUTE, htonl(key), fa_to_delete, plen, tb->tb_id, + &cfg->fc_nlinfo, 0); if (!plen) tb->tb_num_default--; - if (list_empty(fa_head)) { - remove_leaf_info(l, li); - free_leaf_info(li); - } + fib_remove_alias(t, tp, l, fa_to_delete); - if (hlist_empty(&l->list)) - trie_leaf_remove(t, l); - - if (fa->fa_state & FA_S_ACCESSED) + if (fa_to_delete->fa_state & FA_S_ACCESSED) rt_cache_flush(cfg->fc_nlinfo.nl_net); - fib_release_info(fa->fa_info); - alias_free_mem_rcu(fa); + fib_release_info(fa_to_delete->fa_info); + alias_free_mem_rcu(fa_to_delete); return 0; } -static int trie_flush_list(struct list_head *head) +/* Scan for the next leaf starting at the provided key value */ +static struct key_vector *leaf_walk_rcu(struct key_vector **tn, t_key key) { - struct fib_alias *fa, *fa_node; - int found = 0; + struct key_vector *pn, *n = *tn; + unsigned long cindex; - list_for_each_entry_safe(fa, fa_node, head, fa_list) { - struct fib_info *fi = fa->fa_info; + /* this loop is meant to try and find the key in the trie */ + do { + /* record parent and next child index */ + pn = n; + cindex = key ? get_index(key, pn) : 0; - if (fi && (fi->fib_flags & RTNH_F_DEAD)) { - list_del_rcu(&fa->fa_list); - fib_release_info(fa->fa_info); - alias_free_mem_rcu(fa); - found++; + if (cindex >> pn->bits) + break; + + /* descend into the next child */ + n = get_child_rcu(pn, cindex++); + if (!n) + break; + + /* guarantee forward progress on the keys */ + if (IS_LEAF(n) && (n->key >= key)) + goto found; + } while (IS_TNODE(n)); + + /* this loop will search for the next leaf with a greater key */ + while (!IS_TRIE(pn)) { + /* if we exhausted the parent node we will need to climb */ + if (cindex >= (1ul << pn->bits)) { + t_key pkey = pn->key; + + pn = node_parent_rcu(pn); + cindex = get_index(pkey, pn) + 1; + continue; } + + /* grab the next available node */ + n = get_child_rcu(pn, cindex++); + if (!n) + continue; + + /* no need to compare keys since we bumped the index */ + if (IS_LEAF(n)) + goto found; + + /* Rescan start scanning in new node */ + pn = n; + cindex = 0; } - return found; + + *tn = pn; + return NULL; /* Root of trie */ +found: + /* if we are at the limit for keys just return NULL for the tnode */ + *tn = pn; + return n; } -static int trie_flush_leaf(struct tnode *l) +static void fib_trie_free(struct fib_table *tb) { - int found = 0; - struct hlist_head *lih = &l->list; + struct trie *t = (struct trie *)tb->tb_data; + struct key_vector *pn = t->kv; + unsigned long cindex = 1; struct hlist_node *tmp; - struct leaf_info *li = NULL; - unsigned char plen = KEYLENGTH; + struct fib_alias *fa; + + /* walk trie in reverse order and free everything */ + for (;;) { + struct key_vector *n; + + if (!(cindex--)) { + t_key pkey = pn->key; + + if (IS_TRIE(pn)) + break; + + n = pn; + pn = node_parent(pn); - hlist_for_each_entry_safe(li, tmp, lih, hlist) { - found += trie_flush_list(&li->falh); + /* drop emptied tnode */ + put_child_root(pn, n->key, NULL); + node_free(n); + + cindex = get_index(pkey, pn); - if (list_empty(&li->falh)) { - hlist_del_rcu(&li->hlist); - free_leaf_info(li); continue; } - plen = li->plen; - } + /* grab the next available node */ + n = get_child(pn, cindex); + if (!n) + continue; - l->slen = KEYLENGTH - plen; + if (IS_TNODE(n)) { + /* record pn and cindex for leaf walking */ + pn = n; + cindex = 1ul << n->bits; - return found; + continue; + } + + hlist_for_each_entry_safe(fa, tmp, &n->leaf, fa_list) { + hlist_del_rcu(&fa->fa_list); + alias_free_mem_rcu(fa); + } + + put_child_root(pn, n->key, NULL); + node_free(n); + } + +#ifdef CONFIG_IP_FIB_TRIE_STATS + free_percpu(t->stats); +#endif + kfree(tb); } -/* - * Scan for the next right leaf starting at node p->child[idx] - * Since we have back pointer, no recursion necessary. - */ -static struct tnode *leaf_walk_rcu(struct tnode *p, struct tnode *c) +struct fib_table *fib_trie_unmerge(struct fib_table *oldtb) { - do { - unsigned long idx = c ? idx = get_index(c->key, p) + 1 : 0; + struct trie *ot = (struct trie *)oldtb->tb_data; + struct key_vector *l, *tp = ot->kv; + struct fib_table *local_tb; + struct fib_alias *fa; + struct trie *lt; + t_key key = 0; - while (idx < tnode_child_length(p)) { - c = tnode_get_child_rcu(p, idx++); - if (!c) + if (oldtb->tb_data == oldtb->__data) + return oldtb; + + local_tb = fib_trie_table(RT_TABLE_LOCAL, NULL); + if (!local_tb) + return NULL; + + lt = (struct trie *)local_tb->tb_data; + + while ((l = leaf_walk_rcu(&tp, key)) != NULL) { + struct key_vector *local_l = NULL, *local_tp; + + hlist_for_each_entry_rcu(fa, &l->leaf, fa_list) { + struct fib_alias *new_fa; + + if (local_tb->tb_id != fa->tb_id) continue; - if (IS_LEAF(c)) - return c; + /* clone fa for new local table */ + new_fa = kmem_cache_alloc(fn_alias_kmem, GFP_KERNEL); + if (!new_fa) + goto out; + + memcpy(new_fa, fa, sizeof(*fa)); - /* Rescan start scanning in new node */ - p = c; - idx = 0; + /* insert clone into table */ + if (!local_l) + local_l = fib_find_node(lt, &local_tp, l->key); + + if (fib_insert_alias(lt, local_tp, local_l, new_fa, + NULL, l->key)) + goto out; } - /* Node empty, walk back up to parent */ - c = p; - } while ((p = node_parent_rcu(c)) != NULL); + /* stop loop if key wrapped back to 0 */ + key = l->key + 1; + if (key < l->key) + break; + } - return NULL; /* Root of trie */ + return local_tb; +out: + fib_trie_free(local_tb); + + return NULL; } -static struct tnode *trie_firstleaf(struct trie *t) +/* Caller must hold RTNL */ +void fib_table_flush_external(struct fib_table *tb) { - struct tnode *n = rcu_dereference_rtnl(t->trie); + struct trie *t = (struct trie *)tb->tb_data; + struct key_vector *pn = t->kv; + unsigned long cindex = 1; + struct hlist_node *tmp; + struct fib_alias *fa; - if (!n) - return NULL; + /* walk trie in reverse order */ + for (;;) { + unsigned char slen = 0; + struct key_vector *n; - if (IS_LEAF(n)) /* trie is just a leaf */ - return n; + if (!(cindex--)) { + t_key pkey = pn->key; - return leaf_walk_rcu(n, NULL); -} + /* cannot resize the trie vector */ + if (IS_TRIE(pn)) + break; -static struct tnode *trie_nextleaf(struct tnode *l) -{ - struct tnode *p = node_parent_rcu(l); + /* resize completed node */ + pn = resize(t, pn); + cindex = get_index(pkey, pn); - if (!p) - return NULL; /* trie with just one leaf */ + continue; + } - return leaf_walk_rcu(p, l); -} + /* grab the next available node */ + n = get_child(pn, cindex); + if (!n) + continue; -static struct tnode *trie_leafindex(struct trie *t, int index) -{ - struct tnode *l = trie_firstleaf(t); + if (IS_TNODE(n)) { + /* record pn and cindex for leaf walking */ + pn = n; + cindex = 1ul << n->bits; - while (l && index-- > 0) - l = trie_nextleaf(l); + continue; + } - return l; -} + hlist_for_each_entry_safe(fa, tmp, &n->leaf, fa_list) { + struct fib_info *fi = fa->fa_info; + + /* if alias was cloned to local then we just + * need to remove the local copy from main + */ + if (tb->tb_id != fa->tb_id) { + hlist_del_rcu(&fa->fa_list); + alias_free_mem_rcu(fa); + continue; + } + /* record local slen */ + slen = fa->fa_slen; -/* - * Caller must hold RTNL. - */ + if (!fi || !(fi->fib_flags & RTNH_F_EXTERNAL)) + continue; + + netdev_switch_fib_ipv4_del(n->key, + KEYLENGTH - fa->fa_slen, + fi, fa->fa_tos, + fa->fa_type, tb->tb_id); + } + + /* update leaf slen */ + n->slen = slen; + + if (hlist_empty(&n->leaf)) { + put_child_root(pn, n->key, NULL); + node_free(n); + } else { + leaf_pull_suffix(pn, n); + } + } +} + +/* Caller must hold RTNL. */ int fib_table_flush(struct fib_table *tb) { - struct trie *t = (struct trie *) tb->tb_data; - struct tnode *l, *ll = NULL; + struct trie *t = (struct trie *)tb->tb_data; + struct key_vector *pn = t->kv; + unsigned long cindex = 1; + struct hlist_node *tmp; + struct fib_alias *fa; int found = 0; - for (l = trie_firstleaf(t); l; l = trie_nextleaf(l)) { - found += trie_flush_leaf(l); + /* walk trie in reverse order */ + for (;;) { + unsigned char slen = 0; + struct key_vector *n; + + if (!(cindex--)) { + t_key pkey = pn->key; - if (ll) { - if (hlist_empty(&ll->list)) - trie_leaf_remove(t, ll); - else - leaf_pull_suffix(ll); + /* cannot resize the trie vector */ + if (IS_TRIE(pn)) + break; + + /* resize completed node */ + pn = resize(t, pn); + cindex = get_index(pkey, pn); + + continue; } - ll = l; - } + /* grab the next available node */ + n = get_child(pn, cindex); + if (!n) + continue; - if (ll) { - if (hlist_empty(&ll->list)) - trie_leaf_remove(t, ll); - else - leaf_pull_suffix(ll); + if (IS_TNODE(n)) { + /* record pn and cindex for leaf walking */ + pn = n; + cindex = 1ul << n->bits; + + continue; + } + + hlist_for_each_entry_safe(fa, tmp, &n->leaf, fa_list) { + struct fib_info *fi = fa->fa_info; + + if (!fi || !(fi->fib_flags & RTNH_F_DEAD)) { + slen = fa->fa_slen; + continue; + } + + netdev_switch_fib_ipv4_del(n->key, + KEYLENGTH - fa->fa_slen, + fi, fa->fa_tos, + fa->fa_type, tb->tb_id); + hlist_del_rcu(&fa->fa_list); + fib_release_info(fa->fa_info); + alias_free_mem_rcu(fa); + found++; + } + + /* update leaf slen */ + n->slen = slen; + + if (hlist_empty(&n->leaf)) { + put_child_root(pn, n->key, NULL); + node_free(n); + } else { + leaf_pull_suffix(pn, n); + } } pr_debug("trie_flush found=%d\n", found); return found; } -void fib_free_table(struct fib_table *tb) +static void __trie_free_rcu(struct rcu_head *head) { + struct fib_table *tb = container_of(head, struct fib_table, rcu); #ifdef CONFIG_IP_FIB_TRIE_STATS struct trie *t = (struct trie *)tb->tb_data; - free_percpu(t->stats); + if (tb->tb_data == tb->__data) + free_percpu(t->stats); #endif /* CONFIG_IP_FIB_TRIE_STATS */ kfree(tb); } -static int fn_trie_dump_fa(t_key key, int plen, struct list_head *fah, - struct fib_table *tb, - struct sk_buff *skb, struct netlink_callback *cb) +void fib_free_table(struct fib_table *tb) { - int i, s_i; + call_rcu(&tb->rcu, __trie_free_rcu); +} + +static int fn_trie_dump_leaf(struct key_vector *l, struct fib_table *tb, + struct sk_buff *skb, struct netlink_callback *cb) +{ + __be32 xkey = htonl(l->key); struct fib_alias *fa; - __be32 xkey = htonl(key); + int i, s_i; - s_i = cb->args[5]; + s_i = cb->args[4]; i = 0; /* rcu_read_lock is hold by caller */ - - list_for_each_entry_rcu(fa, fah, fa_list) { + hlist_for_each_entry_rcu(fa, &l->leaf, fa_list) { if (i < s_i) { i++; continue; } + if (tb->tb_id != fa->tb_id) { + i++; + continue; + } + if (fib_dump_info(skb, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, RTM_NEWROUTE, tb->tb_id, fa->fa_type, xkey, - plen, + KEYLENGTH - fa->fa_slen, fa->fa_tos, fa->fa_info, NLM_F_MULTI) < 0) { - cb->args[5] = i; - return -1; - } - i++; - } - cb->args[5] = i; - return skb->len; -} - -static int fn_trie_dump_leaf(struct tnode *l, struct fib_table *tb, - struct sk_buff *skb, struct netlink_callback *cb) -{ - struct leaf_info *li; - int i, s_i; - - s_i = cb->args[4]; - i = 0; - - /* rcu_read_lock is hold by caller */ - hlist_for_each_entry_rcu(li, &l->list, hlist) { - if (i < s_i) { - i++; - continue; - } - - if (i > s_i) - cb->args[5] = 0; - - if (list_empty(&li->falh)) - continue; - - if (fn_trie_dump_fa(l->key, li->plen, &li->falh, tb, skb, cb) < 0) { cb->args[4] = i; return -1; } @@ -1801,44 +1918,38 @@ static int fn_trie_dump_leaf(struct tnode *l, struct fib_table *tb, return skb->len; } +/* rcu_read_lock needs to be hold by caller from readside */ int fib_table_dump(struct fib_table *tb, struct sk_buff *skb, struct netlink_callback *cb) { - struct tnode *l; - struct trie *t = (struct trie *) tb->tb_data; - t_key key = cb->args[2]; - int count = cb->args[3]; - - rcu_read_lock(); + struct trie *t = (struct trie *)tb->tb_data; + struct key_vector *l, *tp = t->kv; /* Dump starting at last key. * Note: 0.0.0.0/0 (ie default) is first key. */ - if (count == 0) - l = trie_firstleaf(t); - else { - /* Normally, continue from last key, but if that is missing - * fallback to using slow rescan - */ - l = fib_find_node(t, key); - if (!l) - l = trie_leafindex(t, count); - } + int count = cb->args[2]; + t_key key = cb->args[3]; - while (l) { - cb->args[2] = l->key; + while ((l = leaf_walk_rcu(&tp, key)) != NULL) { if (fn_trie_dump_leaf(l, tb, skb, cb) < 0) { - cb->args[3] = count; - rcu_read_unlock(); + cb->args[3] = key; + cb->args[2] = count; return -1; } ++count; - l = trie_nextleaf(l); + key = l->key + 1; + memset(&cb->args[4], 0, sizeof(cb->args) - 4*sizeof(cb->args[0])); + + /* stop loop if key wrapped back to 0 */ + if (key < l->key) + break; } - cb->args[3] = count; - rcu_read_unlock(); + + cb->args[3] = key; + cb->args[2] = count; return skb->len; } @@ -1850,28 +1961,34 @@ void __init fib_trie_init(void) 0, SLAB_PANIC, NULL); trie_leaf_kmem = kmem_cache_create("ip_fib_trie", - max(sizeof(struct tnode), - sizeof(struct leaf_info)), + LEAF_SIZE, 0, SLAB_PANIC, NULL); } - -struct fib_table *fib_trie_table(u32 id) +struct fib_table *fib_trie_table(u32 id, struct fib_table *alias) { struct fib_table *tb; struct trie *t; + size_t sz = sizeof(*tb); + + if (!alias) + sz += sizeof(struct trie); - tb = kmalloc(sizeof(struct fib_table) + sizeof(struct trie), - GFP_KERNEL); - if (tb == NULL) + tb = kzalloc(sz, GFP_KERNEL); + if (!tb) return NULL; tb->tb_id = id; tb->tb_default = -1; tb->tb_num_default = 0; + tb->tb_data = (alias ? alias->__data : tb->__data); + + if (alias) + return tb; t = (struct trie *) tb->tb_data; - RCU_INIT_POINTER(t->trie, NULL); + t->kv[0].pos = KEYLENGTH; + t->kv[0].slen = KEYLENGTH; #ifdef CONFIG_IP_FIB_TRIE_STATS t->stats = alloc_percpu(struct trie_use_stats); if (!t->stats) { @@ -1888,65 +2005,63 @@ struct fib_table *fib_trie_table(u32 id) struct fib_trie_iter { struct seq_net_private p; struct fib_table *tb; - struct tnode *tnode; + struct key_vector *tnode; unsigned int index; unsigned int depth; }; -static struct tnode *fib_trie_get_next(struct fib_trie_iter *iter) +static struct key_vector *fib_trie_get_next(struct fib_trie_iter *iter) { unsigned long cindex = iter->index; - struct tnode *tn = iter->tnode; - struct tnode *p; - - /* A single entry routing table */ - if (!tn) - return NULL; + struct key_vector *pn = iter->tnode; + t_key pkey; pr_debug("get_next iter={node=%p index=%d depth=%d}\n", iter->tnode, iter->index, iter->depth); -rescan: - while (cindex < tnode_child_length(tn)) { - struct tnode *n = tnode_get_child_rcu(tn, cindex); - if (n) { + while (!IS_TRIE(pn)) { + while (cindex < child_length(pn)) { + struct key_vector *n = get_child_rcu(pn, cindex++); + + if (!n) + continue; + if (IS_LEAF(n)) { - iter->tnode = tn; - iter->index = cindex + 1; + iter->tnode = pn; + iter->index = cindex; } else { /* push down one level */ iter->tnode = n; iter->index = 0; ++iter->depth; } + return n; } - ++cindex; - } - - /* Current node exhausted, pop back up */ - p = node_parent_rcu(tn); - if (p) { - cindex = get_index(tn->key, p) + 1; - tn = p; + /* Current node exhausted, pop back up */ + pkey = pn->key; + pn = node_parent_rcu(pn); + cindex = get_index(pkey, pn) + 1; --iter->depth; - goto rescan; } - /* got root? */ + /* record root node so further searches know we are done */ + iter->tnode = pn; + iter->index = 0; + return NULL; } -static struct tnode *fib_trie_get_first(struct fib_trie_iter *iter, - struct trie *t) +static struct key_vector *fib_trie_get_first(struct fib_trie_iter *iter, + struct trie *t) { - struct tnode *n; + struct key_vector *n, *pn = t->kv; if (!t) return NULL; - n = rcu_dereference(t->trie); + n = rcu_dereference(pn->tnode[0]); if (!n) return NULL; @@ -1955,7 +2070,7 @@ static struct tnode *fib_trie_get_first(struct fib_trie_iter *iter, iter->index = 0; iter->depth = 1; } else { - iter->tnode = NULL; + iter->tnode = pn; iter->index = 0; iter->depth = 0; } @@ -1965,7 +2080,7 @@ static struct tnode *fib_trie_get_first(struct fib_trie_iter *iter, static void trie_collect_stats(struct trie *t, struct trie_stat *s) { - struct tnode *n; + struct key_vector *n; struct fib_trie_iter iter; memset(s, 0, sizeof(*s)); @@ -1973,20 +2088,20 @@ static void trie_collect_stats(struct trie *t, struct trie_stat *s) rcu_read_lock(); for (n = fib_trie_get_first(&iter, t); n; n = fib_trie_get_next(&iter)) { if (IS_LEAF(n)) { - struct leaf_info *li; + struct fib_alias *fa; s->leaves++; s->totdepth += iter.depth; if (iter.depth > s->maxdepth) s->maxdepth = iter.depth; - hlist_for_each_entry_rcu(li, &n->list, hlist) + hlist_for_each_entry_rcu(fa, &n->leaf, fa_list) ++s->prefixes; } else { s->tnodes++; if (n->bits < MAX_STAT_DEPTH) s->nodesizes[n->bits]++; - s->nullpointers += n->empty_children; + s->nullpointers += tn_info(n)->empty_children; } } rcu_read_unlock(); @@ -2009,13 +2124,13 @@ static void trie_show_stats(struct seq_file *seq, struct trie_stat *stat) seq_printf(seq, "\tMax depth: %u\n", stat->maxdepth); seq_printf(seq, "\tLeaves: %u\n", stat->leaves); - bytes = sizeof(struct tnode) * stat->leaves; + bytes = LEAF_SIZE * stat->leaves; seq_printf(seq, "\tPrefixes: %u\n", stat->prefixes); - bytes += sizeof(struct leaf_info) * stat->prefixes; + bytes += sizeof(struct fib_alias) * stat->prefixes; seq_printf(seq, "\tInternal nodes: %u\n\t", stat->tnodes); - bytes += sizeof(struct tnode) * stat->tnodes; + bytes += TNODE_SIZE(0) * stat->tnodes; max = MAX_STAT_DEPTH; while (max > 0 && stat->nodesizes[max-1] == 0) @@ -2030,7 +2145,7 @@ static void trie_show_stats(struct seq_file *seq, struct trie_stat *stat) seq_putc(seq, '\n'); seq_printf(seq, "\tPointers: %u\n", pointers); - bytes += sizeof(struct tnode *) * pointers; + bytes += sizeof(struct key_vector *) * pointers; seq_printf(seq, "Null ptrs: %u\n", stat->nullpointers); seq_printf(seq, "Total size: %u kB\n", (bytes + 1023) / 1024); } @@ -2084,7 +2199,7 @@ static int fib_triestat_seq_show(struct seq_file *seq, void *v) seq_printf(seq, "Basic info: size of leaf:" " %Zd bytes, size of tnode: %Zd bytes.\n", - sizeof(struct tnode), sizeof(struct tnode)); + LEAF_SIZE, TNODE_SIZE(0)); for (h = 0; h < FIB_TABLE_HASHSZ; h++) { struct hlist_head *head = &net->ipv4.fib_table_hash[h]; @@ -2123,7 +2238,7 @@ static const struct file_operations fib_triestat_fops = { .release = single_release_net, }; -static struct tnode *fib_trie_get_idx(struct seq_file *seq, loff_t pos) +static struct key_vector *fib_trie_get_idx(struct seq_file *seq, loff_t pos) { struct fib_trie_iter *iter = seq->private; struct net *net = seq_file_net(seq); @@ -2135,7 +2250,7 @@ static struct tnode *fib_trie_get_idx(struct seq_file *seq, loff_t pos) struct fib_table *tb; hlist_for_each_entry_rcu(tb, head, tb_hlist) { - struct tnode *n; + struct key_vector *n; for (n = fib_trie_get_first(iter, (struct trie *) tb->tb_data); @@ -2164,7 +2279,7 @@ static void *fib_trie_seq_next(struct seq_file *seq, void *v, loff_t *pos) struct fib_table *tb = iter->tb; struct hlist_node *tb_node; unsigned int h; - struct tnode *n; + struct key_vector *n; ++*pos; /* next node in same table */ @@ -2250,9 +2365,9 @@ static inline const char *rtn_type(char *buf, size_t len, unsigned int t) static int fib_trie_seq_show(struct seq_file *seq, void *v) { const struct fib_trie_iter *iter = seq->private; - struct tnode *n = v; + struct key_vector *n = v; - if (!node_parent_rcu(n)) + if (IS_TRIE(node_parent_rcu(n))) fib_table_print(seq, iter->tb); if (IS_TNODE(n)) { @@ -2261,30 +2376,28 @@ static int fib_trie_seq_show(struct seq_file *seq, void *v) seq_indent(seq, iter->depth-1); seq_printf(seq, " +-- %pI4/%zu %u %u %u\n", &prf, KEYLENGTH - n->pos - n->bits, n->bits, - n->full_children, n->empty_children); + tn_info(n)->full_children, + tn_info(n)->empty_children); } else { - struct leaf_info *li; __be32 val = htonl(n->key); + struct fib_alias *fa; seq_indent(seq, iter->depth); seq_printf(seq, " |-- %pI4\n", &val); - hlist_for_each_entry_rcu(li, &n->list, hlist) { - struct fib_alias *fa; - - list_for_each_entry_rcu(fa, &li->falh, fa_list) { - char buf1[32], buf2[32]; - - seq_indent(seq, iter->depth+1); - seq_printf(seq, " /%d %s %s", li->plen, - rtn_scope(buf1, sizeof(buf1), - fa->fa_info->fib_scope), - rtn_type(buf2, sizeof(buf2), - fa->fa_type)); - if (fa->fa_tos) - seq_printf(seq, " tos=%d", fa->fa_tos); - seq_putc(seq, '\n'); - } + hlist_for_each_entry_rcu(fa, &n->leaf, fa_list) { + char buf1[32], buf2[32]; + + seq_indent(seq, iter->depth + 1); + seq_printf(seq, " /%zu %s %s", + KEYLENGTH - fa->fa_slen, + rtn_scope(buf1, sizeof(buf1), + fa->fa_info->fib_scope), + rtn_type(buf2, sizeof(buf2), + fa->fa_type)); + if (fa->fa_tos) + seq_printf(seq, " tos=%d", fa->fa_tos); + seq_putc(seq, '\n'); } } @@ -2314,31 +2427,47 @@ static const struct file_operations fib_trie_fops = { struct fib_route_iter { struct seq_net_private p; - struct trie *main_trie; + struct fib_table *main_tb; + struct key_vector *tnode; loff_t pos; t_key key; }; -static struct tnode *fib_route_get_idx(struct fib_route_iter *iter, loff_t pos) +static struct key_vector *fib_route_get_idx(struct fib_route_iter *iter, + loff_t pos) { - struct tnode *l = NULL; - struct trie *t = iter->main_trie; + struct fib_table *tb = iter->main_tb; + struct key_vector *l, **tp = &iter->tnode; + struct trie *t; + t_key key; - /* use cache location of last found key */ - if (iter->pos > 0 && pos >= iter->pos && (l = fib_find_node(t, iter->key))) + /* use cache location of next-to-find key */ + if (iter->pos > 0 && pos >= iter->pos) { pos -= iter->pos; - else { + key = iter->key; + } else { + t = (struct trie *)tb->tb_data; + iter->tnode = t->kv; iter->pos = 0; - l = trie_firstleaf(t); + key = 0; } - while (l && pos-- > 0) { + while ((l = leaf_walk_rcu(tp, key)) != NULL) { + key = l->key + 1; iter->pos++; - l = trie_nextleaf(l); + + if (pos-- <= 0) + break; + + l = NULL; + + /* handle unlikely case of a key wrap */ + if (!key) + break; } if (l) - iter->key = pos; /* remember it */ + iter->key = key; /* remember it */ else iter->pos = 0; /* forget it */ @@ -2350,37 +2479,46 @@ static void *fib_route_seq_start(struct seq_file *seq, loff_t *pos) { struct fib_route_iter *iter = seq->private; struct fib_table *tb; + struct trie *t; rcu_read_lock(); + tb = fib_get_table(seq_file_net(seq), RT_TABLE_MAIN); if (!tb) return NULL; - iter->main_trie = (struct trie *) tb->tb_data; - if (*pos == 0) - return SEQ_START_TOKEN; - else - return fib_route_get_idx(iter, *pos - 1); + iter->main_tb = tb; + + if (*pos != 0) + return fib_route_get_idx(iter, *pos); + + t = (struct trie *)tb->tb_data; + iter->tnode = t->kv; + iter->pos = 0; + iter->key = 0; + + return SEQ_START_TOKEN; } static void *fib_route_seq_next(struct seq_file *seq, void *v, loff_t *pos) { struct fib_route_iter *iter = seq->private; - struct tnode *l = v; + struct key_vector *l = NULL; + t_key key = iter->key; ++*pos; - if (v == SEQ_START_TOKEN) { - iter->pos = 0; - l = trie_firstleaf(iter->main_trie); - } else { + + /* only allow key of 0 for start of sequence */ + if ((v == SEQ_START_TOKEN) || key) + l = leaf_walk_rcu(&iter->tnode, key); + + if (l) { + iter->key = l->key + 1; iter->pos++; - l = trie_nextleaf(l); + } else { + iter->pos = 0; } - if (l) - iter->key = l->key; - else - iter->pos = 0; return l; } @@ -2412,8 +2550,11 @@ static unsigned int fib_flag_trans(int type, __be32 mask, const struct fib_info */ static int fib_route_seq_show(struct seq_file *seq, void *v) { - struct tnode *l = v; - struct leaf_info *li; + struct fib_route_iter *iter = seq->private; + struct fib_table *tb = iter->main_tb; + struct fib_alias *fa; + struct key_vector *l = v; + __be32 prefix; if (v == SEQ_START_TOKEN) { seq_printf(seq, "%-127s\n", "Iface\tDestination\tGateway " @@ -2422,45 +2563,43 @@ static int fib_route_seq_show(struct seq_file *seq, void *v) return 0; } - hlist_for_each_entry_rcu(li, &l->list, hlist) { - struct fib_alias *fa; - __be32 mask, prefix; + prefix = htonl(l->key); - mask = inet_make_mask(li->plen); - prefix = htonl(l->key); + hlist_for_each_entry_rcu(fa, &l->leaf, fa_list) { + const struct fib_info *fi = fa->fa_info; + __be32 mask = inet_make_mask(KEYLENGTH - fa->fa_slen); + unsigned int flags = fib_flag_trans(fa->fa_type, mask, fi); - list_for_each_entry_rcu(fa, &li->falh, fa_list) { - const struct fib_info *fi = fa->fa_info; - unsigned int flags = fib_flag_trans(fa->fa_type, mask, fi); + if ((fa->fa_type == RTN_BROADCAST) || + (fa->fa_type == RTN_MULTICAST)) + continue; - if (fa->fa_type == RTN_BROADCAST - || fa->fa_type == RTN_MULTICAST) - continue; + if (fa->tb_id != tb->tb_id) + continue; - seq_setwidth(seq, 127); - - if (fi) - seq_printf(seq, - "%s\t%08X\t%08X\t%04X\t%d\t%u\t" - "%d\t%08X\t%d\t%u\t%u", - fi->fib_dev ? fi->fib_dev->name : "*", - prefix, - fi->fib_nh->nh_gw, flags, 0, 0, - fi->fib_priority, - mask, - (fi->fib_advmss ? - fi->fib_advmss + 40 : 0), - fi->fib_window, - fi->fib_rtt >> 3); - else - seq_printf(seq, - "*\t%08X\t%08X\t%04X\t%d\t%u\t" - "%d\t%08X\t%d\t%u\t%u", - prefix, 0, flags, 0, 0, 0, - mask, 0, 0, 0); - - seq_pad(seq, '\n'); - } + seq_setwidth(seq, 127); + + if (fi) + seq_printf(seq, + "%s\t%08X\t%08X\t%04X\t%d\t%u\t" + "%d\t%08X\t%d\t%u\t%u", + fi->fib_dev ? fi->fib_dev->name : "*", + prefix, + fi->fib_nh->nh_gw, flags, 0, 0, + fi->fib_priority, + mask, + (fi->fib_advmss ? + fi->fib_advmss + 40 : 0), + fi->fib_window, + fi->fib_rtt >> 3); + else + seq_printf(seq, + "*\t%08X\t%08X\t%04X\t%d\t%u\t" + "%d\t%08X\t%d\t%u\t%u", + prefix, 0, flags, 0, 0, 0, + mask, 0, 0, 0); + + seq_pad(seq, '\n'); } return 0; diff --git a/net/ipv4/fou.c b/net/ipv4/fou.c index ff069f6597ac..34968cd5c146 100644 --- a/net/ipv4/fou.c +++ b/net/ipv4/fou.c @@ -16,14 +16,12 @@ #include <uapi/linux/fou.h> #include <uapi/linux/genetlink.h> -static DEFINE_SPINLOCK(fou_lock); -static LIST_HEAD(fou_list); - struct fou { struct socket *sock; u8 protocol; u8 flags; - u16 port; + __be16 port; + u16 type; struct udp_offload udp_offloads; struct list_head list; }; @@ -37,6 +35,13 @@ struct fou_cfg { struct udp_port_cfg udp_config; }; +static unsigned int fou_net_id; + +struct fou_net { + struct list_head fou_list; + struct mutex fou_lock; +}; + static inline struct fou *fou_from_sock(struct sock *sk) { return sk->sk_user_data; @@ -387,20 +392,21 @@ out_unlock: return err; } -static int fou_add_to_port_list(struct fou *fou) +static int fou_add_to_port_list(struct net *net, struct fou *fou) { + struct fou_net *fn = net_generic(net, fou_net_id); struct fou *fout; - spin_lock(&fou_lock); - list_for_each_entry(fout, &fou_list, list) { + mutex_lock(&fn->fou_lock); + list_for_each_entry(fout, &fn->fou_list, list) { if (fou->port == fout->port) { - spin_unlock(&fou_lock); + mutex_unlock(&fn->fou_lock); return -EALREADY; } } - list_add(&fou->list, &fou_list); - spin_unlock(&fou_lock); + list_add(&fou->list, &fn->fou_list); + mutex_unlock(&fn->fou_lock); return 0; } @@ -410,14 +416,10 @@ static void fou_release(struct fou *fou) struct socket *sock = fou->sock; struct sock *sk = sock->sk; - udp_del_offload(&fou->udp_offloads); - + if (sk->sk_family == AF_INET) + udp_del_offload(&fou->udp_offloads); list_del(&fou->list); - - /* Remove hooks into tunnel socket */ - sk->sk_user_data = NULL; - - sock_release(sock); + udp_tunnel_sock_release(sock); kfree(fou); } @@ -447,10 +449,10 @@ static int gue_encap_init(struct sock *sk, struct fou *fou, struct fou_cfg *cfg) static int fou_create(struct net *net, struct fou_cfg *cfg, struct socket **sockp) { - struct fou *fou = NULL; - int err; struct socket *sock = NULL; + struct fou *fou = NULL; struct sock *sk; + int err; /* Open UDP socket */ err = udp_sock_create(net, &cfg->udp_config, &sock); @@ -486,6 +488,8 @@ static int fou_create(struct net *net, struct fou_cfg *cfg, goto error; } + fou->type = cfg->type; + udp_sk(sk)->encap_type = 1; udp_encap_enable(); @@ -502,7 +506,7 @@ static int fou_create(struct net *net, struct fou_cfg *cfg, goto error; } - err = fou_add_to_port_list(fou); + err = fou_add_to_port_list(net, fou); if (err) goto error; @@ -514,27 +518,27 @@ static int fou_create(struct net *net, struct fou_cfg *cfg, error: kfree(fou); if (sock) - sock_release(sock); + udp_tunnel_sock_release(sock); return err; } static int fou_destroy(struct net *net, struct fou_cfg *cfg) { - struct fou *fou; - u16 port = cfg->udp_config.local_udp_port; + struct fou_net *fn = net_generic(net, fou_net_id); + __be16 port = cfg->udp_config.local_udp_port; int err = -EINVAL; + struct fou *fou; - spin_lock(&fou_lock); - list_for_each_entry(fou, &fou_list, list) { + mutex_lock(&fn->fou_lock); + list_for_each_entry(fou, &fn->fou_list, list) { if (fou->port == port) { - udp_del_offload(&fou->udp_offloads); fou_release(fou); err = 0; break; } } - spin_unlock(&fou_lock); + mutex_unlock(&fn->fou_lock); return err; } @@ -573,7 +577,7 @@ static int parse_nl_config(struct genl_info *info, } if (info->attrs[FOU_ATTR_PORT]) { - u16 port = nla_get_u16(info->attrs[FOU_ATTR_PORT]); + __be16 port = nla_get_be16(info->attrs[FOU_ATTR_PORT]); cfg->udp_config.local_udp_port = port; } @@ -592,6 +596,7 @@ static int parse_nl_config(struct genl_info *info, static int fou_nl_cmd_add_port(struct sk_buff *skb, struct genl_info *info) { + struct net *net = genl_info_net(info); struct fou_cfg cfg; int err; @@ -599,16 +604,119 @@ static int fou_nl_cmd_add_port(struct sk_buff *skb, struct genl_info *info) if (err) return err; - return fou_create(&init_net, &cfg, NULL); + return fou_create(net, &cfg, NULL); } static int fou_nl_cmd_rm_port(struct sk_buff *skb, struct genl_info *info) { + struct net *net = genl_info_net(info); struct fou_cfg cfg; + int err; - parse_nl_config(info, &cfg); + err = parse_nl_config(info, &cfg); + if (err) + return err; - return fou_destroy(&init_net, &cfg); + return fou_destroy(net, &cfg); +} + +static int fou_fill_info(struct fou *fou, struct sk_buff *msg) +{ + if (nla_put_u8(msg, FOU_ATTR_AF, fou->sock->sk->sk_family) || + nla_put_be16(msg, FOU_ATTR_PORT, fou->port) || + nla_put_u8(msg, FOU_ATTR_IPPROTO, fou->protocol) || + nla_put_u8(msg, FOU_ATTR_TYPE, fou->type)) + return -1; + + if (fou->flags & FOU_F_REMCSUM_NOPARTIAL) + if (nla_put_flag(msg, FOU_ATTR_REMCSUM_NOPARTIAL)) + return -1; + return 0; +} + +static int fou_dump_info(struct fou *fou, u32 portid, u32 seq, + u32 flags, struct sk_buff *skb, u8 cmd) +{ + void *hdr; + + hdr = genlmsg_put(skb, portid, seq, &fou_nl_family, flags, cmd); + if (!hdr) + return -ENOMEM; + + if (fou_fill_info(fou, skb) < 0) + goto nla_put_failure; + + genlmsg_end(skb, hdr); + return 0; + +nla_put_failure: + genlmsg_cancel(skb, hdr); + return -EMSGSIZE; +} + +static int fou_nl_cmd_get_port(struct sk_buff *skb, struct genl_info *info) +{ + struct net *net = genl_info_net(info); + struct fou_net *fn = net_generic(net, fou_net_id); + struct sk_buff *msg; + struct fou_cfg cfg; + struct fou *fout; + __be16 port; + int ret; + + ret = parse_nl_config(info, &cfg); + if (ret) + return ret; + port = cfg.udp_config.local_udp_port; + if (port == 0) + return -EINVAL; + + msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); + if (!msg) + return -ENOMEM; + + ret = -ESRCH; + mutex_lock(&fn->fou_lock); + list_for_each_entry(fout, &fn->fou_list, list) { + if (port == fout->port) { + ret = fou_dump_info(fout, info->snd_portid, + info->snd_seq, 0, msg, + info->genlhdr->cmd); + break; + } + } + mutex_unlock(&fn->fou_lock); + if (ret < 0) + goto out_free; + + return genlmsg_reply(msg, info); + +out_free: + nlmsg_free(msg); + return ret; +} + +static int fou_nl_dump(struct sk_buff *skb, struct netlink_callback *cb) +{ + struct net *net = sock_net(skb->sk); + struct fou_net *fn = net_generic(net, fou_net_id); + struct fou *fout; + int idx = 0, ret; + + mutex_lock(&fn->fou_lock); + list_for_each_entry(fout, &fn->fou_list, list) { + if (idx++ < cb->args[0]) + continue; + ret = fou_dump_info(fout, NETLINK_CB(cb->skb).portid, + cb->nlh->nlmsg_seq, NLM_F_MULTI, + skb, FOU_CMD_GET); + if (ret) + break; + } + mutex_unlock(&fn->fou_lock); + + cb->args[0] = idx; + return skb->len; } static const struct genl_ops fou_nl_ops[] = { @@ -624,6 +732,12 @@ static const struct genl_ops fou_nl_ops[] = { .policy = fou_nl_policy, .flags = GENL_ADMIN_PERM, }, + { + .cmd = FOU_CMD_GET, + .doit = fou_nl_cmd_get_port, + .dumpit = fou_nl_dump, + .policy = fou_nl_policy, + }, }; size_t fou_encap_hlen(struct ip_tunnel_encap *e) @@ -771,12 +885,12 @@ EXPORT_SYMBOL(gue_build_header); #ifdef CONFIG_NET_FOU_IP_TUNNELS -static const struct ip_tunnel_encap_ops __read_mostly fou_iptun_ops = { +static const struct ip_tunnel_encap_ops fou_iptun_ops = { .encap_hlen = fou_encap_hlen, .build_header = fou_build_header, }; -static const struct ip_tunnel_encap_ops __read_mostly gue_iptun_ops = { +static const struct ip_tunnel_encap_ops gue_iptun_ops = { .encap_hlen = gue_encap_hlen, .build_header = gue_build_header, }; @@ -820,38 +934,63 @@ static void ip_tunnel_encap_del_fou_ops(void) #endif +static __net_init int fou_init_net(struct net *net) +{ + struct fou_net *fn = net_generic(net, fou_net_id); + + INIT_LIST_HEAD(&fn->fou_list); + mutex_init(&fn->fou_lock); + return 0; +} + +static __net_exit void fou_exit_net(struct net *net) +{ + struct fou_net *fn = net_generic(net, fou_net_id); + struct fou *fou, *next; + + /* Close all the FOU sockets */ + mutex_lock(&fn->fou_lock); + list_for_each_entry_safe(fou, next, &fn->fou_list, list) + fou_release(fou); + mutex_unlock(&fn->fou_lock); +} + +static struct pernet_operations fou_net_ops = { + .init = fou_init_net, + .exit = fou_exit_net, + .id = &fou_net_id, + .size = sizeof(struct fou_net), +}; + static int __init fou_init(void) { int ret; + ret = register_pernet_device(&fou_net_ops); + if (ret) + goto exit; + ret = genl_register_family_with_ops(&fou_nl_family, fou_nl_ops); - if (ret < 0) - goto exit; + goto unregister; ret = ip_tunnel_encap_add_fou_ops(); - if (ret < 0) - genl_unregister_family(&fou_nl_family); + if (ret == 0) + return 0; + genl_unregister_family(&fou_nl_family); +unregister: + unregister_pernet_device(&fou_net_ops); exit: return ret; } static void __exit fou_fini(void) { - struct fou *fou, *next; - ip_tunnel_encap_del_fou_ops(); - genl_unregister_family(&fou_nl_family); - - /* Close all the FOU sockets */ - - spin_lock(&fou_lock); - list_for_each_entry_safe(fou, next, &fou_list, list) - fou_release(fou); - spin_unlock(&fou_lock); + unregister_pernet_device(&fou_net_ops); } module_init(fou_init); diff --git a/net/ipv4/geneve.c b/net/ipv4/geneve.c index 5a4828ba05ad..8986e63f3bda 100644 --- a/net/ipv4/geneve.c +++ b/net/ipv4/geneve.c @@ -113,10 +113,6 @@ int geneve_xmit_skb(struct geneve_sock *gs, struct rtable *rt, int min_headroom; int err; - skb = udp_tunnel_handle_offloads(skb, csum); - if (IS_ERR(skb)) - return PTR_ERR(skb); - min_headroom = LL_RESERVED_SPACE(rt->dst.dev) + rt->dst.header_len + GENEVE_BASE_HLEN + opt_len + sizeof(struct iphdr) + (skb_vlan_tag_present(skb) ? VLAN_HLEN : 0); @@ -131,12 +127,16 @@ int geneve_xmit_skb(struct geneve_sock *gs, struct rtable *rt, if (unlikely(!skb)) return -ENOMEM; + skb = udp_tunnel_handle_offloads(skb, csum); + if (IS_ERR(skb)) + return PTR_ERR(skb); + gnvh = (struct genevehdr *)__skb_push(skb, sizeof(*gnvh) + opt_len); geneve_build_header(gnvh, tun_flags, vni, opt_len, opt); skb_set_inner_protocol(skb, htons(ETH_P_TEB)); - return udp_tunnel_xmit_skb(rt, skb, src, dst, + return udp_tunnel_xmit_skb(rt, gs->sock->sk, skb, src, dst, tos, ttl, df, src_port, dst_port, xnet, !csum); } @@ -196,7 +196,7 @@ static struct sk_buff **geneve_gro_receive(struct sk_buff **head, rcu_read_lock(); ptype = gro_find_receive_by_type(type); - if (ptype == NULL) { + if (!ptype) { flush = 1; goto out_unlock; } @@ -230,7 +230,7 @@ static int geneve_gro_complete(struct sk_buff *skb, int nhoff, rcu_read_lock(); ptype = gro_find_complete_by_type(type); - if (ptype != NULL) + if (ptype) err = ptype->callbacks.gro_complete(skb, nhoff + gh_len); rcu_read_unlock(); diff --git a/net/ipv4/gre_offload.c b/net/ipv4/gre_offload.c index 51973ddc05a6..5aa46d4b44ef 100644 --- a/net/ipv4/gre_offload.c +++ b/net/ipv4/gre_offload.c @@ -149,7 +149,7 @@ static struct sk_buff **gre_gro_receive(struct sk_buff **head, rcu_read_lock(); ptype = gro_find_receive_by_type(type); - if (ptype == NULL) + if (!ptype) goto out_unlock; grehlen = GRE_HEADER_SECTION; @@ -243,7 +243,7 @@ static int gre_gro_complete(struct sk_buff *skb, int nhoff) rcu_read_lock(); ptype = gro_find_complete_by_type(type); - if (ptype != NULL) + if (ptype) err = ptype->callbacks.gro_complete(skb, nhoff + grehlen); rcu_read_unlock(); diff --git a/net/ipv4/icmp.c b/net/ipv4/icmp.c index 5e564014a0b7..f5203fba6236 100644 --- a/net/ipv4/icmp.c +++ b/net/ipv4/icmp.c @@ -399,7 +399,7 @@ static void icmp_reply(struct icmp_bxm *icmp_param, struct sk_buff *skb) return; sk = icmp_xmit_lock(net); - if (sk == NULL) + if (!sk) return; inet = inet_sk(sk); @@ -609,7 +609,7 @@ void icmp_send(struct sk_buff *skb_in, int type, int code, __be32 info) skb_in->data, sizeof(_inner_type), &_inner_type); - if (itp == NULL) + if (!itp) goto out; /* @@ -627,7 +627,7 @@ void icmp_send(struct sk_buff *skb_in, int type, int code, __be32 info) return; sk = icmp_xmit_lock(net); - if (sk == NULL) + if (!sk) goto out_free; /* diff --git a/net/ipv4/igmp.c b/net/ipv4/igmp.c index 666cf364df86..a3a697f5ffba 100644 --- a/net/ipv4/igmp.c +++ b/net/ipv4/igmp.c @@ -97,6 +97,7 @@ #include <net/route.h> #include <net/sock.h> #include <net/checksum.h> +#include <net/inet_common.h> #include <linux/netfilter_ipv4.h> #ifdef CONFIG_IP_MROUTE #include <linux/mroute.h> @@ -369,7 +370,7 @@ static struct sk_buff *igmpv3_newpack(struct net_device *dev, unsigned int mtu) pip->saddr = fl4.saddr; pip->protocol = IPPROTO_IGMP; pip->tot_len = 0; /* filled in later */ - ip_select_ident(skb, NULL); + ip_select_ident(net, skb, NULL); ((u8 *)&pip[1])[0] = IPOPT_RA; ((u8 *)&pip[1])[1] = 4; ((u8 *)&pip[1])[2] = 0; @@ -691,7 +692,7 @@ static int igmp_send_report(struct in_device *in_dev, struct ip_mc_list *pmc, hlen = LL_RESERVED_SPACE(dev); tlen = dev->needed_tailroom; skb = alloc_skb(IGMP_SIZE + hlen + tlen, GFP_ATOMIC); - if (skb == NULL) { + if (!skb) { ip_rt_put(rt); return -1; } @@ -713,7 +714,7 @@ static int igmp_send_report(struct in_device *in_dev, struct ip_mc_list *pmc, iph->daddr = dst; iph->saddr = fl4.saddr; iph->protocol = IPPROTO_IGMP; - ip_select_ident(skb, NULL); + ip_select_ident(net, skb, NULL); ((u8 *)&iph[1])[0] = IPOPT_RA; ((u8 *)&iph[1])[1] = 4; ((u8 *)&iph[1])[2] = 0; @@ -980,7 +981,7 @@ int igmp_rcv(struct sk_buff *skb) int len = skb->len; bool dropped = true; - if (in_dev == NULL) + if (!in_dev) goto drop; if (!pskb_may_pull(skb, sizeof(struct igmphdr))) @@ -1849,30 +1850,28 @@ static void ip_mc_clear_src(struct ip_mc_list *pmc) pmc->sfcount[MCAST_EXCLUDE] = 1; } - -/* - * Join a multicast group +/* Join a multicast group */ -int ip_mc_join_group(struct sock *sk , struct ip_mreqn *imr) + +int ip_mc_join_group(struct sock *sk, struct ip_mreqn *imr) { - int err; __be32 addr = imr->imr_multiaddr.s_addr; - struct ip_mc_socklist *iml = NULL, *i; + struct ip_mc_socklist *iml, *i; struct in_device *in_dev; struct inet_sock *inet = inet_sk(sk); struct net *net = sock_net(sk); int ifindex; int count = 0; + int err; + + ASSERT_RTNL(); if (!ipv4_is_multicast(addr)) return -EINVAL; - rtnl_lock(); - in_dev = ip_mc_find_dev(net, imr); if (!in_dev) { - iml = NULL; err = -ENODEV; goto done; } @@ -1889,7 +1888,7 @@ int ip_mc_join_group(struct sock *sk , struct ip_mreqn *imr) if (count >= sysctl_igmp_max_memberships) goto done; iml = sock_kmalloc(sk, sizeof(*iml), GFP_KERNEL); - if (iml == NULL) + if (!iml) goto done; memcpy(&iml->multi, imr, sizeof(*imr)); @@ -1900,7 +1899,6 @@ int ip_mc_join_group(struct sock *sk , struct ip_mreqn *imr) ip_mc_inc_group(in_dev, addr); err = 0; done: - rtnl_unlock(); return err; } EXPORT_SYMBOL(ip_mc_join_group); @@ -1911,7 +1909,7 @@ static int ip_mc_leave_src(struct sock *sk, struct ip_mc_socklist *iml, struct ip_sf_socklist *psf = rtnl_dereference(iml->sflist); int err; - if (psf == NULL) { + if (!psf) { /* any-source empty exclude case */ return ip_mc_del_src(in_dev, &iml->multi.imr_multiaddr.s_addr, iml->sfmode, 0, NULL, 0); @@ -1925,10 +1923,6 @@ static int ip_mc_leave_src(struct sock *sk, struct ip_mc_socklist *iml, return err; } -/* - * Ask a socket to leave a group. - */ - int ip_mc_leave_group(struct sock *sk, struct ip_mreqn *imr) { struct inet_sock *inet = inet_sk(sk); @@ -1940,7 +1934,8 @@ int ip_mc_leave_group(struct sock *sk, struct ip_mreqn *imr) u32 ifindex; int ret = -EADDRNOTAVAIL; - rtnl_lock(); + ASSERT_RTNL(); + in_dev = ip_mc_find_dev(net, imr); if (!in_dev) { ret = -ENODEV; @@ -1964,14 +1959,13 @@ int ip_mc_leave_group(struct sock *sk, struct ip_mreqn *imr) *imlp = iml->next_rcu; ip_mc_dec_group(in_dev, group); - rtnl_unlock(); + /* decrease mem now to avoid the memleak warning */ atomic_sub(sizeof(*iml), &sk->sk_omem_alloc); kfree_rcu(iml, rcu); return 0; } out: - rtnl_unlock(); return ret; } EXPORT_SYMBOL(ip_mc_leave_group); @@ -1993,7 +1987,7 @@ int ip_mc_source(int add, int omode, struct sock *sk, struct if (!ipv4_is_multicast(addr)) return -EINVAL; - rtnl_lock(); + ASSERT_RTNL(); imr.imr_multiaddr.s_addr = mreqs->imr_multiaddr; imr.imr_address.s_addr = mreqs->imr_interface; @@ -2107,9 +2101,8 @@ int ip_mc_source(int add, int omode, struct sock *sk, struct ip_mc_add_src(in_dev, &mreqs->imr_multiaddr, omode, 1, &mreqs->imr_sourceaddr, 1); done: - rtnl_unlock(); if (leavegroup) - return ip_mc_leave_group(sk, &imr); + err = ip_mc_leave_group(sk, &imr); return err; } @@ -2131,7 +2124,7 @@ int ip_mc_msfilter(struct sock *sk, struct ip_msfilter *msf, int ifindex) msf->imsf_fmode != MCAST_EXCLUDE) return -EINVAL; - rtnl_lock(); + ASSERT_RTNL(); imr.imr_multiaddr.s_addr = msf->imsf_multiaddr; imr.imr_address.s_addr = msf->imsf_interface; @@ -2193,7 +2186,6 @@ int ip_mc_msfilter(struct sock *sk, struct ip_msfilter *msf, int ifindex) pmc->sfmode = msf->imsf_fmode; err = 0; done: - rtnl_unlock(); if (leavegroup) err = ip_mc_leave_group(sk, &imr); return err; @@ -2368,7 +2360,7 @@ void ip_mc_drop_socket(struct sock *sk) struct ip_mc_socklist *iml; struct net *net = sock_net(sk); - if (inet->mc_list == NULL) + if (!inet->mc_list) return; rtnl_lock(); @@ -2378,7 +2370,7 @@ void ip_mc_drop_socket(struct sock *sk) inet->mc_list = iml->next_rcu; in_dev = inetdev_by_index(net, iml->multi.imr_ifindex); (void) ip_mc_leave_src(sk, iml, in_dev); - if (in_dev != NULL) + if (in_dev) ip_mc_dec_group(in_dev, iml->multi.imr_multiaddr.s_addr); /* decrease mem now to avoid the memleak warning */ atomic_sub(sizeof(*iml), &sk->sk_omem_alloc); @@ -2595,13 +2587,13 @@ static inline struct ip_sf_list *igmp_mcf_get_first(struct seq_file *seq) for_each_netdev_rcu(net, state->dev) { struct in_device *idev; idev = __in_dev_get_rcu(state->dev); - if (unlikely(idev == NULL)) + if (unlikely(!idev)) continue; im = rcu_dereference(idev->mc_list); - if (likely(im != NULL)) { + if (likely(im)) { spin_lock_bh(&im->lock); psf = im->sources; - if (likely(psf != NULL)) { + if (likely(psf)) { state->im = im; state->idev = idev; break; @@ -2671,7 +2663,7 @@ static void igmp_mcf_seq_stop(struct seq_file *seq, void *v) __releases(rcu) { struct igmp_mcf_iter_state *state = igmp_mcf_seq_private(seq); - if (likely(state->im != NULL)) { + if (likely(state->im)) { spin_unlock_bh(&state->im->lock); state->im = NULL; } @@ -2724,6 +2716,7 @@ static const struct file_operations igmp_mcf_seq_fops = { static int __net_init igmp_net_init(struct net *net) { struct proc_dir_entry *pde; + int err; pde = proc_create("igmp", S_IRUGO, net->proc_net, &igmp_mc_seq_fops); if (!pde) @@ -2732,8 +2725,18 @@ static int __net_init igmp_net_init(struct net *net) &igmp_mcf_seq_fops); if (!pde) goto out_mcfilter; + err = inet_ctl_sock_create(&net->ipv4.mc_autojoin_sk, AF_INET, + SOCK_DGRAM, 0, net); + if (err < 0) { + pr_err("Failed to initialize the IGMP autojoin socket (err %d)\n", + err); + goto out_sock; + } + return 0; +out_sock: + remove_proc_entry("mcfilter", net->proc_net); out_mcfilter: remove_proc_entry("igmp", net->proc_net); out_igmp: @@ -2744,6 +2747,7 @@ static void __net_exit igmp_net_exit(struct net *net) { remove_proc_entry("mcfilter", net->proc_net); remove_proc_entry("igmp", net->proc_net); + inet_ctl_sock_destroy(net->ipv4.mc_autojoin_sk); } static struct pernet_operations igmp_net_ops = { diff --git a/net/ipv4/inet_connection_sock.c b/net/ipv4/inet_connection_sock.c index 3e44b9b0b78e..8976ca423a07 100644 --- a/net/ipv4/inet_connection_sock.c +++ b/net/ipv4/inet_connection_sock.c @@ -23,6 +23,7 @@ #include <net/route.h> #include <net/tcp_states.h> #include <net/xfrm.h> +#include <net/tcp.h> #ifdef INET_CSK_DEBUG const char inet_csk_timer_bug_msg[] = "inet_csk BUG: unknown timer value\n"; @@ -294,8 +295,8 @@ struct sock *inet_csk_accept(struct sock *sk, int flags, int *err) { struct inet_connection_sock *icsk = inet_csk(sk); struct request_sock_queue *queue = &icsk->icsk_accept_queue; - struct sock *newsk; struct request_sock *req; + struct sock *newsk; int error; lock_sock(sk); @@ -324,9 +325,11 @@ struct sock *inet_csk_accept(struct sock *sk, int flags, int *err) newsk = req->sk; sk_acceptq_removed(sk); - if (sk->sk_protocol == IPPROTO_TCP && queue->fastopenq != NULL) { + if (sk->sk_protocol == IPPROTO_TCP && + tcp_rsk(req)->tfo_listener && + queue->fastopenq) { spin_lock_bh(&queue->fastopenq->lock); - if (tcp_rsk(req)->listener) { + if (tcp_rsk(req)->tfo_listener) { /* We are still waiting for the final ACK from 3WHS * so can't free req now. Instead, we set req->sk to * NULL to signify that the child socket is taken @@ -341,7 +344,7 @@ struct sock *inet_csk_accept(struct sock *sk, int flags, int *err) out: release_sock(sk); if (req) - __reqsk_free(req); + reqsk_put(req); return newsk; out_err: newsk = NULL; @@ -400,18 +403,17 @@ struct dst_entry *inet_csk_route_req(struct sock *sk, struct flowi4 *fl4, const struct request_sock *req) { - struct rtable *rt; const struct inet_request_sock *ireq = inet_rsk(req); - struct ip_options_rcu *opt = inet_rsk(req)->opt; - struct net *net = sock_net(sk); - int flags = inet_sk_flowi_flags(sk); + struct net *net = read_pnet(&ireq->ireq_net); + struct ip_options_rcu *opt = ireq->opt; + struct rtable *rt; - flowi4_init_output(fl4, sk->sk_bound_dev_if, ireq->ir_mark, + flowi4_init_output(fl4, ireq->ir_iif, ireq->ir_mark, RT_CONN_FLAGS(sk), RT_SCOPE_UNIVERSE, - sk->sk_protocol, - flags, + sk->sk_protocol, inet_sk_flowi_flags(sk), (opt && opt->opt.srr) ? opt->opt.faddr : ireq->ir_rmt_addr, - ireq->ir_loc_addr, ireq->ir_rmt_port, inet_sk(sk)->inet_sport); + ireq->ir_loc_addr, ireq->ir_rmt_port, + htons(ireq->ir_num)); security_req_classify_flow(req, flowi4_to_flowi(fl4)); rt = ip_route_output_flow(net, fl4, sk); if (IS_ERR(rt)) @@ -433,9 +435,9 @@ struct dst_entry *inet_csk_route_child_sock(struct sock *sk, const struct request_sock *req) { const struct inet_request_sock *ireq = inet_rsk(req); + struct net *net = read_pnet(&ireq->ireq_net); struct inet_sock *newinet = inet_sk(newsk); struct ip_options_rcu *opt; - struct net *net = sock_net(sk); struct flowi4 *fl4; struct rtable *rt; @@ -443,11 +445,12 @@ struct dst_entry *inet_csk_route_child_sock(struct sock *sk, rcu_read_lock(); opt = rcu_dereference(newinet->inet_opt); - flowi4_init_output(fl4, sk->sk_bound_dev_if, inet_rsk(req)->ir_mark, + flowi4_init_output(fl4, ireq->ir_iif, ireq->ir_mark, RT_CONN_FLAGS(sk), RT_SCOPE_UNIVERSE, sk->sk_protocol, inet_sk_flowi_flags(sk), (opt && opt->opt.srr) ? opt->opt.faddr : ireq->ir_rmt_addr, - ireq->ir_loc_addr, ireq->ir_rmt_port, inet_sk(sk)->inet_sport); + ireq->ir_loc_addr, ireq->ir_rmt_port, + htons(ireq->ir_num)); security_req_classify_flow(req, flowi4_to_flowi(fl4)); rt = ip_route_output_flow(net, fl4, sk); if (IS_ERR(rt)) @@ -475,33 +478,37 @@ static inline u32 inet_synq_hash(const __be32 raddr, const __be16 rport, #if IS_ENABLED(CONFIG_IPV6) #define AF_INET_FAMILY(fam) ((fam) == AF_INET) #else -#define AF_INET_FAMILY(fam) 1 +#define AF_INET_FAMILY(fam) true #endif -struct request_sock *inet_csk_search_req(const struct sock *sk, - struct request_sock ***prevp, - const __be16 rport, const __be32 raddr, +/* Note: this is temporary : + * req sock will no longer be in listener hash table +*/ +struct request_sock *inet_csk_search_req(struct sock *sk, + const __be16 rport, + const __be32 raddr, const __be32 laddr) { - const struct inet_connection_sock *icsk = inet_csk(sk); + struct inet_connection_sock *icsk = inet_csk(sk); struct listen_sock *lopt = icsk->icsk_accept_queue.listen_opt; - struct request_sock *req, **prev; + struct request_sock *req; + u32 hash = inet_synq_hash(raddr, rport, lopt->hash_rnd, + lopt->nr_table_entries); - for (prev = &lopt->syn_table[inet_synq_hash(raddr, rport, lopt->hash_rnd, - lopt->nr_table_entries)]; - (req = *prev) != NULL; - prev = &req->dl_next) { + spin_lock(&icsk->icsk_accept_queue.syn_wait_lock); + for (req = lopt->syn_table[hash]; req != NULL; req = req->dl_next) { const struct inet_request_sock *ireq = inet_rsk(req); if (ireq->ir_rmt_port == rport && ireq->ir_rmt_addr == raddr && ireq->ir_loc_addr == laddr && AF_INET_FAMILY(req->rsk_ops->family)) { + atomic_inc(&req->rsk_refcnt); WARN_ON(req->sk); - *prevp = prev; break; } } + spin_unlock(&icsk->icsk_accept_queue.syn_wait_lock); return req; } @@ -557,23 +564,58 @@ int inet_rtx_syn_ack(struct sock *parent, struct request_sock *req) } EXPORT_SYMBOL(inet_rtx_syn_ack); -void inet_csk_reqsk_queue_prune(struct sock *parent, - const unsigned long interval, - const unsigned long timeout, - const unsigned long max_rto) +/* return true if req was found in the syn_table[] */ +static bool reqsk_queue_unlink(struct request_sock_queue *queue, + struct request_sock *req) +{ + struct listen_sock *lopt = queue->listen_opt; + struct request_sock **prev; + bool found = false; + + spin_lock(&queue->syn_wait_lock); + + for (prev = &lopt->syn_table[req->rsk_hash]; *prev != NULL; + prev = &(*prev)->dl_next) { + if (*prev == req) { + *prev = req->dl_next; + found = true; + break; + } + } + + spin_unlock(&queue->syn_wait_lock); + if (del_timer(&req->rsk_timer)) + reqsk_put(req); + return found; +} + +void inet_csk_reqsk_queue_drop(struct sock *sk, struct request_sock *req) { - struct inet_connection_sock *icsk = inet_csk(parent); + if (reqsk_queue_unlink(&inet_csk(sk)->icsk_accept_queue, req)) { + reqsk_queue_removed(&inet_csk(sk)->icsk_accept_queue, req); + reqsk_put(req); + } +} +EXPORT_SYMBOL(inet_csk_reqsk_queue_drop); + +static void reqsk_timer_handler(unsigned long data) +{ + struct request_sock *req = (struct request_sock *)data; + struct sock *sk_listener = req->rsk_listener; + struct inet_connection_sock *icsk = inet_csk(sk_listener); struct request_sock_queue *queue = &icsk->icsk_accept_queue; struct listen_sock *lopt = queue->listen_opt; - int max_retries = icsk->icsk_syn_retries ? : sysctl_tcp_synack_retries; - int thresh = max_retries; - unsigned long now = jiffies; - struct request_sock **reqp, *req; - int i, budget; + int qlen, expire = 0, resend = 0; + int max_retries, thresh; + u8 defer_accept; - if (lopt == NULL || lopt->qlen == 0) + if (sk_listener->sk_state != TCP_LISTEN || !lopt) { + reqsk_put(req); return; + } + max_retries = icsk->icsk_syn_retries ? : sysctl_tcp_synack_retries; + thresh = max_retries; /* Normally all the openreqs are young and become mature * (i.e. converted to established socket) for first timeout. * If synack was not acknowledged for 1 second, it means @@ -591,67 +633,65 @@ void inet_csk_reqsk_queue_prune(struct sock *parent, * embrions; and abort old ones without pity, if old * ones are about to clog our table. */ - if (lopt->qlen>>(lopt->max_qlen_log-1)) { - int young = (lopt->qlen_young<<1); + qlen = listen_sock_qlen(lopt); + if (qlen >> (lopt->max_qlen_log - 1)) { + int young = listen_sock_young(lopt) << 1; while (thresh > 2) { - if (lopt->qlen < young) + if (qlen < young) break; thresh--; young <<= 1; } } + defer_accept = READ_ONCE(queue->rskq_defer_accept); + if (defer_accept) + max_retries = defer_accept; + syn_ack_recalc(req, thresh, max_retries, defer_accept, + &expire, &resend); + req->rsk_ops->syn_ack_timeout(req); + if (!expire && + (!resend || + !inet_rtx_syn_ack(sk_listener, req) || + inet_rsk(req)->acked)) { + unsigned long timeo; + + if (req->num_timeout++ == 0) + atomic_inc(&lopt->young_dec); + timeo = min(TCP_TIMEOUT_INIT << req->num_timeout, TCP_RTO_MAX); + mod_timer_pinned(&req->rsk_timer, jiffies + timeo); + return; + } + inet_csk_reqsk_queue_drop(sk_listener, req); + reqsk_put(req); +} - if (queue->rskq_defer_accept) - max_retries = queue->rskq_defer_accept; - - budget = 2 * (lopt->nr_table_entries / (timeout / interval)); - i = lopt->clock_hand; - - do { - reqp=&lopt->syn_table[i]; - while ((req = *reqp) != NULL) { - if (time_after_eq(now, req->expires)) { - int expire = 0, resend = 0; - - syn_ack_recalc(req, thresh, max_retries, - queue->rskq_defer_accept, - &expire, &resend); - req->rsk_ops->syn_ack_timeout(parent, req); - if (!expire && - (!resend || - !inet_rtx_syn_ack(parent, req) || - inet_rsk(req)->acked)) { - unsigned long timeo; - - if (req->num_timeout++ == 0) - lopt->qlen_young--; - timeo = min(timeout << req->num_timeout, - max_rto); - req->expires = now + timeo; - reqp = &req->dl_next; - continue; - } - - /* Drop this request */ - inet_csk_reqsk_queue_unlink(parent, req, reqp); - reqsk_queue_removed(queue, req); - reqsk_free(req); - continue; - } - reqp = &req->dl_next; - } +void reqsk_queue_hash_req(struct request_sock_queue *queue, + u32 hash, struct request_sock *req, + unsigned long timeout) +{ + struct listen_sock *lopt = queue->listen_opt; - i = (i + 1) & (lopt->nr_table_entries - 1); + req->num_retrans = 0; + req->num_timeout = 0; + req->sk = NULL; - } while (--budget > 0); + /* before letting lookups find us, make sure all req fields + * are committed to memory and refcnt initialized. + */ + smp_wmb(); + atomic_set(&req->rsk_refcnt, 2); + setup_timer(&req->rsk_timer, reqsk_timer_handler, (unsigned long)req); + req->rsk_hash = hash; - lopt->clock_hand = i; + spin_lock(&queue->syn_wait_lock); + req->dl_next = lopt->syn_table[hash]; + lopt->syn_table[hash] = req; + spin_unlock(&queue->syn_wait_lock); - if (lopt->qlen) - inet_csk_reset_keepalive_timer(parent, interval); + mod_timer_pinned(&req->rsk_timer, jiffies + timeout); } -EXPORT_SYMBOL_GPL(inet_csk_reqsk_queue_prune); +EXPORT_SYMBOL(reqsk_queue_hash_req); /** * inet_csk_clone_lock - clone an inet socket, and lock its clone @@ -667,7 +707,7 @@ struct sock *inet_csk_clone_lock(const struct sock *sk, { struct sock *newsk = sk_clone_lock(sk, priority); - if (newsk != NULL) { + if (newsk) { struct inet_connection_sock *newicsk = inet_csk(newsk); newsk->sk_state = TCP_SYN_RECV; @@ -679,6 +719,8 @@ struct sock *inet_csk_clone_lock(const struct sock *sk, newsk->sk_write_space = sk_stream_write_space; newsk->sk_mark = inet_rsk(req)->ir_mark; + atomic64_set(&newsk->sk_cookie, + atomic64_read(&inet_rsk(req)->ir_cookie)); newicsk->icsk_retransmits = 0; newicsk->icsk_backoff = 0; @@ -785,8 +827,6 @@ void inet_csk_listen_stop(struct sock *sk) struct request_sock *acc_req; struct request_sock *req; - inet_csk_delete_keepalive_timer(sk); - /* make all the listen_opt local to us */ acc_req = reqsk_queue_yank_acceptq(queue); @@ -816,9 +856,9 @@ void inet_csk_listen_stop(struct sock *sk) percpu_counter_inc(sk->sk_prot->orphan_count); - if (sk->sk_protocol == IPPROTO_TCP && tcp_rsk(req)->listener) { + if (sk->sk_protocol == IPPROTO_TCP && tcp_rsk(req)->tfo_listener) { BUG_ON(tcp_sk(child)->fastopen_rsk != req); - BUG_ON(sk != tcp_rsk(req)->listener); + BUG_ON(sk != req->rsk_listener); /* Paranoid, to prevent race condition if * an inbound pkt destined for child is @@ -827,7 +867,6 @@ void inet_csk_listen_stop(struct sock *sk) * tcp_v4_destroy_sock(). */ tcp_sk(child)->fastopen_rsk = NULL; - sock_put(sk); } inet_csk_destroy_sock(child); @@ -836,9 +875,9 @@ void inet_csk_listen_stop(struct sock *sk) sock_put(child); sk_acceptq_removed(sk); - __reqsk_free(req); + reqsk_put(req); } - if (queue->fastopenq != NULL) { + if (queue->fastopenq) { /* Free all the reqs queued in rskq_rst_head. */ spin_lock_bh(&queue->fastopenq->lock); acc_req = queue->fastopenq->rskq_rst_head; @@ -846,7 +885,7 @@ void inet_csk_listen_stop(struct sock *sk) spin_unlock_bh(&queue->fastopenq->lock); while ((req = acc_req) != NULL) { acc_req = req->dl_next; - __reqsk_free(req); + reqsk_put(req); } } WARN_ON(sk->sk_ack_backlog); @@ -870,7 +909,7 @@ int inet_csk_compat_getsockopt(struct sock *sk, int level, int optname, { const struct inet_connection_sock *icsk = inet_csk(sk); - if (icsk->icsk_af_ops->compat_getsockopt != NULL) + if (icsk->icsk_af_ops->compat_getsockopt) return icsk->icsk_af_ops->compat_getsockopt(sk, level, optname, optval, optlen); return icsk->icsk_af_ops->getsockopt(sk, level, optname, @@ -883,7 +922,7 @@ int inet_csk_compat_setsockopt(struct sock *sk, int level, int optname, { const struct inet_connection_sock *icsk = inet_csk(sk); - if (icsk->icsk_af_ops->compat_setsockopt != NULL) + if (icsk->icsk_af_ops->compat_setsockopt) return icsk->icsk_af_ops->compat_setsockopt(sk, level, optname, optval, optlen); return icsk->icsk_af_ops->setsockopt(sk, level, optname, diff --git a/net/ipv4/inet_diag.c b/net/ipv4/inet_diag.c index 592aff37366b..bb77ebdae3b3 100644 --- a/net/ipv4/inet_diag.c +++ b/net/ipv4/inet_diag.c @@ -38,16 +38,12 @@ static const struct inet_diag_handler **inet_diag_table; struct inet_diag_entry { - __be32 *saddr; - __be32 *daddr; + const __be32 *saddr; + const __be32 *daddr; u16 sport; u16 dport; u16 family; u16 userlocks; -#if IS_ENABLED(CONFIG_IPV6) - struct in6_addr saddr_storage; /* for IPv4-mapped-IPv6 addresses */ - struct in6_addr daddr_storage; /* for IPv4-mapped-IPv6 addresses */ -#endif }; static DEFINE_MUTEX(inet_diag_table_mutex); @@ -65,12 +61,35 @@ static const struct inet_diag_handler *inet_diag_lock_handler(int proto) return inet_diag_table[proto]; } -static inline void inet_diag_unlock_handler( - const struct inet_diag_handler *handler) +static void inet_diag_unlock_handler(const struct inet_diag_handler *handler) { mutex_unlock(&inet_diag_table_mutex); } +static void inet_diag_msg_common_fill(struct inet_diag_msg *r, struct sock *sk) +{ + r->idiag_family = sk->sk_family; + + r->id.idiag_sport = htons(sk->sk_num); + r->id.idiag_dport = sk->sk_dport; + r->id.idiag_if = sk->sk_bound_dev_if; + sock_diag_save_cookie(sk, r->id.idiag_cookie); + +#if IS_ENABLED(CONFIG_IPV6) + if (sk->sk_family == AF_INET6) { + *(struct in6_addr *)r->id.idiag_src = sk->sk_v6_rcv_saddr; + *(struct in6_addr *)r->id.idiag_dst = sk->sk_v6_daddr; + } else +#endif + { + memset(&r->id.idiag_src, 0, sizeof(r->id.idiag_src)); + memset(&r->id.idiag_dst, 0, sizeof(r->id.idiag_dst)); + + r->id.idiag_src[0] = sk->sk_rcv_saddr; + r->id.idiag_dst[0] = sk->sk_daddr; + } +} + static size_t inet_sk_attr_size(void) { return nla_total_size(sizeof(struct tcp_info)) @@ -86,21 +105,22 @@ static size_t inet_sk_attr_size(void) } int inet_sk_diag_fill(struct sock *sk, struct inet_connection_sock *icsk, - struct sk_buff *skb, struct inet_diag_req_v2 *req, - struct user_namespace *user_ns, - u32 portid, u32 seq, u16 nlmsg_flags, - const struct nlmsghdr *unlh) + struct sk_buff *skb, const struct inet_diag_req_v2 *req, + struct user_namespace *user_ns, + u32 portid, u32 seq, u16 nlmsg_flags, + const struct nlmsghdr *unlh) { const struct inet_sock *inet = inet_sk(sk); + const struct tcp_congestion_ops *ca_ops; + const struct inet_diag_handler *handler; + int ext = req->idiag_ext; struct inet_diag_msg *r; struct nlmsghdr *nlh; struct nlattr *attr; void *info = NULL; - const struct inet_diag_handler *handler; - int ext = req->idiag_ext; handler = inet_diag_table[req->sdiag_protocol]; - BUG_ON(handler == NULL); + BUG_ON(!handler); nlh = nlmsg_put(skb, portid, seq, unlh->nlmsg_type, sizeof(*r), nlmsg_flags); @@ -108,25 +128,13 @@ int inet_sk_diag_fill(struct sock *sk, struct inet_connection_sock *icsk, return -EMSGSIZE; r = nlmsg_data(nlh); - BUG_ON(sk->sk_state == TCP_TIME_WAIT); + BUG_ON(!sk_fullsock(sk)); - r->idiag_family = sk->sk_family; + inet_diag_msg_common_fill(r, sk); r->idiag_state = sk->sk_state; r->idiag_timer = 0; r->idiag_retrans = 0; - r->id.idiag_if = sk->sk_bound_dev_if; - sock_diag_save_cookie(sk, r->id.idiag_cookie); - - r->id.idiag_sport = inet->inet_sport; - r->id.idiag_dport = inet->inet_dport; - - memset(&r->id.idiag_src, 0, sizeof(r->id.idiag_src)); - memset(&r->id.idiag_dst, 0, sizeof(r->id.idiag_dst)); - - r->id.idiag_src[0] = inet->inet_rcv_saddr; - r->id.idiag_dst[0] = inet->inet_daddr; - if (nla_put_u8(skb, INET_DIAG_SHUTDOWN, sk->sk_shutdown)) goto errout; @@ -139,10 +147,6 @@ int inet_sk_diag_fill(struct sock *sk, struct inet_connection_sock *icsk, #if IS_ENABLED(CONFIG_IPV6) if (r->idiag_family == AF_INET6) { - - *(struct in6_addr *)r->id.idiag_src = sk->sk_v6_rcv_saddr; - *(struct in6_addr *)r->id.idiag_dst = sk->sk_v6_daddr; - if (ext & (1 << (INET_DIAG_TCLASS - 1))) if (nla_put_u8(skb, INET_DIAG_TCLASS, inet6_sk(sk)->tclass) < 0) @@ -169,7 +173,7 @@ int inet_sk_diag_fill(struct sock *sk, struct inet_connection_sock *icsk, if (sock_diag_put_meminfo(sk, skb, INET_DIAG_SKMEMINFO)) goto errout; - if (icsk == NULL) { + if (!icsk) { handler->idiag_get_info(sk, r, NULL); goto out; } @@ -205,16 +209,31 @@ int inet_sk_diag_fill(struct sock *sk, struct inet_connection_sock *icsk, info = nla_data(attr); } - if ((ext & (1 << (INET_DIAG_CONG - 1))) && icsk->icsk_ca_ops) - if (nla_put_string(skb, INET_DIAG_CONG, - icsk->icsk_ca_ops->name) < 0) + if (ext & (1 << (INET_DIAG_CONG - 1))) { + int err = 0; + + rcu_read_lock(); + ca_ops = READ_ONCE(icsk->icsk_ca_ops); + if (ca_ops) + err = nla_put_string(skb, INET_DIAG_CONG, ca_ops->name); + rcu_read_unlock(); + if (err < 0) goto errout; + } handler->idiag_get_info(sk, r, info); - if (sk->sk_state < TCP_TIME_WAIT && - icsk->icsk_ca_ops && icsk->icsk_ca_ops->get_info) - icsk->icsk_ca_ops->get_info(sk, ext, skb); + if (sk->sk_state < TCP_TIME_WAIT) { + int err = 0; + + rcu_read_lock(); + ca_ops = READ_ONCE(icsk->icsk_ca_ops); + if (ca_ops && ca_ops->get_info) + err = ca_ops->get_info(sk, ext, skb); + rcu_read_unlock(); + if (err < 0) + goto errout; + } out: nlmsg_end(skb, nlh); @@ -227,23 +246,25 @@ errout: EXPORT_SYMBOL_GPL(inet_sk_diag_fill); static int inet_csk_diag_fill(struct sock *sk, - struct sk_buff *skb, struct inet_diag_req_v2 *req, + struct sk_buff *skb, + const struct inet_diag_req_v2 *req, struct user_namespace *user_ns, u32 portid, u32 seq, u16 nlmsg_flags, const struct nlmsghdr *unlh) { - return inet_sk_diag_fill(sk, inet_csk(sk), - skb, req, user_ns, portid, seq, nlmsg_flags, unlh); + return inet_sk_diag_fill(sk, inet_csk(sk), skb, req, + user_ns, portid, seq, nlmsg_flags, unlh); } -static int inet_twsk_diag_fill(struct inet_timewait_sock *tw, - struct sk_buff *skb, struct inet_diag_req_v2 *req, +static int inet_twsk_diag_fill(struct sock *sk, + struct sk_buff *skb, u32 portid, u32 seq, u16 nlmsg_flags, const struct nlmsghdr *unlh) { - s32 tmo; + struct inet_timewait_sock *tw = inet_twsk(sk); struct inet_diag_msg *r; struct nlmsghdr *nlh; + long tmo; nlh = nlmsg_put(skb, portid, seq, unlh->nlmsg_type, sizeof(*r), nlmsg_flags); @@ -253,25 +274,13 @@ static int inet_twsk_diag_fill(struct inet_timewait_sock *tw, r = nlmsg_data(nlh); BUG_ON(tw->tw_state != TCP_TIME_WAIT); - tmo = tw->tw_ttd - inet_tw_time_stamp(); + tmo = tw->tw_timer.expires - jiffies; if (tmo < 0) tmo = 0; - r->idiag_family = tw->tw_family; + inet_diag_msg_common_fill(r, sk); r->idiag_retrans = 0; - r->id.idiag_if = tw->tw_bound_dev_if; - sock_diag_save_cookie(tw, r->id.idiag_cookie); - - r->id.idiag_sport = tw->tw_sport; - r->id.idiag_dport = tw->tw_dport; - - memset(&r->id.idiag_src, 0, sizeof(r->id.idiag_src)); - memset(&r->id.idiag_dst, 0, sizeof(r->id.idiag_dst)); - - r->id.idiag_src[0] = tw->tw_rcv_saddr; - r->id.idiag_dst[0] = tw->tw_daddr; - r->idiag_state = tw->tw_substate; r->idiag_timer = 3; r->idiag_expires = jiffies_to_msecs(tmo); @@ -279,61 +288,91 @@ static int inet_twsk_diag_fill(struct inet_timewait_sock *tw, r->idiag_wqueue = 0; r->idiag_uid = 0; r->idiag_inode = 0; -#if IS_ENABLED(CONFIG_IPV6) - if (tw->tw_family == AF_INET6) { - *(struct in6_addr *)r->id.idiag_src = tw->tw_v6_rcv_saddr; - *(struct in6_addr *)r->id.idiag_dst = tw->tw_v6_daddr; - } -#endif + + nlmsg_end(skb, nlh); + return 0; +} + +static int inet_req_diag_fill(struct sock *sk, struct sk_buff *skb, + u32 portid, u32 seq, u16 nlmsg_flags, + const struct nlmsghdr *unlh) +{ + struct inet_diag_msg *r; + struct nlmsghdr *nlh; + long tmo; + + nlh = nlmsg_put(skb, portid, seq, unlh->nlmsg_type, sizeof(*r), + nlmsg_flags); + if (!nlh) + return -EMSGSIZE; + + r = nlmsg_data(nlh); + inet_diag_msg_common_fill(r, sk); + r->idiag_state = TCP_SYN_RECV; + r->idiag_timer = 1; + r->idiag_retrans = inet_reqsk(sk)->num_retrans; + + BUILD_BUG_ON(offsetof(struct inet_request_sock, ir_cookie) != + offsetof(struct sock, sk_cookie)); + + tmo = inet_reqsk(sk)->rsk_timer.expires - jiffies; + r->idiag_expires = (tmo >= 0) ? jiffies_to_msecs(tmo) : 0; + r->idiag_rqueue = 0; + r->idiag_wqueue = 0; + r->idiag_uid = 0; + r->idiag_inode = 0; nlmsg_end(skb, nlh); return 0; } static int sk_diag_fill(struct sock *sk, struct sk_buff *skb, - struct inet_diag_req_v2 *r, + const struct inet_diag_req_v2 *r, struct user_namespace *user_ns, u32 portid, u32 seq, u16 nlmsg_flags, const struct nlmsghdr *unlh) { if (sk->sk_state == TCP_TIME_WAIT) - return inet_twsk_diag_fill(inet_twsk(sk), skb, r, portid, seq, + return inet_twsk_diag_fill(sk, skb, portid, seq, nlmsg_flags, unlh); + if (sk->sk_state == TCP_NEW_SYN_RECV) + return inet_req_diag_fill(sk, skb, portid, seq, + nlmsg_flags, unlh); + return inet_csk_diag_fill(sk, skb, r, user_ns, portid, seq, nlmsg_flags, unlh); } -int inet_diag_dump_one_icsk(struct inet_hashinfo *hashinfo, struct sk_buff *in_skb, - const struct nlmsghdr *nlh, struct inet_diag_req_v2 *req) +int inet_diag_dump_one_icsk(struct inet_hashinfo *hashinfo, + struct sk_buff *in_skb, + const struct nlmsghdr *nlh, + const struct inet_diag_req_v2 *req) { - int err; - struct sock *sk; - struct sk_buff *rep; struct net *net = sock_net(in_skb->sk); + struct sk_buff *rep; + struct sock *sk; + int err; err = -EINVAL; - if (req->sdiag_family == AF_INET) { + if (req->sdiag_family == AF_INET) sk = inet_lookup(net, hashinfo, req->id.idiag_dst[0], req->id.idiag_dport, req->id.idiag_src[0], req->id.idiag_sport, req->id.idiag_if); - } #if IS_ENABLED(CONFIG_IPV6) - else if (req->sdiag_family == AF_INET6) { + else if (req->sdiag_family == AF_INET6) sk = inet6_lookup(net, hashinfo, (struct in6_addr *)req->id.idiag_dst, req->id.idiag_dport, (struct in6_addr *)req->id.idiag_src, req->id.idiag_sport, req->id.idiag_if); - } #endif - else { + else goto out_nosk; - } err = -ENOENT; - if (sk == NULL) + if (!sk) goto out_nosk; err = sock_diag_check_cookie(sk, req->id.idiag_cookie); @@ -371,7 +410,7 @@ EXPORT_SYMBOL_GPL(inet_diag_dump_one_icsk); static int inet_diag_get_exact(struct sk_buff *in_skb, const struct nlmsghdr *nlh, - struct inet_diag_req_v2 *req) + const struct inet_diag_req_v2 *req) { const struct inet_diag_handler *handler; int err; @@ -412,9 +451,8 @@ static int bitstring_match(const __be32 *a1, const __be32 *a2, int bits) return 1; } - static int inet_diag_bc_run(const struct nlattr *_bc, - const struct inet_diag_entry *entry) + const struct inet_diag_entry *entry) { const void *bc = nla_data(_bc); int len = nla_len(_bc); @@ -446,10 +484,10 @@ static int inet_diag_bc_run(const struct nlattr *_bc, break; case INET_DIAG_BC_S_COND: case INET_DIAG_BC_D_COND: { - struct inet_diag_hostcond *cond; - __be32 *addr; + const struct inet_diag_hostcond *cond; + const __be32 *addr; - cond = (struct inet_diag_hostcond *)(op + 1); + cond = (const struct inet_diag_hostcond *)(op + 1); if (cond->port != -1 && cond->port != (op->code == INET_DIAG_BC_S_COND ? entry->sport : entry->dport)) { @@ -498,29 +536,36 @@ static int inet_diag_bc_run(const struct nlattr *_bc, return len == 0; } +/* This helper is available for all sockets (ESTABLISH, TIMEWAIT, SYN_RECV) + */ +static void entry_fill_addrs(struct inet_diag_entry *entry, + const struct sock *sk) +{ +#if IS_ENABLED(CONFIG_IPV6) + if (sk->sk_family == AF_INET6) { + entry->saddr = sk->sk_v6_rcv_saddr.s6_addr32; + entry->daddr = sk->sk_v6_daddr.s6_addr32; + } else +#endif + { + entry->saddr = &sk->sk_rcv_saddr; + entry->daddr = &sk->sk_daddr; + } +} + int inet_diag_bc_sk(const struct nlattr *bc, struct sock *sk) { - struct inet_diag_entry entry; struct inet_sock *inet = inet_sk(sk); + struct inet_diag_entry entry; - if (bc == NULL) + if (!bc) return 1; entry.family = sk->sk_family; -#if IS_ENABLED(CONFIG_IPV6) - if (entry.family == AF_INET6) { - - entry.saddr = sk->sk_v6_rcv_saddr.s6_addr32; - entry.daddr = sk->sk_v6_daddr.s6_addr32; - } else -#endif - { - entry.saddr = &inet->inet_rcv_saddr; - entry.daddr = &inet->inet_daddr; - } + entry_fill_addrs(&entry, sk); entry.sport = inet->inet_num; entry.dport = ntohs(inet->inet_dport); - entry.userlocks = sk->sk_userlocks; + entry.userlocks = sk_fullsock(sk) ? sk->sk_userlocks : 0; return inet_diag_bc_run(bc, &entry); } @@ -547,8 +592,8 @@ static int valid_cc(const void *bc, int len, int cc) static bool valid_hostcond(const struct inet_diag_bc_op *op, int len, int *min_len) { - int addr_len; struct inet_diag_hostcond *cond; + int addr_len; /* Check hostcond space. */ *min_len += sizeof(struct inet_diag_hostcond); @@ -582,8 +627,8 @@ static bool valid_hostcond(const struct inet_diag_bc_op *op, int len, } /* Validate a port comparison operator. */ -static inline bool valid_port_comparison(const struct inet_diag_bc_op *op, - int len, int *min_len) +static bool valid_port_comparison(const struct inet_diag_bc_op *op, + int len, int *min_len) { /* Port comparisons put the port in a follow-on inet_diag_bc_op. */ *min_len += sizeof(struct inet_diag_bc_op); @@ -598,10 +643,9 @@ static int inet_diag_bc_audit(const void *bytecode, int bytecode_len) int len = bytecode_len; while (len > 0) { - const struct inet_diag_bc_op *op = bc; int min_len = sizeof(struct inet_diag_bc_op); + const struct inet_diag_bc_op *op = bc; -//printk("BC: %d %d %d {%d} / %d\n", op->code, op->yes, op->no, op[1].no, len); switch (op->code) { case INET_DIAG_BC_S_COND: case INET_DIAG_BC_D_COND: @@ -642,7 +686,7 @@ static int inet_diag_bc_audit(const void *bytecode, int bytecode_len) static int inet_csk_diag_dump(struct sock *sk, struct sk_buff *skb, struct netlink_callback *cb, - struct inet_diag_req_v2 *r, + const struct inet_diag_req_v2 *r, const struct nlattr *bc) { if (!inet_diag_bc_sk(bc, sk)) @@ -654,139 +698,42 @@ static int inet_csk_diag_dump(struct sock *sk, cb->nlh->nlmsg_seq, NLM_F_MULTI, cb->nlh); } -static int inet_twsk_diag_dump(struct sock *sk, - struct sk_buff *skb, - struct netlink_callback *cb, - struct inet_diag_req_v2 *r, - const struct nlattr *bc) +static void twsk_build_assert(void) { - struct inet_timewait_sock *tw = inet_twsk(sk); + BUILD_BUG_ON(offsetof(struct inet_timewait_sock, tw_family) != + offsetof(struct sock, sk_family)); - if (bc != NULL) { - struct inet_diag_entry entry; + BUILD_BUG_ON(offsetof(struct inet_timewait_sock, tw_num) != + offsetof(struct inet_sock, inet_num)); - entry.family = tw->tw_family; -#if IS_ENABLED(CONFIG_IPV6) - if (tw->tw_family == AF_INET6) { - entry.saddr = tw->tw_v6_rcv_saddr.s6_addr32; - entry.daddr = tw->tw_v6_daddr.s6_addr32; - } else -#endif - { - entry.saddr = &tw->tw_rcv_saddr; - entry.daddr = &tw->tw_daddr; - } - entry.sport = tw->tw_num; - entry.dport = ntohs(tw->tw_dport); - entry.userlocks = 0; - - if (!inet_diag_bc_run(bc, &entry)) - return 0; - } + BUILD_BUG_ON(offsetof(struct inet_timewait_sock, tw_dport) != + offsetof(struct inet_sock, inet_dport)); - return inet_twsk_diag_fill(tw, skb, r, - NETLINK_CB(cb->skb).portid, - cb->nlh->nlmsg_seq, NLM_F_MULTI, cb->nlh); -} + BUILD_BUG_ON(offsetof(struct inet_timewait_sock, tw_rcv_saddr) != + offsetof(struct inet_sock, inet_rcv_saddr)); -/* Get the IPv4, IPv6, or IPv4-mapped-IPv6 local and remote addresses - * from a request_sock. For IPv4-mapped-IPv6 we must map IPv4 to IPv6. - */ -static inline void inet_diag_req_addrs(const struct sock *sk, - const struct request_sock *req, - struct inet_diag_entry *entry) -{ - struct inet_request_sock *ireq = inet_rsk(req); + BUILD_BUG_ON(offsetof(struct inet_timewait_sock, tw_daddr) != + offsetof(struct inet_sock, inet_daddr)); #if IS_ENABLED(CONFIG_IPV6) - if (sk->sk_family == AF_INET6) { - if (req->rsk_ops->family == AF_INET6) { - entry->saddr = ireq->ir_v6_loc_addr.s6_addr32; - entry->daddr = ireq->ir_v6_rmt_addr.s6_addr32; - } else if (req->rsk_ops->family == AF_INET) { - ipv6_addr_set_v4mapped(ireq->ir_loc_addr, - &entry->saddr_storage); - ipv6_addr_set_v4mapped(ireq->ir_rmt_addr, - &entry->daddr_storage); - entry->saddr = entry->saddr_storage.s6_addr32; - entry->daddr = entry->daddr_storage.s6_addr32; - } - } else -#endif - { - entry->saddr = &ireq->ir_loc_addr; - entry->daddr = &ireq->ir_rmt_addr; - } -} - -static int inet_diag_fill_req(struct sk_buff *skb, struct sock *sk, - struct request_sock *req, - struct user_namespace *user_ns, - u32 portid, u32 seq, - const struct nlmsghdr *unlh) -{ - const struct inet_request_sock *ireq = inet_rsk(req); - struct inet_sock *inet = inet_sk(sk); - struct inet_diag_msg *r; - struct nlmsghdr *nlh; - long tmo; - - nlh = nlmsg_put(skb, portid, seq, unlh->nlmsg_type, sizeof(*r), - NLM_F_MULTI); - if (!nlh) - return -EMSGSIZE; - - r = nlmsg_data(nlh); - r->idiag_family = sk->sk_family; - r->idiag_state = TCP_SYN_RECV; - r->idiag_timer = 1; - r->idiag_retrans = req->num_retrans; - - r->id.idiag_if = sk->sk_bound_dev_if; - sock_diag_save_cookie(req, r->id.idiag_cookie); - - tmo = req->expires - jiffies; - if (tmo < 0) - tmo = 0; - - r->id.idiag_sport = inet->inet_sport; - r->id.idiag_dport = ireq->ir_rmt_port; - - memset(&r->id.idiag_src, 0, sizeof(r->id.idiag_src)); - memset(&r->id.idiag_dst, 0, sizeof(r->id.idiag_dst)); - - r->id.idiag_src[0] = ireq->ir_loc_addr; - r->id.idiag_dst[0] = ireq->ir_rmt_addr; + BUILD_BUG_ON(offsetof(struct inet_timewait_sock, tw_v6_rcv_saddr) != + offsetof(struct sock, sk_v6_rcv_saddr)); - r->idiag_expires = jiffies_to_msecs(tmo); - r->idiag_rqueue = 0; - r->idiag_wqueue = 0; - r->idiag_uid = from_kuid_munged(user_ns, sock_i_uid(sk)); - r->idiag_inode = 0; -#if IS_ENABLED(CONFIG_IPV6) - if (r->idiag_family == AF_INET6) { - struct inet_diag_entry entry; - inet_diag_req_addrs(sk, req, &entry); - memcpy(r->id.idiag_src, entry.saddr, sizeof(struct in6_addr)); - memcpy(r->id.idiag_dst, entry.daddr, sizeof(struct in6_addr)); - } + BUILD_BUG_ON(offsetof(struct inet_timewait_sock, tw_v6_daddr) != + offsetof(struct sock, sk_v6_daddr)); #endif - - nlmsg_end(skb, nlh); - return 0; } static int inet_diag_dump_reqs(struct sk_buff *skb, struct sock *sk, struct netlink_callback *cb, - struct inet_diag_req_v2 *r, + const struct inet_diag_req_v2 *r, const struct nlattr *bc) { - struct inet_diag_entry entry; struct inet_connection_sock *icsk = inet_csk(sk); - struct listen_sock *lopt; struct inet_sock *inet = inet_sk(sk); - int j, s_j; - int reqnum, s_reqnum; + struct inet_diag_entry entry; + int j, s_j, reqnum, s_reqnum; + struct listen_sock *lopt; int err = 0; s_j = cb->args[3]; @@ -797,13 +744,13 @@ static int inet_diag_dump_reqs(struct sk_buff *skb, struct sock *sk, entry.family = sk->sk_family; - read_lock_bh(&icsk->icsk_accept_queue.syn_wait_lock); + spin_lock_bh(&icsk->icsk_accept_queue.syn_wait_lock); lopt = icsk->icsk_accept_queue.listen_opt; - if (!lopt || !lopt->qlen) + if (!lopt || !listen_sock_qlen(lopt)) goto out; - if (bc != NULL) { + if (bc) { entry.sport = inet->inet_num; entry.userlocks = sk->sk_userlocks; } @@ -822,17 +769,18 @@ static int inet_diag_dump_reqs(struct sk_buff *skb, struct sock *sk, continue; if (bc) { - inet_diag_req_addrs(sk, req, &entry); + /* Note: entry.sport and entry.userlocks are already set */ + entry_fill_addrs(&entry, req_to_sk(req)); entry.dport = ntohs(ireq->ir_rmt_port); if (!inet_diag_bc_run(bc, &entry)) continue; } - err = inet_diag_fill_req(skb, sk, req, - sk_user_ns(NETLINK_CB(cb->skb).sk), - NETLINK_CB(cb->skb).portid, - cb->nlh->nlmsg_seq, cb->nlh); + err = inet_req_diag_fill(req_to_sk(req), skb, + NETLINK_CB(cb->skb).portid, + cb->nlh->nlmsg_seq, + NLM_F_MULTI, cb->nlh); if (err < 0) { cb->args[3] = j + 1; cb->args[4] = reqnum; @@ -844,17 +792,17 @@ static int inet_diag_dump_reqs(struct sk_buff *skb, struct sock *sk, } out: - read_unlock_bh(&icsk->icsk_accept_queue.syn_wait_lock); + spin_unlock_bh(&icsk->icsk_accept_queue.syn_wait_lock); return err; } void inet_diag_dump_icsk(struct inet_hashinfo *hashinfo, struct sk_buff *skb, - struct netlink_callback *cb, struct inet_diag_req_v2 *r, struct nlattr *bc) + struct netlink_callback *cb, + const struct inet_diag_req_v2 *r, struct nlattr *bc) { - int i, num; - int s_i, s_num; struct net *net = sock_net(skb->sk); + int i, num, s_i, s_num; s_i = cb->args[1]; s_num = num = cb->args[2]; @@ -864,9 +812,9 @@ void inet_diag_dump_icsk(struct inet_hashinfo *hashinfo, struct sk_buff *skb, goto skip_listen_ht; for (i = s_i; i < INET_LHTABLE_SIZE; i++) { - struct sock *sk; - struct hlist_nulls_node *node; struct inet_listen_hashbucket *ilb; + struct hlist_nulls_node *node; + struct sock *sk; num = 0; ilb = &hashinfo->listening_hash[i]; @@ -883,7 +831,7 @@ void inet_diag_dump_icsk(struct inet_hashinfo *hashinfo, struct sk_buff *skb, } if (r->sdiag_family != AF_UNSPEC && - sk->sk_family != r->sdiag_family) + sk->sk_family != r->sdiag_family) goto next_listen; if (r->id.idiag_sport != inet->inet_sport && @@ -931,8 +879,8 @@ skip_listen_ht: for (i = s_i; i <= hashinfo->ehash_mask; i++) { struct inet_ehash_bucket *head = &hashinfo->ehash[i]; spinlock_t *lock = inet_ehash_lockp(hashinfo, i); - struct sock *sk; struct hlist_nulls_node *node; + struct sock *sk; num = 0; @@ -944,8 +892,7 @@ skip_listen_ht: spin_lock_bh(lock); sk_nulls_for_each(sk, node, &head->chain) { - int res; - int state; + int state, res; if (!net_eq(sock_net(sk), net)) continue; @@ -964,10 +911,16 @@ skip_listen_ht: if (r->id.idiag_dport != sk->sk_dport && r->id.idiag_dport) goto next_normal; - if (sk->sk_state == TCP_TIME_WAIT) - res = inet_twsk_diag_dump(sk, skb, cb, r, bc); - else - res = inet_csk_diag_dump(sk, skb, cb, r, bc); + twsk_build_assert(); + + if (!inet_diag_bc_sk(bc, sk)) + goto next_normal; + + res = sk_diag_fill(sk, skb, r, + sk_user_ns(NETLINK_CB(cb->skb).sk), + NETLINK_CB(cb->skb).portid, + cb->nlh->nlmsg_seq, NLM_F_MULTI, + cb->nlh); if (res < 0) { spin_unlock_bh(lock); goto done; @@ -988,7 +941,8 @@ out: EXPORT_SYMBOL_GPL(inet_diag_dump_icsk); static int __inet_diag_dump(struct sk_buff *skb, struct netlink_callback *cb, - struct inet_diag_req_v2 *r, struct nlattr *bc) + const struct inet_diag_req_v2 *r, + struct nlattr *bc) { const struct inet_diag_handler *handler; int err = 0; @@ -1005,8 +959,8 @@ static int __inet_diag_dump(struct sk_buff *skb, struct netlink_callback *cb, static int inet_diag_dump(struct sk_buff *skb, struct netlink_callback *cb) { - struct nlattr *bc = NULL; int hdrlen = sizeof(struct inet_diag_req_v2); + struct nlattr *bc = NULL; if (nlmsg_attrlen(cb->nlh, hdrlen)) bc = nlmsg_find_attr(cb->nlh, hdrlen, INET_DIAG_REQ_BYTECODE); @@ -1014,7 +968,7 @@ static int inet_diag_dump(struct sk_buff *skb, struct netlink_callback *cb) return __inet_diag_dump(skb, cb, nlmsg_data(cb->nlh), bc); } -static inline int inet_diag_type2proto(int type) +static int inet_diag_type2proto(int type) { switch (type) { case TCPDIAG_GETSOCK: @@ -1026,12 +980,13 @@ static inline int inet_diag_type2proto(int type) } } -static int inet_diag_dump_compat(struct sk_buff *skb, struct netlink_callback *cb) +static int inet_diag_dump_compat(struct sk_buff *skb, + struct netlink_callback *cb) { struct inet_diag_req *rc = nlmsg_data(cb->nlh); + int hdrlen = sizeof(struct inet_diag_req); struct inet_diag_req_v2 req; struct nlattr *bc = NULL; - int hdrlen = sizeof(struct inet_diag_req); req.sdiag_family = AF_UNSPEC; /* compatibility */ req.sdiag_protocol = inet_diag_type2proto(cb->nlh->nlmsg_type); @@ -1046,7 +1001,7 @@ static int inet_diag_dump_compat(struct sk_buff *skb, struct netlink_callback *c } static int inet_diag_get_exact_compat(struct sk_buff *in_skb, - const struct nlmsghdr *nlh) + const struct nlmsghdr *nlh) { struct inet_diag_req *rc = nlmsg_data(nlh); struct inet_diag_req_v2 req; @@ -1075,7 +1030,7 @@ static int inet_diag_rcv_msg_compat(struct sk_buff *skb, struct nlmsghdr *nlh) attr = nlmsg_find_attr(nlh, hdrlen, INET_DIAG_REQ_BYTECODE); - if (attr == NULL || + if (!attr || nla_len(attr) < sizeof(struct inet_diag_bc_op) || inet_diag_bc_audit(nla_data(attr), nla_len(attr))) return -EINVAL; @@ -1102,9 +1057,10 @@ static int inet_diag_handler_dump(struct sk_buff *skb, struct nlmsghdr *h) if (h->nlmsg_flags & NLM_F_DUMP) { if (nlmsg_attrlen(h, hdrlen)) { struct nlattr *attr; + attr = nlmsg_find_attr(h, hdrlen, INET_DIAG_REQ_BYTECODE); - if (attr == NULL || + if (!attr || nla_len(attr) < sizeof(struct inet_diag_bc_op) || inet_diag_bc_audit(nla_data(attr), nla_len(attr))) return -EINVAL; @@ -1140,7 +1096,7 @@ int inet_diag_register(const struct inet_diag_handler *h) mutex_lock(&inet_diag_table_mutex); err = -EEXIST; - if (inet_diag_table[type] == NULL) { + if (!inet_diag_table[type]) { inet_diag_table[type] = h; err = 0; } diff --git a/net/ipv4/inet_fragment.c b/net/ipv4/inet_fragment.c index e7920352646a..5e346a082e5f 100644 --- a/net/ipv4/inet_fragment.c +++ b/net/ipv4/inet_fragment.c @@ -385,7 +385,7 @@ static struct inet_frag_queue *inet_frag_alloc(struct netns_frags *nf, } q = kmem_cache_zalloc(f->frags_cachep, GFP_ATOMIC); - if (q == NULL) + if (!q) return NULL; q->net = nf; @@ -406,7 +406,7 @@ static struct inet_frag_queue *inet_frag_create(struct netns_frags *nf, struct inet_frag_queue *q; q = inet_frag_alloc(nf, f, arg); - if (q == NULL) + if (!q) return NULL; return inet_frag_intern(nf, q, f, arg); diff --git a/net/ipv4/inet_hashtables.c b/net/ipv4/inet_hashtables.c index 9111a4e22155..c6fb80bd5826 100644 --- a/net/ipv4/inet_hashtables.c +++ b/net/ipv4/inet_hashtables.c @@ -24,9 +24,9 @@ #include <net/secure_seq.h> #include <net/ip.h> -static unsigned int inet_ehashfn(struct net *net, const __be32 laddr, - const __u16 lport, const __be32 faddr, - const __be16 fport) +static u32 inet_ehashfn(const struct net *net, const __be32 laddr, + const __u16 lport, const __be32 faddr, + const __be16 fport) { static u32 inet_ehash_secret __read_mostly; @@ -36,17 +36,21 @@ static unsigned int inet_ehashfn(struct net *net, const __be32 laddr, inet_ehash_secret + net_hash_mix(net)); } - -static unsigned int inet_sk_ehashfn(const struct sock *sk) +/* This function handles inet_sock, but also timewait and request sockets + * for IPv4/IPv6. + */ +u32 sk_ehashfn(const struct sock *sk) { - const struct inet_sock *inet = inet_sk(sk); - const __be32 laddr = inet->inet_rcv_saddr; - const __u16 lport = inet->inet_num; - const __be32 faddr = inet->inet_daddr; - const __be16 fport = inet->inet_dport; - struct net *net = sock_net(sk); - - return inet_ehashfn(net, laddr, lport, faddr, fport); +#if IS_ENABLED(CONFIG_IPV6) + if (sk->sk_family == AF_INET6 && + !ipv6_addr_v4mapped(&sk->sk_v6_daddr)) + return inet6_ehashfn(sock_net(sk), + &sk->sk_v6_rcv_saddr, sk->sk_num, + &sk->sk_v6_daddr, sk->sk_dport); +#endif + return inet_ehashfn(sock_net(sk), + sk->sk_rcv_saddr, sk->sk_num, + sk->sk_daddr, sk->sk_dport); } /* @@ -60,8 +64,8 @@ struct inet_bind_bucket *inet_bind_bucket_create(struct kmem_cache *cachep, { struct inet_bind_bucket *tb = kmem_cache_alloc(cachep, GFP_ATOMIC); - if (tb != NULL) { - write_pnet(&tb->ib_net, hold_net(net)); + if (tb) { + write_pnet(&tb->ib_net, net); tb->port = snum; tb->fastreuse = 0; tb->fastreuseport = 0; @@ -79,7 +83,6 @@ void inet_bind_bucket_destroy(struct kmem_cache *cachep, struct inet_bind_bucket { if (hlist_empty(&tb->owners)) { __hlist_del(&tb->node); - release_net(ib_net(tb)); kmem_cache_free(cachep, tb); } } @@ -263,11 +266,19 @@ void sock_gen_put(struct sock *sk) if (sk->sk_state == TCP_TIME_WAIT) inet_twsk_free(inet_twsk(sk)); + else if (sk->sk_state == TCP_NEW_SYN_RECV) + reqsk_free(inet_reqsk(sk)); else sk_free(sk); } EXPORT_SYMBOL_GPL(sock_gen_put); +void sock_edemux(struct sk_buff *skb) +{ + sock_gen_put(skb->sk); +} +EXPORT_SYMBOL(sock_edemux); + struct sock *__inet_lookup_established(struct net *net, struct inet_hashinfo *hashinfo, const __be32 saddr, const __be16 sport, @@ -377,7 +388,7 @@ static int __inet_check_established(struct inet_timewait_death_row *death_row, *twp = tw; } else if (tw) { /* Silly. Should hash-dance instead... */ - inet_twsk_deschedule(tw, death_row); + inet_twsk_deschedule(tw); inet_twsk_put(tw); } @@ -400,13 +411,13 @@ int __inet_hash_nolisten(struct sock *sk, struct inet_timewait_sock *tw) { struct inet_hashinfo *hashinfo = sk->sk_prot->h.hashinfo; struct hlist_nulls_head *list; - spinlock_t *lock; struct inet_ehash_bucket *head; + spinlock_t *lock; int twrefcnt = 0; WARN_ON(!sk_unhashed(sk)); - sk->sk_hash = inet_sk_ehashfn(sk); + sk->sk_hash = sk_ehashfn(sk); head = inet_ehash_bucket(hashinfo, sk->sk_hash); list = &head->chain; lock = inet_ehash_lockp(hashinfo, sk->sk_hash); @@ -423,15 +434,13 @@ int __inet_hash_nolisten(struct sock *sk, struct inet_timewait_sock *tw) } EXPORT_SYMBOL_GPL(__inet_hash_nolisten); -static void __inet_hash(struct sock *sk) +int __inet_hash(struct sock *sk, struct inet_timewait_sock *tw) { struct inet_hashinfo *hashinfo = sk->sk_prot->h.hashinfo; struct inet_listen_hashbucket *ilb; - if (sk->sk_state != TCP_LISTEN) { - __inet_hash_nolisten(sk, NULL); - return; - } + if (sk->sk_state != TCP_LISTEN) + return __inet_hash_nolisten(sk, tw); WARN_ON(!sk_unhashed(sk)); ilb = &hashinfo->listening_hash[inet_sk_listen_hashfn(sk)]; @@ -440,13 +449,15 @@ static void __inet_hash(struct sock *sk) __sk_nulls_add_node_rcu(sk, &ilb->head); sock_prot_inuse_add(sock_net(sk), sk->sk_prot, 1); spin_unlock(&ilb->lock); + return 0; } +EXPORT_SYMBOL(__inet_hash); void inet_hash(struct sock *sk) { if (sk->sk_state != TCP_CLOSE) { local_bh_disable(); - __inet_hash(sk); + __inet_hash(sk, NULL); local_bh_enable(); } } @@ -477,8 +488,7 @@ EXPORT_SYMBOL_GPL(inet_unhash); int __inet_hash_connect(struct inet_timewait_death_row *death_row, struct sock *sk, u32 port_offset, int (*check_established)(struct inet_timewait_death_row *, - struct sock *, __u16, struct inet_timewait_sock **), - int (*hash)(struct sock *sk, struct inet_timewait_sock *twp)) + struct sock *, __u16, struct inet_timewait_sock **)) { struct inet_hashinfo *hinfo = death_row->hashinfo; const unsigned short snum = inet_sk(sk)->inet_num; @@ -548,14 +558,14 @@ ok: inet_bind_hash(sk, tb, port); if (sk_unhashed(sk)) { inet_sk(sk)->inet_sport = htons(port); - twrefcnt += hash(sk, tw); + twrefcnt += __inet_hash_nolisten(sk, tw); } if (tw) twrefcnt += inet_twsk_bind_unhash(tw, hinfo); spin_unlock(&head->lock); if (tw) { - inet_twsk_deschedule(tw, death_row); + inet_twsk_deschedule(tw); while (twrefcnt) { twrefcnt--; inet_twsk_put(tw); @@ -570,7 +580,7 @@ ok: tb = inet_csk(sk)->icsk_bind_hash; spin_lock_bh(&head->lock); if (sk_head(&tb->owners) == sk && !sk->sk_bind_node.next) { - hash(sk, NULL); + __inet_hash_nolisten(sk, NULL); spin_unlock_bh(&head->lock); return 0; } else { @@ -590,7 +600,7 @@ int inet_hash_connect(struct inet_timewait_death_row *death_row, struct sock *sk) { return __inet_hash_connect(death_row, sk, inet_sk_port_offset(sk), - __inet_check_established, __inet_hash_nolisten); + __inet_check_established); } EXPORT_SYMBOL_GPL(inet_hash_connect); diff --git a/net/ipv4/inet_timewait_sock.c b/net/ipv4/inet_timewait_sock.c index 6d592f8555fb..00ec8d5d7e7e 100644 --- a/net/ipv4/inet_timewait_sock.c +++ b/net/ipv4/inet_timewait_sock.c @@ -67,9 +67,9 @@ int inet_twsk_bind_unhash(struct inet_timewait_sock *tw, } /* Must be called with locally disabled BHs. */ -static void __inet_twsk_kill(struct inet_timewait_sock *tw, - struct inet_hashinfo *hashinfo) +static void inet_twsk_kill(struct inet_timewait_sock *tw) { + struct inet_hashinfo *hashinfo = tw->tw_dr->hashinfo; struct inet_bind_hashbucket *bhead; int refcnt; /* Unlink from established hashes. */ @@ -89,6 +89,8 @@ static void __inet_twsk_kill(struct inet_timewait_sock *tw, BUG_ON(refcnt >= atomic_read(&tw->tw_refcnt)); atomic_sub(refcnt, &tw->tw_refcnt); + atomic_dec(&tw->tw_dr->tw_count); + inet_twsk_put(tw); } void inet_twsk_free(struct inet_timewait_sock *tw) @@ -98,7 +100,6 @@ void inet_twsk_free(struct inet_timewait_sock *tw) #ifdef SOCK_REFCNT_DEBUG pr_debug("%s timewait_sock %p released\n", tw->tw_prot->name, tw); #endif - release_net(twsk_net(tw)); kmem_cache_free(tw->tw_prot->twsk_prot->twsk_slab, tw); module_put(owner); } @@ -169,16 +170,34 @@ void __inet_twsk_hashdance(struct inet_timewait_sock *tw, struct sock *sk, } EXPORT_SYMBOL_GPL(__inet_twsk_hashdance); -struct inet_timewait_sock *inet_twsk_alloc(const struct sock *sk, const int state) +void tw_timer_handler(unsigned long data) { - struct inet_timewait_sock *tw = - kmem_cache_alloc(sk->sk_prot_creator->twsk_prot->twsk_slab, - GFP_ATOMIC); - if (tw != NULL) { + struct inet_timewait_sock *tw = (struct inet_timewait_sock *)data; + + if (tw->tw_kill) + NET_INC_STATS_BH(twsk_net(tw), LINUX_MIB_TIMEWAITKILLED); + else + NET_INC_STATS_BH(twsk_net(tw), LINUX_MIB_TIMEWAITED); + inet_twsk_kill(tw); +} + +struct inet_timewait_sock *inet_twsk_alloc(const struct sock *sk, + struct inet_timewait_death_row *dr, + const int state) +{ + struct inet_timewait_sock *tw; + + if (atomic_read(&dr->tw_count) >= dr->sysctl_max_tw_buckets) + return NULL; + + tw = kmem_cache_alloc(sk->sk_prot_creator->twsk_prot->twsk_slab, + GFP_ATOMIC); + if (tw) { const struct inet_sock *inet = inet_sk(sk); kmemcheck_annotate_bitfield(tw, flags); + tw->tw_dr = dr; /* Give us an identity. */ tw->tw_daddr = inet->inet_daddr; tw->tw_rcv_saddr = inet->inet_rcv_saddr; @@ -195,14 +214,16 @@ struct inet_timewait_sock *inet_twsk_alloc(const struct sock *sk, const int stat tw->tw_ipv6only = 0; tw->tw_transparent = inet->transparent; tw->tw_prot = sk->sk_prot_creator; - twsk_net_set(tw, hold_net(sock_net(sk))); + atomic64_set(&tw->tw_cookie, atomic64_read(&sk->sk_cookie)); + twsk_net_set(tw, sock_net(sk)); + setup_timer(&tw->tw_timer, tw_timer_handler, (unsigned long)tw); /* * Because we use RCU lookups, we should not set tw_refcnt * to a non null value before everything is setup for this * timewait socket. */ atomic_set(&tw->tw_refcnt, 0); - inet_twsk_dead_node_init(tw); + __module_get(tw->tw_prot->owner); } @@ -210,139 +231,20 @@ struct inet_timewait_sock *inet_twsk_alloc(const struct sock *sk, const int stat } EXPORT_SYMBOL_GPL(inet_twsk_alloc); -/* Returns non-zero if quota exceeded. */ -static int inet_twdr_do_twkill_work(struct inet_timewait_death_row *twdr, - const int slot) -{ - struct inet_timewait_sock *tw; - unsigned int killed; - int ret; - - /* NOTE: compare this to previous version where lock - * was released after detaching chain. It was racy, - * because tw buckets are scheduled in not serialized context - * in 2.3 (with netfilter), and with softnet it is common, because - * soft irqs are not sequenced. - */ - killed = 0; - ret = 0; -rescan: - inet_twsk_for_each_inmate(tw, &twdr->cells[slot]) { - __inet_twsk_del_dead_node(tw); - spin_unlock(&twdr->death_lock); - __inet_twsk_kill(tw, twdr->hashinfo); -#ifdef CONFIG_NET_NS - NET_INC_STATS_BH(twsk_net(tw), LINUX_MIB_TIMEWAITED); -#endif - inet_twsk_put(tw); - killed++; - spin_lock(&twdr->death_lock); - if (killed > INET_TWDR_TWKILL_QUOTA) { - ret = 1; - break; - } - - /* While we dropped twdr->death_lock, another cpu may have - * killed off the next TW bucket in the list, therefore - * do a fresh re-read of the hlist head node with the - * lock reacquired. We still use the hlist traversal - * macro in order to get the prefetches. - */ - goto rescan; - } - - twdr->tw_count -= killed; -#ifndef CONFIG_NET_NS - NET_ADD_STATS_BH(&init_net, LINUX_MIB_TIMEWAITED, killed); -#endif - return ret; -} - -void inet_twdr_hangman(unsigned long data) -{ - struct inet_timewait_death_row *twdr; - unsigned int need_timer; - - twdr = (struct inet_timewait_death_row *)data; - spin_lock(&twdr->death_lock); - - if (twdr->tw_count == 0) - goto out; - - need_timer = 0; - if (inet_twdr_do_twkill_work(twdr, twdr->slot)) { - twdr->thread_slots |= (1 << twdr->slot); - schedule_work(&twdr->twkill_work); - need_timer = 1; - } else { - /* We purged the entire slot, anything left? */ - if (twdr->tw_count) - need_timer = 1; - twdr->slot = ((twdr->slot + 1) & (INET_TWDR_TWKILL_SLOTS - 1)); - } - if (need_timer) - mod_timer(&twdr->tw_timer, jiffies + twdr->period); -out: - spin_unlock(&twdr->death_lock); -} -EXPORT_SYMBOL_GPL(inet_twdr_hangman); - -void inet_twdr_twkill_work(struct work_struct *work) -{ - struct inet_timewait_death_row *twdr = - container_of(work, struct inet_timewait_death_row, twkill_work); - int i; - - BUILD_BUG_ON((INET_TWDR_TWKILL_SLOTS - 1) > - (sizeof(twdr->thread_slots) * 8)); - - while (twdr->thread_slots) { - spin_lock_bh(&twdr->death_lock); - for (i = 0; i < INET_TWDR_TWKILL_SLOTS; i++) { - if (!(twdr->thread_slots & (1 << i))) - continue; - - while (inet_twdr_do_twkill_work(twdr, i) != 0) { - if (need_resched()) { - spin_unlock_bh(&twdr->death_lock); - schedule(); - spin_lock_bh(&twdr->death_lock); - } - } - - twdr->thread_slots &= ~(1 << i); - } - spin_unlock_bh(&twdr->death_lock); - } -} -EXPORT_SYMBOL_GPL(inet_twdr_twkill_work); - /* These are always called from BH context. See callers in * tcp_input.c to verify this. */ /* This is for handling early-kills of TIME_WAIT sockets. */ -void inet_twsk_deschedule(struct inet_timewait_sock *tw, - struct inet_timewait_death_row *twdr) +void inet_twsk_deschedule(struct inet_timewait_sock *tw) { - spin_lock(&twdr->death_lock); - if (inet_twsk_del_dead_node(tw)) { - inet_twsk_put(tw); - if (--twdr->tw_count == 0) - del_timer(&twdr->tw_timer); - } - spin_unlock(&twdr->death_lock); - __inet_twsk_kill(tw, twdr->hashinfo); + if (del_timer_sync(&tw->tw_timer)) + inet_twsk_kill(tw); } EXPORT_SYMBOL(inet_twsk_deschedule); -void inet_twsk_schedule(struct inet_timewait_sock *tw, - struct inet_timewait_death_row *twdr, - const int timeo, const int timewait_len) +void inet_twsk_schedule(struct inet_timewait_sock *tw, const int timeo) { - struct hlist_head *list; - int slot; - /* timeout := RTO * 3.5 * * 3.5 = 1+2+0.5 to wait for two retransmits. @@ -367,115 +269,15 @@ void inet_twsk_schedule(struct inet_timewait_sock *tw, * is greater than TS tick!) and detect old duplicates with help * of PAWS. */ - slot = (timeo + (1 << INET_TWDR_RECYCLE_TICK) - 1) >> INET_TWDR_RECYCLE_TICK; - spin_lock(&twdr->death_lock); - - /* Unlink it, if it was scheduled */ - if (inet_twsk_del_dead_node(tw)) - twdr->tw_count--; - else + tw->tw_kill = timeo <= 4*HZ; + if (!mod_timer_pinned(&tw->tw_timer, jiffies + timeo)) { atomic_inc(&tw->tw_refcnt); - - if (slot >= INET_TWDR_RECYCLE_SLOTS) { - /* Schedule to slow timer */ - if (timeo >= timewait_len) { - slot = INET_TWDR_TWKILL_SLOTS - 1; - } else { - slot = DIV_ROUND_UP(timeo, twdr->period); - if (slot >= INET_TWDR_TWKILL_SLOTS) - slot = INET_TWDR_TWKILL_SLOTS - 1; - } - tw->tw_ttd = inet_tw_time_stamp() + timeo; - slot = (twdr->slot + slot) & (INET_TWDR_TWKILL_SLOTS - 1); - list = &twdr->cells[slot]; - } else { - tw->tw_ttd = inet_tw_time_stamp() + (slot << INET_TWDR_RECYCLE_TICK); - - if (twdr->twcal_hand < 0) { - twdr->twcal_hand = 0; - twdr->twcal_jiffie = jiffies; - twdr->twcal_timer.expires = twdr->twcal_jiffie + - (slot << INET_TWDR_RECYCLE_TICK); - add_timer(&twdr->twcal_timer); - } else { - if (time_after(twdr->twcal_timer.expires, - jiffies + (slot << INET_TWDR_RECYCLE_TICK))) - mod_timer(&twdr->twcal_timer, - jiffies + (slot << INET_TWDR_RECYCLE_TICK)); - slot = (twdr->twcal_hand + slot) & (INET_TWDR_RECYCLE_SLOTS - 1); - } - list = &twdr->twcal_row[slot]; + atomic_inc(&tw->tw_dr->tw_count); } - - hlist_add_head(&tw->tw_death_node, list); - - if (twdr->tw_count++ == 0) - mod_timer(&twdr->tw_timer, jiffies + twdr->period); - spin_unlock(&twdr->death_lock); } EXPORT_SYMBOL_GPL(inet_twsk_schedule); -void inet_twdr_twcal_tick(unsigned long data) -{ - struct inet_timewait_death_row *twdr; - int n, slot; - unsigned long j; - unsigned long now = jiffies; - int killed = 0; - int adv = 0; - - twdr = (struct inet_timewait_death_row *)data; - - spin_lock(&twdr->death_lock); - if (twdr->twcal_hand < 0) - goto out; - - slot = twdr->twcal_hand; - j = twdr->twcal_jiffie; - - for (n = 0; n < INET_TWDR_RECYCLE_SLOTS; n++) { - if (time_before_eq(j, now)) { - struct hlist_node *safe; - struct inet_timewait_sock *tw; - - inet_twsk_for_each_inmate_safe(tw, safe, - &twdr->twcal_row[slot]) { - __inet_twsk_del_dead_node(tw); - __inet_twsk_kill(tw, twdr->hashinfo); -#ifdef CONFIG_NET_NS - NET_INC_STATS_BH(twsk_net(tw), LINUX_MIB_TIMEWAITKILLED); -#endif - inet_twsk_put(tw); - killed++; - } - } else { - if (!adv) { - adv = 1; - twdr->twcal_jiffie = j; - twdr->twcal_hand = slot; - } - - if (!hlist_empty(&twdr->twcal_row[slot])) { - mod_timer(&twdr->twcal_timer, j); - goto out; - } - } - j += 1 << INET_TWDR_RECYCLE_TICK; - slot = (slot + 1) & (INET_TWDR_RECYCLE_SLOTS - 1); - } - twdr->twcal_hand = -1; - -out: - if ((twdr->tw_count -= killed) == 0) - del_timer(&twdr->tw_timer); -#ifndef CONFIG_NET_NS - NET_ADD_STATS_BH(&init_net, LINUX_MIB_TIMEWAITKILLED, killed); -#endif - spin_unlock(&twdr->death_lock); -} -EXPORT_SYMBOL_GPL(inet_twdr_twcal_tick); - void inet_twsk_purge(struct inet_hashinfo *hashinfo, struct inet_timewait_death_row *twdr, int family) { @@ -487,6 +289,7 @@ void inet_twsk_purge(struct inet_hashinfo *hashinfo, for (slot = 0; slot <= hashinfo->ehash_mask; slot++) { struct inet_ehash_bucket *head = &hashinfo->ehash[slot]; restart_rcu: + cond_resched(); rcu_read_lock(); restart: sk_nulls_for_each_rcu(sk, node, &head->chain) { @@ -508,7 +311,7 @@ restart: rcu_read_unlock(); local_bh_disable(); - inet_twsk_deschedule(tw, twdr); + inet_twsk_deschedule(tw); local_bh_enable(); inet_twsk_put(tw); goto restart_rcu; diff --git a/net/ipv4/ip_forward.c b/net/ipv4/ip_forward.c index d9bc28ac5d1b..3674484946a5 100644 --- a/net/ipv4/ip_forward.c +++ b/net/ipv4/ip_forward.c @@ -57,7 +57,7 @@ static bool ip_exceeds_mtu(const struct sk_buff *skb, unsigned int mtu) } -static int ip_forward_finish(struct sk_buff *skb) +static int ip_forward_finish(struct sock *sk, struct sk_buff *skb) { struct ip_options *opt = &(IPCB(skb)->opt); @@ -68,7 +68,7 @@ static int ip_forward_finish(struct sk_buff *skb) ip_forward_options(skb); skb_sender_cpu_clear(skb); - return dst_output(skb); + return dst_output_sk(sk, skb); } int ip_forward(struct sk_buff *skb) @@ -82,6 +82,9 @@ int ip_forward(struct sk_buff *skb) if (skb->pkt_type != PACKET_HOST) goto drop; + if (unlikely(skb->sk)) + goto drop; + if (skb_warn_if_lro(skb)) goto drop; @@ -136,8 +139,8 @@ int ip_forward(struct sk_buff *skb) skb->priority = rt_tos2priority(iph->tos); - return NF_HOOK(NFPROTO_IPV4, NF_INET_FORWARD, skb, skb->dev, - rt->dst.dev, ip_forward_finish); + return NF_HOOK(NFPROTO_IPV4, NF_INET_FORWARD, NULL, skb, + skb->dev, rt->dst.dev, ip_forward_finish); sr_failed: /* diff --git a/net/ipv4/ip_fragment.c b/net/ipv4/ip_fragment.c index 145a50c4d566..cc1da6d9cb35 100644 --- a/net/ipv4/ip_fragment.c +++ b/net/ipv4/ip_fragment.c @@ -372,7 +372,7 @@ static int ip_frag_queue(struct ipq *qp, struct sk_buff *skb) goto err; err = -ENOMEM; - if (pskb_pull(skb, ihl) == NULL) + if (!pskb_pull(skb, ihl)) goto err; err = pskb_trim_rcsum(skb, end - offset); @@ -537,7 +537,7 @@ static int ip_frag_reasm(struct ipq *qp, struct sk_buff *prev, qp->q.fragments = head; } - WARN_ON(head == NULL); + WARN_ON(!head); WARN_ON(FRAG_CB(head)->offset != 0); /* Allocate a new buffer for the datagram. */ @@ -559,7 +559,8 @@ static int ip_frag_reasm(struct ipq *qp, struct sk_buff *prev, struct sk_buff *clone; int i, plen = 0; - if ((clone = alloc_skb(0, GFP_ATOMIC)) == NULL) + clone = alloc_skb(0, GFP_ATOMIC); + if (!clone) goto out_nomem; clone->next = head->next; head->next = clone; @@ -638,7 +639,8 @@ int ip_defrag(struct sk_buff *skb, u32 user) IP_INC_STATS_BH(net, IPSTATS_MIB_REASMREQDS); /* Lookup (or create) queue header */ - if ((qp = ip_find(net, ip_hdr(skb), user)) != NULL) { + qp = ip_find(net, ip_hdr(skb), user); + if (qp) { int ret; spin_lock(&qp->q.lock); @@ -754,7 +756,7 @@ static int __net_init ip4_frags_ns_ctl_register(struct net *net) table = ip4_frags_ns_ctl_table; if (!net_eq(net, &init_net)) { table = kmemdup(table, sizeof(ip4_frags_ns_ctl_table), GFP_KERNEL); - if (table == NULL) + if (!table) goto err_alloc; table[0].data = &net->ipv4.frags.high_thresh; @@ -770,7 +772,7 @@ static int __net_init ip4_frags_ns_ctl_register(struct net *net) } hdr = register_net_sysctl(net, "net/ipv4", table); - if (hdr == NULL) + if (!hdr) goto err_reg; net->ipv4.frags_hdr = hdr; diff --git a/net/ipv4/ip_gre.c b/net/ipv4/ip_gre.c index 6207275fc749..5fd706473c73 100644 --- a/net/ipv4/ip_gre.c +++ b/net/ipv4/ip_gre.c @@ -182,7 +182,7 @@ static int ipgre_err(struct sk_buff *skb, u32 info, t = ip_tunnel_lookup(itn, skb->dev->ifindex, tpi->flags, iph->daddr, iph->saddr, tpi->key); - if (t == NULL) + if (!t) return PACKET_REJECT; if (t->parms.iph.daddr == 0 || @@ -423,7 +423,7 @@ static int ipgre_open(struct net_device *dev) return -EADDRNOTAVAIL; dev = rt->dst.dev; ip_rt_put(rt); - if (__in_dev_get_rtnl(dev) == NULL) + if (!__in_dev_get_rtnl(dev)) return -EADDRNOTAVAIL; t->mlink = dev->ifindex; ip_mc_inc_group(__in_dev_get_rtnl(dev), t->parms.iph.daddr); @@ -456,6 +456,7 @@ static const struct net_device_ops ipgre_netdev_ops = { .ndo_do_ioctl = ipgre_tunnel_ioctl, .ndo_change_mtu = ip_tunnel_change_mtu, .ndo_get_stats64 = ip_tunnel_get_stats64, + .ndo_get_iflink = ip_tunnel_get_iflink, }; #define GRE_FEATURES (NETIF_F_SG | \ @@ -621,10 +622,10 @@ static void ipgre_netlink_parms(struct nlattr *data[], struct nlattr *tb[], parms->o_key = nla_get_be32(data[IFLA_GRE_OKEY]); if (data[IFLA_GRE_LOCAL]) - parms->iph.saddr = nla_get_be32(data[IFLA_GRE_LOCAL]); + parms->iph.saddr = nla_get_in_addr(data[IFLA_GRE_LOCAL]); if (data[IFLA_GRE_REMOTE]) - parms->iph.daddr = nla_get_be32(data[IFLA_GRE_REMOTE]); + parms->iph.daddr = nla_get_in_addr(data[IFLA_GRE_REMOTE]); if (data[IFLA_GRE_TTL]) parms->iph.ttl = nla_get_u8(data[IFLA_GRE_TTL]); @@ -686,6 +687,7 @@ static const struct net_device_ops gre_tap_netdev_ops = { .ndo_validate_addr = eth_validate_addr, .ndo_change_mtu = ip_tunnel_change_mtu, .ndo_get_stats64 = ip_tunnel_get_stats64, + .ndo_get_iflink = ip_tunnel_get_iflink, }; static void ipgre_tap_setup(struct net_device *dev) @@ -776,8 +778,8 @@ static int ipgre_fill_info(struct sk_buff *skb, const struct net_device *dev) nla_put_be16(skb, IFLA_GRE_OFLAGS, tnl_flags_to_gre_flags(p->o_flags)) || nla_put_be32(skb, IFLA_GRE_IKEY, p->i_key) || nla_put_be32(skb, IFLA_GRE_OKEY, p->o_key) || - nla_put_be32(skb, IFLA_GRE_LOCAL, p->iph.saddr) || - nla_put_be32(skb, IFLA_GRE_REMOTE, p->iph.daddr) || + nla_put_in_addr(skb, IFLA_GRE_LOCAL, p->iph.saddr) || + nla_put_in_addr(skb, IFLA_GRE_REMOTE, p->iph.daddr) || nla_put_u8(skb, IFLA_GRE_TTL, p->iph.ttl) || nla_put_u8(skb, IFLA_GRE_TOS, p->iph.tos) || nla_put_u8(skb, IFLA_GRE_PMTUDISC, diff --git a/net/ipv4/ip_input.c b/net/ipv4/ip_input.c index 3d4da2c16b6a..2db4c8773c1b 100644 --- a/net/ipv4/ip_input.c +++ b/net/ipv4/ip_input.c @@ -187,7 +187,7 @@ bool ip_call_ra_chain(struct sk_buff *skb) return false; } -static int ip_local_deliver_finish(struct sk_buff *skb) +static int ip_local_deliver_finish(struct sock *sk, struct sk_buff *skb) { struct net *net = dev_net(skb->dev); @@ -203,7 +203,7 @@ static int ip_local_deliver_finish(struct sk_buff *skb) raw = raw_local_deliver(skb, protocol); ipprot = rcu_dereference(inet_protos[protocol]); - if (ipprot != NULL) { + if (ipprot) { int ret; if (!ipprot->no_policy) { @@ -253,7 +253,8 @@ int ip_local_deliver(struct sk_buff *skb) return 0; } - return NF_HOOK(NFPROTO_IPV4, NF_INET_LOCAL_IN, skb, skb->dev, NULL, + return NF_HOOK(NFPROTO_IPV4, NF_INET_LOCAL_IN, NULL, skb, + skb->dev, NULL, ip_local_deliver_finish); } @@ -309,12 +310,12 @@ drop: int sysctl_ip_early_demux __read_mostly = 1; EXPORT_SYMBOL(sysctl_ip_early_demux); -static int ip_rcv_finish(struct sk_buff *skb) +static int ip_rcv_finish(struct sock *sk, struct sk_buff *skb) { const struct iphdr *iph = ip_hdr(skb); struct rtable *rt; - if (sysctl_ip_early_demux && !skb_dst(skb) && skb->sk == NULL) { + if (sysctl_ip_early_demux && !skb_dst(skb) && !skb->sk) { const struct net_protocol *ipprot; int protocol = iph->protocol; @@ -387,7 +388,8 @@ int ip_rcv(struct sk_buff *skb, struct net_device *dev, struct packet_type *pt, IP_UPD_PO_STATS_BH(dev_net(dev), IPSTATS_MIB_IN, skb->len); - if ((skb = skb_share_check(skb, GFP_ATOMIC)) == NULL) { + skb = skb_share_check(skb, GFP_ATOMIC); + if (!skb) { IP_INC_STATS_BH(dev_net(dev), IPSTATS_MIB_INDISCARDS); goto out; } @@ -450,7 +452,8 @@ int ip_rcv(struct sk_buff *skb, struct net_device *dev, struct packet_type *pt, /* Must drop socket now because of tproxy. */ skb_orphan(skb); - return NF_HOOK(NFPROTO_IPV4, NF_INET_PRE_ROUTING, skb, dev, NULL, + return NF_HOOK(NFPROTO_IPV4, NF_INET_PRE_ROUTING, NULL, skb, + dev, NULL, ip_rcv_finish); csum_error: diff --git a/net/ipv4/ip_options.c b/net/ipv4/ip_options.c index 5b3d91be2db0..bd246792360b 100644 --- a/net/ipv4/ip_options.c +++ b/net/ipv4/ip_options.c @@ -264,7 +264,7 @@ int ip_options_compile(struct net *net, unsigned char *iph; int optlen, l; - if (skb != NULL) { + if (skb) { rt = skb_rtable(skb); optptr = (unsigned char *)&(ip_hdr(skb)[1]); } else diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c index a7aea2048a0d..c65b93a7b711 100644 --- a/net/ipv4/ip_output.c +++ b/net/ipv4/ip_output.c @@ -91,14 +91,19 @@ void ip_send_check(struct iphdr *iph) } EXPORT_SYMBOL(ip_send_check); -int __ip_local_out(struct sk_buff *skb) +int __ip_local_out_sk(struct sock *sk, struct sk_buff *skb) { struct iphdr *iph = ip_hdr(skb); iph->tot_len = htons(skb->len); ip_send_check(iph); - return nf_hook(NFPROTO_IPV4, NF_INET_LOCAL_OUT, skb, NULL, - skb_dst(skb)->dev, dst_output); + return nf_hook(NFPROTO_IPV4, NF_INET_LOCAL_OUT, sk, skb, NULL, + skb_dst(skb)->dev, dst_output_sk); +} + +int __ip_local_out(struct sk_buff *skb) +{ + return __ip_local_out_sk(skb->sk, skb); } int ip_local_out_sk(struct sock *sk, struct sk_buff *skb) @@ -148,7 +153,7 @@ int ip_build_and_send_pkt(struct sk_buff *skb, struct sock *sk, iph->daddr = (opt && opt->opt.srr ? opt->opt.faddr : daddr); iph->saddr = saddr; iph->protocol = sk->sk_protocol; - ip_select_ident(skb, sk); + ip_select_ident(sock_net(sk), skb, sk); if (opt && opt->opt.optlen) { iph->ihl += opt->opt.optlen>>2; @@ -163,7 +168,7 @@ int ip_build_and_send_pkt(struct sk_buff *skb, struct sock *sk, } EXPORT_SYMBOL_GPL(ip_build_and_send_pkt); -static inline int ip_finish_output2(struct sk_buff *skb) +static inline int ip_finish_output2(struct sock *sk, struct sk_buff *skb) { struct dst_entry *dst = skb_dst(skb); struct rtable *rt = (struct rtable *)dst; @@ -182,7 +187,7 @@ static inline int ip_finish_output2(struct sk_buff *skb) struct sk_buff *skb2; skb2 = skb_realloc_headroom(skb, LL_RESERVED_SPACE(dev)); - if (skb2 == NULL) { + if (!skb2) { kfree_skb(skb); return -ENOMEM; } @@ -211,7 +216,7 @@ static inline int ip_finish_output2(struct sk_buff *skb) return -EINVAL; } -static int ip_finish_output_gso(struct sk_buff *skb) +static int ip_finish_output_gso(struct sock *sk, struct sk_buff *skb) { netdev_features_t features; struct sk_buff *segs; @@ -220,7 +225,7 @@ static int ip_finish_output_gso(struct sk_buff *skb) /* common case: locally created skb or seglen is <= mtu */ if (((IPCB(skb)->flags & IPSKB_FORWARDED) == 0) || skb_gso_network_seglen(skb) <= ip_skb_dst_mtu(skb)) - return ip_finish_output2(skb); + return ip_finish_output2(sk, skb); /* Slowpath - GSO segment length is exceeding the dst MTU. * @@ -243,7 +248,7 @@ static int ip_finish_output_gso(struct sk_buff *skb) int err; segs->next = NULL; - err = ip_fragment(segs, ip_finish_output2); + err = ip_fragment(sk, segs, ip_finish_output2); if (err && ret == 0) ret = err; @@ -253,22 +258,22 @@ static int ip_finish_output_gso(struct sk_buff *skb) return ret; } -static int ip_finish_output(struct sk_buff *skb) +static int ip_finish_output(struct sock *sk, struct sk_buff *skb) { #if defined(CONFIG_NETFILTER) && defined(CONFIG_XFRM) /* Policy lookup after SNAT yielded a new policy */ - if (skb_dst(skb)->xfrm != NULL) { + if (skb_dst(skb)->xfrm) { IPCB(skb)->flags |= IPSKB_REROUTED; - return dst_output(skb); + return dst_output_sk(sk, skb); } #endif if (skb_is_gso(skb)) - return ip_finish_output_gso(skb); + return ip_finish_output_gso(sk, skb); if (skb->len > ip_skb_dst_mtu(skb)) - return ip_fragment(skb, ip_finish_output2); + return ip_fragment(sk, skb, ip_finish_output2); - return ip_finish_output2(skb); + return ip_finish_output2(sk, skb); } int ip_mc_output(struct sock *sk, struct sk_buff *skb) @@ -307,7 +312,7 @@ int ip_mc_output(struct sock *sk, struct sk_buff *skb) struct sk_buff *newskb = skb_clone(skb, GFP_ATOMIC); if (newskb) NF_HOOK(NFPROTO_IPV4, NF_INET_POST_ROUTING, - newskb, NULL, newskb->dev, + sk, newskb, NULL, newskb->dev, dev_loopback_xmit); } @@ -322,11 +327,11 @@ int ip_mc_output(struct sock *sk, struct sk_buff *skb) if (rt->rt_flags&RTCF_BROADCAST) { struct sk_buff *newskb = skb_clone(skb, GFP_ATOMIC); if (newskb) - NF_HOOK(NFPROTO_IPV4, NF_INET_POST_ROUTING, newskb, + NF_HOOK(NFPROTO_IPV4, NF_INET_POST_ROUTING, sk, newskb, NULL, newskb->dev, dev_loopback_xmit); } - return NF_HOOK_COND(NFPROTO_IPV4, NF_INET_POST_ROUTING, skb, NULL, + return NF_HOOK_COND(NFPROTO_IPV4, NF_INET_POST_ROUTING, sk, skb, NULL, skb->dev, ip_finish_output, !(IPCB(skb)->flags & IPSKB_REROUTED)); } @@ -340,7 +345,8 @@ int ip_output(struct sock *sk, struct sk_buff *skb) skb->dev = dev; skb->protocol = htons(ETH_P_IP); - return NF_HOOK_COND(NFPROTO_IPV4, NF_INET_POST_ROUTING, skb, NULL, dev, + return NF_HOOK_COND(NFPROTO_IPV4, NF_INET_POST_ROUTING, sk, skb, + NULL, dev, ip_finish_output, !(IPCB(skb)->flags & IPSKB_REROUTED)); } @@ -376,12 +382,12 @@ int ip_queue_xmit(struct sock *sk, struct sk_buff *skb, struct flowi *fl) inet_opt = rcu_dereference(inet->inet_opt); fl4 = &fl->u.ip4; rt = skb_rtable(skb); - if (rt != NULL) + if (rt) goto packet_routed; /* Make sure we can route this packet. */ rt = (struct rtable *)__sk_dst_check(sk, 0); - if (rt == NULL) { + if (!rt) { __be32 daddr; /* Use correct destination address if we have options. */ @@ -430,7 +436,8 @@ packet_routed: ip_options_build(skb, &inet_opt->opt, inet->inet_daddr, rt, 0); } - ip_select_ident_segs(skb, sk, skb_shinfo(skb)->gso_segs ?: 1); + ip_select_ident_segs(sock_net(sk), skb, sk, + skb_shinfo(skb)->gso_segs ?: 1); /* TODO : should we use skb->sk here instead of sk ? */ skb->priority = sk->sk_priority; @@ -448,7 +455,6 @@ no_route: } EXPORT_SYMBOL(ip_queue_xmit); - static void ip_copy_metadata(struct sk_buff *to, struct sk_buff *from) { to->pkt_type = from->pkt_type; @@ -479,7 +485,8 @@ static void ip_copy_metadata(struct sk_buff *to, struct sk_buff *from) * single device frame, and queue such a frame for sending. */ -int ip_fragment(struct sk_buff *skb, int (*output)(struct sk_buff *)) +int ip_fragment(struct sock *sk, struct sk_buff *skb, + int (*output)(struct sock *, struct sk_buff *)) { struct iphdr *iph; int ptr; @@ -586,13 +593,13 @@ int ip_fragment(struct sk_buff *skb, int (*output)(struct sk_buff *)) ip_options_fragment(frag); offset += skb->len - hlen; iph->frag_off = htons(offset>>3); - if (frag->next != NULL) + if (frag->next) iph->frag_off |= htons(IP_MF); /* Ready, complete checksum */ ip_send_check(iph); } - err = output(skb); + err = output(sk, skb); if (!err) IP_INC_STATS(dev_net(dev), IPSTATS_MIB_FRAGCREATES); @@ -636,10 +643,7 @@ slow_path: left = skb->len - hlen; /* Space per frame */ ptr = hlen; /* Where to start from */ - /* for bridged IP traffic encapsulated inside f.e. a vlan header, - * we need to make room for the encapsulating header - */ - ll_rs = LL_RESERVED_SPACE_EXTRA(rt->dst.dev, nf_bridge_pad(skb)); + ll_rs = LL_RESERVED_SPACE(rt->dst.dev); /* * Fragment the datagram. @@ -732,7 +736,7 @@ slow_path: ip_send_check(iph); - err = output(skb2); + err = output(sk, skb2); if (err) goto fail; @@ -792,12 +796,13 @@ static inline int ip_ufo_append_data(struct sock *sk, * device, so create one single skb packet containing complete * udp datagram */ - if ((skb = skb_peek_tail(queue)) == NULL) { + skb = skb_peek_tail(queue); + if (!skb) { skb = sock_alloc_send_skb(sk, hh_len + fragheaderlen + transhdrlen + 20, (flags & MSG_DONTWAIT), &err); - if (skb == NULL) + if (!skb) return err; /* reserve space for Hardware header */ @@ -814,7 +819,6 @@ static inline int ip_ufo_append_data(struct sock *sk, skb->csum = 0; - __skb_queue_tail(queue, skb); } else if (skb_is_gso(skb)) { goto append; @@ -963,10 +967,10 @@ alloc_new_skb: skb = sock_wmalloc(sk, alloclen + hh_len + 15, 1, sk->sk_allocation); - if (unlikely(skb == NULL)) + if (unlikely(!skb)) err = -ENOBUFS; } - if (skb == NULL) + if (!skb) goto error; /* @@ -1090,10 +1094,10 @@ static int ip_setup_cork(struct sock *sk, struct inet_cork *cork, */ opt = ipc->opt; if (opt) { - if (cork->opt == NULL) { + if (!cork->opt) { cork->opt = kmalloc(sizeof(struct ip_options) + 40, sk->sk_allocation); - if (unlikely(cork->opt == NULL)) + if (unlikely(!cork->opt)) return -ENOBUFS; } memcpy(cork->opt, &opt->opt, sizeof(struct ip_options) + opt->opt.optlen); @@ -1200,7 +1204,8 @@ ssize_t ip_append_page(struct sock *sk, struct flowi4 *fl4, struct page *page, return -EMSGSIZE; } - if ((skb = skb_peek_tail(&sk->sk_write_queue)) == NULL) + skb = skb_peek_tail(&sk->sk_write_queue); + if (!skb) return -EINVAL; cork->length += size; @@ -1211,7 +1216,6 @@ ssize_t ip_append_page(struct sock *sk, struct flowi4 *fl4, struct page *page, skb_shinfo(skb)->gso_type = SKB_GSO_UDP; } - while (size > 0) { int i; @@ -1331,7 +1335,8 @@ struct sk_buff *__ip_make_skb(struct sock *sk, __be16 df = 0; __u8 ttl; - if ((skb = __skb_dequeue(queue)) == NULL) + skb = __skb_dequeue(queue); + if (!skb) goto out; tail_skb = &(skb_shinfo(skb)->frag_list); @@ -1382,7 +1387,7 @@ struct sk_buff *__ip_make_skb(struct sock *sk, iph->ttl = ttl; iph->protocol = sk->sk_protocol; ip_copy_addrs(iph, fl4); - ip_select_ident(skb, sk); + ip_select_ident(net, skb, sk); if (opt) { iph->ihl += opt->optlen>>2; diff --git a/net/ipv4/ip_sockglue.c b/net/ipv4/ip_sockglue.c index 5cd99271d3a6..7cfb0893f263 100644 --- a/net/ipv4/ip_sockglue.c +++ b/net/ipv4/ip_sockglue.c @@ -351,7 +351,7 @@ int ip_ra_control(struct sock *sk, unsigned char on, return 0; } } - if (new_ra == NULL) { + if (!new_ra) { spin_unlock_bh(&ip_ra_lock); return -ENOBUFS; } @@ -387,7 +387,7 @@ void ip_icmp_error(struct sock *sk, struct sk_buff *skb, int err, skb_network_header(skb); serr->port = port; - if (skb_pull(skb, payload - skb->data) != NULL) { + if (skb_pull(skb, payload - skb->data)) { skb_reset_transport_header(skb); if (sock_queue_err_skb(sk, skb) == 0) return; @@ -482,7 +482,7 @@ int ip_recv_error(struct sock *sk, struct msghdr *msg, int len, int *addr_len) err = -EAGAIN; skb = sock_dequeue_err_skb(sk); - if (skb == NULL) + if (!skb) goto out; copied = skb->len; @@ -536,12 +536,34 @@ out: * Socket option code for IP. This is the end of the line after any * TCP,UDP etc options on an IP socket. */ +static bool setsockopt_needs_rtnl(int optname) +{ + switch (optname) { + case IP_ADD_MEMBERSHIP: + case IP_ADD_SOURCE_MEMBERSHIP: + case IP_BLOCK_SOURCE: + case IP_DROP_MEMBERSHIP: + case IP_DROP_SOURCE_MEMBERSHIP: + case IP_MSFILTER: + case IP_UNBLOCK_SOURCE: + case MCAST_BLOCK_SOURCE: + case MCAST_MSFILTER: + case MCAST_JOIN_GROUP: + case MCAST_JOIN_SOURCE_GROUP: + case MCAST_LEAVE_GROUP: + case MCAST_LEAVE_SOURCE_GROUP: + case MCAST_UNBLOCK_SOURCE: + return true; + } + return false; +} static int do_ip_setsockopt(struct sock *sk, int level, int optname, char __user *optval, unsigned int optlen) { struct inet_sock *inet = inet_sk(sk); int val = 0, err; + bool needs_rtnl = setsockopt_needs_rtnl(optname); switch (optname) { case IP_PKTINFO: @@ -584,6 +606,8 @@ static int do_ip_setsockopt(struct sock *sk, int level, return ip_mroute_setsockopt(sk, optname, optval, optlen); err = 0; + if (needs_rtnl) + rtnl_lock(); lock_sock(sk); switch (optname) { @@ -1118,10 +1142,14 @@ mc_msf_out: break; } release_sock(sk); + if (needs_rtnl) + rtnl_unlock(); return err; e_inval: release_sock(sk); + if (needs_rtnl) + rtnl_unlock(); return -EINVAL; } diff --git a/net/ipv4/ip_tunnel.c b/net/ipv4/ip_tunnel.c index 2cd08280c77b..4c2c3ba4ba65 100644 --- a/net/ipv4/ip_tunnel.c +++ b/net/ipv4/ip_tunnel.c @@ -389,7 +389,6 @@ static int ip_tunnel_bind_dev(struct net_device *dev) hlen = tdev->hard_header_len + tdev->needed_headroom; mtu = tdev->mtu; } - dev->iflink = tunnel->parms.link; dev->needed_headroom = t_hlen + hlen; mtu -= (dev->hard_header_len + t_hlen); @@ -655,7 +654,7 @@ void ip_tunnel_xmit(struct sk_buff *skb, struct net_device *dev, if (dst == 0) { /* NBMA tunnel */ - if (skb_dst(skb) == NULL) { + if (!skb_dst(skb)) { dev->stats.tx_fifo_errors++; goto tx_error; } @@ -673,7 +672,7 @@ void ip_tunnel_xmit(struct sk_buff *skb, struct net_device *dev, neigh = dst_neigh_lookup(skb_dst(skb), &ipv6_hdr(skb)->daddr); - if (neigh == NULL) + if (!neigh) goto tx_error; addr6 = (const struct in6_addr *)&neigh->primary_key; @@ -783,7 +782,7 @@ void ip_tunnel_xmit(struct sk_buff *skb, struct net_device *dev, return; } - err = iptunnel_xmit(skb->sk, rt, skb, fl4.saddr, fl4.daddr, protocol, + err = iptunnel_xmit(NULL, rt, skb, fl4.saddr, fl4.daddr, protocol, tos, ttl, df, !net_eq(tunnel->net, dev_net(dev))); iptunnel_xmit_stats(err, &dev->stats, dev->tstats); @@ -844,7 +843,7 @@ int ip_tunnel_ioctl(struct net_device *dev, struct ip_tunnel_parm *p, int cmd) case SIOCGETTUNNEL: if (dev == itn->fb_tunnel_dev) { t = ip_tunnel_find(itn, p, itn->fb_tunnel_dev->type); - if (t == NULL) + if (!t) t = netdev_priv(dev); } memcpy(p, &t->parms, sizeof(*p)); @@ -877,7 +876,7 @@ int ip_tunnel_ioctl(struct net_device *dev, struct ip_tunnel_parm *p, int cmd) break; } if (dev != itn->fb_tunnel_dev && cmd == SIOCCHGTUNNEL) { - if (t != NULL) { + if (t) { if (t->dev != dev) { err = -EEXIST; break; @@ -915,7 +914,7 @@ int ip_tunnel_ioctl(struct net_device *dev, struct ip_tunnel_parm *p, int cmd) if (dev == itn->fb_tunnel_dev) { err = -ENOENT; t = ip_tunnel_find(itn, p, itn->fb_tunnel_dev->type); - if (t == NULL) + if (!t) goto done; err = -EPERM; if (t == netdev_priv(itn->fb_tunnel_dev)) @@ -980,6 +979,14 @@ struct net *ip_tunnel_get_link_net(const struct net_device *dev) } EXPORT_SYMBOL(ip_tunnel_get_link_net); +int ip_tunnel_get_iflink(const struct net_device *dev) +{ + struct ip_tunnel *tunnel = netdev_priv(dev); + + return tunnel->parms.link; +} +EXPORT_SYMBOL(ip_tunnel_get_iflink); + int ip_tunnel_init_net(struct net *net, int ip_tnl_net_id, struct rtnl_link_ops *ops, char *devname) { diff --git a/net/ipv4/ip_tunnel_core.c b/net/ipv4/ip_tunnel_core.c index 88c386cf7d85..ce63ab21b6cd 100644 --- a/net/ipv4/ip_tunnel_core.c +++ b/net/ipv4/ip_tunnel_core.c @@ -74,7 +74,8 @@ int iptunnel_xmit(struct sock *sk, struct rtable *rt, struct sk_buff *skb, iph->daddr = dst; iph->saddr = src; iph->ttl = ttl; - __ip_select_ident(iph, skb_shinfo(skb)->gso_segs ?: 1); + __ip_select_ident(dev_net(rt->dst.dev), iph, + skb_shinfo(skb)->gso_segs ?: 1); err = ip_local_out_sk(sk, skb); if (unlikely(net_xmit_eval(err))) diff --git a/net/ipv4/ip_vti.c b/net/ipv4/ip_vti.c index 94efe148181c..9f7269f3c54a 100644 --- a/net/ipv4/ip_vti.c +++ b/net/ipv4/ip_vti.c @@ -60,7 +60,7 @@ static int vti_input(struct sk_buff *skb, int nexthdr, __be32 spi, tunnel = ip_tunnel_lookup(itn, skb->dev->ifindex, TUNNEL_NO_KEY, iph->saddr, iph->daddr, 0); - if (tunnel != NULL) { + if (tunnel) { if (!xfrm4_policy_check(NULL, XFRM_POLICY_IN, skb)) goto drop; @@ -341,6 +341,7 @@ static const struct net_device_ops vti_netdev_ops = { .ndo_do_ioctl = vti_tunnel_ioctl, .ndo_change_mtu = ip_tunnel_change_mtu, .ndo_get_stats64 = ip_tunnel_get_stats64, + .ndo_get_iflink = ip_tunnel_get_iflink, }; static void vti_tunnel_setup(struct net_device *dev) @@ -361,7 +362,6 @@ static int vti_tunnel_init(struct net_device *dev) dev->hard_header_len = LL_MAX_HEADER + sizeof(struct iphdr); dev->mtu = ETH_DATA_LEN; dev->flags = IFF_NOARP; - dev->iflink = 0; dev->addr_len = 4; dev->features |= NETIF_F_LLTX; netif_keep_dst(dev); @@ -456,10 +456,10 @@ static void vti_netlink_parms(struct nlattr *data[], parms->o_key = nla_get_be32(data[IFLA_VTI_OKEY]); if (data[IFLA_VTI_LOCAL]) - parms->iph.saddr = nla_get_be32(data[IFLA_VTI_LOCAL]); + parms->iph.saddr = nla_get_in_addr(data[IFLA_VTI_LOCAL]); if (data[IFLA_VTI_REMOTE]) - parms->iph.daddr = nla_get_be32(data[IFLA_VTI_REMOTE]); + parms->iph.daddr = nla_get_in_addr(data[IFLA_VTI_REMOTE]); } @@ -505,8 +505,8 @@ static int vti_fill_info(struct sk_buff *skb, const struct net_device *dev) nla_put_u32(skb, IFLA_VTI_LINK, p->link); nla_put_be32(skb, IFLA_VTI_IKEY, p->i_key); nla_put_be32(skb, IFLA_VTI_OKEY, p->o_key); - nla_put_be32(skb, IFLA_VTI_LOCAL, p->iph.saddr); - nla_put_be32(skb, IFLA_VTI_REMOTE, p->iph.daddr); + nla_put_in_addr(skb, IFLA_VTI_LOCAL, p->iph.saddr); + nla_put_in_addr(skb, IFLA_VTI_REMOTE, p->iph.daddr); return 0; } diff --git a/net/ipv4/ipcomp.c b/net/ipv4/ipcomp.c index c0855d50a3fa..d97f4f2787f5 100644 --- a/net/ipv4/ipcomp.c +++ b/net/ipv4/ipcomp.c @@ -63,7 +63,7 @@ static struct xfrm_state *ipcomp_tunnel_create(struct xfrm_state *x) struct xfrm_state *t; t = xfrm_state_alloc(net); - if (t == NULL) + if (!t) goto out; t->id.proto = IPPROTO_IPIP; diff --git a/net/ipv4/ipconfig.c b/net/ipv4/ipconfig.c index b26376ef87f6..8e7328c6a390 100644 --- a/net/ipv4/ipconfig.c +++ b/net/ipv4/ipconfig.c @@ -504,7 +504,8 @@ ic_rarp_recv(struct sk_buff *skb, struct net_device *dev, struct packet_type *pt if (!net_eq(dev_net(dev), &init_net)) goto drop; - if ((skb = skb_share_check(skb, GFP_ATOMIC)) == NULL) + skb = skb_share_check(skb, GFP_ATOMIC); + if (!skb) return NET_RX_DROP; if (!pskb_may_pull(skb, sizeof(struct arphdr))) @@ -958,7 +959,8 @@ static int __init ic_bootp_recv(struct sk_buff *skb, struct net_device *dev, str if (skb->pkt_type == PACKET_OTHERHOST) goto drop; - if ((skb = skb_share_check(skb, GFP_ATOMIC)) == NULL) + skb = skb_share_check(skb, GFP_ATOMIC); + if (!skb) return NET_RX_DROP; if (!pskb_may_pull(skb, diff --git a/net/ipv4/ipip.c b/net/ipv4/ipip.c index 915d215a7d14..ff96396ebec5 100644 --- a/net/ipv4/ipip.c +++ b/net/ipv4/ipip.c @@ -144,7 +144,7 @@ static int ipip_err(struct sk_buff *skb, u32 info) err = -ENOENT; t = ip_tunnel_lookup(itn, skb->dev->ifindex, TUNNEL_NO_KEY, iph->daddr, iph->saddr, 0); - if (t == NULL) + if (!t) goto out; if (type == ICMP_DEST_UNREACH && code == ICMP_FRAG_NEEDED) { @@ -272,6 +272,7 @@ static const struct net_device_ops ipip_netdev_ops = { .ndo_do_ioctl = ipip_tunnel_ioctl, .ndo_change_mtu = ip_tunnel_change_mtu, .ndo_get_stats64 = ip_tunnel_get_stats64, + .ndo_get_iflink = ip_tunnel_get_iflink, }; #define IPIP_FEATURES (NETIF_F_SG | \ @@ -286,7 +287,6 @@ static void ipip_tunnel_setup(struct net_device *dev) dev->type = ARPHRD_TUNNEL; dev->flags = IFF_NOARP; - dev->iflink = 0; dev->addr_len = 4; dev->features |= NETIF_F_LLTX; netif_keep_dst(dev); @@ -325,10 +325,10 @@ static void ipip_netlink_parms(struct nlattr *data[], parms->link = nla_get_u32(data[IFLA_IPTUN_LINK]); if (data[IFLA_IPTUN_LOCAL]) - parms->iph.saddr = nla_get_be32(data[IFLA_IPTUN_LOCAL]); + parms->iph.saddr = nla_get_in_addr(data[IFLA_IPTUN_LOCAL]); if (data[IFLA_IPTUN_REMOTE]) - parms->iph.daddr = nla_get_be32(data[IFLA_IPTUN_REMOTE]); + parms->iph.daddr = nla_get_in_addr(data[IFLA_IPTUN_REMOTE]); if (data[IFLA_IPTUN_TTL]) { parms->iph.ttl = nla_get_u8(data[IFLA_IPTUN_TTL]); @@ -450,8 +450,8 @@ static int ipip_fill_info(struct sk_buff *skb, const struct net_device *dev) struct ip_tunnel_parm *parm = &tunnel->parms; if (nla_put_u32(skb, IFLA_IPTUN_LINK, parm->link) || - nla_put_be32(skb, IFLA_IPTUN_LOCAL, parm->iph.saddr) || - nla_put_be32(skb, IFLA_IPTUN_REMOTE, parm->iph.daddr) || + nla_put_in_addr(skb, IFLA_IPTUN_LOCAL, parm->iph.saddr) || + nla_put_in_addr(skb, IFLA_IPTUN_REMOTE, parm->iph.daddr) || nla_put_u8(skb, IFLA_IPTUN_TTL, parm->iph.ttl) || nla_put_u8(skb, IFLA_IPTUN_TOS, parm->iph.tos) || nla_put_u8(skb, IFLA_IPTUN_PMTUDISC, diff --git a/net/ipv4/ipmr.c b/net/ipv4/ipmr.c index fe54eba6d00d..3a2c0162c3ba 100644 --- a/net/ipv4/ipmr.c +++ b/net/ipv4/ipmr.c @@ -73,9 +73,7 @@ struct mr_table { struct list_head list; -#ifdef CONFIG_NET_NS - struct net *net; -#endif + possible_net_t net; u32 id; struct sock __rcu *mroute_sk; struct timer_list ipmr_expire_timer; @@ -191,7 +189,7 @@ static int ipmr_rule_action(struct fib_rule *rule, struct flowi *flp, } mrt = ipmr_get_table(rule->fr_net, rule->table); - if (mrt == NULL) + if (!mrt) return -EAGAIN; res->mrt = mrt; return 0; @@ -255,7 +253,7 @@ static int __net_init ipmr_rules_init(struct net *net) INIT_LIST_HEAD(&net->ipv4.mr_tables); mrt = ipmr_new_table(net, RT_TABLE_DEFAULT); - if (mrt == NULL) { + if (!mrt) { err = -ENOMEM; goto err1; } @@ -323,11 +321,11 @@ static struct mr_table *ipmr_new_table(struct net *net, u32 id) unsigned int i; mrt = ipmr_get_table(net, id); - if (mrt != NULL) + if (mrt) return mrt; mrt = kzalloc(sizeof(*mrt), GFP_KERNEL); - if (mrt == NULL) + if (!mrt) return NULL; write_pnet(&mrt->net, net); mrt->id = id; @@ -429,7 +427,7 @@ struct net_device *ipmr_new_tunnel(struct net *net, struct vifctl *v) dev->flags |= IFF_MULTICAST; in_dev = __in_dev_get_rtnl(dev); - if (in_dev == NULL) + if (!in_dev) goto failure; ipv4_devconf_setall(in_dev); @@ -480,8 +478,14 @@ static netdev_tx_t reg_vif_xmit(struct sk_buff *skb, struct net_device *dev) return NETDEV_TX_OK; } +static int reg_vif_get_iflink(const struct net_device *dev) +{ + return 0; +} + static const struct net_device_ops reg_vif_netdev_ops = { .ndo_start_xmit = reg_vif_xmit, + .ndo_get_iflink = reg_vif_get_iflink, }; static void reg_vif_setup(struct net_device *dev) @@ -507,7 +511,7 @@ static struct net_device *ipmr_reg_vif(struct net *net, struct mr_table *mrt) dev = alloc_netdev(0, name, NET_NAME_UNKNOWN, reg_vif_setup); - if (dev == NULL) + if (!dev) return NULL; dev_net_set(dev, net); @@ -516,7 +520,6 @@ static struct net_device *ipmr_reg_vif(struct net *net, struct mr_table *mrt) free_netdev(dev); return NULL; } - dev->iflink = 0; rcu_read_lock(); in_dev = __in_dev_get_rcu(dev); @@ -764,7 +767,7 @@ static int vif_add(struct net *net, struct mr_table *mrt, case 0: if (vifc->vifc_flags == VIFF_USE_IFINDEX) { dev = dev_get_by_index(net, vifc->vifc_lcl_ifindex); - if (dev && __in_dev_get_rtnl(dev) == NULL) { + if (dev && !__in_dev_get_rtnl(dev)) { dev_put(dev); return -EADDRNOTAVAIL; } @@ -808,7 +811,7 @@ static int vif_add(struct net *net, struct mr_table *mrt, v->pkt_out = 0; v->link = dev->ifindex; if (v->flags & (VIFF_TUNNEL | VIFF_REGISTER)) - v->link = dev->iflink; + v->link = dev_get_iflink(dev); /* And finish update writing critical data */ write_lock_bh(&mrt_lock); @@ -1010,7 +1013,7 @@ static int ipmr_cache_report(struct mr_table *mrt, rcu_read_lock(); mroute_sk = rcu_dereference(mrt->mroute_sk); - if (mroute_sk == NULL) { + if (!mroute_sk) { rcu_read_unlock(); kfree_skb(skb); return -EINVAL; @@ -1163,7 +1166,7 @@ static int ipmr_mfc_add(struct net *net, struct mr_table *mrt, return -EINVAL; c = ipmr_cache_alloc(); - if (c == NULL) + if (!c) return -ENOMEM; c->mfc_origin = mfc->mfcc_origin.s_addr; @@ -1285,7 +1288,7 @@ int ip_mroute_setsockopt(struct sock *sk, int optname, char __user *optval, unsi return -EOPNOTSUPP; mrt = ipmr_get_table(net, raw_sk(sk)->ipmr_table ? : RT_TABLE_DEFAULT); - if (mrt == NULL) + if (!mrt) return -ENOENT; if (optname != MRT_INIT) { @@ -1448,7 +1451,7 @@ int ip_mroute_getsockopt(struct sock *sk, int optname, char __user *optval, int return -EOPNOTSUPP; mrt = ipmr_get_table(net, raw_sk(sk)->ipmr_table ? : RT_TABLE_DEFAULT); - if (mrt == NULL) + if (!mrt) return -ENOENT; if (optname != MRT_VERSION && @@ -1494,7 +1497,7 @@ int ipmr_ioctl(struct sock *sk, int cmd, void __user *arg) struct mr_table *mrt; mrt = ipmr_get_table(net, raw_sk(sk)->ipmr_table ? : RT_TABLE_DEFAULT); - if (mrt == NULL) + if (!mrt) return -ENOENT; switch (cmd) { @@ -1568,7 +1571,7 @@ int ipmr_compat_ioctl(struct sock *sk, unsigned int cmd, void __user *arg) struct mr_table *mrt; mrt = ipmr_get_table(net, raw_sk(sk)->ipmr_table ? : RT_TABLE_DEFAULT); - if (mrt == NULL) + if (!mrt) return -ENOENT; switch (cmd) { @@ -1649,7 +1652,8 @@ static struct notifier_block ip_mr_notifier = { * important for multicast video. */ -static void ip_encap(struct sk_buff *skb, __be32 saddr, __be32 daddr) +static void ip_encap(struct net *net, struct sk_buff *skb, + __be32 saddr, __be32 daddr) { struct iphdr *iph; const struct iphdr *old_iph = ip_hdr(skb); @@ -1668,14 +1672,14 @@ static void ip_encap(struct sk_buff *skb, __be32 saddr, __be32 daddr) iph->protocol = IPPROTO_IPIP; iph->ihl = 5; iph->tot_len = htons(skb->len); - ip_select_ident(skb, NULL); + ip_select_ident(net, skb, NULL); ip_send_check(iph); memset(&(IPCB(skb)->opt), 0, sizeof(IPCB(skb)->opt)); nf_reset(skb); } -static inline int ipmr_forward_finish(struct sk_buff *skb) +static inline int ipmr_forward_finish(struct sock *sk, struct sk_buff *skb) { struct ip_options *opt = &(IPCB(skb)->opt); @@ -1685,7 +1689,7 @@ static inline int ipmr_forward_finish(struct sk_buff *skb) if (unlikely(opt->optlen)) ip_forward_options(skb); - return dst_output(skb); + return dst_output_sk(sk, skb); } /* @@ -1702,7 +1706,7 @@ static void ipmr_queue_xmit(struct net *net, struct mr_table *mrt, struct flowi4 fl4; int encap = 0; - if (vif->dev == NULL) + if (!vif->dev) goto out_free; #ifdef CONFIG_IP_PIMSM @@ -1765,7 +1769,7 @@ static void ipmr_queue_xmit(struct net *net, struct mr_table *mrt, * What do we do with netfilter? -- RR */ if (vif->flags & VIFF_TUNNEL) { - ip_encap(skb, vif->local, vif->remote); + ip_encap(net, skb, vif->local, vif->remote); /* FIXME: extra output firewall step used to be here. --RR */ vif->dev->stats.tx_packets++; vif->dev->stats.tx_bytes += skb->len; @@ -1784,7 +1788,8 @@ static void ipmr_queue_xmit(struct net *net, struct mr_table *mrt, * not mrouter) cannot join to more than one interface - it will * result in receiving multiple packets. */ - NF_HOOK(NFPROTO_IPV4, NF_INET_FORWARD, skb, skb->dev, dev, + NF_HOOK(NFPROTO_IPV4, NF_INET_FORWARD, NULL, skb, + skb->dev, dev, ipmr_forward_finish); return; @@ -1993,7 +1998,7 @@ int ip_mr_input(struct sk_buff *skb) /* already under rcu_read_lock() */ cache = ipmr_cache_find(mrt, ip_hdr(skb)->saddr, ip_hdr(skb)->daddr); - if (cache == NULL) { + if (!cache) { int vif = ipmr_find_vif(mrt, skb->dev); if (vif >= 0) @@ -2004,13 +2009,13 @@ int ip_mr_input(struct sk_buff *skb) /* * No usable cache entry */ - if (cache == NULL) { + if (!cache) { int vif; if (local) { struct sk_buff *skb2 = skb_clone(skb, GFP_ATOMIC); ip_local_deliver(skb); - if (skb2 == NULL) + if (!skb2) return -ENOBUFS; skb = skb2; } @@ -2069,7 +2074,7 @@ static int __pim_rcv(struct mr_table *mrt, struct sk_buff *skb, reg_dev = mrt->vif_table[mrt->mroute_reg_vif_num].dev; read_unlock(&mrt_lock); - if (reg_dev == NULL) + if (!reg_dev) return 1; skb->mac_header = skb->network_header; @@ -2199,18 +2204,18 @@ int ipmr_get_route(struct net *net, struct sk_buff *skb, int err; mrt = ipmr_get_table(net, RT_TABLE_DEFAULT); - if (mrt == NULL) + if (!mrt) return -ENOENT; rcu_read_lock(); cache = ipmr_cache_find(mrt, saddr, daddr); - if (cache == NULL && skb->dev) { + if (!cache && skb->dev) { int vif = ipmr_find_vif(mrt, skb->dev); if (vif >= 0) cache = ipmr_cache_find_any(mrt, daddr, vif); } - if (cache == NULL) { + if (!cache) { struct sk_buff *skb2; struct iphdr *iph; struct net_device *dev; @@ -2268,7 +2273,7 @@ static int ipmr_fill_mroute(struct mr_table *mrt, struct sk_buff *skb, int err; nlh = nlmsg_put(skb, portid, seq, cmd, sizeof(*rtm), flags); - if (nlh == NULL) + if (!nlh) return -EMSGSIZE; rtm = nlmsg_data(nlh); @@ -2287,8 +2292,8 @@ static int ipmr_fill_mroute(struct mr_table *mrt, struct sk_buff *skb, rtm->rtm_protocol = RTPROT_MROUTED; rtm->rtm_flags = 0; - if (nla_put_be32(skb, RTA_SRC, c->mfc_origin) || - nla_put_be32(skb, RTA_DST, c->mfc_mcastgrp)) + if (nla_put_in_addr(skb, RTA_SRC, c->mfc_origin) || + nla_put_in_addr(skb, RTA_DST, c->mfc_mcastgrp)) goto nla_put_failure; err = __ipmr_fill_mroute(mrt, skb, c, rtm); /* do not break the dump if cache is unresolved */ @@ -2333,7 +2338,7 @@ static void mroute_netlink_event(struct mr_table *mrt, struct mfc_cache *mfc, skb = nlmsg_new(mroute_msgsize(mfc->mfc_parent >= MAXVIFS, mrt->maxvif), GFP_ATOMIC); - if (skb == NULL) + if (!skb) goto errout; err = ipmr_fill_mroute(mrt, skb, 0, 0, mfc, cmd, 0); @@ -2448,7 +2453,7 @@ static void *ipmr_vif_seq_start(struct seq_file *seq, loff_t *pos) struct mr_table *mrt; mrt = ipmr_get_table(net, RT_TABLE_DEFAULT); - if (mrt == NULL) + if (!mrt) return ERR_PTR(-ENOENT); iter->mrt = mrt; @@ -2567,7 +2572,7 @@ static void *ipmr_mfc_seq_start(struct seq_file *seq, loff_t *pos) struct mr_table *mrt; mrt = ipmr_get_table(net, RT_TABLE_DEFAULT); - if (mrt == NULL) + if (!mrt) return ERR_PTR(-ENOENT); it->mrt = mrt; diff --git a/net/ipv4/netfilter.c b/net/ipv4/netfilter.c index 7ebd6e37875c..65de0684e22a 100644 --- a/net/ipv4/netfilter.c +++ b/net/ipv4/netfilter.c @@ -94,7 +94,7 @@ static void nf_ip_saveroute(const struct sk_buff *skb, { struct ip_rt_info *rt_info = nf_queue_entry_reroute(entry); - if (entry->hook == NF_INET_LOCAL_OUT) { + if (entry->state.hook == NF_INET_LOCAL_OUT) { const struct iphdr *iph = ip_hdr(skb); rt_info->tos = iph->tos; @@ -109,7 +109,7 @@ static int nf_ip_reroute(struct sk_buff *skb, { const struct ip_rt_info *rt_info = nf_queue_entry_reroute(entry); - if (entry->hook == NF_INET_LOCAL_OUT) { + if (entry->state.hook == NF_INET_LOCAL_OUT) { const struct iphdr *iph = ip_hdr(skb); if (!(iph->tos == rt_info->tos && diff --git a/net/ipv4/netfilter/Kconfig b/net/ipv4/netfilter/Kconfig index 59f883d9cadf..fb20f363151f 100644 --- a/net/ipv4/netfilter/Kconfig +++ b/net/ipv4/netfilter/Kconfig @@ -36,24 +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 +if NF_TABLES config NF_TABLES_IPV4 - depends on NF_TABLES tristate "IPv4 nf_tables support" help This option enables the IPv4 support for nf_tables. +if NF_TABLES_IPV4 + config NFT_CHAIN_ROUTE_IPV4 - depends on NF_TABLES_IPV4 tristate "IPv4 nf_tables route chain support" help This option enables the "route" chain for IPv4 in nf_tables. This @@ -61,22 +53,34 @@ config NFT_CHAIN_ROUTE_IPV4 fields such as the source, destination, type of service and the packet mark. -config NF_REJECT_IPV4 - tristate "IPv4 packet rejection" - default m if NETFILTER_ADVANCED=n - config NFT_REJECT_IPV4 - depends on NF_TABLES_IPV4 select NF_REJECT_IPV4 default NFT_REJECT tristate +endif # NF_TABLES_IPV4 + config NF_TABLES_ARP - depends on NF_TABLES tristate "ARP nf_tables support" help This option enables the ARP support for nf_tables. +endif # NF_TABLES + +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_REJECT_IPV4 + tristate "IPv4 packet rejection" + default m if NETFILTER_ADVANCED=n + config NF_NAT_IPV4 tristate "IPv4 NAT" depends on NF_CONNTRACK_IPV4 diff --git a/net/ipv4/netfilter/arp_tables.c b/net/ipv4/netfilter/arp_tables.c index f95b6f93814b..13bfe84bf3ca 100644 --- a/net/ipv4/netfilter/arp_tables.c +++ b/net/ipv4/netfilter/arp_tables.c @@ -248,8 +248,7 @@ struct arpt_entry *arpt_next_entry(const struct arpt_entry *entry) unsigned int arpt_do_table(struct sk_buff *skb, unsigned int hook, - const struct net_device *in, - const struct net_device *out, + const struct nf_hook_state *state, struct xt_table *table) { static const char nulldevname[IFNAMSIZ] __attribute__((aligned(sizeof(long)))); @@ -265,8 +264,8 @@ unsigned int arpt_do_table(struct sk_buff *skb, if (!pskb_may_pull(skb, arp_hdr_len(skb->dev))) return NF_DROP; - indev = in ? in->name : nulldevname; - outdev = out ? out->name : nulldevname; + indev = state->in ? state->in->name : nulldevname; + outdev = state->out ? state->out->name : nulldevname; local_bh_disable(); addend = xt_write_recseq_begin(); @@ -281,8 +280,8 @@ unsigned int arpt_do_table(struct sk_buff *skb, e = get_entry(table_base, private->hook_entry[hook]); back = get_entry(table_base, private->underflow[hook]); - acpar.in = in; - acpar.out = out; + acpar.in = state->in; + acpar.out = state->out; acpar.hooknum = hook; acpar.family = NFPROTO_ARP; acpar.hotdrop = false; diff --git a/net/ipv4/netfilter/arptable_filter.c b/net/ipv4/netfilter/arptable_filter.c index 802ddecb30b8..93876d03120c 100644 --- a/net/ipv4/netfilter/arptable_filter.c +++ b/net/ipv4/netfilter/arptable_filter.c @@ -28,12 +28,11 @@ static const struct xt_table packet_filter = { /* The work comes in here from netfilter.c */ static unsigned int arptable_filter_hook(const struct nf_hook_ops *ops, struct sk_buff *skb, - const struct net_device *in, const struct net_device *out, - int (*okfn)(struct sk_buff *)) + const struct nf_hook_state *state) { - const struct net *net = dev_net((in != NULL) ? in : out); + const struct net *net = dev_net(state->in ? state->in : state->out); - return arpt_do_table(skb, ops->hooknum, in, out, + return arpt_do_table(skb, ops->hooknum, state, net->ipv4.arptable_filter); } diff --git a/net/ipv4/netfilter/ip_tables.c b/net/ipv4/netfilter/ip_tables.c index cf5e82f39d3b..c69db7fa25ee 100644 --- a/net/ipv4/netfilter/ip_tables.c +++ b/net/ipv4/netfilter/ip_tables.c @@ -288,8 +288,7 @@ struct ipt_entry *ipt_next_entry(const struct ipt_entry *entry) unsigned int ipt_do_table(struct sk_buff *skb, unsigned int hook, - const struct net_device *in, - const struct net_device *out, + const struct nf_hook_state *state, struct xt_table *table) { static const char nulldevname[IFNAMSIZ] __attribute__((aligned(sizeof(long)))); @@ -306,8 +305,8 @@ ipt_do_table(struct sk_buff *skb, /* Initialization */ ip = ip_hdr(skb); - indev = in ? in->name : nulldevname; - outdev = out ? out->name : nulldevname; + indev = state->in ? state->in->name : nulldevname; + outdev = state->out ? state->out->name : nulldevname; /* We handle fragments by dealing with the first fragment as * if it was a normal packet. All other fragments are treated * normally, except that they will NEVER match rules that ask @@ -317,8 +316,8 @@ ipt_do_table(struct sk_buff *skb, acpar.fragoff = ntohs(ip->frag_off) & IP_OFFSET; acpar.thoff = ip_hdrlen(skb); acpar.hotdrop = false; - acpar.in = in; - acpar.out = out; + acpar.in = state->in; + acpar.out = state->out; acpar.family = NFPROTO_IPV4; acpar.hooknum = hook; @@ -370,7 +369,7 @@ ipt_do_table(struct sk_buff *skb, #if IS_ENABLED(CONFIG_NETFILTER_XT_TARGET_TRACE) /* The packet is traced: log it */ if (unlikely(skb->nf_trace)) - trace_packet(skb, hook, in, out, + trace_packet(skb, hook, state->in, state->out, table->name, private, e); #endif /* Standard target? */ diff --git a/net/ipv4/netfilter/ipt_CLUSTERIP.c b/net/ipv4/netfilter/ipt_CLUSTERIP.c index e90f83a3415b..771ab3d01ad3 100644 --- a/net/ipv4/netfilter/ipt_CLUSTERIP.c +++ b/net/ipv4/netfilter/ipt_CLUSTERIP.c @@ -418,6 +418,13 @@ static int clusterip_tg_check(const struct xt_tgchk_param *par) if (ret < 0) pr_info("cannot load conntrack support for proto=%u\n", par->family); + + if (!par->net->xt.clusterip_deprecated_warning) { + pr_info("ipt_CLUSTERIP is deprecated and it will removed soon, " + "use xt_cluster instead\n"); + par->net->xt.clusterip_deprecated_warning = true; + } + return ret; } @@ -497,14 +504,12 @@ static void arp_print(struct arp_payload *payload) static unsigned int arp_mangle(const struct nf_hook_ops *ops, struct sk_buff *skb, - const struct net_device *in, - const struct net_device *out, - int (*okfn)(struct sk_buff *)) + const struct nf_hook_state *state) { struct arphdr *arp = arp_hdr(skb); struct arp_payload *payload; struct clusterip_config *c; - struct net *net = dev_net(in ? in : out); + struct net *net = dev_net(state->in ? state->in : state->out); /* we don't care about non-ethernet and non-ipv4 ARP */ if (arp->ar_hrd != htons(ARPHRD_ETHER) || @@ -529,10 +534,10 @@ arp_mangle(const struct nf_hook_ops *ops, * addresses on different interfacs. However, in the CLUSTERIP case * this wouldn't work, since we didn't subscribe the mcast group on * other interfaces */ - if (c->dev != out) { + if (c->dev != state->out) { pr_debug("not mangling arp reply on different " "interface: cip'%s'-skb'%s'\n", - c->dev->name, out->name); + c->dev->name, state->out->name); clusterip_config_put(c); return NF_ACCEPT; } diff --git a/net/ipv4/netfilter/ipt_REJECT.c b/net/ipv4/netfilter/ipt_REJECT.c index 8f48f5517e33..87907d4bd259 100644 --- a/net/ipv4/netfilter/ipt_REJECT.c +++ b/net/ipv4/netfilter/ipt_REJECT.c @@ -34,31 +34,32 @@ static unsigned int reject_tg(struct sk_buff *skb, const struct xt_action_param *par) { const struct ipt_reject_info *reject = par->targinfo; + int hook = par->hooknum; switch (reject->with) { case IPT_ICMP_NET_UNREACHABLE: - nf_send_unreach(skb, ICMP_NET_UNREACH); + nf_send_unreach(skb, ICMP_NET_UNREACH, hook); break; case IPT_ICMP_HOST_UNREACHABLE: - nf_send_unreach(skb, ICMP_HOST_UNREACH); + nf_send_unreach(skb, ICMP_HOST_UNREACH, hook); break; case IPT_ICMP_PROT_UNREACHABLE: - nf_send_unreach(skb, ICMP_PROT_UNREACH); + nf_send_unreach(skb, ICMP_PROT_UNREACH, hook); break; case IPT_ICMP_PORT_UNREACHABLE: - nf_send_unreach(skb, ICMP_PORT_UNREACH); + nf_send_unreach(skb, ICMP_PORT_UNREACH, hook); break; case IPT_ICMP_NET_PROHIBITED: - nf_send_unreach(skb, ICMP_NET_ANO); + nf_send_unreach(skb, ICMP_NET_ANO, hook); break; case IPT_ICMP_HOST_PROHIBITED: - nf_send_unreach(skb, ICMP_HOST_ANO); + nf_send_unreach(skb, ICMP_HOST_ANO, hook); break; case IPT_ICMP_ADMIN_PROHIBITED: - nf_send_unreach(skb, ICMP_PKT_FILTERED); + nf_send_unreach(skb, ICMP_PKT_FILTERED, hook); break; case IPT_TCP_RESET: - nf_send_reset(skb, par->hooknum); + nf_send_reset(skb, hook); case IPT_ICMP_ECHOREPLY: /* Doesn't happen. */ break; diff --git a/net/ipv4/netfilter/ipt_SYNPROXY.c b/net/ipv4/netfilter/ipt_SYNPROXY.c index a313c3fbeb46..e9e67793055f 100644 --- a/net/ipv4/netfilter/ipt_SYNPROXY.c +++ b/net/ipv4/netfilter/ipt_SYNPROXY.c @@ -300,11 +300,9 @@ synproxy_tg4(struct sk_buff *skb, const struct xt_action_param *par) static unsigned int ipv4_synproxy_hook(const struct nf_hook_ops *ops, struct sk_buff *skb, - const struct net_device *in, - const struct net_device *out, - int (*okfn)(struct sk_buff *)) + const struct nf_hook_state *nhs) { - struct synproxy_net *snet = synproxy_pernet(dev_net(in ? : out)); + struct synproxy_net *snet = synproxy_pernet(dev_net(nhs->in ? : nhs->out)); enum ip_conntrack_info ctinfo; struct nf_conn *ct; struct nf_conn_synproxy *synproxy; diff --git a/net/ipv4/netfilter/iptable_filter.c b/net/ipv4/netfilter/iptable_filter.c index e08a74a243a8..a0f3beca52d2 100644 --- a/net/ipv4/netfilter/iptable_filter.c +++ b/net/ipv4/netfilter/iptable_filter.c @@ -34,8 +34,7 @@ static const struct xt_table packet_filter = { static unsigned int iptable_filter_hook(const struct nf_hook_ops *ops, struct sk_buff *skb, - const struct net_device *in, const struct net_device *out, - int (*okfn)(struct sk_buff *)) + const struct nf_hook_state *state) { const struct net *net; @@ -45,9 +44,8 @@ iptable_filter_hook(const struct nf_hook_ops *ops, struct sk_buff *skb, /* root is playing with raw sockets. */ return NF_ACCEPT; - net = dev_net((in != NULL) ? in : out); - return ipt_do_table(skb, ops->hooknum, in, out, - net->ipv4.iptable_filter); + net = dev_net(state->in ? state->in : state->out); + return ipt_do_table(skb, ops->hooknum, state, net->ipv4.iptable_filter); } static struct nf_hook_ops *filter_ops __read_mostly; diff --git a/net/ipv4/netfilter/iptable_mangle.c b/net/ipv4/netfilter/iptable_mangle.c index 6a5079c34bb3..62cbb8c5f4a8 100644 --- a/net/ipv4/netfilter/iptable_mangle.c +++ b/net/ipv4/netfilter/iptable_mangle.c @@ -37,8 +37,9 @@ static const struct xt_table packet_mangler = { }; static unsigned int -ipt_mangle_out(struct sk_buff *skb, const struct net_device *out) +ipt_mangle_out(struct sk_buff *skb, const struct nf_hook_state *state) { + struct net_device *out = state->out; unsigned int ret; const struct iphdr *iph; u_int8_t tos; @@ -58,7 +59,7 @@ ipt_mangle_out(struct sk_buff *skb, const struct net_device *out) daddr = iph->daddr; tos = iph->tos; - ret = ipt_do_table(skb, NF_INET_LOCAL_OUT, NULL, out, + ret = ipt_do_table(skb, NF_INET_LOCAL_OUT, state, dev_net(out)->ipv4.iptable_mangle); /* Reroute for ANY change. */ if (ret != NF_DROP && ret != NF_STOLEN) { @@ -81,18 +82,16 @@ ipt_mangle_out(struct sk_buff *skb, const struct net_device *out) static unsigned int iptable_mangle_hook(const struct nf_hook_ops *ops, struct sk_buff *skb, - const struct net_device *in, - const struct net_device *out, - int (*okfn)(struct sk_buff *)) + const struct nf_hook_state *state) { if (ops->hooknum == NF_INET_LOCAL_OUT) - return ipt_mangle_out(skb, out); + return ipt_mangle_out(skb, state); if (ops->hooknum == NF_INET_POST_ROUTING) - return ipt_do_table(skb, ops->hooknum, in, out, - dev_net(out)->ipv4.iptable_mangle); + return ipt_do_table(skb, ops->hooknum, state, + dev_net(state->out)->ipv4.iptable_mangle); /* PREROUTING/INPUT/FORWARD: */ - return ipt_do_table(skb, ops->hooknum, in, out, - dev_net(in)->ipv4.iptable_mangle); + return ipt_do_table(skb, ops->hooknum, state, + dev_net(state->in)->ipv4.iptable_mangle); } static struct nf_hook_ops *mangle_ops __read_mostly; diff --git a/net/ipv4/netfilter/iptable_nat.c b/net/ipv4/netfilter/iptable_nat.c index 6b67d7e9a75d..0d4d9cdf98a4 100644 --- a/net/ipv4/netfilter/iptable_nat.c +++ b/net/ipv4/netfilter/iptable_nat.c @@ -30,49 +30,40 @@ static const struct xt_table nf_nat_ipv4_table = { static unsigned int iptable_nat_do_chain(const struct nf_hook_ops *ops, struct sk_buff *skb, - const struct net_device *in, - const struct net_device *out, + const struct nf_hook_state *state, struct nf_conn *ct) { struct net *net = nf_ct_net(ct); - return ipt_do_table(skb, ops->hooknum, in, out, net->ipv4.nat_table); + return ipt_do_table(skb, ops->hooknum, state, net->ipv4.nat_table); } static unsigned int iptable_nat_ipv4_fn(const struct nf_hook_ops *ops, struct sk_buff *skb, - const struct net_device *in, - const struct net_device *out, - int (*okfn)(struct sk_buff *)) + const struct nf_hook_state *state) { - return nf_nat_ipv4_fn(ops, skb, in, out, iptable_nat_do_chain); + return nf_nat_ipv4_fn(ops, skb, state, iptable_nat_do_chain); } static unsigned int iptable_nat_ipv4_in(const struct nf_hook_ops *ops, struct sk_buff *skb, - const struct net_device *in, - const struct net_device *out, - int (*okfn)(struct sk_buff *)) + const struct nf_hook_state *state) { - return nf_nat_ipv4_in(ops, skb, in, out, iptable_nat_do_chain); + return nf_nat_ipv4_in(ops, skb, state, iptable_nat_do_chain); } static unsigned int iptable_nat_ipv4_out(const struct nf_hook_ops *ops, struct sk_buff *skb, - const struct net_device *in, - const struct net_device *out, - int (*okfn)(struct sk_buff *)) + const struct nf_hook_state *state) { - return nf_nat_ipv4_out(ops, skb, in, out, iptable_nat_do_chain); + return nf_nat_ipv4_out(ops, skb, state, iptable_nat_do_chain); } static unsigned int iptable_nat_ipv4_local_fn(const struct nf_hook_ops *ops, struct sk_buff *skb, - const struct net_device *in, - const struct net_device *out, - int (*okfn)(struct sk_buff *)) + const struct nf_hook_state *state) { - return nf_nat_ipv4_local_fn(ops, skb, in, out, iptable_nat_do_chain); + return nf_nat_ipv4_local_fn(ops, skb, state, iptable_nat_do_chain); } static struct nf_hook_ops nf_nat_ipv4_ops[] __read_mostly = { diff --git a/net/ipv4/netfilter/iptable_raw.c b/net/ipv4/netfilter/iptable_raw.c index b2f7e8f98316..0356e6da4bb7 100644 --- a/net/ipv4/netfilter/iptable_raw.c +++ b/net/ipv4/netfilter/iptable_raw.c @@ -21,8 +21,7 @@ static const struct xt_table packet_raw = { /* The work comes in here from netfilter.c. */ static unsigned int iptable_raw_hook(const struct nf_hook_ops *ops, struct sk_buff *skb, - const struct net_device *in, const struct net_device *out, - int (*okfn)(struct sk_buff *)) + const struct nf_hook_state *state) { const struct net *net; @@ -32,8 +31,8 @@ iptable_raw_hook(const struct nf_hook_ops *ops, struct sk_buff *skb, /* root is playing with raw sockets. */ return NF_ACCEPT; - net = dev_net((in != NULL) ? in : out); - return ipt_do_table(skb, ops->hooknum, in, out, net->ipv4.iptable_raw); + net = dev_net(state->in ? state->in : state->out); + return ipt_do_table(skb, ops->hooknum, state, net->ipv4.iptable_raw); } static struct nf_hook_ops *rawtable_ops __read_mostly; diff --git a/net/ipv4/netfilter/iptable_security.c b/net/ipv4/netfilter/iptable_security.c index c86647ed2078..4bce3980ccd9 100644 --- a/net/ipv4/netfilter/iptable_security.c +++ b/net/ipv4/netfilter/iptable_security.c @@ -38,9 +38,7 @@ static const struct xt_table security_table = { static unsigned int iptable_security_hook(const struct nf_hook_ops *ops, struct sk_buff *skb, - const struct net_device *in, - const struct net_device *out, - int (*okfn)(struct sk_buff *)) + const struct nf_hook_state *state) { const struct net *net; @@ -50,8 +48,8 @@ iptable_security_hook(const struct nf_hook_ops *ops, struct sk_buff *skb, /* Somebody is playing with raw sockets. */ return NF_ACCEPT; - net = dev_net((in != NULL) ? in : out); - return ipt_do_table(skb, ops->hooknum, in, out, + net = dev_net(state->in ? state->in : state->out); + return ipt_do_table(skb, ops->hooknum, state, net->ipv4.iptable_security); } diff --git a/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4.c b/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4.c index 5c61328b7704..30ad9554b5e9 100644 --- a/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4.c +++ b/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4.c @@ -94,9 +94,7 @@ static int ipv4_get_l4proto(const struct sk_buff *skb, unsigned int nhoff, static unsigned int ipv4_helper(const struct nf_hook_ops *ops, struct sk_buff *skb, - const struct net_device *in, - const struct net_device *out, - int (*okfn)(struct sk_buff *)) + const struct nf_hook_state *state) { struct nf_conn *ct; enum ip_conntrack_info ctinfo; @@ -123,9 +121,7 @@ static unsigned int ipv4_helper(const struct nf_hook_ops *ops, static unsigned int ipv4_confirm(const struct nf_hook_ops *ops, struct sk_buff *skb, - const struct net_device *in, - const struct net_device *out, - int (*okfn)(struct sk_buff *)) + const struct nf_hook_state *state) { struct nf_conn *ct; enum ip_conntrack_info ctinfo; @@ -149,24 +145,20 @@ out: static unsigned int ipv4_conntrack_in(const struct nf_hook_ops *ops, struct sk_buff *skb, - const struct net_device *in, - const struct net_device *out, - int (*okfn)(struct sk_buff *)) + const struct nf_hook_state *state) { - return nf_conntrack_in(dev_net(in), PF_INET, ops->hooknum, skb); + return nf_conntrack_in(dev_net(state->in), PF_INET, ops->hooknum, skb); } static unsigned int ipv4_conntrack_local(const struct nf_hook_ops *ops, struct sk_buff *skb, - const struct net_device *in, - const struct net_device *out, - int (*okfn)(struct sk_buff *)) + const struct nf_hook_state *state) { /* root is playing with raw sockets. */ if (skb->len < sizeof(struct iphdr) || ip_hdrlen(skb) < sizeof(struct iphdr)) return NF_ACCEPT; - return nf_conntrack_in(dev_net(out), PF_INET, ops->hooknum, skb); + return nf_conntrack_in(dev_net(state->out), PF_INET, ops->hooknum, skb); } /* Connection tracking may drop packets, but never alters them, so @@ -322,8 +314,8 @@ getorigdst(struct sock *sk, int optval, void __user *user, int *len) static int ipv4_tuple_to_nlattr(struct sk_buff *skb, const struct nf_conntrack_tuple *tuple) { - if (nla_put_be32(skb, CTA_IP_V4_SRC, tuple->src.u3.ip) || - nla_put_be32(skb, CTA_IP_V4_DST, tuple->dst.u3.ip)) + if (nla_put_in_addr(skb, CTA_IP_V4_SRC, tuple->src.u3.ip) || + nla_put_in_addr(skb, CTA_IP_V4_DST, tuple->dst.u3.ip)) goto nla_put_failure; return 0; @@ -342,8 +334,8 @@ static int ipv4_nlattr_to_tuple(struct nlattr *tb[], if (!tb[CTA_IP_V4_SRC] || !tb[CTA_IP_V4_DST]) return -EINVAL; - t->src.u3.ip = nla_get_be32(tb[CTA_IP_V4_SRC]); - t->dst.u3.ip = nla_get_be32(tb[CTA_IP_V4_DST]); + t->src.u3.ip = nla_get_in_addr(tb[CTA_IP_V4_SRC]); + t->dst.u3.ip = nla_get_in_addr(tb[CTA_IP_V4_DST]); return 0; } diff --git a/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4_compat.c b/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4_compat.c index a460a87e14f8..f0dfe92a00d6 100644 --- a/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4_compat.c +++ b/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4_compat.c @@ -300,7 +300,9 @@ static int exp_seq_show(struct seq_file *s, void *v) __nf_ct_l3proto_find(exp->tuple.src.l3num), __nf_ct_l4proto_find(exp->tuple.src.l3num, exp->tuple.dst.protonum)); - return seq_putc(s, '\n'); + seq_putc(s, '\n'); + + return 0; } static const struct seq_operations exp_seq_ops = { diff --git a/net/ipv4/netfilter/nf_defrag_ipv4.c b/net/ipv4/netfilter/nf_defrag_ipv4.c index 7e5ca6f2d0cd..c88b7d434718 100644 --- a/net/ipv4/netfilter/nf_defrag_ipv4.c +++ b/net/ipv4/netfilter/nf_defrag_ipv4.c @@ -63,9 +63,7 @@ static enum ip_defrag_users nf_ct_defrag_user(unsigned int hooknum, static unsigned int ipv4_conntrack_defrag(const struct nf_hook_ops *ops, struct sk_buff *skb, - const struct net_device *in, - const struct net_device *out, - int (*okfn)(struct sk_buff *)) + const struct nf_hook_state *state) { struct sock *sk = skb->sk; struct inet_sock *inet = inet_sk(skb->sk); diff --git a/net/ipv4/netfilter/nf_log_arp.c b/net/ipv4/netfilter/nf_log_arp.c index d059182c1466..e7ad950cf9ef 100644 --- a/net/ipv4/netfilter/nf_log_arp.c +++ b/net/ipv4/netfilter/nf_log_arp.c @@ -10,8 +10,10 @@ * it under the terms of the GNU General Public License version 2 as * published by the Free Software Foundation. */ + #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt +#include <linux/kernel.h> #include <linux/module.h> #include <linux/spinlock.h> #include <linux/skbuff.h> @@ -27,7 +29,7 @@ static struct nf_loginfo default_loginfo = { .type = NF_LOG_TYPE_LOG, .u = { .log = { - .level = 5, + .level = LOGLEVEL_NOTICE, .logflags = NF_LOG_MASK, }, }, diff --git a/net/ipv4/netfilter/nf_log_ipv4.c b/net/ipv4/netfilter/nf_log_ipv4.c index 75101980eeee..076aadda0473 100644 --- a/net/ipv4/netfilter/nf_log_ipv4.c +++ b/net/ipv4/netfilter/nf_log_ipv4.c @@ -5,8 +5,10 @@ * it under the terms of the GNU General Public License version 2 as * published by the Free Software Foundation. */ + #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt +#include <linux/kernel.h> #include <linux/module.h> #include <linux/spinlock.h> #include <linux/skbuff.h> @@ -26,7 +28,7 @@ static struct nf_loginfo default_loginfo = { .type = NF_LOG_TYPE_LOG, .u = { .log = { - .level = 5, + .level = LOGLEVEL_NOTICE, .logflags = NF_LOG_MASK, }, }, diff --git a/net/ipv4/netfilter/nf_nat_l3proto_ipv4.c b/net/ipv4/netfilter/nf_nat_l3proto_ipv4.c index fc37711e11f3..e59cc05c09e9 100644 --- a/net/ipv4/netfilter/nf_nat_l3proto_ipv4.c +++ b/net/ipv4/netfilter/nf_nat_l3proto_ipv4.c @@ -256,11 +256,10 @@ EXPORT_SYMBOL_GPL(nf_nat_icmp_reply_translation); unsigned int nf_nat_ipv4_fn(const struct nf_hook_ops *ops, struct sk_buff *skb, - const struct net_device *in, const struct net_device *out, + const struct nf_hook_state *state, unsigned int (*do_chain)(const struct nf_hook_ops *ops, struct sk_buff *skb, - const struct net_device *in, - const struct net_device *out, + const struct nf_hook_state *state, struct nf_conn *ct)) { struct nf_conn *ct; @@ -309,7 +308,7 @@ nf_nat_ipv4_fn(const struct nf_hook_ops *ops, struct sk_buff *skb, if (!nf_nat_initialized(ct, maniptype)) { unsigned int ret; - ret = do_chain(ops, skb, in, out, ct); + ret = do_chain(ops, skb, state, ct); if (ret != NF_ACCEPT) return ret; @@ -323,7 +322,8 @@ nf_nat_ipv4_fn(const struct nf_hook_ops *ops, struct sk_buff *skb, pr_debug("Already setup manip %s for ct %p\n", maniptype == NF_NAT_MANIP_SRC ? "SRC" : "DST", ct); - if (nf_nat_oif_changed(ops->hooknum, ctinfo, nat, out)) + if (nf_nat_oif_changed(ops->hooknum, ctinfo, nat, + state->out)) goto oif_changed; } break; @@ -332,7 +332,7 @@ nf_nat_ipv4_fn(const struct nf_hook_ops *ops, struct sk_buff *skb, /* ESTABLISHED */ NF_CT_ASSERT(ctinfo == IP_CT_ESTABLISHED || ctinfo == IP_CT_ESTABLISHED_REPLY); - if (nf_nat_oif_changed(ops->hooknum, ctinfo, nat, out)) + if (nf_nat_oif_changed(ops->hooknum, ctinfo, nat, state->out)) goto oif_changed; } @@ -346,17 +346,16 @@ EXPORT_SYMBOL_GPL(nf_nat_ipv4_fn); unsigned int nf_nat_ipv4_in(const struct nf_hook_ops *ops, struct sk_buff *skb, - const struct net_device *in, const struct net_device *out, + const struct nf_hook_state *state, unsigned int (*do_chain)(const struct nf_hook_ops *ops, struct sk_buff *skb, - const struct net_device *in, - const struct net_device *out, + const struct nf_hook_state *state, struct nf_conn *ct)) { unsigned int ret; __be32 daddr = ip_hdr(skb)->daddr; - ret = nf_nat_ipv4_fn(ops, skb, in, out, do_chain); + ret = nf_nat_ipv4_fn(ops, skb, state, do_chain); if (ret != NF_DROP && ret != NF_STOLEN && daddr != ip_hdr(skb)->daddr) skb_dst_drop(skb); @@ -367,11 +366,10 @@ EXPORT_SYMBOL_GPL(nf_nat_ipv4_in); unsigned int nf_nat_ipv4_out(const struct nf_hook_ops *ops, struct sk_buff *skb, - const struct net_device *in, const struct net_device *out, + const struct nf_hook_state *state, unsigned int (*do_chain)(const struct nf_hook_ops *ops, struct sk_buff *skb, - const struct net_device *in, - const struct net_device *out, + const struct nf_hook_state *state, struct nf_conn *ct)) { #ifdef CONFIG_XFRM @@ -386,7 +384,7 @@ nf_nat_ipv4_out(const struct nf_hook_ops *ops, struct sk_buff *skb, ip_hdrlen(skb) < sizeof(struct iphdr)) return NF_ACCEPT; - ret = nf_nat_ipv4_fn(ops, skb, in, out, do_chain); + ret = nf_nat_ipv4_fn(ops, skb, state, do_chain); #ifdef CONFIG_XFRM if (ret != NF_DROP && ret != NF_STOLEN && !(IPCB(skb)->flags & IPSKB_XFRM_TRANSFORMED) && @@ -410,11 +408,10 @@ EXPORT_SYMBOL_GPL(nf_nat_ipv4_out); unsigned int nf_nat_ipv4_local_fn(const struct nf_hook_ops *ops, struct sk_buff *skb, - const struct net_device *in, const struct net_device *out, + const struct nf_hook_state *state, unsigned int (*do_chain)(const struct nf_hook_ops *ops, struct sk_buff *skb, - const struct net_device *in, - const struct net_device *out, + const struct nf_hook_state *state, struct nf_conn *ct)) { const struct nf_conn *ct; @@ -427,7 +424,7 @@ nf_nat_ipv4_local_fn(const struct nf_hook_ops *ops, struct sk_buff *skb, ip_hdrlen(skb) < sizeof(struct iphdr)) return NF_ACCEPT; - ret = nf_nat_ipv4_fn(ops, skb, in, out, do_chain); + ret = nf_nat_ipv4_fn(ops, skb, state, do_chain); if (ret != NF_DROP && ret != NF_STOLEN && (ct = nf_ct_get(skb, &ctinfo)) != NULL) { enum ip_conntrack_dir dir = CTINFO2DIR(ctinfo); diff --git a/net/ipv4/netfilter/nf_reject_ipv4.c b/net/ipv4/netfilter/nf_reject_ipv4.c index 536da7bc598a..3262e41ff76f 100644 --- a/net/ipv4/netfilter/nf_reject_ipv4.c +++ b/net/ipv4/netfilter/nf_reject_ipv4.c @@ -13,6 +13,7 @@ #include <net/dst.h> #include <net/netfilter/ipv4/nf_reject.h> #include <linux/netfilter_ipv4.h> +#include <linux/netfilter_bridge.h> #include <net/netfilter/ipv4/nf_reject.h> const struct tcphdr *nf_reject_ip_tcphdr_get(struct sk_buff *oldskb, @@ -43,7 +44,7 @@ EXPORT_SYMBOL_GPL(nf_reject_ip_tcphdr_get); struct iphdr *nf_reject_iphdr_put(struct sk_buff *nskb, const struct sk_buff *oldskb, - __be16 protocol, int ttl) + __u8 protocol, int ttl) { struct iphdr *niph, *oiph = ip_hdr(oldskb); @@ -146,7 +147,8 @@ void nf_send_reset(struct sk_buff *oldskb, int hook) */ if (oldskb->nf_bridge) { struct ethhdr *oeth = eth_hdr(oldskb); - nskb->dev = oldskb->nf_bridge->physindev; + + nskb->dev = nf_bridge_get_physindev(oldskb); niph->tot_len = htons(nskb->len); ip_send_check(niph); if (dev_hard_header(nskb, nskb->dev, ntohs(nskb->protocol), @@ -164,4 +166,27 @@ void nf_send_reset(struct sk_buff *oldskb, int hook) } EXPORT_SYMBOL_GPL(nf_send_reset); +void nf_send_unreach(struct sk_buff *skb_in, int code, int hook) +{ + struct iphdr *iph = ip_hdr(skb_in); + u8 proto; + + if (skb_in->csum_bad || iph->frag_off & htons(IP_OFFSET)) + return; + + if (skb_csum_unnecessary(skb_in)) { + icmp_send(skb_in, ICMP_DEST_UNREACH, code, 0); + return; + } + + if (iph->protocol == IPPROTO_TCP || iph->protocol == IPPROTO_UDP) + proto = iph->protocol; + else + proto = 0; + + if (nf_ip_checksum(skb_in, hook, ip_hdrlen(skb_in), proto) == 0) + icmp_send(skb_in, ICMP_DEST_UNREACH, code, 0); +} +EXPORT_SYMBOL_GPL(nf_send_unreach); + MODULE_LICENSE("GPL"); diff --git a/net/ipv4/netfilter/nf_tables_arp.c b/net/ipv4/netfilter/nf_tables_arp.c index 19412a4063fb..8412268bbad1 100644 --- a/net/ipv4/netfilter/nf_tables_arp.c +++ b/net/ipv4/netfilter/nf_tables_arp.c @@ -17,13 +17,11 @@ static unsigned int nft_do_chain_arp(const struct nf_hook_ops *ops, struct sk_buff *skb, - const struct net_device *in, - const struct net_device *out, - int (*okfn)(struct sk_buff *)) + const struct nf_hook_state *state) { struct nft_pktinfo pkt; - nft_set_pktinfo(&pkt, ops, skb, in, out); + nft_set_pktinfo(&pkt, ops, skb, state); return nft_do_chain(&pkt, ops); } diff --git a/net/ipv4/netfilter/nf_tables_ipv4.c b/net/ipv4/netfilter/nf_tables_ipv4.c index 6820c8c40842..aa180d3a69a5 100644 --- a/net/ipv4/netfilter/nf_tables_ipv4.c +++ b/net/ipv4/netfilter/nf_tables_ipv4.c @@ -20,22 +20,18 @@ static unsigned int nft_do_chain_ipv4(const struct nf_hook_ops *ops, struct sk_buff *skb, - const struct net_device *in, - const struct net_device *out, - int (*okfn)(struct sk_buff *)) + const struct nf_hook_state *state) { struct nft_pktinfo pkt; - nft_set_pktinfo_ipv4(&pkt, ops, skb, in, out); + nft_set_pktinfo_ipv4(&pkt, ops, skb, state); return nft_do_chain(&pkt, ops); } static unsigned int nft_ipv4_output(const struct nf_hook_ops *ops, struct sk_buff *skb, - const struct net_device *in, - const struct net_device *out, - int (*okfn)(struct sk_buff *)) + const struct nf_hook_state *state) { if (unlikely(skb->len < sizeof(struct iphdr) || ip_hdr(skb)->ihl < sizeof(struct iphdr) / 4)) { @@ -45,7 +41,7 @@ static unsigned int nft_ipv4_output(const struct nf_hook_ops *ops, return NF_ACCEPT; } - return nft_do_chain_ipv4(ops, skb, in, out, okfn); + return nft_do_chain_ipv4(ops, skb, state); } struct nft_af_info nft_af_ipv4 __read_mostly = { diff --git a/net/ipv4/netfilter/nft_chain_nat_ipv4.c b/net/ipv4/netfilter/nft_chain_nat_ipv4.c index df547bf50078..bf5c30ae14e4 100644 --- a/net/ipv4/netfilter/nft_chain_nat_ipv4.c +++ b/net/ipv4/netfilter/nft_chain_nat_ipv4.c @@ -28,51 +28,42 @@ static unsigned int nft_nat_do_chain(const struct nf_hook_ops *ops, struct sk_buff *skb, - const struct net_device *in, - const struct net_device *out, + const struct nf_hook_state *state, struct nf_conn *ct) { struct nft_pktinfo pkt; - nft_set_pktinfo_ipv4(&pkt, ops, skb, in, out); + nft_set_pktinfo_ipv4(&pkt, ops, skb, state); return nft_do_chain(&pkt, ops); } static unsigned int nft_nat_ipv4_fn(const struct nf_hook_ops *ops, struct sk_buff *skb, - const struct net_device *in, - const struct net_device *out, - int (*okfn)(struct sk_buff *)) + const struct nf_hook_state *state) { - return nf_nat_ipv4_fn(ops, skb, in, out, nft_nat_do_chain); + return nf_nat_ipv4_fn(ops, skb, state, nft_nat_do_chain); } static unsigned int nft_nat_ipv4_in(const struct nf_hook_ops *ops, struct sk_buff *skb, - const struct net_device *in, - const struct net_device *out, - int (*okfn)(struct sk_buff *)) + const struct nf_hook_state *state) { - return nf_nat_ipv4_in(ops, skb, in, out, nft_nat_do_chain); + return nf_nat_ipv4_in(ops, skb, state, nft_nat_do_chain); } static unsigned int nft_nat_ipv4_out(const struct nf_hook_ops *ops, struct sk_buff *skb, - const struct net_device *in, - const struct net_device *out, - int (*okfn)(struct sk_buff *)) + const struct nf_hook_state *state) { - return nf_nat_ipv4_out(ops, skb, in, out, nft_nat_do_chain); + return nf_nat_ipv4_out(ops, skb, state, nft_nat_do_chain); } static unsigned int nft_nat_ipv4_local_fn(const struct nf_hook_ops *ops, struct sk_buff *skb, - const struct net_device *in, - const struct net_device *out, - int (*okfn)(struct sk_buff *)) + const struct nf_hook_state *state) { - return nf_nat_ipv4_local_fn(ops, skb, in, out, nft_nat_do_chain); + return nf_nat_ipv4_local_fn(ops, skb, state, nft_nat_do_chain); } static const struct nf_chain_type nft_chain_nat_ipv4 = { diff --git a/net/ipv4/netfilter/nft_chain_route_ipv4.c b/net/ipv4/netfilter/nft_chain_route_ipv4.c index 125b66766c0a..e335b0afdaf3 100644 --- a/net/ipv4/netfilter/nft_chain_route_ipv4.c +++ b/net/ipv4/netfilter/nft_chain_route_ipv4.c @@ -23,9 +23,7 @@ static unsigned int nf_route_table_hook(const struct nf_hook_ops *ops, struct sk_buff *skb, - const struct net_device *in, - const struct net_device *out, - int (*okfn)(struct sk_buff *)) + const struct nf_hook_state *state) { unsigned int ret; struct nft_pktinfo pkt; @@ -39,7 +37,7 @@ static unsigned int nf_route_table_hook(const struct nf_hook_ops *ops, ip_hdrlen(skb) < sizeof(struct iphdr)) return NF_ACCEPT; - nft_set_pktinfo_ipv4(&pkt, ops, skb, in, out); + nft_set_pktinfo_ipv4(&pkt, ops, skb, state); mark = skb->mark; iph = ip_hdr(skb); diff --git a/net/ipv4/netfilter/nft_masq_ipv4.c b/net/ipv4/netfilter/nft_masq_ipv4.c index 665de06561cd..40e414c4ca56 100644 --- a/net/ipv4/netfilter/nft_masq_ipv4.c +++ b/net/ipv4/netfilter/nft_masq_ipv4.c @@ -17,20 +17,17 @@ #include <net/netfilter/ipv4/nf_nat_masquerade.h> static void nft_masq_ipv4_eval(const struct nft_expr *expr, - struct nft_data data[NFT_REG_MAX + 1], + struct nft_regs *regs, const struct nft_pktinfo *pkt) { struct nft_masq *priv = nft_expr_priv(expr); struct nf_nat_range range; - unsigned int verdict; memset(&range, 0, sizeof(range)); range.flags = priv->flags; - verdict = nf_nat_masquerade_ipv4(pkt->skb, pkt->ops->hooknum, - &range, pkt->out); - - data[NFT_REG_VERDICT].verdict = verdict; + regs->verdict.code = nf_nat_masquerade_ipv4(pkt->skb, pkt->ops->hooknum, + &range, pkt->out); } static struct nft_expr_type nft_masq_ipv4_type; diff --git a/net/ipv4/netfilter/nft_redir_ipv4.c b/net/ipv4/netfilter/nft_redir_ipv4.c index 6ecfce63201a..d8d795df9c13 100644 --- a/net/ipv4/netfilter/nft_redir_ipv4.c +++ b/net/ipv4/netfilter/nft_redir_ipv4.c @@ -18,26 +18,25 @@ #include <net/netfilter/nft_redir.h> static void nft_redir_ipv4_eval(const struct nft_expr *expr, - struct nft_data data[NFT_REG_MAX + 1], + struct nft_regs *regs, const struct nft_pktinfo *pkt) { struct nft_redir *priv = nft_expr_priv(expr); struct nf_nat_ipv4_multi_range_compat mr; - unsigned int verdict; memset(&mr, 0, sizeof(mr)); if (priv->sreg_proto_min) { mr.range[0].min.all = - *(__be16 *)&data[priv->sreg_proto_min].data[0]; + *(__be16 *)®s->data[priv->sreg_proto_min]; mr.range[0].max.all = - *(__be16 *)&data[priv->sreg_proto_max].data[0]; + *(__be16 *)®s->data[priv->sreg_proto_max]; mr.range[0].flags |= NF_NAT_RANGE_PROTO_SPECIFIED; } mr.range[0].flags |= priv->flags; - verdict = nf_nat_redirect_ipv4(pkt->skb, &mr, pkt->ops->hooknum); - data[NFT_REG_VERDICT].verdict = verdict; + regs->verdict.code = nf_nat_redirect_ipv4(pkt->skb, &mr, + pkt->ops->hooknum); } static struct nft_expr_type nft_redir_ipv4_type; diff --git a/net/ipv4/netfilter/nft_reject_ipv4.c b/net/ipv4/netfilter/nft_reject_ipv4.c index d729542bd1b7..b07e58b51158 100644 --- a/net/ipv4/netfilter/nft_reject_ipv4.c +++ b/net/ipv4/netfilter/nft_reject_ipv4.c @@ -20,21 +20,24 @@ #include <net/netfilter/nft_reject.h> static void nft_reject_ipv4_eval(const struct nft_expr *expr, - struct nft_data data[NFT_REG_MAX + 1], + struct nft_regs *regs, const struct nft_pktinfo *pkt) { struct nft_reject *priv = nft_expr_priv(expr); switch (priv->type) { case NFT_REJECT_ICMP_UNREACH: - nf_send_unreach(pkt->skb, priv->icmp_code); + nf_send_unreach(pkt->skb, priv->icmp_code, + pkt->ops->hooknum); break; case NFT_REJECT_TCP_RST: nf_send_reset(pkt->skb, pkt->ops->hooknum); break; + default: + break; } - data[NFT_REG_VERDICT].verdict = NF_DROP; + regs->verdict.code = NF_DROP; } static struct nft_expr_type nft_reject_ipv4_type; diff --git a/net/ipv4/ping.c b/net/ipv4/ping.c index 208d5439e59b..05ff44b758df 100644 --- a/net/ipv4/ping.c +++ b/net/ipv4/ping.c @@ -64,11 +64,11 @@ EXPORT_SYMBOL_GPL(pingv6_ops); static u16 ping_port_rover; -static inline int ping_hashfn(struct net *net, unsigned int num, unsigned int mask) +static inline u32 ping_hashfn(const struct net *net, u32 num, u32 mask) { - int res = (num + net_hash_mix(net)) & mask; + u32 res = (num + net_hash_mix(net)) & mask; - pr_debug("hash(%d) = %d\n", num, res); + pr_debug("hash(%u) = %u\n", num, res); return res; } EXPORT_SYMBOL_GPL(ping_hash); @@ -158,6 +158,7 @@ void ping_unhash(struct sock *sk) if (sk_hashed(sk)) { write_lock_bh(&ping_table.lock); hlist_nulls_del(&sk->sk_nulls_node); + sk_nulls_node_init(&sk->sk_nulls_node); sock_put(sk); isk->inet_num = 0; isk->inet_sport = 0; @@ -516,7 +517,7 @@ void ping_err(struct sk_buff *skb, int offset, u32 info) ntohs(icmph->un.echo.sequence)); sk = ping_lookup(net, skb, ntohs(icmph->un.echo.id)); - if (sk == NULL) { + if (!sk) { pr_debug("no socket, dropping\n"); return; /* No socket for error */ } @@ -692,8 +693,7 @@ int ping_common_sendmsg(int family, struct msghdr *msg, size_t len, } EXPORT_SYMBOL_GPL(ping_common_sendmsg); -static int ping_v4_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg, - size_t len) +static int ping_v4_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) { struct net *net = sock_net(sk); struct flowi4 fl4; @@ -849,8 +849,8 @@ do_confirm: goto out; } -int ping_recvmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg, - size_t len, int noblock, int flags, int *addr_len) +int ping_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, int noblock, + int flags, int *addr_len) { struct inet_sock *isk = inet_sk(sk); int family = sk->sk_family; @@ -972,7 +972,7 @@ bool ping_rcv(struct sk_buff *skb) skb_push(skb, skb->data - (u8 *)icmph); sk = ping_lookup(net, skb, ntohs(icmph->un.echo.id)); - if (sk != NULL) { + if (sk) { struct sk_buff *skb2 = skb_clone(skb, GFP_ATOMIC); pr_debug("rcv on socket %p\n", sk); diff --git a/net/ipv4/proc.c b/net/ipv4/proc.c index d8953ef0770c..e1f3b911dd1e 100644 --- a/net/ipv4/proc.c +++ b/net/ipv4/proc.c @@ -63,7 +63,7 @@ static int sockstat_seq_show(struct seq_file *seq, void *v) socket_seq_show(seq); seq_printf(seq, "TCP: inuse %d orphan %d tw %d alloc %d mem %ld\n", sock_prot_inuse_get(net, &tcp_prot), orphans, - tcp_death_row.tw_count, sockets, + atomic_read(&tcp_death_row.tw_count), sockets, proto_memory_allocated(&tcp_prot)); seq_printf(seq, "UDP: inuse %d mem %ld\n", sock_prot_inuse_get(net, &udp_prot), diff --git a/net/ipv4/raw.c b/net/ipv4/raw.c index f027a708b7e0..561cd4b8fc6e 100644 --- a/net/ipv4/raw.c +++ b/net/ipv4/raw.c @@ -46,7 +46,6 @@ #include <linux/stddef.h> #include <linux/slab.h> #include <linux/errno.h> -#include <linux/aio.h> #include <linux/kernel.h> #include <linux/export.h> #include <linux/spinlock.h> @@ -293,7 +292,7 @@ void raw_icmp_error(struct sk_buff *skb, int protocol, u32 info) read_lock(&raw_v4_hashinfo.lock); raw_sk = sk_head(&raw_v4_hashinfo.ht[hash]); - if (raw_sk != NULL) { + if (raw_sk) { iph = (const struct iphdr *)skb->data; net = dev_net(skb->dev); @@ -363,7 +362,7 @@ static int raw_send_hdrinc(struct sock *sk, struct flowi4 *fl4, skb = sock_alloc_send_skb(sk, length + hlen + tlen + 15, flags & MSG_DONTWAIT, &err); - if (skb == NULL) + if (!skb) goto error; skb_reserve(skb, hlen); @@ -404,7 +403,7 @@ static int raw_send_hdrinc(struct sock *sk, struct flowi4 *fl4, iph->check = 0; iph->tot_len = htons(length); if (!iph->id) - ip_select_ident(skb, NULL); + ip_select_ident(net, skb, NULL); iph->check = ip_fast_csum((unsigned char *)iph, iph->ihl); } @@ -412,8 +411,8 @@ static int raw_send_hdrinc(struct sock *sk, struct flowi4 *fl4, icmp_out_count(net, ((struct icmphdr *) skb_transport_header(skb))->type); - err = NF_HOOK(NFPROTO_IPV4, NF_INET_LOCAL_OUT, skb, NULL, - rt->dst.dev, dst_output); + err = NF_HOOK(NFPROTO_IPV4, NF_INET_LOCAL_OUT, sk, skb, + NULL, rt->dst.dev, dst_output_sk); if (err > 0) err = net_xmit_errno(err); if (err) @@ -481,8 +480,7 @@ static int raw_getfrag(void *from, char *to, int offset, int len, int odd, return ip_generic_getfrag(rfv->msg, to, offset, len, odd, skb); } -static int raw_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg, - size_t len) +static int raw_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) { struct inet_sock *inet = inet_sk(sk); struct ipcm_cookie ipc; @@ -709,8 +707,8 @@ out: return ret; * we return it, otherwise we block. */ -static int raw_recvmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg, - size_t len, int noblock, int flags, int *addr_len) +static int raw_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, + int noblock, int flags, int *addr_len) { struct inet_sock *inet = inet_sk(sk); size_t copied = 0; @@ -873,7 +871,7 @@ static int raw_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) + if (skb) amount = skb->len; spin_unlock_bh(&sk->sk_receive_queue.lock); return put_user(amount, (int __user *)arg); diff --git a/net/ipv4/route.c b/net/ipv4/route.c index ad5064362c5c..bff62fc87b8e 100644 --- a/net/ipv4/route.c +++ b/net/ipv4/route.c @@ -152,7 +152,6 @@ static struct neighbour *ipv4_neigh_lookup(const struct dst_entry *dst, static struct dst_ops ipv4_dst_ops = { .family = AF_INET, - .protocol = cpu_to_be16(ETH_P_IP), .check = ipv4_dst_check, .default_advmss = ipv4_default_advmss, .mtu = ipv4_mtu, @@ -483,7 +482,7 @@ u32 ip_idents_reserve(u32 hash, int segs) } EXPORT_SYMBOL(ip_idents_reserve); -void __ip_select_ident(struct iphdr *iph, int segs) +void __ip_select_ident(struct net *net, struct iphdr *iph, int segs) { static u32 ip_idents_hashrnd __read_mostly; u32 hash, id; @@ -492,7 +491,7 @@ void __ip_select_ident(struct iphdr *iph, int segs) hash = jhash_3words((__force u32)iph->daddr, (__force u32)iph->saddr, - iph->protocol, + iph->protocol ^ net_hash_mix(net), ip_idents_hashrnd); id = ip_idents_reserve(hash, segs); iph->id = htons(id); @@ -963,10 +962,7 @@ static void __ip_rt_update_pmtu(struct rtable *rt, struct flowi4 *fl4, u32 mtu) if (dst_metric_locked(dst, RTAX_MTU)) return; - if (dst->dev->mtu < mtu) - return; - - if (rt->rt_pmtu && rt->rt_pmtu < mtu) + if (ipv4_mtu(dst) < mtu) return; if (mtu < ip_rt_min_pmtu) @@ -1057,7 +1053,7 @@ void ipv4_sk_update_pmtu(struct sk_buff *skb, struct sock *sk, u32 mtu) __build_flow_key(&fl4, sk, iph, 0, 0, 0, 0, 0); rt = (struct rtable *)odst; - if (odst->obsolete && odst->ops->check(odst, 0) == NULL) { + if (odst->obsolete && !odst->ops->check(odst, 0)) { rt = ip_route_output_flow(sock_net(sk), &fl4, sk); if (IS_ERR(rt)) goto out; @@ -1451,7 +1447,7 @@ static int ip_route_input_mc(struct sk_buff *skb, __be32 daddr, __be32 saddr, /* Primary sanity checks. */ - if (in_dev == NULL) + if (!in_dev) return -EINVAL; if (ipv4_is_multicast(saddr) || ipv4_is_lbcast(saddr) || @@ -1554,7 +1550,7 @@ static int __mkroute_input(struct sk_buff *skb, /* get a working reference to the output device */ out_dev = __in_dev_get_rcu(FIB_RES_DEV(*res)); - if (out_dev == NULL) { + if (!out_dev) { net_crit_ratelimited("Bug in ip_route_input_slow(). Please report.\n"); return -EINVAL; } @@ -1592,7 +1588,7 @@ static int __mkroute_input(struct sk_buff *skb, fnhe = find_exception(&FIB_RES_NH(*res), daddr); if (do_cache) { - if (fnhe != NULL) + if (fnhe) rth = rcu_dereference(fnhe->fnhe_rth_input); else rth = rcu_dereference(FIB_RES_NH(*res).nh_rth_input); @@ -2055,7 +2051,7 @@ struct rtable *__ip_route_output_key(struct net *net, struct flowi4 *fl4) ipv4_is_lbcast(fl4->daddr))) { /* It is equivalent to inet_addr_type(saddr) == RTN_LOCAL */ dev_out = __ip_dev_find(net, fl4->saddr, false); - if (dev_out == NULL) + if (!dev_out) goto out; /* Special hack: user can direct multicasts @@ -2088,7 +2084,7 @@ struct rtable *__ip_route_output_key(struct net *net, struct flowi4 *fl4) if (fl4->flowi4_oif) { dev_out = dev_get_by_index_rcu(net, fl4->flowi4_oif); rth = ERR_PTR(-ENODEV); - if (dev_out == NULL) + if (!dev_out) goto out; /* RACE: Check return value of inet_select_addr instead. */ @@ -2225,7 +2221,6 @@ static u32 *ipv4_rt_blackhole_cow_metrics(struct dst_entry *dst, static struct dst_ops ipv4_dst_blackhole_ops = { .family = AF_INET, - .protocol = cpu_to_be16(ETH_P_IP), .check = ipv4_blackhole_dst_check, .mtu = ipv4_blackhole_mtu, .default_advmss = ipv4_default_advmss, @@ -2301,7 +2296,7 @@ static int rt_fill_info(struct net *net, __be32 dst, __be32 src, u32 metrics[RTAX_MAX]; nlh = nlmsg_put(skb, portid, seq, event, sizeof(*r), flags); - if (nlh == NULL) + if (!nlh) return -EMSGSIZE; r = nlmsg_data(nlh); @@ -2321,11 +2316,11 @@ static int rt_fill_info(struct net *net, __be32 dst, __be32 src, if (IPCB(skb)->flags & IPSKB_DOREDIRECT) r->rtm_flags |= RTCF_DOREDIRECT; - if (nla_put_be32(skb, RTA_DST, dst)) + if (nla_put_in_addr(skb, RTA_DST, dst)) goto nla_put_failure; if (src) { r->rtm_src_len = 32; - if (nla_put_be32(skb, RTA_SRC, src)) + if (nla_put_in_addr(skb, RTA_SRC, src)) goto nla_put_failure; } if (rt->dst.dev && @@ -2338,11 +2333,11 @@ static int rt_fill_info(struct net *net, __be32 dst, __be32 src, #endif if (!rt_is_input_route(rt) && fl4->saddr != src) { - if (nla_put_be32(skb, RTA_PREFSRC, fl4->saddr)) + if (nla_put_in_addr(skb, RTA_PREFSRC, fl4->saddr)) goto nla_put_failure; } if (rt->rt_uses_gateway && - nla_put_be32(skb, RTA_GATEWAY, rt->rt_gateway)) + nla_put_in_addr(skb, RTA_GATEWAY, rt->rt_gateway)) goto nla_put_failure; expires = rt->dst.expires; @@ -2423,7 +2418,7 @@ static int inet_rtm_getroute(struct sk_buff *in_skb, struct nlmsghdr *nlh) rtm = nlmsg_data(nlh); skb = alloc_skb(NLMSG_GOODSIZE, GFP_KERNEL); - if (skb == NULL) { + if (!skb) { err = -ENOBUFS; goto errout; } @@ -2438,8 +2433,8 @@ static int inet_rtm_getroute(struct sk_buff *in_skb, struct nlmsghdr *nlh) ip_hdr(skb)->protocol = IPPROTO_ICMP; skb_reserve(skb, MAX_HEADER + sizeof(struct iphdr)); - src = tb[RTA_SRC] ? nla_get_be32(tb[RTA_SRC]) : 0; - dst = tb[RTA_DST] ? nla_get_be32(tb[RTA_DST]) : 0; + src = tb[RTA_SRC] ? nla_get_in_addr(tb[RTA_SRC]) : 0; + dst = tb[RTA_DST] ? nla_get_in_addr(tb[RTA_DST]) : 0; iif = tb[RTA_IIF] ? nla_get_u32(tb[RTA_IIF]) : 0; mark = tb[RTA_MARK] ? nla_get_u32(tb[RTA_MARK]) : 0; @@ -2454,7 +2449,7 @@ static int inet_rtm_getroute(struct sk_buff *in_skb, struct nlmsghdr *nlh) struct net_device *dev; dev = __dev_get_by_index(net, iif); - if (dev == NULL) { + if (!dev) { err = -ENODEV; goto errout_free; } @@ -2653,7 +2648,7 @@ static __net_init int sysctl_route_net_init(struct net *net) tbl = ipv4_route_flush_table; if (!net_eq(net, &init_net)) { tbl = kmemdup(tbl, sizeof(ipv4_route_flush_table), GFP_KERNEL); - if (tbl == NULL) + if (!tbl) goto err_dup; /* Don't export sysctls to unprivileged users */ @@ -2663,7 +2658,7 @@ static __net_init int sysctl_route_net_init(struct net *net) tbl[0].extra1 = net; net->ipv4.route_hdr = register_net_sysctl(net, "net/ipv4/route", tbl); - if (net->ipv4.route_hdr == NULL) + if (!net->ipv4.route_hdr) goto err_reg; return 0; diff --git a/net/ipv4/syncookies.c b/net/ipv4/syncookies.c index 45fe60c5238e..df849e5a10f1 100644 --- a/net/ipv4/syncookies.c +++ b/net/ipv4/syncookies.c @@ -219,19 +219,20 @@ int __cookie_v4_check(const struct iphdr *iph, const struct tcphdr *th, } EXPORT_SYMBOL_GPL(__cookie_v4_check); -static inline struct sock *get_cookie_sock(struct sock *sk, struct sk_buff *skb, - struct request_sock *req, - struct dst_entry *dst) +static struct sock *get_cookie_sock(struct sock *sk, struct sk_buff *skb, + struct request_sock *req, + struct dst_entry *dst) { struct inet_connection_sock *icsk = inet_csk(sk); struct sock *child; child = icsk->icsk_af_ops->syn_recv_sock(sk, skb, req, dst); - if (child) + if (child) { + atomic_set(&req->rsk_refcnt, 1); inet_csk_reqsk_queue_add(sk, req, child); - else + } else { reqsk_free(req); - + } return child; } @@ -325,7 +326,7 @@ struct sock *cookie_v4_check(struct sock *sk, struct sk_buff *skb) goto out; ret = NULL; - req = inet_reqsk_alloc(&tcp_request_sock_ops); /* for safety */ + req = inet_reqsk_alloc(&tcp_request_sock_ops, sk); /* for safety */ if (!req) goto out; @@ -336,8 +337,8 @@ struct sock *cookie_v4_check(struct sock *sk, struct sk_buff *skb) req->mss = mss; ireq->ir_num = ntohs(th->dest); ireq->ir_rmt_port = th->source; - ireq->ir_loc_addr = ip_hdr(skb)->daddr; - ireq->ir_rmt_addr = ip_hdr(skb)->saddr; + sk_rcv_saddr_set(req_to_sk(req), ip_hdr(skb)->daddr); + sk_daddr_set(req_to_sk(req), ip_hdr(skb)->saddr); ireq->ir_mark = inet_request_mark(sk, skb); ireq->snd_wscale = tcp_opt.snd_wscale; ireq->sack_ok = tcp_opt.sack_ok; @@ -345,7 +346,9 @@ struct sock *cookie_v4_check(struct sock *sk, struct sk_buff *skb) ireq->tstamp_ok = tcp_opt.saw_tstamp; req->ts_recent = tcp_opt.saw_tstamp ? tcp_opt.rcv_tsval : 0; treq->snt_synack = tcp_opt.saw_tstamp ? tcp_opt.rcv_tsecr : 0; - treq->listener = NULL; + treq->tfo_listener = false; + + ireq->ir_iif = sk->sk_bound_dev_if; /* We throwed the options of the initial SYN away, so we hope * the ACK carries the same options again (see RFC1122 4.2.3.8) @@ -357,7 +360,6 @@ struct sock *cookie_v4_check(struct sock *sk, struct sk_buff *skb) goto out; } - req->expires = 0UL; req->num_retrans = 0; /* diff --git a/net/ipv4/sysctl_net_ipv4.c b/net/ipv4/sysctl_net_ipv4.c index d151539da8e6..c3852a7ff3c7 100644 --- a/net/ipv4/sysctl_net_ipv4.c +++ b/net/ipv4/sysctl_net_ipv4.c @@ -883,6 +883,20 @@ static struct ctl_table ipv4_net_table[] = { .mode = 0644, .proc_handler = proc_dointvec, }, + { + .procname = "tcp_probe_threshold", + .data = &init_net.ipv4.sysctl_tcp_probe_threshold, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec, + }, + { + .procname = "tcp_probe_interval", + .data = &init_net.ipv4.sysctl_tcp_probe_interval, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec, + }, { } }; @@ -895,7 +909,7 @@ static __net_init int ipv4_sysctl_init_net(struct net *net) int i; table = kmemdup(table, sizeof(ipv4_net_table), GFP_KERNEL); - if (table == NULL) + if (!table) goto err_alloc; /* Update the variables to point into the current struct net */ @@ -904,7 +918,7 @@ static __net_init int ipv4_sysctl_init_net(struct net *net) } net->ipv4.ipv4_hdr = register_net_sysctl(net, "net/ipv4", table); - if (net->ipv4.ipv4_hdr == NULL) + if (!net->ipv4.ipv4_hdr) goto err_reg; net->ipv4.sysctl_local_reserved_ports = kzalloc(65536 / 8, GFP_KERNEL); @@ -942,7 +956,7 @@ static __init int sysctl_ipv4_init(void) struct ctl_table_header *hdr; hdr = register_net_sysctl(&init_net, "net/ipv4", ipv4_table); - if (hdr == NULL) + if (!hdr) return -ENOMEM; if (register_pernet_subsys(&ipv4_sysctl_ops)) { diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index 995a2259bcfc..8c5cd9efebbc 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -496,7 +496,7 @@ unsigned int tcp_poll(struct file *file, struct socket *sock, poll_table *wait) /* Connected or passive Fast Open socket? */ if (sk->sk_state != TCP_SYN_SENT && - (sk->sk_state != TCP_SYN_RECV || tp->fastopen_rsk != NULL)) { + (sk->sk_state != TCP_SYN_RECV || tp->fastopen_rsk)) { int target = sock_rcvlowat(sk, 0, INT_MAX); if (tp->urg_seq == tp->copied_seq && @@ -520,8 +520,10 @@ unsigned int tcp_poll(struct file *file, struct socket *sock, poll_table *wait) /* Race breaker. If space is freed after * wspace test but before the flags are set, - * IO signal will be lost. + * IO signal will be lost. Memory barrier + * pairs with the input side. */ + smp_mb__after_atomic(); if (sk_stream_is_writeable(sk)) mask |= POLLOUT | POLLWRNORM; } @@ -1028,7 +1030,7 @@ static inline int select_size(const struct sock *sk, bool sg) void tcp_free_fastopen_req(struct tcp_sock *tp) { - if (tp->fastopen_req != NULL) { + if (tp->fastopen_req) { kfree(tp->fastopen_req); tp->fastopen_req = NULL; } @@ -1042,12 +1044,12 @@ static int tcp_sendmsg_fastopen(struct sock *sk, struct msghdr *msg, if (!(sysctl_tcp_fastopen & TFO_CLIENT_ENABLE)) return -EOPNOTSUPP; - if (tp->fastopen_req != NULL) + if (tp->fastopen_req) return -EALREADY; /* Another Fast Open is in progress */ tp->fastopen_req = kzalloc(sizeof(struct tcp_fastopen_request), sk->sk_allocation); - if (unlikely(tp->fastopen_req == NULL)) + if (unlikely(!tp->fastopen_req)) return -ENOBUFS; tp->fastopen_req->data = msg; tp->fastopen_req->size = size; @@ -1060,8 +1062,7 @@ static int tcp_sendmsg_fastopen(struct sock *sk, struct msghdr *msg, return err; } -int tcp_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg, - size_t size) +int tcp_sendmsg(struct sock *sk, struct msghdr *msg, size_t size) { struct tcp_sock *tp = tcp_sk(sk); struct sk_buff *skb; @@ -1120,7 +1121,7 @@ int tcp_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg, sg = !!(sk->sk_route_caps & NETIF_F_SG); - while (iov_iter_count(&msg->msg_iter)) { + while (msg_data_left(msg)) { int copy = 0; int max = size_goal; @@ -1164,8 +1165,8 @@ new_segment: } /* Try to append data to the end of skb. */ - if (copy > iov_iter_count(&msg->msg_iter)) - copy = iov_iter_count(&msg->msg_iter); + if (copy > msg_data_left(msg)) + copy = msg_data_left(msg); /* Where to copy to? */ if (skb_availroom(skb) > 0) { @@ -1222,7 +1223,7 @@ new_segment: tcp_skb_pcount_set(skb, 0); copied += copy; - if (!iov_iter_count(&msg->msg_iter)) { + if (!msg_data_left(msg)) { tcp_tx_timestamp(sk, skb); goto out; } @@ -1539,8 +1540,8 @@ EXPORT_SYMBOL(tcp_read_sock); * Probably, code can be easily improved even more. */ -int tcp_recvmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg, - size_t len, int nonblock, int flags, int *addr_len) +int tcp_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, int nonblock, + int flags, int *addr_len) { struct tcp_sock *tp = tcp_sk(sk); int copied = 0; @@ -1914,18 +1915,19 @@ EXPORT_SYMBOL_GPL(tcp_set_state); static const unsigned char new_state[16] = { /* current state: new state: action: */ - /* (Invalid) */ TCP_CLOSE, - /* TCP_ESTABLISHED */ TCP_FIN_WAIT1 | TCP_ACTION_FIN, - /* TCP_SYN_SENT */ TCP_CLOSE, - /* TCP_SYN_RECV */ TCP_FIN_WAIT1 | TCP_ACTION_FIN, - /* TCP_FIN_WAIT1 */ TCP_FIN_WAIT1, - /* TCP_FIN_WAIT2 */ TCP_FIN_WAIT2, - /* TCP_TIME_WAIT */ TCP_CLOSE, - /* TCP_CLOSE */ TCP_CLOSE, - /* TCP_CLOSE_WAIT */ TCP_LAST_ACK | TCP_ACTION_FIN, - /* TCP_LAST_ACK */ TCP_LAST_ACK, - /* TCP_LISTEN */ TCP_CLOSE, - /* TCP_CLOSING */ TCP_CLOSING, + [0 /* (Invalid) */] = TCP_CLOSE, + [TCP_ESTABLISHED] = TCP_FIN_WAIT1 | TCP_ACTION_FIN, + [TCP_SYN_SENT] = TCP_CLOSE, + [TCP_SYN_RECV] = TCP_FIN_WAIT1 | TCP_ACTION_FIN, + [TCP_FIN_WAIT1] = TCP_FIN_WAIT1, + [TCP_FIN_WAIT2] = TCP_FIN_WAIT2, + [TCP_TIME_WAIT] = TCP_CLOSE, + [TCP_CLOSE] = TCP_CLOSE, + [TCP_CLOSE_WAIT] = TCP_LAST_ACK | TCP_ACTION_FIN, + [TCP_LAST_ACK] = TCP_LAST_ACK, + [TCP_LISTEN] = TCP_CLOSE, + [TCP_CLOSING] = TCP_CLOSING, + [TCP_NEW_SYN_RECV] = TCP_CLOSE, /* should not happen ! */ }; static int tcp_close_state(struct sock *sk) @@ -2138,7 +2140,7 @@ adjudge_to_death: * aborted (e.g., closed with unread data) before 3WHS * finishes. */ - if (req != NULL) + if (req) reqsk_fastopen_remove(sk, req, false); inet_csk_destroy_sock(sk); } @@ -2595,6 +2597,7 @@ void tcp_get_info(const struct sock *sk, struct tcp_info *info) const struct tcp_sock *tp = tcp_sk(sk); const struct inet_connection_sock *icsk = inet_csk(sk); u32 now = tcp_time_stamp; + u32 rate; memset(info, 0, sizeof(*info)); @@ -2655,10 +2658,11 @@ void tcp_get_info(const struct sock *sk, struct tcp_info *info) info->tcpi_total_retrans = tp->total_retrans; - info->tcpi_pacing_rate = sk->sk_pacing_rate != ~0U ? - sk->sk_pacing_rate : ~0ULL; - info->tcpi_max_pacing_rate = sk->sk_max_pacing_rate != ~0U ? - sk->sk_max_pacing_rate : ~0ULL; + rate = READ_ONCE(sk->sk_pacing_rate); + info->tcpi_pacing_rate = rate != ~0U ? rate : ~0ULL; + + rate = READ_ONCE(sk->sk_max_pacing_rate); + info->tcpi_max_pacing_rate = rate != ~0U ? rate : ~0ULL; } EXPORT_SYMBOL_GPL(tcp_get_info); @@ -2776,7 +2780,7 @@ static int do_tcp_getsockopt(struct sock *sk, int level, break; case TCP_FASTOPEN: - if (icsk->icsk_accept_queue.fastopenq != NULL) + if (icsk->icsk_accept_queue.fastopenq) val = icsk->icsk_accept_queue.fastopenq->max_qlen; else val = 0; @@ -2960,7 +2964,7 @@ void tcp_done(struct sock *sk) tcp_set_state(sk, TCP_CLOSE); tcp_clear_xmit_timers(sk); - if (req != NULL) + if (req) reqsk_fastopen_remove(sk, req, false); sk->sk_shutdown = SHUTDOWN_MASK; @@ -3001,12 +3005,11 @@ static void __init tcp_init_mem(void) void __init tcp_init(void) { - struct sk_buff *skb = NULL; unsigned long limit; int max_rshare, max_wshare, cnt; unsigned int i; - BUILD_BUG_ON(sizeof(struct tcp_skb_cb) > sizeof(skb->cb)); + sock_skb_cb_check_size(sizeof(struct tcp_skb_cb)); percpu_counter_init(&tcp_sockets_allocated, 0, GFP_KERNEL); percpu_counter_init(&tcp_orphan_count, 0, GFP_KERNEL); diff --git a/net/ipv4/tcp_cong.c b/net/ipv4/tcp_cong.c index 62856e185a93..7a5ae50c80c8 100644 --- a/net/ipv4/tcp_cong.c +++ b/net/ipv4/tcp_cong.c @@ -83,7 +83,7 @@ int tcp_register_congestion_control(struct tcp_congestion_ops *ca) ret = -EEXIST; } else { list_add_tail_rcu(&ca->list, &tcp_cong_list); - pr_info("%s registered\n", ca->name); + pr_debug("%s registered\n", ca->name); } spin_unlock(&tcp_cong_list_lock); diff --git a/net/ipv4/tcp_dctcp.c b/net/ipv4/tcp_dctcp.c index b504371af742..4376016f7fa5 100644 --- a/net/ipv4/tcp_dctcp.c +++ b/net/ipv4/tcp_dctcp.c @@ -277,7 +277,7 @@ static void dctcp_cwnd_event(struct sock *sk, enum tcp_ca_event ev) } } -static void dctcp_get_info(struct sock *sk, u32 ext, struct sk_buff *skb) +static int dctcp_get_info(struct sock *sk, u32 ext, struct sk_buff *skb) { const struct dctcp *ca = inet_csk_ca(sk); @@ -297,8 +297,9 @@ static void dctcp_get_info(struct sock *sk, u32 ext, struct sk_buff *skb) info.dctcp_ab_tot = ca->acked_bytes_total; } - nla_put(skb, INET_DIAG_DCTCPINFO, sizeof(info), &info); + return nla_put(skb, INET_DIAG_DCTCPINFO, sizeof(info), &info); } + return 0; } static struct tcp_congestion_ops dctcp __read_mostly = { diff --git a/net/ipv4/tcp_diag.c b/net/ipv4/tcp_diag.c index 0d73f9ddb55b..79b34a0f4a4a 100644 --- a/net/ipv4/tcp_diag.c +++ b/net/ipv4/tcp_diag.c @@ -29,18 +29,18 @@ static void tcp_diag_get_info(struct sock *sk, struct inet_diag_msg *r, r->idiag_rqueue = max_t(int, tp->rcv_nxt - tp->copied_seq, 0); r->idiag_wqueue = tp->write_seq - tp->snd_una; } - if (info != NULL) + if (info) tcp_get_info(sk, info); } static void tcp_diag_dump(struct sk_buff *skb, struct netlink_callback *cb, - struct inet_diag_req_v2 *r, struct nlattr *bc) + const struct inet_diag_req_v2 *r, struct nlattr *bc) { inet_diag_dump_icsk(&tcp_hashinfo, skb, cb, r, bc); } static int tcp_diag_dump_one(struct sk_buff *in_skb, const struct nlmsghdr *nlh, - struct inet_diag_req_v2 *req) + const struct inet_diag_req_v2 *req) { return inet_diag_dump_one_icsk(&tcp_hashinfo, in_skb, nlh, req); } diff --git a/net/ipv4/tcp_fastopen.c b/net/ipv4/tcp_fastopen.c index ea82fd492c1b..e3d87aca6be8 100644 --- a/net/ipv4/tcp_fastopen.c +++ b/net/ipv4/tcp_fastopen.c @@ -141,7 +141,7 @@ static bool tcp_fastopen_create_child(struct sock *sk, req->sk = NULL; child = inet_csk(sk)->icsk_af_ops->syn_recv_sock(sk, skb, req, NULL); - if (child == NULL) + if (!child) return false; spin_lock(&queue->fastopenq->lock); @@ -155,12 +155,7 @@ static bool tcp_fastopen_create_child(struct sock *sk, tp = tcp_sk(child); tp->fastopen_rsk = req; - /* Do a hold on the listner sk so that if the listener is being - * closed, the child that has been accepted can live on and still - * access listen_lock. - */ - sock_hold(sk); - tcp_rsk(req)->listener = sk; + tcp_rsk(req)->tfo_listener = true; /* RFC1323: The window in SYN & SYN/ACK segments is never * scaled. So correct it appropriately. @@ -174,6 +169,7 @@ static bool tcp_fastopen_create_child(struct sock *sk, inet_csk_reset_xmit_timer(child, ICSK_TIME_RETRANS, TCP_TIMEOUT_INIT, TCP_RTO_MAX); + atomic_set(&req->rsk_refcnt, 1); /* Add the child socket directly into the accept queue */ inet_csk_reqsk_queue_add(sk, req, child); @@ -218,10 +214,9 @@ static bool tcp_fastopen_create_child(struct sock *sk, sk->sk_data_ready(sk); bh_unlock_sock(child); sock_put(child); - WARN_ON(req->sk == NULL); + WARN_ON(!req->sk); return true; } -EXPORT_SYMBOL(tcp_fastopen_create_child); static bool tcp_fastopen_queue_check(struct sock *sk) { @@ -238,14 +233,14 @@ static bool tcp_fastopen_queue_check(struct sock *sk) * temporarily vs a server not supporting Fast Open at all. */ fastopenq = inet_csk(sk)->icsk_accept_queue.fastopenq; - if (fastopenq == NULL || fastopenq->max_qlen == 0) + if (!fastopenq || fastopenq->max_qlen == 0) return false; if (fastopenq->qlen >= fastopenq->max_qlen) { struct request_sock *req1; spin_lock(&fastopenq->lock); req1 = fastopenq->rskq_rst_head; - if ((req1 == NULL) || time_after(req1->expires, jiffies)) { + if (!req1 || time_after(req1->rsk_timer.expires, jiffies)) { spin_unlock(&fastopenq->lock); NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_TCPFASTOPENLISTENOVERFLOW); @@ -254,7 +249,7 @@ static bool tcp_fastopen_queue_check(struct sock *sk) fastopenq->rskq_rst_head = req1->dl_next; fastopenq->qlen--; spin_unlock(&fastopenq->lock); - reqsk_free(req1); + reqsk_put(req1); } return true; } @@ -308,6 +303,7 @@ fastopen: } else if (foc->len > 0) /* Client presents an invalid cookie */ NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_TCPFASTOPENPASSIVEFAIL); + valid_foc.exp = foc->exp; *foc = valid_foc; return false; } diff --git a/net/ipv4/tcp_illinois.c b/net/ipv4/tcp_illinois.c index 1d5a30a90adf..67476f085e48 100644 --- a/net/ipv4/tcp_illinois.c +++ b/net/ipv4/tcp_illinois.c @@ -300,8 +300,7 @@ static u32 tcp_illinois_ssthresh(struct sock *sk) } /* Extract info for Tcp socket info provided via netlink. */ -static void tcp_illinois_info(struct sock *sk, u32 ext, - struct sk_buff *skb) +static int tcp_illinois_info(struct sock *sk, u32 ext, struct sk_buff *skb) { const struct illinois *ca = inet_csk_ca(sk); @@ -318,8 +317,9 @@ static void tcp_illinois_info(struct sock *sk, u32 ext, do_div(t, info.tcpv_rttcnt); info.tcpv_rtt = t; } - nla_put(skb, INET_DIAG_VEGASINFO, sizeof(info), &info); + return nla_put(skb, INET_DIAG_VEGASINFO, sizeof(info), &info); } + return 0; } static struct tcp_congestion_ops tcp_illinois __read_mostly = { diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index f501ac048366..3a4d9b34bed4 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -866,7 +866,7 @@ static void tcp_update_reordering(struct sock *sk, const int metric, /* This must be called before lost_out is incremented */ static void tcp_verify_retransmit_hint(struct tcp_sock *tp, struct sk_buff *skb) { - if ((tp->retransmit_skb_hint == NULL) || + if (!tp->retransmit_skb_hint || before(TCP_SKB_CB(skb)->seq, TCP_SKB_CB(tp->retransmit_skb_hint)->seq)) tp->retransmit_skb_hint = skb; @@ -1256,7 +1256,7 @@ static u8 tcp_sacktag_one(struct sock *sk, fack_count += pcount; /* Lost marker hint past SACKed? Tweak RFC3517 cnt */ - if (!tcp_is_fack(tp) && (tp->lost_skb_hint != NULL) && + if (!tcp_is_fack(tp) && tp->lost_skb_hint && before(start_seq, TCP_SKB_CB(tp->lost_skb_hint)->seq)) tp->lost_cnt_hint += pcount; @@ -1535,7 +1535,7 @@ static struct sk_buff *tcp_sacktag_walk(struct sk_buff *skb, struct sock *sk, if (!before(TCP_SKB_CB(skb)->seq, end_seq)) break; - if ((next_dup != NULL) && + if (next_dup && before(TCP_SKB_CB(skb)->seq, next_dup->end_seq)) { in_sack = tcp_match_skb_to_sack(sk, skb, next_dup->start_seq, @@ -1551,7 +1551,7 @@ static struct sk_buff *tcp_sacktag_walk(struct sk_buff *skb, struct sock *sk, if (in_sack <= 0) { tmp = tcp_shift_skb_data(sk, skb, state, start_seq, end_seq, dup_sack); - if (tmp != NULL) { + if (tmp) { if (tmp != skb) { skb = tmp; continue; @@ -1614,7 +1614,7 @@ static struct sk_buff *tcp_maybe_skipping_dsack(struct sk_buff *skb, struct tcp_sacktag_state *state, u32 skip_to_seq) { - if (next_dup == NULL) + if (!next_dup) return skb; if (before(next_dup->start_seq, skip_to_seq)) { @@ -1783,7 +1783,7 @@ tcp_sacktag_write_queue(struct sock *sk, const struct sk_buff *ack_skb, if (tcp_highest_sack_seq(tp) == cache->end_seq) { /* ...but better entrypoint exists! */ skb = tcp_highest_sack(sk); - if (skb == NULL) + if (!skb) break; state.fack_count = tp->fackets_out; cache++; @@ -1798,7 +1798,7 @@ tcp_sacktag_write_queue(struct sock *sk, const struct sk_buff *ack_skb, if (!before(start_seq, tcp_highest_sack_seq(tp))) { skb = tcp_highest_sack(sk); - if (skb == NULL) + if (!skb) break; state.fack_count = tp->fackets_out; } @@ -3099,17 +3099,15 @@ static int tcp_clean_rtx_queue(struct sock *sk, int prior_fackets, if (sacked & TCPCB_SACKED_RETRANS) tp->retrans_out -= acked_pcount; flag |= FLAG_RETRANS_DATA_ACKED; - } else { + } else if (!(sacked & TCPCB_SACKED_ACKED)) { last_ackt = skb->skb_mstamp; WARN_ON_ONCE(last_ackt.v64 == 0); if (!first_ackt.v64) first_ackt = last_ackt; - if (!(sacked & TCPCB_SACKED_ACKED)) { - reord = min(pkts_acked, reord); - if (!after(scb->end_seq, tp->high_seq)) - flag |= FLAG_ORIG_SACK_ACKED; - } + reord = min(pkts_acked, reord); + if (!after(scb->end_seq, tp->high_seq)) + flag |= FLAG_ORIG_SACK_ACKED; } if (sacked & TCPCB_SACKED_ACKED) @@ -3322,6 +3320,36 @@ static int tcp_ack_update_window(struct sock *sk, const struct sk_buff *skb, u32 return flag; } +/* Return true if we're currently rate-limiting out-of-window ACKs and + * thus shouldn't send a dupack right now. We rate-limit dupacks in + * response to out-of-window SYNs or ACKs to mitigate ACK loops or DoS + * attacks that send repeated SYNs or ACKs for the same connection. To + * do this, we do not send a duplicate SYNACK or ACK if the remote + * endpoint is sending out-of-window SYNs or pure ACKs at a high rate. + */ +bool tcp_oow_rate_limited(struct net *net, const struct sk_buff *skb, + int mib_idx, u32 *last_oow_ack_time) +{ + /* Data packets without SYNs are not likely part of an ACK loop. */ + if ((TCP_SKB_CB(skb)->seq != TCP_SKB_CB(skb)->end_seq) && + !tcp_hdr(skb)->syn) + goto not_rate_limited; + + if (*last_oow_ack_time) { + s32 elapsed = (s32)(tcp_time_stamp - *last_oow_ack_time); + + if (0 <= elapsed && elapsed < sysctl_tcp_invalid_ratelimit) { + NET_INC_STATS_BH(net, mib_idx); + return true; /* rate-limited: don't send yet! */ + } + } + + *last_oow_ack_time = tcp_time_stamp; + +not_rate_limited: + return false; /* not rate-limited: go ahead, send dupack now! */ +} + /* RFC 5961 7 [ACK Throttling] */ static void tcp_send_challenge_ack(struct sock *sk, const struct sk_buff *skb) { @@ -3573,6 +3601,23 @@ old_ack: return 0; } +static void tcp_parse_fastopen_option(int len, const unsigned char *cookie, + bool syn, struct tcp_fastopen_cookie *foc, + bool exp_opt) +{ + /* Valid only in SYN or SYN-ACK with an even length. */ + if (!foc || !syn || len < 0 || (len & 1)) + return; + + if (len >= TCP_FASTOPEN_COOKIE_MIN && + len <= TCP_FASTOPEN_COOKIE_MAX) + memcpy(foc->val, cookie, len); + else if (len != 0) + len = -1; + foc->len = len; + foc->exp = exp_opt; +} + /* Look for tcp options. Normally only called on SYN and SYNACK packets. * But, this can also be called on packets in the established flow when * the fast version below fails. @@ -3662,21 +3707,22 @@ void tcp_parse_options(const struct sk_buff *skb, */ break; #endif + case TCPOPT_FASTOPEN: + tcp_parse_fastopen_option( + opsize - TCPOLEN_FASTOPEN_BASE, + ptr, th->syn, foc, false); + break; + case TCPOPT_EXP: /* Fast Open option shares code 254 using a - * 16 bits magic number. It's valid only in - * SYN or SYN-ACK with an even size. + * 16 bits magic number. */ - if (opsize < TCPOLEN_EXP_FASTOPEN_BASE || - get_unaligned_be16(ptr) != TCPOPT_FASTOPEN_MAGIC || - foc == NULL || !th->syn || (opsize & 1)) - break; - foc->len = opsize - TCPOLEN_EXP_FASTOPEN_BASE; - if (foc->len >= TCP_FASTOPEN_COOKIE_MIN && - foc->len <= TCP_FASTOPEN_COOKIE_MAX) - memcpy(foc->val, ptr + 2, foc->len); - else if (foc->len != 0) - foc->len = -1; + if (opsize >= TCPOLEN_EXP_FASTOPEN_BASE && + get_unaligned_be16(ptr) == + TCPOPT_FASTOPEN_MAGIC) + tcp_parse_fastopen_option(opsize - + TCPOLEN_EXP_FASTOPEN_BASE, + ptr + 2, th->syn, foc, true); break; } @@ -4640,7 +4686,7 @@ static void tcp_collapse_ofo_queue(struct sock *sk) struct sk_buff *head; u32 start, end; - if (skb == NULL) + if (!skb) return; start = TCP_SKB_CB(skb)->seq; @@ -4799,6 +4845,8 @@ static void tcp_check_space(struct sock *sk) { if (sock_flag(sk, SOCK_QUEUE_SHRUNK)) { sock_reset_flag(sk, SOCK_QUEUE_SHRUNK); + /* pairs with tcp_poll() */ + smp_mb__after_atomic(); if (sk->sk_socket && test_bit(SOCK_NOSPACE, &sk->sk_socket->flags)) tcp_new_space(sk); @@ -5095,7 +5143,7 @@ void tcp_rcv_established(struct sock *sk, struct sk_buff *skb, { struct tcp_sock *tp = tcp_sk(sk); - if (unlikely(sk->sk_rx_dst == NULL)) + if (unlikely(!sk->sk_rx_dst)) inet_csk(sk)->icsk_af_ops->sk_rx_dst_set(sk, skb); /* * Header prediction. @@ -5292,7 +5340,7 @@ void tcp_finish_connect(struct sock *sk, struct sk_buff *skb) tcp_set_state(sk, TCP_ESTABLISHED); - if (skb != NULL) { + if (skb) { icsk->icsk_af_ops->sk_rx_dst_set(sk, skb); security_inet_conn_established(sk, skb); } @@ -5330,8 +5378,8 @@ static bool tcp_rcv_fastopen_synack(struct sock *sk, struct sk_buff *synack, { struct tcp_sock *tp = tcp_sk(sk); struct sk_buff *data = tp->syn_data ? tcp_write_queue_head(sk) : NULL; - u16 mss = tp->rx_opt.mss_clamp; - bool syn_drop; + u16 mss = tp->rx_opt.mss_clamp, try_exp = 0; + bool syn_drop = false; if (mss == tp->rx_opt.user_mss) { struct tcp_options_received opt; @@ -5343,16 +5391,25 @@ static bool tcp_rcv_fastopen_synack(struct sock *sk, struct sk_buff *synack, mss = opt.mss_clamp; } - if (!tp->syn_fastopen) /* Ignore an unsolicited cookie */ + if (!tp->syn_fastopen) { + /* Ignore an unsolicited cookie */ cookie->len = -1; + } else if (tp->total_retrans) { + /* SYN timed out and the SYN-ACK neither has a cookie nor + * acknowledges data. Presumably the remote received only + * the retransmitted (regular) SYNs: either the original + * SYN-data or the corresponding SYN-ACK was dropped. + */ + syn_drop = (cookie->len < 0 && data); + } else if (cookie->len < 0 && !tp->syn_data) { + /* We requested a cookie but didn't get it. If we did not use + * the (old) exp opt format then try so next time (try_exp=1). + * Otherwise we go back to use the RFC7413 opt (try_exp=2). + */ + try_exp = tp->syn_fastopen_exp ? 2 : 1; + } - /* The SYN-ACK neither has cookie nor acknowledges the data. Presumably - * the remote receives only the retransmitted (regular) SYNs: either - * the original SYN-data or the corresponding SYN-ACK is lost. - */ - syn_drop = (cookie->len <= 0 && data && tp->total_retrans); - - tcp_fastopen_cache_set(sk, mss, cookie, syn_drop); + tcp_fastopen_cache_set(sk, mss, cookie, syn_drop, try_exp); if (data) { /* Retransmit unacked data in SYN */ tcp_for_write_queue_from(data, sk) { @@ -5661,11 +5718,11 @@ int tcp_rcv_state_process(struct sock *sk, struct sk_buff *skb, } req = tp->fastopen_rsk; - if (req != NULL) { + if (req) { WARN_ON_ONCE(sk->sk_state != TCP_SYN_RECV && sk->sk_state != TCP_FIN_WAIT1); - if (tcp_check_req(sk, skb, req, NULL, true) == NULL) + if (!tcp_check_req(sk, skb, req, true)) goto discard; } @@ -5751,7 +5808,7 @@ int tcp_rcv_state_process(struct sock *sk, struct sk_buff *skb, * ACK we have received, this would have acknowledged * our SYNACK so stop the SYNACK timer. */ - if (req != NULL) { + if (req) { /* Return RST if ack_seq is invalid. * Note that RFC793 only says to generate a * DUPACK for it but for TCP Fast Open it seems @@ -5913,6 +5970,80 @@ static void tcp_ecn_create_request(struct request_sock *req, inet_rsk(req)->ecn_ok = 1; } +static void tcp_openreq_init(struct request_sock *req, + const struct tcp_options_received *rx_opt, + struct sk_buff *skb, const struct sock *sk) +{ + struct inet_request_sock *ireq = inet_rsk(req); + + req->rcv_wnd = 0; /* So that tcp_send_synack() knows! */ + req->cookie_ts = 0; + tcp_rsk(req)->rcv_isn = TCP_SKB_CB(skb)->seq; + tcp_rsk(req)->rcv_nxt = TCP_SKB_CB(skb)->seq + 1; + tcp_rsk(req)->snt_synack = tcp_time_stamp; + tcp_rsk(req)->last_oow_ack_time = 0; + req->mss = rx_opt->mss_clamp; + req->ts_recent = rx_opt->saw_tstamp ? rx_opt->rcv_tsval : 0; + ireq->tstamp_ok = rx_opt->tstamp_ok; + ireq->sack_ok = rx_opt->sack_ok; + ireq->snd_wscale = rx_opt->snd_wscale; + ireq->wscale_ok = rx_opt->wscale_ok; + ireq->acked = 0; + ireq->ecn_ok = 0; + ireq->ir_rmt_port = tcp_hdr(skb)->source; + ireq->ir_num = ntohs(tcp_hdr(skb)->dest); + ireq->ir_mark = inet_request_mark(sk, skb); +} + +struct request_sock *inet_reqsk_alloc(const struct request_sock_ops *ops, + struct sock *sk_listener) +{ + struct request_sock *req = reqsk_alloc(ops, sk_listener); + + if (req) { + struct inet_request_sock *ireq = inet_rsk(req); + + kmemcheck_annotate_bitfield(ireq, flags); + ireq->opt = NULL; + atomic64_set(&ireq->ir_cookie, 0); + ireq->ireq_state = TCP_NEW_SYN_RECV; + write_pnet(&ireq->ireq_net, sock_net(sk_listener)); + ireq->ireq_family = sk_listener->sk_family; + } + + return req; +} +EXPORT_SYMBOL(inet_reqsk_alloc); + +/* + * Return true if a syncookie should be sent + */ +static bool tcp_syn_flood_action(struct sock *sk, + const struct sk_buff *skb, + const char *proto) +{ + const char *msg = "Dropping request"; + bool want_cookie = false; + struct listen_sock *lopt; + +#ifdef CONFIG_SYN_COOKIES + if (sysctl_tcp_syncookies) { + msg = "Sending cookies"; + want_cookie = true; + NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_TCPREQQFULLDOCOOKIES); + } else +#endif + NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_TCPREQQFULLDROP); + + lopt = inet_csk(sk)->icsk_accept_queue.listen_opt; + if (!lopt->synflood_warned && sysctl_tcp_syncookies != 2) { + lopt->synflood_warned = 1; + pr_info("%s: Possible SYN flooding on port %d. %s. Check SNMP counters.\n", + proto, ntohs(tcp_hdr(skb)->dest), msg); + } + return want_cookie; +} + 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) @@ -5950,7 +6081,7 @@ int tcp_conn_request(struct request_sock_ops *rsk_ops, goto drop; } - req = inet_reqsk_alloc(rsk_ops); + req = inet_reqsk_alloc(rsk_ops, sk); if (!req) goto drop; @@ -5967,6 +6098,9 @@ int tcp_conn_request(struct request_sock_ops *rsk_ops, tmp_opt.tstamp_ok = tmp_opt.saw_tstamp; tcp_openreq_init(req, &tmp_opt, skb, sk); + /* Note: tcp_v6_init_req() might override ir_iif for link locals */ + inet_rsk(req)->ir_iif = sk->sk_bound_dev_if; + af_ops->init_req(req, sk, skb); if (security_inet_conn_request(sk, skb, req)) @@ -6039,7 +6173,7 @@ int tcp_conn_request(struct request_sock_ops *rsk_ops, if (err || want_cookie) goto drop_and_free; - tcp_rsk(req)->listener = NULL; + tcp_rsk(req)->tfo_listener = false; af_ops->queue_hash_add(sk, req, TCP_TIMEOUT_INIT); } diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index f1756ee02207..fc1c658ec6c1 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -122,7 +122,7 @@ int tcp_twsk_unique(struct sock *sk, struct sock *sktw, void *twp) and use initial timestamp retrieved from peer table. */ if (tcptw->tw_ts_recent_stamp && - (twp == NULL || (sysctl_tcp_tw_reuse && + (!twp || (sysctl_tcp_tw_reuse && get_seconds() - tcptw->tw_ts_recent_stamp > 1))) { tp->write_seq = tcptw->tw_snd_nxt + 65535 + 2; if (tp->write_seq == 0) @@ -189,7 +189,7 @@ int tcp_v4_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len) if (!inet->inet_saddr) inet->inet_saddr = fl4->saddr; - inet->inet_rcv_saddr = inet->inet_saddr; + sk_rcv_saddr_set(sk, inet->inet_saddr); if (tp->rx_opt.ts_recent_stamp && inet->inet_daddr != daddr) { /* Reset inherited state */ @@ -204,7 +204,7 @@ int tcp_v4_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len) tcp_fetch_timewait_stamp(sk, &rt->dst); inet->inet_dport = usin->sin_port; - inet->inet_daddr = daddr; + sk_daddr_set(sk, daddr); inet_csk(sk)->icsk_ext_hdr_len = 0; if (inet_opt) @@ -310,6 +310,34 @@ static void do_redirect(struct sk_buff *skb, struct sock *sk) dst->ops->redirect(dst, sk, skb); } + +/* handle ICMP messages on TCP_NEW_SYN_RECV request sockets */ +void tcp_req_err(struct sock *sk, u32 seq) +{ + struct request_sock *req = inet_reqsk(sk); + struct net *net = sock_net(sk); + + /* ICMPs are not backlogged, hence we cannot get + * an established socket here. + */ + WARN_ON(req->sk); + + if (seq != tcp_rsk(req)->snt_isn) { + NET_INC_STATS_BH(net, LINUX_MIB_OUTOFWINDOWICMPS); + reqsk_put(req); + } else { + /* + * Still in SYN_RECV, just remove it silently. + * There is no good way to pass the error to the newly + * created socket, and POSIX does not want network + * errors returned from accept(). + */ + NET_INC_STATS_BH(net, LINUX_MIB_LISTENDROPS); + inet_csk_reqsk_queue_drop(req->rsk_listener, req); + } +} +EXPORT_SYMBOL(tcp_req_err); + /* * This routine is called by the ICMP module when it gets some * sort of error condition. If err < 0 then the socket should @@ -343,8 +371,9 @@ void tcp_v4_err(struct sk_buff *icmp_skb, u32 info) int err; struct net *net = dev_net(icmp_skb->dev); - sk = inet_lookup(net, &tcp_hashinfo, iph->daddr, th->dest, - iph->saddr, th->source, inet_iif(icmp_skb)); + sk = __inet_lookup_established(net, &tcp_hashinfo, iph->daddr, + th->dest, iph->saddr, ntohs(th->source), + inet_iif(icmp_skb)); if (!sk) { ICMP_INC_STATS_BH(net, ICMP_MIB_INERRORS); return; @@ -353,6 +382,9 @@ void tcp_v4_err(struct sk_buff *icmp_skb, u32 info) inet_twsk_put(inet_twsk(sk)); return; } + seq = ntohl(th->seq); + if (sk->sk_state == TCP_NEW_SYN_RECV) + return tcp_req_err(sk, seq); bh_lock_sock(sk); /* If too many ICMPs get dropped on busy @@ -374,7 +406,6 @@ void tcp_v4_err(struct sk_buff *icmp_skb, u32 info) icsk = inet_csk(sk); tp = tcp_sk(sk); - seq = ntohl(th->seq); /* XXX (TFO) - tp->snd_una should be ISN (tcp_create_openreq_child() */ fastopen = tp->fastopen_rsk; snd_una = fastopen ? tcp_rsk(fastopen)->snt_isn : tp->snd_una; @@ -458,42 +489,12 @@ void tcp_v4_err(struct sk_buff *icmp_skb, u32 info) } switch (sk->sk_state) { - struct request_sock *req, **prev; - case TCP_LISTEN: - if (sock_owned_by_user(sk)) - goto out; - - req = inet_csk_search_req(sk, &prev, th->dest, - iph->daddr, iph->saddr); - if (!req) - goto out; - - /* ICMPs are not backlogged, hence we cannot get - an established socket here. - */ - WARN_ON(req->sk); - - if (seq != tcp_rsk(req)->snt_isn) { - NET_INC_STATS_BH(net, LINUX_MIB_OUTOFWINDOWICMPS); - goto out; - } - - /* - * Still in SYN_RECV, just remove it silently. - * There is no good way to pass the error to the newly - * created socket, and POSIX does not want network - * errors returned from accept(). - */ - inet_csk_reqsk_queue_drop(sk, req, prev); - NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_LISTENDROPS); - goto out; - case TCP_SYN_SENT: case TCP_SYN_RECV: /* Only in fast or simultaneous open. If a fast open socket is * is already accepted it is treated as a connected one below. */ - if (fastopen && fastopen->sk == NULL) + if (fastopen && !fastopen->sk) break; if (!sock_owned_by_user(sk)) { @@ -647,7 +648,7 @@ static void tcp_v4_send_reset(struct sock *sk, struct sk_buff *skb) if (!key) goto release_sk1; - genhash = tcp_v4_md5_hash_skb(newhash, key, NULL, NULL, skb); + genhash = tcp_v4_md5_hash_skb(newhash, key, NULL, skb); if (genhash || memcmp(hash_location, newhash, 16) != 0) goto release_sk1; } else { @@ -855,35 +856,6 @@ static void tcp_v4_reqsk_destructor(struct request_sock *req) kfree(inet_rsk(req)->opt); } -/* - * Return true if a syncookie should be sent - */ -bool tcp_syn_flood_action(struct sock *sk, - const struct sk_buff *skb, - const char *proto) -{ - const char *msg = "Dropping request"; - bool want_cookie = false; - struct listen_sock *lopt; - -#ifdef CONFIG_SYN_COOKIES - if (sysctl_tcp_syncookies) { - msg = "Sending cookies"; - want_cookie = true; - NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_TCPREQQFULLDOCOOKIES); - } else -#endif - NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_TCPREQQFULLDROP); - - lopt = inet_csk(sk)->icsk_accept_queue.listen_opt; - if (!lopt->synflood_warned && sysctl_tcp_syncookies != 2) { - lopt->synflood_warned = 1; - pr_info("%s: Possible SYN flooding on port %d. %s. Check SNMP counters.\n", - proto, ntohs(tcp_hdr(skb)->dest), msg); - } - return want_cookie; -} -EXPORT_SYMBOL(tcp_syn_flood_action); #ifdef CONFIG_TCP_MD5SIG /* @@ -897,10 +869,10 @@ struct tcp_md5sig_key *tcp_md5_do_lookup(struct sock *sk, const union tcp_md5_addr *addr, int family) { - struct tcp_sock *tp = tcp_sk(sk); + const struct tcp_sock *tp = tcp_sk(sk); struct tcp_md5sig_key *key; unsigned int size = sizeof(struct in_addr); - struct tcp_md5sig_info *md5sig; + const struct tcp_md5sig_info *md5sig; /* caller either holds rcu_read_lock() or socket lock */ md5sig = rcu_dereference_check(tp->md5sig_info, @@ -923,24 +895,15 @@ struct tcp_md5sig_key *tcp_md5_do_lookup(struct sock *sk, EXPORT_SYMBOL(tcp_md5_do_lookup); struct tcp_md5sig_key *tcp_v4_md5_lookup(struct sock *sk, - struct sock *addr_sk) + const struct sock *addr_sk) { - union tcp_md5_addr *addr; + const union tcp_md5_addr *addr; - addr = (union tcp_md5_addr *)&inet_sk(addr_sk)->inet_daddr; + addr = (const union tcp_md5_addr *)&addr_sk->sk_daddr; return tcp_md5_do_lookup(sk, addr, AF_INET); } EXPORT_SYMBOL(tcp_v4_md5_lookup); -static struct tcp_md5sig_key *tcp_v4_reqsk_md5_lookup(struct sock *sk, - struct request_sock *req) -{ - union tcp_md5_addr *addr; - - addr = (union tcp_md5_addr *)&inet_rsk(req)->ir_rmt_addr; - return tcp_md5_do_lookup(sk, addr, AF_INET); -} - /* This can be called on a newly created socket, from other files */ int tcp_md5_do_add(struct sock *sk, const union tcp_md5_addr *addr, int family, const u8 *newkey, u8 newkeylen, gfp_t gfp) @@ -1101,8 +1064,8 @@ clear_hash_noput: return 1; } -int tcp_v4_md5_hash_skb(char *md5_hash, struct tcp_md5sig_key *key, - const struct sock *sk, const struct request_sock *req, +int tcp_v4_md5_hash_skb(char *md5_hash, const struct tcp_md5sig_key *key, + const struct sock *sk, const struct sk_buff *skb) { struct tcp_md5sig_pool *hp; @@ -1110,12 +1073,9 @@ int tcp_v4_md5_hash_skb(char *md5_hash, struct tcp_md5sig_key *key, const struct tcphdr *th = tcp_hdr(skb); __be32 saddr, daddr; - if (sk) { - saddr = inet_sk(sk)->inet_saddr; - daddr = inet_sk(sk)->inet_daddr; - } else if (req) { - saddr = inet_rsk(req)->ir_loc_addr; - daddr = inet_rsk(req)->ir_rmt_addr; + if (sk) { /* valid for establish/request sockets */ + saddr = sk->sk_rcv_saddr; + daddr = sk->sk_daddr; } else { const struct iphdr *iph = ip_hdr(skb); saddr = iph->saddr; @@ -1152,8 +1112,9 @@ clear_hash_noput: } EXPORT_SYMBOL(tcp_v4_md5_hash_skb); -static bool __tcp_v4_inbound_md5_hash(struct sock *sk, - const struct sk_buff *skb) +/* Called with rcu_read_lock() */ +static bool tcp_v4_inbound_md5_hash(struct sock *sk, + const struct sk_buff *skb) { /* * This gets called for each TCP segment that arrives @@ -1193,7 +1154,7 @@ static bool __tcp_v4_inbound_md5_hash(struct sock *sk, */ genhash = tcp_v4_md5_hash_skb(newhash, hash_expected, - NULL, NULL, skb); + NULL, skb); if (genhash || memcmp(hash_location, newhash, 16) != 0) { net_info_ratelimited("MD5 Hash failed for (%pI4, %d)->(%pI4, %d)%s\n", @@ -1205,28 +1166,16 @@ static bool __tcp_v4_inbound_md5_hash(struct sock *sk, } return false; } - -static bool tcp_v4_inbound_md5_hash(struct sock *sk, const struct sk_buff *skb) -{ - bool ret; - - rcu_read_lock(); - ret = __tcp_v4_inbound_md5_hash(sk, skb); - rcu_read_unlock(); - - return ret; -} - #endif -static void tcp_v4_init_req(struct request_sock *req, struct sock *sk, +static void tcp_v4_init_req(struct request_sock *req, struct sock *sk_listener, 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; + sk_rcv_saddr_set(req_to_sk(req), ip_hdr(skb)->daddr); + sk_daddr_set(req_to_sk(req), ip_hdr(skb)->saddr); + ireq->no_srccheck = inet_sk(sk_listener)->transparent; ireq->opt = tcp_v4_save_options(skb); } @@ -1259,7 +1208,7 @@ struct request_sock_ops tcp_request_sock_ops __read_mostly = { 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, + .req_md5_lookup = tcp_v4_md5_lookup, .calc_md5_hash = tcp_v4_md5_hash_skb, #endif .init_req = tcp_v4_init_req, @@ -1318,8 +1267,8 @@ struct sock *tcp_v4_syn_recv_sock(struct sock *sk, struct sk_buff *skb, newtp = tcp_sk(newsk); newinet = inet_sk(newsk); ireq = inet_rsk(req); - newinet->inet_daddr = ireq->ir_rmt_addr; - newinet->inet_rcv_saddr = ireq->ir_loc_addr; + sk_daddr_set(newsk, ireq->ir_rmt_addr); + sk_rcv_saddr_set(newsk, ireq->ir_loc_addr); newinet->inet_saddr = ireq->ir_loc_addr; inet_opt = ireq->opt; rcu_assign_pointer(newinet->inet_opt, inet_opt); @@ -1356,7 +1305,7 @@ struct sock *tcp_v4_syn_recv_sock(struct sock *sk, struct sk_buff *skb, /* Copy over the MD5 key from the original socket */ key = tcp_md5_do_lookup(sk, (union tcp_md5_addr *)&newinet->inet_daddr, AF_INET); - if (key != NULL) { + if (key) { /* * We're using one, so create a matching key * on the newsk structure. If we fail to get @@ -1391,15 +1340,18 @@ EXPORT_SYMBOL(tcp_v4_syn_recv_sock); static struct sock *tcp_v4_hnd_req(struct sock *sk, struct sk_buff *skb) { - struct tcphdr *th = tcp_hdr(skb); + const struct tcphdr *th = tcp_hdr(skb); const struct iphdr *iph = ip_hdr(skb); + struct request_sock *req; struct sock *nsk; - struct request_sock **prev; - /* Find possible connection requests. */ - struct request_sock *req = inet_csk_search_req(sk, &prev, th->source, - iph->saddr, iph->daddr); - if (req) - return tcp_check_req(sk, skb, req, prev, false); + + req = inet_csk_search_req(sk, th->source, iph->saddr, iph->daddr); + if (req) { + nsk = tcp_check_req(sk, skb, req, false); + if (!nsk) + reqsk_put(req); + return nsk; + } nsk = inet_lookup_established(sock_net(sk), &tcp_hashinfo, iph->saddr, th->source, iph->daddr, th->dest, inet_iif(skb)); @@ -1439,7 +1391,7 @@ int tcp_v4_do_rcv(struct sock *sk, struct sk_buff *skb) sk_mark_napi_id(sk, skb); if (dst) { if (inet_sk(sk)->rx_dst_ifindex != skb->skb_iif || - dst->ops->check(dst, 0) == NULL) { + !dst->ops->check(dst, 0)) { dst_release(dst); sk->sk_rx_dst = NULL; } @@ -1517,7 +1469,7 @@ void tcp_v4_early_demux(struct sk_buff *skb) if (sk) { skb->sk = sk; skb->destructor = sock_edemux; - if (sk->sk_state != TCP_TIME_WAIT) { + if (sk_fullsock(sk)) { struct dst_entry *dst = READ_ONCE(sk->sk_rx_dst); if (dst) @@ -1734,7 +1686,7 @@ do_time_wait: iph->daddr, th->dest, inet_iif(skb)); if (sk2) { - inet_twsk_deschedule(inet_twsk(sk), &tcp_death_row); + inet_twsk_deschedule(inet_twsk(sk)); inet_twsk_put(inet_twsk(sk)); sk = sk2; goto process; @@ -1846,7 +1798,7 @@ void tcp_v4_destroy_sock(struct sock *sk) if (inet_csk(sk)->icsk_bind_hash) inet_put_port(sk); - BUG_ON(tp->fastopen_rsk != NULL); + BUG_ON(tp->fastopen_rsk); /* If socket is aborted during connect operation */ tcp_free_fastopen_req(tp); @@ -1904,13 +1856,13 @@ get_req: } sk = sk_nulls_next(st->syn_wait_sk); st->state = TCP_SEQ_STATE_LISTENING; - read_unlock_bh(&icsk->icsk_accept_queue.syn_wait_lock); + spin_unlock_bh(&icsk->icsk_accept_queue.syn_wait_lock); } else { icsk = inet_csk(sk); - read_lock_bh(&icsk->icsk_accept_queue.syn_wait_lock); + spin_lock_bh(&icsk->icsk_accept_queue.syn_wait_lock); if (reqsk_queue_len(&icsk->icsk_accept_queue)) goto start_req; - read_unlock_bh(&icsk->icsk_accept_queue.syn_wait_lock); + spin_unlock_bh(&icsk->icsk_accept_queue.syn_wait_lock); sk = sk_nulls_next(sk); } get_sk: @@ -1922,7 +1874,7 @@ get_sk: goto out; } icsk = inet_csk(sk); - read_lock_bh(&icsk->icsk_accept_queue.syn_wait_lock); + spin_lock_bh(&icsk->icsk_accept_queue.syn_wait_lock); if (reqsk_queue_len(&icsk->icsk_accept_queue)) { start_req: st->uid = sock_i_uid(sk); @@ -1931,7 +1883,7 @@ start_req: st->sbucket = 0; goto get_req; } - read_unlock_bh(&icsk->icsk_accept_queue.syn_wait_lock); + spin_unlock_bh(&icsk->icsk_accept_queue.syn_wait_lock); } spin_unlock_bh(&ilb->lock); st->offset = 0; @@ -2150,7 +2102,7 @@ static void tcp_seq_stop(struct seq_file *seq, void *v) case TCP_SEQ_STATE_OPENREQ: if (v) { struct inet_connection_sock *icsk = inet_csk(st->syn_wait_sk); - read_unlock_bh(&icsk->icsk_accept_queue.syn_wait_lock); + spin_unlock_bh(&icsk->icsk_accept_queue.syn_wait_lock); } case TCP_SEQ_STATE_LISTENING: if (v != SEQ_START_TOKEN) @@ -2204,17 +2156,17 @@ void tcp_proc_unregister(struct net *net, struct tcp_seq_afinfo *afinfo) } EXPORT_SYMBOL(tcp_proc_unregister); -static void get_openreq4(const struct sock *sk, const struct request_sock *req, +static void get_openreq4(const struct request_sock *req, struct seq_file *f, int i, kuid_t uid) { const struct inet_request_sock *ireq = inet_rsk(req); - long delta = req->expires - jiffies; + long delta = req->rsk_timer.expires - jiffies; seq_printf(f, "%4d: %08X:%04X %08X:%04X" " %02X %08X:%08X %02X:%08lX %08X %5u %8d %u %d %pK", i, ireq->ir_loc_addr, - ntohs(inet_sk(sk)->inet_sport), + ireq->ir_num, ireq->ir_rmt_addr, ntohs(ireq->ir_rmt_port), TCP_SYN_RECV, @@ -2225,7 +2177,7 @@ static void get_openreq4(const struct sock *sk, const struct request_sock *req, from_kuid_munged(seq_user_ns(f), uid), 0, /* non standard timer */ 0, /* open_requests have no inode */ - atomic_read(&sk->sk_refcnt), + 0, req); } @@ -2291,9 +2243,9 @@ static void get_tcp4_sock(struct sock *sk, struct seq_file *f, int i) static void get_timewait4_sock(const struct inet_timewait_sock *tw, struct seq_file *f, int i) { + long delta = tw->tw_timer.expires - jiffies; __be32 dest, src; __u16 destp, srcp; - s32 delta = tw->tw_ttd - inet_tw_time_stamp(); dest = tw->tw_daddr; src = tw->tw_rcv_saddr; @@ -2332,7 +2284,7 @@ static int tcp4_seq_show(struct seq_file *seq, void *v) get_tcp4_sock(v, seq, st->num); break; case TCP_SEQ_STATE_OPENREQ: - get_openreq4(st->syn_wait_sk, v, seq, st->num, st->uid); + get_openreq4(v, seq, st->num, st->uid); break; } out: @@ -2460,6 +2412,8 @@ static int __net_init tcp_sk_init(struct net *net) } net->ipv4.sysctl_tcp_ecn = 2; net->ipv4.sysctl_tcp_base_mss = TCP_BASE_MSS; + net->ipv4.sysctl_tcp_probe_threshold = TCP_PROBE_THRESHOLD; + net->ipv4.sysctl_tcp_probe_interval = TCP_PROBE_INTERVAL; return 0; fail: diff --git a/net/ipv4/tcp_metrics.c b/net/ipv4/tcp_metrics.c index e5f41bd5ec1b..a51d63a43e33 100644 --- a/net/ipv4/tcp_metrics.c +++ b/net/ipv4/tcp_metrics.c @@ -28,7 +28,8 @@ static struct tcp_metrics_block *__tcp_get_metrics(const struct inetpeer_addr *s struct tcp_fastopen_metrics { u16 mss; - u16 syn_loss:10; /* Recurring Fast Open SYN losses */ + u16 syn_loss:10, /* Recurring Fast Open SYN losses */ + try_exp:2; /* Request w/ exp. option (once) */ unsigned long last_syn_loss; /* Last Fast Open SYN loss */ struct tcp_fastopen_cookie cookie; }; @@ -40,6 +41,7 @@ struct tcp_fastopen_metrics { struct tcp_metrics_block { struct tcp_metrics_block __rcu *tcpm_next; + possible_net_t tcpm_net; struct inetpeer_addr tcpm_saddr; struct inetpeer_addr tcpm_daddr; unsigned long tcpm_stamp; @@ -52,6 +54,11 @@ struct tcp_metrics_block { struct rcu_head rcu_head; }; +static inline struct net *tm_net(struct tcp_metrics_block *tm) +{ + return read_pnet(&tm->tcpm_net); +} + static bool tcp_metric_locked(struct tcp_metrics_block *tm, enum tcp_metric_index idx) { @@ -74,23 +81,20 @@ static void tcp_metric_set(struct tcp_metrics_block *tm, static bool addr_same(const struct inetpeer_addr *a, const struct inetpeer_addr *b) { - const struct in6_addr *a6, *b6; - if (a->family != b->family) return false; if (a->family == AF_INET) return a->addr.a4 == b->addr.a4; - - a6 = (const struct in6_addr *) &a->addr.a6[0]; - b6 = (const struct in6_addr *) &b->addr.a6[0]; - - return ipv6_addr_equal(a6, b6); + return ipv6_addr_equal(&a->addr.in6, &b->addr.in6); } struct tcpm_hash_bucket { struct tcp_metrics_block __rcu *chain; }; +static struct tcpm_hash_bucket *tcp_metrics_hash __read_mostly; +static unsigned int tcp_metrics_hash_log __read_mostly; + static DEFINE_SPINLOCK(tcp_metrics_lock); static void tcpm_suck_dst(struct tcp_metrics_block *tm, @@ -128,6 +132,8 @@ static void tcpm_suck_dst(struct tcp_metrics_block *tm, if (fastopen_clear) { tm->tcpm_fastopen.mss = 0; tm->tcpm_fastopen.syn_loss = 0; + tm->tcpm_fastopen.try_exp = 0; + tm->tcpm_fastopen.cookie.exp = false; tm->tcpm_fastopen.cookie.len = 0; } } @@ -143,6 +149,9 @@ static void tcpm_check_stamp(struct tcp_metrics_block *tm, struct dst_entry *dst #define TCP_METRICS_RECLAIM_DEPTH 5 #define TCP_METRICS_RECLAIM_PTR (struct tcp_metrics_block *) 0x1UL +#define deref_locked(p) \ + rcu_dereference_protected(p, lockdep_is_held(&tcp_metrics_lock)) + static struct tcp_metrics_block *tcpm_new(struct dst_entry *dst, struct inetpeer_addr *saddr, struct inetpeer_addr *daddr, @@ -171,9 +180,9 @@ static struct tcp_metrics_block *tcpm_new(struct dst_entry *dst, if (unlikely(reclaim)) { struct tcp_metrics_block *oldest; - oldest = rcu_dereference(net->ipv4.tcp_metrics_hash[hash].chain); - for (tm = rcu_dereference(oldest->tcpm_next); tm; - tm = rcu_dereference(tm->tcpm_next)) { + oldest = deref_locked(tcp_metrics_hash[hash].chain); + for (tm = deref_locked(oldest->tcpm_next); tm; + tm = deref_locked(tm->tcpm_next)) { if (time_before(tm->tcpm_stamp, oldest->tcpm_stamp)) oldest = tm; } @@ -183,14 +192,15 @@ static struct tcp_metrics_block *tcpm_new(struct dst_entry *dst, if (!tm) goto out_unlock; } + write_pnet(&tm->tcpm_net, net); tm->tcpm_saddr = *saddr; tm->tcpm_daddr = *daddr; tcpm_suck_dst(tm, dst, true); if (likely(!reclaim)) { - tm->tcpm_next = net->ipv4.tcp_metrics_hash[hash].chain; - rcu_assign_pointer(net->ipv4.tcp_metrics_hash[hash].chain, tm); + tm->tcpm_next = tcp_metrics_hash[hash].chain; + rcu_assign_pointer(tcp_metrics_hash[hash].chain, tm); } out_unlock: @@ -214,10 +224,11 @@ static struct tcp_metrics_block *__tcp_get_metrics(const struct inetpeer_addr *s struct tcp_metrics_block *tm; int depth = 0; - for (tm = rcu_dereference(net->ipv4.tcp_metrics_hash[hash].chain); tm; + for (tm = rcu_dereference(tcp_metrics_hash[hash].chain); tm; tm = rcu_dereference(tm->tcpm_next)) { if (addr_same(&tm->tcpm_saddr, saddr) && - addr_same(&tm->tcpm_daddr, daddr)) + addr_same(&tm->tcpm_daddr, daddr) && + net_eq(tm_net(tm), net)) break; depth++; } @@ -242,8 +253,8 @@ static struct tcp_metrics_block *__tcp_get_metrics_req(struct request_sock *req, break; #if IS_ENABLED(CONFIG_IPV6) case AF_INET6: - *(struct in6_addr *)saddr.addr.a6 = inet_rsk(req)->ir_v6_loc_addr; - *(struct in6_addr *)daddr.addr.a6 = inet_rsk(req)->ir_v6_rmt_addr; + saddr.addr.in6 = inet_rsk(req)->ir_v6_loc_addr; + daddr.addr.in6 = inet_rsk(req)->ir_v6_rmt_addr; hash = ipv6_addr_hash(&inet_rsk(req)->ir_v6_rmt_addr); break; #endif @@ -252,12 +263,14 @@ static struct tcp_metrics_block *__tcp_get_metrics_req(struct request_sock *req, } net = dev_net(dst->dev); - hash = hash_32(hash, net->ipv4.tcp_metrics_hash_log); + hash ^= net_hash_mix(net); + hash = hash_32(hash, tcp_metrics_hash_log); - for (tm = rcu_dereference(net->ipv4.tcp_metrics_hash[hash].chain); tm; + for (tm = rcu_dereference(tcp_metrics_hash[hash].chain); tm; tm = rcu_dereference(tm->tcpm_next)) { if (addr_same(&tm->tcpm_saddr, &saddr) && - addr_same(&tm->tcpm_daddr, &daddr)) + addr_same(&tm->tcpm_daddr, &daddr) && + net_eq(tm_net(tm), net)) break; } tcpm_check_stamp(tm, dst); @@ -288,9 +301,9 @@ static struct tcp_metrics_block *__tcp_get_metrics_tw(struct inet_timewait_sock hash = (__force unsigned int) daddr.addr.a4; } else { saddr.family = AF_INET6; - *(struct in6_addr *)saddr.addr.a6 = tw->tw_v6_rcv_saddr; + saddr.addr.in6 = tw->tw_v6_rcv_saddr; daddr.family = AF_INET6; - *(struct in6_addr *)daddr.addr.a6 = tw->tw_v6_daddr; + daddr.addr.in6 = tw->tw_v6_daddr; hash = ipv6_addr_hash(&tw->tw_v6_daddr); } } @@ -299,12 +312,14 @@ static struct tcp_metrics_block *__tcp_get_metrics_tw(struct inet_timewait_sock return NULL; net = twsk_net(tw); - hash = hash_32(hash, net->ipv4.tcp_metrics_hash_log); + hash ^= net_hash_mix(net); + hash = hash_32(hash, tcp_metrics_hash_log); - for (tm = rcu_dereference(net->ipv4.tcp_metrics_hash[hash].chain); tm; + for (tm = rcu_dereference(tcp_metrics_hash[hash].chain); tm; tm = rcu_dereference(tm->tcpm_next)) { if (addr_same(&tm->tcpm_saddr, &saddr) && - addr_same(&tm->tcpm_daddr, &daddr)) + addr_same(&tm->tcpm_daddr, &daddr) && + net_eq(tm_net(tm), net)) break; } return tm; @@ -336,9 +351,9 @@ static struct tcp_metrics_block *tcp_get_metrics(struct sock *sk, hash = (__force unsigned int) daddr.addr.a4; } else { saddr.family = AF_INET6; - *(struct in6_addr *)saddr.addr.a6 = sk->sk_v6_rcv_saddr; + saddr.addr.in6 = sk->sk_v6_rcv_saddr; daddr.family = AF_INET6; - *(struct in6_addr *)daddr.addr.a6 = sk->sk_v6_daddr; + daddr.addr.in6 = sk->sk_v6_daddr; hash = ipv6_addr_hash(&sk->sk_v6_daddr); } } @@ -347,7 +362,8 @@ static struct tcp_metrics_block *tcp_get_metrics(struct sock *sk, return NULL; net = dev_net(dst->dev); - hash = hash_32(hash, net->ipv4.tcp_metrics_hash_log); + hash ^= net_hash_mix(net); + hash = hash_32(hash, tcp_metrics_hash_log); tm = __tcp_get_metrics(&saddr, &daddr, net, hash); if (tm == TCP_METRICS_RECLAIM_PTR) @@ -492,7 +508,7 @@ void tcp_init_metrics(struct sock *sk) struct tcp_metrics_block *tm; u32 val, crtt = 0; /* cached RTT scaled by 8 */ - if (dst == NULL) + if (!dst) goto reset; dst_confirm(dst); @@ -700,6 +716,8 @@ void tcp_fastopen_cache_get(struct sock *sk, u16 *mss, if (tfom->mss) *mss = tfom->mss; *cookie = tfom->cookie; + if (cookie->len <= 0 && tfom->try_exp == 1) + cookie->exp = true; *syn_loss = tfom->syn_loss; *last_syn_loss = *syn_loss ? tfom->last_syn_loss : 0; } while (read_seqretry(&fastopen_seqlock, seq)); @@ -708,7 +726,8 @@ void tcp_fastopen_cache_get(struct sock *sk, u16 *mss, } void tcp_fastopen_cache_set(struct sock *sk, u16 mss, - struct tcp_fastopen_cookie *cookie, bool syn_lost) + struct tcp_fastopen_cookie *cookie, bool syn_lost, + u16 try_exp) { struct dst_entry *dst = __sk_dst_get(sk); struct tcp_metrics_block *tm; @@ -725,6 +744,9 @@ void tcp_fastopen_cache_set(struct sock *sk, u16 mss, tfom->mss = mss; if (cookie && cookie->len > 0) tfom->cookie = *cookie; + else if (try_exp > tfom->try_exp && + tfom->cookie.len <= 0 && !tfom->cookie.exp) + tfom->try_exp = try_exp; if (syn_lost) { ++tfom->syn_loss; tfom->last_syn_loss = jiffies; @@ -773,19 +795,19 @@ static int tcp_metrics_fill_info(struct sk_buff *msg, switch (tm->tcpm_daddr.family) { case AF_INET: - if (nla_put_be32(msg, TCP_METRICS_ATTR_ADDR_IPV4, - tm->tcpm_daddr.addr.a4) < 0) + if (nla_put_in_addr(msg, TCP_METRICS_ATTR_ADDR_IPV4, + tm->tcpm_daddr.addr.a4) < 0) goto nla_put_failure; - if (nla_put_be32(msg, TCP_METRICS_ATTR_SADDR_IPV4, - tm->tcpm_saddr.addr.a4) < 0) + if (nla_put_in_addr(msg, TCP_METRICS_ATTR_SADDR_IPV4, + tm->tcpm_saddr.addr.a4) < 0) goto nla_put_failure; break; case AF_INET6: - if (nla_put(msg, TCP_METRICS_ATTR_ADDR_IPV6, 16, - tm->tcpm_daddr.addr.a6) < 0) + if (nla_put_in6_addr(msg, TCP_METRICS_ATTR_ADDR_IPV6, + &tm->tcpm_daddr.addr.in6) < 0) goto nla_put_failure; - if (nla_put(msg, TCP_METRICS_ATTR_SADDR_IPV6, 16, - tm->tcpm_saddr.addr.a6) < 0) + if (nla_put_in6_addr(msg, TCP_METRICS_ATTR_SADDR_IPV6, + &tm->tcpm_saddr.addr.in6) < 0) goto nla_put_failure; break; default: @@ -898,17 +920,19 @@ static int tcp_metrics_nl_dump(struct sk_buff *skb, struct netlink_callback *cb) { struct net *net = sock_net(skb->sk); - unsigned int max_rows = 1U << net->ipv4.tcp_metrics_hash_log; + unsigned int max_rows = 1U << tcp_metrics_hash_log; unsigned int row, s_row = cb->args[0]; int s_col = cb->args[1], col = s_col; for (row = s_row; row < max_rows; row++, s_col = 0) { struct tcp_metrics_block *tm; - struct tcpm_hash_bucket *hb = net->ipv4.tcp_metrics_hash + row; + struct tcpm_hash_bucket *hb = tcp_metrics_hash + row; rcu_read_lock(); for (col = 0, tm = rcu_dereference(hb->chain); tm; tm = rcu_dereference(tm->tcpm_next), col++) { + if (!net_eq(tm_net(tm), net)) + continue; if (col < s_col) continue; if (tcp_metrics_dump_info(skb, cb, tm) < 0) { @@ -933,7 +957,7 @@ static int __parse_nl_addr(struct genl_info *info, struct inetpeer_addr *addr, a = info->attrs[v4]; if (a) { addr->family = AF_INET; - addr->addr.a4 = nla_get_be32(a); + addr->addr.a4 = nla_get_in_addr(a); if (hash) *hash = (__force unsigned int) addr->addr.a4; return 0; @@ -943,9 +967,9 @@ static int __parse_nl_addr(struct genl_info *info, struct inetpeer_addr *addr, if (nla_len(a) != sizeof(struct in6_addr)) return -EINVAL; addr->family = AF_INET6; - memcpy(addr->addr.a6, nla_data(a), sizeof(addr->addr.a6)); + addr->addr.in6 = nla_get_in6_addr(a); if (hash) - *hash = ipv6_addr_hash((struct in6_addr *) addr->addr.a6); + *hash = ipv6_addr_hash(&addr->addr.in6); return 0; } return optional ? 1 : -EAFNOSUPPORT; @@ -994,13 +1018,15 @@ static int tcp_metrics_nl_cmd_get(struct sk_buff *skb, struct genl_info *info) if (!reply) goto nla_put_failure; - hash = hash_32(hash, net->ipv4.tcp_metrics_hash_log); + hash ^= net_hash_mix(net); + hash = hash_32(hash, tcp_metrics_hash_log); ret = -ESRCH; rcu_read_lock(); - for (tm = rcu_dereference(net->ipv4.tcp_metrics_hash[hash].chain); tm; + for (tm = rcu_dereference(tcp_metrics_hash[hash].chain); tm; tm = rcu_dereference(tm->tcpm_next)) { if (addr_same(&tm->tcpm_daddr, &daddr) && - (!src || addr_same(&tm->tcpm_saddr, &saddr))) { + (!src || addr_same(&tm->tcpm_saddr, &saddr)) && + net_eq(tm_net(tm), net)) { ret = tcp_metrics_fill_info(msg, tm); break; } @@ -1020,34 +1046,27 @@ out_free: return ret; } -#define deref_locked_genl(p) \ - rcu_dereference_protected(p, lockdep_genl_is_held() && \ - lockdep_is_held(&tcp_metrics_lock)) - -#define deref_genl(p) rcu_dereference_protected(p, lockdep_genl_is_held()) - -static int tcp_metrics_flush_all(struct net *net) +static void tcp_metrics_flush_all(struct net *net) { - unsigned int max_rows = 1U << net->ipv4.tcp_metrics_hash_log; - struct tcpm_hash_bucket *hb = net->ipv4.tcp_metrics_hash; + unsigned int max_rows = 1U << tcp_metrics_hash_log; + struct tcpm_hash_bucket *hb = tcp_metrics_hash; struct tcp_metrics_block *tm; unsigned int row; for (row = 0; row < max_rows; row++, hb++) { + struct tcp_metrics_block __rcu **pp; spin_lock_bh(&tcp_metrics_lock); - tm = deref_locked_genl(hb->chain); - if (tm) - hb->chain = NULL; - spin_unlock_bh(&tcp_metrics_lock); - while (tm) { - struct tcp_metrics_block *next; - - next = deref_genl(tm->tcpm_next); - kfree_rcu(tm, rcu_head); - tm = next; + pp = &hb->chain; + for (tm = deref_locked(*pp); tm; tm = deref_locked(*pp)) { + if (net_eq(tm_net(tm), net)) { + *pp = tm->tcpm_next; + kfree_rcu(tm, rcu_head); + } else { + pp = &tm->tcpm_next; + } } + spin_unlock_bh(&tcp_metrics_lock); } - return 0; } static int tcp_metrics_nl_cmd_del(struct sk_buff *skb, struct genl_info *info) @@ -1064,19 +1083,23 @@ static int tcp_metrics_nl_cmd_del(struct sk_buff *skb, struct genl_info *info) ret = parse_nl_addr(info, &daddr, &hash, 1); if (ret < 0) return ret; - if (ret > 0) - return tcp_metrics_flush_all(net); + if (ret > 0) { + tcp_metrics_flush_all(net); + return 0; + } ret = parse_nl_saddr(info, &saddr); if (ret < 0) src = false; - hash = hash_32(hash, net->ipv4.tcp_metrics_hash_log); - hb = net->ipv4.tcp_metrics_hash + hash; + hash ^= net_hash_mix(net); + hash = hash_32(hash, tcp_metrics_hash_log); + hb = tcp_metrics_hash + hash; pp = &hb->chain; spin_lock_bh(&tcp_metrics_lock); - for (tm = deref_locked_genl(*pp); tm; tm = deref_locked_genl(*pp)) { + for (tm = deref_locked(*pp); tm; tm = deref_locked(*pp)) { if (addr_same(&tm->tcpm_daddr, &daddr) && - (!src || addr_same(&tm->tcpm_saddr, &saddr))) { + (!src || addr_same(&tm->tcpm_saddr, &saddr)) && + net_eq(tm_net(tm), net)) { *pp = tm->tcpm_next; kfree_rcu(tm, rcu_head); found = true; @@ -1126,6 +1149,9 @@ static int __net_init tcp_net_metrics_init(struct net *net) size_t size; unsigned int slots; + if (!net_eq(net, &init_net)) + return 0; + slots = tcpmhash_entries; if (!slots) { if (totalram_pages >= 128 * 1024) @@ -1134,14 +1160,14 @@ static int __net_init tcp_net_metrics_init(struct net *net) slots = 8 * 1024; } - net->ipv4.tcp_metrics_hash_log = order_base_2(slots); - size = sizeof(struct tcpm_hash_bucket) << net->ipv4.tcp_metrics_hash_log; + tcp_metrics_hash_log = order_base_2(slots); + size = sizeof(struct tcpm_hash_bucket) << tcp_metrics_hash_log; - net->ipv4.tcp_metrics_hash = kzalloc(size, GFP_KERNEL | __GFP_NOWARN); - if (!net->ipv4.tcp_metrics_hash) - net->ipv4.tcp_metrics_hash = vzalloc(size); + tcp_metrics_hash = kzalloc(size, GFP_KERNEL | __GFP_NOWARN); + if (!tcp_metrics_hash) + tcp_metrics_hash = vzalloc(size); - if (!net->ipv4.tcp_metrics_hash) + if (!tcp_metrics_hash) return -ENOMEM; return 0; @@ -1149,19 +1175,7 @@ static int __net_init tcp_net_metrics_init(struct net *net) static void __net_exit tcp_net_metrics_exit(struct net *net) { - unsigned int i; - - for (i = 0; i < (1U << net->ipv4.tcp_metrics_hash_log) ; i++) { - struct tcp_metrics_block *tm, *next; - - tm = rcu_dereference_protected(net->ipv4.tcp_metrics_hash[i].chain, 1); - while (tm) { - next = rcu_dereference_protected(tm->tcpm_next, 1); - kfree(tm); - tm = next; - } - } - kvfree(net->ipv4.tcp_metrics_hash); + tcp_metrics_flush_all(net); } static __net_initdata struct pernet_operations tcp_net_metrics_ops = { @@ -1175,16 +1189,10 @@ void __init tcp_metrics_init(void) ret = register_pernet_subsys(&tcp_net_metrics_ops); if (ret < 0) - goto cleanup; + panic("Could not allocate the tcp_metrics hash table\n"); + ret = genl_register_family_with_ops(&tcp_metrics_nl_family, tcp_metrics_nl_ops); if (ret < 0) - goto cleanup_subsys; - return; - -cleanup_subsys: - unregister_pernet_subsys(&tcp_net_metrics_ops); - -cleanup: - return; + panic("Could not register tcp_metrics generic netlink\n"); } diff --git a/net/ipv4/tcp_minisocks.c b/net/ipv4/tcp_minisocks.c index dd11ac7798c6..e5d7649136fc 100644 --- a/net/ipv4/tcp_minisocks.c +++ b/net/ipv4/tcp_minisocks.c @@ -34,18 +34,7 @@ int sysctl_tcp_abort_on_overflow __read_mostly; struct inet_timewait_death_row tcp_death_row = { .sysctl_max_tw_buckets = NR_FILE * 2, - .period = TCP_TIMEWAIT_LEN / INET_TWDR_TWKILL_SLOTS, - .death_lock = __SPIN_LOCK_UNLOCKED(tcp_death_row.death_lock), .hashinfo = &tcp_hashinfo, - .tw_timer = TIMER_INITIALIZER(inet_twdr_hangman, 0, - (unsigned long)&tcp_death_row), - .twkill_work = __WORK_INITIALIZER(tcp_death_row.twkill_work, - inet_twdr_twkill_work), -/* Short-time timewait calendar */ - - .twcal_hand = -1, - .twcal_timer = TIMER_INITIALIZER(inet_twdr_twcal_tick, 0, - (unsigned long)&tcp_death_row), }; EXPORT_SYMBOL_GPL(tcp_death_row); @@ -158,7 +147,7 @@ tcp_timewait_state_process(struct inet_timewait_sock *tw, struct sk_buff *skb, if (!th->fin || TCP_SKB_CB(skb)->end_seq != tcptw->tw_rcv_nxt + 1) { kill_with_rst: - inet_twsk_deschedule(tw, &tcp_death_row); + inet_twsk_deschedule(tw); inet_twsk_put(tw); return TCP_TW_RST; } @@ -174,11 +163,9 @@ kill_with_rst: if (tcp_death_row.sysctl_tw_recycle && tcptw->tw_ts_recent_stamp && tcp_tw_remember_stamp(tw)) - inet_twsk_schedule(tw, &tcp_death_row, tw->tw_timeout, - TCP_TIMEWAIT_LEN); + inet_twsk_schedule(tw, tw->tw_timeout); else - inet_twsk_schedule(tw, &tcp_death_row, TCP_TIMEWAIT_LEN, - TCP_TIMEWAIT_LEN); + inet_twsk_schedule(tw, TCP_TIMEWAIT_LEN); return TCP_TW_ACK; } @@ -211,13 +198,12 @@ kill_with_rst: */ if (sysctl_tcp_rfc1337 == 0) { kill: - inet_twsk_deschedule(tw, &tcp_death_row); + inet_twsk_deschedule(tw); inet_twsk_put(tw); return TCP_TW_SUCCESS; } } - inet_twsk_schedule(tw, &tcp_death_row, TCP_TIMEWAIT_LEN, - TCP_TIMEWAIT_LEN); + inet_twsk_schedule(tw, TCP_TIMEWAIT_LEN); if (tmp_opt.saw_tstamp) { tcptw->tw_ts_recent = tmp_opt.rcv_tsval; @@ -267,8 +253,7 @@ kill: * Do not reschedule in the last case. */ if (paws_reject || th->ack) - inet_twsk_schedule(tw, &tcp_death_row, TCP_TIMEWAIT_LEN, - TCP_TIMEWAIT_LEN); + inet_twsk_schedule(tw, TCP_TIMEWAIT_LEN); return tcp_timewait_check_oow_rate_limit( tw, skb, LINUX_MIB_TCPACKSKIPPEDTIMEWAIT); @@ -283,18 +268,17 @@ EXPORT_SYMBOL(tcp_timewait_state_process); */ void tcp_time_wait(struct sock *sk, int state, int timeo) { - struct inet_timewait_sock *tw = NULL; const struct inet_connection_sock *icsk = inet_csk(sk); const struct tcp_sock *tp = tcp_sk(sk); + struct inet_timewait_sock *tw; bool recycle_ok = false; if (tcp_death_row.sysctl_tw_recycle && tp->rx_opt.ts_recent_stamp) recycle_ok = tcp_remember_stamp(sk); - if (tcp_death_row.tw_count < tcp_death_row.sysctl_max_tw_buckets) - tw = inet_twsk_alloc(sk, state); + tw = inet_twsk_alloc(sk, &tcp_death_row, state); - if (tw != NULL) { + if (tw) { struct tcp_timewait_sock *tcptw = tcp_twsk((struct sock *)tw); const int rto = (icsk->icsk_rto << 2) - (icsk->icsk_rto >> 1); struct inet_sock *inet = inet_sk(sk); @@ -332,7 +316,7 @@ void tcp_time_wait(struct sock *sk, int state, int timeo) struct tcp_md5sig_key *key; tcptw->tw_md5_key = NULL; key = tp->af_specific->md5_lookup(sk, sk); - if (key != NULL) { + if (key) { tcptw->tw_md5_key = kmemdup(key, sizeof(*key), GFP_ATOMIC); if (tcptw->tw_md5_key && !tcp_alloc_md5sig_pool()) BUG(); @@ -355,8 +339,7 @@ void tcp_time_wait(struct sock *sk, int state, int timeo) timeo = TCP_TIMEWAIT_LEN; } - inet_twsk_schedule(tw, &tcp_death_row, timeo, - TCP_TIMEWAIT_LEN); + inet_twsk_schedule(tw, timeo); inet_twsk_put(tw); } else { /* Sorry, if we're out of memory, just CLOSE this @@ -454,7 +437,7 @@ struct sock *tcp_create_openreq_child(struct sock *sk, struct request_sock *req, { struct sock *newsk = inet_csk_clone_lock(sk, req, GFP_ATOMIC); - if (newsk != NULL) { + if (newsk) { const struct inet_request_sock *ireq = inet_rsk(req); struct tcp_request_sock *treq = tcp_rsk(req); struct inet_connection_sock *newicsk = inet_csk(newsk); @@ -572,7 +555,6 @@ EXPORT_SYMBOL(tcp_create_openreq_child); struct sock *tcp_check_req(struct sock *sk, struct sk_buff *skb, struct request_sock *req, - struct request_sock **prev, bool fastopen) { struct tcp_options_received tmp_opt; @@ -629,9 +611,16 @@ struct sock *tcp_check_req(struct sock *sk, struct sk_buff *skb, LINUX_MIB_TCPACKSKIPPEDSYNRECV, &tcp_rsk(req)->last_oow_ack_time) && - !inet_rtx_syn_ack(sk, req)) - req->expires = min(TCP_TIMEOUT_INIT << req->num_timeout, - TCP_RTO_MAX) + jiffies; + !inet_rtx_syn_ack(sk, req)) { + unsigned long expires = jiffies; + + expires += min(TCP_TIMEOUT_INIT << req->num_timeout, + TCP_RTO_MAX); + if (!fastopen) + mod_timer_pending(&req->rsk_timer, expires); + else + req->rsk_timer.expires = expires; + } return NULL; } @@ -763,13 +752,14 @@ struct sock *tcp_check_req(struct sock *sk, struct sk_buff *skb, * socket is created, wait for troubles. */ child = inet_csk(sk)->icsk_af_ops->syn_recv_sock(sk, skb, req, NULL); - if (child == NULL) + if (!child) goto listen_overflow; - inet_csk_reqsk_queue_unlink(sk, req, prev); - inet_csk_reqsk_queue_removed(sk, req); - + inet_csk_reqsk_queue_drop(sk, req); inet_csk_reqsk_queue_add(sk, req, child); + /* Warning: caller must not call reqsk_put(req); + * child stole last reference on it. + */ return child; listen_overflow: @@ -791,7 +781,7 @@ embryonic_reset: tcp_reset(sk); } if (!fastopen) { - inet_csk_reqsk_queue_drop(sk, req, prev); + inet_csk_reqsk_queue_drop(sk, req); NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_EMBRYONICRSTS); } return NULL; diff --git a/net/ipv4/tcp_offload.c b/net/ipv4/tcp_offload.c index 9d7930ba8e0f..3f7c2fca5431 100644 --- a/net/ipv4/tcp_offload.c +++ b/net/ipv4/tcp_offload.c @@ -29,8 +29,8 @@ static void tcp_gso_tstamp(struct sk_buff *skb, unsigned int ts_seq, } } -struct sk_buff *tcp4_gso_segment(struct sk_buff *skb, - netdev_features_t features) +static struct sk_buff *tcp4_gso_segment(struct sk_buff *skb, + netdev_features_t features) { if (!pskb_may_pull(skb, sizeof(struct tcphdr))) return ERR_PTR(-EINVAL); diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c index 1db253e36045..a369e8a70b2c 100644 --- a/net/ipv4/tcp_output.c +++ b/net/ipv4/tcp_output.c @@ -518,17 +518,26 @@ static void tcp_options_write(__be32 *ptr, struct tcp_sock *tp, if (unlikely(OPTION_FAST_OPEN_COOKIE & options)) { struct tcp_fastopen_cookie *foc = opts->fastopen_cookie; + u8 *p = (u8 *)ptr; + u32 len; /* Fast Open option length */ + + if (foc->exp) { + len = TCPOLEN_EXP_FASTOPEN_BASE + foc->len; + *ptr = htonl((TCPOPT_EXP << 24) | (len << 16) | + TCPOPT_FASTOPEN_MAGIC); + p += TCPOLEN_EXP_FASTOPEN_BASE; + } else { + len = TCPOLEN_FASTOPEN_BASE + foc->len; + *p++ = TCPOPT_FASTOPEN; + *p++ = len; + } - *ptr++ = htonl((TCPOPT_EXP << 24) | - ((TCPOLEN_EXP_FASTOPEN_BASE + foc->len) << 16) | - TCPOPT_FASTOPEN_MAGIC); - - memcpy(ptr, foc->val, foc->len); - if ((foc->len & 3) == 2) { - u8 *align = ((u8 *)ptr) + foc->len; - align[0] = align[1] = TCPOPT_NOP; + memcpy(p, foc->val, foc->len); + if ((len & 3) == 2) { + p[foc->len] = TCPOPT_NOP; + p[foc->len + 1] = TCPOPT_NOP; } - ptr += (foc->len + 3) >> 2; + ptr += (len + 3) >> 2; } } @@ -565,7 +574,7 @@ static unsigned int tcp_syn_options(struct sock *sk, struct sk_buff *skb, opts->mss = tcp_advertise_mss(sk); remaining -= TCPOLEN_MSS_ALIGNED; - if (likely(sysctl_tcp_timestamps && *md5 == NULL)) { + if (likely(sysctl_tcp_timestamps && !*md5)) { opts->options |= OPTION_TS; opts->tsval = tcp_skb_timestamp(skb) + tp->tsoffset; opts->tsecr = tp->rx_opt.ts_recent; @@ -583,13 +592,17 @@ static unsigned int tcp_syn_options(struct sock *sk, struct sk_buff *skb, } if (fastopen && fastopen->cookie.len >= 0) { - u32 need = TCPOLEN_EXP_FASTOPEN_BASE + fastopen->cookie.len; + u32 need = fastopen->cookie.len; + + need += fastopen->cookie.exp ? TCPOLEN_EXP_FASTOPEN_BASE : + TCPOLEN_FASTOPEN_BASE; need = (need + 3) & ~3U; /* Align to 32 bits */ if (remaining >= need) { opts->options |= OPTION_FAST_OPEN_COOKIE; opts->fastopen_cookie = &fastopen->cookie; remaining -= need; tp->syn_fastopen = 1; + tp->syn_fastopen_exp = fastopen->cookie.exp ? 1 : 0; } } @@ -601,15 +614,14 @@ static unsigned int tcp_synack_options(struct sock *sk, struct request_sock *req, unsigned int mss, struct sk_buff *skb, struct tcp_out_options *opts, - struct tcp_md5sig_key **md5, + const struct tcp_md5sig_key *md5, struct tcp_fastopen_cookie *foc) { struct inet_request_sock *ireq = inet_rsk(req); unsigned int remaining = MAX_TCP_OPTION_SPACE; #ifdef CONFIG_TCP_MD5SIG - *md5 = tcp_rsk(req)->af_specific->md5_lookup(sk, req); - if (*md5) { + if (md5) { opts->options |= OPTION_MD5; remaining -= TCPOLEN_MD5SIG_ALIGNED; @@ -620,8 +632,6 @@ static unsigned int tcp_synack_options(struct sock *sk, */ ireq->tstamp_ok &= !ireq->sack_ok; } -#else - *md5 = NULL; #endif /* We always send an MSS option. */ @@ -645,7 +655,10 @@ static unsigned int tcp_synack_options(struct sock *sk, remaining -= TCPOLEN_SACKPERM_ALIGNED; } if (foc != NULL && foc->len >= 0) { - u32 need = TCPOLEN_EXP_FASTOPEN_BASE + foc->len; + u32 need = foc->len; + + need += foc->exp ? TCPOLEN_EXP_FASTOPEN_BASE : + TCPOLEN_FASTOPEN_BASE; need = (need + 3) & ~3U; /* Align to 32 bits */ if (remaining >= need) { opts->options |= OPTION_FAST_OPEN_COOKIE; @@ -989,7 +1002,7 @@ static int tcp_transmit_skb(struct sock *sk, struct sk_buff *skb, int clone_it, if (md5) { sk_nocaps_add(sk, NETIF_F_GSO_MASK); tp->af_specific->calc_md5_hash(opts.hash_location, - md5, sk, NULL, skb); + md5, sk, skb); } #endif @@ -1151,7 +1164,7 @@ int tcp_fragment(struct sock *sk, struct sk_buff *skb, u32 len, /* Get a new skb... force flag on. */ buff = sk_stream_alloc_skb(sk, nsize, gfp); - if (buff == NULL) + if (!buff) return -ENOMEM; /* We'll just try again later. */ sk->sk_wmem_queued += buff->truesize; @@ -1354,6 +1367,8 @@ void tcp_mtup_init(struct sock *sk) icsk->icsk_af_ops->net_header_len; icsk->icsk_mtup.search_low = tcp_mss_to_mtu(sk, net->ipv4.sysctl_tcp_base_mss); icsk->icsk_mtup.probe_size = 0; + if (icsk->icsk_mtup.enabled) + icsk->icsk_mtup.probe_timestamp = tcp_time_stamp; } EXPORT_SYMBOL(tcp_mtup_init); @@ -1708,7 +1723,7 @@ static int tso_fragment(struct sock *sk, struct sk_buff *skb, unsigned int len, return tcp_fragment(sk, skb, len, mss_now, gfp); buff = sk_stream_alloc_skb(sk, 0, gfp); - if (unlikely(buff == NULL)) + if (unlikely(!buff)) return -ENOMEM; sk->sk_wmem_queued += buff->truesize; @@ -1752,20 +1767,23 @@ static int tso_fragment(struct sock *sk, struct sk_buff *skb, unsigned int len, static bool tcp_tso_should_defer(struct sock *sk, struct sk_buff *skb, bool *is_cwnd_limited, u32 max_segs) { - struct tcp_sock *tp = tcp_sk(sk); const struct inet_connection_sock *icsk = inet_csk(sk); - u32 send_win, cong_win, limit, in_flight; + u32 age, send_win, cong_win, limit, in_flight; + struct tcp_sock *tp = tcp_sk(sk); + struct skb_mstamp now; + struct sk_buff *head; int win_divisor; if (TCP_SKB_CB(skb)->tcp_flags & TCPHDR_FIN) goto send_now; - if (icsk->icsk_ca_state != TCP_CA_Open) + if (!((1 << icsk->icsk_ca_state) & (TCPF_CA_Open | TCPF_CA_CWR))) goto send_now; - /* Defer for less than two clock ticks. */ - if (tp->tso_deferred && - (((u32)jiffies << 1) >> 1) - (tp->tso_deferred >> 1) > 1) + /* Avoid bursty behavior by allowing defer + * only if the last write was recent. + */ + if ((s32)(tcp_time_stamp - tp->lsndtime) > 0) goto send_now; in_flight = tcp_packets_in_flight(tp); @@ -1807,11 +1825,14 @@ static bool tcp_tso_should_defer(struct sock *sk, struct sk_buff *skb, goto send_now; } - /* Ok, it looks like it is advisable to defer. - * Do not rearm the timer if already set to not break TCP ACK clocking. - */ - if (!tp->tso_deferred) - tp->tso_deferred = 1 | (jiffies << 1); + head = tcp_write_queue_head(sk); + skb_mstamp_get(&now); + age = skb_mstamp_us_delta(&now, &head->skb_mstamp); + /* If next ACK is likely to come too late (half srtt), do not defer */ + if (age < (tp->srtt_us >> 4)) + goto send_now; + + /* Ok, it looks like it is advisable to defer. */ if (cong_win < send_win && cong_win < skb->len) *is_cwnd_limited = true; @@ -1819,10 +1840,34 @@ static bool tcp_tso_should_defer(struct sock *sk, struct sk_buff *skb, return true; send_now: - tp->tso_deferred = 0; return false; } +static inline void tcp_mtu_check_reprobe(struct sock *sk) +{ + struct inet_connection_sock *icsk = inet_csk(sk); + struct tcp_sock *tp = tcp_sk(sk); + struct net *net = sock_net(sk); + u32 interval; + s32 delta; + + interval = net->ipv4.sysctl_tcp_probe_interval; + delta = tcp_time_stamp - icsk->icsk_mtup.probe_timestamp; + if (unlikely(delta >= interval * HZ)) { + int mss = tcp_current_mss(sk); + + /* Update current search range */ + icsk->icsk_mtup.probe_size = 0; + icsk->icsk_mtup.search_high = tp->rx_opt.mss_clamp + + sizeof(struct tcphdr) + + icsk->icsk_af_ops->net_header_len; + icsk->icsk_mtup.search_low = tcp_mss_to_mtu(sk, mss); + + /* Update probe time stamp */ + icsk->icsk_mtup.probe_timestamp = tcp_time_stamp; + } +} + /* Create a new MTU probe if we are ready. * MTU probe is regularly attempting to increase the path MTU by * deliberately sending larger packets. This discovers routing @@ -1837,11 +1882,13 @@ static int tcp_mtu_probe(struct sock *sk) struct tcp_sock *tp = tcp_sk(sk); struct inet_connection_sock *icsk = inet_csk(sk); struct sk_buff *skb, *nskb, *next; + struct net *net = sock_net(sk); int len; int probe_size; int size_needed; int copy; int mss_now; + int interval; /* Not currently probing/verifying, * not in recovery, @@ -1854,12 +1901,25 @@ static int tcp_mtu_probe(struct sock *sk) tp->rx_opt.num_sacks || tp->rx_opt.dsack) return -1; - /* Very simple search strategy: just double the MSS. */ + /* Use binary search for probe_size between tcp_mss_base, + * and current mss_clamp. if (search_high - search_low) + * smaller than a threshold, backoff from probing. + */ mss_now = tcp_current_mss(sk); - probe_size = 2 * tp->mss_cache; + probe_size = tcp_mtu_to_mss(sk, (icsk->icsk_mtup.search_high + + icsk->icsk_mtup.search_low) >> 1); size_needed = probe_size + (tp->reordering + 1) * tp->mss_cache; - if (probe_size > tcp_mtu_to_mss(sk, icsk->icsk_mtup.search_high)) { - /* TODO: set timer for probe_converge_event */ + interval = icsk->icsk_mtup.search_high - icsk->icsk_mtup.search_low; + /* When misfortune happens, we are reprobing actively, + * and then reprobe timer has expired. We stick with current + * probing process by not resetting search range to its orignal. + */ + if (probe_size > tcp_mtu_to_mss(sk, icsk->icsk_mtup.search_high) || + interval < net->ipv4.sysctl_tcp_probe_threshold) { + /* Check whether enough time has elaplased for + * another round of probing. + */ + tcp_mtu_check_reprobe(sk); return -1; } @@ -1881,7 +1941,8 @@ static int tcp_mtu_probe(struct sock *sk) } /* We're allowed to probe. Build it now. */ - if ((nskb = sk_stream_alloc_skb(sk, probe_size, GFP_ATOMIC)) == NULL) + nskb = sk_stream_alloc_skb(sk, probe_size, GFP_ATOMIC); + if (!nskb) return -1; sk->sk_wmem_queued += nskb->truesize; sk_mem_charge(sk, nskb->truesize); @@ -2179,7 +2240,7 @@ void tcp_send_loss_probe(struct sock *sk) int mss = tcp_current_mss(sk); int err = -1; - if (tcp_send_head(sk) != NULL) { + if (tcp_send_head(sk)) { err = tcp_write_xmit(sk, mss, TCP_NAGLE_OFF, 2, GFP_ATOMIC); goto rearm_timer; } @@ -2689,7 +2750,7 @@ void tcp_xmit_retransmit_queue(struct sock *sk) if (skb == tcp_send_head(sk)) break; /* we could do better than to assign each time */ - if (hole == NULL) + if (!hole) tp->retransmit_skb_hint = skb; /* Assume this retransmit will generate @@ -2713,7 +2774,7 @@ begin_fwd: if (!tcp_can_forward_retransmit(sk)) break; /* Backtrack if necessary to non-L'ed skb */ - if (hole != NULL) { + if (hole) { skb = hole; hole = NULL; } @@ -2721,7 +2782,7 @@ begin_fwd: goto begin_fwd; } else if (!(sacked & TCPCB_LOST)) { - if (hole == NULL && !(sacked & (TCPCB_SACKED_RETRANS|TCPCB_SACKED_ACKED))) + if (!hole && !(sacked & (TCPCB_SACKED_RETRANS|TCPCB_SACKED_ACKED))) hole = skb; continue; @@ -2751,39 +2812,65 @@ begin_fwd: } } -/* Send a fin. The caller locks the socket for us. This cannot be - * allowed to fail queueing a FIN frame under any circumstances. +/* We allow to exceed memory limits for FIN packets to expedite + * connection tear down and (memory) recovery. + * Otherwise tcp_send_fin() could be tempted to either delay FIN + * or even be forced to close flow without any FIN. + */ +static void sk_forced_wmem_schedule(struct sock *sk, int size) +{ + int amt, status; + + if (size <= sk->sk_forward_alloc) + return; + amt = sk_mem_pages(size); + sk->sk_forward_alloc += amt * SK_MEM_QUANTUM; + sk_memory_allocated_add(sk, amt, &status); +} + +/* Send a FIN. The caller locks the socket for us. + * We should try to send a FIN packet really hard, but eventually give up. */ void tcp_send_fin(struct sock *sk) { + struct sk_buff *skb, *tskb = tcp_write_queue_tail(sk); struct tcp_sock *tp = tcp_sk(sk); - struct sk_buff *skb = tcp_write_queue_tail(sk); - int mss_now; - /* Optimization, tack on the FIN if we have a queue of - * unsent frames. But be careful about outgoing SACKS - * and IP options. + /* Optimization, tack on the FIN if we have one skb in write queue and + * this skb was not yet sent, or we are under memory pressure. + * Note: in the latter case, FIN packet will be sent after a timeout, + * as TCP stack thinks it has already been transmitted. */ - mss_now = tcp_current_mss(sk); - - if (tcp_send_head(sk) != NULL) { - TCP_SKB_CB(skb)->tcp_flags |= TCPHDR_FIN; - TCP_SKB_CB(skb)->end_seq++; + if (tskb && (tcp_send_head(sk) || sk_under_memory_pressure(sk))) { +coalesce: + TCP_SKB_CB(tskb)->tcp_flags |= TCPHDR_FIN; + TCP_SKB_CB(tskb)->end_seq++; tp->write_seq++; + if (!tcp_send_head(sk)) { + /* This means tskb was already sent. + * Pretend we included the FIN on previous transmit. + * We need to set tp->snd_nxt to the value it would have + * if FIN had been sent. This is because retransmit path + * does not change tp->snd_nxt. + */ + tp->snd_nxt++; + return; + } } else { - /* Socket is locked, keep trying until memory is available. */ - for (;;) { - skb = sk_stream_alloc_skb(sk, 0, sk->sk_allocation); - if (skb) - break; - yield(); + skb = alloc_skb_fclone(MAX_TCP_HEADER, sk->sk_allocation); + if (unlikely(!skb)) { + if (tskb) + goto coalesce; + return; } + skb_reserve(skb, MAX_TCP_HEADER); + sk_forced_wmem_schedule(sk, skb->truesize); /* FIN eats a sequence byte, write_seq advanced by tcp_queue_skb(). */ tcp_init_nondata_skb(skb, tp->write_seq, TCPHDR_ACK | TCPHDR_FIN); tcp_queue_skb(sk, skb); } - __tcp_push_pending_frames(sk, mss_now, TCP_NAGLE_OFF); + __tcp_push_pending_frames(sk, tcp_current_mss(sk), TCP_NAGLE_OFF); } /* We get here when a process closes a file descriptor (either due to @@ -2824,14 +2911,14 @@ int tcp_send_synack(struct sock *sk) struct sk_buff *skb; skb = tcp_write_queue_head(sk); - if (skb == NULL || !(TCP_SKB_CB(skb)->tcp_flags & TCPHDR_SYN)) { + if (!skb || !(TCP_SKB_CB(skb)->tcp_flags & TCPHDR_SYN)) { pr_debug("%s: wrong queue state\n", __func__); return -EFAULT; } if (!(TCP_SKB_CB(skb)->tcp_flags & TCPHDR_ACK)) { if (skb_cloned(skb)) { struct sk_buff *nskb = skb_copy(skb, GFP_ATOMIC); - if (nskb == NULL) + if (!nskb) return -ENOMEM; tcp_unlink_write_queue(skb, sk); __skb_header_release(nskb); @@ -2866,7 +2953,7 @@ struct sk_buff *tcp_make_synack(struct sock *sk, struct dst_entry *dst, struct tcp_sock *tp = tcp_sk(sk); struct tcphdr *th; struct sk_buff *skb; - struct tcp_md5sig_key *md5; + struct tcp_md5sig_key *md5 = NULL; int tcp_header_size; int mss; @@ -2879,7 +2966,6 @@ struct sk_buff *tcp_make_synack(struct sock *sk, struct dst_entry *dst, skb_reserve(skb, MAX_TCP_HEADER); skb_dst_set(skb, dst); - security_skb_owned_by(skb, sk); mss = dst_metric_advmss(dst); if (tp->rx_opt.user_mss && tp->rx_opt.user_mss < mss) @@ -2892,7 +2978,12 @@ struct sk_buff *tcp_make_synack(struct sock *sk, struct dst_entry *dst, else #endif skb_mstamp_get(&skb->skb_mstamp); - tcp_header_size = tcp_synack_options(sk, req, mss, skb, &opts, &md5, + +#ifdef CONFIG_TCP_MD5SIG + rcu_read_lock(); + md5 = tcp_rsk(req)->af_specific->req_md5_lookup(sk, req_to_sk(req)); +#endif + tcp_header_size = tcp_synack_options(sk, req, mss, skb, &opts, md5, foc) + sizeof(*th); skb_push(skb, tcp_header_size); @@ -2923,12 +3014,14 @@ struct sk_buff *tcp_make_synack(struct sock *sk, struct dst_entry *dst, #ifdef CONFIG_TCP_MD5SIG /* Okay, we have all we need - do the md5 hash if needed */ - if (md5) { + if (md5) tcp_rsk(req)->af_specific->calc_md5_hash(opts.hash_location, - md5, NULL, req, skb); - } + md5, req_to_sk(req), skb); + rcu_read_unlock(); #endif + /* Do not fool tcpdump (if any), clean our debris */ + skb->tstamp.tv64 = 0; return skb; } EXPORT_SYMBOL(tcp_make_synack); @@ -2966,7 +3059,7 @@ static void tcp_connect_init(struct sock *sk) (sysctl_tcp_timestamps ? TCPOLEN_TSTAMP_ALIGNED : 0); #ifdef CONFIG_TCP_MD5SIG - if (tp->af_specific->md5_lookup(sk, sk) != NULL) + if (tp->af_specific->md5_lookup(sk, sk)) tp->tcp_header_len += TCPOLEN_MD5SIG_ALIGNED; #endif @@ -3252,7 +3345,7 @@ void tcp_send_ack(struct sock *sk) * sock. */ buff = alloc_skb(MAX_TCP_HEADER, sk_gfp_atomic(sk, GFP_ATOMIC)); - if (buff == NULL) { + if (!buff) { inet_csk_schedule_ack(sk); inet_csk(sk)->icsk_ack.ato = TCP_ATO_MIN; inet_csk_reset_xmit_timer(sk, ICSK_TIME_DACK, @@ -3296,7 +3389,7 @@ static int tcp_xmit_probe_skb(struct sock *sk, int urgent) /* We don't queue it, tcp_transmit_skb() sets ownership. */ skb = alloc_skb(MAX_TCP_HEADER, sk_gfp_atomic(sk, GFP_ATOMIC)); - if (skb == NULL) + if (!skb) return -1; /* Reserve space for headers and set control bits. */ @@ -3327,8 +3420,8 @@ int tcp_write_wakeup(struct sock *sk) if (sk->sk_state == TCP_CLOSE) return -1; - if ((skb = tcp_send_head(sk)) != NULL && - before(TCP_SKB_CB(skb)->seq, tcp_wnd_end(tp))) { + skb = tcp_send_head(sk); + if (skb && before(TCP_SKB_CB(skb)->seq, tcp_wnd_end(tp))) { int err; unsigned int mss = tcp_current_mss(sk); unsigned int seg_size = tcp_wnd_end(tp) - TCP_SKB_CB(skb)->seq; diff --git a/net/ipv4/tcp_timer.c b/net/ipv4/tcp_timer.c index 0732b787904e..8c65dc147d8b 100644 --- a/net/ipv4/tcp_timer.c +++ b/net/ipv4/tcp_timer.c @@ -107,6 +107,7 @@ static void tcp_mtu_probing(struct inet_connection_sock *icsk, struct sock *sk) if (net->ipv4.sysctl_tcp_mtu_probing) { if (!icsk->icsk_mtup.enabled) { icsk->icsk_mtup.enabled = 1; + icsk->icsk_mtup.probe_timestamp = tcp_time_stamp; tcp_sync_mss(sk, icsk->icsk_pmtu_cookie); } else { struct net *net = sock_net(sk); @@ -166,7 +167,7 @@ static int tcp_write_timeout(struct sock *sk) if (icsk->icsk_retransmits) { dst_negative_advice(sk); if (tp->syn_fastopen || tp->syn_data) - tcp_fastopen_cache_set(sk, 0, NULL, true); + tcp_fastopen_cache_set(sk, 0, NULL, true, 0); if (tp->syn_data) NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_TCPFASTOPENACTIVEFAIL); @@ -326,7 +327,7 @@ static void tcp_fastopen_synack_timer(struct sock *sk) struct request_sock *req; req = tcp_sk(sk)->fastopen_rsk; - req->rsk_ops->syn_ack_timeout(sk, req); + req->rsk_ops->syn_ack_timeout(req); if (req->num_timeout >= max_retries) { tcp_write_err(sk); @@ -538,19 +539,11 @@ static void tcp_write_timer(unsigned long data) sock_put(sk); } -/* - * Timer for listening sockets - */ - -static void tcp_synack_timer(struct sock *sk) +void tcp_syn_ack_timeout(const struct request_sock *req) { - inet_csk_reqsk_queue_prune(sk, TCP_SYNQ_INTERVAL, - TCP_TIMEOUT_INIT, TCP_RTO_MAX); -} + struct net *net = read_pnet(&inet_rsk(req)->ireq_net); -void tcp_syn_ack_timeout(struct sock *sk, struct request_sock *req) -{ - NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_TCPTIMEOUTS); + NET_INC_STATS_BH(net, LINUX_MIB_TCPTIMEOUTS); } EXPORT_SYMBOL(tcp_syn_ack_timeout); @@ -582,7 +575,7 @@ static void tcp_keepalive_timer (unsigned long data) } if (sk->sk_state == TCP_LISTEN) { - tcp_synack_timer(sk); + pr_err("Hmm... keepalive on a LISTEN ???\n"); goto out; } diff --git a/net/ipv4/tcp_vegas.c b/net/ipv4/tcp_vegas.c index a6afde666ab1..c71a1b8f7bde 100644 --- a/net/ipv4/tcp_vegas.c +++ b/net/ipv4/tcp_vegas.c @@ -286,7 +286,7 @@ static void tcp_vegas_cong_avoid(struct sock *sk, u32 ack, u32 acked) } /* Extract info for Tcp socket info provided via netlink. */ -void tcp_vegas_get_info(struct sock *sk, u32 ext, struct sk_buff *skb) +int tcp_vegas_get_info(struct sock *sk, u32 ext, struct sk_buff *skb) { const struct vegas *ca = inet_csk_ca(sk); if (ext & (1 << (INET_DIAG_VEGASINFO - 1))) { @@ -297,8 +297,9 @@ void tcp_vegas_get_info(struct sock *sk, u32 ext, struct sk_buff *skb) .tcpv_minrtt = ca->minRTT, }; - nla_put(skb, INET_DIAG_VEGASINFO, sizeof(info), &info); + return nla_put(skb, INET_DIAG_VEGASINFO, sizeof(info), &info); } + return 0; } EXPORT_SYMBOL_GPL(tcp_vegas_get_info); diff --git a/net/ipv4/tcp_vegas.h b/net/ipv4/tcp_vegas.h index 0531b99d8637..e8a6b33cc61d 100644 --- a/net/ipv4/tcp_vegas.h +++ b/net/ipv4/tcp_vegas.h @@ -19,6 +19,6 @@ void tcp_vegas_init(struct sock *sk); void tcp_vegas_state(struct sock *sk, u8 ca_state); void tcp_vegas_pkts_acked(struct sock *sk, u32 cnt, s32 rtt_us); void tcp_vegas_cwnd_event(struct sock *sk, enum tcp_ca_event event); -void tcp_vegas_get_info(struct sock *sk, u32 ext, struct sk_buff *skb); +int tcp_vegas_get_info(struct sock *sk, u32 ext, struct sk_buff *skb); #endif /* __TCP_VEGAS_H */ diff --git a/net/ipv4/tcp_westwood.c b/net/ipv4/tcp_westwood.c index bb63fba47d47..b3c57cceb990 100644 --- a/net/ipv4/tcp_westwood.c +++ b/net/ipv4/tcp_westwood.c @@ -256,8 +256,7 @@ static void tcp_westwood_event(struct sock *sk, enum tcp_ca_event event) } /* Extract info for Tcp socket info provided via netlink. */ -static void tcp_westwood_info(struct sock *sk, u32 ext, - struct sk_buff *skb) +static int tcp_westwood_info(struct sock *sk, u32 ext, struct sk_buff *skb) { const struct westwood *ca = inet_csk_ca(sk); @@ -268,8 +267,9 @@ static void tcp_westwood_info(struct sock *sk, u32 ext, .tcpv_minrtt = jiffies_to_usecs(ca->rtt_min), }; - nla_put(skb, INET_DIAG_VEGASINFO, sizeof(info), &info); + return nla_put(skb, INET_DIAG_VEGASINFO, sizeof(info), &info); } + return 0; } static struct tcp_congestion_ops tcp_westwood __read_mostly = { diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c index 97ef1f8b7be8..d10b7e0112eb 100644 --- a/net/ipv4/udp.c +++ b/net/ipv4/udp.c @@ -318,8 +318,8 @@ static int ipv4_rcv_saddr_equal(const struct sock *sk1, const struct sock *sk2) inet1->inet_rcv_saddr == inet2->inet_rcv_saddr)); } -static unsigned int udp4_portaddr_hash(struct net *net, __be32 saddr, - unsigned int port) +static u32 udp4_portaddr_hash(const struct net *net, __be32 saddr, + unsigned int port) { return jhash_1word((__force u32)saddr, net_hash_mix(net)) ^ port; } @@ -421,9 +421,9 @@ static inline int compute_score2(struct sock *sk, struct net *net, return score; } -static unsigned int udp_ehashfn(struct net *net, const __be32 laddr, - const __u16 lport, const __be32 faddr, - const __be16 fport) +static u32 udp_ehashfn(const struct net *net, const __be32 laddr, + const __u16 lport, const __be32 faddr, + const __be16 fport) { static u32 udp_ehash_secret __read_mostly; @@ -433,7 +433,6 @@ static unsigned int udp_ehashfn(struct net *net, const __be32 laddr, udp_ehash_secret + net_hash_mix(net)); } - /* called with read_rcu_lock() */ static struct sock *udp4_lib_lookup2(struct net *net, __be32 saddr, __be16 sport, @@ -633,7 +632,7 @@ void __udp4_lib_err(struct sk_buff *skb, u32 info, struct udp_table *udptable) sk = __udp4_lib_lookup(net, iph->daddr, uh->dest, iph->saddr, uh->source, skb->dev->ifindex, udptable); - if (sk == NULL) { + if (!sk) { ICMP_INC_STATS_BH(net, ICMP_MIB_INERRORS); return; /* No socket for error */ } @@ -873,8 +872,7 @@ out: } EXPORT_SYMBOL(udp_push_pending_frames); -int udp_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg, - size_t len) +int udp_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) { struct inet_sock *inet = inet_sk(sk); struct udp_sock *up = udp_sk(sk); @@ -1012,7 +1010,7 @@ int udp_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg, if (connected) rt = (struct rtable *)sk_dst_check(sk, 0); - if (rt == NULL) { + if (!rt) { struct net *net = sock_net(sk); fl4 = &fl4_stack; @@ -1136,7 +1134,7 @@ int udp_sendpage(struct sock *sk, struct page *page, int offset, * sendpage interface can't pass. * This will succeed only when the socket is connected. */ - ret = udp_sendmsg(NULL, sk, &msg, 0); + ret = udp_sendmsg(sk, &msg, 0); if (ret < 0) return ret; } @@ -1172,7 +1170,6 @@ out: return ret; } - /** * first_packet_length - return length of first packet in receive queue * @sk: socket @@ -1254,8 +1251,8 @@ EXPORT_SYMBOL(udp_ioctl); * return it, otherwise we block. */ -int udp_recvmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg, - size_t len, int noblock, int flags, int *addr_len) +int udp_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, int noblock, + int flags, int *addr_len) { struct inet_sock *inet = inet_sk(sk); DECLARE_SOCKADDR(struct sockaddr_in *, sin, msg->msg_name); @@ -1356,7 +1353,6 @@ csum_copy_err: goto try_again; } - int udp_disconnect(struct sock *sk, int flags) { struct inet_sock *inet = inet_sk(sk); @@ -1523,7 +1519,7 @@ int udp_queue_rcv_skb(struct sock *sk, struct sk_buff *skb) /* if we're overly short, let UDP handle it */ encap_rcv = ACCESS_ONCE(up->encap_rcv); - if (skb->len > sizeof(struct udphdr) && encap_rcv != NULL) { + if (skb->len > sizeof(struct udphdr) && encap_rcv) { int ret; /* Verify checksum before giving to encap */ @@ -1580,7 +1576,6 @@ int udp_queue_rcv_skb(struct sock *sk, struct sk_buff *skb) udp_lib_checksum_complete(skb)) goto csum_error; - if (sk_rcvqueues_full(sk, sk->sk_rcvbuf)) { UDP_INC_STATS_BH(sock_net(sk), UDP_MIB_RCVBUFERRORS, is_udplite); @@ -1610,7 +1605,6 @@ drop: return -1; } - static void flush_stack(struct sock **stack, unsigned int count, struct sk_buff *skb, unsigned int final) { @@ -1620,7 +1614,7 @@ static void flush_stack(struct sock **stack, unsigned int count, for (i = 0; i < count; i++) { sk = stack[i]; - if (likely(skb1 == NULL)) + if (likely(!skb1)) skb1 = (i == final) ? skb : skb_clone(skb, GFP_ATOMIC); if (!skb1) { @@ -1803,7 +1797,7 @@ int __udp4_lib_rcv(struct sk_buff *skb, struct udp_table *udptable, saddr, daddr, udptable, proto); sk = __udp4_lib_lookup_skb(skb, uh->source, uh->dest, udptable); - if (sk != NULL) { + if (sk) { int ret; if (inet_get_convert_csum(sk) && uh->check && !IS_UDPLITE(sk)) @@ -2525,6 +2519,16 @@ void __init udp_table_init(struct udp_table *table, const char *name) } } +u32 udp_flow_hashrnd(void) +{ + static u32 hashrnd __read_mostly; + + net_get_random_once(&hashrnd, sizeof(hashrnd)); + + return hashrnd; +} +EXPORT_SYMBOL(udp_flow_hashrnd); + void __init udp_init(void) { unsigned long limit; diff --git a/net/ipv4/udp_diag.c b/net/ipv4/udp_diag.c index 4a000f1dd757..b763c39ae1d7 100644 --- a/net/ipv4/udp_diag.c +++ b/net/ipv4/udp_diag.c @@ -18,8 +18,9 @@ #include <linux/sock_diag.h> static int sk_diag_dump(struct sock *sk, struct sk_buff *skb, - struct netlink_callback *cb, struct inet_diag_req_v2 *req, - struct nlattr *bc) + struct netlink_callback *cb, + const struct inet_diag_req_v2 *req, + struct nlattr *bc) { if (!inet_diag_bc_sk(bc, sk)) return 0; @@ -31,7 +32,8 @@ static int sk_diag_dump(struct sock *sk, struct sk_buff *skb, } static int udp_dump_one(struct udp_table *tbl, struct sk_buff *in_skb, - const struct nlmsghdr *nlh, struct inet_diag_req_v2 *req) + const struct nlmsghdr *nlh, + const struct inet_diag_req_v2 *req) { int err = -EINVAL; struct sock *sk; @@ -56,7 +58,7 @@ static int udp_dump_one(struct udp_table *tbl, struct sk_buff *in_skb, goto out_nosk; err = -ENOENT; - if (sk == NULL) + if (!sk) goto out_nosk; err = sock_diag_check_cookie(sk, req->id.idiag_cookie); @@ -90,8 +92,9 @@ out_nosk: return err; } -static void udp_dump(struct udp_table *table, struct sk_buff *skb, struct netlink_callback *cb, - struct inet_diag_req_v2 *r, struct nlattr *bc) +static void udp_dump(struct udp_table *table, struct sk_buff *skb, + struct netlink_callback *cb, + const struct inet_diag_req_v2 *r, struct nlattr *bc) { int num, s_num, slot, s_slot; struct net *net = sock_net(skb->sk); @@ -144,13 +147,13 @@ done: } static void udp_diag_dump(struct sk_buff *skb, struct netlink_callback *cb, - struct inet_diag_req_v2 *r, struct nlattr *bc) + const struct inet_diag_req_v2 *r, struct nlattr *bc) { udp_dump(&udp_table, skb, cb, r, bc); } static int udp_diag_dump_one(struct sk_buff *in_skb, const struct nlmsghdr *nlh, - struct inet_diag_req_v2 *req) + const struct inet_diag_req_v2 *req) { return udp_dump_one(&udp_table, in_skb, nlh, req); } @@ -170,13 +173,14 @@ static const struct inet_diag_handler udp_diag_handler = { }; static void udplite_diag_dump(struct sk_buff *skb, struct netlink_callback *cb, - struct inet_diag_req_v2 *r, struct nlattr *bc) + const struct inet_diag_req_v2 *r, + struct nlattr *bc) { udp_dump(&udplite_table, skb, cb, r, bc); } static int udplite_diag_dump_one(struct sk_buff *in_skb, const struct nlmsghdr *nlh, - struct inet_diag_req_v2 *req) + const struct inet_diag_req_v2 *req) { return udp_dump_one(&udplite_table, in_skb, nlh, req); } diff --git a/net/ipv4/udp_impl.h b/net/ipv4/udp_impl.h index f3c27899f62b..7e0fe4bdd967 100644 --- a/net/ipv4/udp_impl.h +++ b/net/ipv4/udp_impl.h @@ -21,8 +21,8 @@ int compat_udp_setsockopt(struct sock *sk, int level, int optname, int compat_udp_getsockopt(struct sock *sk, int level, int optname, char __user *optval, int __user *optlen); #endif -int udp_recvmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg, - size_t len, int noblock, int flags, int *addr_len); +int udp_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, int noblock, + int flags, int *addr_len); int udp_sendpage(struct sock *sk, struct page *page, int offset, size_t size, int flags); int udp_queue_rcv_skb(struct sock *sk, struct sk_buff *skb); diff --git a/net/ipv4/udp_offload.c b/net/ipv4/udp_offload.c index 4915d8284a86..f9386160cbee 100644 --- a/net/ipv4/udp_offload.c +++ b/net/ipv4/udp_offload.c @@ -285,7 +285,7 @@ void udp_del_offload(struct udp_offload *uo) pr_warn("udp_del_offload: didn't find offload for port %d\n", ntohs(uo->port)); unlock: spin_unlock(&udp_offload_lock); - if (uo_priv != NULL) + if (uo_priv) call_rcu(&uo_priv->rcu, udp_offload_free_routine); } EXPORT_SYMBOL(udp_del_offload); @@ -394,7 +394,7 @@ int udp_gro_complete(struct sk_buff *skb, int nhoff) break; } - if (uo_priv != NULL) { + if (uo_priv) { NAPI_GRO_CB(skb)->proto = uo_priv->offload->ipproto; err = uo_priv->offload->callbacks.gro_complete(skb, nhoff + sizeof(struct udphdr), diff --git a/net/ipv4/udp_tunnel.c b/net/ipv4/udp_tunnel.c index c83b35485056..6bb98cc193c9 100644 --- a/net/ipv4/udp_tunnel.c +++ b/net/ipv4/udp_tunnel.c @@ -75,7 +75,7 @@ void setup_udp_tunnel_sock(struct net *net, struct socket *sock, } EXPORT_SYMBOL_GPL(setup_udp_tunnel_sock); -int udp_tunnel_xmit_skb(struct rtable *rt, struct sk_buff *skb, +int udp_tunnel_xmit_skb(struct rtable *rt, struct sock *sk, struct sk_buff *skb, __be32 src, __be32 dst, __u8 tos, __u8 ttl, __be16 df, __be16 src_port, __be16 dst_port, bool xnet, bool nocheck) @@ -92,7 +92,7 @@ int udp_tunnel_xmit_skb(struct rtable *rt, struct sk_buff *skb, udp_set_csum(nocheck, skb, src, dst, skb->len); - return iptunnel_xmit(skb->sk, rt, skb, src, dst, IPPROTO_UDP, + return iptunnel_xmit(sk, rt, skb, src, dst, IPPROTO_UDP, tos, ttl, df, xnet); } EXPORT_SYMBOL_GPL(udp_tunnel_xmit_skb); diff --git a/net/ipv4/xfrm4_input.c b/net/ipv4/xfrm4_input.c index aac6197b7a71..60b032f58ccc 100644 --- a/net/ipv4/xfrm4_input.c +++ b/net/ipv4/xfrm4_input.c @@ -22,9 +22,9 @@ int xfrm4_extract_input(struct xfrm_state *x, struct sk_buff *skb) return xfrm4_extract_header(skb); } -static inline int xfrm4_rcv_encap_finish(struct sk_buff *skb) +static inline int xfrm4_rcv_encap_finish(struct sock *sk, struct sk_buff *skb) { - if (skb_dst(skb) == NULL) { + if (!skb_dst(skb)) { const struct iphdr *iph = ip_hdr(skb); if (ip_route_input_noref(skb, iph->daddr, iph->saddr, @@ -52,7 +52,8 @@ int xfrm4_transport_finish(struct sk_buff *skb, int async) iph->tot_len = htons(skb->len); ip_send_check(iph); - NF_HOOK(NFPROTO_IPV4, NF_INET_PRE_ROUTING, skb, skb->dev, NULL, + NF_HOOK(NFPROTO_IPV4, NF_INET_PRE_ROUTING, NULL, skb, + skb->dev, NULL, xfrm4_rcv_encap_finish); return 0; } diff --git a/net/ipv4/xfrm4_mode_tunnel.c b/net/ipv4/xfrm4_mode_tunnel.c index 91771a7c802f..35feda676464 100644 --- a/net/ipv4/xfrm4_mode_tunnel.c +++ b/net/ipv4/xfrm4_mode_tunnel.c @@ -63,7 +63,7 @@ static int xfrm4_mode_tunnel_output(struct xfrm_state *x, struct sk_buff *skb) top_iph->saddr = x->props.saddr.a4; top_iph->daddr = x->id.daddr.a4; - ip_select_ident(skb, NULL); + ip_select_ident(dev_net(dst->dev), skb, NULL); return 0; } diff --git a/net/ipv4/xfrm4_output.c b/net/ipv4/xfrm4_output.c index dab73813cb92..2878dbfffeb7 100644 --- a/net/ipv4/xfrm4_output.c +++ b/net/ipv4/xfrm4_output.c @@ -69,7 +69,7 @@ int xfrm4_prepare_output(struct xfrm_state *x, struct sk_buff *skb) } EXPORT_SYMBOL(xfrm4_prepare_output); -int xfrm4_output_finish(struct sk_buff *skb) +int xfrm4_output_finish(struct sock *sk, struct sk_buff *skb) { memset(IPCB(skb), 0, sizeof(*IPCB(skb))); @@ -77,26 +77,26 @@ int xfrm4_output_finish(struct sk_buff *skb) IPCB(skb)->flags |= IPSKB_XFRM_TRANSFORMED; #endif - return xfrm_output(skb); + return xfrm_output(sk, skb); } -static int __xfrm4_output(struct sk_buff *skb) +static int __xfrm4_output(struct sock *sk, struct sk_buff *skb) { struct xfrm_state *x = skb_dst(skb)->xfrm; #ifdef CONFIG_NETFILTER if (!x) { IPCB(skb)->flags |= IPSKB_REROUTED; - return dst_output(skb); + return dst_output_sk(sk, skb); } #endif - return x->outer_mode->afinfo->output_finish(skb); + return x->outer_mode->afinfo->output_finish(sk, skb); } int xfrm4_output(struct sock *sk, struct sk_buff *skb) { - return NF_HOOK_COND(NFPROTO_IPV4, NF_INET_POST_ROUTING, skb, + return NF_HOOK_COND(NFPROTO_IPV4, NF_INET_POST_ROUTING, sk, skb, NULL, skb_dst(skb)->dev, __xfrm4_output, !(IPCB(skb)->flags & IPSKB_REROUTED)); } diff --git a/net/ipv4/xfrm4_policy.c b/net/ipv4/xfrm4_policy.c index 6156f68a1e90..bff69746e05f 100644 --- a/net/ipv4/xfrm4_policy.c +++ b/net/ipv4/xfrm4_policy.c @@ -232,7 +232,6 @@ static void xfrm4_dst_ifdown(struct dst_entry *dst, struct net_device *dev, static struct dst_ops xfrm4_dst_ops = { .family = AF_INET, - .protocol = cpu_to_be16(ETH_P_IP), .gc = xfrm4_garbage_collect, .update_pmtu = xfrm4_update_pmtu, .redirect = xfrm4_redirect, @@ -299,7 +298,7 @@ static void __net_exit xfrm4_net_exit(struct net *net) { struct ctl_table *table; - if (net->ipv4.xfrm4_hdr == NULL) + if (!net->ipv4.xfrm4_hdr) return; table = net->ipv4.xfrm4_hdr->ctl_table_arg; diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c index b6030025f411..37b70e82bff8 100644 --- a/net/ipv6/addrconf.c +++ b/net/ipv6/addrconf.c @@ -46,6 +46,7 @@ #include <linux/socket.h> #include <linux/sockios.h> #include <linux/net.h> +#include <linux/inet.h> #include <linux/in6.h> #include <linux/netdevice.h> #include <linux/if_addr.h> @@ -102,6 +103,9 @@ #define INFINITY_LIFE_TIME 0xFFFFFFFF +#define IPV6_MAX_STRLEN \ + sizeof("ffff:ffff:ffff:ffff:ffff:ffff:255.255.255.255") + static inline u32 cstamp_delta(unsigned long cstamp) { return (cstamp - INITIAL_JIFFIES) * 100UL / HZ; @@ -127,6 +131,9 @@ static void ipv6_regen_rndid(unsigned long data); static int ipv6_generate_eui64(u8 *eui, struct net_device *dev); static int ipv6_count_addresses(struct inet6_dev *idev); +static int ipv6_generate_stable_address(struct in6_addr *addr, + u8 dad_count, + const struct inet6_dev *idev); /* * Configured unicast address hash table @@ -202,6 +209,9 @@ static struct ipv6_devconf ipv6_devconf __read_mostly = { .accept_dad = 1, .suppress_frag_ndisc = 1, .accept_ra_mtu = 1, + .stable_secret = { + .initialized = false, + } }; static struct ipv6_devconf ipv6_devconf_dflt __read_mostly = { @@ -240,6 +250,9 @@ static struct ipv6_devconf ipv6_devconf_dflt __read_mostly = { .accept_dad = 1, .suppress_frag_ndisc = 1, .accept_ra_mtu = 1, + .stable_secret = { + .initialized = false, + }, }; /* Check if a valid qdisc is available */ @@ -321,7 +334,7 @@ static struct inet6_dev *ipv6_add_dev(struct net_device *dev) return ERR_PTR(-EINVAL); ndev = kzalloc(sizeof(struct inet6_dev), GFP_KERNEL); - if (ndev == NULL) + if (!ndev) return ERR_PTR(err); rwlock_init(&ndev->lock); @@ -333,7 +346,7 @@ static struct inet6_dev *ipv6_add_dev(struct net_device *dev) ndev->cnf.mtu6 = dev->mtu; ndev->cnf.sysctl = NULL; ndev->nd_parms = neigh_parms_alloc(dev, &nd_tbl); - if (ndev->nd_parms == NULL) { + if (!ndev->nd_parms) { kfree(ndev); return ERR_PTR(err); } @@ -468,7 +481,7 @@ static int inet6_netconf_fill_devconf(struct sk_buff *skb, int ifindex, nlh = nlmsg_put(skb, portid, seq, event, sizeof(struct netconfmsg), flags); - if (nlh == NULL) + if (!nlh) return -EMSGSIZE; ncm = nlmsg_data(nlh); @@ -506,7 +519,7 @@ void inet6_netconf_notify_devconf(struct net *net, int type, int ifindex, int err = -ENOBUFS; skb = nlmsg_new(inet6_netconf_msgsize_devconf(type), GFP_ATOMIC); - if (skb == NULL) + if (!skb) goto errout; err = inet6_netconf_fill_devconf(skb, ifindex, devconf, 0, 0, @@ -561,10 +574,10 @@ static int inet6_netconf_get_devconf(struct sk_buff *in_skb, break; default: dev = __dev_get_by_index(net, ifindex); - if (dev == NULL) + if (!dev) goto errout; in6_dev = __in6_dev_get(dev); - if (in6_dev == NULL) + if (!in6_dev) goto errout; devconf = &in6_dev->cnf; break; @@ -572,7 +585,7 @@ static int inet6_netconf_get_devconf(struct sk_buff *in_skb, err = -ENOBUFS; skb = nlmsg_new(inet6_netconf_msgsize_devconf(-1), GFP_ATOMIC); - if (skb == NULL) + if (!skb) goto errout; err = inet6_netconf_fill_devconf(skb, ifindex, devconf, @@ -841,7 +854,7 @@ ipv6_add_addr(struct inet6_dev *idev, const struct in6_addr *addr, ifa = kzalloc(sizeof(struct inet6_ifaddr), GFP_ATOMIC); - if (ifa == NULL) { + if (!ifa) { ADBG("ipv6_add_addr: malloc failed\n"); err = -ENOBUFS; goto out; @@ -860,7 +873,6 @@ ipv6_add_addr(struct inet6_dev *idev, const struct in6_addr *addr, ifa->peer_addr = *peer_addr; spin_lock_init(&ifa->lock); - spin_lock_init(&ifa->state_lock); INIT_DELAYED_WORK(&ifa->dad_work, addrconf_dad_work); INIT_HLIST_NODE(&ifa->addr_lst); ifa->scope = scope; @@ -1003,10 +1015,10 @@ static void ipv6_del_addr(struct inet6_ifaddr *ifp) ASSERT_RTNL(); - spin_lock_bh(&ifp->state_lock); + spin_lock_bh(&ifp->lock); state = ifp->state; ifp->state = INET6_IFADDR_STATE_DEAD; - spin_unlock_bh(&ifp->state_lock); + spin_unlock_bh(&ifp->lock); if (state == INET6_IFADDR_STATE_DEAD) goto out; @@ -1546,7 +1558,7 @@ int ipv6_chk_addr_and_flags(struct net *net, const struct in6_addr *addr, : ifp->flags; if (ipv6_addr_equal(&ifp->addr, addr) && !(ifp_flags&banned_flags) && - (dev == NULL || ifp->idev->dev == dev || + (!dev || ifp->idev->dev == dev || !(ifp->scope&(IFA_LINK|IFA_HOST) || strict))) { rcu_read_unlock_bh(); return 1; @@ -1568,7 +1580,7 @@ static bool ipv6_chk_same_addr(struct net *net, const struct in6_addr *addr, if (!net_eq(dev_net(ifp->idev->dev), net)) continue; if (ipv6_addr_equal(&ifp->addr, addr)) { - if (dev == NULL || ifp->idev->dev == dev) + if (!dev || ifp->idev->dev == dev) return true; } } @@ -1637,7 +1649,7 @@ struct inet6_ifaddr *ipv6_get_ifaddr(struct net *net, const struct in6_addr *add if (!net_eq(dev_net(ifp->idev->dev), net)) continue; if (ipv6_addr_equal(&ifp->addr, addr)) { - if (dev == NULL || ifp->idev->dev == dev || + if (!dev || ifp->idev->dev == dev || !(ifp->scope&(IFA_LINK|IFA_HOST) || strict)) { result = ifp; in6_ifa_hold(ifp); @@ -1686,19 +1698,21 @@ static int addrconf_dad_end(struct inet6_ifaddr *ifp) { int err = -ENOENT; - spin_lock_bh(&ifp->state_lock); + spin_lock_bh(&ifp->lock); if (ifp->state == INET6_IFADDR_STATE_DAD) { ifp->state = INET6_IFADDR_STATE_POSTDAD; err = 0; } - spin_unlock_bh(&ifp->state_lock); + spin_unlock_bh(&ifp->lock); return err; } void addrconf_dad_failure(struct inet6_ifaddr *ifp) { + struct in6_addr addr; struct inet6_dev *idev = ifp->idev; + struct net *net = dev_net(ifp->idev->dev); if (addrconf_dad_end(ifp)) { in6_ifa_put(ifp); @@ -1708,9 +1722,57 @@ void addrconf_dad_failure(struct inet6_ifaddr *ifp) net_info_ratelimited("%s: IPv6 duplicate address %pI6c detected!\n", ifp->idev->dev->name, &ifp->addr); - if (idev->cnf.accept_dad > 1 && !idev->cnf.disable_ipv6) { - struct in6_addr addr; + spin_lock_bh(&ifp->lock); + + if (ifp->flags & IFA_F_STABLE_PRIVACY) { + int scope = ifp->scope; + u32 flags = ifp->flags; + struct in6_addr new_addr; + struct inet6_ifaddr *ifp2; + u32 valid_lft, preferred_lft; + int pfxlen = ifp->prefix_len; + int retries = ifp->stable_privacy_retry + 1; + + if (retries > net->ipv6.sysctl.idgen_retries) { + net_info_ratelimited("%s: privacy stable address generation failed because of DAD conflicts!\n", + ifp->idev->dev->name); + goto errdad; + } + + new_addr = ifp->addr; + if (ipv6_generate_stable_address(&new_addr, retries, + idev)) + goto errdad; + + valid_lft = ifp->valid_lft; + preferred_lft = ifp->prefered_lft; + + spin_unlock_bh(&ifp->lock); + + if (idev->cnf.max_addresses && + ipv6_count_addresses(idev) >= + idev->cnf.max_addresses) + goto lock_errdad; + + net_info_ratelimited("%s: generating new stable privacy address because of DAD conflict\n", + ifp->idev->dev->name); + + ifp2 = ipv6_add_addr(idev, &new_addr, NULL, pfxlen, + scope, flags, valid_lft, + preferred_lft); + if (IS_ERR(ifp2)) + goto lock_errdad; + + spin_lock_bh(&ifp2->lock); + ifp2->stable_privacy_retry = retries; + ifp2->state = INET6_IFADDR_STATE_PREDAD; + spin_unlock_bh(&ifp2->lock); + addrconf_mod_dad_work(ifp2, net->ipv6.sysctl.idgen_delay); + in6_ifa_put(ifp2); +lock_errdad: + spin_lock_bh(&ifp->lock); + } else if (idev->cnf.accept_dad > 1 && !idev->cnf.disable_ipv6) { addr.s6_addr32[0] = htonl(0xfe800000); addr.s6_addr32[1] = 0; @@ -1724,10 +1786,10 @@ void addrconf_dad_failure(struct inet6_ifaddr *ifp) } } - spin_lock_bh(&ifp->state_lock); +errdad: /* transition from _POSTDAD to _ERRDAD */ ifp->state = INET6_IFADDR_STATE_ERRDAD; - spin_unlock_bh(&ifp->state_lock); + spin_unlock_bh(&ifp->lock); addrconf_mod_dad_work(ifp, 0); } @@ -2052,7 +2114,7 @@ static struct rt6_info *addrconf_get_prefix_route(const struct in6_addr *pfx, struct fib6_table *table; table = fib6_get_table(dev_net(dev), RT6_TABLE_PREFIX); - if (table == NULL) + if (!table) return NULL; read_lock_bh(&table->tb6_lock); @@ -2186,6 +2248,7 @@ void addrconf_prefix_rcv(struct net_device *dev, u8 *opt, int len, bool sllao) __u32 valid_lft; __u32 prefered_lft; int addr_type; + u32 addr_flags = 0; struct inet6_dev *in6_dev; struct net *net = dev_net(dev); @@ -2215,7 +2278,7 @@ void addrconf_prefix_rcv(struct net_device *dev, u8 *opt, int len, bool sllao) in6_dev = in6_dev_get(dev); - if (in6_dev == NULL) { + if (!in6_dev) { net_dbg_ratelimited("addrconf: device %s not configured\n", dev->name); return; @@ -2292,6 +2355,12 @@ void addrconf_prefix_rcv(struct net_device *dev, u8 *opt, int len, bool sllao) in6_dev->token.s6_addr + 8, 8); read_unlock_bh(&in6_dev->lock); tokenized = true; + } else if (in6_dev->addr_gen_mode == + IN6_ADDR_GEN_MODE_STABLE_PRIVACY && + !ipv6_generate_stable_address(&addr, 0, + in6_dev)) { + addr_flags |= IFA_F_STABLE_PRIVACY; + goto ok; } else if (ipv6_generate_eui64(addr.s6_addr + 8, dev) && ipv6_inherit_eui64(addr.s6_addr + 8, in6_dev)) { in6_dev_put(in6_dev); @@ -2308,9 +2377,8 @@ ok: ifp = ipv6_get_ifaddr(net, &addr, dev, 1); - if (ifp == NULL && valid_lft) { + if (!ifp && valid_lft) { int max_addresses = in6_dev->cnf.max_addresses; - u32 addr_flags = 0; #ifdef CONFIG_IPV6_OPTIMISTIC_DAD if (in6_dev->cnf.optimistic_dad && @@ -2350,7 +2418,7 @@ ok: u32 stored_lft; /* update lifetime (RFC2462 5.5.3 e) */ - spin_lock(&ifp->lock); + spin_lock_bh(&ifp->lock); now = jiffies; if (ifp->valid_lft > (now - ifp->tstamp) / HZ) stored_lft = ifp->valid_lft - (now - ifp->tstamp) / HZ; @@ -2380,12 +2448,12 @@ ok: ifp->tstamp = now; flags = ifp->flags; ifp->flags &= ~IFA_F_DEPRECATED; - spin_unlock(&ifp->lock); + spin_unlock_bh(&ifp->lock); if (!(flags&IFA_F_TENTATIVE)) ipv6_ifa_notify(0, ifp); } else - spin_unlock(&ifp->lock); + spin_unlock_bh(&ifp->lock); manage_tempaddrs(in6_dev, ifp, valid_lft, prefered_lft, create, now); @@ -2418,7 +2486,7 @@ int addrconf_set_dstaddr(struct net *net, void __user *arg) dev = __dev_get_by_index(net, ireq.ifr6_ifindex); err = -ENODEV; - if (dev == NULL) + if (!dev) goto err_exit; #if IS_ENABLED(CONFIG_IPV6_SIT) @@ -2464,6 +2532,23 @@ err_exit: return err; } +static int ipv6_mc_config(struct sock *sk, bool join, + const struct in6_addr *addr, int ifindex) +{ + int ret; + + ASSERT_RTNL(); + + lock_sock(sk); + if (join) + ret = ipv6_sock_mc_join(sk, ifindex, addr); + else + ret = ipv6_sock_mc_drop(sk, ifindex, addr); + release_sock(sk); + + return ret; +} + /* * Manual configuration of address on an interface */ @@ -2476,10 +2561,10 @@ static int inet6_addr_add(struct net *net, int ifindex, struct inet6_ifaddr *ifp; struct inet6_dev *idev; struct net_device *dev; + unsigned long timeout; + clock_t expires; int scope; u32 flags; - clock_t expires; - unsigned long timeout; ASSERT_RTNL(); @@ -2501,6 +2586,14 @@ static int inet6_addr_add(struct net *net, int ifindex, if (IS_ERR(idev)) return PTR_ERR(idev); + if (ifa_flags & IFA_F_MCAUTOJOIN) { + int ret = ipv6_mc_config(net->ipv6.mc_autojoin_sk, + true, pfx, ifindex); + + if (ret < 0) + return ret; + } + scope = ipv6_addr_scope(pfx); timeout = addrconf_timeout_fixup(valid_lft, HZ); @@ -2542,6 +2635,9 @@ static int inet6_addr_add(struct net *net, int ifindex, in6_ifa_put(ifp); addrconf_verify_rtnl(); return 0; + } else if (ifa_flags & IFA_F_MCAUTOJOIN) { + ipv6_mc_config(net->ipv6.mc_autojoin_sk, + false, pfx, ifindex); } return PTR_ERR(ifp); @@ -2562,7 +2658,7 @@ static int inet6_addr_del(struct net *net, int ifindex, u32 ifa_flags, return -ENODEV; idev = __in6_dev_get(dev); - if (idev == NULL) + if (!idev) return -ENXIO; read_lock_bh(&idev->lock); @@ -2578,6 +2674,10 @@ static int inet6_addr_del(struct net *net, int ifindex, u32 ifa_flags, jiffies); ipv6_del_addr(ifp); addrconf_verify_rtnl(); + if (ipv6_addr_is_multicast(pfx)) { + ipv6_mc_config(net->ipv6.mc_autojoin_sk, + false, pfx, dev->ifindex); + } return 0; } } @@ -2710,7 +2810,7 @@ static void init_loopback(struct net_device *dev) ASSERT_RTNL(); idev = ipv6_find_idev(dev); - if (idev == NULL) { + if (!idev) { pr_debug("%s: add_dev failed\n", __func__); return; } @@ -2757,10 +2857,11 @@ static void init_loopback(struct net_device *dev) } } -static void addrconf_add_linklocal(struct inet6_dev *idev, const struct in6_addr *addr) +static void addrconf_add_linklocal(struct inet6_dev *idev, + const struct in6_addr *addr, u32 flags) { struct inet6_ifaddr *ifp; - u32 addr_flags = IFA_F_PERMANENT; + u32 addr_flags = flags | IFA_F_PERMANENT; #ifdef CONFIG_IPV6_OPTIMISTIC_DAD if (idev->cnf.optimistic_dad && @@ -2768,7 +2869,6 @@ static void addrconf_add_linklocal(struct inet6_dev *idev, const struct in6_addr addr_flags |= IFA_F_OPTIMISTIC; #endif - ifp = ipv6_add_addr(idev, addr, NULL, 64, IFA_LINK, addr_flags, INFINITY_LIFE_TIME, INFINITY_LIFE_TIME); if (!IS_ERR(ifp)) { @@ -2778,18 +2878,103 @@ static void addrconf_add_linklocal(struct inet6_dev *idev, const struct in6_addr } } +static bool ipv6_reserved_interfaceid(struct in6_addr address) +{ + if ((address.s6_addr32[2] | address.s6_addr32[3]) == 0) + return true; + + if (address.s6_addr32[2] == htonl(0x02005eff) && + ((address.s6_addr32[3] & htonl(0xfe000000)) == htonl(0xfe000000))) + return true; + + if (address.s6_addr32[2] == htonl(0xfdffffff) && + ((address.s6_addr32[3] & htonl(0xffffff80)) == htonl(0xffffff80))) + return true; + + return false; +} + +static int ipv6_generate_stable_address(struct in6_addr *address, + u8 dad_count, + const struct inet6_dev *idev) +{ + static DEFINE_SPINLOCK(lock); + static __u32 digest[SHA_DIGEST_WORDS]; + static __u32 workspace[SHA_WORKSPACE_WORDS]; + + static union { + char __data[SHA_MESSAGE_BYTES]; + struct { + struct in6_addr secret; + __be32 prefix[2]; + unsigned char hwaddr[MAX_ADDR_LEN]; + u8 dad_count; + } __packed; + } data; + + struct in6_addr secret; + struct in6_addr temp; + struct net *net = dev_net(idev->dev); + + BUILD_BUG_ON(sizeof(data.__data) != sizeof(data)); + + if (idev->cnf.stable_secret.initialized) + secret = idev->cnf.stable_secret.secret; + else if (net->ipv6.devconf_dflt->stable_secret.initialized) + secret = net->ipv6.devconf_dflt->stable_secret.secret; + else + return -1; + +retry: + spin_lock_bh(&lock); + + sha_init(digest); + memset(&data, 0, sizeof(data)); + memset(workspace, 0, sizeof(workspace)); + memcpy(data.hwaddr, idev->dev->perm_addr, idev->dev->addr_len); + data.prefix[0] = address->s6_addr32[0]; + data.prefix[1] = address->s6_addr32[1]; + data.secret = secret; + data.dad_count = dad_count; + + sha_transform(digest, data.__data, workspace); + + temp = *address; + temp.s6_addr32[2] = (__force __be32)digest[0]; + temp.s6_addr32[3] = (__force __be32)digest[1]; + + spin_unlock_bh(&lock); + + if (ipv6_reserved_interfaceid(temp)) { + dad_count++; + if (dad_count > dev_net(idev->dev)->ipv6.sysctl.idgen_retries) + return -1; + goto retry; + } + + *address = temp; + return 0; +} + 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; + struct in6_addr addr; + + ipv6_addr_set(&addr, htonl(0xFE800000), 0, 0, 0); - ipv6_addr_set(&addr, htonl(0xFE800000), 0, 0, 0); + if (idev->addr_gen_mode == IN6_ADDR_GEN_MODE_STABLE_PRIVACY) { + if (!ipv6_generate_stable_address(&addr, 0, idev)) + addrconf_add_linklocal(idev, &addr, + IFA_F_STABLE_PRIVACY); + else if (prefix_route) + addrconf_prefix_route(&addr, 64, idev->dev, 0, 0); + } else if (idev->addr_gen_mode == IN6_ADDR_GEN_MODE_EUI64) { /* 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); + addrconf_add_linklocal(idev, &addr, 0); else if (prefix_route) addrconf_prefix_route(&addr, 64, idev->dev, 0, 0); } @@ -2834,7 +3019,7 @@ static void addrconf_sit_config(struct net_device *dev) */ idev = ipv6_find_idev(dev); - if (idev == NULL) { + if (!idev) { pr_debug("%s: add_dev failed\n", __func__); return; } @@ -2859,7 +3044,7 @@ static void addrconf_gre_config(struct net_device *dev) ASSERT_RTNL(); idev = ipv6_find_idev(dev); - if (idev == NULL) { + if (!idev) { pr_debug("%s: add_dev failed\n", __func__); return; } @@ -3056,7 +3241,7 @@ static int addrconf_ifdown(struct net_device *dev, int how) neigh_ifdown(&nd_tbl, dev); idev = __in6_dev_get(dev); - if (idev == NULL) + if (!idev) return -ENODEV; /* @@ -3127,10 +3312,10 @@ restart: write_unlock_bh(&idev->lock); - spin_lock_bh(&ifa->state_lock); + spin_lock_bh(&ifa->lock); state = ifa->state; ifa->state = INET6_IFADDR_STATE_DEAD; - spin_unlock_bh(&ifa->state_lock); + spin_unlock_bh(&ifa->lock); if (state != INET6_IFADDR_STATE_DEAD) { __ipv6_ifa_notify(RTM_DELADDR, ifa); @@ -3288,12 +3473,12 @@ static void addrconf_dad_start(struct inet6_ifaddr *ifp) { bool begin_dad = false; - spin_lock_bh(&ifp->state_lock); + spin_lock_bh(&ifp->lock); if (ifp->state != INET6_IFADDR_STATE_DEAD) { ifp->state = INET6_IFADDR_STATE_PREDAD; begin_dad = true; } - spin_unlock_bh(&ifp->state_lock); + spin_unlock_bh(&ifp->lock); if (begin_dad) addrconf_mod_dad_work(ifp, 0); @@ -3315,7 +3500,7 @@ static void addrconf_dad_work(struct work_struct *w) rtnl_lock(); - spin_lock_bh(&ifp->state_lock); + spin_lock_bh(&ifp->lock); if (ifp->state == INET6_IFADDR_STATE_PREDAD) { action = DAD_BEGIN; ifp->state = INET6_IFADDR_STATE_DAD; @@ -3323,7 +3508,7 @@ static void addrconf_dad_work(struct work_struct *w) action = DAD_ABORT; ifp->state = INET6_IFADDR_STATE_POSTDAD; } - spin_unlock_bh(&ifp->state_lock); + spin_unlock_bh(&ifp->lock); if (action == DAD_BEGIN) { addrconf_dad_begin(ifp); @@ -3811,7 +3996,7 @@ inet6_rtm_deladdr(struct sk_buff *skb, struct nlmsghdr *nlh) ifm = nlmsg_data(nlh); pfx = extract_addr(tb[IFA_ADDRESS], tb[IFA_LOCAL], &peer_pfx); - if (pfx == NULL) + if (!pfx) return -EINVAL; ifa_flags = tb[IFA_FLAGS] ? nla_get_u32(tb[IFA_FLAGS]) : ifm->ifa_flags; @@ -3923,7 +4108,7 @@ inet6_rtm_newaddr(struct sk_buff *skb, struct nlmsghdr *nlh) ifm = nlmsg_data(nlh); pfx = extract_addr(tb[IFA_ADDRESS], tb[IFA_LOCAL], &peer_pfx); - if (pfx == NULL) + if (!pfx) return -EINVAL; if (tb[IFA_CACHEINFO]) { @@ -3938,17 +4123,17 @@ inet6_rtm_newaddr(struct sk_buff *skb, struct nlmsghdr *nlh) } dev = __dev_get_by_index(net, ifm->ifa_index); - if (dev == NULL) + if (!dev) return -ENODEV; ifa_flags = tb[IFA_FLAGS] ? nla_get_u32(tb[IFA_FLAGS]) : ifm->ifa_flags; /* We ignore other flags so far. */ ifa_flags &= IFA_F_NODAD | IFA_F_HOMEADDRESS | IFA_F_MANAGETEMPADDR | - IFA_F_NOPREFIXROUTE; + IFA_F_NOPREFIXROUTE | IFA_F_MCAUTOJOIN; ifa = ipv6_get_ifaddr(net, pfx, dev, 1); - if (ifa == NULL) { + if (!ifa) { /* * It would be best to check for !NLM_F_CREATE here but * userspace already relies on not having to provide this. @@ -4023,7 +4208,7 @@ static int inet6_fill_ifaddr(struct sk_buff *skb, struct inet6_ifaddr *ifa, u32 preferred, valid; nlh = nlmsg_put(skb, portid, seq, event, sizeof(struct ifaddrmsg), flags); - if (nlh == NULL) + if (!nlh) return -EMSGSIZE; put_ifaddrmsg(nlh, ifa->prefix_len, ifa->flags, rt_scope(ifa->scope), @@ -4052,11 +4237,11 @@ static int inet6_fill_ifaddr(struct sk_buff *skb, struct inet6_ifaddr *ifa, } if (!ipv6_addr_any(&ifa->peer_addr)) { - if (nla_put(skb, IFA_LOCAL, 16, &ifa->addr) < 0 || - nla_put(skb, IFA_ADDRESS, 16, &ifa->peer_addr) < 0) + if (nla_put_in6_addr(skb, IFA_LOCAL, &ifa->addr) < 0 || + nla_put_in6_addr(skb, IFA_ADDRESS, &ifa->peer_addr) < 0) goto error; } else - if (nla_put(skb, IFA_ADDRESS, 16, &ifa->addr) < 0) + if (nla_put_in6_addr(skb, IFA_ADDRESS, &ifa->addr) < 0) goto error; if (put_cacheinfo(skb, ifa->cstamp, ifa->tstamp, preferred, valid) < 0) @@ -4084,11 +4269,11 @@ static int inet6_fill_ifmcaddr(struct sk_buff *skb, struct ifmcaddr6 *ifmca, scope = RT_SCOPE_SITE; nlh = nlmsg_put(skb, portid, seq, event, sizeof(struct ifaddrmsg), flags); - if (nlh == NULL) + if (!nlh) return -EMSGSIZE; put_ifaddrmsg(nlh, 128, IFA_F_PERMANENT, scope, ifindex); - if (nla_put(skb, IFA_MULTICAST, 16, &ifmca->mca_addr) < 0 || + if (nla_put_in6_addr(skb, IFA_MULTICAST, &ifmca->mca_addr) < 0 || put_cacheinfo(skb, ifmca->mca_cstamp, ifmca->mca_tstamp, INFINITY_LIFE_TIME, INFINITY_LIFE_TIME) < 0) { nlmsg_cancel(skb, nlh); @@ -4110,11 +4295,11 @@ static int inet6_fill_ifacaddr(struct sk_buff *skb, struct ifacaddr6 *ifaca, scope = RT_SCOPE_SITE; nlh = nlmsg_put(skb, portid, seq, event, sizeof(struct ifaddrmsg), flags); - if (nlh == NULL) + if (!nlh) return -EMSGSIZE; put_ifaddrmsg(nlh, 128, IFA_F_PERMANENT, scope, ifindex); - if (nla_put(skb, IFA_ANYCAST, 16, &ifaca->aca_addr) < 0 || + if (nla_put_in6_addr(skb, IFA_ANYCAST, &ifaca->aca_addr) < 0 || put_cacheinfo(skb, ifaca->aca_cstamp, ifaca->aca_tstamp, INFINITY_LIFE_TIME, INFINITY_LIFE_TIME) < 0) { nlmsg_cancel(skb, nlh); @@ -4283,7 +4468,7 @@ static int inet6_rtm_getaddr(struct sk_buff *in_skb, struct nlmsghdr *nlh) goto errout; addr = extract_addr(tb[IFA_ADDRESS], tb[IFA_LOCAL], &peer); - if (addr == NULL) { + if (!addr) { err = -EINVAL; goto errout; } @@ -4326,7 +4511,7 @@ static void inet6_ifa_notify(int event, struct inet6_ifaddr *ifa) int err = -ENOBUFS; skb = nlmsg_new(inet6_ifaddr_msgsize(), GFP_ATOMIC); - if (skb == NULL) + if (!skb) goto errout; err = inet6_fill_ifaddr(skb, ifa, 0, 0, event, 0); @@ -4398,6 +4583,7 @@ static inline void ipv6_store_devconf(struct ipv6_devconf *cnf, array[DEVCONF_SUPPRESS_FRAG_NDISC] = cnf->suppress_frag_ndisc; array[DEVCONF_ACCEPT_RA_FROM_LOCAL] = cnf->accept_ra_from_local; array[DEVCONF_ACCEPT_RA_MTU] = cnf->accept_ra_mtu; + /* we omit DEVCONF_STABLE_SECRET for now */ } static inline size_t inet6_ifla6_size(void) @@ -4478,24 +4664,24 @@ static int inet6_fill_ifla6_attrs(struct sk_buff *skb, struct inet6_dev *idev) if (nla_put(skb, IFLA_INET6_CACHEINFO, sizeof(ci), &ci)) goto nla_put_failure; nla = nla_reserve(skb, IFLA_INET6_CONF, DEVCONF_MAX * sizeof(s32)); - if (nla == NULL) + if (!nla) goto nla_put_failure; ipv6_store_devconf(&idev->cnf, nla_data(nla), nla_len(nla)); /* XXX - MC not implemented */ nla = nla_reserve(skb, IFLA_INET6_STATS, IPSTATS_MIB_MAX * sizeof(u64)); - if (nla == NULL) + if (!nla) goto nla_put_failure; snmp6_fill_stats(nla_data(nla), idev, IFLA_INET6_STATS, nla_len(nla)); nla = nla_reserve(skb, IFLA_INET6_ICMP6STATS, ICMP6_MIB_MAX * sizeof(u64)); - if (nla == NULL) + if (!nla) goto nla_put_failure; snmp6_fill_stats(nla_data(nla), idev, IFLA_INET6_ICMP6STATS, nla_len(nla)); nla = nla_reserve(skb, IFLA_INET6_TOKEN, sizeof(struct in6_addr)); - if (nla == NULL) + if (!nla) goto nla_put_failure; if (nla_put_u8(skb, IFLA_INET6_ADDR_GEN_MODE, idev->addr_gen_mode)) @@ -4541,7 +4727,7 @@ static int inet6_set_iftoken(struct inet6_dev *idev, struct in6_addr *token) ASSERT_RTNL(); - if (token == NULL) + if (!token) return -EINVAL; if (ipv6_addr_any(token)) return -EINVAL; @@ -4632,8 +4818,15 @@ static int inet6_set_link_af(struct net_device *dev, const struct nlattr *nla) u8 mode = nla_get_u8(tb[IFLA_INET6_ADDR_GEN_MODE]); if (mode != IN6_ADDR_GEN_MODE_EUI64 && - mode != IN6_ADDR_GEN_MODE_NONE) + mode != IN6_ADDR_GEN_MODE_NONE && + mode != IN6_ADDR_GEN_MODE_STABLE_PRIVACY) return -EINVAL; + + if (mode == IN6_ADDR_GEN_MODE_STABLE_PRIVACY && + !idev->cnf.stable_secret.initialized && + !dev_net(dev)->ipv6.devconf_dflt->stable_secret.initialized) + return -EINVAL; + idev->addr_gen_mode = mode; err = 0; } @@ -4650,7 +4843,7 @@ static int inet6_fill_ifinfo(struct sk_buff *skb, struct inet6_dev *idev, void *protoinfo; nlh = nlmsg_put(skb, portid, seq, event, sizeof(*hdr), flags); - if (nlh == NULL) + if (!nlh) return -EMSGSIZE; hdr = nlmsg_data(nlh); @@ -4665,11 +4858,11 @@ static int inet6_fill_ifinfo(struct sk_buff *skb, struct inet6_dev *idev, (dev->addr_len && nla_put(skb, IFLA_ADDRESS, dev->addr_len, dev->dev_addr)) || nla_put_u32(skb, IFLA_MTU, dev->mtu) || - (dev->ifindex != dev->iflink && - nla_put_u32(skb, IFLA_LINK, dev->iflink))) + (dev->ifindex != dev_get_iflink(dev) && + nla_put_u32(skb, IFLA_LINK, dev_get_iflink(dev)))) goto nla_put_failure; protoinfo = nla_nest_start(skb, IFLA_PROTINFO); - if (protoinfo == NULL) + if (!protoinfo) goto nla_put_failure; if (inet6_fill_ifla6_attrs(skb, idev) < 0) @@ -4730,7 +4923,7 @@ void inet6_ifinfo_notify(int event, struct inet6_dev *idev) int err = -ENOBUFS; skb = nlmsg_new(inet6_if_nlmsg_size(), GFP_ATOMIC); - if (skb == NULL) + if (!skb) goto errout; err = inet6_fill_ifinfo(skb, idev, 0, 0, event, 0); @@ -4763,7 +4956,7 @@ static int inet6_fill_prefix(struct sk_buff *skb, struct inet6_dev *idev, struct prefix_cacheinfo ci; nlh = nlmsg_put(skb, portid, seq, event, sizeof(*pmsg), flags); - if (nlh == NULL) + if (!nlh) return -EMSGSIZE; pmsg = nlmsg_data(nlh); @@ -4802,7 +4995,7 @@ static void inet6_prefix_notify(int event, struct inet6_dev *idev, int err = -ENOBUFS; skb = nlmsg_new(inet6_prefix_nlmsg_size(), GFP_ATOMIC); - if (skb == NULL) + if (!skb) goto errout; err = inet6_fill_prefix(skb, idev, pinfo, 0, 0, event, 0); @@ -5042,6 +5235,74 @@ int addrconf_sysctl_proxy_ndp(struct ctl_table *ctl, int write, return ret; } +static int addrconf_sysctl_stable_secret(struct ctl_table *ctl, int write, + void __user *buffer, size_t *lenp, + loff_t *ppos) +{ + int err; + struct in6_addr addr; + char str[IPV6_MAX_STRLEN]; + struct ctl_table lctl = *ctl; + struct net *net = ctl->extra2; + struct ipv6_stable_secret *secret = ctl->data; + + if (&net->ipv6.devconf_all->stable_secret == ctl->data) + return -EIO; + + lctl.maxlen = IPV6_MAX_STRLEN; + lctl.data = str; + + if (!rtnl_trylock()) + return restart_syscall(); + + if (!write && !secret->initialized) { + err = -EIO; + goto out; + } + + if (!write) { + err = snprintf(str, sizeof(str), "%pI6", + &secret->secret); + if (err >= sizeof(str)) { + err = -EIO; + goto out; + } + } + + err = proc_dostring(&lctl, write, buffer, lenp, ppos); + if (err || !write) + goto out; + + if (in6_pton(str, -1, addr.in6_u.u6_addr8, -1, NULL) != 1) { + err = -EIO; + goto out; + } + + secret->initialized = true; + secret->secret = addr; + + if (&net->ipv6.devconf_dflt->stable_secret == ctl->data) { + struct net_device *dev; + + for_each_netdev(net, dev) { + struct inet6_dev *idev = __in6_dev_get(dev); + + if (idev) { + idev->addr_gen_mode = + IN6_ADDR_GEN_MODE_STABLE_PRIVACY; + } + } + } else { + struct inet6_dev *idev = ctl->extra1; + + idev->addr_gen_mode = IN6_ADDR_GEN_MODE_STABLE_PRIVACY; + } + +out: + rtnl_unlock(); + + return err; +} static struct addrconf_sysctl_table { @@ -5315,6 +5576,13 @@ static struct addrconf_sysctl_table .proc_handler = proc_dointvec, }, { + .procname = "stable_secret", + .data = &ipv6_devconf.stable_secret, + .maxlen = IPV6_MAX_STRLEN, + .mode = 0600, + .proc_handler = addrconf_sysctl_stable_secret, + }, + { /* sentinel */ } }, @@ -5328,7 +5596,7 @@ static int __addrconf_sysctl_register(struct net *net, char *dev_name, char path[sizeof("net/ipv6/conf/") + IFNAMSIZ]; t = kmemdup(&addrconf_sysctl, sizeof(*t), GFP_KERNEL); - if (t == NULL) + if (!t) goto out; for (i = 0; t->addrconf_vars[i].data; i++) { @@ -5340,7 +5608,7 @@ static int __addrconf_sysctl_register(struct net *net, char *dev_name, snprintf(path, sizeof(path), "net/ipv6/conf/%s", dev_name); t->sysctl_header = register_net_sysctl(net, path, t->addrconf_vars); - if (t->sysctl_header == NULL) + if (!t->sysctl_header) goto free; p->sysctl = t; @@ -5356,7 +5624,7 @@ static void __addrconf_sysctl_unregister(struct ipv6_devconf *p) { struct addrconf_sysctl_table *t; - if (p->sysctl == NULL) + if (!p->sysctl) return; t = p->sysctl; @@ -5399,17 +5667,20 @@ static int __net_init addrconf_init_net(struct net *net) struct ipv6_devconf *all, *dflt; all = kmemdup(&ipv6_devconf, sizeof(ipv6_devconf), GFP_KERNEL); - if (all == NULL) + if (!all) goto err_alloc_all; dflt = kmemdup(&ipv6_devconf_dflt, sizeof(ipv6_devconf_dflt), GFP_KERNEL); - if (dflt == NULL) + if (!dflt) goto err_alloc_dflt; /* these will be inherited by all namespaces */ dflt->autoconf = ipv6_defaults.autoconf; dflt->disable_ipv6 = ipv6_defaults.disable_ipv6; + dflt->stable_secret.initialized = false; + all->stable_secret.initialized = false; + net->ipv6.devconf_all = all; net->ipv6.devconf_dflt = dflt; diff --git a/net/ipv6/addrconf_core.c b/net/ipv6/addrconf_core.c index 98cc4cd570e2..d873ceea86e6 100644 --- a/net/ipv6/addrconf_core.c +++ b/net/ipv6/addrconf_core.c @@ -140,7 +140,7 @@ void in6_dev_finish_destroy(struct inet6_dev *idev) struct net_device *dev = idev->dev; WARN_ON(!list_empty(&idev->addr_list)); - WARN_ON(idev->mc_list != NULL); + WARN_ON(idev->mc_list); WARN_ON(timer_pending(&idev->rs_timer)); #ifdef NET_REFCNT_DEBUG diff --git a/net/ipv6/addrlabel.c b/net/ipv6/addrlabel.c index e43e79d0a612..882124ebb438 100644 --- a/net/ipv6/addrlabel.c +++ b/net/ipv6/addrlabel.c @@ -29,9 +29,7 @@ * Policy Table */ struct ip6addrlbl_entry { -#ifdef CONFIG_NET_NS - struct net *lbl_net; -#endif + possible_net_t lbl_net; struct in6_addr prefix; int prefixlen; int ifindex; @@ -129,9 +127,6 @@ static const __net_initconst struct ip6addrlbl_init_table /* Object management */ static inline void ip6addrlbl_free(struct ip6addrlbl_entry *p) { -#ifdef CONFIG_NET_NS - release_net(p->lbl_net); -#endif kfree(p); } @@ -240,9 +235,7 @@ static struct ip6addrlbl_entry *ip6addrlbl_alloc(struct net *net, newp->addrtype = addrtype; newp->label = label; INIT_HLIST_NODE(&newp->list); -#ifdef CONFIG_NET_NS - newp->lbl_net = hold_net(net); -#endif + write_pnet(&newp->lbl_net, net); atomic_set(&newp->refcnt, 1); return newp; } @@ -484,7 +477,7 @@ static int ip6addrlbl_fill(struct sk_buff *skb, ip6addrlbl_putmsg(nlh, p->prefixlen, p->ifindex, lseq); - if (nla_put(skb, IFAL_ADDRESS, 16, &p->prefix) < 0 || + if (nla_put_in6_addr(skb, IFAL_ADDRESS, &p->prefix) < 0 || nla_put_u32(skb, IFAL_LABEL, p->label) < 0) { nlmsg_cancel(skb, nlh); return -EMSGSIZE; diff --git a/net/ipv6/af_inet6.c b/net/ipv6/af_inet6.c index e8c4400f23e9..eef63b394c5a 100644 --- a/net/ipv6/af_inet6.c +++ b/net/ipv6/af_inet6.c @@ -164,11 +164,11 @@ lookup_protocol: answer_flags = answer->flags; rcu_read_unlock(); - WARN_ON(answer_prot->slab == NULL); + WARN_ON(!answer_prot->slab); err = -ENOBUFS; sk = sk_alloc(net, PF_INET6, GFP_KERNEL, answer_prot); - if (sk == NULL) + if (!sk) goto out; sock_init_data(sock, sk); @@ -391,7 +391,7 @@ int inet6_release(struct socket *sock) { struct sock *sk = sock->sk; - if (sk == NULL) + if (!sk) return -EINVAL; /* Free mc lists */ @@ -413,11 +413,11 @@ void inet6_destroy_sock(struct sock *sk) /* Release rx options */ skb = xchg(&np->pktoptions, NULL); - if (skb != NULL) + if (skb) kfree_skb(skb); skb = xchg(&np->rxpmtu, NULL); - if (skb != NULL) + if (skb) kfree_skb(skb); /* Free flowlabels */ @@ -426,7 +426,7 @@ void inet6_destroy_sock(struct sock *sk) /* Free tx options */ opt = xchg(&np->opt, NULL); - if (opt != NULL) + if (opt) sock_kfree_s(sk, opt, opt->tot_len); } EXPORT_SYMBOL_GPL(inet6_destroy_sock); @@ -640,7 +640,7 @@ int inet6_sk_rebuild_header(struct sock *sk) dst = __sk_dst_check(sk, np->dst_cookie); - if (dst == NULL) { + if (!dst) { struct inet_sock *inet = inet_sk(sk); struct in6_addr *final_p, final; struct flowi6 fl6; @@ -766,6 +766,8 @@ static int __net_init inet6_net_init(struct net *net) net->ipv6.sysctl.icmpv6_time = 1*HZ; net->ipv6.sysctl.flowlabel_consistency = 1; net->ipv6.sysctl.auto_flowlabels = 0; + net->ipv6.sysctl.idgen_retries = 3; + net->ipv6.sysctl.idgen_delay = 1 * HZ; atomic_set(&net->ipv6.fib6_sernum, 1); err = ipv6_init_mibs(net); @@ -824,7 +826,7 @@ static int __init inet6_init(void) struct list_head *r; int err = 0; - BUILD_BUG_ON(sizeof(struct inet6_skb_parm) > FIELD_SIZEOF(struct sk_buff, cb)); + sock_skb_cb_check_size(sizeof(struct inet6_skb_parm)); /* Register the socket-side information for inet6_create. */ for (r = &inetsw6[0]; r < &inetsw6[SOCK_MAX]; ++r) diff --git a/net/ipv6/ah6.c b/net/ipv6/ah6.c index a6727add2624..ed7d4e3f9c10 100644 --- a/net/ipv6/ah6.c +++ b/net/ipv6/ah6.c @@ -681,7 +681,7 @@ static int ah6_init_state(struct xfrm_state *x) goto error; ahp = kzalloc(sizeof(*ahp), GFP_KERNEL); - if (ahp == NULL) + if (!ahp) return -ENOMEM; ahash = crypto_alloc_ahash(x->aalg->alg_name, 0, 0); diff --git a/net/ipv6/anycast.c b/net/ipv6/anycast.c index baf2742d1ec4..514ac259f543 100644 --- a/net/ipv6/anycast.c +++ b/net/ipv6/anycast.c @@ -60,6 +60,8 @@ int ipv6_sock_ac_join(struct sock *sk, int ifindex, const struct in6_addr *addr) int ishost = !net->ipv6.devconf_all->forwarding; int err = 0; + ASSERT_RTNL(); + if (!ns_capable(net->user_ns, CAP_NET_ADMIN)) return -EPERM; if (ipv6_addr_is_multicast(addr)) @@ -68,12 +70,11 @@ int ipv6_sock_ac_join(struct sock *sk, int ifindex, const struct in6_addr *addr) return -EINVAL; pac = sock_kmalloc(sk, sizeof(struct ipv6_ac_socklist), GFP_KERNEL); - if (pac == NULL) + if (!pac) return -ENOMEM; pac->acl_next = NULL; pac->acl_addr = *addr; - rtnl_lock(); if (ifindex == 0) { struct rt6_info *rt; @@ -92,7 +93,7 @@ int ipv6_sock_ac_join(struct sock *sk, int ifindex, const struct in6_addr *addr) } else dev = __dev_get_by_index(net, ifindex); - if (dev == NULL) { + if (!dev) { err = -ENODEV; goto error; } @@ -130,7 +131,6 @@ int ipv6_sock_ac_join(struct sock *sk, int ifindex, const struct in6_addr *addr) } error: - rtnl_unlock(); if (pac) sock_kfree_s(sk, pac, sizeof(*pac)); return err; @@ -146,7 +146,8 @@ int ipv6_sock_ac_drop(struct sock *sk, int ifindex, const struct in6_addr *addr) struct ipv6_ac_socklist *pac, *prev_pac; struct net *net = sock_net(sk); - rtnl_lock(); + ASSERT_RTNL(); + prev_pac = NULL; for (pac = np->ipv6_ac_list; pac; pac = pac->acl_next) { if ((ifindex == 0 || pac->acl_ifindex == ifindex) && @@ -154,10 +155,8 @@ int ipv6_sock_ac_drop(struct sock *sk, int ifindex, const struct in6_addr *addr) break; prev_pac = pac; } - if (!pac) { - rtnl_unlock(); + if (!pac) return -ENOENT; - } if (prev_pac) prev_pac->acl_next = pac->acl_next; else @@ -166,7 +165,6 @@ int ipv6_sock_ac_drop(struct sock *sk, int ifindex, const struct in6_addr *addr) dev = __dev_get_by_index(net, pac->acl_ifindex); if (dev) ipv6_dev_ac_dec(dev, &pac->acl_addr); - rtnl_unlock(); sock_kfree_s(sk, pac, sizeof(*pac)); return 0; @@ -224,7 +222,7 @@ static struct ifacaddr6 *aca_alloc(struct rt6_info *rt, struct ifacaddr6 *aca; aca = kzalloc(sizeof(*aca), GFP_ATOMIC); - if (aca == NULL) + if (!aca) return NULL; aca->aca_addr = *addr; @@ -270,7 +268,7 @@ int __ipv6_dev_ac_inc(struct inet6_dev *idev, const struct in6_addr *addr) goto out; } aca = aca_alloc(rt, addr); - if (aca == NULL) { + if (!aca) { ip6_rt_put(rt); err = -ENOMEM; goto out; @@ -339,7 +337,7 @@ static int ipv6_dev_ac_dec(struct net_device *dev, const struct in6_addr *addr) { struct inet6_dev *idev = __in6_dev_get(dev); - if (idev == NULL) + if (!idev) return -ENODEV; return __ipv6_dev_ac_dec(idev, addr); } diff --git a/net/ipv6/datagram.c b/net/ipv6/datagram.c index ace8daca5c83..762a58c772b8 100644 --- a/net/ipv6/datagram.c +++ b/net/ipv6/datagram.c @@ -71,7 +71,7 @@ int ip6_datagram_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len) fl6.flowlabel = usin->sin6_flowinfo&IPV6_FLOWINFO_MASK; if (fl6.flowlabel&IPV6_FLOWLABEL_MASK) { flowlabel = fl6_sock_lookup(sk, fl6.flowlabel); - if (flowlabel == NULL) + if (!flowlabel) return -EINVAL; } } @@ -373,7 +373,7 @@ int ipv6_recv_error(struct sock *sk, struct msghdr *msg, int len, int *addr_len) err = -EAGAIN; skb = sock_dequeue_err_skb(sk); - if (skb == NULL) + if (!skb) goto out; copied = skb->len; @@ -463,7 +463,7 @@ int ipv6_recv_rxpmtu(struct sock *sk, struct msghdr *msg, int len, err = -EAGAIN; skb = xchg(&np->rxpmtu, NULL); - if (skb == NULL) + if (!skb) goto out; copied = skb->len; diff --git a/net/ipv6/esp6.c b/net/ipv6/esp6.c index e48f2c7c5c59..31f1b5d5e2ef 100644 --- a/net/ipv6/esp6.c +++ b/net/ipv6/esp6.c @@ -495,7 +495,7 @@ static int esp_init_authenc(struct xfrm_state *x) int err; err = -EINVAL; - if (x->ealg == NULL) + if (!x->ealg) goto error; err = -ENAMETOOLONG; diff --git a/net/ipv6/exthdrs_core.c b/net/ipv6/exthdrs_core.c index 8af3eb57f438..5c5d23e59da5 100644 --- a/net/ipv6/exthdrs_core.c +++ b/net/ipv6/exthdrs_core.c @@ -82,7 +82,7 @@ int ipv6_skip_exthdr(const struct sk_buff *skb, int start, u8 *nexthdrp, if (nexthdr == NEXTHDR_NONE) return -1; hp = skb_header_pointer(skb, start, sizeof(_hdr), &_hdr); - if (hp == NULL) + if (!hp) return -1; if (nexthdr == NEXTHDR_FRAGMENT) { __be16 _frag_off, *fp; @@ -91,7 +91,7 @@ int ipv6_skip_exthdr(const struct sk_buff *skb, int start, u8 *nexthdrp, frag_off), sizeof(_frag_off), &_frag_off); - if (fp == NULL) + if (!fp) return -1; *frag_offp = *fp; @@ -218,7 +218,7 @@ int ipv6_find_hdr(const struct sk_buff *skb, unsigned int *offset, } hp = skb_header_pointer(skb, start, sizeof(_hdr), &_hdr); - if (hp == NULL) + if (!hp) return -EBADMSG; if (nexthdr == NEXTHDR_ROUTING) { @@ -226,7 +226,7 @@ int ipv6_find_hdr(const struct sk_buff *skb, unsigned int *offset, rh = skb_header_pointer(skb, start, sizeof(_rh), &_rh); - if (rh == NULL) + if (!rh) return -EBADMSG; if (flags && (*flags & IP6_FH_F_SKIP_RH) && @@ -245,7 +245,7 @@ int ipv6_find_hdr(const struct sk_buff *skb, unsigned int *offset, frag_off), sizeof(_frag_off), &_frag_off); - if (fp == NULL) + if (!fp) return -EBADMSG; _frag_off = ntohs(*fp) & ~0x7; diff --git a/net/ipv6/fib6_rules.c b/net/ipv6/fib6_rules.c index 70bc6abc0639..2367a16eae58 100644 --- a/net/ipv6/fib6_rules.c +++ b/net/ipv6/fib6_rules.c @@ -199,12 +199,10 @@ static int fib6_rule_configure(struct fib_rule *rule, struct sk_buff *skb, } if (frh->src_len) - nla_memcpy(&rule6->src.addr, tb[FRA_SRC], - sizeof(struct in6_addr)); + rule6->src.addr = nla_get_in6_addr(tb[FRA_SRC]); if (frh->dst_len) - nla_memcpy(&rule6->dst.addr, tb[FRA_DST], - sizeof(struct in6_addr)); + rule6->dst.addr = nla_get_in6_addr(tb[FRA_DST]); rule6->src.plen = frh->src_len; rule6->dst.plen = frh->dst_len; @@ -250,11 +248,9 @@ static int fib6_rule_fill(struct fib_rule *rule, struct sk_buff *skb, frh->tos = rule6->tclass; if ((rule6->dst.plen && - nla_put(skb, FRA_DST, sizeof(struct in6_addr), - &rule6->dst.addr)) || + nla_put_in6_addr(skb, FRA_DST, &rule6->dst.addr)) || (rule6->src.plen && - nla_put(skb, FRA_SRC, sizeof(struct in6_addr), - &rule6->src.addr))) + nla_put_in6_addr(skb, FRA_SRC, &rule6->src.addr))) goto nla_put_failure; return 0; @@ -299,19 +295,16 @@ static int __net_init fib6_rules_net_init(struct net *net) ops = fib_rules_register(&fib6_rules_ops_template, net); if (IS_ERR(ops)) return PTR_ERR(ops); - net->ipv6.fib6_rules_ops = ops; - - err = fib_default_rule_add(net->ipv6.fib6_rules_ops, 0, - RT6_TABLE_LOCAL, 0); + err = fib_default_rule_add(ops, 0, RT6_TABLE_LOCAL, 0); if (err) goto out_fib6_rules_ops; - err = fib_default_rule_add(net->ipv6.fib6_rules_ops, - 0x7FFE, RT6_TABLE_MAIN, 0); + err = fib_default_rule_add(ops, 0x7FFE, RT6_TABLE_MAIN, 0); if (err) goto out_fib6_rules_ops; + net->ipv6.fib6_rules_ops = ops; out: return err; diff --git a/net/ipv6/icmp.c b/net/ipv6/icmp.c index a5e95199585e..2c2b5d51f15c 100644 --- a/net/ipv6/icmp.c +++ b/net/ipv6/icmp.c @@ -160,8 +160,7 @@ static bool is_ineligible(const struct sk_buff *skb) tp = skb_header_pointer(skb, ptr+offsetof(struct icmp6hdr, icmp6_type), sizeof(_type), &_type); - if (tp == NULL || - !(*tp & ICMPV6_INFOMSG_MASK)) + if (!tp || !(*tp & ICMPV6_INFOMSG_MASK)) return true; } return false; @@ -231,7 +230,7 @@ static bool opt_unrec(struct sk_buff *skb, __u32 offset) offset += skb_network_offset(skb); op = skb_header_pointer(skb, offset, sizeof(_optval), &_optval); - if (op == NULL) + if (!op) return true; return (*op & 0xC0) == 0x80; } @@ -244,7 +243,7 @@ int icmpv6_push_pending_frames(struct sock *sk, struct flowi6 *fl6, int err = 0; skb = skb_peek(&sk->sk_write_queue); - if (skb == NULL) + if (!skb) goto out; icmp6h = icmp6_hdr(skb); @@ -479,7 +478,7 @@ static void icmp6_send(struct sk_buff *skb, u8 type, u8 code, __u32 info) security_skb_classify_flow(skb, flowi6_to_flowi(&fl6)); sk = icmpv6_xmit_lock(net); - if (sk == NULL) + if (!sk) return; sk->sk_mark = mark; np = inet6_sk(sk); @@ -582,7 +581,7 @@ static void icmpv6_echo_reply(struct sk_buff *skb) security_skb_classify_flow(skb, flowi6_to_flowi(&fl6)); sk = icmpv6_xmit_lock(net); - if (sk == NULL) + if (!sk) return; sk->sk_mark = mark; np = inet6_sk(sk); @@ -839,7 +838,7 @@ static int __net_init icmpv6_sk_init(struct net *net) net->ipv6.icmp_sk = kzalloc(nr_cpu_ids * sizeof(struct sock *), GFP_KERNEL); - if (net->ipv6.icmp_sk == NULL) + if (!net->ipv6.icmp_sk) return -ENOMEM; for_each_possible_cpu(i) { diff --git a/net/ipv6/inet6_connection_sock.c b/net/ipv6/inet6_connection_sock.c index 29b32206e494..6927f3fb5597 100644 --- a/net/ipv6/inet6_connection_sock.c +++ b/net/ipv6/inet6_connection_sock.c @@ -112,22 +112,20 @@ static u32 inet6_synq_hash(const struct in6_addr *raddr, const __be16 rport, return c & (synq_hsize - 1); } -struct request_sock *inet6_csk_search_req(const struct sock *sk, - struct request_sock ***prevp, +struct request_sock *inet6_csk_search_req(struct sock *sk, const __be16 rport, const struct in6_addr *raddr, const struct in6_addr *laddr, const int iif) { - const struct inet_connection_sock *icsk = inet_csk(sk); + struct inet_connection_sock *icsk = inet_csk(sk); struct listen_sock *lopt = icsk->icsk_accept_queue.listen_opt; - struct request_sock *req, **prev; + struct request_sock *req; + u32 hash = inet6_synq_hash(raddr, rport, lopt->hash_rnd, + lopt->nr_table_entries); - for (prev = &lopt->syn_table[inet6_synq_hash(raddr, rport, - lopt->hash_rnd, - lopt->nr_table_entries)]; - (req = *prev) != NULL; - prev = &req->dl_next) { + spin_lock(&icsk->icsk_accept_queue.syn_wait_lock); + for (req = lopt->syn_table[hash]; req != NULL; req = req->dl_next) { const struct inet_request_sock *ireq = inet_rsk(req); if (ireq->ir_rmt_port == rport && @@ -135,13 +133,14 @@ struct request_sock *inet6_csk_search_req(const struct sock *sk, ipv6_addr_equal(&ireq->ir_v6_rmt_addr, raddr) && ipv6_addr_equal(&ireq->ir_v6_loc_addr, laddr) && (!ireq->ir_iif || ireq->ir_iif == iif)) { + atomic_inc(&req->rsk_refcnt); WARN_ON(req->sk != NULL); - *prevp = prev; - return req; + break; } } + spin_unlock(&icsk->icsk_accept_queue.syn_wait_lock); - return NULL; + return req; } EXPORT_SYMBOL_GPL(inet6_csk_search_req); diff --git a/net/ipv6/inet6_hashtables.c b/net/ipv6/inet6_hashtables.c index 051dffb49c90..871641bc1ed4 100644 --- a/net/ipv6/inet6_hashtables.c +++ b/net/ipv6/inet6_hashtables.c @@ -23,11 +23,9 @@ #include <net/secure_seq.h> #include <net/ip.h> -static unsigned int inet6_ehashfn(struct net *net, - const struct in6_addr *laddr, - const u16 lport, - const struct in6_addr *faddr, - const __be16 fport) +u32 inet6_ehashfn(const struct net *net, + const struct in6_addr *laddr, const u16 lport, + const struct in6_addr *faddr, const __be16 fport) { static u32 inet6_ehash_secret __read_mostly; static u32 ipv6_hash_secret __read_mostly; @@ -44,54 +42,6 @@ static unsigned int inet6_ehashfn(struct net *net, inet6_ehash_secret + net_hash_mix(net)); } -static int inet6_sk_ehashfn(const struct sock *sk) -{ - const struct inet_sock *inet = inet_sk(sk); - const struct in6_addr *laddr = &sk->sk_v6_rcv_saddr; - const struct in6_addr *faddr = &sk->sk_v6_daddr; - const __u16 lport = inet->inet_num; - const __be16 fport = inet->inet_dport; - struct net *net = sock_net(sk); - - return inet6_ehashfn(net, laddr, lport, faddr, fport); -} - -int __inet6_hash(struct sock *sk, struct inet_timewait_sock *tw) -{ - struct inet_hashinfo *hashinfo = sk->sk_prot->h.hashinfo; - int twrefcnt = 0; - - WARN_ON(!sk_unhashed(sk)); - - if (sk->sk_state == TCP_LISTEN) { - struct inet_listen_hashbucket *ilb; - - ilb = &hashinfo->listening_hash[inet_sk_listen_hashfn(sk)]; - spin_lock(&ilb->lock); - __sk_nulls_add_node_rcu(sk, &ilb->head); - spin_unlock(&ilb->lock); - } else { - unsigned int hash; - struct hlist_nulls_head *list; - spinlock_t *lock; - - sk->sk_hash = hash = inet6_sk_ehashfn(sk); - list = &inet_ehash_bucket(hashinfo, hash)->chain; - lock = inet_ehash_lockp(hashinfo, hash); - spin_lock(lock); - __sk_nulls_add_node_rcu(sk, list); - if (tw) { - WARN_ON(sk->sk_hash != tw->tw_hash); - twrefcnt = inet_twsk_unhash(tw); - } - spin_unlock(lock); - } - - sock_prot_inuse_add(sock_net(sk), sk->sk_prot, 1); - return twrefcnt; -} -EXPORT_SYMBOL(__inet6_hash); - /* * Sockets in TCP_CLOSE state are _always_ taken out of the hash, so * we need not check it for TCP lookups anymore, thanks Alexey. -DaveM @@ -296,7 +246,7 @@ static int __inet6_check_established(struct inet_timewait_death_row *death_row, *twp = tw; } else if (tw) { /* Silly. Should hash-dance instead... */ - inet_twsk_deschedule(tw, death_row); + inet_twsk_deschedule(tw); inet_twsk_put(tw); } @@ -320,6 +270,6 @@ int inet6_hash_connect(struct inet_timewait_death_row *death_row, struct sock *sk) { return __inet_hash_connect(death_row, sk, inet6_sk_port_offset(sk), - __inet6_check_established, __inet6_hash); + __inet6_check_established); } EXPORT_SYMBOL_GPL(inet6_hash_connect); diff --git a/net/ipv6/ip6_fib.c b/net/ipv6/ip6_fib.c index 263ef4143bff..96dbffff5a24 100644 --- a/net/ipv6/ip6_fib.c +++ b/net/ipv6/ip6_fib.c @@ -1206,7 +1206,7 @@ static struct fib6_node *fib6_repair_tree(struct net *net, WARN_ON(fn->fn_flags & RTN_RTINFO); WARN_ON(fn->fn_flags & RTN_TL_ROOT); - WARN_ON(fn->leaf != NULL); + WARN_ON(fn->leaf); children = 0; child = NULL; @@ -1361,7 +1361,7 @@ int fib6_del(struct rt6_info *rt, struct nl_info *info) #if RT6_DEBUG >= 2 if (rt->dst.obsolete > 0) { - WARN_ON(fn != NULL); + WARN_ON(fn); return -ENOENT; } #endif diff --git a/net/ipv6/ip6_flowlabel.c b/net/ipv6/ip6_flowlabel.c index f45d6db50a45..d491125011c4 100644 --- a/net/ipv6/ip6_flowlabel.c +++ b/net/ipv6/ip6_flowlabel.c @@ -100,7 +100,6 @@ static void fl_free(struct ip6_flowlabel *fl) if (fl) { if (fl->share == IPV6_FL_S_PROCESS) put_pid(fl->owner.pid); - release_net(fl->fl_net); kfree(fl->opt); kfree_rcu(fl, rcu); } @@ -206,7 +205,7 @@ static struct ip6_flowlabel *fl_intern(struct net *net, fl->label = htonl(prandom_u32())&IPV6_FLOWLABEL_MASK; if (fl->label) { lfl = __fl_lookup(net, fl->label); - if (lfl == NULL) + if (!lfl) break; } } @@ -220,7 +219,7 @@ static struct ip6_flowlabel *fl_intern(struct net *net, * with the same label can only appear on another sock */ lfl = __fl_lookup(net, fl->label); - if (lfl != NULL) { + if (lfl) { atomic_inc(&lfl->users); spin_unlock_bh(&ip6_fl_lock); return lfl; @@ -298,10 +297,10 @@ struct ipv6_txoptions *fl6_merge_options(struct ipv6_txoptions *opt_space, { struct ipv6_txoptions *fl_opt = fl->opt; - if (fopt == NULL || fopt->opt_flen == 0) + if (!fopt || fopt->opt_flen == 0) return fl_opt; - if (fl_opt != NULL) { + if (fl_opt) { opt_space->hopopt = fl_opt->hopopt; opt_space->dst0opt = fl_opt->dst0opt; opt_space->srcrt = fl_opt->srcrt; @@ -367,7 +366,7 @@ fl_create(struct net *net, struct sock *sk, struct in6_flowlabel_req *freq, err = -ENOMEM; fl = kzalloc(sizeof(*fl), GFP_KERNEL); - if (fl == NULL) + if (!fl) goto done; if (olen > 0) { @@ -377,7 +376,7 @@ fl_create(struct net *net, struct sock *sk, struct in6_flowlabel_req *freq, err = -ENOMEM; fl->opt = kmalloc(sizeof(*fl->opt) + olen, GFP_KERNEL); - if (fl->opt == NULL) + if (!fl->opt) goto done; memset(fl->opt, 0, sizeof(*fl->opt)); @@ -403,7 +402,7 @@ fl_create(struct net *net, struct sock *sk, struct in6_flowlabel_req *freq, } } - fl->fl_net = hold_net(net); + fl->fl_net = net; fl->expires = jiffies; err = fl6_renew(fl, freq->flr_linger, freq->flr_expires); if (err) @@ -597,7 +596,7 @@ int ipv6_flowlabel_opt(struct sock *sk, char __user *optval, int optlen) return -EINVAL; fl = fl_create(net, sk, &freq, optval, optlen, &err); - if (fl == NULL) + if (!fl) return err; sfl1 = kmalloc(sizeof(*sfl1), GFP_KERNEL); @@ -617,7 +616,7 @@ int ipv6_flowlabel_opt(struct sock *sk, char __user *optval, int optlen) } rcu_read_unlock_bh(); - if (fl1 == NULL) + if (!fl1) fl1 = fl_lookup(net, freq.flr_label); if (fl1) { recheck: @@ -634,7 +633,7 @@ recheck: goto release; err = -ENOMEM; - if (sfl1 == NULL) + if (!sfl1) goto release; if (fl->linger > fl1->linger) fl1->linger = fl->linger; @@ -654,7 +653,7 @@ release: goto done; err = -ENOMEM; - if (sfl1 == NULL) + if (!sfl1) goto done; err = mem_check(sk); @@ -662,7 +661,7 @@ release: goto done; fl1 = fl_intern(net, fl, freq.flr_label); - if (fl1 != NULL) + if (fl1) goto recheck; if (!freq.flr_label) { diff --git a/net/ipv6/ip6_gre.c b/net/ipv6/ip6_gre.c index bc28b7d42a6d..a38d3ac0f18f 100644 --- a/net/ipv6/ip6_gre.c +++ b/net/ipv6/ip6_gre.c @@ -223,7 +223,7 @@ static struct ip6_tnl *ip6gre_tunnel_lookup(struct net_device *dev, } } - if (cand != NULL) + if (cand) return cand; dev = ign->fb_tunnel_dev; @@ -395,7 +395,7 @@ static void ip6gre_err(struct sk_buff *skb, struct inet6_skb_parm *opt, flags & GRE_KEY ? *(((__be32 *)p) + (grehlen / 4) - 1) : 0, p[1]); - if (t == NULL) + if (!t) return; switch (type) { @@ -760,7 +760,7 @@ static netdev_tx_t ip6gre_xmit2(struct sk_buff *skb, skb_set_inner_protocol(skb, protocol); - ip6tunnel_xmit(skb, dev); + ip6tunnel_xmit(NULL, skb, dev); if (ndst) ip6_tnl_dst_store(tunnel, ndst); return 0; @@ -980,7 +980,7 @@ static void ip6gre_tnl_link_config(struct ip6_tnl *t, int set_mtu) &p->raddr, &p->laddr, p->link, strict); - if (rt == NULL) + if (!rt) return; if (rt->dst.dev) { @@ -1073,7 +1073,7 @@ static int ip6gre_tunnel_ioctl(struct net_device *dev, } ip6gre_tnl_parm_from_user(&p1, &p); t = ip6gre_tunnel_locate(net, &p1, 0); - if (t == NULL) + if (!t) t = netdev_priv(dev); } memset(&p, 0, sizeof(p)); @@ -1105,7 +1105,7 @@ static int ip6gre_tunnel_ioctl(struct net_device *dev, t = ip6gre_tunnel_locate(net, &p1, cmd == SIOCADDTUNNEL); if (dev != ign->fb_tunnel_dev && cmd == SIOCCHGTUNNEL) { - if (t != NULL) { + if (t) { if (t->dev != dev) { err = -EEXIST; break; @@ -1144,7 +1144,7 @@ static int ip6gre_tunnel_ioctl(struct net_device *dev, err = -ENOENT; ip6gre_tnl_parm_from_user(&p1, &p); t = ip6gre_tunnel_locate(net, &p1, 0); - if (t == NULL) + if (!t) goto done; err = -EPERM; if (t == netdev_priv(ign->fb_tunnel_dev)) @@ -1216,6 +1216,7 @@ static const struct net_device_ops ip6gre_netdev_ops = { .ndo_do_ioctl = ip6gre_tunnel_ioctl, .ndo_change_mtu = ip6gre_tunnel_change_mtu, .ndo_get_stats64 = ip_tunnel_get_stats64, + .ndo_get_iflink = ip6_tnl_get_iflink, }; static void ip6gre_dev_free(struct net_device *dev) @@ -1238,7 +1239,6 @@ static void ip6gre_tunnel_setup(struct net_device *dev) if (!(t->parms.flags & IP6_TNL_F_IGN_ENCAP_LIMIT)) dev->mtu -= 8; dev->flags |= IFF_NOARP; - dev->iflink = 0; dev->addr_len = sizeof(struct in6_addr); netif_keep_dst(dev); } @@ -1246,7 +1246,6 @@ static void ip6gre_tunnel_setup(struct net_device *dev) static int ip6gre_tunnel_init(struct net_device *dev) { struct ip6_tnl *tunnel; - int i; tunnel = netdev_priv(dev); @@ -1260,18 +1259,10 @@ static int ip6gre_tunnel_init(struct net_device *dev) if (ipv6_addr_any(&tunnel->parms.raddr)) dev->header_ops = &ip6gre_header_ops; - dev->tstats = alloc_percpu(struct pcpu_sw_netstats); + dev->tstats = netdev_alloc_pcpu_stats(struct pcpu_sw_netstats); if (!dev->tstats) return -ENOMEM; - for_each_possible_cpu(i) { - struct pcpu_sw_netstats *ip6gre_tunnel_stats; - ip6gre_tunnel_stats = per_cpu_ptr(dev->tstats, i); - u64_stats_init(&ip6gre_tunnel_stats->syncp); - } - - dev->iflink = tunnel->parms.link; - return 0; } @@ -1313,7 +1304,7 @@ static void ip6gre_destroy_tunnels(struct net *net, struct list_head *head) t = rtnl_dereference(ign->tunnels[prio][h]); - while (t != NULL) { + while (t) { /* If dev is in the same netns, it has already * been added to the list by the previous loop. */ @@ -1412,7 +1403,7 @@ static int ip6gre_tap_validate(struct nlattr *tb[], struct nlattr *data[]) goto out; if (data[IFLA_GRE_REMOTE]) { - nla_memcpy(&daddr, data[IFLA_GRE_REMOTE], sizeof(struct in6_addr)); + daddr = nla_get_in6_addr(data[IFLA_GRE_REMOTE]); if (ipv6_addr_any(&daddr)) return -EINVAL; } @@ -1446,10 +1437,10 @@ static void ip6gre_netlink_parms(struct nlattr *data[], parms->o_key = nla_get_be32(data[IFLA_GRE_OKEY]); if (data[IFLA_GRE_LOCAL]) - nla_memcpy(&parms->laddr, data[IFLA_GRE_LOCAL], sizeof(struct in6_addr)); + parms->laddr = nla_get_in6_addr(data[IFLA_GRE_LOCAL]); if (data[IFLA_GRE_REMOTE]) - nla_memcpy(&parms->raddr, data[IFLA_GRE_REMOTE], sizeof(struct in6_addr)); + parms->raddr = nla_get_in6_addr(data[IFLA_GRE_REMOTE]); if (data[IFLA_GRE_TTL]) parms->hop_limit = nla_get_u8(data[IFLA_GRE_TTL]); @@ -1480,8 +1471,6 @@ static int ip6gre_tap_init(struct net_device *dev) if (!dev->tstats) return -ENOMEM; - dev->iflink = tunnel->parms.link; - return 0; } @@ -1493,6 +1482,7 @@ static const struct net_device_ops ip6gre_tap_netdev_ops = { .ndo_validate_addr = eth_validate_addr, .ndo_change_mtu = ip6gre_tunnel_change_mtu, .ndo_get_stats64 = ip_tunnel_get_stats64, + .ndo_get_iflink = ip6_tnl_get_iflink, }; static void ip6gre_tap_setup(struct net_device *dev) @@ -1503,7 +1493,6 @@ static void ip6gre_tap_setup(struct net_device *dev) dev->netdev_ops = &ip6gre_tap_netdev_ops; dev->destructor = ip6gre_dev_free; - dev->iflink = 0; dev->features |= NETIF_F_NETNS_LOCAL; } @@ -1622,8 +1611,8 @@ static int ip6gre_fill_info(struct sk_buff *skb, const struct net_device *dev) nla_put_be16(skb, IFLA_GRE_OFLAGS, p->o_flags) || nla_put_be32(skb, IFLA_GRE_IKEY, p->i_key) || nla_put_be32(skb, IFLA_GRE_OKEY, p->o_key) || - nla_put(skb, IFLA_GRE_LOCAL, sizeof(struct in6_addr), &p->laddr) || - nla_put(skb, IFLA_GRE_REMOTE, sizeof(struct in6_addr), &p->raddr) || + nla_put_in6_addr(skb, IFLA_GRE_LOCAL, &p->laddr) || + nla_put_in6_addr(skb, IFLA_GRE_REMOTE, &p->raddr) || nla_put_u8(skb, IFLA_GRE_TTL, p->hop_limit) || /*nla_put_u8(skb, IFLA_GRE_TOS, t->priority) ||*/ nla_put_u8(skb, IFLA_GRE_ENCAP_LIMIT, p->encap_limit) || diff --git a/net/ipv6/ip6_input.c b/net/ipv6/ip6_input.c index aacdcb4dc762..f2e464eba5ef 100644 --- a/net/ipv6/ip6_input.c +++ b/net/ipv6/ip6_input.c @@ -46,8 +46,7 @@ #include <net/xfrm.h> #include <net/inet_ecn.h> - -int ip6_rcv_finish(struct sk_buff *skb) +int ip6_rcv_finish(struct sock *sk, struct sk_buff *skb) { if (sysctl_ip_early_demux && !skb_dst(skb) && skb->sk == NULL) { const struct inet6_protocol *ipprot; @@ -183,7 +182,8 @@ int ipv6_rcv(struct sk_buff *skb, struct net_device *dev, struct packet_type *pt /* Must drop socket now because of tproxy. */ skb_orphan(skb); - return NF_HOOK(NFPROTO_IPV6, NF_INET_PRE_ROUTING, skb, dev, NULL, + return NF_HOOK(NFPROTO_IPV6, NF_INET_PRE_ROUTING, NULL, skb, + dev, NULL, ip6_rcv_finish); err: IP6_INC_STATS_BH(net, idev, IPSTATS_MIB_INHDRERRORS); @@ -198,7 +198,7 @@ drop: */ -static int ip6_input_finish(struct sk_buff *skb) +static int ip6_input_finish(struct sock *sk, struct sk_buff *skb) { struct net *net = dev_net(skb_dst(skb)->dev); const struct inet6_protocol *ipprot; @@ -221,7 +221,7 @@ resubmit: raw = raw6_local_deliver(skb, nexthdr); ipprot = rcu_dereference(inet6_protos[nexthdr]); - if (ipprot != NULL) { + if (ipprot) { int ret; if (ipprot->flags & INET6_PROTO_FINAL) { @@ -277,7 +277,8 @@ discard: int ip6_input(struct sk_buff *skb) { - return NF_HOOK(NFPROTO_IPV6, NF_INET_LOCAL_IN, skb, skb->dev, NULL, + return NF_HOOK(NFPROTO_IPV6, NF_INET_LOCAL_IN, NULL, skb, + skb->dev, NULL, ip6_input_finish); } diff --git a/net/ipv6/ip6_offload.c b/net/ipv6/ip6_offload.c index 46d452a56d3e..e893cd18612f 100644 --- a/net/ipv6/ip6_offload.c +++ b/net/ipv6/ip6_offload.c @@ -124,7 +124,7 @@ static struct sk_buff *ipv6_gso_segment(struct sk_buff *skb, unfrag_ip6hlen = ip6_find_1stfragopt(skb, &prevhdr); fptr = (struct frag_hdr *)((u8 *)ipv6h + unfrag_ip6hlen); fptr->frag_off = htons(offset); - if (skb->next != NULL) + if (skb->next) fptr->frag_off |= htons(IP6_MF); offset += (ntohs(ipv6h->payload_len) - sizeof(struct frag_hdr)); diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c index 36cf0ab685a0..7fde1f265c90 100644 --- a/net/ipv6/ip6_output.c +++ b/net/ipv6/ip6_output.c @@ -56,7 +56,7 @@ #include <net/checksum.h> #include <linux/mroute6.h> -static int ip6_finish_output2(struct sk_buff *skb) +static int ip6_finish_output2(struct sock *sk, struct sk_buff *skb) { struct dst_entry *dst = skb_dst(skb); struct net_device *dev = dst->dev; @@ -70,7 +70,7 @@ static int ip6_finish_output2(struct sk_buff *skb) if (ipv6_addr_is_multicast(&ipv6_hdr(skb)->daddr)) { struct inet6_dev *idev = ip6_dst_idev(skb_dst(skb)); - if (!(dev->flags & IFF_LOOPBACK) && sk_mc_loop(skb->sk) && + if (!(dev->flags & IFF_LOOPBACK) && sk_mc_loop(sk) && ((mroute6_socket(dev_net(dev), skb) && !(IP6CB(skb)->flags & IP6SKB_FORWARDED)) || ipv6_chk_mcast_addr(dev, &ipv6_hdr(skb)->daddr, @@ -82,7 +82,7 @@ static int ip6_finish_output2(struct sk_buff *skb) */ if (newskb) NF_HOOK(NFPROTO_IPV6, NF_INET_POST_ROUTING, - newskb, NULL, newskb->dev, + sk, newskb, NULL, newskb->dev, dev_loopback_xmit); if (ipv6_hdr(skb)->hop_limit == 0) { @@ -122,14 +122,14 @@ static int ip6_finish_output2(struct sk_buff *skb) return -EINVAL; } -static int ip6_finish_output(struct sk_buff *skb) +static int ip6_finish_output(struct sock *sk, struct sk_buff *skb) { if ((skb->len > ip6_skb_dst_mtu(skb) && !skb_is_gso(skb)) || dst_allfrag(skb_dst(skb)) || (IP6CB(skb)->frag_max_size && skb->len > IP6CB(skb)->frag_max_size)) - return ip6_fragment(skb, ip6_finish_output2); + return ip6_fragment(sk, skb, ip6_finish_output2); else - return ip6_finish_output2(skb); + return ip6_finish_output2(sk, skb); } int ip6_output(struct sock *sk, struct sk_buff *skb) @@ -143,7 +143,8 @@ int ip6_output(struct sock *sk, struct sk_buff *skb) return 0; } - return NF_HOOK_COND(NFPROTO_IPV6, NF_INET_POST_ROUTING, skb, NULL, dev, + return NF_HOOK_COND(NFPROTO_IPV6, NF_INET_POST_ROUTING, sk, skb, + NULL, dev, ip6_finish_output, !(IP6CB(skb)->flags & IP6SKB_REROUTED)); } @@ -177,7 +178,7 @@ int ip6_xmit(struct sock *sk, struct sk_buff *skb, struct flowi6 *fl6, if (skb_headroom(skb) < head_room) { struct sk_buff *skb2 = skb_realloc_headroom(skb, head_room); - if (skb2 == NULL) { + if (!skb2) { IP6_INC_STATS(net, ip6_dst_idev(skb_dst(skb)), IPSTATS_MIB_OUTDISCARDS); kfree_skb(skb); @@ -223,8 +224,8 @@ int ip6_xmit(struct sock *sk, struct sk_buff *skb, struct flowi6 *fl6, if ((skb->len <= mtu) || skb->ignore_df || skb_is_gso(skb)) { IP6_UPD_PO_STATS(net, ip6_dst_idev(skb_dst(skb)), IPSTATS_MIB_OUT, skb->len); - return NF_HOOK(NFPROTO_IPV6, NF_INET_LOCAL_OUT, skb, NULL, - dst->dev, dst_output); + return NF_HOOK(NFPROTO_IPV6, NF_INET_LOCAL_OUT, sk, skb, + NULL, dst->dev, dst_output_sk); } skb->dev = dst->dev; @@ -316,10 +317,10 @@ static int ip6_forward_proxy_check(struct sk_buff *skb) return 0; } -static inline int ip6_forward_finish(struct sk_buff *skb) +static inline int ip6_forward_finish(struct sock *sk, struct sk_buff *skb) { skb_sender_cpu_clear(skb); - return dst_output(skb); + return dst_output_sk(sk, skb); } static unsigned int ip6_dst_mtu_forward(const struct dst_entry *dst) @@ -511,7 +512,8 @@ int ip6_forward(struct sk_buff *skb) IP6_INC_STATS_BH(net, ip6_dst_idev(dst), IPSTATS_MIB_OUTFORWDATAGRAMS); IP6_ADD_STATS_BH(net, ip6_dst_idev(dst), IPSTATS_MIB_OUTOCTETS, skb->len); - return NF_HOOK(NFPROTO_IPV6, NF_INET_FORWARD, skb, skb->dev, dst->dev, + return NF_HOOK(NFPROTO_IPV6, NF_INET_FORWARD, NULL, skb, + skb->dev, dst->dev, ip6_forward_finish); error: @@ -538,7 +540,8 @@ static void ip6_copy_metadata(struct sk_buff *to, struct sk_buff *from) skb_copy_secmark(to, from); } -int ip6_fragment(struct sk_buff *skb, int (*output)(struct sk_buff *)) +int ip6_fragment(struct sock *sk, struct sk_buff *skb, + int (*output)(struct sock *, struct sk_buff *)) { struct sk_buff *frag; struct rt6_info *rt = (struct rt6_info *)skb_dst(skb); @@ -629,7 +632,7 @@ int ip6_fragment(struct sk_buff *skb, int (*output)(struct sk_buff *)) skb_reset_network_header(skb); memcpy(skb_network_header(skb), tmp_hdr, hlen); - ipv6_select_ident(fh, rt); + ipv6_select_ident(net, fh, rt); fh->nexthdr = nexthdr; fh->reserved = 0; fh->frag_off = htons(IP6_MF); @@ -658,7 +661,7 @@ int ip6_fragment(struct sk_buff *skb, int (*output)(struct sk_buff *)) fh->nexthdr = nexthdr; fh->reserved = 0; fh->frag_off = htons(offset); - if (frag->next != NULL) + if (frag->next) fh->frag_off |= htons(IP6_MF); fh->identification = frag_id; ipv6_hdr(frag)->payload_len = @@ -667,7 +670,7 @@ int ip6_fragment(struct sk_buff *skb, int (*output)(struct sk_buff *)) ip6_copy_metadata(frag, skb); } - err = output(skb); + err = output(sk, skb); if (!err) IP6_INC_STATS(net, ip6_dst_idev(&rt->dst), IPSTATS_MIB_FRAGCREATES); @@ -776,7 +779,7 @@ slow_path: fh->nexthdr = nexthdr; fh->reserved = 0; if (!frag_id) { - ipv6_select_ident(fh, rt); + ipv6_select_ident(net, fh, rt); frag_id = fh->identification; } else fh->identification = frag_id; @@ -800,7 +803,7 @@ slow_path: /* * Put this fragment into the sending queue. */ - err = output(frag); + err = output(sk, frag); if (err) goto fail; @@ -824,7 +827,7 @@ static inline int ip6_rt_check(const struct rt6key *rt_key, const struct in6_addr *addr_cache) { return (rt_key->plen != 128 || !ipv6_addr_equal(fl_addr, &rt_key->addr)) && - (addr_cache == NULL || !ipv6_addr_equal(fl_addr, addr_cache)); + (!addr_cache || !ipv6_addr_equal(fl_addr, addr_cache)); } static struct dst_entry *ip6_sk_dst_check(struct sock *sk, @@ -883,7 +886,7 @@ static int ip6_dst_lookup_tail(struct sock *sk, #endif int err; - if (*dst == NULL) + if (!*dst) *dst = ip6_route_output(net, sk, fl6); err = (*dst)->error; @@ -1046,11 +1049,11 @@ static inline int ip6_ufo_append_data(struct sock *sk, * udp datagram */ skb = skb_peek_tail(queue); - if (skb == NULL) { + if (!skb) { skb = sock_alloc_send_skb(sk, hh_len + fragheaderlen + transhdrlen + 20, (flags & MSG_DONTWAIT), &err); - if (skb == NULL) + if (!skb) return err; /* reserve space for Hardware header */ @@ -1080,7 +1083,7 @@ static inline int ip6_ufo_append_data(struct sock *sk, skb_shinfo(skb)->gso_size = (mtu - fragheaderlen - sizeof(struct frag_hdr)) & ~7; skb_shinfo(skb)->gso_type = SKB_GSO_UDP; - ipv6_select_ident(&fhdr, rt); + ipv6_select_ident(sock_net(sk), &fhdr, rt); skb_shinfo(skb)->ip6_frag_id = fhdr.identification; append: @@ -1108,7 +1111,7 @@ static void ip6_append_data_mtu(unsigned int *mtu, unsigned int orig_mtu) { if (!(rt->dst.flags & DST_XFRM_TUNNEL)) { - if (skb == NULL) { + if (!skb) { /* first fragment, reserve header_len */ *mtu = orig_mtu - rt->dst.header_len; @@ -1140,7 +1143,7 @@ static int ip6_setup_cork(struct sock *sk, struct inet_cork_full *cork, return -EINVAL; v6_cork->opt = kzalloc(opt->tot_len, sk->sk_allocation); - if (unlikely(v6_cork->opt == NULL)) + if (unlikely(!v6_cork->opt)) return -ENOBUFS; v6_cork->opt->tot_len = opt->tot_len; @@ -1332,7 +1335,7 @@ alloc_new_skb: else fraggap = 0; /* update mtu and maxfraglen if necessary */ - if (skb == NULL || skb_prev == NULL) + if (!skb || !skb_prev) ip6_append_data_mtu(&mtu, &maxfraglen, fragheaderlen, skb, rt, orig_mtu); @@ -1384,10 +1387,10 @@ alloc_new_skb: skb = sock_wmalloc(sk, alloclen + hh_len, 1, sk->sk_allocation); - if (unlikely(skb == NULL)) + if (unlikely(!skb)) err = -ENOBUFS; } - if (skb == NULL) + if (!skb) goto error; /* * Fill in the control structures @@ -1579,7 +1582,7 @@ struct sk_buff *__ip6_make_skb(struct sock *sk, unsigned char proto = fl6->flowi6_proto; skb = __skb_dequeue(queue); - if (skb == NULL) + if (!skb) goto out; tail_skb = &(skb_shinfo(skb)->frag_list); diff --git a/net/ipv6/ip6_tunnel.c b/net/ipv6/ip6_tunnel.c index ddd94eca19b3..5cafd92c2312 100644 --- a/net/ipv6/ip6_tunnel.c +++ b/net/ipv6/ip6_tunnel.c @@ -64,12 +64,6 @@ MODULE_LICENSE("GPL"); MODULE_ALIAS_RTNL_LINK("ip6tnl"); MODULE_ALIAS_NETDEV("ip6tnl0"); -#ifdef IP6_TNL_DEBUG -#define IP6_TNL_TRACE(x...) pr_debug("%s:" x "\n", __func__) -#else -#define IP6_TNL_TRACE(x...) do {;} while(0) -#endif - #define HASH_SIZE_SHIFT 5 #define HASH_SIZE (1 << HASH_SIZE_SHIFT) @@ -137,7 +131,7 @@ struct dst_entry *ip6_tnl_dst_check(struct ip6_tnl *t) struct dst_entry *dst = t->dst_cache; if (dst && dst->obsolete && - dst->ops->check(dst, t->dst_cookie) == NULL) { + !dst->ops->check(dst, t->dst_cookie)) { t->dst_cache = NULL; dst_release(dst); return NULL; @@ -331,7 +325,7 @@ static struct ip6_tnl *ip6_tnl_create(struct net *net, struct __ip6_tnl_parm *p) dev = alloc_netdev(sizeof(*t), name, NET_NAME_UNKNOWN, ip6_tnl_dev_setup); - if (dev == NULL) + if (!dev) goto failed; dev_net_set(dev, net); @@ -502,7 +496,7 @@ ip6_tnl_err(struct sk_buff *skb, __u8 ipproto, struct inet6_skb_parm *opt, rcu_read_lock(); t = ip6_tnl_lookup(dev_net(skb->dev), &ipv6h->daddr, &ipv6h->saddr); - if (t == NULL) + if (!t) goto out; tproto = ACCESS_ONCE(t->parms.proto); @@ -813,7 +807,7 @@ static int ip6_tnl_rcv(struct sk_buff *skb, __u16 protocol, rcu_read_lock(); t = ip6_tnl_lookup(dev_net(skb->dev), &ipv6h->saddr, &ipv6h->daddr); - if (t != NULL) { + if (t) { struct pcpu_sw_netstats *tstats; tproto = ACCESS_ONCE(t->parms.proto); @@ -1106,7 +1100,7 @@ static int ip6_tnl_xmit2(struct sk_buff *skb, ipv6h->nexthdr = proto; ipv6h->saddr = fl6->saddr; ipv6h->daddr = fl6->daddr; - ip6tunnel_xmit(skb, dev); + ip6tunnel_xmit(NULL, skb, dev); if (ndst) ip6_tnl_dst_store(t, ndst); return 0; @@ -1270,8 +1264,6 @@ static void ip6_tnl_link_config(struct ip6_tnl *t) else dev->flags &= ~IFF_POINTOPOINT; - dev->iflink = p->link; - if (p->flags & IP6_TNL_F_CAP_XMIT) { int strict = (ipv6_addr_type(&p->raddr) & (IPV6_ADDR_MULTICAST|IPV6_ADDR_LINKLOCAL)); @@ -1280,7 +1272,7 @@ static void ip6_tnl_link_config(struct ip6_tnl *t) &p->raddr, &p->laddr, p->link, strict); - if (rt == NULL) + if (!rt) return; if (rt->dst.dev) { @@ -1523,6 +1515,13 @@ ip6_tnl_change_mtu(struct net_device *dev, int new_mtu) return 0; } +int ip6_tnl_get_iflink(const struct net_device *dev) +{ + struct ip6_tnl *t = netdev_priv(dev); + + return t->parms.link; +} +EXPORT_SYMBOL(ip6_tnl_get_iflink); static const struct net_device_ops ip6_tnl_netdev_ops = { .ndo_init = ip6_tnl_dev_init, @@ -1531,6 +1530,7 @@ static const struct net_device_ops ip6_tnl_netdev_ops = { .ndo_do_ioctl = ip6_tnl_ioctl, .ndo_change_mtu = ip6_tnl_change_mtu, .ndo_get_stats = ip6_get_stats, + .ndo_get_iflink = ip6_tnl_get_iflink, }; @@ -1646,12 +1646,10 @@ static void ip6_tnl_netlink_parms(struct nlattr *data[], parms->link = nla_get_u32(data[IFLA_IPTUN_LINK]); if (data[IFLA_IPTUN_LOCAL]) - nla_memcpy(&parms->laddr, data[IFLA_IPTUN_LOCAL], - sizeof(struct in6_addr)); + parms->laddr = nla_get_in6_addr(data[IFLA_IPTUN_LOCAL]); if (data[IFLA_IPTUN_REMOTE]) - nla_memcpy(&parms->raddr, data[IFLA_IPTUN_REMOTE], - sizeof(struct in6_addr)); + parms->raddr = nla_get_in6_addr(data[IFLA_IPTUN_REMOTE]); if (data[IFLA_IPTUN_TTL]) parms->hop_limit = nla_get_u8(data[IFLA_IPTUN_TTL]); @@ -1745,10 +1743,8 @@ static int ip6_tnl_fill_info(struct sk_buff *skb, const struct net_device *dev) struct __ip6_tnl_parm *parm = &tunnel->parms; if (nla_put_u32(skb, IFLA_IPTUN_LINK, parm->link) || - nla_put(skb, IFLA_IPTUN_LOCAL, sizeof(struct in6_addr), - &parm->laddr) || - nla_put(skb, IFLA_IPTUN_REMOTE, sizeof(struct in6_addr), - &parm->raddr) || + nla_put_in6_addr(skb, IFLA_IPTUN_LOCAL, &parm->laddr) || + nla_put_in6_addr(skb, IFLA_IPTUN_REMOTE, &parm->raddr) || nla_put_u8(skb, IFLA_IPTUN_TTL, parm->hop_limit) || nla_put_u8(skb, IFLA_IPTUN_ENCAP_LIMIT, parm->encap_limit) || nla_put_be32(skb, IFLA_IPTUN_FLOWINFO, parm->flowinfo) || @@ -1821,7 +1817,7 @@ static void __net_exit ip6_tnl_destroy_tunnels(struct net *net) for (h = 0; h < HASH_SIZE; h++) { t = rtnl_dereference(ip6n->tnls_r_l[h]); - while (t != NULL) { + while (t) { /* If dev is in the same netns, it has already * been added to the list by the previous loop. */ diff --git a/net/ipv6/ip6_udp_tunnel.c b/net/ipv6/ip6_udp_tunnel.c index 32d9b268e7d8..bba8903e871f 100644 --- a/net/ipv6/ip6_udp_tunnel.c +++ b/net/ipv6/ip6_udp_tunnel.c @@ -62,7 +62,8 @@ error: } EXPORT_SYMBOL_GPL(udp_sock_create6); -int udp_tunnel6_xmit_skb(struct dst_entry *dst, struct sk_buff *skb, +int udp_tunnel6_xmit_skb(struct dst_entry *dst, struct sock *sk, + struct sk_buff *skb, struct net_device *dev, struct in6_addr *saddr, struct in6_addr *daddr, __u8 prio, __u8 ttl, __be16 src_port, @@ -97,7 +98,7 @@ int udp_tunnel6_xmit_skb(struct dst_entry *dst, struct sk_buff *skb, ip6h->daddr = *daddr; ip6h->saddr = *saddr; - ip6tunnel_xmit(skb, dev); + ip6tunnel_xmit(sk, skb, dev); return 0; } EXPORT_SYMBOL_GPL(udp_tunnel6_xmit_skb); diff --git a/net/ipv6/ip6_vti.c b/net/ipv6/ip6_vti.c index 5fb9e212eca8..ed9d681207fa 100644 --- a/net/ipv6/ip6_vti.c +++ b/net/ipv6/ip6_vti.c @@ -218,7 +218,7 @@ static struct ip6_tnl *vti6_tnl_create(struct net *net, struct __ip6_tnl_parm *p sprintf(name, "ip6_vti%%d"); dev = alloc_netdev(sizeof(*t), name, NET_NAME_UNKNOWN, vti6_dev_setup); - if (dev == NULL) + if (!dev) goto failed; dev_net_set(dev, net); @@ -288,8 +288,7 @@ static struct ip6_tnl *vti6_locate(struct net *net, struct __ip6_tnl_parm *p, static void vti6_dev_uninit(struct net_device *dev) { struct ip6_tnl *t = netdev_priv(dev); - struct net *net = dev_net(dev); - struct vti6_net *ip6n = net_generic(net, vti6_net_id); + struct vti6_net *ip6n = net_generic(t->net, vti6_net_id); if (dev == ip6n->fb_tnl_dev) RCU_INIT_POINTER(ip6n->tnls_wc[0], NULL); @@ -305,7 +304,7 @@ static int vti6_rcv(struct sk_buff *skb) rcu_read_lock(); t = vti6_tnl_lookup(dev_net(skb->dev), &ipv6h->saddr, &ipv6h->daddr); - if (t != NULL) { + if (t) { if (t->parms.proto != IPPROTO_IPV6 && t->parms.proto != 0) { rcu_read_unlock(); goto discard; @@ -601,8 +600,6 @@ static void vti6_link_config(struct ip6_tnl *t) dev->flags |= IFF_POINTOPOINT; else dev->flags &= ~IFF_POINTOPOINT; - - dev->iflink = p->link; } /** @@ -716,7 +713,7 @@ vti6_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd) } else { memset(&p, 0, sizeof(p)); } - if (t == NULL) + if (!t) t = netdev_priv(dev); vti6_parm_to_user(&p, &t->parms); if (copy_to_user(ifr->ifr_ifru.ifru_data, &p, sizeof(p))) @@ -736,7 +733,7 @@ vti6_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd) vti6_parm_from_user(&p1, &p); t = vti6_locate(net, &p1, cmd == SIOCADDTUNNEL); if (dev != ip6n->fb_tnl_dev && cmd == SIOCCHGTUNNEL) { - if (t != NULL) { + if (t) { if (t->dev != dev) { err = -EEXIST; break; @@ -767,7 +764,7 @@ vti6_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd) err = -ENOENT; vti6_parm_from_user(&p1, &p); t = vti6_locate(net, &p1, 0); - if (t == NULL) + if (!t) break; err = -EPERM; if (t->dev == ip6n->fb_tnl_dev) @@ -808,6 +805,7 @@ static const struct net_device_ops vti6_netdev_ops = { .ndo_do_ioctl = vti6_ioctl, .ndo_change_mtu = vti6_change_mtu, .ndo_get_stats64 = ip_tunnel_get_stats64, + .ndo_get_iflink = ip6_tnl_get_iflink, }; /** @@ -897,12 +895,10 @@ static void vti6_netlink_parms(struct nlattr *data[], parms->link = nla_get_u32(data[IFLA_VTI_LINK]); if (data[IFLA_VTI_LOCAL]) - nla_memcpy(&parms->laddr, data[IFLA_VTI_LOCAL], - sizeof(struct in6_addr)); + parms->laddr = nla_get_in6_addr(data[IFLA_VTI_LOCAL]); if (data[IFLA_VTI_REMOTE]) - nla_memcpy(&parms->raddr, data[IFLA_VTI_REMOTE], - sizeof(struct in6_addr)); + parms->raddr = nla_get_in6_addr(data[IFLA_VTI_REMOTE]); if (data[IFLA_VTI_IKEY]) parms->i_key = nla_get_be32(data[IFLA_VTI_IKEY]); @@ -983,10 +979,8 @@ static int vti6_fill_info(struct sk_buff *skb, const struct net_device *dev) struct __ip6_tnl_parm *parm = &tunnel->parms; if (nla_put_u32(skb, IFLA_VTI_LINK, parm->link) || - nla_put(skb, IFLA_VTI_LOCAL, sizeof(struct in6_addr), - &parm->laddr) || - nla_put(skb, IFLA_VTI_REMOTE, sizeof(struct in6_addr), - &parm->raddr) || + nla_put_in6_addr(skb, IFLA_VTI_LOCAL, &parm->laddr) || + nla_put_in6_addr(skb, IFLA_VTI_REMOTE, &parm->raddr) || nla_put_be32(skb, IFLA_VTI_IKEY, parm->i_key) || nla_put_be32(skb, IFLA_VTI_OKEY, parm->o_key)) goto nla_put_failure; @@ -1027,7 +1021,7 @@ static void __net_exit vti6_destroy_tunnels(struct vti6_net *ip6n) for (h = 0; h < HASH_SIZE; h++) { t = rtnl_dereference(ip6n->tnls_r_l[h]); - while (t != NULL) { + while (t) { unregister_netdevice_queue(t->dev, &list); t = rtnl_dereference(t->next); } diff --git a/net/ipv6/ip6mr.c b/net/ipv6/ip6mr.c index 312e0ff47339..74ceb73c1c9a 100644 --- a/net/ipv6/ip6mr.c +++ b/net/ipv6/ip6mr.c @@ -56,9 +56,7 @@ struct mr6_table { struct list_head list; -#ifdef CONFIG_NET_NS - struct net *net; -#endif + possible_net_t net; u32 id; struct sock *mroute6_sk; struct timer_list ipmr_expire_timer; @@ -175,7 +173,7 @@ static int ip6mr_rule_action(struct fib_rule *rule, struct flowi *flp, } mrt = ip6mr_get_table(rule->fr_net, rule->table); - if (mrt == NULL) + if (!mrt) return -EAGAIN; res->mrt = mrt; return 0; @@ -239,7 +237,7 @@ static int __net_init ip6mr_rules_init(struct net *net) INIT_LIST_HEAD(&net->ipv6.mr6_tables); mrt = ip6mr_new_table(net, RT6_TABLE_DFLT); - if (mrt == NULL) { + if (!mrt) { err = -ENOMEM; goto err1; } @@ -307,11 +305,11 @@ static struct mr6_table *ip6mr_new_table(struct net *net, u32 id) unsigned int i; mrt = ip6mr_get_table(net, id); - if (mrt != NULL) + if (mrt) return mrt; mrt = kzalloc(sizeof(*mrt), GFP_KERNEL); - if (mrt == NULL) + if (!mrt) return NULL; mrt->id = id; write_pnet(&mrt->net, net); @@ -410,7 +408,7 @@ static void *ip6mr_vif_seq_start(struct seq_file *seq, loff_t *pos) struct mr6_table *mrt; mrt = ip6mr_get_table(net, RT6_TABLE_DFLT); - if (mrt == NULL) + if (!mrt) return ERR_PTR(-ENOENT); iter->mrt = mrt; @@ -494,7 +492,7 @@ static void *ipmr_mfc_seq_start(struct seq_file *seq, loff_t *pos) struct mr6_table *mrt; mrt = ip6mr_get_table(net, RT6_TABLE_DFLT); - if (mrt == NULL) + if (!mrt) return ERR_PTR(-ENOENT); it->mrt = mrt; @@ -667,7 +665,7 @@ static int pim6_rcv(struct sk_buff *skb) dev_hold(reg_dev); read_unlock(&mrt_lock); - if (reg_dev == NULL) + if (!reg_dev) goto drop; skb->mac_header = skb->network_header; @@ -720,8 +718,14 @@ static netdev_tx_t reg_vif_xmit(struct sk_buff *skb, return NETDEV_TX_OK; } +static int reg_vif_get_iflink(const struct net_device *dev) +{ + return 0; +} + static const struct net_device_ops reg_vif_netdev_ops = { .ndo_start_xmit = reg_vif_xmit, + .ndo_get_iflink = reg_vif_get_iflink, }; static void reg_vif_setup(struct net_device *dev) @@ -745,7 +749,7 @@ static struct net_device *ip6mr_reg_vif(struct net *net, struct mr6_table *mrt) sprintf(name, "pim6reg%u", mrt->id); dev = alloc_netdev(0, name, NET_NAME_UNKNOWN, reg_vif_setup); - if (dev == NULL) + if (!dev) return NULL; dev_net_set(dev, net); @@ -754,7 +758,6 @@ static struct net_device *ip6mr_reg_vif(struct net *net, struct mr6_table *mrt) free_netdev(dev); return NULL; } - dev->iflink = 0; if (dev_open(dev)) goto failure; @@ -994,7 +997,7 @@ static int mif6_add(struct net *net, struct mr6_table *mrt, v->pkt_out = 0; v->link = dev->ifindex; if (v->flags & MIFF_REGISTER) - v->link = dev->iflink; + v->link = dev_get_iflink(dev); /* And finish update writing critical data */ write_lock_bh(&mrt_lock); @@ -1074,7 +1077,7 @@ skip: static struct mfc6_cache *ip6mr_cache_alloc(void) { struct mfc6_cache *c = kmem_cache_zalloc(mrt_cachep, GFP_KERNEL); - if (c == NULL) + if (!c) return NULL; c->mfc_un.res.minvif = MAXMIFS; return c; @@ -1083,7 +1086,7 @@ static struct mfc6_cache *ip6mr_cache_alloc(void) static struct mfc6_cache *ip6mr_cache_alloc_unres(void) { struct mfc6_cache *c = kmem_cache_zalloc(mrt_cachep, GFP_ATOMIC); - if (c == NULL) + if (!c) return NULL; skb_queue_head_init(&c->mfc_un.unres.unresolved); c->mfc_un.unres.expires = jiffies + 10 * HZ; @@ -1200,7 +1203,7 @@ static int ip6mr_cache_report(struct mr6_table *mrt, struct sk_buff *pkt, skb->ip_summed = CHECKSUM_UNNECESSARY; } - if (mrt->mroute6_sk == NULL) { + if (!mrt->mroute6_sk) { kfree_skb(skb); return -EINVAL; } @@ -1495,7 +1498,7 @@ static int ip6mr_mfc_add(struct net *net, struct mr6_table *mrt, return -EINVAL; c = ip6mr_cache_alloc(); - if (c == NULL) + if (!c) return -ENOMEM; c->mf6c_origin = mfc->mf6cc_origin.sin6_addr; @@ -1665,7 +1668,7 @@ int ip6_mroute_setsockopt(struct sock *sk, int optname, char __user *optval, uns struct mr6_table *mrt; mrt = ip6mr_get_table(net, raw6_sk(sk)->ip6mr_table ? : RT6_TABLE_DFLT); - if (mrt == NULL) + if (!mrt) return -ENOENT; if (optname != MRT6_INIT) { @@ -1814,7 +1817,7 @@ int ip6_mroute_getsockopt(struct sock *sk, int optname, char __user *optval, struct mr6_table *mrt; mrt = ip6mr_get_table(net, raw6_sk(sk)->ip6mr_table ? : RT6_TABLE_DFLT); - if (mrt == NULL) + if (!mrt) return -ENOENT; switch (optname) { @@ -1861,7 +1864,7 @@ int ip6mr_ioctl(struct sock *sk, int cmd, void __user *arg) struct mr6_table *mrt; mrt = ip6mr_get_table(net, raw6_sk(sk)->ip6mr_table ? : RT6_TABLE_DFLT); - if (mrt == NULL) + if (!mrt) return -ENOENT; switch (cmd) { @@ -1935,7 +1938,7 @@ int ip6mr_compat_ioctl(struct sock *sk, unsigned int cmd, void __user *arg) struct mr6_table *mrt; mrt = ip6mr_get_table(net, raw6_sk(sk)->ip6mr_table ? : RT6_TABLE_DFLT); - if (mrt == NULL) + if (!mrt) return -ENOENT; switch (cmd) { @@ -1983,13 +1986,13 @@ int ip6mr_compat_ioctl(struct sock *sk, unsigned int cmd, void __user *arg) } #endif -static inline int ip6mr_forward2_finish(struct sk_buff *skb) +static inline int ip6mr_forward2_finish(struct sock *sk, struct sk_buff *skb) { IP6_INC_STATS_BH(dev_net(skb_dst(skb)->dev), ip6_dst_idev(skb_dst(skb)), IPSTATS_MIB_OUTFORWDATAGRAMS); IP6_ADD_STATS_BH(dev_net(skb_dst(skb)->dev), ip6_dst_idev(skb_dst(skb)), IPSTATS_MIB_OUTOCTETS, skb->len); - return dst_output(skb); + return dst_output_sk(sk, skb); } /* @@ -2005,7 +2008,7 @@ static int ip6mr_forward2(struct net *net, struct mr6_table *mrt, struct dst_entry *dst; struct flowi6 fl6; - if (vif->dev == NULL) + if (!vif->dev) goto out_free; #ifdef CONFIG_IPV6_PIMSM_V2 @@ -2061,7 +2064,8 @@ static int ip6mr_forward2(struct net *net, struct mr6_table *mrt, IP6CB(skb)->flags |= IP6SKB_FORWARDED; - return NF_HOOK(NFPROTO_IPV6, NF_INET_FORWARD, skb, skb->dev, dev, + return NF_HOOK(NFPROTO_IPV6, NF_INET_FORWARD, NULL, skb, + skb->dev, dev, ip6mr_forward2_finish); out_free: @@ -2194,7 +2198,7 @@ int ip6_mr_input(struct sk_buff *skb) read_lock(&mrt_lock); cache = ip6mr_cache_find(mrt, &ipv6_hdr(skb)->saddr, &ipv6_hdr(skb)->daddr); - if (cache == NULL) { + if (!cache) { int vif = ip6mr_find_vif(mrt, skb->dev); if (vif >= 0) @@ -2206,7 +2210,7 @@ int ip6_mr_input(struct sk_buff *skb) /* * No usable cache entry */ - if (cache == NULL) { + if (!cache) { int vif; vif = ip6mr_find_vif(mrt, skb->dev); @@ -2245,13 +2249,13 @@ static int __ip6mr_fill_mroute(struct mr6_table *mrt, struct sk_buff *skb, nla_put_u32(skb, RTA_IIF, mrt->vif6_table[c->mf6c_parent].dev->ifindex) < 0) return -EMSGSIZE; mp_attr = nla_nest_start(skb, RTA_MULTIPATH); - if (mp_attr == NULL) + if (!mp_attr) return -EMSGSIZE; for (ct = c->mfc_un.res.minvif; ct < c->mfc_un.res.maxvif; ct++) { if (MIF_EXISTS(mrt, ct) && c->mfc_un.res.ttls[ct] < 255) { nhp = nla_reserve_nohdr(skb, sizeof(*nhp)); - if (nhp == NULL) { + if (!nhp) { nla_nest_cancel(skb, mp_attr); return -EMSGSIZE; } @@ -2284,7 +2288,7 @@ int ip6mr_get_route(struct net *net, struct rt6_info *rt = (struct rt6_info *)skb_dst(skb); mrt = ip6mr_get_table(net, RT6_TABLE_DFLT); - if (mrt == NULL) + if (!mrt) return -ENOENT; read_lock(&mrt_lock); @@ -2309,7 +2313,7 @@ int ip6mr_get_route(struct net *net, } dev = skb->dev; - if (dev == NULL || (vif = ip6mr_find_vif(mrt, dev)) < 0) { + if (!dev || (vif = ip6mr_find_vif(mrt, dev)) < 0) { read_unlock(&mrt_lock); return -ENODEV; } @@ -2361,7 +2365,7 @@ static int ip6mr_fill_mroute(struct mr6_table *mrt, struct sk_buff *skb, int err; nlh = nlmsg_put(skb, portid, seq, cmd, sizeof(*rtm), flags); - if (nlh == NULL) + if (!nlh) return -EMSGSIZE; rtm = nlmsg_data(nlh); @@ -2380,8 +2384,8 @@ static int ip6mr_fill_mroute(struct mr6_table *mrt, struct sk_buff *skb, rtm->rtm_protocol = RTPROT_MROUTED; rtm->rtm_flags = 0; - if (nla_put(skb, RTA_SRC, 16, &c->mf6c_origin) || - nla_put(skb, RTA_DST, 16, &c->mf6c_mcastgrp)) + if (nla_put_in6_addr(skb, RTA_SRC, &c->mf6c_origin) || + nla_put_in6_addr(skb, RTA_DST, &c->mf6c_mcastgrp)) goto nla_put_failure; err = __ip6mr_fill_mroute(mrt, skb, c, rtm); /* do not break the dump if cache is unresolved */ @@ -2426,7 +2430,7 @@ static void mr6_netlink_event(struct mr6_table *mrt, struct mfc6_cache *mfc, skb = nlmsg_new(mr6_msgsize(mfc->mf6c_parent >= MAXMIFS, mrt->maxvif), GFP_ATOMIC); - if (skb == NULL) + if (!skb) goto errout; err = ip6mr_fill_mroute(mrt, skb, 0, 0, mfc, cmd, 0); diff --git a/net/ipv6/ipv6_sockglue.c b/net/ipv6/ipv6_sockglue.c index 8d766d9100cb..63e6956917c9 100644 --- a/net/ipv6/ipv6_sockglue.c +++ b/net/ipv6/ipv6_sockglue.c @@ -85,7 +85,7 @@ int ip6_ra_control(struct sock *sk, int sel) return 0; } } - if (new_ra == NULL) { + if (!new_ra) { write_unlock_bh(&ip6_ra_lock); return -ENOBUFS; } @@ -117,6 +117,25 @@ struct ipv6_txoptions *ipv6_update_options(struct sock *sk, return opt; } +static bool setsockopt_needs_rtnl(int optname) +{ + switch (optname) { + case IPV6_ADD_MEMBERSHIP: + case IPV6_DROP_MEMBERSHIP: + case IPV6_JOIN_ANYCAST: + case IPV6_LEAVE_ANYCAST: + case MCAST_JOIN_GROUP: + case MCAST_LEAVE_GROUP: + case MCAST_JOIN_SOURCE_GROUP: + case MCAST_LEAVE_SOURCE_GROUP: + case MCAST_BLOCK_SOURCE: + case MCAST_UNBLOCK_SOURCE: + case MCAST_MSFILTER: + return true; + } + return false; +} + static int do_ipv6_setsockopt(struct sock *sk, int level, int optname, char __user *optval, unsigned int optlen) { @@ -124,8 +143,9 @@ static int do_ipv6_setsockopt(struct sock *sk, int level, int optname, struct net *net = sock_net(sk); int val, valbool; int retv = -ENOPROTOOPT; + bool needs_rtnl = setsockopt_needs_rtnl(optname); - if (optval == NULL) + if (!optval) val = 0; else { if (optlen >= sizeof(int)) { @@ -140,6 +160,8 @@ static int do_ipv6_setsockopt(struct sock *sk, int level, int optname, if (ip6_mroute_opt(optname)) return ip6_mroute_setsockopt(sk, optname, optval, optlen); + if (needs_rtnl) + rtnl_lock(); lock_sock(sk); switch (optname) { @@ -370,7 +392,7 @@ static int do_ipv6_setsockopt(struct sock *sk, int level, int optname, */ if (optlen == 0) optval = NULL; - else if (optval == NULL) + else if (!optval) goto e_inval; else if (optlen < sizeof(struct ipv6_opt_hdr) || optlen & 0x7 || optlen > 8 * 255) @@ -421,7 +443,7 @@ sticky_done: if (optlen == 0) goto e_inval; - else if (optlen < sizeof(struct in6_pktinfo) || optval == NULL) + else if (optlen < sizeof(struct in6_pktinfo) || !optval) goto e_inval; if (copy_from_user(&pkt, optval, sizeof(struct in6_pktinfo))) { @@ -460,7 +482,7 @@ sticky_done: opt = sock_kmalloc(sk, sizeof(*opt) + optlen, GFP_KERNEL); retv = -ENOBUFS; - if (opt == NULL) + if (!opt) break; memset(opt, 0, sizeof(*opt)); @@ -624,10 +646,10 @@ done: psin6 = (struct sockaddr_in6 *)&greq.gr_group; if (optname == MCAST_JOIN_GROUP) retv = ipv6_sock_mc_join(sk, greq.gr_interface, - &psin6->sin6_addr); + &psin6->sin6_addr); else retv = ipv6_sock_mc_drop(sk, greq.gr_interface, - &psin6->sin6_addr); + &psin6->sin6_addr); break; } case MCAST_JOIN_SOURCE_GROUP: @@ -660,7 +682,7 @@ done: psin6 = (struct sockaddr_in6 *)&greqs.gsr_group; retv = ipv6_sock_mc_join(sk, greqs.gsr_interface, - &psin6->sin6_addr); + &psin6->sin6_addr); /* prior join w/ different source is ok */ if (retv && retv != -EADDRINUSE) break; @@ -837,11 +859,15 @@ pref_skip_coa: } release_sock(sk); + if (needs_rtnl) + rtnl_unlock(); return retv; e_inval: release_sock(sk); + if (needs_rtnl) + rtnl_unlock(); return -EINVAL; } diff --git a/net/ipv6/mcast.c b/net/ipv6/mcast.c index 5ce107c8aab3..083b2927fc67 100644 --- a/net/ipv6/mcast.c +++ b/net/ipv6/mcast.c @@ -140,6 +140,8 @@ int ipv6_sock_mc_join(struct sock *sk, int ifindex, const struct in6_addr *addr) struct net *net = sock_net(sk); int err; + ASSERT_RTNL(); + if (!ipv6_addr_is_multicast(addr)) return -EINVAL; @@ -155,13 +157,12 @@ int ipv6_sock_mc_join(struct sock *sk, int ifindex, const struct in6_addr *addr) mc_lst = sock_kmalloc(sk, sizeof(struct ipv6_mc_socklist), GFP_KERNEL); - if (mc_lst == NULL) + if (!mc_lst) return -ENOMEM; mc_lst->next = NULL; mc_lst->addr = *addr; - rtnl_lock(); if (ifindex == 0) { struct rt6_info *rt; rt = rt6_lookup(net, addr, NULL, 0, 0); @@ -172,8 +173,7 @@ int ipv6_sock_mc_join(struct sock *sk, int ifindex, const struct in6_addr *addr) } else dev = __dev_get_by_index(net, ifindex); - if (dev == NULL) { - rtnl_unlock(); + if (!dev) { sock_kfree_s(sk, mc_lst, sizeof(*mc_lst)); return -ENODEV; } @@ -190,7 +190,6 @@ int ipv6_sock_mc_join(struct sock *sk, int ifindex, const struct in6_addr *addr) err = ipv6_dev_mc_inc(dev, addr); if (err) { - rtnl_unlock(); sock_kfree_s(sk, mc_lst, sizeof(*mc_lst)); return err; } @@ -198,10 +197,9 @@ int ipv6_sock_mc_join(struct sock *sk, int ifindex, const struct in6_addr *addr) mc_lst->next = np->ipv6_mc_list; rcu_assign_pointer(np->ipv6_mc_list, mc_lst); - rtnl_unlock(); - return 0; } +EXPORT_SYMBOL(ipv6_sock_mc_join); /* * socket leave on multicast group @@ -213,10 +211,11 @@ int ipv6_sock_mc_drop(struct sock *sk, int ifindex, const struct in6_addr *addr) struct ipv6_mc_socklist __rcu **lnk; struct net *net = sock_net(sk); + ASSERT_RTNL(); + if (!ipv6_addr_is_multicast(addr)) return -EINVAL; - rtnl_lock(); for (lnk = &np->ipv6_mc_list; (mc_lst = rtnl_dereference(*lnk)) != NULL; lnk = &mc_lst->next) { @@ -227,7 +226,7 @@ int ipv6_sock_mc_drop(struct sock *sk, int ifindex, const struct in6_addr *addr) *lnk = mc_lst->next; dev = __dev_get_by_index(net, mc_lst->ifindex); - if (dev != NULL) { + if (dev) { struct inet6_dev *idev = __in6_dev_get(dev); (void) ip6_mc_leave_src(sk, mc_lst, idev); @@ -235,17 +234,16 @@ int ipv6_sock_mc_drop(struct sock *sk, int ifindex, const struct in6_addr *addr) __ipv6_dev_mc_dec(idev, &mc_lst->addr); } else (void) ip6_mc_leave_src(sk, mc_lst, NULL); - rtnl_unlock(); atomic_sub(sizeof(*mc_lst), &sk->sk_omem_alloc); kfree_rcu(mc_lst, rcu); return 0; } } - rtnl_unlock(); return -EADDRNOTAVAIL; } +EXPORT_SYMBOL(ipv6_sock_mc_drop); /* called with rcu_read_lock() */ static struct inet6_dev *ip6_mc_find_dev_rcu(struct net *net, @@ -438,7 +436,7 @@ done: read_unlock_bh(&idev->lock); rcu_read_unlock(); if (leavegroup) - return ipv6_sock_mc_drop(sk, pgsr->gsr_interface, group); + err = ipv6_sock_mc_drop(sk, pgsr->gsr_interface, group); return err; } @@ -825,7 +823,7 @@ static struct ifmcaddr6 *mca_alloc(struct inet6_dev *idev, struct ifmcaddr6 *mc; mc = kzalloc(sizeof(*mc), GFP_ATOMIC); - if (mc == NULL) + if (!mc) return NULL; setup_timer(&mc->mca_timer, igmp6_timer_handler, (unsigned long)mc); @@ -862,7 +860,7 @@ int ipv6_dev_mc_inc(struct net_device *dev, const struct in6_addr *addr) /* we need to take a reference on idev */ idev = in6_dev_get(dev); - if (idev == NULL) + if (!idev) return -EINVAL; write_lock_bh(&idev->lock); @@ -1330,7 +1328,7 @@ int igmp6_event_query(struct sk_buff *skb) return -EINVAL; idev = __in6_dev_get(skb->dev); - if (idev == NULL) + if (!idev) return 0; mld = (struct mld_msg *)icmp6_hdr(skb); @@ -1445,7 +1443,7 @@ int igmp6_event_report(struct sk_buff *skb) return -EINVAL; idev = __in6_dev_get(skb->dev); - if (idev == NULL) + if (!idev) return -ENODEV; /* @@ -1646,8 +1644,9 @@ static void mld_sendpack(struct sk_buff *skb) payload_len = skb->len; - err = NF_HOOK(NFPROTO_IPV6, NF_INET_LOCAL_OUT, skb, NULL, skb->dev, - dst_output); + err = NF_HOOK(NFPROTO_IPV6, NF_INET_LOCAL_OUT, + net->ipv6.igmp_sk, skb, NULL, skb->dev, + dst_output_sk); out: if (!err) { ICMP6MSGOUT_INC_STATS(net, idev, ICMPV6_MLD2_REPORT); @@ -1964,7 +1963,7 @@ static void igmp6_send(struct in6_addr *addr, struct net_device *dev, int type) skb = sock_alloc_send_skb(sk, hlen + tlen + full_len, 1, &err); - if (skb == NULL) { + if (!skb) { rcu_read_lock(); IP6_INC_STATS(net, __in6_dev_get(dev), IPSTATS_MIB_OUTDISCARDS); @@ -2009,8 +2008,8 @@ static void igmp6_send(struct in6_addr *addr, struct net_device *dev, int type) } skb_dst_set(skb, dst); - err = NF_HOOK(NFPROTO_IPV6, NF_INET_LOCAL_OUT, skb, NULL, skb->dev, - dst_output); + err = NF_HOOK(NFPROTO_IPV6, NF_INET_LOCAL_OUT, sk, skb, + NULL, skb->dev, dst_output_sk); out: if (!err) { ICMP6MSGOUT_INC_STATS(net, idev, type); @@ -2613,7 +2612,7 @@ static struct ifmcaddr6 *igmp6_mc_get_next(struct seq_file *seq, struct ifmcaddr im = im->next; while (!im) { - if (likely(state->idev != NULL)) + if (likely(state->idev)) read_unlock_bh(&state->idev->lock); state->dev = next_net_device_rcu(state->dev); @@ -2659,7 +2658,7 @@ static void igmp6_mc_seq_stop(struct seq_file *seq, void *v) { struct igmp6_mc_iter_state *state = igmp6_mc_seq_private(seq); - if (likely(state->idev != NULL)) { + if (likely(state->idev)) { read_unlock_bh(&state->idev->lock); state->idev = NULL; } @@ -2728,10 +2727,10 @@ static inline struct ip6_sf_list *igmp6_mcf_get_first(struct seq_file *seq) continue; read_lock_bh(&idev->lock); im = idev->mc_list; - if (likely(im != NULL)) { + if (likely(im)) { spin_lock_bh(&im->mca_lock); psf = im->mca_sources; - if (likely(psf != NULL)) { + if (likely(psf)) { state->im = im; state->idev = idev; break; @@ -2752,7 +2751,7 @@ static struct ip6_sf_list *igmp6_mcf_get_next(struct seq_file *seq, struct ip6_s spin_unlock_bh(&state->im->mca_lock); state->im = state->im->next; while (!state->im) { - if (likely(state->idev != NULL)) + if (likely(state->idev)) read_unlock_bh(&state->idev->lock); state->dev = next_net_device_rcu(state->dev); @@ -2806,11 +2805,11 @@ static void igmp6_mcf_seq_stop(struct seq_file *seq, void *v) __releases(RCU) { struct igmp6_mcf_iter_state *state = igmp6_mcf_seq_private(seq); - if (likely(state->im != NULL)) { + if (likely(state->im)) { spin_unlock_bh(&state->im->mca_lock); state->im = NULL; } - if (likely(state->idev != NULL)) { + if (likely(state->idev)) { read_unlock_bh(&state->idev->lock); state->idev = NULL; } @@ -2907,20 +2906,32 @@ static int __net_init igmp6_net_init(struct net *net) inet6_sk(net->ipv6.igmp_sk)->hop_limit = 1; + err = inet_ctl_sock_create(&net->ipv6.mc_autojoin_sk, PF_INET6, + SOCK_RAW, IPPROTO_ICMPV6, net); + if (err < 0) { + pr_err("Failed to initialize the IGMP6 autojoin socket (err %d)\n", + err); + goto out_sock_create; + } + err = igmp6_proc_init(net); if (err) - goto out_sock_create; -out: - return err; + goto out_sock_create_autojoin; + + return 0; +out_sock_create_autojoin: + inet_ctl_sock_destroy(net->ipv6.mc_autojoin_sk); out_sock_create: inet_ctl_sock_destroy(net->ipv6.igmp_sk); - goto out; +out: + return err; } static void __net_exit igmp6_net_exit(struct net *net) { inet_ctl_sock_destroy(net->ipv6.igmp_sk); + inet_ctl_sock_destroy(net->ipv6.mc_autojoin_sk); igmp6_proc_exit(net); } diff --git a/net/ipv6/ndisc.c b/net/ipv6/ndisc.c index 14ecdaf06bf7..96f153c0846b 100644 --- a/net/ipv6/ndisc.c +++ b/net/ipv6/ndisc.c @@ -84,6 +84,7 @@ do { \ static u32 ndisc_hash(const void *pkey, const struct net_device *dev, __u32 *hash_rnd); +static bool ndisc_key_eq(const struct neighbour *neigh, const void *pkey); static int ndisc_constructor(struct neighbour *neigh); static void ndisc_solicit(struct neighbour *neigh, struct sk_buff *skb); static void ndisc_error_report(struct neighbour *neigh, struct sk_buff *skb); @@ -117,7 +118,9 @@ static const struct neigh_ops ndisc_direct_ops = { struct neigh_table nd_tbl = { .family = AF_INET6, .key_len = sizeof(struct in6_addr), + .protocol = cpu_to_be16(ETH_P_IPV6), .hash = ndisc_hash, + .key_eq = ndisc_key_eq, .constructor = ndisc_constructor, .pconstructor = pndisc_constructor, .pdestructor = pndisc_destructor, @@ -294,6 +297,11 @@ static u32 ndisc_hash(const void *pkey, return ndisc_hashfn(pkey, dev, hash_rnd); } +static bool ndisc_key_eq(const struct neighbour *n, const void *pkey) +{ + return neigh_key_eq128(n, pkey); +} + static int ndisc_constructor(struct neighbour *neigh) { struct in6_addr *addr = (struct in6_addr *)&neigh->primary_key; @@ -303,7 +311,7 @@ static int ndisc_constructor(struct neighbour *neigh) bool is_multicast = ipv6_addr_is_multicast(addr); in6_dev = in6_dev_get(dev); - if (in6_dev == NULL) { + if (!in6_dev) { return -EINVAL; } @@ -348,7 +356,7 @@ static int pndisc_constructor(struct pneigh_entry *n) struct in6_addr maddr; struct net_device *dev = n->dev; - if (dev == NULL || __in6_dev_get(dev) == NULL) + if (!dev || !__in6_dev_get(dev)) return -EINVAL; addrconf_addr_solict_mult(addr, &maddr); ipv6_dev_mc_inc(dev, &maddr); @@ -361,7 +369,7 @@ static void pndisc_destructor(struct pneigh_entry *n) struct in6_addr maddr; struct net_device *dev = n->dev; - if (dev == NULL || __in6_dev_get(dev) == NULL) + if (!dev || !__in6_dev_get(dev)) return; addrconf_addr_solict_mult(addr, &maddr); ipv6_dev_mc_dec(dev, &maddr); @@ -455,8 +463,9 @@ static void ndisc_send_skb(struct sk_buff *skb, idev = __in6_dev_get(dst->dev); IP6_UPD_PO_STATS(net, idev, IPSTATS_MIB_OUT, skb->len); - err = NF_HOOK(NFPROTO_IPV6, NF_INET_LOCAL_OUT, skb, NULL, dst->dev, - dst_output); + err = NF_HOOK(NFPROTO_IPV6, NF_INET_LOCAL_OUT, sk, skb, + NULL, dst->dev, + dst_output_sk); if (!err) { ICMP6MSGOUT_INC_STATS(net, idev, type); ICMP6_INC_STATS(net, idev, ICMP6_MIB_OUTMSGS); @@ -552,7 +561,7 @@ void ndisc_send_ns(struct net_device *dev, struct neighbour *neigh, int optlen = 0; struct nd_msg *msg; - if (saddr == NULL) { + if (!saddr) { if (ipv6_get_lladdr(dev, &addr_buf, (IFA_F_TENTATIVE|IFA_F_OPTIMISTIC))) return; @@ -1022,13 +1031,13 @@ static void ndisc_ra_useropt(struct sk_buff *ra, struct nd_opt_hdr *opt) size_t msg_size = base_size + nla_total_size(sizeof(struct in6_addr)); skb = nlmsg_new(msg_size, GFP_ATOMIC); - if (skb == NULL) { + if (!skb) { err = -ENOBUFS; goto errout; } nlh = nlmsg_put(skb, 0, 0, RTM_NEWNDUSEROPT, base_size, 0); - if (nlh == NULL) { + if (!nlh) { goto nla_put_failure; } @@ -1041,8 +1050,7 @@ static void ndisc_ra_useropt(struct sk_buff *ra, struct nd_opt_hdr *opt) memcpy(ndmsg + 1, opt, opt->nd_opt_len << 3); - if (nla_put(skb, NDUSEROPT_SRCADDR, sizeof(struct in6_addr), - &ipv6_hdr(ra)->saddr)) + if (nla_put_in6_addr(skb, NDUSEROPT_SRCADDR, &ipv6_hdr(ra)->saddr)) goto nla_put_failure; nlmsg_end(skb, nlh); @@ -1096,7 +1104,7 @@ static void ndisc_router_discovery(struct sk_buff *skb) */ in6_dev = __in6_dev_get(skb->dev); - if (in6_dev == NULL) { + if (!in6_dev) { ND_PRINTK(0, err, "RA: can't find inet6 device for %s\n", skb->dev->name); return; @@ -1191,11 +1199,11 @@ static void ndisc_router_discovery(struct sk_buff *skb) ND_PRINTK(3, info, "RA: rt: %p lifetime: %d, for dev: %s\n", rt, lifetime, skb->dev->name); - if (rt == NULL && lifetime) { + if (!rt && lifetime) { ND_PRINTK(3, info, "RA: adding default router\n"); rt = rt6_add_dflt_router(&ipv6_hdr(skb)->saddr, skb->dev, pref); - if (rt == NULL) { + if (!rt) { ND_PRINTK(0, err, "RA: %s failed to add default route\n", __func__); @@ -1203,7 +1211,7 @@ static void ndisc_router_discovery(struct sk_buff *skb) } neigh = dst_neigh_lookup(&rt->dst, &ipv6_hdr(skb)->saddr); - if (neigh == NULL) { + if (!neigh) { ND_PRINTK(0, err, "RA: %s got default router without neighbour\n", __func__); diff --git a/net/ipv6/netfilter.c b/net/ipv6/netfilter.c index 398377a9d018..d958718b5031 100644 --- a/net/ipv6/netfilter.c +++ b/net/ipv6/netfilter.c @@ -84,7 +84,7 @@ static void nf_ip6_saveroute(const struct sk_buff *skb, { struct ip6_rt_info *rt_info = nf_queue_entry_reroute(entry); - if (entry->hook == NF_INET_LOCAL_OUT) { + if (entry->state.hook == NF_INET_LOCAL_OUT) { const struct ipv6hdr *iph = ipv6_hdr(skb); rt_info->daddr = iph->daddr; @@ -98,7 +98,7 @@ static int nf_ip6_reroute(struct sk_buff *skb, { struct ip6_rt_info *rt_info = nf_queue_entry_reroute(entry); - if (entry->hook == NF_INET_LOCAL_OUT) { + if (entry->state.hook == NF_INET_LOCAL_OUT) { const struct ipv6hdr *iph = ipv6_hdr(skb); if (!ipv6_addr_equal(&iph->daddr, &rt_info->daddr) || !ipv6_addr_equal(&iph->saddr, &rt_info->saddr) || diff --git a/net/ipv6/netfilter/Kconfig b/net/ipv6/netfilter/Kconfig index a069822936e6..ca6998345b42 100644 --- a/net/ipv6/netfilter/Kconfig +++ b/net/ipv6/netfilter/Kconfig @@ -25,14 +25,16 @@ config NF_CONNTRACK_IPV6 To compile it as a module, choose M here. If unsure, say N. +if NF_TABLES + config NF_TABLES_IPV6 - depends on NF_TABLES tristate "IPv6 nf_tables support" help This option enables the IPv6 support for nf_tables. +if NF_TABLES_IPV6 + config NFT_CHAIN_ROUTE_IPV6 - depends on NF_TABLES_IPV6 tristate "IPv6 nf_tables route chain support" help This option enables the "route" chain for IPv6 in nf_tables. This @@ -40,16 +42,18 @@ config NFT_CHAIN_ROUTE_IPV6 fields such as the source, destination, flowlabel, hop-limit and the packet mark. -config NF_REJECT_IPV6 - tristate "IPv6 packet rejection" - default m if NETFILTER_ADVANCED=n - config NFT_REJECT_IPV6 - depends on NF_TABLES_IPV6 select NF_REJECT_IPV6 default NFT_REJECT tristate +endif # NF_TABLES_IPV6 +endif # NF_TABLES + +config NF_REJECT_IPV6 + tristate "IPv6 packet rejection" + default m if NETFILTER_ADVANCED=n + config NF_LOG_IPV6 tristate "IPv6 packet logging" default m if NETFILTER_ADVANCED=n diff --git a/net/ipv6/netfilter/ip6_tables.c b/net/ipv6/netfilter/ip6_tables.c index bb00c6f2a885..1a732a1d3c8e 100644 --- a/net/ipv6/netfilter/ip6_tables.c +++ b/net/ipv6/netfilter/ip6_tables.c @@ -9,7 +9,10 @@ * it under the terms of the GNU General Public License version 2 as * published by the Free Software Foundation. */ + #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt + +#include <linux/kernel.h> #include <linux/capability.h> #include <linux/in.h> #include <linux/skbuff.h> @@ -234,7 +237,7 @@ static struct nf_loginfo trace_loginfo = { .type = NF_LOG_TYPE_LOG, .u = { .log = { - .level = 4, + .level = LOGLEVEL_WARNING, .logflags = NF_LOG_MASK, }, }, @@ -314,8 +317,7 @@ ip6t_next_entry(const struct ip6t_entry *entry) unsigned int ip6t_do_table(struct sk_buff *skb, unsigned int hook, - const struct net_device *in, - const struct net_device *out, + const struct nf_hook_state *state, struct xt_table *table) { static const char nulldevname[IFNAMSIZ] __attribute__((aligned(sizeof(long)))); @@ -330,8 +332,8 @@ ip6t_do_table(struct sk_buff *skb, unsigned int addend; /* Initialization */ - indev = in ? in->name : nulldevname; - outdev = out ? out->name : nulldevname; + indev = state->in ? state->in->name : nulldevname; + outdev = state->out ? state->out->name : nulldevname; /* We handle fragments by dealing with the first fragment as * if it was a normal packet. All other fragments are treated * normally, except that they will NEVER match rules that ask @@ -339,8 +341,8 @@ ip6t_do_table(struct sk_buff *skb, * rule is also a fragment-specific rule, non-fragments won't * match it. */ acpar.hotdrop = false; - acpar.in = in; - acpar.out = out; + acpar.in = state->in; + acpar.out = state->out; acpar.family = NFPROTO_IPV6; acpar.hooknum = hook; @@ -390,7 +392,7 @@ ip6t_do_table(struct sk_buff *skb, #if IS_ENABLED(CONFIG_NETFILTER_XT_TARGET_TRACE) /* The packet is traced: log it */ if (unlikely(skb->nf_trace)) - trace_packet(skb, hook, in, out, + trace_packet(skb, hook, state->in, state->out, table->name, private, e); #endif /* Standard target? */ diff --git a/net/ipv6/netfilter/ip6t_REJECT.c b/net/ipv6/netfilter/ip6t_REJECT.c index 544b0a9da1b5..12331efd49cf 100644 --- a/net/ipv6/netfilter/ip6t_REJECT.c +++ b/net/ipv6/netfilter/ip6t_REJECT.c @@ -83,7 +83,8 @@ static int reject_tg6_check(const struct xt_tgchk_param *par) return -EINVAL; } else if (rejinfo->with == IP6T_TCP_RESET) { /* Must specify that it's a TCP packet */ - if (e->ipv6.proto != IPPROTO_TCP || + if (!(e->ipv6.flags & IP6T_F_PROTO) || + e->ipv6.proto != IPPROTO_TCP || (e->ipv6.invflags & XT_INV_PROTO)) { pr_info("TCP_RESET illegal for non-tcp\n"); return -EINVAL; diff --git a/net/ipv6/netfilter/ip6t_SYNPROXY.c b/net/ipv6/netfilter/ip6t_SYNPROXY.c index a0d17270117c..6edb7b106de7 100644 --- a/net/ipv6/netfilter/ip6t_SYNPROXY.c +++ b/net/ipv6/netfilter/ip6t_SYNPROXY.c @@ -315,11 +315,9 @@ synproxy_tg6(struct sk_buff *skb, const struct xt_action_param *par) static unsigned int ipv6_synproxy_hook(const struct nf_hook_ops *ops, struct sk_buff *skb, - const struct net_device *in, - const struct net_device *out, - int (*okfn)(struct sk_buff *)) + const struct nf_hook_state *nhs) { - struct synproxy_net *snet = synproxy_pernet(dev_net(in ? : out)); + struct synproxy_net *snet = synproxy_pernet(dev_net(nhs->in ? : nhs->out)); enum ip_conntrack_info ctinfo; struct nf_conn *ct; struct nf_conn_synproxy *synproxy; diff --git a/net/ipv6/netfilter/ip6table_filter.c b/net/ipv6/netfilter/ip6table_filter.c index ca7f6c128086..5c33d8abc077 100644 --- a/net/ipv6/netfilter/ip6table_filter.c +++ b/net/ipv6/netfilter/ip6table_filter.c @@ -33,13 +33,11 @@ static const struct xt_table packet_filter = { /* The work comes in here from netfilter.c. */ static unsigned int ip6table_filter_hook(const struct nf_hook_ops *ops, struct sk_buff *skb, - const struct net_device *in, const struct net_device *out, - int (*okfn)(struct sk_buff *)) + const struct nf_hook_state *state) { - const struct net *net = dev_net((in != NULL) ? in : out); + const struct net *net = dev_net(state->in ? state->in : state->out); - return ip6t_do_table(skb, ops->hooknum, in, out, - net->ipv6.ip6table_filter); + return ip6t_do_table(skb, ops->hooknum, state, net->ipv6.ip6table_filter); } static struct nf_hook_ops *filter_ops __read_mostly; diff --git a/net/ipv6/netfilter/ip6table_mangle.c b/net/ipv6/netfilter/ip6table_mangle.c index 307bbb782d14..b551f5b79fe2 100644 --- a/net/ipv6/netfilter/ip6table_mangle.c +++ b/net/ipv6/netfilter/ip6table_mangle.c @@ -32,7 +32,7 @@ static const struct xt_table packet_mangler = { }; static unsigned int -ip6t_mangle_out(struct sk_buff *skb, const struct net_device *out) +ip6t_mangle_out(struct sk_buff *skb, const struct nf_hook_state *state) { unsigned int ret; struct in6_addr saddr, daddr; @@ -57,8 +57,8 @@ ip6t_mangle_out(struct sk_buff *skb, const struct net_device *out) /* flowlabel and prio (includes version, which shouldn't change either */ flowlabel = *((u_int32_t *)ipv6_hdr(skb)); - ret = ip6t_do_table(skb, NF_INET_LOCAL_OUT, NULL, out, - dev_net(out)->ipv6.ip6table_mangle); + ret = ip6t_do_table(skb, NF_INET_LOCAL_OUT, state, + dev_net(state->out)->ipv6.ip6table_mangle); if (ret != NF_DROP && ret != NF_STOLEN && (!ipv6_addr_equal(&ipv6_hdr(skb)->saddr, &saddr) || @@ -77,17 +77,16 @@ ip6t_mangle_out(struct sk_buff *skb, const struct net_device *out) /* The work comes in here from netfilter.c. */ static unsigned int ip6table_mangle_hook(const struct nf_hook_ops *ops, struct sk_buff *skb, - const struct net_device *in, const struct net_device *out, - int (*okfn)(struct sk_buff *)) + const struct nf_hook_state *state) { if (ops->hooknum == NF_INET_LOCAL_OUT) - return ip6t_mangle_out(skb, out); + return ip6t_mangle_out(skb, state); if (ops->hooknum == NF_INET_POST_ROUTING) - return ip6t_do_table(skb, ops->hooknum, in, out, - dev_net(out)->ipv6.ip6table_mangle); + return ip6t_do_table(skb, ops->hooknum, state, + dev_net(state->out)->ipv6.ip6table_mangle); /* INPUT/FORWARD */ - return ip6t_do_table(skb, ops->hooknum, in, out, - dev_net(in)->ipv6.ip6table_mangle); + return ip6t_do_table(skb, ops->hooknum, state, + dev_net(state->in)->ipv6.ip6table_mangle); } static struct nf_hook_ops *mangle_ops __read_mostly; diff --git a/net/ipv6/netfilter/ip6table_nat.c b/net/ipv6/netfilter/ip6table_nat.c index b0634ac996b7..c3a7f7af0ed4 100644 --- a/net/ipv6/netfilter/ip6table_nat.c +++ b/net/ipv6/netfilter/ip6table_nat.c @@ -32,49 +32,40 @@ static const struct xt_table nf_nat_ipv6_table = { static unsigned int ip6table_nat_do_chain(const struct nf_hook_ops *ops, struct sk_buff *skb, - const struct net_device *in, - const struct net_device *out, + const struct nf_hook_state *state, struct nf_conn *ct) { struct net *net = nf_ct_net(ct); - return ip6t_do_table(skb, ops->hooknum, in, out, net->ipv6.ip6table_nat); + return ip6t_do_table(skb, ops->hooknum, state, net->ipv6.ip6table_nat); } static unsigned int ip6table_nat_fn(const struct nf_hook_ops *ops, struct sk_buff *skb, - const struct net_device *in, - const struct net_device *out, - int (*okfn)(struct sk_buff *)) + const struct nf_hook_state *state) { - return nf_nat_ipv6_fn(ops, skb, in, out, ip6table_nat_do_chain); + return nf_nat_ipv6_fn(ops, skb, state, ip6table_nat_do_chain); } static unsigned int ip6table_nat_in(const struct nf_hook_ops *ops, struct sk_buff *skb, - const struct net_device *in, - const struct net_device *out, - int (*okfn)(struct sk_buff *)) + const struct nf_hook_state *state) { - return nf_nat_ipv6_in(ops, skb, in, out, ip6table_nat_do_chain); + return nf_nat_ipv6_in(ops, skb, state, ip6table_nat_do_chain); } static unsigned int ip6table_nat_out(const struct nf_hook_ops *ops, struct sk_buff *skb, - const struct net_device *in, - const struct net_device *out, - int (*okfn)(struct sk_buff *)) + const struct nf_hook_state *state) { - return nf_nat_ipv6_out(ops, skb, in, out, ip6table_nat_do_chain); + return nf_nat_ipv6_out(ops, skb, state, ip6table_nat_do_chain); } static unsigned int ip6table_nat_local_fn(const struct nf_hook_ops *ops, struct sk_buff *skb, - const struct net_device *in, - const struct net_device *out, - int (*okfn)(struct sk_buff *)) + const struct nf_hook_state *state) { - return nf_nat_ipv6_local_fn(ops, skb, in, out, ip6table_nat_do_chain); + return nf_nat_ipv6_local_fn(ops, skb, state, ip6table_nat_do_chain); } static struct nf_hook_ops nf_nat_ipv6_ops[] __read_mostly = { diff --git a/net/ipv6/netfilter/ip6table_raw.c b/net/ipv6/netfilter/ip6table_raw.c index 5274740acecc..0b33caad2b69 100644 --- a/net/ipv6/netfilter/ip6table_raw.c +++ b/net/ipv6/netfilter/ip6table_raw.c @@ -20,13 +20,11 @@ static const struct xt_table packet_raw = { /* The work comes in here from netfilter.c. */ static unsigned int ip6table_raw_hook(const struct nf_hook_ops *ops, struct sk_buff *skb, - const struct net_device *in, const struct net_device *out, - int (*okfn)(struct sk_buff *)) + const struct nf_hook_state *state) { - const struct net *net = dev_net((in != NULL) ? in : out); + const struct net *net = dev_net(state->in ? state->in : state->out); - return ip6t_do_table(skb, ops->hooknum, in, out, - net->ipv6.ip6table_raw); + return ip6t_do_table(skb, ops->hooknum, state, net->ipv6.ip6table_raw); } static struct nf_hook_ops *rawtable_ops __read_mostly; diff --git a/net/ipv6/netfilter/ip6table_security.c b/net/ipv6/netfilter/ip6table_security.c index ab3b0219ecfa..fcef83c25f7b 100644 --- a/net/ipv6/netfilter/ip6table_security.c +++ b/net/ipv6/netfilter/ip6table_security.c @@ -37,13 +37,11 @@ static const struct xt_table security_table = { static unsigned int ip6table_security_hook(const struct nf_hook_ops *ops, struct sk_buff *skb, - const struct net_device *in, - const struct net_device *out, - int (*okfn)(struct sk_buff *)) + const struct nf_hook_state *state) { - const struct net *net = dev_net((in != NULL) ? in : out); + const struct net *net = dev_net(state->in ? state->in : state->out); - return ip6t_do_table(skb, ops->hooknum, in, out, + return ip6t_do_table(skb, ops->hooknum, state, net->ipv6.ip6table_security); } diff --git a/net/ipv6/netfilter/nf_conntrack_l3proto_ipv6.c b/net/ipv6/netfilter/nf_conntrack_l3proto_ipv6.c index b68d0e59c1f8..4ba0c34c627b 100644 --- a/net/ipv6/netfilter/nf_conntrack_l3proto_ipv6.c +++ b/net/ipv6/netfilter/nf_conntrack_l3proto_ipv6.c @@ -97,9 +97,7 @@ static int ipv6_get_l4proto(const struct sk_buff *skb, unsigned int nhoff, static unsigned int ipv6_helper(const struct nf_hook_ops *ops, struct sk_buff *skb, - const struct net_device *in, - const struct net_device *out, - int (*okfn)(struct sk_buff *)) + const struct nf_hook_state *state) { struct nf_conn *ct; const struct nf_conn_help *help; @@ -135,9 +133,7 @@ static unsigned int ipv6_helper(const struct nf_hook_ops *ops, static unsigned int ipv6_confirm(const struct nf_hook_ops *ops, struct sk_buff *skb, - const struct net_device *in, - const struct net_device *out, - int (*okfn)(struct sk_buff *)) + const struct nf_hook_state *state) { struct nf_conn *ct; enum ip_conntrack_info ctinfo; @@ -171,25 +167,21 @@ out: static unsigned int ipv6_conntrack_in(const struct nf_hook_ops *ops, struct sk_buff *skb, - const struct net_device *in, - const struct net_device *out, - int (*okfn)(struct sk_buff *)) + const struct nf_hook_state *state) { - return nf_conntrack_in(dev_net(in), PF_INET6, ops->hooknum, skb); + return nf_conntrack_in(dev_net(state->in), PF_INET6, ops->hooknum, skb); } static unsigned int ipv6_conntrack_local(const struct nf_hook_ops *ops, struct sk_buff *skb, - const struct net_device *in, - const struct net_device *out, - int (*okfn)(struct sk_buff *)) + const struct nf_hook_state *state) { /* root is playing with raw sockets. */ if (skb->len < sizeof(struct ipv6hdr)) { net_notice_ratelimited("ipv6_conntrack_local: packet too short\n"); return NF_ACCEPT; } - return nf_conntrack_in(dev_net(out), PF_INET6, ops->hooknum, skb); + return nf_conntrack_in(dev_net(state->out), PF_INET6, ops->hooknum, skb); } static struct nf_hook_ops ipv6_conntrack_ops[] __read_mostly = { @@ -290,10 +282,8 @@ ipv6_getorigdst(struct sock *sk, int optval, void __user *user, int *len) static int ipv6_tuple_to_nlattr(struct sk_buff *skb, const struct nf_conntrack_tuple *tuple) { - if (nla_put(skb, CTA_IP_V6_SRC, sizeof(u_int32_t) * 4, - &tuple->src.u3.ip6) || - nla_put(skb, CTA_IP_V6_DST, sizeof(u_int32_t) * 4, - &tuple->dst.u3.ip6)) + if (nla_put_in6_addr(skb, CTA_IP_V6_SRC, &tuple->src.u3.in6) || + nla_put_in6_addr(skb, CTA_IP_V6_DST, &tuple->dst.u3.in6)) goto nla_put_failure; return 0; @@ -312,10 +302,8 @@ static int ipv6_nlattr_to_tuple(struct nlattr *tb[], if (!tb[CTA_IP_V6_SRC] || !tb[CTA_IP_V6_DST]) return -EINVAL; - memcpy(&t->src.u3.ip6, nla_data(tb[CTA_IP_V6_SRC]), - sizeof(u_int32_t) * 4); - memcpy(&t->dst.u3.ip6, nla_data(tb[CTA_IP_V6_DST]), - sizeof(u_int32_t) * 4); + t->src.u3.in6 = nla_get_in6_addr(tb[CTA_IP_V6_SRC]); + t->dst.u3.in6 = nla_get_in6_addr(tb[CTA_IP_V6_DST]); return 0; } diff --git a/net/ipv6/netfilter/nf_defrag_ipv6_hooks.c b/net/ipv6/netfilter/nf_defrag_ipv6_hooks.c index e70382e4dfb5..a45db0b4785c 100644 --- a/net/ipv6/netfilter/nf_defrag_ipv6_hooks.c +++ b/net/ipv6/netfilter/nf_defrag_ipv6_hooks.c @@ -54,9 +54,7 @@ static enum ip6_defrag_users nf_ct6_defrag_user(unsigned int hooknum, static unsigned int ipv6_defrag(const struct nf_hook_ops *ops, struct sk_buff *skb, - const struct net_device *in, - const struct net_device *out, - int (*okfn)(struct sk_buff *)) + const struct nf_hook_state *state) { struct sk_buff *reasm; @@ -77,9 +75,9 @@ static unsigned int ipv6_defrag(const struct nf_hook_ops *ops, nf_ct_frag6_consume_orig(reasm); - NF_HOOK_THRESH(NFPROTO_IPV6, ops->hooknum, reasm, - (struct net_device *) in, (struct net_device *) out, - okfn, NF_IP6_PRI_CONNTRACK_DEFRAG + 1); + NF_HOOK_THRESH(NFPROTO_IPV6, ops->hooknum, state->sk, reasm, + state->in, state->out, + state->okfn, NF_IP6_PRI_CONNTRACK_DEFRAG + 1); return NF_STOLEN; } diff --git a/net/ipv6/netfilter/nf_log_ipv6.c b/net/ipv6/netfilter/nf_log_ipv6.c index ddf07e6f59d7..8dd869642f45 100644 --- a/net/ipv6/netfilter/nf_log_ipv6.c +++ b/net/ipv6/netfilter/nf_log_ipv6.c @@ -5,8 +5,10 @@ * it under the terms of the GNU General Public License version 2 as * published by the Free Software Foundation. */ + #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt +#include <linux/kernel.h> #include <linux/module.h> #include <linux/spinlock.h> #include <linux/skbuff.h> @@ -27,7 +29,7 @@ static struct nf_loginfo default_loginfo = { .type = NF_LOG_TYPE_LOG, .u = { .log = { - .level = 5, + .level = LOGLEVEL_NOTICE, .logflags = NF_LOG_MASK, }, }, diff --git a/net/ipv6/netfilter/nf_nat_l3proto_ipv6.c b/net/ipv6/netfilter/nf_nat_l3proto_ipv6.c index c5812e1c1ffb..e76900e0aa92 100644 --- a/net/ipv6/netfilter/nf_nat_l3proto_ipv6.c +++ b/net/ipv6/netfilter/nf_nat_l3proto_ipv6.c @@ -263,11 +263,10 @@ EXPORT_SYMBOL_GPL(nf_nat_icmpv6_reply_translation); unsigned int nf_nat_ipv6_fn(const struct nf_hook_ops *ops, struct sk_buff *skb, - const struct net_device *in, const struct net_device *out, + const struct nf_hook_state *state, unsigned int (*do_chain)(const struct nf_hook_ops *ops, struct sk_buff *skb, - const struct net_device *in, - const struct net_device *out, + const struct nf_hook_state *state, struct nf_conn *ct)) { struct nf_conn *ct; @@ -318,7 +317,7 @@ nf_nat_ipv6_fn(const struct nf_hook_ops *ops, struct sk_buff *skb, if (!nf_nat_initialized(ct, maniptype)) { unsigned int ret; - ret = do_chain(ops, skb, in, out, ct); + ret = do_chain(ops, skb, state, ct); if (ret != NF_ACCEPT) return ret; @@ -332,7 +331,7 @@ nf_nat_ipv6_fn(const struct nf_hook_ops *ops, struct sk_buff *skb, pr_debug("Already setup manip %s for ct %p\n", maniptype == NF_NAT_MANIP_SRC ? "SRC" : "DST", ct); - if (nf_nat_oif_changed(ops->hooknum, ctinfo, nat, out)) + if (nf_nat_oif_changed(ops->hooknum, ctinfo, nat, state->out)) goto oif_changed; } break; @@ -341,7 +340,7 @@ nf_nat_ipv6_fn(const struct nf_hook_ops *ops, struct sk_buff *skb, /* ESTABLISHED */ NF_CT_ASSERT(ctinfo == IP_CT_ESTABLISHED || ctinfo == IP_CT_ESTABLISHED_REPLY); - if (nf_nat_oif_changed(ops->hooknum, ctinfo, nat, out)) + if (nf_nat_oif_changed(ops->hooknum, ctinfo, nat, state->out)) goto oif_changed; } @@ -355,17 +354,16 @@ EXPORT_SYMBOL_GPL(nf_nat_ipv6_fn); unsigned int nf_nat_ipv6_in(const struct nf_hook_ops *ops, struct sk_buff *skb, - const struct net_device *in, const struct net_device *out, + const struct nf_hook_state *state, unsigned int (*do_chain)(const struct nf_hook_ops *ops, struct sk_buff *skb, - const struct net_device *in, - const struct net_device *out, + const struct nf_hook_state *state, struct nf_conn *ct)) { unsigned int ret; struct in6_addr daddr = ipv6_hdr(skb)->daddr; - ret = nf_nat_ipv6_fn(ops, skb, in, out, do_chain); + ret = nf_nat_ipv6_fn(ops, skb, state, do_chain); if (ret != NF_DROP && ret != NF_STOLEN && ipv6_addr_cmp(&daddr, &ipv6_hdr(skb)->daddr)) skb_dst_drop(skb); @@ -376,11 +374,10 @@ EXPORT_SYMBOL_GPL(nf_nat_ipv6_in); unsigned int nf_nat_ipv6_out(const struct nf_hook_ops *ops, struct sk_buff *skb, - const struct net_device *in, const struct net_device *out, + const struct nf_hook_state *state, unsigned int (*do_chain)(const struct nf_hook_ops *ops, struct sk_buff *skb, - const struct net_device *in, - const struct net_device *out, + const struct nf_hook_state *state, struct nf_conn *ct)) { #ifdef CONFIG_XFRM @@ -394,7 +391,7 @@ nf_nat_ipv6_out(const struct nf_hook_ops *ops, struct sk_buff *skb, if (skb->len < sizeof(struct ipv6hdr)) return NF_ACCEPT; - ret = nf_nat_ipv6_fn(ops, skb, in, out, do_chain); + ret = nf_nat_ipv6_fn(ops, skb, state, do_chain); #ifdef CONFIG_XFRM if (ret != NF_DROP && ret != NF_STOLEN && !(IP6CB(skb)->flags & IP6SKB_XFRM_TRANSFORMED) && @@ -418,11 +415,10 @@ EXPORT_SYMBOL_GPL(nf_nat_ipv6_out); unsigned int nf_nat_ipv6_local_fn(const struct nf_hook_ops *ops, struct sk_buff *skb, - const struct net_device *in, const struct net_device *out, + const struct nf_hook_state *state, unsigned int (*do_chain)(const struct nf_hook_ops *ops, struct sk_buff *skb, - const struct net_device *in, - const struct net_device *out, + const struct nf_hook_state *state, struct nf_conn *ct)) { const struct nf_conn *ct; @@ -434,7 +430,7 @@ nf_nat_ipv6_local_fn(const struct nf_hook_ops *ops, struct sk_buff *skb, if (skb->len < sizeof(struct ipv6hdr)) return NF_ACCEPT; - ret = nf_nat_ipv6_fn(ops, skb, in, out, do_chain); + ret = nf_nat_ipv6_fn(ops, skb, state, do_chain); if (ret != NF_DROP && ret != NF_STOLEN && (ct = nf_ct_get(skb, &ctinfo)) != NULL) { enum ip_conntrack_dir dir = CTINFO2DIR(ctinfo); diff --git a/net/ipv6/netfilter/nf_reject_ipv6.c b/net/ipv6/netfilter/nf_reject_ipv6.c index d05b36440e8b..94b4c6dfb400 100644 --- a/net/ipv6/netfilter/nf_reject_ipv6.c +++ b/net/ipv6/netfilter/nf_reject_ipv6.c @@ -13,6 +13,7 @@ #include <net/ip6_checksum.h> #include <net/netfilter/ipv6/nf_reject.h> #include <linux/netfilter_ipv6.h> +#include <linux/netfilter_bridge.h> #include <net/netfilter/ipv6/nf_reject.h> const struct tcphdr *nf_reject_ip6_tcphdr_get(struct sk_buff *oldskb, @@ -65,7 +66,7 @@ EXPORT_SYMBOL_GPL(nf_reject_ip6_tcphdr_get); struct ipv6hdr *nf_reject_ip6hdr_put(struct sk_buff *nskb, const struct sk_buff *oldskb, - __be16 protocol, int hoplimit) + __u8 protocol, int hoplimit) { struct ipv6hdr *ip6h; const struct ipv6hdr *oip6h = ipv6_hdr(oldskb); @@ -195,7 +196,8 @@ void nf_send_reset6(struct net *net, struct sk_buff *oldskb, int hook) */ if (oldskb->nf_bridge) { struct ethhdr *oeth = eth_hdr(oldskb); - nskb->dev = oldskb->nf_bridge->physindev; + + nskb->dev = nf_bridge_get_physindev(oldskb); nskb->protocol = htons(ETH_P_IPV6); ip6h->payload_len = htons(sizeof(struct tcphdr)); if (dev_hard_header(nskb, nskb->dev, ntohs(nskb->protocol), @@ -208,4 +210,39 @@ void nf_send_reset6(struct net *net, struct sk_buff *oldskb, int hook) } EXPORT_SYMBOL_GPL(nf_send_reset6); +static bool reject6_csum_ok(struct sk_buff *skb, int hook) +{ + const struct ipv6hdr *ip6h = ipv6_hdr(skb); + int thoff; + __be16 fo; + u8 proto; + + if (skb->csum_bad) + return false; + + if (skb_csum_unnecessary(skb)) + return true; + + proto = ip6h->nexthdr; + thoff = ipv6_skip_exthdr(skb, ((u8*)(ip6h+1) - skb->data), &proto, &fo); + + if (thoff < 0 || thoff >= skb->len || (fo & htons(~0x7)) != 0) + return false; + + return nf_ip6_checksum(skb, hook, thoff, proto) == 0; +} + +void nf_send_unreach6(struct net *net, struct sk_buff *skb_in, + unsigned char code, unsigned int hooknum) +{ + if (!reject6_csum_ok(skb_in, hooknum)) + return; + + if (hooknum == NF_INET_LOCAL_OUT && skb_in->dev == NULL) + skb_in->dev = net->loopback_dev; + + icmpv6_send(skb_in, ICMPV6_DEST_UNREACH, code, 0); +} +EXPORT_SYMBOL_GPL(nf_send_unreach6); + MODULE_LICENSE("GPL"); diff --git a/net/ipv6/netfilter/nf_tables_ipv6.c b/net/ipv6/netfilter/nf_tables_ipv6.c index 0d812b31277d..c8148ba76d1a 100644 --- a/net/ipv6/netfilter/nf_tables_ipv6.c +++ b/net/ipv6/netfilter/nf_tables_ipv6.c @@ -18,14 +18,12 @@ static unsigned int nft_do_chain_ipv6(const struct nf_hook_ops *ops, struct sk_buff *skb, - const struct net_device *in, - const struct net_device *out, - int (*okfn)(struct sk_buff *)) + const struct nf_hook_state *state) { struct nft_pktinfo pkt; /* malformed packet, drop it */ - if (nft_set_pktinfo_ipv6(&pkt, ops, skb, in, out) < 0) + if (nft_set_pktinfo_ipv6(&pkt, ops, skb, state) < 0) return NF_DROP; return nft_do_chain(&pkt, ops); @@ -33,9 +31,7 @@ static unsigned int nft_do_chain_ipv6(const struct nf_hook_ops *ops, static unsigned int nft_ipv6_output(const struct nf_hook_ops *ops, struct sk_buff *skb, - const struct net_device *in, - const struct net_device *out, - int (*okfn)(struct sk_buff *)) + const struct nf_hook_state *state) { if (unlikely(skb->len < sizeof(struct ipv6hdr))) { if (net_ratelimit()) @@ -44,7 +40,7 @@ static unsigned int nft_ipv6_output(const struct nf_hook_ops *ops, return NF_ACCEPT; } - return nft_do_chain_ipv6(ops, skb, in, out, okfn); + return nft_do_chain_ipv6(ops, skb, state); } struct nft_af_info nft_af_ipv6 __read_mostly = { diff --git a/net/ipv6/netfilter/nft_chain_nat_ipv6.c b/net/ipv6/netfilter/nft_chain_nat_ipv6.c index 1c4b75dd425b..951bb458b7bd 100644 --- a/net/ipv6/netfilter/nft_chain_nat_ipv6.c +++ b/net/ipv6/netfilter/nft_chain_nat_ipv6.c @@ -26,51 +26,42 @@ static unsigned int nft_nat_do_chain(const struct nf_hook_ops *ops, struct sk_buff *skb, - const struct net_device *in, - const struct net_device *out, + const struct nf_hook_state *state, struct nf_conn *ct) { struct nft_pktinfo pkt; - nft_set_pktinfo_ipv6(&pkt, ops, skb, in, out); + nft_set_pktinfo_ipv6(&pkt, ops, skb, state); return nft_do_chain(&pkt, ops); } static unsigned int nft_nat_ipv6_fn(const struct nf_hook_ops *ops, struct sk_buff *skb, - const struct net_device *in, - const struct net_device *out, - int (*okfn)(struct sk_buff *)) + const struct nf_hook_state *state) { - return nf_nat_ipv6_fn(ops, skb, in, out, nft_nat_do_chain); + return nf_nat_ipv6_fn(ops, skb, state, nft_nat_do_chain); } static unsigned int nft_nat_ipv6_in(const struct nf_hook_ops *ops, struct sk_buff *skb, - const struct net_device *in, - const struct net_device *out, - int (*okfn)(struct sk_buff *)) + const struct nf_hook_state *state) { - return nf_nat_ipv6_in(ops, skb, in, out, nft_nat_do_chain); + return nf_nat_ipv6_in(ops, skb, state, nft_nat_do_chain); } static unsigned int nft_nat_ipv6_out(const struct nf_hook_ops *ops, struct sk_buff *skb, - const struct net_device *in, - const struct net_device *out, - int (*okfn)(struct sk_buff *)) + const struct nf_hook_state *state) { - return nf_nat_ipv6_out(ops, skb, in, out, nft_nat_do_chain); + return nf_nat_ipv6_out(ops, skb, state, nft_nat_do_chain); } static unsigned int nft_nat_ipv6_local_fn(const struct nf_hook_ops *ops, struct sk_buff *skb, - const struct net_device *in, - const struct net_device *out, - int (*okfn)(struct sk_buff *)) + const struct nf_hook_state *state) { - return nf_nat_ipv6_local_fn(ops, skb, in, out, nft_nat_do_chain); + return nf_nat_ipv6_local_fn(ops, skb, state, nft_nat_do_chain); } static const struct nf_chain_type nft_chain_nat_ipv6 = { diff --git a/net/ipv6/netfilter/nft_chain_route_ipv6.c b/net/ipv6/netfilter/nft_chain_route_ipv6.c index 42031299585e..0dafdaac5e17 100644 --- a/net/ipv6/netfilter/nft_chain_route_ipv6.c +++ b/net/ipv6/netfilter/nft_chain_route_ipv6.c @@ -24,9 +24,7 @@ static unsigned int nf_route_table_hook(const struct nf_hook_ops *ops, struct sk_buff *skb, - const struct net_device *in, - const struct net_device *out, - int (*okfn)(struct sk_buff *)) + const struct nf_hook_state *state) { unsigned int ret; struct nft_pktinfo pkt; @@ -35,7 +33,7 @@ static unsigned int nf_route_table_hook(const struct nf_hook_ops *ops, u32 mark, flowlabel; /* malformed packet, drop it */ - if (nft_set_pktinfo_ipv6(&pkt, ops, skb, in, out) < 0) + if (nft_set_pktinfo_ipv6(&pkt, ops, skb, state) < 0) return NF_DROP; /* save source/dest address, mark, hoplimit, flowlabel, priority */ diff --git a/net/ipv6/netfilter/nft_masq_ipv6.c b/net/ipv6/netfilter/nft_masq_ipv6.c index 529c119cbb14..cd1ac1637a05 100644 --- a/net/ipv6/netfilter/nft_masq_ipv6.c +++ b/net/ipv6/netfilter/nft_masq_ipv6.c @@ -18,19 +18,16 @@ #include <net/netfilter/ipv6/nf_nat_masquerade.h> static void nft_masq_ipv6_eval(const struct nft_expr *expr, - struct nft_data data[NFT_REG_MAX + 1], + struct nft_regs *regs, const struct nft_pktinfo *pkt) { struct nft_masq *priv = nft_expr_priv(expr); struct nf_nat_range range; - unsigned int verdict; memset(&range, 0, sizeof(range)); range.flags = priv->flags; - verdict = nf_nat_masquerade_ipv6(pkt->skb, &range, pkt->out); - - data[NFT_REG_VERDICT].verdict = verdict; + regs->verdict.code = nf_nat_masquerade_ipv6(pkt->skb, &range, pkt->out); } static struct nft_expr_type nft_masq_ipv6_type; diff --git a/net/ipv6/netfilter/nft_redir_ipv6.c b/net/ipv6/netfilter/nft_redir_ipv6.c index 11820b6b3613..effd393bd517 100644 --- a/net/ipv6/netfilter/nft_redir_ipv6.c +++ b/net/ipv6/netfilter/nft_redir_ipv6.c @@ -18,26 +18,25 @@ #include <net/netfilter/nf_nat_redirect.h> static void nft_redir_ipv6_eval(const struct nft_expr *expr, - struct nft_data data[NFT_REG_MAX + 1], + struct nft_regs *regs, const struct nft_pktinfo *pkt) { struct nft_redir *priv = nft_expr_priv(expr); struct nf_nat_range range; - unsigned int verdict; memset(&range, 0, sizeof(range)); if (priv->sreg_proto_min) { range.min_proto.all = - *(__be16 *)&data[priv->sreg_proto_min].data[0]; + *(__be16 *)®s->data[priv->sreg_proto_min], range.max_proto.all = - *(__be16 *)&data[priv->sreg_proto_max].data[0]; + *(__be16 *)®s->data[priv->sreg_proto_max], range.flags |= NF_NAT_RANGE_PROTO_SPECIFIED; } range.flags |= priv->flags; - verdict = nf_nat_redirect_ipv6(pkt->skb, &range, pkt->ops->hooknum); - data[NFT_REG_VERDICT].verdict = verdict; + regs->verdict.code = nf_nat_redirect_ipv6(pkt->skb, &range, + pkt->ops->hooknum); } static struct nft_expr_type nft_redir_ipv6_type; diff --git a/net/ipv6/netfilter/nft_reject_ipv6.c b/net/ipv6/netfilter/nft_reject_ipv6.c index f73285924144..d0d1540ecf87 100644 --- a/net/ipv6/netfilter/nft_reject_ipv6.c +++ b/net/ipv6/netfilter/nft_reject_ipv6.c @@ -20,7 +20,7 @@ #include <net/netfilter/ipv6/nf_reject.h> static void nft_reject_ipv6_eval(const struct nft_expr *expr, - struct nft_data data[NFT_REG_MAX + 1], + struct nft_regs *regs, const struct nft_pktinfo *pkt) { struct nft_reject *priv = nft_expr_priv(expr); @@ -34,9 +34,11 @@ static void nft_reject_ipv6_eval(const struct nft_expr *expr, case NFT_REJECT_TCP_RST: nf_send_reset6(net, pkt->skb, pkt->ops->hooknum); break; + default: + break; } - data[NFT_REG_VERDICT].verdict = NF_DROP; + regs->verdict.code = NF_DROP; } static struct nft_expr_type nft_reject_ipv6_type; diff --git a/net/ipv6/output_core.c b/net/ipv6/output_core.c index 74581f706c4d..85892af57364 100644 --- a/net/ipv6/output_core.c +++ b/net/ipv6/output_core.c @@ -9,13 +9,14 @@ #include <net/addrconf.h> #include <net/secure_seq.h> -static u32 __ipv6_select_ident(u32 hashrnd, struct in6_addr *dst, - struct in6_addr *src) +static u32 __ipv6_select_ident(struct net *net, u32 hashrnd, + struct in6_addr *dst, struct in6_addr *src) { u32 hash, id; hash = __ipv6_addr_jhash(dst, hashrnd); hash = __ipv6_addr_jhash(src, hash); + hash ^= net_hash_mix(net); /* Treat id of 0 as unset and if we get 0 back from ip_idents_reserve, * set the hight order instead thus minimizing possible future @@ -36,7 +37,7 @@ static u32 __ipv6_select_ident(u32 hashrnd, struct in6_addr *dst, * * The network header must be set before calling this. */ -void ipv6_proxy_select_ident(struct sk_buff *skb) +void ipv6_proxy_select_ident(struct net *net, struct sk_buff *skb) { static u32 ip6_proxy_idents_hashrnd __read_mostly; struct in6_addr buf[2]; @@ -53,20 +54,21 @@ void ipv6_proxy_select_ident(struct sk_buff *skb) net_get_random_once(&ip6_proxy_idents_hashrnd, sizeof(ip6_proxy_idents_hashrnd)); - id = __ipv6_select_ident(ip6_proxy_idents_hashrnd, + id = __ipv6_select_ident(net, ip6_proxy_idents_hashrnd, &addrs[1], &addrs[0]); skb_shinfo(skb)->ip6_frag_id = htonl(id); } EXPORT_SYMBOL_GPL(ipv6_proxy_select_ident); -void ipv6_select_ident(struct frag_hdr *fhdr, struct rt6_info *rt) +void ipv6_select_ident(struct net *net, struct frag_hdr *fhdr, + struct rt6_info *rt) { static u32 ip6_idents_hashrnd __read_mostly; u32 id; net_get_random_once(&ip6_idents_hashrnd, sizeof(ip6_idents_hashrnd)); - id = __ipv6_select_ident(ip6_idents_hashrnd, &rt->rt6i_dst.addr, + id = __ipv6_select_ident(net, ip6_idents_hashrnd, &rt->rt6i_dst.addr, &rt->rt6i_src.addr); fhdr->identification = htonl(id); } @@ -134,7 +136,7 @@ int ip6_dst_hoplimit(struct dst_entry *dst) EXPORT_SYMBOL(ip6_dst_hoplimit); #endif -int __ip6_local_out(struct sk_buff *skb) +static int __ip6_local_out_sk(struct sock *sk, struct sk_buff *skb) { int len; @@ -144,19 +146,30 @@ int __ip6_local_out(struct sk_buff *skb) ipv6_hdr(skb)->payload_len = htons(len); IP6CB(skb)->nhoff = offsetof(struct ipv6hdr, nexthdr); - return nf_hook(NFPROTO_IPV6, NF_INET_LOCAL_OUT, skb, NULL, - skb_dst(skb)->dev, dst_output); + return nf_hook(NFPROTO_IPV6, NF_INET_LOCAL_OUT, sk, skb, + NULL, skb_dst(skb)->dev, dst_output_sk); +} + +int __ip6_local_out(struct sk_buff *skb) +{ + return __ip6_local_out_sk(skb->sk, skb); } EXPORT_SYMBOL_GPL(__ip6_local_out); -int ip6_local_out(struct sk_buff *skb) +int ip6_local_out_sk(struct sock *sk, struct sk_buff *skb) { int err; - err = __ip6_local_out(skb); + err = __ip6_local_out_sk(sk, skb); if (likely(err == 1)) - err = dst_output(skb); + err = dst_output_sk(sk, skb); return err; } +EXPORT_SYMBOL_GPL(ip6_local_out_sk); + +int ip6_local_out(struct sk_buff *skb) +{ + return ip6_local_out_sk(skb->sk, skb); +} EXPORT_SYMBOL_GPL(ip6_local_out); diff --git a/net/ipv6/ping.c b/net/ipv6/ping.c index a2dfff6ff227..263a5164a6f5 100644 --- a/net/ipv6/ping.c +++ b/net/ipv6/ping.c @@ -77,8 +77,7 @@ static int dummy_ipv6_chk_addr(struct net *net, const struct in6_addr *addr, return 0; } -int ping_v6_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg, - size_t len) +int ping_v6_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) { struct inet_sock *inet = inet_sk(sk); struct ipv6_pinfo *np = inet6_sk(sk); diff --git a/net/ipv6/raw.c b/net/ipv6/raw.c index dae7f1a1e464..8072bd4139b7 100644 --- a/net/ipv6/raw.c +++ b/net/ipv6/raw.c @@ -32,7 +32,7 @@ #include <linux/netfilter_ipv6.h> #include <linux/skbuff.h> #include <linux/compat.h> -#include <asm/uaccess.h> +#include <linux/uaccess.h> #include <asm/ioctls.h> #include <net/net_namespace.h> @@ -172,7 +172,7 @@ static bool ipv6_raw_deliver(struct sk_buff *skb, int nexthdr) read_lock(&raw_v6_hashinfo.lock); sk = sk_head(&raw_v6_hashinfo.ht[hash]); - if (sk == NULL) + if (!sk) goto out; net = dev_net(skb->dev); @@ -367,7 +367,7 @@ void raw6_icmp_error(struct sk_buff *skb, int nexthdr, read_lock(&raw_v6_hashinfo.lock); sk = sk_head(&raw_v6_hashinfo.ht[hash]); - if (sk != NULL) { + if (sk) { /* Note: ipv6_hdr(skb) != skb->data */ const struct ipv6hdr *ip6h = (const struct ipv6hdr *)skb->data; saddr = &ip6h->saddr; @@ -456,9 +456,8 @@ int rawv6_rcv(struct sock *sk, struct sk_buff *skb) * we return it, otherwise we block. */ -static int rawv6_recvmsg(struct kiocb *iocb, struct sock *sk, - struct msghdr *msg, size_t len, - int noblock, int flags, int *addr_len) +static int rawv6_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, + int noblock, int flags, int *addr_len) { struct ipv6_pinfo *np = inet6_sk(sk); DECLARE_SOCKADDR(struct sockaddr_in6 *, sin6, msg->msg_name); @@ -631,7 +630,7 @@ static int rawv6_send_hdrinc(struct sock *sk, struct msghdr *msg, int length, skb = sock_alloc_send_skb(sk, length + hlen + tlen + 15, flags & MSG_DONTWAIT, &err); - if (skb == NULL) + if (!skb) goto error; skb_reserve(skb, hlen); @@ -653,8 +652,8 @@ static int rawv6_send_hdrinc(struct sock *sk, struct msghdr *msg, int length, goto error_fault; IP6_UPD_PO_STATS(sock_net(sk), rt->rt6i_idev, IPSTATS_MIB_OUT, skb->len); - err = NF_HOOK(NFPROTO_IPV6, NF_INET_LOCAL_OUT, skb, NULL, - rt->dst.dev, dst_output); + err = NF_HOOK(NFPROTO_IPV6, NF_INET_LOCAL_OUT, sk, skb, + NULL, rt->dst.dev, dst_output_sk); if (err > 0) err = net_xmit_errno(err); if (err) @@ -730,8 +729,7 @@ static int raw6_getfrag(void *from, char *to, int offset, int len, int odd, return ip_generic_getfrag(rfv->msg, to, offset, len, odd, skb); } -static int rawv6_sendmsg(struct kiocb *iocb, struct sock *sk, - struct msghdr *msg, size_t len) +static int rawv6_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) { struct ipv6_txoptions opt_space; DECLARE_SOCKADDR(struct sockaddr_in6 *, sin6, msg->msg_name); @@ -791,7 +789,7 @@ static int rawv6_sendmsg(struct kiocb *iocb, struct sock *sk, fl6.flowlabel = sin6->sin6_flowinfo&IPV6_FLOWINFO_MASK; if (fl6.flowlabel&IPV6_FLOWLABEL_MASK) { flowlabel = fl6_sock_lookup(sk, fl6.flowlabel); - if (flowlabel == NULL) + if (!flowlabel) return -EINVAL; } } @@ -833,13 +831,13 @@ static int rawv6_sendmsg(struct kiocb *iocb, struct sock *sk, } if ((fl6.flowlabel&IPV6_FLOWLABEL_MASK) && !flowlabel) { flowlabel = fl6_sock_lookup(sk, fl6.flowlabel); - if (flowlabel == NULL) + if (!flowlabel) return -EINVAL; } if (!(opt->opt_nflen|opt->opt_flen)) opt = NULL; } - if (opt == NULL) + if (!opt) opt = np->opt; if (flowlabel) opt = fl6_merge_options(&opt_space, flowlabel, opt); @@ -1132,7 +1130,7 @@ static int rawv6_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) + if (skb) amount = skb_tail_pointer(skb) - skb_transport_header(skb); spin_unlock_bh(&sk->sk_receive_queue.lock); diff --git a/net/ipv6/reassembly.c b/net/ipv6/reassembly.c index d7d70e69973b..8ffa2c8cce77 100644 --- a/net/ipv6/reassembly.c +++ b/net/ipv6/reassembly.c @@ -430,7 +430,7 @@ static int ip6_frag_reasm(struct frag_queue *fq, struct sk_buff *prev, int i, plen = 0; clone = alloc_skb(0, GFP_ATOMIC); - if (clone == NULL) + if (!clone) goto out_oom; clone->next = head->next; head->next = clone; @@ -552,7 +552,7 @@ static int ipv6_frag_rcv(struct sk_buff *skb) fq = fq_find(net, fhdr->identification, &hdr->saddr, &hdr->daddr, ip6_frag_ecn(hdr)); - if (fq != NULL) { + if (fq) { int ret; spin_lock(&fq->q.lock); @@ -632,7 +632,7 @@ static int __net_init ip6_frags_ns_sysctl_register(struct net *net) table = ip6_frags_ns_ctl_table; if (!net_eq(net, &init_net)) { table = kmemdup(table, sizeof(ip6_frags_ns_ctl_table), GFP_KERNEL); - if (table == NULL) + if (!table) goto err_alloc; table[0].data = &net->ipv6.frags.high_thresh; @@ -648,7 +648,7 @@ static int __net_init ip6_frags_ns_sysctl_register(struct net *net) } hdr = register_net_sysctl(net, "net/ipv6", table); - if (hdr == NULL) + if (!hdr) goto err_reg; net->ipv6.sysctl.frags_hdr = hdr; diff --git a/net/ipv6/route.c b/net/ipv6/route.c index 4688bd4d7f59..5c48293ff062 100644 --- a/net/ipv6/route.c +++ b/net/ipv6/route.c @@ -194,7 +194,6 @@ static struct neighbour *ip6_neigh_lookup(const struct dst_entry *dst, static struct dst_ops ip6_dst_ops_template = { .family = AF_INET6, - .protocol = cpu_to_be16(ETH_P_IPV6), .gc = ip6_dst_gc, .gc_thresh = 1024, .check = ip6_dst_check, @@ -236,7 +235,6 @@ static u32 *ip6_rt_blackhole_cow_metrics(struct dst_entry *dst, static struct dst_ops ip6_dst_blackhole_ops = { .family = AF_INET6, - .protocol = cpu_to_be16(ETH_P_IPV6), .destroy = ip6_dst_destroy, .check = ip6_dst_check, .mtu = ip6_blackhole_mtu, @@ -1478,7 +1476,7 @@ static int ip6_convert_metrics(struct mx6_config *mxc, int remaining; u32 *mp; - if (cfg->fc_mx == NULL) + if (!cfg->fc_mx) return 0; mp = kzalloc(sizeof(u32) * RTAX_MAX, GFP_KERNEL); @@ -2400,6 +2398,7 @@ static const struct nla_policy rtm_ipv6_policy[RTA_MAX+1] = { [RTA_PRIORITY] = { .type = NLA_U32 }, [RTA_METRICS] = { .type = NLA_NESTED }, [RTA_MULTIPATH] = { .len = sizeof(struct rtnexthop) }, + [RTA_PREF] = { .type = NLA_U8 }, }; static int rtm_to_fib6_config(struct sk_buff *skb, struct nlmsghdr *nlh, @@ -2407,6 +2406,7 @@ static int rtm_to_fib6_config(struct sk_buff *skb, struct nlmsghdr *nlh, { struct rtmsg *rtm; struct nlattr *tb[RTA_MAX+1]; + unsigned int pref; int err; err = nlmsg_parse(nlh, sizeof(*rtm), tb, RTA_MAX, rtm_ipv6_policy); @@ -2438,7 +2438,7 @@ static int rtm_to_fib6_config(struct sk_buff *skb, struct nlmsghdr *nlh, cfg->fc_nlinfo.nl_net = sock_net(skb->sk); if (tb[RTA_GATEWAY]) { - nla_memcpy(&cfg->fc_gateway, tb[RTA_GATEWAY], 16); + cfg->fc_gateway = nla_get_in6_addr(tb[RTA_GATEWAY]); cfg->fc_flags |= RTF_GATEWAY; } @@ -2461,7 +2461,7 @@ static int rtm_to_fib6_config(struct sk_buff *skb, struct nlmsghdr *nlh, } if (tb[RTA_PREFSRC]) - nla_memcpy(&cfg->fc_prefsrc, tb[RTA_PREFSRC], 16); + cfg->fc_prefsrc = nla_get_in6_addr(tb[RTA_PREFSRC]); if (tb[RTA_OIF]) cfg->fc_ifindex = nla_get_u32(tb[RTA_OIF]); @@ -2482,6 +2482,14 @@ static int rtm_to_fib6_config(struct sk_buff *skb, struct nlmsghdr *nlh, cfg->fc_mp_len = nla_len(tb[RTA_MULTIPATH]); } + if (tb[RTA_PREF]) { + pref = nla_get_u8(tb[RTA_PREF]); + if (pref != ICMPV6_ROUTER_PREF_LOW && + pref != ICMPV6_ROUTER_PREF_HIGH) + pref = ICMPV6_ROUTER_PREF_MEDIUM; + cfg->fc_flags |= RTF_PREF(pref); + } + err = 0; errout: return err; @@ -2511,7 +2519,7 @@ beginning: nla = nla_find(attrs, attrlen, RTA_GATEWAY); if (nla) { - nla_memcpy(&r_cfg.fc_gateway, nla, 16); + r_cfg.fc_gateway = nla_get_in6_addr(nla); r_cfg.fc_flags |= RTF_GATEWAY; } } @@ -2585,7 +2593,8 @@ static inline size_t rt6_nlmsg_size(void) + nla_total_size(4) /* RTA_PRIORITY */ + RTAX_MAX * nla_total_size(4) /* RTA_METRICS */ + nla_total_size(sizeof(struct rta_cacheinfo)) - + nla_total_size(TCP_CA_NAME_MAX); /* RTAX_CC_ALGO */ + + nla_total_size(TCP_CA_NAME_MAX) /* RTAX_CC_ALGO */ + + nla_total_size(1); /* RTA_PREF */ } static int rt6_fill_node(struct net *net, @@ -2660,19 +2669,19 @@ static int rt6_fill_node(struct net *net, rtm->rtm_flags |= RTM_F_CLONED; if (dst) { - if (nla_put(skb, RTA_DST, 16, dst)) + if (nla_put_in6_addr(skb, RTA_DST, dst)) goto nla_put_failure; rtm->rtm_dst_len = 128; } else if (rtm->rtm_dst_len) - if (nla_put(skb, RTA_DST, 16, &rt->rt6i_dst.addr)) + if (nla_put_in6_addr(skb, RTA_DST, &rt->rt6i_dst.addr)) goto nla_put_failure; #ifdef CONFIG_IPV6_SUBTREES if (src) { - if (nla_put(skb, RTA_SRC, 16, src)) + if (nla_put_in6_addr(skb, RTA_SRC, src)) goto nla_put_failure; rtm->rtm_src_len = 128; } else if (rtm->rtm_src_len && - nla_put(skb, RTA_SRC, 16, &rt->rt6i_src.addr)) + nla_put_in6_addr(skb, RTA_SRC, &rt->rt6i_src.addr)) goto nla_put_failure; #endif if (iif) { @@ -2696,14 +2705,14 @@ static int rt6_fill_node(struct net *net, } else if (dst) { struct in6_addr saddr_buf; if (ip6_route_get_saddr(net, rt, dst, 0, &saddr_buf) == 0 && - nla_put(skb, RTA_PREFSRC, 16, &saddr_buf)) + nla_put_in6_addr(skb, RTA_PREFSRC, &saddr_buf)) goto nla_put_failure; } if (rt->rt6i_prefsrc.plen) { struct in6_addr saddr_buf; saddr_buf = rt->rt6i_prefsrc.addr; - if (nla_put(skb, RTA_PREFSRC, 16, &saddr_buf)) + if (nla_put_in6_addr(skb, RTA_PREFSRC, &saddr_buf)) goto nla_put_failure; } @@ -2711,7 +2720,7 @@ static int rt6_fill_node(struct net *net, goto nla_put_failure; if (rt->rt6i_flags & RTF_GATEWAY) { - if (nla_put(skb, RTA_GATEWAY, 16, &rt->rt6i_gateway) < 0) + if (nla_put_in6_addr(skb, RTA_GATEWAY, &rt->rt6i_gateway) < 0) goto nla_put_failure; } @@ -2726,6 +2735,9 @@ static int rt6_fill_node(struct net *net, if (rtnl_put_cacheinfo(skb, &rt->dst, 0, expires, rt->dst.error) < 0) goto nla_put_failure; + if (nla_put_u8(skb, RTA_PREF, IPV6_EXTRACT_PREF(rt->rt6i_flags))) + goto nla_put_failure; + nlmsg_end(skb, nlh); return 0; diff --git a/net/ipv6/sit.c b/net/ipv6/sit.c index e4cbd5798eba..ac35a28599be 100644 --- a/net/ipv6/sit.c +++ b/net/ipv6/sit.c @@ -118,7 +118,7 @@ static struct ip_tunnel *ipip6_tunnel_lookup(struct net *net, return t; } t = rcu_dereference(sitn->tunnels_wc[0]); - if ((t != NULL) && (t->dev->flags & IFF_UP)) + if (t && (t->dev->flags & IFF_UP)) return t; return NULL; } @@ -251,7 +251,7 @@ static struct ip_tunnel *ipip6_tunnel_locate(struct net *net, dev = alloc_netdev(sizeof(*t), name, NET_NAME_UNKNOWN, ipip6_tunnel_setup); - if (dev == NULL) + if (!dev) return NULL; dev_net_set(dev, net); @@ -555,7 +555,7 @@ static int ipip6_err(struct sk_buff *skb, u32 info) skb->dev, iph->daddr, iph->saddr); - if (t == NULL) + if (!t) goto out; if (type == ICMP_DEST_UNREACH && code == ICMP_FRAG_NEEDED) { @@ -671,7 +671,7 @@ static int ipip6_rcv(struct sk_buff *skb) tunnel = ipip6_tunnel_lookup(dev_net(skb->dev), skb->dev, iph->saddr, iph->daddr); - if (tunnel != NULL) { + if (tunnel) { struct pcpu_sw_netstats *tstats; if (tunnel->parms.iph.protocol != IPPROTO_IPV6 && @@ -733,7 +733,7 @@ static int ipip_rcv(struct sk_buff *skb) iph = ip_hdr(skb); tunnel = ipip6_tunnel_lookup(dev_net(skb->dev), skb->dev, iph->saddr, iph->daddr); - if (tunnel != NULL) { + if (tunnel) { if (tunnel->parms.iph.protocol != IPPROTO_IPIP && tunnel->parms.iph.protocol != 0) goto drop; @@ -838,7 +838,7 @@ static netdev_tx_t ipip6_tunnel_xmit(struct sk_buff *skb, if (skb_dst(skb)) neigh = dst_neigh_lookup(skb_dst(skb), &iph6->daddr); - if (neigh == NULL) { + if (!neigh) { net_dbg_ratelimited("nexthop == NULL\n"); goto tx_error; } @@ -867,7 +867,7 @@ static netdev_tx_t ipip6_tunnel_xmit(struct sk_buff *skb, if (skb_dst(skb)) neigh = dst_neigh_lookup(skb_dst(skb), &iph6->daddr); - if (neigh == NULL) { + if (!neigh) { net_dbg_ratelimited("nexthop == NULL\n"); goto tx_error; } @@ -983,7 +983,7 @@ static netdev_tx_t ipip6_tunnel_xmit(struct sk_buff *skb, skb_set_inner_ipproto(skb, IPPROTO_IPV6); - err = iptunnel_xmit(skb->sk, rt, skb, fl4.saddr, fl4.daddr, + err = iptunnel_xmit(NULL, rt, skb, fl4.saddr, fl4.daddr, protocol, tos, ttl, df, !net_eq(tunnel->net, dev_net(dev))); iptunnel_xmit_stats(err, &dev->stats, dev->tstats); @@ -1076,7 +1076,6 @@ static void ipip6_tunnel_bind_dev(struct net_device *dev) if (dev->mtu < IPV6_MIN_MTU) dev->mtu = IPV6_MIN_MTU; } - dev->iflink = tunnel->parms.link; } static void ipip6_tunnel_update(struct ip_tunnel *t, struct ip_tunnel_parm *p) @@ -1158,7 +1157,7 @@ ipip6_tunnel_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd) break; } t = ipip6_tunnel_locate(net, &p, 0); - if (t == NULL) + if (!t) t = netdev_priv(dev); } @@ -1206,7 +1205,7 @@ ipip6_tunnel_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd) t = ipip6_tunnel_locate(net, &p, cmd == SIOCADDTUNNEL); if (dev != sitn->fb_tunnel_dev && cmd == SIOCCHGTUNNEL) { - if (t != NULL) { + if (t) { if (t->dev != dev) { err = -EEXIST; break; @@ -1242,7 +1241,7 @@ ipip6_tunnel_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd) goto done; err = -ENOENT; t = ipip6_tunnel_locate(net, &p, 0); - if (t == NULL) + if (!t) goto done; err = -EPERM; if (t == netdev_priv(sitn->fb_tunnel_dev)) @@ -1336,6 +1335,7 @@ static const struct net_device_ops ipip6_netdev_ops = { .ndo_do_ioctl = ipip6_tunnel_ioctl, .ndo_change_mtu = ipip6_tunnel_change_mtu, .ndo_get_stats64 = ip_tunnel_get_stats64, + .ndo_get_iflink = ip_tunnel_get_iflink, }; static void ipip6_dev_free(struct net_device *dev) @@ -1366,7 +1366,6 @@ static void ipip6_tunnel_setup(struct net_device *dev) dev->mtu = ETH_DATA_LEN - t_hlen; dev->flags = IFF_NOARP; netif_keep_dst(dev); - dev->iflink = 0; dev->addr_len = 4; dev->features |= NETIF_F_LLTX; dev->features |= SIT_FEATURES; @@ -1530,8 +1529,7 @@ static bool ipip6_netlink_6rd_parms(struct nlattr *data[], if (data[IFLA_IPTUN_6RD_PREFIX]) { ret = true; - nla_memcpy(&ip6rd->prefix, data[IFLA_IPTUN_6RD_PREFIX], - sizeof(struct in6_addr)); + ip6rd->prefix = nla_get_in6_addr(data[IFLA_IPTUN_6RD_PREFIX]); } if (data[IFLA_IPTUN_6RD_RELAY_PREFIX]) { @@ -1683,8 +1681,8 @@ static int ipip6_fill_info(struct sk_buff *skb, const struct net_device *dev) struct ip_tunnel_parm *parm = &tunnel->parms; if (nla_put_u32(skb, IFLA_IPTUN_LINK, parm->link) || - nla_put_be32(skb, IFLA_IPTUN_LOCAL, parm->iph.saddr) || - nla_put_be32(skb, IFLA_IPTUN_REMOTE, parm->iph.daddr) || + nla_put_in_addr(skb, IFLA_IPTUN_LOCAL, parm->iph.saddr) || + nla_put_in_addr(skb, IFLA_IPTUN_REMOTE, parm->iph.daddr) || nla_put_u8(skb, IFLA_IPTUN_TTL, parm->iph.ttl) || nla_put_u8(skb, IFLA_IPTUN_TOS, parm->iph.tos) || nla_put_u8(skb, IFLA_IPTUN_PMTUDISC, @@ -1694,10 +1692,10 @@ static int ipip6_fill_info(struct sk_buff *skb, const struct net_device *dev) goto nla_put_failure; #ifdef CONFIG_IPV6_SIT_6RD - if (nla_put(skb, IFLA_IPTUN_6RD_PREFIX, sizeof(struct in6_addr), - &tunnel->ip6rd.prefix) || - nla_put_be32(skb, IFLA_IPTUN_6RD_RELAY_PREFIX, - tunnel->ip6rd.relay_prefix) || + if (nla_put_in6_addr(skb, IFLA_IPTUN_6RD_PREFIX, + &tunnel->ip6rd.prefix) || + nla_put_in_addr(skb, IFLA_IPTUN_6RD_RELAY_PREFIX, + tunnel->ip6rd.relay_prefix) || nla_put_u16(skb, IFLA_IPTUN_6RD_PREFIXLEN, tunnel->ip6rd.prefixlen) || nla_put_u16(skb, IFLA_IPTUN_6RD_RELAY_PREFIXLEN, @@ -1795,7 +1793,7 @@ static void __net_exit sit_destroy_tunnels(struct net *net, struct ip_tunnel *t; t = rtnl_dereference(sitn->tunnels[prio][h]); - while (t != NULL) { + while (t) { /* If dev is in the same netns, it has already * been added to the list by the previous loop. */ diff --git a/net/ipv6/syncookies.c b/net/ipv6/syncookies.c index 7337fc7947e2..21bc2eb53c57 100644 --- a/net/ipv6/syncookies.c +++ b/net/ipv6/syncookies.c @@ -49,11 +49,12 @@ static inline struct sock *get_cookie_sock(struct sock *sk, struct sk_buff *skb, struct sock *child; child = icsk->icsk_af_ops->syn_recv_sock(sk, skb, req, dst); - if (child) + if (child) { + atomic_set(&req->rsk_refcnt, 1); inet_csk_reqsk_queue_add(sk, req, child); - else + } else { reqsk_free(req); - + } return child; } @@ -189,13 +190,13 @@ struct sock *cookie_v6_check(struct sock *sk, struct sk_buff *skb) goto out; ret = NULL; - req = inet_reqsk_alloc(&tcp6_request_sock_ops); + req = inet_reqsk_alloc(&tcp6_request_sock_ops, sk); if (!req) goto out; ireq = inet_rsk(req); treq = tcp_rsk(req); - treq->listener = NULL; + treq->tfo_listener = false; if (security_inet_conn_request(sk, skb, req)) goto out_free; @@ -220,7 +221,6 @@ struct sock *cookie_v6_check(struct sock *sk, struct sk_buff *skb) ireq->ir_mark = inet_request_mark(sk, skb); - req->expires = 0UL; req->num_retrans = 0; ireq->snd_wscale = tcp_opt.snd_wscale; ireq->sack_ok = tcp_opt.sack_ok; diff --git a/net/ipv6/sysctl_net_ipv6.c b/net/ipv6/sysctl_net_ipv6.c index c5c10fafcfe2..abcc79f649b3 100644 --- a/net/ipv6/sysctl_net_ipv6.c +++ b/net/ipv6/sysctl_net_ipv6.c @@ -54,6 +54,20 @@ static struct ctl_table ipv6_table_template[] = { .mode = 0644, .proc_handler = proc_dointvec }, + { + .procname = "idgen_retries", + .data = &init_net.ipv6.sysctl.idgen_retries, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec, + }, + { + .procname = "idgen_delay", + .data = &init_net.ipv6.sysctl.idgen_delay, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec_jiffies, + }, { } }; @@ -93,6 +107,8 @@ static int __net_init ipv6_sysctl_net_init(struct net *net) 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_table[5].data = &net->ipv6.sysctl.idgen_retries; + ipv6_table[6].data = &net->ipv6.sysctl.idgen_delay; ipv6_route_table = ipv6_route_sysctl_init(net); if (!ipv6_route_table) @@ -163,7 +179,7 @@ int ipv6_sysctl_register(void) int err = -ENOMEM; ip6_header = register_net_sysctl(&init_net, "net/ipv6", ipv6_rotable); - if (ip6_header == NULL) + if (!ip6_header) goto out; err = register_pernet_subsys(&ipv6_sysctl_net_ops); diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c index 1f5e62229aaa..b6575d665568 100644 --- a/net/ipv6/tcp_ipv6.c +++ b/net/ipv6/tcp_ipv6.c @@ -104,19 +104,6 @@ static void inet6_sk_rx_dst_set(struct sock *sk, const struct sk_buff *skb) } } -static void tcp_v6_hash(struct sock *sk) -{ - if (sk->sk_state != TCP_CLOSE) { - if (inet_csk(sk)->icsk_af_ops == &ipv6_mapped) { - tcp_prot.hash(sk); - return; - } - local_bh_disable(); - __inet6_hash(sk, NULL); - local_bh_enable(); - } -} - static __u32 tcp_v6_init_sequence(const struct sk_buff *skb) { return secure_tcpv6_sequence_number(ipv6_hdr(skb)->daddr.s6_addr32, @@ -154,7 +141,7 @@ static int tcp_v6_connect(struct sock *sk, struct sockaddr *uaddr, if (fl6.flowlabel&IPV6_FLOWLABEL_MASK) { struct ip6_flowlabel *flowlabel; flowlabel = fl6_sock_lookup(sk, fl6.flowlabel); - if (flowlabel == NULL) + if (!flowlabel) return -EINVAL; fl6_sock_release(flowlabel); } @@ -233,11 +220,8 @@ static int tcp_v6_connect(struct sock *sk, struct sockaddr *uaddr, tp->af_specific = &tcp_sock_ipv6_specific; #endif goto failure; - } else { - ipv6_addr_set_v4mapped(inet->inet_saddr, &np->saddr); - ipv6_addr_set_v4mapped(inet->inet_rcv_saddr, - &sk->sk_v6_rcv_saddr); } + np->saddr = sk->sk_v6_rcv_saddr; return err; } @@ -263,7 +247,7 @@ static int tcp_v6_connect(struct sock *sk, struct sockaddr *uaddr, goto failure; } - if (saddr == NULL) { + if (!saddr) { saddr = &fl6.saddr; sk->sk_v6_rcv_saddr = *saddr; } @@ -340,18 +324,20 @@ static void tcp_v6_err(struct sk_buff *skb, struct inet6_skb_parm *opt, { const struct ipv6hdr *hdr = (const struct ipv6hdr *)skb->data; const struct tcphdr *th = (struct tcphdr *)(skb->data+offset); + struct net *net = dev_net(skb->dev); + struct request_sock *fastopen; struct ipv6_pinfo *np; - struct sock *sk; - int err; struct tcp_sock *tp; - struct request_sock *fastopen; __u32 seq, snd_una; - struct net *net = dev_net(skb->dev); + struct sock *sk; + int err; - sk = inet6_lookup(net, &tcp_hashinfo, &hdr->daddr, - th->dest, &hdr->saddr, th->source, skb->dev->ifindex); + sk = __inet6_lookup_established(net, &tcp_hashinfo, + &hdr->daddr, th->dest, + &hdr->saddr, ntohs(th->source), + skb->dev->ifindex); - if (sk == NULL) { + if (!sk) { ICMP6_INC_STATS_BH(net, __in6_dev_get(skb->dev), ICMP6_MIB_INERRORS); return; @@ -361,6 +347,9 @@ static void tcp_v6_err(struct sk_buff *skb, struct inet6_skb_parm *opt, inet_twsk_put(inet_twsk(sk)); return; } + seq = ntohl(th->seq); + if (sk->sk_state == TCP_NEW_SYN_RECV) + return tcp_req_err(sk, seq); bh_lock_sock(sk); if (sock_owned_by_user(sk) && type != ICMPV6_PKT_TOOBIG) @@ -375,7 +364,6 @@ static void tcp_v6_err(struct sk_buff *skb, struct inet6_skb_parm *opt, } tp = tcp_sk(sk); - seq = ntohl(th->seq); /* XXX (TFO) - tp->snd_una should be ISN (tcp_create_openreq_child() */ fastopen = tp->fastopen_rsk; snd_una = fastopen ? tcp_rsk(fastopen)->snt_isn : tp->snd_una; @@ -419,37 +407,12 @@ static void tcp_v6_err(struct sk_buff *skb, struct inet6_skb_parm *opt, /* Might be for an request_sock */ switch (sk->sk_state) { - struct request_sock *req, **prev; - case TCP_LISTEN: - if (sock_owned_by_user(sk)) - goto out; - - /* Note : We use inet6_iif() here, not tcp_v6_iif() */ - req = inet6_csk_search_req(sk, &prev, th->dest, &hdr->daddr, - &hdr->saddr, inet6_iif(skb)); - if (!req) - goto out; - - /* ICMPs are not backlogged, hence we cannot get - * an established socket here. - */ - WARN_ON(req->sk != NULL); - - if (seq != tcp_rsk(req)->snt_isn) { - NET_INC_STATS_BH(net, LINUX_MIB_OUTOFWINDOWICMPS); - goto out; - } - - inet_csk_reqsk_queue_drop(sk, req, prev); - NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_LISTENDROPS); - goto out; - case TCP_SYN_SENT: case TCP_SYN_RECV: /* Only in fast or simultaneous open. If a fast open socket is * is already accepted it is treated as a connected one below. */ - if (fastopen && fastopen->sk == NULL) + if (fastopen && !fastopen->sk) break; if (!sock_owned_by_user(sk)) { @@ -497,7 +460,7 @@ static int tcp_v6_send_synack(struct sock *sk, struct dst_entry *dst, &ireq->ir_v6_rmt_addr); fl6->daddr = ireq->ir_v6_rmt_addr; - if (np->repflow && (ireq->pktopts != NULL)) + if (np->repflow && ireq->pktopts) fl6->flowlabel = ip6_flowlabel(ipv6_hdr(ireq->pktopts)); skb_set_queue_mapping(skb, queue_mapping); @@ -523,17 +486,11 @@ static struct tcp_md5sig_key *tcp_v6_md5_do_lookup(struct sock *sk, } static struct tcp_md5sig_key *tcp_v6_md5_lookup(struct sock *sk, - struct sock *addr_sk) + const struct sock *addr_sk) { return tcp_v6_md5_do_lookup(sk, &addr_sk->sk_v6_daddr); } -static struct tcp_md5sig_key *tcp_v6_reqsk_md5_lookup(struct sock *sk, - struct request_sock *req) -{ - return tcp_v6_md5_do_lookup(sk, &inet_rsk(req)->ir_v6_rmt_addr); -} - static int tcp_v6_parse_md5_keys(struct sock *sk, char __user *optval, int optlen) { @@ -619,9 +576,9 @@ clear_hash_noput: return 1; } -static int tcp_v6_md5_hash_skb(char *md5_hash, struct tcp_md5sig_key *key, +static int tcp_v6_md5_hash_skb(char *md5_hash, + const struct tcp_md5sig_key *key, const struct sock *sk, - const struct request_sock *req, const struct sk_buff *skb) { const struct in6_addr *saddr, *daddr; @@ -629,12 +586,9 @@ static int tcp_v6_md5_hash_skb(char *md5_hash, struct tcp_md5sig_key *key, struct hash_desc *desc; const struct tcphdr *th = tcp_hdr(skb); - if (sk) { - saddr = &inet6_sk(sk)->saddr; + if (sk) { /* valid for establish/request sockets */ + saddr = &sk->sk_v6_rcv_saddr; daddr = &sk->sk_v6_daddr; - } else if (req) { - saddr = &inet_rsk(req)->ir_v6_loc_addr; - daddr = &inet_rsk(req)->ir_v6_rmt_addr; } else { const struct ipv6hdr *ip6h = ipv6_hdr(skb); saddr = &ip6h->saddr; @@ -670,8 +624,7 @@ clear_hash_noput: return 1; } -static int __tcp_v6_inbound_md5_hash(struct sock *sk, - const struct sk_buff *skb) +static bool tcp_v6_inbound_md5_hash(struct sock *sk, const struct sk_buff *skb) { const __u8 *hash_location = NULL; struct tcp_md5sig_key *hash_expected; @@ -685,44 +638,32 @@ static int __tcp_v6_inbound_md5_hash(struct sock *sk, /* We've parsed the options - do we have a hash? */ if (!hash_expected && !hash_location) - return 0; + return false; if (hash_expected && !hash_location) { NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_TCPMD5NOTFOUND); - return 1; + return true; } if (!hash_expected && hash_location) { NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_TCPMD5UNEXPECTED); - return 1; + return true; } /* check the signature */ genhash = tcp_v6_md5_hash_skb(newhash, hash_expected, - NULL, NULL, skb); + NULL, skb); if (genhash || memcmp(hash_location, newhash, 16) != 0) { net_info_ratelimited("MD5 Hash %s for [%pI6c]:%u->[%pI6c]:%u\n", genhash ? "failed" : "mismatch", &ip6h->saddr, ntohs(th->source), &ip6h->daddr, ntohs(th->dest)); - return 1; + return true; } - return 0; + return false; } - -static int tcp_v6_inbound_md5_hash(struct sock *sk, const struct sk_buff *skb) -{ - int ret; - - rcu_read_lock(); - ret = __tcp_v6_inbound_md5_hash(sk, skb); - rcu_read_unlock(); - - return ret; -} - #endif static void tcp_v6_init_req(struct request_sock *req, struct sock *sk, @@ -734,8 +675,6 @@ static void tcp_v6_init_req(struct request_sock *req, struct sock *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) @@ -774,7 +713,7 @@ 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, + .req_md5_lookup = tcp_v6_md5_lookup, .calc_md5_hash = tcp_v6_md5_hash_skb, #endif .init_req = tcp_v6_init_req, @@ -811,7 +750,7 @@ static void tcp_v6_send_response(struct sock *sk, struct sk_buff *skb, u32 seq, buff = alloc_skb(MAX_HEADER + sizeof(struct ipv6hdr) + tot_len, GFP_ATOMIC); - if (buff == NULL) + if (!buff) return; skb_reserve(buff, MAX_HEADER + sizeof(struct ipv6hdr) + tot_len); @@ -931,7 +870,7 @@ static void tcp_v6_send_reset(struct sock *sk, struct sk_buff *skb) if (!key) goto release_sk1; - genhash = tcp_v6_md5_hash_skb(newhash, key, NULL, NULL, skb); + genhash = tcp_v6_md5_hash_skb(newhash, key, NULL, skb); if (genhash || memcmp(hash_location, newhash, 16) != 0) goto release_sk1; } else { @@ -997,17 +936,20 @@ static void tcp_v6_reqsk_send_ack(struct sock *sk, struct sk_buff *skb, static struct sock *tcp_v6_hnd_req(struct sock *sk, struct sk_buff *skb) { - struct request_sock *req, **prev; const struct tcphdr *th = tcp_hdr(skb); + struct request_sock *req; struct sock *nsk; /* Find possible connection requests. */ - req = inet6_csk_search_req(sk, &prev, th->source, + req = inet6_csk_search_req(sk, th->source, &ipv6_hdr(skb)->saddr, &ipv6_hdr(skb)->daddr, tcp_v6_iif(skb)); - if (req) - return tcp_check_req(sk, skb, req, prev, false); - + if (req) { + nsk = tcp_check_req(sk, skb, req, false); + if (!nsk) + reqsk_put(req); + return nsk; + } nsk = __inet6_lookup_established(sock_net(sk), &tcp_hashinfo, &ipv6_hdr(skb)->saddr, th->source, &ipv6_hdr(skb)->daddr, ntohs(th->dest), @@ -1067,7 +1009,7 @@ static struct sock *tcp_v6_syn_recv_sock(struct sock *sk, struct sk_buff *skb, newsk = tcp_v4_syn_recv_sock(sk, skb, req, dst); - if (newsk == NULL) + if (!newsk) return NULL; newtcp6sk = (struct tcp6_sock *)newsk; @@ -1079,11 +1021,7 @@ static struct sock *tcp_v6_syn_recv_sock(struct sock *sk, struct sk_buff *skb, memcpy(newnp, np, sizeof(struct ipv6_pinfo)); - ipv6_addr_set_v4mapped(newinet->inet_daddr, &newsk->sk_v6_daddr); - - ipv6_addr_set_v4mapped(newinet->inet_saddr, &newnp->saddr); - - newsk->sk_v6_rcv_saddr = newnp->saddr; + newnp->saddr = newsk->sk_v6_rcv_saddr; inet_csk(newsk)->icsk_af_ops = &ipv6_mapped; newsk->sk_backlog_rcv = tcp_v4_do_rcv; @@ -1128,7 +1066,7 @@ static struct sock *tcp_v6_syn_recv_sock(struct sock *sk, struct sk_buff *skb, } newsk = tcp_create_openreq_child(sk, req, skb); - if (newsk == NULL) + if (!newsk) goto out_nonewsk; /* @@ -1170,7 +1108,7 @@ static struct sock *tcp_v6_syn_recv_sock(struct sock *sk, struct sk_buff *skb, /* Clone pktoptions received with SYN */ newnp->pktoptions = NULL; - if (ireq->pktopts != NULL) { + if (ireq->pktopts) { newnp->pktoptions = skb_clone(ireq->pktopts, sk_gfp_atomic(sk, GFP_ATOMIC)); consume_skb(ireq->pktopts); @@ -1215,7 +1153,7 @@ static struct sock *tcp_v6_syn_recv_sock(struct sock *sk, struct sk_buff *skb, #ifdef CONFIG_TCP_MD5SIG /* Copy over the MD5 key from the original socket */ key = tcp_v6_md5_do_lookup(sk, &newsk->sk_v6_daddr); - if (key != NULL) { + if (key) { /* We're using one, so create a matching key * on the newsk structure. If we fail to get * memory, then we end up not copying the key @@ -1232,7 +1170,7 @@ static struct sock *tcp_v6_syn_recv_sock(struct sock *sk, struct sk_buff *skb, tcp_done(newsk); goto out; } - __inet6_hash(newsk, NULL); + __inet_hash(newsk, NULL); return newsk; @@ -1547,9 +1485,9 @@ do_time_wait: &ipv6_hdr(skb)->saddr, th->source, &ipv6_hdr(skb)->daddr, ntohs(th->dest), tcp_v6_iif(skb)); - if (sk2 != NULL) { + if (sk2) { struct inet_timewait_sock *tw = inet_twsk(sk); - inet_twsk_deschedule(tw, &tcp_death_row); + inet_twsk_deschedule(tw); inet_twsk_put(tw); sk = sk2; tcp_v6_restore_cb(skb); @@ -1595,7 +1533,7 @@ static void tcp_v6_early_demux(struct sk_buff *skb) if (sk) { skb->sk = sk; skb->destructor = sock_edemux; - if (sk->sk_state != TCP_TIME_WAIT) { + if (sk_fullsock(sk)) { struct dst_entry *dst = READ_ONCE(sk->sk_rx_dst); if (dst) @@ -1700,9 +1638,9 @@ static void tcp_v6_destroy_sock(struct sock *sk) #ifdef CONFIG_PROC_FS /* Proc filesystem TCPv6 sock list dumping. */ static void get_openreq6(struct seq_file *seq, - const struct sock *sk, struct request_sock *req, int i, kuid_t uid) + struct request_sock *req, int i, kuid_t uid) { - int ttd = req->expires - jiffies; + long ttd = req->rsk_timer.expires - jiffies; const struct in6_addr *src = &inet_rsk(req)->ir_v6_loc_addr; const struct in6_addr *dest = &inet_rsk(req)->ir_v6_rmt_addr; @@ -1791,9 +1729,9 @@ static void get_tcp6_sock(struct seq_file *seq, struct sock *sp, int i) static void get_timewait6_sock(struct seq_file *seq, struct inet_timewait_sock *tw, int i) { + long delta = tw->tw_timer.expires - jiffies; const struct in6_addr *dest, *src; __u16 destp, srcp; - s32 delta = tw->tw_ttd - inet_tw_time_stamp(); dest = &tw->tw_v6_daddr; src = &tw->tw_v6_rcv_saddr; @@ -1838,7 +1776,7 @@ static int tcp6_seq_show(struct seq_file *seq, void *v) get_tcp6_sock(seq, v, st->num); break; case TCP_SEQ_STATE_OPENREQ: - get_openreq6(seq, st->syn_wait_sk, v, st->num, st->uid); + get_openreq6(seq, v, st->num, st->uid); break; } out: @@ -1902,7 +1840,7 @@ struct proto tcpv6_prot = { .sendpage = tcp_sendpage, .backlog_rcv = tcp_v6_do_rcv, .release_cb = tcp_release_cb, - .hash = tcp_v6_hash, + .hash = inet_hash, .unhash = inet_unhash, .get_port = inet_csk_get_port, .enter_memory_pressure = tcp_enter_memory_pressure, diff --git a/net/ipv6/tcpv6_offload.c b/net/ipv6/tcpv6_offload.c index c1ab77105b4c..d883c9204c01 100644 --- a/net/ipv6/tcpv6_offload.c +++ b/net/ipv6/tcpv6_offload.c @@ -41,8 +41,8 @@ static int tcp6_gro_complete(struct sk_buff *skb, int thoff) return tcp_gro_complete(skb); } -struct sk_buff *tcp6_gso_segment(struct sk_buff *skb, - netdev_features_t features) +static struct sk_buff *tcp6_gso_segment(struct sk_buff *skb, + netdev_features_t features) { struct tcphdr *th; diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c index d048d46779fc..3477c919fcc8 100644 --- a/net/ipv6/udp.c +++ b/net/ipv6/udp.c @@ -53,11 +53,11 @@ #include <trace/events/skb.h> #include "udp_impl.h" -static unsigned int udp6_ehashfn(struct net *net, - const struct in6_addr *laddr, - const u16 lport, - const struct in6_addr *faddr, - const __be16 fport) +static u32 udp6_ehashfn(const struct net *net, + const struct in6_addr *laddr, + const u16 lport, + const struct in6_addr *faddr, + const __be16 fport) { static u32 udp6_ehash_secret __read_mostly; static u32 udp_ipv6_hash_secret __read_mostly; @@ -104,9 +104,9 @@ int ipv6_rcv_saddr_equal(const struct sock *sk, const struct sock *sk2) return 0; } -static unsigned int udp6_portaddr_hash(struct net *net, - const struct in6_addr *addr6, - unsigned int port) +static u32 udp6_portaddr_hash(const struct net *net, + const struct in6_addr *addr6, + unsigned int port) { unsigned int hash, mix = net_hash_mix(net); @@ -120,7 +120,6 @@ static unsigned int udp6_portaddr_hash(struct net *net, return hash ^ port; } - int udp_v6_get_port(struct sock *sk, unsigned short snum) { unsigned int hash2_nulladdr = @@ -385,14 +384,12 @@ struct sock *udp6_lib_lookup(struct net *net, const struct in6_addr *saddr, __be } EXPORT_SYMBOL_GPL(udp6_lib_lookup); - /* * This should be easy, if there is something there we * return it, otherwise we block. */ -int udpv6_recvmsg(struct kiocb *iocb, struct sock *sk, - struct msghdr *msg, size_t len, +int udpv6_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, int noblock, int flags, int *addr_len) { struct ipv6_pinfo *np = inet6_sk(sk); @@ -551,7 +548,7 @@ void __udp6_lib_err(struct sk_buff *skb, struct inet6_skb_parm *opt, sk = __udp6_lib_lookup(net, daddr, uh->dest, saddr, uh->source, inet6_iif(skb), udptable); - if (sk == NULL) { + if (!sk) { ICMP6_INC_STATS_BH(net, __in6_dev_get(skb->dev), ICMP6_MIB_INERRORS); return; @@ -649,7 +646,7 @@ int udpv6_queue_rcv_skb(struct sock *sk, struct sk_buff *skb) /* if we're overly short, let UDP handle it */ encap_rcv = ACCESS_ONCE(up->encap_rcv); - if (skb->len > sizeof(struct udphdr) && encap_rcv != NULL) { + if (skb->len > sizeof(struct udphdr) && encap_rcv) { int ret; /* Verify checksum before giving to encap */ @@ -750,7 +747,7 @@ static void flush_stack(struct sock **stack, unsigned int count, for (i = 0; i < count; i++) { sk = stack[i]; - if (likely(skb1 == NULL)) + if (likely(!skb1)) skb1 = (i == final) ? skb : skb_clone(skb, GFP_ATOMIC); if (!skb1) { atomic_inc(&sk->sk_drops); @@ -900,7 +897,7 @@ int __udp6_lib_rcv(struct sk_buff *skb, struct udp_table *udptable, * for sock caches... i'll skip this for now. */ sk = __udp6_lib_lookup_skb(skb, uh->source, uh->dest, udptable); - if (sk != NULL) { + if (sk) { int ret; if (!uh->check && !udp_sk(sk)->no_check6_rx) { @@ -1101,8 +1098,7 @@ out: return err; } -int udpv6_sendmsg(struct kiocb *iocb, struct sock *sk, - struct msghdr *msg, size_t len) +int udpv6_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) { struct ipv6_txoptions opt_space; struct udp_sock *up = udp_sk(sk); @@ -1164,12 +1160,12 @@ int udpv6_sendmsg(struct kiocb *iocb, struct sock *sk, do_udp_sendmsg: if (__ipv6_only_sock(sk)) return -ENETUNREACH; - return udp_sendmsg(iocb, sk, msg, len); + return udp_sendmsg(sk, msg, len); } } if (up->pending == AF_INET) - return udp_sendmsg(iocb, sk, msg, len); + return udp_sendmsg(sk, msg, len); /* Rough check on arithmetic overflow, better check is made in ip6_append_data(). @@ -1209,7 +1205,7 @@ do_udp_sendmsg: fl6.flowlabel = sin6->sin6_flowinfo&IPV6_FLOWINFO_MASK; if (fl6.flowlabel&IPV6_FLOWLABEL_MASK) { flowlabel = fl6_sock_lookup(sk, fl6.flowlabel); - if (flowlabel == NULL) + if (!flowlabel) return -EINVAL; } } @@ -1257,14 +1253,14 @@ do_udp_sendmsg: } if ((fl6.flowlabel&IPV6_FLOWLABEL_MASK) && !flowlabel) { flowlabel = fl6_sock_lookup(sk, fl6.flowlabel); - if (flowlabel == NULL) + if (!flowlabel) return -EINVAL; } if (!(opt->opt_nflen|opt->opt_flen)) opt = NULL; connected = 0; } - if (opt == NULL) + if (!opt) opt = np->opt; if (flowlabel) opt = fl6_merge_options(&opt_space, flowlabel, opt); @@ -1557,7 +1553,6 @@ static struct inet_protosw udpv6_protosw = { .flags = INET_PROTOSW_PERMANENT, }; - int __init udpv6_init(void) { int ret; diff --git a/net/ipv6/udp_impl.h b/net/ipv6/udp_impl.h index c779c3c90b9d..0682c031ccdc 100644 --- a/net/ipv6/udp_impl.h +++ b/net/ipv6/udp_impl.h @@ -23,10 +23,9 @@ int compat_udpv6_setsockopt(struct sock *sk, int level, int optname, int compat_udpv6_getsockopt(struct sock *sk, int level, int optname, char __user *optval, int __user *optlen); #endif -int udpv6_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg, - size_t len); -int udpv6_recvmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg, - size_t len, int noblock, int flags, int *addr_len); +int udpv6_sendmsg(struct sock *sk, struct msghdr *msg, size_t len); +int udpv6_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, int noblock, + int flags, int *addr_len); int udpv6_queue_rcv_skb(struct sock *sk, struct sk_buff *skb); void udpv6_destroy_sock(struct sock *sk); diff --git a/net/ipv6/udp_offload.c b/net/ipv6/udp_offload.c index be2c0ba82c85..7441e1e63893 100644 --- a/net/ipv6/udp_offload.c +++ b/net/ipv6/udp_offload.c @@ -54,7 +54,7 @@ static struct sk_buff *udp6_ufo_fragment(struct sk_buff *skb, /* Set the IPv6 fragment id if not set yet */ if (!skb_shinfo(skb)->ip6_frag_id) - ipv6_proxy_select_ident(skb); + ipv6_proxy_select_ident(dev_net(skb->dev), skb); segs = NULL; goto out; @@ -113,7 +113,7 @@ static struct sk_buff *udp6_ufo_fragment(struct sk_buff *skb, fptr->nexthdr = nexthdr; fptr->reserved = 0; if (!skb_shinfo(skb)->ip6_frag_id) - ipv6_proxy_select_ident(skb); + ipv6_proxy_select_ident(dev_net(skb->dev), skb); fptr->identification = skb_shinfo(skb)->ip6_frag_id; /* Fragment the skb. ipv6 header and the remaining fields of the diff --git a/net/ipv6/xfrm6_input.c b/net/ipv6/xfrm6_input.c index f48fbe4d16f5..74bd17882a2f 100644 --- a/net/ipv6/xfrm6_input.c +++ b/net/ipv6/xfrm6_input.c @@ -42,7 +42,8 @@ int xfrm6_transport_finish(struct sk_buff *skb, int async) ipv6_hdr(skb)->payload_len = htons(skb->len); __skb_push(skb, skb->data - skb_network_header(skb)); - NF_HOOK(NFPROTO_IPV6, NF_INET_PRE_ROUTING, skb, skb->dev, NULL, + NF_HOOK(NFPROTO_IPV6, NF_INET_PRE_ROUTING, NULL, skb, + skb->dev, NULL, ip6_rcv_finish); return -1; } diff --git a/net/ipv6/xfrm6_mode_beet.c b/net/ipv6/xfrm6_mode_beet.c index 9949a356d62c..1e205c3253ac 100644 --- a/net/ipv6/xfrm6_mode_beet.c +++ b/net/ipv6/xfrm6_mode_beet.c @@ -95,8 +95,8 @@ static int xfrm6_beet_input(struct xfrm_state *x, struct sk_buff *skb) ip6h = ipv6_hdr(skb); ip6h->payload_len = htons(skb->len - size); - ip6h->daddr = *(struct in6_addr *)&x->sel.daddr.a6; - ip6h->saddr = *(struct in6_addr *)&x->sel.saddr.a6; + ip6h->daddr = x->sel.daddr.in6; + ip6h->saddr = x->sel.saddr.in6; err = 0; out: return err; diff --git a/net/ipv6/xfrm6_output.c b/net/ipv6/xfrm6_output.c index 010f8bd2d577..09c76a7b474d 100644 --- a/net/ipv6/xfrm6_output.c +++ b/net/ipv6/xfrm6_output.c @@ -120,7 +120,7 @@ int xfrm6_prepare_output(struct xfrm_state *x, struct sk_buff *skb) } EXPORT_SYMBOL(xfrm6_prepare_output); -int xfrm6_output_finish(struct sk_buff *skb) +int xfrm6_output_finish(struct sock *sk, struct sk_buff *skb) { memset(IP6CB(skb), 0, sizeof(*IP6CB(skb))); @@ -128,10 +128,10 @@ int xfrm6_output_finish(struct sk_buff *skb) IP6CB(skb)->flags |= IP6SKB_XFRM_TRANSFORMED; #endif - return xfrm_output(skb); + return xfrm_output(sk, skb); } -static int __xfrm6_output(struct sk_buff *skb) +static int __xfrm6_output(struct sock *sk, struct sk_buff *skb) { struct dst_entry *dst = skb_dst(skb); struct xfrm_state *x = dst->xfrm; @@ -140,7 +140,7 @@ static int __xfrm6_output(struct sk_buff *skb) #ifdef CONFIG_NETFILTER if (!x) { IP6CB(skb)->flags |= IP6SKB_REROUTED; - return dst_output(skb); + return dst_output_sk(sk, skb); } #endif @@ -160,14 +160,15 @@ static int __xfrm6_output(struct sk_buff *skb) if (x->props.mode == XFRM_MODE_TUNNEL && ((skb->len > mtu && !skb_is_gso(skb)) || dst_allfrag(skb_dst(skb)))) { - return ip6_fragment(skb, x->outer_mode->afinfo->output_finish); + return ip6_fragment(sk, skb, + x->outer_mode->afinfo->output_finish); } - return x->outer_mode->afinfo->output_finish(skb); + return x->outer_mode->afinfo->output_finish(sk, skb); } int xfrm6_output(struct sock *sk, struct sk_buff *skb) { - return NF_HOOK_COND(NFPROTO_IPV6, NF_INET_POST_ROUTING, skb, + return NF_HOOK_COND(NFPROTO_IPV6, NF_INET_POST_ROUTING, sk, skb, NULL, skb_dst(skb)->dev, __xfrm6_output, !(IP6CB(skb)->flags & IP6SKB_REROUTED)); } diff --git a/net/ipv6/xfrm6_policy.c b/net/ipv6/xfrm6_policy.c index 8d2d01b4800a..f337a908a76a 100644 --- a/net/ipv6/xfrm6_policy.c +++ b/net/ipv6/xfrm6_policy.c @@ -61,9 +61,7 @@ static int xfrm6_get_saddr(struct net *net, return -EHOSTUNREACH; dev = ip6_dst_idev(dst)->dev; - ipv6_dev_get_saddr(dev_net(dev), dev, - (struct in6_addr *)&daddr->a6, 0, - (struct in6_addr *)&saddr->a6); + ipv6_dev_get_saddr(dev_net(dev), dev, &daddr->in6, 0, &saddr->in6); dst_release(dst); return 0; } @@ -293,7 +291,6 @@ static void xfrm6_dst_ifdown(struct dst_entry *dst, struct net_device *dev, static struct dst_ops xfrm6_dst_ops = { .family = AF_INET6, - .protocol = cpu_to_be16(ETH_P_IPV6), .gc = xfrm6_garbage_collect, .update_pmtu = xfrm6_update_pmtu, .redirect = xfrm6_redirect, @@ -371,7 +368,7 @@ static void __net_exit xfrm6_net_exit(struct net *net) { struct ctl_table *table; - if (net->ipv6.sysctl.xfrm6_hdr == NULL) + if (!net->ipv6.sysctl.xfrm6_hdr) return; table = net->ipv6.sysctl.xfrm6_hdr->ctl_table_arg; diff --git a/net/ipx/af_ipx.c b/net/ipx/af_ipx.c index f11ad1d95e0e..4ea5d7497b5f 100644 --- a/net/ipx/af_ipx.c +++ b/net/ipx/af_ipx.c @@ -1688,8 +1688,7 @@ out: return rc; } -static int ipx_sendmsg(struct kiocb *iocb, struct socket *sock, - struct msghdr *msg, size_t len) +static int ipx_sendmsg(struct socket *sock, struct msghdr *msg, size_t len) { struct sock *sk = sock->sk; struct ipx_sock *ipxs = ipx_sk(sk); @@ -1754,8 +1753,8 @@ out: } -static int ipx_recvmsg(struct kiocb *iocb, struct socket *sock, - struct msghdr *msg, size_t size, int flags) +static int ipx_recvmsg(struct socket *sock, struct msghdr *msg, size_t size, + int flags) { struct sock *sk = sock->sk; struct ipx_sock *ipxs = ipx_sk(sk); diff --git a/net/irda/af_irda.c b/net/irda/af_irda.c index 568edc72d737..ee0ea25c8e7a 100644 --- a/net/irda/af_irda.c +++ b/net/irda/af_irda.c @@ -1256,14 +1256,13 @@ static int irda_release(struct socket *sock) } /* - * Function irda_sendmsg (iocb, sock, msg, len) + * Function irda_sendmsg (sock, msg, len) * * Send message down to TinyTP. This function is used for both STREAM and * SEQPACK services. This is possible since it forces the client to * fragment the message if necessary */ -static int irda_sendmsg(struct kiocb *iocb, struct socket *sock, - struct msghdr *msg, size_t len) +static int irda_sendmsg(struct socket *sock, struct msghdr *msg, size_t len) { struct sock *sk = sock->sk; struct irda_sock *self; @@ -1348,13 +1347,13 @@ out: } /* - * Function irda_recvmsg_dgram (iocb, sock, msg, size, flags) + * Function irda_recvmsg_dgram (sock, msg, size, flags) * * Try to receive message and copy it to user. The frame is discarded * after being read, regardless of how much the user actually read */ -static int irda_recvmsg_dgram(struct kiocb *iocb, struct socket *sock, - struct msghdr *msg, size_t size, int flags) +static int irda_recvmsg_dgram(struct socket *sock, struct msghdr *msg, + size_t size, int flags) { struct sock *sk = sock->sk; struct irda_sock *self = irda_sk(sk); @@ -1398,10 +1397,10 @@ static int irda_recvmsg_dgram(struct kiocb *iocb, struct socket *sock, } /* - * Function irda_recvmsg_stream (iocb, sock, msg, size, flags) + * Function irda_recvmsg_stream (sock, msg, size, flags) */ -static int irda_recvmsg_stream(struct kiocb *iocb, struct socket *sock, - struct msghdr *msg, size_t size, int flags) +static int irda_recvmsg_stream(struct socket *sock, struct msghdr *msg, + size_t size, int flags) { struct sock *sk = sock->sk; struct irda_sock *self = irda_sk(sk); @@ -1515,14 +1514,14 @@ static int irda_recvmsg_stream(struct kiocb *iocb, struct socket *sock, } /* - * Function irda_sendmsg_dgram (iocb, sock, msg, len) + * Function irda_sendmsg_dgram (sock, msg, len) * * Send message down to TinyTP for the unreliable sequenced * packet service... * */ -static int irda_sendmsg_dgram(struct kiocb *iocb, struct socket *sock, - struct msghdr *msg, size_t len) +static int irda_sendmsg_dgram(struct socket *sock, struct msghdr *msg, + size_t len) { struct sock *sk = sock->sk; struct irda_sock *self; @@ -1594,14 +1593,14 @@ out: } /* - * Function irda_sendmsg_ultra (iocb, sock, msg, len) + * Function irda_sendmsg_ultra (sock, msg, len) * * Send message down to IrLMP for the unreliable Ultra * packet service... */ #ifdef CONFIG_IRDA_ULTRA -static int irda_sendmsg_ultra(struct kiocb *iocb, struct socket *sock, - struct msghdr *msg, size_t len) +static int irda_sendmsg_ultra(struct socket *sock, struct msghdr *msg, + size_t len) { struct sock *sk = sock->sk; struct irda_sock *self; diff --git a/net/iucv/af_iucv.c b/net/iucv/af_iucv.c index 53d931172088..6daa52a18d40 100644 --- a/net/iucv/af_iucv.c +++ b/net/iucv/af_iucv.c @@ -1026,8 +1026,8 @@ static int iucv_send_iprm(struct iucv_path *path, struct iucv_message *msg, (void *) prmdata, 8); } -static int iucv_sock_sendmsg(struct kiocb *iocb, struct socket *sock, - struct msghdr *msg, size_t len) +static int iucv_sock_sendmsg(struct socket *sock, struct msghdr *msg, + size_t len) { struct sock *sk = sock->sk; struct iucv_sock *iucv = iucv_sk(sk); @@ -1315,8 +1315,8 @@ static void iucv_process_message_q(struct sock *sk) } } -static int iucv_sock_recvmsg(struct kiocb *iocb, struct socket *sock, - struct msghdr *msg, size_t len, int flags) +static int iucv_sock_recvmsg(struct socket *sock, struct msghdr *msg, + size_t len, int flags) { int noblock = flags & MSG_DONTWAIT; struct sock *sk = sock->sk; diff --git a/net/key/af_key.c b/net/key/af_key.c index f8ac939d52b4..f0d52d721b3a 100644 --- a/net/key/af_key.c +++ b/net/key/af_key.c @@ -709,7 +709,7 @@ static unsigned int pfkey_sockaddr_fill(const xfrm_address_t *xaddr, __be16 port sin6->sin6_family = AF_INET6; sin6->sin6_port = port; sin6->sin6_flowinfo = 0; - sin6->sin6_addr = *(struct in6_addr *)xaddr->a6; + sin6->sin6_addr = xaddr->in6; sin6->sin6_scope_id = 0; return 128; } @@ -3588,8 +3588,7 @@ static int pfkey_send_migrate(const struct xfrm_selector *sel, u8 dir, u8 type, } #endif -static int pfkey_sendmsg(struct kiocb *kiocb, - struct socket *sock, struct msghdr *msg, size_t len) +static int pfkey_sendmsg(struct socket *sock, struct msghdr *msg, size_t len) { struct sock *sk = sock->sk; struct sk_buff *skb = NULL; @@ -3630,8 +3629,7 @@ out: return err ? : len; } -static int pfkey_recvmsg(struct kiocb *kiocb, - struct socket *sock, struct msghdr *msg, size_t len, +static int pfkey_recvmsg(struct socket *sock, struct msghdr *msg, size_t len, int flags) { struct sock *sk = sock->sk; diff --git a/net/l2tp/l2tp_eth.c b/net/l2tp/l2tp_eth.c index 781b3a226ba7..4b552873b556 100644 --- a/net/l2tp/l2tp_eth.c +++ b/net/l2tp/l2tp_eth.c @@ -74,7 +74,7 @@ static int l2tp_eth_dev_init(struct net_device *dev) priv->dev = dev; eth_hw_addr_random(dev); - memset(&dev->broadcast[0], 0xff, 6); + eth_broadcast_addr(dev->broadcast); dev->qdisc_tx_busylock = &l2tp_eth_tx_busylock; return 0; } diff --git a/net/l2tp/l2tp_ip.c b/net/l2tp/l2tp_ip.c index 05dfc8aa36af..79649937ec71 100644 --- a/net/l2tp/l2tp_ip.c +++ b/net/l2tp/l2tp_ip.c @@ -385,7 +385,7 @@ drop: /* Userspace will call sendmsg() on the tunnel socket to send L2TP * control frames. */ -static int l2tp_ip_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg, size_t len) +static int l2tp_ip_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) { struct sk_buff *skb; int rc; @@ -506,7 +506,7 @@ no_route: goto out; } -static int l2tp_ip_recvmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg, +static int l2tp_ip_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, int noblock, int flags, int *addr_len) { struct inet_sock *inet = inet_sk(sk); diff --git a/net/l2tp/l2tp_ip6.c b/net/l2tp/l2tp_ip6.c index 8611f1b63141..d1ded3777815 100644 --- a/net/l2tp/l2tp_ip6.c +++ b/net/l2tp/l2tp_ip6.c @@ -480,8 +480,7 @@ out: /* Userspace will call sendmsg() on the tunnel socket to send L2TP * control frames. */ -static int l2tp_ip6_sendmsg(struct kiocb *iocb, struct sock *sk, - struct msghdr *msg, size_t len) +static int l2tp_ip6_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) { struct ipv6_txoptions opt_space; DECLARE_SOCKADDR(struct sockaddr_l2tpip6 *, lsa, msg->msg_name); @@ -643,9 +642,8 @@ do_confirm: goto done; } -static int l2tp_ip6_recvmsg(struct kiocb *iocb, struct sock *sk, - struct msghdr *msg, size_t len, int noblock, - int flags, int *addr_len) +static int l2tp_ip6_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, + int noblock, int flags, int *addr_len) { struct ipv6_pinfo *np = inet6_sk(sk); DECLARE_SOCKADDR(struct sockaddr_l2tpip6 *, lsa, msg->msg_name); diff --git a/net/l2tp/l2tp_netlink.c b/net/l2tp/l2tp_netlink.c index b4e923f77954..9e13c2ff8789 100644 --- a/net/l2tp/l2tp_netlink.c +++ b/net/l2tp/l2tp_netlink.c @@ -205,9 +205,9 @@ static int l2tp_nl_cmd_tunnel_create(struct sk_buff *skb, struct genl_info *info #endif if (info->attrs[L2TP_ATTR_IP_SADDR] && info->attrs[L2TP_ATTR_IP_DADDR]) { - cfg.local_ip.s_addr = nla_get_be32( + cfg.local_ip.s_addr = nla_get_in_addr( info->attrs[L2TP_ATTR_IP_SADDR]); - cfg.peer_ip.s_addr = nla_get_be32( + cfg.peer_ip.s_addr = nla_get_in_addr( info->attrs[L2TP_ATTR_IP_DADDR]); } else { ret = -EINVAL; @@ -376,15 +376,17 @@ static int l2tp_nl_tunnel_send(struct sk_buff *skb, u32 portid, u32 seq, int fla case L2TP_ENCAPTYPE_IP: #if IS_ENABLED(CONFIG_IPV6) if (np) { - if (nla_put(skb, L2TP_ATTR_IP6_SADDR, sizeof(np->saddr), - &np->saddr) || - nla_put(skb, L2TP_ATTR_IP6_DADDR, sizeof(sk->sk_v6_daddr), - &sk->sk_v6_daddr)) + if (nla_put_in6_addr(skb, L2TP_ATTR_IP6_SADDR, + &np->saddr) || + nla_put_in6_addr(skb, L2TP_ATTR_IP6_DADDR, + &sk->sk_v6_daddr)) goto nla_put_failure; } else #endif - if (nla_put_be32(skb, L2TP_ATTR_IP_SADDR, inet->inet_saddr) || - nla_put_be32(skb, L2TP_ATTR_IP_DADDR, inet->inet_daddr)) + if (nla_put_in_addr(skb, L2TP_ATTR_IP_SADDR, + inet->inet_saddr) || + nla_put_in_addr(skb, L2TP_ATTR_IP_DADDR, + inet->inet_daddr)) goto nla_put_failure; break; } diff --git a/net/l2tp/l2tp_ppp.c b/net/l2tp/l2tp_ppp.c index cc7a828fc914..e9b0dec56b8e 100644 --- a/net/l2tp/l2tp_ppp.c +++ b/net/l2tp/l2tp_ppp.c @@ -185,9 +185,8 @@ static int pppol2tp_recv_payload_hook(struct sk_buff *skb) /* Receive message. This is the recvmsg for the PPPoL2TP socket. */ -static int pppol2tp_recvmsg(struct kiocb *iocb, struct socket *sock, - struct msghdr *msg, size_t len, - int flags) +static int pppol2tp_recvmsg(struct socket *sock, struct msghdr *msg, + size_t len, int flags) { int err; struct sk_buff *skb; @@ -295,7 +294,7 @@ static void pppol2tp_session_sock_put(struct l2tp_session *session) * when a user application does a sendmsg() on the session socket. L2TP and * PPP headers must be inserted into the user's data. */ -static int pppol2tp_sendmsg(struct kiocb *iocb, struct socket *sock, struct msghdr *m, +static int pppol2tp_sendmsg(struct socket *sock, struct msghdr *m, size_t total_len) { static const unsigned char ppph[2] = { 0xff, 0x03 }; diff --git a/net/llc/af_llc.c b/net/llc/af_llc.c index 2c0b83ce43bd..17a8dff06090 100644 --- a/net/llc/af_llc.c +++ b/net/llc/af_llc.c @@ -704,8 +704,8 @@ out: * Copy received data to the socket user. * Returns non-negative upon success, negative otherwise. */ -static int llc_ui_recvmsg(struct kiocb *iocb, struct socket *sock, - struct msghdr *msg, size_t len, int flags) +static int llc_ui_recvmsg(struct socket *sock, struct msghdr *msg, size_t len, + int flags) { DECLARE_SOCKADDR(struct sockaddr_llc *, uaddr, msg->msg_name); const int nonblock = flags & MSG_DONTWAIT; @@ -878,8 +878,7 @@ copy_uaddr: * Transmit data provided by the socket user. * Returns non-negative upon success, negative otherwise. */ -static int llc_ui_sendmsg(struct kiocb *iocb, struct socket *sock, - struct msghdr *msg, size_t len) +static int llc_ui_sendmsg(struct socket *sock, struct msghdr *msg, size_t len) { struct sock *sk = sock->sk; struct llc_sock *llc = llc_sk(sk); diff --git a/net/mac80211/aes_ccm.c b/net/mac80211/aes_ccm.c index 7869bb40acaa..208df7c0b6ea 100644 --- a/net/mac80211/aes_ccm.c +++ b/net/mac80211/aes_ccm.c @@ -85,11 +85,15 @@ struct crypto_aead *ieee80211_aes_key_setup_encrypt(const u8 key[], return tfm; err = crypto_aead_setkey(tfm, key, key_len); - if (!err) - err = crypto_aead_setauthsize(tfm, mic_len); - if (!err) - return tfm; + if (err) + goto free_aead; + err = crypto_aead_setauthsize(tfm, mic_len); + if (err) + goto free_aead; + + return tfm; +free_aead: crypto_free_aead(tfm); return ERR_PTR(err); } diff --git a/net/mac80211/aes_gcm.c b/net/mac80211/aes_gcm.c index c2bf6698d738..fd278bbe1b0d 100644 --- a/net/mac80211/aes_gcm.c +++ b/net/mac80211/aes_gcm.c @@ -80,11 +80,15 @@ struct crypto_aead *ieee80211_aes_gcm_key_setup_encrypt(const u8 key[], return tfm; err = crypto_aead_setkey(tfm, key, key_len); - if (!err) - err = crypto_aead_setauthsize(tfm, IEEE80211_GCMP_MIC_LEN); - if (!err) - return tfm; + if (err) + goto free_aead; + err = crypto_aead_setauthsize(tfm, IEEE80211_GCMP_MIC_LEN); + if (err) + goto free_aead; + + return tfm; +free_aead: crypto_free_aead(tfm); return ERR_PTR(err); } diff --git a/net/mac80211/aes_gmac.c b/net/mac80211/aes_gmac.c index 1c72edcb0083..f1321b7d6506 100644 --- a/net/mac80211/aes_gmac.c +++ b/net/mac80211/aes_gmac.c @@ -70,9 +70,9 @@ struct crypto_aead *ieee80211_aes_gmac_key_setup(const u8 key[], err = crypto_aead_setkey(tfm, key, key_len); if (!err) - return tfm; - if (!err) err = crypto_aead_setauthsize(tfm, GMAC_MIC_LEN); + if (!err) + return tfm; crypto_free_aead(tfm); return ERR_PTR(err); diff --git a/net/mac80211/agg-rx.c b/net/mac80211/agg-rx.c index 7702978a4c99..5c564a68fb50 100644 --- a/net/mac80211/agg-rx.c +++ b/net/mac80211/agg-rx.c @@ -238,6 +238,14 @@ void __ieee80211_start_rx_ba_session(struct sta_info *sta, int i, ret = -EOPNOTSUPP; u16 status = WLAN_STATUS_REQUEST_DECLINED; + if (!sta->sta.ht_cap.ht_supported) { + ht_dbg(sta->sdata, + "STA %pM erroneously requests BA session on tid %d w/o QoS\n", + sta->sta.addr, tid); + /* send a response anyway, it's an error case if we get here */ + goto end_no_lock; + } + if (test_sta_flag(sta, WLAN_STA_BLOCK_BA)) { ht_dbg(sta->sdata, "Suspend in progress - Denying ADDBA request (%pM tid %d)\n", diff --git a/net/mac80211/agg-tx.c b/net/mac80211/agg-tx.c index a360c15cc978..cce9d425c718 100644 --- a/net/mac80211/agg-tx.c +++ b/net/mac80211/agg-tx.c @@ -188,6 +188,43 @@ ieee80211_wake_queue_agg(struct ieee80211_sub_if_data *sdata, int tid) __release(agg_queue); } +static void +ieee80211_agg_stop_txq(struct sta_info *sta, int tid) +{ + struct ieee80211_txq *txq = sta->sta.txq[tid]; + struct txq_info *txqi; + + if (!txq) + return; + + txqi = to_txq_info(txq); + + /* Lock here to protect against further seqno updates on dequeue */ + spin_lock_bh(&txqi->queue.lock); + set_bit(IEEE80211_TXQ_STOP, &txqi->flags); + spin_unlock_bh(&txqi->queue.lock); +} + +static void +ieee80211_agg_start_txq(struct sta_info *sta, int tid, bool enable) +{ + struct ieee80211_txq *txq = sta->sta.txq[tid]; + struct txq_info *txqi; + + if (!txq) + return; + + txqi = to_txq_info(txq); + + if (enable) + set_bit(IEEE80211_TXQ_AMPDU, &txqi->flags); + else + clear_bit(IEEE80211_TXQ_AMPDU, &txqi->flags); + + clear_bit(IEEE80211_TXQ_STOP, &txqi->flags); + drv_wake_tx_queue(sta->sdata->local, txqi); +} + /* * splice packets from the STA's pending to the local pending, * requires a call to ieee80211_agg_splice_finish later @@ -247,6 +284,7 @@ static void ieee80211_remove_tid_tx(struct sta_info *sta, int tid) ieee80211_assign_tid_tx(sta, tid, NULL); ieee80211_agg_splice_finish(sta->sdata, tid); + ieee80211_agg_start_txq(sta, tid, false); kfree_rcu(tid_tx, rcu_head); } @@ -418,6 +456,8 @@ void ieee80211_tx_ba_session_handle_start(struct sta_info *sta, int tid) */ clear_bit(HT_AGG_STATE_WANT_START, &tid_tx->state); + ieee80211_agg_stop_txq(sta, tid); + /* * Make sure no packets are being processed. This ensures that * we have a valid starting sequence number and that in-flight @@ -440,6 +480,8 @@ void ieee80211_tx_ba_session_handle_start(struct sta_info *sta, int tid) ieee80211_agg_splice_finish(sdata, tid); spin_unlock_bh(&sta->lock); + ieee80211_agg_start_txq(sta, tid, false); + kfree_rcu(tid_tx, rcu_head); return; } @@ -509,11 +551,14 @@ int ieee80211_start_tx_ba_session(struct ieee80211_sta *pubsta, u16 tid, struct tid_ampdu_tx *tid_tx; int ret = 0; + trace_api_start_tx_ba_session(pubsta, tid); + if (WARN(sta->reserved_tid == tid, "Requested to start BA session on reserved tid=%d", tid)) return -EINVAL; - trace_api_start_tx_ba_session(pubsta, tid); + if (!pubsta->ht_cap.ht_supported) + return -EINVAL; if (WARN_ON_ONCE(!local->ops->ampdu_action)) return -EINVAL; @@ -666,6 +711,8 @@ static void ieee80211_agg_tx_operational(struct ieee80211_local *local, ieee80211_agg_splice_finish(sta->sdata, tid); spin_unlock_bh(&sta->lock); + + ieee80211_agg_start_txq(sta, tid, true); } void ieee80211_start_tx_ba_cb(struct ieee80211_vif *vif, u8 *ra, u16 tid) @@ -793,6 +840,7 @@ void ieee80211_stop_tx_ba_cb(struct ieee80211_vif *vif, u8 *ra, u8 tid) struct ieee80211_local *local = sdata->local; struct sta_info *sta; struct tid_ampdu_tx *tid_tx; + bool send_delba = false; trace_api_stop_tx_ba_cb(sdata, ra, tid); @@ -824,13 +872,17 @@ void ieee80211_stop_tx_ba_cb(struct ieee80211_vif *vif, u8 *ra, u8 tid) } if (tid_tx->stop_initiator == WLAN_BACK_INITIATOR && tid_tx->tx_stop) - ieee80211_send_delba(sta->sdata, ra, tid, - WLAN_BACK_INITIATOR, WLAN_REASON_QSTA_NOT_USE); + send_delba = true; ieee80211_remove_tid_tx(sta, tid); unlock_sta: spin_unlock_bh(&sta->lock); + + if (send_delba) + ieee80211_send_delba(sdata, ra, tid, + WLAN_BACK_INITIATOR, WLAN_REASON_QSTA_NOT_USE); + mutex_unlock(&sta->ampdu_mlme.mtx); unlock: mutex_unlock(&local->sta_mtx); diff --git a/net/mac80211/cfg.c b/net/mac80211/cfg.c index dd4ff36c557a..265e42721a66 100644 --- a/net/mac80211/cfg.c +++ b/net/mac80211/cfg.c @@ -24,6 +24,7 @@ static struct wireless_dev *ieee80211_add_iface(struct wiphy *wiphy, const char *name, + unsigned char name_assign_type, enum nl80211_iftype type, u32 *flags, struct vif_params *params) @@ -33,7 +34,7 @@ static struct wireless_dev *ieee80211_add_iface(struct wiphy *wiphy, struct ieee80211_sub_if_data *sdata; int err; - err = ieee80211_if_add(local, name, &wdev, type, params); + err = ieee80211_if_add(local, name, name_assign_type, &wdev, type, params); if (err) return ERR_PTR(err); @@ -977,6 +978,14 @@ static int sta_apply_auth_flags(struct ieee80211_local *local, if (mask & BIT(NL80211_STA_FLAG_ASSOCIATED) && set & BIT(NL80211_STA_FLAG_ASSOCIATED) && !test_sta_flag(sta, WLAN_STA_ASSOC)) { + /* + * When peer becomes associated, init rate control as + * well. Some drivers require rate control initialized + * before drv_sta_state() is called. + */ + if (test_sta_flag(sta, WLAN_STA_TDLS_PEER)) + rate_control_rate_init(sta); + ret = sta_info_move_state(sta, IEEE80211_STA_ASSOC); if (ret) return ret; @@ -1050,6 +1059,10 @@ static int sta_apply_parameters(struct ieee80211_local *local, } } + if (mask & BIT(NL80211_STA_FLAG_WME) && + local->hw.queues >= IEEE80211_NUM_ACS) + sta->sta.wme = set & BIT(NL80211_STA_FLAG_WME); + /* 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); @@ -1064,10 +1077,8 @@ static int sta_apply_parameters(struct ieee80211_local *local, clear_sta_flag(sta, WLAN_STA_SHORT_PREAMBLE); } - if (mask & BIT(NL80211_STA_FLAG_WME)) - sta->sta.wme = set & BIT(NL80211_STA_FLAG_WME); - if (mask & BIT(NL80211_STA_FLAG_MFP)) { + sta->sta.mfp = !!(set & BIT(NL80211_STA_FLAG_MFP)); if (set & BIT(NL80211_STA_FLAG_MFP)) set_sta_flag(sta, WLAN_STA_MFP); else @@ -1377,11 +1388,6 @@ static int ieee80211_change_station(struct wiphy *wiphy, if (err) goto out_err; - /* When peer becomes authorized, init rate control as well */ - if (test_sta_flag(sta, WLAN_STA_TDLS_PEER) && - test_sta_flag(sta, WLAN_STA_AUTHORIZED)) - rate_control_rate_init(sta); - mutex_unlock(&local->sta_mtx); if ((sdata->vif.type == NL80211_IFTYPE_AP || @@ -1488,7 +1494,7 @@ static void mpath_set_pinfo(struct mesh_path *mpath, u8 *next_hop, if (next_hop_sta) memcpy(next_hop, next_hop_sta->sta.addr, ETH_ALEN); else - memset(next_hop, 0, ETH_ALEN); + eth_zero_addr(next_hop); memset(pinfo, 0, sizeof(*pinfo)); @@ -2273,7 +2279,6 @@ int __ieee80211_request_smps_ap(struct ieee80211_sub_if_data *sdata, { struct sta_info *sta; enum ieee80211_smps_mode old_req; - int i; if (WARN_ON_ONCE(sdata->vif.type != NL80211_IFTYPE_AP)) return -EINVAL; @@ -2297,52 +2302,44 @@ int __ieee80211_request_smps_ap(struct ieee80211_sub_if_data *sdata, } ht_dbg(sdata, - "SMSP %d requested in AP mode, sending Action frame to %d stations\n", + "SMPS %d requested in AP mode, sending Action frame to %d stations\n", smps_mode, atomic_read(&sdata->u.ap.num_mcast_sta)); mutex_lock(&sdata->local->sta_mtx); - for (i = 0; i < STA_HASH_SIZE; i++) { - for (sta = rcu_dereference_protected(sdata->local->sta_hash[i], - lockdep_is_held(&sdata->local->sta_mtx)); - sta; - sta = rcu_dereference_protected(sta->hnext, - lockdep_is_held(&sdata->local->sta_mtx))) { - /* - * Only stations associated to our AP and - * associated VLANs - */ - if (sta->sdata->bss != &sdata->u.ap) - continue; + list_for_each_entry(sta, &sdata->local->sta_list, list) { + /* + * Only stations associated to our AP and + * associated VLANs + */ + if (sta->sdata->bss != &sdata->u.ap) + continue; - /* This station doesn't support MIMO - skip it */ - if (sta_info_tx_streams(sta) == 1) - continue; + /* This station doesn't support MIMO - skip it */ + if (sta_info_tx_streams(sta) == 1) + continue; - /* - * Don't wake up a STA just to send the action frame - * unless we are getting more restrictive. - */ - if (test_sta_flag(sta, WLAN_STA_PS_STA) && - !ieee80211_smps_is_restrictive(sta->known_smps_mode, - smps_mode)) { - ht_dbg(sdata, - "Won't send SMPS to sleeping STA %pM\n", - sta->sta.addr); - continue; - } + /* + * Don't wake up a STA just to send the action frame + * unless we are getting more restrictive. + */ + if (test_sta_flag(sta, WLAN_STA_PS_STA) && + !ieee80211_smps_is_restrictive(sta->known_smps_mode, + smps_mode)) { + ht_dbg(sdata, "Won't send SMPS to sleeping STA %pM\n", + sta->sta.addr); + continue; + } - /* - * If the STA is not authorized, wait until it gets - * authorized and the action frame will be sent then. - */ - if (!test_sta_flag(sta, WLAN_STA_AUTHORIZED)) - continue; + /* + * If the STA is not authorized, wait until it gets + * authorized and the action frame will be sent then. + */ + if (!test_sta_flag(sta, WLAN_STA_AUTHORIZED)) + continue; - ht_dbg(sdata, "Sending SMPS to %pM\n", sta->sta.addr); - ieee80211_send_smps_action(sdata, smps_mode, - sta->sta.addr, - sdata->vif.bss_conf.bssid); - } + ht_dbg(sdata, "Sending SMPS to %pM\n", sta->sta.addr); + ieee80211_send_smps_action(sdata, smps_mode, sta->sta.addr, + sdata->vif.bss_conf.bssid); } mutex_unlock(&sdata->local->sta_mtx); @@ -3581,7 +3578,7 @@ static int ieee80211_probe_client(struct wiphy *wiphy, struct net_device *dev, nullfunc->qos_ctrl = cpu_to_le16(7); local_bh_disable(); - ieee80211_xmit(sdata, skb); + ieee80211_xmit(sdata, sta, skb); local_bh_enable(); rcu_read_unlock(); diff --git a/net/mac80211/debugfs.c b/net/mac80211/debugfs.c index eeb0bbd69d98..23813ebb349c 100644 --- a/net/mac80211/debugfs.c +++ b/net/mac80211/debugfs.c @@ -18,172 +18,6 @@ #define DEBUGFS_FORMAT_BUFFER_SIZE 100 -#define TX_LATENCY_BIN_DELIMTER_C ',' -#define TX_LATENCY_BIN_DELIMTER_S "," -#define TX_LATENCY_BINS_DISABLED "enable(bins disabled)\n" -#define TX_LATENCY_DISABLED "disable\n" - - -/* - * Display if Tx latency statistics & bins are enabled/disabled - */ -static ssize_t sta_tx_latency_stat_read(struct file *file, - char __user *userbuf, - size_t count, loff_t *ppos) -{ - struct ieee80211_local *local = file->private_data; - struct ieee80211_tx_latency_bin_ranges *tx_latency; - char *buf; - int bufsz, i, ret; - int pos = 0; - - rcu_read_lock(); - - tx_latency = rcu_dereference(local->tx_latency); - - if (tx_latency && tx_latency->n_ranges) { - bufsz = tx_latency->n_ranges * 15; - buf = kzalloc(bufsz, GFP_ATOMIC); - if (!buf) - goto err; - - for (i = 0; i < tx_latency->n_ranges; i++) - pos += scnprintf(buf + pos, bufsz - pos, "%d,", - tx_latency->ranges[i]); - pos += scnprintf(buf + pos, bufsz - pos, "\n"); - } else if (tx_latency) { - bufsz = sizeof(TX_LATENCY_BINS_DISABLED) + 1; - buf = kzalloc(bufsz, GFP_ATOMIC); - if (!buf) - goto err; - - pos += scnprintf(buf + pos, bufsz - pos, "%s\n", - TX_LATENCY_BINS_DISABLED); - } else { - bufsz = sizeof(TX_LATENCY_DISABLED) + 1; - buf = kzalloc(bufsz, GFP_ATOMIC); - if (!buf) - goto err; - - pos += scnprintf(buf + pos, bufsz - pos, "%s\n", - TX_LATENCY_DISABLED); - } - - rcu_read_unlock(); - - ret = simple_read_from_buffer(userbuf, count, ppos, buf, pos); - kfree(buf); - - return ret; -err: - rcu_read_unlock(); - return -ENOMEM; -} - -/* - * Receive input from user regarding Tx latency statistics - * The input should indicate if Tx latency statistics and bins are - * enabled/disabled. - * If bins are enabled input should indicate the amount of different bins and - * their ranges. Each bin will count how many Tx frames transmitted within the - * appropriate latency. - * Legal input is: - * a) "enable(bins disabled)" - to enable only general statistics - * b) "a,b,c,d,...z" - to enable general statistics and bins, where all are - * numbers and a < b < c < d.. < z - * c) "disable" - disable all statistics - * NOTE: must configure Tx latency statistics bins before stations connected. - */ - -static ssize_t sta_tx_latency_stat_write(struct file *file, - const char __user *userbuf, - size_t count, loff_t *ppos) -{ - struct ieee80211_local *local = file->private_data; - char buf[128] = {}; - char *bins = buf; - char *token; - int buf_size, i, alloc_size; - int prev_bin = 0; - int n_ranges = 0; - int ret = count; - struct ieee80211_tx_latency_bin_ranges *tx_latency; - - if (sizeof(buf) <= count) - return -EINVAL; - buf_size = count; - if (copy_from_user(buf, userbuf, buf_size)) - return -EFAULT; - - mutex_lock(&local->sta_mtx); - - /* cannot change config once we have stations */ - if (local->num_sta) - goto unlock; - - tx_latency = - rcu_dereference_protected(local->tx_latency, - lockdep_is_held(&local->sta_mtx)); - - /* disable Tx statistics */ - if (!strcmp(buf, TX_LATENCY_DISABLED)) { - if (!tx_latency) - goto unlock; - RCU_INIT_POINTER(local->tx_latency, NULL); - synchronize_rcu(); - kfree(tx_latency); - goto unlock; - } - - /* Tx latency already enabled */ - if (tx_latency) - goto unlock; - - if (strcmp(TX_LATENCY_BINS_DISABLED, buf)) { - /* check how many bins and between what ranges user requested */ - token = buf; - while (*token != '\0') { - if (*token == TX_LATENCY_BIN_DELIMTER_C) - n_ranges++; - token++; - } - n_ranges++; - } - - alloc_size = sizeof(struct ieee80211_tx_latency_bin_ranges) + - n_ranges * sizeof(u32); - tx_latency = kzalloc(alloc_size, GFP_ATOMIC); - if (!tx_latency) { - ret = -ENOMEM; - goto unlock; - } - tx_latency->n_ranges = n_ranges; - for (i = 0; i < n_ranges; i++) { /* setting bin ranges */ - token = strsep(&bins, TX_LATENCY_BIN_DELIMTER_S); - sscanf(token, "%d", &tx_latency->ranges[i]); - /* bins values should be in ascending order */ - if (prev_bin >= tx_latency->ranges[i]) { - ret = -EINVAL; - kfree(tx_latency); - goto unlock; - } - prev_bin = tx_latency->ranges[i]; - } - rcu_assign_pointer(local->tx_latency, tx_latency); - -unlock: - mutex_unlock(&local->sta_mtx); - - return ret; -} - -static const struct file_operations stats_tx_latency_ops = { - .write = sta_tx_latency_stat_write, - .read = sta_tx_latency_stat_read, - .open = simple_open, - .llseek = generic_file_llseek, -}; - int mac80211_format_buffer(char __user *userbuf, size_t count, loff_t *ppos, char *fmt, ...) { @@ -440,8 +274,6 @@ void debugfs_hw_add(struct ieee80211_local *local) #ifdef CONFIG_MAC80211_DEBUG_COUNTERS DEBUGFS_STATS_ADD(tx_handlers_drop, local->tx_handlers_drop); DEBUGFS_STATS_ADD(tx_handlers_queued, local->tx_handlers_queued); - DEBUGFS_STATS_ADD(tx_handlers_drop_unencrypted, - local->tx_handlers_drop_unencrypted); DEBUGFS_STATS_ADD(tx_handlers_drop_fragment, local->tx_handlers_drop_fragment); DEBUGFS_STATS_ADD(tx_handlers_drop_wep, @@ -475,6 +307,4 @@ void debugfs_hw_add(struct ieee80211_local *local) DEBUGFS_DEVSTATS_ADD(dot11RTSFailureCount); DEBUGFS_DEVSTATS_ADD(dot11FCSErrorCount); DEBUGFS_DEVSTATS_ADD(dot11RTSSuccessCount); - - DEBUGFS_DEVSTATS_ADD(tx_latency); } diff --git a/net/mac80211/debugfs_netdev.c b/net/mac80211/debugfs_netdev.c index c68896adfa96..29236e832e44 100644 --- a/net/mac80211/debugfs_netdev.c +++ b/net/mac80211/debugfs_netdev.c @@ -177,7 +177,6 @@ static ssize_t ieee80211_if_write_##name(struct file *file, \ IEEE80211_IF_FILE_R(name) /* common attributes */ -IEEE80211_IF_FILE(drop_unencrypted, drop_unencrypted, DEC); IEEE80211_IF_FILE(rc_rateidx_mask_2ghz, rc_rateidx_mask[IEEE80211_BAND_2GHZ], HEX); IEEE80211_IF_FILE(rc_rateidx_mask_5ghz, rc_rateidx_mask[IEEE80211_BAND_5GHZ], @@ -562,7 +561,6 @@ IEEE80211_IF_FILE(dot11MeshAwakeWindowDuration, static void add_common_files(struct ieee80211_sub_if_data *sdata) { - DEBUGFS_ADD(drop_unencrypted); DEBUGFS_ADD(rc_rateidx_mask_2ghz); DEBUGFS_ADD(rc_rateidx_mask_5ghz); DEBUGFS_ADD(rc_rateidx_mcs_mask_2ghz); diff --git a/net/mac80211/debugfs_sta.c b/net/mac80211/debugfs_sta.c index 94c70091bbd7..252859e90e8a 100644 --- a/net/mac80211/debugfs_sta.c +++ b/net/mac80211/debugfs_sta.c @@ -39,13 +39,6 @@ static const struct file_operations sta_ ##name## _ops = { \ .llseek = generic_file_llseek, \ } -#define STA_OPS_W(name) \ -static const struct file_operations sta_ ##name## _ops = { \ - .write = sta_##name##_write, \ - .open = simple_open, \ - .llseek = generic_file_llseek, \ -} - #define STA_OPS_RW(name) \ static const struct file_operations sta_ ##name## _ops = { \ .read = sta_##name##_read, \ @@ -398,131 +391,6 @@ static ssize_t sta_last_rx_rate_read(struct file *file, char __user *userbuf, } STA_OPS(last_rx_rate); -static int -sta_tx_latency_stat_header(struct ieee80211_tx_latency_bin_ranges *tx_latency, - char *buf, int pos, int bufsz) -{ - int i; - int range_count = tx_latency->n_ranges; - u32 *bin_ranges = tx_latency->ranges; - - pos += scnprintf(buf + pos, bufsz - pos, - "Station\t\t\tTID\tMax\tAvg"); - if (range_count) { - pos += scnprintf(buf + pos, bufsz - pos, - "\t<=%d", bin_ranges[0]); - for (i = 0; i < range_count - 1; i++) - pos += scnprintf(buf + pos, bufsz - pos, "\t%d-%d", - bin_ranges[i], bin_ranges[i+1]); - pos += scnprintf(buf + pos, bufsz - pos, - "\t%d<", bin_ranges[range_count - 1]); - } - - pos += scnprintf(buf + pos, bufsz - pos, "\n"); - - return pos; -} - -static int -sta_tx_latency_stat_table(struct ieee80211_tx_latency_bin_ranges *tx_lat_range, - struct ieee80211_tx_latency_stat *tx_lat, - char *buf, int pos, int bufsz, int tid) -{ - u32 avg = 0; - int j; - int bin_count = tx_lat->bin_count; - - pos += scnprintf(buf + pos, bufsz - pos, "\t\t\t%d", tid); - /* make sure you don't divide in 0 */ - if (tx_lat->counter) - avg = tx_lat->sum / tx_lat->counter; - - pos += scnprintf(buf + pos, bufsz - pos, "\t%d\t%d", - tx_lat->max, avg); - - if (tx_lat_range->n_ranges && tx_lat->bins) - for (j = 0; j < bin_count; j++) - pos += scnprintf(buf + pos, bufsz - pos, - "\t%d", tx_lat->bins[j]); - pos += scnprintf(buf + pos, bufsz - pos, "\n"); - - return pos; -} - -/* - * Output Tx latency statistics station && restart all statistics information - */ -static ssize_t sta_tx_latency_stat_read(struct file *file, - char __user *userbuf, - size_t count, loff_t *ppos) -{ - struct sta_info *sta = file->private_data; - struct ieee80211_local *local = sta->local; - struct ieee80211_tx_latency_bin_ranges *tx_latency; - char *buf; - int bufsz, ret, i; - int pos = 0; - - bufsz = 20 * IEEE80211_NUM_TIDS * - sizeof(struct ieee80211_tx_latency_stat); - buf = kzalloc(bufsz, GFP_KERNEL); - if (!buf) - return -ENOMEM; - - rcu_read_lock(); - - tx_latency = rcu_dereference(local->tx_latency); - - if (!sta->tx_lat) { - pos += scnprintf(buf + pos, bufsz - pos, - "Tx latency statistics are not enabled\n"); - goto unlock; - } - - pos = sta_tx_latency_stat_header(tx_latency, buf, pos, bufsz); - - pos += scnprintf(buf + pos, bufsz - pos, "%pM\n", sta->sta.addr); - for (i = 0; i < IEEE80211_NUM_TIDS; i++) - pos = sta_tx_latency_stat_table(tx_latency, &sta->tx_lat[i], - buf, pos, bufsz, i); -unlock: - rcu_read_unlock(); - - ret = simple_read_from_buffer(userbuf, count, ppos, buf, pos); - kfree(buf); - - return ret; -} -STA_OPS(tx_latency_stat); - -static ssize_t sta_tx_latency_stat_reset_write(struct file *file, - const char __user *userbuf, - size_t count, loff_t *ppos) -{ - u32 *bins; - int bin_count; - struct sta_info *sta = file->private_data; - int i; - - if (!sta->tx_lat) - return -EINVAL; - - for (i = 0; i < IEEE80211_NUM_TIDS; i++) { - bins = sta->tx_lat[i].bins; - bin_count = sta->tx_lat[i].bin_count; - - sta->tx_lat[i].max = 0; - sta->tx_lat[i].sum = 0; - sta->tx_lat[i].counter = 0; - - if (bin_count) - memset(bins, 0, bin_count * sizeof(u32)); - } - - return count; -} -STA_OPS_W(tx_latency_stat_reset); - #define DEBUGFS_ADD(name) \ debugfs_create_file(#name, 0400, \ sta->debugfs.dir, sta, &sta_ ##name## _ops); @@ -576,8 +444,6 @@ void ieee80211_sta_debugfs_add(struct sta_info *sta) DEBUGFS_ADD(last_ack_signal); DEBUGFS_ADD(current_tx_rate); DEBUGFS_ADD(last_rx_rate); - DEBUGFS_ADD(tx_latency_stat); - DEBUGFS_ADD(tx_latency_stat_reset); DEBUGFS_ADD_COUNTER(rx_packets, rx_packets); DEBUGFS_ADD_COUNTER(tx_packets, tx_packets); diff --git a/net/mac80211/driver-ops.h b/net/mac80211/driver-ops.h index fdeda17b8dd2..26e1ca8a474a 100644 --- a/net/mac80211/driver-ops.h +++ b/net/mac80211/driver-ops.h @@ -941,13 +941,13 @@ static inline void drv_set_rekey_data(struct ieee80211_local *local, trace_drv_return_void(local); } -static inline void drv_rssi_callback(struct ieee80211_local *local, - struct ieee80211_sub_if_data *sdata, - const enum ieee80211_rssi_event event) +static inline void drv_event_callback(struct ieee80211_local *local, + struct ieee80211_sub_if_data *sdata, + const struct ieee80211_event *event) { - trace_drv_rssi_callback(local, sdata, event); - if (local->ops->rssi_callback) - local->ops->rssi_callback(&local->hw, &sdata->vif, event); + trace_drv_event_callback(local, sdata, event); + if (local->ops->event_callback) + local->ops->event_callback(&local->hw, &sdata->vif, event); trace_drv_return_void(local); } @@ -1367,4 +1367,16 @@ drv_tdls_recv_channel_switch(struct ieee80211_local *local, trace_drv_return_void(local); } +static inline void drv_wake_tx_queue(struct ieee80211_local *local, + struct txq_info *txq) +{ + struct ieee80211_sub_if_data *sdata = vif_to_sdata(txq->txq.vif); + + if (!check_sdata_in_driver(sdata)) + return; + + trace_drv_wake_tx_queue(local, sdata, txq); + local->ops->wake_tx_queue(&local->hw, &txq->txq); +} + #endif /* __MAC80211_DRIVER_OPS */ diff --git a/net/mac80211/ht.c b/net/mac80211/ht.c index ff630be2ca75..7a76ce639d58 100644 --- a/net/mac80211/ht.c +++ b/net/mac80211/ht.c @@ -252,8 +252,6 @@ bool ieee80211_ht_cap_ie_to_sta_ht_cap(struct ieee80211_sub_if_data *sdata, break; } - if (bw != sta->sta.bandwidth) - changed = true; sta->sta.bandwidth = bw; sta->cur_max_bandwidth = diff --git a/net/mac80211/ibss.c b/net/mac80211/ibss.c index b606b53a49a7..bfef1b215050 100644 --- a/net/mac80211/ibss.c +++ b/net/mac80211/ibss.c @@ -188,6 +188,16 @@ ieee80211_ibss_build_presp(struct ieee80211_sub_if_data *sdata, */ pos = ieee80211_ie_build_ht_oper(pos, &sband->ht_cap, chandef, 0); + + /* add VHT capability and information IEs */ + if (chandef->width != NL80211_CHAN_WIDTH_20 && + chandef->width != NL80211_CHAN_WIDTH_40 && + sband->vht_cap.vht_supported) { + pos = ieee80211_ie_build_vht_cap(pos, &sband->vht_cap, + sband->vht_cap.cap); + pos = ieee80211_ie_build_vht_oper(pos, &sband->vht_cap, + chandef); + } } if (local->hw.queues >= IEEE80211_NUM_ACS) @@ -249,8 +259,6 @@ static void __ieee80211_sta_join_ibss(struct ieee80211_sub_if_data *sdata, if (presp) kfree_rcu(presp, rcu_head); - sdata->drop_unencrypted = capability & WLAN_CAPABILITY_PRIVACY ? 1 : 0; - /* make a copy of the chandef, it could be modified below. */ chandef = *req_chandef; chan = chandef.chan; @@ -417,6 +425,11 @@ static void ieee80211_sta_join_ibss(struct ieee80211_sub_if_data *sdata, NL80211_CHAN_WIDTH_20_NOHT); chandef.width = sdata->u.ibss.chandef.width; break; + case NL80211_CHAN_WIDTH_80: + case NL80211_CHAN_WIDTH_160: + chandef = sdata->u.ibss.chandef; + chandef.chan = cbss->channel; + break; default: /* fall back to 20 MHz for unsupported modes */ cfg80211_chandef_create(&chandef, cbss->channel, @@ -470,22 +483,19 @@ int ieee80211_ibss_csa_beacon(struct ieee80211_sub_if_data *sdata, struct beacon_data *presp, *old_presp; struct cfg80211_bss *cbss; const struct cfg80211_bss_ies *ies; - u16 capability; + u16 capability = 0; u64 tsf; int ret = 0; sdata_assert_lock(sdata); - capability = WLAN_CAPABILITY_IBSS; - if (ifibss->privacy) - capability |= WLAN_CAPABILITY_PRIVACY; + capability = WLAN_CAPABILITY_PRIVACY; cbss = cfg80211_get_bss(sdata->local->hw.wiphy, ifibss->chandef.chan, ifibss->bssid, ifibss->ssid, - ifibss->ssid_len, WLAN_CAPABILITY_IBSS | - WLAN_CAPABILITY_PRIVACY, - capability); + ifibss->ssid_len, IEEE80211_BSS_TYPE_IBSS, + IEEE80211_PRIVACY(ifibss->privacy)); if (WARN_ON(!cbss)) { ret = -EINVAL; @@ -525,23 +535,17 @@ int ieee80211_ibss_finish_csa(struct ieee80211_sub_if_data *sdata) struct ieee80211_if_ibss *ifibss = &sdata->u.ibss; struct cfg80211_bss *cbss; int err, changed = 0; - u16 capability; sdata_assert_lock(sdata); /* update cfg80211 bss information with the new channel */ if (!is_zero_ether_addr(ifibss->bssid)) { - capability = WLAN_CAPABILITY_IBSS; - - if (ifibss->privacy) - capability |= WLAN_CAPABILITY_PRIVACY; - cbss = cfg80211_get_bss(sdata->local->hw.wiphy, ifibss->chandef.chan, ifibss->bssid, ifibss->ssid, - ifibss->ssid_len, WLAN_CAPABILITY_IBSS | - WLAN_CAPABILITY_PRIVACY, - capability); + ifibss->ssid_len, + IEEE80211_BSS_TYPE_IBSS, + IEEE80211_PRIVACY(ifibss->privacy)); /* XXX: should not really modify cfg80211 data */ if (cbss) { cbss->channel = sdata->csa_chandef.chan; @@ -682,19 +686,13 @@ static void ieee80211_ibss_disconnect(struct ieee80211_sub_if_data *sdata) struct cfg80211_bss *cbss; struct beacon_data *presp; struct sta_info *sta; - u16 capability; if (!is_zero_ether_addr(ifibss->bssid)) { - capability = WLAN_CAPABILITY_IBSS; - - if (ifibss->privacy) - capability |= WLAN_CAPABILITY_PRIVACY; - cbss = cfg80211_get_bss(local->hw.wiphy, ifibss->chandef.chan, ifibss->bssid, ifibss->ssid, - ifibss->ssid_len, WLAN_CAPABILITY_IBSS | - WLAN_CAPABILITY_PRIVACY, - capability); + ifibss->ssid_len, + IEEE80211_BSS_TYPE_IBSS, + IEEE80211_PRIVACY(ifibss->privacy)); if (cbss) { cfg80211_unlink_bss(local->hw.wiphy, cbss); @@ -980,110 +978,140 @@ static void ieee80211_rx_mgmt_auth_ibss(struct ieee80211_sub_if_data *sdata, mgmt->sa, sdata->u.ibss.bssid, NULL, 0, 0, 0); } -static void ieee80211_rx_bss_info(struct ieee80211_sub_if_data *sdata, - struct ieee80211_mgmt *mgmt, size_t len, - struct ieee80211_rx_status *rx_status, - struct ieee802_11_elems *elems) +static void ieee80211_update_sta_info(struct ieee80211_sub_if_data *sdata, + struct ieee80211_mgmt *mgmt, size_t len, + struct ieee80211_rx_status *rx_status, + struct ieee802_11_elems *elems, + struct ieee80211_channel *channel) { - struct ieee80211_local *local = sdata->local; - struct cfg80211_bss *cbss; - struct ieee80211_bss *bss; struct sta_info *sta; - struct ieee80211_channel *channel; - u64 beacon_timestamp, rx_timestamp; - u32 supp_rates = 0; enum ieee80211_band band = rx_status->band; enum nl80211_bss_scan_width scan_width; + struct ieee80211_local *local = sdata->local; struct ieee80211_supported_band *sband = local->hw.wiphy->bands[band]; bool rates_updated = false; + u32 supp_rates = 0; - channel = ieee80211_get_channel(local->hw.wiphy, rx_status->freq); - if (!channel) + if (sdata->vif.type != NL80211_IFTYPE_ADHOC) return; - if (sdata->vif.type == NL80211_IFTYPE_ADHOC && - ether_addr_equal(mgmt->bssid, sdata->u.ibss.bssid)) { + if (!ether_addr_equal(mgmt->bssid, sdata->u.ibss.bssid)) + return; - rcu_read_lock(); - sta = sta_info_get(sdata, mgmt->sa); - - if (elems->supp_rates) { - supp_rates = ieee80211_sta_get_rates(sdata, elems, - band, NULL); - if (sta) { - u32 prev_rates; - - prev_rates = sta->sta.supp_rates[band]; - /* make sure mandatory rates are always added */ - scan_width = NL80211_BSS_CHAN_WIDTH_20; - if (rx_status->flag & RX_FLAG_5MHZ) - scan_width = NL80211_BSS_CHAN_WIDTH_5; - if (rx_status->flag & RX_FLAG_10MHZ) - scan_width = NL80211_BSS_CHAN_WIDTH_10; - - sta->sta.supp_rates[band] = supp_rates | - ieee80211_mandatory_rates(sband, - scan_width); - if (sta->sta.supp_rates[band] != prev_rates) { - ibss_dbg(sdata, - "updated supp_rates set for %pM based on beacon/probe_resp (0x%x -> 0x%x)\n", - sta->sta.addr, prev_rates, - sta->sta.supp_rates[band]); - rates_updated = true; - } - } else { - rcu_read_unlock(); - sta = ieee80211_ibss_add_sta(sdata, mgmt->bssid, - mgmt->sa, supp_rates); + rcu_read_lock(); + sta = sta_info_get(sdata, mgmt->sa); + + if (elems->supp_rates) { + supp_rates = ieee80211_sta_get_rates(sdata, elems, + band, NULL); + if (sta) { + u32 prev_rates; + + prev_rates = sta->sta.supp_rates[band]; + /* make sure mandatory rates are always added */ + scan_width = NL80211_BSS_CHAN_WIDTH_20; + if (rx_status->flag & RX_FLAG_5MHZ) + scan_width = NL80211_BSS_CHAN_WIDTH_5; + if (rx_status->flag & RX_FLAG_10MHZ) + scan_width = NL80211_BSS_CHAN_WIDTH_10; + + sta->sta.supp_rates[band] = supp_rates | + ieee80211_mandatory_rates(sband, scan_width); + if (sta->sta.supp_rates[band] != prev_rates) { + ibss_dbg(sdata, + "updated supp_rates set for %pM based on beacon/probe_resp (0x%x -> 0x%x)\n", + sta->sta.addr, prev_rates, + sta->sta.supp_rates[band]); + rates_updated = true; } + } else { + rcu_read_unlock(); + sta = ieee80211_ibss_add_sta(sdata, mgmt->bssid, + mgmt->sa, supp_rates); } + } - if (sta && elems->wmm_info) - sta->sta.wme = true; - - if (sta && elems->ht_operation && elems->ht_cap_elem && - sdata->u.ibss.chandef.width != NL80211_CHAN_WIDTH_20_NOHT && - sdata->u.ibss.chandef.width != NL80211_CHAN_WIDTH_5 && - sdata->u.ibss.chandef.width != NL80211_CHAN_WIDTH_10) { - /* we both use HT */ - struct ieee80211_ht_cap htcap_ie; - struct cfg80211_chan_def chandef; - - ieee80211_ht_oper_to_chandef(channel, - elems->ht_operation, - &chandef); - - memcpy(&htcap_ie, elems->ht_cap_elem, sizeof(htcap_ie)); - - /* - * fall back to HT20 if we don't use or use - * the other extension channel - */ - if (chandef.center_freq1 != - sdata->u.ibss.chandef.center_freq1) - htcap_ie.cap_info &= - cpu_to_le16(~IEEE80211_HT_CAP_SUP_WIDTH_20_40); - - rates_updated |= ieee80211_ht_cap_ie_to_sta_ht_cap( - sdata, sband, &htcap_ie, sta); + if (sta && elems->wmm_info && local->hw.queues >= IEEE80211_NUM_ACS) + sta->sta.wme = true; + + if (sta && elems->ht_operation && elems->ht_cap_elem && + sdata->u.ibss.chandef.width != NL80211_CHAN_WIDTH_20_NOHT && + sdata->u.ibss.chandef.width != NL80211_CHAN_WIDTH_5 && + sdata->u.ibss.chandef.width != NL80211_CHAN_WIDTH_10) { + /* we both use HT */ + struct ieee80211_ht_cap htcap_ie; + struct cfg80211_chan_def chandef; + enum ieee80211_sta_rx_bandwidth bw = sta->sta.bandwidth; + + ieee80211_ht_oper_to_chandef(channel, + elems->ht_operation, + &chandef); + + memcpy(&htcap_ie, elems->ht_cap_elem, sizeof(htcap_ie)); + rates_updated |= ieee80211_ht_cap_ie_to_sta_ht_cap(sdata, sband, + &htcap_ie, + sta); + + if (elems->vht_operation && elems->vht_cap_elem && + sdata->u.ibss.chandef.width != NL80211_CHAN_WIDTH_20 && + sdata->u.ibss.chandef.width != NL80211_CHAN_WIDTH_40) { + /* we both use VHT */ + struct ieee80211_vht_cap cap_ie; + struct ieee80211_sta_vht_cap cap = sta->sta.vht_cap; + + ieee80211_vht_oper_to_chandef(channel, + elems->vht_operation, + &chandef); + memcpy(&cap_ie, elems->vht_cap_elem, sizeof(cap_ie)); + ieee80211_vht_cap_ie_to_sta_vht_cap(sdata, sband, + &cap_ie, sta); + if (memcmp(&cap, &sta->sta.vht_cap, sizeof(cap))) + rates_updated |= true; } - if (sta && rates_updated) { - u32 changed = IEEE80211_RC_SUPP_RATES_CHANGED; - u8 rx_nss = sta->sta.rx_nss; + if (bw != sta->sta.bandwidth) + rates_updated |= true; - /* Force rx_nss recalculation */ - sta->sta.rx_nss = 0; - rate_control_rate_init(sta); - if (sta->sta.rx_nss != rx_nss) - changed |= IEEE80211_RC_NSS_CHANGED; + if (!cfg80211_chandef_compatible(&sdata->u.ibss.chandef, + &chandef)) + WARN_ON_ONCE(1); + } - drv_sta_rc_update(local, sdata, &sta->sta, changed); - } + if (sta && rates_updated) { + u32 changed = IEEE80211_RC_SUPP_RATES_CHANGED; + u8 rx_nss = sta->sta.rx_nss; - rcu_read_unlock(); + /* Force rx_nss recalculation */ + sta->sta.rx_nss = 0; + rate_control_rate_init(sta); + if (sta->sta.rx_nss != rx_nss) + changed |= IEEE80211_RC_NSS_CHANGED; + + drv_sta_rc_update(local, sdata, &sta->sta, changed); } + rcu_read_unlock(); +} + +static void ieee80211_rx_bss_info(struct ieee80211_sub_if_data *sdata, + struct ieee80211_mgmt *mgmt, size_t len, + struct ieee80211_rx_status *rx_status, + struct ieee802_11_elems *elems) +{ + struct ieee80211_local *local = sdata->local; + struct cfg80211_bss *cbss; + struct ieee80211_bss *bss; + struct ieee80211_channel *channel; + u64 beacon_timestamp, rx_timestamp; + u32 supp_rates = 0; + enum ieee80211_band band = rx_status->band; + + channel = ieee80211_get_channel(local->hw.wiphy, rx_status->freq); + if (!channel) + return; + + ieee80211_update_sta_info(sdata, mgmt, len, rx_status, elems, channel); + bss = ieee80211_bss_info_update(local, rx_status, mgmt, len, elems, channel); if (!bss) @@ -1273,7 +1301,7 @@ static void ieee80211_sta_merge_ibss(struct ieee80211_sub_if_data *sdata) scan_width = cfg80211_chandef_to_scan_width(&ifibss->chandef); ieee80211_request_ibss_scan(sdata, ifibss->ssid, ifibss->ssid_len, - NULL, scan_width); + NULL, 0, scan_width); } static void ieee80211_sta_create_ibss(struct ieee80211_sub_if_data *sdata) @@ -1304,14 +1332,82 @@ static void ieee80211_sta_create_ibss(struct ieee80211_sub_if_data *sdata) if (ifibss->privacy) capability |= WLAN_CAPABILITY_PRIVACY; - else - sdata->drop_unencrypted = 0; __ieee80211_sta_join_ibss(sdata, bssid, sdata->vif.bss_conf.beacon_int, &ifibss->chandef, ifibss->basic_rates, capability, 0, true); } +static unsigned ibss_setup_channels(struct wiphy *wiphy, + struct ieee80211_channel **channels, + unsigned int channels_max, + u32 center_freq, u32 width) +{ + struct ieee80211_channel *chan = NULL; + unsigned int n_chan = 0; + u32 start_freq, end_freq, freq; + + if (width <= 20) { + start_freq = center_freq; + end_freq = center_freq; + } else { + start_freq = center_freq - width / 2 + 10; + end_freq = center_freq + width / 2 - 10; + } + + for (freq = start_freq; freq <= end_freq; freq += 20) { + chan = ieee80211_get_channel(wiphy, freq); + if (!chan) + continue; + if (n_chan >= channels_max) + return n_chan; + + channels[n_chan] = chan; + n_chan++; + } + + return n_chan; +} + +static unsigned int +ieee80211_ibss_setup_scan_channels(struct wiphy *wiphy, + const struct cfg80211_chan_def *chandef, + struct ieee80211_channel **channels, + unsigned int channels_max) +{ + unsigned int n_chan = 0; + u32 width, cf1, cf2 = 0; + + switch (chandef->width) { + case NL80211_CHAN_WIDTH_40: + width = 40; + break; + case NL80211_CHAN_WIDTH_80P80: + cf2 = chandef->center_freq2; + /* fall through */ + case NL80211_CHAN_WIDTH_80: + width = 80; + break; + case NL80211_CHAN_WIDTH_160: + width = 160; + break; + default: + width = 20; + break; + } + + cf1 = chandef->center_freq1; + + n_chan = ibss_setup_channels(wiphy, channels, channels_max, cf1, width); + + if (cf2) + n_chan += ibss_setup_channels(wiphy, &channels[n_chan], + channels_max - n_chan, cf2, + width); + + return n_chan; +} + /* * This function is called with state == IEEE80211_IBSS_MLME_SEARCH */ @@ -1325,7 +1421,6 @@ static void ieee80211_sta_find_ibss(struct ieee80211_sub_if_data *sdata) const u8 *bssid = NULL; enum nl80211_bss_scan_width scan_width; int active_ibss; - u16 capability; sdata_assert_lock(sdata); @@ -1335,9 +1430,6 @@ static void ieee80211_sta_find_ibss(struct ieee80211_sub_if_data *sdata) if (active_ibss) return; - capability = WLAN_CAPABILITY_IBSS; - if (ifibss->privacy) - capability |= WLAN_CAPABILITY_PRIVACY; if (ifibss->fixed_bssid) bssid = ifibss->bssid; if (ifibss->fixed_channel) @@ -1346,8 +1438,8 @@ static void ieee80211_sta_find_ibss(struct ieee80211_sub_if_data *sdata) bssid = ifibss->bssid; cbss = cfg80211_get_bss(local->hw.wiphy, chan, bssid, ifibss->ssid, ifibss->ssid_len, - WLAN_CAPABILITY_IBSS | WLAN_CAPABILITY_PRIVACY, - capability); + IEEE80211_BSS_TYPE_IBSS, + IEEE80211_PRIVACY(ifibss->privacy)); if (cbss) { struct ieee80211_bss *bss; @@ -1381,11 +1473,18 @@ static void ieee80211_sta_find_ibss(struct ieee80211_sub_if_data *sdata) /* Selected IBSS not found in current scan results - try to scan */ if (time_after(jiffies, ifibss->last_scan_completed + IEEE80211_SCAN_INTERVAL)) { + struct ieee80211_channel *channels[8]; + unsigned int num; + sdata_info(sdata, "Trigger new scan to find an IBSS to join\n"); + num = ieee80211_ibss_setup_scan_channels(local->hw.wiphy, + &ifibss->chandef, + channels, + ARRAY_SIZE(channels)); scan_width = cfg80211_chandef_to_scan_width(&ifibss->chandef); ieee80211_request_ibss_scan(sdata, ifibss->ssid, - ifibss->ssid_len, chan, + ifibss->ssid_len, channels, num, scan_width); } else { int interval = IEEE80211_SCAN_INTERVAL; @@ -1742,7 +1841,7 @@ int ieee80211_ibss_leave(struct ieee80211_sub_if_data *sdata) ieee80211_ibss_disconnect(sdata); ifibss->ssid_len = 0; - memset(ifibss->bssid, 0, ETH_ALEN); + eth_zero_addr(ifibss->bssid); /* remove beacon */ kfree(sdata->u.ibss.ie); diff --git a/net/mac80211/ieee80211_i.h b/net/mac80211/ieee80211_i.h index 8d53d65bd2ab..ab46ab4a7249 100644 --- a/net/mac80211/ieee80211_i.h +++ b/net/mac80211/ieee80211_i.h @@ -26,6 +26,7 @@ #include <linux/etherdevice.h> #include <linux/leds.h> #include <linux/idr.h> +#include <linux/rhashtable.h> #include <net/ieee80211_radiotap.h> #include <net/cfg80211.h> #include <net/mac80211.h> @@ -810,6 +811,19 @@ struct mac80211_qos_map { struct rcu_head rcu_head; }; +enum txq_info_flags { + IEEE80211_TXQ_STOP, + IEEE80211_TXQ_AMPDU, +}; + +struct txq_info { + struct sk_buff_head queue; + unsigned long flags; + + /* keep last! */ + struct ieee80211_txq txq; +}; + struct ieee80211_sub_if_data { struct list_head list; @@ -830,8 +844,6 @@ struct ieee80211_sub_if_data { unsigned long state; - int drop_unencrypted; - char name[IFNAMSIZ]; /* Fragment table for host-based reassembly */ @@ -854,6 +866,7 @@ struct ieee80211_sub_if_data { bool control_port_no_encrypt; int encrypt_headroom; + atomic_t txqs_len[IEEE80211_NUM_ACS]; struct ieee80211_tx_queue_params tx_conf[IEEE80211_NUM_ACS]; struct mac80211_qos_map __rcu *qos_map; @@ -1042,24 +1055,6 @@ struct tpt_led_trigger { }; #endif -/* - * struct ieee80211_tx_latency_bin_ranges - Tx latency statistics bins ranges - * - * Measuring Tx latency statistics. Counts how many Tx frames transmitted in a - * certain latency range (in Milliseconds). Each station that uses these - * ranges will have bins to count the amount of frames received in that range. - * The user can configure the ranges via debugfs. - * If ranges is NULL then Tx latency statistics bins are disabled for all - * stations. - * - * @n_ranges: number of ranges that are taken in account - * @ranges: the ranges that the user requested or NULL if disabled. - */ -struct ieee80211_tx_latency_bin_ranges { - int n_ranges; - u32 ranges[]; -}; - /** * mac80211 scan flags - currently active scan mode * @@ -1207,16 +1202,10 @@ struct ieee80211_local { spinlock_t tim_lock; unsigned long num_sta; struct list_head sta_list; - struct sta_info __rcu *sta_hash[STA_HASH_SIZE]; + struct rhashtable sta_hash; struct timer_list sta_cleanup; int sta_generation; - /* - * Tx latency statistics parameters for all stations. - * Can enable via debugfs (NULL when disabled). - */ - struct ieee80211_tx_latency_bin_ranges __rcu *tx_latency; - struct sk_buff_head pending[IEEE80211_MAX_QUEUES]; struct tasklet_struct tx_pending_tasklet; @@ -1298,7 +1287,6 @@ struct ieee80211_local { /* TX/RX handler statistics */ unsigned int tx_handlers_drop; unsigned int tx_handlers_queued; - unsigned int tx_handlers_drop_unencrypted; unsigned int tx_handlers_drop_fragment; unsigned int tx_handlers_drop_wep; unsigned int tx_handlers_drop_not_assoc; @@ -1476,6 +1464,10 @@ static inline struct ieee80211_local *hw_to_local( return container_of(hw, struct ieee80211_local, hw); } +static inline struct txq_info *to_txq_info(struct ieee80211_txq *txq) +{ + return container_of(txq, struct txq_info, txq); +} static inline int ieee80211_bssid_match(const u8 *raddr, const u8 *addr) { @@ -1568,7 +1560,8 @@ int ieee80211_mesh_finish_csa(struct ieee80211_sub_if_data *sdata); void ieee80211_scan_work(struct work_struct *work); int ieee80211_request_ibss_scan(struct ieee80211_sub_if_data *sdata, const u8 *ssid, u8 ssid_len, - struct ieee80211_channel *chan, + struct ieee80211_channel **channels, + unsigned int n_channels, enum nl80211_bss_scan_width scan_width); int ieee80211_request_scan(struct ieee80211_sub_if_data *sdata, struct cfg80211_scan_request *req); @@ -1617,6 +1610,7 @@ int ieee80211_channel_switch(struct wiphy *wiphy, struct net_device *dev, int ieee80211_iface_init(void); void ieee80211_iface_exit(void); int ieee80211_if_add(struct ieee80211_local *local, const char *name, + unsigned char name_assign_type, struct wireless_dev **new_wdev, enum nl80211_iftype type, struct vif_params *params); int ieee80211_if_change_type(struct ieee80211_sub_if_data *sdata, @@ -1784,7 +1778,8 @@ void mac80211_ev_michael_mic_failure(struct ieee80211_sub_if_data *sdata, int ke gfp_t gfp); void ieee80211_set_wmm_default(struct ieee80211_sub_if_data *sdata, bool bss_notify); -void ieee80211_xmit(struct ieee80211_sub_if_data *sdata, struct sk_buff *skb); +void ieee80211_xmit(struct ieee80211_sub_if_data *sdata, + struct sta_info *sta, struct sk_buff *skb); void __ieee80211_tx_skb_tid_band(struct ieee80211_sub_if_data *sdata, struct sk_buff *skb, int tid, @@ -1929,6 +1924,9 @@ static inline bool ieee80211_can_run_worker(struct ieee80211_local *local) return true; } +void ieee80211_init_tx_queue(struct ieee80211_sub_if_data *sdata, + struct sta_info *sta, + struct txq_info *txq, int tid); void ieee80211_send_auth(struct ieee80211_sub_if_data *sdata, u16 transaction, u16 auth_alg, u16 status, const u8 *extra, size_t extra_len, const u8 *bssid, @@ -1967,10 +1965,6 @@ int __ieee80211_request_smps_ap(struct ieee80211_sub_if_data *sdata, void ieee80211_recalc_smps(struct ieee80211_sub_if_data *sdata); void ieee80211_recalc_min_chandef(struct ieee80211_sub_if_data *sdata); -size_t ieee80211_ie_split_ric(const u8 *ies, size_t ielen, - const u8 *ids, int n_ids, - const u8 *after_ric, int n_after_ric, - size_t offset); size_t ieee80211_ie_split_vendor(const u8 *ies, size_t ielen, size_t offset); u8 *ieee80211_ie_build_ht_cap(u8 *pos, struct ieee80211_sta_ht_cap *ht_cap, u16 cap); @@ -1979,6 +1973,8 @@ u8 *ieee80211_ie_build_ht_oper(u8 *pos, struct ieee80211_sta_ht_cap *ht_cap, u16 prot_mode); u8 *ieee80211_ie_build_vht_cap(u8 *pos, struct ieee80211_sta_vht_cap *vht_cap, u32 cap); +u8 *ieee80211_ie_build_vht_oper(u8 *pos, struct ieee80211_sta_vht_cap *vht_cap, + const struct cfg80211_chan_def *chandef); int ieee80211_parse_bitrates(struct cfg80211_chan_def *chandef, const struct ieee80211_supported_band *sband, const u8 *srates, int srates_len, u32 *rates); @@ -1994,6 +1990,9 @@ u8 *ieee80211_add_wmm_info_ie(u8 *buf, u8 qosinfo); void ieee80211_ht_oper_to_chandef(struct ieee80211_channel *control_chan, const struct ieee80211_ht_operation *ht_oper, struct cfg80211_chan_def *chandef); +void ieee80211_vht_oper_to_chandef(struct ieee80211_channel *control_chan, + const struct ieee80211_vht_operation *oper, + struct cfg80211_chan_def *chandef); u32 ieee80211_chandef_downgrade(struct cfg80211_chan_def *c); int __must_check diff --git a/net/mac80211/iface.c b/net/mac80211/iface.c index 81a27516813e..b4ac596a7cb7 100644 --- a/net/mac80211/iface.c +++ b/net/mac80211/iface.c @@ -969,6 +969,13 @@ static void ieee80211_do_stop(struct ieee80211_sub_if_data *sdata, } spin_unlock_irqrestore(&local->queue_stop_reason_lock, flags); + if (sdata->vif.txq) { + struct txq_info *txqi = to_txq_info(sdata->vif.txq); + + ieee80211_purge_tx_queue(&local->hw, &txqi->queue); + atomic_set(&sdata->txqs_len[txqi->txq.ac], 0); + } + if (local->open_count == 0) ieee80211_clear_tx_pending(local); @@ -1508,7 +1515,6 @@ int ieee80211_if_change_type(struct ieee80211_sub_if_data *sdata, } /* reset some values that shouldn't be kept across type changes */ - sdata->drop_unencrypted = 0; if (type == NL80211_IFTYPE_STATION) sdata->u.mgd.use_4addr = false; @@ -1649,11 +1655,13 @@ static void ieee80211_assign_perm_addr(struct ieee80211_local *local, } int ieee80211_if_add(struct ieee80211_local *local, const char *name, + unsigned char name_assign_type, struct wireless_dev **new_wdev, enum nl80211_iftype type, struct vif_params *params) { struct net_device *ndev = NULL; struct ieee80211_sub_if_data *sdata = NULL; + struct txq_info *txqi; int ret, i; int txqs = 1; @@ -1673,11 +1681,19 @@ int ieee80211_if_add(struct ieee80211_local *local, const char *name, ieee80211_assign_perm_addr(local, wdev->address, type); memcpy(sdata->vif.addr, wdev->address, ETH_ALEN); } else { + int size = ALIGN(sizeof(*sdata) + local->hw.vif_data_size, + sizeof(void *)); + int txq_size = 0; + + if (local->ops->wake_tx_queue) + txq_size += sizeof(struct txq_info) + + local->hw.txq_data_size; + if (local->hw.queues >= IEEE80211_NUM_ACS) txqs = IEEE80211_NUM_ACS; - ndev = alloc_netdev_mqs(sizeof(*sdata) + local->hw.vif_data_size, - name, NET_NAME_UNKNOWN, + ndev = alloc_netdev_mqs(size + txq_size, + name, name_assign_type, ieee80211_if_setup, txqs, 1); if (!ndev) return -ENOMEM; @@ -1711,6 +1727,11 @@ int ieee80211_if_add(struct ieee80211_local *local, const char *name, memcpy(sdata->vif.addr, ndev->dev_addr, ETH_ALEN); memcpy(sdata->name, ndev->name, IFNAMSIZ); + if (txq_size) { + txqi = netdev_priv(ndev) + size; + ieee80211_init_tx_queue(sdata, NULL, txqi, 0); + } + sdata->dev = ndev; } diff --git a/net/mac80211/key.c b/net/mac80211/key.c index 0825d76edcfc..2291cd730091 100644 --- a/net/mac80211/key.c +++ b/net/mac80211/key.c @@ -492,6 +492,7 @@ ieee80211_key_alloc(u32 cipher, int idx, size_t key_len, for (j = 0; j < len; j++) key->u.gen.rx_pn[i][j] = seq[len - j - 1]; + key->flags |= KEY_FLAG_CIPHER_SCHEME; } } memcpy(key->conf.key, key_data, key_len); diff --git a/net/mac80211/key.h b/net/mac80211/key.h index d57a9915494f..c5a31835be0e 100644 --- a/net/mac80211/key.h +++ b/net/mac80211/key.h @@ -30,10 +30,12 @@ struct sta_info; * @KEY_FLAG_UPLOADED_TO_HARDWARE: Indicates that this key is present * in the hardware for TX crypto hardware acceleration. * @KEY_FLAG_TAINTED: Key is tainted and packets should be dropped. + * @KEY_FLAG_CIPHER_SCHEME: This key is for a hardware cipher scheme */ enum ieee80211_internal_key_flags { KEY_FLAG_UPLOADED_TO_HARDWARE = BIT(0), KEY_FLAG_TAINTED = BIT(1), + KEY_FLAG_CIPHER_SCHEME = BIT(2), }; enum ieee80211_internal_tkip_state { diff --git a/net/mac80211/main.c b/net/mac80211/main.c index 5e09d354c5a5..df3051d96aff 100644 --- a/net/mac80211/main.c +++ b/net/mac80211/main.c @@ -557,6 +557,9 @@ struct ieee80211_hw *ieee80211_alloc_hw_nm(size_t priv_data_len, local = wiphy_priv(wiphy); + if (sta_info_init(local)) + goto err_free; + local->hw.wiphy = wiphy; local->hw.priv = (char *)local + ALIGN(sizeof(*local), NETDEV_ALIGN); @@ -629,8 +632,6 @@ struct ieee80211_hw *ieee80211_alloc_hw_nm(size_t priv_data_len, spin_lock_init(&local->ack_status_lock); idr_init(&local->ack_status_frames); - sta_info_init(local); - for (i = 0; i < IEEE80211_MAX_QUEUES; i++) { skb_queue_head_init(&local->pending[i]); atomic_set(&local->agg_queue_stop[i], 0); @@ -650,6 +651,9 @@ struct ieee80211_hw *ieee80211_alloc_hw_nm(size_t priv_data_len, ieee80211_roc_setup(local); return &local->hw; + err_free: + wiphy_free(wiphy); + return NULL; } EXPORT_SYMBOL(ieee80211_alloc_hw_nm); @@ -1035,6 +1039,9 @@ int ieee80211_register_hw(struct ieee80211_hw *hw) local->dynamic_ps_forced_timeout = -1; + if (!local->hw.txq_ac_max_pending) + local->hw.txq_ac_max_pending = 64; + result = ieee80211_wep_init(local); if (result < 0) wiphy_debug(local->hw.wiphy, "Failed to initialize wep: %d\n", @@ -1057,7 +1064,7 @@ int ieee80211_register_hw(struct ieee80211_hw *hw) /* add one default STA interface if supported */ if (local->hw.wiphy->interface_modes & BIT(NL80211_IFTYPE_STATION) && !(hw->flags & IEEE80211_HW_NO_AUTO_VIF)) { - result = ieee80211_if_add(local, "wlan%d", NULL, + result = ieee80211_if_add(local, "wlan%d", NET_NAME_ENUM, NULL, NL80211_IFTYPE_STATION, NULL); if (result) wiphy_warn(local->hw.wiphy, @@ -1173,7 +1180,6 @@ void ieee80211_unregister_hw(struct ieee80211_hw *hw) destroy_workqueue(local->workqueue); wiphy_unregister(local->hw.wiphy); - sta_info_stop(local); ieee80211_wep_free(local); ieee80211_led_exit(local); kfree(local->int_scan_req); @@ -1201,8 +1207,6 @@ void ieee80211_free_hw(struct ieee80211_hw *hw) ieee80211_free_ack_frame, NULL); idr_destroy(&local->ack_status_frames); - kfree(rcu_access_pointer(local->tx_latency)); - sta_info_stop(local); wiphy_free(local->hw.wiphy); diff --git a/net/mac80211/mesh.c b/net/mac80211/mesh.c index 0c8b2a77d312..d4684242e78b 100644 --- a/net/mac80211/mesh.c +++ b/net/mac80211/mesh.c @@ -520,7 +520,7 @@ int ieee80211_fill_mesh_addresses(struct ieee80211_hdr *hdr, __le16 *fc, } else { *fc |= cpu_to_le16(IEEE80211_FCTL_FROMDS | IEEE80211_FCTL_TODS); /* RA TA DA SA */ - memset(hdr->addr1, 0, ETH_ALEN); /* RA is resolved later */ + eth_zero_addr(hdr->addr1); /* RA is resolved later */ memcpy(hdr->addr2, meshsa, ETH_ALEN); memcpy(hdr->addr3, meshda, ETH_ALEN); memcpy(hdr->addr4, meshsa, ETH_ALEN); @@ -574,7 +574,8 @@ static void ieee80211_mesh_housekeeping(struct ieee80211_sub_if_data *sdata) struct ieee80211_if_mesh *ifmsh = &sdata->u.mesh; u32 changed; - ieee80211_sta_expire(sdata, ifmsh->mshcfg.plink_timeout * HZ); + if (ifmsh->mshcfg.plink_timeout > 0) + ieee80211_sta_expire(sdata, ifmsh->mshcfg.plink_timeout * HZ); mesh_path_expire(sdata); changed = mesh_accept_plinks_update(sdata); diff --git a/net/mac80211/mesh_plink.c b/net/mac80211/mesh_plink.c index b488e1859b18..60d737f144e3 100644 --- a/net/mac80211/mesh_plink.c +++ b/net/mac80211/mesh_plink.c @@ -17,7 +17,7 @@ #define PLINK_GET_PLID(p) (p + 4) #define mod_plink_timer(s, t) (mod_timer(&s->plink_timer, \ - jiffies + HZ * t / 1000)) + jiffies + msecs_to_jiffies(t))) enum plink_event { PLINK_UNDEFINED, @@ -382,6 +382,7 @@ static void mesh_sta_info_init(struct ieee80211_sub_if_data *sdata, enum ieee80211_band band = ieee80211_get_sdata_band(sdata); struct ieee80211_supported_band *sband; u32 rates, basic_rates = 0, changed = 0; + enum ieee80211_sta_rx_bandwidth bw = sta->sta.bandwidth; sband = local->hw.wiphy->bands[band]; rates = ieee80211_sta_get_rates(sdata, elems, band, &basic_rates); @@ -401,6 +402,9 @@ static void mesh_sta_info_init(struct ieee80211_sub_if_data *sdata, elems->ht_cap_elem, sta)) changed |= IEEE80211_RC_BW_CHANGED; + if (bw != sta->sta.bandwidth) + changed |= IEEE80211_RC_BW_CHANGED; + /* HT peer is operating 20MHz-only */ if (elems->ht_operation && !(elems->ht_operation->ht_param & @@ -621,9 +625,9 @@ static void mesh_plink_timer(unsigned long data) sta->llid, sta->plid, reason); } -static inline void mesh_plink_timer_set(struct sta_info *sta, int timeout) +static inline void mesh_plink_timer_set(struct sta_info *sta, u32 timeout) { - sta->plink_timer.expires = jiffies + (HZ * timeout / 1000); + sta->plink_timer.expires = jiffies + msecs_to_jiffies(timeout); sta->plink_timer.data = (unsigned long) sta; sta->plink_timer.function = mesh_plink_timer; sta->plink_timeout = timeout; diff --git a/net/mac80211/mlme.c b/net/mac80211/mlme.c index 142f66aece18..26053bf2faa8 100644 --- a/net/mac80211/mlme.c +++ b/net/mac80211/mlme.c @@ -1168,11 +1168,7 @@ ieee80211_sta_process_chanswitch(struct ieee80211_sub_if_data *sdata, 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; + goto drop_connection; } chanctx = container_of(conf, struct ieee80211_chanctx, conf); @@ -1181,11 +1177,7 @@ ieee80211_sta_process_chanswitch(struct ieee80211_sub_if_data *sdata, !(local->hw.flags & IEEE80211_HW_CHANCTX_STA_CSA)) { sdata_info(sdata, "driver doesn't support chan-switch with channel contexts\n"); - ieee80211_queue_work(&local->hw, - &ifmgd->csa_connection_drop_work); - mutex_unlock(&local->chanctx_mtx); - mutex_unlock(&local->mtx); - return; + goto drop_connection; } ch_switch.timestamp = timestamp; @@ -1197,11 +1189,7 @@ ieee80211_sta_process_chanswitch(struct ieee80211_sub_if_data *sdata, if (drv_pre_channel_switch(sdata, &ch_switch)) { sdata_info(sdata, "preparing for channel switch failed, disconnecting\n"); - ieee80211_queue_work(&local->hw, - &ifmgd->csa_connection_drop_work); - mutex_unlock(&local->chanctx_mtx); - mutex_unlock(&local->mtx); - return; + goto drop_connection; } res = ieee80211_vif_reserve_chanctx(sdata, &csa_ie.chandef, @@ -1210,11 +1198,7 @@ ieee80211_sta_process_chanswitch(struct ieee80211_sub_if_data *sdata, sdata_info(sdata, "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; + goto drop_connection; } mutex_unlock(&local->chanctx_mtx); @@ -1244,6 +1228,11 @@ ieee80211_sta_process_chanswitch(struct ieee80211_sub_if_data *sdata, mod_timer(&ifmgd->chswitch_timer, TU_TO_EXP_TIME((csa_ie.count - 1) * cbss->beacon_interval)); + return; + drop_connection: + ieee80211_queue_work(&local->hw, &ifmgd->csa_connection_drop_work); + mutex_unlock(&local->chanctx_mtx); + mutex_unlock(&local->mtx); } static bool @@ -1359,15 +1348,15 @@ static u32 ieee80211_handle_pwr_constr(struct ieee80211_sub_if_data *sdata, */ if (has_80211h_pwr && (!has_cisco_pwr || pwr_level_80211h <= pwr_level_cisco)) { - sdata_info(sdata, - "Limiting TX power to %d (%d - %d) dBm as advertised by %pM\n", - pwr_level_80211h, chan_pwr, pwr_reduction_80211h, - sdata->u.mgd.bssid); + sdata_dbg(sdata, + "Limiting TX power to %d (%d - %d) dBm as advertised by %pM\n", + pwr_level_80211h, chan_pwr, pwr_reduction_80211h, + sdata->u.mgd.bssid); new_ap_level = pwr_level_80211h; } else { /* has_cisco_pwr is always true here. */ - sdata_info(sdata, - "Limiting TX power to %d dBm as advertised by %pM\n", - pwr_level_cisco, sdata->u.mgd.bssid); + sdata_dbg(sdata, + "Limiting TX power to %d dBm as advertised by %pM\n", + pwr_level_cisco, sdata->u.mgd.bssid); new_ap_level = pwr_level_cisco; } @@ -1633,9 +1622,6 @@ void ieee80211_dynamic_ps_timer(unsigned long data) { struct ieee80211_local *local = (void *) data; - if (local->quiescing || local->suspended) - return; - ieee80211_queue_work(&local->hw, &local->dynamic_ps_enable_work); } @@ -2045,7 +2031,7 @@ static void ieee80211_set_disassoc(struct ieee80211_sub_if_data *sdata, ieee80211_flush_queues(local, sdata, false); /* clear bssid only after building the needed mgmt frames */ - memset(ifmgd->bssid, 0, ETH_ALEN); + eth_zero_addr(ifmgd->bssid); /* remove AP and TDLS peers */ sta_info_flush(sdata); @@ -2260,7 +2246,7 @@ static void ieee80211_mgd_probe_ap_send(struct ieee80211_sub_if_data *sdata) else ssid_len = ssid[1]; - ieee80211_send_probe_req(sdata, sdata->vif.addr, NULL, + ieee80211_send_probe_req(sdata, sdata->vif.addr, dst, ssid + 2, ssid_len, NULL, 0, (u32) -1, true, 0, ifmgd->associated->channel, false); @@ -2372,6 +2358,24 @@ struct sk_buff *ieee80211_ap_probereq_get(struct ieee80211_hw *hw, } EXPORT_SYMBOL(ieee80211_ap_probereq_get); +static void ieee80211_report_disconnect(struct ieee80211_sub_if_data *sdata, + const u8 *buf, size_t len, bool tx, + u16 reason) +{ + struct ieee80211_event event = { + .type = MLME_EVENT, + .u.mlme.data = tx ? DEAUTH_TX_EVENT : DEAUTH_RX_EVENT, + .u.mlme.reason = reason, + }; + + if (tx) + cfg80211_tx_mlme_mgmt(sdata->dev, buf, len); + else + cfg80211_rx_mlme_mgmt(sdata->dev, buf, len); + + drv_event_callback(sdata->local, sdata, &event); +} + static void __ieee80211_disconnect(struct ieee80211_sub_if_data *sdata) { struct ieee80211_local *local = sdata->local; @@ -2397,8 +2401,9 @@ static void __ieee80211_disconnect(struct ieee80211_sub_if_data *sdata) } mutex_unlock(&local->mtx); - cfg80211_tx_mlme_mgmt(sdata->dev, frame_buf, - IEEE80211_DEAUTH_FRAME_LEN); + ieee80211_report_disconnect(sdata, frame_buf, sizeof(frame_buf), true, + WLAN_REASON_DISASSOC_DUE_TO_INACTIVITY); + sdata_unlock(sdata); } @@ -2477,7 +2482,7 @@ static void ieee80211_destroy_auth_data(struct ieee80211_sub_if_data *sdata, del_timer_sync(&sdata->u.mgd.timer); sta_info_destroy_addr(sdata, auth_data->bss->bssid); - memset(sdata->u.mgd.bssid, 0, ETH_ALEN); + eth_zero_addr(sdata->u.mgd.bssid); ieee80211_bss_info_change_notify(sdata, BSS_CHANGED_BSSID); sdata->u.mgd.flags = 0; mutex_lock(&sdata->local->mtx); @@ -2522,6 +2527,10 @@ static void ieee80211_rx_mgmt_auth(struct ieee80211_sub_if_data *sdata, u8 bssid[ETH_ALEN]; u16 auth_alg, auth_transaction, status_code; struct sta_info *sta; + struct ieee80211_event event = { + .type = MLME_EVENT, + .u.mlme.data = AUTH_EVENT, + }; sdata_assert_lock(sdata); @@ -2554,6 +2563,9 @@ static void ieee80211_rx_mgmt_auth(struct ieee80211_sub_if_data *sdata, mgmt->sa, status_code); ieee80211_destroy_auth_data(sdata, false); cfg80211_rx_mlme_mgmt(sdata->dev, (u8 *)mgmt, len); + event.u.mlme.status = MLME_DENIED; + event.u.mlme.reason = status_code; + drv_event_callback(sdata->local, sdata, &event); return; } @@ -2576,6 +2588,8 @@ static void ieee80211_rx_mgmt_auth(struct ieee80211_sub_if_data *sdata, return; } + event.u.mlme.status = MLME_SUCCESS; + drv_event_callback(sdata->local, sdata, &event); sdata_info(sdata, "authenticated\n"); ifmgd->auth_data->done = true; ifmgd->auth_data->timeout = jiffies + IEEE80211_AUTH_WAIT_ASSOC; @@ -2694,7 +2708,7 @@ static void ieee80211_rx_mgmt_deauth(struct ieee80211_sub_if_data *sdata, ieee80211_set_disassoc(sdata, 0, 0, false, NULL); - cfg80211_rx_mlme_mgmt(sdata->dev, (u8 *)mgmt, len); + ieee80211_report_disconnect(sdata, (u8 *)mgmt, len, false, reason_code); } @@ -2720,7 +2734,7 @@ static void ieee80211_rx_mgmt_disassoc(struct ieee80211_sub_if_data *sdata, ieee80211_set_disassoc(sdata, 0, 0, false, NULL); - cfg80211_rx_mlme_mgmt(sdata->dev, (u8 *)mgmt, len); + ieee80211_report_disconnect(sdata, (u8 *)mgmt, len, false, reason_code); } static void ieee80211_get_rates(struct ieee80211_supported_band *sband, @@ -2790,7 +2804,7 @@ static void ieee80211_destroy_assoc_data(struct ieee80211_sub_if_data *sdata, del_timer_sync(&sdata->u.mgd.timer); sta_info_destroy_addr(sdata, assoc_data->bss->bssid); - memset(sdata->u.mgd.bssid, 0, ETH_ALEN); + eth_zero_addr(sdata->u.mgd.bssid); ieee80211_bss_info_change_notify(sdata, BSS_CHANGED_BSSID); sdata->u.mgd.flags = 0; mutex_lock(&sdata->local->mtx); @@ -2982,10 +2996,14 @@ static bool ieee80211_assoc_success(struct ieee80211_sub_if_data *sdata, rate_control_rate_init(sta); - if (ifmgd->flags & IEEE80211_STA_MFP_ENABLED) + if (ifmgd->flags & IEEE80211_STA_MFP_ENABLED) { set_sta_flag(sta, WLAN_STA_MFP); + sta->sta.mfp = true; + } else { + sta->sta.mfp = false; + } - sta->sta.wme = elems.wmm_param; + sta->sta.wme = elems.wmm_param && local->hw.queues >= IEEE80211_NUM_ACS; err = sta_info_move_state(sta, IEEE80211_STA_ASSOC); if (!err && !(ifmgd->flags & IEEE80211_STA_CONTROL_PORT)) @@ -3055,6 +3073,10 @@ static void ieee80211_rx_mgmt_assoc_resp(struct ieee80211_sub_if_data *sdata, u8 *pos; bool reassoc; struct cfg80211_bss *bss; + struct ieee80211_event event = { + .type = MLME_EVENT, + .u.mlme.data = ASSOC_EVENT, + }; sdata_assert_lock(sdata); @@ -3106,6 +3128,9 @@ static void ieee80211_rx_mgmt_assoc_resp(struct ieee80211_sub_if_data *sdata, sdata_info(sdata, "%pM denied association (code=%d)\n", mgmt->sa, status_code); ieee80211_destroy_assoc_data(sdata, false); + event.u.mlme.status = MLME_DENIED; + event.u.mlme.reason = status_code; + drv_event_callback(sdata->local, sdata, &event); } else { if (!ieee80211_assoc_success(sdata, bss, mgmt, len)) { /* oops -- internal error -- send timeout for now */ @@ -3113,6 +3138,8 @@ static void ieee80211_rx_mgmt_assoc_resp(struct ieee80211_sub_if_data *sdata, cfg80211_assoc_timeout(sdata->dev, bss); return; } + event.u.mlme.status = MLME_SUCCESS; + drv_event_callback(sdata->local, sdata, &event); sdata_info(sdata, "associated\n"); /* @@ -3315,6 +3342,9 @@ static void ieee80211_rx_mgmt_beacon(struct ieee80211_sub_if_data *sdata, ifmgd->count_beacon_signal >= IEEE80211_SIGNAL_AVE_MIN_COUNT) { int sig = ifmgd->ave_beacon_signal; int last_sig = ifmgd->last_ave_beacon_signal; + struct ieee80211_event event = { + .type = RSSI_EVENT, + }; /* * if signal crosses either of the boundaries, invoke callback @@ -3323,12 +3353,14 @@ static void ieee80211_rx_mgmt_beacon(struct ieee80211_sub_if_data *sdata, if (sig > ifmgd->rssi_max_thold && (last_sig <= ifmgd->rssi_min_thold || last_sig == 0)) { ifmgd->last_ave_beacon_signal = sig; - drv_rssi_callback(local, sdata, RSSI_EVENT_HIGH); + event.u.rssi.data = RSSI_EVENT_HIGH; + drv_event_callback(local, sdata, &event); } else if (sig < ifmgd->rssi_min_thold && (last_sig >= ifmgd->rssi_max_thold || last_sig == 0)) { ifmgd->last_ave_beacon_signal = sig; - drv_rssi_callback(local, sdata, RSSI_EVENT_LOW); + event.u.rssi.data = RSSI_EVENT_LOW; + drv_event_callback(local, sdata, &event); } } @@ -3433,6 +3465,26 @@ static void ieee80211_rx_mgmt_beacon(struct ieee80211_sub_if_data *sdata, if (ifmgd->csa_waiting_bcn) ieee80211_chswitch_post_beacon(sdata); + /* + * Update beacon timing and dtim count on every beacon appearance. This + * will allow the driver to use the most updated values. Do it before + * comparing this one with last received beacon. + * IMPORTANT: These parameters would possibly be out of sync by the time + * the driver will use them. The synchronized view is currently + * guaranteed only in certain callbacks. + */ + if (local->hw.flags & IEEE80211_HW_TIMING_BEACON_ONLY) { + sdata->vif.bss_conf.sync_tsf = + le64_to_cpu(mgmt->u.beacon.timestamp); + sdata->vif.bss_conf.sync_device_ts = + rx_status->device_timestamp; + if (elems.tim) + sdata->vif.bss_conf.sync_dtim_count = + elems.tim->dtim_count; + else + sdata->vif.bss_conf.sync_dtim_count = 0; + } + if (ncrc == ifmgd->beacon_crc && ifmgd->beacon_crc_valid) return; ifmgd->beacon_crc = ncrc; @@ -3460,18 +3512,6 @@ static void ieee80211_rx_mgmt_beacon(struct ieee80211_sub_if_data *sdata, else bss_conf->dtim_period = 1; - if (local->hw.flags & IEEE80211_HW_TIMING_BEACON_ONLY) { - sdata->vif.bss_conf.sync_tsf = - le64_to_cpu(mgmt->u.beacon.timestamp); - sdata->vif.bss_conf.sync_device_ts = - rx_status->device_timestamp; - if (elems.tim) - sdata->vif.bss_conf.sync_dtim_count = - elems.tim->dtim_count; - else - sdata->vif.bss_conf.sync_dtim_count = 0; - } - changed |= BSS_CHANGED_BEACON_INFO; ifmgd->have_beacon = true; @@ -3502,8 +3542,9 @@ static void ieee80211_rx_mgmt_beacon(struct ieee80211_sub_if_data *sdata, ieee80211_set_disassoc(sdata, IEEE80211_STYPE_DEAUTH, WLAN_REASON_DEAUTH_LEAVING, true, deauth_buf); - cfg80211_tx_mlme_mgmt(sdata->dev, deauth_buf, - sizeof(deauth_buf)); + ieee80211_report_disconnect(sdata, deauth_buf, + sizeof(deauth_buf), true, + WLAN_REASON_DEAUTH_LEAVING); return; } @@ -3621,8 +3662,8 @@ static void ieee80211_sta_connection_lost(struct ieee80211_sub_if_data *sdata, ieee80211_set_disassoc(sdata, IEEE80211_STYPE_DEAUTH, reason, tx, frame_buf); - cfg80211_tx_mlme_mgmt(sdata->dev, frame_buf, - IEEE80211_DEAUTH_FRAME_LEN); + ieee80211_report_disconnect(sdata, frame_buf, sizeof(frame_buf), true, + reason); } static int ieee80211_probe_auth(struct ieee80211_sub_if_data *sdata) @@ -3816,12 +3857,18 @@ void ieee80211_sta_work(struct ieee80211_sub_if_data *sdata) ieee80211_destroy_auth_data(sdata, false); } else if (ieee80211_probe_auth(sdata)) { u8 bssid[ETH_ALEN]; + struct ieee80211_event event = { + .type = MLME_EVENT, + .u.mlme.data = AUTH_EVENT, + .u.mlme.status = MLME_TIMEOUT, + }; memcpy(bssid, ifmgd->auth_data->bss->bssid, ETH_ALEN); ieee80211_destroy_auth_data(sdata, false); cfg80211_auth_timeout(sdata->dev, bssid); + drv_event_callback(sdata->local, sdata, &event); } } else if (ifmgd->auth_data && ifmgd->auth_data->timeout_started) run_again(sdata, ifmgd->auth_data->timeout); @@ -3831,9 +3878,15 @@ void ieee80211_sta_work(struct ieee80211_sub_if_data *sdata) if ((ifmgd->assoc_data->need_beacon && !ifmgd->have_beacon) || ieee80211_do_assoc(sdata)) { struct cfg80211_bss *bss = ifmgd->assoc_data->bss; + struct ieee80211_event event = { + .type = MLME_EVENT, + .u.mlme.data = ASSOC_EVENT, + .u.mlme.status = MLME_TIMEOUT, + }; ieee80211_destroy_assoc_data(sdata, false); cfg80211_assoc_timeout(sdata->dev, bss); + drv_event_callback(sdata->local, sdata, &event); } } else if (ifmgd->assoc_data && ifmgd->assoc_data->timeout_started) run_again(sdata, ifmgd->assoc_data->timeout); @@ -3905,12 +3958,8 @@ static void ieee80211_sta_bcn_mon_timer(unsigned long data) { struct ieee80211_sub_if_data *sdata = (struct ieee80211_sub_if_data *) data; - struct ieee80211_local *local = sdata->local; struct ieee80211_if_managed *ifmgd = &sdata->u.mgd; - if (local->quiescing) - return; - if (sdata->vif.csa_active && !ifmgd->csa_waiting_bcn) return; @@ -3926,9 +3975,6 @@ static void ieee80211_sta_conn_mon_timer(unsigned long data) struct ieee80211_if_managed *ifmgd = &sdata->u.mgd; struct ieee80211_local *local = sdata->local; - if (local->quiescing) - return; - if (sdata->vif.csa_active && !ifmgd->csa_waiting_bcn) return; @@ -3991,6 +4037,34 @@ void ieee80211_mgd_quiesce(struct ieee80211_sub_if_data *sdata) IEEE80211_DEAUTH_FRAME_LEN); } + /* This is a bit of a hack - we should find a better and more generic + * solution to this. Normally when suspending, cfg80211 will in fact + * deauthenticate. However, it doesn't (and cannot) stop an ongoing + * auth (not so important) or assoc (this is the problem) process. + * + * As a consequence, it can happen that we are in the process of both + * associating and suspending, and receive an association response + * after cfg80211 has checked if it needs to disconnect, but before + * we actually set the flag to drop incoming frames. This will then + * cause the workqueue flush to process the association response in + * the suspend, resulting in a successful association just before it + * tries to remove the interface from the driver, which now though + * has a channel context assigned ... this results in issues. + * + * To work around this (for now) simply deauth here again if we're + * now connected. + */ + if (ifmgd->associated && !sdata->local->wowlan) { + u8 bssid[ETH_ALEN]; + struct cfg80211_deauth_request req = { + .reason_code = WLAN_REASON_DEAUTH_LEAVING, + .bssid = bssid, + }; + + memcpy(bssid, ifmgd->associated->bssid, ETH_ALEN); + ieee80211_mgd_deauth(sdata, &req); + } + sdata_unlock(sdata); } @@ -4379,6 +4453,10 @@ static int ieee80211_prep_connection(struct ieee80211_sub_if_data *sdata, } else WARN_ON_ONCE(!ether_addr_equal(ifmgd->bssid, cbss->bssid)); + /* Cancel scan to ensure that nothing interferes with connection */ + if (local->scanning) + ieee80211_scan_cancel(local); + return 0; } @@ -4467,8 +4545,9 @@ int ieee80211_mgd_auth(struct ieee80211_sub_if_data *sdata, WLAN_REASON_UNSPECIFIED, false, frame_buf); - cfg80211_tx_mlme_mgmt(sdata->dev, frame_buf, - sizeof(frame_buf)); + ieee80211_report_disconnect(sdata, frame_buf, + sizeof(frame_buf), true, + WLAN_REASON_UNSPECIFIED); } sdata_info(sdata, "authenticate with %pM\n", req->bss->bssid); @@ -4488,7 +4567,7 @@ int ieee80211_mgd_auth(struct ieee80211_sub_if_data *sdata, return 0; err_clear: - memset(ifmgd->bssid, 0, ETH_ALEN); + eth_zero_addr(ifmgd->bssid); ieee80211_bss_info_change_notify(sdata, BSS_CHANGED_BSSID); ifmgd->auth_data = NULL; err_free: @@ -4568,8 +4647,9 @@ int ieee80211_mgd_assoc(struct ieee80211_sub_if_data *sdata, WLAN_REASON_UNSPECIFIED, false, frame_buf); - cfg80211_tx_mlme_mgmt(sdata->dev, frame_buf, - sizeof(frame_buf)); + ieee80211_report_disconnect(sdata, frame_buf, + sizeof(frame_buf), true, + WLAN_REASON_UNSPECIFIED); } if (ifmgd->auth_data && !ifmgd->auth_data->done) { @@ -4831,7 +4911,7 @@ int ieee80211_mgd_assoc(struct ieee80211_sub_if_data *sdata, return 0; err_clear: - memset(ifmgd->bssid, 0, ETH_ALEN); + eth_zero_addr(ifmgd->bssid); ieee80211_bss_info_change_notify(sdata, BSS_CHANGED_BSSID); ifmgd->assoc_data = NULL; err_free: @@ -4859,8 +4939,9 @@ int ieee80211_mgd_deauth(struct ieee80211_sub_if_data *sdata, req->reason_code, tx, frame_buf); ieee80211_destroy_auth_data(sdata, false); - cfg80211_tx_mlme_mgmt(sdata->dev, frame_buf, - IEEE80211_DEAUTH_FRAME_LEN); + ieee80211_report_disconnect(sdata, frame_buf, + sizeof(frame_buf), true, + req->reason_code); return 0; } @@ -4874,8 +4955,9 @@ int ieee80211_mgd_deauth(struct ieee80211_sub_if_data *sdata, ieee80211_set_disassoc(sdata, IEEE80211_STYPE_DEAUTH, req->reason_code, tx, frame_buf); - cfg80211_tx_mlme_mgmt(sdata->dev, frame_buf, - IEEE80211_DEAUTH_FRAME_LEN); + ieee80211_report_disconnect(sdata, frame_buf, + sizeof(frame_buf), true, + req->reason_code); return 0; } @@ -4907,8 +4989,8 @@ int ieee80211_mgd_disassoc(struct ieee80211_sub_if_data *sdata, req->reason_code, !req->local_state_change, frame_buf); - cfg80211_tx_mlme_mgmt(sdata->dev, frame_buf, - IEEE80211_DEAUTH_FRAME_LEN); + ieee80211_report_disconnect(sdata, frame_buf, sizeof(frame_buf), true, + req->reason_code); return 0; } diff --git a/net/mac80211/pm.c b/net/mac80211/pm.c index ca405b6b686d..ac6ad6238e3a 100644 --- a/net/mac80211/pm.c +++ b/net/mac80211/pm.c @@ -59,9 +59,26 @@ int __ieee80211_suspend(struct ieee80211_hw *hw, struct cfg80211_wowlan *wowlan) cancel_work_sync(&local->dynamic_ps_enable_work); del_timer_sync(&local->dynamic_ps_timer); - local->wowlan = wowlan && local->open_count; + local->wowlan = wowlan; if (local->wowlan) { - int err = drv_suspend(local, wowlan); + int err; + + /* Drivers don't expect to suspend while some operations like + * authenticating or associating are in progress. It doesn't + * make sense anyway to accept that, since the authentication + * or association would never finish since the driver can't do + * that on its own. + * Thus, clean up in-progress auth/assoc first. + */ + list_for_each_entry(sdata, &local->interfaces, list) { + if (!ieee80211_sdata_running(sdata)) + continue; + if (sdata->vif.type != NL80211_IFTYPE_STATION) + continue; + ieee80211_mgd_quiesce(sdata); + } + + err = drv_suspend(local, wowlan); if (err < 0) { local->quiescing = false; local->wowlan = false; @@ -80,6 +97,13 @@ int __ieee80211_suspend(struct ieee80211_hw *hw, struct cfg80211_wowlan *wowlan) return err; } else if (err > 0) { WARN_ON(err != 1); + /* cfg80211 will call back into mac80211 to disconnect + * all interfaces, allow that to proceed properly + */ + ieee80211_wake_queues_by_reason(hw, + IEEE80211_MAX_QUEUE_MAP, + IEEE80211_QUEUE_STOP_REASON_SUSPEND, + false); return err; } else { goto suspend; diff --git a/net/mac80211/rc80211_minstrel.c b/net/mac80211/rc80211_minstrel.c index ef6e8a6c4253..247552a7f6c2 100644 --- a/net/mac80211/rc80211_minstrel.c +++ b/net/mac80211/rc80211_minstrel.c @@ -69,14 +69,39 @@ rix_to_ndx(struct minstrel_sta_info *mi, int rix) return i; } +/* return current EMWA throughput */ +int minstrel_get_tp_avg(struct minstrel_rate *mr, int prob_ewma) +{ + int usecs; + + usecs = mr->perfect_tx_time; + if (!usecs) + usecs = 1000000; + + /* reset thr. below 10% success */ + if (mr->stats.prob_ewma < MINSTREL_FRAC(10, 100)) + return 0; + + if (prob_ewma > MINSTREL_FRAC(90, 100)) + return MINSTREL_TRUNC(100000 * (MINSTREL_FRAC(90, 100) / usecs)); + else + return MINSTREL_TRUNC(100000 * (prob_ewma / usecs)); +} + /* find & sort topmost throughput rates */ static inline void minstrel_sort_best_tp_rates(struct minstrel_sta_info *mi, int i, u8 *tp_list) { int j = MAX_THR_RATES; + struct minstrel_rate_stats *tmp_mrs = &mi->r[j - 1].stats; + struct minstrel_rate_stats *cur_mrs = &mi->r[i].stats; - while (j > 0 && mi->r[i].stats.cur_tp > mi->r[tp_list[j - 1]].stats.cur_tp) + while (j > 0 && (minstrel_get_tp_avg(&mi->r[i], cur_mrs->prob_ewma) > + minstrel_get_tp_avg(&mi->r[tp_list[j - 1]], tmp_mrs->prob_ewma))) { j--; + tmp_mrs = &mi->r[tp_list[j - 1]].stats; + } + if (j < MAX_THR_RATES - 1) memmove(&tp_list[j + 1], &tp_list[j], MAX_THR_RATES - (j + 1)); if (j < MAX_THR_RATES) @@ -127,13 +152,47 @@ minstrel_update_rates(struct minstrel_priv *mp, struct minstrel_sta_info *mi) rate_control_set_rates(mp->hw, mi->sta, ratetbl); } +/* +* Recalculate statistics and counters of a given rate +*/ +void +minstrel_calc_rate_stats(struct minstrel_rate_stats *mrs) +{ + if (unlikely(mrs->attempts > 0)) { + mrs->sample_skipped = 0; + mrs->cur_prob = MINSTREL_FRAC(mrs->success, mrs->attempts); + if (unlikely(!mrs->att_hist)) { + mrs->prob_ewma = mrs->cur_prob; + } else { + /* update exponential weighted moving variance */ + mrs->prob_ewmsd = minstrel_ewmsd(mrs->prob_ewmsd, + mrs->cur_prob, + mrs->prob_ewma, + EWMA_LEVEL); + + /*update exponential weighted moving avarage */ + mrs->prob_ewma = minstrel_ewma(mrs->prob_ewma, + mrs->cur_prob, + EWMA_LEVEL); + } + mrs->att_hist += mrs->attempts; + mrs->succ_hist += mrs->success; + } else { + mrs->sample_skipped++; + } + + mrs->last_success = mrs->success; + mrs->last_attempts = mrs->attempts; + mrs->success = 0; + mrs->attempts = 0; +} + static void minstrel_update_stats(struct minstrel_priv *mp, struct minstrel_sta_info *mi) { u8 tmp_tp_rate[MAX_THR_RATES]; u8 tmp_prob_rate = 0; - u32 usecs; - int i; + int i, tmp_cur_tp, tmp_prob_tp; for (i = 0; i < MAX_THR_RATES; i++) tmp_tp_rate[i] = 0; @@ -141,38 +200,15 @@ minstrel_update_stats(struct minstrel_priv *mp, struct minstrel_sta_info *mi) for (i = 0; i < mi->n_rates; i++) { struct minstrel_rate *mr = &mi->r[i]; struct minstrel_rate_stats *mrs = &mi->r[i].stats; + struct minstrel_rate_stats *tmp_mrs = &mi->r[tmp_prob_rate].stats; - usecs = mr->perfect_tx_time; - if (!usecs) - usecs = 1000000; - - if (unlikely(mrs->attempts > 0)) { - mrs->sample_skipped = 0; - mrs->cur_prob = MINSTREL_FRAC(mrs->success, - mrs->attempts); - mrs->succ_hist += mrs->success; - mrs->att_hist += mrs->attempts; - mrs->probability = minstrel_ewma(mrs->probability, - mrs->cur_prob, - EWMA_LEVEL); - } else - mrs->sample_skipped++; - - mrs->last_success = mrs->success; - mrs->last_attempts = mrs->attempts; - mrs->success = 0; - mrs->attempts = 0; - - /* Update throughput per rate, reset thr. below 10% success */ - if (mrs->probability < MINSTREL_FRAC(10, 100)) - mrs->cur_tp = 0; - else - mrs->cur_tp = mrs->probability * (1000000 / usecs); + /* Update statistics of success probability per rate */ + minstrel_calc_rate_stats(mrs); /* Sample less often below the 10% chance of success. * Sample less often above the 95% chance of success. */ - if (mrs->probability > MINSTREL_FRAC(95, 100) || - mrs->probability < MINSTREL_FRAC(10, 100)) { + if (mrs->prob_ewma > MINSTREL_FRAC(95, 100) || + mrs->prob_ewma < MINSTREL_FRAC(10, 100)) { mr->adjusted_retry_count = mrs->retry_count >> 1; if (mr->adjusted_retry_count > 2) mr->adjusted_retry_count = 2; @@ -192,11 +228,14 @@ minstrel_update_stats(struct minstrel_priv *mp, struct minstrel_sta_info *mi) * choose the maximum throughput rate as max_prob_rate * (2) if all success probabilities < 95%, the rate with * highest success probability is chosen as max_prob_rate */ - if (mrs->probability >= MINSTREL_FRAC(95, 100)) { - if (mrs->cur_tp >= mi->r[tmp_prob_rate].stats.cur_tp) + if (mrs->prob_ewma >= MINSTREL_FRAC(95, 100)) { + tmp_cur_tp = minstrel_get_tp_avg(mr, mrs->prob_ewma); + tmp_prob_tp = minstrel_get_tp_avg(&mi->r[tmp_prob_rate], + tmp_mrs->prob_ewma); + if (tmp_cur_tp >= tmp_prob_tp) tmp_prob_rate = i; } else { - if (mrs->probability >= mi->r[tmp_prob_rate].stats.probability) + if (mrs->prob_ewma >= tmp_mrs->prob_ewma) tmp_prob_rate = i; } } @@ -215,7 +254,7 @@ minstrel_update_stats(struct minstrel_priv *mp, struct minstrel_sta_info *mi) #endif /* Reset update timer */ - mi->stats_update = jiffies; + mi->last_stats_update = jiffies; minstrel_update_rates(mp, mi); } @@ -253,7 +292,7 @@ minstrel_tx_status(void *priv, struct ieee80211_supported_band *sband, if (mi->sample_deferred > 0) mi->sample_deferred--; - if (time_after(jiffies, mi->stats_update + + if (time_after(jiffies, mi->last_stats_update + (mp->update_interval * HZ) / 1000)) minstrel_update_stats(mp, mi); } @@ -385,7 +424,7 @@ minstrel_get_rate(void *priv, struct ieee80211_sta *sta, * has a probability of >95%, we shouldn't be attempting * to use it, as this only wastes precious airtime */ if (!mrr_capable && - (mi->r[ndx].stats.probability > MINSTREL_FRAC(95, 100))) + (mi->r[ndx].stats.prob_ewma > MINSTREL_FRAC(95, 100))) return; mi->prev_sample = true; @@ -519,7 +558,7 @@ minstrel_rate_init(void *priv, struct ieee80211_supported_band *sband, } mi->n_rates = n; - mi->stats_update = jiffies; + mi->last_stats_update = jiffies; init_sample_table(mi); minstrel_update_rates(mp, mi); @@ -553,7 +592,7 @@ minstrel_alloc_sta(void *priv, struct ieee80211_sta *sta, gfp_t gfp) if (!mi->sample_table) goto error1; - mi->stats_update = jiffies; + mi->last_stats_update = jiffies; return mi; error1: @@ -663,12 +702,18 @@ minstrel_free(void *priv) static u32 minstrel_get_expected_throughput(void *priv_sta) { struct minstrel_sta_info *mi = priv_sta; + struct minstrel_rate_stats *tmp_mrs; int idx = mi->max_tp_rate[0]; + int tmp_cur_tp; /* convert pkt per sec in kbps (1200 is the average pkt size used for * computing cur_tp */ - return MINSTREL_TRUNC(mi->r[idx].stats.cur_tp) * 1200 * 8 / 1024; + tmp_mrs = &mi->r[idx].stats; + tmp_cur_tp = minstrel_get_tp_avg(&mi->r[idx], tmp_mrs->prob_ewma); + tmp_cur_tp = tmp_cur_tp * 1200 * 8 / 1024; + + return tmp_cur_tp; } const struct rate_control_ops mac80211_minstrel = { diff --git a/net/mac80211/rc80211_minstrel.h b/net/mac80211/rc80211_minstrel.h index 410efe620c57..c230bbe93262 100644 --- a/net/mac80211/rc80211_minstrel.h +++ b/net/mac80211/rc80211_minstrel.h @@ -13,7 +13,6 @@ #define EWMA_DIV 128 #define SAMPLE_COLUMNS 10 /* number of columns in sample table */ - /* scaled fraction values */ #define MINSTREL_SCALE 16 #define MINSTREL_FRAC(val, div) (((val) << MINSTREL_SCALE) / div) @@ -24,11 +23,34 @@ /* * Perform EWMA (Exponentially Weighted Moving Average) calculation - */ + */ static inline int minstrel_ewma(int old, int new, int weight) { - return (new * (EWMA_DIV - weight) + old * weight) / EWMA_DIV; + int diff, incr; + + diff = new - old; + incr = (EWMA_DIV - weight) * diff / EWMA_DIV; + + return old + incr; +} + +/* + * Perform EWMSD (Exponentially Weighted Moving Standard Deviation) calculation + */ +static inline int +minstrel_ewmsd(int old_ewmsd, int cur_prob, int prob_ewma, int weight) +{ + int diff, incr, tmp_var; + + /* calculate exponential weighted moving variance */ + diff = MINSTREL_TRUNC((cur_prob - prob_ewma) * 1000000); + incr = (EWMA_DIV - weight) * diff / EWMA_DIV; + tmp_var = old_ewmsd * old_ewmsd; + tmp_var = weight * (tmp_var + diff * incr / 1000000) / EWMA_DIV; + + /* return standard deviation */ + return (u16) int_sqrt(tmp_var); } struct minstrel_rate_stats { @@ -39,11 +61,13 @@ struct minstrel_rate_stats { /* total attempts/success counters */ u64 att_hist, succ_hist; - /* current throughput */ - unsigned int cur_tp; - - /* packet delivery probabilities */ - unsigned int cur_prob, probability; + /* statistis of packet delivery probability + * cur_prob - current prob within last update intervall + * prob_ewma - exponential weighted moving average of prob + * prob_ewmsd - exp. weighted moving standard deviation of prob */ + unsigned int cur_prob; + unsigned int prob_ewma; + u16 prob_ewmsd; /* maximum retry counts */ u8 retry_count; @@ -71,7 +95,7 @@ struct minstrel_rate { struct minstrel_sta_info { struct ieee80211_sta *sta; - unsigned long stats_update; + unsigned long last_stats_update; unsigned int sp_ack_dur; unsigned int rate_avg; @@ -95,6 +119,7 @@ struct minstrel_sta_info { #ifdef CONFIG_MAC80211_DEBUGFS struct dentry *dbg_stats; + struct dentry *dbg_stats_csv; #endif }; @@ -121,7 +146,6 @@ struct minstrel_priv { u32 fixed_rate_idx; struct dentry *dbg_fixed_rate; #endif - }; struct minstrel_debugfs_info { @@ -133,8 +157,13 @@ extern const struct rate_control_ops mac80211_minstrel; void minstrel_add_sta_debugfs(void *priv, void *priv_sta, struct dentry *dir); void minstrel_remove_sta_debugfs(void *priv, void *priv_sta); +/* Recalculate success probabilities and counters for a given rate using EWMA */ +void minstrel_calc_rate_stats(struct minstrel_rate_stats *mrs); +int minstrel_get_tp_avg(struct minstrel_rate *mr, int prob_ewma); + /* debugfs */ int minstrel_stats_open(struct inode *inode, struct file *file); +int minstrel_stats_csv_open(struct inode *inode, struct file *file); ssize_t minstrel_stats_read(struct file *file, char __user *buf, size_t len, loff_t *ppos); int minstrel_stats_release(struct inode *inode, struct file *file); diff --git a/net/mac80211/rc80211_minstrel_debugfs.c b/net/mac80211/rc80211_minstrel_debugfs.c index 2acab1bcaa4b..1db5f7c3318a 100644 --- a/net/mac80211/rc80211_minstrel_debugfs.c +++ b/net/mac80211/rc80211_minstrel_debugfs.c @@ -54,12 +54,28 @@ #include <net/mac80211.h> #include "rc80211_minstrel.h" +ssize_t +minstrel_stats_read(struct file *file, char __user *buf, size_t len, loff_t *ppos) +{ + struct minstrel_debugfs_info *ms; + + ms = file->private_data; + return simple_read_from_buffer(buf, len, ppos, ms->buf, ms->len); +} + +int +minstrel_stats_release(struct inode *inode, struct file *file) +{ + kfree(file->private_data); + return 0; +} + int minstrel_stats_open(struct inode *inode, struct file *file) { struct minstrel_sta_info *mi = inode->i_private; struct minstrel_debugfs_info *ms; - unsigned int i, tp, prob, eprob; + unsigned int i, tp_max, tp_avg, prob, eprob; char *p; ms = kmalloc(2048, GFP_KERNEL); @@ -68,8 +84,14 @@ minstrel_stats_open(struct inode *inode, struct file *file) file->private_data = ms; p = ms->buf; - p += sprintf(p, "rate tpt eprob *prob" - " *ok(*cum) ok( cum)\n"); + p += sprintf(p, "\n"); + p += sprintf(p, "best __________rate_________ ______" + "statistics______ ________last_______ " + "______sum-of________\n"); + p += sprintf(p, "rate [name idx airtime max_tp] [ ø(tp) ø(prob) " + "sd(prob)] [prob.|retry|suc|att] " + "[#success | #attempts]\n"); + for (i = 0; i < mi->n_rates; i++) { struct minstrel_rate *mr = &mi->r[i]; struct minstrel_rate_stats *mrs = &mi->r[i].stats; @@ -79,18 +101,26 @@ minstrel_stats_open(struct inode *inode, struct file *file) *(p++) = (i == mi->max_tp_rate[2]) ? 'C' : ' '; *(p++) = (i == mi->max_tp_rate[3]) ? 'D' : ' '; *(p++) = (i == mi->max_prob_rate) ? 'P' : ' '; - p += sprintf(p, "%3u%s", mr->bitrate / 2, + + p += sprintf(p, " %3u%s ", mr->bitrate / 2, (mr->bitrate & 1 ? ".5" : " ")); + p += sprintf(p, "%3u ", i); + p += sprintf(p, "%6u ", mr->perfect_tx_time); - tp = MINSTREL_TRUNC(mrs->cur_tp / 10); + tp_max = minstrel_get_tp_avg(mr, MINSTREL_FRAC(100,100)); + tp_avg = minstrel_get_tp_avg(mr, mrs->prob_ewma); prob = MINSTREL_TRUNC(mrs->cur_prob * 1000); - eprob = MINSTREL_TRUNC(mrs->probability * 1000); + eprob = MINSTREL_TRUNC(mrs->prob_ewma * 1000); - p += sprintf(p, " %4u.%1u %3u.%1u %3u.%1u" - " %4u(%4u) %9llu(%9llu)\n", - tp / 10, tp % 10, + p += sprintf(p, "%4u.%1u %4u.%1u %3u.%1u %3u.%1u" + " %3u.%1u %3u %3u %-3u " + "%9llu %-9llu\n", + tp_max / 10, tp_max % 10, + tp_avg / 10, tp_avg % 10, eprob / 10, eprob % 10, + mrs->prob_ewmsd / 10, mrs->prob_ewmsd % 10, prob / 10, prob % 10, + mrs->retry_count, mrs->last_success, mrs->last_attempts, (unsigned long long)mrs->succ_hist, @@ -107,25 +137,75 @@ minstrel_stats_open(struct inode *inode, struct file *file) return 0; } -ssize_t -minstrel_stats_read(struct file *file, char __user *buf, size_t len, loff_t *ppos) +static const struct file_operations minstrel_stat_fops = { + .owner = THIS_MODULE, + .open = minstrel_stats_open, + .read = minstrel_stats_read, + .release = minstrel_stats_release, + .llseek = default_llseek, +}; + +int +minstrel_stats_csv_open(struct inode *inode, struct file *file) { + struct minstrel_sta_info *mi = inode->i_private; struct minstrel_debugfs_info *ms; + unsigned int i, tp_max, tp_avg, prob, eprob; + char *p; - ms = file->private_data; - return simple_read_from_buffer(buf, len, ppos, ms->buf, ms->len); -} + ms = kmalloc(2048, GFP_KERNEL); + if (!ms) + return -ENOMEM; + + file->private_data = ms; + p = ms->buf; + + for (i = 0; i < mi->n_rates; i++) { + struct minstrel_rate *mr = &mi->r[i]; + struct minstrel_rate_stats *mrs = &mi->r[i].stats; + + p += sprintf(p, "%s" ,((i == mi->max_tp_rate[0]) ? "A" : "")); + p += sprintf(p, "%s" ,((i == mi->max_tp_rate[1]) ? "B" : "")); + p += sprintf(p, "%s" ,((i == mi->max_tp_rate[2]) ? "C" : "")); + p += sprintf(p, "%s" ,((i == mi->max_tp_rate[3]) ? "D" : "")); + p += sprintf(p, "%s" ,((i == mi->max_prob_rate) ? "P" : "")); + + p += sprintf(p, ",%u%s", mr->bitrate / 2, + (mr->bitrate & 1 ? ".5," : ",")); + p += sprintf(p, "%u,", i); + p += sprintf(p, "%u,",mr->perfect_tx_time); + + tp_max = minstrel_get_tp_avg(mr, MINSTREL_FRAC(100,100)); + tp_avg = minstrel_get_tp_avg(mr, mrs->prob_ewma); + prob = MINSTREL_TRUNC(mrs->cur_prob * 1000); + eprob = MINSTREL_TRUNC(mrs->prob_ewma * 1000); + + p += sprintf(p, "%u.%u,%u.%u,%u.%u,%u.%u,%u.%u,%u,%u,%u," + "%llu,%llu,%d,%d\n", + tp_max / 10, tp_max % 10, + tp_avg / 10, tp_avg % 10, + eprob / 10, eprob % 10, + mrs->prob_ewmsd / 10, mrs->prob_ewmsd % 10, + prob / 10, prob % 10, + mrs->retry_count, + mrs->last_success, + mrs->last_attempts, + (unsigned long long)mrs->succ_hist, + (unsigned long long)mrs->att_hist, + mi->total_packets - mi->sample_packets, + mi->sample_packets); + + } + ms->len = p - ms->buf; + + WARN_ON(ms->len + sizeof(*ms) > 2048); -int -minstrel_stats_release(struct inode *inode, struct file *file) -{ - kfree(file->private_data); return 0; } -static const struct file_operations minstrel_stat_fops = { +static const struct file_operations minstrel_stat_csv_fops = { .owner = THIS_MODULE, - .open = minstrel_stats_open, + .open = minstrel_stats_csv_open, .read = minstrel_stats_read, .release = minstrel_stats_release, .llseek = default_llseek, @@ -138,6 +218,9 @@ minstrel_add_sta_debugfs(void *priv, void *priv_sta, struct dentry *dir) mi->dbg_stats = debugfs_create_file("rc_stats", S_IRUGO, dir, mi, &minstrel_stat_fops); + + mi->dbg_stats_csv = debugfs_create_file("rc_stats_csv", S_IRUGO, dir, + mi, &minstrel_stat_csv_fops); } void @@ -146,4 +229,6 @@ minstrel_remove_sta_debugfs(void *priv, void *priv_sta) struct minstrel_sta_info *mi = priv_sta; debugfs_remove(mi->dbg_stats); + + debugfs_remove(mi->dbg_stats_csv); } diff --git a/net/mac80211/rc80211_minstrel_ht.c b/net/mac80211/rc80211_minstrel_ht.c index 80452cfd2dc5..7430a1df2ab1 100644 --- a/net/mac80211/rc80211_minstrel_ht.c +++ b/net/mac80211/rc80211_minstrel_ht.c @@ -17,10 +17,11 @@ #include "rc80211_minstrel.h" #include "rc80211_minstrel_ht.h" +#define AVG_AMPDU_SIZE 16 #define AVG_PKT_SIZE 1200 /* Number of bits for an average sized packet */ -#define MCS_NBITS (AVG_PKT_SIZE << 3) +#define MCS_NBITS ((AVG_PKT_SIZE * AVG_AMPDU_SIZE) << 3) /* Number of symbols for a packet with (bps) bits per symbol */ #define MCS_NSYMS(bps) DIV_ROUND_UP(MCS_NBITS, (bps)) @@ -33,7 +34,8 @@ ) /* Transmit duration for the raw data part of an average sized packet */ -#define MCS_DURATION(streams, sgi, bps) MCS_SYMBOL_TIME(sgi, MCS_NSYMS((streams) * (bps))) +#define MCS_DURATION(streams, sgi, bps) \ + (MCS_SYMBOL_TIME(sgi, MCS_NSYMS((streams) * (bps))) / AVG_AMPDU_SIZE) #define BW_20 0 #define BW_40 1 @@ -311,67 +313,35 @@ minstrel_get_ratestats(struct minstrel_ht_sta *mi, int index) return &mi->groups[index / MCS_GROUP_RATES].rates[index % MCS_GROUP_RATES]; } - /* - * Recalculate success probabilities and counters for a rate using EWMA + * Return current throughput based on the average A-MPDU length, taking into + * account the expected number of retransmissions and their expected length */ -static void -minstrel_calc_rate_ewma(struct minstrel_rate_stats *mr) +int +minstrel_ht_get_tp_avg(struct minstrel_ht_sta *mi, int group, int rate, + int prob_ewma) { - if (unlikely(mr->attempts > 0)) { - mr->sample_skipped = 0; - mr->cur_prob = MINSTREL_FRAC(mr->success, mr->attempts); - if (!mr->att_hist) - mr->probability = mr->cur_prob; - else - mr->probability = minstrel_ewma(mr->probability, - mr->cur_prob, EWMA_LEVEL); - mr->att_hist += mr->attempts; - mr->succ_hist += mr->success; - } else { - mr->sample_skipped++; - } - mr->last_success = mr->success; - mr->last_attempts = mr->attempts; - mr->success = 0; - mr->attempts = 0; -} - -/* - * Calculate throughput based on the average A-MPDU length, taking into account - * the expected number of retransmissions and their expected length - */ -static void -minstrel_ht_calc_tp(struct minstrel_ht_sta *mi, int group, int rate) -{ - struct minstrel_rate_stats *mr; unsigned int nsecs = 0; - unsigned int tp; - unsigned int prob; - mr = &mi->groups[group].rates[rate]; - prob = mr->probability; - - if (prob < MINSTREL_FRAC(1, 10)) { - mr->cur_tp = 0; - return; - } - - /* - * For the throughput calculation, limit the probability value to 90% to - * account for collision related packet error rate fluctuation - */ - if (prob > MINSTREL_FRAC(9, 10)) - prob = MINSTREL_FRAC(9, 10); + /* do not account throughput if sucess prob is below 10% */ + if (prob_ewma < MINSTREL_FRAC(10, 100)) + return 0; if (group != MINSTREL_CCK_GROUP) nsecs = 1000 * mi->overhead / MINSTREL_TRUNC(mi->avg_ampdu_len); nsecs += minstrel_mcs_groups[group].duration[rate]; - /* prob is scaled - see MINSTREL_FRAC above */ - tp = 1000000 * ((prob * 1000) / nsecs); - mr->cur_tp = MINSTREL_TRUNC(tp); + /* + * For the throughput calculation, limit the probability value to 90% to + * account for collision related packet error rate fluctuation + * (prob is scaled - see MINSTREL_FRAC above) + */ + if (prob_ewma > MINSTREL_FRAC(90, 100)) + return MINSTREL_TRUNC(100000 * ((MINSTREL_FRAC(90, 100) * 1000) + / nsecs)); + else + return MINSTREL_TRUNC(100000 * ((prob_ewma * 1000) / nsecs)); } /* @@ -385,22 +355,23 @@ static void minstrel_ht_sort_best_tp_rates(struct minstrel_ht_sta *mi, u16 index, u16 *tp_list) { - int cur_group, cur_idx, cur_thr, cur_prob; - int tmp_group, tmp_idx, tmp_thr, tmp_prob; + int cur_group, cur_idx, cur_tp_avg, cur_prob; + int tmp_group, tmp_idx, tmp_tp_avg, tmp_prob; int j = MAX_THR_RATES; cur_group = index / MCS_GROUP_RATES; cur_idx = index % MCS_GROUP_RATES; - cur_thr = mi->groups[cur_group].rates[cur_idx].cur_tp; - cur_prob = mi->groups[cur_group].rates[cur_idx].probability; + cur_prob = mi->groups[cur_group].rates[cur_idx].prob_ewma; + cur_tp_avg = minstrel_ht_get_tp_avg(mi, cur_group, cur_idx, cur_prob); do { tmp_group = tp_list[j - 1] / MCS_GROUP_RATES; tmp_idx = tp_list[j - 1] % MCS_GROUP_RATES; - tmp_thr = mi->groups[tmp_group].rates[tmp_idx].cur_tp; - tmp_prob = mi->groups[tmp_group].rates[tmp_idx].probability; - if (cur_thr < tmp_thr || - (cur_thr == tmp_thr && cur_prob <= tmp_prob)) + tmp_prob = mi->groups[tmp_group].rates[tmp_idx].prob_ewma; + tmp_tp_avg = minstrel_ht_get_tp_avg(mi, tmp_group, tmp_idx, + tmp_prob); + if (cur_tp_avg < tmp_tp_avg || + (cur_tp_avg == tmp_tp_avg && cur_prob <= tmp_prob)) break; j--; } while (j > 0); @@ -420,16 +391,21 @@ static void minstrel_ht_set_best_prob_rate(struct minstrel_ht_sta *mi, u16 index) { struct minstrel_mcs_group_data *mg; - struct minstrel_rate_stats *mr; - int tmp_group, tmp_idx, tmp_tp, tmp_prob, max_tp_group; + struct minstrel_rate_stats *mrs; + int tmp_group, tmp_idx, tmp_tp_avg, tmp_prob; + int max_tp_group, cur_tp_avg, cur_group, cur_idx; + int max_gpr_group, max_gpr_idx; + int max_gpr_tp_avg, max_gpr_prob; + cur_group = index / MCS_GROUP_RATES; + cur_idx = index % MCS_GROUP_RATES; mg = &mi->groups[index / MCS_GROUP_RATES]; - mr = &mg->rates[index % MCS_GROUP_RATES]; + mrs = &mg->rates[index % MCS_GROUP_RATES]; tmp_group = mi->max_prob_rate / MCS_GROUP_RATES; tmp_idx = mi->max_prob_rate % MCS_GROUP_RATES; - tmp_tp = mi->groups[tmp_group].rates[tmp_idx].cur_tp; - tmp_prob = mi->groups[tmp_group].rates[tmp_idx].probability; + tmp_prob = mi->groups[tmp_group].rates[tmp_idx].prob_ewma; + tmp_tp_avg = minstrel_ht_get_tp_avg(mi, tmp_group, tmp_idx, tmp_prob); /* if max_tp_rate[0] is from MCS_GROUP max_prob_rate get selected from * MCS_GROUP as well as CCK_GROUP rates do not allow aggregation */ @@ -438,15 +414,24 @@ minstrel_ht_set_best_prob_rate(struct minstrel_ht_sta *mi, u16 index) (max_tp_group != MINSTREL_CCK_GROUP)) return; - if (mr->probability > MINSTREL_FRAC(75, 100)) { - if (mr->cur_tp > tmp_tp) + if (mrs->prob_ewma > MINSTREL_FRAC(75, 100)) { + cur_tp_avg = minstrel_ht_get_tp_avg(mi, cur_group, cur_idx, + mrs->prob_ewma); + if (cur_tp_avg > tmp_tp_avg) mi->max_prob_rate = index; - if (mr->cur_tp > mg->rates[mg->max_group_prob_rate].cur_tp) + + max_gpr_group = mg->max_group_prob_rate / MCS_GROUP_RATES; + max_gpr_idx = mg->max_group_prob_rate % MCS_GROUP_RATES; + max_gpr_prob = mi->groups[max_gpr_group].rates[max_gpr_idx].prob_ewma; + max_gpr_tp_avg = minstrel_ht_get_tp_avg(mi, max_gpr_group, + max_gpr_idx, + max_gpr_prob); + if (cur_tp_avg > max_gpr_tp_avg) mg->max_group_prob_rate = index; } else { - if (mr->probability > tmp_prob) + if (mrs->prob_ewma > tmp_prob) mi->max_prob_rate = index; - if (mr->probability > mg->rates[mg->max_group_prob_rate].probability) + if (mrs->prob_ewma > mg->rates[mg->max_group_prob_rate].prob_ewma) mg->max_group_prob_rate = index; } } @@ -463,16 +448,18 @@ minstrel_ht_assign_best_tp_rates(struct minstrel_ht_sta *mi, u16 tmp_mcs_tp_rate[MAX_THR_RATES], u16 tmp_cck_tp_rate[MAX_THR_RATES]) { - unsigned int tmp_group, tmp_idx, tmp_cck_tp, tmp_mcs_tp; + unsigned int tmp_group, tmp_idx, tmp_cck_tp, tmp_mcs_tp, tmp_prob; int i; tmp_group = tmp_cck_tp_rate[0] / MCS_GROUP_RATES; tmp_idx = tmp_cck_tp_rate[0] % MCS_GROUP_RATES; - tmp_cck_tp = mi->groups[tmp_group].rates[tmp_idx].cur_tp; + tmp_prob = mi->groups[tmp_group].rates[tmp_idx].prob_ewma; + tmp_cck_tp = minstrel_ht_get_tp_avg(mi, tmp_group, tmp_idx, tmp_prob); tmp_group = tmp_mcs_tp_rate[0] / MCS_GROUP_RATES; tmp_idx = tmp_mcs_tp_rate[0] % MCS_GROUP_RATES; - tmp_mcs_tp = mi->groups[tmp_group].rates[tmp_idx].cur_tp; + tmp_prob = mi->groups[tmp_group].rates[tmp_idx].prob_ewma; + tmp_mcs_tp = minstrel_ht_get_tp_avg(mi, tmp_group, tmp_idx, tmp_prob); if (tmp_cck_tp > tmp_mcs_tp) { for(i = 0; i < MAX_THR_RATES; i++) { @@ -491,8 +478,7 @@ static inline void minstrel_ht_prob_rate_reduce_streams(struct minstrel_ht_sta *mi) { struct minstrel_mcs_group_data *mg; - struct minstrel_rate_stats *mr; - int tmp_max_streams, group; + int tmp_max_streams, group, tmp_idx, tmp_prob; int tmp_tp = 0; tmp_max_streams = minstrel_mcs_groups[mi->max_tp_rate[0] / @@ -501,11 +487,16 @@ minstrel_ht_prob_rate_reduce_streams(struct minstrel_ht_sta *mi) mg = &mi->groups[group]; if (!mg->supported || group == MINSTREL_CCK_GROUP) continue; - mr = minstrel_get_ratestats(mi, mg->max_group_prob_rate); - if (tmp_tp < mr->cur_tp && + + tmp_idx = mg->max_group_prob_rate % MCS_GROUP_RATES; + tmp_prob = mi->groups[group].rates[tmp_idx].prob_ewma; + + if (tmp_tp < minstrel_ht_get_tp_avg(mi, group, tmp_idx, tmp_prob) && (minstrel_mcs_groups[group].streams < tmp_max_streams)) { mi->max_prob_rate = mg->max_group_prob_rate; - tmp_tp = mr->cur_tp; + tmp_tp = minstrel_ht_get_tp_avg(mi, group, + tmp_idx, + tmp_prob); } } } @@ -523,8 +514,8 @@ static void minstrel_ht_update_stats(struct minstrel_priv *mp, struct minstrel_ht_sta *mi) { struct minstrel_mcs_group_data *mg; - struct minstrel_rate_stats *mr; - int group, i, j; + struct minstrel_rate_stats *mrs; + int group, i, j, cur_prob; u16 tmp_mcs_tp_rate[MAX_THR_RATES], tmp_group_tp_rate[MAX_THR_RATES]; u16 tmp_cck_tp_rate[MAX_THR_RATES], index; @@ -563,12 +554,12 @@ minstrel_ht_update_stats(struct minstrel_priv *mp, struct minstrel_ht_sta *mi) index = MCS_GROUP_RATES * group + i; - mr = &mg->rates[i]; - mr->retry_updated = false; - minstrel_calc_rate_ewma(mr); - minstrel_ht_calc_tp(mi, group, i); + mrs = &mg->rates[i]; + mrs->retry_updated = false; + minstrel_calc_rate_stats(mrs); + cur_prob = mrs->prob_ewma; - if (!mr->cur_tp) + if (minstrel_ht_get_tp_avg(mi, group, i, cur_prob) == 0) continue; /* Find max throughput rate set */ @@ -612,7 +603,7 @@ minstrel_ht_update_stats(struct minstrel_priv *mp, struct minstrel_ht_sta *mi) #endif /* Reset update timer */ - mi->stats_update = jiffies; + mi->last_stats_update = jiffies; } static bool @@ -635,7 +626,7 @@ minstrel_ht_txstat_valid(struct minstrel_priv *mp, struct ieee80211_tx_rate *rat } static void -minstrel_next_sample_idx(struct minstrel_ht_sta *mi) +minstrel_set_next_sample_idx(struct minstrel_ht_sta *mi) { struct minstrel_mcs_group_data *mg; @@ -776,7 +767,8 @@ minstrel_ht_tx_status(void *priv, struct ieee80211_supported_band *sband, update = true; } - if (time_after(jiffies, mi->stats_update + (mp->update_interval / 2 * HZ) / 1000)) { + if (time_after(jiffies, mi->last_stats_update + + (mp->update_interval / 2 * HZ) / 1000)) { update = true; minstrel_ht_update_stats(mp, mi); } @@ -789,7 +781,7 @@ static void minstrel_calc_retransmit(struct minstrel_priv *mp, struct minstrel_ht_sta *mi, int index) { - struct minstrel_rate_stats *mr; + struct minstrel_rate_stats *mrs; const struct mcs_group *group; unsigned int tx_time, tx_time_rtscts, tx_time_data; unsigned int cw = mp->cw_min; @@ -798,16 +790,16 @@ minstrel_calc_retransmit(struct minstrel_priv *mp, struct minstrel_ht_sta *mi, unsigned int ampdu_len = MINSTREL_TRUNC(mi->avg_ampdu_len); unsigned int overhead = 0, overhead_rtscts = 0; - mr = minstrel_get_ratestats(mi, index); - if (mr->probability < MINSTREL_FRAC(1, 10)) { - mr->retry_count = 1; - mr->retry_count_rtscts = 1; + mrs = minstrel_get_ratestats(mi, index); + if (mrs->prob_ewma < MINSTREL_FRAC(1, 10)) { + mrs->retry_count = 1; + mrs->retry_count_rtscts = 1; return; } - mr->retry_count = 2; - mr->retry_count_rtscts = 2; - mr->retry_updated = true; + mrs->retry_count = 2; + mrs->retry_count_rtscts = 2; + mrs->retry_updated = true; group = &minstrel_mcs_groups[index / MCS_GROUP_RATES]; tx_time_data = group->duration[index % MCS_GROUP_RATES] * ampdu_len / 1000; @@ -838,9 +830,9 @@ minstrel_calc_retransmit(struct minstrel_priv *mp, struct minstrel_ht_sta *mi, tx_time_rtscts += ctime + overhead_rtscts + tx_time_data; if (tx_time_rtscts < mp->segment_size) - mr->retry_count_rtscts++; + mrs->retry_count_rtscts++; } while ((tx_time < mp->segment_size) && - (++mr->retry_count < mp->max_retry)); + (++mrs->retry_count < mp->max_retry)); } @@ -849,22 +841,22 @@ minstrel_ht_set_rate(struct minstrel_priv *mp, struct minstrel_ht_sta *mi, struct ieee80211_sta_rates *ratetbl, int offset, int index) { const struct mcs_group *group = &minstrel_mcs_groups[index / MCS_GROUP_RATES]; - struct minstrel_rate_stats *mr; + struct minstrel_rate_stats *mrs; u8 idx; u16 flags = group->flags; - mr = minstrel_get_ratestats(mi, index); - if (!mr->retry_updated) + mrs = minstrel_get_ratestats(mi, index); + if (!mrs->retry_updated) minstrel_calc_retransmit(mp, mi, index); - if (mr->probability < MINSTREL_FRAC(20, 100) || !mr->retry_count) { + if (mrs->prob_ewma < MINSTREL_FRAC(20, 100) || !mrs->retry_count) { ratetbl->rate[offset].count = 2; ratetbl->rate[offset].count_rts = 2; ratetbl->rate[offset].count_cts = 2; } else { - ratetbl->rate[offset].count = mr->retry_count; - ratetbl->rate[offset].count_cts = mr->retry_count; - ratetbl->rate[offset].count_rts = mr->retry_count_rtscts; + ratetbl->rate[offset].count = mrs->retry_count; + ratetbl->rate[offset].count_cts = mrs->retry_count; + ratetbl->rate[offset].count_rts = mrs->retry_count_rtscts; } if (index / MCS_GROUP_RATES == MINSTREL_CCK_GROUP) @@ -922,7 +914,7 @@ minstrel_get_duration(int index) static int minstrel_get_sample_rate(struct minstrel_priv *mp, struct minstrel_ht_sta *mi) { - struct minstrel_rate_stats *mr; + struct minstrel_rate_stats *mrs; struct minstrel_mcs_group_data *mg; unsigned int sample_dur, sample_group, cur_max_tp_streams; int sample_idx = 0; @@ -938,12 +930,12 @@ minstrel_get_sample_rate(struct minstrel_priv *mp, struct minstrel_ht_sta *mi) sample_group = mi->sample_group; mg = &mi->groups[sample_group]; sample_idx = sample_table[mg->column][mg->index]; - minstrel_next_sample_idx(mi); + minstrel_set_next_sample_idx(mi); if (!(mg->supported & BIT(sample_idx))) return -1; - mr = &mg->rates[sample_idx]; + mrs = &mg->rates[sample_idx]; sample_idx += sample_group * MCS_GROUP_RATES; /* @@ -960,7 +952,7 @@ minstrel_get_sample_rate(struct minstrel_priv *mp, struct minstrel_ht_sta *mi) * Do not sample if the probability is already higher than 95% * to avoid wasting airtime. */ - if (mr->probability > MINSTREL_FRAC(95, 100)) + if (mrs->prob_ewma > MINSTREL_FRAC(95, 100)) return -1; /* @@ -975,7 +967,7 @@ minstrel_get_sample_rate(struct minstrel_priv *mp, struct minstrel_ht_sta *mi) (cur_max_tp_streams - 1 < minstrel_mcs_groups[sample_group].streams || sample_dur >= minstrel_get_duration(mi->max_prob_rate))) { - if (mr->sample_skipped < 20) + if (mrs->sample_skipped < 20) return -1; if (mi->sample_slow++ > 2) @@ -1129,7 +1121,7 @@ minstrel_ht_update_caps(void *priv, struct ieee80211_supported_band *sband, memset(mi, 0, sizeof(*mi)); mi->sta = sta; - mi->stats_update = jiffies; + mi->last_stats_update = jiffies; ack_dur = ieee80211_frame_duration(sband->band, 10, 60, 1, 1, 0); mi->overhead = ieee80211_frame_duration(sband->band, 0, 60, 1, 1, 0); @@ -1326,16 +1318,19 @@ static u32 minstrel_ht_get_expected_throughput(void *priv_sta) { struct minstrel_ht_sta_priv *msp = priv_sta; struct minstrel_ht_sta *mi = &msp->ht; - int i, j; + int i, j, prob, tp_avg; if (!msp->is_ht) return mac80211_minstrel.get_expected_throughput(priv_sta); i = mi->max_tp_rate[0] / MCS_GROUP_RATES; j = mi->max_tp_rate[0] % MCS_GROUP_RATES; + prob = mi->groups[i].rates[j].prob_ewma; + + /* convert tp_avg from pkt per second in kbps */ + tp_avg = minstrel_ht_get_tp_avg(mi, i, j, prob) * AVG_PKT_SIZE * 8 / 1024; - /* convert cur_tp from pkt per second in kbps */ - return mi->groups[i].rates[j].cur_tp * AVG_PKT_SIZE * 8 / 1024; + return tp_avg; } static const struct rate_control_ops mac80211_minstrel_ht = { diff --git a/net/mac80211/rc80211_minstrel_ht.h b/net/mac80211/rc80211_minstrel_ht.h index f2217d6aa0c2..e8b52a94d24b 100644 --- a/net/mac80211/rc80211_minstrel_ht.h +++ b/net/mac80211/rc80211_minstrel_ht.h @@ -78,7 +78,7 @@ struct minstrel_ht_sta { u16 max_prob_rate; /* time of last status update */ - unsigned long stats_update; + unsigned long last_stats_update; /* overhead time in usec for each frame */ unsigned int overhead; @@ -112,6 +112,7 @@ struct minstrel_ht_sta_priv { }; #ifdef CONFIG_MAC80211_DEBUGFS struct dentry *dbg_stats; + struct dentry *dbg_stats_csv; #endif void *ratelist; void *sample_table; @@ -120,5 +121,7 @@ struct minstrel_ht_sta_priv { void minstrel_ht_add_sta_debugfs(void *priv, void *priv_sta, struct dentry *dir); void minstrel_ht_remove_sta_debugfs(void *priv, void *priv_sta); +int minstrel_ht_get_tp_avg(struct minstrel_ht_sta *mi, int group, int rate, + int prob_ewma); #endif diff --git a/net/mac80211/rc80211_minstrel_ht_debugfs.c b/net/mac80211/rc80211_minstrel_ht_debugfs.c index 20c676b8e5b6..6822ce0f95e5 100644 --- a/net/mac80211/rc80211_minstrel_ht_debugfs.c +++ b/net/mac80211/rc80211_minstrel_ht_debugfs.c @@ -19,7 +19,7 @@ static char * minstrel_ht_stats_dump(struct minstrel_ht_sta *mi, int i, char *p) { const struct mcs_group *mg; - unsigned int j, tp, prob, eprob; + unsigned int j, tp_max, tp_avg, prob, eprob, tx_time; char htmode = '2'; char gimode = 'L'; u32 gflags; @@ -38,19 +38,26 @@ minstrel_ht_stats_dump(struct minstrel_ht_sta *mi, int i, char *p) gimode = 'S'; for (j = 0; j < MCS_GROUP_RATES; j++) { - struct minstrel_rate_stats *mr = &mi->groups[i].rates[j]; + struct minstrel_rate_stats *mrs = &mi->groups[i].rates[j]; static const int bitrates[4] = { 10, 20, 55, 110 }; int idx = i * MCS_GROUP_RATES + j; if (!(mi->groups[i].supported & BIT(j))) continue; - if (gflags & IEEE80211_TX_RC_MCS) - p += sprintf(p, " HT%c0/%cGI ", htmode, gimode); - else if (gflags & IEEE80211_TX_RC_VHT_MCS) - p += sprintf(p, "VHT%c0/%cGI ", htmode, gimode); - else - p += sprintf(p, " CCK/%cP ", j < 4 ? 'L' : 'S'); + if (gflags & IEEE80211_TX_RC_MCS) { + p += sprintf(p, "HT%c0 ", htmode); + p += sprintf(p, "%cGI ", gimode); + p += sprintf(p, "%d ", mg->streams); + } else if (gflags & IEEE80211_TX_RC_VHT_MCS) { + p += sprintf(p, "VHT%c0 ", htmode); + p += sprintf(p, "%cGI ", gimode); + p += sprintf(p, "%d ", mg->streams); + } else { + p += sprintf(p, "CCK "); + p += sprintf(p, "%cP ", j < 4 ? 'L' : 'S'); + p += sprintf(p, "1 "); + } *(p++) = (idx == mi->max_tp_rate[0]) ? 'A' : ' '; *(p++) = (idx == mi->max_tp_rate[1]) ? 'B' : ' '; @@ -59,29 +66,39 @@ minstrel_ht_stats_dump(struct minstrel_ht_sta *mi, int i, char *p) *(p++) = (idx == mi->max_prob_rate) ? 'P' : ' '; if (gflags & IEEE80211_TX_RC_MCS) { - p += sprintf(p, " MCS%-2u ", (mg->streams - 1) * 8 + j); + p += sprintf(p, " MCS%-2u", (mg->streams - 1) * 8 + j); } else if (gflags & IEEE80211_TX_RC_VHT_MCS) { - p += sprintf(p, " MCS%-1u/%1u", j, mg->streams); + p += sprintf(p, " MCS%-1u/%1u", j, mg->streams); } else { int r = bitrates[j % 4]; - p += sprintf(p, " %2u.%1uM ", r / 10, r % 10); + p += sprintf(p, " %2u.%1uM", r / 10, r % 10); } - tp = mr->cur_tp / 10; - prob = MINSTREL_TRUNC(mr->cur_prob * 1000); - eprob = MINSTREL_TRUNC(mr->probability * 1000); + p += sprintf(p, " %3u ", idx); - p += sprintf(p, " %4u.%1u %3u.%1u %3u.%1u " - "%3u %4u(%4u) %9llu(%9llu)\n", - tp / 10, tp % 10, + /* tx_time[rate(i)] in usec */ + tx_time = DIV_ROUND_CLOSEST(mg->duration[j], 1000); + p += sprintf(p, "%6u ", tx_time); + + tp_max = minstrel_ht_get_tp_avg(mi, i, j, MINSTREL_FRAC(100, 100)); + tp_avg = minstrel_ht_get_tp_avg(mi, i, j, mrs->prob_ewma); + prob = MINSTREL_TRUNC(mrs->cur_prob * 1000); + eprob = MINSTREL_TRUNC(mrs->prob_ewma * 1000); + + p += sprintf(p, "%4u.%1u %4u.%1u %3u.%1u %3u.%1u" + " %3u.%1u %3u %3u %-3u " + "%9llu %-9llu\n", + tp_max / 10, tp_max % 10, + tp_avg / 10, tp_avg % 10, eprob / 10, eprob % 10, + mrs->prob_ewmsd / 10, mrs->prob_ewmsd % 10, prob / 10, prob % 10, - mr->retry_count, - mr->last_success, - mr->last_attempts, - (unsigned long long)mr->succ_hist, - (unsigned long long)mr->att_hist); + mrs->retry_count, + mrs->last_success, + mrs->last_attempts, + (unsigned long long)mrs->succ_hist, + (unsigned long long)mrs->att_hist); } return p; @@ -94,8 +111,8 @@ minstrel_ht_stats_open(struct inode *inode, struct file *file) struct minstrel_ht_sta *mi = &msp->ht; struct minstrel_debugfs_info *ms; unsigned int i; - char *p; int ret; + char *p; if (!msp->is_ht) { inode->i_private = &msp->legacy; @@ -110,8 +127,14 @@ minstrel_ht_stats_open(struct inode *inode, struct file *file) file->private_data = ms; p = ms->buf; - p += sprintf(p, " type rate tpt eprob *prob " - "ret *ok(*cum) ok( cum)\n"); + + p += sprintf(p, "\n"); + p += sprintf(p, " best ____________rate__________ " + "______statistics______ ________last_______ " + "______sum-of________\n"); + p += sprintf(p, "mode guard # rate [name idx airtime max_tp] " + "[ ø(tp) ø(prob) sd(prob)] [prob.|retry|suc|att] [#success | " + "#attempts]\n"); p = minstrel_ht_stats_dump(mi, MINSTREL_CCK_GROUP, p); for (i = 0; i < MINSTREL_CCK_GROUP; i++) @@ -123,11 +146,10 @@ minstrel_ht_stats_open(struct inode *inode, struct file *file) "lookaround %d\n", max(0, (int) mi->total_packets - (int) mi->sample_packets), mi->sample_packets); - p += sprintf(p, "Average A-MPDU length: %d.%d\n", + p += sprintf(p, "Average # of aggregated frames per A-MPDU: %d.%d\n", MINSTREL_TRUNC(mi->avg_ampdu_len), MINSTREL_TRUNC(mi->avg_ampdu_len * 10) % 10); ms->len = p - ms->buf; - WARN_ON(ms->len + sizeof(*ms) > 32768); return nonseekable_open(inode, file); @@ -141,6 +163,143 @@ static const struct file_operations minstrel_ht_stat_fops = { .llseek = no_llseek, }; +static char * +minstrel_ht_stats_csv_dump(struct minstrel_ht_sta *mi, int i, char *p) +{ + const struct mcs_group *mg; + unsigned int j, tp_max, tp_avg, prob, eprob, tx_time; + char htmode = '2'; + char gimode = 'L'; + u32 gflags; + + if (!mi->groups[i].supported) + return p; + + mg = &minstrel_mcs_groups[i]; + gflags = mg->flags; + + if (gflags & IEEE80211_TX_RC_40_MHZ_WIDTH) + htmode = '4'; + else if (gflags & IEEE80211_TX_RC_80_MHZ_WIDTH) + htmode = '8'; + if (gflags & IEEE80211_TX_RC_SHORT_GI) + gimode = 'S'; + + for (j = 0; j < MCS_GROUP_RATES; j++) { + struct minstrel_rate_stats *mrs = &mi->groups[i].rates[j]; + static const int bitrates[4] = { 10, 20, 55, 110 }; + int idx = i * MCS_GROUP_RATES + j; + + if (!(mi->groups[i].supported & BIT(j))) + continue; + + if (gflags & IEEE80211_TX_RC_MCS) { + p += sprintf(p, "HT%c0,", htmode); + p += sprintf(p, "%cGI,", gimode); + p += sprintf(p, "%d,", mg->streams); + } else if (gflags & IEEE80211_TX_RC_VHT_MCS) { + p += sprintf(p, "VHT%c0,", htmode); + p += sprintf(p, "%cGI,", gimode); + p += sprintf(p, "%d,", mg->streams); + } else { + p += sprintf(p, "CCK,"); + p += sprintf(p, "%cP,", j < 4 ? 'L' : 'S'); + p += sprintf(p, "1,"); + } + + p += sprintf(p, "%s" ,((idx == mi->max_tp_rate[0]) ? "A" : "")); + p += sprintf(p, "%s" ,((idx == mi->max_tp_rate[1]) ? "B" : "")); + p += sprintf(p, "%s" ,((idx == mi->max_tp_rate[2]) ? "C" : "")); + p += sprintf(p, "%s" ,((idx == mi->max_tp_rate[3]) ? "D" : "")); + p += sprintf(p, "%s" ,((idx == mi->max_prob_rate) ? "P" : "")); + + if (gflags & IEEE80211_TX_RC_MCS) { + p += sprintf(p, ",MCS%-2u,", (mg->streams - 1) * 8 + j); + } else if (gflags & IEEE80211_TX_RC_VHT_MCS) { + p += sprintf(p, ",MCS%-1u/%1u,", j, mg->streams); + } else { + int r = bitrates[j % 4]; + p += sprintf(p, ",%2u.%1uM,", r / 10, r % 10); + } + + p += sprintf(p, "%u,", idx); + tx_time = DIV_ROUND_CLOSEST(mg->duration[j], 1000); + p += sprintf(p, "%u,", tx_time); + + tp_max = minstrel_ht_get_tp_avg(mi, i, j, MINSTREL_FRAC(100, 100)); + tp_avg = minstrel_ht_get_tp_avg(mi, i, j, mrs->prob_ewma); + prob = MINSTREL_TRUNC(mrs->cur_prob * 1000); + eprob = MINSTREL_TRUNC(mrs->prob_ewma * 1000); + + p += sprintf(p, "%u.%u,%u.%u,%u.%u,%u.%u,%u.%u,%u,%u," + "%u,%llu,%llu,", + tp_max / 10, tp_max % 10, + tp_avg / 10, tp_avg % 10, + eprob / 10, eprob % 10, + mrs->prob_ewmsd / 10, mrs->prob_ewmsd % 10, + prob / 10, prob % 10, + mrs->retry_count, + mrs->last_success, + mrs->last_attempts, + (unsigned long long)mrs->succ_hist, + (unsigned long long)mrs->att_hist); + p += sprintf(p, "%d,%d,%d.%d\n", + max(0, (int) mi->total_packets - + (int) mi->sample_packets), + mi->sample_packets, + MINSTREL_TRUNC(mi->avg_ampdu_len), + MINSTREL_TRUNC(mi->avg_ampdu_len * 10) % 10); + } + + return p; +} + +static int +minstrel_ht_stats_csv_open(struct inode *inode, struct file *file) +{ + struct minstrel_ht_sta_priv *msp = inode->i_private; + struct minstrel_ht_sta *mi = &msp->ht; + struct minstrel_debugfs_info *ms; + unsigned int i; + int ret; + char *p; + + if (!msp->is_ht) { + inode->i_private = &msp->legacy; + ret = minstrel_stats_csv_open(inode, file); + inode->i_private = msp; + return ret; + } + + ms = kmalloc(32768, GFP_KERNEL); + + if (!ms) + return -ENOMEM; + + file->private_data = ms; + + p = ms->buf; + + p = minstrel_ht_stats_csv_dump(mi, MINSTREL_CCK_GROUP, p); + for (i = 0; i < MINSTREL_CCK_GROUP; i++) + p = minstrel_ht_stats_csv_dump(mi, i, p); + for (i++; i < ARRAY_SIZE(mi->groups); i++) + p = minstrel_ht_stats_csv_dump(mi, i, p); + + ms->len = p - ms->buf; + WARN_ON(ms->len + sizeof(*ms) > 32768); + + return nonseekable_open(inode, file); +} + +static const struct file_operations minstrel_ht_stat_csv_fops = { + .owner = THIS_MODULE, + .open = minstrel_ht_stats_csv_open, + .read = minstrel_stats_read, + .release = minstrel_stats_release, + .llseek = no_llseek, +}; + void minstrel_ht_add_sta_debugfs(void *priv, void *priv_sta, struct dentry *dir) { @@ -148,6 +307,8 @@ minstrel_ht_add_sta_debugfs(void *priv, void *priv_sta, struct dentry *dir) msp->dbg_stats = debugfs_create_file("rc_stats", S_IRUGO, dir, msp, &minstrel_ht_stat_fops); + msp->dbg_stats_csv = debugfs_create_file("rc_stats_csv", S_IRUGO, + dir, msp, &minstrel_ht_stat_csv_fops); } void @@ -156,4 +317,5 @@ minstrel_ht_remove_sta_debugfs(void *priv, void *priv_sta) struct minstrel_ht_sta_priv *msp = priv_sta; debugfs_remove(msp->dbg_stats); + debugfs_remove(msp->dbg_stats_csv); } diff --git a/net/mac80211/rx.c b/net/mac80211/rx.c index 1eb730bf8752..260eed45b6d2 100644 --- a/net/mac80211/rx.c +++ b/net/mac80211/rx.c @@ -1185,6 +1185,7 @@ static void sta_ps_start(struct sta_info *sta) struct ieee80211_sub_if_data *sdata = sta->sdata; struct ieee80211_local *local = sdata->local; struct ps_data *ps; + int tid; if (sta->sdata->vif.type == NL80211_IFTYPE_AP || sta->sdata->vif.type == NL80211_IFTYPE_AP_VLAN) @@ -1198,6 +1199,18 @@ static void sta_ps_start(struct sta_info *sta) drv_sta_notify(local, sdata, STA_NOTIFY_SLEEP, &sta->sta); ps_dbg(sdata, "STA %pM aid %d enters power save mode\n", sta->sta.addr, sta->sta.aid); + + if (!sta->sta.txq[0]) + return; + + for (tid = 0; tid < ARRAY_SIZE(sta->sta.txq); tid++) { + struct txq_info *txqi = to_txq_info(sta->sta.txq[tid]); + + if (!skb_queue_len(&txqi->queue)) + set_bit(tid, &sta->txq_buffered_tids); + else + clear_bit(tid, &sta->txq_buffered_tids); + } } static void sta_ps_end(struct sta_info *sta) @@ -1913,8 +1926,7 @@ static int ieee80211_drop_unencrypted(struct ieee80211_rx_data *rx, __le16 fc) /* Drop unencrypted frames if key is set. */ if (unlikely(!ieee80211_has_protected(fc) && !ieee80211_is_nullfunc(fc) && - ieee80211_is_data(fc) && - (rx->key || rx->sdata->drop_unencrypted))) + ieee80211_is_data(fc) && rx->key)) return -EACCES; return 0; @@ -2044,6 +2056,9 @@ ieee80211_deliver_skb(struct ieee80211_rx_data *rx) struct sta_info *dsta; struct ieee80211_rx_status *status = IEEE80211_SKB_RXCB(rx->skb); + dev->stats.rx_packets++; + dev->stats.rx_bytes += rx->skb->len; + skb = rx->skb; xmit_skb = NULL; @@ -2174,8 +2189,6 @@ ieee80211_rx_h_amsdu(struct ieee80211_rx_data *rx) dev_kfree_skb(rx->skb); continue; } - dev->stats.rx_packets++; - dev->stats.rx_bytes += rx->skb->len; ieee80211_deliver_skb(rx); } @@ -2401,9 +2414,6 @@ ieee80211_rx_h_data(struct ieee80211_rx_data *rx) rx->skb->dev = dev; - dev->stats.rx_packets++; - dev->stats.rx_bytes += rx->skb->len; - if (local->ps_sdata && local->hw.conf.dynamic_ps_timeout > 0 && !is_multicast_ether_addr( ((struct ethhdr *)rx->skb->data)->h_dest) && @@ -3129,6 +3139,12 @@ static void ieee80211_rx_handlers(struct ieee80211_rx_data *rx, goto rxh_next; \ } while (0); + /* Lock here to avoid hitting all of the data used in the RX + * path (e.g. key data, station data, ...) concurrently when + * a frame is released from the reorder buffer due to timeout + * from the timer, potentially concurrently with RX from the + * driver. + */ spin_lock_bh(&rx->local->rx_path_lock); while ((skb = __skb_dequeue(frames))) { @@ -3421,7 +3437,8 @@ static void __ieee80211_rx_handle_packet(struct ieee80211_hw *hw, __le16 fc; struct ieee80211_rx_data rx; struct ieee80211_sub_if_data *prev; - struct sta_info *sta, *tmp, *prev_sta; + struct sta_info *sta, *prev_sta; + struct rhash_head *tmp; int err = 0; fc = ((struct ieee80211_hdr *)skb->data)->frame_control; @@ -3456,9 +3473,13 @@ static void __ieee80211_rx_handle_packet(struct ieee80211_hw *hw, ieee80211_scan_rx(local, skb); if (ieee80211_is_data(fc)) { + const struct bucket_table *tbl; + prev_sta = NULL; - for_each_sta_info(local, hdr->addr2, sta, tmp) { + tbl = rht_dereference_rcu(local->sta_hash.tbl, &local->sta_hash); + + for_each_sta_info(local, tbl, hdr->addr2, sta, tmp) { if (!prev_sta) { prev_sta = sta; continue; diff --git a/net/mac80211/scan.c b/net/mac80211/scan.c index 05f0d711b6d8..7bb6a9383f58 100644 --- a/net/mac80211/scan.c +++ b/net/mac80211/scan.c @@ -928,11 +928,12 @@ int ieee80211_request_scan(struct ieee80211_sub_if_data *sdata, int ieee80211_request_ibss_scan(struct ieee80211_sub_if_data *sdata, const u8 *ssid, u8 ssid_len, - struct ieee80211_channel *chan, + struct ieee80211_channel **channels, + unsigned int n_channels, enum nl80211_bss_scan_width scan_width) { struct ieee80211_local *local = sdata->local; - int ret = -EBUSY; + int ret = -EBUSY, i, n_ch = 0; enum ieee80211_band band; mutex_lock(&local->mtx); @@ -942,9 +943,8 @@ int ieee80211_request_ibss_scan(struct ieee80211_sub_if_data *sdata, goto unlock; /* fill internal scan request */ - if (!chan) { - int i, max_n; - int n_ch = 0; + if (!channels) { + int max_n; for (band = 0; band < IEEE80211_NUM_BANDS; band++) { if (!local->hw.wiphy->bands[band]) @@ -969,12 +969,19 @@ int ieee80211_request_ibss_scan(struct ieee80211_sub_if_data *sdata, local->int_scan_req->n_channels = n_ch; } else { - if (WARN_ON_ONCE(chan->flags & (IEEE80211_CHAN_NO_IR | - IEEE80211_CHAN_DISABLED))) + for (i = 0; i < n_channels; i++) { + if (channels[i]->flags & (IEEE80211_CHAN_NO_IR | + IEEE80211_CHAN_DISABLED)) + continue; + + local->int_scan_req->channels[n_ch] = channels[i]; + n_ch++; + } + + if (WARN_ON_ONCE(n_ch == 0)) goto unlock; - local->int_scan_req->channels[0] = chan; - local->int_scan_req->n_channels = 1; + local->int_scan_req->n_channels = n_ch; } local->int_scan_req->ssids = &local->scan_ssid; diff --git a/net/mac80211/sta_info.c b/net/mac80211/sta_info.c index 00ca8dcc2bcf..12971b71d0fa 100644 --- a/net/mac80211/sta_info.c +++ b/net/mac80211/sta_info.c @@ -64,32 +64,20 @@ * freed before they are done using it. */ +static const struct rhashtable_params sta_rht_params = { + .nelem_hint = 3, /* start small */ + .head_offset = offsetof(struct sta_info, hash_node), + .key_offset = offsetof(struct sta_info, sta.addr), + .key_len = ETH_ALEN, + .hashfn = sta_addr_hash, +}; + /* Caller must hold local->sta_mtx */ static int sta_info_hash_del(struct ieee80211_local *local, struct sta_info *sta) { - struct sta_info *s; - - s = rcu_dereference_protected(local->sta_hash[STA_HASH(sta->sta.addr)], - lockdep_is_held(&local->sta_mtx)); - if (!s) - return -ENOENT; - if (s == sta) { - rcu_assign_pointer(local->sta_hash[STA_HASH(sta->sta.addr)], - s->hnext); - return 0; - } - - while (rcu_access_pointer(s->hnext) && - rcu_access_pointer(s->hnext) != sta) - s = rcu_dereference_protected(s->hnext, - lockdep_is_held(&local->sta_mtx)); - if (rcu_access_pointer(s->hnext)) { - rcu_assign_pointer(s->hnext, sta->hnext); - return 0; - } - - return -ENOENT; + return rhashtable_remove_fast(&local->sta_hash, &sta->hash_node, + sta_rht_params); } static void __cleanup_single_sta(struct sta_info *sta) @@ -118,6 +106,16 @@ static void __cleanup_single_sta(struct sta_info *sta) atomic_dec(&ps->num_sta_ps); } + if (sta->sta.txq[0]) { + for (i = 0; i < ARRAY_SIZE(sta->sta.txq); i++) { + struct txq_info *txqi = to_txq_info(sta->sta.txq[i]); + int n = skb_queue_len(&txqi->queue); + + ieee80211_purge_tx_queue(&local->hw, &txqi->queue); + atomic_sub(n, &sdata->txqs_len[txqi->txq.ac]); + } + } + for (ac = 0; ac < IEEE80211_NUM_ACS; ac++) { local->total_ps_buffered -= skb_queue_len(&sta->ps_tx_buf[ac]); ieee80211_purge_tx_queue(&local->hw, &sta->ps_tx_buf[ac]); @@ -159,18 +157,8 @@ struct sta_info *sta_info_get(struct ieee80211_sub_if_data *sdata, const u8 *addr) { struct ieee80211_local *local = sdata->local; - struct sta_info *sta; - sta = rcu_dereference_check(local->sta_hash[STA_HASH(addr)], - lockdep_is_held(&local->sta_mtx)); - while (sta) { - if (sta->sdata == sdata && - ether_addr_equal(sta->sta.addr, addr)) - break; - sta = rcu_dereference_check(sta->hnext, - lockdep_is_held(&local->sta_mtx)); - } - return sta; + return rhashtable_lookup_fast(&local->sta_hash, addr, sta_rht_params); } /* @@ -182,18 +170,24 @@ struct sta_info *sta_info_get_bss(struct ieee80211_sub_if_data *sdata, { struct ieee80211_local *local = sdata->local; struct sta_info *sta; + struct rhash_head *tmp; + const struct bucket_table *tbl; - sta = rcu_dereference_check(local->sta_hash[STA_HASH(addr)], - lockdep_is_held(&local->sta_mtx)); - while (sta) { - if ((sta->sdata == sdata || - (sta->sdata->bss && sta->sdata->bss == sdata->bss)) && - ether_addr_equal(sta->sta.addr, addr)) - break; - sta = rcu_dereference_check(sta->hnext, - lockdep_is_held(&local->sta_mtx)); + rcu_read_lock(); + tbl = rht_dereference_rcu(local->sta_hash.tbl, &local->sta_hash); + + for_each_sta_info(local, tbl, addr, sta, tmp) { + if (sta->sdata == sdata || + (sta->sdata->bss && sta->sdata->bss == sdata->bss)) { + rcu_read_unlock(); + /* this is safe as the caller must already hold + * another rcu read section or the mutex + */ + return sta; + } } - return sta; + rcu_read_unlock(); + return NULL; } struct sta_info *sta_info_get_by_idx(struct ieee80211_sub_if_data *sdata, @@ -229,19 +223,13 @@ struct sta_info *sta_info_get_by_idx(struct ieee80211_sub_if_data *sdata, */ void sta_info_free(struct ieee80211_local *local, struct sta_info *sta) { - int i; - if (sta->rate_ctrl) rate_control_free_sta(sta); - if (sta->tx_lat) { - for (i = 0; i < IEEE80211_NUM_TIDS; i++) - kfree(sta->tx_lat[i].bins); - kfree(sta->tx_lat); - } - sta_dbg(sta->sdata, "Destroyed STA %pM\n", sta->sta.addr); + if (sta->sta.txq[0]) + kfree(to_txq_info(sta->sta.txq[0])); kfree(rcu_dereference_raw(sta->sta.rates)); kfree(sta); } @@ -250,9 +238,8 @@ void sta_info_free(struct ieee80211_local *local, struct sta_info *sta) static void sta_info_hash_add(struct ieee80211_local *local, struct sta_info *sta) { - lockdep_assert_held(&local->sta_mtx); - sta->hnext = local->sta_hash[STA_HASH(sta->sta.addr)]; - rcu_assign_pointer(local->sta_hash[STA_HASH(sta->sta.addr)], sta); + rhashtable_insert_fast(&local->sta_hash, &sta->hash_node, + sta_rht_params); } static void sta_deliver_ps_frames(struct work_struct *wk) @@ -293,44 +280,15 @@ struct sta_info *sta_info_alloc(struct ieee80211_sub_if_data *sdata, const u8 *addr, gfp_t gfp) { struct ieee80211_local *local = sdata->local; + struct ieee80211_hw *hw = &local->hw; struct sta_info *sta; struct timespec uptime; - struct ieee80211_tx_latency_bin_ranges *tx_latency; int i; - sta = kzalloc(sizeof(*sta) + local->hw.sta_data_size, gfp); + sta = kzalloc(sizeof(*sta) + hw->sta_data_size, gfp); if (!sta) return NULL; - rcu_read_lock(); - tx_latency = rcu_dereference(local->tx_latency); - /* init stations Tx latency statistics && TID bins */ - if (tx_latency) { - sta->tx_lat = kzalloc(IEEE80211_NUM_TIDS * - sizeof(struct ieee80211_tx_latency_stat), - GFP_ATOMIC); - if (!sta->tx_lat) { - rcu_read_unlock(); - goto free; - } - - if (tx_latency->n_ranges) { - for (i = 0; i < IEEE80211_NUM_TIDS; i++) { - /* size of bins is size of the ranges +1 */ - sta->tx_lat[i].bin_count = - tx_latency->n_ranges + 1; - sta->tx_lat[i].bins = - kcalloc(sta->tx_lat[i].bin_count, - sizeof(u32), GFP_ATOMIC); - if (!sta->tx_lat[i].bins) { - rcu_read_unlock(); - goto free; - } - } - } - } - rcu_read_unlock(); - spin_lock_init(&sta->lock); spin_lock_init(&sta->ps_lock); INIT_WORK(&sta->drv_deliver_wk, sta_deliver_ps_frames); @@ -359,8 +317,24 @@ struct sta_info *sta_info_alloc(struct ieee80211_sub_if_data *sdata, for (i = 0; i < ARRAY_SIZE(sta->chain_signal_avg); i++) ewma_init(&sta->chain_signal_avg[i], 1024, 8); + if (local->ops->wake_tx_queue) { + void *txq_data; + int size = sizeof(struct txq_info) + + ALIGN(hw->txq_data_size, sizeof(void *)); + + txq_data = kcalloc(ARRAY_SIZE(sta->sta.txq), size, gfp); + if (!txq_data) + goto free; + + for (i = 0; i < ARRAY_SIZE(sta->sta.txq); i++) { + struct txq_info *txq = txq_data + i * size; + + ieee80211_init_tx_queue(sdata, sta, txq, i); + } + } + if (sta_prepare_rate_control(local, sta, gfp)) - goto free; + goto free_txq; for (i = 0; i < IEEE80211_NUM_TIDS; i++) { /* @@ -382,7 +356,7 @@ struct sta_info *sta_info_alloc(struct ieee80211_sub_if_data *sdata, if (sdata->vif.type == NL80211_IFTYPE_AP || sdata->vif.type == NL80211_IFTYPE_AP_VLAN) { struct ieee80211_supported_band *sband = - local->hw.wiphy->bands[ieee80211_get_sdata_band(sdata)]; + hw->wiphy->bands[ieee80211_get_sdata_band(sdata)]; u8 smps = (sband->ht_cap.cap & IEEE80211_HT_CAP_SM_PS) >> IEEE80211_HT_CAP_SM_PS_SHIFT; /* @@ -405,14 +379,13 @@ struct sta_info *sta_info_alloc(struct ieee80211_sub_if_data *sdata, } sta_dbg(sdata, "Allocated STA %pM\n", sta->sta.addr); + return sta; +free_txq: + if (sta->sta.txq[0]) + kfree(to_txq_info(sta->sta.txq[0])); free: - if (sta->tx_lat) { - for (i = 0; i < IEEE80211_NUM_TIDS; i++) - kfree(sta->tx_lat[i].bins); - kfree(sta->tx_lat); - } kfree(sta); return NULL; } @@ -684,6 +657,8 @@ static void __sta_info_recalc_tim(struct sta_info *sta, bool ignore_pending) indicate_tim |= sta->driver_buffered_tids & tids; + indicate_tim |= + sta->txq_buffered_tids & tids; } done: @@ -992,19 +967,32 @@ static void sta_info_cleanup(unsigned long data) round_jiffies(jiffies + STA_INFO_CLEANUP_INTERVAL)); } -void sta_info_init(struct ieee80211_local *local) +u32 sta_addr_hash(const void *key, u32 length, u32 seed) +{ + return jhash(key, ETH_ALEN, seed); +} + +int sta_info_init(struct ieee80211_local *local) { + int err; + + err = rhashtable_init(&local->sta_hash, &sta_rht_params); + if (err) + return err; + spin_lock_init(&local->tim_lock); mutex_init(&local->sta_mtx); INIT_LIST_HEAD(&local->sta_list); setup_timer(&local->sta_cleanup, sta_info_cleanup, (unsigned long)local); + return 0; } void sta_info_stop(struct ieee80211_local *local) { del_timer_sync(&local->sta_cleanup); + rhashtable_destroy(&local->sta_hash); } @@ -1068,16 +1056,21 @@ void ieee80211_sta_expire(struct ieee80211_sub_if_data *sdata, } struct ieee80211_sta *ieee80211_find_sta_by_ifaddr(struct ieee80211_hw *hw, - const u8 *addr, - const u8 *localaddr) + const u8 *addr, + const u8 *localaddr) { - struct sta_info *sta, *nxt; + struct ieee80211_local *local = hw_to_local(hw); + struct sta_info *sta; + struct rhash_head *tmp; + const struct bucket_table *tbl; + + tbl = rht_dereference_rcu(local->sta_hash.tbl, &local->sta_hash); /* * Just return a random station if localaddr is NULL * ... first in list. */ - for_each_sta_info(hw_to_local(hw), addr, sta, nxt) { + for_each_sta_info(local, tbl, addr, sta, tmp) { if (localaddr && !ether_addr_equal(sta->sdata->vif.addr, localaddr)) continue; @@ -1115,7 +1108,7 @@ void ieee80211_sta_ps_deliver_wakeup(struct sta_info *sta) struct ieee80211_sub_if_data *sdata = sta->sdata; struct ieee80211_local *local = sdata->local; struct sk_buff_head pending; - int filtered = 0, buffered = 0, ac; + int filtered = 0, buffered = 0, ac, i; unsigned long flags; struct ps_data *ps; @@ -1134,10 +1127,22 @@ void ieee80211_sta_ps_deliver_wakeup(struct sta_info *sta) BUILD_BUG_ON(BITS_TO_LONGS(IEEE80211_NUM_TIDS) > 1); sta->driver_buffered_tids = 0; + sta->txq_buffered_tids = 0; if (!(local->hw.flags & IEEE80211_HW_AP_LINK_PS)) drv_sta_notify(local, sdata, STA_NOTIFY_AWAKE, &sta->sta); + if (sta->sta.txq[0]) { + for (i = 0; i < ARRAY_SIZE(sta->sta.txq); i++) { + struct txq_info *txqi = to_txq_info(sta->sta.txq[i]); + + if (!skb_queue_len(&txqi->queue)) + continue; + + drv_wake_tx_queue(local, txqi); + } + } + skb_queue_head_init(&pending); /* sync with ieee80211_tx_h_unicast_ps_buf */ @@ -1275,7 +1280,7 @@ static void ieee80211_send_null_response(struct ieee80211_sub_if_data *sdata, } info->band = chanctx_conf->def.chan->band; - ieee80211_xmit(sdata, skb); + ieee80211_xmit(sdata, sta, skb); rcu_read_unlock(); } @@ -1319,8 +1324,10 @@ ieee80211_sta_ps_deliver_response(struct sta_info *sta, /* if we already have frames from software, then we can't also * release from hardware queues */ - if (skb_queue_empty(&frames)) + if (skb_queue_empty(&frames)) { driver_release_tids |= sta->driver_buffered_tids & tids; + driver_release_tids |= sta->txq_buffered_tids & tids; + } if (driver_release_tids) { /* If the driver has data on more than one TID then @@ -1491,6 +1498,9 @@ ieee80211_sta_ps_deliver_response(struct sta_info *sta, sta_info_recalc_tim(sta); } else { + unsigned long tids = sta->txq_buffered_tids & driver_release_tids; + int tid; + /* * We need to release a frame that is buffered somewhere in the * driver ... it'll have to handle that. @@ -1510,8 +1520,22 @@ ieee80211_sta_ps_deliver_response(struct sta_info *sta, * that the TID(s) became empty before returning here from the * release function. * Either way, however, when the driver tells us that the TID(s) - * became empty we'll do the TIM recalculation. + * became empty or we find that a txq became empty, we'll do the + * TIM recalculation. */ + + if (!sta->sta.txq[0]) + return; + + for (tid = 0; tid < ARRAY_SIZE(sta->sta.txq); tid++) { + struct txq_info *txqi = to_txq_info(sta->sta.txq[tid]); + + if (!(tids & BIT(tid)) || skb_queue_len(&txqi->queue)) + continue; + + sta_info_recalc_tim(sta); + break; + } } } diff --git a/net/mac80211/sta_info.h b/net/mac80211/sta_info.h index fb0fc1302a58..5c164fb3f6c5 100644 --- a/net/mac80211/sta_info.h +++ b/net/mac80211/sta_info.h @@ -16,6 +16,7 @@ #include <linux/workqueue.h> #include <linux/average.h> #include <linux/etherdevice.h> +#include <linux/rhashtable.h> #include "key.h" /** @@ -236,25 +237,6 @@ struct sta_ampdu_mlme { u8 dialog_token_allocator; }; -/* - * struct ieee80211_tx_latency_stat - Tx latency statistics - * - * Measures TX latency and jitter for a station per TID. - * - * @max: worst case latency - * @sum: sum of all latencies - * @counter: amount of Tx frames sent from interface - * @bins: each bin counts how many frames transmitted within a certain - * latency range. when disabled it is NULL. - * @bin_count: amount of bins. - */ -struct ieee80211_tx_latency_stat { - u32 max; - u32 sum; - u32 counter; - u32 *bins; - u32 bin_count; -}; /* Value to indicate no TID reservation */ #define IEEE80211_TID_UNRESERVED 0xff @@ -267,7 +249,7 @@ struct ieee80211_tx_latency_stat { * * @list: global linked list entry * @free_list: list entry for keeping track of stations to free - * @hnext: hash table linked list pointer + * @hash_node: hash node for rhashtable * @local: pointer to the global information * @sdata: virtual interface this station belongs to * @ptk: peer keys negotiated with this station, if any @@ -295,6 +277,7 @@ struct ieee80211_tx_latency_stat { * entered power saving state, these are also delivered to * the station when it leaves powersave or polls for frames * @driver_buffered_tids: bitmap of TIDs the driver has data buffered on + * @txq_buffered_tids: bitmap of TIDs that mac80211 has txq data buffered on * @rx_packets: Number of MSDUs received from this STA * @rx_bytes: Number of bytes received from this STA * @last_rx: time (in jiffies) when last frame was received from this STA @@ -316,7 +299,6 @@ struct ieee80211_tx_latency_stat { * @tid_seq: per-TID sequence numbers for sending to this STA * @ampdu_mlme: A-MPDU state machine state * @timer_to_tid: identity mapping to ID timers - * @tx_lat: Tx latency statistics * @llid: Local link ID * @plid: Peer link ID * @reason: Cancel reason on PLINK_HOLDING state @@ -361,7 +343,7 @@ struct sta_info { /* General information, mostly static */ struct list_head list, free_list; struct rcu_head rcu_head; - struct sta_info __rcu *hnext; + struct rhash_head hash_node; struct ieee80211_local *local; struct ieee80211_sub_if_data *sdata; struct ieee80211_key __rcu *gtk[NUM_DEFAULT_KEYS + NUM_DEFAULT_MGMT_KEYS]; @@ -390,6 +372,7 @@ struct sta_info { struct sk_buff_head ps_tx_buf[IEEE80211_NUM_ACS]; struct sk_buff_head tx_filtered[IEEE80211_NUM_ACS]; unsigned long driver_buffered_tids; + unsigned long txq_buffered_tids; /* Updated from RX path only, no locking requirements */ unsigned long rx_packets; @@ -437,8 +420,6 @@ struct sta_info { struct sta_ampdu_mlme ampdu_mlme; u8 timer_to_tid[IEEE80211_NUM_TIDS]; - struct ieee80211_tx_latency_stat *tx_lat; - #ifdef CONFIG_MAC80211_MESH /* * Mesh peer link attributes @@ -559,10 +540,6 @@ rcu_dereference_protected_tid_tx(struct sta_info *sta, int tid) lockdep_is_held(&sta->ampdu_mlme.mtx)); } -#define STA_HASH_SIZE 256 -#define STA_HASH(sta) (sta[5]) - - /* Maximum number of frames to buffer per power saving station per AC */ #define STA_MAX_TX_BUFFER 64 @@ -583,26 +560,15 @@ struct sta_info *sta_info_get(struct ieee80211_sub_if_data *sdata, struct sta_info *sta_info_get_bss(struct ieee80211_sub_if_data *sdata, const u8 *addr); -static inline -void for_each_sta_info_type_check(struct ieee80211_local *local, - const u8 *addr, - struct sta_info *sta, - struct sta_info *nxt) -{ -} +u32 sta_addr_hash(const void *key, u32 length, u32 seed); + +#define _sta_bucket_idx(_tbl, _a) \ + rht_bucket_index(_tbl, sta_addr_hash(_a, ETH_ALEN, (_tbl)->hash_rnd)) -#define for_each_sta_info(local, _addr, _sta, nxt) \ - for ( /* initialise loop */ \ - _sta = rcu_dereference(local->sta_hash[STA_HASH(_addr)]),\ - nxt = _sta ? rcu_dereference(_sta->hnext) : NULL; \ - /* typecheck */ \ - for_each_sta_info_type_check(local, (_addr), _sta, nxt),\ - /* continue condition */ \ - _sta; \ - /* advance loop */ \ - _sta = nxt, \ - nxt = _sta ? rcu_dereference(_sta->hnext) : NULL \ - ) \ +#define for_each_sta_info(local, tbl, _addr, _sta, _tmp) \ + rht_for_each_entry_rcu(_sta, _tmp, tbl, \ + _sta_bucket_idx(tbl, _addr), \ + hash_node) \ /* compare address and run code only if it matches */ \ if (ether_addr_equal(_sta->sta.addr, (_addr))) @@ -639,7 +605,7 @@ int sta_info_destroy_addr_bss(struct ieee80211_sub_if_data *sdata, void sta_info_recalc_tim(struct sta_info *sta); -void sta_info_init(struct ieee80211_local *local); +int sta_info_init(struct ieee80211_local *local); void sta_info_stop(struct ieee80211_local *local); /** diff --git a/net/mac80211/status.c b/net/mac80211/status.c index e679b7c9b160..005fdbe39a8b 100644 --- a/net/mac80211/status.c +++ b/net/mac80211/status.c @@ -12,7 +12,6 @@ #include <linux/export.h> #include <linux/etherdevice.h> -#include <linux/time.h> #include <net/mac80211.h> #include <asm/unaligned.h> #include "ieee80211_i.h" @@ -515,73 +514,6 @@ static void ieee80211_report_used_skb(struct ieee80211_local *local, } /* - * Measure Tx frame completion and removal time for Tx latency statistics - * calculation. A single Tx frame latency should be measured from when it - * is entering the Kernel until we receive Tx complete confirmation indication - * and remove the skb. - */ -static void ieee80211_tx_latency_end_msrmnt(struct ieee80211_local *local, - struct sk_buff *skb, - struct sta_info *sta, - struct ieee80211_hdr *hdr) -{ - u32 msrmnt; - u16 tid; - u8 *qc; - int i, bin_range_count; - u32 *bin_ranges; - __le16 fc; - struct ieee80211_tx_latency_stat *tx_lat; - struct ieee80211_tx_latency_bin_ranges *tx_latency; - ktime_t skb_arv = skb->tstamp; - - tx_latency = rcu_dereference(local->tx_latency); - - /* assert Tx latency stats are enabled & frame arrived when enabled */ - if (!tx_latency || !ktime_to_ns(skb_arv)) - return; - - fc = hdr->frame_control; - - if (!ieee80211_is_data(fc)) /* make sure it is a data frame */ - return; - - /* get frame tid */ - if (ieee80211_is_data_qos(hdr->frame_control)) { - qc = ieee80211_get_qos_ctl(hdr); - tid = qc[0] & IEEE80211_QOS_CTL_TID_MASK; - } else { - tid = 0; - } - - tx_lat = &sta->tx_lat[tid]; - - /* Calculate the latency */ - msrmnt = ktime_to_ms(ktime_sub(ktime_get(), skb_arv)); - - if (tx_lat->max < msrmnt) /* update stats */ - tx_lat->max = msrmnt; - tx_lat->counter++; - tx_lat->sum += msrmnt; - - if (!tx_lat->bins) /* bins not activated */ - return; - - /* count how many Tx frames transmitted with the appropriate latency */ - bin_range_count = tx_latency->n_ranges; - bin_ranges = tx_latency->ranges; - - for (i = 0; i < bin_range_count; i++) { - if (msrmnt <= bin_ranges[i]) { - tx_lat->bins[i]++; - break; - } - } - if (i == bin_range_count) /* msrmnt is bigger than the biggest range */ - tx_lat->bins[i]++; -} - -/* * Use a static threshold for now, best value to be determined * by testing ... * Should it depend on: @@ -722,7 +654,8 @@ void ieee80211_tx_status(struct ieee80211_hw *hw, struct sk_buff *skb) struct ieee80211_supported_band *sband; struct ieee80211_sub_if_data *sdata; struct net_device *prev_dev = NULL; - struct sta_info *sta, *tmp; + struct sta_info *sta; + struct rhash_head *tmp; int retry_count; int rates_idx; bool send_to_cooked; @@ -731,6 +664,7 @@ void ieee80211_tx_status(struct ieee80211_hw *hw, struct sk_buff *skb) int rtap_len; int shift = 0; int tid = IEEE80211_NUM_TIDS; + const struct bucket_table *tbl; rates_idx = ieee80211_tx_get_rates(hw, info, &retry_count); @@ -739,7 +673,9 @@ void ieee80211_tx_status(struct ieee80211_hw *hw, struct sk_buff *skb) sband = local->hw.wiphy->bands[info->band]; fc = hdr->frame_control; - for_each_sta_info(local, hdr->addr1, sta, tmp) { + tbl = rht_dereference_rcu(local->sta_hash.tbl, &local->sta_hash); + + for_each_sta_info(local, tbl, hdr->addr1, sta, tmp) { /* skip wrong virtual interface */ if (!ether_addr_equal(hdr->addr2, sta->sdata->vif.addr)) continue; @@ -853,12 +789,6 @@ void ieee80211_tx_status(struct ieee80211_hw *hw, struct sk_buff *skb) if (acked) sta->last_ack_signal = info->status.ack_signal; - - /* - * Measure frame removal for tx latency - * statistics calculation - */ - ieee80211_tx_latency_end_msrmnt(local, skb, sta, hdr); } rcu_read_unlock(); diff --git a/net/mac80211/tdls.c b/net/mac80211/tdls.c index c9f9752217ac..fff0d864adfa 100644 --- a/net/mac80211/tdls.c +++ b/net/mac80211/tdls.c @@ -136,6 +136,24 @@ ieee80211_tdls_add_supp_channels(struct ieee80211_sub_if_data *sdata, *pos = 2 * subband_cnt; } +static void ieee80211_tdls_add_oper_classes(struct ieee80211_sub_if_data *sdata, + struct sk_buff *skb) +{ + u8 *pos; + u8 op_class; + + if (!ieee80211_chandef_to_operating_class(&sdata->vif.bss_conf.chandef, + &op_class)) + return; + + pos = skb_put(skb, 4); + *pos++ = WLAN_EID_SUPPORTED_REGULATORY_CLASSES; + *pos++ = 2; /* len */ + + *pos++ = op_class; + *pos++ = op_class; /* give current operating class as alternate too */ +} + static void ieee80211_tdls_add_bss_coex_ie(struct sk_buff *skb) { u8 *pos = (void *)skb_put(skb, 3); @@ -193,6 +211,17 @@ static void ieee80211_tdls_add_link_ie(struct ieee80211_sub_if_data *sdata, memcpy(lnkid->resp_sta, rsp_addr, ETH_ALEN); } +static void +ieee80211_tdls_add_aid(struct ieee80211_sub_if_data *sdata, struct sk_buff *skb) +{ + struct ieee80211_if_managed *ifmgd = &sdata->u.mgd; + u8 *pos = (void *)skb_put(skb, 4); + + *pos++ = WLAN_EID_AID; + *pos++ = 2; /* len */ + put_unaligned_le16(ifmgd->aid, pos); +} + /* translate numbering in the WMM parameter IE to the mac80211 notation */ static enum ieee80211_ac_numbers ieee80211_ac_from_wmm(int ac) { @@ -271,21 +300,11 @@ ieee80211_tdls_add_setup_start_ies(struct ieee80211_sub_if_data *sdata, struct ieee80211_local *local = sdata->local; struct ieee80211_supported_band *sband; struct ieee80211_sta_ht_cap ht_cap; + struct ieee80211_sta_vht_cap vht_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); ieee80211_tdls_add_supp_channels(sdata, skb); @@ -338,6 +357,19 @@ ieee80211_tdls_add_setup_start_ies(struct ieee80211_sub_if_data *sdata, offset = noffset; } + 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_tdls_add_oper_classes(sdata, skb); + /* * with TDLS we can switch channels, and HT-caps are not necessarily * the same on all bands. The specification limits the setup to a @@ -346,7 +378,9 @@ ieee80211_tdls_add_setup_start_ies(struct ieee80211_sub_if_data *sdata, sband = local->hw.wiphy->bands[band]; memcpy(&ht_cap, &sband->ht_cap, sizeof(ht_cap)); - if (action_code == WLAN_TDLS_SETUP_REQUEST && ht_cap.ht_supported) { + if ((action_code == WLAN_TDLS_SETUP_REQUEST || + action_code == WLAN_PUB_ACTION_TDLS_DISCOVER_RES) && + ht_cap.ht_supported) { ieee80211_apply_htcap_overrides(sdata, &ht_cap); /* disable SMPS in TDLS initiator */ @@ -368,12 +402,63 @@ ieee80211_tdls_add_setup_start_ies(struct ieee80211_sub_if_data *sdata, ieee80211_ie_build_ht_cap(pos, &ht_cap, ht_cap.cap); } - rcu_read_unlock(); - if (ht_cap.ht_supported && (ht_cap.cap & IEEE80211_HT_CAP_SUP_WIDTH_20_40)) ieee80211_tdls_add_bss_coex_ie(skb); + ieee80211_tdls_add_link_ie(sdata, skb, peer, initiator); + + /* add any custom IEs that go before VHT capabilities */ + if (extra_ies_len) { + static const u8 before_vht_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, + WLAN_EID_MULTI_BAND, + }; + noffset = ieee80211_ie_split(extra_ies, extra_ies_len, + before_vht_cap, + ARRAY_SIZE(before_vht_cap), + offset); + pos = skb_put(skb, noffset - offset); + memcpy(pos, extra_ies + offset, noffset - offset); + offset = noffset; + } + + /* build the VHT-cap similarly to the HT-cap */ + memcpy(&vht_cap, &sband->vht_cap, sizeof(vht_cap)); + if ((action_code == WLAN_TDLS_SETUP_REQUEST || + action_code == WLAN_PUB_ACTION_TDLS_DISCOVER_RES) && + vht_cap.vht_supported) { + ieee80211_apply_vhtcap_overrides(sdata, &vht_cap); + + /* the AID is present only when VHT is implemented */ + if (action_code == WLAN_TDLS_SETUP_REQUEST) + ieee80211_tdls_add_aid(sdata, skb); + + pos = skb_put(skb, sizeof(struct ieee80211_vht_cap) + 2); + ieee80211_ie_build_vht_cap(pos, &vht_cap, vht_cap.cap); + } else if (action_code == WLAN_TDLS_SETUP_RESPONSE && + vht_cap.vht_supported && sta->sta.vht_cap.vht_supported) { + /* the peer caps are already intersected with our own */ + memcpy(&vht_cap, &sta->sta.vht_cap, sizeof(vht_cap)); + + /* the AID is present only when VHT is implemented */ + ieee80211_tdls_add_aid(sdata, skb); + + pos = skb_put(skb, sizeof(struct ieee80211_vht_cap) + 2); + ieee80211_ie_build_vht_cap(pos, &vht_cap, vht_cap.cap); + } + + rcu_read_unlock(); + /* add any remaining IEs */ if (extra_ies_len) { noffset = extra_ies_len; @@ -381,7 +466,6 @@ ieee80211_tdls_add_setup_start_ies(struct ieee80211_sub_if_data *sdata, memcpy(pos, extra_ies + offset, noffset - offset); } - ieee80211_tdls_add_link_ie(sdata, skb, peer, initiator); } static void @@ -394,6 +478,7 @@ ieee80211_tdls_add_setup_cfm_ies(struct ieee80211_sub_if_data *sdata, struct ieee80211_if_managed *ifmgd = &sdata->u.mgd; size_t offset = 0, noffset; struct sta_info *sta, *ap_sta; + enum ieee80211_band band = ieee80211_get_sdata_band(sdata); u8 *pos; rcu_read_lock(); @@ -453,6 +538,21 @@ ieee80211_tdls_add_setup_cfm_ies(struct ieee80211_sub_if_data *sdata, } } + ieee80211_tdls_add_link_ie(sdata, skb, peer, initiator); + + /* only include VHT-operation if not on the 2.4GHz band */ + if (band != IEEE80211_BAND_2GHZ && !ap_sta->sta.vht_cap.vht_supported && + sta->sta.vht_cap.vht_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_vht_operation)); + ieee80211_ie_build_vht_oper(pos, &sta->sta.vht_cap, + &chanctx_conf->def); + } + } + rcu_read_unlock(); /* add any remaining IEs */ @@ -461,8 +561,6 @@ ieee80211_tdls_add_setup_cfm_ies(struct ieee80211_sub_if_data *sdata, pos = skb_put(skb, noffset - offset); memcpy(pos, extra_ies + offset, noffset - offset); } - - ieee80211_tdls_add_link_ie(sdata, skb, peer, initiator); } static void @@ -708,8 +806,12 @@ ieee80211_tdls_build_mgmt_packet_data(struct ieee80211_sub_if_data *sdata, 26 + /* max(WMM-info, WMM-param) */ 2 + max(sizeof(struct ieee80211_ht_cap), sizeof(struct ieee80211_ht_operation)) + + 2 + max(sizeof(struct ieee80211_vht_cap), + sizeof(struct ieee80211_vht_operation)) + 50 + /* supported channels */ 3 + /* 40/20 BSS coex */ + 4 + /* AID */ + 4 + /* oper classes */ extra_ies_len + sizeof(struct ieee80211_tdls_lnkie)); if (!skb) @@ -907,7 +1009,7 @@ ieee80211_tdls_mgmt_setup(struct wiphy *wiphy, struct net_device *dev, if (!is_zero_ether_addr(sdata->u.mgd.tdls_peer) && !ether_addr_equal(sdata->u.mgd.tdls_peer, peer)) { ret = -EBUSY; - goto exit; + goto out_unlock; } /* @@ -922,27 +1024,34 @@ ieee80211_tdls_mgmt_setup(struct wiphy *wiphy, struct net_device *dev, if (!sta_info_get(sdata, peer)) { rcu_read_unlock(); ret = -ENOLINK; - goto exit; + goto out_unlock; } rcu_read_unlock(); } ieee80211_flush_queues(local, sdata, false); + memcpy(sdata->u.mgd.tdls_peer, peer, ETH_ALEN); + mutex_unlock(&local->mtx); + /* we cannot take the mutex while preparing the setup packet */ ret = ieee80211_tdls_prep_mgmt_packet(wiphy, dev, peer, action_code, dialog_token, status_code, peer_capability, initiator, extra_ies, extra_ies_len, 0, NULL); - if (ret < 0) - goto exit; + if (ret < 0) { + mutex_lock(&local->mtx); + eth_zero_addr(sdata->u.mgd.tdls_peer); + mutex_unlock(&local->mtx); + return ret; + } - 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); + return 0; -exit: +out_unlock: mutex_unlock(&local->mtx); return ret; } diff --git a/net/mac80211/trace.c b/net/mac80211/trace.c index 386e45d8a958..edfe0c170a1c 100644 --- a/net/mac80211/trace.c +++ b/net/mac80211/trace.c @@ -8,6 +8,7 @@ #include "debug.h" #define CREATE_TRACE_POINTS #include "trace.h" +#include "trace_msg.h" #ifdef CONFIG_MAC80211_MESSAGE_TRACING void __sdata_info(const char *fmt, ...) diff --git a/net/mac80211/trace.h b/net/mac80211/trace.h index 263a9561eb26..4c2e7690226a 100644 --- a/net/mac80211/trace.h +++ b/net/mac80211/trace.h @@ -1256,28 +1256,28 @@ TRACE_EVENT(drv_set_rekey_data, LOCAL_PR_ARG, VIF_PR_ARG) ); -TRACE_EVENT(drv_rssi_callback, +TRACE_EVENT(drv_event_callback, TP_PROTO(struct ieee80211_local *local, struct ieee80211_sub_if_data *sdata, - enum ieee80211_rssi_event rssi_event), + const struct ieee80211_event *_event), - TP_ARGS(local, sdata, rssi_event), + TP_ARGS(local, sdata, _event), TP_STRUCT__entry( LOCAL_ENTRY VIF_ENTRY - __field(u32, rssi_event) + __field(u32, type) ), TP_fast_assign( LOCAL_ASSIGN; VIF_ASSIGN; - __entry->rssi_event = rssi_event; + __entry->type = _event->type; ), TP_printk( - LOCAL_PR_FMT VIF_PR_FMT " rssi_event:%d", - LOCAL_PR_ARG, VIF_PR_ARG, __entry->rssi_event + LOCAL_PR_FMT VIF_PR_FMT " event:%d", + LOCAL_PR_ARG, VIF_PR_ARG, __entry->type ) ); @@ -2312,43 +2312,36 @@ TRACE_EVENT(drv_tdls_recv_channel_switch, ) ); -#ifdef CONFIG_MAC80211_MESSAGE_TRACING -#undef TRACE_SYSTEM -#define TRACE_SYSTEM mac80211_msg - -#define MAX_MSG_LEN 100 - -DECLARE_EVENT_CLASS(mac80211_msg_event, - TP_PROTO(struct va_format *vaf), +TRACE_EVENT(drv_wake_tx_queue, + TP_PROTO(struct ieee80211_local *local, + struct ieee80211_sub_if_data *sdata, + struct txq_info *txq), - TP_ARGS(vaf), + TP_ARGS(local, sdata, txq), TP_STRUCT__entry( - __dynamic_array(char, msg, MAX_MSG_LEN) + LOCAL_ENTRY + VIF_ENTRY + STA_ENTRY + __field(u8, ac) + __field(u8, tid) ), TP_fast_assign( - WARN_ON_ONCE(vsnprintf(__get_dynamic_array(msg), - MAX_MSG_LEN, vaf->fmt, - *vaf->va) >= MAX_MSG_LEN); - ), + struct ieee80211_sta *sta = txq->txq.sta; - TP_printk("%s", __get_str(msg)) -); + LOCAL_ASSIGN; + VIF_ASSIGN; + STA_ASSIGN; + __entry->ac = txq->txq.ac; + __entry->tid = txq->txq.tid; + ), -DEFINE_EVENT(mac80211_msg_event, mac80211_info, - TP_PROTO(struct va_format *vaf), - TP_ARGS(vaf) -); -DEFINE_EVENT(mac80211_msg_event, mac80211_dbg, - TP_PROTO(struct va_format *vaf), - TP_ARGS(vaf) -); -DEFINE_EVENT(mac80211_msg_event, mac80211_err, - TP_PROTO(struct va_format *vaf), - TP_ARGS(vaf) + TP_printk( + LOCAL_PR_FMT VIF_PR_FMT STA_PR_FMT " ac:%d tid:%d", + LOCAL_PR_ARG, VIF_PR_ARG, STA_PR_ARG, __entry->ac, __entry->tid + ) ); -#endif #endif /* !__MAC80211_DRIVER_TRACE || TRACE_HEADER_MULTI_READ */ diff --git a/net/mac80211/trace_msg.h b/net/mac80211/trace_msg.h new file mode 100644 index 000000000000..768f7c22a190 --- /dev/null +++ b/net/mac80211/trace_msg.h @@ -0,0 +1,53 @@ +#ifdef CONFIG_MAC80211_MESSAGE_TRACING + +#if !defined(__MAC80211_MSG_DRIVER_TRACE) || defined(TRACE_HEADER_MULTI_READ) +#define __MAC80211_MSG_DRIVER_TRACE + +#include <linux/tracepoint.h> +#include <net/mac80211.h> +#include "ieee80211_i.h" + +#undef TRACE_SYSTEM +#define TRACE_SYSTEM mac80211_msg + +#define MAX_MSG_LEN 100 + +DECLARE_EVENT_CLASS(mac80211_msg_event, + TP_PROTO(struct va_format *vaf), + + TP_ARGS(vaf), + + TP_STRUCT__entry( + __dynamic_array(char, msg, MAX_MSG_LEN) + ), + + TP_fast_assign( + WARN_ON_ONCE(vsnprintf(__get_dynamic_array(msg), + MAX_MSG_LEN, vaf->fmt, + *vaf->va) >= MAX_MSG_LEN); + ), + + TP_printk("%s", __get_str(msg)) +); + +DEFINE_EVENT(mac80211_msg_event, mac80211_info, + TP_PROTO(struct va_format *vaf), + TP_ARGS(vaf) +); +DEFINE_EVENT(mac80211_msg_event, mac80211_dbg, + TP_PROTO(struct va_format *vaf), + TP_ARGS(vaf) +); +DEFINE_EVENT(mac80211_msg_event, mac80211_err, + TP_PROTO(struct va_format *vaf), + TP_ARGS(vaf) +); +#endif /* !__MAC80211_MSG_DRIVER_TRACE || TRACE_HEADER_MULTI_READ */ + +#undef TRACE_INCLUDE_PATH +#define TRACE_INCLUDE_PATH . +#undef TRACE_INCLUDE_FILE +#define TRACE_INCLUDE_FILE trace_msg +#include <trace/define_trace.h> + +#endif diff --git a/net/mac80211/tx.c b/net/mac80211/tx.c index 07bd8db00af8..667111ee6a20 100644 --- a/net/mac80211/tx.c +++ b/net/mac80211/tx.c @@ -20,7 +20,6 @@ #include <linux/bitmap.h> #include <linux/rcupdate.h> #include <linux/export.h> -#include <linux/time.h> #include <net/net_namespace.h> #include <net/ieee80211_radiotap.h> #include <net/cfg80211.h> @@ -595,23 +594,8 @@ ieee80211_tx_h_select_key(struct ieee80211_tx_data *tx) else if (!is_multicast_ether_addr(hdr->addr1) && (key = rcu_dereference(tx->sdata->default_unicast_key))) tx->key = key; - else if (info->flags & IEEE80211_TX_CTL_INJECTED) - tx->key = NULL; - else if (!tx->sdata->drop_unencrypted) - tx->key = NULL; - else if (tx->skb->protocol == tx->sdata->control_port_protocol) - tx->key = NULL; - else if (ieee80211_is_robust_mgmt_frame(tx->skb) && - !(ieee80211_is_action(hdr->frame_control) && - tx->sta && test_sta_flag(tx->sta, WLAN_STA_MFP))) - tx->key = NULL; - else if (ieee80211_is_mgmt(hdr->frame_control) && - !ieee80211_is_robust_mgmt_frame(tx->skb)) + else tx->key = NULL; - else { - I802_DEBUG_INC(tx->local->tx_handlers_drop_unencrypted); - return TX_DROP; - } if (tx->key) { bool skip_hw = false; @@ -783,12 +767,22 @@ ieee80211_tx_h_rate_ctrl(struct ieee80211_tx_data *tx) return TX_CONTINUE; } +static __le16 ieee80211_tx_next_seq(struct sta_info *sta, int tid) +{ + u16 *seq = &sta->tid_seq[tid]; + __le16 ret = cpu_to_le16(*seq); + + /* Increase the sequence number. */ + *seq = (*seq + 0x10) & IEEE80211_SCTL_SEQ; + + return ret; +} + static ieee80211_tx_result debug_noinline ieee80211_tx_h_sequence(struct ieee80211_tx_data *tx) { struct ieee80211_tx_info *info = IEEE80211_SKB_CB(tx->skb); struct ieee80211_hdr *hdr = (struct ieee80211_hdr *)tx->skb->data; - u16 *seq; u8 *qc; int tid; @@ -839,13 +833,10 @@ ieee80211_tx_h_sequence(struct ieee80211_tx_data *tx) qc = ieee80211_get_qos_ctl(hdr); tid = *qc & IEEE80211_QOS_CTL_TID_MASK; - seq = &tx->sta->tid_seq[tid]; tx->sta->tx_msdu[tid]++; - hdr->seq_ctrl = cpu_to_le16(*seq); - - /* Increase the sequence number. */ - *seq = (*seq + 0x10) & IEEE80211_SCTL_SEQ; + if (!tx->sta->sta.txq[0]) + hdr->seq_ctrl = ieee80211_tx_next_seq(tx->sta, tid); return TX_CONTINUE; } @@ -1086,7 +1077,7 @@ static bool ieee80211_tx_prep_agg(struct ieee80211_tx_data *tx, * nothing -- this aggregation session is being started * but that might still fail with the driver */ - } else { + } else if (!tx->sta->sta.txq[tid]) { spin_lock(&tx->sta->lock); /* * Need to re-check now, because we may get here @@ -1137,11 +1128,13 @@ static bool ieee80211_tx_prep_agg(struct ieee80211_tx_data *tx, /* * initialises @tx + * pass %NULL for the station if unknown, a valid pointer if known + * or an ERR_PTR() if the station is known not to exist */ static ieee80211_tx_result ieee80211_tx_prepare(struct ieee80211_sub_if_data *sdata, struct ieee80211_tx_data *tx, - struct sk_buff *skb) + struct sta_info *sta, struct sk_buff *skb) { struct ieee80211_local *local = sdata->local; struct ieee80211_hdr *hdr; @@ -1164,17 +1157,22 @@ ieee80211_tx_prepare(struct ieee80211_sub_if_data *sdata, hdr = (struct ieee80211_hdr *) skb->data; - if (sdata->vif.type == NL80211_IFTYPE_AP_VLAN) { - tx->sta = rcu_dereference(sdata->u.vlan.sta); - if (!tx->sta && sdata->dev->ieee80211_ptr->use_4addr) - return TX_DROP; - } else if (info->flags & (IEEE80211_TX_CTL_INJECTED | - IEEE80211_TX_INTFL_NL80211_FRAME_TX) || - tx->sdata->control_port_protocol == tx->skb->protocol) { - tx->sta = sta_info_get_bss(sdata, hdr->addr1); + if (likely(sta)) { + if (!IS_ERR(sta)) + tx->sta = sta; + } else { + if (sdata->vif.type == NL80211_IFTYPE_AP_VLAN) { + tx->sta = rcu_dereference(sdata->u.vlan.sta); + if (!tx->sta && sdata->wdev.use_4addr) + return TX_DROP; + } else if (info->flags & (IEEE80211_TX_INTFL_NL80211_FRAME_TX | + IEEE80211_TX_CTL_INJECTED) || + tx->sdata->control_port_protocol == tx->skb->protocol) { + tx->sta = sta_info_get_bss(sdata, hdr->addr1); + } + if (!tx->sta && !is_multicast_ether_addr(hdr->addr1)) + tx->sta = sta_info_get(sdata, hdr->addr1); } - if (!tx->sta) - tx->sta = sta_info_get(sdata, hdr->addr1); if (tx->sta && ieee80211_is_data_qos(hdr->frame_control) && !ieee80211_is_qos_nullfunc(hdr->frame_control) && @@ -1220,13 +1218,102 @@ ieee80211_tx_prepare(struct ieee80211_sub_if_data *sdata, return TX_CONTINUE; } +static void ieee80211_drv_tx(struct ieee80211_local *local, + struct ieee80211_vif *vif, + struct ieee80211_sta *pubsta, + struct sk_buff *skb) +{ + struct ieee80211_hdr *hdr = (struct ieee80211_hdr *) skb->data; + struct ieee80211_sub_if_data *sdata = vif_to_sdata(vif); + struct ieee80211_tx_info *info = IEEE80211_SKB_CB(skb); + struct ieee80211_tx_control control = { + .sta = pubsta, + }; + struct ieee80211_txq *txq = NULL; + struct txq_info *txqi; + u8 ac; + + if (info->control.flags & IEEE80211_TX_CTRL_PS_RESPONSE) + goto tx_normal; + + if (!ieee80211_is_data(hdr->frame_control)) + goto tx_normal; + + if (pubsta) { + u8 tid = skb->priority & IEEE80211_QOS_CTL_TID_MASK; + + txq = pubsta->txq[tid]; + } else if (vif) { + txq = vif->txq; + } + + if (!txq) + goto tx_normal; + + ac = txq->ac; + txqi = to_txq_info(txq); + atomic_inc(&sdata->txqs_len[ac]); + if (atomic_read(&sdata->txqs_len[ac]) >= local->hw.txq_ac_max_pending) + netif_stop_subqueue(sdata->dev, ac); + + skb_queue_tail(&txqi->queue, skb); + drv_wake_tx_queue(local, txqi); + + return; + +tx_normal: + drv_tx(local, &control, skb); +} + +struct sk_buff *ieee80211_tx_dequeue(struct ieee80211_hw *hw, + struct ieee80211_txq *txq) +{ + struct ieee80211_local *local = hw_to_local(hw); + struct ieee80211_sub_if_data *sdata = vif_to_sdata(txq->vif); + struct txq_info *txqi = container_of(txq, struct txq_info, txq); + struct ieee80211_hdr *hdr; + struct sk_buff *skb = NULL; + u8 ac = txq->ac; + + spin_lock_bh(&txqi->queue.lock); + + if (test_bit(IEEE80211_TXQ_STOP, &txqi->flags)) + goto out; + + skb = __skb_dequeue(&txqi->queue); + if (!skb) + goto out; + + atomic_dec(&sdata->txqs_len[ac]); + if (__netif_subqueue_stopped(sdata->dev, ac)) + ieee80211_propagate_queue_wake(local, sdata->vif.hw_queue[ac]); + + hdr = (struct ieee80211_hdr *)skb->data; + if (txq->sta && ieee80211_is_data_qos(hdr->frame_control)) { + struct sta_info *sta = container_of(txq->sta, struct sta_info, + sta); + struct ieee80211_tx_info *info = IEEE80211_SKB_CB(skb); + + hdr->seq_ctrl = ieee80211_tx_next_seq(sta, txq->tid); + if (test_bit(IEEE80211_TXQ_AMPDU, &txqi->flags)) + info->flags |= IEEE80211_TX_CTL_AMPDU; + else + info->flags &= ~IEEE80211_TX_CTL_AMPDU; + } + +out: + spin_unlock_bh(&txqi->queue.lock); + + return skb; +} +EXPORT_SYMBOL(ieee80211_tx_dequeue); + static bool ieee80211_tx_frags(struct ieee80211_local *local, struct ieee80211_vif *vif, struct ieee80211_sta *sta, struct sk_buff_head *skbs, bool txpending) { - struct ieee80211_tx_control control; struct sk_buff *skb, *tmp; unsigned long flags; @@ -1284,10 +1371,9 @@ static bool ieee80211_tx_frags(struct ieee80211_local *local, spin_unlock_irqrestore(&local->queue_stop_reason_lock, flags); info->control.vif = vif; - control.sta = sta; __skb_unlink(skb, skbs); - drv_tx(local, &control, skb); + ieee80211_drv_tx(local, vif, sta, skb); } return true; @@ -1422,8 +1508,9 @@ bool ieee80211_tx_prepare_skb(struct ieee80211_hw *hw, struct ieee80211_sub_if_data *sdata = vif_to_sdata(vif); struct ieee80211_tx_info *info = IEEE80211_SKB_CB(skb); struct ieee80211_tx_data tx; + struct sk_buff *skb2; - if (ieee80211_tx_prepare(sdata, &tx, skb) == TX_DROP) + if (ieee80211_tx_prepare(sdata, &tx, NULL, skb) == TX_DROP) return false; info->band = band; @@ -1440,6 +1527,14 @@ bool ieee80211_tx_prepare_skb(struct ieee80211_hw *hw, *sta = NULL; } + /* this function isn't suitable for fragmented data frames */ + skb2 = __skb_dequeue(&tx.skbs); + if (WARN_ON(skb2 != skb || !skb_queue_empty(&tx.skbs))) { + ieee80211_free_txskb(hw, skb2); + ieee80211_purge_tx_queue(hw, &tx.skbs); + return false; + } + return true; } EXPORT_SYMBOL(ieee80211_tx_prepare_skb); @@ -1448,7 +1543,8 @@ EXPORT_SYMBOL(ieee80211_tx_prepare_skb); * Returns false if the frame couldn't be transmitted but was queued instead. */ static bool ieee80211_tx(struct ieee80211_sub_if_data *sdata, - struct sk_buff *skb, bool txpending) + struct sta_info *sta, struct sk_buff *skb, + bool txpending) { struct ieee80211_local *local = sdata->local; struct ieee80211_tx_data tx; @@ -1464,7 +1560,7 @@ static bool ieee80211_tx(struct ieee80211_sub_if_data *sdata, /* initialises tx */ led_len = skb->len; - res_prepare = ieee80211_tx_prepare(sdata, &tx, skb); + res_prepare = ieee80211_tx_prepare(sdata, &tx, sta, skb); if (unlikely(res_prepare == TX_DROP)) { ieee80211_free_txskb(&local->hw, skb); @@ -1520,7 +1616,8 @@ static int ieee80211_skb_resize(struct ieee80211_sub_if_data *sdata, return 0; } -void ieee80211_xmit(struct ieee80211_sub_if_data *sdata, struct sk_buff *skb) +void ieee80211_xmit(struct ieee80211_sub_if_data *sdata, + struct sta_info *sta, struct sk_buff *skb) { struct ieee80211_local *local = sdata->local; struct ieee80211_tx_info *info = IEEE80211_SKB_CB(skb); @@ -1555,7 +1652,7 @@ void ieee80211_xmit(struct ieee80211_sub_if_data *sdata, struct sk_buff *skb) } ieee80211_set_qos_hdr(sdata, skb); - ieee80211_tx(sdata, skb, false); + ieee80211_tx(sdata, sta, skb, false); } static bool ieee80211_parse_tx_radiotap(struct sk_buff *skb) @@ -1776,7 +1873,7 @@ netdev_tx_t ieee80211_monitor_start_xmit(struct sk_buff *skb, goto fail_rcu; info->band = chandef->chan->band; - ieee80211_xmit(sdata, skb); + ieee80211_xmit(sdata, NULL, skb); rcu_read_unlock(); return NETDEV_TX_OK; @@ -1788,21 +1885,89 @@ fail: return NETDEV_TX_OK; /* meaning, we dealt with the skb */ } -/* - * Measure Tx frame arrival time for Tx latency statistics calculation - * A single Tx frame latency should be measured from when it is entering the - * Kernel until we receive Tx complete confirmation indication and the skb is - * freed. - */ -static void ieee80211_tx_latency_start_msrmnt(struct ieee80211_local *local, - struct sk_buff *skb) +static inline bool ieee80211_is_tdls_setup(struct sk_buff *skb) { - struct ieee80211_tx_latency_bin_ranges *tx_latency; + u16 ethertype = (skb->data[12] << 8) | skb->data[13]; - tx_latency = rcu_dereference(local->tx_latency); - if (!tx_latency) - return; - skb->tstamp = ktime_get(); + return ethertype == ETH_P_TDLS && + skb->len > 14 && + skb->data[14] == WLAN_TDLS_SNAP_RFTYPE; +} + +static int ieee80211_lookup_ra_sta(struct ieee80211_sub_if_data *sdata, + struct sk_buff *skb, + struct sta_info **sta_out) +{ + struct sta_info *sta; + + switch (sdata->vif.type) { + case NL80211_IFTYPE_AP_VLAN: + sta = rcu_dereference(sdata->u.vlan.sta); + if (sta) { + *sta_out = sta; + return 0; + } else if (sdata->wdev.use_4addr) { + return -ENOLINK; + } + /* fall through */ + case NL80211_IFTYPE_AP: + case NL80211_IFTYPE_OCB: + case NL80211_IFTYPE_ADHOC: + if (is_multicast_ether_addr(skb->data)) { + *sta_out = ERR_PTR(-ENOENT); + return 0; + } + sta = sta_info_get_bss(sdata, skb->data); + break; + case NL80211_IFTYPE_WDS: + sta = sta_info_get(sdata, sdata->u.wds.remote_addr); + break; +#ifdef CONFIG_MAC80211_MESH + case NL80211_IFTYPE_MESH_POINT: + /* determined much later */ + *sta_out = NULL; + return 0; +#endif + case NL80211_IFTYPE_STATION: + if (sdata->wdev.wiphy->flags & WIPHY_FLAG_SUPPORTS_TDLS) { + sta = sta_info_get(sdata, skb->data); + if (sta) { + bool tdls_peer, tdls_auth; + + tdls_peer = test_sta_flag(sta, + WLAN_STA_TDLS_PEER); + tdls_auth = test_sta_flag(sta, + WLAN_STA_TDLS_PEER_AUTH); + + if (tdls_peer && tdls_auth) { + *sta_out = sta; + return 0; + } + + /* + * TDLS link during setup - throw out frames to + * peer. 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 && + !ieee80211_is_tdls_setup(skb)) + return -EINVAL; + } + + } + + sta = sta_info_get(sdata, sdata->u.mgd.bssid); + if (!sta) + return -ENOLINK; + break; + default: + return -EINVAL; + } + + *sta_out = sta ?: ERR_PTR(-ENOENT); + return 0; } /** @@ -1824,7 +1989,8 @@ static void ieee80211_tx_latency_start_msrmnt(struct ieee80211_local *local, * Returns: the (possibly reallocated) skb or an ERR_PTR() code */ static struct sk_buff *ieee80211_build_hdr(struct ieee80211_sub_if_data *sdata, - struct sk_buff *skb, u32 info_flags) + struct sk_buff *skb, u32 info_flags, + struct sta_info *sta) { struct ieee80211_local *local = sdata->local; struct ieee80211_tx_info *info; @@ -1837,9 +2003,8 @@ static struct sk_buff *ieee80211_build_hdr(struct ieee80211_sub_if_data *sdata, const u8 *encaps_data; int encaps_len, skip_header_bytes; int nh_pos, h_pos; - struct sta_info *sta = NULL; - bool wme_sta = false, authorized = false, tdls_auth = false; - bool tdls_peer = false, tdls_setup_frame = false; + bool wme_sta = false, authorized = false; + bool tdls_peer; bool multicast; u16 info_id = 0; struct ieee80211_chanctx_conf *chanctx_conf; @@ -1847,6 +2012,9 @@ static struct sk_buff *ieee80211_build_hdr(struct ieee80211_sub_if_data *sdata, enum ieee80211_band band; int ret; + if (IS_ERR(sta)) + sta = NULL; + /* convert Ethernet header to proper 802.11 header (based on * operation mode) */ ethertype = (skb->data[12] << 8) | skb->data[13]; @@ -1854,8 +2022,7 @@ static struct sk_buff *ieee80211_build_hdr(struct ieee80211_sub_if_data *sdata, switch (sdata->vif.type) { case NL80211_IFTYPE_AP_VLAN: - sta = rcu_dereference(sdata->u.vlan.sta); - if (sta) { + if (sdata->wdev.use_4addr) { fc |= cpu_to_le16(IEEE80211_FCTL_FROMDS | IEEE80211_FCTL_TODS); /* RA TA DA SA */ memcpy(hdr.addr1, sta->sta.addr, ETH_ALEN); @@ -1874,7 +2041,7 @@ static struct sk_buff *ieee80211_build_hdr(struct ieee80211_sub_if_data *sdata, goto free; } band = chanctx_conf->def.chan->band; - if (sta) + if (sdata->wdev.use_4addr) break; /* fall through */ case NL80211_IFTYPE_AP: @@ -1978,38 +2145,10 @@ static struct sk_buff *ieee80211_build_hdr(struct ieee80211_sub_if_data *sdata, break; #endif case NL80211_IFTYPE_STATION: - if (sdata->wdev.wiphy->flags & WIPHY_FLAG_SUPPORTS_TDLS) { - sta = sta_info_get(sdata, skb->data); - if (sta) { - authorized = test_sta_flag(sta, - WLAN_STA_AUTHORIZED); - wme_sta = sta->sta.wme; - tdls_peer = test_sta_flag(sta, - WLAN_STA_TDLS_PEER); - tdls_auth = test_sta_flag(sta, - WLAN_STA_TDLS_PEER_AUTH); - } - - if (tdls_peer) - tdls_setup_frame = - ethertype == ETH_P_TDLS && - skb->len > 14 && - skb->data[14] == WLAN_TDLS_SNAP_RFTYPE; - } - - /* - * 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) { - ret = -EINVAL; - goto free; - } + /* we already did checks when looking up the RA STA */ + tdls_peer = test_sta_flag(sta, WLAN_STA_TDLS_PEER); - /* send direct packets to authorized TDLS peers */ - if (tdls_peer && tdls_auth) { + if (tdls_peer) { /* DA SA BSSID */ memcpy(hdr.addr1, skb->data, ETH_ALEN); memcpy(hdr.addr2, skb->data + ETH_ALEN, ETH_ALEN); @@ -2071,26 +2210,19 @@ static struct sk_buff *ieee80211_build_hdr(struct ieee80211_sub_if_data *sdata, goto free; } - /* - * There's no need to try to look up the destination - * if it is a multicast address (which can only happen - * in AP mode) - */ multicast = is_multicast_ether_addr(hdr.addr1); - if (!multicast) { - sta = sta_info_get(sdata, hdr.addr1); - if (sta) { - authorized = test_sta_flag(sta, WLAN_STA_AUTHORIZED); - wme_sta = sta->sta.wme; - } - } - /* For mesh, the use of the QoS header is mandatory */ - if (ieee80211_vif_is_mesh(&sdata->vif)) + /* sta is always NULL for mesh */ + if (sta) { + authorized = test_sta_flag(sta, WLAN_STA_AUTHORIZED); + wme_sta = sta->sta.wme; + } else if (ieee80211_vif_is_mesh(&sdata->vif)) { + /* For mesh, the use of the QoS header is mandatory */ wme_sta = true; + } - /* receiver and we are QoS enabled, use a QoS type frame */ - if (wme_sta && local->hw.queues >= IEEE80211_NUM_ACS) { + /* receiver does QoS (which also means we do) use it */ + if (wme_sta) { fc |= cpu_to_le16(IEEE80211_STYPE_QOS_DATA); hdrlen += 2; } @@ -2260,7 +2392,7 @@ void __ieee80211_subif_start_xmit(struct sk_buff *skb, u32 info_flags) { struct ieee80211_sub_if_data *sdata = IEEE80211_DEV_TO_SUB_IF(dev); - struct ieee80211_local *local = sdata->local; + struct sta_info *sta; if (unlikely(skb->len < ETH_HLEN)) { kfree_skb(skb); @@ -2269,10 +2401,12 @@ void __ieee80211_subif_start_xmit(struct sk_buff *skb, rcu_read_lock(); - /* Measure frame arrival for Tx latency statistics calculation */ - ieee80211_tx_latency_start_msrmnt(local, skb); + if (ieee80211_lookup_ra_sta(sdata, skb, &sta)) { + kfree_skb(skb); + goto out; + } - skb = ieee80211_build_hdr(sdata, skb, info_flags); + skb = ieee80211_build_hdr(sdata, skb, info_flags, sta); if (IS_ERR(skb)) goto out; @@ -2280,7 +2414,7 @@ void __ieee80211_subif_start_xmit(struct sk_buff *skb, dev->stats.tx_bytes += skb->len; dev->trans_start = jiffies; - ieee80211_xmit(sdata, skb); + ieee80211_xmit(sdata, sta, skb); out: rcu_read_unlock(); } @@ -2308,10 +2442,17 @@ ieee80211_build_data_template(struct ieee80211_sub_if_data *sdata, .local = sdata->local, .sdata = sdata, }; + struct sta_info *sta; rcu_read_lock(); - skb = ieee80211_build_hdr(sdata, skb, info_flags); + if (ieee80211_lookup_ra_sta(sdata, skb, &sta)) { + kfree_skb(skb); + skb = ERR_PTR(-EINVAL); + goto out; + } + + skb = ieee80211_build_hdr(sdata, skb, info_flags, sta); if (IS_ERR(skb)) goto out; @@ -2369,7 +2510,7 @@ static bool ieee80211_tx_pending_skb(struct ieee80211_local *local, return true; } info->band = chanctx_conf->def.chan->band; - result = ieee80211_tx(sdata, skb, true); + result = ieee80211_tx(sdata, NULL, skb, true); } else { struct sk_buff_head skbs; @@ -3107,7 +3248,7 @@ ieee80211_get_buffered_bc(struct ieee80211_hw *hw, if (sdata->vif.type == NL80211_IFTYPE_AP) sdata = IEEE80211_DEV_TO_SUB_IF(skb->dev); - if (!ieee80211_tx_prepare(sdata, &tx, skb)) + if (!ieee80211_tx_prepare(sdata, &tx, NULL, skb)) break; dev_kfree_skb_any(skb); } @@ -3239,6 +3380,6 @@ void __ieee80211_tx_skb_tid_band(struct ieee80211_sub_if_data *sdata, */ local_bh_disable(); IEEE80211_SKB_CB(skb)->band = band; - ieee80211_xmit(sdata, skb); + ieee80211_xmit(sdata, NULL, skb); local_bh_enable(); } diff --git a/net/mac80211/util.c b/net/mac80211/util.c index 747bdcf72e92..79412f16b61d 100644 --- a/net/mac80211/util.c +++ b/net/mac80211/util.c @@ -308,6 +308,11 @@ void ieee80211_propagate_queue_wake(struct ieee80211_local *local, int queue) for (ac = 0; ac < n_acs; ac++) { int ac_queue = sdata->vif.hw_queue[ac]; + if (local->ops->wake_tx_queue && + (atomic_read(&sdata->txqs_len[ac]) > + local->hw.txq_ac_max_pending)) + continue; + if (ac_queue == queue || (sdata->vif.cab_queue == queue && local->queue_stop_reasons[ac_queue] == 0 && @@ -625,13 +630,14 @@ void ieee80211_wake_vif_queues(struct ieee80211_local *local, reason, true); } -static void __iterate_active_interfaces(struct ieee80211_local *local, - u32 iter_flags, - void (*iterator)(void *data, u8 *mac, - struct ieee80211_vif *vif), - void *data) +static void __iterate_interfaces(struct ieee80211_local *local, + u32 iter_flags, + void (*iterator)(void *data, u8 *mac, + struct ieee80211_vif *vif), + void *data) { struct ieee80211_sub_if_data *sdata; + bool active_only = iter_flags & IEEE80211_IFACE_ITER_ACTIVE; list_for_each_entry_rcu(sdata, &local->interfaces, list) { switch (sdata->vif.type) { @@ -645,9 +651,9 @@ static void __iterate_active_interfaces(struct ieee80211_local *local, break; } if (!(iter_flags & IEEE80211_IFACE_ITER_RESUME_ALL) && - !(sdata->flags & IEEE80211_SDATA_IN_DRIVER)) + active_only && !(sdata->flags & IEEE80211_SDATA_IN_DRIVER)) continue; - if (ieee80211_sdata_running(sdata)) + if (ieee80211_sdata_running(sdata) || !active_only) iterator(data, sdata->vif.addr, &sdata->vif); } @@ -656,12 +662,12 @@ static void __iterate_active_interfaces(struct ieee80211_local *local, lockdep_is_held(&local->iflist_mtx) || lockdep_rtnl_is_held()); if (sdata && - (iter_flags & IEEE80211_IFACE_ITER_RESUME_ALL || + (iter_flags & IEEE80211_IFACE_ITER_RESUME_ALL || !active_only || sdata->flags & IEEE80211_SDATA_IN_DRIVER)) iterator(data, sdata->vif.addr, &sdata->vif); } -void ieee80211_iterate_active_interfaces( +void ieee80211_iterate_interfaces( struct ieee80211_hw *hw, u32 iter_flags, void (*iterator)(void *data, u8 *mac, struct ieee80211_vif *vif), @@ -670,10 +676,10 @@ void ieee80211_iterate_active_interfaces( struct ieee80211_local *local = hw_to_local(hw); mutex_lock(&local->iflist_mtx); - __iterate_active_interfaces(local, iter_flags, iterator, data); + __iterate_interfaces(local, iter_flags, iterator, data); mutex_unlock(&local->iflist_mtx); } -EXPORT_SYMBOL_GPL(ieee80211_iterate_active_interfaces); +EXPORT_SYMBOL_GPL(ieee80211_iterate_interfaces); void ieee80211_iterate_active_interfaces_atomic( struct ieee80211_hw *hw, u32 iter_flags, @@ -684,7 +690,8 @@ void ieee80211_iterate_active_interfaces_atomic( struct ieee80211_local *local = hw_to_local(hw); rcu_read_lock(); - __iterate_active_interfaces(local, iter_flags, iterator, data); + __iterate_interfaces(local, iter_flags | IEEE80211_IFACE_ITER_ACTIVE, + iterator, data); rcu_read_unlock(); } EXPORT_SYMBOL_GPL(ieee80211_iterate_active_interfaces_atomic); @@ -699,7 +706,8 @@ void ieee80211_iterate_active_interfaces_rtnl( ASSERT_RTNL(); - __iterate_active_interfaces(local, iter_flags, iterator, data); + __iterate_interfaces(local, iter_flags | IEEE80211_IFACE_ITER_ACTIVE, + iterator, data); } EXPORT_SYMBOL_GPL(ieee80211_iterate_active_interfaces_rtnl); @@ -742,6 +750,18 @@ struct ieee80211_vif *wdev_to_ieee80211_vif(struct wireless_dev *wdev) } EXPORT_SYMBOL_GPL(wdev_to_ieee80211_vif); +struct wireless_dev *ieee80211_vif_to_wdev(struct ieee80211_vif *vif) +{ + struct ieee80211_sub_if_data *sdata = vif_to_sdata(vif); + + if (!ieee80211_sdata_running(sdata) || + !(sdata->flags & IEEE80211_SDATA_IN_DRIVER)) + return NULL; + + return &sdata->wdev; +} +EXPORT_SYMBOL_GPL(ieee80211_vif_to_wdev); + /* * Nothing should have been stuffed into the workqueue during * the suspend->resume cycle. Since we can't check each caller @@ -1811,8 +1831,25 @@ int ieee80211_reconfig(struct ieee80211_local *local) list_for_each_entry(sdata, &local->interfaces, list) { if (sdata->vif.type != NL80211_IFTYPE_AP_VLAN && sdata->vif.type != NL80211_IFTYPE_MONITOR && - ieee80211_sdata_running(sdata)) + ieee80211_sdata_running(sdata)) { res = drv_add_interface(local, sdata); + if (WARN_ON(res)) + break; + } + } + + /* If adding any of the interfaces failed above, roll back and + * report failure. + */ + if (res) { + list_for_each_entry_continue_reverse(sdata, &local->interfaces, + list) + if (sdata->vif.type != NL80211_IFTYPE_AP_VLAN && + sdata->vif.type != NL80211_IFTYPE_MONITOR && + ieee80211_sdata_running(sdata)) + drv_remove_interface(local, sdata); + ieee80211_handle_reconfig_failure(local); + return res; } /* add channel contexts */ @@ -2157,46 +2194,6 @@ void ieee80211_recalc_min_chandef(struct ieee80211_sub_if_data *sdata) mutex_unlock(&local->chanctx_mtx); } -static bool ieee80211_id_in_list(const u8 *ids, int n_ids, u8 id) -{ - int i; - - for (i = 0; i < n_ids; i++) - if (ids[i] == id) - return true; - return false; -} - -size_t ieee80211_ie_split_ric(const u8 *ies, size_t ielen, - const u8 *ids, int n_ids, - const u8 *after_ric, int n_after_ric, - size_t offset) -{ - size_t pos = offset; - - while (pos < ielen && ieee80211_id_in_list(ids, n_ids, ies[pos])) { - if (ies[pos] == WLAN_EID_RIC_DATA && n_after_ric) { - pos += 2 + ies[pos + 1]; - - while (pos < ielen && - !ieee80211_id_in_list(after_ric, n_after_ric, - ies[pos])) - pos += 2 + ies[pos + 1]; - } else { - pos += 2 + ies[pos + 1]; - } - } - - return pos; -} - -size_t ieee80211_ie_split(const u8 *ies, size_t ielen, - const u8 *ids, int n_ids, size_t offset) -{ - return ieee80211_ie_split_ric(ies, ielen, ids, n_ids, NULL, 0, offset); -} -EXPORT_SYMBOL(ieee80211_ie_split); - size_t ieee80211_ie_split_vendor(const u8 *ies, size_t ielen, size_t offset) { size_t pos = offset; @@ -2344,6 +2341,41 @@ u8 *ieee80211_ie_build_ht_oper(u8 *pos, struct ieee80211_sta_ht_cap *ht_cap, return pos + sizeof(struct ieee80211_ht_operation); } +u8 *ieee80211_ie_build_vht_oper(u8 *pos, struct ieee80211_sta_vht_cap *vht_cap, + const struct cfg80211_chan_def *chandef) +{ + struct ieee80211_vht_operation *vht_oper; + + *pos++ = WLAN_EID_VHT_OPERATION; + *pos++ = sizeof(struct ieee80211_vht_operation); + vht_oper = (struct ieee80211_vht_operation *)pos; + vht_oper->center_freq_seg1_idx = ieee80211_frequency_to_channel( + chandef->center_freq1); + if (chandef->center_freq2) + vht_oper->center_freq_seg2_idx = + ieee80211_frequency_to_channel(chandef->center_freq2); + + switch (chandef->width) { + case NL80211_CHAN_WIDTH_160: + vht_oper->chan_width = IEEE80211_VHT_CHANWIDTH_160MHZ; + break; + case NL80211_CHAN_WIDTH_80P80: + vht_oper->chan_width = IEEE80211_VHT_CHANWIDTH_80P80MHZ; + break; + case NL80211_CHAN_WIDTH_80: + vht_oper->chan_width = IEEE80211_VHT_CHANWIDTH_80MHZ; + break; + default: + vht_oper->chan_width = IEEE80211_VHT_CHANWIDTH_USE_HT; + break; + } + + /* don't require special VHT peer rates */ + vht_oper->basic_mcs_set = cpu_to_le16(0xffff); + + return pos + sizeof(struct ieee80211_vht_operation); +} + void ieee80211_ht_oper_to_chandef(struct ieee80211_channel *control_chan, const struct ieee80211_ht_operation *ht_oper, struct cfg80211_chan_def *chandef) @@ -2373,6 +2405,39 @@ void ieee80211_ht_oper_to_chandef(struct ieee80211_channel *control_chan, cfg80211_chandef_create(chandef, control_chan, channel_type); } +void ieee80211_vht_oper_to_chandef(struct ieee80211_channel *control_chan, + const struct ieee80211_vht_operation *oper, + struct cfg80211_chan_def *chandef) +{ + if (!oper) + return; + + chandef->chan = control_chan; + + switch (oper->chan_width) { + case IEEE80211_VHT_CHANWIDTH_USE_HT: + break; + case IEEE80211_VHT_CHANWIDTH_80MHZ: + chandef->width = NL80211_CHAN_WIDTH_80; + break; + case IEEE80211_VHT_CHANWIDTH_160MHZ: + chandef->width = NL80211_CHAN_WIDTH_160; + break; + case IEEE80211_VHT_CHANWIDTH_80P80MHZ: + chandef->width = NL80211_CHAN_WIDTH_80P80; + break; + default: + break; + } + + chandef->center_freq1 = + ieee80211_channel_to_frequency(oper->center_freq_seg1_idx, + control_chan->band); + chandef->center_freq2 = + ieee80211_channel_to_frequency(oper->center_freq_seg2_idx, + control_chan->band); +} + int ieee80211_parse_bitrates(struct cfg80211_chan_def *chandef, const struct ieee80211_supported_band *sband, const u8 *srates, int srates_len, u32 *rates) @@ -3252,3 +3317,20 @@ u8 *ieee80211_add_wmm_info_ie(u8 *buf, u8 qosinfo) return buf; } + +void ieee80211_init_tx_queue(struct ieee80211_sub_if_data *sdata, + struct sta_info *sta, + struct txq_info *txqi, int tid) +{ + skb_queue_head_init(&txqi->queue); + txqi->txq.vif = &sdata->vif; + + if (sta) { + txqi->txq.sta = &sta->sta; + sta->sta.txq[tid] = &txqi->txq; + txqi->txq.ac = ieee802_1d_to_ac[tid & 7]; + } else { + sdata->vif.txq = &txqi->txq; + txqi->txq.ac = IEEE80211_AC_BE; + } +} diff --git a/net/mac80211/vht.c b/net/mac80211/vht.c index 85f9596da07b..80694d55db74 100644 --- a/net/mac80211/vht.c +++ b/net/mac80211/vht.c @@ -129,10 +129,6 @@ 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/wpa.c b/net/mac80211/wpa.c index 75de6fac40d1..9d63d93c836e 100644 --- a/net/mac80211/wpa.c +++ b/net/mac80211/wpa.c @@ -780,9 +780,8 @@ ieee80211_crypto_cs_encrypt(struct ieee80211_tx_data *tx, struct ieee80211_hdr *hdr = (struct ieee80211_hdr *)skb->data; struct ieee80211_key *key = tx->key; struct ieee80211_tx_info *info = IEEE80211_SKB_CB(skb); - const struct ieee80211_cipher_scheme *cs = key->sta->cipher_scheme; int hdrlen; - u8 *pos; + u8 *pos, iv_len = key->conf.iv_len; if (info->control.hw_key && !(info->control.hw_key->flags & IEEE80211_KEY_FLAG_PUT_IV_SPACE)) { @@ -790,14 +789,14 @@ ieee80211_crypto_cs_encrypt(struct ieee80211_tx_data *tx, return TX_CONTINUE; } - if (unlikely(skb_headroom(skb) < cs->hdr_len && - pskb_expand_head(skb, cs->hdr_len, 0, GFP_ATOMIC))) + if (unlikely(skb_headroom(skb) < iv_len && + pskb_expand_head(skb, iv_len, 0, GFP_ATOMIC))) return TX_DROP; hdrlen = ieee80211_hdrlen(hdr->frame_control); - pos = skb_push(skb, cs->hdr_len); - memmove(pos, pos + cs->hdr_len, hdrlen); + pos = skb_push(skb, iv_len); + memmove(pos, pos + iv_len, hdrlen); return TX_CONTINUE; } @@ -1217,7 +1216,7 @@ ieee80211_crypto_hw_encrypt(struct ieee80211_tx_data *tx) if (!info->control.hw_key) return TX_DROP; - if (tx->key->sta->cipher_scheme) { + if (tx->key->flags & KEY_FLAG_CIPHER_SCHEME) { res = ieee80211_crypto_cs_encrypt(tx, skb); if (res != TX_CONTINUE) return res; diff --git a/net/mac802154/driver-ops.h b/net/mac802154/driver-ops.h index 98180a9fff4a..a0533357b9ea 100644 --- a/net/mac802154/driver-ops.h +++ b/net/mac802154/driver-ops.h @@ -1,4 +1,4 @@ -#ifndef __MAC802154_DRVIER_OPS +#ifndef __MAC802154_DRIVER_OPS #define __MAC802154_DRIVER_OPS #include <linux/types.h> @@ -220,4 +220,4 @@ drv_set_promiscuous_mode(struct ieee802154_local *local, bool on) return local->ops->set_promiscuous_mode(&local->hw, on); } -#endif /* __MAC802154_DRVIER_OPS */ +#endif /* __MAC802154_DRIVER_OPS */ diff --git a/net/mac802154/iface.c b/net/mac802154/iface.c index 6fb6bdf9868c..38b56f9d9386 100644 --- a/net/mac802154/iface.c +++ b/net/mac802154/iface.c @@ -174,24 +174,16 @@ ieee802154_check_mac_settings(struct ieee802154_local *local, } if (local->hw.flags & IEEE802154_HW_AFILT) { - if (wpan_dev->pan_id != nwpan_dev->pan_id) - return -EBUSY; - - if (wpan_dev->short_addr != nwpan_dev->short_addr) - return -EBUSY; - - if (wpan_dev->extended_addr != nwpan_dev->extended_addr) + if (wpan_dev->pan_id != nwpan_dev->pan_id || + wpan_dev->short_addr != nwpan_dev->short_addr || + wpan_dev->extended_addr != nwpan_dev->extended_addr) return -EBUSY; } if (local->hw.flags & IEEE802154_HW_CSMA_PARAMS) { - if (wpan_dev->min_be != nwpan_dev->min_be) - return -EBUSY; - - if (wpan_dev->max_be != nwpan_dev->max_be) - return -EBUSY; - - if (wpan_dev->csma_retries != nwpan_dev->csma_retries) + if (wpan_dev->min_be != nwpan_dev->min_be || + wpan_dev->max_be != nwpan_dev->max_be || + wpan_dev->csma_retries != nwpan_dev->csma_retries) return -EBUSY; } diff --git a/net/mac802154/util.c b/net/mac802154/util.c index 5fc979027919..150bf807e572 100644 --- a/net/mac802154/util.c +++ b/net/mac802154/util.c @@ -65,8 +65,19 @@ void ieee802154_xmit_complete(struct ieee802154_hw *hw, struct sk_buff *skb, { if (ifs_handling) { struct ieee802154_local *local = hw_to_local(hw); + u8 max_sifs_size; - if (skb->len > 18) + /* If transceiver sets CRC on his own we need to use lifs + * threshold len above 16 otherwise 18, because it's not + * part of skb->len. + */ + if (hw->flags & IEEE802154_HW_TX_OMIT_CKSUM) + max_sifs_size = IEEE802154_MAX_SIFS_FRAME_SIZE - + IEEE802154_FCS_LEN; + else + max_sifs_size = IEEE802154_MAX_SIFS_FRAME_SIZE; + + if (skb->len > max_sifs_size) hrtimer_start(&local->ifs_timer, ktime_set(0, hw->phy->lifs_period * NSEC_PER_USEC), HRTIMER_MODE_REL); diff --git a/net/mpls/Kconfig b/net/mpls/Kconfig index 37421db88965..17bde799c854 100644 --- a/net/mpls/Kconfig +++ b/net/mpls/Kconfig @@ -1,9 +1,30 @@ # # MPLS configuration # + +menuconfig MPLS + bool "MultiProtocol Label Switching" + default n + ---help--- + MultiProtocol Label Switching routes packets through logical + circuits. Originally conceived as a way of routing packets at + hardware speeds (before hardware was capable of routing ipv4 packets), + MPLS remains a simple way of making tunnels. + + If you have not heard of MPLS you probably want to say N here. + +if MPLS + config NET_MPLS_GSO tristate "MPLS: GSO support" help This is helper module to allow segmentation of non-MPLS GSO packets that have had MPLS stack entries pushed onto them and thus become MPLS GSO packets. + +config MPLS_ROUTING + tristate "MPLS: routing support" + help + Add support for forwarding of mpls packets. + +endif # MPLS diff --git a/net/mpls/Makefile b/net/mpls/Makefile index 6dec088c2d0f..65bbe68c72e6 100644 --- a/net/mpls/Makefile +++ b/net/mpls/Makefile @@ -2,3 +2,6 @@ # Makefile for MPLS. # obj-$(CONFIG_NET_MPLS_GSO) += mpls_gso.o +obj-$(CONFIG_MPLS_ROUTING) += mpls_router.o + +mpls_router-y := af_mpls.o diff --git a/net/mpls/af_mpls.c b/net/mpls/af_mpls.c new file mode 100644 index 000000000000..954810c76a86 --- /dev/null +++ b/net/mpls/af_mpls.c @@ -0,0 +1,1142 @@ +#include <linux/types.h> +#include <linux/skbuff.h> +#include <linux/socket.h> +#include <linux/sysctl.h> +#include <linux/net.h> +#include <linux/module.h> +#include <linux/if_arp.h> +#include <linux/ipv6.h> +#include <linux/mpls.h> +#include <linux/vmalloc.h> +#include <net/ip.h> +#include <net/dst.h> +#include <net/sock.h> +#include <net/arp.h> +#include <net/ip_fib.h> +#include <net/netevent.h> +#include <net/netns/generic.h> +#include "internal.h" + +#define LABEL_NOT_SPECIFIED (1<<20) +#define MAX_NEW_LABELS 2 + +/* This maximum ha length copied from the definition of struct neighbour */ +#define MAX_VIA_ALEN (ALIGN(MAX_ADDR_LEN, sizeof(unsigned long))) + +struct mpls_route { /* next hop label forwarding entry */ + struct net_device __rcu *rt_dev; + struct rcu_head rt_rcu; + u32 rt_label[MAX_NEW_LABELS]; + u8 rt_protocol; /* routing protocol that set this entry */ + u8 rt_labels; + u8 rt_via_alen; + u8 rt_via_table; + u8 rt_via[0]; +}; + +static int zero = 0; +static int label_limit = (1 << 20) - 1; + +static void rtmsg_lfib(int event, u32 label, struct mpls_route *rt, + struct nlmsghdr *nlh, struct net *net, u32 portid, + unsigned int nlm_flags); + +static struct mpls_route *mpls_route_input_rcu(struct net *net, unsigned index) +{ + struct mpls_route *rt = NULL; + + if (index < net->mpls.platform_labels) { + struct mpls_route __rcu **platform_label = + rcu_dereference(net->mpls.platform_label); + rt = rcu_dereference(platform_label[index]); + } + return rt; +} + +static inline struct mpls_dev *mpls_dev_get(const struct net_device *dev) +{ + return rcu_dereference_rtnl(dev->mpls_ptr); +} + +static bool mpls_output_possible(const struct net_device *dev) +{ + return dev && (dev->flags & IFF_UP) && netif_carrier_ok(dev); +} + +static unsigned int mpls_rt_header_size(const struct mpls_route *rt) +{ + /* The size of the layer 2.5 labels to be added for this route */ + return rt->rt_labels * sizeof(struct mpls_shim_hdr); +} + +static unsigned int mpls_dev_mtu(const struct net_device *dev) +{ + /* The amount of data the layer 2 frame can hold */ + return dev->mtu; +} + +static bool mpls_pkt_too_big(const struct sk_buff *skb, unsigned int mtu) +{ + if (skb->len <= mtu) + return false; + + if (skb_is_gso(skb) && skb_gso_network_seglen(skb) <= mtu) + return false; + + return true; +} + +static bool mpls_egress(struct mpls_route *rt, struct sk_buff *skb, + struct mpls_entry_decoded dec) +{ + /* RFC4385 and RFC5586 encode other packets in mpls such that + * they don't conflict with the ip version number, making + * decoding by examining the ip version correct in everything + * except for the strangest cases. + * + * The strange cases if we choose to support them will require + * manual configuration. + */ + struct iphdr *hdr4; + bool success = true; + + /* The IPv4 code below accesses through the IPv4 header + * checksum, which is 12 bytes into the packet. + * The IPv6 code below accesses through the IPv6 hop limit + * which is 8 bytes into the packet. + * + * For all supported cases there should always be at least 12 + * bytes of packet data present. The IPv4 header is 20 bytes + * without options and the IPv6 header is always 40 bytes + * long. + */ + if (!pskb_may_pull(skb, 12)) + return false; + + /* Use ip_hdr to find the ip protocol version */ + hdr4 = ip_hdr(skb); + if (hdr4->version == 4) { + skb->protocol = htons(ETH_P_IP); + csum_replace2(&hdr4->check, + htons(hdr4->ttl << 8), + htons(dec.ttl << 8)); + hdr4->ttl = dec.ttl; + } + else if (hdr4->version == 6) { + struct ipv6hdr *hdr6 = ipv6_hdr(skb); + skb->protocol = htons(ETH_P_IPV6); + hdr6->hop_limit = dec.ttl; + } + else + /* version 0 and version 1 are used by pseudo wires */ + success = false; + return success; +} + +static int mpls_forward(struct sk_buff *skb, struct net_device *dev, + struct packet_type *pt, struct net_device *orig_dev) +{ + struct net *net = dev_net(dev); + struct mpls_shim_hdr *hdr; + struct mpls_route *rt; + struct mpls_entry_decoded dec; + struct net_device *out_dev; + struct mpls_dev *mdev; + unsigned int hh_len; + unsigned int new_header_size; + unsigned int mtu; + int err; + + /* Careful this entire function runs inside of an rcu critical section */ + + mdev = mpls_dev_get(dev); + if (!mdev || !mdev->input_enabled) + goto drop; + + if (skb->pkt_type != PACKET_HOST) + goto drop; + + if ((skb = skb_share_check(skb, GFP_ATOMIC)) == NULL) + goto drop; + + if (!pskb_may_pull(skb, sizeof(*hdr))) + goto drop; + + /* Read and decode the label */ + hdr = mpls_hdr(skb); + dec = mpls_entry_decode(hdr); + + /* Pop the label */ + skb_pull(skb, sizeof(*hdr)); + skb_reset_network_header(skb); + + skb_orphan(skb); + + rt = mpls_route_input_rcu(net, dec.label); + if (!rt) + goto drop; + + /* Find the output device */ + out_dev = rcu_dereference(rt->rt_dev); + if (!mpls_output_possible(out_dev)) + goto drop; + + if (skb_warn_if_lro(skb)) + goto drop; + + skb_forward_csum(skb); + + /* Verify ttl is valid */ + if (dec.ttl <= 1) + goto drop; + dec.ttl -= 1; + + /* Verify the destination can hold the packet */ + new_header_size = mpls_rt_header_size(rt); + mtu = mpls_dev_mtu(out_dev); + if (mpls_pkt_too_big(skb, mtu - new_header_size)) + goto drop; + + hh_len = LL_RESERVED_SPACE(out_dev); + if (!out_dev->header_ops) + hh_len = 0; + + /* Ensure there is enough space for the headers in the skb */ + if (skb_cow(skb, hh_len + new_header_size)) + goto drop; + + skb->dev = out_dev; + skb->protocol = htons(ETH_P_MPLS_UC); + + if (unlikely(!new_header_size && dec.bos)) { + /* Penultimate hop popping */ + if (!mpls_egress(rt, skb, dec)) + goto drop; + } else { + bool bos; + int i; + skb_push(skb, new_header_size); + skb_reset_network_header(skb); + /* Push the new labels */ + hdr = mpls_hdr(skb); + bos = dec.bos; + for (i = rt->rt_labels - 1; i >= 0; i--) { + hdr[i] = mpls_entry_encode(rt->rt_label[i], dec.ttl, 0, bos); + bos = false; + } + } + + err = neigh_xmit(rt->rt_via_table, out_dev, rt->rt_via, skb); + if (err) + net_dbg_ratelimited("%s: packet transmission failed: %d\n", + __func__, err); + return 0; + +drop: + kfree_skb(skb); + return NET_RX_DROP; +} + +static struct packet_type mpls_packet_type __read_mostly = { + .type = cpu_to_be16(ETH_P_MPLS_UC), + .func = mpls_forward, +}; + +static const struct nla_policy rtm_mpls_policy[RTA_MAX+1] = { + [RTA_DST] = { .type = NLA_U32 }, + [RTA_OIF] = { .type = NLA_U32 }, +}; + +struct mpls_route_config { + u32 rc_protocol; + u32 rc_ifindex; + u16 rc_via_table; + u16 rc_via_alen; + u8 rc_via[MAX_VIA_ALEN]; + u32 rc_label; + u32 rc_output_labels; + u32 rc_output_label[MAX_NEW_LABELS]; + u32 rc_nlflags; + struct nl_info rc_nlinfo; +}; + +static struct mpls_route *mpls_rt_alloc(size_t alen) +{ + struct mpls_route *rt; + + rt = kzalloc(sizeof(*rt) + alen, GFP_KERNEL); + if (rt) + rt->rt_via_alen = alen; + return rt; +} + +static void mpls_rt_free(struct mpls_route *rt) +{ + if (rt) + kfree_rcu(rt, rt_rcu); +} + +static void mpls_notify_route(struct net *net, unsigned index, + struct mpls_route *old, struct mpls_route *new, + const struct nl_info *info) +{ + struct nlmsghdr *nlh = info ? info->nlh : NULL; + unsigned portid = info ? info->portid : 0; + int event = new ? RTM_NEWROUTE : RTM_DELROUTE; + struct mpls_route *rt = new ? new : old; + unsigned nlm_flags = (old && new) ? NLM_F_REPLACE : 0; + /* Ignore reserved labels for now */ + if (rt && (index >= 16)) + rtmsg_lfib(event, index, rt, nlh, net, portid, nlm_flags); +} + +static void mpls_route_update(struct net *net, unsigned index, + struct net_device *dev, struct mpls_route *new, + const struct nl_info *info) +{ + struct mpls_route __rcu **platform_label; + struct mpls_route *rt, *old = NULL; + + ASSERT_RTNL(); + + platform_label = rtnl_dereference(net->mpls.platform_label); + rt = rtnl_dereference(platform_label[index]); + if (!dev || (rt && (rtnl_dereference(rt->rt_dev) == dev))) { + rcu_assign_pointer(platform_label[index], new); + old = rt; + } + + mpls_notify_route(net, index, old, new, info); + + /* If we removed a route free it now */ + mpls_rt_free(old); +} + +static unsigned find_free_label(struct net *net) +{ + struct mpls_route __rcu **platform_label; + size_t platform_labels; + unsigned index; + + platform_label = rtnl_dereference(net->mpls.platform_label); + platform_labels = net->mpls.platform_labels; + for (index = 16; index < platform_labels; index++) { + if (!rtnl_dereference(platform_label[index])) + return index; + } + return LABEL_NOT_SPECIFIED; +} + +static int mpls_route_add(struct mpls_route_config *cfg) +{ + struct mpls_route __rcu **platform_label; + struct net *net = cfg->rc_nlinfo.nl_net; + struct net_device *dev = NULL; + struct mpls_route *rt, *old; + unsigned index; + int i; + int err = -EINVAL; + + index = cfg->rc_label; + + /* If a label was not specified during insert pick one */ + if ((index == LABEL_NOT_SPECIFIED) && + (cfg->rc_nlflags & NLM_F_CREATE)) { + index = find_free_label(net); + } + + /* The first 16 labels are reserved, and may not be set */ + if (index < 16) + goto errout; + + /* The full 20 bit range may not be supported. */ + if (index >= net->mpls.platform_labels) + goto errout; + + /* Ensure only a supported number of labels are present */ + if (cfg->rc_output_labels > MAX_NEW_LABELS) + goto errout; + + err = -ENODEV; + dev = dev_get_by_index(net, cfg->rc_ifindex); + if (!dev) + goto errout; + + /* Ensure this is a supported device */ + err = -EINVAL; + if (!mpls_dev_get(dev)) + goto errout; + + err = -EINVAL; + if ((cfg->rc_via_table == NEIGH_LINK_TABLE) && + (dev->addr_len != cfg->rc_via_alen)) + goto errout; + + /* Append makes no sense with mpls */ + err = -EOPNOTSUPP; + if (cfg->rc_nlflags & NLM_F_APPEND) + goto errout; + + err = -EEXIST; + platform_label = rtnl_dereference(net->mpls.platform_label); + old = rtnl_dereference(platform_label[index]); + if ((cfg->rc_nlflags & NLM_F_EXCL) && old) + goto errout; + + err = -EEXIST; + if (!(cfg->rc_nlflags & NLM_F_REPLACE) && old) + goto errout; + + err = -ENOENT; + if (!(cfg->rc_nlflags & NLM_F_CREATE) && !old) + goto errout; + + err = -ENOMEM; + rt = mpls_rt_alloc(cfg->rc_via_alen); + if (!rt) + goto errout; + + rt->rt_labels = cfg->rc_output_labels; + for (i = 0; i < rt->rt_labels; i++) + rt->rt_label[i] = cfg->rc_output_label[i]; + rt->rt_protocol = cfg->rc_protocol; + RCU_INIT_POINTER(rt->rt_dev, dev); + rt->rt_via_table = cfg->rc_via_table; + memcpy(rt->rt_via, cfg->rc_via, cfg->rc_via_alen); + + mpls_route_update(net, index, NULL, rt, &cfg->rc_nlinfo); + + dev_put(dev); + return 0; + +errout: + if (dev) + dev_put(dev); + return err; +} + +static int mpls_route_del(struct mpls_route_config *cfg) +{ + struct net *net = cfg->rc_nlinfo.nl_net; + unsigned index; + int err = -EINVAL; + + index = cfg->rc_label; + + /* The first 16 labels are reserved, and may not be removed */ + if (index < 16) + goto errout; + + /* The full 20 bit range may not be supported */ + if (index >= net->mpls.platform_labels) + goto errout; + + mpls_route_update(net, index, NULL, NULL, &cfg->rc_nlinfo); + + err = 0; +errout: + return err; +} + +#define MPLS_PERDEV_SYSCTL_OFFSET(field) \ + (&((struct mpls_dev *)0)->field) + +static const struct ctl_table mpls_dev_table[] = { + { + .procname = "input", + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec, + .data = MPLS_PERDEV_SYSCTL_OFFSET(input_enabled), + }, + { } +}; + +static int mpls_dev_sysctl_register(struct net_device *dev, + struct mpls_dev *mdev) +{ + char path[sizeof("net/mpls/conf/") + IFNAMSIZ]; + struct ctl_table *table; + int i; + + table = kmemdup(&mpls_dev_table, sizeof(mpls_dev_table), GFP_KERNEL); + if (!table) + goto out; + + /* Table data contains only offsets relative to the base of + * the mdev at this point, so make them absolute. + */ + for (i = 0; i < ARRAY_SIZE(mpls_dev_table); i++) + table[i].data = (char *)mdev + (uintptr_t)table[i].data; + + snprintf(path, sizeof(path), "net/mpls/conf/%s", dev->name); + + mdev->sysctl = register_net_sysctl(dev_net(dev), path, table); + if (!mdev->sysctl) + goto free; + + return 0; + +free: + kfree(table); +out: + return -ENOBUFS; +} + +static void mpls_dev_sysctl_unregister(struct mpls_dev *mdev) +{ + struct ctl_table *table; + + table = mdev->sysctl->ctl_table_arg; + unregister_net_sysctl_table(mdev->sysctl); + kfree(table); +} + +static struct mpls_dev *mpls_add_dev(struct net_device *dev) +{ + struct mpls_dev *mdev; + int err = -ENOMEM; + + ASSERT_RTNL(); + + mdev = kzalloc(sizeof(*mdev), GFP_KERNEL); + if (!mdev) + return ERR_PTR(err); + + err = mpls_dev_sysctl_register(dev, mdev); + if (err) + goto free; + + rcu_assign_pointer(dev->mpls_ptr, mdev); + + return mdev; + +free: + kfree(mdev); + return ERR_PTR(err); +} + +static void mpls_ifdown(struct net_device *dev) +{ + struct mpls_route __rcu **platform_label; + struct net *net = dev_net(dev); + struct mpls_dev *mdev; + unsigned index; + + platform_label = rtnl_dereference(net->mpls.platform_label); + for (index = 0; index < net->mpls.platform_labels; index++) { + struct mpls_route *rt = rtnl_dereference(platform_label[index]); + if (!rt) + continue; + if (rtnl_dereference(rt->rt_dev) != dev) + continue; + rt->rt_dev = NULL; + } + + mdev = mpls_dev_get(dev); + if (!mdev) + return; + + mpls_dev_sysctl_unregister(mdev); + + RCU_INIT_POINTER(dev->mpls_ptr, NULL); + + kfree(mdev); +} + +static int mpls_dev_notify(struct notifier_block *this, unsigned long event, + void *ptr) +{ + struct net_device *dev = netdev_notifier_info_to_dev(ptr); + struct mpls_dev *mdev; + + switch(event) { + case NETDEV_REGISTER: + /* For now just support ethernet devices */ + if ((dev->type == ARPHRD_ETHER) || + (dev->type == ARPHRD_LOOPBACK)) { + mdev = mpls_add_dev(dev); + if (IS_ERR(mdev)) + return notifier_from_errno(PTR_ERR(mdev)); + } + break; + + case NETDEV_UNREGISTER: + mpls_ifdown(dev); + break; + } + return NOTIFY_OK; +} + +static struct notifier_block mpls_dev_notifier = { + .notifier_call = mpls_dev_notify, +}; + +static int nla_put_via(struct sk_buff *skb, + u8 table, const void *addr, int alen) +{ + static const int table_to_family[NEIGH_NR_TABLES + 1] = { + AF_INET, AF_INET6, AF_DECnet, AF_PACKET, + }; + struct nlattr *nla; + struct rtvia *via; + int family = AF_UNSPEC; + + nla = nla_reserve(skb, RTA_VIA, alen + 2); + if (!nla) + return -EMSGSIZE; + + if (table <= NEIGH_NR_TABLES) + family = table_to_family[table]; + + via = nla_data(nla); + via->rtvia_family = family; + memcpy(via->rtvia_addr, addr, alen); + return 0; +} + +int nla_put_labels(struct sk_buff *skb, int attrtype, + u8 labels, const u32 label[]) +{ + struct nlattr *nla; + struct mpls_shim_hdr *nla_label; + bool bos; + int i; + nla = nla_reserve(skb, attrtype, labels*4); + if (!nla) + return -EMSGSIZE; + + nla_label = nla_data(nla); + bos = true; + for (i = labels - 1; i >= 0; i--) { + nla_label[i] = mpls_entry_encode(label[i], 0, 0, bos); + bos = false; + } + + return 0; +} + +int nla_get_labels(const struct nlattr *nla, + u32 max_labels, u32 *labels, u32 label[]) +{ + unsigned len = nla_len(nla); + unsigned nla_labels; + struct mpls_shim_hdr *nla_label; + bool bos; + int i; + + /* len needs to be an even multiple of 4 (the label size) */ + if (len & 3) + return -EINVAL; + + /* Limit the number of new labels allowed */ + nla_labels = len/4; + if (nla_labels > max_labels) + return -EINVAL; + + nla_label = nla_data(nla); + bos = true; + for (i = nla_labels - 1; i >= 0; i--, bos = false) { + struct mpls_entry_decoded dec; + dec = mpls_entry_decode(nla_label + i); + + /* Ensure the bottom of stack flag is properly set + * and ttl and tc are both clear. + */ + if ((dec.bos != bos) || dec.ttl || dec.tc) + return -EINVAL; + + switch (dec.label) { + case LABEL_IMPLICIT_NULL: + /* RFC3032: This is a label that an LSR may + * assign and distribute, but which never + * actually appears in the encapsulation. + */ + return -EINVAL; + } + + label[i] = dec.label; + } + *labels = nla_labels; + return 0; +} + +static int rtm_to_route_config(struct sk_buff *skb, struct nlmsghdr *nlh, + struct mpls_route_config *cfg) +{ + struct rtmsg *rtm; + struct nlattr *tb[RTA_MAX+1]; + int index; + int err; + + err = nlmsg_parse(nlh, sizeof(*rtm), tb, RTA_MAX, rtm_mpls_policy); + if (err < 0) + goto errout; + + err = -EINVAL; + rtm = nlmsg_data(nlh); + memset(cfg, 0, sizeof(*cfg)); + + if (rtm->rtm_family != AF_MPLS) + goto errout; + if (rtm->rtm_dst_len != 20) + goto errout; + if (rtm->rtm_src_len != 0) + goto errout; + if (rtm->rtm_tos != 0) + goto errout; + if (rtm->rtm_table != RT_TABLE_MAIN) + goto errout; + /* Any value is acceptable for rtm_protocol */ + + /* As mpls uses destination specific addresses + * (or source specific address in the case of multicast) + * all addresses have universal scope. + */ + if (rtm->rtm_scope != RT_SCOPE_UNIVERSE) + goto errout; + if (rtm->rtm_type != RTN_UNICAST) + goto errout; + if (rtm->rtm_flags != 0) + goto errout; + + cfg->rc_label = LABEL_NOT_SPECIFIED; + cfg->rc_protocol = rtm->rtm_protocol; + cfg->rc_nlflags = nlh->nlmsg_flags; + cfg->rc_nlinfo.portid = NETLINK_CB(skb).portid; + cfg->rc_nlinfo.nlh = nlh; + cfg->rc_nlinfo.nl_net = sock_net(skb->sk); + + for (index = 0; index <= RTA_MAX; index++) { + struct nlattr *nla = tb[index]; + if (!nla) + continue; + + switch(index) { + case RTA_OIF: + cfg->rc_ifindex = nla_get_u32(nla); + break; + case RTA_NEWDST: + if (nla_get_labels(nla, MAX_NEW_LABELS, + &cfg->rc_output_labels, + cfg->rc_output_label)) + goto errout; + break; + case RTA_DST: + { + u32 label_count; + if (nla_get_labels(nla, 1, &label_count, + &cfg->rc_label)) + goto errout; + + /* The first 16 labels are reserved, and may not be set */ + if (cfg->rc_label < 16) + goto errout; + + break; + } + case RTA_VIA: + { + struct rtvia *via = nla_data(nla); + if (nla_len(nla) < offsetof(struct rtvia, rtvia_addr)) + goto errout; + cfg->rc_via_alen = nla_len(nla) - + offsetof(struct rtvia, rtvia_addr); + if (cfg->rc_via_alen > MAX_VIA_ALEN) + goto errout; + + /* Validate the address family */ + switch(via->rtvia_family) { + case AF_PACKET: + cfg->rc_via_table = NEIGH_LINK_TABLE; + break; + case AF_INET: + cfg->rc_via_table = NEIGH_ARP_TABLE; + if (cfg->rc_via_alen != 4) + goto errout; + break; + case AF_INET6: + cfg->rc_via_table = NEIGH_ND_TABLE; + if (cfg->rc_via_alen != 16) + goto errout; + break; + default: + /* Unsupported address family */ + goto errout; + } + + memcpy(cfg->rc_via, via->rtvia_addr, cfg->rc_via_alen); + break; + } + default: + /* Unsupported attribute */ + goto errout; + } + } + + err = 0; +errout: + return err; +} + +static int mpls_rtm_delroute(struct sk_buff *skb, struct nlmsghdr *nlh) +{ + struct mpls_route_config cfg; + int err; + + err = rtm_to_route_config(skb, nlh, &cfg); + if (err < 0) + return err; + + return mpls_route_del(&cfg); +} + + +static int mpls_rtm_newroute(struct sk_buff *skb, struct nlmsghdr *nlh) +{ + struct mpls_route_config cfg; + int err; + + err = rtm_to_route_config(skb, nlh, &cfg); + if (err < 0) + return err; + + return mpls_route_add(&cfg); +} + +static int mpls_dump_route(struct sk_buff *skb, u32 portid, u32 seq, int event, + u32 label, struct mpls_route *rt, int flags) +{ + struct net_device *dev; + struct nlmsghdr *nlh; + struct rtmsg *rtm; + + nlh = nlmsg_put(skb, portid, seq, event, sizeof(*rtm), flags); + if (nlh == NULL) + return -EMSGSIZE; + + rtm = nlmsg_data(nlh); + rtm->rtm_family = AF_MPLS; + rtm->rtm_dst_len = 20; + rtm->rtm_src_len = 0; + rtm->rtm_tos = 0; + rtm->rtm_table = RT_TABLE_MAIN; + rtm->rtm_protocol = rt->rt_protocol; + rtm->rtm_scope = RT_SCOPE_UNIVERSE; + rtm->rtm_type = RTN_UNICAST; + rtm->rtm_flags = 0; + + if (rt->rt_labels && + nla_put_labels(skb, RTA_NEWDST, rt->rt_labels, rt->rt_label)) + goto nla_put_failure; + if (nla_put_via(skb, rt->rt_via_table, rt->rt_via, rt->rt_via_alen)) + goto nla_put_failure; + dev = rtnl_dereference(rt->rt_dev); + if (dev && nla_put_u32(skb, RTA_OIF, dev->ifindex)) + goto nla_put_failure; + if (nla_put_labels(skb, RTA_DST, 1, &label)) + goto nla_put_failure; + + nlmsg_end(skb, nlh); + return 0; + +nla_put_failure: + nlmsg_cancel(skb, nlh); + return -EMSGSIZE; +} + +static int mpls_dump_routes(struct sk_buff *skb, struct netlink_callback *cb) +{ + struct net *net = sock_net(skb->sk); + struct mpls_route __rcu **platform_label; + size_t platform_labels; + unsigned int index; + + ASSERT_RTNL(); + + index = cb->args[0]; + if (index < 16) + index = 16; + + platform_label = rtnl_dereference(net->mpls.platform_label); + platform_labels = net->mpls.platform_labels; + for (; index < platform_labels; index++) { + struct mpls_route *rt; + rt = rtnl_dereference(platform_label[index]); + if (!rt) + continue; + + if (mpls_dump_route(skb, NETLINK_CB(cb->skb).portid, + cb->nlh->nlmsg_seq, RTM_NEWROUTE, + index, rt, NLM_F_MULTI) < 0) + break; + } + cb->args[0] = index; + + return skb->len; +} + +static inline size_t lfib_nlmsg_size(struct mpls_route *rt) +{ + size_t payload = + NLMSG_ALIGN(sizeof(struct rtmsg)) + + nla_total_size(2 + rt->rt_via_alen) /* RTA_VIA */ + + nla_total_size(4); /* RTA_DST */ + if (rt->rt_labels) /* RTA_NEWDST */ + payload += nla_total_size(rt->rt_labels * 4); + if (rt->rt_dev) /* RTA_OIF */ + payload += nla_total_size(4); + return payload; +} + +static void rtmsg_lfib(int event, u32 label, struct mpls_route *rt, + struct nlmsghdr *nlh, struct net *net, u32 portid, + unsigned int nlm_flags) +{ + struct sk_buff *skb; + u32 seq = nlh ? nlh->nlmsg_seq : 0; + int err = -ENOBUFS; + + skb = nlmsg_new(lfib_nlmsg_size(rt), GFP_KERNEL); + if (skb == NULL) + goto errout; + + err = mpls_dump_route(skb, portid, seq, event, label, rt, nlm_flags); + if (err < 0) { + /* -EMSGSIZE implies BUG in lfib_nlmsg_size */ + WARN_ON(err == -EMSGSIZE); + kfree_skb(skb); + goto errout; + } + rtnl_notify(skb, net, portid, RTNLGRP_MPLS_ROUTE, nlh, GFP_KERNEL); + + return; +errout: + if (err < 0) + rtnl_set_sk_err(net, RTNLGRP_MPLS_ROUTE, err); +} + +static int resize_platform_label_table(struct net *net, size_t limit) +{ + size_t size = sizeof(struct mpls_route *) * limit; + size_t old_limit; + size_t cp_size; + struct mpls_route __rcu **labels = NULL, **old; + struct mpls_route *rt0 = NULL, *rt2 = NULL; + unsigned index; + + if (size) { + labels = kzalloc(size, GFP_KERNEL | __GFP_NOWARN | __GFP_NORETRY); + if (!labels) + labels = vzalloc(size); + + if (!labels) + goto nolabels; + } + + /* In case the predefined labels need to be populated */ + if (limit > LABEL_IPV4_EXPLICIT_NULL) { + struct net_device *lo = net->loopback_dev; + rt0 = mpls_rt_alloc(lo->addr_len); + if (!rt0) + goto nort0; + RCU_INIT_POINTER(rt0->rt_dev, lo); + rt0->rt_protocol = RTPROT_KERNEL; + rt0->rt_via_table = NEIGH_LINK_TABLE; + memcpy(rt0->rt_via, lo->dev_addr, lo->addr_len); + } + if (limit > LABEL_IPV6_EXPLICIT_NULL) { + struct net_device *lo = net->loopback_dev; + rt2 = mpls_rt_alloc(lo->addr_len); + if (!rt2) + goto nort2; + RCU_INIT_POINTER(rt2->rt_dev, lo); + rt2->rt_protocol = RTPROT_KERNEL; + rt2->rt_via_table = NEIGH_LINK_TABLE; + memcpy(rt2->rt_via, lo->dev_addr, lo->addr_len); + } + + rtnl_lock(); + /* Remember the original table */ + old = rtnl_dereference(net->mpls.platform_label); + old_limit = net->mpls.platform_labels; + + /* Free any labels beyond the new table */ + for (index = limit; index < old_limit; index++) + mpls_route_update(net, index, NULL, NULL, NULL); + + /* Copy over the old labels */ + cp_size = size; + if (old_limit < limit) + cp_size = old_limit * sizeof(struct mpls_route *); + + memcpy(labels, old, cp_size); + + /* If needed set the predefined labels */ + if ((old_limit <= LABEL_IPV6_EXPLICIT_NULL) && + (limit > LABEL_IPV6_EXPLICIT_NULL)) { + RCU_INIT_POINTER(labels[LABEL_IPV6_EXPLICIT_NULL], rt2); + rt2 = NULL; + } + + if ((old_limit <= LABEL_IPV4_EXPLICIT_NULL) && + (limit > LABEL_IPV4_EXPLICIT_NULL)) { + RCU_INIT_POINTER(labels[LABEL_IPV4_EXPLICIT_NULL], rt0); + rt0 = NULL; + } + + /* Update the global pointers */ + net->mpls.platform_labels = limit; + rcu_assign_pointer(net->mpls.platform_label, labels); + + rtnl_unlock(); + + mpls_rt_free(rt2); + mpls_rt_free(rt0); + + if (old) { + synchronize_rcu(); + kvfree(old); + } + return 0; + +nort2: + mpls_rt_free(rt0); +nort0: + kvfree(labels); +nolabels: + return -ENOMEM; +} + +static int mpls_platform_labels(struct ctl_table *table, int write, + void __user *buffer, size_t *lenp, loff_t *ppos) +{ + struct net *net = table->data; + int platform_labels = net->mpls.platform_labels; + int ret; + struct ctl_table tmp = { + .procname = table->procname, + .data = &platform_labels, + .maxlen = sizeof(int), + .mode = table->mode, + .extra1 = &zero, + .extra2 = &label_limit, + }; + + ret = proc_dointvec_minmax(&tmp, write, buffer, lenp, ppos); + + if (write && ret == 0) + ret = resize_platform_label_table(net, platform_labels); + + return ret; +} + +static const struct ctl_table mpls_table[] = { + { + .procname = "platform_labels", + .data = NULL, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = mpls_platform_labels, + }, + { } +}; + +static int mpls_net_init(struct net *net) +{ + struct ctl_table *table; + + net->mpls.platform_labels = 0; + net->mpls.platform_label = NULL; + + table = kmemdup(mpls_table, sizeof(mpls_table), GFP_KERNEL); + if (table == NULL) + return -ENOMEM; + + table[0].data = net; + net->mpls.ctl = register_net_sysctl(net, "net/mpls", table); + if (net->mpls.ctl == NULL) + return -ENOMEM; + + return 0; +} + +static void mpls_net_exit(struct net *net) +{ + struct mpls_route __rcu **platform_label; + size_t platform_labels; + struct ctl_table *table; + unsigned int index; + + table = net->mpls.ctl->ctl_table_arg; + unregister_net_sysctl_table(net->mpls.ctl); + kfree(table); + + /* An rcu grace period has passed since there was a device in + * the network namespace (and thus the last in flight packet) + * left this network namespace. This is because + * unregister_netdevice_many and netdev_run_todo has completed + * for each network device that was in this network namespace. + * + * As such no additional rcu synchronization is necessary when + * freeing the platform_label table. + */ + rtnl_lock(); + platform_label = rtnl_dereference(net->mpls.platform_label); + platform_labels = net->mpls.platform_labels; + for (index = 0; index < platform_labels; index++) { + struct mpls_route *rt = rtnl_dereference(platform_label[index]); + RCU_INIT_POINTER(platform_label[index], NULL); + mpls_rt_free(rt); + } + rtnl_unlock(); + + kvfree(platform_label); +} + +static struct pernet_operations mpls_net_ops = { + .init = mpls_net_init, + .exit = mpls_net_exit, +}; + +static int __init mpls_init(void) +{ + int err; + + BUILD_BUG_ON(sizeof(struct mpls_shim_hdr) != 4); + + err = register_pernet_subsys(&mpls_net_ops); + if (err) + goto out; + + err = register_netdevice_notifier(&mpls_dev_notifier); + if (err) + goto out_unregister_pernet; + + dev_add_pack(&mpls_packet_type); + + rtnl_register(PF_MPLS, RTM_NEWROUTE, mpls_rtm_newroute, NULL, NULL); + rtnl_register(PF_MPLS, RTM_DELROUTE, mpls_rtm_delroute, NULL, NULL); + rtnl_register(PF_MPLS, RTM_GETROUTE, NULL, mpls_dump_routes, NULL); + err = 0; +out: + return err; + +out_unregister_pernet: + unregister_pernet_subsys(&mpls_net_ops); + goto out; +} +module_init(mpls_init); + +static void __exit mpls_exit(void) +{ + rtnl_unregister_all(PF_MPLS); + dev_remove_pack(&mpls_packet_type); + unregister_netdevice_notifier(&mpls_dev_notifier); + unregister_pernet_subsys(&mpls_net_ops); +} +module_exit(mpls_exit); + +MODULE_DESCRIPTION("MultiProtocol Label Switching"); +MODULE_LICENSE("GPL v2"); +MODULE_ALIAS_NETPROTO(PF_MPLS); diff --git a/net/mpls/internal.h b/net/mpls/internal.h new file mode 100644 index 000000000000..693877d69606 --- /dev/null +++ b/net/mpls/internal.h @@ -0,0 +1,65 @@ +#ifndef MPLS_INTERNAL_H +#define MPLS_INTERNAL_H + +#define LABEL_IPV4_EXPLICIT_NULL 0 /* RFC3032 */ +#define LABEL_ROUTER_ALERT_LABEL 1 /* RFC3032 */ +#define LABEL_IPV6_EXPLICIT_NULL 2 /* RFC3032 */ +#define LABEL_IMPLICIT_NULL 3 /* RFC3032 */ +#define LABEL_ENTROPY_INDICATOR 7 /* RFC6790 */ +#define LABEL_GAL 13 /* RFC5586 */ +#define LABEL_OAM_ALERT 14 /* RFC3429 */ +#define LABEL_EXTENSION 15 /* RFC7274 */ + + +struct mpls_shim_hdr { + __be32 label_stack_entry; +}; + +struct mpls_entry_decoded { + u32 label; + u8 ttl; + u8 tc; + u8 bos; +}; + +struct mpls_dev { + int input_enabled; + + struct ctl_table_header *sysctl; +}; + +struct sk_buff; + +static inline struct mpls_shim_hdr *mpls_hdr(const struct sk_buff *skb) +{ + return (struct mpls_shim_hdr *)skb_network_header(skb); +} + +static inline struct mpls_shim_hdr mpls_entry_encode(u32 label, unsigned ttl, unsigned tc, bool bos) +{ + struct mpls_shim_hdr result; + result.label_stack_entry = + cpu_to_be32((label << MPLS_LS_LABEL_SHIFT) | + (tc << MPLS_LS_TC_SHIFT) | + (bos ? (1 << MPLS_LS_S_SHIFT) : 0) | + (ttl << MPLS_LS_TTL_SHIFT)); + return result; +} + +static inline struct mpls_entry_decoded mpls_entry_decode(struct mpls_shim_hdr *hdr) +{ + struct mpls_entry_decoded result; + unsigned entry = be32_to_cpu(hdr->label_stack_entry); + + result.label = (entry & MPLS_LS_LABEL_MASK) >> MPLS_LS_LABEL_SHIFT; + result.ttl = (entry & MPLS_LS_TTL_MASK) >> MPLS_LS_TTL_SHIFT; + result.tc = (entry & MPLS_LS_TC_MASK) >> MPLS_LS_TC_SHIFT; + result.bos = (entry & MPLS_LS_S_MASK) >> MPLS_LS_S_SHIFT; + + return result; +} + +int nla_put_labels(struct sk_buff *skb, int attrtype, u8 labels, const u32 label[]); +int nla_get_labels(const struct nlattr *nla, u32 max_labels, u32 *labels, u32 label[]); + +#endif /* MPLS_INTERNAL_H */ diff --git a/net/netfilter/Kconfig b/net/netfilter/Kconfig index b02660fa9eb0..f70e34a68f70 100644 --- a/net/netfilter/Kconfig +++ b/net/netfilter/Kconfig @@ -438,8 +438,10 @@ config NF_TABLES To compile it as a module, choose M here. +if NF_TABLES + config NF_TABLES_INET - depends on NF_TABLES && IPV6 + depends on IPV6 select NF_TABLES_IPV4 select NF_TABLES_IPV6 tristate "Netfilter nf_tables mixed IPv4/IPv6 tables support" @@ -447,21 +449,18 @@ config NF_TABLES_INET This option enables support for a mixed IPv4/IPv6 "inet" table. config NFT_EXTHDR - depends on NF_TABLES tristate "Netfilter nf_tables IPv6 exthdr module" help This option adds the "exthdr" expression that you can use to match IPv6 extension headers. config NFT_META - depends on NF_TABLES tristate "Netfilter nf_tables meta module" help This option adds the "meta" expression that you can use to match and to set packet metainformation such as the packet mark. config NFT_CT - depends on NF_TABLES depends on NF_CONNTRACK tristate "Netfilter nf_tables conntrack module" help @@ -469,42 +468,36 @@ config NFT_CT connection tracking information such as the flow state. config NFT_RBTREE - depends on NF_TABLES tristate "Netfilter nf_tables rbtree set module" help This option adds the "rbtree" set type (Red Black tree) that is used to build interval-based sets. config NFT_HASH - depends on NF_TABLES tristate "Netfilter nf_tables hash set module" help This option adds the "hash" set type that is used to build one-way mappings between matchings and actions. config NFT_COUNTER - depends on NF_TABLES tristate "Netfilter nf_tables counter module" help This option adds the "counter" expression that you can use to include packet and byte counters in a rule. config NFT_LOG - depends on NF_TABLES tristate "Netfilter nf_tables log module" help This option adds the "log" expression that you can use to log packets matching some criteria. config NFT_LIMIT - depends on NF_TABLES tristate "Netfilter nf_tables limit module" help This option adds the "limit" expression that you can use to ratelimit rule matchings. config NFT_MASQ - depends on NF_TABLES depends on NF_CONNTRACK depends on NF_NAT tristate "Netfilter nf_tables masquerade support" @@ -513,7 +506,6 @@ config NFT_MASQ to perform NAT in the masquerade flavour. config NFT_REDIR - depends on NF_TABLES depends on NF_CONNTRACK depends on NF_NAT tristate "Netfilter nf_tables redirect support" @@ -522,7 +514,6 @@ config NFT_REDIR to perform NAT in the redirect flavour. config NFT_NAT - depends on NF_TABLES depends on NF_CONNTRACK select NF_NAT tristate "Netfilter nf_tables nat module" @@ -531,8 +522,6 @@ config NFT_NAT typical Network Address Translation (NAT) packet transformations. config NFT_QUEUE - depends on NF_TABLES - depends on NETFILTER_XTABLES depends on NETFILTER_NETLINK_QUEUE tristate "Netfilter nf_tables queue module" help @@ -540,7 +529,6 @@ config NFT_QUEUE infrastructure (also known as NFQUEUE) from nftables. config NFT_REJECT - depends on NF_TABLES default m if NETFILTER_ADVANCED=n tristate "Netfilter nf_tables reject support" help @@ -554,7 +542,6 @@ config NFT_REJECT_INET tristate config NFT_COMPAT - depends on NF_TABLES depends on NETFILTER_XTABLES tristate "Netfilter x_tables over nf_tables module" help @@ -562,6 +549,8 @@ config NFT_COMPAT x_tables match/target extensions over the nf_tables framework. +endif # NF_TABLES + config NETFILTER_XTABLES tristate "Netfilter Xtables support (required for ip_tables)" default m if NETFILTER_ADVANCED=n @@ -951,7 +940,7 @@ comment "Xtables matches" config NETFILTER_XT_MATCH_ADDRTYPE tristate '"addrtype" address type match support' - depends on NETFILTER_ADVANCED + default m if NETFILTER_ADVANCED=n ---help--- This option allows you to match what routing thinks of an address, eg. UNICAST, LOCAL, BROADCAST, ... diff --git a/net/netfilter/Makefile b/net/netfilter/Makefile index 89f73a9e9874..a87d8b8ec730 100644 --- a/net/netfilter/Makefile +++ b/net/netfilter/Makefile @@ -70,7 +70,7 @@ obj-$(CONFIG_NETFILTER_SYNPROXY) += nf_synproxy_core.o # nf_tables nf_tables-objs += nf_tables_core.o nf_tables_api.o -nf_tables-objs += nft_immediate.o nft_cmp.o nft_lookup.o +nf_tables-objs += nft_immediate.o nft_cmp.o nft_lookup.o nft_dynset.o nf_tables-objs += nft_bitwise.o nft_byteorder.o nft_payload.o obj-$(CONFIG_NF_TABLES) += nf_tables.o diff --git a/net/netfilter/core.c b/net/netfilter/core.c index fea9ef566427..e6163017c42d 100644 --- a/net/netfilter/core.c +++ b/net/netfilter/core.c @@ -120,12 +120,8 @@ EXPORT_SYMBOL(nf_unregister_hooks); unsigned int nf_iterate(struct list_head *head, struct sk_buff *skb, - unsigned int hook, - const struct net_device *indev, - const struct net_device *outdev, - struct nf_hook_ops **elemp, - int (*okfn)(struct sk_buff *), - int hook_thresh) + struct nf_hook_state *state, + struct nf_hook_ops **elemp) { unsigned int verdict; @@ -134,19 +130,19 @@ unsigned int nf_iterate(struct list_head *head, * function because of risk of continuing from deleted element. */ list_for_each_entry_continue_rcu((*elemp), head, list) { - if (hook_thresh > (*elemp)->priority) + if (state->thresh > (*elemp)->priority) continue; /* Optimization: we don't need to hold module reference here, since function can't sleep. --RR */ repeat: - verdict = (*elemp)->hook(*elemp, skb, indev, outdev, okfn); + verdict = (*elemp)->hook(*elemp, skb, state); if (verdict != NF_ACCEPT) { #ifdef CONFIG_NETFILTER_DEBUG if (unlikely((verdict & NF_VERDICT_MASK) > NF_MAX_VERDICT)) { NFDEBUG("Evil return from %p(%u).\n", - (*elemp)->hook, hook); + (*elemp)->hook, state->hook); continue; } #endif @@ -161,11 +157,7 @@ repeat: /* Returns 1 if okfn() needs to be executed by the caller, * -EPERM for NF_DROP, 0 otherwise. */ -int nf_hook_slow(u_int8_t pf, unsigned int hook, struct sk_buff *skb, - struct net_device *indev, - struct net_device *outdev, - int (*okfn)(struct sk_buff *), - int hook_thresh) +int nf_hook_slow(struct sk_buff *skb, struct nf_hook_state *state) { struct nf_hook_ops *elem; unsigned int verdict; @@ -174,10 +166,11 @@ int nf_hook_slow(u_int8_t pf, unsigned int hook, struct sk_buff *skb, /* We may already have this, but read-locks nest anyway */ rcu_read_lock(); - elem = list_entry_rcu(&nf_hooks[pf][hook], struct nf_hook_ops, list); + elem = list_entry_rcu(&nf_hooks[state->pf][state->hook], + struct nf_hook_ops, list); next_hook: - verdict = nf_iterate(&nf_hooks[pf][hook], skb, hook, indev, - outdev, &elem, okfn, hook_thresh); + verdict = nf_iterate(&nf_hooks[state->pf][state->hook], skb, state, + &elem); if (verdict == NF_ACCEPT || verdict == NF_STOP) { ret = 1; } else if ((verdict & NF_VERDICT_MASK) == NF_DROP) { @@ -186,8 +179,8 @@ next_hook: if (ret == 0) ret = -EPERM; } else if ((verdict & NF_VERDICT_MASK) == NF_QUEUE) { - int err = nf_queue(skb, elem, pf, hook, indev, outdev, okfn, - verdict >> NF_VERDICT_QBITS); + int err = nf_queue(skb, elem, state, + verdict >> NF_VERDICT_QBITS); if (err < 0) { if (err == -ECANCELED) goto next_hook; diff --git a/net/netfilter/ipset/ip_set_hash_netiface.c b/net/netfilter/ipset/ip_set_hash_netiface.c index 758b002130d9..380ef5148ea1 100644 --- a/net/netfilter/ipset/ip_set_hash_netiface.c +++ b/net/netfilter/ipset/ip_set_hash_netiface.c @@ -19,6 +19,7 @@ #include <net/netlink.h> #include <linux/netfilter.h> +#include <linux/netfilter_bridge.h> #include <linux/netfilter/ipset/pfxlen.h> #include <linux/netfilter/ipset/ip_set.h> #include <linux/netfilter/ipset/ip_set_hash.h> @@ -211,6 +212,22 @@ hash_netiface4_data_next(struct hash_netiface4_elem *next, #define HKEY_DATALEN sizeof(struct hash_netiface4_elem_hashed) #include "ip_set_hash_gen.h" +#if IS_ENABLED(CONFIG_BRIDGE_NETFILTER) +static const char *get_physindev_name(const struct sk_buff *skb) +{ + struct net_device *dev = nf_bridge_get_physindev(skb); + + return dev ? dev->name : NULL; +} + +static const char *get_phyoutdev_name(const struct sk_buff *skb) +{ + struct net_device *dev = nf_bridge_get_physoutdev(skb); + + return dev ? dev->name : NULL; +} +#endif + static int hash_netiface4_kadt(struct ip_set *set, const struct sk_buff *skb, const struct xt_action_param *par, @@ -234,16 +251,15 @@ hash_netiface4_kadt(struct ip_set *set, const struct sk_buff *skb, e.ip &= ip_set_netmask(e.cidr); #define IFACE(dir) (par->dir ? par->dir->name : NULL) -#define PHYSDEV(dir) (nf_bridge->dir ? nf_bridge->dir->name : NULL) #define SRCDIR (opt->flags & IPSET_DIM_TWO_SRC) if (opt->cmdflags & IPSET_FLAG_PHYSDEV) { #if IS_ENABLED(CONFIG_BRIDGE_NETFILTER) - const struct nf_bridge_info *nf_bridge = skb->nf_bridge; + e.iface = SRCDIR ? get_physindev_name(skb) : + get_phyoutdev_name(skb); - if (!nf_bridge) + if (!e.iface) return -EINVAL; - e.iface = SRCDIR ? PHYSDEV(physindev) : PHYSDEV(physoutdev); e.physdev = 1; #else e.iface = NULL; @@ -476,11 +492,11 @@ hash_netiface6_kadt(struct ip_set *set, const struct sk_buff *skb, if (opt->cmdflags & IPSET_FLAG_PHYSDEV) { #if IS_ENABLED(CONFIG_BRIDGE_NETFILTER) - const struct nf_bridge_info *nf_bridge = skb->nf_bridge; - - if (!nf_bridge) + e.iface = SRCDIR ? get_physindev_name(skb) : + get_phyoutdev_name(skb); + if (!e.iface) return -EINVAL; - e.iface = SRCDIR ? PHYSDEV(physindev) : PHYSDEV(physoutdev); + e.physdev = 1; #else e.iface = NULL; diff --git a/net/netfilter/ipvs/ip_vs_core.c b/net/netfilter/ipvs/ip_vs_core.c index b87ca32efa0b..5d2b806a862e 100644 --- a/net/netfilter/ipvs/ip_vs_core.c +++ b/net/netfilter/ipvs/ip_vs_core.c @@ -119,24 +119,24 @@ ip_vs_in_stats(struct ip_vs_conn *cp, struct sk_buff *skb) struct ip_vs_service *svc; s = this_cpu_ptr(dest->stats.cpustats); - s->ustats.inpkts++; u64_stats_update_begin(&s->syncp); - s->ustats.inbytes += skb->len; + s->cnt.inpkts++; + s->cnt.inbytes += skb->len; u64_stats_update_end(&s->syncp); rcu_read_lock(); svc = rcu_dereference(dest->svc); s = this_cpu_ptr(svc->stats.cpustats); - s->ustats.inpkts++; u64_stats_update_begin(&s->syncp); - s->ustats.inbytes += skb->len; + s->cnt.inpkts++; + s->cnt.inbytes += skb->len; u64_stats_update_end(&s->syncp); rcu_read_unlock(); s = this_cpu_ptr(ipvs->tot_stats.cpustats); - s->ustats.inpkts++; u64_stats_update_begin(&s->syncp); - s->ustats.inbytes += skb->len; + s->cnt.inpkts++; + s->cnt.inbytes += skb->len; u64_stats_update_end(&s->syncp); } } @@ -153,24 +153,24 @@ ip_vs_out_stats(struct ip_vs_conn *cp, struct sk_buff *skb) struct ip_vs_service *svc; s = this_cpu_ptr(dest->stats.cpustats); - s->ustats.outpkts++; u64_stats_update_begin(&s->syncp); - s->ustats.outbytes += skb->len; + s->cnt.outpkts++; + s->cnt.outbytes += skb->len; u64_stats_update_end(&s->syncp); rcu_read_lock(); svc = rcu_dereference(dest->svc); s = this_cpu_ptr(svc->stats.cpustats); - s->ustats.outpkts++; u64_stats_update_begin(&s->syncp); - s->ustats.outbytes += skb->len; + s->cnt.outpkts++; + s->cnt.outbytes += skb->len; u64_stats_update_end(&s->syncp); rcu_read_unlock(); s = this_cpu_ptr(ipvs->tot_stats.cpustats); - s->ustats.outpkts++; u64_stats_update_begin(&s->syncp); - s->ustats.outbytes += skb->len; + s->cnt.outpkts++; + s->cnt.outbytes += skb->len; u64_stats_update_end(&s->syncp); } } @@ -183,13 +183,19 @@ ip_vs_conn_stats(struct ip_vs_conn *cp, struct ip_vs_service *svc) struct ip_vs_cpu_stats *s; s = this_cpu_ptr(cp->dest->stats.cpustats); - s->ustats.conns++; + u64_stats_update_begin(&s->syncp); + s->cnt.conns++; + u64_stats_update_end(&s->syncp); s = this_cpu_ptr(svc->stats.cpustats); - s->ustats.conns++; + u64_stats_update_begin(&s->syncp); + s->cnt.conns++; + u64_stats_update_end(&s->syncp); s = this_cpu_ptr(ipvs->tot_stats.cpustats); - s->ustats.conns++; + u64_stats_update_begin(&s->syncp); + s->cnt.conns++; + u64_stats_update_end(&s->syncp); } @@ -1046,6 +1052,26 @@ static inline bool is_new_conn(const struct sk_buff *skb, } } +static inline bool is_new_conn_expected(const struct ip_vs_conn *cp, + int conn_reuse_mode) +{ + /* Controlled (FTP DATA or persistence)? */ + if (cp->control) + return false; + + switch (cp->protocol) { + case IPPROTO_TCP: + return (cp->state == IP_VS_TCP_S_TIME_WAIT) || + ((conn_reuse_mode & 2) && + (cp->state == IP_VS_TCP_S_FIN_WAIT) && + (cp->flags & IP_VS_CONN_F_NOOUTPUT)); + case IPPROTO_SCTP: + return cp->state == IP_VS_SCTP_S_CLOSED; + default: + return false; + } +} + /* Handle response packets: rewrite addresses and send away... */ static unsigned int @@ -1246,8 +1272,7 @@ ip_vs_out(unsigned int hooknum, struct sk_buff *skb, int af) */ static unsigned int ip_vs_reply4(const struct nf_hook_ops *ops, struct sk_buff *skb, - const struct net_device *in, const struct net_device *out, - int (*okfn)(struct sk_buff *)) + const struct nf_hook_state *state) { return ip_vs_out(ops->hooknum, skb, AF_INET); } @@ -1258,8 +1283,7 @@ ip_vs_reply4(const struct nf_hook_ops *ops, struct sk_buff *skb, */ static unsigned int ip_vs_local_reply4(const struct nf_hook_ops *ops, struct sk_buff *skb, - const struct net_device *in, const struct net_device *out, - int (*okfn)(struct sk_buff *)) + const struct nf_hook_state *state) { return ip_vs_out(ops->hooknum, skb, AF_INET); } @@ -1273,8 +1297,7 @@ ip_vs_local_reply4(const struct nf_hook_ops *ops, struct sk_buff *skb, */ static unsigned int ip_vs_reply6(const struct nf_hook_ops *ops, struct sk_buff *skb, - const struct net_device *in, const struct net_device *out, - int (*okfn)(struct sk_buff *)) + const struct nf_hook_state *state) { return ip_vs_out(ops->hooknum, skb, AF_INET6); } @@ -1285,8 +1308,7 @@ ip_vs_reply6(const struct nf_hook_ops *ops, struct sk_buff *skb, */ static unsigned int ip_vs_local_reply6(const struct nf_hook_ops *ops, struct sk_buff *skb, - const struct net_device *in, const struct net_device *out, - int (*okfn)(struct sk_buff *)) + const struct nf_hook_state *state) { return ip_vs_out(ops->hooknum, skb, AF_INET6); } @@ -1585,6 +1607,7 @@ ip_vs_in(unsigned int hooknum, struct sk_buff *skb, int af) struct ip_vs_conn *cp; int ret, pkts; struct netns_ipvs *ipvs; + int conn_reuse_mode; /* Already marked as IPVS request or reply? */ if (skb->ipvs_property) @@ -1653,10 +1676,14 @@ ip_vs_in(unsigned int hooknum, struct sk_buff *skb, int af) */ cp = pp->conn_in_get(af, skb, &iph, 0); - if (unlikely(sysctl_expire_nodest_conn(ipvs)) && cp && cp->dest && - unlikely(!atomic_read(&cp->dest->weight)) && !iph.fragoffs && - is_new_conn(skb, &iph)) { - ip_vs_conn_expire_now(cp); + conn_reuse_mode = sysctl_conn_reuse_mode(ipvs); + if (conn_reuse_mode && !iph.fragoffs && + is_new_conn(skb, &iph) && cp && + ((unlikely(sysctl_expire_nodest_conn(ipvs)) && cp->dest && + unlikely(!atomic_read(&cp->dest->weight))) || + unlikely(is_new_conn_expected(cp, conn_reuse_mode)))) { + if (!atomic_read(&cp->n_control)) + ip_vs_conn_expire_now(cp); __ip_vs_conn_put(cp); cp = NULL; } @@ -1738,9 +1765,7 @@ ip_vs_in(unsigned int hooknum, struct sk_buff *skb, int af) */ static unsigned int ip_vs_remote_request4(const struct nf_hook_ops *ops, struct sk_buff *skb, - const struct net_device *in, - const struct net_device *out, - int (*okfn)(struct sk_buff *)) + const struct nf_hook_state *state) { return ip_vs_in(ops->hooknum, skb, AF_INET); } @@ -1751,8 +1776,7 @@ ip_vs_remote_request4(const struct nf_hook_ops *ops, struct sk_buff *skb, */ static unsigned int ip_vs_local_request4(const struct nf_hook_ops *ops, struct sk_buff *skb, - const struct net_device *in, const struct net_device *out, - int (*okfn)(struct sk_buff *)) + const struct nf_hook_state *state) { return ip_vs_in(ops->hooknum, skb, AF_INET); } @@ -1765,9 +1789,7 @@ ip_vs_local_request4(const struct nf_hook_ops *ops, struct sk_buff *skb, */ static unsigned int ip_vs_remote_request6(const struct nf_hook_ops *ops, struct sk_buff *skb, - const struct net_device *in, - const struct net_device *out, - int (*okfn)(struct sk_buff *)) + const struct nf_hook_state *state) { return ip_vs_in(ops->hooknum, skb, AF_INET6); } @@ -1778,8 +1800,7 @@ ip_vs_remote_request6(const struct nf_hook_ops *ops, struct sk_buff *skb, */ static unsigned int ip_vs_local_request6(const struct nf_hook_ops *ops, struct sk_buff *skb, - const struct net_device *in, const struct net_device *out, - int (*okfn)(struct sk_buff *)) + const struct nf_hook_state *state) { return ip_vs_in(ops->hooknum, skb, AF_INET6); } @@ -1798,8 +1819,7 @@ ip_vs_local_request6(const struct nf_hook_ops *ops, struct sk_buff *skb, */ static unsigned int ip_vs_forward_icmp(const struct nf_hook_ops *ops, struct sk_buff *skb, - const struct net_device *in, const struct net_device *out, - int (*okfn)(struct sk_buff *)) + const struct nf_hook_state *state) { int r; struct net *net; @@ -1820,8 +1840,7 @@ ip_vs_forward_icmp(const struct nf_hook_ops *ops, struct sk_buff *skb, #ifdef CONFIG_IP_VS_IPV6 static unsigned int ip_vs_forward_icmp_v6(const struct nf_hook_ops *ops, struct sk_buff *skb, - const struct net_device *in, const struct net_device *out, - int (*okfn)(struct sk_buff *)) + const struct nf_hook_state *state) { int r; struct net *net; diff --git a/net/netfilter/ipvs/ip_vs_ctl.c b/net/netfilter/ipvs/ip_vs_ctl.c index ed99448671c3..49532672f66d 100644 --- a/net/netfilter/ipvs/ip_vs_ctl.c +++ b/net/netfilter/ipvs/ip_vs_ctl.c @@ -729,9 +729,9 @@ static void ip_vs_trash_cleanup(struct net *net) } static void -ip_vs_copy_stats(struct ip_vs_stats_user *dst, struct ip_vs_stats *src) +ip_vs_copy_stats(struct ip_vs_kstats *dst, struct ip_vs_stats *src) { -#define IP_VS_SHOW_STATS_COUNTER(c) dst->c = src->ustats.c - src->ustats0.c +#define IP_VS_SHOW_STATS_COUNTER(c) dst->c = src->kstats.c - src->kstats0.c spin_lock_bh(&src->lock); @@ -747,13 +747,28 @@ ip_vs_copy_stats(struct ip_vs_stats_user *dst, struct ip_vs_stats *src) } static void +ip_vs_export_stats_user(struct ip_vs_stats_user *dst, struct ip_vs_kstats *src) +{ + dst->conns = (u32)src->conns; + dst->inpkts = (u32)src->inpkts; + dst->outpkts = (u32)src->outpkts; + dst->inbytes = src->inbytes; + dst->outbytes = src->outbytes; + dst->cps = (u32)src->cps; + dst->inpps = (u32)src->inpps; + dst->outpps = (u32)src->outpps; + dst->inbps = (u32)src->inbps; + dst->outbps = (u32)src->outbps; +} + +static void ip_vs_zero_stats(struct ip_vs_stats *stats) { spin_lock_bh(&stats->lock); /* get current counters as zero point, rates are zeroed */ -#define IP_VS_ZERO_STATS_COUNTER(c) stats->ustats0.c = stats->ustats.c +#define IP_VS_ZERO_STATS_COUNTER(c) stats->kstats0.c = stats->kstats.c IP_VS_ZERO_STATS_COUNTER(conns); IP_VS_ZERO_STATS_COUNTER(inpkts); @@ -1808,6 +1823,12 @@ static struct ctl_table vs_vars[] = { .mode = 0644, .proc_handler = proc_dointvec, }, + { + .procname = "conn_reuse_mode", + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec, + }, #ifdef CONFIG_IP_VS_DEBUG { .procname = "debug_level", @@ -2044,7 +2065,7 @@ static const struct file_operations ip_vs_info_fops = { static int ip_vs_stats_show(struct seq_file *seq, void *v) { struct net *net = seq_file_single_net(seq); - struct ip_vs_stats_user show; + struct ip_vs_kstats show; /* 01234567 01234567 01234567 0123456701234567 0123456701234567 */ seq_puts(seq, @@ -2053,17 +2074,22 @@ static int ip_vs_stats_show(struct seq_file *seq, void *v) " Conns Packets Packets Bytes Bytes\n"); ip_vs_copy_stats(&show, &net_ipvs(net)->tot_stats); - seq_printf(seq, "%8X %8X %8X %16LX %16LX\n\n", show.conns, - show.inpkts, show.outpkts, - (unsigned long long) show.inbytes, - (unsigned long long) show.outbytes); - -/* 01234567 01234567 01234567 0123456701234567 0123456701234567 */ + seq_printf(seq, "%8LX %8LX %8LX %16LX %16LX\n\n", + (unsigned long long)show.conns, + (unsigned long long)show.inpkts, + (unsigned long long)show.outpkts, + (unsigned long long)show.inbytes, + (unsigned long long)show.outbytes); + +/* 01234567 01234567 01234567 0123456701234567 0123456701234567*/ seq_puts(seq, - " Conns/s Pkts/s Pkts/s Bytes/s Bytes/s\n"); - seq_printf(seq, "%8X %8X %8X %16X %16X\n", - show.cps, show.inpps, show.outpps, - show.inbps, show.outbps); + " Conns/s Pkts/s Pkts/s Bytes/s Bytes/s\n"); + seq_printf(seq, "%8LX %8LX %8LX %16LX %16LX\n", + (unsigned long long)show.cps, + (unsigned long long)show.inpps, + (unsigned long long)show.outpps, + (unsigned long long)show.inbps, + (unsigned long long)show.outbps); return 0; } @@ -2086,7 +2112,7 @@ static int ip_vs_stats_percpu_show(struct seq_file *seq, void *v) struct net *net = seq_file_single_net(seq); struct ip_vs_stats *tot_stats = &net_ipvs(net)->tot_stats; struct ip_vs_cpu_stats __percpu *cpustats = tot_stats->cpustats; - struct ip_vs_stats_user rates; + struct ip_vs_kstats kstats; int i; /* 01234567 01234567 01234567 0123456701234567 0123456701234567 */ @@ -2098,41 +2124,41 @@ static int ip_vs_stats_percpu_show(struct seq_file *seq, void *v) for_each_possible_cpu(i) { struct ip_vs_cpu_stats *u = per_cpu_ptr(cpustats, i); unsigned int start; - __u64 inbytes, outbytes; + u64 conns, inpkts, outpkts, inbytes, outbytes; do { start = u64_stats_fetch_begin_irq(&u->syncp); - inbytes = u->ustats.inbytes; - outbytes = u->ustats.outbytes; + conns = u->cnt.conns; + inpkts = u->cnt.inpkts; + outpkts = u->cnt.outpkts; + inbytes = u->cnt.inbytes; + outbytes = u->cnt.outbytes; } while (u64_stats_fetch_retry_irq(&u->syncp, start)); - seq_printf(seq, "%3X %8X %8X %8X %16LX %16LX\n", - i, u->ustats.conns, u->ustats.inpkts, - u->ustats.outpkts, (__u64)inbytes, - (__u64)outbytes); + seq_printf(seq, "%3X %8LX %8LX %8LX %16LX %16LX\n", + i, (u64)conns, (u64)inpkts, + (u64)outpkts, (u64)inbytes, + (u64)outbytes); } - spin_lock_bh(&tot_stats->lock); - - seq_printf(seq, " ~ %8X %8X %8X %16LX %16LX\n\n", - tot_stats->ustats.conns, tot_stats->ustats.inpkts, - tot_stats->ustats.outpkts, - (unsigned long long) tot_stats->ustats.inbytes, - (unsigned long long) tot_stats->ustats.outbytes); - - ip_vs_read_estimator(&rates, tot_stats); + ip_vs_copy_stats(&kstats, tot_stats); - spin_unlock_bh(&tot_stats->lock); + seq_printf(seq, " ~ %8LX %8LX %8LX %16LX %16LX\n\n", + (unsigned long long)kstats.conns, + (unsigned long long)kstats.inpkts, + (unsigned long long)kstats.outpkts, + (unsigned long long)kstats.inbytes, + (unsigned long long)kstats.outbytes); -/* 01234567 01234567 01234567 0123456701234567 0123456701234567 */ +/* ... 01234567 01234567 01234567 0123456701234567 0123456701234567 */ seq_puts(seq, - " Conns/s Pkts/s Pkts/s Bytes/s Bytes/s\n"); - seq_printf(seq, " %8X %8X %8X %16X %16X\n", - rates.cps, - rates.inpps, - rates.outpps, - rates.inbps, - rates.outbps); + " Conns/s Pkts/s Pkts/s Bytes/s Bytes/s\n"); + seq_printf(seq, " %8LX %8LX %8LX %16LX %16LX\n", + kstats.cps, + kstats.inpps, + kstats.outpps, + kstats.inbps, + kstats.outbps); return 0; } @@ -2400,6 +2426,7 @@ static void ip_vs_copy_service(struct ip_vs_service_entry *dst, struct ip_vs_service *src) { struct ip_vs_scheduler *sched; + struct ip_vs_kstats kstats; sched = rcu_dereference_protected(src->scheduler, 1); dst->protocol = src->protocol; @@ -2411,7 +2438,8 @@ ip_vs_copy_service(struct ip_vs_service_entry *dst, struct ip_vs_service *src) dst->timeout = src->timeout / HZ; dst->netmask = src->netmask; dst->num_dests = src->num_dests; - ip_vs_copy_stats(&dst->stats, &src->stats); + ip_vs_copy_stats(&kstats, &src->stats); + ip_vs_export_stats_user(&dst->stats, &kstats); } static inline int @@ -2485,6 +2513,7 @@ __ip_vs_get_dest_entries(struct net *net, const struct ip_vs_get_dests *get, int count = 0; struct ip_vs_dest *dest; struct ip_vs_dest_entry entry; + struct ip_vs_kstats kstats; memset(&entry, 0, sizeof(entry)); list_for_each_entry(dest, &svc->destinations, n_list) { @@ -2506,7 +2535,8 @@ __ip_vs_get_dest_entries(struct net *net, const struct ip_vs_get_dests *get, entry.activeconns = atomic_read(&dest->activeconns); entry.inactconns = atomic_read(&dest->inactconns); entry.persistconns = atomic_read(&dest->persistconns); - ip_vs_copy_stats(&entry.stats, &dest->stats); + ip_vs_copy_stats(&kstats, &dest->stats); + ip_vs_export_stats_user(&entry.stats, &kstats); if (copy_to_user(&uptr->entrytable[count], &entry, sizeof(entry))) { ret = -EFAULT; @@ -2798,25 +2828,51 @@ static const struct nla_policy ip_vs_dest_policy[IPVS_DEST_ATTR_MAX + 1] = { }; static int ip_vs_genl_fill_stats(struct sk_buff *skb, int container_type, - struct ip_vs_stats *stats) + struct ip_vs_kstats *kstats) { - struct ip_vs_stats_user ustats; struct nlattr *nl_stats = nla_nest_start(skb, container_type); + if (!nl_stats) return -EMSGSIZE; - ip_vs_copy_stats(&ustats, stats); - - if (nla_put_u32(skb, IPVS_STATS_ATTR_CONNS, ustats.conns) || - nla_put_u32(skb, IPVS_STATS_ATTR_INPKTS, ustats.inpkts) || - nla_put_u32(skb, IPVS_STATS_ATTR_OUTPKTS, ustats.outpkts) || - nla_put_u64(skb, IPVS_STATS_ATTR_INBYTES, ustats.inbytes) || - nla_put_u64(skb, IPVS_STATS_ATTR_OUTBYTES, ustats.outbytes) || - nla_put_u32(skb, IPVS_STATS_ATTR_CPS, ustats.cps) || - nla_put_u32(skb, IPVS_STATS_ATTR_INPPS, ustats.inpps) || - nla_put_u32(skb, IPVS_STATS_ATTR_OUTPPS, ustats.outpps) || - nla_put_u32(skb, IPVS_STATS_ATTR_INBPS, ustats.inbps) || - nla_put_u32(skb, IPVS_STATS_ATTR_OUTBPS, ustats.outbps)) + if (nla_put_u32(skb, IPVS_STATS_ATTR_CONNS, (u32)kstats->conns) || + nla_put_u32(skb, IPVS_STATS_ATTR_INPKTS, (u32)kstats->inpkts) || + nla_put_u32(skb, IPVS_STATS_ATTR_OUTPKTS, (u32)kstats->outpkts) || + nla_put_u64(skb, IPVS_STATS_ATTR_INBYTES, kstats->inbytes) || + nla_put_u64(skb, IPVS_STATS_ATTR_OUTBYTES, kstats->outbytes) || + nla_put_u32(skb, IPVS_STATS_ATTR_CPS, (u32)kstats->cps) || + nla_put_u32(skb, IPVS_STATS_ATTR_INPPS, (u32)kstats->inpps) || + nla_put_u32(skb, IPVS_STATS_ATTR_OUTPPS, (u32)kstats->outpps) || + nla_put_u32(skb, IPVS_STATS_ATTR_INBPS, (u32)kstats->inbps) || + nla_put_u32(skb, IPVS_STATS_ATTR_OUTBPS, (u32)kstats->outbps)) + goto nla_put_failure; + nla_nest_end(skb, nl_stats); + + return 0; + +nla_put_failure: + nla_nest_cancel(skb, nl_stats); + return -EMSGSIZE; +} + +static int ip_vs_genl_fill_stats64(struct sk_buff *skb, int container_type, + struct ip_vs_kstats *kstats) +{ + struct nlattr *nl_stats = nla_nest_start(skb, container_type); + + if (!nl_stats) + return -EMSGSIZE; + + if (nla_put_u64(skb, IPVS_STATS_ATTR_CONNS, kstats->conns) || + nla_put_u64(skb, IPVS_STATS_ATTR_INPKTS, kstats->inpkts) || + nla_put_u64(skb, IPVS_STATS_ATTR_OUTPKTS, kstats->outpkts) || + nla_put_u64(skb, IPVS_STATS_ATTR_INBYTES, kstats->inbytes) || + nla_put_u64(skb, IPVS_STATS_ATTR_OUTBYTES, kstats->outbytes) || + nla_put_u64(skb, IPVS_STATS_ATTR_CPS, kstats->cps) || + nla_put_u64(skb, IPVS_STATS_ATTR_INPPS, kstats->inpps) || + nla_put_u64(skb, IPVS_STATS_ATTR_OUTPPS, kstats->outpps) || + nla_put_u64(skb, IPVS_STATS_ATTR_INBPS, kstats->inbps) || + nla_put_u64(skb, IPVS_STATS_ATTR_OUTBPS, kstats->outbps)) goto nla_put_failure; nla_nest_end(skb, nl_stats); @@ -2835,6 +2891,7 @@ static int ip_vs_genl_fill_service(struct sk_buff *skb, struct nlattr *nl_service; struct ip_vs_flags flags = { .flags = svc->flags, .mask = ~0 }; + struct ip_vs_kstats kstats; nl_service = nla_nest_start(skb, IPVS_CMD_ATTR_SERVICE); if (!nl_service) @@ -2860,7 +2917,10 @@ static int ip_vs_genl_fill_service(struct sk_buff *skb, nla_put_u32(skb, IPVS_SVC_ATTR_TIMEOUT, svc->timeout / HZ) || nla_put_be32(skb, IPVS_SVC_ATTR_NETMASK, svc->netmask)) goto nla_put_failure; - if (ip_vs_genl_fill_stats(skb, IPVS_SVC_ATTR_STATS, &svc->stats)) + ip_vs_copy_stats(&kstats, &svc->stats); + if (ip_vs_genl_fill_stats(skb, IPVS_SVC_ATTR_STATS, &kstats)) + goto nla_put_failure; + if (ip_vs_genl_fill_stats64(skb, IPVS_SVC_ATTR_STATS64, &kstats)) goto nla_put_failure; nla_nest_end(skb, nl_service); @@ -3032,6 +3092,7 @@ static struct ip_vs_service *ip_vs_genl_find_service(struct net *net, static int ip_vs_genl_fill_dest(struct sk_buff *skb, struct ip_vs_dest *dest) { struct nlattr *nl_dest; + struct ip_vs_kstats kstats; nl_dest = nla_nest_start(skb, IPVS_CMD_ATTR_DEST); if (!nl_dest) @@ -3054,7 +3115,10 @@ static int ip_vs_genl_fill_dest(struct sk_buff *skb, struct ip_vs_dest *dest) atomic_read(&dest->persistconns)) || nla_put_u16(skb, IPVS_DEST_ATTR_ADDR_FAMILY, dest->af)) goto nla_put_failure; - if (ip_vs_genl_fill_stats(skb, IPVS_DEST_ATTR_STATS, &dest->stats)) + ip_vs_copy_stats(&kstats, &dest->stats); + if (ip_vs_genl_fill_stats(skb, IPVS_DEST_ATTR_STATS, &kstats)) + goto nla_put_failure; + if (ip_vs_genl_fill_stats64(skb, IPVS_DEST_ATTR_STATS64, &kstats)) goto nla_put_failure; nla_nest_end(skb, nl_dest); @@ -3732,6 +3796,8 @@ static int __net_init ip_vs_control_net_init_sysctl(struct net *net) ipvs->sysctl_pmtu_disc = 1; tbl[idx++].data = &ipvs->sysctl_pmtu_disc; tbl[idx++].data = &ipvs->sysctl_backup_only; + ipvs->sysctl_conn_reuse_mode = 1; + tbl[idx++].data = &ipvs->sysctl_conn_reuse_mode; ipvs->sysctl_hdr = register_net_sysctl(net, "net/ipv4/vs", tbl); diff --git a/net/netfilter/ipvs/ip_vs_est.c b/net/netfilter/ipvs/ip_vs_est.c index 1425e9a924c4..ef0eb0a8d552 100644 --- a/net/netfilter/ipvs/ip_vs_est.c +++ b/net/netfilter/ipvs/ip_vs_est.c @@ -45,17 +45,19 @@ NOTES. - * The stored value for average bps is scaled by 2^5, so that maximal - rate is ~2.15Gbits/s, average pps and cps are scaled by 2^10. + * Average bps is scaled by 2^5, while average pps and cps are scaled by 2^10. - * A lot code is taken from net/sched/estimator.c + * Netlink users can see 64-bit values but sockopt users are restricted + to 32-bit values for conns, packets, bps, cps and pps. + + * A lot of code is taken from net/core/gen_estimator.c */ /* * Make a summary from each cpu */ -static void ip_vs_read_cpu_stats(struct ip_vs_stats_user *sum, +static void ip_vs_read_cpu_stats(struct ip_vs_kstats *sum, struct ip_vs_cpu_stats __percpu *stats) { int i; @@ -64,27 +66,31 @@ static void ip_vs_read_cpu_stats(struct ip_vs_stats_user *sum, for_each_possible_cpu(i) { struct ip_vs_cpu_stats *s = per_cpu_ptr(stats, i); unsigned int start; - __u64 inbytes, outbytes; + u64 conns, inpkts, outpkts, inbytes, outbytes; + if (add) { - sum->conns += s->ustats.conns; - sum->inpkts += s->ustats.inpkts; - sum->outpkts += s->ustats.outpkts; do { start = u64_stats_fetch_begin(&s->syncp); - inbytes = s->ustats.inbytes; - outbytes = s->ustats.outbytes; + conns = s->cnt.conns; + inpkts = s->cnt.inpkts; + outpkts = s->cnt.outpkts; + inbytes = s->cnt.inbytes; + outbytes = s->cnt.outbytes; } while (u64_stats_fetch_retry(&s->syncp, start)); + sum->conns += conns; + sum->inpkts += inpkts; + sum->outpkts += outpkts; sum->inbytes += inbytes; sum->outbytes += outbytes; } else { add = true; - sum->conns = s->ustats.conns; - sum->inpkts = s->ustats.inpkts; - sum->outpkts = s->ustats.outpkts; do { start = u64_stats_fetch_begin(&s->syncp); - sum->inbytes = s->ustats.inbytes; - sum->outbytes = s->ustats.outbytes; + sum->conns = s->cnt.conns; + sum->inpkts = s->cnt.inpkts; + sum->outpkts = s->cnt.outpkts; + sum->inbytes = s->cnt.inbytes; + sum->outbytes = s->cnt.outbytes; } while (u64_stats_fetch_retry(&s->syncp, start)); } } @@ -95,10 +101,7 @@ static void estimation_timer(unsigned long arg) { struct ip_vs_estimator *e; struct ip_vs_stats *s; - u32 n_conns; - u32 n_inpkts, n_outpkts; - u64 n_inbytes, n_outbytes; - u32 rate; + u64 rate; struct net *net = (struct net *)arg; struct netns_ipvs *ipvs; @@ -108,33 +111,29 @@ static void estimation_timer(unsigned long arg) s = container_of(e, struct ip_vs_stats, est); spin_lock(&s->lock); - ip_vs_read_cpu_stats(&s->ustats, s->cpustats); - n_conns = s->ustats.conns; - n_inpkts = s->ustats.inpkts; - n_outpkts = s->ustats.outpkts; - n_inbytes = s->ustats.inbytes; - n_outbytes = s->ustats.outbytes; + ip_vs_read_cpu_stats(&s->kstats, s->cpustats); /* scaled by 2^10, but divided 2 seconds */ - rate = (n_conns - e->last_conns) << 9; - e->last_conns = n_conns; - e->cps += ((long)rate - (long)e->cps) >> 2; - - rate = (n_inpkts - e->last_inpkts) << 9; - e->last_inpkts = n_inpkts; - e->inpps += ((long)rate - (long)e->inpps) >> 2; - - rate = (n_outpkts - e->last_outpkts) << 9; - e->last_outpkts = n_outpkts; - e->outpps += ((long)rate - (long)e->outpps) >> 2; - - rate = (n_inbytes - e->last_inbytes) << 4; - e->last_inbytes = n_inbytes; - e->inbps += ((long)rate - (long)e->inbps) >> 2; - - rate = (n_outbytes - e->last_outbytes) << 4; - e->last_outbytes = n_outbytes; - e->outbps += ((long)rate - (long)e->outbps) >> 2; + rate = (s->kstats.conns - e->last_conns) << 9; + e->last_conns = s->kstats.conns; + e->cps += ((s64)rate - (s64)e->cps) >> 2; + + rate = (s->kstats.inpkts - e->last_inpkts) << 9; + e->last_inpkts = s->kstats.inpkts; + e->inpps += ((s64)rate - (s64)e->inpps) >> 2; + + rate = (s->kstats.outpkts - e->last_outpkts) << 9; + e->last_outpkts = s->kstats.outpkts; + e->outpps += ((s64)rate - (s64)e->outpps) >> 2; + + /* scaled by 2^5, but divided 2 seconds */ + rate = (s->kstats.inbytes - e->last_inbytes) << 4; + e->last_inbytes = s->kstats.inbytes; + e->inbps += ((s64)rate - (s64)e->inbps) >> 2; + + rate = (s->kstats.outbytes - e->last_outbytes) << 4; + e->last_outbytes = s->kstats.outbytes; + e->outbps += ((s64)rate - (s64)e->outbps) >> 2; spin_unlock(&s->lock); } spin_unlock(&ipvs->est_lock); @@ -166,14 +165,14 @@ void ip_vs_stop_estimator(struct net *net, struct ip_vs_stats *stats) void ip_vs_zero_estimator(struct ip_vs_stats *stats) { struct ip_vs_estimator *est = &stats->est; - struct ip_vs_stats_user *u = &stats->ustats; + struct ip_vs_kstats *k = &stats->kstats; /* reset counters, caller must hold the stats->lock lock */ - est->last_inbytes = u->inbytes; - est->last_outbytes = u->outbytes; - est->last_conns = u->conns; - est->last_inpkts = u->inpkts; - est->last_outpkts = u->outpkts; + est->last_inbytes = k->inbytes; + est->last_outbytes = k->outbytes; + est->last_conns = k->conns; + est->last_inpkts = k->inpkts; + est->last_outpkts = k->outpkts; est->cps = 0; est->inpps = 0; est->outpps = 0; @@ -182,8 +181,7 @@ void ip_vs_zero_estimator(struct ip_vs_stats *stats) } /* Get decoded rates */ -void ip_vs_read_estimator(struct ip_vs_stats_user *dst, - struct ip_vs_stats *stats) +void ip_vs_read_estimator(struct ip_vs_kstats *dst, struct ip_vs_stats *stats) { struct ip_vs_estimator *e = &stats->est; diff --git a/net/netfilter/ipvs/ip_vs_sync.c b/net/netfilter/ipvs/ip_vs_sync.c index d93ceeb3ef04..19b9cce6c210 100644 --- a/net/netfilter/ipvs/ip_vs_sync.c +++ b/net/netfilter/ipvs/ip_vs_sync.c @@ -845,10 +845,27 @@ static void ip_vs_proc_conn(struct net *net, struct ip_vs_conn_param *param, struct ip_vs_conn *cp; struct netns_ipvs *ipvs = net_ipvs(net); - if (!(flags & IP_VS_CONN_F_TEMPLATE)) + if (!(flags & IP_VS_CONN_F_TEMPLATE)) { cp = ip_vs_conn_in_get(param); - else + if (cp && ((cp->dport != dport) || + !ip_vs_addr_equal(cp->daf, &cp->daddr, daddr))) { + if (!(flags & IP_VS_CONN_F_INACTIVE)) { + ip_vs_conn_expire_now(cp); + __ip_vs_conn_put(cp); + cp = NULL; + } else { + /* This is the expiration message for the + * connection that was already replaced, so we + * just ignore it. + */ + __ip_vs_conn_put(cp); + kfree(param->pe_data); + return; + } + } + } else { cp = ip_vs_ct_in_get(param); + } if (cp) { /* Free pe_data */ @@ -1388,9 +1405,11 @@ join_mcast_group(struct sock *sk, struct in_addr *addr, char *ifname) mreq.imr_ifindex = dev->ifindex; + rtnl_lock(); lock_sock(sk); ret = ip_mc_join_group(sk, &mreq); release_sock(sk); + rtnl_unlock(); return ret; } diff --git a/net/netfilter/ipvs/ip_vs_xmit.c b/net/netfilter/ipvs/ip_vs_xmit.c index 3aedbda7658a..19986ec5f21a 100644 --- a/net/netfilter/ipvs/ip_vs_xmit.c +++ b/net/netfilter/ipvs/ip_vs_xmit.c @@ -209,7 +209,7 @@ static inline void maybe_update_pmtu(int skb_af, struct sk_buff *skb, int mtu) struct sock *sk = skb->sk; struct rtable *ort = skb_rtable(skb); - if (!skb->dev && sk && sk->sk_state != TCP_TIME_WAIT) + if (!skb->dev && sk && sk_fullsock(sk)) ort->dst.ops->update_pmtu(&ort->dst, sk, NULL, mtu); } @@ -536,8 +536,8 @@ static inline int ip_vs_nat_send_or_cont(int pf, struct sk_buff *skb, ip_vs_update_conntrack(skb, cp, 1); if (!local) { skb_forward_csum(skb); - NF_HOOK(pf, NF_INET_LOCAL_OUT, skb, NULL, skb_dst(skb)->dev, - dst_output); + NF_HOOK(pf, NF_INET_LOCAL_OUT, NULL, skb, + NULL, skb_dst(skb)->dev, dst_output_sk); } else ret = NF_ACCEPT; return ret; @@ -554,8 +554,8 @@ static inline int ip_vs_send_or_cont(int pf, struct sk_buff *skb, ip_vs_notrack(skb); if (!local) { skb_forward_csum(skb); - NF_HOOK(pf, NF_INET_LOCAL_OUT, skb, NULL, skb_dst(skb)->dev, - dst_output); + NF_HOOK(pf, NF_INET_LOCAL_OUT, NULL, skb, + NULL, skb_dst(skb)->dev, dst_output_sk); } else ret = NF_ACCEPT; return ret; @@ -924,7 +924,8 @@ int ip_vs_tunnel_xmit(struct sk_buff *skb, struct ip_vs_conn *cp, struct ip_vs_protocol *pp, struct ip_vs_iphdr *ipvsh) { - struct netns_ipvs *ipvs = net_ipvs(skb_net(skb)); + struct net *net = skb_net(skb); + struct netns_ipvs *ipvs = net_ipvs(net); struct rtable *rt; /* Route to the other host */ __be32 saddr; /* Source for tunnel */ struct net_device *tdev; /* Device to other host */ @@ -991,7 +992,7 @@ ip_vs_tunnel_xmit(struct sk_buff *skb, struct ip_vs_conn *cp, iph->daddr = cp->daddr.ip; iph->saddr = saddr; iph->ttl = ttl; - ip_select_ident(skb, NULL); + ip_select_ident(net, skb, NULL); /* Another hack: avoid icmp_send in ip_fragment */ skb->ignore_df = 1; diff --git a/net/netfilter/nf_conntrack_acct.c b/net/netfilter/nf_conntrack_acct.c index a4b5e2a435ac..45da11afa785 100644 --- a/net/netfilter/nf_conntrack_acct.c +++ b/net/netfilter/nf_conntrack_acct.c @@ -47,9 +47,11 @@ seq_print_acct(struct seq_file *s, const struct nf_conn *ct, int dir) return 0; counter = acct->counter; - return seq_printf(s, "packets=%llu bytes=%llu ", - (unsigned long long)atomic64_read(&counter[dir].packets), - (unsigned long long)atomic64_read(&counter[dir].bytes)); + seq_printf(s, "packets=%llu bytes=%llu ", + (unsigned long long)atomic64_read(&counter[dir].packets), + (unsigned long long)atomic64_read(&counter[dir].bytes)); + + return 0; }; EXPORT_SYMBOL_GPL(seq_print_acct); diff --git a/net/netfilter/nf_conntrack_amanda.c b/net/netfilter/nf_conntrack_amanda.c index b8b95f4027ca..57a26cc90c9f 100644 --- a/net/netfilter/nf_conntrack_amanda.c +++ b/net/netfilter/nf_conntrack_amanda.c @@ -88,7 +88,6 @@ static int amanda_help(struct sk_buff *skb, struct nf_conn *ct, enum ip_conntrack_info ctinfo) { - struct ts_state ts; struct nf_conntrack_expect *exp; struct nf_conntrack_tuple *tuple; unsigned int dataoff, start, stop, off, i; @@ -113,23 +112,20 @@ static int amanda_help(struct sk_buff *skb, return NF_ACCEPT; } - memset(&ts, 0, sizeof(ts)); start = skb_find_text(skb, dataoff, skb->len, - search[SEARCH_CONNECT].ts, &ts); + search[SEARCH_CONNECT].ts); if (start == UINT_MAX) goto out; start += dataoff + search[SEARCH_CONNECT].len; - memset(&ts, 0, sizeof(ts)); stop = skb_find_text(skb, start, skb->len, - search[SEARCH_NEWLINE].ts, &ts); + search[SEARCH_NEWLINE].ts); if (stop == UINT_MAX) goto out; stop += start; for (i = SEARCH_DATA; i <= SEARCH_INDEX; i++) { - memset(&ts, 0, sizeof(ts)); - off = skb_find_text(skb, start, stop, search[i].ts, &ts); + off = skb_find_text(skb, start, stop, search[i].ts); if (off == UINT_MAX) continue; off += start + search[i].len; diff --git a/net/netfilter/nf_conntrack_expect.c b/net/netfilter/nf_conntrack_expect.c index 91a1837acd0e..7a17070c5dab 100644 --- a/net/netfilter/nf_conntrack_expect.c +++ b/net/netfilter/nf_conntrack_expect.c @@ -561,7 +561,9 @@ static int exp_seq_show(struct seq_file *s, void *v) helper->expect_policy[expect->class].name); } - return seq_putc(s, '\n'); + seq_putc(s, '\n'); + + return 0; } static const struct seq_operations exp_seq_ops = { diff --git a/net/netfilter/nf_internals.h b/net/netfilter/nf_internals.h index 61a3c927e63c..ea7f36784b3d 100644 --- a/net/netfilter/nf_internals.h +++ b/net/netfilter/nf_internals.h @@ -14,16 +14,11 @@ /* core.c */ unsigned int nf_iterate(struct list_head *head, struct sk_buff *skb, - unsigned int hook, const struct net_device *indev, - const struct net_device *outdev, - struct nf_hook_ops **elemp, - int (*okfn)(struct sk_buff *), int hook_thresh); + struct nf_hook_state *state, struct nf_hook_ops **elemp); /* nf_queue.c */ -int nf_queue(struct sk_buff *skb, struct nf_hook_ops *elem, u_int8_t pf, - unsigned int hook, struct net_device *indev, - struct net_device *outdev, int (*okfn)(struct sk_buff *), - unsigned int queuenum); +int nf_queue(struct sk_buff *skb, struct nf_hook_ops *elem, + struct nf_hook_state *state, unsigned int queuenum); int __init netfilter_queue_init(void); /* nf_log.c */ diff --git a/net/netfilter/nf_log_common.c b/net/netfilter/nf_log_common.c index a2233e77cf39..a5aa5967b8e1 100644 --- a/net/netfilter/nf_log_common.c +++ b/net/netfilter/nf_log_common.c @@ -17,6 +17,7 @@ #include <net/route.h> #include <linux/netfilter.h> +#include <linux/netfilter_bridge.h> #include <linux/netfilter/xt_LOG.h> #include <net/netfilter/nf_log.h> @@ -133,7 +134,7 @@ 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) + if (!sk || !sk_fullsock(sk)) return; read_lock_bh(&sk->sk_callback_lock); @@ -163,10 +164,10 @@ nf_log_dump_packet_common(struct nf_log_buf *m, u_int8_t pf, const struct net_device *physindev; const struct net_device *physoutdev; - physindev = skb->nf_bridge->physindev; + physindev = nf_bridge_get_physindev(skb); if (physindev && in != physindev) nf_log_buf_add(m, "PHYSIN=%s ", physindev->name); - physoutdev = skb->nf_bridge->physoutdev; + physoutdev = nf_bridge_get_physoutdev(skb); if (physoutdev && out != physoutdev) nf_log_buf_add(m, "PHYSOUT=%s ", physoutdev->name); } diff --git a/net/netfilter/nf_queue.c b/net/netfilter/nf_queue.c index 4c8b68e5fa16..2e88032cd5ad 100644 --- a/net/netfilter/nf_queue.c +++ b/net/netfilter/nf_queue.c @@ -10,6 +10,7 @@ #include <linux/proc_fs.h> #include <linux/skbuff.h> #include <linux/netfilter.h> +#include <linux/netfilter_bridge.h> #include <linux/seq_file.h> #include <linux/rcupdate.h> #include <net/protocol.h> @@ -47,19 +48,25 @@ EXPORT_SYMBOL(nf_unregister_queue_handler); void nf_queue_entry_release_refs(struct nf_queue_entry *entry) { + struct nf_hook_state *state = &entry->state; + /* Release those devices we held, or Alexey will kill me. */ - if (entry->indev) - dev_put(entry->indev); - if (entry->outdev) - dev_put(entry->outdev); + if (state->in) + dev_put(state->in); + if (state->out) + dev_put(state->out); + if (state->sk) + sock_put(state->sk); #if IS_ENABLED(CONFIG_BRIDGE_NETFILTER) if (entry->skb->nf_bridge) { - struct nf_bridge_info *nf_bridge = entry->skb->nf_bridge; + struct net_device *physdev; - if (nf_bridge->physindev) - dev_put(nf_bridge->physindev); - if (nf_bridge->physoutdev) - dev_put(nf_bridge->physoutdev); + physdev = nf_bridge_get_physindev(entry->skb); + if (physdev) + dev_put(physdev); + physdev = nf_bridge_get_physoutdev(entry->skb); + if (physdev) + dev_put(physdev); } #endif /* Drop reference to owner of hook which queued us. */ @@ -70,22 +77,25 @@ EXPORT_SYMBOL_GPL(nf_queue_entry_release_refs); /* Bump dev refs so they don't vanish while packet is out */ bool nf_queue_entry_get_refs(struct nf_queue_entry *entry) { + struct nf_hook_state *state = &entry->state; + if (!try_module_get(entry->elem->owner)) return false; - if (entry->indev) - dev_hold(entry->indev); - if (entry->outdev) - dev_hold(entry->outdev); + if (state->in) + dev_hold(state->in); + if (state->out) + dev_hold(state->out); + if (state->sk) + sock_hold(state->sk); #if IS_ENABLED(CONFIG_BRIDGE_NETFILTER) if (entry->skb->nf_bridge) { - struct nf_bridge_info *nf_bridge = entry->skb->nf_bridge; struct net_device *physdev; - physdev = nf_bridge->physindev; + physdev = nf_bridge_get_physindev(entry->skb); if (physdev) dev_hold(physdev); - physdev = nf_bridge->physoutdev; + physdev = nf_bridge_get_physoutdev(entry->skb); if (physdev) dev_hold(physdev); } @@ -100,12 +110,9 @@ EXPORT_SYMBOL_GPL(nf_queue_entry_get_refs); * through nf_reinject(). */ int nf_queue(struct sk_buff *skb, - struct nf_hook_ops *elem, - u_int8_t pf, unsigned int hook, - struct net_device *indev, - struct net_device *outdev, - int (*okfn)(struct sk_buff *), - unsigned int queuenum) + struct nf_hook_ops *elem, + struct nf_hook_state *state, + unsigned int queuenum) { int status = -ENOENT; struct nf_queue_entry *entry = NULL; @@ -121,7 +128,7 @@ int nf_queue(struct sk_buff *skb, goto err_unlock; } - afinfo = nf_get_afinfo(pf); + afinfo = nf_get_afinfo(state->pf); if (!afinfo) goto err_unlock; @@ -134,11 +141,7 @@ int nf_queue(struct sk_buff *skb, *entry = (struct nf_queue_entry) { .skb = skb, .elem = elem, - .pf = pf, - .hook = hook, - .indev = indev, - .outdev = outdev, - .okfn = okfn, + .state = *state, .size = sizeof(*entry) + afinfo->route_key_size, }; @@ -184,30 +187,29 @@ void nf_reinject(struct nf_queue_entry *entry, unsigned int verdict) } if (verdict == NF_ACCEPT) { - afinfo = nf_get_afinfo(entry->pf); + afinfo = nf_get_afinfo(entry->state.pf); if (!afinfo || afinfo->reroute(skb, entry) < 0) verdict = NF_DROP; } + entry->state.thresh = INT_MIN; + if (verdict == NF_ACCEPT) { next_hook: - verdict = nf_iterate(&nf_hooks[entry->pf][entry->hook], - skb, entry->hook, - entry->indev, entry->outdev, &elem, - entry->okfn, INT_MIN); + verdict = nf_iterate(&nf_hooks[entry->state.pf][entry->state.hook], + skb, &entry->state, &elem); } switch (verdict & NF_VERDICT_MASK) { case NF_ACCEPT: case NF_STOP: local_bh_disable(); - entry->okfn(skb); + entry->state.okfn(entry->state.sk, skb); local_bh_enable(); break; case NF_QUEUE: - err = nf_queue(skb, elem, entry->pf, entry->hook, - entry->indev, entry->outdev, entry->okfn, - verdict >> NF_VERDICT_QBITS); + err = nf_queue(skb, elem, &entry->state, + verdict >> NF_VERDICT_QBITS); if (err < 0) { if (err == -ECANCELED) goto next_hook; diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c index ac1a9528dbf2..ad9d11fb29fd 100644 --- a/net/netfilter/nf_tables_api.c +++ b/net/netfilter/nf_tables_api.c @@ -198,36 +198,31 @@ static int nft_delchain(struct nft_ctx *ctx) static inline bool nft_rule_is_active(struct net *net, const struct nft_rule *rule) { - return (rule->genmask & (1 << net->nft.gencursor)) == 0; -} - -static inline int gencursor_next(struct net *net) -{ - return net->nft.gencursor+1 == 1 ? 1 : 0; + return (rule->genmask & nft_genmask_cur(net)) == 0; } static inline int nft_rule_is_active_next(struct net *net, const struct nft_rule *rule) { - return (rule->genmask & (1 << gencursor_next(net))) == 0; + return (rule->genmask & nft_genmask_next(net)) == 0; } static inline void nft_rule_activate_next(struct net *net, struct nft_rule *rule) { /* Now inactive, will be active in the future */ - rule->genmask = (1 << net->nft.gencursor); + rule->genmask = nft_genmask_cur(net); } static inline void nft_rule_deactivate_next(struct net *net, struct nft_rule *rule) { - rule->genmask = (1 << gencursor_next(net)); + rule->genmask = nft_genmask_next(net); } static inline void nft_rule_clear(struct net *net, struct nft_rule *rule) { - rule->genmask &= ~(1 << gencursor_next(net)); + rule->genmask &= ~nft_genmask_next(net); } static int @@ -401,7 +396,8 @@ nf_tables_chain_type_lookup(const struct nft_af_info *afi, } static const struct nla_policy nft_table_policy[NFTA_TABLE_MAX + 1] = { - [NFTA_TABLE_NAME] = { .type = NLA_STRING }, + [NFTA_TABLE_NAME] = { .type = NLA_STRING, + .len = NFT_TABLE_MAXNAMELEN - 1 }, [NFTA_TABLE_FLAGS] = { .type = NLA_U32 }, }; @@ -686,26 +682,28 @@ static int nf_tables_newtable(struct sock *nlsk, struct sk_buff *skb, if (!try_module_get(afi->owner)) return -EAFNOSUPPORT; - table = kzalloc(sizeof(*table) + nla_len(name), GFP_KERNEL); - if (table == NULL) { - module_put(afi->owner); - return -ENOMEM; - } + err = -ENOMEM; + table = kzalloc(sizeof(*table), GFP_KERNEL); + if (table == NULL) + goto err1; - nla_strlcpy(table->name, name, nla_len(name)); + nla_strlcpy(table->name, name, NFT_TABLE_MAXNAMELEN); INIT_LIST_HEAD(&table->chains); INIT_LIST_HEAD(&table->sets); table->flags = flags; nft_ctx_init(&ctx, skb, nlh, afi, table, NULL, nla); err = nft_trans_table_add(&ctx, NFT_MSG_NEWTABLE); - if (err < 0) { - kfree(table); - module_put(afi->owner); - return err; - } + if (err < 0) + goto err2; + list_add_tail_rcu(&table->list, &afi->tables); return 0; +err2: + kfree(table); +err1: + module_put(afi->owner); + return err; } static int nft_flush_table(struct nft_ctx *ctx) @@ -1351,6 +1349,7 @@ static int nf_tables_newchain(struct sock *nlsk, struct sk_buff *skb, rcu_assign_pointer(basechain->stats, stats); } + write_pnet(&basechain->pnet, net); basechain->type = type; chain = &basechain->chain; @@ -1378,7 +1377,6 @@ static int nf_tables_newchain(struct sock *nlsk, struct sk_buff *skb, INIT_LIST_HEAD(&chain->rules); chain->handle = nf_tables_alloc_handle(table); - chain->net = net; chain->table = table; nla_strlcpy(chain->name, name, NFT_CHAIN_MAXNAMELEN); @@ -1547,6 +1545,23 @@ nla_put_failure: return -1; }; +int nft_expr_dump(struct sk_buff *skb, unsigned int attr, + const struct nft_expr *expr) +{ + struct nlattr *nest; + + nest = nla_nest_start(skb, attr); + if (!nest) + goto nla_put_failure; + if (nf_tables_fill_expr_info(skb, expr) < 0) + goto nla_put_failure; + nla_nest_end(skb, nest); + return 0; + +nla_put_failure: + return -1; +} + struct nft_expr_info { const struct nft_expr_ops *ops; struct nlattr *tb[NFT_EXPR_MAXATTR + 1]; @@ -1624,6 +1639,39 @@ static void nf_tables_expr_destroy(const struct nft_ctx *ctx, module_put(expr->ops->type->owner); } +struct nft_expr *nft_expr_init(const struct nft_ctx *ctx, + const struct nlattr *nla) +{ + struct nft_expr_info info; + struct nft_expr *expr; + int err; + + err = nf_tables_expr_parse(ctx, nla, &info); + if (err < 0) + goto err1; + + err = -ENOMEM; + expr = kzalloc(info.ops->size, GFP_KERNEL); + if (expr == NULL) + goto err2; + + err = nf_tables_newexpr(ctx, &info, expr); + if (err < 0) + goto err2; + + return expr; +err2: + module_put(info.ops->type->owner); +err1: + return ERR_PTR(err); +} + +void nft_expr_destroy(const struct nft_ctx *ctx, struct nft_expr *expr) +{ + nf_tables_expr_destroy(ctx, expr); + kfree(expr); +} + /* * Rules */ @@ -1705,12 +1753,8 @@ static int nf_tables_fill_rule_info(struct sk_buff *skb, struct net *net, if (list == NULL) goto nla_put_failure; nft_rule_for_each_expr(expr, next, rule) { - struct nlattr *elem = nla_nest_start(skb, NFTA_LIST_ELEM); - if (elem == NULL) + if (nft_expr_dump(skb, NFTA_LIST_ELEM, expr) < 0) goto nla_put_failure; - if (nf_tables_fill_expr_info(skb, expr) < 0) - goto nla_put_failure; - nla_nest_end(skb, elem); } nla_nest_end(skb, list); @@ -2161,7 +2205,7 @@ nft_select_set_ops(const struct nlattr * const nla[], features = 0; if (nla[NFTA_SET_FLAGS] != NULL) { features = ntohl(nla_get_be32(nla[NFTA_SET_FLAGS])); - features &= NFT_SET_INTERVAL | NFT_SET_MAP; + features &= NFT_SET_INTERVAL | NFT_SET_MAP | NFT_SET_TIMEOUT; } bops = NULL; @@ -2218,6 +2262,8 @@ static const struct nla_policy nft_set_policy[NFTA_SET_MAX + 1] = { [NFTA_SET_POLICY] = { .type = NLA_U32 }, [NFTA_SET_DESC] = { .type = NLA_NESTED }, [NFTA_SET_ID] = { .type = NLA_U32 }, + [NFTA_SET_TIMEOUT] = { .type = NLA_U64 }, + [NFTA_SET_GC_INTERVAL] = { .type = NLA_U32 }, }; static const struct nla_policy nft_set_desc_policy[NFTA_SET_DESC_MAX + 1] = { @@ -2368,6 +2414,13 @@ static int nf_tables_fill_set(struct sk_buff *skb, const struct nft_ctx *ctx, goto nla_put_failure; } + if (set->timeout && + nla_put_be64(skb, NFTA_SET_TIMEOUT, cpu_to_be64(set->timeout))) + goto nla_put_failure; + if (set->gc_int && + nla_put_be32(skb, NFTA_SET_GC_INTERVAL, htonl(set->gc_int))) + goto nla_put_failure; + if (set->policy != NFT_SET_POL_PERFORMANCE) { if (nla_put_be32(skb, NFTA_SET_POLICY, htonl(set->policy))) goto nla_put_failure; @@ -2580,7 +2633,8 @@ static int nf_tables_newset(struct sock *nlsk, struct sk_buff *skb, char name[IFNAMSIZ]; unsigned int size; bool create; - u32 ktype, dtype, flags, policy; + u64 timeout; + u32 ktype, dtype, flags, policy, gc_int; struct nft_set_desc desc; int err; @@ -2600,15 +2654,20 @@ static int nf_tables_newset(struct sock *nlsk, struct sk_buff *skb, } desc.klen = ntohl(nla_get_be32(nla[NFTA_SET_KEY_LEN])); - if (desc.klen == 0 || desc.klen > FIELD_SIZEOF(struct nft_data, data)) + if (desc.klen == 0 || desc.klen > NFT_DATA_VALUE_MAXLEN) return -EINVAL; flags = 0; if (nla[NFTA_SET_FLAGS] != NULL) { flags = ntohl(nla_get_be32(nla[NFTA_SET_FLAGS])); if (flags & ~(NFT_SET_ANONYMOUS | NFT_SET_CONSTANT | - NFT_SET_INTERVAL | NFT_SET_MAP)) + NFT_SET_INTERVAL | NFT_SET_TIMEOUT | + NFT_SET_MAP | NFT_SET_EVAL)) return -EINVAL; + /* Only one of both operations is supported */ + if ((flags & (NFT_SET_MAP | NFT_SET_EVAL)) == + (NFT_SET_MAP | NFT_SET_EVAL)) + return -EOPNOTSUPP; } dtype = 0; @@ -2625,14 +2684,26 @@ static int nf_tables_newset(struct sock *nlsk, struct sk_buff *skb, if (nla[NFTA_SET_DATA_LEN] == NULL) return -EINVAL; desc.dlen = ntohl(nla_get_be32(nla[NFTA_SET_DATA_LEN])); - if (desc.dlen == 0 || - desc.dlen > FIELD_SIZEOF(struct nft_data, data)) + if (desc.dlen == 0 || desc.dlen > NFT_DATA_VALUE_MAXLEN) return -EINVAL; } else - desc.dlen = sizeof(struct nft_data); + desc.dlen = sizeof(struct nft_verdict); } else if (flags & NFT_SET_MAP) return -EINVAL; + timeout = 0; + if (nla[NFTA_SET_TIMEOUT] != NULL) { + if (!(flags & NFT_SET_TIMEOUT)) + return -EINVAL; + timeout = be64_to_cpu(nla_get_be64(nla[NFTA_SET_TIMEOUT])); + } + gc_int = 0; + if (nla[NFTA_SET_GC_INTERVAL] != NULL) { + if (!(flags & NFT_SET_TIMEOUT)) + return -EINVAL; + gc_int = ntohl(nla_get_be32(nla[NFTA_SET_GC_INTERVAL])); + } + policy = NFT_SET_POL_PERFORMANCE; if (nla[NFTA_SET_POLICY] != NULL) policy = ntohl(nla_get_be32(nla[NFTA_SET_POLICY])); @@ -2692,6 +2763,7 @@ static int nf_tables_newset(struct sock *nlsk, struct sk_buff *skb, goto err2; INIT_LIST_HEAD(&set->bindings); + write_pnet(&set->pnet, net); set->ops = ops; set->ktype = ktype; set->klen = desc.klen; @@ -2700,6 +2772,8 @@ static int nf_tables_newset(struct sock *nlsk, struct sk_buff *skb, set->flags = flags; set->size = desc.size; set->policy = policy; + set->timeout = timeout; + set->gc_int = gc_int; err = ops->init(set, &desc, nla); if (err < 0) @@ -2768,12 +2842,14 @@ static int nf_tables_bind_check_setelem(const struct nft_ctx *ctx, const struct nft_set_iter *iter, const struct nft_set_elem *elem) { + const struct nft_set_ext *ext = nft_set_elem_ext(set, elem->priv); enum nft_registers dreg; dreg = nft_type_to_reg(set->dtype); - return nft_validate_data_load(ctx, dreg, &elem->data, - set->dtype == NFT_DATA_VERDICT ? - NFT_DATA_VERDICT : NFT_DATA_VALUE); + return nft_validate_register_store(ctx, dreg, nft_set_ext_data(ext), + set->dtype == NFT_DATA_VERDICT ? + NFT_DATA_VERDICT : NFT_DATA_VALUE, + set->dlen); } int nf_tables_bind_set(const struct nft_ctx *ctx, struct nft_set *set, @@ -2785,12 +2861,13 @@ int nf_tables_bind_set(const struct nft_ctx *ctx, struct nft_set *set, if (!list_empty(&set->bindings) && set->flags & NFT_SET_ANONYMOUS) return -EBUSY; - if (set->flags & NFT_SET_MAP) { + if (binding->flags & NFT_SET_MAP) { /* If the set is already bound to the same chain all * jumps are already validated for that chain. */ list_for_each_entry(i, &set->bindings, list) { - if (i->chain == binding->chain) + if (binding->flags & NFT_SET_MAP && + i->chain == binding->chain) goto bind; } @@ -2824,6 +2901,35 @@ void nf_tables_unbind_set(const struct nft_ctx *ctx, struct nft_set *set, nf_tables_set_destroy(ctx, set); } +const struct nft_set_ext_type nft_set_ext_types[] = { + [NFT_SET_EXT_KEY] = { + .align = __alignof__(u32), + }, + [NFT_SET_EXT_DATA] = { + .align = __alignof__(u32), + }, + [NFT_SET_EXT_EXPR] = { + .align = __alignof__(struct nft_expr), + }, + [NFT_SET_EXT_FLAGS] = { + .len = sizeof(u8), + .align = __alignof__(u8), + }, + [NFT_SET_EXT_TIMEOUT] = { + .len = sizeof(u64), + .align = __alignof__(u64), + }, + [NFT_SET_EXT_EXPIRATION] = { + .len = sizeof(unsigned long), + .align = __alignof__(unsigned long), + }, + [NFT_SET_EXT_USERDATA] = { + .len = sizeof(struct nft_userdata), + .align = __alignof__(struct nft_userdata), + }, +}; +EXPORT_SYMBOL_GPL(nft_set_ext_types); + /* * Set elements */ @@ -2832,6 +2938,9 @@ static const struct nla_policy nft_set_elem_policy[NFTA_SET_ELEM_MAX + 1] = { [NFTA_SET_ELEM_KEY] = { .type = NLA_NESTED }, [NFTA_SET_ELEM_DATA] = { .type = NLA_NESTED }, [NFTA_SET_ELEM_FLAGS] = { .type = NLA_U32 }, + [NFTA_SET_ELEM_TIMEOUT] = { .type = NLA_U64 }, + [NFTA_SET_ELEM_USERDATA] = { .type = NLA_BINARY, + .len = NFT_USERDATA_MAXLEN }, }; static const struct nla_policy nft_set_elem_list_policy[NFTA_SET_ELEM_LIST_MAX + 1] = { @@ -2870,6 +2979,7 @@ static int nf_tables_fill_setelem(struct sk_buff *skb, const struct nft_set *set, const struct nft_set_elem *elem) { + const struct nft_set_ext *ext = nft_set_elem_ext(set, elem->priv); unsigned char *b = skb_tail_pointer(skb); struct nlattr *nest; @@ -2877,20 +2987,52 @@ static int nf_tables_fill_setelem(struct sk_buff *skb, if (nest == NULL) goto nla_put_failure; - if (nft_data_dump(skb, NFTA_SET_ELEM_KEY, &elem->key, NFT_DATA_VALUE, - set->klen) < 0) + if (nft_data_dump(skb, NFTA_SET_ELEM_KEY, nft_set_ext_key(ext), + NFT_DATA_VALUE, set->klen) < 0) goto nla_put_failure; - if (set->flags & NFT_SET_MAP && - !(elem->flags & NFT_SET_ELEM_INTERVAL_END) && - nft_data_dump(skb, NFTA_SET_ELEM_DATA, &elem->data, + if (nft_set_ext_exists(ext, NFT_SET_EXT_DATA) && + nft_data_dump(skb, NFTA_SET_ELEM_DATA, nft_set_ext_data(ext), set->dtype == NFT_DATA_VERDICT ? NFT_DATA_VERDICT : NFT_DATA_VALUE, set->dlen) < 0) goto nla_put_failure; - if (elem->flags != 0) - if (nla_put_be32(skb, NFTA_SET_ELEM_FLAGS, htonl(elem->flags))) + if (nft_set_ext_exists(ext, NFT_SET_EXT_EXPR) && + nft_expr_dump(skb, NFTA_SET_ELEM_EXPR, nft_set_ext_expr(ext)) < 0) + goto nla_put_failure; + + if (nft_set_ext_exists(ext, NFT_SET_EXT_FLAGS) && + nla_put_be32(skb, NFTA_SET_ELEM_FLAGS, + htonl(*nft_set_ext_flags(ext)))) + goto nla_put_failure; + + if (nft_set_ext_exists(ext, NFT_SET_EXT_TIMEOUT) && + nla_put_be64(skb, NFTA_SET_ELEM_TIMEOUT, + cpu_to_be64(*nft_set_ext_timeout(ext)))) + goto nla_put_failure; + + if (nft_set_ext_exists(ext, NFT_SET_EXT_EXPIRATION)) { + unsigned long expires, now = jiffies; + + expires = *nft_set_ext_expiration(ext); + if (time_before(now, expires)) + expires -= now; + else + expires = 0; + + if (nla_put_be64(skb, NFTA_SET_ELEM_EXPIRATION, + cpu_to_be64(jiffies_to_msecs(expires)))) goto nla_put_failure; + } + + if (nft_set_ext_exists(ext, NFT_SET_EXT_USERDATA)) { + struct nft_userdata *udata; + + udata = nft_set_ext_userdata(ext); + if (nla_put(skb, NFTA_SET_ELEM_USERDATA, + udata->len + 1, udata->data)) + goto nla_put_failure; + } nla_nest_end(skb, nest); return 0; @@ -3111,20 +3253,65 @@ static struct nft_trans *nft_trans_elem_alloc(struct nft_ctx *ctx, return trans; } +void *nft_set_elem_init(const struct nft_set *set, + const struct nft_set_ext_tmpl *tmpl, + const u32 *key, const u32 *data, + u64 timeout, gfp_t gfp) +{ + struct nft_set_ext *ext; + void *elem; + + elem = kzalloc(set->ops->elemsize + tmpl->len, gfp); + if (elem == NULL) + return NULL; + + ext = nft_set_elem_ext(set, elem); + nft_set_ext_init(ext, tmpl); + + memcpy(nft_set_ext_key(ext), key, set->klen); + if (nft_set_ext_exists(ext, NFT_SET_EXT_DATA)) + memcpy(nft_set_ext_data(ext), data, set->dlen); + if (nft_set_ext_exists(ext, NFT_SET_EXT_EXPIRATION)) + *nft_set_ext_expiration(ext) = + jiffies + msecs_to_jiffies(timeout); + if (nft_set_ext_exists(ext, NFT_SET_EXT_TIMEOUT)) + *nft_set_ext_timeout(ext) = timeout; + + return elem; +} + +void nft_set_elem_destroy(const struct nft_set *set, void *elem) +{ + struct nft_set_ext *ext = nft_set_elem_ext(set, elem); + + nft_data_uninit(nft_set_ext_key(ext), NFT_DATA_VALUE); + if (nft_set_ext_exists(ext, NFT_SET_EXT_DATA)) + nft_data_uninit(nft_set_ext_data(ext), set->dtype); + if (nft_set_ext_exists(ext, NFT_SET_EXT_EXPR)) + nf_tables_expr_destroy(NULL, nft_set_ext_expr(ext)); + + kfree(elem); +} +EXPORT_SYMBOL_GPL(nft_set_elem_destroy); + static int nft_add_set_elem(struct nft_ctx *ctx, struct nft_set *set, const struct nlattr *attr) { struct nlattr *nla[NFTA_SET_ELEM_MAX + 1]; struct nft_data_desc d1, d2; + struct nft_set_ext_tmpl tmpl; + struct nft_set_ext *ext; struct nft_set_elem elem; struct nft_set_binding *binding; + struct nft_userdata *udata; + struct nft_data data; enum nft_registers dreg; struct nft_trans *trans; + u64 timeout; + u32 flags; + u8 ulen; int err; - if (set->size && set->nelems == set->size) - return -ENFILE; - err = nla_parse_nested(nla, NFTA_SET_ELEM_MAX, attr, nft_set_elem_policy); if (err < 0) @@ -3133,38 +3320,59 @@ static int nft_add_set_elem(struct nft_ctx *ctx, struct nft_set *set, if (nla[NFTA_SET_ELEM_KEY] == NULL) return -EINVAL; - elem.flags = 0; + nft_set_ext_prepare(&tmpl); + + flags = 0; if (nla[NFTA_SET_ELEM_FLAGS] != NULL) { - elem.flags = ntohl(nla_get_be32(nla[NFTA_SET_ELEM_FLAGS])); - if (elem.flags & ~NFT_SET_ELEM_INTERVAL_END) + flags = ntohl(nla_get_be32(nla[NFTA_SET_ELEM_FLAGS])); + if (flags & ~NFT_SET_ELEM_INTERVAL_END) + return -EINVAL; + if (!(set->flags & NFT_SET_INTERVAL) && + flags & NFT_SET_ELEM_INTERVAL_END) return -EINVAL; + if (flags != 0) + nft_set_ext_add(&tmpl, NFT_SET_EXT_FLAGS); } if (set->flags & NFT_SET_MAP) { if (nla[NFTA_SET_ELEM_DATA] == NULL && - !(elem.flags & NFT_SET_ELEM_INTERVAL_END)) + !(flags & NFT_SET_ELEM_INTERVAL_END)) return -EINVAL; if (nla[NFTA_SET_ELEM_DATA] != NULL && - elem.flags & NFT_SET_ELEM_INTERVAL_END) + flags & NFT_SET_ELEM_INTERVAL_END) return -EINVAL; } else { if (nla[NFTA_SET_ELEM_DATA] != NULL) return -EINVAL; } - err = nft_data_init(ctx, &elem.key, &d1, nla[NFTA_SET_ELEM_KEY]); + timeout = 0; + if (nla[NFTA_SET_ELEM_TIMEOUT] != NULL) { + if (!(set->flags & NFT_SET_TIMEOUT)) + return -EINVAL; + timeout = be64_to_cpu(nla_get_be64(nla[NFTA_SET_ELEM_TIMEOUT])); + } else if (set->flags & NFT_SET_TIMEOUT) { + timeout = set->timeout; + } + + err = nft_data_init(ctx, &elem.key.val, sizeof(elem.key), &d1, + nla[NFTA_SET_ELEM_KEY]); if (err < 0) goto err1; err = -EINVAL; if (d1.type != NFT_DATA_VALUE || d1.len != set->klen) goto err2; - err = -EEXIST; - if (set->ops->get(set, &elem) == 0) - goto err2; + nft_set_ext_add_length(&tmpl, NFT_SET_EXT_KEY, d1.len); + if (timeout > 0) { + nft_set_ext_add(&tmpl, NFT_SET_EXT_EXPIRATION); + if (timeout != set->timeout) + nft_set_ext_add(&tmpl, NFT_SET_EXT_TIMEOUT); + } if (nla[NFTA_SET_ELEM_DATA] != NULL) { - err = nft_data_init(ctx, &elem.data, &d2, nla[NFTA_SET_ELEM_DATA]); + err = nft_data_init(ctx, &data, sizeof(data), &d2, + nla[NFTA_SET_ELEM_DATA]); if (err < 0) goto err2; @@ -3180,32 +3388,68 @@ static int nft_add_set_elem(struct nft_ctx *ctx, struct nft_set *set, .chain = (struct nft_chain *)binding->chain, }; - err = nft_validate_data_load(&bind_ctx, dreg, - &elem.data, d2.type); + if (!(binding->flags & NFT_SET_MAP)) + continue; + + err = nft_validate_register_store(&bind_ctx, dreg, + &data, + d2.type, d2.len); if (err < 0) goto err3; } + + nft_set_ext_add_length(&tmpl, NFT_SET_EXT_DATA, d2.len); + } + + /* The full maximum length of userdata can exceed the maximum + * offset value (U8_MAX) for following extensions, therefor it + * must be the last extension added. + */ + ulen = 0; + if (nla[NFTA_SET_ELEM_USERDATA] != NULL) { + ulen = nla_len(nla[NFTA_SET_ELEM_USERDATA]); + if (ulen > 0) + nft_set_ext_add_length(&tmpl, NFT_SET_EXT_USERDATA, + ulen); + } + + err = -ENOMEM; + elem.priv = nft_set_elem_init(set, &tmpl, elem.key.val.data, data.data, + timeout, GFP_KERNEL); + if (elem.priv == NULL) + goto err3; + + ext = nft_set_elem_ext(set, elem.priv); + if (flags) + *nft_set_ext_flags(ext) = flags; + if (ulen > 0) { + udata = nft_set_ext_userdata(ext); + udata->len = ulen - 1; + nla_memcpy(&udata->data, nla[NFTA_SET_ELEM_USERDATA], ulen); } trans = nft_trans_elem_alloc(ctx, NFT_MSG_NEWSETELEM, set); if (trans == NULL) - goto err3; + goto err4; + ext->genmask = nft_genmask_cur(ctx->net) | NFT_SET_ELEM_BUSY_MASK; err = set->ops->insert(set, &elem); if (err < 0) - goto err4; + goto err5; nft_trans_elem(trans) = elem; list_add_tail(&trans->list, &ctx->net->nft.commit_list); return 0; -err4: +err5: kfree(trans); +err4: + kfree(elem.priv); err3: if (nla[NFTA_SET_ELEM_DATA] != NULL) - nft_data_uninit(&elem.data, d2.type); + nft_data_uninit(&data, d2.type); err2: - nft_data_uninit(&elem.key, d1.type); + nft_data_uninit(&elem.key.val, d1.type); err1: return err; } @@ -3241,11 +3485,15 @@ static int nf_tables_newsetelem(struct sock *nlsk, struct sk_buff *skb, return -EBUSY; nla_for_each_nested(attr, nla[NFTA_SET_ELEM_LIST_ELEMENTS], rem) { + if (set->size && + !atomic_add_unless(&set->nelems, 1, set->size + set->ndeact)) + return -ENFILE; + err = nft_add_set_elem(&ctx, set, attr); - if (err < 0) + if (err < 0) { + atomic_dec(&set->nelems); break; - - set->nelems++; + } } return err; } @@ -3268,7 +3516,8 @@ static int nft_del_setelem(struct nft_ctx *ctx, struct nft_set *set, if (nla[NFTA_SET_ELEM_KEY] == NULL) goto err1; - err = nft_data_init(ctx, &elem.key, &desc, nla[NFTA_SET_ELEM_KEY]); + err = nft_data_init(ctx, &elem.key.val, sizeof(elem.key), &desc, + nla[NFTA_SET_ELEM_KEY]); if (err < 0) goto err1; @@ -3276,21 +3525,26 @@ static int nft_del_setelem(struct nft_ctx *ctx, struct nft_set *set, if (desc.type != NFT_DATA_VALUE || desc.len != set->klen) goto err2; - err = set->ops->get(set, &elem); - if (err < 0) - goto err2; - trans = nft_trans_elem_alloc(ctx, NFT_MSG_DELSETELEM, set); if (trans == NULL) { err = -ENOMEM; goto err2; } + elem.priv = set->ops->deactivate(set, &elem); + if (elem.priv == NULL) { + err = -ENOENT; + goto err3; + } + nft_trans_elem(trans) = elem; list_add_tail(&trans->list, &ctx->net->nft.commit_list); return 0; + +err3: + kfree(trans); err2: - nft_data_uninit(&elem.key, desc.type); + nft_data_uninit(&elem.key.val, desc.type); err1: return err; } @@ -3322,11 +3576,36 @@ static int nf_tables_delsetelem(struct sock *nlsk, struct sk_buff *skb, if (err < 0) break; - set->nelems--; + set->ndeact++; } return err; } +void nft_set_gc_batch_release(struct rcu_head *rcu) +{ + struct nft_set_gc_batch *gcb; + unsigned int i; + + gcb = container_of(rcu, struct nft_set_gc_batch, head.rcu); + for (i = 0; i < gcb->head.cnt; i++) + nft_set_elem_destroy(gcb->head.set, gcb->elems[i]); + kfree(gcb); +} +EXPORT_SYMBOL_GPL(nft_set_gc_batch_release); + +struct nft_set_gc_batch *nft_set_gc_batch_alloc(const struct nft_set *set, + gfp_t gfp) +{ + struct nft_set_gc_batch *gcb; + + gcb = kzalloc(sizeof(*gcb), gfp); + if (gcb == NULL) + return gcb; + gcb->head.set = set; + return gcb; +} +EXPORT_SYMBOL_GPL(nft_set_gc_batch_alloc); + static int nf_tables_fill_gen_info(struct sk_buff *skb, struct net *net, u32 portid, u32 seq) { @@ -3526,6 +3805,10 @@ static void nf_tables_commit_release(struct nft_trans *trans) case NFT_MSG_DELSET: nft_set_destroy(nft_trans_set(trans)); break; + case NFT_MSG_DELSETELEM: + nft_set_elem_destroy(nft_trans_elem_set(trans), + nft_trans_elem(trans).priv); + break; } kfree(trans); } @@ -3540,7 +3823,7 @@ static int nf_tables_commit(struct sk_buff *skb) while (++net->nft.base_seq == 0); /* A new generation has just started */ - net->nft.gencursor = gencursor_next(net); + net->nft.gencursor = nft_gencursor_next(net); /* Make sure all packets have left the previous generation before * purging old rules. @@ -3611,24 +3894,23 @@ static int nf_tables_commit(struct sk_buff *skb) NFT_MSG_DELSET, GFP_KERNEL); break; case NFT_MSG_NEWSETELEM: - nf_tables_setelem_notify(&trans->ctx, - nft_trans_elem_set(trans), - &nft_trans_elem(trans), + te = (struct nft_trans_elem *)trans->data; + + te->set->ops->activate(te->set, &te->elem); + nf_tables_setelem_notify(&trans->ctx, te->set, + &te->elem, NFT_MSG_NEWSETELEM, 0); nft_trans_destroy(trans); break; case NFT_MSG_DELSETELEM: te = (struct nft_trans_elem *)trans->data; + nf_tables_setelem_notify(&trans->ctx, te->set, &te->elem, NFT_MSG_DELSETELEM, 0); - te->set->ops->get(te->set, &te->elem); - nft_data_uninit(&te->elem.key, NFT_DATA_VALUE); - if (te->set->flags & NFT_SET_MAP && - !(te->elem.flags & NFT_SET_ELEM_INTERVAL_END)) - nft_data_uninit(&te->elem.data, te->set->dtype); te->set->ops->remove(te->set, &te->elem); - nft_trans_destroy(trans); + atomic_dec(&te->set->nelems); + te->set->ndeact--; break; } } @@ -3660,6 +3942,10 @@ static void nf_tables_abort_release(struct nft_trans *trans) case NFT_MSG_NEWSET: nft_set_destroy(nft_trans_set(trans)); break; + case NFT_MSG_NEWSETELEM: + nft_set_elem_destroy(nft_trans_elem_set(trans), + nft_trans_elem(trans).priv); + break; } kfree(trans); } @@ -3728,18 +4014,17 @@ static int nf_tables_abort(struct sk_buff *skb) nft_trans_destroy(trans); break; case NFT_MSG_NEWSETELEM: - nft_trans_elem_set(trans)->nelems--; te = (struct nft_trans_elem *)trans->data; - te->set->ops->get(te->set, &te->elem); - nft_data_uninit(&te->elem.key, NFT_DATA_VALUE); - if (te->set->flags & NFT_SET_MAP && - !(te->elem.flags & NFT_SET_ELEM_INTERVAL_END)) - nft_data_uninit(&te->elem.data, te->set->dtype); + te->set->ops->remove(te->set, &te->elem); - nft_trans_destroy(trans); + atomic_dec(&te->set->nelems); break; case NFT_MSG_DELSETELEM: - nft_trans_elem_set(trans)->nelems++; + te = (struct nft_trans_elem *)trans->data; + + te->set->ops->activate(te->set, &te->elem); + te->set->ndeact--; + nft_trans_destroy(trans); break; } @@ -3814,13 +4099,18 @@ static int nf_tables_loop_check_setelem(const struct nft_ctx *ctx, const struct nft_set_iter *iter, const struct nft_set_elem *elem) { - if (elem->flags & NFT_SET_ELEM_INTERVAL_END) + const struct nft_set_ext *ext = nft_set_elem_ext(set, elem->priv); + const struct nft_data *data; + + if (nft_set_ext_exists(ext, NFT_SET_EXT_FLAGS) && + *nft_set_ext_flags(ext) & NFT_SET_ELEM_INTERVAL_END) return 0; - switch (elem->data.verdict) { + data = nft_set_ext_data(ext); + switch (data->verdict.code) { case NFT_JUMP: case NFT_GOTO: - return nf_tables_check_loops(ctx, elem->data.chain); + return nf_tables_check_loops(ctx, data->verdict.chain); default: return 0; } @@ -3853,10 +4143,11 @@ static int nf_tables_check_loops(const struct nft_ctx *ctx, if (data == NULL) continue; - switch (data->verdict) { + switch (data->verdict.code) { case NFT_JUMP: case NFT_GOTO: - err = nf_tables_check_loops(ctx, data->chain); + err = nf_tables_check_loops(ctx, + data->verdict.chain); if (err < 0) return err; default: @@ -3871,7 +4162,8 @@ static int nf_tables_check_loops(const struct nft_ctx *ctx, continue; list_for_each_entry(binding, &set->bindings, list) { - if (binding->chain != chain) + if (!(binding->flags & NFT_SET_MAP) || + binding->chain != chain) continue; iter.skip = 0; @@ -3889,85 +4181,129 @@ static int nf_tables_check_loops(const struct nft_ctx *ctx, } /** - * nft_validate_input_register - validate an expressions' input register + * nft_parse_register - parse a register value from a netlink attribute * - * @reg: the register number + * @attr: netlink attribute * - * Validate that the input register is one of the general purpose - * registers. + * Parse and translate a register value from a netlink attribute. + * Registers used to be 128 bit wide, these register numbers will be + * mapped to the corresponding 32 bit register numbers. */ -int nft_validate_input_register(enum nft_registers reg) +unsigned int nft_parse_register(const struct nlattr *attr) { - if (reg <= NFT_REG_VERDICT) - return -EINVAL; - if (reg > NFT_REG_MAX) - return -ERANGE; - return 0; + unsigned int reg; + + reg = ntohl(nla_get_be32(attr)); + switch (reg) { + case NFT_REG_VERDICT...NFT_REG_4: + return reg * NFT_REG_SIZE / NFT_REG32_SIZE; + default: + return reg + NFT_REG_SIZE / NFT_REG32_SIZE - NFT_REG32_00; + } } -EXPORT_SYMBOL_GPL(nft_validate_input_register); +EXPORT_SYMBOL_GPL(nft_parse_register); /** - * nft_validate_output_register - validate an expressions' output register + * nft_dump_register - dump a register value to a netlink attribute + * + * @skb: socket buffer + * @attr: attribute number + * @reg: register number + * + * Construct a netlink attribute containing the register number. For + * compatibility reasons, register numbers being a multiple of 4 are + * translated to the corresponding 128 bit register numbers. + */ +int nft_dump_register(struct sk_buff *skb, unsigned int attr, unsigned int reg) +{ + if (reg % (NFT_REG_SIZE / NFT_REG32_SIZE) == 0) + reg = reg / (NFT_REG_SIZE / NFT_REG32_SIZE); + else + reg = reg - NFT_REG_SIZE / NFT_REG32_SIZE + NFT_REG32_00; + + return nla_put_be32(skb, attr, htonl(reg)); +} +EXPORT_SYMBOL_GPL(nft_dump_register); + +/** + * nft_validate_register_load - validate a load from a register * * @reg: the register number + * @len: the length of the data * - * Validate that the output register is one of the general purpose - * registers or the verdict register. + * Validate that the input register is one of the general purpose + * registers and that the length of the load is within the bounds. */ -int nft_validate_output_register(enum nft_registers reg) +int nft_validate_register_load(enum nft_registers reg, unsigned int len) { - if (reg < NFT_REG_VERDICT) + if (reg < NFT_REG_1 * NFT_REG_SIZE / NFT_REG32_SIZE) return -EINVAL; - if (reg > NFT_REG_MAX) + if (len == 0) + return -EINVAL; + if (reg * NFT_REG32_SIZE + len > FIELD_SIZEOF(struct nft_regs, data)) return -ERANGE; + return 0; } -EXPORT_SYMBOL_GPL(nft_validate_output_register); +EXPORT_SYMBOL_GPL(nft_validate_register_load); /** - * nft_validate_data_load - validate an expressions' data load + * nft_validate_register_store - validate an expressions' register store * * @ctx: context of the expression performing the load * @reg: the destination register number * @data: the data to load * @type: the data type + * @len: the length of the data * * Validate that a data load uses the appropriate data type for - * the destination register. A value of NULL for the data means - * that its runtime gathered data, which is always of type - * NFT_DATA_VALUE. + * the destination register and the length is within the bounds. + * A value of NULL for the data means that its runtime gathered + * data. */ -int nft_validate_data_load(const struct nft_ctx *ctx, enum nft_registers reg, - const struct nft_data *data, - enum nft_data_types type) +int nft_validate_register_store(const struct nft_ctx *ctx, + enum nft_registers reg, + const struct nft_data *data, + enum nft_data_types type, unsigned int len) { int err; switch (reg) { case NFT_REG_VERDICT: - if (data == NULL || type != NFT_DATA_VERDICT) + if (type != NFT_DATA_VERDICT) return -EINVAL; - if (data->verdict == NFT_GOTO || data->verdict == NFT_JUMP) { - err = nf_tables_check_loops(ctx, data->chain); + if (data != NULL && + (data->verdict.code == NFT_GOTO || + data->verdict.code == NFT_JUMP)) { + err = nf_tables_check_loops(ctx, data->verdict.chain); if (err < 0) return err; - if (ctx->chain->level + 1 > data->chain->level) { + if (ctx->chain->level + 1 > + data->verdict.chain->level) { if (ctx->chain->level + 1 == NFT_JUMP_STACK_SIZE) return -EMLINK; - data->chain->level = ctx->chain->level + 1; + data->verdict.chain->level = ctx->chain->level + 1; } } return 0; default: + if (reg < NFT_REG_1 * NFT_REG_SIZE / NFT_REG32_SIZE) + return -EINVAL; + if (len == 0) + return -EINVAL; + if (reg * NFT_REG32_SIZE + len > + FIELD_SIZEOF(struct nft_regs, data)) + return -ERANGE; + if (data != NULL && type != NFT_DATA_VALUE) return -EINVAL; return 0; } } -EXPORT_SYMBOL_GPL(nft_validate_data_load); +EXPORT_SYMBOL_GPL(nft_validate_register_store); static const struct nla_policy nft_verdict_policy[NFTA_VERDICT_MAX + 1] = { [NFTA_VERDICT_CODE] = { .type = NLA_U32 }, @@ -3988,11 +4324,11 @@ static int nft_verdict_init(const struct nft_ctx *ctx, struct nft_data *data, if (!tb[NFTA_VERDICT_CODE]) return -EINVAL; - data->verdict = ntohl(nla_get_be32(tb[NFTA_VERDICT_CODE])); + data->verdict.code = ntohl(nla_get_be32(tb[NFTA_VERDICT_CODE])); - switch (data->verdict) { + switch (data->verdict.code) { default: - switch (data->verdict & NF_VERDICT_MASK) { + switch (data->verdict.code & NF_VERDICT_MASK) { case NF_ACCEPT: case NF_DROP: case NF_QUEUE: @@ -4004,7 +4340,6 @@ static int nft_verdict_init(const struct nft_ctx *ctx, struct nft_data *data, case NFT_CONTINUE: case NFT_BREAK: case NFT_RETURN: - desc->len = sizeof(data->verdict); break; case NFT_JUMP: case NFT_GOTO: @@ -4018,21 +4353,21 @@ static int nft_verdict_init(const struct nft_ctx *ctx, struct nft_data *data, return -EOPNOTSUPP; chain->use++; - data->chain = chain; - desc->len = sizeof(data); + data->verdict.chain = chain; break; } + desc->len = sizeof(data->verdict); desc->type = NFT_DATA_VERDICT; return 0; } static void nft_verdict_uninit(const struct nft_data *data) { - switch (data->verdict) { + switch (data->verdict.code) { case NFT_JUMP: case NFT_GOTO: - data->chain->use--; + data->verdict.chain->use--; break; } } @@ -4045,13 +4380,14 @@ static int nft_verdict_dump(struct sk_buff *skb, const struct nft_data *data) if (!nest) goto nla_put_failure; - if (nla_put_be32(skb, NFTA_VERDICT_CODE, htonl(data->verdict))) + if (nla_put_be32(skb, NFTA_VERDICT_CODE, htonl(data->verdict.code))) goto nla_put_failure; - switch (data->verdict) { + switch (data->verdict.code) { case NFT_JUMP: case NFT_GOTO: - if (nla_put_string(skb, NFTA_VERDICT_CHAIN, data->chain->name)) + if (nla_put_string(skb, NFTA_VERDICT_CHAIN, + data->verdict.chain->name)) goto nla_put_failure; } nla_nest_end(skb, nest); @@ -4061,7 +4397,8 @@ nla_put_failure: return -1; } -static int nft_value_init(const struct nft_ctx *ctx, struct nft_data *data, +static int nft_value_init(const struct nft_ctx *ctx, + struct nft_data *data, unsigned int size, struct nft_data_desc *desc, const struct nlattr *nla) { unsigned int len; @@ -4069,10 +4406,10 @@ static int nft_value_init(const struct nft_ctx *ctx, struct nft_data *data, len = nla_len(nla); if (len == 0) return -EINVAL; - if (len > sizeof(data->data)) + if (len > size) return -EOVERFLOW; - nla_memcpy(data->data, nla, sizeof(data->data)); + nla_memcpy(data->data, nla, len); desc->type = NFT_DATA_VALUE; desc->len = len; return 0; @@ -4085,8 +4422,7 @@ static int nft_value_dump(struct sk_buff *skb, const struct nft_data *data, } static const struct nla_policy nft_data_policy[NFTA_DATA_MAX + 1] = { - [NFTA_DATA_VALUE] = { .type = NLA_BINARY, - .len = FIELD_SIZEOF(struct nft_data, data) }, + [NFTA_DATA_VALUE] = { .type = NLA_BINARY }, [NFTA_DATA_VERDICT] = { .type = NLA_NESTED }, }; @@ -4095,6 +4431,7 @@ static const struct nla_policy nft_data_policy[NFTA_DATA_MAX + 1] = { * * @ctx: context of the expression using the data * @data: destination struct nft_data + * @size: maximum data length * @desc: data description * @nla: netlink attribute containing data * @@ -4104,7 +4441,8 @@ static const struct nla_policy nft_data_policy[NFTA_DATA_MAX + 1] = { * The caller can indicate that it only wants to accept data of type * NFT_DATA_VALUE by passing NULL for the ctx argument. */ -int nft_data_init(const struct nft_ctx *ctx, struct nft_data *data, +int nft_data_init(const struct nft_ctx *ctx, + struct nft_data *data, unsigned int size, struct nft_data_desc *desc, const struct nlattr *nla) { struct nlattr *tb[NFTA_DATA_MAX + 1]; @@ -4115,7 +4453,8 @@ int nft_data_init(const struct nft_ctx *ctx, struct nft_data *data, return err; if (tb[NFTA_DATA_VALUE]) - return nft_value_init(ctx, data, desc, tb[NFTA_DATA_VALUE]); + return nft_value_init(ctx, data, size, desc, + tb[NFTA_DATA_VALUE]); if (tb[NFTA_DATA_VERDICT] && ctx != NULL) return nft_verdict_init(ctx, data, desc, tb[NFTA_DATA_VERDICT]); return -EINVAL; diff --git a/net/netfilter/nf_tables_core.c b/net/netfilter/nf_tables_core.c index 2d298dccb6dd..f153b07073af 100644 --- a/net/netfilter/nf_tables_core.c +++ b/net/netfilter/nf_tables_core.c @@ -8,6 +8,7 @@ * Development of this code funded by Astaro AG (http://www.astaro.com/) */ +#include <linux/kernel.h> #include <linux/module.h> #include <linux/init.h> #include <linux/list.h> @@ -21,24 +22,66 @@ #include <net/netfilter/nf_tables.h> #include <net/netfilter/nf_log.h> +enum nft_trace { + NFT_TRACE_RULE, + NFT_TRACE_RETURN, + NFT_TRACE_POLICY, +}; + +static const char *const comments[] = { + [NFT_TRACE_RULE] = "rule", + [NFT_TRACE_RETURN] = "return", + [NFT_TRACE_POLICY] = "policy", +}; + +static struct nf_loginfo trace_loginfo = { + .type = NF_LOG_TYPE_LOG, + .u = { + .log = { + .level = LOGLEVEL_WARNING, + .logflags = NF_LOG_MASK, + }, + }, +}; + +static void __nft_trace_packet(const struct nft_pktinfo *pkt, + const struct nft_chain *chain, + int rulenum, enum nft_trace type) +{ + struct net *net = dev_net(pkt->in ? pkt->in : pkt->out); + + nf_log_trace(net, pkt->xt.family, pkt->ops->hooknum, pkt->skb, pkt->in, + pkt->out, &trace_loginfo, "TRACE: %s:%s:%s:%u ", + chain->table->name, chain->name, comments[type], + rulenum); +} + +static inline void nft_trace_packet(const struct nft_pktinfo *pkt, + const struct nft_chain *chain, + int rulenum, enum nft_trace type) +{ + if (unlikely(pkt->skb->nf_trace)) + __nft_trace_packet(pkt, chain, rulenum, type); +} + static void nft_cmp_fast_eval(const struct nft_expr *expr, - struct nft_data data[NFT_REG_MAX + 1]) + struct nft_regs *regs) { const struct nft_cmp_fast_expr *priv = nft_expr_priv(expr); u32 mask = nft_cmp_fast_mask(priv->len); - if ((data[priv->sreg].data[0] & mask) == priv->data) + if ((regs->data[priv->sreg] & mask) == priv->data) return; - data[NFT_REG_VERDICT].verdict = NFT_BREAK; + regs->verdict.code = NFT_BREAK; } static bool nft_payload_fast_eval(const struct nft_expr *expr, - struct nft_data data[NFT_REG_MAX + 1], + struct nft_regs *regs, const struct nft_pktinfo *pkt) { const struct nft_payload *priv = nft_expr_priv(expr); const struct sk_buff *skb = pkt->skb; - struct nft_data *dest = &data[priv->dreg]; + u32 *dest = ®s->data[priv->dreg]; unsigned char *ptr; if (priv->base == NFT_PAYLOAD_NETWORK_HEADER) @@ -51,12 +94,13 @@ static bool nft_payload_fast_eval(const struct nft_expr *expr, if (unlikely(ptr + priv->len >= skb_tail_pointer(skb))) return false; + *dest = 0; if (priv->len == 2) - *(u16 *)dest->data = *(u16 *)ptr; + *(u16 *)dest = *(u16 *)ptr; else if (priv->len == 4) - *(u32 *)dest->data = *(u32 *)ptr; + *(u32 *)dest = *(u32 *)ptr; else - *(u8 *)dest->data = *(u8 *)ptr; + *(u8 *)dest = *(u8 *)ptr; return true; } @@ -66,62 +110,25 @@ struct nft_jumpstack { int rulenum; }; -enum nft_trace { - NFT_TRACE_RULE, - NFT_TRACE_RETURN, - NFT_TRACE_POLICY, -}; - -static const char *const comments[] = { - [NFT_TRACE_RULE] = "rule", - [NFT_TRACE_RETURN] = "return", - [NFT_TRACE_POLICY] = "policy", -}; - -static struct nf_loginfo trace_loginfo = { - .type = NF_LOG_TYPE_LOG, - .u = { - .log = { - .level = 4, - .logflags = NF_LOG_MASK, - }, - }, -}; - -static void nft_trace_packet(const struct nft_pktinfo *pkt, - const struct nft_chain *chain, - int rulenum, enum nft_trace type) -{ - struct net *net = dev_net(pkt->in ? pkt->in : pkt->out); - - nf_log_trace(net, pkt->xt.family, pkt->ops->hooknum, pkt->skb, pkt->in, - pkt->out, &trace_loginfo, "TRACE: %s:%s:%s:%u ", - chain->table->name, chain->name, comments[type], - rulenum); -} - unsigned int nft_do_chain(struct nft_pktinfo *pkt, const struct nf_hook_ops *ops) { const struct nft_chain *chain = ops->priv, *basechain = chain; + const struct net *net = read_pnet(&nft_base_chain(basechain)->pnet); const struct nft_rule *rule; const struct nft_expr *expr, *last; - struct nft_data data[NFT_REG_MAX + 1]; + struct nft_regs regs; unsigned int stackptr = 0; struct nft_jumpstack jumpstack[NFT_JUMP_STACK_SIZE]; struct nft_stats *stats; int rulenum; - /* - * Cache cursor to avoid problems in case that the cursor is updated - * while traversing the ruleset. - */ - unsigned int gencursor = ACCESS_ONCE(chain->net->nft.gencursor); + unsigned int gencursor = nft_genmask_cur(net); do_chain: rulenum = 0; rule = list_entry(&chain->rules, struct nft_rule, list); next_rule: - data[NFT_REG_VERDICT].verdict = NFT_CONTINUE; + regs.verdict.code = NFT_CONTINUE; list_for_each_entry_continue_rcu(rule, &chain->rules, list) { /* This rule is not active, skip. */ @@ -132,62 +139,52 @@ next_rule: nft_rule_for_each_expr(expr, last, rule) { if (expr->ops == &nft_cmp_fast_ops) - nft_cmp_fast_eval(expr, data); + nft_cmp_fast_eval(expr, ®s); else if (expr->ops != &nft_payload_fast_ops || - !nft_payload_fast_eval(expr, data, pkt)) - expr->ops->eval(expr, data, pkt); + !nft_payload_fast_eval(expr, ®s, pkt)) + expr->ops->eval(expr, ®s, pkt); - if (data[NFT_REG_VERDICT].verdict != NFT_CONTINUE) + if (regs.verdict.code != NFT_CONTINUE) break; } - switch (data[NFT_REG_VERDICT].verdict) { + switch (regs.verdict.code) { case NFT_BREAK: - data[NFT_REG_VERDICT].verdict = NFT_CONTINUE; + regs.verdict.code = NFT_CONTINUE; continue; case NFT_CONTINUE: - if (unlikely(pkt->skb->nf_trace)) - nft_trace_packet(pkt, chain, rulenum, NFT_TRACE_RULE); + nft_trace_packet(pkt, chain, rulenum, NFT_TRACE_RULE); continue; } break; } - switch (data[NFT_REG_VERDICT].verdict & NF_VERDICT_MASK) { + switch (regs.verdict.code & NF_VERDICT_MASK) { case NF_ACCEPT: case NF_DROP: case NF_QUEUE: - if (unlikely(pkt->skb->nf_trace)) - nft_trace_packet(pkt, chain, rulenum, NFT_TRACE_RULE); - - return data[NFT_REG_VERDICT].verdict; + nft_trace_packet(pkt, chain, rulenum, NFT_TRACE_RULE); + return regs.verdict.code; } - switch (data[NFT_REG_VERDICT].verdict) { + switch (regs.verdict.code) { case NFT_JUMP: - if (unlikely(pkt->skb->nf_trace)) - nft_trace_packet(pkt, chain, rulenum, NFT_TRACE_RULE); - BUG_ON(stackptr >= NFT_JUMP_STACK_SIZE); jumpstack[stackptr].chain = chain; jumpstack[stackptr].rule = rule; jumpstack[stackptr].rulenum = rulenum; stackptr++; - chain = data[NFT_REG_VERDICT].chain; - goto do_chain; + /* fall through */ case NFT_GOTO: - if (unlikely(pkt->skb->nf_trace)) - nft_trace_packet(pkt, chain, rulenum, NFT_TRACE_RULE); + nft_trace_packet(pkt, chain, rulenum, NFT_TRACE_RULE); - chain = data[NFT_REG_VERDICT].chain; + chain = regs.verdict.chain; goto do_chain; - case NFT_RETURN: - if (unlikely(pkt->skb->nf_trace)) - nft_trace_packet(pkt, chain, rulenum, NFT_TRACE_RETURN); - break; case NFT_CONTINUE: - if (unlikely(pkt->skb->nf_trace && !(chain->flags & NFT_BASE_CHAIN))) - nft_trace_packet(pkt, chain, ++rulenum, NFT_TRACE_RETURN); + rulenum++; + /* fall through */ + case NFT_RETURN: + nft_trace_packet(pkt, chain, rulenum, NFT_TRACE_RETURN); break; default: WARN_ON(1); @@ -201,8 +198,7 @@ next_rule: goto next_rule; } - if (unlikely(pkt->skb->nf_trace)) - nft_trace_packet(pkt, basechain, -1, NFT_TRACE_POLICY); + nft_trace_packet(pkt, basechain, -1, NFT_TRACE_POLICY); rcu_read_lock_bh(); stats = this_cpu_ptr(rcu_dereference(nft_base_chain(basechain)->stats)); @@ -244,8 +240,14 @@ int __init nf_tables_core_module_init(void) if (err < 0) goto err6; + err = nft_dynset_module_init(); + if (err < 0) + goto err7; + return 0; +err7: + nft_payload_module_exit(); err6: nft_byteorder_module_exit(); err5: @@ -262,6 +264,7 @@ err1: void nf_tables_core_module_exit(void) { + nft_dynset_module_exit(); nft_payload_module_exit(); nft_byteorder_module_exit(); nft_bitwise_module_exit(); diff --git a/net/netfilter/nfnetlink_log.c b/net/netfilter/nfnetlink_log.c index 11d85b3813f2..3ad91266c821 100644 --- a/net/netfilter/nfnetlink_log.c +++ b/net/netfilter/nfnetlink_log.c @@ -23,6 +23,7 @@ #include <linux/ipv6.h> #include <linux/netdevice.h> #include <linux/netfilter.h> +#include <linux/netfilter_bridge.h> #include <net/netlink.h> #include <linux/netfilter/nfnetlink.h> #include <linux/netfilter/nfnetlink_log.h> @@ -62,7 +63,7 @@ struct nfulnl_instance { struct timer_list timer; struct net *net; struct user_namespace *peer_user_ns; /* User namespace of the peer process */ - int peer_portid; /* PORTID of the peer process */ + u32 peer_portid; /* PORTID of the peer process */ /* configurable parameters */ unsigned int flushtimeout; /* timeout until queue flush */ @@ -151,7 +152,7 @@ static void nfulnl_timer(unsigned long data); static struct nfulnl_instance * instance_create(struct net *net, u_int16_t group_num, - int portid, struct user_namespace *user_ns) + u32 portid, struct user_namespace *user_ns) { struct nfulnl_instance *inst; struct nfnl_log_net *log = nfnl_log_pernet(net); @@ -448,14 +449,18 @@ __build_packet_message(struct nfnl_log_net *log, htonl(br_port_get_rcu(indev)->br->dev->ifindex))) goto nla_put_failure; } else { + struct net_device *physindev; + /* Case 2: indev is bridge group, we need to look for * physical device (when called from ipv4) */ if (nla_put_be32(inst->skb, NFULA_IFINDEX_INDEV, htonl(indev->ifindex))) goto nla_put_failure; - if (skb->nf_bridge && skb->nf_bridge->physindev && + + physindev = nf_bridge_get_physindev(skb); + if (physindev && nla_put_be32(inst->skb, NFULA_IFINDEX_PHYSINDEV, - htonl(skb->nf_bridge->physindev->ifindex))) + htonl(physindev->ifindex))) goto nla_put_failure; } #endif @@ -479,14 +484,18 @@ __build_packet_message(struct nfnl_log_net *log, htonl(br_port_get_rcu(outdev)->br->dev->ifindex))) goto nla_put_failure; } else { + struct net_device *physoutdev; + /* Case 2: indev is a bridge group, we need to look * for physical device (when called from ipv4) */ if (nla_put_be32(inst->skb, NFULA_IFINDEX_OUTDEV, htonl(outdev->ifindex))) goto nla_put_failure; - if (skb->nf_bridge && skb->nf_bridge->physoutdev && + + physoutdev = nf_bridge_get_physoutdev(skb); + if (physoutdev && nla_put_be32(inst->skb, NFULA_IFINDEX_PHYSOUTDEV, - htonl(skb->nf_bridge->physoutdev->ifindex))) + htonl(physoutdev->ifindex))) goto nla_put_failure; } #endif @@ -539,7 +548,7 @@ __build_packet_message(struct nfnl_log_net *log, /* UID */ sk = skb->sk; - if (sk && sk->sk_state != TCP_TIME_WAIT) { + if (sk && sk_fullsock(sk)) { read_lock_bh(&sk->sk_callback_lock); if (sk->sk_socket && sk->sk_socket->file) { struct file *file = sk->sk_socket->file; @@ -998,11 +1007,13 @@ static int seq_show(struct seq_file *s, void *v) { const struct nfulnl_instance *inst = v; - return seq_printf(s, "%5d %6d %5d %1d %5d %6d %2d\n", - inst->group_num, - inst->peer_portid, inst->qlen, - inst->copy_mode, inst->copy_range, - inst->flushtimeout, atomic_read(&inst->use)); + seq_printf(s, "%5u %6u %5u %1u %5u %6u %2u\n", + inst->group_num, + inst->peer_portid, inst->qlen, + inst->copy_mode, inst->copy_range, + inst->flushtimeout, atomic_read(&inst->use)); + + return 0; } static const struct seq_operations nful_seq_ops = { diff --git a/net/netfilter/nfnetlink_queue_core.c b/net/netfilter/nfnetlink_queue_core.c index 0db8515e76da..0b98c7420239 100644 --- a/net/netfilter/nfnetlink_queue_core.c +++ b/net/netfilter/nfnetlink_queue_core.c @@ -25,6 +25,7 @@ #include <linux/proc_fs.h> #include <linux/netfilter_ipv4.h> #include <linux/netfilter_ipv6.h> +#include <linux/netfilter_bridge.h> #include <linux/netfilter/nfnetlink.h> #include <linux/netfilter/nfnetlink_queue.h> #include <linux/list.h> @@ -54,7 +55,7 @@ struct nfqnl_instance { struct hlist_node hlist; /* global list of queues */ struct rcu_head rcu; - int peer_portid; + u32 peer_portid; unsigned int queue_maxlen; unsigned int copy_range; unsigned int queue_dropped; @@ -109,8 +110,7 @@ instance_lookup(struct nfnl_queue_net *q, u_int16_t queue_num) } static struct nfqnl_instance * -instance_create(struct nfnl_queue_net *q, u_int16_t queue_num, - int portid) +instance_create(struct nfnl_queue_net *q, u_int16_t queue_num, u32 portid) { struct nfqnl_instance *inst; unsigned int h; @@ -257,7 +257,7 @@ static int nfqnl_put_sk_uidgid(struct sk_buff *skb, struct sock *sk) { const struct cred *cred; - if (sk->sk_state == TCP_TIME_WAIT) + if (!sk_fullsock(sk)) return 0; read_lock_bh(&sk->sk_callback_lock); @@ -314,13 +314,13 @@ nfqnl_build_packet_message(struct net *net, struct nfqnl_instance *queue, if (entskb->tstamp.tv64) size += nla_total_size(sizeof(struct nfqnl_msg_packet_timestamp)); - if (entry->hook <= NF_INET_FORWARD || - (entry->hook == NF_INET_POST_ROUTING && entskb->sk == NULL)) + if (entry->state.hook <= NF_INET_FORWARD || + (entry->state.hook == NF_INET_POST_ROUTING && entskb->sk == NULL)) csum_verify = !skb_csum_unnecessary(entskb); else csum_verify = false; - outdev = entry->outdev; + outdev = entry->state.out; switch ((enum nfqnl_config_mode)ACCESS_ONCE(queue->copy_mode)) { case NFQNL_COPY_META: @@ -368,23 +368,23 @@ nfqnl_build_packet_message(struct net *net, struct nfqnl_instance *queue, return NULL; } nfmsg = nlmsg_data(nlh); - nfmsg->nfgen_family = entry->pf; + nfmsg->nfgen_family = entry->state.pf; nfmsg->version = NFNETLINK_V0; nfmsg->res_id = htons(queue->queue_num); nla = __nla_reserve(skb, NFQA_PACKET_HDR, sizeof(*pmsg)); pmsg = nla_data(nla); pmsg->hw_protocol = entskb->protocol; - pmsg->hook = entry->hook; + pmsg->hook = entry->state.hook; *packet_id_ptr = &pmsg->packet_id; - indev = entry->indev; + indev = entry->state.in; if (indev) { #if !IS_ENABLED(CONFIG_BRIDGE_NETFILTER) if (nla_put_be32(skb, NFQA_IFINDEX_INDEV, htonl(indev->ifindex))) goto nla_put_failure; #else - if (entry->pf == PF_BRIDGE) { + if (entry->state.pf == PF_BRIDGE) { /* Case 1: indev is physical input device, we need to * look for bridge group (when called from * netfilter_bridge) */ @@ -396,14 +396,18 @@ nfqnl_build_packet_message(struct net *net, struct nfqnl_instance *queue, htonl(br_port_get_rcu(indev)->br->dev->ifindex))) goto nla_put_failure; } else { + int physinif; + /* Case 2: indev is bridge group, we need to look for * physical device (when called from ipv4) */ if (nla_put_be32(skb, NFQA_IFINDEX_INDEV, htonl(indev->ifindex))) goto nla_put_failure; - if (entskb->nf_bridge && entskb->nf_bridge->physindev && + + physinif = nf_bridge_get_physinif(entskb); + if (physinif && nla_put_be32(skb, NFQA_IFINDEX_PHYSINDEV, - htonl(entskb->nf_bridge->physindev->ifindex))) + htonl(physinif))) goto nla_put_failure; } #endif @@ -414,7 +418,7 @@ nfqnl_build_packet_message(struct net *net, struct nfqnl_instance *queue, if (nla_put_be32(skb, NFQA_IFINDEX_OUTDEV, htonl(outdev->ifindex))) goto nla_put_failure; #else - if (entry->pf == PF_BRIDGE) { + if (entry->state.pf == PF_BRIDGE) { /* Case 1: outdev is physical output device, we need to * look for bridge group (when called from * netfilter_bridge) */ @@ -426,14 +430,18 @@ nfqnl_build_packet_message(struct net *net, struct nfqnl_instance *queue, htonl(br_port_get_rcu(outdev)->br->dev->ifindex))) goto nla_put_failure; } else { + int physoutif; + /* Case 2: outdev is bridge group, we need to look for * physical output device (when called from ipv4) */ if (nla_put_be32(skb, NFQA_IFINDEX_OUTDEV, htonl(outdev->ifindex))) goto nla_put_failure; - if (entskb->nf_bridge && entskb->nf_bridge->physoutdev && + + physoutif = nf_bridge_get_physoutif(entskb); + if (physoutif && nla_put_be32(skb, NFQA_IFINDEX_PHYSOUTDEV, - htonl(entskb->nf_bridge->physoutdev->ifindex))) + htonl(physoutif))) goto nla_put_failure; } #endif @@ -633,8 +641,8 @@ nfqnl_enqueue_packet(struct nf_queue_entry *entry, unsigned int queuenum) struct nfqnl_instance *queue; struct sk_buff *skb, *segs; int err = -ENOBUFS; - struct net *net = dev_net(entry->indev ? - entry->indev : entry->outdev); + struct net *net = dev_net(entry->state.in ? + entry->state.in : entry->state.out); struct nfnl_queue_net *q = nfnl_queue_pernet(net); /* rcu_read_lock()ed by nf_hook_slow() */ @@ -647,7 +655,7 @@ nfqnl_enqueue_packet(struct nf_queue_entry *entry, unsigned int queuenum) skb = entry->skb; - switch (entry->pf) { + switch (entry->state.pf) { case NFPROTO_IPV4: skb->protocol = htons(ETH_P_IP); break; @@ -757,19 +765,20 @@ nfqnl_set_mode(struct nfqnl_instance *queue, static int dev_cmp(struct nf_queue_entry *entry, unsigned long ifindex) { - if (entry->indev) - if (entry->indev->ifindex == ifindex) + if (entry->state.in) + if (entry->state.in->ifindex == ifindex) return 1; - if (entry->outdev) - if (entry->outdev->ifindex == ifindex) + if (entry->state.out) + if (entry->state.out->ifindex == ifindex) return 1; #if IS_ENABLED(CONFIG_BRIDGE_NETFILTER) if (entry->skb->nf_bridge) { - if (entry->skb->nf_bridge->physindev && - entry->skb->nf_bridge->physindev->ifindex == ifindex) - return 1; - if (entry->skb->nf_bridge->physoutdev && - entry->skb->nf_bridge->physoutdev->ifindex == ifindex) + int physinif, physoutif; + + physinif = nf_bridge_get_physinif(entry->skb); + physoutif = nf_bridge_get_physoutif(entry->skb); + + if (physinif == ifindex || physoutif == ifindex) return 1; } #endif @@ -860,7 +869,7 @@ static const struct nla_policy nfqa_verdict_batch_policy[NFQA_MAX+1] = { }; static struct nfqnl_instance * -verdict_instance_lookup(struct nfnl_queue_net *q, u16 queue_num, int nlportid) +verdict_instance_lookup(struct nfnl_queue_net *q, u16 queue_num, u32 nlportid) { struct nfqnl_instance *queue; @@ -1242,7 +1251,7 @@ static int seq_show(struct seq_file *s, void *v) { const struct nfqnl_instance *inst = v; - seq_printf(s, "%5d %6d %5d %1d %5d %5d %5d %8d %2d\n", + seq_printf(s, "%5u %6u %5u %1u %5u %5u %5u %8u %2d\n", inst->queue_num, inst->peer_portid, inst->queue_total, inst->copy_mode, inst->copy_range, diff --git a/net/netfilter/nft_bitwise.c b/net/netfilter/nft_bitwise.c index 4fb6ee2c1106..d71cc18fa35d 100644 --- a/net/netfilter/nft_bitwise.c +++ b/net/netfilter/nft_bitwise.c @@ -26,18 +26,16 @@ struct nft_bitwise { }; static void nft_bitwise_eval(const struct nft_expr *expr, - struct nft_data data[NFT_REG_MAX + 1], + struct nft_regs *regs, const struct nft_pktinfo *pkt) { const struct nft_bitwise *priv = nft_expr_priv(expr); - const struct nft_data *src = &data[priv->sreg]; - struct nft_data *dst = &data[priv->dreg]; + const u32 *src = ®s->data[priv->sreg]; + u32 *dst = ®s->data[priv->dreg]; unsigned int i; - for (i = 0; i < DIV_ROUND_UP(priv->len, 4); i++) { - dst->data[i] = (src->data[i] & priv->mask.data[i]) ^ - priv->xor.data[i]; - } + for (i = 0; i < DIV_ROUND_UP(priv->len, 4); i++) + dst[i] = (src[i] & priv->mask.data[i]) ^ priv->xor.data[i]; } static const struct nla_policy nft_bitwise_policy[NFTA_BITWISE_MAX + 1] = { @@ -63,28 +61,27 @@ static int nft_bitwise_init(const struct nft_ctx *ctx, tb[NFTA_BITWISE_XOR] == NULL) return -EINVAL; - priv->sreg = ntohl(nla_get_be32(tb[NFTA_BITWISE_SREG])); - err = nft_validate_input_register(priv->sreg); + priv->len = ntohl(nla_get_be32(tb[NFTA_BITWISE_LEN])); + priv->sreg = nft_parse_register(tb[NFTA_BITWISE_SREG]); + err = nft_validate_register_load(priv->sreg, priv->len); if (err < 0) return err; - priv->dreg = ntohl(nla_get_be32(tb[NFTA_BITWISE_DREG])); - err = nft_validate_output_register(priv->dreg); + priv->dreg = nft_parse_register(tb[NFTA_BITWISE_DREG]); + err = nft_validate_register_store(ctx, priv->dreg, NULL, + NFT_DATA_VALUE, priv->len); if (err < 0) return err; - err = nft_validate_data_load(ctx, priv->dreg, NULL, NFT_DATA_VALUE); - if (err < 0) - return err; - - priv->len = ntohl(nla_get_be32(tb[NFTA_BITWISE_LEN])); - err = nft_data_init(NULL, &priv->mask, &d1, tb[NFTA_BITWISE_MASK]); + err = nft_data_init(NULL, &priv->mask, sizeof(priv->mask), &d1, + tb[NFTA_BITWISE_MASK]); if (err < 0) return err; if (d1.len != priv->len) return -EINVAL; - err = nft_data_init(NULL, &priv->xor, &d2, tb[NFTA_BITWISE_XOR]); + err = nft_data_init(NULL, &priv->xor, sizeof(priv->xor), &d2, + tb[NFTA_BITWISE_XOR]); if (err < 0) return err; if (d2.len != priv->len) @@ -97,9 +94,9 @@ static int nft_bitwise_dump(struct sk_buff *skb, const struct nft_expr *expr) { const struct nft_bitwise *priv = nft_expr_priv(expr); - if (nla_put_be32(skb, NFTA_BITWISE_SREG, htonl(priv->sreg))) + if (nft_dump_register(skb, NFTA_BITWISE_SREG, priv->sreg)) goto nla_put_failure; - if (nla_put_be32(skb, NFTA_BITWISE_DREG, htonl(priv->dreg))) + if (nft_dump_register(skb, NFTA_BITWISE_DREG, priv->dreg)) goto nla_put_failure; if (nla_put_be32(skb, NFTA_BITWISE_LEN, htonl(priv->len))) goto nla_put_failure; diff --git a/net/netfilter/nft_byteorder.c b/net/netfilter/nft_byteorder.c index c39ed8d29df1..fde5145f2e36 100644 --- a/net/netfilter/nft_byteorder.c +++ b/net/netfilter/nft_byteorder.c @@ -26,16 +26,17 @@ struct nft_byteorder { }; static void nft_byteorder_eval(const struct nft_expr *expr, - struct nft_data data[NFT_REG_MAX + 1], + struct nft_regs *regs, const struct nft_pktinfo *pkt) { const struct nft_byteorder *priv = nft_expr_priv(expr); - struct nft_data *src = &data[priv->sreg], *dst = &data[priv->dreg]; + u32 *src = ®s->data[priv->sreg]; + u32 *dst = ®s->data[priv->dreg]; union { u32 u32; u16 u16; } *s, *d; unsigned int i; - s = (void *)src->data; - d = (void *)dst->data; + s = (void *)src; + d = (void *)dst; switch (priv->size) { case 4: @@ -87,19 +88,6 @@ static int nft_byteorder_init(const struct nft_ctx *ctx, tb[NFTA_BYTEORDER_OP] == NULL) return -EINVAL; - priv->sreg = ntohl(nla_get_be32(tb[NFTA_BYTEORDER_SREG])); - err = nft_validate_input_register(priv->sreg); - if (err < 0) - return err; - - priv->dreg = ntohl(nla_get_be32(tb[NFTA_BYTEORDER_DREG])); - err = nft_validate_output_register(priv->dreg); - if (err < 0) - return err; - err = nft_validate_data_load(ctx, priv->dreg, NULL, NFT_DATA_VALUE); - if (err < 0) - return err; - priv->op = ntohl(nla_get_be32(tb[NFTA_BYTEORDER_OP])); switch (priv->op) { case NFT_BYTEORDER_NTOH: @@ -109,10 +97,6 @@ static int nft_byteorder_init(const struct nft_ctx *ctx, return -EINVAL; } - priv->len = ntohl(nla_get_be32(tb[NFTA_BYTEORDER_LEN])); - if (priv->len == 0 || priv->len > FIELD_SIZEOF(struct nft_data, data)) - return -EINVAL; - priv->size = ntohl(nla_get_be32(tb[NFTA_BYTEORDER_SIZE])); switch (priv->size) { case 2: @@ -122,16 +106,24 @@ static int nft_byteorder_init(const struct nft_ctx *ctx, return -EINVAL; } - return 0; + priv->sreg = nft_parse_register(tb[NFTA_BYTEORDER_SREG]); + priv->len = ntohl(nla_get_be32(tb[NFTA_BYTEORDER_LEN])); + err = nft_validate_register_load(priv->sreg, priv->len); + if (err < 0) + return err; + + priv->dreg = nft_parse_register(tb[NFTA_BYTEORDER_DREG]); + return nft_validate_register_store(ctx, priv->dreg, NULL, + NFT_DATA_VALUE, priv->len); } static int nft_byteorder_dump(struct sk_buff *skb, const struct nft_expr *expr) { const struct nft_byteorder *priv = nft_expr_priv(expr); - if (nla_put_be32(skb, NFTA_BYTEORDER_SREG, htonl(priv->sreg))) + if (nft_dump_register(skb, NFTA_BYTEORDER_SREG, priv->sreg)) goto nla_put_failure; - if (nla_put_be32(skb, NFTA_BYTEORDER_DREG, htonl(priv->dreg))) + if (nft_dump_register(skb, NFTA_BYTEORDER_DREG, priv->dreg)) goto nla_put_failure; if (nla_put_be32(skb, NFTA_BYTEORDER_OP, htonl(priv->op))) goto nla_put_failure; diff --git a/net/netfilter/nft_cmp.c b/net/netfilter/nft_cmp.c index e2b3f51c81f1..e25b35d70e4d 100644 --- a/net/netfilter/nft_cmp.c +++ b/net/netfilter/nft_cmp.c @@ -25,13 +25,13 @@ struct nft_cmp_expr { }; static void nft_cmp_eval(const struct nft_expr *expr, - struct nft_data data[NFT_REG_MAX + 1], + struct nft_regs *regs, const struct nft_pktinfo *pkt) { const struct nft_cmp_expr *priv = nft_expr_priv(expr); int d; - d = nft_data_cmp(&data[priv->sreg], &priv->data, priv->len); + d = memcmp(®s->data[priv->sreg], &priv->data, priv->len); switch (priv->op) { case NFT_CMP_EQ: if (d != 0) @@ -59,7 +59,7 @@ static void nft_cmp_eval(const struct nft_expr *expr, return; mismatch: - data[NFT_REG_VERDICT].verdict = NFT_BREAK; + regs->verdict.code = NFT_BREAK; } static const struct nla_policy nft_cmp_policy[NFTA_CMP_MAX + 1] = { @@ -75,12 +75,16 @@ static int nft_cmp_init(const struct nft_ctx *ctx, const struct nft_expr *expr, struct nft_data_desc desc; int err; - priv->sreg = ntohl(nla_get_be32(tb[NFTA_CMP_SREG])); - priv->op = ntohl(nla_get_be32(tb[NFTA_CMP_OP])); - - err = nft_data_init(NULL, &priv->data, &desc, tb[NFTA_CMP_DATA]); + err = nft_data_init(NULL, &priv->data, sizeof(priv->data), &desc, + tb[NFTA_CMP_DATA]); BUG_ON(err < 0); + priv->sreg = nft_parse_register(tb[NFTA_CMP_SREG]); + err = nft_validate_register_load(priv->sreg, desc.len); + if (err < 0) + return err; + + priv->op = ntohl(nla_get_be32(tb[NFTA_CMP_OP])); priv->len = desc.len; return 0; } @@ -89,7 +93,7 @@ static int nft_cmp_dump(struct sk_buff *skb, const struct nft_expr *expr) { const struct nft_cmp_expr *priv = nft_expr_priv(expr); - if (nla_put_be32(skb, NFTA_CMP_SREG, htonl(priv->sreg))) + if (nft_dump_register(skb, NFTA_CMP_SREG, priv->sreg)) goto nla_put_failure; if (nla_put_be32(skb, NFTA_CMP_OP, htonl(priv->op))) goto nla_put_failure; @@ -122,13 +126,18 @@ static int nft_cmp_fast_init(const struct nft_ctx *ctx, u32 mask; int err; - priv->sreg = ntohl(nla_get_be32(tb[NFTA_CMP_SREG])); - - err = nft_data_init(NULL, &data, &desc, tb[NFTA_CMP_DATA]); + err = nft_data_init(NULL, &data, sizeof(data), &desc, + tb[NFTA_CMP_DATA]); BUG_ON(err < 0); - desc.len *= BITS_PER_BYTE; + priv->sreg = nft_parse_register(tb[NFTA_CMP_SREG]); + err = nft_validate_register_load(priv->sreg, desc.len); + if (err < 0) + return err; + + desc.len *= BITS_PER_BYTE; mask = nft_cmp_fast_mask(desc.len); + priv->data = data.data[0] & mask; priv->len = desc.len; return 0; @@ -139,7 +148,7 @@ static int nft_cmp_fast_dump(struct sk_buff *skb, const struct nft_expr *expr) const struct nft_cmp_fast_expr *priv = nft_expr_priv(expr); struct nft_data data; - if (nla_put_be32(skb, NFTA_CMP_SREG, htonl(priv->sreg))) + if (nft_dump_register(skb, NFTA_CMP_SREG, priv->sreg)) goto nla_put_failure; if (nla_put_be32(skb, NFTA_CMP_OP, htonl(NFT_CMP_EQ))) goto nla_put_failure; @@ -167,7 +176,6 @@ nft_cmp_select_ops(const struct nft_ctx *ctx, const struct nlattr * const tb[]) { struct nft_data_desc desc; struct nft_data data; - enum nft_registers sreg; enum nft_cmp_ops op; int err; @@ -176,11 +184,6 @@ nft_cmp_select_ops(const struct nft_ctx *ctx, const struct nlattr * const tb[]) tb[NFTA_CMP_DATA] == NULL) return ERR_PTR(-EINVAL); - sreg = ntohl(nla_get_be32(tb[NFTA_CMP_SREG])); - err = nft_validate_input_register(sreg); - if (err < 0) - return ERR_PTR(err); - op = ntohl(nla_get_be32(tb[NFTA_CMP_OP])); switch (op) { case NFT_CMP_EQ: @@ -194,7 +197,8 @@ nft_cmp_select_ops(const struct nft_ctx *ctx, const struct nlattr * const tb[]) return ERR_PTR(-EINVAL); } - err = nft_data_init(NULL, &data, &desc, tb[NFTA_CMP_DATA]); + err = nft_data_init(NULL, &data, sizeof(data), &desc, + tb[NFTA_CMP_DATA]); if (err < 0) return ERR_PTR(err); diff --git a/net/netfilter/nft_compat.c b/net/netfilter/nft_compat.c index 65f3e2b6be44..7f29cfc76349 100644 --- a/net/netfilter/nft_compat.c +++ b/net/netfilter/nft_compat.c @@ -20,6 +20,7 @@ #include <linux/netfilter_ipv4/ip_tables.h> #include <linux/netfilter_ipv6/ip6_tables.h> #include <linux/netfilter_bridge/ebtables.h> +#include <linux/netfilter_arp/arp_tables.h> #include <net/netfilter/nf_tables.h> static int nft_compat_chain_validate_dependency(const char *tablename, @@ -42,6 +43,7 @@ union nft_entry { struct ipt_entry e4; struct ip6t_entry e6; struct ebt_entry ebt; + struct arpt_entry arp; }; static inline void @@ -53,7 +55,7 @@ nft_compat_set_par(struct xt_action_param *par, void *xt, const void *xt_info) } static void nft_target_eval_xt(const struct nft_expr *expr, - struct nft_data data[NFT_REG_MAX + 1], + struct nft_regs *regs, const struct nft_pktinfo *pkt) { void *info = nft_expr_priv(expr); @@ -70,16 +72,16 @@ static void nft_target_eval_xt(const struct nft_expr *expr, switch (ret) { case XT_CONTINUE: - data[NFT_REG_VERDICT].verdict = NFT_CONTINUE; + regs->verdict.code = NFT_CONTINUE; break; default: - data[NFT_REG_VERDICT].verdict = ret; + regs->verdict.code = ret; break; } } static void nft_target_eval_bridge(const struct nft_expr *expr, - struct nft_data data[NFT_REG_MAX + 1], + struct nft_regs *regs, const struct nft_pktinfo *pkt) { void *info = nft_expr_priv(expr); @@ -96,19 +98,19 @@ static void nft_target_eval_bridge(const struct nft_expr *expr, switch (ret) { case EBT_ACCEPT: - data[NFT_REG_VERDICT].verdict = NF_ACCEPT; + regs->verdict.code = NF_ACCEPT; break; case EBT_DROP: - data[NFT_REG_VERDICT].verdict = NF_DROP; + regs->verdict.code = NF_DROP; break; case EBT_CONTINUE: - data[NFT_REG_VERDICT].verdict = NFT_CONTINUE; + regs->verdict.code = NFT_CONTINUE; break; case EBT_RETURN: - data[NFT_REG_VERDICT].verdict = NFT_RETURN; + regs->verdict.code = NFT_RETURN; break; default: - data[NFT_REG_VERDICT].verdict = ret; + regs->verdict.code = ret; break; } } @@ -143,6 +145,8 @@ nft_target_set_tgchk_param(struct xt_tgchk_param *par, entry->ebt.ethproto = (__force __be16)proto; entry->ebt.invflags = inv ? EBT_IPROTO : 0; break; + case NFPROTO_ARP: + break; } par->entryinfo = entry; par->target = target; @@ -300,7 +304,7 @@ static int nft_target_validate(const struct nft_ctx *ctx, } static void nft_match_eval(const struct nft_expr *expr, - struct nft_data data[NFT_REG_MAX + 1], + struct nft_regs *regs, const struct nft_pktinfo *pkt) { void *info = nft_expr_priv(expr); @@ -313,16 +317,16 @@ static void nft_match_eval(const struct nft_expr *expr, ret = match->match(skb, (struct xt_action_param *)&pkt->xt); if (pkt->xt.hotdrop) { - data[NFT_REG_VERDICT].verdict = NF_DROP; + regs->verdict.code = NF_DROP; return; } - switch(ret) { - case true: - data[NFT_REG_VERDICT].verdict = NFT_CONTINUE; + switch (ret ? 1 : 0) { + case 1: + regs->verdict.code = NFT_CONTINUE; break; - case false: - data[NFT_REG_VERDICT].verdict = NFT_BREAK; + case 0: + regs->verdict.code = NFT_BREAK; break; } } @@ -357,6 +361,8 @@ nft_match_set_mtchk_param(struct xt_mtchk_param *par, const struct nft_ctx *ctx, entry->ebt.ethproto = (__force __be16)proto; entry->ebt.invflags = inv ? EBT_IPROTO : 0; break; + case NFPROTO_ARP: + break; } par->entryinfo = entry; par->match = match; @@ -543,6 +549,9 @@ nfnl_compat_get(struct sock *nfnl, struct sk_buff *skb, case NFPROTO_BRIDGE: fmt = "ebt_%s"; break; + case NFPROTO_ARP: + fmt = "arpt_%s"; + break; default: pr_err("nft_compat: unsupported protocol %d\n", nfmsg->nfgen_family); diff --git a/net/netfilter/nft_counter.c b/net/netfilter/nft_counter.c index c89ee486ce54..17591239229f 100644 --- a/net/netfilter/nft_counter.c +++ b/net/netfilter/nft_counter.c @@ -24,7 +24,7 @@ struct nft_counter { }; static void nft_counter_eval(const struct nft_expr *expr, - struct nft_data data[NFT_REG_MAX + 1], + struct nft_regs *regs, const struct nft_pktinfo *pkt) { struct nft_counter *priv = nft_expr_priv(expr); @@ -92,6 +92,7 @@ static struct nft_expr_type nft_counter_type __read_mostly = { .ops = &nft_counter_ops, .policy = nft_counter_policy, .maxattr = NFTA_COUNTER_MAX, + .flags = NFT_EXPR_STATEFUL, .owner = THIS_MODULE, }; diff --git a/net/netfilter/nft_ct.c b/net/netfilter/nft_ct.c index cc5603016242..8cbca3432f90 100644 --- a/net/netfilter/nft_ct.c +++ b/net/netfilter/nft_ct.c @@ -31,11 +31,11 @@ struct nft_ct { }; static void nft_ct_get_eval(const struct nft_expr *expr, - struct nft_data data[NFT_REG_MAX + 1], + struct nft_regs *regs, const struct nft_pktinfo *pkt) { const struct nft_ct *priv = nft_expr_priv(expr); - struct nft_data *dest = &data[priv->dreg]; + u32 *dest = ®s->data[priv->dreg]; enum ip_conntrack_info ctinfo; const struct nf_conn *ct; const struct nf_conn_help *help; @@ -54,8 +54,10 @@ static void nft_ct_get_eval(const struct nft_expr *expr, state = NF_CT_STATE_UNTRACKED_BIT; else state = NF_CT_STATE_BIT(ctinfo); - dest->data[0] = state; + *dest = state; return; + default: + break; } if (ct == NULL) @@ -63,26 +65,26 @@ static void nft_ct_get_eval(const struct nft_expr *expr, switch (priv->key) { case NFT_CT_DIRECTION: - dest->data[0] = CTINFO2DIR(ctinfo); + *dest = CTINFO2DIR(ctinfo); return; case NFT_CT_STATUS: - dest->data[0] = ct->status; + *dest = ct->status; return; #ifdef CONFIG_NF_CONNTRACK_MARK case NFT_CT_MARK: - dest->data[0] = ct->mark; + *dest = ct->mark; return; #endif #ifdef CONFIG_NF_CONNTRACK_SECMARK case NFT_CT_SECMARK: - dest->data[0] = ct->secmark; + *dest = ct->secmark; return; #endif case NFT_CT_EXPIRATION: diff = (long)jiffies - (long)ct->timeout.expires; if (diff < 0) diff = 0; - dest->data[0] = jiffies_to_msecs(diff); + *dest = jiffies_to_msecs(diff); return; case NFT_CT_HELPER: if (ct->master == NULL) @@ -93,9 +95,7 @@ static void nft_ct_get_eval(const struct nft_expr *expr, helper = rcu_dereference(help->helper); if (helper == NULL) goto err; - if (strlen(helper->name) >= sizeof(dest->data)) - goto err; - strncpy((char *)dest->data, helper->name, sizeof(dest->data)); + strncpy((char *)dest, helper->name, NF_CT_HELPER_NAME_LEN); return; #ifdef CONFIG_NF_CONNTRACK_LABELS case NFT_CT_LABELS: { @@ -103,58 +103,60 @@ static void nft_ct_get_eval(const struct nft_expr *expr, unsigned int size; if (!labels) { - memset(dest->data, 0, sizeof(dest->data)); + memset(dest, 0, NF_CT_LABELS_MAX_SIZE); return; } - BUILD_BUG_ON(NF_CT_LABELS_MAX_SIZE > sizeof(dest->data)); size = labels->words * sizeof(long); - - memcpy(dest->data, labels->bits, size); - if (size < sizeof(dest->data)) - memset(((char *) dest->data) + size, 0, - sizeof(dest->data) - size); + memcpy(dest, labels->bits, size); + if (size < NF_CT_LABELS_MAX_SIZE) + memset(((char *) dest) + size, 0, + NF_CT_LABELS_MAX_SIZE - size); return; } #endif + default: + break; } tuple = &ct->tuplehash[priv->dir].tuple; switch (priv->key) { case NFT_CT_L3PROTOCOL: - dest->data[0] = nf_ct_l3num(ct); + *dest = nf_ct_l3num(ct); return; case NFT_CT_SRC: - memcpy(dest->data, tuple->src.u3.all, + memcpy(dest, tuple->src.u3.all, nf_ct_l3num(ct) == NFPROTO_IPV4 ? 4 : 16); return; case NFT_CT_DST: - memcpy(dest->data, tuple->dst.u3.all, + memcpy(dest, tuple->dst.u3.all, nf_ct_l3num(ct) == NFPROTO_IPV4 ? 4 : 16); return; case NFT_CT_PROTOCOL: - dest->data[0] = nf_ct_protonum(ct); + *dest = nf_ct_protonum(ct); return; case NFT_CT_PROTO_SRC: - dest->data[0] = (__force __u16)tuple->src.u.all; + *dest = (__force __u16)tuple->src.u.all; return; case NFT_CT_PROTO_DST: - dest->data[0] = (__force __u16)tuple->dst.u.all; + *dest = (__force __u16)tuple->dst.u.all; return; + default: + break; } return; err: - data[NFT_REG_VERDICT].verdict = NFT_BREAK; + regs->verdict.code = NFT_BREAK; } static void nft_ct_set_eval(const struct nft_expr *expr, - struct nft_data data[NFT_REG_MAX + 1], + struct nft_regs *regs, const struct nft_pktinfo *pkt) { const struct nft_ct *priv = nft_expr_priv(expr); struct sk_buff *skb = pkt->skb; #ifdef CONFIG_NF_CONNTRACK_MARK - u32 value = data[priv->sreg].data[0]; + u32 value = regs->data[priv->sreg]; #endif enum ip_conntrack_info ctinfo; struct nf_conn *ct; @@ -172,6 +174,8 @@ static void nft_ct_set_eval(const struct nft_expr *expr, } break; #endif + default: + break; } } @@ -220,12 +224,17 @@ static int nft_ct_get_init(const struct nft_ctx *ctx, const struct nlattr * const tb[]) { struct nft_ct *priv = nft_expr_priv(expr); + unsigned int len; int err; priv->key = ntohl(nla_get_be32(tb[NFTA_CT_KEY])); switch (priv->key) { - case NFT_CT_STATE: case NFT_CT_DIRECTION: + if (tb[NFTA_CT_DIRECTION] != NULL) + return -EINVAL; + len = sizeof(u8); + break; + case NFT_CT_STATE: case NFT_CT_STATUS: #ifdef CONFIG_NF_CONNTRACK_MARK case NFT_CT_MARK: @@ -233,22 +242,54 @@ static int nft_ct_get_init(const struct nft_ctx *ctx, #ifdef CONFIG_NF_CONNTRACK_SECMARK case NFT_CT_SECMARK: #endif + case NFT_CT_EXPIRATION: + if (tb[NFTA_CT_DIRECTION] != NULL) + return -EINVAL; + len = sizeof(u32); + break; #ifdef CONFIG_NF_CONNTRACK_LABELS case NFT_CT_LABELS: + if (tb[NFTA_CT_DIRECTION] != NULL) + return -EINVAL; + len = NF_CT_LABELS_MAX_SIZE; + break; #endif - case NFT_CT_EXPIRATION: case NFT_CT_HELPER: if (tb[NFTA_CT_DIRECTION] != NULL) return -EINVAL; + len = NF_CT_HELPER_NAME_LEN; break; + case NFT_CT_L3PROTOCOL: case NFT_CT_PROTOCOL: + if (tb[NFTA_CT_DIRECTION] == NULL) + return -EINVAL; + len = sizeof(u8); + break; case NFT_CT_SRC: case NFT_CT_DST: + if (tb[NFTA_CT_DIRECTION] == NULL) + return -EINVAL; + + switch (ctx->afi->family) { + case NFPROTO_IPV4: + len = FIELD_SIZEOF(struct nf_conntrack_tuple, + src.u3.ip); + break; + case NFPROTO_IPV6: + case NFPROTO_INET: + len = FIELD_SIZEOF(struct nf_conntrack_tuple, + src.u3.ip6); + break; + default: + return -EAFNOSUPPORT; + } + break; case NFT_CT_PROTO_SRC: case NFT_CT_PROTO_DST: if (tb[NFTA_CT_DIRECTION] == NULL) return -EINVAL; + len = FIELD_SIZEOF(struct nf_conntrack_tuple, src.u.all); break; default: return -EOPNOTSUPP; @@ -265,12 +306,9 @@ static int nft_ct_get_init(const struct nft_ctx *ctx, } } - priv->dreg = ntohl(nla_get_be32(tb[NFTA_CT_DREG])); - err = nft_validate_output_register(priv->dreg); - if (err < 0) - return err; - - err = nft_validate_data_load(ctx, priv->dreg, NULL, NFT_DATA_VALUE); + priv->dreg = nft_parse_register(tb[NFTA_CT_DREG]); + err = nft_validate_register_store(ctx, priv->dreg, NULL, + NFT_DATA_VALUE, len); if (err < 0) return err; @@ -286,20 +324,22 @@ static int nft_ct_set_init(const struct nft_ctx *ctx, const struct nlattr * const tb[]) { struct nft_ct *priv = nft_expr_priv(expr); + unsigned int len; int err; priv->key = ntohl(nla_get_be32(tb[NFTA_CT_KEY])); switch (priv->key) { #ifdef CONFIG_NF_CONNTRACK_MARK case NFT_CT_MARK: + len = FIELD_SIZEOF(struct nf_conn, mark); break; #endif default: return -EOPNOTSUPP; } - priv->sreg = ntohl(nla_get_be32(tb[NFTA_CT_SREG])); - err = nft_validate_input_register(priv->sreg); + priv->sreg = nft_parse_register(tb[NFTA_CT_SREG]); + err = nft_validate_register_load(priv->sreg, len); if (err < 0) return err; @@ -320,7 +360,7 @@ static int nft_ct_get_dump(struct sk_buff *skb, const struct nft_expr *expr) { const struct nft_ct *priv = nft_expr_priv(expr); - if (nla_put_be32(skb, NFTA_CT_DREG, htonl(priv->dreg))) + if (nft_dump_register(skb, NFTA_CT_DREG, priv->dreg)) goto nla_put_failure; if (nla_put_be32(skb, NFTA_CT_KEY, htonl(priv->key))) goto nla_put_failure; @@ -347,7 +387,7 @@ static int nft_ct_set_dump(struct sk_buff *skb, const struct nft_expr *expr) { const struct nft_ct *priv = nft_expr_priv(expr); - if (nla_put_be32(skb, NFTA_CT_SREG, htonl(priv->sreg))) + if (nft_dump_register(skb, NFTA_CT_SREG, priv->sreg)) goto nla_put_failure; if (nla_put_be32(skb, NFTA_CT_KEY, htonl(priv->key))) goto nla_put_failure; diff --git a/net/netfilter/nft_dynset.c b/net/netfilter/nft_dynset.c new file mode 100644 index 000000000000..513a8ef60a59 --- /dev/null +++ b/net/netfilter/nft_dynset.c @@ -0,0 +1,265 @@ +/* + * Copyright (c) 2015 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. + * + */ + +#include <linux/kernel.h> +#include <linux/module.h> +#include <linux/init.h> +#include <linux/netlink.h> +#include <linux/netfilter.h> +#include <linux/netfilter/nf_tables.h> +#include <net/netfilter/nf_tables.h> +#include <net/netfilter/nf_tables_core.h> + +struct nft_dynset { + struct nft_set *set; + struct nft_set_ext_tmpl tmpl; + enum nft_dynset_ops op:8; + enum nft_registers sreg_key:8; + enum nft_registers sreg_data:8; + u64 timeout; + struct nft_expr *expr; + struct nft_set_binding binding; +}; + +static void *nft_dynset_new(struct nft_set *set, const struct nft_expr *expr, + struct nft_regs *regs) +{ + const struct nft_dynset *priv = nft_expr_priv(expr); + struct nft_set_ext *ext; + u64 timeout; + void *elem; + + if (set->size && !atomic_add_unless(&set->nelems, 1, set->size)) + return NULL; + + timeout = priv->timeout ? : set->timeout; + elem = nft_set_elem_init(set, &priv->tmpl, + ®s->data[priv->sreg_key], + ®s->data[priv->sreg_data], + timeout, GFP_ATOMIC); + if (elem == NULL) { + if (set->size) + atomic_dec(&set->nelems); + return NULL; + } + + ext = nft_set_elem_ext(set, elem); + if (priv->expr != NULL) + nft_expr_clone(nft_set_ext_expr(ext), priv->expr); + + return elem; +} + +static void nft_dynset_eval(const struct nft_expr *expr, + struct nft_regs *regs, + const struct nft_pktinfo *pkt) +{ + const struct nft_dynset *priv = nft_expr_priv(expr); + struct nft_set *set = priv->set; + const struct nft_set_ext *ext; + const struct nft_expr *sexpr; + u64 timeout; + + if (set->ops->update(set, ®s->data[priv->sreg_key], nft_dynset_new, + expr, regs, &ext)) { + sexpr = NULL; + if (nft_set_ext_exists(ext, NFT_SET_EXT_EXPR)) + sexpr = nft_set_ext_expr(ext); + + if (priv->op == NFT_DYNSET_OP_UPDATE && + nft_set_ext_exists(ext, NFT_SET_EXT_EXPIRATION)) { + timeout = priv->timeout ? : set->timeout; + *nft_set_ext_expiration(ext) = jiffies + timeout; + } else if (sexpr == NULL) + goto out; + + if (sexpr != NULL) + sexpr->ops->eval(sexpr, regs, pkt); + return; + } +out: + regs->verdict.code = NFT_BREAK; +} + +static const struct nla_policy nft_dynset_policy[NFTA_DYNSET_MAX + 1] = { + [NFTA_DYNSET_SET_NAME] = { .type = NLA_STRING }, + [NFTA_DYNSET_SET_ID] = { .type = NLA_U32 }, + [NFTA_DYNSET_OP] = { .type = NLA_U32 }, + [NFTA_DYNSET_SREG_KEY] = { .type = NLA_U32 }, + [NFTA_DYNSET_SREG_DATA] = { .type = NLA_U32 }, + [NFTA_DYNSET_TIMEOUT] = { .type = NLA_U64 }, + [NFTA_DYNSET_EXPR] = { .type = NLA_NESTED }, +}; + +static int nft_dynset_init(const struct nft_ctx *ctx, + const struct nft_expr *expr, + const struct nlattr * const tb[]) +{ + struct nft_dynset *priv = nft_expr_priv(expr); + struct nft_set *set; + u64 timeout; + int err; + + if (tb[NFTA_DYNSET_SET_NAME] == NULL || + tb[NFTA_DYNSET_OP] == NULL || + tb[NFTA_DYNSET_SREG_KEY] == NULL) + return -EINVAL; + + set = nf_tables_set_lookup(ctx->table, tb[NFTA_DYNSET_SET_NAME]); + if (IS_ERR(set)) { + if (tb[NFTA_DYNSET_SET_ID]) + set = nf_tables_set_lookup_byid(ctx->net, + tb[NFTA_DYNSET_SET_ID]); + if (IS_ERR(set)) + return PTR_ERR(set); + } + + if (set->flags & NFT_SET_CONSTANT) + return -EBUSY; + + priv->op = ntohl(nla_get_be32(tb[NFTA_DYNSET_OP])); + switch (priv->op) { + case NFT_DYNSET_OP_ADD: + break; + case NFT_DYNSET_OP_UPDATE: + if (!(set->flags & NFT_SET_TIMEOUT)) + return -EOPNOTSUPP; + break; + default: + return -EOPNOTSUPP; + } + + timeout = 0; + if (tb[NFTA_DYNSET_TIMEOUT] != NULL) { + if (!(set->flags & NFT_SET_TIMEOUT)) + return -EINVAL; + timeout = be64_to_cpu(nla_get_be64(tb[NFTA_DYNSET_TIMEOUT])); + } + + priv->sreg_key = nft_parse_register(tb[NFTA_DYNSET_SREG_KEY]); + err = nft_validate_register_load(priv->sreg_key, set->klen);; + if (err < 0) + return err; + + if (tb[NFTA_DYNSET_SREG_DATA] != NULL) { + if (!(set->flags & NFT_SET_MAP)) + return -EINVAL; + if (set->dtype == NFT_DATA_VERDICT) + return -EOPNOTSUPP; + + priv->sreg_data = nft_parse_register(tb[NFTA_DYNSET_SREG_DATA]); + err = nft_validate_register_load(priv->sreg_data, set->dlen); + if (err < 0) + return err; + } else if (set->flags & NFT_SET_MAP) + return -EINVAL; + + if (tb[NFTA_DYNSET_EXPR] != NULL) { + if (!(set->flags & NFT_SET_EVAL)) + return -EINVAL; + if (!(set->flags & NFT_SET_ANONYMOUS)) + return -EOPNOTSUPP; + + priv->expr = nft_expr_init(ctx, tb[NFTA_DYNSET_EXPR]); + if (IS_ERR(priv->expr)) + return PTR_ERR(priv->expr); + + err = -EOPNOTSUPP; + if (!(priv->expr->ops->type->flags & NFT_EXPR_STATEFUL)) + goto err1; + } else if (set->flags & NFT_SET_EVAL) + return -EINVAL; + + nft_set_ext_prepare(&priv->tmpl); + nft_set_ext_add_length(&priv->tmpl, NFT_SET_EXT_KEY, set->klen); + if (set->flags & NFT_SET_MAP) + nft_set_ext_add_length(&priv->tmpl, NFT_SET_EXT_DATA, set->dlen); + if (priv->expr != NULL) + nft_set_ext_add_length(&priv->tmpl, NFT_SET_EXT_EXPR, + priv->expr->ops->size); + if (set->flags & NFT_SET_TIMEOUT) { + if (timeout || set->timeout) + nft_set_ext_add(&priv->tmpl, NFT_SET_EXT_EXPIRATION); + } + + priv->timeout = timeout; + + err = nf_tables_bind_set(ctx, set, &priv->binding); + if (err < 0) + goto err1; + + priv->set = set; + return 0; + +err1: + if (priv->expr != NULL) + nft_expr_destroy(ctx, priv->expr); + return err; +} + +static void nft_dynset_destroy(const struct nft_ctx *ctx, + const struct nft_expr *expr) +{ + struct nft_dynset *priv = nft_expr_priv(expr); + + nf_tables_unbind_set(ctx, priv->set, &priv->binding); + if (priv->expr != NULL) + nft_expr_destroy(ctx, priv->expr); +} + +static int nft_dynset_dump(struct sk_buff *skb, const struct nft_expr *expr) +{ + const struct nft_dynset *priv = nft_expr_priv(expr); + + if (nft_dump_register(skb, NFTA_DYNSET_SREG_KEY, priv->sreg_key)) + goto nla_put_failure; + if (priv->set->flags & NFT_SET_MAP && + nft_dump_register(skb, NFTA_DYNSET_SREG_DATA, priv->sreg_data)) + goto nla_put_failure; + if (nla_put_be32(skb, NFTA_DYNSET_OP, htonl(priv->op))) + goto nla_put_failure; + if (nla_put_string(skb, NFTA_DYNSET_SET_NAME, priv->set->name)) + goto nla_put_failure; + if (nla_put_be64(skb, NFTA_DYNSET_TIMEOUT, cpu_to_be64(priv->timeout))) + goto nla_put_failure; + if (priv->expr && nft_expr_dump(skb, NFTA_DYNSET_EXPR, priv->expr)) + goto nla_put_failure; + return 0; + +nla_put_failure: + return -1; +} + +static struct nft_expr_type nft_dynset_type; +static const struct nft_expr_ops nft_dynset_ops = { + .type = &nft_dynset_type, + .size = NFT_EXPR_SIZE(sizeof(struct nft_dynset)), + .eval = nft_dynset_eval, + .init = nft_dynset_init, + .destroy = nft_dynset_destroy, + .dump = nft_dynset_dump, +}; + +static struct nft_expr_type nft_dynset_type __read_mostly = { + .name = "dynset", + .ops = &nft_dynset_ops, + .policy = nft_dynset_policy, + .maxattr = NFTA_DYNSET_MAX, + .owner = THIS_MODULE, +}; + +int __init nft_dynset_module_init(void) +{ + return nft_register_expr(&nft_dynset_type); +} + +void nft_dynset_module_exit(void) +{ + nft_unregister_expr(&nft_dynset_type); +} diff --git a/net/netfilter/nft_expr_template.c b/net/netfilter/nft_expr_template.c deleted file mode 100644 index b6eed4d5a096..000000000000 --- a/net/netfilter/nft_expr_template.c +++ /dev/null @@ -1,94 +0,0 @@ -/* - * Copyright (c) 2008-2009 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. - * - * Development of this code funded by Astaro AG (http://www.astaro.com/) - */ - -#include <linux/kernel.h> -#include <linux/init.h> -#include <linux/netlink.h> -#include <linux/netfilter.h> -#include <linux/netfilter/nf_tables.h> -#include <net/netfilter/nf_tables.h> - -struct nft_template { - -}; - -static void nft_template_eval(const struct nft_expr *expr, - struct nft_data data[NFT_REG_MAX + 1], - const struct nft_pktinfo *pkt) -{ - struct nft_template *priv = nft_expr_priv(expr); - -} - -static const struct nla_policy nft_template_policy[NFTA_TEMPLATE_MAX + 1] = { - [NFTA_TEMPLATE_ATTR] = { .type = NLA_U32 }, -}; - -static int nft_template_init(const struct nft_ctx *ctx, - const struct nft_expr *expr, - const struct nlattr * const tb[]) -{ - struct nft_template *priv = nft_expr_priv(expr); - - return 0; -} - -static void nft_template_destroy(const struct nft_ctx *ctx, - const struct nft_expr *expr) -{ - struct nft_template *priv = nft_expr_priv(expr); - -} - -static int nft_template_dump(struct sk_buff *skb, const struct nft_expr *expr) -{ - const struct nft_template *priv = nft_expr_priv(expr); - - NLA_PUT_BE32(skb, NFTA_TEMPLATE_ATTR, priv->field); - return 0; - -nla_put_failure: - return -1; -} - -static struct nft_expr_type nft_template_type; -static const struct nft_expr_ops nft_template_ops = { - .type = &nft_template_type, - .size = NFT_EXPR_SIZE(sizeof(struct nft_template)), - .eval = nft_template_eval, - .init = nft_template_init, - .destroy = nft_template_destroy, - .dump = nft_template_dump, -}; - -static struct nft_expr_type nft_template_type __read_mostly = { - .name = "template", - .ops = &nft_template_ops, - .policy = nft_template_policy, - .maxattr = NFTA_TEMPLATE_MAX, - .owner = THIS_MODULE, -}; - -static int __init nft_template_module_init(void) -{ - return nft_register_expr(&nft_template_type); -} - -static void __exit nft_template_module_exit(void) -{ - nft_unregister_expr(&nft_template_type); -} - -module_init(nft_template_module_init); -module_exit(nft_template_module_exit); - -MODULE_LICENSE("GPL"); -MODULE_AUTHOR("Patrick McHardy <kaber@trash.net>"); -MODULE_ALIAS_NFT_EXPR("template"); diff --git a/net/netfilter/nft_exthdr.c b/net/netfilter/nft_exthdr.c index 55c939f5371f..ba7aed13e174 100644 --- a/net/netfilter/nft_exthdr.c +++ b/net/netfilter/nft_exthdr.c @@ -26,11 +26,11 @@ struct nft_exthdr { }; static void nft_exthdr_eval(const struct nft_expr *expr, - struct nft_data data[NFT_REG_MAX + 1], + struct nft_regs *regs, const struct nft_pktinfo *pkt) { struct nft_exthdr *priv = nft_expr_priv(expr); - struct nft_data *dest = &data[priv->dreg]; + u32 *dest = ®s->data[priv->dreg]; unsigned int offset = 0; int err; @@ -39,11 +39,12 @@ static void nft_exthdr_eval(const struct nft_expr *expr, goto err; offset += priv->offset; - if (skb_copy_bits(pkt->skb, offset, dest->data, priv->len) < 0) + dest[priv->len / NFT_REG32_SIZE] = 0; + if (skb_copy_bits(pkt->skb, offset, dest, priv->len) < 0) goto err; return; err: - data[NFT_REG_VERDICT].verdict = NFT_BREAK; + regs->verdict.code = NFT_BREAK; } static const struct nla_policy nft_exthdr_policy[NFTA_EXTHDR_MAX + 1] = { @@ -58,7 +59,6 @@ static int nft_exthdr_init(const struct nft_ctx *ctx, const struct nlattr * const tb[]) { struct nft_exthdr *priv = nft_expr_priv(expr); - int err; if (tb[NFTA_EXTHDR_DREG] == NULL || tb[NFTA_EXTHDR_TYPE] == NULL || @@ -69,22 +69,17 @@ static int nft_exthdr_init(const struct nft_ctx *ctx, priv->type = nla_get_u8(tb[NFTA_EXTHDR_TYPE]); priv->offset = ntohl(nla_get_be32(tb[NFTA_EXTHDR_OFFSET])); priv->len = ntohl(nla_get_be32(tb[NFTA_EXTHDR_LEN])); - if (priv->len == 0 || - priv->len > FIELD_SIZEOF(struct nft_data, data)) - return -EINVAL; + priv->dreg = nft_parse_register(tb[NFTA_EXTHDR_DREG]); - priv->dreg = ntohl(nla_get_be32(tb[NFTA_EXTHDR_DREG])); - err = nft_validate_output_register(priv->dreg); - if (err < 0) - return err; - return nft_validate_data_load(ctx, priv->dreg, NULL, NFT_DATA_VALUE); + return nft_validate_register_store(ctx, priv->dreg, NULL, + NFT_DATA_VALUE, priv->len); } static int nft_exthdr_dump(struct sk_buff *skb, const struct nft_expr *expr) { const struct nft_exthdr *priv = nft_expr_priv(expr); - if (nla_put_be32(skb, NFTA_EXTHDR_DREG, htonl(priv->dreg))) + if (nft_dump_register(skb, NFTA_EXTHDR_DREG, priv->dreg)) goto nla_put_failure; if (nla_put_u8(skb, NFTA_EXTHDR_TYPE, priv->type)) goto nla_put_failure; diff --git a/net/netfilter/nft_hash.c b/net/netfilter/nft_hash.c index 37c15e674884..3f9d45d3d9b7 100644 --- a/net/netfilter/nft_hash.c +++ b/net/netfilter/nft_hash.c @@ -15,6 +15,7 @@ #include <linux/log2.h> #include <linux/jhash.h> #include <linux/netlink.h> +#include <linux/workqueue.h> #include <linux/rhashtable.h> #include <linux/netfilter.h> #include <linux/netfilter/nf_tables.h> @@ -23,119 +24,175 @@ /* We target a hash table size of 4, element hint is 75% of final size */ #define NFT_HASH_ELEMENT_HINT 3 +struct nft_hash { + struct rhashtable ht; + struct delayed_work gc_work; +}; + struct nft_hash_elem { struct rhash_head node; - struct nft_data key; - struct nft_data data[]; + struct nft_set_ext ext; +}; + +struct nft_hash_cmp_arg { + const struct nft_set *set; + const u32 *key; + u8 genmask; }; -static bool nft_hash_lookup(const struct nft_set *set, - const struct nft_data *key, - struct nft_data *data) +static const struct rhashtable_params nft_hash_params; + +static inline u32 nft_hash_key(const void *data, u32 len, u32 seed) +{ + const struct nft_hash_cmp_arg *arg = data; + + return jhash(arg->key, len, seed); +} + +static inline u32 nft_hash_obj(const void *data, u32 len, u32 seed) { - struct rhashtable *priv = nft_set_priv(set); + const struct nft_hash_elem *he = data; + + return jhash(nft_set_ext_key(&he->ext), len, seed); +} + +static inline int nft_hash_cmp(struct rhashtable_compare_arg *arg, + const void *ptr) +{ + const struct nft_hash_cmp_arg *x = arg->key; + const struct nft_hash_elem *he = ptr; + + if (memcmp(nft_set_ext_key(&he->ext), x->key, x->set->klen)) + return 1; + if (nft_set_elem_expired(&he->ext)) + return 1; + if (!nft_set_elem_active(&he->ext, x->genmask)) + return 1; + return 0; +} + +static bool nft_hash_lookup(const struct nft_set *set, const u32 *key, + const struct nft_set_ext **ext) +{ + struct nft_hash *priv = nft_set_priv(set); const struct nft_hash_elem *he; + struct nft_hash_cmp_arg arg = { + .genmask = nft_genmask_cur(read_pnet(&set->pnet)), + .set = set, + .key = key, + }; - he = rhashtable_lookup(priv, key); - if (he && set->flags & NFT_SET_MAP) - nft_data_copy(data, he->data); + he = rhashtable_lookup_fast(&priv->ht, &arg, nft_hash_params); + if (he != NULL) + *ext = &he->ext; return !!he; } -static int nft_hash_insert(const struct nft_set *set, - const struct nft_set_elem *elem) +static bool nft_hash_update(struct nft_set *set, const u32 *key, + void *(*new)(struct nft_set *, + const struct nft_expr *, + struct nft_regs *regs), + const struct nft_expr *expr, + struct nft_regs *regs, + const struct nft_set_ext **ext) { - struct rhashtable *priv = nft_set_priv(set); + struct nft_hash *priv = nft_set_priv(set); struct nft_hash_elem *he; - unsigned int size; - - if (elem->flags != 0) - return -EINVAL; + struct nft_hash_cmp_arg arg = { + .genmask = NFT_GENMASK_ANY, + .set = set, + .key = key, + }; - size = sizeof(*he); - if (set->flags & NFT_SET_MAP) - size += sizeof(he->data[0]); + he = rhashtable_lookup_fast(&priv->ht, &arg, nft_hash_params); + if (he != NULL) + goto out; - he = kzalloc(size, GFP_KERNEL); + he = new(set, expr, regs); if (he == NULL) - return -ENOMEM; - - nft_data_copy(&he->key, &elem->key); - if (set->flags & NFT_SET_MAP) - nft_data_copy(he->data, &elem->data); - - rhashtable_insert(priv, &he->node); + goto err1; + if (rhashtable_lookup_insert_key(&priv->ht, &arg, &he->node, + nft_hash_params)) + goto err2; +out: + *ext = &he->ext; + return true; - return 0; +err2: + nft_set_elem_destroy(set, he); +err1: + return false; } -static void nft_hash_elem_destroy(const struct nft_set *set, - struct nft_hash_elem *he) +static int nft_hash_insert(const struct nft_set *set, + const struct nft_set_elem *elem) { - nft_data_uninit(&he->key, NFT_DATA_VALUE); - if (set->flags & NFT_SET_MAP) - nft_data_uninit(he->data, set->dtype); - kfree(he); + struct nft_hash *priv = nft_set_priv(set); + struct nft_hash_elem *he = elem->priv; + struct nft_hash_cmp_arg arg = { + .genmask = nft_genmask_next(read_pnet(&set->pnet)), + .set = set, + .key = elem->key.val.data, + }; + + return rhashtable_lookup_insert_key(&priv->ht, &arg, &he->node, + nft_hash_params); } -static void nft_hash_remove(const struct nft_set *set, - const struct nft_set_elem *elem) +static void nft_hash_activate(const struct nft_set *set, + const struct nft_set_elem *elem) { - struct rhashtable *priv = nft_set_priv(set); + struct nft_hash_elem *he = elem->priv; - rhashtable_remove(priv, elem->cookie); - synchronize_rcu(); - kfree(elem->cookie); + nft_set_elem_change_active(set, &he->ext); + nft_set_elem_clear_busy(&he->ext); } -struct nft_compare_arg { - const struct nft_set *set; - struct nft_set_elem *elem; -}; - -static bool nft_hash_compare(void *ptr, void *arg) +static void *nft_hash_deactivate(const struct nft_set *set, + const struct nft_set_elem *elem) { - struct nft_hash_elem *he = ptr; - struct nft_compare_arg *x = arg; - - if (!nft_data_cmp(&he->key, &x->elem->key, x->set->klen)) { - x->elem->cookie = he; - x->elem->flags = 0; - if (x->set->flags & NFT_SET_MAP) - nft_data_copy(&x->elem->data, he->data); + struct nft_hash *priv = nft_set_priv(set); + struct nft_hash_elem *he; + struct nft_hash_cmp_arg arg = { + .genmask = nft_genmask_next(read_pnet(&set->pnet)), + .set = set, + .key = elem->key.val.data, + }; - return true; + rcu_read_lock(); + he = rhashtable_lookup_fast(&priv->ht, &arg, nft_hash_params); + if (he != NULL) { + if (!nft_set_elem_mark_busy(&he->ext)) + nft_set_elem_change_active(set, &he->ext); + else + he = NULL; } + rcu_read_unlock(); - return false; + return he; } -static int nft_hash_get(const struct nft_set *set, struct nft_set_elem *elem) +static void nft_hash_remove(const struct nft_set *set, + const struct nft_set_elem *elem) { - struct rhashtable *priv = nft_set_priv(set); - struct nft_compare_arg arg = { - .set = set, - .elem = elem, - }; + struct nft_hash *priv = nft_set_priv(set); + struct nft_hash_elem *he = elem->priv; - if (rhashtable_lookup_compare(priv, &elem->key, - &nft_hash_compare, &arg)) - return 0; - - return -ENOENT; + rhashtable_remove_fast(&priv->ht, &he->node, nft_hash_params); } static void nft_hash_walk(const struct nft_ctx *ctx, const struct nft_set *set, struct nft_set_iter *iter) { - struct rhashtable *priv = nft_set_priv(set); - const struct nft_hash_elem *he; + struct nft_hash *priv = nft_set_priv(set); + struct nft_hash_elem *he; struct rhashtable_iter hti; struct nft_set_elem elem; + u8 genmask = nft_genmask_cur(read_pnet(&set->pnet)); int err; - err = rhashtable_walk_init(priv, &hti); + err = rhashtable_walk_init(&priv->ht, &hti); iter->err = err; if (err) return; @@ -159,11 +216,12 @@ static void nft_hash_walk(const struct nft_ctx *ctx, const struct nft_set *set, if (iter->count < iter->skip) goto cont; + if (nft_set_elem_expired(&he->ext)) + goto cont; + if (!nft_set_elem_active(&he->ext, genmask)) + goto cont; - memcpy(&elem.key, &he->key, sizeof(elem.key)); - if (set->flags & NFT_SET_MAP) - memcpy(&elem.data, he->data, sizeof(elem.data)); - elem.flags = 0; + elem.priv = he; iter->err = iter->fn(ctx, set, iter, &elem); if (iter->err < 0) @@ -178,47 +236,102 @@ out: rhashtable_walk_exit(&hti); } +static void nft_hash_gc(struct work_struct *work) +{ + struct nft_set *set; + struct nft_hash_elem *he; + struct nft_hash *priv; + struct nft_set_gc_batch *gcb = NULL; + struct rhashtable_iter hti; + int err; + + priv = container_of(work, struct nft_hash, gc_work.work); + set = nft_set_container_of(priv); + + err = rhashtable_walk_init(&priv->ht, &hti); + if (err) + goto schedule; + + err = rhashtable_walk_start(&hti); + if (err && err != -EAGAIN) + goto out; + + while ((he = rhashtable_walk_next(&hti))) { + if (IS_ERR(he)) { + if (PTR_ERR(he) != -EAGAIN) + goto out; + continue; + } + + if (!nft_set_elem_expired(&he->ext)) + continue; + if (nft_set_elem_mark_busy(&he->ext)) + continue; + + gcb = nft_set_gc_batch_check(set, gcb, GFP_ATOMIC); + if (gcb == NULL) + goto out; + rhashtable_remove_fast(&priv->ht, &he->node, nft_hash_params); + atomic_dec(&set->nelems); + nft_set_gc_batch_add(gcb, he); + } +out: + rhashtable_walk_stop(&hti); + rhashtable_walk_exit(&hti); + + nft_set_gc_batch_complete(gcb); +schedule: + queue_delayed_work(system_power_efficient_wq, &priv->gc_work, + nft_set_gc_interval(set)); +} + static unsigned int nft_hash_privsize(const struct nlattr * const nla[]) { - return sizeof(struct rhashtable); + return sizeof(struct nft_hash); } +static const struct rhashtable_params nft_hash_params = { + .head_offset = offsetof(struct nft_hash_elem, node), + .hashfn = nft_hash_key, + .obj_hashfn = nft_hash_obj, + .obj_cmpfn = nft_hash_cmp, + .automatic_shrinking = true, +}; + static int nft_hash_init(const struct nft_set *set, const struct nft_set_desc *desc, const struct nlattr * const tb[]) { - 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, - }; + struct nft_hash *priv = nft_set_priv(set); + struct rhashtable_params params = nft_hash_params; + int err; - return rhashtable_init(priv, ¶ms); + params.nelem_hint = desc->size ?: NFT_HASH_ELEMENT_HINT; + params.key_len = set->klen; + + err = rhashtable_init(&priv->ht, ¶ms); + if (err < 0) + return err; + + INIT_DEFERRABLE_WORK(&priv->gc_work, nft_hash_gc); + if (set->flags & NFT_SET_TIMEOUT) + queue_delayed_work(system_power_efficient_wq, &priv->gc_work, + nft_set_gc_interval(set)); + return 0; } -static void nft_hash_destroy(const struct nft_set *set) +static void nft_hash_elem_destroy(void *ptr, void *arg) { - struct rhashtable *priv = nft_set_priv(set); - const struct bucket_table *tbl; - struct nft_hash_elem *he; - struct rhash_head *pos, *next; - unsigned int i; - - /* Stop an eventual async resizing */ - priv->being_destroyed = true; - mutex_lock(&priv->mutex); + nft_set_elem_destroy((const struct nft_set *)arg, ptr); +} - tbl = rht_dereference(priv->tbl, priv); - for (i = 0; i < tbl->size; i++) { - rht_for_each_entry_safe(he, pos, next, tbl, i, node) - nft_hash_elem_destroy(set, he); - } - mutex_unlock(&priv->mutex); +static void nft_hash_destroy(const struct nft_set *set) +{ + struct nft_hash *priv = nft_set_priv(set); - rhashtable_destroy(priv); + cancel_delayed_work_sync(&priv->gc_work); + rhashtable_free_and_destroy(&priv->ht, nft_hash_elem_destroy, + (void *)set); } static bool nft_hash_estimate(const struct nft_set_desc *desc, u32 features, @@ -227,11 +340,8 @@ static bool nft_hash_estimate(const struct nft_set_desc *desc, u32 features, unsigned int esize; esize = sizeof(struct nft_hash_elem); - if (features & NFT_SET_MAP) - esize += FIELD_SIZEOF(struct nft_hash_elem, data[0]); - if (desc->size) { - est->size = sizeof(struct rhashtable) + + est->size = sizeof(struct nft_hash) + roundup_pow_of_two(desc->size * 4 / 3) * sizeof(struct nft_hash_elem *) + desc->size * esize; @@ -251,15 +361,18 @@ static bool nft_hash_estimate(const struct nft_set_desc *desc, u32 features, static struct nft_set_ops nft_hash_ops __read_mostly = { .privsize = nft_hash_privsize, + .elemsize = offsetof(struct nft_hash_elem, ext), .estimate = nft_hash_estimate, .init = nft_hash_init, .destroy = nft_hash_destroy, - .get = nft_hash_get, .insert = nft_hash_insert, + .activate = nft_hash_activate, + .deactivate = nft_hash_deactivate, .remove = nft_hash_remove, .lookup = nft_hash_lookup, + .update = nft_hash_update, .walk = nft_hash_walk, - .features = NFT_SET_MAP, + .features = NFT_SET_MAP | NFT_SET_TIMEOUT, .owner = THIS_MODULE, }; diff --git a/net/netfilter/nft_immediate.c b/net/netfilter/nft_immediate.c index 810385eb7249..db3b746858e3 100644 --- a/net/netfilter/nft_immediate.c +++ b/net/netfilter/nft_immediate.c @@ -24,12 +24,12 @@ struct nft_immediate_expr { }; static void nft_immediate_eval(const struct nft_expr *expr, - struct nft_data data[NFT_REG_MAX + 1], + struct nft_regs *regs, const struct nft_pktinfo *pkt) { const struct nft_immediate_expr *priv = nft_expr_priv(expr); - nft_data_copy(&data[priv->dreg], &priv->data); + nft_data_copy(®s->data[priv->dreg], &priv->data, priv->dlen); } static const struct nla_policy nft_immediate_policy[NFTA_IMMEDIATE_MAX + 1] = { @@ -49,17 +49,15 @@ static int nft_immediate_init(const struct nft_ctx *ctx, tb[NFTA_IMMEDIATE_DATA] == NULL) return -EINVAL; - priv->dreg = ntohl(nla_get_be32(tb[NFTA_IMMEDIATE_DREG])); - err = nft_validate_output_register(priv->dreg); - if (err < 0) - return err; - - err = nft_data_init(ctx, &priv->data, &desc, tb[NFTA_IMMEDIATE_DATA]); + err = nft_data_init(ctx, &priv->data, sizeof(priv->data), &desc, + tb[NFTA_IMMEDIATE_DATA]); if (err < 0) return err; priv->dlen = desc.len; - err = nft_validate_data_load(ctx, priv->dreg, &priv->data, desc.type); + priv->dreg = nft_parse_register(tb[NFTA_IMMEDIATE_DREG]); + err = nft_validate_register_store(ctx, priv->dreg, &priv->data, + desc.type, desc.len); if (err < 0) goto err1; @@ -81,7 +79,7 @@ static int nft_immediate_dump(struct sk_buff *skb, const struct nft_expr *expr) { const struct nft_immediate_expr *priv = nft_expr_priv(expr); - if (nla_put_be32(skb, NFTA_IMMEDIATE_DREG, htonl(priv->dreg))) + if (nft_dump_register(skb, NFTA_IMMEDIATE_DREG, priv->dreg)) goto nla_put_failure; return nft_data_dump(skb, NFTA_IMMEDIATE_DATA, &priv->data, diff --git a/net/netfilter/nft_limit.c b/net/netfilter/nft_limit.c index 85da5bd02f64..435c1ccd6c0e 100644 --- a/net/netfilter/nft_limit.c +++ b/net/netfilter/nft_limit.c @@ -27,7 +27,7 @@ struct nft_limit { }; static void nft_limit_eval(const struct nft_expr *expr, - struct nft_data data[NFT_REG_MAX + 1], + struct nft_regs *regs, const struct nft_pktinfo *pkt) { struct nft_limit *priv = nft_expr_priv(expr); @@ -45,7 +45,7 @@ static void nft_limit_eval(const struct nft_expr *expr, } spin_unlock_bh(&limit_lock); - data[NFT_REG_VERDICT].verdict = NFT_BREAK; + regs->verdict.code = NFT_BREAK; } static const struct nla_policy nft_limit_policy[NFTA_LIMIT_MAX + 1] = { @@ -98,6 +98,7 @@ static struct nft_expr_type nft_limit_type __read_mostly = { .ops = &nft_limit_ops, .policy = nft_limit_policy, .maxattr = NFTA_LIMIT_MAX, + .flags = NFT_EXPR_STATEFUL, .owner = THIS_MODULE, }; diff --git a/net/netfilter/nft_log.c b/net/netfilter/nft_log.c index bde05f28cf14..a13d6a386d63 100644 --- a/net/netfilter/nft_log.c +++ b/net/netfilter/nft_log.c @@ -27,7 +27,7 @@ struct nft_log { }; static void nft_log_eval(const struct nft_expr *expr, - struct nft_data data[NFT_REG_MAX + 1], + struct nft_regs *regs, const struct nft_pktinfo *pkt) { const struct nft_log *priv = nft_expr_priv(expr); @@ -78,7 +78,7 @@ static int nft_log_init(const struct nft_ctx *ctx, li->u.log.level = ntohl(nla_get_be32(tb[NFTA_LOG_LEVEL])); } else { - li->u.log.level = 4; + li->u.log.level = LOGLEVEL_WARNING; } if (tb[NFTA_LOG_FLAGS] != NULL) { li->u.log.logflags = diff --git a/net/netfilter/nft_lookup.c b/net/netfilter/nft_lookup.c index 9615b8b9fb37..b3c31ef8015d 100644 --- a/net/netfilter/nft_lookup.c +++ b/net/netfilter/nft_lookup.c @@ -26,15 +26,20 @@ struct nft_lookup { }; static void nft_lookup_eval(const struct nft_expr *expr, - struct nft_data data[NFT_REG_MAX + 1], + struct nft_regs *regs, const struct nft_pktinfo *pkt) { const struct nft_lookup *priv = nft_expr_priv(expr); const struct nft_set *set = priv->set; + const struct nft_set_ext *ext; - if (set->ops->lookup(set, &data[priv->sreg], &data[priv->dreg])) + if (set->ops->lookup(set, ®s->data[priv->sreg], &ext)) { + if (set->flags & NFT_SET_MAP) + nft_data_copy(®s->data[priv->dreg], + nft_set_ext_data(ext), set->dlen); return; - data[NFT_REG_VERDICT].verdict = NFT_BREAK; + } + regs->verdict.code = NFT_BREAK; } static const struct nla_policy nft_lookup_policy[NFTA_LOOKUP_MAX + 1] = { @@ -66,8 +71,11 @@ static int nft_lookup_init(const struct nft_ctx *ctx, return PTR_ERR(set); } - priv->sreg = ntohl(nla_get_be32(tb[NFTA_LOOKUP_SREG])); - err = nft_validate_input_register(priv->sreg); + if (set->flags & NFT_SET_EVAL) + return -EOPNOTSUPP; + + priv->sreg = nft_parse_register(tb[NFTA_LOOKUP_SREG]); + err = nft_validate_register_load(priv->sreg, set->klen); if (err < 0) return err; @@ -75,19 +83,16 @@ static int nft_lookup_init(const struct nft_ctx *ctx, if (!(set->flags & NFT_SET_MAP)) return -EINVAL; - priv->dreg = ntohl(nla_get_be32(tb[NFTA_LOOKUP_DREG])); - err = nft_validate_output_register(priv->dreg); + priv->dreg = nft_parse_register(tb[NFTA_LOOKUP_DREG]); + err = nft_validate_register_store(ctx, priv->dreg, NULL, + set->dtype, set->dlen); if (err < 0) return err; - - if (priv->dreg == NFT_REG_VERDICT) { - if (set->dtype != NFT_DATA_VERDICT) - return -EINVAL; - } else if (set->dtype == NFT_DATA_VERDICT) - return -EINVAL; } else if (set->flags & NFT_SET_MAP) return -EINVAL; + priv->binding.flags = set->flags & NFT_SET_MAP; + err = nf_tables_bind_set(ctx, set, &priv->binding); if (err < 0) return err; @@ -110,10 +115,10 @@ static int nft_lookup_dump(struct sk_buff *skb, const struct nft_expr *expr) if (nla_put_string(skb, NFTA_LOOKUP_SET, priv->set->name)) goto nla_put_failure; - if (nla_put_be32(skb, NFTA_LOOKUP_SREG, htonl(priv->sreg))) + if (nft_dump_register(skb, NFTA_LOOKUP_SREG, priv->sreg)) goto nla_put_failure; if (priv->set->flags & NFT_SET_MAP) - if (nla_put_be32(skb, NFTA_LOOKUP_DREG, htonl(priv->dreg))) + if (nft_dump_register(skb, NFTA_LOOKUP_DREG, priv->dreg)) goto nla_put_failure; return 0; diff --git a/net/netfilter/nft_meta.c b/net/netfilter/nft_meta.c index e99911eda915..52561e1c31e2 100644 --- a/net/netfilter/nft_meta.c +++ b/net/netfilter/nft_meta.c @@ -25,65 +25,68 @@ #include <net/netfilter/nft_meta.h> void nft_meta_get_eval(const struct nft_expr *expr, - struct nft_data data[NFT_REG_MAX + 1], + struct nft_regs *regs, const struct nft_pktinfo *pkt) { const struct nft_meta *priv = nft_expr_priv(expr); const struct sk_buff *skb = pkt->skb; const struct net_device *in = pkt->in, *out = pkt->out; - struct nft_data *dest = &data[priv->dreg]; + u32 *dest = ®s->data[priv->dreg]; switch (priv->key) { case NFT_META_LEN: - dest->data[0] = skb->len; + *dest = skb->len; break; case NFT_META_PROTOCOL: - *(__be16 *)dest->data = skb->protocol; + *dest = 0; + *(__be16 *)dest = skb->protocol; break; case NFT_META_NFPROTO: - dest->data[0] = pkt->ops->pf; + *dest = pkt->ops->pf; break; case NFT_META_L4PROTO: - dest->data[0] = pkt->tprot; + *dest = pkt->tprot; break; case NFT_META_PRIORITY: - dest->data[0] = skb->priority; + *dest = skb->priority; break; case NFT_META_MARK: - dest->data[0] = skb->mark; + *dest = skb->mark; break; case NFT_META_IIF: if (in == NULL) goto err; - dest->data[0] = in->ifindex; + *dest = in->ifindex; break; case NFT_META_OIF: if (out == NULL) goto err; - dest->data[0] = out->ifindex; + *dest = out->ifindex; break; case NFT_META_IIFNAME: if (in == NULL) goto err; - strncpy((char *)dest->data, in->name, sizeof(dest->data)); + strncpy((char *)dest, in->name, IFNAMSIZ); break; case NFT_META_OIFNAME: if (out == NULL) goto err; - strncpy((char *)dest->data, out->name, sizeof(dest->data)); + strncpy((char *)dest, out->name, IFNAMSIZ); break; case NFT_META_IIFTYPE: if (in == NULL) goto err; - *(u16 *)dest->data = in->type; + *dest = 0; + *(u16 *)dest = in->type; break; case NFT_META_OIFTYPE: if (out == NULL) goto err; - *(u16 *)dest->data = out->type; + *dest = 0; + *(u16 *)dest = out->type; break; case NFT_META_SKUID: - if (skb->sk == NULL || skb->sk->sk_state == TCP_TIME_WAIT) + if (skb->sk == NULL || !sk_fullsock(skb->sk)) goto err; read_lock_bh(&skb->sk->sk_callback_lock); @@ -93,13 +96,12 @@ void nft_meta_get_eval(const struct nft_expr *expr, goto err; } - dest->data[0] = - from_kuid_munged(&init_user_ns, + *dest = from_kuid_munged(&init_user_ns, skb->sk->sk_socket->file->f_cred->fsuid); read_unlock_bh(&skb->sk->sk_callback_lock); break; case NFT_META_SKGID: - if (skb->sk == NULL || skb->sk->sk_state == TCP_TIME_WAIT) + if (skb->sk == NULL || !sk_fullsock(skb->sk)) goto err; read_lock_bh(&skb->sk->sk_callback_lock); @@ -108,8 +110,7 @@ void nft_meta_get_eval(const struct nft_expr *expr, read_unlock_bh(&skb->sk->sk_callback_lock); goto err; } - dest->data[0] = - from_kgid_munged(&init_user_ns, + *dest = from_kgid_munged(&init_user_ns, skb->sk->sk_socket->file->f_cred->fsgid); read_unlock_bh(&skb->sk->sk_callback_lock); break; @@ -119,33 +120,33 @@ void nft_meta_get_eval(const struct nft_expr *expr, if (dst == NULL) goto err; - dest->data[0] = dst->tclassid; + *dest = dst->tclassid; break; } #endif #ifdef CONFIG_NETWORK_SECMARK case NFT_META_SECMARK: - dest->data[0] = skb->secmark; + *dest = skb->secmark; break; #endif case NFT_META_PKTTYPE: if (skb->pkt_type != PACKET_LOOPBACK) { - dest->data[0] = skb->pkt_type; + *dest = skb->pkt_type; break; } switch (pkt->ops->pf) { case NFPROTO_IPV4: if (ipv4_is_multicast(ip_hdr(skb)->daddr)) - dest->data[0] = PACKET_MULTICAST; + *dest = PACKET_MULTICAST; else - dest->data[0] = PACKET_BROADCAST; + *dest = PACKET_BROADCAST; break; case NFPROTO_IPV6: if (ipv6_hdr(skb)->daddr.s6_addr[0] == 0xFF) - dest->data[0] = PACKET_MULTICAST; + *dest = PACKET_MULTICAST; else - dest->data[0] = PACKET_BROADCAST; + *dest = PACKET_BROADCAST; break; default: WARN_ON(1); @@ -153,23 +154,22 @@ void nft_meta_get_eval(const struct nft_expr *expr, } break; case NFT_META_CPU: - dest->data[0] = smp_processor_id(); + *dest = raw_smp_processor_id(); break; case NFT_META_IIFGROUP: if (in == NULL) goto err; - dest->data[0] = in->group; + *dest = in->group; break; case NFT_META_OIFGROUP: if (out == NULL) goto err; - dest->data[0] = out->group; + *dest = out->group; break; case NFT_META_CGROUP: - if (skb->sk == NULL) - break; - - dest->data[0] = skb->sk->sk_classid; + if (skb->sk == NULL || !sk_fullsock(skb->sk)) + goto err; + *dest = skb->sk->sk_classid; break; default: WARN_ON(1); @@ -178,17 +178,17 @@ void nft_meta_get_eval(const struct nft_expr *expr, return; err: - data[NFT_REG_VERDICT].verdict = NFT_BREAK; + regs->verdict.code = NFT_BREAK; } EXPORT_SYMBOL_GPL(nft_meta_get_eval); void nft_meta_set_eval(const struct nft_expr *expr, - struct nft_data data[NFT_REG_MAX + 1], + struct nft_regs *regs, const struct nft_pktinfo *pkt) { const struct nft_meta *meta = nft_expr_priv(expr); struct sk_buff *skb = pkt->skb; - u32 value = data[meta->sreg].data[0]; + u32 value = regs->data[meta->sreg]; switch (meta->key) { case NFT_META_MARK: @@ -218,22 +218,22 @@ int nft_meta_get_init(const struct nft_ctx *ctx, const struct nlattr * const tb[]) { struct nft_meta *priv = nft_expr_priv(expr); - int err; + unsigned int len; priv->key = ntohl(nla_get_be32(tb[NFTA_META_KEY])); switch (priv->key) { - case NFT_META_LEN: case NFT_META_PROTOCOL: + case NFT_META_IIFTYPE: + case NFT_META_OIFTYPE: + len = sizeof(u16); + break; case NFT_META_NFPROTO: case NFT_META_L4PROTO: + case NFT_META_LEN: case NFT_META_PRIORITY: case NFT_META_MARK: case NFT_META_IIF: case NFT_META_OIF: - case NFT_META_IIFNAME: - case NFT_META_OIFNAME: - case NFT_META_IIFTYPE: - case NFT_META_OIFTYPE: case NFT_META_SKUID: case NFT_META_SKGID: #ifdef CONFIG_IP_ROUTE_CLASSID @@ -247,21 +247,19 @@ int nft_meta_get_init(const struct nft_ctx *ctx, case NFT_META_IIFGROUP: case NFT_META_OIFGROUP: case NFT_META_CGROUP: + len = sizeof(u32); + break; + case NFT_META_IIFNAME: + case NFT_META_OIFNAME: + len = IFNAMSIZ; break; default: return -EOPNOTSUPP; } - priv->dreg = ntohl(nla_get_be32(tb[NFTA_META_DREG])); - err = nft_validate_output_register(priv->dreg); - if (err < 0) - return err; - - err = nft_validate_data_load(ctx, priv->dreg, NULL, NFT_DATA_VALUE); - if (err < 0) - return err; - - return 0; + priv->dreg = nft_parse_register(tb[NFTA_META_DREG]); + return nft_validate_register_store(ctx, priv->dreg, NULL, + NFT_DATA_VALUE, len); } EXPORT_SYMBOL_GPL(nft_meta_get_init); @@ -270,20 +268,24 @@ int nft_meta_set_init(const struct nft_ctx *ctx, const struct nlattr * const tb[]) { struct nft_meta *priv = nft_expr_priv(expr); + unsigned int len; int err; priv->key = ntohl(nla_get_be32(tb[NFTA_META_KEY])); switch (priv->key) { case NFT_META_MARK: case NFT_META_PRIORITY: + len = sizeof(u32); + break; case NFT_META_NFTRACE: + len = sizeof(u8); break; default: return -EOPNOTSUPP; } - priv->sreg = ntohl(nla_get_be32(tb[NFTA_META_SREG])); - err = nft_validate_input_register(priv->sreg); + priv->sreg = nft_parse_register(tb[NFTA_META_SREG]); + err = nft_validate_register_load(priv->sreg, len); if (err < 0) return err; @@ -298,7 +300,7 @@ int nft_meta_get_dump(struct sk_buff *skb, if (nla_put_be32(skb, NFTA_META_KEY, htonl(priv->key))) goto nla_put_failure; - if (nla_put_be32(skb, NFTA_META_DREG, htonl(priv->dreg))) + if (nft_dump_register(skb, NFTA_META_DREG, priv->dreg)) goto nla_put_failure; return 0; @@ -314,7 +316,7 @@ int nft_meta_set_dump(struct sk_buff *skb, if (nla_put_be32(skb, NFTA_META_KEY, htonl(priv->key))) goto nla_put_failure; - if (nla_put_be32(skb, NFTA_META_SREG, htonl(priv->sreg))) + if (nft_dump_register(skb, NFTA_META_SREG, priv->sreg)) goto nla_put_failure; return 0; diff --git a/net/netfilter/nft_nat.c b/net/netfilter/nft_nat.c index a0837c6c9283..ee2d71753746 100644 --- a/net/netfilter/nft_nat.c +++ b/net/netfilter/nft_nat.c @@ -37,7 +37,7 @@ struct nft_nat { }; static void nft_nat_eval(const struct nft_expr *expr, - struct nft_data data[NFT_REG_MAX + 1], + struct nft_regs *regs, const struct nft_pktinfo *pkt) { const struct nft_nat *priv = nft_expr_priv(expr); @@ -49,33 +49,32 @@ static void nft_nat_eval(const struct nft_expr *expr, if (priv->sreg_addr_min) { if (priv->family == AF_INET) { range.min_addr.ip = (__force __be32) - data[priv->sreg_addr_min].data[0]; + regs->data[priv->sreg_addr_min]; range.max_addr.ip = (__force __be32) - data[priv->sreg_addr_max].data[0]; + regs->data[priv->sreg_addr_max]; } else { memcpy(range.min_addr.ip6, - data[priv->sreg_addr_min].data, - sizeof(struct nft_data)); + ®s->data[priv->sreg_addr_min], + sizeof(range.min_addr.ip6)); memcpy(range.max_addr.ip6, - data[priv->sreg_addr_max].data, - sizeof(struct nft_data)); + ®s->data[priv->sreg_addr_max], + sizeof(range.max_addr.ip6)); } range.flags |= NF_NAT_RANGE_MAP_IPS; } if (priv->sreg_proto_min) { range.min_proto.all = - *(__be16 *)&data[priv->sreg_proto_min].data[0]; + *(__be16 *)®s->data[priv->sreg_proto_min]; range.max_proto.all = - *(__be16 *)&data[priv->sreg_proto_max].data[0]; + *(__be16 *)®s->data[priv->sreg_proto_max]; range.flags |= NF_NAT_RANGE_PROTO_SPECIFIED; } range.flags |= priv->flags; - data[NFT_REG_VERDICT].verdict = - nf_nat_setup_info(ct, &range, priv->type); + regs->verdict.code = nf_nat_setup_info(ct, &range, priv->type); } static const struct nla_policy nft_nat_policy[NFTA_NAT_MAX + 1] = { @@ -119,6 +118,7 @@ static int nft_nat_init(const struct nft_ctx *ctx, const struct nft_expr *expr, const struct nlattr * const tb[]) { struct nft_nat *priv = nft_expr_priv(expr); + unsigned int alen, plen; u32 family; int err; @@ -146,25 +146,34 @@ static int nft_nat_init(const struct nft_ctx *ctx, const struct nft_expr *expr, return -EINVAL; family = ntohl(nla_get_be32(tb[NFTA_NAT_FAMILY])); - if (family != AF_INET && family != AF_INET6) - return -EAFNOSUPPORT; if (family != ctx->afi->family) return -EOPNOTSUPP; + + switch (family) { + case NFPROTO_IPV4: + alen = FIELD_SIZEOF(struct nf_nat_range, min_addr.ip); + break; + case NFPROTO_IPV6: + alen = FIELD_SIZEOF(struct nf_nat_range, min_addr.ip6); + break; + default: + return -EAFNOSUPPORT; + } priv->family = family; if (tb[NFTA_NAT_REG_ADDR_MIN]) { priv->sreg_addr_min = - ntohl(nla_get_be32(tb[NFTA_NAT_REG_ADDR_MIN])); - - err = nft_validate_input_register(priv->sreg_addr_min); + nft_parse_register(tb[NFTA_NAT_REG_ADDR_MIN]); + err = nft_validate_register_load(priv->sreg_addr_min, alen); if (err < 0) return err; if (tb[NFTA_NAT_REG_ADDR_MAX]) { priv->sreg_addr_max = - ntohl(nla_get_be32(tb[NFTA_NAT_REG_ADDR_MAX])); + nft_parse_register(tb[NFTA_NAT_REG_ADDR_MAX]); - err = nft_validate_input_register(priv->sreg_addr_max); + err = nft_validate_register_load(priv->sreg_addr_max, + alen); if (err < 0) return err; } else { @@ -172,19 +181,21 @@ static int nft_nat_init(const struct nft_ctx *ctx, const struct nft_expr *expr, } } + plen = FIELD_SIZEOF(struct nf_nat_range, min_addr.all); if (tb[NFTA_NAT_REG_PROTO_MIN]) { priv->sreg_proto_min = - ntohl(nla_get_be32(tb[NFTA_NAT_REG_PROTO_MIN])); + nft_parse_register(tb[NFTA_NAT_REG_PROTO_MIN]); - err = nft_validate_input_register(priv->sreg_proto_min); + err = nft_validate_register_load(priv->sreg_proto_min, plen); if (err < 0) return err; if (tb[NFTA_NAT_REG_PROTO_MAX]) { priv->sreg_proto_max = - ntohl(nla_get_be32(tb[NFTA_NAT_REG_PROTO_MAX])); + nft_parse_register(tb[NFTA_NAT_REG_PROTO_MAX]); - err = nft_validate_input_register(priv->sreg_proto_max); + err = nft_validate_register_load(priv->sreg_proto_max, + plen); if (err < 0) return err; } else { @@ -220,18 +231,18 @@ static int nft_nat_dump(struct sk_buff *skb, const struct nft_expr *expr) goto nla_put_failure; if (priv->sreg_addr_min) { - if (nla_put_be32(skb, NFTA_NAT_REG_ADDR_MIN, - htonl(priv->sreg_addr_min)) || - nla_put_be32(skb, NFTA_NAT_REG_ADDR_MAX, - htonl(priv->sreg_addr_max))) + if (nft_dump_register(skb, NFTA_NAT_REG_ADDR_MIN, + priv->sreg_addr_min) || + nft_dump_register(skb, NFTA_NAT_REG_ADDR_MAX, + priv->sreg_addr_max)) goto nla_put_failure; } if (priv->sreg_proto_min) { - if (nla_put_be32(skb, NFTA_NAT_REG_PROTO_MIN, - htonl(priv->sreg_proto_min)) || - nla_put_be32(skb, NFTA_NAT_REG_PROTO_MAX, - htonl(priv->sreg_proto_max))) + if (nft_dump_register(skb, NFTA_NAT_REG_PROTO_MIN, + priv->sreg_proto_min) || + nft_dump_register(skb, NFTA_NAT_REG_PROTO_MAX, + priv->sreg_proto_max)) goto nla_put_failure; } diff --git a/net/netfilter/nft_payload.c b/net/netfilter/nft_payload.c index 85daa84bfdfe..94fb3b27a2c5 100644 --- a/net/netfilter/nft_payload.c +++ b/net/netfilter/nft_payload.c @@ -18,12 +18,12 @@ #include <net/netfilter/nf_tables.h> static void nft_payload_eval(const struct nft_expr *expr, - struct nft_data data[NFT_REG_MAX + 1], + struct nft_regs *regs, const struct nft_pktinfo *pkt) { const struct nft_payload *priv = nft_expr_priv(expr); const struct sk_buff *skb = pkt->skb; - struct nft_data *dest = &data[priv->dreg]; + u32 *dest = ®s->data[priv->dreg]; int offset; switch (priv->base) { @@ -43,11 +43,12 @@ static void nft_payload_eval(const struct nft_expr *expr, } offset += priv->offset; - if (skb_copy_bits(skb, offset, dest->data, priv->len) < 0) + dest[priv->len / NFT_REG32_SIZE] = 0; + if (skb_copy_bits(skb, offset, dest, priv->len) < 0) goto err; return; err: - data[NFT_REG_VERDICT].verdict = NFT_BREAK; + regs->verdict.code = NFT_BREAK; } static const struct nla_policy nft_payload_policy[NFTA_PAYLOAD_MAX + 1] = { @@ -62,24 +63,21 @@ static int nft_payload_init(const struct nft_ctx *ctx, const struct nlattr * const tb[]) { struct nft_payload *priv = nft_expr_priv(expr); - int err; priv->base = ntohl(nla_get_be32(tb[NFTA_PAYLOAD_BASE])); priv->offset = ntohl(nla_get_be32(tb[NFTA_PAYLOAD_OFFSET])); priv->len = ntohl(nla_get_be32(tb[NFTA_PAYLOAD_LEN])); + priv->dreg = nft_parse_register(tb[NFTA_PAYLOAD_DREG]); - priv->dreg = ntohl(nla_get_be32(tb[NFTA_PAYLOAD_DREG])); - err = nft_validate_output_register(priv->dreg); - if (err < 0) - return err; - return nft_validate_data_load(ctx, priv->dreg, NULL, NFT_DATA_VALUE); + return nft_validate_register_store(ctx, priv->dreg, NULL, + NFT_DATA_VALUE, priv->len); } static int nft_payload_dump(struct sk_buff *skb, const struct nft_expr *expr) { const struct nft_payload *priv = nft_expr_priv(expr); - if (nla_put_be32(skb, NFTA_PAYLOAD_DREG, htonl(priv->dreg)) || + if (nft_dump_register(skb, NFTA_PAYLOAD_DREG, priv->dreg) || nla_put_be32(skb, NFTA_PAYLOAD_BASE, htonl(priv->base)) || nla_put_be32(skb, NFTA_PAYLOAD_OFFSET, htonl(priv->offset)) || nla_put_be32(skb, NFTA_PAYLOAD_LEN, htonl(priv->len))) @@ -131,9 +129,7 @@ nft_payload_select_ops(const struct nft_ctx *ctx, } offset = ntohl(nla_get_be32(tb[NFTA_PAYLOAD_OFFSET])); - len = ntohl(nla_get_be32(tb[NFTA_PAYLOAD_LEN])); - if (len == 0 || len > FIELD_SIZEOF(struct nft_data, data)) - return ERR_PTR(-EINVAL); + len = ntohl(nla_get_be32(tb[NFTA_PAYLOAD_LEN])); if (len <= 4 && is_power_of_2(len) && IS_ALIGNED(offset, len) && base != NFT_PAYLOAD_LL_HEADER) diff --git a/net/netfilter/nft_queue.c b/net/netfilter/nft_queue.c index e8ae2f6bf232..96805d21d618 100644 --- a/net/netfilter/nft_queue.c +++ b/net/netfilter/nft_queue.c @@ -28,7 +28,7 @@ struct nft_queue { }; static void nft_queue_eval(const struct nft_expr *expr, - struct nft_data data[NFT_REG_MAX + 1], + struct nft_regs *regs, const struct nft_pktinfo *pkt) { struct nft_queue *priv = nft_expr_priv(expr); @@ -51,7 +51,7 @@ static void nft_queue_eval(const struct nft_expr *expr, if (priv->flags & NFT_QUEUE_FLAG_BYPASS) ret |= NF_VERDICT_FLAG_QUEUE_BYPASS; - data[NFT_REG_VERDICT].verdict = ret; + regs->verdict.code = ret; } static const struct nla_policy nft_queue_policy[NFTA_QUEUE_MAX + 1] = { diff --git a/net/netfilter/nft_rbtree.c b/net/netfilter/nft_rbtree.c index 46214f245665..1c30f41cff5b 100644 --- a/net/netfilter/nft_rbtree.c +++ b/net/netfilter/nft_rbtree.c @@ -26,25 +26,25 @@ struct nft_rbtree { struct nft_rbtree_elem { struct rb_node node; - u16 flags; - struct nft_data key; - struct nft_data data[]; + struct nft_set_ext ext; }; -static bool nft_rbtree_lookup(const struct nft_set *set, - const struct nft_data *key, - struct nft_data *data) + +static bool nft_rbtree_lookup(const struct nft_set *set, const u32 *key, + const struct nft_set_ext **ext) { const struct nft_rbtree *priv = nft_set_priv(set); const struct nft_rbtree_elem *rbe, *interval = NULL; - const struct rb_node *parent = priv->root.rb_node; + const struct rb_node *parent; + u8 genmask = nft_genmask_cur(read_pnet(&set->pnet)); int d; spin_lock_bh(&nft_rbtree_lock); + parent = priv->root.rb_node; while (parent != NULL) { rbe = rb_entry(parent, struct nft_rbtree_elem, node); - d = nft_data_cmp(&rbe->key, key, set->klen); + d = memcmp(nft_set_ext_key(&rbe->ext), key, set->klen); if (d < 0) { parent = parent->rb_left; interval = rbe; @@ -52,12 +52,17 @@ static bool nft_rbtree_lookup(const struct nft_set *set, parent = parent->rb_right; else { found: - if (rbe->flags & NFT_SET_ELEM_INTERVAL_END) + if (!nft_set_elem_active(&rbe->ext, genmask)) { + parent = parent->rb_left; + continue; + } + if (nft_set_ext_exists(&rbe->ext, NFT_SET_EXT_FLAGS) && + *nft_set_ext_flags(&rbe->ext) & + NFT_SET_ELEM_INTERVAL_END) goto out; - if (set->flags & NFT_SET_MAP) - nft_data_copy(data, rbe->data); - spin_unlock_bh(&nft_rbtree_lock); + + *ext = &rbe->ext; return true; } } @@ -71,23 +76,13 @@ out: return false; } -static void nft_rbtree_elem_destroy(const struct nft_set *set, - struct nft_rbtree_elem *rbe) -{ - nft_data_uninit(&rbe->key, NFT_DATA_VALUE); - if (set->flags & NFT_SET_MAP && - !(rbe->flags & NFT_SET_ELEM_INTERVAL_END)) - nft_data_uninit(rbe->data, set->dtype); - - kfree(rbe); -} - static int __nft_rbtree_insert(const struct nft_set *set, struct nft_rbtree_elem *new) { struct nft_rbtree *priv = nft_set_priv(set); struct nft_rbtree_elem *rbe; struct rb_node *parent, **p; + u8 genmask = nft_genmask_next(read_pnet(&set->pnet)); int d; parent = NULL; @@ -95,13 +90,18 @@ static int __nft_rbtree_insert(const struct nft_set *set, while (*p != NULL) { parent = *p; rbe = rb_entry(parent, struct nft_rbtree_elem, node); - d = nft_data_cmp(&rbe->key, &new->key, set->klen); + d = memcmp(nft_set_ext_key(&rbe->ext), + nft_set_ext_key(&new->ext), + set->klen); if (d < 0) p = &parent->rb_left; else if (d > 0) p = &parent->rb_right; - else - return -EEXIST; + else { + if (nft_set_elem_active(&rbe->ext, genmask)) + return -EEXIST; + p = &parent->rb_left; + } } rb_link_node(&new->node, parent, p); rb_insert_color(&new->node, &priv->root); @@ -111,31 +111,13 @@ static int __nft_rbtree_insert(const struct nft_set *set, static int nft_rbtree_insert(const struct nft_set *set, const struct nft_set_elem *elem) { - struct nft_rbtree_elem *rbe; - unsigned int size; + struct nft_rbtree_elem *rbe = elem->priv; int err; - size = sizeof(*rbe); - if (set->flags & NFT_SET_MAP && - !(elem->flags & NFT_SET_ELEM_INTERVAL_END)) - size += sizeof(rbe->data[0]); - - rbe = kzalloc(size, GFP_KERNEL); - if (rbe == NULL) - return -ENOMEM; - - rbe->flags = elem->flags; - nft_data_copy(&rbe->key, &elem->key); - if (set->flags & NFT_SET_MAP && - !(rbe->flags & NFT_SET_ELEM_INTERVAL_END)) - nft_data_copy(rbe->data, &elem->data); - spin_lock_bh(&nft_rbtree_lock); err = __nft_rbtree_insert(set, rbe); - if (err < 0) - kfree(rbe); - spin_unlock_bh(&nft_rbtree_lock); + return err; } @@ -143,42 +125,49 @@ static void nft_rbtree_remove(const struct nft_set *set, const struct nft_set_elem *elem) { struct nft_rbtree *priv = nft_set_priv(set); - struct nft_rbtree_elem *rbe = elem->cookie; + struct nft_rbtree_elem *rbe = elem->priv; spin_lock_bh(&nft_rbtree_lock); rb_erase(&rbe->node, &priv->root); spin_unlock_bh(&nft_rbtree_lock); - kfree(rbe); } -static int nft_rbtree_get(const struct nft_set *set, struct nft_set_elem *elem) +static void nft_rbtree_activate(const struct nft_set *set, + const struct nft_set_elem *elem) +{ + struct nft_rbtree_elem *rbe = elem->priv; + + nft_set_elem_change_active(set, &rbe->ext); +} + +static void *nft_rbtree_deactivate(const struct nft_set *set, + const struct nft_set_elem *elem) { const struct nft_rbtree *priv = nft_set_priv(set); const struct rb_node *parent = priv->root.rb_node; struct nft_rbtree_elem *rbe; + u8 genmask = nft_genmask_cur(read_pnet(&set->pnet)); int d; - spin_lock_bh(&nft_rbtree_lock); while (parent != NULL) { rbe = rb_entry(parent, struct nft_rbtree_elem, node); - d = nft_data_cmp(&rbe->key, &elem->key, set->klen); + d = memcmp(nft_set_ext_key(&rbe->ext), &elem->key.val, + set->klen); if (d < 0) parent = parent->rb_left; else if (d > 0) parent = parent->rb_right; else { - elem->cookie = rbe; - if (set->flags & NFT_SET_MAP && - !(rbe->flags & NFT_SET_ELEM_INTERVAL_END)) - nft_data_copy(&elem->data, rbe->data); - elem->flags = rbe->flags; - spin_unlock_bh(&nft_rbtree_lock); - return 0; + if (!nft_set_elem_active(&rbe->ext, genmask)) { + parent = parent->rb_left; + continue; + } + nft_set_elem_change_active(set, &rbe->ext); + return rbe; } } - spin_unlock_bh(&nft_rbtree_lock); - return -ENOENT; + return NULL; } static void nft_rbtree_walk(const struct nft_ctx *ctx, @@ -186,21 +175,21 @@ static void nft_rbtree_walk(const struct nft_ctx *ctx, struct nft_set_iter *iter) { const struct nft_rbtree *priv = nft_set_priv(set); - const struct nft_rbtree_elem *rbe; + struct nft_rbtree_elem *rbe; struct nft_set_elem elem; struct rb_node *node; + u8 genmask = nft_genmask_cur(read_pnet(&set->pnet)); spin_lock_bh(&nft_rbtree_lock); for (node = rb_first(&priv->root); node != NULL; node = rb_next(node)) { + rbe = rb_entry(node, struct nft_rbtree_elem, node); + if (iter->count < iter->skip) goto cont; + if (!nft_set_elem_active(&rbe->ext, genmask)) + goto cont; - rbe = rb_entry(node, struct nft_rbtree_elem, node); - nft_data_copy(&elem.key, &rbe->key); - if (set->flags & NFT_SET_MAP && - !(rbe->flags & NFT_SET_ELEM_INTERVAL_END)) - nft_data_copy(&elem.data, rbe->data); - elem.flags = rbe->flags; + elem.priv = rbe; iter->err = iter->fn(ctx, set, iter, &elem); if (iter->err < 0) { @@ -237,7 +226,7 @@ static void nft_rbtree_destroy(const struct nft_set *set) while ((node = priv->root.rb_node) != NULL) { rb_erase(node, &priv->root); rbe = rb_entry(node, struct nft_rbtree_elem, node); - nft_rbtree_elem_destroy(set, rbe); + nft_set_elem_destroy(set, rbe); } } @@ -247,9 +236,6 @@ static bool nft_rbtree_estimate(const struct nft_set_desc *desc, u32 features, unsigned int nsize; nsize = sizeof(struct nft_rbtree_elem); - if (features & NFT_SET_MAP) - nsize += FIELD_SIZEOF(struct nft_rbtree_elem, data[0]); - if (desc->size) est->size = sizeof(struct nft_rbtree) + desc->size * nsize; else @@ -262,12 +248,14 @@ static bool nft_rbtree_estimate(const struct nft_set_desc *desc, u32 features, static struct nft_set_ops nft_rbtree_ops __read_mostly = { .privsize = nft_rbtree_privsize, + .elemsize = offsetof(struct nft_rbtree_elem, ext), .estimate = nft_rbtree_estimate, .init = nft_rbtree_init, .destroy = nft_rbtree_destroy, .insert = nft_rbtree_insert, .remove = nft_rbtree_remove, - .get = nft_rbtree_get, + .deactivate = nft_rbtree_deactivate, + .activate = nft_rbtree_activate, .lookup = nft_rbtree_lookup, .walk = nft_rbtree_walk, .features = NFT_SET_INTERVAL | NFT_SET_MAP, diff --git a/net/netfilter/nft_redir.c b/net/netfilter/nft_redir.c index d7e9e93a4e90..03f7bf40ae75 100644 --- a/net/netfilter/nft_redir.c +++ b/net/netfilter/nft_redir.c @@ -44,25 +44,28 @@ int nft_redir_init(const struct nft_ctx *ctx, const struct nlattr * const tb[]) { struct nft_redir *priv = nft_expr_priv(expr); + unsigned int plen; int err; err = nft_redir_validate(ctx, expr, NULL); if (err < 0) return err; + plen = FIELD_SIZEOF(struct nf_nat_range, min_addr.all); if (tb[NFTA_REDIR_REG_PROTO_MIN]) { priv->sreg_proto_min = - ntohl(nla_get_be32(tb[NFTA_REDIR_REG_PROTO_MIN])); + nft_parse_register(tb[NFTA_REDIR_REG_PROTO_MIN]); - err = nft_validate_input_register(priv->sreg_proto_min); + err = nft_validate_register_load(priv->sreg_proto_min, plen); if (err < 0) return err; if (tb[NFTA_REDIR_REG_PROTO_MAX]) { priv->sreg_proto_max = - ntohl(nla_get_be32(tb[NFTA_REDIR_REG_PROTO_MAX])); + nft_parse_register(tb[NFTA_REDIR_REG_PROTO_MAX]); - err = nft_validate_input_register(priv->sreg_proto_max); + err = nft_validate_register_load(priv->sreg_proto_max, + plen); if (err < 0) return err; } else { @@ -85,11 +88,11 @@ int nft_redir_dump(struct sk_buff *skb, const struct nft_expr *expr) const struct nft_redir *priv = nft_expr_priv(expr); if (priv->sreg_proto_min) { - if (nla_put_be32(skb, NFTA_REDIR_REG_PROTO_MIN, - htonl(priv->sreg_proto_min))) + if (nft_dump_register(skb, NFTA_REDIR_REG_PROTO_MIN, + priv->sreg_proto_min)) goto nla_put_failure; - if (nla_put_be32(skb, NFTA_REDIR_REG_PROTO_MAX, - htonl(priv->sreg_proto_max))) + if (nft_dump_register(skb, NFTA_REDIR_REG_PROTO_MAX, + priv->sreg_proto_max)) goto nla_put_failure; } diff --git a/net/netfilter/nft_reject.c b/net/netfilter/nft_reject.c index 57d3e1af5630..0522fc9bfb0a 100644 --- a/net/netfilter/nft_reject.c +++ b/net/netfilter/nft_reject.c @@ -63,6 +63,8 @@ int nft_reject_dump(struct sk_buff *skb, const struct nft_expr *expr) if (nla_put_u8(skb, NFTA_REJECT_ICMP_CODE, priv->icmp_code)) goto nla_put_failure; break; + default: + break; } return 0; diff --git a/net/netfilter/nft_reject_inet.c b/net/netfilter/nft_reject_inet.c index 7b5f9d58680a..635dbba93d01 100644 --- a/net/netfilter/nft_reject_inet.c +++ b/net/netfilter/nft_reject_inet.c @@ -18,7 +18,7 @@ #include <net/netfilter/ipv6/nf_reject.h> static void nft_reject_inet_eval(const struct nft_expr *expr, - struct nft_data data[NFT_REG_MAX + 1], + struct nft_regs *regs, const struct nft_pktinfo *pkt) { struct nft_reject *priv = nft_expr_priv(expr); @@ -28,14 +28,16 @@ static void nft_reject_inet_eval(const struct nft_expr *expr, case NFPROTO_IPV4: switch (priv->type) { case NFT_REJECT_ICMP_UNREACH: - nf_send_unreach(pkt->skb, priv->icmp_code); + nf_send_unreach(pkt->skb, priv->icmp_code, + pkt->ops->hooknum); break; case NFT_REJECT_TCP_RST: nf_send_reset(pkt->skb, pkt->ops->hooknum); break; case NFT_REJECT_ICMPX_UNREACH: nf_send_unreach(pkt->skb, - nft_reject_icmp_code(priv->icmp_code)); + nft_reject_icmp_code(priv->icmp_code), + pkt->ops->hooknum); break; } break; @@ -56,7 +58,8 @@ static void nft_reject_inet_eval(const struct nft_expr *expr, } break; } - data[NFT_REG_VERDICT].verdict = NF_DROP; + + regs->verdict.code = NF_DROP; } static int nft_reject_inet_init(const struct nft_ctx *ctx, @@ -105,6 +108,8 @@ static int nft_reject_inet_dump(struct sk_buff *skb, if (nla_put_u8(skb, NFTA_REJECT_ICMP_CODE, priv->icmp_code)) goto nla_put_failure; break; + default: + break; } return 0; diff --git a/net/netfilter/xt_TPROXY.c b/net/netfilter/xt_TPROXY.c index 50e1e5aaf4ce..cca96cec1b68 100644 --- a/net/netfilter/xt_TPROXY.c +++ b/net/netfilter/xt_TPROXY.c @@ -42,15 +42,21 @@ enum nf_tproxy_lookup_t { static bool tproxy_sk_is_transparent(struct sock *sk) { - if (sk->sk_state != TCP_TIME_WAIT) { - if (inet_sk(sk)->transparent) - return true; - sock_put(sk); - } else { + switch (sk->sk_state) { + case TCP_TIME_WAIT: if (inet_twsk(sk)->tw_transparent) return true; - inet_twsk_put(inet_twsk(sk)); + break; + case TCP_NEW_SYN_RECV: + if (inet_rsk(inet_reqsk(sk))->no_srccheck) + return true; + break; + default: + if (inet_sk(sk)->transparent) + return true; } + + sock_gen_put(sk); return false; } @@ -266,7 +272,7 @@ tproxy_handle_time_wait4(struct sk_buff *skb, __be32 laddr, __be16 lport, hp->source, lport ? lport : hp->dest, skb->dev, NFT_LOOKUP_LISTENER); if (sk2) { - inet_twsk_deschedule(inet_twsk(sk), &tcp_death_row); + inet_twsk_deschedule(inet_twsk(sk)); inet_twsk_put(inet_twsk(sk)); sk = sk2; } @@ -431,7 +437,7 @@ tproxy_handle_time_wait6(struct sk_buff *skb, int tproto, int thoff, tgi->lport ? tgi->lport : hp->dest, skb->dev, NFT_LOOKUP_LISTENER); if (sk2) { - inet_twsk_deschedule(inet_twsk(sk), &tcp_death_row); + inet_twsk_deschedule(inet_twsk(sk)); inet_twsk_put(inet_twsk(sk)); sk = sk2; } diff --git a/net/netfilter/xt_cgroup.c b/net/netfilter/xt_cgroup.c index 7198d660b4de..a1d126f29463 100644 --- a/net/netfilter/xt_cgroup.c +++ b/net/netfilter/xt_cgroup.c @@ -39,7 +39,7 @@ cgroup_mt(const struct sk_buff *skb, struct xt_action_param *par) { const struct xt_cgroup_info *info = par->matchinfo; - if (skb->sk == NULL) + if (skb->sk == NULL || !sk_fullsock(skb->sk)) return false; return (info->id == skb->sk->sk_classid) ^ info->invert; diff --git a/net/netfilter/xt_physdev.c b/net/netfilter/xt_physdev.c index f440f57a452f..1caaccbc306c 100644 --- a/net/netfilter/xt_physdev.c +++ b/net/netfilter/xt_physdev.c @@ -25,16 +25,15 @@ MODULE_ALIAS("ip6t_physdev"); static bool physdev_mt(const struct sk_buff *skb, struct xt_action_param *par) { - static const char nulldevname[IFNAMSIZ] __attribute__((aligned(sizeof(long)))); const struct xt_physdev_info *info = par->matchinfo; + const struct net_device *physdev; unsigned long ret; const char *indev, *outdev; - const struct nf_bridge_info *nf_bridge; /* Not a bridged IP packet or no info available yet: * LOCAL_OUT/mangle and LOCAL_OUT/nat don't know if * the destination device will be a bridge. */ - if (!(nf_bridge = skb->nf_bridge)) { + if (!skb->nf_bridge) { /* Return MATCH if the invert flags of the used options are on */ if ((info->bitmask & XT_PHYSDEV_OP_BRIDGED) && !(info->invert & XT_PHYSDEV_OP_BRIDGED)) @@ -54,31 +53,41 @@ physdev_mt(const struct sk_buff *skb, struct xt_action_param *par) return true; } + physdev = nf_bridge_get_physoutdev(skb); + outdev = physdev ? physdev->name : NULL; + /* This only makes sense in the FORWARD and POSTROUTING chains */ if ((info->bitmask & XT_PHYSDEV_OP_BRIDGED) && - (!!(nf_bridge->mask & BRNF_BRIDGED) ^ - !(info->invert & XT_PHYSDEV_OP_BRIDGED))) + (!!outdev ^ !(info->invert & XT_PHYSDEV_OP_BRIDGED))) return false; + physdev = nf_bridge_get_physindev(skb); + indev = physdev ? physdev->name : NULL; + if ((info->bitmask & XT_PHYSDEV_OP_ISIN && - (!nf_bridge->physindev ^ !!(info->invert & XT_PHYSDEV_OP_ISIN))) || + (!indev ^ !!(info->invert & XT_PHYSDEV_OP_ISIN))) || (info->bitmask & XT_PHYSDEV_OP_ISOUT && - (!nf_bridge->physoutdev ^ !!(info->invert & XT_PHYSDEV_OP_ISOUT)))) + (!outdev ^ !!(info->invert & XT_PHYSDEV_OP_ISOUT)))) return false; if (!(info->bitmask & XT_PHYSDEV_OP_IN)) goto match_outdev; - indev = nf_bridge->physindev ? nf_bridge->physindev->name : nulldevname; - ret = ifname_compare_aligned(indev, info->physindev, info->in_mask); - if (!ret ^ !(info->invert & XT_PHYSDEV_OP_IN)) - return false; + if (indev) { + ret = ifname_compare_aligned(indev, info->physindev, + info->in_mask); + + if (!ret ^ !(info->invert & XT_PHYSDEV_OP_IN)) + return false; + } match_outdev: if (!(info->bitmask & XT_PHYSDEV_OP_OUT)) return true; - outdev = nf_bridge->physoutdev ? - nf_bridge->physoutdev->name : nulldevname; + + if (!outdev) + return false; + ret = ifname_compare_aligned(outdev, info->physoutdev, info->out_mask); return (!!ret ^ !(info->invert & XT_PHYSDEV_OP_OUT)); diff --git a/net/netfilter/xt_set.c b/net/netfilter/xt_set.c index 0d47afea9682..89045982ec94 100644 --- a/net/netfilter/xt_set.c +++ b/net/netfilter/xt_set.c @@ -193,7 +193,7 @@ set_match_v3(const struct sk_buff *skb, struct xt_action_param *par) return ret; if (!match_counter0(opt.ext.packets, &info->packets)) - return 0; + return false; return match_counter0(opt.ext.bytes, &info->bytes); } @@ -239,7 +239,7 @@ set_match_v4(const struct sk_buff *skb, struct xt_action_param *par) return ret; if (!match_counter(opt.ext.packets, &info->packets)) - return 0; + return false; return match_counter(opt.ext.bytes, &info->bytes); } diff --git a/net/netfilter/xt_socket.c b/net/netfilter/xt_socket.c index 13332dbf291d..e092cb046326 100644 --- a/net/netfilter/xt_socket.c +++ b/net/netfilter/xt_socket.c @@ -129,13 +129,24 @@ xt_socket_get_sock_v4(struct net *net, const u8 protocol, return NULL; } -static bool -socket_match(const struct sk_buff *skb, struct xt_action_param *par, - const struct xt_socket_mtinfo1 *info) +static bool xt_socket_sk_is_transparent(struct sock *sk) +{ + switch (sk->sk_state) { + case TCP_TIME_WAIT: + return inet_twsk(sk)->tw_transparent; + + case TCP_NEW_SYN_RECV: + return inet_rsk(inet_reqsk(sk))->no_srccheck; + + default: + return inet_sk(sk)->transparent; + } +} + +static struct sock *xt_socket_lookup_slow_v4(const struct sk_buff *skb, + const struct net_device *indev) { const struct iphdr *iph = ip_hdr(skb); - struct udphdr _hdr, *hp = NULL; - struct sock *sk = skb->sk; __be32 uninitialized_var(daddr), uninitialized_var(saddr); __be16 uninitialized_var(dport), uninitialized_var(sport); u8 uninitialized_var(protocol); @@ -145,10 +156,12 @@ socket_match(const struct sk_buff *skb, struct xt_action_param *par, #endif if (iph->protocol == IPPROTO_UDP || iph->protocol == IPPROTO_TCP) { + struct udphdr _hdr, *hp; + hp = skb_header_pointer(skb, ip_hdrlen(skb), sizeof(_hdr), &_hdr); if (hp == NULL) - return false; + return NULL; protocol = iph->protocol; saddr = iph->saddr; @@ -158,16 +171,17 @@ socket_match(const struct sk_buff *skb, struct xt_action_param *par, } else if (iph->protocol == IPPROTO_ICMP) { if (extract_icmp4_fields(skb, &protocol, &saddr, &daddr, - &sport, &dport)) - return false; + &sport, &dport)) + return NULL; } else { - return false; + return NULL; } #ifdef XT_SOCKET_HAVE_CONNTRACK - /* Do the lookup with the original socket address in case this is a - * reply packet of an established SNAT-ted connection. */ - + /* Do the lookup with the original socket address in + * case this is a reply packet of an established + * SNAT-ted connection. + */ ct = nf_ct_get(skb, &ctinfo); if (ct && !nf_ct_is_untracked(ct) && ((iph->protocol != IPPROTO_ICMP && @@ -183,10 +197,18 @@ socket_match(const struct sk_buff *skb, struct xt_action_param *par, } #endif + return xt_socket_get_sock_v4(dev_net(skb->dev), protocol, saddr, daddr, + sport, dport, indev); +} + +static bool +socket_match(const struct sk_buff *skb, struct xt_action_param *par, + const struct xt_socket_mtinfo1 *info) +{ + struct sock *sk = skb->sk; + if (!sk) - sk = xt_socket_get_sock_v4(dev_net(skb->dev), protocol, - saddr, daddr, sport, dport, - par->in); + sk = xt_socket_lookup_slow_v4(skb, par->in); if (sk) { bool wildcard; bool transparent = true; @@ -195,16 +217,14 @@ socket_match(const struct sk_buff *skb, struct xt_action_param *par, * unless XT_SOCKET_NOWILDCARD is set */ wildcard = (!(info->flags & XT_SOCKET_NOWILDCARD) && - sk->sk_state != TCP_TIME_WAIT && + sk_fullsock(sk) && inet_sk(sk)->inet_rcv_saddr == 0); /* Ignore non-transparent sockets, - if XT_SOCKET_TRANSPARENT is used */ + * if XT_SOCKET_TRANSPARENT is used + */ if (info->flags & XT_SOCKET_TRANSPARENT) - transparent = ((sk->sk_state != TCP_TIME_WAIT && - inet_sk(sk)->transparent) || - (sk->sk_state == TCP_TIME_WAIT && - inet_twsk(sk)->tw_transparent)); + transparent = xt_socket_sk_is_transparent(sk); if (sk != skb->sk) sock_gen_put(sk); @@ -213,12 +233,7 @@ socket_match(const struct sk_buff *skb, struct xt_action_param *par, sk = NULL; } - pr_debug("proto %hhu %pI4:%hu -> %pI4:%hu (orig %pI4:%hu) sock %p\n", - protocol, &saddr, ntohs(sport), - &daddr, ntohs(dport), - &iph->daddr, hp ? ntohs(hp->dest) : 0, sk); - - return (sk != NULL); + return sk != NULL; } static bool @@ -315,28 +330,26 @@ xt_socket_get_sock_v6(struct net *net, const u8 protocol, return NULL; } -static bool -socket_mt6_v1_v2(const struct sk_buff *skb, struct xt_action_param *par) +static struct sock *xt_socket_lookup_slow_v6(const struct sk_buff *skb, + const struct net_device *indev) { - struct ipv6hdr ipv6_var, *iph = ipv6_hdr(skb); - struct udphdr _hdr, *hp = NULL; - struct sock *sk = skb->sk; - const struct in6_addr *daddr = NULL, *saddr = NULL; __be16 uninitialized_var(dport), uninitialized_var(sport); - int thoff = 0, uninitialized_var(tproto); - const struct xt_socket_mtinfo1 *info = (struct xt_socket_mtinfo1 *) par->matchinfo; + const struct in6_addr *daddr = NULL, *saddr = NULL; + struct ipv6hdr *iph = ipv6_hdr(skb); + int thoff = 0, tproto; tproto = ipv6_find_hdr(skb, &thoff, -1, NULL, NULL); if (tproto < 0) { pr_debug("unable to find transport header in IPv6 packet, dropping\n"); - return NF_DROP; + return NULL; } if (tproto == IPPROTO_UDP || tproto == IPPROTO_TCP) { - hp = skb_header_pointer(skb, thoff, - sizeof(_hdr), &_hdr); + struct udphdr _hdr, *hp; + + hp = skb_header_pointer(skb, thoff, sizeof(_hdr), &_hdr); if (hp == NULL) - return false; + return NULL; saddr = &iph->saddr; sport = hp->source; @@ -344,17 +357,27 @@ socket_mt6_v1_v2(const struct sk_buff *skb, struct xt_action_param *par) dport = hp->dest; } else if (tproto == IPPROTO_ICMPV6) { + struct ipv6hdr ipv6_var; + if (extract_icmp6_fields(skb, thoff, &tproto, &saddr, &daddr, &sport, &dport, &ipv6_var)) - return false; + return NULL; } else { - return false; + return NULL; } + return xt_socket_get_sock_v6(dev_net(skb->dev), tproto, saddr, daddr, + sport, dport, indev); +} + +static bool +socket_mt6_v1_v2(const struct sk_buff *skb, struct xt_action_param *par) +{ + const struct xt_socket_mtinfo1 *info = (struct xt_socket_mtinfo1 *) par->matchinfo; + struct sock *sk = skb->sk; + if (!sk) - sk = xt_socket_get_sock_v6(dev_net(skb->dev), tproto, - saddr, daddr, sport, dport, - par->in); + sk = xt_socket_lookup_slow_v6(skb, par->in); if (sk) { bool wildcard; bool transparent = true; @@ -363,16 +386,14 @@ socket_mt6_v1_v2(const struct sk_buff *skb, struct xt_action_param *par) * unless XT_SOCKET_NOWILDCARD is set */ wildcard = (!(info->flags & XT_SOCKET_NOWILDCARD) && - sk->sk_state != TCP_TIME_WAIT && + sk_fullsock(sk) && ipv6_addr_any(&sk->sk_v6_rcv_saddr)); /* Ignore non-transparent sockets, - if XT_SOCKET_TRANSPARENT is used */ + * if XT_SOCKET_TRANSPARENT is used + */ if (info->flags & XT_SOCKET_TRANSPARENT) - transparent = ((sk->sk_state != TCP_TIME_WAIT && - inet_sk(sk)->transparent) || - (sk->sk_state == TCP_TIME_WAIT && - inet_twsk(sk)->tw_transparent)); + transparent = xt_socket_sk_is_transparent(sk); if (sk != skb->sk) sock_gen_put(sk); @@ -381,13 +402,7 @@ socket_mt6_v1_v2(const struct sk_buff *skb, struct xt_action_param *par) sk = NULL; } - pr_debug("proto %hhd %pI6:%hu -> %pI6:%hu " - "(orig %pI6:%hu) sock %p\n", - tproto, saddr, ntohs(sport), - daddr, ntohs(dport), - &iph->daddr, hp ? ntohs(hp->dest) : 0, sk); - - return (sk != NULL); + return sk != NULL; } #endif diff --git a/net/netfilter/xt_string.c b/net/netfilter/xt_string.c index 5699adb97652..0bc3460319c8 100644 --- a/net/netfilter/xt_string.c +++ b/net/netfilter/xt_string.c @@ -26,13 +26,12 @@ static bool string_mt(const struct sk_buff *skb, struct xt_action_param *par) { const struct xt_string_info *conf = par->matchinfo; - struct ts_state state; bool invert; invert = conf->u.v1.flags & XT_STRING_FLAG_INVERT; return (skb_find_text((struct sk_buff *)skb, conf->from_offset, - conf->to_offset, conf->config, &state) + conf->to_offset, conf->config) != UINT_MAX) ^ invert; } diff --git a/net/netlabel/netlabel_mgmt.c b/net/netlabel/netlabel_mgmt.c index 70440748fe5c..13f777f20995 100644 --- a/net/netlabel/netlabel_mgmt.c +++ b/net/netlabel/netlabel_mgmt.c @@ -293,15 +293,13 @@ static int netlbl_mgmt_listentry(struct sk_buff *skb, return -ENOMEM; addr_struct.s_addr = iter4->addr; - ret_val = nla_put(skb, NLBL_MGMT_A_IPV4ADDR, - sizeof(struct in_addr), - &addr_struct); + ret_val = nla_put_in_addr(skb, NLBL_MGMT_A_IPV4ADDR, + addr_struct.s_addr); if (ret_val != 0) return ret_val; addr_struct.s_addr = iter4->mask; - ret_val = nla_put(skb, NLBL_MGMT_A_IPV4MASK, - sizeof(struct in_addr), - &addr_struct); + ret_val = nla_put_in_addr(skb, NLBL_MGMT_A_IPV4MASK, + addr_struct.s_addr); if (ret_val != 0) return ret_val; map4 = netlbl_domhsh_addr4_entry(iter4); @@ -328,14 +326,12 @@ static int netlbl_mgmt_listentry(struct sk_buff *skb, if (nla_b == NULL) return -ENOMEM; - ret_val = nla_put(skb, NLBL_MGMT_A_IPV6ADDR, - sizeof(struct in6_addr), - &iter6->addr); + ret_val = nla_put_in6_addr(skb, NLBL_MGMT_A_IPV6ADDR, + &iter6->addr); if (ret_val != 0) return ret_val; - ret_val = nla_put(skb, NLBL_MGMT_A_IPV6MASK, - sizeof(struct in6_addr), - &iter6->mask); + ret_val = nla_put_in6_addr(skb, NLBL_MGMT_A_IPV6MASK, + &iter6->mask); if (ret_val != 0) return ret_val; map6 = netlbl_domhsh_addr6_entry(iter6); diff --git a/net/netlabel/netlabel_unlabeled.c b/net/netlabel/netlabel_unlabeled.c index aec7994f78cf..b0380927f05f 100644 --- a/net/netlabel/netlabel_unlabeled.c +++ b/net/netlabel/netlabel_unlabeled.c @@ -1117,34 +1117,30 @@ static int netlbl_unlabel_staticlist_gen(u32 cmd, struct in_addr addr_struct; addr_struct.s_addr = addr4->list.addr; - ret_val = nla_put(cb_arg->skb, - NLBL_UNLABEL_A_IPV4ADDR, - sizeof(struct in_addr), - &addr_struct); + ret_val = nla_put_in_addr(cb_arg->skb, + NLBL_UNLABEL_A_IPV4ADDR, + addr_struct.s_addr); if (ret_val != 0) goto list_cb_failure; addr_struct.s_addr = addr4->list.mask; - ret_val = nla_put(cb_arg->skb, - NLBL_UNLABEL_A_IPV4MASK, - sizeof(struct in_addr), - &addr_struct); + ret_val = nla_put_in_addr(cb_arg->skb, + NLBL_UNLABEL_A_IPV4MASK, + addr_struct.s_addr); if (ret_val != 0) goto list_cb_failure; secid = addr4->secid; } else { - ret_val = nla_put(cb_arg->skb, - NLBL_UNLABEL_A_IPV6ADDR, - sizeof(struct in6_addr), - &addr6->list.addr); + ret_val = nla_put_in6_addr(cb_arg->skb, + NLBL_UNLABEL_A_IPV6ADDR, + &addr6->list.addr); if (ret_val != 0) goto list_cb_failure; - ret_val = nla_put(cb_arg->skb, - NLBL_UNLABEL_A_IPV6MASK, - sizeof(struct in6_addr), - &addr6->list.mask); + ret_val = nla_put_in6_addr(cb_arg->skb, + NLBL_UNLABEL_A_IPV6MASK, + &addr6->list.mask); if (ret_val != 0) goto list_cb_failure; diff --git a/net/netlink/af_netlink.c b/net/netlink/af_netlink.c index 05919bf3f670..ec4adbdcb9b4 100644 --- a/net/netlink/af_netlink.c +++ b/net/netlink/af_netlink.c @@ -116,6 +116,8 @@ static ATOMIC_NOTIFIER_HEAD(netlink_chain); static DEFINE_SPINLOCK(netlink_tap_lock); static struct list_head netlink_tap_all __read_mostly; +static const struct rhashtable_params netlink_rhashtable_params; + static inline u32 netlink_group_mask(u32 group) { return group ? 1 << (group - 1) : 0; @@ -970,41 +972,50 @@ netlink_unlock_table(void) struct netlink_compare_arg { - struct net *net; + possible_net_t pnet; u32 portid; }; -static bool netlink_compare(void *ptr, void *arg) +/* Doing sizeof directly may yield 4 extra bytes on 64-bit. */ +#define netlink_compare_arg_len \ + (offsetof(struct netlink_compare_arg, portid) + sizeof(u32)) + +static inline int netlink_compare(struct rhashtable_compare_arg *arg, + const void *ptr) { - struct netlink_compare_arg *x = arg; - struct sock *sk = ptr; + const struct netlink_compare_arg *x = arg->key; + const struct netlink_sock *nlk = ptr; + + return nlk->portid != x->portid || + !net_eq(sock_net(&nlk->sk), read_pnet(&x->pnet)); +} - return nlk_sk(sk)->portid == x->portid && - net_eq(sock_net(sk), x->net); +static void netlink_compare_arg_init(struct netlink_compare_arg *arg, + struct net *net, u32 portid) +{ + memset(arg, 0, sizeof(*arg)); + write_pnet(&arg->pnet, net); + arg->portid = portid; } static struct sock *__netlink_lookup(struct netlink_table *table, u32 portid, struct net *net) { - struct netlink_compare_arg arg = { - .net = net, - .portid = portid, - }; + struct netlink_compare_arg arg; - return rhashtable_lookup_compare(&table->hash, &portid, - &netlink_compare, &arg); + netlink_compare_arg_init(&arg, net, portid); + return rhashtable_lookup_fast(&table->hash, &arg, + netlink_rhashtable_params); } -static bool __netlink_insert(struct netlink_table *table, struct sock *sk) +static int __netlink_insert(struct netlink_table *table, struct sock *sk) { - struct netlink_compare_arg arg = { - .net = sock_net(sk), - .portid = nlk_sk(sk)->portid, - }; + struct netlink_compare_arg arg; - return rhashtable_lookup_compare_insert(&table->hash, - &nlk_sk(sk)->node, - &netlink_compare, &arg); + netlink_compare_arg_init(&arg, sock_net(sk), nlk_sk(sk)->portid); + return rhashtable_lookup_insert_key(&table->hash, &arg, + &nlk_sk(sk)->node, + netlink_rhashtable_params); } static struct sock *netlink_lookup(struct net *net, int protocol, u32 portid) @@ -1066,9 +1077,10 @@ static int netlink_insert(struct sock *sk, u32 portid) nlk_sk(sk)->portid = portid; sock_hold(sk); - err = 0; - if (!__netlink_insert(table, sk)) { - err = -EADDRINUSE; + err = __netlink_insert(table, sk); + if (err) { + if (err == -EEXIST) + err = -EADDRINUSE; sock_put(sk); } @@ -1082,7 +1094,8 @@ static void netlink_remove(struct sock *sk) struct netlink_table *table; table = &nl_table[sk->sk_protocol]; - if (rhashtable_remove(&table->hash, &nlk_sk(sk)->node)) { + if (!rhashtable_remove_fast(&table->hash, &nlk_sk(sk)->node, + netlink_rhashtable_params)) { WARN_ON(atomic_read(&sk->sk_refcnt) == 1); __sock_put(sk); } @@ -1616,13 +1629,11 @@ static struct sk_buff *netlink_alloc_large_skb(unsigned int size, if (data == NULL) return NULL; - skb = build_skb(data, size); + skb = __build_skb(data, size); if (skb == NULL) vfree(data); - else { - skb->head_frag = 0; + else skb->destructor = netlink_skb_destructor; - } return skb; } @@ -2256,8 +2267,7 @@ static void netlink_cmsg_recv_pktinfo(struct msghdr *msg, struct sk_buff *skb) put_cmsg(msg, SOL_NETLINK, NETLINK_PKTINFO, sizeof(info), &info); } -static int netlink_sendmsg(struct kiocb *kiocb, struct socket *sock, - struct msghdr *msg, size_t len) +static int netlink_sendmsg(struct socket *sock, struct msghdr *msg, size_t len) { struct sock *sk = sock->sk; struct netlink_sock *nlk = nlk_sk(sk); @@ -2346,8 +2356,7 @@ out: return err; } -static int netlink_recvmsg(struct kiocb *kiocb, struct socket *sock, - struct msghdr *msg, size_t len, +static int netlink_recvmsg(struct socket *sock, struct msghdr *msg, size_t len, int flags) { struct scm_cookie scm; @@ -3116,17 +3125,28 @@ static struct pernet_operations __net_initdata netlink_net_ops = { .exit = netlink_net_exit, }; +static inline u32 netlink_hash(const void *data, u32 len, u32 seed) +{ + const struct netlink_sock *nlk = data; + struct netlink_compare_arg arg; + + netlink_compare_arg_init(&arg, sock_net(&nlk->sk), nlk->portid); + return jhash2((u32 *)&arg, netlink_compare_arg_len / sizeof(u32), seed); +} + +static const struct rhashtable_params netlink_rhashtable_params = { + .head_offset = offsetof(struct netlink_sock, node), + .key_len = netlink_compare_arg_len, + .obj_hashfn = netlink_hash, + .obj_cmpfn = netlink_compare, + .max_size = 65536, + .automatic_shrinking = true, +}; + static int __init netlink_proto_init(void) { int i; 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 = jhash, - .max_shift = 16, /* 64K */ - }; if (err != 0) goto out; @@ -3138,7 +3158,8 @@ static int __init netlink_proto_init(void) goto panic; for (i = 0; i < MAX_LINKS; i++) { - if (rhashtable_init(&nl_table[i].hash, &ht_params) < 0) { + if (rhashtable_init(&nl_table[i].hash, + &netlink_rhashtable_params) < 0) { while (--i > 0) rhashtable_destroy(&nl_table[i].hash); kfree(nl_table); diff --git a/net/netrom/af_netrom.c b/net/netrom/af_netrom.c index 69f1d5e9959f..b987fd56c3c5 100644 --- a/net/netrom/af_netrom.c +++ b/net/netrom/af_netrom.c @@ -1023,8 +1023,7 @@ int nr_rx_frame(struct sk_buff *skb, struct net_device *dev) return 1; } -static int nr_sendmsg(struct kiocb *iocb, struct socket *sock, - struct msghdr *msg, size_t len) +static int nr_sendmsg(struct socket *sock, struct msghdr *msg, size_t len) { struct sock *sk = sock->sk; struct nr_sock *nr = nr_sk(sk); @@ -1133,8 +1132,8 @@ out: return err; } -static int nr_recvmsg(struct kiocb *iocb, struct socket *sock, - struct msghdr *msg, size_t size, int flags) +static int nr_recvmsg(struct socket *sock, struct msghdr *msg, size_t size, + int flags) { struct sock *sk = sock->sk; DECLARE_SOCKADDR(struct sockaddr_ax25 *, sax, msg->msg_name); diff --git a/net/netrom/nr_dev.c b/net/netrom/nr_dev.c index 6ae063cebf7d..988f542481a8 100644 --- a/net/netrom/nr_dev.c +++ b/net/netrom/nr_dev.c @@ -65,36 +65,6 @@ int nr_rx_ip(struct sk_buff *skb, struct net_device *dev) return 1; } -#ifdef CONFIG_INET - -static int nr_rebuild_header(struct sk_buff *skb) -{ - unsigned char *bp = skb->data; - - if (arp_find(bp + 7, skb)) - return 1; - - bp[6] &= ~AX25_CBIT; - bp[6] &= ~AX25_EBIT; - bp[6] |= AX25_SSSID_SPARE; - bp += AX25_ADDR_LEN; - - bp[6] &= ~AX25_CBIT; - bp[6] |= AX25_EBIT; - bp[6] |= AX25_SSSID_SPARE; - - return 0; -} - -#else - -static int nr_rebuild_header(struct sk_buff *skb) -{ - return 1; -} - -#endif - static int nr_header(struct sk_buff *skb, struct net_device *dev, unsigned short type, const void *daddr, const void *saddr, unsigned int len) @@ -188,7 +158,6 @@ static netdev_tx_t nr_xmit(struct sk_buff *skb, struct net_device *dev) static const struct header_ops nr_header_ops = { .create = nr_header, - .rebuild= nr_rebuild_header, }; static const struct net_device_ops nr_netdev_ops = { diff --git a/net/nfc/llcp_sock.c b/net/nfc/llcp_sock.c index e181e290427c..9578bd6a4f3e 100644 --- a/net/nfc/llcp_sock.c +++ b/net/nfc/llcp_sock.c @@ -750,8 +750,8 @@ error: return ret; } -static int llcp_sock_sendmsg(struct kiocb *iocb, struct socket *sock, - struct msghdr *msg, size_t len) +static int llcp_sock_sendmsg(struct socket *sock, struct msghdr *msg, + size_t len) { struct sock *sk = sock->sk; struct nfc_llcp_sock *llcp_sock = nfc_llcp_sock(sk); @@ -793,8 +793,8 @@ static int llcp_sock_sendmsg(struct kiocb *iocb, struct socket *sock, return nfc_llcp_send_i_frame(llcp_sock, msg, len); } -static int llcp_sock_recvmsg(struct kiocb *iocb, struct socket *sock, - struct msghdr *msg, size_t len, int flags) +static int llcp_sock_recvmsg(struct socket *sock, struct msghdr *msg, + size_t len, int flags) { int noblock = flags & MSG_DONTWAIT; struct sock *sk = sock->sk; diff --git a/net/nfc/nci/core.c b/net/nfc/nci/core.c index 9575a1892607..49ff32106080 100644 --- a/net/nfc/nci/core.c +++ b/net/nfc/nci/core.c @@ -907,6 +907,16 @@ static int nci_se_io(struct nfc_dev *nfc_dev, u32 se_idx, return 0; } +static int nci_fw_download(struct nfc_dev *nfc_dev, const char *firmware_name) +{ + struct nci_dev *ndev = nfc_get_drvdata(nfc_dev); + + if (!ndev->ops->fw_download) + return -ENOTSUPP; + + return ndev->ops->fw_download(ndev, firmware_name); +} + static struct nfc_ops nci_nfc_ops = { .dev_up = nci_dev_up, .dev_down = nci_dev_down, @@ -922,6 +932,7 @@ static struct nfc_ops nci_nfc_ops = { .disable_se = nci_disable_se, .discover_se = nci_discover_se, .se_io = nci_se_io, + .fw_download = nci_fw_download, }; /* ---- Interface to NCI drivers ---- */ diff --git a/net/nfc/netlink.c b/net/nfc/netlink.c index 14a2d11581da..3763036710ae 100644 --- a/net/nfc/netlink.c +++ b/net/nfc/netlink.c @@ -1584,7 +1584,7 @@ static const struct genl_ops nfc_genl_ops[] = { struct urelease_work { struct work_struct w; - int portid; + u32 portid; }; static void nfc_urelease_event_work(struct work_struct *work) diff --git a/net/nfc/rawsock.c b/net/nfc/rawsock.c index 373e138c0ab6..82b4e8024778 100644 --- a/net/nfc/rawsock.c +++ b/net/nfc/rawsock.c @@ -211,8 +211,7 @@ static void rawsock_tx_work(struct work_struct *work) } } -static int rawsock_sendmsg(struct kiocb *iocb, struct socket *sock, - struct msghdr *msg, size_t len) +static int rawsock_sendmsg(struct socket *sock, struct msghdr *msg, size_t len) { struct sock *sk = sock->sk; struct nfc_dev *dev = nfc_rawsock(sk)->dev; @@ -248,8 +247,8 @@ static int rawsock_sendmsg(struct kiocb *iocb, struct socket *sock, return len; } -static int rawsock_recvmsg(struct kiocb *iocb, struct socket *sock, - struct msghdr *msg, size_t len, int flags) +static int rawsock_recvmsg(struct socket *sock, struct msghdr *msg, size_t len, + int flags) { int noblock = flags & MSG_DONTWAIT; struct sock *sk = sock->sk; diff --git a/net/openvswitch/Kconfig b/net/openvswitch/Kconfig index b7d818c59423..ed6b0f8dd1bb 100644 --- a/net/openvswitch/Kconfig +++ b/net/openvswitch/Kconfig @@ -6,6 +6,7 @@ config OPENVSWITCH tristate "Open vSwitch" depends on INET select LIBCRC32C + select MPLS select NET_MPLS_GSO ---help--- Open vSwitch is a multilayer Ethernet switch targeted at virtualized diff --git a/net/openvswitch/datapath.c b/net/openvswitch/datapath.c index 5bae7243c577..096c6276e6b9 100644 --- a/net/openvswitch/datapath.c +++ b/net/openvswitch/datapath.c @@ -203,7 +203,6 @@ static void destroy_dp_rcu(struct rcu_head *rcu) ovs_flow_tbl_destroy(&dp->table); free_percpu(dp->stats_percpu); - release_net(ovs_dp_get_net(dp)); kfree(dp->ports); kfree(dp); } @@ -1501,7 +1500,7 @@ static int ovs_dp_cmd_new(struct sk_buff *skb, struct genl_info *info) if (dp == NULL) goto err_free_reply; - ovs_dp_set_net(dp, hold_net(sock_net(skb->sk))); + ovs_dp_set_net(dp, sock_net(skb->sk)); /* Allocate table. */ err = ovs_flow_tbl_init(&dp->table); @@ -1575,7 +1574,6 @@ err_destroy_percpu: err_destroy_table: ovs_flow_tbl_destroy(&dp->table); err_free_dp: - release_net(ovs_dp_get_net(dp)); kfree(dp); err_free_reply: kfree_skb(reply); diff --git a/net/openvswitch/datapath.h b/net/openvswitch/datapath.h index 3ece94563079..4ec4a480b147 100644 --- a/net/openvswitch/datapath.h +++ b/net/openvswitch/datapath.h @@ -84,10 +84,8 @@ struct datapath { /* Stats. */ struct dp_stats_percpu __percpu *stats_percpu; -#ifdef CONFIG_NET_NS /* Network namespace ref. */ - struct net *net; -#endif + possible_net_t net; u32 user_features; }; diff --git a/net/openvswitch/flow.c b/net/openvswitch/flow.c index 50ec42f170a0..2dacc7b5af23 100644 --- a/net/openvswitch/flow.c +++ b/net/openvswitch/flow.c @@ -100,7 +100,9 @@ void ovs_flow_stats_update(struct sw_flow *flow, __be16 tcp_flags, new_stats = kmem_cache_alloc_node(flow_stats_cache, - GFP_THISNODE | + GFP_NOWAIT | + __GFP_THISNODE | + __GFP_NOWARN | __GFP_NOMEMALLOC, node); if (likely(new_stats)) { diff --git a/net/openvswitch/flow_netlink.c b/net/openvswitch/flow_netlink.c index 22b18c145c92..c691b1a1eee0 100644 --- a/net/openvswitch/flow_netlink.c +++ b/net/openvswitch/flow_netlink.c @@ -535,11 +535,11 @@ static int ipv4_tun_from_nlattr(const struct nlattr *attr, break; case OVS_TUNNEL_KEY_ATTR_IPV4_SRC: SW_FLOW_KEY_PUT(match, tun_key.ipv4_src, - nla_get_be32(a), is_mask); + nla_get_in_addr(a), is_mask); break; case OVS_TUNNEL_KEY_ATTR_IPV4_DST: SW_FLOW_KEY_PUT(match, tun_key.ipv4_dst, - nla_get_be32(a), is_mask); + nla_get_in_addr(a), is_mask); break; case OVS_TUNNEL_KEY_ATTR_TOS: SW_FLOW_KEY_PUT(match, tun_key.ipv4_tos, @@ -648,10 +648,12 @@ static int __ipv4_tun_to_nlattr(struct sk_buff *skb, nla_put_be64(skb, OVS_TUNNEL_KEY_ATTR_ID, output->tun_id)) return -EMSGSIZE; if (output->ipv4_src && - nla_put_be32(skb, OVS_TUNNEL_KEY_ATTR_IPV4_SRC, output->ipv4_src)) + nla_put_in_addr(skb, OVS_TUNNEL_KEY_ATTR_IPV4_SRC, + output->ipv4_src)) return -EMSGSIZE; if (output->ipv4_dst && - nla_put_be32(skb, OVS_TUNNEL_KEY_ATTR_IPV4_DST, output->ipv4_dst)) + nla_put_in_addr(skb, OVS_TUNNEL_KEY_ATTR_IPV4_DST, + output->ipv4_dst)) return -EMSGSIZE; if (output->ipv4_tos && nla_put_u8(skb, OVS_TUNNEL_KEY_ATTR_TOS, output->ipv4_tos)) diff --git a/net/openvswitch/vport-vxlan.c b/net/openvswitch/vport-vxlan.c index 3277a7520e31..6d39766e7828 100644 --- a/net/openvswitch/vport-vxlan.c +++ b/net/openvswitch/vport-vxlan.c @@ -222,7 +222,8 @@ static int vxlan_tnl_send(struct vport *vport, struct sk_buff *skb) { struct net *net = ovs_dp_get_net(vport->dp); struct vxlan_port *vxlan_port = vxlan_vport(vport); - __be16 dst_port = inet_sk(vxlan_port->vs->sock->sk)->inet_sport; + struct sock *sk = vxlan_port->vs->sock->sk; + __be16 dst_port = inet_sk(sk)->inet_sport; const struct ovs_key_ipv4_tunnel *tun_key; struct vxlan_metadata md = {0}; struct rtable *rt; @@ -255,7 +256,7 @@ static int vxlan_tnl_send(struct vport *vport, struct sk_buff *skb) vxflags = vxlan_port->exts | (tun_key->tun_flags & TUNNEL_CSUM ? VXLAN_F_UDP_CSUM : 0); - err = vxlan_xmit_skb(rt, skb, fl.saddr, tun_key->ipv4_dst, + err = vxlan_xmit_skb(rt, sk, skb, fl.saddr, tun_key->ipv4_dst, tun_key->ipv4_tos, tun_key->ipv4_ttl, df, src_port, dst_port, &md, false, vxflags); diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c index f8db7064d81c..5102c3cc4eec 100644 --- a/net/packet/af_packet.c +++ b/net/packet/af_packet.c @@ -216,10 +216,16 @@ static void prb_fill_vlan_info(struct tpacket_kbdq_core *, static void packet_flush_mclist(struct sock *sk); struct packet_skb_cb { - unsigned int origlen; union { struct sockaddr_pkt pkt; - struct sockaddr_ll ll; + union { + /* Trick: alias skb original length with + * ll.sll_family and ll.protocol in order + * to save room. + */ + unsigned int origlen; + struct sockaddr_ll ll; + }; } sa; }; @@ -1608,8 +1614,8 @@ oom: * protocol layers and you must therefore supply it with a complete frame */ -static int packet_sendmsg_spkt(struct kiocb *iocb, struct socket *sock, - struct msghdr *msg, size_t len) +static int packet_sendmsg_spkt(struct socket *sock, struct msghdr *msg, + size_t len) { struct sock *sk = sock->sk; DECLARE_SOCKADDR(struct sockaddr_pkt *, saddr, msg->msg_name); @@ -1818,13 +1824,10 @@ static int packet_rcv(struct sk_buff *skb, struct net_device *dev, skb = nskb; } - BUILD_BUG_ON(sizeof(*PACKET_SKB_CB(skb)) + MAX_ADDR_LEN - 8 > - sizeof(skb->cb)); + sock_skb_cb_check_size(sizeof(*PACKET_SKB_CB(skb)) + MAX_ADDR_LEN - 8); sll = &PACKET_SKB_CB(skb)->sa.ll; - sll->sll_family = AF_PACKET; sll->sll_hatype = dev->type; - sll->sll_protocol = skb->protocol; sll->sll_pkttype = skb->pkt_type; if (unlikely(po->origdev)) sll->sll_ifindex = orig_dev->ifindex; @@ -1833,7 +1836,10 @@ static int packet_rcv(struct sk_buff *skb, struct net_device *dev, sll->sll_halen = dev_parse_header(skb, sll->sll_addr); - PACKET_SKB_CB(skb)->origlen = skb->len; + /* sll->sll_family and sll->sll_protocol are set in packet_recvmsg(). + * Use their space for storing the original skb length. + */ + PACKET_SKB_CB(skb)->sa.origlen = skb->len; if (pskb_trim(skb, snaplen)) goto drop_n_acct; @@ -1847,7 +1853,7 @@ static int packet_rcv(struct sk_buff *skb, struct net_device *dev, spin_lock(&sk->sk_receive_queue.lock); po->stats.stats1.tp_packets++; - skb->dropcount = atomic_read(&sk->sk_drops); + sock_skb_set_dropcount(sk, skb); __skb_queue_tail(&sk->sk_receive_queue, skb); spin_unlock(&sk->sk_receive_queue.lock); sk->sk_data_ready(sk); @@ -1910,14 +1916,19 @@ static int tpacket_rcv(struct sk_buff *skb, struct net_device *dev, } } - if (skb->ip_summed == CHECKSUM_PARTIAL) - status |= TP_STATUS_CSUMNOTREADY; - snaplen = skb->len; res = run_filter(skb, sk, snaplen); if (!res) goto drop_n_restore; + + if (skb->ip_summed == CHECKSUM_PARTIAL) + status |= TP_STATUS_CSUMNOTREADY; + else if (skb->pkt_type != PACKET_OUTGOING && + (skb->ip_summed == CHECKSUM_COMPLETE || + skb_csum_unnecessary(skb))) + status |= TP_STATUS_CSUM_VALID; + if (snaplen > res) snaplen = res; @@ -2603,8 +2614,7 @@ out: return err; } -static int packet_sendmsg(struct kiocb *iocb, struct socket *sock, - struct msghdr *msg, size_t len) +static int packet_sendmsg(struct socket *sock, struct msghdr *msg, size_t len) { struct sock *sk = sock->sk; struct packet_sock *po = pkt_sk(sk); @@ -2884,13 +2894,14 @@ out: * If necessary we block. */ -static int packet_recvmsg(struct kiocb *iocb, struct socket *sock, - struct msghdr *msg, size_t len, int flags) +static int packet_recvmsg(struct socket *sock, struct msghdr *msg, size_t len, + int flags) { struct sock *sk = sock->sk; struct sk_buff *skb; int copied, err; int vnet_hdr_len = 0; + unsigned int origlen = 0; err = -EINVAL; if (flags & ~(MSG_PEEK|MSG_DONTWAIT|MSG_TRUNC|MSG_CMSG_COMPAT|MSG_ERRQUEUE)) @@ -2990,6 +3001,15 @@ static int packet_recvmsg(struct kiocb *iocb, struct socket *sock, if (err) goto out_free; + if (sock->type != SOCK_PACKET) { + struct sockaddr_ll *sll = &PACKET_SKB_CB(skb)->sa.ll; + + /* Original length was stored in sockaddr_ll fields */ + origlen = PACKET_SKB_CB(skb)->sa.origlen; + sll->sll_family = AF_PACKET; + sll->sll_protocol = skb->protocol; + } + sock_recv_ts_and_drops(msg, sk, skb); if (msg->msg_name) { @@ -3001,6 +3021,7 @@ static int packet_recvmsg(struct kiocb *iocb, struct socket *sock, msg->msg_namelen = sizeof(struct sockaddr_pkt); } else { struct sockaddr_ll *sll = &PACKET_SKB_CB(skb)->sa.ll; + msg->msg_namelen = sll->sll_halen + offsetof(struct sockaddr_ll, sll_addr); } @@ -3014,7 +3035,12 @@ static int packet_recvmsg(struct kiocb *iocb, struct socket *sock, aux.tp_status = TP_STATUS_USER; if (skb->ip_summed == CHECKSUM_PARTIAL) aux.tp_status |= TP_STATUS_CSUMNOTREADY; - aux.tp_len = PACKET_SKB_CB(skb)->origlen; + else if (skb->pkt_type != PACKET_OUTGOING && + (skb->ip_summed == CHECKSUM_COMPLETE || + skb_csum_unnecessary(skb))) + aux.tp_status |= TP_STATUS_CSUM_VALID; + + aux.tp_len = origlen; aux.tp_snaplen = skb->len; aux.tp_mac = 0; aux.tp_net = skb_network_offset(skb); diff --git a/net/packet/internal.h b/net/packet/internal.h index cdddf6a30399..fe6e20caea1d 100644 --- a/net/packet/internal.h +++ b/net/packet/internal.h @@ -74,9 +74,7 @@ extern struct mutex fanout_mutex; #define PACKET_FANOUT_MAX 256 struct packet_fanout { -#ifdef CONFIG_NET_NS - struct net *net; -#endif + possible_net_t net; unsigned int num_members; u16 id; u8 type; diff --git a/net/phonet/datagram.c b/net/phonet/datagram.c index 26054b4b467c..5e710435ffa9 100644 --- a/net/phonet/datagram.c +++ b/net/phonet/datagram.c @@ -83,8 +83,7 @@ static int pn_init(struct sock *sk) return 0; } -static int pn_sendmsg(struct kiocb *iocb, struct sock *sk, - struct msghdr *msg, size_t len) +static int pn_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) { DECLARE_SOCKADDR(struct sockaddr_pn *, target, msg->msg_name); struct sk_buff *skb; @@ -125,9 +124,8 @@ static int pn_sendmsg(struct kiocb *iocb, struct sock *sk, return (err >= 0) ? len : err; } -static int pn_recvmsg(struct kiocb *iocb, struct sock *sk, - struct msghdr *msg, size_t len, int noblock, - int flags, int *addr_len) +static int pn_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, + int noblock, int flags, int *addr_len) { struct sk_buff *skb = NULL; struct sockaddr_pn sa; diff --git a/net/phonet/pep.c b/net/phonet/pep.c index 5d3f2b7507d4..6de2aeb98a1f 100644 --- a/net/phonet/pep.c +++ b/net/phonet/pep.c @@ -1118,8 +1118,7 @@ static int pipe_skb_send(struct sock *sk, struct sk_buff *skb) } -static int pep_sendmsg(struct kiocb *iocb, struct sock *sk, - struct msghdr *msg, size_t len) +static int pep_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) { struct pep_sock *pn = pep_sk(sk); struct sk_buff *skb; @@ -1246,9 +1245,8 @@ struct sk_buff *pep_read(struct sock *sk) return skb; } -static int pep_recvmsg(struct kiocb *iocb, struct sock *sk, - struct msghdr *msg, size_t len, int noblock, - int flags, int *addr_len) +static int pep_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, + int noblock, int flags, int *addr_len) { struct sk_buff *skb; int err; diff --git a/net/phonet/socket.c b/net/phonet/socket.c index 008214a3d5eb..d575ef4e9aa6 100644 --- a/net/phonet/socket.c +++ b/net/phonet/socket.c @@ -425,15 +425,15 @@ out: return err; } -static int pn_socket_sendmsg(struct kiocb *iocb, struct socket *sock, - struct msghdr *m, size_t total_len) +static int pn_socket_sendmsg(struct socket *sock, struct msghdr *m, + size_t total_len) { struct sock *sk = sock->sk; if (pn_socket_autobind(sock)) return -EAGAIN; - return sk->sk_prot->sendmsg(iocb, sk, m, total_len); + return sk->sk_prot->sendmsg(sk, m, total_len); } const struct proto_ops phonet_dgram_ops = { diff --git a/net/rds/connection.c b/net/rds/connection.c index 378c3a6acf84..14f041398ca1 100644 --- a/net/rds/connection.c +++ b/net/rds/connection.c @@ -130,7 +130,7 @@ static struct rds_connection *__rds_conn_create(__be32 laddr, __be32 faddr, rcu_read_lock(); conn = rds_conn_lookup(head, laddr, faddr, trans); if (conn && conn->c_loopback && conn->c_trans != &rds_loop_transport && - !is_outgoing) { + laddr == faddr && !is_outgoing) { /* This is a looped back IB connection, and we're * called by the code handling the incoming connect. * We need a second connection object into which we @@ -193,6 +193,7 @@ static struct rds_connection *__rds_conn_create(__be32 laddr, __be32 faddr, } atomic_set(&conn->c_state, RDS_CONN_DOWN); + conn->c_send_gen = 0; conn->c_reconnect_jiffies = 0; INIT_DELAYED_WORK(&conn->c_send_w, rds_send_worker); INIT_DELAYED_WORK(&conn->c_recv_w, rds_recv_worker); diff --git a/net/rds/rds.h b/net/rds/rds.h index c2a5eef41343..0d41155a2258 100644 --- a/net/rds/rds.h +++ b/net/rds/rds.h @@ -110,6 +110,7 @@ struct rds_connection { void *c_transport_data; atomic_t c_state; + unsigned long c_send_gen; unsigned long c_flags; unsigned long c_reconnect_jiffies; struct delayed_work c_send_w; @@ -702,8 +703,8 @@ void rds_inc_init(struct rds_incoming *inc, struct rds_connection *conn, void rds_inc_put(struct rds_incoming *inc); void rds_recv_incoming(struct rds_connection *conn, __be32 saddr, __be32 daddr, struct rds_incoming *inc, gfp_t gfp); -int rds_recvmsg(struct kiocb *iocb, struct socket *sock, struct msghdr *msg, - size_t size, int msg_flags); +int rds_recvmsg(struct socket *sock, struct msghdr *msg, size_t size, + int msg_flags); void rds_clear_recv_queue(struct rds_sock *rs); int rds_notify_queue_get(struct rds_sock *rs, struct msghdr *msg); void rds_inc_info_copy(struct rds_incoming *inc, @@ -711,8 +712,7 @@ void rds_inc_info_copy(struct rds_incoming *inc, __be32 saddr, __be32 daddr, int flip); /* send.c */ -int rds_sendmsg(struct kiocb *iocb, struct socket *sock, struct msghdr *msg, - size_t payload_len); +int rds_sendmsg(struct socket *sock, struct msghdr *msg, size_t payload_len); void rds_send_reset(struct rds_connection *conn); int rds_send_xmit(struct rds_connection *conn); struct sockaddr_in; diff --git a/net/rds/recv.c b/net/rds/recv.c index f9ec1acd801c..a00462b0d01d 100644 --- a/net/rds/recv.c +++ b/net/rds/recv.c @@ -395,8 +395,8 @@ static int rds_cmsg_recv(struct rds_incoming *inc, struct msghdr *msg) return 0; } -int rds_recvmsg(struct kiocb *iocb, struct socket *sock, struct msghdr *msg, - size_t size, int msg_flags) +int rds_recvmsg(struct socket *sock, struct msghdr *msg, size_t size, + int msg_flags) { struct sock *sk = sock->sk; struct rds_sock *rs = rds_sk_to_rs(sk); diff --git a/net/rds/send.c b/net/rds/send.c index 42f65d4305c8..e9430f537f9c 100644 --- a/net/rds/send.c +++ b/net/rds/send.c @@ -140,8 +140,11 @@ int rds_send_xmit(struct rds_connection *conn) struct scatterlist *sg; int ret = 0; LIST_HEAD(to_be_dropped); + int batch_count; + unsigned long send_gen = 0; restart: + batch_count = 0; /* * sendmsg calls here after having queued its message on the send @@ -157,6 +160,17 @@ restart: } /* + * we record the send generation after doing the xmit acquire. + * if someone else manages to jump in and do some work, we'll use + * this to avoid a goto restart farther down. + * + * The acquire_in_xmit() check above ensures that only one + * caller can increment c_send_gen at any time. + */ + conn->c_send_gen++; + send_gen = conn->c_send_gen; + + /* * rds_conn_shutdown() sets the conn state and then tests RDS_IN_XMIT, * we do the opposite to avoid races. */ @@ -202,6 +216,16 @@ restart: if (!rm) { unsigned int len; + batch_count++; + + /* we want to process as big a batch as we can, but + * we also want to avoid softlockups. If we've been + * through a lot of messages, lets back off and see + * if anyone else jumps in + */ + if (batch_count >= 1024) + goto over_batch; + spin_lock_irqsave(&conn->c_lock, flags); if (!list_empty(&conn->c_send_queue)) { @@ -357,9 +381,9 @@ restart: } } +over_batch: if (conn->c_trans->xmit_complete) conn->c_trans->xmit_complete(conn); - release_in_xmit(conn); /* Nuke any messages we decided not to retransmit. */ @@ -380,10 +404,15 @@ restart: * If the transport cannot continue (i.e ret != 0), then it must * call us when more room is available, such as from the tx * completion handler. + * + * We have an extra generation check here so that if someone manages + * to jump in after our release_in_xmit, we'll see that they have done + * some work and we will skip our goto */ if (ret == 0) { smp_mb(); - if (!list_empty(&conn->c_send_queue)) { + if (!list_empty(&conn->c_send_queue) && + send_gen == conn->c_send_gen) { rds_stats_inc(s_send_lock_queue_raced); goto restart; } @@ -920,8 +949,7 @@ static int rds_cmsg_send(struct rds_sock *rs, struct rds_message *rm, return ret; } -int rds_sendmsg(struct kiocb *iocb, struct socket *sock, struct msghdr *msg, - size_t payload_len) +int rds_sendmsg(struct socket *sock, struct msghdr *msg, size_t payload_len) { struct sock *sk = sock->sk; struct rds_sock *rs = rds_sk_to_rs(sk); diff --git a/net/rose/af_rose.c b/net/rose/af_rose.c index 43bac7c4dd9e..8ae603069a1a 100644 --- a/net/rose/af_rose.c +++ b/net/rose/af_rose.c @@ -1046,8 +1046,7 @@ int rose_rx_call_request(struct sk_buff *skb, struct net_device *dev, struct ros return 1; } -static int rose_sendmsg(struct kiocb *iocb, struct socket *sock, - struct msghdr *msg, size_t len) +static int rose_sendmsg(struct socket *sock, struct msghdr *msg, size_t len) { struct sock *sk = sock->sk; struct rose_sock *rose = rose_sk(sk); @@ -1211,8 +1210,8 @@ static int rose_sendmsg(struct kiocb *iocb, struct socket *sock, } -static int rose_recvmsg(struct kiocb *iocb, struct socket *sock, - struct msghdr *msg, size_t size, int flags) +static int rose_recvmsg(struct socket *sock, struct msghdr *msg, size_t size, + int flags) { struct sock *sk = sock->sk; struct rose_sock *rose = rose_sk(sk); diff --git a/net/rose/rose_dev.c b/net/rose/rose_dev.c index 50005888be57..369ca81a8c5d 100644 --- a/net/rose/rose_dev.c +++ b/net/rose/rose_dev.c @@ -41,6 +41,9 @@ static int rose_header(struct sk_buff *skb, struct net_device *dev, { unsigned char *buff = skb_push(skb, ROSE_MIN_LEN + 2); + if (daddr) + memcpy(buff + 7, daddr, dev->addr_len); + *buff++ = ROSE_GFI | ROSE_Q_BIT; *buff++ = 0x00; *buff++ = ROSE_DATA; @@ -53,43 +56,6 @@ static int rose_header(struct sk_buff *skb, struct net_device *dev, return -37; } -static int rose_rebuild_header(struct sk_buff *skb) -{ -#ifdef CONFIG_INET - struct net_device *dev = skb->dev; - struct net_device_stats *stats = &dev->stats; - unsigned char *bp = (unsigned char *)skb->data; - struct sk_buff *skbn; - unsigned int len; - - if (arp_find(bp + 7, skb)) { - return 1; - } - - if ((skbn = skb_clone(skb, GFP_ATOMIC)) == NULL) { - kfree_skb(skb); - return 1; - } - - if (skb->sk != NULL) - skb_set_owner_w(skbn, skb->sk); - - kfree_skb(skb); - - len = skbn->len; - - if (!rose_route_frame(skbn, NULL)) { - kfree_skb(skbn); - stats->tx_errors++; - return 1; - } - - stats->tx_packets++; - stats->tx_bytes += len; -#endif - return 1; -} - static int rose_set_mac_address(struct net_device *dev, void *addr) { struct sockaddr *sa = addr; @@ -134,19 +100,26 @@ static int rose_close(struct net_device *dev) static netdev_tx_t rose_xmit(struct sk_buff *skb, struct net_device *dev) { struct net_device_stats *stats = &dev->stats; + unsigned int len = skb->len; if (!netif_running(dev)) { printk(KERN_ERR "ROSE: rose_xmit - called when iface is down\n"); return NETDEV_TX_BUSY; } - dev_kfree_skb(skb); - stats->tx_errors++; + + if (!rose_route_frame(skb, NULL)) { + dev_kfree_skb(skb); + stats->tx_errors++; + return NETDEV_TX_OK; + } + + stats->tx_packets++; + stats->tx_bytes += len; return NETDEV_TX_OK; } static const struct header_ops rose_header_ops = { .create = rose_header, - .rebuild = rose_rebuild_header, }; static const struct net_device_ops rose_netdev_ops = { diff --git a/net/rxrpc/af_rxrpc.c b/net/rxrpc/af_rxrpc.c index 7b1670489638..0095b9a0b779 100644 --- a/net/rxrpc/af_rxrpc.c +++ b/net/rxrpc/af_rxrpc.c @@ -441,8 +441,7 @@ static int rxrpc_connect(struct socket *sock, struct sockaddr *addr, * - sends a call data packet * - may send an abort (abort code in control data) */ -static int rxrpc_sendmsg(struct kiocb *iocb, struct socket *sock, - struct msghdr *m, size_t len) +static int rxrpc_sendmsg(struct socket *sock, struct msghdr *m, size_t len) { struct rxrpc_transport *trans; struct rxrpc_sock *rx = rxrpc_sk(sock->sk); @@ -482,7 +481,7 @@ static int rxrpc_sendmsg(struct kiocb *iocb, struct socket *sock, switch (rx->sk.sk_state) { case RXRPC_SERVER_LISTENING: if (!m->msg_name) { - ret = rxrpc_server_sendmsg(iocb, rx, m, len); + ret = rxrpc_server_sendmsg(rx, m, len); break; } case RXRPC_SERVER_BOUND: @@ -492,7 +491,7 @@ static int rxrpc_sendmsg(struct kiocb *iocb, struct socket *sock, break; } case RXRPC_CLIENT_CONNECTED: - ret = rxrpc_client_sendmsg(iocb, rx, trans, m, len); + ret = rxrpc_client_sendmsg(rx, trans, m, len); break; default: ret = -ENOTCONN; diff --git a/net/rxrpc/ar-input.c b/net/rxrpc/ar-input.c index 481f89f93789..4505a691d88c 100644 --- a/net/rxrpc/ar-input.c +++ b/net/rxrpc/ar-input.c @@ -28,7 +28,7 @@ const char *rxrpc_pkts[] = { "?00", "DATA", "ACK", "BUSY", "ABORT", "ACKALL", "CHALL", "RESP", "DEBUG", - "?09", "?10", "?11", "?12", "?13", "?14", "?15" + "?09", "?10", "?11", "?12", "VERSION", "?14", "?15" }; /* @@ -593,6 +593,20 @@ static void rxrpc_post_packet_to_conn(struct rxrpc_connection *conn, rxrpc_queue_conn(conn); } +/* + * post endpoint-level events to the local endpoint + * - this includes debug and version messages + */ +static void rxrpc_post_packet_to_local(struct rxrpc_local *local, + struct sk_buff *skb) +{ + _enter("%p,%p", local, skb); + + atomic_inc(&local->usage); + skb_queue_tail(&local->event_queue, skb); + rxrpc_queue_work(&local->event_processor); +} + static struct rxrpc_connection *rxrpc_conn_from_local(struct rxrpc_local *local, struct sk_buff *skb, struct rxrpc_skb_priv *sp) @@ -699,6 +713,11 @@ void rxrpc_data_ready(struct sock *sk) goto bad_message; } + if (sp->hdr.type == RXRPC_PACKET_TYPE_VERSION) { + rxrpc_post_packet_to_local(local, skb); + goto out; + } + if (sp->hdr.type == RXRPC_PACKET_TYPE_DATA && (sp->hdr.callNumber == 0 || sp->hdr.seq == 0)) goto bad_message; @@ -731,6 +750,8 @@ void rxrpc_data_ready(struct sock *sk) else goto cant_route_call; } + +out: rxrpc_put_local(local); return; diff --git a/net/rxrpc/ar-internal.h b/net/rxrpc/ar-internal.h index ba9fd36d3f15..aef1bd294e17 100644 --- a/net/rxrpc/ar-internal.h +++ b/net/rxrpc/ar-internal.h @@ -152,11 +152,13 @@ struct rxrpc_local { struct work_struct destroyer; /* endpoint destroyer */ struct work_struct acceptor; /* incoming call processor */ struct work_struct rejecter; /* packet reject writer */ + struct work_struct event_processor; /* endpoint event processor */ struct list_head services; /* services listening on this endpoint */ struct list_head link; /* link in endpoint list */ struct rw_semaphore defrag_sem; /* control re-enablement of IP DF bit */ struct sk_buff_head accept_queue; /* incoming calls awaiting acceptance */ struct sk_buff_head reject_queue; /* packets awaiting rejection */ + struct sk_buff_head event_queue; /* endpoint event packets awaiting processing */ spinlock_t lock; /* access lock */ rwlock_t services_lock; /* lock for services list */ atomic_t usage; @@ -548,10 +550,9 @@ int rxrpc_get_server_data_key(struct rxrpc_connection *, const void *, time_t, extern unsigned rxrpc_resend_timeout; int rxrpc_send_packet(struct rxrpc_transport *, struct sk_buff *); -int rxrpc_client_sendmsg(struct kiocb *, struct rxrpc_sock *, - struct rxrpc_transport *, struct msghdr *, size_t); -int rxrpc_server_sendmsg(struct kiocb *, struct rxrpc_sock *, struct msghdr *, - size_t); +int rxrpc_client_sendmsg(struct rxrpc_sock *, struct rxrpc_transport *, + struct msghdr *, size_t); +int rxrpc_server_sendmsg(struct rxrpc_sock *, struct msghdr *, size_t); /* * ar-peer.c @@ -572,8 +573,7 @@ extern const struct file_operations rxrpc_connection_seq_fops; * ar-recvmsg.c */ void rxrpc_remove_user_ID(struct rxrpc_sock *, struct rxrpc_call *); -int rxrpc_recvmsg(struct kiocb *, struct socket *, struct msghdr *, size_t, - int); +int rxrpc_recvmsg(struct socket *, struct msghdr *, size_t, int); /* * ar-security.c diff --git a/net/rxrpc/ar-local.c b/net/rxrpc/ar-local.c index 87f7135d238b..ca904ed5400a 100644 --- a/net/rxrpc/ar-local.c +++ b/net/rxrpc/ar-local.c @@ -13,16 +13,22 @@ #include <linux/net.h> #include <linux/skbuff.h> #include <linux/slab.h> +#include <linux/udp.h> +#include <linux/ip.h> #include <net/sock.h> #include <net/af_rxrpc.h> +#include <generated/utsrelease.h> #include "ar-internal.h" +static const char rxrpc_version_string[65] = "linux-" UTS_RELEASE " AF_RXRPC"; + static LIST_HEAD(rxrpc_locals); DEFINE_RWLOCK(rxrpc_local_lock); static DECLARE_RWSEM(rxrpc_local_sem); static DECLARE_WAIT_QUEUE_HEAD(rxrpc_local_wq); static void rxrpc_destroy_local(struct work_struct *work); +static void rxrpc_process_local_events(struct work_struct *work); /* * allocate a new local @@ -37,11 +43,13 @@ struct rxrpc_local *rxrpc_alloc_local(struct sockaddr_rxrpc *srx) INIT_WORK(&local->destroyer, &rxrpc_destroy_local); INIT_WORK(&local->acceptor, &rxrpc_accept_incoming_calls); INIT_WORK(&local->rejecter, &rxrpc_reject_packets); + INIT_WORK(&local->event_processor, &rxrpc_process_local_events); INIT_LIST_HEAD(&local->services); INIT_LIST_HEAD(&local->link); init_rwsem(&local->defrag_sem); skb_queue_head_init(&local->accept_queue); skb_queue_head_init(&local->reject_queue); + skb_queue_head_init(&local->event_queue); spin_lock_init(&local->lock); rwlock_init(&local->services_lock); atomic_set(&local->usage, 1); @@ -264,10 +272,12 @@ static void rxrpc_destroy_local(struct work_struct *work) ASSERT(list_empty(&local->services)); ASSERT(!work_pending(&local->acceptor)); ASSERT(!work_pending(&local->rejecter)); + ASSERT(!work_pending(&local->event_processor)); /* finish cleaning up the local descriptor */ rxrpc_purge_queue(&local->accept_queue); rxrpc_purge_queue(&local->reject_queue); + rxrpc_purge_queue(&local->event_queue); kernel_sock_shutdown(local->socket, SHUT_RDWR); sock_release(local->socket); @@ -308,3 +318,91 @@ void __exit rxrpc_destroy_all_locals(void) _leave(""); } + +/* + * Reply to a version request + */ +static void rxrpc_send_version_request(struct rxrpc_local *local, + struct rxrpc_header *hdr, + struct sk_buff *skb) +{ + struct sockaddr_in sin; + struct msghdr msg; + struct kvec iov[2]; + size_t len; + int ret; + + _enter(""); + + sin.sin_family = AF_INET; + sin.sin_port = udp_hdr(skb)->source; + sin.sin_addr.s_addr = ip_hdr(skb)->saddr; + + msg.msg_name = &sin; + msg.msg_namelen = sizeof(sin); + msg.msg_control = NULL; + msg.msg_controllen = 0; + msg.msg_flags = 0; + + hdr->seq = 0; + hdr->serial = 0; + hdr->type = RXRPC_PACKET_TYPE_VERSION; + hdr->flags = RXRPC_LAST_PACKET | (~hdr->flags & RXRPC_CLIENT_INITIATED); + hdr->userStatus = 0; + hdr->_rsvd = 0; + + iov[0].iov_base = hdr; + iov[0].iov_len = sizeof(*hdr); + iov[1].iov_base = (char *)rxrpc_version_string; + iov[1].iov_len = sizeof(rxrpc_version_string); + + len = iov[0].iov_len + iov[1].iov_len; + + _proto("Tx VERSION (reply)"); + + ret = kernel_sendmsg(local->socket, &msg, iov, 2, len); + if (ret < 0) + _debug("sendmsg failed: %d", ret); + + _leave(""); +} + +/* + * Process event packets targetted at a local endpoint. + */ +static void rxrpc_process_local_events(struct work_struct *work) +{ + struct rxrpc_local *local = container_of(work, struct rxrpc_local, event_processor); + struct sk_buff *skb; + char v; + + _enter(""); + + atomic_inc(&local->usage); + + while ((skb = skb_dequeue(&local->event_queue))) { + struct rxrpc_skb_priv *sp = rxrpc_skb(skb); + + kdebug("{%d},{%u}", local->debug_id, sp->hdr.type); + + switch (sp->hdr.type) { + case RXRPC_PACKET_TYPE_VERSION: + if (skb_copy_bits(skb, 0, &v, 1) < 0) + return; + _proto("Rx VERSION { %02x }", v); + if (v == 0) + rxrpc_send_version_request(local, &sp->hdr, skb); + break; + + default: + /* Just ignore anything we don't understand */ + break; + } + + rxrpc_put_local(local); + rxrpc_free_skb(skb); + } + + rxrpc_put_local(local); + _leave(""); +} diff --git a/net/rxrpc/ar-output.c b/net/rxrpc/ar-output.c index 8331c95e1522..c0042807bfc6 100644 --- a/net/rxrpc/ar-output.c +++ b/net/rxrpc/ar-output.c @@ -23,8 +23,7 @@ */ unsigned rxrpc_resend_timeout = 4 * HZ; -static int rxrpc_send_data(struct kiocb *iocb, - struct rxrpc_sock *rx, +static int rxrpc_send_data(struct rxrpc_sock *rx, struct rxrpc_call *call, struct msghdr *msg, size_t len); @@ -129,9 +128,8 @@ static void rxrpc_send_abort(struct rxrpc_call *call, u32 abort_code) * - caller holds the socket locked * - the socket may be either a client socket or a server socket */ -int rxrpc_client_sendmsg(struct kiocb *iocb, struct rxrpc_sock *rx, - struct rxrpc_transport *trans, struct msghdr *msg, - size_t len) +int rxrpc_client_sendmsg(struct rxrpc_sock *rx, struct rxrpc_transport *trans, + struct msghdr *msg, size_t len) { struct rxrpc_conn_bundle *bundle; enum rxrpc_command cmd; @@ -191,7 +189,7 @@ int rxrpc_client_sendmsg(struct kiocb *iocb, struct rxrpc_sock *rx, /* request phase complete for this client call */ ret = -EPROTO; } else { - ret = rxrpc_send_data(iocb, rx, call, msg, len); + ret = rxrpc_send_data(rx, call, msg, len); } rxrpc_put_call(call); @@ -232,7 +230,7 @@ int rxrpc_kernel_send_data(struct rxrpc_call *call, struct msghdr *msg, call->state != RXRPC_CALL_SERVER_SEND_REPLY) { ret = -EPROTO; /* request phase complete for this client call */ } else { - ret = rxrpc_send_data(NULL, call->socket, call, msg, len); + ret = rxrpc_send_data(call->socket, call, msg, len); } release_sock(&call->socket->sk); @@ -271,8 +269,7 @@ EXPORT_SYMBOL(rxrpc_kernel_abort_call); * send a message through a server socket * - caller holds the socket locked */ -int rxrpc_server_sendmsg(struct kiocb *iocb, struct rxrpc_sock *rx, - struct msghdr *msg, size_t len) +int rxrpc_server_sendmsg(struct rxrpc_sock *rx, struct msghdr *msg, size_t len) { enum rxrpc_command cmd; struct rxrpc_call *call; @@ -313,7 +310,7 @@ int rxrpc_server_sendmsg(struct kiocb *iocb, struct rxrpc_sock *rx, break; } - ret = rxrpc_send_data(iocb, rx, call, msg, len); + ret = rxrpc_send_data(rx, call, msg, len); break; case RXRPC_CMD_SEND_ABORT: @@ -520,8 +517,7 @@ static void rxrpc_queue_packet(struct rxrpc_call *call, struct sk_buff *skb, * - must be called in process context * - caller holds the socket locked */ -static int rxrpc_send_data(struct kiocb *iocb, - struct rxrpc_sock *rx, +static int rxrpc_send_data(struct rxrpc_sock *rx, struct rxrpc_call *call, struct msghdr *msg, size_t len) { @@ -546,11 +542,7 @@ static int rxrpc_send_data(struct kiocb *iocb, call->tx_pending = NULL; copied = 0; - if (len > iov_iter_count(&msg->msg_iter)) - len = iov_iter_count(&msg->msg_iter); - while (len) { - int copy; - + do { if (!skb) { size_t size, chunk, max, space; @@ -572,8 +564,8 @@ static int rxrpc_send_data(struct kiocb *iocb, max &= ~(call->conn->size_align - 1UL); chunk = max; - if (chunk > len && !more) - chunk = len; + if (chunk > msg_data_left(msg) && !more) + chunk = msg_data_left(msg); space = chunk + call->conn->size_align; space &= ~(call->conn->size_align - 1UL); @@ -616,23 +608,23 @@ static int rxrpc_send_data(struct kiocb *iocb, sp = rxrpc_skb(skb); /* append next segment of data to the current buffer */ - copy = skb_tailroom(skb); - ASSERTCMP(copy, >, 0); - if (copy > len) - copy = len; - if (copy > sp->remain) - copy = sp->remain; - - _debug("add"); - ret = skb_add_data(skb, &msg->msg_iter, copy); - _debug("added"); - if (ret < 0) - goto efault; - sp->remain -= copy; - skb->mark += copy; - copied += copy; - - len -= copy; + if (msg_data_left(msg) > 0) { + int copy = skb_tailroom(skb); + ASSERTCMP(copy, >, 0); + if (copy > msg_data_left(msg)) + copy = msg_data_left(msg); + if (copy > sp->remain) + copy = sp->remain; + + _debug("add"); + ret = skb_add_data(skb, &msg->msg_iter, copy); + _debug("added"); + if (ret < 0) + goto efault; + sp->remain -= copy; + skb->mark += copy; + copied += copy; + } /* check for the far side aborting the call or a network error * occurring */ @@ -640,7 +632,8 @@ static int rxrpc_send_data(struct kiocb *iocb, goto call_aborted; /* add the packet to the send queue if it's now full */ - if (sp->remain <= 0 || (!len && !more)) { + if (sp->remain <= 0 || + (msg_data_left(msg) == 0 && !more)) { struct rxrpc_connection *conn = call->conn; uint32_t seq; size_t pad; @@ -670,7 +663,7 @@ static int rxrpc_send_data(struct kiocb *iocb, sp->hdr.serviceId = conn->service_id; sp->hdr.flags = conn->out_clientflag; - if (len == 0 && !more) + if (msg_data_left(msg) == 0 && !more) sp->hdr.flags |= RXRPC_LAST_PACKET; else if (CIRC_SPACE(call->acks_head, call->acks_tail, call->acks_winsz) > 1) @@ -686,10 +679,10 @@ static int rxrpc_send_data(struct kiocb *iocb, memcpy(skb->head, &sp->hdr, sizeof(struct rxrpc_header)); - rxrpc_queue_packet(call, skb, !iov_iter_count(&msg->msg_iter) && !more); + rxrpc_queue_packet(call, skb, !msg_data_left(msg) && !more); skb = NULL; } - } + } while (msg_data_left(msg) > 0); success: ret = copied; diff --git a/net/rxrpc/ar-recvmsg.c b/net/rxrpc/ar-recvmsg.c index 19a560626dc4..b92beded7459 100644 --- a/net/rxrpc/ar-recvmsg.c +++ b/net/rxrpc/ar-recvmsg.c @@ -43,8 +43,8 @@ void rxrpc_remove_user_ID(struct rxrpc_sock *rx, struct rxrpc_call *call) * - we need to be careful about two or more threads calling recvmsg * simultaneously */ -int rxrpc_recvmsg(struct kiocb *iocb, struct socket *sock, - struct msghdr *msg, size_t len, int flags) +int rxrpc_recvmsg(struct socket *sock, struct msghdr *msg, size_t len, + int flags) { struct rxrpc_skb_priv *sp; struct rxrpc_call *call = NULL, *continue_call = NULL; @@ -150,7 +150,7 @@ int rxrpc_recvmsg(struct kiocb *iocb, struct socket *sock, &call->conn->trans->peer->srx, len); msg->msg_namelen = len; } - sock_recv_ts_and_drops(msg, &rx->sk, skb); + sock_recv_timestamp(msg, &rx->sk, skb); } /* receive the message */ diff --git a/net/sched/act_bpf.c b/net/sched/act_bpf.c index 5f6288fa3f12..dc6a2d324bd8 100644 --- a/net/sched/act_bpf.c +++ b/net/sched/act_bpf.c @@ -13,26 +13,43 @@ #include <linux/skbuff.h> #include <linux/rtnetlink.h> #include <linux/filter.h> +#include <linux/bpf.h> + #include <net/netlink.h> #include <net/pkt_sched.h> #include <linux/tc_act/tc_bpf.h> #include <net/tc_act/tc_bpf.h> -#define BPF_TAB_MASK 15 +#define BPF_TAB_MASK 15 +#define ACT_BPF_NAME_LEN 256 + +struct tcf_bpf_cfg { + struct bpf_prog *filter; + struct sock_filter *bpf_ops; + char *bpf_name; + u32 bpf_fd; + u16 bpf_num_ops; +}; -static int tcf_bpf(struct sk_buff *skb, const struct tc_action *a, +static int tcf_bpf(struct sk_buff *skb, const struct tc_action *act, struct tcf_result *res) { - struct tcf_bpf *b = a->priv; + struct tcf_bpf *prog = act->priv; int action, filter_res; - spin_lock(&b->tcf_lock); + if (unlikely(!skb_mac_header_was_set(skb))) + return TC_ACT_UNSPEC; + + spin_lock(&prog->tcf_lock); - b->tcf_tm.lastuse = jiffies; - bstats_update(&b->tcf_bstats, skb); + prog->tcf_tm.lastuse = jiffies; + bstats_update(&prog->tcf_bstats, skb); - filter_res = BPF_PROG_RUN(b->filter, skb); + /* Needed here for accessing maps. */ + rcu_read_lock(); + filter_res = BPF_PROG_RUN(prog->filter, skb); + rcu_read_unlock(); /* A BPF program may overwrite the default action opcode. * Similarly as in cls_bpf, if filter_res == -1 we use the @@ -52,52 +69,87 @@ static int tcf_bpf(struct sk_buff *skb, const struct tc_action *a, break; case TC_ACT_SHOT: action = filter_res; - b->tcf_qstats.drops++; + prog->tcf_qstats.drops++; break; case TC_ACT_UNSPEC: - action = b->tcf_action; + action = prog->tcf_action; break; default: action = TC_ACT_UNSPEC; break; } - spin_unlock(&b->tcf_lock); + spin_unlock(&prog->tcf_lock); return action; } -static int tcf_bpf_dump(struct sk_buff *skb, struct tc_action *a, +static bool tcf_bpf_is_ebpf(const struct tcf_bpf *prog) +{ + return !prog->bpf_ops; +} + +static int tcf_bpf_dump_bpf_info(const struct tcf_bpf *prog, + struct sk_buff *skb) +{ + struct nlattr *nla; + + if (nla_put_u16(skb, TCA_ACT_BPF_OPS_LEN, prog->bpf_num_ops)) + return -EMSGSIZE; + + nla = nla_reserve(skb, TCA_ACT_BPF_OPS, prog->bpf_num_ops * + sizeof(struct sock_filter)); + if (nla == NULL) + return -EMSGSIZE; + + memcpy(nla_data(nla), prog->bpf_ops, nla_len(nla)); + + return 0; +} + +static int tcf_bpf_dump_ebpf_info(const struct tcf_bpf *prog, + struct sk_buff *skb) +{ + if (nla_put_u32(skb, TCA_ACT_BPF_FD, prog->bpf_fd)) + return -EMSGSIZE; + + if (prog->bpf_name && + nla_put_string(skb, TCA_ACT_BPF_NAME, prog->bpf_name)) + return -EMSGSIZE; + + return 0; +} + +static int tcf_bpf_dump(struct sk_buff *skb, struct tc_action *act, int bind, int ref) { unsigned char *tp = skb_tail_pointer(skb); - struct tcf_bpf *b = a->priv; + struct tcf_bpf *prog = act->priv; struct tc_act_bpf opt = { - .index = b->tcf_index, - .refcnt = b->tcf_refcnt - ref, - .bindcnt = b->tcf_bindcnt - bind, - .action = b->tcf_action, + .index = prog->tcf_index, + .refcnt = prog->tcf_refcnt - ref, + .bindcnt = prog->tcf_bindcnt - bind, + .action = prog->tcf_action, }; - struct tcf_t t; - struct nlattr *nla; + struct tcf_t tm; + int ret; if (nla_put(skb, TCA_ACT_BPF_PARMS, sizeof(opt), &opt)) goto nla_put_failure; - if (nla_put_u16(skb, TCA_ACT_BPF_OPS_LEN, b->bpf_num_ops)) - goto nla_put_failure; - - nla = nla_reserve(skb, TCA_ACT_BPF_OPS, b->bpf_num_ops * - sizeof(struct sock_filter)); - if (!nla) + if (tcf_bpf_is_ebpf(prog)) + ret = tcf_bpf_dump_ebpf_info(prog, skb); + else + ret = tcf_bpf_dump_bpf_info(prog, skb); + if (ret) goto nla_put_failure; - memcpy(nla_data(nla), b->bpf_ops, nla_len(nla)); + tm.install = jiffies_to_clock_t(jiffies - prog->tcf_tm.install); + tm.lastuse = jiffies_to_clock_t(jiffies - prog->tcf_tm.lastuse); + tm.expires = jiffies_to_clock_t(prog->tcf_tm.expires); - t.install = jiffies_to_clock_t(jiffies - b->tcf_tm.install); - t.lastuse = jiffies_to_clock_t(jiffies - b->tcf_tm.lastuse); - t.expires = jiffies_to_clock_t(b->tcf_tm.expires); - if (nla_put(skb, TCA_ACT_BPF_TM, sizeof(t), &t)) + if (nla_put(skb, TCA_ACT_BPF_TM, sizeof(tm), &tm)) goto nla_put_failure; + return skb->len; nla_put_failure: @@ -107,36 +159,21 @@ nla_put_failure: static const struct nla_policy act_bpf_policy[TCA_ACT_BPF_MAX + 1] = { [TCA_ACT_BPF_PARMS] = { .len = sizeof(struct tc_act_bpf) }, + [TCA_ACT_BPF_FD] = { .type = NLA_U32 }, + [TCA_ACT_BPF_NAME] = { .type = NLA_NUL_STRING, .len = ACT_BPF_NAME_LEN }, [TCA_ACT_BPF_OPS_LEN] = { .type = NLA_U16 }, [TCA_ACT_BPF_OPS] = { .type = NLA_BINARY, .len = sizeof(struct sock_filter) * BPF_MAXINSNS }, }; -static int tcf_bpf_init(struct net *net, struct nlattr *nla, - struct nlattr *est, struct tc_action *a, - int ovr, int bind) +static int tcf_bpf_init_from_ops(struct nlattr **tb, struct tcf_bpf_cfg *cfg) { - struct nlattr *tb[TCA_ACT_BPF_MAX + 1]; - struct tc_act_bpf *parm; - struct tcf_bpf *b; - u16 bpf_size, bpf_num_ops; struct sock_filter *bpf_ops; - struct sock_fprog_kern tmp; + struct sock_fprog_kern fprog_tmp; struct bpf_prog *fp; + u16 bpf_size, bpf_num_ops; int ret; - if (!nla) - return -EINVAL; - - ret = nla_parse_nested(tb, TCA_ACT_BPF_MAX, nla, act_bpf_policy); - if (ret < 0) - return ret; - - if (!tb[TCA_ACT_BPF_PARMS] || - !tb[TCA_ACT_BPF_OPS_LEN] || !tb[TCA_ACT_BPF_OPS]) - return -EINVAL; - parm = nla_data(tb[TCA_ACT_BPF_PARMS]); - bpf_num_ops = nla_get_u16(tb[TCA_ACT_BPF_OPS_LEN]); if (bpf_num_ops > BPF_MAXINSNS || bpf_num_ops == 0) return -EINVAL; @@ -146,68 +183,165 @@ static int tcf_bpf_init(struct net *net, struct nlattr *nla, return -EINVAL; bpf_ops = kzalloc(bpf_size, GFP_KERNEL); - if (!bpf_ops) + if (bpf_ops == NULL) return -ENOMEM; memcpy(bpf_ops, nla_data(tb[TCA_ACT_BPF_OPS]), bpf_size); - tmp.len = bpf_num_ops; - tmp.filter = bpf_ops; + fprog_tmp.len = bpf_num_ops; + fprog_tmp.filter = bpf_ops; - ret = bpf_prog_create(&fp, &tmp); - if (ret) - goto free_bpf_ops; + ret = bpf_prog_create(&fp, &fprog_tmp); + if (ret < 0) { + kfree(bpf_ops); + return ret; + } - if (!tcf_hash_check(parm->index, a, bind)) { - ret = tcf_hash_create(parm->index, est, a, sizeof(*b), bind); - if (ret) + cfg->bpf_ops = bpf_ops; + cfg->bpf_num_ops = bpf_num_ops; + cfg->filter = fp; + + return 0; +} + +static int tcf_bpf_init_from_efd(struct nlattr **tb, struct tcf_bpf_cfg *cfg) +{ + struct bpf_prog *fp; + char *name = NULL; + u32 bpf_fd; + + bpf_fd = nla_get_u32(tb[TCA_ACT_BPF_FD]); + + fp = bpf_prog_get(bpf_fd); + if (IS_ERR(fp)) + return PTR_ERR(fp); + + if (fp->type != BPF_PROG_TYPE_SCHED_ACT) { + bpf_prog_put(fp); + return -EINVAL; + } + + if (tb[TCA_ACT_BPF_NAME]) { + name = kmemdup(nla_data(tb[TCA_ACT_BPF_NAME]), + nla_len(tb[TCA_ACT_BPF_NAME]), + GFP_KERNEL); + if (!name) { + bpf_prog_put(fp); + return -ENOMEM; + } + } + + cfg->bpf_fd = bpf_fd; + cfg->bpf_name = name; + cfg->filter = fp; + + return 0; +} + +static int tcf_bpf_init(struct net *net, struct nlattr *nla, + struct nlattr *est, struct tc_action *act, + int replace, int bind) +{ + struct nlattr *tb[TCA_ACT_BPF_MAX + 1]; + struct tc_act_bpf *parm; + struct tcf_bpf *prog; + struct tcf_bpf_cfg cfg; + bool is_bpf, is_ebpf; + int ret; + + if (!nla) + return -EINVAL; + + ret = nla_parse_nested(tb, TCA_ACT_BPF_MAX, nla, act_bpf_policy); + if (ret < 0) + return ret; + + is_bpf = tb[TCA_ACT_BPF_OPS_LEN] && tb[TCA_ACT_BPF_OPS]; + is_ebpf = tb[TCA_ACT_BPF_FD]; + + if ((!is_bpf && !is_ebpf) || (is_bpf && is_ebpf) || + !tb[TCA_ACT_BPF_PARMS]) + return -EINVAL; + + parm = nla_data(tb[TCA_ACT_BPF_PARMS]); + + memset(&cfg, 0, sizeof(cfg)); + + ret = is_bpf ? tcf_bpf_init_from_ops(tb, &cfg) : + tcf_bpf_init_from_efd(tb, &cfg); + if (ret < 0) + return ret; + + if (!tcf_hash_check(parm->index, act, bind)) { + ret = tcf_hash_create(parm->index, est, act, + sizeof(*prog), bind); + if (ret < 0) goto destroy_fp; ret = ACT_P_CREATED; } else { + /* Don't override defaults. */ if (bind) goto destroy_fp; - tcf_hash_release(a, bind); - if (!ovr) { + + tcf_hash_release(act, bind); + if (!replace) { ret = -EEXIST; goto destroy_fp; } } - b = to_bpf(a); - spin_lock_bh(&b->tcf_lock); - b->tcf_action = parm->action; - b->bpf_num_ops = bpf_num_ops; - b->bpf_ops = bpf_ops; - b->filter = fp; - spin_unlock_bh(&b->tcf_lock); + prog = to_bpf(act); + spin_lock_bh(&prog->tcf_lock); + + prog->bpf_ops = cfg.bpf_ops; + prog->bpf_name = cfg.bpf_name; + + if (cfg.bpf_num_ops) + prog->bpf_num_ops = cfg.bpf_num_ops; + if (cfg.bpf_fd) + prog->bpf_fd = cfg.bpf_fd; + + prog->tcf_action = parm->action; + prog->filter = cfg.filter; + + spin_unlock_bh(&prog->tcf_lock); if (ret == ACT_P_CREATED) - tcf_hash_insert(a); + tcf_hash_insert(act); + return ret; destroy_fp: - bpf_prog_destroy(fp); -free_bpf_ops: - kfree(bpf_ops); + if (is_ebpf) + bpf_prog_put(cfg.filter); + else + bpf_prog_destroy(cfg.filter); + + kfree(cfg.bpf_ops); + kfree(cfg.bpf_name); + return ret; } -static void tcf_bpf_cleanup(struct tc_action *a, int bind) +static void tcf_bpf_cleanup(struct tc_action *act, int bind) { - struct tcf_bpf *b = a->priv; + const struct tcf_bpf *prog = act->priv; - bpf_prog_destroy(b->filter); + if (tcf_bpf_is_ebpf(prog)) + bpf_prog_put(prog->filter); + else + bpf_prog_destroy(prog->filter); } -static struct tc_action_ops act_bpf_ops = { - .kind = "bpf", - .type = TCA_ACT_BPF, - .owner = THIS_MODULE, - .act = tcf_bpf, - .dump = tcf_bpf_dump, - .cleanup = tcf_bpf_cleanup, - .init = tcf_bpf_init, +static struct tc_action_ops act_bpf_ops __read_mostly = { + .kind = "bpf", + .type = TCA_ACT_BPF, + .owner = THIS_MODULE, + .act = tcf_bpf, + .dump = tcf_bpf_dump, + .cleanup = tcf_bpf_cleanup, + .init = tcf_bpf_init, }; static int __init bpf_init_module(void) diff --git a/net/sched/act_connmark.c b/net/sched/act_connmark.c index 8e472518f9f6..295d14bd6c67 100644 --- a/net/sched/act_connmark.c +++ b/net/sched/act_connmark.c @@ -63,7 +63,6 @@ static int tcf_connmark(struct sk_buff *skb, const struct tc_action *a, skb->mark = c->mark; /* using overlimits stats to count how many packets marked */ ca->tcf_qstats.overlimits++; - nf_ct_put(c); goto out; } @@ -82,7 +81,6 @@ static int tcf_connmark(struct sk_buff *skb, const struct tc_action *a, nf_ct_put(c); out: - skb->nfct = NULL; spin_unlock(&ca->tcf_lock); return ca->tcf_action; } diff --git a/net/sched/act_mirred.c b/net/sched/act_mirred.c index 5953517ec059..3f63ceac8e01 100644 --- a/net/sched/act_mirred.c +++ b/net/sched/act_mirred.c @@ -157,7 +157,7 @@ static int tcf_mirred(struct sk_buff *skb, const struct tc_action *a, if (!(at & AT_EGRESS)) { if (m->tcfm_ok_push) - skb_push(skb2, skb2->dev->hard_header_len); + skb_push(skb2, skb->mac_len); } /* mirror is always swallowed */ diff --git a/net/sched/cls_api.c b/net/sched/cls_api.c index baef987fe2c0..8b0470e418dc 100644 --- a/net/sched/cls_api.c +++ b/net/sched/cls_api.c @@ -286,7 +286,7 @@ replay: RCU_INIT_POINTER(*back, next); tfilter_notify(net, skb, n, tp, fh, RTM_DELTFILTER); - tcf_destroy(tp); + tcf_destroy(tp, true); err = 0; goto errout; } @@ -301,14 +301,20 @@ replay: err = -EEXIST; if (n->nlmsg_flags & NLM_F_EXCL) { if (tp_created) - tcf_destroy(tp); + tcf_destroy(tp, true); goto errout; } break; case RTM_DELTFILTER: err = tp->ops->delete(tp, fh); - if (err == 0) + if (err == 0) { tfilter_notify(net, skb, n, tp, fh, RTM_DELTFILTER); + if (tcf_destroy(tp, false)) { + struct tcf_proto *next = rtnl_dereference(tp->next); + + RCU_INIT_POINTER(*back, next); + } + } goto errout; case RTM_GETTFILTER: err = tfilter_notify(net, skb, n, tp, fh, RTM_NEWTFILTER); @@ -329,7 +335,7 @@ replay: tfilter_notify(net, skb, n, tp, fh, RTM_NEWTFILTER); } else { if (tp_created) - tcf_destroy(tp); + tcf_destroy(tp, true); } errout: diff --git a/net/sched/cls_basic.c b/net/sched/cls_basic.c index fc399db86f11..0b8c3ace671f 100644 --- a/net/sched/cls_basic.c +++ b/net/sched/cls_basic.c @@ -96,11 +96,14 @@ static void basic_delete_filter(struct rcu_head *head) kfree(f); } -static void basic_destroy(struct tcf_proto *tp) +static bool basic_destroy(struct tcf_proto *tp, bool force) { struct basic_head *head = rtnl_dereference(tp->root); struct basic_filter *f, *n; + if (!force && !list_empty(&head->flist)) + return false; + list_for_each_entry_safe(f, n, &head->flist, link) { list_del_rcu(&f->link); tcf_unbind_filter(tp, &f->res); @@ -108,6 +111,7 @@ static void basic_destroy(struct tcf_proto *tp) } RCU_INIT_POINTER(tp->root, NULL); kfree_rcu(head, rcu); + return true; } static int basic_delete(struct tcf_proto *tp, unsigned long arg) diff --git a/net/sched/cls_bpf.c b/net/sched/cls_bpf.c index 5f3ee9e4b5bf..91bd9c19471d 100644 --- a/net/sched/cls_bpf.c +++ b/net/sched/cls_bpf.c @@ -16,6 +16,8 @@ #include <linux/types.h> #include <linux/skbuff.h> #include <linux/filter.h> +#include <linux/bpf.h> + #include <net/rtnetlink.h> #include <net/pkt_cls.h> #include <net/sock.h> @@ -24,6 +26,8 @@ MODULE_LICENSE("GPL"); MODULE_AUTHOR("Daniel Borkmann <dborkman@redhat.com>"); MODULE_DESCRIPTION("TC BPF based classifier"); +#define CLS_BPF_NAME_LEN 256 + struct cls_bpf_head { struct list_head plist; u32 hgen; @@ -32,18 +36,24 @@ struct cls_bpf_head { struct cls_bpf_prog { struct bpf_prog *filter; - struct sock_filter *bpf_ops; - struct tcf_exts exts; - struct tcf_result res; struct list_head link; + struct tcf_result res; + struct tcf_exts exts; u32 handle; - u16 bpf_num_ops; + union { + u32 bpf_fd; + u16 bpf_num_ops; + }; + struct sock_filter *bpf_ops; + const char *bpf_name; struct tcf_proto *tp; struct rcu_head rcu; }; static const struct nla_policy bpf_policy[TCA_BPF_MAX + 1] = { [TCA_BPF_CLASSID] = { .type = NLA_U32 }, + [TCA_BPF_FD] = { .type = NLA_U32 }, + [TCA_BPF_NAME] = { .type = NLA_NUL_STRING, .len = CLS_BPF_NAME_LEN }, [TCA_BPF_OPS_LEN] = { .type = NLA_U16 }, [TCA_BPF_OPS] = { .type = NLA_BINARY, .len = sizeof(struct sock_filter) * BPF_MAXINSNS }, @@ -54,8 +64,13 @@ static int cls_bpf_classify(struct sk_buff *skb, const struct tcf_proto *tp, { struct cls_bpf_head *head = rcu_dereference_bh(tp->root); struct cls_bpf_prog *prog; - int ret; + int ret = -1; + + if (unlikely(!skb_mac_header_was_set(skb))) + return -1; + /* Needed here for accessing maps. */ + rcu_read_lock(); list_for_each_entry_rcu(prog, &head->plist, link) { int filter_res = BPF_PROG_RUN(prog->filter, skb); @@ -70,10 +85,16 @@ static int cls_bpf_classify(struct sk_buff *skb, const struct tcf_proto *tp, if (ret < 0) continue; - return ret; + break; } + rcu_read_unlock(); - return -1; + return ret; +} + +static bool cls_bpf_is_ebpf(const struct cls_bpf_prog *prog) +{ + return !prog->bpf_ops; } static int cls_bpf_init(struct tcf_proto *tp) @@ -94,8 +115,12 @@ static void cls_bpf_delete_prog(struct tcf_proto *tp, struct cls_bpf_prog *prog) { tcf_exts_destroy(&prog->exts); - bpf_prog_destroy(prog->filter); + if (cls_bpf_is_ebpf(prog)) + bpf_prog_put(prog->filter); + else + bpf_prog_destroy(prog->filter); + kfree(prog->bpf_name); kfree(prog->bpf_ops); kfree(prog); } @@ -114,14 +139,18 @@ static int cls_bpf_delete(struct tcf_proto *tp, unsigned long arg) list_del_rcu(&prog->link); tcf_unbind_filter(tp, &prog->res); call_rcu(&prog->rcu, __cls_bpf_delete_prog); + return 0; } -static void cls_bpf_destroy(struct tcf_proto *tp) +static bool cls_bpf_destroy(struct tcf_proto *tp, bool force) { struct cls_bpf_head *head = rtnl_dereference(tp->root); struct cls_bpf_prog *prog, *tmp; + if (!force && !list_empty(&head->plist)) + return false; + list_for_each_entry_safe(prog, tmp, &head->plist, link) { list_del_rcu(&prog->link); tcf_unbind_filter(tp, &prog->res); @@ -130,6 +159,7 @@ static void cls_bpf_destroy(struct tcf_proto *tp) RCU_INIT_POINTER(tp->root, NULL); kfree_rcu(head, rcu); + return true; } static unsigned long cls_bpf_get(struct tcf_proto *tp, u32 handle) @@ -151,69 +181,121 @@ static unsigned long cls_bpf_get(struct tcf_proto *tp, u32 handle) return ret; } -static int cls_bpf_modify_existing(struct net *net, struct tcf_proto *tp, - struct cls_bpf_prog *prog, - unsigned long base, struct nlattr **tb, - struct nlattr *est, bool ovr) +static int cls_bpf_prog_from_ops(struct nlattr **tb, + struct cls_bpf_prog *prog, u32 classid) { struct sock_filter *bpf_ops; - struct tcf_exts exts; - struct sock_fprog_kern tmp; + struct sock_fprog_kern fprog_tmp; struct bpf_prog *fp; u16 bpf_size, bpf_num_ops; - u32 classid; int ret; - if (!tb[TCA_BPF_OPS_LEN] || !tb[TCA_BPF_OPS] || !tb[TCA_BPF_CLASSID]) - return -EINVAL; - - tcf_exts_init(&exts, TCA_BPF_ACT, TCA_BPF_POLICE); - ret = tcf_exts_validate(net, tp, tb, est, &exts, ovr); - if (ret < 0) - return ret; - - classid = nla_get_u32(tb[TCA_BPF_CLASSID]); bpf_num_ops = nla_get_u16(tb[TCA_BPF_OPS_LEN]); - if (bpf_num_ops > BPF_MAXINSNS || bpf_num_ops == 0) { - ret = -EINVAL; - goto errout; - } + if (bpf_num_ops > BPF_MAXINSNS || bpf_num_ops == 0) + return -EINVAL; bpf_size = bpf_num_ops * sizeof(*bpf_ops); - if (bpf_size != nla_len(tb[TCA_BPF_OPS])) { - ret = -EINVAL; - goto errout; - } + if (bpf_size != nla_len(tb[TCA_BPF_OPS])) + return -EINVAL; bpf_ops = kzalloc(bpf_size, GFP_KERNEL); - if (bpf_ops == NULL) { - ret = -ENOMEM; - goto errout; - } + if (bpf_ops == NULL) + return -ENOMEM; memcpy(bpf_ops, nla_data(tb[TCA_BPF_OPS]), bpf_size); - tmp.len = bpf_num_ops; - tmp.filter = bpf_ops; + fprog_tmp.len = bpf_num_ops; + fprog_tmp.filter = bpf_ops; - ret = bpf_prog_create(&fp, &tmp); - if (ret) - goto errout_free; + ret = bpf_prog_create(&fp, &fprog_tmp); + if (ret < 0) { + kfree(bpf_ops); + return ret; + } - prog->bpf_num_ops = bpf_num_ops; prog->bpf_ops = bpf_ops; + prog->bpf_num_ops = bpf_num_ops; + prog->bpf_name = NULL; + prog->filter = fp; prog->res.classid = classid; + return 0; +} + +static int cls_bpf_prog_from_efd(struct nlattr **tb, + struct cls_bpf_prog *prog, u32 classid) +{ + struct bpf_prog *fp; + char *name = NULL; + u32 bpf_fd; + + bpf_fd = nla_get_u32(tb[TCA_BPF_FD]); + + fp = bpf_prog_get(bpf_fd); + if (IS_ERR(fp)) + return PTR_ERR(fp); + + if (fp->type != BPF_PROG_TYPE_SCHED_CLS) { + bpf_prog_put(fp); + return -EINVAL; + } + + if (tb[TCA_BPF_NAME]) { + name = kmemdup(nla_data(tb[TCA_BPF_NAME]), + nla_len(tb[TCA_BPF_NAME]), + GFP_KERNEL); + if (!name) { + bpf_prog_put(fp); + return -ENOMEM; + } + } + + prog->bpf_ops = NULL; + prog->bpf_fd = bpf_fd; + prog->bpf_name = name; + + prog->filter = fp; + prog->res.classid = classid; + + return 0; +} + +static int cls_bpf_modify_existing(struct net *net, struct tcf_proto *tp, + struct cls_bpf_prog *prog, + unsigned long base, struct nlattr **tb, + struct nlattr *est, bool ovr) +{ + struct tcf_exts exts; + bool is_bpf, is_ebpf; + u32 classid; + int ret; + + is_bpf = tb[TCA_BPF_OPS_LEN] && tb[TCA_BPF_OPS]; + is_ebpf = tb[TCA_BPF_FD]; + + if ((!is_bpf && !is_ebpf) || (is_bpf && is_ebpf) || + !tb[TCA_BPF_CLASSID]) + return -EINVAL; + + tcf_exts_init(&exts, TCA_BPF_ACT, TCA_BPF_POLICE); + ret = tcf_exts_validate(net, tp, tb, est, &exts, ovr); + if (ret < 0) + return ret; + + classid = nla_get_u32(tb[TCA_BPF_CLASSID]); + + ret = is_bpf ? cls_bpf_prog_from_ops(tb, prog, classid) : + cls_bpf_prog_from_efd(tb, prog, classid); + if (ret < 0) { + tcf_exts_destroy(&exts); + return ret; + } + tcf_bind_filter(tp, &prog->res, base); tcf_exts_change(tp, &prog->exts, &exts); return 0; -errout_free: - kfree(bpf_ops); -errout: - tcf_exts_destroy(&exts); - return ret; } static u32 cls_bpf_grab_new_handle(struct tcf_proto *tp, @@ -297,11 +379,43 @@ errout: return ret; } +static int cls_bpf_dump_bpf_info(const struct cls_bpf_prog *prog, + struct sk_buff *skb) +{ + struct nlattr *nla; + + if (nla_put_u16(skb, TCA_BPF_OPS_LEN, prog->bpf_num_ops)) + return -EMSGSIZE; + + nla = nla_reserve(skb, TCA_BPF_OPS, prog->bpf_num_ops * + sizeof(struct sock_filter)); + if (nla == NULL) + return -EMSGSIZE; + + memcpy(nla_data(nla), prog->bpf_ops, nla_len(nla)); + + return 0; +} + +static int cls_bpf_dump_ebpf_info(const struct cls_bpf_prog *prog, + struct sk_buff *skb) +{ + if (nla_put_u32(skb, TCA_BPF_FD, prog->bpf_fd)) + return -EMSGSIZE; + + if (prog->bpf_name && + nla_put_string(skb, TCA_BPF_NAME, prog->bpf_name)) + return -EMSGSIZE; + + return 0; +} + static int cls_bpf_dump(struct net *net, struct tcf_proto *tp, unsigned long fh, struct sk_buff *skb, struct tcmsg *tm) { struct cls_bpf_prog *prog = (struct cls_bpf_prog *) fh; - struct nlattr *nest, *nla; + struct nlattr *nest; + int ret; if (prog == NULL) return skb->len; @@ -314,16 +428,14 @@ static int cls_bpf_dump(struct net *net, struct tcf_proto *tp, unsigned long fh, if (nla_put_u32(skb, TCA_BPF_CLASSID, prog->res.classid)) goto nla_put_failure; - if (nla_put_u16(skb, TCA_BPF_OPS_LEN, prog->bpf_num_ops)) - goto nla_put_failure; - nla = nla_reserve(skb, TCA_BPF_OPS, prog->bpf_num_ops * - sizeof(struct sock_filter)); - if (nla == NULL) + if (cls_bpf_is_ebpf(prog)) + ret = cls_bpf_dump_ebpf_info(prog, skb); + else + ret = cls_bpf_dump_bpf_info(prog, skb); + if (ret) goto nla_put_failure; - memcpy(nla_data(nla), prog->bpf_ops, nla_len(nla)); - if (tcf_exts_dump(skb, &prog->exts) < 0) goto nla_put_failure; diff --git a/net/sched/cls_cgroup.c b/net/sched/cls_cgroup.c index 221697ab0247..ea611b216412 100644 --- a/net/sched/cls_cgroup.c +++ b/net/sched/cls_cgroup.c @@ -143,14 +143,18 @@ errout: return err; } -static void cls_cgroup_destroy(struct tcf_proto *tp) +static bool cls_cgroup_destroy(struct tcf_proto *tp, bool force) { struct cls_cgroup_head *head = rtnl_dereference(tp->root); + if (!force) + return false; + if (head) { RCU_INIT_POINTER(tp->root, NULL); call_rcu(&head->rcu, cls_cgroup_destroy_rcu); } + return true; } static int cls_cgroup_delete(struct tcf_proto *tp, unsigned long arg) diff --git a/net/sched/cls_flow.c b/net/sched/cls_flow.c index 461410394d08..a620c4e288a5 100644 --- a/net/sched/cls_flow.c +++ b/net/sched/cls_flow.c @@ -557,17 +557,21 @@ static int flow_init(struct tcf_proto *tp) return 0; } -static void flow_destroy(struct tcf_proto *tp) +static bool flow_destroy(struct tcf_proto *tp, bool force) { struct flow_head *head = rtnl_dereference(tp->root); struct flow_filter *f, *next; + if (!force && !list_empty(&head->filters)) + return false; + list_for_each_entry_safe(f, next, &head->filters, list) { list_del_rcu(&f->list); call_rcu(&f->rcu, flow_destroy_filter); } RCU_INIT_POINTER(tp->root, NULL); kfree_rcu(head, rcu); + return true; } static unsigned long flow_get(struct tcf_proto *tp, u32 handle) diff --git a/net/sched/cls_fw.c b/net/sched/cls_fw.c index a5269f76004c..715e01e5910a 100644 --- a/net/sched/cls_fw.c +++ b/net/sched/cls_fw.c @@ -33,6 +33,7 @@ struct fw_head { u32 mask; + bool mask_set; struct fw_filter __rcu *ht[HTSIZE]; struct rcu_head rcu; }; @@ -113,6 +114,14 @@ static unsigned long fw_get(struct tcf_proto *tp, u32 handle) static int fw_init(struct tcf_proto *tp) { + struct fw_head *head; + + head = kzalloc(sizeof(struct fw_head), GFP_KERNEL); + if (head == NULL) + return -ENOBUFS; + + head->mask_set = false; + rcu_assign_pointer(tp->root, head); return 0; } @@ -124,14 +133,20 @@ static void fw_delete_filter(struct rcu_head *head) kfree(f); } -static void fw_destroy(struct tcf_proto *tp) +static bool fw_destroy(struct tcf_proto *tp, bool force) { struct fw_head *head = rtnl_dereference(tp->root); struct fw_filter *f; int h; if (head == NULL) - return; + return true; + + if (!force) { + for (h = 0; h < HTSIZE; h++) + if (rcu_access_pointer(head->ht[h])) + return false; + } for (h = 0; h < HTSIZE; h++) { while ((f = rtnl_dereference(head->ht[h])) != NULL) { @@ -143,6 +158,7 @@ static void fw_destroy(struct tcf_proto *tp) } RCU_INIT_POINTER(tp->root, NULL); kfree_rcu(head, rcu); + return true; } static int fw_delete(struct tcf_proto *tp, unsigned long arg) @@ -286,17 +302,11 @@ static int fw_change(struct net *net, struct sk_buff *in_skb, if (!handle) return -EINVAL; - if (head == NULL) { - u32 mask = 0xFFFFFFFF; + if (!head->mask_set) { + head->mask = 0xFFFFFFFF; if (tb[TCA_FW_MASK]) - mask = nla_get_u32(tb[TCA_FW_MASK]); - - head = kzalloc(sizeof(struct fw_head), GFP_KERNEL); - if (head == NULL) - return -ENOBUFS; - head->mask = mask; - - rcu_assign_pointer(tp->root, head); + head->mask = nla_get_u32(tb[TCA_FW_MASK]); + head->mask_set = true; } f = kzalloc(sizeof(struct fw_filter), GFP_KERNEL); diff --git a/net/sched/cls_route.c b/net/sched/cls_route.c index 2ecd24688554..08a3b0a6f5ab 100644 --- a/net/sched/cls_route.c +++ b/net/sched/cls_route.c @@ -258,6 +258,13 @@ static unsigned long route4_get(struct tcf_proto *tp, u32 handle) static int route4_init(struct tcf_proto *tp) { + struct route4_head *head; + + head = kzalloc(sizeof(struct route4_head), GFP_KERNEL); + if (head == NULL) + return -ENOBUFS; + + rcu_assign_pointer(tp->root, head); return 0; } @@ -270,13 +277,20 @@ route4_delete_filter(struct rcu_head *head) kfree(f); } -static void route4_destroy(struct tcf_proto *tp) +static bool route4_destroy(struct tcf_proto *tp, bool force) { struct route4_head *head = rtnl_dereference(tp->root); int h1, h2; if (head == NULL) - return; + return true; + + if (!force) { + for (h1 = 0; h1 <= 256; h1++) { + if (rcu_access_pointer(head->table[h1])) + return false; + } + } for (h1 = 0; h1 <= 256; h1++) { struct route4_bucket *b; @@ -301,6 +315,7 @@ static void route4_destroy(struct tcf_proto *tp) } RCU_INIT_POINTER(tp->root, NULL); kfree_rcu(head, rcu); + return true; } static int route4_delete(struct tcf_proto *tp, unsigned long arg) @@ -484,13 +499,6 @@ static int route4_change(struct net *net, struct sk_buff *in_skb, return -EINVAL; err = -ENOBUFS; - if (head == NULL) { - head = kzalloc(sizeof(struct route4_head), GFP_KERNEL); - if (head == NULL) - goto errout; - rcu_assign_pointer(tp->root, head); - } - f = kzalloc(sizeof(struct route4_filter), GFP_KERNEL); if (!f) goto errout; diff --git a/net/sched/cls_rsvp.h b/net/sched/cls_rsvp.h index edd8ade3fbc1..02fa82792dab 100644 --- a/net/sched/cls_rsvp.h +++ b/net/sched/cls_rsvp.h @@ -291,13 +291,20 @@ rsvp_delete_filter(struct tcf_proto *tp, struct rsvp_filter *f) kfree_rcu(f, rcu); } -static void rsvp_destroy(struct tcf_proto *tp) +static bool rsvp_destroy(struct tcf_proto *tp, bool force) { struct rsvp_head *data = rtnl_dereference(tp->root); int h1, h2; if (data == NULL) - return; + return true; + + if (!force) { + for (h1 = 0; h1 < 256; h1++) { + if (rcu_access_pointer(data->ht[h1])) + return false; + } + } RCU_INIT_POINTER(tp->root, NULL); @@ -319,6 +326,7 @@ static void rsvp_destroy(struct tcf_proto *tp) } } kfree_rcu(data, rcu); + return true; } static int rsvp_delete(struct tcf_proto *tp, unsigned long arg) diff --git a/net/sched/cls_tcindex.c b/net/sched/cls_tcindex.c index bd49bf547a47..a557dbaf5afe 100644 --- a/net/sched/cls_tcindex.c +++ b/net/sched/cls_tcindex.c @@ -468,11 +468,14 @@ static void tcindex_walk(struct tcf_proto *tp, struct tcf_walker *walker) } } -static void tcindex_destroy(struct tcf_proto *tp) +static bool tcindex_destroy(struct tcf_proto *tp, bool force) { struct tcindex_data *p = rtnl_dereference(tp->root); struct tcf_walker walker; + if (!force) + return false; + pr_debug("tcindex_destroy(tp %p),p %p\n", tp, p); walker.count = 0; walker.skip = 0; @@ -481,6 +484,7 @@ static void tcindex_destroy(struct tcf_proto *tp) RCU_INIT_POINTER(tp->root, NULL); call_rcu(&p->rcu, __tcindex_destroy); + return true; } diff --git a/net/sched/cls_u32.c b/net/sched/cls_u32.c index 95fdf4e40051..cab9e9b43967 100644 --- a/net/sched/cls_u32.c +++ b/net/sched/cls_u32.c @@ -463,13 +463,35 @@ static int u32_destroy_hnode(struct tcf_proto *tp, struct tc_u_hnode *ht) return -ENOENT; } -static void u32_destroy(struct tcf_proto *tp) +static bool ht_empty(struct tc_u_hnode *ht) +{ + unsigned int h; + + for (h = 0; h <= ht->divisor; h++) + if (rcu_access_pointer(ht->ht[h])) + return false; + + return true; +} + +static bool u32_destroy(struct tcf_proto *tp, bool force) { struct tc_u_common *tp_c = tp->data; struct tc_u_hnode *root_ht = rtnl_dereference(tp->root); WARN_ON(root_ht == NULL); + if (!force) { + if (root_ht) { + if (root_ht->refcnt > 1) + return false; + if (root_ht->refcnt == 1) { + if (!ht_empty(root_ht)) + return false; + } + } + } + if (root_ht && --root_ht->refcnt == 0) u32_destroy_hnode(tp, root_ht); @@ -494,6 +516,7 @@ static void u32_destroy(struct tcf_proto *tp) } tp->data = NULL; + return true; } static int u32_delete(struct tcf_proto *tp, unsigned long arg) diff --git a/net/sched/em_text.c b/net/sched/em_text.c index f03c3de16c27..73e2ed576ceb 100644 --- a/net/sched/em_text.c +++ b/net/sched/em_text.c @@ -34,7 +34,6 @@ static int em_text_match(struct sk_buff *skb, struct tcf_ematch *m, { struct text_match *tm = EM_TEXT_PRIV(m); int from, to; - struct ts_state state; from = tcf_get_base_ptr(skb, tm->from_layer) - skb->data; from += tm->from_offset; @@ -42,7 +41,7 @@ static int em_text_match(struct sk_buff *skb, struct tcf_ematch *m, to = tcf_get_base_ptr(skb, tm->to_layer) - skb->data; to += tm->to_offset; - return skb_find_text(skb, from, to, tm->config, &state) != UINT_MAX; + return skb_find_text(skb, from, to, tm->config) != UINT_MAX; } static int em_text_change(struct net *net, void *data, int len, diff --git a/net/sched/sch_api.c b/net/sched/sch_api.c index 243b7d169d61..ad9eed70bc8f 100644 --- a/net/sched/sch_api.c +++ b/net/sched/sch_api.c @@ -1858,11 +1858,15 @@ reclassify: } EXPORT_SYMBOL(tc_classify); -void tcf_destroy(struct tcf_proto *tp) +bool tcf_destroy(struct tcf_proto *tp, bool force) { - tp->ops->destroy(tp); - module_put(tp->ops->owner); - kfree_rcu(tp, rcu); + if (tp->ops->destroy(tp, force)) { + module_put(tp->ops->owner); + kfree_rcu(tp, rcu); + return true; + } + + return false; } void tcf_destroy_chain(struct tcf_proto __rcu **fl) @@ -1871,7 +1875,7 @@ void tcf_destroy_chain(struct tcf_proto __rcu **fl) while ((tp = rtnl_dereference(*fl)) != NULL) { RCU_INIT_POINTER(*fl, tp->next); - tcf_destroy(tp); + tcf_destroy(tp, true); } } EXPORT_SYMBOL(tcf_destroy_chain); diff --git a/net/sched/sch_fq.c b/net/sched/sch_fq.c index dfcea20e3171..f377702d4b91 100644 --- a/net/sched/sch_fq.c +++ b/net/sched/sch_fq.c @@ -8,7 +8,7 @@ * as published by the Free Software Foundation; either version * 2 of the License, or (at your option) any later version. * - * Meant to be mostly used for localy generated traffic : + * Meant to be mostly used for locally generated traffic : * Fast classification depends on skb->sk being set before reaching us. * If not, (router workload), we use rxhash as fallback, with 32 bits wide hash. * All packets belonging to a socket are considered as a 'flow'. @@ -63,7 +63,7 @@ struct fq_flow { struct sk_buff *tail; /* last skb in the list */ unsigned long age; /* jiffies when flow was emptied, for gc */ }; - struct rb_node fq_node; /* anchor in fq_root[] trees */ + struct rb_node fq_node; /* anchor in fq_root[] trees */ struct sock *sk; int qlen; /* number of packets in flow queue */ int credit; diff --git a/net/sched/sch_ingress.c b/net/sched/sch_ingress.c index eb5b8445fef9..4cdbfb85686a 100644 --- a/net/sched/sch_ingress.c +++ b/net/sched/sch_ingress.c @@ -88,11 +88,19 @@ static int ingress_enqueue(struct sk_buff *skb, struct Qdisc *sch) /* ------------------------------------------------------------- */ +static int ingress_init(struct Qdisc *sch, struct nlattr *opt) +{ + net_inc_ingress_queue(); + + return 0; +} + static void ingress_destroy(struct Qdisc *sch) { struct ingress_qdisc_data *p = qdisc_priv(sch); tcf_destroy_chain(&p->filter_list); + net_dec_ingress_queue(); } static int ingress_dump(struct Qdisc *sch, struct sk_buff *skb) @@ -124,6 +132,7 @@ static struct Qdisc_ops ingress_qdisc_ops __read_mostly = { .id = "ingress", .priv_size = sizeof(struct ingress_qdisc_data), .enqueue = ingress_enqueue, + .init = ingress_init, .destroy = ingress_destroy, .dump = ingress_dump, .owner = THIS_MODULE, diff --git a/net/sched/sch_netem.c b/net/sched/sch_netem.c index 179f1c8c0d8b..956ead2cab9a 100644 --- a/net/sched/sch_netem.c +++ b/net/sched/sch_netem.c @@ -560,8 +560,8 @@ static struct sk_buff *netem_dequeue(struct Qdisc *sch) tfifo_dequeue: skb = __skb_dequeue(&sch->q); if (skb) { -deliver: qdisc_qstats_backlog_dec(sch, skb); +deliver: qdisc_unthrottled(sch); qdisc_bstats_update(sch, skb); return skb; @@ -578,6 +578,7 @@ deliver: rb_erase(p, &q->t_root); sch->q.qlen--; + qdisc_qstats_backlog_dec(sch, skb); skb->next = NULL; skb->prev = NULL; skb->tstamp = netem_skb_cb(skb)->tstamp_save; diff --git a/net/sctp/protocol.c b/net/sctp/protocol.c index 8f34b27d5775..53b7acde9aa3 100644 --- a/net/sctp/protocol.c +++ b/net/sctp/protocol.c @@ -1322,8 +1322,7 @@ static __init int sctp_init(void) int max_share; int order; - BUILD_BUG_ON(sizeof(struct sctp_ulpevent) > - sizeof(((struct sk_buff *) 0)->cb)); + sock_skb_cb_check_size(sizeof(struct sctp_ulpevent)); /* Allocate bind_bucket and chunk caches. */ status = -ENOBUFS; diff --git a/net/sctp/socket.c b/net/sctp/socket.c index aafe94bf292e..f09de7fac2e6 100644 --- a/net/sctp/socket.c +++ b/net/sctp/socket.c @@ -102,11 +102,6 @@ static int sctp_autobind(struct sock *sk); static void sctp_sock_migrate(struct sock *, struct sock *, struct sctp_association *, sctp_socket_type_t); -extern struct kmem_cache *sctp_bucket_cachep; -extern long sysctl_sctp_mem[3]; -extern int sysctl_sctp_rmem[3]; -extern int sysctl_sctp_wmem[3]; - static int sctp_memory_pressure; static atomic_long_t sctp_memory_allocated; struct percpu_counter sctp_sockets_allocated; @@ -1586,8 +1581,7 @@ static int sctp_error(struct sock *sk, int flags, int err) static int sctp_msghdr_parse(const struct msghdr *, sctp_cmsgs_t *); -static int sctp_sendmsg(struct kiocb *iocb, struct sock *sk, - struct msghdr *msg, size_t msg_len) +static int sctp_sendmsg(struct sock *sk, struct msghdr *msg, size_t msg_len) { struct net *net = sock_net(sk); struct sctp_sock *sp; @@ -2066,9 +2060,8 @@ 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 int sctp_recvmsg(struct kiocb *iocb, struct sock *sk, - struct msghdr *msg, size_t len, int noblock, - int flags, int *addr_len) +static int sctp_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, + int noblock, int flags, int *addr_len) { struct sctp_ulpevent *event = NULL; struct sctp_sock *sp = sctp_sk(sk); diff --git a/net/sctp/sysctl.c b/net/sctp/sysctl.c index 2e9ada10fd84..26d50c565f54 100644 --- a/net/sctp/sysctl.c +++ b/net/sctp/sysctl.c @@ -58,10 +58,6 @@ static unsigned long max_autoclose_max = (MAX_SCHEDULE_TIMEOUT / HZ > UINT_MAX) ? UINT_MAX : MAX_SCHEDULE_TIMEOUT / HZ; -extern long sysctl_sctp_mem[3]; -extern int sysctl_sctp_rmem[3]; -extern int sysctl_sctp_wmem[3]; - static int proc_sctp_do_hmac_alg(struct ctl_table *ctl, int write, void __user *buffer, size_t *lenp, loff_t *ppos); diff --git a/net/socket.c b/net/socket.c index 245330ca0015..884e32997698 100644 --- a/net/socket.c +++ b/net/socket.c @@ -140,8 +140,6 @@ static ssize_t sock_splice_read(struct file *file, loff_t *ppos, static const struct file_operations socket_file_ops = { .owner = THIS_MODULE, .llseek = no_llseek, - .read = new_sync_read, - .write = new_sync_write, .read_iter = sock_read_iter, .write_iter = sock_write_iter, .poll = sock_poll, @@ -314,7 +312,7 @@ static const struct super_operations sockfs_ops = { static char *sockfs_dname(struct dentry *dentry, char *buffer, int buflen) { return dynamic_dname(dentry, buffer, buflen, "socket:[%lu]", - dentry->d_inode->i_ino); + d_inode(dentry)->i_ino); } static const struct dentry_operations sockfs_dentry_operations = { @@ -377,7 +375,7 @@ struct file *sock_alloc_file(struct socket *sock, int flags, const char *dname) &socket_file_ops); if (unlikely(IS_ERR(file))) { /* drop dentry, keep inode */ - ihold(path.dentry->d_inode); + ihold(d_inode(path.dentry)); path_put(&path); return file; } @@ -499,7 +497,7 @@ static ssize_t sockfs_listxattr(struct dentry *dentry, char *buffer, ssize_t len; ssize_t used = 0; - len = security_inode_listsecurity(dentry->d_inode, buffer, size); + len = security_inode_listsecurity(d_inode(dentry), buffer, size); if (len < 0) return len; used += len; @@ -610,60 +608,27 @@ void __sock_tx_timestamp(const struct sock *sk, __u8 *tx_flags) } EXPORT_SYMBOL(__sock_tx_timestamp); -static inline int __sock_sendmsg_nosec(struct kiocb *iocb, struct socket *sock, - struct msghdr *msg, size_t size) +static inline int sock_sendmsg_nosec(struct socket *sock, struct msghdr *msg) { - return sock->ops->sendmsg(iocb, sock, msg, size); -} - -static inline int __sock_sendmsg(struct kiocb *iocb, struct socket *sock, - struct msghdr *msg, size_t size) -{ - int err = security_socket_sendmsg(sock, msg, size); - - return err ?: __sock_sendmsg_nosec(iocb, sock, msg, size); -} - -static int do_sock_sendmsg(struct socket *sock, struct msghdr *msg, - size_t size, bool nosec) -{ - struct kiocb iocb; - int ret; - - init_sync_kiocb(&iocb, NULL); - ret = nosec ? __sock_sendmsg_nosec(&iocb, sock, msg, size) : - __sock_sendmsg(&iocb, sock, msg, size); - if (-EIOCBQUEUED == ret) - ret = wait_on_sync_kiocb(&iocb); + int ret = sock->ops->sendmsg(sock, msg, msg_data_left(msg)); + BUG_ON(ret == -EIOCBQUEUED); return ret; } -int sock_sendmsg(struct socket *sock, struct msghdr *msg, size_t size) +int sock_sendmsg(struct socket *sock, struct msghdr *msg) { - return do_sock_sendmsg(sock, msg, size, false); -} -EXPORT_SYMBOL(sock_sendmsg); + int err = security_socket_sendmsg(sock, msg, + msg_data_left(msg)); -static int sock_sendmsg_nosec(struct socket *sock, struct msghdr *msg, size_t size) -{ - return do_sock_sendmsg(sock, msg, size, true); + return err ?: sock_sendmsg_nosec(sock, msg); } +EXPORT_SYMBOL(sock_sendmsg); int kernel_sendmsg(struct socket *sock, struct msghdr *msg, struct kvec *vec, size_t num, size_t size) { - mm_segment_t oldfs = get_fs(); - int result; - - set_fs(KERNEL_DS); - /* - * the following is safe, since for compiler definitions of kvec and - * iovec are identical, yielding the same in-core layout and alignment - */ - iov_iter_init(&msg->msg_iter, WRITE, (struct iovec *)vec, num, size); - result = sock_sendmsg(sock, msg, size); - set_fs(oldfs); - return result; + iov_iter_kvec(&msg->msg_iter, WRITE | ITER_KVEC, vec, num, size); + return sock_sendmsg(sock, msg); } EXPORT_SYMBOL(kernel_sendmsg); @@ -731,9 +696,9 @@ EXPORT_SYMBOL_GPL(__sock_recv_wifi_status); static inline void sock_recv_drops(struct msghdr *msg, struct sock *sk, struct sk_buff *skb) { - if (sock_flag(sk, SOCK_RXQ_OVFL) && skb && skb->dropcount) + if (sock_flag(sk, SOCK_RXQ_OVFL) && skb && SOCK_SKB_CB(skb)->dropcount) put_cmsg(msg, SOL_SOCKET, SO_RXQ_OVFL, - sizeof(__u32), &skb->dropcount); + sizeof(__u32), &SOCK_SKB_CB(skb)->dropcount); } void __sock_recv_ts_and_drops(struct msghdr *msg, struct sock *sk, @@ -744,47 +709,21 @@ void __sock_recv_ts_and_drops(struct msghdr *msg, struct sock *sk, } EXPORT_SYMBOL_GPL(__sock_recv_ts_and_drops); -static inline int __sock_recvmsg_nosec(struct kiocb *iocb, struct socket *sock, - struct msghdr *msg, size_t size, int flags) +static inline int sock_recvmsg_nosec(struct socket *sock, struct msghdr *msg, + size_t size, int flags) { - return sock->ops->recvmsg(iocb, sock, msg, size, flags); + return sock->ops->recvmsg(sock, msg, size, flags); } -static inline int __sock_recvmsg(struct kiocb *iocb, struct socket *sock, - struct msghdr *msg, size_t size, int flags) +int sock_recvmsg(struct socket *sock, struct msghdr *msg, size_t size, + int flags) { int err = security_socket_recvmsg(sock, msg, size, flags); - return err ?: __sock_recvmsg_nosec(iocb, sock, msg, size, flags); -} - -int sock_recvmsg(struct socket *sock, struct msghdr *msg, - size_t size, int flags) -{ - struct kiocb iocb; - int ret; - - init_sync_kiocb(&iocb, NULL); - ret = __sock_recvmsg(&iocb, sock, msg, size, flags); - if (-EIOCBQUEUED == ret) - ret = wait_on_sync_kiocb(&iocb); - return ret; + return err ?: sock_recvmsg_nosec(sock, msg, size, flags); } EXPORT_SYMBOL(sock_recvmsg); -static int sock_recvmsg_nosec(struct socket *sock, struct msghdr *msg, - size_t size, int flags) -{ - struct kiocb iocb; - int ret; - - init_sync_kiocb(&iocb, NULL); - ret = __sock_recvmsg_nosec(&iocb, sock, msg, size, flags); - if (-EIOCBQUEUED == ret) - ret = wait_on_sync_kiocb(&iocb); - return ret; -} - /** * kernel_recvmsg - Receive a message from a socket (kernel space) * @sock: The socket to receive the message from @@ -806,12 +745,8 @@ int kernel_recvmsg(struct socket *sock, struct msghdr *msg, mm_segment_t oldfs = get_fs(); int result; + iov_iter_kvec(&msg->msg_iter, READ | ITER_KVEC, vec, num, size); set_fs(KERNEL_DS); - /* - * the following is safe, since for compiler definitions of kvec and - * iovec are identical, yielding the same in-core layout and alignment - */ - iov_iter_init(&msg->msg_iter, READ, (struct iovec *)vec, num, size); result = sock_recvmsg(sock, msg, size, flags); set_fs(oldfs); return result; @@ -849,7 +784,8 @@ static ssize_t sock_read_iter(struct kiocb *iocb, struct iov_iter *to) { struct file *file = iocb->ki_filp; struct socket *sock = file->private_data; - struct msghdr msg = {.msg_iter = *to}; + struct msghdr msg = {.msg_iter = *to, + .msg_iocb = iocb}; ssize_t res; if (file->f_flags & O_NONBLOCK) @@ -858,11 +794,10 @@ static ssize_t sock_read_iter(struct kiocb *iocb, struct iov_iter *to) if (iocb->ki_pos != 0) return -ESPIPE; - if (iocb->ki_nbytes == 0) /* Match SYS5 behaviour */ + if (!iov_iter_count(to)) /* Match SYS5 behaviour */ return 0; - res = __sock_recvmsg(iocb, sock, &msg, - iocb->ki_nbytes, msg.msg_flags); + res = sock_recvmsg(sock, &msg, iov_iter_count(to), msg.msg_flags); *to = msg.msg_iter; return res; } @@ -871,7 +806,8 @@ static ssize_t sock_write_iter(struct kiocb *iocb, struct iov_iter *from) { struct file *file = iocb->ki_filp; struct socket *sock = file->private_data; - struct msghdr msg = {.msg_iter = *from}; + struct msghdr msg = {.msg_iter = *from, + .msg_iocb = iocb}; ssize_t res; if (iocb->ki_pos != 0) @@ -883,7 +819,7 @@ static ssize_t sock_write_iter(struct kiocb *iocb, struct iov_iter *from) if (sock->type == SOCK_SEQPACKET) msg.msg_flags |= MSG_EOR; - res = __sock_sendmsg(iocb, sock, &msg, iocb->ki_nbytes); + res = sock_sendmsg(sock, &msg); *from = msg.msg_iter; return res; } @@ -1700,18 +1636,14 @@ SYSCALL_DEFINE6(sendto, int, fd, void __user *, buff, size_t, len, struct iovec iov; int fput_needed; - if (len > INT_MAX) - len = INT_MAX; - if (unlikely(!access_ok(VERIFY_READ, buff, len))) - return -EFAULT; + err = import_single_range(WRITE, buff, len, &iov, &msg.msg_iter); + if (unlikely(err)) + return err; sock = sockfd_lookup_light(fd, &err, &fput_needed); if (!sock) goto out; - iov.iov_base = buff; - iov.iov_len = len; msg.msg_name = NULL; - iov_iter_init(&msg.msg_iter, WRITE, &iov, 1, len); msg.msg_control = NULL; msg.msg_controllen = 0; msg.msg_namelen = 0; @@ -1725,7 +1657,7 @@ SYSCALL_DEFINE6(sendto, int, fd, void __user *, buff, size_t, len, if (sock->file->f_flags & O_NONBLOCK) flags |= MSG_DONTWAIT; msg.msg_flags = flags; - err = sock_sendmsg(sock, &msg, len); + err = sock_sendmsg(sock, &msg); out_put: fput_light(sock->file, fput_needed); @@ -1760,26 +1692,22 @@ SYSCALL_DEFINE6(recvfrom, int, fd, void __user *, ubuf, size_t, size, int err, err2; int fput_needed; - if (size > INT_MAX) - size = INT_MAX; - if (unlikely(!access_ok(VERIFY_WRITE, ubuf, size))) - return -EFAULT; + err = import_single_range(READ, ubuf, size, &iov, &msg.msg_iter); + if (unlikely(err)) + return err; sock = sockfd_lookup_light(fd, &err, &fput_needed); if (!sock) goto out; msg.msg_control = NULL; msg.msg_controllen = 0; - iov.iov_len = size; - iov.iov_base = ubuf; - iov_iter_init(&msg.msg_iter, READ, &iov, 1, size); /* Save some cycles and don't copy the address if not needed */ msg.msg_name = addr ? (struct sockaddr *)&address : NULL; /* We assume all kernel code knows the size of sockaddr_storage */ msg.msg_namelen = 0; if (sock->file->f_flags & O_NONBLOCK) flags |= MSG_DONTWAIT; - err = sock_recvmsg(sock, &msg, size, flags); + err = sock_recvmsg(sock, &msg, iov_iter_count(&msg.msg_iter), flags); if (err >= 0 && addr != NULL) { err2 = move_addr_to_user(&address, @@ -1899,10 +1827,10 @@ struct used_address { unsigned int name_len; }; -static ssize_t copy_msghdr_from_user(struct msghdr *kmsg, - struct user_msghdr __user *umsg, - struct sockaddr __user **save_addr, - struct iovec **iov) +static int copy_msghdr_from_user(struct msghdr *kmsg, + struct user_msghdr __user *umsg, + struct sockaddr __user **save_addr, + struct iovec **iov) { struct sockaddr __user *uaddr; struct iovec __user *uiov; @@ -1946,13 +1874,10 @@ static ssize_t copy_msghdr_from_user(struct msghdr *kmsg, if (nr_segs > UIO_MAXIOV) return -EMSGSIZE; - err = rw_copy_check_uvector(save_addr ? READ : WRITE, - uiov, nr_segs, - UIO_FASTIOV, *iov, iov); - if (err >= 0) - iov_iter_init(&kmsg->msg_iter, save_addr ? READ : WRITE, - *iov, nr_segs, err); - return err; + kmsg->msg_iocb = NULL; + + return import_iovec(save_addr ? READ : WRITE, uiov, nr_segs, + UIO_FASTIOV, iov, &kmsg->msg_iter); } static int ___sys_sendmsg(struct socket *sock, struct user_msghdr __user *msg, @@ -1967,7 +1892,7 @@ static int ___sys_sendmsg(struct socket *sock, struct user_msghdr __user *msg, __attribute__ ((aligned(sizeof(__kernel_size_t)))); /* 20 is size of ipv6_pktinfo */ unsigned char *ctl_buf = ctl; - int ctl_len, total_len; + int ctl_len; ssize_t err; msg_sys->msg_name = &address; @@ -1977,8 +1902,7 @@ static int ___sys_sendmsg(struct socket *sock, struct user_msghdr __user *msg, else err = copy_msghdr_from_user(msg_sys, msg, NULL, &iov); if (err < 0) - goto out_freeiov; - total_len = err; + return err; err = -ENOBUFS; @@ -2025,10 +1949,10 @@ static int ___sys_sendmsg(struct socket *sock, struct user_msghdr __user *msg, used_address->name_len == msg_sys->msg_namelen && !memcmp(&used_address->name, msg_sys->msg_name, used_address->name_len)) { - err = sock_sendmsg_nosec(sock, msg_sys, total_len); + err = sock_sendmsg_nosec(sock, msg_sys); goto out_freectl; } - err = sock_sendmsg(sock, msg_sys, total_len); + err = sock_sendmsg(sock, msg_sys); /* * If this is sendmmsg() and sending to current destination address was * successful, remember it. @@ -2044,8 +1968,7 @@ out_freectl: if (ctl_buf != ctl) sock_kfree_s(sock->sk, ctl_buf, ctl_len); out_freeiov: - if (iov != iovstack) - kfree(iov); + kfree(iov); return err; } @@ -2170,8 +2093,8 @@ static int ___sys_recvmsg(struct socket *sock, struct user_msghdr __user *msg, else err = copy_msghdr_from_user(msg_sys, msg, &uaddr, &iov); if (err < 0) - goto out_freeiov; - total_len = err; + return err; + total_len = iov_iter_count(&msg_sys->msg_iter); cmsg_ptr = (unsigned long)msg_sys->msg_control; msg_sys->msg_flags = flags & (MSG_CMSG_CLOEXEC|MSG_CMSG_COMPAT); @@ -2209,8 +2132,7 @@ static int ___sys_recvmsg(struct socket *sock, struct user_msghdr __user *msg, err = len; out_freeiov: - if (iov != iovstack) - kfree(iov); + kfree(iov); return err; } diff --git a/net/sunrpc/Kconfig b/net/sunrpc/Kconfig index fb78117b896c..9068e72aa73c 100644 --- a/net/sunrpc/Kconfig +++ b/net/sunrpc/Kconfig @@ -1,9 +1,11 @@ config SUNRPC tristate + depends on MULTIUSER config SUNRPC_GSS tristate select OID_REGISTRY + depends on MULTIUSER config SUNRPC_BACKCHANNEL bool diff --git a/net/sunrpc/cache.c b/net/sunrpc/cache.c index 5199bb1a017e..2928afffbb81 100644 --- a/net/sunrpc/cache.c +++ b/net/sunrpc/cache.c @@ -1072,10 +1072,12 @@ void qword_add(char **bpp, int *lp, char *str) if (len < 0) return; - ret = string_escape_str(str, &bp, len, ESCAPE_OCTAL, "\\ \n\t"); - if (ret < 0 || ret == len) + ret = string_escape_str(str, bp, len, ESCAPE_OCTAL, "\\ \n\t"); + if (ret >= len) { + bp += len; len = -1; - else { + } else { + bp += ret; len -= ret; *bp++ = ' '; len--; diff --git a/net/sunrpc/rpc_pipe.c b/net/sunrpc/rpc_pipe.c index 2d12b76b5a64..d81186d34558 100644 --- a/net/sunrpc/rpc_pipe.c +++ b/net/sunrpc/rpc_pipe.c @@ -94,7 +94,7 @@ rpc_timeout_upcall_queue(struct work_struct *work) } dentry = dget(pipe->dentry); spin_unlock(&pipe->lock); - rpc_purge_list(dentry ? &RPC_I(dentry->d_inode)->waitq : NULL, + rpc_purge_list(dentry ? &RPC_I(d_inode(dentry))->waitq : NULL, &free_list, destroy_msg, -ETIMEDOUT); dput(dentry); } @@ -152,7 +152,7 @@ rpc_queue_upcall(struct rpc_pipe *pipe, struct rpc_pipe_msg *msg) dentry = dget(pipe->dentry); spin_unlock(&pipe->lock); if (dentry) { - wake_up(&RPC_I(dentry->d_inode)->waitq); + wake_up(&RPC_I(d_inode(dentry))->waitq); dput(dentry); } return res; @@ -591,7 +591,7 @@ static int __rpc_mkpipe_dentry(struct inode *dir, struct dentry *dentry, err = __rpc_create_common(dir, dentry, S_IFIFO | mode, i_fop, private); if (err) return err; - rpci = RPC_I(dentry->d_inode); + rpci = RPC_I(d_inode(dentry)); rpci->private = private; rpci->pipe = pipe; fsnotify_create(dir, dentry); @@ -616,7 +616,7 @@ int rpc_rmdir(struct dentry *dentry) int error; parent = dget_parent(dentry); - dir = parent->d_inode; + dir = d_inode(parent); mutex_lock_nested(&dir->i_mutex, I_MUTEX_PARENT); error = __rpc_rmdir(dir, dentry); mutex_unlock(&dir->i_mutex); @@ -638,7 +638,7 @@ static int __rpc_unlink(struct inode *dir, struct dentry *dentry) static int __rpc_rmpipe(struct inode *dir, struct dentry *dentry) { - struct inode *inode = dentry->d_inode; + struct inode *inode = d_inode(dentry); rpc_close_pipes(inode); return __rpc_unlink(dir, dentry); @@ -654,7 +654,7 @@ static struct dentry *__rpc_lookup_create_exclusive(struct dentry *parent, if (!dentry) return ERR_PTR(-ENOMEM); } - if (dentry->d_inode == NULL) + if (d_really_is_negative(dentry)) return dentry; dput(dentry); return ERR_PTR(-EEXIST); @@ -667,7 +667,7 @@ static void __rpc_depopulate(struct dentry *parent, const struct rpc_filelist *files, int start, int eof) { - struct inode *dir = parent->d_inode; + struct inode *dir = d_inode(parent); struct dentry *dentry; struct qstr name; int i; @@ -679,9 +679,9 @@ static void __rpc_depopulate(struct dentry *parent, if (dentry == NULL) continue; - if (dentry->d_inode == NULL) + if (d_really_is_negative(dentry)) goto next; - switch (dentry->d_inode->i_mode & S_IFMT) { + switch (d_inode(dentry)->i_mode & S_IFMT) { default: BUG(); case S_IFREG: @@ -699,7 +699,7 @@ static void rpc_depopulate(struct dentry *parent, const struct rpc_filelist *files, int start, int eof) { - struct inode *dir = parent->d_inode; + struct inode *dir = d_inode(parent); mutex_lock_nested(&dir->i_mutex, I_MUTEX_CHILD); __rpc_depopulate(parent, files, start, eof); @@ -711,7 +711,7 @@ static int rpc_populate(struct dentry *parent, int start, int eof, void *private) { - struct inode *dir = parent->d_inode; + struct inode *dir = d_inode(parent); struct dentry *dentry; int i, err; @@ -754,7 +754,7 @@ static struct dentry *rpc_mkdir_populate(struct dentry *parent, int (*populate)(struct dentry *, void *), void *args_populate) { struct dentry *dentry; - struct inode *dir = parent->d_inode; + struct inode *dir = d_inode(parent); int error; mutex_lock_nested(&dir->i_mutex, I_MUTEX_PARENT); @@ -787,7 +787,7 @@ static int rpc_rmdir_depopulate(struct dentry *dentry, int error; parent = dget_parent(dentry); - dir = parent->d_inode; + dir = d_inode(parent); mutex_lock_nested(&dir->i_mutex, I_MUTEX_PARENT); if (depopulate != NULL) depopulate(dentry); @@ -819,7 +819,7 @@ struct dentry *rpc_mkpipe_dentry(struct dentry *parent, const char *name, void *private, struct rpc_pipe *pipe) { struct dentry *dentry; - struct inode *dir = parent->d_inode; + struct inode *dir = d_inode(parent); umode_t umode = S_IFIFO | S_IRUSR | S_IWUSR; int err; @@ -864,7 +864,7 @@ rpc_unlink(struct dentry *dentry) int error = 0; parent = dget_parent(dentry); - dir = parent->d_inode; + dir = d_inode(parent); mutex_lock_nested(&dir->i_mutex, I_MUTEX_PARENT); error = __rpc_rmpipe(dir, dentry); mutex_unlock(&dir->i_mutex); @@ -1375,7 +1375,7 @@ rpc_gssd_dummy_depopulate(struct dentry *pipe_dentry) struct dentry *clnt_dir = pipe_dentry->d_parent; struct dentry *gssd_dir = clnt_dir->d_parent; - __rpc_rmpipe(clnt_dir->d_inode, pipe_dentry); + __rpc_rmpipe(d_inode(clnt_dir), pipe_dentry); __rpc_depopulate(clnt_dir, gssd_dummy_info_file, 0, 1); __rpc_depopulate(gssd_dir, gssd_dummy_clnt_dir, 0, 1); dput(pipe_dentry); diff --git a/net/sunrpc/sched.c b/net/sunrpc/sched.c index b91fd9c597b4..337ca851a350 100644 --- a/net/sunrpc/sched.c +++ b/net/sunrpc/sched.c @@ -89,8 +89,8 @@ __rpc_add_timer(struct rpc_wait_queue *queue, struct rpc_task *task) if (!task->tk_timeout) return; - dprintk("RPC: %5u setting alarm for %lu ms\n", - task->tk_pid, task->tk_timeout * 1000 / HZ); + dprintk("RPC: %5u setting alarm for %u ms\n", + task->tk_pid, jiffies_to_msecs(task->tk_timeout)); task->u.tk_wait.expires = jiffies + task->tk_timeout; if (list_empty(&queue->timer_list.list) || time_before(task->u.tk_wait.expires, queue->timer_list.expires)) diff --git a/net/sunrpc/svcsock.c b/net/sunrpc/svcsock.c index cc331b6cf573..0c8120229a03 100644 --- a/net/sunrpc/svcsock.c +++ b/net/sunrpc/svcsock.c @@ -257,7 +257,7 @@ static int svc_sendto(struct svc_rqst *rqstp, struct xdr_buf *xdr) svc_set_cmsg_data(rqstp, cmh); - if (sock_sendmsg(sock, &msg, 0) < 0) + if (sock_sendmsg(sock, &msg) < 0) goto out; } diff --git a/net/sunrpc/xprt.c b/net/sunrpc/xprt.c index 9949722d99ce..1d4fe24af06a 100644 --- a/net/sunrpc/xprt.c +++ b/net/sunrpc/xprt.c @@ -326,6 +326,15 @@ out_unlock: xprt_clear_locked(xprt); } +static void xprt_task_clear_bytes_sent(struct rpc_task *task) +{ + if (task != NULL) { + struct rpc_rqst *req = task->tk_rqstp; + if (req != NULL) + req->rq_bytes_sent = 0; + } +} + /** * xprt_release_xprt - allow other requests to use a transport * @xprt: transport with other tasks potentially waiting @@ -336,11 +345,7 @@ out_unlock: void xprt_release_xprt(struct rpc_xprt *xprt, struct rpc_task *task) { if (xprt->snd_task == task) { - if (task != NULL) { - struct rpc_rqst *req = task->tk_rqstp; - if (req != NULL) - req->rq_bytes_sent = 0; - } + xprt_task_clear_bytes_sent(task); xprt_clear_locked(xprt); __xprt_lock_write_next(xprt); } @@ -358,11 +363,7 @@ EXPORT_SYMBOL_GPL(xprt_release_xprt); void xprt_release_xprt_cong(struct rpc_xprt *xprt, struct rpc_task *task) { if (xprt->snd_task == task) { - if (task != NULL) { - struct rpc_rqst *req = task->tk_rqstp; - if (req != NULL) - req->rq_bytes_sent = 0; - } + xprt_task_clear_bytes_sent(task); xprt_clear_locked(xprt); __xprt_lock_write_next_cong(xprt); } @@ -700,6 +701,7 @@ bool xprt_lock_connect(struct rpc_xprt *xprt, goto out; if (xprt->snd_task != task) goto out; + xprt_task_clear_bytes_sent(task); xprt->snd_task = cookie; ret = true; out: diff --git a/net/sunrpc/xprtrdma/Makefile b/net/sunrpc/xprtrdma/Makefile index da5136fd5694..579f72bbcf4b 100644 --- a/net/sunrpc/xprtrdma/Makefile +++ b/net/sunrpc/xprtrdma/Makefile @@ -1,6 +1,7 @@ obj-$(CONFIG_SUNRPC_XPRT_RDMA_CLIENT) += xprtrdma.o -xprtrdma-y := transport.o rpc_rdma.o verbs.o +xprtrdma-y := transport.o rpc_rdma.o verbs.o \ + fmr_ops.o frwr_ops.o physical_ops.o obj-$(CONFIG_SUNRPC_XPRT_RDMA_SERVER) += svcrdma.o diff --git a/net/sunrpc/xprtrdma/fmr_ops.c b/net/sunrpc/xprtrdma/fmr_ops.c new file mode 100644 index 000000000000..302d4ebf6fbf --- /dev/null +++ b/net/sunrpc/xprtrdma/fmr_ops.c @@ -0,0 +1,208 @@ +/* + * Copyright (c) 2015 Oracle. All rights reserved. + * Copyright (c) 2003-2007 Network Appliance, Inc. All rights reserved. + */ + +/* Lightweight memory registration using Fast Memory Regions (FMR). + * Referred to sometimes as MTHCAFMR mode. + * + * FMR uses synchronous memory registration and deregistration. + * FMR registration is known to be fast, but FMR deregistration + * can take tens of usecs to complete. + */ + +#include "xprt_rdma.h" + +#if IS_ENABLED(CONFIG_SUNRPC_DEBUG) +# define RPCDBG_FACILITY RPCDBG_TRANS +#endif + +/* Maximum scatter/gather per FMR */ +#define RPCRDMA_MAX_FMR_SGES (64) + +static int +fmr_op_open(struct rpcrdma_ia *ia, struct rpcrdma_ep *ep, + struct rpcrdma_create_data_internal *cdata) +{ + return 0; +} + +/* FMR mode conveys up to 64 pages of payload per chunk segment. + */ +static size_t +fmr_op_maxpages(struct rpcrdma_xprt *r_xprt) +{ + return min_t(unsigned int, RPCRDMA_MAX_DATA_SEGS, + rpcrdma_max_segments(r_xprt) * RPCRDMA_MAX_FMR_SGES); +} + +static int +fmr_op_init(struct rpcrdma_xprt *r_xprt) +{ + struct rpcrdma_buffer *buf = &r_xprt->rx_buf; + int mr_access_flags = IB_ACCESS_REMOTE_WRITE | IB_ACCESS_REMOTE_READ; + struct ib_fmr_attr fmr_attr = { + .max_pages = RPCRDMA_MAX_FMR_SGES, + .max_maps = 1, + .page_shift = PAGE_SHIFT + }; + struct ib_pd *pd = r_xprt->rx_ia.ri_pd; + struct rpcrdma_mw *r; + int i, rc; + + INIT_LIST_HEAD(&buf->rb_mws); + INIT_LIST_HEAD(&buf->rb_all); + + i = (buf->rb_max_requests + 1) * RPCRDMA_MAX_SEGS; + dprintk("RPC: %s: initializing %d FMRs\n", __func__, i); + + while (i--) { + r = kzalloc(sizeof(*r), GFP_KERNEL); + if (!r) + return -ENOMEM; + + r->r.fmr = ib_alloc_fmr(pd, mr_access_flags, &fmr_attr); + if (IS_ERR(r->r.fmr)) + goto out_fmr_err; + + list_add(&r->mw_list, &buf->rb_mws); + list_add(&r->mw_all, &buf->rb_all); + } + return 0; + +out_fmr_err: + rc = PTR_ERR(r->r.fmr); + dprintk("RPC: %s: ib_alloc_fmr status %i\n", __func__, rc); + kfree(r); + return rc; +} + +/* Use the ib_map_phys_fmr() verb to register a memory region + * for remote access via RDMA READ or RDMA WRITE. + */ +static int +fmr_op_map(struct rpcrdma_xprt *r_xprt, struct rpcrdma_mr_seg *seg, + int nsegs, bool writing) +{ + struct rpcrdma_ia *ia = &r_xprt->rx_ia; + struct ib_device *device = ia->ri_id->device; + enum dma_data_direction direction = rpcrdma_data_dir(writing); + struct rpcrdma_mr_seg *seg1 = seg; + struct rpcrdma_mw *mw = seg1->rl_mw; + u64 physaddrs[RPCRDMA_MAX_DATA_SEGS]; + int len, pageoff, i, rc; + + pageoff = offset_in_page(seg1->mr_offset); + seg1->mr_offset -= pageoff; /* start of page */ + seg1->mr_len += pageoff; + len = -pageoff; + if (nsegs > RPCRDMA_MAX_FMR_SGES) + nsegs = RPCRDMA_MAX_FMR_SGES; + for (i = 0; i < nsegs;) { + rpcrdma_map_one(device, seg, direction); + physaddrs[i] = seg->mr_dma; + len += seg->mr_len; + ++seg; + ++i; + /* Check for holes */ + if ((i < nsegs && offset_in_page(seg->mr_offset)) || + offset_in_page((seg-1)->mr_offset + (seg-1)->mr_len)) + break; + } + + rc = ib_map_phys_fmr(mw->r.fmr, physaddrs, i, seg1->mr_dma); + if (rc) + goto out_maperr; + + seg1->mr_rkey = mw->r.fmr->rkey; + seg1->mr_base = seg1->mr_dma + pageoff; + seg1->mr_nsegs = i; + seg1->mr_len = len; + return i; + +out_maperr: + dprintk("RPC: %s: ib_map_phys_fmr %u@0x%llx+%i (%d) status %i\n", + __func__, len, (unsigned long long)seg1->mr_dma, + pageoff, i, rc); + while (i--) + rpcrdma_unmap_one(device, --seg); + return rc; +} + +/* Use the ib_unmap_fmr() verb to prevent further remote + * access via RDMA READ or RDMA WRITE. + */ +static int +fmr_op_unmap(struct rpcrdma_xprt *r_xprt, struct rpcrdma_mr_seg *seg) +{ + struct rpcrdma_ia *ia = &r_xprt->rx_ia; + struct rpcrdma_mr_seg *seg1 = seg; + struct ib_device *device; + int rc, nsegs = seg->mr_nsegs; + LIST_HEAD(l); + + list_add(&seg1->rl_mw->r.fmr->list, &l); + rc = ib_unmap_fmr(&l); + read_lock(&ia->ri_qplock); + device = ia->ri_id->device; + while (seg1->mr_nsegs--) + rpcrdma_unmap_one(device, seg++); + read_unlock(&ia->ri_qplock); + if (rc) + goto out_err; + return nsegs; + +out_err: + dprintk("RPC: %s: ib_unmap_fmr status %i\n", __func__, rc); + return nsegs; +} + +/* After a disconnect, unmap all FMRs. + * + * This is invoked only in the transport connect worker in order + * to serialize with rpcrdma_register_fmr_external(). + */ +static void +fmr_op_reset(struct rpcrdma_xprt *r_xprt) +{ + struct rpcrdma_buffer *buf = &r_xprt->rx_buf; + struct rpcrdma_mw *r; + LIST_HEAD(list); + int rc; + + list_for_each_entry(r, &buf->rb_all, mw_all) + list_add(&r->r.fmr->list, &list); + + rc = ib_unmap_fmr(&list); + if (rc) + dprintk("RPC: %s: ib_unmap_fmr failed %i\n", + __func__, rc); +} + +static void +fmr_op_destroy(struct rpcrdma_buffer *buf) +{ + struct rpcrdma_mw *r; + int rc; + + while (!list_empty(&buf->rb_all)) { + r = list_entry(buf->rb_all.next, struct rpcrdma_mw, mw_all); + list_del(&r->mw_all); + rc = ib_dealloc_fmr(r->r.fmr); + if (rc) + dprintk("RPC: %s: ib_dealloc_fmr failed %i\n", + __func__, rc); + kfree(r); + } +} + +const struct rpcrdma_memreg_ops rpcrdma_fmr_memreg_ops = { + .ro_map = fmr_op_map, + .ro_unmap = fmr_op_unmap, + .ro_open = fmr_op_open, + .ro_maxpages = fmr_op_maxpages, + .ro_init = fmr_op_init, + .ro_reset = fmr_op_reset, + .ro_destroy = fmr_op_destroy, + .ro_displayname = "fmr", +}; diff --git a/net/sunrpc/xprtrdma/frwr_ops.c b/net/sunrpc/xprtrdma/frwr_ops.c new file mode 100644 index 000000000000..dff0481dbcf8 --- /dev/null +++ b/net/sunrpc/xprtrdma/frwr_ops.c @@ -0,0 +1,353 @@ +/* + * Copyright (c) 2015 Oracle. All rights reserved. + * Copyright (c) 2003-2007 Network Appliance, Inc. All rights reserved. + */ + +/* Lightweight memory registration using Fast Registration Work + * Requests (FRWR). Also referred to sometimes as FRMR mode. + * + * FRWR features ordered asynchronous registration and deregistration + * of arbitrarily sized memory regions. This is the fastest and safest + * but most complex memory registration mode. + */ + +#include "xprt_rdma.h" + +#if IS_ENABLED(CONFIG_SUNRPC_DEBUG) +# define RPCDBG_FACILITY RPCDBG_TRANS +#endif + +static int +__frwr_init(struct rpcrdma_mw *r, struct ib_pd *pd, struct ib_device *device, + unsigned int depth) +{ + struct rpcrdma_frmr *f = &r->r.frmr; + int rc; + + f->fr_mr = ib_alloc_fast_reg_mr(pd, depth); + if (IS_ERR(f->fr_mr)) + goto out_mr_err; + f->fr_pgl = ib_alloc_fast_reg_page_list(device, depth); + if (IS_ERR(f->fr_pgl)) + goto out_list_err; + return 0; + +out_mr_err: + rc = PTR_ERR(f->fr_mr); + dprintk("RPC: %s: ib_alloc_fast_reg_mr status %i\n", + __func__, rc); + return rc; + +out_list_err: + rc = PTR_ERR(f->fr_pgl); + dprintk("RPC: %s: ib_alloc_fast_reg_page_list status %i\n", + __func__, rc); + ib_dereg_mr(f->fr_mr); + return rc; +} + +static void +__frwr_release(struct rpcrdma_mw *r) +{ + int rc; + + rc = ib_dereg_mr(r->r.frmr.fr_mr); + if (rc) + dprintk("RPC: %s: ib_dereg_mr status %i\n", + __func__, rc); + ib_free_fast_reg_page_list(r->r.frmr.fr_pgl); +} + +static int +frwr_op_open(struct rpcrdma_ia *ia, struct rpcrdma_ep *ep, + struct rpcrdma_create_data_internal *cdata) +{ + struct ib_device_attr *devattr = &ia->ri_devattr; + int depth, delta; + + ia->ri_max_frmr_depth = + min_t(unsigned int, RPCRDMA_MAX_DATA_SEGS, + devattr->max_fast_reg_page_list_len); + dprintk("RPC: %s: device's max FR page list len = %u\n", + __func__, ia->ri_max_frmr_depth); + + /* Add room for frmr register and invalidate WRs. + * 1. FRMR reg WR for head + * 2. FRMR invalidate WR for head + * 3. N FRMR reg WRs for pagelist + * 4. N FRMR invalidate WRs for pagelist + * 5. FRMR reg WR for tail + * 6. FRMR invalidate WR for tail + * 7. The RDMA_SEND WR + */ + depth = 7; + + /* Calculate N if the device max FRMR depth is smaller than + * RPCRDMA_MAX_DATA_SEGS. + */ + if (ia->ri_max_frmr_depth < RPCRDMA_MAX_DATA_SEGS) { + delta = RPCRDMA_MAX_DATA_SEGS - ia->ri_max_frmr_depth; + do { + depth += 2; /* FRMR reg + invalidate */ + delta -= ia->ri_max_frmr_depth; + } while (delta > 0); + } + + ep->rep_attr.cap.max_send_wr *= depth; + if (ep->rep_attr.cap.max_send_wr > devattr->max_qp_wr) { + cdata->max_requests = devattr->max_qp_wr / depth; + if (!cdata->max_requests) + return -EINVAL; + ep->rep_attr.cap.max_send_wr = cdata->max_requests * + depth; + } + + return 0; +} + +/* FRWR mode conveys a list of pages per chunk segment. The + * maximum length of that list is the FRWR page list depth. + */ +static size_t +frwr_op_maxpages(struct rpcrdma_xprt *r_xprt) +{ + struct rpcrdma_ia *ia = &r_xprt->rx_ia; + + return min_t(unsigned int, RPCRDMA_MAX_DATA_SEGS, + rpcrdma_max_segments(r_xprt) * ia->ri_max_frmr_depth); +} + +/* If FAST_REG or LOCAL_INV failed, indicate the frmr needs to be reset. */ +static void +frwr_sendcompletion(struct ib_wc *wc) +{ + struct rpcrdma_mw *r; + + if (likely(wc->status == IB_WC_SUCCESS)) + return; + + /* WARNING: Only wr_id and status are reliable at this point */ + r = (struct rpcrdma_mw *)(unsigned long)wc->wr_id; + dprintk("RPC: %s: frmr %p (stale), status %d\n", + __func__, r, wc->status); + r->r.frmr.fr_state = FRMR_IS_STALE; +} + +static int +frwr_op_init(struct rpcrdma_xprt *r_xprt) +{ + struct rpcrdma_buffer *buf = &r_xprt->rx_buf; + struct ib_device *device = r_xprt->rx_ia.ri_id->device; + unsigned int depth = r_xprt->rx_ia.ri_max_frmr_depth; + struct ib_pd *pd = r_xprt->rx_ia.ri_pd; + int i; + + INIT_LIST_HEAD(&buf->rb_mws); + INIT_LIST_HEAD(&buf->rb_all); + + i = (buf->rb_max_requests + 1) * RPCRDMA_MAX_SEGS; + dprintk("RPC: %s: initializing %d FRMRs\n", __func__, i); + + while (i--) { + struct rpcrdma_mw *r; + int rc; + + r = kzalloc(sizeof(*r), GFP_KERNEL); + if (!r) + return -ENOMEM; + + rc = __frwr_init(r, pd, device, depth); + if (rc) { + kfree(r); + return rc; + } + + list_add(&r->mw_list, &buf->rb_mws); + list_add(&r->mw_all, &buf->rb_all); + r->mw_sendcompletion = frwr_sendcompletion; + } + + return 0; +} + +/* Post a FAST_REG Work Request to register a memory region + * for remote access via RDMA READ or RDMA WRITE. + */ +static int +frwr_op_map(struct rpcrdma_xprt *r_xprt, struct rpcrdma_mr_seg *seg, + int nsegs, bool writing) +{ + struct rpcrdma_ia *ia = &r_xprt->rx_ia; + struct ib_device *device = ia->ri_id->device; + enum dma_data_direction direction = rpcrdma_data_dir(writing); + struct rpcrdma_mr_seg *seg1 = seg; + struct rpcrdma_mw *mw = seg1->rl_mw; + struct rpcrdma_frmr *frmr = &mw->r.frmr; + struct ib_mr *mr = frmr->fr_mr; + struct ib_send_wr fastreg_wr, *bad_wr; + u8 key; + int len, pageoff; + int i, rc; + int seg_len; + u64 pa; + int page_no; + + pageoff = offset_in_page(seg1->mr_offset); + seg1->mr_offset -= pageoff; /* start of page */ + seg1->mr_len += pageoff; + len = -pageoff; + if (nsegs > ia->ri_max_frmr_depth) + nsegs = ia->ri_max_frmr_depth; + for (page_no = i = 0; i < nsegs;) { + rpcrdma_map_one(device, seg, direction); + pa = seg->mr_dma; + for (seg_len = seg->mr_len; seg_len > 0; seg_len -= PAGE_SIZE) { + frmr->fr_pgl->page_list[page_no++] = pa; + pa += PAGE_SIZE; + } + len += seg->mr_len; + ++seg; + ++i; + /* Check for holes */ + if ((i < nsegs && offset_in_page(seg->mr_offset)) || + offset_in_page((seg-1)->mr_offset + (seg-1)->mr_len)) + break; + } + dprintk("RPC: %s: Using frmr %p to map %d segments (%d bytes)\n", + __func__, mw, i, len); + + frmr->fr_state = FRMR_IS_VALID; + + memset(&fastreg_wr, 0, sizeof(fastreg_wr)); + fastreg_wr.wr_id = (unsigned long)(void *)mw; + fastreg_wr.opcode = IB_WR_FAST_REG_MR; + fastreg_wr.wr.fast_reg.iova_start = seg1->mr_dma + pageoff; + fastreg_wr.wr.fast_reg.page_list = frmr->fr_pgl; + fastreg_wr.wr.fast_reg.page_shift = PAGE_SHIFT; + fastreg_wr.wr.fast_reg.page_list_len = page_no; + fastreg_wr.wr.fast_reg.length = len; + fastreg_wr.wr.fast_reg.access_flags = writing ? + IB_ACCESS_REMOTE_WRITE | IB_ACCESS_LOCAL_WRITE : + IB_ACCESS_REMOTE_READ; + key = (u8)(mr->rkey & 0x000000FF); + ib_update_fast_reg_key(mr, ++key); + fastreg_wr.wr.fast_reg.rkey = mr->rkey; + + DECR_CQCOUNT(&r_xprt->rx_ep); + rc = ib_post_send(ia->ri_id->qp, &fastreg_wr, &bad_wr); + if (rc) + goto out_senderr; + + seg1->mr_rkey = mr->rkey; + seg1->mr_base = seg1->mr_dma + pageoff; + seg1->mr_nsegs = i; + seg1->mr_len = len; + return i; + +out_senderr: + dprintk("RPC: %s: ib_post_send status %i\n", __func__, rc); + ib_update_fast_reg_key(mr, --key); + frmr->fr_state = FRMR_IS_INVALID; + while (i--) + rpcrdma_unmap_one(device, --seg); + return rc; +} + +/* Post a LOCAL_INV Work Request to prevent further remote access + * via RDMA READ or RDMA WRITE. + */ +static int +frwr_op_unmap(struct rpcrdma_xprt *r_xprt, struct rpcrdma_mr_seg *seg) +{ + struct rpcrdma_mr_seg *seg1 = seg; + struct rpcrdma_ia *ia = &r_xprt->rx_ia; + struct ib_send_wr invalidate_wr, *bad_wr; + int rc, nsegs = seg->mr_nsegs; + struct ib_device *device; + + seg1->rl_mw->r.frmr.fr_state = FRMR_IS_INVALID; + + memset(&invalidate_wr, 0, sizeof(invalidate_wr)); + invalidate_wr.wr_id = (unsigned long)(void *)seg1->rl_mw; + invalidate_wr.opcode = IB_WR_LOCAL_INV; + invalidate_wr.ex.invalidate_rkey = seg1->rl_mw->r.frmr.fr_mr->rkey; + DECR_CQCOUNT(&r_xprt->rx_ep); + + read_lock(&ia->ri_qplock); + device = ia->ri_id->device; + while (seg1->mr_nsegs--) + rpcrdma_unmap_one(device, seg++); + rc = ib_post_send(ia->ri_id->qp, &invalidate_wr, &bad_wr); + read_unlock(&ia->ri_qplock); + if (rc) + goto out_err; + return nsegs; + +out_err: + /* Force rpcrdma_buffer_get() to retry */ + seg1->rl_mw->r.frmr.fr_state = FRMR_IS_STALE; + dprintk("RPC: %s: ib_post_send status %i\n", __func__, rc); + return nsegs; +} + +/* After a disconnect, a flushed FAST_REG_MR can leave an FRMR in + * an unusable state. Find FRMRs in this state and dereg / reg + * each. FRMRs that are VALID and attached to an rpcrdma_req are + * also torn down. + * + * This gives all in-use FRMRs a fresh rkey and leaves them INVALID. + * + * This is invoked only in the transport connect worker in order + * to serialize with rpcrdma_register_frmr_external(). + */ +static void +frwr_op_reset(struct rpcrdma_xprt *r_xprt) +{ + struct rpcrdma_buffer *buf = &r_xprt->rx_buf; + struct ib_device *device = r_xprt->rx_ia.ri_id->device; + unsigned int depth = r_xprt->rx_ia.ri_max_frmr_depth; + struct ib_pd *pd = r_xprt->rx_ia.ri_pd; + struct rpcrdma_mw *r; + int rc; + + list_for_each_entry(r, &buf->rb_all, mw_all) { + if (r->r.frmr.fr_state == FRMR_IS_INVALID) + continue; + + __frwr_release(r); + rc = __frwr_init(r, pd, device, depth); + if (rc) { + dprintk("RPC: %s: mw %p left %s\n", + __func__, r, + (r->r.frmr.fr_state == FRMR_IS_STALE ? + "stale" : "valid")); + continue; + } + + r->r.frmr.fr_state = FRMR_IS_INVALID; + } +} + +static void +frwr_op_destroy(struct rpcrdma_buffer *buf) +{ + struct rpcrdma_mw *r; + + while (!list_empty(&buf->rb_all)) { + r = list_entry(buf->rb_all.next, struct rpcrdma_mw, mw_all); + list_del(&r->mw_all); + __frwr_release(r); + kfree(r); + } +} + +const struct rpcrdma_memreg_ops rpcrdma_frwr_memreg_ops = { + .ro_map = frwr_op_map, + .ro_unmap = frwr_op_unmap, + .ro_open = frwr_op_open, + .ro_maxpages = frwr_op_maxpages, + .ro_init = frwr_op_init, + .ro_reset = frwr_op_reset, + .ro_destroy = frwr_op_destroy, + .ro_displayname = "frwr", +}; diff --git a/net/sunrpc/xprtrdma/physical_ops.c b/net/sunrpc/xprtrdma/physical_ops.c new file mode 100644 index 000000000000..ba518af16787 --- /dev/null +++ b/net/sunrpc/xprtrdma/physical_ops.c @@ -0,0 +1,94 @@ +/* + * Copyright (c) 2015 Oracle. All rights reserved. + * Copyright (c) 2003-2007 Network Appliance, Inc. All rights reserved. + */ + +/* No-op chunk preparation. All client memory is pre-registered. + * Sometimes referred to as ALLPHYSICAL mode. + * + * Physical registration is simple because all client memory is + * pre-registered and never deregistered. This mode is good for + * adapter bring up, but is considered not safe: the server is + * trusted not to abuse its access to client memory not involved + * in RDMA I/O. + */ + +#include "xprt_rdma.h" + +#if IS_ENABLED(CONFIG_SUNRPC_DEBUG) +# define RPCDBG_FACILITY RPCDBG_TRANS +#endif + +static int +physical_op_open(struct rpcrdma_ia *ia, struct rpcrdma_ep *ep, + struct rpcrdma_create_data_internal *cdata) +{ + return 0; +} + +/* PHYSICAL memory registration conveys one page per chunk segment. + */ +static size_t +physical_op_maxpages(struct rpcrdma_xprt *r_xprt) +{ + return min_t(unsigned int, RPCRDMA_MAX_DATA_SEGS, + rpcrdma_max_segments(r_xprt)); +} + +static int +physical_op_init(struct rpcrdma_xprt *r_xprt) +{ + return 0; +} + +/* The client's physical memory is already exposed for + * remote access via RDMA READ or RDMA WRITE. + */ +static int +physical_op_map(struct rpcrdma_xprt *r_xprt, struct rpcrdma_mr_seg *seg, + int nsegs, bool writing) +{ + struct rpcrdma_ia *ia = &r_xprt->rx_ia; + + rpcrdma_map_one(ia->ri_id->device, seg, + rpcrdma_data_dir(writing)); + seg->mr_rkey = ia->ri_bind_mem->rkey; + seg->mr_base = seg->mr_dma; + seg->mr_nsegs = 1; + return 1; +} + +/* Unmap a memory region, but leave it registered. + */ +static int +physical_op_unmap(struct rpcrdma_xprt *r_xprt, struct rpcrdma_mr_seg *seg) +{ + struct rpcrdma_ia *ia = &r_xprt->rx_ia; + + read_lock(&ia->ri_qplock); + rpcrdma_unmap_one(ia->ri_id->device, seg); + read_unlock(&ia->ri_qplock); + + return 1; +} + +static void +physical_op_reset(struct rpcrdma_xprt *r_xprt) +{ +} + +static void +physical_op_destroy(struct rpcrdma_buffer *buf) +{ +} + +const struct rpcrdma_memreg_ops rpcrdma_physical_memreg_ops = { + .ro_map = physical_op_map, + .ro_unmap = physical_op_unmap, + .ro_open = physical_op_open, + .ro_maxpages = physical_op_maxpages, + .ro_init = physical_op_init, + .ro_reset = physical_op_reset, + .ro_destroy = physical_op_destroy, + .ro_displayname = "physical", +}; diff --git a/net/sunrpc/xprtrdma/rpc_rdma.c b/net/sunrpc/xprtrdma/rpc_rdma.c index 91ffde82fa0c..2c53ea9e1b83 100644 --- a/net/sunrpc/xprtrdma/rpc_rdma.c +++ b/net/sunrpc/xprtrdma/rpc_rdma.c @@ -53,6 +53,14 @@ # define RPCDBG_FACILITY RPCDBG_TRANS #endif +enum rpcrdma_chunktype { + rpcrdma_noch = 0, + rpcrdma_readch, + rpcrdma_areadch, + rpcrdma_writech, + rpcrdma_replych +}; + #if IS_ENABLED(CONFIG_SUNRPC_DEBUG) static const char transfertypes[][12] = { "pure inline", /* no chunks */ @@ -179,6 +187,7 @@ rpcrdma_create_chunks(struct rpc_rqst *rqst, struct xdr_buf *target, struct rpcrdma_write_array *warray = NULL; struct rpcrdma_write_chunk *cur_wchunk = NULL; __be32 *iptr = headerp->rm_body.rm_chunks; + int (*map)(struct rpcrdma_xprt *, struct rpcrdma_mr_seg *, int, bool); if (type == rpcrdma_readch || type == rpcrdma_areadch) { /* a read chunk - server will RDMA Read our memory */ @@ -201,9 +210,9 @@ rpcrdma_create_chunks(struct rpc_rqst *rqst, struct xdr_buf *target, if (nsegs < 0) return nsegs; + map = r_xprt->rx_ia.ri_ops->ro_map; do { - n = rpcrdma_register_external(seg, nsegs, - cur_wchunk != NULL, r_xprt); + n = map(r_xprt, seg, nsegs, cur_wchunk != NULL); if (n <= 0) goto out; if (cur_rchunk) { /* read */ @@ -275,34 +284,13 @@ rpcrdma_create_chunks(struct rpc_rqst *rqst, struct xdr_buf *target, return (unsigned char *)iptr - (unsigned char *)headerp; out: - if (r_xprt->rx_ia.ri_memreg_strategy != RPCRDMA_FRMR) { - for (pos = 0; nchunks--;) - pos += rpcrdma_deregister_external( - &req->rl_segments[pos], r_xprt); - } - return n; -} + if (r_xprt->rx_ia.ri_memreg_strategy == RPCRDMA_FRMR) + return n; -/* - * Marshal chunks. This routine returns the header length - * consumed by marshaling. - * - * Returns positive RPC/RDMA header size, or negative errno. - */ - -ssize_t -rpcrdma_marshal_chunks(struct rpc_rqst *rqst, ssize_t result) -{ - struct rpcrdma_req *req = rpcr_to_rdmar(rqst); - struct rpcrdma_msg *headerp = rdmab_to_msg(req->rl_rdmabuf); - - if (req->rl_rtype != rpcrdma_noch) - result = rpcrdma_create_chunks(rqst, &rqst->rq_snd_buf, - headerp, req->rl_rtype); - else if (req->rl_wtype != rpcrdma_noch) - result = rpcrdma_create_chunks(rqst, &rqst->rq_rcv_buf, - headerp, req->rl_wtype); - return result; + for (pos = 0; nchunks--;) + pos += r_xprt->rx_ia.ri_ops->ro_unmap(r_xprt, + &req->rl_segments[pos]); + return n; } /* @@ -397,6 +385,7 @@ rpcrdma_marshal_req(struct rpc_rqst *rqst) char *base; size_t rpclen, padlen; ssize_t hdrlen; + enum rpcrdma_chunktype rtype, wtype; struct rpcrdma_msg *headerp; /* @@ -433,13 +422,13 @@ rpcrdma_marshal_req(struct rpc_rqst *rqst) * into pages; otherwise use reply chunks. */ if (rqst->rq_rcv_buf.buflen <= RPCRDMA_INLINE_READ_THRESHOLD(rqst)) - req->rl_wtype = rpcrdma_noch; + wtype = rpcrdma_noch; else if (rqst->rq_rcv_buf.page_len == 0) - req->rl_wtype = rpcrdma_replych; + wtype = rpcrdma_replych; else if (rqst->rq_rcv_buf.flags & XDRBUF_READ) - req->rl_wtype = rpcrdma_writech; + wtype = rpcrdma_writech; else - req->rl_wtype = rpcrdma_replych; + wtype = rpcrdma_replych; /* * Chunks needed for arguments? @@ -456,16 +445,16 @@ rpcrdma_marshal_req(struct rpc_rqst *rqst) * TBD check NFSv4 setacl */ if (rqst->rq_snd_buf.len <= RPCRDMA_INLINE_WRITE_THRESHOLD(rqst)) - req->rl_rtype = rpcrdma_noch; + rtype = rpcrdma_noch; else if (rqst->rq_snd_buf.page_len == 0) - req->rl_rtype = rpcrdma_areadch; + rtype = rpcrdma_areadch; else - req->rl_rtype = rpcrdma_readch; + rtype = rpcrdma_readch; /* The following simplification is not true forever */ - if (req->rl_rtype != rpcrdma_noch && req->rl_wtype == rpcrdma_replych) - req->rl_wtype = rpcrdma_noch; - if (req->rl_rtype != rpcrdma_noch && req->rl_wtype != rpcrdma_noch) { + if (rtype != rpcrdma_noch && wtype == rpcrdma_replych) + wtype = rpcrdma_noch; + if (rtype != rpcrdma_noch && wtype != rpcrdma_noch) { dprintk("RPC: %s: cannot marshal multiple chunk lists\n", __func__); return -EIO; @@ -479,7 +468,7 @@ rpcrdma_marshal_req(struct rpc_rqst *rqst) * When padding is in use and applies to the transfer, insert * it and change the message type. */ - if (req->rl_rtype == rpcrdma_noch) { + if (rtype == rpcrdma_noch) { padlen = rpcrdma_inline_pullup(rqst, RPCRDMA_INLINE_PAD_VALUE(rqst)); @@ -494,7 +483,7 @@ rpcrdma_marshal_req(struct rpc_rqst *rqst) headerp->rm_body.rm_padded.rm_pempty[1] = xdr_zero; headerp->rm_body.rm_padded.rm_pempty[2] = xdr_zero; hdrlen += 2 * sizeof(u32); /* extra words in padhdr */ - if (req->rl_wtype != rpcrdma_noch) { + if (wtype != rpcrdma_noch) { dprintk("RPC: %s: invalid chunk list\n", __func__); return -EIO; @@ -515,18 +504,26 @@ rpcrdma_marshal_req(struct rpc_rqst *rqst) * on receive. Therefore, we request a reply chunk * for non-writes wherever feasible and efficient. */ - if (req->rl_wtype == rpcrdma_noch) - req->rl_wtype = rpcrdma_replych; + if (wtype == rpcrdma_noch) + wtype = rpcrdma_replych; } } - hdrlen = rpcrdma_marshal_chunks(rqst, hdrlen); + if (rtype != rpcrdma_noch) { + hdrlen = rpcrdma_create_chunks(rqst, &rqst->rq_snd_buf, + headerp, rtype); + wtype = rtype; /* simplify dprintk */ + + } else if (wtype != rpcrdma_noch) { + hdrlen = rpcrdma_create_chunks(rqst, &rqst->rq_rcv_buf, + headerp, wtype); + } if (hdrlen < 0) return hdrlen; dprintk("RPC: %s: %s: hdrlen %zd rpclen %zd padlen %zd" " headerp 0x%p base 0x%p lkey 0x%x\n", - __func__, transfertypes[req->rl_wtype], hdrlen, rpclen, padlen, + __func__, transfertypes[wtype], hdrlen, rpclen, padlen, headerp, base, rdmab_lkey(req->rl_rdmabuf)); /* diff --git a/net/sunrpc/xprtrdma/transport.c b/net/sunrpc/xprtrdma/transport.c index 2e192baa59f3..54f23b1be986 100644 --- a/net/sunrpc/xprtrdma/transport.c +++ b/net/sunrpc/xprtrdma/transport.c @@ -157,12 +157,47 @@ static struct ctl_table sunrpc_table[] = { static struct rpc_xprt_ops xprt_rdma_procs; /* forward reference */ static void +xprt_rdma_format_addresses4(struct rpc_xprt *xprt, struct sockaddr *sap) +{ + struct sockaddr_in *sin = (struct sockaddr_in *)sap; + char buf[20]; + + snprintf(buf, sizeof(buf), "%08x", ntohl(sin->sin_addr.s_addr)); + xprt->address_strings[RPC_DISPLAY_HEX_ADDR] = kstrdup(buf, GFP_KERNEL); + + xprt->address_strings[RPC_DISPLAY_NETID] = RPCBIND_NETID_RDMA; +} + +static void +xprt_rdma_format_addresses6(struct rpc_xprt *xprt, struct sockaddr *sap) +{ + struct sockaddr_in6 *sin6 = (struct sockaddr_in6 *)sap; + char buf[40]; + + snprintf(buf, sizeof(buf), "%pi6", &sin6->sin6_addr); + xprt->address_strings[RPC_DISPLAY_HEX_ADDR] = kstrdup(buf, GFP_KERNEL); + + xprt->address_strings[RPC_DISPLAY_NETID] = RPCBIND_NETID_RDMA6; +} + +static void xprt_rdma_format_addresses(struct rpc_xprt *xprt) { struct sockaddr *sap = (struct sockaddr *) &rpcx_to_rdmad(xprt).addr; - struct sockaddr_in *sin = (struct sockaddr_in *)sap; - char buf[64]; + char buf[128]; + + switch (sap->sa_family) { + case AF_INET: + xprt_rdma_format_addresses4(xprt, sap); + break; + case AF_INET6: + xprt_rdma_format_addresses6(xprt, sap); + break; + default: + pr_err("rpcrdma: Unrecognized address family\n"); + return; + } (void)rpc_ntop(sap, buf, sizeof(buf)); xprt->address_strings[RPC_DISPLAY_ADDR] = kstrdup(buf, GFP_KERNEL); @@ -170,16 +205,10 @@ xprt_rdma_format_addresses(struct rpc_xprt *xprt) snprintf(buf, sizeof(buf), "%u", rpc_get_port(sap)); xprt->address_strings[RPC_DISPLAY_PORT] = kstrdup(buf, GFP_KERNEL); - xprt->address_strings[RPC_DISPLAY_PROTO] = "rdma"; - - snprintf(buf, sizeof(buf), "%08x", ntohl(sin->sin_addr.s_addr)); - xprt->address_strings[RPC_DISPLAY_HEX_ADDR] = kstrdup(buf, GFP_KERNEL); - snprintf(buf, sizeof(buf), "%4hx", rpc_get_port(sap)); xprt->address_strings[RPC_DISPLAY_HEX_PORT] = kstrdup(buf, GFP_KERNEL); - /* netid */ - xprt->address_strings[RPC_DISPLAY_NETID] = "rdma"; + xprt->address_strings[RPC_DISPLAY_PROTO] = "rdma"; } static void @@ -377,7 +406,10 @@ xprt_setup_rdma(struct xprt_create *args) xprt_rdma_connect_worker); xprt_rdma_format_addresses(xprt); - xprt->max_payload = rpcrdma_max_payload(new_xprt); + xprt->max_payload = new_xprt->rx_ia.ri_ops->ro_maxpages(new_xprt); + if (xprt->max_payload == 0) + goto out4; + xprt->max_payload <<= PAGE_SHIFT; dprintk("RPC: %s: transport data payload maximum: %zu bytes\n", __func__, xprt->max_payload); @@ -552,8 +584,8 @@ xprt_rdma_free(void *buffer) for (i = 0; req->rl_nchunks;) { --req->rl_nchunks; - i += rpcrdma_deregister_external( - &req->rl_segments[i], r_xprt); + i += r_xprt->rx_ia.ri_ops->ro_unmap(r_xprt, + &req->rl_segments[i]); } rpcrdma_buffer_put(req); @@ -579,10 +611,7 @@ xprt_rdma_send_request(struct rpc_task *task) struct rpcrdma_xprt *r_xprt = rpcx_to_rdmax(xprt); int rc = 0; - if (req->rl_niovs == 0) - rc = rpcrdma_marshal_req(rqst); - else if (r_xprt->rx_ia.ri_memreg_strategy != RPCRDMA_ALLPHYSICAL) - rc = rpcrdma_marshal_chunks(rqst, 0); + rc = rpcrdma_marshal_req(rqst); if (rc < 0) goto failed_marshal; diff --git a/net/sunrpc/xprtrdma/verbs.c b/net/sunrpc/xprtrdma/verbs.c index 124676c13780..4870d272e006 100644 --- a/net/sunrpc/xprtrdma/verbs.c +++ b/net/sunrpc/xprtrdma/verbs.c @@ -50,6 +50,7 @@ #include <linux/interrupt.h> #include <linux/slab.h> #include <linux/prefetch.h> +#include <linux/sunrpc/addr.h> #include <asm/bitops.h> #include "xprt_rdma.h" @@ -62,9 +63,6 @@ # define RPCDBG_FACILITY RPCDBG_TRANS #endif -static void rpcrdma_reset_frmrs(struct rpcrdma_ia *); -static void rpcrdma_reset_fmrs(struct rpcrdma_ia *); - /* * internal functions */ @@ -188,7 +186,7 @@ static const char * const wc_status[] = { "remote access error", "remote operation error", "transport retry counter exceeded", - "RNR retrycounter exceeded", + "RNR retry counter exceeded", "local RDD violation error", "remove invalid RD request", "operation aborted", @@ -206,21 +204,17 @@ static const char * const wc_status[] = { static void rpcrdma_sendcq_process_wc(struct ib_wc *wc) { - if (likely(wc->status == IB_WC_SUCCESS)) - return; - /* WARNING: Only wr_id and status are reliable at this point */ - if (wc->wr_id == 0ULL) { - if (wc->status != IB_WC_WR_FLUSH_ERR) + if (wc->wr_id == RPCRDMA_IGNORE_COMPLETION) { + if (wc->status != IB_WC_SUCCESS && + wc->status != IB_WC_WR_FLUSH_ERR) pr_err("RPC: %s: SEND: %s\n", __func__, COMPLETION_MSG(wc->status)); } else { struct rpcrdma_mw *r; r = (struct rpcrdma_mw *)(unsigned long)wc->wr_id; - r->r.frmr.fr_state = FRMR_IS_STALE; - pr_err("RPC: %s: frmr %p (stale): %s\n", - __func__, r, COMPLETION_MSG(wc->status)); + r->mw_sendcompletion(wc); } } @@ -424,7 +418,7 @@ rpcrdma_conn_upcall(struct rdma_cm_id *id, struct rdma_cm_event *event) struct rpcrdma_ia *ia = &xprt->rx_ia; struct rpcrdma_ep *ep = &xprt->rx_ep; #if IS_ENABLED(CONFIG_SUNRPC_DEBUG) - struct sockaddr_in *addr = (struct sockaddr_in *) &ep->rep_remote_addr; + struct sockaddr *sap = (struct sockaddr *)&ep->rep_remote_addr; #endif struct ib_qp_attr *attr = &ia->ri_qp_attr; struct ib_qp_init_attr *iattr = &ia->ri_qp_init_attr; @@ -480,9 +474,8 @@ connected: wake_up_all(&ep->rep_connect_wait); /*FALLTHROUGH*/ default: - dprintk("RPC: %s: %pI4:%u (ep 0x%p): %s\n", - __func__, &addr->sin_addr.s_addr, - ntohs(addr->sin_port), ep, + dprintk("RPC: %s: %pIS:%u (ep 0x%p): %s\n", + __func__, sap, rpc_get_port(sap), ep, CONNECTION_MSG(event->event)); break; } @@ -491,19 +484,16 @@ connected: if (connstate == 1) { int ird = attr->max_dest_rd_atomic; int tird = ep->rep_remote_cma.responder_resources; - printk(KERN_INFO "rpcrdma: connection to %pI4:%u " - "on %s, memreg %d slots %d ird %d%s\n", - &addr->sin_addr.s_addr, - ntohs(addr->sin_port), + + pr_info("rpcrdma: connection to %pIS:%u on %s, memreg '%s', %d credits, %d responders%s\n", + sap, rpc_get_port(sap), ia->ri_id->device->name, - ia->ri_memreg_strategy, + ia->ri_ops->ro_displayname, xprt->rx_buf.rb_max_requests, ird, ird < 4 && ird < tird / 2 ? " (low!)" : ""); } else if (connstate < 0) { - printk(KERN_INFO "rpcrdma: connection to %pI4:%u closed (%d)\n", - &addr->sin_addr.s_addr, - ntohs(addr->sin_port), - connstate); + pr_info("rpcrdma: connection to %pIS:%u closed (%d)\n", + sap, rpc_get_port(sap), connstate); } #endif @@ -621,17 +611,13 @@ rpcrdma_ia_open(struct rpcrdma_xprt *xprt, struct sockaddr *addr, int memreg) if (memreg == RPCRDMA_FRMR) { /* Requires both frmr reg and local dma lkey */ - if ((devattr->device_cap_flags & + if (((devattr->device_cap_flags & (IB_DEVICE_MEM_MGT_EXTENSIONS|IB_DEVICE_LOCAL_DMA_LKEY)) != - (IB_DEVICE_MEM_MGT_EXTENSIONS|IB_DEVICE_LOCAL_DMA_LKEY)) { + (IB_DEVICE_MEM_MGT_EXTENSIONS|IB_DEVICE_LOCAL_DMA_LKEY)) || + (devattr->max_fast_reg_page_list_len == 0)) { dprintk("RPC: %s: FRMR registration " "not supported by HCA\n", __func__); memreg = RPCRDMA_MTHCAFMR; - } else { - /* Mind the ia limit on FRMR page list depth */ - ia->ri_max_frmr_depth = min_t(unsigned int, - RPCRDMA_MAX_DATA_SEGS, - devattr->max_fast_reg_page_list_len); } } if (memreg == RPCRDMA_MTHCAFMR) { @@ -652,13 +638,16 @@ rpcrdma_ia_open(struct rpcrdma_xprt *xprt, struct sockaddr *addr, int memreg) */ switch (memreg) { case RPCRDMA_FRMR: + ia->ri_ops = &rpcrdma_frwr_memreg_ops; break; case RPCRDMA_ALLPHYSICAL: + ia->ri_ops = &rpcrdma_physical_memreg_ops; mem_priv = IB_ACCESS_LOCAL_WRITE | IB_ACCESS_REMOTE_WRITE | IB_ACCESS_REMOTE_READ; goto register_setup; case RPCRDMA_MTHCAFMR: + ia->ri_ops = &rpcrdma_fmr_memreg_ops; if (ia->ri_have_dma_lkey) break; mem_priv = IB_ACCESS_LOCAL_WRITE; @@ -678,8 +667,8 @@ rpcrdma_ia_open(struct rpcrdma_xprt *xprt, struct sockaddr *addr, int memreg) rc = -ENOMEM; goto out3; } - dprintk("RPC: %s: memory registration strategy is %d\n", - __func__, memreg); + dprintk("RPC: %s: memory registration strategy is '%s'\n", + __func__, ia->ri_ops->ro_displayname); /* Else will do memory reg/dereg for each chunk */ ia->ri_memreg_strategy = memreg; @@ -743,49 +732,11 @@ rpcrdma_ep_create(struct rpcrdma_ep *ep, struct rpcrdma_ia *ia, ep->rep_attr.event_handler = rpcrdma_qp_async_error_upcall; ep->rep_attr.qp_context = ep; - /* send_cq and recv_cq initialized below */ ep->rep_attr.srq = NULL; ep->rep_attr.cap.max_send_wr = cdata->max_requests; - switch (ia->ri_memreg_strategy) { - case RPCRDMA_FRMR: { - int depth = 7; - - /* Add room for frmr register and invalidate WRs. - * 1. FRMR reg WR for head - * 2. FRMR invalidate WR for head - * 3. N FRMR reg WRs for pagelist - * 4. N FRMR invalidate WRs for pagelist - * 5. FRMR reg WR for tail - * 6. FRMR invalidate WR for tail - * 7. The RDMA_SEND WR - */ - - /* Calculate N if the device max FRMR depth is smaller than - * RPCRDMA_MAX_DATA_SEGS. - */ - if (ia->ri_max_frmr_depth < RPCRDMA_MAX_DATA_SEGS) { - int delta = RPCRDMA_MAX_DATA_SEGS - - ia->ri_max_frmr_depth; - - do { - depth += 2; /* FRMR reg + invalidate */ - delta -= ia->ri_max_frmr_depth; - } while (delta > 0); - - } - ep->rep_attr.cap.max_send_wr *= depth; - if (ep->rep_attr.cap.max_send_wr > devattr->max_qp_wr) { - cdata->max_requests = devattr->max_qp_wr / depth; - if (!cdata->max_requests) - return -EINVAL; - ep->rep_attr.cap.max_send_wr = cdata->max_requests * - depth; - } - break; - } - default: - break; - } + rc = ia->ri_ops->ro_open(ia, ep, cdata); + if (rc) + return rc; ep->rep_attr.cap.max_recv_wr = cdata->max_requests; ep->rep_attr.cap.max_send_sge = (cdata->padding ? 4 : 2); ep->rep_attr.cap.max_recv_sge = 1; @@ -944,21 +895,9 @@ retry: rpcrdma_ep_disconnect(ep, ia); rpcrdma_flush_cqs(ep); - switch (ia->ri_memreg_strategy) { - case RPCRDMA_FRMR: - rpcrdma_reset_frmrs(ia); - break; - case RPCRDMA_MTHCAFMR: - rpcrdma_reset_fmrs(ia); - break; - case RPCRDMA_ALLPHYSICAL: - break; - default: - rc = -EIO; - goto out; - } - xprt = container_of(ia, struct rpcrdma_xprt, rx_ia); + ia->ri_ops->ro_reset(xprt); + id = rpcrdma_create_id(xprt, ia, (struct sockaddr *)&xprt->rx_data.addr); if (IS_ERR(id)) { @@ -1123,91 +1062,6 @@ out: return ERR_PTR(rc); } -static int -rpcrdma_init_fmrs(struct rpcrdma_ia *ia, struct rpcrdma_buffer *buf) -{ - int mr_access_flags = IB_ACCESS_REMOTE_WRITE | IB_ACCESS_REMOTE_READ; - struct ib_fmr_attr fmr_attr = { - .max_pages = RPCRDMA_MAX_DATA_SEGS, - .max_maps = 1, - .page_shift = PAGE_SHIFT - }; - struct rpcrdma_mw *r; - int i, rc; - - i = (buf->rb_max_requests + 1) * RPCRDMA_MAX_SEGS; - dprintk("RPC: %s: initalizing %d FMRs\n", __func__, i); - - while (i--) { - r = kzalloc(sizeof(*r), GFP_KERNEL); - if (r == NULL) - return -ENOMEM; - - r->r.fmr = ib_alloc_fmr(ia->ri_pd, mr_access_flags, &fmr_attr); - if (IS_ERR(r->r.fmr)) { - rc = PTR_ERR(r->r.fmr); - dprintk("RPC: %s: ib_alloc_fmr failed %i\n", - __func__, rc); - goto out_free; - } - - list_add(&r->mw_list, &buf->rb_mws); - list_add(&r->mw_all, &buf->rb_all); - } - return 0; - -out_free: - kfree(r); - return rc; -} - -static int -rpcrdma_init_frmrs(struct rpcrdma_ia *ia, struct rpcrdma_buffer *buf) -{ - struct rpcrdma_frmr *f; - struct rpcrdma_mw *r; - int i, rc; - - i = (buf->rb_max_requests + 1) * RPCRDMA_MAX_SEGS; - dprintk("RPC: %s: initalizing %d FRMRs\n", __func__, i); - - while (i--) { - r = kzalloc(sizeof(*r), GFP_KERNEL); - if (r == NULL) - return -ENOMEM; - f = &r->r.frmr; - - f->fr_mr = ib_alloc_fast_reg_mr(ia->ri_pd, - ia->ri_max_frmr_depth); - if (IS_ERR(f->fr_mr)) { - rc = PTR_ERR(f->fr_mr); - dprintk("RPC: %s: ib_alloc_fast_reg_mr " - "failed %i\n", __func__, rc); - goto out_free; - } - - f->fr_pgl = ib_alloc_fast_reg_page_list(ia->ri_id->device, - ia->ri_max_frmr_depth); - if (IS_ERR(f->fr_pgl)) { - rc = PTR_ERR(f->fr_pgl); - dprintk("RPC: %s: ib_alloc_fast_reg_page_list " - "failed %i\n", __func__, rc); - - ib_dereg_mr(f->fr_mr); - goto out_free; - } - - list_add(&r->mw_list, &buf->rb_mws); - list_add(&r->mw_all, &buf->rb_all); - } - - return 0; - -out_free: - kfree(r); - return rc; -} - int rpcrdma_buffer_create(struct rpcrdma_xprt *r_xprt) { @@ -1244,22 +1098,9 @@ rpcrdma_buffer_create(struct rpcrdma_xprt *r_xprt) buf->rb_recv_bufs = (struct rpcrdma_rep **) p; p = (char *) &buf->rb_recv_bufs[buf->rb_max_requests]; - INIT_LIST_HEAD(&buf->rb_mws); - INIT_LIST_HEAD(&buf->rb_all); - switch (ia->ri_memreg_strategy) { - case RPCRDMA_FRMR: - rc = rpcrdma_init_frmrs(ia, buf); - if (rc) - goto out; - break; - case RPCRDMA_MTHCAFMR: - rc = rpcrdma_init_fmrs(ia, buf); - if (rc) - goto out; - break; - default: - break; - } + rc = ia->ri_ops->ro_init(r_xprt); + if (rc) + goto out; for (i = 0; i < buf->rb_max_requests; i++) { struct rpcrdma_req *req; @@ -1311,47 +1152,6 @@ rpcrdma_destroy_req(struct rpcrdma_ia *ia, struct rpcrdma_req *req) kfree(req); } -static void -rpcrdma_destroy_fmrs(struct rpcrdma_buffer *buf) -{ - struct rpcrdma_mw *r; - int rc; - - while (!list_empty(&buf->rb_all)) { - r = list_entry(buf->rb_all.next, struct rpcrdma_mw, mw_all); - list_del(&r->mw_all); - list_del(&r->mw_list); - - rc = ib_dealloc_fmr(r->r.fmr); - if (rc) - dprintk("RPC: %s: ib_dealloc_fmr failed %i\n", - __func__, rc); - - kfree(r); - } -} - -static void -rpcrdma_destroy_frmrs(struct rpcrdma_buffer *buf) -{ - struct rpcrdma_mw *r; - int rc; - - while (!list_empty(&buf->rb_all)) { - r = list_entry(buf->rb_all.next, struct rpcrdma_mw, mw_all); - list_del(&r->mw_all); - list_del(&r->mw_list); - - rc = ib_dereg_mr(r->r.frmr.fr_mr); - if (rc) - dprintk("RPC: %s: ib_dereg_mr failed %i\n", - __func__, rc); - ib_free_fast_reg_page_list(r->r.frmr.fr_pgl); - - kfree(r); - } -} - void rpcrdma_buffer_destroy(struct rpcrdma_buffer *buf) { @@ -1372,104 +1172,11 @@ rpcrdma_buffer_destroy(struct rpcrdma_buffer *buf) rpcrdma_destroy_req(ia, buf->rb_send_bufs[i]); } - switch (ia->ri_memreg_strategy) { - case RPCRDMA_FRMR: - rpcrdma_destroy_frmrs(buf); - break; - case RPCRDMA_MTHCAFMR: - rpcrdma_destroy_fmrs(buf); - break; - default: - break; - } + ia->ri_ops->ro_destroy(buf); kfree(buf->rb_pool); } -/* After a disconnect, unmap all FMRs. - * - * This is invoked only in the transport connect worker in order - * to serialize with rpcrdma_register_fmr_external(). - */ -static void -rpcrdma_reset_fmrs(struct rpcrdma_ia *ia) -{ - struct rpcrdma_xprt *r_xprt = - container_of(ia, struct rpcrdma_xprt, rx_ia); - struct rpcrdma_buffer *buf = &r_xprt->rx_buf; - struct list_head *pos; - struct rpcrdma_mw *r; - LIST_HEAD(l); - int rc; - - list_for_each(pos, &buf->rb_all) { - r = list_entry(pos, struct rpcrdma_mw, mw_all); - - INIT_LIST_HEAD(&l); - list_add(&r->r.fmr->list, &l); - rc = ib_unmap_fmr(&l); - if (rc) - dprintk("RPC: %s: ib_unmap_fmr failed %i\n", - __func__, rc); - } -} - -/* After a disconnect, a flushed FAST_REG_MR can leave an FRMR in - * an unusable state. Find FRMRs in this state and dereg / reg - * each. FRMRs that are VALID and attached to an rpcrdma_req are - * also torn down. - * - * This gives all in-use FRMRs a fresh rkey and leaves them INVALID. - * - * This is invoked only in the transport connect worker in order - * to serialize with rpcrdma_register_frmr_external(). - */ -static void -rpcrdma_reset_frmrs(struct rpcrdma_ia *ia) -{ - struct rpcrdma_xprt *r_xprt = - container_of(ia, struct rpcrdma_xprt, rx_ia); - struct rpcrdma_buffer *buf = &r_xprt->rx_buf; - struct list_head *pos; - struct rpcrdma_mw *r; - int rc; - - list_for_each(pos, &buf->rb_all) { - r = list_entry(pos, struct rpcrdma_mw, mw_all); - - if (r->r.frmr.fr_state == FRMR_IS_INVALID) - continue; - - rc = ib_dereg_mr(r->r.frmr.fr_mr); - if (rc) - dprintk("RPC: %s: ib_dereg_mr failed %i\n", - __func__, rc); - ib_free_fast_reg_page_list(r->r.frmr.fr_pgl); - - r->r.frmr.fr_mr = ib_alloc_fast_reg_mr(ia->ri_pd, - ia->ri_max_frmr_depth); - if (IS_ERR(r->r.frmr.fr_mr)) { - rc = PTR_ERR(r->r.frmr.fr_mr); - dprintk("RPC: %s: ib_alloc_fast_reg_mr" - " failed %i\n", __func__, rc); - continue; - } - r->r.frmr.fr_pgl = ib_alloc_fast_reg_page_list( - ia->ri_id->device, - ia->ri_max_frmr_depth); - if (IS_ERR(r->r.frmr.fr_pgl)) { - rc = PTR_ERR(r->r.frmr.fr_pgl); - dprintk("RPC: %s: " - "ib_alloc_fast_reg_page_list " - "failed %i\n", __func__, rc); - - ib_dereg_mr(r->r.frmr.fr_mr); - continue; - } - r->r.frmr.fr_state = FRMR_IS_INVALID; - } -} - /* "*mw" can be NULL when rpcrdma_buffer_get_mrs() fails, leaving * some req segments uninitialized. */ @@ -1509,7 +1216,7 @@ rpcrdma_buffer_put_sendbuf(struct rpcrdma_req *req, struct rpcrdma_buffer *buf) } } -/* rpcrdma_unmap_one() was already done by rpcrdma_deregister_frmr_external(). +/* rpcrdma_unmap_one() was already done during deregistration. * Redo only the ib_post_send(). */ static void @@ -1729,6 +1436,14 @@ rpcrdma_recv_buffer_put(struct rpcrdma_rep *rep) * Wrappers for internal-use kmalloc memory registration, used by buffer code. */ +void +rpcrdma_mapping_error(struct rpcrdma_mr_seg *seg) +{ + dprintk("RPC: map_one: offset %p iova %llx len %zu\n", + seg->mr_offset, + (unsigned long long)seg->mr_dma, seg->mr_dmalen); +} + static int rpcrdma_register_internal(struct rpcrdma_ia *ia, void *va, int len, struct ib_mr **mrp, struct ib_sge *iov) @@ -1854,287 +1569,6 @@ rpcrdma_free_regbuf(struct rpcrdma_ia *ia, struct rpcrdma_regbuf *rb) } /* - * Wrappers for chunk registration, shared by read/write chunk code. - */ - -static void -rpcrdma_map_one(struct rpcrdma_ia *ia, struct rpcrdma_mr_seg *seg, int writing) -{ - seg->mr_dir = writing ? DMA_FROM_DEVICE : DMA_TO_DEVICE; - seg->mr_dmalen = seg->mr_len; - if (seg->mr_page) - seg->mr_dma = ib_dma_map_page(ia->ri_id->device, - seg->mr_page, offset_in_page(seg->mr_offset), - seg->mr_dmalen, seg->mr_dir); - else - seg->mr_dma = ib_dma_map_single(ia->ri_id->device, - seg->mr_offset, - seg->mr_dmalen, seg->mr_dir); - if (ib_dma_mapping_error(ia->ri_id->device, seg->mr_dma)) { - dprintk("RPC: %s: mr_dma %llx mr_offset %p mr_dma_len %zu\n", - __func__, - (unsigned long long)seg->mr_dma, - seg->mr_offset, seg->mr_dmalen); - } -} - -static void -rpcrdma_unmap_one(struct rpcrdma_ia *ia, struct rpcrdma_mr_seg *seg) -{ - if (seg->mr_page) - ib_dma_unmap_page(ia->ri_id->device, - seg->mr_dma, seg->mr_dmalen, seg->mr_dir); - else - ib_dma_unmap_single(ia->ri_id->device, - seg->mr_dma, seg->mr_dmalen, seg->mr_dir); -} - -static int -rpcrdma_register_frmr_external(struct rpcrdma_mr_seg *seg, - int *nsegs, int writing, struct rpcrdma_ia *ia, - struct rpcrdma_xprt *r_xprt) -{ - struct rpcrdma_mr_seg *seg1 = seg; - struct rpcrdma_mw *mw = seg1->rl_mw; - struct rpcrdma_frmr *frmr = &mw->r.frmr; - struct ib_mr *mr = frmr->fr_mr; - struct ib_send_wr fastreg_wr, *bad_wr; - u8 key; - int len, pageoff; - int i, rc; - int seg_len; - u64 pa; - int page_no; - - pageoff = offset_in_page(seg1->mr_offset); - seg1->mr_offset -= pageoff; /* start of page */ - seg1->mr_len += pageoff; - len = -pageoff; - if (*nsegs > ia->ri_max_frmr_depth) - *nsegs = ia->ri_max_frmr_depth; - for (page_no = i = 0; i < *nsegs;) { - rpcrdma_map_one(ia, seg, writing); - pa = seg->mr_dma; - for (seg_len = seg->mr_len; seg_len > 0; seg_len -= PAGE_SIZE) { - frmr->fr_pgl->page_list[page_no++] = pa; - pa += PAGE_SIZE; - } - len += seg->mr_len; - ++seg; - ++i; - /* Check for holes */ - if ((i < *nsegs && offset_in_page(seg->mr_offset)) || - offset_in_page((seg-1)->mr_offset + (seg-1)->mr_len)) - break; - } - dprintk("RPC: %s: Using frmr %p to map %d segments\n", - __func__, mw, i); - - frmr->fr_state = FRMR_IS_VALID; - - memset(&fastreg_wr, 0, sizeof(fastreg_wr)); - fastreg_wr.wr_id = (unsigned long)(void *)mw; - fastreg_wr.opcode = IB_WR_FAST_REG_MR; - fastreg_wr.wr.fast_reg.iova_start = seg1->mr_dma; - fastreg_wr.wr.fast_reg.page_list = frmr->fr_pgl; - fastreg_wr.wr.fast_reg.page_list_len = page_no; - fastreg_wr.wr.fast_reg.page_shift = PAGE_SHIFT; - fastreg_wr.wr.fast_reg.length = page_no << PAGE_SHIFT; - if (fastreg_wr.wr.fast_reg.length < len) { - rc = -EIO; - goto out_err; - } - - /* Bump the key */ - key = (u8)(mr->rkey & 0x000000FF); - ib_update_fast_reg_key(mr, ++key); - - fastreg_wr.wr.fast_reg.access_flags = (writing ? - IB_ACCESS_REMOTE_WRITE | IB_ACCESS_LOCAL_WRITE : - IB_ACCESS_REMOTE_READ); - fastreg_wr.wr.fast_reg.rkey = mr->rkey; - DECR_CQCOUNT(&r_xprt->rx_ep); - - rc = ib_post_send(ia->ri_id->qp, &fastreg_wr, &bad_wr); - if (rc) { - dprintk("RPC: %s: failed ib_post_send for register," - " status %i\n", __func__, rc); - ib_update_fast_reg_key(mr, --key); - goto out_err; - } else { - seg1->mr_rkey = mr->rkey; - seg1->mr_base = seg1->mr_dma + pageoff; - seg1->mr_nsegs = i; - seg1->mr_len = len; - } - *nsegs = i; - return 0; -out_err: - frmr->fr_state = FRMR_IS_INVALID; - while (i--) - rpcrdma_unmap_one(ia, --seg); - return rc; -} - -static int -rpcrdma_deregister_frmr_external(struct rpcrdma_mr_seg *seg, - struct rpcrdma_ia *ia, struct rpcrdma_xprt *r_xprt) -{ - struct rpcrdma_mr_seg *seg1 = seg; - struct ib_send_wr invalidate_wr, *bad_wr; - int rc; - - seg1->rl_mw->r.frmr.fr_state = FRMR_IS_INVALID; - - memset(&invalidate_wr, 0, sizeof invalidate_wr); - invalidate_wr.wr_id = (unsigned long)(void *)seg1->rl_mw; - invalidate_wr.opcode = IB_WR_LOCAL_INV; - invalidate_wr.ex.invalidate_rkey = seg1->rl_mw->r.frmr.fr_mr->rkey; - DECR_CQCOUNT(&r_xprt->rx_ep); - - read_lock(&ia->ri_qplock); - while (seg1->mr_nsegs--) - rpcrdma_unmap_one(ia, seg++); - rc = ib_post_send(ia->ri_id->qp, &invalidate_wr, &bad_wr); - read_unlock(&ia->ri_qplock); - if (rc) { - /* Force rpcrdma_buffer_get() to retry */ - seg1->rl_mw->r.frmr.fr_state = FRMR_IS_STALE; - dprintk("RPC: %s: failed ib_post_send for invalidate," - " status %i\n", __func__, rc); - } - return rc; -} - -static int -rpcrdma_register_fmr_external(struct rpcrdma_mr_seg *seg, - int *nsegs, int writing, struct rpcrdma_ia *ia) -{ - struct rpcrdma_mr_seg *seg1 = seg; - u64 physaddrs[RPCRDMA_MAX_DATA_SEGS]; - int len, pageoff, i, rc; - - pageoff = offset_in_page(seg1->mr_offset); - seg1->mr_offset -= pageoff; /* start of page */ - seg1->mr_len += pageoff; - len = -pageoff; - if (*nsegs > RPCRDMA_MAX_DATA_SEGS) - *nsegs = RPCRDMA_MAX_DATA_SEGS; - for (i = 0; i < *nsegs;) { - rpcrdma_map_one(ia, seg, writing); - physaddrs[i] = seg->mr_dma; - len += seg->mr_len; - ++seg; - ++i; - /* Check for holes */ - if ((i < *nsegs && offset_in_page(seg->mr_offset)) || - offset_in_page((seg-1)->mr_offset + (seg-1)->mr_len)) - break; - } - rc = ib_map_phys_fmr(seg1->rl_mw->r.fmr, physaddrs, i, seg1->mr_dma); - if (rc) { - dprintk("RPC: %s: failed ib_map_phys_fmr " - "%u@0x%llx+%i (%d)... status %i\n", __func__, - len, (unsigned long long)seg1->mr_dma, - pageoff, i, rc); - while (i--) - rpcrdma_unmap_one(ia, --seg); - } else { - seg1->mr_rkey = seg1->rl_mw->r.fmr->rkey; - seg1->mr_base = seg1->mr_dma + pageoff; - seg1->mr_nsegs = i; - seg1->mr_len = len; - } - *nsegs = i; - return rc; -} - -static int -rpcrdma_deregister_fmr_external(struct rpcrdma_mr_seg *seg, - struct rpcrdma_ia *ia) -{ - struct rpcrdma_mr_seg *seg1 = seg; - LIST_HEAD(l); - int rc; - - list_add(&seg1->rl_mw->r.fmr->list, &l); - rc = ib_unmap_fmr(&l); - read_lock(&ia->ri_qplock); - while (seg1->mr_nsegs--) - rpcrdma_unmap_one(ia, seg++); - read_unlock(&ia->ri_qplock); - if (rc) - dprintk("RPC: %s: failed ib_unmap_fmr," - " status %i\n", __func__, rc); - return rc; -} - -int -rpcrdma_register_external(struct rpcrdma_mr_seg *seg, - int nsegs, int writing, struct rpcrdma_xprt *r_xprt) -{ - struct rpcrdma_ia *ia = &r_xprt->rx_ia; - int rc = 0; - - switch (ia->ri_memreg_strategy) { - - case RPCRDMA_ALLPHYSICAL: - rpcrdma_map_one(ia, seg, writing); - seg->mr_rkey = ia->ri_bind_mem->rkey; - seg->mr_base = seg->mr_dma; - seg->mr_nsegs = 1; - nsegs = 1; - break; - - /* Registration using frmr registration */ - case RPCRDMA_FRMR: - rc = rpcrdma_register_frmr_external(seg, &nsegs, writing, ia, r_xprt); - break; - - /* Registration using fmr memory registration */ - case RPCRDMA_MTHCAFMR: - rc = rpcrdma_register_fmr_external(seg, &nsegs, writing, ia); - break; - - default: - return -EIO; - } - if (rc) - return rc; - - return nsegs; -} - -int -rpcrdma_deregister_external(struct rpcrdma_mr_seg *seg, - struct rpcrdma_xprt *r_xprt) -{ - struct rpcrdma_ia *ia = &r_xprt->rx_ia; - int nsegs = seg->mr_nsegs, rc; - - switch (ia->ri_memreg_strategy) { - - case RPCRDMA_ALLPHYSICAL: - read_lock(&ia->ri_qplock); - rpcrdma_unmap_one(ia, seg); - read_unlock(&ia->ri_qplock); - break; - - case RPCRDMA_FRMR: - rc = rpcrdma_deregister_frmr_external(seg, ia, r_xprt); - break; - - case RPCRDMA_MTHCAFMR: - rc = rpcrdma_deregister_fmr_external(seg, ia); - break; - - default: - break; - } - return nsegs; -} - -/* * Prepost any receive buffer, then post send. * * Receive buffer is donated to hardware, reclaimed upon recv completion. @@ -2156,7 +1590,7 @@ rpcrdma_ep_post(struct rpcrdma_ia *ia, } send_wr.next = NULL; - send_wr.wr_id = 0ULL; /* no send cookie */ + send_wr.wr_id = RPCRDMA_IGNORE_COMPLETION; send_wr.sg_list = req->rl_send_iov; send_wr.num_sge = req->rl_niovs; send_wr.opcode = IB_WR_SEND; @@ -2215,43 +1649,24 @@ rpcrdma_ep_post_recv(struct rpcrdma_ia *ia, return rc; } -/* Physical mapping means one Read/Write list entry per-page. - * All list entries must fit within an inline buffer - * - * NB: The server must return a Write list for NFS READ, - * which has the same constraint. Factor in the inline - * rsize as well. +/* How many chunk list items fit within our inline buffers? */ -static size_t -rpcrdma_physical_max_payload(struct rpcrdma_xprt *r_xprt) +unsigned int +rpcrdma_max_segments(struct rpcrdma_xprt *r_xprt) { struct rpcrdma_create_data_internal *cdata = &r_xprt->rx_data; - unsigned int inline_size, pages; + int bytes, segments; - inline_size = min_t(unsigned int, - cdata->inline_wsize, cdata->inline_rsize); - inline_size -= RPCRDMA_HDRLEN_MIN; - pages = inline_size / sizeof(struct rpcrdma_segment); - return pages << PAGE_SHIFT; -} - -static size_t -rpcrdma_mr_max_payload(struct rpcrdma_xprt *r_xprt) -{ - return RPCRDMA_MAX_DATA_SEGS << PAGE_SHIFT; -} - -size_t -rpcrdma_max_payload(struct rpcrdma_xprt *r_xprt) -{ - size_t result; - - switch (r_xprt->rx_ia.ri_memreg_strategy) { - case RPCRDMA_ALLPHYSICAL: - result = rpcrdma_physical_max_payload(r_xprt); - break; - default: - result = rpcrdma_mr_max_payload(r_xprt); + bytes = min_t(unsigned int, cdata->inline_wsize, cdata->inline_rsize); + bytes -= RPCRDMA_HDRLEN_MIN; + if (bytes < sizeof(struct rpcrdma_segment) * 2) { + pr_warn("RPC: %s: inline threshold too small\n", + __func__); + return 0; } - return result; + + segments = 1 << (fls(bytes / sizeof(struct rpcrdma_segment)) - 1); + dprintk("RPC: %s: max chunk list size = %d segments\n", + __func__, segments); + return segments; } diff --git a/net/sunrpc/xprtrdma/xprt_rdma.h b/net/sunrpc/xprtrdma/xprt_rdma.h index 0a16fb6f0885..78e0b8beaa36 100644 --- a/net/sunrpc/xprtrdma/xprt_rdma.h +++ b/net/sunrpc/xprtrdma/xprt_rdma.h @@ -60,6 +60,7 @@ * Interface Adapter -- one per transport instance */ struct rpcrdma_ia { + const struct rpcrdma_memreg_ops *ri_ops; rwlock_t ri_qplock; struct rdma_cm_id *ri_id; struct ib_pd *ri_pd; @@ -105,6 +106,10 @@ struct rpcrdma_ep { #define INIT_CQCOUNT(ep) atomic_set(&(ep)->rep_cqcount, (ep)->rep_cqinit) #define DECR_CQCOUNT(ep) atomic_sub_return(1, &(ep)->rep_cqcount) +/* Force completion handler to ignore the signal + */ +#define RPCRDMA_IGNORE_COMPLETION (0ULL) + /* Registered buffer -- registered kmalloc'd memory for RDMA SEND/RECV * * The below structure appears at the front of a large region of kmalloc'd @@ -143,14 +148,6 @@ rdmab_to_msg(struct rpcrdma_regbuf *rb) return (struct rpcrdma_msg *)rb->rg_base; } -enum rpcrdma_chunktype { - rpcrdma_noch = 0, - rpcrdma_readch, - rpcrdma_areadch, - rpcrdma_writech, - rpcrdma_replych -}; - /* * struct rpcrdma_rep -- this structure encapsulates state required to recv * and complete a reply, asychronously. It needs several pieces of @@ -213,6 +210,7 @@ struct rpcrdma_mw { struct ib_fmr *fmr; struct rpcrdma_frmr frmr; } r; + void (*mw_sendcompletion)(struct ib_wc *); struct list_head mw_list; struct list_head mw_all; }; @@ -258,7 +256,6 @@ struct rpcrdma_req { unsigned int rl_niovs; /* 0, 2 or 4 */ unsigned int rl_nchunks; /* non-zero if chunks */ unsigned int rl_connect_cookie; /* retry detection */ - enum rpcrdma_chunktype rl_rtype, rl_wtype; struct rpcrdma_buffer *rl_buffer; /* home base for this structure */ struct rpcrdma_rep *rl_reply;/* holder for reply buffer */ struct ib_sge rl_send_iov[4]; /* for active requests */ @@ -340,6 +337,29 @@ struct rpcrdma_stats { }; /* + * Per-registration mode operations + */ +struct rpcrdma_xprt; +struct rpcrdma_memreg_ops { + int (*ro_map)(struct rpcrdma_xprt *, + struct rpcrdma_mr_seg *, int, bool); + int (*ro_unmap)(struct rpcrdma_xprt *, + struct rpcrdma_mr_seg *); + int (*ro_open)(struct rpcrdma_ia *, + struct rpcrdma_ep *, + struct rpcrdma_create_data_internal *); + size_t (*ro_maxpages)(struct rpcrdma_xprt *); + int (*ro_init)(struct rpcrdma_xprt *); + void (*ro_reset)(struct rpcrdma_xprt *); + void (*ro_destroy)(struct rpcrdma_buffer *); + const char *ro_displayname; +}; + +extern const struct rpcrdma_memreg_ops rpcrdma_fmr_memreg_ops; +extern const struct rpcrdma_memreg_ops rpcrdma_frwr_memreg_ops; +extern const struct rpcrdma_memreg_ops rpcrdma_physical_memreg_ops; + +/* * RPCRDMA transport -- encapsulates the structures above for * integration with RPC. * @@ -398,16 +418,56 @@ void rpcrdma_buffer_put(struct rpcrdma_req *); void rpcrdma_recv_buffer_get(struct rpcrdma_req *); void rpcrdma_recv_buffer_put(struct rpcrdma_rep *); -int rpcrdma_register_external(struct rpcrdma_mr_seg *, - int, int, struct rpcrdma_xprt *); -int rpcrdma_deregister_external(struct rpcrdma_mr_seg *, - struct rpcrdma_xprt *); - struct rpcrdma_regbuf *rpcrdma_alloc_regbuf(struct rpcrdma_ia *, size_t, gfp_t); void rpcrdma_free_regbuf(struct rpcrdma_ia *, struct rpcrdma_regbuf *); +unsigned int rpcrdma_max_segments(struct rpcrdma_xprt *); + +/* + * Wrappers for chunk registration, shared by read/write chunk code. + */ + +void rpcrdma_mapping_error(struct rpcrdma_mr_seg *); + +static inline enum dma_data_direction +rpcrdma_data_dir(bool writing) +{ + return writing ? DMA_FROM_DEVICE : DMA_TO_DEVICE; +} + +static inline void +rpcrdma_map_one(struct ib_device *device, struct rpcrdma_mr_seg *seg, + enum dma_data_direction direction) +{ + seg->mr_dir = direction; + seg->mr_dmalen = seg->mr_len; + + if (seg->mr_page) + seg->mr_dma = ib_dma_map_page(device, + seg->mr_page, offset_in_page(seg->mr_offset), + seg->mr_dmalen, seg->mr_dir); + else + seg->mr_dma = ib_dma_map_single(device, + seg->mr_offset, + seg->mr_dmalen, seg->mr_dir); + + if (ib_dma_mapping_error(device, seg->mr_dma)) + rpcrdma_mapping_error(seg); +} + +static inline void +rpcrdma_unmap_one(struct ib_device *device, struct rpcrdma_mr_seg *seg) +{ + if (seg->mr_page) + ib_dma_unmap_page(device, + seg->mr_dma, seg->mr_dmalen, seg->mr_dir); + else + ib_dma_unmap_single(device, + seg->mr_dma, seg->mr_dmalen, seg->mr_dir); +} + /* * RPC/RDMA connection management calls - xprtrdma/rpc_rdma.c */ @@ -418,9 +478,7 @@ void rpcrdma_reply_handler(struct rpcrdma_rep *); /* * RPC/RDMA protocol calls - xprtrdma/rpc_rdma.c */ -ssize_t rpcrdma_marshal_chunks(struct rpc_rqst *, ssize_t); int rpcrdma_marshal_req(struct rpc_rqst *); -size_t rpcrdma_max_payload(struct rpcrdma_xprt *); /* Temporary NFS request map cache. Created in svc_rdma.c */ extern struct kmem_cache *svc_rdma_map_cachep; diff --git a/net/switchdev/switchdev.c b/net/switchdev/switchdev.c index 8c1e558db118..46568b85c333 100644 --- a/net/switchdev/switchdev.c +++ b/net/switchdev/switchdev.c @@ -1,6 +1,7 @@ /* * net/switchdev/switchdev.c - Switch device API * Copyright (c) 2014 Jiri Pirko <jiri@resnulli.us> + * Copyright (c) 2014-2015 Scott Feldman <sfeldma@gmail.com> * * 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 @@ -14,6 +15,7 @@ #include <linux/mutex.h> #include <linux/notifier.h> #include <linux/netdevice.h> +#include <net/ip_fib.h> #include <net/switchdev.h> /** @@ -26,13 +28,13 @@ int netdev_switch_parent_id_get(struct net_device *dev, struct netdev_phys_item_id *psid) { - const struct net_device_ops *ops = dev->netdev_ops; + const struct swdev_ops *ops = dev->swdev_ops; - if (!ops->ndo_switch_parent_id_get) + if (!ops || !ops->swdev_parent_id_get) return -EOPNOTSUPP; - return ops->ndo_switch_parent_id_get(dev, psid); + return ops->swdev_parent_id_get(dev, psid); } -EXPORT_SYMBOL(netdev_switch_parent_id_get); +EXPORT_SYMBOL_GPL(netdev_switch_parent_id_get); /** * netdev_switch_port_stp_update - Notify switch device port of STP @@ -44,20 +46,29 @@ EXPORT_SYMBOL(netdev_switch_parent_id_get); */ int netdev_switch_port_stp_update(struct net_device *dev, u8 state) { - const struct net_device_ops *ops = dev->netdev_ops; + const struct swdev_ops *ops = dev->swdev_ops; + struct net_device *lower_dev; + struct list_head *iter; + int err = -EOPNOTSUPP; - if (!ops->ndo_switch_port_stp_update) - return -EOPNOTSUPP; - WARN_ON(!ops->ndo_switch_parent_id_get); - return ops->ndo_switch_port_stp_update(dev, state); + if (ops && ops->swdev_port_stp_update) + return ops->swdev_port_stp_update(dev, state); + + netdev_for_each_lower_dev(dev, lower_dev, iter) { + err = netdev_switch_port_stp_update(lower_dev, state); + if (err && err != -EOPNOTSUPP) + return err; + } + + return err; } -EXPORT_SYMBOL(netdev_switch_port_stp_update); +EXPORT_SYMBOL_GPL(netdev_switch_port_stp_update); static DEFINE_MUTEX(netdev_switch_mutex); static RAW_NOTIFIER_HEAD(netdev_switch_notif_chain); /** - * register_netdev_switch_notifier - Register nofifier + * register_netdev_switch_notifier - Register notifier * @nb: notifier_block * * Register switch device notifier. This should be used by code @@ -73,10 +84,10 @@ int register_netdev_switch_notifier(struct notifier_block *nb) mutex_unlock(&netdev_switch_mutex); return err; } -EXPORT_SYMBOL(register_netdev_switch_notifier); +EXPORT_SYMBOL_GPL(register_netdev_switch_notifier); /** - * unregister_netdev_switch_notifier - Unregister nofifier + * unregister_netdev_switch_notifier - Unregister notifier * @nb: notifier_block * * Unregister switch device notifier. @@ -91,10 +102,10 @@ int unregister_netdev_switch_notifier(struct notifier_block *nb) mutex_unlock(&netdev_switch_mutex); return err; } -EXPORT_SYMBOL(unregister_netdev_switch_notifier); +EXPORT_SYMBOL_GPL(unregister_netdev_switch_notifier); /** - * call_netdev_switch_notifiers - Call nofifiers + * call_netdev_switch_notifiers - Call notifiers * @val: value passed unmodified to notifier function * @dev: port device * @info: notifier information data @@ -114,7 +125,7 @@ int call_netdev_switch_notifiers(unsigned long val, struct net_device *dev, mutex_unlock(&netdev_switch_mutex); return err; } -EXPORT_SYMBOL(call_netdev_switch_notifiers); +EXPORT_SYMBOL_GPL(call_netdev_switch_notifiers); /** * netdev_switch_port_bridge_setlink - Notify switch device port of bridge @@ -139,7 +150,7 @@ int netdev_switch_port_bridge_setlink(struct net_device *dev, return ops->ndo_bridge_setlink(dev, nlh, flags); } -EXPORT_SYMBOL(netdev_switch_port_bridge_setlink); +EXPORT_SYMBOL_GPL(netdev_switch_port_bridge_setlink); /** * netdev_switch_port_bridge_dellink - Notify switch device port of bridge @@ -164,7 +175,7 @@ int netdev_switch_port_bridge_dellink(struct net_device *dev, return ops->ndo_bridge_dellink(dev, nlh, flags); } -EXPORT_SYMBOL(netdev_switch_port_bridge_dellink); +EXPORT_SYMBOL_GPL(netdev_switch_port_bridge_dellink); /** * ndo_dflt_netdev_switch_port_bridge_setlink - default ndo bridge setlink @@ -194,7 +205,7 @@ int ndo_dflt_netdev_switch_port_bridge_setlink(struct net_device *dev, return ret; } -EXPORT_SYMBOL(ndo_dflt_netdev_switch_port_bridge_setlink); +EXPORT_SYMBOL_GPL(ndo_dflt_netdev_switch_port_bridge_setlink); /** * ndo_dflt_netdev_switch_port_bridge_dellink - default ndo bridge dellink @@ -224,4 +235,170 @@ int ndo_dflt_netdev_switch_port_bridge_dellink(struct net_device *dev, return ret; } -EXPORT_SYMBOL(ndo_dflt_netdev_switch_port_bridge_dellink); +EXPORT_SYMBOL_GPL(ndo_dflt_netdev_switch_port_bridge_dellink); + +static struct net_device *netdev_switch_get_lowest_dev(struct net_device *dev) +{ + const struct swdev_ops *ops = dev->swdev_ops; + struct net_device *lower_dev; + struct net_device *port_dev; + struct list_head *iter; + + /* Recusively search down until we find a sw port dev. + * (A sw port dev supports swdev_parent_id_get). + */ + + if (dev->features & NETIF_F_HW_SWITCH_OFFLOAD && + ops && ops->swdev_parent_id_get) + return dev; + + netdev_for_each_lower_dev(dev, lower_dev, iter) { + port_dev = netdev_switch_get_lowest_dev(lower_dev); + if (port_dev) + return port_dev; + } + + return NULL; +} + +static struct net_device *netdev_switch_get_dev_by_nhs(struct fib_info *fi) +{ + struct netdev_phys_item_id psid; + struct netdev_phys_item_id prev_psid; + struct net_device *dev = NULL; + int nhsel; + + /* For this route, all nexthop devs must be on the same switch. */ + + for (nhsel = 0; nhsel < fi->fib_nhs; nhsel++) { + const struct fib_nh *nh = &fi->fib_nh[nhsel]; + + if (!nh->nh_dev) + return NULL; + + dev = netdev_switch_get_lowest_dev(nh->nh_dev); + if (!dev) + return NULL; + + if (netdev_switch_parent_id_get(dev, &psid)) + return NULL; + + if (nhsel > 0) { + if (prev_psid.id_len != psid.id_len) + return NULL; + if (memcmp(prev_psid.id, psid.id, psid.id_len)) + return NULL; + } + + prev_psid = psid; + } + + return dev; +} + +/** + * netdev_switch_fib_ipv4_add - Add IPv4 route entry to switch + * + * @dst: route's IPv4 destination address + * @dst_len: destination address length (prefix length) + * @fi: route FIB info structure + * @tos: route TOS + * @type: route type + * @nlflags: netlink flags passed in (NLM_F_*) + * @tb_id: route table ID + * + * Add IPv4 route entry to switch device. + */ +int netdev_switch_fib_ipv4_add(u32 dst, int dst_len, struct fib_info *fi, + u8 tos, u8 type, u32 nlflags, u32 tb_id) +{ + struct net_device *dev; + const struct swdev_ops *ops; + int err = 0; + + /* Don't offload route if using custom ip rules or if + * IPv4 FIB offloading has been disabled completely. + */ + +#ifdef CONFIG_IP_MULTIPLE_TABLES + if (fi->fib_net->ipv4.fib_has_custom_rules) + return 0; +#endif + + if (fi->fib_net->ipv4.fib_offload_disabled) + return 0; + + dev = netdev_switch_get_dev_by_nhs(fi); + if (!dev) + return 0; + ops = dev->swdev_ops; + + if (ops->swdev_fib_ipv4_add) { + err = ops->swdev_fib_ipv4_add(dev, htonl(dst), dst_len, + fi, tos, type, nlflags, + tb_id); + if (!err) + fi->fib_flags |= RTNH_F_EXTERNAL; + } + + return err; +} +EXPORT_SYMBOL_GPL(netdev_switch_fib_ipv4_add); + +/** + * netdev_switch_fib_ipv4_del - Delete IPv4 route entry from switch + * + * @dst: route's IPv4 destination address + * @dst_len: destination address length (prefix length) + * @fi: route FIB info structure + * @tos: route TOS + * @type: route type + * @tb_id: route table ID + * + * Delete IPv4 route entry from switch device. + */ +int netdev_switch_fib_ipv4_del(u32 dst, int dst_len, struct fib_info *fi, + u8 tos, u8 type, u32 tb_id) +{ + struct net_device *dev; + const struct swdev_ops *ops; + int err = 0; + + if (!(fi->fib_flags & RTNH_F_EXTERNAL)) + return 0; + + dev = netdev_switch_get_dev_by_nhs(fi); + if (!dev) + return 0; + ops = dev->swdev_ops; + + if (ops->swdev_fib_ipv4_del) { + err = ops->swdev_fib_ipv4_del(dev, htonl(dst), dst_len, + fi, tos, type, tb_id); + if (!err) + fi->fib_flags &= ~RTNH_F_EXTERNAL; + } + + return err; +} +EXPORT_SYMBOL_GPL(netdev_switch_fib_ipv4_del); + +/** + * netdev_switch_fib_ipv4_abort - Abort an IPv4 FIB operation + * + * @fi: route FIB info structure + */ +void netdev_switch_fib_ipv4_abort(struct fib_info *fi) +{ + /* There was a problem installing this route to the offload + * device. For now, until we come up with more refined + * policy handling, abruptly end IPv4 fib offloading for + * for entire net by flushing offload device(s) of all + * IPv4 routes, and mark IPv4 fib offloading broken from + * this point forward. + */ + + fib_flush_external(fi->fib_net); + fi->fib_net->ipv4.fib_offload_disabled = true; +} +EXPORT_SYMBOL_GPL(netdev_switch_fib_ipv4_abort); diff --git a/net/tipc/Kconfig b/net/tipc/Kconfig index 91c8a8e031db..c25a3a149dc4 100644 --- a/net/tipc/Kconfig +++ b/net/tipc/Kconfig @@ -26,3 +26,11 @@ config TIPC_MEDIA_IB help Saying Y here will enable support for running TIPC on IP-over-InfiniBand devices. +config TIPC_MEDIA_UDP + bool "IP/UDP media type support" + depends on TIPC + select NET_UDP_TUNNEL + help + Saying Y here will enable support for running TIPC over IP/UDP + bool + default y diff --git a/net/tipc/Makefile b/net/tipc/Makefile index 599b1a540d2b..57e460be4692 100644 --- a/net/tipc/Makefile +++ b/net/tipc/Makefile @@ -10,5 +10,6 @@ tipc-y += addr.o bcast.o bearer.o \ netlink.o netlink_compat.o node.o socket.o eth_media.o \ server.o socket.o +tipc-$(CONFIG_TIPC_MEDIA_UDP) += udp_media.o tipc-$(CONFIG_TIPC_MEDIA_IB) += ib_media.o tipc-$(CONFIG_SYSCTL) += sysctl.o diff --git a/net/tipc/addr.c b/net/tipc/addr.c index 48fd3b5a73fb..ba7daa864d44 100644 --- a/net/tipc/addr.c +++ b/net/tipc/addr.c @@ -38,6 +38,13 @@ #include "addr.h" #include "core.h" +u32 tipc_own_addr(struct net *net) +{ + struct tipc_net *tn = net_generic(net, tipc_net_id); + + return tn->own_addr; +} + /** * in_own_cluster - test for cluster inclusion; <0.0.0> always matches */ diff --git a/net/tipc/addr.h b/net/tipc/addr.h index c700c2d28e09..7ba6d5c8ae40 100644 --- a/net/tipc/addr.h +++ b/net/tipc/addr.h @@ -55,6 +55,7 @@ static inline u32 tipc_cluster_mask(u32 addr) return addr & TIPC_CLUSTER_MASK; } +u32 tipc_own_addr(struct net *net); int in_own_cluster(struct net *net, u32 addr); int in_own_cluster_exact(struct net *net, u32 addr); int in_own_node(struct net *net, u32 addr); diff --git a/net/tipc/bcast.c b/net/tipc/bcast.c index 3e41704832de..c5cbdcb1f0b5 100644 --- a/net/tipc/bcast.c +++ b/net/tipc/bcast.c @@ -62,21 +62,8 @@ static void tipc_bclink_lock(struct net *net) static void tipc_bclink_unlock(struct net *net) { struct tipc_net *tn = net_generic(net, tipc_net_id); - struct tipc_node *node = NULL; - if (likely(!tn->bclink->flags)) { - spin_unlock_bh(&tn->bclink->lock); - return; - } - - if (tn->bclink->flags & TIPC_BCLINK_RESET) { - tn->bclink->flags &= ~TIPC_BCLINK_RESET; - node = tipc_bclink_retransmit_to(net); - } spin_unlock_bh(&tn->bclink->lock); - - if (node) - tipc_link_reset_all(node); } void tipc_bclink_input(struct net *net) @@ -91,13 +78,6 @@ uint tipc_bclink_get_mtu(void) return MAX_PKT_DEFAULT_MCAST; } -void tipc_bclink_set_flags(struct net *net, unsigned int flags) -{ - struct tipc_net *tn = net_generic(net, tipc_net_id); - - tn->bclink->flags |= flags; -} - static u32 bcbuf_acks(struct sk_buff *buf) { return (u32)(unsigned long)TIPC_SKB_CB(buf)->handle; @@ -135,9 +115,10 @@ static void bclink_set_last_sent(struct net *net) { struct tipc_net *tn = net_generic(net, tipc_net_id); struct tipc_link *bcl = tn->bcl; + struct sk_buff *skb = skb_peek(&bcl->backlogq); - if (bcl->next_out) - bcl->fsm_msg_cnt = mod(buf_seqno(bcl->next_out) - 1); + if (skb) + bcl->fsm_msg_cnt = mod(buf_seqno(skb) - 1); else bcl->fsm_msg_cnt = mod(bcl->next_out_no - 1); } @@ -155,7 +136,6 @@ static void bclink_update_last_sent(struct tipc_node *node, u32 seqno) seqno : node->bclink.last_sent; } - /** * tipc_bclink_retransmit_to - get most recent node to request retransmission * @@ -180,7 +160,7 @@ static void bclink_retransmit_pkt(struct tipc_net *tn, u32 after, u32 to) struct sk_buff *skb; struct tipc_link *bcl = tn->bcl; - skb_queue_walk(&bcl->outqueue, skb) { + skb_queue_walk(&bcl->transmq, skb) { if (more(buf_seqno(skb), after)) { tipc_link_retransmit(bcl, skb, mod(to - after)); break; @@ -210,14 +190,17 @@ void tipc_bclink_wakeup_users(struct net *net) void tipc_bclink_acknowledge(struct tipc_node *n_ptr, u32 acked) { struct sk_buff *skb, *tmp; - struct sk_buff *next; unsigned int released = 0; struct net *net = n_ptr->net; struct tipc_net *tn = net_generic(net, tipc_net_id); + if (unlikely(!n_ptr->bclink.recv_permitted)) + return; + tipc_bclink_lock(net); + /* Bail out if tx queue is empty (no clean up is required) */ - skb = skb_peek(&tn->bcl->outqueue); + skb = skb_peek(&tn->bcl->transmq); if (!skb) goto exit; @@ -244,27 +227,19 @@ void tipc_bclink_acknowledge(struct tipc_node *n_ptr, u32 acked) } /* Skip over packets that node has previously acknowledged */ - skb_queue_walk(&tn->bcl->outqueue, skb) { + skb_queue_walk(&tn->bcl->transmq, skb) { if (more(buf_seqno(skb), n_ptr->bclink.acked)) break; } /* Update packets that node is now acknowledging */ - skb_queue_walk_from_safe(&tn->bcl->outqueue, skb, tmp) { + skb_queue_walk_from_safe(&tn->bcl->transmq, skb, tmp) { if (more(buf_seqno(skb), acked)) break; - - next = tipc_skb_queue_next(&tn->bcl->outqueue, skb); - if (skb != tn->bcl->next_out) { - bcbuf_decr_acks(skb); - } else { - bcbuf_set_acks(skb, 0); - tn->bcl->next_out = next; - bclink_set_last_sent(net); - } - + bcbuf_decr_acks(skb); + bclink_set_last_sent(net); if (bcbuf_acks(skb) == 0) { - __skb_unlink(skb, &tn->bcl->outqueue); + __skb_unlink(skb, &tn->bcl->transmq); kfree_skb(skb); released = 1; } @@ -272,7 +247,7 @@ void tipc_bclink_acknowledge(struct tipc_node *n_ptr, u32 acked) n_ptr->bclink.acked = acked; /* Try resolving broadcast link congestion, if necessary */ - if (unlikely(tn->bcl->next_out)) { + if (unlikely(skb_peek(&tn->bcl->backlogq))) { tipc_link_push_packets(tn->bcl); bclink_set_last_sent(net); } @@ -319,7 +294,7 @@ void tipc_bclink_update_link_state(struct tipc_node *n_ptr, buf = tipc_buf_acquire(INT_H_SIZE); if (buf) { struct tipc_msg *msg = buf_msg(buf); - struct sk_buff *skb = skb_peek(&n_ptr->bclink.deferred_queue); + struct sk_buff *skb = skb_peek(&n_ptr->bclink.deferdq); u32 to = skb ? buf_seqno(skb) - 1 : n_ptr->bclink.last_sent; tipc_msg_init(tn->own_addr, msg, BCAST_PROTOCOL, STATE_MSG, @@ -354,13 +329,12 @@ static void bclink_peek_nack(struct net *net, struct tipc_msg *msg) return; tipc_node_lock(n_ptr); - if (n_ptr->bclink.recv_permitted && (n_ptr->bclink.last_in != n_ptr->bclink.last_sent) && (n_ptr->bclink.last_in == msg_bcgap_after(msg))) n_ptr->bclink.oos_state = 2; - tipc_node_unlock(n_ptr); + tipc_node_put(n_ptr); } /* tipc_bclink_xmit - deliver buffer chain to all nodes in cluster @@ -387,14 +361,13 @@ int tipc_bclink_xmit(struct net *net, struct sk_buff_head *list) __skb_queue_purge(list); return -EHOSTUNREACH; } - /* Broadcast to all nodes */ if (likely(bclink)) { tipc_bclink_lock(net); if (likely(bclink->bcast_nodes.count)) { rc = __tipc_link_xmit(net, bcl, list); if (likely(!rc)) { - u32 len = skb_queue_len(&bcl->outqueue); + u32 len = skb_queue_len(&bcl->transmq); bclink_set_last_sent(net); bcl->stats.queue_sz_counts++; @@ -440,7 +413,7 @@ static void bclink_accept_pkt(struct tipc_node *node, u32 seqno) */ if (((seqno - tn->own_addr) % TIPC_MIN_LINK_WIN) == 0) { tipc_link_proto_xmit(node->active_links[node->addr & 1], - STATE_MSG, 0, 0, 0, 0, 0); + STATE_MSG, 0, 0, 0, 0); tn->bcl->stats.sent_acks++; } } @@ -481,17 +454,18 @@ void tipc_bclink_rcv(struct net *net, struct sk_buff *buf) goto unlock; if (msg_destnode(msg) == tn->own_addr) { tipc_bclink_acknowledge(node, msg_bcast_ack(msg)); - tipc_node_unlock(node); tipc_bclink_lock(net); bcl->stats.recv_nacks++; tn->bclink->retransmit_to = node; bclink_retransmit_pkt(tn, msg_bcgap_after(msg), msg_bcgap_to(msg)); tipc_bclink_unlock(net); + tipc_node_unlock(node); } else { tipc_node_unlock(node); bclink_peek_nack(net, msg); } + tipc_node_put(node); goto exit; } @@ -528,11 +502,13 @@ receive: tipc_bclink_unlock(net); tipc_node_unlock(node); } else if (msg_user(msg) == MSG_FRAGMENTER) { - tipc_buf_append(&node->bclink.reasm_buf, &buf); - if (unlikely(!buf && !node->bclink.reasm_buf)) - goto unlock; tipc_bclink_lock(net); bclink_accept_pkt(node, seqno); + tipc_buf_append(&node->bclink.reasm_buf, &buf); + if (unlikely(!buf && !node->bclink.reasm_buf)) { + tipc_bclink_unlock(net); + goto unlock; + } bcl->stats.recv_fragments++; if (buf) { bcl->stats.recv_fragmented++; @@ -559,25 +535,25 @@ receive: if (node->bclink.last_in == node->bclink.last_sent) goto unlock; - if (skb_queue_empty(&node->bclink.deferred_queue)) { + if (skb_queue_empty(&node->bclink.deferdq)) { node->bclink.oos_state = 1; goto unlock; } - msg = buf_msg(skb_peek(&node->bclink.deferred_queue)); + msg = buf_msg(skb_peek(&node->bclink.deferdq)); seqno = msg_seqno(msg); next_in = mod(next_in + 1); if (seqno != next_in) goto unlock; /* Take in-sequence message from deferred queue & deliver it */ - buf = __skb_dequeue(&node->bclink.deferred_queue); + buf = __skb_dequeue(&node->bclink.deferdq); goto receive; } /* Handle out-of-sequence broadcast message */ if (less(next_in, seqno)) { - deferred = tipc_link_defer_pkt(&node->bclink.deferred_queue, + deferred = tipc_link_defer_pkt(&node->bclink.deferdq, buf); bclink_update_last_sent(node, seqno); buf = NULL; @@ -594,6 +570,7 @@ receive: unlock: tipc_node_unlock(node); + tipc_node_put(node); exit: kfree_skb(buf); } @@ -634,7 +611,6 @@ static int tipc_bcbearer_send(struct net *net, struct sk_buff *buf, msg_set_non_seq(msg, 1); msg_set_mc_netid(msg, tn->net_id); tn->bcl->stats.sent_info++; - if (WARN_ON(!bclink->bcast_nodes.count)) { dump_stack(); return 0; @@ -835,7 +811,7 @@ int tipc_nl_add_bc_link(struct net *net, struct tipc_nl_msg *msg) prop = nla_nest_start(msg->skb, TIPC_NLA_LINK_PROP); if (!prop) goto attr_msg_full; - if (nla_put_u32(msg->skb, TIPC_NLA_PROP_WIN, bcl->queue_limit[0])) + if (nla_put_u32(msg->skb, TIPC_NLA_PROP_WIN, bcl->window)) goto prop_msg_full; nla_nest_end(msg->skb, prop); @@ -913,8 +889,9 @@ int tipc_bclink_init(struct net *net) sprintf(bcbearer->media.name, "tipc-broadcast"); spin_lock_init(&bclink->lock); - __skb_queue_head_init(&bcl->outqueue); - __skb_queue_head_init(&bcl->deferred_queue); + __skb_queue_head_init(&bcl->transmq); + __skb_queue_head_init(&bcl->backlogq); + __skb_queue_head_init(&bcl->deferdq); skb_queue_head_init(&bcl->wakeupq); bcl->next_out_no = 1; spin_lock_init(&bclink->node.lock); @@ -922,7 +899,7 @@ int tipc_bclink_init(struct net *net) skb_queue_head_init(&bclink->inputq); bcl->owner = &bclink->node; bcl->owner->net = net; - bcl->max_pkt = MAX_PKT_DEFAULT_MCAST; + bcl->mtu = MAX_PKT_DEFAULT_MCAST; tipc_link_set_queue_limits(bcl, BCLINK_WIN_DEFAULT); bcl->bearer_id = MAX_BEARERS; rcu_assign_pointer(tn->bearer_list[MAX_BEARERS], &bcbearer->bearer); diff --git a/net/tipc/bcast.h b/net/tipc/bcast.h index 43f397fbac55..4bdc12277d33 100644 --- a/net/tipc/bcast.h +++ b/net/tipc/bcast.h @@ -55,7 +55,6 @@ struct tipc_bcbearer_pair { struct tipc_bearer *secondary; }; -#define TIPC_BCLINK_RESET 1 #define BCBEARER MAX_BEARERS /** @@ -86,7 +85,6 @@ struct tipc_bcbearer { * @lock: spinlock governing access to structure * @link: (non-standard) broadcast link structure * @node: (non-standard) node structure representing b'cast link's peer node - * @flags: represent bclink states * @bcast_nodes: map of broadcast-capable nodes * @retransmit_to: node that most recently requested a retransmit * @@ -96,7 +94,6 @@ struct tipc_bclink { spinlock_t lock; struct tipc_link link; struct tipc_node node; - unsigned int flags; struct sk_buff_head arrvq; struct sk_buff_head inputq; struct tipc_node_map bcast_nodes; @@ -117,7 +114,6 @@ static inline int tipc_nmap_equal(struct tipc_node_map *nm_a, int tipc_bclink_init(struct net *net); void tipc_bclink_stop(struct net *net); -void tipc_bclink_set_flags(struct net *tn, unsigned int flags); void tipc_bclink_add_node(struct net *net, u32 addr); void tipc_bclink_remove_node(struct net *net, u32 addr); struct tipc_node *tipc_bclink_retransmit_to(struct net *tn); diff --git a/net/tipc/bearer.c b/net/tipc/bearer.c index 48852c2dcc03..70e3dacbf84a 100644 --- a/net/tipc/bearer.c +++ b/net/tipc/bearer.c @@ -48,6 +48,9 @@ static struct tipc_media * const media_info_array[] = { #ifdef CONFIG_TIPC_MEDIA_IB &ib_media_info, #endif +#ifdef CONFIG_TIPC_MEDIA_UDP + &udp_media_info, +#endif NULL }; @@ -216,7 +219,8 @@ void tipc_bearer_remove_dest(struct net *net, u32 bearer_id, u32 dest) * tipc_enable_bearer - enable bearer with the given name */ static int tipc_enable_bearer(struct net *net, const char *name, - u32 disc_domain, u32 priority) + u32 disc_domain, u32 priority, + struct nlattr *attr[]) { struct tipc_net *tn = net_generic(net, tipc_net_id); struct tipc_bearer *b_ptr; @@ -304,7 +308,7 @@ restart: strcpy(b_ptr->name, name); b_ptr->media = m_ptr; - res = m_ptr->enable_media(net, b_ptr); + res = m_ptr->enable_media(net, b_ptr, attr); if (res) { pr_warn("Bearer <%s> rejected, enable failure (%d)\n", name, -res); @@ -372,7 +376,8 @@ static void bearer_disable(struct net *net, struct tipc_bearer *b_ptr, kfree_rcu(b_ptr, rcu); } -int tipc_enable_l2_media(struct net *net, struct tipc_bearer *b) +int tipc_enable_l2_media(struct net *net, struct tipc_bearer *b, + struct nlattr *attr[]) { struct net_device *dev; char *driver_name = strchr((const char *)b->name, ':') + 1; @@ -586,14 +591,14 @@ void tipc_bearer_stop(struct net *net) /* Caller should hold rtnl_lock to protect the bearer */ static int __tipc_nl_add_bearer(struct tipc_nl_msg *msg, - struct tipc_bearer *bearer) + struct tipc_bearer *bearer, int nlflags) { void *hdr; struct nlattr *attrs; struct nlattr *prop; hdr = genlmsg_put(msg->skb, msg->portid, msg->seq, &tipc_genl_family, - NLM_F_MULTI, TIPC_NL_BEARER_GET); + nlflags, TIPC_NL_BEARER_GET); if (!hdr) return -EMSGSIZE; @@ -652,7 +657,7 @@ int tipc_nl_bearer_dump(struct sk_buff *skb, struct netlink_callback *cb) if (!bearer) continue; - err = __tipc_nl_add_bearer(&msg, bearer); + err = __tipc_nl_add_bearer(&msg, bearer, NLM_F_MULTI); if (err) break; } @@ -700,7 +705,7 @@ int tipc_nl_bearer_get(struct sk_buff *skb, struct genl_info *info) goto err_out; } - err = __tipc_nl_add_bearer(&msg, bearer); + err = __tipc_nl_add_bearer(&msg, bearer, 0); if (err) goto err_out; rtnl_unlock(); @@ -791,7 +796,7 @@ int tipc_nl_bearer_enable(struct sk_buff *skb, struct genl_info *info) } rtnl_lock(); - err = tipc_enable_bearer(net, bearer, domain, prio); + err = tipc_enable_bearer(net, bearer, domain, prio, attrs); if (err) { rtnl_unlock(); return err; @@ -852,14 +857,14 @@ int tipc_nl_bearer_set(struct sk_buff *skb, struct genl_info *info) } static int __tipc_nl_add_media(struct tipc_nl_msg *msg, - struct tipc_media *media) + struct tipc_media *media, int nlflags) { void *hdr; struct nlattr *attrs; struct nlattr *prop; hdr = genlmsg_put(msg->skb, msg->portid, msg->seq, &tipc_genl_family, - NLM_F_MULTI, TIPC_NL_MEDIA_GET); + nlflags, TIPC_NL_MEDIA_GET); if (!hdr) return -EMSGSIZE; @@ -911,7 +916,8 @@ int tipc_nl_media_dump(struct sk_buff *skb, struct netlink_callback *cb) rtnl_lock(); for (; media_info_array[i] != NULL; i++) { - err = __tipc_nl_add_media(&msg, media_info_array[i]); + err = __tipc_nl_add_media(&msg, media_info_array[i], + NLM_F_MULTI); if (err) break; } @@ -958,7 +964,7 @@ int tipc_nl_media_get(struct sk_buff *skb, struct genl_info *info) goto err_out; } - err = __tipc_nl_add_media(&msg, media); + err = __tipc_nl_add_media(&msg, media, 0); if (err) goto err_out; rtnl_unlock(); diff --git a/net/tipc/bearer.h b/net/tipc/bearer.h index 6b17795ff8bc..5cad243ee8fc 100644 --- a/net/tipc/bearer.h +++ b/net/tipc/bearer.h @@ -41,7 +41,7 @@ #include <net/genetlink.h> #define MAX_BEARERS 2 -#define MAX_MEDIA 2 +#define MAX_MEDIA 3 #define MAX_NODES 4096 #define WSIZE 32 @@ -50,14 +50,16 @@ * - the field's actual content and length is defined per media * - remaining unused bytes in the field are set to zero */ -#define TIPC_MEDIA_ADDR_SIZE 32 +#define TIPC_MEDIA_INFO_SIZE 32 #define TIPC_MEDIA_TYPE_OFFSET 3 +#define TIPC_MEDIA_ADDR_OFFSET 4 /* * Identifiers of supported TIPC media types */ #define TIPC_MEDIA_TYPE_ETH 1 #define TIPC_MEDIA_TYPE_IB 2 +#define TIPC_MEDIA_TYPE_UDP 3 /** * struct tipc_node_map - set of node identifiers @@ -76,7 +78,7 @@ struct tipc_node_map { * @broadcast: non-zero if address is a broadcast address */ struct tipc_media_addr { - u8 value[TIPC_MEDIA_ADDR_SIZE]; + u8 value[TIPC_MEDIA_INFO_SIZE]; u8 media_id; u8 broadcast; }; @@ -103,7 +105,8 @@ struct tipc_media { int (*send_msg)(struct net *net, struct sk_buff *buf, struct tipc_bearer *b_ptr, struct tipc_media_addr *dest); - int (*enable_media)(struct net *net, struct tipc_bearer *b_ptr); + int (*enable_media)(struct net *net, struct tipc_bearer *b_ptr, + struct nlattr *attr[]); void (*disable_media)(struct tipc_bearer *b_ptr); int (*addr2str)(struct tipc_media_addr *addr, char *strbuf, @@ -182,6 +185,9 @@ extern struct tipc_media eth_media_info; #ifdef CONFIG_TIPC_MEDIA_IB extern struct tipc_media ib_media_info; #endif +#ifdef CONFIG_TIPC_MEDIA_UDP +extern struct tipc_media udp_media_info; +#endif int tipc_nl_bearer_disable(struct sk_buff *skb, struct genl_info *info); int tipc_nl_bearer_enable(struct sk_buff *skb, struct genl_info *info); @@ -196,7 +202,8 @@ int tipc_nl_media_set(struct sk_buff *skb, struct genl_info *info); int tipc_media_set_priority(const char *name, u32 new_value); int tipc_media_set_window(const char *name, u32 new_value); void tipc_media_addr_printf(char *buf, int len, struct tipc_media_addr *a); -int tipc_enable_l2_media(struct net *net, struct tipc_bearer *b); +int tipc_enable_l2_media(struct net *net, struct tipc_bearer *b, + struct nlattr *attrs[]); void tipc_disable_l2_media(struct tipc_bearer *b); int tipc_l2_send_msg(struct net *net, struct sk_buff *buf, struct tipc_bearer *b, struct tipc_media_addr *dest); diff --git a/net/tipc/discover.c b/net/tipc/discover.c index feef3753615d..967e292f53c8 100644 --- a/net/tipc/discover.c +++ b/net/tipc/discover.c @@ -86,9 +86,10 @@ static void tipc_disc_init_msg(struct net *net, struct sk_buff *buf, u32 type, msg = buf_msg(buf); tipc_msg_init(tn->own_addr, msg, LINK_CONFIG, type, - INT_H_SIZE, dest_domain); + MAX_H_SIZE, dest_domain); msg_set_non_seq(msg, 1); msg_set_node_sig(msg, tn->random); + msg_set_node_capabilities(msg, 0); msg_set_dest_domain(msg, dest_domain); msg_set_bc_netid(msg, tn->net_id); b_ptr->media->addr2msg(msg_media_addr(msg), &b_ptr->addr); @@ -133,6 +134,7 @@ void tipc_disc_rcv(struct net *net, struct sk_buff *buf, u32 net_id = msg_bc_netid(msg); u32 mtyp = msg_type(msg); u32 signature = msg_node_sig(msg); + u16 caps = msg_node_capabilities(msg); bool addr_match = false; bool sign_match = false; bool link_up = false; @@ -167,6 +169,7 @@ void tipc_disc_rcv(struct net *net, struct sk_buff *buf, if (!node) return; tipc_node_lock(node); + node->capabilities = caps; link = node->links[bearer->identity]; /* Prepare to validate requesting node's signature and media address */ @@ -249,7 +252,7 @@ void tipc_disc_rcv(struct net *net, struct sk_buff *buf, /* Send response, if necessary */ if (respond && (mtyp == DSC_REQ_MSG)) { - rbuf = tipc_buf_acquire(INT_H_SIZE); + rbuf = tipc_buf_acquire(MAX_H_SIZE); if (rbuf) { tipc_disc_init_msg(net, rbuf, DSC_RESP_MSG, bearer); tipc_bearer_send(net, bearer->identity, rbuf, &maddr); @@ -257,6 +260,7 @@ void tipc_disc_rcv(struct net *net, struct sk_buff *buf, } } tipc_node_unlock(node); + tipc_node_put(node); } /** @@ -359,8 +363,7 @@ int tipc_disc_create(struct net *net, struct tipc_bearer *b_ptr, req = kmalloc(sizeof(*req), GFP_ATOMIC); if (!req) return -ENOMEM; - - req->buf = tipc_buf_acquire(INT_H_SIZE); + req->buf = tipc_buf_acquire(MAX_H_SIZE); if (!req->buf) { kfree(req); return -ENOMEM; diff --git a/net/tipc/eth_media.c b/net/tipc/eth_media.c index 5e1426f1751f..f69a2fde9f4a 100644 --- a/net/tipc/eth_media.c +++ b/net/tipc/eth_media.c @@ -37,8 +37,6 @@ #include "core.h" #include "bearer.h" -#define ETH_ADDR_OFFSET 4 /* MAC addr position inside address field */ - /* Convert Ethernet address (media address format) to string */ static int tipc_eth_addr2str(struct tipc_media_addr *addr, char *strbuf, int bufsz) @@ -53,9 +51,9 @@ static int tipc_eth_addr2str(struct tipc_media_addr *addr, /* Convert from media address format to discovery message addr format */ static int tipc_eth_addr2msg(char *msg, struct tipc_media_addr *addr) { - memset(msg, 0, TIPC_MEDIA_ADDR_SIZE); + memset(msg, 0, TIPC_MEDIA_INFO_SIZE); msg[TIPC_MEDIA_TYPE_OFFSET] = TIPC_MEDIA_TYPE_ETH; - memcpy(msg + ETH_ADDR_OFFSET, addr->value, ETH_ALEN); + memcpy(msg + TIPC_MEDIA_ADDR_OFFSET, addr->value, ETH_ALEN); return 0; } @@ -79,7 +77,7 @@ static int tipc_eth_msg2addr(struct tipc_bearer *b, char *msg) { /* Skip past preamble: */ - msg += ETH_ADDR_OFFSET; + msg += TIPC_MEDIA_ADDR_OFFSET; return tipc_eth_raw2addr(b, addr, msg); } diff --git a/net/tipc/ib_media.c b/net/tipc/ib_media.c index 8522eef9c136..e8c16718e3fa 100644 --- a/net/tipc/ib_media.c +++ b/net/tipc/ib_media.c @@ -57,7 +57,7 @@ static int tipc_ib_addr2str(struct tipc_media_addr *a, char *str_buf, /* Convert from media address format to discovery message addr format */ static int tipc_ib_addr2msg(char *msg, struct tipc_media_addr *addr) { - memset(msg, 0, TIPC_MEDIA_ADDR_SIZE); + memset(msg, 0, TIPC_MEDIA_INFO_SIZE); memcpy(msg, addr->value, INFINIBAND_ALEN); return 0; } diff --git a/net/tipc/link.c b/net/tipc/link.c index 14f09b3cb87c..43a515dc97b0 100644 --- a/net/tipc/link.c +++ b/net/tipc/link.c @@ -1,7 +1,7 @@ /* * net/tipc/link.c: TIPC link code * - * Copyright (c) 1996-2007, 2012-2014, Ericsson AB + * Copyright (c) 1996-2007, 2012-2015, Ericsson AB * Copyright (c) 2004-2007, 2010-2013, Wind River Systems * All rights reserved. * @@ -35,6 +35,7 @@ */ #include "core.h" +#include "subscr.h" #include "link.h" #include "bcast.h" #include "socket.h" @@ -88,24 +89,14 @@ static const struct nla_policy tipc_nl_prop_policy[TIPC_NLA_PROP_MAX + 1] = { #define TIMEOUT_EVT 560817u /* link timer expired */ /* - * The following two 'message types' is really just implementation - * data conveniently stored in the message header. - * They must not be considered part of the protocol + * State value stored in 'failover_pkts' */ -#define OPEN_MSG 0 -#define CLOSED_MSG 1 - -/* - * State value stored in 'exp_msg_count' - */ -#define START_CHANGEOVER 100000u +#define FIRST_FAILOVER 0xffffu static void link_handle_out_of_seq_msg(struct tipc_link *link, struct sk_buff *skb); static void tipc_link_proto_rcv(struct tipc_link *link, struct sk_buff *skb); -static int tipc_link_tunnel_rcv(struct tipc_node *node, - struct sk_buff **skb); static void link_set_supervision_props(struct tipc_link *l_ptr, u32 tol); static void link_state_event(struct tipc_link *l_ptr, u32 event); static void link_reset_statistics(struct tipc_link *l_ptr); @@ -114,7 +105,7 @@ 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 void tipc_link_input(struct tipc_link *l, struct sk_buff *skb); static bool tipc_data_input(struct tipc_link *l, struct sk_buff *skb); - +static bool tipc_link_failover_rcv(struct tipc_link *l, struct sk_buff **skb); /* * Simple link routines */ @@ -138,32 +129,11 @@ static void tipc_link_put(struct tipc_link *l_ptr) kref_put(&l_ptr->ref, tipc_link_release); } -static void link_init_max_pkt(struct tipc_link *l_ptr) +static struct tipc_link *tipc_parallel_link(struct tipc_link *l) { - struct tipc_node *node = l_ptr->owner; - struct tipc_net *tn = net_generic(node->net, tipc_net_id); - struct tipc_bearer *b_ptr; - u32 max_pkt; - - rcu_read_lock(); - b_ptr = rcu_dereference_rtnl(tn->bearer_list[l_ptr->bearer_id]); - if (!b_ptr) { - rcu_read_unlock(); - return; - } - max_pkt = (b_ptr->mtu & ~3); - rcu_read_unlock(); - - if (max_pkt > MAX_MSG_SIZE) - max_pkt = MAX_MSG_SIZE; - - l_ptr->max_pkt_target = max_pkt; - if (l_ptr->max_pkt_target < MAX_PKT_DEFAULT) - l_ptr->max_pkt = l_ptr->max_pkt_target; - else - l_ptr->max_pkt = MAX_PKT_DEFAULT; - - l_ptr->max_pkt_probes = 0; + if (l->owner->active_links[0] != l) + return l->owner->active_links[0]; + return l->owner->active_links[1]; } /* @@ -194,10 +164,10 @@ static void link_timeout(unsigned long data) tipc_node_lock(l_ptr->owner); /* update counters used in statistical profiling of send traffic */ - l_ptr->stats.accu_queue_sz += skb_queue_len(&l_ptr->outqueue); + l_ptr->stats.accu_queue_sz += skb_queue_len(&l_ptr->transmq); l_ptr->stats.queue_sz_counts++; - skb = skb_peek(&l_ptr->outqueue); + skb = skb_peek(&l_ptr->transmq); if (skb) { struct tipc_msg *msg = buf_msg(skb); u32 length = msg_size(msg); @@ -229,7 +199,7 @@ static void link_timeout(unsigned long data) /* do all other link processing performed on a periodic basis */ link_state_event(l_ptr, TIMEOUT_EVT); - if (l_ptr->next_out) + if (skb_queue_len(&l_ptr->backlogq)) tipc_link_push_packets(l_ptr); tipc_node_unlock(l_ptr->owner); @@ -305,16 +275,15 @@ struct tipc_link *tipc_link_create(struct tipc_node *n_ptr, msg_set_session(msg, (tn->random & 0xffff)); msg_set_bearer_id(msg, b_ptr->identity); strcpy((char *)msg_data(msg), if_name); - + l_ptr->net_plane = b_ptr->net_plane; + l_ptr->advertised_mtu = b_ptr->mtu; + l_ptr->mtu = l_ptr->advertised_mtu; l_ptr->priority = b_ptr->priority; tipc_link_set_queue_limits(l_ptr, b_ptr->window); - - l_ptr->net_plane = b_ptr->net_plane; - link_init_max_pkt(l_ptr); - l_ptr->next_out_no = 1; - __skb_queue_head_init(&l_ptr->outqueue); - __skb_queue_head_init(&l_ptr->deferred_queue); + __skb_queue_head_init(&l_ptr->transmq); + __skb_queue_head_init(&l_ptr->backlogq); + __skb_queue_head_init(&l_ptr->deferdq); skb_queue_head_init(&l_ptr->wakeupq); skb_queue_head_init(&l_ptr->inputq); skb_queue_head_init(&l_ptr->namedq); @@ -327,15 +296,19 @@ struct tipc_link *tipc_link_create(struct tipc_node *n_ptr, } /** - * link_delete - Conditional deletion of link. - * If timer still running, real delete is done when it expires - * @link: link to be deleted + * tipc_link_delete - Delete a link + * @l: link to be deleted */ -void tipc_link_delete(struct tipc_link *link) +void tipc_link_delete(struct tipc_link *l) { - tipc_link_reset_fragments(link); - tipc_node_detach_link(link->owner, link); - tipc_link_put(link); + tipc_link_reset(l); + if (del_timer(&l->timer)) + tipc_link_put(l); + l->flags |= LINK_STOPPED; + /* Delete link now, or when timer is finished: */ + tipc_link_reset_fragments(l); + tipc_node_detach_link(l->owner, l); + tipc_link_put(l); } void tipc_link_delete_list(struct net *net, unsigned int bearer_id, @@ -349,16 +322,7 @@ void tipc_link_delete_list(struct net *net, unsigned int bearer_id, list_for_each_entry_rcu(node, &tn->node_list, list) { tipc_node_lock(node); link = node->links[bearer_id]; - if (!link) { - tipc_node_unlock(node); - continue; - } - tipc_link_reset(link); - if (del_timer(&link->timer)) - tipc_link_put(link); - link->flags |= LINK_STOPPED; - /* Delete link now, or when failover is finished: */ - if (shutting_down || !tipc_node_is_up(node)) + if (link) tipc_link_delete(link); tipc_node_unlock(node); } @@ -366,28 +330,43 @@ void tipc_link_delete_list(struct net *net, unsigned int bearer_id, } /** - * link_schedule_user - schedule user for wakeup after congestion + * link_schedule_user - schedule a message sender for wakeup after congestion * @link: congested link - * @oport: sending port - * @chain_sz: size of buffer chain that was attempted sent - * @imp: importance of message attempted sent + * @list: message that was attempted sent * Create pseudo msg to send back to user when congestion abates + * Only consumes message if there is an error */ -static bool link_schedule_user(struct tipc_link *link, u32 oport, - uint chain_sz, uint imp) +static int link_schedule_user(struct tipc_link *link, struct sk_buff_head *list) { - struct sk_buff *buf; + struct tipc_msg *msg = buf_msg(skb_peek(list)); + int imp = msg_importance(msg); + u32 oport = msg_origport(msg); + u32 addr = link_own_addr(link); + struct sk_buff *skb; - buf = tipc_msg_create(SOCK_WAKEUP, 0, INT_H_SIZE, 0, - link_own_addr(link), link_own_addr(link), - oport, 0, 0); - if (!buf) - return false; - TIPC_SKB_CB(buf)->chain_sz = chain_sz; - TIPC_SKB_CB(buf)->chain_imp = imp; - skb_queue_tail(&link->wakeupq, buf); + /* This really cannot happen... */ + if (unlikely(imp > TIPC_CRITICAL_IMPORTANCE)) { + pr_warn("%s<%s>, send queue full", link_rst_msg, link->name); + tipc_link_reset(link); + goto err; + } + /* Non-blocking sender: */ + if (TIPC_SKB_CB(skb_peek(list))->wakeup_pending) + return -ELINKCONG; + + /* Create and schedule wakeup pseudo message */ + skb = tipc_msg_create(SOCK_WAKEUP, 0, INT_H_SIZE, 0, + addr, addr, oport, 0, 0); + if (!skb) + goto err; + TIPC_SKB_CB(skb)->chain_sz = skb_queue_len(list); + TIPC_SKB_CB(skb)->chain_imp = imp; + skb_queue_tail(&link->wakeupq, skb); link->stats.link_congs++; - return true; + return -ELINKCONG; +err: + __skb_queue_purge(list); + return -ENOBUFS; } /** @@ -396,19 +375,22 @@ static bool link_schedule_user(struct tipc_link *link, u32 oport, * Move a number of waiting users, as permitted by available space in * the send queue, from link wait queue to node wait queue for wakeup */ -void link_prepare_wakeup(struct tipc_link *link) +void link_prepare_wakeup(struct tipc_link *l) { - uint pend_qsz = skb_queue_len(&link->outqueue); + int pnd[TIPC_SYSTEM_IMPORTANCE + 1] = {0,}; + int imp, lim; struct sk_buff *skb, *tmp; - skb_queue_walk_safe(&link->wakeupq, skb, tmp) { - if (pend_qsz >= link->queue_limit[TIPC_SKB_CB(skb)->chain_imp]) + skb_queue_walk_safe(&l->wakeupq, skb, tmp) { + imp = TIPC_SKB_CB(skb)->chain_imp; + lim = l->window + l->backlog[imp].limit; + pnd[imp] += TIPC_SKB_CB(skb)->chain_sz; + if ((pnd[imp] + l->backlog[imp].len) >= lim) break; - pend_qsz += TIPC_SKB_CB(skb)->chain_sz; - skb_unlink(skb, &link->wakeupq); - skb_queue_tail(&link->inputq, skb); - link->owner->inputq = &link->inputq; - link->owner->action_flags |= TIPC_MSG_EVT; + skb_unlink(skb, &l->wakeupq); + skb_queue_tail(&l->inputq, skb); + l->owner->inputq = &l->inputq; + l->owner->action_flags |= TIPC_MSG_EVT; } } @@ -422,31 +404,42 @@ void tipc_link_reset_fragments(struct tipc_link *l_ptr) l_ptr->reasm_buf = NULL; } +static void tipc_link_purge_backlog(struct tipc_link *l) +{ + __skb_queue_purge(&l->backlogq); + l->backlog[TIPC_LOW_IMPORTANCE].len = 0; + l->backlog[TIPC_MEDIUM_IMPORTANCE].len = 0; + l->backlog[TIPC_HIGH_IMPORTANCE].len = 0; + l->backlog[TIPC_CRITICAL_IMPORTANCE].len = 0; + l->backlog[TIPC_SYSTEM_IMPORTANCE].len = 0; +} + /** * tipc_link_purge_queues - purge all pkt queues associated with link * @l_ptr: pointer to link */ void tipc_link_purge_queues(struct tipc_link *l_ptr) { - __skb_queue_purge(&l_ptr->deferred_queue); - __skb_queue_purge(&l_ptr->outqueue); + __skb_queue_purge(&l_ptr->deferdq); + __skb_queue_purge(&l_ptr->transmq); + tipc_link_purge_backlog(l_ptr); tipc_link_reset_fragments(l_ptr); } void tipc_link_reset(struct tipc_link *l_ptr) { u32 prev_state = l_ptr->state; - u32 checkpoint = l_ptr->next_in_no; int was_active_link = tipc_link_is_active(l_ptr); struct tipc_node *owner = l_ptr->owner; + struct tipc_link *pl = tipc_parallel_link(l_ptr); msg_set_session(l_ptr->pmsg, ((msg_session(l_ptr->pmsg) + 1) & 0xffff)); /* Link is down, accept any session */ l_ptr->peer_session = INVALID_SESSION; - /* Prepare for max packet size negotiation */ - link_init_max_pkt(l_ptr); + /* Prepare for renewed mtu size negotiation */ + l_ptr->mtu = l_ptr->advertised_mtu; l_ptr->state = RESET_UNKNOWN; @@ -456,21 +449,26 @@ void tipc_link_reset(struct tipc_link *l_ptr) tipc_node_link_down(l_ptr->owner, l_ptr); tipc_bearer_remove_dest(owner->net, l_ptr->bearer_id, l_ptr->addr); - if (was_active_link && tipc_node_active_links(l_ptr->owner)) { - l_ptr->reset_checkpoint = checkpoint; - l_ptr->exp_msg_count = START_CHANGEOVER; + if (was_active_link && tipc_node_is_up(l_ptr->owner) && (pl != l_ptr)) { + l_ptr->flags |= LINK_FAILINGOVER; + l_ptr->failover_checkpt = l_ptr->next_in_no; + pl->failover_pkts = FIRST_FAILOVER; + pl->failover_checkpt = l_ptr->next_in_no; + pl->failover_skb = l_ptr->reasm_buf; + } else { + kfree_skb(l_ptr->reasm_buf); } - /* Clean up all queues, except inputq: */ - __skb_queue_purge(&l_ptr->outqueue); - __skb_queue_purge(&l_ptr->deferred_queue); + __skb_queue_purge(&l_ptr->transmq); + __skb_queue_purge(&l_ptr->deferdq); if (!owner->inputq) owner->inputq = &l_ptr->inputq; skb_queue_splice_init(&l_ptr->wakeupq, owner->inputq); if (!skb_queue_empty(owner->inputq)) owner->action_flags |= TIPC_MSG_EVT; - l_ptr->next_out = NULL; - l_ptr->unacked_window = 0; + tipc_link_purge_backlog(l_ptr); + l_ptr->reasm_buf = NULL; + l_ptr->rcv_unacked = 0; l_ptr->checkpoint = 1; l_ptr->next_out_no = 1; l_ptr->fsm_msg_cnt = 0; @@ -521,8 +519,7 @@ static void link_state_event(struct tipc_link *l_ptr, unsigned int event) if (!(l_ptr->flags & LINK_STARTED) && (event != STARTING_EVT)) return; /* Not yet. */ - /* Check whether changeover is going on */ - if (l_ptr->exp_msg_count) { + if (l_ptr->flags & LINK_FAILINGOVER) { if (event == TIMEOUT_EVT) link_set_timer(l_ptr, cont_intv); return; @@ -539,11 +536,7 @@ static void link_state_event(struct tipc_link *l_ptr, unsigned int event) l_ptr->checkpoint = l_ptr->next_in_no; if (tipc_bclink_acks_missing(l_ptr->owner)) { tipc_link_proto_xmit(l_ptr, STATE_MSG, - 0, 0, 0, 0, 0); - l_ptr->fsm_msg_cnt++; - } else if (l_ptr->max_pkt < l_ptr->max_pkt_target) { - tipc_link_proto_xmit(l_ptr, STATE_MSG, - 1, 0, 0, 0, 0); + 0, 0, 0, 0); l_ptr->fsm_msg_cnt++; } link_set_timer(l_ptr, cont_intv); @@ -551,7 +544,7 @@ static void link_state_event(struct tipc_link *l_ptr, unsigned int event) } l_ptr->state = WORKING_UNKNOWN; l_ptr->fsm_msg_cnt = 0; - tipc_link_proto_xmit(l_ptr, STATE_MSG, 1, 0, 0, 0, 0); + tipc_link_proto_xmit(l_ptr, STATE_MSG, 1, 0, 0, 0); l_ptr->fsm_msg_cnt++; link_set_timer(l_ptr, cont_intv / 4); break; @@ -562,7 +555,7 @@ static void link_state_event(struct tipc_link *l_ptr, unsigned int event) l_ptr->state = RESET_RESET; l_ptr->fsm_msg_cnt = 0; tipc_link_proto_xmit(l_ptr, ACTIVATE_MSG, - 0, 0, 0, 0, 0); + 0, 0, 0, 0); l_ptr->fsm_msg_cnt++; link_set_timer(l_ptr, cont_intv); break; @@ -585,7 +578,7 @@ static void link_state_event(struct tipc_link *l_ptr, unsigned int event) l_ptr->state = RESET_RESET; l_ptr->fsm_msg_cnt = 0; tipc_link_proto_xmit(l_ptr, ACTIVATE_MSG, - 0, 0, 0, 0, 0); + 0, 0, 0, 0); l_ptr->fsm_msg_cnt++; link_set_timer(l_ptr, cont_intv); break; @@ -596,13 +589,13 @@ static void link_state_event(struct tipc_link *l_ptr, unsigned int event) l_ptr->checkpoint = l_ptr->next_in_no; if (tipc_bclink_acks_missing(l_ptr->owner)) { tipc_link_proto_xmit(l_ptr, STATE_MSG, - 0, 0, 0, 0, 0); + 0, 0, 0, 0); l_ptr->fsm_msg_cnt++; } link_set_timer(l_ptr, cont_intv); } else if (l_ptr->fsm_msg_cnt < l_ptr->abort_limit) { tipc_link_proto_xmit(l_ptr, STATE_MSG, - 1, 0, 0, 0, 0); + 1, 0, 0, 0); l_ptr->fsm_msg_cnt++; link_set_timer(l_ptr, cont_intv / 4); } else { /* Link has failed */ @@ -612,7 +605,7 @@ static void link_state_event(struct tipc_link *l_ptr, unsigned int event) l_ptr->state = RESET_UNKNOWN; l_ptr->fsm_msg_cnt = 0; tipc_link_proto_xmit(l_ptr, RESET_MSG, - 0, 0, 0, 0, 0); + 0, 0, 0, 0); l_ptr->fsm_msg_cnt++; link_set_timer(l_ptr, cont_intv); } @@ -632,7 +625,7 @@ static void link_state_event(struct tipc_link *l_ptr, unsigned int event) l_ptr->state = WORKING_WORKING; l_ptr->fsm_msg_cnt = 0; link_activate(l_ptr); - tipc_link_proto_xmit(l_ptr, STATE_MSG, 1, 0, 0, 0, 0); + tipc_link_proto_xmit(l_ptr, STATE_MSG, 1, 0, 0, 0); l_ptr->fsm_msg_cnt++; if (l_ptr->owner->working_links == 1) tipc_link_sync_xmit(l_ptr); @@ -642,7 +635,7 @@ static void link_state_event(struct tipc_link *l_ptr, unsigned int event) l_ptr->state = RESET_RESET; l_ptr->fsm_msg_cnt = 0; tipc_link_proto_xmit(l_ptr, ACTIVATE_MSG, - 1, 0, 0, 0, 0); + 1, 0, 0, 0); l_ptr->fsm_msg_cnt++; link_set_timer(l_ptr, cont_intv); break; @@ -652,7 +645,7 @@ static void link_state_event(struct tipc_link *l_ptr, unsigned int event) link_set_timer(l_ptr, cont_intv); break; case TIMEOUT_EVT: - tipc_link_proto_xmit(l_ptr, RESET_MSG, 0, 0, 0, 0, 0); + tipc_link_proto_xmit(l_ptr, RESET_MSG, 0, 0, 0, 0); l_ptr->fsm_msg_cnt++; link_set_timer(l_ptr, cont_intv); break; @@ -670,7 +663,7 @@ static void link_state_event(struct tipc_link *l_ptr, unsigned int event) l_ptr->state = WORKING_WORKING; l_ptr->fsm_msg_cnt = 0; link_activate(l_ptr); - tipc_link_proto_xmit(l_ptr, STATE_MSG, 1, 0, 0, 0, 0); + tipc_link_proto_xmit(l_ptr, STATE_MSG, 1, 0, 0, 0); l_ptr->fsm_msg_cnt++; if (l_ptr->owner->working_links == 1) tipc_link_sync_xmit(l_ptr); @@ -680,7 +673,7 @@ static void link_state_event(struct tipc_link *l_ptr, unsigned int event) break; case TIMEOUT_EVT: tipc_link_proto_xmit(l_ptr, ACTIVATE_MSG, - 0, 0, 0, 0, 0); + 0, 0, 0, 0); l_ptr->fsm_msg_cnt++; link_set_timer(l_ptr, cont_intv); break; @@ -693,101 +686,65 @@ static void link_state_event(struct tipc_link *l_ptr, unsigned int event) } } -/* 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 tipc_link_cong(struct tipc_link *link, struct sk_buff_head *list) -{ - struct sk_buff *skb = skb_peek(list); - struct tipc_msg *msg = buf_msg(skb); - uint imp = tipc_msg_tot_importance(msg); - u32 oport = msg_tot_origport(msg); - - if (unlikely(imp > TIPC_CRITICAL_IMPORTANCE)) { - pr_warn("%s<%s>, send queue full", link_rst_msg, link->name); - tipc_link_reset(link); - goto drop; - } - if (unlikely(msg_errcode(msg))) - goto drop; - if (unlikely(msg_reroute_cnt(msg))) - goto drop; - if (TIPC_SKB_CB(skb)->wakeup_pending) - return -ELINKCONG; - if (link_schedule_user(link, oport, skb_queue_len(list), imp)) - return -ELINKCONG; -drop: - __skb_queue_purge(list); - return -EHOSTUNREACH; -} - /** * __tipc_link_xmit(): same as tipc_link_xmit, but destlink is known & locked * @link: link to use * @list: 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. + * Consumes the buffer chain, except when returning -ELINKCONG, + * since the caller then may want to make more send attempts. + * Returns 0 if success, or errno: -ELINKCONG, -EMSGSIZE or -ENOBUFS + * Messages at TIPC_SYSTEM_IMPORTANCE are always accepted */ int __tipc_link_xmit(struct net *net, struct tipc_link *link, struct sk_buff_head *list) { struct tipc_msg *msg = buf_msg(skb_peek(list)); - uint psz = msg_size(msg); - uint sndlim = link->queue_limit[0]; - uint imp = tipc_msg_tot_importance(msg); - uint mtu = link->max_pkt; + unsigned int maxwin = link->window; + unsigned int imp = msg_importance(msg); + uint mtu = link->mtu; 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_head *outqueue = &link->outqueue; + struct sk_buff_head *transmq = &link->transmq; + struct sk_buff_head *backlogq = &link->backlogq; struct sk_buff *skb, *tmp; - /* Match queue limits against msg importance: */ - if (unlikely(skb_queue_len(outqueue) >= link->queue_limit[imp])) - return tipc_link_cong(link, list); + /* Match backlog limit against msg importance: */ + if (unlikely(link->backlog[imp].len >= link->backlog[imp].limit)) + return link_schedule_user(link, list); - /* Has valid packet limit been used ? */ - if (unlikely(psz > mtu)) { + if (unlikely(msg_size(msg) > mtu)) { __skb_queue_purge(list); return -EMSGSIZE; } - - /* Prepare each packet for sending, and add to outqueue: */ + /* Prepare each packet for sending, and add to relevant queue: */ skb_queue_walk_safe(list, skb, tmp) { __skb_unlink(skb, list); msg = buf_msg(skb); - msg_set_word(msg, 2, ((ack << 16) | mod(seqno))); + msg_set_seqno(msg, seqno); + msg_set_ack(msg, ack); msg_set_bcast_ack(msg, bc_last_in); - if (skb_queue_len(outqueue) < sndlim) { - __skb_queue_tail(outqueue, skb); - tipc_bearer_send(net, link->bearer_id, - skb, addr); - link->next_out = NULL; - link->unacked_window = 0; - } else if (tipc_msg_bundle(outqueue, skb, mtu)) { + if (likely(skb_queue_len(transmq) < maxwin)) { + __skb_queue_tail(transmq, skb); + tipc_bearer_send(net, link->bearer_id, skb, addr); + link->rcv_unacked = 0; + seqno++; + continue; + } + if (tipc_msg_bundle(skb_peek_tail(backlogq), skb, mtu)) { link->stats.sent_bundled++; continue; - } else if (tipc_msg_make_bundle(outqueue, skb, mtu, - link->addr)) { + } + if (tipc_msg_make_bundle(&skb, mtu, link->addr)) { link->stats.sent_bundled++; link->stats.sent_bundles++; - if (!link->next_out) - link->next_out = skb_peek_tail(outqueue); - } else { - __skb_queue_tail(outqueue, skb); - if (!link->next_out) - link->next_out = skb; + imp = msg_importance(buf_msg(skb)); } + __skb_queue_tail(backlogq, skb); + link->backlog[imp].len++; seqno++; } link->next_out_no = seqno; @@ -808,13 +765,25 @@ static int __tipc_link_xmit_skb(struct tipc_link *link, struct sk_buff *skb) return __tipc_link_xmit(link->owner->net, link, &head); } +/* tipc_link_xmit_skb(): send single buffer to destination + * Buffers sent via this functon are generally TIPC_SYSTEM_IMPORTANCE + * messages, which will not be rejected + * The only exception is datagram messages rerouted after secondary + * lookup, which are rare and safe to dispose of anyway. + * TODO: Return real return value, and let callers use + * tipc_wait_for_sendpkt() where applicable + */ int tipc_link_xmit_skb(struct net *net, struct sk_buff *skb, u32 dnode, u32 selector) { struct sk_buff_head head; + int rc; skb2list(skb, &head); - return tipc_link_xmit(net, &head, dnode, selector); + rc = tipc_link_xmit(net, &head, dnode, selector); + if (rc == -ELINKCONG) + kfree_skb(skb); + return 0; } /** @@ -841,12 +810,15 @@ int tipc_link_xmit(struct net *net, struct sk_buff_head *list, u32 dnode, if (link) rc = __tipc_link_xmit(net, link, list); tipc_node_unlock(node); + tipc_node_put(node); } if (link) return rc; - if (likely(in_own_node(net, dnode))) - return tipc_sk_rcv(net, list); + if (likely(in_own_node(net, dnode))) { + tipc_sk_rcv(net, list); + return 0; + } __skb_queue_purge(list); return rc; @@ -893,14 +865,6 @@ static void tipc_link_sync_rcv(struct tipc_node *n, struct sk_buff *buf) kfree_skb(buf); } -struct sk_buff *tipc_skb_queue_next(const struct sk_buff_head *list, - const struct sk_buff *skb) -{ - if (skb_queue_is_last(list, skb)) - return NULL; - return skb->next; -} - /* * tipc_link_push_packets - push unsent packets to bearer * @@ -909,30 +873,24 @@ struct sk_buff *tipc_skb_queue_next(const struct sk_buff_head *list, * * Called with node locked */ -void tipc_link_push_packets(struct tipc_link *l_ptr) +void tipc_link_push_packets(struct tipc_link *link) { - struct sk_buff_head *outqueue = &l_ptr->outqueue; - struct sk_buff *skb = l_ptr->next_out; + struct sk_buff *skb; struct tipc_msg *msg; - u32 next, first; + unsigned int ack = mod(link->next_in_no - 1); - skb_queue_walk_from(outqueue, skb) { - msg = buf_msg(skb); - next = msg_seqno(msg); - first = buf_seqno(skb_peek(outqueue)); - - if (mod(next - first) < l_ptr->queue_limit[0]) { - msg_set_ack(msg, mod(l_ptr->next_in_no - 1)); - msg_set_bcast_ack(msg, l_ptr->owner->bclink.last_in); - if (msg_user(msg) == MSG_BUNDLER) - TIPC_SKB_CB(skb)->bundling = false; - tipc_bearer_send(l_ptr->owner->net, - l_ptr->bearer_id, skb, - &l_ptr->media_addr); - l_ptr->next_out = tipc_skb_queue_next(outqueue, skb); - } else { + while (skb_queue_len(&link->transmq) < link->window) { + skb = __skb_dequeue(&link->backlogq); + if (!skb) break; - } + msg = buf_msg(skb); + link->backlog[msg_importance(msg)].len--; + msg_set_ack(msg, ack); + msg_set_bcast_ack(msg, link->owner->bclink.last_in); + link->rcv_unacked = 0; + __skb_queue_tail(&link->transmq, skb); + tipc_bearer_send(link->owner->net, link->bearer_id, + skb, &link->media_addr); } } @@ -979,7 +937,6 @@ static void link_retransmit_failure(struct tipc_link *l_ptr, (unsigned long) TIPC_SKB_CB(buf)->handle); n_ptr = tipc_bclink_retransmit_to(net); - tipc_node_lock(n_ptr); tipc_addr_string_fill(addr_string, n_ptr->addr); pr_info("Broadcast link info for %s\n", addr_string); @@ -991,9 +948,7 @@ static void link_retransmit_failure(struct tipc_link *l_ptr, n_ptr->bclink.oos_state, n_ptr->bclink.last_sent); - tipc_node_unlock(n_ptr); - - tipc_bclink_set_flags(net, TIPC_BCLINK_RESET); + n_ptr->action_flags |= TIPC_BCAST_RESET; l_ptr->stale_count = 0; } } @@ -1019,8 +974,8 @@ void tipc_link_retransmit(struct tipc_link *l_ptr, struct sk_buff *skb, l_ptr->stale_count = 1; } - skb_queue_walk_from(&l_ptr->outqueue, skb) { - if (!retransmits || skb == l_ptr->next_out) + skb_queue_walk_from(&l_ptr->transmq, skb) { + if (!retransmits) break; msg = buf_msg(skb); msg_set_ack(msg, mod(l_ptr->next_in_no - 1)); @@ -1032,72 +987,43 @@ void tipc_link_retransmit(struct tipc_link *l_ptr, struct sk_buff *skb, } } -static void link_retrieve_defq(struct tipc_link *link, - struct sk_buff_head *list) -{ - u32 seq_no; - - if (skb_queue_empty(&link->deferred_queue)) - return; - - seq_no = buf_seqno(skb_peek(&link->deferred_queue)); - if (seq_no == mod(link->next_in_no)) - skb_queue_splice_tail_init(&link->deferred_queue, list); -} - -/** - * link_recv_buf_validate - validate basic format of received message - * - * This routine ensures a TIPC message has an acceptable header, and at least - * as much data as the header indicates it should. The routine also ensures - * that the entire message header is stored in the main fragment of the message - * buffer, to simplify future access to message header fields. - * - * Note: Having extra info present in the message header or data areas is OK. - * TIPC will ignore the excess, under the assumption that it is optional info - * introduced by a later release of the protocol. +/* link_synch(): check if all packets arrived before the synch + * point have been consumed + * Returns true if the parallel links are synched, otherwise false */ -static int link_recv_buf_validate(struct sk_buff *buf) +static bool link_synch(struct tipc_link *l) { - static u32 min_data_hdr_size[8] = { - SHORT_H_SIZE, MCAST_H_SIZE, NAMED_H_SIZE, BASIC_H_SIZE, - MAX_H_SIZE, MAX_H_SIZE, MAX_H_SIZE, MAX_H_SIZE - }; - - struct tipc_msg *msg; - u32 tipc_hdr[2]; - u32 size; - u32 hdr_size; - u32 min_hdr_size; - - /* If this packet comes from the defer queue, the skb has already - * been validated - */ - if (unlikely(TIPC_SKB_CB(buf)->deferred)) - return 1; + unsigned int post_synch; + struct tipc_link *pl; - if (unlikely(buf->len < MIN_H_SIZE)) - return 0; + pl = tipc_parallel_link(l); + if (pl == l) + goto synched; - msg = skb_header_pointer(buf, 0, sizeof(tipc_hdr), tipc_hdr); - if (msg == NULL) - return 0; + /* Was last pre-synch packet added to input queue ? */ + if (less_eq(pl->next_in_no, l->synch_point)) + return false; - if (unlikely(msg_version(msg) != TIPC_VERSION)) - return 0; + /* Is it still in the input queue ? */ + post_synch = mod(pl->next_in_no - l->synch_point) - 1; + if (skb_queue_len(&pl->inputq) > post_synch) + return false; +synched: + l->flags &= ~LINK_SYNCHING; + return true; +} - size = msg_size(msg); - hdr_size = msg_hdr_sz(msg); - min_hdr_size = msg_isdata(msg) ? - min_data_hdr_size[msg_type(msg)] : INT_H_SIZE; +static void link_retrieve_defq(struct tipc_link *link, + struct sk_buff_head *list) +{ + u32 seq_no; - if (unlikely((hdr_size < min_hdr_size) || - (size < hdr_size) || - (buf->len < size) || - (size - hdr_size > TIPC_MAX_USER_MSG_SIZE))) - return 0; + if (skb_queue_empty(&link->deferdq)) + return; - return pskb_may_pull(buf, hdr_size); + seq_no = buf_seqno(skb_peek(&link->deferdq)); + if (seq_no == mod(link->next_in_no)) + skb_queue_splice_tail_init(&link->deferdq, list); } /** @@ -1125,16 +1051,11 @@ void tipc_rcv(struct net *net, struct sk_buff *skb, struct tipc_bearer *b_ptr) while ((skb = __skb_dequeue(&head))) { /* Ensure message is well-formed */ - if (unlikely(!link_recv_buf_validate(skb))) - goto discard; - - /* Ensure message data is a single contiguous unit */ - if (unlikely(skb_linearize(skb))) + if (unlikely(!tipc_msg_validate(skb))) goto discard; /* Handle arrival of a non-unicast link message */ msg = buf_msg(skb); - if (unlikely(msg_non_seq(msg))) { if (msg_user(msg) == LINK_CONFIG) tipc_disc_rcv(net, skb, b_ptr); @@ -1152,8 +1073,8 @@ void tipc_rcv(struct net *net, struct sk_buff *skb, struct tipc_bearer *b_ptr) n_ptr = tipc_node_find(net, msg_prevnode(msg)); if (unlikely(!n_ptr)) goto discard; - tipc_node_lock(n_ptr); + tipc_node_lock(n_ptr); /* Locate unicast link endpoint that should handle message */ l_ptr = n_ptr->links[b_ptr->identity]; if (unlikely(!l_ptr)) @@ -1175,21 +1096,20 @@ void tipc_rcv(struct net *net, struct sk_buff *skb, struct tipc_bearer *b_ptr) ackd = msg_ack(msg); /* Release acked messages */ - if (n_ptr->bclink.recv_permitted) + if (unlikely(n_ptr->bclink.acked != msg_bcast_ack(msg))) tipc_bclink_acknowledge(n_ptr, msg_bcast_ack(msg)); released = 0; - skb_queue_walk_safe(&l_ptr->outqueue, skb1, tmp) { - if (skb1 == l_ptr->next_out || - more(buf_seqno(skb1), ackd)) + skb_queue_walk_safe(&l_ptr->transmq, skb1, tmp) { + if (more(buf_seqno(skb1), ackd)) break; - __skb_unlink(skb1, &l_ptr->outqueue); + __skb_unlink(skb1, &l_ptr->transmq); kfree_skb(skb1); released = 1; } /* Try sending any messages link endpoint has pending */ - if (unlikely(l_ptr->next_out)) + if (unlikely(skb_queue_len(&l_ptr->backlogq))) tipc_link_push_packets(l_ptr); if (released && !skb_queue_empty(&l_ptr->wakeupq)) @@ -1223,18 +1143,23 @@ void tipc_rcv(struct net *net, struct sk_buff *skb, struct tipc_bearer *b_ptr) skb = NULL; goto unlock; } + /* Synchronize with parallel link if applicable */ + if (unlikely((l_ptr->flags & LINK_SYNCHING) && !msg_dup(msg))) { + if (!link_synch(l_ptr)) + goto unlock; + } l_ptr->next_in_no++; - if (unlikely(!skb_queue_empty(&l_ptr->deferred_queue))) + if (unlikely(!skb_queue_empty(&l_ptr->deferdq))) link_retrieve_defq(l_ptr, &head); - - if (unlikely(++l_ptr->unacked_window >= TIPC_MIN_LINK_WIN)) { + if (unlikely(++l_ptr->rcv_unacked >= TIPC_MIN_LINK_WIN)) { l_ptr->stats.sent_acks++; - tipc_link_proto_xmit(l_ptr, STATE_MSG, 0, 0, 0, 0, 0); + tipc_link_proto_xmit(l_ptr, STATE_MSG, 0, 0, 0, 0); } tipc_link_input(l_ptr, skb); skb = NULL; unlock: tipc_node_unlock(n_ptr); + tipc_node_put(n_ptr); discard: if (unlikely(skb)) kfree_skb(skb); @@ -1271,7 +1196,7 @@ static bool tipc_data_input(struct tipc_link *link, struct sk_buff *skb) node->action_flags |= TIPC_NAMED_MSG_EVT; return true; case MSG_BUNDLER: - case CHANGEOVER_PROTOCOL: + case TUNNEL_PROTOCOL: case MSG_FRAGMENTER: case BCAST_PROTOCOL: return false; @@ -1298,8 +1223,14 @@ static void tipc_link_input(struct tipc_link *link, struct sk_buff *skb) return; switch (msg_user(msg)) { - case CHANGEOVER_PROTOCOL: - if (!tipc_link_tunnel_rcv(node, &skb)) + case TUNNEL_PROTOCOL: + if (msg_dup(msg)) { + link->flags |= LINK_SYNCHING; + link->synch_point = msg_seqno(msg_get_wrapped(msg)); + kfree_skb(skb); + break; + } + if (!tipc_link_failover_rcv(link, &skb)) break; if (msg_user(buf_msg(skb)) != MSG_BUNDLER) { tipc_data_input(link, skb); @@ -1394,11 +1325,10 @@ static void link_handle_out_of_seq_msg(struct tipc_link *l_ptr, return; } - if (tipc_link_defer_pkt(&l_ptr->deferred_queue, buf)) { + if (tipc_link_defer_pkt(&l_ptr->deferdq, buf)) { l_ptr->stats.deferred_recv++; - TIPC_SKB_CB(buf)->deferred = true; - if ((skb_queue_len(&l_ptr->deferred_queue) % 16) == 1) - tipc_link_proto_xmit(l_ptr, STATE_MSG, 0, 0, 0, 0, 0); + if ((skb_queue_len(&l_ptr->deferdq) % TIPC_MIN_LINK_WIN) == 1) + tipc_link_proto_xmit(l_ptr, STATE_MSG, 0, 0, 0, 0); } else { l_ptr->stats.duplicates++; } @@ -1408,15 +1338,15 @@ static void link_handle_out_of_seq_msg(struct tipc_link *l_ptr, * Send protocol message to the other endpoint. */ void tipc_link_proto_xmit(struct tipc_link *l_ptr, u32 msg_typ, int probe_msg, - u32 gap, u32 tolerance, u32 priority, u32 ack_mtu) + u32 gap, u32 tolerance, u32 priority) { struct sk_buff *buf = NULL; struct tipc_msg *msg = l_ptr->pmsg; u32 msg_size = sizeof(l_ptr->proto_msg); int r_flag; - /* Don't send protocol message during link changeover */ - if (l_ptr->exp_msg_count) + /* Don't send protocol message during link failover */ + if (l_ptr->flags & LINK_FAILINGOVER) return; /* Abort non-RESET send if communication with node is prohibited */ @@ -1434,11 +1364,11 @@ void tipc_link_proto_xmit(struct tipc_link *l_ptr, u32 msg_typ, int probe_msg, if (!tipc_link_is_up(l_ptr)) return; - if (l_ptr->next_out) - next_sent = buf_seqno(l_ptr->next_out); + if (skb_queue_len(&l_ptr->backlogq)) + next_sent = buf_seqno(skb_peek(&l_ptr->backlogq)); msg_set_next_sent(msg, next_sent); - if (!skb_queue_empty(&l_ptr->deferred_queue)) { - u32 rec = buf_seqno(skb_peek(&l_ptr->deferred_queue)); + if (!skb_queue_empty(&l_ptr->deferdq)) { + u32 rec = buf_seqno(skb_peek(&l_ptr->deferdq)); gap = mod(rec - mod(l_ptr->next_in_no)); } msg_set_seq_gap(msg, gap); @@ -1446,35 +1376,20 @@ void tipc_link_proto_xmit(struct tipc_link *l_ptr, u32 msg_typ, int probe_msg, l_ptr->stats.sent_nacks++; msg_set_link_tolerance(msg, tolerance); msg_set_linkprio(msg, priority); - msg_set_max_pkt(msg, ack_mtu); + msg_set_max_pkt(msg, l_ptr->mtu); msg_set_ack(msg, mod(l_ptr->next_in_no - 1)); msg_set_probe(msg, probe_msg != 0); - if (probe_msg) { - u32 mtu = l_ptr->max_pkt; - - if ((mtu < l_ptr->max_pkt_target) && - link_working_working(l_ptr) && - l_ptr->fsm_msg_cnt) { - msg_size = (mtu + (l_ptr->max_pkt_target - mtu)/2 + 2) & ~3; - if (l_ptr->max_pkt_probes == 10) { - l_ptr->max_pkt_target = (msg_size - 4); - l_ptr->max_pkt_probes = 0; - msg_size = (mtu + (l_ptr->max_pkt_target - mtu)/2 + 2) & ~3; - } - l_ptr->max_pkt_probes++; - } - + if (probe_msg) l_ptr->stats.sent_probes++; - } l_ptr->stats.sent_states++; } else { /* RESET_MSG or ACTIVATE_MSG */ - msg_set_ack(msg, mod(l_ptr->reset_checkpoint - 1)); + msg_set_ack(msg, mod(l_ptr->failover_checkpt - 1)); msg_set_seq_gap(msg, 0); msg_set_next_sent(msg, 1); msg_set_probe(msg, 0); msg_set_link_tolerance(msg, l_ptr->tolerance); msg_set_linkprio(msg, l_ptr->priority); - msg_set_max_pkt(msg, l_ptr->max_pkt_target); + msg_set_max_pkt(msg, l_ptr->advertised_mtu); } r_flag = (l_ptr->owner->working_links > tipc_link_is_up(l_ptr)); @@ -1490,10 +1405,9 @@ void tipc_link_proto_xmit(struct tipc_link *l_ptr, u32 msg_typ, int probe_msg, skb_copy_to_linear_data(buf, msg, sizeof(l_ptr->proto_msg)); buf->priority = TC_PRIO_CONTROL; - tipc_bearer_send(l_ptr->owner->net, l_ptr->bearer_id, buf, &l_ptr->media_addr); - l_ptr->unacked_window = 0; + l_ptr->rcv_unacked = 0; kfree_skb(buf); } @@ -1506,13 +1420,10 @@ static void tipc_link_proto_rcv(struct tipc_link *l_ptr, struct sk_buff *buf) { u32 rec_gap = 0; - u32 max_pkt_info; - u32 max_pkt_ack; u32 msg_tol; struct tipc_msg *msg = buf_msg(buf); - /* Discard protocol message during link changeover */ - if (l_ptr->exp_msg_count) + if (l_ptr->flags & LINK_FAILINGOVER) goto exit; if (l_ptr->net_plane != msg_net_plane(msg)) @@ -1551,15 +1462,8 @@ static void tipc_link_proto_rcv(struct tipc_link *l_ptr, if (msg_linkprio(msg) > l_ptr->priority) l_ptr->priority = msg_linkprio(msg); - max_pkt_info = msg_max_pkt(msg); - if (max_pkt_info) { - if (max_pkt_info < l_ptr->max_pkt_target) - l_ptr->max_pkt_target = max_pkt_info; - if (l_ptr->max_pkt > l_ptr->max_pkt_target) - l_ptr->max_pkt = l_ptr->max_pkt_target; - } else { - l_ptr->max_pkt = l_ptr->max_pkt_target; - } + if (l_ptr->mtu > msg_max_pkt(msg)) + l_ptr->mtu = msg_max_pkt(msg); /* Synchronize broadcast link info, if not done previously */ if (!tipc_node_is_up(l_ptr->owner)) { @@ -1604,18 +1508,8 @@ static void tipc_link_proto_rcv(struct tipc_link *l_ptr, mod(l_ptr->next_in_no)); } - max_pkt_ack = msg_max_pkt(msg); - if (max_pkt_ack > l_ptr->max_pkt) { - l_ptr->max_pkt = max_pkt_ack; - l_ptr->max_pkt_probes = 0; - } - - max_pkt_ack = 0; - if (msg_probe(msg)) { + if (msg_probe(msg)) l_ptr->stats.recv_probes++; - if (msg_size(msg) > sizeof(l_ptr->proto_msg)) - max_pkt_ack = msg_size(msg); - } /* Protocol message before retransmits, reduce loss risk */ if (l_ptr->owner->bclink.recv_permitted) @@ -1623,12 +1517,12 @@ static void tipc_link_proto_rcv(struct tipc_link *l_ptr, msg_last_bcast(msg)); if (rec_gap || (msg_probe(msg))) { - tipc_link_proto_xmit(l_ptr, STATE_MSG, 0, rec_gap, 0, - 0, max_pkt_ack); + tipc_link_proto_xmit(l_ptr, STATE_MSG, 0, + rec_gap, 0, 0); } if (msg_seq_gap(msg)) { l_ptr->stats.recv_nacks++; - tipc_link_retransmit(l_ptr, skb_peek(&l_ptr->outqueue), + tipc_link_retransmit(l_ptr, skb_peek(&l_ptr->transmq), msg_seq_gap(msg)); } break; @@ -1675,7 +1569,7 @@ static void tipc_link_tunnel_xmit(struct tipc_link *l_ptr, */ void tipc_link_failover_send_queue(struct tipc_link *l_ptr) { - u32 msgcount = skb_queue_len(&l_ptr->outqueue); + int msgcount; struct tipc_link *tunnel = l_ptr->owner->active_links[0]; struct tipc_msg tunnel_hdr; struct sk_buff *skb; @@ -1684,12 +1578,15 @@ void tipc_link_failover_send_queue(struct tipc_link *l_ptr) if (!tunnel) return; - tipc_msg_init(link_own_addr(l_ptr), &tunnel_hdr, CHANGEOVER_PROTOCOL, - ORIGINAL_MSG, INT_H_SIZE, l_ptr->addr); + tipc_msg_init(link_own_addr(l_ptr), &tunnel_hdr, TUNNEL_PROTOCOL, + FAILOVER_MSG, INT_H_SIZE, l_ptr->addr); + skb_queue_splice_tail_init(&l_ptr->backlogq, &l_ptr->transmq); + tipc_link_purge_backlog(l_ptr); + msgcount = skb_queue_len(&l_ptr->transmq); msg_set_bearer_id(&tunnel_hdr, l_ptr->peer_bearer_id); msg_set_msgcnt(&tunnel_hdr, msgcount); - if (skb_queue_empty(&l_ptr->outqueue)) { + if (skb_queue_empty(&l_ptr->transmq)) { skb = tipc_buf_acquire(INT_H_SIZE); if (skb) { skb_copy_to_linear_data(skb, &tunnel_hdr, INT_H_SIZE); @@ -1705,7 +1602,7 @@ void tipc_link_failover_send_queue(struct tipc_link *l_ptr) split_bundles = (l_ptr->owner->active_links[0] != l_ptr->owner->active_links[1]); - skb_queue_walk(&l_ptr->outqueue, skb) { + skb_queue_walk(&l_ptr->transmq, skb) { struct tipc_msg *msg = buf_msg(skb); if ((msg_user(msg) == MSG_BUNDLER) && split_bundles) { @@ -1736,157 +1633,105 @@ void tipc_link_failover_send_queue(struct tipc_link *l_ptr) * and sequence order is preserved per sender/receiver socket pair. * Owner node is locked. */ -void tipc_link_dup_queue_xmit(struct tipc_link *l_ptr, - struct tipc_link *tunnel) +void tipc_link_dup_queue_xmit(struct tipc_link *link, + struct tipc_link *tnl) { struct sk_buff *skb; - struct tipc_msg tunnel_hdr; - - tipc_msg_init(link_own_addr(l_ptr), &tunnel_hdr, CHANGEOVER_PROTOCOL, - DUPLICATE_MSG, INT_H_SIZE, l_ptr->addr); - msg_set_msgcnt(&tunnel_hdr, skb_queue_len(&l_ptr->outqueue)); - msg_set_bearer_id(&tunnel_hdr, l_ptr->peer_bearer_id); - skb_queue_walk(&l_ptr->outqueue, skb) { + struct tipc_msg tnl_hdr; + struct sk_buff_head *queue = &link->transmq; + int mcnt; + + tipc_msg_init(link_own_addr(link), &tnl_hdr, TUNNEL_PROTOCOL, + SYNCH_MSG, INT_H_SIZE, link->addr); + mcnt = skb_queue_len(&link->transmq) + skb_queue_len(&link->backlogq); + msg_set_msgcnt(&tnl_hdr, mcnt); + msg_set_bearer_id(&tnl_hdr, link->peer_bearer_id); + +tunnel_queue: + skb_queue_walk(queue, skb) { struct sk_buff *outskb; struct tipc_msg *msg = buf_msg(skb); - u32 length = msg_size(msg); + u32 len = msg_size(msg); - if (msg_user(msg) == MSG_BUNDLER) - msg_set_type(msg, CLOSED_MSG); - msg_set_ack(msg, mod(l_ptr->next_in_no - 1)); /* Update */ - msg_set_bcast_ack(msg, l_ptr->owner->bclink.last_in); - msg_set_size(&tunnel_hdr, length + INT_H_SIZE); - outskb = tipc_buf_acquire(length + INT_H_SIZE); + msg_set_ack(msg, mod(link->next_in_no - 1)); + msg_set_bcast_ack(msg, link->owner->bclink.last_in); + msg_set_size(&tnl_hdr, len + INT_H_SIZE); + outskb = tipc_buf_acquire(len + INT_H_SIZE); if (outskb == NULL) { pr_warn("%sunable to send duplicate msg\n", link_co_err); return; } - skb_copy_to_linear_data(outskb, &tunnel_hdr, INT_H_SIZE); - skb_copy_to_linear_data_offset(outskb, INT_H_SIZE, skb->data, - length); - __tipc_link_xmit_skb(tunnel, outskb); - if (!tipc_link_is_up(l_ptr)) + skb_copy_to_linear_data(outskb, &tnl_hdr, INT_H_SIZE); + skb_copy_to_linear_data_offset(outskb, INT_H_SIZE, + skb->data, len); + __tipc_link_xmit_skb(tnl, outskb); + if (!tipc_link_is_up(link)) return; } -} - -/** - * buf_extract - extracts embedded TIPC message from another message - * @skb: encapsulating message buffer - * @from_pos: offset to extract from - * - * Returns a new message buffer containing an embedded message. The - * encapsulating buffer is left unchanged. - */ -static struct sk_buff *buf_extract(struct sk_buff *skb, u32 from_pos) -{ - struct tipc_msg *msg = (struct tipc_msg *)(skb->data + from_pos); - u32 size = msg_size(msg); - struct sk_buff *eb; - - eb = tipc_buf_acquire(size); - if (eb) - skb_copy_to_linear_data(eb, msg, size); - return eb; -} - -/* tipc_link_dup_rcv(): Receive a tunnelled DUPLICATE_MSG packet. - * Owner node is locked. - */ -static void tipc_link_dup_rcv(struct tipc_link *l_ptr, - struct sk_buff *t_buf) -{ - struct sk_buff *buf; - - if (!tipc_link_is_up(l_ptr)) + if (queue == &link->backlogq) return; - - buf = buf_extract(t_buf, INT_H_SIZE); - if (buf == NULL) { - pr_warn("%sfailed to extract inner dup pkt\n", link_co_err); - return; - } - - /* Add buffer to deferred queue, if applicable: */ - link_handle_out_of_seq_msg(l_ptr, buf); + queue = &link->backlogq; + goto tunnel_queue; } -/* tipc_link_failover_rcv(): Receive a tunnelled ORIGINAL_MSG packet +/* tipc_link_failover_rcv(): Receive a tunnelled FAILOVER_MSG packet * Owner node is locked. */ -static struct sk_buff *tipc_link_failover_rcv(struct tipc_link *l_ptr, - struct sk_buff *t_buf) +static bool tipc_link_failover_rcv(struct tipc_link *link, + struct sk_buff **skb) { - struct tipc_msg *t_msg = buf_msg(t_buf); - struct sk_buff *buf = NULL; - struct tipc_msg *msg; - - if (tipc_link_is_up(l_ptr)) - tipc_link_reset(l_ptr); - - /* First failover packet? */ - if (l_ptr->exp_msg_count == START_CHANGEOVER) - l_ptr->exp_msg_count = msg_msgcnt(t_msg); - - /* Should there be an inner packet? */ - if (l_ptr->exp_msg_count) { - l_ptr->exp_msg_count--; - buf = buf_extract(t_buf, INT_H_SIZE); - if (buf == NULL) { - pr_warn("%sno inner failover pkt\n", link_co_err); - goto exit; - } - msg = buf_msg(buf); + struct tipc_msg *msg = buf_msg(*skb); + struct sk_buff *iskb = NULL; + struct tipc_link *pl = NULL; + int bearer_id = msg_bearer_id(msg); + int pos = 0; - if (less(msg_seqno(msg), l_ptr->reset_checkpoint)) { - kfree_skb(buf); - buf = NULL; - goto exit; - } - if (msg_user(msg) == MSG_FRAGMENTER) { - l_ptr->stats.recv_fragments++; - tipc_buf_append(&l_ptr->reasm_buf, &buf); - } + if (msg_type(msg) != FAILOVER_MSG) { + pr_warn("%sunknown tunnel pkt received\n", link_co_err); + goto exit; } -exit: - if ((!l_ptr->exp_msg_count) && (l_ptr->flags & LINK_STOPPED)) - tipc_link_delete(l_ptr); - return buf; -} + if (bearer_id >= MAX_BEARERS) + goto exit; -/* tipc_link_tunnel_rcv(): Receive a tunnelled packet, sent - * via other link as result of a failover (ORIGINAL_MSG) or - * a new active link (DUPLICATE_MSG). Failover packets are - * returned to the active link for delivery upwards. - * Owner node is locked. - */ -static int tipc_link_tunnel_rcv(struct tipc_node *n_ptr, - struct sk_buff **buf) -{ - struct sk_buff *t_buf = *buf; - struct tipc_link *l_ptr; - struct tipc_msg *t_msg = buf_msg(t_buf); - u32 bearer_id = msg_bearer_id(t_msg); + if (bearer_id == link->bearer_id) + goto exit; - *buf = NULL; + pl = link->owner->links[bearer_id]; + if (pl && tipc_link_is_up(pl)) + tipc_link_reset(pl); - if (bearer_id >= MAX_BEARERS) + if (link->failover_pkts == FIRST_FAILOVER) + link->failover_pkts = msg_msgcnt(msg); + + /* Should we expect an inner packet? */ + if (!link->failover_pkts) goto exit; - l_ptr = n_ptr->links[bearer_id]; - if (!l_ptr) + if (!tipc_msg_extract(*skb, &iskb, &pos)) { + pr_warn("%sno inner failover pkt\n", link_co_err); + *skb = NULL; goto exit; + } + link->failover_pkts--; + *skb = NULL; - if (msg_type(t_msg) == DUPLICATE_MSG) - tipc_link_dup_rcv(l_ptr, t_buf); - else if (msg_type(t_msg) == ORIGINAL_MSG) - *buf = tipc_link_failover_rcv(l_ptr, t_buf); - else - pr_warn("%sunknown tunnel pkt received\n", link_co_err); + /* Was this packet already delivered? */ + if (less(buf_seqno(iskb), link->failover_checkpt)) { + kfree_skb(iskb); + iskb = NULL; + goto exit; + } + if (msg_user(buf_msg(iskb)) == MSG_FRAGMENTER) { + link->stats.recv_fragments++; + tipc_buf_append(&link->failover_skb, &iskb); + } exit: - kfree_skb(t_buf); - return *buf != NULL; + if (!link->failover_pkts && pl) + pl->flags &= ~LINK_FAILINGOVER; + kfree_skb(*skb); + *skb = iskb; + return *skb; } static void link_set_supervision_props(struct tipc_link *l_ptr, u32 tol) @@ -1901,23 +1746,16 @@ static void link_set_supervision_props(struct tipc_link *l_ptr, u32 tol) l_ptr->abort_limit = tol / (jiffies_to_msecs(l_ptr->cont_intv) / 4); } -void tipc_link_set_queue_limits(struct tipc_link *l_ptr, u32 window) +void tipc_link_set_queue_limits(struct tipc_link *l, u32 win) { - /* Data messages from this node, inclusive FIRST_FRAGM */ - l_ptr->queue_limit[TIPC_LOW_IMPORTANCE] = window; - l_ptr->queue_limit[TIPC_MEDIUM_IMPORTANCE] = (window / 3) * 4; - l_ptr->queue_limit[TIPC_HIGH_IMPORTANCE] = (window / 3) * 5; - l_ptr->queue_limit[TIPC_CRITICAL_IMPORTANCE] = (window / 3) * 6; - /* Transiting data messages,inclusive FIRST_FRAGM */ - l_ptr->queue_limit[TIPC_LOW_IMPORTANCE + 4] = 300; - l_ptr->queue_limit[TIPC_MEDIUM_IMPORTANCE + 4] = 600; - l_ptr->queue_limit[TIPC_HIGH_IMPORTANCE + 4] = 900; - l_ptr->queue_limit[TIPC_CRITICAL_IMPORTANCE + 4] = 1200; - l_ptr->queue_limit[CONN_MANAGER] = 1200; - l_ptr->queue_limit[CHANGEOVER_PROTOCOL] = 2500; - l_ptr->queue_limit[NAME_DISTRIBUTOR] = 3000; - /* FRAGMENT and LAST_FRAGMENT packets */ - l_ptr->queue_limit[MSG_FRAGMENTER] = 4000; + int max_bulk = TIPC_MAX_PUBLICATIONS / (l->mtu / ITEM_SIZE); + + l->window = win; + l->backlog[TIPC_LOW_IMPORTANCE].limit = win / 2; + l->backlog[TIPC_MEDIUM_IMPORTANCE].limit = win; + l->backlog[TIPC_HIGH_IMPORTANCE].limit = win / 2 * 3; + l->backlog[TIPC_CRITICAL_IMPORTANCE].limit = win * 2; + l->backlog[TIPC_SYSTEM_IMPORTANCE].limit = max_bulk; } /* tipc_link_find_owner - locate owner node of link by link's name @@ -2082,14 +1920,14 @@ int tipc_nl_link_set(struct sk_buff *skb, struct genl_info *info) tol = nla_get_u32(props[TIPC_NLA_PROP_TOL]); link_set_supervision_props(link, tol); - tipc_link_proto_xmit(link, STATE_MSG, 0, 0, tol, 0, 0); + tipc_link_proto_xmit(link, STATE_MSG, 0, 0, tol, 0); } if (props[TIPC_NLA_PROP_PRIO]) { u32 prio; prio = nla_get_u32(props[TIPC_NLA_PROP_PRIO]); link->priority = prio; - tipc_link_proto_xmit(link, STATE_MSG, 0, 0, 0, prio, 0); + tipc_link_proto_xmit(link, STATE_MSG, 0, 0, 0, prio); } if (props[TIPC_NLA_PROP_WIN]) { u32 win; @@ -2172,7 +2010,7 @@ msg_full: /* Caller should hold appropriate locks to protect the link */ static int __tipc_nl_add_link(struct net *net, struct tipc_nl_msg *msg, - struct tipc_link *link) + struct tipc_link *link, int nlflags) { int err; void *hdr; @@ -2181,7 +2019,7 @@ static int __tipc_nl_add_link(struct net *net, struct tipc_nl_msg *msg, struct tipc_net *tn = net_generic(net, tipc_net_id); hdr = genlmsg_put(msg->skb, msg->portid, msg->seq, &tipc_genl_family, - NLM_F_MULTI, TIPC_NL_LINK_GET); + nlflags, TIPC_NL_LINK_GET); if (!hdr) return -EMSGSIZE; @@ -2194,7 +2032,7 @@ static int __tipc_nl_add_link(struct net *net, struct tipc_nl_msg *msg, if (nla_put_u32(msg->skb, TIPC_NLA_LINK_DEST, tipc_cluster_mask(tn->own_addr))) goto attr_msg_full; - if (nla_put_u32(msg->skb, TIPC_NLA_LINK_MTU, link->max_pkt)) + if (nla_put_u32(msg->skb, TIPC_NLA_LINK_MTU, link->mtu)) goto attr_msg_full; if (nla_put_u32(msg->skb, TIPC_NLA_LINK_RX, link->next_in_no)) goto attr_msg_full; @@ -2216,7 +2054,7 @@ static int __tipc_nl_add_link(struct net *net, struct tipc_nl_msg *msg, if (nla_put_u32(msg->skb, TIPC_NLA_PROP_TOL, link->tolerance)) goto prop_msg_full; if (nla_put_u32(msg->skb, TIPC_NLA_PROP_WIN, - link->queue_limit[TIPC_LOW_IMPORTANCE])) + link->window)) goto prop_msg_full; if (nla_put_u32(msg->skb, TIPC_NLA_PROP_PRIO, link->priority)) goto prop_msg_full; @@ -2254,7 +2092,7 @@ static int __tipc_nl_add_node_links(struct net *net, struct tipc_nl_msg *msg, if (!node->links[i]) continue; - err = __tipc_nl_add_link(net, msg, node->links[i]); + err = __tipc_nl_add_link(net, msg, node->links[i], NLM_F_MULTI); if (err) return err; } @@ -2282,7 +2120,6 @@ int tipc_nl_link_dump(struct sk_buff *skb, struct netlink_callback *cb) msg.seq = cb->nlh->nlmsg_seq; rcu_read_lock(); - if (prev_node) { node = tipc_node_find(net, prev_node); if (!node) { @@ -2295,6 +2132,7 @@ int tipc_nl_link_dump(struct sk_buff *skb, struct netlink_callback *cb) cb->prev_seq = 1; goto out; } + tipc_node_put(node); list_for_each_entry_continue_rcu(node, &tn->node_list, list) { @@ -2368,7 +2206,7 @@ int tipc_nl_link_get(struct sk_buff *skb, struct genl_info *info) goto err_out; } - err = __tipc_nl_add_link(net, &msg, link); + err = __tipc_nl_add_link(net, &msg, link, 0); if (err) goto err_out; diff --git a/net/tipc/link.h b/net/tipc/link.h index 7aeb52092bf3..b5b4e3554d4e 100644 --- a/net/tipc/link.h +++ b/net/tipc/link.h @@ -58,8 +58,10 @@ /* Link endpoint execution states */ -#define LINK_STARTED 0x0001 -#define LINK_STOPPED 0x0002 +#define LINK_STARTED 0x0001 +#define LINK_STOPPED 0x0002 +#define LINK_SYNCHING 0x0004 +#define LINK_FAILINGOVER 0x0008 /* Starting value for maximum packet size negotiation on unicast links * (unless bearer MTU is less) @@ -118,13 +120,13 @@ struct tipc_stats { * @pmsg: convenience pointer to "proto_msg" field * @priority: current link priority * @net_plane: current link network plane ('A' through 'H') - * @queue_limit: outbound message queue congestion thresholds (indexed by user) + * @backlog_limit: backlog queue congestion thresholds (indexed by importance) * @exp_msg_count: # of tunnelled messages expected during link changeover * @reset_checkpoint: seq # of last acknowledged message at time of link reset - * @max_pkt: current maximum packet size for this link - * @max_pkt_target: desired maximum packet size for this link - * @max_pkt_probes: # of probes based on current (max_pkt, max_pkt_target) - * @outqueue: outbound message queue + * @mtu: current maximum packet size for this link + * @advertised_mtu: advertised own mtu when link is being established + * @transmitq: queue for sent, non-acked messages + * @backlogq: queue for messages waiting to be sent * @next_out_no: next sequence number to use for outbound messages * @last_retransmitted: sequence number of most recently retransmitted message * @stale_count: # of identical retransmit requests made by peer @@ -165,36 +167,40 @@ struct tipc_link { struct tipc_msg *pmsg; u32 priority; char net_plane; - u32 queue_limit[15]; /* queue_limit[0]==window limit */ + u16 synch_point; - /* Changeover */ - u32 exp_msg_count; - u32 reset_checkpoint; + /* Failover */ + u16 failover_pkts; + u16 failover_checkpt; + struct sk_buff *failover_skb; /* Max packet negotiation */ - u32 max_pkt; - u32 max_pkt_target; - u32 max_pkt_probes; + u16 mtu; + u16 advertised_mtu; /* Sending */ - struct sk_buff_head outqueue; + struct sk_buff_head transmq; + struct sk_buff_head backlogq; + struct { + u16 len; + u16 limit; + } backlog[5]; u32 next_out_no; + u32 window; u32 last_retransmitted; u32 stale_count; /* Reception */ u32 next_in_no; - struct sk_buff_head deferred_queue; - u32 unacked_window; + u32 rcv_unacked; + struct sk_buff_head deferdq; struct sk_buff_head inputq; struct sk_buff_head namedq; /* Congestion handling */ - struct sk_buff *next_out; struct sk_buff_head wakeupq; /* Fragmentation/reassembly */ - u32 long_msg_seq_no; struct sk_buff *reasm_buf; /* Statistics */ @@ -225,7 +231,7 @@ int tipc_link_xmit(struct net *net, struct sk_buff_head *list, u32 dest, int __tipc_link_xmit(struct net *net, struct tipc_link *link, struct sk_buff_head *list); void tipc_link_proto_xmit(struct tipc_link *l_ptr, u32 msg_typ, int prob, - u32 gap, u32 tolerance, u32 priority, u32 acked_mtu); + u32 gap, u32 tolerance, u32 priority); void tipc_link_push_packets(struct tipc_link *l_ptr); u32 tipc_link_defer_pkt(struct sk_buff_head *list, struct sk_buff *buf); void tipc_link_set_queue_limits(struct tipc_link *l_ptr, u32 window); @@ -302,9 +308,4 @@ static inline int link_reset_reset(struct tipc_link *l_ptr) return l_ptr->state == RESET_RESET; } -static inline int link_congested(struct tipc_link *l_ptr) -{ - return skb_queue_len(&l_ptr->outqueue) >= l_ptr->queue_limit[0]; -} - #endif diff --git a/net/tipc/msg.c b/net/tipc/msg.c index b6eb90cd3ef7..c3e96e815418 100644 --- a/net/tipc/msg.c +++ b/net/tipc/msg.c @@ -1,7 +1,7 @@ /* * net/tipc/msg.c: TIPC message header routines * - * Copyright (c) 2000-2006, 2014, Ericsson AB + * Copyright (c) 2000-2006, 2014-2015, Ericsson AB * Copyright (c) 2005, 2010-2011, Wind River Systems * All rights reserved. * @@ -165,6 +165,9 @@ int tipc_buf_append(struct sk_buff **headbuf, struct sk_buff **buf) } if (fragid == LAST_FRAGMENT) { + TIPC_SKB_CB(head)->validated = false; + if (unlikely(!tipc_msg_validate(head))) + goto err; *buf = head; TIPC_SKB_CB(head)->tail = NULL; *headbuf = NULL; @@ -172,7 +175,6 @@ int tipc_buf_append(struct sk_buff **headbuf, struct sk_buff **buf) } *buf = NULL; return 0; - err: pr_warn_ratelimited("Unable to build fragment list\n"); kfree_skb(*buf); @@ -181,6 +183,48 @@ err: return 0; } +/* tipc_msg_validate - validate basic format of received message + * + * This routine ensures a TIPC message has an acceptable header, and at least + * as much data as the header indicates it should. The routine also ensures + * that the entire message header is stored in the main fragment of the message + * buffer, to simplify future access to message header fields. + * + * Note: Having extra info present in the message header or data areas is OK. + * TIPC will ignore the excess, under the assumption that it is optional info + * introduced by a later release of the protocol. + */ +bool tipc_msg_validate(struct sk_buff *skb) +{ + struct tipc_msg *msg; + int msz, hsz; + + if (unlikely(TIPC_SKB_CB(skb)->validated)) + return true; + if (unlikely(!pskb_may_pull(skb, MIN_H_SIZE))) + return false; + + hsz = msg_hdr_sz(buf_msg(skb)); + if (unlikely(hsz < MIN_H_SIZE) || (hsz > MAX_H_SIZE)) + return false; + if (unlikely(!pskb_may_pull(skb, hsz))) + return false; + + msg = buf_msg(skb); + if (unlikely(msg_version(msg) != TIPC_VERSION)) + return false; + + msz = msg_size(msg); + if (unlikely(msz < hsz)) + return false; + if (unlikely((msz - hsz) > TIPC_MAX_USER_MSG_SIZE)) + return false; + if (unlikely(skb->len < msz)) + return false; + + TIPC_SKB_CB(skb)->validated = true; + return true; +} /** * tipc_msg_build - create buffer chain containing specified header and data @@ -228,6 +272,7 @@ int tipc_msg_build(struct tipc_msg *mhdr, struct msghdr *m, FIRST_FRAGMENT, INT_H_SIZE, msg_destnode(mhdr)); msg_set_size(&pkthdr, pktmax); msg_set_fragm_no(&pkthdr, pktno); + msg_set_importance(&pkthdr, msg_importance(mhdr)); /* Prepare first fragment */ skb = tipc_buf_acquire(pktmax); @@ -286,33 +331,36 @@ error: /** * tipc_msg_bundle(): Append contents of a buffer to tail of an existing one - * @list: the buffer chain of the existing buffer ("bundle") + * @bskb: the buffer to append to ("bundle") * @skb: 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_head *list, struct sk_buff *skb, u32 mtu) +bool tipc_msg_bundle(struct sk_buff *bskb, struct sk_buff *skb, u32 mtu) { - struct sk_buff *bskb = skb_peek_tail(list); - struct tipc_msg *bmsg = buf_msg(bskb); + struct tipc_msg *bmsg; struct tipc_msg *msg = buf_msg(skb); - unsigned int bsz = msg_size(bmsg); + unsigned int bsz; unsigned int msz = msg_size(msg); - u32 start = align(bsz); + u32 start, pad; 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)) + if (!bskb) + return false; + bmsg = buf_msg(bskb); + bsz = msg_size(bmsg); + start = align(bsz); + pad = start - bsz; + + if (unlikely(msg_user(msg) == TUNNEL_PROTOCOL)) return false; if (unlikely(msg_user(msg) == BCAST_PROTOCOL)) return false; if (likely(msg_user(bmsg) != MSG_BUNDLER)) return false; - if (likely(!TIPC_SKB_CB(bskb)->bundling)) - return false; if (unlikely(skb_tailroom(bskb) < (pad + msz))) return false; if (unlikely(max < (start + msz))) @@ -328,34 +376,40 @@ bool tipc_msg_bundle(struct sk_buff_head *list, struct sk_buff *skb, u32 mtu) /** * tipc_msg_extract(): extract bundled inner packet from buffer - * @skb: linear outer buffer, to be extracted from. + * @skb: buffer to be extracted from. * @iskb: extracted inner buffer, to be returned - * @pos: position of msg to be extracted. Returns with pointer of next msg + * @pos: position in outer message of msg to be extracted. + * Returns position of next msg * Consumes outer buffer when last packet extracted * Returns true when when there is an extracted buffer, otherwise false */ bool tipc_msg_extract(struct sk_buff *skb, struct sk_buff **iskb, int *pos) { - struct tipc_msg *msg = buf_msg(skb); - int imsz; - struct tipc_msg *imsg = (struct tipc_msg *)(msg_data(msg) + *pos); + struct tipc_msg *msg; + int imsz, offset; - /* Is there space left for shortest possible message? */ - if (*pos > (msg_data_sz(msg) - SHORT_H_SIZE)) + *iskb = NULL; + if (unlikely(skb_linearize(skb))) + goto none; + + msg = buf_msg(skb); + offset = msg_hdr_sz(msg) + *pos; + if (unlikely(offset > (msg_size(msg) - MIN_H_SIZE))) goto none; - imsz = msg_size(imsg); - /* Is there space left for current message ? */ - if ((*pos + imsz) > msg_data_sz(msg)) + *iskb = skb_clone(skb, GFP_ATOMIC); + if (unlikely(!*iskb)) goto none; - *iskb = tipc_buf_acquire(imsz); - if (!*iskb) + skb_pull(*iskb, offset); + imsz = msg_size(buf_msg(*iskb)); + skb_trim(*iskb, imsz); + if (unlikely(!tipc_msg_validate(*iskb))) goto none; - skb_copy_to_linear_data(*iskb, imsg, imsz); *pos += align(imsz); return true; none: kfree_skb(skb); + kfree_skb(*iskb); *iskb = NULL; return false; } @@ -369,18 +423,17 @@ none: * Replaces buffer if successful * Returns true if success, otherwise false */ -bool tipc_msg_make_bundle(struct sk_buff_head *list, - struct sk_buff *skb, u32 mtu, u32 dnode) +bool tipc_msg_make_bundle(struct sk_buff **skb, u32 mtu, u32 dnode) { struct sk_buff *bskb; struct tipc_msg *bmsg; - struct tipc_msg *msg = buf_msg(skb); + struct tipc_msg *msg = buf_msg(*skb); 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) + if (msg_user(msg) == TUNNEL_PROTOCOL) return false; if (msg_user(msg) == BCAST_PROTOCOL) return false; @@ -398,9 +451,9 @@ bool tipc_msg_make_bundle(struct sk_buff_head *list, msg_set_seqno(bmsg, msg_seqno(msg)); msg_set_ack(bmsg, msg_ack(msg)); msg_set_bcast_ack(bmsg, msg_bcast_ack(msg)); - TIPC_SKB_CB(bskb)->bundling = true; - __skb_queue_tail(list, bskb); - return tipc_msg_bundle(list, skb, mtu); + tipc_msg_bundle(bskb, *skb, mtu); + *skb = bskb; + return true; } /** @@ -415,21 +468,17 @@ bool tipc_msg_reverse(u32 own_addr, 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; + msg = buf_msg(buf); 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)); @@ -462,15 +511,18 @@ bool tipc_msg_lookup_dest(struct net *net, struct sk_buff *skb, { struct tipc_msg *msg = buf_msg(skb); u32 dport; + u32 own_addr = tipc_own_addr(net); if (!msg_isdata(msg)) return false; if (!msg_named(msg)) return false; + if (msg_errcode(msg)) + return false; *err = -TIPC_ERR_NO_NAME; if (skb_linearize(skb)) return false; - if (msg_reroute_cnt(msg) > 0) + if (msg_reroute_cnt(msg)) return false; *dnode = addr_domain(net, msg_lookup_scope(msg)); dport = tipc_nametbl_translate(net, msg_nametype(msg), @@ -478,6 +530,8 @@ bool tipc_msg_lookup_dest(struct net *net, struct sk_buff *skb, if (!dport) return false; msg_incr_reroute_cnt(msg); + if (*dnode != own_addr) + msg_set_prevnode(msg, own_addr); msg_set_destnode(msg, *dnode); msg_set_destport(msg, dport); *err = TIPC_OK; diff --git a/net/tipc/msg.h b/net/tipc/msg.h index 9ace47f44a69..e1d3595e2ee9 100644 --- a/net/tipc/msg.h +++ b/net/tipc/msg.h @@ -1,7 +1,7 @@ /* * net/tipc/msg.h: Include file for TIPC message header routines * - * Copyright (c) 2000-2007, 2014, Ericsson AB + * Copyright (c) 2000-2007, 2014-2015 Ericsson AB * Copyright (c) 2005-2008, 2010-2011, Wind River Systems * All rights reserved. * @@ -54,6 +54,8 @@ struct plist; * - TIPC_HIGH_IMPORTANCE * - TIPC_CRITICAL_IMPORTANCE */ +#define TIPC_SYSTEM_IMPORTANCE 4 + /* * Payload message types @@ -64,6 +66,19 @@ struct plist; #define TIPC_DIRECT_MSG 3 /* + * Internal message users + */ +#define BCAST_PROTOCOL 5 +#define MSG_BUNDLER 6 +#define LINK_PROTOCOL 7 +#define CONN_MANAGER 8 +#define TUNNEL_PROTOCOL 10 +#define NAME_DISTRIBUTOR 11 +#define MSG_FRAGMENTER 12 +#define LINK_CONFIG 13 +#define SOCK_WAKEUP 14 /* pseudo user */ + +/* * Message header sizes */ #define SHORT_H_SIZE 24 /* In-cluster basic payload message */ @@ -76,7 +91,7 @@ struct plist; #define MAX_MSG_SIZE (MAX_H_SIZE + TIPC_MAX_USER_MSG_SIZE) -#define TIPC_MEDIA_ADDR_OFFSET 5 +#define TIPC_MEDIA_INFO_OFFSET 5 /** * TIPC message buffer code @@ -87,12 +102,12 @@ struct plist; * Note: Headroom should be a multiple of 4 to ensure the TIPC header fields * are word aligned for quicker access */ -#define BUF_HEADROOM LL_MAX_HEADER +#define BUF_HEADROOM (LL_MAX_HEADER + 48) struct tipc_skb_cb { void *handle; struct sk_buff *tail; - bool deferred; + bool validated; bool wakeup_pending; bool bundling; u16 chain_sz; @@ -170,16 +185,6 @@ static inline void msg_set_user(struct tipc_msg *m, u32 n) msg_set_bits(m, 0, 25, 0xf, n); } -static inline u32 msg_importance(struct tipc_msg *m) -{ - return msg_bits(m, 0, 25, 0xf); -} - -static inline void msg_set_importance(struct tipc_msg *m, u32 i) -{ - msg_set_user(m, i); -} - static inline u32 msg_hdr_sz(struct tipc_msg *m) { return msg_bits(m, 0, 21, 0xf) << 2; @@ -235,6 +240,15 @@ static inline void msg_set_size(struct tipc_msg *m, u32 sz) m->hdr[0] = htonl((msg_word(m, 0) & ~0x1ffff) | sz); } +static inline unchar *msg_data(struct tipc_msg *m) +{ + return ((unchar *)m) + msg_hdr_sz(m); +} + +static inline struct tipc_msg *msg_get_wrapped(struct tipc_msg *m) +{ + return (struct tipc_msg *)msg_data(m); +} /* * Word 1 @@ -336,6 +350,25 @@ static inline void msg_set_seqno(struct tipc_msg *m, u32 n) /* * Words 3-10 */ +static inline u32 msg_importance(struct tipc_msg *m) +{ + if (unlikely(msg_user(m) == MSG_FRAGMENTER)) + return msg_bits(m, 5, 13, 0x7); + if (likely(msg_isdata(m) && !msg_errcode(m))) + return msg_user(m); + return TIPC_SYSTEM_IMPORTANCE; +} + +static inline void msg_set_importance(struct tipc_msg *m, u32 i) +{ + if (unlikely(msg_user(m) == MSG_FRAGMENTER)) + msg_set_bits(m, 5, 13, 0x7, i); + else if (likely(i < TIPC_SYSTEM_IMPORTANCE)) + msg_set_user(m, i); + else + pr_warn("Trying to set illegal importance in message\n"); +} + static inline u32 msg_prevnode(struct tipc_msg *m) { return msg_word(m, 3); @@ -348,6 +381,8 @@ static inline void msg_set_prevnode(struct tipc_msg *m, u32 a) static inline u32 msg_origport(struct tipc_msg *m) { + if (msg_user(m) == MSG_FRAGMENTER) + m = msg_get_wrapped(m); return msg_word(m, 4); } @@ -443,35 +478,11 @@ static inline void msg_set_nameupper(struct tipc_msg *m, u32 n) msg_set_word(m, 10, n); } -static inline unchar *msg_data(struct tipc_msg *m) -{ - return ((unchar *)m) + msg_hdr_sz(m); -} - -static inline struct tipc_msg *msg_get_wrapped(struct tipc_msg *m) -{ - return (struct tipc_msg *)msg_data(m); -} - /* * Constants and routines used to read and write TIPC internal message headers */ /* - * Internal message users - */ -#define BCAST_PROTOCOL 5 -#define MSG_BUNDLER 6 -#define LINK_PROTOCOL 7 -#define CONN_MANAGER 8 -#define ROUTE_DISTRIBUTOR 9 /* obsoleted */ -#define CHANGEOVER_PROTOCOL 10 -#define NAME_DISTRIBUTOR 11 -#define MSG_FRAGMENTER 12 -#define LINK_CONFIG 13 -#define SOCK_WAKEUP 14 /* pseudo user */ - -/* * Connection management protocol message types */ #define CONN_PROBE 0 @@ -501,8 +512,8 @@ static inline struct tipc_msg *msg_get_wrapped(struct tipc_msg *m) /* * Changeover tunnel message types */ -#define DUPLICATE_MSG 0 -#define ORIGINAL_MSG 1 +#define SYNCH_MSG 0 +#define FAILOVER_MSG 1 /* * Config protocol message types @@ -510,7 +521,6 @@ static inline struct tipc_msg *msg_get_wrapped(struct tipc_msg *m) #define DSC_REQ_MSG 0 #define DSC_RESP_MSG 1 - /* * Word 1 */ @@ -534,6 +544,24 @@ static inline void msg_set_node_sig(struct tipc_msg *m, u32 n) msg_set_bits(m, 1, 0, 0xffff, n); } +static inline u32 msg_node_capabilities(struct tipc_msg *m) +{ + return msg_bits(m, 1, 15, 0x1fff); +} + +static inline void msg_set_node_capabilities(struct tipc_msg *m, u32 n) +{ + msg_set_bits(m, 1, 15, 0x1fff, n); +} + +static inline bool msg_dup(struct tipc_msg *m) +{ + if (likely(msg_user(m) != TUNNEL_PROTOCOL)) + return false; + if (msg_type(m) != SYNCH_MSG) + return false; + return true; +} /* * Word 2 @@ -688,7 +716,7 @@ static inline void msg_set_redundant_link(struct tipc_msg *m, u32 r) static inline char *msg_media_addr(struct tipc_msg *m) { - return (char *)&m->hdr[TIPC_MEDIA_ADDR_OFFSET]; + return (char *)&m->hdr[TIPC_MEDIA_INFO_OFFSET]; } /* @@ -734,21 +762,8 @@ static inline void msg_set_link_tolerance(struct tipc_msg *m, u32 n) msg_set_bits(m, 9, 0, 0xffff, n); } -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); -} - struct sk_buff *tipc_buf_acquire(u32 size); +bool tipc_msg_validate(struct sk_buff *skb); bool tipc_msg_reverse(u32 own_addr, struct sk_buff *buf, u32 *dnode, int err); void tipc_msg_init(u32 own_addr, struct tipc_msg *m, u32 user, u32 type, @@ -757,9 +772,9 @@ struct sk_buff *tipc_msg_create(uint user, uint type, uint hdr_sz, uint data_sz, u32 dnode, u32 onode, u32 dport, u32 oport, int errcode); int tipc_buf_append(struct sk_buff **headbuf, struct sk_buff **buf); -bool tipc_msg_bundle(struct sk_buff_head *list, struct sk_buff *skb, u32 mtu); -bool tipc_msg_make_bundle(struct sk_buff_head *list, - struct sk_buff *skb, u32 mtu, u32 dnode); +bool tipc_msg_bundle(struct sk_buff *bskb, struct sk_buff *skb, u32 mtu); + +bool tipc_msg_make_bundle(struct sk_buff **skb, u32 mtu, u32 dnode); bool tipc_msg_extract(struct sk_buff *skb, struct sk_buff **iskb, int *pos); int tipc_msg_build(struct tipc_msg *mhdr, struct msghdr *m, int offset, int dsz, int mtu, struct sk_buff_head *list); diff --git a/net/tipc/name_distr.c b/net/tipc/name_distr.c index fcb07915aaac..41e7b7e4dda0 100644 --- a/net/tipc/name_distr.c +++ b/net/tipc/name_distr.c @@ -98,7 +98,7 @@ void named_cluster_distribute(struct net *net, struct sk_buff *skb) continue; if (!tipc_node_active_links(node)) continue; - oskb = skb_copy(skb, GFP_ATOMIC); + oskb = pskb_copy(skb, GFP_ATOMIC); if (!oskb) break; msg_set_destnode(buf_msg(oskb), dnode); @@ -244,6 +244,7 @@ static void tipc_publ_subscribe(struct net *net, struct publication *publ, tipc_node_lock(node); list_add_tail(&publ->nodesub_list, &node->publ_list); tipc_node_unlock(node); + tipc_node_put(node); } static void tipc_publ_unsubscribe(struct net *net, struct publication *publ, @@ -258,6 +259,7 @@ static void tipc_publ_unsubscribe(struct net *net, struct publication *publ, tipc_node_lock(node); list_del_init(&publ->nodesub_list); tipc_node_unlock(node); + tipc_node_put(node); } /** diff --git a/net/tipc/name_table.c b/net/tipc/name_table.c index 105ba7adf06f..ab0ac62a1287 100644 --- a/net/tipc/name_table.c +++ b/net/tipc/name_table.c @@ -811,8 +811,8 @@ static void tipc_purge_publications(struct net *net, struct name_seq *seq) sseq = seq->sseqs; info = sseq->info; list_for_each_entry_safe(publ, safe, &info->zone_list, zone_list) { - tipc_nametbl_remove_publ(net, publ->type, publ->lower, - publ->node, publ->ref, publ->key); + tipc_nameseq_remove_publ(net, seq, publ->lower, publ->node, + publ->ref, publ->key); kfree_rcu(publ, rcu); } hlist_del_init_rcu(&seq->ns_list); diff --git a/net/tipc/node.c b/net/tipc/node.c index 86152de8248d..22c059ad2999 100644 --- a/net/tipc/node.c +++ b/net/tipc/node.c @@ -42,6 +42,7 @@ static void node_lost_contact(struct tipc_node *n_ptr); static void node_established_contact(struct tipc_node *n_ptr); +static void tipc_node_delete(struct tipc_node *node); struct tipc_sock_conn { u32 port; @@ -67,6 +68,23 @@ static unsigned int tipc_hashfn(u32 addr) return addr & (NODE_HTABLE_SIZE - 1); } +static void tipc_node_kref_release(struct kref *kref) +{ + struct tipc_node *node = container_of(kref, struct tipc_node, kref); + + tipc_node_delete(node); +} + +void tipc_node_put(struct tipc_node *node) +{ + kref_put(&node->kref, tipc_node_kref_release); +} + +static void tipc_node_get(struct tipc_node *node) +{ + kref_get(&node->kref); +} + /* * tipc_node_find - locate specified node object, if it exists */ @@ -82,6 +100,7 @@ struct tipc_node *tipc_node_find(struct net *net, u32 addr) hlist_for_each_entry_rcu(node, &tn->node_htable[tipc_hashfn(addr)], hash) { if (node->addr == addr) { + tipc_node_get(node); rcu_read_unlock(); return node; } @@ -106,12 +125,13 @@ struct tipc_node *tipc_node_create(struct net *net, u32 addr) } n_ptr->addr = addr; n_ptr->net = net; + kref_init(&n_ptr->kref); spin_lock_init(&n_ptr->lock); INIT_HLIST_NODE(&n_ptr->hash); INIT_LIST_HEAD(&n_ptr->list); INIT_LIST_HEAD(&n_ptr->publ_list); INIT_LIST_HEAD(&n_ptr->conn_sks); - __skb_queue_head_init(&n_ptr->bclink.deferred_queue); + __skb_queue_head_init(&n_ptr->bclink.deferdq); hlist_add_head_rcu(&n_ptr->hash, &tn->node_htable[tipc_hashfn(addr)]); list_for_each_entry_rcu(temp_node, &tn->node_list, list) { if (n_ptr->addr < temp_node->addr) @@ -120,16 +140,17 @@ struct tipc_node *tipc_node_create(struct net *net, u32 addr) list_add_tail_rcu(&n_ptr->list, &temp_node->list); n_ptr->action_flags = TIPC_WAIT_PEER_LINKS_DOWN; n_ptr->signature = INVALID_NODE_SIG; + tipc_node_get(n_ptr); exit: spin_unlock_bh(&tn->node_list_lock); return n_ptr; } -static void tipc_node_delete(struct tipc_net *tn, struct tipc_node *n_ptr) +static void tipc_node_delete(struct tipc_node *node) { - list_del_rcu(&n_ptr->list); - hlist_del_rcu(&n_ptr->hash); - kfree_rcu(n_ptr, rcu); + list_del_rcu(&node->list); + hlist_del_rcu(&node->hash); + kfree_rcu(node, rcu); } void tipc_node_stop(struct net *net) @@ -139,7 +160,7 @@ void tipc_node_stop(struct net *net) spin_lock_bh(&tn->node_list_lock); list_for_each_entry_safe(node, t_node, &tn->node_list, list) - tipc_node_delete(tn, node); + tipc_node_put(node); spin_unlock_bh(&tn->node_list_lock); } @@ -147,6 +168,7 @@ int tipc_node_add_conn(struct net *net, u32 dnode, u32 port, u32 peer_port) { struct tipc_node *node; struct tipc_sock_conn *conn; + int err = 0; if (in_own_node(net, dnode)) return 0; @@ -157,8 +179,10 @@ int tipc_node_add_conn(struct net *net, u32 dnode, u32 port, u32 peer_port) return -EHOSTUNREACH; } conn = kmalloc(sizeof(*conn), GFP_ATOMIC); - if (!conn) - return -EHOSTUNREACH; + if (!conn) { + err = -EHOSTUNREACH; + goto exit; + } conn->peer_node = dnode; conn->port = port; conn->peer_port = peer_port; @@ -166,7 +190,9 @@ int tipc_node_add_conn(struct net *net, u32 dnode, u32 port, u32 peer_port) tipc_node_lock(node); list_add_tail(&conn->list, &node->conn_sks); tipc_node_unlock(node); - return 0; +exit: + tipc_node_put(node); + return err; } void tipc_node_remove_conn(struct net *net, u32 dnode, u32 port) @@ -189,6 +215,7 @@ void tipc_node_remove_conn(struct net *net, u32 dnode, u32 port) kfree(conn); } tipc_node_unlock(node); + tipc_node_put(node); } /** @@ -227,8 +254,8 @@ void tipc_node_link_up(struct tipc_node *n_ptr, struct tipc_link *l_ptr) 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; + n_ptr->act_mtus[0] = active[0]->mtu - INT_H_SIZE; + n_ptr->act_mtus[1] = active[1]->mtu - INT_H_SIZE; } /** @@ -292,11 +319,10 @@ void tipc_node_link_down(struct tipc_node *n_ptr, struct tipc_link *l_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; + n_ptr->act_mtus[0] = active[0]->mtu - INT_H_SIZE; + n_ptr->act_mtus[1] = active[1]->mtu - INT_H_SIZE; return; } - /* Loopback link went down? No fragmentation needed from now on. */ if (n_ptr->addr == tn->own_addr) { n_ptr->act_mtus[0] = MAX_MSG_SIZE; @@ -354,7 +380,7 @@ static void node_lost_contact(struct tipc_node *n_ptr) /* Flush broadcast link info associated with lost node */ if (n_ptr->bclink.recv_permitted) { - __skb_queue_purge(&n_ptr->bclink.deferred_queue); + __skb_queue_purge(&n_ptr->bclink.deferdq); if (n_ptr->bclink.reasm_buf) { kfree_skb(n_ptr->bclink.reasm_buf); @@ -367,18 +393,17 @@ static void node_lost_contact(struct tipc_node *n_ptr) n_ptr->bclink.recv_permitted = false; } - /* Abort link changeover */ + /* Abort any ongoing link failover */ for (i = 0; i < MAX_BEARERS; i++) { struct tipc_link *l_ptr = n_ptr->links[i]; if (!l_ptr) continue; - l_ptr->reset_checkpoint = l_ptr->next_in_no; - l_ptr->exp_msg_count = 0; + l_ptr->flags &= ~LINK_FAILINGOVER; + l_ptr->failover_checkpt = 0; + l_ptr->failover_pkts = 0; + kfree_skb(l_ptr->failover_skb); + l_ptr->failover_skb = NULL; tipc_link_reset_fragments(l_ptr); - - /* Link marked for deletion after failover? => do it now */ - if (l_ptr->flags & LINK_STOPPED) - tipc_link_delete(l_ptr); } n_ptr->action_flags &= ~TIPC_WAIT_OWN_LINKS_DOWN; @@ -417,19 +442,25 @@ int tipc_node_get_linkname(struct net *net, u32 bearer_id, u32 addr, char *linkname, size_t len) { struct tipc_link *link; + int err = -EINVAL; struct tipc_node *node = tipc_node_find(net, addr); - if ((bearer_id >= MAX_BEARERS) || !node) - return -EINVAL; + if (!node) + return err; + + if (bearer_id >= MAX_BEARERS) + goto exit; + tipc_node_lock(node); link = node->links[bearer_id]; if (link) { strncpy(linkname, link->name, len); - tipc_node_unlock(node); - return 0; + err = 0; } +exit: tipc_node_unlock(node); - return -EINVAL; + tipc_node_put(node); + return err; } void tipc_node_unlock(struct tipc_node *node) @@ -459,7 +490,7 @@ void tipc_node_unlock(struct tipc_node *node) TIPC_NOTIFY_NODE_DOWN | TIPC_NOTIFY_NODE_UP | TIPC_NOTIFY_LINK_DOWN | TIPC_NOTIFY_LINK_UP | TIPC_WAKEUP_BCAST_USERS | TIPC_BCAST_MSG_EVT | - TIPC_NAMED_MSG_EVT); + TIPC_NAMED_MSG_EVT | TIPC_BCAST_RESET); spin_unlock_bh(&node->lock); @@ -488,6 +519,9 @@ void tipc_node_unlock(struct tipc_node *node) if (flags & TIPC_BCAST_MSG_EVT) tipc_bclink_input(net); + + if (flags & TIPC_BCAST_RESET) + tipc_link_reset_all(node); } /* Caller should hold node lock for the passed node */ @@ -542,17 +576,21 @@ int tipc_nl_node_dump(struct sk_buff *skb, struct netlink_callback *cb) msg.seq = cb->nlh->nlmsg_seq; rcu_read_lock(); - - if (last_addr && !tipc_node_find(net, last_addr)) { - rcu_read_unlock(); - /* We never set seq or call nl_dump_check_consistent() this - * means that setting prev_seq here will cause the consistence - * check to fail in the netlink callback handler. Resulting in - * the NLMSG_DONE message having the NLM_F_DUMP_INTR flag set if - * the node state changed while we released the lock. - */ - cb->prev_seq = 1; - return -EPIPE; + if (last_addr) { + node = tipc_node_find(net, last_addr); + if (!node) { + rcu_read_unlock(); + /* We never set seq or call nl_dump_check_consistent() + * this means that setting prev_seq here will cause the + * consistence check to fail in the netlink callback + * handler. Resulting in the NLMSG_DONE message having + * the NLM_F_DUMP_INTR flag set if the node state + * changed while we released the lock. + */ + cb->prev_seq = 1; + return -EPIPE; + } + tipc_node_put(node); } list_for_each_entry_rcu(node, &tn->node_list, list) { diff --git a/net/tipc/node.h b/net/tipc/node.h index 3d18c66b7f78..02d5c20dc551 100644 --- a/net/tipc/node.h +++ b/net/tipc/node.h @@ -64,7 +64,8 @@ enum { TIPC_NOTIFY_LINK_UP = (1 << 6), TIPC_NOTIFY_LINK_DOWN = (1 << 7), TIPC_NAMED_MSG_EVT = (1 << 8), - TIPC_BCAST_MSG_EVT = (1 << 9) + TIPC_BCAST_MSG_EVT = (1 << 9), + TIPC_BCAST_RESET = (1 << 10) }; /** @@ -84,7 +85,7 @@ struct tipc_node_bclink { u32 last_sent; u32 oos_state; u32 deferred_size; - struct sk_buff_head deferred_queue; + struct sk_buff_head deferdq; struct sk_buff *reasm_buf; int inputq_map; bool recv_permitted; @@ -93,6 +94,7 @@ struct tipc_node_bclink { /** * struct tipc_node - TIPC node structure * @addr: network address of node + * @ref: reference counter to node object * @lock: spinlock governing access to structure * @net: the applicable net namespace * @hash: links to adjacent nodes in unsorted hash chain @@ -106,6 +108,7 @@ struct tipc_node_bclink { * @list: links to adjacent nodes in sorted list of cluster's nodes * @working_links: number of working links to node (both active and standby) * @link_cnt: number of links to node + * @capabilities: bitmap, indicating peer node's functional capabilities * @signature: node instance identifier * @link_id: local and remote bearer ids of changing link, if any * @publ_list: list of publications @@ -113,6 +116,7 @@ struct tipc_node_bclink { */ struct tipc_node { u32 addr; + struct kref kref; spinlock_t lock; struct net *net; struct hlist_node hash; @@ -125,7 +129,8 @@ struct tipc_node { struct tipc_node_bclink bclink; struct list_head list; int link_cnt; - int working_links; + u16 working_links; + u16 capabilities; u32 signature; u32 link_id; struct list_head publ_list; @@ -134,6 +139,7 @@ struct tipc_node { }; struct tipc_node *tipc_node_find(struct net *net, u32 addr); +void tipc_node_put(struct tipc_node *node); struct tipc_node *tipc_node_create(struct net *net, u32 addr); void tipc_node_stop(struct net *net); void tipc_node_attach_link(struct tipc_node *n_ptr, struct tipc_link *l_ptr); @@ -168,10 +174,12 @@ static inline uint tipc_node_get_mtu(struct net *net, u32 addr, u32 selector) node = tipc_node_find(net, addr); - if (likely(node)) + if (likely(node)) { mtu = node->act_mtus[selector & 1]; - else + tipc_node_put(node); + } else { mtu = MAX_MSG_SIZE; + } return mtu; } diff --git a/net/tipc/server.c b/net/tipc/server.c index eadd4ed45905..77ff03ed1e18 100644 --- a/net/tipc/server.c +++ b/net/tipc/server.c @@ -37,11 +37,13 @@ #include "core.h" #include "socket.h" #include <net/sock.h> +#include <linux/module.h> /* Number of messages to send before rescheduling */ #define MAX_SEND_MSG_COUNT 25 #define MAX_RECV_MSG_COUNT 25 #define CF_CONNECTED 1 +#define CF_SERVER 2 #define sock2con(x) ((struct tipc_conn *)(x)->sk_user_data) @@ -88,9 +90,19 @@ static void tipc_clean_outqueues(struct tipc_conn *con); static void tipc_conn_kref_release(struct kref *kref) { struct tipc_conn *con = container_of(kref, struct tipc_conn, kref); + struct sockaddr_tipc *saddr = con->server->saddr; + struct socket *sock = con->sock; + struct sock *sk; - if (con->sock) { - tipc_sock_release_local(con->sock); + if (sock) { + sk = sock->sk; + if (test_bit(CF_SERVER, &con->flags)) { + __module_get(sock->ops->owner); + __module_get(sk->sk_prot_creator->owner); + } + saddr->scope = -TIPC_NODE_SCOPE; + kernel_bind(sock, (struct sockaddr *)saddr, sizeof(*saddr)); + sock_release(sock); con->sock = NULL; } @@ -281,7 +293,7 @@ static int tipc_accept_from_sock(struct tipc_conn *con) struct tipc_conn *newcon; int ret; - ret = tipc_sock_accept_local(sock, &newsock, O_NONBLOCK); + ret = kernel_accept(sock, &newsock, O_NONBLOCK); if (ret < 0) return ret; @@ -309,7 +321,7 @@ static struct socket *tipc_create_listen_sock(struct tipc_conn *con) struct socket *sock = NULL; int ret; - ret = tipc_sock_create_local(s->net, s->type, &sock); + ret = __sock_create(s->net, AF_TIPC, SOCK_SEQPACKET, 0, &sock, 1); if (ret < 0) return NULL; ret = kernel_setsockopt(sock, SOL_TIPC, TIPC_IMPORTANCE, @@ -337,11 +349,31 @@ static struct socket *tipc_create_listen_sock(struct tipc_conn *con) pr_err("Unknown socket type %d\n", s->type); goto create_err; } + + /* As server's listening socket owner and creator is the same module, + * we have to decrease TIPC module reference count to guarantee that + * it remains zero after the server socket is created, otherwise, + * executing "rmmod" command is unable to make TIPC module deleted + * after TIPC module is inserted successfully. + * + * However, the reference count is ever increased twice in + * sock_create_kern(): one is to increase the reference count of owner + * of TIPC socket's proto_ops struct; another is to increment the + * reference count of owner of TIPC proto struct. Therefore, we must + * decrement the module reference count twice to ensure that it keeps + * zero after server's listening socket is created. Of course, we + * must bump the module reference count twice as well before the socket + * is closed. + */ + module_put(sock->ops->owner); + module_put(sock->sk->sk_prot_creator->owner); + set_bit(CF_SERVER, &con->flags); + return sock; create_err: + kernel_sock_shutdown(sock, SHUT_RDWR); sock_release(sock); - con->sock = NULL; return NULL; } diff --git a/net/tipc/socket.c b/net/tipc/socket.c index b4d4467d0bb0..9074b5cede38 100644 --- a/net/tipc/socket.c +++ b/net/tipc/socket.c @@ -35,7 +35,6 @@ */ #include <linux/rhashtable.h> -#include <linux/jhash.h> #include "core.h" #include "name_table.h" #include "node.h" @@ -74,6 +73,7 @@ * @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 + * @remote: 'connected' peer for dgram/rdm * @node: hash table node * @rcu: rcu struct for tipc_sock */ @@ -96,6 +96,7 @@ struct tipc_sock { bool link_cong; uint sent_unacked; uint rcv_unacked; + struct sockaddr_tipc remote; struct rhash_head node; struct rcu_head rcu; }; @@ -114,13 +115,14 @@ static int tipc_sk_withdraw(struct tipc_sock *tsk, uint scope, static struct tipc_sock *tipc_sk_lookup(struct net *net, u32 portid); static int tipc_sk_insert(struct tipc_sock *tsk); static void tipc_sk_remove(struct tipc_sock *tsk); +static int __tipc_send_stream(struct socket *sock, struct msghdr *m, + size_t dsz); +static int __tipc_sendmsg(struct socket *sock, struct msghdr *m, size_t dsz); static const struct proto_ops packet_ops; static const struct proto_ops stream_ops; static const struct proto_ops msg_ops; - static struct proto tipc_proto; -static struct proto tipc_proto_kern; static const struct nla_policy tipc_nl_sock_policy[TIPC_NLA_SOCK_MAX + 1] = { [TIPC_NLA_SOCK_UNSPEC] = { .type = NLA_UNSPEC }, @@ -130,6 +132,8 @@ static const struct nla_policy tipc_nl_sock_policy[TIPC_NLA_SOCK_MAX + 1] = { [TIPC_NLA_SOCK_HAS_PUBL] = { .type = NLA_FLAG } }; +static const struct rhashtable_params tsk_rht_params; + /* * Revised TIPC socket locking policy: * @@ -338,11 +342,7 @@ static int tipc_sk_create(struct net *net, struct socket *sock, } /* Allocate socket's protocol area */ - if (!kern) - sk = sk_alloc(net, AF_TIPC, GFP_KERNEL, &tipc_proto); - else - sk = sk_alloc(net, AF_TIPC, GFP_KERNEL, &tipc_proto_kern); - + sk = sk_alloc(net, AF_TIPC, GFP_KERNEL, &tipc_proto); if (sk == NULL) return -ENOMEM; @@ -380,75 +380,6 @@ static int tipc_sk_create(struct net *net, struct socket *sock, return 0; } -/** - * tipc_sock_create_local - create TIPC socket from inside TIPC module - * @type: socket type - SOCK_RDM or SOCK_SEQPACKET - * - * We cannot use sock_creat_kern here because it bumps module user count. - * Since socket owner and creator is the same module we must make sure - * that module count remains zero for module local sockets, otherwise - * we cannot do rmmod. - * - * Returns 0 on success, errno otherwise - */ -int tipc_sock_create_local(struct net *net, int type, struct socket **res) -{ - int rc; - - rc = sock_create_lite(AF_TIPC, type, 0, res); - if (rc < 0) { - pr_err("Failed to create kernel socket\n"); - return rc; - } - tipc_sk_create(net, *res, 0, 1); - - return 0; -} - -/** - * tipc_sock_release_local - release socket created by tipc_sock_create_local - * @sock: the socket to be released. - * - * Module reference count is not incremented when such sockets are created, - * so we must keep it from being decremented when they are released. - */ -void tipc_sock_release_local(struct socket *sock) -{ - tipc_release(sock); - sock->ops = NULL; - sock_release(sock); -} - -/** - * tipc_sock_accept_local - accept a connection on a socket created - * with tipc_sock_create_local. Use this function to avoid that - * module reference count is inadvertently incremented. - * - * @sock: the accepting socket - * @newsock: reference to the new socket to be created - * @flags: socket flags - */ - -int tipc_sock_accept_local(struct socket *sock, struct socket **newsock, - int flags) -{ - struct sock *sk = sock->sk; - int ret; - - ret = sock_create_lite(sk->sk_family, sk->sk_type, - sk->sk_protocol, newsock); - if (ret < 0) - return ret; - - ret = tipc_accept(sock, *newsock, flags); - if (ret < 0) { - sock_release(*newsock); - return ret; - } - (*newsock)->ops = sock->ops; - return ret; -} - static void tipc_sk_callback(struct rcu_head *head) { struct tipc_sock *tsk = container_of(head, struct tipc_sock, rcu); @@ -892,7 +823,6 @@ static int tipc_wait_for_sndmsg(struct socket *sock, long *timeo_p) /** * tipc_sendmsg - send message in connectionless manner - * @iocb: if NULL, indicates that socket lock is already held * @sock: socket structure * @m: message to send * @dsz: amount of user data to be sent @@ -904,9 +834,21 @@ 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, +static int tipc_sendmsg(struct socket *sock, struct msghdr *m, size_t dsz) { + struct sock *sk = sock->sk; + int ret; + + lock_sock(sk); + ret = __tipc_sendmsg(sock, m, dsz); + release_sock(sk); + + return ret; +} + +static int __tipc_sendmsg(struct socket *sock, 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); @@ -915,49 +857,40 @@ static int tipc_sendmsg(struct kiocb *iocb, struct socket *sock, u32 dnode, dport; struct sk_buff_head *pktchain = &sk->sk_write_queue; struct sk_buff *skb; - struct tipc_name_seq *seq = &dest->addr.nameseq; + struct tipc_name_seq *seq; struct iov_iter save; u32 mtu; long timeo; int rc; - if (unlikely(!dest)) - return -EDESTADDRREQ; - - if (unlikely((m->msg_namelen < sizeof(*dest)) || - (dest->family != AF_TIPC))) - return -EINVAL; - if (dsz > TIPC_MAX_USER_MSG_SIZE) return -EMSGSIZE; - - if (iocb) - lock_sock(sk); - + if (unlikely(!dest)) { + if (tsk->connected && sock->state == SS_READY) + dest = &tsk->remote; + else + return -EDESTADDRREQ; + } else if (unlikely(m->msg_namelen < sizeof(*dest)) || + dest->family != AF_TIPC) { + return -EINVAL; + } if (unlikely(sock->state != SS_READY)) { - if (sock->state == SS_LISTENING) { - rc = -EPIPE; - goto exit; - } - if (sock->state != SS_UNCONNECTED) { - rc = -EISCONN; - goto exit; - } - if (tsk->published) { - rc = -EOPNOTSUPP; - goto exit; - } + if (sock->state == SS_LISTENING) + return -EPIPE; + if (sock->state != SS_UNCONNECTED) + return -EISCONN; + if (tsk->published) + return -EOPNOTSUPP; if (dest->addrtype == TIPC_ADDR_NAME) { tsk->conn_type = dest->addr.name.name.type; tsk->conn_instance = dest->addr.name.name.instance; } } - + seq = &dest->addr.nameseq; timeo = sock_sndtimeo(sk, m->msg_flags & MSG_DONTWAIT); if (dest->addrtype == TIPC_ADDR_MCAST) { - rc = tipc_sendmcast(sock, seq, m, dsz, timeo); - goto exit; + return tipc_sendmcast(sock, seq, m, dsz, timeo); } else if (dest->addrtype == TIPC_ADDR_NAME) { u32 type = dest->addr.name.name.type; u32 inst = dest->addr.name.name.instance; @@ -972,10 +905,8 @@ static int tipc_sendmsg(struct kiocb *iocb, struct socket *sock, dport = tipc_nametbl_translate(net, type, inst, &dnode); msg_set_destnode(mhdr, dnode); msg_set_destport(mhdr, dport); - if (unlikely(!dport && !dnode)) { - rc = -EHOSTUNREACH; - goto exit; - } + if (unlikely(!dport && !dnode)) + return -EHOSTUNREACH; } else if (dest->addrtype == TIPC_ADDR_ID) { dnode = dest->addr.id.node; msg_set_type(mhdr, TIPC_DIRECT_MSG); @@ -990,7 +921,7 @@ new_mtu: mtu = tipc_node_get_mtu(net, dnode, tsk->portid); rc = tipc_msg_build(mhdr, m, 0, dsz, mtu, pktchain); if (rc < 0) - goto exit; + return rc; do { skb = skb_peek(pktchain); @@ -1013,9 +944,6 @@ new_mtu: if (rc) __skb_queue_purge(pktchain); } while (!rc); -exit: - if (iocb) - release_sock(sk); return rc; } @@ -1052,7 +980,6 @@ static int tipc_wait_for_sndpkt(struct socket *sock, long *timeo_p) /** * tipc_send_stream - send stream-oriented data - * @iocb: (unused) * @sock: socket structure * @m: data to send * @dsz: total length of data to be transmitted @@ -1062,8 +989,19 @@ static int tipc_wait_for_sndpkt(struct socket *sock, long *timeo_p) * Returns the number of bytes sent on success (or partial success), * or errno if no data sent */ -static int tipc_send_stream(struct kiocb *iocb, struct socket *sock, - struct msghdr *m, size_t dsz) +static int tipc_send_stream(struct socket *sock, struct msghdr *m, size_t dsz) +{ + struct sock *sk = sock->sk; + int ret; + + lock_sock(sk); + ret = __tipc_send_stream(sock, m, dsz); + release_sock(sk); + + return ret; +} + +static int __tipc_send_stream(struct socket *sock, struct msghdr *m, size_t dsz) { struct sock *sk = sock->sk; struct net *net = sock_net(sk); @@ -1080,7 +1018,7 @@ static int tipc_send_stream(struct kiocb *iocb, struct socket *sock, /* Handle implied connection establishment */ if (unlikely(dest)) { - rc = tipc_sendmsg(iocb, sock, m, dsz); + rc = __tipc_sendmsg(sock, m, dsz); if (dsz && (dsz == rc)) tsk->sent_unacked = 1; return rc; @@ -1088,15 +1026,11 @@ static int tipc_send_stream(struct kiocb *iocb, struct socket *sock, if (dsz > (uint)INT_MAX) return -EMSGSIZE; - if (iocb) - lock_sock(sk); - if (unlikely(sock->state != SS_CONNECTED)) { if (sock->state == SS_DISCONNECTING) - rc = -EPIPE; + return -EPIPE; else - rc = -ENOTCONN; - goto exit; + return -ENOTCONN; } timeo = sock_sndtimeo(sk, m->msg_flags & MSG_DONTWAIT); @@ -1108,7 +1042,7 @@ next: send = min_t(uint, dsz - sent, TIPC_MAX_USER_MSG_SIZE); rc = tipc_msg_build(mhdr, m, sent, send, mtu, pktchain); if (unlikely(rc < 0)) - goto exit; + return rc; do { if (likely(!tsk_conn_cong(tsk))) { rc = tipc_link_xmit(net, pktchain, dnode, portid); @@ -1133,15 +1067,12 @@ next: if (rc) __skb_queue_purge(pktchain); } while (!rc); -exit: - if (iocb) - release_sock(sk); + return sent ? sent : rc; } /** * tipc_send_packet - send a connection-oriented message - * @iocb: if NULL, indicates that socket lock is already held * @sock: socket structure * @m: message to send * @dsz: length of data to be transmitted @@ -1150,13 +1081,12 @@ exit: * * Returns the number of bytes sent on success, or errno otherwise */ -static int tipc_send_packet(struct kiocb *iocb, struct socket *sock, - struct msghdr *m, size_t dsz) +static int tipc_send_packet(struct socket *sock, struct msghdr *m, size_t dsz) { if (dsz > TIPC_MAX_USER_MSG_SIZE) return -EMSGSIZE; - return tipc_send_stream(iocb, sock, m, dsz); + return tipc_send_stream(sock, m, dsz); } /* tipc_sk_finish_conn - complete the setup of a connection @@ -1317,12 +1247,12 @@ static int tipc_wait_for_rcvmsg(struct socket *sock, long *timeop) err = 0; if (!skb_queue_empty(&sk->sk_receive_queue)) break; - err = sock_intr_errno(timeo); - if (signal_pending(current)) - break; err = -EAGAIN; if (!timeo) break; + err = sock_intr_errno(timeo); + if (signal_pending(current)) + break; } finish_wait(sk_sleep(sk), &wait); *timeop = timeo; @@ -1331,7 +1261,6 @@ static int tipc_wait_for_rcvmsg(struct socket *sock, long *timeop) /** * tipc_recvmsg - receive packet-oriented message - * @iocb: (unused) * @m: descriptor for message info * @buf_len: total size of user buffer area * @flags: receive flags @@ -1341,8 +1270,8 @@ static int tipc_wait_for_rcvmsg(struct socket *sock, long *timeop) * * Returns size of returned message data, errno otherwise */ -static int tipc_recvmsg(struct kiocb *iocb, struct socket *sock, - struct msghdr *m, size_t buf_len, int flags) +static int tipc_recvmsg(struct socket *sock, struct msghdr *m, size_t buf_len, + int flags) { struct sock *sk = sock->sk; struct tipc_sock *tsk = tipc_sk(sk); @@ -1426,7 +1355,6 @@ exit: /** * tipc_recv_stream - receive stream-oriented data - * @iocb: (unused) * @m: descriptor for message info * @buf_len: total size of user buffer area * @flags: receive flags @@ -1436,8 +1364,8 @@ exit: * * Returns size of returned message data, errno otherwise */ -static int tipc_recv_stream(struct kiocb *iocb, struct socket *sock, - struct msghdr *m, size_t buf_len, int flags) +static int tipc_recv_stream(struct socket *sock, struct msghdr *m, + size_t buf_len, int flags) { struct sock *sk = sock->sk; struct tipc_sock *tsk = tipc_sk(sk); @@ -1836,13 +1764,14 @@ static int tipc_sk_enqueue(struct sk_buff_head *inputq, struct sock *sk, int tipc_sk_rcv(struct net *net, struct sk_buff_head *inputq) { u32 dnode, dport = 0; - int err = -TIPC_ERR_NO_PORT; + int err; struct sk_buff *skb; struct tipc_sock *tsk; struct tipc_net *tn; struct sock *sk; while (skb_queue_len(inputq)) { + err = -TIPC_ERR_NO_PORT; skb = NULL; dport = tipc_skb_peek_port(inputq, dport); tsk = tipc_sk_lookup(net, dport); @@ -1909,17 +1838,26 @@ static int tipc_connect(struct socket *sock, struct sockaddr *dest, int destlen, int flags) { struct sock *sk = sock->sk; + struct tipc_sock *tsk = tipc_sk(sk); struct sockaddr_tipc *dst = (struct sockaddr_tipc *)dest; struct msghdr m = {NULL,}; - long timeout = (flags & O_NONBLOCK) ? 0 : tipc_sk(sk)->conn_timeout; + long timeout = (flags & O_NONBLOCK) ? 0 : tsk->conn_timeout; socket_state previous; - int res; + int res = 0; lock_sock(sk); - /* For now, TIPC does not allow use of connect() with DGRAM/RDM types */ + /* DGRAM/RDM connect(), just save the destaddr */ if (sock->state == SS_READY) { - res = -EOPNOTSUPP; + if (dst->family == AF_UNSPEC) { + memset(&tsk->remote, 0, sizeof(struct sockaddr_tipc)); + tsk->connected = 0; + } else if (destlen != sizeof(struct sockaddr_tipc)) { + res = -EINVAL; + } else { + memcpy(&tsk->remote, dest, destlen); + tsk->connected = 1; + } goto exit; } @@ -1947,7 +1885,7 @@ static int tipc_connect(struct socket *sock, struct sockaddr *dest, if (!timeout) m.msg_flags = MSG_DONTWAIT; - res = tipc_sendmsg(NULL, sock, &m, 0); + res = __tipc_sendmsg(sock, &m, 0); if ((res < 0) && (res != -EWOULDBLOCK)) goto exit; @@ -2027,12 +1965,12 @@ static int tipc_wait_for_accept(struct socket *sock, long timeo) err = -EINVAL; if (sock->state != SS_LISTENING) break; - err = sock_intr_errno(timeo); - if (signal_pending(current)) - break; err = -EAGAIN; if (!timeo) break; + err = sock_intr_errno(timeo); + if (signal_pending(current)) + break; } finish_wait(sk_sleep(sk), &wait); return err; @@ -2103,7 +2041,7 @@ static int tipc_accept(struct socket *sock, struct socket *new_sock, int flags) struct msghdr m = {NULL,}; tsk_advance_rx_queue(sk); - tipc_send_packet(NULL, new_sock, &m, 0); + __tipc_send_stream(new_sock, &m, 0); } else { __skb_dequeue(&sk->sk_receive_queue); __skb_queue_head(&new_sk->sk_receive_queue, buf); @@ -2154,7 +2092,6 @@ restart: TIPC_CONN_SHUTDOWN)) tipc_link_xmit_skb(net, skb, dnode, tsk->portid); - tipc_node_remove_conn(net, dnode, tsk->portid); } else { dnode = tsk_peer_node(tsk); @@ -2312,7 +2249,7 @@ static struct tipc_sock *tipc_sk_lookup(struct net *net, u32 portid) struct tipc_sock *tsk; rcu_read_lock(); - tsk = rhashtable_lookup(&tn->sk_rht, &portid); + tsk = rhashtable_lookup_fast(&tn->sk_rht, &portid, tsk_rht_params); if (tsk) sock_hold(&tsk->sk); rcu_read_unlock(); @@ -2334,7 +2271,8 @@ static int tipc_sk_insert(struct tipc_sock *tsk) portid = TIPC_MIN_PORT; tsk->portid = portid; sock_hold(&tsk->sk); - if (rhashtable_lookup_insert(&tn->sk_rht, &tsk->node)) + if (!rhashtable_lookup_insert_fast(&tn->sk_rht, &tsk->node, + tsk_rht_params)) return 0; sock_put(&tsk->sk); } @@ -2347,26 +2285,27 @@ static void tipc_sk_remove(struct tipc_sock *tsk) struct sock *sk = &tsk->sk; struct tipc_net *tn = net_generic(sock_net(sk), tipc_net_id); - if (rhashtable_remove(&tn->sk_rht, &tsk->node)) { + if (!rhashtable_remove_fast(&tn->sk_rht, &tsk->node, tsk_rht_params)) { WARN_ON(atomic_read(&sk->sk_refcnt) == 1); __sock_put(sk); } } +static const struct rhashtable_params tsk_rht_params = { + .nelem_hint = 192, + .head_offset = offsetof(struct tipc_sock, node), + .key_offset = offsetof(struct tipc_sock, portid), + .key_len = sizeof(u32), /* portid */ + .max_size = 1048576, + .min_size = 256, + .automatic_shrinking = true, +}; + int tipc_sk_rht_init(struct net *net) { struct tipc_net *tn = net_generic(net, tipc_net_id); - struct rhashtable_params rht_params = { - .nelem_hint = 192, - .head_offset = offsetof(struct tipc_sock, node), - .key_offset = offsetof(struct tipc_sock, portid), - .key_len = sizeof(u32), /* portid */ - .hashfn = jhash, - .max_shift = 20, /* 1M */ - .min_shift = 8, /* 256 */ - }; - return rhashtable_init(&tn->sk_rht, &rht_params); + return rhashtable_init(&tn->sk_rht, &tsk_rht_params); } void tipc_sk_rht_destroy(struct net *net) @@ -2609,12 +2548,6 @@ static struct proto tipc_proto = { .sysctl_rmem = sysctl_tipc_rmem }; -static struct proto tipc_proto_kern = { - .name = "TIPC", - .obj_size = sizeof(struct tipc_sock), - .sysctl_rmem = sysctl_tipc_rmem -}; - /** * tipc_socket_init - initialize TIPC socket interface * diff --git a/net/tipc/socket.h b/net/tipc/socket.h index 238f1b7bd9bd..bf6551389522 100644 --- a/net/tipc/socket.h +++ b/net/tipc/socket.h @@ -44,10 +44,6 @@ SKB_TRUESIZE(TIPC_MAX_USER_MSG_SIZE)) int tipc_socket_init(void); void tipc_socket_stop(void); -int tipc_sock_create_local(struct net *net, int type, struct socket **res); -void tipc_sock_release_local(struct socket *sock); -int tipc_sock_accept_local(struct socket *sock, struct socket **newsock, - int flags); int tipc_sk_rcv(struct net *net, struct sk_buff_head *inputq); void tipc_sk_mcast_rcv(struct net *net, struct sk_buff_head *arrvq, struct sk_buff_head *inputq); diff --git a/net/tipc/subscr.c b/net/tipc/subscr.c index 72c339e432aa..1c147c869c2e 100644 --- a/net/tipc/subscr.c +++ b/net/tipc/subscr.c @@ -162,19 +162,6 @@ static void subscr_del(struct tipc_subscription *sub) atomic_dec(&tn->subscription_count); } -/** - * subscr_terminate - terminate communication with a subscriber - * - * Note: Must call it in process context since it might sleep. - */ -static void subscr_terminate(struct tipc_subscription *sub) -{ - struct tipc_subscriber *subscriber = sub->subscriber; - struct tipc_net *tn = net_generic(sub->net, tipc_net_id); - - tipc_conn_terminate(tn->topsrv, subscriber->conid); -} - static void subscr_release(struct tipc_subscriber *subscriber) { struct tipc_subscription *sub; @@ -312,16 +299,14 @@ static void subscr_conn_msg_event(struct net *net, int conid, { struct tipc_subscriber *subscriber = usr_data; struct tipc_subscription *sub = NULL; + struct tipc_net *tn = net_generic(net, tipc_net_id); spin_lock_bh(&subscriber->lock); - if (subscr_subscribe(net, (struct tipc_subscr *)buf, subscriber, - &sub) < 0) { - spin_unlock_bh(&subscriber->lock); - subscr_terminate(sub); - return; - } + subscr_subscribe(net, (struct tipc_subscr *)buf, subscriber, &sub); if (sub) tipc_nametbl_subscribe(sub); + else + tipc_conn_terminate(tn->topsrv, subscriber->conid); spin_unlock_bh(&subscriber->lock); } diff --git a/net/tipc/udp_media.c b/net/tipc/udp_media.c new file mode 100644 index 000000000000..66deebc66aa1 --- /dev/null +++ b/net/tipc/udp_media.c @@ -0,0 +1,448 @@ +/* net/tipc/udp_media.c: IP bearer support for TIPC + * + * Copyright (c) 2015, Ericsson AB + * All rights reserved. + * + * Redistribution and use in source and binary forms, with or without + * modification, are permitted provided that the following conditions are met: + * + * 1. Redistributions of source code must retain the above copyright + * notice, this list of conditions and the following disclaimer. + * 2. Redistributions in binary form must reproduce the above copyright + * notice, this list of conditions and the following disclaimer in the + * documentation and/or other materials provided with the distribution. + * 3. Neither the names of the copyright holders nor the names of its + * contributors may be used to endorse or promote products derived from + * this software without specific prior written permission. + * + * Alternatively, this software may be distributed under the terms of the + * GNU General Public License ("GPL") version 2 as published by the Free + * Software Foundation. + * + * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS" + * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE + * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE + * ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE + * LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR + * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF + * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS + * INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN + * CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) + * ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE + * POSSIBILITY OF SUCH DAMAGE. + */ + +#include <linux/socket.h> +#include <linux/ip.h> +#include <linux/udp.h> +#include <linux/inet.h> +#include <linux/inetdevice.h> +#include <linux/igmp.h> +#include <linux/kernel.h> +#include <linux/workqueue.h> +#include <linux/list.h> +#include <net/sock.h> +#include <net/ip.h> +#include <net/udp_tunnel.h> +#include <net/addrconf.h> +#include <linux/tipc_netlink.h> +#include "core.h" +#include "bearer.h" + +/* IANA assigned UDP port */ +#define UDP_PORT_DEFAULT 6118 + +static const struct nla_policy tipc_nl_udp_policy[TIPC_NLA_UDP_MAX + 1] = { + [TIPC_NLA_UDP_UNSPEC] = {.type = NLA_UNSPEC}, + [TIPC_NLA_UDP_LOCAL] = {.type = NLA_BINARY, + .len = sizeof(struct sockaddr_storage)}, + [TIPC_NLA_UDP_REMOTE] = {.type = NLA_BINARY, + .len = sizeof(struct sockaddr_storage)}, +}; + +/** + * struct udp_media_addr - IP/UDP addressing information + * + * This is the bearer level originating address used in neighbor discovery + * messages, and all fields should be in network byte order + */ +struct udp_media_addr { + __be16 proto; + __be16 udp_port; + union { + struct in_addr ipv4; + struct in6_addr ipv6; + }; +}; + +/** + * struct udp_bearer - ip/udp bearer data structure + * @bearer: associated generic tipc bearer + * @ubsock: bearer associated socket + * @ifindex: local address scope + * @work: used to schedule deferred work on a bearer + */ +struct udp_bearer { + struct tipc_bearer __rcu *bearer; + struct socket *ubsock; + u32 ifindex; + struct work_struct work; +}; + +/* udp_media_addr_set - convert a ip/udp address to a TIPC media address */ +static void tipc_udp_media_addr_set(struct tipc_media_addr *addr, + struct udp_media_addr *ua) +{ + memset(addr, 0, sizeof(struct tipc_media_addr)); + addr->media_id = TIPC_MEDIA_TYPE_UDP; + memcpy(addr->value, ua, sizeof(struct udp_media_addr)); + if (ntohs(ua->proto) == ETH_P_IP) { + if (ipv4_is_multicast(ua->ipv4.s_addr)) + addr->broadcast = 1; + } else if (ntohs(ua->proto) == ETH_P_IPV6) { + if (ipv6_addr_type(&ua->ipv6) & IPV6_ADDR_MULTICAST) + addr->broadcast = 1; + } else { + pr_err("Invalid UDP media address\n"); + } +} + +/* tipc_udp_addr2str - convert ip/udp address to string */ +static int tipc_udp_addr2str(struct tipc_media_addr *a, char *buf, int size) +{ + struct udp_media_addr *ua = (struct udp_media_addr *)&a->value; + + if (ntohs(ua->proto) == ETH_P_IP) + snprintf(buf, size, "%pI4:%u", &ua->ipv4, ntohs(ua->udp_port)); + else if (ntohs(ua->proto) == ETH_P_IPV6) + snprintf(buf, size, "%pI6:%u", &ua->ipv6, ntohs(ua->udp_port)); + else + pr_err("Invalid UDP media address\n"); + return 0; +} + +/* tipc_udp_msg2addr - extract an ip/udp address from a TIPC ndisc message */ +static int tipc_udp_msg2addr(struct tipc_bearer *b, struct tipc_media_addr *a, + char *msg) +{ + struct udp_media_addr *ua; + + ua = (struct udp_media_addr *) (msg + TIPC_MEDIA_ADDR_OFFSET); + if (msg[TIPC_MEDIA_TYPE_OFFSET] != TIPC_MEDIA_TYPE_UDP) + return -EINVAL; + tipc_udp_media_addr_set(a, ua); + return 0; +} + +/* tipc_udp_addr2msg - write an ip/udp address to a TIPC ndisc message */ +static int tipc_udp_addr2msg(char *msg, struct tipc_media_addr *a) +{ + memset(msg, 0, TIPC_MEDIA_INFO_SIZE); + msg[TIPC_MEDIA_TYPE_OFFSET] = TIPC_MEDIA_TYPE_UDP; + memcpy(msg + TIPC_MEDIA_ADDR_OFFSET, a->value, + sizeof(struct udp_media_addr)); + return 0; +} + +/* tipc_send_msg - enqueue a send request */ +static int tipc_udp_send_msg(struct net *net, struct sk_buff *skb, + struct tipc_bearer *b, + struct tipc_media_addr *dest) +{ + int ttl, err = 0; + struct udp_bearer *ub; + struct udp_media_addr *dst = (struct udp_media_addr *)&dest->value; + struct udp_media_addr *src = (struct udp_media_addr *)&b->addr.value; + struct sk_buff *clone; + struct rtable *rt; + + clone = skb_clone(skb, GFP_ATOMIC); + skb_set_inner_protocol(clone, htons(ETH_P_TIPC)); + ub = rcu_dereference_rtnl(b->media_ptr); + if (!ub) { + err = -ENODEV; + goto tx_error; + } + if (dst->proto == htons(ETH_P_IP)) { + struct flowi4 fl = { + .daddr = dst->ipv4.s_addr, + .saddr = src->ipv4.s_addr, + .flowi4_mark = clone->mark, + .flowi4_proto = IPPROTO_UDP + }; + rt = ip_route_output_key(net, &fl); + if (IS_ERR(rt)) { + err = PTR_ERR(rt); + goto tx_error; + } + ttl = ip4_dst_hoplimit(&rt->dst); + err = udp_tunnel_xmit_skb(rt, ub->ubsock->sk, clone, + src->ipv4.s_addr, + dst->ipv4.s_addr, 0, ttl, 0, + src->udp_port, dst->udp_port, + false, true); + if (err < 0) { + ip_rt_put(rt); + goto tx_error; + } +#if IS_ENABLED(CONFIG_IPV6) + } else { + struct dst_entry *ndst; + struct flowi6 fl6 = { + .flowi6_oif = ub->ifindex, + .daddr = dst->ipv6, + .saddr = src->ipv6, + .flowi6_proto = IPPROTO_UDP + }; + err = ipv6_stub->ipv6_dst_lookup(ub->ubsock->sk, &ndst, &fl6); + if (err) + goto tx_error; + ttl = ip6_dst_hoplimit(ndst); + err = udp_tunnel6_xmit_skb(ndst, ub->ubsock->sk, clone, + ndst->dev, &src->ipv6, + &dst->ipv6, 0, ttl, src->udp_port, + dst->udp_port, false); +#endif + } + return err; + +tx_error: + kfree_skb(clone); + return err; +} + +/* tipc_udp_recv - read data from bearer socket */ +static int tipc_udp_recv(struct sock *sk, struct sk_buff *skb) +{ + struct udp_bearer *ub; + struct tipc_bearer *b; + + ub = rcu_dereference_sk_user_data(sk); + if (!ub) { + pr_err_ratelimited("Failed to get UDP bearer reference"); + kfree_skb(skb); + return 0; + } + + skb_pull(skb, sizeof(struct udphdr)); + rcu_read_lock(); + b = rcu_dereference_rtnl(ub->bearer); + + if (b) { + tipc_rcv(sock_net(sk), skb, b); + rcu_read_unlock(); + return 0; + } + rcu_read_unlock(); + kfree_skb(skb); + return 0; +} + +static int enable_mcast(struct udp_bearer *ub, struct udp_media_addr *remote) +{ + int err = 0; + struct ip_mreqn mreqn; + struct sock *sk = ub->ubsock->sk; + + if (ntohs(remote->proto) == ETH_P_IP) { + if (!ipv4_is_multicast(remote->ipv4.s_addr)) + return 0; + mreqn.imr_multiaddr = remote->ipv4; + mreqn.imr_ifindex = ub->ifindex; + err = ip_mc_join_group(sk, &mreqn); +#if IS_ENABLED(CONFIG_IPV6) + } else { + if (!ipv6_addr_is_multicast(&remote->ipv6)) + return 0; + err = ipv6_stub->ipv6_sock_mc_join(sk, ub->ifindex, + &remote->ipv6); +#endif + } + return err; +} + +/** + * parse_options - build local/remote addresses from configuration + * @attrs: netlink config data + * @ub: UDP bearer instance + * @local: local bearer IP address/port + * @remote: peer or multicast IP/port + */ +static int parse_options(struct nlattr *attrs[], struct udp_bearer *ub, + struct udp_media_addr *local, + struct udp_media_addr *remote) +{ + struct nlattr *opts[TIPC_NLA_UDP_MAX + 1]; + struct sockaddr_storage *sa_local, *sa_remote; + + if (!attrs[TIPC_NLA_BEARER_UDP_OPTS]) + goto err; + if (nla_parse_nested(opts, TIPC_NLA_UDP_MAX, + attrs[TIPC_NLA_BEARER_UDP_OPTS], + tipc_nl_udp_policy)) + goto err; + if (opts[TIPC_NLA_UDP_LOCAL] && opts[TIPC_NLA_UDP_REMOTE]) { + sa_local = nla_data(opts[TIPC_NLA_UDP_LOCAL]); + sa_remote = nla_data(opts[TIPC_NLA_UDP_REMOTE]); + } else { +err: + pr_err("Invalid UDP bearer configuration"); + return -EINVAL; + } + if ((sa_local->ss_family & sa_remote->ss_family) == AF_INET) { + struct sockaddr_in *ip4; + + ip4 = (struct sockaddr_in *)sa_local; + local->proto = htons(ETH_P_IP); + local->udp_port = ip4->sin_port; + local->ipv4.s_addr = ip4->sin_addr.s_addr; + + ip4 = (struct sockaddr_in *)sa_remote; + remote->proto = htons(ETH_P_IP); + remote->udp_port = ip4->sin_port; + remote->ipv4.s_addr = ip4->sin_addr.s_addr; + return 0; + +#if IS_ENABLED(CONFIG_IPV6) + } else if ((sa_local->ss_family & sa_remote->ss_family) == AF_INET6) { + struct sockaddr_in6 *ip6; + + ip6 = (struct sockaddr_in6 *)sa_local; + local->proto = htons(ETH_P_IPV6); + local->udp_port = ip6->sin6_port; + local->ipv6 = ip6->sin6_addr; + ub->ifindex = ip6->sin6_scope_id; + + ip6 = (struct sockaddr_in6 *)sa_remote; + remote->proto = htons(ETH_P_IPV6); + remote->udp_port = ip6->sin6_port; + remote->ipv6 = ip6->sin6_addr; + return 0; +#endif + } + return -EADDRNOTAVAIL; +} + +/** + * tipc_udp_enable - callback to create a new udp bearer instance + * @net: network namespace + * @b: pointer to generic tipc_bearer + * @attrs: netlink bearer configuration + * + * validate the bearer parameters and initialize the udp bearer + * rtnl_lock should be held + */ +static int tipc_udp_enable(struct net *net, struct tipc_bearer *b, + struct nlattr *attrs[]) +{ + int err = -EINVAL; + struct udp_bearer *ub; + struct udp_media_addr *remote; + struct udp_media_addr local = {0}; + struct udp_port_cfg udp_conf = {0}; + struct udp_tunnel_sock_cfg tuncfg = {NULL}; + + ub = kzalloc(sizeof(*ub), GFP_ATOMIC); + if (!ub) + return -ENOMEM; + + remote = (struct udp_media_addr *)&b->bcast_addr.value; + memset(remote, 0, sizeof(struct udp_media_addr)); + err = parse_options(attrs, ub, &local, remote); + if (err) + goto err; + + b->bcast_addr.media_id = TIPC_MEDIA_TYPE_UDP; + b->bcast_addr.broadcast = 1; + rcu_assign_pointer(b->media_ptr, ub); + rcu_assign_pointer(ub->bearer, b); + tipc_udp_media_addr_set(&b->addr, &local); + if (local.proto == htons(ETH_P_IP)) { + struct net_device *dev; + + dev = __ip_dev_find(net, local.ipv4.s_addr, false); + if (!dev) { + err = -ENODEV; + goto err; + } + udp_conf.family = AF_INET; + udp_conf.local_ip.s_addr = htonl(INADDR_ANY); + udp_conf.use_udp_checksums = false; + ub->ifindex = dev->ifindex; + b->mtu = dev->mtu - sizeof(struct iphdr) + - sizeof(struct udphdr); +#if IS_ENABLED(CONFIG_IPV6) + } else if (local.proto == htons(ETH_P_IPV6)) { + udp_conf.family = AF_INET6; + udp_conf.use_udp6_tx_checksums = true; + udp_conf.use_udp6_rx_checksums = true; + udp_conf.local_ip6 = in6addr_any; + b->mtu = 1280; +#endif + } else { + err = -EAFNOSUPPORT; + goto err; + } + udp_conf.local_udp_port = local.udp_port; + err = udp_sock_create(net, &udp_conf, &ub->ubsock); + if (err) + goto err; + tuncfg.sk_user_data = ub; + tuncfg.encap_type = 1; + tuncfg.encap_rcv = tipc_udp_recv; + tuncfg.encap_destroy = NULL; + setup_udp_tunnel_sock(net, ub->ubsock, &tuncfg); + + if (enable_mcast(ub, remote)) + goto err; + return 0; +err: + kfree(ub); + return err; +} + +/* cleanup_bearer - break the socket/bearer association */ +static void cleanup_bearer(struct work_struct *work) +{ + struct udp_bearer *ub = container_of(work, struct udp_bearer, work); + + if (ub->ubsock) + udp_tunnel_sock_release(ub->ubsock); + synchronize_net(); + kfree(ub); +} + +/* tipc_udp_disable - detach bearer from socket */ +static void tipc_udp_disable(struct tipc_bearer *b) +{ + struct udp_bearer *ub; + + ub = rcu_dereference_rtnl(b->media_ptr); + if (!ub) { + pr_err("UDP bearer instance not found\n"); + return; + } + if (ub->ubsock) + sock_set_flag(ub->ubsock->sk, SOCK_DEAD); + RCU_INIT_POINTER(b->media_ptr, NULL); + RCU_INIT_POINTER(ub->bearer, NULL); + + /* sock_release need to be done outside of rtnl lock */ + INIT_WORK(&ub->work, cleanup_bearer); + schedule_work(&ub->work); +} + +struct tipc_media udp_media_info = { + .send_msg = tipc_udp_send_msg, + .enable_media = tipc_udp_enable, + .disable_media = tipc_udp_disable, + .addr2str = tipc_udp_addr2str, + .addr2msg = tipc_udp_addr2msg, + .msg2addr = tipc_udp_msg2addr, + .priority = TIPC_DEF_LINK_PRI, + .tolerance = TIPC_DEF_LINK_TOL, + .window = TIPC_DEF_LINK_WIN, + .type_id = TIPC_MEDIA_TYPE_UDP, + .hwaddr_len = 0, + .name = "udp" +}; diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c index 526b6edab018..5266ea7b922b 100644 --- a/net/unix/af_unix.c +++ b/net/unix/af_unix.c @@ -305,7 +305,7 @@ static struct sock *unix_find_socket_byinode(struct inode *i) &unix_socket_table[i->i_ino & (UNIX_HASH_SIZE - 1)]) { struct dentry *dentry = unix_sk(s)->path.dentry; - if (dentry && dentry->d_inode == i) { + if (dentry && d_backing_inode(dentry) == i) { sock_hold(s); goto found; } @@ -516,20 +516,15 @@ static unsigned int unix_dgram_poll(struct file *, struct socket *, poll_table *); static int unix_ioctl(struct socket *, unsigned int, unsigned long); static int unix_shutdown(struct socket *, int); -static int unix_stream_sendmsg(struct kiocb *, struct socket *, - struct msghdr *, size_t); -static int unix_stream_recvmsg(struct kiocb *, struct socket *, - struct msghdr *, size_t, int); -static int unix_dgram_sendmsg(struct kiocb *, struct socket *, - struct msghdr *, size_t); -static int unix_dgram_recvmsg(struct kiocb *, struct socket *, - struct msghdr *, size_t, int); +static int unix_stream_sendmsg(struct socket *, struct msghdr *, size_t); +static int unix_stream_recvmsg(struct socket *, struct msghdr *, size_t, int); +static int unix_dgram_sendmsg(struct socket *, struct msghdr *, size_t); +static int unix_dgram_recvmsg(struct socket *, struct msghdr *, size_t, int); static int unix_dgram_connect(struct socket *, struct sockaddr *, int, int); -static int unix_seqpacket_sendmsg(struct kiocb *, struct socket *, - struct msghdr *, size_t); -static int unix_seqpacket_recvmsg(struct kiocb *, struct socket *, - struct msghdr *, size_t, int); +static int unix_seqpacket_sendmsg(struct socket *, struct msghdr *, size_t); +static int unix_seqpacket_recvmsg(struct socket *, struct msghdr *, size_t, + int); static int unix_set_peek_off(struct sock *sk, int val) { @@ -783,7 +778,7 @@ static struct sock *unix_find_other(struct net *net, err = kern_path(sunname->sun_path, LOOKUP_FOLLOW, &path); if (err) goto fail; - inode = path.dentry->d_inode; + inode = d_backing_inode(path.dentry); err = inode_permission(inode, MAY_WRITE); if (err) goto put_fail; @@ -844,7 +839,7 @@ static int unix_mknod(const char *sun_path, umode_t mode, struct path *res) */ err = security_path_mknod(&path, dentry, mode, 0); if (!err) { - err = vfs_mknod(path.dentry->d_inode, dentry, mode, 0); + err = vfs_mknod(d_inode(path.dentry), dentry, mode, 0); if (!err) { res->mnt = mntget(path.mnt); res->dentry = dget(dentry); @@ -910,7 +905,7 @@ static int unix_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len) goto out_up; } addr->hash = UNIX_HASH_SIZE; - hash = path.dentry->d_inode->i_ino & (UNIX_HASH_SIZE-1); + hash = d_backing_inode(path.dentry)->i_ino & (UNIX_HASH_SIZE-1); spin_lock(&unix_table_lock); u->path = path; list = &unix_socket_table[hash]; @@ -1442,8 +1437,8 @@ static void maybe_add_creds(struct sk_buff *skb, const struct socket *sock, * Send AF_UNIX data. */ -static int unix_dgram_sendmsg(struct kiocb *kiocb, struct socket *sock, - struct msghdr *msg, size_t len) +static int unix_dgram_sendmsg(struct socket *sock, struct msghdr *msg, + size_t len) { struct sock *sk = sock->sk; struct net *net = sock_net(sk); @@ -1622,8 +1617,8 @@ out: */ #define UNIX_SKB_FRAGS_SZ (PAGE_SIZE << get_order(32768)) -static int unix_stream_sendmsg(struct kiocb *kiocb, struct socket *sock, - struct msghdr *msg, size_t len) +static int unix_stream_sendmsg(struct socket *sock, struct msghdr *msg, + size_t len) { struct sock *sk = sock->sk; struct sock *other = NULL; @@ -1725,8 +1720,8 @@ out_err: return sent ? : err; } -static int unix_seqpacket_sendmsg(struct kiocb *kiocb, struct socket *sock, - struct msghdr *msg, size_t len) +static int unix_seqpacket_sendmsg(struct socket *sock, struct msghdr *msg, + size_t len) { int err; struct sock *sk = sock->sk; @@ -1741,19 +1736,18 @@ static int unix_seqpacket_sendmsg(struct kiocb *kiocb, struct socket *sock, if (msg->msg_namelen) msg->msg_namelen = 0; - return unix_dgram_sendmsg(kiocb, sock, msg, len); + return unix_dgram_sendmsg(sock, msg, len); } -static int unix_seqpacket_recvmsg(struct kiocb *iocb, struct socket *sock, - struct msghdr *msg, size_t size, - int flags) +static int unix_seqpacket_recvmsg(struct socket *sock, struct msghdr *msg, + size_t size, int flags) { struct sock *sk = sock->sk; if (sk->sk_state != TCP_ESTABLISHED) return -ENOTCONN; - return unix_dgram_recvmsg(iocb, sock, msg, size, flags); + return unix_dgram_recvmsg(sock, msg, size, flags); } static void unix_copy_addr(struct msghdr *msg, struct sock *sk) @@ -1766,9 +1760,8 @@ static void unix_copy_addr(struct msghdr *msg, struct sock *sk) } } -static int unix_dgram_recvmsg(struct kiocb *iocb, struct socket *sock, - struct msghdr *msg, size_t size, - int flags) +static int unix_dgram_recvmsg(struct socket *sock, struct msghdr *msg, + size_t size, int flags) { struct scm_cookie scm; struct sock *sk = sock->sk; @@ -1900,9 +1893,8 @@ static unsigned int unix_skb_len(const struct sk_buff *skb) return skb->len - UNIXCB(skb).consumed; } -static int unix_stream_recvmsg(struct kiocb *iocb, struct socket *sock, - struct msghdr *msg, size_t size, - int flags) +static int unix_stream_recvmsg(struct socket *sock, struct msghdr *msg, + size_t size, int flags) { struct scm_cookie scm; struct sock *sk = sock->sk; diff --git a/net/unix/diag.c b/net/unix/diag.c index ef542fbca9fe..c512f64d5287 100644 --- a/net/unix/diag.c +++ b/net/unix/diag.c @@ -25,7 +25,7 @@ static int sk_diag_dump_vfs(struct sock *sk, struct sk_buff *nlskb) if (dentry) { struct unix_diag_vfs uv = { - .udiag_vfs_ino = dentry->d_inode->i_ino, + .udiag_vfs_ino = d_backing_inode(dentry)->i_ino, .udiag_vfs_dev = dentry->d_sb->s_dev, }; diff --git a/net/unix/garbage.c b/net/unix/garbage.c index 99f7012b23b9..a73a226f2d33 100644 --- a/net/unix/garbage.c +++ b/net/unix/garbage.c @@ -95,39 +95,36 @@ static DECLARE_WAIT_QUEUE_HEAD(unix_gc_wait); unsigned int unix_tot_inflight; - struct sock *unix_get_socket(struct file *filp) { struct sock *u_sock = NULL; struct inode *inode = file_inode(filp); - /* - * Socket ? - */ + /* Socket ? */ if (S_ISSOCK(inode->i_mode) && !(filp->f_mode & FMODE_PATH)) { struct socket *sock = SOCKET_I(inode); struct sock *s = sock->sk; - /* - * PF_UNIX ? - */ + /* PF_UNIX ? */ if (s && sock->ops && sock->ops->family == PF_UNIX) u_sock = s; } return u_sock; } -/* - * Keep the number of times in flight count for the file - * descriptor if it is for an AF_UNIX socket. +/* Keep the number of times in flight count for the file + * descriptor if it is for an AF_UNIX socket. */ void unix_inflight(struct file *fp) { struct sock *s = unix_get_socket(fp); + if (s) { struct unix_sock *u = unix_sk(s); + spin_lock(&unix_gc_lock); + if (atomic_long_inc_return(&u->inflight) == 1) { BUG_ON(!list_empty(&u->link)); list_add_tail(&u->link, &gc_inflight_list); @@ -142,10 +139,13 @@ void unix_inflight(struct file *fp) void unix_notinflight(struct file *fp) { struct sock *s = unix_get_socket(fp); + if (s) { struct unix_sock *u = unix_sk(s); + spin_lock(&unix_gc_lock); BUG_ON(list_empty(&u->link)); + if (atomic_long_dec_and_test(&u->inflight)) list_del_init(&u->link); unix_tot_inflight--; @@ -161,32 +161,27 @@ static void scan_inflight(struct sock *x, void (*func)(struct unix_sock *), spin_lock(&x->sk_receive_queue.lock); skb_queue_walk_safe(&x->sk_receive_queue, skb, next) { - /* - * Do we have file descriptors ? - */ + /* Do we have file descriptors ? */ if (UNIXCB(skb).fp) { bool hit = false; - /* - * Process the descriptors of this socket - */ + /* Process the descriptors of this socket */ int nfd = UNIXCB(skb).fp->count; struct file **fp = UNIXCB(skb).fp->fp; + while (nfd--) { - /* - * Get the socket the fd matches - * if it indeed does so - */ + /* Get the socket the fd matches if it indeed does so */ struct sock *sk = unix_get_socket(*fp++); + if (sk) { struct unix_sock *u = unix_sk(sk); - /* - * Ignore non-candidates, they could + /* Ignore non-candidates, they could * have been added to the queues after * starting the garbage collection */ if (test_bit(UNIX_GC_CANDIDATE, &u->gc_flags)) { hit = true; + func(u); } } @@ -203,24 +198,22 @@ static void scan_inflight(struct sock *x, void (*func)(struct unix_sock *), static void scan_children(struct sock *x, void (*func)(struct unix_sock *), struct sk_buff_head *hitlist) { - if (x->sk_state != TCP_LISTEN) + if (x->sk_state != TCP_LISTEN) { scan_inflight(x, func, hitlist); - else { + } else { struct sk_buff *skb; struct sk_buff *next; struct unix_sock *u; LIST_HEAD(embryos); - /* - * For a listening socket collect the queued embryos + /* For a listening socket collect the queued embryos * and perform a scan on them as well. */ spin_lock(&x->sk_receive_queue.lock); skb_queue_walk_safe(&x->sk_receive_queue, skb, next) { u = unix_sk(skb->sk); - /* - * An embryo cannot be in-flight, so it's safe + /* An embryo cannot be in-flight, so it's safe * to use the list link. */ BUG_ON(!list_empty(&u->link)); @@ -249,8 +242,7 @@ static void inc_inflight(struct unix_sock *usk) static void inc_inflight_move_tail(struct unix_sock *u) { atomic_long_inc(&u->inflight); - /* - * If this still might be part of a cycle, move it to the end + /* If this still might be part of a cycle, move it to the end * of the list, so that it's checked even if it was already * passed over */ @@ -263,8 +255,7 @@ static bool gc_in_progress; void wait_for_unix_gc(void) { - /* - * If number of inflight sockets is insane, + /* If number of inflight sockets is insane, * force a garbage collect right now. */ if (unix_tot_inflight > UNIX_INFLIGHT_TRIGGER_GC && !gc_in_progress) @@ -288,8 +279,7 @@ void unix_gc(void) goto out; gc_in_progress = true; - /* - * First, select candidates for garbage collection. Only + /* First, select candidates for garbage collection. Only * in-flight sockets are considered, and from those only ones * which don't have any external reference. * @@ -320,15 +310,13 @@ void unix_gc(void) } } - /* - * Now remove all internal in-flight reference to children of + /* Now remove all internal in-flight reference to children of * the candidates. */ list_for_each_entry(u, &gc_candidates, link) scan_children(&u->sk, dec_inflight, NULL); - /* - * Restore the references for children of all candidates, + /* Restore the references for children of all candidates, * which have remaining references. Do this recursively, so * only those remain, which form cyclic references. * @@ -350,8 +338,7 @@ void unix_gc(void) } list_del(&cursor); - /* - * not_cycle_list contains those sockets which do not make up a + /* not_cycle_list contains those sockets which do not make up a * cycle. Restore these to the inflight list. */ while (!list_empty(¬_cycle_list)) { @@ -360,8 +347,7 @@ void unix_gc(void) list_move_tail(&u->link, &gc_inflight_list); } - /* - * Now gc_candidates contains only garbage. Restore original + /* Now gc_candidates contains only garbage. Restore original * inflight counters for these as well, and remove the skbuffs * which are creating the cycle(s). */ diff --git a/net/vmw_vsock/af_vsock.c b/net/vmw_vsock/af_vsock.c index 1d0e39c9a3e2..2ec86e652a19 100644 --- a/net/vmw_vsock/af_vsock.c +++ b/net/vmw_vsock/af_vsock.c @@ -949,8 +949,8 @@ static unsigned int vsock_poll(struct file *file, struct socket *sock, return mask; } -static int vsock_dgram_sendmsg(struct kiocb *kiocb, struct socket *sock, - struct msghdr *msg, size_t len) +static int vsock_dgram_sendmsg(struct socket *sock, struct msghdr *msg, + size_t len) { int err; struct sock *sk; @@ -1062,11 +1062,10 @@ out: return err; } -static int vsock_dgram_recvmsg(struct kiocb *kiocb, struct socket *sock, - struct msghdr *msg, size_t len, int flags) +static int vsock_dgram_recvmsg(struct socket *sock, struct msghdr *msg, + size_t len, int flags) { - return transport->dgram_dequeue(kiocb, vsock_sk(sock->sk), msg, len, - flags); + return transport->dgram_dequeue(vsock_sk(sock->sk), msg, len, flags); } static const struct proto_ops vsock_dgram_ops = { @@ -1505,8 +1504,8 @@ static int vsock_stream_getsockopt(struct socket *sock, return 0; } -static int vsock_stream_sendmsg(struct kiocb *kiocb, struct socket *sock, - struct msghdr *msg, size_t len) +static int vsock_stream_sendmsg(struct socket *sock, struct msghdr *msg, + size_t len) { struct sock *sk; struct vsock_sock *vsk; @@ -1644,9 +1643,8 @@ out: static int -vsock_stream_recvmsg(struct kiocb *kiocb, - struct socket *sock, - struct msghdr *msg, size_t len, int flags) +vsock_stream_recvmsg(struct socket *sock, struct msghdr *msg, size_t len, + int flags) { struct sock *sk; struct vsock_sock *vsk; diff --git a/net/vmw_vsock/vmci_transport.c b/net/vmw_vsock/vmci_transport.c index 7f3255084a6c..c294da095461 100644 --- a/net/vmw_vsock/vmci_transport.c +++ b/net/vmw_vsock/vmci_transport.c @@ -1730,8 +1730,7 @@ static int vmci_transport_dgram_enqueue( return err - sizeof(*dg); } -static int vmci_transport_dgram_dequeue(struct kiocb *kiocb, - struct vsock_sock *vsk, +static int vmci_transport_dgram_dequeue(struct vsock_sock *vsk, struct msghdr *msg, size_t len, int flags) { diff --git a/net/wireless/Kconfig b/net/wireless/Kconfig index 29c8675f9a11..4f5543dd2524 100644 --- a/net/wireless/Kconfig +++ b/net/wireless/Kconfig @@ -175,13 +175,21 @@ config CFG80211_INTERNAL_REGDB Most distributions have a CRDA package. So if unsure, say N. config CFG80211_WEXT - bool "cfg80211 wireless extensions compatibility" + bool "cfg80211 wireless extensions compatibility" if !CFG80211_WEXT_EXPORT depends on CFG80211 select WEXT_CORE + default y if CFG80211_WEXT_EXPORT help Enable this option if you need old userspace for wireless extensions with cfg80211-based drivers. +config CFG80211_WEXT_EXPORT + bool + depends on CFG80211 + help + Drivers should select this option if they require cfg80211's + wext compatibility symbols to be exported. + config LIB80211 tristate default n diff --git a/net/wireless/ibss.c b/net/wireless/ibss.c index e24fc585c883..4c55fab9b4e4 100644 --- a/net/wireless/ibss.c +++ b/net/wireless/ibss.c @@ -30,7 +30,7 @@ void __cfg80211_ibss_joined(struct net_device *dev, const u8 *bssid, return; bss = cfg80211_get_bss(wdev->wiphy, channel, bssid, NULL, 0, - WLAN_CAPABILITY_IBSS, WLAN_CAPABILITY_IBSS); + IEEE80211_BSS_TYPE_IBSS, IEEE80211_PRIVACY_ANY); if (WARN_ON(!bss)) return; @@ -533,7 +533,7 @@ int cfg80211_ibss_wext_giwap(struct net_device *dev, else if (wdev->wext.ibss.bssid) memcpy(ap_addr->sa_data, wdev->wext.ibss.bssid, ETH_ALEN); else - memset(ap_addr->sa_data, 0, ETH_ALEN); + eth_zero_addr(ap_addr->sa_data); wdev_unlock(wdev); diff --git a/net/wireless/mlme.c b/net/wireless/mlme.c index 2c52b59e43f3..7aae329e2b4e 100644 --- a/net/wireless/mlme.c +++ b/net/wireless/mlme.c @@ -229,7 +229,8 @@ int cfg80211_mlme_auth(struct cfg80211_registered_device *rdev, return -EALREADY; req.bss = cfg80211_get_bss(&rdev->wiphy, chan, bssid, ssid, ssid_len, - WLAN_CAPABILITY_ESS, WLAN_CAPABILITY_ESS); + IEEE80211_BSS_TYPE_ESS, + IEEE80211_PRIVACY_ANY); if (!req.bss) return -ENOENT; @@ -296,7 +297,8 @@ int cfg80211_mlme_assoc(struct cfg80211_registered_device *rdev, rdev->wiphy.vht_capa_mod_mask); req->bss = cfg80211_get_bss(&rdev->wiphy, chan, bssid, ssid, ssid_len, - WLAN_CAPABILITY_ESS, WLAN_CAPABILITY_ESS); + IEEE80211_BSS_TYPE_ESS, + IEEE80211_PRIVACY_ANY); if (!req->bss) return -ENOENT; diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c index b6f84f6a2a09..dd78445c7d50 100644 --- a/net/wireless/nl80211.c +++ b/net/wireless/nl80211.c @@ -399,6 +399,7 @@ static const struct nla_policy nl80211_policy[NUM_NL80211_ATTR] = { [NL80211_ATTR_WIPHY_SELF_MANAGED_REG] = { .type = NLA_FLAG }, [NL80211_ATTR_NETNS_FD] = { .type = NLA_U32 }, [NL80211_ATTR_SCHED_SCAN_DELAY] = { .type = NLA_U32 }, + [NL80211_ATTR_REG_INDOOR] = { .type = NLA_FLAG }, }; /* policy for the key attributes */ @@ -1098,8 +1099,6 @@ static int nl80211_send_wowlan(struct sk_buff *msg, if (large && nl80211_send_wowlan_tcp_caps(rdev, msg)) return -ENOBUFS; - /* TODO: send wowlan net detect */ - nla_nest_end(msg, nl_wowlan); return 0; @@ -2668,7 +2667,8 @@ static int nl80211_new_interface(struct sk_buff *skb, struct genl_info *info) wdev = rdev_add_virtual_intf(rdev, nla_data(info->attrs[NL80211_ATTR_IFNAME]), - type, err ? NULL : &flags, ¶ms); + NET_NAME_USER, type, err ? NULL : &flags, + ¶ms); if (WARN_ON(!wdev)) { nlmsg_free(msg); return -EPROTO; @@ -4968,7 +4968,10 @@ static int parse_reg_rule(struct nlattr *tb[], static int nl80211_req_set_reg(struct sk_buff *skb, struct genl_info *info) { char *data = NULL; + bool is_indoor; enum nl80211_user_reg_hint_type user_reg_hint_type; + u32 owner_nlportid; + /* * You should only get this when cfg80211 hasn't yet initialized @@ -4994,7 +4997,15 @@ static int nl80211_req_set_reg(struct sk_buff *skb, struct genl_info *info) data = nla_data(info->attrs[NL80211_ATTR_REG_ALPHA2]); return regulatory_hint_user(data, user_reg_hint_type); case NL80211_USER_REG_HINT_INDOOR: - return regulatory_hint_indoor_user(); + if (info->attrs[NL80211_ATTR_SOCKET_OWNER]) { + owner_nlportid = info->snd_portid; + is_indoor = !!info->attrs[NL80211_ATTR_REG_INDOOR]; + } else { + owner_nlportid = 0; + is_indoor = true; + } + + return regulatory_hint_indoor(is_indoor, owner_nlportid); default: return -EINVAL; } @@ -5275,7 +5286,7 @@ do { \ FILL_IN_MESH_PARAM_IF_SET(tb, cfg, dot11MeshAwakeWindowDuration, 0, 65535, mask, NL80211_MESHCONF_AWAKE_WINDOW, nla_get_u16); - FILL_IN_MESH_PARAM_IF_SET(tb, cfg, plink_timeout, 1, 0xffffffff, + FILL_IN_MESH_PARAM_IF_SET(tb, cfg, plink_timeout, 0, 0xffffffff, mask, NL80211_MESHCONF_PLINK_TIMEOUT, nla_get_u32); if (mask_out) @@ -5653,7 +5664,7 @@ static int nl80211_set_reg(struct sk_buff *skb, struct genl_info *info) } } - r = set_regdom(rd); + r = set_regdom(rd, REGD_SOURCE_CRDA); /* set_regdom took ownership */ rd = NULL; @@ -5693,8 +5704,8 @@ static int nl80211_parse_random_mac(struct nlattr **attrs, int i; if (!attrs[NL80211_ATTR_MAC] && !attrs[NL80211_ATTR_MAC_MASK]) { - memset(mac_addr, 0, ETH_ALEN); - memset(mac_addr_mask, 0, ETH_ALEN); + eth_zero_addr(mac_addr); + eth_zero_addr(mac_addr_mask); mac_addr[0] = 0x2; mac_addr_mask[0] = 0x3; @@ -7275,8 +7286,18 @@ static int nl80211_join_ibss(struct sk_buff *skb, struct genl_info *info) break; case NL80211_CHAN_WIDTH_20: case NL80211_CHAN_WIDTH_40: - if (rdev->wiphy.features & NL80211_FEATURE_HT_IBSS) - break; + if (!(rdev->wiphy.features & NL80211_FEATURE_HT_IBSS)) + return -EINVAL; + break; + case NL80211_CHAN_WIDTH_80: + case NL80211_CHAN_WIDTH_80P80: + case NL80211_CHAN_WIDTH_160: + if (!(rdev->wiphy.features & NL80211_FEATURE_HT_IBSS)) + return -EINVAL; + if (!wiphy_ext_feature_isset(&rdev->wiphy, + NL80211_EXT_FEATURE_VHT_IBSS)) + return -EINVAL; + break; default: return -EINVAL; } @@ -7389,8 +7410,8 @@ static int nl80211_set_mcast_rate(struct sk_buff *skb, struct genl_info *info) static struct sk_buff * __cfg80211_alloc_vendor_skb(struct cfg80211_registered_device *rdev, - int approxlen, u32 portid, u32 seq, - enum nl80211_commands cmd, + struct wireless_dev *wdev, int approxlen, + u32 portid, u32 seq, enum nl80211_commands cmd, enum nl80211_attrs attr, const struct nl80211_vendor_cmd_info *info, gfp_t gfp) @@ -7421,6 +7442,16 @@ __cfg80211_alloc_vendor_skb(struct cfg80211_registered_device *rdev, goto nla_put_failure; } + if (wdev) { + if (nla_put_u64(skb, NL80211_ATTR_WDEV, + wdev_id(wdev))) + goto nla_put_failure; + if (wdev->netdev && + nla_put_u32(skb, NL80211_ATTR_IFINDEX, + wdev->netdev->ifindex)) + goto nla_put_failure; + } + data = nla_nest_start(skb, attr); ((void **)skb->cb)[0] = rdev; @@ -7435,6 +7466,7 @@ __cfg80211_alloc_vendor_skb(struct cfg80211_registered_device *rdev, } struct sk_buff *__cfg80211_alloc_event_skb(struct wiphy *wiphy, + struct wireless_dev *wdev, enum nl80211_commands cmd, enum nl80211_attrs attr, int vendor_event_idx, @@ -7460,7 +7492,7 @@ struct sk_buff *__cfg80211_alloc_event_skb(struct wiphy *wiphy, return NULL; } - return __cfg80211_alloc_vendor_skb(rdev, approxlen, 0, 0, + return __cfg80211_alloc_vendor_skb(rdev, wdev, approxlen, 0, 0, cmd, attr, info, gfp); } EXPORT_SYMBOL(__cfg80211_alloc_event_skb); @@ -8761,8 +8793,8 @@ static int nl80211_send_wowlan_tcp(struct sk_buff *msg, if (!nl_tcp) return -ENOBUFS; - if (nla_put_be32(msg, NL80211_WOWLAN_TCP_SRC_IPV4, tcp->src) || - nla_put_be32(msg, NL80211_WOWLAN_TCP_DST_IPV4, tcp->dst) || + if (nla_put_in_addr(msg, NL80211_WOWLAN_TCP_SRC_IPV4, tcp->src) || + nla_put_in_addr(msg, NL80211_WOWLAN_TCP_DST_IPV4, tcp->dst) || nla_put(msg, NL80211_WOWLAN_TCP_DST_MAC, ETH_ALEN, tcp->dst_mac) || nla_put_u16(msg, NL80211_WOWLAN_TCP_SRC_PORT, tcp->src_port) || nla_put_u16(msg, NL80211_WOWLAN_TCP_DST_PORT, tcp->dst_port) || @@ -8808,6 +8840,9 @@ static int nl80211_send_wowlan_nd(struct sk_buff *msg, if (nla_put_u32(msg, NL80211_ATTR_SCHED_SCAN_INTERVAL, req->interval)) return -ENOBUFS; + if (nla_put_u32(msg, NL80211_ATTR_SCHED_SCAN_DELAY, req->delay)) + return -ENOBUFS; + freqs = nla_nest_start(msg, NL80211_ATTR_SCAN_FREQUENCIES); if (!freqs) return -ENOBUFS; @@ -8993,8 +9028,8 @@ static int nl80211_parse_wowlan_tcp(struct cfg80211_registered_device *rdev, cfg = kzalloc(size, GFP_KERNEL); if (!cfg) return -ENOMEM; - cfg->src = nla_get_be32(tb[NL80211_WOWLAN_TCP_SRC_IPV4]); - cfg->dst = nla_get_be32(tb[NL80211_WOWLAN_TCP_DST_IPV4]); + cfg->src = nla_get_in_addr(tb[NL80211_WOWLAN_TCP_SRC_IPV4]); + cfg->dst = nla_get_in_addr(tb[NL80211_WOWLAN_TCP_DST_IPV4]); memcpy(cfg->dst_mac, nla_data(tb[NL80211_WOWLAN_TCP_DST_MAC]), ETH_ALEN); if (tb[NL80211_WOWLAN_TCP_SRC_PORT]) @@ -9094,6 +9129,7 @@ static int nl80211_set_wowlan(struct sk_buff *skb, struct genl_info *info) const struct wiphy_wowlan_support *wowlan = rdev->wiphy.wowlan; int err, i; bool prev_enabled = rdev->wiphy.wowlan_config; + bool regular = false; if (!wowlan) return -EOPNOTSUPP; @@ -9121,12 +9157,14 @@ static int nl80211_set_wowlan(struct sk_buff *skb, struct genl_info *info) if (!(wowlan->flags & WIPHY_WOWLAN_DISCONNECT)) return -EINVAL; new_triggers.disconnect = true; + regular = true; } if (tb[NL80211_WOWLAN_TRIG_MAGIC_PKT]) { if (!(wowlan->flags & WIPHY_WOWLAN_MAGIC_PKT)) return -EINVAL; new_triggers.magic_pkt = true; + regular = true; } if (tb[NL80211_WOWLAN_TRIG_GTK_REKEY_SUPPORTED]) @@ -9136,24 +9174,28 @@ static int nl80211_set_wowlan(struct sk_buff *skb, struct genl_info *info) if (!(wowlan->flags & WIPHY_WOWLAN_GTK_REKEY_FAILURE)) return -EINVAL; new_triggers.gtk_rekey_failure = true; + regular = true; } if (tb[NL80211_WOWLAN_TRIG_EAP_IDENT_REQUEST]) { if (!(wowlan->flags & WIPHY_WOWLAN_EAP_IDENTITY_REQ)) return -EINVAL; new_triggers.eap_identity_req = true; + regular = true; } if (tb[NL80211_WOWLAN_TRIG_4WAY_HANDSHAKE]) { if (!(wowlan->flags & WIPHY_WOWLAN_4WAY_HANDSHAKE)) return -EINVAL; new_triggers.four_way_handshake = true; + regular = true; } if (tb[NL80211_WOWLAN_TRIG_RFKILL_RELEASE]) { if (!(wowlan->flags & WIPHY_WOWLAN_RFKILL_RELEASE)) return -EINVAL; new_triggers.rfkill_release = true; + regular = true; } if (tb[NL80211_WOWLAN_TRIG_PKT_PATTERN]) { @@ -9162,6 +9204,8 @@ static int nl80211_set_wowlan(struct sk_buff *skb, struct genl_info *info) int rem, pat_len, mask_len, pkt_offset; struct nlattr *pat_tb[NUM_NL80211_PKTPAT]; + regular = true; + nla_for_each_nested(pat, tb[NL80211_WOWLAN_TRIG_PKT_PATTERN], rem) n_patterns++; @@ -9223,6 +9267,7 @@ static int nl80211_set_wowlan(struct sk_buff *skb, struct genl_info *info) } if (tb[NL80211_WOWLAN_TRIG_TCP_CONNECTION]) { + regular = true; err = nl80211_parse_wowlan_tcp( rdev, tb[NL80211_WOWLAN_TRIG_TCP_CONNECTION], &new_triggers); @@ -9231,6 +9276,7 @@ static int nl80211_set_wowlan(struct sk_buff *skb, struct genl_info *info) } if (tb[NL80211_WOWLAN_TRIG_NET_DETECT]) { + regular = true; err = nl80211_parse_wowlan_nd( rdev, wowlan, tb[NL80211_WOWLAN_TRIG_NET_DETECT], &new_triggers); @@ -9238,6 +9284,17 @@ static int nl80211_set_wowlan(struct sk_buff *skb, struct genl_info *info) goto error; } + /* The 'any' trigger means the device continues operating more or less + * as in its normal operation mode and wakes up the host on most of the + * normal interrupts (like packet RX, ...) + * It therefore makes little sense to combine with the more constrained + * wakeup trigger modes. + */ + if (new_triggers.any && regular) { + err = -EINVAL; + goto error; + } + ntrig = kmemdup(&new_triggers, sizeof(new_triggers), GFP_KERNEL); if (!ntrig) { err = -ENOMEM; @@ -9906,7 +9963,7 @@ struct sk_buff *__cfg80211_alloc_reply_skb(struct wiphy *wiphy, if (WARN_ON(!rdev->cur_cmd_info)) return NULL; - return __cfg80211_alloc_vendor_skb(rdev, approxlen, + return __cfg80211_alloc_vendor_skb(rdev, NULL, approxlen, rdev->cur_cmd_info->snd_portid, rdev->cur_cmd_info->snd_seq, cmd, attr, NULL, GFP_KERNEL); @@ -12775,6 +12832,11 @@ static int nl80211_netlink_notify(struct notifier_block * nb, rcu_read_unlock(); + /* + * It is possible that the user space process that is controlling the + * indoor setting disappeared, so notify the regulatory core. + */ + regulatory_netlink_notify(notify->portid); return NOTIFY_OK; } diff --git a/net/wireless/rdev-ops.h b/net/wireless/rdev-ops.h index 35cfb7134bdb..c6e83a7468c0 100644 --- a/net/wireless/rdev-ops.h +++ b/net/wireless/rdev-ops.h @@ -35,13 +35,14 @@ static inline void rdev_set_wakeup(struct cfg80211_registered_device *rdev, static inline struct wireless_dev *rdev_add_virtual_intf(struct cfg80211_registered_device *rdev, char *name, + unsigned char name_assign_type, enum nl80211_iftype type, u32 *flags, struct vif_params *params) { struct wireless_dev *ret; trace_rdev_add_virtual_intf(&rdev->wiphy, name, type); - ret = rdev->ops->add_virtual_intf(&rdev->wiphy, name, type, flags, - params); + ret = rdev->ops->add_virtual_intf(&rdev->wiphy, name, name_assign_type, + type, flags, params); trace_rdev_return_wdev(&rdev->wiphy, ret); return ret; } diff --git a/net/wireless/reg.c b/net/wireless/reg.c index 48dfc7b4e981..0e347f888fe9 100644 --- a/net/wireless/reg.c +++ b/net/wireless/reg.c @@ -82,17 +82,12 @@ * be intersected with the current one. * @REG_REQ_ALREADY_SET: the regulatory request will not change the current * regulatory settings, and no further processing is required. - * @REG_REQ_USER_HINT_HANDLED: a non alpha2 user hint was handled and no - * further processing is required, i.e., not need to update last_request - * etc. This should be used for user hints that do not provide an alpha2 - * but some other type of regulatory hint, i.e., indoor operation. */ enum reg_request_treatment { REG_REQ_OK, REG_REQ_IGNORE, REG_REQ_INTERSECT, REG_REQ_ALREADY_SET, - REG_REQ_USER_HINT_HANDLED, }; static struct regulatory_request core_request_world = { @@ -133,9 +128,17 @@ static int reg_num_devs_support_basehint; * State variable indicating if the platform on which the devices * are attached is operating in an indoor environment. The state variable * is relevant for all registered devices. - * (protected by RTNL) */ static bool reg_is_indoor; +static spinlock_t reg_indoor_lock; + +/* Used to track the userspace process controlling the indoor setting */ +static u32 reg_is_indoor_portid; + +/* Max number of consecutive attempts to communicate with CRDA */ +#define REG_MAX_CRDA_TIMEOUTS 10 + +static u32 reg_crda_timeouts; static const struct ieee80211_regdomain *get_cfg80211_regdom(void) { @@ -487,7 +490,7 @@ static void reg_regdb_search(struct work_struct *work) mutex_unlock(®_regdb_search_mutex); if (!IS_ERR_OR_NULL(regdom)) - set_regdom(regdom); + set_regdom(regdom, REGD_SOURCE_INTERNAL_DB); rtnl_unlock(); } @@ -537,15 +540,20 @@ static int call_crda(const char *alpha2) snprintf(country, sizeof(country), "COUNTRY=%c%c", alpha2[0], alpha2[1]); + /* query internal regulatory database (if it exists) */ + reg_regdb_query(alpha2); + + if (reg_crda_timeouts > REG_MAX_CRDA_TIMEOUTS) { + pr_info("Exceeded CRDA call max attempts. Not calling CRDA\n"); + return -EINVAL; + } + if (!is_world_regdom((char *) alpha2)) pr_info("Calling CRDA for country: %c%c\n", alpha2[0], alpha2[1]); else pr_info("Calling CRDA to update world regulatory domain\n"); - /* query internal regulatory database (if it exists) */ - reg_regdb_query(alpha2); - return kobject_uevent_env(®_pdev->dev.kobj, KOBJ_CHANGE, env); } @@ -554,6 +562,9 @@ reg_call_crda(struct regulatory_request *request) { if (call_crda(request->alpha2)) return REG_REQ_IGNORE; + + queue_delayed_work(system_power_efficient_wq, + ®_timeout, msecs_to_jiffies(3142)); return REG_REQ_OK; } @@ -1248,13 +1259,6 @@ static bool reg_request_cell_base(struct regulatory_request *request) return request->user_reg_hint_type == NL80211_USER_REG_HINT_CELL_BASE; } -static bool reg_request_indoor(struct regulatory_request *request) -{ - if (request->initiator != NL80211_REGDOM_SET_BY_USER) - return false; - return request->user_reg_hint_type == NL80211_USER_REG_HINT_INDOOR; -} - bool reg_last_request_cell_base(void) { return reg_request_cell_base(get_last_request()); @@ -1800,8 +1804,7 @@ static void reg_set_request_processed(void) need_more_processing = true; spin_unlock(®_requests_lock); - if (lr->initiator == NL80211_REGDOM_SET_BY_USER) - cancel_delayed_work(®_timeout); + cancel_delayed_work(®_timeout); if (need_more_processing) schedule_work(®_work); @@ -1833,11 +1836,6 @@ __reg_process_hint_user(struct regulatory_request *user_request) { struct regulatory_request *lr = get_last_request(); - if (reg_request_indoor(user_request)) { - reg_is_indoor = true; - return REG_REQ_USER_HINT_HANDLED; - } - if (reg_request_cell_base(user_request)) return reg_ignore_cell_hint(user_request); @@ -1885,8 +1883,7 @@ reg_process_hint_user(struct regulatory_request *user_request) treatment = __reg_process_hint_user(user_request); if (treatment == REG_REQ_IGNORE || - treatment == REG_REQ_ALREADY_SET || - treatment == REG_REQ_USER_HINT_HANDLED) { + treatment == REG_REQ_ALREADY_SET) { reg_free_request(user_request); return treatment; } @@ -1947,7 +1944,6 @@ reg_process_hint_driver(struct wiphy *wiphy, case REG_REQ_OK: break; case REG_REQ_IGNORE: - case REG_REQ_USER_HINT_HANDLED: reg_free_request(driver_request); return treatment; case REG_REQ_INTERSECT: @@ -2047,7 +2043,6 @@ reg_process_hint_country_ie(struct wiphy *wiphy, case REG_REQ_OK: break; case REG_REQ_IGNORE: - case REG_REQ_USER_HINT_HANDLED: /* fall through */ case REG_REQ_ALREADY_SET: reg_free_request(country_ie_request); @@ -2086,11 +2081,8 @@ static void reg_process_hint(struct regulatory_request *reg_request) case NL80211_REGDOM_SET_BY_USER: treatment = reg_process_hint_user(reg_request); if (treatment == REG_REQ_IGNORE || - treatment == REG_REQ_ALREADY_SET || - treatment == REG_REQ_USER_HINT_HANDLED) + treatment == REG_REQ_ALREADY_SET) return; - queue_delayed_work(system_power_efficient_wq, - ®_timeout, msecs_to_jiffies(3142)); return; case NL80211_REGDOM_SET_BY_DRIVER: if (!wiphy) @@ -2177,6 +2169,13 @@ static void reg_process_pending_hints(void) } reg_process_hint(reg_request); + + lr = get_last_request(); + + spin_lock(®_requests_lock); + if (!list_empty(®_requests_list) && lr && lr->processed) + schedule_work(®_work); + spin_unlock(®_requests_lock); } /* Processes beacon hints -- this has nothing to do with country IEs */ @@ -2304,27 +2303,58 @@ int regulatory_hint_user(const char *alpha2, request->initiator = NL80211_REGDOM_SET_BY_USER; request->user_reg_hint_type = user_reg_hint_type; + /* Allow calling CRDA again */ + reg_crda_timeouts = 0; + queue_regulatory_request(request); return 0; } -int regulatory_hint_indoor_user(void) +int regulatory_hint_indoor(bool is_indoor, u32 portid) { - struct regulatory_request *request; + spin_lock(®_indoor_lock); - request = kzalloc(sizeof(struct regulatory_request), GFP_KERNEL); - if (!request) - return -ENOMEM; + /* It is possible that more than one user space process is trying to + * configure the indoor setting. To handle such cases, clear the indoor + * setting in case that some process does not think that the device + * is operating in an indoor environment. In addition, if a user space + * process indicates that it is controlling the indoor setting, save its + * portid, i.e., make it the owner. + */ + reg_is_indoor = is_indoor; + if (reg_is_indoor) { + if (!reg_is_indoor_portid) + reg_is_indoor_portid = portid; + } else { + reg_is_indoor_portid = 0; + } - request->wiphy_idx = WIPHY_IDX_INVALID; - request->initiator = NL80211_REGDOM_SET_BY_USER; - request->user_reg_hint_type = NL80211_USER_REG_HINT_INDOOR; - queue_regulatory_request(request); + spin_unlock(®_indoor_lock); + + if (!is_indoor) + reg_check_channels(); return 0; } +void regulatory_netlink_notify(u32 portid) +{ + spin_lock(®_indoor_lock); + + if (reg_is_indoor_portid != portid) { + spin_unlock(®_indoor_lock); + return; + } + + reg_is_indoor = false; + reg_is_indoor_portid = 0; + + spin_unlock(®_indoor_lock); + + reg_check_channels(); +} + /* Driver hints */ int regulatory_hint(struct wiphy *wiphy, const char *alpha2) { @@ -2345,6 +2375,9 @@ int regulatory_hint(struct wiphy *wiphy, const char *alpha2) request->alpha2[1] = alpha2[1]; request->initiator = NL80211_REGDOM_SET_BY_DRIVER; + /* Allow calling CRDA again */ + reg_crda_timeouts = 0; + queue_regulatory_request(request); return 0; @@ -2398,6 +2431,9 @@ void regulatory_hint_country_ie(struct wiphy *wiphy, enum ieee80211_band band, request->initiator = NL80211_REGDOM_SET_BY_COUNTRY_IE; request->country_ie_env = env; + /* Allow calling CRDA again */ + reg_crda_timeouts = 0; + queue_regulatory_request(request); request = NULL; out: @@ -2486,13 +2522,22 @@ static void restore_regulatory_settings(bool reset_user) char alpha2[2]; char world_alpha2[2]; struct reg_beacon *reg_beacon, *btmp; - struct regulatory_request *reg_request, *tmp; LIST_HEAD(tmp_reg_req_list); struct cfg80211_registered_device *rdev; ASSERT_RTNL(); - reg_is_indoor = false; + /* + * Clear the indoor setting in case that it is not controlled by user + * space, as otherwise there is no guarantee that the device is still + * operating in an indoor environment. + */ + spin_lock(®_indoor_lock); + if (reg_is_indoor && !reg_is_indoor_portid) { + reg_is_indoor = false; + reg_check_channels(); + } + spin_unlock(®_indoor_lock); reset_regdomains(true, &world_regdom); restore_alpha2(alpha2, reset_user); @@ -2504,11 +2549,7 @@ static void restore_regulatory_settings(bool reset_user) * settings. */ spin_lock(®_requests_lock); - list_for_each_entry_safe(reg_request, tmp, ®_requests_list, list) { - if (reg_request->initiator != NL80211_REGDOM_SET_BY_USER) - continue; - list_move_tail(®_request->list, &tmp_reg_req_list); - } + list_splice_tail_init(®_requests_list, &tmp_reg_req_list); spin_unlock(®_requests_lock); /* Clear beacon hints */ @@ -2871,7 +2912,8 @@ static int reg_set_rd_country_ie(const struct ieee80211_regdomain *rd, * multiple drivers can be ironed out later. Caller must've already * kmalloc'd the rd structure. */ -int set_regdom(const struct ieee80211_regdomain *rd) +int set_regdom(const struct ieee80211_regdomain *rd, + enum ieee80211_regd_source regd_src) { struct regulatory_request *lr; bool user_reset = false; @@ -2882,6 +2924,9 @@ int set_regdom(const struct ieee80211_regdomain *rd) return -EINVAL; } + if (regd_src == REGD_SOURCE_CRDA) + reg_crda_timeouts = 0; + lr = get_last_request(); /* Note that this doesn't update the wiphys, this is done below */ @@ -3041,6 +3086,7 @@ static void reg_timeout_work(struct work_struct *work) { REG_DBG_PRINT("Timeout while waiting for CRDA to reply, restoring regulatory settings\n"); rtnl_lock(); + reg_crda_timeouts++; restore_regulatory_settings(true); rtnl_unlock(); } @@ -3089,6 +3135,7 @@ int __init regulatory_init(void) spin_lock_init(®_requests_lock); spin_lock_init(®_pending_beacons_lock); + spin_lock_init(®_indoor_lock); reg_regdb_size_check(); diff --git a/net/wireless/reg.h b/net/wireless/reg.h index 4b45d6e61d24..9f495d76eca0 100644 --- a/net/wireless/reg.h +++ b/net/wireless/reg.h @@ -16,6 +16,11 @@ * OR IN CONNECTION WITH THE USE OR PERFORMANCE OF THIS SOFTWARE. */ +enum ieee80211_regd_source { + REGD_SOURCE_INTERNAL_DB, + REGD_SOURCE_CRDA, +}; + extern const struct ieee80211_regdomain __rcu *cfg80211_regdomain; bool reg_is_valid_request(const char *alpha2); @@ -25,7 +30,20 @@ enum nl80211_dfs_regions reg_get_dfs_region(struct wiphy *wiphy); int regulatory_hint_user(const char *alpha2, enum nl80211_user_reg_hint_type user_reg_hint_type); -int regulatory_hint_indoor_user(void); + +/** + * regulatory_hint_indoor - hint operation in indoor env. or not + * @is_indoor: if true indicates that user space thinks that the + * device is operating in an indoor environment. + * @portid: the netlink port ID on which the hint was given. + */ +int regulatory_hint_indoor(bool is_indoor, u32 portid); + +/** + * regulatory_netlink_notify - notify on released netlink socket + * @portid: the netlink socket port ID + */ +void regulatory_netlink_notify(u32 portid); void wiphy_regulatory_register(struct wiphy *wiphy); void wiphy_regulatory_deregister(struct wiphy *wiphy); @@ -33,7 +51,9 @@ void wiphy_regulatory_deregister(struct wiphy *wiphy); int __init regulatory_init(void); void regulatory_exit(void); -int set_regdom(const struct ieee80211_regdomain *rd); +int set_regdom(const struct ieee80211_regdomain *rd, + enum ieee80211_regd_source regd_src); + unsigned int reg_get_max_bandwidth(const struct ieee80211_regdomain *rd, const struct ieee80211_reg_rule *rule); diff --git a/net/wireless/scan.c b/net/wireless/scan.c index c705c3e2b751..3a50aa2553bf 100644 --- a/net/wireless/scan.c +++ b/net/wireless/scan.c @@ -531,24 +531,78 @@ static int cmp_bss(struct cfg80211_bss *a, } } +static bool cfg80211_bss_type_match(u16 capability, + enum ieee80211_band band, + enum ieee80211_bss_type bss_type) +{ + bool ret = true; + u16 mask, val; + + if (bss_type == IEEE80211_BSS_TYPE_ANY) + return ret; + + if (band == IEEE80211_BAND_60GHZ) { + mask = WLAN_CAPABILITY_DMG_TYPE_MASK; + switch (bss_type) { + case IEEE80211_BSS_TYPE_ESS: + val = WLAN_CAPABILITY_DMG_TYPE_AP; + break; + case IEEE80211_BSS_TYPE_PBSS: + val = WLAN_CAPABILITY_DMG_TYPE_PBSS; + break; + case IEEE80211_BSS_TYPE_IBSS: + val = WLAN_CAPABILITY_DMG_TYPE_IBSS; + break; + default: + return false; + } + } else { + mask = WLAN_CAPABILITY_ESS | WLAN_CAPABILITY_IBSS; + switch (bss_type) { + case IEEE80211_BSS_TYPE_ESS: + val = WLAN_CAPABILITY_ESS; + break; + case IEEE80211_BSS_TYPE_IBSS: + val = WLAN_CAPABILITY_IBSS; + break; + case IEEE80211_BSS_TYPE_MBSS: + val = 0; + break; + default: + return false; + } + } + + ret = ((capability & mask) == val); + return ret; +} + /* Returned bss is reference counted and must be cleaned up appropriately. */ struct cfg80211_bss *cfg80211_get_bss(struct wiphy *wiphy, struct ieee80211_channel *channel, const u8 *bssid, const u8 *ssid, size_t ssid_len, - u16 capa_mask, u16 capa_val) + enum ieee80211_bss_type bss_type, + enum ieee80211_privacy privacy) { struct cfg80211_registered_device *rdev = wiphy_to_rdev(wiphy); struct cfg80211_internal_bss *bss, *res = NULL; unsigned long now = jiffies; + int bss_privacy; - trace_cfg80211_get_bss(wiphy, channel, bssid, ssid, ssid_len, capa_mask, - capa_val); + trace_cfg80211_get_bss(wiphy, channel, bssid, ssid, ssid_len, bss_type, + privacy); spin_lock_bh(&rdev->bss_lock); list_for_each_entry(bss, &rdev->bss_list, list) { - if ((bss->pub.capability & capa_mask) != capa_val) + if (!cfg80211_bss_type_match(bss->pub.capability, + bss->pub.channel->band, bss_type)) + continue; + + bss_privacy = (bss->pub.capability & WLAN_CAPABILITY_PRIVACY); + if ((privacy == IEEE80211_PRIVACY_ON && !bss_privacy) || + (privacy == IEEE80211_PRIVACY_OFF && bss_privacy)) continue; if (channel && bss->pub.channel != channel) continue; @@ -896,6 +950,7 @@ cfg80211_inform_bss_width(struct wiphy *wiphy, struct cfg80211_bss_ies *ies; struct ieee80211_channel *channel; struct cfg80211_internal_bss tmp = {}, *res; + int bss_type; bool signal_valid; if (WARN_ON(!wiphy)) @@ -950,8 +1005,15 @@ cfg80211_inform_bss_width(struct wiphy *wiphy, if (!res) return NULL; - if (res->pub.capability & WLAN_CAPABILITY_ESS) - regulatory_hint_found_beacon(wiphy, channel, gfp); + if (channel->band == IEEE80211_BAND_60GHZ) { + bss_type = res->pub.capability & WLAN_CAPABILITY_DMG_TYPE_MASK; + if (bss_type == WLAN_CAPABILITY_DMG_TYPE_AP || + bss_type == WLAN_CAPABILITY_DMG_TYPE_PBSS) + regulatory_hint_found_beacon(wiphy, channel, gfp); + } else { + if (res->pub.capability & WLAN_CAPABILITY_ESS) + regulatory_hint_found_beacon(wiphy, channel, gfp); + } trace_cfg80211_return_bss(&res->pub); /* cfg80211_bss_update gives us a referenced result */ @@ -973,6 +1035,7 @@ cfg80211_inform_bss_width_frame(struct wiphy *wiphy, bool signal_valid; size_t ielen = len - offsetof(struct ieee80211_mgmt, u.probe_resp.variable); + int bss_type; BUILD_BUG_ON(offsetof(struct ieee80211_mgmt, u.probe_resp.variable) != offsetof(struct ieee80211_mgmt, u.beacon.variable)); @@ -1025,8 +1088,15 @@ cfg80211_inform_bss_width_frame(struct wiphy *wiphy, if (!res) return NULL; - if (res->pub.capability & WLAN_CAPABILITY_ESS) - regulatory_hint_found_beacon(wiphy, channel, gfp); + if (channel->band == IEEE80211_BAND_60GHZ) { + bss_type = res->pub.capability & WLAN_CAPABILITY_DMG_TYPE_MASK; + if (bss_type == WLAN_CAPABILITY_DMG_TYPE_AP || + bss_type == WLAN_CAPABILITY_DMG_TYPE_PBSS) + regulatory_hint_found_beacon(wiphy, channel, gfp); + } else { + if (res->pub.capability & WLAN_CAPABILITY_ESS) + regulatory_hint_found_beacon(wiphy, channel, gfp); + } trace_cfg80211_return_bss(&res->pub); /* cfg80211_bss_update gives us a referenced result */ @@ -1237,17 +1307,17 @@ int cfg80211_wext_siwscan(struct net_device *dev, kfree(creq); return err; } -EXPORT_SYMBOL_GPL(cfg80211_wext_siwscan); +EXPORT_WEXT_HANDLER(cfg80211_wext_siwscan); -static void ieee80211_scan_add_ies(struct iw_request_info *info, - const struct cfg80211_bss_ies *ies, - char **current_ev, char *end_buf) +static char *ieee80211_scan_add_ies(struct iw_request_info *info, + const struct cfg80211_bss_ies *ies, + char *current_ev, char *end_buf) { const u8 *pos, *end, *next; struct iw_event iwe; if (!ies) - return; + return current_ev; /* * If needed, fragment the IEs buffer (at IE boundaries) into short @@ -1264,10 +1334,11 @@ static void ieee80211_scan_add_ies(struct iw_request_info *info, memset(&iwe, 0, sizeof(iwe)); iwe.cmd = IWEVGENIE; iwe.u.data.length = next - pos; - *current_ev = iwe_stream_add_point(info, *current_ev, - end_buf, &iwe, - (void *)pos); - + current_ev = iwe_stream_add_point_check(info, current_ev, + end_buf, &iwe, + (void *)pos); + if (IS_ERR(current_ev)) + return current_ev; pos = next; } @@ -1275,10 +1346,14 @@ static void ieee80211_scan_add_ies(struct iw_request_info *info, memset(&iwe, 0, sizeof(iwe)); iwe.cmd = IWEVGENIE; iwe.u.data.length = end - pos; - *current_ev = iwe_stream_add_point(info, *current_ev, - end_buf, &iwe, - (void *)pos); + current_ev = iwe_stream_add_point_check(info, current_ev, + end_buf, &iwe, + (void *)pos); + if (IS_ERR(current_ev)) + return current_ev; } + + return current_ev; } static char * @@ -1289,7 +1364,8 @@ ieee80211_bss(struct wiphy *wiphy, struct iw_request_info *info, const struct cfg80211_bss_ies *ies; struct iw_event iwe; const u8 *ie; - u8 *buf, *cfg, *p; + u8 buf[50]; + u8 *cfg, *p, *tmp; int rem, i, sig; bool ismesh = false; @@ -1297,22 +1373,28 @@ ieee80211_bss(struct wiphy *wiphy, struct iw_request_info *info, iwe.cmd = SIOCGIWAP; iwe.u.ap_addr.sa_family = ARPHRD_ETHER; memcpy(iwe.u.ap_addr.sa_data, bss->pub.bssid, ETH_ALEN); - current_ev = iwe_stream_add_event(info, current_ev, end_buf, &iwe, - IW_EV_ADDR_LEN); + current_ev = iwe_stream_add_event_check(info, current_ev, end_buf, &iwe, + IW_EV_ADDR_LEN); + if (IS_ERR(current_ev)) + return current_ev; memset(&iwe, 0, sizeof(iwe)); iwe.cmd = SIOCGIWFREQ; iwe.u.freq.m = ieee80211_frequency_to_channel(bss->pub.channel->center_freq); iwe.u.freq.e = 0; - current_ev = iwe_stream_add_event(info, current_ev, end_buf, &iwe, - IW_EV_FREQ_LEN); + current_ev = iwe_stream_add_event_check(info, current_ev, end_buf, &iwe, + IW_EV_FREQ_LEN); + if (IS_ERR(current_ev)) + return current_ev; memset(&iwe, 0, sizeof(iwe)); iwe.cmd = SIOCGIWFREQ; iwe.u.freq.m = bss->pub.channel->center_freq; iwe.u.freq.e = 6; - current_ev = iwe_stream_add_event(info, current_ev, end_buf, &iwe, - IW_EV_FREQ_LEN); + current_ev = iwe_stream_add_event_check(info, current_ev, end_buf, &iwe, + IW_EV_FREQ_LEN); + if (IS_ERR(current_ev)) + return current_ev; if (wiphy->signal_type != CFG80211_SIGNAL_TYPE_NONE) { memset(&iwe, 0, sizeof(iwe)); @@ -1341,8 +1423,11 @@ ieee80211_bss(struct wiphy *wiphy, struct iw_request_info *info, /* not reached */ break; } - current_ev = iwe_stream_add_event(info, current_ev, end_buf, - &iwe, IW_EV_QUAL_LEN); + current_ev = iwe_stream_add_event_check(info, current_ev, + end_buf, &iwe, + IW_EV_QUAL_LEN); + if (IS_ERR(current_ev)) + return current_ev; } memset(&iwe, 0, sizeof(iwe)); @@ -1352,8 +1437,10 @@ ieee80211_bss(struct wiphy *wiphy, struct iw_request_info *info, else iwe.u.data.flags = IW_ENCODE_DISABLED; iwe.u.data.length = 0; - current_ev = iwe_stream_add_point(info, current_ev, end_buf, - &iwe, ""); + current_ev = iwe_stream_add_point_check(info, current_ev, end_buf, + &iwe, ""); + if (IS_ERR(current_ev)) + return current_ev; rcu_read_lock(); ies = rcu_dereference(bss->pub.ies); @@ -1371,66 +1458,91 @@ ieee80211_bss(struct wiphy *wiphy, struct iw_request_info *info, iwe.cmd = SIOCGIWESSID; iwe.u.data.length = ie[1]; iwe.u.data.flags = 1; - current_ev = iwe_stream_add_point(info, current_ev, end_buf, - &iwe, (u8 *)ie + 2); + current_ev = iwe_stream_add_point_check(info, + current_ev, + end_buf, &iwe, + (u8 *)ie + 2); + if (IS_ERR(current_ev)) + goto unlock; break; case WLAN_EID_MESH_ID: memset(&iwe, 0, sizeof(iwe)); iwe.cmd = SIOCGIWESSID; iwe.u.data.length = ie[1]; iwe.u.data.flags = 1; - current_ev = iwe_stream_add_point(info, current_ev, end_buf, - &iwe, (u8 *)ie + 2); + current_ev = iwe_stream_add_point_check(info, + current_ev, + end_buf, &iwe, + (u8 *)ie + 2); + if (IS_ERR(current_ev)) + goto unlock; break; case WLAN_EID_MESH_CONFIG: ismesh = true; if (ie[1] != sizeof(struct ieee80211_meshconf_ie)) break; - buf = kmalloc(50, GFP_ATOMIC); - if (!buf) - break; cfg = (u8 *)ie + 2; memset(&iwe, 0, sizeof(iwe)); iwe.cmd = IWEVCUSTOM; sprintf(buf, "Mesh Network Path Selection Protocol ID: " "0x%02X", cfg[0]); iwe.u.data.length = strlen(buf); - current_ev = iwe_stream_add_point(info, current_ev, - end_buf, - &iwe, buf); + current_ev = iwe_stream_add_point_check(info, + current_ev, + end_buf, + &iwe, buf); + if (IS_ERR(current_ev)) + goto unlock; sprintf(buf, "Path Selection Metric ID: 0x%02X", cfg[1]); iwe.u.data.length = strlen(buf); - current_ev = iwe_stream_add_point(info, current_ev, - end_buf, - &iwe, buf); + current_ev = iwe_stream_add_point_check(info, + current_ev, + end_buf, + &iwe, buf); + if (IS_ERR(current_ev)) + goto unlock; sprintf(buf, "Congestion Control Mode ID: 0x%02X", cfg[2]); iwe.u.data.length = strlen(buf); - current_ev = iwe_stream_add_point(info, current_ev, - end_buf, - &iwe, buf); + current_ev = iwe_stream_add_point_check(info, + current_ev, + end_buf, + &iwe, buf); + if (IS_ERR(current_ev)) + goto unlock; sprintf(buf, "Synchronization ID: 0x%02X", cfg[3]); iwe.u.data.length = strlen(buf); - current_ev = iwe_stream_add_point(info, current_ev, - end_buf, - &iwe, buf); + current_ev = iwe_stream_add_point_check(info, + current_ev, + end_buf, + &iwe, buf); + if (IS_ERR(current_ev)) + goto unlock; sprintf(buf, "Authentication ID: 0x%02X", cfg[4]); iwe.u.data.length = strlen(buf); - current_ev = iwe_stream_add_point(info, current_ev, - end_buf, - &iwe, buf); + current_ev = iwe_stream_add_point_check(info, + current_ev, + end_buf, + &iwe, buf); + if (IS_ERR(current_ev)) + goto unlock; sprintf(buf, "Formation Info: 0x%02X", cfg[5]); iwe.u.data.length = strlen(buf); - current_ev = iwe_stream_add_point(info, current_ev, - end_buf, - &iwe, buf); + current_ev = iwe_stream_add_point_check(info, + current_ev, + end_buf, + &iwe, buf); + if (IS_ERR(current_ev)) + goto unlock; sprintf(buf, "Capabilities: 0x%02X", cfg[6]); iwe.u.data.length = strlen(buf); - current_ev = iwe_stream_add_point(info, current_ev, - end_buf, - &iwe, buf); - kfree(buf); + current_ev = iwe_stream_add_point_check(info, + current_ev, + end_buf, + &iwe, buf); + if (IS_ERR(current_ev)) + goto unlock; break; case WLAN_EID_SUPP_RATES: case WLAN_EID_EXT_SUPP_RATES: @@ -1445,8 +1557,14 @@ ieee80211_bss(struct wiphy *wiphy, struct iw_request_info *info, for (i = 0; i < ie[1]; i++) { iwe.u.bitrate.value = ((ie[i + 2] & 0x7f) * 500000); + tmp = p; p = iwe_stream_add_value(info, current_ev, p, - end_buf, &iwe, IW_EV_PARAM_LEN); + end_buf, &iwe, + IW_EV_PARAM_LEN); + if (p == tmp) { + current_ev = ERR_PTR(-E2BIG); + goto unlock; + } } current_ev = p; break; @@ -1465,31 +1583,35 @@ ieee80211_bss(struct wiphy *wiphy, struct iw_request_info *info, iwe.u.mode = IW_MODE_MASTER; else iwe.u.mode = IW_MODE_ADHOC; - current_ev = iwe_stream_add_event(info, current_ev, end_buf, - &iwe, IW_EV_UINT_LEN); - } - - buf = kmalloc(31, GFP_ATOMIC); - if (buf) { - memset(&iwe, 0, sizeof(iwe)); - iwe.cmd = IWEVCUSTOM; - sprintf(buf, "tsf=%016llx", (unsigned long long)(ies->tsf)); - iwe.u.data.length = strlen(buf); - current_ev = iwe_stream_add_point(info, current_ev, end_buf, - &iwe, buf); - memset(&iwe, 0, sizeof(iwe)); - iwe.cmd = IWEVCUSTOM; - sprintf(buf, " Last beacon: %ums ago", - elapsed_jiffies_msecs(bss->ts)); - iwe.u.data.length = strlen(buf); - current_ev = iwe_stream_add_point(info, current_ev, - end_buf, &iwe, buf); - kfree(buf); + current_ev = iwe_stream_add_event_check(info, current_ev, + end_buf, &iwe, + IW_EV_UINT_LEN); + if (IS_ERR(current_ev)) + goto unlock; } - ieee80211_scan_add_ies(info, ies, ¤t_ev, end_buf); + memset(&iwe, 0, sizeof(iwe)); + iwe.cmd = IWEVCUSTOM; + sprintf(buf, "tsf=%016llx", (unsigned long long)(ies->tsf)); + iwe.u.data.length = strlen(buf); + current_ev = iwe_stream_add_point_check(info, current_ev, end_buf, + &iwe, buf); + if (IS_ERR(current_ev)) + goto unlock; + memset(&iwe, 0, sizeof(iwe)); + iwe.cmd = IWEVCUSTOM; + sprintf(buf, " Last beacon: %ums ago", + elapsed_jiffies_msecs(bss->ts)); + iwe.u.data.length = strlen(buf); + current_ev = iwe_stream_add_point_check(info, current_ev, + end_buf, &iwe, buf); + if (IS_ERR(current_ev)) + goto unlock; + + current_ev = ieee80211_scan_add_ies(info, ies, current_ev, end_buf); + + unlock: rcu_read_unlock(); - return current_ev; } @@ -1501,19 +1623,27 @@ static int ieee80211_scan_results(struct cfg80211_registered_device *rdev, char *current_ev = buf; char *end_buf = buf + len; struct cfg80211_internal_bss *bss; + int err = 0; spin_lock_bh(&rdev->bss_lock); cfg80211_bss_expire(rdev); list_for_each_entry(bss, &rdev->bss_list, list) { if (buf + len - current_ev <= IW_EV_ADDR_LEN) { - spin_unlock_bh(&rdev->bss_lock); - return -E2BIG; + err = -E2BIG; + break; } current_ev = ieee80211_bss(&rdev->wiphy, info, bss, current_ev, end_buf); + if (IS_ERR(current_ev)) { + err = PTR_ERR(current_ev); + break; + } } spin_unlock_bh(&rdev->bss_lock); + + if (err) + return err; return current_ev - buf; } @@ -1545,5 +1675,5 @@ int cfg80211_wext_giwscan(struct net_device *dev, return res; } -EXPORT_SYMBOL_GPL(cfg80211_wext_giwscan); +EXPORT_WEXT_HANDLER(cfg80211_wext_giwscan); #endif diff --git a/net/wireless/sme.c b/net/wireless/sme.c index 0ab3711c79a0..d11454f87bac 100644 --- a/net/wireless/sme.c +++ b/net/wireless/sme.c @@ -42,7 +42,7 @@ struct cfg80211_conn { CFG80211_CONN_CONNECTED, } state; u8 bssid[ETH_ALEN], prev_bssid[ETH_ALEN]; - u8 *ie; + const u8 *ie; size_t ie_len; bool auto_auth, prev_bssid_valid; }; @@ -257,19 +257,15 @@ static struct cfg80211_bss *cfg80211_get_conn_bss(struct wireless_dev *wdev) { struct cfg80211_registered_device *rdev = wiphy_to_rdev(wdev->wiphy); struct cfg80211_bss *bss; - u16 capa = WLAN_CAPABILITY_ESS; ASSERT_WDEV_LOCK(wdev); - if (wdev->conn->params.privacy) - capa |= WLAN_CAPABILITY_PRIVACY; - bss = cfg80211_get_bss(wdev->wiphy, wdev->conn->params.channel, wdev->conn->params.bssid, wdev->conn->params.ssid, wdev->conn->params.ssid_len, - WLAN_CAPABILITY_ESS | WLAN_CAPABILITY_PRIVACY, - capa); + IEEE80211_BSS_TYPE_ESS, + IEEE80211_PRIVACY(wdev->conn->params.privacy)); if (!bss) return NULL; @@ -427,6 +423,62 @@ void cfg80211_sme_assoc_timeout(struct wireless_dev *wdev) schedule_work(&rdev->conn_work); } +static int cfg80211_sme_get_conn_ies(struct wireless_dev *wdev, + const u8 *ies, size_t ies_len, + const u8 **out_ies, size_t *out_ies_len) +{ + struct cfg80211_registered_device *rdev = wiphy_to_rdev(wdev->wiphy); + u8 *buf; + size_t offs; + + if (!rdev->wiphy.extended_capabilities_len || + (ies && cfg80211_find_ie(WLAN_EID_EXT_CAPABILITY, ies, ies_len))) { + *out_ies = kmemdup(ies, ies_len, GFP_KERNEL); + if (!*out_ies) + return -ENOMEM; + *out_ies_len = ies_len; + return 0; + } + + buf = kmalloc(ies_len + rdev->wiphy.extended_capabilities_len + 2, + GFP_KERNEL); + if (!buf) + return -ENOMEM; + + if (ies_len) { + static const u8 before_extcapa[] = { + /* not listing IEs expected to be created by driver */ + WLAN_EID_RSN, + WLAN_EID_QOS_CAPA, + WLAN_EID_RRM_ENABLED_CAPABILITIES, + WLAN_EID_MOBILITY_DOMAIN, + WLAN_EID_SUPPORTED_REGULATORY_CLASSES, + WLAN_EID_BSS_COEX_2040, + }; + + offs = ieee80211_ie_split(ies, ies_len, before_extcapa, + ARRAY_SIZE(before_extcapa), 0); + memcpy(buf, ies, offs); + /* leave a whole for extended capabilities IE */ + memcpy(buf + offs + rdev->wiphy.extended_capabilities_len + 2, + ies + offs, ies_len - offs); + } else { + offs = 0; + } + + /* place extended capabilities IE (with only driver capabilities) */ + buf[offs] = WLAN_EID_EXT_CAPABILITY; + buf[offs + 1] = rdev->wiphy.extended_capabilities_len; + memcpy(buf + offs + 2, + rdev->wiphy.extended_capabilities, + rdev->wiphy.extended_capabilities_len); + + *out_ies = buf; + *out_ies_len = ies_len + rdev->wiphy.extended_capabilities_len + 2; + + return 0; +} + static int cfg80211_sme_connect(struct wireless_dev *wdev, struct cfg80211_connect_params *connect, const u8 *prev_bssid) @@ -457,16 +509,14 @@ static int cfg80211_sme_connect(struct wireless_dev *wdev, memcpy(wdev->conn->bssid, connect->bssid, ETH_ALEN); } - if (connect->ie) { - wdev->conn->ie = kmemdup(connect->ie, connect->ie_len, - GFP_KERNEL); - wdev->conn->params.ie = wdev->conn->ie; - if (!wdev->conn->ie) { - kfree(wdev->conn); - wdev->conn = NULL; - return -ENOMEM; - } + if (cfg80211_sme_get_conn_ies(wdev, connect->ie, connect->ie_len, + &wdev->conn->ie, + &wdev->conn->params.ie_len)) { + kfree(wdev->conn); + wdev->conn = NULL; + return -ENOMEM; } + wdev->conn->params.ie = wdev->conn->ie; if (connect->auth_type == NL80211_AUTHTYPE_AUTOMATIC) { wdev->conn->auto_auth = true; @@ -637,8 +687,8 @@ void __cfg80211_connect_result(struct net_device *dev, const u8 *bssid, WARN_ON_ONCE(!wiphy_to_rdev(wdev->wiphy)->ops->connect); bss = cfg80211_get_bss(wdev->wiphy, NULL, bssid, wdev->ssid, wdev->ssid_len, - WLAN_CAPABILITY_ESS, - WLAN_CAPABILITY_ESS); + IEEE80211_BSS_TYPE_ESS, + IEEE80211_PRIVACY_ANY); if (bss) cfg80211_hold_bss(bss_from_pub(bss)); } @@ -795,8 +845,8 @@ void cfg80211_roamed(struct net_device *dev, struct cfg80211_bss *bss; bss = cfg80211_get_bss(wdev->wiphy, channel, bssid, wdev->ssid, - wdev->ssid_len, WLAN_CAPABILITY_ESS, - WLAN_CAPABILITY_ESS); + wdev->ssid_len, + IEEE80211_BSS_TYPE_ESS, IEEE80211_PRIVACY_ANY); if (WARN_ON(!bss)) return; diff --git a/net/wireless/trace.h b/net/wireless/trace.h index b17b3692f8c2..af3617c9879e 100644 --- a/net/wireless/trace.h +++ b/net/wireless/trace.h @@ -7,6 +7,7 @@ #include <linux/tracepoint.h> #include <linux/rtnetlink.h> +#include <linux/etherdevice.h> #include <net/cfg80211.h> #include "core.h" @@ -15,7 +16,7 @@ if (given_mac) \ memcpy(__entry->entry_mac, given_mac, ETH_ALEN); \ else \ - memset(__entry->entry_mac, 0, ETH_ALEN); \ + eth_zero_addr(__entry->entry_mac); \ } while (0) #define MAC_PR_FMT "%pM" #define MAC_PR_ARG(entry_mac) (__entry->entry_mac) @@ -627,6 +628,7 @@ DECLARE_EVENT_CLASS(station_add_change, __field(u8, plink_state) __field(u8, uapsd_queues) __array(u8, ht_capa, (int)sizeof(struct ieee80211_ht_cap)) + __array(char, vlan, IFNAMSIZ) ), TP_fast_assign( WIPHY_ASSIGN; @@ -644,16 +646,19 @@ DECLARE_EVENT_CLASS(station_add_change, if (params->ht_capa) memcpy(__entry->ht_capa, params->ht_capa, sizeof(struct ieee80211_ht_cap)); + memset(__entry->vlan, 0, sizeof(__entry->vlan)); + if (params->vlan) + memcpy(__entry->vlan, params->vlan->name, IFNAMSIZ); ), TP_printk(WIPHY_PR_FMT ", " NETDEV_PR_FMT ", station mac: " MAC_PR_FMT ", station flags mask: %u, station flags set: %u, " "station modify mask: %u, listen interval: %d, aid: %u, " - "plink action: %u, plink state: %u, uapsd queues: %u", + "plink action: %u, plink state: %u, uapsd queues: %u, vlan:%s", WIPHY_PR_ARG, NETDEV_PR_ARG, MAC_PR_ARG(sta_mac), __entry->sta_flags_mask, __entry->sta_flags_set, __entry->sta_modify_mask, __entry->listen_interval, __entry->aid, __entry->plink_action, __entry->plink_state, - __entry->uapsd_queues) + __entry->uapsd_queues, __entry->vlan) ); DEFINE_EVENT(station_add_change, rdev_add_station, @@ -1077,7 +1082,7 @@ TRACE_EVENT(rdev_auth, if (req->bss) MAC_ASSIGN(bssid, req->bss->bssid); else - memset(__entry->bssid, 0, ETH_ALEN); + eth_zero_addr(__entry->bssid); __entry->auth_type = req->auth_type; ), TP_printk(WIPHY_PR_FMT ", " NETDEV_PR_FMT ", auth type: %d, bssid: " MAC_PR_FMT, @@ -1103,7 +1108,7 @@ TRACE_EVENT(rdev_assoc, if (req->bss) MAC_ASSIGN(bssid, req->bss->bssid); else - memset(__entry->bssid, 0, ETH_ALEN); + eth_zero_addr(__entry->bssid); MAC_ASSIGN(prev_bssid, req->prev_bssid); __entry->use_mfp = req->use_mfp; __entry->flags = req->flags; @@ -1153,7 +1158,7 @@ TRACE_EVENT(rdev_disassoc, if (req->bss) MAC_ASSIGN(bssid, req->bss->bssid); else - memset(__entry->bssid, 0, ETH_ALEN); + eth_zero_addr(__entry->bssid); __entry->reason_code = req->reason_code; __entry->local_state_change = req->local_state_change; ), @@ -2636,28 +2641,30 @@ DEFINE_EVENT(wiphy_only_evt, cfg80211_sched_scan_stopped, TRACE_EVENT(cfg80211_get_bss, TP_PROTO(struct wiphy *wiphy, struct ieee80211_channel *channel, const u8 *bssid, const u8 *ssid, size_t ssid_len, - u16 capa_mask, u16 capa_val), - TP_ARGS(wiphy, channel, bssid, ssid, ssid_len, capa_mask, capa_val), + enum ieee80211_bss_type bss_type, + enum ieee80211_privacy privacy), + TP_ARGS(wiphy, channel, bssid, ssid, ssid_len, bss_type, privacy), TP_STRUCT__entry( WIPHY_ENTRY CHAN_ENTRY MAC_ENTRY(bssid) __dynamic_array(u8, ssid, ssid_len) - __field(u16, capa_mask) - __field(u16, capa_val) + __field(enum ieee80211_bss_type, bss_type) + __field(enum ieee80211_privacy, privacy) ), TP_fast_assign( WIPHY_ASSIGN; CHAN_ASSIGN(channel); MAC_ASSIGN(bssid, bssid); memcpy(__get_dynamic_array(ssid), ssid, ssid_len); - __entry->capa_mask = capa_mask; - __entry->capa_val = capa_val; - ), - TP_printk(WIPHY_PR_FMT ", " CHAN_PR_FMT ", " MAC_PR_FMT ", buf: %#.2x, " - "capa_mask: %d, capa_val: %u", WIPHY_PR_ARG, CHAN_PR_ARG, - MAC_PR_ARG(bssid), ((u8 *)__get_dynamic_array(ssid))[0], - __entry->capa_mask, __entry->capa_val) + __entry->bss_type = bss_type; + __entry->privacy = privacy; + ), + TP_printk(WIPHY_PR_FMT ", " CHAN_PR_FMT ", " MAC_PR_FMT + ", buf: %#.2x, bss_type: %d, privacy: %d", + WIPHY_PR_ARG, CHAN_PR_ARG, MAC_PR_ARG(bssid), + ((u8 *)__get_dynamic_array(ssid))[0], __entry->bss_type, + __entry->privacy) ); TRACE_EVENT(cfg80211_inform_bss_width_frame, diff --git a/net/wireless/util.c b/net/wireless/util.c index 6903dbdcb8c1..70051ab52f4f 100644 --- a/net/wireless/util.c +++ b/net/wireless/util.c @@ -1290,12 +1290,54 @@ int cfg80211_get_p2p_attr(const u8 *ies, unsigned int len, } EXPORT_SYMBOL(cfg80211_get_p2p_attr); +static bool ieee80211_id_in_list(const u8 *ids, int n_ids, u8 id) +{ + int i; + + for (i = 0; i < n_ids; i++) + if (ids[i] == id) + return true; + return false; +} + +size_t ieee80211_ie_split_ric(const u8 *ies, size_t ielen, + const u8 *ids, int n_ids, + const u8 *after_ric, int n_after_ric, + size_t offset) +{ + size_t pos = offset; + + while (pos < ielen && ieee80211_id_in_list(ids, n_ids, ies[pos])) { + if (ies[pos] == WLAN_EID_RIC_DATA && n_after_ric) { + pos += 2 + ies[pos + 1]; + + while (pos < ielen && + !ieee80211_id_in_list(after_ric, n_after_ric, + ies[pos])) + pos += 2 + ies[pos + 1]; + } else { + pos += 2 + ies[pos + 1]; + } + } + + return pos; +} +EXPORT_SYMBOL(ieee80211_ie_split_ric); + +size_t ieee80211_ie_split(const u8 *ies, size_t ielen, + const u8 *ids, int n_ids, size_t offset) +{ + return ieee80211_ie_split_ric(ies, ielen, ids, n_ids, NULL, 0, offset); +} +EXPORT_SYMBOL(ieee80211_ie_split); + bool ieee80211_operating_class_to_band(u8 operating_class, enum ieee80211_band *band) { switch (operating_class) { case 112: case 115 ... 127: + case 128 ... 130: *band = IEEE80211_BAND_5GHZ; return true; case 81: @@ -1313,6 +1355,135 @@ bool ieee80211_operating_class_to_band(u8 operating_class, } EXPORT_SYMBOL(ieee80211_operating_class_to_band); +bool ieee80211_chandef_to_operating_class(struct cfg80211_chan_def *chandef, + u8 *op_class) +{ + u8 vht_opclass; + u16 freq = chandef->center_freq1; + + if (freq >= 2412 && freq <= 2472) { + if (chandef->width > NL80211_CHAN_WIDTH_40) + return false; + + /* 2.407 GHz, channels 1..13 */ + if (chandef->width == NL80211_CHAN_WIDTH_40) { + if (freq > chandef->chan->center_freq) + *op_class = 83; /* HT40+ */ + else + *op_class = 84; /* HT40- */ + } else { + *op_class = 81; + } + + return true; + } + + if (freq == 2484) { + if (chandef->width > NL80211_CHAN_WIDTH_40) + return false; + + *op_class = 82; /* channel 14 */ + return true; + } + + switch (chandef->width) { + case NL80211_CHAN_WIDTH_80: + vht_opclass = 128; + break; + case NL80211_CHAN_WIDTH_160: + vht_opclass = 129; + break; + case NL80211_CHAN_WIDTH_80P80: + vht_opclass = 130; + break; + case NL80211_CHAN_WIDTH_10: + case NL80211_CHAN_WIDTH_5: + return false; /* unsupported for now */ + default: + vht_opclass = 0; + break; + } + + /* 5 GHz, channels 36..48 */ + if (freq >= 5180 && freq <= 5240) { + if (vht_opclass) { + *op_class = vht_opclass; + } else if (chandef->width == NL80211_CHAN_WIDTH_40) { + if (freq > chandef->chan->center_freq) + *op_class = 116; + else + *op_class = 117; + } else { + *op_class = 115; + } + + return true; + } + + /* 5 GHz, channels 52..64 */ + if (freq >= 5260 && freq <= 5320) { + if (vht_opclass) { + *op_class = vht_opclass; + } else if (chandef->width == NL80211_CHAN_WIDTH_40) { + if (freq > chandef->chan->center_freq) + *op_class = 119; + else + *op_class = 120; + } else { + *op_class = 118; + } + + return true; + } + + /* 5 GHz, channels 100..144 */ + if (freq >= 5500 && freq <= 5720) { + if (vht_opclass) { + *op_class = vht_opclass; + } else if (chandef->width == NL80211_CHAN_WIDTH_40) { + if (freq > chandef->chan->center_freq) + *op_class = 122; + else + *op_class = 123; + } else { + *op_class = 121; + } + + return true; + } + + /* 5 GHz, channels 149..169 */ + if (freq >= 5745 && freq <= 5845) { + if (vht_opclass) { + *op_class = vht_opclass; + } else if (chandef->width == NL80211_CHAN_WIDTH_40) { + if (freq > chandef->chan->center_freq) + *op_class = 126; + else + *op_class = 127; + } else if (freq <= 5805) { + *op_class = 124; + } else { + *op_class = 125; + } + + return true; + } + + /* 56.16 GHz, channel 1..4 */ + if (freq >= 56160 + 2160 * 1 && freq <= 56160 + 2160 * 4) { + if (chandef->width >= NL80211_CHAN_WIDTH_40) + return false; + + *op_class = 180; + return true; + } + + /* not supported yet */ + return false; +} +EXPORT_SYMBOL(ieee80211_chandef_to_operating_class); + int cfg80211_validate_beacon_int(struct cfg80211_registered_device *rdev, u32 beacon_int) { diff --git a/net/wireless/wext-compat.c b/net/wireless/wext-compat.c index 5b24d39d7903..fff1bef6ed6d 100644 --- a/net/wireless/wext-compat.c +++ b/net/wireless/wext-compat.c @@ -63,7 +63,7 @@ int cfg80211_wext_giwname(struct net_device *dev, return 0; } -EXPORT_SYMBOL_GPL(cfg80211_wext_giwname); +EXPORT_WEXT_HANDLER(cfg80211_wext_giwname); int cfg80211_wext_siwmode(struct net_device *dev, struct iw_request_info *info, u32 *mode, char *extra) @@ -99,7 +99,7 @@ int cfg80211_wext_siwmode(struct net_device *dev, struct iw_request_info *info, return cfg80211_change_iface(rdev, dev, type, NULL, &vifparams); } -EXPORT_SYMBOL_GPL(cfg80211_wext_siwmode); +EXPORT_WEXT_HANDLER(cfg80211_wext_siwmode); int cfg80211_wext_giwmode(struct net_device *dev, struct iw_request_info *info, u32 *mode, char *extra) @@ -134,7 +134,7 @@ int cfg80211_wext_giwmode(struct net_device *dev, struct iw_request_info *info, } return 0; } -EXPORT_SYMBOL_GPL(cfg80211_wext_giwmode); +EXPORT_WEXT_HANDLER(cfg80211_wext_giwmode); int cfg80211_wext_giwrange(struct net_device *dev, @@ -248,7 +248,7 @@ int cfg80211_wext_giwrange(struct net_device *dev, return 0; } -EXPORT_SYMBOL_GPL(cfg80211_wext_giwrange); +EXPORT_WEXT_HANDLER(cfg80211_wext_giwrange); /** @@ -303,7 +303,7 @@ int cfg80211_wext_siwrts(struct net_device *dev, return err; } -EXPORT_SYMBOL_GPL(cfg80211_wext_siwrts); +EXPORT_WEXT_HANDLER(cfg80211_wext_siwrts); int cfg80211_wext_giwrts(struct net_device *dev, struct iw_request_info *info, @@ -317,7 +317,7 @@ int cfg80211_wext_giwrts(struct net_device *dev, return 0; } -EXPORT_SYMBOL_GPL(cfg80211_wext_giwrts); +EXPORT_WEXT_HANDLER(cfg80211_wext_giwrts); int cfg80211_wext_siwfrag(struct net_device *dev, struct iw_request_info *info, @@ -343,7 +343,7 @@ int cfg80211_wext_siwfrag(struct net_device *dev, return err; } -EXPORT_SYMBOL_GPL(cfg80211_wext_siwfrag); +EXPORT_WEXT_HANDLER(cfg80211_wext_siwfrag); int cfg80211_wext_giwfrag(struct net_device *dev, struct iw_request_info *info, @@ -357,7 +357,7 @@ int cfg80211_wext_giwfrag(struct net_device *dev, return 0; } -EXPORT_SYMBOL_GPL(cfg80211_wext_giwfrag); +EXPORT_WEXT_HANDLER(cfg80211_wext_giwfrag); static int cfg80211_wext_siwretry(struct net_device *dev, struct iw_request_info *info, @@ -427,7 +427,7 @@ int cfg80211_wext_giwretry(struct net_device *dev, return 0; } -EXPORT_SYMBOL_GPL(cfg80211_wext_giwretry); +EXPORT_WEXT_HANDLER(cfg80211_wext_giwretry); static int __cfg80211_set_encryption(struct cfg80211_registered_device *rdev, struct net_device *dev, bool pairwise, diff --git a/net/wireless/wext-compat.h b/net/wireless/wext-compat.h index ebcacca2f731..94c7405a5413 100644 --- a/net/wireless/wext-compat.h +++ b/net/wireless/wext-compat.h @@ -4,6 +4,12 @@ #include <net/iw_handler.h> #include <linux/wireless.h> +#ifdef CONFIG_CFG80211_WEXT_EXPORT +#define EXPORT_WEXT_HANDLER(h) EXPORT_SYMBOL_GPL(h) +#else +#define EXPORT_WEXT_HANDLER(h) +#endif /* CONFIG_CFG80211_WEXT_EXPORT */ + int cfg80211_ibss_wext_siwfreq(struct net_device *dev, struct iw_request_info *info, struct iw_freq *freq, char *extra); diff --git a/net/wireless/wext-sme.c b/net/wireless/wext-sme.c index 368611c05739..a4e8af3321d2 100644 --- a/net/wireless/wext-sme.c +++ b/net/wireless/wext-sme.c @@ -322,7 +322,7 @@ int cfg80211_mgd_wext_giwap(struct net_device *dev, if (wdev->current_bss) memcpy(ap_addr->sa_data, wdev->current_bss->pub.bssid, ETH_ALEN); else - memset(ap_addr->sa_data, 0, ETH_ALEN); + eth_zero_addr(ap_addr->sa_data); wdev_unlock(wdev); return 0; diff --git a/net/x25/af_x25.c b/net/x25/af_x25.c index d9149b68b9bc..c3ab230e4493 100644 --- a/net/x25/af_x25.c +++ b/net/x25/af_x25.c @@ -1077,8 +1077,7 @@ out_clear_request: goto out; } -static int x25_sendmsg(struct kiocb *iocb, struct socket *sock, - struct msghdr *msg, size_t len) +static int x25_sendmsg(struct socket *sock, struct msghdr *msg, size_t len) { struct sock *sk = sock->sk; struct x25_sock *x25 = x25_sk(sk); @@ -1252,8 +1251,7 @@ out_kfree_skb: } -static int x25_recvmsg(struct kiocb *iocb, struct socket *sock, - struct msghdr *msg, size_t size, +static int x25_recvmsg(struct socket *sock, struct msghdr *msg, size_t size, int flags) { struct sock *sk = sock->sk; diff --git a/net/xfrm/xfrm_input.c b/net/xfrm/xfrm_input.c index 85d1d4764612..526c4feb3b50 100644 --- a/net/xfrm/xfrm_input.c +++ b/net/xfrm/xfrm_input.c @@ -238,11 +238,6 @@ int xfrm_input(struct sk_buff *skb, int nexthdr, __be32 spi, int encap_type) skb->sp->xvec[skb->sp->len++] = x; - if (xfrm_tunnel_check(skb, x, family)) { - XFRM_INC_STATS(net, LINUX_MIB_XFRMINSTATEMODEERROR); - goto drop; - } - spin_lock(&x->lock); if (unlikely(x->km.state == XFRM_STATE_ACQ)) { XFRM_INC_STATS(net, LINUX_MIB_XFRMACQUIREERROR); @@ -271,6 +266,11 @@ int xfrm_input(struct sk_buff *skb, int nexthdr, __be32 spi, int encap_type) spin_unlock(&x->lock); + if (xfrm_tunnel_check(skb, x, family)) { + XFRM_INC_STATS(net, LINUX_MIB_XFRMINSTATEMODEERROR); + goto drop; + } + seq_hi = htonl(xfrm_replay_seqhi(x, seq)); XFRM_SKB_CB(skb)->seq.input.low = seq; diff --git a/net/xfrm/xfrm_output.c b/net/xfrm/xfrm_output.c index 7c532856b398..fbcedbe33190 100644 --- a/net/xfrm/xfrm_output.c +++ b/net/xfrm/xfrm_output.c @@ -19,7 +19,7 @@ #include <net/dst.h> #include <net/xfrm.h> -static int xfrm_output2(struct sk_buff *skb); +static int xfrm_output2(struct sock *sk, struct sk_buff *skb); static int xfrm_skb_check_space(struct sk_buff *skb) { @@ -130,7 +130,7 @@ int xfrm_output_resume(struct sk_buff *skb, int err) return dst_output(skb); err = nf_hook(skb_dst(skb)->ops->family, - NF_INET_POST_ROUTING, skb, + NF_INET_POST_ROUTING, skb->sk, skb, NULL, skb_dst(skb)->dev, xfrm_output2); if (unlikely(err != 1)) goto out; @@ -144,12 +144,12 @@ out: } EXPORT_SYMBOL_GPL(xfrm_output_resume); -static int xfrm_output2(struct sk_buff *skb) +static int xfrm_output2(struct sock *sk, struct sk_buff *skb) { return xfrm_output_resume(skb, 1); } -static int xfrm_output_gso(struct sk_buff *skb) +static int xfrm_output_gso(struct sock *sk, struct sk_buff *skb) { struct sk_buff *segs; @@ -165,7 +165,7 @@ static int xfrm_output_gso(struct sk_buff *skb) int err; segs->next = NULL; - err = xfrm_output2(segs); + err = xfrm_output2(sk, segs); if (unlikely(err)) { kfree_skb_list(nskb); @@ -178,13 +178,13 @@ static int xfrm_output_gso(struct sk_buff *skb) return 0; } -int xfrm_output(struct sk_buff *skb) +int xfrm_output(struct sock *sk, struct sk_buff *skb) { struct net *net = dev_net(skb_dst(skb)->dev); int err; if (skb_is_gso(skb)) - return xfrm_output_gso(skb); + return xfrm_output_gso(sk, skb); if (skb->ip_summed == CHECKSUM_PARTIAL) { err = skb_checksum_help(skb); @@ -195,7 +195,7 @@ int xfrm_output(struct sk_buff *skb) } } - return xfrm_output2(skb); + return xfrm_output2(sk, skb); } EXPORT_SYMBOL_GPL(xfrm_output); diff --git a/net/xfrm/xfrm_state.c b/net/xfrm/xfrm_state.c index de971b6d38c5..f5e39e35d73a 100644 --- a/net/xfrm/xfrm_state.c +++ b/net/xfrm/xfrm_state.c @@ -1043,12 +1043,12 @@ static struct xfrm_state *__find_acq_core(struct net *net, break; case AF_INET6: - *(struct in6_addr *)x->sel.daddr.a6 = *(struct in6_addr *)daddr; - *(struct in6_addr *)x->sel.saddr.a6 = *(struct in6_addr *)saddr; + x->sel.daddr.in6 = daddr->in6; + x->sel.saddr.in6 = saddr->in6; x->sel.prefixlen_d = 128; x->sel.prefixlen_s = 128; - *(struct in6_addr *)x->props.saddr.a6 = *(struct in6_addr *)saddr; - *(struct in6_addr *)x->id.daddr.a6 = *(struct in6_addr *)daddr; + x->props.saddr.in6 = saddr->in6; + x->id.daddr.in6 = daddr->in6; break; } diff --git a/net/xfrm/xfrm_user.c b/net/xfrm/xfrm_user.c index 7de2ed9ec46d..2091664295ba 100644 --- a/net/xfrm/xfrm_user.c +++ b/net/xfrm/xfrm_user.c @@ -2423,6 +2423,11 @@ static int xfrm_user_rcv_msg(struct sk_buff *skb, struct nlmsghdr *nlh) const struct xfrm_link *link; int type, err; +#ifdef CONFIG_COMPAT + if (is_compat_task()) + return -ENOTSUPP; +#endif + type = nlh->nlmsg_type; if (type > XFRM_MSG_MAX) return -EINVAL; |