From 8496e85c20e7836b3dec97780e40f420a3ae2801 Mon Sep 17 00:00:00 2001 From: "Rafael J. Wysocki" Date: Sun, 1 Dec 2013 02:34:37 +0100 Subject: PCI / tg3: Give up chip reset and carrier loss handling if PCI device is not present Modify tg3_chip_reset() and tg3_close() to check if the PCI network adapter device is accessible at all in order to skip poking it or trying to handle a carrier loss in vain when that's not the case. Introduce a special PCI helper function pci_device_is_present() for this purpose. Of course, this uncovers the lack of the appropriate RTNL locking in tg3_suspend() and tg3_resume(), so add that locking in there too. These changes prevent tg3 from burning a CPU at 100% load level for solid several seconds after the Thunderbolt link is disconnected from a Matrox DS1 docking station. Signed-off-by: Rafael J. Wysocki Acked-by: Michael Chan Signed-off-by: David S. Miller --- include/linux/pci.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/pci.h b/include/linux/pci.h index 1084a15175e0..25a389566e47 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -960,6 +960,7 @@ void pci_update_resource(struct pci_dev *dev, int resno); int __must_check pci_assign_resource(struct pci_dev *dev, int i); int __must_check pci_reassign_resource(struct pci_dev *dev, int i, resource_size_t add_size, resource_size_t align); int pci_select_bars(struct pci_dev *dev, unsigned long flags); +bool pci_device_is_present(struct pci_dev *pdev); /* ROM control related routines */ int pci_enable_rom(struct pci_dev *pdev); -- cgit v1.3-8-gc7d7 From 7ce5a27f2ef8ed4f8f892f46391f933c0e2ac0f1 Mon Sep 17 00:00:00 2001 From: "David S. Miller" Date: Mon, 2 Dec 2013 17:26:05 -0500 Subject: Revert "net: Handle CHECKSUM_COMPLETE more adequately in pskb_trim_rcsum()." This reverts commit 018c5bba052b3a383d83cf0c756da0e7bc748397. It causes regressions for people using chips driven by the sungem driver. Suspicion is that the skb->csum value isn't being adjusted properly. The change also has a bug in that if __pskb_trim() fails, we'll leave a corruped skb->csum value in there. We would really need to revert it to it's original value in that case. Signed-off-by: David S. Miller --- include/linux/skbuff.h | 39 ++++++++++++++++++--------------------- 1 file changed, 18 insertions(+), 21 deletions(-) (limited to 'include/linux') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index bec1cc7d5e3c..215b5ea1cb30 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -2263,6 +2263,24 @@ static inline void skb_postpull_rcsum(struct sk_buff *skb, unsigned char *skb_pull_rcsum(struct sk_buff *skb, unsigned int len); +/** + * pskb_trim_rcsum - trim received skb and update checksum + * @skb: buffer to trim + * @len: new length + * + * This is exactly the same as pskb_trim except that it ensures the + * checksum of received packets are still valid after the operation. + */ + +static inline int pskb_trim_rcsum(struct sk_buff *skb, unsigned int len) +{ + if (likely(len >= skb->len)) + return 0; + if (skb->ip_summed == CHECKSUM_COMPLETE) + skb->ip_summed = CHECKSUM_NONE; + return __pskb_trim(skb, len); +} + #define skb_queue_walk(queue, skb) \ for (skb = (queue)->next; \ skb != (struct sk_buff *)(queue); \ @@ -2360,27 +2378,6 @@ __wsum __skb_checksum(const struct sk_buff *skb, int offset, int len, __wsum skb_checksum(const struct sk_buff *skb, int offset, int len, __wsum csum); -/** - * pskb_trim_rcsum - trim received skb and update checksum - * @skb: buffer to trim - * @len: new length - * - * This is exactly the same as pskb_trim except that it ensures the - * checksum of received packets are still valid after the operation. - */ - -static inline int pskb_trim_rcsum(struct sk_buff *skb, unsigned int len) -{ - if (likely(len >= skb->len)) - return 0; - if (skb->ip_summed == CHECKSUM_COMPLETE) { - __wsum adj = skb_checksum(skb, len, skb->len - len, 0); - - skb->csum = csum_sub(skb->csum, adj); - } - return __pskb_trim(skb, len); -} - static inline void *skb_header_pointer(const struct sk_buff *skb, int offset, int len, void *buffer) { -- cgit v1.3-8-gc7d7 From 1431fb31ecbaba1b5718006128f0f2ed0b94e1c3 Mon Sep 17 00:00:00 2001 From: Paul Durrant Date: Tue, 3 Dec 2013 17:39:29 +0000 Subject: xen-netback: fix fragment detection in checksum setup The code to detect fragments in checksum_setup() was missing for IPv4 and too eager for IPv6. (It transpires that Windows seems to send IPv6 packets with a fragment header even if they are not a fragment - i.e. offset is zero, and M bit is not set). This patch also incorporates a fix to callers of maybe_pull_tail() where skb->network_header was being erroneously added to the length argument. Signed-off-by: Paul Durrant Signed-off-by: Zoltan Kiss Cc: Wei Liu Cc: Ian Campbell Cc: David Vrabel cc: David Miller Acked-by: Wei Liu Signed-off-by: David S. Miller --- drivers/net/xen-netback/netback.c | 236 ++++++++++++++++++++++---------------- include/linux/ipv6.h | 1 + include/net/ipv6.h | 3 +- 3 files changed, 140 insertions(+), 100 deletions(-) (limited to 'include/linux') diff --git a/drivers/net/xen-netback/netback.c b/drivers/net/xen-netback/netback.c index 64f0e0d18b81..acf13920e6d1 100644 --- a/drivers/net/xen-netback/netback.c +++ b/drivers/net/xen-netback/netback.c @@ -1149,49 +1149,72 @@ static int xenvif_set_skb_gso(struct xenvif *vif, return 0; } -static inline void maybe_pull_tail(struct sk_buff *skb, unsigned int len) +static inline int maybe_pull_tail(struct sk_buff *skb, unsigned int len, + unsigned int max) { - if (skb_is_nonlinear(skb) && skb_headlen(skb) < len) { - /* If we need to pullup then pullup to the max, so we - * won't need to do it again. - */ - int target = min_t(int, skb->len, MAX_TCP_HEADER); - __pskb_pull_tail(skb, target - skb_headlen(skb)); - } + if (skb_headlen(skb) >= len) + return 0; + + /* If we need to pullup then pullup to the max, so we + * won't need to do it again. + */ + if (max > skb->len) + max = skb->len; + + if (__pskb_pull_tail(skb, max - skb_headlen(skb)) == NULL) + return -ENOMEM; + + if (skb_headlen(skb) < len) + return -EPROTO; + + return 0; } +/* This value should be large enough to cover a tagged ethernet header plus + * maximally sized IP and TCP or UDP headers. + */ +#define MAX_IP_HDR_LEN 128 + static int checksum_setup_ip(struct xenvif *vif, struct sk_buff *skb, int recalculate_partial_csum) { - struct iphdr *iph = (void *)skb->data; - unsigned int header_size; unsigned int off; - int err = -EPROTO; + bool fragment; + int err; + + fragment = false; + + err = maybe_pull_tail(skb, + sizeof(struct iphdr), + MAX_IP_HDR_LEN); + if (err < 0) + goto out; - off = sizeof(struct iphdr); + if (ip_hdr(skb)->frag_off & htons(IP_OFFSET | IP_MF)) + fragment = true; - header_size = skb->network_header + off + MAX_IPOPTLEN; - maybe_pull_tail(skb, header_size); + off = ip_hdrlen(skb); - off = iph->ihl * 4; + err = -EPROTO; - switch (iph->protocol) { + switch (ip_hdr(skb)->protocol) { case IPPROTO_TCP: if (!skb_partial_csum_set(skb, off, offsetof(struct tcphdr, check))) goto out; if (recalculate_partial_csum) { - struct tcphdr *tcph = tcp_hdr(skb); - - header_size = skb->network_header + - off + - sizeof(struct tcphdr); - maybe_pull_tail(skb, header_size); - - tcph->check = ~csum_tcpudp_magic(iph->saddr, iph->daddr, - skb->len - off, - IPPROTO_TCP, 0); + err = maybe_pull_tail(skb, + off + sizeof(struct tcphdr), + MAX_IP_HDR_LEN); + if (err < 0) + goto out; + + tcp_hdr(skb)->check = + ~csum_tcpudp_magic(ip_hdr(skb)->saddr, + ip_hdr(skb)->daddr, + skb->len - off, + IPPROTO_TCP, 0); } break; case IPPROTO_UDP: @@ -1200,24 +1223,20 @@ static int checksum_setup_ip(struct xenvif *vif, struct sk_buff *skb, goto out; if (recalculate_partial_csum) { - struct udphdr *udph = udp_hdr(skb); - - header_size = skb->network_header + - off + - sizeof(struct udphdr); - maybe_pull_tail(skb, header_size); - - udph->check = ~csum_tcpudp_magic(iph->saddr, iph->daddr, - skb->len - off, - IPPROTO_UDP, 0); + err = maybe_pull_tail(skb, + off + sizeof(struct udphdr), + MAX_IP_HDR_LEN); + if (err < 0) + goto out; + + udp_hdr(skb)->check = + ~csum_tcpudp_magic(ip_hdr(skb)->saddr, + ip_hdr(skb)->daddr, + skb->len - off, + IPPROTO_UDP, 0); } break; default: - if (net_ratelimit()) - netdev_err(vif->dev, - "Attempting to checksum a non-TCP/UDP packet, " - "dropping a protocol %d packet\n", - iph->protocol); goto out; } @@ -1227,75 +1246,99 @@ out: return err; } +/* This value should be large enough to cover a tagged ethernet header plus + * an IPv6 header, all options, and a maximal TCP or UDP header. + */ +#define MAX_IPV6_HDR_LEN 256 + +#define OPT_HDR(type, skb, off) \ + (type *)(skb_network_header(skb) + (off)) + static int checksum_setup_ipv6(struct xenvif *vif, struct sk_buff *skb, int recalculate_partial_csum) { - int err = -EPROTO; - struct ipv6hdr *ipv6h = (void *)skb->data; + int err; u8 nexthdr; - unsigned int header_size; unsigned int off; + unsigned int len; bool fragment; bool done; + fragment = false; done = false; off = sizeof(struct ipv6hdr); - header_size = skb->network_header + off; - maybe_pull_tail(skb, header_size); + err = maybe_pull_tail(skb, off, MAX_IPV6_HDR_LEN); + if (err < 0) + goto out; - nexthdr = ipv6h->nexthdr; + nexthdr = ipv6_hdr(skb)->nexthdr; - while ((off <= sizeof(struct ipv6hdr) + ntohs(ipv6h->payload_len)) && - !done) { + len = sizeof(struct ipv6hdr) + ntohs(ipv6_hdr(skb)->payload_len); + while (off <= len && !done) { switch (nexthdr) { case IPPROTO_DSTOPTS: case IPPROTO_HOPOPTS: case IPPROTO_ROUTING: { - struct ipv6_opt_hdr *hp = (void *)(skb->data + off); + struct ipv6_opt_hdr *hp; - header_size = skb->network_header + - off + - sizeof(struct ipv6_opt_hdr); - maybe_pull_tail(skb, header_size); + err = maybe_pull_tail(skb, + off + + sizeof(struct ipv6_opt_hdr), + MAX_IPV6_HDR_LEN); + if (err < 0) + goto out; + hp = OPT_HDR(struct ipv6_opt_hdr, skb, off); nexthdr = hp->nexthdr; off += ipv6_optlen(hp); break; } case IPPROTO_AH: { - struct ip_auth_hdr *hp = (void *)(skb->data + off); + struct ip_auth_hdr *hp; + + err = maybe_pull_tail(skb, + off + + sizeof(struct ip_auth_hdr), + MAX_IPV6_HDR_LEN); + if (err < 0) + goto out; + + hp = OPT_HDR(struct ip_auth_hdr, skb, off); + nexthdr = hp->nexthdr; + off += ipv6_authlen(hp); + break; + } + case IPPROTO_FRAGMENT: { + struct frag_hdr *hp; - header_size = skb->network_header + - off + - sizeof(struct ip_auth_hdr); - maybe_pull_tail(skb, header_size); + err = maybe_pull_tail(skb, + off + + sizeof(struct frag_hdr), + MAX_IPV6_HDR_LEN); + if (err < 0) + goto out; + + hp = OPT_HDR(struct frag_hdr, skb, off); + + if (hp->frag_off & htons(IP6_OFFSET | IP6_MF)) + fragment = true; nexthdr = hp->nexthdr; - off += (hp->hdrlen+2)<<2; + off += sizeof(struct frag_hdr); break; } - case IPPROTO_FRAGMENT: - fragment = true; - /* fall through */ default: done = true; break; } } - if (!done) { - if (net_ratelimit()) - netdev_err(vif->dev, "Failed to parse packet header\n"); - goto out; - } + err = -EPROTO; - if (fragment) { - if (net_ratelimit()) - netdev_err(vif->dev, "Packet is a fragment!\n"); + if (!done || fragment) goto out; - } switch (nexthdr) { case IPPROTO_TCP: @@ -1304,17 +1347,17 @@ static int checksum_setup_ipv6(struct xenvif *vif, struct sk_buff *skb, goto out; if (recalculate_partial_csum) { - struct tcphdr *tcph = tcp_hdr(skb); - - header_size = skb->network_header + - off + - sizeof(struct tcphdr); - maybe_pull_tail(skb, header_size); - - tcph->check = ~csum_ipv6_magic(&ipv6h->saddr, - &ipv6h->daddr, - skb->len - off, - IPPROTO_TCP, 0); + err = maybe_pull_tail(skb, + off + sizeof(struct tcphdr), + MAX_IPV6_HDR_LEN); + if (err < 0) + goto out; + + tcp_hdr(skb)->check = + ~csum_ipv6_magic(&ipv6_hdr(skb)->saddr, + &ipv6_hdr(skb)->daddr, + skb->len - off, + IPPROTO_TCP, 0); } break; case IPPROTO_UDP: @@ -1323,25 +1366,20 @@ static int checksum_setup_ipv6(struct xenvif *vif, struct sk_buff *skb, goto out; if (recalculate_partial_csum) { - struct udphdr *udph = udp_hdr(skb); - - header_size = skb->network_header + - off + - sizeof(struct udphdr); - maybe_pull_tail(skb, header_size); - - udph->check = ~csum_ipv6_magic(&ipv6h->saddr, - &ipv6h->daddr, - skb->len - off, - IPPROTO_UDP, 0); + err = maybe_pull_tail(skb, + off + sizeof(struct udphdr), + MAX_IPV6_HDR_LEN); + if (err < 0) + goto out; + + udp_hdr(skb)->check = + ~csum_ipv6_magic(&ipv6_hdr(skb)->saddr, + &ipv6_hdr(skb)->daddr, + skb->len - off, + IPPROTO_UDP, 0); } break; default: - if (net_ratelimit()) - netdev_err(vif->dev, - "Attempting to checksum a non-TCP/UDP packet, " - "dropping a protocol %d packet\n", - nexthdr); goto out; } diff --git a/include/linux/ipv6.h b/include/linux/ipv6.h index 5d89d1b808a6..c56c350324e4 100644 --- a/include/linux/ipv6.h +++ b/include/linux/ipv6.h @@ -4,6 +4,7 @@ #include #define ipv6_optlen(p) (((p)->hdrlen+1) << 3) +#define ipv6_authlen(p) (((p)->hdrlen+2) << 2) /* * This structure contains configuration options per IPv6 link. */ diff --git a/include/net/ipv6.h b/include/net/ipv6.h index eb198acaac1d..488316e339a1 100644 --- a/include/net/ipv6.h +++ b/include/net/ipv6.h @@ -110,7 +110,8 @@ struct frag_hdr { __be32 identification; }; -#define IP6_MF 0x0001 +#define IP6_MF 0x0001 +#define IP6_OFFSET 0xFFF8 #include -- cgit v1.3-8-gc7d7 From 12663bfc97c8b3fdb292428105dd92d563164050 Mon Sep 17 00:00:00 2001 From: Sasha Levin Date: Sat, 7 Dec 2013 17:26:27 -0500 Subject: net: unix: allow set_peek_off to fail unix_dgram_recvmsg() will hold the readlock of the socket until recv is complete. In the same time, we may try to setsockopt(SO_PEEK_OFF) which will hang until unix_dgram_recvmsg() will complete (which can take a while) without allowing us to break out of it, triggering a hung task spew. Instead, allow set_peek_off to fail, this way userspace will not hang. Signed-off-by: Sasha Levin Acked-by: Pavel Emelyanov Signed-off-by: David S. Miller --- include/linux/net.h | 2 +- net/core/sock.c | 2 +- net/unix/af_unix.c | 8 ++++++-- 3 files changed, 8 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/net.h b/include/linux/net.h index 4bcee94cef93..69be3e6079c8 100644 --- a/include/linux/net.h +++ b/include/linux/net.h @@ -181,7 +181,7 @@ struct proto_ops { int offset, size_t size, int flags); ssize_t (*splice_read)(struct socket *sock, loff_t *ppos, struct pipe_inode_info *pipe, size_t len, unsigned int flags); - void (*set_peek_off)(struct sock *sk, int val); + int (*set_peek_off)(struct sock *sk, int val); }; #define DECLARE_SOCKADDR(type, dst, src) \ diff --git a/net/core/sock.c b/net/core/sock.c index ab20ed9b0f31..5393b4b719d7 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -882,7 +882,7 @@ set_rcvbuf: case SO_PEEK_OFF: if (sock->ops->set_peek_off) - sock->ops->set_peek_off(sk, val); + ret = sock->ops->set_peek_off(sk, val); else ret = -EOPNOTSUPP; break; diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c index 01625ccc3ae6..a0ca162e5bd5 100644 --- a/net/unix/af_unix.c +++ b/net/unix/af_unix.c @@ -530,13 +530,17 @@ static int unix_seqpacket_sendmsg(struct kiocb *, struct socket *, static int unix_seqpacket_recvmsg(struct kiocb *, struct socket *, struct msghdr *, size_t, int); -static void unix_set_peek_off(struct sock *sk, int val) +static int unix_set_peek_off(struct sock *sk, int val) { struct unix_sock *u = unix_sk(sk); - mutex_lock(&u->readlock); + if (mutex_lock_interruptible(&u->readlock)) + return -EINTR; + sk->sk_peek_off = val; mutex_unlock(&u->readlock); + + return 0; } -- cgit v1.3-8-gc7d7 From 4bd7b5127bd02c12c1cc837a7a0b6ce295eb2505 Mon Sep 17 00:00:00 2001 From: Sergei Shtylyov Date: Tue, 10 Dec 2013 02:20:41 +0300 Subject: micrel: add support for KSZ8041RNLI Renesas R-Car development boards use KSZ8041RNLI PHY which for some reason has ID of 0x00221537 that is not documented for KSZ8041-family PHYs and does not match the documented ID of 0x0022151x (where 'x' is the revision). We have to add the new #define PHY_ID_* and new ksphy_driver[] entry, almost the same as KSZ8041 one, differing only in the 'phy_id' and 'name' fields. Signed-off-by: Sergei Shtylyov Tested-by: Geert Uytterhoeven Signed-off-by: David S. Miller --- drivers/net/phy/micrel.c | 15 +++++++++++++++ include/linux/micrel_phy.h | 2 ++ 2 files changed, 17 insertions(+) (limited to 'include/linux') diff --git a/drivers/net/phy/micrel.c b/drivers/net/phy/micrel.c index 3ae28f420868..26fa05a472b4 100644 --- a/drivers/net/phy/micrel.c +++ b/drivers/net/phy/micrel.c @@ -335,6 +335,21 @@ static struct phy_driver ksphy_driver[] = { .suspend = genphy_suspend, .resume = genphy_resume, .driver = { .owner = THIS_MODULE,}, +}, { + .phy_id = PHY_ID_KSZ8041RNLI, + .phy_id_mask = 0x00fffff0, + .name = "Micrel KSZ8041RNLI", + .features = PHY_BASIC_FEATURES | + SUPPORTED_Pause | SUPPORTED_Asym_Pause, + .flags = PHY_HAS_MAGICANEG | PHY_HAS_INTERRUPT, + .config_init = kszphy_config_init, + .config_aneg = genphy_config_aneg, + .read_status = genphy_read_status, + .ack_interrupt = kszphy_ack_interrupt, + .config_intr = kszphy_config_intr, + .suspend = genphy_suspend, + .resume = genphy_resume, + .driver = { .owner = THIS_MODULE,}, }, { .phy_id = PHY_ID_KSZ8051, .phy_id_mask = 0x00fffff0, diff --git a/include/linux/micrel_phy.h b/include/linux/micrel_phy.h index ad05ce60c1c9..2e5b194b9b19 100644 --- a/include/linux/micrel_phy.h +++ b/include/linux/micrel_phy.h @@ -22,6 +22,8 @@ #define PHY_ID_KSZ8021 0x00221555 #define PHY_ID_KSZ8031 0x00221556 #define PHY_ID_KSZ8041 0x00221510 +/* undocumented */ +#define PHY_ID_KSZ8041RNLI 0x00221537 #define PHY_ID_KSZ8051 0x00221550 /* same id: ks8001 Rev. A/B, and ks8721 Rev 3. */ #define PHY_ID_KSZ8001 0x0022161A -- cgit v1.3-8-gc7d7 From a0a9663dd2146d54339237764e1bfc60e8a39328 Mon Sep 17 00:00:00 2001 From: Sebastian Siewior Date: Thu, 12 Dec 2013 10:15:59 +0100 Subject: net: make neigh_priv_len in struct net_device 16bit instead of 8bit neigh_priv_len is defined as u8. With all debug enabled struct ipoib_neigh has 200 bytes. The largest part is sk_buff_head with 96 bytes and here the spinlock with 72 bytes. The size value still fits in this u8 leaving some room for more. On -RT struct ipoib_neigh put on weight and has 392 bytes. The main reason is sk_buff_head with 288 and the fatty here is spinlock with 192 bytes. This does no longer fit into into neigh_priv_len and gcc complains. This patch changes neigh_priv_len from being 8bit to 16bit. Since the following element (dev_id) is 16bit followed by a spinlock which is aligned, the struct remains with a total size of 3200 (allmodconfig) / 2048 (with as much debug off as possible) bytes on x86-64. On x86-32 the struct is 1856 (allmodconfig) / 1216 (with as much debug off as possible) bytes long. The numbers were gained with and without the patch to prove that this change does not increase the size of the struct. Cc: Steven Rostedt Cc: Thomas Gleixner Signed-off-by: Sebastian Andrzej Siewior Signed-off-by: David S. Miller --- include/linux/netdevice.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 7f0ed423a360..d9a550bf3e8e 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -1255,7 +1255,7 @@ struct net_device { unsigned char perm_addr[MAX_ADDR_LEN]; /* permanent hw address */ unsigned char addr_assign_type; /* hw address assignment type */ unsigned char addr_len; /* hardware address length */ - unsigned char neigh_priv_len; + unsigned short neigh_priv_len; unsigned short dev_id; /* Used to differentiate devices * that share the same link * layer address -- cgit v1.3-8-gc7d7