From a5fe8e7695dc3f547e955ad2b662e3e72969e506 Mon Sep 17 00:00:00 2001 From: Eliad Peller Date: Wed, 11 Jun 2014 10:23:35 +0300 Subject: [PATCH 001/101] regulatory: add NUL to alpha2 alpha2 is defined as 2-chars array, but is used in multiple places as string (e.g. with nla_put_string calls), which might leak kernel data. Solve it by simply adding an extra char for the NULL terminator, making such operations safe. Cc: stable@vger.kernel.org Signed-off-by: Eliad Peller Signed-off-by: Johannes Berg --- include/net/regulatory.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/include/net/regulatory.h b/include/net/regulatory.h index 259992444e80..dad7ab20a8cb 100644 --- a/include/net/regulatory.h +++ b/include/net/regulatory.h @@ -167,7 +167,7 @@ struct ieee80211_reg_rule { struct ieee80211_regdomain { struct rcu_head rcu_head; u32 n_reg_rules; - char alpha2[2]; + char alpha2[3]; enum nl80211_dfs_regions dfs_region; struct ieee80211_reg_rule reg_rules[]; }; From 8993cf8edf42527119186b558766539243b791a5 Mon Sep 17 00:00:00 2001 From: Pablo Neira Ayuso Date: Mon, 11 Aug 2014 18:21:49 +0200 Subject: [PATCH 002/101] netfilter: move NAT Kconfig switches out of the iptables scope Currently, the NAT configs depend on iptables and ip6tables. However, users should be capable of enabling NAT for nft without having to switch on iptables. Fix this by adding new specific IP_NF_NAT and IP6_NF_NAT config switches for iptables and ip6tables NAT support. I have also moved the original NF_NAT_IPV4 and NF_NAT_IPV6 configs out of the scope of iptables to make them independent of it. This patch also adds NETFILTER_XT_NAT which selects the xt_nat combo that provides snat/dnat for iptables. We cannot use NF_NAT anymore since nf_tables can select this. Reported-by: Matteo Croce Signed-off-by: Pablo Neira Ayuso --- net/ipv4/netfilter/Kconfig | 102 +++++++++++++++++++----------------- net/ipv4/netfilter/Makefile | 2 +- net/ipv6/netfilter/Kconfig | 26 ++++++--- net/ipv6/netfilter/Makefile | 2 +- net/netfilter/Makefile | 2 +- 5 files changed, 77 insertions(+), 57 deletions(-) diff --git a/net/ipv4/netfilter/Kconfig b/net/ipv4/netfilter/Kconfig index fb173126f03d..7cbcaf4f0194 100644 --- a/net/ipv4/netfilter/Kconfig +++ b/net/ipv4/netfilter/Kconfig @@ -82,6 +82,52 @@ config NF_TABLES_ARP help This option enables the ARP support for nf_tables. +config NF_NAT_IPV4 + tristate "IPv4 NAT" + depends on NF_CONNTRACK_IPV4 + default m if NETFILTER_ADVANCED=n + select NF_NAT + help + The IPv4 NAT option allows masquerading, port forwarding and other + forms of full Network Address Port Translation. This can be + controlled by iptables or nft. + +if NF_NAT_IPV4 + +config NF_NAT_SNMP_BASIC + tristate "Basic SNMP-ALG support" + depends on NF_CONNTRACK_SNMP + depends on NETFILTER_ADVANCED + default NF_NAT && NF_CONNTRACK_SNMP + ---help--- + + This module implements an Application Layer Gateway (ALG) for + SNMP payloads. In conjunction with NAT, it allows a network + management system to access multiple private networks with + conflicting addresses. It works by modifying IP addresses + inside SNMP payloads to match IP-layer NAT mapping. + + This is the "basic" form of SNMP-ALG, as described in RFC 2962 + + To compile it as a module, choose M here. If unsure, say N. + +config NF_NAT_PROTO_GRE + tristate + depends on NF_CT_PROTO_GRE + +config NF_NAT_PPTP + tristate + depends on NF_CONNTRACK + default NF_CONNTRACK_PPTP + select NF_NAT_PROTO_GRE + +config NF_NAT_H323 + tristate + depends on NF_CONNTRACK + default NF_CONNTRACK_H323 + +endif # NF_NAT_IPV4 + config IP_NF_IPTABLES tristate "IP tables support (required for filtering/masq/NAT)" default m if NETFILTER_ADVANCED=n @@ -170,19 +216,21 @@ config IP_NF_TARGET_SYNPROXY To compile it as a module, choose M here. If unsure, say N. # NAT + specific targets: nf_conntrack -config NF_NAT_IPV4 - tristate "IPv4 NAT" +config IP_NF_NAT + tristate "iptables NAT support" depends on NF_CONNTRACK_IPV4 default m if NETFILTER_ADVANCED=n select NF_NAT + select NF_NAT_IPV4 + select NETFILTER_XT_NAT help - The IPv4 NAT option allows masquerading, port forwarding and other - forms of full Network Address Port Translation. It is controlled by - the `nat' table in iptables: see the man page for iptables(8). + This enables the `nat' table in iptables. This allows masquerading, + port forwarding and other forms of full Network Address Port + Translation. To compile it as a module, choose M here. If unsure, say N. -if NF_NAT_IPV4 +if IP_NF_NAT config IP_NF_TARGET_MASQUERADE tristate "MASQUERADE target support" @@ -214,47 +262,7 @@ config IP_NF_TARGET_REDIRECT (e.g. when running oldconfig). It selects CONFIG_NETFILTER_XT_TARGET_REDIRECT. -endif - -config NF_NAT_SNMP_BASIC - tristate "Basic SNMP-ALG support" - depends on NF_CONNTRACK_SNMP && NF_NAT_IPV4 - depends on NETFILTER_ADVANCED - default NF_NAT && NF_CONNTRACK_SNMP - ---help--- - - This module implements an Application Layer Gateway (ALG) for - SNMP payloads. In conjunction with NAT, it allows a network - management system to access multiple private networks with - conflicting addresses. It works by modifying IP addresses - inside SNMP payloads to match IP-layer NAT mapping. - - This is the "basic" form of SNMP-ALG, as described in RFC 2962 - - To compile it as a module, choose M here. If unsure, say N. - -# If they want FTP, set to $CONFIG_IP_NF_NAT (m or y), -# or $CONFIG_IP_NF_FTP (m or y), whichever is weaker. -# From kconfig-language.txt: -# -# '&&' (6) -# -# (6) Returns the result of min(/expr/, /expr/). - -config NF_NAT_PROTO_GRE - tristate - depends on NF_NAT_IPV4 && NF_CT_PROTO_GRE - -config NF_NAT_PPTP - tristate - depends on NF_CONNTRACK && NF_NAT_IPV4 - default NF_NAT_IPV4 && NF_CONNTRACK_PPTP - select NF_NAT_PROTO_GRE - -config NF_NAT_H323 - tristate - depends on NF_CONNTRACK && NF_NAT_IPV4 - default NF_NAT_IPV4 && NF_CONNTRACK_H323 +endif # IP_NF_NAT # mangle + specific targets config IP_NF_MANGLE diff --git a/net/ipv4/netfilter/Makefile b/net/ipv4/netfilter/Makefile index 33001621465b..edf4af32e9f2 100644 --- a/net/ipv4/netfilter/Makefile +++ b/net/ipv4/netfilter/Makefile @@ -43,7 +43,7 @@ obj-$(CONFIG_IP_NF_IPTABLES) += ip_tables.o # the three instances of ip_tables obj-$(CONFIG_IP_NF_FILTER) += iptable_filter.o obj-$(CONFIG_IP_NF_MANGLE) += iptable_mangle.o -obj-$(CONFIG_NF_NAT_IPV4) += iptable_nat.o +obj-$(CONFIG_IP_NF_NAT) += iptable_nat.o obj-$(CONFIG_IP_NF_RAW) += iptable_raw.o obj-$(CONFIG_IP_NF_SECURITY) += iptable_security.o diff --git a/net/ipv6/netfilter/Kconfig b/net/ipv6/netfilter/Kconfig index ac93df16f5af..cf0b88f30f6f 100644 --- a/net/ipv6/netfilter/Kconfig +++ b/net/ipv6/netfilter/Kconfig @@ -60,6 +60,16 @@ config NF_LOG_IPV6 depends on NETFILTER_ADVANCED select NF_LOG_COMMON +config NF_NAT_IPV6 + tristate "IPv6 NAT" + depends on NF_CONNTRACK_IPV6 + depends on NETFILTER_ADVANCED + select NF_NAT + help + The IPv6 NAT option allows masquerading, port forwarding and other + forms of full Network Address Port Translation. This can be + controlled by iptables or nft. + config IP6_NF_IPTABLES tristate "IP6 tables support (required for filtering)" depends on INET && IPV6 @@ -232,19 +242,21 @@ config IP6_NF_SECURITY If unsure, say N. -config NF_NAT_IPV6 - tristate "IPv6 NAT" +config IP6_NF_NAT + tristate "ip6tables NAT support" depends on NF_CONNTRACK_IPV6 depends on NETFILTER_ADVANCED select NF_NAT + select NF_NAT_IPV6 + select NETFILTER_XT_NAT help - The IPv6 NAT option allows masquerading, port forwarding and other - forms of full Network Address Port Translation. It is controlled by - the `nat' table in ip6tables, see the man page for ip6tables(8). + This enables the `nat' table in ip6tables. This allows masquerading, + port forwarding and other forms of full Network Address Port + Translation. To compile it as a module, choose M here. If unsure, say N. -if NF_NAT_IPV6 +if IP6_NF_NAT config IP6_NF_TARGET_MASQUERADE tristate "MASQUERADE target support" @@ -265,7 +277,7 @@ config IP6_NF_TARGET_NPT To compile it as a module, choose M here. If unsure, say N. -endif # NF_NAT_IPV6 +endif # IP6_NF_NAT endif # IP6_NF_IPTABLES diff --git a/net/ipv6/netfilter/Makefile b/net/ipv6/netfilter/Makefile index c0b263104ed2..c3d3286db4bb 100644 --- a/net/ipv6/netfilter/Makefile +++ b/net/ipv6/netfilter/Makefile @@ -8,7 +8,7 @@ obj-$(CONFIG_IP6_NF_FILTER) += ip6table_filter.o obj-$(CONFIG_IP6_NF_MANGLE) += ip6table_mangle.o obj-$(CONFIG_IP6_NF_RAW) += ip6table_raw.o obj-$(CONFIG_IP6_NF_SECURITY) += ip6table_security.o -obj-$(CONFIG_NF_NAT_IPV6) += ip6table_nat.o +obj-$(CONFIG_IP6_NF_NAT) += ip6table_nat.o # objects for l3 independent conntrack nf_conntrack_ipv6-y := nf_conntrack_l3proto_ipv6.o nf_conntrack_proto_icmpv6.o diff --git a/net/netfilter/Makefile b/net/netfilter/Makefile index 8308624a406a..fad5fdba34e5 100644 --- a/net/netfilter/Makefile +++ b/net/netfilter/Makefile @@ -95,7 +95,7 @@ obj-$(CONFIG_NETFILTER_XTABLES) += x_tables.o xt_tcpudp.o obj-$(CONFIG_NETFILTER_XT_MARK) += xt_mark.o obj-$(CONFIG_NETFILTER_XT_CONNMARK) += xt_connmark.o obj-$(CONFIG_NETFILTER_XT_SET) += xt_set.o -obj-$(CONFIG_NF_NAT) += xt_nat.o +obj-$(CONFIG_NETFILTER_XT_NAT) += xt_nat.o # targets obj-$(CONFIG_NETFILTER_XT_TARGET_AUDIT) += xt_AUDIT.o From 7629d1eaf33672c9d35ba1e2ad12b459d56ca3b1 Mon Sep 17 00:00:00 2001 From: Martin Townsend Date: Tue, 19 Aug 2014 19:03:28 +0200 Subject: [PATCH 003/101] mac802154: fixed potential skb leak with mac802154_parse_frame_start This patch fix a memory leak if received frame was not able to parse. Signed-off-by: Martin Townsend Signed-off-by: Alexander Aring Signed-off-by: Marcel Holtmann --- net/mac802154/wpan.c | 1 + 1 file changed, 1 insertion(+) diff --git a/net/mac802154/wpan.c b/net/mac802154/wpan.c index 3c3069fd6971..4c133239ad39 100644 --- a/net/mac802154/wpan.c +++ b/net/mac802154/wpan.c @@ -573,6 +573,7 @@ void mac802154_wpans_rx(struct mac802154_priv *priv, struct sk_buff *skb) ret = mac802154_parse_frame_start(skb, &hdr); if (ret) { pr_debug("got invalid frame\n"); + kfree_skb(skb); return; } From c4cb901ac667f81786b402ca7d69a9063e770b3a Mon Sep 17 00:00:00 2001 From: Alexander Aring Date: Tue, 19 Aug 2014 19:03:29 +0200 Subject: [PATCH 004/101] ieee802154: 6lowpan_rtnl: fix correct errno value This patch correct the return value of lowpan_alloc_frag if an error occur. Errno numbers should always be negative. Signed-off-by: Alexander Aring Signed-off-by: Marcel Holtmann --- net/ieee802154/6lowpan_rtnl.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/net/ieee802154/6lowpan_rtnl.c b/net/ieee802154/6lowpan_rtnl.c index 016b77ee88f0..71fa7d42966c 100644 --- a/net/ieee802154/6lowpan_rtnl.c +++ b/net/ieee802154/6lowpan_rtnl.c @@ -246,7 +246,7 @@ lowpan_alloc_frag(struct sk_buff *skb, int size, return ERR_PTR(-rc); } } else { - frag = ERR_PTR(ENOMEM); + frag = ERR_PTR(-ENOMEM); } return frag; From 6e361d6ffee322fcd092d97720e05032ffb98ae6 Mon Sep 17 00:00:00 2001 From: Martin Townsend Date: Tue, 19 Aug 2014 19:03:30 +0200 Subject: [PATCH 005/101] ieee802154: mac802154: handle the reserved dest mode by dropping the packet If received frame contains the reserved destination address mode. The frame should be dropped and free the skb. Signed-off-by: Martin Townsend Signed-off-by: Alexander Aring Signed-off-by: Marcel Holtmann --- net/mac802154/wpan.c | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) diff --git a/net/mac802154/wpan.c b/net/mac802154/wpan.c index 4c133239ad39..547838822d5e 100644 --- a/net/mac802154/wpan.c +++ b/net/mac802154/wpan.c @@ -462,7 +462,10 @@ mac802154_subif_frame(struct mac802154_sub_if_data *sdata, struct sk_buff *skb, skb->pkt_type = PACKET_OTHERHOST; break; default: - break; + spin_unlock_bh(&sdata->mib_lock); + pr_debug("invalid dest mode\n"); + kfree_skb(skb); + return NET_RX_DROP; } spin_unlock_bh(&sdata->mib_lock); From 685d632804b89ea25d3339afad162c48646ada5c Mon Sep 17 00:00:00 2001 From: Alexander Aring Date: Tue, 19 Aug 2014 19:03:31 +0200 Subject: [PATCH 006/101] ieee802154: 6lowpan: ensure of sending 1280 packets This patch changes the 1281 MTU to 1280. Others stack have only a 1280 byte array for uncompressed 6LoWPAN packets, this avoid that these stacks have an overflow. Sending 1281 uncompressed 6LoWPAN packets isn't also rfc complaint. Signed-off-by: Alexander Aring Signed-off-by: Marcel Holtmann --- net/ieee802154/6lowpan_rtnl.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/net/ieee802154/6lowpan_rtnl.c b/net/ieee802154/6lowpan_rtnl.c index 71fa7d42966c..6591d27e53a4 100644 --- a/net/ieee802154/6lowpan_rtnl.c +++ b/net/ieee802154/6lowpan_rtnl.c @@ -437,7 +437,7 @@ static void lowpan_setup(struct net_device *dev) /* Frame Control + Sequence Number + Address fields + Security Header */ dev->hard_header_len = 2 + 1 + 20 + 14; dev->needed_tailroom = 2; /* FCS */ - dev->mtu = 1281; + dev->mtu = IPV6_MIN_MTU; dev->tx_queue_len = 0; dev->flags = IFF_BROADCAST | IFF_MULTICAST; dev->watchdog_timeo = 0; From 6697dabe27e03302ddfddc975275e6401defe2dd Mon Sep 17 00:00:00 2001 From: Martin Townsend Date: Tue, 19 Aug 2014 19:03:32 +0200 Subject: [PATCH 007/101] ieee802154: 6lowpan: ensure MTU of 1280 for 6lowpan This patch drops the userspace accessable sysfs entry for the maximum datagram size of a 6LoWPAN fragment packet. A fragment should not have a datagram size value greater than 1280 byte. Instead of make this value configurable, we accept 1280 datagram size fragment packets only. Signed-off-by: Martin Townsend Signed-off-by: Alexander Aring Signed-off-by: Marcel Holtmann --- include/net/netns/ieee802154_6lowpan.h | 1 - net/ieee802154/reassembly.c | 15 +++------------ 2 files changed, 3 insertions(+), 13 deletions(-) diff --git a/include/net/netns/ieee802154_6lowpan.h b/include/net/netns/ieee802154_6lowpan.h index e2070960bac0..8170f8d7052b 100644 --- a/include/net/netns/ieee802154_6lowpan.h +++ b/include/net/netns/ieee802154_6lowpan.h @@ -16,7 +16,6 @@ struct netns_sysctl_lowpan { struct netns_ieee802154_lowpan { struct netns_sysctl_lowpan sysctl; struct netns_frags frags; - int max_dsize; }; #endif diff --git a/net/ieee802154/reassembly.c b/net/ieee802154/reassembly.c index ffec6ce51005..32755cb7e64e 100644 --- a/net/ieee802154/reassembly.c +++ b/net/ieee802154/reassembly.c @@ -355,8 +355,6 @@ int lowpan_frag_rcv(struct sk_buff *skb, const u8 frag_type) struct net *net = dev_net(skb->dev); struct lowpan_frag_info *frag_info = lowpan_cb(skb); struct ieee802154_addr source, dest; - struct netns_ieee802154_lowpan *ieee802154_lowpan = - net_ieee802154_lowpan(net); int err; source = mac_cb(skb)->source; @@ -366,8 +364,10 @@ int lowpan_frag_rcv(struct sk_buff *skb, const u8 frag_type) if (err < 0) goto err; - if (frag_info->d_size > ieee802154_lowpan->max_dsize) + if (frag_info->d_size > IPV6_MIN_MTU) { + net_warn_ratelimited("lowpan_frag_rcv: datagram size exceeds MTU\n"); goto err; + } fq = fq_find(net, frag_info, &source, &dest); if (fq != NULL) { @@ -415,13 +415,6 @@ static struct ctl_table lowpan_frags_ns_ctl_table[] = { .mode = 0644, .proc_handler = proc_dointvec_jiffies, }, - { - .procname = "6lowpanfrag_max_datagram_size", - .data = &init_net.ieee802154_lowpan.max_dsize, - .maxlen = sizeof(int), - .mode = 0644, - .proc_handler = proc_dointvec - }, { } }; @@ -458,7 +451,6 @@ static int __net_init lowpan_frags_ns_sysctl_register(struct net *net) table[1].data = &ieee802154_lowpan->frags.low_thresh; table[1].extra2 = &ieee802154_lowpan->frags.high_thresh; table[2].data = &ieee802154_lowpan->frags.timeout; - table[3].data = &ieee802154_lowpan->max_dsize; /* Don't export sysctls to unprivileged users */ if (net->user_ns != &init_user_ns) @@ -533,7 +525,6 @@ static int __net_init lowpan_frags_init_net(struct net *net) ieee802154_lowpan->frags.high_thresh = IPV6_FRAG_HIGH_THRESH; ieee802154_lowpan->frags.low_thresh = IPV6_FRAG_LOW_THRESH; ieee802154_lowpan->frags.timeout = IPV6_FRAG_TIMEOUT; - ieee802154_lowpan->max_dsize = 0xFFFF; inet_frags_init_net(&ieee802154_lowpan->frags); From caa8ad94edf686d02b555c65a6162c0d1b434958 Mon Sep 17 00:00:00 2001 From: Daniel Borkmann Date: Mon, 18 Aug 2014 15:46:28 +0200 Subject: [PATCH 008/101] netfilter: x_tables: allow to use default cgroup match There's actually no good reason why we cannot use cgroup id 0, so lets just remove this artificial barrier. Reported-by: Alexey Perevalov Signed-off-by: Daniel Borkmann Tested-by: Alexey Perevalov Signed-off-by: Pablo Neira Ayuso --- net/netfilter/xt_cgroup.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/net/netfilter/xt_cgroup.c b/net/netfilter/xt_cgroup.c index f4e833005320..7198d660b4de 100644 --- a/net/netfilter/xt_cgroup.c +++ b/net/netfilter/xt_cgroup.c @@ -31,7 +31,7 @@ static int cgroup_mt_check(const struct xt_mtchk_param *par) if (info->invert & ~1) return -EINVAL; - return info->id ? 0 : -EINVAL; + return 0; } static bool From 1e8430f30b55a1f3f6925c9f37f8cc9afd141d2e Mon Sep 17 00:00:00 2001 From: Pablo Neira Ayuso Date: Mon, 11 Aug 2014 18:21:50 +0200 Subject: [PATCH 009/101] netfilter: nf_tables: nat expression must select CONFIG_NF_NAT This enables the netfilter NAT engine in first place, otherwise you cannot ever select the nf_tables nat expression if iptables is not selected. Reported-by: Matteo Croce Signed-off-by: Pablo Neira Ayuso --- net/netfilter/Kconfig | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/net/netfilter/Kconfig b/net/netfilter/Kconfig index ad751fe2e82b..05eb177ea852 100644 --- a/net/netfilter/Kconfig +++ b/net/netfilter/Kconfig @@ -499,7 +499,7 @@ config NFT_LIMIT config NFT_NAT depends on NF_TABLES depends on NF_CONNTRACK - depends on NF_NAT + select NF_NAT tristate "Netfilter nf_tables nat module" help This option adds the "nat" expression that you can use to perform From f161dd4122ffa73e4e12000309dca65bec80d416 Mon Sep 17 00:00:00 2001 From: Johan Hedberg Date: Fri, 15 Aug 2014 21:06:54 +0300 Subject: [PATCH 010/101] Bluetooth: Fix hci_conn reference counting for auto-connections Recently the LE passive scanning and auto-connections feature was introduced. It uses the hci_connect_le() API which returns a hci_conn along with a reference count to that object. All previous users would tie this returned reference to some existing object, such as an L2CAP channel, and there'd be no leaked references this way. For auto-connections however the reference was returned but not stored anywhere, leaving established connections with one higher reference count than they should have. Instead of playing special tricks with hci_conn_hold/drop this patch associates the returned reference from hci_connect_le() with the object that in practice does own this reference, i.e. the hci_conn_params struct that caused us to initiate a connection in the first place. Once the connection is established or fails to establish this reference is removed appropriately. One extra thing needed is to call hci_pend_le_actions_clear() before calling hci_conn_hash_flush() so that the reference is cleared before the hci_conn objects are fully removed. Signed-off-by: Johan Hedberg Signed-off-by: Marcel Holtmann --- include/net/bluetooth/hci_core.h | 2 ++ net/bluetooth/hci_conn.c | 8 ++++++++ net/bluetooth/hci_core.c | 14 ++++++++++++-- net/bluetooth/hci_event.c | 17 +++++++++++++++-- 4 files changed, 37 insertions(+), 4 deletions(-) diff --git a/include/net/bluetooth/hci_core.h b/include/net/bluetooth/hci_core.h index b5d5af3aa469..6f884e6c731e 100644 --- a/include/net/bluetooth/hci_core.h +++ b/include/net/bluetooth/hci_core.h @@ -464,6 +464,8 @@ struct hci_conn_params { HCI_AUTO_CONN_ALWAYS, HCI_AUTO_CONN_LINK_LOSS, } auto_connect; + + struct hci_conn *conn; }; extern struct list_head hci_dev_list; diff --git a/net/bluetooth/hci_conn.c b/net/bluetooth/hci_conn.c index b50dabb3f86a..faff6247ac8f 100644 --- a/net/bluetooth/hci_conn.c +++ b/net/bluetooth/hci_conn.c @@ -589,6 +589,14 @@ EXPORT_SYMBOL(hci_get_route); void hci_le_conn_failed(struct hci_conn *conn, u8 status) { struct hci_dev *hdev = conn->hdev; + struct hci_conn_params *params; + + params = hci_pend_le_action_lookup(&hdev->pend_le_conns, &conn->dst, + conn->dst_type); + if (params && params->conn) { + hci_conn_drop(params->conn); + params->conn = NULL; + } conn->state = BT_CLOSED; diff --git a/net/bluetooth/hci_core.c b/net/bluetooth/hci_core.c index c32d361c0cf7..1d9c29a00568 100644 --- a/net/bluetooth/hci_core.c +++ b/net/bluetooth/hci_core.c @@ -2536,8 +2536,13 @@ static void hci_pend_le_actions_clear(struct hci_dev *hdev) { struct hci_conn_params *p; - list_for_each_entry(p, &hdev->le_conn_params, list) + list_for_each_entry(p, &hdev->le_conn_params, list) { + if (p->conn) { + hci_conn_drop(p->conn); + p->conn = NULL; + } list_del_init(&p->action); + } BT_DBG("All LE pending actions cleared"); } @@ -2578,8 +2583,8 @@ static int hci_dev_do_close(struct hci_dev *hdev) hci_dev_lock(hdev); hci_inquiry_cache_flush(hdev); - hci_conn_hash_flush(hdev); hci_pend_le_actions_clear(hdev); + hci_conn_hash_flush(hdev); hci_dev_unlock(hdev); hci_notify(hdev, HCI_DEV_DOWN); @@ -3727,6 +3732,9 @@ void hci_conn_params_del(struct hci_dev *hdev, bdaddr_t *addr, u8 addr_type) if (!params) return; + if (params->conn) + hci_conn_drop(params->conn); + list_del(¶ms->action); list_del(¶ms->list); kfree(params); @@ -3757,6 +3765,8 @@ void hci_conn_params_clear_all(struct hci_dev *hdev) struct hci_conn_params *params, *tmp; list_for_each_entry_safe(params, tmp, &hdev->le_conn_params, list) { + if (params->conn) + hci_conn_drop(params->conn); list_del(¶ms->action); list_del(¶ms->list); kfree(params); diff --git a/net/bluetooth/hci_event.c b/net/bluetooth/hci_event.c index be35598984d9..a6000823f0ff 100644 --- a/net/bluetooth/hci_event.c +++ b/net/bluetooth/hci_event.c @@ -4221,8 +4221,13 @@ static void hci_le_conn_complete_evt(struct hci_dev *hdev, struct sk_buff *skb) hci_proto_connect_cfm(conn, ev->status); params = hci_conn_params_lookup(hdev, &conn->dst, conn->dst_type); - if (params) + if (params) { list_del_init(¶ms->action); + if (params->conn) { + hci_conn_drop(params->conn); + params->conn = NULL; + } + } unlock: hci_update_background_scan(hdev); @@ -4304,8 +4309,16 @@ static void check_pending_le_conn(struct hci_dev *hdev, bdaddr_t *addr, conn = hci_connect_le(hdev, addr, addr_type, BT_SECURITY_LOW, HCI_LE_AUTOCONN_TIMEOUT, HCI_ROLE_MASTER); - if (!IS_ERR(conn)) + if (!IS_ERR(conn)) { + /* Store the pointer since we don't really have any + * other owner of the object besides the params that + * triggered it. This way we can abort the connection if + * the parameters get removed and keep the reference + * count consistent once the connection is established. + */ + params->conn = conn; return; + } switch (PTR_ERR(conn)) { case -EBUSY: From a45e92a599e77ee6a850eabdd0141633fde03915 Mon Sep 17 00:00:00 2001 From: Gerhard Stenzel Date: Fri, 22 Aug 2014 21:34:16 +0200 Subject: [PATCH 011/101] vxlan: fix incorrect initializer in union vxlan_addr The first initializer in the following union vxlan_addr ipa = { .sin.sin_addr.s_addr = tip, .sa.sa_family = AF_INET, }; is optimised away by the compiler, due to the second initializer, therefore initialising .sin.sin_addr.s_addr always to 0. This results in netlink messages indicating a L3 miss never contain the missed IP address. This was observed with GCC 4.8 and 4.9. I do not know about previous versions. The problem affects user space programs relying on an IP address being sent as part of a netlink message indicating a L3 miss. Changing .sa.sa_family = AF_INET, to .sin.sin_family = AF_INET, fixes the problem. Signed-off-by: Gerhard Stenzel Signed-off-by: David S. Miller --- drivers/net/vxlan.c | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/drivers/net/vxlan.c b/drivers/net/vxlan.c index 1fb7b37d1402..beb377b2d4b7 100644 --- a/drivers/net/vxlan.c +++ b/drivers/net/vxlan.c @@ -1327,7 +1327,7 @@ static int arp_reduce(struct net_device *dev, struct sk_buff *skb) } else if (vxlan->flags & VXLAN_F_L3MISS) { union vxlan_addr ipa = { .sin.sin_addr.s_addr = tip, - .sa.sa_family = AF_INET, + .sin.sin_family = AF_INET, }; vxlan_ip_miss(dev, &ipa); @@ -1488,7 +1488,7 @@ static int neigh_reduce(struct net_device *dev, struct sk_buff *skb) } else if (vxlan->flags & VXLAN_F_L3MISS) { union vxlan_addr ipa = { .sin6.sin6_addr = msg->target, - .sa.sa_family = AF_INET6, + .sin6.sin6_family = AF_INET6, }; vxlan_ip_miss(dev, &ipa); @@ -1521,7 +1521,7 @@ static bool route_shortcircuit(struct net_device *dev, struct sk_buff *skb) if (!n && (vxlan->flags & VXLAN_F_L3MISS)) { union vxlan_addr ipa = { .sin.sin_addr.s_addr = pip->daddr, - .sa.sa_family = AF_INET, + .sin.sin_family = AF_INET, }; vxlan_ip_miss(dev, &ipa); @@ -1542,7 +1542,7 @@ static bool route_shortcircuit(struct net_device *dev, struct sk_buff *skb) if (!n && (vxlan->flags & VXLAN_F_L3MISS)) { union vxlan_addr ipa = { .sin6.sin6_addr = pip6->daddr, - .sa.sa_family = AF_INET6, + .sin6.sin6_family = AF_INET6, }; vxlan_ip_miss(dev, &ipa); From d1c85c2ebe7ffe1f1b27846bd1ba0944c513d822 Mon Sep 17 00:00:00 2001 From: Zhouyi Zhou Date: Fri, 22 Aug 2014 10:40:15 +0800 Subject: [PATCH 012/101] netfilter: HAVE_JUMP_LABEL instead of CONFIG_JUMP_LABEL Use HAVE_JUMP_LABEL as elsewhere in the kernel to ensure that the toolchain has the required support in addition to CONFIG_JUMP_LABEL being set. Signed-off-by: Zhouyi Zhou Reviewed-by: Florian Westphal Signed-off-by: Pablo Neira Ayuso --- include/linux/netfilter.h | 5 +++-- net/netfilter/core.c | 6 +++--- 2 files changed, 6 insertions(+), 5 deletions(-) diff --git a/include/linux/netfilter.h b/include/linux/netfilter.h index 2077489f9887..2517ece98820 100644 --- a/include/linux/netfilter.h +++ b/include/linux/netfilter.h @@ -9,6 +9,7 @@ #include #include #include +#include #include #ifdef CONFIG_NETFILTER static inline int NF_DROP_GETERR(int verdict) @@ -99,9 +100,9 @@ void nf_unregister_sockopt(struct nf_sockopt_ops *reg); extern struct list_head nf_hooks[NFPROTO_NUMPROTO][NF_MAX_HOOKS]; -#if defined(CONFIG_JUMP_LABEL) -#include +#ifdef HAVE_JUMP_LABEL extern struct static_key nf_hooks_needed[NFPROTO_NUMPROTO][NF_MAX_HOOKS]; + static inline bool nf_hooks_active(u_int8_t pf, unsigned int hook) { if (__builtin_constant_p(pf) && diff --git a/net/netfilter/core.c b/net/netfilter/core.c index a93c97f106d4..024a2e25c8a4 100644 --- a/net/netfilter/core.c +++ b/net/netfilter/core.c @@ -54,7 +54,7 @@ EXPORT_SYMBOL_GPL(nf_unregister_afinfo); struct list_head nf_hooks[NFPROTO_NUMPROTO][NF_MAX_HOOKS] __read_mostly; EXPORT_SYMBOL(nf_hooks); -#if defined(CONFIG_JUMP_LABEL) +#ifdef HAVE_JUMP_LABEL struct static_key nf_hooks_needed[NFPROTO_NUMPROTO][NF_MAX_HOOKS]; EXPORT_SYMBOL(nf_hooks_needed); #endif @@ -72,7 +72,7 @@ int nf_register_hook(struct nf_hook_ops *reg) } list_add_rcu(®->list, elem->list.prev); mutex_unlock(&nf_hook_mutex); -#if defined(CONFIG_JUMP_LABEL) +#ifdef HAVE_JUMP_LABEL static_key_slow_inc(&nf_hooks_needed[reg->pf][reg->hooknum]); #endif return 0; @@ -84,7 +84,7 @@ void nf_unregister_hook(struct nf_hook_ops *reg) mutex_lock(&nf_hook_mutex); list_del_rcu(®->list); mutex_unlock(&nf_hook_mutex); -#if defined(CONFIG_JUMP_LABEL) +#ifdef HAVE_JUMP_LABEL static_key_slow_dec(&nf_hooks_needed[reg->pf][reg->hooknum]); #endif synchronize_net(); From 9837baa99717c7526e4bae9c68e8728dea4af183 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?=C3=81lvaro=20Fern=C3=A1ndez=20Rojas?= Date: Mon, 28 Jul 2014 21:01:06 +0200 Subject: [PATCH 013/101] ssb: add PCI ID 0x4351 MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit 14e4:4351 is found on a Broadcom BCM43222. Signed-off-by: Álvaro Fernández Rojas Signed-off-by: John W. Linville --- drivers/ssb/b43_pci_bridge.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/ssb/b43_pci_bridge.c b/drivers/ssb/b43_pci_bridge.c index 19396dc4ee47..bed2fedeb057 100644 --- a/drivers/ssb/b43_pci_bridge.c +++ b/drivers/ssb/b43_pci_bridge.c @@ -38,6 +38,7 @@ static const struct pci_device_id b43_pci_bridge_tbl[] = { { PCI_DEVICE(PCI_VENDOR_ID_BROADCOM, 0x432b) }, { PCI_DEVICE(PCI_VENDOR_ID_BROADCOM, 0x432c) }, { PCI_DEVICE(PCI_VENDOR_ID_BROADCOM, 0x4350) }, + { PCI_DEVICE(PCI_VENDOR_ID_BROADCOM, 0x4351) }, { 0, }, }; MODULE_DEVICE_TABLE(pci, b43_pci_bridge_tbl); From e5cd6cee46764467e6cb14841ff59cd2e2573502 Mon Sep 17 00:00:00 2001 From: Himangi Saraogi Date: Wed, 13 Aug 2014 01:09:29 +0530 Subject: [PATCH 014/101] rtlwifi: btcoexist: adjust double test Rewrite a duplicated test to test the correct value The Coccinelle semantic patch that finds this problem is: // @@ expression E; @@ ( * E || ... || E | * E && ... && E ) // Signed-off-by: Himangi Saraogi Acked-by: Larry.Finger Signed-off-by: John W. Linville --- drivers/net/wireless/rtlwifi/btcoexist/halbtcoutsrc.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/net/wireless/rtlwifi/btcoexist/halbtcoutsrc.c b/drivers/net/wireless/rtlwifi/btcoexist/halbtcoutsrc.c index 33da3dfcfa4f..d4bd550f505c 100644 --- a/drivers/net/wireless/rtlwifi/btcoexist/halbtcoutsrc.c +++ b/drivers/net/wireless/rtlwifi/btcoexist/halbtcoutsrc.c @@ -101,7 +101,7 @@ static bool halbtc_legacy(struct rtl_priv *adapter) bool is_legacy = false; - if ((mac->mode == WIRELESS_MODE_B) || (mac->mode == WIRELESS_MODE_B)) + if ((mac->mode == WIRELESS_MODE_B) || (mac->mode == WIRELESS_MODE_G)) is_legacy = true; return is_legacy; From 29e20aa6c6aff35c81d4da2e2cd516dadb569061 Mon Sep 17 00:00:00 2001 From: Alexey Khoroshilov Date: Fri, 15 Aug 2014 03:00:06 +0400 Subject: [PATCH 015/101] at76c50x-usb: fix use after free on failure path in at76_probe() After commit 174beab7d445 ("at76c50x-usb: Don't perform DMA from stack memory") at76_delete_device() and usb_put_dev() are called both if at76_init_new_device() fails in at76_probe(). But at76_delete_device() does usb_put_dev(priv->dev) itself that means double usb_put_dev(). The patch avoids the problem by moving usb_put_dev() from at76_delete_device() to at76_disconnect(). Found by Linux Driver Verification project (linuxtesting.org). Signed-off-by: Alexey Khoroshilov Signed-off-by: John W. Linville --- drivers/net/wireless/at76c50x-usb.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) diff --git a/drivers/net/wireless/at76c50x-usb.c b/drivers/net/wireless/at76c50x-usb.c index 334c2ece855a..da92bfa76b7c 100644 --- a/drivers/net/wireless/at76c50x-usb.c +++ b/drivers/net/wireless/at76c50x-usb.c @@ -2423,8 +2423,6 @@ static void at76_delete_device(struct at76_priv *priv) kfree_skb(priv->rx_skb); - usb_put_dev(priv->udev); - at76_dbg(DBG_PROC_ENTRY, "%s: before freeing priv/ieee80211_hw", __func__); ieee80211_free_hw(priv->hw); @@ -2558,6 +2556,7 @@ static void at76_disconnect(struct usb_interface *interface) wiphy_info(priv->hw->wiphy, "disconnecting\n"); at76_delete_device(priv); + usb_put_dev(priv->udev); dev_info(&interface->dev, "disconnected\n"); } From ded3fb4cba11a678dbc44b2d70ebd95ba9684427 Mon Sep 17 00:00:00 2001 From: Maks Naumov Date: Sat, 16 Aug 2014 00:41:07 -0700 Subject: [PATCH 016/101] ath9k: fix wrong string size for strncmp in write_file_spec_scan_ctl() Signed-off-by: Maks Naumov Signed-off-by: John W. Linville --- drivers/net/wireless/ath/ath9k/spectral.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/net/wireless/ath/ath9k/spectral.c b/drivers/net/wireless/ath/ath9k/spectral.c index 5fe29b9f8fa2..8f68426ca653 100644 --- a/drivers/net/wireless/ath/ath9k/spectral.c +++ b/drivers/net/wireless/ath/ath9k/spectral.c @@ -253,7 +253,7 @@ static ssize_t write_file_spec_scan_ctl(struct file *file, if (strncmp("trigger", buf, 7) == 0) { ath9k_spectral_scan_trigger(sc->hw); - } else if (strncmp("background", buf, 9) == 0) { + } else if (strncmp("background", buf, 10) == 0) { ath9k_spectral_scan_config(sc->hw, SPECTRAL_BACKGROUND); ath_dbg(common, CONFIG, "spectral scan: background mode enabled\n"); } else if (strncmp("chanscan", buf, 8) == 0) { From fb70118c0e8b436eb0d957ef506a1d94028ae10c Mon Sep 17 00:00:00 2001 From: Mika Westerberg Date: Tue, 19 Aug 2014 15:41:32 +0300 Subject: [PATCH 017/101] net: rfkill: gpio: Add more Broadcom bluetooth ACPI IDs This adds one more ACPI ID of a Broadcom bluetooth chip. Signed-off-by: Mika Westerberg Signed-off-by: John W. Linville --- net/rfkill/rfkill-gpio.c | 1 + 1 file changed, 1 insertion(+) diff --git a/net/rfkill/rfkill-gpio.c b/net/rfkill/rfkill-gpio.c index 14c98e48f261..02a86a27fd84 100644 --- a/net/rfkill/rfkill-gpio.c +++ b/net/rfkill/rfkill-gpio.c @@ -158,6 +158,7 @@ static const struct acpi_device_id rfkill_acpi_match[] = { { "BCM2E1A", RFKILL_TYPE_BLUETOOTH }, { "BCM2E39", RFKILL_TYPE_BLUETOOTH }, { "BCM2E3D", RFKILL_TYPE_BLUETOOTH }, + { "BCM2E64", RFKILL_TYPE_BLUETOOTH }, { "BCM4752", RFKILL_TYPE_GPS }, { "LNV4752", RFKILL_TYPE_GPS }, { }, From ed96c03ec01340281d97a0e6e3db4670258592a1 Mon Sep 17 00:00:00 2001 From: Hauke Mehrtens Date: Sat, 23 Aug 2014 17:58:11 +0200 Subject: [PATCH 018/101] bcma: add PCI ID for spromless BCM43217 This adds the PCI ID a BCM43217 without a sprom. This devices was found on a Netgear R6250 attached to a BCM4708 ARM SoC. bcma: bus1: Found chip with id 0xA8D1, rev 0x00 and package 0x08 bcma: bus1: Core 0 found: ChipCommon (manuf 0x4BF, id 0x800, rev 0x27, class 0x0) bcma: bus1: Core 1 found: IEEE 802.11 (manuf 0x4BF, id 0x812, rev 0x1E, class 0x0) bcma: bus1: Core 2 found: PCIe (manuf 0x4BF, id 0x820, rev 0x14, class 0x0) b43-phy0: Broadcom 43217 WLAN found (core revision 30) b43-phy0: Found PHY: Analog 9, Type 4 (N), Revision 17 b43-phy0: Found Radio: Manuf 0x17F, ID 0x2057, Revision 14, Version 1 Signed-off-by: Hauke Mehrtens Signed-off-by: John W. Linville --- drivers/bcma/host_pci.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/bcma/host_pci.c b/drivers/bcma/host_pci.c index 294a7dd25190..f032ed6dd459 100644 --- a/drivers/bcma/host_pci.c +++ b/drivers/bcma/host_pci.c @@ -282,6 +282,7 @@ static const struct pci_device_id bcma_pci_bridge_tbl[] = { { PCI_DEVICE(PCI_VENDOR_ID_BROADCOM, 0x43a9) }, { PCI_DEVICE(PCI_VENDOR_ID_BROADCOM, 0x43aa) }, { PCI_DEVICE(PCI_VENDOR_ID_BROADCOM, 0x4727) }, + { PCI_DEVICE(PCI_VENDOR_ID_BROADCOM, 43227) }, /* 0xA8DB */ { 0, }, }; MODULE_DEVICE_TABLE(pci, bcma_pci_bridge_tbl); From c66517165610b911e4c6d268f28d8c640832dbd1 Mon Sep 17 00:00:00 2001 From: Larry Finger Date: Sun, 24 Aug 2014 17:49:43 -0500 Subject: [PATCH 019/101] rtlwifi: rtl8192cu: Add new ID The Sitecom WLA-2102 adapter uses this driver. Reported-by: Nico Baggus Signed-off-by: Larry Finger Cc: Nico Baggus Cc: Stable Signed-off-by: John W. Linville --- drivers/net/wireless/rtlwifi/rtl8192cu/sw.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/net/wireless/rtlwifi/rtl8192cu/sw.c b/drivers/net/wireless/rtlwifi/rtl8192cu/sw.c index 361435f8608a..1ac6383e7947 100644 --- a/drivers/net/wireless/rtlwifi/rtl8192cu/sw.c +++ b/drivers/net/wireless/rtlwifi/rtl8192cu/sw.c @@ -317,6 +317,7 @@ static struct usb_device_id rtl8192c_usb_ids[] = { {RTL_USB_DEVICE(0x0bda, 0x5088, rtl92cu_hal_cfg)}, /*Thinkware-CC&C*/ {RTL_USB_DEVICE(0x0df6, 0x0052, rtl92cu_hal_cfg)}, /*Sitecom - Edimax*/ {RTL_USB_DEVICE(0x0df6, 0x005c, rtl92cu_hal_cfg)}, /*Sitecom - Edimax*/ + {RTL_USB_DEVICE(0x0df6, 0x0070, rtl92cu_hal_cfg)}, /*Sitecom - 150N */ {RTL_USB_DEVICE(0x0df6, 0x0077, rtl92cu_hal_cfg)}, /*Sitecom-WLA2100V2*/ {RTL_USB_DEVICE(0x0eb0, 0x9071, rtl92cu_hal_cfg)}, /*NO Brand - Etop*/ {RTL_USB_DEVICE(0x4856, 0x0091, rtl92cu_hal_cfg)}, /*NetweeN - Feixun*/ From 4c75431ac3520631f1d9e74aa88407e6374dbbc4 Mon Sep 17 00:00:00 2001 From: "Alexander Y. Fomichev" Date: Mon, 25 Aug 2014 16:26:45 +0400 Subject: [PATCH 020/101] net: prevent of emerging cross-namespace symlinks Code manipulating sysfs symlinks on adjacent net_devices(s) currently doesn't take into account that devices potentially belong to different namespaces. This patch trying to fix an issue as follows: - check for net_ns before creating / deleting symlink. for now only netdev_adjacent_rename_links and __netdev_adjacent_dev_remove are affected, afaics __netdev_adjacent_dev_insert implies both net_devs belong to the same namespace. - Drop all existing symlinks to / from all adj_devs before switching namespace and recreate them just after. Signed-off-by: Alexander Y. Fomichev Signed-off-by: David S. Miller --- net/core/dev.c | 61 +++++++++++++++++++++++++++++++++++++++++++++++++- 1 file changed, 60 insertions(+), 1 deletion(-) diff --git a/net/core/dev.c b/net/core/dev.c index b65a5051361f..66738e9d66e4 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -4889,7 +4889,8 @@ static void __netdev_adjacent_dev_remove(struct net_device *dev, if (adj->master) sysfs_remove_link(&(dev->dev.kobj), "master"); - if (netdev_adjacent_is_neigh_list(dev, dev_list)) + if (netdev_adjacent_is_neigh_list(dev, dev_list) && + net_eq(dev_net(dev),dev_net(adj_dev))) netdev_adjacent_sysfs_del(dev, adj_dev->name, dev_list); list_del_rcu(&adj->list); @@ -5159,11 +5160,65 @@ void netdev_upper_dev_unlink(struct net_device *dev, } EXPORT_SYMBOL(netdev_upper_dev_unlink); +void netdev_adjacent_add_links(struct net_device *dev) +{ + struct netdev_adjacent *iter; + + struct net *net = dev_net(dev); + + list_for_each_entry(iter, &dev->adj_list.upper, list) { + if (!net_eq(net,dev_net(iter->dev))) + continue; + netdev_adjacent_sysfs_add(iter->dev, dev, + &iter->dev->adj_list.lower); + netdev_adjacent_sysfs_add(dev, iter->dev, + &dev->adj_list.upper); + } + + list_for_each_entry(iter, &dev->adj_list.lower, list) { + if (!net_eq(net,dev_net(iter->dev))) + continue; + netdev_adjacent_sysfs_add(iter->dev, dev, + &iter->dev->adj_list.upper); + netdev_adjacent_sysfs_add(dev, iter->dev, + &dev->adj_list.lower); + } +} + +void netdev_adjacent_del_links(struct net_device *dev) +{ + struct netdev_adjacent *iter; + + struct net *net = dev_net(dev); + + list_for_each_entry(iter, &dev->adj_list.upper, list) { + if (!net_eq(net,dev_net(iter->dev))) + continue; + netdev_adjacent_sysfs_del(iter->dev, dev->name, + &iter->dev->adj_list.lower); + netdev_adjacent_sysfs_del(dev, iter->dev->name, + &dev->adj_list.upper); + } + + list_for_each_entry(iter, &dev->adj_list.lower, list) { + if (!net_eq(net,dev_net(iter->dev))) + continue; + netdev_adjacent_sysfs_del(iter->dev, dev->name, + &iter->dev->adj_list.upper); + netdev_adjacent_sysfs_del(dev, iter->dev->name, + &dev->adj_list.lower); + } +} + void netdev_adjacent_rename_links(struct net_device *dev, char *oldname) { struct netdev_adjacent *iter; + struct net *net = dev_net(dev); + list_for_each_entry(iter, &dev->adj_list.upper, list) { + if (!net_eq(net,dev_net(iter->dev))) + continue; netdev_adjacent_sysfs_del(iter->dev, oldname, &iter->dev->adj_list.lower); netdev_adjacent_sysfs_add(iter->dev, dev, @@ -5171,6 +5226,8 @@ void netdev_adjacent_rename_links(struct net_device *dev, char *oldname) } list_for_each_entry(iter, &dev->adj_list.lower, list) { + if (!net_eq(net,dev_net(iter->dev))) + continue; netdev_adjacent_sysfs_del(iter->dev, oldname, &iter->dev->adj_list.upper); netdev_adjacent_sysfs_add(iter->dev, dev, @@ -6773,6 +6830,7 @@ int dev_change_net_namespace(struct net_device *dev, struct net *net, const char /* Send a netdev-removed uevent to the old namespace */ kobject_uevent(&dev->dev.kobj, KOBJ_REMOVE); + netdev_adjacent_del_links(dev); /* Actually switch the network namespace */ dev_net_set(dev, net); @@ -6787,6 +6845,7 @@ int dev_change_net_namespace(struct net_device *dev, struct net *net, const char /* Send a netdev-add uevent to the new namespace */ kobject_uevent(&dev->dev.kobj, KOBJ_ADD); + netdev_adjacent_add_links(dev); /* Fixup kobjects */ err = device_rename(&dev->dev, dev->name); From 978aded4b39de7f441bb9bfb18cf830de6a968d3 Mon Sep 17 00:00:00 2001 From: Giuseppe CAVALLARO Date: Mon, 25 Aug 2014 14:56:18 +0200 Subject: [PATCH 021/101] stmmac: fix rx checksum programming This patch is to fix the IPC bit into the GMAC control register that must be done after the core initialization otherwise it will not have any effect. Signed-off-by: Giuseppe Cavallaro Signed-off-by: David S. Miller --- drivers/net/ethernet/stmicro/stmmac/stmmac_main.c | 13 ++++++------- 1 file changed, 6 insertions(+), 7 deletions(-) diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c index 08addd653728..51a89d4bb125 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c @@ -1637,6 +1637,12 @@ static int stmmac_hw_setup(struct net_device *dev) /* Initialize the MAC Core */ priv->hw->mac->core_init(priv->hw, dev->mtu); + ret = priv->hw->mac->rx_ipc(priv->hw); + if (!ret) { + pr_warn(" RX IPC Checksum Offload disabled\n"); + priv->plat->rx_coe = STMMAC_RX_COE_NONE; + } + /* Enable the MAC Rx/Tx */ stmmac_set_mac(priv->ioaddr, true); @@ -2592,7 +2598,6 @@ static const struct net_device_ops stmmac_netdev_ops = { */ static int stmmac_hw_init(struct stmmac_priv *priv) { - int ret; struct mac_device_info *mac; /* Identify the MAC HW device */ @@ -2649,12 +2654,6 @@ static int stmmac_hw_init(struct stmmac_priv *priv) /* To use alternate (extended) or normal descriptor structures */ stmmac_selec_desc_mode(priv); - ret = priv->hw->mac->rx_ipc(priv->hw); - if (!ret) { - pr_warn(" RX IPC Checksum Offload not configured.\n"); - priv->plat->rx_coe = STMMAC_RX_COE_NONE; - } - if (priv->plat->rx_coe) pr_info(" RX Checksum Offload Engine supported (type %d)\n", priv->plat->rx_coe); From f95f4045c734f801031782c8c6f8a5f381b0f69c Mon Sep 17 00:00:00 2001 From: Giuseppe CAVALLARO Date: Mon, 25 Aug 2014 14:56:19 +0200 Subject: [PATCH 022/101] stmmac: set ptp_clock to NULL while unregister This is to properly put to NULL the ptp_clock while un-register the PTP support. Signed-off-by: Giuseppe Cavallaro Signed-off-by: David S. Miller --- drivers/net/ethernet/stmicro/stmmac/stmmac_ptp.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_ptp.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_ptp.c index b7ad3565566c..c5ee79d8a8c5 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_ptp.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_ptp.c @@ -206,6 +206,7 @@ void stmmac_ptp_unregister(struct stmmac_priv *priv) { if (priv->ptp_clock) { ptp_clock_unregister(priv->ptp_clock); + priv->ptp_clock = NULL; pr_debug("Removed PTP HW clock successfully on %s\n", priv->dev->name); } From db115037bb57cdfe97078b13da762213f7980e81 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Michal=20Kube=C4=8Dek?= Date: Mon, 25 Aug 2014 15:16:22 +0200 Subject: [PATCH 023/101] net: fix checksum features handling in netif_skb_features() This is follow-up to da08143b8520 ("vlan: more careful checksum features handling") which introduced more careful feature intersection in vlan code, taking into account that HW_CSUM should be considered superset of IP_CSUM/IPV6_CSUM. The same is needed in netif_skb_features() in order to avoid offloading mismatch warning when vlan is created on top of a bond consisting of slaves supporting IP/IPv6 checksumming but not vlan Tx offloading. Signed-off-by: Michal Kubecek Signed-off-by: David S. Miller --- net/core/dev.c | 16 +++++++++++----- 1 file changed, 11 insertions(+), 5 deletions(-) diff --git a/net/core/dev.c b/net/core/dev.c index 66738e9d66e4..ab9a16530c36 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -2587,13 +2587,19 @@ netdev_features_t netif_skb_features(struct sk_buff *skb) return harmonize_features(skb, features); } - features &= (skb->dev->vlan_features | NETIF_F_HW_VLAN_CTAG_TX | - NETIF_F_HW_VLAN_STAG_TX); + features = netdev_intersect_features(features, + skb->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)) - features &= NETIF_F_SG | NETIF_F_HIGHDMA | NETIF_F_FRAGLIST | - NETIF_F_GEN_CSUM | NETIF_F_HW_VLAN_CTAG_TX | - NETIF_F_HW_VLAN_STAG_TX; + features = netdev_intersect_features(features, + NETIF_F_SG | + NETIF_F_HIGHDMA | + NETIF_F_FRAGLIST | + NETIF_F_GEN_CSUM | + NETIF_F_HW_VLAN_CTAG_TX | + NETIF_F_HW_VLAN_STAG_TX); return harmonize_features(skb, features); } From b853f31940c84cce6a3f5cb4f529b029906ee69c Mon Sep 17 00:00:00 2001 From: Jonas Jensen Date: Mon, 25 Aug 2014 16:22:11 +0200 Subject: [PATCH 024/101] net: moxa: clear DESC1 on ndo_start_xmit() TX buffer length is not cleared on ndo_start_xmit(). Failing to do so can bug/hang the controller and cause TX interrupts to stop altogether. Remove the readl() and compute a new value for DESC1. Addresses https://bugzilla.kernel.org/show_bug.cgi?id=69031 Signed-off-by: Jonas Jensen Signed-off-by: David S. Miller --- drivers/net/ethernet/moxa/moxart_ether.c | 7 +++---- 1 file changed, 3 insertions(+), 4 deletions(-) diff --git a/drivers/net/ethernet/moxa/moxart_ether.c b/drivers/net/ethernet/moxa/moxart_ether.c index 5020fd47825d..eed70d9f0d9d 100644 --- a/drivers/net/ethernet/moxa/moxart_ether.c +++ b/drivers/net/ethernet/moxa/moxart_ether.c @@ -346,10 +346,9 @@ static int moxart_mac_start_xmit(struct sk_buff *skb, struct net_device *ndev) len = ETH_ZLEN; } - txdes1 = readl(desc + TX_REG_OFFSET_DESC1); - txdes1 |= TX_DESC1_LTS | TX_DESC1_FTS; - txdes1 &= ~(TX_DESC1_FIFO_COMPLETE | TX_DESC1_INTR_COMPLETE); - txdes1 |= (len & TX_DESC1_BUF_SIZE_MASK); + txdes1 = TX_DESC1_LTS | TX_DESC1_FTS | (len & TX_DESC1_BUF_SIZE_MASK); + if (tx_head == TX_DESC_NUM_MASK) + txdes1 |= TX_DESC1_END; writel(txdes1, desc + TX_REG_OFFSET_DESC1); writel(TX_DESC0_DMA_OWN, desc + TX_REG_OFFSET_DESC0); From 9fe1b3bc8d9182e950a744e4a47187420efa67f3 Mon Sep 17 00:00:00 2001 From: Jonas Jensen Date: Mon, 25 Aug 2014 16:22:22 +0200 Subject: [PATCH 025/101] net: moxa: replace build_skb() with netdev_alloc_skb_ip_align() / memcpy() build_skb() is used to make skbs out of existing RX ring memory which is bad because the RX ring is allocated only once, on probe. Memory corruption occur because said memory is reclaimed, i.e. __kfree_skb() (and eventually put_page()). Replace build_skb() with netdev_alloc_skb_ip_align() and use memcpy(). Remove SKB_DATA_ALIGN() from RX buffer size while we're at it. Addresses https://bugzilla.kernel.org/show_bug.cgi?id=69041 Signed-off-by: Jonas Jensen Signed-off-by: David S. Miller --- drivers/net/ethernet/moxa/moxart_ether.c | 9 +++++---- 1 file changed, 5 insertions(+), 4 deletions(-) diff --git a/drivers/net/ethernet/moxa/moxart_ether.c b/drivers/net/ethernet/moxa/moxart_ether.c index eed70d9f0d9d..d66058d5c429 100644 --- a/drivers/net/ethernet/moxa/moxart_ether.c +++ b/drivers/net/ethernet/moxa/moxart_ether.c @@ -226,13 +226,15 @@ static int moxart_rx_poll(struct napi_struct *napi, int budget) if (len > RX_BUF_SIZE) len = RX_BUF_SIZE; - skb = build_skb(priv->rx_buf[rx_head], priv->rx_buf_size); + skb = netdev_alloc_skb_ip_align(ndev, len); + if (unlikely(!skb)) { - net_dbg_ratelimited("build_skb failed\n"); + net_dbg_ratelimited("netdev_alloc_skb_ip_align failed\n"); priv->stats.rx_dropped++; priv->stats.rx_errors++; } + memcpy(skb->data, priv->rx_buf[rx_head], len); skb_put(skb, len); skb->protocol = eth_type_trans(skb, ndev); napi_gro_receive(&priv->napi, skb); @@ -464,8 +466,7 @@ static int moxart_mac_probe(struct platform_device *pdev) spin_lock_init(&priv->txlock); priv->tx_buf_size = TX_BUF_SIZE; - priv->rx_buf_size = RX_BUF_SIZE + - SKB_DATA_ALIGN(sizeof(struct skb_shared_info)); + priv->rx_buf_size = RX_BUF_SIZE; priv->tx_desc_base = dma_alloc_coherent(NULL, TX_REG_DESC_SIZE * TX_DESC_NUM, &priv->tx_base, From 777fbc31447f111a1492c90fae2bc616f836d407 Mon Sep 17 00:00:00 2001 From: Jonas Jensen Date: Mon, 25 Aug 2014 16:22:32 +0200 Subject: [PATCH 026/101] net: moxa: synchronize DMA memory DMA memory should be synchronized before data is passed to/from controller. Add dma_sync_single_for_cpu(.., DMA_FROM_DEVICE) to RX path and dma_sync_single_for_device(.., DMA_TO_DEVICE) to TX path. Signed-off-by: Jonas Jensen Signed-off-by: David S. Miller --- drivers/net/ethernet/moxa/moxart_ether.c | 6 ++++++ 1 file changed, 6 insertions(+) diff --git a/drivers/net/ethernet/moxa/moxart_ether.c b/drivers/net/ethernet/moxa/moxart_ether.c index d66058d5c429..983d01949795 100644 --- a/drivers/net/ethernet/moxa/moxart_ether.c +++ b/drivers/net/ethernet/moxa/moxart_ether.c @@ -226,6 +226,9 @@ static int moxart_rx_poll(struct napi_struct *napi, int budget) if (len > RX_BUF_SIZE) len = RX_BUF_SIZE; + dma_sync_single_for_cpu(&ndev->dev, + priv->rx_mapping[rx_head], + priv->rx_buf_size, DMA_FROM_DEVICE); skb = netdev_alloc_skb_ip_align(ndev, len); if (unlikely(!skb)) { @@ -348,6 +351,9 @@ static int moxart_mac_start_xmit(struct sk_buff *skb, struct net_device *ndev) len = ETH_ZLEN; } + dma_sync_single_for_device(&ndev->dev, priv->tx_mapping[tx_head], + priv->tx_buf_size, DMA_TO_DEVICE); + txdes1 = TX_DESC1_LTS | TX_DESC1_FTS | (len & TX_DESC1_BUF_SIZE_MASK); if (tx_head == TX_DESC_NUM_MASK) txdes1 |= TX_DESC1_END; From 2b7890e757bc42f963c835521c2657bd16d7b7d6 Mon Sep 17 00:00:00 2001 From: Jonas Jensen Date: Mon, 25 Aug 2014 16:22:40 +0200 Subject: [PATCH 027/101] net: moxa: continue loop on skb allocation failure If netdev_alloc_skb_ip_align() fails, subsequent code will try to dereference an invalid pointer. Continue to next descriptor on error. While we're at it, 1. eliminate the chance of an endless loop, replace the main loop with while(rx < budget) 2. use napi_complete() and remove the explicit napi_gro_flush() Signed-off-by: Jonas Jensen Signed-off-by: David S. Miller --- drivers/net/ethernet/moxa/moxart_ether.c | 12 +++++------- 1 file changed, 5 insertions(+), 7 deletions(-) diff --git a/drivers/net/ethernet/moxa/moxart_ether.c b/drivers/net/ethernet/moxa/moxart_ether.c index 983d01949795..2f12c88c66ab 100644 --- a/drivers/net/ethernet/moxa/moxart_ether.c +++ b/drivers/net/ethernet/moxa/moxart_ether.c @@ -206,7 +206,7 @@ static int moxart_rx_poll(struct napi_struct *napi, int budget) int rx_head = priv->rx_head; int rx = 0; - while (1) { + while (rx < budget) { desc = priv->rx_desc_base + (RX_REG_DESC_SIZE * rx_head); desc0 = readl(desc + RX_REG_OFFSET_DESC0); @@ -218,7 +218,7 @@ static int moxart_rx_poll(struct napi_struct *napi, int budget) net_dbg_ratelimited("packet error\n"); priv->stats.rx_dropped++; priv->stats.rx_errors++; - continue; + goto rx_next; } len = desc0 & RX_DESC0_FRAME_LEN_MASK; @@ -235,6 +235,7 @@ static int moxart_rx_poll(struct napi_struct *napi, int budget) net_dbg_ratelimited("netdev_alloc_skb_ip_align failed\n"); priv->stats.rx_dropped++; priv->stats.rx_errors++; + goto rx_next; } memcpy(skb->data, priv->rx_buf[rx_head], len); @@ -249,18 +250,15 @@ static int moxart_rx_poll(struct napi_struct *napi, int budget) if (desc0 & RX_DESC0_MULTICAST) priv->stats.multicast++; +rx_next: writel(RX_DESC0_DMA_OWN, desc + RX_REG_OFFSET_DESC0); rx_head = RX_NEXT(rx_head); priv->rx_head = rx_head; - - if (rx >= budget) - break; } if (rx < budget) { - napi_gro_flush(napi, false); - __napi_complete(napi); + napi_complete(napi); } priv->reg_imr |= RPKT_FINISH_M; From 47ccd1edc57ddabb81f6ba07e1e30201a8f578d6 Mon Sep 17 00:00:00 2001 From: Vlad Yasevich Date: Mon, 25 Aug 2014 10:34:48 -0400 Subject: [PATCH 028/101] e1000e: Fix TSO with non-accelerated vlans This device claims TSO support for vlans. It also allows a user to control vlan acceleration offloading. As such, it is possible to turn off vlan acceleration and configure a vlan which will continue to support TSO. In such situation the packet passed down the the device will contain a vlan header and skb->protocol will be set to ETH_P_8021Q. The device assumes that skb->protocol contains network protocol value and uses that value to set up TSO information. This results in corrupted frames sent on the wire. Corruptions include incorrect IP total length and invalid IP checksum. This patch extract the protocol value correctly and corrects TSO for non-accelerated traffic. CC: Jeff Kirsher CC: Jesse Brandeburg CC: Bruce Allan CC: Carolyn Wyborny CC: Don Skidmore CC: Greg Rose CC: Alex Duyck CC: John Ronciak CC: Mitch Williams CC: Linux NICS CC: e1000-devel@lists.sourceforge.net Signed-off-by: Vladislav Yasevich Signed-off-by: David S. Miller --- drivers/net/ethernet/intel/e1000e/netdev.c | 21 +++++++++------------ 1 file changed, 9 insertions(+), 12 deletions(-) diff --git a/drivers/net/ethernet/intel/e1000e/netdev.c b/drivers/net/ethernet/intel/e1000e/netdev.c index 65c3aef2bd36..247335d2c7ec 100644 --- a/drivers/net/ethernet/intel/e1000e/netdev.c +++ b/drivers/net/ethernet/intel/e1000e/netdev.c @@ -5164,7 +5164,8 @@ link_up: #define E1000_TX_FLAGS_VLAN_MASK 0xffff0000 #define E1000_TX_FLAGS_VLAN_SHIFT 16 -static int e1000_tso(struct e1000_ring *tx_ring, struct sk_buff *skb) +static int e1000_tso(struct e1000_ring *tx_ring, struct sk_buff *skb, + __be16 protocol) { struct e1000_context_desc *context_desc; struct e1000_buffer *buffer_info; @@ -5183,7 +5184,7 @@ static int e1000_tso(struct e1000_ring *tx_ring, struct sk_buff *skb) hdr_len = skb_transport_offset(skb) + tcp_hdrlen(skb); mss = skb_shinfo(skb)->gso_size; - if (skb->protocol == htons(ETH_P_IP)) { + if (protocol == htons(ETH_P_IP)) { struct iphdr *iph = ip_hdr(skb); iph->tot_len = 0; iph->check = 0; @@ -5231,7 +5232,8 @@ static int e1000_tso(struct e1000_ring *tx_ring, struct sk_buff *skb) return 1; } -static bool e1000_tx_csum(struct e1000_ring *tx_ring, struct sk_buff *skb) +static bool e1000_tx_csum(struct e1000_ring *tx_ring, struct sk_buff *skb, + __be16 protocol) { struct e1000_adapter *adapter = tx_ring->adapter; struct e1000_context_desc *context_desc; @@ -5239,16 +5241,10 @@ static bool e1000_tx_csum(struct e1000_ring *tx_ring, struct sk_buff *skb) unsigned int i; u8 css; u32 cmd_len = E1000_TXD_CMD_DEXT; - __be16 protocol; if (skb->ip_summed != CHECKSUM_PARTIAL) return false; - if (skb->protocol == cpu_to_be16(ETH_P_8021Q)) - protocol = vlan_eth_hdr(skb)->h_vlan_encapsulated_proto; - else - protocol = skb->protocol; - switch (protocol) { case cpu_to_be16(ETH_P_IP): if (ip_hdr(skb)->protocol == IPPROTO_TCP) @@ -5546,6 +5542,7 @@ static netdev_tx_t e1000_xmit_frame(struct sk_buff *skb, int count = 0; int tso; unsigned int f; + __be16 protocol = vlan_get_protocol(skb); if (test_bit(__E1000_DOWN, &adapter->state)) { dev_kfree_skb_any(skb); @@ -5620,7 +5617,7 @@ static netdev_tx_t e1000_xmit_frame(struct sk_buff *skb, first = tx_ring->next_to_use; - tso = e1000_tso(tx_ring, skb); + tso = e1000_tso(tx_ring, skb, protocol); if (tso < 0) { dev_kfree_skb_any(skb); return NETDEV_TX_OK; @@ -5628,14 +5625,14 @@ static netdev_tx_t e1000_xmit_frame(struct sk_buff *skb, if (tso) tx_flags |= E1000_TX_FLAGS_TSO; - else if (e1000_tx_csum(tx_ring, skb)) + else if (e1000_tx_csum(tx_ring, skb, protocol)) tx_flags |= E1000_TX_FLAGS_CSUM; /* Old method was to assume IPv4 packet by default if TSO was enabled. * 82571 hardware supports TSO capabilities for IPv6 as well... * no longer assume, we must. */ - if (skb->protocol == htons(ETH_P_IP)) + if (protocol == htons(ETH_P_IP)) tx_flags |= E1000_TX_FLAGS_IPV4; if (unlikely(skb->no_fcs)) From 06f4d0333e86e302da3ac8386f873d5e353baf2e Mon Sep 17 00:00:00 2001 From: Vlad Yasevich Date: Mon, 25 Aug 2014 10:34:49 -0400 Subject: [PATCH 029/101] e1000: Fix TSO for non-accelerated vlan traffic This device claims TSO and checksum support for vlans. It also allows a user to control vlan acceleration offloading. As such, it is possible to turn off vlan acceleration and configure a vlan which will continue to support TSO. In such situation the packet passed down the the device will contain a vlan header and skb->protocol will be set to ETH_P_8021Q. The device assumes that skb->protocol contains network protocol value and uses that value to set up TSO and checksum information. This will results in corrupted frames sent on the wire. This patch extract the protocol value correctly and corrects TSO for non-accelerated traffic. CC: Jeff Kirsher CC: Jesse Brandeburg CC: Bruce Allan CC: Carolyn Wyborny CC: Don Skidmore CC: Greg Rose CC: Alex Duyck CC: John Ronciak CC: Mitch Williams CC: Linux NICS CC: e1000-devel@lists.sourceforge.net Signed-off-by: Vladislav Yasevich Signed-off-by: David S. Miller --- drivers/net/ethernet/intel/e1000/e1000_main.c | 19 +++++++++++-------- 1 file changed, 11 insertions(+), 8 deletions(-) diff --git a/drivers/net/ethernet/intel/e1000/e1000_main.c b/drivers/net/ethernet/intel/e1000/e1000_main.c index cbc330b301cd..ad3d5d12173f 100644 --- a/drivers/net/ethernet/intel/e1000/e1000_main.c +++ b/drivers/net/ethernet/intel/e1000/e1000_main.c @@ -2674,7 +2674,8 @@ set_itr_now: #define E1000_TX_FLAGS_VLAN_SHIFT 16 static int e1000_tso(struct e1000_adapter *adapter, - struct e1000_tx_ring *tx_ring, struct sk_buff *skb) + struct e1000_tx_ring *tx_ring, struct sk_buff *skb, + __be16 protocol) { struct e1000_context_desc *context_desc; struct e1000_buffer *buffer_info; @@ -2692,7 +2693,7 @@ static int e1000_tso(struct e1000_adapter *adapter, hdr_len = skb_transport_offset(skb) + tcp_hdrlen(skb); mss = skb_shinfo(skb)->gso_size; - if (skb->protocol == htons(ETH_P_IP)) { + if (protocol == htons(ETH_P_IP)) { struct iphdr *iph = ip_hdr(skb); iph->tot_len = 0; iph->check = 0; @@ -2702,7 +2703,7 @@ static int e1000_tso(struct e1000_adapter *adapter, 0); cmd_length = E1000_TXD_CMD_IP; ipcse = skb_transport_offset(skb) - 1; - } else if (skb->protocol == htons(ETH_P_IPV6)) { + } else if (skb_is_gso_v6(skb)) { ipv6_hdr(skb)->payload_len = 0; tcp_hdr(skb)->check = ~csum_ipv6_magic(&ipv6_hdr(skb)->saddr, @@ -2745,7 +2746,8 @@ static int e1000_tso(struct e1000_adapter *adapter, } static bool e1000_tx_csum(struct e1000_adapter *adapter, - struct e1000_tx_ring *tx_ring, struct sk_buff *skb) + struct e1000_tx_ring *tx_ring, struct sk_buff *skb, + __be16 protocol) { struct e1000_context_desc *context_desc; struct e1000_buffer *buffer_info; @@ -2756,7 +2758,7 @@ static bool e1000_tx_csum(struct e1000_adapter *adapter, if (skb->ip_summed != CHECKSUM_PARTIAL) return false; - switch (skb->protocol) { + switch (protocol) { case cpu_to_be16(ETH_P_IP): if (ip_hdr(skb)->protocol == IPPROTO_TCP) cmd_len |= E1000_TXD_CMD_TCP; @@ -3097,6 +3099,7 @@ static netdev_tx_t e1000_xmit_frame(struct sk_buff *skb, int count = 0; int tso; unsigned int f; + __be16 protocol = vlan_get_protocol(skb); /* This goes back to the question of how to logically map a Tx queue * to a flow. Right now, performance is impacted slightly negatively @@ -3210,7 +3213,7 @@ static netdev_tx_t e1000_xmit_frame(struct sk_buff *skb, first = tx_ring->next_to_use; - tso = e1000_tso(adapter, tx_ring, skb); + tso = e1000_tso(adapter, tx_ring, skb, protocol); if (tso < 0) { dev_kfree_skb_any(skb); return NETDEV_TX_OK; @@ -3220,10 +3223,10 @@ static netdev_tx_t e1000_xmit_frame(struct sk_buff *skb, if (likely(hw->mac_type != e1000_82544)) tx_ring->last_tx_tso = true; tx_flags |= E1000_TX_FLAGS_TSO; - } else if (likely(e1000_tx_csum(adapter, tx_ring, skb))) + } else if (likely(e1000_tx_csum(adapter, tx_ring, skb, protocol))) tx_flags |= E1000_TX_FLAGS_CSUM; - if (likely(skb->protocol == htons(ETH_P_IP))) + if (protocol == htons(ETH_P_IP)) tx_flags |= E1000_TX_FLAGS_IPV4; if (unlikely(skb->no_fcs)) From 1c53730a04fb651e35af0a12bd35f6a00481f53c Mon Sep 17 00:00:00 2001 From: Vlad Yasevich Date: Mon, 25 Aug 2014 10:34:50 -0400 Subject: [PATCH 030/101] bna: Support TSO and partial checksum with non-accelerated vlans. This device claims TSO and checksum support for vlans. It also allows a user to control vlan acceleration offloading. As such, it is possible to turn off vlan acceleration and configure a vlan which will continue to support TSO. In such situation the packet passed down the the device will contain a vlan header and skb->protocol will be set to ETH_P_8021Q. The device assumes that skb->protocol contains network protocol value and uses that value to set up TSO information. This results in corrupted frames sent on the wire. This patch extract the protocol value correctly and corrects TSO and checksums for non-accelerated traffic. CC: Rasesh Mody Signed-off-by: Vladislav Yasevich Signed-off-by: David S. Miller --- drivers/net/ethernet/brocade/bna/bnad.c | 7 ++++--- 1 file changed, 4 insertions(+), 3 deletions(-) diff --git a/drivers/net/ethernet/brocade/bna/bnad.c b/drivers/net/ethernet/brocade/bna/bnad.c index ff8cae5e2535..ffc92a41d75b 100644 --- a/drivers/net/ethernet/brocade/bna/bnad.c +++ b/drivers/net/ethernet/brocade/bna/bnad.c @@ -2506,7 +2506,7 @@ bnad_tso_prepare(struct bnad *bnad, struct sk_buff *skb) * For TSO, the TCP checksum field is seeded with pseudo-header sum * excluding the length field. */ - if (skb->protocol == htons(ETH_P_IP)) { + if (vlan_get_protocol(skb) == htons(ETH_P_IP)) { struct iphdr *iph = ip_hdr(skb); /* Do we really need these? */ @@ -2870,12 +2870,13 @@ bnad_txq_wi_prepare(struct bnad *bnad, struct bna_tcb *tcb, } if (skb->ip_summed == CHECKSUM_PARTIAL) { + __be16 net_proto = vlan_get_protocol(skb); u8 proto = 0; - if (skb->protocol == htons(ETH_P_IP)) + if (net_proto == htons(ETH_P_IP)) proto = ip_hdr(skb)->protocol; #ifdef NETIF_F_IPV6_CSUM - else if (skb->protocol == htons(ETH_P_IPV6)) { + else if (net_proto == htons(ETH_P_IPV6)) { /* nexthdr may not be TCP immediately. */ proto = ipv6_hdr(skb)->nexthdr; } From be1d1486122092f5a323539ee4cc328d06083f63 Mon Sep 17 00:00:00 2001 From: Vlad Yasevich Date: Mon, 25 Aug 2014 10:34:51 -0400 Subject: [PATCH 031/101] ehea: Fix TSO and hw checksums with non-accelerated vlan packets. The driver claims that it can do TSO and IP checksums on vlan devices and also allows user to control vlan acceleration offloading. This makes it possible to push traffic to this driver that has TSO or partial checksums set, but also have a non-accelearted vlan header. In this case, the driver will fail to correctly identify such traffic and will not correctly perform segmentation and checksum calculation. Fix this by using vlan_get_protocol() helper instead of assuming skb->protocol always has this information. CC: Thadeu Lima de Souza Cascardo Signed-off-by: Vladislav Yasevich Signed-off-by: David S. Miller --- drivers/net/ethernet/ibm/ehea/ehea_main.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/net/ethernet/ibm/ehea/ehea_main.c b/drivers/net/ethernet/ibm/ehea/ehea_main.c index a0b418e007a0..566b17db135a 100644 --- a/drivers/net/ethernet/ibm/ehea/ehea_main.c +++ b/drivers/net/ethernet/ibm/ehea/ehea_main.c @@ -1994,7 +1994,7 @@ static void xmit_common(struct sk_buff *skb, struct ehea_swqe *swqe) { swqe->tx_control |= EHEA_SWQE_IMM_DATA_PRESENT | EHEA_SWQE_CRC; - if (skb->protocol != htons(ETH_P_IP)) + if (vlan_get_protocol(skb) != htons(ETH_P_IP)) return; if (skb->ip_summed == CHECKSUM_PARTIAL) From 3d34dd03d55c3fa6c332e43e545ec18feb79ee85 Mon Sep 17 00:00:00 2001 From: Vlad Yasevich Date: Mon, 25 Aug 2014 10:34:52 -0400 Subject: [PATCH 032/101] i40e: Fix TSO and hw checksums for non-accelerated vlan packets. This device claims TSO and checksum support for vlans. It also allows a user to control vlan acceleration offloading. As such, it is possible to turn off vlan acceleration and configure a vlan which will continue to support TSO and hw checksums. In such situation the packet passed down the the device will contain a vlan header and skb->protocol will be set to ETH_P_8021Q. The device assumes that skb->protocol contains network protocol value and uses that value to set up TSO and checksum information. This results in corrupted frames sent on the wire. This patch extract the protocol value correctly and corrects TSO and checksums for non-accelerated traffic. Fix this by using vlan_get_protocol() helper. CC: Jeff Kirsher CC: Jesse Brandeburg CC: Bruce Allan CC: Carolyn Wyborny CC: Don Skidmore CC: Greg Rose CC: Alex Duyck CC: John Ronciak CC: Mitch Williams CC: Linux NICS CC: e1000-devel@lists.sourceforge.net Signed-off-by: Vladislav Yasevich Signed-off-by: David S. Miller --- drivers/net/ethernet/intel/i40e/i40e_txrx.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/net/ethernet/intel/i40e/i40e_txrx.c b/drivers/net/ethernet/intel/i40e/i40e_txrx.c index a51aa37b7b5a..369848e107f8 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_txrx.c +++ b/drivers/net/ethernet/intel/i40e/i40e_txrx.c @@ -2295,7 +2295,7 @@ static netdev_tx_t i40e_xmit_frame_ring(struct sk_buff *skb, goto out_drop; /* obtain protocol of skb */ - protocol = skb->protocol; + protocol = vlan_get_protocol(skb); /* record the location of the first descriptor for this packet */ first = &tx_ring->tx_bi[tx_ring->next_to_use]; From a12c415834cc335ae015ba104e78c3fb35ec9be9 Mon Sep 17 00:00:00 2001 From: Vlad Yasevich Date: Mon, 25 Aug 2014 10:34:53 -0400 Subject: [PATCH 033/101] i40evf: Fix TSO and hw checksums for non-accelerated vlan packets. This device claims TSO and checksum support for vlans. It also allows a user to control vlan acceleration offloading. As such, it is possible to turn off vlan acceleration and configure a vlan which will continue to support TSO and hw checksums. In such situation the packet passed down the the device will contain a vlan header and skb->protocol will be set to ETH_P_8021Q. The device assumes that skb->protocol contains network protocol value and uses that value to set up TSO and checksum information. This results in corrupted frames sent on the wire. This patch extract the protocol value correctly and corrects TSO and checksums for non-accelerated traffic. Fix this by using vlan_get_protocol() helper. CC: Jeff Kirsher CC: Jesse Brandeburg CC: Bruce Allan CC: Carolyn Wyborny CC: Don Skidmore CC: Greg Rose CC: Alex Duyck CC: John Ronciak CC: Mitch Williams CC: Linux NICS CC: e1000-devel@lists.sourceforge.net Signed-off-by: Vladislav Yasevich Signed-off-by: David S. Miller --- drivers/net/ethernet/intel/i40evf/i40e_txrx.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/net/ethernet/intel/i40evf/i40e_txrx.c b/drivers/net/ethernet/intel/i40evf/i40e_txrx.c index 79bf96ca6489..95a3ec236b49 100644 --- a/drivers/net/ethernet/intel/i40evf/i40e_txrx.c +++ b/drivers/net/ethernet/intel/i40evf/i40e_txrx.c @@ -1597,7 +1597,7 @@ static netdev_tx_t i40e_xmit_frame_ring(struct sk_buff *skb, goto out_drop; /* obtain protocol of skb */ - protocol = skb->protocol; + protocol = vlan_get_protocol(skb); /* record the location of the first descriptor for this packet */ first = &tx_ring->tx_bi[tx_ring->next_to_use]; From 817dbfa5d1bc276a72c1a577310382008e8aca0a Mon Sep 17 00:00:00 2001 From: Vlad Yasevich Date: Mon, 25 Aug 2014 10:34:54 -0400 Subject: [PATCH 034/101] mvneta: Fix TSO and checksum for non-acceleration vlan traffic This driver doesn't appear to support vlan acceleration at all. However, it does claim to support TSO and IP checksums for vlan devices. Thus any configured vlan device would end up passing down partial checksums or TSO frames. The driver also uses the value from skb->protocol to determine TSO and checksum offload information, but assumes that skb->protocol holds the l3 protocol information. As a result, vlan traffic with partial checksums or TSO will fail those checks and TSO will not happen. Fix this by using vlan_get_protocol() helper. CC: Thomas Petazzoni Signed-off-by: Vladislav Yasevich Signed-off-by: David S. Miller --- drivers/net/ethernet/marvell/mvneta.c | 7 ++++--- 1 file changed, 4 insertions(+), 3 deletions(-) diff --git a/drivers/net/ethernet/marvell/mvneta.c b/drivers/net/ethernet/marvell/mvneta.c index c9f1d1b7ef37..133f8c6444e0 100644 --- a/drivers/net/ethernet/marvell/mvneta.c +++ b/drivers/net/ethernet/marvell/mvneta.c @@ -1371,15 +1371,16 @@ static u32 mvneta_skb_tx_csum(struct mvneta_port *pp, struct sk_buff *skb) { if (skb->ip_summed == CHECKSUM_PARTIAL) { int ip_hdr_len = 0; + __be16 l3_proto = vlan_get_protocol(skb); u8 l4_proto; - if (skb->protocol == htons(ETH_P_IP)) { + if (l3_proto == htons(ETH_P_IP)) { struct iphdr *ip4h = ip_hdr(skb); /* Calculate IPv4 checksum and L4 checksum */ ip_hdr_len = ip4h->ihl; l4_proto = ip4h->protocol; - } else if (skb->protocol == htons(ETH_P_IPV6)) { + } else if (l3_proto == htons(ETH_P_IPV6)) { struct ipv6hdr *ip6h = ipv6_hdr(skb); /* Read l4_protocol from one of IPv6 extra headers */ @@ -1390,7 +1391,7 @@ static u32 mvneta_skb_tx_csum(struct mvneta_port *pp, struct sk_buff *skb) return MVNETA_TX_L4_CSUM_NOT; return mvneta_txq_desc_csum(skb_network_offset(skb), - skb->protocol, ip_hdr_len, l4_proto); + l3_proto, ip_hdr_len, l4_proto); } return MVNETA_TX_L4_CSUM_NOT; From 1ee1cfe7d3df00bff11dd28576eeac1875d7d51f Mon Sep 17 00:00:00 2001 From: Vlad Yasevich Date: Mon, 25 Aug 2014 10:34:55 -0400 Subject: [PATCH 035/101] qlge: Fix TSO for non-accelerated vlan traffic This device claims TSO support for vlans. It also allows a user to control vlan acceleration offloading. As such, it is possible to turn off vlan acceleration and configure a vlan which will continue to send TSO traffic. In such situation the packet passed down the the device will contain a vlan header and skb->protocol will be set to ETH_P_8021Q. The device assumes that skb->protocol contains network protocol value and uses that value to set up TSO information. This results in corrupted frames sent on the wire. This patch extracts the protocol value correctly by using a vlan_get_protocol() helper and corrects corrupt TSO frames. CC: Shahed Shaikh CC: Jitendra Kalsaria CC: Ron Mercer CC: linux-driver@qlogic.com Signed-off-by: Vladislav Yasevich Acked-by: Shahed Shaikh Signed-off-by: David S. Miller --- drivers/net/ethernet/qlogic/qlge/qlge_main.c | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) diff --git a/drivers/net/ethernet/qlogic/qlge/qlge_main.c b/drivers/net/ethernet/qlogic/qlge/qlge_main.c index 188626e2a861..3e96f269150d 100644 --- a/drivers/net/ethernet/qlogic/qlge/qlge_main.c +++ b/drivers/net/ethernet/qlogic/qlge/qlge_main.c @@ -2556,6 +2556,7 @@ static int ql_tso(struct sk_buff *skb, struct ob_mac_tso_iocb_req *mac_iocb_ptr) if (skb_is_gso(skb)) { int err; + __be16 l3_proto = vlan_get_protocol(skb); err = skb_cow_head(skb, 0); if (err < 0) @@ -2572,7 +2573,7 @@ static int ql_tso(struct sk_buff *skb, struct ob_mac_tso_iocb_req *mac_iocb_ptr) << OB_MAC_TRANSPORT_HDR_SHIFT); mac_iocb_ptr->mss = cpu_to_le16(skb_shinfo(skb)->gso_size); mac_iocb_ptr->flags2 |= OB_MAC_TSO_IOCB_LSO; - if (likely(skb->protocol == htons(ETH_P_IP))) { + if (likely(l3_proto == htons(ETH_P_IP))) { struct iphdr *iph = ip_hdr(skb); iph->check = 0; mac_iocb_ptr->flags1 |= OB_MAC_TSO_IOCB_IP4; @@ -2580,7 +2581,7 @@ static int ql_tso(struct sk_buff *skb, struct ob_mac_tso_iocb_req *mac_iocb_ptr) iph->daddr, 0, IPPROTO_TCP, 0); - } else if (skb->protocol == htons(ETH_P_IPV6)) { + } else if (l3_proto == htons(ETH_P_IPV6)) { mac_iocb_ptr->flags1 |= OB_MAC_TSO_IOCB_IP6; tcp_hdr(skb)->check = ~csum_ipv6_magic(&ipv6_hdr(skb)->saddr, From e24f8191cc35ae3780b4656a6befae8b8657edc2 Mon Sep 17 00:00:00 2001 From: Wei Liu Date: Mon, 25 Aug 2014 16:44:00 +0100 Subject: [PATCH 036/101] xen-netback: move netif_napi_add before binding interrupt Interrupt is enabled when bind_interdomain_evtchn_to_irqhandler returns. If there's interrupt pending interrupt handler is invoked. NAPI needs to be initialised before binding interrupt otherwise the interrupt handler will try to scheduling a NAPI instance that is not initialised yet, resulting in kernel OOPS. This fixes a regression introduced in ea2c5e13 ("xen-netback: move NAPI add/remove calls"). Ideally function calls to create kthreads should also be moved before binding but I intent to fix this regression with minimal changes and refactor the code with another patch. Reported-by: Thomas Leonard Signed-off-by: Wei Liu Cc: Ian Campbell Signed-off-by: David S. Miller --- drivers/net/xen-netback/interface.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/drivers/net/xen-netback/interface.c b/drivers/net/xen-netback/interface.c index e29e15dca86e..f379689dde30 100644 --- a/drivers/net/xen-netback/interface.c +++ b/drivers/net/xen-netback/interface.c @@ -576,6 +576,9 @@ int xenvif_connect(struct xenvif_queue *queue, unsigned long tx_ring_ref, init_waitqueue_head(&queue->dealloc_wq); atomic_set(&queue->inflight_packets, 0); + netif_napi_add(queue->vif->dev, &queue->napi, xenvif_poll, + XENVIF_NAPI_WEIGHT); + if (tx_evtchn == rx_evtchn) { /* feature-split-event-channels == 0 */ err = bind_interdomain_evtchn_to_irqhandler( @@ -629,9 +632,6 @@ int xenvif_connect(struct xenvif_queue *queue, unsigned long tx_ring_ref, wake_up_process(queue->task); wake_up_process(queue->dealloc_task); - netif_napi_add(queue->vif->dev, &queue->napi, xenvif_poll, - XENVIF_NAPI_WEIGHT); - return 0; err_rx_unbind: From 2d39d120781a5770573dc6ed672a5a562f541aea Mon Sep 17 00:00:00 2001 From: "David S. Miller" Date: Mon, 25 Aug 2014 20:21:55 -0700 Subject: [PATCH 037/101] mvneta: Add missing if_vlan.h include. drivers/net/ethernet/marvell/mvneta.c: In function 'mvneta_skb_tx_csum': drivers/net/ethernet/marvell/mvneta.c:1374:3: error: implicit declaration of function 'vlan_get_protocol' [-Werror=implicit-function-declaration] __be16 l3_proto = vlan_get_protocol(skb); ^ Reporeted-by: Stephen Rothwell Signed-off-by: David S. Miller --- drivers/net/ethernet/marvell/mvneta.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/net/ethernet/marvell/mvneta.c b/drivers/net/ethernet/marvell/mvneta.c index 133f8c6444e0..ade067de1689 100644 --- a/drivers/net/ethernet/marvell/mvneta.c +++ b/drivers/net/ethernet/marvell/mvneta.c @@ -20,6 +20,7 @@ #include #include #include +#include #include #include #include From bb512ad0732232f1d2693bb68f31a76bed8f22ae Mon Sep 17 00:00:00 2001 From: Johannes Berg Date: Mon, 25 Aug 2014 12:08:09 +0200 Subject: [PATCH 038/101] Revert "mac80211: disable uAPSD if all ACs are under ACM" This reverts commit 24aa11ab8ae03292d38ec0dbd9bc2ac49fe8a6dd. That commit was wrong since it uses data that hasn't even been set up yet, but might be a hold-over from a previous connection. Additionally, it seems like a driver-specific workaround that shouldn't have been in mac80211 to start with. Cc: stable@vger.kernel.org Fixes: 24aa11ab8ae0 ("mac80211: disable uAPSD if all ACs are under ACM") Reviewed-by: Luciano Coelho Signed-off-by: Johannes Berg --- net/mac80211/mlme.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) diff --git a/net/mac80211/mlme.c b/net/mac80211/mlme.c index 31a8afaf7332..b82a12a9f0f1 100644 --- a/net/mac80211/mlme.c +++ b/net/mac80211/mlme.c @@ -4376,8 +4376,7 @@ int ieee80211_mgd_assoc(struct ieee80211_sub_if_data *sdata, rcu_read_unlock(); if (bss->wmm_used && bss->uapsd_supported && - (sdata->local->hw.flags & IEEE80211_HW_SUPPORTS_UAPSD) && - sdata->wmm_acm != 0xff) { + (sdata->local->hw.flags & IEEE80211_HW_SUPPORTS_UAPSD)) { assoc_data->uapsd = true; ifmgd->flags |= IEEE80211_STA_UAPSD_ENABLED; } else { From 0e67c13667a72093aa3ef3cb54dd521e34e500fc Mon Sep 17 00:00:00 2001 From: Felix Fietkau Date: Fri, 25 Jul 2014 16:20:22 +0200 Subject: [PATCH 039/101] mac80211: ignore AP_VLAN in ieee80211_recalc_chanctx_chantype When bringing down the AP, a WARN_ON is hit because the bss config chandef is empty here. Since AP_VLAN channel settings do not matter for anything chanctx related (always inherits the settings from the AP interface), let's just ignore it here. Signed-off-by: Felix Fietkau Signed-off-by: Johannes Berg --- net/mac80211/chan.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/net/mac80211/chan.c b/net/mac80211/chan.c index 6d537f03c0ba..4206a11bf8d7 100644 --- a/net/mac80211/chan.c +++ b/net/mac80211/chan.c @@ -541,6 +541,8 @@ static void ieee80211_recalc_chanctx_chantype(struct ieee80211_local *local, continue; if (rcu_access_pointer(sdata->vif.chanctx_conf) != conf) continue; + if (sdata->vif.type == NL80211_IFTYPE_AP_VLAN) + continue; if (!compat) compat = &sdata->vif.bss_conf.chandef; From 3918edb0e6a8b16c2866f4657d9fed41f9da562d Mon Sep 17 00:00:00 2001 From: Felix Fietkau Date: Fri, 25 Jul 2014 16:20:23 +0200 Subject: [PATCH 040/101] mac80211: fix smps mode check for AP_VLAN In ieee80211_sta_ps_deliver_wakeup, sdata->smps_mode is checked. This is initialized only for the base AP interface, not the individual VLANs. Signed-off-by: Felix Fietkau Signed-off-by: Johannes Berg --- net/mac80211/sta_info.c | 7 +++++-- 1 file changed, 5 insertions(+), 2 deletions(-) diff --git a/net/mac80211/sta_info.c b/net/mac80211/sta_info.c index c6ee2139fbc5..441875f03750 100644 --- a/net/mac80211/sta_info.c +++ b/net/mac80211/sta_info.c @@ -1094,8 +1094,11 @@ void ieee80211_sta_ps_deliver_wakeup(struct sta_info *sta) unsigned long flags; struct ps_data *ps; - if (sdata->vif.type == NL80211_IFTYPE_AP || - sdata->vif.type == NL80211_IFTYPE_AP_VLAN) + if (sdata->vif.type == NL80211_IFTYPE_AP_VLAN) + sdata = container_of(sdata->bss, struct ieee80211_sub_if_data, + u.ap); + + if (sdata->vif.type == NL80211_IFTYPE_AP) ps = &sdata->bss->ps; else if (ieee80211_vif_is_mesh(&sdata->vif)) ps = &sdata->u.mesh.ps; From 6c6fa49649dc826b7ef81314324fe55cf1d0d954 Mon Sep 17 00:00:00 2001 From: Bob Copeland Date: Sat, 28 Jun 2014 16:35:25 -0400 Subject: [PATCH 041/101] mac80211: mesh_plink: handle confirm frames with new plid The 802.11 standard says when processing a plink confirm frame: "If the peerLinkID in the mesh peering instance has not been set, the Local Link ID field of the Mesh Peering Confirm request shall be copied into the peerLinkID in the mesh peering instance." We were only doing this when receiving an open peering frame, but it could happen that the open frame gets lost and so we should handle this case rather than rejecting the confirm and failing the whole peering process. Reported-by: Yu Niiro Signed-off-by: Bob Copeland Signed-off-by: Johannes Berg --- net/mac80211/mesh_plink.c | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-) diff --git a/net/mac80211/mesh_plink.c b/net/mac80211/mesh_plink.c index 63b874101b27..c47194d27149 100644 --- a/net/mac80211/mesh_plink.c +++ b/net/mac80211/mesh_plink.c @@ -959,7 +959,8 @@ mesh_plink_get_event(struct ieee80211_sub_if_data *sdata, if (!matches_local) event = CNF_RJCT; if (!mesh_plink_free_count(sdata) || - (sta->llid != llid || sta->plid != plid)) + sta->llid != llid || + (sta->plid && sta->plid != plid)) event = CNF_IGNR; else event = CNF_ACPT; @@ -1080,6 +1081,10 @@ mesh_process_plink_frame(struct ieee80211_sub_if_data *sdata, goto unlock_rcu; } + /* 802.11-2012 13.3.7.2 - update plid on CNF if not set */ + if (!sta->plid && event == CNF_ACPT) + sta->plid = plid; + changed |= mesh_plink_fsm(sdata, sta, event); unlock_rcu: From c7dcb45facedbff84237adb77bd3ba50f75c0de4 Mon Sep 17 00:00:00 2001 From: Denton Gentry Date: Mon, 28 Jul 2014 23:36:32 -0700 Subject: [PATCH 042/101] mac80211: fix start_seq_num in Rx reorder offload sta->last_seq_ctrl is the seq_ctrl field from the last header seen, need to shift it 4 bits to extract the sequence number. Otherwise the ieee80211_sn_less() check at the top of ieee80211_sta_manage_reorder_buf drops frames until the sequence number catches up. Cc: Michal Kazior Signed-off-by: Denton Gentry Signed-off-by: Johannes Berg --- net/mac80211/iface.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/net/mac80211/iface.c b/net/mac80211/iface.c index 01eede7406a5..f75e5f132c5a 100644 --- a/net/mac80211/iface.c +++ b/net/mac80211/iface.c @@ -1175,8 +1175,8 @@ static void ieee80211_iface_work(struct work_struct *work) if (sta) { u16 last_seq; - last_seq = le16_to_cpu( - sta->last_seq_ctrl[rx_agg->tid]); + last_seq = IEEE80211_SEQ_TO_SN(le16_to_cpu( + sta->last_seq_ctrl[rx_agg->tid])); __ieee80211_start_rx_ba_session(sta, 0, 0, From 14b058bbce9279ee432f0944ca14df69f4a0d170 Mon Sep 17 00:00:00 2001 From: Johannes Berg Date: Tue, 5 Aug 2014 09:34:05 +0200 Subject: [PATCH 043/101] mac80211: fix agg_status debugfs file alignment The "RX active" string is too long, so the columns get shifted. Change it to just "RX" to avoid this. Signed-off-by: Johannes Berg --- net/mac80211/debugfs_sta.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/net/mac80211/debugfs_sta.c b/net/mac80211/debugfs_sta.c index 3db96648b45a..86173c0de40e 100644 --- a/net/mac80211/debugfs_sta.c +++ b/net/mac80211/debugfs_sta.c @@ -167,7 +167,7 @@ static ssize_t sta_agg_status_read(struct file *file, char __user *userbuf, p += scnprintf(p, sizeof(buf) + buf - p, "next dialog_token: %#02x\n", sta->ampdu_mlme.dialog_token_allocator + 1); p += scnprintf(p, sizeof(buf) + buf - p, - "TID\t\tRX active\tDTKN\tSSN\t\tTX\tDTKN\tpending\n"); + "TID\t\tRX\tDTKN\tSSN\t\tTX\tDTKN\tpending\n"); for (i = 0; i < IEEE80211_NUM_TIDS; i++) { tid_rx = rcu_dereference(sta->ampdu_mlme.tid_rx[i]); From ea1d5d7755a3e556de78cc757d1895d5c7180548 Mon Sep 17 00:00:00 2001 From: Julian Anastasov Date: Fri, 1 Aug 2014 10:36:17 +0300 Subject: [PATCH 044/101] ipvs: properly declare tunnel encapsulation The tunneling method should properly use tunnel encapsulation. Fixes problem with CHECKSUM_PARTIAL packets when TCP/UDP csum offload is supported. Thanks to Alex Gartrell for reporting the problem, providing solution and for all suggestions. Reported-by: Alex Gartrell Signed-off-by: Julian Anastasov Signed-off-by: Alex Gartrell Signed-off-by: Simon Horman --- net/netfilter/ipvs/ip_vs_xmit.c | 20 ++++++++++++++++---- 1 file changed, 16 insertions(+), 4 deletions(-) diff --git a/net/netfilter/ipvs/ip_vs_xmit.c b/net/netfilter/ipvs/ip_vs_xmit.c index 6f70bdd3a90a..56896a412bce 100644 --- a/net/netfilter/ipvs/ip_vs_xmit.c +++ b/net/netfilter/ipvs/ip_vs_xmit.c @@ -38,6 +38,7 @@ #include /* for ip_route_output */ #include #include +#include #include #include #include @@ -862,11 +863,15 @@ ip_vs_tunnel_xmit(struct sk_buff *skb, struct ip_vs_conn *cp, old_iph = ip_hdr(skb); } - skb->transport_header = skb->network_header; - /* fix old IP header checksum */ ip_send_check(old_iph); + skb = iptunnel_handle_offloads(skb, false, SKB_GSO_IPIP); + if (IS_ERR(skb)) + goto tx_error; + + skb->transport_header = skb->network_header; + skb_push(skb, sizeof(struct iphdr)); skb_reset_network_header(skb); memset(&(IPCB(skb)->opt), 0, sizeof(IPCB(skb)->opt)); @@ -900,7 +905,8 @@ ip_vs_tunnel_xmit(struct sk_buff *skb, struct ip_vs_conn *cp, return NF_STOLEN; tx_error: - kfree_skb(skb); + if (!IS_ERR(skb)) + kfree_skb(skb); rcu_read_unlock(); LeaveFunction(10); return NF_STOLEN; @@ -953,6 +959,11 @@ ip_vs_tunnel_xmit_v6(struct sk_buff *skb, struct ip_vs_conn *cp, old_iph = ipv6_hdr(skb); } + /* GSO: we need to provide proper SKB_GSO_ value for IPv6 */ + skb = iptunnel_handle_offloads(skb, false, 0); /* SKB_GSO_SIT/IPV6 */ + if (IS_ERR(skb)) + goto tx_error; + skb->transport_header = skb->network_header; skb_push(skb, sizeof(struct ipv6hdr)); @@ -988,7 +999,8 @@ ip_vs_tunnel_xmit_v6(struct sk_buff *skb, struct ip_vs_conn *cp, return NF_STOLEN; tx_error: - kfree_skb(skb); + if (!IS_ERR(skb)) + kfree_skb(skb); rcu_read_unlock(); LeaveFunction(10); return NF_STOLEN; From 7a4cecf74c165653b2d01301b301a8659438217e Mon Sep 17 00:00:00 2001 From: Giuseppe CAVALLARO Date: Tue, 26 Aug 2014 09:26:52 +0200 Subject: [PATCH 045/101] phy: fix EEE checks inside the phy_init_eee. According to the Std 802.3az if the EEE Adv (Reg 7.60), Link partner ability (Reg 7.61) and EEE capability (Register 3.20) bits return 0 this means no EEE is supported. So this patch fixes the checks inside the phy_init_eee function. Signed-off-by: Nandini Sharma Signed-off-by: Giuseppe Cavallaro Reviewed-by: Florian Fainelli Signed-off-by: David S. Miller --- drivers/net/phy/phy.c | 18 +++++++++--------- 1 file changed, 9 insertions(+), 9 deletions(-) diff --git a/drivers/net/phy/phy.c b/drivers/net/phy/phy.c index c94e2a27446a..a854d38c231d 100644 --- a/drivers/net/phy/phy.c +++ b/drivers/net/phy/phy.c @@ -1036,31 +1036,31 @@ int phy_init_eee(struct phy_device *phydev, bool clk_stop_enable) /* First check if the EEE ability is supported */ eee_cap = phy_read_mmd_indirect(phydev, MDIO_PCS_EEE_ABLE, MDIO_MMD_PCS, phydev->addr); - if (eee_cap < 0) - return eee_cap; + if (eee_cap <= 0) + goto eee_exit_err; cap = mmd_eee_cap_to_ethtool_sup_t(eee_cap); if (!cap) - return -EPROTONOSUPPORT; + goto eee_exit_err; /* Check which link settings negotiated and verify it in * the EEE advertising registers. */ eee_lp = phy_read_mmd_indirect(phydev, MDIO_AN_EEE_LPABLE, MDIO_MMD_AN, phydev->addr); - if (eee_lp < 0) - return eee_lp; + if (eee_lp <= 0) + goto eee_exit_err; eee_adv = phy_read_mmd_indirect(phydev, MDIO_AN_EEE_ADV, MDIO_MMD_AN, phydev->addr); - if (eee_adv < 0) - return eee_adv; + if (eee_adv <= 0) + goto eee_exit_err; adv = mmd_eee_adv_to_ethtool_adv_t(eee_adv); lp = mmd_eee_adv_to_ethtool_adv_t(eee_lp); idx = phy_find_setting(phydev->speed, phydev->duplex); if (!(lp & adv & settings[idx].setting)) - return -EPROTONOSUPPORT; + goto eee_exit_err; if (clk_stop_enable) { /* Configure the PHY to stop receiving xMII @@ -1080,7 +1080,7 @@ int phy_init_eee(struct phy_device *phydev, bool clk_stop_enable) return 0; /* EEE supported */ } - +eee_exit_err: return -EPROTONOSUPPORT; } EXPORT_SYMBOL(phy_init_eee); From eb90b0c734ad793d5f5bf230a9e9a4dcc48df8aa Mon Sep 17 00:00:00 2001 From: Julian Anastasov Date: Fri, 22 Aug 2014 17:53:41 +0300 Subject: [PATCH 046/101] ipvs: fix ipv6 hook registration for local replies commit fc604767613b6d2036cdc35b660bc39451040a47 ("ipvs: changes for local real server") from 2.6.37 introduced DNAT support to local real server but the IPv6 LOCAL_OUT handler ip_vs_local_reply6() is registered incorrectly as IPv4 hook causing any outgoing IPv4 traffic to be dropped depending on the IP header values. Chris tracked down the problem to CONFIG_IP_VS_IPV6=y Bug report: https://bugs.launchpad.net/ubuntu/+source/linux/+bug/1349768 Reported-by: Chris J Arges Tested-by: Chris J Arges Signed-off-by: Julian Anastasov Signed-off-by: Simon Horman --- net/netfilter/ipvs/ip_vs_core.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/net/netfilter/ipvs/ip_vs_core.c b/net/netfilter/ipvs/ip_vs_core.c index e6836755c45d..5c34e8d42e01 100644 --- a/net/netfilter/ipvs/ip_vs_core.c +++ b/net/netfilter/ipvs/ip_vs_core.c @@ -1906,7 +1906,7 @@ static struct nf_hook_ops ip_vs_ops[] __read_mostly = { { .hook = ip_vs_local_reply6, .owner = THIS_MODULE, - .pf = NFPROTO_IPV4, + .pf = NFPROTO_IPV6, .hooknum = NF_INET_LOCAL_OUT, .priority = NF_IP6_PRI_NAT_DST + 1, }, From b1dee4793fb8fec8e6b2efb68953b465a65c6b3e Mon Sep 17 00:00:00 2001 From: Giuseppe CAVALLARO Date: Wed, 27 Aug 2014 08:20:04 +0200 Subject: [PATCH 047/101] stmmac: prevent false carrier sense detection This patch is to w/a a problem that happens on some boxes when run at 10Mbps Half duplex mode. During the transmission the CSR signal is asserted for some time and the frames aborted because of carrier sense error. This is reported by MMC HW counter: txcarrier signal. This actually is a false carrier so the frames are good and there is no reason to ask for dropping them. This patch so disables the Carrier Sense During Transmission and this means that the MAC transmitter ignore the CRS signal during frame transmission in Half-Duplex mode. Signed-off-by: Giuseppe Cavallaro Acked-by: Vince Bridgers Acked-by: Ley Foon Tan Acked-by: Chen-Yu Tsai Signed-off-by: David S. Miller --- drivers/net/ethernet/stmicro/stmmac/dwmac1000.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac1000.h b/drivers/net/ethernet/stmicro/stmmac/dwmac1000.h index 71b5419256c1..64d8f56a9c17 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac1000.h +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac1000.h @@ -153,7 +153,7 @@ enum inter_frame_gap { #define GMAC_CONTROL_RE 0x00000004 /* Receiver Enable */ #define GMAC_CORE_INIT (GMAC_CONTROL_JD | GMAC_CONTROL_PS | GMAC_CONTROL_ACS | \ - GMAC_CONTROL_BE) + GMAC_CONTROL_BE | GMAC_CONTROL_DCRS) /* GMAC Frame Filter defines */ #define GMAC_FRAME_FILTER_PR 0x00000001 /* Promiscuous Mode */ From 2b78d348f1bc3396ca1662c6a6177a7fb1ca62ff Mon Sep 17 00:00:00 2001 From: Giuseppe CAVALLARO Date: Wed, 27 Aug 2014 08:26:13 +0200 Subject: [PATCH 048/101] stmmac: fix tipo on mmc crc error This patch is to fix a typo on mmc rx crc error when reported by ethtool. Signed-off-by: Giuseppe Cavallaro Signed-off-by: David S. Miller --- drivers/net/ethernet/stmicro/stmmac/mmc.h | 2 +- drivers/net/ethernet/stmicro/stmmac/mmc_core.c | 2 +- drivers/net/ethernet/stmicro/stmmac/stmmac_ethtool.c | 2 +- 3 files changed, 3 insertions(+), 3 deletions(-) diff --git a/drivers/net/ethernet/stmicro/stmmac/mmc.h b/drivers/net/ethernet/stmicro/stmmac/mmc.h index 8607488cbcfc..192c2491330b 100644 --- a/drivers/net/ethernet/stmicro/stmmac/mmc.h +++ b/drivers/net/ethernet/stmicro/stmmac/mmc.h @@ -68,7 +68,7 @@ struct stmmac_counters { unsigned int mmc_rx_octetcount_g; unsigned int mmc_rx_broadcastframe_g; unsigned int mmc_rx_multicastframe_g; - unsigned int mmc_rx_crc_errror; + unsigned int mmc_rx_crc_error; unsigned int mmc_rx_align_error; unsigned int mmc_rx_run_error; unsigned int mmc_rx_jabber_error; diff --git a/drivers/net/ethernet/stmicro/stmmac/mmc_core.c b/drivers/net/ethernet/stmicro/stmmac/mmc_core.c index 50617c5a0bdb..08c483bd2ec7 100644 --- a/drivers/net/ethernet/stmicro/stmmac/mmc_core.c +++ b/drivers/net/ethernet/stmicro/stmmac/mmc_core.c @@ -196,7 +196,7 @@ void dwmac_mmc_read(void __iomem *ioaddr, struct stmmac_counters *mmc) mmc->mmc_rx_octetcount_g += readl(ioaddr + MMC_RX_OCTETCOUNT_G); mmc->mmc_rx_broadcastframe_g += readl(ioaddr + MMC_RX_BROADCASTFRAME_G); mmc->mmc_rx_multicastframe_g += readl(ioaddr + MMC_RX_MULTICASTFRAME_G); - mmc->mmc_rx_crc_errror += readl(ioaddr + MMC_RX_CRC_ERRROR); + mmc->mmc_rx_crc_error += readl(ioaddr + MMC_RX_CRC_ERRROR); mmc->mmc_rx_align_error += readl(ioaddr + MMC_RX_ALIGN_ERROR); mmc->mmc_rx_run_error += readl(ioaddr + MMC_RX_RUN_ERROR); mmc->mmc_rx_jabber_error += readl(ioaddr + MMC_RX_JABBER_ERROR); diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_ethtool.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_ethtool.c index 9af50bae4dde..cf4f38db1c0a 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_ethtool.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_ethtool.c @@ -175,7 +175,7 @@ static const struct stmmac_stats stmmac_mmc[] = { STMMAC_MMC_STAT(mmc_rx_octetcount_g), STMMAC_MMC_STAT(mmc_rx_broadcastframe_g), STMMAC_MMC_STAT(mmc_rx_multicastframe_g), - STMMAC_MMC_STAT(mmc_rx_crc_errror), + STMMAC_MMC_STAT(mmc_rx_crc_error), STMMAC_MMC_STAT(mmc_rx_align_error), STMMAC_MMC_STAT(mmc_rx_run_error), STMMAC_MMC_STAT(mmc_rx_jabber_error), From 5566401f2f10556776fd199c11d6a02a5e0b7b95 Mon Sep 17 00:00:00 2001 From: Giuseppe CAVALLARO Date: Wed, 27 Aug 2014 10:37:49 +0200 Subject: [PATCH 049/101] stmmac: ptp: fix the reference clock The PTP reference clock, used for setting the addend in the Timestamp Addend Register, was erroneously hard-coded (as reported in the databook just as example). The patch removes the macro named: STMMAC_SYSCLOCK and allows to use a reference clock (clk_ptp_ref_i) that can be passed from the platform. If not passed, the main driver clock will be used as default; note that this can be fine on some platforms. Note that, prior this patch, using the old STMMAC_SYSCLOCK on some platforms, as side effect, the ptp clock can move faster/slower than the system clock. Signed-off-by: Giuseppe Cavallaro Signed-off-by: David S. Miller --- .../devicetree/bindings/net/stmmac.txt | 4 ++++ drivers/net/ethernet/stmicro/stmmac/stmmac.h | 2 ++ .../net/ethernet/stmicro/stmmac/stmmac_main.c | 20 +++++++++++++++---- .../net/ethernet/stmicro/stmmac/stmmac_ptp.h | 2 -- 4 files changed, 22 insertions(+), 6 deletions(-) diff --git a/Documentation/devicetree/bindings/net/stmmac.txt b/Documentation/devicetree/bindings/net/stmmac.txt index 9b03c57563a4..e45ac3f926b1 100644 --- a/Documentation/devicetree/bindings/net/stmmac.txt +++ b/Documentation/devicetree/bindings/net/stmmac.txt @@ -39,6 +39,10 @@ Optional properties: further clocks may be specified in derived bindings. - clock-names: One name for each entry in the clocks property, the first one should be "stmmaceth". +- clk_ptp_ref: this is the PTP reference clock; in case of the PTP is + available this clock is used for programming the Timestamp Addend Register. + If not passed then the system clock will be used and this is fine on some + platforms. Examples: diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac.h b/drivers/net/ethernet/stmicro/stmmac/stmmac.h index ca01035634a7..128a0b723a00 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac.h +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac.h @@ -105,6 +105,8 @@ struct stmmac_priv { struct ptp_clock *ptp_clock; struct ptp_clock_info ptp_clock_ops; unsigned int default_addend; + struct clk *clk_ptp_ref; + unsigned int clk_ptp_rate; u32 adv_ts; int use_riwt; int irq_wake; diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c index 51a89d4bb125..03652891fcbf 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c @@ -603,16 +603,16 @@ static int stmmac_hwtstamp_ioctl(struct net_device *dev, struct ifreq *ifr) /* calculate default added value: * formula is : * addend = (2^32)/freq_div_ratio; - * where, freq_div_ratio = STMMAC_SYSCLOCK/50MHz - * hence, addend = ((2^32) * 50MHz)/STMMAC_SYSCLOCK; - * NOTE: STMMAC_SYSCLOCK should be >= 50MHz to + * where, freq_div_ratio = clk_ptp_ref_i/50MHz + * hence, addend = ((2^32) * 50MHz)/clk_ptp_ref_i; + * NOTE: clk_ptp_ref_i should be >= 50MHz to * achive 20ns accuracy. * * 2^x * y == (y << x), hence * 2^32 * 50000000 ==> (50000000 << 32) */ temp = (u64) (50000000ULL << 32); - priv->default_addend = div_u64(temp, STMMAC_SYSCLOCK); + priv->default_addend = div_u64(temp, priv->clk_ptp_rate); priv->hw->ptp->config_addend(priv->ioaddr, priv->default_addend); @@ -638,6 +638,16 @@ static int stmmac_init_ptp(struct stmmac_priv *priv) if (!(priv->dma_cap.time_stamp || priv->dma_cap.atime_stamp)) return -EOPNOTSUPP; + /* Fall-back to main clock in case of no PTP ref is passed */ + priv->clk_ptp_ref = devm_clk_get(priv->device, "clk_ptp_ref"); + if (IS_ERR(priv->clk_ptp_ref)) { + priv->clk_ptp_rate = clk_get_rate(priv->stmmac_clk); + priv->clk_ptp_ref = NULL; + } else { + clk_prepare_enable(priv->clk_ptp_ref); + priv->clk_ptp_rate = clk_get_rate(priv->clk_ptp_ref); + } + priv->adv_ts = 0; if (priv->dma_cap.atime_stamp && priv->extend_desc) priv->adv_ts = 1; @@ -657,6 +667,8 @@ static int stmmac_init_ptp(struct stmmac_priv *priv) static void stmmac_release_ptp(struct stmmac_priv *priv) { + if (priv->clk_ptp_ref) + clk_disable_unprepare(priv->clk_ptp_ref); stmmac_ptp_unregister(priv); } diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_ptp.h b/drivers/net/ethernet/stmicro/stmmac/stmmac_ptp.h index 3dbc047622fa..4535df37c227 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_ptp.h +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_ptp.h @@ -25,8 +25,6 @@ #ifndef __STMMAC_PTP_H__ #define __STMMAC_PTP_H__ -#define STMMAC_SYSCLOCK 62500000 - /* IEEE 1588 PTP register offsets */ #define PTP_TCR 0x0700 /* Timestamp Control Reg */ #define PTP_SSIR 0x0704 /* Sub-Second Increment Reg */ From 362b37be01edc7429e3ebaa89613517d57863f5c Mon Sep 17 00:00:00 2001 From: Giuseppe CAVALLARO Date: Wed, 27 Aug 2014 11:27:00 +0200 Subject: [PATCH 050/101] stmmac: fix dma api misuse Enabling DMA_API_DEBUG, warnings are reported at runtime because the device driver frees DMA memory with wrong functions and it does not call dma_mapping_error after mapping dma memory. The first problem is fixed by of introducing a flag that helps us keeping track which mapping technique was used, so that we can use the right API for unmap. This approach was inspired by the e1000 driver, which uses a similar technique. Signed-off-by: Andre Draszik Signed-off-by: Giuseppe Cavallaro Reviewed-by: Denis Kirjanov Cc: Hans de Goede Signed-off-by: David S. Miller --- .../net/ethernet/stmicro/stmmac/chain_mode.c | 14 ++-- drivers/net/ethernet/stmicro/stmmac/common.h | 2 +- .../net/ethernet/stmicro/stmmac/ring_mode.c | 15 ++-- drivers/net/ethernet/stmicro/stmmac/stmmac.h | 7 +- .../net/ethernet/stmicro/stmmac/stmmac_main.c | 68 ++++++++++++++----- 5 files changed, 79 insertions(+), 27 deletions(-) diff --git a/drivers/net/ethernet/stmicro/stmmac/chain_mode.c b/drivers/net/ethernet/stmicro/stmmac/chain_mode.c index c553f6b5a913..cf28daba4346 100644 --- a/drivers/net/ethernet/stmicro/stmmac/chain_mode.c +++ b/drivers/net/ethernet/stmicro/stmmac/chain_mode.c @@ -28,7 +28,7 @@ #include "stmmac.h" -static unsigned int stmmac_jumbo_frm(void *p, struct sk_buff *skb, int csum) +static int stmmac_jumbo_frm(void *p, struct sk_buff *skb, int csum) { struct stmmac_priv *priv = (struct stmmac_priv *)p; unsigned int txsize = priv->dma_tx_size; @@ -47,7 +47,9 @@ static unsigned int stmmac_jumbo_frm(void *p, struct sk_buff *skb, int csum) desc->des2 = dma_map_single(priv->device, skb->data, bmax, DMA_TO_DEVICE); - priv->tx_skbuff_dma[entry] = desc->des2; + if (dma_mapping_error(priv->device, desc->des2)) + return -1; + priv->tx_skbuff_dma[entry].buf = desc->des2; priv->hw->desc->prepare_tx_desc(desc, 1, bmax, csum, STMMAC_CHAIN_MODE); while (len != 0) { @@ -59,7 +61,9 @@ static unsigned int stmmac_jumbo_frm(void *p, struct sk_buff *skb, int csum) desc->des2 = dma_map_single(priv->device, (skb->data + bmax * i), bmax, DMA_TO_DEVICE); - priv->tx_skbuff_dma[entry] = desc->des2; + if (dma_mapping_error(priv->device, desc->des2)) + return -1; + priv->tx_skbuff_dma[entry].buf = desc->des2; priv->hw->desc->prepare_tx_desc(desc, 0, bmax, csum, STMMAC_CHAIN_MODE); priv->hw->desc->set_tx_owner(desc); @@ -69,7 +73,9 @@ static unsigned int stmmac_jumbo_frm(void *p, struct sk_buff *skb, int csum) desc->des2 = dma_map_single(priv->device, (skb->data + bmax * i), len, DMA_TO_DEVICE); - priv->tx_skbuff_dma[entry] = desc->des2; + if (dma_mapping_error(priv->device, desc->des2)) + return -1; + priv->tx_skbuff_dma[entry].buf = desc->des2; priv->hw->desc->prepare_tx_desc(desc, 0, len, csum, STMMAC_CHAIN_MODE); priv->hw->desc->set_tx_owner(desc); diff --git a/drivers/net/ethernet/stmicro/stmmac/common.h b/drivers/net/ethernet/stmicro/stmmac/common.h index de507c32036c..bd54238e2df8 100644 --- a/drivers/net/ethernet/stmicro/stmmac/common.h +++ b/drivers/net/ethernet/stmicro/stmmac/common.h @@ -425,7 +425,7 @@ struct stmmac_mode_ops { void (*init) (void *des, dma_addr_t phy_addr, unsigned int size, unsigned int extend_desc); unsigned int (*is_jumbo_frm) (int len, int ehn_desc); - unsigned int (*jumbo_frm) (void *priv, struct sk_buff *skb, int csum); + int (*jumbo_frm)(void *priv, struct sk_buff *skb, int csum); int (*set_16kib_bfsize)(int mtu); void (*init_desc3)(struct dma_desc *p); void (*refill_desc3) (void *priv, struct dma_desc *p); diff --git a/drivers/net/ethernet/stmicro/stmmac/ring_mode.c b/drivers/net/ethernet/stmicro/stmmac/ring_mode.c index 650a4be6bce5..5dd50c6cda5b 100644 --- a/drivers/net/ethernet/stmicro/stmmac/ring_mode.c +++ b/drivers/net/ethernet/stmicro/stmmac/ring_mode.c @@ -28,7 +28,7 @@ #include "stmmac.h" -static unsigned int stmmac_jumbo_frm(void *p, struct sk_buff *skb, int csum) +static int stmmac_jumbo_frm(void *p, struct sk_buff *skb, int csum) { struct stmmac_priv *priv = (struct stmmac_priv *)p; unsigned int txsize = priv->dma_tx_size; @@ -53,7 +53,10 @@ static unsigned int stmmac_jumbo_frm(void *p, struct sk_buff *skb, int csum) desc->des2 = dma_map_single(priv->device, skb->data, bmax, DMA_TO_DEVICE); - priv->tx_skbuff_dma[entry] = desc->des2; + if (dma_mapping_error(priv->device, desc->des2)) + return -1; + + priv->tx_skbuff_dma[entry].buf = desc->des2; desc->des3 = desc->des2 + BUF_SIZE_4KiB; priv->hw->desc->prepare_tx_desc(desc, 1, bmax, csum, STMMAC_RING_MODE); @@ -68,7 +71,9 @@ static unsigned int stmmac_jumbo_frm(void *p, struct sk_buff *skb, int csum) desc->des2 = dma_map_single(priv->device, skb->data + bmax, len, DMA_TO_DEVICE); - priv->tx_skbuff_dma[entry] = desc->des2; + if (dma_mapping_error(priv->device, desc->des2)) + return -1; + priv->tx_skbuff_dma[entry].buf = desc->des2; desc->des3 = desc->des2 + BUF_SIZE_4KiB; priv->hw->desc->prepare_tx_desc(desc, 0, len, csum, STMMAC_RING_MODE); @@ -77,7 +82,9 @@ static unsigned int stmmac_jumbo_frm(void *p, struct sk_buff *skb, int csum) } else { desc->des2 = dma_map_single(priv->device, skb->data, nopaged_len, DMA_TO_DEVICE); - priv->tx_skbuff_dma[entry] = desc->des2; + if (dma_mapping_error(priv->device, desc->des2)) + return -1; + priv->tx_skbuff_dma[entry].buf = desc->des2; desc->des3 = desc->des2 + BUF_SIZE_4KiB; priv->hw->desc->prepare_tx_desc(desc, 1, nopaged_len, csum, STMMAC_RING_MODE); diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac.h b/drivers/net/ethernet/stmicro/stmmac/stmmac.h index 128a0b723a00..58097c0e2ad5 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac.h +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac.h @@ -34,6 +34,11 @@ #include #include +struct stmmac_tx_info { + dma_addr_t buf; + bool map_as_page; +}; + struct stmmac_priv { /* Frequently used values are kept adjacent for cache effect */ struct dma_extended_desc *dma_etx ____cacheline_aligned_in_smp; @@ -45,7 +50,7 @@ struct stmmac_priv { u32 tx_count_frames; u32 tx_coal_frames; u32 tx_coal_timer; - dma_addr_t *tx_skbuff_dma; + struct stmmac_tx_info *tx_skbuff_dma; dma_addr_t dma_tx_phy; int tx_coalesce; int hwts_tx_en; diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c index 03652891fcbf..df15f00b1246 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c @@ -1073,7 +1073,8 @@ static int init_dma_desc_rings(struct net_device *dev) else p = priv->dma_tx + i; p->des2 = 0; - priv->tx_skbuff_dma[i] = 0; + priv->tx_skbuff_dma[i].buf = 0; + priv->tx_skbuff_dma[i].map_as_page = false; priv->tx_skbuff[i] = NULL; } @@ -1112,17 +1113,24 @@ static void dma_free_tx_skbufs(struct stmmac_priv *priv) else p = priv->dma_tx + i; - if (priv->tx_skbuff_dma[i]) { - dma_unmap_single(priv->device, - priv->tx_skbuff_dma[i], - priv->hw->desc->get_tx_len(p), - DMA_TO_DEVICE); - priv->tx_skbuff_dma[i] = 0; + if (priv->tx_skbuff_dma[i].buf) { + if (priv->tx_skbuff_dma[i].map_as_page) + dma_unmap_page(priv->device, + priv->tx_skbuff_dma[i].buf, + priv->hw->desc->get_tx_len(p), + DMA_TO_DEVICE); + else + dma_unmap_single(priv->device, + priv->tx_skbuff_dma[i].buf, + priv->hw->desc->get_tx_len(p), + DMA_TO_DEVICE); } if (priv->tx_skbuff[i] != NULL) { dev_kfree_skb_any(priv->tx_skbuff[i]); priv->tx_skbuff[i] = NULL; + priv->tx_skbuff_dma[i].buf = 0; + priv->tx_skbuff_dma[i].map_as_page = false; } } } @@ -1143,7 +1151,8 @@ static int alloc_dma_desc_resources(struct stmmac_priv *priv) if (!priv->rx_skbuff) goto err_rx_skbuff; - priv->tx_skbuff_dma = kmalloc_array(txsize, sizeof(dma_addr_t), + priv->tx_skbuff_dma = kmalloc_array(txsize, + sizeof(*priv->tx_skbuff_dma), GFP_KERNEL); if (!priv->tx_skbuff_dma) goto err_tx_skbuff_dma; @@ -1305,12 +1314,19 @@ static void stmmac_tx_clean(struct stmmac_priv *priv) pr_debug("%s: curr %d, dirty %d\n", __func__, priv->cur_tx, priv->dirty_tx); - if (likely(priv->tx_skbuff_dma[entry])) { - dma_unmap_single(priv->device, - priv->tx_skbuff_dma[entry], - priv->hw->desc->get_tx_len(p), - DMA_TO_DEVICE); - priv->tx_skbuff_dma[entry] = 0; + if (likely(priv->tx_skbuff_dma[entry].buf)) { + if (priv->tx_skbuff_dma[entry].map_as_page) + dma_unmap_page(priv->device, + priv->tx_skbuff_dma[entry].buf, + priv->hw->desc->get_tx_len(p), + DMA_TO_DEVICE); + else + dma_unmap_single(priv->device, + priv->tx_skbuff_dma[entry].buf, + priv->hw->desc->get_tx_len(p), + DMA_TO_DEVICE); + priv->tx_skbuff_dma[entry].buf = 0; + priv->tx_skbuff_dma[entry].map_as_page = false; } priv->hw->mode->clean_desc3(priv, p); @@ -1905,12 +1921,16 @@ static netdev_tx_t stmmac_xmit(struct sk_buff *skb, struct net_device *dev) if (likely(!is_jumbo)) { desc->des2 = dma_map_single(priv->device, skb->data, nopaged_len, DMA_TO_DEVICE); - priv->tx_skbuff_dma[entry] = desc->des2; + if (dma_mapping_error(priv->device, desc->des2)) + goto dma_map_err; + priv->tx_skbuff_dma[entry].buf = desc->des2; priv->hw->desc->prepare_tx_desc(desc, 1, nopaged_len, csum_insertion, priv->mode); } else { desc = first; entry = priv->hw->mode->jumbo_frm(priv, skb, csum_insertion); + if (unlikely(entry < 0)) + goto dma_map_err; } for (i = 0; i < nfrags; i++) { @@ -1926,7 +1946,11 @@ static netdev_tx_t stmmac_xmit(struct sk_buff *skb, struct net_device *dev) desc->des2 = skb_frag_dma_map(priv->device, frag, 0, len, DMA_TO_DEVICE); - priv->tx_skbuff_dma[entry] = desc->des2; + if (dma_mapping_error(priv->device, desc->des2)) + goto dma_map_err; /* should reuse desc w/o issues */ + + priv->tx_skbuff_dma[entry].buf = desc->des2; + priv->tx_skbuff_dma[entry].map_as_page = true; priv->hw->desc->prepare_tx_desc(desc, 0, len, csum_insertion, priv->mode); wmb(); @@ -1993,7 +2017,12 @@ static netdev_tx_t stmmac_xmit(struct sk_buff *skb, struct net_device *dev) priv->hw->dma->enable_dma_transmission(priv->ioaddr); spin_unlock(&priv->tx_lock); + return NETDEV_TX_OK; +dma_map_err: + dev_err(priv->device, "Tx dma map failed\n"); + dev_kfree_skb(skb); + priv->dev->stats.tx_dropped++; return NETDEV_TX_OK; } @@ -2046,7 +2075,12 @@ static inline void stmmac_rx_refill(struct stmmac_priv *priv) priv->rx_skbuff_dma[entry] = dma_map_single(priv->device, skb->data, bfsize, DMA_FROM_DEVICE); - + if (dma_mapping_error(priv->device, + priv->rx_skbuff_dma[entry])) { + dev_err(priv->device, "Rx dma map failed\n"); + dev_kfree_skb(skb); + break; + } p->des2 = priv->rx_skbuff_dma[entry]; priv->hw->mode->refill_desc3(priv, p); From b95089d00c04712a9d4655d5c638930ac24b7bd3 Mon Sep 17 00:00:00 2001 From: Or Gerlitz Date: Wed, 27 Aug 2014 16:47:48 +0300 Subject: [PATCH 051/101] net/mlx4: Move the tunnel steering helper function to mlx4_core Move the function which we use to set VXLAN DMFS (flow-steering) rules from mlx4_en to mlx4_core. This refactoring will allow the mlx4_ib driver to call the helper for the use case of user-space RAW Ethernet QPs, such that they can serve VXLAN traffic too. Signed-off-by: Or Gerlitz Signed-off-by: David S. Miller --- .../net/ethernet/mellanox/mlx4/en_netdev.c | 31 +-------------- drivers/net/ethernet/mellanox/mlx4/mcg.c | 38 +++++++++++++++++++ include/linux/mlx4/device.h | 3 ++ 3 files changed, 43 insertions(+), 29 deletions(-) diff --git a/drivers/net/ethernet/mellanox/mlx4/en_netdev.c b/drivers/net/ethernet/mellanox/mlx4/en_netdev.c index bb536aa613f4..abddcf8c40aa 100644 --- a/drivers/net/ethernet/mellanox/mlx4/en_netdev.c +++ b/drivers/net/ethernet/mellanox/mlx4/en_netdev.c @@ -474,39 +474,12 @@ static int mlx4_en_tunnel_steer_add(struct mlx4_en_priv *priv, unsigned char *ad int qpn, u64 *reg_id) { int err; - struct mlx4_spec_list spec_eth_outer = { {NULL} }; - struct mlx4_spec_list spec_vxlan = { {NULL} }; - struct mlx4_spec_list spec_eth_inner = { {NULL} }; - - struct mlx4_net_trans_rule rule = { - .queue_mode = MLX4_NET_TRANS_Q_FIFO, - .exclusive = 0, - .allow_loopback = 1, - .promisc_mode = MLX4_FS_REGULAR, - .priority = MLX4_DOMAIN_NIC, - }; - - __be64 mac_mask = cpu_to_be64(MLX4_MAC_MASK << 16); if (priv->mdev->dev->caps.tunnel_offload_mode != MLX4_TUNNEL_OFFLOAD_MODE_VXLAN) return 0; /* do nothing */ - rule.port = priv->port; - rule.qpn = qpn; - INIT_LIST_HEAD(&rule.list); - - spec_eth_outer.id = MLX4_NET_TRANS_RULE_ID_ETH; - memcpy(spec_eth_outer.eth.dst_mac, addr, ETH_ALEN); - memcpy(spec_eth_outer.eth.dst_mac_msk, &mac_mask, ETH_ALEN); - - spec_vxlan.id = MLX4_NET_TRANS_RULE_ID_VXLAN; /* any vxlan header */ - spec_eth_inner.id = MLX4_NET_TRANS_RULE_ID_ETH; /* any inner eth header */ - - list_add_tail(&spec_eth_outer.list, &rule.list); - list_add_tail(&spec_vxlan.list, &rule.list); - list_add_tail(&spec_eth_inner.list, &rule.list); - - err = mlx4_flow_attach(priv->mdev->dev, &rule, reg_id); + err = mlx4_tunnel_steer_add(priv->mdev->dev, addr, priv->port, qpn, + MLX4_DOMAIN_NIC, reg_id); if (err) { en_err(priv, "failed to add vxlan steering rule, err %d\n", err); return err; diff --git a/drivers/net/ethernet/mellanox/mlx4/mcg.c b/drivers/net/ethernet/mellanox/mlx4/mcg.c index d80e7a6fac74..ca0f98c95105 100644 --- a/drivers/net/ethernet/mellanox/mlx4/mcg.c +++ b/drivers/net/ethernet/mellanox/mlx4/mcg.c @@ -1020,6 +1020,44 @@ int mlx4_flow_detach(struct mlx4_dev *dev, u64 reg_id) } EXPORT_SYMBOL_GPL(mlx4_flow_detach); +int mlx4_tunnel_steer_add(struct mlx4_dev *dev, unsigned char *addr, + int port, int qpn, u16 prio, u64 *reg_id) +{ + int err; + struct mlx4_spec_list spec_eth_outer = { {NULL} }; + struct mlx4_spec_list spec_vxlan = { {NULL} }; + struct mlx4_spec_list spec_eth_inner = { {NULL} }; + + struct mlx4_net_trans_rule rule = { + .queue_mode = MLX4_NET_TRANS_Q_FIFO, + .exclusive = 0, + .allow_loopback = 1, + .promisc_mode = MLX4_FS_REGULAR, + }; + + __be64 mac_mask = cpu_to_be64(MLX4_MAC_MASK << 16); + + rule.port = port; + rule.qpn = qpn; + rule.priority = prio; + INIT_LIST_HEAD(&rule.list); + + spec_eth_outer.id = MLX4_NET_TRANS_RULE_ID_ETH; + memcpy(spec_eth_outer.eth.dst_mac, addr, ETH_ALEN); + memcpy(spec_eth_outer.eth.dst_mac_msk, &mac_mask, ETH_ALEN); + + spec_vxlan.id = MLX4_NET_TRANS_RULE_ID_VXLAN; /* any vxlan header */ + spec_eth_inner.id = MLX4_NET_TRANS_RULE_ID_ETH; /* any inner eth header */ + + list_add_tail(&spec_eth_outer.list, &rule.list); + list_add_tail(&spec_vxlan.list, &rule.list); + list_add_tail(&spec_eth_inner.list, &rule.list); + + err = mlx4_flow_attach(dev, &rule, reg_id); + return err; +} +EXPORT_SYMBOL(mlx4_tunnel_steer_add); + int mlx4_FLOW_STEERING_IB_UC_QP_RANGE(struct mlx4_dev *dev, u32 min_range_qpn, u32 max_range_qpn) { diff --git a/include/linux/mlx4/device.h b/include/linux/mlx4/device.h index 071f6b234604..511c6e0d21a9 100644 --- a/include/linux/mlx4/device.h +++ b/include/linux/mlx4/device.h @@ -1196,6 +1196,9 @@ int mlx4_map_sw_to_hw_steering_id(struct mlx4_dev *dev, enum mlx4_net_trans_rule_id id); int mlx4_hw_rule_sz(struct mlx4_dev *dev, enum mlx4_net_trans_rule_id id); +int mlx4_tunnel_steer_add(struct mlx4_dev *dev, unsigned char *addr, + int port, int qpn, u16 prio, u64 *reg_id); + void mlx4_sync_pkey_table(struct mlx4_dev *dev, int slave, int port, int i, int val); From d2fce8a9060db3af7e1b25e259b251da17f6a0d6 Mon Sep 17 00:00:00 2001 From: Or Gerlitz Date: Wed, 27 Aug 2014 16:47:49 +0300 Subject: [PATCH 052/101] mlx4: Set user-space raw Ethernet QPs to properly handle VXLAN traffic Raw Ethernet QPs opened from user-space lack the proper setup to recieve/handle VXLAN traffic when VXLAN offloads are enabled. Fix that by adding a tunnel steering rule on top of the normal unicast steering rule and set the tunnel_type field in the QP context. Signed-off-by: Or Gerlitz Signed-off-by: David S. Miller --- drivers/infiniband/hw/mlx4/main.c | 30 ++++++++++++++++++++++++++++++ drivers/infiniband/hw/mlx4/qp.c | 8 +++++++- 2 files changed, 37 insertions(+), 1 deletion(-) diff --git a/drivers/infiniband/hw/mlx4/main.c b/drivers/infiniband/hw/mlx4/main.c index e1e558a3d692..af8256353c7d 100644 --- a/drivers/infiniband/hw/mlx4/main.c +++ b/drivers/infiniband/hw/mlx4/main.c @@ -1089,6 +1089,30 @@ static int __mlx4_ib_destroy_flow(struct mlx4_dev *dev, u64 reg_id) return err; } +static int mlx4_ib_tunnel_steer_add(struct ib_qp *qp, struct ib_flow_attr *flow_attr, + u64 *reg_id) +{ + void *ib_flow; + union ib_flow_spec *ib_spec; + struct mlx4_dev *dev = to_mdev(qp->device)->dev; + int err = 0; + + if (dev->caps.tunnel_offload_mode != MLX4_TUNNEL_OFFLOAD_MODE_VXLAN) + return 0; /* do nothing */ + + ib_flow = flow_attr + 1; + ib_spec = (union ib_flow_spec *)ib_flow; + + if (ib_spec->type != IB_FLOW_SPEC_ETH || flow_attr->num_of_specs != 1) + return 0; /* do nothing */ + + err = mlx4_tunnel_steer_add(to_mdev(qp->device)->dev, ib_spec->eth.val.dst_mac, + flow_attr->port, qp->qp_num, + MLX4_DOMAIN_UVERBS | (flow_attr->priority & 0xff), + reg_id); + return err; +} + static struct ib_flow *mlx4_ib_create_flow(struct ib_qp *qp, struct ib_flow_attr *flow_attr, int domain) @@ -1136,6 +1160,12 @@ static struct ib_flow *mlx4_ib_create_flow(struct ib_qp *qp, i++; } + if (i < ARRAY_SIZE(type) && flow_attr->type == IB_FLOW_ATTR_NORMAL) { + err = mlx4_ib_tunnel_steer_add(qp, flow_attr, &mflow->reg_id[i]); + if (err) + goto err_free; + } + return &mflow->ibflow; err_free: diff --git a/drivers/infiniband/hw/mlx4/qp.c b/drivers/infiniband/hw/mlx4/qp.c index 67780452f0cf..efb9eff8906c 100644 --- a/drivers/infiniband/hw/mlx4/qp.c +++ b/drivers/infiniband/hw/mlx4/qp.c @@ -1677,9 +1677,15 @@ static int __mlx4_ib_modify_qp(struct ib_qp *ibqp, } } - if (qp->ibqp.qp_type == IB_QPT_RAW_PACKET) + if (qp->ibqp.qp_type == IB_QPT_RAW_PACKET) { context->pri_path.ackto = (context->pri_path.ackto & 0xf8) | MLX4_IB_LINK_TYPE_ETH; + if (dev->dev->caps.tunnel_offload_mode == MLX4_TUNNEL_OFFLOAD_MODE_VXLAN) { + /* set QP to receive both tunneled & non-tunneled packets */ + if (!(context->flags & (1 << MLX4_RSS_QPC_FLAG_OFFSET))) + context->srqn = cpu_to_be32(7 << 28); + } + } if (ibqp->qp_type == IB_QPT_UD && (new_state == IB_QPS_RTR)) { int is_eth = rdma_port_get_link_layer( From d9b2938aabf757da2d40153489b251d4fc3fdd18 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Wed, 27 Aug 2014 20:49:34 -0700 Subject: [PATCH 053/101] net: attempt a single high order allocation In commit ed98df3361f0 ("net: use __GFP_NORETRY for high order allocations") we tried to address one issue caused by order-3 allocations. We still observe high latencies and system overhead in situations where compaction is not successful. Instead of trying order-3, order-2, and order-1, do a single order-3 best effort and immediately fallback to plain order-0. This mimics slub strategy to fallback to slab min order if the high order allocation used for performance failed. Order-3 allocations give a performance boost only if they can be done without recurring and expensive memory scan. Quoting David : The page allocator relies on synchronous (sync light) memory compaction after direct reclaim for allocations that don't retry and deferred compaction doesn't work with this strategy because the allocation order is always decreasing from the previous failed attempt. This means sync light compaction will always be encountered if memory cannot be defragmented or reclaimed several times during the skb_page_frag_refill() iteration. Signed-off-by: Eric Dumazet Acked-by: David Rientjes Signed-off-by: David S. Miller --- net/core/sock.c | 30 ++++++++++++++++-------------- 1 file changed, 16 insertions(+), 14 deletions(-) diff --git a/net/core/sock.c b/net/core/sock.c index 2714811afbd8..29870571c42f 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -1822,6 +1822,9 @@ struct sk_buff *sock_alloc_send_pskb(struct sock *sk, unsigned long header_len, order); if (page) goto fill_page; + /* Do not retry other high order allocations */ + order = 1; + max_page_order = 0; } order--; } @@ -1869,10 +1872,8 @@ EXPORT_SYMBOL(sock_alloc_send_skb); * no guarantee that allocations succeed. Therefore, @sz MUST be * less or equal than PAGE_SIZE. */ -bool skb_page_frag_refill(unsigned int sz, struct page_frag *pfrag, gfp_t prio) +bool skb_page_frag_refill(unsigned int sz, struct page_frag *pfrag, gfp_t gfp) { - int order; - if (pfrag->page) { if (atomic_read(&pfrag->page->_count) == 1) { pfrag->offset = 0; @@ -1883,20 +1884,21 @@ bool skb_page_frag_refill(unsigned int sz, struct page_frag *pfrag, gfp_t prio) put_page(pfrag->page); } - order = SKB_FRAG_PAGE_ORDER; - do { - gfp_t gfp = prio; - - if (order) - gfp |= __GFP_COMP | __GFP_NOWARN | __GFP_NORETRY; - pfrag->page = alloc_pages(gfp, order); + pfrag->offset = 0; + if (SKB_FRAG_PAGE_ORDER) { + pfrag->page = alloc_pages(gfp | __GFP_COMP | + __GFP_NOWARN | __GFP_NORETRY, + SKB_FRAG_PAGE_ORDER); if (likely(pfrag->page)) { - pfrag->offset = 0; - pfrag->size = PAGE_SIZE << order; + pfrag->size = PAGE_SIZE << SKB_FRAG_PAGE_ORDER; return true; } - } while (--order >= 0); - + } + pfrag->page = alloc_page(gfp); + if (likely(pfrag->page)) { + pfrag->size = PAGE_SIZE; + return true; + } return false; } EXPORT_SYMBOL(skb_page_frag_refill); From 38ab1fa981d543e1b00f4ffbce4ddb480cd2effe Mon Sep 17 00:00:00 2001 From: Daniel Borkmann Date: Thu, 28 Aug 2014 15:28:26 +0200 Subject: [PATCH 054/101] net: sctp: fix ABI mismatch through sctp_assoc_to_state helper Since SCTP day 1, that is, 19b55a2af145 ("Initial commit") from lksctp tree, the official header carries a copy of enum sctp_sstat_state that looks like (compared to the current in-kernel enumeration): User definition: Kernel definition: enum sctp_sstat_state { typedef enum { SCTP_EMPTY = 0, SCTP_CLOSED = 1, SCTP_STATE_CLOSED = 0, SCTP_COOKIE_WAIT = 2, SCTP_STATE_COOKIE_WAIT = 1, SCTP_COOKIE_ECHOED = 3, SCTP_STATE_COOKIE_ECHOED = 2, SCTP_ESTABLISHED = 4, SCTP_STATE_ESTABLISHED = 3, SCTP_SHUTDOWN_PENDING = 5, SCTP_STATE_SHUTDOWN_PENDING = 4, SCTP_SHUTDOWN_SENT = 6, SCTP_STATE_SHUTDOWN_SENT = 5, SCTP_SHUTDOWN_RECEIVED = 7, SCTP_STATE_SHUTDOWN_RECEIVED = 6, SCTP_SHUTDOWN_ACK_SENT = 8, SCTP_STATE_SHUTDOWN_ACK_SENT = 7, }; } sctp_state_t; This header was later on also placed into the uapi, so that user space programs can compile without having , but the shipped with instead. While RFC6458 under 8.2.1.Association Status (SCTP_STATUS) says that sstat_state can range from SCTP_CLOSED to SCTP_SHUTDOWN_ACK_SENT, we nevertheless have a what it appears to be dummy SCTP_EMPTY state from the very early days. While it seems to do just nothing, commit 0b8f9e25b0aa ("sctp: remove completely unsed EMPTY state") did the right thing and removed this dead code. That however, causes an off-by-one when the user asks the SCTP stack via SCTP_STATUS API and checks for the current socket state thus yielding possibly undefined behaviour in applications as they expect the kernel to tell the right thing. The enumeration had to be changed however as based on the current socket state, we access a function pointer lookup-table through this. Therefore, I think the best way to deal with this is just to add a helper function sctp_assoc_to_state() to encapsulate the off-by-one quirk. Reported-by: Tristan Su Fixes: 0b8f9e25b0aa ("sctp: remove completely unsed EMPTY state") Signed-off-by: Daniel Borkmann Acked-by: Vlad Yasevich Signed-off-by: David S. Miller --- include/net/sctp/sctp.h | 13 +++++++++++++ net/sctp/socket.c | 2 +- 2 files changed, 14 insertions(+), 1 deletion(-) diff --git a/include/net/sctp/sctp.h b/include/net/sctp/sctp.h index f6e7397e799d..9fbd856e6713 100644 --- a/include/net/sctp/sctp.h +++ b/include/net/sctp/sctp.h @@ -320,6 +320,19 @@ static inline sctp_assoc_t sctp_assoc2id(const struct sctp_association *asoc) return asoc ? asoc->assoc_id : 0; } +static inline enum sctp_sstat_state +sctp_assoc_to_state(const struct sctp_association *asoc) +{ + /* SCTP's uapi always had SCTP_EMPTY(=0) as a dummy state, but we + * got rid of it in kernel space. Therefore SCTP_CLOSED et al + * start at =1 in user space, but actually as =0 in kernel space. + * Now that we can not break user space and SCTP_EMPTY is exposed + * there, we need to fix it up with an ugly offset not to break + * applications. :( + */ + return asoc->state + 1; +} + /* Look up the association by its id. */ struct sctp_association *sctp_id2assoc(struct sock *sk, sctp_assoc_t id); diff --git a/net/sctp/socket.c b/net/sctp/socket.c index eb71d49e7653..634a2abb5f3a 100644 --- a/net/sctp/socket.c +++ b/net/sctp/socket.c @@ -4243,7 +4243,7 @@ static int sctp_getsockopt_sctp_status(struct sock *sk, int len, transport = asoc->peer.primary_path; status.sstat_assoc_id = sctp_assoc2id(asoc); - status.sstat_state = asoc->state; + status.sstat_state = sctp_assoc_to_state(asoc); status.sstat_rwnd = asoc->peer.rwnd; status.sstat_unackdata = asoc->unack_data; From f47f46d7b09cf1d09e4b44b6cc4dd7d68a08028c Mon Sep 17 00:00:00 2001 From: Emmanuel Grumbach Date: Sun, 31 Aug 2014 22:11:11 +0300 Subject: [PATCH 055/101] Revert "iwlwifi: dvm: don't enable CTS to self" This reverts commit 43d826ca5979927131685cc2092c7ce862cb91cd. This commit caused packet loss. Cc: Signed-off-by: Emmanuel Grumbach --- drivers/net/wireless/iwlwifi/dvm/rxon.c | 12 ++++++++++++ 1 file changed, 12 insertions(+) diff --git a/drivers/net/wireless/iwlwifi/dvm/rxon.c b/drivers/net/wireless/iwlwifi/dvm/rxon.c index 6dc5dd3ced44..ed50de6362ed 100644 --- a/drivers/net/wireless/iwlwifi/dvm/rxon.c +++ b/drivers/net/wireless/iwlwifi/dvm/rxon.c @@ -1068,6 +1068,13 @@ int iwlagn_commit_rxon(struct iwl_priv *priv, struct iwl_rxon_context *ctx) /* recalculate basic rates */ iwl_calc_basic_rates(priv, ctx); + /* + * force CTS-to-self frames protection if RTS-CTS is not preferred + * one aggregation protection method + */ + if (!priv->hw_params.use_rts_for_aggregation) + ctx->staging.flags |= RXON_FLG_SELF_CTS_EN; + if ((ctx->vif && ctx->vif->bss_conf.use_short_slot) || !(ctx->staging.flags & RXON_FLG_BAND_24G_MSK)) ctx->staging.flags |= RXON_FLG_SHORT_SLOT_MSK; @@ -1473,6 +1480,11 @@ void iwlagn_bss_info_changed(struct ieee80211_hw *hw, else ctx->staging.flags &= ~RXON_FLG_TGG_PROTECT_MSK; + if (bss_conf->use_cts_prot) + ctx->staging.flags |= RXON_FLG_SELF_CTS_EN; + else + ctx->staging.flags &= ~RXON_FLG_SELF_CTS_EN; + memcpy(ctx->staging.bssid_addr, bss_conf->bssid, ETH_ALEN); if (vif->type == NL80211_IFTYPE_AP || From ab1304b986468e3ef698ec4e1cb1a3d4ba080811 Mon Sep 17 00:00:00 2001 From: Marcel Holtmann Date: Mon, 11 Aug 2014 22:11:35 +0200 Subject: [PATCH 056/101] iwlwifi: Remove module build requirement for Intel Wireless WiFi The CONFIG_IWLDVM and CONFIG_IWLMVM currently have a "depends on m" as its requirement forcing it to be build as module. This is not needed and thus just remove it. Fixes: ae7486a2b734 ("iwlwifi: fix Kconfig issues") Signed-off-by: Marcel Holtmann [Squashed 2 commites for MVM and DVM] Signed-off-by: Emmanuel Grumbach --- drivers/net/wireless/iwlwifi/Kconfig | 2 -- 1 file changed, 2 deletions(-) diff --git a/drivers/net/wireless/iwlwifi/Kconfig b/drivers/net/wireless/iwlwifi/Kconfig index 6451d2b6abcf..824f5e287783 100644 --- a/drivers/net/wireless/iwlwifi/Kconfig +++ b/drivers/net/wireless/iwlwifi/Kconfig @@ -51,7 +51,6 @@ config IWLWIFI_LEDS config IWLDVM tristate "Intel Wireless WiFi DVM Firmware support" - depends on m default IWLWIFI help This is the driver that supports the DVM firmware which is @@ -60,7 +59,6 @@ config IWLDVM config IWLMVM tristate "Intel Wireless WiFi MVM Firmware support" - depends on m help This is the driver that supports the MVM firmware which is currently only available for 7260 and 3160 devices. From 162fb1d6559c4dcb454f172248d6d8ffa7a30bf8 Mon Sep 17 00:00:00 2001 From: nandini sharma Date: Thu, 28 Aug 2014 08:11:41 +0200 Subject: [PATCH 057/101] stmmac: fix the EEE LPI Macro definitions. This patch is to fix the definition of macros for EEE otherwise the LPI TX/RX entry/exit cannot be properly managed. Signed-off-by: Nandini Sharma Signed-off-by: Giuseppe Cavallaro Signed-off-by: David S. Miller --- drivers/net/ethernet/stmicro/stmmac/common.h | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/drivers/net/ethernet/stmicro/stmmac/common.h b/drivers/net/ethernet/stmicro/stmmac/common.h index bd54238e2df8..11702d8d2ddb 100644 --- a/drivers/net/ethernet/stmicro/stmmac/common.h +++ b/drivers/net/ethernet/stmicro/stmmac/common.h @@ -220,10 +220,10 @@ enum dma_irq_status { handle_tx = 0x8, }; -#define CORE_IRQ_TX_PATH_IN_LPI_MODE (1 << 1) -#define CORE_IRQ_TX_PATH_EXIT_LPI_MODE (1 << 2) -#define CORE_IRQ_RX_PATH_IN_LPI_MODE (1 << 3) -#define CORE_IRQ_RX_PATH_EXIT_LPI_MODE (1 << 4) +#define CORE_IRQ_TX_PATH_IN_LPI_MODE (1 << 0) +#define CORE_IRQ_TX_PATH_EXIT_LPI_MODE (1 << 1) +#define CORE_IRQ_RX_PATH_IN_LPI_MODE (1 << 2) +#define CORE_IRQ_RX_PATH_EXIT_LPI_MODE (1 << 3) #define CORE_PCS_ANE_COMPLETE (1 << 5) #define CORE_PCS_LINK_STATUS (1 << 6) From 438a62b16e0aeff5c4a5ab457343cebe4d7278da Mon Sep 17 00:00:00 2001 From: nandini sharma Date: Thu, 28 Aug 2014 08:11:42 +0200 Subject: [PATCH 058/101] stmmac: fix LPI TW timer value to 20.5us. The value for LPI TW timer has to be updated to 0x1E that is the hardcoded value of 20.5us and it will apply to all EEE enabled Remote PHYs. Disadvantage is for PHY's that support lesser wakeup time but we can accept it waiting to implement LLDP to negotiate the Wakeup time of Remote PHY. Signed-off-by: nandini sharma Signed-off-by: Giuseppe Cavallaro Signed-off-by: David S. Miller --- drivers/net/ethernet/stmicro/stmmac/common.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/net/ethernet/stmicro/stmmac/common.h b/drivers/net/ethernet/stmicro/stmmac/common.h index 11702d8d2ddb..e3b81cdc94b2 100644 --- a/drivers/net/ethernet/stmicro/stmmac/common.h +++ b/drivers/net/ethernet/stmicro/stmmac/common.h @@ -287,7 +287,7 @@ struct dma_features { /* Default LPI timers */ #define STMMAC_DEFAULT_LIT_LS 0x3E8 -#define STMMAC_DEFAULT_TWT_LS 0x0 +#define STMMAC_DEFAULT_TWT_LS 0x1E #define STMMAC_CHAIN_MODE 0x1 #define STMMAC_RING_MODE 0x2 From 56b88c25c543f1d4b1fff7f1c0267f59f53c261f Mon Sep 17 00:00:00 2001 From: Giuseppe CAVALLARO Date: Thu, 28 Aug 2014 08:11:43 +0200 Subject: [PATCH 059/101] stmmac: never check EEE in case of a switch is attached This patch is to skip the EEE initialisation when the stmmac is using a switch (with a fixed phy support). Signed-off-by: Giuseppe Cavallaro Signed-off-by: David S. Miller --- drivers/net/ethernet/stmicro/stmmac/stmmac_main.c | 5 +++++ 1 file changed, 5 insertions(+) diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c index df15f00b1246..3b8b57e3bd20 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c @@ -275,6 +275,7 @@ static void stmmac_eee_ctrl_timer(unsigned long arg) */ bool stmmac_eee_init(struct stmmac_priv *priv) { + char *phy_bus_name = priv->plat->phy_bus_name; bool ret = false; /* Using PCS we cannot dial with the phy registers at this stage @@ -284,6 +285,10 @@ bool stmmac_eee_init(struct stmmac_priv *priv) (priv->pcs == STMMAC_PCS_RTBI)) goto out; + /* Never init EEE in case of a switch is attached */ + if (phy_bus_name && (!strcmp(phy_bus_name, "fixed"))) + goto out; + /* MAC core supports the EEE feature. */ if (priv->dma_cap.eee) { int tx_lpi_timer = priv->tx_lpi_timer; From 71965352eedd0cc524de36accc6da7d5166a2c62 Mon Sep 17 00:00:00 2001 From: Giuseppe CAVALLARO Date: Thu, 28 Aug 2014 08:11:44 +0200 Subject: [PATCH 060/101] stmmac: fix PLS bit setting when EEE is active In case of PLS is active the PLS (PHY Link Status) bit in the Reg12 has to be set to allow the MAC to asserts the LPI pattern when the link is ok. Signed-off-by: nandini sharma Signed-off-by: Giuseppe Cavallaro Signed-off-by: David S. Miller --- drivers/net/ethernet/stmicro/stmmac/stmmac_main.c | 7 +++---- 1 file changed, 3 insertions(+), 4 deletions(-) diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c index 3b8b57e3bd20..3d3db16c97d4 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c @@ -321,10 +321,9 @@ bool stmmac_eee_init(struct stmmac_priv *priv) priv->hw->mac->set_eee_timer(priv->hw, STMMAC_DEFAULT_LIT_LS, tx_lpi_timer); - } else - /* Set HW EEE according to the speed */ - priv->hw->mac->set_eee_pls(priv->hw, - priv->phydev->link); + } + /* Set HW EEE according to the speed */ + priv->hw->mac->set_eee_pls(priv->hw, priv->phydev->link); pr_debug("stmmac: Energy-Efficient Ethernet initialized\n"); From d88c8958dc13b4e4eb7fc57e3f06dc1c4abc7b1f Mon Sep 17 00:00:00 2001 From: Emmanuel Grumbach Date: Mon, 1 Sep 2014 09:50:14 +0300 Subject: [PATCH 061/101] iwlwifi: bump firmware API version to 10 for 7000 and 8000 New firmware on the way. Signed-off-by: Emmanuel Grumbach --- drivers/net/wireless/iwlwifi/iwl-7000.c | 4 ++-- drivers/net/wireless/iwlwifi/iwl-8000.c | 2 +- 2 files changed, 3 insertions(+), 3 deletions(-) diff --git a/drivers/net/wireless/iwlwifi/iwl-7000.c b/drivers/net/wireless/iwlwifi/iwl-7000.c index 48730064da73..d67a37a786aa 100644 --- a/drivers/net/wireless/iwlwifi/iwl-7000.c +++ b/drivers/net/wireless/iwlwifi/iwl-7000.c @@ -67,8 +67,8 @@ #include "iwl-agn-hw.h" /* Highest firmware API version supported */ -#define IWL7260_UCODE_API_MAX 9 -#define IWL3160_UCODE_API_MAX 9 +#define IWL7260_UCODE_API_MAX 10 +#define IWL3160_UCODE_API_MAX 10 /* Oldest version we won't warn about */ #define IWL7260_UCODE_API_OK 9 diff --git a/drivers/net/wireless/iwlwifi/iwl-8000.c b/drivers/net/wireless/iwlwifi/iwl-8000.c index 44b19e015102..e93c6972290b 100644 --- a/drivers/net/wireless/iwlwifi/iwl-8000.c +++ b/drivers/net/wireless/iwlwifi/iwl-8000.c @@ -67,7 +67,7 @@ #include "iwl-agn-hw.h" /* Highest firmware API version supported */ -#define IWL8000_UCODE_API_MAX 9 +#define IWL8000_UCODE_API_MAX 10 /* Oldest version we won't warn about */ #define IWL8000_UCODE_API_OK 8 From d79a61d646db950b68dd79ecc627cb5f11e0d8ac Mon Sep 17 00:00:00 2001 From: Pablo Neira Ayuso Date: Fri, 29 Aug 2014 09:34:49 +0200 Subject: [PATCH 062/101] netfilter: NETFILTER_XT_TARGET_LOG selects NF_LOG_* MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit CONFIG_NETFILTER_XT_TARGET_LOG is not selected anymore when jumping from 3.16 to 3.17-rc1 if you don't set on the new NF_LOG_IPV4 and NF_LOG_IPV6 switches. Change this to select the three new symbols NF_LOG_COMMON, NF_LOG_IPV4 and NF_LOG_IPV6 instead, so NETFILTER_XT_TARGET_LOG remains enabled when moving from old to new kernels. Reported-by: Rafał Miłecki Signed-off-by: Pablo Neira Ayuso --- net/netfilter/Kconfig | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/net/netfilter/Kconfig b/net/netfilter/Kconfig index 05eb177ea852..4bef6eb7c40d 100644 --- a/net/netfilter/Kconfig +++ b/net/netfilter/Kconfig @@ -747,7 +747,9 @@ config NETFILTER_XT_TARGET_LED config NETFILTER_XT_TARGET_LOG tristate "LOG target support" - depends on NF_LOG_IPV4 && NF_LOG_IPV6 + select NF_LOG_COMMON + select NF_LOG_IPV4 + select NF_LOG_IPV6 if IPV6 default m if NETFILTER_ADVANCED=n help This option adds a `LOG' target, which allows you to create rules in From e148e1bf6fcdecb19015c63ba8c6c25ed5dc3a2a Mon Sep 17 00:00:00 2001 From: Geert Uytterhoeven Date: Fri, 29 Aug 2014 18:21:41 +0200 Subject: [PATCH 063/101] drivers: net: NET_XGENE should depend on HAS_DMA If NO_DMA=y: drivers/built-in.o: In function `xgene_enet_delete_ring': xgene_enet_main.c:(.text+0x28755a): undefined reference to `dma_free_coherent' drivers/built-in.o: In function `xgene_enet_setup_tx_desc': xgene_enet_main.c:(.text+0x287774): undefined reference to `dma_map_single' xgene_enet_main.c:(.text+0x287780): undefined reference to `dma_mapping_error' drivers/built-in.o: In function `xgene_enet_tx_completion': xgene_enet_main.c:(.text+0x2878e6): undefined reference to `dma_unmap_single' drivers/built-in.o: In function `xgene_enet_refill_bufpool': xgene_enet_main.c:(.text+0x2879d4): undefined reference to `dma_map_single' xgene_enet_main.c:(.text+0x2879e0): undefined reference to `dma_mapping_error' drivers/built-in.o: In function `xgene_enet_rx_frame': xgene_enet_main.c:(.text+0x287aaa): undefined reference to `dma_unmap_single' drivers/built-in.o: In function `xgene_enet_free_desc_ring': xgene_enet_main.c:(.text+0x287f98): undefined reference to `dma_free_coherent' drivers/built-in.o: In function `xgene_enet_create_desc_ring': xgene_enet_main.c:(.text+0x28808e): undefined reference to `dma_alloc_coherent' drivers/built-in.o: In function `xgene_enet_probe': xgene_enet_main.c:(.text+0x2883d4): undefined reference to `dma_set_mask' xgene_enet_main.c:(.text+0x2883ec): undefined reference to `dma_supported' Signed-off-by: Geert Uytterhoeven Signed-off-by: David S. Miller --- drivers/net/ethernet/apm/xgene/Kconfig | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/net/ethernet/apm/xgene/Kconfig b/drivers/net/ethernet/apm/xgene/Kconfig index 616dff6d3f5f..f4054d242f3c 100644 --- a/drivers/net/ethernet/apm/xgene/Kconfig +++ b/drivers/net/ethernet/apm/xgene/Kconfig @@ -1,5 +1,6 @@ config NET_XGENE tristate "APM X-Gene SoC Ethernet Driver" + depends on HAS_DMA select PHYLIB help This is the Ethernet driver for the on-chip ethernet interface on the From a9a4a2d9d622e3bde41356aa4e2694cee052d002 Mon Sep 17 00:00:00 2001 From: "Lendacky, Thomas" Date: Fri, 29 Aug 2014 13:16:50 -0500 Subject: [PATCH 064/101] amd-xgbe: Check for Tx hardware queue flushing support The flushing of the Tx hardware queues is only supported at a certain level of the hardware. Retrieve the current version of the hardware and use that to determine if flushing is supported. Signed-off-by: Tom Lendacky Signed-off-by: David S. Miller --- drivers/net/ethernet/amd/xgbe/xgbe-dev.c | 3 +++ drivers/net/ethernet/amd/xgbe/xgbe-drv.c | 2 ++ drivers/net/ethernet/amd/xgbe/xgbe-ethtool.c | 7 ++++--- drivers/net/ethernet/amd/xgbe/xgbe.h | 3 +++ 4 files changed, 12 insertions(+), 3 deletions(-) diff --git a/drivers/net/ethernet/amd/xgbe/xgbe-dev.c b/drivers/net/ethernet/amd/xgbe/xgbe-dev.c index edaca4496264..e43747a9926f 100644 --- a/drivers/net/ethernet/amd/xgbe/xgbe-dev.c +++ b/drivers/net/ethernet/amd/xgbe/xgbe-dev.c @@ -1633,6 +1633,9 @@ static int xgbe_flush_tx_queues(struct xgbe_prv_data *pdata) { unsigned int i, count; + if (XGMAC_GET_BITS(pdata->hw_feat.version, MAC_VR, SNPSVER) < 0x21) + return 0; + for (i = 0; i < pdata->tx_q_count; i++) XGMAC_MTL_IOWRITE_BITS(pdata, i, MTL_Q_TQOMR, FTQ, 1); diff --git a/drivers/net/ethernet/amd/xgbe/xgbe-drv.c b/drivers/net/ethernet/amd/xgbe/xgbe-drv.c index dc84f7193c2d..b26d75856553 100644 --- a/drivers/net/ethernet/amd/xgbe/xgbe-drv.c +++ b/drivers/net/ethernet/amd/xgbe/xgbe-drv.c @@ -361,6 +361,8 @@ void xgbe_get_all_hw_features(struct xgbe_prv_data *pdata) memset(hw_feat, 0, sizeof(*hw_feat)); + hw_feat->version = XGMAC_IOREAD(pdata, MAC_VR); + /* Hardware feature register 0 */ hw_feat->gmii = XGMAC_GET_BITS(mac_hfr0, MAC_HWF0R, GMIISEL); hw_feat->vlhash = XGMAC_GET_BITS(mac_hfr0, MAC_HWF0R, VLHASH); diff --git a/drivers/net/ethernet/amd/xgbe/xgbe-ethtool.c b/drivers/net/ethernet/amd/xgbe/xgbe-ethtool.c index a076aca138a1..46f613028e9c 100644 --- a/drivers/net/ethernet/amd/xgbe/xgbe-ethtool.c +++ b/drivers/net/ethernet/amd/xgbe/xgbe-ethtool.c @@ -361,15 +361,16 @@ static void xgbe_get_drvinfo(struct net_device *netdev, struct ethtool_drvinfo *drvinfo) { struct xgbe_prv_data *pdata = netdev_priv(netdev); + struct xgbe_hw_features *hw_feat = &pdata->hw_feat; strlcpy(drvinfo->driver, XGBE_DRV_NAME, sizeof(drvinfo->driver)); strlcpy(drvinfo->version, XGBE_DRV_VERSION, sizeof(drvinfo->version)); strlcpy(drvinfo->bus_info, dev_name(pdata->dev), sizeof(drvinfo->bus_info)); snprintf(drvinfo->fw_version, sizeof(drvinfo->fw_version), "%d.%d.%d", - XGMAC_IOREAD_BITS(pdata, MAC_VR, USERVER), - XGMAC_IOREAD_BITS(pdata, MAC_VR, DEVID), - XGMAC_IOREAD_BITS(pdata, MAC_VR, SNPSVER)); + XGMAC_GET_BITS(hw_feat->version, MAC_VR, USERVER), + XGMAC_GET_BITS(hw_feat->version, MAC_VR, DEVID), + XGMAC_GET_BITS(hw_feat->version, MAC_VR, SNPSVER)); drvinfo->n_stats = XGBE_STATS_COUNT; } diff --git a/drivers/net/ethernet/amd/xgbe/xgbe.h b/drivers/net/ethernet/amd/xgbe/xgbe.h index 07bf70a82908..5af5c38eef4b 100644 --- a/drivers/net/ethernet/amd/xgbe/xgbe.h +++ b/drivers/net/ethernet/amd/xgbe/xgbe.h @@ -526,6 +526,9 @@ struct xgbe_desc_if { * or configurations are present in the device. */ struct xgbe_hw_features { + /* HW Version */ + unsigned int version; + /* HW Feature Register0 */ unsigned int gmii; /* 1000 Mbps support */ unsigned int vlhash; /* VLAN Hash Filter */ From f076f453729bb7dd63a798743ee11dea039c7df3 Mon Sep 17 00:00:00 2001 From: "Lendacky, Thomas" Date: Fri, 29 Aug 2014 13:16:56 -0500 Subject: [PATCH 065/101] amd-xgbe: Reported fifo size from hardware is not correct The fifo size reported by the hardware is not correct. Add support to limit the reported size to what is actually present. Also, fix the argument types used in the fifo size calculation function. Signed-off-by: Tom Lendacky Signed-off-by: David S. Miller --- drivers/net/ethernet/amd/xgbe/xgbe-dev.c | 8 ++++++-- drivers/net/ethernet/amd/xgbe/xgbe.h | 1 + 2 files changed, 7 insertions(+), 2 deletions(-) diff --git a/drivers/net/ethernet/amd/xgbe/xgbe-dev.c b/drivers/net/ethernet/amd/xgbe/xgbe-dev.c index e43747a9926f..acde00c8fdb4 100644 --- a/drivers/net/ethernet/amd/xgbe/xgbe-dev.c +++ b/drivers/net/ethernet/amd/xgbe/xgbe-dev.c @@ -1706,8 +1706,8 @@ static void xgbe_config_mtl_mode(struct xgbe_prv_data *pdata) XGMAC_IOWRITE_BITS(pdata, MTL_OMR, RAA, MTL_RAA_SP); } -static unsigned int xgbe_calculate_per_queue_fifo(unsigned long fifo_size, - unsigned char queue_count) +static unsigned int xgbe_calculate_per_queue_fifo(unsigned int fifo_size, + unsigned int queue_count) { unsigned int q_fifo_size = 0; enum xgbe_mtl_fifo_size p_fifo = XGMAC_MTL_FIFO_SIZE_256; @@ -1751,6 +1751,10 @@ static unsigned int xgbe_calculate_per_queue_fifo(unsigned long fifo_size, q_fifo_size = XGBE_FIFO_SIZE_KB(256); break; } + + /* The configured value is not the actual amount of fifo RAM */ + q_fifo_size = min_t(unsigned int, XGBE_FIFO_MAX, q_fifo_size); + q_fifo_size = q_fifo_size / queue_count; /* Set the queue fifo size programmable value */ diff --git a/drivers/net/ethernet/amd/xgbe/xgbe.h b/drivers/net/ethernet/amd/xgbe/xgbe.h index 5af5c38eef4b..e9fe6e6ddcc3 100644 --- a/drivers/net/ethernet/amd/xgbe/xgbe.h +++ b/drivers/net/ethernet/amd/xgbe/xgbe.h @@ -183,6 +183,7 @@ #define XGMAC_DRIVER_CONTEXT 1 #define XGMAC_IOCTL_CONTEXT 2 +#define XGBE_FIFO_MAX 81920 #define XGBE_FIFO_SIZE_B(x) (x) #define XGBE_FIFO_SIZE_KB(x) (x * 1024) From 625c8e4a2f307650fd18cf4a4f897260c800db89 Mon Sep 17 00:00:00 2001 From: "Lendacky, Thomas" Date: Fri, 29 Aug 2014 13:17:02 -0500 Subject: [PATCH 066/101] amd-xgbe: Fix the xpcs mmd debugfs support The debugfs support for the xpcs registers did not properly use the specified mmd (xpcs_mmd entry) which resulted in the default mmd value always being used. Update the debugfs support to generate the proper mmd register value. Signed-off-by: Tom Lendacky Signed-off-by: David S. Miller --- drivers/net/ethernet/amd/xgbe/xgbe-debugfs.c | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/drivers/net/ethernet/amd/xgbe/xgbe-debugfs.c b/drivers/net/ethernet/amd/xgbe/xgbe-debugfs.c index 346592dca33c..a3c11355a34d 100644 --- a/drivers/net/ethernet/amd/xgbe/xgbe-debugfs.c +++ b/drivers/net/ethernet/amd/xgbe/xgbe-debugfs.c @@ -272,8 +272,8 @@ static ssize_t xpcs_reg_value_read(struct file *filp, char __user *buffer, struct xgbe_prv_data *pdata = filp->private_data; unsigned int value; - value = pdata->hw_if.read_mmd_regs(pdata, pdata->debugfs_xpcs_mmd, - pdata->debugfs_xpcs_reg); + value = XMDIO_READ(pdata, pdata->debugfs_xpcs_mmd, + pdata->debugfs_xpcs_reg); return xgbe_common_read(buffer, count, ppos, value); } @@ -290,8 +290,8 @@ static ssize_t xpcs_reg_value_write(struct file *filp, if (len < 0) return len; - pdata->hw_if.write_mmd_regs(pdata, pdata->debugfs_xpcs_mmd, - pdata->debugfs_xpcs_reg, value); + XMDIO_WRITE(pdata, pdata->debugfs_xpcs_mmd, pdata->debugfs_xpcs_reg, + value); return len; } From 9fc69affda1b576c0b4c2aed8acb9cf3de3349ba Mon Sep 17 00:00:00 2001 From: "Lendacky, Thomas" Date: Fri, 29 Aug 2014 13:17:08 -0500 Subject: [PATCH 067/101] amd-xgbe: Use the Tx queue count for Tx flow control support When configuring Tx flow control the Rx queue count was used instead of the Tx queue count for looping through the Tx hardware queues. Fix the code to use the Tx queue count. Signed-off-by: Tom Lendacky Signed-off-by: David S. Miller --- drivers/net/ethernet/amd/xgbe/xgbe-dev.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/net/ethernet/amd/xgbe/xgbe-dev.c b/drivers/net/ethernet/amd/xgbe/xgbe-dev.c index acde00c8fdb4..6d0207eac265 100644 --- a/drivers/net/ethernet/amd/xgbe/xgbe-dev.c +++ b/drivers/net/ethernet/amd/xgbe/xgbe-dev.c @@ -348,7 +348,7 @@ static int xgbe_disable_tx_flow_control(struct xgbe_prv_data *pdata) /* Clear MAC flow control */ max_q_count = XGMAC_MAX_FLOW_CONTROL_QUEUES; - q_count = min_t(unsigned int, pdata->rx_q_count, max_q_count); + q_count = min_t(unsigned int, pdata->tx_q_count, max_q_count); reg = MAC_Q0TFCR; for (i = 0; i < q_count; i++) { reg_val = XGMAC_IOREAD(pdata, reg); @@ -373,7 +373,7 @@ static int xgbe_enable_tx_flow_control(struct xgbe_prv_data *pdata) /* Set MAC flow control */ max_q_count = XGMAC_MAX_FLOW_CONTROL_QUEUES; - q_count = min_t(unsigned int, pdata->rx_q_count, max_q_count); + q_count = min_t(unsigned int, pdata->tx_q_count, max_q_count); reg = MAC_Q0TFCR; for (i = 0; i < q_count; i++) { reg_val = XGMAC_IOREAD(pdata, reg); From d2afb5bdffde3da175b9ced66f70a4b453103d71 Mon Sep 17 00:00:00 2001 From: Giuseppe CAVALLARO Date: Mon, 1 Sep 2014 09:17:52 +0200 Subject: [PATCH 068/101] stmmac: fix the rx csum feature For new GMACs it is possible to turn-on/off the COE. In the current driver, when disabled the Rx-checksum via ethtool, the tool reported that csum was disabled but the HW continued to set the IPC. Indeed this is because the fix_features allows this. So the patch fixes this problem by adding the set_features. Signed-off-by: Giuseppe Cavallaro Signed-off-by: David S. Miller --- drivers/net/ethernet/stmicro/stmmac/common.h | 1 + .../ethernet/stmicro/stmmac/dwmac1000_core.c | 6 ++++- .../net/ethernet/stmicro/stmmac/stmmac_main.c | 27 +++++++++++++++++-- 3 files changed, 31 insertions(+), 3 deletions(-) diff --git a/drivers/net/ethernet/stmicro/stmmac/common.h b/drivers/net/ethernet/stmicro/stmmac/common.h index e3b81cdc94b2..593e6c4144a7 100644 --- a/drivers/net/ethernet/stmicro/stmmac/common.h +++ b/drivers/net/ethernet/stmicro/stmmac/common.h @@ -445,6 +445,7 @@ struct mac_device_info { int multicast_filter_bins; int unicast_filter_entries; int mcast_bits_log2; + unsigned int rx_csum; }; struct mac_device_info *dwmac1000_setup(void __iomem *ioaddr, int mcbins, diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac1000_core.c b/drivers/net/ethernet/stmicro/stmmac/dwmac1000_core.c index d8ef18786a1c..5efe60ea6526 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac1000_core.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac1000_core.c @@ -58,7 +58,11 @@ static int dwmac1000_rx_ipc_enable(struct mac_device_info *hw) void __iomem *ioaddr = hw->pcsr; u32 value = readl(ioaddr + GMAC_CONTROL); - value |= GMAC_CONTROL_IPC; + if (hw->rx_csum) + value |= GMAC_CONTROL_IPC; + else + value &= ~GMAC_CONTROL_IPC; + writel(value, ioaddr + GMAC_CONTROL); value = readl(ioaddr + GMAC_CONTROL); diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c index 3d3db16c97d4..0ed8ac81238b 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c @@ -1673,6 +1673,7 @@ static int stmmac_hw_setup(struct net_device *dev) if (!ret) { pr_warn(" RX IPC Checksum Offload disabled\n"); priv->plat->rx_coe = STMMAC_RX_COE_NONE; + priv->hw->rx_csum = 0; } /* Enable the MAC Rx/Tx */ @@ -2111,7 +2112,7 @@ static int stmmac_rx(struct stmmac_priv *priv, int limit) unsigned int entry = priv->cur_rx % rxsize; unsigned int next_entry; unsigned int count = 0; - int coe = priv->plat->rx_coe; + int coe = priv->hw->rx_csum; if (netif_msg_rx_status(priv)) { pr_debug("%s: descriptor ring:\n", __func__); @@ -2334,6 +2335,7 @@ static netdev_features_t stmmac_fix_features(struct net_device *dev, features &= ~NETIF_F_RXCSUM; else if (priv->plat->rx_coe == STMMAC_RX_COE_TYPE1) features &= ~NETIF_F_IPV6_CSUM; + if (!priv->plat->tx_coe) features &= ~NETIF_F_ALL_CSUM; @@ -2348,6 +2350,24 @@ static netdev_features_t stmmac_fix_features(struct net_device *dev, return features; } +static int stmmac_set_features(struct net_device *netdev, + netdev_features_t features) +{ + struct stmmac_priv *priv = netdev_priv(netdev); + + /* Keep the COE Type in case of csum is supporting */ + if (features & NETIF_F_RXCSUM) + priv->hw->rx_csum = priv->plat->rx_coe; + else + priv->hw->rx_csum = 0; + /* No check needed because rx_coe has been set before and it will be + * fixed in case of issue. + */ + priv->hw->mac->rx_ipc(priv->hw); + + return 0; +} + /** * stmmac_interrupt - main ISR * @irq: interrupt number. @@ -2628,6 +2648,7 @@ static const struct net_device_ops stmmac_netdev_ops = { .ndo_stop = stmmac_release, .ndo_change_mtu = stmmac_change_mtu, .ndo_fix_features = stmmac_fix_features, + .ndo_set_features = stmmac_set_features, .ndo_set_rx_mode = stmmac_set_rx_mode, .ndo_tx_timeout = stmmac_tx_timeout, .ndo_do_ioctl = stmmac_ioctl, @@ -2704,9 +2725,11 @@ static int stmmac_hw_init(struct stmmac_priv *priv) /* To use alternate (extended) or normal descriptor structures */ stmmac_selec_desc_mode(priv); - if (priv->plat->rx_coe) + if (priv->plat->rx_coe) { + priv->hw->rx_csum = priv->plat->rx_coe; pr_info(" RX Checksum Offload Engine supported (type %d)\n", priv->plat->rx_coe); + } if (priv->plat->tx_coe) pr_info(" TX Checksum insertion supported\n"); From cc25f0cbe4409d6a573b1f3bf7020d5b04076ee9 Mon Sep 17 00:00:00 2001 From: Giuseppe CAVALLARO Date: Mon, 1 Sep 2014 09:17:53 +0200 Subject: [PATCH 069/101] stmmac: only remove RXCSUM feature if no rx coe is available In case of the HW is not able to do the receive checksum offloading the only feature to remove is NETIF_F_RXCSUM. Signed-off-by: Giuseppe Cavallaro Signed-off-by: David S. Miller --- drivers/net/ethernet/stmicro/stmmac/stmmac_main.c | 2 -- 1 file changed, 2 deletions(-) diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c index 0ed8ac81238b..6e6ee226de04 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c @@ -2333,8 +2333,6 @@ static netdev_features_t stmmac_fix_features(struct net_device *dev, if (priv->plat->rx_coe == STMMAC_RX_COE_NONE) features &= ~NETIF_F_RXCSUM; - else if (priv->plat->rx_coe == STMMAC_RX_COE_TYPE1) - features &= ~NETIF_F_IPV6_CSUM; if (!priv->plat->tx_coe) features &= ~NETIF_F_ALL_CSUM; From 444018a7f1f46d588328498777cab5a9f4d29105 Mon Sep 17 00:00:00 2001 From: Hariprasad Shenai Date: Mon, 1 Sep 2014 19:54:55 +0530 Subject: [PATCH 070/101] cxgb4: Fix for handling 1Gb/s SFP+ Transceiver Modules We previously assumed that a Port's Capabilities and Advertised Capabilities would never change from Port Initialization time. This is no longer true when we can have 10Gb/s and 1Gb/s SFP+ Transceiver Modules randomly swapped. Signed-off-by: Hariprasad Shenai Signed-off-by: David S. Miller --- drivers/net/ethernet/chelsio/cxgb4/t4_hw.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/net/ethernet/chelsio/cxgb4/t4_hw.c b/drivers/net/ethernet/chelsio/cxgb4/t4_hw.c index a853133d8db8..6b92c4c5a241 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/t4_hw.c +++ b/drivers/net/ethernet/chelsio/cxgb4/t4_hw.c @@ -3742,6 +3742,7 @@ int t4_handle_fw_rpl(struct adapter *adap, const __be64 *rpl) lc->link_ok = link_ok; lc->speed = speed; lc->fc = fc; + lc->supported = be16_to_cpu(p->u.info.pcap); t4_os_link_changed(adap, port, link_ok); } if (mod != pi->mod_type) { From 63a92fe6f7e40069086be21bf9fbcfbe8d001345 Mon Sep 17 00:00:00 2001 From: Hariprasad Shenai Date: Mon, 1 Sep 2014 19:54:56 +0530 Subject: [PATCH 071/101] cxgb4: Fixed the code to use correct length for part number Previously it was using the length value of serial number. Also added macro for VPD unique identifier (0x82). Signed-off-by: Casey Leedom Signed-off-by: Hariprasad Shenai Signed-off-by: David S. Miller --- drivers/net/ethernet/chelsio/cxgb4/t4_hw.c | 11 ++++++++++- 1 file changed, 10 insertions(+), 1 deletion(-) diff --git a/drivers/net/ethernet/chelsio/cxgb4/t4_hw.c b/drivers/net/ethernet/chelsio/cxgb4/t4_hw.c index 6b92c4c5a241..adf16a54da26 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/t4_hw.c +++ b/drivers/net/ethernet/chelsio/cxgb4/t4_hw.c @@ -566,6 +566,7 @@ int t4_memory_rw(struct adapter *adap, int win, int mtype, u32 addr, #define VPD_BASE 0x400 #define VPD_BASE_OLD 0 #define VPD_LEN 1024 +#define CHELSIO_VPD_UNIQUE_ID 0x82 /** * t4_seeprom_wp - enable/disable EEPROM write protection @@ -603,7 +604,14 @@ int get_vpd_params(struct adapter *adapter, struct vpd_params *p) ret = pci_read_vpd(adapter->pdev, VPD_BASE, sizeof(u32), vpd); if (ret < 0) goto out; - addr = *vpd == 0x82 ? VPD_BASE : VPD_BASE_OLD; + + /* The VPD shall have a unique identifier specified by the PCI SIG. + * For chelsio adapters, the identifier is 0x82. The first byte of a VPD + * shall be CHELSIO_VPD_UNIQUE_ID (0x82). The VPD programming software + * is expected to automatically put this entry at the + * beginning of the VPD. + */ + addr = *vpd == CHELSIO_VPD_UNIQUE_ID ? VPD_BASE : VPD_BASE_OLD; ret = pci_read_vpd(adapter->pdev, addr, VPD_LEN, vpd); if (ret < 0) @@ -667,6 +675,7 @@ int get_vpd_params(struct adapter *adapter, struct vpd_params *p) i = pci_vpd_info_field_size(vpd + sn - PCI_VPD_INFO_FLD_HDR_SIZE); memcpy(p->sn, vpd + sn, min(i, SERNUM_LEN)); strim(p->sn); + i = pci_vpd_info_field_size(vpd + pn - PCI_VPD_INFO_FLD_HDR_SIZE); memcpy(p->pn, vpd + pn, min(i, PN_LEN)); strim(p->pn); From 9bb59b96ae88ee9dc035d5cc9818b02b12208904 Mon Sep 17 00:00:00 2001 From: Hariprasad Shenai Date: Mon, 1 Sep 2014 19:54:57 +0530 Subject: [PATCH 072/101] cxgb4: Fix T5 adapter accessing T4 adapter registers Fixes few register access for both T4 and T5. PCIE_CORE_UTL_SYSTEM_BUS_AGENT_STATUS & PCIE_CORE_UTL_PCI_EXPRESS_PORT_STATUS is T4 only register don't let T5 access them. For T5 MA_PARITY_ERROR_STATUS2 is additionally read. MPS_TRC_RSS_CONTROL is T4 only register, for T5 use MPS_T5_TRC_RSS_CONTROL. Signed-off-by: Hariprasad Shenai Signed-off-by: David S. Miller --- .../net/ethernet/chelsio/cxgb4/cxgb4_main.c | 4 ++- drivers/net/ethernet/chelsio/cxgb4/t4_hw.c | 29 ++++++++++++------- drivers/net/ethernet/chelsio/cxgb4/t4_regs.h | 2 ++ 3 files changed, 24 insertions(+), 11 deletions(-) diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c index 18fb9c61d7ba..cf387ae8d7f8 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c +++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c @@ -1253,7 +1253,9 @@ freeout: t4_free_sge_resources(adap); goto freeout; } - t4_write_reg(adap, MPS_TRC_RSS_CONTROL, + t4_write_reg(adap, is_t4(adap->params.chip) ? + MPS_TRC_RSS_CONTROL : + MPS_T5_TRC_RSS_CONTROL, RSSCONTROL(netdev2pinfo(adap->port[0])->tx_chan) | QUEUENUMBER(s->ethrxq[0].rspq.abs_id)); return 0; diff --git a/drivers/net/ethernet/chelsio/cxgb4/t4_hw.c b/drivers/net/ethernet/chelsio/cxgb4/t4_hw.c index adf16a54da26..0250a9deb292 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/t4_hw.c +++ b/drivers/net/ethernet/chelsio/cxgb4/t4_hw.c @@ -1403,15 +1403,18 @@ static void pcie_intr_handler(struct adapter *adapter) int fat; - fat = t4_handle_intr_status(adapter, - PCIE_CORE_UTL_SYSTEM_BUS_AGENT_STATUS, - sysbus_intr_info) + - t4_handle_intr_status(adapter, - PCIE_CORE_UTL_PCI_EXPRESS_PORT_STATUS, - pcie_port_intr_info) + - t4_handle_intr_status(adapter, PCIE_INT_CAUSE, - is_t4(adapter->params.chip) ? - pcie_intr_info : t5_pcie_intr_info); + if (is_t4(adapter->params.chip)) + fat = t4_handle_intr_status(adapter, + PCIE_CORE_UTL_SYSTEM_BUS_AGENT_STATUS, + sysbus_intr_info) + + t4_handle_intr_status(adapter, + PCIE_CORE_UTL_PCI_EXPRESS_PORT_STATUS, + pcie_port_intr_info) + + t4_handle_intr_status(adapter, PCIE_INT_CAUSE, + pcie_intr_info); + else + fat = t4_handle_intr_status(adapter, PCIE_INT_CAUSE, + t5_pcie_intr_info); if (fat) t4_fatal_err(adapter); @@ -1777,10 +1780,16 @@ static void ma_intr_handler(struct adapter *adap) { u32 v, status = t4_read_reg(adap, MA_INT_CAUSE); - if (status & MEM_PERR_INT_CAUSE) + if (status & MEM_PERR_INT_CAUSE) { dev_alert(adap->pdev_dev, "MA parity error, parity status %#x\n", t4_read_reg(adap, MA_PARITY_ERROR_STATUS)); + if (is_t5(adap->params.chip)) + dev_alert(adap->pdev_dev, + "MA parity error, parity status %#x\n", + t4_read_reg(adap, + MA_PARITY_ERROR_STATUS2)); + } if (status & MEM_WRAP_INT_CAUSE) { v = t4_read_reg(adap, MA_INT_WRAP_STATUS); dev_alert(adap->pdev_dev, "MA address wrap-around error by " diff --git a/drivers/net/ethernet/chelsio/cxgb4/t4_regs.h b/drivers/net/ethernet/chelsio/cxgb4/t4_regs.h index e3146e83df20..39fb325474f7 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/t4_regs.h +++ b/drivers/net/ethernet/chelsio/cxgb4/t4_regs.h @@ -511,6 +511,7 @@ #define MEM_WRAP_CLIENT_NUM_GET(x) (((x) & MEM_WRAP_CLIENT_NUM_MASK) >> MEM_WRAP_CLIENT_NUM_SHIFT) #define MA_PCIE_FW 0x30b8 #define MA_PARITY_ERROR_STATUS 0x77f4 +#define MA_PARITY_ERROR_STATUS2 0x7804 #define MA_EXT_MEMORY1_BAR 0x7808 #define EDC_0_BASE_ADDR 0x7900 @@ -959,6 +960,7 @@ #define TRCMULTIFILTER 0x00000001U #define MPS_TRC_RSS_CONTROL 0x9808 +#define MPS_T5_TRC_RSS_CONTROL 0xa00c #define RSSCONTROL_MASK 0x00ff0000U #define RSSCONTROL_SHIFT 16 #define RSSCONTROL(x) ((x) << RSSCONTROL_SHIFT) From 31d55c2d6672430f3ef0bfd4de72c5a4f6a8bab9 Mon Sep 17 00:00:00 2001 From: Hariprasad Shenai Date: Mon, 1 Sep 2014 19:54:58 +0530 Subject: [PATCH 073/101] cxgb4: Detect and display firmware reported errors The adapter firmware can indicate error conditions to the host. If the firmware has indicated an error, print out the reason for the firmware error. Based on original work by Casey Leedom Signed-off-by: Hariprasad Shenai Signed-off-by: David S. Miller --- drivers/net/ethernet/chelsio/cxgb4/t4_hw.c | 38 ++++++++++++++++++- drivers/net/ethernet/chelsio/cxgb4/t4fw_api.h | 4 ++ 2 files changed, 41 insertions(+), 1 deletion(-) diff --git a/drivers/net/ethernet/chelsio/cxgb4/t4_hw.c b/drivers/net/ethernet/chelsio/cxgb4/t4_hw.c index 0250a9deb292..41d04462b72e 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/t4_hw.c +++ b/drivers/net/ethernet/chelsio/cxgb4/t4_hw.c @@ -167,6 +167,34 @@ void t4_hw_pci_read_cfg4(struct adapter *adap, int reg, u32 *val) t4_write_reg(adap, PCIE_CFG_SPACE_REQ, 0); } +/* + * t4_report_fw_error - report firmware error + * @adap: the adapter + * + * The adapter firmware can indicate error conditions to the host. + * If the firmware has indicated an error, print out the reason for + * the firmware error. + */ +static void t4_report_fw_error(struct adapter *adap) +{ + static const char *const reason[] = { + "Crash", /* PCIE_FW_EVAL_CRASH */ + "During Device Preparation", /* PCIE_FW_EVAL_PREP */ + "During Device Configuration", /* PCIE_FW_EVAL_CONF */ + "During Device Initialization", /* PCIE_FW_EVAL_INIT */ + "Unexpected Event", /* PCIE_FW_EVAL_UNEXPECTEDEVENT */ + "Insufficient Airflow", /* PCIE_FW_EVAL_OVERHEAT */ + "Device Shutdown", /* PCIE_FW_EVAL_DEVICESHUTDOWN */ + "Reserved", /* reserved */ + }; + u32 pcie_fw; + + pcie_fw = t4_read_reg(adap, MA_PCIE_FW); + if (pcie_fw & FW_PCIE_FW_ERR) + dev_err(adap->pdev_dev, "Firmware reports adapter error: %s\n", + reason[FW_PCIE_FW_EVAL_GET(pcie_fw)]); +} + /* * Get the reply to a mailbox command and store it in @rpl in big-endian order. */ @@ -300,6 +328,7 @@ int t4_wr_mbox_meat(struct adapter *adap, int mbox, const void *cmd, int size, dump_mbox(adap, mbox, data_reg); dev_err(adap->pdev_dev, "command %#x in mailbox %d timed out\n", *(const u8 *)cmd, mbox); + t4_report_fw_error(adap); return -ETIMEDOUT; } @@ -1533,6 +1562,9 @@ static void cim_intr_handler(struct adapter *adapter) int fat; + if (t4_read_reg(adapter, MA_PCIE_FW) & FW_PCIE_FW_ERR) + t4_report_fw_error(adapter); + fat = t4_handle_intr_status(adapter, CIM_HOST_INT_CAUSE, cim_intr_info) + t4_handle_intr_status(adapter, CIM_HOST_UPACC_INT_CAUSE, @@ -2751,12 +2783,16 @@ retry: /* * Issue the HELLO command to the firmware. If it's not successful * but indicates that we got a "busy" or "timeout" condition, retry - * the HELLO until we exhaust our retry limit. + * the HELLO until we exhaust our retry limit. If we do exceed our + * retry limit, check to see if the firmware left us any error + * information and report that if so. */ ret = t4_wr_mbox(adap, mbox, &c, sizeof(c), &c); if (ret < 0) { if ((ret == -EBUSY || ret == -ETIMEDOUT) && retries-- > 0) goto retry; + if (t4_read_reg(adap, MA_PCIE_FW) & FW_PCIE_FW_ERR) + t4_report_fw_error(adap); return ret; } diff --git a/drivers/net/ethernet/chelsio/cxgb4/t4fw_api.h b/drivers/net/ethernet/chelsio/cxgb4/t4fw_api.h index 5f2729ebadbe..3409756a85b9 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/t4fw_api.h +++ b/drivers/net/ethernet/chelsio/cxgb4/t4fw_api.h @@ -2228,6 +2228,10 @@ struct fw_debug_cmd { #define FW_PCIE_FW_MASTER(x) ((x) << FW_PCIE_FW_MASTER_SHIFT) #define FW_PCIE_FW_MASTER_GET(x) (((x) >> FW_PCIE_FW_MASTER_SHIFT) & \ FW_PCIE_FW_MASTER_MASK) +#define FW_PCIE_FW_EVAL_MASK 0x7 +#define FW_PCIE_FW_EVAL_SHIFT 24 +#define FW_PCIE_FW_EVAL_GET(x) (((x) >> FW_PCIE_FW_EVAL_SHIFT) & \ + FW_PCIE_FW_EVAL_MASK) struct fw_hdr { u8 ver; From 3d9103f80d7b1e8f0be85d87d102ba8dc1084f2d Mon Sep 17 00:00:00 2001 From: Hariprasad Shenai Date: Mon, 1 Sep 2014 19:54:59 +0530 Subject: [PATCH 074/101] cxgb4: Avoid dumping Write-only registers in register dump Avoid dumping MPS_RPLC_MAP_CTL for reg dumps; this is a Write-Only register. Reading this register may cause MPS TCAM corruption. Signed-off-by: Hariprasad Shenai Signed-off-by: David S. Miller --- drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c index cf387ae8d7f8..1b5020a847c7 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c +++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c @@ -1763,7 +1763,8 @@ static void get_regs(struct net_device *dev, struct ethtool_regs *regs, 0xd004, 0xd03c, 0xdfc0, 0xdfe0, 0xe000, 0xea7c, - 0xf000, 0x11190, + 0xf000, 0x11110, + 0x11118, 0x11190, 0x19040, 0x1906c, 0x19078, 0x19080, 0x1908c, 0x19124, @@ -1970,7 +1971,8 @@ static void get_regs(struct net_device *dev, struct ethtool_regs *regs, 0xd004, 0xd03c, 0xdfc0, 0xdfe0, 0xe000, 0x11088, - 0x1109c, 0x1117c, + 0x1109c, 0x11110, + 0x11118, 0x1117c, 0x11190, 0x11204, 0x19040, 0x1906c, 0x19078, 0x19080, From 5c937dd3f9eb999e6f4802987a674eae5718be54 Mon Sep 17 00:00:00 2001 From: Hariprasad Shenai Date: Mon, 1 Sep 2014 19:55:00 +0530 Subject: [PATCH 075/101] cxgb4: Issue mbox commands on correct mbox A couple of RDMA-related called to t4_query_params() were issuing mbox commands on mbox0 instead of mbox4. Signed-off-by: Hariprasad Shenai Signed-off-by: David S. Miller --- drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c index 1b5020a847c7..8c34811a1128 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c +++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c @@ -5959,7 +5959,8 @@ static int adap_init0(struct adapter *adap) params[3] = FW_PARAM_PFVF(CQ_END); params[4] = FW_PARAM_PFVF(OCQ_START); params[5] = FW_PARAM_PFVF(OCQ_END); - ret = t4_query_params(adap, 0, 0, 0, 6, params, val); + ret = t4_query_params(adap, adap->mbox, adap->fn, 0, 6, params, + val); if (ret < 0) goto bye; adap->vres.qp.start = val[0]; @@ -5971,7 +5972,8 @@ static int adap_init0(struct adapter *adap) params[0] = FW_PARAM_DEV(MAXORDIRD_QP); params[1] = FW_PARAM_DEV(MAXIRD_ADAPTER); - ret = t4_query_params(adap, 0, 0, 0, 2, params, val); + ret = t4_query_params(adap, adap->mbox, adap->fn, 0, 2, params, + val); if (ret < 0) { adap->params.max_ordird_qp = 8; adap->params.max_ird_adapter = 32 * adap->tids.ntids; From 0486a063b1ffce4f37ef80970689c64bf7b99e98 Mon Sep 17 00:00:00 2001 From: Ivan Vecera Date: Mon, 1 Sep 2014 14:21:57 +0200 Subject: [PATCH 076/101] tg3: prevent ifup/ifdown during PCI error recovery The patch fixes race conditions between PCI error recovery callbacks and potential ifup/ifdown. First, if ifup (tg3_open) is called between tg3_io_error_detected() and tg3_io_resume() then tp->timer is armed twice before expiry. Once during tg3_open() and again during tg3_io_resume(). This results in BUG at kernel/time/timer.c:945. Second, if ifdown (tg3_close) is called between tg3_io_error_detected() and tg3_io_resume() then tg3_napi_disable() is called twice without a tg3_napi_enable between. Once during tg3_io_error_detected() and again during tg3_close(). The tg3_io_resume() then hangs on rtnl_lock(). v2: Added logging messages per Prashant's request Cc: Prashant Sreedharan Cc: Michael Chan Signed-off-by: Ivan Vecera Acked-by: Prashant Sreedharan Signed-off-by: David S. Miller --- drivers/net/ethernet/broadcom/tg3.c | 16 ++++++++++++++++ drivers/net/ethernet/broadcom/tg3.h | 1 + 2 files changed, 17 insertions(+) diff --git a/drivers/net/ethernet/broadcom/tg3.c b/drivers/net/ethernet/broadcom/tg3.c index 3ac5d23454a8..cb77ae93d89a 100644 --- a/drivers/net/ethernet/broadcom/tg3.c +++ b/drivers/net/ethernet/broadcom/tg3.c @@ -11617,6 +11617,12 @@ static int tg3_open(struct net_device *dev) struct tg3 *tp = netdev_priv(dev); int err; + if (tp->pcierr_recovery) { + netdev_err(dev, "Failed to open device. PCI error recovery " + "in progress\n"); + return -EAGAIN; + } + if (tp->fw_needed) { err = tg3_request_firmware(tp); if (tg3_asic_rev(tp) == ASIC_REV_57766) { @@ -11674,6 +11680,12 @@ static int tg3_close(struct net_device *dev) { struct tg3 *tp = netdev_priv(dev); + if (tp->pcierr_recovery) { + netdev_err(dev, "Failed to close device. PCI error recovery " + "in progress\n"); + return -EAGAIN; + } + tg3_ptp_fini(tp); tg3_stop(tp); @@ -17561,6 +17573,7 @@ static int tg3_init_one(struct pci_dev *pdev, tp->rx_mode = TG3_DEF_RX_MODE; tp->tx_mode = TG3_DEF_TX_MODE; tp->irq_sync = 1; + tp->pcierr_recovery = false; if (tg3_debug > 0) tp->msg_enable = tg3_debug; @@ -18071,6 +18084,8 @@ static pci_ers_result_t tg3_io_error_detected(struct pci_dev *pdev, rtnl_lock(); + tp->pcierr_recovery = true; + /* We probably don't have netdev yet */ if (!netdev || !netif_running(netdev)) goto done; @@ -18195,6 +18210,7 @@ static void tg3_io_resume(struct pci_dev *pdev) tg3_phy_start(tp); done: + tp->pcierr_recovery = false; rtnl_unlock(); } diff --git a/drivers/net/ethernet/broadcom/tg3.h b/drivers/net/ethernet/broadcom/tg3.h index 461accaf0aa4..31c9f8295953 100644 --- a/drivers/net/ethernet/broadcom/tg3.h +++ b/drivers/net/ethernet/broadcom/tg3.h @@ -3407,6 +3407,7 @@ struct tg3 { struct device *hwmon_dev; bool link_up; + bool pcierr_recovery; }; /* Accessor macros for chip and asic attributes From aff88a0695976596b39dcfa65da4896c802c938d Mon Sep 17 00:00:00 2001 From: Roland Stigge Date: Mon, 1 Sep 2014 13:46:46 +0200 Subject: [PATCH 077/101] net: lpc_eth: Fix crash on ip link up When a link is already up, the following sequence makes the kernel block completely: ip link set dev eth0 down ip link set dev eth0 up This is because on suspended phy, the following lines __lpc_eth_reset(pldat); __lpc_eth_init(pldat); make the LPC ethernet core block (see LPC32x0 manual). The PHY needs to be (re-)activated low-level first. Signed-off-by: Roland Stigge Signed-off-by: David S. Miller --- drivers/net/ethernet/nxp/lpc_eth.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/drivers/net/ethernet/nxp/lpc_eth.c b/drivers/net/ethernet/nxp/lpc_eth.c index 8706c0dbd0c3..a44a03c45014 100644 --- a/drivers/net/ethernet/nxp/lpc_eth.c +++ b/drivers/net/ethernet/nxp/lpc_eth.c @@ -1220,6 +1220,9 @@ static int lpc_eth_open(struct net_device *ndev) __lpc_eth_clock_enable(pldat, true); + /* Suspended PHY makes LPC ethernet core block, so resume now */ + phy_resume(pldat->phy_dev); + /* Reset and initialize */ __lpc_eth_reset(pldat); __lpc_eth_init(pldat); From f6ec9c335b502d8011971d07508589d212cb3c93 Mon Sep 17 00:00:00 2001 From: Bartlomiej Zolnierkiewicz Date: Mon, 1 Sep 2014 16:25:35 +0200 Subject: [PATCH 078/101] net: sh_eth: fix driver dependencies Renesas SuperH Ethernet support should be available only on Renesas ARM SoCs and SuperH architecture. Signed-off-by: Bartlomiej Zolnierkiewicz Acked-by: Kyungmin Park Cc: Simon Horman Cc: Magnus Damm Acked-by: Sergei Shtylyov Acked-by: Geert Uytterhoeven Acked-by: Simon Horman Signed-off-by: David S. Miller --- drivers/net/ethernet/renesas/Kconfig | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/net/ethernet/renesas/Kconfig b/drivers/net/ethernet/renesas/Kconfig index 9e757c792d84..196e98a2d93b 100644 --- a/drivers/net/ethernet/renesas/Kconfig +++ b/drivers/net/ethernet/renesas/Kconfig @@ -5,6 +5,7 @@ config SH_ETH tristate "Renesas SuperH Ethernet support" depends on HAS_DMA + depends on ARCH_SHMOBILE || SUPERH || COMPILE_TEST select CRC32 select MII select MDIO_BITBANG From c24f33796830aa42c496c2b2529ce6d51533af84 Mon Sep 17 00:00:00 2001 From: Bartlomiej Zolnierkiewicz Date: Mon, 1 Sep 2014 17:39:04 +0200 Subject: [PATCH 079/101] net: calxedaxgmac: fix driver dependencies Calxeda 1G/10G XGMAC Ethernet support should be available only on Calxeda ECX-1000/2000 (Highbank/Midway) platforms. Signed-off-by: Bartlomiej Zolnierkiewicz Acked-by: Kyungmin Park Cc: Rob Herring Signed-off-by: David S. Miller --- drivers/net/ethernet/calxeda/Kconfig | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/net/ethernet/calxeda/Kconfig b/drivers/net/ethernet/calxeda/Kconfig index 184a063bed5f..07d2201530d2 100644 --- a/drivers/net/ethernet/calxeda/Kconfig +++ b/drivers/net/ethernet/calxeda/Kconfig @@ -1,6 +1,7 @@ config NET_CALXEDA_XGMAC tristate "Calxeda 1G/10G XGMAC Ethernet driver" depends on HAS_IOMEM && HAS_DMA + depends on ARCH_HIGHBANK || COMPILE_TEST select CRC32 help This is the driver for the XGMAC Ethernet IP block found on Calxeda From 511c24456ad19d51fcdbc5eda9df7be98c20e6b0 Mon Sep 17 00:00:00 2001 From: Eugene Crosser Date: Tue, 2 Sep 2014 08:20:17 +0200 Subject: [PATCH 080/101] qeth: don't query for info if hardware not ready. When qeth device is queried for ethtool data, hardware operation is performed to extract the necessary information from the card. If the card is not online at the moment (e.g. it is undergoing recovery), this operation produces undesired effects like temporarily freezing the system. This patch prevents execution of the hardware query operation when the card is not online. In such case, ioctl() operation returns error with errno ENODEV. Reviewed-by: Ursula Braun Signed-off-by: Eugene Crosser Signed-off-by: Frank Blaschka Signed-off-by: David S. Miller --- drivers/s390/net/qeth_core.h | 1 + drivers/s390/net/qeth_core_main.c | 16 +++++++++++++++- drivers/s390/net/qeth_l2_sys.c | 7 +------ 3 files changed, 17 insertions(+), 7 deletions(-) diff --git a/drivers/s390/net/qeth_core.h b/drivers/s390/net/qeth_core.h index 97ef37b51068..e7646ce3d659 100644 --- a/drivers/s390/net/qeth_core.h +++ b/drivers/s390/net/qeth_core.h @@ -889,6 +889,7 @@ extern const struct attribute_group *qeth_generic_attr_groups[]; extern const struct attribute_group *qeth_osn_attr_groups[]; extern struct workqueue_struct *qeth_wq; +int qeth_card_hw_is_reachable(struct qeth_card *); const char *qeth_get_cardname_short(struct qeth_card *); int qeth_realloc_buffer_pool(struct qeth_card *, int); int qeth_core_load_discipline(struct qeth_card *, enum qeth_discipline_id); diff --git a/drivers/s390/net/qeth_core_main.c b/drivers/s390/net/qeth_core_main.c index c0d6ba8655c7..fd22c811cbe1 100644 --- a/drivers/s390/net/qeth_core_main.c +++ b/drivers/s390/net/qeth_core_main.c @@ -73,6 +73,13 @@ static int qeth_init_qdio_out_buf(struct qeth_qdio_out_q *, int); struct workqueue_struct *qeth_wq; EXPORT_SYMBOL_GPL(qeth_wq); +int qeth_card_hw_is_reachable(struct qeth_card *card) +{ + return (card->state == CARD_STATE_SOFTSETUP) || + (card->state == CARD_STATE_UP); +} +EXPORT_SYMBOL_GPL(qeth_card_hw_is_reachable); + static void qeth_close_dev_handler(struct work_struct *work) { struct qeth_card *card; @@ -5790,6 +5797,7 @@ int qeth_core_ethtool_get_settings(struct net_device *netdev, struct qeth_card *card = netdev->ml_priv; enum qeth_link_types link_type; struct carrier_info carrier_info; + int rc; u32 speed; if ((card->info.type == QETH_CARD_TYPE_IQD) || (card->info.guestlan)) @@ -5832,8 +5840,14 @@ int qeth_core_ethtool_get_settings(struct net_device *netdev, /* Check if we can obtain more accurate information. */ /* If QUERY_CARD_INFO command is not supported or fails, */ /* just return the heuristics that was filled above. */ - if (qeth_query_card_info(card, &carrier_info) != 0) + if (!qeth_card_hw_is_reachable(card)) + return -ENODEV; + rc = qeth_query_card_info(card, &carrier_info); + if (rc == -EOPNOTSUPP) /* for old hardware, return heuristic */ return 0; + if (rc) /* report error from the hardware operation */ + return rc; + /* on success, fill in the information got from the hardware */ netdev_dbg(netdev, "card info: card_type=0x%02x, port_mode=0x%04x, port_speed=0x%08x\n", diff --git a/drivers/s390/net/qeth_l2_sys.c b/drivers/s390/net/qeth_l2_sys.c index ae1bc04b8653..59e3aa538b4d 100644 --- a/drivers/s390/net/qeth_l2_sys.c +++ b/drivers/s390/net/qeth_l2_sys.c @@ -5,17 +5,12 @@ #include #include +#include "qeth_core.h" #include "qeth_l2.h" #define QETH_DEVICE_ATTR(_id, _name, _mode, _show, _store) \ struct device_attribute dev_attr_##_id = __ATTR(_name, _mode, _show, _store) -static int qeth_card_hw_is_reachable(struct qeth_card *card) -{ - return (card->state == CARD_STATE_SOFTSETUP) || - (card->state == CARD_STATE_UP); -} - static ssize_t qeth_bridge_port_role_state_show(struct device *dev, struct device_attribute *attr, char *buf, int show_state) From 04860eb7d911bbd958463416cc045b69ffdf73b3 Mon Sep 17 00:00:00 2001 From: Manish Chopra Date: Tue, 2 Sep 2014 04:31:25 -0400 Subject: [PATCH 081/101] bnx2x: Configure device endianity on driver load and reset endianity on removal. Some hosts can be both little and big endian. In certain scenarios a big endian kernel can kexec a little endian kernel. This patch fixes this case from both ends: 1) Return endianity to original values on shutdown (in case little endian kernel boots after we shutdown). 2) Do not rely on HW reset values when loading driver in little endian kernel but configure them explicitly (in case previous kernel was big endian and did not reset the HW). Signed-off-by: Manish Chopra Signed-off-by: Ariel Elior Signed-off-by: David S. Miller --- .../net/ethernet/broadcom/bnx2x/bnx2x_main.c | 57 +++++++++++++------ 1 file changed, 39 insertions(+), 18 deletions(-) diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c index 900cab420810..d1c093dcb054 100644 --- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c +++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c @@ -6849,6 +6849,37 @@ static void bnx2x__common_init_phy(struct bnx2x *bp) bnx2x_release_phy_lock(bp); } +static void bnx2x_config_endianity(struct bnx2x *bp, u32 val) +{ + REG_WR(bp, PXP2_REG_RQ_QM_ENDIAN_M, val); + REG_WR(bp, PXP2_REG_RQ_TM_ENDIAN_M, val); + REG_WR(bp, PXP2_REG_RQ_SRC_ENDIAN_M, val); + REG_WR(bp, PXP2_REG_RQ_CDU_ENDIAN_M, val); + REG_WR(bp, PXP2_REG_RQ_DBG_ENDIAN_M, val); + + /* make sure this value is 0 */ + REG_WR(bp, PXP2_REG_RQ_HC_ENDIAN_M, 0); + + REG_WR(bp, PXP2_REG_RD_QM_SWAP_MODE, val); + REG_WR(bp, PXP2_REG_RD_TM_SWAP_MODE, val); + REG_WR(bp, PXP2_REG_RD_SRC_SWAP_MODE, val); + REG_WR(bp, PXP2_REG_RD_CDURD_SWAP_MODE, val); +} + +static void bnx2x_set_endianity(struct bnx2x *bp) +{ +#ifdef __BIG_ENDIAN + bnx2x_config_endianity(bp, 1); +#else + bnx2x_config_endianity(bp, 0); +#endif +} + +static void bnx2x_reset_endianity(struct bnx2x *bp) +{ + bnx2x_config_endianity(bp, 0); +} + /** * bnx2x_init_hw_common - initialize the HW at the COMMON phase. * @@ -6915,23 +6946,7 @@ static int bnx2x_init_hw_common(struct bnx2x *bp) bnx2x_init_block(bp, BLOCK_PXP2, PHASE_COMMON); bnx2x_init_pxp(bp); - -#ifdef __BIG_ENDIAN - REG_WR(bp, PXP2_REG_RQ_QM_ENDIAN_M, 1); - REG_WR(bp, PXP2_REG_RQ_TM_ENDIAN_M, 1); - REG_WR(bp, PXP2_REG_RQ_SRC_ENDIAN_M, 1); - REG_WR(bp, PXP2_REG_RQ_CDU_ENDIAN_M, 1); - REG_WR(bp, PXP2_REG_RQ_DBG_ENDIAN_M, 1); - /* make sure this value is 0 */ - REG_WR(bp, PXP2_REG_RQ_HC_ENDIAN_M, 0); - -/* REG_WR(bp, PXP2_REG_RD_PBF_SWAP_MODE, 1); */ - REG_WR(bp, PXP2_REG_RD_QM_SWAP_MODE, 1); - REG_WR(bp, PXP2_REG_RD_TM_SWAP_MODE, 1); - REG_WR(bp, PXP2_REG_RD_SRC_SWAP_MODE, 1); - REG_WR(bp, PXP2_REG_RD_CDURD_SWAP_MODE, 1); -#endif - + bnx2x_set_endianity(bp); bnx2x_ilt_init_page_size(bp, INITOP_SET); if (CHIP_REV_IS_FPGA(bp) && CHIP_IS_E1H(bp)) @@ -13169,9 +13184,15 @@ static void __bnx2x_remove(struct pci_dev *pdev, bnx2x_iov_remove_one(bp); /* Power on: we can't let PCI layer write to us while we are in D3 */ - if (IS_PF(bp)) + if (IS_PF(bp)) { bnx2x_set_power_state(bp, PCI_D0); + /* Set endianity registers to reset values in case next driver + * boots in different endianty environment. + */ + bnx2x_reset_endianity(bp); + } + /* Disable MSI/MSI-X */ bnx2x_disable_msi(bp); From 41ad82f7f8f59a472c8e8ccca56a9c6bdf3c5092 Mon Sep 17 00:00:00 2001 From: Pablo Neira Date: Tue, 2 Sep 2014 14:26:17 +0200 Subject: [PATCH 082/101] netfilter: fix missing dependencies in NETFILTER_XT_TARGET_LOG make defconfig reports: warning: (NETFILTER_XT_TARGET_LOG) selects NF_LOG_IPV6 which has unmet direct dependencies (NET && INET && IPV6 && NETFILTER && NETFILTER_ADVANCED) Fixes: d79a61d netfilter: NETFILTER_XT_TARGET_LOG selects NF_LOG_* Reported-by: kbuild test robot Signed-off-by: Pablo Neira Ayuso Signed-off-by: David S. Miller --- net/ipv6/netfilter/Kconfig | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/net/ipv6/netfilter/Kconfig b/net/ipv6/netfilter/Kconfig index cf0b88f30f6f..2812816aabdc 100644 --- a/net/ipv6/netfilter/Kconfig +++ b/net/ipv6/netfilter/Kconfig @@ -57,7 +57,7 @@ config NFT_REJECT_IPV6 config NF_LOG_IPV6 tristate "IPv6 packet logging" - depends on NETFILTER_ADVANCED + default m if NETFILTER_ADVANCED=n select NF_LOG_COMMON config NF_NAT_IPV6 From 4ee45ea05c8710c7ab8a5eb1a72700b874712746 Mon Sep 17 00:00:00 2001 From: Li RongQing Date: Tue, 2 Sep 2014 20:52:28 +0800 Subject: [PATCH 083/101] openvswitch: fix a memory leak The user_skb maybe be leaked if the operation on it failed and codes skipped into the label "out:" without calling genlmsg_unicast. Cc: Pravin Shelar Signed-off-by: Li RongQing Acked-by: Pravin B Shelar Signed-off-by: David S. Miller --- net/openvswitch/datapath.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/net/openvswitch/datapath.c b/net/openvswitch/datapath.c index 7228ec3faf19..35d866f036e7 100644 --- a/net/openvswitch/datapath.c +++ b/net/openvswitch/datapath.c @@ -404,7 +404,7 @@ static int queue_userspace_packet(struct datapath *dp, struct sk_buff *skb, { struct ovs_header *upcall; struct sk_buff *nskb = NULL; - struct sk_buff *user_skb; /* to be queued to userspace */ + struct sk_buff *user_skb = NULL; /* to be queued to userspace */ struct nlattr *nla; struct genl_info info = { .dst_sk = ovs_dp_get_net(dp)->genl_sock, @@ -494,9 +494,11 @@ static int queue_userspace_packet(struct datapath *dp, struct sk_buff *skb, ((struct nlmsghdr *) user_skb->data)->nlmsg_len = user_skb->len; err = genlmsg_unicast(ovs_dp_get_net(dp), user_skb, upcall_info->portid); + user_skb = NULL; out: if (err) skb_tx_error(skb); + kfree_skb(user_skb); kfree_skb(nskb); return err; } From bec6bfb2437f4676dbaaacba6019e9dafef18962 Mon Sep 17 00:00:00 2001 From: "Lendacky, Thomas" Date: Tue, 2 Sep 2014 09:40:22 -0500 Subject: [PATCH 084/101] amd-xgbe: Fix initialization of the wrong spin lock During allocation and initialization of the network driver structures, the wrong pointer is used to initialize a spin lock. Fix the spin lock initialization by using the proper pointer. Signed-off-by: Tom Lendacky Signed-off-by: David S. Miller --- drivers/net/ethernet/amd/xgbe/xgbe-main.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/net/ethernet/amd/xgbe/xgbe-main.c b/drivers/net/ethernet/amd/xgbe/xgbe-main.c index 8aa6a9353f7b..bdf9cfa70e88 100644 --- a/drivers/net/ethernet/amd/xgbe/xgbe-main.c +++ b/drivers/net/ethernet/amd/xgbe/xgbe-main.c @@ -172,7 +172,7 @@ static struct xgbe_channel *xgbe_alloc_rings(struct xgbe_prv_data *pdata) } if (i < pdata->rx_ring_count) { - spin_lock_init(&tx_ring->lock); + spin_lock_init(&rx_ring->lock); channel->rx_ring = rx_ring++; } From c5eba0b6f84eb4f0fdc1d8a4abc1c7d40db6e8a6 Mon Sep 17 00:00:00 2001 From: Li RongQing Date: Wed, 3 Sep 2014 17:43:45 +0800 Subject: [PATCH 085/101] openvswitch: distinguish between the dropped and consumed skb distinguish between the dropped and consumed skb, not assume the skb is consumed always Cc: Thomas Graf Cc: Pravin Shelar Signed-off-by: Li RongQing Acked-by: Pravin B Shelar Signed-off-by: David S. Miller --- net/openvswitch/datapath.c | 7 +++++-- 1 file changed, 5 insertions(+), 2 deletions(-) diff --git a/net/openvswitch/datapath.c b/net/openvswitch/datapath.c index 35d866f036e7..91d66b7e64ac 100644 --- a/net/openvswitch/datapath.c +++ b/net/openvswitch/datapath.c @@ -265,8 +265,11 @@ void ovs_dp_process_received_packet(struct vport *p, struct sk_buff *skb) upcall.key = &key; upcall.userdata = NULL; upcall.portid = ovs_vport_find_upcall_portid(p, skb); - ovs_dp_upcall(dp, skb, &upcall); - consume_skb(skb); + error = ovs_dp_upcall(dp, skb, &upcall); + if (unlikely(error)) + kfree_skb(skb); + else + consume_skb(skb); stats_counter = &stats->n_missed; goto out; } From 4ad9a64f53c619969dede1143d56ccda1a453c39 Mon Sep 17 00:00:00 2001 From: Andy King Date: Tue, 2 Sep 2014 13:13:44 -0700 Subject: [PATCH 086/101] VMXNET3: Check for map error in vmxnet3_set_mc We should check if the map of the table actually succeeds, and also free resources accordingly. Version bumped to 1.2.1.0 Acked-by: Shelley Gong Acked-by: Bhavesh Davda Signed-off-by: Andy King Reported-by: Tetsuo Handa Signed-off-by: David S. Miller --- drivers/net/vmxnet3/vmxnet3_drv.c | 15 ++++++++------- drivers/net/vmxnet3/vmxnet3_int.h | 4 ++-- 2 files changed, 10 insertions(+), 9 deletions(-) diff --git a/drivers/net/vmxnet3/vmxnet3_drv.c b/drivers/net/vmxnet3/vmxnet3_drv.c index d6e90c72c257..6dfcbf523936 100644 --- a/drivers/net/vmxnet3/vmxnet3_drv.c +++ b/drivers/net/vmxnet3/vmxnet3_drv.c @@ -2056,7 +2056,6 @@ vmxnet3_set_mc(struct net_device *netdev) if (!netdev_mc_empty(netdev)) { new_table = vmxnet3_copy_mc(netdev); if (new_table) { - new_mode |= VMXNET3_RXM_MCAST; rxConf->mfTableLen = cpu_to_le16( netdev_mc_count(netdev) * ETH_ALEN); new_table_pa = dma_map_single( @@ -2064,15 +2063,18 @@ vmxnet3_set_mc(struct net_device *netdev) new_table, rxConf->mfTableLen, PCI_DMA_TODEVICE); + } + + if (new_table_pa) { + new_mode |= VMXNET3_RXM_MCAST; rxConf->mfTablePA = cpu_to_le64(new_table_pa); } else { - netdev_info(netdev, "failed to copy mcast list" - ", setting ALL_MULTI\n"); + netdev_info(netdev, + "failed to copy mcast list, setting ALL_MULTI\n"); new_mode |= VMXNET3_RXM_ALL_MULTI; } } - if (!(new_mode & VMXNET3_RXM_MCAST)) { rxConf->mfTableLen = 0; rxConf->mfTablePA = 0; @@ -2091,11 +2093,10 @@ vmxnet3_set_mc(struct net_device *netdev) VMXNET3_CMD_UPDATE_MAC_FILTERS); spin_unlock_irqrestore(&adapter->cmd_lock, flags); - if (new_table) { + if (new_table_pa) dma_unmap_single(&adapter->pdev->dev, new_table_pa, rxConf->mfTableLen, PCI_DMA_TODEVICE); - kfree(new_table); - } + kfree(new_table); } void diff --git a/drivers/net/vmxnet3/vmxnet3_int.h b/drivers/net/vmxnet3/vmxnet3_int.h index 29ee77f2c97f..3759479f959a 100644 --- a/drivers/net/vmxnet3/vmxnet3_int.h +++ b/drivers/net/vmxnet3/vmxnet3_int.h @@ -69,10 +69,10 @@ /* * Version numbers */ -#define VMXNET3_DRIVER_VERSION_STRING "1.2.0.0-k" +#define VMXNET3_DRIVER_VERSION_STRING "1.2.1.0-k" /* a 32-bit int, each byte encode a verion number in VMXNET3_DRIVER_VERSION */ -#define VMXNET3_DRIVER_VERSION_NUM 0x01020000 +#define VMXNET3_DRIVER_VERSION_NUM 0x01020100 #if defined(CONFIG_PCI_MSI) /* RSS only makes sense if MSI-X is supported. */ From a9ed4a2986e13011fcf4ed2d1a1647c53112f55b Mon Sep 17 00:00:00 2001 From: Sabrina Dubroca Date: Tue, 2 Sep 2014 10:29:29 +0200 Subject: [PATCH 087/101] ipv6: fix rtnl locking in setsockopt for anycast and multicast Calling setsockopt with IPV6_JOIN_ANYCAST or IPV6_LEAVE_ANYCAST triggers the assertion in addrconf_join_solict()/addrconf_leave_solict() ipv6_sock_ac_join(), ipv6_sock_ac_drop(), ipv6_sock_ac_close() need to take RTNL before calling ipv6_dev_ac_inc/dec. Same thing with ipv6_sock_mc_join(), ipv6_sock_mc_drop(), ipv6_sock_mc_close() before calling ipv6_dev_mc_inc/dec. This patch moves ASSERT_RTNL() up a level in the call stack. Signed-off-by: Cong Wang Signed-off-by: Sabrina Dubroca Reported-by: Tommi Rantala Acked-by: Hannes Frederic Sowa Signed-off-by: David S. Miller --- net/ipv6/addrconf.c | 15 +++++---------- net/ipv6/anycast.c | 12 ++++++++++++ net/ipv6/mcast.c | 14 ++++++++++++++ 3 files changed, 31 insertions(+), 10 deletions(-) diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c index 0b239fc1816e..aa0e135b808c 100644 --- a/net/ipv6/addrconf.c +++ b/net/ipv6/addrconf.c @@ -1690,14 +1690,12 @@ void addrconf_dad_failure(struct inet6_ifaddr *ifp) addrconf_mod_dad_work(ifp, 0); } -/* Join to solicited addr multicast group. */ - +/* Join to solicited addr multicast group. + * caller must hold RTNL */ void addrconf_join_solict(struct net_device *dev, const struct in6_addr *addr) { struct in6_addr maddr; - ASSERT_RTNL(); - if (dev->flags&(IFF_LOOPBACK|IFF_NOARP)) return; @@ -1705,12 +1703,11 @@ void addrconf_join_solict(struct net_device *dev, const struct in6_addr *addr) ipv6_dev_mc_inc(dev, &maddr); } +/* caller must hold RTNL */ void addrconf_leave_solict(struct inet6_dev *idev, const struct in6_addr *addr) { struct in6_addr maddr; - ASSERT_RTNL(); - if (idev->dev->flags&(IFF_LOOPBACK|IFF_NOARP)) return; @@ -1718,12 +1715,11 @@ void addrconf_leave_solict(struct inet6_dev *idev, const struct in6_addr *addr) __ipv6_dev_mc_dec(idev, &maddr); } +/* caller must hold RTNL */ static void addrconf_join_anycast(struct inet6_ifaddr *ifp) { struct in6_addr addr; - ASSERT_RTNL(); - if (ifp->prefix_len >= 127) /* RFC 6164 */ return; ipv6_addr_prefix(&addr, &ifp->addr, ifp->prefix_len); @@ -1732,12 +1728,11 @@ static void addrconf_join_anycast(struct inet6_ifaddr *ifp) ipv6_dev_ac_inc(ifp->idev->dev, &addr); } +/* caller must hold RTNL */ static void addrconf_leave_anycast(struct inet6_ifaddr *ifp) { struct in6_addr addr; - ASSERT_RTNL(); - if (ifp->prefix_len >= 127) /* RFC 6164 */ return; ipv6_addr_prefix(&addr, &ifp->addr, ifp->prefix_len); diff --git a/net/ipv6/anycast.c b/net/ipv6/anycast.c index 210183244689..45b9d81d91e8 100644 --- a/net/ipv6/anycast.c +++ b/net/ipv6/anycast.c @@ -77,6 +77,7 @@ int ipv6_sock_ac_join(struct sock *sk, int ifindex, const struct in6_addr *addr) pac->acl_next = NULL; pac->acl_addr = *addr; + rtnl_lock(); rcu_read_lock(); if (ifindex == 0) { struct rt6_info *rt; @@ -137,6 +138,7 @@ int ipv6_sock_ac_join(struct sock *sk, int ifindex, const struct in6_addr *addr) error: rcu_read_unlock(); + rtnl_unlock(); if (pac) sock_kfree_s(sk, pac, sizeof(*pac)); return err; @@ -171,13 +173,17 @@ int ipv6_sock_ac_drop(struct sock *sk, int ifindex, const struct in6_addr *addr) spin_unlock_bh(&ipv6_sk_ac_lock); + rtnl_lock(); rcu_read_lock(); dev = dev_get_by_index_rcu(net, pac->acl_ifindex); if (dev) ipv6_dev_ac_dec(dev, &pac->acl_addr); rcu_read_unlock(); + rtnl_unlock(); sock_kfree_s(sk, pac, sizeof(*pac)); + if (!dev) + return -ENODEV; return 0; } @@ -198,6 +204,7 @@ void ipv6_sock_ac_close(struct sock *sk) spin_unlock_bh(&ipv6_sk_ac_lock); prev_index = 0; + rtnl_lock(); rcu_read_lock(); while (pac) { struct ipv6_ac_socklist *next = pac->acl_next; @@ -212,6 +219,7 @@ void ipv6_sock_ac_close(struct sock *sk) pac = next; } rcu_read_unlock(); + rtnl_unlock(); } static void aca_put(struct ifacaddr6 *ac) @@ -233,6 +241,8 @@ int ipv6_dev_ac_inc(struct net_device *dev, const struct in6_addr *addr) struct rt6_info *rt; int err; + ASSERT_RTNL(); + idev = in6_dev_get(dev); if (idev == NULL) @@ -302,6 +312,8 @@ int __ipv6_dev_ac_dec(struct inet6_dev *idev, const struct in6_addr *addr) { struct ifacaddr6 *aca, *prev_aca; + ASSERT_RTNL(); + write_lock_bh(&idev->lock); prev_aca = NULL; for (aca = idev->ac_list; aca; aca = aca->aca_next) { diff --git a/net/ipv6/mcast.c b/net/ipv6/mcast.c index 617f0958e164..a23b655a7627 100644 --- a/net/ipv6/mcast.c +++ b/net/ipv6/mcast.c @@ -172,6 +172,7 @@ int ipv6_sock_mc_join(struct sock *sk, int ifindex, const struct in6_addr *addr) mc_lst->next = NULL; mc_lst->addr = *addr; + rtnl_lock(); rcu_read_lock(); if (ifindex == 0) { struct rt6_info *rt; @@ -185,6 +186,7 @@ int ipv6_sock_mc_join(struct sock *sk, int ifindex, const struct in6_addr *addr) if (dev == NULL) { rcu_read_unlock(); + rtnl_unlock(); sock_kfree_s(sk, mc_lst, sizeof(*mc_lst)); return -ENODEV; } @@ -202,6 +204,7 @@ int ipv6_sock_mc_join(struct sock *sk, int ifindex, const struct in6_addr *addr) if (err) { rcu_read_unlock(); + rtnl_unlock(); sock_kfree_s(sk, mc_lst, sizeof(*mc_lst)); return err; } @@ -212,6 +215,7 @@ int ipv6_sock_mc_join(struct sock *sk, int ifindex, const struct in6_addr *addr) spin_unlock(&ipv6_sk_mc_lock); rcu_read_unlock(); + rtnl_unlock(); return 0; } @@ -229,6 +233,7 @@ int ipv6_sock_mc_drop(struct sock *sk, int ifindex, const struct in6_addr *addr) if (!ipv6_addr_is_multicast(addr)) return -EINVAL; + rtnl_lock(); spin_lock(&ipv6_sk_mc_lock); for (lnk = &np->ipv6_mc_list; (mc_lst = rcu_dereference_protected(*lnk, @@ -252,12 +257,15 @@ int ipv6_sock_mc_drop(struct sock *sk, int ifindex, const struct in6_addr *addr) } else (void) ip6_mc_leave_src(sk, mc_lst, NULL); rcu_read_unlock(); + rtnl_unlock(); + atomic_sub(sizeof(*mc_lst), &sk->sk_omem_alloc); kfree_rcu(mc_lst, rcu); return 0; } } spin_unlock(&ipv6_sk_mc_lock); + rtnl_unlock(); return -EADDRNOTAVAIL; } @@ -302,6 +310,7 @@ void ipv6_sock_mc_close(struct sock *sk) if (!rcu_access_pointer(np->ipv6_mc_list)) return; + rtnl_lock(); spin_lock(&ipv6_sk_mc_lock); while ((mc_lst = rcu_dereference_protected(np->ipv6_mc_list, lockdep_is_held(&ipv6_sk_mc_lock))) != NULL) { @@ -328,6 +337,7 @@ void ipv6_sock_mc_close(struct sock *sk) spin_lock(&ipv6_sk_mc_lock); } spin_unlock(&ipv6_sk_mc_lock); + rtnl_unlock(); } int ip6_mc_source(int add, int omode, struct sock *sk, @@ -845,6 +855,8 @@ int ipv6_dev_mc_inc(struct net_device *dev, const struct in6_addr *addr) struct ifmcaddr6 *mc; struct inet6_dev *idev; + ASSERT_RTNL(); + /* we need to take a reference on idev */ idev = in6_dev_get(dev); @@ -916,6 +928,8 @@ int __ipv6_dev_mc_dec(struct inet6_dev *idev, const struct in6_addr *addr) { struct ifmcaddr6 *ma, **map; + ASSERT_RTNL(); + write_lock_bh(&idev->lock); for (map = &idev->mc_list; (ma=*map) != NULL; map = &ma->next) { if (ipv6_addr_equal(&ma->mca_addr, addr)) { From eed4d839b0cdf9d84b0a9bc63de90fd5e1e886fb Mon Sep 17 00:00:00 2001 From: Guillaume Nault Date: Wed, 3 Sep 2014 14:12:55 +0200 Subject: [PATCH 088/101] l2tp: fix race while getting PMTU on PPP pseudo-wire Use dst_entry held by sk_dst_get() to retrieve tunnel's PMTU. The dst_mtu(__sk_dst_get(tunnel->sock)) call was racy. __sk_dst_get() could return NULL if tunnel->sock->sk_dst_cache was reset just before the call, thus making dst_mtu() dereference a NULL pointer: [ 1937.661598] BUG: unable to handle kernel NULL pointer dereference at 0000000000000020 [ 1937.664005] IP: [] pppol2tp_connect+0x33d/0x41e [l2tp_ppp] [ 1937.664005] PGD daf0c067 PUD d9f93067 PMD 0 [ 1937.664005] Oops: 0000 [#1] SMP [ 1937.664005] Modules linked in: l2tp_ppp l2tp_netlink l2tp_core ip6table_filter ip6_tables iptable_filter ip_tables ebtable_nat ebtables x_tables udp_tunnel pppoe pppox ppp_generic slhc deflate ctr twofish_generic twofish_x86_64_3way xts lrw gf128mul glue_helper twofish_x86_64 twofish_common blowfish_generic blowfish_x86_64 blowfish_common des_generic cbc xcbc rmd160 sha512_generic hmac crypto_null af_key xfrm_algo 8021q garp bridge stp llc tun atmtcp clip atm ext3 mbcache jbd iTCO_wdt coretemp kvm_intel iTCO_vendor_support kvm pcspkr evdev ehci_pci lpc_ich mfd_core i5400_edac edac_core i5k_amb shpchp button processor thermal_sys xfs crc32c_generic libcrc32c dm_mod usbhid sg hid sr_mod sd_mod cdrom crc_t10dif crct10dif_common ata_generic ahci ata_piix tg3 libahci libata uhci_hcd ptp ehci_hcd pps_core usbcore scsi_mod libphy usb_common [last unloaded: l2tp_core] [ 1937.664005] CPU: 0 PID: 10022 Comm: l2tpstress Tainted: G O 3.17.0-rc1 #1 [ 1937.664005] Hardware name: HP ProLiant DL160 G5, BIOS O12 08/22/2008 [ 1937.664005] task: ffff8800d8fda790 ti: ffff8800c43c4000 task.ti: ffff8800c43c4000 [ 1937.664005] RIP: 0010:[] [] pppol2tp_connect+0x33d/0x41e [l2tp_ppp] [ 1937.664005] RSP: 0018:ffff8800c43c7de8 EFLAGS: 00010282 [ 1937.664005] RAX: ffff8800da8a7240 RBX: ffff8800d8c64600 RCX: 000001c325a137b5 [ 1937.664005] RDX: 8c6318c6318c6320 RSI: 000000000000010c RDI: 0000000000000000 [ 1937.664005] RBP: ffff8800c43c7ea8 R08: 0000000000000000 R09: 0000000000000000 [ 1937.664005] R10: ffffffffa048e2c0 R11: ffff8800d8c64600 R12: ffff8800ca7a5000 [ 1937.664005] R13: ffff8800c439bf40 R14: 000000000000000c R15: 0000000000000009 [ 1937.664005] FS: 00007fd7f610f700(0000) GS:ffff88011a600000(0000) knlGS:0000000000000000 [ 1937.664005] CS: 0010 DS: 0000 ES: 0000 CR0: 000000008005003b [ 1937.664005] CR2: 0000000000000020 CR3: 00000000d9d75000 CR4: 00000000000027e0 [ 1937.664005] Stack: [ 1937.664005] ffffffffa049da80 ffff8800d8fda790 000000000000005b ffff880000000009 [ 1937.664005] ffff8800daf3f200 0000000000000003 ffff8800c43c7e48 ffffffff81109b57 [ 1937.664005] ffffffff81109b0e ffffffff8114c566 0000000000000000 0000000000000000 [ 1937.664005] Call Trace: [ 1937.664005] [] ? pppol2tp_connect+0x235/0x41e [l2tp_ppp] [ 1937.664005] [] ? might_fault+0x9e/0xa5 [ 1937.664005] [] ? might_fault+0x55/0xa5 [ 1937.664005] [] ? rcu_read_unlock+0x1c/0x26 [ 1937.664005] [] SYSC_connect+0x87/0xb1 [ 1937.664005] [] ? sysret_check+0x1b/0x56 [ 1937.664005] [] ? trace_hardirqs_on_caller+0x145/0x1a1 [ 1937.664005] [] ? trace_hardirqs_on_thunk+0x3a/0x3f [ 1937.664005] [] ? spin_lock+0x9/0xb [ 1937.664005] [] SyS_connect+0x9/0xb [ 1937.664005] [] system_call_fastpath+0x16/0x1b [ 1937.664005] Code: 10 2a 84 81 e8 65 76 bd e0 65 ff 0c 25 10 bb 00 00 4d 85 ed 74 37 48 8b 85 60 ff ff ff 48 8b 80 88 01 00 00 48 8b b8 10 02 00 00 <48> 8b 47 20 ff 50 20 85 c0 74 0f 83 e8 28 89 83 10 01 00 00 89 [ 1937.664005] RIP [] pppol2tp_connect+0x33d/0x41e [l2tp_ppp] [ 1937.664005] RSP [ 1937.664005] CR2: 0000000000000020 [ 1939.559375] ---[ end trace 82d44500f28f8708 ]--- Fixes: f34c4a35d879 ("l2tp: take PMTU from tunnel UDP socket") Signed-off-by: Guillaume Nault Acked-by: Eric Dumazet Signed-off-by: David S. Miller --- net/l2tp/l2tp_ppp.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/net/l2tp/l2tp_ppp.c b/net/l2tp/l2tp_ppp.c index 13752d96275e..b704a9356208 100644 --- a/net/l2tp/l2tp_ppp.c +++ b/net/l2tp/l2tp_ppp.c @@ -755,7 +755,8 @@ static int pppol2tp_connect(struct socket *sock, struct sockaddr *uservaddr, /* If PMTU discovery was enabled, use the MTU that was discovered */ dst = sk_dst_get(tunnel->sock); if (dst != NULL) { - u32 pmtu = dst_mtu(__sk_dst_get(tunnel->sock)); + u32 pmtu = dst_mtu(dst); + if (pmtu != 0) session->mtu = session->mru = pmtu - PPPOL2TP_HEADER_OVERHEAD; From 4357450af3422219d3f77bd54f7b9a8a40f193c9 Mon Sep 17 00:00:00 2001 From: Chen Gang Date: Wed, 3 Sep 2014 23:26:26 +0800 Subject: [PATCH 089/101] drivers/net/fddi/skfp/h/skfbi.h: Remove useless PCI_BASE_2ND macros They are use less, and may generate compiling warnings, so remove them (microblaze, arc, arm64, and unicore32 have already defined PCI_IOBASE). The related warnings (with allmodconfig under microblaze): CC [M] drivers/net/fddi/skfp/skfddi.o In file included from drivers/net/fddi/skfp/skfddi.c:95:0: drivers/net/fddi/skfp/h/skfbi.h:151:0: warning: "PCI_IOBASE" redefined #define PCI_IOBASE 0xffffff00L /* Bit 31..8: I/O Base address */ ^ In file included from include/linux/io.h:22:0, from include/linux/pci.h:31, from drivers/net/fddi/skfp/skfddi.c:82: ./arch/microblaze/include/asm/io.h:33:0: note: this is the location of the previous definition #define PCI_IOBASE ((void __iomem *)_IO_BASE) ^ Signed-off-by: Chen Gang Signed-off-by: David S. Miller --- drivers/net/fddi/skfp/h/skfbi.h | 5 ----- 1 file changed, 5 deletions(-) diff --git a/drivers/net/fddi/skfp/h/skfbi.h b/drivers/net/fddi/skfp/h/skfbi.h index c1ba26c06d73..3de2f0d15fe2 100644 --- a/drivers/net/fddi/skfp/h/skfbi.h +++ b/drivers/net/fddi/skfp/h/skfbi.h @@ -147,11 +147,6 @@ #define PCI_MEM64BIT (2<<1) /* Base addr anywhere in 64 Bit range */ #define PCI_MEMSPACE 0x00000001L /* Bit 0: Memory Space Indic. */ -/* PCI_BASE_2ND 32 bit 2nd Base address */ -#define PCI_IOBASE 0xffffff00L /* Bit 31..8: I/O Base address */ -#define PCI_IOSIZE 0x000000fcL /* Bit 7..2: I/O Size Requirements */ -#define PCI_IOSPACE 0x00000001L /* Bit 0: I/O Space Indicator */ - /* PCI_SUB_VID 16 bit Subsystem Vendor ID */ /* PCI_SUB_ID 16 bit Subsystem ID */ From c199105d154e029cd8c94cccd35bd073e64acc45 Mon Sep 17 00:00:00 2001 From: Willem de Bruijn Date: Wed, 3 Sep 2014 12:01:18 -0400 Subject: [PATCH 090/101] net-timestamp: only report sw timestamp if reporting bit is set The timestamping API has separate bits for generating and reporting timestamps. A software timestamp should only be reported for a packet when the packet has the relevant generation flag (SKBTX_..) set and the socket has reporting bit SOF_TIMESTAMPING_SOFTWARE set. The second check was accidentally removed. Reinstitute the original behavior. Tested: Without this patch, Documentation/networking/txtimestamp reports timestamps regardless of whether SOF_TIMESTAMPING_SOFTWARE is set. After the patch, it only reports them when the flag is set. Fixes: f24b9be5957b ("net-timestamp: extend SCM_TIMESTAMPING ancillary data struct") Signed-off-by: Willem de Bruijn Signed-off-by: David S. Miller --- include/net/sock.h | 4 +--- net/socket.c | 3 +-- 2 files changed, 2 insertions(+), 5 deletions(-) diff --git a/include/net/sock.h b/include/net/sock.h index 7f2ab72f321a..b9a5bd0ed9f3 100644 --- a/include/net/sock.h +++ b/include/net/sock.h @@ -2165,9 +2165,7 @@ sock_recv_timestamp(struct msghdr *msg, struct sock *sk, struct sk_buff *skb) */ if (sock_flag(sk, SOCK_RCVTSTAMP) || (sk->sk_tsflags & SOF_TIMESTAMPING_RX_SOFTWARE) || - (kt.tv64 && - (sk->sk_tsflags & SOF_TIMESTAMPING_SOFTWARE || - skb_shinfo(skb)->tx_flags & SKBTX_ANY_SW_TSTAMP)) || + (kt.tv64 && sk->sk_tsflags & SOF_TIMESTAMPING_SOFTWARE) || (hwtstamps->hwtstamp.tv64 && (sk->sk_tsflags & SOF_TIMESTAMPING_RAW_HARDWARE))) __sock_recv_timestamp(msg, sk, skb); diff --git a/net/socket.c b/net/socket.c index 95ee7d8682e7..4eb09b34b2d3 100644 --- a/net/socket.c +++ b/net/socket.c @@ -734,8 +734,7 @@ void __sock_recv_timestamp(struct msghdr *msg, struct sock *sk, } memset(&tss, 0, sizeof(tss)); - if ((sk->sk_tsflags & SOF_TIMESTAMPING_SOFTWARE || - skb_shinfo(skb)->tx_flags & SKBTX_ANY_SW_TSTAMP) && + if ((sk->sk_tsflags & SOF_TIMESTAMPING_SOFTWARE) && ktime_to_timespec_cond(skb->tstamp, tss.ts + 0)) empty = 0; if (shhwtstamps && From f24062b07dda89b0e24fa48e7bc3865a725f5ee6 Mon Sep 17 00:00:00 2001 From: Nicolas Dichtel Date: Wed, 3 Sep 2014 23:59:21 +0200 Subject: [PATCH 091/101] ipv6: fix a refcnt leak with peer addr There is no reason to take a refcnt before deleting the peer address route. It's done some lines below for the local prefix route because inet6_ifa_finish_destroy() will release it at the end. For the peer address route, we want to free it right now. This bug has been introduced by commit caeaba79009c ("ipv6: add support of peer address"). Signed-off-by: Nicolas Dichtel Acked-by: Hannes Frederic Sowa Signed-off-by: David S. Miller --- net/ipv6/addrconf.c | 7 ++----- 1 file changed, 2 insertions(+), 5 deletions(-) diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c index aa0e135b808c..ce761c7e6675 100644 --- a/net/ipv6/addrconf.c +++ b/net/ipv6/addrconf.c @@ -4772,11 +4772,8 @@ static void __ipv6_ifa_notify(int event, struct inet6_ifaddr *ifp) rt = rt6_lookup(dev_net(dev), &ifp->peer_addr, NULL, dev->ifindex, 1); - if (rt) { - dst_hold(&rt->dst); - if (ip6_del_rt(rt)) - dst_free(&rt->dst); - } + if (rt && ip6_del_rt(rt)) + dst_free(&rt->dst); } dst_hold(&ifp->rt->dst); From e7478dfc4656f4a739ed1b07cfd59c12f8eb112e Mon Sep 17 00:00:00 2001 From: Nicolas Dichtel Date: Wed, 3 Sep 2014 23:59:22 +0200 Subject: [PATCH 092/101] ipv6: use addrconf_get_prefix_route() to remove peer addr addrconf_get_prefix_route() ensures to get the right route in the right table. Signed-off-by: Nicolas Dichtel Acked-by: Hannes Frederic Sowa Signed-off-by: David S. Miller --- net/ipv6/addrconf.c | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-) diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c index ce761c7e6675..fc1fac2a0528 100644 --- a/net/ipv6/addrconf.c +++ b/net/ipv6/addrconf.c @@ -4768,10 +4768,9 @@ static void __ipv6_ifa_notify(int event, struct inet6_ifaddr *ifp) addrconf_leave_solict(ifp->idev, &ifp->addr); if (!ipv6_addr_any(&ifp->peer_addr)) { struct rt6_info *rt; - struct net_device *dev = ifp->idev->dev; - rt = rt6_lookup(dev_net(dev), &ifp->peer_addr, NULL, - dev->ifindex, 1); + rt = addrconf_get_prefix_route(&ifp->peer_addr, 128, + ifp->idev->dev, 0, 0); if (rt && ip6_del_rt(rt)) dst_free(&rt->dst); } From 84a59ca55f699d1d1fbfffd75445bcfe0c3daf06 Mon Sep 17 00:00:00 2001 From: Pablo Neira Ayuso Date: Thu, 4 Sep 2014 09:47:21 +0200 Subject: [PATCH 093/101] netfilter: add explicit Kconfig for NETFILTER_XT_NAT Paul Bolle reports that 'select NETFILTER_XT_NAT' from the IPV4 and IPV6 NAT tables becomes noop since there is no Kconfig switch for it. Add the Kconfig switch to resolve this problem. Fixes: 8993cf8 netfilter: move NAT Kconfig switches out of the iptables scope Reported-by: Paul Bolle Signed-off-by: Pablo Neira Ayuso Signed-off-by: David S. Miller --- net/netfilter/Kconfig | 8 ++++++++ 1 file changed, 8 insertions(+) diff --git a/net/netfilter/Kconfig b/net/netfilter/Kconfig index 4bef6eb7c40d..b5c1d3aadb41 100644 --- a/net/netfilter/Kconfig +++ b/net/netfilter/Kconfig @@ -766,6 +766,14 @@ config NETFILTER_XT_TARGET_MARK (e.g. when running oldconfig). It selects CONFIG_NETFILTER_XT_MARK (combined mark/MARK module). +config NETFILTER_XT_NAT + tristate '"SNAT and DNAT" targets support' + depends on NF_NAT + ---help--- + This option enables the SNAT and DNAT targets. + + To compile it as a module, choose M here. If unsure, say N. + config NETFILTER_XT_TARGET_NETMAP tristate '"NETMAP" target support' depends on NF_NAT From 98ea232cf63961fad734cc8c5e07e8915ec73073 Mon Sep 17 00:00:00 2001 From: Neil Horman Date: Thu, 4 Sep 2014 06:13:38 -0400 Subject: [PATCH 094/101] 3c59x: avoid panic in boomerang_start_xmit when finding page address: This bug was reported on a very old kernel (RHEL6, 2.6.32-491.el6): BUG: unable to handle kernel paging request at 00800000 IP: [] nommu_map_page+0x15/0x110 *pdpt = 000000003454f001 *pde = 000000003f03d067 Oops: 0000 [#1] SMP last sysfs file: /sys/devices/system/cpu/online Modules linked in: nfsd lockd nfs_acl auth_rpcgss sunrpc exportfs p4_clockmod ipv6 ppdev parport_pc parport microcode iTCO_wdt iTCO_vendor_support 3c59x mii dcdbas serio_raw snd_intel8x0 snd_ac97_codec ac97_bus snd_seq snd_seq_device snd_pcm snd_timer snd soundcore snd_page_alloc i2c_i801 sg lpc_ich mfd_core ext4 jbd2 mbcache sr_mod cdrom sd_mod crc_t10dif pata_acpi ata_generic ata_piix radeon ttm drm_kms_helper drm i2c_algo_bit i2c_core dm_mirror dm_region_hash dm_log dm_mod [last unloaded: mperf] Pid: 4219, comm: nfsd Not tainted 2.6.32-491.el6.i686 #1 Dell Computer Corporation OptiPlex GX240 /OptiPlex GX240 EIP: 0060:[] EFLAGS: 00010246 CPU: 0 EIP is at nommu_map_page+0x15/0x110 EAX: 00000000 EBX: c0a83480 ECX: 00000000 EDX: 00800000 ESI: 00000000 EDI: f70e7860 EBP: e2d09b54 ESP: e2d09b24 DS: 007b ES: 007b FS: 00d8 GS: 00e0 SS: 0068 Process nfsd (pid: 4219, ti=e2d08000 task=e2ceaaa0 task.ti=e2d08000) Stack: 00000056 00000000 0000000e c65efd38 00000020 00000296 00000206 00000206 <0> c050c850 c0a83480 e2cef154 00000001 e2d09ba8 f8fcd585 00000510 00000001 <0> 00000000 00000000 f5172200 f8fdac00 0039ef8c f5277020 f70e7860 00000510 Call Trace: [] ? page_address+0xd0/0xe0 [] ? boomerang_start_xmit+0x3b5/0x520 [3c59x] [] ? dev_hard_start_xmit+0xe5/0x400 [] ? ip6_output_finish+0x0/0xf0 [ipv6] [] ? sch_direct_xmit+0x113/0x180 [] ? nf_hook_slow+0x68/0x120 [] ? dev_queue_xmit+0x1b5/0x290 [] ? ip6_output_finish+0x6d/0xf0 [ipv6] [] ? ip6_xmit+0x3e8/0x490 [ipv6] [] ? inet6_csk_xmit+0x289/0x2f0 [ipv6] [] ? tcp_transmit_skb+0x431/0x7f0 [] ? __alloc_skb+0x4f/0x140 [] ? tcp_write_xmit+0x1c2/0xa50 [] ? __tcp_push_pending_frames+0x31/0xe0 [] ? tcp_sendpage+0x44a/0x4b0 [] ? tcp_sendpage+0x0/0x4b0 [] ? kernel_sendpage+0x4e/0x90 [] ? svc_send_common+0xc9/0x120 [sunrpc] [] ? svc_sendto+0x75/0x1f0 [sunrpc] [] ? _atomic_dec_and_lock+0x59/0x90 [] ? nfs3svc_encode_readres+0x0/0xc0 [nfsd] [] ? svc_authorise+0x2d/0x40 [sunrpc] [] ? nfs3svc_release_fhandle+0x0/0x10 [nfsd] [] ? svc_process_common+0xf1/0x5a0 [sunrpc] [] ? svc_tcp_sendto+0x36/0xa0 [sunrpc] [] ? svc_send+0x98/0xd0 [sunrpc] [] ? nfsd+0xac/0x140 [nfsd] [] ? complete+0x40/0x60 [] ? nfsd+0x0/0x140 [nfsd] [] ? kthread+0x7c/0xa0 [] ? kthread+0x0/0xa0 [] ? kernel_thread_helper+0x7/0x10 Code: 8d b6 00 00 00 00 eb f8 8d b4 26 00 00 00 00 8d bc 27 00 00 00 00 55 89 e5 83 ec 30 89 75 f8 31 f6 89 7d fc 89 c7 89 c8 89 5d f4 <8b> 1a 8b 4d 08 c1 eb 19 c1 e3 04 8b 9b c0 29 c7 c0 83 e3 fc 29 But the problem seems to still exist upstream. It seems on 32 bit kernels page_address() can reutrn a NULL value in some circumstances, and the pci_map_single api isn't prepared to handle that (on this system it results in a bogus pointer deference in nommu_map_page. The fix is pretty easy, if we convert the 3c59x driver to use the more convieient skb_frag_dma_map api we don't need to find the virtual address of the page at all, and page gets mapped to the hardware properly. Verified to fix the problem as described by the reporter. Applies to the net tree Change Notes: v2) Converted PCI_DMA_TODEVICE to DMA_TO_DEVICE. Thanks Dave! v3) Actually Run git commit after making changes to v2 :) Signed-off-by: Neil Horman CC: klassert@mathematik.tu-chemnitz.de CC: "David S. Miller" Signed-off-by: David S. Miller --- drivers/net/ethernet/3com/3c59x.c | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/drivers/net/ethernet/3com/3c59x.c b/drivers/net/ethernet/3com/3c59x.c index 059c7414e303..3fe45c705933 100644 --- a/drivers/net/ethernet/3com/3c59x.c +++ b/drivers/net/ethernet/3com/3c59x.c @@ -2177,10 +2177,10 @@ boomerang_start_xmit(struct sk_buff *skb, struct net_device *dev) skb_frag_t *frag = &skb_shinfo(skb)->frags[i]; vp->tx_ring[entry].frag[i+1].addr = - cpu_to_le32(pci_map_single( - VORTEX_PCI(vp), - (void *)skb_frag_address(frag), - skb_frag_size(frag), PCI_DMA_TODEVICE)); + cpu_to_le32(skb_frag_dma_map( + &VORTEX_PCI(vp)->dev, + frag, + frag->page_offset, frag->size, DMA_TO_DEVICE)); if (i == skb_shinfo(skb)->nr_frags-1) vp->tx_ring[entry].frag[i+1].length = cpu_to_le32(skb_frag_size(frag)|LAST_FRAG); From 6e9e5644378bdeebe09db9181534a03361701f4e Mon Sep 17 00:00:00 2001 From: Yaniv Rosner Date: Thu, 4 Sep 2014 13:26:00 +0300 Subject: [PATCH 095/101] bnx2x: Fix link problems for 1G SFP RJ45 module When 1G SFP RJ45 module is detected, driver must reset the Tx laser in order to prevent link issues. As part of change, the link_attr_sync was relocated from vars to params. Signed-off-by: Yaniv Rosner Signed-off-by: Yuval Mintz Signed-off-by: David S. Miller --- .../net/ethernet/broadcom/bnx2x/bnx2x_hsi.h | 7 +- .../net/ethernet/broadcom/bnx2x/bnx2x_link.c | 74 ++++++++++--------- .../net/ethernet/broadcom/bnx2x/bnx2x_link.h | 5 +- 3 files changed, 50 insertions(+), 36 deletions(-) diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_hsi.h b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_hsi.h index 5ba8af50c84f..c4daa068f1db 100644 --- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_hsi.h +++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_hsi.h @@ -2233,7 +2233,12 @@ struct shmem2_region { u32 reserved3; /* Offset 0x14C */ u32 reserved4; /* Offset 0x150 */ u32 link_attr_sync[PORT_MAX]; /* Offset 0x154 */ - #define LINK_ATTR_SYNC_KR2_ENABLE (1<<0) + #define LINK_ATTR_SYNC_KR2_ENABLE 0x00000001 + #define LINK_SFP_EEPROM_COMP_CODE_MASK 0x0000ff00 + #define LINK_SFP_EEPROM_COMP_CODE_SHIFT 8 + #define LINK_SFP_EEPROM_COMP_CODE_SR 0x00001000 + #define LINK_SFP_EEPROM_COMP_CODE_LR 0x00002000 + #define LINK_SFP_EEPROM_COMP_CODE_LRM 0x00004000 u32 reserved5[2]; u32 reserved6[PORT_MAX]; diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_link.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_link.c index 53fb4fa61b40..549549eaf580 100644 --- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_link.c +++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_link.c @@ -154,15 +154,22 @@ typedef int (*read_sfp_module_eeprom_func_p)(struct bnx2x_phy *phy, LINK_STATUS_LINK_PARTNER_ASYMMETRIC_PAUSE) #define SFP_EEPROM_CON_TYPE_ADDR 0x2 + #define SFP_EEPROM_CON_TYPE_VAL_UNKNOWN 0x0 #define SFP_EEPROM_CON_TYPE_VAL_LC 0x7 #define SFP_EEPROM_CON_TYPE_VAL_COPPER 0x21 #define SFP_EEPROM_CON_TYPE_VAL_RJ45 0x22 -#define SFP_EEPROM_COMP_CODE_ADDR 0x3 - #define SFP_EEPROM_COMP_CODE_SR_MASK (1<<4) - #define SFP_EEPROM_COMP_CODE_LR_MASK (1<<5) - #define SFP_EEPROM_COMP_CODE_LRM_MASK (1<<6) +#define SFP_EEPROM_10G_COMP_CODE_ADDR 0x3 + #define SFP_EEPROM_10G_COMP_CODE_SR_MASK (1<<4) + #define SFP_EEPROM_10G_COMP_CODE_LR_MASK (1<<5) + #define SFP_EEPROM_10G_COMP_CODE_LRM_MASK (1<<6) + +#define SFP_EEPROM_1G_COMP_CODE_ADDR 0x6 + #define SFP_EEPROM_1G_COMP_CODE_SX (1<<0) + #define SFP_EEPROM_1G_COMP_CODE_LX (1<<1) + #define SFP_EEPROM_1G_COMP_CODE_CX (1<<2) + #define SFP_EEPROM_1G_COMP_CODE_BASE_T (1<<3) #define SFP_EEPROM_FC_TX_TECH_ADDR 0x8 #define SFP_EEPROM_FC_TX_TECH_BITMASK_COPPER_PASSIVE 0x4 @@ -3633,8 +3640,8 @@ static void bnx2x_warpcore_enable_AN_KR2(struct bnx2x_phy *phy, reg_set[i].val); /* Start KR2 work-around timer which handles BCM8073 link-parner */ - vars->link_attr_sync |= LINK_ATTR_SYNC_KR2_ENABLE; - bnx2x_update_link_attr(params, vars->link_attr_sync); + params->link_attr_sync |= LINK_ATTR_SYNC_KR2_ENABLE; + bnx2x_update_link_attr(params, params->link_attr_sync); } static void bnx2x_disable_kr2(struct link_params *params, @@ -3666,8 +3673,8 @@ static void bnx2x_disable_kr2(struct link_params *params, for (i = 0; i < ARRAY_SIZE(reg_set); i++) bnx2x_cl45_write(bp, phy, reg_set[i].devad, reg_set[i].reg, reg_set[i].val); - vars->link_attr_sync &= ~LINK_ATTR_SYNC_KR2_ENABLE; - bnx2x_update_link_attr(params, vars->link_attr_sync); + params->link_attr_sync &= ~LINK_ATTR_SYNC_KR2_ENABLE; + bnx2x_update_link_attr(params, params->link_attr_sync); vars->check_kr2_recovery_cnt = CHECK_KR2_RECOVERY_CNT; } @@ -4810,7 +4817,7 @@ void bnx2x_link_status_update(struct link_params *params, ~FEATURE_CONFIG_PFC_ENABLED; if (SHMEM2_HAS(bp, link_attr_sync)) - vars->link_attr_sync = SHMEM2_RD(bp, + params->link_attr_sync = SHMEM2_RD(bp, link_attr_sync[params->port]); DP(NETIF_MSG_LINK, "link_status 0x%x phy_link_up %x int_mask 0x%x\n", @@ -8057,21 +8064,24 @@ static int bnx2x_get_edc_mode(struct bnx2x_phy *phy, { struct bnx2x *bp = params->bp; u32 sync_offset = 0, phy_idx, media_types; - u8 gport, val[2], check_limiting_mode = 0; + u8 val[SFP_EEPROM_FC_TX_TECH_ADDR + 1], check_limiting_mode = 0; *edc_mode = EDC_MODE_LIMITING; phy->media_type = ETH_PHY_UNSPECIFIED; /* First check for copper cable */ if (bnx2x_read_sfp_module_eeprom(phy, params, I2C_DEV_ADDR_A0, - SFP_EEPROM_CON_TYPE_ADDR, - 2, + 0, + SFP_EEPROM_FC_TX_TECH_ADDR + 1, (u8 *)val) != 0) { DP(NETIF_MSG_LINK, "Failed to read from SFP+ module EEPROM\n"); return -EINVAL; } - - switch (val[0]) { + params->link_attr_sync &= ~LINK_SFP_EEPROM_COMP_CODE_MASK; + params->link_attr_sync |= val[SFP_EEPROM_10G_COMP_CODE_ADDR] << + LINK_SFP_EEPROM_COMP_CODE_SHIFT; + bnx2x_update_link_attr(params, params->link_attr_sync); + switch (val[SFP_EEPROM_CON_TYPE_ADDR]) { case SFP_EEPROM_CON_TYPE_VAL_COPPER: { u8 copper_module_type; @@ -8079,17 +8089,7 @@ static int bnx2x_get_edc_mode(struct bnx2x_phy *phy, /* Check if its active cable (includes SFP+ module) * of passive cable */ - if (bnx2x_read_sfp_module_eeprom(phy, - params, - I2C_DEV_ADDR_A0, - SFP_EEPROM_FC_TX_TECH_ADDR, - 1, - &copper_module_type) != 0) { - DP(NETIF_MSG_LINK, - "Failed to read copper-cable-type" - " from SFP+ EEPROM\n"); - return -EINVAL; - } + copper_module_type = val[SFP_EEPROM_FC_TX_TECH_ADDR]; if (copper_module_type & SFP_EEPROM_FC_TX_TECH_BITMASK_COPPER_ACTIVE) { @@ -8115,16 +8115,18 @@ static int bnx2x_get_edc_mode(struct bnx2x_phy *phy, } break; } + case SFP_EEPROM_CON_TYPE_VAL_UNKNOWN: case SFP_EEPROM_CON_TYPE_VAL_LC: case SFP_EEPROM_CON_TYPE_VAL_RJ45: check_limiting_mode = 1; - if ((val[1] & (SFP_EEPROM_COMP_CODE_SR_MASK | - SFP_EEPROM_COMP_CODE_LR_MASK | - SFP_EEPROM_COMP_CODE_LRM_MASK)) == 0) { + if ((val[SFP_EEPROM_10G_COMP_CODE_ADDR] & + (SFP_EEPROM_10G_COMP_CODE_SR_MASK | + SFP_EEPROM_10G_COMP_CODE_LR_MASK | + SFP_EEPROM_10G_COMP_CODE_LRM_MASK)) == 0) { DP(NETIF_MSG_LINK, "1G SFP module detected\n"); - gport = params->port; phy->media_type = ETH_PHY_SFP_1G_FIBER; if (phy->req_line_speed != SPEED_1000) { + u8 gport = params->port; phy->req_line_speed = SPEED_1000; if (!CHIP_IS_E1x(bp)) { gport = BP_PATH(bp) + @@ -8134,6 +8136,12 @@ static int bnx2x_get_edc_mode(struct bnx2x_phy *phy, "Warning: Link speed was forced to 1000Mbps. Current SFP module in port %d is not compliant with 10G Ethernet\n", gport); } + if (val[SFP_EEPROM_1G_COMP_CODE_ADDR] & + SFP_EEPROM_1G_COMP_CODE_BASE_T) { + bnx2x_sfp_set_transmitter(params, phy, 0); + msleep(40); + bnx2x_sfp_set_transmitter(params, phy, 1); + } } else { int idx, cfg_idx = 0; DP(NETIF_MSG_LINK, "10G Optic module detected\n"); @@ -8149,7 +8157,7 @@ static int bnx2x_get_edc_mode(struct bnx2x_phy *phy, break; default: DP(NETIF_MSG_LINK, "Unable to determine module type 0x%x !!!\n", - val[0]); + val[SFP_EEPROM_CON_TYPE_ADDR]); return -EINVAL; } sync_offset = params->shmem_base + @@ -13507,7 +13515,7 @@ static void bnx2x_check_kr2_wa(struct link_params *params, sigdet = bnx2x_warpcore_get_sigdet(phy, params); if (!sigdet) { - if (!(vars->link_attr_sync & LINK_ATTR_SYNC_KR2_ENABLE)) { + if (!(params->link_attr_sync & LINK_ATTR_SYNC_KR2_ENABLE)) { bnx2x_kr2_recovery(params, vars, phy); DP(NETIF_MSG_LINK, "No sigdet\n"); } @@ -13525,7 +13533,7 @@ static void bnx2x_check_kr2_wa(struct link_params *params, /* CL73 has not begun yet */ if (base_page == 0) { - if (!(vars->link_attr_sync & LINK_ATTR_SYNC_KR2_ENABLE)) { + if (!(params->link_attr_sync & LINK_ATTR_SYNC_KR2_ENABLE)) { bnx2x_kr2_recovery(params, vars, phy); DP(NETIF_MSG_LINK, "No BP\n"); } @@ -13541,7 +13549,7 @@ static void bnx2x_check_kr2_wa(struct link_params *params, ((next_page & 0xe0) == 0x20)))); /* In case KR2 is already disabled, check if we need to re-enable it */ - if (!(vars->link_attr_sync & LINK_ATTR_SYNC_KR2_ENABLE)) { + if (!(params->link_attr_sync & LINK_ATTR_SYNC_KR2_ENABLE)) { if (!not_kr2_device) { DP(NETIF_MSG_LINK, "BP=0x%x, NP=0x%x\n", base_page, next_page); diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_link.h b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_link.h index 389f5f8cb0a3..d9cce4c3899b 100644 --- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_link.h +++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_link.h @@ -323,6 +323,9 @@ struct link_params { #define LINK_FLAGS_INT_DISABLED (1<<0) #define PHY_INITIALIZED (1<<1) u32 lfa_base; + + /* The same definitions as the shmem2 parameter */ + u32 link_attr_sync; }; /* Output parameters */ @@ -364,8 +367,6 @@ struct link_vars { u8 rx_tx_asic_rst; u8 turn_to_run_wc_rt; u16 rsrv2; - /* The same definitions as the shmem2 parameter */ - u32 link_attr_sync; }; /***********************************************************/ From e793c0f70e9bdf4a2e71c151a1a3cf85c4db92ad Mon Sep 17 00:00:00 2001 From: Masanari Iida Date: Thu, 4 Sep 2014 23:44:36 +0900 Subject: [PATCH 096/101] net: treewide: Fix typo found in DocBook/networking.xml This patch fix spelling typo found in DocBook/networking.xml. It is because the neworking.xml is generated from comments in the source, I have to fix typo in comments within the source. Signed-off-by: Masanari Iida Acked-by: Randy Dunlap Signed-off-by: David S. Miller --- include/linux/netdevice.h | 4 ++-- include/net/wimax.h | 2 +- include/trace/events/irq.h | 4 ++-- net/core/datagram.c | 2 +- net/core/gen_estimator.c | 2 +- net/core/gen_stats.c | 2 +- net/core/skbuff.c | 4 ++-- net/core/sock.c | 4 ++-- net/socket.c | 2 +- 9 files changed, 13 insertions(+), 13 deletions(-) diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 38377392d082..c8e388e5fccc 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -3176,7 +3176,7 @@ static inline int __dev_uc_sync(struct net_device *dev, } /** - * __dev_uc_unsync - Remove synchonized addresses from device + * __dev_uc_unsync - Remove synchronized addresses from device * @dev: device to sync * @unsync: function to call if address should be removed * @@ -3220,7 +3220,7 @@ static inline int __dev_mc_sync(struct net_device *dev, } /** - * __dev_mc_unsync - Remove synchonized addresses from device + * __dev_mc_unsync - Remove synchronized addresses from device * @dev: device to sync * @unsync: function to call if address should be removed * diff --git a/include/net/wimax.h b/include/net/wimax.h index e52ef5357e08..c52b68577cb0 100644 --- a/include/net/wimax.h +++ b/include/net/wimax.h @@ -290,7 +290,7 @@ struct wimax_dev; * This operation has to be synchronous, and return only when the * reset is complete. In case of having had to resort to bus/cold * reset implying a device disconnection, the call is allowed to - * return inmediately. + * return immediately. * NOTE: wimax_dev->mutex is NOT locked when this op is being * called; however, wimax_dev->mutex_reset IS locked to ensure * serialization of calls to wimax_reset(). diff --git a/include/trace/events/irq.h b/include/trace/events/irq.h index 1c09820df585..3608bebd3d9c 100644 --- a/include/trace/events/irq.h +++ b/include/trace/events/irq.h @@ -107,7 +107,7 @@ DECLARE_EVENT_CLASS(softirq, * @vec_nr: softirq vector number * * When used in combination with the softirq_exit tracepoint - * we can determine the softirq handler runtine. + * we can determine the softirq handler routine. */ DEFINE_EVENT(softirq, softirq_entry, @@ -121,7 +121,7 @@ DEFINE_EVENT(softirq, softirq_entry, * @vec_nr: softirq vector number * * When used in combination with the softirq_entry tracepoint - * we can determine the softirq handler runtine. + * we can determine the softirq handler routine. */ DEFINE_EVENT(softirq, softirq_exit, diff --git a/net/core/datagram.c b/net/core/datagram.c index 488dd1a825c0..fdbc9a81d4c2 100644 --- a/net/core/datagram.c +++ b/net/core/datagram.c @@ -775,7 +775,7 @@ __sum16 __skb_checksum_complete(struct sk_buff *skb) EXPORT_SYMBOL(__skb_checksum_complete); /** - * skb_copy_and_csum_datagram_iovec - Copy and checkum skb to user iovec. + * skb_copy_and_csum_datagram_iovec - Copy and checksum skb to user iovec. * @skb: skbuff * @hlen: hardware length * @iov: io vector diff --git a/net/core/gen_estimator.c b/net/core/gen_estimator.c index 6b5b6e7013ca..9d33dfffca19 100644 --- a/net/core/gen_estimator.c +++ b/net/core/gen_estimator.c @@ -197,7 +197,7 @@ struct gen_estimator *gen_find_node(const struct gnet_stats_basic_packed *bstats * as destination. A new timer with the interval specified in the * configuration TLV is created. Upon each interval, the latest statistics * will be read from &bstats and the estimated rate will be stored in - * &rate_est with the statistics lock grabed during this period. + * &rate_est with the statistics lock grabbed during this period. * * Returns 0 on success or a negative error code. * diff --git a/net/core/gen_stats.c b/net/core/gen_stats.c index 9d3d9e78397b..2ddbce4cce14 100644 --- a/net/core/gen_stats.c +++ b/net/core/gen_stats.c @@ -206,7 +206,7 @@ EXPORT_SYMBOL(gnet_stats_copy_queue); * @st: application specific statistics data * @len: length of data * - * Appends the application sepecific statistics to the top level TLV created by + * Appends the application specific statistics to the top level TLV created by * gnet_stats_start_copy() and remembers the data for XSTATS if the dumping * handle is in backward compatibility mode. * diff --git a/net/core/skbuff.c b/net/core/skbuff.c index 163b673f9e62..da1378a3e2c7 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -2647,7 +2647,7 @@ EXPORT_SYMBOL(skb_prepare_seq_read); * skb_seq_read() will return the remaining part of the block. * * Note 1: The size of each block of data returned can be arbitrary, - * this limitation is the cost for zerocopy seqeuental + * this limitation is the cost for zerocopy sequential * reads of potentially non linear data. * * Note 2: Fragment lists within fragments are not implemented @@ -2781,7 +2781,7 @@ EXPORT_SYMBOL(skb_find_text); /** * skb_append_datato_frags - append the user data to a skb * @sk: sock structure - * @skb: skb structure to be appened with user data. + * @skb: skb structure to be appended with user data. * @getfrag: call back function to be used for getting the user data * @from: pointer to user message iov * @length: length of the iov message diff --git a/net/core/sock.c b/net/core/sock.c index 29870571c42f..d372b4bd3f99 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -166,7 +166,7 @@ EXPORT_SYMBOL(sk_ns_capable); /** * sk_capable - Socket global capability test * @sk: Socket to use a capability on or through - * @cap: The global capbility to use + * @cap: The global capability to use * * Test to see if the opener of the socket had when the socket was * created and the current process has the capability @cap in all user @@ -183,7 +183,7 @@ EXPORT_SYMBOL(sk_capable); * @sk: Socket to use a capability on or through * @cap: The capability to use * - * Test to see if the opener of the socket had when the socke was created + * Test to see if the opener of the socket had when the socket was created * and the current process has the capability @cap over the network namespace * the socket is a member of. */ diff --git a/net/socket.c b/net/socket.c index 4eb09b34b2d3..2e2586e2dee1 100644 --- a/net/socket.c +++ b/net/socket.c @@ -2601,7 +2601,7 @@ SYSCALL_DEFINE2(socketcall, int, call, unsigned long __user *, args) * * This function is called by a protocol handler that wants to * advertise its address family, and have it linked into the - * socket interface. The value ops->family coresponds to the + * socket interface. The value ops->family corresponds to the * socket system call protocol family. */ int sock_register(const struct net_proto_family *ops) From c99d667e852766afc755fa4430be64bb94e5ea1c Mon Sep 17 00:00:00 2001 From: Anish Bhatt Date: Thu, 4 Sep 2014 17:12:57 -0700 Subject: [PATCH 097/101] cnic : Cleanup CONFIG_IPV6 & VLAN check The cnic module needs to ensure that if ipv6 support is compiled as a module, then the cnic module cannot be compiled as built-in as it depends on ipv6. Made this check cleaner via Kconfig Use simpler IS_ENABLED for CONFIG_VLAN_8021Q check Signed-off-by: Anish Bhatt Acked-by: Michael Chan Signed-off-by: David S. Miller --- drivers/net/ethernet/broadcom/Kconfig | 2 +- drivers/net/ethernet/broadcom/cnic.c | 4 ++-- 2 files changed, 3 insertions(+), 3 deletions(-) diff --git a/drivers/net/ethernet/broadcom/Kconfig b/drivers/net/ethernet/broadcom/Kconfig index 7dcfb19a31c8..d8d07a818b89 100644 --- a/drivers/net/ethernet/broadcom/Kconfig +++ b/drivers/net/ethernet/broadcom/Kconfig @@ -84,7 +84,7 @@ config BNX2 config CNIC tristate "QLogic CNIC support" - depends on PCI + depends on PCI && (IPV6 || IPV6=n) select BNX2 select UIO ---help--- diff --git a/drivers/net/ethernet/broadcom/cnic.c b/drivers/net/ethernet/broadcom/cnic.c index 27861a6c7ca5..a6a9f284c8dd 100644 --- a/drivers/net/ethernet/broadcom/cnic.c +++ b/drivers/net/ethernet/broadcom/cnic.c @@ -31,7 +31,7 @@ #include #include #include -#if defined(CONFIG_VLAN_8021Q) || defined(CONFIG_VLAN_8021Q_MODULE) +#if IS_ENABLED(CONFIG_VLAN_8021Q) #define BCM_VLAN 1 #endif #include @@ -3685,7 +3685,7 @@ static int cnic_get_v4_route(struct sockaddr_in *dst_addr, static int cnic_get_v6_route(struct sockaddr_in6 *dst_addr, struct dst_entry **dst) { -#if defined(CONFIG_IPV6) || (defined(CONFIG_IPV6_MODULE) && defined(MODULE)) +#if IS_ENABLED(CONFIG_IPV6) struct flowi6 fl6; memset(&fl6, 0, sizeof(fl6)); From e1743a16a043f3d6b707730e46ba33ca931fb553 Mon Sep 17 00:00:00 2001 From: Daniel Hellstrom Date: Fri, 5 Sep 2014 13:13:48 +0200 Subject: [PATCH 098/101] greth: moved TX ring cleaning to NAPI rx poll func This patch does not affect the 10/100 GRETH MAC. Before all GBit GRETH TX descriptor ring cleaning was done in start_xmit(), when descriptor list became full it activated TX interrupt to start the NAPI rx poll function to do TX ring cleaning. With this patch the TX descriptor ring is always cleaned from the NAPI rx poll function, triggered via TX or RX interrupt. Otherwise we could end up in TX frames being sent but not reported to the stack being sent. On the 10/100 GRETH this is not an issue since the SKB is copied&aligned into private buffers so that the SKB can be freed directly on start_xmit() Signed-off-by: Daniel Hellstrom Signed-off-by: David S. Miller --- drivers/net/ethernet/aeroflex/greth.c | 86 +++++++++++++++------------ drivers/net/ethernet/aeroflex/greth.h | 2 +- 2 files changed, 49 insertions(+), 39 deletions(-) diff --git a/drivers/net/ethernet/aeroflex/greth.c b/drivers/net/ethernet/aeroflex/greth.c index 23578dfee249..3005155e412b 100644 --- a/drivers/net/ethernet/aeroflex/greth.c +++ b/drivers/net/ethernet/aeroflex/greth.c @@ -123,6 +123,12 @@ static inline void greth_enable_tx(struct greth_private *greth) GRETH_REGORIN(greth->regs->control, GRETH_TXEN); } +static inline void greth_enable_tx_and_irq(struct greth_private *greth) +{ + wmb(); /* BDs must been written to memory before enabling TX */ + GRETH_REGORIN(greth->regs->control, GRETH_TXEN | GRETH_TXI); +} + static inline void greth_disable_tx(struct greth_private *greth) { GRETH_REGANDIN(greth->regs->control, ~GRETH_TXEN); @@ -447,29 +453,30 @@ out: return err; } +static inline u16 greth_num_free_bds(u16 tx_last, u16 tx_next) +{ + if (tx_next < tx_last) + return (tx_last - tx_next) - 1; + else + return GRETH_TXBD_NUM - (tx_next - tx_last) - 1; +} static netdev_tx_t greth_start_xmit_gbit(struct sk_buff *skb, struct net_device *dev) { struct greth_private *greth = netdev_priv(dev); struct greth_bd *bdp; - u32 status = 0, dma_addr, ctrl; + u32 status, dma_addr; int curr_tx, nr_frags, i, err = NETDEV_TX_OK; unsigned long flags; + u16 tx_last; nr_frags = skb_shinfo(skb)->nr_frags; + tx_last = greth->tx_last; + rmb(); /* tx_last is updated by the poll task */ - /* Clean TX Ring */ - greth_clean_tx_gbit(dev); - - if (greth->tx_free < nr_frags + 1) { - spin_lock_irqsave(&greth->devlock, flags);/*save from poll/irq*/ - ctrl = GRETH_REGLOAD(greth->regs->control); - /* Enable TX IRQ only if not already in poll() routine */ - if (ctrl & GRETH_RXI) - GRETH_REGSAVE(greth->regs->control, ctrl | GRETH_TXI); + if (greth_num_free_bds(tx_last, greth->tx_next) < nr_frags + 1) { netif_stop_queue(dev); - spin_unlock_irqrestore(&greth->devlock, flags); err = NETDEV_TX_BUSY; goto out; } @@ -488,6 +495,8 @@ greth_start_xmit_gbit(struct sk_buff *skb, struct net_device *dev) /* Linear buf */ if (nr_frags != 0) status = GRETH_TXBD_MORE; + else + status = GRETH_BD_IE; if (skb->ip_summed == CHECKSUM_PARTIAL) status |= GRETH_TXBD_CSALL; @@ -545,14 +554,12 @@ greth_start_xmit_gbit(struct sk_buff *skb, struct net_device *dev) /* Enable the descriptor chain by enabling the first descriptor */ bdp = greth->tx_bd_base + greth->tx_next; - greth_write_bd(&bdp->stat, greth_read_bd(&bdp->stat) | GRETH_BD_EN); - greth->tx_next = curr_tx; - greth->tx_free -= nr_frags + 1; - - wmb(); + greth_write_bd(&bdp->stat, + greth_read_bd(&bdp->stat) | GRETH_BD_EN); spin_lock_irqsave(&greth->devlock, flags); /*save from poll/irq*/ - greth_enable_tx(greth); + greth->tx_next = curr_tx; + greth_enable_tx_and_irq(greth); spin_unlock_irqrestore(&greth->devlock, flags); return NETDEV_TX_OK; @@ -648,7 +655,6 @@ static void greth_clean_tx(struct net_device *dev) if (greth->tx_free > 0) { netif_wake_queue(dev); } - } static inline void greth_update_tx_stats(struct net_device *dev, u32 stat) @@ -670,20 +676,22 @@ static void greth_clean_tx_gbit(struct net_device *dev) { struct greth_private *greth; struct greth_bd *bdp, *bdp_last_frag; - struct sk_buff *skb; + struct sk_buff *skb = NULL; u32 stat; int nr_frags, i; + u16 tx_last; greth = netdev_priv(dev); + tx_last = greth->tx_last; - while (greth->tx_free < GRETH_TXBD_NUM) { + while (tx_last != greth->tx_next) { - skb = greth->tx_skbuff[greth->tx_last]; + skb = greth->tx_skbuff[tx_last]; nr_frags = skb_shinfo(skb)->nr_frags; /* We only clean fully completed SKBs */ - bdp_last_frag = greth->tx_bd_base + SKIP_TX(greth->tx_last, nr_frags); + bdp_last_frag = greth->tx_bd_base + SKIP_TX(tx_last, nr_frags); GRETH_REGSAVE(greth->regs->status, GRETH_INT_TE | GRETH_INT_TX); mb(); @@ -692,14 +700,14 @@ static void greth_clean_tx_gbit(struct net_device *dev) if (stat & GRETH_BD_EN) break; - greth->tx_skbuff[greth->tx_last] = NULL; + greth->tx_skbuff[tx_last] = NULL; greth_update_tx_stats(dev, stat); dev->stats.tx_bytes += skb->len; - bdp = greth->tx_bd_base + greth->tx_last; + bdp = greth->tx_bd_base + tx_last; - greth->tx_last = NEXT_TX(greth->tx_last); + tx_last = NEXT_TX(tx_last); dma_unmap_single(greth->dev, greth_read_bd(&bdp->addr), @@ -708,21 +716,26 @@ static void greth_clean_tx_gbit(struct net_device *dev) for (i = 0; i < nr_frags; i++) { skb_frag_t *frag = &skb_shinfo(skb)->frags[i]; - bdp = greth->tx_bd_base + greth->tx_last; + bdp = greth->tx_bd_base + tx_last; dma_unmap_page(greth->dev, greth_read_bd(&bdp->addr), skb_frag_size(frag), DMA_TO_DEVICE); - greth->tx_last = NEXT_TX(greth->tx_last); + tx_last = NEXT_TX(tx_last); } - greth->tx_free += nr_frags+1; dev_kfree_skb(skb); } + if (skb) { /* skb is set only if the above while loop was entered */ + wmb(); + greth->tx_last = tx_last; - if (netif_queue_stopped(dev) && (greth->tx_free > (MAX_SKB_FRAGS+1))) - netif_wake_queue(dev); + if (netif_queue_stopped(dev) && + (greth_num_free_bds(tx_last, greth->tx_next) > + (MAX_SKB_FRAGS+1))) + netif_wake_queue(dev); + } } static int greth_rx(struct net_device *dev, int limit) @@ -965,16 +978,12 @@ static int greth_poll(struct napi_struct *napi, int budget) greth = container_of(napi, struct greth_private, napi); restart_txrx_poll: - if (netif_queue_stopped(greth->netdev)) { - if (greth->gbit_mac) - greth_clean_tx_gbit(greth->netdev); - else - greth_clean_tx(greth->netdev); - } - if (greth->gbit_mac) { + greth_clean_tx_gbit(greth->netdev); work_done += greth_rx_gbit(greth->netdev, budget - work_done); } else { + if (netif_queue_stopped(greth->netdev)) + greth_clean_tx(greth->netdev); work_done += greth_rx(greth->netdev, budget - work_done); } @@ -983,7 +992,8 @@ restart_txrx_poll: spin_lock_irqsave(&greth->devlock, flags); ctrl = GRETH_REGLOAD(greth->regs->control); - if (netif_queue_stopped(greth->netdev)) { + if ((greth->gbit_mac && (greth->tx_last != greth->tx_next)) || + (!greth->gbit_mac && netif_queue_stopped(greth->netdev))) { GRETH_REGSAVE(greth->regs->control, ctrl | GRETH_TXI | GRETH_RXI); mask = GRETH_INT_RX | GRETH_INT_RE | diff --git a/drivers/net/ethernet/aeroflex/greth.h b/drivers/net/ethernet/aeroflex/greth.h index 232a622a85b7..ae16ac94daf8 100644 --- a/drivers/net/ethernet/aeroflex/greth.h +++ b/drivers/net/ethernet/aeroflex/greth.h @@ -107,7 +107,7 @@ struct greth_private { u16 tx_next; u16 tx_last; - u16 tx_free; + u16 tx_free; /* only used on 10/100Mbit */ u16 rx_cur; struct greth_regs *regs; /* Address of controller registers. */ From 6026510896adfa0db5ed76a6d6d1cd1602b29208 Mon Sep 17 00:00:00 2001 From: "Lendacky, Thomas" Date: Fri, 5 Sep 2014 18:02:30 -0500 Subject: [PATCH 099/101] amd-xgbe: Treat certain counter registers as 64 bit Even if the management counters are configured to be 32 bit register values, the [rt]xoctetcount_gb and [rt]xoctetcount_g counters are always 64 bit counter registers. Since they are not being treated as 64 bit values, these statistics are being reported incorrectly (ifconfig, ethtool, etc.). Update the routines used to read the registers to access the "hi" register (an offset of 4 from the "lo" register) to create a 64 bit value for these 64 bit counters. Signed-off-by: Tom Lendacky Signed-off-by: David S. Miller --- drivers/net/ethernet/amd/xgbe/xgbe-dev.c | 190 +++++++++++++---------- 1 file changed, 108 insertions(+), 82 deletions(-) diff --git a/drivers/net/ethernet/amd/xgbe/xgbe-dev.c b/drivers/net/ethernet/amd/xgbe/xgbe-dev.c index 6d0207eac265..f3d04f19ebd4 100644 --- a/drivers/net/ethernet/amd/xgbe/xgbe-dev.c +++ b/drivers/net/ethernet/amd/xgbe/xgbe-dev.c @@ -1954,6 +1954,32 @@ static void xgbe_config_vlan_support(struct xgbe_prv_data *pdata) xgbe_disable_rx_vlan_stripping(pdata); } +static u64 xgbe_mmc_read(struct xgbe_prv_data *pdata, unsigned int reg_lo) +{ + bool read_hi; + u64 val; + + switch (reg_lo) { + /* These registers are always 64 bit */ + case MMC_TXOCTETCOUNT_GB_LO: + case MMC_TXOCTETCOUNT_G_LO: + case MMC_RXOCTETCOUNT_GB_LO: + case MMC_RXOCTETCOUNT_G_LO: + read_hi = true; + break; + + default: + read_hi = false; + }; + + val = XGMAC_IOREAD(pdata, reg_lo); + + if (read_hi) + val |= ((u64)XGMAC_IOREAD(pdata, reg_lo + 4) << 32); + + return val; +} + static void xgbe_tx_mmc_int(struct xgbe_prv_data *pdata) { struct xgbe_mmc_stats *stats = &pdata->mmc_stats; @@ -1961,75 +1987,75 @@ static void xgbe_tx_mmc_int(struct xgbe_prv_data *pdata) if (XGMAC_GET_BITS(mmc_isr, MMC_TISR, TXOCTETCOUNT_GB)) stats->txoctetcount_gb += - XGMAC_IOREAD(pdata, MMC_TXOCTETCOUNT_GB_LO); + xgbe_mmc_read(pdata, MMC_TXOCTETCOUNT_GB_LO); if (XGMAC_GET_BITS(mmc_isr, MMC_TISR, TXFRAMECOUNT_GB)) stats->txframecount_gb += - XGMAC_IOREAD(pdata, MMC_TXFRAMECOUNT_GB_LO); + xgbe_mmc_read(pdata, MMC_TXFRAMECOUNT_GB_LO); if (XGMAC_GET_BITS(mmc_isr, MMC_TISR, TXBROADCASTFRAMES_G)) stats->txbroadcastframes_g += - XGMAC_IOREAD(pdata, MMC_TXBROADCASTFRAMES_G_LO); + xgbe_mmc_read(pdata, MMC_TXBROADCASTFRAMES_G_LO); if (XGMAC_GET_BITS(mmc_isr, MMC_TISR, TXMULTICASTFRAMES_G)) stats->txmulticastframes_g += - XGMAC_IOREAD(pdata, MMC_TXMULTICASTFRAMES_G_LO); + xgbe_mmc_read(pdata, MMC_TXMULTICASTFRAMES_G_LO); if (XGMAC_GET_BITS(mmc_isr, MMC_TISR, TX64OCTETS_GB)) stats->tx64octets_gb += - XGMAC_IOREAD(pdata, MMC_TX64OCTETS_GB_LO); + xgbe_mmc_read(pdata, MMC_TX64OCTETS_GB_LO); if (XGMAC_GET_BITS(mmc_isr, MMC_TISR, TX65TO127OCTETS_GB)) stats->tx65to127octets_gb += - XGMAC_IOREAD(pdata, MMC_TX65TO127OCTETS_GB_LO); + xgbe_mmc_read(pdata, MMC_TX65TO127OCTETS_GB_LO); if (XGMAC_GET_BITS(mmc_isr, MMC_TISR, TX128TO255OCTETS_GB)) stats->tx128to255octets_gb += - XGMAC_IOREAD(pdata, MMC_TX128TO255OCTETS_GB_LO); + xgbe_mmc_read(pdata, MMC_TX128TO255OCTETS_GB_LO); if (XGMAC_GET_BITS(mmc_isr, MMC_TISR, TX256TO511OCTETS_GB)) stats->tx256to511octets_gb += - XGMAC_IOREAD(pdata, MMC_TX256TO511OCTETS_GB_LO); + xgbe_mmc_read(pdata, MMC_TX256TO511OCTETS_GB_LO); if (XGMAC_GET_BITS(mmc_isr, MMC_TISR, TX512TO1023OCTETS_GB)) stats->tx512to1023octets_gb += - XGMAC_IOREAD(pdata, MMC_TX512TO1023OCTETS_GB_LO); + xgbe_mmc_read(pdata, MMC_TX512TO1023OCTETS_GB_LO); if (XGMAC_GET_BITS(mmc_isr, MMC_TISR, TX1024TOMAXOCTETS_GB)) stats->tx1024tomaxoctets_gb += - XGMAC_IOREAD(pdata, MMC_TX1024TOMAXOCTETS_GB_LO); + xgbe_mmc_read(pdata, MMC_TX1024TOMAXOCTETS_GB_LO); if (XGMAC_GET_BITS(mmc_isr, MMC_TISR, TXUNICASTFRAMES_GB)) stats->txunicastframes_gb += - XGMAC_IOREAD(pdata, MMC_TXUNICASTFRAMES_GB_LO); + xgbe_mmc_read(pdata, MMC_TXUNICASTFRAMES_GB_LO); if (XGMAC_GET_BITS(mmc_isr, MMC_TISR, TXMULTICASTFRAMES_GB)) stats->txmulticastframes_gb += - XGMAC_IOREAD(pdata, MMC_TXMULTICASTFRAMES_GB_LO); + xgbe_mmc_read(pdata, MMC_TXMULTICASTFRAMES_GB_LO); if (XGMAC_GET_BITS(mmc_isr, MMC_TISR, TXBROADCASTFRAMES_GB)) stats->txbroadcastframes_g += - XGMAC_IOREAD(pdata, MMC_TXBROADCASTFRAMES_GB_LO); + xgbe_mmc_read(pdata, MMC_TXBROADCASTFRAMES_GB_LO); if (XGMAC_GET_BITS(mmc_isr, MMC_TISR, TXUNDERFLOWERROR)) stats->txunderflowerror += - XGMAC_IOREAD(pdata, MMC_TXUNDERFLOWERROR_LO); + xgbe_mmc_read(pdata, MMC_TXUNDERFLOWERROR_LO); if (XGMAC_GET_BITS(mmc_isr, MMC_TISR, TXOCTETCOUNT_G)) stats->txoctetcount_g += - XGMAC_IOREAD(pdata, MMC_TXOCTETCOUNT_G_LO); + xgbe_mmc_read(pdata, MMC_TXOCTETCOUNT_G_LO); if (XGMAC_GET_BITS(mmc_isr, MMC_TISR, TXFRAMECOUNT_G)) stats->txframecount_g += - XGMAC_IOREAD(pdata, MMC_TXFRAMECOUNT_G_LO); + xgbe_mmc_read(pdata, MMC_TXFRAMECOUNT_G_LO); if (XGMAC_GET_BITS(mmc_isr, MMC_TISR, TXPAUSEFRAMES)) stats->txpauseframes += - XGMAC_IOREAD(pdata, MMC_TXPAUSEFRAMES_LO); + xgbe_mmc_read(pdata, MMC_TXPAUSEFRAMES_LO); if (XGMAC_GET_BITS(mmc_isr, MMC_TISR, TXVLANFRAMES_G)) stats->txvlanframes_g += - XGMAC_IOREAD(pdata, MMC_TXVLANFRAMES_G_LO); + xgbe_mmc_read(pdata, MMC_TXVLANFRAMES_G_LO); } static void xgbe_rx_mmc_int(struct xgbe_prv_data *pdata) @@ -2039,95 +2065,95 @@ static void xgbe_rx_mmc_int(struct xgbe_prv_data *pdata) if (XGMAC_GET_BITS(mmc_isr, MMC_RISR, RXFRAMECOUNT_GB)) stats->rxframecount_gb += - XGMAC_IOREAD(pdata, MMC_RXFRAMECOUNT_GB_LO); + xgbe_mmc_read(pdata, MMC_RXFRAMECOUNT_GB_LO); if (XGMAC_GET_BITS(mmc_isr, MMC_RISR, RXOCTETCOUNT_GB)) stats->rxoctetcount_gb += - XGMAC_IOREAD(pdata, MMC_RXOCTETCOUNT_GB_LO); + xgbe_mmc_read(pdata, MMC_RXOCTETCOUNT_GB_LO); if (XGMAC_GET_BITS(mmc_isr, MMC_RISR, RXOCTETCOUNT_G)) stats->rxoctetcount_g += - XGMAC_IOREAD(pdata, MMC_RXOCTETCOUNT_G_LO); + xgbe_mmc_read(pdata, MMC_RXOCTETCOUNT_G_LO); if (XGMAC_GET_BITS(mmc_isr, MMC_RISR, RXBROADCASTFRAMES_G)) stats->rxbroadcastframes_g += - XGMAC_IOREAD(pdata, MMC_RXBROADCASTFRAMES_G_LO); + xgbe_mmc_read(pdata, MMC_RXBROADCASTFRAMES_G_LO); if (XGMAC_GET_BITS(mmc_isr, MMC_RISR, RXMULTICASTFRAMES_G)) stats->rxmulticastframes_g += - XGMAC_IOREAD(pdata, MMC_RXMULTICASTFRAMES_G_LO); + xgbe_mmc_read(pdata, MMC_RXMULTICASTFRAMES_G_LO); if (XGMAC_GET_BITS(mmc_isr, MMC_RISR, RXCRCERROR)) stats->rxcrcerror += - XGMAC_IOREAD(pdata, MMC_RXCRCERROR_LO); + xgbe_mmc_read(pdata, MMC_RXCRCERROR_LO); if (XGMAC_GET_BITS(mmc_isr, MMC_RISR, RXRUNTERROR)) stats->rxrunterror += - XGMAC_IOREAD(pdata, MMC_RXRUNTERROR); + xgbe_mmc_read(pdata, MMC_RXRUNTERROR); if (XGMAC_GET_BITS(mmc_isr, MMC_RISR, RXJABBERERROR)) stats->rxjabbererror += - XGMAC_IOREAD(pdata, MMC_RXJABBERERROR); + xgbe_mmc_read(pdata, MMC_RXJABBERERROR); if (XGMAC_GET_BITS(mmc_isr, MMC_RISR, RXUNDERSIZE_G)) stats->rxundersize_g += - XGMAC_IOREAD(pdata, MMC_RXUNDERSIZE_G); + xgbe_mmc_read(pdata, MMC_RXUNDERSIZE_G); if (XGMAC_GET_BITS(mmc_isr, MMC_RISR, RXOVERSIZE_G)) stats->rxoversize_g += - XGMAC_IOREAD(pdata, MMC_RXOVERSIZE_G); + xgbe_mmc_read(pdata, MMC_RXOVERSIZE_G); if (XGMAC_GET_BITS(mmc_isr, MMC_RISR, RX64OCTETS_GB)) stats->rx64octets_gb += - XGMAC_IOREAD(pdata, MMC_RX64OCTETS_GB_LO); + xgbe_mmc_read(pdata, MMC_RX64OCTETS_GB_LO); if (XGMAC_GET_BITS(mmc_isr, MMC_RISR, RX65TO127OCTETS_GB)) stats->rx65to127octets_gb += - XGMAC_IOREAD(pdata, MMC_RX65TO127OCTETS_GB_LO); + xgbe_mmc_read(pdata, MMC_RX65TO127OCTETS_GB_LO); if (XGMAC_GET_BITS(mmc_isr, MMC_RISR, RX128TO255OCTETS_GB)) stats->rx128to255octets_gb += - XGMAC_IOREAD(pdata, MMC_RX128TO255OCTETS_GB_LO); + xgbe_mmc_read(pdata, MMC_RX128TO255OCTETS_GB_LO); if (XGMAC_GET_BITS(mmc_isr, MMC_RISR, RX256TO511OCTETS_GB)) stats->rx256to511octets_gb += - XGMAC_IOREAD(pdata, MMC_RX256TO511OCTETS_GB_LO); + xgbe_mmc_read(pdata, MMC_RX256TO511OCTETS_GB_LO); if (XGMAC_GET_BITS(mmc_isr, MMC_RISR, RX512TO1023OCTETS_GB)) stats->rx512to1023octets_gb += - XGMAC_IOREAD(pdata, MMC_RX512TO1023OCTETS_GB_LO); + xgbe_mmc_read(pdata, MMC_RX512TO1023OCTETS_GB_LO); if (XGMAC_GET_BITS(mmc_isr, MMC_RISR, RX1024TOMAXOCTETS_GB)) stats->rx1024tomaxoctets_gb += - XGMAC_IOREAD(pdata, MMC_RX1024TOMAXOCTETS_GB_LO); + xgbe_mmc_read(pdata, MMC_RX1024TOMAXOCTETS_GB_LO); if (XGMAC_GET_BITS(mmc_isr, MMC_RISR, RXUNICASTFRAMES_G)) stats->rxunicastframes_g += - XGMAC_IOREAD(pdata, MMC_RXUNICASTFRAMES_G_LO); + xgbe_mmc_read(pdata, MMC_RXUNICASTFRAMES_G_LO); if (XGMAC_GET_BITS(mmc_isr, MMC_RISR, RXLENGTHERROR)) stats->rxlengtherror += - XGMAC_IOREAD(pdata, MMC_RXLENGTHERROR_LO); + xgbe_mmc_read(pdata, MMC_RXLENGTHERROR_LO); if (XGMAC_GET_BITS(mmc_isr, MMC_RISR, RXOUTOFRANGETYPE)) stats->rxoutofrangetype += - XGMAC_IOREAD(pdata, MMC_RXOUTOFRANGETYPE_LO); + xgbe_mmc_read(pdata, MMC_RXOUTOFRANGETYPE_LO); if (XGMAC_GET_BITS(mmc_isr, MMC_RISR, RXPAUSEFRAMES)) stats->rxpauseframes += - XGMAC_IOREAD(pdata, MMC_RXPAUSEFRAMES_LO); + xgbe_mmc_read(pdata, MMC_RXPAUSEFRAMES_LO); if (XGMAC_GET_BITS(mmc_isr, MMC_RISR, RXFIFOOVERFLOW)) stats->rxfifooverflow += - XGMAC_IOREAD(pdata, MMC_RXFIFOOVERFLOW_LO); + xgbe_mmc_read(pdata, MMC_RXFIFOOVERFLOW_LO); if (XGMAC_GET_BITS(mmc_isr, MMC_RISR, RXVLANFRAMES_GB)) stats->rxvlanframes_gb += - XGMAC_IOREAD(pdata, MMC_RXVLANFRAMES_GB_LO); + xgbe_mmc_read(pdata, MMC_RXVLANFRAMES_GB_LO); if (XGMAC_GET_BITS(mmc_isr, MMC_RISR, RXWATCHDOGERROR)) stats->rxwatchdogerror += - XGMAC_IOREAD(pdata, MMC_RXWATCHDOGERROR); + xgbe_mmc_read(pdata, MMC_RXWATCHDOGERROR); } static void xgbe_read_mmc_stats(struct xgbe_prv_data *pdata) @@ -2138,127 +2164,127 @@ static void xgbe_read_mmc_stats(struct xgbe_prv_data *pdata) XGMAC_IOWRITE_BITS(pdata, MMC_CR, MCF, 1); stats->txoctetcount_gb += - XGMAC_IOREAD(pdata, MMC_TXOCTETCOUNT_GB_LO); + xgbe_mmc_read(pdata, MMC_TXOCTETCOUNT_GB_LO); stats->txframecount_gb += - XGMAC_IOREAD(pdata, MMC_TXFRAMECOUNT_GB_LO); + xgbe_mmc_read(pdata, MMC_TXFRAMECOUNT_GB_LO); stats->txbroadcastframes_g += - XGMAC_IOREAD(pdata, MMC_TXBROADCASTFRAMES_G_LO); + xgbe_mmc_read(pdata, MMC_TXBROADCASTFRAMES_G_LO); stats->txmulticastframes_g += - XGMAC_IOREAD(pdata, MMC_TXMULTICASTFRAMES_G_LO); + xgbe_mmc_read(pdata, MMC_TXMULTICASTFRAMES_G_LO); stats->tx64octets_gb += - XGMAC_IOREAD(pdata, MMC_TX64OCTETS_GB_LO); + xgbe_mmc_read(pdata, MMC_TX64OCTETS_GB_LO); stats->tx65to127octets_gb += - XGMAC_IOREAD(pdata, MMC_TX65TO127OCTETS_GB_LO); + xgbe_mmc_read(pdata, MMC_TX65TO127OCTETS_GB_LO); stats->tx128to255octets_gb += - XGMAC_IOREAD(pdata, MMC_TX128TO255OCTETS_GB_LO); + xgbe_mmc_read(pdata, MMC_TX128TO255OCTETS_GB_LO); stats->tx256to511octets_gb += - XGMAC_IOREAD(pdata, MMC_TX256TO511OCTETS_GB_LO); + xgbe_mmc_read(pdata, MMC_TX256TO511OCTETS_GB_LO); stats->tx512to1023octets_gb += - XGMAC_IOREAD(pdata, MMC_TX512TO1023OCTETS_GB_LO); + xgbe_mmc_read(pdata, MMC_TX512TO1023OCTETS_GB_LO); stats->tx1024tomaxoctets_gb += - XGMAC_IOREAD(pdata, MMC_TX1024TOMAXOCTETS_GB_LO); + xgbe_mmc_read(pdata, MMC_TX1024TOMAXOCTETS_GB_LO); stats->txunicastframes_gb += - XGMAC_IOREAD(pdata, MMC_TXUNICASTFRAMES_GB_LO); + xgbe_mmc_read(pdata, MMC_TXUNICASTFRAMES_GB_LO); stats->txmulticastframes_gb += - XGMAC_IOREAD(pdata, MMC_TXMULTICASTFRAMES_GB_LO); + xgbe_mmc_read(pdata, MMC_TXMULTICASTFRAMES_GB_LO); stats->txbroadcastframes_g += - XGMAC_IOREAD(pdata, MMC_TXBROADCASTFRAMES_GB_LO); + xgbe_mmc_read(pdata, MMC_TXBROADCASTFRAMES_GB_LO); stats->txunderflowerror += - XGMAC_IOREAD(pdata, MMC_TXUNDERFLOWERROR_LO); + xgbe_mmc_read(pdata, MMC_TXUNDERFLOWERROR_LO); stats->txoctetcount_g += - XGMAC_IOREAD(pdata, MMC_TXOCTETCOUNT_G_LO); + xgbe_mmc_read(pdata, MMC_TXOCTETCOUNT_G_LO); stats->txframecount_g += - XGMAC_IOREAD(pdata, MMC_TXFRAMECOUNT_G_LO); + xgbe_mmc_read(pdata, MMC_TXFRAMECOUNT_G_LO); stats->txpauseframes += - XGMAC_IOREAD(pdata, MMC_TXPAUSEFRAMES_LO); + xgbe_mmc_read(pdata, MMC_TXPAUSEFRAMES_LO); stats->txvlanframes_g += - XGMAC_IOREAD(pdata, MMC_TXVLANFRAMES_G_LO); + xgbe_mmc_read(pdata, MMC_TXVLANFRAMES_G_LO); stats->rxframecount_gb += - XGMAC_IOREAD(pdata, MMC_RXFRAMECOUNT_GB_LO); + xgbe_mmc_read(pdata, MMC_RXFRAMECOUNT_GB_LO); stats->rxoctetcount_gb += - XGMAC_IOREAD(pdata, MMC_RXOCTETCOUNT_GB_LO); + xgbe_mmc_read(pdata, MMC_RXOCTETCOUNT_GB_LO); stats->rxoctetcount_g += - XGMAC_IOREAD(pdata, MMC_RXOCTETCOUNT_G_LO); + xgbe_mmc_read(pdata, MMC_RXOCTETCOUNT_G_LO); stats->rxbroadcastframes_g += - XGMAC_IOREAD(pdata, MMC_RXBROADCASTFRAMES_G_LO); + xgbe_mmc_read(pdata, MMC_RXBROADCASTFRAMES_G_LO); stats->rxmulticastframes_g += - XGMAC_IOREAD(pdata, MMC_RXMULTICASTFRAMES_G_LO); + xgbe_mmc_read(pdata, MMC_RXMULTICASTFRAMES_G_LO); stats->rxcrcerror += - XGMAC_IOREAD(pdata, MMC_RXCRCERROR_LO); + xgbe_mmc_read(pdata, MMC_RXCRCERROR_LO); stats->rxrunterror += - XGMAC_IOREAD(pdata, MMC_RXRUNTERROR); + xgbe_mmc_read(pdata, MMC_RXRUNTERROR); stats->rxjabbererror += - XGMAC_IOREAD(pdata, MMC_RXJABBERERROR); + xgbe_mmc_read(pdata, MMC_RXJABBERERROR); stats->rxundersize_g += - XGMAC_IOREAD(pdata, MMC_RXUNDERSIZE_G); + xgbe_mmc_read(pdata, MMC_RXUNDERSIZE_G); stats->rxoversize_g += - XGMAC_IOREAD(pdata, MMC_RXOVERSIZE_G); + xgbe_mmc_read(pdata, MMC_RXOVERSIZE_G); stats->rx64octets_gb += - XGMAC_IOREAD(pdata, MMC_RX64OCTETS_GB_LO); + xgbe_mmc_read(pdata, MMC_RX64OCTETS_GB_LO); stats->rx65to127octets_gb += - XGMAC_IOREAD(pdata, MMC_RX65TO127OCTETS_GB_LO); + xgbe_mmc_read(pdata, MMC_RX65TO127OCTETS_GB_LO); stats->rx128to255octets_gb += - XGMAC_IOREAD(pdata, MMC_RX128TO255OCTETS_GB_LO); + xgbe_mmc_read(pdata, MMC_RX128TO255OCTETS_GB_LO); stats->rx256to511octets_gb += - XGMAC_IOREAD(pdata, MMC_RX256TO511OCTETS_GB_LO); + xgbe_mmc_read(pdata, MMC_RX256TO511OCTETS_GB_LO); stats->rx512to1023octets_gb += - XGMAC_IOREAD(pdata, MMC_RX512TO1023OCTETS_GB_LO); + xgbe_mmc_read(pdata, MMC_RX512TO1023OCTETS_GB_LO); stats->rx1024tomaxoctets_gb += - XGMAC_IOREAD(pdata, MMC_RX1024TOMAXOCTETS_GB_LO); + xgbe_mmc_read(pdata, MMC_RX1024TOMAXOCTETS_GB_LO); stats->rxunicastframes_g += - XGMAC_IOREAD(pdata, MMC_RXUNICASTFRAMES_G_LO); + xgbe_mmc_read(pdata, MMC_RXUNICASTFRAMES_G_LO); stats->rxlengtherror += - XGMAC_IOREAD(pdata, MMC_RXLENGTHERROR_LO); + xgbe_mmc_read(pdata, MMC_RXLENGTHERROR_LO); stats->rxoutofrangetype += - XGMAC_IOREAD(pdata, MMC_RXOUTOFRANGETYPE_LO); + xgbe_mmc_read(pdata, MMC_RXOUTOFRANGETYPE_LO); stats->rxpauseframes += - XGMAC_IOREAD(pdata, MMC_RXPAUSEFRAMES_LO); + xgbe_mmc_read(pdata, MMC_RXPAUSEFRAMES_LO); stats->rxfifooverflow += - XGMAC_IOREAD(pdata, MMC_RXFIFOOVERFLOW_LO); + xgbe_mmc_read(pdata, MMC_RXFIFOOVERFLOW_LO); stats->rxvlanframes_gb += - XGMAC_IOREAD(pdata, MMC_RXVLANFRAMES_GB_LO); + xgbe_mmc_read(pdata, MMC_RXVLANFRAMES_GB_LO); stats->rxwatchdogerror += - XGMAC_IOREAD(pdata, MMC_RXWATCHDOGERROR); + xgbe_mmc_read(pdata, MMC_RXWATCHDOGERROR); /* Un-freeze counters */ XGMAC_IOWRITE_BITS(pdata, MMC_CR, MCF, 0); From a3ba7c989d7c80b34401c58269c5903a1da8412a Mon Sep 17 00:00:00 2001 From: "Lendacky, Thomas" Date: Fri, 5 Sep 2014 18:02:36 -0500 Subject: [PATCH 100/101] amd-xgbe: Enable interrupts for all management counters As the management counters reach a threshold they will generate an interrupt so the value can be saved and the counter reset. The current code does not enable this interrupt on all counters. This can result in inaccurate statistics. Update the code to enable all the counters to generate an interrupt when its threshold is exceeded. Signed-off-by: Tom Lendacky Signed-off-by: David S. Miller --- drivers/net/ethernet/amd/xgbe/xgbe-dev.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/net/ethernet/amd/xgbe/xgbe-dev.c b/drivers/net/ethernet/amd/xgbe/xgbe-dev.c index f3d04f19ebd4..ea273836d999 100644 --- a/drivers/net/ethernet/amd/xgbe/xgbe-dev.c +++ b/drivers/net/ethernet/amd/xgbe/xgbe-dev.c @@ -509,8 +509,8 @@ static void xgbe_enable_mac_interrupts(struct xgbe_prv_data *pdata) XGMAC_IOWRITE(pdata, MAC_IER, mac_ier); /* Enable all counter interrupts */ - XGMAC_IOWRITE_BITS(pdata, MMC_RIER, ALL_INTERRUPTS, 0xff); - XGMAC_IOWRITE_BITS(pdata, MMC_TIER, ALL_INTERRUPTS, 0xff); + XGMAC_IOWRITE_BITS(pdata, MMC_RIER, ALL_INTERRUPTS, 0xffffffff); + XGMAC_IOWRITE_BITS(pdata, MMC_TIER, ALL_INTERRUPTS, 0xffffffff); } static int xgbe_set_gmii_speed(struct xgbe_prv_data *pdata) From de185ab46cb02df9738b0d898b0c3a89181c5526 Mon Sep 17 00:00:00 2001 From: WANG Cong Date: Fri, 5 Sep 2014 14:33:00 -0700 Subject: [PATCH 101/101] ipv6: restore the behavior of ipv6_sock_ac_drop() It is possible that the interface is already gone after joining the list of anycast on this interface as we don't hold a refcount for the device, in this case we are safe to ignore the error. What's more important, for API compatibility we should not change this behavior for applications even if it were correct. Fixes: commit a9ed4a2986e13011 ("ipv6: fix rtnl locking in setsockopt for anycast and multicast") Cc: Sabrina Dubroca Cc: David S. Miller Signed-off-by: Cong Wang Acked-by: Hannes Frederic Sowa Signed-off-by: David S. Miller --- net/ipv6/anycast.c | 2 -- 1 file changed, 2 deletions(-) diff --git a/net/ipv6/anycast.c b/net/ipv6/anycast.c index 45b9d81d91e8..ff2de7d9d8e6 100644 --- a/net/ipv6/anycast.c +++ b/net/ipv6/anycast.c @@ -182,8 +182,6 @@ int ipv6_sock_ac_drop(struct sock *sk, int ifindex, const struct in6_addr *addr) rtnl_unlock(); sock_kfree_s(sk, pac, sizeof(*pac)); - if (!dev) - return -ENODEV; return 0; }