From 076bb0c82a44fbe46fe2c8527a5b5b64b69f679d Mon Sep 17 00:00:00 2001 From: Eliezer Tamir Date: Wed, 10 Jul 2013 17:13:17 +0300 Subject: [PATCH 01/36] net: rename include/net/ll_poll.h to include/net/busy_poll.h Rename the file and correct all the places where it is included. Signed-off-by: Eliezer Tamir Signed-off-by: David S. Miller --- drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c | 2 +- drivers/net/ethernet/intel/ixgbe/ixgbe.h | 2 +- drivers/net/ethernet/mellanox/mlx4/en_netdev.c | 2 +- drivers/net/ethernet/mellanox/mlx4/en_rx.c | 2 +- fs/select.c | 2 +- include/net/{ll_poll.h => busy_poll.h} | 0 net/core/datagram.c | 2 +- net/core/sock.c | 2 +- net/core/sysctl_net_core.c | 2 +- net/ipv4/tcp.c | 2 +- net/ipv4/tcp_ipv4.c | 2 +- net/ipv4/udp.c | 2 +- net/ipv6/tcp_ipv6.c | 2 +- net/ipv6/udp.c | 2 +- net/socket.c | 2 +- 15 files changed, 14 insertions(+), 14 deletions(-) rename include/net/{ll_poll.h => busy_poll.h} (100%) diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c index ec3aa1d451e8..05b6b4e8b073 100644 --- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c +++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c @@ -24,7 +24,7 @@ #include #include #include -#include +#include #include #include "bnx2x_cmn.h" #include "bnx2x_init.h" diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe.h b/drivers/net/ethernet/intel/ixgbe/ixgbe.h index fb098b46c6a6..7be725cdfea8 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe.h +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe.h @@ -52,7 +52,7 @@ #include #endif -#include +#include #ifdef CONFIG_NET_LL_RX_POLL #define LL_EXTENDED_STATS diff --git a/drivers/net/ethernet/mellanox/mlx4/en_netdev.c b/drivers/net/ethernet/mellanox/mlx4/en_netdev.c index caf204770569..0fb2438dc2c7 100644 --- a/drivers/net/ethernet/mellanox/mlx4/en_netdev.c +++ b/drivers/net/ethernet/mellanox/mlx4/en_netdev.c @@ -38,7 +38,7 @@ #include #include #include -#include +#include #include #include diff --git a/drivers/net/ethernet/mellanox/mlx4/en_rx.c b/drivers/net/ethernet/mellanox/mlx4/en_rx.c index 76997b93fdfe..90746d37ac9b 100644 --- a/drivers/net/ethernet/mellanox/mlx4/en_rx.c +++ b/drivers/net/ethernet/mellanox/mlx4/en_rx.c @@ -31,7 +31,7 @@ * */ -#include +#include #include #include #include diff --git a/fs/select.c b/fs/select.c index f9f49c40cfd4..35d4adc749d9 100644 --- a/fs/select.c +++ b/fs/select.c @@ -28,7 +28,7 @@ #include #include #include -#include +#include #include diff --git a/include/net/ll_poll.h b/include/net/busy_poll.h similarity index 100% rename from include/net/ll_poll.h rename to include/net/busy_poll.h diff --git a/net/core/datagram.c b/net/core/datagram.c index 6e9ab31e457e..8ab48cd89559 100644 --- a/net/core/datagram.c +++ b/net/core/datagram.c @@ -56,7 +56,7 @@ #include #include #include -#include +#include /* * Is a socket 'connection oriented' ? diff --git a/net/core/sock.c b/net/core/sock.c index ab06b719f5b1..9bfe83f4d670 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -139,7 +139,7 @@ #include #endif -#include +#include static DEFINE_MUTEX(proto_list_mutex); static LIST_HEAD(proto_list); diff --git a/net/core/sysctl_net_core.c b/net/core/sysctl_net_core.c index afc677eadd93..1a298cb3daee 100644 --- a/net/core/sysctl_net_core.c +++ b/net/core/sysctl_net_core.c @@ -19,7 +19,7 @@ #include #include #include -#include +#include static int one = 1; diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index 15cbfa94bd8e..5423223e93c2 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -279,7 +279,7 @@ #include #include -#include +#include int sysctl_tcp_fin_timeout __read_mostly = TCP_FIN_TIMEOUT; diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index 35675e46aff8..3a261b41a00c 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -75,7 +75,7 @@ #include #include #include -#include +#include #include #include diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c index 6b270e53c207..bcc0ff2c16da 100644 --- a/net/ipv4/udp.c +++ b/net/ipv4/udp.c @@ -109,7 +109,7 @@ #include #include #include -#include +#include #include "udp_impl.h" struct udp_table udp_table __read_mostly; diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c index 5cffa5c3e6b8..345bd92d4ddb 100644 --- a/net/ipv6/tcp_ipv6.c +++ b/net/ipv6/tcp_ipv6.c @@ -63,7 +63,7 @@ #include #include #include -#include +#include #include diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c index b6f31437a1f8..40e72034da07 100644 --- a/net/ipv6/udp.c +++ b/net/ipv6/udp.c @@ -46,7 +46,7 @@ #include #include #include -#include +#include #include #include diff --git a/net/socket.c b/net/socket.c index 45afa648364a..6a3e9a3f50ad 100644 --- a/net/socket.c +++ b/net/socket.c @@ -104,7 +104,7 @@ #include #include #include -#include +#include #ifdef CONFIG_NET_LL_RX_POLL unsigned int sysctl_net_ll_read __read_mostly; From 8b80cda536ea9bceec0364e897868a30ee13b992 Mon Sep 17 00:00:00 2001 From: Eliezer Tamir Date: Wed, 10 Jul 2013 17:13:26 +0300 Subject: [PATCH 02/36] net: rename ll methods to busy-poll Rename ndo_ll_poll to ndo_busy_poll. Rename sk_mark_ll to sk_mark_napi_id. Rename skb_mark_ll to skb_mark_napi_id. Correct all useres of these functions. Update comments and defines in include/net/busy_poll.h Signed-off-by: Eliezer Tamir Signed-off-by: David S. Miller --- .../net/ethernet/broadcom/bnx2x/bnx2x_cmn.c | 2 +- .../net/ethernet/broadcom/bnx2x/bnx2x_main.c | 2 +- drivers/net/ethernet/intel/ixgbe/ixgbe_main.c | 4 ++-- .../net/ethernet/mellanox/mlx4/en_netdev.c | 2 +- drivers/net/ethernet/mellanox/mlx4/en_rx.c | 2 +- include/linux/netdevice.h | 2 +- include/net/busy_poll.h | 22 ++++++++++--------- net/ipv4/tcp_ipv4.c | 2 +- net/ipv4/udp.c | 2 +- net/ipv6/tcp_ipv6.c | 2 +- net/ipv6/udp.c | 2 +- 11 files changed, 23 insertions(+), 21 deletions(-) diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c index 05b6b4e8b073..3353efe79194 100644 --- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c +++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c @@ -990,7 +990,7 @@ reuse_rx: __vlan_hwaccel_put_tag(skb, htons(ETH_P_8021Q), le16_to_cpu(cqe_fp->vlan_tag)); - skb_mark_ll(skb, &fp->napi); + skb_mark_napi_id(skb, &fp->napi); if (bnx2x_fp_ll_polling(fp)) netif_receive_skb(skb); diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c index 15a528bda87c..e5da07858a2f 100644 --- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c +++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c @@ -12027,7 +12027,7 @@ static const struct net_device_ops bnx2x_netdev_ops = { #endif #ifdef CONFIG_NET_LL_RX_POLL - .ndo_ll_poll = bnx2x_low_latency_recv, + .ndo_busy_poll = bnx2x_low_latency_recv, #endif }; diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c index 047ebaaf0141..bad8f14b1941 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c @@ -1978,7 +1978,7 @@ static int ixgbe_clean_rx_irq(struct ixgbe_q_vector *q_vector, } #endif /* IXGBE_FCOE */ - skb_mark_ll(skb, &q_vector->napi); + skb_mark_napi_id(skb, &q_vector->napi); ixgbe_rx_skb(q_vector, skb); /* update budget accounting */ @@ -7228,7 +7228,7 @@ static const struct net_device_ops ixgbe_netdev_ops = { .ndo_poll_controller = ixgbe_netpoll, #endif #ifdef CONFIG_NET_LL_RX_POLL - .ndo_ll_poll = ixgbe_low_latency_recv, + .ndo_busy_poll = ixgbe_low_latency_recv, #endif #ifdef IXGBE_FCOE .ndo_fcoe_ddp_setup = ixgbe_fcoe_ddp_get, diff --git a/drivers/net/ethernet/mellanox/mlx4/en_netdev.c b/drivers/net/ethernet/mellanox/mlx4/en_netdev.c index 0fb2438dc2c7..5eac871399d8 100644 --- a/drivers/net/ethernet/mellanox/mlx4/en_netdev.c +++ b/drivers/net/ethernet/mellanox/mlx4/en_netdev.c @@ -2141,7 +2141,7 @@ static const struct net_device_ops mlx4_netdev_ops = { .ndo_rx_flow_steer = mlx4_en_filter_rfs, #endif #ifdef CONFIG_NET_LL_RX_POLL - .ndo_ll_poll = mlx4_en_low_latency_recv, + .ndo_busy_poll = mlx4_en_low_latency_recv, #endif }; diff --git a/drivers/net/ethernet/mellanox/mlx4/en_rx.c b/drivers/net/ethernet/mellanox/mlx4/en_rx.c index 90746d37ac9b..dec455c8f627 100644 --- a/drivers/net/ethernet/mellanox/mlx4/en_rx.c +++ b/drivers/net/ethernet/mellanox/mlx4/en_rx.c @@ -767,7 +767,7 @@ int mlx4_en_process_rx_cq(struct net_device *dev, struct mlx4_en_cq *cq, int bud timestamp); } - skb_mark_ll(skb, &cq->napi); + skb_mark_napi_id(skb, &cq->napi); /* Push it up the stack */ netif_receive_skb(skb); diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index bb82871b8494..0741a1e919a5 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -974,7 +974,7 @@ struct net_device_ops { void (*ndo_netpoll_cleanup)(struct net_device *dev); #endif #ifdef CONFIG_NET_LL_RX_POLL - int (*ndo_ll_poll)(struct napi_struct *dev); + int (*ndo_busy_poll)(struct napi_struct *dev); #endif int (*ndo_set_vf_mac)(struct net_device *dev, int queue, u8 *mac); diff --git a/include/net/busy_poll.h b/include/net/busy_poll.h index 76f034087743..4ff71908fd42 100644 --- a/include/net/busy_poll.h +++ b/include/net/busy_poll.h @@ -1,5 +1,5 @@ /* - * Low Latency Sockets + * net busy poll support * Copyright(c) 2013 Intel Corporation. * * This program is free software; you can redistribute it and/or modify it @@ -21,8 +21,8 @@ * e1000-devel Mailing List */ -#ifndef _LINUX_NET_LL_POLL_H -#define _LINUX_NET_LL_POLL_H +#ifndef _LINUX_NET_BUSY_POLL_H +#define _LINUX_NET_BUSY_POLL_H #include #include @@ -110,11 +110,11 @@ static inline bool sk_busy_loop(struct sock *sk, int nonblock) goto out; ops = napi->dev->netdev_ops; - if (!ops->ndo_ll_poll) + if (!ops->ndo_busy_poll) goto out; do { - rc = ops->ndo_ll_poll(napi); + rc = ops->ndo_busy_poll(napi); if (rc == LL_FLUSH_FAILED) break; /* permanent failure */ @@ -134,13 +134,14 @@ out: } /* used in the NIC receive handler to mark the skb */ -static inline void skb_mark_ll(struct sk_buff *skb, struct napi_struct *napi) +static inline void skb_mark_napi_id(struct sk_buff *skb, + struct napi_struct *napi) { skb->napi_id = napi->napi_id; } /* used in the protocol hanlder to propagate the napi_id to the socket */ -static inline void sk_mark_ll(struct sock *sk, struct sk_buff *skb) +static inline void sk_mark_napi_id(struct sock *sk, struct sk_buff *skb) { sk->sk_napi_id = skb->napi_id; } @@ -166,11 +167,12 @@ static inline bool sk_busy_poll(struct sock *sk, int nonblock) return false; } -static inline void skb_mark_ll(struct sk_buff *skb, struct napi_struct *napi) +static inline void skb_mark_napi_id(struct sk_buff *skb, + struct napi_struct *napi) { } -static inline void sk_mark_ll(struct sock *sk, struct sk_buff *skb) +static inline void sk_mark_napi_id(struct sock *sk, struct sk_buff *skb) { } @@ -180,4 +182,4 @@ static inline bool busy_loop_timeout(unsigned long end_time) } #endif /* CONFIG_NET_LL_RX_POLL */ -#endif /* _LINUX_NET_LL_POLL_H */ +#endif /* _LINUX_NET_BUSY_POLL_H */ diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index 3a261b41a00c..b299da5ff499 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -1994,7 +1994,7 @@ process: if (sk_filter(sk, skb)) goto discard_and_relse; - sk_mark_ll(sk, skb); + sk_mark_napi_id(sk, skb); skb->dev = NULL; bh_lock_sock_nested(sk); diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c index bcc0ff2c16da..a0d7151ffbd9 100644 --- a/net/ipv4/udp.c +++ b/net/ipv4/udp.c @@ -1713,7 +1713,7 @@ int __udp4_lib_rcv(struct sk_buff *skb, struct udp_table *udptable, if (sk != NULL) { int ret; - sk_mark_ll(sk, skb); + sk_mark_napi_id(sk, skb); ret = udp_queue_rcv_skb(sk, skb); sock_put(sk); diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c index 345bd92d4ddb..6e1649d58533 100644 --- a/net/ipv6/tcp_ipv6.c +++ b/net/ipv6/tcp_ipv6.c @@ -1499,7 +1499,7 @@ process: if (sk_filter(sk, skb)) goto discard_and_relse; - sk_mark_ll(sk, skb); + sk_mark_napi_id(sk, skb); skb->dev = NULL; bh_lock_sock_nested(sk); diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c index 40e72034da07..f4058150262b 100644 --- a/net/ipv6/udp.c +++ b/net/ipv6/udp.c @@ -844,7 +844,7 @@ int __udp6_lib_rcv(struct sk_buff *skb, struct udp_table *udptable, if (sk != NULL) { int ret; - sk_mark_ll(sk, skb); + sk_mark_napi_id(sk, skb); ret = udpv6_queue_rcv_skb(sk, skb); sock_put(sk); From 64b0dc517ea1b35d02565a779e6cb77ae9045685 Mon Sep 17 00:00:00 2001 From: Eliezer Tamir Date: Wed, 10 Jul 2013 17:13:36 +0300 Subject: [PATCH 03/36] net: rename busy poll socket op and globals Rename LL_SO to BUSY_POLL_SO Rename sysctl_net_ll_{read,poll} to sysctl_busy_{read,poll} Fix up users of these variables. Fix documentation for sysctl. a patch for the socket.7 man page will follow separately, because of limitations of my mail setup. Signed-off-by: Eliezer Tamir Signed-off-by: David S. Miller --- Documentation/sysctl/net.txt | 17 +++++++++-------- arch/alpha/include/uapi/asm/socket.h | 2 +- arch/avr32/include/uapi/asm/socket.h | 2 +- arch/cris/include/uapi/asm/socket.h | 2 +- arch/frv/include/uapi/asm/socket.h | 2 +- arch/h8300/include/uapi/asm/socket.h | 2 +- arch/ia64/include/uapi/asm/socket.h | 2 +- arch/m32r/include/uapi/asm/socket.h | 2 +- arch/mips/include/uapi/asm/socket.h | 2 +- arch/mn10300/include/uapi/asm/socket.h | 2 +- arch/parisc/include/uapi/asm/socket.h | 2 +- arch/powerpc/include/uapi/asm/socket.h | 2 +- arch/s390/include/uapi/asm/socket.h | 2 +- arch/sparc/include/uapi/asm/socket.h | 2 +- arch/xtensa/include/uapi/asm/socket.h | 2 +- include/net/busy_poll.h | 8 ++++---- include/uapi/asm-generic/socket.h | 2 +- net/core/sock.c | 6 +++--- net/core/sysctl_net_core.c | 8 ++++---- net/socket.c | 4 ++-- 20 files changed, 37 insertions(+), 36 deletions(-) diff --git a/Documentation/sysctl/net.txt b/Documentation/sysctl/net.txt index d69e14c9002c..1c15043aaee4 100644 --- a/Documentation/sysctl/net.txt +++ b/Documentation/sysctl/net.txt @@ -50,26 +50,27 @@ The maximum number of packets that kernel can handle on a NAPI interrupt, it's a Per-CPU variable. Default: 64 -low_latency_read +busy_read ---------------- Low latency busy poll timeout for socket reads. (needs CONFIG_NET_LL_RX_POLL) Approximate time in us to busy loop waiting for packets on the device queue. -This sets the default value of the SO_LL socket option. -Can be set or overridden per socket by setting socket option SO_LL, which is -the preferred method of enabling. -If you need to enable the feature globally via sysctl, a value of 50 is recommended. +This sets the default value of the SO_BUSY_POLL socket option. +Can be set or overridden per socket by setting socket option SO_BUSY_POLL, +which is the preferred method of enabling. If you need to enable the feature +globally via sysctl, a value of 50 is recommended. Will increase power usage. Default: 0 (off) -low_latency_poll +busy_poll ---------------- Low latency busy poll timeout for poll and select. (needs CONFIG_NET_LL_RX_POLL) Approximate time in us to busy loop waiting for events. Recommended value depends on the number of sockets you poll on. For several sockets 50, for several hundreds 100. For more than that you probably want to use epoll. -Note that only sockets with SO_LL set will be busy polled, so you want to either -selectively set SO_LL on those sockets or set sysctl.net.low_latency_read globally. +Note that only sockets with SO_BUSY_POLL set will be busy polled, +so you want to either selectively set SO_BUSY_POLL on those sockets or set +sysctl.net.busy_read globally. Will increase power usage. Default: 0 (off) diff --git a/arch/alpha/include/uapi/asm/socket.h b/arch/alpha/include/uapi/asm/socket.h index 4885825e498d..467de010ea7e 100644 --- a/arch/alpha/include/uapi/asm/socket.h +++ b/arch/alpha/include/uapi/asm/socket.h @@ -81,6 +81,6 @@ #define SO_SELECT_ERR_QUEUE 45 -#define SO_LL 46 +#define SO_BUSY_POLL 46 #endif /* _UAPI_ASM_SOCKET_H */ diff --git a/arch/avr32/include/uapi/asm/socket.h b/arch/avr32/include/uapi/asm/socket.h index 79b61798ebf8..11c4259c62fb 100644 --- a/arch/avr32/include/uapi/asm/socket.h +++ b/arch/avr32/include/uapi/asm/socket.h @@ -74,6 +74,6 @@ #define SO_SELECT_ERR_QUEUE 45 -#define SO_LL 46 +#define SO_BUSY_POLL 46 #endif /* __ASM_AVR32_SOCKET_H */ diff --git a/arch/cris/include/uapi/asm/socket.h b/arch/cris/include/uapi/asm/socket.h index 47b1ec55092d..eb723e51554e 100644 --- a/arch/cris/include/uapi/asm/socket.h +++ b/arch/cris/include/uapi/asm/socket.h @@ -76,7 +76,7 @@ #define SO_SELECT_ERR_QUEUE 45 -#define SO_LL 46 +#define SO_BUSY_POLL 46 #endif /* _ASM_SOCKET_H */ diff --git a/arch/frv/include/uapi/asm/socket.h b/arch/frv/include/uapi/asm/socket.h index dbc08520f22c..f0cb1c341163 100644 --- a/arch/frv/include/uapi/asm/socket.h +++ b/arch/frv/include/uapi/asm/socket.h @@ -74,7 +74,7 @@ #define SO_SELECT_ERR_QUEUE 45 -#define SO_LL 46 +#define SO_BUSY_POLL 46 #endif /* _ASM_SOCKET_H */ diff --git a/arch/h8300/include/uapi/asm/socket.h b/arch/h8300/include/uapi/asm/socket.h index a38d38a6520b..9490758c5e2b 100644 --- a/arch/h8300/include/uapi/asm/socket.h +++ b/arch/h8300/include/uapi/asm/socket.h @@ -74,6 +74,6 @@ #define SO_SELECT_ERR_QUEUE 45 -#define SO_LL 46 +#define SO_BUSY_POLL 46 #endif /* _ASM_SOCKET_H */ diff --git a/arch/ia64/include/uapi/asm/socket.h b/arch/ia64/include/uapi/asm/socket.h index d3358b760681..556d0701a155 100644 --- a/arch/ia64/include/uapi/asm/socket.h +++ b/arch/ia64/include/uapi/asm/socket.h @@ -83,6 +83,6 @@ #define SO_SELECT_ERR_QUEUE 45 -#define SO_LL 46 +#define SO_BUSY_POLL 46 #endif /* _ASM_IA64_SOCKET_H */ diff --git a/arch/m32r/include/uapi/asm/socket.h b/arch/m32r/include/uapi/asm/socket.h index 44aaf4639a4a..24be7c8da86a 100644 --- a/arch/m32r/include/uapi/asm/socket.h +++ b/arch/m32r/include/uapi/asm/socket.h @@ -74,6 +74,6 @@ #define SO_SELECT_ERR_QUEUE 45 -#define SO_LL 46 +#define SO_BUSY_POLL 46 #endif /* _ASM_M32R_SOCKET_H */ diff --git a/arch/mips/include/uapi/asm/socket.h b/arch/mips/include/uapi/asm/socket.h index 6a07992ba6c6..61c01f054d1b 100644 --- a/arch/mips/include/uapi/asm/socket.h +++ b/arch/mips/include/uapi/asm/socket.h @@ -92,6 +92,6 @@ #define SO_SELECT_ERR_QUEUE 45 -#define SO_LL 46 +#define SO_BUSY_POLL 46 #endif /* _UAPI_ASM_SOCKET_H */ diff --git a/arch/mn10300/include/uapi/asm/socket.h b/arch/mn10300/include/uapi/asm/socket.h index db80fd3e398b..e2a2b203eb00 100644 --- a/arch/mn10300/include/uapi/asm/socket.h +++ b/arch/mn10300/include/uapi/asm/socket.h @@ -74,6 +74,6 @@ #define SO_SELECT_ERR_QUEUE 45 -#define SO_LL 46 +#define SO_BUSY_POLL 46 #endif /* _ASM_SOCKET_H */ diff --git a/arch/parisc/include/uapi/asm/socket.h b/arch/parisc/include/uapi/asm/socket.h index f866fff9a004..71700e636a8e 100644 --- a/arch/parisc/include/uapi/asm/socket.h +++ b/arch/parisc/include/uapi/asm/socket.h @@ -73,7 +73,7 @@ #define SO_SELECT_ERR_QUEUE 0x4026 -#define SO_LL 0x4027 +#define SO_BUSY_POLL 0x4027 /* O_NONBLOCK clashes with the bits used for socket types. Therefore we * have to define SOCK_NONBLOCK to a different value here. diff --git a/arch/powerpc/include/uapi/asm/socket.h b/arch/powerpc/include/uapi/asm/socket.h index 405fb09bda94..a6d74467c9ed 100644 --- a/arch/powerpc/include/uapi/asm/socket.h +++ b/arch/powerpc/include/uapi/asm/socket.h @@ -81,6 +81,6 @@ #define SO_SELECT_ERR_QUEUE 45 -#define SO_LL 46 +#define SO_BUSY_POLL 46 #endif /* _ASM_POWERPC_SOCKET_H */ diff --git a/arch/s390/include/uapi/asm/socket.h b/arch/s390/include/uapi/asm/socket.h index 0c5105fbaaf3..92494494692e 100644 --- a/arch/s390/include/uapi/asm/socket.h +++ b/arch/s390/include/uapi/asm/socket.h @@ -80,6 +80,6 @@ #define SO_SELECT_ERR_QUEUE 45 -#define SO_LL 46 +#define SO_BUSY_POLL 46 #endif /* _ASM_SOCKET_H */ diff --git a/arch/sparc/include/uapi/asm/socket.h b/arch/sparc/include/uapi/asm/socket.h index b46c3fa0b265..4e1d66c3ce71 100644 --- a/arch/sparc/include/uapi/asm/socket.h +++ b/arch/sparc/include/uapi/asm/socket.h @@ -70,7 +70,7 @@ #define SO_SELECT_ERR_QUEUE 0x0029 -#define SO_LL 0x0030 +#define SO_BUSY_POLL 0x0030 /* Security levels - as per NRL IPv6 - don't actually do anything */ #define SO_SECURITY_AUTHENTICATION 0x5001 diff --git a/arch/xtensa/include/uapi/asm/socket.h b/arch/xtensa/include/uapi/asm/socket.h index b21ace4fc9ba..c114483010c1 100644 --- a/arch/xtensa/include/uapi/asm/socket.h +++ b/arch/xtensa/include/uapi/asm/socket.h @@ -85,6 +85,6 @@ #define SO_SELECT_ERR_QUEUE 45 -#define SO_LL 46 +#define SO_BUSY_POLL 46 #endif /* _XTENSA_SOCKET_H */ diff --git a/include/net/busy_poll.h b/include/net/busy_poll.h index 4ff71908fd42..a14339c2985f 100644 --- a/include/net/busy_poll.h +++ b/include/net/busy_poll.h @@ -30,8 +30,8 @@ #ifdef CONFIG_NET_LL_RX_POLL struct napi_struct; -extern unsigned int sysctl_net_ll_read __read_mostly; -extern unsigned int sysctl_net_ll_poll __read_mostly; +extern unsigned int sysctl_net_busy_read __read_mostly; +extern unsigned int sysctl_net_busy_poll __read_mostly; /* return values from ndo_ll_poll */ #define LL_FLUSH_FAILED -1 @@ -39,7 +39,7 @@ extern unsigned int sysctl_net_ll_poll __read_mostly; static inline bool net_busy_loop_on(void) { - return sysctl_net_ll_poll; + return sysctl_net_busy_poll; } /* a wrapper to make debug_smp_processor_id() happy @@ -72,7 +72,7 @@ static inline unsigned long sk_busy_loop_end_time(struct sock *sk) /* in poll/select we use the global sysctl_net_ll_poll value */ static inline unsigned long busy_loop_end_time(void) { - return busy_loop_us_clock() + ACCESS_ONCE(sysctl_net_ll_poll); + return busy_loop_us_clock() + ACCESS_ONCE(sysctl_net_busy_poll); } static inline bool sk_can_busy_loop(struct sock *sk) diff --git a/include/uapi/asm-generic/socket.h b/include/uapi/asm-generic/socket.h index ca3a20d772ac..f04b69b6abf2 100644 --- a/include/uapi/asm-generic/socket.h +++ b/include/uapi/asm-generic/socket.h @@ -76,6 +76,6 @@ #define SO_SELECT_ERR_QUEUE 45 -#define SO_LL 46 +#define SO_BUSY_POLL 46 #endif /* __ASM_GENERIC_SOCKET_H */ diff --git a/net/core/sock.c b/net/core/sock.c index 9bfe83f4d670..548d716c5f62 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -901,7 +901,7 @@ set_rcvbuf: break; #ifdef CONFIG_NET_LL_RX_POLL - case SO_LL: + case SO_BUSY_POLL: /* allow unprivileged users to decrease the value */ if ((val > sk->sk_ll_usec) && !capable(CAP_NET_ADMIN)) ret = -EPERM; @@ -1171,7 +1171,7 @@ int sock_getsockopt(struct socket *sock, int level, int optname, break; #ifdef CONFIG_NET_LL_RX_POLL - case SO_LL: + case SO_BUSY_POLL: v.val = sk->sk_ll_usec; break; #endif @@ -2294,7 +2294,7 @@ void sock_init_data(struct socket *sock, struct sock *sk) #ifdef CONFIG_NET_LL_RX_POLL sk->sk_napi_id = 0; - sk->sk_ll_usec = sysctl_net_ll_read; + sk->sk_ll_usec = sysctl_net_busy_read; #endif /* diff --git a/net/core/sysctl_net_core.c b/net/core/sysctl_net_core.c index 1a298cb3daee..660968616637 100644 --- a/net/core/sysctl_net_core.c +++ b/net/core/sysctl_net_core.c @@ -300,15 +300,15 @@ static struct ctl_table net_core_table[] = { #endif /* CONFIG_NET_FLOW_LIMIT */ #ifdef CONFIG_NET_LL_RX_POLL { - .procname = "low_latency_poll", - .data = &sysctl_net_ll_poll, + .procname = "busy_poll", + .data = &sysctl_net_busy_poll, .maxlen = sizeof(unsigned int), .mode = 0644, .proc_handler = proc_dointvec }, { - .procname = "low_latency_read", - .data = &sysctl_net_ll_read, + .procname = "busy_read", + .data = &sysctl_net_busy_read, .maxlen = sizeof(unsigned int), .mode = 0644, .proc_handler = proc_dointvec diff --git a/net/socket.c b/net/socket.c index 6a3e9a3f50ad..829b460acb87 100644 --- a/net/socket.c +++ b/net/socket.c @@ -107,8 +107,8 @@ #include #ifdef CONFIG_NET_LL_RX_POLL -unsigned int sysctl_net_ll_read __read_mostly; -unsigned int sysctl_net_ll_poll __read_mostly; +unsigned int sysctl_net_busy_read __read_mostly; +unsigned int sysctl_net_busy_poll __read_mostly; #endif static int sock_no_open(struct inode *irrelevant, struct file *dontcare); From 45dd95c443c2d81d8d41e55afeafd4c61042fa76 Mon Sep 17 00:00:00 2001 From: hayeswang Date: Mon, 8 Jul 2013 17:09:01 +0800 Subject: [PATCH 04/36] r8169: add a new chip for RTL8411 Add a new chip for RTL8411 series. Signed-off-by: Hayes Wang Signed-off-by: David S. Miller --- drivers/net/ethernet/realtek/r8169.c | 67 ++++++++++++++++++++++++++++ 1 file changed, 67 insertions(+) diff --git a/drivers/net/ethernet/realtek/r8169.c b/drivers/net/ethernet/realtek/r8169.c index 393f961a013c..4106a743ca74 100644 --- a/drivers/net/ethernet/realtek/r8169.c +++ b/drivers/net/ethernet/realtek/r8169.c @@ -46,6 +46,7 @@ #define FIRMWARE_8105E_1 "rtl_nic/rtl8105e-1.fw" #define FIRMWARE_8402_1 "rtl_nic/rtl8402-1.fw" #define FIRMWARE_8411_1 "rtl_nic/rtl8411-1.fw" +#define FIRMWARE_8411_2 "rtl_nic/rtl8411-2.fw" #define FIRMWARE_8106E_1 "rtl_nic/rtl8106e-1.fw" #define FIRMWARE_8106E_2 "rtl_nic/rtl8106e-2.fw" #define FIRMWARE_8168G_2 "rtl_nic/rtl8168g-2.fw" @@ -144,6 +145,7 @@ enum mac_version { RTL_GIGA_MAC_VER_41, RTL_GIGA_MAC_VER_42, RTL_GIGA_MAC_VER_43, + RTL_GIGA_MAC_VER_44, RTL_GIGA_MAC_NONE = 0xff, }; @@ -276,6 +278,9 @@ static const struct { [RTL_GIGA_MAC_VER_43] = _R("RTL8106e", RTL_TD_1, FIRMWARE_8106E_2, JUMBO_1K, true), + [RTL_GIGA_MAC_VER_44] = + _R("RTL8411", RTL_TD_1, FIRMWARE_8411_2, + JUMBO_9K, false), }; #undef _R @@ -394,6 +399,7 @@ enum rtl8168_8101_registers { #define CSIAR_FUNC_CARD 0x00000000 #define CSIAR_FUNC_SDIO 0x00010000 #define CSIAR_FUNC_NIC 0x00020000 +#define CSIAR_FUNC_NIC2 0x00010000 PMCH = 0x6f, EPHYAR = 0x80, #define EPHYAR_FLAG 0x80000000 @@ -826,6 +832,7 @@ MODULE_FIRMWARE(FIRMWARE_8168F_1); MODULE_FIRMWARE(FIRMWARE_8168F_2); MODULE_FIRMWARE(FIRMWARE_8402_1); MODULE_FIRMWARE(FIRMWARE_8411_1); +MODULE_FIRMWARE(FIRMWARE_8411_2); MODULE_FIRMWARE(FIRMWARE_8106E_1); MODULE_FIRMWARE(FIRMWARE_8106E_2); MODULE_FIRMWARE(FIRMWARE_8168G_2); @@ -2051,6 +2058,7 @@ static void rtl8169_get_mac_version(struct rtl8169_private *tp, int mac_version; } mac_info[] = { /* 8168G family. */ + { 0x7cf00000, 0x5c800000, RTL_GIGA_MAC_VER_44 }, { 0x7cf00000, 0x50900000, RTL_GIGA_MAC_VER_42 }, { 0x7cf00000, 0x4c100000, RTL_GIGA_MAC_VER_41 }, { 0x7cf00000, 0x4c000000, RTL_GIGA_MAC_VER_40 }, @@ -3651,6 +3659,7 @@ static void rtl_hw_phy_config(struct net_device *dev) break; case RTL_GIGA_MAC_VER_42: case RTL_GIGA_MAC_VER_43: + case RTL_GIGA_MAC_VER_44: rtl8168g_2_hw_phy_config(tp); break; @@ -3863,6 +3872,7 @@ static void rtl_init_mdio_ops(struct rtl8169_private *tp) case RTL_GIGA_MAC_VER_41: case RTL_GIGA_MAC_VER_42: case RTL_GIGA_MAC_VER_43: + case RTL_GIGA_MAC_VER_44: ops->write = r8168g_mdio_write; ops->read = r8168g_mdio_read; break; @@ -3916,6 +3926,7 @@ static void rtl_wol_suspend_quirk(struct rtl8169_private *tp) case RTL_GIGA_MAC_VER_41: case RTL_GIGA_MAC_VER_42: case RTL_GIGA_MAC_VER_43: + case RTL_GIGA_MAC_VER_44: RTL_W32(RxConfig, RTL_R32(RxConfig) | AcceptBroadcast | AcceptMulticast | AcceptMyPhys); break; @@ -4178,6 +4189,7 @@ static void rtl_init_pll_power_ops(struct rtl8169_private *tp) case RTL_GIGA_MAC_VER_40: case RTL_GIGA_MAC_VER_41: case RTL_GIGA_MAC_VER_42: + case RTL_GIGA_MAC_VER_44: ops->down = r8168_pll_power_down; ops->up = r8168_pll_power_up; break; @@ -4224,6 +4236,7 @@ static void rtl_init_rxcfg(struct rtl8169_private *tp) case RTL_GIGA_MAC_VER_41: case RTL_GIGA_MAC_VER_42: case RTL_GIGA_MAC_VER_43: + case RTL_GIGA_MAC_VER_44: RTL_W32(RxConfig, RX128_INT_EN | RX_DMA_BURST | RX_EARLY_OFF); break; default: @@ -4384,6 +4397,7 @@ static void rtl_init_jumbo_ops(struct rtl8169_private *tp) case RTL_GIGA_MAC_VER_41: case RTL_GIGA_MAC_VER_42: case RTL_GIGA_MAC_VER_43: + case RTL_GIGA_MAC_VER_44: default: ops->disable = NULL; ops->enable = NULL; @@ -4493,6 +4507,7 @@ static void rtl8169_hw_reset(struct rtl8169_private *tp) tp->mac_version == RTL_GIGA_MAC_VER_41 || tp->mac_version == RTL_GIGA_MAC_VER_42 || tp->mac_version == RTL_GIGA_MAC_VER_43 || + tp->mac_version == RTL_GIGA_MAC_VER_44 || tp->mac_version == RTL_GIGA_MAC_VER_38) { RTL_W8(ChipCmd, RTL_R8(ChipCmd) | StopReq); rtl_udelay_loop_wait_high(tp, &rtl_txcfg_empty_cond, 100, 666); @@ -4782,6 +4797,29 @@ static u32 r8402_csi_read(struct rtl8169_private *tp, int addr) RTL_R32(CSIDR) : ~0; } +static void r8411_csi_write(struct rtl8169_private *tp, int addr, int value) +{ + void __iomem *ioaddr = tp->mmio_addr; + + RTL_W32(CSIDR, value); + RTL_W32(CSIAR, CSIAR_WRITE_CMD | (addr & CSIAR_ADDR_MASK) | + CSIAR_BYTE_ENABLE << CSIAR_BYTE_ENABLE_SHIFT | + CSIAR_FUNC_NIC2); + + rtl_udelay_loop_wait_low(tp, &rtl_csiar_cond, 10, 100); +} + +static u32 r8411_csi_read(struct rtl8169_private *tp, int addr) +{ + void __iomem *ioaddr = tp->mmio_addr; + + RTL_W32(CSIAR, (addr & CSIAR_ADDR_MASK) | CSIAR_FUNC_NIC2 | + CSIAR_BYTE_ENABLE << CSIAR_BYTE_ENABLE_SHIFT); + + return rtl_udelay_loop_wait_high(tp, &rtl_csiar_cond, 10, 100) ? + RTL_R32(CSIDR) : ~0; +} + static void rtl_init_csi_ops(struct rtl8169_private *tp) { struct csi_ops *ops = &tp->csi_ops; @@ -4811,6 +4849,11 @@ static void rtl_init_csi_ops(struct rtl8169_private *tp) ops->read = r8402_csi_read; break; + case RTL_GIGA_MAC_VER_44: + ops->write = r8411_csi_write; + ops->read = r8411_csi_read; + break; + default: ops->write = r8169_csi_write; ops->read = r8169_csi_read; @@ -5255,6 +5298,25 @@ static void rtl_hw_start_8168g_2(struct rtl8169_private *tp) rtl_ephy_init(tp, e_info_8168g_2, ARRAY_SIZE(e_info_8168g_2)); } +static void rtl_hw_start_8411_2(struct rtl8169_private *tp) +{ + void __iomem *ioaddr = tp->mmio_addr; + static const struct ephy_info e_info_8411_2[] = { + { 0x00, 0x0000, 0x0008 }, + { 0x0c, 0x3df0, 0x0200 }, + { 0x0f, 0xffff, 0x5200 }, + { 0x19, 0x0020, 0x0000 }, + { 0x1e, 0x0000, 0x2000 } + }; + + rtl_hw_start_8168g_1(tp); + + /* disable aspm and clock request before access ephy */ + RTL_W8(Config2, RTL_R8(Config2) & ~ClkReqEn); + RTL_W8(Config5, RTL_R8(Config5) & ~ASPM_en); + rtl_ephy_init(tp, e_info_8411_2, ARRAY_SIZE(e_info_8411_2)); +} + static void rtl_hw_start_8168(struct net_device *dev) { struct rtl8169_private *tp = netdev_priv(dev); @@ -5361,6 +5423,10 @@ static void rtl_hw_start_8168(struct net_device *dev) rtl_hw_start_8168g_2(tp); break; + case RTL_GIGA_MAC_VER_44: + rtl_hw_start_8411_2(tp); + break; + default: printk(KERN_ERR PFX "%s: unknown chipset (mac_version = %d).\n", dev->name, tp->mac_version); @@ -6877,6 +6943,7 @@ static void rtl_hw_initialize(struct rtl8169_private *tp) case RTL_GIGA_MAC_VER_41: case RTL_GIGA_MAC_VER_42: case RTL_GIGA_MAC_VER_43: + case RTL_GIGA_MAC_VER_44: rtl_hw_init_8168g(tp); break; From 440d57bc5ff55ec1efb3efc9cbe9420b4bbdfefa Mon Sep 17 00:00:00 2001 From: dingtianhong Date: Wed, 10 Jul 2013 12:04:02 +0800 Subject: [PATCH 05/36] ifb: fix rcu_sched self-detected stalls According to the commit 16b0dc29c1af9df341428f4c49ada4f626258082 (dummy: fix rcu_sched self-detected stalls) Eric Dumazet fix the problem in dummy, but the ifb will occur the same problem like the dummy modules. Trying to "modprobe ifb numifbs=30000" triggers : INFO: rcu_sched self-detected stall on CPU After this splat, RTNL is locked and reboot is needed. We must call cond_resched() to avoid this, even holding RTNL. Signed-off-by: Ding Tianhong Signed-off-by: David S. Miller --- drivers/net/ifb.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/drivers/net/ifb.c b/drivers/net/ifb.c index dc9f6a45515d..a11f7a45cb5f 100644 --- a/drivers/net/ifb.c +++ b/drivers/net/ifb.c @@ -292,8 +292,10 @@ static int __init ifb_init_module(void) rtnl_lock(); err = __rtnl_link_register(&ifb_link_ops); - for (i = 0; i < numifbs && !err; i++) + for (i = 0; i < numifbs && !err; i++) { err = ifb_init_one(i); + cond_resched(); + } if (err) __rtnl_link_unregister(&ifb_link_ops); rtnl_unlock(); From 3dd5c3308e8b671e8e8882ba972f51cefbe9fd0d Mon Sep 17 00:00:00 2001 From: Jason Wang Date: Wed, 10 Jul 2013 13:43:27 +0800 Subject: [PATCH 06/36] tuntap: correctly linearize skb when zerocopy is used Userspace may produce vectors greater than MAX_SKB_FRAGS. When we try to linearize parts of the skb to let the rest of iov to be fit in the frags, we need count copylen into linear when calling tun_alloc_skb() instead of partly counting it into data_len. Since this breaks zerocopy_sg_from_iovec() since its inner counter assumes nr_frags should be zero at beginning. This cause nr_frags to be increased wrongly without setting the correct frags. This bug were introduced from 0690899b4d4501b3505be069b9a687e68ccbe15b (tun: experimental zero copy tx support) Cc: Michael S. Tsirkin Signed-off-by: Jason Wang Acked-by: Michael S. Tsirkin Signed-off-by: David S. Miller --- drivers/net/tun.c | 9 ++++++--- 1 file changed, 6 insertions(+), 3 deletions(-) diff --git a/drivers/net/tun.c b/drivers/net/tun.c index 7eab5fcd064f..5cdcf92eb310 100644 --- a/drivers/net/tun.c +++ b/drivers/net/tun.c @@ -1042,7 +1042,7 @@ static ssize_t tun_get_user(struct tun_struct *tun, struct tun_file *tfile, { struct tun_pi pi = { 0, cpu_to_be16(ETH_P_IP) }; struct sk_buff *skb; - size_t len = total_len, align = NET_SKB_PAD; + size_t len = total_len, align = NET_SKB_PAD, linear; struct virtio_net_hdr gso = { 0 }; int offset = 0; int copylen; @@ -1106,10 +1106,13 @@ static ssize_t tun_get_user(struct tun_struct *tun, struct tun_file *tfile, copylen = gso.hdr_len; if (!copylen) copylen = GOODCOPY_LEN; - } else + linear = copylen; + } else { copylen = len; + linear = gso.hdr_len; + } - skb = tun_alloc_skb(tfile, align, copylen, gso.hdr_len, noblock); + skb = tun_alloc_skb(tfile, align, copylen, linear, noblock); if (IS_ERR(skb)) { if (PTR_ERR(skb) != -EAGAIN) tun->dev->stats.rx_dropped++; From 61d46bf979d5cd7c164709a80ad5676a35494aae Mon Sep 17 00:00:00 2001 From: Jason Wang Date: Wed, 10 Jul 2013 13:43:28 +0800 Subject: [PATCH 07/36] macvtap: correctly linearize skb when zerocopy is used Userspace may produce vectors greater than MAX_SKB_FRAGS. When we try to linearize parts of the skb to let the rest of iov to be fit in the frags, we need count copylen into linear when calling macvtap_alloc_skb() instead of partly counting it into data_len. Since this breaks zerocopy_sg_from_iovec() since its inner counter assumes nr_frags should be zero at beginning. This cause nr_frags to be increased wrongly without setting the correct frags. This bug were introduced from b92946e2919134ebe2a4083e4302236295ea2a73 (macvtap: zerocopy: validate vectors before building skb). Cc: Michael S. Tsirkin Signed-off-by: Jason Wang Acked-by: Michael S. Tsirkin Signed-off-by: David S. Miller --- drivers/net/macvtap.c | 8 ++++++-- 1 file changed, 6 insertions(+), 2 deletions(-) diff --git a/drivers/net/macvtap.c b/drivers/net/macvtap.c index f2c4a3b218fc..876c72246ae9 100644 --- a/drivers/net/macvtap.c +++ b/drivers/net/macvtap.c @@ -712,6 +712,7 @@ static ssize_t macvtap_get_user(struct macvtap_queue *q, struct msghdr *m, int vnet_hdr_len = 0; int copylen = 0; bool zerocopy = false; + size_t linear; if (q->flags & IFF_VNET_HDR) { vnet_hdr_len = q->vnet_hdr_sz; @@ -766,11 +767,14 @@ static ssize_t macvtap_get_user(struct macvtap_queue *q, struct msghdr *m, copylen = vnet_hdr.hdr_len; if (!copylen) copylen = GOODCOPY_LEN; - } else + linear = copylen; + } else { copylen = len; + linear = vnet_hdr.hdr_len; + } skb = macvtap_alloc_skb(&q->sk, NET_IP_ALIGN, copylen, - vnet_hdr.hdr_len, noblock, &err); + linear, noblock, &err); if (!skb) goto err; From 1eb4f758286884e7566627164bca4c4a16952a83 Mon Sep 17 00:00:00 2001 From: Hannes Frederic Sowa Date: Wed, 10 Jul 2013 23:00:57 +0200 Subject: [PATCH 08/36] ipv6: in case of link failure remove route directly instead of letting it expire We could end up expiring a route which is part of an ecmp route set. Doing so would invalidate the rt->rt6i_nsiblings calculations and could provoke the following panic: [ 80.144667] ------------[ cut here ]------------ [ 80.145172] kernel BUG at net/ipv6/ip6_fib.c:733! [ 80.145172] invalid opcode: 0000 [#1] SMP [ 80.145172] Modules linked in: 8021q nf_conntrack_netbios_ns nf_conntrack_broadcast ipt_MASQUERADE ip6table_mangle ip6t_REJECT nf_conntrack_ipv6 nf_defrag_ipv6 iptable_nat nf_nat_ipv4 nf_nat iptable_mangle nf_conntrack_ipv4 nf_defrag_ipv4 xt_conntrack nf_conntrack ebtable_filter ebtables ip6table_filter ip6_tables +snd_hda_intel snd_hda_codec snd_hwdep snd_seq snd_seq_device snd_pcm snd_page_alloc snd_timer virtio_balloon snd soundcore i2c_piix4 i2c_core virtio_net virtio_blk [ 80.145172] CPU: 1 PID: 786 Comm: ping6 Not tainted 3.10.0+ #118 [ 80.145172] Hardware name: Bochs Bochs, BIOS Bochs 01/01/2011 [ 80.145172] task: ffff880117fa0000 ti: ffff880118770000 task.ti: ffff880118770000 [ 80.145172] RIP: 0010:[] [] fib6_add+0x75d/0x830 [ 80.145172] RSP: 0018:ffff880118771798 EFLAGS: 00010202 [ 80.145172] RAX: 0000000000000000 RBX: 0000000000000000 RCX: ffff88011350e480 [ 80.145172] RDX: ffff88011350e238 RSI: 0000000000000004 RDI: ffff88011350f738 [ 80.145172] RBP: ffff880118771848 R08: ffff880117903280 R09: 0000000000000001 [ 80.145172] R10: 0000000000000000 R11: 0000000000000000 R12: ffff88011350f680 [ 80.145172] R13: ffff880117903280 R14: ffff880118771890 R15: ffff88011350ef90 [ 80.145172] FS: 00007f02b5127740(0000) GS:ffff88011fd00000(0000) knlGS:0000000000000000 [ 80.145172] CS: 0010 DS: 0000 ES: 0000 CR0: 000000008005003b [ 80.145172] CR2: 00007f981322a000 CR3: 00000001181b1000 CR4: 00000000000006e0 [ 80.145172] DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 [ 80.145172] DR3: 0000000000000000 DR6: 00000000ffff0ff0 DR7: 0000000000000400 [ 80.145172] Stack: [ 80.145172] 0000000000000001 ffff880100000000 ffff880100000000 ffff880117903280 [ 80.145172] 0000000000000000 ffff880119a4cf00 0000000000000400 00000000000007fa [ 80.145172] 0000000000000000 0000000000000000 0000000000000000 ffff88011350f680 [ 80.145172] Call Trace: [ 80.145172] [] ? rt6_bind_peer+0x4b/0x90 [ 80.145172] [] __ip6_ins_rt+0x45/0x70 [ 80.145172] [] ip6_ins_rt+0x35/0x40 [ 80.145172] [] ip6_pol_route.isra.44+0x3a4/0x4b0 [ 80.145172] [] ip6_pol_route_output+0x2a/0x30 [ 80.145172] [] fib6_rule_action+0xd7/0x210 [ 80.145172] [] ? ip6_pol_route_input+0x30/0x30 [ 80.145172] [] fib_rules_lookup+0xc6/0x140 [ 80.145172] [] fib6_rule_lookup+0x44/0x80 [ 80.145172] [] ? ip6_pol_route_input+0x30/0x30 [ 80.145172] [] ip6_route_output+0x73/0xb0 [ 80.145172] [] ip6_dst_lookup_tail+0x2c3/0x2e0 [ 80.145172] [] ? list_del+0x11/0x40 [ 80.145172] [] ? remove_wait_queue+0x3c/0x50 [ 80.145172] [] ip6_dst_lookup_flow+0x3d/0xa0 [ 80.145172] [] rawv6_sendmsg+0x267/0xc20 [ 80.145172] [] inet_sendmsg+0x63/0xb0 [ 80.145172] [] ? selinux_socket_sendmsg+0x23/0x30 [ 80.145172] [] sock_sendmsg+0xa6/0xd0 [ 80.145172] [] SYSC_sendto+0x128/0x180 [ 80.145172] [] ? update_curr+0xec/0x170 [ 80.145172] [] ? kvm_clock_get_cycles+0x9/0x10 [ 80.145172] [] ? __getnstimeofday+0x3e/0xd0 [ 80.145172] [] SyS_sendto+0xe/0x10 [ 80.145172] [] system_call_fastpath+0x16/0x1b [ 80.145172] Code: fe ff ff 41 f6 45 2a 06 0f 85 ca fe ff ff 49 8b 7e 08 4c 89 ee e8 94 ef ff ff e9 b9 fe ff ff 48 8b 82 28 05 00 00 e9 01 ff ff ff <0f> 0b 49 8b 54 24 30 0d 00 00 40 00 89 83 14 01 00 00 48 89 53 [ 80.145172] RIP [] fib6_add+0x75d/0x830 [ 80.145172] RSP [ 80.387413] ---[ end trace 02f20b7a8b81ed95 ]--- [ 80.390154] Kernel panic - not syncing: Fatal exception in interrupt Cc: Nicolas Dichtel Cc: YOSHIFUJI Hideaki Signed-off-by: Hannes Frederic Sowa Signed-off-by: David S. Miller --- net/ipv6/route.c | 9 ++++++--- 1 file changed, 6 insertions(+), 3 deletions(-) diff --git a/net/ipv6/route.c b/net/ipv6/route.c index bd5fd7054031..5b127e09c224 100644 --- a/net/ipv6/route.c +++ b/net/ipv6/route.c @@ -1080,10 +1080,13 @@ static void ip6_link_failure(struct sk_buff *skb) rt = (struct rt6_info *) skb_dst(skb); if (rt) { - if (rt->rt6i_flags & RTF_CACHE) - rt6_update_expires(rt, 0); - else if (rt->rt6i_node && (rt->rt6i_flags & RTF_DEFAULT)) + if (rt->rt6i_flags & RTF_CACHE) { + dst_hold(&rt->dst); + if (ip6_del_rt(rt)) + dst_free(&rt->dst); + } else if (rt->rt6i_node && (rt->rt6i_flags & RTF_DEFAULT)) { rt->rt6i_node->fn_sernum = -1; + } } } From b41e6a51d57e231d2ed237f17f002cc536c0987c Mon Sep 17 00:00:00 2001 From: Geert Uytterhoeven Date: Wed, 10 Jul 2013 23:03:34 +0200 Subject: [PATCH 09/36] sh_eth: SH_ETH should depend on HAS_DMA If NO_DMA=y: drivers/built-in.o: In function `sh_eth_free_dma_buffer': drivers/net/ethernet/renesas/sh_eth.c:1103: undefined reference to `dma_free_coherent' drivers/net/ethernet/renesas/sh_eth.c:1110: undefined reference to `dma_free_coherent' drivers/built-in.o: In function `sh_eth_ring_init': drivers/net/ethernet/renesas/sh_eth.c:1065: undefined reference to `dma_alloc_coherent' drivers/net/ethernet/renesas/sh_eth.c:1086: undefined reference to `dma_free_coherent' drivers/built-in.o: In function `sh_eth_ring_format': drivers/net/ethernet/renesas/sh_eth.c:988: undefined reference to `dma_map_single' drivers/built-in.o: In function `sh_eth_txfree': drivers/net/ethernet/renesas/sh_eth.c:1220: undefined reference to `dma_unmap_single' drivers/built-in.o: In function `sh_eth_rx': drivers/net/ethernet/renesas/sh_eth.c:1323: undefined reference to `dma_map_single' drivers/built-in.o: In function `sh_eth_start_xmit': drivers/net/ethernet/renesas/sh_eth.c:1954: undefined reference to `dma_map_single' Signed-off-by: Geert Uytterhoeven 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 544514e66187..19a8a045e077 100644 --- a/drivers/net/ethernet/renesas/Kconfig +++ b/drivers/net/ethernet/renesas/Kconfig @@ -4,6 +4,7 @@ config SH_ETH tristate "Renesas SuperH Ethernet support" + depends on HAS_DMA select CRC32 select MII select MDIO_BITBANG From 110ecd69a9feea82a152bbf9b12aba57e6396883 Mon Sep 17 00:00:00 2001 From: Sasha Levin Date: Thu, 11 Jul 2013 13:16:54 -0400 Subject: [PATCH 10/36] 9p: fix off by one causing access violations and memory corruption p9_release_pages() would attempt to dereference one value past the end of pages[]. This would cause the following crashes: [ 6293.171817] BUG: unable to handle kernel paging request at ffff8807c96f3000 [ 6293.174146] IP: [] p9_release_pages+0x3b/0x60 [ 6293.176447] PGD 79c5067 PUD 82c1e3067 PMD 82c197067 PTE 80000007c96f3060 [ 6293.180060] Oops: 0000 [#1] PREEMPT SMP DEBUG_PAGEALLOC [ 6293.180060] Modules linked in: [ 6293.180060] CPU: 62 PID: 174043 Comm: modprobe Tainted: G W 3.10.0-next-20130710-sasha #3954 [ 6293.180060] task: ffff8807b803b000 ti: ffff880787dde000 task.ti: ffff880787dde000 [ 6293.180060] RIP: 0010:[] [] p9_release_pages+0x3b/0x60 [ 6293.214316] RSP: 0000:ffff880787ddfc28 EFLAGS: 00010202 [ 6293.214316] RAX: 0000000000000001 RBX: ffff8807c96f2ff8 RCX: 0000000000000000 [ 6293.222017] RDX: ffff8807b803b000 RSI: 0000000000000001 RDI: ffffea001c7e3d40 [ 6293.222017] RBP: ffff880787ddfc48 R08: 0000000000000000 R09: 0000000000000000 [ 6293.222017] R10: 0000000000000001 R11: 0000000000000000 R12: 0000000000000001 [ 6293.222017] R13: 0000000000000001 R14: ffff8807cc50c070 R15: ffff8807cc50c070 [ 6293.222017] FS: 00007f572641d700(0000) GS:ffff8807f3600000(0000) knlGS:0000000000000000 [ 6293.256784] CS: 0010 DS: 0000 ES: 0000 CR0: 000000008005003b [ 6293.256784] CR2: ffff8807c96f3000 CR3: 00000007c8e81000 CR4: 00000000000006e0 [ 6293.256784] Stack: [ 6293.256784] ffff880787ddfcc8 ffff880787ddfcc8 0000000000000000 ffff880787ddfcc8 [ 6293.256784] ffff880787ddfd48 ffffffff84128be8 ffff880700000002 0000000000000001 [ 6293.256784] ffff8807b803b000 ffff880787ddfce0 0000100000000000 0000000000000000 [ 6293.256784] Call Trace: [ 6293.256784] [] p9_virtio_zc_request+0x598/0x630 [ 6293.256784] [] ? wake_up_bit+0x40/0x40 [ 6293.256784] [] p9_client_zc_rpc+0x111/0x3a0 [ 6293.256784] [] ? sched_clock_cpu+0x108/0x120 [ 6293.256784] [] p9_client_read+0xe1/0x2c0 [ 6293.256784] [] v9fs_file_read+0x90/0xc0 [ 6293.256784] [] vfs_read+0xc3/0x130 [ 6293.256784] [] ? trace_hardirqs_on+0xd/0x10 [ 6293.256784] [] SyS_read+0x62/0xa0 [ 6293.256784] [] tracesys+0xdd/0xe2 [ 6293.256784] Code: 66 90 48 89 fb 41 89 f5 48 8b 3f 48 85 ff 74 29 85 f6 74 25 45 31 e4 66 0f 1f 84 00 00 00 00 00 e8 eb 14 12 fd 41 ff c4 49 63 c4 <48> 8b 3c c3 48 85 ff 74 05 45 39 e5 75 e7 48 83 c4 08 5b 41 5c [ 6293.256784] RIP [] p9_release_pages+0x3b/0x60 [ 6293.256784] RSP [ 6293.256784] CR2: ffff8807c96f3000 [ 6293.256784] ---[ end trace 50822ee72cd360fc ]--- Signed-off-by: Sasha Levin Signed-off-by: David S. Miller --- net/9p/trans_common.c | 10 +++++----- 1 file changed, 5 insertions(+), 5 deletions(-) diff --git a/net/9p/trans_common.c b/net/9p/trans_common.c index de8df957867d..2ee3879161b1 100644 --- a/net/9p/trans_common.c +++ b/net/9p/trans_common.c @@ -24,11 +24,11 @@ */ void p9_release_pages(struct page **pages, int nr_pages) { - int i = 0; - while (pages[i] && nr_pages--) { - put_page(pages[i]); - i++; - } + int i; + + for (i = 0; i < nr_pages; i++) + if (pages[i]) + put_page(pages[i]); } EXPORT_SYMBOL(p9_release_pages); From f89e57c4f5d7efdbe73b6214c73058aa335870e4 Mon Sep 17 00:00:00 2001 From: Pravin B Shelar Date: Thu, 11 Jul 2013 11:38:06 -0700 Subject: [PATCH 11/36] vxlan: Fix kernel crash on rmmod. vxlan exit module unregisters vxlan net and then it unregisters rtnl ops which triggers vxlan_dellink() from __rtnl_kill_links(). vxlan_dellink() deletes vxlan-dev from vxlan_list which has list-head in vxlan-net-struct but that is already gone due to net-unregister. That is how we are getting following crash. Following commit fixes the crash by fixing module exit path. BUG: unable to handle kernel paging request at ffff8804102c8000 IP: [] __list_del_entry+0x29/0xd0 PGD 2972067 PUD 83e019067 PMD 83df97067 PTE 80000004102c8060 Oops: 0000 [#1] SMP DEBUG_PAGEALLOC Modules linked in: --- CPU: 19 PID: 6712 Comm: rmmod Tainted: GF 3.10.0+ #95 Hardware name: Dell Inc. PowerEdge R620/0KCKR5, BIOS 1.4.8 10/25/2012 task: ffff88080c47c580 ti: ffff88080ac50000 task.ti: ffff88080ac50000 RIP: 0010:[] [] __list_del_entry+0x29/0xd0 RSP: 0018:ffff88080ac51e08 EFLAGS: 00010206 RAX: ffff8804102c8000 RBX: ffff88040f0d4b10 RCX: dead000000200200 RDX: ffff8804102c8000 RSI: ffff88080ac51e58 RDI: ffff88040f0d4b10 RBP: ffff88080ac51e08 R08: 0000000000000001 R09: 2222222222222222 R10: 2222222222222222 R11: 2222222222222222 R12: ffff88080ac51e58 R13: ffffffffa07b8840 R14: ffffffff81ae48c0 R15: ffff88080ac51e58 FS: 00007f9ef105c700(0000) GS:ffff88082a800000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: ffff8804102c8000 CR3: 00000008227e5000 CR4: 00000000000407e0 DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 DR3: 0000000000000000 DR6: 00000000ffff0ff0 DR7: 0000000000000400 Stack: ffff88080ac51e28 ffffffff812cc6a1 2222222222222222 ffff88040f0d4000 ffff88080ac51e48 ffffffffa07b3311 ffff88040f0d4000 ffffffff81ae49c8 ffff88080ac51e98 ffffffff81492fc2 ffff88080ac51e58 ffff88080ac51e58 Call Trace: [] list_del+0x11/0x40 [] vxlan_dellink+0x51/0x70 [vxlan] [] __rtnl_link_unregister+0xa2/0xb0 [] rtnl_link_unregister+0x1e/0x30 [] vxlan_cleanup_module+0x1c/0x2f [vxlan] [] SyS_delete_module+0x1d1/0x2c0 [] ? trace_hardirqs_on_thunk+0x3a/0x3f [] system_call_fastpath+0x16/0x1b Code: eb 9f 55 48 8b 17 48 b9 00 01 10 00 00 00 ad de 48 8b 47 08 48 89 e5 48 39 ca 74 29 48 b9 00 02 20 00 00 00 ad de 48 39 c8 74 7a <4c> 8b 00 4c 39 c7 75 53 4c 8b 42 08 4c 39 c7 75 2b 48 89 42 08 RIP [] __list_del_entry+0x29/0xd0 RSP CR2: ffff8804102c8000 Signed-off-by: Pravin B Shelar Signed-off-by: David S. Miller --- drivers/net/vxlan.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/net/vxlan.c b/drivers/net/vxlan.c index 227b54a1f88a..0ba1e7edbb1b 100644 --- a/drivers/net/vxlan.c +++ b/drivers/net/vxlan.c @@ -1916,9 +1916,9 @@ late_initcall(vxlan_init_module); static void __exit vxlan_cleanup_module(void) { - unregister_pernet_device(&vxlan_net_ops); rtnl_link_unregister(&vxlan_link_ops); destroy_workqueue(vxlan_wq); + unregister_pernet_device(&vxlan_net_ops); rcu_barrier(); } module_exit(vxlan_cleanup_module); From a8798a5c77c9981e88caef1373a3310bf8aed219 Mon Sep 17 00:00:00 2001 From: Maarten Lankhorst Date: Thu, 11 Jul 2013 15:53:21 +0200 Subject: [PATCH 12/36] alx: fix lockdep annotation Move spin_lock_init to be called before the spinlocks are used, preventing a lockdep splat. Signed-off-by: Maarten Lankhorst Signed-off-by: David S. Miller --- drivers/net/ethernet/atheros/alx/main.c | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-) diff --git a/drivers/net/ethernet/atheros/alx/main.c b/drivers/net/ethernet/atheros/alx/main.c index 0e0b242a9dd4..027398ebbba6 100644 --- a/drivers/net/ethernet/atheros/alx/main.c +++ b/drivers/net/ethernet/atheros/alx/main.c @@ -1245,6 +1245,8 @@ static int alx_probe(struct pci_dev *pdev, const struct pci_device_id *ent) SET_NETDEV_DEV(netdev, &pdev->dev); alx = netdev_priv(netdev); + spin_lock_init(&alx->hw.mdio_lock); + spin_lock_init(&alx->irq_lock); alx->dev = netdev; alx->hw.pdev = pdev; alx->msg_enable = NETIF_MSG_LINK | NETIF_MSG_HW | NETIF_MSG_IFUP | @@ -1327,9 +1329,6 @@ static int alx_probe(struct pci_dev *pdev, const struct pci_device_id *ent) INIT_WORK(&alx->link_check_wk, alx_link_check); INIT_WORK(&alx->reset_wk, alx_reset); - spin_lock_init(&alx->hw.mdio_lock); - spin_lock_init(&alx->irq_lock); - netif_carrier_off(netdev); err = register_netdev(netdev); From 1b4fc0e249d61916b8a525b0e7b3c028232457c9 Mon Sep 17 00:00:00 2001 From: Dmitry Kravkov Date: Thu, 11 Jul 2013 15:48:21 +0300 Subject: [PATCH 13/36] bnx2x: fix tunneling CSUM calculation Since commit c957d09ffda417f6c8e3d1f10e2b05228607d6d7 "bnx2x: Remove sparse and coccinelle warnings" driver provided wrong partial csum for HW in tunneing scenarios. Reported-by: Eric Dumazet CC: Alexander Duyck CC: Pravin Shelar CC: Cong Wang Signed-off-by: Dmitry Kravkov Tested-by: Eric Dumazet Signed-off-by: David S. Miller --- drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c index 3353efe79194..ee350bde1818 100644 --- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c +++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c @@ -3543,9 +3543,9 @@ static void bnx2x_update_pbds_gso_enc(struct sk_buff *skb, /* outer IP header info */ if (xmit_type & XMIT_CSUM_V4) { struct iphdr *iph = ip_hdr(skb); - u16 csum = (__force u16)(~iph->check) - - (__force u16)iph->tot_len - - (__force u16)iph->frag_off; + u32 csum = (__force u32)(~iph->check) - + (__force u32)iph->tot_len - + (__force u32)iph->frag_off; pbd2->fw_ip_csum_wo_len_flags_frag = bswab16(csum_fold((__force __wsum)csum)); From afc154e978de1eb11c555bc8bcec1552f75ebc43 Mon Sep 17 00:00:00 2001 From: Hannes Frederic Sowa Date: Thu, 11 Jul 2013 12:43:42 +0200 Subject: [PATCH 14/36] ipv6: fix route selection if kernel is not compiled with CONFIG_IPV6_ROUTER_PREF This is a follow-up patch to 3630d40067a21d4dfbadc6002bb469ce26ac5d52 ("ipv6: rt6_check_neigh should successfully verify neigh if no NUD information are available"). Since the removal of rt->n in rt6_info we can end up with a dst == NULL in rt6_check_neigh. In case the kernel is not compiled with CONFIG_IPV6_ROUTER_PREF we should also select a route with unkown NUD state but we must not avoid doing round robin selection on routes with the same target. So introduce and pass down a boolean ``do_rr'' to indicate when we should update rt->rr_ptr. As soon as no route is valid we do backtracking and do a lookup on a higher level in the fib trie. v2: a) Improved rt6_check_neigh logic (no need to create neighbour there) and documented return values. v3: a) Introduce enum rt6_nud_state to get rid of the magic numbers (thanks to David Miller). b) Update and shorten commit message a bit to actualy reflect the source. Reported-by: Pierre Emeriaud Cc: YOSHIFUJI Hideaki Signed-off-by: Hannes Frederic Sowa Signed-off-by: David S. Miller --- net/ipv6/route.c | 69 ++++++++++++++++++++++++++++++------------------ 1 file changed, 43 insertions(+), 26 deletions(-) diff --git a/net/ipv6/route.c b/net/ipv6/route.c index 5b127e09c224..a8c891aa2464 100644 --- a/net/ipv6/route.c +++ b/net/ipv6/route.c @@ -65,6 +65,12 @@ #include #endif +enum rt6_nud_state { + RT6_NUD_FAIL_HARD = -2, + RT6_NUD_FAIL_SOFT = -1, + RT6_NUD_SUCCEED = 1 +}; + static struct rt6_info *ip6_rt_copy(struct rt6_info *ort, const struct in6_addr *dest); static struct dst_entry *ip6_dst_check(struct dst_entry *dst, u32 cookie); @@ -531,28 +537,29 @@ static inline int rt6_check_dev(struct rt6_info *rt, int oif) return 0; } -static inline bool rt6_check_neigh(struct rt6_info *rt) +static inline enum rt6_nud_state rt6_check_neigh(struct rt6_info *rt) { struct neighbour *neigh; - bool ret = false; + enum rt6_nud_state ret = RT6_NUD_FAIL_HARD; if (rt->rt6i_flags & RTF_NONEXTHOP || !(rt->rt6i_flags & RTF_GATEWAY)) - return true; + return RT6_NUD_SUCCEED; rcu_read_lock_bh(); neigh = __ipv6_neigh_lookup_noref(rt->dst.dev, &rt->rt6i_gateway); if (neigh) { read_lock(&neigh->lock); if (neigh->nud_state & NUD_VALID) - ret = true; + ret = RT6_NUD_SUCCEED; #ifdef CONFIG_IPV6_ROUTER_PREF else if (!(neigh->nud_state & NUD_FAILED)) - ret = true; + ret = RT6_NUD_SUCCEED; #endif read_unlock(&neigh->lock); - } else if (IS_ENABLED(CONFIG_IPV6_ROUTER_PREF)) { - ret = true; + } else { + ret = IS_ENABLED(CONFIG_IPV6_ROUTER_PREF) ? + RT6_NUD_SUCCEED : RT6_NUD_FAIL_SOFT; } rcu_read_unlock_bh(); @@ -566,43 +573,52 @@ static int rt6_score_route(struct rt6_info *rt, int oif, m = rt6_check_dev(rt, oif); if (!m && (strict & RT6_LOOKUP_F_IFACE)) - return -1; + return RT6_NUD_FAIL_HARD; #ifdef CONFIG_IPV6_ROUTER_PREF m |= IPV6_DECODE_PREF(IPV6_EXTRACT_PREF(rt->rt6i_flags)) << 2; #endif - if (!rt6_check_neigh(rt) && (strict & RT6_LOOKUP_F_REACHABLE)) - return -1; + if (strict & RT6_LOOKUP_F_REACHABLE) { + int n = rt6_check_neigh(rt); + if (n < 0) + return n; + } return m; } static struct rt6_info *find_match(struct rt6_info *rt, int oif, int strict, - int *mpri, struct rt6_info *match) + int *mpri, struct rt6_info *match, + bool *do_rr) { int m; + bool match_do_rr = false; if (rt6_check_expired(rt)) goto out; m = rt6_score_route(rt, oif, strict); - if (m < 0) + if (m == RT6_NUD_FAIL_SOFT && !IS_ENABLED(CONFIG_IPV6_ROUTER_PREF)) { + match_do_rr = true; + m = 0; /* lowest valid score */ + } else if (m < 0) { goto out; - - if (m > *mpri) { - if (strict & RT6_LOOKUP_F_REACHABLE) - rt6_probe(match); - *mpri = m; - match = rt; - } else if (strict & RT6_LOOKUP_F_REACHABLE) { - rt6_probe(rt); } + if (strict & RT6_LOOKUP_F_REACHABLE) + rt6_probe(rt); + + if (m > *mpri) { + *do_rr = match_do_rr; + *mpri = m; + match = rt; + } out: return match; } static struct rt6_info *find_rr_leaf(struct fib6_node *fn, struct rt6_info *rr_head, - u32 metric, int oif, int strict) + u32 metric, int oif, int strict, + bool *do_rr) { struct rt6_info *rt, *match; int mpri = -1; @@ -610,10 +626,10 @@ static struct rt6_info *find_rr_leaf(struct fib6_node *fn, match = NULL; for (rt = rr_head; rt && rt->rt6i_metric == metric; rt = rt->dst.rt6_next) - match = find_match(rt, oif, strict, &mpri, match); + match = find_match(rt, oif, strict, &mpri, match, do_rr); for (rt = fn->leaf; rt && rt != rr_head && rt->rt6i_metric == metric; rt = rt->dst.rt6_next) - match = find_match(rt, oif, strict, &mpri, match); + match = find_match(rt, oif, strict, &mpri, match, do_rr); return match; } @@ -622,15 +638,16 @@ static struct rt6_info *rt6_select(struct fib6_node *fn, int oif, int strict) { struct rt6_info *match, *rt0; struct net *net; + bool do_rr = false; rt0 = fn->rr_ptr; if (!rt0) fn->rr_ptr = rt0 = fn->leaf; - match = find_rr_leaf(fn, rt0, rt0->rt6i_metric, oif, strict); + match = find_rr_leaf(fn, rt0, rt0->rt6i_metric, oif, strict, + &do_rr); - if (!match && - (strict & RT6_LOOKUP_F_REACHABLE)) { + if (do_rr) { struct rt6_info *next = rt0->dst.rt6_next; /* no entries matched; do round-robin */ From ce9a1bf8e6c65d2ab6786e759952a3548347ad6f Mon Sep 17 00:00:00 2001 From: Helmut Schaa Date: Thu, 11 Jul 2013 13:57:34 +0200 Subject: [PATCH 15/36] drivers: net: phy: at803x: Add missing mdio device id at803x supports Atheros 8030, 8031 and 8035 PHYs. 8031 was missing from the mdio device id table. Signed-off-by: Helmut Schaa Signed-off-by: David S. Miller --- drivers/net/phy/at803x.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/net/phy/at803x.c b/drivers/net/phy/at803x.c index 1f7091b3c27c..ac22283aaf23 100644 --- a/drivers/net/phy/at803x.c +++ b/drivers/net/phy/at803x.c @@ -217,6 +217,7 @@ module_exit(atheros_exit); static struct mdio_device_id __maybe_unused atheros_tbl[] = { { 0x004dd076, 0xffffffef }, + { 0x004dd074, 0xffffffef }, { 0x004dd072, 0xffffffef }, { } }; From 2c8a01894a12665d8059fad8f0a293c98a264121 Mon Sep 17 00:00:00 2001 From: dingtianhong Date: Thu, 11 Jul 2013 19:04:02 +0800 Subject: [PATCH 16/36] dummy: fix oops when loading the dummy failed We rename the dummy in modprobe.conf like this: install dummy0 /sbin/modprobe -o dummy0 --ignore-install dummy install dummy1 /sbin/modprobe -o dummy1 --ignore-install dummy We got oops when we run the command: modprobe dummy0 modprobe dummy1 ------------[ cut here ]------------ [ 3302.187584] BUG: unable to handle kernel NULL pointer dereference at 0000000000000008 [ 3302.195411] IP: [] __rtnl_link_unregister+0x9a/0xd0 [ 3302.201844] PGD 85c94a067 PUD 8517bd067 PMD 0 [ 3302.206305] Oops: 0002 [#1] SMP [ 3302.299737] task: ffff88105ccea300 ti: ffff880eba4a0000 task.ti: ffff880eba4a0000 [ 3302.307186] RIP: 0010:[] [] __rtnl_link_unregister+0x9a/0xd0 [ 3302.316044] RSP: 0018:ffff880eba4a1dd8 EFLAGS: 00010246 [ 3302.321332] RAX: 0000000000000000 RBX: ffffffff81a9d738 RCX: 0000000000000002 [ 3302.328436] RDX: 0000000000000000 RSI: ffffffffa04d602c RDI: ffff880eba4a1dd8 [ 3302.335541] RBP: ffff880eba4a1e18 R08: dead000000200200 R09: dead000000100100 [ 3302.342644] R10: 0000000000000080 R11: 0000000000000003 R12: ffffffff81a9d788 [ 3302.349748] R13: ffffffffa04d7020 R14: ffffffff81a9d670 R15: ffff880eba4a1dd8 [ 3302.364910] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [ 3302.370630] CR2: 0000000000000008 CR3: 000000085e15e000 CR4: 00000000000427e0 [ 3302.377734] DR0: 0000000000000003 DR1: 00000000000000b0 DR2: 0000000000000001 [ 3302.384838] DR3: 0000000000000000 DR6: 00000000ffff0ff0 DR7: 0000000000000400 [ 3302.391940] Stack: [ 3302.393944] ffff880eba4a1dd8 ffff880eba4a1dd8 ffff880eba4a1e18 ffffffffa04d70c0 [ 3302.401350] 00000000ffffffef ffffffffa01a8000 0000000000000000 ffffffff816111c8 [ 3302.408758] ffff880eba4a1e48 ffffffffa01a80be ffff880eba4a1e48 ffffffffa04d70c0 [ 3302.416164] Call Trace: [ 3302.418605] [] ? 0xffffffffa01a7fff [ 3302.423727] [] dummy_init_module+0xbe/0x1000 [dummy0] [ 3302.430405] [] ? 0xffffffffa01a7fff [ 3302.435535] [] do_one_initcall+0x152/0x1b0 [ 3302.441263] [] do_init_module+0x7b/0x200 [ 3302.446824] [] load_module+0x4e2/0x530 [ 3302.452215] [] ? ddebug_dyndbg_boot_param_cb+0x60/0x60 [ 3302.458979] [] SyS_init_module+0xd1/0x130 [ 3302.464627] [] system_call_fastpath+0x16/0x1b [ 3302.490090] RIP [] __rtnl_link_unregister+0x9a/0xd0 [ 3302.496607] RSP [ 3302.500084] CR2: 0000000000000008 [ 3302.503466] ---[ end trace 8342d49cd49f78ed ]--- The reason is that when loading dummy, if __rtnl_link_register() return failed, the init_module should return and avoid take the wrong path. Signed-off-by: Tan Xiaojun Signed-off-by: Ding Tianhong Signed-off-by: David S. Miller --- drivers/net/dummy.c | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/drivers/net/dummy.c b/drivers/net/dummy.c index 42aa54af6842..b710c6b2d659 100644 --- a/drivers/net/dummy.c +++ b/drivers/net/dummy.c @@ -185,6 +185,8 @@ static int __init dummy_init_module(void) rtnl_lock(); err = __rtnl_link_register(&dummy_link_ops); + if (err < 0) + goto out; for (i = 0; i < numdummies && !err; i++) { err = dummy_init_one(); @@ -192,6 +194,8 @@ static int __init dummy_init_module(void) } if (err < 0) __rtnl_link_unregister(&dummy_link_ops); + +out: rtnl_unlock(); return err; From f2966cd5691058b8674a20766525bedeaea9cbcf Mon Sep 17 00:00:00 2001 From: dingtianhong Date: Thu, 11 Jul 2013 19:04:06 +0800 Subject: [PATCH 17/36] ifb: fix oops when loading the ifb failed If __rtnl_link_register() return faild when loading the ifb, it will take the wrong path and get oops, so fix it just like dummy. Signed-off-by: Ding Tianhong Signed-off-by: David S. Miller --- drivers/net/ifb.c | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/drivers/net/ifb.c b/drivers/net/ifb.c index a11f7a45cb5f..a3bed28197d2 100644 --- a/drivers/net/ifb.c +++ b/drivers/net/ifb.c @@ -291,6 +291,8 @@ static int __init ifb_init_module(void) rtnl_lock(); err = __rtnl_link_register(&ifb_link_ops); + if (err < 0) + goto out; for (i = 0; i < numifbs && !err; i++) { err = ifb_init_one(i); @@ -298,6 +300,8 @@ static int __init ifb_init_module(void) } if (err) __rtnl_link_unregister(&ifb_link_ops); + +out: rtnl_unlock(); return err; From 3b8ccd447375acebed9af0a3798e1ab4e58bedf4 Mon Sep 17 00:00:00 2001 From: Camelia Groza Date: Thu, 11 Jul 2013 09:55:51 +0300 Subject: [PATCH 18/36] inet: fix spacing in assignment Found using checkpatch.pl Signed-off-by: Camelia Groza Signed-off-by: David S. Miller --- net/ipv4/inet_hashtables.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/net/ipv4/inet_hashtables.c b/net/ipv4/inet_hashtables.c index 6af375afeeef..7bd8983dbfcf 100644 --- a/net/ipv4/inet_hashtables.c +++ b/net/ipv4/inet_hashtables.c @@ -467,7 +467,7 @@ void inet_unhash(struct sock *sk) lock = inet_ehash_lockp(hashinfo, sk->sk_hash); spin_lock_bh(lock); - done =__sk_nulls_del_node_init_rcu(sk); + done = __sk_nulls_del_node_init_rcu(sk); if (done) sock_prot_inuse_add(sock_net(sk), sk->sk_prot, -1); spin_unlock_bh(lock); From cdbaa0bb26d8116d00be24e6b49043777b382f3a Mon Sep 17 00:00:00 2001 From: Alexander Duyck Date: Wed, 10 Jul 2013 17:05:06 -0700 Subject: [PATCH 19/36] gso: Update tunnel segmentation to support Tx checksum offload This change makes it so that the GRE and VXLAN tunnels can make use of Tx checksum offload support provided by some drivers via the hw_enc_features. Without this fix enabling GSO means sacrificing Tx checksum offload and this actually leads to a performance regression as shown below: Utilization Send Throughput local GSO 10^6bits/s % S state 6276.51 8.39 enabled 7123.52 8.42 disabled To resolve this it was necessary to address two items. First netif_skb_features needed to be updated so that it would correctly handle the Trans Ether Bridging protocol without impacting the need to check for Q-in-Q tagging. To do this it was necessary to update harmonize_features so that it used skb_network_protocol instead of just using the outer protocol. Second it was necessary to update the GRE and UDP tunnel segmentation offloads so that they would reset the encapsulation bit and inner header offsets after the offload was complete. As a result of this change I have seen the following results on a interface with Tx checksum enabled for encapsulated frames: Utilization Send Throughput local GSO 10^6bits/s % S state 7123.52 8.42 disabled 8321.75 5.43 enabled v2: Instead of replacing refrence to skb->protocol with skb_network_protocol just replace the protocol reference in harmonize_features to allow for double VLAN tag checks. Signed-off-by: Alexander Duyck Signed-off-by: David S. Miller --- net/core/dev.c | 14 ++++++-------- net/ipv4/gre_offload.c | 3 +++ net/ipv4/udp.c | 4 +++- 3 files changed, 12 insertions(+), 9 deletions(-) diff --git a/net/core/dev.c b/net/core/dev.c index 560dafd83adf..a3d8d44cb7f4 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -2481,10 +2481,10 @@ static int dev_gso_segment(struct sk_buff *skb, netdev_features_t features) } static netdev_features_t harmonize_features(struct sk_buff *skb, - __be16 protocol, netdev_features_t features) + netdev_features_t features) { if (skb->ip_summed != CHECKSUM_NONE && - !can_checksum_protocol(features, protocol)) { + !can_checksum_protocol(features, skb_network_protocol(skb))) { features &= ~NETIF_F_ALL_CSUM; } else if (illegal_highdma(skb->dev, skb)) { features &= ~NETIF_F_SG; @@ -2505,20 +2505,18 @@ netdev_features_t netif_skb_features(struct sk_buff *skb) struct vlan_ethhdr *veh = (struct vlan_ethhdr *)skb->data; protocol = veh->h_vlan_encapsulated_proto; } else if (!vlan_tx_tag_present(skb)) { - return harmonize_features(skb, protocol, features); + return harmonize_features(skb, 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)) { - return harmonize_features(skb, protocol, features); - } else { + 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; - return harmonize_features(skb, protocol, features); - } + + return harmonize_features(skb, features); } EXPORT_SYMBOL(netif_skb_features); diff --git a/net/ipv4/gre_offload.c b/net/ipv4/gre_offload.c index 775d5b532ece..55e6bfb3a289 100644 --- a/net/ipv4/gre_offload.c +++ b/net/ipv4/gre_offload.c @@ -100,6 +100,9 @@ static struct sk_buff *gre_gso_segment(struct sk_buff *skb, } __skb_push(skb, tnl_hlen - ghl); + skb_reset_inner_headers(skb); + skb->encapsulation = 1; + skb_reset_mac_header(skb); skb_set_network_header(skb, mac_len); skb->mac_len = mac_len; diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c index a0d7151ffbd9..766e6bab9113 100644 --- a/net/ipv4/udp.c +++ b/net/ipv4/udp.c @@ -2323,6 +2323,9 @@ struct sk_buff *skb_udp_tunnel_segment(struct sk_buff *skb, struct udphdr *uh; int udp_offset = outer_hlen - tnl_hlen; + skb_reset_inner_headers(skb); + skb->encapsulation = 1; + skb->mac_len = mac_len; skb_push(skb, outer_hlen); @@ -2345,7 +2348,6 @@ struct sk_buff *skb_udp_tunnel_segment(struct sk_buff *skb, uh->check = CSUM_MANGLED_0; } - skb->ip_summed = CHECKSUM_NONE; skb->protocol = protocol; } while ((skb = skb->next)); out: From 87f1369d6e2e820c77cf9eac542eed4dcf036f64 Mon Sep 17 00:00:00 2001 From: Paolo Valente Date: Wed, 10 Jul 2013 15:46:08 +0200 Subject: [PATCH 20/36] pkt_sched: sch_qfq: improve efficiency of make_eligible In make_eligible, a mask is used to decide which groups must become eligible: the i-th group becomes eligible only if the i-th bit of the mask (from the right) is set. The mask is computed by left-shifting a 1 by a given number of places, and decrementing the result. The shift is performed on a ULL to avoid problems in case the number of places to shift is higher than 31. On a 32-bit machine, this is more costly than working on an UL. This patch replaces such a costly operation with two cheaper branches. The trick is based on the following fact: in case of a shift of at least 32 places, the resulting mask has at least the 32 less significant bits set, whereas the total number of groups is lower than 32. As a consequence, in this case it is enough to just set the 32 less significant bits of the mask with a cheaper ~0UL. In the other case, the shift can be safely performed on a UL. Reported-by: David S. Miller Reported-by: David Laight Signed-off-by: Paolo Valente Signed-off-by: David S. Miller --- net/sched/sch_qfq.c | 9 ++++++++- 1 file changed, 8 insertions(+), 1 deletion(-) diff --git a/net/sched/sch_qfq.c b/net/sched/sch_qfq.c index 7c195d972bf0..8d86a8b5522a 100644 --- a/net/sched/sch_qfq.c +++ b/net/sched/sch_qfq.c @@ -821,7 +821,14 @@ static void qfq_make_eligible(struct qfq_sched *q) unsigned long old_vslot = q->oldV >> q->min_slot_shift; if (vslot != old_vslot) { - unsigned long mask = (1ULL << fls(vslot ^ old_vslot)) - 1; + unsigned long mask; + int last_flip_pos = fls(vslot ^ old_vslot); + + if (last_flip_pos > 31) /* higher than the number of groups */ + mask = ~0UL; /* make all groups eligible */ + else + mask = (1UL << last_flip_pos) - 1; + qfq_move_groups(q, mask, IR, ER); qfq_move_groups(q, mask, IB, EB); } From 88d4f419a43b474a4524f41f55c36bee13416bdd Mon Sep 17 00:00:00 2001 From: Paolo Valente Date: Wed, 10 Jul 2013 15:46:09 +0200 Subject: [PATCH 21/36] pkt_sched: sch_qfq: remove forward declaration of qfq_update_agg_ts This patch removes the forward declaration of qfq_update_agg_ts, by moving the definition of the function above its first call. This patch also removes a useless forward declaration of qfq_schedule_agg. Reported-by: David S. Miller Signed-off-by: Paolo Valente Signed-off-by: David S. Miller --- net/sched/sch_qfq.c | 118 +++++++++++++++++++++----------------------- 1 file changed, 55 insertions(+), 63 deletions(-) diff --git a/net/sched/sch_qfq.c b/net/sched/sch_qfq.c index 8d86a8b5522a..a7ab323849b6 100644 --- a/net/sched/sch_qfq.c +++ b/net/sched/sch_qfq.c @@ -1010,9 +1010,61 @@ static inline void charge_actual_service(struct qfq_aggregate *agg) agg->F = agg->S + (u64)service_received * agg->inv_w; } -static inline void qfq_update_agg_ts(struct qfq_sched *q, - struct qfq_aggregate *agg, - enum update_reason reason); +/* Assign a reasonable start time for a new aggregate in group i. + * Admissible values for \hat(F) are multiples of \sigma_i + * no greater than V+\sigma_i . Larger values mean that + * we had a wraparound so we consider the timestamp to be stale. + * + * If F is not stale and F >= V then we set S = F. + * Otherwise we should assign S = V, but this may violate + * the ordering in EB (see [2]). So, if we have groups in ER, + * set S to the F_j of the first group j which would be blocking us. + * We are guaranteed not to move S backward because + * otherwise our group i would still be blocked. + */ +static void qfq_update_start(struct qfq_sched *q, struct qfq_aggregate *agg) +{ + unsigned long mask; + u64 limit, roundedF; + int slot_shift = agg->grp->slot_shift; + + roundedF = qfq_round_down(agg->F, slot_shift); + limit = qfq_round_down(q->V, slot_shift) + (1ULL << slot_shift); + + if (!qfq_gt(agg->F, q->V) || qfq_gt(roundedF, limit)) { + /* timestamp was stale */ + mask = mask_from(q->bitmaps[ER], agg->grp->index); + if (mask) { + struct qfq_group *next = qfq_ffs(q, mask); + if (qfq_gt(roundedF, next->F)) { + if (qfq_gt(limit, next->F)) + agg->S = next->F; + else /* preserve timestamp correctness */ + agg->S = limit; + return; + } + } + agg->S = q->V; + } else /* timestamp is not stale */ + agg->S = agg->F; +} + +/* Update the timestamps of agg before scheduling/rescheduling it for + * service. In particular, assign to agg->F its maximum possible + * value, i.e., the virtual finish time with which the aggregate + * should be labeled if it used all its budget once in service. + */ +static inline void +qfq_update_agg_ts(struct qfq_sched *q, + struct qfq_aggregate *agg, enum update_reason reason) +{ + if (reason != requeue) + qfq_update_start(q, agg); + else /* just charge agg for the service received */ + agg->S = agg->F; + + agg->F = agg->S + (u64)agg->budgetmax * agg->inv_w; +} static void qfq_schedule_agg(struct qfq_sched *q, struct qfq_aggregate *agg); @@ -1135,66 +1187,6 @@ static struct qfq_aggregate *qfq_choose_next_agg(struct qfq_sched *q) return agg; } -/* - * Assign a reasonable start time for a new aggregate in group i. - * Admissible values for \hat(F) are multiples of \sigma_i - * no greater than V+\sigma_i . Larger values mean that - * we had a wraparound so we consider the timestamp to be stale. - * - * If F is not stale and F >= V then we set S = F. - * Otherwise we should assign S = V, but this may violate - * the ordering in EB (see [2]). So, if we have groups in ER, - * set S to the F_j of the first group j which would be blocking us. - * We are guaranteed not to move S backward because - * otherwise our group i would still be blocked. - */ -static void qfq_update_start(struct qfq_sched *q, struct qfq_aggregate *agg) -{ - unsigned long mask; - u64 limit, roundedF; - int slot_shift = agg->grp->slot_shift; - - roundedF = qfq_round_down(agg->F, slot_shift); - limit = qfq_round_down(q->V, slot_shift) + (1ULL << slot_shift); - - if (!qfq_gt(agg->F, q->V) || qfq_gt(roundedF, limit)) { - /* timestamp was stale */ - mask = mask_from(q->bitmaps[ER], agg->grp->index); - if (mask) { - struct qfq_group *next = qfq_ffs(q, mask); - if (qfq_gt(roundedF, next->F)) { - if (qfq_gt(limit, next->F)) - agg->S = next->F; - else /* preserve timestamp correctness */ - agg->S = limit; - return; - } - } - agg->S = q->V; - } else /* timestamp is not stale */ - agg->S = agg->F; -} - -/* - * Update the timestamps of agg before scheduling/rescheduling it for - * service. In particular, assign to agg->F its maximum possible - * value, i.e., the virtual finish time with which the aggregate - * should be labeled if it used all its budget once in service. - */ -static inline void -qfq_update_agg_ts(struct qfq_sched *q, - struct qfq_aggregate *agg, enum update_reason reason) -{ - if (reason != requeue) - qfq_update_start(q, agg); - else /* just charge agg for the service received */ - agg->S = agg->F; - - agg->F = agg->S + (u64)agg->budgetmax * agg->inv_w; -} - -static void qfq_schedule_agg(struct qfq_sched *, struct qfq_aggregate *); - static int qfq_enqueue(struct sk_buff *skb, struct Qdisc *sch) { struct qfq_sched *q = qdisc_priv(sch); From 8c91e162e058bb91b7766f26f4d5823a21941026 Mon Sep 17 00:00:00 2001 From: Alexander Duyck Date: Thu, 11 Jul 2013 13:12:22 -0700 Subject: [PATCH 22/36] gre: Fix MTU sizing check for gretap tunnels This change fixes an MTU sizing issue seen with gretap tunnels when non-gso packets are sent from the interface. In my case I was able to reproduce the issue by simply sending a ping of 1421 bytes with the gretap interface created on a device with a standard 1500 mtu. This fix is based on the fact that the tunnel mtu is already adjusted by dev->hard_header_len so it would make sense that any packets being compared against that mtu should also be adjusted by hard_header_len and the tunnel header instead of just the tunnel header. Signed-off-by: Alexander Duyck Reported-by: Cong Wang Acked-by: Eric Dumazet Signed-off-by: David S. Miller --- net/ipv4/ip_tunnel.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/net/ipv4/ip_tunnel.c b/net/ipv4/ip_tunnel.c index 945734b2f209..ca1cb2d5f6e2 100644 --- a/net/ipv4/ip_tunnel.c +++ b/net/ipv4/ip_tunnel.c @@ -476,7 +476,7 @@ static int tnl_update_pmtu(struct net_device *dev, struct sk_buff *skb, struct rtable *rt, __be16 df) { struct ip_tunnel *tunnel = netdev_priv(dev); - int pkt_size = skb->len - tunnel->hlen; + int pkt_size = skb->len - tunnel->hlen - dev->hard_header_len; int mtu; if (df) From 7ad031ee468e4ed9196215394d7e18a78a66a7da Mon Sep 17 00:00:00 2001 From: Jitendra Kalsaria Date: Wed, 10 Jul 2013 14:00:22 -0400 Subject: [PATCH 23/36] qlcnic: Adding Maintainers. Signed-off-by: Jitendra Kalsaria Signed-off-by: David S. Miller --- MAINTAINERS | 2 ++ 1 file changed, 2 insertions(+) diff --git a/MAINTAINERS b/MAINTAINERS index 37f9a71c744f..6a904d30d6a2 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -6651,10 +6651,12 @@ F: Documentation/networking/LICENSE.qla3xxx F: drivers/net/ethernet/qlogic/qla3xxx.* QLOGIC QLCNIC (1/10)Gb ETHERNET DRIVER +M: Himanshu Madhani M: Rajesh Borundia M: Shahed Shaikh M: Jitendra Kalsaria M: Sony Chacko +M: Sucheta Chakraborty M: linux-driver@qlogic.com L: netdev@vger.kernel.org S: Supported From d77e41e12744e53ca7f98f920350998b5f00c93a Mon Sep 17 00:00:00 2001 From: Andy Shevchenko Date: Wed, 10 Jul 2013 17:30:34 +0300 Subject: [PATCH 24/36] net/tipc: use %*phC to dump small buffers in hex form Instead of passing each byte by stack let's use nice specifier for that. Signed-off-by: Andy Shevchenko Signed-off-by: David S. Miller --- net/tipc/ib_media.c | 8 +------- 1 file changed, 1 insertion(+), 7 deletions(-) diff --git a/net/tipc/ib_media.c b/net/tipc/ib_media.c index ad2e1ec4117e..9934a32bfa87 100644 --- a/net/tipc/ib_media.c +++ b/net/tipc/ib_media.c @@ -292,13 +292,7 @@ static int ib_addr2str(struct tipc_media_addr *a, char *str_buf, int str_size) if (str_size < 60) /* 60 = 19 * strlen("xx:") + strlen("xx\0") */ return 1; - sprintf(str_buf, "%02x:%02x:%02x:%02x:%02x:%02x:%02x:%02x:%02x:%02x:" - "%02x:%02x:%02x:%02x:%02x:%02x:%02x:%02x:%02x:%02x", - a->value[0], a->value[1], a->value[2], a->value[3], - a->value[4], a->value[5], a->value[6], a->value[7], - a->value[8], a->value[9], a->value[10], a->value[11], - a->value[12], a->value[13], a->value[14], a->value[15], - a->value[16], a->value[17], a->value[18], a->value[19]); + sprintf(str_buf, "%20phC", a->value); return 0; } From c073f666ff5c38477849c5109f2c430df1a60e82 Mon Sep 17 00:00:00 2001 From: hayeswang Date: Mon, 8 Jul 2013 10:41:21 +0800 Subject: [PATCH 25/36] net/usb: add relative mii functions for r815x Base on cdc_ether, add the mii functions for RTL8152 and RTL8153. The RTL8152 and RTL8153 support ECM mode which use the driver of cdc_ether. Add the mii functions. Then, the basic PHY access is possible. Signed-off-by: Hayes Wang Signed-off-by: David S. Miller --- drivers/net/usb/Makefile | 2 +- drivers/net/usb/cdc_ether.c | 9 +- drivers/net/usb/r815x.c | 231 ++++++++++++++++++++++++++++++++++++ 3 files changed, 239 insertions(+), 3 deletions(-) create mode 100644 drivers/net/usb/r815x.c diff --git a/drivers/net/usb/Makefile b/drivers/net/usb/Makefile index 9ab5c9d4b45a..e8171784529d 100644 --- a/drivers/net/usb/Makefile +++ b/drivers/net/usb/Makefile @@ -11,7 +11,7 @@ obj-$(CONFIG_USB_HSO) += hso.o obj-$(CONFIG_USB_NET_AX8817X) += asix.o asix-y := asix_devices.o asix_common.o ax88172a.o obj-$(CONFIG_USB_NET_AX88179_178A) += ax88179_178a.o -obj-$(CONFIG_USB_NET_CDCETHER) += cdc_ether.o +obj-$(CONFIG_USB_NET_CDCETHER) += cdc_ether.o r815x.o obj-$(CONFIG_USB_NET_CDC_EEM) += cdc_eem.o obj-$(CONFIG_USB_NET_DM9601) += dm9601.o obj-$(CONFIG_USB_NET_SMSC75XX) += smsc75xx.o diff --git a/drivers/net/usb/cdc_ether.c b/drivers/net/usb/cdc_ether.c index 4393f1483126..03ad4dc293aa 100644 --- a/drivers/net/usb/cdc_ether.c +++ b/drivers/net/usb/cdc_ether.c @@ -646,13 +646,18 @@ static const struct usb_device_id products [] = { }, /* Realtek RTL8152 Based USB 2.0 Ethernet Adapters */ -#if defined(CONFIG_USB_RTL8152) || defined(CONFIG_USB_RTL8152_MODULE) { USB_DEVICE_AND_INTERFACE_INFO(REALTEK_VENDOR_ID, 0x8152, USB_CLASS_COMM, USB_CDC_SUBCLASS_ETHERNET, USB_CDC_PROTO_NONE), .driver_info = 0, }, -#endif + +/* Realtek RTL8153 Based USB 3.0 Ethernet Adapters */ +{ + USB_DEVICE_AND_INTERFACE_INFO(REALTEK_VENDOR_ID, 0x8153, USB_CLASS_COMM, + USB_CDC_SUBCLASS_ETHERNET, USB_CDC_PROTO_NONE), + .driver_info = 0, +}, /* * WHITELIST!!! diff --git a/drivers/net/usb/r815x.c b/drivers/net/usb/r815x.c new file mode 100644 index 000000000000..65167377ff09 --- /dev/null +++ b/drivers/net/usb/r815x.c @@ -0,0 +1,231 @@ +#include +#include +#include +#include +#include +#include + +#define RTL815x_REQT_READ 0xc0 +#define RTL815x_REQT_WRITE 0x40 +#define RTL815x_REQ_GET_REGS 0x05 +#define RTL815x_REQ_SET_REGS 0x05 + +#define MCU_TYPE_PLA 0x0100 +#define OCP_BASE 0xe86c +#define BASE_MII 0xa400 + +#define BYTE_EN_DWORD 0xff +#define BYTE_EN_WORD 0x33 +#define BYTE_EN_BYTE 0x11 + +#define R815x_PHY_ID 32 +#define REALTEK_VENDOR_ID 0x0bda + + +static int pla_read_word(struct usb_device *udev, u16 index) +{ + int data, ret; + u8 shift = index & 2; + + index &= ~3; + + ret = usb_control_msg(udev, usb_rcvctrlpipe(udev, 0), + RTL815x_REQ_GET_REGS, RTL815x_REQT_READ, + index, MCU_TYPE_PLA, &data, sizeof(data), 500); + if (ret < 0) + return ret; + + data = __le32_to_cpu(data); + data >>= (shift * 8); + data &= 0xffff; + + return data; +} + +static int pla_write_word(struct usb_device *udev, u16 index, u32 data) +{ + u32 tmp, mask = 0xffff; + u16 byen = BYTE_EN_WORD; + u8 shift = index & 2; + int ret; + + data &= mask; + + if (shift) { + byen <<= shift; + mask <<= (shift * 8); + data <<= (shift * 8); + index &= ~3; + } + + ret = usb_control_msg(udev, usb_rcvctrlpipe(udev, 0), + RTL815x_REQ_GET_REGS, RTL815x_REQT_READ, + index, MCU_TYPE_PLA, &tmp, sizeof(tmp), 500); + if (ret < 0) + return ret; + + tmp = __le32_to_cpu(tmp) & ~mask; + tmp |= data; + tmp = __cpu_to_le32(tmp); + + ret = usb_control_msg(udev, usb_sndctrlpipe(udev, 0), + RTL815x_REQ_SET_REGS, RTL815x_REQT_WRITE, + index, MCU_TYPE_PLA | byen, &tmp, + sizeof(tmp), 500); + + return ret; +} + +static int ocp_reg_read(struct usbnet *dev, u16 addr) +{ + u16 ocp_base, ocp_index; + int ret; + + ocp_base = addr & 0xf000; + ret = pla_write_word(dev->udev, OCP_BASE, ocp_base); + if (ret < 0) + goto out; + + ocp_index = (addr & 0x0fff) | 0xb000; + ret = pla_read_word(dev->udev, ocp_index); + +out: + return ret; +} + +static int ocp_reg_write(struct usbnet *dev, u16 addr, u16 data) +{ + u16 ocp_base, ocp_index; + int ret; + + ocp_base = addr & 0xf000; + ret = pla_write_word(dev->udev, OCP_BASE, ocp_base); + if (ret < 0) + goto out1; + + ocp_index = (addr & 0x0fff) | 0xb000; + ret = pla_write_word(dev->udev, ocp_index, data); + +out1: + return ret; +} + +static int r815x_mdio_read(struct net_device *netdev, int phy_id, int reg) +{ + struct usbnet *dev = netdev_priv(netdev); + + if (phy_id != R815x_PHY_ID) + return -EINVAL; + + return ocp_reg_read(dev, BASE_MII + reg * 2); +} + +static +void r815x_mdio_write(struct net_device *netdev, int phy_id, int reg, int val) +{ + struct usbnet *dev = netdev_priv(netdev); + + if (phy_id != R815x_PHY_ID) + return; + + ocp_reg_write(dev, BASE_MII + reg * 2, val); +} + +static int r8153_bind(struct usbnet *dev, struct usb_interface *intf) +{ + int status; + + status = usbnet_cdc_bind(dev, intf); + if (status < 0) + return status; + + dev->mii.dev = dev->net; + dev->mii.mdio_read = r815x_mdio_read; + dev->mii.mdio_write = r815x_mdio_write; + dev->mii.phy_id_mask = 0x3f; + dev->mii.reg_num_mask = 0x1f; + dev->mii.phy_id = R815x_PHY_ID; + dev->mii.supports_gmii = 1; + + return 0; +} + +static int r8152_bind(struct usbnet *dev, struct usb_interface *intf) +{ + int status; + + status = usbnet_cdc_bind(dev, intf); + if (status < 0) + return status; + + dev->mii.dev = dev->net; + dev->mii.mdio_read = r815x_mdio_read; + dev->mii.mdio_write = r815x_mdio_write; + dev->mii.phy_id_mask = 0x3f; + dev->mii.reg_num_mask = 0x1f; + dev->mii.phy_id = R815x_PHY_ID; + dev->mii.supports_gmii = 0; + + return 0; +} + +static const struct driver_info r8152_info = { + .description = "RTL8152 ECM Device", + .flags = FLAG_ETHER | FLAG_POINTTOPOINT, + .bind = r8152_bind, + .unbind = usbnet_cdc_unbind, + .status = usbnet_cdc_status, + .manage_power = usbnet_manage_power, +}; + +static const struct driver_info r8153_info = { + .description = "RTL8153 ECM Device", + .flags = FLAG_ETHER | FLAG_POINTTOPOINT, + .bind = r8153_bind, + .unbind = usbnet_cdc_unbind, + .status = usbnet_cdc_status, + .manage_power = usbnet_manage_power, +}; + +static const struct usb_device_id products[] = { +{ + USB_DEVICE_AND_INTERFACE_INFO(REALTEK_VENDOR_ID, 0x8152, USB_CLASS_COMM, + USB_CDC_SUBCLASS_ETHERNET, USB_CDC_PROTO_NONE), +#if defined(CONFIG_USB_RTL8152) || defined(CONFIG_USB_RTL8152_MODULE) + .driver_info = 0, +#else + .driver_info = (unsigned long) &r8152_info, +#endif +}, + +{ + USB_DEVICE_AND_INTERFACE_INFO(REALTEK_VENDOR_ID, 0x8153, USB_CLASS_COMM, + USB_CDC_SUBCLASS_ETHERNET, USB_CDC_PROTO_NONE), +#if defined(CONFIG_USB_RTL8153) || defined(CONFIG_USB_RTL8153_MODULE) + .driver_info = 0, +#else + .driver_info = (unsigned long) &r8153_info, +#endif +}, + + { }, /* END */ +}; +MODULE_DEVICE_TABLE(usb, products); + +static struct usb_driver r815x_driver = { + .name = "r815x", + .id_table = products, + .probe = usbnet_probe, + .disconnect = usbnet_disconnect, + .suspend = usbnet_suspend, + .resume = usbnet_resume, + .reset_resume = usbnet_resume, + .supports_autosuspend = 1, + .disable_hub_initiated_lpm = 1, +}; + +module_usb_driver(r815x_driver); + +MODULE_AUTHOR("Hayes Wang"); +MODULE_DESCRIPTION("Realtek USB ECM device"); +MODULE_LICENSE("GPL"); From d25903f894849fa799141e774c4ad34199e3e6a1 Mon Sep 17 00:00:00 2001 From: Wolfram Sang Date: Wed, 10 Jul 2013 16:57:42 +0100 Subject: [PATCH 26/36] drivers/net/can/c_can: don't use devm_pinctrl_get_select_default() in probe Since commit ab78029 (drivers/pinctrl: grab default handles from device core), we can rely on device core for setting the default pins. Compile tested only. Acked-by: Linus Walleij (personally at LCE13) Signed-off-by: Wolfram Sang Acked-by: Marc Kleine-Budde Signed-off-by: David S. Miller --- drivers/net/can/c_can/c_can_platform.c | 7 ------- 1 file changed, 7 deletions(-) diff --git a/drivers/net/can/c_can/c_can_platform.c b/drivers/net/can/c_can/c_can_platform.c index b918c7329426..c6f838d922a5 100644 --- a/drivers/net/can/c_can/c_can_platform.c +++ b/drivers/net/can/c_can/c_can_platform.c @@ -32,7 +32,6 @@ #include #include #include -#include #include @@ -114,7 +113,6 @@ static int c_can_plat_probe(struct platform_device *pdev) struct c_can_priv *priv; const struct of_device_id *match; const struct platform_device_id *id; - struct pinctrl *pinctrl; struct resource *mem, *res; int irq; struct clk *clk; @@ -131,11 +129,6 @@ static int c_can_plat_probe(struct platform_device *pdev) id = platform_get_device_id(pdev); } - pinctrl = devm_pinctrl_get_select_default(&pdev->dev); - if (IS_ERR(pinctrl)) - dev_warn(&pdev->dev, - "failed to configure pins from driver\n"); - /* get the appropriate clk */ clk = clk_get(&pdev->dev, NULL); if (IS_ERR(clk)) { From 54842ec2b0644b3e04c6fcfb52bc94dfcf918a43 Mon Sep 17 00:00:00 2001 From: Wolfram Sang Date: Wed, 10 Jul 2013 16:57:43 +0100 Subject: [PATCH 27/36] drivers/net/ethernet/cadence: don't use devm_pinctrl_get_select_default() in probe Since commit ab78029 (drivers/pinctrl: grab default handles from device core), we can rely on device core for setting the default pins. Compile tested only. Acked-by: Linus Walleij (personally at LCE13) Signed-off-by: Wolfram Sang Acked-by: Nicolas Ferre Signed-off-by: David S. Miller --- drivers/net/ethernet/cadence/at91_ether.c | 11 ----------- 1 file changed, 11 deletions(-) diff --git a/drivers/net/ethernet/cadence/at91_ether.c b/drivers/net/ethernet/cadence/at91_ether.c index 3f1957158a3b..bb5d63fb2e6d 100644 --- a/drivers/net/ethernet/cadence/at91_ether.c +++ b/drivers/net/ethernet/cadence/at91_ether.c @@ -29,7 +29,6 @@ #include #include #include -#include #include "macb.h" @@ -309,7 +308,6 @@ static int __init at91ether_probe(struct platform_device *pdev) struct resource *regs; struct net_device *dev; struct phy_device *phydev; - struct pinctrl *pinctrl; struct macb *lp; int res; u32 reg; @@ -319,15 +317,6 @@ static int __init at91ether_probe(struct platform_device *pdev) if (!regs) return -ENOENT; - pinctrl = devm_pinctrl_get_select_default(&pdev->dev); - if (IS_ERR(pinctrl)) { - res = PTR_ERR(pinctrl); - if (res == -EPROBE_DEFER) - return res; - - dev_warn(&pdev->dev, "No pinctrl provided\n"); - } - dev = alloc_etherdev(sizeof(struct macb)); if (!dev) return -ENOMEM; From fdb70270015466076846a0525f195f59849c1966 Mon Sep 17 00:00:00 2001 From: Wolfram Sang Date: Wed, 10 Jul 2013 16:57:44 +0100 Subject: [PATCH 28/36] drivers/net/ieee802154: don't use devm_pinctrl_get_select_default() in probe Since commit ab78029 (drivers/pinctrl: grab default handles from device core), we can rely on device core for setting the default pins. Compile tested only. Acked-by: Linus Walleij (personally at LCE13) Signed-off-by: Wolfram Sang Signed-off-by: David S. Miller --- drivers/net/ieee802154/mrf24j40.c | 7 ------- 1 file changed, 7 deletions(-) diff --git a/drivers/net/ieee802154/mrf24j40.c b/drivers/net/ieee802154/mrf24j40.c index ede3ce4912f9..42e6deee6db5 100644 --- a/drivers/net/ieee802154/mrf24j40.c +++ b/drivers/net/ieee802154/mrf24j40.c @@ -22,7 +22,6 @@ #include #include #include -#include #include #include #include @@ -627,7 +626,6 @@ static int mrf24j40_probe(struct spi_device *spi) int ret = -ENOMEM; u8 val; struct mrf24j40 *devrec; - struct pinctrl *pinctrl; printk(KERN_INFO "mrf24j40: probe(). IRQ: %d\n", spi->irq); @@ -638,11 +636,6 @@ static int mrf24j40_probe(struct spi_device *spi) if (!devrec->buf) goto err_buf; - pinctrl = devm_pinctrl_get_select_default(&spi->dev); - if (IS_ERR(pinctrl)) - dev_warn(&spi->dev, - "pinctrl pins are not configured from the driver"); - spi->mode = SPI_MODE_0; /* TODO: Is this appropriate for right here? */ if (spi->max_speed_hz > MAX_SPI_SPEED_HZ) spi->max_speed_hz = MAX_SPI_SPEED_HZ; From 92338dc2fb33c8526256a458a520af73d9ab2d14 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?=E2=80=9CCosmin?= Date: Fri, 12 Jul 2013 09:33:33 +0300 Subject: [PATCH 29/36] net: strict_strtoul is obsolete, use kstrtoul instead patch found using checkpatch.pl Signed-off-by: Cosmin Stanescu Signed-off-by: David S. Miller --- net/dns_resolver/dns_key.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/net/dns_resolver/dns_key.c b/net/dns_resolver/dns_key.c index 0a69d0757795..f347a2ca7d7e 100644 --- a/net/dns_resolver/dns_key.c +++ b/net/dns_resolver/dns_key.c @@ -118,7 +118,7 @@ dns_resolver_instantiate(struct key *key, struct key_preparsed_payload *prep) if (opt_vlen <= 0) goto bad_option_value; - ret = strict_strtoul(eq, 10, &derrno); + ret = kstrtoul(eq, 10, &derrno); if (ret < 0) goto bad_option_value; From 40dadff26539d1695d2a37b44f66c53158439ae9 Mon Sep 17 00:00:00 2001 From: Sunghan Suh Date: Fri, 12 Jul 2013 16:17:23 +0900 Subject: [PATCH 30/36] net: access page->private by using page_private Signed-off-by: Sunghan Suh Signed-off-by: David S. Miller --- net/core/skbuff.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/net/core/skbuff.c b/net/core/skbuff.c index 724bb7cb173f..20e02d2605ec 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -824,7 +824,7 @@ int skb_copy_ubufs(struct sk_buff *skb, gfp_t gfp_mask) page = alloc_page(gfp_mask); if (!page) { while (head) { - struct page *next = (struct page *)head->private; + struct page *next = (struct page *)page_private(head); put_page(head); head = next; } @@ -834,7 +834,7 @@ int skb_copy_ubufs(struct sk_buff *skb, gfp_t gfp_mask) memcpy(page_address(page), vaddr + f->page_offset, skb_frag_size(f)); kunmap_atomic(vaddr); - page->private = (unsigned long)head; + set_page_private(page, (unsigned long)head); head = page; } @@ -848,7 +848,7 @@ int skb_copy_ubufs(struct sk_buff *skb, gfp_t gfp_mask) for (i = num_frags - 1; i >= 0; i--) { __skb_fill_page_desc(skb, i, head, 0, skb_shinfo(skb)->frags[i].size); - head = (struct page *)head->private; + head = (struct page *)page_private(head); } skb_shinfo(skb)->tx_flags &= ~SKBTX_DEV_ZEROCOPY; From 3ff25e3c4531aff5b1a96e2ea6e1a2d355263019 Mon Sep 17 00:00:00 2001 From: hayeswang Date: Fri, 12 Jul 2013 16:26:15 +0800 Subject: [PATCH 31/36] usb/net/r8152: fix integer overflow in expression config: make ARCH=avr32 allyesconfig drivers/net/usb/r8152.c: In function 'rtl8152_start_xmit': drivers/net/usb/r8152.c:956: warning: integer overflow in expression 955 memset(tx_desc, 0, sizeof(*tx_desc)); > 956 tx_desc->opts1 = cpu_to_le32((len & TX_LEN_MASK) | TX_FS | TX_LS); 957 tp->tx_skb = skb; Signed-off-by: Hayes Wang Spotted-by: kbuild test robot Signed-off-by: David S. Miller --- drivers/net/usb/r8152.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/drivers/net/usb/r8152.c b/drivers/net/usb/r8152.c index d02bac82fc57..ee13f9eb740c 100644 --- a/drivers/net/usb/r8152.c +++ b/drivers/net/usb/r8152.c @@ -934,7 +934,8 @@ static netdev_tx_t rtl8152_start_xmit(struct sk_buff *skb, struct r8152 *tp = netdev_priv(netdev); struct net_device_stats *stats = rtl8152_get_stats(netdev); struct tx_desc *tx_desc; - int len, res; + unsigned int len; + int res; netif_stop_queue(netdev); len = skb->len; From e76385240ee5c812267319c9084e5a0d62bfbf90 Mon Sep 17 00:00:00 2001 From: hayeswang Date: Fri, 12 Jul 2013 16:26:16 +0800 Subject: [PATCH 32/36] usb/net/r815x: fix cast to restricted __le32 >> drivers/net/usb/r815x.c:38:16: sparse: cast to restricted __le32 >> drivers/net/usb/r815x.c:67:15: sparse: cast to restricted __le32 >> drivers/net/usb/r815x.c:69:13: sparse: incorrect type in assignment (different base types) drivers/net/usb/r815x.c:69:13: expected unsigned int [unsigned] [addressable] [assigned] [usertype] tmp drivers/net/usb/r815x.c:69:13: got restricted __le32 [usertype] Signed-off-by: Hayes Wang Spotted-by: kbuild test robot Signed-off-by: David S. Miller --- drivers/net/usb/r815x.c | 21 ++++++++++++--------- 1 file changed, 12 insertions(+), 9 deletions(-) diff --git a/drivers/net/usb/r815x.c b/drivers/net/usb/r815x.c index 65167377ff09..852392269718 100644 --- a/drivers/net/usb/r815x.c +++ b/drivers/net/usb/r815x.c @@ -26,16 +26,18 @@ static int pla_read_word(struct usb_device *udev, u16 index) { int data, ret; u8 shift = index & 2; + __le32 ocp_data; index &= ~3; ret = usb_control_msg(udev, usb_rcvctrlpipe(udev, 0), RTL815x_REQ_GET_REGS, RTL815x_REQT_READ, - index, MCU_TYPE_PLA, &data, sizeof(data), 500); + index, MCU_TYPE_PLA, &ocp_data, sizeof(ocp_data), + 500); if (ret < 0) return ret; - data = __le32_to_cpu(data); + data = __le32_to_cpu(ocp_data); data >>= (shift * 8); data &= 0xffff; @@ -44,7 +46,8 @@ static int pla_read_word(struct usb_device *udev, u16 index) static int pla_write_word(struct usb_device *udev, u16 index, u32 data) { - u32 tmp, mask = 0xffff; + __le32 ocp_data; + u32 mask = 0xffff; u16 byen = BYTE_EN_WORD; u8 shift = index & 2; int ret; @@ -60,18 +63,18 @@ static int pla_write_word(struct usb_device *udev, u16 index, u32 data) ret = usb_control_msg(udev, usb_rcvctrlpipe(udev, 0), RTL815x_REQ_GET_REGS, RTL815x_REQT_READ, - index, MCU_TYPE_PLA, &tmp, sizeof(tmp), 500); + index, MCU_TYPE_PLA, &ocp_data, sizeof(ocp_data), + 500); if (ret < 0) return ret; - tmp = __le32_to_cpu(tmp) & ~mask; - tmp |= data; - tmp = __cpu_to_le32(tmp); + data |= __le32_to_cpu(ocp_data) & ~mask; + ocp_data = __cpu_to_le32(data); ret = usb_control_msg(udev, usb_sndctrlpipe(udev, 0), RTL815x_REQ_SET_REGS, RTL815x_REQT_WRITE, - index, MCU_TYPE_PLA | byen, &tmp, - sizeof(tmp), 500); + index, MCU_TYPE_PLA | byen, &ocp_data, + sizeof(ocp_data), 500); return ret; } From 24ab6bec80861d0c55263047e8bf97e460a32e7b Mon Sep 17 00:00:00 2001 From: Yuchung Cheng Date: Fri, 12 Jul 2013 11:33:04 -0700 Subject: [PATCH 33/36] tcp: account all retransmit failures Change snmp RETRANSFAILS stat to include timeout retransmit failures in addition to other loss recoveries. Signed-off-by: Yuchung Cheng Acked-by: Neal Cardwell Acked-by: Eric Dumazet Signed-off-by: David S. Miller --- net/ipv4/tcp_output.c | 7 ++++--- 1 file changed, 4 insertions(+), 3 deletions(-) diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c index 3d609490f118..92fde8d1aa82 100644 --- a/net/ipv4/tcp_output.c +++ b/net/ipv4/tcp_output.c @@ -2407,6 +2407,8 @@ int tcp_retransmit_skb(struct sock *sk, struct sk_buff *skb) * see tcp_input.c tcp_sacktag_write_queue(). */ TCP_SKB_CB(skb)->ack_seq = tp->snd_nxt; + } else { + NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_TCPRETRANSFAIL); } return err; } @@ -2528,10 +2530,9 @@ begin_fwd: if (sacked & (TCPCB_SACKED_ACKED|TCPCB_SACKED_RETRANS)) continue; - if (tcp_retransmit_skb(sk, skb)) { - NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_TCPRETRANSFAIL); + if (tcp_retransmit_skb(sk, skb)) return; - } + NET_INC_STATS_BH(sock_net(sk), mib_idx); if (tcp_in_cwnd_reduction(sk)) From 352900b583b2852152a1e05ea0e8b579292e731e Mon Sep 17 00:00:00 2001 From: Neil Horman Date: Fri, 12 Jul 2013 10:58:48 -0400 Subject: [PATCH 34/36] atl1e: fix dma mapping warnings Recently had this backtrace reported: WARNING: at lib/dma-debug.c:937 check_unmap+0x47d/0x930() Hardware name: System Product Name ATL1E 0000:02:00.0: DMA-API: device driver failed to check map error[device address=0x00000000cbfd1000] [size=90 bytes] [mapped as single] Modules linked in: xt_conntrack nf_conntrack ebtable_filter ebtables ip6table_filter ip6_tables snd_hda_codec_hdmi snd_hda_codec_realtek iTCO_wdt iTCO_vendor_support snd_hda_intel acpi_cpufreq mperf coretemp btrfs zlib_deflate snd_hda_codec snd_hwdep microcode raid6_pq libcrc32c snd_seq usblp serio_raw xor snd_seq_device joydev snd_pcm snd_page_alloc snd_timer snd lpc_ich i2c_i801 soundcore mfd_core atl1e asus_atk0110 ata_generic pata_acpi radeon i2c_algo_bit drm_kms_helper ttm drm i2c_core pata_marvell uinput Pid: 314, comm: systemd-journal Not tainted 3.9.0-0.rc6.git2.3.fc19.x86_64 #1 Call Trace: [] warn_slowpath_common+0x66/0x80 [] warn_slowpath_fmt+0x4c/0x50 [] check_unmap+0x47d/0x930 [] ? sched_clock_cpu+0xa8/0x100 [] debug_dma_unmap_page+0x5f/0x70 [] ? unmap_single+0x20/0x30 [] atl1e_intr+0x3a1/0x5b0 [atl1e] [] ? trace_hardirqs_off+0xd/0x10 [] handle_irq_event_percpu+0x56/0x390 [] handle_irq_event+0x3d/0x60 [] handle_fasteoi_irq+0x5a/0x100 [] handle_irq+0xbf/0x150 [] ? file_sb_list_del+0x3f/0x50 [] ? irq_enter+0x50/0xa0 [] do_IRQ+0x4d/0xc0 [] ? file_sb_list_del+0x3f/0x50 [] common_interrupt+0x72/0x72 [] ? lock_release+0xc2/0x310 [] lg_local_unlock_cpu+0x24/0x50 [] file_sb_list_del+0x3f/0x50 [] fput+0x2d/0xc0 [] filp_close+0x61/0x90 [] __close_fd+0x8d/0x150 [] sys_close+0x20/0x50 [] system_call_fastpath+0x16/0x1b The usual straighforward failure to check for dma_mapping_error after a map operation is completed. This patch should fix it, the reporter wandered off after filing this bz: https://bugzilla.redhat.com/show_bug.cgi?id=954170 and I don't have hardware to test, but the fix is pretty straightforward, so I figured I'd post it for review. Signed-off-by: Neil Horman CC: Jay Cliburn CC: Chris Snook CC: "David S. Miller" Signed-off-by: David S. Miller --- .../net/ethernet/atheros/atl1e/atl1e_main.c | 28 +++++++++++++++++-- 1 file changed, 25 insertions(+), 3 deletions(-) diff --git a/drivers/net/ethernet/atheros/atl1e/atl1e_main.c b/drivers/net/ethernet/atheros/atl1e/atl1e_main.c index 895f5377ad1b..6d1a62a84c9d 100644 --- a/drivers/net/ethernet/atheros/atl1e/atl1e_main.c +++ b/drivers/net/ethernet/atheros/atl1e/atl1e_main.c @@ -1665,8 +1665,8 @@ check_sum: return 0; } -static void atl1e_tx_map(struct atl1e_adapter *adapter, - struct sk_buff *skb, struct atl1e_tpd_desc *tpd) +static int atl1e_tx_map(struct atl1e_adapter *adapter, + struct sk_buff *skb, struct atl1e_tpd_desc *tpd) { struct atl1e_tpd_desc *use_tpd = NULL; struct atl1e_tx_buffer *tx_buffer = NULL; @@ -1677,6 +1677,7 @@ static void atl1e_tx_map(struct atl1e_adapter *adapter, u16 nr_frags; u16 f; int segment; + int ring_start = adapter->tx_ring.next_to_use; nr_frags = skb_shinfo(skb)->nr_frags; segment = (tpd->word3 >> TPD_SEGMENT_EN_SHIFT) & TPD_SEGMENT_EN_MASK; @@ -1689,6 +1690,9 @@ static void atl1e_tx_map(struct atl1e_adapter *adapter, tx_buffer->length = map_len; tx_buffer->dma = pci_map_single(adapter->pdev, skb->data, hdr_len, PCI_DMA_TODEVICE); + if (dma_mapping_error(&adapter->pdev->dev, tx_buffer->dma)) + return -ENOSPC; + ATL1E_SET_PCIMAP_TYPE(tx_buffer, ATL1E_TX_PCIMAP_SINGLE); mapped_len += map_len; use_tpd->buffer_addr = cpu_to_le64(tx_buffer->dma); @@ -1715,6 +1719,13 @@ static void atl1e_tx_map(struct atl1e_adapter *adapter, tx_buffer->dma = pci_map_single(adapter->pdev, skb->data + mapped_len, map_len, PCI_DMA_TODEVICE); + + if (dma_mapping_error(&adapter->pdev->dev, tx_buffer->dma)) { + /* Reset the tx rings next pointer */ + adapter->tx_ring.next_to_use = ring_start; + return -ENOSPC; + } + ATL1E_SET_PCIMAP_TYPE(tx_buffer, ATL1E_TX_PCIMAP_SINGLE); mapped_len += map_len; use_tpd->buffer_addr = cpu_to_le64(tx_buffer->dma); @@ -1750,6 +1761,13 @@ static void atl1e_tx_map(struct atl1e_adapter *adapter, (i * MAX_TX_BUF_LEN), tx_buffer->length, DMA_TO_DEVICE); + + if (dma_mapping_error(&adapter->pdev->dev, tx_buffer->dma)) { + /* Reset the ring next to use pointer */ + adapter->tx_ring.next_to_use = ring_start; + return -ENOSPC; + } + ATL1E_SET_PCIMAP_TYPE(tx_buffer, ATL1E_TX_PCIMAP_PAGE); use_tpd->buffer_addr = cpu_to_le64(tx_buffer->dma); use_tpd->word2 = (use_tpd->word2 & (~TPD_BUFLEN_MASK)) | @@ -1767,6 +1785,7 @@ static void atl1e_tx_map(struct atl1e_adapter *adapter, /* The last buffer info contain the skb address, so it will be free after unmap */ tx_buffer->skb = skb; + return 0; } static void atl1e_tx_queue(struct atl1e_adapter *adapter, u16 count, @@ -1834,10 +1853,13 @@ static netdev_tx_t atl1e_xmit_frame(struct sk_buff *skb, return NETDEV_TX_OK; } - atl1e_tx_map(adapter, skb, tpd); + if (atl1e_tx_map(adapter, skb, tpd)) + goto out; + atl1e_tx_queue(adapter, tpd_req, tpd); netdev->trans_start = jiffies; /* NETIF_F_LLTX driver :( */ +out: spin_unlock_irqrestore(&adapter->tx_lock, flags); return NETDEV_TX_OK; } From 9b4fe5fb0bdd8f31f24cbfe77e38ec8155c250c5 Mon Sep 17 00:00:00 2001 From: Neil Horman Date: Fri, 12 Jul 2013 13:35:33 -0400 Subject: [PATCH 35/36] via-rhine: fix dma mapping errors this bug: https://bugzilla.redhat.com/show_bug.cgi?id=951695 Reported a dma debug backtrace: WARNING: at lib/dma-debug.c:937 check_unmap+0x47d/0x930() Hardware name: To Be Filled By O.E.M. via-rhine 0000:00:12.0: DMA-API: device driver failed to check map error[device address=0x0000000075a837b2] [size=90 bytes] [mapped as single] Modules linked in: ip6_tables gspca_spca561 gspca_main videodev media snd_hda_codec_realtek snd_hda_intel i2c_viapro snd_hda_codec snd_hwdep snd_seq ppdev mperf via_rhine coretemp snd_pcm mii microcode snd_page_alloc snd_timer snd_mpu401 snd_mpu401_uart snd_rawmidi snd_seq_device snd soundcore parport_pc parport shpchp ata_generic pata_acpi radeon i2c_algo_bit drm_kms_helper ttm drm pata_via sata_via i2c_core uinput Pid: 295, comm: systemd-journal Not tainted 3.9.0-0.rc6.git2.1.fc20.x86_64 #1 Call Trace: [] warn_slowpath_common+0x70/0xa0 [] warn_slowpath_fmt+0x4c/0x50 [] check_unmap+0x47d/0x930 [] ? local_clock+0x5f/0x70 [] debug_dma_unmap_page+0x5f/0x70 [] ? rhine_ack_events.isra.14+0x3c/0x50 [via_rhine] [] rhine_napipoll+0x1d8/0xd80 [via_rhine] [] ? net_rx_action+0xa1/0x380 [] net_rx_action+0x172/0x380 [] __do_softirq+0xff/0x400 [] irq_exit+0xb5/0xc0 [] do_IRQ+0x56/0xc0 [] common_interrupt+0x72/0x72 [] ? __slab_alloc+0x4c2/0x526 [] ? mmap_region+0x2b0/0x5a0 [] ? __lock_is_held+0x57/0x80 [] ? mmap_region+0x2b0/0x5a0 [] kmem_cache_alloc+0x2df/0x360 [] mmap_region+0x2b0/0x5a0 [] do_mmap_pgoff+0x316/0x3d0 [] vm_mmap_pgoff+0x90/0xc0 [] sys_mmap_pgoff+0x4c/0x190 [] ? trace_hardirqs_on_thunk+0x3a/0x3f [] sys_mmap+0x22/0x30 [] system_call_fastpath+0x16/0x1b Usual problem with the usual fix, add the appropriate calls to dma_mapping_error where appropriate Untested, as I don't have hardware, but its pretty straightforward Signed-off-by: Neil Horman CC: David S. Miller CC: Roger Luethi Signed-off-by: David S. Miller --- drivers/net/ethernet/via/via-rhine.c | 17 ++++++++++++++++- 1 file changed, 16 insertions(+), 1 deletion(-) diff --git a/drivers/net/ethernet/via/via-rhine.c b/drivers/net/ethernet/via/via-rhine.c index ca98acabf1b4..b75eb9e0e867 100644 --- a/drivers/net/ethernet/via/via-rhine.c +++ b/drivers/net/ethernet/via/via-rhine.c @@ -1171,7 +1171,11 @@ static void alloc_rbufs(struct net_device *dev) rp->rx_skbuff_dma[i] = pci_map_single(rp->pdev, skb->data, rp->rx_buf_sz, PCI_DMA_FROMDEVICE); - + if (dma_mapping_error(&rp->pdev->dev, rp->rx_skbuff_dma[i])) { + rp->rx_skbuff_dma[i] = 0; + dev_kfree_skb(skb); + break; + } rp->rx_ring[i].addr = cpu_to_le32(rp->rx_skbuff_dma[i]); rp->rx_ring[i].rx_status = cpu_to_le32(DescOwn); } @@ -1687,6 +1691,12 @@ static netdev_tx_t rhine_start_tx(struct sk_buff *skb, rp->tx_skbuff_dma[entry] = pci_map_single(rp->pdev, skb->data, skb->len, PCI_DMA_TODEVICE); + if (dma_mapping_error(&rp->pdev->dev, rp->tx_skbuff_dma[entry])) { + dev_kfree_skb(skb); + rp->tx_skbuff_dma[entry] = 0; + dev->stats.tx_dropped++; + return NETDEV_TX_OK; + } rp->tx_ring[entry].addr = cpu_to_le32(rp->tx_skbuff_dma[entry]); } @@ -1961,6 +1971,11 @@ static int rhine_rx(struct net_device *dev, int limit) pci_map_single(rp->pdev, skb->data, rp->rx_buf_sz, PCI_DMA_FROMDEVICE); + if (dma_mapping_error(&rp->pdev->dev, rp->rx_skbuff_dma[entry])) { + dev_kfree_skb(skb); + rp->rx_skbuff_dma[entry] = 0; + break; + } rp->rx_ring[entry].addr = cpu_to_le32(rp->rx_skbuff_dma[entry]); } rp->rx_ring[entry].rx_status = cpu_to_le32(DescOwn); From 307f2fb95e9b96b3577916e73d92e104f8f26494 Mon Sep 17 00:00:00 2001 From: Hannes Frederic Sowa Date: Fri, 12 Jul 2013 23:46:33 +0200 Subject: [PATCH 36/36] ipv6: only static routes qualify for equal cost multipathing Static routes in this case are non-expiring routes which did not get configured by autoconf or by icmpv6 redirects. To make sure we actually get an ecmp route while searching for the first one in this fib6_node's leafs, also make sure it matches the ecmp route assumptions. v2: a) Removed RTF_EXPIRE check in dst.from chain. The check of RTF_ADDRCONF already ensures that this route, even if added again without RTF_EXPIRES (in case of a RA announcement with infinite timeout), does not cause the rt6i_nsiblings logic to go wrong if a later RA updates the expiration time later. v3: a) Allow RTF_EXPIRES routes to enter the ecmp route set. We have to do so, because an pmtu event could update the RTF_EXPIRES flag and we would not count this route, if another route joins this set. We now filter only for RTF_GATEWAY|RTF_ADDRCONF|RTF_DYNAMIC, which are flags that don't get changed after rt6_info construction. Cc: Nicolas Dichtel Signed-off-by: Hannes Frederic Sowa Signed-off-by: David S. Miller --- net/ipv6/ip6_fib.c | 15 +++++++++++---- 1 file changed, 11 insertions(+), 4 deletions(-) diff --git a/net/ipv6/ip6_fib.c b/net/ipv6/ip6_fib.c index 192dd1a0e188..5fc9c7a68d8d 100644 --- a/net/ipv6/ip6_fib.c +++ b/net/ipv6/ip6_fib.c @@ -632,6 +632,12 @@ insert_above: return ln; } +static inline bool rt6_qualify_for_ecmp(struct rt6_info *rt) +{ + return (rt->rt6i_flags & (RTF_GATEWAY|RTF_ADDRCONF|RTF_DYNAMIC)) == + RTF_GATEWAY; +} + /* * Insert routing information in a node. */ @@ -646,6 +652,7 @@ static int fib6_add_rt2node(struct fib6_node *fn, struct rt6_info *rt, int add = (!info->nlh || (info->nlh->nlmsg_flags & NLM_F_CREATE)); int found = 0; + bool rt_can_ecmp = rt6_qualify_for_ecmp(rt); ins = &fn->leaf; @@ -691,9 +698,8 @@ static int fib6_add_rt2node(struct fib6_node *fn, struct rt6_info *rt, * To avoid long list, we only had siblings if the * route have a gateway. */ - if (rt->rt6i_flags & RTF_GATEWAY && - !(rt->rt6i_flags & RTF_EXPIRES) && - !(iter->rt6i_flags & RTF_EXPIRES)) + if (rt_can_ecmp && + rt6_qualify_for_ecmp(iter)) rt->rt6i_nsiblings++; } @@ -715,7 +721,8 @@ static int fib6_add_rt2node(struct fib6_node *fn, struct rt6_info *rt, /* Find the first route that have the same metric */ sibling = fn->leaf; while (sibling) { - if (sibling->rt6i_metric == rt->rt6i_metric) { + if (sibling->rt6i_metric == rt->rt6i_metric && + rt6_qualify_for_ecmp(sibling)) { list_add_tail(&rt->rt6i_siblings, &sibling->rt6i_siblings); break;