From b0e010c527de742cb18e8d50a06dfd1a995b5382 Mon Sep 17 00:00:00 2001 From: Alex Gartrell Date: Wed, 26 Aug 2015 09:40:28 -0700 Subject: ipvs: replace ip_vs_fill_ip4hdr with ip_vs_fill_iph_skb_off This removes some duplicated code and makes the ICMPv6 path look more like the ICMP path. Signed-off-by: Alex Gartrell Acked-by: Julian Anastasov Signed-off-by: Simon Horman --- include/net/ip_vs.h | 49 +++++++++++++++++++++++++++++-------------------- 1 file changed, 29 insertions(+), 20 deletions(-) (limited to 'include') diff --git a/include/net/ip_vs.h b/include/net/ip_vs.h index 9b9ca87a4210..0c8309f34982 100644 --- a/include/net/ip_vs.h +++ b/include/net/ip_vs.h @@ -104,6 +104,7 @@ static inline struct net *seq_file_single_net(struct seq_file *seq) extern int ip_vs_conn_tab_size; struct ip_vs_iphdr { + __u32 off; /* Where IP or IPv4 header starts */ __u32 len; /* IPv4 simply where L4 starts * IPv6 where L4 Transport Header starts */ __u16 fragoffs; /* IPv6 fragment offset, 0 if first frag (or not frag)*/ @@ -120,48 +121,56 @@ static inline void *frag_safe_skb_hp(const struct sk_buff *skb, int offset, return skb_header_pointer(skb, offset, len, buffer); } -static inline void -ip_vs_fill_ip4hdr(const void *nh, struct ip_vs_iphdr *iphdr) -{ - const struct iphdr *iph = nh; - - iphdr->len = iph->ihl * 4; - iphdr->fragoffs = 0; - iphdr->protocol = iph->protocol; - iphdr->saddr.ip = iph->saddr; - iphdr->daddr.ip = iph->daddr; -} - /* This function handles filling *ip_vs_iphdr, both for IPv4 and IPv6. * IPv6 requires some extra work, as finding proper header position, * depend on the IPv6 extension headers. */ -static inline void -ip_vs_fill_iph_skb(int af, const struct sk_buff *skb, struct ip_vs_iphdr *iphdr) +static inline int +ip_vs_fill_iph_skb_off(int af, const struct sk_buff *skb, int offset, + struct ip_vs_iphdr *iphdr) { + iphdr->off = offset; #ifdef CONFIG_IP_VS_IPV6 if (af == AF_INET6) { - const struct ipv6hdr *iph = - (struct ipv6hdr *)skb_network_header(skb); + struct ipv6hdr _iph; + const struct ipv6hdr *iph = skb_header_pointer( + skb, offset, sizeof(_iph), &_iph); + if (!iph) + return 0; + iphdr->saddr.in6 = iph->saddr; iphdr->daddr.in6 = iph->daddr; /* ipv6_find_hdr() updates len, flags */ - iphdr->len = 0; + iphdr->len = offset; iphdr->flags = 0; iphdr->protocol = ipv6_find_hdr(skb, &iphdr->len, -1, &iphdr->fragoffs, &iphdr->flags); + if (iphdr->protocol < 0) + return 0; } else #endif { - const struct iphdr *iph = - (struct iphdr *)skb_network_header(skb); - iphdr->len = iph->ihl * 4; + struct iphdr _iph; + const struct iphdr *iph = skb_header_pointer( + skb, offset, sizeof(_iph), &_iph); + if (!iph) + return 0; + + iphdr->len = offset + iph->ihl * 4; iphdr->fragoffs = 0; iphdr->protocol = iph->protocol; iphdr->saddr.ip = iph->saddr; iphdr->daddr.ip = iph->daddr; } + + return 1; +} + +static inline int +ip_vs_fill_iph_skb(int af, const struct sk_buff *skb, struct ip_vs_iphdr *iphdr) +{ + return ip_vs_fill_iph_skb_off(af, skb, skb_network_offset(skb), iphdr); } static inline void ip_vs_addr_copy(int af, union nf_inet_addr *dst, -- cgit v1.2.3 From 4fd9beef37f3a14aa34cb025479a0e431dc9e58b Mon Sep 17 00:00:00 2001 From: Alex Gartrell Date: Wed, 26 Aug 2015 09:40:29 -0700 Subject: ipvs: Add hdr_flags to iphdr These flags contain information like whether or not the addresses are inverted or from icmp. The first will allow us to drop an inverse param all over the place, and the second will later be useful in scheduling icmp. Signed-off-by: Alex Gartrell Acked-by: Julian Anastasov Signed-off-by: Simon Horman --- include/net/ip_vs.h | 43 ++++++++++++++++++++++++++++++++++++++++--- 1 file changed, 40 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/include/net/ip_vs.h b/include/net/ip_vs.h index 0c8309f34982..ac336a79ad3d 100644 --- a/include/net/ip_vs.h +++ b/include/net/ip_vs.h @@ -29,6 +29,9 @@ #endif #include /* Netw namespace */ +#define IP_VS_HDR_INVERSE 1 +#define IP_VS_HDR_ICMP 2 + /* Generic access of ipvs struct */ static inline struct netns_ipvs *net_ipvs(struct net* net) { @@ -104,6 +107,7 @@ static inline struct net *seq_file_single_net(struct seq_file *seq) extern int ip_vs_conn_tab_size; struct ip_vs_iphdr { + int hdr_flags; /* ipvs flags */ __u32 off; /* Where IP or IPv4 header starts */ __u32 len; /* IPv4 simply where L4 starts * IPv6 where L4 Transport Header starts */ @@ -127,9 +131,11 @@ static inline void *frag_safe_skb_hp(const struct sk_buff *skb, int offset, */ static inline int ip_vs_fill_iph_skb_off(int af, const struct sk_buff *skb, int offset, - struct ip_vs_iphdr *iphdr) + int hdr_flags, struct ip_vs_iphdr *iphdr) { + iphdr->hdr_flags = hdr_flags; iphdr->off = offset; + #ifdef CONFIG_IP_VS_IPV6 if (af == AF_INET6) { struct ipv6hdr _iph; @@ -168,9 +174,40 @@ ip_vs_fill_iph_skb_off(int af, const struct sk_buff *skb, int offset, } static inline int -ip_vs_fill_iph_skb(int af, const struct sk_buff *skb, struct ip_vs_iphdr *iphdr) +ip_vs_fill_iph_skb_icmp(int af, const struct sk_buff *skb, int offset, + bool inverse, struct ip_vs_iphdr *iphdr) +{ + int hdr_flags = IP_VS_HDR_ICMP; + + if (inverse) + hdr_flags |= IP_VS_HDR_INVERSE; + + return ip_vs_fill_iph_skb_off(af, skb, offset, hdr_flags, iphdr); +} + +static inline int +ip_vs_fill_iph_skb(int af, const struct sk_buff *skb, bool inverse, + struct ip_vs_iphdr *iphdr) +{ + int hdr_flags = 0; + + if (inverse) + hdr_flags |= IP_VS_HDR_INVERSE; + + return ip_vs_fill_iph_skb_off(af, skb, skb_network_offset(skb), + hdr_flags, iphdr); +} + +static inline bool +ip_vs_iph_inverse(const struct ip_vs_iphdr *iph) +{ + return !!(iph->hdr_flags & IP_VS_HDR_INVERSE); +} + +static inline bool +ip_vs_iph_icmp(const struct ip_vs_iphdr *iph) { - return ip_vs_fill_iph_skb_off(af, skb, skb_network_offset(skb), iphdr); + return !!(iph->hdr_flags & IP_VS_HDR_ICMP); } static inline void ip_vs_addr_copy(int af, union nf_inet_addr *dst, -- cgit v1.2.3 From 802c41adcf3be63f351c302c9665865d705cada9 Mon Sep 17 00:00:00 2001 From: Alex Gartrell Date: Wed, 26 Aug 2015 09:40:32 -0700 Subject: ipvs: drop inverse argument to conn_{in,out}_get No longer necessary since the information is included in the ip_vs_iphdr itself. Signed-off-by: Alex Gartrell Acked-by: Julian Anastasov Signed-off-by: Simon Horman --- include/net/ip_vs.h | 12 ++++-------- 1 file changed, 4 insertions(+), 8 deletions(-) (limited to 'include') diff --git a/include/net/ip_vs.h b/include/net/ip_vs.h index ac336a79ad3d..ba90729d1111 100644 --- a/include/net/ip_vs.h +++ b/include/net/ip_vs.h @@ -495,14 +495,12 @@ struct ip_vs_protocol { struct ip_vs_conn * (*conn_in_get)(int af, const struct sk_buff *skb, - const struct ip_vs_iphdr *iph, - int inverse); + const struct ip_vs_iphdr *iph); struct ip_vs_conn * (*conn_out_get)(int af, const struct sk_buff *skb, - const struct ip_vs_iphdr *iph, - int inverse); + const struct ip_vs_iphdr *iph); int (*snat_handler)(struct sk_buff *skb, struct ip_vs_protocol *pp, struct ip_vs_conn *cp, struct ip_vs_iphdr *iph); @@ -1232,14 +1230,12 @@ struct ip_vs_conn *ip_vs_conn_in_get(const struct ip_vs_conn_param *p); struct ip_vs_conn *ip_vs_ct_in_get(const struct ip_vs_conn_param *p); struct ip_vs_conn * ip_vs_conn_in_get_proto(int af, const struct sk_buff *skb, - const struct ip_vs_iphdr *iph, - int inverse); + const struct ip_vs_iphdr *iph); struct ip_vs_conn *ip_vs_conn_out_get(const struct ip_vs_conn_param *p); struct ip_vs_conn * ip_vs_conn_out_get_proto(int af, const struct sk_buff *skb, - const struct ip_vs_iphdr *iph, - int inverse); + const struct ip_vs_iphdr *iph); /* Get reference to gain full access to conn. * By default, RCU read-side critical sections have access only to -- cgit v1.2.3 From 94485fedcb176a9105961e47bd9dda23801c1906 Mon Sep 17 00:00:00 2001 From: Alex Gartrell Date: Wed, 26 Aug 2015 09:40:34 -0700 Subject: ipvs: add schedule_icmp sysctl This sysctl will be used to enable the scheduling of icmp packets. Signed-off-by: Alex Gartrell Acked-by: Julian Anastasov Signed-off-by: Simon Horman --- include/net/ip_vs.h | 11 +++++++++++ 1 file changed, 11 insertions(+) (limited to 'include') diff --git a/include/net/ip_vs.h b/include/net/ip_vs.h index ba90729d1111..47677f0493c7 100644 --- a/include/net/ip_vs.h +++ b/include/net/ip_vs.h @@ -997,6 +997,7 @@ struct netns_ipvs { int sysctl_pmtu_disc; int sysctl_backup_only; int sysctl_conn_reuse_mode; + int sysctl_schedule_icmp; /* ip_vs_lblc */ int sysctl_lblc_expiration; @@ -1115,6 +1116,11 @@ static inline int sysctl_conn_reuse_mode(struct netns_ipvs *ipvs) return ipvs->sysctl_conn_reuse_mode; } +static inline int sysctl_schedule_icmp(struct netns_ipvs *ipvs) +{ + return ipvs->sysctl_schedule_icmp; +} + #else static inline int sysctl_sync_threshold(struct netns_ipvs *ipvs) @@ -1187,6 +1193,11 @@ static inline int sysctl_conn_reuse_mode(struct netns_ipvs *ipvs) return 1; } +static inline int sysctl_schedule_icmp(struct netns_ipvs *ipvs) +{ + return 0; +} + #endif /* IPVS core functions -- cgit v1.2.3 From b7503e0cdb5dbec5d201aa69d8888c14679b5ae8 Mon Sep 17 00:00:00 2001 From: David Ahern Date: Wed, 2 Sep 2015 13:58:35 -0700 Subject: net: Add FIB table id to rtable Add the FIB table id to rtable to make the information available for IPv4 as it is for IPv6. Signed-off-by: David Ahern Signed-off-by: David S. Miller --- include/net/route.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/net/route.h b/include/net/route.h index cc61cb95f059..10a7d21a211c 100644 --- a/include/net/route.h +++ b/include/net/route.h @@ -64,6 +64,8 @@ struct rtable { /* Miscellaneous cached information */ u32 rt_pmtu; + u32 rt_table_id; + struct list_head rt_uncached; struct uncached_list *rt_uncached_list; }; -- cgit v1.2.3 From c36ba6603a1154ac617d023bbcc062a12afb258b Mon Sep 17 00:00:00 2001 From: David Ahern Date: Wed, 2 Sep 2015 13:58:36 -0700 Subject: net: Allow user to get table id from route lookup rt_fill_info which is called for 'route get' requests hardcodes the table id as RT_TABLE_MAIN which is not correct when multiple tables are used. Use the newly added table id in the rtable to send back the correct table similar to what is done for IPv6. To maintain current ABI a new request flag, RTM_F_LOOKUP_TABLE, is added to indicate the actual table is wanted versus the hardcoded response. Signed-off-by: David Ahern Signed-off-by: David S. Miller --- include/uapi/linux/rtnetlink.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/uapi/linux/rtnetlink.h b/include/uapi/linux/rtnetlink.h index 702024769c74..06625b401422 100644 --- a/include/uapi/linux/rtnetlink.h +++ b/include/uapi/linux/rtnetlink.h @@ -270,6 +270,7 @@ enum rt_scope_t { #define RTM_F_CLONED 0x200 /* This route is cloned */ #define RTM_F_EQUALIZE 0x400 /* Multipath equalizer: NI */ #define RTM_F_PREFIX 0x800 /* Prefix addresses */ +#define RTM_F_LOOKUP_TABLE 0x1000 /* set rtm_table to FIB lookup result */ /* Reserved table identifiers */ -- cgit v1.2.3 From c40a2c8817e42273a4627c48c884b805475a733f Mon Sep 17 00:00:00 2001 From: Oliver Neukum Date: Mon, 7 Sep 2015 16:05:38 +0200 Subject: CDC: common parser for extra headers CDC drivers all implement their own parser for the extra headers. This patch fixes the code duplication introducing a single common parser in usbnet. Signed-off-by: Oliver Neukum Signed-off-by: David S. Miller --- include/linux/usb/cdc.h | 47 +++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 47 insertions(+) create mode 100644 include/linux/usb/cdc.h (limited to 'include') diff --git a/include/linux/usb/cdc.h b/include/linux/usb/cdc.h new file mode 100644 index 000000000000..cd8f2e1c3bdf --- /dev/null +++ b/include/linux/usb/cdc.h @@ -0,0 +1,47 @@ +/* + * USB CDC common helpers + * + * Copyright (c) 2015 Oliver Neukum + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License + * version 2 as published by the Free Software Foundation. + */ + +#include + +/* + * inofficial magic numbers + */ + +#define CDC_PHONET_MAGIC_NUMBER 0xAB + +/* + * parsing CDC headers + */ + +struct usb_cdc_parsed_header { + struct usb_cdc_union_desc *usb_cdc_union_desc; + struct usb_cdc_header_desc *usb_cdc_header_desc; + + struct usb_cdc_call_mgmt_descriptor *usb_cdc_call_mgmt_descriptor; + struct usb_cdc_acm_descriptor *usb_cdc_acm_descriptor; + struct usb_cdc_country_functional_desc *usb_cdc_country_functional_desc; + struct usb_cdc_network_terminal_desc *usb_cdc_network_terminal_desc; + struct usb_cdc_ether_desc *usb_cdc_ether_desc; + struct usb_cdc_dmm_desc *usb_cdc_dmm_desc; + struct usb_cdc_mdlm_desc *usb_cdc_mdlm_desc; + struct usb_cdc_mdlm_detail_desc *usb_cdc_mdlm_detail_desc; + struct usb_cdc_obex_desc *usb_cdc_obex_desc; + struct usb_cdc_ncm_desc *usb_cdc_ncm_desc; + struct usb_cdc_mbim_desc *usb_cdc_mbim_desc; + struct usb_cdc_mbim_extended_desc *usb_cdc_mbim_extended_desc; + + bool phonet_magic_present; +}; + + +int cdc_parse_cdc_header(struct usb_cdc_parsed_header *hdr, + struct usb_interface *intf, + u8 *buffer, + int buflen); -- cgit v1.2.3 From ad1e7b97b3adb91d46f3adb70a7867a50fc274cf Mon Sep 17 00:00:00 2001 From: "David S. Miller" Date: Tue, 15 Sep 2015 13:25:03 -0700 Subject: cdc: Fix build warning. In file included from drivers/usb/gadget/function/u_serial.h:16:0, from drivers/usb/gadget/function/f_acm.c:23: >> include/linux/usb/cdc.h:47:5: warning: 'struct usb_interface' declared inside parameter list int buflen); ^ >> include/linux/usb/cdc.h:47:5: warning: its scope is only this definition or declaration, which is probably not what you want Reported-by: kbuild test robot Signed-off-by: David S. Miller --- include/linux/usb/cdc.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/usb/cdc.h b/include/linux/usb/cdc.h index cd8f2e1c3bdf..959d0c838113 100644 --- a/include/linux/usb/cdc.h +++ b/include/linux/usb/cdc.h @@ -40,7 +40,7 @@ struct usb_cdc_parsed_header { bool phonet_magic_present; }; - +struct usb_interface; int cdc_parse_cdc_header(struct usb_cdc_parsed_header *hdr, struct usb_interface *intf, u8 *buffer, -- cgit v1.2.3 From d5566fd72ec1924958fcfd48b65c022c8f7eae64 Mon Sep 17 00:00:00 2001 From: Sowmini Varadhan Date: Fri, 11 Sep 2015 16:48:48 -0400 Subject: rtnetlink: RTEXT_FILTER_SKIP_STATS support to avoid dumping inet/inet6 stats Many commonly used functions like getifaddrs() invoke RTM_GETLINK to dump the interface information, and do not need the the AF_INET6 statististics that are always returned by default from rtnl_fill_ifinfo(). Computing the statistics can be an expensive operation that impacts scaling, so it is desirable to avoid this if the information is not needed. This patch adds a the RTEXT_FILTER_SKIP_STATS extended info flag that can be passed with netlink_request() to avoid statistics computation for the ifinfo path. Signed-off-by: Sowmini Varadhan Signed-off-by: David S. Miller --- include/net/rtnetlink.h | 3 ++- include/uapi/linux/rtnetlink.h | 1 + 2 files changed, 3 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/net/rtnetlink.h b/include/net/rtnetlink.h index 18fdb98185ab..aff6ceb891a9 100644 --- a/include/net/rtnetlink.h +++ b/include/net/rtnetlink.h @@ -122,7 +122,8 @@ struct rtnl_af_ops { int family; int (*fill_link_af)(struct sk_buff *skb, - const struct net_device *dev); + const struct net_device *dev, + u32 ext_filter_mask); size_t (*get_link_af_size)(const struct net_device *dev); int (*validate_link_af)(const struct net_device *dev, diff --git a/include/uapi/linux/rtnetlink.h b/include/uapi/linux/rtnetlink.h index 06625b401422..4db0b3ccb497 100644 --- a/include/uapi/linux/rtnetlink.h +++ b/include/uapi/linux/rtnetlink.h @@ -667,6 +667,7 @@ struct tcamsg { #define RTEXT_FILTER_VF (1 << 0) #define RTEXT_FILTER_BRVLAN (1 << 1) #define RTEXT_FILTER_BRVLAN_COMPRESSED (1 << 2) +#define RTEXT_FILTER_SKIP_STATS (1 << 3) /* End of information exported to user level */ -- cgit v1.2.3 From b84ee0d7f375ed7840c7c110d46eac24cf94b2a2 Mon Sep 17 00:00:00 2001 From: Stephen Rothwell Date: Wed, 16 Sep 2015 11:10:16 +1000 Subject: cdc: add header guards Signed-off-by: Stephen Rothwell Signed-off-by: David S. Miller --- include/linux/usb/cdc.h | 4 ++++ include/uapi/linux/usb/cdc.h | 6 +++--- 2 files changed, 7 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/include/linux/usb/cdc.h b/include/linux/usb/cdc.h index 959d0c838113..b5706f94ee9e 100644 --- a/include/linux/usb/cdc.h +++ b/include/linux/usb/cdc.h @@ -7,6 +7,8 @@ * modify it under the terms of the GNU General Public License * version 2 as published by the Free Software Foundation. */ +#ifndef __LINUX_USB_CDC_H +#define __LINUX_USB_CDC_H #include @@ -45,3 +47,5 @@ int cdc_parse_cdc_header(struct usb_cdc_parsed_header *hdr, struct usb_interface *intf, u8 *buffer, int buflen); + +#endif /* __LINUX_USB_CDC_H */ diff --git a/include/uapi/linux/usb/cdc.h b/include/uapi/linux/usb/cdc.h index b6a9cdd6e096..e2bc417b243b 100644 --- a/include/uapi/linux/usb/cdc.h +++ b/include/uapi/linux/usb/cdc.h @@ -6,8 +6,8 @@ * firmware based USB peripherals. */ -#ifndef __LINUX_USB_CDC_H -#define __LINUX_USB_CDC_H +#ifndef __UAPI_LINUX_USB_CDC_H +#define __UAPI_LINUX_USB_CDC_H #include @@ -444,4 +444,4 @@ struct usb_cdc_ncm_ndp_input_size { #define USB_CDC_NCM_CRC_NOT_APPENDED 0x00 #define USB_CDC_NCM_CRC_APPENDED 0x01 -#endif /* __LINUX_USB_CDC_H */ +#endif /* __UAPI_LINUX_USB_CDC_H */ -- cgit v1.2.3 From 4e478098ac0ac1b6ef9a70fcdc2ec8b93f1b59a1 Mon Sep 17 00:00:00 2001 From: Alex Gartrell Date: Mon, 14 Sep 2015 23:23:05 -0700 Subject: ipvs: add sysctl to ignore tunneled packets This is a way to avoid nasty routing loops when multiple ipvs instances can forward to eachother. Signed-off-by: Alex Gartrell Signed-off-by: Simon Horman --- include/net/ip_vs.h | 11 +++++++++++ 1 file changed, 11 insertions(+) (limited to 'include') diff --git a/include/net/ip_vs.h b/include/net/ip_vs.h index 47677f0493c7..1096a71ab6ed 100644 --- a/include/net/ip_vs.h +++ b/include/net/ip_vs.h @@ -998,6 +998,7 @@ struct netns_ipvs { int sysctl_backup_only; int sysctl_conn_reuse_mode; int sysctl_schedule_icmp; + int sysctl_ignore_tunneled; /* ip_vs_lblc */ int sysctl_lblc_expiration; @@ -1121,6 +1122,11 @@ static inline int sysctl_schedule_icmp(struct netns_ipvs *ipvs) return ipvs->sysctl_schedule_icmp; } +static inline int sysctl_ignore_tunneled(struct netns_ipvs *ipvs) +{ + return ipvs->sysctl_ignore_tunneled; +} + #else static inline int sysctl_sync_threshold(struct netns_ipvs *ipvs) @@ -1198,6 +1204,11 @@ static inline int sysctl_schedule_icmp(struct netns_ipvs *ipvs) return 0; } +static inline int sysctl_ignore_tunneled(struct netns_ipvs *ipvs) +{ + return 0; +} + #endif /* IPVS core functions -- cgit v1.2.3 From 6f558b70fb39fc8272fc513ecf191b3ad87d867b Mon Sep 17 00:00:00 2001 From: Loic Poulain Date: Sun, 30 Aug 2015 18:16:55 +0200 Subject: Bluetooth: Add bt_dev logging macros Add specific bluetooth device logging macros since hci device name is repeatedly referred in bluetooth subsystem logs. Signed-off-by: Loic Poulain Signed-off-by: Marcel Holtmann --- include/net/bluetooth/bluetooth.h | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'include') diff --git a/include/net/bluetooth/bluetooth.h b/include/net/bluetooth/bluetooth.h index 38d8a34d3589..fcf2ae7dbfa0 100644 --- a/include/net/bluetooth/bluetooth.h +++ b/include/net/bluetooth/bluetooth.h @@ -128,6 +128,13 @@ void bt_err(const char *fmt, ...); #define BT_ERR(fmt, ...) bt_err(fmt "\n", ##__VA_ARGS__) #define BT_DBG(fmt, ...) pr_debug(fmt "\n", ##__VA_ARGS__) +#define bt_dev_info(hdev, fmt, ...) \ + BT_INFO("%s: " fmt, (hdev)->name, ##__VA_ARGS__) +#define bt_dev_err(hdev, fmt, ...) \ + BT_ERR("%s: " fmt, (hdev)->name, ##__VA_ARGS__) +#define bt_dev_dbg(hdev, fmt, ...) \ + BT_DBG("%s: " fmt, (hdev)->name, ##__VA_ARGS__) + /* Connection and socket states */ enum { BT_CONNECTED = 1, /* Equal to TCP_ESTABLISHED to make net code happy */ -- cgit v1.2.3 From 6b3cc1db68ac83647d37f7d16f0261621eda24aa Mon Sep 17 00:00:00 2001 From: Simon Fels Date: Wed, 2 Sep 2015 12:10:12 +0200 Subject: Bluetooth: close HCI device when user channel socket gets closed With 9380f9eacfbbee701daa416edd6625efcd3e29e1 the order of unsetting the HCI_USER_CHANNEL flag of the HCI device was reverted to ensure the device is first closed before making it available again. Due to hci_dev_close checking for HCI_USER_CHANNEL being set on the device it was never really closed and was kept opened. We're now calling hci_dev_do_close directly to make sure the device is correctly closed and we keep the correct order to unset the flag on our device object. Signed-off-by: Simon Fels Signed-off-by: Marcel Holtmann --- include/net/bluetooth/hci_core.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/net/bluetooth/hci_core.h b/include/net/bluetooth/hci_core.h index 9e1a59e01fa2..256e6734c1fb 100644 --- a/include/net/bluetooth/hci_core.h +++ b/include/net/bluetooth/hci_core.h @@ -987,6 +987,7 @@ int hci_resume_dev(struct hci_dev *hdev); int hci_reset_dev(struct hci_dev *hdev); int hci_dev_open(__u16 dev); int hci_dev_close(__u16 dev); +int hci_dev_do_close(struct hci_dev *hdev); int hci_dev_reset(__u16 dev); int hci_dev_reset_stat(__u16 dev); int hci_dev_cmd(unsigned int cmd, void __user *arg); -- cgit v1.2.3 From 72a5e6bb5120d6464c9e7855c5a22555ede819dc Mon Sep 17 00:00:00 2001 From: Alexander Aring Date: Wed, 2 Sep 2015 14:21:25 +0200 Subject: ieee820154: 6lowpan: dispatch evaluation rework This patch complete reworks the evaluation of 6lowpan dispatch value by introducing a receive handler mechanism for each dispatch value. A list of changes: - Doing uncompression on-the-fly when FRAG1 is received, this require some special handling for 802.15.4 lltype in generic 6lowpan branch for setting the payload length correct. - Fix dispatch mask for fragmentation. - Add IPv6 dispatch evaluation for FRAG1. - Add skb_unshare for dispatch which might manipulate the skb data buffer. Cc: Jukka Rissanen Reviewed-by: Stefan Schmidt Signed-off-by: Alexander Aring Signed-off-by: Marcel Holtmann --- include/net/6lowpan.h | 31 +++++++++++++++++++++++++------ 1 file changed, 25 insertions(+), 6 deletions(-) (limited to 'include') diff --git a/include/net/6lowpan.h b/include/net/6lowpan.h index a2f59ec98d24..35098411dbb4 100644 --- a/include/net/6lowpan.h +++ b/include/net/6lowpan.h @@ -126,13 +126,19 @@ (((a)[6]) == 0xFF) && \ (((a)[7]) == 0xFF)) -#define LOWPAN_DISPATCH_IPV6 0x41 /* 01000001 = 65 */ -#define LOWPAN_DISPATCH_HC1 0x42 /* 01000010 = 66 */ -#define LOWPAN_DISPATCH_IPHC 0x60 /* 011xxxxx = ... */ -#define LOWPAN_DISPATCH_FRAG1 0xc0 /* 11000xxx */ -#define LOWPAN_DISPATCH_FRAGN 0xe0 /* 11100xxx */ +#define LOWPAN_DISPATCH_IPV6 0x41 /* 01000001 = 65 */ +#define LOWPAN_DISPATCH_IPHC 0x60 /* 011xxxxx = ... */ +#define LOWPAN_DISPATCH_IPHC_MASK 0xe0 -#define LOWPAN_DISPATCH_MASK 0xf8 /* 11111000 */ +static inline bool lowpan_is_ipv6(u8 dispatch) +{ + return dispatch == LOWPAN_DISPATCH_IPV6; +} + +static inline bool lowpan_is_iphc(u8 dispatch) +{ + return (dispatch & LOWPAN_DISPATCH_IPHC_MASK) == LOWPAN_DISPATCH_IPHC; +} #define LOWPAN_FRAG_TIMEOUT (HZ * 60) /* time-out 60 sec */ @@ -218,6 +224,19 @@ struct lowpan_priv *lowpan_priv(const struct net_device *dev) return netdev_priv(dev); } +struct lowpan_802154_cb { + u16 d_tag; + unsigned int d_size; + u8 d_offset; +}; + +static inline +struct lowpan_802154_cb *lowpan_802154_cb(const struct sk_buff *skb) +{ + BUILD_BUG_ON(sizeof(struct lowpan_802154_cb) > sizeof(skb->cb)); + return (struct lowpan_802154_cb *)skb->cb; +} + #ifdef DEBUG /* print data in line */ static inline void raw_dump_inline(const char *caller, char *msg, -- cgit v1.2.3 From 54552d03023cfd485cedf8d7471d1554139d58aa Mon Sep 17 00:00:00 2001 From: Alexander Aring Date: Wed, 2 Sep 2015 14:21:29 +0200 Subject: ieee802154: 6lowpan: check on valid 802.15.4 frame This patch adds frame control checks to check if the received frame is something which could contain a 6LoWPAN packet. Reviewed-by: Stefan Schmidt Signed-off-by: Alexander Aring Signed-off-by: Marcel Holtmann --- include/linux/ieee802154.h | 25 +++++++++++++++++++++++++ include/net/mac802154.h | 15 +++++++++++++++ 2 files changed, 40 insertions(+) (limited to 'include') diff --git a/include/linux/ieee802154.h b/include/linux/ieee802154.h index 1dc1f4ed4001..db01492814d3 100644 --- a/include/linux/ieee802154.h +++ b/include/linux/ieee802154.h @@ -205,6 +205,31 @@ enum { IEEE802154_SCAN_IN_PROGRESS = 0xfc, }; +/* frame control handling */ +#define IEEE802154_FCTL_FTYPE 0x0003 +#define IEEE802154_FCTL_INTRA_PAN 0x0040 + +#define IEEE802154_FTYPE_DATA 0x0001 + +/* + * ieee802154_is_data - check if type is IEEE802154_FTYPE_DATA + * @fc: frame control bytes in little-endian byteorder + */ +static inline int ieee802154_is_data(__le16 fc) +{ + return (fc & cpu_to_le16(IEEE802154_FCTL_FTYPE)) == + cpu_to_le16(IEEE802154_FTYPE_DATA); +} + +/** + * ieee802154_is_intra_pan - check if intra pan id communication + * @fc: frame control bytes in little-endian byteorder + */ +static inline bool ieee802154_is_intra_pan(__le16 fc) +{ + return fc & cpu_to_le16(IEEE802154_FCTL_INTRA_PAN); +} + /** * ieee802154_is_valid_psdu_len - check if psdu len is valid * available lengths: diff --git a/include/net/mac802154.h b/include/net/mac802154.h index b7f99615224b..32bd7c0467d4 100644 --- a/include/net/mac802154.h +++ b/include/net/mac802154.h @@ -249,6 +249,21 @@ struct ieee802154_ops { const bool on); }; +/** + * ieee802154_get_fc_from_skb - get the frame control field from an skb + * @skb: skb where the frame control field will be get from + */ +static inline __le16 ieee802154_get_fc_from_skb(const struct sk_buff *skb) +{ + /* return some invalid fc on failure */ + if (unlikely(skb->mac_len < 2)) { + WARN_ON(1); + return cpu_to_le16(0); + } + + return (__force __le16)__get_unaligned_memmove16(skb_mac_header(skb)); +} + /** * ieee802154_be64_to_le64 - copies and convert be64 to le64 * @le64_dst: le64 destination pointer -- cgit v1.2.3 From 187625e18498ff0f3738a059778a8578171f06c8 Mon Sep 17 00:00:00 2001 From: Alexander Aring Date: Wed, 2 Sep 2015 14:21:31 +0200 Subject: ieee802154: 6lowpan: remove tx full-size calc workaround This patch removes a workaround for datagram_size calculation while doing fragmentation on transmit. Reviewed-by: Stefan Schmidt Signed-off-by: Alexander Aring Signed-off-by: Marcel Holtmann --- include/net/6lowpan.h | 113 -------------------------------------------------- 1 file changed, 113 deletions(-) (limited to 'include') diff --git a/include/net/6lowpan.h b/include/net/6lowpan.h index 35098411dbb4..eeae5eb58754 100644 --- a/include/net/6lowpan.h +++ b/include/net/6lowpan.h @@ -299,119 +299,6 @@ static inline void lowpan_push_hc_data(u8 **hc_ptr, const void *data, *hc_ptr += len; } -static inline u8 lowpan_addr_mode_size(const u8 addr_mode) -{ - static const u8 addr_sizes[] = { - [LOWPAN_IPHC_ADDR_00] = 16, - [LOWPAN_IPHC_ADDR_01] = 8, - [LOWPAN_IPHC_ADDR_02] = 2, - [LOWPAN_IPHC_ADDR_03] = 0, - }; - return addr_sizes[addr_mode]; -} - -static inline u8 lowpan_next_hdr_size(const u8 h_enc, u16 *uncomp_header) -{ - u8 ret = 1; - - if ((h_enc & LOWPAN_NHC_UDP_MASK) == LOWPAN_NHC_UDP_ID) { - *uncomp_header += sizeof(struct udphdr); - - switch (h_enc & LOWPAN_NHC_UDP_CS_P_11) { - case LOWPAN_NHC_UDP_CS_P_00: - ret += 4; - break; - case LOWPAN_NHC_UDP_CS_P_01: - case LOWPAN_NHC_UDP_CS_P_10: - ret += 3; - break; - case LOWPAN_NHC_UDP_CS_P_11: - ret++; - break; - default: - break; - } - - if (!(h_enc & LOWPAN_NHC_UDP_CS_C)) - ret += 2; - } - - return ret; -} - -/** - * lowpan_uncompress_size - returns skb->len size with uncompressed header - * @skb: sk_buff with 6lowpan header inside - * @datagram_offset: optional to get the datagram_offset value - * - * Returns the skb->len with uncompressed header - */ -static inline u16 -lowpan_uncompress_size(const struct sk_buff *skb, u16 *dgram_offset) -{ - u16 ret = 2, uncomp_header = sizeof(struct ipv6hdr); - u8 iphc0, iphc1, h_enc; - - iphc0 = skb_network_header(skb)[0]; - iphc1 = skb_network_header(skb)[1]; - - switch ((iphc0 & LOWPAN_IPHC_TF) >> 3) { - case 0: - ret += 4; - break; - case 1: - ret += 3; - break; - case 2: - ret++; - break; - default: - break; - } - - if (!(iphc0 & LOWPAN_IPHC_NH_C)) - ret++; - - if (!(iphc0 & 0x03)) - ret++; - - ret += lowpan_addr_mode_size((iphc1 & LOWPAN_IPHC_SAM) >> - LOWPAN_IPHC_SAM_BIT); - - if (iphc1 & LOWPAN_IPHC_M) { - switch ((iphc1 & LOWPAN_IPHC_DAM_11) >> - LOWPAN_IPHC_DAM_BIT) { - case LOWPAN_IPHC_DAM_00: - ret += 16; - break; - case LOWPAN_IPHC_DAM_01: - ret += 6; - break; - case LOWPAN_IPHC_DAM_10: - ret += 4; - break; - case LOWPAN_IPHC_DAM_11: - ret++; - break; - default: - break; - } - } else { - ret += lowpan_addr_mode_size((iphc1 & LOWPAN_IPHC_DAM_11) >> - LOWPAN_IPHC_DAM_BIT); - } - - if (iphc0 & LOWPAN_IPHC_NH_C) { - h_enc = skb_network_header(skb)[ret]; - ret += lowpan_next_hdr_size(h_enc, &uncomp_header); - } - - if (dgram_offset) - *dgram_offset = uncomp_header; - - return skb->len + uncomp_header - ret; -} - void lowpan_netdev_setup(struct net_device *dev, enum lowpan_lltypes lltype); int -- cgit v1.2.3 From bfe08a875a8903c0abb1ef5d57722252d14ede2e Mon Sep 17 00:00:00 2001 From: Stefan Schmidt Date: Thu, 3 Sep 2015 16:31:35 +0200 Subject: ieee802154: af_ieee802154: fix typo in comment. Signed-off-by: Stefan Schmidt Acked-by: Alexander Aring Signed-off-by: Marcel Holtmann --- include/net/af_ieee802154.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/net/af_ieee802154.h b/include/net/af_ieee802154.h index 7d38e2ffd256..a5563d27a3eb 100644 --- a/include/net/af_ieee802154.h +++ b/include/net/af_ieee802154.h @@ -1,5 +1,5 @@ /* - * IEEE 802.15.4 inteface for userspace + * IEEE 802.15.4 interface for userspace * * Copyright 2007, 2008 Siemens AG * -- cgit v1.2.3 From fb884253a919148677c5bf347ffb62c539370440 Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Tue, 15 Sep 2015 20:03:49 -0500 Subject: netfilter: Remove !CONFIG_NETFITLER definition of nf_hook_thresh The !CONFIG_NETFILTER definition of nf_hook_thresh calls okfn when the CONFIG_NETFITLER defintion does not, making it buggy. As the !CONFIG_NETFILTER defintion of nf_hook_thresh is not used remove it rather than fix it. Signed-off-by: "Eric W. Biederman" Signed-off-by: David S. Miller --- include/linux/netfilter.h | 9 --------- 1 file changed, 9 deletions(-) (limited to 'include') diff --git a/include/linux/netfilter.h b/include/linux/netfilter.h index 36a652531791..1abac85ec907 100644 --- a/include/linux/netfilter.h +++ b/include/linux/netfilter.h @@ -344,15 +344,6 @@ nf_nat_decode_session(struct sk_buff *skb, struct flowi *fl, u_int8_t family) #else /* !CONFIG_NETFILTER */ #define NF_HOOK(pf, hook, sk, skb, indev, outdev, okfn) (okfn)(sk, skb) #define NF_HOOK_COND(pf, hook, sk, skb, indev, outdev, okfn, cond) (okfn)(sk, skb) -static inline int nf_hook_thresh(u_int8_t pf, unsigned int hook, - struct sock *sk, - struct sk_buff *skb, - struct net_device *indev, - struct net_device *outdev, - int (*okfn)(struct sock *sk, struct sk_buff *), int thresh) -{ - return okfn(sk, skb); -} static inline int nf_hook(u_int8_t pf, unsigned int hook, struct sock *sk, struct sk_buff *skb, struct net_device *indev, struct net_device *outdev, -- cgit v1.2.3 From b11b1f652dccde707d568f4012b01a8ec5bd5f57 Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Tue, 15 Sep 2015 20:03:50 -0500 Subject: netfilter: Store net in nf_hook_state Signed-off-by: "Eric W. Biederman" Signed-off-by: David S. Miller --- include/linux/netfilter.h | 5 ++++- include/linux/netfilter_ingress.h | 2 +- 2 files changed, 5 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/netfilter.h b/include/linux/netfilter.h index 1abac85ec907..889ac0e11f01 100644 --- a/include/linux/netfilter.h +++ b/include/linux/netfilter.h @@ -54,6 +54,7 @@ struct nf_hook_state { struct net_device *in; struct net_device *out; struct sock *sk; + struct net *net; struct list_head *hook_list; int (*okfn)(struct sock *, struct sk_buff *); }; @@ -65,6 +66,7 @@ static inline void nf_hook_state_init(struct nf_hook_state *p, struct net_device *indev, struct net_device *outdev, struct sock *sk, + struct net *net, int (*okfn)(struct sock *, struct sk_buff *)) { p->hook = hook; @@ -73,6 +75,7 @@ static inline void nf_hook_state_init(struct nf_hook_state *p, p->in = indev; p->out = outdev; p->sk = sk; + p->net = net; p->hook_list = hook_list; p->okfn = okfn; } @@ -181,7 +184,7 @@ static inline int nf_hook_thresh(u_int8_t pf, unsigned int hook, struct nf_hook_state state; nf_hook_state_init(&state, hook_list, hook, thresh, - pf, indev, outdev, sk, okfn); + pf, indev, outdev, sk, net, okfn); return nf_hook_slow(skb, &state); } return 1; diff --git a/include/linux/netfilter_ingress.h b/include/linux/netfilter_ingress.h index cb0727fe2b3d..187feabe557c 100644 --- a/include/linux/netfilter_ingress.h +++ b/include/linux/netfilter_ingress.h @@ -17,7 +17,7 @@ static inline int nf_hook_ingress(struct sk_buff *skb) nf_hook_state_init(&state, &skb->dev->nf_hooks_ingress, NF_NETDEV_INGRESS, INT_MIN, NFPROTO_NETDEV, NULL, - skb->dev, NULL, NULL); + skb->dev, NULL, dev_net(skb->dev), NULL); return nf_hook_slow(skb, &state); } -- cgit v1.2.3 From 7a7735044e1eab1415697b3139e758d24a600099 Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Tue, 15 Sep 2015 20:03:51 -0500 Subject: netfilter: Pass net to nf_hook_thresh Signed-off-by: "Eric W. Biederman" Signed-off-by: David S. Miller --- include/linux/netfilter.h | 11 +++++++---- 1 file changed, 7 insertions(+), 4 deletions(-) (limited to 'include') diff --git a/include/linux/netfilter.h b/include/linux/netfilter.h index 889ac0e11f01..042148dc1e22 100644 --- a/include/linux/netfilter.h +++ b/include/linux/netfilter.h @@ -170,6 +170,7 @@ int nf_hook_slow(struct sk_buff *skb, struct nf_hook_state *state); * value indicates the packet has been consumed by the hook. */ static inline int nf_hook_thresh(u_int8_t pf, unsigned int hook, + struct net *net, struct sock *sk, struct sk_buff *skb, struct net_device *indev, @@ -177,7 +178,6 @@ static inline int nf_hook_thresh(u_int8_t pf, unsigned int hook, int (*okfn)(struct sock *, struct sk_buff *), int thresh) { - struct net *net = dev_net(indev ? indev : outdev); struct list_head *hook_list = &net->nf.hooks[pf][hook]; if (nf_hook_list_active(hook_list, pf, hook)) { @@ -195,7 +195,8 @@ static inline int nf_hook(u_int8_t pf, unsigned int hook, struct sock *sk, struct net_device *outdev, int (*okfn)(struct sock *, struct sk_buff *)) { - return nf_hook_thresh(pf, hook, sk, skb, indev, outdev, okfn, INT_MIN); + struct net *net = dev_net(indev ? indev : outdev); + return nf_hook_thresh(pf, hook, net, sk, skb, indev, outdev, okfn, INT_MIN); } /* Activate hook; either okfn or kfree_skb called, unless a hook @@ -221,7 +222,8 @@ NF_HOOK_THRESH(uint8_t pf, unsigned int hook, struct sock *sk, struct net_device *out, int (*okfn)(struct sock *, struct sk_buff *), int thresh) { - int ret = nf_hook_thresh(pf, hook, sk, skb, in, out, okfn, thresh); + struct net *net = dev_net(in ? in : out); + int ret = nf_hook_thresh(pf, hook, net, sk, skb, in, out, okfn, thresh); if (ret == 1) ret = okfn(sk, skb); return ret; @@ -232,10 +234,11 @@ NF_HOOK_COND(uint8_t pf, unsigned int hook, struct sock *sk, struct sk_buff *skb, struct net_device *in, struct net_device *out, int (*okfn)(struct sock *, struct sk_buff *), bool cond) { + struct net *net = dev_net(in ? in : out); int ret; if (!cond || - ((ret = nf_hook_thresh(pf, hook, sk, skb, in, out, okfn, INT_MIN)) == 1)) + ((ret = nf_hook_thresh(pf, hook, net, sk, skb, in, out, okfn, INT_MIN)) == 1)) ret = okfn(sk, skb); return ret; } -- cgit v1.2.3 From a6568b2425daffc7b21ae63b6601b57ae14b5cb8 Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Tue, 15 Sep 2015 20:03:52 -0500 Subject: xfrm: Remove unused afinfo method init_dst Signed-off-by: "Eric W. Biederman" Signed-off-by: David S. Miller --- include/net/xfrm.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include') diff --git a/include/net/xfrm.h b/include/net/xfrm.h index 312e3fee9ccf..fd176106909a 100644 --- a/include/net/xfrm.h +++ b/include/net/xfrm.h @@ -296,8 +296,6 @@ struct xfrm_policy_afinfo { struct flowi *fl, int reverse); int (*get_tos)(const struct flowi *fl); - void (*init_dst)(struct net *net, - struct xfrm_dst *dst); int (*init_path)(struct xfrm_dst *path, struct dst_entry *dst, int nfheader_len); -- cgit v1.2.3 From 5a70649e0dae02ba5090540fffce667d2300bc5a Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Tue, 15 Sep 2015 20:03:53 -0500 Subject: net: Merge dst_output and dst_output_sk Add a sock paramter to dst_output making dst_output_sk superfluous. Add a skb->sk parameter to all of the callers of dst_output Have the callers of dst_output_sk call dst_output. Signed-off-by: "Eric W. Biederman" Signed-off-by: David S. Miller --- include/net/dst.h | 6 +----- 1 file changed, 1 insertion(+), 5 deletions(-) (limited to 'include') diff --git a/include/net/dst.h b/include/net/dst.h index 9261d928303d..c72e58474e52 100644 --- a/include/net/dst.h +++ b/include/net/dst.h @@ -454,14 +454,10 @@ static inline void dst_set_expires(struct dst_entry *dst, int timeout) } /* Output packet to network from transport. */ -static inline int dst_output_sk(struct sock *sk, struct sk_buff *skb) +static inline int dst_output(struct sock *sk, struct sk_buff *skb) { return skb_dst(skb)->output(sk, skb); } -static inline int dst_output(struct sk_buff *skb) -{ - return dst_output_sk(skb->sk, skb); -} /* Input packet from network to transport. */ static inline int dst_input(struct sk_buff *skb) -- cgit v1.2.3 From 2b4aa3cec4873005a0d5155395b34641584b3a4e Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Tue, 15 Sep 2015 20:04:07 -0500 Subject: net: Remove dev_queue_xmit_sk A function with weird arguments that it will never use to accomdate a netfilter callback prototype is absolutely in the core of the networking stack. Frankly it does not make sense and it causes a lot of confusion as to why arguments that are never used are being passed to the function. As I am preparing to make a second change to arguments to the okfn even the names stops making sense. As I have removed the two callers of this function remove this confusion from the networking stack. Signed-off-by: "Eric W. Biederman" Signed-off-by: David S. Miller --- include/linux/netdevice.h | 6 +----- 1 file changed, 1 insertion(+), 5 deletions(-) (limited to 'include') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 88a00694eda5..e664f87c8e4c 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -2213,11 +2213,7 @@ int dev_close(struct net_device *dev); int dev_close_many(struct list_head *head, bool unlink); void dev_disable_lro(struct net_device *dev); int dev_loopback_xmit(struct sock *sk, struct sk_buff *newskb); -int dev_queue_xmit_sk(struct sock *sk, struct sk_buff *skb); -static inline int dev_queue_xmit(struct sk_buff *skb) -{ - return dev_queue_xmit_sk(skb->sk, skb); -} +int dev_queue_xmit(struct sk_buff *skb); int dev_queue_xmit_accel(struct sk_buff *skb, void *accel_priv); int register_netdevice(struct net_device *dev); void unregister_netdevice_queue(struct net_device *dev, struct list_head *head); -- cgit v1.2.3 From 04eb44890e5bb3cc855e5c0f18a05eb7311364b7 Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Tue, 15 Sep 2015 20:04:15 -0500 Subject: bridge: Add br_netif_receive_skb remove netif_receive_skb_sk netif_receive_skb_sk is only called once in the bridge code, replace it with a bridge specific function that calls netif_receive_skb. Signed-off-by: "Eric W. Biederman" Signed-off-by: David S. Miller --- include/linux/netdevice.h | 6 +----- 1 file changed, 1 insertion(+), 5 deletions(-) (limited to 'include') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index e664f87c8e4c..97ab5c9a7069 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -2985,11 +2985,7 @@ static inline void dev_consume_skb_any(struct sk_buff *skb) int netif_rx(struct sk_buff *skb); int netif_rx_ni(struct sk_buff *skb); -int netif_receive_skb_sk(struct sock *sk, struct sk_buff *skb); -static inline int netif_receive_skb(struct sk_buff *skb) -{ - return netif_receive_skb_sk(skb->sk, skb); -} +int netif_receive_skb(struct sk_buff *skb); gro_result_t napi_gro_receive(struct napi_struct *napi, struct sk_buff *skb); void napi_gro_flush(struct napi_struct *napi, bool flush_old); struct sk_buff *napi_get_frags(struct napi_struct *napi); -- cgit v1.2.3 From 29a26a56803855a79dbd028cd61abee56237d6e5 Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Tue, 15 Sep 2015 20:04:16 -0500 Subject: netfilter: Pass struct net into the netfilter hooks Pass a network namespace parameter into the netfilter hooks. At the call site of the netfilter hooks the path a packet is taking through the network stack is well known which allows the network namespace to be easily and reliabily. This allows the replacement of magic code like "dev_net(state->in?:state->out)" that appears at the start of most netfilter hooks with "state->net". In almost all cases the network namespace passed in is derived from the first network device passed in, guaranteeing those paths will not see any changes in practice. The exceptions are: xfrm/xfrm_output.c:xfrm_output_resume() xs_net(skb_dst(skb)->xfrm) ipvs/ip_vs_xmit.c:ip_vs_nat_send_or_cont() ip_vs_conn_net(cp) ipvs/ip_vs_xmit.c:ip_vs_send_or_cont() ip_vs_conn_net(cp) ipv4/raw.c:raw_send_hdrinc() sock_net(sk) ipv6/ip6_output.c:ip6_xmit() sock_net(sk) ipv6/ndisc.c:ndisc_send_skb() dev_net(skb->dev) not dev_net(dst->dev) ipv6/raw.c:raw6_send_hdrinc() sock_net(sk) br_netfilter_hooks.c:br_nf_pre_routing_finish() dev_net(skb->dev) before skb->dev is set to nf_bridge->physindev In all cases these exceptions seem to be a better expression for the network namespace the packet is being processed in then the historic "dev_net(in?in:out)". I am documenting them in case something odd pops up and someone starts trying to track down what happened. Signed-off-by: "Eric W. Biederman" Signed-off-by: David S. Miller --- include/linux/netfilter.h | 27 ++++++++++++--------------- 1 file changed, 12 insertions(+), 15 deletions(-) (limited to 'include') diff --git a/include/linux/netfilter.h b/include/linux/netfilter.h index 042148dc1e22..295f2650b5dc 100644 --- a/include/linux/netfilter.h +++ b/include/linux/netfilter.h @@ -190,12 +190,11 @@ static inline int nf_hook_thresh(u_int8_t pf, unsigned int hook, return 1; } -static inline int nf_hook(u_int8_t pf, unsigned int hook, struct sock *sk, - struct sk_buff *skb, struct net_device *indev, - struct net_device *outdev, +static inline int nf_hook(u_int8_t pf, unsigned int hook, struct net *net, + struct sock *sk, struct sk_buff *skb, + struct net_device *indev, struct net_device *outdev, int (*okfn)(struct sock *, struct sk_buff *)) { - struct net *net = dev_net(indev ? indev : outdev); return nf_hook_thresh(pf, hook, net, sk, skb, indev, outdev, okfn, INT_MIN); } @@ -217,12 +216,11 @@ static inline int nf_hook(u_int8_t pf, unsigned int hook, struct sock *sk, */ static inline int -NF_HOOK_THRESH(uint8_t pf, unsigned int hook, struct sock *sk, +NF_HOOK_THRESH(uint8_t pf, unsigned int hook, struct net *net, struct sock *sk, struct sk_buff *skb, struct net_device *in, struct net_device *out, int (*okfn)(struct sock *, struct sk_buff *), int thresh) { - struct net *net = dev_net(in ? in : out); int ret = nf_hook_thresh(pf, hook, net, sk, skb, in, out, okfn, thresh); if (ret == 1) ret = okfn(sk, skb); @@ -230,11 +228,10 @@ NF_HOOK_THRESH(uint8_t pf, unsigned int hook, struct sock *sk, } static inline int -NF_HOOK_COND(uint8_t pf, unsigned int hook, struct sock *sk, +NF_HOOK_COND(uint8_t pf, unsigned int hook, struct net *net, struct sock *sk, struct sk_buff *skb, struct net_device *in, struct net_device *out, int (*okfn)(struct sock *, struct sk_buff *), bool cond) { - struct net *net = dev_net(in ? in : out); int ret; if (!cond || @@ -244,11 +241,11 @@ NF_HOOK_COND(uint8_t pf, unsigned int hook, struct sock *sk, } static inline int -NF_HOOK(uint8_t pf, unsigned int hook, struct sock *sk, struct sk_buff *skb, +NF_HOOK(uint8_t pf, unsigned int hook, struct net *net, struct sock *sk, struct sk_buff *skb, struct net_device *in, struct net_device *out, int (*okfn)(struct sock *, struct sk_buff *)) { - return NF_HOOK_THRESH(pf, hook, sk, skb, in, out, okfn, INT_MIN); + return NF_HOOK_THRESH(pf, hook, net, sk, skb, in, out, okfn, INT_MIN); } /* Call setsockopt() */ @@ -348,11 +345,11 @@ nf_nat_decode_session(struct sk_buff *skb, struct flowi *fl, u_int8_t family) } #else /* !CONFIG_NETFILTER */ -#define NF_HOOK(pf, hook, sk, skb, indev, outdev, okfn) (okfn)(sk, skb) -#define NF_HOOK_COND(pf, hook, sk, skb, indev, outdev, okfn, cond) (okfn)(sk, skb) -static inline int nf_hook(u_int8_t pf, unsigned int hook, struct sock *sk, - struct sk_buff *skb, struct net_device *indev, - struct net_device *outdev, +#define NF_HOOK(pf, hook, net, sk, skb, indev, outdev, okfn) (okfn)(sk, skb) +#define NF_HOOK_COND(pf, hook, net, sk, skb, indev, outdev, okfn, cond) (okfn)(sk, skb) +static inline int nf_hook(u_int8_t pf, unsigned int hook, struct net *net, + struct sock *sk, struct sk_buff *skb, + struct net_device *indev, struct net_device *outdev, int (*okfn)(struct sock *, struct sk_buff *)) { return 1; -- cgit v1.2.3 From 0c4b51f0054ce85c0ec578ab818f0631834573eb Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Tue, 15 Sep 2015 20:04:18 -0500 Subject: netfilter: Pass net into okfn This is immediately motivated by the bridge code that chains functions that call into netfilter. Without passing net into the okfns the bridge code would need to guess about the best expression for the network namespace to process packets in. As net is frequently one of the first things computed in continuation functions after netfilter has done it's job passing in the desired network namespace is in many cases a code simplification. To support this change the function dst_output_okfn is introduced to simplify passing dst_output as an okfn. For the moment dst_output_okfn just silently drops the struct net. Signed-off-by: "Eric W. Biederman" Signed-off-by: David S. Miller --- include/linux/netdevice.h | 2 +- include/linux/netfilter.h | 26 ++++++++++++++------------ include/linux/netfilter_bridge.h | 2 +- include/net/dn_neigh.h | 6 +++--- include/net/dst.h | 4 ++++ include/net/ipv6.h | 2 +- include/net/netfilter/br_netfilter.h | 2 +- 7 files changed, 25 insertions(+), 19 deletions(-) (limited to 'include') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 97ab5c9a7069..b791405958b4 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -2212,7 +2212,7 @@ int dev_open(struct net_device *dev); int dev_close(struct net_device *dev); int dev_close_many(struct list_head *head, bool unlink); void dev_disable_lro(struct net_device *dev); -int dev_loopback_xmit(struct sock *sk, struct sk_buff *newskb); +int dev_loopback_xmit(struct net *net, struct sock *sk, struct sk_buff *newskb); int dev_queue_xmit(struct sk_buff *skb); int dev_queue_xmit_accel(struct sk_buff *skb, void *accel_priv); int register_netdevice(struct net_device *dev); diff --git a/include/linux/netfilter.h b/include/linux/netfilter.h index 295f2650b5dc..0b4d4560f33d 100644 --- a/include/linux/netfilter.h +++ b/include/linux/netfilter.h @@ -56,7 +56,7 @@ struct nf_hook_state { struct sock *sk; struct net *net; struct list_head *hook_list; - int (*okfn)(struct sock *, struct sk_buff *); + int (*okfn)(struct net *, struct sock *, struct sk_buff *); }; static inline void nf_hook_state_init(struct nf_hook_state *p, @@ -67,7 +67,7 @@ static inline void nf_hook_state_init(struct nf_hook_state *p, struct net_device *outdev, struct sock *sk, struct net *net, - int (*okfn)(struct sock *, struct sk_buff *)) + int (*okfn)(struct net *, struct sock *, struct sk_buff *)) { p->hook = hook; p->thresh = thresh; @@ -175,7 +175,7 @@ static inline int nf_hook_thresh(u_int8_t pf, unsigned int hook, struct sk_buff *skb, struct net_device *indev, struct net_device *outdev, - int (*okfn)(struct sock *, struct sk_buff *), + int (*okfn)(struct net *, struct sock *, struct sk_buff *), int thresh) { struct list_head *hook_list = &net->nf.hooks[pf][hook]; @@ -193,7 +193,7 @@ static inline int nf_hook_thresh(u_int8_t pf, unsigned int hook, static inline int nf_hook(u_int8_t pf, unsigned int hook, struct net *net, struct sock *sk, struct sk_buff *skb, struct net_device *indev, struct net_device *outdev, - int (*okfn)(struct sock *, struct sk_buff *)) + int (*okfn)(struct net *, struct sock *, struct sk_buff *)) { return nf_hook_thresh(pf, hook, net, sk, skb, indev, outdev, okfn, INT_MIN); } @@ -219,31 +219,33 @@ static inline int NF_HOOK_THRESH(uint8_t pf, unsigned int hook, struct net *net, struct sock *sk, struct sk_buff *skb, struct net_device *in, struct net_device *out, - int (*okfn)(struct sock *, struct sk_buff *), int thresh) + int (*okfn)(struct net *, struct sock *, struct sk_buff *), + int thresh) { int ret = nf_hook_thresh(pf, hook, net, sk, skb, in, out, okfn, thresh); if (ret == 1) - ret = okfn(sk, skb); + ret = okfn(net, sk, skb); return ret; } static inline int NF_HOOK_COND(uint8_t pf, unsigned int hook, struct net *net, struct sock *sk, struct sk_buff *skb, struct net_device *in, struct net_device *out, - int (*okfn)(struct sock *, struct sk_buff *), bool cond) + int (*okfn)(struct net *, struct sock *, struct sk_buff *), + bool cond) { int ret; if (!cond || ((ret = nf_hook_thresh(pf, hook, net, sk, skb, in, out, okfn, INT_MIN)) == 1)) - ret = okfn(sk, skb); + ret = okfn(net, sk, skb); return ret; } static inline int NF_HOOK(uint8_t pf, unsigned int hook, struct net *net, struct sock *sk, struct sk_buff *skb, struct net_device *in, struct net_device *out, - int (*okfn)(struct sock *, struct sk_buff *)) + int (*okfn)(struct net *, struct sock *, struct sk_buff *)) { return NF_HOOK_THRESH(pf, hook, net, sk, skb, in, out, okfn, INT_MIN); } @@ -345,12 +347,12 @@ nf_nat_decode_session(struct sk_buff *skb, struct flowi *fl, u_int8_t family) } #else /* !CONFIG_NETFILTER */ -#define NF_HOOK(pf, hook, net, sk, skb, indev, outdev, okfn) (okfn)(sk, skb) -#define NF_HOOK_COND(pf, hook, net, sk, skb, indev, outdev, okfn, cond) (okfn)(sk, skb) +#define NF_HOOK(pf, hook, net, sk, skb, indev, outdev, okfn) (okfn)(net, sk, skb) +#define NF_HOOK_COND(pf, hook, net, sk, skb, indev, outdev, okfn, cond) (okfn)(net, sk, skb) static inline int nf_hook(u_int8_t pf, unsigned int hook, struct net *net, struct sock *sk, struct sk_buff *skb, struct net_device *indev, struct net_device *outdev, - int (*okfn)(struct sock *, struct sk_buff *)) + int (*okfn)(struct net *, struct sock *, struct sk_buff *)) { return 1; } diff --git a/include/linux/netfilter_bridge.h b/include/linux/netfilter_bridge.h index 2437b8a5d7a9..2ed40c402b5e 100644 --- a/include/linux/netfilter_bridge.h +++ b/include/linux/netfilter_bridge.h @@ -17,7 +17,7 @@ enum nf_br_hook_priorities { #if IS_ENABLED(CONFIG_BRIDGE_NETFILTER) -int br_handle_frame_finish(struct sock *sk, struct sk_buff *skb); +int br_handle_frame_finish(struct net *net, struct sock *sk, struct sk_buff *skb); static inline void br_drop_fake_rtable(struct sk_buff *skb) { diff --git a/include/net/dn_neigh.h b/include/net/dn_neigh.h index d0424269313f..5e902fc3f4eb 100644 --- a/include/net/dn_neigh.h +++ b/include/net/dn_neigh.h @@ -18,11 +18,11 @@ struct dn_neigh { void dn_neigh_init(void); void dn_neigh_cleanup(void); -int dn_neigh_router_hello(struct sock *sk, struct sk_buff *skb); -int dn_neigh_endnode_hello(struct sock *sk, struct sk_buff *skb); +int dn_neigh_router_hello(struct net *net, struct sock *sk, struct sk_buff *skb); +int dn_neigh_endnode_hello(struct net *net, struct sock *sk, struct sk_buff *skb); void dn_neigh_pointopoint_hello(struct sk_buff *skb); int dn_neigh_elist(struct net_device *dev, unsigned char *ptr, int n); -int dn_to_neigh_output(struct sock *sk, struct sk_buff *skb); +int dn_to_neigh_output(struct net *net, struct sock *sk, struct sk_buff *skb); extern struct neigh_table dn_neigh_table; diff --git a/include/net/dst.h b/include/net/dst.h index c72e58474e52..df0481a07029 100644 --- a/include/net/dst.h +++ b/include/net/dst.h @@ -458,6 +458,10 @@ static inline int dst_output(struct sock *sk, struct sk_buff *skb) { return skb_dst(skb)->output(sk, skb); } +static inline int dst_output_okfn(struct net *net, struct sock *sk, struct sk_buff *skb) +{ + return dst_output(sk, skb); +} /* Input packet from network to transport. */ static inline int dst_input(struct sk_buff *skb) diff --git a/include/net/ipv6.h b/include/net/ipv6.h index 711cca428cc8..384a93cf07d6 100644 --- a/include/net/ipv6.h +++ b/include/net/ipv6.h @@ -807,7 +807,7 @@ static inline u8 ip6_tclass(__be32 flowinfo) int ipv6_rcv(struct sk_buff *skb, struct net_device *dev, struct packet_type *pt, struct net_device *orig_dev); -int ip6_rcv_finish(struct sock *sk, struct sk_buff *skb); +int ip6_rcv_finish(struct net *net, struct sock *sk, struct sk_buff *skb); /* * upper-layer output functions diff --git a/include/net/netfilter/br_netfilter.h b/include/net/netfilter/br_netfilter.h index d4c6b5f30acd..8fe266504900 100644 --- a/include/net/netfilter/br_netfilter.h +++ b/include/net/netfilter/br_netfilter.h @@ -31,7 +31,7 @@ static inline void nf_bridge_push_encap_header(struct sk_buff *skb) skb->network_header -= len; } -int br_nf_pre_routing_finish_bridge(struct sock *sk, struct sk_buff *skb); +int br_nf_pre_routing_finish_bridge(struct net *net, struct sock *sk, struct sk_buff *skb); static inline struct rtable *bridge_parent_rtable(const struct net_device *dev) { -- cgit v1.2.3 From 58d607d3e52f2b15902f58a1161da9fb3b0f6d47 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Tue, 15 Sep 2015 15:24:20 -0700 Subject: tcp: provide skb->hash to synack packets In commit b73c3d0e4f0e ("net: Save TX flow hash in sock and set in skbuf on xmit"), Tom provided a l4 hash to most outgoing TCP packets. We'd like to provide one as well for SYNACK packets, so that all packets of a given flow share same txhash, to later enable bonding driver to also use skb->hash to perform slave selection. Note that a SYNACK retransmit shuffles the tx hash, as Tom did in commit 265f94ff54d62 ("net: Recompute sk_txhash on negative routing advice") for established sockets. This has nice effect making TCP flows resilient to some kind of black holes, even at connection establish phase. Signed-off-by: Eric Dumazet Cc: Tom Herbert Cc: Mahesh Bandewar Acked-by: Tom Herbert Signed-off-by: David S. Miller --- include/linux/tcp.h | 1 + include/net/sock.h | 12 ++++++++---- 2 files changed, 9 insertions(+), 4 deletions(-) (limited to 'include') diff --git a/include/linux/tcp.h b/include/linux/tcp.h index 48c3696e8645..937b97893d5f 100644 --- a/include/linux/tcp.h +++ b/include/linux/tcp.h @@ -113,6 +113,7 @@ struct tcp_request_sock { struct inet_request_sock req; const struct tcp_request_sock_ops *af_specific; bool tfo_listener; + u32 txhash; u32 rcv_isn; u32 snt_isn; u32 snt_synack; /* synack sent time */ diff --git a/include/net/sock.h b/include/net/sock.h index 7aa78440559a..94dff7f566f5 100644 --- a/include/net/sock.h +++ b/include/net/sock.h @@ -1654,12 +1654,16 @@ static inline void sock_graft(struct sock *sk, struct socket *parent) kuid_t sock_i_uid(struct sock *sk); unsigned long sock_i_ino(struct sock *sk); -static inline void sk_set_txhash(struct sock *sk) +static inline u32 net_tx_rndhash(void) { - sk->sk_txhash = prandom_u32(); + u32 v = prandom_u32(); + + return v ?: 1; +} - if (unlikely(!sk->sk_txhash)) - sk->sk_txhash = 1; +static inline void sk_set_txhash(struct sock *sk) +{ + sk->sk_txhash = net_tx_rndhash(); } static inline void sk_rethink_txhash(struct sock *sk) -- cgit v1.2.3 From 045efa82ff563cd4e656ca1c2e354fa5bf6bbda4 Mon Sep 17 00:00:00 2001 From: Daniel Borkmann Date: Tue, 15 Sep 2015 23:05:42 -0700 Subject: cls_bpf: introduce integrated actions Often cls_bpf classifier is used with single action drop attached. Optimize this use case and let cls_bpf return both classid and action. For backwards compatibility reasons enable this feature under TCA_BPF_FLAG_ACT_DIRECT flag. Then more interesting programs like the following are easier to write: int cls_bpf_prog(struct __sk_buff *skb) { /* classify arp, ip, ipv6 into different traffic classes * and drop all other packets */ switch (skb->protocol) { case htons(ETH_P_ARP): skb->tc_classid = 1; break; case htons(ETH_P_IP): skb->tc_classid = 2; break; case htons(ETH_P_IPV6): skb->tc_classid = 3; break; default: return TC_ACT_SHOT; } return TC_ACT_OK; } Joint work with Daniel Borkmann. Signed-off-by: Daniel Borkmann Signed-off-by: Alexei Starovoitov Signed-off-by: David S. Miller --- include/net/sch_generic.h | 2 +- include/uapi/linux/bpf.h | 1 + include/uapi/linux/pkt_cls.h | 3 +++ 3 files changed, 5 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/net/sch_generic.h b/include/net/sch_generic.h index 444faa89a55f..da61febb9091 100644 --- a/include/net/sch_generic.h +++ b/include/net/sch_generic.h @@ -251,7 +251,7 @@ struct tcf_proto { struct qdisc_skb_cb { unsigned int pkt_len; u16 slave_dev_queue_mapping; - u16 _pad; + u16 tc_classid; #define QDISC_CB_PRIV_LEN 20 unsigned char data[QDISC_CB_PRIV_LEN]; }; diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index 92a48e2d5461..2fbd1c71fa3b 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -293,6 +293,7 @@ struct __sk_buff { __u32 tc_index; __u32 cb[5]; __u32 hash; + __u32 tc_classid; }; struct bpf_tunnel_key { diff --git a/include/uapi/linux/pkt_cls.h b/include/uapi/linux/pkt_cls.h index 4f0d1bc3647d..0a262a83f9d4 100644 --- a/include/uapi/linux/pkt_cls.h +++ b/include/uapi/linux/pkt_cls.h @@ -373,6 +373,8 @@ enum { /* BPF classifier */ +#define TCA_BPF_FLAG_ACT_DIRECT (1 << 0) + enum { TCA_BPF_UNSPEC, TCA_BPF_ACT, @@ -382,6 +384,7 @@ enum { TCA_BPF_OPS, TCA_BPF_FD, TCA_BPF_NAME, + TCA_BPF_FLAGS, __TCA_BPF_MAX, }; -- cgit v1.2.3 From 27b29f63058d26c6c1742f1993338280d5a41dc6 Mon Sep 17 00:00:00 2001 From: Alexei Starovoitov Date: Tue, 15 Sep 2015 23:05:43 -0700 Subject: bpf: add bpf_redirect() helper Existing bpf_clone_redirect() helper clones skb before redirecting it to RX or TX of destination netdev. Introduce bpf_redirect() helper that does that without cloning. Benchmarked with two hosts using 10G ixgbe NICs. One host is doing line rate pktgen. Another host is configured as: $ tc qdisc add dev $dev ingress $ tc filter add dev $dev root pref 10 u32 match u32 0 0 flowid 1:2 \ action bpf run object-file tcbpf1_kern.o section clone_redirect_xmit drop so it receives the packet on $dev and immediately xmits it on $dev + 1 The section 'clone_redirect_xmit' in tcbpf1_kern.o file has the program that does bpf_clone_redirect() and performance is 2.0 Mpps $ tc filter add dev $dev root pref 10 u32 match u32 0 0 flowid 1:2 \ action bpf run object-file tcbpf1_kern.o section redirect_xmit drop which is using bpf_redirect() - 2.4 Mpps and using cls_bpf with integrated actions as: $ tc filter add dev $dev root pref 10 \ bpf run object-file tcbpf1_kern.o section redirect_xmit integ_act classid 1 performance is 2.5 Mpps To summarize: u32+act_bpf using clone_redirect - 2.0 Mpps u32+act_bpf using redirect - 2.4 Mpps cls_bpf using redirect - 2.5 Mpps For comparison linux bridge in this setup is doing 2.1 Mpps and ixgbe rx + drop in ip_rcv - 7.8 Mpps Signed-off-by: Alexei Starovoitov Acked-by: Daniel Borkmann Acked-by: John Fastabend Signed-off-by: David S. Miller --- include/net/sch_generic.h | 1 + include/uapi/linux/bpf.h | 8 ++++++++ include/uapi/linux/pkt_cls.h | 1 + 3 files changed, 10 insertions(+) (limited to 'include') diff --git a/include/net/sch_generic.h b/include/net/sch_generic.h index da61febb9091..4c79ce8c1f92 100644 --- a/include/net/sch_generic.h +++ b/include/net/sch_generic.h @@ -402,6 +402,7 @@ void __qdisc_calculate_pkt_len(struct sk_buff *skb, const struct qdisc_size_table *stab); bool tcf_destroy(struct tcf_proto *tp, bool force); void tcf_destroy_chain(struct tcf_proto __rcu **fl); +int skb_do_redirect(struct sk_buff *); /* Reset all TX qdiscs greater then index of a device. */ static inline void qdisc_reset_all_tx_gt(struct net_device *dev, unsigned int i) diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index 2fbd1c71fa3b..4ec0b5488294 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -272,6 +272,14 @@ enum bpf_func_id { BPF_FUNC_skb_get_tunnel_key, BPF_FUNC_skb_set_tunnel_key, BPF_FUNC_perf_event_read, /* u64 bpf_perf_event_read(&map, index) */ + /** + * bpf_redirect(ifindex, flags) - redirect to another netdev + * @ifindex: ifindex of the net device + * @flags: bit 0 - if set, redirect to ingress instead of egress + * other bits - reserved + * Return: TC_ACT_REDIRECT + */ + BPF_FUNC_redirect, __BPF_FUNC_MAX_ID, }; diff --git a/include/uapi/linux/pkt_cls.h b/include/uapi/linux/pkt_cls.h index 0a262a83f9d4..439873775d49 100644 --- a/include/uapi/linux/pkt_cls.h +++ b/include/uapi/linux/pkt_cls.h @@ -87,6 +87,7 @@ enum { #define TC_ACT_STOLEN 4 #define TC_ACT_QUEUED 5 #define TC_ACT_REPEAT 6 +#define TC_ACT_REDIRECT 7 #define TC_ACT_JUMP 0x10000000 /* Action type identifiers*/ -- cgit v1.2.3 From e781b7f7fcc141d69f63d4eef70d249549dfaeda Mon Sep 17 00:00:00 2001 From: Szymon Janc Date: Wed, 16 Sep 2015 20:21:53 +0200 Subject: Bluetooth: Add BT_ERR_RATELIMITED This patch adds ratelimited version of the BT_ERR macro. Signed-off-by: Szymon Janc Signed-off-by: Marcel Holtmann --- include/net/bluetooth/bluetooth.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include') diff --git a/include/net/bluetooth/bluetooth.h b/include/net/bluetooth/bluetooth.h index fcf2ae7dbfa0..f5ade8573393 100644 --- a/include/net/bluetooth/bluetooth.h +++ b/include/net/bluetooth/bluetooth.h @@ -123,11 +123,15 @@ __printf(1, 2) void bt_info(const char *fmt, ...); __printf(1, 2) void bt_err(const char *fmt, ...); +__printf(1, 2) +void bt_err_ratelimited(const char *fmt, ...); #define BT_INFO(fmt, ...) bt_info(fmt "\n", ##__VA_ARGS__) #define BT_ERR(fmt, ...) bt_err(fmt "\n", ##__VA_ARGS__) #define BT_DBG(fmt, ...) pr_debug(fmt "\n", ##__VA_ARGS__) +#define BT_ERR_RATELIMITED(fmt, ...) bt_err_ratelimited(fmt "\n", ##__VA_ARGS__) + #define bt_dev_info(hdev, fmt, ...) \ BT_INFO("%s: " fmt, (hdev)->name, ##__VA_ARGS__) #define bt_dev_err(hdev, fmt, ...) \ -- cgit v1.2.3 From 97b59c3a91d5ee4777658ff2136d1fdf13bd23d0 Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Fri, 18 Sep 2015 14:32:54 -0500 Subject: netfilter: ebtables: Simplify the arguments to ebt_do_table Nearly everything thing of interest to ebt_do_table is already present in nf_hook_state. Simplify ebt_do_table by just passing in the skb, nf_hook_state, and the table. This make the code easier to read and maintenance easier. To support this create an nf_hook_state on the stack in ebt_broute (the only caller without a nf_hook_state already available). This new nf_hook_state adds no new computations to ebt_broute, but does use a few more bytes of stack. Signed-off-by: "Eric W. Biederman" Signed-off-by: Pablo Neira Ayuso --- include/linux/netfilter_bridge/ebtables.h | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/include/linux/netfilter_bridge/ebtables.h b/include/linux/netfilter_bridge/ebtables.h index 8ca6d6464ea3..2ea517c7c6b9 100644 --- a/include/linux/netfilter_bridge/ebtables.h +++ b/include/linux/netfilter_bridge/ebtables.h @@ -111,9 +111,9 @@ struct ebt_table { extern struct ebt_table *ebt_register_table(struct net *net, const struct ebt_table *table); extern void ebt_unregister_table(struct net *net, struct ebt_table *table); -extern unsigned int ebt_do_table(unsigned int hook, struct sk_buff *skb, - const struct net_device *in, const struct net_device *out, - struct ebt_table *table); +extern unsigned int ebt_do_table(struct sk_buff *skb, + const struct nf_hook_state *state, + struct ebt_table *table); /* Used in the kernel match() functions */ #define FWINV(bool,invflg) ((bool) ^ !!(info->invflags & invflg)) -- cgit v1.2.3 From 6cb8ff3f1a535b1d8eb5ea318932513d08eb3da7 Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Fri, 18 Sep 2015 14:32:55 -0500 Subject: inet netfilter: Remove hook from ip6t_do_table, arp_do_table, ipt_do_table The values of ops->hooknum and state->hook are guaraneted to be equal making the hook argument to ip6t_do_table, arp_do_table, and ipt_do_table is unnecessary. Remove the unnecessary hook argument. In the callers use state->hook instead of ops->hooknum for clarity and to reduce the number of cachelines the callers touch. Signed-off-by: "Eric W. Biederman" Signed-off-by: Pablo Neira Ayuso --- include/linux/netfilter_arp/arp_tables.h | 1 - include/linux/netfilter_ipv4/ip_tables.h | 1 - include/linux/netfilter_ipv6/ip6_tables.h | 1 - 3 files changed, 3 deletions(-) (limited to 'include') diff --git a/include/linux/netfilter_arp/arp_tables.h b/include/linux/netfilter_arp/arp_tables.h index c22a7fb8d0df..6f074db2f23d 100644 --- a/include/linux/netfilter_arp/arp_tables.h +++ b/include/linux/netfilter_arp/arp_tables.h @@ -53,7 +53,6 @@ extern struct xt_table *arpt_register_table(struct net *net, const struct arpt_replace *repl); extern void arpt_unregister_table(struct xt_table *table); extern unsigned int arpt_do_table(struct sk_buff *skb, - unsigned int hook, const struct nf_hook_state *state, struct xt_table *table); diff --git a/include/linux/netfilter_ipv4/ip_tables.h b/include/linux/netfilter_ipv4/ip_tables.h index 4073510da485..aa598f942c01 100644 --- a/include/linux/netfilter_ipv4/ip_tables.h +++ b/include/linux/netfilter_ipv4/ip_tables.h @@ -64,7 +64,6 @@ struct ipt_error { extern void *ipt_alloc_initial_table(const struct xt_table *); extern unsigned int ipt_do_table(struct sk_buff *skb, - unsigned int hook, const struct nf_hook_state *state, struct xt_table *table); diff --git a/include/linux/netfilter_ipv6/ip6_tables.h b/include/linux/netfilter_ipv6/ip6_tables.h index b40d2b635778..0f76e5c674f9 100644 --- a/include/linux/netfilter_ipv6/ip6_tables.h +++ b/include/linux/netfilter_ipv6/ip6_tables.h @@ -30,7 +30,6 @@ extern struct xt_table *ip6t_register_table(struct net *net, const struct ip6t_replace *repl); extern void ip6t_unregister_table(struct net *net, struct xt_table *table); extern unsigned int ip6t_do_table(struct sk_buff *skb, - unsigned int hook, const struct nf_hook_state *state, struct xt_table *table); -- cgit v1.2.3 From 6aa187f21ca2d8ade791f01fd8fab908b1f27673 Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Fri, 18 Sep 2015 14:32:57 -0500 Subject: netfilter: nf_tables: kill nft_pktinfo.ops - Add nft_pktinfo.pf to replace ops->pf - Add nft_pktinfo.hook to replace ops->hooknum This simplifies the code, makes it more readable, and likely reduces cache line misses. Maintainability is enhanced as the details of nft_hook_ops are of no concern to the recpients of nft_pktinfo. Signed-off-by: "Eric W. Biederman" Signed-off-by: Pablo Neira Ayuso --- include/net/netfilter/nf_tables.h | 9 ++++----- include/net/netfilter/nf_tables_ipv4.h | 3 +-- include/net/netfilter/nf_tables_ipv6.h | 3 +-- 3 files changed, 6 insertions(+), 9 deletions(-) (limited to 'include') diff --git a/include/net/netfilter/nf_tables.h b/include/net/netfilter/nf_tables.h index aa8bee72c9d3..c0899f97ff8d 100644 --- a/include/net/netfilter/nf_tables.h +++ b/include/net/netfilter/nf_tables.h @@ -16,7 +16,8 @@ struct nft_pktinfo { struct sk_buff *skb; const struct net_device *in; const struct net_device *out; - const struct nf_hook_ops *ops; + u8 pf; + u8 hook; u8 nhoff; u8 thoff; u8 tprot; @@ -25,16 +26,14 @@ struct nft_pktinfo { }; static inline void nft_set_pktinfo(struct nft_pktinfo *pkt, - const struct nf_hook_ops *ops, struct sk_buff *skb, const struct nf_hook_state *state) { pkt->skb = skb; pkt->in = pkt->xt.in = state->in; pkt->out = pkt->xt.out = state->out; - pkt->ops = ops; - pkt->xt.hooknum = ops->hooknum; - pkt->xt.family = ops->pf; + pkt->hook = pkt->xt.hooknum = state->hook; + pkt->pf = pkt->xt.family = state->pf; } /** diff --git a/include/net/netfilter/nf_tables_ipv4.h b/include/net/netfilter/nf_tables_ipv4.h index 2df7f96902ee..ca6ef6bf775e 100644 --- a/include/net/netfilter/nf_tables_ipv4.h +++ b/include/net/netfilter/nf_tables_ipv4.h @@ -6,13 +6,12 @@ static inline void nft_set_pktinfo_ipv4(struct nft_pktinfo *pkt, - const struct nf_hook_ops *ops, struct sk_buff *skb, const struct nf_hook_state *state) { struct iphdr *ip; - nft_set_pktinfo(pkt, ops, skb, state); + nft_set_pktinfo(pkt, skb, state); ip = ip_hdr(pkt->skb); pkt->tprot = ip->protocol; diff --git a/include/net/netfilter/nf_tables_ipv6.h b/include/net/netfilter/nf_tables_ipv6.h index 97db2e3a5e65..8ad39a6a5fe1 100644 --- a/include/net/netfilter/nf_tables_ipv6.h +++ b/include/net/netfilter/nf_tables_ipv6.h @@ -6,14 +6,13 @@ static inline int nft_set_pktinfo_ipv6(struct nft_pktinfo *pkt, - const struct nf_hook_ops *ops, struct sk_buff *skb, const struct nf_hook_state *state) { int protohdr, thoff = 0; unsigned short frag_off; - nft_set_pktinfo(pkt, ops, skb, state); + nft_set_pktinfo(pkt, skb, state); protohdr = ipv6_find_hdr(pkt->skb, &thoff, -1, &frag_off, NULL); /* If malformed, drop it */ -- cgit v1.2.3 From 156c196f6038610770588a708b9e0f7df2ead74a Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Fri, 18 Sep 2015 14:32:58 -0500 Subject: netfilter: x_tables: Pass struct net in xt_action_param As xt_action_param lives on the stack this does not bloat any persistent data structures. This is a first step in making netfilter code that needs to know which network namespace it is executing in simpler. Signed-off-by: "Eric W. Biederman" Signed-off-by: Pablo Neira Ayuso --- include/linux/netfilter/x_tables.h | 3 ++- include/net/netfilter/nf_tables.h | 1 + 2 files changed, 3 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/netfilter/x_tables.h b/include/linux/netfilter/x_tables.h index b006b719183f..c5577410c25d 100644 --- a/include/linux/netfilter/x_tables.h +++ b/include/linux/netfilter/x_tables.h @@ -13,6 +13,7 @@ * @target: the target extension * @matchinfo: per-match data * @targetinfo: per-target data + * @net network namespace through which the action was invoked * @in: input netdevice * @out: output netdevice * @fragoff: packet is a fragment, this is the data offset @@ -24,7 +25,6 @@ * Fields written to by extensions: * * @hotdrop: drop packet if we had inspection problems - * Network namespace obtainable using dev_net(in/out) */ struct xt_action_param { union { @@ -34,6 +34,7 @@ struct xt_action_param { union { const void *matchinfo, *targinfo; }; + struct net *net; const struct net_device *in, *out; int fragoff; unsigned int thoff; diff --git a/include/net/netfilter/nf_tables.h b/include/net/netfilter/nf_tables.h index c0899f97ff8d..c0516529e8a0 100644 --- a/include/net/netfilter/nf_tables.h +++ b/include/net/netfilter/nf_tables.h @@ -30,6 +30,7 @@ static inline void nft_set_pktinfo(struct nft_pktinfo *pkt, const struct nf_hook_state *state) { pkt->skb = skb; + pkt->xt.net = state->net; pkt->in = pkt->xt.in = state->in; pkt->out = pkt->xt.out = state->out; pkt->hook = pkt->xt.hooknum = state->hook; -- cgit v1.2.3 From 46448d0093ba18a212e314fd9ea029e740baa476 Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Fri, 18 Sep 2015 14:33:00 -0500 Subject: netfilter: nf_tables: Pass struct net in nft_pktinfo nft_pktinfo is passed on the stack so this does not bloat any in core data structures. By centrally computing this information this makes maintence of the code simpler, and understading of the code easier. Signed-off-by: "Eric W. Biederman" Signed-off-by: Pablo Neira Ayuso --- include/net/netfilter/nf_tables.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/net/netfilter/nf_tables.h b/include/net/netfilter/nf_tables.h index c0516529e8a0..42e239e55aa3 100644 --- a/include/net/netfilter/nf_tables.h +++ b/include/net/netfilter/nf_tables.h @@ -14,6 +14,7 @@ struct nft_pktinfo { struct sk_buff *skb; + struct net *net; const struct net_device *in; const struct net_device *out; u8 pf; @@ -30,7 +31,7 @@ static inline void nft_set_pktinfo(struct nft_pktinfo *pkt, const struct nf_hook_state *state) { pkt->skb = skb; - pkt->xt.net = state->net; + pkt->net = pkt->xt.net = state->net; pkt->in = pkt->xt.in = state->in; pkt->out = pkt->xt.out = state->out; pkt->hook = pkt->xt.hooknum = state->hook; -- cgit v1.2.3 From 206e8c00752fbe9cc463184236ac64b2a532cda5 Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Fri, 18 Sep 2015 14:33:02 -0500 Subject: netfilter: Pass net to nf_dup_ipv4 and nf_dup_ipv6 This allows them to stop guessing the network namespace with pick_net. Signed-off-by: "Eric W. Biederman" Signed-off-by: Pablo Neira Ayuso --- include/net/netfilter/ipv4/nf_dup_ipv4.h | 2 +- include/net/netfilter/ipv6/nf_dup_ipv6.h | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/net/netfilter/ipv4/nf_dup_ipv4.h b/include/net/netfilter/ipv4/nf_dup_ipv4.h index 42008f10dfc4..0a14733e8b82 100644 --- a/include/net/netfilter/ipv4/nf_dup_ipv4.h +++ b/include/net/netfilter/ipv4/nf_dup_ipv4.h @@ -1,7 +1,7 @@ #ifndef _NF_DUP_IPV4_H_ #define _NF_DUP_IPV4_H_ -void nf_dup_ipv4(struct sk_buff *skb, unsigned int hooknum, +void nf_dup_ipv4(struct net *net, struct sk_buff *skb, unsigned int hooknum, const struct in_addr *gw, int oif); #endif /* _NF_DUP_IPV4_H_ */ diff --git a/include/net/netfilter/ipv6/nf_dup_ipv6.h b/include/net/netfilter/ipv6/nf_dup_ipv6.h index ed6bd66fa5a0..fa6237b382a3 100644 --- a/include/net/netfilter/ipv6/nf_dup_ipv6.h +++ b/include/net/netfilter/ipv6/nf_dup_ipv6.h @@ -1,7 +1,7 @@ #ifndef _NF_DUP_IPV6_H_ #define _NF_DUP_IPV6_H_ -void nf_dup_ipv6(struct sk_buff *skb, unsigned int hooknum, +void nf_dup_ipv6(struct net *net, struct sk_buff *skb, unsigned int hooknum, const struct in6_addr *gw, int oif); #endif /* _NF_DUP_IPV6_H_ */ -- cgit v1.2.3 From a4ffe319ae72034e3f3332698a2fd83b6f063b18 Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Fri, 18 Sep 2015 14:33:03 -0500 Subject: act_connmark: Remember the struct net instead of guessing it. Stop guessing the struct net instead of remember it. Guessing is just silly and will be problematic in the future when I implement routes between network namespaces. Signed-off-by: "Eric W. Biederman" Signed-off-by: Pablo Neira Ayuso --- include/net/tc_act/tc_connmark.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/net/tc_act/tc_connmark.h b/include/net/tc_act/tc_connmark.h index 5c1104c2e24f..02caa406611b 100644 --- a/include/net/tc_act/tc_connmark.h +++ b/include/net/tc_act/tc_connmark.h @@ -5,6 +5,7 @@ struct tcf_connmark_info { struct tcf_common common; + struct net *net; u16 zone; }; -- cgit v1.2.3 From a31f1adc0948930fba9ab5a111ccd735a5d864c6 Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Fri, 18 Sep 2015 14:33:04 -0500 Subject: netfilter: nf_conntrack: Add a struct net parameter to l4_pkt_to_tuple As gre does not have the srckey in the packet gre_pkt_to_tuple needs to perform a lookup in it's per network namespace tables. Pass in the proper network namespace to all pkt_to_tuple implementations to ensure gre (and any similar protocols) can get this right. Signed-off-by: "Eric W. Biederman" Signed-off-by: Pablo Neira Ayuso --- include/net/netfilter/nf_conntrack.h | 3 ++- include/net/netfilter/nf_conntrack_core.h | 1 + include/net/netfilter/nf_conntrack_l4proto.h | 2 +- 3 files changed, 4 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/net/netfilter/nf_conntrack.h b/include/net/netfilter/nf_conntrack.h index e8ad46834df8..d642f68a7c73 100644 --- a/include/net/netfilter/nf_conntrack.h +++ b/include/net/netfilter/nf_conntrack.h @@ -191,7 +191,8 @@ int nf_conntrack_hash_check_insert(struct nf_conn *ct); bool nf_ct_delete(struct nf_conn *ct, u32 pid, int report); bool nf_ct_get_tuplepr(const struct sk_buff *skb, unsigned int nhoff, - u_int16_t l3num, struct nf_conntrack_tuple *tuple); + u_int16_t l3num, struct net *net, + struct nf_conntrack_tuple *tuple); bool nf_ct_invert_tuplepr(struct nf_conntrack_tuple *inverse, const struct nf_conntrack_tuple *orig); diff --git a/include/net/netfilter/nf_conntrack_core.h b/include/net/netfilter/nf_conntrack_core.h index c03f9c42b3cd..788ef58a66b9 100644 --- a/include/net/netfilter/nf_conntrack_core.h +++ b/include/net/netfilter/nf_conntrack_core.h @@ -41,6 +41,7 @@ void nf_conntrack_cleanup_end(void); bool nf_ct_get_tuple(const struct sk_buff *skb, unsigned int nhoff, unsigned int dataoff, u_int16_t l3num, u_int8_t protonum, + struct net *net, struct nf_conntrack_tuple *tuple, const struct nf_conntrack_l3proto *l3proto, const struct nf_conntrack_l4proto *l4proto); diff --git a/include/net/netfilter/nf_conntrack_l4proto.h b/include/net/netfilter/nf_conntrack_l4proto.h index 1f7061313d54..956d8a6ac069 100644 --- a/include/net/netfilter/nf_conntrack_l4proto.h +++ b/include/net/netfilter/nf_conntrack_l4proto.h @@ -26,7 +26,7 @@ struct nf_conntrack_l4proto { /* Try to fill in the third arg: dataoff is offset past network protocol hdr. Return true if possible. */ bool (*pkt_to_tuple)(const struct sk_buff *skb, unsigned int dataoff, - struct nf_conntrack_tuple *tuple); + struct net *net, struct nf_conntrack_tuple *tuple); /* Invert the per-proto part of the tuple: ie. turn xmit into reply. * Some packets can't be inverted: return 0 in that case. -- cgit v1.2.3 From 06198b34a3e09e06d9aecaa3727e0d37206cea77 Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Fri, 18 Sep 2015 14:33:06 -0500 Subject: netfilter: Pass priv instead of nf_hook_ops to netfilter hooks Only pass the void *priv parameter out of the nf_hook_ops. That is all any of the functions are interested now, and by limiting what is passed it becomes simpler to change implementation details. Signed-off-by: "Eric W. Biederman" Signed-off-by: Pablo Neira Ayuso --- include/linux/netfilter.h | 2 +- include/net/netfilter/br_netfilter.h | 2 +- include/net/netfilter/nf_nat_l3proto.h | 32 ++++++++++++++++---------------- include/net/netfilter/nf_tables.h | 3 +-- 4 files changed, 19 insertions(+), 20 deletions(-) (limited to 'include') diff --git a/include/linux/netfilter.h b/include/linux/netfilter.h index 0b4d4560f33d..987c74cd523c 100644 --- a/include/linux/netfilter.h +++ b/include/linux/netfilter.h @@ -80,7 +80,7 @@ static inline void nf_hook_state_init(struct nf_hook_state *p, p->okfn = okfn; } -typedef unsigned int nf_hookfn(const struct nf_hook_ops *ops, +typedef unsigned int nf_hookfn(void *priv, struct sk_buff *skb, const struct nf_hook_state *state); diff --git a/include/net/netfilter/br_netfilter.h b/include/net/netfilter/br_netfilter.h index 8fe266504900..c93c75fa41ad 100644 --- a/include/net/netfilter/br_netfilter.h +++ b/include/net/netfilter/br_netfilter.h @@ -46,7 +46,7 @@ void br_netfilter_enable(void); #if IS_ENABLED(CONFIG_IPV6) int br_validate_ipv6(struct sk_buff *skb); -unsigned int br_nf_pre_routing_ipv6(const struct nf_hook_ops *ops, +unsigned int br_nf_pre_routing_ipv6(void *priv, struct sk_buff *skb, const struct nf_hook_state *state); #else diff --git a/include/net/netfilter/nf_nat_l3proto.h b/include/net/netfilter/nf_nat_l3proto.h index a3127325f624..aef3e5fc9fd9 100644 --- a/include/net/netfilter/nf_nat_l3proto.h +++ b/include/net/netfilter/nf_nat_l3proto.h @@ -43,31 +43,31 @@ int nf_nat_icmp_reply_translation(struct sk_buff *skb, struct nf_conn *ct, enum ip_conntrack_info ctinfo, unsigned int hooknum); -unsigned int nf_nat_ipv4_in(const struct nf_hook_ops *ops, struct sk_buff *skb, +unsigned int nf_nat_ipv4_in(void *priv, struct sk_buff *skb, const struct nf_hook_state *state, - unsigned int (*do_chain)(const struct nf_hook_ops *ops, + unsigned int (*do_chain)(void *priv, struct sk_buff *skb, const struct nf_hook_state *state, struct nf_conn *ct)); -unsigned int nf_nat_ipv4_out(const struct nf_hook_ops *ops, struct sk_buff *skb, +unsigned int nf_nat_ipv4_out(void *priv, struct sk_buff *skb, const struct nf_hook_state *state, - unsigned int (*do_chain)(const struct nf_hook_ops *ops, + unsigned int (*do_chain)(void *priv, struct sk_buff *skb, const struct nf_hook_state *state, struct nf_conn *ct)); -unsigned int nf_nat_ipv4_local_fn(const struct nf_hook_ops *ops, +unsigned int nf_nat_ipv4_local_fn(void *priv, struct sk_buff *skb, const struct nf_hook_state *state, - unsigned int (*do_chain)(const struct nf_hook_ops *ops, + unsigned int (*do_chain)(void *priv, struct sk_buff *skb, const struct nf_hook_state *state, struct nf_conn *ct)); -unsigned int nf_nat_ipv4_fn(const struct nf_hook_ops *ops, struct sk_buff *skb, +unsigned int nf_nat_ipv4_fn(void *priv, struct sk_buff *skb, const struct nf_hook_state *state, - unsigned int (*do_chain)(const struct nf_hook_ops *ops, + unsigned int (*do_chain)(void *priv, struct sk_buff *skb, const struct nf_hook_state *state, struct nf_conn *ct)); @@ -76,31 +76,31 @@ int nf_nat_icmpv6_reply_translation(struct sk_buff *skb, struct nf_conn *ct, enum ip_conntrack_info ctinfo, unsigned int hooknum, unsigned int hdrlen); -unsigned int nf_nat_ipv6_in(const struct nf_hook_ops *ops, struct sk_buff *skb, +unsigned int nf_nat_ipv6_in(void *priv, struct sk_buff *skb, const struct nf_hook_state *state, - unsigned int (*do_chain)(const struct nf_hook_ops *ops, + unsigned int (*do_chain)(void *priv, struct sk_buff *skb, const struct nf_hook_state *state, struct nf_conn *ct)); -unsigned int nf_nat_ipv6_out(const struct nf_hook_ops *ops, struct sk_buff *skb, +unsigned int nf_nat_ipv6_out(void *priv, struct sk_buff *skb, const struct nf_hook_state *state, - unsigned int (*do_chain)(const struct nf_hook_ops *ops, + unsigned int (*do_chain)(void *priv, struct sk_buff *skb, const struct nf_hook_state *state, struct nf_conn *ct)); -unsigned int nf_nat_ipv6_local_fn(const struct nf_hook_ops *ops, +unsigned int nf_nat_ipv6_local_fn(void *priv, struct sk_buff *skb, const struct nf_hook_state *state, - unsigned int (*do_chain)(const struct nf_hook_ops *ops, + unsigned int (*do_chain)(void *priv, struct sk_buff *skb, const struct nf_hook_state *state, struct nf_conn *ct)); -unsigned int nf_nat_ipv6_fn(const struct nf_hook_ops *ops, struct sk_buff *skb, +unsigned int nf_nat_ipv6_fn(void *priv, struct sk_buff *skb, const struct nf_hook_state *state, - unsigned int (*do_chain)(const struct nf_hook_ops *ops, + unsigned int (*do_chain)(void *priv, struct sk_buff *skb, const struct nf_hook_state *state, struct nf_conn *ct)); diff --git a/include/net/netfilter/nf_tables.h b/include/net/netfilter/nf_tables.h index 42e239e55aa3..c9149cc0a02d 100644 --- a/include/net/netfilter/nf_tables.h +++ b/include/net/netfilter/nf_tables.h @@ -816,8 +816,7 @@ int nft_register_basechain(struct nft_base_chain *basechain, void nft_unregister_basechain(struct nft_base_chain *basechain, unsigned int hook_nops); -unsigned int nft_do_chain(struct nft_pktinfo *pkt, - const struct nf_hook_ops *ops); +unsigned int nft_do_chain(struct nft_pktinfo *pkt, void *priv); /** * struct nft_table - nf_tables table -- cgit v1.2.3 From c7af6483b9f7f3eaba01b2e62d3d8a70cd89bdaf Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Fri, 18 Sep 2015 14:33:07 -0500 Subject: netfilter: Pass net into nf_xfrm_me_harder Instead of calling dev_net on a likley looking network device pass state->net into nf_xfrm_me_harder. Signed-off-by: "Eric W. Biederman" Signed-off-by: Pablo Neira Ayuso --- include/net/netfilter/nf_nat_core.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/net/netfilter/nf_nat_core.h b/include/net/netfilter/nf_nat_core.h index fbfd1ba4254e..186c54138f35 100644 --- a/include/net/netfilter/nf_nat_core.h +++ b/include/net/netfilter/nf_nat_core.h @@ -10,7 +10,7 @@ unsigned int nf_nat_packet(struct nf_conn *ct, enum ip_conntrack_info ctinfo, unsigned int hooknum, struct sk_buff *skb); -int nf_xfrm_me_harder(struct sk_buff *skb, unsigned int family); +int nf_xfrm_me_harder(struct net *net, struct sk_buff *skb, unsigned int family); static inline int nf_nat_initialized(struct nf_conn *ct, enum nf_nat_manip_type manip) -- cgit v1.2.3 From 2785968cd122b22b289db565b7438f2200984044 Mon Sep 17 00:00:00 2001 From: Marc Kleine-Budde Date: Sat, 9 May 2015 17:47:52 +0200 Subject: can: headers: make header files self contained This patch adds the missing #include-s to the dev.h and led.h, so that they can be used without including further header files. Signed-off-by: Marc Kleine-Budde --- include/linux/can/dev.h | 3 ++- include/linux/can/led.h | 1 + 2 files changed, 3 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/can/dev.h b/include/linux/can/dev.h index c3a9c8fc60fa..56dcadd83716 100644 --- a/include/linux/can/dev.h +++ b/include/linux/can/dev.h @@ -14,9 +14,10 @@ #define _CAN_DEV_H #include -#include #include #include +#include +#include /* * CAN mode diff --git a/include/linux/can/led.h b/include/linux/can/led.h index 146de4506d21..2746f7c2f87d 100644 --- a/include/linux/can/led.h +++ b/include/linux/can/led.h @@ -11,6 +11,7 @@ #include #include +#include enum can_led_event { CAN_LED_EVENT_OPEN, -- cgit v1.2.3 From 91e60eb60bdf078fc58b8d2fd1ac12f3c09bb893 Mon Sep 17 00:00:00 2001 From: Ursula Braun Date: Fri, 18 Sep 2015 16:06:52 +0200 Subject: s390/iucv: do not use arrays as argument The iucv code uses arrays as arguments. Even though this does not really cause a problem, it could be misleading, since the compiler turns array arguments into just a pointer argument. To be more precise this patch changes the array arguments into pointers. Signed-off-by: Ursula Braun Signed-off-by: David S. Miller --- include/net/iucv/iucv.h | 20 ++++++++++---------- 1 file changed, 10 insertions(+), 10 deletions(-) (limited to 'include') diff --git a/include/net/iucv/iucv.h b/include/net/iucv/iucv.h index 0894ced31957..b867b0cf79e8 100644 --- a/include/net/iucv/iucv.h +++ b/include/net/iucv/iucv.h @@ -141,14 +141,14 @@ struct iucv_handler { * called is the order of the registration of the iucv handlers * to the base code. */ - int (*path_pending)(struct iucv_path *, u8 ipvmid[8], u8 ipuser[16]); + int (*path_pending)(struct iucv_path *, u8 *ipvmid, u8 *ipuser); /* * The path_complete function is called after an iucv interrupt * type 0x02 has been received for a path that has been established * for this handler with iucv_path_connect and got accepted by the * peer with iucv_path_accept. */ - void (*path_complete)(struct iucv_path *, u8 ipuser[16]); + void (*path_complete)(struct iucv_path *, u8 *ipuser); /* * The path_severed function is called after an iucv interrupt * type 0x03 has been received. The communication peer shutdown @@ -156,20 +156,20 @@ struct iucv_handler { * remaining messages can be received until a iucv_path_sever * shuts down the other end of the path as well. */ - void (*path_severed)(struct iucv_path *, u8 ipuser[16]); + void (*path_severed)(struct iucv_path *, u8 *ipuser); /* * The path_quiesced function is called after an icuv interrupt * type 0x04 has been received. The communication peer has quiesced * the path. Delivery of messages is stopped until iucv_path_resume * has been called. */ - void (*path_quiesced)(struct iucv_path *, u8 ipuser[16]); + void (*path_quiesced)(struct iucv_path *, u8 *ipuser); /* * The path_resumed function is called after an icuv interrupt * type 0x05 has been received. The communication peer has resumed * the path. */ - void (*path_resumed)(struct iucv_path *, u8 ipuser[16]); + void (*path_resumed)(struct iucv_path *, u8 *ipuser); /* * The message_pending function is called after an icuv interrupt * type 0x06 or type 0x07 has been received. A new message is @@ -256,7 +256,7 @@ static inline void iucv_path_free(struct iucv_path *path) * Returns the result of the CP IUCV call. */ int iucv_path_accept(struct iucv_path *path, struct iucv_handler *handler, - u8 userdata[16], void *private); + u8 *userdata, void *private); /** * iucv_path_connect @@ -274,7 +274,7 @@ int iucv_path_accept(struct iucv_path *path, struct iucv_handler *handler, * Returns the result of the CP IUCV call. */ int iucv_path_connect(struct iucv_path *path, struct iucv_handler *handler, - u8 userid[8], u8 system[8], u8 userdata[16], + u8 *userid, u8 *system, u8 *userdata, void *private); /** @@ -287,7 +287,7 @@ int iucv_path_connect(struct iucv_path *path, struct iucv_handler *handler, * * Returns the result from the CP IUCV call. */ -int iucv_path_quiesce(struct iucv_path *path, u8 userdata[16]); +int iucv_path_quiesce(struct iucv_path *path, u8 *userdata); /** * iucv_path_resume: @@ -299,7 +299,7 @@ int iucv_path_quiesce(struct iucv_path *path, u8 userdata[16]); * * Returns the result from the CP IUCV call. */ -int iucv_path_resume(struct iucv_path *path, u8 userdata[16]); +int iucv_path_resume(struct iucv_path *path, u8 *userdata); /** * iucv_path_sever @@ -310,7 +310,7 @@ int iucv_path_resume(struct iucv_path *path, u8 userdata[16]); * * Returns the result from the CP IUCV call. */ -int iucv_path_sever(struct iucv_path *path, u8 userdata[16]); +int iucv_path_sever(struct iucv_path *path, u8 *userdata); /** * iucv_message_purge -- cgit v1.2.3 From 0f1c28ae74bb1a34d36fca2db5161611d58b3148 Mon Sep 17 00:00:00 2001 From: Yuchung Cheng Date: Fri, 18 Sep 2015 11:36:14 -0700 Subject: tcp: usec resolution SYN/ACK RTT Currently SYN/ACK RTT is measured in jiffies. For LAN the SYN/ACK RTT is often measured as 0ms or sometimes 1ms, which would affect RTT estimation and min RTT samping used by some congestion control. This patch improves SYN/ACK RTT to be usec resolution if platform supports it. While the timestamping of SYN/ACK is done in request sock, the RTT measurement is carefully arranged to avoid storing another u64 timestamp in tcp_sock. For regular handshake w/o SYNACK retransmission, the RTT is sampled right after the child socket is created and right before the request sock is released (tcp_check_req() in tcp_minisocks.c) For Fast Open the child socket is already created when SYN/ACK was sent, the RTT is sampled in tcp_rcv_state_process() after processing the final ACK an right before the request socket is released. If the SYN/ACK was retransmistted or SYN-cookie was used, we rely on TCP timestamps to measure the RTT. The sample is taken at the same place in tcp_rcv_state_process() after the timestamp values are validated in tcp_validate_incoming(). Note that we do not store TS echo value in request_sock for SYN-cookies, because the value is already stored in tp->rx_opt used by tcp_ack_update_rtt(). One side benefit is that the RTT measurement now happens before initializing congestion control (of the passive side). Therefore the congestion control can use the SYN/ACK RTT. Signed-off-by: Yuchung Cheng Signed-off-by: Neal Cardwell Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- include/linux/tcp.h | 2 +- include/net/tcp.h | 1 + 2 files changed, 2 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/tcp.h b/include/linux/tcp.h index 937b97893d5f..fcb573be75d9 100644 --- a/include/linux/tcp.h +++ b/include/linux/tcp.h @@ -112,11 +112,11 @@ struct tcp_request_sock_ops; struct tcp_request_sock { struct inet_request_sock req; const struct tcp_request_sock_ops *af_specific; + struct skb_mstamp snt_synack; /* first SYNACK sent time */ bool tfo_listener; u32 txhash; u32 rcv_isn; u32 snt_isn; - u32 snt_synack; /* synack sent time */ u32 last_oow_ack_time; /* last SYNACK */ u32 rcv_nxt; /* the ack # by SYNACK. For * FastOpen it's the seq# diff --git a/include/net/tcp.h b/include/net/tcp.h index 0cab28cd43a9..5cf9672c13e2 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -565,6 +565,7 @@ bool tcp_schedule_loss_probe(struct sock *sk); /* tcp_input.c */ void tcp_resume_early_retransmit(struct sock *sk); void tcp_rearm_rto(struct sock *sk); +void tcp_synack_rtt_meas(struct sock *sk, struct request_sock *req); void tcp_reset(struct sock *sk); /* tcp_timer.c */ -- cgit v1.2.3 From a1da67b8117ddbe88c770b48b5b1527393b8c9c0 Mon Sep 17 00:00:00 2001 From: Alexander Aring Date: Fri, 18 Sep 2015 11:30:41 +0200 Subject: ieee802154: header_ops: fix frame control setting Sometimes upper-layer protocols wants to generate a new mac header by filling "struct ieee802154_hdr" only. These upper-layers sets for the address settings the source and dest fields, but not the fc fields for indicate the source and dest address mode. This patch changes the "ieee802154_hdr_push" function so the fc address fields are set according the source and dest fields of "struct ieee802154_hdr". Signed-off-by: Alexander Aring Signed-off-by: Marcel Holtmann --- include/net/ieee802154_netdev.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/net/ieee802154_netdev.h b/include/net/ieee802154_netdev.h index 2c10a9f0c6d9..95a71bc113b3 100644 --- a/include/net/ieee802154_netdev.h +++ b/include/net/ieee802154_netdev.h @@ -99,7 +99,7 @@ struct ieee802154_hdr { * hdr->fc will be ignored. this includes the INTRA_PAN bit and the frame * version, if SECEN is set. */ -int ieee802154_hdr_push(struct sk_buff *skb, const struct ieee802154_hdr *hdr); +int ieee802154_hdr_push(struct sk_buff *skb, struct ieee802154_hdr *hdr); /* pulls the entire 802.15.4 header off of the skb, including the security * header, and performs pan id decompression -- cgit v1.2.3 From 838b83d63d2909f9136f3030dc4fffa8230c31da Mon Sep 17 00:00:00 2001 From: Alexander Aring Date: Fri, 18 Sep 2015 11:30:42 +0200 Subject: ieee802154: introduce wpan_dev_header_ops The current header_ops callback structure of net device are used mostly from 802.15.4 upper-layers. Because this callback structure is a very generic one, which is also used by e.g. DGRAM AF_PACKET sockets, we can't make this callback structure 802.15.4 specific which is currently is. I saw the smallest "constraint" for calling this callback with dev_hard_header/dev_parse_header by AF_PACKET which assign a 8 byte array for address void pointers. Currently 802.15.4 specific protocols like af802154 and 6LoWPAN will assign the "struct ieee802154_addr" as these parameters which is greater than 8 bytes. The current callback implementation for header_ops.create assumes always a complete "struct ieee802154_addr" which AF_PACKET can't never handled and is greater than 8 bytes. For that reason we introduce now a "generic" create/parse header_ops callback which allows handling with intra-pan extended addresses only. This allows a small use-case with AF_PACKET to send "somehow" a valid dataframe over DGRAM. To keeping the current dev_hard_header behaviour we introduce a similar callback structure "wpan_dev_header_ops" which contains 802.15.4 specific upper-layer header creation functionality, which can be called by wpan_dev_hard_header. Signed-off-by: Alexander Aring Signed-off-by: Marcel Holtmann --- include/net/cfg802154.h | 33 +++++++++++++++++++++++++++++++++ include/net/ieee802154_netdev.h | 9 --------- 2 files changed, 33 insertions(+), 9 deletions(-) (limited to 'include') diff --git a/include/net/cfg802154.h b/include/net/cfg802154.h index 76b1ffaea863..242273ccf34b 100644 --- a/include/net/cfg802154.h +++ b/include/net/cfg802154.h @@ -167,6 +167,26 @@ struct wpan_phy { char priv[0] __aligned(NETDEV_ALIGN); }; +struct ieee802154_addr { + u8 mode; + __le16 pan_id; + union { + __le16 short_addr; + __le64 extended_addr; + }; +}; + +struct wpan_dev_header_ops { + /* TODO create callback currently assumes ieee802154_mac_cb inside + * skb->cb. This should be changed to give these information as + * parameter. + */ + int (*create)(struct sk_buff *skb, struct net_device *dev, + const struct ieee802154_addr *daddr, + const struct ieee802154_addr *saddr, + unsigned int len); +}; + struct wpan_dev { struct wpan_phy *wpan_phy; int iftype; @@ -175,6 +195,8 @@ struct wpan_dev { struct list_head list; struct net_device *netdev; + const struct wpan_dev_header_ops *header_ops; + /* lowpan interface, set when the wpan_dev belongs to one lowpan_dev */ struct net_device *lowpan_dev; @@ -205,6 +227,17 @@ struct wpan_dev { #define to_phy(_dev) container_of(_dev, struct wpan_phy, dev) +static inline int +wpan_dev_hard_header(struct sk_buff *skb, struct net_device *dev, + const struct ieee802154_addr *daddr, + const struct ieee802154_addr *saddr, + unsigned int len) +{ + struct wpan_dev *wpan_dev = dev->ieee802154_ptr; + + return wpan_dev->header_ops->create(skb, dev, daddr, saddr, len); +} + struct wpan_phy * wpan_phy_new(const struct cfg802154_ops *ops, size_t priv_size); static inline void wpan_phy_set_dev(struct wpan_phy *phy, struct device *dev) diff --git a/include/net/ieee802154_netdev.h b/include/net/ieee802154_netdev.h index 95a71bc113b3..aebb9d8d7a11 100644 --- a/include/net/ieee802154_netdev.h +++ b/include/net/ieee802154_netdev.h @@ -50,15 +50,6 @@ struct ieee802154_sechdr { }; }; -struct ieee802154_addr { - u8 mode; - __le16 pan_id; - union { - __le16 short_addr; - __le64 extended_addr; - }; -}; - struct ieee802154_hdr_fc { #if defined(__LITTLE_ENDIAN_BITFIELD) u16 type:3, -- cgit v1.2.3 From 87a93e4eceb495f93e3f37b100334d2641765b6c Mon Sep 17 00:00:00 2001 From: Alexander Aring Date: Fri, 18 Sep 2015 11:30:43 +0200 Subject: ieee802154: change needed headroom/tailroom This patch cleanups needed_headroom, needed_tailroom and hard_header_len fields for wpan and lowpan interfaces. For wpan interfaces the worst case mac header len should be part of needed_headroom, currently this is set as hard_header_len, but hard_header_len should be set to the minimum header length which xmit call assumes and this is the minimum frame length of 802.15.4. The hard_header_len value will check inside send callbacl of AF_PACKET raw sockets. For lowpan interfaces, if fragmentation isn't needed the skb will call dev_hard_header for 802154 layer and queue it afterwards. This happens without new skb allocation, so we need the same headroom and tailroom lengths like 802154 inside 802154 6lowpan layer. At least we assume as minimum header length an ipv6 header size. Signed-off-by: Alexander Aring Signed-off-by: Marcel Holtmann --- include/linux/ieee802154.h | 11 +++++++++++ include/net/6lowpan.h | 8 ++++++++ include/net/mac802154.h | 8 -------- 3 files changed, 19 insertions(+), 8 deletions(-) (limited to 'include') diff --git a/include/linux/ieee802154.h b/include/linux/ieee802154.h index db01492814d3..205ce4e1ac32 100644 --- a/include/linux/ieee802154.h +++ b/include/linux/ieee802154.h @@ -31,6 +31,17 @@ #define IEEE802154_ACK_PSDU_LEN 5 #define IEEE802154_MIN_PSDU_LEN 9 #define IEEE802154_FCS_LEN 2 +#define IEEE802154_MAX_AUTH_TAG_LEN 16 + +/* General MAC frame format: + * 2 bytes: Frame Control + * 1 byte: Sequence Number + * 20 bytes: Addressing fields + * 14 bytes: Auxiliary Security Header + */ +#define IEEE802154_MAX_HEADER_LEN (2 + 1 + 20 + 14) +#define IEEE802154_MIN_HEADER_LEN (IEEE802154_ACK_PSDU_LEN - \ + IEEE802154_FCS_LEN) #define IEEE802154_PAN_ID_BROADCAST 0xffff #define IEEE802154_ADDR_SHORT_BROADCAST 0xffff diff --git a/include/net/6lowpan.h b/include/net/6lowpan.h index eeae5eb58754..c17f556644fc 100644 --- a/include/net/6lowpan.h +++ b/include/net/6lowpan.h @@ -61,6 +61,14 @@ #define UIP_PROTO_UDP 17 /* ipv6 next header value for UDP */ #define UIP_FRAGH_LEN 8 /* ipv6 fragment header size */ +#define LOWPAN_NHC_MAX_ID_LEN 1 +/* Max IPHC Header len without IPv6 hdr specific inline data. + * Useful for getting the "extra" bytes we need at worst case compression. + * + * LOWPAN_IPHC + CID + LOWPAN_NHC_MAX_ID_LEN + */ +#define LOWPAN_IPHC_MAX_HEADER_LEN (2 + 1 + LOWPAN_NHC_MAX_ID_LEN) + /* * ipv6 address based on mac * second bit-flip (Universe/Local) is done according RFC2464 diff --git a/include/net/mac802154.h b/include/net/mac802154.h index 32bd7c0467d4..2c478501ad14 100644 --- a/include/net/mac802154.h +++ b/include/net/mac802154.h @@ -23,14 +23,6 @@ #include -/* General MAC frame format: - * 2 bytes: Frame Control - * 1 byte: Sequence Number - * 20 bytes: Addressing fields - * 14 bytes: Auxiliary Security Header - */ -#define MAC802154_FRAME_HARD_HEADER_LEN (2 + 1 + 20 + 14) - /** * enum ieee802154_hw_addr_filt_flags - hardware address filtering flags * -- cgit v1.2.3 From 79750ac4257763ff595a8b2cdc7ba580f0b0c8e0 Mon Sep 17 00:00:00 2001 From: Alexander Aring Date: Mon, 21 Sep 2015 11:24:33 +0200 Subject: ieee802154: add helpers for frame control checks This patch introduce two static inline functions. The first to get the frame control field from an sk_buff. The second is for checking on the acknowledgment request bit on the frame control field. Later we can introduce more functions to check on the frame control fields. These will deprecate the current behaviour which requires a host-byteorder conversion and manually bit handling. Reviewed-by: Stefan Schmidt Signed-off-by: Alexander Aring Signed-off-by: Marcel Holtmann --- include/linux/ieee802154.h | 12 ++++++++++++ 1 file changed, 12 insertions(+) (limited to 'include') diff --git a/include/linux/ieee802154.h b/include/linux/ieee802154.h index 205ce4e1ac32..aca228b81464 100644 --- a/include/linux/ieee802154.h +++ b/include/linux/ieee802154.h @@ -25,6 +25,8 @@ #include #include +#include +#include #include #define IEEE802154_MTU 127 @@ -218,6 +220,7 @@ enum { /* frame control handling */ #define IEEE802154_FCTL_FTYPE 0x0003 +#define IEEE802154_FCTL_ACKREQ 0x0020 #define IEEE802154_FCTL_INTRA_PAN 0x0040 #define IEEE802154_FTYPE_DATA 0x0001 @@ -232,6 +235,15 @@ static inline int ieee802154_is_data(__le16 fc) cpu_to_le16(IEEE802154_FTYPE_DATA); } +/** + * ieee802154_is_ackreq - check if acknowledgment request bit is set + * @fc: frame control bytes in little-endian byteorder + */ +static inline bool ieee802154_is_ackreq(__le16 fc) +{ + return fc & cpu_to_le16(IEEE802154_FCTL_ACKREQ); +} + /** * ieee802154_is_intra_pan - check if intra pan id communication * @fc: frame control bytes in little-endian byteorder -- cgit v1.2.3 From 7bdbe400d1b2aac116513f90b75969ad2365fba6 Mon Sep 17 00:00:00 2001 From: Johannes Berg Date: Sat, 15 Aug 2015 22:39:49 +0300 Subject: nl80211: support vendor dumpit commands In order to transfer many items in vendor commands, support the dumpit netlink method for them. Signed-off-by: Johannes Berg --- include/net/cfg80211.h | 9 +++++++++ 1 file changed, 9 insertions(+) (limited to 'include') diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h index f0889a247643..0f54c9ef4c7d 100644 --- a/include/net/cfg80211.h +++ b/include/net/cfg80211.h @@ -2971,12 +2971,21 @@ enum wiphy_vendor_command_flags { * @doit: callback for the operation, note that wdev is %NULL if the * flags didn't ask for a wdev and non-%NULL otherwise; the data * pointer may be %NULL if userspace provided no data at all + * @dumpit: dump callback, for transferring bigger/multiple items. The + * @storage points to cb->args[5], ie. is preserved over the multiple + * dumpit calls. + * It's recommended to not have the same sub command with both @doit and + * @dumpit, so that userspace can assume certain ones are get and others + * are used with dump requests. */ struct wiphy_vendor_command { struct nl80211_vendor_cmd_info info; u32 flags; int (*doit)(struct wiphy *wiphy, struct wireless_dev *wdev, const void *data, int data_len); + int (*dumpit)(struct wiphy *wiphy, struct wireless_dev *wdev, + struct sk_buff *skb, const void *data, int data_len, + unsigned long *storage); }; /** -- cgit v1.2.3 From 1b09b5568e5f46c6dfb781d7c1dfad431a6d8ec1 Mon Sep 17 00:00:00 2001 From: Andrei Otcheretianski Date: Sat, 15 Aug 2015 22:39:50 +0300 Subject: mac80211: introduce per vif frame registration API Currently the cfg80211's frame registration api receives wdev, however mac80211 assumes per device filter configuration and ignores wdev. Per device filtering is too wasteful, especially for multi-channel devices. Introduce new per vif frame registration API and use it for probe request registrations in ieee80211_mgmt_frame_register() Also call directly to ieee80211_configure_filter instead of using a work since it is now allowed to sleep in ieee80211_mgmt_frame_register. Signed-off-by: Andrei Otcheretianski Signed-off-by: Emmanuel Grumbach Signed-off-by: Johannes Berg --- include/net/mac80211.h | 16 ++++++++++++++++ 1 file changed, 16 insertions(+) (limited to 'include') diff --git a/include/net/mac80211.h b/include/net/mac80211.h index e3314e516681..167864503138 100644 --- a/include/net/mac80211.h +++ b/include/net/mac80211.h @@ -5,6 +5,7 @@ * Copyright 2006-2007 Jiri Benc * Copyright 2007-2010 Johannes Berg * Copyright 2013-2014 Intel Mobile Communications GmbH + * Copyright (C) 2015 Intel Deutschland GmbH * * This program is free software; you can redistribute it and/or modify * it under the terms of the GNU General Public License version 2 as @@ -1358,6 +1359,8 @@ enum ieee80211_vif_flags { * @debugfs_dir: debugfs dentry, can be used by drivers to create own per * interface debug files. Note that it will be NULL for the virtual * monitor interface (if that is requested.) + * @probe_req_reg: probe requests should be reported to mac80211 for this + * interface. * @drv_priv: data area for driver use, will always be aligned to * sizeof(void *). * @txq: the multicast data TX queue (if driver uses the TXQ abstraction) @@ -1382,6 +1385,8 @@ struct ieee80211_vif { struct dentry *debugfs_dir; #endif + unsigned int probe_req_reg; + /* must be last */ u8 drv_priv[0] __aligned(sizeof(void *)); }; @@ -2825,6 +2830,13 @@ enum ieee80211_reconfig_type { * See the section "Frame filtering" for more information. * This callback must be implemented and can sleep. * + * @config_iface_filter: Configure the interface's RX filter. + * This callback is optional and is used to configure which frames + * should be passed to mac80211. The filter_flags is the combination + * of FIF_* flags. The changed_flags is a bit mask that indicates + * which flags are changed. + * This callback can sleep. + * * @set_tim: Set TIM bit. mac80211 calls this function when a TIM bit * must be set or cleared for a given STA. Must be atomic. * @@ -3264,6 +3276,10 @@ struct ieee80211_ops { unsigned int changed_flags, unsigned int *total_flags, u64 multicast); + void (*config_iface_filter)(struct ieee80211_hw *hw, + struct ieee80211_vif *vif, + unsigned int filter_flags, + unsigned int changed_flags); int (*set_tim)(struct ieee80211_hw *hw, struct ieee80211_sta *sta, bool set); int (*set_key)(struct ieee80211_hw *hw, enum set_key_cmd cmd, -- cgit v1.2.3 From e3abc8ff0fc18b3925fd5d5c5fbd1613856f4e7c Mon Sep 17 00:00:00 2001 From: Emmanuel Grumbach Date: Sun, 16 Aug 2015 11:13:22 +0300 Subject: mac80211: allow to transmit A-MSDU within A-MPDU Advertise the capability to send A-MSDU within A-MPDU in the AddBA request sent by mac80211. Let the driver know about the peer's capabilities. Signed-off-by: Emmanuel Grumbach Signed-off-by: Johannes Berg --- include/linux/ieee80211.h | 1 + include/net/mac80211.h | 5 ++++- 2 files changed, 5 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/ieee80211.h b/include/linux/ieee80211.h index cfa906f28b7a..19eb9ecd6cf3 100644 --- a/include/linux/ieee80211.h +++ b/include/linux/ieee80211.h @@ -1379,6 +1379,7 @@ struct ieee80211_ht_operation { /* block-ack parameters */ +#define IEEE80211_ADDBA_PARAM_AMSDU_MASK 0x0001 #define IEEE80211_ADDBA_PARAM_POLICY_MASK 0x0002 #define IEEE80211_ADDBA_PARAM_TID_MASK 0x003C #define IEEE80211_ADDBA_PARAM_BUF_SIZE_MASK 0xFFC0 diff --git a/include/net/mac80211.h b/include/net/mac80211.h index 167864503138..f28cbc0988eb 100644 --- a/include/net/mac80211.h +++ b/include/net/mac80211.h @@ -3026,6 +3026,9 @@ enum ieee80211_reconfig_type { * buffer size of 8. Correct ways to retransmit #1 would be: * - TX: 1 or 18 or 81 * Even "189" would be wrong since 1 could be lost again. + * The @amsdu parameter is valid when the action is set to + * %IEEE80211_AMPDU_TX_OPERATIONAL and indicates the peer's ability + * to receive A-MSDU within A-MPDU. * * Returns a negative error code on failure. * The callback can sleep. @@ -3363,7 +3366,7 @@ struct ieee80211_ops { struct ieee80211_vif *vif, enum ieee80211_ampdu_mlme_action action, struct ieee80211_sta *sta, u16 tid, u16 *ssn, - u8 buf_size); + u8 buf_size, bool amsdu); int (*get_survey)(struct ieee80211_hw *hw, int idx, struct survey_info *survey); void (*rfkill_poll)(struct ieee80211_hw *hw); -- cgit v1.2.3 From 99e7ca44bb910f0cbfda5d9008e8517df0ebc939 Mon Sep 17 00:00:00 2001 From: Emmanuel Grumbach Date: Sat, 15 Aug 2015 22:39:51 +0300 Subject: mac80211: allow the driver to advertise A-MSDU within A-MPDU Rx support Drivers may be interested in receiving A-MSDU within A-MDPU. Not all the devices may be able to do so, make it configurable. Signed-off-by: Emmanuel Grumbach Signed-off-by: Johannes Berg --- include/net/mac80211.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include') diff --git a/include/net/mac80211.h b/include/net/mac80211.h index f28cbc0988eb..d62d6f41548b 100644 --- a/include/net/mac80211.h +++ b/include/net/mac80211.h @@ -1897,6 +1897,9 @@ struct ieee80211_txq { * @IEEE80211_HW_TDLS_WIDER_BW: The device/driver supports wider bandwidth * than then BSS bandwidth for a TDLS link on the base channel. * + * @IEEE80211_HW_SUPPORTS_AMSDU_IN_AMPDU: The driver supports receiving A-MSDUs + * within A-MPDU. + * * @NUM_IEEE80211_HW_FLAGS: number of hardware flags, used for sizing arrays */ enum ieee80211_hw_flags { @@ -1930,6 +1933,7 @@ enum ieee80211_hw_flags { IEEE80211_HW_SUPPORTS_CLONED_SKBS, IEEE80211_HW_SINGLE_SCAN_ON_ALL_BANDS, IEEE80211_HW_TDLS_WIDER_BW, + IEEE80211_HW_SUPPORTS_AMSDU_IN_AMPDU, /* keep last, obviously */ NUM_IEEE80211_HW_FLAGS -- cgit v1.2.3 From 0edd5faeb07bfd3ec5402f9467e4c169dcd131e8 Mon Sep 17 00:00:00 2001 From: Johannes Berg Date: Fri, 28 Aug 2015 14:31:48 +0200 Subject: wireless: mark element IDs 8 and 9 reserved These were never used in the tree, and are marked as reserved in the IEEE 802.11 documentation (ANA). Signed-off-by: Johannes Berg --- include/linux/ieee80211.h | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/ieee80211.h b/include/linux/ieee80211.h index 19eb9ecd6cf3..f79a02a69d26 100644 --- a/include/linux/ieee80211.h +++ b/include/linux/ieee80211.h @@ -1746,8 +1746,7 @@ enum ieee80211_eid { WLAN_EID_TIM = 5, WLAN_EID_IBSS_PARAMS = 6, WLAN_EID_COUNTRY = 7, - WLAN_EID_HP_PARAMS = 8, - WLAN_EID_HP_TABLE = 9, + /* 8, 9 reserved */ WLAN_EID_REQUEST = 10, WLAN_EID_QBSS_LOAD = 11, WLAN_EID_EDCA_PARAM_SET = 12, -- cgit v1.2.3 From 5359d112dcb081fd7a5f2de287fa995f6ba0800c Mon Sep 17 00:00:00 2001 From: Johannes Berg Date: Mon, 14 Sep 2015 13:56:17 +0200 Subject: Revert "mac80211: add pointer for driver use to key" This reverts commit f9a060f4b2003eb7350762e60dfc576447e44bad. No driver has turned up needing this functionality, and I've just implemented the functionality I wanted this for in a different way. Thus, remove it again, until somebody shows up with a need for having it. Signed-off-by: Johannes Berg --- include/net/mac80211.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include') diff --git a/include/net/mac80211.h b/include/net/mac80211.h index d62d6f41548b..3424ac6efb2a 100644 --- a/include/net/mac80211.h +++ b/include/net/mac80211.h @@ -1497,10 +1497,8 @@ enum ieee80211_key_flags { * - Temporal Authenticator Rx MIC Key (64 bits) * @icv_len: The ICV length for this key type * @iv_len: The IV length for this key type - * @drv_priv: pointer for driver use */ struct ieee80211_key_conf { - void *drv_priv; atomic64_t tx_pn; u32 cipher; u8 icv_len; -- cgit v1.2.3 From 37587fadff8ce8f40a6952f0383c571a89b29d1d Mon Sep 17 00:00:00 2001 From: Joe Perches Date: Thu, 30 Jul 2015 13:22:43 -0700 Subject: arcnet: fix indentation of if_arcnet.h Standardized spacing is easier to read. Signed-off-by: Joe Perches Signed-off-by: Michael Grzeschik --- include/uapi/linux/if_arcnet.h | 55 ++++++++++++++++++++---------------------- 1 file changed, 26 insertions(+), 29 deletions(-) (limited to 'include') diff --git a/include/uapi/linux/if_arcnet.h b/include/uapi/linux/if_arcnet.h index 46e34bd0e783..cfb642f8e7bd 100644 --- a/include/uapi/linux/if_arcnet.h +++ b/include/uapi/linux/if_arcnet.h @@ -19,7 +19,6 @@ #include #include - /* * These are the defined ARCnet Protocol ID's. */ @@ -57,42 +56,40 @@ * The RFC1201-specific components of an arcnet packet header. */ struct arc_rfc1201 { - __u8 proto; /* protocol ID field - varies */ - __u8 split_flag; /* for use with split packets */ - __be16 sequence; /* sequence number */ - __u8 payload[0]; /* space remaining in packet (504 bytes)*/ + __u8 proto; /* protocol ID field - varies */ + __u8 split_flag; /* for use with split packets */ + __be16 sequence; /* sequence number */ + __u8 payload[0]; /* space remaining in packet (504 bytes)*/ }; #define RFC1201_HDR_SIZE 4 - /* * The RFC1051-specific components. */ struct arc_rfc1051 { - __u8 proto; /* ARC_P_RFC1051_ARP/RFC1051_IP */ - __u8 payload[0]; /* 507 bytes */ + __u8 proto; /* ARC_P_RFC1051_ARP/RFC1051_IP */ + __u8 payload[0]; /* 507 bytes */ }; #define RFC1051_HDR_SIZE 1 - /* * The ethernet-encap-specific components. We have a real ethernet header * and some data. */ struct arc_eth_encap { - __u8 proto; /* Always ARC_P_ETHER */ - struct ethhdr eth; /* standard ethernet header (yuck!) */ - __u8 payload[0]; /* 493 bytes */ + __u8 proto; /* Always ARC_P_ETHER */ + struct ethhdr eth; /* standard ethernet header (yuck!) */ + __u8 payload[0]; /* 493 bytes */ }; #define ETH_ENCAP_HDR_SIZE 14 - struct arc_cap { __u8 proto; - __u8 cookie[sizeof(int)]; /* Actually NOT sent over the network */ + __u8 cookie[sizeof(int)]; + /* Actually NOT sent over the network */ union { __u8 ack; - __u8 raw[0]; /* 507 bytes */ + __u8 raw[0]; /* 507 bytes */ } mes; }; @@ -105,9 +102,9 @@ struct arc_cap { * driver. */ struct arc_hardware { - __u8 source, /* source ARCnet - filled in automagically */ - dest, /* destination ARCnet - 0 for broadcast */ - offset[2]; /* offset bytes (some weird semantics) */ + __u8 source; /* source ARCnet - filled in automagically */ + __u8 dest; /* destination ARCnet - 0 for broadcast */ + __u8 offset[2]; /* offset bytes (some weird semantics) */ }; #define ARC_HDR_SIZE 4 @@ -116,17 +113,17 @@ struct arc_hardware { * when you do a raw packet capture). */ struct archdr { - /* hardware requirements */ - struct arc_hardware hard; - - /* arcnet encapsulation-specific bits */ - union { - struct arc_rfc1201 rfc1201; - struct arc_rfc1051 rfc1051; - struct arc_eth_encap eth_encap; - struct arc_cap cap; - __u8 raw[0]; /* 508 bytes */ - } soft; + /* hardware requirements */ + struct arc_hardware hard; + + /* arcnet encapsulation-specific bits */ + union { + struct arc_rfc1201 rfc1201; + struct arc_rfc1051 rfc1051; + struct arc_eth_encap eth_encap; + struct arc_cap cap; + __u8 raw[0]; /* 508 bytes */ + } soft; }; #endif /* _LINUX_IF_ARCNET_H */ -- cgit v1.2.3 From cb334648a10c7fa6f0f163c22602f4dc1c6d56b4 Mon Sep 17 00:00:00 2001 From: Joe Perches Date: Tue, 5 May 2015 10:05:47 -0700 Subject: arcnet: Use normal kernel spacing style Standardized spacing is easier to read. git diff -w shows no differences. objdiff shows no differences. Signed-off-by: Joe Perches Signed-off-by: Michael Grzeschik --- include/linux/arcdevice.h | 90 +++++++++++++++++++++++------------------------ 1 file changed, 45 insertions(+), 45 deletions(-) (limited to 'include') diff --git a/include/linux/arcdevice.h b/include/linux/arcdevice.h index df0356220730..ccfd1d2f984b 100644 --- a/include/linux/arcdevice.h +++ b/include/linux/arcdevice.h @@ -51,7 +51,7 @@ /* * Debugging bitflags: each option can be enabled individually. - * + * * Note: only debug flags included in the ARCNET_DEBUG_MAX define will * actually be available. GCC will (at least, GCC 2.7.0 will) notice * lines using a BUGLVL not in ARCNET_DEBUG_MAX and automatically optimize @@ -77,33 +77,33 @@ #endif #ifndef ARCNET_DEBUG -#define ARCNET_DEBUG (D_NORMAL|D_EXTRA) +#define ARCNET_DEBUG (D_NORMAL | D_EXTRA) #endif extern int arcnet_debug; /* macros to simplify debug checking */ -#define BUGLVL(x) if ((ARCNET_DEBUG_MAX)&arcnet_debug&(x)) -#define BUGMSG2(x,msg,args...) do { BUGLVL(x) printk(msg, ## args); } while (0) -#define BUGMSG(x,msg,args...) \ - BUGMSG2(x, "%s%6s: " msg, \ - x==D_NORMAL ? KERN_WARNING \ - : x < D_DURING ? KERN_INFO : KERN_DEBUG, \ - dev->name , ## args) +#define BUGLVL(x) if ((ARCNET_DEBUG_MAX) & arcnet_debug & (x)) +#define BUGMSG2(x, msg, args...) do { BUGLVL(x) printk(msg, ## args); } while (0) +#define BUGMSG(x, msg, args...) \ + BUGMSG2(x, "%s%6s: " msg, \ + x == D_NORMAL ? KERN_WARNING \ + : x < D_DURING ? KERN_INFO : KERN_DEBUG, \ + dev->name, ## args) /* see how long a function call takes to run, expressed in CPU cycles */ -#define TIME(name, bytes, call) BUGLVL(D_TIMING) { \ - unsigned long _x, _y; \ - _x = get_cycles(); \ - call; \ - _y = get_cycles(); \ - BUGMSG(D_TIMING, \ - "%s: %d bytes in %lu cycles == " \ - "%lu Kbytes/100Mcycle\n",\ - name, bytes, _y - _x, \ - 100000000 / 1024 * bytes / (_y - _x + 1));\ - } \ - else { \ - call;\ +#define TIME(name, bytes, call) BUGLVL(D_TIMING) { \ + unsigned long _x, _y; \ + _x = get_cycles(); \ + call; \ + _y = get_cycles(); \ + BUGMSG(D_TIMING, \ + "%s: %d bytes in %lu cycles == " \ + "%lu Kbytes/100Mcycle\n", \ + name, bytes, _y - _x, \ + 100000000 / 1024 * bytes / (_y - _x + 1)); \ + } \ + else { \ + call; \ } @@ -189,16 +189,16 @@ struct ArcProto { int mtu; /* largest possible packet */ int is_ip; /* This is a ip plugin - not a raw thing */ - void (*rx) (struct net_device * dev, int bufnum, - struct archdr * pkthdr, int length); - int (*build_header) (struct sk_buff * skb, struct net_device *dev, - unsigned short ethproto, uint8_t daddr); + void (*rx)(struct net_device *dev, int bufnum, + struct archdr *pkthdr, int length); + int (*build_header)(struct sk_buff *skb, struct net_device *dev, + unsigned short ethproto, uint8_t daddr); /* these functions return '1' if the skb can now be freed */ - int (*prepare_tx) (struct net_device * dev, struct archdr * pkt, int length, - int bufnum); - int (*continue_tx) (struct net_device * dev, int bufnum); - int (*ack_tx) (struct net_device * dev, int acked); + int (*prepare_tx)(struct net_device *dev, struct archdr *pkt, int length, + int bufnum); + int (*continue_tx)(struct net_device *dev, int bufnum); + int (*ack_tx)(struct net_device *dev, int acked); }; extern struct ArcProto *arc_proto_map[256], *arc_proto_default, @@ -263,13 +263,13 @@ struct arcnet_local { * situations in which we (for example) want to pre-load a transmit * buffer, or start receiving while we copy a received packet to * memory. - * + * * The rules: only the interrupt handler is allowed to _add_ buffers to * the queue; thus, this doesn't require a lock. Both the interrupt * handler and the transmit function will want to _remove_ buffers, so * we need to handle the situation where they try to do it at the same * time. - * + * * If next_buf == first_free_buf, the queue is empty. Since there are * only four possible buffers, the queue should never be full. */ @@ -298,17 +298,17 @@ struct arcnet_local { /* hardware-specific functions */ struct { struct module *owner; - void (*command) (struct net_device * dev, int cmd); - int (*status) (struct net_device * dev); - void (*intmask) (struct net_device * dev, int mask); - int (*reset) (struct net_device * dev, int really_reset); - void (*open) (struct net_device * dev); - void (*close) (struct net_device * dev); - - void (*copy_to_card) (struct net_device * dev, int bufnum, int offset, - void *buf, int count); - void (*copy_from_card) (struct net_device * dev, int bufnum, int offset, - void *buf, int count); + void (*command)(struct net_device *dev, int cmd); + int (*status)(struct net_device *dev); + void (*intmask)(struct net_device *dev, int mask); + int (*reset)(struct net_device *dev, int really_reset); + void (*open)(struct net_device *dev); + void (*close)(struct net_device *dev); + + void (*copy_to_card)(struct net_device *dev, int bufnum, int offset, + void *buf, int count); + void (*copy_from_card)(struct net_device *dev, int bufnum, int offset, + void *buf, int count); } hw; void __iomem *mem_start; /* pointer to ioremap'ed MMIO */ @@ -325,7 +325,7 @@ struct arcnet_local { #if ARCNET_DEBUG_MAX & D_SKB void arcnet_dump_skb(struct net_device *dev, struct sk_buff *skb, char *desc); #else -#define arcnet_dump_skb(dev,skb,desc) ; +#define arcnet_dump_skb(dev, skb, desc) ; #endif void arcnet_unregister_proto(struct ArcProto *proto); @@ -335,7 +335,7 @@ struct net_device *alloc_arcdev(const char *name); int arcnet_open(struct net_device *dev); int arcnet_close(struct net_device *dev); netdev_tx_t arcnet_send_packet(struct sk_buff *skb, - struct net_device *dev); + struct net_device *dev); void arcnet_timeout(struct net_device *dev); #endif /* __KERNEL__ */ -- cgit v1.2.3 From 01a1d5ac4e1a5890fd6c0d0ae900e1b6e4f851d6 Mon Sep 17 00:00:00 2001 From: Joe Perches Date: Tue, 5 May 2015 10:05:48 -0700 Subject: arcnet: Add and remove blank lines Use a more current kernel line style. Signed-off-by: Joe Perches Signed-off-by: Michael Grzeschik --- include/linux/arcdevice.h | 12 ------------ 1 file changed, 12 deletions(-) (limited to 'include') diff --git a/include/linux/arcdevice.h b/include/linux/arcdevice.h index ccfd1d2f984b..78687885eb81 100644 --- a/include/linux/arcdevice.h +++ b/include/linux/arcdevice.h @@ -34,7 +34,6 @@ */ #define RECON_THRESHOLD 30 - /* * Define this to the minimum "timeout" value. If a transmit takes longer * than TX_TIMEOUT jiffies, Linux will abort the TX and retry. On a large @@ -44,11 +43,9 @@ */ #define TX_TIMEOUT (HZ * 200 / 1000) - /* Display warnings about the driver being an ALPHA version. */ #undef ALPHA_WARNING - /* * Debugging bitflags: each option can be enabled individually. * @@ -106,7 +103,6 @@ extern int arcnet_debug; call; \ } - /* * Time needed to reset the card - in ms (milliseconds). This works on my * SMC PC100. I can't find a reference that tells me just how long I @@ -182,7 +178,6 @@ extern int arcnet_debug; #define ARC_CAN_10MBIT 2 /* card uses COM20022, supporting 10MBit, but default is 2.5MBit. */ - /* information needed to define an encapsulation driver */ struct ArcProto { char suffix; /* a for RFC1201, e for ether-encap, etc. */ @@ -204,7 +199,6 @@ struct ArcProto { extern struct ArcProto *arc_proto_map[256], *arc_proto_default, *arc_bcast_proto, *arc_raw_proto; - /* * "Incoming" is information needed for each address that could be sending * to us. Mostly for partially-received split packets. @@ -216,7 +210,6 @@ struct Incoming { numpackets; /* number of packets in split */ }; - /* only needed for RFC1201 */ struct Outgoing { struct ArcProto *proto; /* protocol driver that owns this: @@ -230,7 +223,6 @@ struct Outgoing { numsegs; /* number of segments */ }; - struct arcnet_local { uint8_t config, /* current value of CONFIG register */ timeout, /* Extended timeout for COM20020 */ @@ -251,7 +243,6 @@ struct arcnet_local { char *card_name; /* card ident string */ int card_flags; /* special card features */ - /* On preemtive and SMB a lock is needed */ spinlock_t lock; @@ -314,14 +305,11 @@ struct arcnet_local { void __iomem *mem_start; /* pointer to ioremap'ed MMIO */ }; - #define ARCRESET(x) (lp->hw.reset(dev, (x))) #define ACOMMAND(x) (lp->hw.command(dev, (x))) #define ASTATUS() (lp->hw.status(dev)) #define AINTMASK(x) (lp->hw.intmask(dev, (x))) - - #if ARCNET_DEBUG_MAX & D_SKB void arcnet_dump_skb(struct net_device *dev, struct sk_buff *skb, char *desc); #else -- cgit v1.2.3 From d77510f3436e0db9b5e72fa8159ce26c3ac88d2d Mon Sep 17 00:00:00 2001 From: Joe Perches Date: Tue, 5 May 2015 10:05:53 -0700 Subject: arcnet: Neaten BUGMSG macro defines These macros are actually printk and pr_cont uses with a flag. Add a new BUGLVL_TEST macro which is just the "should use" test and not an odd "if ()" macro to simplify uses in a new patch. Signed-off-by: Joe Perches Signed-off-by: Michael Grzeschik --- include/linux/arcdevice.h | 24 +++++++++++++++++------- 1 file changed, 17 insertions(+), 7 deletions(-) (limited to 'include') diff --git a/include/linux/arcdevice.h b/include/linux/arcdevice.h index 78687885eb81..ad610208fbba 100644 --- a/include/linux/arcdevice.h +++ b/include/linux/arcdevice.h @@ -78,14 +78,24 @@ #endif extern int arcnet_debug; +#define BUGLVL_TEST(x) ((x) & ARCNET_DEBUG_MAX & arcnet_debug) +#define BUGLVL(x) if (BUGLVL_TEST(x)) + /* macros to simplify debug checking */ -#define BUGLVL(x) if ((ARCNET_DEBUG_MAX) & arcnet_debug & (x)) -#define BUGMSG2(x, msg, args...) do { BUGLVL(x) printk(msg, ## args); } while (0) -#define BUGMSG(x, msg, args...) \ - BUGMSG2(x, "%s%6s: " msg, \ - x == D_NORMAL ? KERN_WARNING \ - : x < D_DURING ? KERN_INFO : KERN_DEBUG, \ - dev->name, ## args) +#define BUGMSG(x, fmt, ...) \ +do { \ + if (BUGLVL_TEST(x)) \ + printk("%s%6s: " fmt, \ + (x) == D_NORMAL ? KERN_WARNING : \ + (x) < D_DURING ? KERN_INFO : KERN_DEBUG, \ + dev->name, ##__VA_ARGS__); \ +} while (0) + +#define BUGMSG2(x, fmt, ...) \ +do { \ + if (BUGLVL_TEST(x)) \ + printk(fmt, ##__VA_ARGS__); \ +} while (0) /* see how long a function call takes to run, expressed in CPU cycles */ #define TIME(name, bytes, call) BUGLVL(D_TIMING) { \ -- cgit v1.2.3 From 72aeea4841c037b9b3abf65859673cbd7b6664a9 Mon Sep 17 00:00:00 2001 From: Joe Perches Date: Tue, 5 May 2015 10:05:54 -0700 Subject: arcnet: Expand odd BUGLVL macro with if and uses Don't hide what should be obvious. Make the macro a simple test instead of using if and test. Signed-off-by: Joe Perches Signed-off-by: Michael Grzeschik --- include/linux/arcdevice.h | 17 +++++++++-------- 1 file changed, 9 insertions(+), 8 deletions(-) (limited to 'include') diff --git a/include/linux/arcdevice.h b/include/linux/arcdevice.h index ad610208fbba..f07c66383b88 100644 --- a/include/linux/arcdevice.h +++ b/include/linux/arcdevice.h @@ -78,13 +78,12 @@ #endif extern int arcnet_debug; -#define BUGLVL_TEST(x) ((x) & ARCNET_DEBUG_MAX & arcnet_debug) -#define BUGLVL(x) if (BUGLVL_TEST(x)) +#define BUGLVL(x) ((x) & ARCNET_DEBUG_MAX & arcnet_debug) /* macros to simplify debug checking */ #define BUGMSG(x, fmt, ...) \ do { \ - if (BUGLVL_TEST(x)) \ + if (BUGLVL(x)) \ printk("%s%6s: " fmt, \ (x) == D_NORMAL ? KERN_WARNING : \ (x) < D_DURING ? KERN_INFO : KERN_DEBUG, \ @@ -93,12 +92,14 @@ do { \ #define BUGMSG2(x, fmt, ...) \ do { \ - if (BUGLVL_TEST(x)) \ + if (BUGLVL(x)) \ printk(fmt, ##__VA_ARGS__); \ } while (0) /* see how long a function call takes to run, expressed in CPU cycles */ -#define TIME(name, bytes, call) BUGLVL(D_TIMING) { \ +#define TIME(name, bytes, call) \ +do { \ + if (BUGLVL(D_TIMING)) { \ unsigned long _x, _y; \ _x = get_cycles(); \ call; \ @@ -108,10 +109,10 @@ do { \ "%lu Kbytes/100Mcycle\n", \ name, bytes, _y - _x, \ 100000000 / 1024 * bytes / (_y - _x + 1)); \ - } \ - else { \ + } else { \ call; \ - } + } \ +} while (0) /* * Time needed to reset the card - in ms (milliseconds). This works on my -- cgit v1.2.3 From a34c0932c3b2f28542825ffc5280d562c49ad42d Mon Sep 17 00:00:00 2001 From: Joe Perches Date: Tue, 5 May 2015 10:05:55 -0700 Subject: arcnet: Convert BUGMSG and BUGMSG2 to arc_prink and arc_cont These macros don't actually represent BUG uses but are more commonly used as logging macros, so use a more kernel style macro. Convert the BUGMSG from a netdev_ like use to actually use netdev_. Signed-off-by: Joe Perches Signed-off-by: Michael Grzeschik --- include/linux/arcdevice.h | 32 +++++++++++++++++--------------- 1 file changed, 17 insertions(+), 15 deletions(-) (limited to 'include') diff --git a/include/linux/arcdevice.h b/include/linux/arcdevice.h index f07c66383b88..a678027ff6c2 100644 --- a/include/linux/arcdevice.h +++ b/include/linux/arcdevice.h @@ -81,34 +81,36 @@ extern int arcnet_debug; #define BUGLVL(x) ((x) & ARCNET_DEBUG_MAX & arcnet_debug) /* macros to simplify debug checking */ -#define BUGMSG(x, fmt, ...) \ +#define arc_printk(x, dev, fmt, ...) \ do { \ - if (BUGLVL(x)) \ - printk("%s%6s: " fmt, \ - (x) == D_NORMAL ? KERN_WARNING : \ - (x) < D_DURING ? KERN_INFO : KERN_DEBUG, \ - dev->name, ##__VA_ARGS__); \ + if (BUGLVL(x)) { \ + if ((x) == D_NORMAL) \ + netdev_warn(dev, fmt, ##__VA_ARGS__); \ + else if ((x) < D_DURING) \ + netdev_info(dev, fmt, ##__VA_ARGS__); \ + else \ + netdev_dbg(dev, fmt, ##__VA_ARGS__); \ + } \ } while (0) -#define BUGMSG2(x, fmt, ...) \ +#define arc_cont(x, fmt, ...) \ do { \ - if (BUGLVL(x)) \ - printk(fmt, ##__VA_ARGS__); \ + if (BUGLVL(x)) \ + pr_cont(fmt, ##__VA_ARGS__); \ } while (0) /* see how long a function call takes to run, expressed in CPU cycles */ -#define TIME(name, bytes, call) \ +#define TIME(dev, name, bytes, call) \ do { \ if (BUGLVL(D_TIMING)) { \ unsigned long _x, _y; \ _x = get_cycles(); \ call; \ _y = get_cycles(); \ - BUGMSG(D_TIMING, \ - "%s: %d bytes in %lu cycles == " \ - "%lu Kbytes/100Mcycle\n", \ - name, bytes, _y - _x, \ - 100000000 / 1024 * bytes / (_y - _x + 1)); \ + arc_printk(D_TIMING, dev, \ + "%s: %d bytes in %lu cycles == %lu Kbytes/100Mcycle\n", \ + name, bytes, _y - _x, \ + 100000000 / 1024 * bytes / (_y - _x + 1)); \ } else { \ call; \ } \ -- cgit v1.2.3 From 83df99b50f901cb7c72cf132a83f43bbaeb01362 Mon Sep 17 00:00:00 2001 From: Joe Perches Date: Tue, 5 May 2015 10:06:01 -0700 Subject: arcnet: Convert arcnet_dump_skb macro to static inline Make sure the arguments are tested appropriately when not using this function. Signed-off-by: Joe Perches Signed-off-by: Michael Grzeschik --- include/linux/arcdevice.h | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/arcdevice.h b/include/linux/arcdevice.h index a678027ff6c2..1d8e36e13616 100644 --- a/include/linux/arcdevice.h +++ b/include/linux/arcdevice.h @@ -326,7 +326,10 @@ struct arcnet_local { #if ARCNET_DEBUG_MAX & D_SKB void arcnet_dump_skb(struct net_device *dev, struct sk_buff *skb, char *desc); #else -#define arcnet_dump_skb(dev, skb, desc) ; +static inline +void arcnet_dump_skb(struct net_device *dev, struct sk_buff *skb, char *desc) +{ +} #endif void arcnet_unregister_proto(struct ArcProto *proto); -- cgit v1.2.3 From d6d7d3ed56e3bfe7fd34108dbe23f0610e3d8621 Mon Sep 17 00:00:00 2001 From: Joe Perches Date: Tue, 5 May 2015 10:06:02 -0700 Subject: arcnet: Wrap some long lines Just neatening. Signed-off-by: Joe Perches Signed-off-by: Michael Grzeschik --- include/linux/arcdevice.h | 12 ++++++------ 1 file changed, 6 insertions(+), 6 deletions(-) (limited to 'include') diff --git a/include/linux/arcdevice.h b/include/linux/arcdevice.h index 1d8e36e13616..9ca135d0f114 100644 --- a/include/linux/arcdevice.h +++ b/include/linux/arcdevice.h @@ -203,8 +203,8 @@ struct ArcProto { unsigned short ethproto, uint8_t daddr); /* these functions return '1' if the skb can now be freed */ - int (*prepare_tx)(struct net_device *dev, struct archdr *pkt, int length, - int bufnum); + int (*prepare_tx)(struct net_device *dev, struct archdr *pkt, + int length, int bufnum); int (*continue_tx)(struct net_device *dev, int bufnum); int (*ack_tx)(struct net_device *dev, int acked); }; @@ -309,10 +309,10 @@ struct arcnet_local { void (*open)(struct net_device *dev); void (*close)(struct net_device *dev); - void (*copy_to_card)(struct net_device *dev, int bufnum, int offset, - void *buf, int count); - void (*copy_from_card)(struct net_device *dev, int bufnum, int offset, - void *buf, int count); + void (*copy_to_card)(struct net_device *dev, int bufnum, + int offset, void *buf, int count); + void (*copy_from_card)(struct net_device *dev, int bufnum, + int offset, void *buf, int count); } hw; void __iomem *mem_start; /* pointer to ioremap'ed MMIO */ -- cgit v1.2.3 From 26c6d281688e8bb8154fa78c60e551d024f5d0b8 Mon Sep 17 00:00:00 2001 From: Joe Perches Date: Tue, 5 May 2015 10:06:03 -0700 Subject: arcnet: Move files out of include/linux These #include files don't need to be in the include/linux directory as they can be local to drivers/net/arcnet/ Move them and update the #include statements. Update the MAINTAINERS file pattern by deleting arcdevice from the NETWORKING block as arcnet is currently unmaintained. Signed-off-by: Joe Perches Signed-off-by: Michael Grzeschik --- include/linux/arcdevice.h | 346 ---------------------------------------------- include/linux/com20020.h | 145 ------------------- 2 files changed, 491 deletions(-) delete mode 100644 include/linux/arcdevice.h delete mode 100644 include/linux/com20020.h (limited to 'include') diff --git a/include/linux/arcdevice.h b/include/linux/arcdevice.h deleted file mode 100644 index 9ca135d0f114..000000000000 --- a/include/linux/arcdevice.h +++ /dev/null @@ -1,346 +0,0 @@ -/* - * INET An implementation of the TCP/IP protocol suite for the LINUX - * operating system. NET is implemented using the BSD Socket - * interface as the means of communication with the user level. - * - * Definitions used by the ARCnet driver. - * - * Authors: Avery Pennarun and David Woodhouse - * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public License - * as published by the Free Software Foundation; either version - * 2 of the License, or (at your option) any later version. - * - */ -#ifndef _LINUX_ARCDEVICE_H -#define _LINUX_ARCDEVICE_H - -#include -#include - -#ifdef __KERNEL__ -#include - -/* - * RECON_THRESHOLD is the maximum number of RECON messages to receive - * within one minute before printing a "cabling problem" warning. The - * default value should be fine. - * - * After that, a "cabling restored" message will be printed on the next IRQ - * if no RECON messages have been received for 10 seconds. - * - * Do not define RECON_THRESHOLD at all if you want to disable this feature. - */ -#define RECON_THRESHOLD 30 - -/* - * Define this to the minimum "timeout" value. If a transmit takes longer - * than TX_TIMEOUT jiffies, Linux will abort the TX and retry. On a large - * network, or one with heavy network traffic, this timeout may need to be - * increased. The larger it is, though, the longer it will be between - * necessary transmits - don't set this too high. - */ -#define TX_TIMEOUT (HZ * 200 / 1000) - -/* Display warnings about the driver being an ALPHA version. */ -#undef ALPHA_WARNING - -/* - * Debugging bitflags: each option can be enabled individually. - * - * Note: only debug flags included in the ARCNET_DEBUG_MAX define will - * actually be available. GCC will (at least, GCC 2.7.0 will) notice - * lines using a BUGLVL not in ARCNET_DEBUG_MAX and automatically optimize - * them out. - */ -#define D_NORMAL 1 /* important operational info */ -#define D_EXTRA 2 /* useful, but non-vital information */ -#define D_INIT 4 /* show init/probe messages */ -#define D_INIT_REASONS 8 /* show reasons for discarding probes */ -#define D_RECON 32 /* print a message whenever token is lost */ -#define D_PROTO 64 /* debug auto-protocol support */ -/* debug levels below give LOTS of output during normal operation! */ -#define D_DURING 128 /* trace operations (including irq's) */ -#define D_TX 256 /* show tx packets */ -#define D_RX 512 /* show rx packets */ -#define D_SKB 1024 /* show skb's */ -#define D_SKB_SIZE 2048 /* show skb sizes */ -#define D_TIMING 4096 /* show time needed to copy buffers to card */ -#define D_DEBUG 8192 /* Very detailed debug line for line */ - -#ifndef ARCNET_DEBUG_MAX -#define ARCNET_DEBUG_MAX (127) /* change to ~0 if you want detailed debugging */ -#endif - -#ifndef ARCNET_DEBUG -#define ARCNET_DEBUG (D_NORMAL | D_EXTRA) -#endif -extern int arcnet_debug; - -#define BUGLVL(x) ((x) & ARCNET_DEBUG_MAX & arcnet_debug) - -/* macros to simplify debug checking */ -#define arc_printk(x, dev, fmt, ...) \ -do { \ - if (BUGLVL(x)) { \ - if ((x) == D_NORMAL) \ - netdev_warn(dev, fmt, ##__VA_ARGS__); \ - else if ((x) < D_DURING) \ - netdev_info(dev, fmt, ##__VA_ARGS__); \ - else \ - netdev_dbg(dev, fmt, ##__VA_ARGS__); \ - } \ -} while (0) - -#define arc_cont(x, fmt, ...) \ -do { \ - if (BUGLVL(x)) \ - pr_cont(fmt, ##__VA_ARGS__); \ -} while (0) - -/* see how long a function call takes to run, expressed in CPU cycles */ -#define TIME(dev, name, bytes, call) \ -do { \ - if (BUGLVL(D_TIMING)) { \ - unsigned long _x, _y; \ - _x = get_cycles(); \ - call; \ - _y = get_cycles(); \ - arc_printk(D_TIMING, dev, \ - "%s: %d bytes in %lu cycles == %lu Kbytes/100Mcycle\n", \ - name, bytes, _y - _x, \ - 100000000 / 1024 * bytes / (_y - _x + 1)); \ - } else { \ - call; \ - } \ -} while (0) - -/* - * Time needed to reset the card - in ms (milliseconds). This works on my - * SMC PC100. I can't find a reference that tells me just how long I - * should wait. - */ -#define RESETtime (300) - -/* - * These are the max/min lengths of packet payload, not including the - * arc_hardware header, but definitely including the soft header. - * - * Note: packet sizes 254, 255, 256 are impossible because of the way - * ARCnet registers work That's why RFC1201 defines "exception" packets. - * In non-RFC1201 protocols, we have to just tack some extra bytes on the - * end. - */ -#define MTU 253 /* normal packet max size */ -#define MinTU 257 /* extended packet min size */ -#define XMTU 508 /* extended packet max size */ - -/* status/interrupt mask bit fields */ -#define TXFREEflag 0x01 /* transmitter available */ -#define TXACKflag 0x02 /* transmitted msg. ackd */ -#define RECONflag 0x04 /* network reconfigured */ -#define TESTflag 0x08 /* test flag */ -#define EXCNAKflag 0x08 /* excesive nak flag */ -#define RESETflag 0x10 /* power-on-reset */ -#define RES1flag 0x20 /* reserved - usually set by jumper */ -#define RES2flag 0x40 /* reserved - usually set by jumper */ -#define NORXflag 0x80 /* receiver inhibited */ - -/* Flags used for IO-mapped memory operations */ -#define AUTOINCflag 0x40 /* Increase location with each access */ -#define IOMAPflag 0x02 /* (for 90xx) Use IO mapped memory, not mmap */ -#define ENABLE16flag 0x80 /* (for 90xx) Enable 16-bit mode */ - -/* in the command register, the following bits have these meanings: - * 0-2 command - * 3-4 page number (for enable rcv/xmt command) - * 7 receive broadcasts - */ -#define NOTXcmd 0x01 /* disable transmitter */ -#define NORXcmd 0x02 /* disable receiver */ -#define TXcmd 0x03 /* enable transmitter */ -#define RXcmd 0x04 /* enable receiver */ -#define CONFIGcmd 0x05 /* define configuration */ -#define CFLAGScmd 0x06 /* clear flags */ -#define TESTcmd 0x07 /* load test flags */ - -/* flags for "clear flags" command */ -#define RESETclear 0x08 /* power-on-reset */ -#define CONFIGclear 0x10 /* system reconfigured */ - -#define EXCNAKclear 0x0E /* Clear and acknowledge the excive nak bit */ - -/* flags for "load test flags" command */ -#define TESTload 0x08 /* test flag (diagnostic) */ - -/* byte deposited into first address of buffers on reset */ -#define TESTvalue 0321 /* that's octal for 0xD1 :) */ - -/* for "enable receiver" command */ -#define RXbcasts 0x80 /* receive broadcasts */ - -/* flags for "define configuration" command */ -#define NORMALconf 0x00 /* 1-249 byte packets */ -#define EXTconf 0x08 /* 250-504 byte packets */ - -/* card feature flags, set during auto-detection. - * (currently only used by com20020pci) - */ -#define ARC_IS_5MBIT 1 /* card default speed is 5MBit */ -#define ARC_CAN_10MBIT 2 /* card uses COM20022, supporting 10MBit, - but default is 2.5MBit. */ - -/* information needed to define an encapsulation driver */ -struct ArcProto { - char suffix; /* a for RFC1201, e for ether-encap, etc. */ - int mtu; /* largest possible packet */ - int is_ip; /* This is a ip plugin - not a raw thing */ - - void (*rx)(struct net_device *dev, int bufnum, - struct archdr *pkthdr, int length); - int (*build_header)(struct sk_buff *skb, struct net_device *dev, - unsigned short ethproto, uint8_t daddr); - - /* these functions return '1' if the skb can now be freed */ - int (*prepare_tx)(struct net_device *dev, struct archdr *pkt, - int length, int bufnum); - int (*continue_tx)(struct net_device *dev, int bufnum); - int (*ack_tx)(struct net_device *dev, int acked); -}; - -extern struct ArcProto *arc_proto_map[256], *arc_proto_default, - *arc_bcast_proto, *arc_raw_proto; - -/* - * "Incoming" is information needed for each address that could be sending - * to us. Mostly for partially-received split packets. - */ -struct Incoming { - struct sk_buff *skb; /* packet data buffer */ - __be16 sequence; /* sequence number of assembly */ - uint8_t lastpacket, /* number of last packet (from 1) */ - numpackets; /* number of packets in split */ -}; - -/* only needed for RFC1201 */ -struct Outgoing { - struct ArcProto *proto; /* protocol driver that owns this: - * if NULL, no packet is pending. - */ - struct sk_buff *skb; /* buffer from upper levels */ - struct archdr *pkt; /* a pointer into the skb */ - uint16_t length, /* bytes total */ - dataleft, /* bytes left */ - segnum, /* segment being sent */ - numsegs; /* number of segments */ -}; - -struct arcnet_local { - uint8_t config, /* current value of CONFIG register */ - timeout, /* Extended timeout for COM20020 */ - backplane, /* Backplane flag for COM20020 */ - clockp, /* COM20020 clock divider */ - clockm, /* COM20020 clock multiplier flag */ - setup, /* Contents of setup1 register */ - setup2, /* Contents of setup2 register */ - intmask; /* current value of INTMASK register */ - uint8_t default_proto[256]; /* default encap to use for each host */ - int cur_tx, /* buffer used by current transmit, or -1 */ - next_tx, /* buffer where a packet is ready to send */ - cur_rx; /* current receive buffer */ - int lastload_dest, /* can last loaded packet be acked? */ - lasttrans_dest; /* can last TX'd packet be acked? */ - int timed_out; /* need to process TX timeout and drop packet */ - unsigned long last_timeout; /* time of last reported timeout */ - char *card_name; /* card ident string */ - int card_flags; /* special card features */ - - /* On preemtive and SMB a lock is needed */ - spinlock_t lock; - - /* - * Buffer management: an ARCnet card has 4 x 512-byte buffers, each of - * which can be used for either sending or receiving. The new dynamic - * buffer management routines use a simple circular queue of available - * buffers, and take them as they're needed. This way, we simplify - * situations in which we (for example) want to pre-load a transmit - * buffer, or start receiving while we copy a received packet to - * memory. - * - * The rules: only the interrupt handler is allowed to _add_ buffers to - * the queue; thus, this doesn't require a lock. Both the interrupt - * handler and the transmit function will want to _remove_ buffers, so - * we need to handle the situation where they try to do it at the same - * time. - * - * If next_buf == first_free_buf, the queue is empty. Since there are - * only four possible buffers, the queue should never be full. - */ - atomic_t buf_lock; - int buf_queue[5]; - int next_buf, first_free_buf; - - /* network "reconfiguration" handling */ - unsigned long first_recon; /* time of "first" RECON message to count */ - unsigned long last_recon; /* time of most recent RECON */ - int num_recons; /* number of RECONs between first and last. */ - int network_down; /* do we think the network is down? */ - - int excnak_pending; /* We just got an excesive nak interrupt */ - - struct { - uint16_t sequence; /* sequence number (incs with each packet) */ - __be16 aborted_seq; - - struct Incoming incoming[256]; /* one from each address */ - } rfc1201; - - /* really only used by rfc1201, but we'll pretend it's not */ - struct Outgoing outgoing; /* packet currently being sent */ - - /* hardware-specific functions */ - struct { - struct module *owner; - void (*command)(struct net_device *dev, int cmd); - int (*status)(struct net_device *dev); - void (*intmask)(struct net_device *dev, int mask); - int (*reset)(struct net_device *dev, int really_reset); - void (*open)(struct net_device *dev); - void (*close)(struct net_device *dev); - - void (*copy_to_card)(struct net_device *dev, int bufnum, - int offset, void *buf, int count); - void (*copy_from_card)(struct net_device *dev, int bufnum, - int offset, void *buf, int count); - } hw; - - void __iomem *mem_start; /* pointer to ioremap'ed MMIO */ -}; - -#define ARCRESET(x) (lp->hw.reset(dev, (x))) -#define ACOMMAND(x) (lp->hw.command(dev, (x))) -#define ASTATUS() (lp->hw.status(dev)) -#define AINTMASK(x) (lp->hw.intmask(dev, (x))) - -#if ARCNET_DEBUG_MAX & D_SKB -void arcnet_dump_skb(struct net_device *dev, struct sk_buff *skb, char *desc); -#else -static inline -void arcnet_dump_skb(struct net_device *dev, struct sk_buff *skb, char *desc) -{ -} -#endif - -void arcnet_unregister_proto(struct ArcProto *proto); -irqreturn_t arcnet_interrupt(int irq, void *dev_id); -struct net_device *alloc_arcdev(const char *name); - -int arcnet_open(struct net_device *dev); -int arcnet_close(struct net_device *dev); -netdev_tx_t arcnet_send_packet(struct sk_buff *skb, - struct net_device *dev); -void arcnet_timeout(struct net_device *dev); - -#endif /* __KERNEL__ */ -#endif /* _LINUX_ARCDEVICE_H */ diff --git a/include/linux/com20020.h b/include/linux/com20020.h deleted file mode 100644 index 85898995b234..000000000000 --- a/include/linux/com20020.h +++ /dev/null @@ -1,145 +0,0 @@ -/* - * Linux ARCnet driver - COM20020 chipset support - function declarations - * - * Written 1997 by David Woodhouse. - * Written 1994-1999 by Avery Pennarun. - * Derived from skeleton.c by Donald Becker. - * - * Special thanks to Contemporary Controls, Inc. (www.ccontrols.com) - * for sponsoring the further development of this driver. - * - * ********************** - * - * The original copyright of skeleton.c was as follows: - * - * skeleton.c Written 1993 by Donald Becker. - * Copyright 1993 United States Government as represented by the - * Director, National Security Agency. This software may only be used - * and distributed according to the terms of the GNU General Public License as - * modified by SRC, incorporated herein by reference. - * - * ********************** - * - * For more details, see drivers/net/arcnet.c - * - * ********************** - */ -#ifndef __COM20020_H -#define __COM20020_H - -int com20020_check(struct net_device *dev); -int com20020_found(struct net_device *dev, int shared); -extern const struct net_device_ops com20020_netdev_ops; - -/* The number of low I/O ports used by the card. */ -#define ARCNET_TOTAL_SIZE 8 - -/* various register addresses */ -#ifdef CONFIG_SA1100_CT6001 -#define BUS_ALIGN 2 /* 8 bit device on a 16 bit bus - needs padding */ -#else -#define BUS_ALIGN 1 -#endif - -#define PLX_PCI_MAX_CARDS 2 - -struct com20020_pci_channel_map { - u32 bar; - u32 offset; - u32 size; /* 0x00 - auto, e.g. length of entire bar */ -}; - -struct com20020_pci_card_info { - const char *name; - int devcount; - - struct com20020_pci_channel_map chan_map_tbl[PLX_PCI_MAX_CARDS]; - - unsigned int flags; -}; - -struct com20020_priv { - struct com20020_pci_card_info *ci; - struct list_head list_dev; -}; - -struct com20020_dev { - struct list_head list; - struct net_device *dev; - - struct com20020_priv *pci_priv; - int index; -}; - -#define _INTMASK (ioaddr+BUS_ALIGN*0) /* writable */ -#define _STATUS (ioaddr+BUS_ALIGN*0) /* readable */ -#define _COMMAND (ioaddr+BUS_ALIGN*1) /* standard arcnet commands */ -#define _DIAGSTAT (ioaddr+BUS_ALIGN*1) /* diagnostic status register */ -#define _ADDR_HI (ioaddr+BUS_ALIGN*2) /* control registers for IO-mapped memory */ -#define _ADDR_LO (ioaddr+BUS_ALIGN*3) -#define _MEMDATA (ioaddr+BUS_ALIGN*4) /* data port for IO-mapped memory */ -#define _SUBADR (ioaddr+BUS_ALIGN*5) /* the extended port _XREG refers to */ -#define _CONFIG (ioaddr+BUS_ALIGN*6) /* configuration register */ -#define _XREG (ioaddr+BUS_ALIGN*7) /* extra registers (indexed by _CONFIG - or _SUBADR) */ - -/* in the ADDR_HI register */ -#define RDDATAflag 0x80 /* next access is a read (not a write) */ - -/* in the DIAGSTAT register */ -#define NEWNXTIDflag 0x02 /* ID to which token is passed has changed */ - -/* in the CONFIG register */ -#define RESETcfg 0x80 /* put card in reset state */ -#define TXENcfg 0x20 /* enable TX */ - -/* in SETUP register */ -#define PROMISCset 0x10 /* enable RCV_ALL */ -#define P1MODE 0x80 /* enable P1-MODE for Backplane */ -#define SLOWARB 0x01 /* enable Slow Arbitration for >=5Mbps */ - -/* COM2002x */ -#define SUB_TENTATIVE 0 /* tentative node ID */ -#define SUB_NODE 1 /* node ID */ -#define SUB_SETUP1 2 /* various options */ -#define SUB_TEST 3 /* test/diag register */ - -/* COM20022 only */ -#define SUB_SETUP2 4 /* sundry options */ -#define SUB_BUSCTL 5 /* bus control options */ -#define SUB_DMACOUNT 6 /* DMA count options */ - -#define SET_SUBADR(x) do { \ - if ((x) < 4) \ - { \ - lp->config = (lp->config & ~0x03) | (x); \ - SETCONF; \ - } \ - else \ - { \ - outb(x, _SUBADR); \ - } \ -} while (0) - -#undef ARCRESET -#undef ASTATUS -#undef ACOMMAND -#undef AINTMASK - -#define ARCRESET { outb(lp->config | 0x80, _CONFIG); \ - udelay(5); \ - outb(lp->config , _CONFIG); \ - } -#define ARCRESET0 { outb(0x18 | 0x80, _CONFIG); \ - udelay(5); \ - outb(0x18 , _CONFIG); \ - } - -#define ASTATUS() inb(_STATUS) -#define ADIAGSTATUS() inb(_DIAGSTAT) -#define ACOMMAND(cmd) outb((cmd),_COMMAND) -#define AINTMASK(msk) outb((msk),_INTMASK) - -#define SETCONF outb(lp->config, _CONFIG) - -#endif /* __COM20020_H */ -- cgit v1.2.3 From a79e88d9fbbe2e3ecb9d883fb59dca7468d42d79 Mon Sep 17 00:00:00 2001 From: Scott Feldman Date: Wed, 23 Sep 2015 08:39:16 -0700 Subject: bridge: define some min/max/default ageing time constants Signed-off-by: Scott Feldman Acked-by: Jiri Pirko Signed-off-by: David S. Miller --- include/linux/if_bridge.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include') diff --git a/include/linux/if_bridge.h b/include/linux/if_bridge.h index dad8b00beed2..a338a688ee4a 100644 --- a/include/linux/if_bridge.h +++ b/include/linux/if_bridge.h @@ -46,6 +46,12 @@ struct br_ip_list { #define BR_LEARNING_SYNC BIT(9) #define BR_PROXYARP_WIFI BIT(10) +/* values as per ieee8021QBridgeFdbAgingTime */ +#define BR_MIN_AGEING_TIME (10 * HZ) +#define BR_MAX_AGEING_TIME (1000000 * HZ) + +#define BR_DEFAULT_AGEING_TIME (300 * HZ) + extern void brioctl_set(int (*ioctl_hook)(struct net *, unsigned int, void __user *)); typedef int br_should_route_hook_t(struct sk_buff *skb); -- cgit v1.2.3 From 06e60e5912c0373b15143cc52e4a11fafeaafff3 Mon Sep 17 00:00:00 2001 From: Max Filippov Date: Tue, 22 Sep 2015 14:27:16 +0300 Subject: net/ethoc: support big-endian register layout Signed-off-by: Max Filippov Signed-off-by: David S. Miller --- include/net/ethoc.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/net/ethoc.h b/include/net/ethoc.h index 2a2d6bb34eb8..bb7f467da7fc 100644 --- a/include/net/ethoc.h +++ b/include/net/ethoc.h @@ -17,6 +17,7 @@ struct ethoc_platform_data { u8 hwaddr[IFHWADDRLEN]; s8 phy_id; u32 eth_clkfreq; + bool big_endian; }; #endif /* !LINUX_NET_ETHOC_H */ -- cgit v1.2.3 From 58dbc6f2604a2cbff9e6ec144d1bb9d000a1a1ec Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Mon, 21 Sep 2015 13:01:41 -0500 Subject: ipvs: Store ipvs not net in struct ip_vs_conn In practice struct netns_ipvs is as meaningful as struct net and more useful as it holds the ipvs specific data. So store a pointer to struct netns_ipvs. Update the accesses of conn->net to access conn->ipvs->net instead. Signed-off-by: "Eric W. Biederman" Acked-by: Julian Anastasov Signed-off-by: Simon Horman --- include/net/ip_vs.h | 31 +------------------------------ 1 file changed, 1 insertion(+), 30 deletions(-) (limited to 'include') diff --git a/include/net/ip_vs.h b/include/net/ip_vs.h index 1096a71ab6ed..3bf6da8fdaf1 100644 --- a/include/net/ip_vs.h +++ b/include/net/ip_vs.h @@ -572,9 +572,7 @@ struct ip_vs_conn { volatile __u32 flags; /* status flags */ __u16 protocol; /* Which protocol (TCP/UDP) */ __u16 daf; /* Address family of the dest */ -#ifdef CONFIG_NET_NS - struct net *net; /* Name space */ -#endif + struct netns_ipvs *ipvs; /* counter and timer */ atomic_t refcnt; /* reference count */ @@ -621,33 +619,6 @@ struct ip_vs_conn { struct rcu_head rcu_head; }; -/* To save some memory in conn table when name space is disabled. */ -static inline struct net *ip_vs_conn_net(const struct ip_vs_conn *cp) -{ -#ifdef CONFIG_NET_NS - return cp->net; -#else - return &init_net; -#endif -} - -static inline void ip_vs_conn_net_set(struct ip_vs_conn *cp, struct net *net) -{ -#ifdef CONFIG_NET_NS - cp->net = net; -#endif -} - -static inline int ip_vs_conn_net_eq(const struct ip_vs_conn *cp, - struct net *net) -{ -#ifdef CONFIG_NET_NS - return cp->net == net; -#else - return 1; -#endif -} - /* Extended internal versions of struct ip_vs_service_user and ip_vs_dest_user * for IPv6 support. * -- cgit v1.2.3 From e64e2b460cedadf93d05a23e9ad397cc0386568c Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Mon, 21 Sep 2015 13:01:42 -0500 Subject: ipvs: Store ipvs not net in struct ip_vs_conn_param In practice struct netns_ipvs is as meaningful as struct net and more useful as it holds the ipvs specific data. So store a pointer to struct netns_ipvs. Update the accesses of param->net to access param->ipvs->net instead. When lookup up struct ip_vs_conn in a hash table replace comparisons of cp->net with comparisons of cp->ipvs which is possible now that ipvs is present in ip_vs_conn_param. Signed-off-by: "Eric W. Biederman" Acked-by: Julian Anastasov Signed-off-by: Simon Horman --- include/net/ip_vs.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/net/ip_vs.h b/include/net/ip_vs.h index 3bf6da8fdaf1..8cca99bbe15b 100644 --- a/include/net/ip_vs.h +++ b/include/net/ip_vs.h @@ -545,7 +545,7 @@ struct ip_vs_proto_data *ip_vs_proto_data_get(struct net *net, unsigned short proto); struct ip_vs_conn_param { - struct net *net; + struct netns_ipvs *ipvs; const union nf_inet_addr *caddr; const union nf_inet_addr *vaddr; __be16 cport; @@ -1208,7 +1208,7 @@ static inline void ip_vs_conn_fill_param(struct net *net, int af, int protocol, __be16 vport, struct ip_vs_conn_param *p) { - p->net = net; + p->ipvs = net_ipvs(net); p->af = af; p->protocol = protocol; p->caddr = caddr; -- cgit v1.2.3 From 19913dec1bc1d1aa5afe26db858507d4c3042665 Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Mon, 21 Sep 2015 13:01:43 -0500 Subject: ipvs: Pass ipvs not net to ip_vs_fill_conn ipvs is what is actually desired so change the parameter and the modify the callers to pass struct netns_ipvs. Signed-off-by: "Eric W. Biederman" Acked-by: Julian Anastasov Signed-off-by: Simon Horman --- include/net/ip_vs.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/net/ip_vs.h b/include/net/ip_vs.h index 8cca99bbe15b..83e2aea63db2 100644 --- a/include/net/ip_vs.h +++ b/include/net/ip_vs.h @@ -1201,14 +1201,14 @@ enum { IP_VS_DIR_LAST, }; -static inline void ip_vs_conn_fill_param(struct net *net, int af, int protocol, +static inline void ip_vs_conn_fill_param(struct netns_ipvs *ipvs, int af, int protocol, const union nf_inet_addr *caddr, __be16 cport, const union nf_inet_addr *vaddr, __be16 vport, struct ip_vs_conn_param *p) { - p->ipvs = net_ipvs(net); + p->ipvs = ipvs; p->af = af; p->protocol = protocol; p->caddr = caddr; -- cgit v1.2.3 From 3109d2f2d1fe068f1cc3b1f74f5022ab4aef52a7 Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Mon, 21 Sep 2015 13:01:44 -0500 Subject: ipvs: Store ipvs not net in struct ip_vs_service In practice struct netns_ipvs is as meaningful as struct net and more useful as it holds the ipvs specific data. So store a pointer to struct netns_ipvs. Update the accesses of param->net to access param->ipvs->net instead. In functions where we are searching for an svc and filtering by net filter by ipvs instead. Signed-off-by: "Eric W. Biederman" Acked-by: Julian Anastasov Signed-off-by: Simon Horman --- include/net/ip_vs.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/net/ip_vs.h b/include/net/ip_vs.h index 83e2aea63db2..2c22380b9ad7 100644 --- a/include/net/ip_vs.h +++ b/include/net/ip_vs.h @@ -678,7 +678,7 @@ struct ip_vs_service { unsigned int flags; /* service status flags */ unsigned int timeout; /* persistent timeout in ticks */ __be32 netmask; /* grouping granularity, mask/plen */ - struct net *net; + struct netns_ipvs *ipvs; struct list_head destinations; /* real server d-linked list */ __u32 num_dests; /* number of servers */ -- cgit v1.2.3 From 0a4fd6ce92460ec325f7e56813645e4308da170e Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Mon, 21 Sep 2015 13:01:49 -0500 Subject: ipvs: Pass ipvs not net to ip_vs_service_find Signed-off-by: "Eric W. Biederman" Acked-by: Julian Anastasov Signed-off-by: Simon Horman --- include/net/ip_vs.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/net/ip_vs.h b/include/net/ip_vs.h index 2c22380b9ad7..828b19b23e02 100644 --- a/include/net/ip_vs.h +++ b/include/net/ip_vs.h @@ -1410,7 +1410,7 @@ extern struct ip_vs_stats ip_vs_stats; extern int sysctl_ip_vs_sync_ver; struct ip_vs_service * -ip_vs_service_find(struct net *net, int af, __u32 fwmark, __u16 protocol, +ip_vs_service_find(struct netns_ipvs *ipvs, int af, __u32 fwmark, __u16 protocol, const union nf_inet_addr *vaddr, __be16 vport); bool ip_vs_has_real_service(struct net *net, int af, __u16 protocol, -- cgit v1.2.3 From 48aed1b029597d5f33316b1e978392fe30814f8d Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Mon, 21 Sep 2015 13:01:50 -0500 Subject: ipvs: Pass ipvs not net to ip_vs_has_real_service Signed-off-by: "Eric W. Biederman" Acked-by: Julian Anastasov Signed-off-by: Simon Horman --- include/net/ip_vs.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/net/ip_vs.h b/include/net/ip_vs.h index 828b19b23e02..b93ee28fb011 100644 --- a/include/net/ip_vs.h +++ b/include/net/ip_vs.h @@ -1413,7 +1413,7 @@ struct ip_vs_service * ip_vs_service_find(struct netns_ipvs *ipvs, int af, __u32 fwmark, __u16 protocol, const union nf_inet_addr *vaddr, __be16 vport); -bool ip_vs_has_real_service(struct net *net, int af, __u16 protocol, +bool ip_vs_has_real_service(struct netns_ipvs *ipvs, int af, __u16 protocol, const union nf_inet_addr *daddr, __be16 dport); int ip_vs_use_count_inc(void); -- cgit v1.2.3 From dc2add6f2e35916afd6ffcd7819a06ce9b28063d Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Mon, 21 Sep 2015 13:01:51 -0500 Subject: ipvs: Pass ipvs not net to ip_vs_find_dest Signed-off-by: "Eric W. Biederman" Acked-by: Julian Anastasov Signed-off-by: Simon Horman --- include/net/ip_vs.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/net/ip_vs.h b/include/net/ip_vs.h index b93ee28fb011..b54a19eaa630 100644 --- a/include/net/ip_vs.h +++ b/include/net/ip_vs.h @@ -1423,7 +1423,7 @@ void ip_vs_unregister_nl_ioctl(void); int ip_vs_control_init(void); void ip_vs_control_cleanup(void); struct ip_vs_dest * -ip_vs_find_dest(struct net *net, int svc_af, int dest_af, +ip_vs_find_dest(struct netns_ipvs *ipvs, int svc_af, int dest_af, const union nf_inet_addr *daddr, __be16 dport, const union nf_inet_addr *vaddr, __be16 vport, __u16 protocol, __u32 fwmark, __u32 flags); -- cgit v1.2.3 From 56d2169b7734f9b5cb2a4e66887ce6dc33d53632 Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Mon, 21 Sep 2015 13:01:58 -0500 Subject: ipvs: Pass ipvs not net to ip_vs_service_net_cleanup Signed-off-by: "Eric W. Biederman" Acked-by: Julian Anastasov Signed-off-by: Simon Horman --- include/net/ip_vs.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/net/ip_vs.h b/include/net/ip_vs.h index b54a19eaa630..3c7040a313b5 100644 --- a/include/net/ip_vs.h +++ b/include/net/ip_vs.h @@ -1335,7 +1335,7 @@ void ip_vs_protocol_net_cleanup(struct net *net); void ip_vs_control_net_cleanup(struct net *net); void ip_vs_estimator_net_cleanup(struct net *net); void ip_vs_sync_net_cleanup(struct net *net); -void ip_vs_service_net_cleanup(struct net *net); +void ip_vs_service_net_cleanup(struct netns_ipvs *ipvs); /* IPVS application functions * (from ip_vs_app.c) -- cgit v1.2.3 From 18d6ade63c8d796c272e2b4922d649cf108d7980 Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Mon, 21 Sep 2015 13:02:01 -0500 Subject: ipvs: Pass ipvs not net to ip_vs_proto_data_get Signed-off-by: "Eric W. Biederman" Acked-by: Julian Anastasov Signed-off-by: Simon Horman --- include/net/ip_vs.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/net/ip_vs.h b/include/net/ip_vs.h index 3c7040a313b5..3c077e8a038c 100644 --- a/include/net/ip_vs.h +++ b/include/net/ip_vs.h @@ -541,7 +541,7 @@ struct ip_vs_proto_data { }; struct ip_vs_protocol *ip_vs_proto_get(unsigned short proto); -struct ip_vs_proto_data *ip_vs_proto_data_get(struct net *net, +struct ip_vs_proto_data *ip_vs_proto_data_get(struct netns_ipvs *ipvs, unsigned short proto); struct ip_vs_conn_param { -- cgit v1.2.3 From 6ac121d710697cee894d6981b804583b0a66ed38 Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Mon, 21 Sep 2015 13:02:10 -0500 Subject: ipvs: Pass ipvs not net to start_sync_thread Signed-off-by: "Eric W. Biederman" Acked-by: Julian Anastasov Signed-off-by: Simon Horman --- include/net/ip_vs.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/net/ip_vs.h b/include/net/ip_vs.h index 3c077e8a038c..dd7cd3a48fd4 100644 --- a/include/net/ip_vs.h +++ b/include/net/ip_vs.h @@ -1449,7 +1449,7 @@ static inline void ip_vs_dest_put_and_free(struct ip_vs_dest *dest) /* IPVS sync daemon data and function prototypes * (from ip_vs_sync.c) */ -int start_sync_thread(struct net *net, struct ipvs_sync_daemon_cfg *cfg, +int start_sync_thread(struct netns_ipvs *ipvs, struct ipvs_sync_daemon_cfg *cfg, int state); int stop_sync_thread(struct net *net, int state); void ip_vs_sync_conn(struct net *net, struct ip_vs_conn *cp, int pkts); -- cgit v1.2.3 From b3cf3cbfb57c273cf9f88230416fcc5b97287862 Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Mon, 21 Sep 2015 13:02:11 -0500 Subject: ipvs: Pass ipvs not net to stop_sync_thread Signed-off-by: "Eric W. Biederman" Acked-by: Julian Anastasov Signed-off-by: Simon Horman --- include/net/ip_vs.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/net/ip_vs.h b/include/net/ip_vs.h index dd7cd3a48fd4..71f4d338c208 100644 --- a/include/net/ip_vs.h +++ b/include/net/ip_vs.h @@ -1451,7 +1451,7 @@ static inline void ip_vs_dest_put_and_free(struct ip_vs_dest *dest) */ int start_sync_thread(struct netns_ipvs *ipvs, struct ipvs_sync_daemon_cfg *cfg, int state); -int stop_sync_thread(struct net *net, int state); +int stop_sync_thread(struct netns_ipvs *ipvs, int state); void ip_vs_sync_conn(struct net *net, struct ip_vs_conn *cp, int pkts); /* IPVS rate estimator prototypes (from ip_vs_est.c) */ -- cgit v1.2.3 From b61a8c1a40c2a9417eb6f710cce54353d195c9c7 Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Mon, 21 Sep 2015 13:02:17 -0500 Subject: ipvs: Pass ipvs not net to ip_vs_sync_conn Signed-off-by: "Eric W. Biederman" Acked-by: Julian Anastasov Signed-off-by: Simon Horman --- include/net/ip_vs.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/net/ip_vs.h b/include/net/ip_vs.h index 71f4d338c208..b10b337ce974 100644 --- a/include/net/ip_vs.h +++ b/include/net/ip_vs.h @@ -1452,7 +1452,7 @@ static inline void ip_vs_dest_put_and_free(struct ip_vs_dest *dest) int start_sync_thread(struct netns_ipvs *ipvs, struct ipvs_sync_daemon_cfg *cfg, int state); int stop_sync_thread(struct netns_ipvs *ipvs, int state); -void ip_vs_sync_conn(struct net *net, struct ip_vs_conn *cp, int pkts); +void ip_vs_sync_conn(struct netns_ipvs *ipvs, struct ip_vs_conn *cp, int pkts); /* IPVS rate estimator prototypes (from ip_vs_est.c) */ void ip_vs_start_estimator(struct net *net, struct ip_vs_stats *stats); -- cgit v1.2.3 From 802cb43703d080bd6269578bf6747189b654cc24 Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Mon, 21 Sep 2015 13:02:20 -0500 Subject: ipvs: Pass ipvs not net to ip_vs_sync_net_init Signed-off-by: "Eric W. Biederman" Acked-by: Julian Anastasov Signed-off-by: Simon Horman --- include/net/ip_vs.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/net/ip_vs.h b/include/net/ip_vs.h index b10b337ce974..47a4cddb7c33 100644 --- a/include/net/ip_vs.h +++ b/include/net/ip_vs.h @@ -1328,7 +1328,7 @@ int ip_vs_control_net_init(struct net *net); int ip_vs_protocol_net_init(struct net *net); int ip_vs_app_net_init(struct net *net); int ip_vs_conn_net_init(struct net *net); -int ip_vs_sync_net_init(struct net *net); +int ip_vs_sync_net_init(struct netns_ipvs *ipvs); void ip_vs_conn_net_cleanup(struct net *net); void ip_vs_app_net_cleanup(struct net *net); void ip_vs_protocol_net_cleanup(struct net *net); -- cgit v1.2.3 From ebea1f7c0b8c0bb02045c87e4b548a31fc5612a6 Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Mon, 21 Sep 2015 13:02:21 -0500 Subject: ipvs: Pass ipvs not net to ip_vs_sync_net_cleanup Signed-off-by: "Eric W. Biederman" Acked-by: Julian Anastasov Signed-off-by: Simon Horman --- include/net/ip_vs.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/net/ip_vs.h b/include/net/ip_vs.h index 47a4cddb7c33..f3ddf7696d68 100644 --- a/include/net/ip_vs.h +++ b/include/net/ip_vs.h @@ -1334,7 +1334,7 @@ void ip_vs_app_net_cleanup(struct net *net); void ip_vs_protocol_net_cleanup(struct net *net); void ip_vs_control_net_cleanup(struct net *net); void ip_vs_estimator_net_cleanup(struct net *net); -void ip_vs_sync_net_cleanup(struct net *net); +void ip_vs_sync_net_cleanup(struct netns_ipvs *ipvs); void ip_vs_service_net_cleanup(struct netns_ipvs *ipvs); /* IPVS application functions -- cgit v1.2.3 From 0f34d54bf48892f23e2abef2f9fd8d0237db4623 Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Mon, 21 Sep 2015 13:02:23 -0500 Subject: ipvs: Pass ipvs not net to ip_vs_start_estimator aned ip_vs_stop_estimator Signed-off-by: "Eric W. Biederman" Acked-by: Julian Anastasov Signed-off-by: Simon Horman --- include/net/ip_vs.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/net/ip_vs.h b/include/net/ip_vs.h index f3ddf7696d68..2d49357b328c 100644 --- a/include/net/ip_vs.h +++ b/include/net/ip_vs.h @@ -1455,8 +1455,8 @@ int stop_sync_thread(struct netns_ipvs *ipvs, int state); void ip_vs_sync_conn(struct netns_ipvs *ipvs, struct ip_vs_conn *cp, int pkts); /* IPVS rate estimator prototypes (from ip_vs_est.c) */ -void ip_vs_start_estimator(struct net *net, struct ip_vs_stats *stats); -void ip_vs_stop_estimator(struct net *net, struct ip_vs_stats *stats); +void ip_vs_start_estimator(struct netns_ipvs *ipvs, struct ip_vs_stats *stats); +void ip_vs_stop_estimator(struct netns_ipvs *ipvs, struct ip_vs_stats *stats); void ip_vs_zero_estimator(struct ip_vs_stats *stats); void ip_vs_read_estimator(struct ip_vs_kstats *dst, struct ip_vs_stats *stats); -- cgit v1.2.3 From 423b55954de222380a6b63c5b6ae7b6686e98e63 Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Mon, 21 Sep 2015 13:02:24 -0500 Subject: ipvs: Pass ipvs not net to ip_vs_random_drop_entry Signed-off-by: "Eric W. Biederman" Acked-by: Julian Anastasov Signed-off-by: Simon Horman --- include/net/ip_vs.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/net/ip_vs.h b/include/net/ip_vs.h index 2d49357b328c..c88a3bf85f98 100644 --- a/include/net/ip_vs.h +++ b/include/net/ip_vs.h @@ -1258,7 +1258,7 @@ const char *ip_vs_state_name(__u16 proto, int state); void ip_vs_tcp_conn_listen(struct net *net, struct ip_vs_conn *cp); int ip_vs_check_template(struct ip_vs_conn *ct); -void ip_vs_random_dropentry(struct net *net); +void ip_vs_random_dropentry(struct netns_ipvs *ipvs); int ip_vs_conn_init(void); void ip_vs_conn_cleanup(void); -- cgit v1.2.3 From 3d99376689ee40d4e88c90d26588268a4fccb383 Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Mon, 21 Sep 2015 13:02:26 -0500 Subject: ipvs: Pass ipvs not net into ip_vs_control_net_(init|cleanup) Signed-off-by: "Eric W. Biederman" Acked-by: Julian Anastasov Signed-off-by: Simon Horman --- include/net/ip_vs.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/net/ip_vs.h b/include/net/ip_vs.h index c88a3bf85f98..38c1fca0c1a7 100644 --- a/include/net/ip_vs.h +++ b/include/net/ip_vs.h @@ -1324,7 +1324,7 @@ ip_vs_control_add(struct ip_vs_conn *cp, struct ip_vs_conn *ctl_cp) /* IPVS netns init & cleanup functions */ int ip_vs_estimator_net_init(struct net *net); -int ip_vs_control_net_init(struct net *net); +int ip_vs_control_net_init(struct netns_ipvs *ipvs); int ip_vs_protocol_net_init(struct net *net); int ip_vs_app_net_init(struct net *net); int ip_vs_conn_net_init(struct net *net); @@ -1332,7 +1332,7 @@ int ip_vs_sync_net_init(struct netns_ipvs *ipvs); void ip_vs_conn_net_cleanup(struct net *net); void ip_vs_app_net_cleanup(struct net *net); void ip_vs_protocol_net_cleanup(struct net *net); -void ip_vs_control_net_cleanup(struct net *net); +void ip_vs_control_net_cleanup(struct netns_ipvs *ipvs); void ip_vs_estimator_net_cleanup(struct net *net); void ip_vs_sync_net_cleanup(struct netns_ipvs *ipvs); void ip_vs_service_net_cleanup(struct netns_ipvs *ipvs); -- cgit v1.2.3 From a4dd0360c623e5beac011f3674ff7e13b35b5b05 Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Mon, 21 Sep 2015 13:02:28 -0500 Subject: ipvs: Pass ipvs not net to ip_vs_estimator_net_init and ip_vs_estimator_cleanup Signed-off-by: "Eric W. Biederman" Acked-by: Julian Anastasov Signed-off-by: Simon Horman --- include/net/ip_vs.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/net/ip_vs.h b/include/net/ip_vs.h index 38c1fca0c1a7..02734eaae679 100644 --- a/include/net/ip_vs.h +++ b/include/net/ip_vs.h @@ -1323,7 +1323,7 @@ ip_vs_control_add(struct ip_vs_conn *cp, struct ip_vs_conn *ctl_cp) } /* IPVS netns init & cleanup functions */ -int ip_vs_estimator_net_init(struct net *net); +int ip_vs_estimator_net_init(struct netns_ipvs *ipvs); int ip_vs_control_net_init(struct netns_ipvs *ipvs); int ip_vs_protocol_net_init(struct net *net); int ip_vs_app_net_init(struct net *net); @@ -1333,7 +1333,7 @@ void ip_vs_conn_net_cleanup(struct net *net); void ip_vs_app_net_cleanup(struct net *net); void ip_vs_protocol_net_cleanup(struct net *net); void ip_vs_control_net_cleanup(struct netns_ipvs *ipvs); -void ip_vs_estimator_net_cleanup(struct net *net); +void ip_vs_estimator_net_cleanup(struct netns_ipvs *ipvs); void ip_vs_sync_net_cleanup(struct netns_ipvs *ipvs); void ip_vs_service_net_cleanup(struct netns_ipvs *ipvs); -- cgit v1.2.3 From 19648918fbf245ab2dda8c7842c9a83fd412ac35 Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Mon, 21 Sep 2015 13:02:29 -0500 Subject: ipvs: Pass ipvs not net into register_app and unregister_app Signed-off-by: "Eric W. Biederman" Acked-by: Julian Anastasov Signed-off-by: Simon Horman --- include/net/ip_vs.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/net/ip_vs.h b/include/net/ip_vs.h index 02734eaae679..a7275ae18b96 100644 --- a/include/net/ip_vs.h +++ b/include/net/ip_vs.h @@ -517,9 +517,9 @@ struct ip_vs_protocol { const struct sk_buff *skb, struct ip_vs_proto_data *pd); - int (*register_app)(struct net *net, struct ip_vs_app *inc); + int (*register_app)(struct netns_ipvs *ipvs, struct ip_vs_app *inc); - void (*unregister_app)(struct net *net, struct ip_vs_app *inc); + void (*unregister_app)(struct netns_ipvs *ipvs, struct ip_vs_app *inc); int (*app_conn_bind)(struct ip_vs_conn *cp); -- cgit v1.2.3 From 3250dc9c52045dd3f38297d1e189cc147a8db884 Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Mon, 21 Sep 2015 13:02:31 -0500 Subject: ipvs: Pass ipvs not net to register_ip_vs_app_inc Signed-off-by: "Eric W. Biederman" Acked-by: Julian Anastasov Signed-off-by: Simon Horman --- include/net/ip_vs.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/net/ip_vs.h b/include/net/ip_vs.h index a7275ae18b96..c06bad39958d 100644 --- a/include/net/ip_vs.h +++ b/include/net/ip_vs.h @@ -1345,7 +1345,7 @@ struct ip_vs_app *register_ip_vs_app(struct net *net, struct ip_vs_app *app); void unregister_ip_vs_app(struct net *net, struct ip_vs_app *app); int ip_vs_bind_app(struct ip_vs_conn *cp, struct ip_vs_protocol *pp); void ip_vs_unbind_app(struct ip_vs_conn *cp); -int register_ip_vs_app_inc(struct net *net, struct ip_vs_app *app, __u16 proto, +int register_ip_vs_app_inc(struct netns_ipvs *ipvs, struct ip_vs_app *app, __u16 proto, __u16 port); int ip_vs_app_inc_get(struct ip_vs_app *inc); void ip_vs_app_inc_put(struct ip_vs_app *inc); -- cgit v1.2.3 From 9f8128a56ef241753ea038e92948fe13beacf59f Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Mon, 21 Sep 2015 13:02:32 -0500 Subject: ipvs: Pass ipvs not net to register_ip_vs_app and unregister_ip_vs_app Also move the tests for net_ipvs being NULL into __ip_vs_ftp_init and __ip_vs_ftp_exit. The only places where they possibly make sense. Signed-off-by: "Eric W. Biederman" Acked-by: Julian Anastasov Signed-off-by: Simon Horman --- include/net/ip_vs.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/net/ip_vs.h b/include/net/ip_vs.h index c06bad39958d..5caafed5af2e 100644 --- a/include/net/ip_vs.h +++ b/include/net/ip_vs.h @@ -1341,8 +1341,8 @@ void ip_vs_service_net_cleanup(struct netns_ipvs *ipvs); * (from ip_vs_app.c) */ #define IP_VS_APP_MAX_PORTS 8 -struct ip_vs_app *register_ip_vs_app(struct net *net, struct ip_vs_app *app); -void unregister_ip_vs_app(struct net *net, struct ip_vs_app *app); +struct ip_vs_app *register_ip_vs_app(struct netns_ipvs *ipvs, struct ip_vs_app *app); +void unregister_ip_vs_app(struct netns_ipvs *ipvs, struct ip_vs_app *app); int ip_vs_bind_app(struct ip_vs_conn *cp, struct ip_vs_protocol *pp); void ip_vs_unbind_app(struct ip_vs_conn *cp); int register_ip_vs_app_inc(struct netns_ipvs *ipvs, struct ip_vs_app *app, __u16 proto, -- cgit v1.2.3 From b5dd212cc147603372d39dbe52480d687c98da7d Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Mon, 21 Sep 2015 13:02:34 -0500 Subject: ipvs: Pass ipvs not net into ip_vs_app_net_init and ip_vs_app_net_cleanup Signed-off-by: "Eric W. Biederman" Acked-by: Julian Anastasov Signed-off-by: Simon Horman --- include/net/ip_vs.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/net/ip_vs.h b/include/net/ip_vs.h index 5caafed5af2e..728a670d69fd 100644 --- a/include/net/ip_vs.h +++ b/include/net/ip_vs.h @@ -1326,11 +1326,11 @@ ip_vs_control_add(struct ip_vs_conn *cp, struct ip_vs_conn *ctl_cp) int ip_vs_estimator_net_init(struct netns_ipvs *ipvs); int ip_vs_control_net_init(struct netns_ipvs *ipvs); int ip_vs_protocol_net_init(struct net *net); -int ip_vs_app_net_init(struct net *net); +int ip_vs_app_net_init(struct netns_ipvs *ipvs); int ip_vs_conn_net_init(struct net *net); int ip_vs_sync_net_init(struct netns_ipvs *ipvs); void ip_vs_conn_net_cleanup(struct net *net); -void ip_vs_app_net_cleanup(struct net *net); +void ip_vs_app_net_cleanup(struct netns_ipvs *ipvs); void ip_vs_protocol_net_cleanup(struct net *net); void ip_vs_control_net_cleanup(struct netns_ipvs *ipvs); void ip_vs_estimator_net_cleanup(struct netns_ipvs *ipvs); -- cgit v1.2.3 From 1281a9c2d181a932ae2f59f5711ae087a58f1c13 Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Mon, 21 Sep 2015 13:02:36 -0500 Subject: ipvs: Pass ipvs not net into init_netns and exit_netns Signed-off-by: "Eric W. Biederman" Acked-by: Julian Anastasov Signed-off-by: Simon Horman --- include/net/ip_vs.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/net/ip_vs.h b/include/net/ip_vs.h index 728a670d69fd..fe3373c9bb3b 100644 --- a/include/net/ip_vs.h +++ b/include/net/ip_vs.h @@ -483,9 +483,9 @@ struct ip_vs_protocol { void (*exit)(struct ip_vs_protocol *pp); - int (*init_netns)(struct net *net, struct ip_vs_proto_data *pd); + int (*init_netns)(struct netns_ipvs *ipvs, struct ip_vs_proto_data *pd); - void (*exit_netns)(struct net *net, struct ip_vs_proto_data *pd); + void (*exit_netns)(struct netns_ipvs *ipvs, struct ip_vs_proto_data *pd); int (*conn_schedule)(int af, struct sk_buff *skb, struct ip_vs_proto_data *pd, -- cgit v1.2.3 From ab161976421585812bcdab6592852b1b5b7dec1f Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Mon, 21 Sep 2015 13:02:38 -0500 Subject: ipvs: Pass ipvs into .conn_in_get and ip_vs_conn_in_get_proto Stop relying on "net_ipvs(skb_net(skb))" to derive the ipvs as skb_net is a hack. Signed-off-by: "Eric W. Biederman" Acked-by: Julian Anastasov Signed-off-by: Simon Horman --- include/net/ip_vs.h | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/net/ip_vs.h b/include/net/ip_vs.h index fe3373c9bb3b..5c26383542e3 100644 --- a/include/net/ip_vs.h +++ b/include/net/ip_vs.h @@ -493,7 +493,8 @@ struct ip_vs_protocol { struct ip_vs_iphdr *iph); struct ip_vs_conn * - (*conn_in_get)(int af, + (*conn_in_get)(struct netns_ipvs *ipvs, + int af, const struct sk_buff *skb, const struct ip_vs_iphdr *iph); @@ -1222,7 +1223,8 @@ static inline void ip_vs_conn_fill_param(struct netns_ipvs *ipvs, int af, int pr struct ip_vs_conn *ip_vs_conn_in_get(const struct ip_vs_conn_param *p); struct ip_vs_conn *ip_vs_ct_in_get(const struct ip_vs_conn_param *p); -struct ip_vs_conn * ip_vs_conn_in_get_proto(int af, const struct sk_buff *skb, +struct ip_vs_conn * ip_vs_conn_in_get_proto(struct netns_ipvs *ipvs, int af, + const struct sk_buff *skb, const struct ip_vs_iphdr *iph); struct ip_vs_conn *ip_vs_conn_out_get(const struct ip_vs_conn_param *p); -- cgit v1.2.3 From 0cf705c8c2e8333aff5b472cfff13f9542620500 Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Mon, 21 Sep 2015 13:02:39 -0500 Subject: ipvs: Pass ipvs into conn_out_get Move the hack of relying on "net_ipvs(skb_net(skb))" to derive the ipvs up a layer. Signed-off-by: "Eric W. Biederman" Acked-by: Julian Anastasov Signed-off-by: Simon Horman --- include/net/ip_vs.h | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/net/ip_vs.h b/include/net/ip_vs.h index 5c26383542e3..0ca436ef7dad 100644 --- a/include/net/ip_vs.h +++ b/include/net/ip_vs.h @@ -499,7 +499,8 @@ struct ip_vs_protocol { const struct ip_vs_iphdr *iph); struct ip_vs_conn * - (*conn_out_get)(int af, + (*conn_out_get)(struct netns_ipvs *ipvs, + int af, const struct sk_buff *skb, const struct ip_vs_iphdr *iph); @@ -1229,7 +1230,8 @@ struct ip_vs_conn * ip_vs_conn_in_get_proto(struct netns_ipvs *ipvs, int af, struct ip_vs_conn *ip_vs_conn_out_get(const struct ip_vs_conn_param *p); -struct ip_vs_conn * ip_vs_conn_out_get_proto(int af, const struct sk_buff *skb, +struct ip_vs_conn * ip_vs_conn_out_get_proto(struct netns_ipvs *ipvs, int af, + const struct sk_buff *skb, const struct ip_vs_iphdr *iph); /* Get reference to gain full access to conn. -- cgit v1.2.3 From 2f3edc6a5bb2a570f491e8e8a4a16526aff3675b Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Mon, 21 Sep 2015 13:02:42 -0500 Subject: ipvs: Pass ipvs not net into ip_vs_conn_net_init and ip_vs_conn_net_cleanup Signed-off-by: "Eric W. Biederman" Acked-by: Julian Anastasov Signed-off-by: Simon Horman --- include/net/ip_vs.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/net/ip_vs.h b/include/net/ip_vs.h index 0ca436ef7dad..5ad04be64895 100644 --- a/include/net/ip_vs.h +++ b/include/net/ip_vs.h @@ -1331,9 +1331,9 @@ int ip_vs_estimator_net_init(struct netns_ipvs *ipvs); int ip_vs_control_net_init(struct netns_ipvs *ipvs); int ip_vs_protocol_net_init(struct net *net); int ip_vs_app_net_init(struct netns_ipvs *ipvs); -int ip_vs_conn_net_init(struct net *net); +int ip_vs_conn_net_init(struct netns_ipvs *ipvs); int ip_vs_sync_net_init(struct netns_ipvs *ipvs); -void ip_vs_conn_net_cleanup(struct net *net); +void ip_vs_conn_net_cleanup(struct netns_ipvs *ipvs); void ip_vs_app_net_cleanup(struct netns_ipvs *ipvs); void ip_vs_protocol_net_cleanup(struct net *net); void ip_vs_control_net_cleanup(struct netns_ipvs *ipvs); -- cgit v1.2.3 From d8f44c335a1111d647f41e9fa6ae65b18db112e4 Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Mon, 21 Sep 2015 13:02:43 -0500 Subject: ipvs: Pass ipvs into .conn_schedule and ip_vs_try_to_schedule This moves the hack "net_ipvs(skb_net(skb))" up one level where it will be easier to remove. Signed-off-by: "Eric W. Biederman" Acked-by: Julian Anastasov Signed-off-by: Simon Horman --- include/net/ip_vs.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/net/ip_vs.h b/include/net/ip_vs.h index 5ad04be64895..c68c2c8ae48a 100644 --- a/include/net/ip_vs.h +++ b/include/net/ip_vs.h @@ -487,7 +487,8 @@ struct ip_vs_protocol { void (*exit_netns)(struct netns_ipvs *ipvs, struct ip_vs_proto_data *pd); - int (*conn_schedule)(int af, struct sk_buff *skb, + int (*conn_schedule)(struct netns_ipvs *ipvs, + int af, struct sk_buff *skb, struct ip_vs_proto_data *pd, int *verdict, struct ip_vs_conn **cpp, struct ip_vs_iphdr *iph); -- cgit v1.2.3 From 570329487437d4531eb806accdf98726923367ae Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Mon, 21 Sep 2015 13:02:49 -0500 Subject: ipvs: Wrap sysctl_cache_bypass and remove ifdefs in ip_vs_leave With sysctl_cache_bypass now a compile time constant the compiler can figue out that it can elimiate all of the code that depends on sysctl_cache_bypass being true. Also remove the duplicate computation of net previously necessitated by #ifdef CONFIG_SYSCTL Signed-off-by: "Eric W. Biederman" Acked-by: Julian Anastasov Signed-off-by: Simon Horman --- include/net/ip_vs.h | 10 ++++++++++ 1 file changed, 10 insertions(+) (limited to 'include') diff --git a/include/net/ip_vs.h b/include/net/ip_vs.h index c68c2c8ae48a..dacd873e8bb9 100644 --- a/include/net/ip_vs.h +++ b/include/net/ip_vs.h @@ -1101,6 +1101,11 @@ static inline int sysctl_ignore_tunneled(struct netns_ipvs *ipvs) return ipvs->sysctl_ignore_tunneled; } +static inline int sysctl_cache_bypass(struct netns_ipvs *ipvs) +{ + return ipvs->sysctl_cache_bypass; +} + #else static inline int sysctl_sync_threshold(struct netns_ipvs *ipvs) @@ -1183,6 +1188,11 @@ static inline int sysctl_ignore_tunneled(struct netns_ipvs *ipvs) return 0; } +static inline int sysctl_cache_bypass(struct netns_ipvs *ipvs) +{ + return 0; +} + #endif /* IPVS core functions -- cgit v1.2.3 From 69f390934b26154573fc7c360645ced8b0c7871a Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Mon, 21 Sep 2015 13:02:57 -0500 Subject: ipvs: Remove net argument from ip_vs_tcp_conn_listen The argument is unnecessary and in practice confusing, and has caused the callers to do all manner of silly things. Signed-off-by: "Eric W. Biederman" Acked-by: Julian Anastasov Signed-off-by: Simon Horman --- include/net/ip_vs.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/net/ip_vs.h b/include/net/ip_vs.h index dacd873e8bb9..f0a39ce3bf0e 100644 --- a/include/net/ip_vs.h +++ b/include/net/ip_vs.h @@ -1271,7 +1271,7 @@ void ip_vs_conn_expire_now(struct ip_vs_conn *cp); const char *ip_vs_state_name(__u16 proto, int state); -void ip_vs_tcp_conn_listen(struct net *net, struct ip_vs_conn *cp); +void ip_vs_tcp_conn_listen(struct ip_vs_conn *cp); int ip_vs_check_template(struct ip_vs_conn *ct); void ip_vs_random_dropentry(struct netns_ipvs *ipvs); int ip_vs_conn_init(void); -- cgit v1.2.3 From 7d1f88eca0ae7228bdbd971f060603b3a1270693 Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Mon, 21 Sep 2015 13:02:58 -0500 Subject: ipvs: Pass ipvs not net to ip_vs_protocol_net_(init|cleanup) Signed-off-by: "Eric W. Biederman" Acked-by: Julian Anastasov Signed-off-by: Simon Horman --- include/net/ip_vs.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/net/ip_vs.h b/include/net/ip_vs.h index f0a39ce3bf0e..00318d63a565 100644 --- a/include/net/ip_vs.h +++ b/include/net/ip_vs.h @@ -1340,13 +1340,13 @@ ip_vs_control_add(struct ip_vs_conn *cp, struct ip_vs_conn *ctl_cp) /* IPVS netns init & cleanup functions */ int ip_vs_estimator_net_init(struct netns_ipvs *ipvs); int ip_vs_control_net_init(struct netns_ipvs *ipvs); -int ip_vs_protocol_net_init(struct net *net); +int ip_vs_protocol_net_init(struct netns_ipvs *ipvs); int ip_vs_app_net_init(struct netns_ipvs *ipvs); int ip_vs_conn_net_init(struct netns_ipvs *ipvs); int ip_vs_sync_net_init(struct netns_ipvs *ipvs); void ip_vs_conn_net_cleanup(struct netns_ipvs *ipvs); void ip_vs_app_net_cleanup(struct netns_ipvs *ipvs); -void ip_vs_protocol_net_cleanup(struct net *net); +void ip_vs_protocol_net_cleanup(struct netns_ipvs *ipvs); void ip_vs_control_net_cleanup(struct netns_ipvs *ipvs); void ip_vs_estimator_net_cleanup(struct netns_ipvs *ipvs); void ip_vs_sync_net_cleanup(struct netns_ipvs *ipvs); -- cgit v1.2.3 From 7c6c21ee94452081a5219667851d2084a45c5009 Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Mon, 21 Sep 2015 13:02:59 -0500 Subject: ipvs: Remove skb_net This hack has no more users so remove it. Signed-off-by: "Eric W. Biederman" Acked-by: Julian Anastasov Signed-off-by: Simon Horman --- include/net/ip_vs.h | 31 ------------------------------- 1 file changed, 31 deletions(-) (limited to 'include') diff --git a/include/net/ip_vs.h b/include/net/ip_vs.h index 00318d63a565..d621330d423c 100644 --- a/include/net/ip_vs.h +++ b/include/net/ip_vs.h @@ -38,37 +38,6 @@ static inline struct netns_ipvs *net_ipvs(struct net* net) return net->ipvs; } -/* Get net ptr from skb in traffic cases - * use skb_sknet when call is from userland (ioctl or netlink) - */ -static inline struct net *skb_net(const struct sk_buff *skb) -{ -#ifdef CONFIG_NET_NS -#ifdef CONFIG_IP_VS_DEBUG - /* - * This is used for debug only. - * Start with the most likely hit - * End with BUG - */ - if (likely(skb->dev && dev_net(skb->dev))) - return dev_net(skb->dev); - if (skb_dst(skb) && skb_dst(skb)->dev) - return dev_net(skb_dst(skb)->dev); - WARN(skb->sk, "Maybe skb_sknet should be used in %s() at line:%d\n", - __func__, __LINE__); - if (likely(skb->sk && sock_net(skb->sk))) - return sock_net(skb->sk); - pr_err("There is no net ptr to find in the skb in %s() line:%d\n", - __func__, __LINE__); - BUG(); -#else - return dev_net(skb->dev ? : skb_dst(skb)->dev); -#endif -#else - return &init_net; -#endif -} - static inline struct net *skb_sknet(const struct sk_buff *skb) { #ifdef CONFIG_NET_NS -- cgit v1.2.3 From 9cfdd75b7c049895317aebb0e27f8112e7e31593 Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Mon, 21 Sep 2015 13:03:00 -0500 Subject: ipvs: Remove skb_sknet This function adds no real value and it obscures what the code is doing. Signed-off-by: "Eric W. Biederman" Acked-by: Julian Anastasov Signed-off-by: Simon Horman --- include/net/ip_vs.h | 22 ---------------------- 1 file changed, 22 deletions(-) (limited to 'include') diff --git a/include/net/ip_vs.h b/include/net/ip_vs.h index d621330d423c..0816c872b689 100644 --- a/include/net/ip_vs.h +++ b/include/net/ip_vs.h @@ -38,28 +38,6 @@ static inline struct netns_ipvs *net_ipvs(struct net* net) return net->ipvs; } -static inline struct net *skb_sknet(const struct sk_buff *skb) -{ -#ifdef CONFIG_NET_NS -#ifdef CONFIG_IP_VS_DEBUG - /* Start with the most likely hit */ - if (likely(skb->sk && sock_net(skb->sk))) - return sock_net(skb->sk); - WARN(skb->dev, "Maybe skb_net should be used instead in %s() line:%d\n", - __func__, __LINE__); - if (likely(skb->dev && dev_net(skb->dev))) - return dev_net(skb->dev); - pr_err("There is no net ptr to find in the skb in %s() line:%d\n", - __func__, __LINE__); - BUG(); -#else - return sock_net(skb->sk); -#endif -#else - return &init_net; -#endif -} - /* This one needed for single_open_net since net is stored directly in * private not as a struct i.e. seq_file_net can't be used. */ -- cgit v1.2.3 From 594b31ea7dc6101519deee1b31483fce2e1a7414 Mon Sep 17 00:00:00 2001 From: Frederic Danis Date: Wed, 23 Sep 2015 18:18:07 +0200 Subject: Bluetooth: Add BT_WARN and bt_dev_warn logging macros Add warning logging macros to bluetooth subsystem logs. Signed-off-by: Frederic Danis Signed-off-by: Marcel Holtmann --- include/net/bluetooth/bluetooth.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include') diff --git a/include/net/bluetooth/bluetooth.h b/include/net/bluetooth/bluetooth.h index f5ade8573393..c4defef319d5 100644 --- a/include/net/bluetooth/bluetooth.h +++ b/include/net/bluetooth/bluetooth.h @@ -122,11 +122,14 @@ struct bt_voice { __printf(1, 2) void bt_info(const char *fmt, ...); __printf(1, 2) +void bt_warn(const char *fmt, ...); +__printf(1, 2) void bt_err(const char *fmt, ...); __printf(1, 2) void bt_err_ratelimited(const char *fmt, ...); #define BT_INFO(fmt, ...) bt_info(fmt "\n", ##__VA_ARGS__) +#define BT_WARN(fmt, ...) bt_warn(fmt "\n", ##__VA_ARGS__) #define BT_ERR(fmt, ...) bt_err(fmt "\n", ##__VA_ARGS__) #define BT_DBG(fmt, ...) pr_debug(fmt "\n", ##__VA_ARGS__) @@ -134,6 +137,8 @@ void bt_err_ratelimited(const char *fmt, ...); #define bt_dev_info(hdev, fmt, ...) \ BT_INFO("%s: " fmt, (hdev)->name, ##__VA_ARGS__) +#define bt_dev_warn(hdev, fmt, ...) \ + BT_WARN("%s: " fmt, (hdev)->name, ##__VA_ARGS__) #define bt_dev_err(hdev, fmt, ...) \ BT_ERR("%s: " fmt, (hdev)->name, ##__VA_ARGS__) #define bt_dev_dbg(hdev, fmt, ...) \ -- cgit v1.2.3 From f856f21dbcd162a53e30987a91d75d5ab54a7f80 Mon Sep 17 00:00:00 2001 From: Alexander Aring Date: Thu, 24 Sep 2015 09:37:10 +0200 Subject: ieee802154: remove unnecessary includes This patch removes some unnecessary includes from ieee802154 header, which was introduced by commit b609fb54adfa ("ieee802154: add helpers for frame control checks"). Signed-off-by: Alexander Aring Signed-off-by: Marcel Holtmann --- include/linux/ieee802154.h | 3 --- 1 file changed, 3 deletions(-) (limited to 'include') diff --git a/include/linux/ieee802154.h b/include/linux/ieee802154.h index aca228b81464..d3e415674dac 100644 --- a/include/linux/ieee802154.h +++ b/include/linux/ieee802154.h @@ -25,9 +25,6 @@ #include #include -#include -#include -#include #define IEEE802154_MTU 127 #define IEEE802154_ACK_PSDU_LEN 5 -- cgit v1.2.3 From 92c14d9b5ee86fd6cf136c01b6a87353522aebdd Mon Sep 17 00:00:00 2001 From: Jiri Benc Date: Tue, 22 Sep 2015 18:56:43 +0200 Subject: genetlink: simplify genl_notify The genl_notify function has too many arguments for no real reason - all callers use genl_info to get them anyway. Just pass the genl_info down to genl_notify. Signed-off-by: Jiri Benc Signed-off-by: David S. Miller --- include/net/genetlink.h | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/include/net/genetlink.h b/include/net/genetlink.h index a9af1cc8c1bc..1b6b6dcb018d 100644 --- a/include/net/genetlink.h +++ b/include/net/genetlink.h @@ -183,9 +183,8 @@ _genl_register_family_with_ops_grps(struct genl_family *family, (grps), ARRAY_SIZE(grps)) int genl_unregister_family(struct genl_family *family); -void genl_notify(struct genl_family *family, - struct sk_buff *skb, struct net *net, u32 portid, - u32 group, struct nlmsghdr *nlh, gfp_t flags); +void genl_notify(struct genl_family *family, struct sk_buff *skb, + struct genl_info *info, u32 group, gfp_t flags); struct sk_buff *genlmsg_new_unicast(size_t payload, struct genl_info *info, gfp_t flags); -- cgit v1.2.3 From 38cf595b195552276e1cf1826434e05782de4be8 Mon Sep 17 00:00:00 2001 From: Jiri Benc Date: Tue, 22 Sep 2015 18:57:13 +0200 Subject: ipv6: remove unused neigh parameter from ndisc functions Since commit 12fd84f4383b1 ("ipv6: Remove unused neigh argument for icmp6_dst_alloc() and its callers."), the neigh parameter of ndisc_send_na and ndisc_send_ns is unused. CC: YOSHIFUJI Hideaki Signed-off-by: Jiri Benc Signed-off-by: David S. Miller --- include/net/addrconf.h | 3 +-- include/net/ndisc.h | 6 ++---- 2 files changed, 3 insertions(+), 6 deletions(-) (limited to 'include') diff --git a/include/net/addrconf.h b/include/net/addrconf.h index b5474b1fcd83..78003dfb8539 100644 --- a/include/net/addrconf.h +++ b/include/net/addrconf.h @@ -192,8 +192,7 @@ struct ipv6_stub { int (*ipv6_dst_lookup)(struct net *net, struct sock *sk, struct dst_entry **dst, struct flowi6 *fl6); void (*udpv6_encap_enable)(void); - void (*ndisc_send_na)(struct net_device *dev, struct neighbour *neigh, - const struct in6_addr *daddr, + void (*ndisc_send_na)(struct net_device *dev, const struct in6_addr *daddr, const struct in6_addr *solicited_addr, bool router, bool solicited, bool override, bool inc_opt); struct neigh_table *nd_tbl; diff --git a/include/net/ndisc.h b/include/net/ndisc.h index aba5695fadb0..bf3937431030 100644 --- a/include/net/ndisc.h +++ b/include/net/ndisc.h @@ -180,15 +180,13 @@ void ndisc_cleanup(void); int ndisc_rcv(struct sk_buff *skb); -void ndisc_send_ns(struct net_device *dev, struct neighbour *neigh, - const struct in6_addr *solicit, +void ndisc_send_ns(struct net_device *dev, const struct in6_addr *solicit, const struct in6_addr *daddr, const struct in6_addr *saddr, struct sk_buff *oskb); void ndisc_send_rs(struct net_device *dev, const struct in6_addr *saddr, const struct in6_addr *daddr); -void ndisc_send_na(struct net_device *dev, struct neighbour *neigh, - const struct in6_addr *daddr, +void ndisc_send_na(struct net_device *dev, const struct in6_addr *daddr, const struct in6_addr *solicited_addr, bool router, bool solicited, bool override, bool inc_opt); -- cgit v1.2.3 From 69f5df491e0becb75d2d795add7481a35218d657 Mon Sep 17 00:00:00 2001 From: Jiri Pirko Date: Thu, 24 Sep 2015 10:02:40 +0200 Subject: switchdev: rename "trans" to "trans_ph". This is temporary, name "trans" will be used for something else and "trans_ph" will eventually disappear. Signed-off-by: Jiri Pirko Signed-off-by: David S. Miller --- include/net/switchdev.h | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/include/net/switchdev.h b/include/net/switchdev.h index 319baab3b48e..494f51097dc6 100644 --- a/include/net/switchdev.h +++ b/include/net/switchdev.h @@ -16,7 +16,7 @@ #define SWITCHDEV_F_NO_RECURSE BIT(0) -enum switchdev_trans { +enum switchdev_trans_ph { SWITCHDEV_TRANS_NONE, SWITCHDEV_TRANS_PREPARE, SWITCHDEV_TRANS_ABORT, @@ -32,7 +32,7 @@ enum switchdev_attr_id { struct switchdev_attr { enum switchdev_attr_id id; - enum switchdev_trans trans; + enum switchdev_trans_ph trans_ph; u32 flags; union { struct netdev_phys_item_id ppid; /* PORT_PARENT_ID */ @@ -52,7 +52,7 @@ enum switchdev_obj_id { struct switchdev_obj { enum switchdev_obj_id id; - enum switchdev_trans trans; + enum switchdev_trans_ph trans_ph; int (*cb)(struct net_device *dev, struct switchdev_obj *obj); union { struct switchdev_obj_vlan { /* PORT_VLAN */ -- cgit v1.2.3 From 7ea6eb3f56f45cf4babae8b9a7421868e5005f17 Mon Sep 17 00:00:00 2001 From: Jiri Pirko Date: Thu, 24 Sep 2015 10:02:41 +0200 Subject: switchdev: introduce transaction item queue for attr_set and obj_add Now, the memory allocation in prepare/commit state is done separatelly in each driver (rocker). Introduce the similar mechanism in generic switchdev code, in form of queue. That can be used not only for memory allocations, but also for different items. Abort item destruction is handled as well. Signed-off-by: Jiri Pirko Signed-off-by: David S. Miller --- include/net/switchdev.h | 24 +++++++++++++++++++++--- 1 file changed, 21 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/include/net/switchdev.h b/include/net/switchdev.h index 494f51097dc6..1e394f1176b6 100644 --- a/include/net/switchdev.h +++ b/include/net/switchdev.h @@ -1,6 +1,6 @@ /* * include/net/switchdev.h - Switch device API - * Copyright (c) 2014 Jiri Pirko + * Copyright (c) 2014-2015 Jiri Pirko * Copyright (c) 2014-2015 Scott Feldman * * This program is free software; you can redistribute it and/or modify @@ -13,6 +13,7 @@ #include #include +#include #define SWITCHDEV_F_NO_RECURSE BIT(0) @@ -23,6 +24,16 @@ enum switchdev_trans_ph { SWITCHDEV_TRANS_COMMIT, }; +struct switchdev_trans_item { + struct list_head list; + void *data; + void (*destructor)(const void *data); +}; + +struct switchdev_trans { + struct list_head item_list; +}; + enum switchdev_attr_id { SWITCHDEV_ATTR_UNDEFINED, SWITCHDEV_ATTR_PORT_PARENT_ID, @@ -77,6 +88,11 @@ struct switchdev_obj { } u; }; +void switchdev_trans_item_enqueue(struct switchdev_trans *trans, + void *data, void (*destructor)(void const *), + struct switchdev_trans_item *tritem); +void *switchdev_trans_item_dequeue(struct switchdev_trans *trans); + /** * struct switchdev_ops - switchdev operations * @@ -94,9 +110,11 @@ struct switchdev_ops { int (*switchdev_port_attr_get)(struct net_device *dev, struct switchdev_attr *attr); int (*switchdev_port_attr_set)(struct net_device *dev, - struct switchdev_attr *attr); + struct switchdev_attr *attr, + struct switchdev_trans *trans); int (*switchdev_port_obj_add)(struct net_device *dev, - struct switchdev_obj *obj); + struct switchdev_obj *obj, + struct switchdev_trans *trans); int (*switchdev_port_obj_del)(struct net_device *dev, struct switchdev_obj *obj); int (*switchdev_port_obj_dump)(struct net_device *dev, -- cgit v1.2.3 From f8db83486e316ff50f97961a82b614985645508e Mon Sep 17 00:00:00 2001 From: Jiri Pirko Date: Thu, 24 Sep 2015 10:02:42 +0200 Subject: switchdev: move transaction phase enum under transaction structure Before it disappears completely, move transaction phase enum under transaction structure and make attr/obj structures a bit cleaner. Signed-off-by: Jiri Pirko Signed-off-by: David S. Miller --- include/net/switchdev.h | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) (limited to 'include') diff --git a/include/net/switchdev.h b/include/net/switchdev.h index 1e394f1176b6..368a6429198d 100644 --- a/include/net/switchdev.h +++ b/include/net/switchdev.h @@ -32,6 +32,7 @@ struct switchdev_trans_item { struct switchdev_trans { struct list_head item_list; + enum switchdev_trans_ph ph; }; enum switchdev_attr_id { @@ -43,7 +44,6 @@ enum switchdev_attr_id { struct switchdev_attr { enum switchdev_attr_id id; - enum switchdev_trans_ph trans_ph; u32 flags; union { struct netdev_phys_item_id ppid; /* PORT_PARENT_ID */ @@ -63,7 +63,6 @@ enum switchdev_obj_id { struct switchdev_obj { enum switchdev_obj_id id; - enum switchdev_trans_ph trans_ph; int (*cb)(struct net_device *dev, struct switchdev_obj *obj); union { struct switchdev_obj_vlan { /* PORT_VLAN */ -- cgit v1.2.3 From 8bdb427206f077cdb567bf34da2e7212ecb2603c Mon Sep 17 00:00:00 2001 From: Jiri Pirko Date: Thu, 24 Sep 2015 10:02:43 +0200 Subject: switchdev: add switchdev_trans_ph_prepare/commit helpers Add helpers which should be used int attr_set/obj_add switchdev ops to check the phase of transaction. Signed-off-by: Jiri Pirko Signed-off-by: David S. Miller --- include/net/switchdev.h | 10 ++++++++++ 1 file changed, 10 insertions(+) (limited to 'include') diff --git a/include/net/switchdev.h b/include/net/switchdev.h index 368a6429198d..f84ecf4e5d77 100644 --- a/include/net/switchdev.h +++ b/include/net/switchdev.h @@ -35,6 +35,16 @@ struct switchdev_trans { enum switchdev_trans_ph ph; }; +static inline bool switchdev_trans_ph_prepare(struct switchdev_trans *trans) +{ + return trans && trans->ph == SWITCHDEV_TRANS_PREPARE; +} + +static inline bool switchdev_trans_ph_commit(struct switchdev_trans *trans) +{ + return trans && trans->ph == SWITCHDEV_TRANS_COMMIT; +} + enum switchdev_attr_id { SWITCHDEV_ATTR_UNDEFINED, SWITCHDEV_ATTR_PORT_PARENT_ID, -- cgit v1.2.3 From 2b8a61a6fd5fdd161ae16e4f76bfb09d6de95ddd Mon Sep 17 00:00:00 2001 From: Jiri Pirko Date: Thu, 24 Sep 2015 10:02:46 +0200 Subject: switchdev: remove "NONE" transaction phase Shouldn't have been there in the first place. Now it is unused, kill it. Signed-off-by: Jiri Pirko Signed-off-by: David S. Miller --- include/net/switchdev.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include') diff --git a/include/net/switchdev.h b/include/net/switchdev.h index f84ecf4e5d77..f61ee38c7c96 100644 --- a/include/net/switchdev.h +++ b/include/net/switchdev.h @@ -18,7 +18,6 @@ #define SWITCHDEV_F_NO_RECURSE BIT(0) enum switchdev_trans_ph { - SWITCHDEV_TRANS_NONE, SWITCHDEV_TRANS_PREPARE, SWITCHDEV_TRANS_ABORT, SWITCHDEV_TRANS_COMMIT, -- cgit v1.2.3 From 9f6467cf229a0e8a7580401b07de2a76e4c8618d Mon Sep 17 00:00:00 2001 From: Jiri Pirko Date: Thu, 24 Sep 2015 10:02:47 +0200 Subject: switchdev: remove "ABORT" transaction phase No longer used by drivers, as transaction queue with item destructors takes care of abort phase internally in switchdev code. So kill it. Signed-off-by: Jiri Pirko Signed-off-by: David S. Miller --- include/net/switchdev.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include') diff --git a/include/net/switchdev.h b/include/net/switchdev.h index f61ee38c7c96..9cf372fe1365 100644 --- a/include/net/switchdev.h +++ b/include/net/switchdev.h @@ -19,7 +19,6 @@ enum switchdev_trans_ph { SWITCHDEV_TRANS_PREPARE, - SWITCHDEV_TRANS_ABORT, SWITCHDEV_TRANS_COMMIT, }; -- cgit v1.2.3 From f623ab7f51b1bfb523c9cd492747392abf3c4421 Mon Sep 17 00:00:00 2001 From: Jiri Pirko Date: Thu, 24 Sep 2015 10:02:49 +0200 Subject: switchdev: reduce transaction phase enum down to a boolean Now, since we have only 2 values for transaction phase, just use bool. Signed-off-by: Jiri Pirko Signed-off-by: David S. Miller --- include/net/switchdev.h | 11 +++-------- 1 file changed, 3 insertions(+), 8 deletions(-) (limited to 'include') diff --git a/include/net/switchdev.h b/include/net/switchdev.h index 9cf372fe1365..18207878e407 100644 --- a/include/net/switchdev.h +++ b/include/net/switchdev.h @@ -17,11 +17,6 @@ #define SWITCHDEV_F_NO_RECURSE BIT(0) -enum switchdev_trans_ph { - SWITCHDEV_TRANS_PREPARE, - SWITCHDEV_TRANS_COMMIT, -}; - struct switchdev_trans_item { struct list_head list; void *data; @@ -30,17 +25,17 @@ struct switchdev_trans_item { struct switchdev_trans { struct list_head item_list; - enum switchdev_trans_ph ph; + bool ph_prepare; }; static inline bool switchdev_trans_ph_prepare(struct switchdev_trans *trans) { - return trans && trans->ph == SWITCHDEV_TRANS_PREPARE; + return trans && trans->ph_prepare; } static inline bool switchdev_trans_ph_commit(struct switchdev_trans *trans) { - return trans && trans->ph == SWITCHDEV_TRANS_COMMIT; + return trans && !trans->ph_prepare; } enum switchdev_attr_id { -- cgit v1.2.3 From b40cf18ef7961b6d67732e234780586590510ce1 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Fri, 25 Sep 2015 07:39:08 -0700 Subject: tcp: constify listener socket in tcp_v[46]_init_req() Soon, listener socket spinlock will no longer be held, add const arguments to tcp_v[46]_init_req() to make clear these functions can not mess socket fields. Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- include/net/tcp.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/net/tcp.h b/include/net/tcp.h index 5cf9672c13e2..c006255a0df1 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -1705,7 +1705,8 @@ struct tcp_request_sock_ops { const struct sock *sk, const struct sk_buff *skb); #endif - void (*init_req)(struct request_sock *req, struct sock *sk, + void (*init_req)(struct request_sock *req, + const struct sock *sk_listener, struct sk_buff *skb); #ifdef CONFIG_SYN_COOKIES __u32 (*cookie_init_seq)(struct sock *sk, const struct sk_buff *skb, -- cgit v1.2.3 From b1964b5fce389a5660139ca39c25ff294da07b4f Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Fri, 25 Sep 2015 07:39:09 -0700 Subject: tcp: constify tcp_openreq_init_rwin() Soon, listener socket wont be locked when tcp_openreq_init_rwin() is called. We need to read socket fields once, as their value could change under us. Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- include/net/tcp.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/net/tcp.h b/include/net/tcp.h index c006255a0df1..d37ad0c3ea9c 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -1207,7 +1207,8 @@ static inline int tcp_full_space(const struct sock *sk) } extern void tcp_openreq_init_rwin(struct request_sock *req, - struct sock *sk, struct dst_entry *dst); + const struct sock *sk_listener, + const struct dst_entry *dst); void tcp_enter_memory_pressure(struct sock *sk); -- cgit v1.2.3 From 6f9c961546699ff8bc5e1c1c52200616867ec68a Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Fri, 25 Sep 2015 07:39:10 -0700 Subject: inet: constify ip_route_output_flow() socket argument Very soon, TCP stack might call inet_csk_route_req(), which calls inet_csk_route_req() with an unlocked listener socket, so we need to make sure ip_route_output_flow() is not trying to change any field from its socket argument. Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- include/net/dst.h | 9 +++++---- include/net/route.h | 2 +- 2 files changed, 6 insertions(+), 5 deletions(-) (limited to 'include') diff --git a/include/net/dst.h b/include/net/dst.h index df0481a07029..779206c15f8b 100644 --- a/include/net/dst.h +++ b/include/net/dst.h @@ -489,7 +489,8 @@ struct flowi; #ifndef CONFIG_XFRM static inline struct dst_entry *xfrm_lookup(struct net *net, struct dst_entry *dst_orig, - const struct flowi *fl, struct sock *sk, + const struct flowi *fl, + const struct sock *sk, int flags) { return dst_orig; @@ -498,7 +499,7 @@ static inline struct dst_entry *xfrm_lookup(struct net *net, static inline struct dst_entry *xfrm_lookup_route(struct net *net, struct dst_entry *dst_orig, const struct flowi *fl, - struct sock *sk, + const struct sock *sk, int flags) { return dst_orig; @@ -511,11 +512,11 @@ static inline struct xfrm_state *dst_xfrm(const struct dst_entry *dst) #else struct dst_entry *xfrm_lookup(struct net *net, struct dst_entry *dst_orig, - const struct flowi *fl, struct sock *sk, + const struct flowi *fl, const struct sock *sk, int flags); struct dst_entry *xfrm_lookup_route(struct net *net, struct dst_entry *dst_orig, - const struct flowi *fl, struct sock *sk, + const struct flowi *fl, const struct sock *sk, int flags); /* skb attached with this dst needs transformation if dst->xfrm is valid */ diff --git a/include/net/route.h b/include/net/route.h index 10a7d21a211c..414beadc619f 100644 --- a/include/net/route.h +++ b/include/net/route.h @@ -114,7 +114,7 @@ void rt_cache_flush(struct net *net); void rt_flush_dev(struct net_device *dev); struct rtable *__ip_route_output_key(struct net *, struct flowi4 *flp); struct rtable *ip_route_output_flow(struct net *, struct flowi4 *flp, - struct sock *sk); + const struct sock *sk); struct dst_entry *ipv4_blackhole_route(struct net *net, struct dst_entry *dst_orig); -- cgit v1.2.3 From e5895bc600ccba1fde4ea0741813f9c33b5b4021 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Fri, 25 Sep 2015 07:39:11 -0700 Subject: inet: constify inet_csk_route_req() socket argument This is used by TCP listener core, and listener socket shall not be modified by inet_csk_route_req(). Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- include/net/inet_connection_sock.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/net/inet_connection_sock.h b/include/net/inet_connection_sock.h index 0320bbb7d7b5..00c3ced6ee55 100644 --- a/include/net/inet_connection_sock.h +++ b/include/net/inet_connection_sock.h @@ -266,7 +266,7 @@ int inet_csk_bind_conflict(const struct sock *sk, const struct inet_bind_bucket *tb, bool relax); int inet_csk_get_port(struct sock *sk, unsigned short snum); -struct dst_entry *inet_csk_route_req(struct sock *sk, struct flowi4 *fl4, +struct dst_entry *inet_csk_route_req(const struct sock *sk, struct flowi4 *fl4, const struct request_sock *req); struct dst_entry *inet_csk_route_child_sock(struct sock *sk, struct sock *newsk, const struct request_sock *req); -- cgit v1.2.3 From 3aef934f4d4b97532c333d9c1f5f73fb80aeb459 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Fri, 25 Sep 2015 07:39:12 -0700 Subject: ipv6: constify ip6_dst_lookup_{flow|tail}() sock arguments ip6_dst_lookup_flow() and ip6_dst_lookup_tail() do not touch socket, lets add a const qualifier. This will permit the same change in inet6_csk_route_req() Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- include/net/ipv6.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/net/ipv6.h b/include/net/ipv6.h index 384a93cf07d6..9877b68ad207 100644 --- a/include/net/ipv6.h +++ b/include/net/ipv6.h @@ -849,7 +849,7 @@ static inline struct sk_buff *ip6_finish_skb(struct sock *sk) int ip6_dst_lookup(struct net *net, struct sock *sk, struct dst_entry **dst, struct flowi6 *fl6); -struct dst_entry *ip6_dst_lookup_flow(struct sock *sk, struct flowi6 *fl6, +struct dst_entry *ip6_dst_lookup_flow(const struct sock *sk, struct flowi6 *fl6, const struct in6_addr *final_dst); struct dst_entry *ip6_sk_dst_lookup_flow(struct sock *sk, struct flowi6 *fl6, const struct in6_addr *final_dst); -- cgit v1.2.3 From 30d50c61df94bc8d7700272ea09a716e0af8b58b Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Fri, 25 Sep 2015 07:39:13 -0700 Subject: ipv6: constify inet6_csk_route_req() socket argument socket is not modified, make it const so that callers can do the same if they need. Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- include/net/inet6_connection_sock.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/net/inet6_connection_sock.h b/include/net/inet6_connection_sock.h index 6d539e4e5ba7..81d937e820c4 100644 --- a/include/net/inet6_connection_sock.h +++ b/include/net/inet6_connection_sock.h @@ -25,7 +25,7 @@ struct sockaddr; int inet6_csk_bind_conflict(const struct sock *sk, const struct inet_bind_bucket *tb, bool relax); -struct dst_entry *inet6_csk_route_req(struct sock *sk, struct flowi6 *fl6, +struct dst_entry *inet6_csk_route_req(const struct sock *sk, struct flowi6 *fl6, const struct request_sock *req); struct request_sock *inet6_csk_search_req(struct sock *sk, -- cgit v1.2.3 From 4e3f5d727d60939c890a6e86944da52b3a1625ce Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Fri, 25 Sep 2015 07:39:14 -0700 Subject: inet: constify ip_dont_fragment() arguments ip_dont_fragment() can accept const socket and dst Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- include/net/ip.h | 8 +++++--- 1 file changed, 5 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/include/net/ip.h b/include/net/ip.h index 9b9ca2839399..525dc0778926 100644 --- a/include/net/ip.h +++ b/include/net/ip.h @@ -282,10 +282,12 @@ int ip_decrease_ttl(struct iphdr *iph) } static inline -int ip_dont_fragment(struct sock *sk, struct dst_entry *dst) +int ip_dont_fragment(const struct sock *sk, const struct dst_entry *dst) { - return inet_sk(sk)->pmtudisc == IP_PMTUDISC_DO || - (inet_sk(sk)->pmtudisc == IP_PMTUDISC_WANT && + u8 pmtudisc = READ_ONCE(inet_sk(sk)->pmtudisc); + + return pmtudisc == IP_PMTUDISC_DO || + (pmtudisc == IP_PMTUDISC_WANT && !(dst_metric_locked(dst, RTAX_MTU))); } -- cgit v1.2.3 From b83e3deb974ca2c11e21256fe602e517afb83247 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Fri, 25 Sep 2015 07:39:15 -0700 Subject: tcp: md5: constify tcp_md5_do_lookup() socket argument When TCP new listener is done, these functions will be called without socket lock being held. Make sure they don't change anything. Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- include/net/tcp.h | 10 +++++----- 1 file changed, 5 insertions(+), 5 deletions(-) (limited to 'include') diff --git a/include/net/tcp.h b/include/net/tcp.h index d37ad0c3ea9c..45bc3c63c3fd 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -1372,16 +1372,16 @@ int tcp_md5_do_add(struct sock *sk, const union tcp_md5_addr *addr, int family, const u8 *newkey, u8 newkeylen, gfp_t gfp); int tcp_md5_do_del(struct sock *sk, const union tcp_md5_addr *addr, int family); -struct tcp_md5sig_key *tcp_v4_md5_lookup(struct sock *sk, +struct tcp_md5sig_key *tcp_v4_md5_lookup(const struct sock *sk, const struct sock *addr_sk); #ifdef CONFIG_TCP_MD5SIG -struct tcp_md5sig_key *tcp_md5_do_lookup(struct sock *sk, +struct tcp_md5sig_key *tcp_md5_do_lookup(const struct sock *sk, const union tcp_md5_addr *addr, int family); #define tcp_twsk_md5_key(twsk) ((twsk)->tw_md5_key) #else -static inline struct tcp_md5sig_key *tcp_md5_do_lookup(struct sock *sk, +static inline struct tcp_md5sig_key *tcp_md5_do_lookup(const struct sock *sk, const union tcp_md5_addr *addr, int family) { @@ -1684,7 +1684,7 @@ int tcp_conn_request(struct request_sock_ops *rsk_ops, /* TCP af-specific functions */ struct tcp_sock_af_ops { #ifdef CONFIG_TCP_MD5SIG - struct tcp_md5sig_key *(*md5_lookup) (struct sock *sk, + struct tcp_md5sig_key *(*md5_lookup) (const struct sock *sk, const struct sock *addr_sk); int (*calc_md5_hash)(char *location, const struct tcp_md5sig_key *md5, @@ -1699,7 +1699,7 @@ struct tcp_sock_af_ops { struct tcp_request_sock_ops { u16 mss_clamp; #ifdef CONFIG_TCP_MD5SIG - struct tcp_md5sig_key *(*req_md5_lookup)(struct sock *sk, + struct tcp_md5sig_key *(*req_md5_lookup)(const struct sock *sk, const struct sock *addr_sk); int (*calc_md5_hash) (char *location, const struct tcp_md5sig_key *md5, -- cgit v1.2.3 From cfe673b0ae4754ffc051482f4a948b67ddbeec10 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Fri, 25 Sep 2015 07:39:16 -0700 Subject: ip: constify ip_build_and_send_pkt() socket argument This function is used to build and send SYNACK packets, possibly on behalf of unlocked listener socket. Make sure we did not miss a write by making this socket const. We no longer can use ip_select_ident() and have to either set iph->id to 0 or directly call __ip_select_ident() Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- include/net/ip.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/net/ip.h b/include/net/ip.h index 525dc0778926..91a6b2c88341 100644 --- a/include/net/ip.h +++ b/include/net/ip.h @@ -100,7 +100,7 @@ int igmp_mc_init(void); * Functions provided by ip.c */ -int ip_build_and_send_pkt(struct sk_buff *skb, struct sock *sk, +int ip_build_and_send_pkt(struct sk_buff *skb, const struct sock *sk, __be32 saddr, __be32 daddr, struct ip_options_rcu *opt); int ip_rcv(struct sk_buff *skb, struct net_device *dev, struct packet_type *pt, -- cgit v1.2.3 From 5d062de7f8ea1ca7c635957ff1144fba815ba34c Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Fri, 25 Sep 2015 07:39:19 -0700 Subject: tcp: constify tcp_make_synack() socket argument listener socket is not locked when tcp_make_synack() is called. We better make sure no field is written. There is one exception : Since SYNACK packets are attached to the listener at this moment (or SYN_RECV child in case of Fast Open), sock_wmalloc() needs to update sk->sk_wmem_alloc, but this is done using atomic operations so this is safe. Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- include/net/tcp.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/net/tcp.h b/include/net/tcp.h index 45bc3c63c3fd..19f23590baa0 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -461,7 +461,7 @@ struct sock *tcp_v4_syn_recv_sock(struct sock *sk, struct sk_buff *skb, int tcp_v4_do_rcv(struct sock *sk, struct sk_buff *skb); int tcp_v4_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len); int tcp_connect(struct sock *sk); -struct sk_buff *tcp_make_synack(struct sock *sk, struct dst_entry *dst, +struct sk_buff *tcp_make_synack(const struct sock *sk, struct dst_entry *dst, struct request_sock *req, struct tcp_fastopen_cookie *foc); int tcp_disconnect(struct sock *sk, int flags); -- cgit v1.2.3 From 1c1e9d2b67897316770fc8a2e1acdd9f2787838d Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Fri, 25 Sep 2015 07:39:20 -0700 Subject: ipv6: constify ip6_xmit() sock argument This is to document that socket lock might not be held at this point. skb_set_owner_w() and ipv6_local_error() are using proper atomic ops or spinlocks, so we promote the socket to non const when calling them. netfilter hooks should never assume socket lock is held, we also promote the socket to non const. Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- include/net/ipv6.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/net/ipv6.h b/include/net/ipv6.h index 9877b68ad207..3dde042bcd3f 100644 --- a/include/net/ipv6.h +++ b/include/net/ipv6.h @@ -812,7 +812,7 @@ int ip6_rcv_finish(struct net *net, struct sock *sk, struct sk_buff *skb); /* * upper-layer output functions */ -int ip6_xmit(struct sock *sk, struct sk_buff *skb, struct flowi6 *fl6, +int ip6_xmit(const struct sock *sk, struct sk_buff *skb, struct flowi6 *fl6, struct ipv6_txoptions *opt, int tclass); int ip6_find_1stfragopt(struct sk_buff *skb, u8 **nexthdr); -- cgit v1.2.3 From 0f935dbedc49a5044ebff08b47eef35a2f2bbe92 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Fri, 25 Sep 2015 07:39:21 -0700 Subject: tcp: constify tcp_v{4|6}_send_synack() socket argument This documents fact that listener lock might not be held at the time SYNACK are sent. Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- include/net/tcp.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/net/tcp.h b/include/net/tcp.h index 19f23590baa0..868c53532169 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -1717,7 +1717,7 @@ struct tcp_request_sock_ops { const struct request_sock *req, bool *strict); __u32 (*init_seq)(const struct sk_buff *skb); - int (*send_synack)(struct sock *sk, struct dst_entry *dst, + int (*send_synack)(const struct sock *sk, struct dst_entry *dst, struct flowi *fl, struct request_sock *req, u16 queue_mapping, struct tcp_fastopen_cookie *foc); void (*queue_hash_add)(struct sock *sk, struct request_sock *req, -- cgit v1.2.3 From ea3bea3a1d38aab1542176b2ff11a99ce3db9656 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Fri, 25 Sep 2015 07:39:23 -0700 Subject: tcp/dccp: constify rtx_synack() and friends This is done to make sure we do not change listener socket while sending SYNACK packets while socket lock is not held. Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- include/net/request_sock.h | 2 +- include/net/tcp.h | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/net/request_sock.h b/include/net/request_sock.h index 87935cad2f7b..ff7ce1e53ed4 100644 --- a/include/net/request_sock.h +++ b/include/net/request_sock.h @@ -32,7 +32,7 @@ struct request_sock_ops { int obj_size; struct kmem_cache *slab; char *slab_name; - int (*rtx_syn_ack)(struct sock *sk, + int (*rtx_syn_ack)(const struct sock *sk, struct request_sock *req); void (*send_ack)(struct sock *sk, struct sk_buff *skb, struct request_sock *req); diff --git a/include/net/tcp.h b/include/net/tcp.h index 868c53532169..6630ab180f5c 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -1676,7 +1676,7 @@ int tcp4_proc_init(void); void tcp4_proc_exit(void); #endif -int tcp_rtx_synack(struct sock *sk, struct request_sock *req); +int tcp_rtx_synack(const struct sock *sk, struct request_sock *req); int tcp_conn_request(struct request_sock_ops *rsk_ops, const struct tcp_request_sock_ops *af_ops, struct sock *sk, struct sk_buff *skb); -- cgit v1.2.3 From 1b70e977cef6ce7e7411c9bbec21f9adc8e29097 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Fri, 25 Sep 2015 07:39:24 -0700 Subject: inet: constify inet_rtx_syn_ack() sock argument SYNACK packets are sent on behalf on unlocked listeners or fastopen sockets. Mark socket as const to catch future changes that might break the assumption. Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- include/net/request_sock.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/net/request_sock.h b/include/net/request_sock.h index ff7ce1e53ed4..181f97f9fe1c 100644 --- a/include/net/request_sock.h +++ b/include/net/request_sock.h @@ -42,7 +42,7 @@ struct request_sock_ops { void (*syn_ack_timeout)(const struct request_sock *req); }; -int inet_rtx_syn_ack(struct sock *parent, struct request_sock *req); +int inet_rtx_syn_ack(const struct sock *parent, struct request_sock *req); /* struct request_sock - mini sock to represent a connection request */ -- cgit v1.2.3 From b1be00a6c39fda2ec380e168d7bcf96fb8c9da42 Mon Sep 17 00:00:00 2001 From: Jiri Benc Date: Thu, 24 Sep 2015 13:50:02 +0200 Subject: vxlan: support both IPv4 and IPv6 sockets in a single vxlan device For metadata based vxlan interface, open both IPv4 and IPv6 socket. This is much more user friendly: it's not necessary to create two vxlan interfaces and pay attention to using the right one in routing rules. Signed-off-by: Jiri Benc Signed-off-by: David S. Miller --- include/net/vxlan.h | 14 +++++++++++--- 1 file changed, 11 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/include/net/vxlan.h b/include/net/vxlan.h index 480a319b4c92..c1c899c3a51b 100644 --- a/include/net/vxlan.h +++ b/include/net/vxlan.h @@ -152,7 +152,10 @@ struct vxlan_config { struct vxlan_dev { struct hlist_node hlist; /* vni hash table */ struct list_head next; /* vxlan's per namespace list */ - struct vxlan_sock *vn_sock; /* listening socket */ + struct vxlan_sock *vn4_sock; /* listening socket for IPv4 */ +#if IS_ENABLED(CONFIG_IPV6) + struct vxlan_sock *vn6_sock; /* listening socket for IPv6 */ +#endif struct net_device *dev; struct net *net; /* netns for packet i/o */ struct vxlan_rdst default_dst; /* default destination */ @@ -195,9 +198,14 @@ struct vxlan_dev { struct net_device *vxlan_dev_create(struct net *net, const char *name, u8 name_assign_type, struct vxlan_config *conf); -static inline __be16 vxlan_dev_dst_port(struct vxlan_dev *vxlan) +static inline __be16 vxlan_dev_dst_port(struct vxlan_dev *vxlan, + unsigned short family) { - return inet_sk(vxlan->vn_sock->sock->sk)->inet_sport; +#if IS_ENABLED(CONFIG_IPV6) + if (family == AF_INET6) + return inet_sk(vxlan->vn6_sock->sock->sk)->inet_sport; +#endif + return inet_sk(vxlan->vn4_sock->sock->sk)->inet_sport; } static inline netdev_features_t vxlan_features_check(struct sk_buff *skb, -- cgit v1.2.3 From 7c85af8810448d8ef59331be51e482413b5f503d Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Thu, 24 Sep 2015 17:16:05 -0700 Subject: tcp: avoid reorders for TFO passive connections We found that a TCP Fast Open passive connection was vulnerable to reorders, as the exchange might look like [1] C -> S S [2] S -> C S. ack request [3] S -> C . packets [2] and [3] can be generated at almost the same time. If C receives the 3rd packet before the 2nd, it will drop it as the socket is in SYN_SENT state and expects a SYNACK. S will have to retransmit the answer. Current OOO avoidance in linux is defeated because SYNACK packets are attached to the LISTEN socket, while DATA packets are attached to the children. They might be sent by different cpus, and different TX queues might be selected. It turns out that for TFO, we created a child, which is a full blown socket in TCP_SYN_RECV state, and we simply can attach the SYNACK packet to this socket. This means that at the time tcp_sendmsg() pushes DATA packet, skb->ooo_okay will be set iff the SYNACK packet had been sent and TX completed. This removes the reorder source at the host level. We also removed the export of tcp_try_fastopen(), as it is no longer called from IPv6. Signed-off-by: Eric Dumazet Signed-off-by: Yuchung Cheng Signed-off-by: David S. Miller --- include/net/tcp.h | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) (limited to 'include') diff --git a/include/net/tcp.h b/include/net/tcp.h index 6630ab180f5c..cdbf63d3c5cf 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -1422,10 +1422,10 @@ void tcp_free_fastopen_req(struct tcp_sock *tp); extern struct tcp_fastopen_context __rcu *tcp_fastopen_ctx; int tcp_fastopen_reset_cipher(void *key, unsigned int len); -bool tcp_try_fastopen(struct sock *sk, struct sk_buff *skb, - struct request_sock *req, - struct tcp_fastopen_cookie *foc, - struct dst_entry *dst); +struct sock *tcp_try_fastopen(struct sock *sk, struct sk_buff *skb, + struct request_sock *req, + struct tcp_fastopen_cookie *foc, + struct dst_entry *dst); void tcp_fastopen_init_key_once(bool publish); #define TCP_FASTOPEN_KEY_LENGTH 16 -- cgit v1.2.3 From 78ccb25861d76a8fc5c678d762180e6918834200 Mon Sep 17 00:00:00 2001 From: Eli Cohen Date: Fri, 25 Sep 2015 10:49:15 +0300 Subject: net/mlx5_core: Fix wrong name in struct The name refers to syndrome so uset ext_synd instread of ext_sync. Signed-off-by: Eli Cohen Signed-off-by: Or Gerlitz Signed-off-by: David S. Miller --- include/linux/mlx5/device.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/mlx5/device.h b/include/linux/mlx5/device.h index 8eb3b19af2a4..41e9f3bd663c 100644 --- a/include/linux/mlx5/device.h +++ b/include/linux/mlx5/device.h @@ -440,7 +440,7 @@ struct health_buffer { __be32 rsvd2; u8 irisc_index; u8 synd; - __be16 ext_sync; + __be16 ext_synd; }; struct mlx5_init_seg { -- cgit v1.2.3 From 55acca90da52b85299c033354e51ddaa7b73e019 Mon Sep 17 00:00:00 2001 From: Hante Meuleman Date: Fri, 18 Sep 2015 22:08:17 +0200 Subject: brcmfmac: Add support for the BCM4365 and BCM4366 PCIE devices. This patch adds support for the BCM4365 and BCM4366 11ac Wave2 PCIE devices. Reviewed-by: Arend Van Spriel Reviewed-by: Pieter-Paul Giesberts Signed-off-by: Hante Meuleman Signed-off-by: Arend van Spriel Signed-off-by: Kalle Valo --- include/linux/bcma/bcma.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/linux/bcma/bcma.h b/include/linux/bcma/bcma.h index 2ff4a9961e1d..3feb1b2d75d8 100644 --- a/include/linux/bcma/bcma.h +++ b/include/linux/bcma/bcma.h @@ -151,6 +151,8 @@ struct bcma_host_ops { #define BCMA_CORE_PCIE2 0x83C /* PCI Express Gen2 */ #define BCMA_CORE_USB30_DEV 0x83D #define BCMA_CORE_ARM_CR4 0x83E +#define BCMA_CORE_ARM_CA7 0x847 +#define BCMA_CORE_SYS_MEM 0x849 #define BCMA_CORE_DEFAULT 0xFFF #define BCMA_MAX_NR_CORES 16 -- cgit v1.2.3 From fbef168fec837ae26c8725737cd4b49dc8a0f917 Mon Sep 17 00:00:00 2001 From: Loic Poulain Date: Tue, 29 Sep 2015 15:05:44 +0200 Subject: Bluetooth: Add hci_cmd_sync function Send a HCI command and wait for command complete event. This function serializes the requests by grabbing the req_lock. Signed-off-by: Loic Poulain Signed-off-by: Marcel Holtmann --- include/net/bluetooth/hci_core.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include') diff --git a/include/net/bluetooth/hci_core.h b/include/net/bluetooth/hci_core.h index 256e6734c1fb..61dc786358be 100644 --- a/include/net/bluetooth/hci_core.h +++ b/include/net/bluetooth/hci_core.h @@ -1349,6 +1349,9 @@ void hci_send_sco(struct hci_conn *conn, struct sk_buff *skb); void *hci_sent_cmd_data(struct hci_dev *hdev, __u16 opcode); +struct sk_buff *hci_cmd_sync(struct hci_dev *hdev, u16 opcode, u32 plen, + const void *param, u32 timeout); + /* ----- HCI Sockets ----- */ void hci_send_to_sock(struct hci_dev *hdev, struct sk_buff *skb); void hci_send_to_channel(unsigned short channel, struct sk_buff *skb, -- cgit v1.2.3 From 35afa588624c4f9e19a0edfbb51769b59c90bb0d Mon Sep 17 00:00:00 2001 From: Helmut Schaa Date: Wed, 9 Sep 2015 09:46:32 +0200 Subject: mac80211: Copy tx'ed beacons to monitor mode When debugging wireless powersave issues on the AP side it's quite helpful to see our own beacons that are transmitted by the hardware/driver. However, this is not that easy since beacons don't pass through the regular TX queues. Preferably drivers would call ieee80211_tx_status also for tx'ed beacons but that's not always possible. Hence, just send a copy of each beacon generated by ieee80211_beacon_get_tim to monitor devices when they are getting fetched by the driver. Also add a HW flag IEEE80211_HW_BEACON_TX_STATUS that can be used by drivers to indicate that they report TX status for beacons. Signed-off-by: Helmut Schaa (with a fix from Christian Lamparted rolled in) Signed-off-by: Johannes Berg --- include/net/mac80211.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include') diff --git a/include/net/mac80211.h b/include/net/mac80211.h index 3424ac6efb2a..301fceb2fd10 100644 --- a/include/net/mac80211.h +++ b/include/net/mac80211.h @@ -1898,6 +1898,9 @@ struct ieee80211_txq { * @IEEE80211_HW_SUPPORTS_AMSDU_IN_AMPDU: The driver supports receiving A-MSDUs * within A-MPDU. * + * @IEEE80211_HW_BEACON_TX_STATUS: The device/driver provides TX status + * for sent beacons. + * * @NUM_IEEE80211_HW_FLAGS: number of hardware flags, used for sizing arrays */ enum ieee80211_hw_flags { @@ -1932,6 +1935,7 @@ enum ieee80211_hw_flags { IEEE80211_HW_SINGLE_SCAN_ON_ALL_BANDS, IEEE80211_HW_TDLS_WIDER_BW, IEEE80211_HW_SUPPORTS_AMSDU_IN_AMPDU, + IEEE80211_HW_BEACON_TX_STATUS, /* keep last, obviously */ NUM_IEEE80211_HW_FLAGS -- cgit v1.2.3 From 47edb11b522561658fe719e56aa69a3c3098a3fe Mon Sep 17 00:00:00 2001 From: Ayala Beker Date: Mon, 21 Sep 2015 15:49:53 +0300 Subject: cfg80211: allow changing station capabilities for unassociated stations Currently, cfg80211 rejects capability updates for existing entries and as a result it's impossible to update entries that were added unassociated, but that is necessary to go through the full station states from userspace, adding a station before authentication etc. Fix this by allowing updates to capabilities for stations that the driver (or mac80211) assigned unassociated state. Drivers setting the full station state support flag must use the new station type for proper operation. Signed-off-by: Ayala Beker Signed-off-by: Luca Coelho Signed-off-by: Johannes Berg --- include/net/cfg80211.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include') diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h index 0f54c9ef4c7d..90332a1838cc 100644 --- a/include/net/cfg80211.h +++ b/include/net/cfg80211.h @@ -858,6 +858,8 @@ struct station_del_parameters { /** * enum cfg80211_station_type - the type of station being modified * @CFG80211_STA_AP_CLIENT: client of an AP interface + * @CFG80211_STA_AP_CLIENT_UNASSOC: client of an AP interface that is still + * unassociated (update properties for this type of client is permitted) * @CFG80211_STA_AP_MLME_CLIENT: client of an AP interface that has * the AP MLME in the device * @CFG80211_STA_AP_STA: AP station on managed interface @@ -873,6 +875,7 @@ struct station_del_parameters { */ enum cfg80211_station_type { CFG80211_STA_AP_CLIENT, + CFG80211_STA_AP_CLIENT_UNASSOC, CFG80211_STA_AP_MLME_CLIENT, CFG80211_STA_AP_STA, CFG80211_STA_IBSS, -- cgit v1.2.3 From 372892ec1151c895c7dec362f3246f089690cfc7 Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Fri, 25 Sep 2015 15:07:27 -0500 Subject: ipv4: Push struct net down into nf_send_reset This is needed so struct net can be pushed down into ip_route_me_harder. Signed-off-by: "Eric W. Biederman" Signed-off-by: Pablo Neira Ayuso --- include/net/netfilter/ipv4/nf_reject.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/net/netfilter/ipv4/nf_reject.h b/include/net/netfilter/ipv4/nf_reject.h index 77862c3645f0..df7ecd806aba 100644 --- a/include/net/netfilter/ipv4/nf_reject.h +++ b/include/net/netfilter/ipv4/nf_reject.h @@ -6,7 +6,7 @@ #include void nf_send_unreach(struct sk_buff *skb_in, int code, int hook); -void nf_send_reset(struct sk_buff *oldskb, int hook); +void nf_send_reset(struct net *net, struct sk_buff *oldskb, int hook); const struct tcphdr *nf_reject_ip_tcphdr_get(struct sk_buff *oldskb, struct tcphdr *_oth, int hook); -- cgit v1.2.3 From d815d90bbbc08777c0e3a36f57b97fc4a4fb3150 Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Fri, 25 Sep 2015 15:07:28 -0500 Subject: netfilter: Push struct net down into nf_afinfo.reroute The network namespace is needed when routing a packet. Stop making nf_afinfo.reroute guess which network namespace is the proper namespace to route the packet in. Signed-off-by: "Eric W. Biederman" Signed-off-by: Pablo Neira Ayuso --- include/linux/netfilter.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/netfilter.h b/include/linux/netfilter.h index 987c74cd523c..165ab2d14734 100644 --- a/include/linux/netfilter.h +++ b/include/linux/netfilter.h @@ -283,7 +283,7 @@ struct nf_afinfo { struct flowi *fl, bool strict); void (*saveroute)(const struct sk_buff *skb, struct nf_queue_entry *entry); - int (*reroute)(struct sk_buff *skb, + int (*reroute)(struct net *net, struct sk_buff *skb, const struct nf_queue_entry *entry); int route_key_size; }; -- cgit v1.2.3 From e45f50660ee5fd38a540afabb7c0f65d063db631 Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Fri, 25 Sep 2015 15:07:30 -0500 Subject: ipv4: Pass struct net into ip_route_me_harder Don't make ip_route_me_harder guess which network namespace it is routing in, pass the network namespace in. Signed-off-by: "Eric W. Biederman" Signed-off-by: Pablo Neira Ayuso --- include/linux/netfilter_ipv4.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/netfilter_ipv4.h b/include/linux/netfilter_ipv4.h index 6e4591bb54d4..98c03b2462b5 100644 --- a/include/linux/netfilter_ipv4.h +++ b/include/linux/netfilter_ipv4.h @@ -6,7 +6,7 @@ #include -int ip_route_me_harder(struct sk_buff *skb, unsigned addr_type); +int ip_route_me_harder(struct net *net, struct sk_buff *skb, unsigned addr_type); __sum16 nf_ip_checksum(struct sk_buff *skb, unsigned int hook, unsigned int dataoff, u_int8_t protocol); #endif /*__LINUX_IP_NETFILTER_H*/ -- cgit v1.2.3 From 5f5d74d723146c5b97c7318b5851af15b30e3304 Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Fri, 25 Sep 2015 15:07:31 -0500 Subject: ipv6: Pass struct net into ip6_route_me_harder Don't make ip6_route_me_harder guess which network namespace it is routing in, pass the network namespace in. Signed-off-by: Eric W. Biederman Signed-off-by: Pablo Neira Ayuso --- include/linux/netfilter_ipv6.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/netfilter_ipv6.h b/include/linux/netfilter_ipv6.h index 771574677e83..2ac8369fa96c 100644 --- a/include/linux/netfilter_ipv6.h +++ b/include/linux/netfilter_ipv6.h @@ -22,7 +22,7 @@ struct nf_ipv6_ops { }; #ifdef CONFIG_NETFILTER -int ip6_route_me_harder(struct sk_buff *skb); +int ip6_route_me_harder(struct net *net, struct sk_buff *skb); __sum16 nf_ip6_checksum(struct sk_buff *skb, unsigned int hook, unsigned int dataoff, u_int8_t protocol); -- cgit v1.2.3 From c1444c6357217cea405415b4c96491d4057b0746 Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Fri, 25 Sep 2015 16:52:51 -0500 Subject: bridge: Pass net into br_validate_ipv4 and br_validate_ipv6 The network namespace is easiliy available in state->net so use it. Signed-off-by: "Eric W. Biederman" Signed-off-by: Pablo Neira Ayuso --- include/net/netfilter/br_netfilter.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/net/netfilter/br_netfilter.h b/include/net/netfilter/br_netfilter.h index c93c75fa41ad..e8d1448425a7 100644 --- a/include/net/netfilter/br_netfilter.h +++ b/include/net/netfilter/br_netfilter.h @@ -45,12 +45,12 @@ struct net_device *setup_pre_routing(struct sk_buff *skb); void br_netfilter_enable(void); #if IS_ENABLED(CONFIG_IPV6) -int br_validate_ipv6(struct sk_buff *skb); +int br_validate_ipv6(struct net *net, struct sk_buff *skb); unsigned int br_nf_pre_routing_ipv6(void *priv, struct sk_buff *skb, const struct nf_hook_state *state); #else -static inline int br_validate_ipv6(struct sk_buff *skb) +static inline int br_validate_ipv6(struct net *net, struct sk_buff *skb) { return -1; } -- cgit v1.2.3 From 2594e9064a57634efc146ff4e89a5de562e05011 Mon Sep 17 00:00:00 2001 From: Nikolay Aleksandrov Date: Fri, 25 Sep 2015 19:00:11 +0200 Subject: bridge: vlan: add per-vlan struct and move to rhashtables This patch changes the bridge vlan implementation to use rhashtables instead of bitmaps. The main motivation behind this change is that we need extensible per-vlan structures (both per-port and global) so more advanced features can be introduced and the vlan support can be extended. I've tried to break this up but the moment net_port_vlans is changed and the whole API goes away, thus this is a larger patch. A few short goals of this patch are: - Extensible per-vlan structs stored in rhashtables and a sorted list - Keep user-visible behaviour (compressed vlans etc) - Keep fastpath ingress/egress logic the same (optimizations to come later) Here's a brief list of some of the new features we'd like to introduce: - per-vlan counters - vlan ingress/egress mapping - per-vlan igmp configuration - vlan priorities - avoid fdb entries replication (e.g. local fdb scaling issues) The structure is kept single for both global and per-port entries so to avoid code duplication where possible and also because we'll soon introduce "port0 / aka bridge as port" which should simplify things further (thanks to Vlad for the suggestion!). Now we have per-vlan global rhashtable (bridge-wide) and per-vlan port rhashtable, if an entry is added to a port it'll get a pointer to its global context so it can be quickly accessed later. There's also a sorted vlan list which is used for stable walks and some user-visible behaviour such as the vlan ranges, also for error paths. VLANs are stored in a "vlan group" which currently contains the rhashtable, sorted vlan list and the number of "real" vlan entries. A good side-effect of this change is that it resembles how hw keeps per-vlan data. One important note after this change is that if a VLAN is being looked up in the bridge's rhashtable for filtering purposes (or to check if it's an existing usable entry, not just a global context) then the new helper br_vlan_should_use() needs to be used if the vlan is found. In case the lookup is done only with a port's vlan group, then this check can be skipped. Things tested so far: - basic vlan ingress/egress - pvids - untagged vlans - undef CONFIG_BRIDGE_VLAN_FILTERING - adding/deleting vlans in different scenarios (with/without global ctx, while transmitting traffic, in ranges etc) - loading/removing the module while having/adding/deleting vlans - extracting bridge vlan information (user ABI), compressed requests - adding/deleting fdbs on vlans - bridge mac change, promisc mode - default pvid change - kmemleak ON during the whole time Signed-off-by: Nikolay Aleksandrov Signed-off-by: David S. Miller --- include/uapi/linux/if_bridge.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/uapi/linux/if_bridge.h b/include/uapi/linux/if_bridge.h index 3635b7797508..18db14477bdd 100644 --- a/include/uapi/linux/if_bridge.h +++ b/include/uapi/linux/if_bridge.h @@ -127,6 +127,7 @@ enum { #define BRIDGE_VLAN_INFO_UNTAGGED (1<<2) /* VLAN egresses untagged */ #define BRIDGE_VLAN_INFO_RANGE_BEGIN (1<<3) /* VLAN is start of vlan range */ #define BRIDGE_VLAN_INFO_RANGE_END (1<<4) /* VLAN is end of vlan range */ +#define BRIDGE_VLAN_INFO_BRENTRY (1<<5) /* Global bridge VLAN entry */ struct bridge_vlan_info { __u16 flags; -- cgit v1.2.3 From 2094acbb714e24e464c810c2d8fa57493fcb25a6 Mon Sep 17 00:00:00 2001 From: Alexander Duyck Date: Mon, 28 Sep 2015 11:10:31 -0700 Subject: net/ipv4: Pass proto as u8 instead of u16 in ip_check_mc_rcu This patch updates ip_check_mc_rcu so that protocol is passed as a u8 instead of a u16. The motivation is just to avoid any unneeded type transitions since some systems will require an instruction to zero extend a u8 field to a u16. Also it makes it a bit more readable as to the fact that protocol is a u8 so there are no byte ordering changes needed to pass it. Signed-off-by: Alexander Duyck Signed-off-by: David S. Miller --- include/linux/igmp.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/igmp.h b/include/linux/igmp.h index 908429216d9f..9c9de11549a7 100644 --- a/include/linux/igmp.h +++ b/include/linux/igmp.h @@ -110,7 +110,7 @@ struct ip_mc_list { #define IGMPV3_QQIC(value) IGMPV3_EXP(0x80, 4, 3, value) #define IGMPV3_MRC(value) IGMPV3_EXP(0x80, 4, 3, value) -extern int ip_check_mc_rcu(struct in_device *dev, __be32 mc_addr, __be32 src_addr, u16 proto); +extern int ip_check_mc_rcu(struct in_device *dev, __be32 mc_addr, __be32 src_addr, u8 proto); extern int igmp_rcv(struct sk_buff *); extern int ip_mc_join_group(struct sock *sk, struct ip_mreqn *imr); extern int ip_mc_leave_group(struct sock *sk, struct ip_mreqn *imr); -- cgit v1.2.3 From a00e74442bac5ad19a929d097370da7e07540ea6 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Tue, 29 Sep 2015 07:42:39 -0700 Subject: tcp/dccp: constify send_synack and send_reset socket argument None of these functions need to change the socket, make it const. Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- include/net/request_sock.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/net/request_sock.h b/include/net/request_sock.h index 181f97f9fe1c..90247ec7955b 100644 --- a/include/net/request_sock.h +++ b/include/net/request_sock.h @@ -34,9 +34,9 @@ struct request_sock_ops { char *slab_name; int (*rtx_syn_ack)(const struct sock *sk, struct request_sock *req); - void (*send_ack)(struct sock *sk, struct sk_buff *skb, + void (*send_ack)(const struct sock *sk, struct sk_buff *skb, struct request_sock *req); - void (*send_reset)(struct sock *sk, + void (*send_reset)(const struct sock *sk, struct sk_buff *skb); void (*destructor)(struct request_sock *req); void (*syn_ack_timeout)(const struct request_sock *req); -- cgit v1.2.3 From bda07a64c09c44ced789dbb815c71854f0c59839 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Tue, 29 Sep 2015 07:42:40 -0700 Subject: tcp: remove unused len argument from tcp_rcv_state_process() Once we realize tcp_rcv_synsent_state_process() does not use its 'len' argument and we get rid of it, then it becomes clear this argument is no longer used in tcp_rcv_state_process() Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- include/net/tcp.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/net/tcp.h b/include/net/tcp.h index cdbf63d3c5cf..1cfdedbe47e1 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -366,7 +366,7 @@ void tcp_write_timer_handler(struct sock *sk); void tcp_delack_timer_handler(struct sock *sk); int tcp_ioctl(struct sock *sk, int cmd, unsigned long arg); int tcp_rcv_state_process(struct sock *sk, struct sk_buff *skb, - const struct tcphdr *th, unsigned int len); + const struct tcphdr *th); void tcp_rcv_established(struct sock *sk, struct sk_buff *skb, const struct tcphdr *th, unsigned int len); void tcp_rcv_space_adjust(struct sock *sk); -- cgit v1.2.3 From 72ab4a86f7a260d4c2a320b49662da107ce77a81 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Tue, 29 Sep 2015 07:42:41 -0700 Subject: tcp: remove tcp_rcv_state_process() tcp_hdr argument Factorize code to get tcp header from skb. It makes no sense to duplicate code in callers. Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- include/net/tcp.h | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) (limited to 'include') diff --git a/include/net/tcp.h b/include/net/tcp.h index 1cfdedbe47e1..1fe0bd458cb4 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -365,8 +365,7 @@ void tcp_wfree(struct sk_buff *skb); void tcp_write_timer_handler(struct sock *sk); void tcp_delack_timer_handler(struct sock *sk); int tcp_ioctl(struct sock *sk, int cmd, unsigned long arg); -int tcp_rcv_state_process(struct sock *sk, struct sk_buff *skb, - const struct tcphdr *th); +int tcp_rcv_state_process(struct sock *sk, struct sk_buff *skb); void tcp_rcv_established(struct sock *sk, struct sk_buff *skb, const struct tcphdr *th, unsigned int len); void tcp_rcv_space_adjust(struct sock *sk); -- cgit v1.2.3 From f76b33c32b1913dd8909d8509f2726b1661aa6b1 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Tue, 29 Sep 2015 07:42:42 -0700 Subject: dccp: use inet6_csk_route_req() helper Before changing dccp_v6_request_recv_sock() sock argument to const, we need to get rid of security_sk_classify_flow(), and it seems doable by reusing inet6_csk_route_req() helper. We need to add a proto parameter to inet6_csk_route_req(), not assume it is TCP. Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- include/net/inet6_connection_sock.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/net/inet6_connection_sock.h b/include/net/inet6_connection_sock.h index 81d937e820c4..79b2a4c09ca6 100644 --- a/include/net/inet6_connection_sock.h +++ b/include/net/inet6_connection_sock.h @@ -26,7 +26,7 @@ int inet6_csk_bind_conflict(const struct sock *sk, const struct inet_bind_bucket *tb, bool relax); struct dst_entry *inet6_csk_route_req(const struct sock *sk, struct flowi6 *fl6, - const struct request_sock *req); + const struct request_sock *req, u8 proto); struct request_sock *inet6_csk_search_req(struct sock *sk, const __be16 rport, -- cgit v1.2.3 From a2432c4fa5e3c4c06df6efe0c406b6f575829a7b Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Tue, 29 Sep 2015 07:42:43 -0700 Subject: inet: constify inet_csk_route_child_sock() socket argument The socket points to the (shared) listener. Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- include/net/inet_connection_sock.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/net/inet_connection_sock.h b/include/net/inet_connection_sock.h index 00c3ced6ee55..187cef7e56d5 100644 --- a/include/net/inet_connection_sock.h +++ b/include/net/inet_connection_sock.h @@ -268,7 +268,8 @@ int inet_csk_get_port(struct sock *sk, unsigned short snum); struct dst_entry *inet_csk_route_req(const struct sock *sk, struct flowi4 *fl4, const struct request_sock *req); -struct dst_entry *inet_csk_route_child_sock(struct sock *sk, struct sock *newsk, +struct dst_entry *inet_csk_route_child_sock(const struct sock *sk, + struct sock *newsk, const struct request_sock *req); static inline void inet_csk_reqsk_queue_add(struct sock *sk, -- cgit v1.2.3 From 1ce31c9e08997ea0fa62be0a7437f868be173f13 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Tue, 29 Sep 2015 07:42:44 -0700 Subject: inet: constify __inet_inherit_port() sock argument socket is not touched, make it const. Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- include/net/inet_hashtables.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/net/inet_hashtables.h b/include/net/inet_hashtables.h index b07d126694a7..3fb778d7c875 100644 --- a/include/net/inet_hashtables.h +++ b/include/net/inet_hashtables.h @@ -199,7 +199,7 @@ static inline int inet_sk_listen_hashfn(const struct sock *sk) } /* Caller must disable local BH processing. */ -int __inet_inherit_port(struct sock *sk, struct sock *child); +int __inet_inherit_port(const struct sock *sk, struct sock *child); void inet_put_port(struct sock *sk); -- cgit v1.2.3 From 87e002b21aafccfe71faeec62f3543d30600a518 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Tue, 29 Sep 2015 07:42:45 -0700 Subject: net: constify sk_gfp_atomic() sock argument Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- include/net/sock.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/net/sock.h b/include/net/sock.h index 94dff7f566f5..dfe2eb8e1132 100644 --- a/include/net/sock.h +++ b/include/net/sock.h @@ -759,7 +759,7 @@ static inline int sk_memalloc_socks(void) #endif -static inline gfp_t sk_gfp_atomic(struct sock *sk, gfp_t gfp_mask) +static inline gfp_t sk_gfp_atomic(const struct sock *sk, gfp_t gfp_mask) { return GFP_ATOMIC | (sk->sk_allocation & __GFP_MEMALLOC); } -- cgit v1.2.3 From c28c6f045945f53e842467bf0e86c5fac051643d Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Tue, 29 Sep 2015 07:42:47 -0700 Subject: tcp: constify tcp_create_openreq_child() socket argument This method does not touch the listener socket. Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- include/net/tcp.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/net/tcp.h b/include/net/tcp.h index 1fe0bd458cb4..85995c1291d0 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -450,7 +450,7 @@ void tcp_v4_send_check(struct sock *sk, struct sk_buff *skb); void tcp_v4_mtu_reduced(struct sock *sk); void tcp_req_err(struct sock *sk, u32 seq); int tcp_v4_conn_request(struct sock *sk, struct sk_buff *skb); -struct sock *tcp_create_openreq_child(struct sock *sk, +struct sock *tcp_create_openreq_child(const struct sock *sk, struct request_sock *req, struct sk_buff *skb); void tcp_ca_openreq_child(struct sock *sk, const struct dst_entry *dst); -- cgit v1.2.3 From 0c27171e66d94f9121fc00e87407ca7103bb6649 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Tue, 29 Sep 2015 07:42:48 -0700 Subject: tcp/dccp: constify syn_recv_sock() method sock argument We'll soon no longer hold listener socket lock, these functions do not modify the socket in any way. Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- include/net/inet_connection_sock.h | 2 +- include/net/tcp.h | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/net/inet_connection_sock.h b/include/net/inet_connection_sock.h index 187cef7e56d5..ee54f21a8113 100644 --- a/include/net/inet_connection_sock.h +++ b/include/net/inet_connection_sock.h @@ -41,7 +41,7 @@ struct inet_connection_sock_af_ops { int (*rebuild_header)(struct sock *sk); void (*sk_rx_dst_set)(struct sock *sk, const struct sk_buff *skb); int (*conn_request)(struct sock *sk, struct sk_buff *skb); - struct sock *(*syn_recv_sock)(struct sock *sk, struct sk_buff *skb, + struct sock *(*syn_recv_sock)(const struct sock *sk, struct sk_buff *skb, struct request_sock *req, struct dst_entry *dst); u16 net_header_len; diff --git a/include/net/tcp.h b/include/net/tcp.h index 85995c1291d0..a1d2f5d6a430 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -454,7 +454,7 @@ struct sock *tcp_create_openreq_child(const struct sock *sk, struct request_sock *req, struct sk_buff *skb); void tcp_ca_openreq_child(struct sock *sk, const struct dst_entry *dst); -struct sock *tcp_v4_syn_recv_sock(struct sock *sk, struct sk_buff *skb, +struct sock *tcp_v4_syn_recv_sock(const struct sock *sk, struct sk_buff *skb, struct request_sock *req, struct dst_entry *dst); int tcp_v4_do_rcv(struct sock *sk, struct sk_buff *skb); -- cgit v1.2.3 From 3f684b4b1f1c86e3a6ac63389d1032e239fddd79 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Tue, 29 Sep 2015 07:42:49 -0700 Subject: tcp: cookie_init_sequence() cleanups Some common IPv4/IPv6 code can be factorized. Also constify cookie_init_sequence() socket argument. Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- include/net/tcp.h | 19 ++++++++++--------- 1 file changed, 10 insertions(+), 9 deletions(-) (limited to 'include') diff --git a/include/net/tcp.h b/include/net/tcp.h index a1d2f5d6a430..5aa6672c6f5b 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -491,8 +491,9 @@ struct sock *cookie_v4_check(struct sock *sk, struct sk_buff *skb); /* syncookies: remember time of last synqueue overflow * But do not dirty this field too often (once per second is enough) + * It is racy as we do not hold a lock, but race is very minor. */ -static inline void tcp_synq_overflow(struct sock *sk) +static inline void tcp_synq_overflow(const struct sock *sk) { unsigned long last_overflow = tcp_sk(sk)->rx_opt.ts_recent_stamp; unsigned long now = jiffies; @@ -519,8 +520,7 @@ static inline u32 tcp_cookie_time(void) u32 __cookie_v4_init_sequence(const struct iphdr *iph, const struct tcphdr *th, u16 *mssp); -__u32 cookie_v4_init_sequence(struct sock *sk, const struct sk_buff *skb, - __u16 *mss); +__u32 cookie_v4_init_sequence(const struct sk_buff *skb, __u16 *mss); __u32 cookie_init_timestamp(struct request_sock *req); bool cookie_timestamp_decode(struct tcp_options_received *opt); bool cookie_ecn_ok(const struct tcp_options_received *opt, @@ -533,8 +533,7 @@ struct sock *cookie_v6_check(struct sock *sk, struct sk_buff *skb); u32 __cookie_v6_init_sequence(const struct ipv6hdr *iph, const struct tcphdr *th, u16 *mssp); -__u32 cookie_v6_init_sequence(struct sock *sk, const struct sk_buff *skb, - __u16 *mss); +__u32 cookie_v6_init_sequence(const struct sk_buff *skb, __u16 *mss); #endif /* tcp_output.c */ @@ -1709,7 +1708,7 @@ struct tcp_request_sock_ops { const struct sock *sk_listener, struct sk_buff *skb); #ifdef CONFIG_SYN_COOKIES - __u32 (*cookie_init_seq)(struct sock *sk, const struct sk_buff *skb, + __u32 (*cookie_init_seq)(const struct sk_buff *skb, __u16 *mss); #endif struct dst_entry *(*route_req)(struct sock *sk, struct flowi *fl, @@ -1725,14 +1724,16 @@ struct tcp_request_sock_ops { #ifdef CONFIG_SYN_COOKIES static inline __u32 cookie_init_sequence(const struct tcp_request_sock_ops *ops, - struct sock *sk, struct sk_buff *skb, + const struct sock *sk, struct sk_buff *skb, __u16 *mss) { - return ops->cookie_init_seq(sk, skb, mss); + tcp_synq_overflow(sk); + NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_SYNCOOKIESSENT); + return ops->cookie_init_seq(skb, mss); } #else static inline __u32 cookie_init_sequence(const struct tcp_request_sock_ops *ops, - struct sock *sk, struct sk_buff *skb, + const struct sock *sk, struct sk_buff *skb, __u16 *mss) { return 0; -- cgit v1.2.3 From f964629e3338d9e5a78c9b354380d5a1e2fa4617 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Tue, 29 Sep 2015 07:42:50 -0700 Subject: tcp: constify tcp_v{4|6}_route_req() sock argument These functions do not change the listener socket. Goal is to make sure tcp_conn_request() is not messing with listener in a racy way. Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- include/net/tcp.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/net/tcp.h b/include/net/tcp.h index 5aa6672c6f5b..2c7dfe52f473 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -1711,7 +1711,7 @@ struct tcp_request_sock_ops { __u32 (*cookie_init_seq)(const struct sk_buff *skb, __u16 *mss); #endif - struct dst_entry *(*route_req)(struct sock *sk, struct flowi *fl, + struct dst_entry *(*route_req)(const struct sock *sk, struct flowi *fl, const struct request_sock *req, bool *strict); __u32 (*init_seq)(const struct sk_buff *skb); -- cgit v1.2.3 From 2985aaac010ebd5e562ce1a22cc61acbb0e40cf2 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Tue, 29 Sep 2015 07:42:51 -0700 Subject: tcp: constify tcp_syn_flood_action() socket argument tcp_syn_flood_action() will soon be called with unlocked socket. In order to avoid SYN flood warning being emitted multiple times, use xchg(). Extend max_qlen_log and synflood_warned fields in struct listen_sock to u32 Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- include/net/request_sock.h | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/include/net/request_sock.h b/include/net/request_sock.h index 90247ec7955b..c146b5284786 100644 --- a/include/net/request_sock.h +++ b/include/net/request_sock.h @@ -129,9 +129,8 @@ struct listen_sock { atomic_t qlen_dec; /* qlen = qlen_inc - qlen_dec */ atomic_t young_dec; - u8 max_qlen_log ____cacheline_aligned_in_smp; - u8 synflood_warned; - /* 2 bytes hole, try to use */ + u32 max_qlen_log ____cacheline_aligned_in_smp; + u32 synflood_warned; u32 hash_rnd; u32 nr_table_entries; struct request_sock *syn_table[0]; -- cgit v1.2.3 From 0536fcc039a8926ec12ec587f41a83f7acafeb82 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Tue, 29 Sep 2015 07:42:52 -0700 Subject: tcp: prepare fastopen code for upcoming listener changes While auditing TCP stack for upcoming 'lockless' listener changes, I found I had to change fastopen_init_queue() to properly init the object before publishing it. Otherwise an other cpu could try to lock the spinlock before it gets properly initialized. Instead of adding appropriate barriers, just remove dynamic memory allocations : - Structure is 28 bytes on 64bit arches. Using additional 8 bytes for holding a pointer seems overkill. - Two listeners can share same cache line and performance would suffer. If we really want to save few bytes, we would instead dynamically allocate whole struct request_sock_queue in the future. Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- include/linux/tcp.h | 22 ++++------------------ include/net/request_sock.h | 7 ++----- 2 files changed, 6 insertions(+), 23 deletions(-) (limited to 'include') diff --git a/include/linux/tcp.h b/include/linux/tcp.h index fcb573be75d9..e442e6e9a365 100644 --- a/include/linux/tcp.h +++ b/include/linux/tcp.h @@ -382,25 +382,11 @@ static inline bool tcp_passive_fastopen(const struct sock *sk) tcp_sk(sk)->fastopen_rsk != NULL); } -extern void tcp_sock_destruct(struct sock *sk); - -static inline int fastopen_init_queue(struct sock *sk, int backlog) +static inline void fastopen_queue_tune(struct sock *sk, int backlog) { - struct request_sock_queue *queue = - &inet_csk(sk)->icsk_accept_queue; - - if (queue->fastopenq == NULL) { - queue->fastopenq = kzalloc( - sizeof(struct fastopen_queue), - sk->sk_allocation); - if (queue->fastopenq == NULL) - return -ENOMEM; - - sk->sk_destruct = tcp_sock_destruct; - spin_lock_init(&queue->fastopenq->lock); - } - queue->fastopenq->max_qlen = backlog; - return 0; + struct request_sock_queue *queue = &inet_csk(sk)->icsk_accept_queue; + + queue->fastopenq.max_qlen = backlog; } static inline void tcp_saved_syn_free(struct tcp_sock *tp) diff --git a/include/net/request_sock.h b/include/net/request_sock.h index c146b5284786..d2544de329bd 100644 --- a/include/net/request_sock.h +++ b/include/net/request_sock.h @@ -180,11 +180,8 @@ struct request_sock_queue { struct request_sock *rskq_accept_tail; u8 rskq_defer_accept; struct listen_sock *listen_opt; - struct fastopen_queue *fastopenq; /* This is non-NULL iff TFO has been - * enabled on this listener. Check - * max_qlen != 0 in fastopen_queue - * to determine if TFO is enabled - * right at this moment. + struct fastopen_queue fastopenq; /* Check max_qlen != 0 to determine + * if TFO is enabled. */ /* temporary alignment, our goal is to get rid of this lock */ -- cgit v1.2.3 From 007979eaf94d1c888d8c7cf8a5250c2c6c9bd98e Mon Sep 17 00:00:00 2001 From: David Ahern Date: Tue, 29 Sep 2015 20:07:10 -0700 Subject: net: Rename IFF_VRF_MASTER to IFF_L3MDEV_MASTER Rename IFF_VRF_MASTER to IFF_L3MDEV_MASTER and update the name of the netif_is_vrf and netif_index_is_vrf macros. Signed-off-by: David Ahern Signed-off-by: David S. Miller --- include/linux/netdevice.h | 14 +++++++------- include/net/route.h | 2 +- include/net/vrf.h | 4 ++-- 3 files changed, 10 insertions(+), 10 deletions(-) (limited to 'include') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index d2ffeafc9998..99c33e83822f 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -1258,7 +1258,7 @@ struct net_device_ops { * @IFF_LIVE_ADDR_CHANGE: device supports hardware address * change when it's running * @IFF_MACVLAN: Macvlan device - * @IFF_VRF_MASTER: device is a VRF master + * @IFF_L3MDEV_MASTER: device is an L3 master device * @IFF_NO_QUEUE: device can run without qdisc attached * @IFF_OPENVSWITCH: device is a Open vSwitch master */ @@ -1283,7 +1283,7 @@ enum netdev_priv_flags { IFF_XMIT_DST_RELEASE_PERM = 1<<17, IFF_IPVLAN_MASTER = 1<<18, IFF_IPVLAN_SLAVE = 1<<19, - IFF_VRF_MASTER = 1<<20, + IFF_L3MDEV_MASTER = 1<<20, IFF_NO_QUEUE = 1<<21, IFF_OPENVSWITCH = 1<<22, }; @@ -1308,7 +1308,7 @@ enum netdev_priv_flags { #define IFF_XMIT_DST_RELEASE_PERM IFF_XMIT_DST_RELEASE_PERM #define IFF_IPVLAN_MASTER IFF_IPVLAN_MASTER #define IFF_IPVLAN_SLAVE IFF_IPVLAN_SLAVE -#define IFF_VRF_MASTER IFF_VRF_MASTER +#define IFF_L3MDEV_MASTER IFF_L3MDEV_MASTER #define IFF_NO_QUEUE IFF_NO_QUEUE #define IFF_OPENVSWITCH IFF_OPENVSWITCH @@ -3824,9 +3824,9 @@ static inline bool netif_supports_nofcs(struct net_device *dev) return dev->priv_flags & IFF_SUPP_NOFCS; } -static inline bool netif_is_vrf(const struct net_device *dev) +static inline bool netif_is_l3_master(const struct net_device *dev) { - return dev->priv_flags & IFF_VRF_MASTER; + return dev->priv_flags & IFF_L3MDEV_MASTER; } static inline bool netif_is_bridge_master(const struct net_device *dev) @@ -3839,7 +3839,7 @@ static inline bool netif_is_ovs_master(const struct net_device *dev) return dev->priv_flags & IFF_OPENVSWITCH; } -static inline bool netif_index_is_vrf(struct net *net, int ifindex) +static inline bool netif_index_is_l3_master(struct net *net, int ifindex) { bool rc = false; @@ -3853,7 +3853,7 @@ static inline bool netif_index_is_vrf(struct net *net, int ifindex) dev = dev_get_by_index_rcu(net, ifindex); if (dev) - rc = netif_is_vrf(dev); + rc = netif_is_l3_master(dev); rcu_read_unlock(); #endif diff --git a/include/net/route.h b/include/net/route.h index d1bd90bb3187..a565d0dad12c 100644 --- a/include/net/route.h +++ b/include/net/route.h @@ -256,7 +256,7 @@ static inline void ip_route_connect_init(struct flowi4 *fl4, __be32 dst, __be32 if (inet_sk(sk)->transparent) flow_flags |= FLOWI_FLAG_ANYSRC; - if (netif_index_is_vrf(sock_net(sk), oif)) + if (netif_index_is_l3_master(sock_net(sk), oif)) flow_flags |= FLOWI_FLAG_VRFSRC | FLOWI_FLAG_SKIP_NH_OIF; flowi4_init_output(fl4, oif, sk->sk_mark, tos, RT_SCOPE_UNIVERSE, diff --git a/include/net/vrf.h b/include/net/vrf.h index 593e6094ddd4..34bb3f69def2 100644 --- a/include/net/vrf.h +++ b/include/net/vrf.h @@ -43,7 +43,7 @@ static inline int vrf_master_ifindex_rcu(const struct net_device *dev) if (!dev) return 0; - if (netif_is_vrf(dev)) { + if (netif_is_l3_master(dev)) { ifindex = dev->ifindex; } else { vrf_ptr = rcu_dereference(dev->vrf_ptr); @@ -125,7 +125,7 @@ static inline u32 vrf_dev_table_rtnl(const struct net_device *dev) return tb_id; } -/* caller has already checked netif_is_vrf(dev) */ +/* caller has already checked netif_is_l3_master(dev) */ static inline struct rtable *vrf_dev_get_rth(const struct net_device *dev) { struct rtable *rth = ERR_PTR(-ENETUNREACH); -- cgit v1.2.3 From 1b69c6d0ae90b7f1a4f61d5c8209d5cb7a55f849 Mon Sep 17 00:00:00 2001 From: David Ahern Date: Tue, 29 Sep 2015 20:07:11 -0700 Subject: net: Introduce L3 Master device abstraction L3 master devices allow users of the abstraction to influence FIB lookups for enslaved devices. Current API provides a means for the master device to return a specific FIB table for an enslaved device, to return an rtable/custom dst and influence the OIF used for fib lookups. Signed-off-by: David Ahern Signed-off-by: David S. Miller --- include/linux/netdevice.h | 3 ++ include/net/l3mdev.h | 125 ++++++++++++++++++++++++++++++++++++++++++++++ 2 files changed, 128 insertions(+) create mode 100644 include/net/l3mdev.h (limited to 'include') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 99c33e83822f..c7f14794fe14 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -1587,6 +1587,9 @@ struct net_device { #ifdef CONFIG_NET_SWITCHDEV const struct switchdev_ops *switchdev_ops; #endif +#ifdef CONFIG_NET_L3_MASTER_DEV + const struct l3mdev_ops *l3mdev_ops; +#endif const struct header_ops *header_ops; diff --git a/include/net/l3mdev.h b/include/net/l3mdev.h new file mode 100644 index 000000000000..e382c777bab8 --- /dev/null +++ b/include/net/l3mdev.h @@ -0,0 +1,125 @@ +/* + * include/net/l3mdev.h - L3 master device API + * Copyright (c) 2015 Cumulus Networks + * Copyright (c) 2015 David Ahern + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + */ +#ifndef _NET_L3MDEV_H_ +#define _NET_L3MDEV_H_ + +/** + * struct l3mdev_ops - l3mdev operations + * + * @l3mdev_fib_table: Get FIB table id to use for lookups + * + * @l3mdev_get_rtable: Get cached IPv4 rtable (dst_entry) for device + */ + +struct l3mdev_ops { + u32 (*l3mdev_fib_table)(const struct net_device *dev); + struct rtable * (*l3mdev_get_rtable)(const struct net_device *dev, + const struct flowi4 *fl4); +}; + +#ifdef CONFIG_NET_L3_MASTER_DEV + +int l3mdev_master_ifindex_rcu(struct net_device *dev); +static inline int l3mdev_master_ifindex(struct net_device *dev) +{ + int ifindex; + + rcu_read_lock(); + ifindex = l3mdev_master_ifindex_rcu(dev); + rcu_read_unlock(); + + return ifindex; +} + +/* get index of an interface to use for FIB lookups. For devices + * enslaved to an L3 master device FIB lookups are based on the + * master index + */ +static inline int l3mdev_fib_oif_rcu(struct net_device *dev) +{ + return l3mdev_master_ifindex_rcu(dev) ? : dev->ifindex; +} + +static inline int l3mdev_fib_oif(struct net_device *dev) +{ + int oif; + + rcu_read_lock(); + oif = l3mdev_fib_oif_rcu(dev); + rcu_read_unlock(); + + return oif; +} + +u32 l3mdev_fib_table_rcu(const struct net_device *dev); +u32 l3mdev_fib_table_by_index(struct net *net, int ifindex); +static inline u32 l3mdev_fib_table(const struct net_device *dev) +{ + u32 tb_id; + + rcu_read_lock(); + tb_id = l3mdev_fib_table_rcu(dev); + rcu_read_unlock(); + + return tb_id; +} + +static inline struct rtable *l3mdev_get_rtable(const struct net_device *dev, + const struct flowi4 *fl4) +{ + if (netif_is_l3_master(dev) && dev->l3mdev_ops->l3mdev_get_rtable) + return dev->l3mdev_ops->l3mdev_get_rtable(dev, fl4); + + return NULL; +} + +#else + +static inline int l3mdev_master_ifindex_rcu(struct net_device *dev) +{ + return 0; +} +static inline int l3mdev_master_ifindex(struct net_device *dev) +{ + return 0; +} + +static inline int l3mdev_fib_oif_rcu(struct net_device *dev) +{ + return dev ? dev->ifindex : 0; +} +static inline int l3mdev_fib_oif(struct net_device *dev) +{ + return dev ? dev->ifindex : 0; +} + +static inline u32 l3mdev_fib_table_rcu(const struct net_device *dev) +{ + return 0; +} +static inline u32 l3mdev_fib_table(const struct net_device *dev) +{ + return 0; +} +static inline u32 l3mdev_fib_table_by_index(struct net *net, int ifindex) +{ + return 0; +} + +static inline struct rtable *l3mdev_get_rtable(const struct net_device *dev, + const struct flowi4 *fl4) +{ + return NULL; +} + +#endif + +#endif /* _NET_L3MDEV_H_ */ -- cgit v1.2.3 From 385add906b6155e8bc64035ad56fb8ccfef925f7 Mon Sep 17 00:00:00 2001 From: David Ahern Date: Tue, 29 Sep 2015 20:07:13 -0700 Subject: net: Replace vrf_master_ifindex{, _rcu} with l3mdev equivalents Replace calls to vrf_master_ifindex_rcu and vrf_master_ifindex with either l3mdev_master_ifindex_rcu or l3mdev_master_ifindex. The pattern: oif = vrf_master_ifindex(dev) ? : dev->ifindex; is replaced with oif = l3mdev_fib_oif(dev); And remove the now unused vrf macros. Signed-off-by: David Ahern Signed-off-by: David S. Miller --- include/net/vrf.h | 41 ----------------------------------------- 1 file changed, 41 deletions(-) (limited to 'include') diff --git a/include/net/vrf.h b/include/net/vrf.h index 34bb3f69def2..874a6c9e4217 100644 --- a/include/net/vrf.h +++ b/include/net/vrf.h @@ -34,37 +34,6 @@ struct net_vrf { #if IS_ENABLED(CONFIG_NET_VRF) -/* called with rcu_read_lock() */ -static inline int vrf_master_ifindex_rcu(const struct net_device *dev) -{ - struct net_vrf_dev *vrf_ptr; - int ifindex = 0; - - if (!dev) - return 0; - - if (netif_is_l3_master(dev)) { - ifindex = dev->ifindex; - } else { - vrf_ptr = rcu_dereference(dev->vrf_ptr); - if (vrf_ptr) - ifindex = vrf_ptr->ifindex; - } - - return ifindex; -} - -static inline int vrf_master_ifindex(const struct net_device *dev) -{ - int ifindex; - - rcu_read_lock(); - ifindex = vrf_master_ifindex_rcu(dev); - rcu_read_unlock(); - - return ifindex; -} - /* called with rcu_read_lock */ static inline u32 vrf_dev_table_rcu(const struct net_device *dev) { @@ -139,16 +108,6 @@ static inline struct rtable *vrf_dev_get_rth(const struct net_device *dev) } #else -static inline int vrf_master_ifindex_rcu(const struct net_device *dev) -{ - return 0; -} - -static inline int vrf_master_ifindex(const struct net_device *dev) -{ - return 0; -} - static inline u32 vrf_dev_table_rcu(const struct net_device *dev) { return 0; -- cgit v1.2.3 From 3236b0042ba6555b45d75b6be12922922e17d66e Mon Sep 17 00:00:00 2001 From: David Ahern Date: Tue, 29 Sep 2015 20:07:14 -0700 Subject: net: Replace vrf_dev_table and friends Replace calls to vrf_dev_table and friends with l3mdev_fib_table and kin. Signed-off-by: David Ahern Signed-off-by: David S. Miller --- include/net/vrf.h | 80 ------------------------------------------------------- 1 file changed, 80 deletions(-) (limited to 'include') diff --git a/include/net/vrf.h b/include/net/vrf.h index 874a6c9e4217..b05b96646e2a 100644 --- a/include/net/vrf.h +++ b/include/net/vrf.h @@ -34,66 +34,6 @@ struct net_vrf { #if IS_ENABLED(CONFIG_NET_VRF) -/* called with rcu_read_lock */ -static inline u32 vrf_dev_table_rcu(const struct net_device *dev) -{ - u32 tb_id = 0; - - if (dev) { - struct net_vrf_dev *vrf_ptr; - - vrf_ptr = rcu_dereference(dev->vrf_ptr); - if (vrf_ptr) - tb_id = vrf_ptr->tb_id; - } - return tb_id; -} - -static inline u32 vrf_dev_table(const struct net_device *dev) -{ - u32 tb_id; - - rcu_read_lock(); - tb_id = vrf_dev_table_rcu(dev); - rcu_read_unlock(); - - return tb_id; -} - -static inline u32 vrf_dev_table_ifindex(struct net *net, int ifindex) -{ - struct net_device *dev; - u32 tb_id = 0; - - if (!ifindex) - return 0; - - rcu_read_lock(); - - dev = dev_get_by_index_rcu(net, ifindex); - if (dev) - tb_id = vrf_dev_table_rcu(dev); - - rcu_read_unlock(); - - return tb_id; -} - -/* called with rtnl */ -static inline u32 vrf_dev_table_rtnl(const struct net_device *dev) -{ - u32 tb_id = 0; - - if (dev) { - struct net_vrf_dev *vrf_ptr; - - vrf_ptr = rtnl_dereference(dev->vrf_ptr); - if (vrf_ptr) - tb_id = vrf_ptr->tb_id; - } - return tb_id; -} - /* caller has already checked netif_is_l3_master(dev) */ static inline struct rtable *vrf_dev_get_rth(const struct net_device *dev) { @@ -108,26 +48,6 @@ static inline struct rtable *vrf_dev_get_rth(const struct net_device *dev) } #else -static inline u32 vrf_dev_table_rcu(const struct net_device *dev) -{ - return 0; -} - -static inline u32 vrf_dev_table(const struct net_device *dev) -{ - return 0; -} - -static inline u32 vrf_dev_table_ifindex(struct net *net, int ifindex) -{ - return 0; -} - -static inline u32 vrf_dev_table_rtnl(const struct net_device *dev) -{ - return 0; -} - static inline struct rtable *vrf_dev_get_rth(const struct net_device *dev) { return ERR_PTR(-ENETUNREACH); -- cgit v1.2.3 From 8e1ed7058b3c79b085cf5b1529698a157499074c Mon Sep 17 00:00:00 2001 From: David Ahern Date: Tue, 29 Sep 2015 20:07:15 -0700 Subject: net: Replace calls to vrf_dev_get_rth Replace calls to vrf_dev_get_rth with l3mdev_get_rtable. The check on the flow flags is handled in the l3mdev operation. Signed-off-by: David Ahern Signed-off-by: David S. Miller --- include/net/vrf.h | 22 ---------------------- 1 file changed, 22 deletions(-) (limited to 'include') diff --git a/include/net/vrf.h b/include/net/vrf.h index b05b96646e2a..5bba1535ba73 100644 --- a/include/net/vrf.h +++ b/include/net/vrf.h @@ -32,26 +32,4 @@ struct net_vrf { u32 tb_id; }; - -#if IS_ENABLED(CONFIG_NET_VRF) -/* caller has already checked netif_is_l3_master(dev) */ -static inline struct rtable *vrf_dev_get_rth(const struct net_device *dev) -{ - struct rtable *rth = ERR_PTR(-ENETUNREACH); - struct net_vrf *vrf = netdev_priv(dev); - - if (vrf) { - rth = vrf->rth; - atomic_inc(&rth->dst.__refcnt); - } - return rth; -} - -#else -static inline struct rtable *vrf_dev_get_rth(const struct net_device *dev) -{ - return ERR_PTR(-ENETUNREACH); -} -#endif - #endif /* __LINUX_NET_VRF_H */ -- cgit v1.2.3 From 93a7e7e837af6846052481da974320c19ab82e5c Mon Sep 17 00:00:00 2001 From: David Ahern Date: Tue, 29 Sep 2015 20:07:16 -0700 Subject: net: Remove the now unused vrf_ptr Signed-off-by: David Ahern Signed-off-by: David S. Miller --- include/linux/netdevice.h | 2 -- include/net/vrf.h | 6 ------ 2 files changed, 8 deletions(-) (limited to 'include') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index c7f14794fe14..72bf9e37a2f0 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -1427,7 +1427,6 @@ enum netdev_priv_flags { * @dn_ptr: DECnet specific data * @ip6_ptr: IPv6 specific data * @ax25_ptr: AX.25 specific data - * @vrf_ptr: VRF specific data * @ieee80211_ptr: IEEE 802.11 specific data, assign before registering * * @last_rx: Time of last Rx @@ -1649,7 +1648,6 @@ struct net_device { struct dn_dev __rcu *dn_ptr; struct inet6_dev __rcu *ip6_ptr; void *ax25_ptr; - struct net_vrf_dev __rcu *vrf_ptr; struct wireless_dev *ieee80211_ptr; struct wpan_dev *ieee802154_ptr; #if IS_ENABLED(CONFIG_MPLS_ROUTING) diff --git a/include/net/vrf.h b/include/net/vrf.h index 5bba1535ba73..e83fc38770dd 100644 --- a/include/net/vrf.h +++ b/include/net/vrf.h @@ -11,12 +11,6 @@ #ifndef __LINUX_NET_VRF_H #define __LINUX_NET_VRF_H -struct net_vrf_dev { - struct rcu_head rcu; - int ifindex; /* ifindex of master dev */ - u32 tb_id; /* table id for VRF */ -}; - struct slave { struct list_head list; struct net_device *dev; -- cgit v1.2.3 From ec539514e56284b21c47468f23f7d01ff882f51b Mon Sep 17 00:00:00 2001 From: David Ahern Date: Tue, 29 Sep 2015 20:07:17 -0700 Subject: net: Remove vrf header file Move remaining structs to VRF driver and delete the vrf header file. Signed-off-by: David Ahern Signed-off-by: David S. Miller --- include/net/vrf.h | 29 ----------------------------- 1 file changed, 29 deletions(-) delete mode 100644 include/net/vrf.h (limited to 'include') diff --git a/include/net/vrf.h b/include/net/vrf.h deleted file mode 100644 index e83fc38770dd..000000000000 --- a/include/net/vrf.h +++ /dev/null @@ -1,29 +0,0 @@ -/* - * include/net/net_vrf.h - adds vrf dev structure definitions - * Copyright (c) 2015 Cumulus Networks - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License as published by - * the Free Software Foundation; either version 2 of the License, or - * (at your option) any later version. - */ - -#ifndef __LINUX_NET_VRF_H -#define __LINUX_NET_VRF_H - -struct slave { - struct list_head list; - struct net_device *dev; -}; - -struct slave_queue { - struct list_head all_slaves; -}; - -struct net_vrf { - struct slave_queue queue; - struct rtable *rth; - u32 tb_id; -}; - -#endif /* __LINUX_NET_VRF_H */ -- cgit v1.2.3 From 9478d12d33ad12d29c5343ae7346b51bc1f4c5a9 Mon Sep 17 00:00:00 2001 From: David Ahern Date: Tue, 29 Sep 2015 20:07:18 -0700 Subject: net: Move netif_index_is_l3_master to l3mdev.h Change CONFIG dependency to CONFIG_NET_L3_MASTER_DEV as well. Signed-off-by: David Ahern Signed-off-by: David S. Miller --- include/linux/netdevice.h | 21 --------------------- include/net/l3mdev.h | 24 ++++++++++++++++++++++++ include/net/route.h | 1 + 3 files changed, 25 insertions(+), 21 deletions(-) (limited to 'include') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 72bf9e37a2f0..b9450784ae06 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -3840,27 +3840,6 @@ static inline bool netif_is_ovs_master(const struct net_device *dev) return dev->priv_flags & IFF_OPENVSWITCH; } -static inline bool netif_index_is_l3_master(struct net *net, int ifindex) -{ - bool rc = false; - -#if IS_ENABLED(CONFIG_NET_VRF) - struct net_device *dev; - - if (ifindex == 0) - return false; - - rcu_read_lock(); - - dev = dev_get_by_index_rcu(net, ifindex); - if (dev) - rc = netif_is_l3_master(dev); - - rcu_read_unlock(); -#endif - return rc; -} - /* This device needs to keep skb dst for qdisc enqueue or ndo_start_xmit() */ static inline void netif_keep_dst(struct net_device *dev) { diff --git a/include/net/l3mdev.h b/include/net/l3mdev.h index e382c777bab8..87cee05a0a17 100644 --- a/include/net/l3mdev.h +++ b/include/net/l3mdev.h @@ -81,6 +81,25 @@ static inline struct rtable *l3mdev_get_rtable(const struct net_device *dev, return NULL; } +static inline bool netif_index_is_l3_master(struct net *net, int ifindex) +{ + struct net_device *dev; + bool rc = false; + + if (ifindex == 0) + return false; + + rcu_read_lock(); + + dev = dev_get_by_index_rcu(net, ifindex); + if (dev) + rc = netif_is_l3_master(dev); + + rcu_read_unlock(); + + return rc; +} + #else static inline int l3mdev_master_ifindex_rcu(struct net_device *dev) @@ -120,6 +139,11 @@ static inline struct rtable *l3mdev_get_rtable(const struct net_device *dev, return NULL; } +static inline bool netif_index_is_l3_master(struct net *net, int ifindex) +{ + return false; +} + #endif #endif /* _NET_L3MDEV_H_ */ diff --git a/include/net/route.h b/include/net/route.h index a565d0dad12c..e211dc167db1 100644 --- a/include/net/route.h +++ b/include/net/route.h @@ -28,6 +28,7 @@ #include #include #include +#include #include #include #include -- cgit v1.2.3 From 03d5fb18626aff95426a380aef0d1c6904cac7c9 Mon Sep 17 00:00:00 2001 From: Vivien Didelot Date: Tue, 29 Sep 2015 12:07:15 -0400 Subject: net: switchdev: remove dev from switchdev_obj cb The net_device associated to a dump operation does not have to be passed to the callback. switchdev stores it in a superset struct, if needed. Also some drivers (such as DSA drivers) may not have easy access to it. This will simplify pushing the callback function down to the drivers. Signed-off-by: Vivien Didelot Signed-off-by: David S. Miller --- include/net/switchdev.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/net/switchdev.h b/include/net/switchdev.h index 18207878e407..9ef7c5635769 100644 --- a/include/net/switchdev.h +++ b/include/net/switchdev.h @@ -66,7 +66,7 @@ enum switchdev_obj_id { struct switchdev_obj { enum switchdev_obj_id id; - int (*cb)(struct net_device *dev, struct switchdev_obj *obj); + int (*cb)(struct switchdev_obj *obj); union { struct switchdev_obj_vlan { /* PORT_VLAN */ u16 flags; -- cgit v1.2.3 From 25f07adc473f05f850efc9414b9da3374563015f Mon Sep 17 00:00:00 2001 From: Vivien Didelot Date: Tue, 29 Sep 2015 12:07:16 -0400 Subject: net: switchdev: pass callback to dump operation Similar to the notifier_call callback of a notifier_block, change the function signature of switchdev dump operation to: int switchdev_port_obj_dump(struct net_device *dev, enum switchdev_obj_id id, void *obj, int (*cb)(void *obj)); This allows the caller to pass and expect back a specific switchdev_obj_* structure instead of the generic switchdev_obj one. Drivers implementation of dump operation can now expect this specific structure and call the callback with it. Drivers have been changed accordingly. Signed-off-by: Vivien Didelot Signed-off-by: David S. Miller --- include/net/switchdev.h | 9 ++++++--- 1 file changed, 6 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/include/net/switchdev.h b/include/net/switchdev.h index 9ef7c5635769..a2f57fb5f622 100644 --- a/include/net/switchdev.h +++ b/include/net/switchdev.h @@ -120,7 +120,8 @@ struct switchdev_ops { int (*switchdev_port_obj_del)(struct net_device *dev, struct switchdev_obj *obj); int (*switchdev_port_obj_dump)(struct net_device *dev, - struct switchdev_obj *obj); + enum switchdev_obj_id id, void *obj, + int (*cb)(void *obj)); }; enum switchdev_notifier_type { @@ -152,7 +153,8 @@ int switchdev_port_attr_set(struct net_device *dev, struct switchdev_attr *attr); int switchdev_port_obj_add(struct net_device *dev, struct switchdev_obj *obj); int switchdev_port_obj_del(struct net_device *dev, struct switchdev_obj *obj); -int switchdev_port_obj_dump(struct net_device *dev, struct switchdev_obj *obj); +int switchdev_port_obj_dump(struct net_device *dev, enum switchdev_obj_id id, + void *obj, int (*cb)(void *obj)); int register_switchdev_notifier(struct notifier_block *nb); int unregister_switchdev_notifier(struct notifier_block *nb); int call_switchdev_notifiers(unsigned long val, struct net_device *dev, @@ -209,7 +211,8 @@ static inline int switchdev_port_obj_del(struct net_device *dev, } static inline int switchdev_port_obj_dump(struct net_device *dev, - struct switchdev_obj *obj) + enum switchdev_obj_id id, void *obj, + int (*cb)(void *obj)) { return -EOPNOTSUPP; } -- cgit v1.2.3 From ab06900230181b5a717b1e1a39c44e96f6292e71 Mon Sep 17 00:00:00 2001 From: Vivien Didelot Date: Tue, 29 Sep 2015 12:07:17 -0400 Subject: net: switchdev: abstract object in add/del ops Similar to the notifier_call callback of a notifier_block, change the function signature of switchdev add and del operations to: int switchdev_port_obj_add/del(struct net_device *dev, enum switchdev_obj_id id, void *obj); This allows the caller to pass a specific switchdev_obj_* structure instead of the generic switchdev_obj one. Drivers implementation of these operations and switchdev have been changed accordingly. Signed-off-by: Vivien Didelot Signed-off-by: David S. Miller --- include/net/switchdev.h | 18 ++++++++++++------ 1 file changed, 12 insertions(+), 6 deletions(-) (limited to 'include') diff --git a/include/net/switchdev.h b/include/net/switchdev.h index a2f57fb5f622..bcadac33c29c 100644 --- a/include/net/switchdev.h +++ b/include/net/switchdev.h @@ -115,10 +115,12 @@ struct switchdev_ops { struct switchdev_attr *attr, struct switchdev_trans *trans); int (*switchdev_port_obj_add)(struct net_device *dev, - struct switchdev_obj *obj, + enum switchdev_obj_id id, + const void *obj, struct switchdev_trans *trans); int (*switchdev_port_obj_del)(struct net_device *dev, - struct switchdev_obj *obj); + enum switchdev_obj_id id, + const void *obj); int (*switchdev_port_obj_dump)(struct net_device *dev, enum switchdev_obj_id id, void *obj, int (*cb)(void *obj)); @@ -151,8 +153,10 @@ int switchdev_port_attr_get(struct net_device *dev, struct switchdev_attr *attr); int switchdev_port_attr_set(struct net_device *dev, struct switchdev_attr *attr); -int switchdev_port_obj_add(struct net_device *dev, struct switchdev_obj *obj); -int switchdev_port_obj_del(struct net_device *dev, struct switchdev_obj *obj); +int switchdev_port_obj_add(struct net_device *dev, enum switchdev_obj_id id, + const void *obj); +int switchdev_port_obj_del(struct net_device *dev, enum switchdev_obj_id id, + const void *obj); int switchdev_port_obj_dump(struct net_device *dev, enum switchdev_obj_id id, void *obj, int (*cb)(void *obj)); int register_switchdev_notifier(struct notifier_block *nb); @@ -199,13 +203,15 @@ static inline int switchdev_port_attr_set(struct net_device *dev, } static inline int switchdev_port_obj_add(struct net_device *dev, - struct switchdev_obj *obj) + enum switchdev_obj_id id, + const void *obj) { return -EOPNOTSUPP; } static inline int switchdev_port_obj_del(struct net_device *dev, - struct switchdev_obj *obj) + enum switchdev_obj_id id, + const void *obj) { return -EOPNOTSUPP; } -- cgit v1.2.3 From 44bbcf5c4a19a8be43ba35ca7e22310e171f022c Mon Sep 17 00:00:00 2001 From: Vivien Didelot Date: Tue, 29 Sep 2015 12:07:18 -0400 Subject: net: switchdev: extract struct switchdev_obj_* Now that switchdev and its drivers directly use specific switchdev_obj_* structures, move them out of the switchdev_obj union and get rif of this outer structure. Signed-off-by: Vivien Didelot Signed-off-by: David S. Miller --- include/net/switchdev.h | 53 ++++++++++++++++++++++++------------------------- 1 file changed, 26 insertions(+), 27 deletions(-) (limited to 'include') diff --git a/include/net/switchdev.h b/include/net/switchdev.h index bcadac33c29c..e11425eb0735 100644 --- a/include/net/switchdev.h +++ b/include/net/switchdev.h @@ -64,30 +64,29 @@ enum switchdev_obj_id { SWITCHDEV_OBJ_PORT_FDB, }; -struct switchdev_obj { - enum switchdev_obj_id id; - int (*cb)(struct switchdev_obj *obj); - union { - struct switchdev_obj_vlan { /* PORT_VLAN */ - u16 flags; - u16 vid_begin; - u16 vid_end; - } vlan; - struct switchdev_obj_ipv4_fib { /* IPV4_FIB */ - u32 dst; - int dst_len; - struct fib_info *fi; - u8 tos; - u8 type; - u32 nlflags; - u32 tb_id; - } ipv4_fib; - struct switchdev_obj_fdb { /* PORT_FDB */ - const unsigned char *addr; - u16 vid; - u16 ndm_state; - } fdb; - } u; +/* SWITCHDEV_OBJ_PORT_VLAN */ +struct switchdev_obj_vlan { + u16 flags; + u16 vid_begin; + u16 vid_end; +}; + +/* SWITCHDEV_OBJ_IPV4_FIB */ +struct switchdev_obj_ipv4_fib { + u32 dst; + int dst_len; + struct fib_info *fi; + u8 tos; + u8 type; + u32 nlflags; + u32 tb_id; +}; + +/* SWITCHDEV_OBJ_PORT_FDB */ +struct switchdev_obj_fdb { + const unsigned char *addr; + u16 vid; + u16 ndm_state; }; void switchdev_trans_item_enqueue(struct switchdev_trans *trans, @@ -102,11 +101,11 @@ void *switchdev_trans_item_dequeue(struct switchdev_trans *trans); * * @switchdev_port_attr_set: Set a port attribute (see switchdev_attr). * - * @switchdev_port_obj_add: Add an object to port (see switchdev_obj). + * @switchdev_port_obj_add: Add an object to port (see switchdev_obj_*). * - * @switchdev_port_obj_del: Delete an object from port (see switchdev_obj). + * @switchdev_port_obj_del: Delete an object from port (see switchdev_obj_*). * - * @switchdev_port_obj_dump: Dump port objects (see switchdev_obj). + * @switchdev_port_obj_dump: Dump port objects (see switchdev_obj_*). */ struct switchdev_ops { int (*switchdev_port_attr_get)(struct net_device *dev, -- cgit v1.2.3 From 21fdd092acc7ebda0dfe682008592eb79c382707 Mon Sep 17 00:00:00 2001 From: David Ahern Date: Tue, 29 Sep 2015 09:32:03 -0700 Subject: net: Add support for filtering neigh dump by master device Add support for filtering neighbor dumps by master device by adding the NDA_MASTER attribute to the dump request. A new netlink flag, NLM_F_DUMP_FILTERED, is added to indicate the kernel supports the request and output is filtered as requested. Signed-off-by: David Ahern Acked-by: Roopa Prabhu Signed-off-by: David S. Miller --- include/uapi/linux/netlink.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/uapi/linux/netlink.h b/include/uapi/linux/netlink.h index 6f3fe16cd22a..f095155d8749 100644 --- a/include/uapi/linux/netlink.h +++ b/include/uapi/linux/netlink.h @@ -54,6 +54,7 @@ struct nlmsghdr { #define NLM_F_ACK 4 /* Reply with ack, with zero or error code */ #define NLM_F_ECHO 8 /* Echo this request */ #define NLM_F_DUMP_INTR 16 /* Dump was inconsistent due to sequence change */ +#define NLM_F_DUMP_FILTERED 32 /* Dump was filtered as requested */ /* Modifiers to GET request */ #define NLM_F_ROOT 0x100 /* specify tree root */ -- cgit v1.2.3 From 694869b3c5440e0d821583ec8811b6cb5d03742d Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Fri, 12 Jun 2015 21:55:31 -0500 Subject: ipv4: Pass struct net through ip_fragment Signed-off-by: "Eric W. Biederman" --- include/net/ip.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/net/ip.h b/include/net/ip.h index 91a6b2c88341..b783141b0671 100644 --- a/include/net/ip.h +++ b/include/net/ip.h @@ -109,8 +109,8 @@ int ip_local_deliver(struct sk_buff *skb); int ip_mr_input(struct sk_buff *skb); int ip_output(struct sock *sk, struct sk_buff *skb); int ip_mc_output(struct sock *sk, struct sk_buff *skb); -int ip_do_fragment(struct sock *sk, struct sk_buff *skb, - int (*output)(struct sock *, struct sk_buff *)); +int ip_do_fragment(struct net *net, struct sock *sk, struct sk_buff *skb, + int (*output)(struct net *, struct sock *, struct sk_buff *)); void ip_send_check(struct iphdr *ip); int __ip_local_out(struct sk_buff *skb); int ip_local_out_sk(struct sock *sk, struct sk_buff *skb); -- cgit v1.2.3 From 7d8c6e391575ee86c870b88635a163743fca9eac Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Fri, 12 Jun 2015 22:12:04 -0500 Subject: ipv6: Pass struct net through ip6_fragment Signed-off-by: Eric W. Biederman --- include/linux/netfilter_ipv6.h | 4 ++-- include/net/ip6_route.h | 4 ++-- 2 files changed, 4 insertions(+), 4 deletions(-) (limited to 'include') diff --git a/include/linux/netfilter_ipv6.h b/include/linux/netfilter_ipv6.h index 2ac8369fa96c..47c6b04c28c0 100644 --- a/include/linux/netfilter_ipv6.h +++ b/include/linux/netfilter_ipv6.h @@ -17,8 +17,8 @@ struct nf_ipv6_ops { int (*chk_addr)(struct net *net, const struct in6_addr *addr, const struct net_device *dev, int strict); void (*route_input)(struct sk_buff *skb); - int (*fragment)(struct sock *sk, struct sk_buff *skb, - int (*output)(struct sock *, struct sk_buff *)); + int (*fragment)(struct net *net, struct sock *sk, struct sk_buff *skb, + int (*output)(struct net *, struct sock *, struct sk_buff *)); }; #ifdef CONFIG_NETFILTER diff --git a/include/net/ip6_route.h b/include/net/ip6_route.h index 297629aadb19..2bfb2ad2fab1 100644 --- a/include/net/ip6_route.h +++ b/include/net/ip6_route.h @@ -173,8 +173,8 @@ static inline bool ipv6_anycast_destination(const struct dst_entry *dst, ipv6_addr_equal(&rt->rt6i_dst.addr, daddr)); } -int ip6_fragment(struct sock *sk, struct sk_buff *skb, - int (*output)(struct sock *, struct sk_buff *)); +int ip6_fragment(struct net *net, struct sock *sk, struct sk_buff *skb, + int (*output)(struct net *, struct sock *, struct sk_buff *)); static inline int ip6_skb_dst_mtu(struct sk_buff *skb) { -- cgit v1.2.3 From c648a0138b8f79b6cb4bd092dfab761e4becb1c2 Mon Sep 17 00:00:00 2001 From: Alexander Aring Date: Mon, 28 Sep 2015 09:00:23 +0200 Subject: netlink: add nla_get for le32 and le64 This patch adds missing inline wrappers for nla_get_le32 and nla_get_le64. The 802.15.4 MAC byteorder is little endian and we keep the byteorder for fields like address configuration in the same byteorder as it comes from the MAC layer. To provide these fields for nl802154 userspace applications, we need these inline wrappers for netlink. Cc: David S. Miller Signed-off-by: Alexander Aring Signed-off-by: Marcel Holtmann --- include/net/netlink.h | 18 ++++++++++++++++++ 1 file changed, 18 insertions(+) (limited to 'include') diff --git a/include/net/netlink.h b/include/net/netlink.h index 2a5dbcc90d1c..0e3172751755 100644 --- a/include/net/netlink.h +++ b/include/net/netlink.h @@ -1003,6 +1003,15 @@ static inline __be32 nla_get_be32(const struct nlattr *nla) return *(__be32 *) nla_data(nla); } +/** + * nla_get_le32 - return payload of __le32 attribute + * @nla: __le32 netlink attribute + */ +static inline __le32 nla_get_le32(const struct nlattr *nla) +{ + return *(__le32 *) nla_data(nla); +} + /** * nla_get_u16 - return payload of u16 attribute * @nla: u16 netlink attribute @@ -1065,6 +1074,15 @@ static inline __be64 nla_get_be64(const struct nlattr *nla) return tmp; } +/** + * nla_get_le64 - return payload of __le64 attribute + * @nla: __le64 netlink attribute + */ +static inline __le64 nla_get_le64(const struct nlattr *nla) +{ + return *(__le64 *) nla_data(nla); +} + /** * nla_get_s32 - return payload of s32 attribute * @nla: s32 netlink attribute -- cgit v1.2.3 From a26c5fd7622d4951425131d54a8c99f076fe2068 Mon Sep 17 00:00:00 2001 From: Alexander Aring Date: Mon, 28 Sep 2015 09:00:25 +0200 Subject: nl802154: add support for security layer This patch adds support for accessing mac802154 llsec implementation over nl802154. I added for a new Kconfig entry to provide this functionality CONFIG_IEEE802154_NL802154_EXPERIMENTAL. This interface is still in development. It provides to change security parameters and add/del/dump entries of security tables. Later we can add also a get to get an entry by unique identifier. Cc: Phoebe Buckheister Signed-off-by: Alexander Aring Signed-off-by: Marcel Holtmann --- include/net/cfg802154.h | 131 +++++++++++++++++++++++++++ include/net/ieee802154_netdev.h | 75 ---------------- include/net/nl802154.h | 191 ++++++++++++++++++++++++++++++++++++++++ 3 files changed, 322 insertions(+), 75 deletions(-) (limited to 'include') diff --git a/include/net/cfg802154.h b/include/net/cfg802154.h index 242273ccf34b..171cd76558fb 100644 --- a/include/net/cfg802154.h +++ b/include/net/cfg802154.h @@ -27,6 +27,16 @@ struct wpan_phy; struct wpan_phy_cca; +#ifdef CONFIG_IEEE802154_NL802154_EXPERIMENTAL +struct ieee802154_llsec_device_key; +struct ieee802154_llsec_seclevel; +struct ieee802154_llsec_params; +struct ieee802154_llsec_device; +struct ieee802154_llsec_table; +struct ieee802154_llsec_key_id; +struct ieee802154_llsec_key; +#endif /* CONFIG_IEEE802154_NL802154_EXPERIMENTAL */ + struct cfg802154_ops { struct net_device * (*add_virtual_intf_deprecated)(struct wpan_phy *wpan_phy, const char *name, @@ -65,6 +75,51 @@ struct cfg802154_ops { struct wpan_dev *wpan_dev, bool mode); int (*set_ackreq_default)(struct wpan_phy *wpan_phy, struct wpan_dev *wpan_dev, bool ackreq); +#ifdef CONFIG_IEEE802154_NL802154_EXPERIMENTAL + void (*get_llsec_table)(struct wpan_phy *wpan_phy, + struct wpan_dev *wpan_dev, + struct ieee802154_llsec_table **table); + void (*lock_llsec_table)(struct wpan_phy *wpan_phy, + struct wpan_dev *wpan_dev); + void (*unlock_llsec_table)(struct wpan_phy *wpan_phy, + struct wpan_dev *wpan_dev); + /* TODO remove locking/get table callbacks, this is part of the + * nl802154 interface and should be accessible from ieee802154 layer. + */ + int (*get_llsec_params)(struct wpan_phy *wpan_phy, + struct wpan_dev *wpan_dev, + struct ieee802154_llsec_params *params); + int (*set_llsec_params)(struct wpan_phy *wpan_phy, + struct wpan_dev *wpan_dev, + const struct ieee802154_llsec_params *params, + int changed); + int (*add_llsec_key)(struct wpan_phy *wpan_phy, + struct wpan_dev *wpan_dev, + const struct ieee802154_llsec_key_id *id, + const struct ieee802154_llsec_key *key); + int (*del_llsec_key)(struct wpan_phy *wpan_phy, + struct wpan_dev *wpan_dev, + const struct ieee802154_llsec_key_id *id); + int (*add_seclevel)(struct wpan_phy *wpan_phy, + struct wpan_dev *wpan_dev, + const struct ieee802154_llsec_seclevel *sl); + int (*del_seclevel)(struct wpan_phy *wpan_phy, + struct wpan_dev *wpan_dev, + const struct ieee802154_llsec_seclevel *sl); + int (*add_device)(struct wpan_phy *wpan_phy, + struct wpan_dev *wpan_dev, + const struct ieee802154_llsec_device *dev); + int (*del_device)(struct wpan_phy *wpan_phy, + struct wpan_dev *wpan_dev, __le64 extended_addr); + int (*add_devkey)(struct wpan_phy *wpan_phy, + struct wpan_dev *wpan_dev, + __le64 extended_addr, + const struct ieee802154_llsec_device_key *key); + int (*del_devkey)(struct wpan_phy *wpan_phy, + struct wpan_dev *wpan_dev, + __le64 extended_addr, + const struct ieee802154_llsec_device_key *key); +#endif /* CONFIG_IEEE802154_NL802154_EXPERIMENTAL */ }; static inline bool @@ -176,6 +231,82 @@ struct ieee802154_addr { }; }; +struct ieee802154_llsec_key_id { + u8 mode; + u8 id; + union { + struct ieee802154_addr device_addr; + __le32 short_source; + __le64 extended_source; + }; +}; + +#define IEEE802154_LLSEC_KEY_SIZE 16 + +struct ieee802154_llsec_key { + u8 frame_types; + u32 cmd_frame_ids; + /* TODO replace with NL802154_KEY_SIZE */ + u8 key[IEEE802154_LLSEC_KEY_SIZE]; +}; + +struct ieee802154_llsec_key_entry { + struct list_head list; + + struct ieee802154_llsec_key_id id; + struct ieee802154_llsec_key *key; +}; + +struct ieee802154_llsec_params { + bool enabled; + + __be32 frame_counter; + u8 out_level; + struct ieee802154_llsec_key_id out_key; + + __le64 default_key_source; + + __le16 pan_id; + __le64 hwaddr; + __le64 coord_hwaddr; + __le16 coord_shortaddr; +}; + +struct ieee802154_llsec_table { + struct list_head keys; + struct list_head devices; + struct list_head security_levels; +}; + +struct ieee802154_llsec_seclevel { + struct list_head list; + + u8 frame_type; + u8 cmd_frame_id; + bool device_override; + u32 sec_levels; +}; + +struct ieee802154_llsec_device { + struct list_head list; + + __le16 pan_id; + __le16 short_addr; + __le64 hwaddr; + u32 frame_counter; + bool seclevel_exempt; + + u8 key_mode; + struct list_head keys; +}; + +struct ieee802154_llsec_device_key { + struct list_head list; + + struct ieee802154_llsec_key_id key_id; + u32 frame_counter; +}; + struct wpan_dev_header_ops { /* TODO create callback currently assumes ieee802154_mac_cb inside * skb->cb. This should be changed to give these information as diff --git a/include/net/ieee802154_netdev.h b/include/net/ieee802154_netdev.h index aebb9d8d7a11..a62a051a3a2f 100644 --- a/include/net/ieee802154_netdev.h +++ b/include/net/ieee802154_netdev.h @@ -234,38 +234,6 @@ static inline struct ieee802154_mac_cb *mac_cb_init(struct sk_buff *skb) return mac_cb(skb); } -#define IEEE802154_LLSEC_KEY_SIZE 16 - -struct ieee802154_llsec_key_id { - u8 mode; - u8 id; - union { - struct ieee802154_addr device_addr; - __le32 short_source; - __le64 extended_source; - }; -}; - -struct ieee802154_llsec_key { - u8 frame_types; - u32 cmd_frame_ids; - u8 key[IEEE802154_LLSEC_KEY_SIZE]; -}; - -struct ieee802154_llsec_key_entry { - struct list_head list; - - struct ieee802154_llsec_key_id id; - struct ieee802154_llsec_key *key; -}; - -struct ieee802154_llsec_device_key { - struct list_head list; - - struct ieee802154_llsec_key_id key_id; - u32 frame_counter; -}; - enum { IEEE802154_LLSEC_DEVKEY_IGNORE, IEEE802154_LLSEC_DEVKEY_RESTRICT, @@ -274,49 +242,6 @@ enum { __IEEE802154_LLSEC_DEVKEY_MAX, }; -struct ieee802154_llsec_device { - struct list_head list; - - __le16 pan_id; - __le16 short_addr; - __le64 hwaddr; - u32 frame_counter; - bool seclevel_exempt; - - u8 key_mode; - struct list_head keys; -}; - -struct ieee802154_llsec_seclevel { - struct list_head list; - - u8 frame_type; - u8 cmd_frame_id; - bool device_override; - u32 sec_levels; -}; - -struct ieee802154_llsec_params { - bool enabled; - - __be32 frame_counter; - u8 out_level; - struct ieee802154_llsec_key_id out_key; - - __le64 default_key_source; - - __le16 pan_id; - __le64 hwaddr; - __le64 coord_hwaddr; - __le16 coord_shortaddr; -}; - -struct ieee802154_llsec_table { - struct list_head keys; - struct list_head devices; - struct list_head security_levels; -}; - #define IEEE802154_MAC_SCAN_ED 0 #define IEEE802154_MAC_SCAN_ACTIVE 1 #define IEEE802154_MAC_SCAN_PASSIVE 2 diff --git a/include/net/nl802154.h b/include/net/nl802154.h index cf2713d8b975..32cb3e591e07 100644 --- a/include/net/nl802154.h +++ b/include/net/nl802154.h @@ -56,6 +56,22 @@ enum nl802154_commands { /* add new commands above here */ +#ifdef CONFIG_IEEE802154_NL802154_EXPERIMENTAL + NL802154_CMD_SET_SEC_PARAMS, + NL802154_CMD_GET_SEC_KEY, /* can dump */ + NL802154_CMD_NEW_SEC_KEY, + NL802154_CMD_DEL_SEC_KEY, + NL802154_CMD_GET_SEC_DEV, /* can dump */ + NL802154_CMD_NEW_SEC_DEV, + NL802154_CMD_DEL_SEC_DEV, + NL802154_CMD_GET_SEC_DEVKEY, /* can dump */ + NL802154_CMD_NEW_SEC_DEVKEY, + NL802154_CMD_DEL_SEC_DEVKEY, + NL802154_CMD_GET_SEC_LEVEL, /* can dump */ + NL802154_CMD_NEW_SEC_LEVEL, + NL802154_CMD_DEL_SEC_LEVEL, +#endif /* CONFIG_IEEE802154_NL802154_EXPERIMENTAL */ + /* used to define NL802154_CMD_MAX below */ __NL802154_CMD_AFTER_LAST, NL802154_CMD_MAX = __NL802154_CMD_AFTER_LAST - 1 @@ -110,6 +126,18 @@ enum nl802154_attrs { /* add attributes here, update the policy in nl802154.c */ +#ifdef CONFIG_IEEE802154_NL802154_EXPERIMENTAL + NL802154_ATTR_SEC_ENABLED, + NL802154_ATTR_SEC_OUT_LEVEL, + NL802154_ATTR_SEC_OUT_KEY_ID, + NL802154_ATTR_SEC_FRAME_COUNTER, + + NL802154_ATTR_SEC_LEVEL, + NL802154_ATTR_SEC_DEVICE, + NL802154_ATTR_SEC_DEVKEY, + NL802154_ATTR_SEC_KEY, +#endif /* CONFIG_IEEE802154_NL802154_EXPERIMENTAL */ + __NL802154_ATTR_AFTER_LAST, NL802154_ATTR_MAX = __NL802154_ATTR_AFTER_LAST - 1 }; @@ -247,4 +275,167 @@ enum nl802154_supported_bool_states { NL802154_SUPPORTED_BOOL_MAX = __NL802154_SUPPORTED_BOOL_AFTER_LAST - 1 }; +#ifdef CONFIG_IEEE802154_NL802154_EXPERIMENTAL + +enum nl802154_dev_addr_modes { + NL802154_DEV_ADDR_NONE, + __NL802154_DEV_ADDR_INVALID, + NL802154_DEV_ADDR_SHORT, + NL802154_DEV_ADDR_EXTENDED, + + /* keep last */ + __NL802154_DEV_ADDR_AFTER_LAST, + NL802154_DEV_ADDR_MAX = __NL802154_DEV_ADDR_AFTER_LAST - 1 +}; + +enum nl802154_dev_addr_attrs { + NL802154_DEV_ADDR_ATTR_UNSPEC, + + NL802154_DEV_ADDR_ATTR_PAN_ID, + NL802154_DEV_ADDR_ATTR_MODE, + NL802154_DEV_ADDR_ATTR_SHORT, + NL802154_DEV_ADDR_ATTR_EXTENDED, + + /* keep last */ + __NL802154_DEV_ADDR_ATTR_AFTER_LAST, + NL802154_DEV_ADDR_ATTR_MAX = __NL802154_DEV_ADDR_ATTR_AFTER_LAST - 1 +}; + +enum nl802154_key_id_modes { + NL802154_KEY_ID_MODE_IMPLICIT, + NL802154_KEY_ID_MODE_INDEX, + NL802154_KEY_ID_MODE_INDEX_SHORT, + NL802154_KEY_ID_MODE_INDEX_EXTENDED, + + /* keep last */ + __NL802154_KEY_ID_MODE_AFTER_LAST, + NL802154_KEY_ID_MODE_MAX = __NL802154_KEY_ID_MODE_AFTER_LAST - 1 +}; + +enum nl802154_key_id_attrs { + NL802154_KEY_ID_ATTR_UNSPEC, + + NL802154_KEY_ID_ATTR_MODE, + NL802154_KEY_ID_ATTR_INDEX, + NL802154_KEY_ID_ATTR_IMPLICIT, + NL802154_KEY_ID_ATTR_SOURCE_SHORT, + NL802154_KEY_ID_ATTR_SOURCE_EXTENDED, + + /* keep last */ + __NL802154_KEY_ID_ATTR_AFTER_LAST, + NL802154_KEY_ID_ATTR_MAX = __NL802154_KEY_ID_ATTR_AFTER_LAST - 1 +}; + +enum nl802154_seclevels { + NL802154_SECLEVEL_NONE, + NL802154_SECLEVEL_MIC32, + NL802154_SECLEVEL_MIC64, + NL802154_SECLEVEL_MIC128, + NL802154_SECLEVEL_ENC, + NL802154_SECLEVEL_ENC_MIC32, + NL802154_SECLEVEL_ENC_MIC64, + NL802154_SECLEVEL_ENC_MIC128, + + /* keep last */ + __NL802154_SECLEVEL_AFTER_LAST, + NL802154_SECLEVEL_MAX = __NL802154_SECLEVEL_AFTER_LAST - 1 +}; + +enum nl802154_frames { + NL802154_FRAME_BEACON, + NL802154_FRAME_DATA, + NL802154_FRAME_ACK, + NL802154_FRAME_CMD, + + /* keep last */ + __NL802154_FRAME_AFTER_LAST, + NL802154_FRAME_MAX = __NL802154_FRAME_AFTER_LAST - 1 +}; + +enum nl802154_cmd_frames { + __NL802154_CMD_FRAME_INVALID, + NL802154_CMD_FRAME_ASSOC_REQUEST, + NL802154_CMD_FRAME_ASSOC_RESPONSE, + NL802154_CMD_FRAME_DISASSOC_NOTIFY, + NL802154_CMD_FRAME_DATA_REQUEST, + NL802154_CMD_FRAME_PAN_ID_CONFLICT_NOTIFY, + NL802154_CMD_FRAME_ORPHAN_NOTIFY, + NL802154_CMD_FRAME_BEACON_REQUEST, + NL802154_CMD_FRAME_COORD_REALIGNMENT, + NL802154_CMD_FRAME_GTS_REQUEST, + + /* keep last */ + __NL802154_CMD_FRAME_AFTER_LAST, + NL802154_CMD_FRAME_MAX = __NL802154_CMD_FRAME_AFTER_LAST - 1 +}; + +enum nl802154_seclevel_attrs { + NL802154_SECLEVEL_ATTR_UNSPEC, + + NL802154_SECLEVEL_ATTR_LEVELS, + NL802154_SECLEVEL_ATTR_FRAME, + NL802154_SECLEVEL_ATTR_CMD_FRAME, + NL802154_SECLEVEL_ATTR_DEV_OVERRIDE, + + /* keep last */ + __NL802154_SECLEVEL_ATTR_AFTER_LAST, + NL802154_SECLEVEL_ATTR_MAX = __NL802154_SECLEVEL_ATTR_AFTER_LAST - 1 +}; + +/* TODO what is this? couldn't find in mib */ +enum { + NL802154_DEVKEY_IGNORE, + NL802154_DEVKEY_RESTRICT, + NL802154_DEVKEY_RECORD, + + /* keep last */ + __NL802154_DEVKEY_AFTER_LAST, + NL802154_DEVKEY_MAX = __NL802154_DEVKEY_AFTER_LAST - 1 +}; + +enum nl802154_dev { + NL802154_DEV_ATTR_UNSPEC, + + NL802154_DEV_ATTR_FRAME_COUNTER, + NL802154_DEV_ATTR_PAN_ID, + NL802154_DEV_ATTR_SHORT_ADDR, + NL802154_DEV_ATTR_EXTENDED_ADDR, + NL802154_DEV_ATTR_SECLEVEL_EXEMPT, + NL802154_DEV_ATTR_KEY_MODE, + + /* keep last */ + __NL802154_DEV_ATTR_AFTER_LAST, + NL802154_DEV_ATTR_MAX = __NL802154_DEV_ATTR_AFTER_LAST - 1 +}; + +enum nl802154_devkey { + NL802154_DEVKEY_ATTR_UNSPEC, + + NL802154_DEVKEY_ATTR_FRAME_COUNTER, + NL802154_DEVKEY_ATTR_EXTENDED_ADDR, + NL802154_DEVKEY_ATTR_ID, + + /* keep last */ + __NL802154_DEVKEY_ATTR_AFTER_LAST, + NL802154_DEVKEY_ATTR_MAX = __NL802154_DEVKEY_ATTR_AFTER_LAST - 1 +}; + +enum nl802154_key { + NL802154_KEY_ATTR_UNSPEC, + + NL802154_KEY_ATTR_ID, + NL802154_KEY_ATTR_USAGE_FRAMES, + NL802154_KEY_ATTR_USAGE_CMDS, + NL802154_KEY_ATTR_BYTES, + + /* keep last */ + __NL802154_KEY_ATTR_AFTER_LAST, + NL802154_KEY_ATTR_MAX = __NL802154_KEY_ATTR_AFTER_LAST - 1 +}; + +#define NL802154_KEY_SIZE 16 +#define NL802154_CMD_FRAME_NR_IDS 256 + +#endif /* CONFIG_IEEE802154_NL802154_EXPERIMENTAL */ + #endif /* __NL802154_H */ -- cgit v1.2.3 From 5f2ebb3b59c81a461ffd4921d12e9f6e09c32945 Mon Sep 17 00:00:00 2001 From: Alexander Aring Date: Mon, 28 Sep 2015 19:59:48 +0200 Subject: mac802154: check on len instead mac_len This patch change the length check to len instead of mac_len for checking if the frame control field is available to dereference. We need to change it because I saw issues with af_packet raw sockets and the mrf24j40 which calls this functionality. The raw socket functionality doesn't set the mac_len but resets the skb_mac_header to skb->data which is still correct. The issue occur at mrf24j40 only, because the driver need to evaluate the fc fields. Signed-off-by: Alexander Aring Signed-off-by: Marcel Holtmann --- include/net/mac802154.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/net/mac802154.h b/include/net/mac802154.h index 2c478501ad14..5718765cbd95 100644 --- a/include/net/mac802154.h +++ b/include/net/mac802154.h @@ -248,7 +248,7 @@ struct ieee802154_ops { static inline __le16 ieee802154_get_fc_from_skb(const struct sk_buff *skb) { /* return some invalid fc on failure */ - if (unlikely(skb->mac_len < 2)) { + if (unlikely(skb->len < 2)) { WARN_ON(1); return cpu_to_le16(0); } -- cgit v1.2.3 From fff1f3001cc58b5064a0f1154a7ac09b76f29c44 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Fri, 2 Oct 2015 11:43:23 -0700 Subject: tcp: add a spinlock to protect struct request_sock_queue struct request_sock_queue fields are currently protected by the listener 'lock' (not a real spinlock) We need to add a private spinlock instead, so that softirq handlers creating children do not have to worry with backlog notion that the listener 'lock' carries. Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- include/net/request_sock.h | 37 ++++++++++++++++++------------------- 1 file changed, 18 insertions(+), 19 deletions(-) (limited to 'include') diff --git a/include/net/request_sock.h b/include/net/request_sock.h index d2544de329bd..202e36163ae3 100644 --- a/include/net/request_sock.h +++ b/include/net/request_sock.h @@ -176,9 +176,11 @@ struct fastopen_queue { * */ struct request_sock_queue { + spinlock_t rskq_lock; + u8 rskq_defer_accept; + struct request_sock *rskq_accept_head; struct request_sock *rskq_accept_tail; - u8 rskq_defer_accept; struct listen_sock *listen_opt; struct fastopen_queue fastopenq; /* Check max_qlen != 0 to determine * if TFO is enabled. @@ -196,16 +198,7 @@ void reqsk_queue_destroy(struct request_sock_queue *queue); void reqsk_fastopen_remove(struct sock *sk, struct request_sock *req, bool reset); -static inline struct request_sock * - reqsk_queue_yank_acceptq(struct request_sock_queue *queue) -{ - struct request_sock *req = queue->rskq_accept_head; - - queue->rskq_accept_head = NULL; - return req; -} - -static inline int reqsk_queue_empty(struct request_sock_queue *queue) +static inline bool reqsk_queue_empty(const struct request_sock_queue *queue) { return queue->rskq_accept_head == NULL; } @@ -215,6 +208,7 @@ static inline void reqsk_queue_add(struct request_sock_queue *queue, struct sock *parent, struct sock *child) { + spin_lock(&queue->rskq_lock); req->sk = child; sk_acceptq_added(parent); @@ -225,18 +219,23 @@ static inline void reqsk_queue_add(struct request_sock_queue *queue, queue->rskq_accept_tail = req; req->dl_next = NULL; + spin_unlock(&queue->rskq_lock); } -static inline struct request_sock *reqsk_queue_remove(struct request_sock_queue *queue) +static inline struct request_sock *reqsk_queue_remove(struct request_sock_queue *queue, + struct sock *parent) { - struct request_sock *req = queue->rskq_accept_head; - - WARN_ON(req == NULL); - - queue->rskq_accept_head = req->dl_next; - if (queue->rskq_accept_head == NULL) - queue->rskq_accept_tail = NULL; + struct request_sock *req; + spin_lock_bh(&queue->rskq_lock); + req = queue->rskq_accept_head; + if (req) { + sk_acceptq_removed(parent); + queue->rskq_accept_head = req->dl_next; + if (queue->rskq_accept_head == NULL) + queue->rskq_accept_tail = NULL; + } + spin_unlock_bh(&queue->rskq_lock); return req; } -- cgit v1.2.3 From aac065c50aba0c534a929aeb687eb68c58e523b8 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Fri, 2 Oct 2015 11:43:24 -0700 Subject: tcp: move qlen/young out of struct listen_sock qlen_inc & young_inc were protected by listener lock, while qlen_dec & young_dec were atomic fields. Everything needs to be atomic for upcoming lockless listener. Also move qlen/young in request_sock_queue as we'll get rid of struct listen_sock eventually. Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- include/net/request_sock.h | 40 ++++++++++------------------------------ 1 file changed, 10 insertions(+), 30 deletions(-) (limited to 'include') diff --git a/include/net/request_sock.h b/include/net/request_sock.h index 202e36163ae3..d128e7f89042 100644 --- a/include/net/request_sock.h +++ b/include/net/request_sock.h @@ -122,14 +122,7 @@ extern int sysctl_max_syn_backlog; * @max_qlen_log - log_2 of maximal queued SYNs/REQUESTs */ struct listen_sock { - int qlen_inc; /* protected by listener lock */ - int young_inc;/* protected by listener lock */ - - /* following fields can be updated by timer */ - atomic_t qlen_dec; /* qlen = qlen_inc - qlen_dec */ - atomic_t young_dec; - - u32 max_qlen_log ____cacheline_aligned_in_smp; + u32 max_qlen_log; u32 synflood_warned; u32 hash_rnd; u32 nr_table_entries; @@ -179,6 +172,9 @@ struct request_sock_queue { spinlock_t rskq_lock; u8 rskq_defer_accept; + atomic_t qlen; + atomic_t young; + struct request_sock *rskq_accept_head; struct request_sock *rskq_accept_tail; struct listen_sock *listen_opt; @@ -242,41 +238,25 @@ static inline struct request_sock *reqsk_queue_remove(struct request_sock_queue static inline void reqsk_queue_removed(struct request_sock_queue *queue, const struct request_sock *req) { - struct listen_sock *lopt = queue->listen_opt; - if (req->num_timeout == 0) - atomic_inc(&lopt->young_dec); - atomic_inc(&lopt->qlen_dec); + atomic_dec(&queue->young); + atomic_dec(&queue->qlen); } static inline void reqsk_queue_added(struct request_sock_queue *queue) { - struct listen_sock *lopt = queue->listen_opt; - - lopt->young_inc++; - lopt->qlen_inc++; -} - -static inline int listen_sock_qlen(const struct listen_sock *lopt) -{ - return lopt->qlen_inc - atomic_read(&lopt->qlen_dec); -} - -static inline int listen_sock_young(const struct listen_sock *lopt) -{ - return lopt->young_inc - atomic_read(&lopt->young_dec); + atomic_inc(&queue->young); + atomic_inc(&queue->qlen); } static inline int reqsk_queue_len(const struct request_sock_queue *queue) { - const struct listen_sock *lopt = queue->listen_opt; - - return lopt ? listen_sock_qlen(lopt) : 0; + return atomic_read(&queue->qlen); } static inline int reqsk_queue_len_young(const struct request_sock_queue *queue) { - return listen_sock_young(queue->listen_opt); + return atomic_read(&queue->young); } static inline int reqsk_queue_is_full(const struct request_sock_queue *queue) -- cgit v1.2.3 From 8d2675f1e464aa5cedda63849adecffd8d33fead Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Fri, 2 Oct 2015 11:43:25 -0700 Subject: tcp: move synflood_warned into struct request_sock_queue long term plan is to remove struct listen_sock when its hash table is no longer there. Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- include/net/request_sock.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/net/request_sock.h b/include/net/request_sock.h index d128e7f89042..273fb7235ce3 100644 --- a/include/net/request_sock.h +++ b/include/net/request_sock.h @@ -123,7 +123,6 @@ extern int sysctl_max_syn_backlog; */ struct listen_sock { u32 max_qlen_log; - u32 synflood_warned; u32 hash_rnd; u32 nr_table_entries; struct request_sock *syn_table[0]; @@ -171,6 +170,7 @@ struct fastopen_queue { struct request_sock_queue { spinlock_t rskq_lock; u8 rskq_defer_accept; + u32 synflood_warned; atomic_t qlen; atomic_t young; -- cgit v1.2.3 From b267cdd1075d28501b7c05c7aeb8466775505e8d Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Fri, 2 Oct 2015 11:43:27 -0700 Subject: tcp/dccp: init sk_prot and call sk_node_init() in reqsk_alloc() We plan to use generic functions to insert request sockets into ehash table. sk_prot needs to be set (to retrieve sk_prot->h.hashinfo) sk_node needs to be cleared. Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- include/net/request_sock.h | 22 ++++++++++++---------- 1 file changed, 12 insertions(+), 10 deletions(-) (limited to 'include') diff --git a/include/net/request_sock.h b/include/net/request_sock.h index 273fb7235ce3..97c1ba61ed2d 100644 --- a/include/net/request_sock.h +++ b/include/net/request_sock.h @@ -69,6 +69,16 @@ struct request_sock { u32 peer_secid; }; +static inline struct request_sock *inet_reqsk(struct sock *sk) +{ + return (struct request_sock *)sk; +} + +static inline struct sock *req_to_sk(struct request_sock *req) +{ + return (struct sock *)req; +} + static inline struct request_sock * reqsk_alloc(const struct request_sock_ops *ops, struct sock *sk_listener) { @@ -78,6 +88,8 @@ reqsk_alloc(const struct request_sock_ops *ops, struct sock *sk_listener) req->rsk_ops = ops; sock_hold(sk_listener); req->rsk_listener = sk_listener; + req_to_sk(req)->sk_prot = sk_listener->sk_prot; + sk_node_init(&req_to_sk(req)->sk_node); req->saved_syn = NULL; /* Following is temporary. It is coupled with debugging * helpers in reqsk_put() & reqsk_free() @@ -87,16 +99,6 @@ reqsk_alloc(const struct request_sock_ops *ops, struct sock *sk_listener) return req; } -static inline struct request_sock *inet_reqsk(struct sock *sk) -{ - return (struct request_sock *)sk; -} - -static inline struct sock *req_to_sk(struct request_sock *req) -{ - return (struct sock *)req; -} - static inline void reqsk_free(struct request_sock *req) { /* temporary debugging */ -- cgit v1.2.3 From aa3a0c8ce651b5e16124866b0a10d1b90b9ef022 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Fri, 2 Oct 2015 11:43:30 -0700 Subject: tcp: get_openreq[46]() changes When request sockets are no longer in a per listener hash table but on regular TCP ehash, we need to access listener uid through req->rsk_listener get_openreq6() also gets a const for its request socket argument. Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- include/net/tcp.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include') diff --git a/include/net/tcp.h b/include/net/tcp.h index 2c7dfe52f473..a26341d2ad67 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -1637,7 +1637,6 @@ struct tcp_iter_state { enum tcp_seq_states state; struct sock *syn_wait_sk; int bucket, offset, sbucket, num; - kuid_t uid; loff_t last_pos; }; -- cgit v1.2.3 From 2feda34192a379f8b35a7c6c5826b2f23e884f32 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Fri, 2 Oct 2015 11:43:31 -0700 Subject: tcp/dccp: remove inet_csk_reqsk_queue_added() timeout argument This is no longer used. Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- include/net/inet_connection_sock.h | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) (limited to 'include') diff --git a/include/net/inet_connection_sock.h b/include/net/inet_connection_sock.h index ee54f21a8113..b2e2e30befa9 100644 --- a/include/net/inet_connection_sock.h +++ b/include/net/inet_connection_sock.h @@ -282,8 +282,7 @@ static inline void inet_csk_reqsk_queue_add(struct sock *sk, void inet_csk_reqsk_queue_hash_add(struct sock *sk, struct request_sock *req, unsigned long timeout); -static inline void inet_csk_reqsk_queue_added(struct sock *sk, - const unsigned long timeout) +static inline void inet_csk_reqsk_queue_added(struct sock *sk) { reqsk_queue_added(&inet_csk(sk)->icsk_accept_queue); } -- cgit v1.2.3 From 079096f103faca2dd87342cca6f23d4b34da8871 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Fri, 2 Oct 2015 11:43:32 -0700 Subject: tcp/dccp: install syn_recv requests into ehash table In this patch, we insert request sockets into TCP/DCCP regular ehash table (where ESTABLISHED and TIMEWAIT sockets are) instead of using the per listener hash table. ACK packets find SYN_RECV pseudo sockets without having to find and lock the listener. In nominal conditions, this halves pressure on listener lock. Note that this will allow for SO_REUSEPORT refinements, so that we can select a listener using cpu/numa affinities instead of the prior 'consistent hash', since only SYN packets will apply this selection logic. We will shrink listen_sock in the following patch to ease code review. Signed-off-by: Eric Dumazet Cc: Ying Cai Cc: Willem de Bruijn Signed-off-by: David S. Miller --- include/net/inet_connection_sock.h | 4 ---- include/net/inet_hashtables.h | 1 + include/net/request_sock.h | 4 ---- include/net/tcp.h | 3 --- 4 files changed, 1 insertion(+), 11 deletions(-) (limited to 'include') diff --git a/include/net/inet_connection_sock.h b/include/net/inet_connection_sock.h index b2e2e30befa9..730aa034cd3d 100644 --- a/include/net/inet_connection_sock.h +++ b/include/net/inet_connection_sock.h @@ -258,10 +258,6 @@ inet_csk_rto_backoff(const struct inet_connection_sock *icsk, struct sock *inet_csk_accept(struct sock *sk, int flags, int *err); -struct request_sock *inet_csk_search_req(struct sock *sk, - const __be16 rport, - const __be32 raddr, - const __be32 laddr); int inet_csk_bind_conflict(const struct sock *sk, const struct inet_bind_bucket *tb, bool relax); int inet_csk_get_port(struct sock *sk, unsigned short snum); diff --git a/include/net/inet_hashtables.h b/include/net/inet_hashtables.h index 3fb778d7c875..6683ada25fef 100644 --- a/include/net/inet_hashtables.h +++ b/include/net/inet_hashtables.h @@ -205,6 +205,7 @@ void inet_put_port(struct sock *sk); void inet_hashinfo_init(struct inet_hashinfo *h); +int inet_ehash_insert(struct sock *sk, struct sock *osk); void __inet_hash_nolisten(struct sock *sk, struct sock *osk); void __inet_hash(struct sock *sk, struct sock *osk); void inet_hash(struct sock *sk); diff --git a/include/net/request_sock.h b/include/net/request_sock.h index 97c1ba61ed2d..e1850923c4f5 100644 --- a/include/net/request_sock.h +++ b/include/net/request_sock.h @@ -266,8 +266,4 @@ static inline int reqsk_queue_is_full(const struct request_sock_queue *queue) return reqsk_queue_len(queue) >> queue->listen_opt->max_qlen_log; } -void reqsk_queue_hash_req(struct request_sock_queue *queue, - u32 hash, struct request_sock *req, - unsigned long timeout); - #endif /* _REQUEST_SOCK_H */ diff --git a/include/net/tcp.h b/include/net/tcp.h index a26341d2ad67..225e9561af35 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -1618,7 +1618,6 @@ static inline bool tcp_stream_is_thin(struct tcp_sock *tp) /* /proc */ enum tcp_seq_states { TCP_SEQ_STATE_LISTENING, - TCP_SEQ_STATE_OPENREQ, TCP_SEQ_STATE_ESTABLISHED, }; @@ -1717,8 +1716,6 @@ struct tcp_request_sock_ops { int (*send_synack)(const struct sock *sk, struct dst_entry *dst, struct flowi *fl, struct request_sock *req, u16 queue_mapping, struct tcp_fastopen_cookie *foc); - void (*queue_hash_add)(struct sock *sk, struct request_sock *req, - const unsigned long timeout); }; #ifdef CONFIG_SYN_COOKIES -- cgit v1.2.3 From 81b496b31a4331415b6a644b485a329ec0b45155 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Fri, 2 Oct 2015 11:43:33 -0700 Subject: tcp/dccp: shrink struct listen_sock We no longer use hash_rnd, nr_table_entries and syn_table[] For a listener with a backlog of 10 millions sockets, this saves 80 MBytes of vmalloced memory. Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- include/net/request_sock.h | 3 --- 1 file changed, 3 deletions(-) (limited to 'include') diff --git a/include/net/request_sock.h b/include/net/request_sock.h index e1850923c4f5..353cb61bb399 100644 --- a/include/net/request_sock.h +++ b/include/net/request_sock.h @@ -125,9 +125,6 @@ extern int sysctl_max_syn_backlog; */ struct listen_sock { u32 max_qlen_log; - u32 hash_rnd; - u32 nr_table_entries; - struct request_sock *syn_table[0]; }; /* -- cgit v1.2.3 From 1b33bc3e9e903f7293f7dfe80a875b2a5d0305aa Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Fri, 2 Oct 2015 11:43:34 -0700 Subject: ipv6: remove obsolete inet6 functions inet6_csk_search_req() and inet6_csk_reqsk_queue_hash_add() no longer exist. Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- include/net/inet6_connection_sock.h | 9 --------- 1 file changed, 9 deletions(-) (limited to 'include') diff --git a/include/net/inet6_connection_sock.h b/include/net/inet6_connection_sock.h index 79b2a4c09ca6..064cfbe639d0 100644 --- a/include/net/inet6_connection_sock.h +++ b/include/net/inet6_connection_sock.h @@ -28,15 +28,6 @@ int inet6_csk_bind_conflict(const struct sock *sk, struct dst_entry *inet6_csk_route_req(const struct sock *sk, struct flowi6 *fl6, const struct request_sock *req, u8 proto); -struct request_sock *inet6_csk_search_req(struct sock *sk, - const __be16 rport, - const struct in6_addr *raddr, - const struct in6_addr *laddr, - const int iif); - -void inet6_csk_reqsk_queue_hash_add(struct sock *sk, struct request_sock *req, - const unsigned long timeout); - void inet6_csk_addr2sockaddr(struct sock *sk, struct sockaddr *uaddr); int inet6_csk_xmit(struct sock *sk, struct sk_buff *skb, struct flowi *fl); -- cgit v1.2.3 From ca6fb06518836ef9b65dc0aac02ff97704d52a05 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Fri, 2 Oct 2015 11:43:35 -0700 Subject: tcp: attach SYNACK messages to request sockets instead of listener If a listen backlog is very big (to avoid syncookies), then the listener sk->sk_wmem_alloc is the main source of false sharing, as we need to touch it twice per SYNACK re-transmit and TX completion. (One SYN packet takes listener lock once, but up to 6 SYNACK are generated) By attaching the skb to the request socket, we remove this source of contention. Tested: listen(fd, 10485760); // single listener (no SO_REUSEPORT) 16 RX/TX queue NIC Sustain a SYNFLOOD attack of ~320,000 SYN per second, Sending ~1,400,000 SYNACK per second. Perf profiles now show listener spinlock being next bottleneck. 20.29% [kernel] [k] queued_spin_lock_slowpath 10.06% [kernel] [k] __inet_lookup_established 5.12% [kernel] [k] reqsk_timer_handler 3.22% [kernel] [k] get_next_timer_interrupt 3.00% [kernel] [k] tcp_make_synack 2.77% [kernel] [k] ipt_do_table 2.70% [kernel] [k] run_timer_softirq 2.50% [kernel] [k] ip_finish_output 2.04% [kernel] [k] cascade Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- include/net/tcp.h | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/net/tcp.h b/include/net/tcp.h index 225e9561af35..a6be56d5f0e3 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -462,7 +462,8 @@ int tcp_v4_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len); int tcp_connect(struct sock *sk); struct sk_buff *tcp_make_synack(const struct sock *sk, struct dst_entry *dst, struct request_sock *req, - struct tcp_fastopen_cookie *foc); + struct tcp_fastopen_cookie *foc, + bool attach_req); int tcp_disconnect(struct sock *sk, int flags); void tcp_finish_connect(struct sock *sk, struct sk_buff *skb); @@ -1715,7 +1716,8 @@ struct tcp_request_sock_ops { __u32 (*init_seq)(const struct sk_buff *skb); int (*send_synack)(const struct sock *sk, struct dst_entry *dst, struct flowi *fl, struct request_sock *req, - u16 queue_mapping, struct tcp_fastopen_cookie *foc); + u16 queue_mapping, struct tcp_fastopen_cookie *foc, + bool attach_req); }; #ifdef CONFIG_SYN_COOKIES -- cgit v1.2.3 From 10cbc8f179177c1a6d5f56a46ebddc8f602ce5ac Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Fri, 2 Oct 2015 11:43:36 -0700 Subject: tcp/dccp: remove struct listen_sock It is enough to check listener sk_state, no need for an extra condition. max_qlen_log can be moved into struct request_sock_queue We can remove syn_wait_lock and the alignment it enforced. Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- include/net/request_sock.h | 26 ++++---------------------- 1 file changed, 4 insertions(+), 22 deletions(-) (limited to 'include') diff --git a/include/net/request_sock.h b/include/net/request_sock.h index 353cb61bb399..a66ab1345373 100644 --- a/include/net/request_sock.h +++ b/include/net/request_sock.h @@ -119,14 +119,6 @@ static inline void reqsk_put(struct request_sock *req) extern int sysctl_max_syn_backlog; -/** struct listen_sock - listen state - * - * @max_qlen_log - log_2 of maximal queued SYNs/REQUESTs - */ -struct listen_sock { - u32 max_qlen_log; -}; - /* * For a TCP Fast Open listener - * lock - protects the access to all the reqsk, which is co-owned by @@ -160,36 +152,26 @@ struct fastopen_queue { * @rskq_accept_head - FIFO head of established children * @rskq_accept_tail - FIFO tail of established children * @rskq_defer_accept - User waits for some data after accept() - * @syn_wait_lock - serializer - * - * %syn_wait_lock is necessary only to avoid proc interface having to grab the main - * lock sock while browsing the listening hash (otherwise it's deadlock prone). * */ struct request_sock_queue { spinlock_t rskq_lock; u8 rskq_defer_accept; + u8 max_qlen_log; u32 synflood_warned; - atomic_t qlen; atomic_t young; struct request_sock *rskq_accept_head; struct request_sock *rskq_accept_tail; - struct listen_sock *listen_opt; struct fastopen_queue fastopenq; /* Check max_qlen != 0 to determine * if TFO is enabled. */ - - /* temporary alignment, our goal is to get rid of this lock */ - spinlock_t syn_wait_lock ____cacheline_aligned_in_smp; }; -int reqsk_queue_alloc(struct request_sock_queue *queue, - unsigned int nr_table_entries); +void reqsk_queue_alloc(struct request_sock_queue *queue, + unsigned int nr_table_entries); -void __reqsk_queue_destroy(struct request_sock_queue *queue); -void reqsk_queue_destroy(struct request_sock_queue *queue); void reqsk_fastopen_remove(struct sock *sk, struct request_sock *req, bool reset); @@ -260,7 +242,7 @@ static inline int reqsk_queue_len_young(const struct request_sock_queue *queue) static inline int reqsk_queue_is_full(const struct request_sock_queue *queue) { - return reqsk_queue_len(queue) >> queue->listen_opt->max_qlen_log; + return reqsk_queue_len(queue) >> queue->max_qlen_log; } #endif /* _REQUEST_SOCK_H */ -- cgit v1.2.3 From ef547f2ac16bd9d77a780a0e7c70857e69e8f23f Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Fri, 2 Oct 2015 11:43:37 -0700 Subject: tcp: remove max_qlen_log This control variable was set at first listen(fd, backlog) call, but not updated if application tried to increase or decrease backlog. It made sense at the time listener had a non resizeable hash table. Also rounding to powers of two was not very friendly. Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- include/net/inet_connection_sock.h | 2 +- include/net/request_sock.h | 10 ++-------- 2 files changed, 3 insertions(+), 9 deletions(-) (limited to 'include') diff --git a/include/net/inet_connection_sock.h b/include/net/inet_connection_sock.h index 730aa034cd3d..3208a65d1c28 100644 --- a/include/net/inet_connection_sock.h +++ b/include/net/inet_connection_sock.h @@ -295,7 +295,7 @@ static inline int inet_csk_reqsk_queue_young(const struct sock *sk) static inline int inet_csk_reqsk_queue_is_full(const struct sock *sk) { - return reqsk_queue_is_full(&inet_csk(sk)->icsk_accept_queue); + return inet_csk_reqsk_queue_len(sk) >= sk->sk_max_ack_backlog; } void inet_csk_reqsk_queue_drop(struct sock *sk, struct request_sock *req); diff --git a/include/net/request_sock.h b/include/net/request_sock.h index a66ab1345373..bae6936d75c4 100644 --- a/include/net/request_sock.h +++ b/include/net/request_sock.h @@ -157,7 +157,7 @@ struct fastopen_queue { struct request_sock_queue { spinlock_t rskq_lock; u8 rskq_defer_accept; - u8 max_qlen_log; + u32 synflood_warned; atomic_t qlen; atomic_t young; @@ -169,8 +169,7 @@ struct request_sock_queue { */ }; -void reqsk_queue_alloc(struct request_sock_queue *queue, - unsigned int nr_table_entries); +void reqsk_queue_alloc(struct request_sock_queue *queue); void reqsk_fastopen_remove(struct sock *sk, struct request_sock *req, bool reset); @@ -240,9 +239,4 @@ static inline int reqsk_queue_len_young(const struct request_sock_queue *queue) return atomic_read(&queue->young); } -static inline int reqsk_queue_is_full(const struct request_sock_queue *queue) -{ - return reqsk_queue_len(queue) >> queue->max_qlen_log; -} - #endif /* _REQUEST_SOCK_H */ -- cgit v1.2.3 From 57d80838dae55c1bc6ca629e471c84100513079a Mon Sep 17 00:00:00 2001 From: Jiri Pirko Date: Thu, 1 Oct 2015 11:03:41 +0200 Subject: switchdev: rename SWITCHDEV_OBJ_* enum values to SWITCHDEV_OBJ_ID_* Suggested-by: Vivien Didelot Signed-off-by: Jiri Pirko Acked-by: Scott Feldman Reviewed-by: Vivien Didelot Signed-off-by: David S. Miller --- include/net/switchdev.h | 14 +++++++------- 1 file changed, 7 insertions(+), 7 deletions(-) (limited to 'include') diff --git a/include/net/switchdev.h b/include/net/switchdev.h index e11425eb0735..11f9c706cf5c 100644 --- a/include/net/switchdev.h +++ b/include/net/switchdev.h @@ -58,20 +58,20 @@ struct switchdev_attr { struct fib_info; enum switchdev_obj_id { - SWITCHDEV_OBJ_UNDEFINED, - SWITCHDEV_OBJ_PORT_VLAN, - SWITCHDEV_OBJ_IPV4_FIB, - SWITCHDEV_OBJ_PORT_FDB, + SWITCHDEV_OBJ_ID_UNDEFINED, + SWITCHDEV_OBJ_ID_PORT_VLAN, + SWITCHDEV_OBJ_ID_IPV4_FIB, + SWITCHDEV_OBJ_ID_PORT_FDB, }; -/* SWITCHDEV_OBJ_PORT_VLAN */ +/* SWITCHDEV_OBJ_ID_PORT_VLAN */ struct switchdev_obj_vlan { u16 flags; u16 vid_begin; u16 vid_end; }; -/* SWITCHDEV_OBJ_IPV4_FIB */ +/* SWITCHDEV_OBJ_ID_IPV4_FIB */ struct switchdev_obj_ipv4_fib { u32 dst; int dst_len; @@ -82,7 +82,7 @@ struct switchdev_obj_ipv4_fib { u32 tb_id; }; -/* SWITCHDEV_OBJ_PORT_FDB */ +/* SWITCHDEV_OBJ_ID_PORT_FDB */ struct switchdev_obj_fdb { const unsigned char *addr; u16 vid; -- cgit v1.2.3 From 1f86839874a50c9ee2009567d2f312b1e1949e24 Mon Sep 17 00:00:00 2001 From: Jiri Pirko Date: Thu, 1 Oct 2015 11:03:42 +0200 Subject: switchdev: rename SWITCHDEV_ATTR_* enum values to SWITCHDEV_ATTR_ID_* To be aligned with obj. Signed-off-by: Jiri Pirko Acked-by: Scott Feldman Reviewed-by: Vivien Didelot Signed-off-by: David S. Miller --- include/net/switchdev.h | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) (limited to 'include') diff --git a/include/net/switchdev.h b/include/net/switchdev.h index 11f9c706cf5c..612719b9618a 100644 --- a/include/net/switchdev.h +++ b/include/net/switchdev.h @@ -39,10 +39,10 @@ static inline bool switchdev_trans_ph_commit(struct switchdev_trans *trans) } enum switchdev_attr_id { - SWITCHDEV_ATTR_UNDEFINED, - SWITCHDEV_ATTR_PORT_PARENT_ID, - SWITCHDEV_ATTR_PORT_STP_STATE, - SWITCHDEV_ATTR_PORT_BRIDGE_FLAGS, + SWITCHDEV_ATTR_ID_UNDEFINED, + SWITCHDEV_ATTR_ID_PORT_PARENT_ID, + SWITCHDEV_ATTR_ID_PORT_STP_STATE, + SWITCHDEV_ATTR_ID_PORT_BRIDGE_FLAGS, }; struct switchdev_attr { -- cgit v1.2.3 From 8f24f3095dcedaa4eb4719eee2bed738fe2ce4a0 Mon Sep 17 00:00:00 2001 From: Jiri Pirko Date: Thu, 1 Oct 2015 11:03:43 +0200 Subject: switchdev: rename switchdev_obj_vlan to switchdev_obj_port_vlan Make the struct name in sync with object id name. Suggested-by: Vivien Didelot Signed-off-by: Jiri Pirko Acked-by: Scott Feldman Reviewed-by: Vivien Didelot Signed-off-by: David S. Miller --- include/net/switchdev.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/net/switchdev.h b/include/net/switchdev.h index 612719b9618a..0138f9b374e2 100644 --- a/include/net/switchdev.h +++ b/include/net/switchdev.h @@ -65,7 +65,7 @@ enum switchdev_obj_id { }; /* SWITCHDEV_OBJ_ID_PORT_VLAN */ -struct switchdev_obj_vlan { +struct switchdev_obj_port_vlan { u16 flags; u16 vid_begin; u16 vid_end; -- cgit v1.2.3 From 52ba57cfdc4c90da3bf996dfbe0c5feb731eb477 Mon Sep 17 00:00:00 2001 From: Jiri Pirko Date: Thu, 1 Oct 2015 11:03:44 +0200 Subject: switchdev: rename switchdev_obj_fdb to switchdev_obj_port_fdb Make the struct name in sync with object id name. Suggested-by: Vivien Didelot Signed-off-by: Jiri Pirko Acked-by: Scott Feldman Reviewed-by: Vivien Didelot Signed-off-by: David S. Miller --- include/net/switchdev.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/net/switchdev.h b/include/net/switchdev.h index 0138f9b374e2..8d71fdbaa7a6 100644 --- a/include/net/switchdev.h +++ b/include/net/switchdev.h @@ -83,7 +83,7 @@ struct switchdev_obj_ipv4_fib { }; /* SWITCHDEV_OBJ_ID_PORT_FDB */ -struct switchdev_obj_fdb { +struct switchdev_obj_port_fdb { const unsigned char *addr; u16 vid; u16 ndm_state; -- cgit v1.2.3 From 648b4a995a057187ddd77cdb181e6a0b24ab2959 Mon Sep 17 00:00:00 2001 From: Jiri Pirko Date: Thu, 1 Oct 2015 11:03:45 +0200 Subject: switchdev: bring back switchdev_obj and use it as a generic object param Replace "void *obj" with a generic structure. Introduce couple of helpers along that. Signed-off-by: Jiri Pirko Acked-by: Scott Feldman Reviewed-by: Vivien Didelot Signed-off-by: David S. Miller --- include/net/switchdev.h | 42 +++++++++++++++++++++++++++++++----------- 1 file changed, 31 insertions(+), 11 deletions(-) (limited to 'include') diff --git a/include/net/switchdev.h b/include/net/switchdev.h index 8d71fdbaa7a6..3e1bd14cc0ab 100644 --- a/include/net/switchdev.h +++ b/include/net/switchdev.h @@ -64,15 +64,23 @@ enum switchdev_obj_id { SWITCHDEV_OBJ_ID_PORT_FDB, }; +struct switchdev_obj { +}; + /* SWITCHDEV_OBJ_ID_PORT_VLAN */ struct switchdev_obj_port_vlan { + struct switchdev_obj obj; u16 flags; u16 vid_begin; u16 vid_end; }; +#define SWITCHDEV_OBJ_PORT_VLAN(obj) \ + container_of(obj, struct switchdev_obj_port_vlan, obj) + /* SWITCHDEV_OBJ_ID_IPV4_FIB */ struct switchdev_obj_ipv4_fib { + struct switchdev_obj obj; u32 dst; int dst_len; struct fib_info *fi; @@ -82,18 +90,27 @@ struct switchdev_obj_ipv4_fib { u32 tb_id; }; +#define SWITCHDEV_OBJ_IPV4_FIB(obj) \ + container_of(obj, struct switchdev_obj_ipv4_fib, obj) + /* SWITCHDEV_OBJ_ID_PORT_FDB */ struct switchdev_obj_port_fdb { + struct switchdev_obj obj; const unsigned char *addr; u16 vid; u16 ndm_state; }; +#define SWITCHDEV_OBJ_PORT_FDB(obj) \ + container_of(obj, struct switchdev_obj_port_fdb, obj) + void switchdev_trans_item_enqueue(struct switchdev_trans *trans, void *data, void (*destructor)(void const *), struct switchdev_trans_item *tritem); void *switchdev_trans_item_dequeue(struct switchdev_trans *trans); +typedef int switchdev_obj_dump_cb_t(struct switchdev_obj *obj); + /** * struct switchdev_ops - switchdev operations * @@ -115,14 +132,15 @@ struct switchdev_ops { struct switchdev_trans *trans); int (*switchdev_port_obj_add)(struct net_device *dev, enum switchdev_obj_id id, - const void *obj, + const struct switchdev_obj *obj, struct switchdev_trans *trans); int (*switchdev_port_obj_del)(struct net_device *dev, enum switchdev_obj_id id, - const void *obj); + const struct switchdev_obj *obj); int (*switchdev_port_obj_dump)(struct net_device *dev, - enum switchdev_obj_id id, void *obj, - int (*cb)(void *obj)); + enum switchdev_obj_id id, + struct switchdev_obj *obj, + switchdev_obj_dump_cb_t *cb); }; enum switchdev_notifier_type { @@ -153,11 +171,12 @@ int switchdev_port_attr_get(struct net_device *dev, int switchdev_port_attr_set(struct net_device *dev, struct switchdev_attr *attr); int switchdev_port_obj_add(struct net_device *dev, enum switchdev_obj_id id, - const void *obj); + const struct switchdev_obj *obj); int switchdev_port_obj_del(struct net_device *dev, enum switchdev_obj_id id, - const void *obj); + const struct switchdev_obj *obj); int switchdev_port_obj_dump(struct net_device *dev, enum switchdev_obj_id id, - void *obj, int (*cb)(void *obj)); + struct switchdev_obj *obj, + switchdev_obj_dump_cb_t *cb); int register_switchdev_notifier(struct notifier_block *nb); int unregister_switchdev_notifier(struct notifier_block *nb); int call_switchdev_notifiers(unsigned long val, struct net_device *dev, @@ -203,21 +222,22 @@ static inline int switchdev_port_attr_set(struct net_device *dev, static inline int switchdev_port_obj_add(struct net_device *dev, enum switchdev_obj_id id, - const void *obj) + const struct switchdev_obj *obj) { return -EOPNOTSUPP; } static inline int switchdev_port_obj_del(struct net_device *dev, enum switchdev_obj_id id, - const void *obj) + const struct switchdev_obj *obj) { return -EOPNOTSUPP; } static inline int switchdev_port_obj_dump(struct net_device *dev, - enum switchdev_obj_id id, void *obj, - int (*cb)(void *obj)) + enum switchdev_obj_id id, + const struct switchdev_obj *obj, + switchdev_obj_dump_cb_t *cb) { return -EOPNOTSUPP; } -- cgit v1.2.3 From 9e8f4a548ab4710002c23c94c4b1bbde91b5e335 Mon Sep 17 00:00:00 2001 From: Jiri Pirko Date: Thu, 1 Oct 2015 11:03:46 +0200 Subject: switchdev: push object ID back to object structure Suggested-by: Scott Feldman Signed-off-by: Jiri Pirko Acked-by: Scott Feldman Reviewed-by: Vivien Didelot Signed-off-by: David S. Miller --- include/net/switchdev.h | 14 ++++---------- 1 file changed, 4 insertions(+), 10 deletions(-) (limited to 'include') diff --git a/include/net/switchdev.h b/include/net/switchdev.h index 3e1bd14cc0ab..89266a3e473d 100644 --- a/include/net/switchdev.h +++ b/include/net/switchdev.h @@ -65,6 +65,7 @@ enum switchdev_obj_id { }; struct switchdev_obj { + enum switchdev_obj_id id; }; /* SWITCHDEV_OBJ_ID_PORT_VLAN */ @@ -131,14 +132,11 @@ struct switchdev_ops { struct switchdev_attr *attr, struct switchdev_trans *trans); int (*switchdev_port_obj_add)(struct net_device *dev, - enum switchdev_obj_id id, const struct switchdev_obj *obj, struct switchdev_trans *trans); int (*switchdev_port_obj_del)(struct net_device *dev, - enum switchdev_obj_id id, const struct switchdev_obj *obj); int (*switchdev_port_obj_dump)(struct net_device *dev, - enum switchdev_obj_id id, struct switchdev_obj *obj, switchdev_obj_dump_cb_t *cb); }; @@ -170,12 +168,11 @@ int switchdev_port_attr_get(struct net_device *dev, struct switchdev_attr *attr); int switchdev_port_attr_set(struct net_device *dev, struct switchdev_attr *attr); -int switchdev_port_obj_add(struct net_device *dev, enum switchdev_obj_id id, +int switchdev_port_obj_add(struct net_device *dev, const struct switchdev_obj *obj); -int switchdev_port_obj_del(struct net_device *dev, enum switchdev_obj_id id, +int switchdev_port_obj_del(struct net_device *dev, const struct switchdev_obj *obj); -int switchdev_port_obj_dump(struct net_device *dev, enum switchdev_obj_id id, - struct switchdev_obj *obj, +int switchdev_port_obj_dump(struct net_device *dev, struct switchdev_obj *obj, switchdev_obj_dump_cb_t *cb); int register_switchdev_notifier(struct notifier_block *nb); int unregister_switchdev_notifier(struct notifier_block *nb); @@ -221,21 +218,18 @@ static inline int switchdev_port_attr_set(struct net_device *dev, } static inline int switchdev_port_obj_add(struct net_device *dev, - enum switchdev_obj_id id, const struct switchdev_obj *obj) { return -EOPNOTSUPP; } static inline int switchdev_port_obj_del(struct net_device *dev, - enum switchdev_obj_id id, const struct switchdev_obj *obj) { return -EOPNOTSUPP; } static inline int switchdev_port_obj_dump(struct net_device *dev, - enum switchdev_obj_id id, const struct switchdev_obj *obj, switchdev_obj_dump_cb_t *cb) { -- cgit v1.2.3 From a91263d520246b63c63e75ddfb072ee6a853fe15 Mon Sep 17 00:00:00 2001 From: Daniel Borkmann Date: Wed, 30 Sep 2015 01:41:50 +0200 Subject: ebpf: migrate bpf_prog's flags to bitfield As we need to add further flags to the bpf_prog structure, lets migrate both bools to a bitfield representation. The size of the base structure (excluding insns) remains unchanged at 40 bytes. Add also tags for the kmemchecker, so that it doesn't throw false positives. Even in case gcc would generate suboptimal code, it's not being accessed in performance critical paths. Signed-off-by: Daniel Borkmann Acked-by: Alexei Starovoitov Signed-off-by: David S. Miller --- include/linux/filter.h | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/filter.h b/include/linux/filter.h index fa2cab985e57..bad618f316d7 100644 --- a/include/linux/filter.h +++ b/include/linux/filter.h @@ -326,8 +326,10 @@ struct bpf_binary_header { struct bpf_prog { u16 pages; /* Number of allocated pages */ - bool jited; /* Is our filter JIT'ed? */ - bool gpl_compatible; /* Is our filter GPL compatible? */ + kmemcheck_bitfield_begin(meta); + u16 jited:1, /* Is our filter JIT'ed? */ + gpl_compatible:1; /* Is filter GPL compatible? */ + kmemcheck_bitfield_end(meta); u32 len; /* Number of filter blocks */ enum bpf_prog_type type; /* Type of BPF program */ struct bpf_prog_aux *aux; /* Auxiliary fields */ -- cgit v1.2.3 From c46646d0484f5d08e2bede9b45034ba5b8b489cc Mon Sep 17 00:00:00 2001 From: Daniel Borkmann Date: Wed, 30 Sep 2015 01:41:51 +0200 Subject: sched, bpf: add helper for retrieving routing realms Using routing realms as part of the classifier is quite useful, it can be viewed as a tag for one or multiple routing entries (think of an analogy to net_cls cgroup for processes), set by user space routing daemons or via iproute2 as an indicator for traffic classifiers and later on processed in the eBPF program. Unlike actions, the classifier can inspect device flags and enable netif_keep_dst() if necessary. tc actions don't have that possibility, but in case people know what they are doing, it can be used from there as well (e.g. via devs that must keep dsts by design anyway). If a realm is set, the handler returns the non-zero realm. User space can set the full 32bit realm for the dst. Signed-off-by: Daniel Borkmann Acked-by: Alexei Starovoitov Signed-off-by: David S. Miller --- include/linux/filter.h | 3 ++- include/uapi/linux/bpf.h | 7 +++++++ 2 files changed, 9 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/filter.h b/include/linux/filter.h index bad618f316d7..3d5fd24b321b 100644 --- a/include/linux/filter.h +++ b/include/linux/filter.h @@ -328,7 +328,8 @@ struct bpf_prog { u16 pages; /* Number of allocated pages */ kmemcheck_bitfield_begin(meta); u16 jited:1, /* Is our filter JIT'ed? */ - gpl_compatible:1; /* Is filter GPL compatible? */ + gpl_compatible:1, /* Is filter GPL compatible? */ + dst_needed:1; /* Do we need dst entry? */ kmemcheck_bitfield_end(meta); u32 len; /* Number of filter blocks */ enum bpf_prog_type type; /* Type of BPF program */ diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index 4ec0b5488294..564f1f091991 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -280,6 +280,13 @@ enum bpf_func_id { * Return: TC_ACT_REDIRECT */ BPF_FUNC_redirect, + + /** + * bpf_get_route_realm(skb) - retrieve a dst's tclassid + * @skb: pointer to skb + * Return: realm if != 0 + */ + BPF_FUNC_get_route_realm, __BPF_FUNC_MAX_ID, }; -- cgit v1.2.3 From f3a6bd393c2c5d0e6b16624ba99a1c5fa07bdb0b Mon Sep 17 00:00:00 2001 From: Simon Horman Date: Wed, 30 Sep 2015 15:15:52 +0900 Subject: phylib: Add phy_set_max_speed helper Add a helper to allow ethernet drivers to limit the speed of a phy (that they are attached to). This mainly involves factoring out the business-end of of_set_phy_supported() and exporting a new symbol. This code seems to be open coded in several places, in several different variants. It is is envisaged that this will be used in situations where setting the "max-speed" property in DT is not appropriate, e.g. because the maximum speed is not a property of the phy hardware. Signed-off-by: Simon Horman Signed-off-by: David S. Miller --- include/linux/phy.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/phy.h b/include/linux/phy.h index 4a4e3a092337..4c477e6ece33 100644 --- a/include/linux/phy.h +++ b/include/linux/phy.h @@ -798,6 +798,7 @@ int phy_mii_ioctl(struct phy_device *phydev, struct ifreq *ifr, int cmd); int phy_start_interrupts(struct phy_device *phydev); void phy_print_status(struct phy_device *phydev); void phy_device_free(struct phy_device *phydev); +int phy_set_max_speed(struct phy_device *phydev, u32 max_speed); int phy_register_fixup(const char *bus_id, u32 phy_uid, u32 phy_uid_mask, int (*run)(struct phy_device *)); -- cgit v1.2.3 From e96f78ab2703f3b0d512f6b469bc685d2ef20475 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Sat, 3 Oct 2015 06:27:28 -0700 Subject: tcp/dccp: add SLAB_DESTROY_BY_RCU flag for request sockets Before letting request sockets being put in TCP/DCCP regular ehash table, we need to add either : - SLAB_DESTROY_BY_RCU flag to their kmem_cache - add RCU grace period before freeing them. Since we carefully respected the SLAB_DESTROY_BY_RCU protocol like ESTABLISH and TIMEWAIT sockets, use it here. req_prot_init() being only used by TCP and DCCP, I did not add a new slab_flags into their rsk_prot, but reuse prot->slab_flags Since all reqsk_alloc() users are correctly dealing with a failure, add the __GFP_NOWARN flag to avoid traces under pressure. Fixes: 079096f103fa ("tcp/dccp: install syn_recv requests into ehash table") Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- include/net/request_sock.h | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/net/request_sock.h b/include/net/request_sock.h index bae6936d75c4..dd423d840852 100644 --- a/include/net/request_sock.h +++ b/include/net/request_sock.h @@ -82,7 +82,9 @@ static inline struct sock *req_to_sk(struct request_sock *req) static inline struct request_sock * reqsk_alloc(const struct request_sock_ops *ops, struct sock *sk_listener) { - struct request_sock *req = kmem_cache_alloc(ops->slab, GFP_ATOMIC); + struct request_sock *req; + + req = kmem_cache_alloc(ops->slab, GFP_ATOMIC | __GFP_NOWARN); if (req) { req->rsk_ops = ops; -- cgit v1.2.3 From b7bd1809e0784435791657502bc0d8280ad6f7ea Mon Sep 17 00:00:00 2001 From: Pablo Neira Ayuso Date: Wed, 30 Sep 2015 22:53:44 +0100 Subject: netfilter: nfnetlink_queue: get rid of nfnetlink_queue_ct.c The original intention was to avoid dependencies between nfnetlink_queue and conntrack without ifdef pollution. However, we can achieve this by moving the conntrack dependent code into ctnetlink and keep some glue code to access the nfq_ct indirection from nfqueue. After this patch, the nfq_ct indirection is always compiled in the netfilter core to avoid polluting nfqueue with ifdefs. Thus, if nf_conntrack is not compiled this results in only 8-bytes of memory waste in x86_64. This patch also adds ctnetlink_nfqueue_seqadj() to avoid that the nf_conn structure layout if exposed to nf_queue, which creates another dependency with nf_conntrack at compilation time. Signed-off-by: Pablo Neira Ayuso --- include/linux/netfilter.h | 12 +++++--- include/net/netfilter/nfnetlink_queue.h | 51 --------------------------------- 2 files changed, 8 insertions(+), 55 deletions(-) delete mode 100644 include/net/netfilter/nfnetlink_queue.h (limited to 'include') diff --git a/include/linux/netfilter.h b/include/linux/netfilter.h index 165ab2d14734..3e5e8f2b65f6 100644 --- a/include/linux/netfilter.h +++ b/include/linux/netfilter.h @@ -369,14 +369,21 @@ nf_nat_decode_session(struct sk_buff *skb, struct flowi *fl, u_int8_t family) extern void (*ip_ct_attach)(struct sk_buff *, const struct sk_buff *) __rcu; void nf_ct_attach(struct sk_buff *, const struct sk_buff *); extern void (*nf_ct_destroy)(struct nf_conntrack *) __rcu; +#else +static inline void nf_ct_attach(struct sk_buff *new, struct sk_buff *skb) {} +#endif struct nf_conn; enum ip_conntrack_info; struct nlattr; struct nfq_ct_hook { + struct nf_conn *(*get_ct)(struct sk_buff *skb, + enum ip_conntrack_info *ctinfo); size_t (*build_size)(const struct nf_conn *ct); - int (*build)(struct sk_buff *skb, struct nf_conn *ct); + int (*build)(struct sk_buff *skb, struct nf_conn *ct, + enum ip_conntrack_info ctinfo, + u_int16_t ct_attr, u_int16_t ct_info_attr); int (*parse)(const struct nlattr *attr, struct nf_conn *ct); int (*attach_expect)(const struct nlattr *attr, struct nf_conn *ct, u32 portid, u32 report); @@ -384,9 +391,6 @@ struct nfq_ct_hook { enum ip_conntrack_info ctinfo, s32 off); }; extern struct nfq_ct_hook __rcu *nfq_ct_hook; -#else -static inline void nf_ct_attach(struct sk_buff *new, struct sk_buff *skb) {} -#endif /** * nf_skb_duplicated - TEE target has sent a packet diff --git a/include/net/netfilter/nfnetlink_queue.h b/include/net/netfilter/nfnetlink_queue.h deleted file mode 100644 index aff88ba91391..000000000000 --- a/include/net/netfilter/nfnetlink_queue.h +++ /dev/null @@ -1,51 +0,0 @@ -#ifndef _NET_NFNL_QUEUE_H_ -#define _NET_NFNL_QUEUE_H_ - -#include - -struct nf_conn; - -#ifdef CONFIG_NETFILTER_NETLINK_QUEUE_CT -struct nf_conn *nfqnl_ct_get(struct sk_buff *entskb, size_t *size, - enum ip_conntrack_info *ctinfo); -struct nf_conn *nfqnl_ct_parse(const struct sk_buff *skb, - const struct nlattr *attr, - enum ip_conntrack_info *ctinfo); -int nfqnl_ct_put(struct sk_buff *skb, struct nf_conn *ct, - enum ip_conntrack_info ctinfo); -void nfqnl_ct_seq_adjust(struct sk_buff *skb, struct nf_conn *ct, - enum ip_conntrack_info ctinfo, int diff); -int nfqnl_attach_expect(struct nf_conn *ct, const struct nlattr *attr, - u32 portid, u32 report); -#else -inline struct nf_conn * -nfqnl_ct_get(struct sk_buff *entskb, size_t *size, enum ip_conntrack_info *ctinfo) -{ - return NULL; -} - -inline struct nf_conn *nfqnl_ct_parse(const struct sk_buff *skb, - const struct nlattr *attr, - enum ip_conntrack_info *ctinfo) -{ - return NULL; -} - -inline int -nfqnl_ct_put(struct sk_buff *skb, struct nf_conn *ct, enum ip_conntrack_info ctinfo) -{ - return 0; -} - -inline void nfqnl_ct_seq_adjust(struct sk_buff *skb, struct nf_conn *ct, - enum ip_conntrack_info ctinfo, int diff) -{ -} - -inline int nfqnl_attach_expect(struct nf_conn *ct, const struct nlattr *attr, - u32 portid, u32 report) -{ - return 0; -} -#endif /* NF_CONNTRACK */ -#endif -- cgit v1.2.3 From 7910228b6bb35f3c8e0bc72a8d84c29616cb1b90 Mon Sep 17 00:00:00 2001 From: Nikolay Aleksandrov Date: Sun, 4 Oct 2015 14:23:28 +0200 Subject: bridge: netlink: add group_fwd_mask support Add IFLA_BR_GROUP_FWD_MASK attribute to allow setting and retrieving the group_fwd_mask via netlink. Signed-off-by: Nikolay Aleksandrov Signed-off-by: David S. Miller --- include/uapi/linux/if_link.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/uapi/linux/if_link.h b/include/uapi/linux/if_link.h index 3a5f263cfc2f..f7f480613555 100644 --- a/include/uapi/linux/if_link.h +++ b/include/uapi/linux/if_link.h @@ -232,6 +232,7 @@ enum { IFLA_BR_PRIORITY, IFLA_BR_VLAN_FILTERING, IFLA_BR_VLAN_PROTOCOL, + IFLA_BR_GROUP_FWD_MASK, __IFLA_BR_MAX, }; -- cgit v1.2.3 From 5127c81f84de0dd643d5840a2c7de571bc6aceb3 Mon Sep 17 00:00:00 2001 From: Nikolay Aleksandrov Date: Sun, 4 Oct 2015 14:23:29 +0200 Subject: bridge: netlink: export root id Add IFLA_BR_ROOT_ID and export br->designated_root via netlink. For this purpose add struct ifla_bridge_id that would represent struct bridge_id. Signed-off-by: Nikolay Aleksandrov Signed-off-by: David S. Miller --- include/uapi/linux/if_link.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include') diff --git a/include/uapi/linux/if_link.h b/include/uapi/linux/if_link.h index f7f480613555..03814371df44 100644 --- a/include/uapi/linux/if_link.h +++ b/include/uapi/linux/if_link.h @@ -233,11 +233,17 @@ enum { IFLA_BR_VLAN_FILTERING, IFLA_BR_VLAN_PROTOCOL, IFLA_BR_GROUP_FWD_MASK, + IFLA_BR_ROOT_ID, __IFLA_BR_MAX, }; #define IFLA_BR_MAX (__IFLA_BR_MAX - 1) +struct ifla_bridge_id { + __u8 prio[2]; + __u8 addr[6]; /* ETH_ALEN */ +}; + enum { BRIDGE_MODE_UNSPEC, BRIDGE_MODE_HAIRPIN, -- cgit v1.2.3 From 7599a2201fc71cdca16a92d350f14cce8730e03f Mon Sep 17 00:00:00 2001 From: Nikolay Aleksandrov Date: Sun, 4 Oct 2015 14:23:30 +0200 Subject: bridge: netlink: export bridge id Add IFLA_BR_BRIDGE_ID and export br->bridge_id via netlink. Signed-off-by: Nikolay Aleksandrov Signed-off-by: David S. Miller --- include/uapi/linux/if_link.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/uapi/linux/if_link.h b/include/uapi/linux/if_link.h index 03814371df44..748495438a8b 100644 --- a/include/uapi/linux/if_link.h +++ b/include/uapi/linux/if_link.h @@ -234,6 +234,7 @@ enum { IFLA_BR_VLAN_PROTOCOL, IFLA_BR_GROUP_FWD_MASK, IFLA_BR_ROOT_ID, + IFLA_BR_BRIDGE_ID, __IFLA_BR_MAX, }; -- cgit v1.2.3 From 8762ba680fe8d41b444fc92f90ce7194b2b8303b Mon Sep 17 00:00:00 2001 From: Nikolay Aleksandrov Date: Sun, 4 Oct 2015 14:23:31 +0200 Subject: bridge: netlink: export root port Add IFLA_BR_ROOT_PORT and export it via netlink. Signed-off-by: Nikolay Aleksandrov Signed-off-by: David S. Miller --- include/uapi/linux/if_link.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/uapi/linux/if_link.h b/include/uapi/linux/if_link.h index 748495438a8b..172268a5767d 100644 --- a/include/uapi/linux/if_link.h +++ b/include/uapi/linux/if_link.h @@ -235,6 +235,7 @@ enum { IFLA_BR_GROUP_FWD_MASK, IFLA_BR_ROOT_ID, IFLA_BR_BRIDGE_ID, + IFLA_BR_ROOT_PORT, __IFLA_BR_MAX, }; -- cgit v1.2.3 From 684dd248bee8c73eadb90706123bf1494d3218b8 Mon Sep 17 00:00:00 2001 From: Nikolay Aleksandrov Date: Sun, 4 Oct 2015 14:23:32 +0200 Subject: bridge: netlink: export root path cost Add IFLA_BR_ROOT_PATH_COST and export it via netlink. Signed-off-by: Nikolay Aleksandrov Signed-off-by: David S. Miller --- include/uapi/linux/if_link.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/uapi/linux/if_link.h b/include/uapi/linux/if_link.h index 172268a5767d..7d7236d143fb 100644 --- a/include/uapi/linux/if_link.h +++ b/include/uapi/linux/if_link.h @@ -236,6 +236,7 @@ enum { IFLA_BR_ROOT_ID, IFLA_BR_BRIDGE_ID, IFLA_BR_ROOT_PORT, + IFLA_BR_ROOT_PATH_COST, __IFLA_BR_MAX, }; -- cgit v1.2.3 From ed4163098e3090bb7b51421bde977e355275a554 Mon Sep 17 00:00:00 2001 From: Nikolay Aleksandrov Date: Sun, 4 Oct 2015 14:23:33 +0200 Subject: bridge: netlink: export topology_change and topology_change_detected Add IFLA_BR_TOPOLOGY_CHANGE and IFLA_BR_TOPOLOGY_CHANGE_DETECTED and export them via netlink. Signed-off-by: Nikolay Aleksandrov Signed-off-by: David S. Miller --- include/uapi/linux/if_link.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/uapi/linux/if_link.h b/include/uapi/linux/if_link.h index 7d7236d143fb..b00286ca1bfe 100644 --- a/include/uapi/linux/if_link.h +++ b/include/uapi/linux/if_link.h @@ -237,6 +237,8 @@ enum { IFLA_BR_BRIDGE_ID, IFLA_BR_ROOT_PORT, IFLA_BR_ROOT_PATH_COST, + IFLA_BR_TOPOLOGY_CHANGE, + IFLA_BR_TOPOLOGY_CHANGE_DETECTED, __IFLA_BR_MAX, }; -- cgit v1.2.3 From d76bd14e0f759040efc8ce142dd6d1f9eca33d39 Mon Sep 17 00:00:00 2001 From: Nikolay Aleksandrov Date: Sun, 4 Oct 2015 14:23:34 +0200 Subject: bridge: netlink: export all timers Export the following bridge timers (also exported via sysfs): IFLA_BR_HELLO_TIMER, IFLA_BR_TCN_TIMER, IFLA_BR_TOPOLOGY_CHANGE_TIMER, IFLA_BR_GC_TIMER via netlink. Signed-off-by: Nikolay Aleksandrov Signed-off-by: David S. Miller --- include/uapi/linux/if_link.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include') diff --git a/include/uapi/linux/if_link.h b/include/uapi/linux/if_link.h index b00286ca1bfe..a1e33282ab9d 100644 --- a/include/uapi/linux/if_link.h +++ b/include/uapi/linux/if_link.h @@ -239,6 +239,10 @@ enum { IFLA_BR_ROOT_PATH_COST, IFLA_BR_TOPOLOGY_CHANGE, IFLA_BR_TOPOLOGY_CHANGE_DETECTED, + IFLA_BR_HELLO_TIMER, + IFLA_BR_TCN_TIMER, + IFLA_BR_TOPOLOGY_CHANGE_TIMER, + IFLA_BR_GC_TIMER, __IFLA_BR_MAX, }; -- cgit v1.2.3 From 111189abc5c3f0ea6f516a6c3e8d8c3a2cf391d9 Mon Sep 17 00:00:00 2001 From: Nikolay Aleksandrov Date: Sun, 4 Oct 2015 14:23:35 +0200 Subject: bridge: netlink: add group_addr support Add IFLA_BR_GROUP_ADDR attribute to allow setting and retrieving the group_addr via netlink. Signed-off-by: Nikolay Aleksandrov Signed-off-by: David S. Miller --- include/uapi/linux/if_link.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/uapi/linux/if_link.h b/include/uapi/linux/if_link.h index a1e33282ab9d..eaeaac17dfdd 100644 --- a/include/uapi/linux/if_link.h +++ b/include/uapi/linux/if_link.h @@ -243,6 +243,7 @@ enum { IFLA_BR_TCN_TIMER, IFLA_BR_TOPOLOGY_CHANGE_TIMER, IFLA_BR_GC_TIMER, + IFLA_BR_GROUP_ADDR, __IFLA_BR_MAX, }; -- cgit v1.2.3 From 150217c688217e549ef8a36ea4f6718977373765 Mon Sep 17 00:00:00 2001 From: Nikolay Aleksandrov Date: Sun, 4 Oct 2015 14:23:36 +0200 Subject: bridge: netlink: add fdb flush Simple attribute that flushes the bridge's fdb. Signed-off-by: Nikolay Aleksandrov Signed-off-by: David S. Miller --- include/uapi/linux/if_link.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/uapi/linux/if_link.h b/include/uapi/linux/if_link.h index eaeaac17dfdd..9ca9bf8bfe04 100644 --- a/include/uapi/linux/if_link.h +++ b/include/uapi/linux/if_link.h @@ -244,6 +244,7 @@ enum { IFLA_BR_TOPOLOGY_CHANGE_TIMER, IFLA_BR_GC_TIMER, IFLA_BR_GROUP_ADDR, + IFLA_BR_FDB_FLUSH, __IFLA_BR_MAX, }; -- cgit v1.2.3 From a9a6bc70f5f70b3835b081e401b469b88c7c8a3a Mon Sep 17 00:00:00 2001 From: Nikolay Aleksandrov Date: Sun, 4 Oct 2015 14:23:37 +0200 Subject: bridge: netlink: add support for multicast_router Add IFLA_BR_MCAST_ROUTER to allow setting and retrieving br->multicast_router when igmp snooping is enabled. Signed-off-by: Nikolay Aleksandrov Signed-off-by: David S. Miller --- include/uapi/linux/if_link.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/uapi/linux/if_link.h b/include/uapi/linux/if_link.h index 9ca9bf8bfe04..5d2c92973afe 100644 --- a/include/uapi/linux/if_link.h +++ b/include/uapi/linux/if_link.h @@ -245,6 +245,7 @@ enum { IFLA_BR_GC_TIMER, IFLA_BR_GROUP_ADDR, IFLA_BR_FDB_FLUSH, + IFLA_BR_MCAST_ROUTER, __IFLA_BR_MAX, }; -- cgit v1.2.3 From 89126327f921bd278c72284d38428443bbef344f Mon Sep 17 00:00:00 2001 From: Nikolay Aleksandrov Date: Sun, 4 Oct 2015 14:23:38 +0200 Subject: bridge: netlink: add support for multicast_snooping Add IFLA_BR_MCAST_SNOOPING to allow enabling/disabling multicast snooping via netlink. Signed-off-by: Nikolay Aleksandrov Signed-off-by: David S. Miller --- include/uapi/linux/if_link.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/uapi/linux/if_link.h b/include/uapi/linux/if_link.h index 5d2c92973afe..22cb395a713d 100644 --- a/include/uapi/linux/if_link.h +++ b/include/uapi/linux/if_link.h @@ -246,6 +246,7 @@ enum { IFLA_BR_GROUP_ADDR, IFLA_BR_FDB_FLUSH, IFLA_BR_MCAST_ROUTER, + IFLA_BR_MCAST_SNOOPING, __IFLA_BR_MAX, }; -- cgit v1.2.3 From 295141d9049bdf4fa316b325d2e2501b210dbe06 Mon Sep 17 00:00:00 2001 From: Nikolay Aleksandrov Date: Sun, 4 Oct 2015 14:23:39 +0200 Subject: bridge: netlink: add support for multicast_query_use_ifaddr Add IFLA_BR_MCAST_QUERY_USE_IFADDR to allow setting/getting br->multicast_query_use_ifaddr via netlink. Signed-off-by: Nikolay Aleksandrov Signed-off-by: David S. Miller --- include/uapi/linux/if_link.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/uapi/linux/if_link.h b/include/uapi/linux/if_link.h index 22cb395a713d..7090b3977eac 100644 --- a/include/uapi/linux/if_link.h +++ b/include/uapi/linux/if_link.h @@ -247,6 +247,7 @@ enum { IFLA_BR_FDB_FLUSH, IFLA_BR_MCAST_ROUTER, IFLA_BR_MCAST_SNOOPING, + IFLA_BR_MCAST_QUERY_USE_IFADDR, __IFLA_BR_MAX, }; -- cgit v1.2.3 From ba062d7cc6a09a8194eba975d5ee635378a55bfc Mon Sep 17 00:00:00 2001 From: Nikolay Aleksandrov Date: Sun, 4 Oct 2015 14:23:40 +0200 Subject: bridge: netlink: add support for multicast_querier Add IFLA_BR_MCAST_QUERIER to allow setting/getting br->multicast_querier via netlink. Signed-off-by: Nikolay Aleksandrov Signed-off-by: David S. Miller --- include/uapi/linux/if_link.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/uapi/linux/if_link.h b/include/uapi/linux/if_link.h index 7090b3977eac..fe5fac5c2a7f 100644 --- a/include/uapi/linux/if_link.h +++ b/include/uapi/linux/if_link.h @@ -248,6 +248,7 @@ enum { IFLA_BR_MCAST_ROUTER, IFLA_BR_MCAST_SNOOPING, IFLA_BR_MCAST_QUERY_USE_IFADDR, + IFLA_BR_MCAST_QUERIER, __IFLA_BR_MAX, }; -- cgit v1.2.3 From 431db3c050af0be72b3b01fa7484982f35cb268f Mon Sep 17 00:00:00 2001 From: Nikolay Aleksandrov Date: Sun, 4 Oct 2015 14:23:41 +0200 Subject: bridge: netlink: add support for igmp's hash_elasticity Add IFLA_BR_MCAST_HASH_ELASTICITY to allow setting/getting br->hash_elasticity via netlink. Signed-off-by: Nikolay Aleksandrov Signed-off-by: David S. Miller --- include/uapi/linux/if_link.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/uapi/linux/if_link.h b/include/uapi/linux/if_link.h index fe5fac5c2a7f..ca7ca766d8af 100644 --- a/include/uapi/linux/if_link.h +++ b/include/uapi/linux/if_link.h @@ -249,6 +249,7 @@ enum { IFLA_BR_MCAST_SNOOPING, IFLA_BR_MCAST_QUERY_USE_IFADDR, IFLA_BR_MCAST_QUERIER, + IFLA_BR_MCAST_HASH_ELASTICITY, __IFLA_BR_MAX, }; -- cgit v1.2.3 From 858079fdae16421d4908722140346cfdddedf343 Mon Sep 17 00:00:00 2001 From: Nikolay Aleksandrov Date: Sun, 4 Oct 2015 14:23:42 +0200 Subject: bridge: netlink: add support for igmp's hash_max Add IFLA_BR_MCAST_HASH_MAX to allow setting/getting br->hash_max via netlink. Signed-off-by: Nikolay Aleksandrov Signed-off-by: David S. Miller --- include/uapi/linux/if_link.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/uapi/linux/if_link.h b/include/uapi/linux/if_link.h index ca7ca766d8af..10a44a735512 100644 --- a/include/uapi/linux/if_link.h +++ b/include/uapi/linux/if_link.h @@ -250,6 +250,7 @@ enum { IFLA_BR_MCAST_QUERY_USE_IFADDR, IFLA_BR_MCAST_QUERIER, IFLA_BR_MCAST_HASH_ELASTICITY, + IFLA_BR_MCAST_HASH_MAX, __IFLA_BR_MAX, }; -- cgit v1.2.3 From 79b859f573d6afa64e328cc7f50ad7a209e0c92d Mon Sep 17 00:00:00 2001 From: Nikolay Aleksandrov Date: Sun, 4 Oct 2015 14:23:43 +0200 Subject: bridge: netlink: add support for multicast_last_member_count Add IFLA_BR_MCAST_LAST_MEMBER_CNT to allow setting/getting br->multicast_last_member_count via netlink. Signed-off-by: Nikolay Aleksandrov Signed-off-by: David S. Miller --- include/uapi/linux/if_link.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/uapi/linux/if_link.h b/include/uapi/linux/if_link.h index 10a44a735512..5409a461e47e 100644 --- a/include/uapi/linux/if_link.h +++ b/include/uapi/linux/if_link.h @@ -251,6 +251,7 @@ enum { IFLA_BR_MCAST_QUERIER, IFLA_BR_MCAST_HASH_ELASTICITY, IFLA_BR_MCAST_HASH_MAX, + IFLA_BR_MCAST_LAST_MEMBER_CNT, __IFLA_BR_MAX, }; -- cgit v1.2.3 From b89e6babad4b7ca7298ad863c6c83dc76b0abdef Mon Sep 17 00:00:00 2001 From: Nikolay Aleksandrov Date: Sun, 4 Oct 2015 14:23:44 +0200 Subject: bridge: netlink: add support for multicast_startup_query_count Add IFLA_BR_MCAST_STARTUP_QUERY_CNT to allow setting/getting br->multicast_startup_query_count via netlink. Also align the ifla comments. Signed-off-by: Nikolay Aleksandrov Signed-off-by: David S. Miller --- include/uapi/linux/if_link.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/uapi/linux/if_link.h b/include/uapi/linux/if_link.h index 5409a461e47e..fd841b5269c1 100644 --- a/include/uapi/linux/if_link.h +++ b/include/uapi/linux/if_link.h @@ -252,6 +252,7 @@ enum { IFLA_BR_MCAST_HASH_ELASTICITY, IFLA_BR_MCAST_HASH_MAX, IFLA_BR_MCAST_LAST_MEMBER_CNT, + IFLA_BR_MCAST_STARTUP_QUERY_CNT, __IFLA_BR_MAX, }; -- cgit v1.2.3 From 7e4df51eb35deedd3ba8d4db92a6c36fb7eff90a Mon Sep 17 00:00:00 2001 From: Nikolay Aleksandrov Date: Sun, 4 Oct 2015 14:23:45 +0200 Subject: bridge: netlink: add support for igmp's intervals Add support to set/get all of the igmp's configurable intervals via netlink. These currently are: IFLA_BR_MCAST_LAST_MEMBER_INTVL IFLA_BR_MCAST_MEMBERSHIP_INTVL IFLA_BR_MCAST_QUERIER_INTVL IFLA_BR_MCAST_QUERY_INTVL IFLA_BR_MCAST_QUERY_RESPONSE_INTVL IFLA_BR_MCAST_STARTUP_QUERY_INTVL Signed-off-by: Nikolay Aleksandrov Signed-off-by: David S. Miller --- include/uapi/linux/if_link.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include') diff --git a/include/uapi/linux/if_link.h b/include/uapi/linux/if_link.h index fd841b5269c1..b8c88aa19fef 100644 --- a/include/uapi/linux/if_link.h +++ b/include/uapi/linux/if_link.h @@ -253,6 +253,12 @@ enum { IFLA_BR_MCAST_HASH_MAX, IFLA_BR_MCAST_LAST_MEMBER_CNT, IFLA_BR_MCAST_STARTUP_QUERY_CNT, + IFLA_BR_MCAST_LAST_MEMBER_INTVL, + IFLA_BR_MCAST_MEMBERSHIP_INTVL, + IFLA_BR_MCAST_QUERIER_INTVL, + IFLA_BR_MCAST_QUERY_INTVL, + IFLA_BR_MCAST_QUERY_RESPONSE_INTVL, + IFLA_BR_MCAST_STARTUP_QUERY_INTVL, __IFLA_BR_MAX, }; -- cgit v1.2.3 From 93870cc02a0af4392401713d14235accafc752bc Mon Sep 17 00:00:00 2001 From: Nikolay Aleksandrov Date: Sun, 4 Oct 2015 14:23:46 +0200 Subject: bridge: netlink: add support for netfilter tables config Add support to allow getting/setting netfilter tables settings. Currently these are IFLA_BR_NF_CALL_IPTABLES, IFLA_BR_NF_CALL_IP6TABLES and IFLA_BR_NF_CALL_ARPTABLES. Signed-off-by: Nikolay Aleksandrov Signed-off-by: David S. Miller --- include/uapi/linux/if_link.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include') diff --git a/include/uapi/linux/if_link.h b/include/uapi/linux/if_link.h index b8c88aa19fef..0200bed6e5d6 100644 --- a/include/uapi/linux/if_link.h +++ b/include/uapi/linux/if_link.h @@ -259,6 +259,9 @@ enum { IFLA_BR_MCAST_QUERY_INTVL, IFLA_BR_MCAST_QUERY_RESPONSE_INTVL, IFLA_BR_MCAST_STARTUP_QUERY_INTVL, + IFLA_BR_NF_CALL_IPTABLES, + IFLA_BR_NF_CALL_IP6TABLES, + IFLA_BR_NF_CALL_ARPTABLES, __IFLA_BR_MAX, }; -- cgit v1.2.3 From 0f963b7592ef9e054974b6672b86ec1edd84b4bc Mon Sep 17 00:00:00 2001 From: Nikolay Aleksandrov Date: Sun, 4 Oct 2015 14:23:47 +0200 Subject: bridge: netlink: add support for default_pvid Add IFLA_BR_VLAN_DEFAULT_PVID to allow setting/getting bridge's default_pvid via netlink. Signed-off-by: Nikolay Aleksandrov Signed-off-by: David S. Miller --- include/uapi/linux/if_link.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/uapi/linux/if_link.h b/include/uapi/linux/if_link.h index 0200bed6e5d6..c5b15bfeabe2 100644 --- a/include/uapi/linux/if_link.h +++ b/include/uapi/linux/if_link.h @@ -262,6 +262,7 @@ enum { IFLA_BR_NF_CALL_IPTABLES, IFLA_BR_NF_CALL_IP6TABLES, IFLA_BR_NF_CALL_ARPTABLES, + IFLA_BR_VLAN_DEFAULT_PVID, __IFLA_BR_MAX, }; -- cgit v1.2.3 From 4a3f95b7b62e50a1e42e42ba6571ec9e747f4861 Mon Sep 17 00:00:00 2001 From: Marcel Holtmann Date: Sun, 4 Oct 2015 23:34:00 +0200 Subject: Bluetooth: Introduce HCI_DEV_OPEN and HCI_DEV_CLOSE events When opening the HCI transport via hdev->open send HCI_DEV_OPEN event and when closing the HCI transport via hdev->close send HCI_DEV_CLOSE. Signed-off-by: Marcel Holtmann Signed-off-by: Johan Hedberg --- include/net/bluetooth/hci.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/net/bluetooth/hci.h b/include/net/bluetooth/hci.h index 7ca6690355ea..e7f938cac7c6 100644 --- a/include/net/bluetooth/hci.h +++ b/include/net/bluetooth/hci.h @@ -44,6 +44,8 @@ #define HCI_DEV_DOWN 4 #define HCI_DEV_SUSPEND 5 #define HCI_DEV_RESUME 6 +#define HCI_DEV_OPEN 7 +#define HCI_DEV_CLOSE 8 /* HCI notify events */ #define HCI_NOTIFY_CONN_ADD 1 -- cgit v1.2.3 From 22db3cbcf9f91eef848db0986869822b4bf27193 Mon Sep 17 00:00:00 2001 From: Marcel Holtmann Date: Sun, 4 Oct 2015 23:34:03 +0200 Subject: Bluetooth: Send transport open and close monitor events When the core starts or shuts down the actual HCI transport, send a new monitor event that indicates that this is happening. These new events correspond to HCI_DEV_OPEN and HCI_DEV_CLOSE events. Signed-off-by: Marcel Holtmann Signed-off-by: Johan Hedberg --- include/net/bluetooth/hci_mon.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/net/bluetooth/hci_mon.h b/include/net/bluetooth/hci_mon.h index 77d1e5764185..37e4283d1d68 100644 --- a/include/net/bluetooth/hci_mon.h +++ b/include/net/bluetooth/hci_mon.h @@ -39,6 +39,8 @@ struct hci_mon_hdr { #define HCI_MON_ACL_RX_PKT 5 #define HCI_MON_SCO_TX_PKT 6 #define HCI_MON_SCO_RX_PKT 7 +#define HCI_MON_OPEN_INDEX 8 +#define HCI_MON_CLOSE_INDEX 9 struct hci_mon_new_index { __u8 type; -- cgit v1.2.3 From caf3f2676aaad395903d24a54e22f8ac4bc4823d Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Sun, 4 Oct 2015 21:08:08 -0700 Subject: inet: ip_skb_dst_mtu() should use sk_fullsock() SYN_RECV & TIMEWAIT sockets are not full blown, do not even try to call ip_sk_use_pmtu() on them. Fixes: ca6fb0651883 ("tcp: attach SYNACK messages to request sockets instead of listener") Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- include/net/ip.h | 9 ++++++--- 1 file changed, 6 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/include/net/ip.h b/include/net/ip.h index 91a6b2c88341..aa7811993276 100644 --- a/include/net/ip.h +++ b/include/net/ip.h @@ -323,12 +323,15 @@ static inline unsigned int ip_dst_mtu_maybe_forward(const struct dst_entry *dst, static inline unsigned int ip_skb_dst_mtu(const struct sk_buff *skb) { - if (!skb->sk || ip_sk_use_pmtu(skb->sk)) { + struct sock *sk = skb->sk; + + if (!sk || !sk_fullsock(sk) || ip_sk_use_pmtu(sk)) { bool forwarding = IPCB(skb)->flags & IPSKB_FORWARDED; + return ip_dst_mtu_maybe_forward(skb_dst(skb), forwarding); - } else { - return min(skb_dst(skb)->dev->mtu, IP_MAX_MTU); } + + return min(skb_dst(skb)->dev->mtu, IP_MAX_MTU); } u32 ip_idents_reserve(u32 hash, int segs); -- cgit v1.2.3 From e7eadb4de9e645e1b34539dc4128240b1e5f71dc Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Sun, 4 Oct 2015 21:08:09 -0700 Subject: ipv6: inet6_sk() should use sk_fullsock() SYN_RECV & TIMEWAIT sockets are not full blown, they do not have a pinet6 pointer. Fixes: ca6fb0651883 ("tcp: attach SYNACK messages to request sockets instead of listener") Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- include/linux/ipv6.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/ipv6.h b/include/linux/ipv6.h index f1f32af6d9b9..0ef2a97ccdb5 100644 --- a/include/linux/ipv6.h +++ b/include/linux/ipv6.h @@ -264,9 +264,9 @@ struct tcp6_timewait_sock { }; #if IS_ENABLED(CONFIG_IPV6) -static inline struct ipv6_pinfo * inet6_sk(const struct sock *__sk) +static inline struct ipv6_pinfo *inet6_sk(const struct sock *__sk) { - return inet_sk(__sk)->pinet6; + return sk_fullsock(__sk) ? inet_sk(__sk)->pinet6 : NULL; } static inline struct raw6_sock *raw6_sk(const struct sock *sk) -- cgit v1.2.3 From 004a5d0140ce1d05c1f5fce5df4baa2717a330e0 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Sun, 4 Oct 2015 21:08:10 -0700 Subject: net: use sk_fullsock() in __netdev_pick_tx() SYN_RECV & TIMEWAIT sockets are not full blown, they do not have a sk_dst_cache pointer. Fixes: ca6fb0651883 ("tcp: attach SYNACK messages to request sockets instead of listener") Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- include/net/request_sock.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/net/request_sock.h b/include/net/request_sock.h index dd423d840852..f83669460d82 100644 --- a/include/net/request_sock.h +++ b/include/net/request_sock.h @@ -92,6 +92,7 @@ reqsk_alloc(const struct request_sock_ops *ops, struct sock *sk_listener) req->rsk_listener = sk_listener; req_to_sk(req)->sk_prot = sk_listener->sk_prot; sk_node_init(&req_to_sk(req)->sk_node); + sk_tx_queue_clear(req_to_sk(req)); req->saved_syn = NULL; /* Following is temporary. It is coupled with debugging * helpers in reqsk_put() & reqsk_free() -- cgit v1.2.3 From a1a5344ddbe8fd3e080013b317ac9a664490cfdf Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Sun, 4 Oct 2015 21:08:11 -0700 Subject: tcp: avoid two atomic ops for syncookies inet_reqsk_alloc() is used to allocate a temporary request in order to generate a SYNACK with a cookie. Then later, syncookie validation also uses a temporary request. These paths already took a reference on listener refcount, we can avoid a couple of atomic operations. Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- include/net/inet_sock.h | 3 ++- include/net/request_sock.h | 11 ++++++++--- 2 files changed, 10 insertions(+), 4 deletions(-) (limited to 'include') diff --git a/include/net/inet_sock.h b/include/net/inet_sock.h index 47eb67b08abd..f5bf7310e334 100644 --- a/include/net/inet_sock.h +++ b/include/net/inet_sock.h @@ -245,7 +245,8 @@ static inline unsigned int __inet_ehashfn(const __be32 laddr, } struct request_sock *inet_reqsk_alloc(const struct request_sock_ops *ops, - struct sock *sk_listener); + struct sock *sk_listener, + bool attach_listener); static inline __u8 inet_sk_flowi_flags(const struct sock *sk) { diff --git a/include/net/request_sock.h b/include/net/request_sock.h index f83669460d82..95ab5d7aab96 100644 --- a/include/net/request_sock.h +++ b/include/net/request_sock.h @@ -80,7 +80,8 @@ static inline struct sock *req_to_sk(struct request_sock *req) } static inline struct request_sock * -reqsk_alloc(const struct request_sock_ops *ops, struct sock *sk_listener) +reqsk_alloc(const struct request_sock_ops *ops, struct sock *sk_listener, + bool attach_listener) { struct request_sock *req; @@ -88,8 +89,12 @@ reqsk_alloc(const struct request_sock_ops *ops, struct sock *sk_listener) if (req) { req->rsk_ops = ops; - sock_hold(sk_listener); - req->rsk_listener = sk_listener; + if (attach_listener) { + sock_hold(sk_listener); + req->rsk_listener = sk_listener; + } else { + req->rsk_listener = NULL; + } req_to_sk(req)->sk_prot = sk_listener->sk_prot; sk_node_init(&req_to_sk(req)->sk_node); sk_tx_queue_clear(req_to_sk(req)); -- cgit v1.2.3 From 0e884c78ee19e902f300ed147083c28a0c6302f0 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Peter=20N=C3=B8rlund?= Date: Wed, 30 Sep 2015 10:12:21 +0200 Subject: ipv4: L3 hash-based multipath MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Replaces the per-packet multipath with a hash-based multipath using source and destination address. Signed-off-by: Peter Nørlund Signed-off-by: David S. Miller --- include/net/ip_fib.h | 14 +++++++++++--- 1 file changed, 11 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/include/net/ip_fib.h b/include/net/ip_fib.h index 727d6e9a9685..7a51fd8d99e4 100644 --- a/include/net/ip_fib.h +++ b/include/net/ip_fib.h @@ -79,7 +79,7 @@ struct fib_nh { unsigned char nh_scope; #ifdef CONFIG_IP_ROUTE_MULTIPATH int nh_weight; - int nh_power; + atomic_t nh_upper_bound; #endif #ifdef CONFIG_IP_ROUTE_CLASSID __u32 nh_tclassid; @@ -118,7 +118,7 @@ struct fib_info { #define fib_advmss fib_metrics[RTAX_ADVMSS-1] int fib_nhs; #ifdef CONFIG_IP_ROUTE_MULTIPATH - int fib_power; + int fib_weight; #endif struct rcu_head rcu; struct fib_nh fib_nh[0]; @@ -320,7 +320,15 @@ int ip_fib_check_default(__be32 gw, struct net_device *dev); int fib_sync_down_dev(struct net_device *dev, unsigned long event); int fib_sync_down_addr(struct net *net, __be32 local); int fib_sync_up(struct net_device *dev, unsigned int nh_flags); -void fib_select_multipath(struct fib_result *res); + +extern u32 fib_multipath_secret __read_mostly; + +static inline int fib_multipath_hash(__be32 saddr, __be32 daddr) +{ + return jhash_2words(saddr, daddr, fib_multipath_secret) >> 1; +} + +void fib_select_multipath(struct fib_result *res, int hash); /* Exported by fib_trie.c */ void fib_trie_init(void); -- cgit v1.2.3 From 79a131592dbb81a2dba208622a2ffbfc53f28bc0 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Peter=20N=C3=B8rlund?= Date: Wed, 30 Sep 2015 10:12:22 +0200 Subject: ipv4: ICMP packet inspection for multipath MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit ICMP packets are inspected to let them route together with the flow they belong to, minimizing the chance that a problematic path will affect flows on other paths, and so that anycast environments can work with ECMP. Signed-off-by: Peter Nørlund Signed-off-by: David S. Miller --- include/net/route.h | 11 ++++++++++- 1 file changed, 10 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/net/route.h b/include/net/route.h index e211dc167db1..d32cb76f5302 100644 --- a/include/net/route.h +++ b/include/net/route.h @@ -28,6 +28,7 @@ #include #include #include +#include #include #include #include @@ -113,7 +114,15 @@ struct in_device; int ip_rt_init(void); void rt_cache_flush(struct net *net); void rt_flush_dev(struct net_device *dev); -struct rtable *__ip_route_output_key(struct net *, struct flowi4 *flp); +struct rtable *__ip_route_output_key_hash(struct net *, struct flowi4 *flp, + int mp_hash); + +static inline struct rtable *__ip_route_output_key(struct net *net, + struct flowi4 *flp) +{ + return __ip_route_output_key_hash(net, flp, -1); +} + struct rtable *ip_route_output_flow(struct net *, struct flowi4 *flp, const struct sock *sk); struct dst_entry *ipv4_blackhole_route(struct net *net, -- cgit v1.2.3 From 70ba07b675b53782ad366ebc4d3a00eab9a06bc9 Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Wed, 30 Sep 2015 17:32:01 +0200 Subject: atm: remove 'struct zatm_t_hist' The zatm_t_hist structure is not used anywhere in the kernel, but is exported to user space. As we are trying to eliminate uses of time_t in the kernel for y2038 compatibility, the current definition triggers checking tools because it contains 'struct timeval'. As pointed out by Chas Williams, the only user of this structure was the ZATM_GETHIST ioctl command that has been removed a long time ago, and we can remove the structure as well without breaking any user space. Signed-off-by: Arnd Bergmann Cc: Chas Williams <3chas3@gmail.com> Cc: linux-atm-general@lists.sourceforge.net Signed-off-by: David S. Miller --- include/uapi/linux/atm_zatm.h | 6 ------ 1 file changed, 6 deletions(-) (limited to 'include') diff --git a/include/uapi/linux/atm_zatm.h b/include/uapi/linux/atm_zatm.h index 10f0fa29454f..9c9c6ad55f14 100644 --- a/include/uapi/linux/atm_zatm.h +++ b/include/uapi/linux/atm_zatm.h @@ -35,12 +35,6 @@ struct zatm_pool_req { struct zatm_pool_info info; /* actual information */ }; -struct zatm_t_hist { - struct timeval real; /* real (wall-clock) time */ - struct timeval expected; /* expected real time */ -}; - - #define ZATM_OAM_POOL 0 /* free buffer pool for OAM cells */ #define ZATM_AAL0_POOL 1 /* free buffer pool for AAL0 cells */ #define ZATM_AAL5_POOL_BASE 2 /* first AAL5 free buffer pool */ -- cgit v1.2.3 From 7741c373cf3ea1f5383fa97fb7a640a429d3dd7c Mon Sep 17 00:00:00 2001 From: Jon Ringle Date: Thu, 1 Oct 2015 07:43:20 -0400 Subject: regmap: Allow installing custom reg_update_bits function This commit allows installing a custom reg_update_bits function for cases where the hardware provides a mechanism to set or clear register bits without a read/modify/write cycle. Such is the case with the Microchip ENCX24J600. Signed-off-by: Jon Ringle Signed-off-by: David S. Miller --- include/linux/regmap.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include') diff --git a/include/linux/regmap.h b/include/linux/regmap.h index 8fc0bfd8edc4..4d3a3b1680bb 100644 --- a/include/linux/regmap.h +++ b/include/linux/regmap.h @@ -296,6 +296,9 @@ typedef int (*regmap_hw_reg_read)(void *context, unsigned int reg, unsigned int *val); typedef int (*regmap_hw_reg_write)(void *context, unsigned int reg, unsigned int val); +typedef int (*regmap_hw_reg_update_bits)(void *context, unsigned int reg, + unsigned int mask, unsigned int val, + bool *change, bool force_write); typedef struct regmap_async *(*regmap_hw_async_alloc)(void); typedef void (*regmap_hw_free_context)(void *context); @@ -335,6 +338,7 @@ struct regmap_bus { regmap_hw_gather_write gather_write; regmap_hw_async_write async_write; regmap_hw_reg_write reg_write; + regmap_hw_reg_update_bits reg_update_bits; regmap_hw_read read; regmap_hw_reg_read reg_read; regmap_hw_free_context free_context; -- cgit v1.2.3 From bab18991871545dfbd10c931eb0fe8f7637156a9 Mon Sep 17 00:00:00 2001 From: Daniel Borkmann Date: Fri, 2 Oct 2015 15:17:33 +0200 Subject: bpf, seccomp: prepare for upcoming criu support The current ongoing effort to dump existing cBPF seccomp filters back to user space requires to hold the pre-transformed instructions like we do in case of socket filters from sk_attach_filter() side, so they can be reloaded in original form at a later point in time by utilities such as criu. To prepare for this, simply extend the bpf_prog_create_from_user() API to hold a flag that tells whether we should store the original or not. Also, fanout filters could make use of that in future for things like diag. While fanout filters already use bpf_prog_destroy(), move seccomp over to them as well to handle original programs when present. Signed-off-by: Daniel Borkmann Cc: Tycho Andersen Cc: Pavel Emelyanov Cc: Kees Cook Cc: Andy Lutomirski Cc: Alexei Starovoitov Tested-by: Tycho Andersen Acked-by: Alexei Starovoitov Signed-off-by: David S. Miller --- include/linux/filter.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/filter.h b/include/linux/filter.h index 3d5fd24b321b..1bbce14bcf17 100644 --- a/include/linux/filter.h +++ b/include/linux/filter.h @@ -411,7 +411,7 @@ typedef int (*bpf_aux_classic_check_t)(struct sock_filter *filter, int bpf_prog_create(struct bpf_prog **pfp, struct sock_fprog_kern *fprog); int bpf_prog_create_from_user(struct bpf_prog **pfp, struct sock_fprog *fprog, - bpf_aux_classic_check_t trans); + bpf_aux_classic_check_t trans, bool save_orig); void bpf_prog_destroy(struct bpf_prog *fp); int sk_attach_filter(struct sock_fprog *fprog, struct sock *sk); -- cgit v1.2.3 From 0cdf5640e4f6940bdbbefee4bb0adb7dffb185ec Mon Sep 17 00:00:00 2001 From: Daniel Borkmann Date: Fri, 2 Oct 2015 18:42:00 +0200 Subject: ebpf: include perf_event only where really needed Commit ea317b267e9d ("bpf: Add new bpf map type to store the pointer to struct perf_event") added perf_event.h to the main eBPF header, so it gets included for all users. perf_event.h is actually only needed from array map side, so lets sanitize this a bit. Signed-off-by: Daniel Borkmann Cc: Kaixu Xia Acked-by: Alexei Starovoitov Signed-off-by: David S. Miller --- include/linux/bpf.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index f57d7fed9ec3..c915a6b54570 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -10,7 +10,6 @@ #include #include #include -#include struct bpf_map; -- cgit v1.2.3 From 0647e708344f4bf8b9e3f1855361c597f93d084d Mon Sep 17 00:00:00 2001 From: Flavio Leitner Date: Wed, 30 Sep 2015 10:23:50 -0300 Subject: netfilter: remove dead code Remove __nf_conntrack_find() from headers. Fixes: dcd93ed4cd1 ("netfilter: nf_conntrack: remove dead code") Signed-off-by: Flavio Leitner Signed-off-by: Pablo Neira Ayuso --- include/net/netfilter/nf_conntrack.h | 4 ---- 1 file changed, 4 deletions(-) (limited to 'include') diff --git a/include/net/netfilter/nf_conntrack.h b/include/net/netfilter/nf_conntrack.h index d642f68a7c73..fde4068eec0b 100644 --- a/include/net/netfilter/nf_conntrack.h +++ b/include/net/netfilter/nf_conntrack.h @@ -183,10 +183,6 @@ void *nf_ct_alloc_hashtable(unsigned int *sizep, int nulls); void nf_ct_free_hashtable(void *hash, unsigned int size); -struct nf_conntrack_tuple_hash * -__nf_conntrack_find(struct net *net, u16 zone, - const struct nf_conntrack_tuple *tuple); - int nf_conntrack_hash_check_insert(struct nf_conn *ct); bool nf_ct_delete(struct nf_conn *ct, u32 pid, int report); -- cgit v1.2.3 From a4b4766c3cebb4018167e06b863d8e95b7274757 Mon Sep 17 00:00:00 2001 From: Ken-ichirou MATSUZAWA Date: Mon, 5 Oct 2015 11:47:13 +0900 Subject: netfilter: nfnetlink_queue: rename related to nfqueue attaching conntrack info The idea of this series of patch is to attach conntrack information to nflog like nfqueue has already done. nfqueue conntrack info attaching basis is generic, rename those names to generic one, glue. Signed-off-by: Ken-ichirou MATSUZAWA Signed-off-by: Pablo Neira Ayuso --- include/linux/netfilter.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/netfilter.h b/include/linux/netfilter.h index 3e5e8f2b65f6..27747deb96ed 100644 --- a/include/linux/netfilter.h +++ b/include/linux/netfilter.h @@ -377,7 +377,7 @@ struct nf_conn; enum ip_conntrack_info; struct nlattr; -struct nfq_ct_hook { +struct nfnl_ct_hook { struct nf_conn *(*get_ct)(struct sk_buff *skb, enum ip_conntrack_info *ctinfo); size_t (*build_size)(const struct nf_conn *ct); @@ -390,7 +390,7 @@ struct nfq_ct_hook { void (*seq_adjust)(struct sk_buff *skb, struct nf_conn *ct, enum ip_conntrack_info ctinfo, s32 off); }; -extern struct nfq_ct_hook __rcu *nfq_ct_hook; +extern struct nfnl_ct_hook __rcu *nfnl_ct_hook; /** * nf_skb_duplicated - TEE target has sent a packet -- cgit v1.2.3 From 224a05975ebbbdf507c65043f8aba280ccb39e6e Mon Sep 17 00:00:00 2001 From: Ken-ichirou MATSUZAWA Date: Mon, 5 Oct 2015 11:49:56 +0900 Subject: netfilter: ctnetlink: add const qualifier to nfnl_hook.get_ct get_ct as is and will not update its skb argument, and users of nfnl_ct_hook is currently only nfqueue, we can add const qualifier. Signed-off-by: Ken-ichirou MATSUZAWA --- include/linux/netfilter.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/netfilter.h b/include/linux/netfilter.h index 27747deb96ed..edb3dc32f1da 100644 --- a/include/linux/netfilter.h +++ b/include/linux/netfilter.h @@ -378,7 +378,7 @@ enum ip_conntrack_info; struct nlattr; struct nfnl_ct_hook { - struct nf_conn *(*get_ct)(struct sk_buff *skb, + struct nf_conn *(*get_ct)(const struct sk_buff *skb, enum ip_conntrack_info *ctinfo); size_t (*build_size)(const struct nf_conn *ct); int (*build)(struct sk_buff *skb, struct nf_conn *ct, -- cgit v1.2.3 From a29a9a585b2840a205f085a34dfd65c75e86f7c3 Mon Sep 17 00:00:00 2001 From: Ken-ichirou MATSUZAWA Date: Mon, 5 Oct 2015 11:50:46 +0900 Subject: netfilter: nfnetlink_log: allow to attach conntrack This patch enables to include the conntrack information together with the packet that is sent to user-space via NFLOG, then a user-space program can acquire NATed information by this NFULA_CT attribute. Including the conntrack information is optional, you can set it via NFULNL_CFG_F_CONNTRACK flag with the NFULA_CFG_FLAGS attribute like NFQUEUE. Signed-off-by: Ken-ichirou MATSUZAWA Signed-off-by: Pablo Neira Ayuso --- include/uapi/linux/netfilter/nfnetlink_log.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include') diff --git a/include/uapi/linux/netfilter/nfnetlink_log.h b/include/uapi/linux/netfilter/nfnetlink_log.h index 90c2c9575bac..fb21f0c717a1 100644 --- a/include/uapi/linux/netfilter/nfnetlink_log.h +++ b/include/uapi/linux/netfilter/nfnetlink_log.h @@ -51,6 +51,8 @@ enum nfulnl_attr_type { NFULA_HWTYPE, /* hardware type */ NFULA_HWHEADER, /* hardware header */ NFULA_HWLEN, /* hardware header length */ + NFULA_CT, /* nf_conntrack_netlink.h */ + NFULA_CT_INFO, /* enum ip_conntrack_info */ __NFULA_MAX }; @@ -93,5 +95,6 @@ enum nfulnl_attr_config { #define NFULNL_CFG_F_SEQ 0x0001 #define NFULNL_CFG_F_SEQ_GLOBAL 0x0002 +#define NFULNL_CFG_F_CONNTRACK 0x0004 #endif /* _NFNETLINK_LOG_H */ -- cgit v1.2.3 From 21c4c073f14509d685ed219aa3c76362a7bfa0ac Mon Sep 17 00:00:00 2001 From: "David S. Miller" Date: Tue, 6 Oct 2015 06:25:43 -0700 Subject: Revert "regmap: Allow installing custom reg_update_bits function" This reverts commit 7741c373cf3ea1f5383fa97fb7a640a429d3dd7c. --- include/linux/regmap.h | 4 ---- 1 file changed, 4 deletions(-) (limited to 'include') diff --git a/include/linux/regmap.h b/include/linux/regmap.h index 4d3a3b1680bb..8fc0bfd8edc4 100644 --- a/include/linux/regmap.h +++ b/include/linux/regmap.h @@ -296,9 +296,6 @@ typedef int (*regmap_hw_reg_read)(void *context, unsigned int reg, unsigned int *val); typedef int (*regmap_hw_reg_write)(void *context, unsigned int reg, unsigned int val); -typedef int (*regmap_hw_reg_update_bits)(void *context, unsigned int reg, - unsigned int mask, unsigned int val, - bool *change, bool force_write); typedef struct regmap_async *(*regmap_hw_async_alloc)(void); typedef void (*regmap_hw_free_context)(void *context); @@ -338,7 +335,6 @@ struct regmap_bus { regmap_hw_gather_write gather_write; regmap_hw_async_write async_write; regmap_hw_reg_write reg_write; - regmap_hw_reg_update_bits reg_update_bits; regmap_hw_read read; regmap_hw_reg_read reg_read; regmap_hw_free_context free_context; -- cgit v1.2.3 From 6b26ba3a7d952e611dcde1f3f77ce63bcc70540a Mon Sep 17 00:00:00 2001 From: Jiri Benc Date: Mon, 5 Oct 2015 13:09:47 +0200 Subject: openvswitch: netlink attributes for IPv6 tunneling Add netlink attributes for IPv6 tunnel addresses. This enables IPv6 support for tunnels. Signed-off-by: Jiri Benc Acked-by: Pravin B Shelar Acked-by: Thomas Graf Signed-off-by: David S. Miller --- include/uapi/linux/openvswitch.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/uapi/linux/openvswitch.h b/include/uapi/linux/openvswitch.h index 32e07d8cbaf4..4036e1b1980f 100644 --- a/include/uapi/linux/openvswitch.h +++ b/include/uapi/linux/openvswitch.h @@ -349,6 +349,8 @@ enum ovs_tunnel_key_attr { OVS_TUNNEL_KEY_ATTR_TP_SRC, /* be16 src Transport Port. */ OVS_TUNNEL_KEY_ATTR_TP_DST, /* be16 dst Transport Port. */ OVS_TUNNEL_KEY_ATTR_VXLAN_OPTS, /* Nested OVS_VXLAN_EXT_* */ + OVS_TUNNEL_KEY_ATTR_IPV6_SRC, /* struct in6_addr src IPv6 address. */ + OVS_TUNNEL_KEY_ATTR_IPV6_DST, /* struct in6_addr dst IPv6 address. */ __OVS_TUNNEL_KEY_ATTR_MAX }; -- cgit v1.2.3 From 6e2895a8e3824eb5611c97a015a3b6d678b4503e Mon Sep 17 00:00:00 2001 From: David Ahern Date: Mon, 5 Oct 2015 08:51:23 -0700 Subject: net: Rename FLOWI_FLAG_VRFSRC to FLOWI_FLAG_L3MDEV_SRC Signed-off-by: David Ahern Signed-off-by: David S. Miller --- include/net/flow.h | 2 +- include/net/route.h | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/net/flow.h b/include/net/flow.h index 9b85db85f13c..83969eebebf3 100644 --- a/include/net/flow.h +++ b/include/net/flow.h @@ -34,7 +34,7 @@ struct flowi_common { __u8 flowic_flags; #define FLOWI_FLAG_ANYSRC 0x01 #define FLOWI_FLAG_KNOWN_NH 0x02 -#define FLOWI_FLAG_VRFSRC 0x04 +#define FLOWI_FLAG_L3MDEV_SRC 0x04 #define FLOWI_FLAG_SKIP_NH_OIF 0x08 __u32 flowic_secid; struct flowi_tunnel flowic_tun_key; diff --git a/include/net/route.h b/include/net/route.h index d32cb76f5302..3e18d90b3f4e 100644 --- a/include/net/route.h +++ b/include/net/route.h @@ -267,7 +267,7 @@ static inline void ip_route_connect_init(struct flowi4 *fl4, __be32 dst, __be32 flow_flags |= FLOWI_FLAG_ANYSRC; if (netif_index_is_l3_master(sock_net(sk), oif)) - flow_flags |= FLOWI_FLAG_VRFSRC | FLOWI_FLAG_SKIP_NH_OIF; + flow_flags |= FLOWI_FLAG_L3MDEV_SRC | FLOWI_FLAG_SKIP_NH_OIF; flowi4_init_output(fl4, oif, sk->sk_mark, tos, RT_SCOPE_UNIVERSE, protocol, flow_flags, dst, src, dport, sport); -- cgit v1.2.3 From fee6d4c777a125e56de9370db3b2bf359bf958d6 Mon Sep 17 00:00:00 2001 From: David Ahern Date: Mon, 5 Oct 2015 08:51:24 -0700 Subject: net: Add netif_is_l3_slave IPv6 addrconf keys off of IFF_SLAVE so can not use it for L3 slave. Add a new private flag and add netif_is_l3_slave function for checking it. Signed-off-by: David Ahern Signed-off-by: David S. Miller --- include/linux/netdevice.h | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'include') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index b9450784ae06..b3374402c1ea 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -1261,6 +1261,7 @@ struct net_device_ops { * @IFF_L3MDEV_MASTER: device is an L3 master device * @IFF_NO_QUEUE: device can run without qdisc attached * @IFF_OPENVSWITCH: device is a Open vSwitch master + * @IFF_L3MDEV_SLAVE: device is enslaved to an L3 master device */ enum netdev_priv_flags { IFF_802_1Q_VLAN = 1<<0, @@ -1286,6 +1287,7 @@ enum netdev_priv_flags { IFF_L3MDEV_MASTER = 1<<20, IFF_NO_QUEUE = 1<<21, IFF_OPENVSWITCH = 1<<22, + IFF_L3MDEV_SLAVE = 1<<23, }; #define IFF_802_1Q_VLAN IFF_802_1Q_VLAN @@ -3830,6 +3832,11 @@ static inline bool netif_is_l3_master(const struct net_device *dev) return dev->priv_flags & IFF_L3MDEV_MASTER; } +static inline bool netif_is_l3_slave(const struct net_device *dev) +{ + return dev->priv_flags & IFF_L3MDEV_SLAVE; +} + static inline bool netif_is_bridge_master(const struct net_device *dev) { return dev->priv_flags & IFF_EBRIDGE; -- cgit v1.2.3 From 3ce58d84358c7b477811b5100152fad848f936fc Mon Sep 17 00:00:00 2001 From: David Ahern Date: Mon, 5 Oct 2015 08:51:25 -0700 Subject: net: Refactor path selection in __ip_route_output_key_hash VRF device needs the same path selection following lookup to set source address. Rather than duplicating code, move existing code into a function that is exported to modules. Code move only; no functional change. Signed-off-by: David Ahern Signed-off-by: David S. Miller --- include/net/ip_fib.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/net/ip_fib.h b/include/net/ip_fib.h index 7a51fd8d99e4..ac5c6e80586a 100644 --- a/include/net/ip_fib.h +++ b/include/net/ip_fib.h @@ -329,6 +329,8 @@ static inline int fib_multipath_hash(__be32 saddr, __be32 daddr) } void fib_select_multipath(struct fib_result *res, int hash); +void fib_select_path(struct net *net, struct fib_result *res, + struct flowi4 *fl4, int mp_hash); /* Exported by fib_trie.c */ void fib_trie_init(void); -- cgit v1.2.3 From 8cbb512c923d5f695ff6265b2b741b1718e3b444 Mon Sep 17 00:00:00 2001 From: David Ahern Date: Mon, 5 Oct 2015 08:51:26 -0700 Subject: net: Add source address lookup op for VRF Add operation to l3mdev to lookup source address for a given flow. Add support for the operation to VRF driver and convert existing IPv4 hooks to use the new lookup. Signed-off-by: David Ahern Signed-off-by: David S. Miller --- include/net/l3mdev.h | 27 +++++++++++++++++++++++++++ include/net/route.h | 7 ++++--- 2 files changed, 31 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/include/net/l3mdev.h b/include/net/l3mdev.h index 87cee05a0a17..44a19a171104 100644 --- a/include/net/l3mdev.h +++ b/include/net/l3mdev.h @@ -17,12 +17,16 @@ * @l3mdev_fib_table: Get FIB table id to use for lookups * * @l3mdev_get_rtable: Get cached IPv4 rtable (dst_entry) for device + * + * @l3mdev_get_saddr: Get source address for a flow */ struct l3mdev_ops { u32 (*l3mdev_fib_table)(const struct net_device *dev); struct rtable * (*l3mdev_get_rtable)(const struct net_device *dev, const struct flowi4 *fl4); + void (*l3mdev_get_saddr)(struct net_device *dev, + struct flowi4 *fl4); }; #ifdef CONFIG_NET_L3_MASTER_DEV @@ -100,6 +104,25 @@ static inline bool netif_index_is_l3_master(struct net *net, int ifindex) return rc; } +static inline void l3mdev_get_saddr(struct net *net, int ifindex, + struct flowi4 *fl4) +{ + struct net_device *dev; + + if (ifindex) { + + rcu_read_lock(); + + dev = dev_get_by_index_rcu(net, ifindex); + if (dev && netif_is_l3_master(dev) && + dev->l3mdev_ops->l3mdev_get_saddr) { + dev->l3mdev_ops->l3mdev_get_saddr(dev, fl4); + } + + rcu_read_unlock(); + } +} + #else static inline int l3mdev_master_ifindex_rcu(struct net_device *dev) @@ -144,6 +167,10 @@ static inline bool netif_index_is_l3_master(struct net *net, int ifindex) return false; } +static inline void l3mdev_get_saddr(struct net *net, int ifindex, + struct flowi4 *fl4) +{ +} #endif #endif /* _NET_L3MDEV_H_ */ diff --git a/include/net/route.h b/include/net/route.h index 3e18d90b3f4e..ee81307863d5 100644 --- a/include/net/route.h +++ b/include/net/route.h @@ -266,9 +266,6 @@ static inline void ip_route_connect_init(struct flowi4 *fl4, __be32 dst, __be32 if (inet_sk(sk)->transparent) flow_flags |= FLOWI_FLAG_ANYSRC; - if (netif_index_is_l3_master(sock_net(sk), oif)) - flow_flags |= FLOWI_FLAG_L3MDEV_SRC | FLOWI_FLAG_SKIP_NH_OIF; - flowi4_init_output(fl4, oif, sk->sk_mark, tos, RT_SCOPE_UNIVERSE, protocol, flow_flags, dst, src, dport, sport); } @@ -285,6 +282,10 @@ static inline struct rtable *ip_route_connect(struct flowi4 *fl4, ip_route_connect_init(fl4, dst, src, tos, oif, protocol, sport, dport, sk); + if (!src && oif) { + l3mdev_get_saddr(net, oif, fl4); + src = fl4->saddr; + } if (!dst || !src) { rt = __ip_route_output_key(net, fl4); if (IS_ERR(rt)) -- cgit v1.2.3 From 4ebc7660ab4559cad10b6595e05f70562bb26dc5 Mon Sep 17 00:00:00 2001 From: Nikolay Aleksandrov Date: Tue, 6 Oct 2015 14:11:55 +0200 Subject: bridge: netlink: export port's root id Add IFLA_BRPORT_ROOT_ID to allow getting the designated root id via netlink. Signed-off-by: Nikolay Aleksandrov Signed-off-by: David S. Miller --- include/uapi/linux/if_link.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/uapi/linux/if_link.h b/include/uapi/linux/if_link.h index c5b15bfeabe2..c45c1d7894e7 100644 --- a/include/uapi/linux/if_link.h +++ b/include/uapi/linux/if_link.h @@ -292,6 +292,7 @@ enum { IFLA_BRPORT_PROXYARP, /* proxy ARP */ IFLA_BRPORT_LEARNING_SYNC, /* mac learning sync from device */ IFLA_BRPORT_PROXYARP_WIFI, /* proxy ARP for Wi-Fi */ + IFLA_BRPORT_ROOT_ID, /* designated root */ __IFLA_BRPORT_MAX }; #define IFLA_BRPORT_MAX (__IFLA_BRPORT_MAX - 1) -- cgit v1.2.3 From 80df9a2692edf7afffda9282e716e7b1df198e07 Mon Sep 17 00:00:00 2001 From: Nikolay Aleksandrov Date: Tue, 6 Oct 2015 14:11:56 +0200 Subject: bridge: netlink: export port's bridge id Add IFLA_BRPORT_BRIDGE_ID to allow getting the designated bridge id via netlink. Signed-off-by: Nikolay Aleksandrov Signed-off-by: David S. Miller --- include/uapi/linux/if_link.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/uapi/linux/if_link.h b/include/uapi/linux/if_link.h index c45c1d7894e7..e891c32c9993 100644 --- a/include/uapi/linux/if_link.h +++ b/include/uapi/linux/if_link.h @@ -293,6 +293,7 @@ enum { IFLA_BRPORT_LEARNING_SYNC, /* mac learning sync from device */ IFLA_BRPORT_PROXYARP_WIFI, /* proxy ARP for Wi-Fi */ IFLA_BRPORT_ROOT_ID, /* designated root */ + IFLA_BRPORT_BRIDGE_ID, /* designated bridge */ __IFLA_BRPORT_MAX }; #define IFLA_BRPORT_MAX (__IFLA_BRPORT_MAX - 1) -- cgit v1.2.3 From 96f94e7f4a216282a24819968184c881e6343692 Mon Sep 17 00:00:00 2001 From: Nikolay Aleksandrov Date: Tue, 6 Oct 2015 14:11:57 +0200 Subject: bridge: netlink: export port's designated cost and port Add IFLA_BRPORT_DESIGNATED_(COST|PORT) to allow getting the port's designated cost and port respectively via netlink. Signed-off-by: Nikolay Aleksandrov Signed-off-by: David S. Miller --- include/uapi/linux/if_link.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/uapi/linux/if_link.h b/include/uapi/linux/if_link.h index e891c32c9993..837caf940135 100644 --- a/include/uapi/linux/if_link.h +++ b/include/uapi/linux/if_link.h @@ -294,6 +294,8 @@ enum { IFLA_BRPORT_PROXYARP_WIFI, /* proxy ARP for Wi-Fi */ IFLA_BRPORT_ROOT_ID, /* designated root */ IFLA_BRPORT_BRIDGE_ID, /* designated bridge */ + IFLA_BRPORT_DESIGNATED_PORT, + IFLA_BRPORT_DESIGNATED_COST, __IFLA_BRPORT_MAX }; #define IFLA_BRPORT_MAX (__IFLA_BRPORT_MAX - 1) -- cgit v1.2.3 From 42d452c4b5e7bf0e3024fa9512ec462f70545ae5 Mon Sep 17 00:00:00 2001 From: Nikolay Aleksandrov Date: Tue, 6 Oct 2015 14:11:58 +0200 Subject: bridge: netlink: export port's id and number Add IFLA_BRPORT_(ID|NO) to allow getting port's port_id and port_no respectively via netlink. Signed-off-by: Nikolay Aleksandrov Signed-off-by: David S. Miller --- include/uapi/linux/if_link.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/uapi/linux/if_link.h b/include/uapi/linux/if_link.h index 837caf940135..6857563eb27c 100644 --- a/include/uapi/linux/if_link.h +++ b/include/uapi/linux/if_link.h @@ -296,6 +296,8 @@ enum { IFLA_BRPORT_BRIDGE_ID, /* designated bridge */ IFLA_BRPORT_DESIGNATED_PORT, IFLA_BRPORT_DESIGNATED_COST, + IFLA_BRPORT_ID, + IFLA_BRPORT_NO, __IFLA_BRPORT_MAX }; #define IFLA_BRPORT_MAX (__IFLA_BRPORT_MAX - 1) -- cgit v1.2.3 From e08e838ac5707cb1f1294e0d53b31997a0367b99 Mon Sep 17 00:00:00 2001 From: Nikolay Aleksandrov Date: Tue, 6 Oct 2015 14:11:59 +0200 Subject: bridge: netlink: export port's topology_change_ack and config_pending Add IFLA_BRPORT_TOPOLOGY_CHANGE_ACK and IFLA_BRPORT_CONFIG_PENDING to allow getting port's topology_change_ack and config_pending respectively via netlink. Signed-off-by: Nikolay Aleksandrov Signed-off-by: David S. Miller --- include/uapi/linux/if_link.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/uapi/linux/if_link.h b/include/uapi/linux/if_link.h index 6857563eb27c..1d6aeb1bbe95 100644 --- a/include/uapi/linux/if_link.h +++ b/include/uapi/linux/if_link.h @@ -298,6 +298,8 @@ enum { IFLA_BRPORT_DESIGNATED_COST, IFLA_BRPORT_ID, IFLA_BRPORT_NO, + IFLA_BRPORT_TOPOLOGY_CHANGE_ACK, + IFLA_BRPORT_CONFIG_PENDING, __IFLA_BRPORT_MAX }; #define IFLA_BRPORT_MAX (__IFLA_BRPORT_MAX - 1) -- cgit v1.2.3 From 61c0a9a83e0b12c712cd686172446aba8ea48685 Mon Sep 17 00:00:00 2001 From: Nikolay Aleksandrov Date: Tue, 6 Oct 2015 14:12:00 +0200 Subject: bridge: netlink: export port's timer values Add the following attributes in order to export port's timer values: IFLA_BRPORT_MESSAGE_AGE_TIMER, IFLA_BRPORT_FORWARD_DELAY_TIMER and IFLA_BRPORT_HOLD_TIMER. Signed-off-by: Nikolay Aleksandrov Signed-off-by: David S. Miller --- include/uapi/linux/if_link.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include') diff --git a/include/uapi/linux/if_link.h b/include/uapi/linux/if_link.h index 1d6aeb1bbe95..9c17f605e013 100644 --- a/include/uapi/linux/if_link.h +++ b/include/uapi/linux/if_link.h @@ -300,6 +300,9 @@ enum { IFLA_BRPORT_NO, IFLA_BRPORT_TOPOLOGY_CHANGE_ACK, IFLA_BRPORT_CONFIG_PENDING, + IFLA_BRPORT_MESSAGE_AGE_TIMER, + IFLA_BRPORT_FORWARD_DELAY_TIMER, + IFLA_BRPORT_HOLD_TIMER, __IFLA_BRPORT_MAX }; #define IFLA_BRPORT_MAX (__IFLA_BRPORT_MAX - 1) -- cgit v1.2.3 From 9b0c6e4deb3df91bf0aea8158ea77dc58c9d90b6 Mon Sep 17 00:00:00 2001 From: Nikolay Aleksandrov Date: Tue, 6 Oct 2015 14:12:01 +0200 Subject: bridge: netlink: allow to flush port's fdb Add IFLA_BRPORT_FLUSH to allow flushing port's fdb similar to sysfs's flush. Signed-off-by: Nikolay Aleksandrov Signed-off-by: David S. Miller --- include/uapi/linux/if_link.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/uapi/linux/if_link.h b/include/uapi/linux/if_link.h index 9c17f605e013..fcea39a56095 100644 --- a/include/uapi/linux/if_link.h +++ b/include/uapi/linux/if_link.h @@ -303,6 +303,7 @@ enum { IFLA_BRPORT_MESSAGE_AGE_TIMER, IFLA_BRPORT_FORWARD_DELAY_TIMER, IFLA_BRPORT_HOLD_TIMER, + IFLA_BRPORT_FLUSH, __IFLA_BRPORT_MAX }; #define IFLA_BRPORT_MAX (__IFLA_BRPORT_MAX - 1) -- cgit v1.2.3 From 5d6ae479ab7ddf77bb22bdf739268581453ff886 Mon Sep 17 00:00:00 2001 From: Nikolay Aleksandrov Date: Tue, 6 Oct 2015 14:12:02 +0200 Subject: bridge: netlink: add support for port's multicast_router attribute Add IFLA_BRPORT_MULTICAST_ROUTER to allow setting/getting port's multicast_router via netlink. Signed-off-by: Nikolay Aleksandrov Signed-off-by: David S. Miller --- include/uapi/linux/if_link.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/uapi/linux/if_link.h b/include/uapi/linux/if_link.h index fcea39a56095..e3b6217f34f1 100644 --- a/include/uapi/linux/if_link.h +++ b/include/uapi/linux/if_link.h @@ -304,6 +304,7 @@ enum { IFLA_BRPORT_FORWARD_DELAY_TIMER, IFLA_BRPORT_HOLD_TIMER, IFLA_BRPORT_FLUSH, + IFLA_BRPORT_MULTICAST_ROUTER, __IFLA_BRPORT_MAX }; #define IFLA_BRPORT_MAX (__IFLA_BRPORT_MAX - 1) -- cgit v1.2.3 From 6c566dd5a1253f73458ce6ba6cf3830e9d38c132 Mon Sep 17 00:00:00 2001 From: Marcel Holtmann Date: Wed, 7 Oct 2015 15:32:13 +0200 Subject: Bluetooth: Send index information updates to monitor channel The Bluetooth public device address might change during controller setup and it makes it a lot simpler for monitoring tools if they just get told what the new address is. In addition include the manufacturer / company information of the controller. That allows for easy vendor specific HCI command and event handling. Signed-off-by: Marcel Holtmann Signed-off-by: Johan Hedberg --- include/net/bluetooth/hci_mon.h | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'include') diff --git a/include/net/bluetooth/hci_mon.h b/include/net/bluetooth/hci_mon.h index 37e4283d1d68..842bb754a078 100644 --- a/include/net/bluetooth/hci_mon.h +++ b/include/net/bluetooth/hci_mon.h @@ -41,6 +41,7 @@ struct hci_mon_hdr { #define HCI_MON_SCO_RX_PKT 7 #define HCI_MON_OPEN_INDEX 8 #define HCI_MON_CLOSE_INDEX 9 +#define HCI_MON_INDEX_INFO 10 struct hci_mon_new_index { __u8 type; @@ -50,4 +51,10 @@ struct hci_mon_new_index { } __packed; #define HCI_MON_NEW_INDEX_SIZE 16 +struct hci_mon_index_info { + bdaddr_t bdaddr; + __le16 manufacturer; +} __packed; +#define HCI_MON_INDEX_INFO_SIZE 8 + #endif /* __HCI_MON_H */ -- cgit v1.2.3 From e875ff84079b9e7d3ce24b97e3396230d41044d4 Mon Sep 17 00:00:00 2001 From: Marcel Holtmann Date: Wed, 7 Oct 2015 16:38:35 +0200 Subject: Bluetooth: Add support for vendor specific diagnostic channel Introduce hci_recv_diag function for HCI drivers to allow sending vendor specific diagnostic messages into the Bluetooth core stack. The messages are not processed, but they are forwarded to the monitor channel and can be retrieved by user space diagnostic tools. Signed-off-by: Marcel Holtmann Signed-off-by: Johan Hedberg --- include/net/bluetooth/hci.h | 1 + include/net/bluetooth/hci_core.h | 1 + include/net/bluetooth/hci_mon.h | 1 + 3 files changed, 3 insertions(+) (limited to 'include') diff --git a/include/net/bluetooth/hci.h b/include/net/bluetooth/hci.h index e7f938cac7c6..cf75c4391945 100644 --- a/include/net/bluetooth/hci.h +++ b/include/net/bluetooth/hci.h @@ -262,6 +262,7 @@ enum { #define HCI_ACLDATA_PKT 0x02 #define HCI_SCODATA_PKT 0x03 #define HCI_EVENT_PKT 0x04 +#define HCI_DIAG_PKT 0xf0 #define HCI_VENDOR_PKT 0xff /* HCI packet types */ diff --git a/include/net/bluetooth/hci_core.h b/include/net/bluetooth/hci_core.h index 61dc786358be..d473b67a2c65 100644 --- a/include/net/bluetooth/hci_core.h +++ b/include/net/bluetooth/hci_core.h @@ -1066,6 +1066,7 @@ int hci_remove_adv_instance(struct hci_dev *hdev, u8 instance); void hci_event_packet(struct hci_dev *hdev, struct sk_buff *skb); int hci_recv_frame(struct hci_dev *hdev, struct sk_buff *skb); +int hci_recv_diag(struct hci_dev *hdev, struct sk_buff *skb); void hci_init_sysfs(struct hci_dev *hdev); void hci_conn_init_sysfs(struct hci_conn *conn); diff --git a/include/net/bluetooth/hci_mon.h b/include/net/bluetooth/hci_mon.h index 842bb754a078..2b67567cf28d 100644 --- a/include/net/bluetooth/hci_mon.h +++ b/include/net/bluetooth/hci_mon.h @@ -42,6 +42,7 @@ struct hci_mon_hdr { #define HCI_MON_OPEN_INDEX 8 #define HCI_MON_CLOSE_INDEX 9 #define HCI_MON_INDEX_INFO 10 +#define HCI_MON_VENDOR_DIAG 11 struct hci_mon_new_index { __u8 type; -- cgit v1.2.3 From 4b4113d6dbdbdac095743c05f694af9b7cdc9a44 Mon Sep 17 00:00:00 2001 From: Marcel Holtmann Date: Wed, 7 Oct 2015 19:52:35 +0200 Subject: Bluetooth: Add debugfs entry for setting vendor diagnostic mode This adds a new debugfs entry for enabling and disabling the vendor diagnostic mode. It is only exposed for drivers that provide the set_diag driver callback and actually have an option for vendor specific diagnostic information. Signed-off-by: Marcel Holtmann Signed-off-by: Johan Hedberg --- include/net/bluetooth/hci.h | 1 + include/net/bluetooth/hci_core.h | 1 + 2 files changed, 2 insertions(+) (limited to 'include') diff --git a/include/net/bluetooth/hci.h b/include/net/bluetooth/hci.h index cf75c4391945..a26ff28ca878 100644 --- a/include/net/bluetooth/hci.h +++ b/include/net/bluetooth/hci.h @@ -240,6 +240,7 @@ enum { HCI_LE_SCAN_INTERRUPTED, HCI_DUT_MODE, + HCI_VENDOR_DIAG, HCI_FORCE_BREDR_SMP, HCI_FORCE_STATIC_ADDR, diff --git a/include/net/bluetooth/hci_core.h b/include/net/bluetooth/hci_core.h index d473b67a2c65..f28470e59682 100644 --- a/include/net/bluetooth/hci_core.h +++ b/include/net/bluetooth/hci_core.h @@ -398,6 +398,7 @@ struct hci_dev { int (*send)(struct hci_dev *hdev, struct sk_buff *skb); void (*notify)(struct hci_dev *hdev, unsigned int evt); void (*hw_error)(struct hci_dev *hdev, u8 code); + int (*set_diag)(struct hci_dev *hdev, bool enable); int (*set_bdaddr)(struct hci_dev *hdev, const bdaddr_t *bdaddr); }; -- cgit v1.2.3 From 13206b6bff3b15b724926a222406476bf2c23c40 Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Wed, 7 Oct 2015 16:48:35 -0500 Subject: net: Pass net into dst_output and remove dst_output_okfn Replace dst_output_okfn with dst_output Signed-off-by: "Eric W. Biederman" Signed-off-by: David S. Miller --- include/net/dst.h | 6 +----- 1 file changed, 1 insertion(+), 5 deletions(-) (limited to 'include') diff --git a/include/net/dst.h b/include/net/dst.h index 779206c15f8b..fdd01fed1a7b 100644 --- a/include/net/dst.h +++ b/include/net/dst.h @@ -454,14 +454,10 @@ static inline void dst_set_expires(struct dst_entry *dst, int timeout) } /* Output packet to network from transport. */ -static inline int dst_output(struct sock *sk, struct sk_buff *skb) +static inline int dst_output(struct net *net, struct sock *sk, struct sk_buff *skb) { return skb_dst(skb)->output(sk, skb); } -static inline int dst_output_okfn(struct net *net, struct sock *sk, struct sk_buff *skb) -{ - return dst_output(sk, skb); -} /* Input packet from network to transport. */ static inline int dst_input(struct sk_buff *skb) -- cgit v1.2.3 From 4ebdfba73c09d8568d891bae87c40fad43dd7f41 Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Wed, 7 Oct 2015 16:48:36 -0500 Subject: dst: Pass a sk into .local_out For consistency with the other similar methods in the kernel pass a struct sock into the dst_ops .local_out method. Simplifying the socket passing case is needed a prequel to passing a struct net reference into .local_out. Signed-off-by: "Eric W. Biederman" Signed-off-by: David S. Miller --- include/net/dst_ops.h | 2 +- include/net/ip.h | 1 + include/net/ipv6.h | 1 + 3 files changed, 3 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/net/dst_ops.h b/include/net/dst_ops.h index d64253914a6a..3f26a6af444e 100644 --- a/include/net/dst_ops.h +++ b/include/net/dst_ops.h @@ -28,7 +28,7 @@ struct dst_ops { struct sk_buff *skb, u32 mtu); void (*redirect)(struct dst_entry *dst, struct sock *sk, struct sk_buff *skb); - int (*local_out)(struct sk_buff *skb); + int (*local_out)(struct sock *sk, struct sk_buff *skb); struct neighbour * (*neigh_lookup)(const struct dst_entry *dst, struct sk_buff *skb, const void *daddr); diff --git a/include/net/ip.h b/include/net/ip.h index dd06ab3669f9..ea1f721f7224 100644 --- a/include/net/ip.h +++ b/include/net/ip.h @@ -112,6 +112,7 @@ int ip_mc_output(struct sock *sk, struct sk_buff *skb); int ip_do_fragment(struct net *net, struct sock *sk, struct sk_buff *skb, int (*output)(struct net *, struct sock *, struct sk_buff *)); void ip_send_check(struct iphdr *ip); +int __ip_local_out_sk(struct sock *sk, struct sk_buff *skb); int __ip_local_out(struct sk_buff *skb); int ip_local_out_sk(struct sock *sk, struct sk_buff *skb); static inline int ip_local_out(struct sk_buff *skb) diff --git a/include/net/ipv6.h b/include/net/ipv6.h index 3dde042bcd3f..56920262dbe9 100644 --- a/include/net/ipv6.h +++ b/include/net/ipv6.h @@ -865,6 +865,7 @@ int ip6_forward(struct sk_buff *skb); int ip6_input(struct sk_buff *skb); int ip6_mc_input(struct sk_buff *skb); +int __ip6_local_out_sk(struct sock *sk, struct sk_buff *skb); int __ip6_local_out(struct sk_buff *skb); int ip6_local_out_sk(struct sock *sk, struct sk_buff *skb); int ip6_local_out(struct sk_buff *skb); -- cgit v1.2.3 From b92dacd45698e120104ff81066ceb534916090d9 Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Wed, 7 Oct 2015 16:48:37 -0500 Subject: ipv4: Merge __ip_local_out and __ip_local_out_sk Signed-off-by: "Eric W. Biederman" Signed-off-by: David S. Miller --- include/net/ip.h | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) (limited to 'include') diff --git a/include/net/ip.h b/include/net/ip.h index ea1f721f7224..46272e04f3b6 100644 --- a/include/net/ip.h +++ b/include/net/ip.h @@ -112,8 +112,7 @@ int ip_mc_output(struct sock *sk, struct sk_buff *skb); int ip_do_fragment(struct net *net, struct sock *sk, struct sk_buff *skb, int (*output)(struct net *, struct sock *, struct sk_buff *)); void ip_send_check(struct iphdr *ip); -int __ip_local_out_sk(struct sock *sk, struct sk_buff *skb); -int __ip_local_out(struct sk_buff *skb); +int __ip_local_out(struct sock *sk, struct sk_buff *skb); int ip_local_out_sk(struct sock *sk, struct sk_buff *skb); static inline int ip_local_out(struct sk_buff *skb) { -- cgit v1.2.3 From e2cb77db089796f163092326ca25512845df7a3a Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Wed, 7 Oct 2015 16:48:38 -0500 Subject: ipv4: Merge ip_local_out and ip_local_out_sk It is confusing and silly hiding a parameter so modify all of the callers to pass in the appropriate socket or skb->sk if no socket is known. Signed-off-by: "Eric W. Biederman" Signed-off-by: David S. Miller --- include/net/ip.h | 6 +----- 1 file changed, 1 insertion(+), 5 deletions(-) (limited to 'include') diff --git a/include/net/ip.h b/include/net/ip.h index 46272e04f3b6..03e80f936847 100644 --- a/include/net/ip.h +++ b/include/net/ip.h @@ -113,11 +113,7 @@ int ip_do_fragment(struct net *net, struct sock *sk, struct sk_buff *skb, int (*output)(struct net *, struct sock *, struct sk_buff *)); void ip_send_check(struct iphdr *ip); int __ip_local_out(struct sock *sk, struct sk_buff *skb); -int ip_local_out_sk(struct sock *sk, struct sk_buff *skb); -static inline int ip_local_out(struct sk_buff *skb) -{ - return ip_local_out_sk(skb->sk, skb); -} +int ip_local_out(struct sock *sk, struct sk_buff *skb); int ip_queue_xmit(struct sock *sk, struct sk_buff *skb, struct flowi *fl); void ip_init(void); -- cgit v1.2.3 From 9f8955cc468ddb7d08a0e614a45f9a82c4019b00 Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Wed, 7 Oct 2015 16:48:39 -0500 Subject: ipv6: Merge __ip6_local_out and __ip6_local_out_sk Only __ip6_local_out_sk has callers so rename __ip6_local_out_sk __ip6_local_out and remove the previous __ip6_local_out. Signed-off-by: "Eric W. Biederman" Signed-off-by: David S. Miller --- include/net/ipv6.h | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) (limited to 'include') diff --git a/include/net/ipv6.h b/include/net/ipv6.h index 56920262dbe9..be7e7689514b 100644 --- a/include/net/ipv6.h +++ b/include/net/ipv6.h @@ -865,8 +865,7 @@ int ip6_forward(struct sk_buff *skb); int ip6_input(struct sk_buff *skb); int ip6_mc_input(struct sk_buff *skb); -int __ip6_local_out_sk(struct sock *sk, struct sk_buff *skb); -int __ip6_local_out(struct sk_buff *skb); +int __ip6_local_out(struct sock *sk, struct sk_buff *skb); int ip6_local_out_sk(struct sock *sk, struct sk_buff *skb); int ip6_local_out(struct sk_buff *skb); -- cgit v1.2.3 From 792883303cdb3a7edd16017d7aba53926189ef41 Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Wed, 7 Oct 2015 16:48:40 -0500 Subject: ipv6: Merge ip6_local_out and ip6_local_out_sk Stop hidding the sk parameter with an inline helper function and make all of the callers pass it, so that it is clear what the function is doing. Signed-off-by: "Eric W. Biederman" Signed-off-by: David S. Miller --- include/net/ip6_tunnel.h | 2 +- include/net/ipv6.h | 3 +-- 2 files changed, 2 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/include/net/ip6_tunnel.h b/include/net/ip6_tunnel.h index fa915fa0f703..8f18a8b126e9 100644 --- a/include/net/ip6_tunnel.h +++ b/include/net/ip6_tunnel.h @@ -87,7 +87,7 @@ static inline void ip6tunnel_xmit(struct sock *sk, struct sk_buff *skb, int pkt_len, err; pkt_len = skb->len - skb_inner_network_offset(skb); - err = ip6_local_out_sk(sk, skb); + err = ip6_local_out(sk, skb); if (net_xmit_eval(err) == 0) { struct pcpu_sw_netstats *tstats = this_cpu_ptr(dev->tstats); diff --git a/include/net/ipv6.h b/include/net/ipv6.h index be7e7689514b..30eb1821c184 100644 --- a/include/net/ipv6.h +++ b/include/net/ipv6.h @@ -866,8 +866,7 @@ int ip6_input(struct sk_buff *skb); int ip6_mc_input(struct sk_buff *skb); int __ip6_local_out(struct sock *sk, struct sk_buff *skb); -int ip6_local_out_sk(struct sock *sk, struct sk_buff *skb); -int ip6_local_out(struct sk_buff *skb); +int ip6_local_out(struct sock *sk, struct sk_buff *skb); /* * Extension header (options) processing -- cgit v1.2.3 From cf91a99daa4651d0c1f52b8c3d813fd44b43cada Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Wed, 7 Oct 2015 16:48:45 -0500 Subject: ipv4, ipv6: Pass net into __ip_local_out and __ip6_local_out Signed-off-by: "Eric W. Biederman" Signed-off-by: David S. Miller --- include/net/dst_ops.h | 3 ++- include/net/ip.h | 2 +- include/net/ipv6.h | 2 +- 3 files changed, 4 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/include/net/dst_ops.h b/include/net/dst_ops.h index 3f26a6af444e..a0d443ca16fc 100644 --- a/include/net/dst_ops.h +++ b/include/net/dst_ops.h @@ -9,6 +9,7 @@ struct kmem_cachep; struct net_device; struct sk_buff; struct sock; +struct net; struct dst_ops { unsigned short family; @@ -28,7 +29,7 @@ struct dst_ops { struct sk_buff *skb, u32 mtu); void (*redirect)(struct dst_entry *dst, struct sock *sk, struct sk_buff *skb); - int (*local_out)(struct sock *sk, struct sk_buff *skb); + int (*local_out)(struct net *net, struct sock *sk, struct sk_buff *skb); struct neighbour * (*neigh_lookup)(const struct dst_entry *dst, struct sk_buff *skb, const void *daddr); diff --git a/include/net/ip.h b/include/net/ip.h index 03e80f936847..34b40381fb9b 100644 --- a/include/net/ip.h +++ b/include/net/ip.h @@ -112,7 +112,7 @@ int ip_mc_output(struct sock *sk, struct sk_buff *skb); int ip_do_fragment(struct net *net, struct sock *sk, struct sk_buff *skb, int (*output)(struct net *, struct sock *, struct sk_buff *)); void ip_send_check(struct iphdr *ip); -int __ip_local_out(struct sock *sk, struct sk_buff *skb); +int __ip_local_out(struct net *net, struct sock *sk, struct sk_buff *skb); int ip_local_out(struct sock *sk, struct sk_buff *skb); int ip_queue_xmit(struct sock *sk, struct sk_buff *skb, struct flowi *fl); diff --git a/include/net/ipv6.h b/include/net/ipv6.h index 30eb1821c184..42834039cf20 100644 --- a/include/net/ipv6.h +++ b/include/net/ipv6.h @@ -865,7 +865,7 @@ int ip6_forward(struct sk_buff *skb); int ip6_input(struct sk_buff *skb); int ip6_mc_input(struct sk_buff *skb); -int __ip6_local_out(struct sock *sk, struct sk_buff *skb); +int __ip6_local_out(struct net *net, struct sock *sk, struct sk_buff *skb); int ip6_local_out(struct sock *sk, struct sk_buff *skb); /* -- cgit v1.2.3 From 33224b16ffccb49cf798317670389e0bfba0024c Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Wed, 7 Oct 2015 16:48:46 -0500 Subject: ipv4, ipv6: Pass net into ip_local_out and ip6_local_out Signed-off-by: "Eric W. Biederman" Signed-off-by: David S. Miller --- include/net/ip.h | 2 +- include/net/ip6_tunnel.h | 2 +- include/net/ipv6.h | 2 +- 3 files changed, 3 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/include/net/ip.h b/include/net/ip.h index 34b40381fb9b..7febbab784cd 100644 --- a/include/net/ip.h +++ b/include/net/ip.h @@ -113,7 +113,7 @@ int ip_do_fragment(struct net *net, struct sock *sk, struct sk_buff *skb, int (*output)(struct net *, struct sock *, struct sk_buff *)); void ip_send_check(struct iphdr *ip); int __ip_local_out(struct net *net, struct sock *sk, struct sk_buff *skb); -int ip_local_out(struct sock *sk, struct sk_buff *skb); +int ip_local_out(struct net *net, struct sock *sk, struct sk_buff *skb); int ip_queue_xmit(struct sock *sk, struct sk_buff *skb, struct flowi *fl); void ip_init(void); diff --git a/include/net/ip6_tunnel.h b/include/net/ip6_tunnel.h index 8f18a8b126e9..aaee6fa02cf1 100644 --- a/include/net/ip6_tunnel.h +++ b/include/net/ip6_tunnel.h @@ -87,7 +87,7 @@ static inline void ip6tunnel_xmit(struct sock *sk, struct sk_buff *skb, int pkt_len, err; pkt_len = skb->len - skb_inner_network_offset(skb); - err = ip6_local_out(sk, skb); + err = ip6_local_out(dev_net(skb_dst(skb)->dev), sk, skb); if (net_xmit_eval(err) == 0) { struct pcpu_sw_netstats *tstats = this_cpu_ptr(dev->tstats); diff --git a/include/net/ipv6.h b/include/net/ipv6.h index 42834039cf20..fce8120c2be3 100644 --- a/include/net/ipv6.h +++ b/include/net/ipv6.h @@ -866,7 +866,7 @@ int ip6_input(struct sk_buff *skb); int ip6_mc_input(struct sk_buff *skb); int __ip6_local_out(struct net *net, struct sock *sk, struct sk_buff *skb); -int ip6_local_out(struct sock *sk, struct sk_buff *skb); +int ip6_local_out(struct net *net, struct sock *sk, struct sk_buff *skb); /* * Extension header (options) processing -- cgit v1.2.3 From ede2059dbaf9c6557a49d466c8c7778343b208ff Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Wed, 7 Oct 2015 16:48:47 -0500 Subject: dst: Pass net into dst->output The network namespace is already passed into dst_output pass it into dst->output lwt->output and friends. Signed-off-by: "Eric W. Biederman" Signed-off-by: David S. Miller --- include/net/dst.h | 8 ++++---- include/net/ip.h | 4 ++-- include/net/ipv6.h | 2 +- include/net/lwtunnel.h | 8 ++++---- include/net/xfrm.h | 6 +++--- 5 files changed, 14 insertions(+), 14 deletions(-) (limited to 'include') diff --git a/include/net/dst.h b/include/net/dst.h index fdd01fed1a7b..1279f9b09791 100644 --- a/include/net/dst.h +++ b/include/net/dst.h @@ -45,7 +45,7 @@ struct dst_entry { void *__pad1; #endif int (*input)(struct sk_buff *); - int (*output)(struct sock *sk, struct sk_buff *skb); + int (*output)(struct net *net, struct sock *sk, struct sk_buff *skb); unsigned short flags; #define DST_HOST 0x0001 @@ -365,10 +365,10 @@ static inline void skb_tunnel_rx(struct sk_buff *skb, struct net_device *dev, __skb_tunnel_rx(skb, dev, net); } -int dst_discard_sk(struct sock *sk, struct sk_buff *skb); +int dst_discard_out(struct net *net, struct sock *sk, struct sk_buff *skb); static inline int dst_discard(struct sk_buff *skb) { - return dst_discard_sk(skb->sk, skb); + return dst_discard_out(&init_net, skb->sk, skb); } void *dst_alloc(struct dst_ops *ops, struct net_device *dev, int initial_ref, int initial_obsolete, unsigned short flags); @@ -456,7 +456,7 @@ static inline void dst_set_expires(struct dst_entry *dst, int timeout) /* Output packet to network from transport. */ static inline int dst_output(struct net *net, struct sock *sk, struct sk_buff *skb) { - return skb_dst(skb)->output(sk, skb); + return skb_dst(skb)->output(net, sk, skb); } /* Input packet from network to transport. */ diff --git a/include/net/ip.h b/include/net/ip.h index 7febbab784cd..3c904a28d5e5 100644 --- a/include/net/ip.h +++ b/include/net/ip.h @@ -107,8 +107,8 @@ int ip_rcv(struct sk_buff *skb, struct net_device *dev, struct packet_type *pt, struct net_device *orig_dev); int ip_local_deliver(struct sk_buff *skb); int ip_mr_input(struct sk_buff *skb); -int ip_output(struct sock *sk, struct sk_buff *skb); -int ip_mc_output(struct sock *sk, struct sk_buff *skb); +int ip_output(struct net *net, struct sock *sk, struct sk_buff *skb); +int ip_mc_output(struct net *net, struct sock *sk, struct sk_buff *skb); int ip_do_fragment(struct net *net, struct sock *sk, struct sk_buff *skb, int (*output)(struct net *, struct sock *, struct sk_buff *)); void ip_send_check(struct iphdr *ip); diff --git a/include/net/ipv6.h b/include/net/ipv6.h index fce8120c2be3..e1a10b0ac0b0 100644 --- a/include/net/ipv6.h +++ b/include/net/ipv6.h @@ -860,7 +860,7 @@ struct dst_entry *ip6_blackhole_route(struct net *net, * skb processing functions */ -int ip6_output(struct sock *sk, struct sk_buff *skb); +int ip6_output(struct net *net, struct sock *sk, struct sk_buff *skb); int ip6_forward(struct sk_buff *skb); int ip6_input(struct sk_buff *skb); int ip6_mc_input(struct sk_buff *skb); diff --git a/include/net/lwtunnel.h b/include/net/lwtunnel.h index fce0e35e74d0..66350ce3e955 100644 --- a/include/net/lwtunnel.h +++ b/include/net/lwtunnel.h @@ -18,7 +18,7 @@ struct lwtunnel_state { __u16 type; __u16 flags; atomic_t refcnt; - int (*orig_output)(struct sock *sk, struct sk_buff *skb); + int (*orig_output)(struct net *net, struct sock *sk, struct sk_buff *skb); int (*orig_input)(struct sk_buff *); int len; __u8 data[0]; @@ -28,7 +28,7 @@ struct lwtunnel_encap_ops { int (*build_state)(struct net_device *dev, struct nlattr *encap, unsigned int family, const void *cfg, struct lwtunnel_state **ts); - int (*output)(struct sock *sk, struct sk_buff *skb); + int (*output)(struct net *net, struct sock *sk, struct sk_buff *skb); int (*input)(struct sk_buff *skb); int (*fill_encap)(struct sk_buff *skb, struct lwtunnel_state *lwtstate); @@ -88,7 +88,7 @@ int lwtunnel_fill_encap(struct sk_buff *skb, int lwtunnel_get_encap_size(struct lwtunnel_state *lwtstate); struct lwtunnel_state *lwtunnel_state_alloc(int hdr_len); int lwtunnel_cmp_encap(struct lwtunnel_state *a, struct lwtunnel_state *b); -int lwtunnel_output(struct sock *sk, struct sk_buff *skb); +int lwtunnel_output(struct net *net, struct sock *sk, struct sk_buff *skb); int lwtunnel_input(struct sk_buff *skb); #else @@ -160,7 +160,7 @@ static inline int lwtunnel_cmp_encap(struct lwtunnel_state *a, return 0; } -static inline int lwtunnel_output(struct sock *sk, struct sk_buff *skb) +static inline int lwtunnel_output(struct net *net, struct sock *sk, struct sk_buff *skb) { return -EOPNOTSUPP; } diff --git a/include/net/xfrm.h b/include/net/xfrm.h index fd176106909a..4a9c21f9b4ea 100644 --- a/include/net/xfrm.h +++ b/include/net/xfrm.h @@ -333,7 +333,7 @@ struct xfrm_state_afinfo { const xfrm_address_t *saddr); int (*tmpl_sort)(struct xfrm_tmpl **dst, struct xfrm_tmpl **src, int n); int (*state_sort)(struct xfrm_state **dst, struct xfrm_state **src, int n); - int (*output)(struct sock *sk, struct sk_buff *skb); + int (*output)(struct net *net, struct sock *sk, struct sk_buff *skb); int (*output_finish)(struct sock *sk, struct sk_buff *skb); int (*extract_input)(struct xfrm_state *x, struct sk_buff *skb); @@ -1527,7 +1527,7 @@ static inline int xfrm4_rcv_spi(struct sk_buff *skb, int nexthdr, __be32 spi) int xfrm4_extract_output(struct xfrm_state *x, struct sk_buff *skb); int xfrm4_prepare_output(struct xfrm_state *x, struct sk_buff *skb); -int xfrm4_output(struct sock *sk, struct sk_buff *skb); +int xfrm4_output(struct net *net, struct sock *sk, struct sk_buff *skb); int xfrm4_output_finish(struct sock *sk, struct sk_buff *skb); int xfrm4_rcv_cb(struct sk_buff *skb, u8 protocol, int err); int xfrm4_protocol_register(struct xfrm4_protocol *handler, unsigned char protocol); @@ -1552,7 +1552,7 @@ __be32 xfrm6_tunnel_alloc_spi(struct net *net, xfrm_address_t *saddr); __be32 xfrm6_tunnel_spi_lookup(struct net *net, const xfrm_address_t *saddr); int xfrm6_extract_output(struct xfrm_state *x, struct sk_buff *skb); int xfrm6_prepare_output(struct xfrm_state *x, struct sk_buff *skb); -int xfrm6_output(struct sock *sk, struct sk_buff *skb); +int xfrm6_output(struct net *net, struct sock *sk, struct sk_buff *skb); int xfrm6_output_finish(struct sock *sk, struct sk_buff *skb); int xfrm6_find_1stfragopt(struct xfrm_state *x, struct sk_buff *skb, u8 **prevhdr); -- cgit v1.2.3 From a1cba5613edf50c2a213fa90c30aa10500b241b7 Mon Sep 17 00:00:00 2001 From: Arun Parameswaran Date: Tue, 6 Oct 2015 12:25:48 -0700 Subject: net: phy: Add Broadcom phy library for common interfaces This patch adds the Broadcom phy library to consolidate common interfaces shared by Broadcom phy's. Moved the common interfaces to the 'bcm-phy-lib.c' and updated the Broadcom PHY drivers to use the new APIs. Signed-off-by: Arun Parameswaran Signed-off-by: David S. Miller --- include/linux/brcmphy.h | 22 +++------------------- 1 file changed, 3 insertions(+), 19 deletions(-) (limited to 'include') diff --git a/include/linux/brcmphy.h b/include/linux/brcmphy.h index 697ca7795bd9..6a53ab91407c 100644 --- a/include/linux/brcmphy.h +++ b/include/linux/brcmphy.h @@ -138,7 +138,10 @@ /* 01010: Auto Power-Down */ #define BCM54XX_SHD_APD 0x0a +#define BCM_APD_CLR_MASK 0xFE9F /* clear bits 5, 6 & 8 */ #define BCM54XX_SHD_APD_EN 0x0020 +#define BCM_NO_ANEG_APD_EN 0x0060 /* bits 5 & 6 */ +#define BCM_APD_SINGLELP_EN 0x0100 /* Bit 8 */ #define BCM5482_SHD_LEDS1 0x0d /* 01101: LED Selector 1 */ /* LED3 / ~LINKSPD[2] selector */ @@ -209,25 +212,6 @@ #define MII_BRCM_FET_SHDW_AUXSTAT2 0x1b /* Auxiliary status 2 */ #define MII_BRCM_FET_SHDW_AS2_APDE 0x0020 /* Auto power down enable */ -/* - * Indirect register access functions for the 1000BASE-T/100BASE-TX/10BASE-T - * 0x1c shadow registers. - */ -static inline int bcm54xx_shadow_read(struct phy_device *phydev, u16 shadow) -{ - phy_write(phydev, MII_BCM54XX_SHD, MII_BCM54XX_SHD_VAL(shadow)); - return MII_BCM54XX_SHD_DATA(phy_read(phydev, MII_BCM54XX_SHD)); -} - -static inline int bcm54xx_shadow_write(struct phy_device *phydev, u16 shadow, - u16 val) -{ - return phy_write(phydev, MII_BCM54XX_SHD, - MII_BCM54XX_SHD_WRITE | - MII_BCM54XX_SHD_VAL(shadow) | - MII_BCM54XX_SHD_DATA(val)); -} - #define BRCM_CL45VEN_EEE_CONTROL 0x803d #define LPI_FEATURE_EN 0x8000 #define LPI_FEATURE_EN_DIG1000X 0x4000 -- cgit v1.2.3 From 8e185d6997bb67068f0ca8f062a50caa2608cf1b Mon Sep 17 00:00:00 2001 From: Arun Parameswaran Date: Tue, 6 Oct 2015 12:25:49 -0700 Subject: net: phy: Broadcom Cygnus internal Etherent PHY driver Add support for the Broadcom Cygnus SoCs internal PHY's. The PHYs are 1000M/100M/10M capable with support for 'EEE' and 'APD' (Auto Power Down). This driver supports the following Broadcom Cygnus SoCs: - BCM583XX (BCM58300, BCM58302, BCM58303, BCM58305) - BCM113XX (BCM11300, BCM11320, BCM11350, BCM11360) The PHY's on these SoC's require some workarounds for stable operation, both during configuration time and during suspend/resume. This driver handles the application of the workarounds. Signed-off-by: Arun Parameswaran Signed-off-by: David S. Miller --- include/linux/brcmphy.h | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'include') diff --git a/include/linux/brcmphy.h b/include/linux/brcmphy.h index 6a53ab91407c..59f4a7304419 100644 --- a/include/linux/brcmphy.h +++ b/include/linux/brcmphy.h @@ -30,6 +30,8 @@ #define PHY_ID_BCM7439_2 0xae025080 #define PHY_ID_BCM7445 0x600d8510 +#define PHY_ID_BCM_CYGNUS 0xae025200 + #define PHY_BCM_OUI_MASK 0xfffffc00 #define PHY_BCM_OUI_1 0x00206000 #define PHY_BCM_OUI_2 0x0143bc00 @@ -216,4 +218,9 @@ #define LPI_FEATURE_EN 0x8000 #define LPI_FEATURE_EN_DIG1000X 0x4000 +/* Core register definitions*/ +#define MII_BRCM_CORE_BASE1E 0x1E +#define MII_BRCM_CORE_EXPB0 0xB0 +#define MII_BRCM_CORE_EXPB1 0xB1 + #endif /* _LINUX_BRCMPHY_H */ -- cgit v1.2.3 From 4d6a6aed22f91b35c14a6717d42953f260090175 Mon Sep 17 00:00:00 2001 From: Alexander Aring Date: Fri, 2 Oct 2015 20:28:04 +0200 Subject: 6lowpan: move shared settings to lowpan_netdev_setup This patch moves values for all lowpan interface to the shared implementation of 6lowpan. This patch also quietly fixes the forgotten IFF_NO_QUEUE flag for the bluetooth 6LoWPAN interface. An identically commit is 4afbc0d ("net: 6lowpan: convert to using IFF_NO_QUEUE") which wasn't changed for bluetooth 6lowpan. All 6lowpan interfaces should be virtual with IFF_NO_QUEUE, using EUI64 address length, the mtu size is 1280 (IPV6_MIN_MTU) and the netdev type is ARPHRD_6LOWPAN. Signed-off-by: Alexander Aring Acked-by: Jukka Rissanen Signed-off-by: Marcel Holtmann --- include/net/6lowpan.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/net/6lowpan.h b/include/net/6lowpan.h index c17f556644fc..07db532696df 100644 --- a/include/net/6lowpan.h +++ b/include/net/6lowpan.h @@ -61,6 +61,8 @@ #define UIP_PROTO_UDP 17 /* ipv6 next header value for UDP */ #define UIP_FRAGH_LEN 8 /* ipv6 fragment header size */ +#define EUI64_ADDR_LEN 8 + #define LOWPAN_NHC_MAX_ID_LEN 1 /* Max IPHC Header len without IPv6 hdr specific inline data. * Useful for getting the "extra" bytes we need at worst case compression. -- cgit v1.2.3 From 46234253b9363894a254844a6550b4cc5f3edfe8 Mon Sep 17 00:00:00 2001 From: Hannes Frederic Sowa Date: Thu, 8 Oct 2015 01:20:35 +0200 Subject: net: move net_get_random_once to lib There's no good reason why users outside of networking should not be using this facility, f.e. for initializing their seeds. Therefore, make it accessible from there as get_random_once(). Signed-off-by: Hannes Frederic Sowa Signed-off-by: Daniel Borkmann Acked-by: Alexei Starovoitov Signed-off-by: David S. Miller --- include/linux/net.h | 21 ++++----------------- include/linux/once.h | 24 ++++++++++++++++++++++++ 2 files changed, 28 insertions(+), 17 deletions(-) create mode 100644 include/linux/once.h (limited to 'include') diff --git a/include/linux/net.h b/include/linux/net.h index 049d4b03c4c4..70ac5e28e6b7 100644 --- a/include/linux/net.h +++ b/include/linux/net.h @@ -24,7 +24,8 @@ #include /* For O_CLOEXEC and O_NONBLOCK */ #include #include -#include +#include + #include struct poll_table_struct; @@ -250,22 +251,8 @@ do { \ } while (0) #endif -bool __net_get_random_once(void *buf, int nbytes, bool *done, - struct static_key *done_key); - -#define net_get_random_once(buf, nbytes) \ - ({ \ - bool ___ret = false; \ - static bool ___done = false; \ - static struct static_key ___once_key = \ - STATIC_KEY_INIT_TRUE; \ - if (static_key_true(&___once_key)) \ - ___ret = __net_get_random_once(buf, \ - nbytes, \ - &___done, \ - &___once_key); \ - ___ret; \ - }) +#define net_get_random_once(buf, nbytes) \ + get_random_once((buf), (nbytes)) int kernel_sendmsg(struct socket *sock, struct msghdr *msg, struct kvec *vec, size_t num, size_t len); diff --git a/include/linux/once.h b/include/linux/once.h new file mode 100644 index 000000000000..2a83b538dd6a --- /dev/null +++ b/include/linux/once.h @@ -0,0 +1,24 @@ +#ifndef _LINUX_ONCE_H +#define _LINUX_ONCE_H + +#include +#include + +bool __get_random_once(void *buf, int nbytes, bool *done, + struct static_key *once_key); + +#define get_random_once(buf, nbytes) \ + ({ \ + bool ___ret = false; \ + static bool ___done = false; \ + static struct static_key ___once_key = \ + STATIC_KEY_INIT_TRUE; \ + if (static_key_true(&___once_key)) \ + ___ret = __get_random_once((buf), \ + (nbytes), \ + &___done, \ + &___once_key); \ + ___ret; \ + }) + +#endif /* _LINUX_ONCE_H */ -- cgit v1.2.3 From c90aeb948222a7b3d3391d232ec4f50fd8322ad3 Mon Sep 17 00:00:00 2001 From: Hannes Frederic Sowa Date: Thu, 8 Oct 2015 01:20:36 +0200 Subject: once: make helper generic for calling functions once Make the get_random_once() helper generic enough, so that functions in general would only be called once, where one user of this is then net_get_random_once(). The only implementation specific call is to get_random_bytes(), all the rest of this *_once() facility would be duplicated among different subsystems otherwise. The new DO_ONCE() helper will be used by prandom() later on, but might also be useful for other scenarios/subsystems as well where a one-time initialization in often-called, possibly fast path code could occur. Signed-off-by: Hannes Frederic Sowa Signed-off-by: Daniel Borkmann Acked-by: Alexei Starovoitov Signed-off-by: David S. Miller --- include/linux/once.h | 61 ++++++++++++++++++++++++++++++++++++++++------------ 1 file changed, 47 insertions(+), 14 deletions(-) (limited to 'include') diff --git a/include/linux/once.h b/include/linux/once.h index 2a83b538dd6a..285f12cb40e6 100644 --- a/include/linux/once.h +++ b/include/linux/once.h @@ -4,21 +4,54 @@ #include #include -bool __get_random_once(void *buf, int nbytes, bool *done, - struct static_key *once_key); +bool __do_once_start(bool *done, unsigned long *flags); +void __do_once_done(bool *done, struct static_key *once_key, + unsigned long *flags); -#define get_random_once(buf, nbytes) \ - ({ \ - bool ___ret = false; \ - static bool ___done = false; \ - static struct static_key ___once_key = \ - STATIC_KEY_INIT_TRUE; \ - if (static_key_true(&___once_key)) \ - ___ret = __get_random_once((buf), \ - (nbytes), \ - &___done, \ - &___once_key); \ - ___ret; \ +/* Call a function exactly once. The idea of DO_ONCE() is to perform + * a function call such as initialization of random seeds, etc, only + * once, where DO_ONCE() can live in the fast-path. After @func has + * been called with the passed arguments, the static key will patch + * out the condition into a nop. DO_ONCE() guarantees type safety of + * arguments! + * + * Not that the following is not equivalent ... + * + * DO_ONCE(func, arg); + * DO_ONCE(func, arg); + * + * ... to this version: + * + * void foo(void) + * { + * DO_ONCE(func, arg); + * } + * + * foo(); + * foo(); + * + * In case the one-time invocation could be triggered from multiple + * places, then a common helper function must be defined, so that only + * a single static key will be placed there! + */ +#define DO_ONCE(func, ...) \ + ({ \ + bool ___ret = false; \ + static bool ___done = false; \ + static struct static_key ___once_key = STATIC_KEY_INIT_TRUE; \ + if (static_key_true(&___once_key)) { \ + unsigned long ___flags; \ + ___ret = __do_once_start(&___done, &___flags); \ + if (unlikely(___ret)) { \ + func(__VA_ARGS__); \ + __do_once_done(&___done, &___once_key, \ + &___flags); \ + } \ + } \ + ___ret; \ }) +#define get_random_once(buf, nbytes) \ + DO_ONCE(get_random_bytes, (buf), (nbytes)) + #endif /* _LINUX_ONCE_H */ -- cgit v1.2.3 From 897ece56e714a2cc64e6914cb89a362d7021b36e Mon Sep 17 00:00:00 2001 From: Daniel Borkmann Date: Thu, 8 Oct 2015 01:20:38 +0200 Subject: random32: add prandom_init_once helper for own rngs Add a prandom_init_once() facility that works on the rnd_state, so that users that are keeping their own state independent from prandom_u32() can initialize their taus113 per cpu states. The motivation here is similar to net_get_random_once(): initialize the state as late as possible in the hope that enough entropy has been collected for the seeding. prandom_init_once() makes use of the recently introduced prandom_seed_full_state() helper and is generic enough so that it could also be used on fast-paths due to the DO_ONCE(). Signed-off-by: Daniel Borkmann Acked-by: Hannes Frederic Sowa Acked-by: Alexei Starovoitov Signed-off-by: David S. Miller --- include/linux/random.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include') diff --git a/include/linux/random.h b/include/linux/random.h index e651874df2c9..a75840c1aa71 100644 --- a/include/linux/random.h +++ b/include/linux/random.h @@ -7,6 +7,8 @@ #define _LINUX_RANDOM_H #include +#include + #include struct random_ready_callback { @@ -45,6 +47,10 @@ struct rnd_state { u32 prandom_u32_state(struct rnd_state *state); void prandom_bytes_state(struct rnd_state *state, void *buf, size_t nbytes); +void prandom_seed_full_state(struct rnd_state __percpu *pcpu_state); + +#define prandom_init_once(pcpu_state) \ + DO_ONCE(prandom_seed_full_state, (pcpu_state)) /** * prandom_u32_max - returns a pseudo-random number in interval [0, ep_ro) -- cgit v1.2.3 From 3ad0040573b0c00f88488bc31958acd07a55ee2e Mon Sep 17 00:00:00 2001 From: Daniel Borkmann Date: Thu, 8 Oct 2015 01:20:39 +0200 Subject: bpf: split state from prandom_u32() and consolidate {c, e}BPF prngs While recently arguing on a seccomp discussion that raw prandom_u32() access shouldn't be exposed to unpriviledged user space, I forgot the fact that SKF_AD_RANDOM extension actually already does it for some time in cBPF via commit 4cd3675ebf74 ("filter: added BPF random opcode"). Since prandom_u32() is being used in a lot of critical networking code, lets be more conservative and split their states. Furthermore, consolidate eBPF and cBPF prandom handlers to use the new internal PRNG. For eBPF, bpf_get_prandom_u32() was only accessible for priviledged users, but should that change one day, we also don't want to leak raw sequences through things like eBPF maps. One thought was also to have own per bpf_prog states, but due to ABI reasons this is not easily possible, i.e. the program code currently cannot access bpf_prog itself, and copying the rnd_state to/from the stack scratch space whenever a program uses the prng seems not really worth the trouble and seems too hacky. If needed, taus113 could in such cases be implemented within eBPF using a map entry to keep the state space, or get_random_bytes() could become a second helper in cases where performance would not be critical. Both sides can trigger a one-time late init via prandom_init_once() on the shared state. Performance-wise, there should even be a tiny gain as bpf_user_rnd_u32() saves one function call. The PRNG needs to live inside the BPF core since kernels could have a NET-less config as well. Signed-off-by: Daniel Borkmann Acked-by: Hannes Frederic Sowa Acked-by: Alexei Starovoitov Cc: Chema Gonzalez Signed-off-by: David S. Miller --- include/linux/bpf.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index c915a6b54570..3697ad563899 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -200,4 +200,8 @@ extern const struct bpf_func_proto bpf_get_current_comm_proto; extern const struct bpf_func_proto bpf_skb_vlan_push_proto; extern const struct bpf_func_proto bpf_skb_vlan_pop_proto; +/* Shared helpers among cBPF and eBPF. */ +void bpf_user_rnd_init_once(void); +u64 bpf_user_rnd_u32(u64 r1, u64 r2, u64 r3, u64 r4, u64 r5); + #endif /* _LINUX_BPF_H */ -- cgit v1.2.3 From 020446e01eebc9dbe7eda038e570ab9c7ab13586 Mon Sep 17 00:00:00 2001 From: Eli Cohen Date: Thu, 8 Oct 2015 17:13:58 +0300 Subject: net/mlx5_core: Prepare cmd interface to system errors handling In preparation to handling system errors at the mlx5_core level, change the interface of cmd_work_handler to accept a 64 bit argument for the vector. This allows to encode a flag that signifies when the handler is called as a result of a driver logic that wishes to terminate commands that the hardware may not be able to terminate. Such command completions are detected at the handler and proper return status is encoded. To be able to terminate page handler commands, we make sure to set the corresponding bit in the bitmask. Signed-off-by: Eli Cohen Signed-off-by: Or Gerlitz Signed-off-by: David S. Miller --- include/linux/mlx5/driver.h | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h index 8b6d6f2154a4..aa899559eec0 100644 --- a/include/linux/mlx5/driver.h +++ b/include/linux/mlx5/driver.h @@ -731,7 +731,7 @@ void mlx5_eq_pagefault(struct mlx5_core_dev *dev, struct mlx5_eqe *eqe); #endif void mlx5_srq_event(struct mlx5_core_dev *dev, u32 srqn, int event_type); struct mlx5_core_srq *mlx5_core_get_srq(struct mlx5_core_dev *dev, u32 srqn); -void mlx5_cmd_comp_handler(struct mlx5_core_dev *dev, unsigned long vector); +void mlx5_cmd_comp_handler(struct mlx5_core_dev *dev, u64 vec); void mlx5_cq_event(struct mlx5_core_dev *dev, u32 cqn, int event_type); int mlx5_create_map_eq(struct mlx5_core_dev *dev, struct mlx5_eq *eq, u8 vecidx, int nent, u64 mask, const char *name, struct mlx5_uar *uar); @@ -865,4 +865,8 @@ static inline int mlx5_get_gid_table_len(u16 param) return 8 * (1 << param); } +enum { + MLX5_TRIGGERED_CMD_COMP = (u64)1 << 32, +}; + #endif /* MLX5_DRIVER_H */ -- cgit v1.2.3 From ac6ea6e81a80172612e0c9ef93720f371b198918 Mon Sep 17 00:00:00 2001 From: Eli Cohen Date: Thu, 8 Oct 2015 17:14:00 +0300 Subject: net/mlx5_core: Use private health thread for each device Use a single threaded work queue for each device in the system instead of using one thread for any device. This is required so we can concurrently process system error handling for all the devices that need that. Signed-off-by: Eli Cohen Signed-off-by: Or Gerlitz Signed-off-by: David S. Miller --- include/linux/mlx5/driver.h | 7 ++++--- 1 file changed, 4 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h index aa899559eec0..41a32873f608 100644 --- a/include/linux/mlx5/driver.h +++ b/include/linux/mlx5/driver.h @@ -391,9 +391,10 @@ struct mlx5_core_health { struct health_buffer __iomem *health; __be32 __iomem *health_counter; struct timer_list timer; - struct list_head list; u32 prev; int miss_counter; + struct workqueue_struct *wq; + struct work_struct work; }; struct mlx5_cq_table { @@ -676,8 +677,8 @@ int mlx5_alloc_uuars(struct mlx5_core_dev *dev, struct mlx5_uuar_info *uuari); int mlx5_free_uuars(struct mlx5_core_dev *dev, struct mlx5_uuar_info *uuari); int mlx5_alloc_map_uar(struct mlx5_core_dev *mdev, struct mlx5_uar *uar); void mlx5_unmap_free_uar(struct mlx5_core_dev *mdev, struct mlx5_uar *uar); -void mlx5_health_cleanup(void); -void __init mlx5_health_init(void); +void mlx5_health_cleanup(struct mlx5_core_dev *dev); +int mlx5_health_init(struct mlx5_core_dev *dev); void mlx5_start_health_poll(struct mlx5_core_dev *dev); void mlx5_stop_health_poll(struct mlx5_core_dev *dev); int mlx5_buf_alloc_node(struct mlx5_core_dev *dev, int size, -- cgit v1.2.3 From 61d03535e4be3a46c1e171a25458237e343195e3 Mon Sep 17 00:00:00 2001 From: Yaowei Bai Date: Thu, 8 Oct 2015 21:28:54 +0800 Subject: net/netlink: lockdep_genl_is_held can be boolean This patch makes lockdep_genl_is_held return bool to improve readability due to this particular function only using either one or zero as its return value. No functional change. Signed-off-by: Yaowei Bai Signed-off-by: David S. Miller --- include/linux/genetlink.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/genetlink.h b/include/linux/genetlink.h index 09460d6d6682..a4c61cbce777 100644 --- a/include/linux/genetlink.h +++ b/include/linux/genetlink.h @@ -8,7 +8,7 @@ extern void genl_lock(void); extern void genl_unlock(void); #ifdef CONFIG_LOCKDEP -extern int lockdep_genl_is_held(void); +extern bool lockdep_genl_is_held(void); #endif /* for synchronisation between af_netlink and genetlink */ -- cgit v1.2.3 From 35498edc6481d588feadee7e76220884d5bbca48 Mon Sep 17 00:00:00 2001 From: Yaowei Bai Date: Thu, 8 Oct 2015 21:28:55 +0800 Subject: net/ieee80211: ieee80211_is_* can be boolean This patch makes ieee80211_is_* return bool to improve readability due to these particular functions only using either one or zero as their return value. No functional change. Signed-off-by: Yaowei Bai Signed-off-by: David S. Miller --- include/linux/ieee80211.h | 76 +++++++++++++++++++++++------------------------ 1 file changed, 38 insertions(+), 38 deletions(-) (limited to 'include') diff --git a/include/linux/ieee80211.h b/include/linux/ieee80211.h index f79a02a69d26..dcfb2f43d316 100644 --- a/include/linux/ieee80211.h +++ b/include/linux/ieee80211.h @@ -121,7 +121,7 @@ #define IEEE80211_MAX_SN IEEE80211_SN_MASK #define IEEE80211_SN_MODULO (IEEE80211_MAX_SN + 1) -static inline int ieee80211_sn_less(u16 sn1, u16 sn2) +static inline bool ieee80211_sn_less(u16 sn1, u16 sn2) { return ((sn1 - sn2) & IEEE80211_SN_MASK) > (IEEE80211_SN_MODULO >> 1); } @@ -250,7 +250,7 @@ struct ieee80211_qos_hdr { * ieee80211_has_tods - check if IEEE80211_FCTL_TODS is set * @fc: frame control bytes in little-endian byteorder */ -static inline int ieee80211_has_tods(__le16 fc) +static inline bool ieee80211_has_tods(__le16 fc) { return (fc & cpu_to_le16(IEEE80211_FCTL_TODS)) != 0; } @@ -259,7 +259,7 @@ static inline int ieee80211_has_tods(__le16 fc) * ieee80211_has_fromds - check if IEEE80211_FCTL_FROMDS is set * @fc: frame control bytes in little-endian byteorder */ -static inline int ieee80211_has_fromds(__le16 fc) +static inline bool ieee80211_has_fromds(__le16 fc) { return (fc & cpu_to_le16(IEEE80211_FCTL_FROMDS)) != 0; } @@ -268,7 +268,7 @@ static inline int ieee80211_has_fromds(__le16 fc) * ieee80211_has_a4 - check if IEEE80211_FCTL_TODS and IEEE80211_FCTL_FROMDS are set * @fc: frame control bytes in little-endian byteorder */ -static inline int ieee80211_has_a4(__le16 fc) +static inline bool ieee80211_has_a4(__le16 fc) { __le16 tmp = cpu_to_le16(IEEE80211_FCTL_TODS | IEEE80211_FCTL_FROMDS); return (fc & tmp) == tmp; @@ -278,7 +278,7 @@ static inline int ieee80211_has_a4(__le16 fc) * ieee80211_has_morefrags - check if IEEE80211_FCTL_MOREFRAGS is set * @fc: frame control bytes in little-endian byteorder */ -static inline int ieee80211_has_morefrags(__le16 fc) +static inline bool ieee80211_has_morefrags(__le16 fc) { return (fc & cpu_to_le16(IEEE80211_FCTL_MOREFRAGS)) != 0; } @@ -287,7 +287,7 @@ static inline int ieee80211_has_morefrags(__le16 fc) * ieee80211_has_retry - check if IEEE80211_FCTL_RETRY is set * @fc: frame control bytes in little-endian byteorder */ -static inline int ieee80211_has_retry(__le16 fc) +static inline bool ieee80211_has_retry(__le16 fc) { return (fc & cpu_to_le16(IEEE80211_FCTL_RETRY)) != 0; } @@ -296,7 +296,7 @@ static inline int ieee80211_has_retry(__le16 fc) * ieee80211_has_pm - check if IEEE80211_FCTL_PM is set * @fc: frame control bytes in little-endian byteorder */ -static inline int ieee80211_has_pm(__le16 fc) +static inline bool ieee80211_has_pm(__le16 fc) { return (fc & cpu_to_le16(IEEE80211_FCTL_PM)) != 0; } @@ -305,7 +305,7 @@ static inline int ieee80211_has_pm(__le16 fc) * ieee80211_has_moredata - check if IEEE80211_FCTL_MOREDATA is set * @fc: frame control bytes in little-endian byteorder */ -static inline int ieee80211_has_moredata(__le16 fc) +static inline bool ieee80211_has_moredata(__le16 fc) { return (fc & cpu_to_le16(IEEE80211_FCTL_MOREDATA)) != 0; } @@ -314,7 +314,7 @@ static inline int ieee80211_has_moredata(__le16 fc) * ieee80211_has_protected - check if IEEE80211_FCTL_PROTECTED is set * @fc: frame control bytes in little-endian byteorder */ -static inline int ieee80211_has_protected(__le16 fc) +static inline bool ieee80211_has_protected(__le16 fc) { return (fc & cpu_to_le16(IEEE80211_FCTL_PROTECTED)) != 0; } @@ -323,7 +323,7 @@ static inline int ieee80211_has_protected(__le16 fc) * ieee80211_has_order - check if IEEE80211_FCTL_ORDER is set * @fc: frame control bytes in little-endian byteorder */ -static inline int ieee80211_has_order(__le16 fc) +static inline bool ieee80211_has_order(__le16 fc) { return (fc & cpu_to_le16(IEEE80211_FCTL_ORDER)) != 0; } @@ -332,7 +332,7 @@ static inline int ieee80211_has_order(__le16 fc) * ieee80211_is_mgmt - check if type is IEEE80211_FTYPE_MGMT * @fc: frame control bytes in little-endian byteorder */ -static inline int ieee80211_is_mgmt(__le16 fc) +static inline bool ieee80211_is_mgmt(__le16 fc) { return (fc & cpu_to_le16(IEEE80211_FCTL_FTYPE)) == cpu_to_le16(IEEE80211_FTYPE_MGMT); @@ -342,7 +342,7 @@ static inline int ieee80211_is_mgmt(__le16 fc) * ieee80211_is_ctl - check if type is IEEE80211_FTYPE_CTL * @fc: frame control bytes in little-endian byteorder */ -static inline int ieee80211_is_ctl(__le16 fc) +static inline bool ieee80211_is_ctl(__le16 fc) { return (fc & cpu_to_le16(IEEE80211_FCTL_FTYPE)) == cpu_to_le16(IEEE80211_FTYPE_CTL); @@ -352,7 +352,7 @@ static inline int ieee80211_is_ctl(__le16 fc) * ieee80211_is_data - check if type is IEEE80211_FTYPE_DATA * @fc: frame control bytes in little-endian byteorder */ -static inline int ieee80211_is_data(__le16 fc) +static inline bool ieee80211_is_data(__le16 fc) { return (fc & cpu_to_le16(IEEE80211_FCTL_FTYPE)) == cpu_to_le16(IEEE80211_FTYPE_DATA); @@ -362,7 +362,7 @@ static inline int ieee80211_is_data(__le16 fc) * ieee80211_is_data_qos - check if type is IEEE80211_FTYPE_DATA and IEEE80211_STYPE_QOS_DATA is set * @fc: frame control bytes in little-endian byteorder */ -static inline int ieee80211_is_data_qos(__le16 fc) +static inline bool ieee80211_is_data_qos(__le16 fc) { /* * mask with QOS_DATA rather than IEEE80211_FCTL_STYPE as we just need @@ -376,7 +376,7 @@ static inline int ieee80211_is_data_qos(__le16 fc) * ieee80211_is_data_present - check if type is IEEE80211_FTYPE_DATA and has data * @fc: frame control bytes in little-endian byteorder */ -static inline int ieee80211_is_data_present(__le16 fc) +static inline bool ieee80211_is_data_present(__le16 fc) { /* * mask with 0x40 and test that that bit is clear to only return true @@ -390,7 +390,7 @@ static inline int ieee80211_is_data_present(__le16 fc) * ieee80211_is_assoc_req - check if IEEE80211_FTYPE_MGMT && IEEE80211_STYPE_ASSOC_REQ * @fc: frame control bytes in little-endian byteorder */ -static inline int ieee80211_is_assoc_req(__le16 fc) +static inline bool ieee80211_is_assoc_req(__le16 fc) { return (fc & cpu_to_le16(IEEE80211_FCTL_FTYPE | IEEE80211_FCTL_STYPE)) == cpu_to_le16(IEEE80211_FTYPE_MGMT | IEEE80211_STYPE_ASSOC_REQ); @@ -400,7 +400,7 @@ static inline int ieee80211_is_assoc_req(__le16 fc) * ieee80211_is_assoc_resp - check if IEEE80211_FTYPE_MGMT && IEEE80211_STYPE_ASSOC_RESP * @fc: frame control bytes in little-endian byteorder */ -static inline int ieee80211_is_assoc_resp(__le16 fc) +static inline bool ieee80211_is_assoc_resp(__le16 fc) { return (fc & cpu_to_le16(IEEE80211_FCTL_FTYPE | IEEE80211_FCTL_STYPE)) == cpu_to_le16(IEEE80211_FTYPE_MGMT | IEEE80211_STYPE_ASSOC_RESP); @@ -410,7 +410,7 @@ static inline int ieee80211_is_assoc_resp(__le16 fc) * ieee80211_is_reassoc_req - check if IEEE80211_FTYPE_MGMT && IEEE80211_STYPE_REASSOC_REQ * @fc: frame control bytes in little-endian byteorder */ -static inline int ieee80211_is_reassoc_req(__le16 fc) +static inline bool ieee80211_is_reassoc_req(__le16 fc) { return (fc & cpu_to_le16(IEEE80211_FCTL_FTYPE | IEEE80211_FCTL_STYPE)) == cpu_to_le16(IEEE80211_FTYPE_MGMT | IEEE80211_STYPE_REASSOC_REQ); @@ -420,7 +420,7 @@ static inline int ieee80211_is_reassoc_req(__le16 fc) * ieee80211_is_reassoc_resp - check if IEEE80211_FTYPE_MGMT && IEEE80211_STYPE_REASSOC_RESP * @fc: frame control bytes in little-endian byteorder */ -static inline int ieee80211_is_reassoc_resp(__le16 fc) +static inline bool ieee80211_is_reassoc_resp(__le16 fc) { return (fc & cpu_to_le16(IEEE80211_FCTL_FTYPE | IEEE80211_FCTL_STYPE)) == cpu_to_le16(IEEE80211_FTYPE_MGMT | IEEE80211_STYPE_REASSOC_RESP); @@ -430,7 +430,7 @@ static inline int ieee80211_is_reassoc_resp(__le16 fc) * ieee80211_is_probe_req - check if IEEE80211_FTYPE_MGMT && IEEE80211_STYPE_PROBE_REQ * @fc: frame control bytes in little-endian byteorder */ -static inline int ieee80211_is_probe_req(__le16 fc) +static inline bool ieee80211_is_probe_req(__le16 fc) { return (fc & cpu_to_le16(IEEE80211_FCTL_FTYPE | IEEE80211_FCTL_STYPE)) == cpu_to_le16(IEEE80211_FTYPE_MGMT | IEEE80211_STYPE_PROBE_REQ); @@ -440,7 +440,7 @@ static inline int ieee80211_is_probe_req(__le16 fc) * ieee80211_is_probe_resp - check if IEEE80211_FTYPE_MGMT && IEEE80211_STYPE_PROBE_RESP * @fc: frame control bytes in little-endian byteorder */ -static inline int ieee80211_is_probe_resp(__le16 fc) +static inline bool ieee80211_is_probe_resp(__le16 fc) { return (fc & cpu_to_le16(IEEE80211_FCTL_FTYPE | IEEE80211_FCTL_STYPE)) == cpu_to_le16(IEEE80211_FTYPE_MGMT | IEEE80211_STYPE_PROBE_RESP); @@ -450,7 +450,7 @@ static inline int ieee80211_is_probe_resp(__le16 fc) * ieee80211_is_beacon - check if IEEE80211_FTYPE_MGMT && IEEE80211_STYPE_BEACON * @fc: frame control bytes in little-endian byteorder */ -static inline int ieee80211_is_beacon(__le16 fc) +static inline bool ieee80211_is_beacon(__le16 fc) { return (fc & cpu_to_le16(IEEE80211_FCTL_FTYPE | IEEE80211_FCTL_STYPE)) == cpu_to_le16(IEEE80211_FTYPE_MGMT | IEEE80211_STYPE_BEACON); @@ -460,7 +460,7 @@ static inline int ieee80211_is_beacon(__le16 fc) * ieee80211_is_atim - check if IEEE80211_FTYPE_MGMT && IEEE80211_STYPE_ATIM * @fc: frame control bytes in little-endian byteorder */ -static inline int ieee80211_is_atim(__le16 fc) +static inline bool ieee80211_is_atim(__le16 fc) { return (fc & cpu_to_le16(IEEE80211_FCTL_FTYPE | IEEE80211_FCTL_STYPE)) == cpu_to_le16(IEEE80211_FTYPE_MGMT | IEEE80211_STYPE_ATIM); @@ -470,7 +470,7 @@ static inline int ieee80211_is_atim(__le16 fc) * ieee80211_is_disassoc - check if IEEE80211_FTYPE_MGMT && IEEE80211_STYPE_DISASSOC * @fc: frame control bytes in little-endian byteorder */ -static inline int ieee80211_is_disassoc(__le16 fc) +static inline bool ieee80211_is_disassoc(__le16 fc) { return (fc & cpu_to_le16(IEEE80211_FCTL_FTYPE | IEEE80211_FCTL_STYPE)) == cpu_to_le16(IEEE80211_FTYPE_MGMT | IEEE80211_STYPE_DISASSOC); @@ -480,7 +480,7 @@ static inline int ieee80211_is_disassoc(__le16 fc) * ieee80211_is_auth - check if IEEE80211_FTYPE_MGMT && IEEE80211_STYPE_AUTH * @fc: frame control bytes in little-endian byteorder */ -static inline int ieee80211_is_auth(__le16 fc) +static inline bool ieee80211_is_auth(__le16 fc) { return (fc & cpu_to_le16(IEEE80211_FCTL_FTYPE | IEEE80211_FCTL_STYPE)) == cpu_to_le16(IEEE80211_FTYPE_MGMT | IEEE80211_STYPE_AUTH); @@ -490,7 +490,7 @@ static inline int ieee80211_is_auth(__le16 fc) * ieee80211_is_deauth - check if IEEE80211_FTYPE_MGMT && IEEE80211_STYPE_DEAUTH * @fc: frame control bytes in little-endian byteorder */ -static inline int ieee80211_is_deauth(__le16 fc) +static inline bool ieee80211_is_deauth(__le16 fc) { return (fc & cpu_to_le16(IEEE80211_FCTL_FTYPE | IEEE80211_FCTL_STYPE)) == cpu_to_le16(IEEE80211_FTYPE_MGMT | IEEE80211_STYPE_DEAUTH); @@ -500,7 +500,7 @@ static inline int ieee80211_is_deauth(__le16 fc) * ieee80211_is_action - check if IEEE80211_FTYPE_MGMT && IEEE80211_STYPE_ACTION * @fc: frame control bytes in little-endian byteorder */ -static inline int ieee80211_is_action(__le16 fc) +static inline bool ieee80211_is_action(__le16 fc) { return (fc & cpu_to_le16(IEEE80211_FCTL_FTYPE | IEEE80211_FCTL_STYPE)) == cpu_to_le16(IEEE80211_FTYPE_MGMT | IEEE80211_STYPE_ACTION); @@ -510,7 +510,7 @@ static inline int ieee80211_is_action(__le16 fc) * ieee80211_is_back_req - check if IEEE80211_FTYPE_CTL && IEEE80211_STYPE_BACK_REQ * @fc: frame control bytes in little-endian byteorder */ -static inline int ieee80211_is_back_req(__le16 fc) +static inline bool ieee80211_is_back_req(__le16 fc) { return (fc & cpu_to_le16(IEEE80211_FCTL_FTYPE | IEEE80211_FCTL_STYPE)) == cpu_to_le16(IEEE80211_FTYPE_CTL | IEEE80211_STYPE_BACK_REQ); @@ -520,7 +520,7 @@ static inline int ieee80211_is_back_req(__le16 fc) * ieee80211_is_back - check if IEEE80211_FTYPE_CTL && IEEE80211_STYPE_BACK * @fc: frame control bytes in little-endian byteorder */ -static inline int ieee80211_is_back(__le16 fc) +static inline bool ieee80211_is_back(__le16 fc) { return (fc & cpu_to_le16(IEEE80211_FCTL_FTYPE | IEEE80211_FCTL_STYPE)) == cpu_to_le16(IEEE80211_FTYPE_CTL | IEEE80211_STYPE_BACK); @@ -530,7 +530,7 @@ static inline int ieee80211_is_back(__le16 fc) * ieee80211_is_pspoll - check if IEEE80211_FTYPE_CTL && IEEE80211_STYPE_PSPOLL * @fc: frame control bytes in little-endian byteorder */ -static inline int ieee80211_is_pspoll(__le16 fc) +static inline bool ieee80211_is_pspoll(__le16 fc) { return (fc & cpu_to_le16(IEEE80211_FCTL_FTYPE | IEEE80211_FCTL_STYPE)) == cpu_to_le16(IEEE80211_FTYPE_CTL | IEEE80211_STYPE_PSPOLL); @@ -540,7 +540,7 @@ static inline int ieee80211_is_pspoll(__le16 fc) * ieee80211_is_rts - check if IEEE80211_FTYPE_CTL && IEEE80211_STYPE_RTS * @fc: frame control bytes in little-endian byteorder */ -static inline int ieee80211_is_rts(__le16 fc) +static inline bool ieee80211_is_rts(__le16 fc) { return (fc & cpu_to_le16(IEEE80211_FCTL_FTYPE | IEEE80211_FCTL_STYPE)) == cpu_to_le16(IEEE80211_FTYPE_CTL | IEEE80211_STYPE_RTS); @@ -550,7 +550,7 @@ static inline int ieee80211_is_rts(__le16 fc) * ieee80211_is_cts - check if IEEE80211_FTYPE_CTL && IEEE80211_STYPE_CTS * @fc: frame control bytes in little-endian byteorder */ -static inline int ieee80211_is_cts(__le16 fc) +static inline bool ieee80211_is_cts(__le16 fc) { return (fc & cpu_to_le16(IEEE80211_FCTL_FTYPE | IEEE80211_FCTL_STYPE)) == cpu_to_le16(IEEE80211_FTYPE_CTL | IEEE80211_STYPE_CTS); @@ -560,7 +560,7 @@ static inline int ieee80211_is_cts(__le16 fc) * ieee80211_is_ack - check if IEEE80211_FTYPE_CTL && IEEE80211_STYPE_ACK * @fc: frame control bytes in little-endian byteorder */ -static inline int ieee80211_is_ack(__le16 fc) +static inline bool ieee80211_is_ack(__le16 fc) { return (fc & cpu_to_le16(IEEE80211_FCTL_FTYPE | IEEE80211_FCTL_STYPE)) == cpu_to_le16(IEEE80211_FTYPE_CTL | IEEE80211_STYPE_ACK); @@ -570,7 +570,7 @@ static inline int ieee80211_is_ack(__le16 fc) * ieee80211_is_cfend - check if IEEE80211_FTYPE_CTL && IEEE80211_STYPE_CFEND * @fc: frame control bytes in little-endian byteorder */ -static inline int ieee80211_is_cfend(__le16 fc) +static inline bool ieee80211_is_cfend(__le16 fc) { return (fc & cpu_to_le16(IEEE80211_FCTL_FTYPE | IEEE80211_FCTL_STYPE)) == cpu_to_le16(IEEE80211_FTYPE_CTL | IEEE80211_STYPE_CFEND); @@ -580,7 +580,7 @@ static inline int ieee80211_is_cfend(__le16 fc) * ieee80211_is_cfendack - check if IEEE80211_FTYPE_CTL && IEEE80211_STYPE_CFENDACK * @fc: frame control bytes in little-endian byteorder */ -static inline int ieee80211_is_cfendack(__le16 fc) +static inline bool ieee80211_is_cfendack(__le16 fc) { return (fc & cpu_to_le16(IEEE80211_FCTL_FTYPE | IEEE80211_FCTL_STYPE)) == cpu_to_le16(IEEE80211_FTYPE_CTL | IEEE80211_STYPE_CFENDACK); @@ -590,7 +590,7 @@ static inline int ieee80211_is_cfendack(__le16 fc) * ieee80211_is_nullfunc - check if frame is a regular (non-QoS) nullfunc frame * @fc: frame control bytes in little-endian byteorder */ -static inline int ieee80211_is_nullfunc(__le16 fc) +static inline bool ieee80211_is_nullfunc(__le16 fc) { return (fc & cpu_to_le16(IEEE80211_FCTL_FTYPE | IEEE80211_FCTL_STYPE)) == cpu_to_le16(IEEE80211_FTYPE_DATA | IEEE80211_STYPE_NULLFUNC); @@ -600,7 +600,7 @@ static inline int ieee80211_is_nullfunc(__le16 fc) * ieee80211_is_qos_nullfunc - check if frame is a QoS nullfunc frame * @fc: frame control bytes in little-endian byteorder */ -static inline int ieee80211_is_qos_nullfunc(__le16 fc) +static inline bool ieee80211_is_qos_nullfunc(__le16 fc) { return (fc & cpu_to_le16(IEEE80211_FCTL_FTYPE | IEEE80211_FCTL_STYPE)) == cpu_to_le16(IEEE80211_FTYPE_DATA | IEEE80211_STYPE_QOS_NULLFUNC); @@ -624,7 +624,7 @@ static inline bool ieee80211_is_bufferable_mmpdu(__le16 fc) * ieee80211_is_first_frag - check if IEEE80211_SCTL_FRAG is not set * @seq_ctrl: frame sequence control bytes in little-endian byteorder */ -static inline int ieee80211_is_first_frag(__le16 seq_ctrl) +static inline bool ieee80211_is_first_frag(__le16 seq_ctrl) { return (seq_ctrl & cpu_to_le16(IEEE80211_SCTL_FRAG)) == 0; } -- cgit v1.2.3 From 875e08294911b3cb8c60416d64d990809421de29 Mon Sep 17 00:00:00 2001 From: Yaowei Bai Date: Thu, 8 Oct 2015 21:28:56 +0800 Subject: net/nfnetlink: lockdep_nfnl_is_held can be boolean This patch makes lockdep_nfnl_is_held return bool to improve readability due to this particular function only using either one or zero as its return value. No functional change. Signed-off-by: Yaowei Bai Signed-off-by: David S. Miller --- include/linux/netfilter/nfnetlink.h | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/include/linux/netfilter/nfnetlink.h b/include/linux/netfilter/nfnetlink.h index e955d4730625..249d1bb01e03 100644 --- a/include/linux/netfilter/nfnetlink.h +++ b/include/linux/netfilter/nfnetlink.h @@ -45,11 +45,11 @@ int nfnetlink_unicast(struct sk_buff *skb, struct net *net, u32 portid, void nfnl_lock(__u8 subsys_id); void nfnl_unlock(__u8 subsys_id); #ifdef CONFIG_PROVE_LOCKING -int lockdep_nfnl_is_held(__u8 subsys_id); +bool lockdep_nfnl_is_held(__u8 subsys_id); #else -static inline int lockdep_nfnl_is_held(__u8 subsys_id) +static inline bool lockdep_nfnl_is_held(__u8 subsys_id) { - return 1; + return true; } #endif /* CONFIG_PROVE_LOCKING */ -- cgit v1.2.3 From d6fbaea5f635216c9861587c4e658086cf3b1b6b Mon Sep 17 00:00:00 2001 From: Yaowei Bai Date: Thu, 8 Oct 2015 21:28:57 +0800 Subject: net/can: can_dropped_invalid_skb can be boolean This patch makes can_dropped_invalid_skb return bool due to this particular function only using either one or zero as its return value. No functional change. Signed-off-by: Yaowei Bai Acked-by: Marc Kleine-Budde Signed-off-by: David S. Miller --- include/linux/can/dev.h | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/include/linux/can/dev.h b/include/linux/can/dev.h index 56dcadd83716..735f9f8c4e43 100644 --- a/include/linux/can/dev.h +++ b/include/linux/can/dev.h @@ -78,7 +78,7 @@ struct can_priv { #define get_canfd_dlc(i) (min_t(__u8, (i), CANFD_MAX_DLC)) /* Drop a given socketbuffer if it does not contain a valid CAN frame. */ -static inline int can_dropped_invalid_skb(struct net_device *dev, +static inline bool can_dropped_invalid_skb(struct net_device *dev, struct sk_buff *skb) { const struct canfd_frame *cfd = (struct canfd_frame *)skb->data; @@ -94,12 +94,12 @@ static inline int can_dropped_invalid_skb(struct net_device *dev, } else goto inval_skb; - return 0; + return false; inval_skb: kfree_skb(skb); dev->stats.tx_dropped++; - return 1; + return true; } static inline bool can_is_canfd_skb(const struct sk_buff *skb) -- cgit v1.2.3 From 0c6119d99bf5df9403a688d267537284e9cc8bcb Mon Sep 17 00:00:00 2001 From: Yaowei Bai Date: Thu, 8 Oct 2015 21:28:58 +0800 Subject: net/dccp: dccp_list_has_service can be boolean This patch makes dccp_list_has_service return bool due to this particular function only using either one or zero as its return value. No functional change. Signed-off-by: Yaowei Bai Signed-off-by: David S. Miller --- include/linux/dccp.h | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/include/linux/dccp.h b/include/linux/dccp.h index 221025423e6c..61d042bbbf60 100644 --- a/include/linux/dccp.h +++ b/include/linux/dccp.h @@ -202,16 +202,16 @@ struct dccp_service_list { #define DCCP_SERVICE_INVALID_VALUE htonl((__u32)-1) #define DCCP_SERVICE_CODE_IS_ABSENT 0 -static inline int dccp_list_has_service(const struct dccp_service_list *sl, +static inline bool dccp_list_has_service(const struct dccp_service_list *sl, const __be32 service) { if (likely(sl != NULL)) { u32 i = sl->dccpsl_nr; while (i--) if (sl->dccpsl_list[i] == service) - return 1; + return true; } - return 0; + return false; } struct dccp_ackvec; -- cgit v1.2.3 From c3225164cf60ccecce2459dcb5813dd798233f2d Mon Sep 17 00:00:00 2001 From: Yaowei Bai Date: Thu, 8 Oct 2015 21:29:00 +0800 Subject: net/inetdevice: inet_ifa_match can be boolean This patch makes inet_ifa_match return bool due to this particular function only using either one or zero as its return value. No functional change. Signed-off-by: Yaowei Bai Signed-off-by: David S. Miller --- include/linux/inetdevice.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/inetdevice.h b/include/linux/inetdevice.h index a4328cea376a..3b0999e0260f 100644 --- a/include/linux/inetdevice.h +++ b/include/linux/inetdevice.h @@ -171,7 +171,7 @@ __be32 inet_confirm_addr(struct net *net, struct in_device *in_dev, __be32 dst, __be32 local, int scope); struct in_ifaddr *inet_ifa_byprefix(struct in_device *in_dev, __be32 prefix, __be32 mask); -static __inline__ int inet_ifa_match(__be32 addr, struct in_ifaddr *ifa) +static __inline__ bool inet_ifa_match(__be32 addr, struct in_ifaddr *ifa) { return !((addr^ifa->ifa_address)&ifa->ifa_mask); } -- cgit v1.2.3 From f06cc7b284f3dfb2c5decbf9fde711b50a530050 Mon Sep 17 00:00:00 2001 From: Yaowei Bai Date: Thu, 8 Oct 2015 21:29:01 +0800 Subject: net/inetdevice: bad_mask can be boolean This patch makes bad_mask return bool due to this particular function only using either one or zero as its return value. No functional change. Signed-off-by: Yaowei Bai Signed-off-by: David S. Miller --- include/linux/inetdevice.h | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) (limited to 'include') diff --git a/include/linux/inetdevice.h b/include/linux/inetdevice.h index 3b0999e0260f..ee971f335a8b 100644 --- a/include/linux/inetdevice.h +++ b/include/linux/inetdevice.h @@ -180,15 +180,15 @@ static __inline__ bool inet_ifa_match(__be32 addr, struct in_ifaddr *ifa) * Check if a mask is acceptable. */ -static __inline__ int bad_mask(__be32 mask, __be32 addr) +static __inline__ bool bad_mask(__be32 mask, __be32 addr) { __u32 hmask; if (addr & (mask = ~mask)) - return 1; + return true; hmask = ntohl(mask); if (hmask & (hmask+1)) - return 1; - return 0; + return true; + return false; } #define for_primary_ifa(in_dev) { struct in_ifaddr *ifa; \ -- cgit v1.2.3 From 0cbf334376d5e82d7a2f5cd234ca4f5d0843f3ea Mon Sep 17 00:00:00 2001 From: Yaowei Bai Date: Thu, 8 Oct 2015 21:29:02 +0800 Subject: net/core: lockdep_rtnl_is_held can be boolean This patch makes lockdep_rtnl_is_held return bool due to this particular function only using either one or zero as its return value. In another patch lockdep_is_held is also made return bool. No functional change. Signed-off-by: Yaowei Bai Signed-off-by: David S. Miller --- include/linux/rtnetlink.h | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/include/linux/rtnetlink.h b/include/linux/rtnetlink.h index 39adaa9529eb..4be5048b1fbe 100644 --- a/include/linux/rtnetlink.h +++ b/include/linux/rtnetlink.h @@ -33,11 +33,11 @@ extern wait_queue_head_t netdev_unregistering_wq; extern struct mutex net_mutex; #ifdef CONFIG_PROVE_LOCKING -extern int lockdep_rtnl_is_held(void); +extern bool lockdep_rtnl_is_held(void); #else -static inline int lockdep_rtnl_is_held(void) +static inline bool lockdep_rtnl_is_held(void) { - return 1; + return true; } #endif /* #ifdef CONFIG_PROVE_LOCKING */ -- cgit v1.2.3 From ff936a04e5f28b7e0455be0e7fa91334f89e4b44 Mon Sep 17 00:00:00 2001 From: Alexei Starovoitov Date: Wed, 7 Oct 2015 10:55:41 -0700 Subject: bpf: fix cb access in socket filter programs eBPF socket filter programs may see junk in 'u32 cb[5]' area, since it could have been used by protocol layers earlier. For socket filter programs used in af_packet we need to clean 20 bytes of skb->cb area if it could be used by the program. For programs attached to TCP/UDP sockets we need to save/restore these 20 bytes, since it's used by protocol layers. Remove SK_RUN_FILTER macro, since it's no longer used. Long term we may move this bpf cb area to per-cpu scratch, but that requires addition of new 'per-cpu load/store' instructions, so not suitable as a short term fix. Fixes: d691f9e8d440 ("bpf: allow programs to write to certain skb fields") Reported-by: Eric Dumazet Signed-off-by: Alexei Starovoitov Signed-off-by: David S. Miller --- include/linux/bpf.h | 6 +++--- include/linux/filter.h | 39 +++++++++++++++++++++++++++++++++++---- 2 files changed, 38 insertions(+), 7 deletions(-) (limited to 'include') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 3697ad563899..b4fdee6cb686 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -100,6 +100,8 @@ enum bpf_access_type { BPF_WRITE = 2 }; +struct bpf_prog; + struct bpf_verifier_ops { /* return eBPF function prototype for verification */ const struct bpf_func_proto *(*get_func_proto)(enum bpf_func_id func_id); @@ -111,7 +113,7 @@ struct bpf_verifier_ops { u32 (*convert_ctx_access)(enum bpf_access_type type, int dst_reg, int src_reg, int ctx_off, - struct bpf_insn *insn); + struct bpf_insn *insn, struct bpf_prog *prog); }; struct bpf_prog_type_list { @@ -120,8 +122,6 @@ struct bpf_prog_type_list { enum bpf_prog_type type; }; -struct bpf_prog; - struct bpf_prog_aux { atomic_t refcnt; u32 used_map_cnt; diff --git a/include/linux/filter.h b/include/linux/filter.h index 1bbce14bcf17..4165e9ac9e36 100644 --- a/include/linux/filter.h +++ b/include/linux/filter.h @@ -13,6 +13,7 @@ #include #include #include +#include #include @@ -302,10 +303,6 @@ struct bpf_prog_aux; bpf_size; \ }) -/* Macro to invoke filter function. */ -#define SK_RUN_FILTER(filter, ctx) \ - (*filter->prog->bpf_func)(ctx, filter->prog->insnsi) - #ifdef CONFIG_COMPAT /* A struct sock_filter is architecture independent. */ struct compat_sock_fprog { @@ -329,6 +326,7 @@ struct bpf_prog { kmemcheck_bitfield_begin(meta); u16 jited:1, /* Is our filter JIT'ed? */ gpl_compatible:1, /* Is filter GPL compatible? */ + cb_access:1, /* Is control block accessed? */ dst_needed:1; /* Do we need dst entry? */ kmemcheck_bitfield_end(meta); u32 len; /* Number of filter blocks */ @@ -352,6 +350,39 @@ struct sk_filter { #define BPF_PROG_RUN(filter, ctx) (*filter->bpf_func)(ctx, filter->insnsi) +static inline u32 bpf_prog_run_save_cb(const struct bpf_prog *prog, + struct sk_buff *skb) +{ + u8 *cb_data = qdisc_skb_cb(skb)->data; + u8 saved_cb[QDISC_CB_PRIV_LEN]; + u32 res; + + BUILD_BUG_ON(FIELD_SIZEOF(struct __sk_buff, cb) != + QDISC_CB_PRIV_LEN); + + if (unlikely(prog->cb_access)) { + memcpy(saved_cb, cb_data, sizeof(saved_cb)); + memset(cb_data, 0, sizeof(saved_cb)); + } + + res = BPF_PROG_RUN(prog, skb); + + if (unlikely(prog->cb_access)) + memcpy(cb_data, saved_cb, sizeof(saved_cb)); + + return res; +} + +static inline u32 bpf_prog_run_clear_cb(const struct bpf_prog *prog, + struct sk_buff *skb) +{ + u8 *cb_data = qdisc_skb_cb(skb)->data; + + if (unlikely(prog->cb_access)) + memset(cb_data, 0, QDISC_CB_PRIV_LEN); + return BPF_PROG_RUN(prog, skb); +} + static inline unsigned int bpf_prog_size(unsigned int proglen) { return max(sizeof(struct bpf_prog), -- cgit v1.2.3 From e446f9dfe17bbaa76a1fe22912636f38be1e1af8 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Thu, 8 Oct 2015 05:01:55 -0700 Subject: net: synack packets can be attached to request sockets selinux needs few changes to accommodate fact that SYNACK messages can be attached to a request socket, lacking sk_security pointer (Only syncookies are still attached to a TCP_LISTEN socket) Adds a new sk_listener() helper, and use it in selinux and sch_fq Fixes: ca6fb0651883 ("tcp: attach SYNACK messages to request sockets instead of listener") Signed-off-by: Eric Dumazet Reported by: kernel test robot Cc: Paul Moore Cc: Stephen Smalley Cc: Eric Paris Acked-by: Paul Moore Signed-off-by: David S. Miller --- include/net/sock.h | 8 ++++++++ 1 file changed, 8 insertions(+) (limited to 'include') diff --git a/include/net/sock.h b/include/net/sock.h index dfe2eb8e1132..771ca1996442 100644 --- a/include/net/sock.h +++ b/include/net/sock.h @@ -2201,6 +2201,14 @@ static inline bool sk_fullsock(const struct sock *sk) return (1 << sk->sk_state) & ~(TCPF_TIME_WAIT | TCPF_NEW_SYN_RECV); } +/* This helper checks if a socket is a LISTEN or NEW_SYN_RECV + * SYNACK messages can be attached to either ones (depending on SYNCOOKIE) + */ +static inline bool sk_listener(const struct sock *sk) +{ + return (1 << sk->sk_state) & (TCPF_LISTEN | TCPF_NEW_SYN_RECV); +} + void sock_enable_timestamp(struct sock *sk, int flag); int sock_get_timestamp(struct sock *, struct timeval __user *); int sock_get_timestampns(struct sock *, struct timespec __user *); -- cgit v1.2.3 From 146a32067b3fde1424d737d7fb333eb0951e6419 Mon Sep 17 00:00:00 2001 From: Vivien Didelot Date: Thu, 8 Oct 2015 11:35:12 -0400 Subject: net: dsa: add port_fdb_prepare Push the prepare phase for FDB operations down to the DSA drivers, with a new port_fdb_prepare function. Currently only mv88e6xxx is affected. Signed-off-by: Vivien Didelot Reviewed-by: Jiri Pirko Signed-off-by: David S. Miller --- include/net/dsa.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include') diff --git a/include/net/dsa.h b/include/net/dsa.h index b34d812bc5d0..4f66f8411583 100644 --- a/include/net/dsa.h +++ b/include/net/dsa.h @@ -197,6 +197,9 @@ static inline u8 dsa_upstream_port(struct dsa_switch *ds) return ds->pd->rtable[dst->cpu_switch]; } +struct switchdev_trans; +struct switchdev_obj_port_fdb; + struct dsa_switch_driver { struct list_head list; @@ -316,6 +319,9 @@ struct dsa_switch_driver { /* * Forwarding database */ + int (*port_fdb_prepare)(struct dsa_switch *ds, int port, + const struct switchdev_obj_port_fdb *fdb, + struct switchdev_trans *trans); int (*port_fdb_add)(struct dsa_switch *ds, int port, const unsigned char *addr, u16 vid); int (*port_fdb_del)(struct dsa_switch *ds, int port, -- cgit v1.2.3 From 1f36faf26943f5f5fc1d1a7be6ce252d2ff25e1a Mon Sep 17 00:00:00 2001 From: Vivien Didelot Date: Thu, 8 Oct 2015 11:35:13 -0400 Subject: net: dsa: push prepare phase in port_fdb_add Now that the prepare phase is pushed down to the DSA drivers, propagate it to the port_fdb_add function. Signed-off-by: Vivien Didelot Reviewed-by: Jiri Pirko Signed-off-by: David S. Miller --- include/net/dsa.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/net/dsa.h b/include/net/dsa.h index 4f66f8411583..ce8f9b748a77 100644 --- a/include/net/dsa.h +++ b/include/net/dsa.h @@ -323,7 +323,8 @@ struct dsa_switch_driver { const struct switchdev_obj_port_fdb *fdb, struct switchdev_trans *trans); int (*port_fdb_add)(struct dsa_switch *ds, int port, - const unsigned char *addr, u16 vid); + const struct switchdev_obj_port_fdb *fdb, + struct switchdev_trans *trans); int (*port_fdb_del)(struct dsa_switch *ds, int port, const unsigned char *addr, u16 vid); int (*port_fdb_getnext)(struct dsa_switch *ds, int port, -- cgit v1.2.3 From 8057b3e7a1cfb4da61717ba609e1ea642bb82f9b Mon Sep 17 00:00:00 2001 From: Vivien Didelot Date: Thu, 8 Oct 2015 11:35:14 -0400 Subject: net: dsa: use switchdev obj in port_fdb_del For consistency with the FDB add operation, propagate the switchdev_obj_port_fdb structure in the DSA drivers. Signed-off-by: Vivien Didelot Reviewed-by: Jiri Pirko Signed-off-by: David S. Miller --- include/net/dsa.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/net/dsa.h b/include/net/dsa.h index ce8f9b748a77..e00588625bc2 100644 --- a/include/net/dsa.h +++ b/include/net/dsa.h @@ -326,7 +326,7 @@ struct dsa_switch_driver { const struct switchdev_obj_port_fdb *fdb, struct switchdev_trans *trans); int (*port_fdb_del)(struct dsa_switch *ds, int port, - const unsigned char *addr, u16 vid); + const struct switchdev_obj_port_fdb *fdb); int (*port_fdb_getnext)(struct dsa_switch *ds, int port, unsigned char *addr, u16 *vid, bool *is_static); -- cgit v1.2.3 From f55ac58ae64cbb0315382e738681fe31837dcac0 Mon Sep 17 00:00:00 2001 From: Scott Feldman Date: Thu, 8 Oct 2015 19:23:17 -0700 Subject: switchdev: add bridge ageing_time attribute Setting the stage to push bridge-level attributes down to port driver so hardware can be programmed accordingly. Bridge-level attribute example is ageing_time. This is a per-bridge attribute, not a per-bridge-port attr. Signed-off-by: Scott Feldman Acked-by: Jiri Pirko Signed-off-by: David S. Miller --- include/net/switchdev.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/net/switchdev.h b/include/net/switchdev.h index 89266a3e473d..61f129bd74b2 100644 --- a/include/net/switchdev.h +++ b/include/net/switchdev.h @@ -43,6 +43,7 @@ enum switchdev_attr_id { SWITCHDEV_ATTR_ID_PORT_PARENT_ID, SWITCHDEV_ATTR_ID_PORT_STP_STATE, SWITCHDEV_ATTR_ID_PORT_BRIDGE_FLAGS, + SWITCHDEV_ATTR_ID_BRIDGE_AGEING_TIME, }; struct switchdev_attr { @@ -52,6 +53,7 @@ struct switchdev_attr { struct netdev_phys_item_id ppid; /* PORT_PARENT_ID */ u8 stp_state; /* PORT_STP_STATE */ unsigned long brport_flags; /* PORT_BRIDGE_FLAGS */ + u32 ageing_time; /* BRIDGE_AGEING_TIME */ } u; }; -- cgit v1.2.3 From 464314ea6c119ebc22ee78453e63814453c31611 Mon Sep 17 00:00:00 2001 From: Scott Feldman Date: Thu, 8 Oct 2015 19:23:18 -0700 Subject: switchdev: skip over ports returning -EOPNOTSUPP when recursing ports This allows us to recurse over all the ports, skipping over unsupporting ports. Without the change, the recursion would stop at first unsupported port. Signed-off-by: Scott Feldman Acked-by: Jiri Pirko Signed-off-by: David S. Miller --- include/net/switchdev.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/net/switchdev.h b/include/net/switchdev.h index 61f129bd74b2..1ce70830357d 100644 --- a/include/net/switchdev.h +++ b/include/net/switchdev.h @@ -16,6 +16,7 @@ #include #define SWITCHDEV_F_NO_RECURSE BIT(0) +#define SWITCHDEV_F_SKIP_EOPNOTSUPP BIT(1) struct switchdev_trans_item { struct list_head list; -- cgit v1.2.3 From ae2d708ed8fb8fa713fdd7eacea5df40bae6315b Mon Sep 17 00:00:00 2001 From: Pablo Neira Ayuso Date: Mon, 5 Oct 2015 16:51:01 +0200 Subject: netfilter: conntrack: fix crash on timeout object removal The object and module refcounts are updated for each conntrack template, however, if we delete the iptables rules and we flush the timeout database, we may end up with invalid references to timeout object that are just gone. Resolve this problem by setting the timeout reference to NULL when the custom timeout entry is removed from our base. This patch requires some RCU trickery to ensure safe pointer handling. This handling is similar to what we already do with conntrack helpers, the idea is to avoid bumping the timeout object reference counter from the packet path to avoid the cost of atomic ops. Reported-by: Stephen Hemminger Signed-off-by: Pablo Neira Ayuso --- include/net/netfilter/nf_conntrack_timeout.h | 25 +++++++++++++++++++------ 1 file changed, 19 insertions(+), 6 deletions(-) (limited to 'include') diff --git a/include/net/netfilter/nf_conntrack_timeout.h b/include/net/netfilter/nf_conntrack_timeout.h index 62308713dd7f..f72be38860a7 100644 --- a/include/net/netfilter/nf_conntrack_timeout.h +++ b/include/net/netfilter/nf_conntrack_timeout.h @@ -20,10 +20,20 @@ struct ctnl_timeout { }; struct nf_conn_timeout { - struct ctnl_timeout *timeout; + struct ctnl_timeout __rcu *timeout; }; -#define NF_CT_TIMEOUT_EXT_DATA(__t) (unsigned int *) &((__t)->timeout->data) +static inline unsigned int * +nf_ct_timeout_data(struct nf_conn_timeout *t) +{ + struct ctnl_timeout *timeout; + + timeout = rcu_dereference(t->timeout); + if (timeout == NULL) + return NULL; + + return (unsigned int *)timeout->data; +} static inline struct nf_conn_timeout *nf_ct_timeout_find(const struct nf_conn *ct) @@ -47,7 +57,7 @@ struct nf_conn_timeout *nf_ct_timeout_ext_add(struct nf_conn *ct, if (timeout_ext == NULL) return NULL; - timeout_ext->timeout = timeout; + rcu_assign_pointer(timeout_ext->timeout, timeout); return timeout_ext; #else @@ -64,10 +74,13 @@ nf_ct_timeout_lookup(struct net *net, struct nf_conn *ct, unsigned int *timeouts; timeout_ext = nf_ct_timeout_find(ct); - if (timeout_ext) - timeouts = NF_CT_TIMEOUT_EXT_DATA(timeout_ext); - else + if (timeout_ext) { + timeouts = nf_ct_timeout_data(timeout_ext); + if (unlikely(!timeouts)) + timeouts = l4proto->get_timeouts(net); + } else { timeouts = l4proto->get_timeouts(net); + } return timeouts; #else -- cgit v1.2.3 From 1be7f75d1668d6296b80bf35dcf6762393530afc Mon Sep 17 00:00:00 2001 From: Alexei Starovoitov Date: Wed, 7 Oct 2015 22:23:21 -0700 Subject: bpf: enable non-root eBPF programs In order to let unprivileged users load and execute eBPF programs teach verifier to prevent pointer leaks. Verifier will prevent - any arithmetic on pointers (except R10+Imm which is used to compute stack addresses) - comparison of pointers (except if (map_value_ptr == 0) ... ) - passing pointers to helper functions - indirectly passing pointers in stack to helper functions - returning pointer from bpf program - storing pointers into ctx or maps Spill/fill of pointers into stack is allowed, but mangling of pointers stored in the stack or reading them byte by byte is not. Within bpf programs the pointers do exist, since programs need to be able to access maps, pass skb pointer to LD_ABS insns, etc but programs cannot pass such pointer values to the outside or obfuscate them. Only allow BPF_PROG_TYPE_SOCKET_FILTER unprivileged programs, so that socket filters (tcpdump), af_packet (quic acceleration) and future kcm can use it. tracing and tc cls/act program types still require root permissions, since tracing actually needs to be able to see all kernel pointers and tc is for root only. For example, the following unprivileged socket filter program is allowed: int bpf_prog1(struct __sk_buff *skb) { u32 index = load_byte(skb, ETH_HLEN + offsetof(struct iphdr, protocol)); u64 *value = bpf_map_lookup_elem(&my_map, &index); if (value) *value += skb->len; return 0; } but the following program is not: int bpf_prog1(struct __sk_buff *skb) { u32 index = load_byte(skb, ETH_HLEN + offsetof(struct iphdr, protocol)); u64 *value = bpf_map_lookup_elem(&my_map, &index); if (value) *value += (u64) skb; return 0; } since it would leak the kernel address into the map. Unprivileged socket filter bpf programs have access to the following helper functions: - map lookup/update/delete (but they cannot store kernel pointers into them) - get_random (it's already exposed to unprivileged user space) - get_smp_processor_id - tail_call into another socket filter program - ktime_get_ns The feature is controlled by sysctl kernel.unprivileged_bpf_disabled. This toggle defaults to off (0), but can be set true (1). Once true, bpf programs and maps cannot be accessed from unprivileged process, and the toggle cannot be set back to false. Signed-off-by: Alexei Starovoitov Reviewed-by: Kees Cook Signed-off-by: David S. Miller --- include/linux/bpf.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index b4fdee6cb686..02fa3db3c1ec 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -167,6 +167,8 @@ void bpf_prog_put_rcu(struct bpf_prog *prog); struct bpf_map *bpf_map_get(struct fd f); void bpf_map_put(struct bpf_map *map); +extern int sysctl_unprivileged_bpf_disabled; + /* verify correctness of eBPF program */ int bpf_check(struct bpf_prog **fp, union bpf_attr *attr); #else -- cgit v1.2.3 From aaac3ba95e4c8b496d22f68bd1bc01cfbf525eca Mon Sep 17 00:00:00 2001 From: Alexei Starovoitov Date: Wed, 7 Oct 2015 22:23:22 -0700 Subject: bpf: charge user for creation of BPF maps and programs since eBPF programs and maps use kernel memory consider it 'locked' memory from user accounting point of view and charge it against RLIMIT_MEMLOCK limit. This limit is typically set to 64Kbytes by distros, so almost all bpf+tracing programs would need to increase it, since they use maps, but kernel charges maximum map size upfront. For example the hash map of 1024 elements will be charged as 64Kbyte. It's inconvenient for current users and changes current behavior for root, but probably worth doing to be consistent root vs non-root. Similar accounting logic is done by mmap of perf_event. Signed-off-by: Alexei Starovoitov Signed-off-by: David S. Miller --- include/linux/bpf.h | 3 +++ include/linux/sched.h | 2 +- 2 files changed, 4 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 02fa3db3c1ec..e3a51b74e275 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -36,6 +36,8 @@ struct bpf_map { u32 key_size; u32 value_size; u32 max_entries; + u32 pages; + struct user_struct *user; const struct bpf_map_ops *ops; struct work_struct work; }; @@ -128,6 +130,7 @@ struct bpf_prog_aux { const struct bpf_verifier_ops *ops; struct bpf_map **used_maps; struct bpf_prog *prog; + struct user_struct *user; union { struct work_struct work; struct rcu_head rcu; diff --git a/include/linux/sched.h b/include/linux/sched.h index b7b9501b41af..4817df5fffae 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -840,7 +840,7 @@ struct user_struct { struct hlist_node uidhash_node; kuid_t uid; -#ifdef CONFIG_PERF_EVENTS +#if defined(CONFIG_PERF_EVENTS) || defined(CONFIG_BPF_SYSCALL) atomic_long_t locked_vm; #endif }; -- cgit v1.2.3 From f28ea365cdefc3b4fd0373e70b0106a0cd9b4c23 Mon Sep 17 00:00:00 2001 From: Edward Jee Date: Thu, 8 Oct 2015 14:56:48 -0700 Subject: sock: support per-packet fwmark It's useful to allow users to set fwmark for an individual packet, without changing the socket state. The function this patch adds in sock layer can be used by the protocols that need such a feature. Signed-off-by: Edward Hyunkoo Jee Signed-off-by: Eric Dumazet Cc: Willem de Bruijn Signed-off-by: David S. Miller --- include/net/sock.h | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'include') diff --git a/include/net/sock.h b/include/net/sock.h index 771ca1996442..9322cafd191b 100644 --- a/include/net/sock.h +++ b/include/net/sock.h @@ -1514,6 +1514,13 @@ void sock_kfree_s(struct sock *sk, void *mem, int size); void sock_kzfree_s(struct sock *sk, void *mem, int size); void sk_send_sigurg(struct sock *sk); +struct sockcm_cookie { + u32 mark; +}; + +int sock_cmsg_send(struct sock *sk, struct msghdr *msg, + struct sockcm_cookie *sockc); + /* * Functions to fill in entries in struct proto_ops when a protocol * does not implement a particular function. -- cgit v1.2.3 From 70da268b569d32a9fddeea85dc18043de9d89f89 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Thu, 8 Oct 2015 19:33:21 -0700 Subject: net: SO_INCOMING_CPU setsockopt() support SO_INCOMING_CPU as added in commit 2c8c56e15df3 was a getsockopt() command to fetch incoming cpu handling a particular TCP flow after accept() This commits adds setsockopt() support and extends SO_REUSEPORT selection logic : If a TCP listener or UDP socket has this option set, a packet is delivered to this socket only if CPU handling the packet matches the specified one. This allows to build very efficient TCP servers, using one listener per RX queue, as the associated TCP listener should only accept flows handled in softirq by the same cpu. This provides optimal NUMA behavior and keep cpu caches hot. Note that __inet_lookup_listener() still has to iterate over the list of all listeners. Following patch puts sk_refcnt in a different cache line to let this iteration hit only shared and read mostly cache lines. Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- include/net/sock.h | 10 ++++------ 1 file changed, 4 insertions(+), 6 deletions(-) (limited to 'include') diff --git a/include/net/sock.h b/include/net/sock.h index 9322cafd191b..cf54739f30d5 100644 --- a/include/net/sock.h +++ b/include/net/sock.h @@ -150,6 +150,7 @@ typedef __u64 __bitwise __addrpair; * @skc_node: main hash linkage for various protocol lookup tables * @skc_nulls_node: main hash linkage for TCP/UDP/UDP-Lite protocol * @skc_tx_queue_mapping: tx queue number for this connection + * @skc_incoming_cpu: record/match cpu processing incoming packets * @skc_refcnt: reference count * * This is the minimal network layer representation of sockets, the header @@ -212,6 +213,8 @@ struct sock_common { struct hlist_nulls_node skc_nulls_node; }; int skc_tx_queue_mapping; + int skc_incoming_cpu; + atomic_t skc_refcnt; /* private: */ int skc_dontcopy_end[0]; @@ -274,7 +277,6 @@ struct cg_proto; * @sk_rcvtimeo: %SO_RCVTIMEO setting * @sk_sndtimeo: %SO_SNDTIMEO setting * @sk_rxhash: flow hash received from netif layer - * @sk_incoming_cpu: record cpu processing incoming packets * @sk_txhash: computed flow hash for use on transmit * @sk_filter: socket filtering instructions * @sk_timer: sock cleanup timer @@ -331,6 +333,7 @@ struct sock { #define sk_v6_daddr __sk_common.skc_v6_daddr #define sk_v6_rcv_saddr __sk_common.skc_v6_rcv_saddr #define sk_cookie __sk_common.skc_cookie +#define sk_incoming_cpu __sk_common.skc_incoming_cpu socket_lock_t sk_lock; struct sk_buff_head sk_receive_queue; @@ -353,11 +356,6 @@ struct sock { #ifdef CONFIG_RPS __u32 sk_rxhash; #endif - u16 sk_incoming_cpu; - /* 16bit hole - * Warned : sk_incoming_cpu can be set from softirq, - * Do not use this hole without fully understanding possible issues. - */ __u32 sk_txhash; #ifdef CONFIG_NET_RX_BUSY_POLL -- cgit v1.2.3 From 8e5eb54d303b7cb1174977ca79030e135728c95e Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Thu, 8 Oct 2015 19:33:22 -0700 Subject: net: align sk_refcnt on 128 bytes boundary sk->sk_refcnt is dirtied for every TCP/UDP incoming packet. This is a performance issue if multiple cpus hit a common socket, or multiple sockets are chained due to SO_REUSEPORT. By moving sk_refcnt 8 bytes further, first 128 bytes of sockets are mostly read. As they contain the lookup keys, this has a considerable performance impact, as cpus can cache them. These 8 bytes are not wasted, we use them as a place holder for various fields, depending on the socket type. Tested: SYN flood hitting a 16 RX queues NIC. TCP listener using 16 sockets and SO_REUSEPORT and SO_INCOMING_CPU for proper siloing. Could process 6.0 Mpps SYN instead of 4.2 Mpps Kernel profile looked like : 11.68% [kernel] [k] sha_transform 6.51% [kernel] [k] __inet_lookup_listener 5.07% [kernel] [k] __inet_lookup_established 4.15% [kernel] [k] memcpy_erms 3.46% [kernel] [k] ipt_do_table 2.74% [kernel] [k] fib_table_lookup 2.54% [kernel] [k] tcp_make_synack 2.34% [kernel] [k] tcp_conn_request 2.05% [kernel] [k] __netif_receive_skb_core 2.03% [kernel] [k] kmem_cache_alloc Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- include/net/inet_timewait_sock.h | 2 +- include/net/request_sock.h | 2 +- include/net/sock.h | 17 ++++++++++++++--- 3 files changed, 16 insertions(+), 5 deletions(-) (limited to 'include') diff --git a/include/net/inet_timewait_sock.h b/include/net/inet_timewait_sock.h index 186f3a1e1b1f..e581fc69129d 100644 --- a/include/net/inet_timewait_sock.h +++ b/include/net/inet_timewait_sock.h @@ -70,6 +70,7 @@ struct inet_timewait_sock { #define tw_dport __tw_common.skc_dport #define tw_num __tw_common.skc_num #define tw_cookie __tw_common.skc_cookie +#define tw_dr __tw_common.skc_tw_dr int tw_timeout; volatile unsigned char tw_substate; @@ -88,7 +89,6 @@ struct inet_timewait_sock { kmemcheck_bitfield_end(flags); struct timer_list tw_timer; struct inet_bind_bucket *tw_tb; - struct inet_timewait_death_row *tw_dr; }; #define tw_tclass tw_tos diff --git a/include/net/request_sock.h b/include/net/request_sock.h index 95ab5d7aab96..6b818b77d5e5 100644 --- a/include/net/request_sock.h +++ b/include/net/request_sock.h @@ -50,9 +50,9 @@ struct request_sock { struct sock_common __req_common; #define rsk_refcnt __req_common.skc_refcnt #define rsk_hash __req_common.skc_hash +#define rsk_listener __req_common.skc_listener struct request_sock *dl_next; - struct sock *rsk_listener; u16 mss; u8 num_retrans; /* number of retransmits */ u8 cookie_ts:1; /* syncookie: encode tcpopts in timestamp */ diff --git a/include/net/sock.h b/include/net/sock.h index cf54739f30d5..65712409464b 100644 --- a/include/net/sock.h +++ b/include/net/sock.h @@ -150,6 +150,9 @@ typedef __u64 __bitwise __addrpair; * @skc_node: main hash linkage for various protocol lookup tables * @skc_nulls_node: main hash linkage for TCP/UDP/UDP-Lite protocol * @skc_tx_queue_mapping: tx queue number for this connection + * @skc_flags: place holder for sk_flags + * %SO_LINGER (l_onoff), %SO_BROADCAST, %SO_KEEPALIVE, + * %SO_OOBINLINE settings, %SO_TIMESTAMPING settings * @skc_incoming_cpu: record/match cpu processing incoming packets * @skc_refcnt: reference count * @@ -201,6 +204,16 @@ struct sock_common { atomic64_t skc_cookie; + /* following fields are padding to force + * offset(struct sock, sk_refcnt) == 128 on 64bit arches + * assuming IPV6 is enabled. We use this padding differently + * for different kind of 'sockets' + */ + union { + unsigned long skc_flags; + struct sock *skc_listener; /* request_sock */ + struct inet_timewait_death_row *skc_tw_dr; /* inet_timewait_sock */ + }; /* * fields between dontcopy_begin/dontcopy_end * are not copied in sock_copy() @@ -246,8 +259,6 @@ struct cg_proto; * @sk_pacing_rate: Pacing rate (if supported by transport/packet scheduler) * @sk_max_pacing_rate: Maximum pacing rate (%SO_MAX_PACING_RATE) * @sk_sndbuf: size of send buffer in bytes - * @sk_flags: %SO_LINGER (l_onoff), %SO_BROADCAST, %SO_KEEPALIVE, - * %SO_OOBINLINE settings, %SO_TIMESTAMPING settings * @sk_no_check_tx: %SO_NO_CHECK setting, set checksum in TX packets * @sk_no_check_rx: allow zero checksum in RX packets * @sk_route_caps: route capabilities (e.g. %NETIF_F_TSO) @@ -334,6 +345,7 @@ struct sock { #define sk_v6_rcv_saddr __sk_common.skc_v6_rcv_saddr #define sk_cookie __sk_common.skc_cookie #define sk_incoming_cpu __sk_common.skc_incoming_cpu +#define sk_flags __sk_common.skc_flags socket_lock_t sk_lock; struct sk_buff_head sk_receive_queue; @@ -371,7 +383,6 @@ struct sock { #ifdef CONFIG_XFRM struct xfrm_policy *sk_policy[2]; #endif - unsigned long sk_flags; struct dst_entry *sk_rx_dst; struct dst_entry __rcu *sk_dst_cache; spinlock_t sk_dst_lock; -- cgit v1.2.3 From ed53d0ab761f5c71d77c8dc05fd19c0a851200db Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Thu, 8 Oct 2015 19:33:23 -0700 Subject: net: shrink struct sock and request_sock by 8 bytes One 32bit hole is following skc_refcnt, use it. skc_incoming_cpu can also be an union for request_sock rcv_wnd. Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- include/net/request_sock.h | 5 ++--- include/net/sock.h | 14 +++++++++----- 2 files changed, 11 insertions(+), 8 deletions(-) (limited to 'include') diff --git a/include/net/request_sock.h b/include/net/request_sock.h index 6b818b77d5e5..2e73748956d5 100644 --- a/include/net/request_sock.h +++ b/include/net/request_sock.h @@ -51,15 +51,14 @@ struct request_sock { #define rsk_refcnt __req_common.skc_refcnt #define rsk_hash __req_common.skc_hash #define rsk_listener __req_common.skc_listener +#define rsk_window_clamp __req_common.skc_window_clamp +#define rsk_rcv_wnd __req_common.skc_rcv_wnd struct request_sock *dl_next; u16 mss; u8 num_retrans; /* number of retransmits */ u8 cookie_ts:1; /* syncookie: encode tcpopts in timestamp */ u8 num_timeout:7; /* number of timeouts */ - /* The following two fields can be easily recomputed I think -AK */ - u32 window_clamp; /* window clamp at creation time */ - u32 rcv_wnd; /* rcv_wnd offered first time */ u32 ts_recent; struct timer_list rsk_timer; const struct request_sock_ops *rsk_ops; diff --git a/include/net/sock.h b/include/net/sock.h index 65712409464b..19cfe1fc911c 100644 --- a/include/net/sock.h +++ b/include/net/sock.h @@ -226,11 +226,18 @@ struct sock_common { struct hlist_nulls_node skc_nulls_node; }; int skc_tx_queue_mapping; - int skc_incoming_cpu; + union { + int skc_incoming_cpu; + u32 skc_rcv_wnd; + }; atomic_t skc_refcnt; /* private: */ int skc_dontcopy_end[0]; + union { + u32 skc_rxhash; + u32 skc_window_clamp; + }; /* public: */ }; @@ -287,7 +294,6 @@ struct cg_proto; * @sk_rcvlowat: %SO_RCVLOWAT setting * @sk_rcvtimeo: %SO_RCVTIMEO setting * @sk_sndtimeo: %SO_SNDTIMEO setting - * @sk_rxhash: flow hash received from netif layer * @sk_txhash: computed flow hash for use on transmit * @sk_filter: socket filtering instructions * @sk_timer: sock cleanup timer @@ -346,6 +352,7 @@ struct sock { #define sk_cookie __sk_common.skc_cookie #define sk_incoming_cpu __sk_common.skc_incoming_cpu #define sk_flags __sk_common.skc_flags +#define sk_rxhash __sk_common.skc_rxhash socket_lock_t sk_lock; struct sk_buff_head sk_receive_queue; @@ -365,9 +372,6 @@ struct sock { } sk_backlog; #define sk_rmem_alloc sk_backlog.rmem_alloc int sk_forward_alloc; -#ifdef CONFIG_RPS - __u32 sk_rxhash; -#endif __u32 sk_txhash; #ifdef CONFIG_NET_RX_BUSY_POLL -- cgit v1.2.3 From d475f090bf1c0dc2999e98bbf2e7cb2243358849 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Thu, 8 Oct 2015 19:33:24 -0700 Subject: tcp: shrink tcp_timewait_sock by 8 bytes Reducing tcp_timewait_sock from 280 bytes to 272 bytes allows SLAB to pack 15 objects per page instead of 14 (on x86) Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- include/linux/tcp.h | 4 ++-- include/net/sock.h | 2 ++ 2 files changed, 4 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/tcp.h b/include/linux/tcp.h index e442e6e9a365..86a7edaa6797 100644 --- a/include/linux/tcp.h +++ b/include/linux/tcp.h @@ -356,8 +356,8 @@ static inline struct tcp_sock *tcp_sk(const struct sock *sk) struct tcp_timewait_sock { struct inet_timewait_sock tw_sk; - u32 tw_rcv_nxt; - u32 tw_snd_nxt; +#define tw_rcv_nxt tw_sk.__tw_common.skc_tw_rcv_nxt +#define tw_snd_nxt tw_sk.__tw_common.skc_tw_snd_nxt u32 tw_rcv_wnd; u32 tw_ts_offset; u32 tw_ts_recent; diff --git a/include/net/sock.h b/include/net/sock.h index 19cfe1fc911c..64a75458d22c 100644 --- a/include/net/sock.h +++ b/include/net/sock.h @@ -229,6 +229,7 @@ struct sock_common { union { int skc_incoming_cpu; u32 skc_rcv_wnd; + u32 skc_tw_rcv_nxt; /* struct tcp_timewait_sock */ }; atomic_t skc_refcnt; @@ -237,6 +238,7 @@ struct sock_common { union { u32 skc_rxhash; u32 skc_window_clamp; + u32 skc_tw_snd_nxt; /* struct tcp_timewait_sock */ }; /* public: */ }; -- cgit v1.2.3 From e2ca690b657f4ca5c204fcc6470d462b776d73b3 Mon Sep 17 00:00:00 2001 From: Paolo Abeni Date: Fri, 9 Oct 2015 14:34:31 +0200 Subject: ipv4/icmp: redirect messages can use the ingress daddr as source This patch allows configuring how the source address of ICMP redirect messages is selected; by default the old behaviour is retained, while setting icmp_redirects_use_orig_daddr force the usage of the destination address of the packet that caused the redirect. The new behaviour fits closely the RFC 5798 section 8.1.1, and fix the following scenario: Two machines are set up with VRRP to act as routers out of a subnet, they have IPs x.x.x.1/24 and x.x.x.2/24, with VRRP holding on to x.x.x.254/24. If a host in said subnet needs to get an ICMP redirect from the VRRP router, i.e. to reach a destination behind a different gateway, the source IP in the ICMP redirect is chosen as the primary IP on the interface that the packet arrived at, i.e. x.x.x.1 or x.x.x.2. The host will then ignore said redirect, due to RFC 1122 section 3.2.2.2, and will continue to use the wrong next-op. Signed-off-by: Paolo Abeni Signed-off-by: David S. Miller --- include/net/netns/ipv4.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/net/netns/ipv4.h b/include/net/netns/ipv4.h index c68926b4899c..46d336abca92 100644 --- a/include/net/netns/ipv4.h +++ b/include/net/netns/ipv4.h @@ -74,6 +74,7 @@ struct netns_ipv4 { int sysctl_icmp_ratelimit; int sysctl_icmp_ratemask; int sysctl_icmp_errors_use_inbound_ifaddr; + int sysctl_icmp_redirects_use_orig_daddr; struct local_ports ip_local_ports; -- cgit v1.2.3 From 19bcf9f203c82c2028f5a0881b1f0690e3207190 Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Fri, 9 Oct 2015 13:44:54 -0500 Subject: ipv4: Pass struct net into ip_defrag and ip_check_defrag The function ip_defrag is called on both the input and the output paths of the networking stack. In particular conntrack when it is tracking outbound packets from the local machine calls ip_defrag. So add a struct net parameter and stop making ip_defrag guess which network namespace it needs to defragment packets in. Signed-off-by: "Eric W. Biederman" Acked-by: Pablo Neira Ayuso Signed-off-by: David S. Miller --- include/net/ip.h | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/include/net/ip.h b/include/net/ip.h index 3c904a28d5e5..1a98f1ca1638 100644 --- a/include/net/ip.h +++ b/include/net/ip.h @@ -506,11 +506,11 @@ static inline bool ip_defrag_user_in_between(u32 user, return user >= lower_bond && user <= upper_bond; } -int ip_defrag(struct sk_buff *skb, u32 user); +int ip_defrag(struct net *net, struct sk_buff *skb, u32 user); #ifdef CONFIG_INET -struct sk_buff *ip_check_defrag(struct sk_buff *skb, u32 user); +struct sk_buff *ip_check_defrag(struct net *net, struct sk_buff *skb, u32 user); #else -static inline struct sk_buff *ip_check_defrag(struct sk_buff *skb, u32 user) +static inline struct sk_buff *ip_check_defrag(struct net *net, struct sk_buff *skb, u32 user) { return skb; } -- cgit v1.2.3 From b72775977c39dcd380777ff5ea8041fdf67ee382 Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Fri, 9 Oct 2015 13:44:55 -0500 Subject: ipv6: Pass struct net into nf_ct_frag6_gather The function nf_ct_frag6_gather is called on both the input and the output paths of the networking stack. In particular ipv6_defrag which calls nf_ct_frag6_gather is called from both the the PRE_ROUTING chain on input and the LOCAL_OUT chain on output. The addition of a net parameter makes it explicit which network namespace the packets are being reassembled in, and removes the need for nf_ct_frag6_gather to guess. Signed-off-by: "Eric W. Biederman" Acked-by: Pablo Neira Ayuso Signed-off-by: David S. Miller --- include/net/netfilter/ipv6/nf_defrag_ipv6.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/net/netfilter/ipv6/nf_defrag_ipv6.h b/include/net/netfilter/ipv6/nf_defrag_ipv6.h index 27666d8a0bd0..fb7da5bb76cc 100644 --- a/include/net/netfilter/ipv6/nf_defrag_ipv6.h +++ b/include/net/netfilter/ipv6/nf_defrag_ipv6.h @@ -5,7 +5,7 @@ void nf_defrag_ipv6_enable(void); int nf_ct_frag6_init(void); void nf_ct_frag6_cleanup(void); -struct sk_buff *nf_ct_frag6_gather(struct sk_buff *skb, u32 user); +struct sk_buff *nf_ct_frag6_gather(struct net *net, struct sk_buff *skb, u32 user); void nf_ct_frag6_consume_orig(struct sk_buff *skb); struct inet_frags_ctl; -- cgit v1.2.3 From 93f0490e5deb9445737cabf0e436f3288a4042b7 Mon Sep 17 00:00:00 2001 From: Tamizh chelvam Date: Wed, 7 Oct 2015 10:40:04 +0530 Subject: Revert "mac80211: remove exposing 'mfp' to drivers" This reverts commit 5c48f1201744233d4f235c7dd916d5196ed20716. Some device drivers (ath10k) offload part of aggregation including AddBA/DelBA negotiations to firmware. In such scenario, the PMF configuration of the station needs to be provided to driver to enable encryption of AddBA/DelBA action frames. Signed-off-by: Tamizh chelvam Signed-off-by: Johannes Berg --- include/net/mac80211.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/net/mac80211.h b/include/net/mac80211.h index 4ec6fedeb220..1bb2a2b4e187 100644 --- a/include/net/mac80211.h +++ b/include/net/mac80211.h @@ -1683,6 +1683,7 @@ struct ieee80211_sta_rates { * @tdls: indicates whether the STA is a TDLS peer * @tdls_initiator: indicates the STA is an initiator of the TDLS link. Only * valid if the STA is a TDLS peer in the first place. + * @mfp: indicates whether the STA uses management frame protection or not. * @txq: per-TID data TX queues (if driver uses the TXQ abstraction) */ struct ieee80211_sta { @@ -1700,6 +1701,7 @@ struct ieee80211_sta { struct ieee80211_sta_rates __rcu *rates; bool tdls; bool tdls_initiator; + bool mfp; struct ieee80211_txq *txq[IEEE80211_NUM_TIDS]; -- cgit v1.2.3 From 6e19bc4b7091ffd26586100eee78232b44427ec7 Mon Sep 17 00:00:00 2001 From: Dmitry Shmidt Date: Wed, 7 Oct 2015 11:32:53 +0200 Subject: nl80211: allow BSS data to include CLOCK_BOOTTIME timestamp For location and connectivity services, userspace would often like to know the time when the BSS was last seen. The current "last seen" value is calculated in a way that makes it less useful, especially if the system suspended in the meantime. Add the ability for the driver to report a real CLOCK_BOOTTIME stamp that can then be reported to userspace (if present). Drivers wishing to use this must be converted to the new API to call cfg80211_inform_bss_data() or cfg80211_inform_bss_frame_data(). They need to ensure the reported value is accurate enough even when the frame might have been buffered in the device (e.g. firmware.) Signed-off-by: Dmitry Shmidt [modified to use struct, inlines] Signed-off-by: Johannes Berg --- include/net/cfg80211.h | 95 +++++++++++++++++++++++++++++++++++--------- include/uapi/linux/nl80211.h | 4 ++ 2 files changed, 80 insertions(+), 19 deletions(-) (limited to 'include') diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h index 90332a1838cc..7f1e9ee844e2 100644 --- a/include/net/cfg80211.h +++ b/include/net/cfg80211.h @@ -1575,6 +1575,26 @@ enum cfg80211_signal_type { CFG80211_SIGNAL_TYPE_UNSPEC, }; +/** + * struct cfg80211_inform_bss - BSS inform data + * @chan: channel the frame was received on + * @scan_width: scan width that was used + * @signal: signal strength value, according to the wiphy's + * signal type + * @boottime_ns: timestamp (CLOCK_BOOTTIME) when the information was + * received; should match the time when the frame was actually + * received by the device (not just by the host, in case it was + * buffered on the device) and be accurate to about 10ms. + * If the frame isn't buffered, just passing the return value of + * ktime_get_boot_ns() is likely appropriate. + */ +struct cfg80211_inform_bss { + struct ieee80211_channel *chan; + enum nl80211_bss_scan_width scan_width; + s32 signal; + u64 boottime_ns; +}; + /** * struct cfg80211_bss_ie_data - BSS entry IE data * @tsf: TSF contained in the frame that carried these IEs @@ -3958,14 +3978,11 @@ void cfg80211_sched_scan_stopped(struct wiphy *wiphy); void cfg80211_sched_scan_stopped_rtnl(struct wiphy *wiphy); /** - * cfg80211_inform_bss_width_frame - inform cfg80211 of a received BSS frame - * + * cfg80211_inform_bss_frame_data - inform cfg80211 of a received BSS frame * @wiphy: the wiphy reporting the BSS - * @rx_channel: The channel the frame was received on - * @scan_width: width of the control channel + * @data: the BSS metadata * @mgmt: the management frame (probe response or beacon) * @len: length of the management frame - * @signal: the signal strength, type depends on the wiphy's signal_type * @gfp: context flags * * This informs cfg80211 that BSS information was found and @@ -3975,11 +3992,26 @@ void cfg80211_sched_scan_stopped_rtnl(struct wiphy *wiphy); * Or %NULL on error. */ struct cfg80211_bss * __must_check +cfg80211_inform_bss_frame_data(struct wiphy *wiphy, + struct cfg80211_inform_bss *data, + struct ieee80211_mgmt *mgmt, size_t len, + gfp_t gfp); + +static inline struct cfg80211_bss * __must_check cfg80211_inform_bss_width_frame(struct wiphy *wiphy, struct ieee80211_channel *rx_channel, enum nl80211_bss_scan_width scan_width, struct ieee80211_mgmt *mgmt, size_t len, - s32 signal, gfp_t gfp); + s32 signal, gfp_t gfp) +{ + struct cfg80211_inform_bss data = { + .chan = rx_channel, + .scan_width = scan_width, + .signal = signal, + }; + + return cfg80211_inform_bss_frame_data(wiphy, &data, mgmt, len, gfp); +} static inline struct cfg80211_bss * __must_check cfg80211_inform_bss_frame(struct wiphy *wiphy, @@ -3987,9 +4019,13 @@ cfg80211_inform_bss_frame(struct wiphy *wiphy, struct ieee80211_mgmt *mgmt, size_t len, s32 signal, gfp_t gfp) { - return cfg80211_inform_bss_width_frame(wiphy, rx_channel, - NL80211_BSS_CHAN_WIDTH_20, - mgmt, len, signal, gfp); + struct cfg80211_inform_bss data = { + .chan = rx_channel, + .scan_width = NL80211_BSS_CHAN_WIDTH_20, + .signal = signal, + }; + + return cfg80211_inform_bss_frame_data(wiphy, &data, mgmt, len, gfp); } /** @@ -4006,11 +4042,10 @@ enum cfg80211_bss_frame_type { }; /** - * cfg80211_inform_bss_width - inform cfg80211 of a new BSS + * cfg80211_inform_bss_data - inform cfg80211 of a new BSS * * @wiphy: the wiphy reporting the BSS - * @rx_channel: The channel the frame was received on - * @scan_width: width of the control channel + * @data: the BSS metadata * @ftype: frame type (if known) * @bssid: the BSSID of the BSS * @tsf: the TSF sent by the peer in the beacon/probe response (or 0) @@ -4018,7 +4053,6 @@ enum cfg80211_bss_frame_type { * @beacon_interval: the beacon interval announced by the peer * @ie: additional IEs sent by the peer * @ielen: length of the additional IEs - * @signal: the signal strength, type depends on the wiphy's signal_type * @gfp: context flags * * This informs cfg80211 that BSS information was found and @@ -4028,13 +4062,32 @@ enum cfg80211_bss_frame_type { * Or %NULL on error. */ struct cfg80211_bss * __must_check +cfg80211_inform_bss_data(struct wiphy *wiphy, + struct cfg80211_inform_bss *data, + enum cfg80211_bss_frame_type ftype, + const u8 *bssid, u64 tsf, u16 capability, + u16 beacon_interval, const u8 *ie, size_t ielen, + gfp_t gfp); + +static inline struct cfg80211_bss * __must_check cfg80211_inform_bss_width(struct wiphy *wiphy, struct ieee80211_channel *rx_channel, enum nl80211_bss_scan_width scan_width, enum cfg80211_bss_frame_type ftype, const u8 *bssid, u64 tsf, u16 capability, u16 beacon_interval, const u8 *ie, size_t ielen, - s32 signal, gfp_t gfp); + s32 signal, gfp_t gfp) +{ + struct cfg80211_inform_bss data = { + .chan = rx_channel, + .scan_width = scan_width, + .signal = signal, + }; + + return cfg80211_inform_bss_data(wiphy, &data, ftype, bssid, tsf, + capability, beacon_interval, ie, ielen, + gfp); +} static inline struct cfg80211_bss * __must_check cfg80211_inform_bss(struct wiphy *wiphy, @@ -4044,11 +4097,15 @@ cfg80211_inform_bss(struct wiphy *wiphy, u16 beacon_interval, const u8 *ie, size_t ielen, s32 signal, gfp_t gfp) { - return cfg80211_inform_bss_width(wiphy, rx_channel, - NL80211_BSS_CHAN_WIDTH_20, ftype, - bssid, tsf, capability, - beacon_interval, ie, ielen, signal, - gfp); + struct cfg80211_inform_bss data = { + .chan = rx_channel, + .scan_width = NL80211_BSS_CHAN_WIDTH_20, + .signal = signal, + }; + + return cfg80211_inform_bss_data(wiphy, &data, ftype, bssid, tsf, + capability, beacon_interval, ie, ielen, + gfp); } struct cfg80211_bss *cfg80211_get_bss(struct wiphy *wiphy, diff --git a/include/uapi/linux/nl80211.h b/include/uapi/linux/nl80211.h index c0ab6b0a3919..5dadb844fe18 100644 --- a/include/uapi/linux/nl80211.h +++ b/include/uapi/linux/nl80211.h @@ -3364,6 +3364,9 @@ enum nl80211_bss_scan_width { * (not present if no beacon frame has been received yet) * @NL80211_BSS_PRESP_DATA: the data in @NL80211_BSS_INFORMATION_ELEMENTS and * @NL80211_BSS_TSF is known to be from a probe response (flag attribute) + * @NL80211_BSS_LAST_SEEN_BOOTTIME: CLOCK_BOOTTIME timestamp when this entry + * was last updated by a received frame. The value is expected to be + * accurate to about 10ms. (u64, nanoseconds) * @__NL80211_BSS_AFTER_LAST: internal * @NL80211_BSS_MAX: highest BSS attribute */ @@ -3383,6 +3386,7 @@ enum nl80211_bss { NL80211_BSS_CHAN_WIDTH, NL80211_BSS_BEACON_TSF, NL80211_BSS_PRESP_DATA, + NL80211_BSS_LAST_SEEN_BOOTTIME, /* keep last */ __NL80211_BSS_AFTER_LAST, -- cgit v1.2.3 From a4288289f585d42a19145f266e214acb165fe9b3 Mon Sep 17 00:00:00 2001 From: Johannes Berg Date: Wed, 7 Oct 2015 15:48:25 +0200 Subject: wireless: update robust action frame list Unprotected DMG and VHT action frames are not protected, reflect that in the list. Signed-off-by: Johannes Berg --- include/linux/ieee80211.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/linux/ieee80211.h b/include/linux/ieee80211.h index dcfb2f43d316..0109f3847e9a 100644 --- a/include/linux/ieee80211.h +++ b/include/linux/ieee80211.h @@ -2397,6 +2397,8 @@ static inline bool _ieee80211_is_robust_mgmt_frame(struct ieee80211_hdr *hdr) return *category != WLAN_CATEGORY_PUBLIC && *category != WLAN_CATEGORY_HT && *category != WLAN_CATEGORY_SELF_PROTECTED && + *category != WLAN_CATEGORY_UNPROT_DMG && + *category != WLAN_CATEGORY_VHT && *category != WLAN_CATEGORY_VENDOR_SPECIFIC; } -- cgit v1.2.3 From af61426187cd854bffe013ca8547bd8fa3c4dfbf Mon Sep 17 00:00:00 2001 From: Johannes Berg Date: Wed, 7 Oct 2015 15:48:26 +0200 Subject: wireless: add WNM action frame categories Add the WNM and unprotected WNM categories and mark the latter as not robust. Signed-off-by: Johannes Berg --- include/linux/ieee80211.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include') diff --git a/include/linux/ieee80211.h b/include/linux/ieee80211.h index 0109f3847e9a..452c0b0d2f32 100644 --- a/include/linux/ieee80211.h +++ b/include/linux/ieee80211.h @@ -1932,6 +1932,8 @@ enum ieee80211_category { WLAN_CATEGORY_HT = 7, WLAN_CATEGORY_SA_QUERY = 8, WLAN_CATEGORY_PROTECTED_DUAL_OF_ACTION = 9, + WLAN_CATEGORY_WNM = 10, + WLAN_CATEGORY_WNM_UNPROTECTED = 11, WLAN_CATEGORY_TDLS = 12, WLAN_CATEGORY_MESH_ACTION = 13, WLAN_CATEGORY_MULTIHOP_ACTION = 14, @@ -2396,6 +2398,7 @@ static inline bool _ieee80211_is_robust_mgmt_frame(struct ieee80211_hdr *hdr) category = ((u8 *) hdr) + 24; return *category != WLAN_CATEGORY_PUBLIC && *category != WLAN_CATEGORY_HT && + *category != WLAN_CATEGORY_WNM_UNPROTECTED && *category != WLAN_CATEGORY_SELF_PROTECTED && *category != WLAN_CATEGORY_UNPROT_DMG && *category != WLAN_CATEGORY_VHT && -- cgit v1.2.3 From 3b06d277957c7af705a9c0cdda4b371759efb717 Mon Sep 17 00:00:00 2001 From: Avraham Stern Date: Mon, 12 Oct 2015 09:51:34 +0300 Subject: cfg80211: Add multiple scan plans for scheduled scan Add the option to configure multiple 'scan plans' for scheduled scan. Each 'scan plan' defines the number of scan cycles and the interval between scans. The scan plans are executed in the order they were configured. The last scan plan will always run infinitely and thus defines only the interval between scans. The maximum number of scan plans supported by the device and the maximum number of iterations in a single scan plan are advertised to userspace so it can configure the scan plans appropriately. When scheduled scan results are received there is no way to know which scan plan is being currently executed, so there is no way to know when the next scan iteration will start. This is not a problem, however. The scan start timestamp is only used for flushing old scan results, and there is no difference between flushing all results received until the end of the previous iteration or the start of the current one, since no results will be received in between. Signed-off-by: Avraham Stern Signed-off-by: Luca Coelho Signed-off-by: Johannes Berg --- include/net/cfg80211.h | 31 ++++++++++++++++++++++++-- include/uapi/linux/nl80211.h | 53 +++++++++++++++++++++++++++++++++++++++++++- 2 files changed, 81 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h index 7f1e9ee844e2..48155be5db7f 100644 --- a/include/net/cfg80211.h +++ b/include/net/cfg80211.h @@ -5,6 +5,7 @@ * * Copyright 2006-2010 Johannes Berg * Copyright 2013-2014 Intel Mobile Communications GmbH + * Copyright 2015 Intel Deutschland GmbH * * This program is free software; you can redistribute it and/or modify * it under the terms of the GNU General Public License version 2 as @@ -1500,6 +1501,20 @@ struct cfg80211_match_set { s32 rssi_thold; }; +/** + * struct cfg80211_sched_scan_plan - scan plan for scheduled scan + * + * @interval: interval between scheduled scan iterations. In seconds. + * @iterations: number of scan iterations in this scan plan. Zero means + * infinite loop. + * The last scan plan will always have this parameter set to zero, + * all other scan plans will have a finite number of iterations. + */ +struct cfg80211_sched_scan_plan { + u32 interval; + u32 iterations; +}; + /** * struct cfg80211_sched_scan_request - scheduled scan request description * @@ -1507,7 +1522,6 @@ struct cfg80211_match_set { * @n_ssids: number of SSIDs * @n_channels: total number of channels to scan * @scan_width: channel width for scanning - * @interval: interval between each scheduled scan cycle * @ie: optional information element(s) to add into Probe Request or %NULL * @ie_len: length of ie in octets * @flags: bit field of flags controlling operation @@ -1526,6 +1540,9 @@ struct cfg80211_match_set { * @mac_addr_mask: MAC address mask used with randomisation, bits that * are 0 in the mask should be randomised, bits that are 1 should * be taken from the @mac_addr + * @scan_plans: scan plans to be executed in this scheduled scan. Lowest + * index must be executed first. + * @n_scan_plans: number of scan plans, at least 1. * @rcu_head: RCU callback used to free the struct * @owner_nlportid: netlink portid of owner (if this should is a request * owned by a particular socket) @@ -1539,7 +1556,6 @@ struct cfg80211_sched_scan_request { int n_ssids; u32 n_channels; enum nl80211_bss_scan_width scan_width; - u32 interval; const u8 *ie; size_t ie_len; u32 flags; @@ -1547,6 +1563,8 @@ struct cfg80211_sched_scan_request { int n_match_sets; s32 min_rssi_thold; u32 delay; + struct cfg80211_sched_scan_plan *scan_plans; + int n_scan_plans; u8 mac_addr[ETH_ALEN] __aligned(2); u8 mac_addr_mask[ETH_ALEN] __aligned(2); @@ -3076,6 +3094,12 @@ struct wiphy_vendor_command { * include fixed IEs like supported rates * @max_sched_scan_ie_len: same as max_scan_ie_len, but for scheduled * scans + * @max_sched_scan_plans: maximum number of scan plans (scan interval and number + * of iterations) for scheduled scan supported by the device. + * @max_sched_scan_plan_interval: maximum interval (in seconds) for a + * single scan plan supported by the device. + * @max_sched_scan_plan_iterations: maximum number of iterations for a single + * scan plan supported by the device. * @coverage_class: current coverage class * @fw_version: firmware version for ethtool reporting * @hw_version: hardware version for ethtool reporting @@ -3183,6 +3207,9 @@ struct wiphy { u8 max_match_sets; u16 max_scan_ie_len; u16 max_sched_scan_ie_len; + u32 max_sched_scan_plans; + u32 max_sched_scan_plan_interval; + u32 max_sched_scan_plan_iterations; int n_cipher_suites; const u32 *cipher_suites; diff --git a/include/uapi/linux/nl80211.h b/include/uapi/linux/nl80211.h index 5dadb844fe18..1f0b4cf5dd03 100644 --- a/include/uapi/linux/nl80211.h +++ b/include/uapi/linux/nl80211.h @@ -10,6 +10,7 @@ * Copyright 2008, 2009 Luis R. Rodriguez * Copyright 2008 Jouni Malinen * Copyright 2008 Colin McCabe + * Copyright 2015 Intel Deutschland GmbH * * Permission to use, copy, modify, and/or distribute this software for any * purpose with or without fee is hereby granted, provided that the above @@ -328,7 +329,15 @@ * partial scan results may be available * * @NL80211_CMD_START_SCHED_SCAN: start a scheduled scan at certain - * intervals, as specified by %NL80211_ATTR_SCHED_SCAN_INTERVAL. + * intervals and certain number of cycles, as specified by + * %NL80211_ATTR_SCHED_SCAN_PLANS. If %NL80211_ATTR_SCHED_SCAN_PLANS is + * not specified and only %NL80211_ATTR_SCHED_SCAN_INTERVAL is specified, + * scheduled scan will run in an infinite loop with the specified interval. + * These attributes are mutually exculsive, + * i.e. NL80211_ATTR_SCHED_SCAN_INTERVAL must not be passed if + * NL80211_ATTR_SCHED_SCAN_PLANS is defined. + * If for some reason scheduled scan is aborted by the driver, all scan + * plans are canceled (including scan plans that did not start yet). * Like with normal scans, if SSIDs (%NL80211_ATTR_SCAN_SSIDS) * are passed, they are used in the probe requests. For * broadcast, a broadcast SSID must be passed (ie. an empty @@ -1761,6 +1770,19 @@ enum nl80211_commands { * @NL80211_ATTR_REG_INDOOR: flag attribute, if set indicates that the device * is operating in an indoor environment. * + * @NL80211_ATTR_MAX_NUM_SCHED_SCAN_PLANS: maximum number of scan plans for + * scheduled scan supported by the device (u32), a wiphy attribute. + * @NL80211_ATTR_MAX_SCAN_PLAN_INTERVAL: maximum interval (in seconds) for + * a scan plan (u32), a wiphy attribute. + * @NL80211_ATTR_MAX_SCAN_PLAN_ITERATIONS: maximum number of iterations in + * a scan plan (u32), a wiphy attribute. + * @NL80211_ATTR_SCHED_SCAN_PLANS: a list of scan plans for scheduled scan. + * Each scan plan defines the number of scan iterations and the interval + * between scans. The last scan plan will always run infinitely, + * thus it must not specify the number of iterations, only the interval + * between scans. The scan plans are executed sequentially. + * Each scan plan is a nested attribute of &enum nl80211_sched_scan_plan. + * * @NUM_NL80211_ATTR: total number of nl80211_attrs available * @NL80211_ATTR_MAX: highest attribute number currently defined * @__NL80211_ATTR_AFTER_LAST: internal use @@ -2130,6 +2152,11 @@ enum nl80211_attrs { NL80211_ATTR_REG_INDOOR, + NL80211_ATTR_MAX_NUM_SCHED_SCAN_PLANS, + NL80211_ATTR_MAX_SCAN_PLAN_INTERVAL, + NL80211_ATTR_MAX_SCAN_PLAN_ITERATIONS, + NL80211_ATTR_SCHED_SCAN_PLANS, + /* add attributes here, update the policy in nl80211.c */ __NL80211_ATTR_AFTER_LAST, @@ -4593,4 +4620,28 @@ enum nl80211_tdls_peer_capability { NL80211_TDLS_PEER_WMM = 1<<2, }; +/** + * enum nl80211_sched_scan_plan - scanning plan for scheduled scan + * @__NL80211_SCHED_SCAN_PLAN_INVALID: attribute number 0 is reserved + * @NL80211_SCHED_SCAN_PLAN_INTERVAL: interval between scan iterations. In + * seconds (u32). + * @NL80211_SCHED_SCAN_PLAN_ITERATIONS: number of scan iterations in this + * scan plan (u32). The last scan plan must not specify this attribute + * because it will run infinitely. A value of zero is invalid as it will + * make the scan plan meaningless. + * @NL80211_SCHED_SCAN_PLAN_MAX: highest scheduled scan plan attribute number + * currently defined + * @__NL80211_SCHED_SCAN_PLAN_AFTER_LAST: internal use + */ +enum nl80211_sched_scan_plan { + __NL80211_SCHED_SCAN_PLAN_INVALID, + NL80211_SCHED_SCAN_PLAN_INTERVAL, + NL80211_SCHED_SCAN_PLAN_ITERATIONS, + + /* keep last */ + __NL80211_SCHED_SCAN_PLAN_AFTER_LAST, + NL80211_SCHED_SCAN_PLAN_MAX = + __NL80211_SCHED_SCAN_PLAN_AFTER_LAST - 1 +}; + #endif /* __LINUX_NL80211_H */ -- cgit v1.2.3 From ccf3c8c3fe1bd4828556650ae7928da6ffb4aaf6 Mon Sep 17 00:00:00 2001 From: David Ahern Date: Mon, 12 Oct 2015 11:47:07 -0700 Subject: net: Add IPv6 support to l3mdev Add operations to retrieve cached IPv6 dst entry from l3mdev device and lookup IPv6 source address. Signed-off-by: David Ahern Signed-off-by: David S. Miller --- include/net/l3mdev.h | 46 ++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 46 insertions(+) (limited to 'include') diff --git a/include/net/l3mdev.h b/include/net/l3mdev.h index 44a19a171104..774d85b2d5d9 100644 --- a/include/net/l3mdev.h +++ b/include/net/l3mdev.h @@ -19,14 +19,22 @@ * @l3mdev_get_rtable: Get cached IPv4 rtable (dst_entry) for device * * @l3mdev_get_saddr: Get source address for a flow + * + * @l3mdev_get_rt6_dst: Get cached IPv6 rt6_info (dst_entry) for device */ struct l3mdev_ops { u32 (*l3mdev_fib_table)(const struct net_device *dev); + + /* IPv4 ops */ struct rtable * (*l3mdev_get_rtable)(const struct net_device *dev, const struct flowi4 *fl4); void (*l3mdev_get_saddr)(struct net_device *dev, struct flowi4 *fl4); + + /* IPv6 ops */ + struct dst_entry * (*l3mdev_get_rt6_dst)(const struct net_device *dev, + const struct flowi6 *fl6); }; #ifdef CONFIG_NET_L3_MASTER_DEV @@ -123,6 +131,31 @@ static inline void l3mdev_get_saddr(struct net *net, int ifindex, } } +static inline struct dst_entry *l3mdev_get_rt6_dst(const struct net_device *dev, + const struct flowi6 *fl6) +{ + if (netif_is_l3_master(dev) && dev->l3mdev_ops->l3mdev_get_rt6_dst) + return dev->l3mdev_ops->l3mdev_get_rt6_dst(dev, fl6); + + return NULL; +} + +static inline +struct dst_entry *l3mdev_rt6_dst_by_oif(struct net *net, + const struct flowi6 *fl6) +{ + struct dst_entry *dst = NULL; + struct net_device *dev; + + dev = dev_get_by_index(net, fl6->flowi6_oif); + if (dev) { + dst = l3mdev_get_rt6_dst(dev, fl6); + dev_put(dev); + } + + return dst; +} + #else static inline int l3mdev_master_ifindex_rcu(struct net_device *dev) @@ -171,6 +204,19 @@ static inline void l3mdev_get_saddr(struct net *net, int ifindex, struct flowi4 *fl4) { } + +static inline +struct dst_entry *l3mdev_get_rt6_dst(const struct net_device *dev, + const struct flowi6 *fl6) +{ + return NULL; +} +static inline +struct dst_entry *l3mdev_rt6_dst_by_oif(struct net *net, + const struct flowi6 *fl6) +{ + return NULL; +} #endif #endif /* _NET_L3MDEV_H_ */ -- cgit v1.2.3 From ba61a8d9d780980e8284355a0be750897e7af212 Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Wed, 30 Sep 2015 13:26:42 +0200 Subject: can: avoid using timeval for uapi The can subsystem communicates with user space using a bcm_msg_head header, which contains two timestamps. This is problematic for multiple reasons: a) The structure layout is currently incompatible between 64-bit user space and 32-bit user space, and cannot work in compat mode (other than x32). b) The timeval structure layout will change in 32-bit user space when we fix the y2038 overflow problem by redefining time_t to 64-bit, making new 32-bit user space incompatible with the current kernel interface. Cars last a long time and often use old kernels, so the actual users of this code are the most likely ones to migrate to y2038 safe user space. This tries to work around part of the problem by changing the publicly visible user interface in the header, but not the binary interface. Fortunately, the values passed around in the structure are relative times and do not actually suffer from the y2038 overflow, so 32-bit is enough here. We replace the use of 'struct timeval' with a newly defined 'struct bcm_timeval' that uses the exact same binary layout as before and that still suffers from problem a) but not problem b). The downside of this approach is that any user space program that currently assigns a timeval structure to these members rather than writing the tv_sec/tv_usec portions individually will suffer a compile-time error when built with an updated kernel header. Fixing this error makes it work fine with old and new headers though. We could address problem a) by using '__u32' or 'int' members rather than 'long', but that would have a more significant downside in also breaking support for all existing 64-bit user binaries that might be using this interface, which is likely not acceptable. Signed-off-by: Arnd Bergmann Acked-by: Oliver Hartkopp Cc: linux-can@vger.kernel.org Cc: linux-api@vger.kernel.org Signed-off-by: Marc Kleine-Budde --- include/uapi/linux/can/bcm.h | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/uapi/linux/can/bcm.h b/include/uapi/linux/can/bcm.h index 89ddb9dc9bdf..7a291dc1ff15 100644 --- a/include/uapi/linux/can/bcm.h +++ b/include/uapi/linux/can/bcm.h @@ -47,6 +47,11 @@ #include #include +struct bcm_timeval { + long tv_sec; + long tv_usec; +}; + /** * struct bcm_msg_head - head of messages to/from the broadcast manager * @opcode: opcode, see enum below. @@ -62,7 +67,7 @@ struct bcm_msg_head { __u32 opcode; __u32 flags; __u32 count; - struct timeval ival1, ival2; + struct bcm_timeval ival1, ival2; canid_t can_id; __u32 nframes; struct can_frame frames[0]; -- cgit v1.2.3 From 42160a041db89807691b2a3fbf42e36a98b6019e Mon Sep 17 00:00:00 2001 From: Alexandre Belloni Date: Thu, 8 Oct 2015 16:56:07 +0200 Subject: can: at91: remove at91_can_data struct at91_can_data was used to pass a callback to the driver, allowing it to switch the transceiver on and off. As all at91 boards are now using DT, this is not used anymore, remove that structure. Signed-off-by: Alexandre Belloni Signed-off-by: Marc Kleine-Budde --- include/linux/platform_data/atmel.h | 5 ----- 1 file changed, 5 deletions(-) (limited to 'include') diff --git a/include/linux/platform_data/atmel.h b/include/linux/platform_data/atmel.h index 527a85c61924..c121ddf74f7f 100644 --- a/include/linux/platform_data/atmel.h +++ b/include/linux/platform_data/atmel.h @@ -74,11 +74,6 @@ struct atmel_uart_data { struct serial_rs485 rs485; /* rs485 settings */ }; -/* CAN */ -struct at91_can_data { - void (*transceiver_switch)(int on); -}; - /* FIXME: this needs a better location, but gets stuff building again */ extern int at91_suspend_entering_slow_clock(void); -- cgit v1.2.3 From 02a6d6136fa2a17f400a030829a6435556b3e65b Mon Sep 17 00:00:00 2001 From: Paolo Abeni Date: Wed, 14 Oct 2015 14:25:53 +0200 Subject: Revert "ipv4/icmp: redirect messages can use the ingress daddr as source" Revert the commit e2ca690b657f ("ipv4/icmp: redirect messages can use the ingress daddr as source"), which tried to introduce a more suitable behaviour for ICMP redirect messages generated by VRRP routers. However RFC 5798 section 8.1.1 states: The IPv4 source address of an ICMP redirect should be the address that the end-host used when making its next-hop routing decision. while said commit used the generating packet destination address, which do not match the above and in most cases leads to no redirect packets to be generated. Signed-off-by: Paolo Abeni Signed-off-by: David S. Miller --- include/net/netns/ipv4.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include') diff --git a/include/net/netns/ipv4.h b/include/net/netns/ipv4.h index 46d336abca92..c68926b4899c 100644 --- a/include/net/netns/ipv4.h +++ b/include/net/netns/ipv4.h @@ -74,7 +74,6 @@ struct netns_ipv4 { int sysctl_icmp_ratelimit; int sysctl_icmp_ratemask; int sysctl_icmp_errors_use_inbound_ifaddr; - int sysctl_icmp_redirects_use_orig_daddr; struct local_ports ip_local_ports; -- cgit v1.2.3 From 4a733ef1bea705cdc69d936b95fedab4b47fbd40 Mon Sep 17 00:00:00 2001 From: Johannes Berg Date: Wed, 14 Oct 2015 18:02:43 +0200 Subject: mac80211: remove PM-QoS listener As this API has never really seen any use and most drivers don't ever use the value derived from it, remove it. Change the only driver using it (rt2x00) to simply use the DTIM period instead of the "max sleep" time. Signed-off-by: Johannes Berg --- include/net/mac80211.h | 6 ------ 1 file changed, 6 deletions(-) (limited to 'include') diff --git a/include/net/mac80211.h b/include/net/mac80211.h index 1bb2a2b4e187..4b9dd070aeb9 100644 --- a/include/net/mac80211.h +++ b/include/net/mac80211.h @@ -1241,11 +1241,6 @@ enum ieee80211_smps_mode { * @flags: configuration flags defined above * * @listen_interval: listen interval in units of beacon interval - * @max_sleep_period: the maximum number of beacon intervals to sleep for - * before checking the beacon for a TIM bit (managed mode only); this - * value will be only achievable between DTIM frames, the hardware - * needs to check for the multicast traffic bit in DTIM beacons. - * This variable is valid only when the CONF_PS flag is set. * @ps_dtim_period: The DTIM period of the AP we're connected to, for use * in power saving. Power saving will not be enabled until a beacon * has been received and the DTIM period is known. @@ -1275,7 +1270,6 @@ enum ieee80211_smps_mode { struct ieee80211_conf { u32 flags; int power_level, dynamic_ps_timeout; - int max_sleep_period; u16 listen_interval; u8 ps_dtim_period; -- cgit v1.2.3 From f985c65c908f6b26c30019a83dc5ea295f5fcf62 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Wed, 14 Oct 2015 06:16:49 -0700 Subject: tcp: avoid spurious SYN flood detection at listen() time At listen() time, there is a small window where listener is visible with a zero backlog, triggering a spurious "Possible SYN flooding on port" message. Nothing prevents us from setting the correct backlog. Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- include/net/inet_connection_sock.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/net/inet_connection_sock.h b/include/net/inet_connection_sock.h index 3208a65d1c28..fd645c49e71e 100644 --- a/include/net/inet_connection_sock.h +++ b/include/net/inet_connection_sock.h @@ -312,7 +312,7 @@ static inline unsigned int inet_csk_listen_poll(const struct sock *sk) (POLLIN | POLLRDNORM) : 0; } -int inet_csk_listen_start(struct sock *sk, const int nr_table_entries); +int inet_csk_listen_start(struct sock *sk, int backlog); void inet_csk_listen_stop(struct sock *sk); void inet_csk_addr2sockaddr(struct sock *sk, struct sockaddr *uaddr); -- cgit v1.2.3 From fd76ee4da55abb21babfc69310d321b9cb9a32e0 Mon Sep 17 00:00:00 2001 From: Eli Cohen Date: Wed, 14 Oct 2015 17:43:45 +0300 Subject: net/mlx5_core: Fix internal error detection conditions The detection of a fatal condition has been updated to take into account the state reported by the device or by detecting an all ones read of the firmware version which indicates that the device is not accessible. Signed-off-by: Eli Cohen Signed-off-by: Or Gerlitz Signed-off-by: David S. Miller --- include/linux/mlx5/driver.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h index 41a32873f608..62b7d439813d 100644 --- a/include/linux/mlx5/driver.h +++ b/include/linux/mlx5/driver.h @@ -393,6 +393,7 @@ struct mlx5_core_health { struct timer_list timer; u32 prev; int miss_counter; + bool sick; struct workqueue_struct *wq; struct work_struct work; }; -- cgit v1.2.3 From 89d44f0a6c732db23b219be708e2fe1e03ee4842 Mon Sep 17 00:00:00 2001 From: Majd Dibbiny Date: Wed, 14 Oct 2015 17:43:46 +0300 Subject: net/mlx5_core: Add pci error handlers to mlx5_core driver This patch implement the pci_error_handlers for mlx5_core which allow the driver to recover from PCI error. Once an error is detected in the PCI, the mlx5_pci_err_detected is called and it: 1) Marks the device to be in 'Internal Error' state. 2) Dispatches an event to the mlx5_ib to flush all the outstanding cqes with error. 3) Returns all the on going commands with error. 4) Unloads the driver. Afterwards, the FW is reset and mlx5_pci_slot_reset is called and it enables the device and restore it's pci state. If the later succeeds, mlx5_pci_resume is called, and it loads the SW stack. Signed-off-by: Majd Dibbiny Signed-off-by: Eli Cohen Signed-off-by: Or Gerlitz Signed-off-by: David S. Miller --- include/linux/mlx5/driver.h | 22 ++++++++++++++++++++++ 1 file changed, 22 insertions(+) (limited to 'include') diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h index 62b7d439813d..9aba8d5139fa 100644 --- a/include/linux/mlx5/driver.h +++ b/include/linux/mlx5/driver.h @@ -487,8 +487,26 @@ struct mlx5_priv { spinlock_t ctx_lock; }; +enum mlx5_device_state { + MLX5_DEVICE_STATE_UP, + MLX5_DEVICE_STATE_INTERNAL_ERROR, +}; + +enum mlx5_interface_state { + MLX5_INTERFACE_STATE_DOWN, + MLX5_INTERFACE_STATE_UP, +}; + +enum mlx5_pci_status { + MLX5_PCI_STATUS_DISABLED, + MLX5_PCI_STATUS_ENABLED, +}; + struct mlx5_core_dev { struct pci_dev *pdev; + /* sync pci state */ + struct mutex pci_status_mutex; + enum mlx5_pci_status pci_status; u8 rev_id; char board_id[MLX5_BOARD_ID_LEN]; struct mlx5_cmd cmd; @@ -497,6 +515,10 @@ struct mlx5_core_dev { u32 hca_caps_max[MLX5_CAP_NUM][MLX5_UN_SZ_DW(hca_cap_union)]; phys_addr_t iseg_base; struct mlx5_init_seg __iomem *iseg; + enum mlx5_device_state state; + /* sync interface state */ + struct mutex intf_state_mutex; + enum mlx5_interface_state interface_state; void (*event) (struct mlx5_core_dev *dev, enum mlx5_dev_event event, unsigned long param); -- cgit v1.2.3 From e3297246c2c8cf8548ba722da3e3a8104cdcd035 Mon Sep 17 00:00:00 2001 From: Eli Cohen Date: Wed, 14 Oct 2015 17:43:47 +0300 Subject: net/mlx5_core: Wait for FW readiness on startup On device initialization, wait till firmware indicates that that it is done with initialization before proceeding to initialize the device. Also update initialization segment layout to match driver/firmware interface definitions. Signed-off-by: Eli Cohen Signed-off-by: Or Gerlitz Signed-off-by: David S. Miller --- include/linux/mlx5/device.h | 3 ++- include/linux/mlx5/driver.h | 5 +++++ 2 files changed, 7 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/mlx5/device.h b/include/linux/mlx5/device.h index 2a0b95662548..0b473cbfa7ef 100644 --- a/include/linux/mlx5/device.h +++ b/include/linux/mlx5/device.h @@ -439,7 +439,8 @@ struct mlx5_init_seg { __be32 cmdq_addr_h; __be32 cmdq_addr_l_sz; __be32 cmd_dbell; - __be32 rsvd1[121]; + __be32 rsvd1[120]; + __be32 initializing; struct health_buffer health; __be32 rsvd2[884]; __be32 health_counter; diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h index 9aba8d5139fa..5c857f2a20d7 100644 --- a/include/linux/mlx5/driver.h +++ b/include/linux/mlx5/driver.h @@ -826,6 +826,11 @@ void mlx5_core_put_rsc(struct mlx5_core_rsc_common *common); int mlx5_query_odp_caps(struct mlx5_core_dev *dev, struct mlx5_odp_caps *odp_caps); +static inline int fw_initializing(struct mlx5_core_dev *dev) +{ + return ioread32be(&dev->iseg->initializing) >> 31; +} + static inline u32 mlx5_mkey_to_idx(u32 mkey) { return mkey >> 8; -- cgit v1.2.3 From 2b3ddf27f48c8061f0676c5a8796008099945280 Mon Sep 17 00:00:00 2001 From: Jack Morgenstein Date: Wed, 14 Oct 2015 17:43:48 +0300 Subject: net/mlx4_core: Replace VF zero mac with random mac in mlx4_core By design, when no default MAC addresses are set in the Hypervisor for VFs, the VFs are passed zero-macs. When such a MAC is received by the VF, it generates a random MAC address and registers that MAC address with the Hypervisor. This random mac generation is currently done in the mlx4_en module. There is a problem, though, if the mlx4_ib module is loaded by a VF before the mlx4_en module. In this case, for RoCE, mlx4_ib will see the un-replaced zero-mac and register that zero-mac as part of QP1 initialization. Having a zero-mac in the port's MAC table creates problems for a Baseboard Management Console. The BMC occasionally sends packets with a zero-mac destination MAC. If there is a zero-mac present in the port's MAC table, the FW will send such BMC packets to the host driver rather than to the wire, and BMC will stop working. To address this problem, we move the replacement of zero-mac addresses with random-mac addresses to procedure mlx4_slave_cap(), which is part of the driver startup for VFs, and is before activation of mlx4_ib and mlx4_en. As a result, zero-mac addresses will never be registered in the port MAC table by the driver. In addition, when mlx4_en does initialize the net device, it needs to set the NET_ADDR_RANDOM flag in the netdev structure if the address was randomly generated. This is done so that udev on the VM does not create a new device name after each VF probe (VM boot and such). To accomplish this, we add a per-port flag in mlx4_dev which gets set whenever mlx4_core replaces a zero-mac with a randomly-generated mac. This flag is examined when mlx4_en initializes the net-device. Fix was suggested by Matan Barak Signed-off-by: Jack Morgenstein Signed-off-by: Or Gerlitz Signed-off-by: David S. Miller --- include/linux/mlx4/device.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/mlx4/device.h b/include/linux/mlx4/device.h index baad4cb8e9b0..5a8677bafe04 100644 --- a/include/linux/mlx4/device.h +++ b/include/linux/mlx4/device.h @@ -833,6 +833,7 @@ struct mlx4_dev { struct mlx4_quotas quotas; struct radix_tree_root qp_table_tree; u8 rev_id; + u8 port_random_macs; char board_id[MLX4_BOARD_ID_LEN]; int numa_node; int oper_log_mgm_entry_size; -- cgit v1.2.3 From 793f40147e82cdedc80971fa7f5596d6ed1e555e Mon Sep 17 00:00:00 2001 From: Jiri Pirko Date: Wed, 14 Oct 2015 19:40:48 +0200 Subject: switchdev: introduce switchdev deferred ops infrastructure Introduce infrastructure which will be used internally to defer ops. Note that the deferred ops are queued up and either are processed by scheduled work or explicitly by user calling deferred_process function. Signed-off-by: Jiri Pirko Signed-off-by: David S. Miller --- include/net/switchdev.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include') diff --git a/include/net/switchdev.h b/include/net/switchdev.h index 1ce70830357d..31b9038e07b0 100644 --- a/include/net/switchdev.h +++ b/include/net/switchdev.h @@ -167,6 +167,7 @@ switchdev_notifier_info_to_dev(const struct switchdev_notifier_info *info) #ifdef CONFIG_NET_SWITCHDEV +void switchdev_deferred_process(void); int switchdev_port_attr_get(struct net_device *dev, struct switchdev_attr *attr); int switchdev_port_attr_set(struct net_device *dev, @@ -208,6 +209,10 @@ void switchdev_port_fwd_mark_set(struct net_device *dev, #else +static inline void switchdev_deferred_process(void) +{ +} + static inline int switchdev_port_attr_get(struct net_device *dev, struct switchdev_attr *attr) { -- cgit v1.2.3 From f7fadf3047d005d17376da65aa9e5734f45a77d4 Mon Sep 17 00:00:00 2001 From: Jiri Pirko Date: Wed, 14 Oct 2015 19:40:49 +0200 Subject: switchdev: make struct switchdev_attr parameter const for attr_set calls Signed-off-by: Jiri Pirko Reviewed-by: Vivien Didelot Signed-off-by: David S. Miller --- include/net/switchdev.h | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/include/net/switchdev.h b/include/net/switchdev.h index 31b9038e07b0..d1c7f901ea61 100644 --- a/include/net/switchdev.h +++ b/include/net/switchdev.h @@ -132,7 +132,7 @@ struct switchdev_ops { int (*switchdev_port_attr_get)(struct net_device *dev, struct switchdev_attr *attr); int (*switchdev_port_attr_set)(struct net_device *dev, - struct switchdev_attr *attr, + const struct switchdev_attr *attr, struct switchdev_trans *trans); int (*switchdev_port_obj_add)(struct net_device *dev, const struct switchdev_obj *obj, @@ -171,7 +171,7 @@ void switchdev_deferred_process(void); int switchdev_port_attr_get(struct net_device *dev, struct switchdev_attr *attr); int switchdev_port_attr_set(struct net_device *dev, - struct switchdev_attr *attr); + const struct switchdev_attr *attr); int switchdev_port_obj_add(struct net_device *dev, const struct switchdev_obj *obj); int switchdev_port_obj_del(struct net_device *dev, @@ -220,7 +220,7 @@ static inline int switchdev_port_attr_get(struct net_device *dev, } static inline int switchdev_port_attr_set(struct net_device *dev, - struct switchdev_attr *attr) + const struct switchdev_attr *attr) { return -EOPNOTSUPP; } -- cgit v1.2.3 From 0bc05d585d381c30de3fdf955730df31593d2101 Mon Sep 17 00:00:00 2001 From: Jiri Pirko Date: Wed, 14 Oct 2015 19:40:50 +0200 Subject: switchdev: allow caller to explicitly request attr_set as deferred Caller should know if he can call attr_set directly (when holding RTNL) or if he has to defer the att_set processing for later. This also allows drivers to sleep inside attr_set and report operation status back to switchdev core. Switchdev core then warns if status is not ok, instead of silent errors happening in drivers. Benefit from newly introduced switchdev deferred ops infrastructure. Signed-off-by: Jiri Pirko Signed-off-by: David S. Miller --- include/net/switchdev.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/net/switchdev.h b/include/net/switchdev.h index d1c7f901ea61..f7de6f8e9a4c 100644 --- a/include/net/switchdev.h +++ b/include/net/switchdev.h @@ -17,6 +17,7 @@ #define SWITCHDEV_F_NO_RECURSE BIT(0) #define SWITCHDEV_F_SKIP_EOPNOTSUPP BIT(1) +#define SWITCHDEV_F_DEFER BIT(2) struct switchdev_trans_item { struct list_head list; -- cgit v1.2.3 From 850d0cbc9171f63f0418afffb0d89a84db927851 Mon Sep 17 00:00:00 2001 From: Jiri Pirko Date: Wed, 14 Oct 2015 19:40:51 +0200 Subject: switchdev: remove pointers from switchdev objects When object is used in deferred work, we cannot use pointers in switchdev object structures because the memory they point at may be already used by someone else. So rather do local copy of the value. Signed-off-by: Jiri Pirko Acked-by: Scott Feldman Reviewed-by: John Fastabend Signed-off-by: David S. Miller --- include/net/switchdev.h | 7 +++---- 1 file changed, 3 insertions(+), 4 deletions(-) (limited to 'include') diff --git a/include/net/switchdev.h b/include/net/switchdev.h index f7de6f8e9a4c..f8672d7f3ff2 100644 --- a/include/net/switchdev.h +++ b/include/net/switchdev.h @@ -14,6 +14,7 @@ #include #include #include +#include #define SWITCHDEV_F_NO_RECURSE BIT(0) #define SWITCHDEV_F_SKIP_EOPNOTSUPP BIT(1) @@ -59,8 +60,6 @@ struct switchdev_attr { } u; }; -struct fib_info; - enum switchdev_obj_id { SWITCHDEV_OBJ_ID_UNDEFINED, SWITCHDEV_OBJ_ID_PORT_VLAN, @@ -88,7 +87,7 @@ struct switchdev_obj_ipv4_fib { struct switchdev_obj obj; u32 dst; int dst_len; - struct fib_info *fi; + struct fib_info fi; u8 tos; u8 type; u32 nlflags; @@ -101,7 +100,7 @@ struct switchdev_obj_ipv4_fib { /* SWITCHDEV_OBJ_ID_PORT_FDB */ struct switchdev_obj_port_fdb { struct switchdev_obj obj; - const unsigned char *addr; + unsigned char addr[ETH_ALEN]; u16 vid; u16 ndm_state; }; -- cgit v1.2.3 From 4d429c5ddc5128fccd3048059ae26bb39f0d8284 Mon Sep 17 00:00:00 2001 From: Jiri Pirko Date: Wed, 14 Oct 2015 19:40:52 +0200 Subject: switchdev: introduce possibility to defer obj_add/del Similar to the attr usecase, the caller knows if he is holding RTNL and is in atomic section. So let the called to decide the correct call variant. This allows drivers to sleep inside their ops and wait for hw to get the operation status. Then the status is propagated into switchdev core. This avoids silent errors in drivers. Signed-off-by: Jiri Pirko Signed-off-by: David S. Miller --- include/net/switchdev.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/net/switchdev.h b/include/net/switchdev.h index f8672d7f3ff2..bc865e244efe 100644 --- a/include/net/switchdev.h +++ b/include/net/switchdev.h @@ -69,6 +69,7 @@ enum switchdev_obj_id { struct switchdev_obj { enum switchdev_obj_id id; + u32 flags; }; /* SWITCHDEV_OBJ_ID_PORT_VLAN */ -- cgit v1.2.3 From f03f2e154f52fdaa982de7e2c386737679963dc9 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Wed, 14 Oct 2015 11:16:27 -0700 Subject: tcp/dccp: add inet_csk_reqsk_queue_drop_and_put() helper Let's reduce the confusion about inet_csk_reqsk_queue_drop() : In many cases we also need to release reference on request socket, so add a helper to do this, reducing code size and complexity. Fixes: 4bdc3d66147b ("tcp/dccp: fix behavior of stale SYN_RECV request sockets") Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- include/net/inet_connection_sock.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/net/inet_connection_sock.h b/include/net/inet_connection_sock.h index fd645c49e71e..e84ea9f2498f 100644 --- a/include/net/inet_connection_sock.h +++ b/include/net/inet_connection_sock.h @@ -299,6 +299,7 @@ static inline int inet_csk_reqsk_queue_is_full(const struct sock *sk) } void inet_csk_reqsk_queue_drop(struct sock *sk, struct request_sock *req); +void inet_csk_reqsk_queue_drop_and_put(struct sock *sk, struct request_sock *req); void inet_csk_destroy_sock(struct sock *sk); void inet_csk_prepare_forced_close(struct sock *sk); -- cgit v1.2.3 From ebb516af60e18258aac8e80bbe068740ef1579ed Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Wed, 14 Oct 2015 11:16:28 -0700 Subject: tcp/dccp: fix race at listener dismantle phase Under stress, a close() on a listener can trigger the WARN_ON(sk->sk_ack_backlog) in inet_csk_listen_stop() We need to test if listener is still active before queueing a child in inet_csk_reqsk_queue_add() Create a common inet_child_forget() helper, and use it from inet_csk_reqsk_queue_add() and inet_csk_listen_stop() Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- include/net/inet_connection_sock.h | 9 ++------- include/net/request_sock.h | 19 ------------------- 2 files changed, 2 insertions(+), 26 deletions(-) (limited to 'include') diff --git a/include/net/inet_connection_sock.h b/include/net/inet_connection_sock.h index e84ea9f2498f..63615709839d 100644 --- a/include/net/inet_connection_sock.h +++ b/include/net/inet_connection_sock.h @@ -268,13 +268,8 @@ struct dst_entry *inet_csk_route_child_sock(const struct sock *sk, struct sock *newsk, const struct request_sock *req); -static inline void inet_csk_reqsk_queue_add(struct sock *sk, - struct request_sock *req, - struct sock *child) -{ - reqsk_queue_add(&inet_csk(sk)->icsk_accept_queue, req, sk, child); -} - +void inet_csk_reqsk_queue_add(struct sock *sk, struct request_sock *req, + struct sock *child); void inet_csk_reqsk_queue_hash_add(struct sock *sk, struct request_sock *req, unsigned long timeout); diff --git a/include/net/request_sock.h b/include/net/request_sock.h index 2e73748956d5..a0dde04eb178 100644 --- a/include/net/request_sock.h +++ b/include/net/request_sock.h @@ -186,25 +186,6 @@ static inline bool reqsk_queue_empty(const struct request_sock_queue *queue) return queue->rskq_accept_head == NULL; } -static inline void reqsk_queue_add(struct request_sock_queue *queue, - struct request_sock *req, - struct sock *parent, - struct sock *child) -{ - spin_lock(&queue->rskq_lock); - req->sk = child; - sk_acceptq_added(parent); - - if (queue->rskq_accept_head == NULL) - queue->rskq_accept_head = req; - else - queue->rskq_accept_tail->dl_next = req; - - queue->rskq_accept_tail = req; - req->dl_next = NULL; - spin_unlock(&queue->rskq_lock); -} - static inline struct request_sock *reqsk_queue_remove(struct request_sock_queue *queue, struct sock *parent) { -- cgit v1.2.3 From 573c7ba006edbecff0714db651dd3602b9d0a6a0 Mon Sep 17 00:00:00 2001 From: Jiri Pirko Date: Fri, 16 Oct 2015 14:01:22 +0200 Subject: net: introduce pre-change upper device notifier This newly introduced netdevice notifier is called before actual change upper happens. That provides a possibility for notifier handlers to know upper change will happen and react to it, including possibility to forbid the change. That is valuable for drivers which can check if the upper device linkage is supported and forbid that in case it is not. Signed-off-by: Jiri Pirko Signed-off-by: David S. Miller --- include/linux/netdevice.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index b3374402c1ea..69fdd427c8cb 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -2106,6 +2106,7 @@ struct pcpu_sw_netstats { #define NETDEV_PRECHANGEMTU 0x0017 /* notify before mtu change happened */ #define NETDEV_CHANGEINFODATA 0x0018 #define NETDEV_BONDING_INFO 0x0019 +#define NETDEV_PRECHANGEUPPER 0x001A int register_netdevice_notifier(struct notifier_block *nb); int unregister_netdevice_notifier(struct notifier_block *nb); -- cgit v1.2.3 From 2ffbceb2b08f8ca0496c54a9ebcd11d25275954e Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Tue, 13 Oct 2015 14:33:26 +0200 Subject: netfilter: remove hook owner refcounting since commit 8405a8fff3f8 ("netfilter: nf_qeueue: Drop queue entries on nf_unregister_hook") all pending queued entries are discarded. So we can simply remove all of the owner handling -- when module is removed it also needs to unregister all its hooks. Signed-off-by: Florian Westphal Signed-off-by: Pablo Neira Ayuso --- include/linux/netfilter.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include') diff --git a/include/linux/netfilter.h b/include/linux/netfilter.h index edb3dc32f1da..ef11e1d77699 100644 --- a/include/linux/netfilter.h +++ b/include/linux/netfilter.h @@ -90,7 +90,6 @@ struct nf_hook_ops { /* User fills in from here down. */ nf_hookfn *hook; struct net_device *dev; - struct module *owner; void *priv; u_int8_t pf; unsigned int hooknum; -- cgit v1.2.3 From ed78d09d59ba9764b7454e8e1ccbb0072a55b6d7 Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Tue, 13 Oct 2015 14:33:27 +0200 Subject: netfilter: make nf_queue_entry_get_refs return void We don't care if module is being unloaded anymore since hook unregister handling will destroy queue entries using that hook. Signed-off-by: Florian Westphal Signed-off-by: Pablo Neira Ayuso --- include/net/netfilter/nf_queue.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/net/netfilter/nf_queue.h b/include/net/netfilter/nf_queue.h index e8635854a55b..9c5638ad872e 100644 --- a/include/net/netfilter/nf_queue.h +++ b/include/net/netfilter/nf_queue.h @@ -32,7 +32,7 @@ void nf_register_queue_handler(const struct nf_queue_handler *qh); void nf_unregister_queue_handler(void); void nf_reinject(struct nf_queue_entry *entry, unsigned int verdict); -bool nf_queue_entry_get_refs(struct nf_queue_entry *entry); +void nf_queue_entry_get_refs(struct nf_queue_entry *entry); void nf_queue_entry_release_refs(struct nf_queue_entry *entry); static inline void init_hashrandom(u32 *jhash_initval) -- cgit v1.2.3 From 008027c31d57a22bd80dda5acc95b037634eee0f Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Fri, 9 Oct 2015 20:45:42 +0200 Subject: netfilter: turn NF_HOOK into an inline function A recent change to the dst_output handling caused a new warning when the call to NF_HOOK() is the only used of a local variable passed as 'dev', and CONFIG_NETFILTER is disabled: net/ipv6/ip6_output.c: In function 'ip6_output': net/ipv6/ip6_output.c:135:21: warning: unused variable 'dev' [-Wunused-variable] The reason for this is that the NF_HOOK macro in this case does not reference the variable at all, and the call to dev_net(dev) got removed from the ip6_output function. To avoid that warning now and in the future, this changes the macro into an equivalent inline function, which tells the compiler that the variable is passed correctly but still unused. The dn_forward function apparently had the same problem in the past and added a local workaround that no longer works with the inline function. In order to avoid a regression, we have to also remove the #ifdef from decnet in the same patch. Fixes: ede2059dbaf9 ("dst: Pass net into dst->output") Signed-off-by: Arnd Bergmann Signed-off-by: Pablo Neira Ayuso --- include/linux/netfilter.h | 19 +++++++++++++++++-- 1 file changed, 17 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/netfilter.h b/include/linux/netfilter.h index ef11e1d77699..0ad556726181 100644 --- a/include/linux/netfilter.h +++ b/include/linux/netfilter.h @@ -346,8 +346,23 @@ nf_nat_decode_session(struct sk_buff *skb, struct flowi *fl, u_int8_t family) } #else /* !CONFIG_NETFILTER */ -#define NF_HOOK(pf, hook, net, sk, skb, indev, outdev, okfn) (okfn)(net, sk, skb) -#define NF_HOOK_COND(pf, hook, net, sk, skb, indev, outdev, okfn, cond) (okfn)(net, sk, skb) +static inline int +NF_HOOK_COND(uint8_t pf, unsigned int hook, struct net *net, struct sock *sk, + struct sk_buff *skb, struct net_device *in, struct net_device *out, + int (*okfn)(struct net *, struct sock *, struct sk_buff *), + bool cond) +{ + return okfn(net, sk, skb); +} + +static inline int +NF_HOOK(uint8_t pf, unsigned int hook, struct net *net, struct sock *sk, + struct sk_buff *skb, struct net_device *in, struct net_device *out, + int (*okfn)(struct net *, struct sock *, struct sk_buff *)) +{ + return okfn(net, sk, skb); +} + static inline int nf_hook(u_int8_t pf, unsigned int hook, struct net *net, struct sock *sk, struct sk_buff *skb, struct net_device *indev, struct net_device *outdev, -- cgit v1.2.3 From dc6ef6be52154490c5c03f742e28bc781cc751b2 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Fri, 16 Oct 2015 13:00:01 -0700 Subject: tcp: do not set queue_mapping on SYNACK At the time of commit fff326990789 ("tcp: reflect SYN queue_mapping into SYNACK packets") we had little ways to cope with SYN floods. We no longer need to reflect incoming skb queue mappings, and instead can pick a TX queue based on cpu cooking the SYNACK, with normal XPS affinities. Note that all SYNACK retransmits were picking TX queue 0, this no longer is a win given that SYNACK rtx are now distributed on all cpus. Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- include/net/tcp.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/net/tcp.h b/include/net/tcp.h index a6be56d5f0e3..eed94fc355c1 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -1716,7 +1716,7 @@ struct tcp_request_sock_ops { __u32 (*init_seq)(const struct sk_buff *skb); int (*send_synack)(const struct sock *sk, struct dst_entry *dst, struct flowi *fl, struct request_sock *req, - u16 queue_mapping, struct tcp_fastopen_cookie *foc, + struct tcp_fastopen_cookie *foc, bool attach_req); }; -- cgit v1.2.3 From b3958b9e18140457b5600b03619e4c2e530761fe Mon Sep 17 00:00:00 2001 From: stephen hemminger Date: Fri, 16 Oct 2015 16:12:34 -0700 Subject: uapi: add mpls_iptunnel.h Add missing rule to export mpls iptunnel header needed by iproute2 Signed-off-by: Stephen Hemminger Acked-by: Roopa Prabhu Signed-off-by: David S. Miller --- include/uapi/linux/Kbuild | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/uapi/linux/Kbuild b/include/uapi/linux/Kbuild index f7b2db44eb4b..70d89230b641 100644 --- a/include/uapi/linux/Kbuild +++ b/include/uapi/linux/Kbuild @@ -263,6 +263,7 @@ header-y += minix_fs.h header-y += mman.h header-y += mmtimer.h header-y += mpls.h +header-y += mpls_iptunnel.h header-y += mqueue.h header-y += mroute6.h header-y += mroute.h -- cgit v1.2.3 From cad20c278085d893ebd616cd20c0747a8e9d53c7 Mon Sep 17 00:00:00 2001 From: Johan Hedberg Date: Mon, 12 Oct 2015 13:36:19 +0200 Subject: Bluetooth: Don't use remote address type to decide IRK persistency There are LE devices on the market that start off by announcing their public address and then once paired switch to using private address. To be interoperable with such devices we should simply trust the fact that we're receiving an IRK from them to indicate that they may use private addresses in the future. Instead, simply tie the persistency to the bonding/no-bonding information the same way as for LTKs and CSRKs. Signed-off-by: Johan Hedberg Signed-off-by: Marcel Holtmann --- include/net/bluetooth/hci_core.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/net/bluetooth/hci_core.h b/include/net/bluetooth/hci_core.h index f28470e59682..989c72aabc45 100644 --- a/include/net/bluetooth/hci_core.h +++ b/include/net/bluetooth/hci_core.h @@ -1458,7 +1458,7 @@ void mgmt_remote_name(struct hci_dev *hdev, bdaddr_t *bdaddr, u8 link_type, void mgmt_discovering(struct hci_dev *hdev, u8 discovering); bool mgmt_powering_down(struct hci_dev *hdev); void mgmt_new_ltk(struct hci_dev *hdev, struct smp_ltk *key, bool persistent); -void mgmt_new_irk(struct hci_dev *hdev, struct smp_irk *irk); +void mgmt_new_irk(struct hci_dev *hdev, struct smp_irk *irk, bool persistent); void mgmt_new_csrk(struct hci_dev *hdev, struct smp_csrk *csrk, bool persistent); void mgmt_new_conn_param(struct hci_dev *hdev, bdaddr_t *bdaddr, -- cgit v1.2.3 From 7e995b9eadbe226e355b785a765fd90fe0487414 Mon Sep 17 00:00:00 2001 From: Marcel Holtmann Date: Sat, 17 Oct 2015 16:00:26 +0200 Subject: Bluetooth: Add new quirk for non-persistent diagnostic settings If the diagnostic settings are not persistent over HCI Reset, then this quirk can be used to tell the Bluetoth core about it. This will ensure that the settings are programmed correctly when the controller is powered up. Signed-off-by: Marcel Holtmann Signed-off-by: Johan Hedberg --- include/net/bluetooth/hci.h | 9 +++++++++ 1 file changed, 9 insertions(+) (limited to 'include') diff --git a/include/net/bluetooth/hci.h b/include/net/bluetooth/hci.h index a26ff28ca878..b59971c5cb71 100644 --- a/include/net/bluetooth/hci.h +++ b/include/net/bluetooth/hci.h @@ -170,6 +170,15 @@ enum { * during the hdev->setup vendor callback. */ HCI_QUIRK_SIMULTANEOUS_DISCOVERY, + + /* When this quirk is set, the enabling of diagnostic mode is + * not persistent over HCI Reset. Every time the controller + * is brought up it needs to be reprogrammed. + * + * This quirk can be set before hci_register_dev is called or + * during the hdev->setup vendor callback. + */ + HCI_QUIRK_NON_PERSISTENT_DIAG, }; /* HCI device flags */ -- cgit v1.2.3 From e131d74a3afe2b44c3bc59dc4ff06bfd0481ab1a Mon Sep 17 00:00:00 2001 From: Marcel Holtmann Date: Tue, 20 Oct 2015 02:30:47 +0200 Subject: Bluetooth: Add support setup stage internal notification event Before the vendor specific setup stage is triggered call back into the core to trigger an internal notification event. That event is used to send an index update to the monitor interface. With that specific event it is possible to update userspace with manufacturer information before any HCI command has been executed. This is useful for early stage debugging of vendor specific initialization sequences. Signed-off-by: Marcel Holtmann Signed-off-by: Johan Hedberg --- include/net/bluetooth/hci.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/net/bluetooth/hci.h b/include/net/bluetooth/hci.h index b59971c5cb71..0205b80cc90b 100644 --- a/include/net/bluetooth/hci.h +++ b/include/net/bluetooth/hci.h @@ -46,6 +46,7 @@ #define HCI_DEV_RESUME 6 #define HCI_DEV_OPEN 7 #define HCI_DEV_CLOSE 8 +#define HCI_DEV_SETUP 9 /* HCI notify events */ #define HCI_NOTIFY_CONN_ADD 1 -- cgit v1.2.3 From bf513fd6fc609590b7835c0dba624ccb9f8f9214 Mon Sep 17 00:00:00 2001 From: Alexander Aring Date: Tue, 13 Oct 2015 13:42:56 +0200 Subject: 6lowpan: introduce LOWPAN_IPHC_MAX_HC_BUF_LEN This patch introduces the LOWPAN_IPHC_MAX_HC_BUF_LEN define which represent the worst-case supported IPHC buffer length. It's used to allocate the stack buffer space for creating the IPHC header. Signed-off-by: Alexander Aring Acked-by: Jukka Rissanen Signed-off-by: Marcel Holtmann --- include/net/6lowpan.h | 8 ++++++++ 1 file changed, 8 insertions(+) (limited to 'include') diff --git a/include/net/6lowpan.h b/include/net/6lowpan.h index 07db532696df..aa5a82380e4e 100644 --- a/include/net/6lowpan.h +++ b/include/net/6lowpan.h @@ -64,12 +64,20 @@ #define EUI64_ADDR_LEN 8 #define LOWPAN_NHC_MAX_ID_LEN 1 +/* Maximum next header compression length which we currently support inclusive + * possible inline data. + */ +#define LOWPAN_NHC_MAX_HDR_LEN (sizeof(struct udphdr)) /* Max IPHC Header len without IPv6 hdr specific inline data. * Useful for getting the "extra" bytes we need at worst case compression. * * LOWPAN_IPHC + CID + LOWPAN_NHC_MAX_ID_LEN */ #define LOWPAN_IPHC_MAX_HEADER_LEN (2 + 1 + LOWPAN_NHC_MAX_ID_LEN) +/* Maximum worst case IPHC header buffer size */ +#define LOWPAN_IPHC_MAX_HC_BUF_LEN (sizeof(struct ipv6hdr) + \ + LOWPAN_IPHC_MAX_HEADER_LEN + \ + LOWPAN_NHC_MAX_HDR_LEN) /* * ipv6 address based on mac -- cgit v1.2.3 From a6f773891a836abfa16fcbb8af14c29c3e109336 Mon Sep 17 00:00:00 2001 From: Alexander Aring Date: Tue, 13 Oct 2015 13:42:57 +0200 Subject: 6lowpan: cleanup lowpan_header_compress This patch changes the lowpan_header_compress function by removing unused parameters like "len" and drop static value parameters of protocol type. Instead we really check the protocol type inside inside the skb structure. Also we drop the use of IEEE802154_ADDR_LEN which is link-layer specific. Instead we using EUI64_ADDR_LEN which should always the default case for now. Signed-off-by: Alexander Aring Acked-by: Jukka Rissanen Signed-off-by: Marcel Holtmann --- include/net/6lowpan.h | 30 +++++++++++++++++++++++------- 1 file changed, 23 insertions(+), 7 deletions(-) (limited to 'include') diff --git a/include/net/6lowpan.h b/include/net/6lowpan.h index aa5a82380e4e..6f1e0bd3d211 100644 --- a/include/net/6lowpan.h +++ b/include/net/6lowpan.h @@ -258,7 +258,7 @@ struct lowpan_802154_cb *lowpan_802154_cb(const struct sk_buff *skb) #ifdef DEBUG /* print data in line */ static inline void raw_dump_inline(const char *caller, char *msg, - unsigned char *buf, int len) + const unsigned char *buf, int len) { if (msg) pr_debug("%s():%s: ", caller, msg); @@ -273,7 +273,7 @@ static inline void raw_dump_inline(const char *caller, char *msg, * ... */ static inline void raw_dump_table(const char *caller, char *msg, - unsigned char *buf, int len) + const unsigned char *buf, int len) { if (msg) pr_debug("%s():%s:\n", caller, msg); @@ -282,9 +282,9 @@ static inline void raw_dump_table(const char *caller, char *msg, } #else static inline void raw_dump_table(const char *caller, char *msg, - unsigned char *buf, int len) { } + const unsigned char *buf, int len) { } static inline void raw_dump_inline(const char *caller, char *msg, - unsigned char *buf, int len) { } + const unsigned char *buf, int len) { } #endif static inline int lowpan_fetch_skb_u8(struct sk_buff *skb, u8 *val) @@ -325,8 +325,24 @@ lowpan_header_decompress(struct sk_buff *skb, struct net_device *dev, const u8 saddr_len, const u8 *daddr, const u8 daddr_type, const u8 daddr_len, u8 iphc0, u8 iphc1); -int lowpan_header_compress(struct sk_buff *skb, struct net_device *dev, - unsigned short type, const void *_daddr, - const void *_saddr, unsigned int len); + +/** + * lowpan_header_compress - replace IPv6 header with 6LoWPAN header + * + * This function replaces the IPv6 header which should be pointed at + * skb->data and skb_network_header, with the IPHC 6LoWPAN header. + * The caller need to be sure that the sk buffer is not shared and at have + * at least a headroom which is smaller or equal LOWPAN_IPHC_MAX_HEADER_LEN, + * which is the IPHC "more bytes than IPv6 header" at worst case. + * + * @skb: the buffer which should be manipulate. + * @dev: the lowpan net device pointer. + * @daddr: destination lladdr of mac header which is used for compression + * methods. + * @saddr: source lladdr of mac header which is used for compression + * methods. + */ +int lowpan_header_compress(struct sk_buff *skb, const struct net_device *dev, + const void *daddr, const void *saddr); #endif /* __6LOWPAN_H__ */ -- cgit v1.2.3 From 8911d7748ca360ef96cb207cc5165eb9c08669e5 Mon Sep 17 00:00:00 2001 From: Alexander Aring Date: Tue, 13 Oct 2015 13:42:58 +0200 Subject: 6lowpan: cleanup lowpan_header_decompress This patch changes the lowpan_header_decompress function by removing inklayer related information from parameters. This is currently for supporting short and extended address for iphc handling in 802154. We don't support short address handling anyway right now, but there exists already code for handling short addresses in lowpan_header_decompress. The address parameters are also changed to a void pointer, so 6LoWPAN linklayer specific code can put complex structures as these parameters and cast it again inside the generic code by evaluating linklayer type before. The order is also changed by destination address at first and then source address, which is the same like all others functions where destination is always the first, memcpy, dev_hard_header, lowpan_header_compress, etc. This patch also moves the fetching of iphc values from 6LoWPAN linklayer specific code into the generic branch. Signed-off-by: Alexander Aring Acked-by: Jukka Rissanen Signed-off-by: Marcel Holtmann --- include/net/6lowpan.h | 24 ++++++++++++++++++------ include/net/mac802154.h | 10 ++++++++++ 2 files changed, 28 insertions(+), 6 deletions(-) (limited to 'include') diff --git a/include/net/6lowpan.h b/include/net/6lowpan.h index 6f1e0bd3d211..ac30ad3d8cd3 100644 --- a/include/net/6lowpan.h +++ b/include/net/6lowpan.h @@ -319,12 +319,24 @@ static inline void lowpan_push_hc_data(u8 **hc_ptr, const void *data, void lowpan_netdev_setup(struct net_device *dev, enum lowpan_lltypes lltype); -int -lowpan_header_decompress(struct sk_buff *skb, struct net_device *dev, - const u8 *saddr, const u8 saddr_type, - const u8 saddr_len, const u8 *daddr, - const u8 daddr_type, const u8 daddr_len, - u8 iphc0, u8 iphc1); +/** + * lowpan_header_decompress - replace 6LoWPAN header with IPv6 header + * + * This function replaces the IPHC 6LoWPAN header which should be pointed at + * skb->data and skb_network_header, with the IPv6 header. + * It would be nice that the caller have the necessary headroom of IPv6 header + * and greatest Transport layer header, this would reduce the overhead for + * reallocate headroom. + * + * @skb: the buffer which should be manipulate. + * @dev: the lowpan net device pointer. + * @daddr: destination lladdr of mac header which is used for compression + * methods. + * @saddr: source lladdr of mac header which is used for compression + * methods. + */ +int lowpan_header_decompress(struct sk_buff *skb, const struct net_device *dev, + const void *daddr, const void *saddr); /** * lowpan_header_compress - replace IPv6 header with 6LoWPAN header diff --git a/include/net/mac802154.h b/include/net/mac802154.h index 5718765cbd95..da574bbdc333 100644 --- a/include/net/mac802154.h +++ b/include/net/mac802154.h @@ -276,6 +276,16 @@ static inline void ieee802154_le64_to_be64(void *be64_dst, const void *le64_src) __put_unaligned_memmove64(swab64p(le64_src), be64_dst); } +/** + * ieee802154_le16_to_be16 - copies and convert le16 to be16 + * @be16_dst: be16 destination pointer + * @le16_src: le16 source pointer + */ +static inline void ieee802154_le16_to_be16(void *be16_dst, const void *le16_src) +{ + __put_unaligned_memmove16(swab16p(le16_src), be16_dst); +} + /** * ieee802154_alloc_hw - Allocate a new hardware device * -- cgit v1.2.3 From 478208e3b9988adc7ec2c480f237049aaf7c4609 Mon Sep 17 00:00:00 2001 From: Alexander Aring Date: Tue, 13 Oct 2015 13:42:59 +0200 Subject: 6lowpan: remove lowpan_fetch_skb_u8 This patch removes the lowpan_fetch_skb_u8 function for getting the iphc bytes. Instead we using the generic which has a len parameter to tell the amount of bytes to fetch. Signed-off-by: Alexander Aring Acked-by: Jukka Rissanen Signed-off-by: Marcel Holtmann --- include/net/6lowpan.h | 27 ++++++++++++++------------- 1 file changed, 14 insertions(+), 13 deletions(-) (limited to 'include') diff --git a/include/net/6lowpan.h b/include/net/6lowpan.h index ac30ad3d8cd3..4afdbb3ab6d8 100644 --- a/include/net/6lowpan.h +++ b/include/net/6lowpan.h @@ -287,19 +287,20 @@ static inline void raw_dump_inline(const char *caller, char *msg, const unsigned char *buf, int len) { } #endif -static inline int lowpan_fetch_skb_u8(struct sk_buff *skb, u8 *val) -{ - if (unlikely(!pskb_may_pull(skb, 1))) - return -EINVAL; - - *val = skb->data[0]; - skb_pull(skb, 1); - - return 0; -} - -static inline bool lowpan_fetch_skb(struct sk_buff *skb, - void *data, const unsigned int len) +/** + * lowpan_fetch_skb - getting inline data from 6LoWPAN header + * + * This function will pull data from sk buffer and put it into data to + * remove the 6LoWPAN inline data. This function returns true if the + * sk buffer is too small to pull the amount of data which is specified + * by len. + * + * @skb: the buffer where the inline data should be pulled from. + * @data: destination buffer for the inline data. + * @len: amount of data which should be pulled in bytes. + */ +static inline bool lowpan_fetch_skb(struct sk_buff *skb, void *data, + unsigned int len) { if (unlikely(!pskb_may_pull(skb, len))) return true; -- cgit v1.2.3 From 6350047eb8dbd3dcf0ff29a637ece96db8f59d8d Mon Sep 17 00:00:00 2001 From: Alexander Aring Date: Tue, 20 Oct 2015 08:31:22 +0200 Subject: 6lowpan: move IPHC functionality defines This patch removes the IPHC related defines for doing bit manipulation from global 6lowpan header to the iphc file which should the only one implementation which use these defines. Also move next header compression defines to their nhc implementation. Signed-off-by: Alexander Aring Signed-off-by: Marcel Holtmann --- include/net/6lowpan.h | 123 -------------------------------------------------- 1 file changed, 123 deletions(-) (limited to 'include') diff --git a/include/net/6lowpan.h b/include/net/6lowpan.h index 4afdbb3ab6d8..f127a92d1b94 100644 --- a/include/net/6lowpan.h +++ b/include/net/6lowpan.h @@ -56,11 +56,6 @@ #include #include -#define UIP_802154_SHORTADDR_LEN 2 /* compressed ipv6 address length */ -#define UIP_IPH_LEN 40 /* ipv6 fixed header size */ -#define UIP_PROTO_UDP 17 /* ipv6 next header value for UDP */ -#define UIP_FRAGH_LEN 8 /* ipv6 fragment header size */ - #define EUI64_ADDR_LEN 8 #define LOWPAN_NHC_MAX_ID_LEN 1 @@ -79,61 +74,6 @@ LOWPAN_IPHC_MAX_HEADER_LEN + \ LOWPAN_NHC_MAX_HDR_LEN) -/* - * ipv6 address based on mac - * second bit-flip (Universe/Local) is done according RFC2464 - */ -#define is_addr_mac_addr_based(a, m) \ - ((((a)->s6_addr[8]) == (((m)[0]) ^ 0x02)) && \ - (((a)->s6_addr[9]) == (m)[1]) && \ - (((a)->s6_addr[10]) == (m)[2]) && \ - (((a)->s6_addr[11]) == (m)[3]) && \ - (((a)->s6_addr[12]) == (m)[4]) && \ - (((a)->s6_addr[13]) == (m)[5]) && \ - (((a)->s6_addr[14]) == (m)[6]) && \ - (((a)->s6_addr[15]) == (m)[7])) - -/* - * check whether we can compress the IID to 16 bits, - * it's possible for unicast adresses with first 49 bits are zero only. - */ -#define lowpan_is_iid_16_bit_compressable(a) \ - ((((a)->s6_addr16[4]) == 0) && \ - (((a)->s6_addr[10]) == 0) && \ - (((a)->s6_addr[11]) == 0xff) && \ - (((a)->s6_addr[12]) == 0xfe) && \ - (((a)->s6_addr[13]) == 0)) - -/* check whether the 112-bit gid of the multicast address is mappable to: */ - -/* 48 bits, FFXX::00XX:XXXX:XXXX */ -#define lowpan_is_mcast_addr_compressable48(a) \ - ((((a)->s6_addr16[1]) == 0) && \ - (((a)->s6_addr16[2]) == 0) && \ - (((a)->s6_addr16[3]) == 0) && \ - (((a)->s6_addr16[4]) == 0) && \ - (((a)->s6_addr[10]) == 0)) - -/* 32 bits, FFXX::00XX:XXXX */ -#define lowpan_is_mcast_addr_compressable32(a) \ - ((((a)->s6_addr16[1]) == 0) && \ - (((a)->s6_addr16[2]) == 0) && \ - (((a)->s6_addr16[3]) == 0) && \ - (((a)->s6_addr16[4]) == 0) && \ - (((a)->s6_addr16[5]) == 0) && \ - (((a)->s6_addr[12]) == 0)) - -/* 8 bits, FF02::00XX */ -#define lowpan_is_mcast_addr_compressable8(a) \ - ((((a)->s6_addr[1]) == 2) && \ - (((a)->s6_addr16[1]) == 0) && \ - (((a)->s6_addr16[2]) == 0) && \ - (((a)->s6_addr16[3]) == 0) && \ - (((a)->s6_addr16[4]) == 0) && \ - (((a)->s6_addr16[5]) == 0) && \ - (((a)->s6_addr16[6]) == 0) && \ - (((a)->s6_addr[14]) == 0)) - #define lowpan_is_addr_broadcast(a) \ ((((a)[0]) == 0xFF) && \ (((a)[1]) == 0xFF) && \ @@ -158,69 +98,6 @@ static inline bool lowpan_is_iphc(u8 dispatch) return (dispatch & LOWPAN_DISPATCH_IPHC_MASK) == LOWPAN_DISPATCH_IPHC; } -#define LOWPAN_FRAG_TIMEOUT (HZ * 60) /* time-out 60 sec */ - -#define LOWPAN_FRAG1_HEAD_SIZE 0x4 -#define LOWPAN_FRAGN_HEAD_SIZE 0x5 - -/* - * Values of fields within the IPHC encoding first byte - * (C stands for compressed and I for inline) - */ -#define LOWPAN_IPHC_TF 0x18 - -#define LOWPAN_IPHC_FL_C 0x10 -#define LOWPAN_IPHC_TC_C 0x08 -#define LOWPAN_IPHC_NH_C 0x04 -#define LOWPAN_IPHC_TTL_1 0x01 -#define LOWPAN_IPHC_TTL_64 0x02 -#define LOWPAN_IPHC_TTL_255 0x03 -#define LOWPAN_IPHC_TTL_I 0x00 - - -/* Values of fields within the IPHC encoding second byte */ -#define LOWPAN_IPHC_CID 0x80 - -#define LOWPAN_IPHC_ADDR_00 0x00 -#define LOWPAN_IPHC_ADDR_01 0x01 -#define LOWPAN_IPHC_ADDR_02 0x02 -#define LOWPAN_IPHC_ADDR_03 0x03 - -#define LOWPAN_IPHC_SAC 0x40 -#define LOWPAN_IPHC_SAM 0x30 - -#define LOWPAN_IPHC_SAM_BIT 4 - -#define LOWPAN_IPHC_M 0x08 -#define LOWPAN_IPHC_DAC 0x04 -#define LOWPAN_IPHC_DAM_00 0x00 -#define LOWPAN_IPHC_DAM_01 0x01 -#define LOWPAN_IPHC_DAM_10 0x02 -#define LOWPAN_IPHC_DAM_11 0x03 - -#define LOWPAN_IPHC_DAM_BIT 0 -/* - * LOWPAN_UDP encoding (works together with IPHC) - */ -#define LOWPAN_NHC_UDP_MASK 0xF8 -#define LOWPAN_NHC_UDP_ID 0xF0 -#define LOWPAN_NHC_UDP_CHECKSUMC 0x04 -#define LOWPAN_NHC_UDP_CHECKSUMI 0x00 - -#define LOWPAN_NHC_UDP_4BIT_PORT 0xF0B0 -#define LOWPAN_NHC_UDP_4BIT_MASK 0xFFF0 -#define LOWPAN_NHC_UDP_8BIT_PORT 0xF000 -#define LOWPAN_NHC_UDP_8BIT_MASK 0xFF00 - -/* values for port compression, _with checksum_ ie bit 5 set to 0 */ -#define LOWPAN_NHC_UDP_CS_P_00 0xF0 /* all inline */ -#define LOWPAN_NHC_UDP_CS_P_01 0xF1 /* source 16bit inline, - dest = 0xF0 + 8 bit inline */ -#define LOWPAN_NHC_UDP_CS_P_10 0xF2 /* source = 0xF0 + 8bit inline, - dest = 16 bit inline */ -#define LOWPAN_NHC_UDP_CS_P_11 0xF3 /* source & dest = 0xF0B + 4bit inline */ -#define LOWPAN_NHC_UDP_CS_C 0x04 /* checksum elided */ - #define LOWPAN_PRIV_SIZE(llpriv_size) \ (sizeof(struct lowpan_priv) + llpriv_size) -- cgit v1.2.3 From 028b2a8c16c7c6a482075fe42275a44fbe5463fa Mon Sep 17 00:00:00 2001 From: Alexander Aring Date: Tue, 20 Oct 2015 08:31:23 +0200 Subject: 6lowpan: remove lowpan_is_addr_broadcast This macro is used at 802.15.4 6LoWPAN only and can be replaced by memcmp with the interface broadcast address. Signed-off-by: Alexander Aring Signed-off-by: Marcel Holtmann --- include/net/6lowpan.h | 10 ---------- 1 file changed, 10 deletions(-) (limited to 'include') diff --git a/include/net/6lowpan.h b/include/net/6lowpan.h index f127a92d1b94..cf3bc564ac03 100644 --- a/include/net/6lowpan.h +++ b/include/net/6lowpan.h @@ -74,16 +74,6 @@ LOWPAN_IPHC_MAX_HEADER_LEN + \ LOWPAN_NHC_MAX_HDR_LEN) -#define lowpan_is_addr_broadcast(a) \ - ((((a)[0]) == 0xFF) && \ - (((a)[1]) == 0xFF) && \ - (((a)[2]) == 0xFF) && \ - (((a)[3]) == 0xFF) && \ - (((a)[4]) == 0xFF) && \ - (((a)[5]) == 0xFF) && \ - (((a)[6]) == 0xFF) && \ - (((a)[7]) == 0xFF)) - #define LOWPAN_DISPATCH_IPV6 0x41 /* 01000001 = 65 */ #define LOWPAN_DISPATCH_IPHC 0x60 /* 011xxxxx = ... */ #define LOWPAN_DISPATCH_IPHC_MASK 0xe0 -- cgit v1.2.3 From 98a63aaf245e2522b0ddd86f38fb83883344bcaf Mon Sep 17 00:00:00 2001 From: Marcel Holtmann Date: Tue, 20 Oct 2015 23:25:42 +0200 Subject: Bluetooth: Introduce driver specific post init callback Some drivers might have to restore certain settings after the init procedure has been completed. This driver callback allows them to hook into that stage. This callback is run just before the controller is declared as powered up. Signed-off-by: Marcel Holtmann Signed-off-by: Johan Hedberg --- include/net/bluetooth/hci_core.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/net/bluetooth/hci_core.h b/include/net/bluetooth/hci_core.h index 989c72aabc45..44fb95685611 100644 --- a/include/net/bluetooth/hci_core.h +++ b/include/net/bluetooth/hci_core.h @@ -398,6 +398,7 @@ struct hci_dev { int (*send)(struct hci_dev *hdev, struct sk_buff *skb); void (*notify)(struct hci_dev *hdev, unsigned int evt); void (*hw_error)(struct hci_dev *hdev, u8 code); + int (*post_init)(struct hci_dev *hdev); int (*set_diag)(struct hci_dev *hdev, bool enable); int (*set_bdaddr)(struct hci_dev *hdev, const bdaddr_t *bdaddr); }; -- cgit v1.2.3 From 8ce783dc5ea3af3a213ac9b4d9d2ccfeeb9c9058 Mon Sep 17 00:00:00 2001 From: Johan Hedberg Date: Wed, 21 Oct 2015 15:21:31 +0300 Subject: Bluetooth: Fix missing hdev locking for LE scan cleanup The hci_conn objects don't have a dedicated lock themselves but rely on the caller to hold the hci_dev lock for most types of access. The hci_conn_timeout() function has so far sent certain HCI commands based on the hci_conn state which has been possible without holding the hci_dev lock. The recent changes to do LE scanning before connect attempts added even more operations to hci_conn and hci_dev from hci_conn_timeout, thereby exposing potential race conditions with the hci_dev and hci_conn states. As an example of such a race, here there's a timeout but an l2cap_sock_connect() call manages to race with the cleanup routine: [Oct21 08:14] l2cap_chan_timeout: chan ee4b12c0 state BT_CONNECT [ +0.000004] l2cap_chan_close: chan ee4b12c0 state BT_CONNECT [ +0.000002] l2cap_chan_del: chan ee4b12c0, conn f3141580, err 111, state BT_CONNECT [ +0.000002] l2cap_sock_teardown_cb: chan ee4b12c0 state BT_CONNECT [ +0.000005] l2cap_chan_put: chan ee4b12c0 orig refcnt 4 [ +0.000010] hci_conn_drop: hcon f53d56e0 orig refcnt 1 [ +0.000013] l2cap_chan_put: chan ee4b12c0 orig refcnt 3 [ +0.000063] hci_conn_timeout: hcon f53d56e0 state BT_CONNECT [ +0.000049] hci_conn_params_del: addr ee:0d:30:09:53:1f (type 1) [ +0.000002] hci_chan_list_flush: hcon f53d56e0 [ +0.000001] hci_chan_del: hci0 hcon f53d56e0 chan f4e7ccc0 [ +0.004528] l2cap_sock_create: sock e708fc00 [ +0.000023] l2cap_chan_create: chan ee4b1770 [ +0.000001] l2cap_chan_hold: chan ee4b1770 orig refcnt 1 [ +0.000002] l2cap_sock_init: sk ee4b3390 [ +0.000029] l2cap_sock_bind: sk ee4b3390 [ +0.000010] l2cap_sock_setsockopt: sk ee4b3390 [ +0.000037] l2cap_sock_connect: sk ee4b3390 [ +0.000002] l2cap_chan_connect: 00:02:72:d9:e5:8b -> ee:0d:30:09:53:1f (type 2) psm 0x00 [ +0.000002] hci_get_route: 00:02:72:d9:e5:8b -> ee:0d:30:09:53:1f [ +0.000001] hci_dev_hold: hci0 orig refcnt 8 [ +0.000003] hci_conn_hold: hcon f53d56e0 orig refcnt 0 Above the l2cap_chan_connect() shouldn't have been able to reach the hci_conn f53d56e0 anymore but since hci_conn_timeout didn't do proper locking that's not the case. The end result is a reference to hci_conn that's not in the conn_hash list, resulting in list corruption when trying to remove it later: [Oct21 08:15] l2cap_chan_timeout: chan ee4b1770 state BT_CONNECT [ +0.000004] l2cap_chan_close: chan ee4b1770 state BT_CONNECT [ +0.000003] l2cap_chan_del: chan ee4b1770, conn f3141580, err 111, state BT_CONNECT [ +0.000001] l2cap_sock_teardown_cb: chan ee4b1770 state BT_CONNECT [ +0.000005] l2cap_chan_put: chan ee4b1770 orig refcnt 4 [ +0.000002] hci_conn_drop: hcon f53d56e0 orig refcnt 1 [ +0.000015] l2cap_chan_put: chan ee4b1770 orig refcnt 3 [ +0.000038] hci_conn_timeout: hcon f53d56e0 state BT_CONNECT [ +0.000003] hci_chan_list_flush: hcon f53d56e0 [ +0.000002] hci_conn_hash_del: hci0 hcon f53d56e0 [ +0.000001] ------------[ cut here ]------------ [ +0.000461] WARNING: CPU: 0 PID: 1782 at lib/list_debug.c:56 __list_del_entry+0x3f/0x71() [ +0.000839] list_del corruption, f53d56e0->prev is LIST_POISON2 (00000200) The necessary fix is unfortunately more complicated than just adding hci_dev_lock/unlock calls to the hci_conn_timeout() call path. Particularly, the hci_conn_del() API, which expects the hci_dev lock to be held, performs a cancel_delayed_work_sync(&hcon->disc_work) which would lead to a deadlock if the hci_conn_timeout() call path tries to acquire the same lock. This patch solves the problem by deferring the cleanup work to a separate work callback. To protect against the hci_dev or hci_conn going away meanwhile temporary references are taken with the help of hci_dev_hold() and hci_conn_get(). Signed-off-by: Johan Hedberg Signed-off-by: Marcel Holtmann Cc: stable@vger.kernel.org # 4.3 --- include/net/bluetooth/hci_core.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/net/bluetooth/hci_core.h b/include/net/bluetooth/hci_core.h index 44fb95685611..0015d087d8b1 100644 --- a/include/net/bluetooth/hci_core.h +++ b/include/net/bluetooth/hci_core.h @@ -471,6 +471,7 @@ struct hci_conn { struct delayed_work auto_accept_work; struct delayed_work idle_work; struct delayed_work le_conn_timeout; + struct work_struct le_scan_cleanup; struct device dev; struct dentry *debugfs; -- cgit v1.2.3 From f672258391b42a5c7cc2732c9c063e56a85c8dbe Mon Sep 17 00:00:00 2001 From: Yuchung Cheng Date: Fri, 16 Oct 2015 21:57:42 -0700 Subject: tcp: track min RTT using windowed min-filter Kathleen Nichols' algorithm for tracking the minimum RTT of a data stream over some measurement window. It uses constant space and constant time per update. Yet it almost always delivers the same minimum as an implementation that has to keep all the data in the window. The measurement window is tunable via sysctl.net.ipv4.tcp_min_rtt_wlen with a default value of 5 minutes. The algorithm keeps track of the best, 2nd best & 3rd best min values, maintaining an invariant that the measurement time of the n'th best >= n-1'th best. It also makes sure that the three values are widely separated in the time window since that bounds the worse case error when that data is monotonically increasing over the window. Upon getting a new min, we can forget everything earlier because it has no value - the new min is less than everything else in the window by definition and it's the most recent. So we restart fresh on every new min and overwrites the 2nd & 3rd choices. The same property holds for the 2nd & 3rd best. Therefore we have to maintain two invariants to maximize the information in the samples, one on values (1st.v <= 2nd.v <= 3rd.v) and the other on times (now-win <=1st.t <= 2nd.t <= 3rd.t <= now). These invariants determine the structure of the code The RTT input to the windowed filter is the minimum RTT measured from ACK or SACK, or as the last resort from TCP timestamps. The accessor tcp_min_rtt() returns the minimum RTT seen in the window. ~0U indicates it is not available. The minimum is 1usec even if the true RTT is below that. Signed-off-by: Yuchung Cheng Signed-off-by: Neal Cardwell Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- include/linux/tcp.h | 3 +++ include/net/tcp.h | 7 +++++++ 2 files changed, 10 insertions(+) (limited to 'include') diff --git a/include/linux/tcp.h b/include/linux/tcp.h index 86a7edaa6797..90edef5508f9 100644 --- a/include/linux/tcp.h +++ b/include/linux/tcp.h @@ -217,6 +217,9 @@ struct tcp_sock { u32 mdev_max_us; /* maximal mdev for the last rtt period */ u32 rttvar_us; /* smoothed mdev_max */ u32 rtt_seq; /* sequence number to update rttvar */ + struct rtt_meas { + u32 rtt, ts; /* RTT in usec and sampling time in jiffies. */ + } rtt_min[3]; u32 packets_out; /* Packets which are "in flight" */ u32 retrans_out; /* Retransmitted packets out */ diff --git a/include/net/tcp.h b/include/net/tcp.h index eed94fc355c1..4a43152229ea 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -279,6 +279,7 @@ extern int sysctl_tcp_limit_output_bytes; extern int sysctl_tcp_challenge_ack_limit; extern unsigned int sysctl_tcp_notsent_lowat; extern int sysctl_tcp_min_tso_segs; +extern int sysctl_tcp_min_rtt_wlen; extern int sysctl_tcp_autocorking; extern int sysctl_tcp_invalid_ratelimit; extern int sysctl_tcp_pacing_ss_ratio; @@ -671,6 +672,12 @@ static inline bool tcp_ca_dst_locked(const struct dst_entry *dst) return dst_metric_locked(dst, RTAX_CC_ALGO); } +/* Minimum RTT in usec. ~0 means not available. */ +static inline u32 tcp_min_rtt(const struct tcp_sock *tp) +{ + return tp->rtt_min[0].rtt; +} + /* Compute the actual receive window we are currently advertising. * Rcv_nxt can be after the window if our peer push more data * than the offered window. -- cgit v1.2.3 From af82f4e84866ecd360a53f770d6217637116e6c1 Mon Sep 17 00:00:00 2001 From: Yuchung Cheng Date: Fri, 16 Oct 2015 21:57:43 -0700 Subject: tcp: remove tcp_mark_lost_retrans() Remove the existing lost retransmit detection because RACK subsumes it completely. This also stops the overloading the ack_seq field of the skb control block. Signed-off-by: Yuchung Cheng Signed-off-by: Neal Cardwell Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- include/linux/tcp.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include') diff --git a/include/linux/tcp.h b/include/linux/tcp.h index 90edef5508f9..8c54863dfc38 100644 --- a/include/linux/tcp.h +++ b/include/linux/tcp.h @@ -283,8 +283,6 @@ struct tcp_sock { int lost_cnt_hint; u32 retransmit_high; /* L-bits may be on up to this seqno */ - u32 lost_retrans_low; /* Sent seq after any rxmit (lowest) */ - u32 prior_ssthresh; /* ssthresh saved at recovery start */ u32 high_seq; /* snd_nxt at onset of congestion */ -- cgit v1.2.3 From 625a5e109a3ed6f36a1008a43069a3462b44a424 Mon Sep 17 00:00:00 2001 From: Yuchung Cheng Date: Fri, 16 Oct 2015 21:57:45 -0700 Subject: tcp: skb_mstamp_after helper a helper to prepare the first main RACK patch. Signed-off-by: Yuchung Cheng Signed-off-by: Neal Cardwell Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- include/linux/skbuff.h | 9 +++++++++ 1 file changed, 9 insertions(+) (limited to 'include') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 4398411236f1..24f4dfd94c51 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -463,6 +463,15 @@ static inline u32 skb_mstamp_us_delta(const struct skb_mstamp *t1, return delta_us; } +static inline bool skb_mstamp_after(const struct skb_mstamp *t1, + const struct skb_mstamp *t0) +{ + s32 diff = t1->stamp_jiffies - t0->stamp_jiffies; + + if (!diff) + diff = t1->stamp_us - t0->stamp_us; + return diff > 0; +} /** * struct sk_buff - socket buffer -- cgit v1.2.3 From 659a8ad56f490279f0efee43a62ffa1ac914a4e0 Mon Sep 17 00:00:00 2001 From: Yuchung Cheng Date: Fri, 16 Oct 2015 21:57:46 -0700 Subject: tcp: track the packet timings in RACK This patch is the first half of the RACK loss recovery. RACK loss recovery uses the notion of time instead of packet sequence (FACK) or counts (dupthresh). It's inspired by the previous FACK heuristic in tcp_mark_lost_retrans(): when a limited transmit (new data packet) is sacked, then current retransmitted sequence below the newly sacked sequence must been lost, since at least one round trip time has elapsed. But it has several limitations: 1) can't detect tail drops since it depends on limited transmit 2) is disabled upon reordering (assumes no reordering) 3) only enabled in fast recovery ut not timeout recovery RACK (Recently ACK) addresses these limitations with the notion of time instead: a packet P1 is lost if a later packet P2 is s/acked, as at least one round trip has passed. Since RACK cares about the time sequence instead of the data sequence of packets, it can detect tail drops when later retransmission is s/acked while FACK or dupthresh can't. For reordering RACK uses a dynamically adjusted reordering window ("reo_wnd") to reduce false positives on ever (small) degree of reordering. This patch implements tcp_advanced_rack() which tracks the most recent transmission time among the packets that have been delivered (ACKed or SACKed) in tp->rack.mstamp. This timestamp is the key to determine which packet has been lost. Consider an example that the sender sends six packets: T1: P1 (lost) T2: P2 T3: P3 T4: P4 T100: sack of P2. rack.mstamp = T2 T101: retransmit P1 T102: sack of P2,P3,P4. rack.mstamp = T4 T205: ACK of P4 since the hole is repaired. rack.mstamp = T101 We need to be careful about spurious retransmission because it may falsely advance tp->rack.mstamp by an RTT or an RTO, causing RACK to falsely mark all packets lost, just like a spurious timeout. We identify spurious retransmission by the ACK's TS echo value. If TS option is not applicable but the retransmission is acknowledged less than min-RTT ago, it is likely to be spurious. We refrain from using the transmission time of these spurious retransmissions. The second half is implemented in the next patch that marks packet lost using RACK timestamp. Signed-off-by: Yuchung Cheng Signed-off-by: Neal Cardwell Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- include/linux/tcp.h | 6 ++++++ include/net/tcp.h | 5 +++++ 2 files changed, 11 insertions(+) (limited to 'include') diff --git a/include/linux/tcp.h b/include/linux/tcp.h index 8c54863dfc38..5dce9705fe84 100644 --- a/include/linux/tcp.h +++ b/include/linux/tcp.h @@ -194,6 +194,12 @@ struct tcp_sock { u32 window_clamp; /* Maximal window to advertise */ u32 rcv_ssthresh; /* Current window clamp */ + /* Information of the most recently (s)acked skb */ + struct tcp_rack { + struct skb_mstamp mstamp; /* (Re)sent time of the skb */ + u8 advanced; /* mstamp advanced since last lost marking */ + u8 reord; /* reordering detected */ + } rack; u16 advmss; /* Advertised MSS */ u8 unused; u8 nonagle : 4,/* Disable Nagle algorithm? */ diff --git a/include/net/tcp.h b/include/net/tcp.h index 4a43152229ea..3c3a9fe057d3 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -1750,6 +1750,11 @@ int tcpv4_offload_init(void); void tcp_v4_init(void); void tcp_init(void); +/* tcp_recovery.c */ + +extern void tcp_rack_advance(struct tcp_sock *tp, + const struct skb_mstamp *xmit_time, u8 sacked); + /* * Save and compile IPv4 options, return a pointer to it */ -- cgit v1.2.3 From 4f41b1c58a32537542f14c1150099131613a5e8a Mon Sep 17 00:00:00 2001 From: Yuchung Cheng Date: Fri, 16 Oct 2015 21:57:47 -0700 Subject: tcp: use RACK to detect losses This patch implements the second half of RACK that uses the the most recent transmit time among all delivered packets to detect losses. tcp_rack_mark_lost() is called upon receiving a dubious ACK. It then checks if an not-yet-sacked packet was sent at least "reo_wnd" prior to the sent time of the most recently delivered. If so the packet is deemed lost. The "reo_wnd" reordering window starts with 1msec for fast loss detection and changes to min-RTT/4 when reordering is observed. We found 1msec accommodates well on tiny degree of reordering (<3 pkts) on faster links. We use min-RTT instead of SRTT because reordering is more of a path property but SRTT can be inflated by self-inflicated congestion. The factor of 4 is borrowed from the delayed early retransmit and seems to work reasonably well. Since RACK is still experimental, it is now used as a supplemental loss detection on top of existing algorithms. It is only effective after the fast recovery starts or after the timeout occurs. The fast recovery is still triggered by FACK and/or dupack threshold instead of RACK. We introduce a new sysctl net.ipv4.tcp_recovery for future experiments of loss recoveries. For now RACK can be disabled by setting it to 0. Signed-off-by: Yuchung Cheng Signed-off-by: Neal Cardwell Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- include/net/tcp.h | 9 +++++++++ 1 file changed, 9 insertions(+) (limited to 'include') diff --git a/include/net/tcp.h b/include/net/tcp.h index 3c3a9fe057d3..11e320412216 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -567,6 +567,7 @@ void tcp_resume_early_retransmit(struct sock *sk); void tcp_rearm_rto(struct sock *sk); void tcp_synack_rtt_meas(struct sock *sk, struct request_sock *req); void tcp_reset(struct sock *sk); +void tcp_skb_mark_lost_uncond_verify(struct tcp_sock *tp, struct sk_buff *skb); /* tcp_timer.c */ void tcp_init_xmit_timers(struct sock *); @@ -1752,6 +1753,14 @@ void tcp_init(void); /* tcp_recovery.c */ +/* Flags to enable various loss recovery features. See below */ +extern int sysctl_tcp_recovery; + +/* Use TCP RACK to detect (some) tail and retransmit losses */ +#define TCP_RACK_LOST_RETRANS 0x1 + +extern int tcp_rack_mark_lost(struct sock *sk); + extern void tcp_rack_advance(struct tcp_sock *tp, const struct skb_mstamp *xmit_time, u8 sacked); -- cgit v1.2.3 From 1b51c7b6e878a2df6fdb5bcf51f966eb46a330e0 Mon Sep 17 00:00:00 2001 From: Johan Hedberg Date: Wed, 21 Oct 2015 18:03:00 +0300 Subject: Bluetooth: Add hci_conn_hash_lookup_le() helper function Many of the existing LE connection lookups are forced to use hci_conn_hash_lookup_ba() which doesn't take into account the address type. What's worse, most of the users don't bother checking that the returned address type matches what was wanted. This patch adds a new helper API to look up LE connections based on their address and address type, paving the way to have the hci_conn_hash_lookup_ba() users converted to do more precise lookups. Signed-off-by: Johan Hedberg Signed-off-by: Marcel Holtmann --- include/net/bluetooth/hci_core.h | 24 ++++++++++++++++++++++++ 1 file changed, 24 insertions(+) (limited to 'include') diff --git a/include/net/bluetooth/hci_core.h b/include/net/bluetooth/hci_core.h index 0015d087d8b1..32bb281e6aa6 100644 --- a/include/net/bluetooth/hci_core.h +++ b/include/net/bluetooth/hci_core.h @@ -794,6 +794,30 @@ static inline struct hci_conn *hci_conn_hash_lookup_ba(struct hci_dev *hdev, return NULL; } +static inline struct hci_conn *hci_conn_hash_lookup_le(struct hci_dev *hdev, + bdaddr_t *ba, + __u8 ba_type) +{ + struct hci_conn_hash *h = &hdev->conn_hash; + struct hci_conn *c; + + rcu_read_lock(); + + list_for_each_entry_rcu(c, &h->list, list) { + if (c->type != LE_LINK) + continue; + + if (ba_type == c->dst_type && !bacmp(&c->dst, ba)) { + rcu_read_unlock(); + return c; + } + } + + rcu_read_unlock(); + + return NULL; +} + static inline struct hci_conn *hci_conn_hash_lookup_state(struct hci_dev *hdev, __u8 type, __u16 state) { -- cgit v1.2.3 From 17bc08f0d1b17d6d5e4967c1b430af627c5f2041 Mon Sep 17 00:00:00 2001 From: Johan Hedberg Date: Wed, 21 Oct 2015 18:03:10 +0300 Subject: Bluetooth: Remove unnecessary hci_explicit_connect_lookup function There's only one user of this helper which can be replaces with a call to hci_pend_le_action_lookup() and a check for params->explicit_connect. Signed-off-by: Johan Hedberg Signed-off-by: Marcel Holtmann --- include/net/bluetooth/hci_core.h | 3 --- 1 file changed, 3 deletions(-) (limited to 'include') diff --git a/include/net/bluetooth/hci_core.h b/include/net/bluetooth/hci_core.h index 32bb281e6aa6..1878d0a96333 100644 --- a/include/net/bluetooth/hci_core.h +++ b/include/net/bluetooth/hci_core.h @@ -1042,9 +1042,6 @@ void hci_conn_params_clear_disabled(struct hci_dev *hdev); struct hci_conn_params *hci_pend_le_action_lookup(struct list_head *list, bdaddr_t *addr, u8 addr_type); -struct hci_conn_params *hci_explicit_connect_lookup(struct hci_dev *hdev, - bdaddr_t *addr, - u8 addr_type); void hci_uuids_clear(struct hci_dev *hdev); -- cgit v1.2.3 From b1974ed05ea90264d534a200e8a13932ad55f8b8 Mon Sep 17 00:00:00 2001 From: "Arad, Ronen" Date: Mon, 19 Oct 2015 09:23:28 -0700 Subject: netlink: Rightsize IFLA_AF_SPEC size calculation if_nlmsg_size() overestimates the minimum allocation size of netlink dump request (when called from rtnl_calcit()) or the size of the message (when called from rtnl_getlink()). This is because ext_filter_mask is not supported by rtnl_link_get_af_size() and rtnl_link_get_size(). The over-estimation is significant when at least one netdev has many VLANs configured (8 bytes for each configured VLAN). This patch-set "rightsizes" the protocol specific attribute size calculation by propagating ext_filter_mask to rtnl_link_get_af_size() and adding this a argument to get_link_af_size op in rtnl_af_ops. Bridge module already used filtering aware sizing for notifications. br_get_link_af_size_filtered() is consistent with the modified get_link_af_size op so it replaces br_get_link_af_size() in br_af_ops. br_get_link_af_size() becomes unused and thus removed. Signed-off-by: Ronen Arad Acked-by: Sridhar Samudrala Signed-off-by: David S. Miller --- include/net/rtnetlink.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/net/rtnetlink.h b/include/net/rtnetlink.h index aff6ceb891a9..2f87c1ba13de 100644 --- a/include/net/rtnetlink.h +++ b/include/net/rtnetlink.h @@ -124,7 +124,8 @@ struct rtnl_af_ops { int (*fill_link_af)(struct sk_buff *skb, const struct net_device *dev, u32 ext_filter_mask); - size_t (*get_link_af_size)(const struct net_device *dev); + size_t (*get_link_af_size)(const struct net_device *dev, + u32 ext_filter_mask); int (*validate_link_af)(const struct net_device *dev, const struct nlattr *attr); -- cgit v1.2.3 From e2aacd963a06fc558a809ecb62f5833e6c340b28 Mon Sep 17 00:00:00 2001 From: Vivien Didelot Date: Tue, 20 Oct 2015 10:08:59 -0400 Subject: net: mdio-gpio: move platform data header This header file only contains the platform data structure definition, so move it to the include/linux/platform_data/ directory. Signed-off-by: Vivien Didelot Signed-off-by: David S. Miller --- include/linux/mdio-gpio.h | 33 --------------------------------- include/linux/platform_data/mdio-gpio.h | 33 +++++++++++++++++++++++++++++++++ 2 files changed, 33 insertions(+), 33 deletions(-) delete mode 100644 include/linux/mdio-gpio.h create mode 100644 include/linux/platform_data/mdio-gpio.h (limited to 'include') diff --git a/include/linux/mdio-gpio.h b/include/linux/mdio-gpio.h deleted file mode 100644 index 11f00cdabe3d..000000000000 --- a/include/linux/mdio-gpio.h +++ /dev/null @@ -1,33 +0,0 @@ -/* - * MDIO-GPIO bus platform data structures - * - * Copyright (C) 2008, Paulius Zaleckas - * - * This file is licensed under the terms of the GNU General Public License - * version 2. This program is licensed "as is" without any warranty of any - * kind, whether express or implied. - */ - -#ifndef __LINUX_MDIO_GPIO_H -#define __LINUX_MDIO_GPIO_H - -#include - -struct mdio_gpio_platform_data { - /* GPIO numbers for bus pins */ - unsigned int mdc; - unsigned int mdio; - unsigned int mdo; - - bool mdc_active_low; - bool mdio_active_low; - bool mdo_active_low; - - u32 phy_mask; - u32 phy_ignore_ta_mask; - int irqs[PHY_MAX_ADDR]; - /* reset callback */ - int (*reset)(struct mii_bus *bus); -}; - -#endif /* __LINUX_MDIO_GPIO_H */ diff --git a/include/linux/platform_data/mdio-gpio.h b/include/linux/platform_data/mdio-gpio.h new file mode 100644 index 000000000000..11f00cdabe3d --- /dev/null +++ b/include/linux/platform_data/mdio-gpio.h @@ -0,0 +1,33 @@ +/* + * MDIO-GPIO bus platform data structures + * + * Copyright (C) 2008, Paulius Zaleckas + * + * This file is licensed under the terms of the GNU General Public License + * version 2. This program is licensed "as is" without any warranty of any + * kind, whether express or implied. + */ + +#ifndef __LINUX_MDIO_GPIO_H +#define __LINUX_MDIO_GPIO_H + +#include + +struct mdio_gpio_platform_data { + /* GPIO numbers for bus pins */ + unsigned int mdc; + unsigned int mdio; + unsigned int mdo; + + bool mdc_active_low; + bool mdio_active_low; + bool mdo_active_low; + + u32 phy_mask; + u32 phy_ignore_ta_mask; + int irqs[PHY_MAX_ADDR]; + /* reset callback */ + int (*reset)(struct mii_bus *bus); +}; + +#endif /* __LINUX_MDIO_GPIO_H */ -- cgit v1.2.3 From dbf650b67bb4db1b95807d2aafe2d7cfafd458da Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Tue, 20 Oct 2015 13:17:40 -0700 Subject: tcp: fastopen: limit max_qlen Allowing an application to set whatever limit for the list of recently RST fastopen sessions [1] is not wise, as it open ways to deplete kernel memory. Cap the user provided limit by somaxconn sysctl, like listen() backlog. [1] https://tools.ietf.org/html/rfc7413#section-5.1 Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- include/linux/tcp.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/tcp.h b/include/linux/tcp.h index 5dce9705fe84..c906f4534581 100644 --- a/include/linux/tcp.h +++ b/include/linux/tcp.h @@ -392,8 +392,9 @@ static inline bool tcp_passive_fastopen(const struct sock *sk) static inline void fastopen_queue_tune(struct sock *sk, int backlog) { struct request_sock_queue *queue = &inet_csk(sk)->icsk_accept_queue; + int somaxconn = READ_ONCE(sock_net(sk)->core.sysctl_somaxconn); - queue->fastopenq.max_qlen = backlog; + queue->fastopenq.max_qlen = min_t(unsigned int, backlog, somaxconn); } static inline void tcp_saved_syn_free(struct tcp_sock *tp) -- cgit v1.2.3 From a43eec304259a6c637f4014a6d4767159b6a3aa3 Mon Sep 17 00:00:00 2001 From: Alexei Starovoitov Date: Tue, 20 Oct 2015 20:02:34 -0700 Subject: bpf: introduce bpf_perf_event_output() helper This helper is used to send raw data from eBPF program into special PERF_TYPE_SOFTWARE/PERF_COUNT_SW_BPF_OUTPUT perf_event. User space needs to perf_event_open() it (either for one or all cpus) and store FD into perf_event_array (similar to bpf_perf_event_read() helper) before eBPF program can send data into it. Today the programs triggered by kprobe collect the data and either store it into the maps or print it via bpf_trace_printk() where latter is the debug facility and not suitable to stream the data. This new helper replaces such bpf_trace_printk() usage and allows programs to have dedicated channel into user space for post-processing of the raw data collected. Signed-off-by: Alexei Starovoitov Signed-off-by: David S. Miller --- include/uapi/linux/bpf.h | 11 +++++++++++ include/uapi/linux/perf_event.h | 1 + 2 files changed, 12 insertions(+) (limited to 'include') diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index 564f1f091991..2e032426cfb7 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -287,6 +287,17 @@ enum bpf_func_id { * Return: realm if != 0 */ BPF_FUNC_get_route_realm, + + /** + * bpf_perf_event_output(ctx, map, index, data, size) - output perf raw sample + * @ctx: struct pt_regs* + * @map: pointer to perf_event_array map + * @index: index of event in the map + * @data: data on stack to be output as raw data + * @size: size of data + * Return: 0 on success + */ + BPF_FUNC_perf_event_output, __BPF_FUNC_MAX_ID, }; diff --git a/include/uapi/linux/perf_event.h b/include/uapi/linux/perf_event.h index 2881145cda86..d3c417615361 100644 --- a/include/uapi/linux/perf_event.h +++ b/include/uapi/linux/perf_event.h @@ -110,6 +110,7 @@ enum perf_sw_ids { PERF_COUNT_SW_ALIGNMENT_FAULTS = 7, PERF_COUNT_SW_EMULATION_FAULTS = 8, PERF_COUNT_SW_DUMMY = 9, + PERF_COUNT_SW_BPF_OUTPUT = 10, PERF_COUNT_SW_MAX, /* non-ABI */ }; -- cgit v1.2.3 From ea70ba980666cffacb57d90d867b2c7952d90700 Mon Sep 17 00:00:00 2001 From: Vivien Didelot Date: Thu, 22 Oct 2015 09:34:38 -0400 Subject: net: dsa: add port_fdb_dump function Not all switch chips support a Get Next operation to iterate on its FDB. So add a more simple port_fdb_dump function for them. Signed-off-by: Vivien Didelot Signed-off-by: David S. Miller --- include/net/dsa.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include') diff --git a/include/net/dsa.h b/include/net/dsa.h index e00588625bc2..0cfa44af8fd2 100644 --- a/include/net/dsa.h +++ b/include/net/dsa.h @@ -198,6 +198,7 @@ static inline u8 dsa_upstream_port(struct dsa_switch *ds) } struct switchdev_trans; +struct switchdev_obj; struct switchdev_obj_port_fdb; struct dsa_switch_driver { @@ -330,6 +331,9 @@ struct dsa_switch_driver { int (*port_fdb_getnext)(struct dsa_switch *ds, int port, unsigned char *addr, u16 *vid, bool *is_static); + int (*port_fdb_dump)(struct dsa_switch *ds, int port, + struct switchdev_obj_port_fdb *fdb, + int (*cb)(struct switchdev_obj *obj)); }; void register_switch_driver(struct dsa_switch_driver *type); -- cgit v1.2.3 From 1a49a2fbf8c15d63a0b5e60d935ec7d5d3d07fd5 Mon Sep 17 00:00:00 2001 From: Vivien Didelot Date: Thu, 22 Oct 2015 09:34:43 -0400 Subject: net: dsa: remove port_fdb_getnext No driver implements port_fdb_getnext anymore, and port_fdb_dump is preferred anyway, so remove this function from DSA. Signed-off-by: Vivien Didelot Signed-off-by: David S. Miller --- include/net/dsa.h | 3 --- 1 file changed, 3 deletions(-) (limited to 'include') diff --git a/include/net/dsa.h b/include/net/dsa.h index 0cfa44af8fd2..98ccbdef646f 100644 --- a/include/net/dsa.h +++ b/include/net/dsa.h @@ -328,9 +328,6 @@ struct dsa_switch_driver { struct switchdev_trans *trans); int (*port_fdb_del)(struct dsa_switch *ds, int port, const struct switchdev_obj_port_fdb *fdb); - int (*port_fdb_getnext)(struct dsa_switch *ds, int port, - unsigned char *addr, u16 *vid, - bool *is_static); int (*port_fdb_dump)(struct dsa_switch *ds, int port, struct switchdev_obj_port_fdb *fdb, int (*cb)(struct switchdev_obj *obj)); -- cgit v1.2.3 From 5e0724d027f0548511a2165a209572d48fe7a4c8 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Thu, 22 Oct 2015 08:20:46 -0700 Subject: tcp/dccp: fix hashdance race for passive sessions Multiple cpus can process duplicates of incoming ACK messages matching a SYN_RECV request socket. This is a rare event under normal operations, but definitely can happen. Only one must win the race, otherwise corruption would occur. To fix this without adding new atomic ops, we use logic in inet_ehash_nolisten() to detect the request was present in the same ehash bucket where we try to insert the new child. If request socket was not found, we have to undo the child creation. This actually removes a spin_lock()/spin_unlock() pair in reqsk_queue_unlink() for the fast path. Fixes: e994b2f0fb92 ("tcp: do not lock listener to process SYN packets") Fixes: 079096f103fa ("tcp/dccp: install syn_recv requests into ehash table") Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- include/net/inet_connection_sock.h | 7 ++++++- include/net/inet_hashtables.h | 4 ++-- include/net/tcp.h | 4 +++- 3 files changed, 11 insertions(+), 4 deletions(-) (limited to 'include') diff --git a/include/net/inet_connection_sock.h b/include/net/inet_connection_sock.h index 63615709839d..481fe1c9044c 100644 --- a/include/net/inet_connection_sock.h +++ b/include/net/inet_connection_sock.h @@ -43,7 +43,9 @@ struct inet_connection_sock_af_ops { int (*conn_request)(struct sock *sk, struct sk_buff *skb); struct sock *(*syn_recv_sock)(const struct sock *sk, struct sk_buff *skb, struct request_sock *req, - struct dst_entry *dst); + struct dst_entry *dst, + struct request_sock *req_unhash, + bool *own_req); u16 net_header_len; u16 net_frag_header_len; u16 sockaddr_len; @@ -272,6 +274,9 @@ void inet_csk_reqsk_queue_add(struct sock *sk, struct request_sock *req, struct sock *child); void inet_csk_reqsk_queue_hash_add(struct sock *sk, struct request_sock *req, unsigned long timeout); +struct sock *inet_csk_complete_hashdance(struct sock *sk, struct sock *child, + struct request_sock *req, + bool own_req); static inline void inet_csk_reqsk_queue_added(struct sock *sk) { diff --git a/include/net/inet_hashtables.h b/include/net/inet_hashtables.h index 6683ada25fef..de2e3ade6102 100644 --- a/include/net/inet_hashtables.h +++ b/include/net/inet_hashtables.h @@ -205,8 +205,8 @@ void inet_put_port(struct sock *sk); void inet_hashinfo_init(struct inet_hashinfo *h); -int inet_ehash_insert(struct sock *sk, struct sock *osk); -void __inet_hash_nolisten(struct sock *sk, struct sock *osk); +bool inet_ehash_insert(struct sock *sk, struct sock *osk); +bool inet_ehash_nolisten(struct sock *sk, struct sock *osk); void __inet_hash(struct sock *sk, struct sock *osk); void inet_hash(struct sock *sk); void inet_unhash(struct sock *sk); diff --git a/include/net/tcp.h b/include/net/tcp.h index 11e320412216..f80e74c5ad18 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -457,7 +457,9 @@ struct sock *tcp_create_openreq_child(const struct sock *sk, void tcp_ca_openreq_child(struct sock *sk, const struct dst_entry *dst); struct sock *tcp_v4_syn_recv_sock(const struct sock *sk, struct sk_buff *skb, struct request_sock *req, - struct dst_entry *dst); + struct dst_entry *dst, + struct request_sock *req_unhash, + bool *own_req); int tcp_v4_do_rcv(struct sock *sk, struct sk_buff *skb); int tcp_v4_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len); int tcp_connect(struct sock *sk); -- cgit v1.2.3 From dd461d6aa894761fe67c30ddf81eec0d08be216b Mon Sep 17 00:00:00 2001 From: Hiroshi Shimamoto Date: Fri, 28 Aug 2015 06:57:55 +0000 Subject: if_link: Add control trust VF Add netlink directives and ndo entry to trust VF user. This controls the special permission of VF user. The administrator will dedicatedly trust VF user to use some features which impacts security and/or performance. The administrator never turn it on unless VF user is fully trusted. CC: Sy Jong Choi Signed-off-by: Hiroshi Shimamoto Acked-by: Greg Rose Tested-by: Krishneil Singh Signed-off-by: Jeff Kirsher --- include/linux/if_link.h | 1 + include/linux/netdevice.h | 3 +++ include/uapi/linux/if_link.h | 6 ++++++ 3 files changed, 10 insertions(+) (limited to 'include') diff --git a/include/linux/if_link.h b/include/linux/if_link.h index ae5d0d22955d..f923d15b432c 100644 --- a/include/linux/if_link.h +++ b/include/linux/if_link.h @@ -24,5 +24,6 @@ struct ifla_vf_info { __u32 min_tx_rate; __u32 max_tx_rate; __u32 rss_query_en; + __u32 trusted; }; #endif /* _LINUX_IF_LINK_H */ diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 69fdd427c8cb..773383859bd9 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -881,6 +881,7 @@ typedef u16 (*select_queue_fallback_t)(struct net_device *dev, * int (*ndo_set_vf_rate)(struct net_device *dev, int vf, int min_tx_rate, * int max_tx_rate); * int (*ndo_set_vf_spoofchk)(struct net_device *dev, int vf, bool setting); + * int (*ndo_set_vf_trust)(struct net_device *dev, int vf, bool setting); * int (*ndo_get_vf_config)(struct net_device *dev, * int vf, struct ifla_vf_info *ivf); * int (*ndo_set_vf_link_state)(struct net_device *dev, int vf, int link_state); @@ -1109,6 +1110,8 @@ struct net_device_ops { int max_tx_rate); int (*ndo_set_vf_spoofchk)(struct net_device *dev, int vf, bool setting); + int (*ndo_set_vf_trust)(struct net_device *dev, + int vf, bool setting); int (*ndo_get_vf_config)(struct net_device *dev, int vf, struct ifla_vf_info *ivf); diff --git a/include/uapi/linux/if_link.h b/include/uapi/linux/if_link.h index e3b6217f34f1..a7aea8418abb 100644 --- a/include/uapi/linux/if_link.h +++ b/include/uapi/linux/if_link.h @@ -550,6 +550,7 @@ enum { * on/off switch */ IFLA_VF_STATS, /* network device statistics */ + IFLA_VF_TRUST, /* Trust VF */ __IFLA_VF_MAX, }; @@ -611,6 +612,11 @@ enum { #define IFLA_VF_STATS_MAX (__IFLA_VF_STATS_MAX - 1) +struct ifla_vf_trust { + __u32 vf; + __u32 setting; +}; + /* VF ports management section * * Nested layout of set/get msg is: -- cgit v1.2.3 From 21dd19fed3c3eb42a3877600f4a97a774323e562 Mon Sep 17 00:00:00 2001 From: Neil Armstrong Date: Thu, 22 Oct 2015 10:37:49 +0200 Subject: net: phy: Add nested variants of mdiobus read/write Since nested variants of mdiobus_read/write are used in multiple drivers, add nested variants in the mdiobus core. Suggested-by: Andrew Lunn Signed-off-by: Neil Armstrong Signed-off-by: David S. Miller --- include/linux/phy.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/linux/phy.h b/include/linux/phy.h index 4c477e6ece33..05fde31b6dc6 100644 --- a/include/linux/phy.h +++ b/include/linux/phy.h @@ -213,7 +213,9 @@ static inline struct mii_bus *devm_mdiobus_alloc(struct device *dev) void devm_mdiobus_free(struct device *dev, struct mii_bus *bus); struct phy_device *mdiobus_scan(struct mii_bus *bus, int addr); int mdiobus_read(struct mii_bus *bus, int addr, u32 regnum); +int mdiobus_read_nested(struct mii_bus *bus, int addr, u32 regnum); int mdiobus_write(struct mii_bus *bus, int addr, u32 regnum, u16 val); +int mdiobus_write_nested(struct mii_bus *bus, int addr, u32 regnum, u16 val); #define PHY_INTERRUPT_DISABLED 0x0 -- cgit v1.2.3 From f8efb73c97e2fa0abbe2e07c5c5df07800312643 Mon Sep 17 00:00:00 2001 From: Roopa Prabhu Date: Fri, 23 Oct 2015 06:03:27 -0700 Subject: mpls: multipath route support This patch adds support for MPLS multipath routes. Includes following changes to support multipath: - splits struct mpls_route into 'struct mpls_route + struct mpls_nh' - 'struct mpls_nh' represents a mpls nexthop label forwarding entry - moves mpls route and nexthop structures into internal.h - A mpls_route can point to multiple mpls_nh structs - the nexthops are maintained as a array (similar to ipv4 fib) - In the process of restructuring, this patch also consistently changes all labels to u8 - Adds support to parse/fill RTA_MULTIPATH netlink attribute for multipath routes similar to ipv4/v6 fib - In this patch, the multipath route nexthop selection algorithm simply returns the first nexthop. It is replaced by a hash based algorithm from Robert Shearman in the next patch - mpls_route_update cleanup: remove 'dev' handling in mpls_route_update. mpls_route_update though implemented to update based on dev, it was never used that way. And the dev handling gets tricky with multiple nexthops. Cannot match against any single nexthops dev. So, this patch removes the unused 'dev' handling in mpls_route_update. - dead route/path handling will be implemented in a subsequent patch Example: $ip -f mpls route add 100 nexthop as 200 via inet 10.1.1.2 dev swp1 \ nexthop as 700 via inet 10.1.1.6 dev swp2 \ nexthop as 800 via inet 40.1.1.2 dev swp3 $ip -f mpls route show 100 nexthop as to 200 via inet 10.1.1.2 dev swp1 nexthop as to 700 via inet 10.1.1.6 dev swp2 nexthop as to 800 via inet 40.1.1.2 dev swp3 Signed-off-by: Roopa Prabhu Acked-by: Robert Shearman Signed-off-by: David S. Miller --- include/net/mpls_iptunnel.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/net/mpls_iptunnel.h b/include/net/mpls_iptunnel.h index 4757997f76ed..179253f9dcfd 100644 --- a/include/net/mpls_iptunnel.h +++ b/include/net/mpls_iptunnel.h @@ -18,7 +18,7 @@ struct mpls_iptunnel_encap { u32 label[MAX_NEW_LABELS]; - u32 labels; + u8 labels; }; static inline struct mpls_iptunnel_encap *mpls_lwtunnel_encap(struct lwtunnel_state *lwtstate) -- cgit v1.2.3 From 2663589ce67e5429bac89544bb0e102bb1fcf617 Mon Sep 17 00:00:00 2001 From: Robert Dolca Date: Thu, 22 Oct 2015 12:11:34 +0300 Subject: NFC: nci: Add function to get max packet size for conn FDP driver needs to send the firmware as regular packets (not fragmented). The driver should have a way to get the max packet size for a given connection. Signed-off-by: Robert Dolca Signed-off-by: Samuel Ortiz --- include/net/nfc/nci_core.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/net/nfc/nci_core.h b/include/net/nfc/nci_core.h index d0d0f1e53bb9..aaada20bf78e 100644 --- a/include/net/nfc/nci_core.h +++ b/include/net/nfc/nci_core.h @@ -351,6 +351,7 @@ int nci_prop_ntf_packet(struct nci_dev *ndev, __u16 opcode, void nci_rx_data_packet(struct nci_dev *ndev, struct sk_buff *skb); int nci_send_cmd(struct nci_dev *ndev, __u16 opcode, __u8 plen, void *payload); int nci_send_data(struct nci_dev *ndev, __u8 conn_id, struct sk_buff *skb); +int nci_conn_max_data_pkt_payload_size(struct nci_dev *ndev, __u8 conn_id); void nci_data_exchange_complete(struct nci_dev *ndev, struct sk_buff *skb, __u8 conn_id, int err); void nci_hci_data_received_cb(void *context, struct sk_buff *skb, int err); -- cgit v1.2.3 From a9433c11b1aa0639cc6e4842fff52af2422af06d Mon Sep 17 00:00:00 2001 From: Robert Dolca Date: Thu, 22 Oct 2015 12:11:35 +0300 Subject: NFC: nci: Introduce new core opcodes Add NCI_OP_CORE_GET_CONFIG_CMD, NCI_OP_CORE_GET_CONFIG_RSP and NCI_OP_CORE_RESET_NTF. Signed-off-by: Robert Dolca Signed-off-by: Samuel Ortiz --- include/net/nfc/nci.h | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'include') diff --git a/include/net/nfc/nci.h b/include/net/nfc/nci.h index 75d2e1880059..b495825f8f49 100644 --- a/include/net/nfc/nci.h +++ b/include/net/nfc/nci.h @@ -315,6 +315,8 @@ struct nci_nfcee_mode_set_cmd { __u8 nfcee_mode; } __packed; +#define NCI_OP_CORE_GET_CONFIG_CMD nci_opcode_pack(NCI_GID_CORE, 0x03) + /* ----------------------- */ /* ---- NCI Responses ---- */ /* ----------------------- */ @@ -375,6 +377,9 @@ struct nci_nfcee_discover_rsp { } __packed; #define NCI_OP_NFCEE_MODE_SET_RSP nci_opcode_pack(NCI_GID_NFCEE_MGMT, 0x01) + +#define NCI_OP_CORE_GET_CONFIG_RSP nci_opcode_pack(NCI_GID_CORE, 0x03) + /* --------------------------- */ /* ---- NCI Notifications ---- */ /* --------------------------- */ @@ -528,4 +533,6 @@ struct nci_nfcee_discover_ntf { struct nci_nfcee_information_tlv information_tlv; } __packed; +#define NCI_OP_CORE_RESET_NTF nci_opcode_pack(NCI_GID_CORE, 0x00) + #endif /* __NCI_H */ -- cgit v1.2.3 From 7bc4824ed5cf9feb0173b90a6bec28f694a5f7ce Mon Sep 17 00:00:00 2001 From: Robert Dolca Date: Thu, 22 Oct 2015 12:11:37 +0300 Subject: NFC: nci: Introduce nci_core_cmd This allows sending core commands from the driver. The driver should be able to send NCI core commands like CORE_GET_CONFIG_CMD. Signed-off-by: Robert Dolca Signed-off-by: Samuel Ortiz --- include/net/nfc/nci_core.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/net/nfc/nci_core.h b/include/net/nfc/nci_core.h index aaada20bf78e..4ca1b6d1684b 100644 --- a/include/net/nfc/nci_core.h +++ b/include/net/nfc/nci_core.h @@ -278,6 +278,7 @@ int nci_request(struct nci_dev *ndev, unsigned long opt), unsigned long opt, __u32 timeout); int nci_prop_cmd(struct nci_dev *ndev, __u8 oid, size_t len, __u8 *payload); +int nci_core_cmd(struct nci_dev *ndev, __u16 opcode, size_t len, __u8 *payload); int nci_core_reset(struct nci_dev *ndev); int nci_core_init(struct nci_dev *ndev); -- cgit v1.2.3 From 0a97a3cba298fd989802bf34541c94b6488c3834 Mon Sep 17 00:00:00 2001 From: Robert Dolca Date: Thu, 22 Oct 2015 12:11:38 +0300 Subject: NFC: nci: Allow the driver to set handler for core nci ops The driver may be required to act when some responses or notifications arrive. For example the NCI core does not have a handler for NCI_OP_CORE_GET_CONFIG_RSP. The NFCC can send a config response that has to be read by the driver and the packet may contain vendor specific data. The Fields Peak driver needs to take certain actions when a reset notification arrives (packet also not handled by the nfc core). The driver handlers do not interfere with the core and they are called after the core processes the packet. Signed-off-by: Robert Dolca Signed-off-by: Samuel Ortiz --- include/net/nfc/nci_core.h | 11 +++++++++-- 1 file changed, 9 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/net/nfc/nci_core.h b/include/net/nfc/nci_core.h index 4ca1b6d1684b..d5a1caae9fd9 100644 --- a/include/net/nfc/nci_core.h +++ b/include/net/nfc/nci_core.h @@ -96,6 +96,9 @@ struct nci_ops { struct nci_prop_ops *prop_ops; size_t n_prop_ops; + + struct nci_prop_ops *core_ops; + size_t n_core_ops; }; #define NCI_MAX_SUPPORTED_RF_INTERFACES 4 @@ -345,9 +348,13 @@ static inline int nci_set_vendor_cmds(struct nci_dev *ndev, void nci_rsp_packet(struct nci_dev *ndev, struct sk_buff *skb); void nci_ntf_packet(struct nci_dev *ndev, struct sk_buff *skb); -int nci_prop_rsp_packet(struct nci_dev *ndev, __u16 opcode, +inline int nci_prop_rsp_packet(struct nci_dev *ndev, __u16 opcode, + struct sk_buff *skb); +inline int nci_prop_ntf_packet(struct nci_dev *ndev, __u16 opcode, + struct sk_buff *skb); +inline int nci_core_rsp_packet(struct nci_dev *ndev, __u16 opcode, struct sk_buff *skb); -int nci_prop_ntf_packet(struct nci_dev *ndev, __u16 opcode, +inline int nci_core_ntf_packet(struct nci_dev *ndev, __u16 opcode, struct sk_buff *skb); void nci_rx_data_packet(struct nci_dev *ndev, struct sk_buff *skb); int nci_send_cmd(struct nci_dev *ndev, __u16 opcode, __u8 plen, void *payload); -- cgit v1.2.3 From 22e4bd09c401905671f3787a8392d269a0ebfa0d Mon Sep 17 00:00:00 2001 From: Robert Dolca Date: Thu, 22 Oct 2015 12:11:39 +0300 Subject: NFC: nci: rename nci_prop_ops to nci_driver_ops Initially it was used to create hooks in the driver for proprietary operations. Currently it is being used for hooks for both proprietary and generic operations. Signed-off-by: Robert Dolca Signed-off-by: Samuel Ortiz --- include/net/nfc/nci_core.h | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/include/net/nfc/nci_core.h b/include/net/nfc/nci_core.h index d5a1caae9fd9..5daf0042261e 100644 --- a/include/net/nfc/nci_core.h +++ b/include/net/nfc/nci_core.h @@ -67,7 +67,7 @@ enum nci_state { struct nci_dev; -struct nci_prop_ops { +struct nci_driver_ops { __u16 opcode; int (*rsp)(struct nci_dev *dev, struct sk_buff *skb); int (*ntf)(struct nci_dev *dev, struct sk_buff *skb); @@ -94,10 +94,10 @@ struct nci_ops { void (*hci_cmd_received)(struct nci_dev *ndev, u8 pipe, u8 cmd, struct sk_buff *skb); - struct nci_prop_ops *prop_ops; + struct nci_driver_ops *prop_ops; size_t n_prop_ops; - struct nci_prop_ops *core_ops; + struct nci_driver_ops *core_ops; size_t n_core_ops; }; -- cgit v1.2.3 From 85b9ce9a21b119a8163f20d60e7f0ce58fffbeef Mon Sep 17 00:00:00 2001 From: Robert Dolca Date: Thu, 22 Oct 2015 12:11:41 +0300 Subject: NFC: nci: add nci_get_conn_info_by_id function This functin takes as a parameter a pointer to the nci_dev struct and the first byte from the values of the first domain specific parameter that was used for the connection creation. Signed-off-by: Robert Dolca Signed-off-by: Samuel Ortiz --- include/net/nfc/nci_core.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/net/nfc/nci_core.h b/include/net/nfc/nci_core.h index 5daf0042261e..0569cb251135 100644 --- a/include/net/nfc/nci_core.h +++ b/include/net/nfc/nci_core.h @@ -374,6 +374,7 @@ void nci_clear_target_list(struct nci_dev *ndev); void nci_req_complete(struct nci_dev *ndev, int result); struct nci_conn_info *nci_get_conn_info_by_conn_id(struct nci_dev *ndev, int conn_id); +int nci_get_conn_info_by_id(struct nci_dev *ndev, u8 id); /* ----- NCI status code ----- */ int nci_to_errno(__u8 code); -- cgit v1.2.3 From fa6fbadea5d3618339fae8f9d5136a470bad4fa7 Mon Sep 17 00:00:00 2001 From: Christophe Ricard Date: Sun, 25 Oct 2015 22:54:23 +0100 Subject: NFC: nci: add nci_hci_clear_all_pipes functions nci_hci_clear_all_pipes might be use full in some cases for example after a firmware update. Signed-off-by: Christophe Ricard Signed-off-by: Samuel Ortiz --- include/net/nfc/nci_core.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/net/nfc/nci_core.h b/include/net/nfc/nci_core.h index 0569cb251135..65e40df05df2 100644 --- a/include/net/nfc/nci_core.h +++ b/include/net/nfc/nci_core.h @@ -309,6 +309,7 @@ int nci_hci_set_param(struct nci_dev *ndev, u8 gate, u8 idx, const u8 *param, size_t param_len); int nci_hci_get_param(struct nci_dev *ndev, u8 gate, u8 idx, struct sk_buff **skb); +int nci_hci_clear_all_pipes(struct nci_dev *ndev); int nci_hci_dev_session_init(struct nci_dev *ndev); static inline struct sk_buff *nci_skb_alloc(struct nci_dev *ndev, -- cgit v1.2.3 From 7e35740438bafcc8be0e05ff2461b73d631caeb0 Mon Sep 17 00:00:00 2001 From: Christophe Ricard Date: Sun, 25 Oct 2015 22:54:33 +0100 Subject: NFC: st-nci: Add support for NCI_HCI_IDENTITY_MGMT_GATE NCI_HCI_IDENTITY_MGMT_GATE might be useful to get information about hardware or firmware version. Signed-off-by: Christophe Ricard Signed-off-by: Samuel Ortiz --- include/net/nfc/nci_core.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/net/nfc/nci_core.h b/include/net/nfc/nci_core.h index 65e40df05df2..79c6d1af209d 100644 --- a/include/net/nfc/nci_core.h +++ b/include/net/nfc/nci_core.h @@ -128,6 +128,7 @@ struct nci_conn_info { /* Gates */ #define NCI_HCI_ADMIN_GATE 0x00 +#define NCI_HCI_IDENTITY_MGMT_GATE 0x05 #define NCI_HCI_LINK_MGMT_GATE 0x06 /* Pipes */ -- cgit v1.2.3 From 242c0ebd3730334c43b9c04eeec40d8dd5c3a26e Mon Sep 17 00:00:00 2001 From: Marcel Holtmann Date: Sun, 25 Oct 2015 22:45:53 +0100 Subject: Bluetooth: Rename bt_cb()->req into bt_cb()->hci The SKB context buffer for HCI request is really not just for requests, information in their are preserved for the whole HCI layer. So it makes more sense to actually rename it into bt_cb()->hci and also call it then struct hci_ctrl. In addition that allows moving the decoded opcode for outgoing packets into that struct. So far it was just consuming valuable space from the main shared items. And opcode are not valid for L2CAP packets. Signed-off-by: Marcel Holtmann Signed-off-by: Johan Hedberg --- include/net/bluetooth/bluetooth.h | 14 +++++++------- 1 file changed, 7 insertions(+), 7 deletions(-) (limited to 'include') diff --git a/include/net/bluetooth/bluetooth.h b/include/net/bluetooth/bluetooth.h index c4defef319d5..42844d7b154a 100644 --- a/include/net/bluetooth/bluetooth.h +++ b/include/net/bluetooth/bluetooth.h @@ -296,22 +296,22 @@ typedef void (*hci_req_complete_t)(struct hci_dev *hdev, u8 status, u16 opcode); typedef void (*hci_req_complete_skb_t)(struct hci_dev *hdev, u8 status, u16 opcode, struct sk_buff *skb); -struct req_ctrl { - bool start; - u8 event; - hci_req_complete_t complete; - hci_req_complete_skb_t complete_skb; +struct hci_ctrl { + __u16 opcode; + bool req_start; + u8 req_event; + hci_req_complete_t req_complete; + hci_req_complete_skb_t req_complete_skb; }; struct bt_skb_cb { __u8 pkt_type; __u8 force_active; - __u16 opcode; __u16 expect; __u8 incoming:1; union { struct l2cap_ctrl l2cap; - struct req_ctrl req; + struct hci_ctrl hci; }; }; #define bt_cb(skb) ((struct bt_skb_cb *)((skb)->cb)) -- cgit v1.2.3 From 8890624a4e8c2c7046d63bfd15d7331af9f55f10 Mon Sep 17 00:00:00 2001 From: Michael Grzeschik Date: Thu, 18 Sep 2014 00:12:50 +0200 Subject: arcnet: com20020-pci: add led trigger support The EAE PLX-PCI card has special leds on the the main io pci resource bar. This patch adds support to trigger the conflict and data leds with the packages. Signed-off-by: Michael Grzeschik --- include/linux/leds.h | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'include') diff --git a/include/linux/leds.h b/include/linux/leds.h index b122eeafb5dc..fa359c79c825 100644 --- a/include/linux/leds.h +++ b/include/linux/leds.h @@ -283,6 +283,13 @@ static inline void led_trigger_register_simple(const char *name, static inline void led_trigger_unregister_simple(struct led_trigger *trigger) {} static inline void led_trigger_event(struct led_trigger *trigger, enum led_brightness event) {} +static inline void led_trigger_blink(struct led_trigger *trigger, + unsigned long *delay_on, + unsigned long *delay_off) {} +static inline void led_trigger_blink_oneshot(struct led_trigger *trigger, + unsigned long *delay_on, + unsigned long *delay_off, + int invert) {} static inline void led_trigger_set_default(struct led_classdev *led_cdev) {} static inline void led_trigger_set(struct led_classdev *led_cdev, struct led_trigger *trigger) {} -- cgit v1.2.3 From b1fa4dc4ffef843bda17f26bbf54fb5d8bc23d2b Mon Sep 17 00:00:00 2001 From: Christophe Ricard Date: Sun, 25 Oct 2015 22:54:36 +0100 Subject: NFC: st-nci: Add support for proprietary commands Add support for proprietary commands useful mainly for factory testings. Here is a list: - FACTORY_MODE: Allow to set the driver into a mode where no secure element are activated. It does not consider any NFC_ATTR_VENDOR_DATA. - HCI_CLEAR_ALL_PIPES: Allow to execute a HCI clear all pipes command. It does not consider any NFC_ATTR_VENDOR_DATA. - HCI_DM_PUT_DATA: Allow to configure specific CLF registry like for example RF trimmings or low level drivers configurations (I2C, SPI, SWP). - HCI_DM_UPDATE_AID: Allow to configure an AID routing into the CLF routing table following RF technology, CLF mode or protocol. - HCI_DM_GET_INFO: Allow to retrieve CLF information. - HCI_DM_GET_DATA: Allow to retrieve CLF configurable data such as low level drivers configurations or RF trimmings. - HCI_DM_DIRECT_LOAD: Allow to load a firmware into the CLF. A complete packet can be more than 8KB. - HCI_DM_RESET: Allow to run a CLF reset in order to "commit" CLF configuration changes without CLF power off. - HCI_GET_PARAM: Allow to retrieve an HCI CLF parameter (for example the white list). - HCI_DM_FIELD_GENERATOR: Allow to generate different kind of RF technology. When using this command to anti-collision is done. - HCI_LOOPBACK: Allow to echo a command and test the Dh to CLF connectivity. - HCI_DM_VDC_MEASUREMENT_VALUE: Allow to measure the field applied on the CLF antenna. A value between 0 and 0x0f is returned. 0 is maximum. - HCI_DM_FWUPD_START: Allow to put CLF into firmware update mode. It is a specific CLF command as there is no GPIO for this. - HCI_DM_FWUPD_END: Allow to complete firmware update. - HCI_DM_VDC_VALUE_COMPARISON: Allow to compare the field applied on the CLF antenna to a reference value. - MANUFACTURER_SPECIFIC: Allow to retrieve manufacturer specific data received during a NCI_CORE_INIT_CMD. Signed-off-by: Christophe Ricard Signed-off-by: Samuel Ortiz --- include/net/nfc/nci_core.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/net/nfc/nci_core.h b/include/net/nfc/nci_core.h index 79c6d1af209d..530df66f9484 100644 --- a/include/net/nfc/nci_core.h +++ b/include/net/nfc/nci_core.h @@ -128,6 +128,7 @@ struct nci_conn_info { /* Gates */ #define NCI_HCI_ADMIN_GATE 0x00 +#define NCI_HCI_LOOPBACK_GATE 0x04 #define NCI_HCI_IDENTITY_MGMT_GATE 0x05 #define NCI_HCI_LINK_MGMT_GATE 0x06 -- cgit v1.2.3 From be73c2cbc857a4a3424c0e3cdd70002d5a27a756 Mon Sep 17 00:00:00 2001 From: Christophe Ricard Date: Sun, 25 Oct 2015 22:54:38 +0100 Subject: NFC: netlink: Add missing NFC_ATTR comments NFC_CMD_ACTIVATE_TARGET and NFC_ATTR_SE_PARAMS comments are missing. Signed-off-by: Christophe Ricard Signed-off-by: Samuel Ortiz --- include/uapi/linux/nfc.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/uapi/linux/nfc.h b/include/uapi/linux/nfc.h index dd3f75389076..399f39ff8048 100644 --- a/include/uapi/linux/nfc.h +++ b/include/uapi/linux/nfc.h @@ -86,6 +86,7 @@ * for this event is the application ID (AID). * @NFC_CMD_GET_SE: Dump all discovered secure elements from an NFC controller. * @NFC_CMD_SE_IO: Send/Receive APDUs to/from the selected secure element. + * @NFC_CMD_ACTIVATE_TARGET: Request NFC controller to reactivate target. * @NFC_CMD_VENDOR: Vendor specific command, to be implemented directly * from the driver in order to support hardware specific operations. */ @@ -156,6 +157,7 @@ enum nfc_commands { * @NFC_ATTR_APDU: Secure element APDU * @NFC_ATTR_TARGET_ISO15693_DSFID: ISO 15693 Data Storage Format Identifier * @NFC_ATTR_TARGET_ISO15693_UID: ISO 15693 Unique Identifier + * @NFC_ATTR_SE_PARAMS: Parameters data from an evt_transaction * @NFC_ATTR_VENDOR_ID: NFC manufacturer unique ID, typically an OUI * @NFC_ATTR_VENDOR_SUBCMD: Vendor specific sub command * @NFC_ATTR_VENDOR_DATA: Vendor specific data, to be optionally passed -- cgit v1.2.3 From 3648dc6d27f648b8e3ce9b48874627a833d53c3a Mon Sep 17 00:00:00 2001 From: Christophe Ricard Date: Sun, 25 Oct 2015 22:54:39 +0100 Subject: NFC: st-nci: Add ese-present/uicc-present dts properties In order to align with st21nfca, dts configuration properties ese_present and uicc_present are made available in st-nci driver. So far, in early development firmware, because nci_nfcee_mode_set(DISABLE) was not supported we had to try to enable it during the secure element discovery phase. After several trials on commercial and qualified firmware it appears that nci_nfcee_mode_set(ENABLE) and nci_nfcee_mode_set(DISABLE) are properly supported. Such feature also help us to eventually save some time (~5ms) when only one secure element is connected. Acked-by: Rob Herring Signed-off-by: Christophe Ricard Signed-off-by: Samuel Ortiz --- include/linux/platform_data/st-nci.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/linux/platform_data/st-nci.h b/include/linux/platform_data/st-nci.h index d9d400a297bd..f6494b347c06 100644 --- a/include/linux/platform_data/st-nci.h +++ b/include/linux/platform_data/st-nci.h @@ -24,6 +24,8 @@ struct st_nci_nfc_platform_data { unsigned int gpio_reset; unsigned int irq_polarity; + bool is_ese_present; + bool is_uicc_present; }; #endif /* _ST_NCI_H_ */ -- cgit v1.2.3 From 96d4581f0b3712221d6ed4a765bb6b4ea40f2b2f Mon Sep 17 00:00:00 2001 From: Christophe Ricard Date: Sun, 25 Oct 2015 22:54:43 +0100 Subject: NFC: netlink: Add mode parameter to deactivate_target functions In order to manage in a better way the nci poll mode state machine, add mode parameter to deactivate_target functions. This way we can manage different target state. mode parameter make sense only in nci core. Signed-off-by: Christophe Ricard Signed-off-by: Samuel Ortiz --- include/net/nfc/nfc.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/net/nfc/nfc.h b/include/net/nfc/nfc.h index 30afc9a6718c..dcfcfc9c00bf 100644 --- a/include/net/nfc/nfc.h +++ b/include/net/nfc/nfc.h @@ -68,7 +68,7 @@ struct nfc_ops { int (*activate_target)(struct nfc_dev *dev, struct nfc_target *target, u32 protocol); void (*deactivate_target)(struct nfc_dev *dev, - struct nfc_target *target); + struct nfc_target *target, u8 mode); int (*im_transceive)(struct nfc_dev *dev, struct nfc_target *target, struct sk_buff *skb, data_exchange_cb_t cb, void *cb_context); -- cgit v1.2.3 From e5629d29470134af1954d2bbe45c4f2b73f68ee9 Mon Sep 17 00:00:00 2001 From: Vincent Cuissard Date: Mon, 26 Oct 2015 10:27:38 +0100 Subject: NFC: NCI: export nci_send_frame and nci_send_cmd function Export nci_send_frame and nci_send_cmd symbols to allow drivers to use it. This is needed for example if NCI is used during firmware download phase. Signed-off-by: Vincent Cuissard Signed-off-by: Samuel Ortiz --- include/net/nfc/nci_core.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/net/nfc/nci_core.h b/include/net/nfc/nci_core.h index 530df66f9484..77880bdf93a8 100644 --- a/include/net/nfc/nci_core.h +++ b/include/net/nfc/nci_core.h @@ -288,6 +288,7 @@ int nci_core_reset(struct nci_dev *ndev); int nci_core_init(struct nci_dev *ndev); int nci_recv_frame(struct nci_dev *ndev, struct sk_buff *skb); +int nci_send_frame(struct nci_dev *ndev, struct sk_buff *skb); int nci_set_config(struct nci_dev *ndev, __u8 id, size_t len, __u8 *val); int nci_nfcee_discover(struct nci_dev *ndev, u8 action); -- cgit v1.2.3 From b5b3e23e4cace008e1a30e8614a484d14dfd07a1 Mon Sep 17 00:00:00 2001 From: Vincent Cuissard Date: Mon, 26 Oct 2015 10:27:41 +0100 Subject: NFC: nfcmrvl: add i2c driver This driver adds the support of I2C-based Marvell NFC controller. Signed-off-by: Vincent Cuissard Signed-off-by: Samuel Ortiz --- include/linux/platform_data/nfcmrvl.h | 8 ++++++++ include/net/nfc/nci.h | 1 + 2 files changed, 9 insertions(+) (limited to 'include') diff --git a/include/linux/platform_data/nfcmrvl.h b/include/linux/platform_data/nfcmrvl.h index ac91707dabcb..a6f9d633f5be 100644 --- a/include/linux/platform_data/nfcmrvl.h +++ b/include/linux/platform_data/nfcmrvl.h @@ -35,6 +35,14 @@ struct nfcmrvl_platform_data { unsigned int flow_control; /* Tell if firmware supports break control for power management */ unsigned int break_control; + + + /* + * I2C specific + */ + + unsigned int irq; + unsigned int irq_polarity; }; #endif /* _NFCMRVL_PTF_H_ */ diff --git a/include/net/nfc/nci.h b/include/net/nfc/nci.h index b495825f8f49..707e3ab816c2 100644 --- a/include/net/nfc/nci.h +++ b/include/net/nfc/nci.h @@ -35,6 +35,7 @@ #define NCI_MAX_NUM_RF_CONFIGS 10 #define NCI_MAX_NUM_CONN 10 #define NCI_MAX_PARAM_LEN 251 +#define NCI_MAX_PAYLOAD_SIZE 255 #define NCI_MAX_PACKET_SIZE 258 /* NCI Status Codes */ -- cgit v1.2.3 From 2bd832459a0827b8dcf13b345380b66f92089d74 Mon Sep 17 00:00:00 2001 From: Vincent Cuissard Date: Mon, 26 Oct 2015 10:27:43 +0100 Subject: NFC: NCI: allow spi driver to choose transfer clock In some cases low level drivers might want to update the SPI transfer clock (e.g. during firmware download). This patch adds this support. Without any modification the driver will use the default SPI clock (from pdata or device tree). Signed-off-by: Vincent Cuissard Signed-off-by: Samuel Ortiz --- include/net/nfc/nci_core.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include') diff --git a/include/net/nfc/nci_core.h b/include/net/nfc/nci_core.h index 77880bdf93a8..5a1572a34c49 100644 --- a/include/net/nfc/nci_core.h +++ b/include/net/nfc/nci_core.h @@ -394,6 +394,12 @@ struct nci_spi { unsigned int xfer_udelay; /* microseconds delay between transactions */ + + unsigned int xfer_speed_hz; /* + * SPI clock frequency + * 0 => default clock + */ + u8 acknowledge_mode; struct completion req_completion; -- cgit v1.2.3 From 62544ce8e01c1879d420ba309f7f319d24c0f4e6 Mon Sep 17 00:00:00 2001 From: Alexei Starovoitov Date: Thu, 22 Oct 2015 17:10:14 -0700 Subject: bpf: fix bpf_perf_event_read() helper Fix safety checks for bpf_perf_event_read(): - only non-inherited events can be added to perf_event_array map (do this check statically at map insertion time) - dynamically check that event is local and !pmu->count Otherwise buggy bpf program can cause kernel splat. Also fix error path after perf_event_attrs() and remove redundant 'extern'. Fixes: 35578d798400 ("bpf: Implement function bpf_perf_event_read() that get the selected hardware PMU conuter") Signed-off-by: Alexei Starovoitov Tested-by: Wang Nan Signed-off-by: David S. Miller --- include/linux/bpf.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index e3a51b74e275..75718fa28260 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -194,7 +194,6 @@ extern const struct bpf_func_proto bpf_map_lookup_elem_proto; extern const struct bpf_func_proto bpf_map_update_elem_proto; extern const struct bpf_func_proto bpf_map_delete_elem_proto; -extern const struct bpf_func_proto bpf_perf_event_read_proto; extern const struct bpf_func_proto bpf_get_prandom_u32_proto; extern const struct bpf_func_proto bpf_get_smp_processor_id_proto; extern const struct bpf_func_proto bpf_tail_call_proto; -- cgit v1.2.3 From 8941faa161b526199e55ca7764cf875383453612 Mon Sep 17 00:00:00 2001 From: "emmanuel.grumbach@intel.com" Date: Mon, 26 Oct 2015 10:31:29 +0200 Subject: net: tso: add support for IPv6 Adding IPv6 for the TSO helper API is trivial: * Don't play with the id (which doesn't exist in IPv6) * Correctly update the payload_len (don't include the length of the IP header itself) Signed-off-by: Emmanuel Grumbach Acked-by: Eric Dumazet Signed-off-by: David S. Miller --- include/net/tso.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/net/tso.h b/include/net/tso.h index 47e5444f7d15..b7be852bfe9d 100644 --- a/include/net/tso.h +++ b/include/net/tso.h @@ -8,6 +8,7 @@ struct tso_t { void *data; size_t size; u16 ip_id; + bool ipv6; u32 tcp_seq; }; -- cgit v1.2.3 From fe56b9e6a8d957d6a20729d626027f800c17a2da Mon Sep 17 00:00:00 2001 From: Yuval Mintz Date: Mon, 26 Oct 2015 11:02:25 +0200 Subject: qed: Add module with basic common support The Qlogic Everest Driver is the backend module for the QL4xxx ethernet products by Qlogic. This module serves two main purposes: 1. It's responsible to contain all the common code that will be shared between the various drivers that would be used with said line of products. Flows such as chip initialization and de-initialization fall under this category. 2. It would abstract the protocol-specific HW & FW components, allowing the protocol drivers to have a clean APIs which is detached in its slowpath configuration from the actual HSI. This adds a very basic module without any protocol-specific bits. I.e., this adds a basic implementation that almost entirely falls under the first category. Signed-off-by: Yuval Mintz Signed-off-by: Ariel Elior Signed-off-by: David S. Miller --- include/linux/qed/common_hsi.h | 607 +++++++++++++++++++++++++++++++++++++++++ include/linux/qed/qed_chain.h | 539 ++++++++++++++++++++++++++++++++++++ include/linux/qed/qed_if.h | 498 +++++++++++++++++++++++++++++++++ 3 files changed, 1644 insertions(+) create mode 100644 include/linux/qed/common_hsi.h create mode 100644 include/linux/qed/qed_chain.h create mode 100644 include/linux/qed/qed_if.h (limited to 'include') diff --git a/include/linux/qed/common_hsi.h b/include/linux/qed/common_hsi.h new file mode 100644 index 000000000000..6a4347639c03 --- /dev/null +++ b/include/linux/qed/common_hsi.h @@ -0,0 +1,607 @@ +/* QLogic qed NIC Driver + * Copyright (c) 2015 QLogic Corporation + * + * This software is available under the terms of the GNU General Public License + * (GPL) Version 2, available from the file COPYING in the main directory of + * this source tree. + */ + +#ifndef __COMMON_HSI__ +#define __COMMON_HSI__ + +#define FW_MAJOR_VERSION 8 +#define FW_MINOR_VERSION 4 +#define FW_REVISION_VERSION 2 +#define FW_ENGINEERING_VERSION 0 + +/***********************/ +/* COMMON HW CONSTANTS */ +/***********************/ + +/* PCI functions */ +#define MAX_NUM_PORTS_K2 (4) +#define MAX_NUM_PORTS_BB (2) +#define MAX_NUM_PORTS (MAX_NUM_PORTS_K2) + +#define MAX_NUM_PFS_K2 (16) +#define MAX_NUM_PFS_BB (8) +#define MAX_NUM_PFS (MAX_NUM_PFS_K2) +#define MAX_NUM_OF_PFS_IN_CHIP (16) /* On both engines */ + +#define MAX_NUM_VFS_K2 (192) +#define MAX_NUM_VFS_BB (120) +#define MAX_NUM_VFS (MAX_NUM_VFS_K2) + +#define MAX_NUM_FUNCTIONS_BB (MAX_NUM_PFS_BB + MAX_NUM_VFS_BB) +#define MAX_NUM_FUNCTIONS (MAX_NUM_PFS + MAX_NUM_VFS) + +#define MAX_FUNCTION_NUMBER_BB (MAX_NUM_PFS + MAX_NUM_VFS_BB) +#define MAX_FUNCTION_NUMBER (MAX_NUM_PFS + MAX_NUM_VFS) + +#define MAX_NUM_VPORTS_K2 (208) +#define MAX_NUM_VPORTS_BB (160) +#define MAX_NUM_VPORTS (MAX_NUM_VPORTS_K2) + +#define MAX_NUM_L2_QUEUES_K2 (320) +#define MAX_NUM_L2_QUEUES_BB (256) +#define MAX_NUM_L2_QUEUES (MAX_NUM_L2_QUEUES_K2) + +/* Traffic classes in network-facing blocks (PBF, BTB, NIG, BRB, PRS and QM) */ +#define NUM_PHYS_TCS_4PORT_K2 (4) +#define NUM_OF_PHYS_TCS (8) + +#define NUM_TCS_4PORT_K2 (NUM_PHYS_TCS_4PORT_K2 + 1) +#define NUM_OF_TCS (NUM_OF_PHYS_TCS + 1) + +#define LB_TC (NUM_OF_PHYS_TCS) + +/* Num of possible traffic priority values */ +#define NUM_OF_PRIO (8) + +#define MAX_NUM_VOQS_K2 (NUM_TCS_4PORT_K2 * MAX_NUM_PORTS_K2) +#define MAX_NUM_VOQS_BB (NUM_OF_TCS * MAX_NUM_PORTS_BB) +#define MAX_NUM_VOQS (MAX_NUM_VOQS_K2) +#define MAX_PHYS_VOQS (NUM_OF_PHYS_TCS * MAX_NUM_PORTS_BB) + +/* CIDs */ +#define NUM_OF_CONNECTION_TYPES (8) +#define NUM_OF_LCIDS (320) +#define NUM_OF_LTIDS (320) + +/*****************/ +/* CDU CONSTANTS */ +/*****************/ + +#define CDU_SEG_TYPE_OFFSET_REG_TYPE_SHIFT (17) +#define CDU_SEG_TYPE_OFFSET_REG_OFFSET_MASK (0x1ffff) + +/*****************/ +/* DQ CONSTANTS */ +/*****************/ + +/* DEMS */ +#define DQ_DEMS_LEGACY 0 + +/* XCM agg val selection */ +#define DQ_XCM_AGG_VAL_SEL_WORD2 0 +#define DQ_XCM_AGG_VAL_SEL_WORD3 1 +#define DQ_XCM_AGG_VAL_SEL_WORD4 2 +#define DQ_XCM_AGG_VAL_SEL_WORD5 3 +#define DQ_XCM_AGG_VAL_SEL_REG3 4 +#define DQ_XCM_AGG_VAL_SEL_REG4 5 +#define DQ_XCM_AGG_VAL_SEL_REG5 6 +#define DQ_XCM_AGG_VAL_SEL_REG6 7 + +/* XCM agg val selection */ +#define DQ_XCM_ETH_EDPM_NUM_BDS_CMD \ + DQ_XCM_AGG_VAL_SEL_WORD2 +#define DQ_XCM_ETH_TX_BD_CONS_CMD \ + DQ_XCM_AGG_VAL_SEL_WORD3 +#define DQ_XCM_CORE_TX_BD_CONS_CMD \ + DQ_XCM_AGG_VAL_SEL_WORD3 +#define DQ_XCM_ETH_TX_BD_PROD_CMD \ + DQ_XCM_AGG_VAL_SEL_WORD4 +#define DQ_XCM_CORE_TX_BD_PROD_CMD \ + DQ_XCM_AGG_VAL_SEL_WORD4 +#define DQ_XCM_CORE_SPQ_PROD_CMD \ + DQ_XCM_AGG_VAL_SEL_WORD4 +#define DQ_XCM_ETH_GO_TO_BD_CONS_CMD DQ_XCM_AGG_VAL_SEL_WORD5 + +/* XCM agg counter flag selection */ +#define DQ_XCM_AGG_FLG_SHIFT_BIT14 0 +#define DQ_XCM_AGG_FLG_SHIFT_BIT15 1 +#define DQ_XCM_AGG_FLG_SHIFT_CF12 2 +#define DQ_XCM_AGG_FLG_SHIFT_CF13 3 +#define DQ_XCM_AGG_FLG_SHIFT_CF18 4 +#define DQ_XCM_AGG_FLG_SHIFT_CF19 5 +#define DQ_XCM_AGG_FLG_SHIFT_CF22 6 +#define DQ_XCM_AGG_FLG_SHIFT_CF23 7 + +/* XCM agg counter flag selection */ +#define DQ_XCM_ETH_DQ_CF_CMD (1 << \ + DQ_XCM_AGG_FLG_SHIFT_CF18) +#define DQ_XCM_CORE_DQ_CF_CMD (1 << \ + DQ_XCM_AGG_FLG_SHIFT_CF18) +#define DQ_XCM_ETH_TERMINATE_CMD (1 << \ + DQ_XCM_AGG_FLG_SHIFT_CF19) +#define DQ_XCM_CORE_TERMINATE_CMD (1 << \ + DQ_XCM_AGG_FLG_SHIFT_CF19) +#define DQ_XCM_ETH_SLOW_PATH_CMD (1 << \ + DQ_XCM_AGG_FLG_SHIFT_CF22) +#define DQ_XCM_CORE_SLOW_PATH_CMD (1 << \ + DQ_XCM_AGG_FLG_SHIFT_CF22) +#define DQ_XCM_ETH_TPH_EN_CMD (1 << \ + DQ_XCM_AGG_FLG_SHIFT_CF23) + +/*****************/ +/* QM CONSTANTS */ +/*****************/ + +/* number of TX queues in the QM */ +#define MAX_QM_TX_QUEUES_K2 512 +#define MAX_QM_TX_QUEUES_BB 448 +#define MAX_QM_TX_QUEUES MAX_QM_TX_QUEUES_K2 + +/* number of Other queues in the QM */ +#define MAX_QM_OTHER_QUEUES_BB 64 +#define MAX_QM_OTHER_QUEUES_K2 128 +#define MAX_QM_OTHER_QUEUES MAX_QM_OTHER_QUEUES_K2 + +/* number of queues in a PF queue group */ +#define QM_PF_QUEUE_GROUP_SIZE 8 + +/* base number of Tx PQs in the CM PQ representation. + * should be used when storing PQ IDs in CM PQ registers and context + */ +#define CM_TX_PQ_BASE 0x200 + +/* QM registers data */ +#define QM_LINE_CRD_REG_WIDTH 16 +#define QM_LINE_CRD_REG_SIGN_BIT (1 << (QM_LINE_CRD_REG_WIDTH - 1)) +#define QM_BYTE_CRD_REG_WIDTH 24 +#define QM_BYTE_CRD_REG_SIGN_BIT (1 << (QM_BYTE_CRD_REG_WIDTH - 1)) +#define QM_WFQ_CRD_REG_WIDTH 32 +#define QM_WFQ_CRD_REG_SIGN_BIT (1 << (QM_WFQ_CRD_REG_WIDTH - 1)) +#define QM_RL_CRD_REG_WIDTH 32 +#define QM_RL_CRD_REG_SIGN_BIT (1 << (QM_RL_CRD_REG_WIDTH - 1)) + +/*****************/ +/* CAU CONSTANTS */ +/*****************/ + +#define CAU_FSM_ETH_RX 0 +#define CAU_FSM_ETH_TX 1 + +/* Number of Protocol Indices per Status Block */ +#define PIS_PER_SB 12 + +#define CAU_HC_STOPPED_STATE 3 +#define CAU_HC_DISABLE_STATE 4 +#define CAU_HC_ENABLE_STATE 0 + +/*****************/ +/* IGU CONSTANTS */ +/*****************/ + +#define MAX_SB_PER_PATH_K2 (368) +#define MAX_SB_PER_PATH_BB (288) +#define MAX_TOT_SB_PER_PATH \ + MAX_SB_PER_PATH_K2 + +#define MAX_SB_PER_PF_MIMD 129 +#define MAX_SB_PER_PF_SIMD 64 +#define MAX_SB_PER_VF 64 + +/* Memory addresses on the BAR for the IGU Sub Block */ +#define IGU_MEM_BASE 0x0000 + +#define IGU_MEM_MSIX_BASE 0x0000 +#define IGU_MEM_MSIX_UPPER 0x0101 +#define IGU_MEM_MSIX_RESERVED_UPPER 0x01ff + +#define IGU_MEM_PBA_MSIX_BASE 0x0200 +#define IGU_MEM_PBA_MSIX_UPPER 0x0202 +#define IGU_MEM_PBA_MSIX_RESERVED_UPPER 0x03ff + +#define IGU_CMD_INT_ACK_BASE 0x0400 +#define IGU_CMD_INT_ACK_UPPER (IGU_CMD_INT_ACK_BASE + \ + MAX_TOT_SB_PER_PATH - \ + 1) +#define IGU_CMD_INT_ACK_RESERVED_UPPER 0x05ff + +#define IGU_CMD_ATTN_BIT_UPD_UPPER 0x05f0 +#define IGU_CMD_ATTN_BIT_SET_UPPER 0x05f1 +#define IGU_CMD_ATTN_BIT_CLR_UPPER 0x05f2 + +#define IGU_REG_SISR_MDPC_WMASK_UPPER 0x05f3 +#define IGU_REG_SISR_MDPC_WMASK_LSB_UPPER 0x05f4 +#define IGU_REG_SISR_MDPC_WMASK_MSB_UPPER 0x05f5 +#define IGU_REG_SISR_MDPC_WOMASK_UPPER 0x05f6 + +#define IGU_CMD_PROD_UPD_BASE 0x0600 +#define IGU_CMD_PROD_UPD_UPPER (IGU_CMD_PROD_UPD_BASE +\ + MAX_TOT_SB_PER_PATH - \ + 1) +#define IGU_CMD_PROD_UPD_RESERVED_UPPER 0x07ff + +/*****************/ +/* PXP CONSTANTS */ +/*****************/ + +/* PTT and GTT */ +#define PXP_NUM_PF_WINDOWS 12 +#define PXP_PER_PF_ENTRY_SIZE 8 +#define PXP_NUM_GLOBAL_WINDOWS 243 +#define PXP_GLOBAL_ENTRY_SIZE 4 +#define PXP_ADMIN_WINDOW_ALLOWED_LENGTH 4 +#define PXP_PF_WINDOW_ADMIN_START 0 +#define PXP_PF_WINDOW_ADMIN_LENGTH 0x1000 +#define PXP_PF_WINDOW_ADMIN_END (PXP_PF_WINDOW_ADMIN_START + \ + PXP_PF_WINDOW_ADMIN_LENGTH - 1) +#define PXP_PF_WINDOW_ADMIN_PER_PF_START 0 +#define PXP_PF_WINDOW_ADMIN_PER_PF_LENGTH (PXP_NUM_PF_WINDOWS * \ + PXP_PER_PF_ENTRY_SIZE) +#define PXP_PF_WINDOW_ADMIN_PER_PF_END (PXP_PF_WINDOW_ADMIN_PER_PF_START + \ + PXP_PF_WINDOW_ADMIN_PER_PF_LENGTH - 1) +#define PXP_PF_WINDOW_ADMIN_GLOBAL_START 0x200 +#define PXP_PF_WINDOW_ADMIN_GLOBAL_LENGTH (PXP_NUM_GLOBAL_WINDOWS * \ + PXP_GLOBAL_ENTRY_SIZE) +#define PXP_PF_WINDOW_ADMIN_GLOBAL_END \ + (PXP_PF_WINDOW_ADMIN_GLOBAL_START + \ + PXP_PF_WINDOW_ADMIN_GLOBAL_LENGTH - 1) +#define PXP_PF_GLOBAL_PRETEND_ADDR 0x1f0 +#define PXP_PF_ME_OPAQUE_MASK_ADDR 0xf4 +#define PXP_PF_ME_OPAQUE_ADDR 0x1f8 +#define PXP_PF_ME_CONCRETE_ADDR 0x1fc + +#define PXP_EXTERNAL_BAR_PF_WINDOW_START 0x1000 +#define PXP_EXTERNAL_BAR_PF_WINDOW_NUM PXP_NUM_PF_WINDOWS +#define PXP_EXTERNAL_BAR_PF_WINDOW_SINGLE_SIZE 0x1000 +#define PXP_EXTERNAL_BAR_PF_WINDOW_LENGTH \ + (PXP_EXTERNAL_BAR_PF_WINDOW_NUM * \ + PXP_EXTERNAL_BAR_PF_WINDOW_SINGLE_SIZE) +#define PXP_EXTERNAL_BAR_PF_WINDOW_END \ + (PXP_EXTERNAL_BAR_PF_WINDOW_START + \ + PXP_EXTERNAL_BAR_PF_WINDOW_LENGTH - 1) + +#define PXP_EXTERNAL_BAR_GLOBAL_WINDOW_START \ + (PXP_EXTERNAL_BAR_PF_WINDOW_END + 1) +#define PXP_EXTERNAL_BAR_GLOBAL_WINDOW_NUM PXP_NUM_GLOBAL_WINDOWS +#define PXP_EXTERNAL_BAR_GLOBAL_WINDOW_SINGLE_SIZE 0x1000 +#define PXP_EXTERNAL_BAR_GLOBAL_WINDOW_LENGTH \ + (PXP_EXTERNAL_BAR_GLOBAL_WINDOW_NUM * \ + PXP_EXTERNAL_BAR_GLOBAL_WINDOW_SINGLE_SIZE) +#define PXP_EXTERNAL_BAR_GLOBAL_WINDOW_END \ + (PXP_EXTERNAL_BAR_GLOBAL_WINDOW_START + \ + PXP_EXTERNAL_BAR_GLOBAL_WINDOW_LENGTH - 1) + +#define PXP_ILT_PAGE_SIZE_NUM_BITS_MIN 12 +#define PXP_ILT_BLOCK_FACTOR_MULTIPLIER 1024 + +/* ILT Records */ +#define PXP_NUM_ILT_RECORDS_BB 7600 +#define PXP_NUM_ILT_RECORDS_K2 11000 +#define MAX_NUM_ILT_RECORDS MAX(PXP_NUM_ILT_RECORDS_BB, PXP_NUM_ILT_RECORDS_K2) + +/******************/ +/* PBF CONSTANTS */ +/******************/ + +/* Number of PBF command queue lines. Each line is 32B. */ +#define PBF_MAX_CMD_LINES 3328 + +/* Number of BTB blocks. Each block is 256B. */ +#define BTB_MAX_BLOCKS 1440 + +/*****************/ +/* PRS CONSTANTS */ +/*****************/ + +/* Async data KCQ CQE */ +struct async_data { + __le32 cid; + __le16 itid; + u8 error_code; + u8 fw_debug_param; +}; + +struct regpair { + __le32 lo; + __le32 hi; +}; + +/* Event Data Union */ +union event_ring_data { + u8 bytes[8]; + struct async_data async_info; +}; + +/* Event Ring Entry */ +struct event_ring_entry { + u8 protocol_id; + u8 opcode; + __le16 reserved0; + __le16 echo; + u8 fw_return_code; + u8 flags; +#define EVENT_RING_ENTRY_ASYNC_MASK 0x1 +#define EVENT_RING_ENTRY_ASYNC_SHIFT 0 +#define EVENT_RING_ENTRY_RESERVED1_MASK 0x7F +#define EVENT_RING_ENTRY_RESERVED1_SHIFT 1 + union event_ring_data data; +}; + +/* Multi function mode */ +enum mf_mode { + SF, + MF_OVLAN, + MF_NPAR, + MAX_MF_MODE +}; + +/* Per-protocol connection types */ +enum protocol_type { + PROTOCOLID_RESERVED1, + PROTOCOLID_RESERVED2, + PROTOCOLID_RESERVED3, + PROTOCOLID_CORE, + PROTOCOLID_ETH, + PROTOCOLID_RESERVED4, + PROTOCOLID_RESERVED5, + PROTOCOLID_PREROCE, + PROTOCOLID_COMMON, + PROTOCOLID_RESERVED6, + MAX_PROTOCOL_TYPE +}; + +/* status block structure */ +struct cau_pi_entry { + u32 prod; +#define CAU_PI_ENTRY_PROD_VAL_MASK 0xFFFF +#define CAU_PI_ENTRY_PROD_VAL_SHIFT 0 +#define CAU_PI_ENTRY_PI_TIMESET_MASK 0x7F +#define CAU_PI_ENTRY_PI_TIMESET_SHIFT 16 +#define CAU_PI_ENTRY_FSM_SEL_MASK 0x1 +#define CAU_PI_ENTRY_FSM_SEL_SHIFT 23 +#define CAU_PI_ENTRY_RESERVED_MASK 0xFF +#define CAU_PI_ENTRY_RESERVED_SHIFT 24 +}; + +/* status block structure */ +struct cau_sb_entry { + u32 data; +#define CAU_SB_ENTRY_SB_PROD_MASK 0xFFFFFF +#define CAU_SB_ENTRY_SB_PROD_SHIFT 0 +#define CAU_SB_ENTRY_STATE0_MASK 0xF +#define CAU_SB_ENTRY_STATE0_SHIFT 24 +#define CAU_SB_ENTRY_STATE1_MASK 0xF +#define CAU_SB_ENTRY_STATE1_SHIFT 28 + u32 params; +#define CAU_SB_ENTRY_SB_TIMESET0_MASK 0x7F +#define CAU_SB_ENTRY_SB_TIMESET0_SHIFT 0 +#define CAU_SB_ENTRY_SB_TIMESET1_MASK 0x7F +#define CAU_SB_ENTRY_SB_TIMESET1_SHIFT 7 +#define CAU_SB_ENTRY_TIMER_RES0_MASK 0x3 +#define CAU_SB_ENTRY_TIMER_RES0_SHIFT 14 +#define CAU_SB_ENTRY_TIMER_RES1_MASK 0x3 +#define CAU_SB_ENTRY_TIMER_RES1_SHIFT 16 +#define CAU_SB_ENTRY_VF_NUMBER_MASK 0xFF +#define CAU_SB_ENTRY_VF_NUMBER_SHIFT 18 +#define CAU_SB_ENTRY_VF_VALID_MASK 0x1 +#define CAU_SB_ENTRY_VF_VALID_SHIFT 26 +#define CAU_SB_ENTRY_PF_NUMBER_MASK 0xF +#define CAU_SB_ENTRY_PF_NUMBER_SHIFT 27 +#define CAU_SB_ENTRY_TPH_MASK 0x1 +#define CAU_SB_ENTRY_TPH_SHIFT 31 +}; + +/* core doorbell data */ +struct core_db_data { + u8 params; +#define CORE_DB_DATA_DEST_MASK 0x3 +#define CORE_DB_DATA_DEST_SHIFT 0 +#define CORE_DB_DATA_AGG_CMD_MASK 0x3 +#define CORE_DB_DATA_AGG_CMD_SHIFT 2 +#define CORE_DB_DATA_BYPASS_EN_MASK 0x1 +#define CORE_DB_DATA_BYPASS_EN_SHIFT 4 +#define CORE_DB_DATA_RESERVED_MASK 0x1 +#define CORE_DB_DATA_RESERVED_SHIFT 5 +#define CORE_DB_DATA_AGG_VAL_SEL_MASK 0x3 +#define CORE_DB_DATA_AGG_VAL_SEL_SHIFT 6 + u8 agg_flags; + __le16 spq_prod; +}; + +/* Enum of doorbell aggregative command selection */ +enum db_agg_cmd_sel { + DB_AGG_CMD_NOP, + DB_AGG_CMD_SET, + DB_AGG_CMD_ADD, + DB_AGG_CMD_MAX, + MAX_DB_AGG_CMD_SEL +}; + +/* Enum of doorbell destination */ +enum db_dest { + DB_DEST_XCM, + DB_DEST_UCM, + DB_DEST_TCM, + DB_NUM_DESTINATIONS, + MAX_DB_DEST +}; + +/* Structure for doorbell address, in legacy mode */ +struct db_legacy_addr { + __le32 addr; +#define DB_LEGACY_ADDR_RESERVED0_MASK 0x3 +#define DB_LEGACY_ADDR_RESERVED0_SHIFT 0 +#define DB_LEGACY_ADDR_DEMS_MASK 0x7 +#define DB_LEGACY_ADDR_DEMS_SHIFT 2 +#define DB_LEGACY_ADDR_ICID_MASK 0x7FFFFFF +#define DB_LEGACY_ADDR_ICID_SHIFT 5 +}; + +/* Igu interrupt command */ +enum igu_int_cmd { + IGU_INT_ENABLE = 0, + IGU_INT_DISABLE = 1, + IGU_INT_NOP = 2, + IGU_INT_NOP2 = 3, + MAX_IGU_INT_CMD +}; + +/* IGU producer or consumer update command */ +struct igu_prod_cons_update { + u32 sb_id_and_flags; +#define IGU_PROD_CONS_UPDATE_SB_INDEX_MASK 0xFFFFFF +#define IGU_PROD_CONS_UPDATE_SB_INDEX_SHIFT 0 +#define IGU_PROD_CONS_UPDATE_UPDATE_FLAG_MASK 0x1 +#define IGU_PROD_CONS_UPDATE_UPDATE_FLAG_SHIFT 24 +#define IGU_PROD_CONS_UPDATE_ENABLE_INT_MASK 0x3 +#define IGU_PROD_CONS_UPDATE_ENABLE_INT_SHIFT 25 +#define IGU_PROD_CONS_UPDATE_SEGMENT_ACCESS_MASK 0x1 +#define IGU_PROD_CONS_UPDATE_SEGMENT_ACCESS_SHIFT 27 +#define IGU_PROD_CONS_UPDATE_TIMER_MASK_MASK 0x1 +#define IGU_PROD_CONS_UPDATE_TIMER_MASK_SHIFT 28 +#define IGU_PROD_CONS_UPDATE_RESERVED0_MASK 0x3 +#define IGU_PROD_CONS_UPDATE_RESERVED0_SHIFT 29 +#define IGU_PROD_CONS_UPDATE_COMMAND_TYPE_MASK 0x1 +#define IGU_PROD_CONS_UPDATE_COMMAND_TYPE_SHIFT 31 + u32 reserved1; +}; + +/* Igu segments access for default status block only */ +enum igu_seg_access { + IGU_SEG_ACCESS_REG = 0, + IGU_SEG_ACCESS_ATTN = 1, + MAX_IGU_SEG_ACCESS +}; + +struct parsing_and_err_flags { + __le16 flags; +#define PARSING_AND_ERR_FLAGS_L3TYPE_MASK 0x3 +#define PARSING_AND_ERR_FLAGS_L3TYPE_SHIFT 0 +#define PARSING_AND_ERR_FLAGS_L4PROTOCOL_MASK 0x3 +#define PARSING_AND_ERR_FLAGS_L4PROTOCOL_SHIFT 2 +#define PARSING_AND_ERR_FLAGS_IPV4FRAG_MASK 0x1 +#define PARSING_AND_ERR_FLAGS_IPV4FRAG_SHIFT 4 +#define PARSING_AND_ERR_FLAGS_TAG8021QEXIST_MASK 0x1 +#define PARSING_AND_ERR_FLAGS_TAG8021QEXIST_SHIFT 5 +#define PARSING_AND_ERR_FLAGS_L4CHKSMWASCALCULATED_MASK 0x1 +#define PARSING_AND_ERR_FLAGS_L4CHKSMWASCALCULATED_SHIFT 6 +#define PARSING_AND_ERR_FLAGS_TIMESYNCPKT_MASK 0x1 +#define PARSING_AND_ERR_FLAGS_TIMESYNCPKT_SHIFT 7 +#define PARSING_AND_ERR_FLAGS_TIMESTAMPRECORDED_MASK 0x1 +#define PARSING_AND_ERR_FLAGS_TIMESTAMPRECORDED_SHIFT 8 +#define PARSING_AND_ERR_FLAGS_IPHDRERROR_MASK 0x1 +#define PARSING_AND_ERR_FLAGS_IPHDRERROR_SHIFT 9 +#define PARSING_AND_ERR_FLAGS_L4CHKSMERROR_MASK 0x1 +#define PARSING_AND_ERR_FLAGS_L4CHKSMERROR_SHIFT 10 +#define PARSING_AND_ERR_FLAGS_TUNNELEXIST_MASK 0x1 +#define PARSING_AND_ERR_FLAGS_TUNNELEXIST_SHIFT 11 +#define PARSING_AND_ERR_FLAGS_TUNNEL8021QTAGEXIST_MASK 0x1 +#define PARSING_AND_ERR_FLAGS_TUNNEL8021QTAGEXIST_SHIFT 12 +#define PARSING_AND_ERR_FLAGS_TUNNELIPHDRERROR_MASK 0x1 +#define PARSING_AND_ERR_FLAGS_TUNNELIPHDRERROR_SHIFT 13 +#define PARSING_AND_ERR_FLAGS_TUNNELL4CHKSMWASCALCULATED_MASK 0x1 +#define PARSING_AND_ERR_FLAGS_TUNNELL4CHKSMWASCALCULATED_SHIFT 14 +#define PARSING_AND_ERR_FLAGS_TUNNELL4CHKSMERROR_MASK 0x1 +#define PARSING_AND_ERR_FLAGS_TUNNELL4CHKSMERROR_SHIFT 15 +}; + +/* Concrete Function ID. */ +struct pxp_concrete_fid { + __le16 fid; +#define PXP_CONCRETE_FID_PFID_MASK 0xF +#define PXP_CONCRETE_FID_PFID_SHIFT 0 +#define PXP_CONCRETE_FID_PORT_MASK 0x3 +#define PXP_CONCRETE_FID_PORT_SHIFT 4 +#define PXP_CONCRETE_FID_PATH_MASK 0x1 +#define PXP_CONCRETE_FID_PATH_SHIFT 6 +#define PXP_CONCRETE_FID_VFVALID_MASK 0x1 +#define PXP_CONCRETE_FID_VFVALID_SHIFT 7 +#define PXP_CONCRETE_FID_VFID_MASK 0xFF +#define PXP_CONCRETE_FID_VFID_SHIFT 8 +}; + +struct pxp_pretend_concrete_fid { + __le16 fid; +#define PXP_PRETEND_CONCRETE_FID_PFID_MASK 0xF +#define PXP_PRETEND_CONCRETE_FID_PFID_SHIFT 0 +#define PXP_PRETEND_CONCRETE_FID_RESERVED_MASK 0x7 +#define PXP_PRETEND_CONCRETE_FID_RESERVED_SHIFT 4 +#define PXP_PRETEND_CONCRETE_FID_VFVALID_MASK 0x1 +#define PXP_PRETEND_CONCRETE_FID_VFVALID_SHIFT 7 +#define PXP_PRETEND_CONCRETE_FID_VFID_MASK 0xFF +#define PXP_PRETEND_CONCRETE_FID_VFID_SHIFT 8 +}; + +union pxp_pretend_fid { + struct pxp_pretend_concrete_fid concrete_fid; + __le16 opaque_fid; +}; + +/* Pxp Pretend Command Register. */ +struct pxp_pretend_cmd { + union pxp_pretend_fid fid; + __le16 control; +#define PXP_PRETEND_CMD_PATH_MASK 0x1 +#define PXP_PRETEND_CMD_PATH_SHIFT 0 +#define PXP_PRETEND_CMD_USE_PORT_MASK 0x1 +#define PXP_PRETEND_CMD_USE_PORT_SHIFT 1 +#define PXP_PRETEND_CMD_PORT_MASK 0x3 +#define PXP_PRETEND_CMD_PORT_SHIFT 2 +#define PXP_PRETEND_CMD_RESERVED0_MASK 0xF +#define PXP_PRETEND_CMD_RESERVED0_SHIFT 4 +#define PXP_PRETEND_CMD_RESERVED1_MASK 0xF +#define PXP_PRETEND_CMD_RESERVED1_SHIFT 8 +#define PXP_PRETEND_CMD_PRETEND_PATH_MASK 0x1 +#define PXP_PRETEND_CMD_PRETEND_PATH_SHIFT 12 +#define PXP_PRETEND_CMD_PRETEND_PORT_MASK 0x1 +#define PXP_PRETEND_CMD_PRETEND_PORT_SHIFT 13 +#define PXP_PRETEND_CMD_PRETEND_FUNCTION_MASK 0x1 +#define PXP_PRETEND_CMD_PRETEND_FUNCTION_SHIFT 14 +#define PXP_PRETEND_CMD_IS_CONCRETE_MASK 0x1 +#define PXP_PRETEND_CMD_IS_CONCRETE_SHIFT 15 +}; + +/* PTT Record in PXP Admin Window. */ +struct pxp_ptt_entry { + __le32 offset; +#define PXP_PTT_ENTRY_OFFSET_MASK 0x7FFFFF +#define PXP_PTT_ENTRY_OFFSET_SHIFT 0 +#define PXP_PTT_ENTRY_RESERVED0_MASK 0x1FF +#define PXP_PTT_ENTRY_RESERVED0_SHIFT 23 + struct pxp_pretend_cmd pretend; +}; + +/* RSS hash type */ +enum rss_hash_type { + RSS_HASH_TYPE_DEFAULT = 0, + RSS_HASH_TYPE_IPV4 = 1, + RSS_HASH_TYPE_TCP_IPV4 = 2, + RSS_HASH_TYPE_IPV6 = 3, + RSS_HASH_TYPE_TCP_IPV6 = 4, + RSS_HASH_TYPE_UDP_IPV4 = 5, + RSS_HASH_TYPE_UDP_IPV6 = 6, + MAX_RSS_HASH_TYPE +}; + +/* status block structure */ +struct status_block { + __le16 pi_array[PIS_PER_SB]; + __le32 sb_num; +#define STATUS_BLOCK_SB_NUM_MASK 0x1FF +#define STATUS_BLOCK_SB_NUM_SHIFT 0 +#define STATUS_BLOCK_ZERO_PAD_MASK 0x7F +#define STATUS_BLOCK_ZERO_PAD_SHIFT 9 +#define STATUS_BLOCK_ZERO_PAD2_MASK 0xFFFF +#define STATUS_BLOCK_ZERO_PAD2_SHIFT 16 + __le32 prod_index; +#define STATUS_BLOCK_PROD_INDEX_MASK 0xFFFFFF +#define STATUS_BLOCK_PROD_INDEX_SHIFT 0 +#define STATUS_BLOCK_ZERO_PAD3_MASK 0xFF +#define STATUS_BLOCK_ZERO_PAD3_SHIFT 24 +}; + +#endif /* __COMMON_HSI__ */ diff --git a/include/linux/qed/qed_chain.h b/include/linux/qed/qed_chain.h new file mode 100644 index 000000000000..b920c3605c46 --- /dev/null +++ b/include/linux/qed/qed_chain.h @@ -0,0 +1,539 @@ +/* QLogic qed NIC Driver + * Copyright (c) 2015 QLogic Corporation + * + * This software is available under the terms of the GNU General Public License + * (GPL) Version 2, available from the file COPYING in the main directory of + * this source tree. + */ + +#ifndef _QED_CHAIN_H +#define _QED_CHAIN_H + +#include +#include +#include +#include +#include +#include + +/* dma_addr_t manip */ +#define DMA_LO_LE(x) cpu_to_le32(lower_32_bits(x)) +#define DMA_HI_LE(x) cpu_to_le32(upper_32_bits(x)) + +#define HILO_GEN(hi, lo, type) ((((type)(hi)) << 32) + (lo)) +#define HILO_DMA(hi, lo) HILO_GEN(hi, lo, dma_addr_t) +#define HILO_64(hi, lo) HILO_GEN((le32_to_cpu(hi)), (le32_to_cpu(lo)), u64) +#define HILO_DMA_REGPAIR(regpair) (HILO_DMA(regpair.hi, regpair.lo)) +#define HILO_64_REGPAIR(regpair) (HILO_64(regpair.hi, regpair.lo)) + +enum qed_chain_mode { + /* Each Page contains a next pointer at its end */ + QED_CHAIN_MODE_NEXT_PTR, + + /* Chain is a single page (next ptr) is unrequired */ + QED_CHAIN_MODE_SINGLE, + + /* Page pointers are located in a side list */ + QED_CHAIN_MODE_PBL, +}; + +enum qed_chain_use_mode { + QED_CHAIN_USE_TO_PRODUCE, /* Chain starts empty */ + QED_CHAIN_USE_TO_CONSUME, /* Chain starts full */ + QED_CHAIN_USE_TO_CONSUME_PRODUCE, /* Chain starts empty */ +}; + +struct qed_chain_next { + struct regpair next_phys; + void *next_virt; +}; + +struct qed_chain_pbl { + dma_addr_t p_phys_table; + void *p_virt_table; + u16 prod_page_idx; + u16 cons_page_idx; +}; + +struct qed_chain { + void *p_virt_addr; + dma_addr_t p_phys_addr; + void *p_prod_elem; + void *p_cons_elem; + u16 page_cnt; + enum qed_chain_mode mode; + enum qed_chain_use_mode intended_use; /* used to produce/consume */ + u16 capacity; /*< number of _usable_ elements */ + u16 size; /* number of elements */ + u16 prod_idx; + u16 cons_idx; + u16 elem_per_page; + u16 elem_per_page_mask; + u16 elem_unusable; + u16 usable_per_page; + u16 elem_size; + u16 next_page_mask; + struct qed_chain_pbl pbl; +}; + +#define QED_CHAIN_PBL_ENTRY_SIZE (8) +#define QED_CHAIN_PAGE_SIZE (0x1000) +#define ELEMS_PER_PAGE(elem_size) (QED_CHAIN_PAGE_SIZE / (elem_size)) + +#define UNUSABLE_ELEMS_PER_PAGE(elem_size, mode) \ + ((mode == QED_CHAIN_MODE_NEXT_PTR) ? \ + (1 + ((sizeof(struct qed_chain_next) - 1) / \ + (elem_size))) : 0) + +#define USABLE_ELEMS_PER_PAGE(elem_size, mode) \ + ((u32)(ELEMS_PER_PAGE(elem_size) - \ + UNUSABLE_ELEMS_PER_PAGE(elem_size, mode))) + +#define QED_CHAIN_PAGE_CNT(elem_cnt, elem_size, mode) \ + DIV_ROUND_UP(elem_cnt, USABLE_ELEMS_PER_PAGE(elem_size, mode)) + +/* Accessors */ +static inline u16 qed_chain_get_prod_idx(struct qed_chain *p_chain) +{ + return p_chain->prod_idx; +} + +static inline u16 qed_chain_get_cons_idx(struct qed_chain *p_chain) +{ + return p_chain->cons_idx; +} + +static inline u16 qed_chain_get_elem_left(struct qed_chain *p_chain) +{ + u16 used; + + /* we don't need to trancate upon assignmet, as we assign u32->u16 */ + used = ((u32)0x10000u + (u32)(p_chain->prod_idx)) - + (u32)p_chain->cons_idx; + if (p_chain->mode == QED_CHAIN_MODE_NEXT_PTR) + used -= (used / p_chain->elem_per_page); + + return p_chain->capacity - used; +} + +static inline u8 qed_chain_is_full(struct qed_chain *p_chain) +{ + return qed_chain_get_elem_left(p_chain) == p_chain->capacity; +} + +static inline u8 qed_chain_is_empty(struct qed_chain *p_chain) +{ + return qed_chain_get_elem_left(p_chain) == 0; +} + +static inline u16 qed_chain_get_elem_per_page( + struct qed_chain *p_chain) +{ + return p_chain->elem_per_page; +} + +static inline u16 qed_chain_get_usable_per_page( + struct qed_chain *p_chain) +{ + return p_chain->usable_per_page; +} + +static inline u16 qed_chain_get_unusable_per_page( + struct qed_chain *p_chain) +{ + return p_chain->elem_unusable; +} + +static inline u16 qed_chain_get_size(struct qed_chain *p_chain) +{ + return p_chain->size; +} + +static inline dma_addr_t +qed_chain_get_pbl_phys(struct qed_chain *p_chain) +{ + return p_chain->pbl.p_phys_table; +} + +/** + * @brief qed_chain_advance_page - + * + * Advance the next element accros pages for a linked chain + * + * @param p_chain + * @param p_next_elem + * @param idx_to_inc + * @param page_to_inc + */ +static inline void +qed_chain_advance_page(struct qed_chain *p_chain, + void **p_next_elem, + u16 *idx_to_inc, + u16 *page_to_inc) + +{ + switch (p_chain->mode) { + case QED_CHAIN_MODE_NEXT_PTR: + { + struct qed_chain_next *p_next = *p_next_elem; + *p_next_elem = p_next->next_virt; + *idx_to_inc += p_chain->elem_unusable; + break; + } + case QED_CHAIN_MODE_SINGLE: + *p_next_elem = p_chain->p_virt_addr; + break; + + case QED_CHAIN_MODE_PBL: + /* It is assumed pages are sequential, next element needs + * to change only when passing going back to first from last. + */ + if (++(*page_to_inc) == p_chain->page_cnt) { + *page_to_inc = 0; + *p_next_elem = p_chain->p_virt_addr; + } + } +} + +#define is_unusable_idx(p, idx) \ + (((p)->idx & (p)->elem_per_page_mask) == (p)->usable_per_page) + +#define is_unusable_next_idx(p, idx) \ + ((((p)->idx + 1) & (p)->elem_per_page_mask) == (p)->usable_per_page) + +#define test_ans_skip(p, idx) \ + do { \ + if (is_unusable_idx(p, idx)) { \ + (p)->idx += (p)->elem_unusable; \ + } \ + } while (0) + +/** + * @brief qed_chain_return_multi_produced - + * + * A chain in which the driver "Produces" elements should use this API + * to indicate previous produced elements are now consumed. + * + * @param p_chain + * @param num + */ +static inline void +qed_chain_return_multi_produced(struct qed_chain *p_chain, + u16 num) +{ + p_chain->cons_idx += num; + test_ans_skip(p_chain, cons_idx); +} + +/** + * @brief qed_chain_return_produced - + * + * A chain in which the driver "Produces" elements should use this API + * to indicate previous produced elements are now consumed. + * + * @param p_chain + */ +static inline void qed_chain_return_produced(struct qed_chain *p_chain) +{ + p_chain->cons_idx++; + test_ans_skip(p_chain, cons_idx); +} + +/** + * @brief qed_chain_produce - + * + * A chain in which the driver "Produces" elements should use this to get + * a pointer to the next element which can be "Produced". It's driver + * responsibility to validate that the chain has room for new element. + * + * @param p_chain + * + * @return void*, a pointer to next element + */ +static inline void *qed_chain_produce(struct qed_chain *p_chain) +{ + void *ret = NULL; + + if ((p_chain->prod_idx & p_chain->elem_per_page_mask) == + p_chain->next_page_mask) { + qed_chain_advance_page(p_chain, &p_chain->p_prod_elem, + &p_chain->prod_idx, + &p_chain->pbl.prod_page_idx); + } + + ret = p_chain->p_prod_elem; + p_chain->prod_idx++; + p_chain->p_prod_elem = (void *)(((u8 *)p_chain->p_prod_elem) + + p_chain->elem_size); + + return ret; +} + +/** + * @brief qed_chain_get_capacity - + * + * Get the maximum number of BDs in chain + * + * @param p_chain + * @param num + * + * @return u16, number of unusable BDs + */ +static inline u16 qed_chain_get_capacity(struct qed_chain *p_chain) +{ + return p_chain->capacity; +} + +/** + * @brief qed_chain_recycle_consumed - + * + * Returns an element which was previously consumed; + * Increments producers so they could be written to FW. + * + * @param p_chain + */ +static inline void +qed_chain_recycle_consumed(struct qed_chain *p_chain) +{ + test_ans_skip(p_chain, prod_idx); + p_chain->prod_idx++; +} + +/** + * @brief qed_chain_consume - + * + * A Chain in which the driver utilizes data written by a different source + * (i.e., FW) should use this to access passed buffers. + * + * @param p_chain + * + * @return void*, a pointer to the next buffer written + */ +static inline void *qed_chain_consume(struct qed_chain *p_chain) +{ + void *ret = NULL; + + if ((p_chain->cons_idx & p_chain->elem_per_page_mask) == + p_chain->next_page_mask) { + qed_chain_advance_page(p_chain, &p_chain->p_cons_elem, + &p_chain->cons_idx, + &p_chain->pbl.cons_page_idx); + } + + ret = p_chain->p_cons_elem; + p_chain->cons_idx++; + p_chain->p_cons_elem = (void *)(((u8 *)p_chain->p_cons_elem) + + p_chain->elem_size); + + return ret; +} + +/** + * @brief qed_chain_reset - Resets the chain to its start state + * + * @param p_chain pointer to a previously allocted chain + */ +static inline void qed_chain_reset(struct qed_chain *p_chain) +{ + int i; + + p_chain->prod_idx = 0; + p_chain->cons_idx = 0; + p_chain->p_cons_elem = p_chain->p_virt_addr; + p_chain->p_prod_elem = p_chain->p_virt_addr; + + if (p_chain->mode == QED_CHAIN_MODE_PBL) { + p_chain->pbl.prod_page_idx = p_chain->page_cnt - 1; + p_chain->pbl.cons_page_idx = p_chain->page_cnt - 1; + } + + switch (p_chain->intended_use) { + case QED_CHAIN_USE_TO_CONSUME_PRODUCE: + case QED_CHAIN_USE_TO_PRODUCE: + /* Do nothing */ + break; + + case QED_CHAIN_USE_TO_CONSUME: + /* produce empty elements */ + for (i = 0; i < p_chain->capacity; i++) + qed_chain_recycle_consumed(p_chain); + break; + } +} + +/** + * @brief qed_chain_init - Initalizes a basic chain struct + * + * @param p_chain + * @param p_virt_addr + * @param p_phys_addr physical address of allocated buffer's beginning + * @param page_cnt number of pages in the allocated buffer + * @param elem_size size of each element in the chain + * @param intended_use + * @param mode + */ +static inline void qed_chain_init(struct qed_chain *p_chain, + void *p_virt_addr, + dma_addr_t p_phys_addr, + u16 page_cnt, + u8 elem_size, + enum qed_chain_use_mode intended_use, + enum qed_chain_mode mode) +{ + /* chain fixed parameters */ + p_chain->p_virt_addr = p_virt_addr; + p_chain->p_phys_addr = p_phys_addr; + p_chain->elem_size = elem_size; + p_chain->page_cnt = page_cnt; + p_chain->mode = mode; + + p_chain->intended_use = intended_use; + p_chain->elem_per_page = ELEMS_PER_PAGE(elem_size); + p_chain->usable_per_page = + USABLE_ELEMS_PER_PAGE(elem_size, mode); + p_chain->capacity = p_chain->usable_per_page * page_cnt; + p_chain->size = p_chain->elem_per_page * page_cnt; + p_chain->elem_per_page_mask = p_chain->elem_per_page - 1; + + p_chain->elem_unusable = UNUSABLE_ELEMS_PER_PAGE(elem_size, mode); + + p_chain->next_page_mask = (p_chain->usable_per_page & + p_chain->elem_per_page_mask); + + if (mode == QED_CHAIN_MODE_NEXT_PTR) { + struct qed_chain_next *p_next; + u16 i; + + for (i = 0; i < page_cnt - 1; i++) { + /* Increment mem_phy to the next page. */ + p_phys_addr += QED_CHAIN_PAGE_SIZE; + + /* Initialize the physical address of the next page. */ + p_next = (struct qed_chain_next *)((u8 *)p_virt_addr + + elem_size * + p_chain-> + usable_per_page); + + p_next->next_phys.lo = DMA_LO_LE(p_phys_addr); + p_next->next_phys.hi = DMA_HI_LE(p_phys_addr); + + /* Initialize the virtual address of the next page. */ + p_next->next_virt = (void *)((u8 *)p_virt_addr + + QED_CHAIN_PAGE_SIZE); + + /* Move to the next page. */ + p_virt_addr = p_next->next_virt; + } + + /* Last page's next should point to beginning of the chain */ + p_next = (struct qed_chain_next *)((u8 *)p_virt_addr + + elem_size * + p_chain->usable_per_page); + + p_next->next_phys.lo = DMA_LO_LE(p_chain->p_phys_addr); + p_next->next_phys.hi = DMA_HI_LE(p_chain->p_phys_addr); + p_next->next_virt = p_chain->p_virt_addr; + } + qed_chain_reset(p_chain); +} + +/** + * @brief qed_chain_pbl_init - Initalizes a basic pbl chain + * struct + * @param p_chain + * @param p_virt_addr virtual address of allocated buffer's beginning + * @param p_phys_addr physical address of allocated buffer's beginning + * @param page_cnt number of pages in the allocated buffer + * @param elem_size size of each element in the chain + * @param use_mode + * @param p_phys_pbl pointer to a pre-allocated side table + * which will hold physical page addresses. + * @param p_virt_pbl pointer to a pre allocated side table + * which will hold virtual page addresses. + */ +static inline void +qed_chain_pbl_init(struct qed_chain *p_chain, + void *p_virt_addr, + dma_addr_t p_phys_addr, + u16 page_cnt, + u8 elem_size, + enum qed_chain_use_mode use_mode, + dma_addr_t p_phys_pbl, + dma_addr_t *p_virt_pbl) +{ + dma_addr_t *p_pbl_dma = p_virt_pbl; + int i; + + qed_chain_init(p_chain, p_virt_addr, p_phys_addr, page_cnt, + elem_size, use_mode, QED_CHAIN_MODE_PBL); + + p_chain->pbl.p_phys_table = p_phys_pbl; + p_chain->pbl.p_virt_table = p_virt_pbl; + + /* Fill the PBL with physical addresses*/ + for (i = 0; i < page_cnt; i++) { + *p_pbl_dma = p_phys_addr; + p_phys_addr += QED_CHAIN_PAGE_SIZE; + p_pbl_dma++; + } +} + +/** + * @brief qed_chain_set_prod - sets the prod to the given + * value + * + * @param prod_idx + * @param p_prod_elem + */ +static inline void qed_chain_set_prod(struct qed_chain *p_chain, + u16 prod_idx, + void *p_prod_elem) +{ + p_chain->prod_idx = prod_idx; + p_chain->p_prod_elem = p_prod_elem; +} + +/** + * @brief qed_chain_get_elem - + * + * get a pointer to an element represented by absolute idx + * + * @param p_chain + * @assumption p_chain->size is a power of 2 + * + * @return void*, a pointer to next element + */ +static inline void *qed_chain_sge_get_elem(struct qed_chain *p_chain, + u16 idx) +{ + void *ret = NULL; + + if (idx >= p_chain->size) + return NULL; + + ret = (u8 *)p_chain->p_virt_addr + p_chain->elem_size * idx; + + return ret; +} + +/** + * @brief qed_chain_sge_inc_cons_prod + * + * for sge chains, producer isn't increased serially, the ring + * is expected to be full at all times. Once elements are + * consumed, they are immediately produced. + * + * @param p_chain + * @param cnt + * + * @return inline void + */ +static inline void +qed_chain_sge_inc_cons_prod(struct qed_chain *p_chain, + u16 cnt) +{ + p_chain->prod_idx += cnt; + p_chain->cons_idx += cnt; +} + +#endif diff --git a/include/linux/qed/qed_if.h b/include/linux/qed/qed_if.h new file mode 100644 index 000000000000..dc9a1353f971 --- /dev/null +++ b/include/linux/qed/qed_if.h @@ -0,0 +1,498 @@ +/* QLogic qed NIC Driver + * + * Copyright (c) 2015 QLogic Corporation + * + * This software is available under the terms of the GNU General Public License + * (GPL) Version 2, available from the file COPYING in the main directory of + * this source tree. + */ + +#ifndef _QED_IF_H +#define _QED_IF_H + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#define DIRECT_REG_WR(reg_addr, val) writel((u32)val, \ + (void __iomem *)(reg_addr)) + +#define DIRECT_REG_RD(reg_addr) readl((void __iomem *)(reg_addr)) + +#define QED_COALESCE_MAX 0xFF + +/* forward */ +struct qed_dev; + +struct qed_eth_pf_params { + /* The following parameters are used during HW-init + * and these parameters need to be passed as arguments + * to update_pf_params routine invoked before slowpath start + */ + u16 num_cons; +}; + +struct qed_pf_params { + struct qed_eth_pf_params eth_pf_params; +}; + +enum qed_int_mode { + QED_INT_MODE_INTA, + QED_INT_MODE_MSIX, + QED_INT_MODE_MSI, + QED_INT_MODE_POLL, +}; + +struct qed_sb_info { + struct status_block *sb_virt; + dma_addr_t sb_phys; + u32 sb_ack; /* Last given ack */ + u16 igu_sb_id; + void __iomem *igu_addr; + u8 flags; +#define QED_SB_INFO_INIT 0x1 +#define QED_SB_INFO_SETUP 0x2 + + struct qed_dev *cdev; +}; + +struct qed_dev_info { + unsigned long pci_mem_start; + unsigned long pci_mem_end; + unsigned int pci_irq; + u8 num_hwfns; + + u8 hw_mac[ETH_ALEN]; + bool is_mf; + + /* FW version */ + u16 fw_major; + u16 fw_minor; + u16 fw_rev; + u16 fw_eng; + + /* MFW version */ + u32 mfw_rev; + + u32 flash_size; + u8 mf_mode; +}; + +enum qed_sb_type { + QED_SB_TYPE_L2_QUEUE, +}; + +enum qed_protocol { + QED_PROTOCOL_ETH, +}; + +struct qed_link_params { + bool link_up; + +#define QED_LINK_OVERRIDE_SPEED_AUTONEG BIT(0) +#define QED_LINK_OVERRIDE_SPEED_ADV_SPEEDS BIT(1) +#define QED_LINK_OVERRIDE_SPEED_FORCED_SPEED BIT(2) +#define QED_LINK_OVERRIDE_PAUSE_CONFIG BIT(3) + u32 override_flags; + bool autoneg; + u32 adv_speeds; + u32 forced_speed; +#define QED_LINK_PAUSE_AUTONEG_ENABLE BIT(0) +#define QED_LINK_PAUSE_RX_ENABLE BIT(1) +#define QED_LINK_PAUSE_TX_ENABLE BIT(2) + u32 pause_config; +}; + +struct qed_link_output { + bool link_up; + + u32 supported_caps; /* In SUPPORTED defs */ + u32 advertised_caps; /* In ADVERTISED defs */ + u32 lp_caps; /* In ADVERTISED defs */ + u32 speed; /* In Mb/s */ + u8 duplex; /* In DUPLEX defs */ + u8 port; /* In PORT defs */ + bool autoneg; + u32 pause_config; +}; + +#define QED_DRV_VER_STR_SIZE 12 +struct qed_slowpath_params { + u32 int_mode; + u8 drv_major; + u8 drv_minor; + u8 drv_rev; + u8 drv_eng; + u8 name[QED_DRV_VER_STR_SIZE]; +}; + +#define ILT_PAGE_SIZE_TCFC 0x8000 /* 32KB */ + +struct qed_int_info { + struct msix_entry *msix; + u8 msix_cnt; + + /* This should be updated by the protocol driver */ + u8 used_cnt; +}; + +struct qed_common_cb_ops { + void (*link_update)(void *dev, + struct qed_link_output *link); +}; + +struct qed_common_ops { + struct qed_dev* (*probe)(struct pci_dev *dev, + enum qed_protocol protocol, + u32 dp_module, u8 dp_level); + + void (*remove)(struct qed_dev *cdev); + + int (*set_power_state)(struct qed_dev *cdev, + pci_power_t state); + + void (*set_id)(struct qed_dev *cdev, + char name[], + char ver_str[]); + + /* Client drivers need to make this call before slowpath_start. + * PF params required for the call before slowpath_start is + * documented within the qed_pf_params structure definition. + */ + void (*update_pf_params)(struct qed_dev *cdev, + struct qed_pf_params *params); + int (*slowpath_start)(struct qed_dev *cdev, + struct qed_slowpath_params *params); + + int (*slowpath_stop)(struct qed_dev *cdev); + + /* Requests to use `cnt' interrupts for fastpath. + * upon success, returns number of interrupts allocated for fastpath. + */ + int (*set_fp_int)(struct qed_dev *cdev, + u16 cnt); + + /* Fills `info' with pointers required for utilizing interrupts */ + int (*get_fp_int)(struct qed_dev *cdev, + struct qed_int_info *info); + + u32 (*sb_init)(struct qed_dev *cdev, + struct qed_sb_info *sb_info, + void *sb_virt_addr, + dma_addr_t sb_phy_addr, + u16 sb_id, + enum qed_sb_type type); + + u32 (*sb_release)(struct qed_dev *cdev, + struct qed_sb_info *sb_info, + u16 sb_id); + + void (*simd_handler_config)(struct qed_dev *cdev, + void *token, + int index, + void (*handler)(void *)); + + void (*simd_handler_clean)(struct qed_dev *cdev, + int index); +/** + * @brief set_link - set links according to params + * + * @param cdev + * @param params - values used to override the default link configuration + * + * @return 0 on success, error otherwise. + */ + int (*set_link)(struct qed_dev *cdev, + struct qed_link_params *params); + +/** + * @brief get_link - returns the current link state. + * + * @param cdev + * @param if_link - structure to be filled with current link configuration. + */ + void (*get_link)(struct qed_dev *cdev, + struct qed_link_output *if_link); + +/** + * @brief - drains chip in case Tx completions fail to arrive due to pause. + * + * @param cdev + */ + int (*drain)(struct qed_dev *cdev); + +/** + * @brief update_msglvl - update module debug level + * + * @param cdev + * @param dp_module + * @param dp_level + */ + void (*update_msglvl)(struct qed_dev *cdev, + u32 dp_module, + u8 dp_level); + + int (*chain_alloc)(struct qed_dev *cdev, + enum qed_chain_use_mode intended_use, + enum qed_chain_mode mode, + u16 num_elems, + size_t elem_size, + struct qed_chain *p_chain); + + void (*chain_free)(struct qed_dev *cdev, + struct qed_chain *p_chain); +}; + +/** + * @brief qed_get_protocol_version + * + * @param protocol + * + * @return version supported by qed for given protocol driver + */ +u32 qed_get_protocol_version(enum qed_protocol protocol); + +#define MASK_FIELD(_name, _value) \ + ((_value) &= (_name ## _MASK)) + +#define FIELD_VALUE(_name, _value) \ + ((_value & _name ## _MASK) << _name ## _SHIFT) + +#define SET_FIELD(value, name, flag) \ + do { \ + (value) &= ~(name ## _MASK << name ## _SHIFT); \ + (value) |= (((u64)flag) << (name ## _SHIFT)); \ + } while (0) + +#define GET_FIELD(value, name) \ + (((value) >> (name ## _SHIFT)) & name ## _MASK) + +/* Debug print definitions */ +#define DP_ERR(cdev, fmt, ...) \ + pr_err("[%s:%d(%s)]" fmt, \ + __func__, __LINE__, \ + DP_NAME(cdev) ? DP_NAME(cdev) : "", \ + ## __VA_ARGS__) \ + +#define DP_NOTICE(cdev, fmt, ...) \ + do { \ + if (unlikely((cdev)->dp_level <= QED_LEVEL_NOTICE)) { \ + pr_notice("[%s:%d(%s)]" fmt, \ + __func__, __LINE__, \ + DP_NAME(cdev) ? DP_NAME(cdev) : "", \ + ## __VA_ARGS__); \ + \ + } \ + } while (0) + +#define DP_INFO(cdev, fmt, ...) \ + do { \ + if (unlikely((cdev)->dp_level <= QED_LEVEL_INFO)) { \ + pr_notice("[%s:%d(%s)]" fmt, \ + __func__, __LINE__, \ + DP_NAME(cdev) ? DP_NAME(cdev) : "", \ + ## __VA_ARGS__); \ + } \ + } while (0) + +#define DP_VERBOSE(cdev, module, fmt, ...) \ + do { \ + if (unlikely(((cdev)->dp_level <= QED_LEVEL_VERBOSE) && \ + ((cdev)->dp_module & module))) { \ + pr_notice("[%s:%d(%s)]" fmt, \ + __func__, __LINE__, \ + DP_NAME(cdev) ? DP_NAME(cdev) : "", \ + ## __VA_ARGS__); \ + } \ + } while (0) + +enum DP_LEVEL { + QED_LEVEL_VERBOSE = 0x0, + QED_LEVEL_INFO = 0x1, + QED_LEVEL_NOTICE = 0x2, + QED_LEVEL_ERR = 0x3, +}; + +#define QED_LOG_LEVEL_SHIFT (30) +#define QED_LOG_VERBOSE_MASK (0x3fffffff) +#define QED_LOG_INFO_MASK (0x40000000) +#define QED_LOG_NOTICE_MASK (0x80000000) + +enum DP_MODULE { + QED_MSG_SPQ = 0x10000, + QED_MSG_STATS = 0x20000, + QED_MSG_DCB = 0x40000, + QED_MSG_IOV = 0x80000, + QED_MSG_SP = 0x100000, + QED_MSG_STORAGE = 0x200000, + QED_MSG_CXT = 0x800000, + QED_MSG_ILT = 0x2000000, + QED_MSG_ROCE = 0x4000000, + QED_MSG_DEBUG = 0x8000000, + /* to be added...up to 0x8000000 */ +}; + +struct qed_eth_stats { + u64 no_buff_discards; + u64 packet_too_big_discard; + u64 ttl0_discard; + u64 rx_ucast_bytes; + u64 rx_mcast_bytes; + u64 rx_bcast_bytes; + u64 rx_ucast_pkts; + u64 rx_mcast_pkts; + u64 rx_bcast_pkts; + u64 mftag_filter_discards; + u64 mac_filter_discards; + u64 tx_ucast_bytes; + u64 tx_mcast_bytes; + u64 tx_bcast_bytes; + u64 tx_ucast_pkts; + u64 tx_mcast_pkts; + u64 tx_bcast_pkts; + u64 tx_err_drop_pkts; + u64 tpa_coalesced_pkts; + u64 tpa_coalesced_events; + u64 tpa_aborts_num; + u64 tpa_not_coalesced_pkts; + u64 tpa_coalesced_bytes; + + /* port */ + u64 rx_64_byte_packets; + u64 rx_127_byte_packets; + u64 rx_255_byte_packets; + u64 rx_511_byte_packets; + u64 rx_1023_byte_packets; + u64 rx_1518_byte_packets; + u64 rx_1522_byte_packets; + u64 rx_2047_byte_packets; + u64 rx_4095_byte_packets; + u64 rx_9216_byte_packets; + u64 rx_16383_byte_packets; + u64 rx_crc_errors; + u64 rx_mac_crtl_frames; + u64 rx_pause_frames; + u64 rx_pfc_frames; + u64 rx_align_errors; + u64 rx_carrier_errors; + u64 rx_oversize_packets; + u64 rx_jabbers; + u64 rx_undersize_packets; + u64 rx_fragments; + u64 tx_64_byte_packets; + u64 tx_65_to_127_byte_packets; + u64 tx_128_to_255_byte_packets; + u64 tx_256_to_511_byte_packets; + u64 tx_512_to_1023_byte_packets; + u64 tx_1024_to_1518_byte_packets; + u64 tx_1519_to_2047_byte_packets; + u64 tx_2048_to_4095_byte_packets; + u64 tx_4096_to_9216_byte_packets; + u64 tx_9217_to_16383_byte_packets; + u64 tx_pause_frames; + u64 tx_pfc_frames; + u64 tx_lpi_entry_count; + u64 tx_total_collisions; + u64 brb_truncates; + u64 brb_discards; + u64 rx_mac_bytes; + u64 rx_mac_uc_packets; + u64 rx_mac_mc_packets; + u64 rx_mac_bc_packets; + u64 rx_mac_frames_ok; + u64 tx_mac_bytes; + u64 tx_mac_uc_packets; + u64 tx_mac_mc_packets; + u64 tx_mac_bc_packets; + u64 tx_mac_ctrl_frames; +}; + +#define QED_SB_IDX 0x0002 + +#define RX_PI 0 +#define TX_PI(tc) (RX_PI + 1 + tc) + +static inline u16 qed_sb_update_sb_idx(struct qed_sb_info *sb_info) +{ + u32 prod = 0; + u16 rc = 0; + + prod = le32_to_cpu(sb_info->sb_virt->prod_index) & + STATUS_BLOCK_PROD_INDEX_MASK; + if (sb_info->sb_ack != prod) { + sb_info->sb_ack = prod; + rc |= QED_SB_IDX; + } + + /* Let SB update */ + mmiowb(); + return rc; +} + +/** + * + * @brief This function creates an update command for interrupts that is + * written to the IGU. + * + * @param sb_info - This is the structure allocated and + * initialized per status block. Assumption is + * that it was initialized using qed_sb_init + * @param int_cmd - Enable/Disable/Nop + * @param upd_flg - whether igu consumer should be + * updated. + * + * @return inline void + */ +static inline void qed_sb_ack(struct qed_sb_info *sb_info, + enum igu_int_cmd int_cmd, + u8 upd_flg) +{ + struct igu_prod_cons_update igu_ack = { 0 }; + + igu_ack.sb_id_and_flags = + ((sb_info->sb_ack << IGU_PROD_CONS_UPDATE_SB_INDEX_SHIFT) | + (upd_flg << IGU_PROD_CONS_UPDATE_UPDATE_FLAG_SHIFT) | + (int_cmd << IGU_PROD_CONS_UPDATE_ENABLE_INT_SHIFT) | + (IGU_SEG_ACCESS_REG << + IGU_PROD_CONS_UPDATE_SEGMENT_ACCESS_SHIFT)); + + DIRECT_REG_WR(sb_info->igu_addr, igu_ack.sb_id_and_flags); + + /* Both segments (interrupts & acks) are written to same place address; + * Need to guarantee all commands will be received (in-order) by HW. + */ + mmiowb(); + barrier(); +} + +static inline void __internal_ram_wr(void *p_hwfn, + void __iomem *addr, + int size, + u32 *data) + +{ + unsigned int i; + + for (i = 0; i < size / sizeof(*data); i++) + DIRECT_REG_WR(&((u32 __iomem *)addr)[i], data[i]); +} + +static inline void internal_ram_wr(void __iomem *addr, + int size, + u32 *data) +{ + __internal_ram_wr(NULL, addr, size, data); +} + +#endif -- cgit v1.2.3 From 25c089d78f3833edf614fc377e75e9cf848562f5 Mon Sep 17 00:00:00 2001 From: Yuval Mintz Date: Mon, 26 Oct 2015 11:02:26 +0200 Subject: qed: Add basic L2 interface This patch adds a public API for a network driver to work on top of QED. The interface itself is very minimal - it's mostly infrastructure, as the only content it has after this patch is a query for HW-based information required for the creation of a network interface [I.e., no actual protocol-specific configurations are supported]. Signed-off-by: Manish Chopra Signed-off-by: Yuval Mintz Signed-off-by: Ariel Elior Signed-off-by: David S. Miller --- include/linux/qed/eth_common.h | 279 +++++++++++++++++++++++++++++++++++++++++ include/linux/qed/qed_eth_if.h | 38 ++++++ 2 files changed, 317 insertions(+) create mode 100644 include/linux/qed/eth_common.h create mode 100644 include/linux/qed/qed_eth_if.h (limited to 'include') diff --git a/include/linux/qed/eth_common.h b/include/linux/qed/eth_common.h new file mode 100644 index 000000000000..320b3373ac1d --- /dev/null +++ b/include/linux/qed/eth_common.h @@ -0,0 +1,279 @@ +/* QLogic qed NIC Driver + * Copyright (c) 2015 QLogic Corporation + * + * This software is available under the terms of the GNU General Public License + * (GPL) Version 2, available from the file COPYING in the main directory of + * this source tree. + */ + +#ifndef __ETH_COMMON__ +#define __ETH_COMMON__ + +/********************/ +/* ETH FW CONSTANTS */ +/********************/ +#define ETH_CACHE_LINE_SIZE 64 + +#define ETH_MAX_RAMROD_PER_CON 8 +#define ETH_TX_BD_PAGE_SIZE_BYTES 4096 +#define ETH_RX_BD_PAGE_SIZE_BYTES 4096 +#define ETH_RX_SGE_PAGE_SIZE_BYTES 4096 +#define ETH_RX_CQE_PAGE_SIZE_BYTES 4096 +#define ETH_RX_NUM_NEXT_PAGE_BDS 2 +#define ETH_RX_NUM_NEXT_PAGE_SGES 2 + +#define ETH_TX_MIN_BDS_PER_NON_LSO_PKT 1 +#define ETH_TX_MAX_BDS_PER_NON_LSO_PACKET 18 +#define ETH_TX_MAX_LSO_HDR_NBD 4 +#define ETH_TX_MIN_BDS_PER_LSO_PKT 3 +#define ETH_TX_MIN_BDS_PER_TUNN_IPV6_WITH_EXT_PKT 3 +#define ETH_TX_MIN_BDS_PER_IPV6_WITH_EXT_PKT 2 +#define ETH_TX_MIN_BDS_PER_PKT_W_LOOPBACK_MODE 2 +#define ETH_TX_MAX_NON_LSO_PKT_LEN (9700 - (4 + 12 + 8)) +#define ETH_TX_MAX_LSO_HDR_BYTES 510 + +#define ETH_NUM_STATISTIC_COUNTERS MAX_NUM_VPORTS + +#define ETH_REG_CQE_PBL_SIZE 3 + +/* num of MAC/VLAN filters */ +#define ETH_NUM_MAC_FILTERS 512 +#define ETH_NUM_VLAN_FILTERS 512 + +/* approx. multicast constants */ +#define ETH_MULTICAST_BIN_FROM_MAC_SEED 0 +#define ETH_MULTICAST_MAC_BINS 256 +#define ETH_MULTICAST_MAC_BINS_IN_REGS (ETH_MULTICAST_MAC_BINS / 32) + +/* ethernet vport update constants */ +#define ETH_FILTER_RULES_COUNT 10 +#define ETH_RSS_IND_TABLE_ENTRIES_NUM 128 +#define ETH_RSS_KEY_SIZE_REGS 10 +#define ETH_RSS_ENGINE_NUM_K2 207 +#define ETH_RSS_ENGINE_NUM_BB 127 + +/* TPA constants */ +#define ETH_TPA_MAX_AGGS_NUM 64 +#define ETH_TPA_CQE_START_SGL_SIZE 3 +#define ETH_TPA_CQE_CONT_SGL_SIZE 6 +#define ETH_TPA_CQE_END_SGL_SIZE 4 + +/* Queue Zone sizes */ +#define TSTORM_QZONE_SIZE 0 +#define MSTORM_QZONE_SIZE sizeof(struct mstorm_eth_queue_zone) +#define USTORM_QZONE_SIZE sizeof(struct ustorm_eth_queue_zone) +#define XSTORM_QZONE_SIZE 0 +#define YSTORM_QZONE_SIZE sizeof(struct ystorm_eth_queue_zone) +#define PSTORM_QZONE_SIZE 0 + +/* Interrupt coalescing TimeSet */ +struct coalescing_timeset { + u8 timeset; + u8 valid; +}; + +struct eth_tx_1st_bd_flags { + u8 bitfields; +#define ETH_TX_1ST_BD_FLAGS_FORCE_VLAN_MODE_MASK 0x1 +#define ETH_TX_1ST_BD_FLAGS_FORCE_VLAN_MODE_SHIFT 0 +#define ETH_TX_1ST_BD_FLAGS_IP_CSUM_MASK 0x1 +#define ETH_TX_1ST_BD_FLAGS_IP_CSUM_SHIFT 1 +#define ETH_TX_1ST_BD_FLAGS_L4_CSUM_MASK 0x1 +#define ETH_TX_1ST_BD_FLAGS_L4_CSUM_SHIFT 2 +#define ETH_TX_1ST_BD_FLAGS_VLAN_INSERTION_MASK 0x1 +#define ETH_TX_1ST_BD_FLAGS_VLAN_INSERTION_SHIFT 3 +#define ETH_TX_1ST_BD_FLAGS_LSO_MASK 0x1 +#define ETH_TX_1ST_BD_FLAGS_LSO_SHIFT 4 +#define ETH_TX_1ST_BD_FLAGS_START_BD_MASK 0x1 +#define ETH_TX_1ST_BD_FLAGS_START_BD_SHIFT 5 +#define ETH_TX_1ST_BD_FLAGS_TUNN_IP_CSUM_MASK 0x1 +#define ETH_TX_1ST_BD_FLAGS_TUNN_IP_CSUM_SHIFT 6 +#define ETH_TX_1ST_BD_FLAGS_TUNN_L4_CSUM_MASK 0x1 +#define ETH_TX_1ST_BD_FLAGS_TUNN_L4_CSUM_SHIFT 7 +}; + +/* The parsing information data fo rthe first tx bd of a given packet. */ +struct eth_tx_data_1st_bd { + __le16 vlan; + u8 nbds; + struct eth_tx_1st_bd_flags bd_flags; + __le16 fw_use_only; +}; + +/* The parsing information data for the second tx bd of a given packet. */ +struct eth_tx_data_2nd_bd { + __le16 tunn_ip_size; + __le16 bitfields; +#define ETH_TX_DATA_2ND_BD_L4_HDR_START_OFFSET_W_MASK 0x1FFF +#define ETH_TX_DATA_2ND_BD_L4_HDR_START_OFFSET_W_SHIFT 0 +#define ETH_TX_DATA_2ND_BD_RESERVED0_MASK 0x7 +#define ETH_TX_DATA_2ND_BD_RESERVED0_SHIFT 13 + __le16 bitfields2; +#define ETH_TX_DATA_2ND_BD_TUNN_INNER_L2_HDR_SIZE_W_MASK 0xF +#define ETH_TX_DATA_2ND_BD_TUNN_INNER_L2_HDR_SIZE_W_SHIFT 0 +#define ETH_TX_DATA_2ND_BD_TUNN_INNER_ETH_TYPE_MASK 0x3 +#define ETH_TX_DATA_2ND_BD_TUNN_INNER_ETH_TYPE_SHIFT 4 +#define ETH_TX_DATA_2ND_BD_DEST_PORT_MODE_MASK 0x3 +#define ETH_TX_DATA_2ND_BD_DEST_PORT_MODE_SHIFT 6 +#define ETH_TX_DATA_2ND_BD_TUNN_TYPE_MASK 0x3 +#define ETH_TX_DATA_2ND_BD_TUNN_TYPE_SHIFT 8 +#define ETH_TX_DATA_2ND_BD_TUNN_INNER_IPV6_MASK 0x1 +#define ETH_TX_DATA_2ND_BD_TUNN_INNER_IPV6_SHIFT 10 +#define ETH_TX_DATA_2ND_BD_IPV6_EXT_MASK 0x1 +#define ETH_TX_DATA_2ND_BD_IPV6_EXT_SHIFT 11 +#define ETH_TX_DATA_2ND_BD_TUNN_IPV6_EXT_MASK 0x1 +#define ETH_TX_DATA_2ND_BD_TUNN_IPV6_EXT_SHIFT 12 +#define ETH_TX_DATA_2ND_BD_L4_UDP_MASK 0x1 +#define ETH_TX_DATA_2ND_BD_L4_UDP_SHIFT 13 +#define ETH_TX_DATA_2ND_BD_L4_PSEUDO_CSUM_MODE_MASK 0x1 +#define ETH_TX_DATA_2ND_BD_L4_PSEUDO_CSUM_MODE_SHIFT 14 +#define ETH_TX_DATA_2ND_BD_RESERVED1_MASK 0x1 +#define ETH_TX_DATA_2ND_BD_RESERVED1_SHIFT 15 +}; + +/* Regular ETH Rx FP CQE. */ +struct eth_fast_path_rx_reg_cqe { + u8 type; + u8 bitfields; +#define ETH_FAST_PATH_RX_REG_CQE_RSS_HASH_TYPE_MASK 0x7 +#define ETH_FAST_PATH_RX_REG_CQE_RSS_HASH_TYPE_SHIFT 0 +#define ETH_FAST_PATH_RX_REG_CQE_TC_MASK 0xF +#define ETH_FAST_PATH_RX_REG_CQE_TC_SHIFT 3 +#define ETH_FAST_PATH_RX_REG_CQE_RESERVED0_MASK 0x1 +#define ETH_FAST_PATH_RX_REG_CQE_RESERVED0_SHIFT 7 + __le16 pkt_len; + struct parsing_and_err_flags pars_flags; + __le16 vlan_tag; + __le32 rss_hash; + __le16 len_on_bd; + u8 placement_offset; + u8 reserved; + __le16 pbl[ETH_REG_CQE_PBL_SIZE]; + u8 reserved1[10]; +}; + +/* The L4 pseudo checksum mode for Ethernet */ +enum eth_l4_pseudo_checksum_mode { + ETH_L4_PSEUDO_CSUM_CORRECT_LENGTH, + ETH_L4_PSEUDO_CSUM_ZERO_LENGTH, + MAX_ETH_L4_PSEUDO_CHECKSUM_MODE +}; + +struct eth_rx_bd { + struct regpair addr; +}; + +/* regular ETH Rx SP CQE */ +struct eth_slow_path_rx_cqe { + u8 type; + u8 ramrod_cmd_id; + u8 error_flag; + u8 reserved[27]; + __le16 echo; +}; + +/* union for all ETH Rx CQE types */ +union eth_rx_cqe { + struct eth_fast_path_rx_reg_cqe fast_path_regular; + struct eth_slow_path_rx_cqe slow_path; +}; + +/* ETH Rx CQE type */ +enum eth_rx_cqe_type { + ETH_RX_CQE_TYPE_UNUSED, + ETH_RX_CQE_TYPE_REGULAR, + ETH_RX_CQE_TYPE_SLOW_PATH, + MAX_ETH_RX_CQE_TYPE +}; + +/* ETH Rx producers data */ +struct eth_rx_prod_data { + __le16 bd_prod; + __le16 sge_prod; + __le16 cqe_prod; + __le16 reserved; +}; + +/* The first tx bd of a given packet */ +struct eth_tx_1st_bd { + struct regpair addr; + __le16 nbytes; + struct eth_tx_data_1st_bd data; +}; + +/* The second tx bd of a given packet */ +struct eth_tx_2nd_bd { + struct regpair addr; + __le16 nbytes; + struct eth_tx_data_2nd_bd data; +}; + +/* The parsing information data for the third tx bd of a given packet. */ +struct eth_tx_data_3rd_bd { + __le16 lso_mss; + u8 bitfields; +#define ETH_TX_DATA_3RD_BD_TCP_HDR_LEN_DW_MASK 0xF +#define ETH_TX_DATA_3RD_BD_TCP_HDR_LEN_DW_SHIFT 0 +#define ETH_TX_DATA_3RD_BD_HDR_NBD_MASK 0xF +#define ETH_TX_DATA_3RD_BD_HDR_NBD_SHIFT 4 + u8 resereved0[3]; +}; + +/* The third tx bd of a given packet */ +struct eth_tx_3rd_bd { + struct regpair addr; + __le16 nbytes; + struct eth_tx_data_3rd_bd data; +}; + +/* The common non-special TX BD ring element */ +struct eth_tx_bd { + struct regpair addr; + __le16 nbytes; + __le16 reserved0; + __le32 reserved1; +}; + +union eth_tx_bd_types { + struct eth_tx_1st_bd first_bd; + struct eth_tx_2nd_bd second_bd; + struct eth_tx_3rd_bd third_bd; + struct eth_tx_bd reg_bd; +}; + +/* Mstorm Queue Zone */ +struct mstorm_eth_queue_zone { + struct eth_rx_prod_data rx_producers; + __le32 reserved[2]; +}; + +/* Ustorm Queue Zone */ +struct ustorm_eth_queue_zone { + struct coalescing_timeset int_coalescing_timeset; + __le16 reserved[3]; +}; + +/* Ystorm Queue Zone */ +struct ystorm_eth_queue_zone { + struct coalescing_timeset int_coalescing_timeset; + __le16 reserved[3]; +}; + +/* ETH doorbell data */ +struct eth_db_data { + u8 params; +#define ETH_DB_DATA_DEST_MASK 0x3 +#define ETH_DB_DATA_DEST_SHIFT 0 +#define ETH_DB_DATA_AGG_CMD_MASK 0x3 +#define ETH_DB_DATA_AGG_CMD_SHIFT 2 +#define ETH_DB_DATA_BYPASS_EN_MASK 0x1 +#define ETH_DB_DATA_BYPASS_EN_SHIFT 4 +#define ETH_DB_DATA_RESERVED_MASK 0x1 +#define ETH_DB_DATA_RESERVED_SHIFT 5 +#define ETH_DB_DATA_AGG_VAL_SEL_MASK 0x3 +#define ETH_DB_DATA_AGG_VAL_SEL_SHIFT 6 + u8 agg_flags; + __le16 bd_prod; +}; + +#endif /* __ETH_COMMON__ */ diff --git a/include/linux/qed/qed_eth_if.h b/include/linux/qed/qed_eth_if.h new file mode 100644 index 000000000000..fbd8700f0b31 --- /dev/null +++ b/include/linux/qed/qed_eth_if.h @@ -0,0 +1,38 @@ +/* QLogic qed NIC Driver + * Copyright (c) 2015 QLogic Corporation + * + * This software is available under the terms of the GNU General Public License + * (GPL) Version 2, available from the file COPYING in the main directory of + * this source tree. + */ + +#ifndef _QED_ETH_IF_H +#define _QED_ETH_IF_H + +#include +#include +#include +#include + +struct qed_dev_eth_info { + struct qed_dev_info common; + + u8 num_queues; + u8 num_tc; + + u8 port_mac[ETH_ALEN]; + u8 num_vlan_filters; +}; + +struct qed_eth_ops { + const struct qed_common_ops *common; + + int (*fill_dev_info)(struct qed_dev *cdev, + struct qed_dev_eth_info *info); + +}; + +const struct qed_eth_ops *qed_get_eth_ops(u32 version); +void qed_put_eth_ops(void); + +#endif -- cgit v1.2.3 From cee4d26448c1000ccc1711eb5e6ed4c15f18fa83 Mon Sep 17 00:00:00 2001 From: Manish Chopra Date: Mon, 26 Oct 2015 11:02:28 +0200 Subject: qed: Add slowpath L2 support This patch adds to the qed the support to configure various L2 elements, such as channels and basic filtering conditions. It also enhances its public API to allow qede to later utilize this functionality. Signed-off-by: Manish Chopra Signed-off-by: Yuval Mintz Signed-off-by: Ariel Elior Signed-off-by: David S. Miller --- include/linux/qed/qed_eth_if.h | 120 +++++++++++++++++++++++++++++++++++++++++ 1 file changed, 120 insertions(+) (limited to 'include') diff --git a/include/linux/qed/qed_eth_if.h b/include/linux/qed/qed_eth_if.h index fbd8700f0b31..67a7b41b70aa 100644 --- a/include/linux/qed/qed_eth_if.h +++ b/include/linux/qed/qed_eth_if.h @@ -24,12 +24,132 @@ struct qed_dev_eth_info { u8 num_vlan_filters; }; +struct qed_update_vport_rss_params { + u16 rss_ind_table[128]; + u32 rss_key[10]; +}; + +struct qed_update_vport_params { + u8 vport_id; + u8 update_vport_active_flg; + u8 vport_active_flg; + u8 update_rss_flg; + struct qed_update_vport_rss_params rss_params; +}; + +struct qed_stop_rxq_params { + u8 rss_id; + u8 rx_queue_id; + u8 vport_id; + bool eq_completion_only; +}; + +struct qed_stop_txq_params { + u8 rss_id; + u8 tx_queue_id; +}; + +enum qed_filter_rx_mode_type { + QED_FILTER_RX_MODE_TYPE_REGULAR, + QED_FILTER_RX_MODE_TYPE_MULTI_PROMISC, + QED_FILTER_RX_MODE_TYPE_PROMISC, +}; + +enum qed_filter_xcast_params_type { + QED_FILTER_XCAST_TYPE_ADD, + QED_FILTER_XCAST_TYPE_DEL, + QED_FILTER_XCAST_TYPE_REPLACE, +}; + +struct qed_filter_ucast_params { + enum qed_filter_xcast_params_type type; + u8 vlan_valid; + u16 vlan; + u8 mac_valid; + unsigned char mac[ETH_ALEN]; +}; + +struct qed_filter_mcast_params { + enum qed_filter_xcast_params_type type; + u8 num; + unsigned char mac[64][ETH_ALEN]; +}; + +union qed_filter_type_params { + enum qed_filter_rx_mode_type accept_flags; + struct qed_filter_ucast_params ucast; + struct qed_filter_mcast_params mcast; +}; + +enum qed_filter_type { + QED_FILTER_TYPE_UCAST, + QED_FILTER_TYPE_MCAST, + QED_FILTER_TYPE_RX_MODE, + QED_MAX_FILTER_TYPES, +}; + +struct qed_filter_params { + enum qed_filter_type type; + union qed_filter_type_params filter; +}; + +struct qed_queue_start_common_params { + u8 rss_id; + u8 queue_id; + u8 vport_id; + u16 sb; + u16 sb_idx; +}; + +struct qed_eth_cb_ops { + struct qed_common_cb_ops common; +}; + struct qed_eth_ops { const struct qed_common_ops *common; int (*fill_dev_info)(struct qed_dev *cdev, struct qed_dev_eth_info *info); + int (*vport_start)(struct qed_dev *cdev, + u8 vport_id, u16 mtu, + u8 drop_ttl0_flg, + u8 inner_vlan_removal_en_flg); + + int (*vport_stop)(struct qed_dev *cdev, + u8 vport_id); + + int (*vport_update)(struct qed_dev *cdev, + struct qed_update_vport_params *params); + + int (*q_rx_start)(struct qed_dev *cdev, + struct qed_queue_start_common_params *params, + u16 bd_max_bytes, + dma_addr_t bd_chain_phys_addr, + dma_addr_t cqe_pbl_addr, + u16 cqe_pbl_size, + void __iomem **pp_prod); + + int (*q_rx_stop)(struct qed_dev *cdev, + struct qed_stop_rxq_params *params); + + int (*q_tx_start)(struct qed_dev *cdev, + struct qed_queue_start_common_params *params, + dma_addr_t pbl_addr, + u16 pbl_size, + void __iomem **pp_doorbell); + + int (*q_tx_stop)(struct qed_dev *cdev, + struct qed_stop_txq_params *params); + + int (*filter_config)(struct qed_dev *cdev, + struct qed_filter_params *params); + + int (*fastpath_stop)(struct qed_dev *cdev); + + int (*eth_cqe_completion)(struct qed_dev *cdev, + u8 rss_id, + struct eth_slow_path_rx_cqe *cqe); }; const struct qed_eth_ops *qed_get_eth_ops(u32 version); -- cgit v1.2.3 From cc875c2e4f34e86c2f562f18b6e917cfcc560bcb Mon Sep 17 00:00:00 2001 From: Yuval Mintz Date: Mon, 26 Oct 2015 11:02:31 +0200 Subject: qed: Add link support Physical link is handled by the management Firmware. This patch lays the infrastructure for attention handling in the driver, as link change notifications arrive via async. attentions, as well the handling of such notifications. This patch also extends the API with the protocol drivers by adding registered callbacks which the protocol driver passes to qed in order to be notified of async. events originating from the FW/HW. Signed-off-by: Yuval Mintz Signed-off-by: Ariel Elior Signed-off-by: David S. Miller --- include/linux/qed/qed_eth_if.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include') diff --git a/include/linux/qed/qed_eth_if.h b/include/linux/qed/qed_eth_if.h index 67a7b41b70aa..ab1041424013 100644 --- a/include/linux/qed/qed_eth_if.h +++ b/include/linux/qed/qed_eth_if.h @@ -111,6 +111,10 @@ struct qed_eth_ops { int (*fill_dev_info)(struct qed_dev *cdev, struct qed_dev_eth_info *info); + void (*register_ops)(struct qed_dev *cdev, + struct qed_eth_cb_ops *ops, + void *cookie); + int (*vport_start)(struct qed_dev *cdev, u8 vport_id, u16 mtu, u8 drop_ttl0_flg, -- cgit v1.2.3 From 9df2ed0415b13218f84262c2372323ef028310fc Mon Sep 17 00:00:00 2001 From: Manish Chopra Date: Mon, 26 Oct 2015 11:02:33 +0200 Subject: qed: Add statistics support Device statistics can be gathered on-demand. This adds the qed support for reading the statistics [both function and port] from the device, and adds to the public API a method for requesting the current statistics. Signed-off-by: Manish Chopra Signed-off-by: Yuval Mintz Signed-off-by: Ariel Elior Signed-off-by: David S. Miller --- include/linux/qed/qed_eth_if.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include') diff --git a/include/linux/qed/qed_eth_if.h b/include/linux/qed/qed_eth_if.h index ab1041424013..81ab178e31c1 100644 --- a/include/linux/qed/qed_eth_if.h +++ b/include/linux/qed/qed_eth_if.h @@ -154,6 +154,9 @@ struct qed_eth_ops { int (*eth_cqe_completion)(struct qed_dev *cdev, u8 rss_id, struct eth_slow_path_rx_cqe *cqe); + + void (*get_vport_stats)(struct qed_dev *cdev, + struct qed_eth_stats *stats); }; const struct qed_eth_ops *qed_get_eth_ops(u32 version); -- cgit v1.2.3 From f8e529ed941ba2bbcbf310b575d968159ce7e895 Mon Sep 17 00:00:00 2001 From: Tycho Andersen Date: Tue, 27 Oct 2015 09:23:59 +0900 Subject: seccomp, ptrace: add support for dumping seccomp filters This patch adds support for dumping a process' (classic BPF) seccomp filters via ptrace. PTRACE_SECCOMP_GET_FILTER allows the tracer to dump the user's classic BPF seccomp filters. addr should be an integer which represents the ith seccomp filter (0 is the most recently installed filter). data should be a struct sock_filter * with enough room for the ith filter, or NULL, in which case the filter is not saved. The return value for this command is the number of BPF instructions the program represents, or negative in the case of errors. Command specific errors are ENOENT: which indicates that there is no ith filter in this seccomp tree, and EMEDIUMTYPE, which indicates that the ith filter was not installed as a classic BPF filter. A caveat with this approach is that there is no way to get explicitly at the heirarchy of seccomp filters, and users need to memcmp() filters to decide which are inherited. This means that a task which installs two of the same filter can potentially confuse users of this interface. v2: * make save_orig const * check that the orig_prog exists (not necessary right now, but when grows eBPF support it will be) * s/n/filter_off and make it an unsigned long to match ptrace * count "down" the tree instead of "up" when passing a filter offset v3: * don't take the current task's lock for inspecting its seccomp mode * use a 0x42** constant for the ptrace command value v4: * don't copy to userspace while holding spinlocks v5: * add another condition to WARN_ON v6: * rebase on net-next Signed-off-by: Tycho Andersen Acked-by: Kees Cook CC: Will Drewry Reviewed-by: Oleg Nesterov CC: Andy Lutomirski CC: Pavel Emelyanov CC: Serge E. Hallyn CC: Alexei Starovoitov CC: Daniel Borkmann Acked-by: Alexei Starovoitov Signed-off-by: David S. Miller --- include/linux/seccomp.h | 11 +++++++++++ include/uapi/linux/ptrace.h | 2 ++ 2 files changed, 13 insertions(+) (limited to 'include') diff --git a/include/linux/seccomp.h b/include/linux/seccomp.h index f4265039a94c..2296e6b2f690 100644 --- a/include/linux/seccomp.h +++ b/include/linux/seccomp.h @@ -95,4 +95,15 @@ static inline void get_seccomp_filter(struct task_struct *tsk) return; } #endif /* CONFIG_SECCOMP_FILTER */ + +#if defined(CONFIG_SECCOMP_FILTER) && defined(CONFIG_CHECKPOINT_RESTORE) +extern long seccomp_get_filter(struct task_struct *task, + unsigned long filter_off, void __user *data); +#else +static inline long seccomp_get_filter(struct task_struct *task, + unsigned long n, void __user *data) +{ + return -EINVAL; +} +#endif /* CONFIG_SECCOMP_FILTER && CONFIG_CHECKPOINT_RESTORE */ #endif /* _LINUX_SECCOMP_H */ diff --git a/include/uapi/linux/ptrace.h b/include/uapi/linux/ptrace.h index a7a697986614..fb8106509000 100644 --- a/include/uapi/linux/ptrace.h +++ b/include/uapi/linux/ptrace.h @@ -64,6 +64,8 @@ struct ptrace_peeksiginfo_args { #define PTRACE_GETSIGMASK 0x420a #define PTRACE_SETSIGMASK 0x420b +#define PTRACE_SECCOMP_GET_FILTER 0x420c + /* Read signals from a shared (process wide) queue */ #define PTRACE_PEEKSIGINFO_SHARED (1 << 0) -- cgit v1.2.3 From f11631748ee6973f85238109a3fa8ab8e760e5a4 Mon Sep 17 00:00:00 2001 From: Robert Dolca Date: Mon, 26 Oct 2015 13:58:54 +0200 Subject: NFC: nci: non-static functions can not be inline MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit This fixes a build error that seems to be toochain dependent (Not seen with gcc v5.1): In file included from net/nfc/nci/rsp.c:36:0: net/nfc/nci/rsp.c: In function ‘nci_rsp_packet’: include/net/nfc/nci_core.h:355:12: error: inlining failed in call to always_inline ‘nci_prop_rsp_packet’: function body not available inline int nci_prop_rsp_packet(struct nci_dev *ndev, __u16 opcode, Signed-off-by: Robert Dolca Signed-off-by: Samuel Ortiz --- include/net/nfc/nci_core.h | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) (limited to 'include') diff --git a/include/net/nfc/nci_core.h b/include/net/nfc/nci_core.h index 5a1572a34c49..57ce24fb0047 100644 --- a/include/net/nfc/nci_core.h +++ b/include/net/nfc/nci_core.h @@ -352,13 +352,13 @@ static inline int nci_set_vendor_cmds(struct nci_dev *ndev, void nci_rsp_packet(struct nci_dev *ndev, struct sk_buff *skb); void nci_ntf_packet(struct nci_dev *ndev, struct sk_buff *skb); -inline int nci_prop_rsp_packet(struct nci_dev *ndev, __u16 opcode, +int nci_prop_rsp_packet(struct nci_dev *ndev, __u16 opcode, struct sk_buff *skb); -inline int nci_prop_ntf_packet(struct nci_dev *ndev, __u16 opcode, +int nci_prop_ntf_packet(struct nci_dev *ndev, __u16 opcode, struct sk_buff *skb); -inline int nci_core_rsp_packet(struct nci_dev *ndev, __u16 opcode, +int nci_core_rsp_packet(struct nci_dev *ndev, __u16 opcode, struct sk_buff *skb); -inline int nci_core_ntf_packet(struct nci_dev *ndev, __u16 opcode, +int nci_core_ntf_packet(struct nci_dev *ndev, __u16 opcode, struct sk_buff *skb); void nci_rx_data_packet(struct nci_dev *ndev, struct sk_buff *skb); int nci_send_cmd(struct nci_dev *ndev, __u16 opcode, __u8 plen, void *payload); -- cgit v1.2.3 From 8ed66f0e8235118a31720acdab3bbbe9debd0f6a Mon Sep 17 00:00:00 2001 From: "John W. Linville" Date: Mon, 26 Oct 2015 17:01:44 -0400 Subject: geneve: implement support for IPv6-based tunnels NOTE: Link-local IPv6 addresses for remote endpoints are not supported, since the driver currently has no capacity for binding a geneve interface to a specific link. Signed-off-by: John W. Linville Reviewed-by: Jesse Gross Signed-off-by: David S. Miller --- include/uapi/linux/if_link.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/uapi/linux/if_link.h b/include/uapi/linux/if_link.h index a7aea8418abb..5ad57375a99f 100644 --- a/include/uapi/linux/if_link.h +++ b/include/uapi/linux/if_link.h @@ -461,6 +461,7 @@ enum { IFLA_GENEVE_TOS, IFLA_GENEVE_PORT, /* destination port */ IFLA_GENEVE_COLLECT_METADATA, + IFLA_GENEVE_REMOTE6, __IFLA_GENEVE_MAX }; #define IFLA_GENEVE_MAX (__IFLA_GENEVE_MAX - 1) -- cgit v1.2.3 From ea3803c193df18d8353d6c8d77034066a08c19f5 Mon Sep 17 00:00:00 2001 From: Stefan Hajnoczi Date: Thu, 29 Oct 2015 11:57:42 +0000 Subject: VSOCK: define VSOCK_SS_LISTEN once only The SS_LISTEN socket state is defined by both af_vsock.c and vmci_transport.c. This is risky since the value could be changed in one file and the other would be out of sync. Rename from SS_LISTEN to VSOCK_SS_LISTEN since the constant is not part of enum socket_state (SS_CONNECTED, ...). This way it is clear that the constant is vsock-specific. The big text reflow in af_vsock.c was necessary to keep to the maximum line length. Text is unchanged except for s/SS_LISTEN/VSOCK_SS_LISTEN/. Signed-off-by: Stefan Hajnoczi Signed-off-by: David S. Miller --- include/net/af_vsock.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include') diff --git a/include/net/af_vsock.h b/include/net/af_vsock.h index db639a4c5ab8..e9eb2d6791b3 100644 --- a/include/net/af_vsock.h +++ b/include/net/af_vsock.h @@ -22,6 +22,9 @@ #include "vsock_addr.h" +/* vsock-specific sock->sk_state constants */ +#define VSOCK_SS_LISTEN 255 + #define LAST_RESERVED_PORT 1023 #define vsock_sk(__sk) ((struct vsock_sock *)__sk) -- cgit v1.2.3 From 76e398a6271285c1f361d66445a55cdcee5c1b4b Mon Sep 17 00:00:00 2001 From: Vivien Didelot Date: Sun, 1 Nov 2015 12:33:55 -0500 Subject: net: dsa: use switchdev obj for VLAN add/del ops Simplify DSA by pushing the switchdev objects for VLAN add and delete operations down to its drivers. Currently only mv88e6xxx is affected. Signed-off-by: Vivien Didelot Signed-off-by: David S. Miller --- include/net/dsa.h | 13 +++++++++---- 1 file changed, 9 insertions(+), 4 deletions(-) (limited to 'include') diff --git a/include/net/dsa.h b/include/net/dsa.h index 98ccbdef646f..82a4c6011173 100644 --- a/include/net/dsa.h +++ b/include/net/dsa.h @@ -200,6 +200,7 @@ static inline u8 dsa_upstream_port(struct dsa_switch *ds) struct switchdev_trans; struct switchdev_obj; struct switchdev_obj_port_fdb; +struct switchdev_obj_port_vlan; struct dsa_switch_driver { struct list_head list; @@ -309,11 +310,15 @@ struct dsa_switch_driver { /* * VLAN support */ + int (*port_vlan_prepare)(struct dsa_switch *ds, int port, + const struct switchdev_obj_port_vlan *vlan, + struct switchdev_trans *trans); + int (*port_vlan_add)(struct dsa_switch *ds, int port, + const struct switchdev_obj_port_vlan *vlan, + struct switchdev_trans *trans); + int (*port_vlan_del)(struct dsa_switch *ds, int port, + const struct switchdev_obj_port_vlan *vlan); int (*port_pvid_get)(struct dsa_switch *ds, int port, u16 *pvid); - int (*port_pvid_set)(struct dsa_switch *ds, int port, u16 pvid); - int (*port_vlan_add)(struct dsa_switch *ds, int port, u16 vid, - bool untagged); - int (*port_vlan_del)(struct dsa_switch *ds, int port, u16 vid); int (*vlan_getnext)(struct dsa_switch *ds, u16 *vid, unsigned long *ports, unsigned long *untagged); -- cgit v1.2.3 From 4f823defdd5b106a5e89745ee8b163c71855de1e Mon Sep 17 00:00:00 2001 From: Julian Anastasov Date: Fri, 30 Oct 2015 10:23:33 +0200 Subject: ipv4: fix to not remove local route on link down When fib_netdev_event calls fib_disable_ip on NETDEV_DOWN event we should not delete the local routes if the local address is still present. The confusion comes from the fact that both fib_netdev_event and fib_inetaddr_event use the NETDEV_DOWN constant. Fix it by returning back the variable 'force'. Steps to reproduce: modprobe dummy ifconfig dummy0 192.168.168.1 up ifconfig dummy0 down ip route list table local | grep dummy | grep host local 192.168.168.1 dev dummy0 proto kernel scope host src 192.168.168.1 Fixes: 8a3d03166f19 ("net: track link-status of ipv4 nexthops") Signed-off-by: Julian Anastasov Signed-off-by: David S. Miller --- include/net/ip_fib.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/net/ip_fib.h b/include/net/ip_fib.h index 727d6e9a9685..965fa5b1a274 100644 --- a/include/net/ip_fib.h +++ b/include/net/ip_fib.h @@ -317,7 +317,7 @@ void fib_flush_external(struct net *net); /* Exported by fib_semantics.c */ int ip_fib_check_default(__be32 gw, struct net_device *dev); -int fib_sync_down_dev(struct net_device *dev, unsigned long event); +int fib_sync_down_dev(struct net_device *dev, unsigned long event, bool force); int fib_sync_down_addr(struct net *net, __be32 local); int fib_sync_up(struct net_device *dev, unsigned int nh_flags); void fib_select_multipath(struct fib_result *res); -- cgit v1.2.3 From 9e17f8a475fca81950fdddc08df428ed66cf441f Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Sun, 1 Nov 2015 15:36:55 -0800 Subject: net: make skb_set_owner_w() more robust skb_set_owner_w() is called from various places that assume skb->sk always point to a full blown socket (as it changes sk->sk_wmem_alloc) We'd like to attach skb to request sockets, and in the future to timewait sockets as well. For these kind of pseudo sockets, we need to take a traditional refcount and use sock_edemux() as the destructor. It is now time to un-inline skb_set_owner_w(), being too big. Fixes: ca6fb0651883 ("tcp: attach SYNACK messages to request sockets instead of listener") Signed-off-by: Eric Dumazet Bisected-by: Haiyang Zhang Signed-off-by: David S. Miller --- include/net/sock.h | 17 ++--------------- 1 file changed, 2 insertions(+), 15 deletions(-) (limited to 'include') diff --git a/include/net/sock.h b/include/net/sock.h index aeed5c95f3ca..f570e75e3da9 100644 --- a/include/net/sock.h +++ b/include/net/sock.h @@ -1951,6 +1951,8 @@ static inline void skb_set_hash_from_sk(struct sk_buff *skb, struct sock *sk) } } +void skb_set_owner_w(struct sk_buff *skb, struct sock *sk); + /* * Queue a received datagram if it will fit. Stream and sequenced * protocols can't normally use this as they need to fit buffers in @@ -1959,21 +1961,6 @@ static inline void skb_set_hash_from_sk(struct sk_buff *skb, struct sock *sk) * Inlined as it's very short and called for pretty much every * packet ever received. */ - -static inline void skb_set_owner_w(struct sk_buff *skb, struct sock *sk) -{ - skb_orphan(skb); - skb->sk = sk; - skb->destructor = sock_wfree; - skb_set_hash_from_sk(skb, sk); - /* - * We used to take a refcount on sk, but following operation - * is enough to guarantee sk_free() wont free this sock until - * all in-flight packets are completed - */ - atomic_add(skb->truesize, &sk->sk_wmem_alloc); -} - static inline void skb_set_owner_r(struct sk_buff *skb, struct sock *sk) { skb_orphan(skb); -- cgit v1.2.3 From 8fa677d2706d325d71dab91bf6e6512c05214e37 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Mon, 2 Nov 2015 07:50:07 -0800 Subject: net: avoid NULL deref in inet_ctl_sock_destroy() Under low memory conditions, tcp_sk_init() and icmp_sk_init() can both iterate on all possible cpus and call inet_ctl_sock_destroy(), with eventual NULL pointer. Signed-off-by: Eric Dumazet Reported-by: Dmitry Vyukov Signed-off-by: David S. Miller --- include/net/inet_common.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/net/inet_common.h b/include/net/inet_common.h index 279f83591971..109e3ee9108c 100644 --- a/include/net/inet_common.h +++ b/include/net/inet_common.h @@ -41,7 +41,8 @@ int inet_recv_error(struct sock *sk, struct msghdr *msg, int len, static inline void inet_ctl_sock_destroy(struct sock *sk) { - sock_release(sk->sk_socket); + if (sk) + sock_release(sk->sk_socket); } #endif -- cgit v1.2.3 From 1d6119baf0610f813eb9d9580eb4fd16de5b4ceb Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Mon, 2 Nov 2015 09:03:11 -0800 Subject: net: fix percpu memory leaks This patch fixes following problems : 1) percpu_counter_init() can return an error, therefore init_frag_mem_limit() must propagate this error so that inet_frags_init_net() can do the same up to its callers. 2) If ip[46]_frags_ns_ctl_register() fail, we must unwind properly and free the percpu_counter. Without this fix, we leave freed object in percpu_counters global list (if CONFIG_HOTPLUG_CPU) leading to crashes. This bug was detected by KASAN and syzkaller tool (http://github.com/google/syzkaller) Fixes: 6d7b857d541e ("net: use lib/percpu_counter API for fragmentation mem accounting") Signed-off-by: Eric Dumazet Reported-by: Dmitry Vyukov Cc: Hannes Frederic Sowa Cc: Jesper Dangaard Brouer Acked-by: Hannes Frederic Sowa Signed-off-by: David S. Miller --- include/net/inet_frag.h | 15 +++++++++------ 1 file changed, 9 insertions(+), 6 deletions(-) (limited to 'include') diff --git a/include/net/inet_frag.h b/include/net/inet_frag.h index 53eead2da743..ac42bbb37b2d 100644 --- a/include/net/inet_frag.h +++ b/include/net/inet_frag.h @@ -108,7 +108,15 @@ struct inet_frags { int inet_frags_init(struct inet_frags *); void inet_frags_fini(struct inet_frags *); -void inet_frags_init_net(struct netns_frags *nf); +static inline int inet_frags_init_net(struct netns_frags *nf) +{ + return percpu_counter_init(&nf->mem, 0, GFP_KERNEL); +} +static inline void inet_frags_uninit_net(struct netns_frags *nf) +{ + percpu_counter_destroy(&nf->mem); +} + void inet_frags_exit_net(struct netns_frags *nf, struct inet_frags *f); void inet_frag_kill(struct inet_frag_queue *q, struct inet_frags *f); @@ -154,11 +162,6 @@ static inline void add_frag_mem_limit(struct netns_frags *nf, int i) __percpu_counter_add(&nf->mem, i, frag_percpu_counter_batch); } -static inline void init_frag_mem_limit(struct netns_frags *nf) -{ - percpu_counter_init(&nf->mem, 0, GFP_KERNEL); -} - static inline unsigned int sum_frag_mem_limit(struct netns_frags *nf) { unsigned int res; -- cgit v1.2.3 From c210129760a010b555372ef74f4e1a46d4eb8a22 Mon Sep 17 00:00:00 2001 From: Daniel Borkmann Date: Thu, 29 Oct 2015 14:58:07 +0100 Subject: bpf: align and clean bpf_{map,prog}_get helpers Add a bpf_map_get() function that we're going to use later on and align/clean the remaining helpers a bit so that we have them a bit more consistent: - __bpf_map_get() and __bpf_prog_get() that both work on the fd struct, check whether the descriptor is eBPF and return the pointer to the map/prog stored in the private data. Also, we can return f.file->private_data directly, the function signature is enough of a documentation already. - bpf_map_get() and bpf_prog_get() that both work on u32 user fd, call their respective __bpf_map_get()/__bpf_prog_get() variants, and take a reference. Signed-off-by: Daniel Borkmann Acked-by: Alexei Starovoitov Signed-off-by: David S. Miller --- include/linux/bpf.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 75718fa28260..0b5fb6acef64 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -167,7 +167,7 @@ struct bpf_prog *bpf_prog_get(u32 ufd); void bpf_prog_put(struct bpf_prog *prog); void bpf_prog_put_rcu(struct bpf_prog *prog); -struct bpf_map *bpf_map_get(struct fd f); +struct bpf_map *__bpf_map_get(struct fd f); void bpf_map_put(struct bpf_map *map); extern int sysctl_unprivileged_bpf_disabled; -- cgit v1.2.3 From b2197755b2633e164a439682fb05a9b5ea48f706 Mon Sep 17 00:00:00 2001 From: Daniel Borkmann Date: Thu, 29 Oct 2015 14:58:09 +0100 Subject: bpf: add support for persistent maps/progs This work adds support for "persistent" eBPF maps/programs. The term "persistent" is to be understood that maps/programs have a facility that lets them survive process termination. This is desired by various eBPF subsystem users. Just to name one example: tc classifier/action. Whenever tc parses the ELF object, extracts and loads maps/progs into the kernel, these file descriptors will be out of reach after the tc instance exits. So a subsequent tc invocation won't be able to access/relocate on this resource, and therefore maps cannot easily be shared, f.e. between the ingress and egress networking data path. The current workaround is that Unix domain sockets (UDS) need to be instrumented in order to pass the created eBPF map/program file descriptors to a third party management daemon through UDS' socket passing facility. This makes it a bit complicated to deploy shared eBPF maps or programs (programs f.e. for tail calls) among various processes. We've been brainstorming on how we could tackle this issue and various approches have been tried out so far, which can be read up further in the below reference. The architecture we eventually ended up with is a minimal file system that can hold map/prog objects. The file system is a per mount namespace singleton, and the default mount point is /sys/fs/bpf/. Any subsequent mounts within a given namespace will point to the same instance. The file system allows for creating a user-defined directory structure. The objects for maps/progs are created/fetched through bpf(2) with two new commands (BPF_OBJ_PIN/BPF_OBJ_GET). I.e. a bpf file descriptor along with a pathname is being passed to bpf(2) that in turn creates (we call it eBPF object pinning) the file system nodes. Only the pathname is being passed to bpf(2) for getting a new BPF file descriptor to an existing node. The user can use that to access maps and progs later on, through bpf(2). Removal of file system nodes is being managed through normal VFS functions such as unlink(2), etc. The file system code is kept to a very minimum and can be further extended later on. The next step I'm working on is to add dump eBPF map/prog commands to bpf(2), so that a specification from a given file descriptor can be retrieved. This can be used by things like CRIU but also applications can inspect the meta data after calling BPF_OBJ_GET. Big thanks also to Alexei and Hannes who significantly contributed in the design discussion that eventually let us end up with this architecture here. Reference: https://lkml.org/lkml/2015/10/15/925 Signed-off-by: Daniel Borkmann Signed-off-by: Alexei Starovoitov Signed-off-by: Hannes Frederic Sowa Signed-off-by: David S. Miller --- include/linux/bpf.h | 7 +++++++ include/uapi/linux/bpf.h | 45 ++++++++------------------------------------- include/uapi/linux/magic.h | 1 + 3 files changed, 16 insertions(+), 37 deletions(-) (limited to 'include') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 0b5fb6acef64..de464e6683b6 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -167,11 +167,18 @@ struct bpf_prog *bpf_prog_get(u32 ufd); void bpf_prog_put(struct bpf_prog *prog); void bpf_prog_put_rcu(struct bpf_prog *prog); +struct bpf_map *bpf_map_get(u32 ufd); struct bpf_map *__bpf_map_get(struct fd f); void bpf_map_put(struct bpf_map *map); extern int sysctl_unprivileged_bpf_disabled; +int bpf_map_new_fd(struct bpf_map *map); +int bpf_prog_new_fd(struct bpf_prog *prog); + +int bpf_obj_pin_user(u32 ufd, const char __user *pathname); +int bpf_obj_get_user(const char __user *pathname); + /* verify correctness of eBPF program */ int bpf_check(struct bpf_prog **fp, union bpf_attr *attr); #else diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index 2e032426cfb7..9ea2d22fa2cb 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -63,50 +63,16 @@ struct bpf_insn { __s32 imm; /* signed immediate constant */ }; -/* BPF syscall commands */ +/* BPF syscall commands, see bpf(2) man-page for details. */ enum bpf_cmd { - /* create a map with given type and attributes - * fd = bpf(BPF_MAP_CREATE, union bpf_attr *, u32 size) - * returns fd or negative error - * map is deleted when fd is closed - */ BPF_MAP_CREATE, - - /* lookup key in a given map - * err = bpf(BPF_MAP_LOOKUP_ELEM, union bpf_attr *attr, u32 size) - * Using attr->map_fd, attr->key, attr->value - * returns zero and stores found elem into value - * or negative error - */ BPF_MAP_LOOKUP_ELEM, - - /* create or update key/value pair in a given map - * err = bpf(BPF_MAP_UPDATE_ELEM, union bpf_attr *attr, u32 size) - * Using attr->map_fd, attr->key, attr->value, attr->flags - * returns zero or negative error - */ BPF_MAP_UPDATE_ELEM, - - /* find and delete elem by key in a given map - * err = bpf(BPF_MAP_DELETE_ELEM, union bpf_attr *attr, u32 size) - * Using attr->map_fd, attr->key - * returns zero or negative error - */ BPF_MAP_DELETE_ELEM, - - /* lookup key in a given map and return next key - * err = bpf(BPF_MAP_GET_NEXT_KEY, union bpf_attr *attr, u32 size) - * Using attr->map_fd, attr->key, attr->next_key - * returns zero and stores next key or negative error - */ BPF_MAP_GET_NEXT_KEY, - - /* verify and load eBPF program - * prog_fd = bpf(BPF_PROG_LOAD, union bpf_attr *attr, u32 size) - * Using attr->prog_type, attr->insns, attr->license - * returns fd or negative error - */ BPF_PROG_LOAD, + BPF_OBJ_PIN, + BPF_OBJ_GET, }; enum bpf_map_type { @@ -160,6 +126,11 @@ union bpf_attr { __aligned_u64 log_buf; /* user supplied buffer */ __u32 kern_version; /* checked when prog_type=kprobe */ }; + + struct { /* anonymous struct used by BPF_OBJ_* commands */ + __aligned_u64 pathname; + __u32 bpf_fd; + }; } __attribute__((aligned(8))); /* integer value in 'imm' field of BPF_CALL instruction selects which helper diff --git a/include/uapi/linux/magic.h b/include/uapi/linux/magic.h index 7b1425a6b370..accb036bbc9c 100644 --- a/include/uapi/linux/magic.h +++ b/include/uapi/linux/magic.h @@ -75,5 +75,6 @@ #define ANON_INODE_FS_MAGIC 0x09041934 #define BTRFS_TEST_MAGIC 0x73727279 #define NSFS_MAGIC 0x6e736673 +#define BPF_FS_MAGIC 0xcafe4a11 #endif /* __LINUX_MAGIC_H__ */ -- cgit v1.2.3 From 52bc67168109ade61014a36feedf09f4bc53d8f1 Mon Sep 17 00:00:00 2001 From: Mahesh Bandewar Date: Sat, 31 Oct 2015 12:45:11 -0700 Subject: bonding: simplify / unify event handling code for 3ad mode. Old logic of updating state-machine is not required since ad_update_actor_keys() does it implicitly. The only loss is the notification differentiation between speed vs. duplex change. Now only one unified notification is printed. Signed-off-by: Mahesh Bandewar Signed-off-by: David S. Miller --- include/net/bond_3ad.h | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) (limited to 'include') diff --git a/include/net/bond_3ad.h b/include/net/bond_3ad.h index c2a40a172fcd..f1fbc3b11962 100644 --- a/include/net/bond_3ad.h +++ b/include/net/bond_3ad.h @@ -297,8 +297,7 @@ void bond_3ad_bind_slave(struct slave *slave); void bond_3ad_unbind_slave(struct slave *slave); void bond_3ad_state_machine_handler(struct work_struct *); void bond_3ad_initiate_agg_selection(struct bonding *bond, int timeout); -void bond_3ad_adapter_speed_changed(struct slave *slave); -void bond_3ad_adapter_duplex_changed(struct slave *slave); +void bond_3ad_adapter_speed_duplex_changed(struct slave *slave); void bond_3ad_handle_link_change(struct slave *slave, char link); int bond_3ad_get_active_agg_info(struct bonding *bond, struct ad_info *ad_info); int __bond_3ad_get_active_agg_info(struct bonding *bond, -- cgit v1.2.3 From fd867d51f889aec11cca235ebb008578780d052d Mon Sep 17 00:00:00 2001 From: Jarod Wilson Date: Mon, 2 Nov 2015 21:55:59 -0500 Subject: net/core: generic support for disabling netdev features down stack There are some netdev features, which when disabled on an upper device, such as a bonding master or a bridge, must be disabled and cannot be re-enabled on underlying devices. This is a rework of an earlier more heavy-handed appraoch, which simply disables and prevents re-enabling of netdev features listed in a new define in include/net/netdev_features.h, NETIF_F_UPPER_DISABLES. Any upper device that disables a flag in that feature mask, the disabling will propagate down the stack, and any lower device that has any upper device with one of those flags disabled should not be able to enable said flag. Initially, only LRO is included for proof of concept, and because this code effectively does the same thing as dev_disable_lro(), though it will also activate from the ethtool path, which was one of the goals here. [root@dell-per730-01 ~]# ethtool -k bond0 |grep large large-receive-offload: on [root@dell-per730-01 ~]# ethtool -k p5p1 |grep large large-receive-offload: on [root@dell-per730-01 ~]# ethtool -K bond0 lro off [root@dell-per730-01 ~]# ethtool -k bond0 |grep large large-receive-offload: off [root@dell-per730-01 ~]# ethtool -k p5p1 |grep large large-receive-offload: off dmesg dump: [ 1033.277986] bond0: Disabling feature 0x0000000000008000 on lower dev p5p2. [ 1034.067949] bnx2x 0000:06:00.1 p5p2: using MSI-X IRQs: sp 74 fp[0] 76 ... fp[7] 83 [ 1034.753612] bond0: Disabling feature 0x0000000000008000 on lower dev p5p1. [ 1035.591019] bnx2x 0000:06:00.0 p5p1: using MSI-X IRQs: sp 62 fp[0] 64 ... fp[7] 71 This has been successfully tested with bnx2x, qlcnic and netxen network cards as slaves in a bond interface. Turning LRO on or off on the master also turns it on or off on each of the slaves, new slaves are added with LRO in the same state as the master, and LRO can't be toggled on the slaves. Also, this should largely remove the need for dev_disable_lro(), and most, if not all, of its call sites can be replaced by simply making sure NETIF_F_LRO isn't included in the relevant device's feature flags. Note that this patch is driven by bug reports from users saying it was confusing that bonds and slaves had different settings for the same features, and while it won't be 100% in sync if a lower device doesn't support a feature like LRO, I think this is a good step in the right direction. CC: "David S. Miller" CC: Eric Dumazet CC: Jay Vosburgh CC: Veaceslav Falico CC: Andy Gospodarek CC: Jiri Pirko CC: Nikolay Aleksandrov CC: Michal Kubecek CC: Alexander Duyck CC: netdev@vger.kernel.org Signed-off-by: Jarod Wilson Signed-off-by: David S. Miller --- include/linux/netdev_features.h | 11 +++++++++++ 1 file changed, 11 insertions(+) (limited to 'include') diff --git a/include/linux/netdev_features.h b/include/linux/netdev_features.h index 9672781c593d..0f5837a9b1ba 100644 --- a/include/linux/netdev_features.h +++ b/include/linux/netdev_features.h @@ -125,6 +125,11 @@ enum { #define NETIF_F_HW_L2FW_DOFFLOAD __NETIF_F(HW_L2FW_DOFFLOAD) #define NETIF_F_BUSY_POLL __NETIF_F(BUSY_POLL) +#define for_each_netdev_feature(mask_addr, feature) \ + int bit; \ + for_each_set_bit(bit, (unsigned long *)mask_addr, NETDEV_FEATURE_COUNT) \ + feature = __NETIF_F_BIT(bit); + /* Features valid for ethtool to change */ /* = all defined minus driver/device-class-related */ #define NETIF_F_NEVER_CHANGE (NETIF_F_VLAN_CHALLENGED | \ @@ -167,6 +172,12 @@ enum { */ #define NETIF_F_ALL_FOR_ALL (NETIF_F_NOCACHE_COPY | NETIF_F_FSO) +/* + * If upper/master device has these features disabled, they must be disabled + * on all lower/slave devices as well. + */ +#define NETIF_F_UPPER_DISABLES NETIF_F_LRO + /* changeable features with no special hardware requirements */ #define NETIF_F_SOFT_FEATURES (NETIF_F_GSO | NETIF_F_GRO) -- cgit v1.2.3 From e86abc689c5cb963f713c1bab9c37775421a6a96 Mon Sep 17 00:00:00 2001 From: Johannes Berg Date: Thu, 22 Oct 2015 17:35:14 +0200 Subject: cfg80211/mac80211: clarify RSSI CQM reporting requirements The previous patch changed mac80211 to always report an event after a CQM RSSI reconfiguration. Document that as expected behaviour in both the cfg80211 and mac80211 API. Currently, iwlmvm already implements that behaviour; the other drivers implementing CQM RSSI events may have to be changed. This behaviour lets userspace know what the current state is without relying on querying the data which is racy. Reviewed-by: Sharon, Sara Signed-off-by: Johannes Berg --- include/net/cfg80211.h | 4 ++++ include/net/mac80211.h | 4 +++- 2 files changed, 7 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h index 48155be5db7f..2c7bdb81d30c 100644 --- a/include/net/cfg80211.h +++ b/include/net/cfg80211.h @@ -2399,6 +2399,10 @@ struct cfg80211_qos_map { * @set_power_mgmt: Configure WLAN power management. A timeout value of -1 * allows the driver to adjust the dynamic ps timeout value. * @set_cqm_rssi_config: Configure connection quality monitor RSSI threshold. + * After configuration, the driver should (soon) send an event indicating + * the current level is above/below the configured threshold; this may + * need some care when the configuration is changed (without first being + * disabled.) * @set_cqm_txe_config: Configure connection quality monitor TX error * thresholds. * @sched_scan_start: Tell the driver to start a scheduled scan. diff --git a/include/net/mac80211.h b/include/net/mac80211.h index 4b9dd070aeb9..dac575c55c62 100644 --- a/include/net/mac80211.h +++ b/include/net/mac80211.h @@ -482,7 +482,9 @@ struct ieee80211_event { * Note that with TDLS this can be the case (channel is HT, protection must * be used from this field) even when the BSS association isn't using HT. * @cqm_rssi_thold: Connection quality monitor RSSI threshold, a zero value - * implies disabled + * implies disabled. As with the cfg80211 callback, a change here should + * cause an event to be sent indicating where the current value is in + * relation to the newly configured threshold. * @cqm_rssi_hyst: Connection quality monitor RSSI hysteresis * @arp_addr_list: List of IPv4 addresses for hardware ARP filtering. The * may filter ARP queries targeted for other addresses than listed here. -- cgit v1.2.3 From dcae9e0203dfd887a7413cd38d1f87aaac1127f4 Mon Sep 17 00:00:00 2001 From: Chaitanya T K Date: Fri, 30 Oct 2015 23:16:15 +0530 Subject: mac80211: document sleep requirements for channel context ops Channel context driver operations can sleep, so add might_sleep() and document this. Signed-off-by: Chaitanya T K Signed-off-by: Johannes Berg --- include/net/mac80211.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include') diff --git a/include/net/mac80211.h b/include/net/mac80211.h index dac575c55c62..82045fca388b 100644 --- a/include/net/mac80211.h +++ b/include/net/mac80211.h @@ -3172,18 +3172,24 @@ enum ieee80211_reconfig_type { * The callback is optional and can sleep. * * @add_chanctx: Notifies device driver about new channel context creation. + * This callback may sleep. * @remove_chanctx: Notifies device driver about channel context destruction. + * This callback may sleep. * @change_chanctx: Notifies device driver about channel context changes that * may happen when combining different virtual interfaces on the same * channel context with different settings + * This callback may sleep. * @assign_vif_chanctx: Notifies device driver about channel context being bound * to vif. Possible use is for hw queue remapping. + * This callback may sleep. * @unassign_vif_chanctx: Notifies device driver about channel context being * unbound from vif. + * This callback may sleep. * @switch_vif_chanctx: switch a number of vifs from one chanctx to * another, as specified in the list of * @ieee80211_vif_chanctx_switch passed to the driver, according * to the mode defined in &ieee80211_chanctx_switch_mode. + * This callback may sleep. * * @start_ap: Start operation on the AP interface, this is called after all the * information in bss_conf is set and beacon can be retrieved. A channel -- cgit v1.2.3 From 5f94c943d5dd4b51f3248193e622dd5fcdbb8b11 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Stefan=20S=C3=B8rensen?= Date: Tue, 3 Nov 2015 09:34:07 +0100 Subject: ptp: Change ptp_class to a proper bitmask MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Change the definition of PTP_CLASS_L2 to not have any bits overlapping with the other defined protocol values, allowing the PTP_CLASS_* definitions to be for simple filtering on packet type. Signed-off-by: Stefan Sørensen Signed-off-by: David S. Miller --- include/linux/ptp_classify.h | 7 ++++--- 1 file changed, 4 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/include/linux/ptp_classify.h b/include/linux/ptp_classify.h index 159c987b1853..a079656b614c 100644 --- a/include/linux/ptp_classify.h +++ b/include/linux/ptp_classify.h @@ -32,9 +32,9 @@ #define PTP_CLASS_VMASK 0x0f /* max protocol version is 15 */ #define PTP_CLASS_IPV4 0x10 /* event in an IPV4 UDP packet */ #define PTP_CLASS_IPV6 0x20 /* event in an IPV6 UDP packet */ -#define PTP_CLASS_L2 0x30 /* event in a L2 packet */ -#define PTP_CLASS_PMASK 0x30 /* mask for the packet type field */ -#define PTP_CLASS_VLAN 0x40 /* event in a VLAN tagged packet */ +#define PTP_CLASS_L2 0x40 /* event in a L2 packet */ +#define PTP_CLASS_PMASK 0x70 /* mask for the packet type field */ +#define PTP_CLASS_VLAN 0x80 /* event in a VLAN tagged packet */ #define PTP_CLASS_V1_IPV4 (PTP_CLASS_V1 | PTP_CLASS_IPV4) #define PTP_CLASS_V1_IPV6 (PTP_CLASS_V1 | PTP_CLASS_IPV6) /* probably DNE */ @@ -42,6 +42,7 @@ #define PTP_CLASS_V2_IPV6 (PTP_CLASS_V2 | PTP_CLASS_IPV6) #define PTP_CLASS_V2_L2 (PTP_CLASS_V2 | PTP_CLASS_L2) #define PTP_CLASS_V2_VLAN (PTP_CLASS_V2 | PTP_CLASS_VLAN) +#define PTP_CLASS_L4 (PTP_CLASS_IPV4 | PTP_CLASS_IPV6) #define PTP_EV_PORT 319 #define PTP_GEN_BIT 0x08 /* indicates general message, if set in message type */ -- cgit v1.2.3 From 5ba3f7d61a3a9e6d94462b207d302931b53d8c61 Mon Sep 17 00:00:00 2001 From: Jarod Wilson Date: Tue, 3 Nov 2015 10:15:59 -0500 Subject: net/core: fix for_each_netdev_feature As pointed out by Nikolay and further explained by Geert, the initial for_each_netdev_feature macro was broken, as feature would get set outside of the block of code it was intended to run in, thus only ever working for the first feature bit in the mask. While less pretty this way, this is tested and confirmed functional with multiple feature bits set in NETIF_F_UPPER_DISABLES. [root@dell-per730-01 ~]# ethtool -K bond0 lro off ... [ 242.761394] bond0: Disabling feature 0x0000000000008000 on lower dev p5p2. [ 243.552178] bnx2x 0000:06:00.1 p5p2: using MSI-X IRQs: sp 74 fp[0] 76 ... fp[7] 83 [ 244.353978] bond0: Disabling feature 0x0000000000008000 on lower dev p5p1. [ 245.147420] bnx2x 0000:06:00.0 p5p1: using MSI-X IRQs: sp 62 fp[0] 64 ... fp[7] 71 [root@dell-per730-01 ~]# ethtool -K bond0 gro off ... [ 251.925645] bond0: Disabling feature 0x0000000000004000 on lower dev p5p2. [ 252.713693] bnx2x 0000:06:00.1 p5p2: using MSI-X IRQs: sp 74 fp[0] 76 ... fp[7] 83 [ 253.499085] bond0: Disabling feature 0x0000000000004000 on lower dev p5p1. [ 254.290922] bnx2x 0000:06:00.0 p5p1: using MSI-X IRQs: sp 62 fp[0] 64 ... fp[7] 71 Fixes: fd867d51f ("net/core: generic support for disabling netdev features down stack") CC: "David S. Miller" CC: Eric Dumazet CC: Jay Vosburgh CC: Veaceslav Falico CC: Andy Gospodarek CC: Jiri Pirko CC: Nikolay Aleksandrov CC: Michal Kubecek CC: Alexander Duyck CC: Geert Uytterhoeven CC: netdev@vger.kernel.org Signed-off-by: Jarod Wilson Acked-by: Nikolay Aleksandrov Signed-off-by: David S. Miller --- include/linux/netdev_features.h | 6 ++---- 1 file changed, 2 insertions(+), 4 deletions(-) (limited to 'include') diff --git a/include/linux/netdev_features.h b/include/linux/netdev_features.h index 0f5837a9b1ba..f0d87347df19 100644 --- a/include/linux/netdev_features.h +++ b/include/linux/netdev_features.h @@ -125,10 +125,8 @@ enum { #define NETIF_F_HW_L2FW_DOFFLOAD __NETIF_F(HW_L2FW_DOFFLOAD) #define NETIF_F_BUSY_POLL __NETIF_F(BUSY_POLL) -#define for_each_netdev_feature(mask_addr, feature) \ - int bit; \ - for_each_set_bit(bit, (unsigned long *)mask_addr, NETDEV_FEATURE_COUNT) \ - feature = __NETIF_F_BIT(bit); +#define for_each_netdev_feature(mask_addr, bit) \ + for_each_set_bit(bit, (unsigned long *)mask_addr, NETDEV_FEATURE_COUNT) /* Features valid for ethtool to change */ /* = all defined minus driver/device-class-related */ -- cgit v1.2.3