From cae9910e73446cac68a54e3a7b02aaa12b689026 Mon Sep 17 00:00:00 2001 From: Felipe Gasper Date: Mon, 20 May 2019 19:43:51 -0500 Subject: net: Add UNIX_DIAG_UID to Netlink UNIX socket diagnostics. This adds the ability for Netlink to report a socket's UID along with the other UNIX diagnostic information that is already available. This will allow diagnostic tools greater insight into which users control which socket. To test this, do the following as a non-root user: unshare -U -r bash nc -l -U user.socket.$$ & .. and verify from within that same session that Netlink UNIX socket diagnostics report the socket's UID as 0. Also verify that Netlink UNIX socket diagnostics report the socket's UID as the user's UID from an unprivileged process in a different session. Verify the same from a root process. Signed-off-by: Felipe Gasper Signed-off-by: David S. Miller --- include/uapi/linux/unix_diag.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/uapi/linux/unix_diag.h b/include/uapi/linux/unix_diag.h index 5c502fdf7a42..a1988576fa8a 100644 --- a/include/uapi/linux/unix_diag.h +++ b/include/uapi/linux/unix_diag.h @@ -20,6 +20,7 @@ struct unix_diag_req { #define UDIAG_SHOW_ICONS 0x00000008 /* show pending connections */ #define UDIAG_SHOW_RQLEN 0x00000010 /* show skb receive queue len */ #define UDIAG_SHOW_MEMINFO 0x00000020 /* show memory info of a socket */ +#define UDIAG_SHOW_UID 0x00000040 /* show socket's UID */ struct unix_diag_msg { __u8 udiag_family; @@ -40,6 +41,7 @@ enum { UNIX_DIAG_RQLEN, UNIX_DIAG_MEMINFO, UNIX_DIAG_SHUTDOWN, + UNIX_DIAG_UID, __UNIX_DIAG_MAX, }; -- cgit v1.2.3 From 980066e6d9642fa5854bed8e592b1a30ea885b76 Mon Sep 17 00:00:00 2001 From: Trent Piepho Date: Wed, 22 May 2019 18:43:21 +0000 Subject: dt-bindings: phy: dp83867: Add documentation for disabling clock output The clock output is generally only used for testing and development and not used to daisy-chain PHYs. It's just a source of RF noise afterward. Add a mux value for "off". I've added it as another enumeration to the output property. In the actual PHY, the mux and the output enable are independently controllable. However, it doesn't seem useful to be able to describe the mux setting when the output is disabled. Document that PHY's default setting will be left as is if the property is omitted. Cc: Rob Herring Cc: Mark Rutland Signed-off-by: Trent Piepho Reviewed-by: Andrew Lunn Signed-off-by: David S. Miller --- include/dt-bindings/net/ti-dp83867.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/dt-bindings/net/ti-dp83867.h b/include/dt-bindings/net/ti-dp83867.h index 7b1656427cbe..192b79439eb7 100644 --- a/include/dt-bindings/net/ti-dp83867.h +++ b/include/dt-bindings/net/ti-dp83867.h @@ -56,4 +56,6 @@ #define DP83867_CLK_O_SEL_CHN_C_TCLK 0xA #define DP83867_CLK_O_SEL_CHN_D_TCLK 0xB #define DP83867_CLK_O_SEL_REF_CLK 0xC +/* Special flag to indicate clock should be off */ +#define DP83867_CLK_O_SEL_OFF 0xFFFFFFFF #endif -- cgit v1.2.3 From b2557764d0ebf387da7a11967fd955f3b226b172 Mon Sep 17 00:00:00 2001 From: Andrew Lunn Date: Wed, 22 May 2019 20:47:03 +0200 Subject: net: phy: Add support for 100BaseT1 and 1000BaseT1 Add link modes for 100Mbps and 1Gbps over a single pair. Signed-off-by: Andrew Lunn Signed-off-by: David S. Miller --- include/uapi/linux/ethtool.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/uapi/linux/ethtool.h b/include/uapi/linux/ethtool.h index 3534ce157ae9..dd06302aa93e 100644 --- a/include/uapi/linux/ethtool.h +++ b/include/uapi/linux/ethtool.h @@ -1483,6 +1483,8 @@ enum ethtool_link_mode_bit_indices { ETHTOOL_LINK_MODE_200000baseLR4_ER4_FR4_Full_BIT = 64, ETHTOOL_LINK_MODE_200000baseDR4_Full_BIT = 65, ETHTOOL_LINK_MODE_200000baseCR4_Full_BIT = 66, + ETHTOOL_LINK_MODE_100baseT1_Full_BIT = 67, + ETHTOOL_LINK_MODE_1000baseT1_Full_BIT = 68, /* must be last entry */ __ETHTOOL_LINK_MODE_MASK_NBITS -- cgit v1.2.3 From 68a9b13d9219a52cd272bd8e93f7fdfd1c22eba1 Mon Sep 17 00:00:00 2001 From: David Ahern Date: Wed, 22 May 2019 12:04:39 -0700 Subject: ipv6: Add delete route hook to stubs Add ip6_del_rt to the IPv6 stub. The hook is needed by the nexthop code to remove entries linked to a nexthop that is getting deleted. Signed-off-by: David Ahern Signed-off-by: David S. Miller --- include/net/ipv6_stubs.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/net/ipv6_stubs.h b/include/net/ipv6_stubs.h index 6c0c4fde16f8..307114a46eee 100644 --- a/include/net/ipv6_stubs.h +++ b/include/net/ipv6_stubs.h @@ -45,6 +45,7 @@ struct ipv6_stub { struct fib6_config *cfg, gfp_t gfp_flags, struct netlink_ext_ack *extack); void (*fib6_nh_release)(struct fib6_nh *fib6_nh); + int (*ip6_del_rt)(struct net *net, struct fib6_info *rt); void (*udpv6_encap_enable)(void); void (*ndisc_send_na)(struct net_device *dev, const struct in6_addr *daddr, const struct in6_addr *solicited_addr, -- cgit v1.2.3 From cdaa16a4f70cfa6c55641588c3a3eb9b53abd56b Mon Sep 17 00:00:00 2001 From: David Ahern Date: Wed, 22 May 2019 12:04:40 -0700 Subject: ipv6: Add hook to bump sernum for a route to stubs Add hook to ipv6 stub to bump the sernum up to the root node for a route. This is needed by the nexthop code when a nexthop config changes. Signed-off-by: David Ahern Signed-off-by: David S. Miller --- include/net/ip6_fib.h | 1 + include/net/ipv6_stubs.h | 1 + 2 files changed, 2 insertions(+) (limited to 'include') diff --git a/include/net/ip6_fib.h b/include/net/ip6_fib.h index 525f701653ca..d038d02cbc3c 100644 --- a/include/net/ip6_fib.h +++ b/include/net/ip6_fib.h @@ -485,6 +485,7 @@ int fib6_tables_dump(struct net *net, struct notifier_block *nb); void fib6_update_sernum(struct net *net, struct fib6_info *rt); void fib6_update_sernum_upto_root(struct net *net, struct fib6_info *rt); +void fib6_update_sernum_stub(struct net *net, struct fib6_info *f6i); void fib6_metric_set(struct fib6_info *f6i, int metric, u32 val); static inline bool fib6_metric_locked(struct fib6_info *f6i, int metric) diff --git a/include/net/ipv6_stubs.h b/include/net/ipv6_stubs.h index 307114a46eee..97f42e16b3b3 100644 --- a/include/net/ipv6_stubs.h +++ b/include/net/ipv6_stubs.h @@ -45,6 +45,7 @@ struct ipv6_stub { struct fib6_config *cfg, gfp_t gfp_flags, struct netlink_ext_ack *extack); void (*fib6_nh_release)(struct fib6_nh *fib6_nh); + void (*fib6_update_sernum)(struct net *net, struct fib6_info *rt); int (*ip6_del_rt)(struct net *net, struct fib6_info *rt); void (*udpv6_encap_enable)(void); void (*ndisc_send_na)(struct net_device *dev, const struct in6_addr *daddr, -- cgit v1.2.3 From 19a3b7eea42402accf52bcb9ddb51bfdb4d7a13b Mon Sep 17 00:00:00 2001 From: David Ahern Date: Wed, 22 May 2019 12:04:41 -0700 Subject: ipv6: export function to send route updates Add fib6_rt_update to send RTM_NEWROUTE with NLM_F_REPLACE set. This helper will be used by the nexthop code to notify userspace of routes that are impacted when a nexthop config is updated via replace. This notification is needed for legacy apps that do not understand the new nexthop object. Apps that are nexthop aware can use the RTA_NH_ID attribute in the route notification to just ignore it. In the future this should be wrapped in a sysctl to allow OS'es that are fully updated to avoid the notificaton storm. Signed-off-by: David Ahern Signed-off-by: David S. Miller --- include/net/ip6_fib.h | 6 ++++++ include/net/ipv6_stubs.h | 3 +++ 2 files changed, 9 insertions(+) (limited to 'include') diff --git a/include/net/ip6_fib.h b/include/net/ip6_fib.h index d038d02cbc3c..0d0d06b1cd26 100644 --- a/include/net/ip6_fib.h +++ b/include/net/ip6_fib.h @@ -452,6 +452,12 @@ int fib6_nh_init(struct net *net, struct fib6_nh *fib6_nh, struct netlink_ext_ack *extack); void fib6_nh_release(struct fib6_nh *fib6_nh); +int call_fib6_entry_notifiers(struct net *net, + enum fib_event_type event_type, + struct fib6_info *rt, + struct netlink_ext_ack *extack); +void fib6_rt_update(struct net *net, struct fib6_info *rt, + struct nl_info *info); void inet6_rt_notify(int event, struct fib6_info *rt, struct nl_info *info, unsigned int flags); diff --git a/include/net/ipv6_stubs.h b/include/net/ipv6_stubs.h index 97f42e16b3b3..5c93e942c50b 100644 --- a/include/net/ipv6_stubs.h +++ b/include/net/ipv6_stubs.h @@ -47,6 +47,9 @@ struct ipv6_stub { void (*fib6_nh_release)(struct fib6_nh *fib6_nh); void (*fib6_update_sernum)(struct net *net, struct fib6_info *rt); int (*ip6_del_rt)(struct net *net, struct fib6_info *rt); + void (*fib6_rt_update)(struct net *net, struct fib6_info *rt, + struct nl_info *info); + void (*udpv6_encap_enable)(void); void (*ndisc_send_na)(struct net_device *dev, const struct in6_addr *daddr, const struct in6_addr *solicited_addr, -- cgit v1.2.3 From 1bff1a0c9bbda06f1646030082123baf23ea8e7f Mon Sep 17 00:00:00 2001 From: David Ahern Date: Wed, 22 May 2019 12:04:42 -0700 Subject: ipv4: Add function to send route updates Add fib_info_notify_update to walk the fib and send RTM_NEWROUTE notifications with NLM_F_REPLACE set for entries linked to a fib_info that have nh_updated flag set. This helper will be used by the nexthop code to notify userspace of routes that are impacted when a nexthop config is updated via replace. The new function and its helper are similar to how fib_flush and fib_table_flush work for address delete and link down events. This notification is needed for legacy apps that do not understand the new nexthop object. Apps that are nexthop aware can use the RTA_NH_ID attribute in the route notification to just ignore it. In the future this should be wrapped in a sysctl to allow OS'es that are fully updated to avoid the notificaton storm. 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 d0e28f4ab099..ec6496c08f48 100644 --- a/include/net/ip_fib.h +++ b/include/net/ip_fib.h @@ -150,6 +150,7 @@ struct fib_info { #define fib_advmss fib_metrics->metrics[RTAX_ADVMSS-1] int fib_nhs; bool fib_nh_is_v6; + bool nh_updated; struct rcu_head rcu; struct fib_nh fib_nh[0]; #define fib_dev fib_nh[0].fib_nh_dev @@ -231,6 +232,7 @@ int call_fib4_notifiers(struct net *net, enum fib_event_type event_type, int __net_init fib4_notifier_init(struct net *net); void __net_exit fib4_notifier_exit(struct net *net); +void fib_info_notify_update(struct net *net, struct nl_info *info); void fib_notify(struct net *net, struct notifier_block *nb); struct fib_table { -- cgit v1.2.3 From ac1fab2d139447d84b10d99f80bec5d7b08c365a Mon Sep 17 00:00:00 2001 From: David Ahern Date: Wed, 22 May 2019 12:04:43 -0700 Subject: ipv4: export fib_check_nh Change fib_check_nh to take net, table and scope as input arguments over struct fib_config and export for use by nexthop code. 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 ec6496c08f48..27d7c89ca9c4 100644 --- a/include/net/ip_fib.h +++ b/include/net/ip_fib.h @@ -436,6 +436,8 @@ void fib_sync_mtu(struct net_device *dev, u32 orig_mtu); int fib_multipath_hash(const struct net *net, const struct flowi4 *fl4, const struct sk_buff *skb, struct flow_keys *flkeys); #endif +int fib_check_nh(struct net *net, struct fib_nh *nh, u32 table, u8 scope, + struct netlink_ext_ack *extack); void fib_select_multipath(struct fib_result *res, int hash); void fib_select_path(struct net *net, struct fib_result *res, struct flowi4 *fl4, const struct sk_buff *skb); -- cgit v1.2.3 From 9bd836679210534396a93a02f2fcf3ece64f45f7 Mon Sep 17 00:00:00 2001 From: David Ahern Date: Wed, 22 May 2019 12:04:44 -0700 Subject: ipv4: export fib_flush As nexthops are deleted, fib entries referencing it are marked dead. Export fib_flush so those entries can be removed in a timely manner. Signed-off-by: David Ahern Signed-off-by: David S. Miller --- include/net/ip_fib.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/net/ip_fib.h b/include/net/ip_fib.h index 27d7c89ca9c4..79c18bd6a059 100644 --- a/include/net/ip_fib.h +++ b/include/net/ip_fib.h @@ -473,6 +473,7 @@ static inline void fib_combine_itag(u32 *itag, const struct fib_result *res) #endif } +void fib_flush(struct net *net); void free_fib_info(struct fib_info *fi); static inline void fib_info_hold(struct fib_info *fi) -- cgit v1.2.3 From c3669486b5127165fd348daf4a785996820ac8f2 Mon Sep 17 00:00:00 2001 From: David Ahern Date: Wed, 22 May 2019 12:04:45 -0700 Subject: ipv4: export fib_info_update_nh_saddr Add scope as input argument versus relying on fib_info reference in fib_nh, and export fib_info_update_nh_saddr. Signed-off-by: David Ahern Signed-off-by: David S. Miller --- include/net/ip_fib.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/net/ip_fib.h b/include/net/ip_fib.h index 79c18bd6a059..8511ebb6f7be 100644 --- a/include/net/ip_fib.h +++ b/include/net/ip_fib.h @@ -201,7 +201,8 @@ static inline struct fib_nh_common *fib_info_nhc(struct fib_info *fi, int nhsel) #define FIB_TABLE_HASHSZ 2 #endif -__be32 fib_info_update_nh_saddr(struct net *net, struct fib_nh *nh); +__be32 fib_info_update_nh_saddr(struct net *net, struct fib_nh *nh, + unsigned char scope); __be32 fib_result_prefsrc(struct net *net, struct fib_result *res); #define FIB_RES_NHC(res) ((res).nhc) -- cgit v1.2.3 From 06c77c3e67b0352473345a162ab17729a132e7db Mon Sep 17 00:00:00 2001 From: David Ahern Date: Wed, 22 May 2019 12:04:46 -0700 Subject: ipv4: Rename and export nh_update_mtu Rename nh_update_mtu to fib_nhc_update_mtu and export for use by the nexthop code. Signed-off-by: David Ahern Signed-off-by: David S. Miller --- include/net/ip_fib.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/net/ip_fib.h b/include/net/ip_fib.h index 8511ebb6f7be..70ba0302c8c9 100644 --- a/include/net/ip_fib.h +++ b/include/net/ip_fib.h @@ -432,6 +432,7 @@ int fib_sync_down_dev(struct net_device *dev, unsigned long event, bool force); int fib_sync_down_addr(struct net_device *dev, __be32 local); int fib_sync_up(struct net_device *dev, unsigned char nh_flags); void fib_sync_mtu(struct net_device *dev, u32 orig_mtu); +void fib_nhc_update_mtu(struct fib_nh_common *nhc, u32 new, u32 orig); #ifdef CONFIG_IP_ROUTE_MULTIPATH int fib_multipath_hash(const struct net *net, const struct flowi4 *fl4, -- cgit v1.2.3 From 75425657fe3ad853b300976966d8fafa3f209b89 Mon Sep 17 00:00:00 2001 From: David Ahern Date: Wed, 22 May 2019 12:07:43 -0700 Subject: net: Set strict_start_type for routes and rules New userspace on an older kernel can send unknown and unsupported attributes resulting in an incompelete config which is almost always wrong for routing (few exceptions are passthrough settings like the protocol that installed the route). Set strict_start_type in the policies for IPv4 and IPv6 routes and rules to detect new, unsupported attributes and fail the route add. Signed-off-by: David Ahern Signed-off-by: David S. Miller --- include/net/fib_rules.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/net/fib_rules.h b/include/net/fib_rules.h index b473df5b9512..eba8465e1d86 100644 --- a/include/net/fib_rules.h +++ b/include/net/fib_rules.h @@ -103,6 +103,7 @@ struct fib_rule_notifier_info { }; #define FRA_GENERIC_POLICY \ + [FRA_UNSPEC] = { .strict_start_type = FRA_DPORT_RANGE + 1 }, \ [FRA_IIFNAME] = { .type = NLA_STRING, .len = IFNAMSIZ - 1 }, \ [FRA_OIFNAME] = { .type = NLA_STRING, .len = IFNAMSIZ - 1 }, \ [FRA_PRIORITY] = { .type = NLA_U32 }, \ -- cgit v1.2.3 From fc651001d2c5ca4f8b87efae2edb69fca94a6365 Mon Sep 17 00:00:00 2001 From: David Ahern Date: Wed, 22 May 2019 12:22:21 -0700 Subject: neighbor: Add tracepoint to __neigh_create Add tracepoint to __neigh_create to enable debugging of new entries. Signed-off-by: David Ahern Signed-off-by: David S. Miller --- include/trace/events/neigh.h | 49 ++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 49 insertions(+) (limited to 'include') diff --git a/include/trace/events/neigh.h b/include/trace/events/neigh.h index 0bdb08557763..62bb17516713 100644 --- a/include/trace/events/neigh.h +++ b/include/trace/events/neigh.h @@ -20,6 +20,55 @@ { NUD_NOARP, "noarp" }, \ { NUD_PERMANENT, "permanent"}) +TRACE_EVENT(neigh_create, + + TP_PROTO(struct neigh_table *tbl, struct net_device *dev, + const void *pkey, const struct neighbour *n, + bool exempt_from_gc), + + TP_ARGS(tbl, dev, pkey, n, exempt_from_gc), + + TP_STRUCT__entry( + __field(u32, family) + __dynamic_array(char, dev, IFNAMSIZ ) + __field(int, entries) + __field(u8, created) + __field(u8, gc_exempt) + __array(u8, primary_key4, 4) + __array(u8, primary_key6, 16) + ), + + TP_fast_assign( + struct in6_addr *pin6; + __be32 *p32; + + __entry->family = tbl->family; + __assign_str(dev, (dev ? dev->name : "NULL")); + __entry->entries = atomic_read(&tbl->gc_entries); + __entry->created = n != NULL; + __entry->gc_exempt = exempt_from_gc; + pin6 = (struct in6_addr *)__entry->primary_key6; + p32 = (__be32 *)__entry->primary_key4; + + if (tbl->family == AF_INET) + *p32 = *(__be32 *)pkey; + else + *p32 = 0; + +#if IS_ENABLED(CONFIG_IPV6) + if (tbl->family == AF_INET6) { + pin6 = (struct in6_addr *)__entry->primary_key6; + *pin6 = *(struct in6_addr *)pkey; + } +#endif + ), + + TP_printk("family %d dev %s entries %d primary_key4 %pI4 primary_key6 %pI6c created %d gc_exempt %d", + __entry->family, __get_str(dev), __entry->entries, + __entry->primary_key4, __entry->primary_key6, + __entry->created, __entry->gc_exempt) +); + TRACE_EVENT(neigh_update, TP_PROTO(struct neighbour *n, const u8 *lladdr, u8 new, -- cgit v1.2.3 From 0db355d499f10a79b6a5161e77c7eba8f062bde4 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Wed, 22 May 2019 15:00:25 -0700 Subject: ipv4/igmp: shrink struct ip_sf_list Removing two 4 bytes holes allows to use kmalloc-32 kmem cache instead of kmalloc-64 on 64bit kernels. Signed-off-by: Eric Dumazet 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 9c94b2ea789c..6649cb78de4a 100644 --- a/include/linux/igmp.h +++ b/include/linux/igmp.h @@ -65,8 +65,8 @@ struct ip_mc_socklist { struct ip_sf_list { struct ip_sf_list *sf_next; - __be32 sf_inaddr; unsigned long sf_count[2]; /* include/exclude counts */ + __be32 sf_inaddr; unsigned char sf_gsresp; /* include in g & s response? */ unsigned char sf_oldin; /* change state */ unsigned char sf_crcount; /* retrans. left to send */ -- cgit v1.2.3 From 136bf27fc0e9376525b9b6d9a1aa08508a0d1ac2 Mon Sep 17 00:00:00 2001 From: Jiri Pirko Date: Thu, 23 May 2019 10:43:35 +0200 Subject: devlink: add warning in case driver does not set port type Prevent misbehavior of drivers who would not set port type for longer period of time. Drivers should always set port type. Do WARN if that happens. Note that it is perfectly fine to temporarily not have the type set, during initialization and port type change. Signed-off-by: Jiri Pirko Signed-off-by: David S. Miller --- include/net/devlink.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/net/devlink.h b/include/net/devlink.h index 1c4adfb4195a..151eb930d329 100644 --- a/include/net/devlink.h +++ b/include/net/devlink.h @@ -17,6 +17,7 @@ #include #include #include +#include #include #include @@ -64,6 +65,7 @@ struct devlink_port { enum devlink_port_type desired_type; void *type_dev; struct devlink_port_attrs attrs; + struct delayed_work type_warn_dw; }; struct devlink_sb_pool_info { -- cgit v1.2.3 From 1bd33bf0fe6d3012410db0302187199871b510a0 Mon Sep 17 00:00:00 2001 From: Esben Haabendal Date: Thu, 23 May 2019 14:02:20 +0200 Subject: net: ll_temac: Prepare indirect register access for multicast support With .ndo_set_rx_mode/temac_set_multicast_list() being called in atomic context (holding addr_list_lock), and temac_set_multicast_list() needing to access temac indirect registers, the mutex used to synchronize indirect register is a no-no. Replace it with a spinlock, and avoid sleeping in temac_indirect_busywait(). To avoid excessive holding of the lock, which is now a spinlock, the temac_device_reset() function is changed to only hold the lock for short periods. With timeouts, it could be holding the spinlock for more than 2 seconds. Signed-off-by: Esben Haabendal Signed-off-by: David S. Miller --- include/linux/platform_data/xilinx-ll-temac.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/platform_data/xilinx-ll-temac.h b/include/linux/platform_data/xilinx-ll-temac.h index 368530f98176..f4a68136afa6 100644 --- a/include/linux/platform_data/xilinx-ll-temac.h +++ b/include/linux/platform_data/xilinx-ll-temac.h @@ -4,6 +4,7 @@ #include #include +#include struct ll_temac_platform_data { bool txcsum; /* Enable/disable TX checksum */ @@ -21,7 +22,7 @@ struct ll_temac_platform_data { * TEMAC IP block, the same mutex should be passed here, as * they share the same DCR bus bridge. */ - struct mutex *indirect_mutex; + spinlock_t *indirect_lock; /* DMA channel control setup */ u8 tx_irq_timeout; /* TX Interrupt Delay Time-out */ u8 tx_irq_count; /* TX Interrupt Coalescing Threshold Count */ -- cgit v1.2.3 From 9395da4efbd46661f0049d24d54d1cea63241fc9 Mon Sep 17 00:00:00 2001 From: Subash Abhinov Kasiviswanathan Date: Wed, 22 May 2019 14:21:07 -0600 Subject: net: qualcomm: rmnet: Move common struct definitions to include Create if_rmnet.h and move the rmnet MAP packet structs to this common include file. To account for portablity, add little and big endian bitfield definitions similar to the ip & tcp headers. The definitions in the headers can now be re-used by the upcoming ipa driver series as well as qmi_wwan. Signed-off-by: Subash Abhinov Kasiviswanathan Signed-off-by: David S. Miller --- include/linux/if_rmnet.h | 55 ++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 55 insertions(+) create mode 100644 include/linux/if_rmnet.h (limited to 'include') diff --git a/include/linux/if_rmnet.h b/include/linux/if_rmnet.h new file mode 100644 index 000000000000..b4f5403383fc --- /dev/null +++ b/include/linux/if_rmnet.h @@ -0,0 +1,55 @@ +/* SPDX-License-Identifier: GPL-2.0-only + * Copyright (c) 2013-2019, The Linux Foundation. All rights reserved. + */ + +#ifndef _LINUX_IF_RMNET_H_ +#define _LINUX_IF_RMNET_H_ + +struct rmnet_map_header { +#if defined(__LITTLE_ENDIAN_BITFIELD) + u8 pad_len:6; + u8 reserved_bit:1; + u8 cd_bit:1; +#elif defined (__BIG_ENDIAN_BITFIELD) + u8 cd_bit:1; + u8 reserved_bit:1; + u8 pad_len:6; +#else +#error "Please fix " +#endif + u8 mux_id; + __be16 pkt_len; +} __aligned(1); + +struct rmnet_map_dl_csum_trailer { + u8 reserved1; +#if defined(__LITTLE_ENDIAN_BITFIELD) + u8 valid:1; + u8 reserved2:7; +#elif defined (__BIG_ENDIAN_BITFIELD) + u8 reserved2:7; + u8 valid:1; +#else +#error "Please fix " +#endif + u16 csum_start_offset; + u16 csum_length; + __be16 csum_value; +} __aligned(1); + +struct rmnet_map_ul_csum_header { + __be16 csum_start_offset; +#if defined(__LITTLE_ENDIAN_BITFIELD) + u16 csum_insert_offset:14; + u16 udp_ip4_ind:1; + u16 csum_enabled:1; +#elif defined (__BIG_ENDIAN_BITFIELD) + u16 csum_enabled:1; + u16 udp_ip4_ind:1; + u16 csum_insert_offset:14; +#else +#error "Please fix " +#endif +} __aligned(1); + +#endif /* !(_LINUX_IF_RMNET_H_) */ -- cgit v1.2.3 From a8f500af0ccffc3d2aaf9018537981cb173865a1 Mon Sep 17 00:00:00 2001 From: Alexei Starovoitov Date: Tue, 21 May 2019 20:17:06 -0700 Subject: bpf: split explored_states split explored_states into prune_point boolean mark and link list of explored states. This removes STATE_LIST_MARK hack and allows marks to be separate from states. Signed-off-by: Alexei Starovoitov Signed-off-by: Daniel Borkmann --- include/linux/bpf_verifier.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/bpf_verifier.h b/include/linux/bpf_verifier.h index 1305ccbd8fe6..02bba09a0ea1 100644 --- a/include/linux/bpf_verifier.h +++ b/include/linux/bpf_verifier.h @@ -233,6 +233,7 @@ struct bpf_insn_aux_data { int sanitize_stack_off; /* stack slot to be cleared */ bool seen; /* this insn was processed by the verifier */ u8 alu_state; /* used in combination with alu_limit */ + bool prune_point; unsigned int orig_idx; /* original instruction index */ }; -- cgit v1.2.3 From dc2a4ebc0b44a212fcf72242210e56aa17e7317b Mon Sep 17 00:00:00 2001 From: Alexei Starovoitov Date: Tue, 21 May 2019 20:17:07 -0700 Subject: bpf: convert explored_states to hash table All prune points inside a callee bpf function most likely will have different callsites. For example, if function foo() is called from two callsites the half of explored states in all prune points in foo() will be useless for subsequent walking of one of those callsites. Fortunately explored_states pruning heuristics keeps the number of states per prune point small, but walking these states is still a waste of cpu time when the callsite of the current state is different from the callsite of the explored state. To improve pruning logic convert explored_states into hash table and use simple insn_idx ^ callsite hash to select hash bucket. This optimization has no effect on programs without bpf2bpf calls and drastically improves programs with calls. In the later case it reduces total memory consumption in 1M scale tests by almost 3 times (peak_states drops from 5752 to 2016). Care should be taken when comparing the states for equivalency. Since the same hash bucket can now contain states with different indices the insn_idx has to be part of verifier_state and compared. Different hash table sizes and different hash functions were explored, but the results were not significantly better vs this patch. They can be improved in the future. Hit/miss heuristic is not counting index miscompare as a miss. Otherwise verifier stats become unstable when experimenting with different hash functions. Signed-off-by: Alexei Starovoitov Signed-off-by: Daniel Borkmann --- include/linux/bpf_verifier.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/bpf_verifier.h b/include/linux/bpf_verifier.h index 02bba09a0ea1..405b502283c5 100644 --- a/include/linux/bpf_verifier.h +++ b/include/linux/bpf_verifier.h @@ -187,6 +187,7 @@ struct bpf_func_state { struct bpf_verifier_state { /* call stack tracking */ struct bpf_func_state *frame[MAX_CALL_FRAMES]; + u32 insn_idx; u32 curframe; u32 active_spin_lock; bool speculative; -- cgit v1.2.3 From f40b6ae2b612446dc970d7b51eeec47bd1619f82 Mon Sep 17 00:00:00 2001 From: David Ahern Date: Wed, 22 May 2019 20:27:55 -0700 Subject: ipv6: Move pcpu cached routes to fib6_nh rt6_info are specific instances of a fib entry and are tied to a device and gateway - ie., a nexthop. Before nexthop objects, IPv6 fib entries have separate fib6_info for each nexthop in a multipath route, so the location of the pcpu cache in the fib6_info struct worked. However, with nexthop objects a fib6_info can point to a set of nexthops (yet another alignment of ipv6 with ipv4). Accordingly, the pcpu cache needs to be moved to the fib6_nh struct so the cached entries are local to the nexthop specification used to create the rt6_info. Initialization and free of the pcpu entries moved to fib6_nh_init and fib6_nh_release. Change in location only, from fib6_info down to fib6_nh; no other functional change intended. Signed-off-by: David Ahern Signed-off-by: David S. Miller --- include/net/ip6_fib.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/net/ip6_fib.h b/include/net/ip6_fib.h index 0d0d06b1cd26..38e87ef81b7e 100644 --- a/include/net/ip6_fib.h +++ b/include/net/ip6_fib.h @@ -131,6 +131,8 @@ struct fib6_nh { #ifdef CONFIG_IPV6_ROUTER_PREF unsigned long last_probe; #endif + + struct rt6_info * __percpu *rt6i_pcpu; }; struct fib6_info { @@ -156,7 +158,6 @@ struct fib6_info { struct rt6key fib6_src; struct rt6key fib6_prefsrc; - struct rt6_info * __percpu *rt6i_pcpu; struct rt6_exception_bucket __rcu *rt6i_exception_bucket; u32 fib6_metric; -- cgit v1.2.3 From cc5c073a693fa6ed7a207b0436114f68cce72434 Mon Sep 17 00:00:00 2001 From: David Ahern Date: Wed, 22 May 2019 20:27:58 -0700 Subject: ipv6: Move exception bucket to fib6_nh Similar to the pcpu routes exceptions are really per nexthop, so move rt6i_exception_bucket from fib6_info to fib6_nh. To avoid additional increases to the size of fib6_nh for a 1-bit flag, use the lowest bit in the allocated memory pointer for the flushed flag. Add helpers for retrieving the bucket pointer to mask off the flag. The cleanup of the exception bucket is moved to fib6_nh_release. fib6_nh_flush_exceptions can now be called from 2 contexts: 1. deleting a fib entry 2. deleting a fib6_nh For 1., fib6_nh_flush_exceptions is called for a specific fib6_info that is getting deleted. All exceptions in the cache using the entry are deleted. For 2, the fib6_nh itself is getting destroyed so fib6_nh_flush_exceptions is called for a NULL fib6_info which means flush all entries. The pmtu.sh selftest exercises the affected code paths - from creating exceptions to cleaning them up on device delete. All tests pass without any rcu locking or memleak warnings. Signed-off-by: David Ahern Signed-off-by: David S. Miller --- include/net/ip6_fib.h | 8 +++----- 1 file changed, 3 insertions(+), 5 deletions(-) (limited to 'include') diff --git a/include/net/ip6_fib.h b/include/net/ip6_fib.h index 38e87ef81b7e..6b4852cf2fc2 100644 --- a/include/net/ip6_fib.h +++ b/include/net/ip6_fib.h @@ -133,6 +133,7 @@ struct fib6_nh { #endif struct rt6_info * __percpu *rt6i_pcpu; + struct rt6_exception_bucket __rcu *rt6i_exception_bucket; }; struct fib6_info { @@ -158,18 +159,15 @@ struct fib6_info { struct rt6key fib6_src; struct rt6key fib6_prefsrc; - struct rt6_exception_bucket __rcu *rt6i_exception_bucket; - u32 fib6_metric; u8 fib6_protocol; u8 fib6_type; - u8 exception_bucket_flushed:1, - should_flush:1, + u8 should_flush:1, dst_nocount:1, dst_nopolicy:1, dst_host:1, fib6_destroying:1, - unused:2; + unused:3; struct fib6_nh fib6_nh; struct rcu_head rcu; -- cgit v1.2.3 From 1cf844c747d5424abe76f7b599c00b1ac17d3fce Mon Sep 17 00:00:00 2001 From: David Ahern Date: Wed, 22 May 2019 20:27:59 -0700 Subject: ipv6: Make fib6_nh optional at the end of fib6_info Move fib6_nh to the end of fib6_info and make it an array of size 0. Pass a flag to fib6_info_alloc indicating if the allocation needs to add space for a fib6_nh. The current code path always has a fib6_nh allocated with a fib6_info; with nexthop objects they will be separate. Signed-off-by: David Ahern Signed-off-by: David S. Miller --- include/net/ip6_fib.h | 6 +++--- include/net/ip6_route.h | 4 ++-- 2 files changed, 5 insertions(+), 5 deletions(-) (limited to 'include') diff --git a/include/net/ip6_fib.h b/include/net/ip6_fib.h index 6b4852cf2fc2..ebe5d65f97e0 100644 --- a/include/net/ip6_fib.h +++ b/include/net/ip6_fib.h @@ -169,8 +169,8 @@ struct fib6_info { fib6_destroying:1, unused:3; - struct fib6_nh fib6_nh; struct rcu_head rcu; + struct fib6_nh fib6_nh[0]; }; struct rt6_info { @@ -280,7 +280,7 @@ static inline void ip6_rt_put(struct rt6_info *rt) dst_release(&rt->dst); } -struct fib6_info *fib6_info_alloc(gfp_t gfp_flags); +struct fib6_info *fib6_info_alloc(gfp_t gfp_flags, bool with_fib6_nh); void fib6_info_destroy_rcu(struct rcu_head *head); static inline void fib6_info_hold(struct fib6_info *f6i) @@ -443,7 +443,7 @@ void rt6_get_prefsrc(const struct rt6_info *rt, struct in6_addr *addr) static inline struct net_device *fib6_info_nh_dev(const struct fib6_info *f6i) { - return f6i->fib6_nh.fib_nh_dev; + return f6i->fib6_nh->fib_nh_dev; } int fib6_nh_init(struct net *net, struct fib6_nh *fib6_nh, diff --git a/include/net/ip6_route.h b/include/net/ip6_route.h index 4790beaa86e0..a6ce6ea856b9 100644 --- a/include/net/ip6_route.h +++ b/include/net/ip6_route.h @@ -70,7 +70,7 @@ static inline bool rt6_qualify_for_ecmp(const struct fib6_info *f6i) { /* the RTF_ADDRCONF flag filters out RA's */ return !(f6i->fib6_flags & RTF_ADDRCONF) && - f6i->fib6_nh.fib_nh_gw_family; + f6i->fib6_nh->fib_nh_gw_family; } void ip6_route_input(struct sk_buff *skb); @@ -275,7 +275,7 @@ static inline struct in6_addr *rt6_nexthop(struct rt6_info *rt, static inline bool rt6_duplicate_nexthop(struct fib6_info *a, struct fib6_info *b) { - struct fib6_nh *nha = &a->fib6_nh, *nhb = &b->fib6_nh; + struct fib6_nh *nha = a->fib6_nh, *nhb = b->fib6_nh; return nha->fib_nh_dev == nhb->fib_nh_dev && ipv6_addr_equal(&nha->fib_nh_gw6, &nhb->fib_nh_gw6) && -- cgit v1.2.3 From 4618d6719743b60f1da4b8112c4518ee46110b94 Mon Sep 17 00:00:00 2001 From: Heiner Kallweit Date: Thu, 23 May 2019 20:06:49 +0200 Subject: net: phy: add interface mode PHY_INTERFACE_MODE_USXGMII Add support for interface mode PHY_INTERFACE_MODE_USXGMII. Signed-off-by: Heiner Kallweit Reviewed-by: Florian Fainelli Signed-off-by: David S. Miller --- include/linux/phy.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include') diff --git a/include/linux/phy.h b/include/linux/phy.h index 073fb151b5a9..7180b1d1e5e3 100644 --- a/include/linux/phy.h +++ b/include/linux/phy.h @@ -103,6 +103,7 @@ typedef enum { PHY_INTERFACE_MODE_XAUI, /* 10GBASE-KR, XFI, SFI - single lane 10G Serdes */ PHY_INTERFACE_MODE_10GKR, + PHY_INTERFACE_MODE_USXGMII, PHY_INTERFACE_MODE_MAX, } phy_interface_t; @@ -178,6 +179,8 @@ static inline const char *phy_modes(phy_interface_t interface) return "xaui"; case PHY_INTERFACE_MODE_10GKR: return "10gbase-kr"; + case PHY_INTERFACE_MODE_USXGMII: + return "usxgmii"; default: return "unknown"; } -- cgit v1.2.3 From 8b401f9ed2441ad9e219953927a842d24ed051fc Mon Sep 17 00:00:00 2001 From: Yonghong Song Date: Thu, 23 May 2019 14:47:45 -0700 Subject: bpf: implement bpf_send_signal() helper This patch tries to solve the following specific use case. Currently, bpf program can already collect stack traces through kernel function get_perf_callchain() when certain events happens (e.g., cache miss counter or cpu clock counter overflows). But such stack traces are not enough for jitted programs, e.g., hhvm (jited php). To get real stack trace, jit engine internal data structures need to be traversed in order to get the real user functions. bpf program itself may not be the best place to traverse the jit engine as the traversing logic could be complex and it is not a stable interface either. Instead, hhvm implements a signal handler, e.g. for SIGALARM, and a set of program locations which it can dump stack traces. When it receives a signal, it will dump the stack in next such program location. Such a mechanism can be implemented in the following way: . a perf ring buffer is created between bpf program and tracing app. . once a particular event happens, bpf program writes to the ring buffer and the tracing app gets notified. . the tracing app sends a signal SIGALARM to the hhvm. But this method could have large delays and causing profiling results skewed. This patch implements bpf_send_signal() helper to send a signal to hhvm in real time, resulting in intended stack traces. Acked-by: Andrii Nakryiko Signed-off-by: Yonghong Song Signed-off-by: Daniel Borkmann --- include/uapi/linux/bpf.h | 17 ++++++++++++++++- 1 file changed, 16 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index 63e0cf66f01a..68d4470523a0 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -2672,6 +2672,20 @@ union bpf_attr { * 0 on success. * * **-ENOENT** if the bpf-local-storage cannot be found. + * + * int bpf_send_signal(u32 sig) + * Description + * Send signal *sig* to the current task. + * Return + * 0 on success or successfully queued. + * + * **-EBUSY** if work queue under nmi is full. + * + * **-EINVAL** if *sig* is invalid. + * + * **-EPERM** if no permission to send the *sig*. + * + * **-EAGAIN** if bpf program can try again. */ #define __BPF_FUNC_MAPPER(FN) \ FN(unspec), \ @@ -2782,7 +2796,8 @@ union bpf_attr { FN(strtol), \ FN(strtoul), \ FN(sk_storage_get), \ - FN(sk_storage_delete), + FN(sk_storage_delete), \ + FN(send_signal), /* integer value in 'imm' field of BPF_CALL instruction selects which helper * function eBPF program intends to call -- cgit v1.2.3 From 5327ed3d44b754f5cc51d5b3f18e442eaebacff5 Mon Sep 17 00:00:00 2001 From: Jiong Wang Date: Fri, 24 May 2019 23:25:12 +0100 Subject: bpf: verifier: mark verified-insn with sub-register zext flag eBPF ISA specification requires high 32-bit cleared when low 32-bit sub-register is written. This applies to destination register of ALU32 etc. JIT back-ends must guarantee this semantic when doing code-gen. x86_64 and AArch64 ISA has the same semantics, so the corresponding JIT back-end doesn't need to do extra work. However, 32-bit arches (arm, x86, nfp etc.) and some other 64-bit arches (PowerPC, SPARC etc) need to do explicit zero extension to meet this requirement, otherwise code like the following will fail. u64_value = (u64) u32_value ... other uses of u64_value This is because compiler could exploit the semantic described above and save those zero extensions for extending u32_value to u64_value, these JIT back-ends are expected to guarantee this through inserting extra zero extensions which however could be a significant increase on the code size. Some benchmarks show there could be ~40% sub-register writes out of total insns, meaning at least ~40% extra code-gen. One observation is these extra zero extensions are not always necessary. Take above code snippet for example, it is possible u32_value will never be casted into a u64, the value of high 32-bit of u32_value then could be ignored and extra zero extension could be eliminated. This patch implements this idea, insns defining sub-registers will be marked when the high 32-bit of the defined sub-register matters. For those unmarked insns, it is safe to eliminate high 32-bit clearnace for them. Algo: - Split read flags into READ32 and READ64. - Record index of insn that does sub-register write. Keep the index inside reg state and update it during verifier insn walking. - A full register read on a sub-register marks its definition insn as needing zero extension on dst register. A new sub-register write overrides the old one. - When propagating read64 during path pruning, also mark any insn defining a sub-register that is read in the pruned path as full-register. Reviewed-by: Jakub Kicinski Signed-off-by: Jiong Wang Signed-off-by: Alexei Starovoitov --- include/linux/bpf_verifier.h | 14 +++++++++++--- 1 file changed, 11 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/include/linux/bpf_verifier.h b/include/linux/bpf_verifier.h index 405b502283c5..704ed7971472 100644 --- a/include/linux/bpf_verifier.h +++ b/include/linux/bpf_verifier.h @@ -36,9 +36,11 @@ */ enum bpf_reg_liveness { REG_LIVE_NONE = 0, /* reg hasn't been read or written this branch */ - REG_LIVE_READ, /* reg was read, so we're sensitive to initial value */ - REG_LIVE_WRITTEN, /* reg was written first, screening off later reads */ - REG_LIVE_DONE = 4, /* liveness won't be updating this register anymore */ + REG_LIVE_READ32 = 0x1, /* reg was read, so we're sensitive to initial value */ + REG_LIVE_READ64 = 0x2, /* likewise, but full 64-bit content matters */ + REG_LIVE_READ = REG_LIVE_READ32 | REG_LIVE_READ64, + REG_LIVE_WRITTEN = 0x4, /* reg was written first, screening off later reads */ + REG_LIVE_DONE = 0x8, /* liveness won't be updating this register anymore */ }; struct bpf_reg_state { @@ -131,6 +133,11 @@ struct bpf_reg_state { * pointing to bpf_func_state. */ u32 frameno; + /* Tracks subreg definition. The stored value is the insn_idx of the + * writing insn. This is safe because subreg_def is used before any insn + * patching which only happens after main verification finished. + */ + s32 subreg_def; enum bpf_reg_liveness live; }; @@ -233,6 +240,7 @@ struct bpf_insn_aux_data { int ctx_field_size; /* the ctx field size for load insn, maybe 0 */ int sanitize_stack_off; /* stack slot to be cleared */ bool seen; /* this insn was processed by the verifier */ + bool zext_dst; /* this insn zero extends dst reg */ u8 alu_state; /* used in combination with alu_limit */ bool prune_point; unsigned int orig_idx; /* original instruction index */ -- cgit v1.2.3 From 7d134041a89610ae552501fc88652805addcdee4 Mon Sep 17 00:00:00 2001 From: Jiong Wang Date: Fri, 24 May 2019 23:25:14 +0100 Subject: bpf: introduce new mov32 variant for doing explicit zero extension The encoding for this new variant is based on BPF_X format. "imm" field was 0 only, now it could be 1 which means doing zero extension unconditionally .code = BPF_ALU | BPF_MOV | BPF_X .dst_reg = DST .src_reg = SRC .imm = 1 We use this new form for doing zero extension for which verifier will guarantee SRC == DST. Implications on JIT back-ends when doing code-gen for BPF_ALU | BPF_MOV | BPF_X: 1. No change if hardware already does zero extension unconditionally for sub-register write. 2. Otherwise, when seeing imm == 1, just generate insns to clear high 32-bit. No need to generate insns for the move because when imm == 1, dst_reg is the same as src_reg at the moment. Interpreter doesn't need change as well. It is doing unconditionally zero extension for mov32 already. One helper macro BPF_ZEXT_REG is added to help creating zero extension insn using this new mov32 variant. One helper function insn_is_zext is added for checking one insn is an zero extension on dst. This will be widely used by a few JIT back-ends in later patches in this set. Signed-off-by: Jiong Wang Signed-off-by: Alexei Starovoitov --- include/linux/filter.h | 14 ++++++++++++++ 1 file changed, 14 insertions(+) (limited to 'include') diff --git a/include/linux/filter.h b/include/linux/filter.h index 7148bab96943..bb10ffb88452 100644 --- a/include/linux/filter.h +++ b/include/linux/filter.h @@ -160,6 +160,20 @@ struct ctl_table_header; .off = 0, \ .imm = IMM }) +/* Special form of mov32, used for doing explicit zero extension on dst. */ +#define BPF_ZEXT_REG(DST) \ + ((struct bpf_insn) { \ + .code = BPF_ALU | BPF_MOV | BPF_X, \ + .dst_reg = DST, \ + .src_reg = DST, \ + .off = 0, \ + .imm = 1 }) + +static inline bool insn_is_zext(const struct bpf_insn *insn) +{ + return insn->code == (BPF_ALU | BPF_MOV | BPF_X) && insn->imm == 1; +} + /* BPF_LD_IMM64 macro encodes single 'load 64-bit immediate' insn */ #define BPF_LD_IMM64(DST, IMM) \ BPF_LD_IMM64_RAW(DST, 0, IMM) -- cgit v1.2.3 From a4b1d3c1ddf6cb441187b6c130a473c16a05a356 Mon Sep 17 00:00:00 2001 From: Jiong Wang Date: Fri, 24 May 2019 23:25:15 +0100 Subject: bpf: verifier: insert zero extension according to analysis result After previous patches, verifier will mark a insn if it really needs zero extension on dst_reg. It is then for back-ends to decide how to use such information to eliminate unnecessary zero extension code-gen during JIT compilation. One approach is verifier insert explicit zero extension for those insns that need zero extension in a generic way, JIT back-ends then do not generate zero extension for sub-register write at default. However, only those back-ends which do not have hardware zero extension want this optimization. Back-ends like x86_64 and AArch64 have hardware zero extension support that the insertion should be disabled. This patch introduces new target hook "bpf_jit_needs_zext" which returns false at default, meaning verifier zero extension insertion is disabled at default. A back-end could override this hook to return true if it doesn't have hardware support and want verifier insert zero extension explicitly. Offload targets do not use this native target hook, instead, they could get the optimization results using bpf_prog_offload_ops.finalize. NOTE: arches could have diversified features, it is possible for one arch to have hardware zero extension support for some sub-register write insns but not for all. For example, PowerPC, SPARC have zero extended loads, but not for alu32. So when verifier zero extension insertion enabled, these JIT back-ends need to peephole insns to remove those zero extension inserted for insn that actually has hardware zero extension support. The peephole could be as simple as looking the next insn, if it is a special zero extension insn then it is safe to eliminate it if the current insn has hardware zero extension support. Reviewed-by: Jakub Kicinski Signed-off-by: Jiong Wang Signed-off-by: Alexei Starovoitov --- include/linux/bpf.h | 1 + include/linux/filter.h | 1 + 2 files changed, 2 insertions(+) (limited to 'include') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 4fb3aa2dc975..d98141edb74b 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -370,6 +370,7 @@ struct bpf_prog_aux { u32 id; u32 func_cnt; /* used by non-func prog as the number of func progs */ u32 func_idx; /* 0 for non-func prog, the index in func array for func prog */ + bool verifier_zext; /* Zero extensions has been inserted by verifier. */ bool offload_requested; struct bpf_prog **func; void *jit_data; /* JIT specific data. arch dependent */ diff --git a/include/linux/filter.h b/include/linux/filter.h index bb10ffb88452..ba8b65270e0d 100644 --- a/include/linux/filter.h +++ b/include/linux/filter.h @@ -825,6 +825,7 @@ u64 __bpf_call_base(u64 r1, u64 r2, u64 r3, u64 r4, u64 r5); struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *prog); void bpf_jit_compile(struct bpf_prog *prog); +bool bpf_jit_needs_zext(void); bool bpf_helper_changes_pkt_data(void *func); static inline bool bpf_dump_raw_ok(void) -- cgit v1.2.3 From c240eff63a1cf1c4edc768e0cfc374811c02f069 Mon Sep 17 00:00:00 2001 From: Jiong Wang Date: Fri, 24 May 2019 23:25:16 +0100 Subject: bpf: introduce new bpf prog load flags "BPF_F_TEST_RND_HI32" x86_64 and AArch64 perhaps are two arches that running bpf testsuite frequently, however the zero extension insertion pass is not enabled for them because of their hardware support. It is critical to guarantee the pass correction as it is supposed to be enabled at default for a couple of other arches, for example PowerPC, SPARC, arm, NFP etc. Therefore, it would be very useful if there is a way to test this pass on for example x86_64. The test methodology employed by this set is "poisoning" useless bits. High 32-bit of a definition is randomized if it is identified as not used by any later insn. Such randomization is only enabled under testing mode which is gated by the new bpf prog load flags "BPF_F_TEST_RND_HI32". Suggested-by: Alexei Starovoitov Signed-off-by: Jiong Wang Signed-off-by: Alexei Starovoitov --- include/uapi/linux/bpf.h | 18 ++++++++++++++++++ 1 file changed, 18 insertions(+) (limited to 'include') diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index 68d4470523a0..7c6aef253173 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -260,6 +260,24 @@ enum bpf_attach_type { */ #define BPF_F_ANY_ALIGNMENT (1U << 1) +/* BPF_F_TEST_RND_HI32 is used in BPF_PROG_LOAD command for testing purpose. + * Verifier does sub-register def/use analysis and identifies instructions whose + * def only matters for low 32-bit, high 32-bit is never referenced later + * through implicit zero extension. Therefore verifier notifies JIT back-ends + * that it is safe to ignore clearing high 32-bit for these instructions. This + * saves some back-ends a lot of code-gen. However such optimization is not + * necessary on some arches, for example x86_64, arm64 etc, whose JIT back-ends + * hence hasn't used verifier's analysis result. But, we really want to have a + * way to be able to verify the correctness of the described optimization on + * x86_64 on which testsuites are frequently exercised. + * + * So, this flag is introduced. Once it is set, verifier will randomize high + * 32-bit for those instructions who has been identified as safe to ignore them. + * Then, if verifier is not doing correct analysis, such randomization will + * regress tests to expose bugs. + */ +#define BPF_F_TEST_RND_HI32 (1U << 2) + /* When BPF ldimm64's insn[0].src_reg != 0 then this can have * two extensions: * -- cgit v1.2.3 From 08eb1fb0f77b0036568d2228f3425f2595d671bb Mon Sep 17 00:00:00 2001 From: Michal Kalderon Date: Sun, 26 May 2019 15:22:22 +0300 Subject: qed*: Change hwfn used for sb initialization When initializing status blocks use the affined hwfn instead of the leading one for RDMA / Storage Signed-off-by: Ariel Elior Signed-off-by: Michal Kalderon Signed-off-by: David S. Miller --- include/linux/qed/qed_if.h | 10 +++++++++- 1 file changed, 9 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/qed/qed_if.h b/include/linux/qed/qed_if.h index 48841e5dab90..eef02e64b422 100644 --- a/include/linux/qed/qed_if.h +++ b/include/linux/qed/qed_if.h @@ -907,7 +907,8 @@ struct qed_common_ops { u32 (*sb_release)(struct qed_dev *cdev, struct qed_sb_info *sb_info, - u16 sb_id); + u16 sb_id, + enum qed_sb_type type); void (*simd_handler_config)(struct qed_dev *cdev, void *token, @@ -1123,6 +1124,13 @@ struct qed_common_ops { */ int (*read_module_eeprom)(struct qed_dev *cdev, char *buf, u8 dev_addr, u32 offset, u32 len); + +/** + * @brief get_affin_hwfn_idx + * + * @param cdev + */ + u8 (*get_affin_hwfn_idx)(struct qed_dev *cdev); }; #define MASK_FIELD(_name, _value) \ -- cgit v1.2.3 From 3576e99e08217f291290ac62431c7e330ac111c4 Mon Sep 17 00:00:00 2001 From: Michal Kalderon Date: Sun, 26 May 2019 15:22:27 +0300 Subject: qed*: Add iWARP 100g support Add iWARP engine affinity setting for supporting iWARP over 100g. iWARP cannot be distinguished by the LLH from L2, hence the engine division will affect L2 as well. For this reason we add a parameter to devlink to determine the engine division. Signed-off-by: Ariel Elior Signed-off-by: Michal Kalderon Signed-off-by: David S. Miller --- include/linux/qed/qed_rdma_if.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/linux/qed/qed_rdma_if.h b/include/linux/qed/qed_rdma_if.h index d15f8e4815e3..898f595ea3d6 100644 --- a/include/linux/qed/qed_rdma_if.h +++ b/include/linux/qed/qed_rdma_if.h @@ -670,6 +670,8 @@ struct qed_rdma_ops { int (*ll2_set_mac_filter)(struct qed_dev *cdev, u8 *old_mac_address, u8 *new_mac_address); + int (*iwarp_set_engine_affin)(struct qed_dev *cdev, bool b_reset); + int (*iwarp_connect)(void *rdma_cxt, struct qed_iwarp_connect_in *iparams, struct qed_iwarp_connect_out *oparams); -- cgit v1.2.3 From 6ce3b4dcee4f96a5000d3f790403eb6997e3d553 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Fri, 24 May 2019 09:03:30 -0700 Subject: inet: rename netns_frags to fqdir 1) struct netns_frags is renamed to struct fqdir This structure is really holding many frag queues in a hash table. 2) (struct inet_frag_queue)->net field is renamed to fqdir since net is generally associated to a 'struct net' pointer in networking stack. Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- include/net/inet_frag.h | 29 +++++++++++++++-------------- include/net/netns/ieee802154_6lowpan.h | 2 +- include/net/netns/ipv4.h | 2 +- include/net/netns/ipv6.h | 4 ++-- 4 files changed, 19 insertions(+), 18 deletions(-) (limited to 'include') diff --git a/include/net/inet_frag.h b/include/net/inet_frag.h index 378904ee9129..b19b1ba44ac5 100644 --- a/include/net/inet_frag.h +++ b/include/net/inet_frag.h @@ -4,7 +4,8 @@ #include -struct netns_frags { +/* Per netns frag queues directory */ +struct fqdir { /* sysctls */ long high_thresh; long low_thresh; @@ -64,7 +65,7 @@ struct frag_v6_compare_key { * @meat: length of received fragments so far * @flags: fragment queue flags * @max_size: maximum received fragment size - * @net: namespace that this frag belongs to + * @fqdir: pointer to struct fqdir * @rcu: rcu head for freeing deferall */ struct inet_frag_queue { @@ -84,7 +85,7 @@ struct inet_frag_queue { int meat; __u8 flags; u16 max_size; - struct netns_frags *net; + struct fqdir *fqdir; struct rcu_head rcu; }; @@ -103,16 +104,16 @@ struct inet_frags { int inet_frags_init(struct inet_frags *); void inet_frags_fini(struct inet_frags *); -static inline int inet_frags_init_net(struct netns_frags *nf) +static inline int inet_frags_init_net(struct fqdir *fqdir) { - atomic_long_set(&nf->mem, 0); - return rhashtable_init(&nf->rhashtable, &nf->f->rhash_params); + atomic_long_set(&fqdir->mem, 0); + return rhashtable_init(&fqdir->rhashtable, &fqdir->f->rhash_params); } -void inet_frags_exit_net(struct netns_frags *nf); +void inet_frags_exit_net(struct fqdir *fqdir); void inet_frag_kill(struct inet_frag_queue *q); void inet_frag_destroy(struct inet_frag_queue *q); -struct inet_frag_queue *inet_frag_find(struct netns_frags *nf, void *key); +struct inet_frag_queue *inet_frag_find(struct fqdir *fqdir, void *key); /* Free all skbs in the queue; return the sum of their truesizes. */ unsigned int inet_frag_rbtree_purge(struct rb_root *root); @@ -125,19 +126,19 @@ static inline void inet_frag_put(struct inet_frag_queue *q) /* Memory Tracking Functions. */ -static inline long frag_mem_limit(const struct netns_frags *nf) +static inline long frag_mem_limit(const struct fqdir *fqdir) { - return atomic_long_read(&nf->mem); + return atomic_long_read(&fqdir->mem); } -static inline void sub_frag_mem_limit(struct netns_frags *nf, long val) +static inline void sub_frag_mem_limit(struct fqdir *fqdir, long val) { - atomic_long_sub(val, &nf->mem); + atomic_long_sub(val, &fqdir->mem); } -static inline void add_frag_mem_limit(struct netns_frags *nf, long val) +static inline void add_frag_mem_limit(struct fqdir *fqdir, long val) { - atomic_long_add(val, &nf->mem); + atomic_long_add(val, &fqdir->mem); } /* RFC 3168 support : diff --git a/include/net/netns/ieee802154_6lowpan.h b/include/net/netns/ieee802154_6lowpan.h index 736aeac52f56..48897cbcb538 100644 --- a/include/net/netns/ieee802154_6lowpan.h +++ b/include/net/netns/ieee802154_6lowpan.h @@ -16,7 +16,7 @@ struct netns_sysctl_lowpan { struct netns_ieee802154_lowpan { struct netns_sysctl_lowpan sysctl; - struct netns_frags frags; + struct fqdir frags; }; #endif diff --git a/include/net/netns/ipv4.h b/include/net/netns/ipv4.h index 7698460a3dd1..22f712141962 100644 --- a/include/net/netns/ipv4.h +++ b/include/net/netns/ipv4.h @@ -72,7 +72,7 @@ struct netns_ipv4 { struct inet_peer_base *peers; struct sock * __percpu *tcp_sk; - struct netns_frags frags; + struct fqdir frags; #ifdef CONFIG_NETFILTER struct xt_table *iptable_filter; struct xt_table *iptable_mangle; diff --git a/include/net/netns/ipv6.h b/include/net/netns/ipv6.h index 5e61b5a8635d..a22e8702d828 100644 --- a/include/net/netns/ipv6.h +++ b/include/net/netns/ipv6.h @@ -58,7 +58,7 @@ struct netns_ipv6 { struct ipv6_devconf *devconf_all; struct ipv6_devconf *devconf_dflt; struct inet_peer_base *peers; - struct netns_frags frags; + struct fqdir frags; #ifdef CONFIG_NETFILTER struct xt_table *ip6table_filter; struct xt_table *ip6table_mangle; @@ -116,7 +116,7 @@ struct netns_ipv6 { #if IS_ENABLED(CONFIG_NF_DEFRAG_IPV6) struct netns_nf_frag { - struct netns_frags frags; + struct fqdir frags; }; #endif -- cgit v1.2.3 From 89fb900514d1623cf6019848f39d0557a3d31890 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Fri, 24 May 2019 09:03:31 -0700 Subject: net: rename inet_frags_exit_net() to fqdir_exit() Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- include/net/inet_frag.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/net/inet_frag.h b/include/net/inet_frag.h index b19b1ba44ac5..d1bfd5dbe2d4 100644 --- a/include/net/inet_frag.h +++ b/include/net/inet_frag.h @@ -109,7 +109,7 @@ static inline int inet_frags_init_net(struct fqdir *fqdir) atomic_long_set(&fqdir->mem, 0); return rhashtable_init(&fqdir->rhashtable, &fqdir->f->rhash_params); } -void inet_frags_exit_net(struct fqdir *fqdir); +void fqdir_exit(struct fqdir *fqdir); void inet_frag_kill(struct inet_frag_queue *q); void inet_frag_destroy(struct inet_frag_queue *q); -- cgit v1.2.3 From 803fdd99684714b3cdcbed4364473d41abbd6afe Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Fri, 24 May 2019 09:03:32 -0700 Subject: net: rename struct fqdir fields Rename the @frags fields from structs netns_ipv4, netns_ipv6, netns_nf_frag and netns_ieee802154_lowpan to @fqdir Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- include/net/netns/ieee802154_6lowpan.h | 2 +- include/net/netns/ipv4.h | 2 +- include/net/netns/ipv6.h | 4 ++-- 3 files changed, 4 insertions(+), 4 deletions(-) (limited to 'include') diff --git a/include/net/netns/ieee802154_6lowpan.h b/include/net/netns/ieee802154_6lowpan.h index 48897cbcb538..d27ac64f8dfe 100644 --- a/include/net/netns/ieee802154_6lowpan.h +++ b/include/net/netns/ieee802154_6lowpan.h @@ -16,7 +16,7 @@ struct netns_sysctl_lowpan { struct netns_ieee802154_lowpan { struct netns_sysctl_lowpan sysctl; - struct fqdir frags; + struct fqdir fqdir; }; #endif diff --git a/include/net/netns/ipv4.h b/include/net/netns/ipv4.h index 22f712141962..3c270baa32e0 100644 --- a/include/net/netns/ipv4.h +++ b/include/net/netns/ipv4.h @@ -72,7 +72,7 @@ struct netns_ipv4 { struct inet_peer_base *peers; struct sock * __percpu *tcp_sk; - struct fqdir frags; + struct fqdir fqdir; #ifdef CONFIG_NETFILTER struct xt_table *iptable_filter; struct xt_table *iptable_mangle; diff --git a/include/net/netns/ipv6.h b/include/net/netns/ipv6.h index a22e8702d828..3dd2ae2a38e2 100644 --- a/include/net/netns/ipv6.h +++ b/include/net/netns/ipv6.h @@ -58,7 +58,7 @@ struct netns_ipv6 { struct ipv6_devconf *devconf_all; struct ipv6_devconf *devconf_dflt; struct inet_peer_base *peers; - struct fqdir frags; + struct fqdir fqdir; #ifdef CONFIG_NETFILTER struct xt_table *ip6table_filter; struct xt_table *ip6table_mangle; @@ -116,7 +116,7 @@ struct netns_ipv6 { #if IS_ENABLED(CONFIG_NF_DEFRAG_IPV6) struct netns_nf_frag { - struct fqdir frags; + struct fqdir fqdir; }; #endif -- cgit v1.2.3 From 9cce45f22ceedf639cbb5fb5dfe612a278d36b58 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Fri, 24 May 2019 09:03:37 -0700 Subject: net: rename inet_frags_init_net() to fdir_init() And pass an extra parameter, since we will soon dynamically allocate fqdir structures. Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- include/net/inet_frag.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/net/inet_frag.h b/include/net/inet_frag.h index d1bfd5dbe2d4..fca246b0abd8 100644 --- a/include/net/inet_frag.h +++ b/include/net/inet_frag.h @@ -104,8 +104,9 @@ struct inet_frags { int inet_frags_init(struct inet_frags *); void inet_frags_fini(struct inet_frags *); -static inline int inet_frags_init_net(struct fqdir *fqdir) +static inline int fqdir_init(struct fqdir *fqdir, struct inet_frags *f) { + fqdir->f = f; atomic_long_set(&fqdir->mem, 0); return rhashtable_init(&fqdir->rhashtable, &fqdir->f->rhash_params); } -- cgit v1.2.3 From a39aca678a0626941aa99c18c1c452ca758e7865 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Fri, 24 May 2019 09:03:38 -0700 Subject: net: add a net pointer to struct fqdir fqdir will soon be dynamically allocated. We need to reach the struct net pointer from fqdir, so add it, and replace the various container_of() constructs by direct access to the new field. Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- include/net/inet_frag.h | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/net/inet_frag.h b/include/net/inet_frag.h index fca246b0abd8..37cde5c1498c 100644 --- a/include/net/inet_frag.h +++ b/include/net/inet_frag.h @@ -12,6 +12,7 @@ struct fqdir { int timeout; int max_dist; struct inet_frags *f; + struct net *net; struct rhashtable rhashtable ____cacheline_aligned_in_smp; @@ -104,9 +105,11 @@ struct inet_frags { int inet_frags_init(struct inet_frags *); void inet_frags_fini(struct inet_frags *); -static inline int fqdir_init(struct fqdir *fqdir, struct inet_frags *f) +static inline int fqdir_init(struct fqdir *fqdir, struct inet_frags *f, + struct net *net) { fqdir->f = f; + fqdir->net = net; atomic_long_set(&fqdir->mem, 0); return rhashtable_init(&fqdir->rhashtable, &fqdir->f->rhash_params); } -- cgit v1.2.3 From 4907abc605e328d61bee56e4e89db4f56ade2090 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Fri, 24 May 2019 09:03:39 -0700 Subject: net: dynamically allocate fqdir structures Following patch will add rcu grace period before fqdir rhashtable destruction, so we need to dynamically allocate fqdir structures to not force expensive synchronize_rcu() calls in netns dismantle path. Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- include/net/inet_frag.h | 17 ++++++++++++++--- include/net/netns/ieee802154_6lowpan.h | 2 +- include/net/netns/ipv4.h | 2 +- include/net/netns/ipv6.h | 4 ++-- 4 files changed, 18 insertions(+), 7 deletions(-) (limited to 'include') diff --git a/include/net/inet_frag.h b/include/net/inet_frag.h index 37cde5c1498c..5f754c660cfa 100644 --- a/include/net/inet_frag.h +++ b/include/net/inet_frag.h @@ -105,14 +105,25 @@ struct inet_frags { int inet_frags_init(struct inet_frags *); void inet_frags_fini(struct inet_frags *); -static inline int fqdir_init(struct fqdir *fqdir, struct inet_frags *f, +static inline int fqdir_init(struct fqdir **fqdirp, struct inet_frags *f, struct net *net) { + struct fqdir *fqdir = kzalloc(sizeof(*fqdir), GFP_KERNEL); + int res; + + if (!fqdir) + return -ENOMEM; fqdir->f = f; fqdir->net = net; - atomic_long_set(&fqdir->mem, 0); - return rhashtable_init(&fqdir->rhashtable, &fqdir->f->rhash_params); + res = rhashtable_init(&fqdir->rhashtable, &fqdir->f->rhash_params); + if (res < 0) { + kfree(fqdir); + return res; + } + *fqdirp = fqdir; + return 0; } + void fqdir_exit(struct fqdir *fqdir); void inet_frag_kill(struct inet_frag_queue *q); diff --git a/include/net/netns/ieee802154_6lowpan.h b/include/net/netns/ieee802154_6lowpan.h index d27ac64f8dfe..95406e1342cb 100644 --- a/include/net/netns/ieee802154_6lowpan.h +++ b/include/net/netns/ieee802154_6lowpan.h @@ -16,7 +16,7 @@ struct netns_sysctl_lowpan { struct netns_ieee802154_lowpan { struct netns_sysctl_lowpan sysctl; - struct fqdir fqdir; + struct fqdir *fqdir; }; #endif diff --git a/include/net/netns/ipv4.h b/include/net/netns/ipv4.h index 3c270baa32e0..c07cee1e0c9e 100644 --- a/include/net/netns/ipv4.h +++ b/include/net/netns/ipv4.h @@ -72,7 +72,7 @@ struct netns_ipv4 { struct inet_peer_base *peers; struct sock * __percpu *tcp_sk; - struct fqdir fqdir; + struct fqdir *fqdir; #ifdef CONFIG_NETFILTER struct xt_table *iptable_filter; struct xt_table *iptable_mangle; diff --git a/include/net/netns/ipv6.h b/include/net/netns/ipv6.h index 3dd2ae2a38e2..022a0fd1a5a4 100644 --- a/include/net/netns/ipv6.h +++ b/include/net/netns/ipv6.h @@ -58,7 +58,7 @@ struct netns_ipv6 { struct ipv6_devconf *devconf_all; struct ipv6_devconf *devconf_dflt; struct inet_peer_base *peers; - struct fqdir fqdir; + struct fqdir *fqdir; #ifdef CONFIG_NETFILTER struct xt_table *ip6table_filter; struct xt_table *ip6table_mangle; @@ -116,7 +116,7 @@ struct netns_ipv6 { #if IS_ENABLED(CONFIG_NF_DEFRAG_IPV6) struct netns_nf_frag { - struct fqdir fqdir; + struct fqdir *fqdir; }; #endif -- cgit v1.2.3 From 3c8fc87820446ce5b948dc17648509340102b818 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Fri, 24 May 2019 09:03:40 -0700 Subject: inet: frags: rework rhashtable dismantle syszbot found an interesting use-after-free [1] happening while IPv4 fragment rhashtable was destroyed at netns dismantle. While no insertions can possibly happen at the time a dismantling netns is destroying this rhashtable, timers can still fire and attempt to remove elements from this rhashtable. This is forbidden, since rhashtable_free_and_destroy() has no synchronization against concurrent inserts and deletes. Add a new fqdir->dead flag so that timers do not attempt a rhashtable_remove_fast() operation. We also have to respect an RCU grace period before starting the rhashtable_free_and_destroy() from process context, thus we use rcu_work infrastructure. This is a refinement of a prior rough attempt to fix this bug : https://marc.info/?l=linux-netdev&m=153845936820900&w=2 Since the rhashtable cleanup is now deferred to a work queue, netns dismantles should be slightly faster. [1] BUG: KASAN: use-after-free in __read_once_size include/linux/compiler.h:194 [inline] BUG: KASAN: use-after-free in rhashtable_last_table+0x162/0x180 lib/rhashtable.c:212 Read of size 8 at addr ffff8880a6497b70 by task kworker/0:0/5 CPU: 0 PID: 5 Comm: kworker/0:0 Not tainted 5.2.0-rc1+ #2 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011 Workqueue: events rht_deferred_worker Call Trace: __dump_stack lib/dump_stack.c:77 [inline] dump_stack+0x172/0x1f0 lib/dump_stack.c:113 print_address_description.cold+0x7c/0x20d mm/kasan/report.c:188 __kasan_report.cold+0x1b/0x40 mm/kasan/report.c:317 kasan_report+0x12/0x20 mm/kasan/common.c:614 __asan_report_load8_noabort+0x14/0x20 mm/kasan/generic_report.c:132 __read_once_size include/linux/compiler.h:194 [inline] rhashtable_last_table+0x162/0x180 lib/rhashtable.c:212 rht_deferred_worker+0x111/0x2030 lib/rhashtable.c:411 process_one_work+0x989/0x1790 kernel/workqueue.c:2269 worker_thread+0x98/0xe40 kernel/workqueue.c:2415 kthread+0x354/0x420 kernel/kthread.c:255 ret_from_fork+0x24/0x30 arch/x86/entry/entry_64.S:352 Allocated by task 32687: save_stack+0x23/0x90 mm/kasan/common.c:71 set_track mm/kasan/common.c:79 [inline] __kasan_kmalloc mm/kasan/common.c:489 [inline] __kasan_kmalloc.constprop.0+0xcf/0xe0 mm/kasan/common.c:462 kasan_kmalloc+0x9/0x10 mm/kasan/common.c:503 __do_kmalloc_node mm/slab.c:3620 [inline] __kmalloc_node+0x4e/0x70 mm/slab.c:3627 kmalloc_node include/linux/slab.h:590 [inline] kvmalloc_node+0x68/0x100 mm/util.c:431 kvmalloc include/linux/mm.h:637 [inline] kvzalloc include/linux/mm.h:645 [inline] bucket_table_alloc+0x90/0x480 lib/rhashtable.c:178 rhashtable_init+0x3f4/0x7b0 lib/rhashtable.c:1057 inet_frags_init_net include/net/inet_frag.h:109 [inline] ipv4_frags_init_net+0x182/0x410 net/ipv4/ip_fragment.c:683 ops_init+0xb3/0x410 net/core/net_namespace.c:130 setup_net+0x2d3/0x740 net/core/net_namespace.c:316 copy_net_ns+0x1df/0x340 net/core/net_namespace.c:439 create_new_namespaces+0x400/0x7b0 kernel/nsproxy.c:107 unshare_nsproxy_namespaces+0xc2/0x200 kernel/nsproxy.c:206 ksys_unshare+0x440/0x980 kernel/fork.c:2692 __do_sys_unshare kernel/fork.c:2760 [inline] __se_sys_unshare kernel/fork.c:2758 [inline] __x64_sys_unshare+0x31/0x40 kernel/fork.c:2758 do_syscall_64+0xfd/0x680 arch/x86/entry/common.c:301 entry_SYSCALL_64_after_hwframe+0x49/0xbe Freed by task 7: save_stack+0x23/0x90 mm/kasan/common.c:71 set_track mm/kasan/common.c:79 [inline] __kasan_slab_free+0x102/0x150 mm/kasan/common.c:451 kasan_slab_free+0xe/0x10 mm/kasan/common.c:459 __cache_free mm/slab.c:3432 [inline] kfree+0xcf/0x220 mm/slab.c:3755 kvfree+0x61/0x70 mm/util.c:460 bucket_table_free+0x69/0x150 lib/rhashtable.c:108 rhashtable_free_and_destroy+0x165/0x8b0 lib/rhashtable.c:1155 inet_frags_exit_net+0x3d/0x50 net/ipv4/inet_fragment.c:152 ipv4_frags_exit_net+0x73/0x90 net/ipv4/ip_fragment.c:695 ops_exit_list.isra.0+0xaa/0x150 net/core/net_namespace.c:154 cleanup_net+0x3fb/0x960 net/core/net_namespace.c:553 process_one_work+0x989/0x1790 kernel/workqueue.c:2269 worker_thread+0x98/0xe40 kernel/workqueue.c:2415 kthread+0x354/0x420 kernel/kthread.c:255 ret_from_fork+0x24/0x30 arch/x86/entry/entry_64.S:352 The buggy address belongs to the object at ffff8880a6497b40 which belongs to the cache kmalloc-1k of size 1024 The buggy address is located 48 bytes inside of 1024-byte region [ffff8880a6497b40, ffff8880a6497f40) The buggy address belongs to the page: page:ffffea0002992580 refcount:1 mapcount:0 mapping:ffff8880aa400ac0 index:0xffff8880a64964c0 compound_mapcount: 0 flags: 0x1fffc0000010200(slab|head) raw: 01fffc0000010200 ffffea0002916e88 ffffea000218fe08 ffff8880aa400ac0 raw: ffff8880a64964c0 ffff8880a6496040 0000000100000005 0000000000000000 page dumped because: kasan: bad access detected Memory state around the buggy address: ffff8880a6497a00: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb ffff8880a6497a80: fb fb fb fb fb fb fb fb fc fc fc fc fc fc fc fc >ffff8880a6497b00: fc fc fc fc fc fc fc fc fb fb fb fb fb fb fb fb ^ ffff8880a6497b80: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb ffff8880a6497c00: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb Fixes: 648700f76b03 ("inet: frags: use rhashtables for reassembly units") Signed-off-by: Eric Dumazet Reported-by: syzbot Signed-off-by: David S. Miller --- include/net/inet_frag.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include') diff --git a/include/net/inet_frag.h b/include/net/inet_frag.h index 5f754c660cfa..002f23c1a1a7 100644 --- a/include/net/inet_frag.h +++ b/include/net/inet_frag.h @@ -13,11 +13,13 @@ struct fqdir { int max_dist; struct inet_frags *f; struct net *net; + bool dead; struct rhashtable rhashtable ____cacheline_aligned_in_smp; /* Keep atomic mem on separate cachelines in structs that include it */ atomic_long_t mem ____cacheline_aligned_in_smp; + struct rcu_work destroy_rwork; }; /** @@ -26,11 +28,13 @@ struct fqdir { * @INET_FRAG_FIRST_IN: first fragment has arrived * @INET_FRAG_LAST_IN: final fragment has arrived * @INET_FRAG_COMPLETE: frag queue has been processed and is due for destruction + * @INET_FRAG_HASH_DEAD: inet_frag_kill() has not removed fq from rhashtable */ enum { INET_FRAG_FIRST_IN = BIT(0), INET_FRAG_LAST_IN = BIT(1), INET_FRAG_COMPLETE = BIT(2), + INET_FRAG_HASH_DEAD = BIT(3), }; struct frag_v4_compare_key { -- cgit v1.2.3 From a3ce17d1495b65d62fceb2c7a704bb97133c5de9 Mon Sep 17 00:00:00 2001 From: Chaitanya Tata Date: Wed, 1 May 2019 18:25:24 +0530 Subject: cfg80211: Handle bss expiry during connection If the BSS is expired during connection, the connect result will trigger a kernel warning. Ideally cfg80211 should hold the BSS before the connection is attempted, but as the BSSID is not known in case of auth/assoc MLME offload (connect op) it doesn't. For those drivers without the connect op cfg80211 holds down the reference so it wil not be removed from list. Fix this by removing the warning and silently adding the BSS back to the bss list which is return by the driver (with proper BSSID set) or in case the BSS is already added use that. The requirements for drivers are documented in the API's. Signed-off-by: Chaitanya Tata [formatting fixes, keep old timestamp] Signed-off-by: Johannes Berg --- include/net/cfg80211.h | 15 +++++++++++---- 1 file changed, 11 insertions(+), 4 deletions(-) (limited to 'include') diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h index 87dae868707e..c19687833493 100644 --- a/include/net/cfg80211.h +++ b/include/net/cfg80211.h @@ -6231,8 +6231,11 @@ struct cfg80211_fils_resp_params { * case. * @bssid: The BSSID of the AP (may be %NULL) * @bss: Entry of bss to which STA got connected to, can be obtained through - * cfg80211_get_bss() (may be %NULL). Only one parameter among @bssid and - * @bss needs to be specified. + * cfg80211_get_bss() (may be %NULL). But it is recommended to store the + * bss from the connect_request and hold a reference to it and return + * through this param to avoid a warning if the bss is expired during the + * connection, esp. for those drivers implementing connect op. + * Only one parameter among @bssid and @bss needs to be specified. * @req_ie: Association request IEs (may be %NULL) * @req_ie_len: Association request IEs length * @resp_ie: Association response IEs (may be %NULL) @@ -6280,8 +6283,12 @@ void cfg80211_connect_done(struct net_device *dev, * * @dev: network device * @bssid: the BSSID of the AP - * @bss: entry of bss to which STA got connected to, can be obtained - * through cfg80211_get_bss (may be %NULL) + * @bss: Entry of bss to which STA got connected to, can be obtained through + * cfg80211_get_bss() (may be %NULL). But it is recommended to store the + * bss from the connect_request and hold a reference to it and return + * through this param to avoid a warning if the bss is expired during the + * connection, esp. for those drivers implementing connect op. + * Only one parameter among @bssid and @bss needs to be specified. * @req_ie: association request IEs (maybe be %NULL) * @req_ie_len: association request IEs length * @resp_ie: association response IEs (may be %NULL) -- cgit v1.2.3 From 4bfc0bb2c60e2f4cc8eb60f03cf8dfa72336272a Mon Sep 17 00:00:00 2001 From: Roman Gushchin Date: Sat, 25 May 2019 09:37:39 -0700 Subject: bpf: decouple the lifetime of cgroup_bpf from cgroup itself Currently the lifetime of bpf programs attached to a cgroup is bound to the lifetime of the cgroup itself. It means that if a user forgets (or intentionally avoids) to detach a bpf program before removing the cgroup, it will stay attached up to the release of the cgroup. Since the cgroup can stay in the dying state (the state between being rmdir()'ed and being released) for a very long time, it leads to a waste of memory. Also, it blocks a possibility to implement the memcg-based memory accounting for bpf objects, because a circular reference dependency will occur. Charged memory pages are pinning the corresponding memory cgroup, and if the memory cgroup is pinning the attached bpf program, nothing will be ever released. A dying cgroup can not contain any processes, so the only chance for an attached bpf program to be executed is a live socket associated with the cgroup. So in order to release all bpf data early, let's count associated sockets using a new percpu refcounter. On cgroup removal the counter is transitioned to the atomic mode, and as soon as it reaches 0, all bpf programs are detached. Because cgroup_bpf_release() can block, it can't be called from the percpu ref counter callback directly, so instead an asynchronous work is scheduled. The reference counter is not socket specific, and can be used for any other types of programs, which can be executed from a cgroup-bpf hook outside of the process context, had such a need arise in the future. Signed-off-by: Roman Gushchin Cc: jolsa@redhat.com Signed-off-by: Alexei Starovoitov --- include/linux/bpf-cgroup.h | 11 +++++++++-- include/linux/cgroup.h | 18 ++++++++++++++++++ 2 files changed, 27 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/bpf-cgroup.h b/include/linux/bpf-cgroup.h index cb3c6b3b89c8..9f100fc422c3 100644 --- a/include/linux/bpf-cgroup.h +++ b/include/linux/bpf-cgroup.h @@ -6,6 +6,7 @@ #include #include #include +#include #include #include @@ -72,10 +73,16 @@ struct cgroup_bpf { /* temp storage for effective prog array used by prog_attach/detach */ struct bpf_prog_array __rcu *inactive; + + /* reference counter used to detach bpf programs after cgroup removal */ + struct percpu_ref refcnt; + + /* cgroup_bpf is released using a work queue */ + struct work_struct release_work; }; -void cgroup_bpf_put(struct cgroup *cgrp); int cgroup_bpf_inherit(struct cgroup *cgrp); +void cgroup_bpf_offline(struct cgroup *cgrp); int __cgroup_bpf_attach(struct cgroup *cgrp, struct bpf_prog *prog, enum bpf_attach_type type, u32 flags); @@ -283,8 +290,8 @@ int cgroup_bpf_prog_query(const union bpf_attr *attr, struct bpf_prog; struct cgroup_bpf {}; -static inline void cgroup_bpf_put(struct cgroup *cgrp) {} static inline int cgroup_bpf_inherit(struct cgroup *cgrp) { return 0; } +static inline void cgroup_bpf_offline(struct cgroup *cgrp) {} static inline int cgroup_bpf_prog_attach(const union bpf_attr *attr, enum bpf_prog_type ptype, diff --git a/include/linux/cgroup.h b/include/linux/cgroup.h index c0077adeea83..49e8facf7c4a 100644 --- a/include/linux/cgroup.h +++ b/include/linux/cgroup.h @@ -924,4 +924,22 @@ static inline bool cgroup_task_frozen(struct task_struct *task) #endif /* !CONFIG_CGROUPS */ +#ifdef CONFIG_CGROUP_BPF +static inline void cgroup_bpf_get(struct cgroup *cgrp) +{ + percpu_ref_get(&cgrp->bpf.refcnt); +} + +static inline void cgroup_bpf_put(struct cgroup *cgrp) +{ + percpu_ref_put(&cgrp->bpf.refcnt); +} + +#else /* CONFIG_CGROUP_BPF */ + +static inline void cgroup_bpf_get(struct cgroup *cgrp) {} +static inline void cgroup_bpf_put(struct cgroup *cgrp) {} + +#endif /* CONFIG_CGROUP_BPF */ + #endif /* _LINUX_CGROUP_H */ -- cgit v1.2.3 From 6b73d19711d0989cbdcd19c61faa0f79a1a5e466 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Mon, 27 May 2019 16:56:47 -0700 Subject: inet: frags: uninline fqdir_init() fqdir_init() is not fast path and is getting bigger. Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- include/net/inet_frag.h | 20 +------------------- 1 file changed, 1 insertion(+), 19 deletions(-) (limited to 'include') diff --git a/include/net/inet_frag.h b/include/net/inet_frag.h index 002f23c1a1a7..94092b1ef22e 100644 --- a/include/net/inet_frag.h +++ b/include/net/inet_frag.h @@ -109,25 +109,7 @@ struct inet_frags { int inet_frags_init(struct inet_frags *); void inet_frags_fini(struct inet_frags *); -static inline int fqdir_init(struct fqdir **fqdirp, struct inet_frags *f, - struct net *net) -{ - struct fqdir *fqdir = kzalloc(sizeof(*fqdir), GFP_KERNEL); - int res; - - if (!fqdir) - return -ENOMEM; - fqdir->f = f; - fqdir->net = net; - res = rhashtable_init(&fqdir->rhashtable, &fqdir->f->rhash_params); - if (res < 0) { - kfree(fqdir); - return res; - } - *fqdirp = fqdir; - return 0; -} - +int fqdir_init(struct fqdir **fqdirp, struct inet_frags *f, struct net *net); void fqdir_exit(struct fqdir *fqdir); void inet_frag_kill(struct inet_frag_queue *q); -- cgit v1.2.3 From dc93f46bc4e00899eaf4579962cfac8cf2f9966d Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Mon, 27 May 2019 16:56:49 -0700 Subject: inet: frags: fix use-after-free read in inet_frag_destroy_rcu As caught by syzbot [1], the rcu grace period that is respected before fqdir_rwork_fn() proceeds and frees fqdir is not enough to prevent inet_frag_destroy_rcu() being run after the freeing. We need a proper rcu_barrier() synchronization to replace the one we had in inet_frags_fini() We also have to fix a potential problem at module removal : inet_frags_fini() needs to make sure that all queued work queues (fqdir_rwork_fn) have completed, otherwise we might call kmem_cache_destroy() too soon and get another use-after-free. [1] BUG: KASAN: use-after-free in inet_frag_destroy_rcu+0xd9/0xe0 net/ipv4/inet_fragment.c:201 Read of size 8 at addr ffff88806ed47a18 by task swapper/1/0 CPU: 1 PID: 0 Comm: swapper/1 Not tainted 5.2.0-rc1+ #2 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011 Call Trace: __dump_stack lib/dump_stack.c:77 [inline] dump_stack+0x172/0x1f0 lib/dump_stack.c:113 print_address_description.cold+0x7c/0x20d mm/kasan/report.c:188 __kasan_report.cold+0x1b/0x40 mm/kasan/report.c:317 kasan_report+0x12/0x20 mm/kasan/common.c:614 __asan_report_load8_noabort+0x14/0x20 mm/kasan/generic_report.c:132 inet_frag_destroy_rcu+0xd9/0xe0 net/ipv4/inet_fragment.c:201 __rcu_reclaim kernel/rcu/rcu.h:222 [inline] rcu_do_batch kernel/rcu/tree.c:2092 [inline] invoke_rcu_callbacks kernel/rcu/tree.c:2310 [inline] rcu_core+0xba5/0x1500 kernel/rcu/tree.c:2291 __do_softirq+0x25c/0x94c kernel/softirq.c:293 invoke_softirq kernel/softirq.c:374 [inline] irq_exit+0x180/0x1d0 kernel/softirq.c:414 exiting_irq arch/x86/include/asm/apic.h:536 [inline] smp_apic_timer_interrupt+0x13b/0x550 arch/x86/kernel/apic/apic.c:1068 apic_timer_interrupt+0xf/0x20 arch/x86/entry/entry_64.S:806 RIP: 0010:native_safe_halt+0xe/0x10 arch/x86/include/asm/irqflags.h:61 Code: ff ff 48 89 df e8 f2 95 8c fa eb 82 e9 07 00 00 00 0f 00 2d e4 45 4b 00 f4 c3 66 90 e9 07 00 00 00 0f 00 2d d4 45 4b 00 fb f4 90 55 48 89 e5 41 57 41 56 41 55 41 54 53 e8 8e 18 42 fa e8 99 RSP: 0018:ffff8880a98e7d78 EFLAGS: 00000282 ORIG_RAX: ffffffffffffff13 RAX: 1ffffffff1164e11 RBX: ffff8880a98d4340 RCX: 0000000000000000 RDX: dffffc0000000000 RSI: 0000000000000006 RDI: ffff8880a98d4bbc RBP: ffff8880a98e7da8 R08: ffff8880a98d4340 R09: 0000000000000000 R10: 0000000000000000 R11: 0000000000000000 R12: 0000000000000001 R13: ffffffff88b27078 R14: 0000000000000001 R15: 0000000000000000 arch_cpu_idle+0xa/0x10 arch/x86/kernel/process.c:571 default_idle_call+0x36/0x90 kernel/sched/idle.c:94 cpuidle_idle_call kernel/sched/idle.c:154 [inline] do_idle+0x377/0x560 kernel/sched/idle.c:263 cpu_startup_entry+0x1b/0x20 kernel/sched/idle.c:354 start_secondary+0x34e/0x4c0 arch/x86/kernel/smpboot.c:267 secondary_startup_64+0xa4/0xb0 arch/x86/kernel/head_64.S:243 Allocated by task 8877: save_stack+0x23/0x90 mm/kasan/common.c:71 set_track mm/kasan/common.c:79 [inline] __kasan_kmalloc mm/kasan/common.c:489 [inline] __kasan_kmalloc.constprop.0+0xcf/0xe0 mm/kasan/common.c:462 kasan_kmalloc+0x9/0x10 mm/kasan/common.c:503 kmem_cache_alloc_trace+0x151/0x750 mm/slab.c:3555 kmalloc include/linux/slab.h:547 [inline] kzalloc include/linux/slab.h:742 [inline] fqdir_init include/net/inet_frag.h:115 [inline] ipv6_frags_init_net+0x48/0x460 net/ipv6/reassembly.c:513 ops_init+0xb3/0x410 net/core/net_namespace.c:130 setup_net+0x2d3/0x740 net/core/net_namespace.c:316 copy_net_ns+0x1df/0x340 net/core/net_namespace.c:439 create_new_namespaces+0x400/0x7b0 kernel/nsproxy.c:107 unshare_nsproxy_namespaces+0xc2/0x200 kernel/nsproxy.c:206 ksys_unshare+0x440/0x980 kernel/fork.c:2692 __do_sys_unshare kernel/fork.c:2760 [inline] __se_sys_unshare kernel/fork.c:2758 [inline] __x64_sys_unshare+0x31/0x40 kernel/fork.c:2758 do_syscall_64+0xfd/0x680 arch/x86/entry/common.c:301 entry_SYSCALL_64_after_hwframe+0x49/0xbe Freed by task 17: save_stack+0x23/0x90 mm/kasan/common.c:71 set_track mm/kasan/common.c:79 [inline] __kasan_slab_free+0x102/0x150 mm/kasan/common.c:451 kasan_slab_free+0xe/0x10 mm/kasan/common.c:459 __cache_free mm/slab.c:3432 [inline] kfree+0xcf/0x220 mm/slab.c:3755 fqdir_rwork_fn+0x33/0x40 net/ipv4/inet_fragment.c:154 process_one_work+0x989/0x1790 kernel/workqueue.c:2269 worker_thread+0x98/0xe40 kernel/workqueue.c:2415 kthread+0x354/0x420 kernel/kthread.c:255 ret_from_fork+0x24/0x30 arch/x86/entry/entry_64.S:352 The buggy address belongs to the object at ffff88806ed47a00 which belongs to the cache kmalloc-512 of size 512 The buggy address is located 24 bytes inside of 512-byte region [ffff88806ed47a00, ffff88806ed47c00) The buggy address belongs to the page: page:ffffea0001bb51c0 refcount:1 mapcount:0 mapping:ffff8880aa400940 index:0x0 flags: 0x1fffc0000000200(slab) raw: 01fffc0000000200 ffffea000282a788 ffffea0001bb53c8 ffff8880aa400940 raw: 0000000000000000 ffff88806ed47000 0000000100000006 0000000000000000 page dumped because: kasan: bad access detected Memory state around the buggy address: ffff88806ed47900: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb ffff88806ed47980: fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc >ffff88806ed47a00: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb ^ ffff88806ed47a80: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb ffff88806ed47b00: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb Fixes: 3c8fc8782044 ("inet: frags: rework rhashtable dismantle") Signed-off-by: Eric Dumazet Reported-by: syzbot Signed-off-by: David S. Miller --- include/net/inet_frag.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include') diff --git a/include/net/inet_frag.h b/include/net/inet_frag.h index 94092b1ef22e..e91b79ad4e4a 100644 --- a/include/net/inet_frag.h +++ b/include/net/inet_frag.h @@ -3,6 +3,7 @@ #define __NET_FRAG_H__ #include +#include /* Per netns frag queues directory */ struct fqdir { @@ -104,6 +105,8 @@ struct inet_frags { struct kmem_cache *frags_cachep; const char *frags_cache_name; struct rhashtable_params rhash_params; + refcount_t refcnt; + struct completion completion; }; int inet_frags_init(struct inet_frags *); -- cgit v1.2.3 From 65ee00a9409f751188a8cdc0988167858eb4a536 Mon Sep 17 00:00:00 2001 From: David Ahern Date: Fri, 24 May 2019 14:43:03 -0700 Subject: net: nexthop uapi New UAPI for nexthops as standalone objects: - defines netlink ancillary header, struct nhmsg - RTM commands for nexthop objects, RTM_*NEXTHOP, - RTNLGRP for nexthop notifications, RTNLGRP_NEXTHOP, - Attributes for creating nexthops, NHA_* - Attribute for route specs to specify a nexthop by id, RTA_NH_ID. The nexthop attributes and semantics follow the route and RTA ones for device, gateway and lwt encap. Unique to nexthop objects are a blackhole and a group which contains references to other nexthop objects. With the exception of blackhole and group, nexthop objects MUST contain a device. Gateway and encap are optional. Nexthop groups can only reference other pre-existing nexthops by id. If the NHA_ID attribute is present that id is used for the nexthop. If not specified, one is auto assigned. Dump requests can include attributes: - NHA_GROUPS to return only nexthop groups, - NHA_MASTER to limit dumps to nexthops with devices enslaved to the given master (e.g., VRF) - NHA_OIF to limit dumps to nexthops using given device nlmsg_route_perms in selinux code is updated for the new RTM comands. Signed-off-by: David Ahern Signed-off-by: David S. Miller --- include/uapi/linux/nexthop.h | 56 ++++++++++++++++++++++++++++++++++++++++++ include/uapi/linux/rtnetlink.h | 10 ++++++++ 2 files changed, 66 insertions(+) create mode 100644 include/uapi/linux/nexthop.h (limited to 'include') diff --git a/include/uapi/linux/nexthop.h b/include/uapi/linux/nexthop.h new file mode 100644 index 000000000000..7b61867e9848 --- /dev/null +++ b/include/uapi/linux/nexthop.h @@ -0,0 +1,56 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ +#ifndef _UAPI_LINUX_NEXTHOP_H +#define _UAPI_LINUX_NEXTHOP_H + +#include + +struct nhmsg { + unsigned char nh_family; + unsigned char nh_scope; /* return only */ + unsigned char nh_protocol; /* Routing protocol that installed nh */ + unsigned char resvd; + unsigned int nh_flags; /* RTNH_F flags */ +}; + +/* entry in a nexthop group */ +struct nexthop_grp { + __u32 id; /* nexthop id - must exist */ + __u8 weight; /* weight of this nexthop */ + __u8 resvd1; + __u16 resvd2; +}; + +enum { + NEXTHOP_GRP_TYPE_MPATH, /* default type if not specified */ + __NEXTHOP_GRP_TYPE_MAX, +}; + +#define NEXTHOP_GRP_TYPE_MAX (__NEXTHOP_GRP_TYPE_MAX - 1) + +enum { + NHA_UNSPEC, + NHA_ID, /* u32; id for nexthop. id == 0 means auto-assign */ + + NHA_GROUP, /* array of nexthop_grp */ + NHA_GROUP_TYPE, /* u16 one of NEXTHOP_GRP_TYPE */ + /* if NHA_GROUP attribute is added, no other attributes can be set */ + + NHA_BLACKHOLE, /* flag; nexthop used to blackhole packets */ + /* if NHA_BLACKHOLE is added, OIF, GATEWAY, ENCAP can not be set */ + + NHA_OIF, /* u32; nexthop device */ + NHA_GATEWAY, /* be32 (IPv4) or in6_addr (IPv6) gw address */ + NHA_ENCAP_TYPE, /* u16; lwt encap type */ + NHA_ENCAP, /* lwt encap data */ + + /* NHA_OIF can be appended to dump request to return only + * nexthops using given device + */ + NHA_GROUPS, /* flag; only return nexthop groups in dump */ + NHA_MASTER, /* u32; only return nexthops with given master dev */ + + __NHA_MAX, +}; + +#define NHA_MAX (__NHA_MAX - 1) +#endif diff --git a/include/uapi/linux/rtnetlink.h b/include/uapi/linux/rtnetlink.h index 46399367627f..ce2a623abb75 100644 --- a/include/uapi/linux/rtnetlink.h +++ b/include/uapi/linux/rtnetlink.h @@ -157,6 +157,13 @@ enum { RTM_GETCHAIN, #define RTM_GETCHAIN RTM_GETCHAIN + RTM_NEWNEXTHOP = 104, +#define RTM_NEWNEXTHOP RTM_NEWNEXTHOP + RTM_DELNEXTHOP, +#define RTM_DELNEXTHOP RTM_DELNEXTHOP + RTM_GETNEXTHOP, +#define RTM_GETNEXTHOP RTM_GETNEXTHOP + __RTM_MAX, #define RTM_MAX (((__RTM_MAX + 3) & ~3) - 1) }; @@ -342,6 +349,7 @@ enum rtattr_type_t { RTA_IP_PROTO, RTA_SPORT, RTA_DPORT, + RTA_NH_ID, __RTA_MAX }; @@ -704,6 +712,8 @@ enum rtnetlink_groups { #define RTNLGRP_IPV4_MROUTE_R RTNLGRP_IPV4_MROUTE_R RTNLGRP_IPV6_MROUTE_R, #define RTNLGRP_IPV6_MROUTE_R RTNLGRP_IPV6_MROUTE_R + RTNLGRP_NEXTHOP, +#define RTNLGRP_NEXTHOP RTNLGRP_NEXTHOP __RTNLGRP_MAX }; #define RTNLGRP_MAX (__RTNLGRP_MAX - 1) -- cgit v1.2.3 From ab84be7e54fc3d9b248285f1a14067558d858819 Mon Sep 17 00:00:00 2001 From: David Ahern Date: Fri, 24 May 2019 14:43:04 -0700 Subject: net: Initial nexthop code Barebones start point for nexthops. Implementation for RTM commands, notifications, management of rbtree for holding nexthops by id, and kernel side data structures for nexthops and nexthop config. Nexthops are maintained in an rbtree sorted by id. Similar to routes, nexthops are configured per namespace using netns_nexthop struct added to struct net. Nexthop notifications are sent when a nexthop is added or deleted, but NOT if the delete is due to a device event or network namespace teardown (which also involves device events). Applications are expected to use the device down event to flush nexthops and any routes used by the nexthops. Signed-off-by: David Ahern Signed-off-by: David S. Miller --- include/net/net_namespace.h | 2 ++ include/net/netns/nexthop.h | 18 ++++++++++ include/net/nexthop.h | 88 +++++++++++++++++++++++++++++++++++++++++++++ 3 files changed, 108 insertions(+) create mode 100644 include/net/netns/nexthop.h create mode 100644 include/net/nexthop.h (limited to 'include') diff --git a/include/net/net_namespace.h b/include/net/net_namespace.h index 12689ddfc24c..abb4f92456e1 100644 --- a/include/net/net_namespace.h +++ b/include/net/net_namespace.h @@ -19,6 +19,7 @@ #include #include #include +#include #include #include #include @@ -108,6 +109,7 @@ struct net { struct netns_mib mib; struct netns_packet packet; struct netns_unix unx; + struct netns_nexthop nexthop; struct netns_ipv4 ipv4; #if IS_ENABLED(CONFIG_IPV6) struct netns_ipv6 ipv6; diff --git a/include/net/netns/nexthop.h b/include/net/netns/nexthop.h new file mode 100644 index 000000000000..c712ee5eebd9 --- /dev/null +++ b/include/net/netns/nexthop.h @@ -0,0 +1,18 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * nexthops in net namespaces + */ + +#ifndef __NETNS_NEXTHOP_H__ +#define __NETNS_NEXTHOP_H__ + +#include + +struct netns_nexthop { + struct rb_root rb_root; /* tree of nexthops by id */ + struct hlist_head *devhash; /* nexthops by device */ + + unsigned int seq; /* protected by rtnl_mutex */ + u32 last_id_allocated; +}; +#endif diff --git a/include/net/nexthop.h b/include/net/nexthop.h new file mode 100644 index 000000000000..18e1f512f866 --- /dev/null +++ b/include/net/nexthop.h @@ -0,0 +1,88 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Generic nexthop implementation + * + * Copyright (c) 2017-19 Cumulus Networks + * Copyright (c) 2017-19 David Ahern + */ + +#ifndef __LINUX_NEXTHOP_H +#define __LINUX_NEXTHOP_H + +#include +#include +#include +#include + +#define NEXTHOP_VALID_USER_FLAGS RTNH_F_ONLINK + +struct nexthop; + +struct nh_config { + u32 nh_id; + + u8 nh_family; + u8 nh_protocol; + u8 nh_blackhole; + u32 nh_flags; + + int nh_ifindex; + struct net_device *dev; + + u32 nlflags; + struct nl_info nlinfo; +}; + +struct nh_info { + struct hlist_node dev_hash; /* entry on netns devhash */ + struct nexthop *nh_parent; + + u8 family; + bool reject_nh; + + union { + struct fib_nh_common fib_nhc; + }; +}; + +struct nexthop { + struct rb_node rb_node; /* entry on netns rbtree */ + struct net *net; + + u32 id; + + u8 protocol; /* app managing this nh */ + u8 nh_flags; + + refcount_t refcnt; + struct rcu_head rcu; + + union { + struct nh_info __rcu *nh_info; + }; +}; + +/* caller is holding rcu or rtnl; no reference taken to nexthop */ +struct nexthop *nexthop_find_by_id(struct net *net, u32 id); +void nexthop_free_rcu(struct rcu_head *head); + +static inline bool nexthop_get(struct nexthop *nh) +{ + return refcount_inc_not_zero(&nh->refcnt); +} + +static inline void nexthop_put(struct nexthop *nh) +{ + if (refcount_dec_and_test(&nh->refcnt)) + call_rcu(&nh->rcu, nexthop_free_rcu); +} + +/* called with rcu lock */ +static inline bool nexthop_is_blackhole(const struct nexthop *nh) +{ + const struct nh_info *nhi; + + nhi = rcu_dereference(nh->nh_info); + return nhi->reject_nh; +} +#endif -- cgit v1.2.3 From 597cfe4fc3390a055f42546c254e48601b37009f Mon Sep 17 00:00:00 2001 From: David Ahern Date: Fri, 24 May 2019 14:43:05 -0700 Subject: nexthop: Add support for IPv4 nexthops Add support for IPv4 nexthops. If nh_family is set to AF_INET, then NHA_GATEWAY is expected to be an IPv4 address. Register for netdev events to be notified of admin up/down changes as well as deletes. A hash table is used to track nexthop per devices to quickly convert device events to the affected nexthops. Signed-off-by: David Ahern Signed-off-by: David S. Miller --- include/net/nexthop.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include') diff --git a/include/net/nexthop.h b/include/net/nexthop.h index 18e1f512f866..c0e4b0d92c39 100644 --- a/include/net/nexthop.h +++ b/include/net/nexthop.h @@ -29,6 +29,10 @@ struct nh_config { int nh_ifindex; struct net_device *dev; + union { + __be32 ipv4; + } gw; + u32 nlflags; struct nl_info nlinfo; }; @@ -42,6 +46,7 @@ struct nh_info { union { struct fib_nh_common fib_nhc; + struct fib_nh fib_nh; }; }; -- cgit v1.2.3 From 53010f991a9f5e4ed2db705ddde6ff32709192a2 Mon Sep 17 00:00:00 2001 From: David Ahern Date: Fri, 24 May 2019 14:43:06 -0700 Subject: nexthop: Add support for IPv6 gateways Handle IPv6 gateway in a nexthop spec. If nh_family is set to AF_INET6, NHA_GATEWAY is expected to be an IPv6 address. Add ipv6 option to gw in nh_config to hold the address, add fib6_nh to nh_info to leverage the ipv6 initialization and cleanup code. Update nh_fill_node to dump the v6 address. Signed-off-by: David Ahern Signed-off-by: David S. Miller --- include/net/nexthop.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include') diff --git a/include/net/nexthop.h b/include/net/nexthop.h index c0e4b0d92c39..d188f16c0c4f 100644 --- a/include/net/nexthop.h +++ b/include/net/nexthop.h @@ -12,6 +12,7 @@ #include #include #include +#include #include #define NEXTHOP_VALID_USER_FLAGS RTNH_F_ONLINK @@ -31,6 +32,7 @@ struct nh_config { union { __be32 ipv4; + struct in6_addr ipv6; } gw; u32 nlflags; @@ -47,6 +49,7 @@ struct nh_info { union { struct fib_nh_common fib_nhc; struct fib_nh fib_nh; + struct fib6_nh fib6_nh; }; }; -- cgit v1.2.3 From b513bd035f4044aa2667fb01418918523a049b9c Mon Sep 17 00:00:00 2001 From: David Ahern Date: Fri, 24 May 2019 14:43:07 -0700 Subject: nexthop: Add support for lwt encaps Add support for NHA_ENCAP and NHA_ENCAP_TYPE. Leverages the existing code for lwtunnel within fib_nh_common, so the only change needed is handling the attributes in the nexthop code. Signed-off-by: David Ahern Signed-off-by: David S. Miller --- include/net/nexthop.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include') diff --git a/include/net/nexthop.h b/include/net/nexthop.h index d188f16c0c4f..7cde03337e14 100644 --- a/include/net/nexthop.h +++ b/include/net/nexthop.h @@ -35,6 +35,9 @@ struct nh_config { struct in6_addr ipv6; } gw; + struct nlattr *nh_encap; + u16 nh_encap_type; + u32 nlflags; struct nl_info nlinfo; }; -- cgit v1.2.3 From 430a049190de3c9e219f43084de9f1122da04570 Mon Sep 17 00:00:00 2001 From: David Ahern Date: Fri, 24 May 2019 14:43:08 -0700 Subject: nexthop: Add support for nexthop groups Allow the creation of nexthop groups which reference other nexthop objects to create multipath routes: +--------------+ +------------+ +--------------+ | | nh nh_grp --->| nh_grp_entry |-+ +------------+ +---------|----+ ^ | | +------------+ +----------------+ +--->| nh, weight | nh_parent +------------+ A group entry points to a nexthop with a weight for that hop within the group. The nexthop has a list_head, grp_list, for tracking which groups it is a member of and the group entry has a reference back to the parent. The grp_list is used when a nexthop is deleted - to efficiently remove it from groups using it. If a nexthop group spec is given, no other attributes can be set. Each nexthop id in a group spec must already exist. Similar to single nexthops, the specification of a nexthop group can be updated so that data is managed with rcu locking. Add path selection function to account for multiple paths and add ipv{4,6}_good_nh helpers to know that if a neighbor entry exists it is in a good state. Update NETDEV event handling to rebalance multipath nexthop groups if a nexthop is deleted due to a link event (down or unregister). When a nexthop is removed any groups using it are updated. Groups using a nexthop a tracked via a grp_list. Nexthop dumps can be limited to groups only by adding NHA_GROUPS to the request. Signed-off-by: David Ahern Signed-off-by: David S. Miller --- include/net/nexthop.h | 98 ++++++++++++++++++++++++++++++++++++++++++++++++++- 1 file changed, 97 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/net/nexthop.h b/include/net/nexthop.h index 7cde03337e14..6e1b8f53624c 100644 --- a/include/net/nexthop.h +++ b/include/net/nexthop.h @@ -35,6 +35,9 @@ struct nh_config { struct in6_addr ipv6; } gw; + struct nlattr *nh_grp; + u16 nh_grp_type; + struct nlattr *nh_encap; u16 nh_encap_type; @@ -56,20 +59,39 @@ struct nh_info { }; }; +struct nh_grp_entry { + struct nexthop *nh; + u8 weight; + atomic_t upper_bound; + + struct list_head nh_list; + struct nexthop *nh_parent; /* nexthop of group with this entry */ +}; + +struct nh_group { + u16 num_nh; + bool mpath; + bool has_v4; + struct nh_grp_entry nh_entries[0]; +}; + struct nexthop { struct rb_node rb_node; /* entry on netns rbtree */ + struct list_head grp_list; /* nh group entries using this nh */ struct net *net; u32 id; u8 protocol; /* app managing this nh */ u8 nh_flags; + bool is_group; refcount_t refcnt; struct rcu_head rcu; union { struct nh_info __rcu *nh_info; + struct nh_group __rcu *nh_grp; }; }; @@ -88,12 +110,86 @@ static inline void nexthop_put(struct nexthop *nh) call_rcu(&nh->rcu, nexthop_free_rcu); } +static inline bool nexthop_is_multipath(const struct nexthop *nh) +{ + if (nh->is_group) { + struct nh_group *nh_grp; + + nh_grp = rcu_dereference_rtnl(nh->nh_grp); + return nh_grp->mpath; + } + return false; +} + +struct nexthop *nexthop_select_path(struct nexthop *nh, int hash); + +static inline unsigned int nexthop_num_path(const struct nexthop *nh) +{ + unsigned int rc = 1; + + if (nexthop_is_multipath(nh)) { + struct nh_group *nh_grp; + + nh_grp = rcu_dereference_rtnl(nh->nh_grp); + rc = nh_grp->num_nh; + } else { + const struct nh_info *nhi; + + nhi = rcu_dereference_rtnl(nh->nh_info); + if (nhi->reject_nh) + rc = 0; + } + + return rc; +} + +static inline +struct nexthop *nexthop_mpath_select(const struct nexthop *nh, int nhsel) +{ + const struct nh_group *nhg = rcu_dereference_rtnl(nh->nh_grp); + + /* for_nexthops macros in fib_semantics.c grabs a pointer to + * the nexthop before checking nhsel + */ + if (nhsel > nhg->num_nh) + return NULL; + + return nhg->nh_entries[nhsel].nh; +} + +static inline +int nexthop_mpath_fill_node(struct sk_buff *skb, struct nexthop *nh) +{ + struct nh_group *nhg = rtnl_dereference(nh->nh_grp); + int i; + + for (i = 0; i < nhg->num_nh; i++) { + struct nexthop *nhe = nhg->nh_entries[i].nh; + struct nh_info *nhi = rcu_dereference_rtnl(nhe->nh_info); + struct fib_nh_common *nhc = &nhi->fib_nhc; + int weight = nhg->nh_entries[i].weight; + + if (fib_add_nexthop(skb, nhc, weight) < 0) + return -EMSGSIZE; + } + + return 0; +} + /* called with rcu lock */ static inline bool nexthop_is_blackhole(const struct nexthop *nh) { const struct nh_info *nhi; - nhi = rcu_dereference(nh->nh_info); + if (nexthop_is_multipath(nh)) { + if (nexthop_num_path(nh) > 1) + return false; + nh = nexthop_mpath_select(nh, 0); + if (!nh) + return false; + } + + nhi = rcu_dereference_rtnl(nh->nh_info); return nhi->reject_nh; } #endif -- cgit v1.2.3 From 54e9c9d4b506b611228890752d1cfa960e0965e1 Mon Sep 17 00:00:00 2001 From: Stanislav Fomichev Date: Tue, 28 May 2019 14:14:41 -0700 Subject: bpf: remove __rcu annotations from bpf_prog_array Drop __rcu annotations and rcu read sections from bpf_prog_array helper functions. They are not needed since all existing callers call those helpers from the rcu update side while holding a mutex. This guarantees that use-after-free could not happen. In the next patches I'll fix the callers with missing rcu_dereference_protected to make sparse/lockdep happy, the proper way to use these helpers is: struct bpf_prog_array __rcu *progs = ...; struct bpf_prog_array *p; mutex_lock(&mtx); p = rcu_dereference_protected(progs, lockdep_is_held(&mtx)); bpf_prog_array_length(p); bpf_prog_array_copy_to_user(p, ...); bpf_prog_array_delete_safe(p, ...); bpf_prog_array_copy_info(p, ...); bpf_prog_array_copy(p, ...); bpf_prog_array_free(p); mutex_unlock(&mtx); No functional changes! rcu_dereference_protected with lockdep_is_held should catch any cases where we update prog array without a mutex (I've looked at existing call sites and I think we hold a mutex everywhere). Motivation is to fix sparse warnings: kernel/bpf/core.c:1803:9: warning: incorrect type in argument 1 (different address spaces) kernel/bpf/core.c:1803:9: expected struct callback_head *head kernel/bpf/core.c:1803:9: got struct callback_head [noderef] * kernel/bpf/core.c:1877:44: warning: incorrect type in initializer (different address spaces) kernel/bpf/core.c:1877:44: expected struct bpf_prog_array_item *item kernel/bpf/core.c:1877:44: got struct bpf_prog_array_item [noderef] * kernel/bpf/core.c:1901:26: warning: incorrect type in assignment (different address spaces) kernel/bpf/core.c:1901:26: expected struct bpf_prog_array_item *existing kernel/bpf/core.c:1901:26: got struct bpf_prog_array_item [noderef] * kernel/bpf/core.c:1935:26: warning: incorrect type in assignment (different address spaces) kernel/bpf/core.c:1935:26: expected struct bpf_prog_array_item *[assigned] existing kernel/bpf/core.c:1935:26: got struct bpf_prog_array_item [noderef] * v2: * remove comment about potential race; that can't happen because all callers are in rcu-update section Cc: Roman Gushchin Acked-by: Roman Gushchin Signed-off-by: Stanislav Fomichev Signed-off-by: Daniel Borkmann --- include/linux/bpf.h | 12 ++++++------ 1 file changed, 6 insertions(+), 6 deletions(-) (limited to 'include') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index d98141edb74b..ff3e00ff84d2 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -514,17 +514,17 @@ struct bpf_prog_array { }; struct bpf_prog_array *bpf_prog_array_alloc(u32 prog_cnt, gfp_t flags); -void bpf_prog_array_free(struct bpf_prog_array __rcu *progs); -int bpf_prog_array_length(struct bpf_prog_array __rcu *progs); -int bpf_prog_array_copy_to_user(struct bpf_prog_array __rcu *progs, +void bpf_prog_array_free(struct bpf_prog_array *progs); +int bpf_prog_array_length(struct bpf_prog_array *progs); +int bpf_prog_array_copy_to_user(struct bpf_prog_array *progs, __u32 __user *prog_ids, u32 cnt); -void bpf_prog_array_delete_safe(struct bpf_prog_array __rcu *progs, +void bpf_prog_array_delete_safe(struct bpf_prog_array *progs, struct bpf_prog *old_prog); -int bpf_prog_array_copy_info(struct bpf_prog_array __rcu *array, +int bpf_prog_array_copy_info(struct bpf_prog_array *array, u32 *prog_ids, u32 request_cnt, u32 *prog_cnt); -int bpf_prog_array_copy(struct bpf_prog_array __rcu *old_array, +int bpf_prog_array_copy(struct bpf_prog_array *old_array, struct bpf_prog *exclude_prog, struct bpf_prog *include_prog, struct bpf_prog_array **new_array); -- cgit v1.2.3 From dbcc1ba26e43bd32cb308e50ac4cb4a29d2f5967 Mon Sep 17 00:00:00 2001 From: Stanislav Fomichev Date: Tue, 28 May 2019 14:14:43 -0700 Subject: bpf: cgroup: properly use bpf_prog_array api Now that we don't have __rcu markers on the bpf_prog_array helpers, let's use proper rcu_dereference_protected to obtain array pointer under mutex. We also don't need __rcu annotations on cgroup_bpf.inactive since it's not read/updated concurrently. v4: * drop cgroup_rcu_xyz wrappers and use rcu APIs directly; presumably should be more clear to understand which mutex/refcount protects each particular place v3: * amend cgroup_rcu_dereference to include percpu_ref_is_dying; cgroup_bpf is now reference counted and we don't hold cgroup_mutex anymore in cgroup_bpf_release v2: * replace xchg with rcu_swap_protected Cc: Roman Gushchin Signed-off-by: Stanislav Fomichev Acked-by: Roman Gushchin Signed-off-by: Daniel Borkmann --- include/linux/bpf-cgroup.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/bpf-cgroup.h b/include/linux/bpf-cgroup.h index 9f100fc422c3..b631ee75762d 100644 --- a/include/linux/bpf-cgroup.h +++ b/include/linux/bpf-cgroup.h @@ -72,7 +72,7 @@ struct cgroup_bpf { u32 flags[MAX_BPF_ATTACH_TYPE]; /* temp storage for effective prog array used by prog_attach/detach */ - struct bpf_prog_array __rcu *inactive; + struct bpf_prog_array *inactive; /* reference counter used to detach bpf programs after cgroup removal */ struct percpu_ref refcnt; -- cgit v1.2.3 From 279758f8001f0014b15656a4ef130a20852f6df6 Mon Sep 17 00:00:00 2001 From: Herbert Xu Date: Tue, 28 May 2019 15:02:31 +0800 Subject: rhashtable: Add rht_ptr_rcu and improve rht_ptr This patch moves common code between rht_ptr and rht_ptr_exclusive into __rht_ptr. It also adds a new helper rht_ptr_rcu exclusively for the RCU case. This way rht_ptr becomes a lock-only construct so we can use the lighter rcu_dereference_protected primitive. Signed-off-by: Herbert Xu Signed-off-by: David S. Miller --- include/linux/rhashtable.h | 36 ++++++++++++++++++------------------ 1 file changed, 18 insertions(+), 18 deletions(-) (limited to 'include') diff --git a/include/linux/rhashtable.h b/include/linux/rhashtable.h index 9f8bc06d4136..beb9a9da1699 100644 --- a/include/linux/rhashtable.h +++ b/include/linux/rhashtable.h @@ -352,37 +352,38 @@ static inline void rht_unlock(struct bucket_table *tbl, static inline struct rhash_head __rcu *__rht_ptr( struct rhash_lock_head *const *bkt) { - return (struct rhash_head __rcu *)((unsigned long)*bkt & ~BIT(0)); + return (struct rhash_head __rcu *) + ((unsigned long)*bkt & ~BIT(0) ?: + (unsigned long)RHT_NULLS_MARKER(bkt)); } /* * Where 'bkt' is a bucket and might be locked: - * rht_ptr() dereferences that pointer and clears the lock bit. + * rht_ptr_rcu() dereferences that pointer and clears the lock bit. + * rht_ptr() dereferences in a context where the bucket is locked. * rht_ptr_exclusive() dereferences in a context where exclusive * access is guaranteed, such as when destroying the table. */ +static inline struct rhash_head *rht_ptr_rcu( + struct rhash_lock_head *const *bkt) +{ + struct rhash_head __rcu *p = __rht_ptr(bkt); + + return rcu_dereference(p); +} + static inline struct rhash_head *rht_ptr( struct rhash_lock_head *const *bkt, struct bucket_table *tbl, unsigned int hash) { - struct rhash_head __rcu *p = __rht_ptr(bkt); - - if (!p) - return RHT_NULLS_MARKER(bkt); - - return rht_dereference_bucket_rcu(p, tbl, hash); + return rht_dereference_bucket(__rht_ptr(bkt), tbl, hash); } static inline struct rhash_head *rht_ptr_exclusive( struct rhash_lock_head *const *bkt) { - struct rhash_head __rcu *p = __rht_ptr(bkt); - - if (!p) - return RHT_NULLS_MARKER(bkt); - - return rcu_dereference_protected(p, 1); + return rcu_dereference_protected(__rht_ptr(bkt), 1); } static inline void rht_assign_locked(struct rhash_lock_head **bkt, @@ -509,7 +510,7 @@ static inline void rht_assign_unlock(struct bucket_table *tbl, */ #define rht_for_each_rcu(pos, tbl, hash) \ for (({barrier(); }), \ - pos = rht_ptr(rht_bucket(tbl, hash), tbl, hash); \ + pos = rht_ptr_rcu(rht_bucket(tbl, hash)); \ !rht_is_a_nulls(pos); \ pos = rcu_dereference_raw(pos->next)) @@ -546,8 +547,7 @@ static inline void rht_assign_unlock(struct bucket_table *tbl, */ #define rht_for_each_entry_rcu(tpos, pos, tbl, hash, member) \ rht_for_each_entry_rcu_from(tpos, pos, \ - rht_ptr(rht_bucket(tbl, hash), \ - tbl, hash), \ + rht_ptr_rcu(rht_bucket(tbl, hash)), \ tbl, hash, member) /** @@ -603,7 +603,7 @@ restart: hash = rht_key_hashfn(ht, tbl, key, params); bkt = rht_bucket(tbl, hash); do { - rht_for_each_rcu_from(he, rht_ptr(bkt, tbl, hash), tbl, hash) { + rht_for_each_rcu_from(he, rht_ptr_rcu(bkt), tbl, hash) { if (params.obj_cmpfn ? params.obj_cmpfn(&arg, rht_obj(ht, he)) : rhashtable_compare(&arg, rht_obj(ht, he))) -- cgit v1.2.3 From 24ec483cec981618f8a4782a36d1e3f319d42cad Mon Sep 17 00:00:00 2001 From: Kevin 'ldir' Darbyshire-Bryant Date: Tue, 28 May 2019 17:03:50 +0000 Subject: net: sched: Introduce act_ctinfo action MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit ctinfo is a new tc filter action module. It is designed to restore information contained in firewall conntrack marks to other packet fields and is typically used on packet ingress paths. At present it has two independent sub-functions or operating modes, DSCP restoration mode & skb mark restoration mode. The DSCP restore mode: This mode copies DSCP values that have been placed in the firewall conntrack mark back into the IPv4/v6 diffserv fields of relevant packets. The DSCP restoration is intended for use and has been found useful for restoring ingress classifications based on egress classifications across links that bleach or otherwise change DSCP, typically home ISP Internet links. Restoring DSCP on ingress on the WAN link allows qdiscs such as but by no means limited to CAKE to shape inbound packets according to policies that are easier to set & mark on egress. Ingress classification is traditionally a challenging task since iptables rules haven't yet run and tc filter/eBPF programs are pre-NAT lookups, hence are unable to see internal IPv4 addresses as used on the typical home masquerading gateway. Thus marking the connection in some manner on egress for later restoration of classification on ingress is easier to implement. Parameters related to DSCP restore mode: dscpmask - a 32 bit mask of 6 contiguous bits and indicate bits of the conntrack mark field contain the DSCP value to be restored. statemask - a 32 bit mask of (usually) 1 bit length, outside the area specified by dscpmask. This represents a conditional operation flag whereby the DSCP is only restored if the flag is set. This is useful to implement a 'one shot' iptables based classification where the 'complicated' iptables rules are only run once to classify the connection on initial (egress) packet and subsequent packets are all marked/restored with the same DSCP. A mask of zero disables the conditional behaviour ie. the conntrack mark DSCP bits are always restored to the ip diffserv field (assuming the conntrack entry is found & the skb is an ipv4/ipv6 type) e.g. dscpmask 0xfc000000 statemask 0x01000000 |----0xFC----conntrack mark----000000---| | Bits 31-26 | bit 25 | bit24 |~~~ Bit 0| | DSCP | unused | flag |unused | |-----------------------0x01---000000---| | | | | ---| Conditional flag v only restore if set |-ip diffserv-| | 6 bits | |-------------| The skb mark restore mode (cpmark): This mode copies the firewall conntrack mark to the skb's mark field. It is completely the functional equivalent of the existing act_connmark action with the additional feature of being able to apply a mask to the restored value. Parameters related to skb mark restore mode: mask - a 32 bit mask applied to the firewall conntrack mark to mask out bits unwanted for restoration. This can be useful where the conntrack mark is being used for different purposes by different applications. If not specified and by default the whole mark field is copied (i.e. default mask of 0xffffffff) e.g. mask 0x00ffffff to mask out the top 8 bits being used by the aforementioned DSCP restore mode. |----0x00----conntrack mark----ffffff---| | Bits 31-24 | | | DSCP & flag| some value here | |---------------------------------------| | | v |------------skb mark-------------------| | | | | zeroed | | |---------------------------------------| Overall parameters: zone - conntrack zone control - action related control (reclassify | pipe | drop | continue | ok | goto chain ) Signed-off-by: Kevin Darbyshire-Bryant Reviewed-by: Toke Høiland-Jørgensen Acked-by: Cong Wang Signed-off-by: David S. Miller --- include/net/tc_act/tc_ctinfo.h | 28 ++++++++++++++++++++++++++++ include/uapi/linux/pkt_cls.h | 1 + include/uapi/linux/tc_act/tc_ctinfo.h | 34 ++++++++++++++++++++++++++++++++++ 3 files changed, 63 insertions(+) create mode 100644 include/net/tc_act/tc_ctinfo.h create mode 100644 include/uapi/linux/tc_act/tc_ctinfo.h (limited to 'include') diff --git a/include/net/tc_act/tc_ctinfo.h b/include/net/tc_act/tc_ctinfo.h new file mode 100644 index 000000000000..d6a688571672 --- /dev/null +++ b/include/net/tc_act/tc_ctinfo.h @@ -0,0 +1,28 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef __NET_TC_CTINFO_H +#define __NET_TC_CTINFO_H + +#include + +struct tcf_ctinfo_params { + struct rcu_head rcu; + struct net *net; + u32 dscpmask; + u32 dscpstatemask; + u32 cpmarkmask; + u16 zone; + u8 mode; + u8 dscpmaskshift; +}; + +struct tcf_ctinfo { + struct tc_action common; + struct tcf_ctinfo_params __rcu *params; + u64 stats_dscp_set; + u64 stats_dscp_error; + u64 stats_cpmark_set; +}; + +#define to_ctinfo(a) ((struct tcf_ctinfo *)a) + +#endif /* __NET_TC_CTINFO_H */ diff --git a/include/uapi/linux/pkt_cls.h b/include/uapi/linux/pkt_cls.h index 51a0496f78ea..a93680fc4bfa 100644 --- a/include/uapi/linux/pkt_cls.h +++ b/include/uapi/linux/pkt_cls.h @@ -105,6 +105,7 @@ enum tca_id { TCA_ID_IFE = TCA_ACT_IFE, TCA_ID_SAMPLE = TCA_ACT_SAMPLE, /* other actions go here */ + TCA_ID_CTINFO, __TCA_ID_MAX = 255 }; diff --git a/include/uapi/linux/tc_act/tc_ctinfo.h b/include/uapi/linux/tc_act/tc_ctinfo.h new file mode 100644 index 000000000000..da803e05a89b --- /dev/null +++ b/include/uapi/linux/tc_act/tc_ctinfo.h @@ -0,0 +1,34 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ +#ifndef __UAPI_TC_CTINFO_H +#define __UAPI_TC_CTINFO_H + +#include +#include + +struct tc_ctinfo { + tc_gen; +}; + +enum { + TCA_CTINFO_UNSPEC, + TCA_CTINFO_PAD, + TCA_CTINFO_TM, + TCA_CTINFO_ACT, + TCA_CTINFO_ZONE, + TCA_CTINFO_PARMS_DSCP_MASK, + TCA_CTINFO_PARMS_DSCP_STATEMASK, + TCA_CTINFO_PARMS_CPMARK_MASK, + TCA_CTINFO_STATS_DSCP_SET, + TCA_CTINFO_STATS_DSCP_ERROR, + TCA_CTINFO_STATS_CPMARK_SET, + __TCA_CTINFO_MAX +}; + +#define TCA_CTINFO_MAX (__TCA_CTINFO_MAX - 1) + +enum { + CTINFO_MODE_DSCP = BIT(0), + CTINFO_MODE_CPMARK = BIT(1) +}; + +#endif -- cgit v1.2.3 From 44cc27e43fa3b8977373915a8e7f515a9d263343 Mon Sep 17 00:00:00 2001 From: Ioana Ciornei Date: Tue, 28 May 2019 20:38:12 +0300 Subject: net: phylink: Add struct phylink_config to PHYLINK API The phylink_config structure will encapsulate a pointer to a struct device and the operation type requested for this instance of PHYLINK. This patch does not make any functional changes, it just transitions the PHYLINK internals and all its users to the new API. A pointer to a phylink_config structure will be passed to phylink_create() instead of the net_device directly. Also, the same phylink_config pointer will be passed back to all phylink_mac_ops callbacks instead of the net_device. Using this mechanism, a PHYLINK user can get the original net_device using a structure such as 'to_net_dev(config->dev)' or directly the structure containing the phylink_config using a container_of call. At the moment, only the PHYLINK_NETDEV is defined as a valid operation type for PHYLINK. In this mode, a valid reference to a struct device linked to the original net_device should be passed to PHYLINK through the phylink_config structure. This API changes is mainly driven by the necessity of adding a new operation type in PHYLINK that disconnects the phy_device from the net_device and also works when the net_device is lacking. Signed-off-by: Ioana Ciornei Signed-off-by: Vladimir Oltean Reviewed-by: Florian Fainelli Reviewed-by: Maxime Chevallier Tested-by: Maxime Chevallier Signed-off-by: David S. Miller --- include/linux/phylink.h | 56 +++++++++++++++++++++++++++++++------------------ include/net/dsa.h | 2 ++ 2 files changed, 38 insertions(+), 20 deletions(-) (limited to 'include') diff --git a/include/linux/phylink.h b/include/linux/phylink.h index 6411c624f63a..67f35f07ac4b 100644 --- a/include/linux/phylink.h +++ b/include/linux/phylink.h @@ -54,6 +54,20 @@ struct phylink_link_state { unsigned int an_complete:1; }; +enum phylink_op_type { + PHYLINK_NETDEV = 0, +}; + +/** + * struct phylink_config - PHYLINK configuration structure + * @dev: a pointer to a struct device associated with the MAC + * @type: operation type of PHYLINK instance + */ +struct phylink_config { + struct device *dev; + enum phylink_op_type type; +}; + /** * struct phylink_mac_ops - MAC operations structure. * @validate: Validate and update the link configuration. @@ -66,16 +80,17 @@ struct phylink_link_state { * The individual methods are described more fully below. */ struct phylink_mac_ops { - void (*validate)(struct net_device *ndev, unsigned long *supported, + void (*validate)(struct phylink_config *config, + unsigned long *supported, struct phylink_link_state *state); - int (*mac_link_state)(struct net_device *ndev, + int (*mac_link_state)(struct phylink_config *config, struct phylink_link_state *state); - void (*mac_config)(struct net_device *ndev, unsigned int mode, + void (*mac_config)(struct phylink_config *config, unsigned int mode, const struct phylink_link_state *state); - void (*mac_an_restart)(struct net_device *ndev); - void (*mac_link_down)(struct net_device *ndev, unsigned int mode, + void (*mac_an_restart)(struct phylink_config *config); + void (*mac_link_down)(struct phylink_config *config, unsigned int mode, phy_interface_t interface); - void (*mac_link_up)(struct net_device *ndev, unsigned int mode, + void (*mac_link_up)(struct phylink_config *config, unsigned int mode, phy_interface_t interface, struct phy_device *phy); }; @@ -83,7 +98,7 @@ struct phylink_mac_ops { #if 0 /* For kernel-doc purposes only. */ /** * validate - Validate and update the link configuration - * @ndev: a pointer to a &struct net_device for the MAC. + * @config: a pointer to a &struct phylink_config. * @supported: ethtool bitmask for supported link modes. * @state: a pointer to a &struct phylink_link_state. * @@ -100,12 +115,12 @@ struct phylink_mac_ops { * based on @state->advertising and/or @state->speed and update * @state->interface accordingly. */ -void validate(struct net_device *ndev, unsigned long *supported, +void validate(struct phylink_config *config, unsigned long *supported, struct phylink_link_state *state); /** * mac_link_state() - Read the current link state from the hardware - * @ndev: a pointer to a &struct net_device for the MAC. + * @config: a pointer to a &struct phylink_config. * @state: a pointer to a &struct phylink_link_state. * * Read the current link state from the MAC, reporting the current @@ -114,12 +129,12 @@ void validate(struct net_device *ndev, unsigned long *supported, * negotiation completion state in @state->an_complete, and link * up state in @state->link. */ -int mac_link_state(struct net_device *ndev, +int mac_link_state(struct phylink_config *config, struct phylink_link_state *state); /** * mac_config() - configure the MAC for the selected mode and state - * @ndev: a pointer to a &struct net_device for the MAC. + * @config: a pointer to a &struct phylink_config. * @mode: one of %MLO_AN_FIXED, %MLO_AN_PHY, %MLO_AN_INBAND. * @state: a pointer to a &struct phylink_link_state. * @@ -157,18 +172,18 @@ int mac_link_state(struct net_device *ndev, * down. This "update" behaviour is critical to avoid bouncing the * link up status. */ -void mac_config(struct net_device *ndev, unsigned int mode, +void mac_config(struct phylink_config *config, unsigned int mode, const struct phylink_link_state *state); /** * mac_an_restart() - restart 802.3z BaseX autonegotiation - * @ndev: a pointer to a &struct net_device for the MAC. + * @config: a pointer to a &struct phylink_config. */ -void mac_an_restart(struct net_device *ndev); +void mac_an_restart(struct phylink_config *config); /** * mac_link_down() - take the link down - * @ndev: a pointer to a &struct net_device for the MAC. + * @config: a pointer to a &struct phylink_config. * @mode: link autonegotiation mode * @interface: link &typedef phy_interface_t mode * @@ -177,12 +192,12 @@ void mac_an_restart(struct net_device *ndev); * Energy Efficient Ethernet MAC configuration. Interface type * selection must be done in mac_config(). */ -void mac_link_down(struct net_device *ndev, unsigned int mode, +void mac_link_down(struct phylink_config *config, unsigned int mode, phy_interface_t interface); /** * mac_link_up() - allow the link to come up - * @ndev: a pointer to a &struct net_device for the MAC. + * @config: a pointer to a &struct phylink_config. * @mode: link autonegotiation mode * @interface: link &typedef phy_interface_t mode * @phy: any attached phy @@ -193,13 +208,14 @@ void mac_link_down(struct net_device *ndev, unsigned int mode, * phy_init_eee() and perform appropriate MAC configuration for EEE. * Interface type selection must be done in mac_config(). */ -void mac_link_up(struct net_device *ndev, unsigned int mode, +void mac_link_up(struct phylink_config *config, unsigned int mode, phy_interface_t interface, struct phy_device *phy); #endif -struct phylink *phylink_create(struct net_device *, struct fwnode_handle *, - phy_interface_t iface, const struct phylink_mac_ops *ops); +struct phylink *phylink_create(struct phylink_config *, struct fwnode_handle *, + phy_interface_t iface, + const struct phylink_mac_ops *ops); void phylink_destroy(struct phylink *); int phylink_connect_phy(struct phylink *, struct phy_device *); diff --git a/include/net/dsa.h b/include/net/dsa.h index 685294817712..a7f36219904f 100644 --- a/include/net/dsa.h +++ b/include/net/dsa.h @@ -22,6 +22,7 @@ #include #include #include +#include #include #include @@ -193,6 +194,7 @@ struct dsa_port { struct net_device *bridge_dev; struct devlink_port devlink_port; struct phylink *pl; + struct phylink_config pl_config; struct work_struct xmit_work; struct sk_buff_head xmit_queue; -- cgit v1.2.3 From 43de61959b999279bafb031c0c9bdf0f6cd1c501 Mon Sep 17 00:00:00 2001 From: Ioana Ciornei Date: Tue, 28 May 2019 20:38:13 +0300 Subject: net: phylink: Add PHYLINK_DEV operation type In the PHYLINK_DEV operation type, the PHYLINK infrastructure can work without an attached net_device. For printing usecases, instead, a struct device * should be passed to PHYLINK using the phylink_config structure. Also, netif_carrier_* calls ar guarded by the presence of a valid net_device. When using the PHYLINK_DEV operation type, we cannot check link status using the netif_carrier_ok() API so instead, keep an internal state of the MAC and call mac_link_{down,up} only when the link changed. Signed-off-by: Ioana Ciornei Signed-off-by: Vladimir Oltean Reviewed-by: Florian Fainelli Signed-off-by: David S. Miller --- include/linux/phylink.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/phylink.h b/include/linux/phylink.h index 67f35f07ac4b..0f6f65bb9d44 100644 --- a/include/linux/phylink.h +++ b/include/linux/phylink.h @@ -56,6 +56,7 @@ struct phylink_link_state { enum phylink_op_type { PHYLINK_NETDEV = 0, + PHYLINK_DEV, }; /** -- cgit v1.2.3 From 1e91a2e5d827e643cbabad66d133f155a7fcb0de Mon Sep 17 00:00:00 2001 From: Ruslan Babayev Date: Tue, 28 May 2019 16:02:32 -0700 Subject: i2c: acpi: export i2c_acpi_find_adapter_by_handle This allows drivers to lookup i2c adapters on ACPI based systems similar to of_get_i2c_adapter_by_node() with DT based systems. Signed-off-by: Ruslan Babayev Cc: xe-linux-external@cisco.com Reviewed-by: Andrew Lunn Signed-off-by: David S. Miller --- include/linux/i2c.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include') diff --git a/include/linux/i2c.h b/include/linux/i2c.h index 1308126fc384..e982b8913b73 100644 --- a/include/linux/i2c.h +++ b/include/linux/i2c.h @@ -14,6 +14,7 @@ #ifndef _LINUX_I2C_H #define _LINUX_I2C_H +#include /* for acpi_handle */ #include #include /* for struct device */ #include /* for completion */ @@ -981,6 +982,7 @@ bool i2c_acpi_get_i2c_resource(struct acpi_resource *ares, u32 i2c_acpi_find_bus_speed(struct device *dev); struct i2c_client *i2c_acpi_new_device(struct device *dev, int index, struct i2c_board_info *info); +struct i2c_adapter *i2c_acpi_find_adapter_by_handle(acpi_handle handle); #else static inline bool i2c_acpi_get_i2c_resource(struct acpi_resource *ares, struct acpi_resource_i2c_serialbus **i2c) @@ -996,6 +998,10 @@ static inline struct i2c_client *i2c_acpi_new_device(struct device *dev, { return NULL; } +static inline struct i2c_adapter *i2c_acpi_find_adapter_by_handle(acpi_handle handle) +{ + return NULL; +} #endif /* CONFIG_ACPI */ #endif /* _LINUX_I2C_H */ -- cgit v1.2.3 From 9092a76d3cf8638467b09bbb4f409094349b2b53 Mon Sep 17 00:00:00 2001 From: Jason Baron Date: Wed, 29 May 2019 12:33:57 -0400 Subject: tcp: add backup TFO key infrastructure We would like to be able to rotate TFO keys while minimizing the number of client cookies that are rejected. Currently, we have only one key which can be used to generate and validate cookies, thus if we simply replace this key clients can easily have cookies rejected upon rotation. We propose having the ability to have both a primary key and a backup key. The primary key is used to generate as well as to validate cookies. The backup is only used to validate cookies. Thus, keys can be rotated as: 1) generate new key 2) add new key as the backup key 3) swap the primary and backup key, thus setting the new key as the primary We don't simply set the new key as the primary key and move the old key to the backup slot because the ip may be behind a load balancer and we further allow for the fact that all machines behind the load balancer will not be updated simultaneously. We make use of this infrastructure in subsequent patches. Suggested-by: Igor Lubashev Signed-off-by: Jason Baron Signed-off-by: Christoph Paasch Acked-by: Yuchung Cheng Signed-off-by: David S. Miller --- include/net/tcp.h | 41 ++++++++++++++++++++++++++++++++++++++--- include/uapi/linux/snmp.h | 1 + 2 files changed, 39 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/include/net/tcp.h b/include/net/tcp.h index 985aa5db570c..0083a14fb64f 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -1614,7 +1614,8 @@ void tcp_free_fastopen_req(struct tcp_sock *tp); void tcp_fastopen_destroy_cipher(struct sock *sk); void tcp_fastopen_ctx_destroy(struct net *net); int tcp_fastopen_reset_cipher(struct net *net, struct sock *sk, - void *key, unsigned int len); + void *primary_key, void *backup_key, + unsigned int len); void tcp_fastopen_add_skb(struct sock *sk, struct sk_buff *skb); struct sock *tcp_try_fastopen(struct sock *sk, struct sk_buff *skb, struct request_sock *req, @@ -1625,11 +1626,14 @@ bool tcp_fastopen_cookie_check(struct sock *sk, u16 *mss, struct tcp_fastopen_cookie *cookie); bool tcp_fastopen_defer_connect(struct sock *sk, int *err); #define TCP_FASTOPEN_KEY_LENGTH 16 +#define TCP_FASTOPEN_KEY_MAX 2 +#define TCP_FASTOPEN_KEY_BUF_LENGTH \ + (TCP_FASTOPEN_KEY_LENGTH * TCP_FASTOPEN_KEY_MAX) /* Fastopen key context */ struct tcp_fastopen_context { - struct crypto_cipher *tfm; - __u8 key[TCP_FASTOPEN_KEY_LENGTH]; + struct crypto_cipher *tfm[TCP_FASTOPEN_KEY_MAX]; + __u8 key[TCP_FASTOPEN_KEY_BUF_LENGTH]; struct rcu_head rcu; }; @@ -1639,6 +1643,37 @@ bool tcp_fastopen_active_should_disable(struct sock *sk); void tcp_fastopen_active_disable_ofo_check(struct sock *sk); void tcp_fastopen_active_detect_blackhole(struct sock *sk, bool expired); +/* Caller needs to wrap with rcu_read_(un)lock() */ +static inline +struct tcp_fastopen_context *tcp_fastopen_get_ctx(const struct sock *sk) +{ + struct tcp_fastopen_context *ctx; + + ctx = rcu_dereference(inet_csk(sk)->icsk_accept_queue.fastopenq.ctx); + if (!ctx) + ctx = rcu_dereference(sock_net(sk)->ipv4.tcp_fastopen_ctx); + return ctx; +} + +static inline +bool tcp_fastopen_cookie_match(const struct tcp_fastopen_cookie *foc, + const struct tcp_fastopen_cookie *orig) +{ + if (orig->len == TCP_FASTOPEN_COOKIE_SIZE && + orig->len == foc->len && + !memcmp(orig->val, foc->val, foc->len)) + return true; + return false; +} + +static inline +int tcp_fastopen_context_len(const struct tcp_fastopen_context *ctx) +{ + if (ctx->tfm[1]) + return 2; + return 1; +} + /* Latencies incurred by various limits for a sender. They are * chronograph-like stats that are mutually exclusive. */ diff --git a/include/uapi/linux/snmp.h b/include/uapi/linux/snmp.h index 86dc24a96c90..74904e9d1b72 100644 --- a/include/uapi/linux/snmp.h +++ b/include/uapi/linux/snmp.h @@ -283,6 +283,7 @@ enum LINUX_MIB_TCPACKCOMPRESSED, /* TCPAckCompressed */ LINUX_MIB_TCPZEROWINDOWDROP, /* TCPZeroWindowDrop */ LINUX_MIB_TCPRCVQDROP, /* TCPRcvQDrop */ + LINUX_MIB_TCPFASTOPENPASSIVEALTKEY, /* TCPFastOpenPassiveAltKey */ __LINUX_MIB_MAX }; -- cgit v1.2.3 From c8b17be0b7a45d707fc202c11d257c25bc3952b8 Mon Sep 17 00:00:00 2001 From: Pablo Neira Ayuso Date: Wed, 29 May 2019 13:25:31 +0200 Subject: net: ipv4: add skbuff fraglist splitter This patch adds the skbuff fraglist splitter. This API provides an iterator to transform the fraglist into single skbuff objects, it consists of: * ip_fraglist_init(), that initializes the internal state of the fraglist splitter. * ip_fraglist_prepare(), that restores the IPv4 header on the fragments. * ip_fraglist_next(), that retrieves the fragment from the fraglist and it updates the internal state of the splitter to point to the next fragment skbuff in the fraglist. The ip_fraglist_iter object stores the internal state of the iterator. This code has been extracted from ip_do_fragment(). Symbols are also exported to allow to reuse this iterator from the bridge codepath to build its own refragmentation routine by reusing the existing codebase. Signed-off-by: Pablo Neira Ayuso Signed-off-by: David S. Miller --- include/net/ip.h | 23 +++++++++++++++++++++++ 1 file changed, 23 insertions(+) (limited to 'include') diff --git a/include/net/ip.h b/include/net/ip.h index 2d3cce7c3e8a..be899677504b 100644 --- a/include/net/ip.h +++ b/include/net/ip.h @@ -165,6 +165,29 @@ 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 *)); + +struct ip_fraglist_iter { + struct sk_buff *frag_list; + struct sk_buff *frag; + struct iphdr *iph; + int offset; + unsigned int hlen; +}; + +void ip_fraglist_init(struct sk_buff *skb, struct iphdr *iph, + unsigned int hlen, struct ip_fraglist_iter *iter); +void ip_fraglist_prepare(struct sk_buff *skb, struct ip_fraglist_iter *iter); + +static inline struct sk_buff *ip_fraglist_next(struct ip_fraglist_iter *iter) +{ + struct sk_buff *skb = iter->frag; + + iter->frag = skb->next; + skb_mark_not_on_list(skb); + + return skb; +} + 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 net *net, struct sock *sk, struct sk_buff *skb); -- cgit v1.2.3 From 0feca6190f88a1b7c9a9b9cdf41824e3ea4ba02c Mon Sep 17 00:00:00 2001 From: Pablo Neira Ayuso Date: Wed, 29 May 2019 13:25:32 +0200 Subject: net: ipv6: add skbuff fraglist splitter This patch adds the skbuff fraglist split iterator. This API provides an iterator to transform the fraglist into single skbuff objects, it consists of: * ip6_fraglist_init(), that initializes the internal state of the fraglist iterator. * ip6_fraglist_prepare(), that restores the IPv6 header on the fragment. * ip6_fraglist_next(), that retrieves the fragment from the fraglist and updates the internal state of the iterator to point to the next fragment in the fraglist. The ip6_fraglist_iter object stores the internal state of the iterator. This code has been extracted from ip6_fragment(). Symbols are also exported to allow to reuse this iterator from the bridge codepath to build its own refragmentation routine by reusing the existing codebase. Signed-off-by: Pablo Neira Ayuso Signed-off-by: David S. Miller --- include/net/ipv6.h | 25 +++++++++++++++++++++++++ 1 file changed, 25 insertions(+) (limited to 'include') diff --git a/include/net/ipv6.h b/include/net/ipv6.h index daf80863d3a5..acefbc718abe 100644 --- a/include/net/ipv6.h +++ b/include/net/ipv6.h @@ -154,6 +154,31 @@ struct frag_hdr { #define IP6_MF 0x0001 #define IP6_OFFSET 0xFFF8 +struct ip6_fraglist_iter { + struct ipv6hdr *tmp_hdr; + struct sk_buff *frag_list; + struct sk_buff *frag; + int offset; + unsigned int hlen; + __be32 frag_id; + u8 nexthdr; +}; + +int ip6_fraglist_init(struct sk_buff *skb, unsigned int hlen, u8 *prevhdr, + u8 nexthdr, __be32 frag_id, + struct ip6_fraglist_iter *iter); +void ip6_fraglist_prepare(struct sk_buff *skb, struct ip6_fraglist_iter *iter); + +static inline struct sk_buff *ip6_fraglist_next(struct ip6_fraglist_iter *iter) +{ + struct sk_buff *skb = iter->frag; + + iter->frag = skb->next; + skb_mark_not_on_list(skb); + + return skb; +} + #define IP6_REPLY_MARK(net, mark) \ ((net)->ipv6.sysctl.fwmark_reflect ? (mark) : 0) -- cgit v1.2.3 From 065ff79f8881e6267f4c29abb476d697eb87bfba Mon Sep 17 00:00:00 2001 From: Pablo Neira Ayuso Date: Wed, 29 May 2019 13:25:33 +0200 Subject: net: ipv4: split skbuff into fragments transformer This patch exposes a new API to refragment a skbuff. This allows you to split either a linear skbuff or to force the refragmentation of an existing fraglist using a different mtu. The API consists of: * ip_frag_init(), that initializes the internal state of the transformer. * ip_frag_next(), that allows you to fetch the next fragment. This function internally allocates the skbuff that represents the fragment, it pushes the IPv4 header, and it also copies the payload for each fragment. The ip_frag_state object stores the internal state of the splitter. This code has been extracted from ip_do_fragment(). Symbols are also exported to allow to reuse this iterator from the bridge codepath to build its own refragmentation routine by reusing the existing codebase. Signed-off-by: Pablo Neira Ayuso Signed-off-by: David S. Miller --- include/net/ip.h | 16 ++++++++++++++++ 1 file changed, 16 insertions(+) (limited to 'include') diff --git a/include/net/ip.h b/include/net/ip.h index be899677504b..029cc3fd26bd 100644 --- a/include/net/ip.h +++ b/include/net/ip.h @@ -188,6 +188,22 @@ static inline struct sk_buff *ip_fraglist_next(struct ip_fraglist_iter *iter) return skb; } +struct ip_frag_state { + struct iphdr *iph; + unsigned int hlen; + unsigned int ll_rs; + unsigned int mtu; + unsigned int left; + int offset; + int ptr; + __be16 not_last_frag; +}; + +void ip_frag_init(struct sk_buff *skb, unsigned int hlen, unsigned int ll_rs, + unsigned int mtu, struct ip_frag_state *state); +struct sk_buff *ip_frag_next(struct sk_buff *skb, + struct ip_frag_state *state); + 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 net *net, struct sock *sk, struct sk_buff *skb); -- cgit v1.2.3 From 8a6a1f17640198f7daa5cfcce9a74e3674ce3b00 Mon Sep 17 00:00:00 2001 From: Pablo Neira Ayuso Date: Wed, 29 May 2019 13:25:34 +0200 Subject: net: ipv6: split skbuff into fragments transformer This patch exposes a new API to refragment a skbuff. This allows you to split either a linear skbuff or to force the refragmentation of an existing fraglist using a different mtu. The API consists of: * ip6_frag_init(), that initializes the internal state of the transformer. * ip6_frag_next(), that allows you to fetch the next fragment. This function internally allocates the skbuff that represents the fragment, it pushes the IPv6 header, and it also copies the payload for each fragment. The ip6_frag_state object stores the internal state of the splitter. This code has been extracted from ip6_fragment(). Symbols are also exported to allow to reuse this iterator from the bridge codepath to build its own refragmentation routine by reusing the existing codebase. Signed-off-by: Pablo Neira Ayuso Signed-off-by: David S. Miller --- include/net/ipv6.h | 19 +++++++++++++++++++ 1 file changed, 19 insertions(+) (limited to 'include') diff --git a/include/net/ipv6.h b/include/net/ipv6.h index acefbc718abe..21bb830e9679 100644 --- a/include/net/ipv6.h +++ b/include/net/ipv6.h @@ -179,6 +179,25 @@ static inline struct sk_buff *ip6_fraglist_next(struct ip6_fraglist_iter *iter) return skb; } +struct ip6_frag_state { + u8 *prevhdr; + unsigned int hlen; + unsigned int mtu; + unsigned int left; + int offset; + int ptr; + int hroom; + int troom; + __be32 frag_id; + u8 nexthdr; +}; + +void ip6_frag_init(struct sk_buff *skb, unsigned int hlen, unsigned int mtu, + unsigned short needed_tailroom, int hdr_room, u8 *prevhdr, + u8 nexthdr, __be32 frag_id, struct ip6_frag_state *state); +struct sk_buff *ip6_frag_next(struct sk_buff *skb, + struct ip6_frag_state *state); + #define IP6_REPLY_MARK(net, mark) \ ((net)->ipv6.sysctl.fwmark_reflect ? (mark) : 0) -- cgit v1.2.3 From d035f19f59c5bca2fda2faa43b5e9fe09dfb7884 Mon Sep 17 00:00:00 2001 From: Pablo Neira Ayuso Date: Wed, 29 May 2019 13:25:36 +0200 Subject: netfilter: nf_conntrack: allow to register bridge support This patch adds infrastructure to register and to unregister bridge support for the conntrack module via nf_ct_bridge_register() and nf_ct_bridge_unregister(). Signed-off-by: Pablo Neira Ayuso Signed-off-by: David S. Miller --- include/net/netfilter/nf_conntrack.h | 1 + include/net/netfilter/nf_conntrack_bridge.h | 13 +++++++++++++ 2 files changed, 14 insertions(+) create mode 100644 include/net/netfilter/nf_conntrack_bridge.h (limited to 'include') diff --git a/include/net/netfilter/nf_conntrack.h b/include/net/netfilter/nf_conntrack.h index d2bc733a2ef1..5cb19ce454d1 100644 --- a/include/net/netfilter/nf_conntrack.h +++ b/include/net/netfilter/nf_conntrack.h @@ -49,6 +49,7 @@ union nf_conntrack_expect_proto { struct nf_conntrack_net { unsigned int users4; unsigned int users6; + unsigned int users_bridge; }; #include diff --git a/include/net/netfilter/nf_conntrack_bridge.h b/include/net/netfilter/nf_conntrack_bridge.h new file mode 100644 index 000000000000..3be1642e04f7 --- /dev/null +++ b/include/net/netfilter/nf_conntrack_bridge.h @@ -0,0 +1,13 @@ +#ifndef NF_CONNTRACK_BRIDGE_ +#define NF_CONNTRACK_BRIDGE_ + +struct nf_ct_bridge_info { + struct nf_hook_ops *ops; + unsigned int ops_size; + struct module *me; +}; + +void nf_ct_bridge_register(struct nf_ct_bridge_info *info); +void nf_ct_bridge_unregister(struct nf_ct_bridge_info *info); + +#endif -- cgit v1.2.3 From 3c171f496ef57774f8e5d509923372549734877f Mon Sep 17 00:00:00 2001 From: Pablo Neira Ayuso Date: Wed, 29 May 2019 13:25:37 +0200 Subject: netfilter: bridge: add connection tracking system This patch adds basic connection tracking support for the bridge, including initial IPv4 support. This patch register two hooks to deal with the bridge forwarding path, one from the bridge prerouting hook to call nf_conntrack_in(); and another from the bridge postrouting hook to confirm the entry. The conntrack bridge prerouting hook defragments packets before passing them to nf_conntrack_in() to look up for an existing entry, otherwise a new entry is allocated and it is attached to the skbuff. The conntrack bridge postrouting hook confirms new conntrack entries, ie. if this is the first packet seen, then it adds the entry to the hashtable and (if needed) it refragments the skbuff into the original fragments, leaving the geometry as is if possible. Exceptions are linearized skbuffs, eg. skbuffs that are passed up to nfqueue and conntrack helpers, as well as cloned skbuff for the local delivery (eg. tcpdump), also in case of bridge port flooding (cloned skbuff too). The packet defragmentation is done through the ip_defrag() call. This forces us to save the bridge control buffer, reset the IP control buffer area and then restore it after call. This function also bumps the IP fragmentation statistics, it would be probably desiderable to have independent statistics for the bridge defragmentation/refragmentation. The maximum fragment length is stored in the control buffer and it is used to refragment the skbuff from the postrouting path. The new fraglist splitter and fragment transformer APIs are used to implement the bridge refragmentation code. The br_ip_fragment() function drops the packet in case the maximum fragment size seen is larger than the output port MTU. This patchset follows the principle that conntrack should not drop packets, so users can do it through policy via invalid state matching. Like br_netfilter, there is no refragmentation for packets that are passed up for local delivery, ie. prerouting -> input path. There are calls to nf_reset() already in several spots in the stack since time ago already, eg. af_packet, that show that skbuff fraglist handling from the netif_rx path is supported already. The helpers are called from the postrouting hook, before confirmation, from there we may see packet floods to bridge ports. Then, although unlikely, this may result in exercising the helpers many times for each clone. It would be good to explore how to pass all the packets in a list to the conntrack hook to do this handle only once for this case. Thanks to Florian Westphal for handing me over an initial patchset version to add support for conntrack bridge. Signed-off-by: Pablo Neira Ayuso Signed-off-by: David S. Miller --- include/net/netfilter/nf_conntrack_bridge.h | 7 +++++++ include/net/netfilter/nf_conntrack_core.h | 3 +++ 2 files changed, 10 insertions(+) (limited to 'include') diff --git a/include/net/netfilter/nf_conntrack_bridge.h b/include/net/netfilter/nf_conntrack_bridge.h index 3be1642e04f7..9a5514d5bc51 100644 --- a/include/net/netfilter/nf_conntrack_bridge.h +++ b/include/net/netfilter/nf_conntrack_bridge.h @@ -10,4 +10,11 @@ struct nf_ct_bridge_info { void nf_ct_bridge_register(struct nf_ct_bridge_info *info); void nf_ct_bridge_unregister(struct nf_ct_bridge_info *info); +struct nf_ct_bridge_frag_data { + char mac[ETH_HLEN]; + bool vlan_present; + u16 vlan_tci; + __be16 vlan_proto; +}; + #endif diff --git a/include/net/netfilter/nf_conntrack_core.h b/include/net/netfilter/nf_conntrack_core.h index ae41e92251dd..de10faf2ce91 100644 --- a/include/net/netfilter/nf_conntrack_core.h +++ b/include/net/netfilter/nf_conntrack_core.h @@ -64,6 +64,9 @@ static inline int nf_conntrack_confirm(struct sk_buff *skb) return ret; } +unsigned int nf_confirm(struct sk_buff *skb, unsigned int protoff, + struct nf_conn *ct, enum ip_conntrack_info ctinfo); + void print_tuple(struct seq_file *s, const struct nf_conntrack_tuple *tuple, const struct nf_conntrack_l4proto *proto); -- cgit v1.2.3 From 764dd163ac922f8683b5bcd3007251ce7b26cd33 Mon Sep 17 00:00:00 2001 From: Pablo Neira Ayuso Date: Wed, 29 May 2019 13:25:38 +0200 Subject: netfilter: nf_conntrack_bridge: add support for IPv6 br_defrag() and br_fragment() indirections are added in case that IPv6 support comes as a module, to avoid pulling innecessary dependencies in. The new fraglist iterator and fragment transformer APIs are used to implement the refragmentation code. Signed-off-by: Pablo Neira Ayuso Signed-off-by: David S. Miller --- include/linux/netfilter_ipv6.h | 50 ++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 50 insertions(+) (limited to 'include') diff --git a/include/linux/netfilter_ipv6.h b/include/linux/netfilter_ipv6.h index 12113e502656..a21b8c9623ee 100644 --- a/include/linux/netfilter_ipv6.h +++ b/include/linux/netfilter_ipv6.h @@ -19,6 +19,7 @@ struct ip6_rt_info { }; struct nf_queue_entry; +struct nf_ct_bridge_frag_data; /* * Hook functions for ipv6 to allow xt_* modules to be built-in even @@ -39,6 +40,15 @@ struct nf_ipv6_ops { int (*fragment)(struct net *net, struct sock *sk, struct sk_buff *skb, int (*output)(struct net *, struct sock *, struct sk_buff *)); int (*reroute)(struct sk_buff *skb, const struct nf_queue_entry *entry); +#if IS_MODULE(CONFIG_IPV6) + int (*br_defrag)(struct net *net, struct sk_buff *skb, u32 user); + int (*br_fragment)(struct net *net, struct sock *sk, + struct sk_buff *skb, + struct nf_ct_bridge_frag_data *data, + int (*output)(struct net *, struct sock *sk, + const struct nf_ct_bridge_frag_data *data, + struct sk_buff *)); +#endif }; #ifdef CONFIG_NETFILTER @@ -86,6 +96,46 @@ static inline int nf_ip6_route(struct net *net, struct dst_entry **dst, #endif } +static inline int nf_ipv6_br_defrag(struct net *net, struct sk_buff *skb, + u32 user) +{ +#if IS_MODULE(CONFIG_IPV6) + const struct nf_ipv6_ops *v6_ops = nf_get_ipv6_ops(); + + if (!v6_ops) + return 1; + + return v6_ops->br_defrag(net, skb, user); +#else + return nf_ct_frag6_gather(net, skb, user); +#endif +} + +int br_ip6_fragment(struct net *net, struct sock *sk, struct sk_buff *skb, + struct nf_ct_bridge_frag_data *data, + int (*output)(struct net *, struct sock *sk, + const struct nf_ct_bridge_frag_data *data, + struct sk_buff *)); + +static inline int nf_br_ip6_fragment(struct net *net, struct sock *sk, + struct sk_buff *skb, + struct nf_ct_bridge_frag_data *data, + int (*output)(struct net *, struct sock *sk, + const struct nf_ct_bridge_frag_data *data, + struct sk_buff *)) +{ +#if IS_MODULE(CONFIG_IPV6) + const struct nf_ipv6_ops *v6_ops = nf_get_ipv6_ops(); + + if (!v6_ops) + return 1; + + return v6_ops->br_fragment(net, sk, skb, data, output); +#else + return br_ip6_fragment(net, sk, skb, data, output); +#endif +} + int ip6_route_me_harder(struct net *net, struct sk_buff *skb); static inline int nf_ip6_route_me_harder(struct net *net, struct sk_buff *skb) -- cgit v1.2.3 From c3e933a5b8c19145d14e207e0ecf220f1d6cfda1 Mon Sep 17 00:00:00 2001 From: Matteo Croce Date: Wed, 29 May 2019 17:39:41 +0200 Subject: sctp: deduplicate identical skb_checksum_ops The same skb_checksum_ops struct is defined twice in two different places, leading to code duplication. Declare it as a global variable into a common header instead of allocating it on the stack on each function call. bloat-o-meter reports a slight code shrink. add/remove: 1/1 grow/shrink: 0/10 up/down: 128/-1282 (-1154) Function old new delta sctp_csum_ops - 128 +128 crc32c_csum_ops 16 - -16 sctp_rcv 6616 6583 -33 sctp_packet_pack 4542 4504 -38 nf_conntrack_sctp_packet 4980 4926 -54 execute_masked_set_action 6453 6389 -64 tcf_csum_sctp 575 428 -147 sctp_gso_segment 1292 1126 -166 sctp_csum_check 579 412 -167 sctp_snat_handler 957 772 -185 sctp_dnat_handler 1321 1132 -189 l4proto_manip_pkt 2536 2313 -223 Total: Before=359297613, After=359296459, chg -0.00% Reviewed-by: Xin Long Signed-off-by: Matteo Croce Acked-by: Neil Horman Acked-by: Marcelo Ricardo Leitner Signed-off-by: David S. Miller --- include/net/sctp/checksum.h | 12 +++++++----- 1 file changed, 7 insertions(+), 5 deletions(-) (limited to 'include') diff --git a/include/net/sctp/checksum.h b/include/net/sctp/checksum.h index 1c6e6c0766ca..1b74af2477d1 100644 --- a/include/net/sctp/checksum.h +++ b/include/net/sctp/checksum.h @@ -58,19 +58,21 @@ static inline __wsum sctp_csum_combine(__wsum csum, __wsum csum2, (__force __u32)csum2, len); } +static const struct skb_checksum_ops sctp_csum_ops = { + .update = sctp_csum_update, + .combine = sctp_csum_combine, +}; + static inline __le32 sctp_compute_cksum(const struct sk_buff *skb, unsigned int offset) { struct sctphdr *sh = (struct sctphdr *)(skb->data + offset); - const struct skb_checksum_ops ops = { - .update = sctp_csum_update, - .combine = sctp_csum_combine, - }; __le32 old = sh->checksum; __wsum new; sh->checksum = 0; - new = ~__skb_checksum(skb, offset, skb->len - offset, ~(__wsum)0, &ops); + new = ~__skb_checksum(skb, offset, skb->len - offset, ~(__wsum)0, + &sctp_csum_ops); sh->checksum = old; return cpu_to_le32((__force __u32)new); -- cgit v1.2.3 From 07b0928918c694c845a387cc16256a8b63ced4fc Mon Sep 17 00:00:00 2001 From: Heiner Kallweit Date: Thu, 30 May 2019 15:09:15 +0200 Subject: net: phy: enable interrupts when PHY is attached already This patch is a step towards allowing PHY drivers to handle more interrupt sources than just link change. E.g. several PHY's have built-in temperature monitoring and can raise an interrupt if a temperature threshold is exceeded. We may be interested in such interrupts also if the phylib state machine isn't started. Therefore move enabling interrupts to phy_request_interrupt(). v2: - patch added to series Signed-off-by: Heiner Kallweit Reviewed-by: Andrew Lunn 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 7180b1d1e5e3..72e1196f9799 100644 --- a/include/linux/phy.h +++ b/include/linux/phy.h @@ -1147,6 +1147,7 @@ int phy_ethtool_ksettings_set(struct phy_device *phydev, const struct ethtool_link_ksettings *cmd); int phy_mii_ioctl(struct phy_device *phydev, struct ifreq *ifr, int cmd); void phy_request_interrupt(struct phy_device *phydev); +void phy_free_interrupt(struct phy_device *phydev); void phy_print_status(struct phy_device *phydev); int phy_set_max_speed(struct phy_device *phydev, u32 max_speed); void phy_remove_link_mode(struct phy_device *phydev, u32 link_mode); -- cgit v1.2.3 From 49644e68f472c6480e015253fa4d7448c6cfa2aa Mon Sep 17 00:00:00 2001 From: Heiner Kallweit Date: Thu, 30 May 2019 15:10:06 +0200 Subject: net: phy: add callback for custom interrupt handler to struct phy_driver The phylib interrupt handler handles link change events only currently. However PHY drivers may want to use other interrupt sources too, e.g. to report temperature monitoring events. Therefore add a callback to struct phy_driver allowing PHY drivers to implement a custom interrupt handler. Signed-off-by: Heiner Kallweit Suggested-by: Russell King - ARM Linux admin Acked-by: Russell King Signed-off-by: David S. Miller --- include/linux/phy.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include') diff --git a/include/linux/phy.h b/include/linux/phy.h index 72e1196f9799..16cd33915496 100644 --- a/include/linux/phy.h +++ b/include/linux/phy.h @@ -537,6 +537,9 @@ struct phy_driver { */ int (*did_interrupt)(struct phy_device *phydev); + /* Override default interrupt handling */ + int (*handle_interrupt)(struct phy_device *phydev); + /* Clears up any memory if needed */ void (*remove)(struct phy_device *phydev); -- cgit v1.2.3 From 97b33bdf9bddb6bebc2e87148df3e30aa7a13b2d Mon Sep 17 00:00:00 2001 From: Heiner Kallweit Date: Thu, 30 May 2019 15:11:06 +0200 Subject: net: phy: export phy_queue_state_machine We face the issue that link change interrupt and link status may be reported by different PHY layers. As a result the link change interrupt may occur before the link status changes. Export phy_queue_state_machine to allow PHY drivers to specify a delay between link status change interrupt and link status check. v2: - change jiffies parameter type to unsigned long Signed-off-by: Heiner Kallweit Suggested-by: Russell King Acked-by: Russell King Signed-off-by: David S. Miller --- include/linux/phy.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/phy.h b/include/linux/phy.h index 16cd33915496..dc4b51060ebc 100644 --- a/include/linux/phy.h +++ b/include/linux/phy.h @@ -188,7 +188,6 @@ static inline const char *phy_modes(phy_interface_t interface) #define PHY_INIT_TIMEOUT 100000 -#define PHY_STATE_TIME 1 #define PHY_FORCE_TIMEOUT 10 #define PHY_MAX_ADDR 32 @@ -1140,6 +1139,7 @@ int phy_driver_register(struct phy_driver *new_driver, struct module *owner); int phy_drivers_register(struct phy_driver *new_driver, int n, struct module *owner); void phy_state_machine(struct work_struct *work); +void phy_queue_state_machine(struct phy_device *phydev, unsigned long jiffies); void phy_mac_interrupt(struct phy_device *phydev); void phy_start_machine(struct phy_device *phydev); void phy_stop_machine(struct phy_device *phydev); -- cgit v1.2.3 From 9c3c0c2048149d946d7f3ebdcbe70e2946750bfb Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Thu, 18 Apr 2019 22:43:36 +0200 Subject: isdn: remove isdn4linux With all isdn4linux hardware drivers gone, this is only a wrapper around CAPI to support old user space. However, from looking at the mailing list, it seems that the last time anyone asked about it was in 2014, when the upgrade from a linux-2.4 installation failed, and mISDN was suggested as a replacement. The largest public ISDN network (Deutsche Telekom) was supposed to be shut down 2018, which must have drastically reduced the number of legacy installations. When we last discussed removing i4l in 2016, Karsten Keil suggested revisiting this in 2018. I guess this is overdue. Link: http://listserv.isdn4linux.de/pipermail/isdn4linux/2014-October/006165.html Link: https://patchwork.kernel.org/patch/8484861/#17900371 Link: https://listserv.isdn4linux.de/pipermail/isdn4linux/2019-April/thread.html Signed-off-by: Arnd Bergmann --- include/linux/concap.h | 112 -------- include/linux/isdn.h | 473 ---------------------------------- include/linux/isdn_divertif.h | 35 --- include/linux/isdn_ppp.h | 194 -------------- include/linux/isdnif.h | 505 ------------------------------------- include/linux/wanrouter.h | 11 - include/uapi/linux/isdn.h | 144 ----------- include/uapi/linux/isdn_divertif.h | 31 --- include/uapi/linux/isdn_ppp.h | 68 ----- include/uapi/linux/isdnif.h | 57 ----- include/uapi/linux/wanrouter.h | 18 -- 11 files changed, 1648 deletions(-) delete mode 100644 include/linux/concap.h delete mode 100644 include/linux/isdn.h delete mode 100644 include/linux/isdn_divertif.h delete mode 100644 include/linux/isdn_ppp.h delete mode 100644 include/linux/isdnif.h delete mode 100644 include/linux/wanrouter.h delete mode 100644 include/uapi/linux/isdn.h delete mode 100644 include/uapi/linux/isdn_divertif.h delete mode 100644 include/uapi/linux/isdn_ppp.h delete mode 100644 include/uapi/linux/isdnif.h delete mode 100644 include/uapi/linux/wanrouter.h (limited to 'include') diff --git a/include/linux/concap.h b/include/linux/concap.h deleted file mode 100644 index 977acb3d1fb2..000000000000 --- a/include/linux/concap.h +++ /dev/null @@ -1,112 +0,0 @@ -/* $Id: concap.h,v 1.3.2.2 2004/01/12 23:08:35 keil Exp $ - * - * Copyright 1997 by Henner Eisen - * - * This software may be used and distributed according to the terms - * of the GNU General Public License, incorporated herein by reference. - */ - -#ifndef _LINUX_CONCAP_H -#define _LINUX_CONCAP_H - -#include -#include - -/* Stuff to support encapsulation protocols genericly. The encapsulation - protocol is processed at the uppermost layer of the network interface. - - Based on a ideas developed in a 'synchronous device' thread in the - linux-x25 mailing list contributed by Alan Cox, Thomasz Motylewski - and Jonathan Naylor. - - For more documetation on this refer to Documentation/isdn/README.concap -*/ - -struct concap_proto_ops; -struct concap_device_ops; - -/* this manages all data needed by the encapsulation protocol - */ -struct concap_proto{ - struct net_device *net_dev; /* net device using our service */ - struct concap_device_ops *dops; /* callbacks provided by device */ - struct concap_proto_ops *pops; /* callbacks provided by us */ - spinlock_t lock; - int flags; - void *proto_data; /* protocol specific private data, to - be accessed via *pops methods only*/ - /* - : - whatever - : - */ -}; - -/* Operations to be supported by the net device. Called by the encapsulation - * protocol entity. No receive method is offered because the encapsulation - * protocol directly calls netif_rx(). - */ -struct concap_device_ops{ - - /* to request data is submitted by device*/ - int (*data_req)(struct concap_proto *, struct sk_buff *); - - /* Control methods must be set to NULL by devices which do not - support connection control.*/ - /* to request a connection is set up */ - int (*connect_req)(struct concap_proto *); - - /* to request a connection is released */ - int (*disconn_req)(struct concap_proto *); -}; - -/* Operations to be supported by the encapsulation protocol. Called by - * device driver. - */ -struct concap_proto_ops{ - - /* create a new encapsulation protocol instance of same type */ - struct concap_proto * (*proto_new) (void); - - /* delete encapsulation protocol instance and free all its resources. - cprot may no loger be referenced after calling this */ - void (*proto_del)(struct concap_proto *cprot); - - /* initialize the protocol's data. To be called at interface startup - or when the device driver resets the interface. All services of the - encapsulation protocol may be used after this*/ - int (*restart)(struct concap_proto *cprot, - struct net_device *ndev, - struct concap_device_ops *dops); - - /* inactivate an encapsulation protocol instance. The encapsulation - protocol may not call any *dops methods after this. */ - int (*close)(struct concap_proto *cprot); - - /* process a frame handed down to us by upper layer */ - int (*encap_and_xmit)(struct concap_proto *cprot, struct sk_buff *skb); - - /* to be called for each data entity received from lower layer*/ - int (*data_ind)(struct concap_proto *cprot, struct sk_buff *skb); - - /* to be called when a connection was set up/down. - Protocols that don't process these primitives might fill in - dummy methods here */ - int (*connect_ind)(struct concap_proto *cprot); - int (*disconn_ind)(struct concap_proto *cprot); - /* - Some network device support functions, like net_header(), rebuild_header(), - and others, that depend solely on the encapsulation protocol, might - be provided here, too. The net device would just fill them in its - corresponding fields when it is opened. - */ -}; - -/* dummy restart/close/connect/reset/disconn methods - */ -extern int concap_nop(struct concap_proto *cprot); - -/* dummy submit method - */ -extern int concap_drop_skb(struct concap_proto *cprot, struct sk_buff *skb); -#endif diff --git a/include/linux/isdn.h b/include/linux/isdn.h deleted file mode 100644 index df97c8444f5d..000000000000 --- a/include/linux/isdn.h +++ /dev/null @@ -1,473 +0,0 @@ -/* $Id: isdn.h,v 1.125.2.3 2004/02/10 01:07:14 keil Exp $ - * - * Main header for the Linux ISDN subsystem (linklevel). - * - * Copyright 1994,95,96 by Fritz Elfert (fritz@isdn4linux.de) - * Copyright 1995,96 by Thinking Objects Software GmbH Wuerzburg - * Copyright 1995,96 by Michael Hipp (Michael.Hipp@student.uni-tuebingen.de) - * - * This software may be used and distributed according to the terms - * of the GNU General Public License, incorporated herein by reference. - * - */ -#ifndef __ISDN_H__ -#define __ISDN_H__ - - -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include - -#define ISDN_TTY_MAJOR 43 -#define ISDN_TTYAUX_MAJOR 44 -#define ISDN_MAJOR 45 - -/* The minor-devicenumbers for Channel 0 and 1 are used as arguments for - * physical Channel-Mapping, so they MUST NOT be changed without changing - * the correspondent code in isdn.c - */ - -#define ISDN_MINOR_B 0 -#define ISDN_MINOR_BMAX (ISDN_MAX_CHANNELS-1) -#define ISDN_MINOR_CTRL 64 -#define ISDN_MINOR_CTRLMAX (64 + (ISDN_MAX_CHANNELS-1)) -#define ISDN_MINOR_PPP 128 -#define ISDN_MINOR_PPPMAX (128 + (ISDN_MAX_CHANNELS-1)) -#define ISDN_MINOR_STATUS 255 - -#ifdef CONFIG_ISDN_PPP - -#ifdef CONFIG_ISDN_PPP_VJ -# include -#endif - -#include -#include - -#include -#endif - -#ifdef CONFIG_ISDN_X25 -# include -#endif - -#include - -#define ISDN_DRVIOCTL_MASK 0x7f /* Mask for Device-ioctl */ - -/* Until now unused */ -#define ISDN_SERVICE_VOICE 1 -#define ISDN_SERVICE_AB 1<<1 -#define ISDN_SERVICE_X21 1<<2 -#define ISDN_SERVICE_G4 1<<3 -#define ISDN_SERVICE_BTX 1<<4 -#define ISDN_SERVICE_DFUE 1<<5 -#define ISDN_SERVICE_X25 1<<6 -#define ISDN_SERVICE_TTX 1<<7 -#define ISDN_SERVICE_MIXED 1<<8 -#define ISDN_SERVICE_FW 1<<9 -#define ISDN_SERVICE_GTEL 1<<10 -#define ISDN_SERVICE_BTXN 1<<11 -#define ISDN_SERVICE_BTEL 1<<12 - -/* Macros checking plain usage */ -#define USG_NONE(x) ((x & ISDN_USAGE_MASK)==ISDN_USAGE_NONE) -#define USG_RAW(x) ((x & ISDN_USAGE_MASK)==ISDN_USAGE_RAW) -#define USG_MODEM(x) ((x & ISDN_USAGE_MASK)==ISDN_USAGE_MODEM) -#define USG_VOICE(x) ((x & ISDN_USAGE_MASK)==ISDN_USAGE_VOICE) -#define USG_NET(x) ((x & ISDN_USAGE_MASK)==ISDN_USAGE_NET) -#define USG_FAX(x) ((x & ISDN_USAGE_MASK)==ISDN_USAGE_FAX) -#define USG_OUTGOING(x) ((x & ISDN_USAGE_OUTGOING)==ISDN_USAGE_OUTGOING) -#define USG_MODEMORVOICE(x) (((x & ISDN_USAGE_MASK)==ISDN_USAGE_MODEM) || \ - ((x & ISDN_USAGE_MASK)==ISDN_USAGE_VOICE) ) - -/* Timer-delays and scheduling-flags */ -#define ISDN_TIMER_RES 4 /* Main Timer-Resolution */ -#define ISDN_TIMER_02SEC (HZ/ISDN_TIMER_RES/5) /* Slow-Timer1 .2 sec */ -#define ISDN_TIMER_1SEC (HZ/ISDN_TIMER_RES) /* Slow-Timer2 1 sec */ -#define ISDN_TIMER_RINGING 5 /* tty RINGs = ISDN_TIMER_1SEC * this factor */ -#define ISDN_TIMER_KEEPINT 10 /* Cisco-Keepalive = ISDN_TIMER_1SEC * this factor */ -#define ISDN_TIMER_MODEMREAD 1 -#define ISDN_TIMER_MODEMPLUS 2 -#define ISDN_TIMER_MODEMRING 4 -#define ISDN_TIMER_MODEMXMIT 8 -#define ISDN_TIMER_NETDIAL 16 -#define ISDN_TIMER_NETHANGUP 32 -#define ISDN_TIMER_CARRIER 256 /* Wait for Carrier */ -#define ISDN_TIMER_FAST (ISDN_TIMER_MODEMREAD | ISDN_TIMER_MODEMPLUS | \ - ISDN_TIMER_MODEMXMIT) -#define ISDN_TIMER_SLOW (ISDN_TIMER_MODEMRING | ISDN_TIMER_NETHANGUP | \ - ISDN_TIMER_NETDIAL | ISDN_TIMER_CARRIER) - -/* Timeout-Values for isdn_net_dial() */ -#define ISDN_TIMER_DTIMEOUT10 (10*HZ/(ISDN_TIMER_02SEC*(ISDN_TIMER_RES+1))) -#define ISDN_TIMER_DTIMEOUT15 (15*HZ/(ISDN_TIMER_02SEC*(ISDN_TIMER_RES+1))) -#define ISDN_TIMER_DTIMEOUT60 (60*HZ/(ISDN_TIMER_02SEC*(ISDN_TIMER_RES+1))) - -/* GLOBAL_FLAGS */ -#define ISDN_GLOBAL_STOPPED 1 - -/*=================== Start of ip-over-ISDN stuff =========================*/ - -/* Feature- and status-flags for a net-interface */ -#define ISDN_NET_CONNECTED 0x01 /* Bound to ISDN-Channel */ -#define ISDN_NET_SECURE 0x02 /* Accept calls from phonelist only */ -#define ISDN_NET_CALLBACK 0x04 /* activate callback */ -#define ISDN_NET_CBHUP 0x08 /* hangup before callback */ -#define ISDN_NET_CBOUT 0x10 /* remote machine does callback */ - -#define ISDN_NET_MAGIC 0x49344C02 /* for paranoia-checking */ - -/* Phone-list-element */ -typedef struct { - void *next; - char num[ISDN_MSNLEN]; -} isdn_net_phone; - -/* - Principles when extending structures for generic encapsulation protocol - ("concap") support: - - Stuff which is hardware specific (here i4l-specific) goes in - the netdev -> local structure (here: isdn_net_local) - - Stuff which is encapsulation protocol specific goes in the structure - which holds the linux device structure (here: isdn_net_device) -*/ - -/* Local interface-data */ -typedef struct isdn_net_local_s { - ulong magic; - struct net_device_stats stats; /* Ethernet Statistics */ - int isdn_device; /* Index to isdn-device */ - int isdn_channel; /* Index to isdn-channel */ - int ppp_slot; /* PPPD device slot number */ - int pre_device; /* Preselected isdn-device */ - int pre_channel; /* Preselected isdn-channel */ - int exclusive; /* If non-zero idx to reserved chan.*/ - int flags; /* Connection-flags */ - int dialretry; /* Counter for Dialout-retries */ - int dialmax; /* Max. Number of Dial-retries */ - int cbdelay; /* Delay before Callback starts */ - int dtimer; /* Timeout-counter for dialing */ - char msn[ISDN_MSNLEN]; /* MSNs/EAZs for this interface */ - u_char cbhup; /* Flag: Reject Call before Callback*/ - u_char dialstate; /* State for dialing */ - u_char p_encap; /* Packet encapsulation */ - /* 0 = Ethernet over ISDN */ - /* 1 = RAW-IP */ - /* 2 = IP with type field */ - u_char l2_proto; /* Layer-2-protocol */ - /* See ISDN_PROTO_L2..-constants in */ - /* isdnif.h */ - /* 0 = X75/LAPB with I-Frames */ - /* 1 = X75/LAPB with UI-Frames */ - /* 2 = X75/LAPB with BUI-Frames */ - /* 3 = HDLC */ - u_char l3_proto; /* Layer-3-protocol */ - /* See ISDN_PROTO_L3..-constants in */ - /* isdnif.h */ - /* 0 = Transparent */ - int huptimer; /* Timeout-counter for auto-hangup */ - int charge; /* Counter for charging units */ - ulong chargetime; /* Timer for Charging info */ - int hupflags; /* Flags for charge-unit-hangup: */ - /* bit0: chargeint is invalid */ - /* bit1: Getting charge-interval */ - /* bit2: Do charge-unit-hangup */ - /* bit3: Do hangup even on incoming */ - int outgoing; /* Flag: outgoing call */ - int onhtime; /* Time to keep link up */ - int chargeint; /* Interval between charge-infos */ - int onum; /* Flag: at least 1 outgoing number */ - int cps; /* current speed of this interface */ - int transcount; /* byte-counter for cps-calculation */ - int sqfull; /* Flag: netdev-queue overloaded */ - ulong sqfull_stamp; /* Start-Time of overload */ - ulong slavedelay; /* Dynamic bundling delaytime */ - int triggercps; /* BogoCPS needed for trigger slave */ - isdn_net_phone *phone[2]; /* List of remote-phonenumbers */ - /* phone[0] = Incoming Numbers */ - /* phone[1] = Outgoing Numbers */ - isdn_net_phone *dial; /* Pointer to dialed number */ - struct net_device *master; /* Ptr to Master device for slaves */ - struct net_device *slave; /* Ptr to Slave device for masters */ - struct isdn_net_local_s *next; /* Ptr to next link in bundle */ - struct isdn_net_local_s *last; /* Ptr to last link in bundle */ - struct isdn_net_dev_s *netdev; /* Ptr to netdev */ - struct sk_buff_head super_tx_queue; /* List of supervisory frames to */ - /* be transmitted asap */ - atomic_t frame_cnt; /* number of frames currently */ - /* queued in HL driver */ - /* Ptr to orig. hard_header_cache */ - spinlock_t xmit_lock; /* used to protect the xmit path of */ - /* a particular channel (including */ - /* the frame_cnt */ - - int pppbind; /* ippp device for bindings */ - int dialtimeout; /* How long shall we try on dialing? (jiffies) */ - int dialwait; /* How long shall we wait after failed attempt? (jiffies) */ - ulong dialstarted; /* jiffies of first dialing-attempt */ - ulong dialwait_timer; /* jiffies of earliest next dialing-attempt */ - int huptimeout; /* How long will the connection be up? (seconds) */ -#ifdef CONFIG_ISDN_X25 - struct concap_device_ops *dops; /* callbacks used by encapsulator */ -#endif - /* use an own struct for that in later versions */ - ulong cisco_myseq; /* Local keepalive seq. for Cisco */ - ulong cisco_mineseen; /* returned keepalive seq. from remote */ - ulong cisco_yourseq; /* Remote keepalive seq. for Cisco */ - int cisco_keepalive_period; /* keepalive period */ - ulong cisco_last_slarp_in; /* jiffie of last keepalive packet we received */ - char cisco_line_state; /* state of line according to keepalive packets */ - char cisco_debserint; /* debugging flag of cisco hdlc with slarp */ - struct timer_list cisco_timer; - struct work_struct tqueue; -} isdn_net_local; - -/* the interface itself */ -typedef struct isdn_net_dev_s { - isdn_net_local *local; - isdn_net_local *queue; /* circular list of all bundled - channels, which are currently - online */ - spinlock_t queue_lock; /* lock to protect queue */ - void *next; /* Pointer to next isdn-interface */ - struct net_device *dev; /* interface to upper levels */ -#ifdef CONFIG_ISDN_PPP - ippp_bundle * pb; /* pointer to the common bundle structure - * with the per-bundle data */ -#endif -#ifdef CONFIG_ISDN_X25 - struct concap_proto *cprot; /* connection oriented encapsulation protocol */ -#endif - -} isdn_net_dev; - -/*===================== End of ip-over-ISDN stuff ===========================*/ - -/*======================= Start of ISDN-tty stuff ===========================*/ - -#define ISDN_ASYNC_MAGIC 0x49344C01 /* for paranoia-checking */ -#define ISDN_SERIAL_XMIT_SIZE 1024 /* Default bufsize for write */ -#define ISDN_SERIAL_XMIT_MAX 4000 /* Maximum bufsize for write */ - -#ifdef CONFIG_ISDN_AUDIO -/* For using sk_buffs with audio we need some private variables - * within each sk_buff. For this purpose, we declare a struct here, - * and put it always at the private skb->cb data array. A few macros help - * accessing the variables. - */ -typedef struct _isdn_audio_data { - unsigned short dle_count; - unsigned char lock; -} isdn_audio_data_t; - -#define ISDN_AUDIO_SKB_DLECOUNT(skb) (((isdn_audio_data_t *)&skb->cb[0])->dle_count) -#define ISDN_AUDIO_SKB_LOCK(skb) (((isdn_audio_data_t *)&skb->cb[0])->lock) -#endif - -/* Private data of AT-command-interpreter */ -typedef struct atemu { - u_char profile[ISDN_MODEM_NUMREG]; /* Modem-Regs. Profile 0 */ - u_char mdmreg[ISDN_MODEM_NUMREG]; /* Modem-Registers */ - char pmsn[ISDN_MSNLEN]; /* EAZ/MSNs Profile 0 */ - char msn[ISDN_MSNLEN]; /* EAZ/MSN */ - char plmsn[ISDN_LMSNLEN]; /* Listening MSNs Profile 0 */ - char lmsn[ISDN_LMSNLEN]; /* Listening MSNs */ - char cpn[ISDN_MSNLEN]; /* CalledPartyNumber on incoming call */ - char connmsg[ISDN_CMSGLEN]; /* CONNECT-Msg from HL-Driver */ -#ifdef CONFIG_ISDN_AUDIO - u_char vpar[10]; /* Voice-parameters */ - int lastDLE; /* Flag for voice-coding: DLE seen */ -#endif - int mdmcmdl; /* Length of Modem-Commandbuffer */ - int pluscount; /* Counter for +++ sequence */ - u_long lastplus; /* Timestamp of last + */ - int carrierwait; /* Seconds of carrier waiting */ - char mdmcmd[255]; /* Modem-Commandbuffer */ - unsigned int charge; /* Charge units of current connection */ -} atemu; - -/* Private data (similar to async_struct in ) */ -typedef struct modem_info { - int magic; - struct tty_port port; - int x_char; /* xon/xoff character */ - int mcr; /* Modem control register */ - int msr; /* Modem status register */ - int lsr; /* Line status register */ - int line; - int online; /* 1 = B-Channel is up, drop data */ - /* 2 = B-Channel is up, deliver d.*/ - int dialing; /* Dial in progress or ATA */ - int closing; - int rcvsched; /* Receive needs schedule */ - int isdn_driver; /* Index to isdn-driver */ - int isdn_channel; /* Index to isdn-channel */ - int drv_index; /* Index to dev->usage */ - int ncarrier; /* Flag: schedule NO CARRIER */ - unsigned char last_cause[8]; /* Last cause message */ - unsigned char last_num[ISDN_MSNLEN]; - /* Last phone-number */ - unsigned char last_l2; /* Last layer-2 protocol */ - unsigned char last_si; /* Last service */ - unsigned char last_lhup; /* Last hangup local? */ - unsigned char last_dir; /* Last direction (in or out) */ - struct timer_list nc_timer; /* Timer for delayed NO CARRIER */ - int send_outstanding;/* # of outstanding send-requests */ - int xmit_size; /* max. # of chars in xmit_buf */ - int xmit_count; /* # of chars in xmit_buf */ - struct sk_buff_head xmit_queue; /* transmit queue */ - atomic_t xmit_lock; /* Semaphore for isdn_tty_write */ -#ifdef CONFIG_ISDN_AUDIO - int vonline; /* Voice-channel status */ - /* Bit 0 = recording */ - /* Bit 1 = playback */ - /* Bit 2 = playback, DLE-ETX seen */ - struct sk_buff_head dtmf_queue; /* queue for dtmf results */ - void *adpcms; /* state for adpcm decompression */ - void *adpcmr; /* state for adpcm compression */ - void *dtmf_state; /* state for dtmf decoder */ - void *silence_state; /* state for silence detection */ -#endif -#ifdef CONFIG_ISDN_TTY_FAX - struct T30_s *fax; /* T30 Fax Group 3 data/interface */ - int faxonline; /* Fax-channel status */ -#endif - atemu emu; /* AT-emulator data */ - spinlock_t readlock; -} modem_info; - -#define ISDN_MODEM_WINSIZE 8 - -/* Description of one ISDN-tty */ -typedef struct _isdn_modem { - int refcount; /* Number of opens */ - struct tty_driver *tty_modem; /* tty-device */ - struct tty_struct *modem_table[ISDN_MAX_CHANNELS]; /* ?? copied from Orig */ - struct ktermios *modem_termios[ISDN_MAX_CHANNELS]; - struct ktermios *modem_termios_locked[ISDN_MAX_CHANNELS]; - modem_info info[ISDN_MAX_CHANNELS]; /* Private data */ -} isdn_modem_t; - -/*======================= End of ISDN-tty stuff ============================*/ - -/*======================== Start of V.110 stuff ============================*/ -#define V110_BUFSIZE 1024 - -typedef struct { - int nbytes; /* 1 Matrixbyte -> nbytes in stream */ - int nbits; /* Number of used bits in streambyte */ - unsigned char key; /* Bitmask in stream eg. 11 (nbits=2) */ - int decodelen; /* Amount of data in decodebuf */ - int SyncInit; /* Number of sync frames to send */ - unsigned char *OnlineFrame; /* Precalculated V110 idle frame */ - unsigned char *OfflineFrame; /* Precalculated V110 sync Frame */ - int framelen; /* Length of frames */ - int skbuser; /* Number of unacked userdata skbs */ - int skbidle; /* Number of unacked idle/sync skbs */ - int introducer; /* Local vars for decoder */ - int dbit; - unsigned char b; - int skbres; /* space to reserve in outgoing skb */ - int maxsize; /* maxbufsize of lowlevel driver */ - unsigned char *encodebuf; /* temporary buffer for encoding */ - unsigned char decodebuf[V110_BUFSIZE]; /* incomplete V110 matrices */ -} isdn_v110_stream; - -/*========================= End of V.110 stuff =============================*/ - -/*======================= Start of general stuff ===========================*/ - -typedef struct { - char *next; - char *private; -} infostruct; - -#define DRV_FLAG_RUNNING 1 -#define DRV_FLAG_REJBUS 2 -#define DRV_FLAG_LOADED 4 - -/* Description of hardware-level-driver */ -typedef struct _isdn_driver { - ulong online; /* Channel-Online flags */ - ulong flags; /* Misc driver Flags */ - int locks; /* Number of locks for this driver */ - int channels; /* Number of channels */ - wait_queue_head_t st_waitq; /* Wait-Queue for status-read's */ - int maxbufsize; /* Maximum Buffersize supported */ - unsigned long pktcount; /* Until now: unused */ - int stavail; /* Chars avail on Status-device */ - isdn_if *interface; /* Interface to driver */ - int *rcverr; /* Error-counters for B-Ch.-receive */ - int *rcvcount; /* Byte-counters for B-Ch.-receive */ -#ifdef CONFIG_ISDN_AUDIO - unsigned long DLEflag; /* Flags: Insert DLE at next read */ -#endif - struct sk_buff_head *rpqueue; /* Pointers to start of Rcv-Queue */ - wait_queue_head_t *rcv_waitq; /* Wait-Queues for B-Channel-Reads */ - wait_queue_head_t *snd_waitq; /* Wait-Queue for B-Channel-Send's */ - char msn2eaz[10][ISDN_MSNLEN]; /* Mapping-Table MSN->EAZ */ -} isdn_driver_t; - -/* Main driver-data */ -typedef struct isdn_devt { - struct module *owner; - spinlock_t lock; - unsigned short flags; /* Bitmapped Flags: */ - int drivers; /* Current number of drivers */ - int channels; /* Current number of channels */ - int net_verbose; /* Verbose-Flag */ - int modempoll; /* Flag: tty-read active */ - spinlock_t timerlock; - int tflags; /* Timer-Flags: */ - /* see ISDN_TIMER_..defines */ - int global_flags; - infostruct *infochain; /* List of open info-devs. */ - wait_queue_head_t info_waitq; /* Wait-Queue for isdninfo */ - struct timer_list timer; /* Misc.-function Timer */ - int chanmap[ISDN_MAX_CHANNELS]; /* Map minor->device-channel */ - int drvmap[ISDN_MAX_CHANNELS]; /* Map minor->driver-index */ - int usage[ISDN_MAX_CHANNELS]; /* Used by tty/ip/voice */ - char num[ISDN_MAX_CHANNELS][ISDN_MSNLEN]; - /* Remote number of active ch.*/ - int m_idx[ISDN_MAX_CHANNELS]; /* Index for mdm.... */ - isdn_driver_t *drv[ISDN_MAX_DRIVERS]; /* Array of drivers */ - isdn_net_dev *netdev; /* Linked list of net-if's */ - char drvid[ISDN_MAX_DRIVERS][20];/* Driver-ID */ - struct task_struct *profd; /* For iprofd */ - isdn_modem_t mdm; /* tty-driver-data */ - isdn_net_dev *rx_netdev[ISDN_MAX_CHANNELS]; /* rx netdev-pointers */ - isdn_net_dev *st_netdev[ISDN_MAX_CHANNELS]; /* stat netdev-pointers */ - ulong ibytes[ISDN_MAX_CHANNELS]; /* Statistics incoming bytes */ - ulong obytes[ISDN_MAX_CHANNELS]; /* Statistics outgoing bytes */ - int v110emu[ISDN_MAX_CHANNELS]; /* V.110 emulator-mode 0=none */ - atomic_t v110use[ISDN_MAX_CHANNELS]; /* Usage-Semaphore for stream */ - isdn_v110_stream *v110[ISDN_MAX_CHANNELS]; /* V.110 private data */ - struct mutex mtx; /* serialize list access*/ - unsigned long global_features; -} isdn_dev; - -extern isdn_dev *dev; - - -#endif /* __ISDN_H__ */ diff --git a/include/linux/isdn_divertif.h b/include/linux/isdn_divertif.h deleted file mode 100644 index 19ab361f9f07..000000000000 --- a/include/linux/isdn_divertif.h +++ /dev/null @@ -1,35 +0,0 @@ -/* $Id: isdn_divertif.h,v 1.4.6.1 2001/09/23 22:25:05 kai Exp $ - * - * Header for the diversion supplementary interface for i4l. - * - * Author Werner Cornelius (werner@titro.de) - * Copyright by Werner Cornelius (werner@titro.de) - * - * This software may be used and distributed according to the terms - * of the GNU General Public License, incorporated herein by reference. - * - */ -#ifndef _LINUX_ISDN_DIVERTIF_H -#define _LINUX_ISDN_DIVERTIF_H - -#include -#include -#include - -/***************************************************************/ -/* structure exchanging data between isdn hl and divert module */ -/***************************************************************/ -typedef struct - { ulong if_magic; /* magic info and version */ - int cmd; /* command */ - int (*stat_callback)(isdn_ctrl *); /* supplied by divert module when calling */ - int (*ll_cmd)(isdn_ctrl *); /* supplied by hl on return */ - char * (*drv_to_name)(int); /* map a driver id to name, supplied by hl */ - int (*name_to_drv)(char *); /* map a driver id to name, supplied by hl */ - } isdn_divert_if; - -/*********************/ -/* function register */ -/*********************/ -extern int DIVERT_REG_NAME(isdn_divert_if *); -#endif /* _LINUX_ISDN_DIVERTIF_H */ diff --git a/include/linux/isdn_ppp.h b/include/linux/isdn_ppp.h deleted file mode 100644 index a0070c6dfaf8..000000000000 --- a/include/linux/isdn_ppp.h +++ /dev/null @@ -1,194 +0,0 @@ -/* Linux ISDN subsystem, sync PPP, interface to ipppd - * - * Copyright 1994-1999 by Fritz Elfert (fritz@isdn4linux.de) - * Copyright 1995,96 Thinking Objects Software GmbH Wuerzburg - * Copyright 1995,96 by Michael Hipp (Michael.Hipp@student.uni-tuebingen.de) - * Copyright 2000-2002 by Kai Germaschewski (kai@germaschewski.name) - * - * This software may be used and distributed according to the terms - * of the GNU General Public License, incorporated herein by reference. - * - */ -#ifndef _LINUX_ISDN_PPP_H -#define _LINUX_ISDN_PPP_H - - - - -#ifdef CONFIG_IPPP_FILTER -#include -#endif -#include - -#define DECOMP_ERR_NOMEM (-10) - -#define MP_END_FRAG 0x40 -#define MP_BEGIN_FRAG 0x80 - -#define MP_MAX_QUEUE_LEN 16 - -/* - * We need a way for the decompressor to influence the generation of CCP - * Reset-Requests in a variety of ways. The decompressor is already returning - * a lot of information (generated skb length, error conditions) so we use - * another parameter. This parameter is a pointer to a structure which is - * to be marked valid by the decompressor and only in this case is ever used. - * Furthermore, the only case where this data is used is when the decom- - * pressor returns DECOMP_ERROR. - * - * We use this same struct for the reset entry of the compressor to commu- - * nicate to its caller how to deal with sending of a Reset Ack. In this - * case, expra is not used, but other options still apply (suppressing - * sending with rsend, appending arbitrary data, etc). - */ - -#define IPPP_RESET_MAXDATABYTES 32 - -struct isdn_ppp_resetparams { - unsigned char valid:1; /* rw Is this structure filled at all ? */ - unsigned char rsend:1; /* rw Should we send one at all ? */ - unsigned char idval:1; /* rw Is the id field valid ? */ - unsigned char dtval:1; /* rw Is the data field valid ? */ - unsigned char expra:1; /* rw Is an Ack expected for this Req ? */ - unsigned char id; /* wo Send CCP ResetReq with this id */ - unsigned short maxdlen; /* ro Max bytes to be stored in data field */ - unsigned short dlen; /* rw Bytes stored in data field */ - unsigned char *data; /* wo Data for ResetReq info field */ -}; - -/* - * this is an 'old friend' from ppp-comp.h under a new name - * check the original include for more information - */ -struct isdn_ppp_compressor { - struct isdn_ppp_compressor *next, *prev; - struct module *owner; - int num; /* CCP compression protocol number */ - - void *(*alloc) (struct isdn_ppp_comp_data *); - void (*free) (void *state); - int (*init) (void *state, struct isdn_ppp_comp_data *, - int unit,int debug); - - /* The reset entry needs to get more exact information about the - ResetReq or ResetAck it was called with. The parameters are - obvious. If reset is called without a Req or Ack frame which - could be handed into it, code MUST be set to 0. Using rsparm, - the reset entry can control if and how a ResetAck is returned. */ - - void (*reset) (void *state, unsigned char code, unsigned char id, - unsigned char *data, unsigned len, - struct isdn_ppp_resetparams *rsparm); - - int (*compress) (void *state, struct sk_buff *in, - struct sk_buff *skb_out, int proto); - - int (*decompress) (void *state,struct sk_buff *in, - struct sk_buff *skb_out, - struct isdn_ppp_resetparams *rsparm); - - void (*incomp) (void *state, struct sk_buff *in,int proto); - void (*stat) (void *state, struct compstat *stats); -}; - -extern int isdn_ppp_register_compressor(struct isdn_ppp_compressor *); -extern int isdn_ppp_unregister_compressor(struct isdn_ppp_compressor *); -extern int isdn_ppp_dial_slave(char *); -extern int isdn_ppp_hangup_slave(char *); - -typedef struct { - unsigned long seqerrs; - unsigned long frame_drops; - unsigned long overflows; - unsigned long max_queue_len; -} isdn_mppp_stats; - -typedef struct { - int mp_mrru; /* unused */ - struct sk_buff * frags; /* fragments sl list -- use skb->next */ - long frames; /* number of frames in the frame list */ - unsigned int seq; /* last processed packet seq #: any packets - * with smaller seq # will be dropped - * unconditionally */ - spinlock_t lock; - int ref_ct; - /* statistics */ - isdn_mppp_stats stats; -} ippp_bundle; - -#define NUM_RCV_BUFFS 64 - -struct ippp_buf_queue { - struct ippp_buf_queue *next; - struct ippp_buf_queue *last; - char *buf; /* NULL here indicates end of queue */ - int len; -}; - -/* The data structure for one CCP reset transaction */ -enum ippp_ccp_reset_states { - CCPResetIdle, - CCPResetSentReq, - CCPResetRcvdReq, - CCPResetSentAck, - CCPResetRcvdAck -}; - -struct ippp_ccp_reset_state { - enum ippp_ccp_reset_states state; /* State of this transaction */ - struct ippp_struct *is; /* Backlink to device stuff */ - unsigned char id; /* Backlink id index */ - unsigned char ta:1; /* The timer is active (flag) */ - unsigned char expra:1; /* We expect a ResetAck at all */ - int dlen; /* Databytes stored in data */ - struct timer_list timer; /* For timeouts/retries */ - /* This is a hack but seems sufficient for the moment. We do not want - to have this be yet another allocation for some bytes, it is more - memory management overhead than the whole mess is worth. */ - unsigned char data[IPPP_RESET_MAXDATABYTES]; -}; - -/* The data structure keeping track of the currently outstanding CCP Reset - transactions. */ -struct ippp_ccp_reset { - struct ippp_ccp_reset_state *rs[256]; /* One per possible id */ - unsigned char lastid; /* Last id allocated by the engine */ -}; - -struct ippp_struct { - struct ippp_struct *next_link; - int state; - spinlock_t buflock; - struct ippp_buf_queue rq[NUM_RCV_BUFFS]; /* packet queue for isdn_ppp_read() */ - struct ippp_buf_queue *first; /* pointer to (current) first packet */ - struct ippp_buf_queue *last; /* pointer to (current) last used packet in queue */ - wait_queue_head_t wq; - struct task_struct *tk; - unsigned int mpppcfg; - unsigned int pppcfg; - unsigned int mru; - unsigned int mpmru; - unsigned int mpmtu; - unsigned int maxcid; - struct isdn_net_local_s *lp; - int unit; - int minor; - unsigned int last_link_seqno; - long mp_seqno; -#ifdef CONFIG_ISDN_PPP_VJ - unsigned char *cbuf; - struct slcompress *slcomp; -#endif -#ifdef CONFIG_IPPP_FILTER - struct bpf_prog *pass_filter; /* filter for packets to pass */ - struct bpf_prog *active_filter; /* filter for pkts to reset idle */ -#endif - unsigned long debug; - struct isdn_ppp_compressor *compressor,*decompressor; - struct isdn_ppp_compressor *link_compressor,*link_decompressor; - void *decomp_stat,*comp_stat,*link_decomp_stat,*link_comp_stat; - struct ippp_ccp_reset *reset; /* Allocated on demand, may never be needed */ - unsigned long compflags; -}; - -#endif /* _LINUX_ISDN_PPP_H */ diff --git a/include/linux/isdnif.h b/include/linux/isdnif.h deleted file mode 100644 index 8d80fdc68647..000000000000 --- a/include/linux/isdnif.h +++ /dev/null @@ -1,505 +0,0 @@ -/* $Id: isdnif.h,v 1.43.2.2 2004/01/12 23:08:35 keil Exp $ - * - * Linux ISDN subsystem - * Definition of the interface between the subsystem and its low-level drivers. - * - * Copyright 1994,95,96 by Fritz Elfert (fritz@isdn4linux.de) - * Copyright 1995,96 Thinking Objects Software GmbH Wuerzburg - * - * This software may be used and distributed according to the terms - * of the GNU General Public License, incorporated herein by reference. - * - */ -#ifndef __ISDNIF_H__ -#define __ISDNIF_H__ - - -#include -#include - -/***************************************************************************/ -/* Extensions made by Werner Cornelius (werner@ikt.de) */ -/* */ -/* The proceed command holds a incoming call in a state to leave processes */ -/* enough time to check whether ist should be accepted. */ -/* The PROT_IO Command extends the interface to make protocol dependent */ -/* features available (call diversion, call waiting...). */ -/* */ -/* The PROT_IO Command is executed with the desired driver id and the arg */ -/* parameter coded as follows: */ -/* The lower 8 bits of arg contain the desired protocol from ISDN_PTYPE */ -/* definitions. The upper 24 bits represent the protocol specific cmd/stat.*/ -/* Any additional data is protocol and command specific. */ -/* This mechanism also applies to the statcallb callback STAT_PROT. */ -/* */ -/* This suggested extension permits an easy expansion of protocol specific */ -/* handling. Extensions may be added at any time without changing the HL */ -/* driver code and not getting conflicts without certifications. */ -/* The well known CAPI 2.0 interface handles such extensions in a similar */ -/* way. Perhaps a protocol specific module may be added and separately */ -/* loaded and linked to the basic isdn module for handling. */ -/***************************************************************************/ - -/*****************/ -/* DSS1 commands */ -/*****************/ -#define DSS1_CMD_INVOKE ((0x00 << 8) | ISDN_PTYPE_EURO) /* invoke a supplementary service */ -#define DSS1_CMD_INVOKE_ABORT ((0x01 << 8) | ISDN_PTYPE_EURO) /* abort a invoke cmd */ - -/*******************************/ -/* DSS1 Status callback values */ -/*******************************/ -#define DSS1_STAT_INVOKE_RES ((0x80 << 8) | ISDN_PTYPE_EURO) /* Result for invocation */ -#define DSS1_STAT_INVOKE_ERR ((0x81 << 8) | ISDN_PTYPE_EURO) /* Error Return for invocation */ -#define DSS1_STAT_INVOKE_BRD ((0x82 << 8) | ISDN_PTYPE_EURO) /* Deliver invoke broadcast info */ - - -/*********************************************************************/ -/* structures for DSS1 commands and callback */ -/* */ -/* An action is invoked by sending a DSS1_CMD_INVOKE. The ll_id, proc*/ -/* timeout, datalen and data fields must be set before calling. */ -/* */ -/* The return value is a positive hl_id value also delivered in the */ -/* hl_id field. A value of zero signals no more left hl_id capacitys.*/ -/* A negative return value signals errors in LL. So if the return */ -/* value is <= 0 no action in LL will be taken -> request ignored */ -/* */ -/* The timeout field must be filled with a positive value specifying */ -/* the amount of time the INVOKED process waits for a reaction from */ -/* the network. */ -/* If a response (either error or result) is received during this */ -/* intervall, a reporting callback is initiated and the process will */ -/* be deleted, the hl identifier will be freed. */ -/* If no response is received during the specified intervall, a error*/ -/* callback is initiated with timeout set to -1 and a datalen set */ -/* to 0. */ -/* If timeout is set to a value <= 0 during INVOCATION the process is*/ -/* immediately deleted after sending the data. No callback occurs ! */ -/* */ -/* A currently waiting process may be aborted with INVOKE_ABORT. No */ -/* callback will occur when a process has been aborted. */ -/* */ -/* Broadcast invoke frames from the network are reported via the */ -/* STAT_INVOKE_BRD callback. The ll_id is set to 0, the other fields */ -/* are supplied by the network and not by the HL. */ -/*********************************************************************/ - -/*****************/ -/* NI1 commands */ -/*****************/ -#define NI1_CMD_INVOKE ((0x00 << 8) | ISDN_PTYPE_NI1) /* invoke a supplementary service */ -#define NI1_CMD_INVOKE_ABORT ((0x01 << 8) | ISDN_PTYPE_NI1) /* abort a invoke cmd */ - -/*******************************/ -/* NI1 Status callback values */ -/*******************************/ -#define NI1_STAT_INVOKE_RES ((0x80 << 8) | ISDN_PTYPE_NI1) /* Result for invocation */ -#define NI1_STAT_INVOKE_ERR ((0x81 << 8) | ISDN_PTYPE_NI1) /* Error Return for invocation */ -#define NI1_STAT_INVOKE_BRD ((0x82 << 8) | ISDN_PTYPE_NI1) /* Deliver invoke broadcast info */ - -typedef struct - { ulong ll_id; /* ID supplied by LL when executing */ - /* a command and returned by HL for */ - /* INVOKE_RES and INVOKE_ERR */ - int hl_id; /* ID supplied by HL when called */ - /* for executing a cmd and delivered */ - /* for results and errors */ - /* must be supplied by LL when aborting*/ - int proc; /* invoke procedure used by CMD_INVOKE */ - /* returned by callback and broadcast */ - int timeout; /* timeout for INVOKE CMD in ms */ - /* -1 in stat callback when timed out */ - /* error value when error callback */ - int datalen; /* length of cmd or stat data */ - u_char *data;/* pointer to data delivered or send */ - } isdn_cmd_stat; - -/* - * Commands from linklevel to lowlevel - * - */ -#define ISDN_CMD_IOCTL 0 /* Perform ioctl */ -#define ISDN_CMD_DIAL 1 /* Dial out */ -#define ISDN_CMD_ACCEPTD 2 /* Accept an incoming call on D-Chan. */ -#define ISDN_CMD_ACCEPTB 3 /* Request B-Channel connect. */ -#define ISDN_CMD_HANGUP 4 /* Hangup */ -#define ISDN_CMD_CLREAZ 5 /* Clear EAZ(s) of channel */ -#define ISDN_CMD_SETEAZ 6 /* Set EAZ(s) of channel */ -#define ISDN_CMD_GETEAZ 7 /* Get EAZ(s) of channel */ -#define ISDN_CMD_SETSIL 8 /* Set Service-Indicator-List of channel */ -#define ISDN_CMD_GETSIL 9 /* Get Service-Indicator-List of channel */ -#define ISDN_CMD_SETL2 10 /* Set B-Chan. Layer2-Parameter */ -#define ISDN_CMD_GETL2 11 /* Get B-Chan. Layer2-Parameter */ -#define ISDN_CMD_SETL3 12 /* Set B-Chan. Layer3-Parameter */ -#define ISDN_CMD_GETL3 13 /* Get B-Chan. Layer3-Parameter */ -// #define ISDN_CMD_LOCK 14 /* Signal usage by upper levels */ -// #define ISDN_CMD_UNLOCK 15 /* Release usage-lock */ -#define ISDN_CMD_SUSPEND 16 /* Suspend connection */ -#define ISDN_CMD_RESUME 17 /* Resume connection */ -#define ISDN_CMD_PROCEED 18 /* Proceed with call establishment */ -#define ISDN_CMD_ALERT 19 /* Alert after Proceeding */ -#define ISDN_CMD_REDIR 20 /* Redir a incoming call */ -#define ISDN_CMD_PROT_IO 21 /* Protocol specific commands */ -#define CAPI_PUT_MESSAGE 22 /* CAPI message send down or up */ -#define ISDN_CMD_FAXCMD 23 /* FAX commands to HL-driver */ -#define ISDN_CMD_AUDIO 24 /* DSP, DTMF, ... settings */ - -/* - * Status-Values delivered from lowlevel to linklevel via - * statcallb(). - * - */ -#define ISDN_STAT_STAVAIL 256 /* Raw status-data available */ -#define ISDN_STAT_ICALL 257 /* Incoming call detected */ -#define ISDN_STAT_RUN 258 /* Signal protocol-code is running */ -#define ISDN_STAT_STOP 259 /* Signal halt of protocol-code */ -#define ISDN_STAT_DCONN 260 /* Signal D-Channel connect */ -#define ISDN_STAT_BCONN 261 /* Signal B-Channel connect */ -#define ISDN_STAT_DHUP 262 /* Signal D-Channel disconnect */ -#define ISDN_STAT_BHUP 263 /* Signal B-Channel disconnect */ -#define ISDN_STAT_CINF 264 /* Charge-Info */ -#define ISDN_STAT_LOAD 265 /* Signal new lowlevel-driver is loaded */ -#define ISDN_STAT_UNLOAD 266 /* Signal unload of lowlevel-driver */ -#define ISDN_STAT_BSENT 267 /* Signal packet sent */ -#define ISDN_STAT_NODCH 268 /* Signal no D-Channel */ -#define ISDN_STAT_ADDCH 269 /* Add more Channels */ -#define ISDN_STAT_CAUSE 270 /* Cause-Message */ -#define ISDN_STAT_ICALLW 271 /* Incoming call without B-chan waiting */ -#define ISDN_STAT_REDIR 272 /* Redir result */ -#define ISDN_STAT_PROT 273 /* protocol IO specific callback */ -#define ISDN_STAT_DISPLAY 274 /* deliver a received display message */ -#define ISDN_STAT_L1ERR 275 /* Signal Layer-1 Error */ -#define ISDN_STAT_FAXIND 276 /* FAX indications from HL-driver */ -#define ISDN_STAT_AUDIO 277 /* DTMF, DSP indications */ -#define ISDN_STAT_DISCH 278 /* Disable/Enable channel usage */ - -/* - * Audio commands - */ -#define ISDN_AUDIO_SETDD 0 /* Set DTMF detection */ -#define ISDN_AUDIO_DTMF 1 /* Rx/Tx DTMF */ - -/* - * Values for errcode field - */ -#define ISDN_STAT_L1ERR_SEND 1 -#define ISDN_STAT_L1ERR_RECV 2 - -/* - * Values for feature-field of interface-struct. - */ -/* Layer 2 */ -#define ISDN_FEATURE_L2_X75I (0x0001 << ISDN_PROTO_L2_X75I) -#define ISDN_FEATURE_L2_X75UI (0x0001 << ISDN_PROTO_L2_X75UI) -#define ISDN_FEATURE_L2_X75BUI (0x0001 << ISDN_PROTO_L2_X75BUI) -#define ISDN_FEATURE_L2_HDLC (0x0001 << ISDN_PROTO_L2_HDLC) -#define ISDN_FEATURE_L2_TRANS (0x0001 << ISDN_PROTO_L2_TRANS) -#define ISDN_FEATURE_L2_X25DTE (0x0001 << ISDN_PROTO_L2_X25DTE) -#define ISDN_FEATURE_L2_X25DCE (0x0001 << ISDN_PROTO_L2_X25DCE) -#define ISDN_FEATURE_L2_V11096 (0x0001 << ISDN_PROTO_L2_V11096) -#define ISDN_FEATURE_L2_V11019 (0x0001 << ISDN_PROTO_L2_V11019) -#define ISDN_FEATURE_L2_V11038 (0x0001 << ISDN_PROTO_L2_V11038) -#define ISDN_FEATURE_L2_MODEM (0x0001 << ISDN_PROTO_L2_MODEM) -#define ISDN_FEATURE_L2_FAX (0x0001 << ISDN_PROTO_L2_FAX) -#define ISDN_FEATURE_L2_HDLC_56K (0x0001 << ISDN_PROTO_L2_HDLC_56K) - -#define ISDN_FEATURE_L2_MASK (0x0FFFF) /* Max. 16 protocols */ -#define ISDN_FEATURE_L2_SHIFT (0) - -/* Layer 3 */ -#define ISDN_FEATURE_L3_TRANS (0x10000 << ISDN_PROTO_L3_TRANS) -#define ISDN_FEATURE_L3_TRANSDSP (0x10000 << ISDN_PROTO_L3_TRANSDSP) -#define ISDN_FEATURE_L3_FCLASS2 (0x10000 << ISDN_PROTO_L3_FCLASS2) -#define ISDN_FEATURE_L3_FCLASS1 (0x10000 << ISDN_PROTO_L3_FCLASS1) - -#define ISDN_FEATURE_L3_MASK (0x0FF0000) /* Max. 8 Protocols */ -#define ISDN_FEATURE_L3_SHIFT (16) - -/* Signaling */ -#define ISDN_FEATURE_P_UNKNOWN (0x1000000 << ISDN_PTYPE_UNKNOWN) -#define ISDN_FEATURE_P_1TR6 (0x1000000 << ISDN_PTYPE_1TR6) -#define ISDN_FEATURE_P_EURO (0x1000000 << ISDN_PTYPE_EURO) -#define ISDN_FEATURE_P_NI1 (0x1000000 << ISDN_PTYPE_NI1) - -#define ISDN_FEATURE_P_MASK (0x0FF000000) /* Max. 8 Protocols */ -#define ISDN_FEATURE_P_SHIFT (24) - -typedef struct setup_parm { - unsigned char phone[32]; /* Remote Phone-Number */ - unsigned char eazmsn[32]; /* Local EAZ or MSN */ - unsigned char si1; /* Service Indicator 1 */ - unsigned char si2; /* Service Indicator 2 */ - unsigned char plan; /* Numbering plan */ - unsigned char screen; /* Screening info */ -} setup_parm; - - -#ifdef CONFIG_ISDN_TTY_FAX -/* T.30 Fax G3 */ - -#define FAXIDLEN 21 - -typedef struct T30_s { - /* session parameters */ - __u8 resolution; - __u8 rate; - __u8 width; - __u8 length; - __u8 compression; - __u8 ecm; - __u8 binary; - __u8 scantime; - __u8 id[FAXIDLEN]; - /* additional parameters */ - __u8 phase; - __u8 direction; - __u8 code; - __u8 badlin; - __u8 badmul; - __u8 bor; - __u8 fet; - __u8 pollid[FAXIDLEN]; - __u8 cq; - __u8 cr; - __u8 ctcrty; - __u8 minsp; - __u8 phcto; - __u8 rel; - __u8 nbc; - /* remote station parameters */ - __u8 r_resolution; - __u8 r_rate; - __u8 r_width; - __u8 r_length; - __u8 r_compression; - __u8 r_ecm; - __u8 r_binary; - __u8 r_scantime; - __u8 r_id[FAXIDLEN]; - __u8 r_code; -} __packed T30_s; - -#define ISDN_TTY_FAX_CONN_IN 0 -#define ISDN_TTY_FAX_CONN_OUT 1 - -#define ISDN_TTY_FAX_FCON 0 -#define ISDN_TTY_FAX_DIS 1 -#define ISDN_TTY_FAX_FTT 2 -#define ISDN_TTY_FAX_MCF 3 -#define ISDN_TTY_FAX_DCS 4 -#define ISDN_TTY_FAX_TRAIN_OK 5 -#define ISDN_TTY_FAX_EOP 6 -#define ISDN_TTY_FAX_EOM 7 -#define ISDN_TTY_FAX_MPS 8 -#define ISDN_TTY_FAX_DTC 9 -#define ISDN_TTY_FAX_RID 10 -#define ISDN_TTY_FAX_HNG 11 -#define ISDN_TTY_FAX_DT 12 -#define ISDN_TTY_FAX_FCON_I 13 -#define ISDN_TTY_FAX_DR 14 -#define ISDN_TTY_FAX_ET 15 -#define ISDN_TTY_FAX_CFR 16 -#define ISDN_TTY_FAX_PTS 17 -#define ISDN_TTY_FAX_SENT 18 - -#define ISDN_FAX_PHASE_IDLE 0 -#define ISDN_FAX_PHASE_A 1 -#define ISDN_FAX_PHASE_B 2 -#define ISDN_FAX_PHASE_C 3 -#define ISDN_FAX_PHASE_D 4 -#define ISDN_FAX_PHASE_E 5 - -#endif /* TTY_FAX */ - -#define ISDN_FAX_CLASS1_FAE 0 -#define ISDN_FAX_CLASS1_FTS 1 -#define ISDN_FAX_CLASS1_FRS 2 -#define ISDN_FAX_CLASS1_FTM 3 -#define ISDN_FAX_CLASS1_FRM 4 -#define ISDN_FAX_CLASS1_FTH 5 -#define ISDN_FAX_CLASS1_FRH 6 -#define ISDN_FAX_CLASS1_CTRL 7 - -#define ISDN_FAX_CLASS1_OK 0 -#define ISDN_FAX_CLASS1_CONNECT 1 -#define ISDN_FAX_CLASS1_NOCARR 2 -#define ISDN_FAX_CLASS1_ERROR 3 -#define ISDN_FAX_CLASS1_FCERROR 4 -#define ISDN_FAX_CLASS1_QUERY 5 - -typedef struct { - __u8 cmd; - __u8 subcmd; - __u8 para[50]; -} aux_s; - -#define AT_COMMAND 0 -#define AT_EQ_VALUE 1 -#define AT_QUERY 2 -#define AT_EQ_QUERY 3 - -/* CAPI structs */ - -/* this is compatible to the old union size */ -#define MAX_CAPI_PARA_LEN 50 - -typedef struct { - /* Header */ - __u16 Length; - __u16 ApplId; - __u8 Command; - __u8 Subcommand; - __u16 Messagenumber; - - /* Parameter */ - union { - __u32 Controller; - __u32 PLCI; - __u32 NCCI; - } adr; - __u8 para[MAX_CAPI_PARA_LEN]; -} capi_msg; - -/* - * Structure for exchanging above infos - * - */ -typedef struct { - int driver; /* Lowlevel-Driver-ID */ - int command; /* Command or Status (see above) */ - ulong arg; /* Additional Data */ - union { - ulong errcode; /* Type of error with STAT_L1ERR */ - int length; /* Amount of bytes sent with STAT_BSENT */ - u_char num[50]; /* Additional Data */ - setup_parm setup;/* For SETUP msg */ - capi_msg cmsg; /* For CAPI like messages */ - char display[85];/* display message data */ - isdn_cmd_stat isdn_io; /* ISDN IO-parameter/result */ - aux_s aux; /* for modem commands/indications */ -#ifdef CONFIG_ISDN_TTY_FAX - T30_s *fax; /* Pointer to ttys fax struct */ -#endif - ulong userdata; /* User Data */ - } parm; -} isdn_ctrl; - -#define dss1_io isdn_io -#define ni1_io isdn_io - -/* - * The interface-struct itself (initialized at load-time of lowlevel-driver) - * - * See Documentation/isdn/INTERFACE for a description, how the communication - * between the ISDN subsystem and its drivers is done. - * - */ -typedef struct { - struct module *owner; - - /* Number of channels supported by this driver - */ - int channels; - - /* - * Maximum Size of transmit/receive-buffer this driver supports. - */ - int maxbufsize; - - /* Feature-Flags for this driver. - * See defines ISDN_FEATURE_... for Values - */ - unsigned long features; - - /* - * Needed for calculating - * dev->hard_header_len = linklayer header + hl_hdrlen; - * Drivers, not supporting sk_buff's should set this to 0. - */ - unsigned short hl_hdrlen; - - /* - * Receive-Callback using sk_buff's - * Parameters: - * int Driver-ID - * int local channel-number (0 ...) - * struct sk_buff *skb received Data - */ - void (*rcvcallb_skb)(int, int, struct sk_buff *); - - /* Status-Callback - * Parameters: - * isdn_ctrl* - * driver = Driver ID. - * command = One of above ISDN_STAT_... constants. - * arg = depending on status-type. - * num = depending on status-type. - */ - int (*statcallb)(isdn_ctrl*); - - /* Send command - * Parameters: - * isdn_ctrl* - * driver = Driver ID. - * command = One of above ISDN_CMD_... constants. - * arg = depending on command. - * num = depending on command. - */ - int (*command)(isdn_ctrl*); - - /* - * Send data using sk_buff's - * Parameters: - * int driverId - * int local channel-number (0...) - * int Flag: Need ACK for this packet. - * struct sk_buff *skb Data to send - */ - int (*writebuf_skb) (int, int, int, struct sk_buff *); - - /* Send raw D-Channel-Commands - * Parameters: - * u_char pointer data - * int length of data - * int driverId - * int local channel-number (0 ...) - */ - int (*writecmd)(const u_char __user *, int, int, int); - - /* Read raw Status replies - * u_char pointer data (volatile) - * int length of buffer - * int driverId - * int local channel-number (0 ...) - */ - int (*readstat)(u_char __user *, int, int, int); - - char id[20]; -} isdn_if; - -/* - * Function which must be called by lowlevel-driver at loadtime with - * the following fields of above struct set: - * - * channels Number of channels that will be supported. - * hl_hdrlen Space to preserve in sk_buff's when sending. Drivers, not - * supporting sk_buff's should set this to 0. - * command Address of Command-Handler. - * features Bitwise coded Features of this driver. (use ISDN_FEATURE_...) - * writebuf_skb Address of Skbuff-Send-Handler. - * writecmd " " D-Channel " which accepts raw D-Ch-Commands. - * readstat " " D-Channel " which delivers raw Status-Data. - * - * The linklevel-driver fills the following fields: - * - * channels Driver-ID assigned to this driver. (Must be used on all - * subsequent callbacks. - * rcvcallb_skb Address of handler for received Skbuff's. - * statcallb " " " for status-changes. - * - */ -extern int register_isdn(isdn_if*); -#include - -#endif /* __ISDNIF_H__ */ diff --git a/include/linux/wanrouter.h b/include/linux/wanrouter.h deleted file mode 100644 index f6358558f9f5..000000000000 --- a/include/linux/wanrouter.h +++ /dev/null @@ -1,11 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -/* - * wanrouter.h Legacy declarations kept around until X25 is removed - */ - -#ifndef _ROUTER_H -#define _ROUTER_H - -#include - -#endif /* _ROUTER_H */ diff --git a/include/uapi/linux/isdn.h b/include/uapi/linux/isdn.h deleted file mode 100644 index f371fd52ed75..000000000000 --- a/include/uapi/linux/isdn.h +++ /dev/null @@ -1,144 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ -/* $Id: isdn.h,v 1.125.2.3 2004/02/10 01:07:14 keil Exp $ - * - * Main header for the Linux ISDN subsystem (linklevel). - * - * Copyright 1994,95,96 by Fritz Elfert (fritz@isdn4linux.de) - * Copyright 1995,96 by Thinking Objects Software GmbH Wuerzburg - * Copyright 1995,96 by Michael Hipp (Michael.Hipp@student.uni-tuebingen.de) - * - * This software may be used and distributed according to the terms - * of the GNU General Public License, incorporated herein by reference. - * - */ - -#ifndef _UAPI__ISDN_H__ -#define _UAPI__ISDN_H__ - -#include -#include - -#define ISDN_MAX_DRIVERS 32 -#define ISDN_MAX_CHANNELS 64 - -/* New ioctl-codes */ -#define IIOCNETAIF _IO('I',1) -#define IIOCNETDIF _IO('I',2) -#define IIOCNETSCF _IO('I',3) -#define IIOCNETGCF _IO('I',4) -#define IIOCNETANM _IO('I',5) -#define IIOCNETDNM _IO('I',6) -#define IIOCNETGNM _IO('I',7) -#define IIOCGETSET _IO('I',8) /* no longer supported */ -#define IIOCSETSET _IO('I',9) /* no longer supported */ -#define IIOCSETVER _IO('I',10) -#define IIOCNETHUP _IO('I',11) -#define IIOCSETGST _IO('I',12) -#define IIOCSETBRJ _IO('I',13) -#define IIOCSIGPRF _IO('I',14) -#define IIOCGETPRF _IO('I',15) -#define IIOCSETPRF _IO('I',16) -#define IIOCGETMAP _IO('I',17) -#define IIOCSETMAP _IO('I',18) -#define IIOCNETASL _IO('I',19) -#define IIOCNETDIL _IO('I',20) -#define IIOCGETCPS _IO('I',21) -#define IIOCGETDVR _IO('I',22) -#define IIOCNETLCR _IO('I',23) /* dwabc ioctl for LCR from isdnlog */ -#define IIOCNETDWRSET _IO('I',24) /* dwabc ioctl to reset abc-values to default on a net-interface */ - -#define IIOCNETALN _IO('I',32) -#define IIOCNETDLN _IO('I',33) - -#define IIOCNETGPN _IO('I',34) - -#define IIOCDBGVAR _IO('I',127) - -#define IIOCDRVCTL _IO('I',128) - -/* cisco hdlck device private ioctls */ -#define SIOCGKEEPPERIOD (SIOCDEVPRIVATE + 0) -#define SIOCSKEEPPERIOD (SIOCDEVPRIVATE + 1) -#define SIOCGDEBSERINT (SIOCDEVPRIVATE + 2) -#define SIOCSDEBSERINT (SIOCDEVPRIVATE + 3) - -/* Packet encapsulations for net-interfaces */ -#define ISDN_NET_ENCAP_ETHER 0 -#define ISDN_NET_ENCAP_RAWIP 1 -#define ISDN_NET_ENCAP_IPTYP 2 -#define ISDN_NET_ENCAP_CISCOHDLC 3 /* Without SLARP and keepalive */ -#define ISDN_NET_ENCAP_SYNCPPP 4 -#define ISDN_NET_ENCAP_UIHDLC 5 -#define ISDN_NET_ENCAP_CISCOHDLCK 6 /* With SLARP and keepalive */ -#define ISDN_NET_ENCAP_X25IFACE 7 /* Documentation/networking/x25-iface.txt */ -#define ISDN_NET_ENCAP_MAX_ENCAP ISDN_NET_ENCAP_X25IFACE - -/* Facility which currently uses an ISDN-channel */ -#define ISDN_USAGE_NONE 0 -#define ISDN_USAGE_RAW 1 -#define ISDN_USAGE_MODEM 2 -#define ISDN_USAGE_NET 3 -#define ISDN_USAGE_VOICE 4 -#define ISDN_USAGE_FAX 5 -#define ISDN_USAGE_MASK 7 /* Mask to get plain usage */ -#define ISDN_USAGE_DISABLED 32 /* This bit is set, if channel is disabled */ -#define ISDN_USAGE_EXCLUSIVE 64 /* This bit is set, if channel is exclusive */ -#define ISDN_USAGE_OUTGOING 128 /* This bit is set, if channel is outgoing */ - -#define ISDN_MODEM_NUMREG 24 /* Number of Modem-Registers */ -#define ISDN_LMSNLEN 255 /* Length of tty's Listen-MSN string */ -#define ISDN_CMSGLEN 50 /* Length of CONNECT-Message to add for Modem */ - -#define ISDN_MSNLEN 32 -#define NET_DV 0x06 /* Data version for isdn_net_ioctl_cfg */ -#define TTY_DV 0x06 /* Data version for iprofd etc. */ - -#define INF_DV 0x01 /* Data version for /dev/isdninfo */ - -typedef struct { - char drvid[25]; - unsigned long arg; -} isdn_ioctl_struct; - -typedef struct { - char name[10]; - char phone[ISDN_MSNLEN]; - int outgoing; -} isdn_net_ioctl_phone; - -typedef struct { - char name[10]; /* Name of interface */ - char master[10]; /* Name of Master for Bundling */ - char slave[10]; /* Name of Slave for Bundling */ - char eaz[256]; /* EAZ/MSN */ - char drvid[25]; /* DriverId for Bindings */ - int onhtime; /* Hangup-Timeout */ - int charge; /* Charge-Units */ - int l2_proto; /* Layer-2 protocol */ - int l3_proto; /* Layer-3 protocol */ - int p_encap; /* Encapsulation */ - int exclusive; /* Channel, if bound exclusive */ - int dialmax; /* Dial Retry-Counter */ - int slavedelay; /* Delay until slave starts up */ - int cbdelay; /* Delay before Callback */ - int chargehup; /* Flag: Charge-Hangup */ - int ihup; /* Flag: Hangup-Timeout on incoming line */ - int secure; /* Flag: Secure */ - int callback; /* Flag: Callback */ - int cbhup; /* Flag: Reject Call before Callback */ - int pppbind; /* ippp device for bindings */ - int chargeint; /* Use fixed charge interval length */ - int triggercps; /* BogoCPS needed for triggering slave */ - int dialtimeout; /* Dial-Timeout */ - int dialwait; /* Time to wait after failed dial */ - int dialmode; /* Flag: off / on / auto */ -} isdn_net_ioctl_cfg; - -#define ISDN_NET_DIALMODE_MASK 0xC0 /* bits for status */ -#define ISDN_NET_DM_OFF 0x00 /* this interface is stopped */ -#define ISDN_NET_DM_MANUAL 0x40 /* this interface is on (manual) */ -#define ISDN_NET_DM_AUTO 0x80 /* this interface is autodial */ -#define ISDN_NET_DIALMODE(x) ((&(x))->flags & ISDN_NET_DIALMODE_MASK) - - -#endif /* _UAPI__ISDN_H__ */ diff --git a/include/uapi/linux/isdn_divertif.h b/include/uapi/linux/isdn_divertif.h deleted file mode 100644 index 0a17bb1bcb1b..000000000000 --- a/include/uapi/linux/isdn_divertif.h +++ /dev/null @@ -1,31 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ -/* $Id: isdn_divertif.h,v 1.4.6.1 2001/09/23 22:25:05 kai Exp $ - * - * Header for the diversion supplementary interface for i4l. - * - * Author Werner Cornelius (werner@titro.de) - * Copyright by Werner Cornelius (werner@titro.de) - * - * This software may be used and distributed according to the terms - * of the GNU General Public License, incorporated herein by reference. - * - */ - -#ifndef _UAPI_LINUX_ISDN_DIVERTIF_H -#define _UAPI_LINUX_ISDN_DIVERTIF_H - -/***********************************************************/ -/* magic value is also used to control version information */ -/***********************************************************/ -#define DIVERT_IF_MAGIC 0x25873401 -#define DIVERT_CMD_REG 0x00 /* register command */ -#define DIVERT_CMD_REL 0x01 /* release command */ -#define DIVERT_NO_ERR 0x00 /* return value no error */ -#define DIVERT_CMD_ERR 0x01 /* invalid cmd */ -#define DIVERT_VER_ERR 0x02 /* magic/version invalid */ -#define DIVERT_REG_ERR 0x03 /* module already registered */ -#define DIVERT_REL_ERR 0x04 /* module not registered */ -#define DIVERT_REG_NAME isdn_register_divert - - -#endif /* _UAPI_LINUX_ISDN_DIVERTIF_H */ diff --git a/include/uapi/linux/isdn_ppp.h b/include/uapi/linux/isdn_ppp.h deleted file mode 100644 index 0bdc4efaacb2..000000000000 --- a/include/uapi/linux/isdn_ppp.h +++ /dev/null @@ -1,68 +0,0 @@ -/* SPDX-License-Identifier: GPL-1.0+ WITH Linux-syscall-note */ -/* Linux ISDN subsystem, sync PPP, interface to ipppd - * - * Copyright 1994-1999 by Fritz Elfert (fritz@isdn4linux.de) - * Copyright 1995,96 Thinking Objects Software GmbH Wuerzburg - * Copyright 1995,96 by Michael Hipp (Michael.Hipp@student.uni-tuebingen.de) - * Copyright 2000-2002 by Kai Germaschewski (kai@germaschewski.name) - * - * This software may be used and distributed according to the terms - * of the GNU General Public License, incorporated herein by reference. - * - */ - -#ifndef _UAPI_LINUX_ISDN_PPP_H -#define _UAPI_LINUX_ISDN_PPP_H - -#define CALLTYPE_INCOMING 0x1 -#define CALLTYPE_OUTGOING 0x2 -#define CALLTYPE_CALLBACK 0x4 - -#define IPPP_VERSION "2.2.0" - -struct pppcallinfo -{ - int calltype; - unsigned char local_num[64]; - unsigned char remote_num[64]; - int charge_units; -}; - -#define PPPIOCGCALLINFO _IOWR('t',128,struct pppcallinfo) -#define PPPIOCBUNDLE _IOW('t',129,int) -#define PPPIOCGMPFLAGS _IOR('t',130,int) -#define PPPIOCSMPFLAGS _IOW('t',131,int) -#define PPPIOCSMPMTU _IOW('t',132,int) -#define PPPIOCSMPMRU _IOW('t',133,int) -#define PPPIOCGCOMPRESSORS _IOR('t',134,unsigned long [8]) -#define PPPIOCSCOMPRESSOR _IOW('t',135,int) -#define PPPIOCGIFNAME _IOR('t',136, char [IFNAMSIZ] ) - - -#define SC_MP_PROT 0x00000200 -#define SC_REJ_MP_PROT 0x00000400 -#define SC_OUT_SHORT_SEQ 0x00000800 -#define SC_IN_SHORT_SEQ 0x00004000 - -#define SC_DECOMP_ON 0x01 -#define SC_COMP_ON 0x02 -#define SC_DECOMP_DISCARD 0x04 -#define SC_COMP_DISCARD 0x08 -#define SC_LINK_DECOMP_ON 0x10 -#define SC_LINK_COMP_ON 0x20 -#define SC_LINK_DECOMP_DISCARD 0x40 -#define SC_LINK_COMP_DISCARD 0x80 - -#define ISDN_PPP_COMP_MAX_OPTIONS 16 - -#define IPPP_COMP_FLAG_XMIT 0x1 -#define IPPP_COMP_FLAG_LINK 0x2 - -struct isdn_ppp_comp_data { - int num; - unsigned char options[ISDN_PPP_COMP_MAX_OPTIONS]; - int optlen; - int flags; -}; - -#endif /* _UAPI_LINUX_ISDN_PPP_H */ diff --git a/include/uapi/linux/isdnif.h b/include/uapi/linux/isdnif.h deleted file mode 100644 index 611a69196738..000000000000 --- a/include/uapi/linux/isdnif.h +++ /dev/null @@ -1,57 +0,0 @@ -/* SPDX-License-Identifier: GPL-1.0+ WITH Linux-syscall-note */ -/* $Id: isdnif.h,v 1.43.2.2 2004/01/12 23:08:35 keil Exp $ - * - * Linux ISDN subsystem - * Definition of the interface between the subsystem and its low-level drivers. - * - * Copyright 1994,95,96 by Fritz Elfert (fritz@isdn4linux.de) - * Copyright 1995,96 Thinking Objects Software GmbH Wuerzburg - * - * This software may be used and distributed according to the terms - * of the GNU General Public License, incorporated herein by reference. - * - */ - -#ifndef _UAPI__ISDNIF_H__ -#define _UAPI__ISDNIF_H__ - - -/* - * Values for general protocol-selection - */ -#define ISDN_PTYPE_UNKNOWN 0 /* Protocol undefined */ -#define ISDN_PTYPE_1TR6 1 /* german 1TR6-protocol */ -#define ISDN_PTYPE_EURO 2 /* EDSS1-protocol */ -#define ISDN_PTYPE_LEASED 3 /* for leased lines */ -#define ISDN_PTYPE_NI1 4 /* US NI-1 protocol */ -#define ISDN_PTYPE_MAX 7 /* Max. 8 Protocols */ - -/* - * Values for Layer-2-protocol-selection - */ -#define ISDN_PROTO_L2_X75I 0 /* X75/LAPB with I-Frames */ -#define ISDN_PROTO_L2_X75UI 1 /* X75/LAPB with UI-Frames */ -#define ISDN_PROTO_L2_X75BUI 2 /* X75/LAPB with UI-Frames */ -#define ISDN_PROTO_L2_HDLC 3 /* HDLC */ -#define ISDN_PROTO_L2_TRANS 4 /* Transparent (Voice) */ -#define ISDN_PROTO_L2_X25DTE 5 /* X25/LAPB DTE mode */ -#define ISDN_PROTO_L2_X25DCE 6 /* X25/LAPB DCE mode */ -#define ISDN_PROTO_L2_V11096 7 /* V.110 bitrate adaption 9600 Baud */ -#define ISDN_PROTO_L2_V11019 8 /* V.110 bitrate adaption 19200 Baud */ -#define ISDN_PROTO_L2_V11038 9 /* V.110 bitrate adaption 38400 Baud */ -#define ISDN_PROTO_L2_MODEM 10 /* Analog Modem on Board */ -#define ISDN_PROTO_L2_FAX 11 /* Fax Group 2/3 */ -#define ISDN_PROTO_L2_HDLC_56K 12 /* HDLC 56k */ -#define ISDN_PROTO_L2_MAX 15 /* Max. 16 Protocols */ - -/* - * Values for Layer-3-protocol-selection - */ -#define ISDN_PROTO_L3_TRANS 0 /* Transparent */ -#define ISDN_PROTO_L3_TRANSDSP 1 /* Transparent with DSP */ -#define ISDN_PROTO_L3_FCLASS2 2 /* Fax Group 2/3 CLASS 2 */ -#define ISDN_PROTO_L3_FCLASS1 3 /* Fax Group 2/3 CLASS 1 */ -#define ISDN_PROTO_L3_MAX 7 /* Max. 8 Protocols */ - - -#endif /* _UAPI__ISDNIF_H__ */ diff --git a/include/uapi/linux/wanrouter.h b/include/uapi/linux/wanrouter.h deleted file mode 100644 index 2f1216d00caa..000000000000 --- a/include/uapi/linux/wanrouter.h +++ /dev/null @@ -1,18 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ -/* - * wanrouter.h Legacy declarations kept around until X25 is removed - */ - -#ifndef _UAPI_ROUTER_H -#define _UAPI_ROUTER_H - -/* 'state' defines */ -enum wan_states -{ - WAN_UNCONFIGURED, /* link/channel is not configured */ - WAN_DISCONNECTED, /* link/channel is disconnected */ - WAN_CONNECTING, /* connection is in progress */ - WAN_CONNECTED /* link/channel is operational */ -}; - -#endif /* _UAPI_ROUTER_H */ -- cgit v1.2.3 From 99c2aa151a7182c58f9477a376304c538d9cc5ab Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Thu, 18 Apr 2019 22:57:08 +0200 Subject: isdn: hdlc: move into mISDN The last remnant of the isdn4linux interface is now the isdnhdlc support, used by the netjet driver. Move it next to that driver. Signed-off-by: Arnd Bergmann --- include/linux/isdn/hdlc.h | 82 ----------------------------------------------- 1 file changed, 82 deletions(-) delete mode 100644 include/linux/isdn/hdlc.h (limited to 'include') diff --git a/include/linux/isdn/hdlc.h b/include/linux/isdn/hdlc.h deleted file mode 100644 index 96521370c782..000000000000 --- a/include/linux/isdn/hdlc.h +++ /dev/null @@ -1,82 +0,0 @@ -/* - * hdlc.h -- General purpose ISDN HDLC decoder. - * - * Implementation of a HDLC decoder/encoder in software. - * Necessary because some ISDN devices don't have HDLC - * controllers. - * - * Copyright (C) - * 2009 Karsten Keil - * 2002 Wolfgang Mües - * 2001 Frode Isaksen - * 2001 Kai Germaschewski - * - * 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. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * - * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software - * Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA. - */ - -#ifndef __ISDNHDLC_H__ -#define __ISDNHDLC_H__ - -struct isdnhdlc_vars { - int bit_shift; - int hdlc_bits1; - int data_bits; - int ffbit_shift; /* encoding only */ - int state; - int dstpos; - - u16 crc; - - u8 cbin; - u8 shift_reg; - u8 ffvalue; - - /* set if transferring data */ - u32 data_received:1; - /* set if D channel (send idle instead of flags) */ - u32 dchannel:1; - /* set if 56K adaptation */ - u32 do_adapt56:1; - /* set if in closing phase (need to send CRC + flag) */ - u32 do_closing:1; - /* set if data is bitreverse */ - u32 do_bitreverse:1; -}; - -/* Feature Flags */ -#define HDLC_56KBIT 0x01 -#define HDLC_DCHANNEL 0x02 -#define HDLC_BITREVERSE 0x04 - -/* - The return value from isdnhdlc_decode is - the frame length, 0 if no complete frame was decoded, - or a negative error number -*/ -#define HDLC_FRAMING_ERROR 1 -#define HDLC_CRC_ERROR 2 -#define HDLC_LENGTH_ERROR 3 - -extern void isdnhdlc_rcv_init(struct isdnhdlc_vars *hdlc, u32 features); - -extern int isdnhdlc_decode(struct isdnhdlc_vars *hdlc, const u8 *src, - int slen, int *count, u8 *dst, int dsize); - -extern void isdnhdlc_out_init(struct isdnhdlc_vars *hdlc, u32 features); - -extern int isdnhdlc_encode(struct isdnhdlc_vars *hdlc, const u8 *src, - u16 slen, int *count, u8 *dst, int dsize); - -#endif /* __ISDNHDLC_H__ */ -- cgit v1.2.3 From 1da40ab6caf924633116582c4c86939c486f20db Mon Sep 17 00:00:00 2001 From: Julian Anastasov Date: Sun, 5 May 2019 15:14:38 +0300 Subject: ipvs: allow rs_table to contain different real server types Before now rs_table was used only for NAT real servers. Change it to allow TUN real severs from different types, possibly hashed with different port key. Signed-off-by: Julian Anastasov Signed-off-by: Simon Horman Signed-off-by: Pablo Neira Ayuso --- include/net/ip_vs.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include') diff --git a/include/net/ip_vs.h b/include/net/ip_vs.h index 2ac40135b576..9a8ac8997e34 100644 --- a/include/net/ip_vs.h +++ b/include/net/ip_vs.h @@ -1497,6 +1497,9 @@ static inline int ip_vs_todrop(struct netns_ipvs *ipvs) static inline int ip_vs_todrop(struct netns_ipvs *ipvs) { return 0; } #endif +#define IP_VS_DFWD_METHOD(dest) (atomic_read(&(dest)->conn_flags) & \ + IP_VS_CONN_F_FWD_MASK) + /* ip_vs_fwd_tag returns the forwarding tag of the connection */ #define IP_VS_FWD_METHOD(cp) (cp->flags & IP_VS_CONN_F_FWD_MASK) -- cgit v1.2.3 From 2aa3c9f48bc28ca0effd9877e010ad54c8a630e5 Mon Sep 17 00:00:00 2001 From: Julian Anastasov Date: Sun, 5 May 2019 15:14:39 +0300 Subject: ipvs: add function to find tunnels Add ip_vs_find_tunnel() to match tunnel headers by family, address and optional port. Use it to properly find the tunnel real server used in received ICMP errors. Signed-off-by: Julian Anastasov Signed-off-by: Simon Horman Signed-off-by: Pablo Neira Ayuso --- include/net/ip_vs.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include') diff --git a/include/net/ip_vs.h b/include/net/ip_vs.h index 9a8ac8997e34..b01a94ebfc0e 100644 --- a/include/net/ip_vs.h +++ b/include/net/ip_vs.h @@ -1404,6 +1404,9 @@ bool ip_vs_has_real_service(struct netns_ipvs *ipvs, int af, __u16 protocol, struct ip_vs_dest * ip_vs_find_real_service(struct netns_ipvs *ipvs, int af, __u16 protocol, const union nf_inet_addr *daddr, __be16 dport); +struct ip_vs_dest *ip_vs_find_tunnel(struct netns_ipvs *ipvs, int af, + const union nf_inet_addr *daddr, + __be16 tun_port); int ip_vs_use_count_inc(void); void ip_vs_use_count_dec(void); -- cgit v1.2.3 From ea6cc2fd8a2b89ab6dcd096ba6dbc1ecbdf26564 Mon Sep 17 00:00:00 2001 From: Lukasz Pawelczyk Date: Fri, 10 May 2019 13:46:22 +0200 Subject: netfilter: xt_owner: Add supplementary groups option The XT_OWNER_SUPPL_GROUPS flag causes GIDs specified with XT_OWNER_GID to be also checked in the supplementary groups of a process. f_cred->group_info cannot be modified during its lifetime and f_cred holds a reference to it so it's safe to use. Signed-off-by: Lukasz Pawelczyk Signed-off-by: Pablo Neira Ayuso --- include/uapi/linux/netfilter/xt_owner.h | 7 ++++--- 1 file changed, 4 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/include/uapi/linux/netfilter/xt_owner.h b/include/uapi/linux/netfilter/xt_owner.h index fa3ad84957d5..9e98c09eda32 100644 --- a/include/uapi/linux/netfilter/xt_owner.h +++ b/include/uapi/linux/netfilter/xt_owner.h @@ -5,9 +5,10 @@ #include enum { - XT_OWNER_UID = 1 << 0, - XT_OWNER_GID = 1 << 1, - XT_OWNER_SOCKET = 1 << 2, + XT_OWNER_UID = 1 << 0, + XT_OWNER_GID = 1 << 1, + XT_OWNER_SOCKET = 1 << 2, + XT_OWNER_SUPPL_GROUPS = 1 << 3, }; struct xt_owner_match_info { -- cgit v1.2.3 From 5e2ad02e9001fd99cae3c14e52f67bb976e9bee3 Mon Sep 17 00:00:00 2001 From: Taehee Yoo Date: Thu, 16 May 2019 04:02:31 +0900 Subject: netfilter: nf_flow_table: remove unnecessary variable in flow_offload_tuple The oifidx in the struct flow_offload_tuple is not used anymore. Signed-off-by: Taehee Yoo Signed-off-by: Pablo Neira Ayuso --- include/net/netfilter/nf_flow_table.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include') diff --git a/include/net/netfilter/nf_flow_table.h b/include/net/netfilter/nf_flow_table.h index 3e370cb36263..d8c187936bec 100644 --- a/include/net/netfilter/nf_flow_table.h +++ b/include/net/netfilter/nf_flow_table.h @@ -53,8 +53,6 @@ struct flow_offload_tuple { u8 l4proto; u8 dir; - int oifidx; - u16 mtu; struct dst_entry *dst_cache; -- cgit v1.2.3 From 2cf6bffc49dae26edd12af6b57c8c780590380bf Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Thu, 23 May 2019 15:44:12 +0200 Subject: netfilter: replace skb_make_writable with skb_ensure_writable This converts all remaining users and then removes skb_make_writable. Suggested-by: Daniel Borkmann Signed-off-by: Florian Westphal Signed-off-by: Pablo Neira Ayuso --- include/linux/netfilter.h | 5 ----- 1 file changed, 5 deletions(-) (limited to 'include') diff --git a/include/linux/netfilter.h b/include/linux/netfilter.h index 996bc247ef6e..049aeb40fa35 100644 --- a/include/linux/netfilter.h +++ b/include/linux/netfilter.h @@ -336,11 +336,6 @@ int compat_nf_getsockopt(struct sock *sk, u_int8_t pf, int optval, char __user *opt, int *len); #endif -/* Call this before modifying an existing packet: ensures it is - modifiable and linear to the point you care about (writable_len). - Returns true or false. */ -int skb_make_writable(struct sk_buff *skb, unsigned int writable_len); - struct flowi; struct nf_queue_entry; -- cgit v1.2.3 From 29930e314da3833437a2ddc7b17f6a954f38d8fb Mon Sep 17 00:00:00 2001 From: Jacky Hu Date: Thu, 30 May 2019 08:16:40 +0800 Subject: ipvs: add checksum support for gue encapsulation Add checksum support for gue encapsulation with the tun_flags parameter, which could be one of the values below: IP_VS_TUNNEL_ENCAP_FLAG_NOCSUM IP_VS_TUNNEL_ENCAP_FLAG_CSUM IP_VS_TUNNEL_ENCAP_FLAG_REMCSUM Signed-off-by: Jacky Hu Signed-off-by: Julian Anastasov Signed-off-by: Simon Horman Signed-off-by: Pablo Neira Ayuso --- include/net/ip_vs.h | 2 ++ include/uapi/linux/ip_vs.h | 7 +++++++ 2 files changed, 9 insertions(+) (limited to 'include') diff --git a/include/net/ip_vs.h b/include/net/ip_vs.h index b01a94ebfc0e..cb1ad0cc5c7b 100644 --- a/include/net/ip_vs.h +++ b/include/net/ip_vs.h @@ -603,6 +603,7 @@ struct ip_vs_dest_user_kern { u16 tun_type; /* tunnel type */ __be16 tun_port; /* tunnel port */ + u16 tun_flags; /* tunnel flags */ }; @@ -665,6 +666,7 @@ struct ip_vs_dest { atomic_t last_weight; /* server latest weight */ __u16 tun_type; /* tunnel type */ __be16 tun_port; /* tunnel port */ + __u16 tun_flags; /* tunnel flags */ refcount_t refcnt; /* reference counter */ struct ip_vs_stats stats; /* statistics */ diff --git a/include/uapi/linux/ip_vs.h b/include/uapi/linux/ip_vs.h index e34f436fc79d..e4f18061a4fd 100644 --- a/include/uapi/linux/ip_vs.h +++ b/include/uapi/linux/ip_vs.h @@ -131,6 +131,11 @@ enum { IP_VS_CONN_F_TUNNEL_TYPE_MAX, }; +/* Tunnel encapsulation flags */ +#define IP_VS_TUNNEL_ENCAP_FLAG_NOCSUM (0) +#define IP_VS_TUNNEL_ENCAP_FLAG_CSUM (1 << 0) +#define IP_VS_TUNNEL_ENCAP_FLAG_REMCSUM (1 << 1) + /* * The struct ip_vs_service_user and struct ip_vs_dest_user are * used to set IPVS rules through setsockopt. @@ -403,6 +408,8 @@ enum { IPVS_DEST_ATTR_TUN_PORT, /* tunnel port */ + IPVS_DEST_ATTR_TUN_FLAGS, /* tunnel flags */ + __IPVS_DEST_ATTR_MAX, }; -- cgit v1.2.3 From c9bb6165a16e6d5498981a6c777b94a78e74462b Mon Sep 17 00:00:00 2001 From: Pablo Neira Ayuso Date: Fri, 31 May 2019 11:15:26 +0200 Subject: netfilter: nf_conntrack_bridge: fix CONFIG_IPV6=y This patch fixes a few problems with CONFIG_IPV6=y and CONFIG_NF_CONNTRACK_BRIDGE=m: In file included from net/netfilter/utils.c:5: include/linux/netfilter_ipv6.h: In function 'nf_ipv6_br_defrag': include/linux/netfilter_ipv6.h:110:9: error: implicit declaration of function 'nf_ct_frag6_gather'; did you mean 'nf_ct_attach'? [-Werror=implicit-function-declaration] And these too: net/ipv6/netfilter.c:242:2: error: unknown field 'br_defrag' specified in initializer net/ipv6/netfilter.c:243:2: error: unknown field 'br_fragment' specified in initializer This patch includes an original chunk from wenxu. Fixes: 764dd163ac92 ("netfilter: nf_conntrack_bridge: add support for IPv6") Reported-by: Stephen Rothwell Reported-by: Yuehaibing Reported-by: kbuild test robot Reported-by: wenxu Signed-off-by: Pablo Neira Ayuso Signed-off-by: wenxu Signed-off-by: David S. Miller --- include/linux/netfilter_ipv6.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/linux/netfilter_ipv6.h b/include/linux/netfilter_ipv6.h index a21b8c9623ee..3a3dc4b1f0e7 100644 --- a/include/linux/netfilter_ipv6.h +++ b/include/linux/netfilter_ipv6.h @@ -96,6 +96,8 @@ static inline int nf_ip6_route(struct net *net, struct dst_entry **dst, #endif } +#include + static inline int nf_ipv6_br_defrag(struct net *net, struct sk_buff *skb, u32 user) { -- cgit v1.2.3 From 0b9055a112fd86c07b9d4857b61019485ec6526f Mon Sep 17 00:00:00 2001 From: Moshe Shemesh Date: Wed, 29 May 2019 22:50:24 +0000 Subject: net/mlx5: Add core dump register access HW bits Add Firmware core dump registers and HW definitions. Signed-off-by: Moshe Shemesh Signed-off-by: Eran Ben Elisha Signed-off-by: Saeed Mahameed --- include/linux/mlx5/driver.h | 1 + include/linux/mlx5/mlx5_ifc.h | 17 ++++++++++++++++- 2 files changed, 17 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h index 5a27246db883..b5431f7d97cb 100644 --- a/include/linux/mlx5/driver.h +++ b/include/linux/mlx5/driver.h @@ -107,6 +107,7 @@ enum { MLX5_REG_FPGA_CAP = 0x4022, MLX5_REG_FPGA_CTRL = 0x4023, MLX5_REG_FPGA_ACCESS_REG = 0x4024, + MLX5_REG_CORE_DUMP = 0x402e, MLX5_REG_PCAP = 0x5001, MLX5_REG_PMTU = 0x5003, MLX5_REG_PTYS = 0x5004, diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h index 5e74305e2e57..7ee422e38826 100644 --- a/include/linux/mlx5/mlx5_ifc.h +++ b/include/linux/mlx5/mlx5_ifc.h @@ -715,7 +715,9 @@ struct mlx5_ifc_qos_cap_bits { }; struct mlx5_ifc_debug_cap_bits { - u8 reserved_at_0[0x20]; + u8 core_dump_general[0x1]; + u8 core_dump_qp[0x1]; + u8 reserved_at_2[0x1e]; u8 reserved_at_20[0x2]; u8 stall_detect[0x1]; @@ -2531,6 +2533,7 @@ union mlx5_ifc_hca_cap_union_bits { struct mlx5_ifc_e_switch_cap_bits e_switch_cap; struct mlx5_ifc_vector_calc_cap_bits vector_calc_cap; struct mlx5_ifc_qos_cap_bits qos_cap; + struct mlx5_ifc_debug_cap_bits debug_cap; struct mlx5_ifc_fpga_cap_bits fpga_cap; u8 reserved_at_0[0x8000]; }; @@ -8546,6 +8549,18 @@ struct mlx5_ifc_qcam_reg_bits { u8 reserved_at_1c0[0x80]; }; +struct mlx5_ifc_core_dump_reg_bits { + u8 reserved_at_0[0x18]; + u8 core_dump_type[0x8]; + + u8 reserved_at_20[0x30]; + u8 vhca_id[0x10]; + + u8 reserved_at_60[0x8]; + u8 qpn[0x18]; + u8 reserved_at_80[0x180]; +}; + struct mlx5_ifc_pcap_reg_bits { u8 reserved_at_0[0x8]; u8 local_port[0x8]; -- cgit v1.2.3 From c6d4e45d3b44b71227588c2f76615380b3961f96 Mon Sep 17 00:00:00 2001 From: Eli Britstein Date: Wed, 29 May 2019 22:50:29 +0000 Subject: net/mlx5: Introduce termination table bits Termination table is a flow table with a termination flag. The flag allows the firmware to assume that the the specified actions are the last actions list. This assumption allows the FW to safely perform potential looping logic (e.g. hairpin). Introduce the bits for this attribute. Signed-off-by: Eli Britstein Reviewed-by: Oz Shlomo Signed-off-by: Saeed Mahameed --- include/linux/mlx5/fs.h | 1 + include/linux/mlx5/mlx5_ifc.h | 6 ++++-- 2 files changed, 5 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/mlx5/fs.h b/include/linux/mlx5/fs.h index e690ba0f965c..2ddaa97f2179 100644 --- a/include/linux/mlx5/fs.h +++ b/include/linux/mlx5/fs.h @@ -47,6 +47,7 @@ enum { enum { MLX5_FLOW_TABLE_TUNNEL_EN_REFORMAT = BIT(0), MLX5_FLOW_TABLE_TUNNEL_EN_DECAP = BIT(1), + MLX5_FLOW_TABLE_TERMINATION = BIT(2), }; #define LEFTOVERS_RULE_NUM 2 diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h index 7ee422e38826..feaa909bf14f 100644 --- a/include/linux/mlx5/mlx5_ifc.h +++ b/include/linux/mlx5/mlx5_ifc.h @@ -382,7 +382,8 @@ struct mlx5_ifc_flow_table_prop_layout_bits { u8 reformat_and_modify_action[0x1]; u8 reserved_at_15[0x2]; u8 table_miss_action_domain[0x1]; - u8 reserved_at_18[0x8]; + u8 termination_table[0x1]; + u8 reserved_at_19[0x7]; u8 reserved_at_20[0x2]; u8 log_max_ft_size[0x6]; u8 log_max_modify_header_context[0x8]; @@ -7239,7 +7240,8 @@ struct mlx5_ifc_create_flow_table_out_bits { struct mlx5_ifc_flow_table_context_bits { u8 reformat_en[0x1]; u8 decap_en[0x1]; - u8 reserved_at_2[0x2]; + u8 reserved_at_2[0x1]; + u8 termination_table[0x1]; u8 table_miss_action[0x4]; u8 level[0x8]; u8 reserved_at_10[0x8]; -- cgit v1.2.3 From cd56f929e6a547180f889a4def370bdd6d48d223 Mon Sep 17 00:00:00 2001 From: Vu Pham Date: Wed, 29 May 2019 22:50:34 +0000 Subject: net/mlx5: E-Switch, Replace host_params event with functions_changed event To support sriov on a E-Switch manager, num_vfs are queried to the firmware whenever E-Switch manager is notified by esw_functions_changed event. Replace host_params event with esw_functions_changed event that reflects more appropriate naming. While at it, also correct num_vfs type from int to u16 as expected by the function mlx5_esw_query_functions(). Signed-off-by: Vu Pham Reviewed-by: Parav Pandit Reviewed-by: Bodong Wang Signed-off-by: Saeed Mahameed --- include/linux/mlx5/device.h | 2 +- include/linux/mlx5/mlx5_ifc.h | 6 +++--- 2 files changed, 4 insertions(+), 4 deletions(-) (limited to 'include') diff --git a/include/linux/mlx5/device.h b/include/linux/mlx5/device.h index fc2b6e807f06..5e760067ac41 100644 --- a/include/linux/mlx5/device.h +++ b/include/linux/mlx5/device.h @@ -342,7 +342,7 @@ enum mlx5_event { MLX5_EVENT_TYPE_PAGE_FAULT = 0xc, MLX5_EVENT_TYPE_NIC_VPORT_CHANGE = 0xd, - MLX5_EVENT_TYPE_HOST_PARAMS_CHANGE = 0xe, + MLX5_EVENT_TYPE_ESW_FUNCTIONS_CHANGED = 0xe, MLX5_EVENT_TYPE_DCT_DRAINED = 0x1c, diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h index feaa909bf14f..0780242a757a 100644 --- a/include/linux/mlx5/mlx5_ifc.h +++ b/include/linux/mlx5/mlx5_ifc.h @@ -155,7 +155,7 @@ enum { MLX5_CMD_OP_QUERY_XRQ_DC_PARAMS_ENTRY = 0x725, MLX5_CMD_OP_SET_XRQ_DC_PARAMS_ENTRY = 0x726, MLX5_CMD_OP_QUERY_XRQ_ERROR_PARAMS = 0x727, - MLX5_CMD_OP_QUERY_HOST_PARAMS = 0x740, + MLX5_CMD_OP_QUERY_ESW_FUNCTIONS = 0x740, MLX5_CMD_OP_QUERY_VPORT_STATE = 0x750, MLX5_CMD_OP_MODIFY_VPORT_STATE = 0x751, MLX5_CMD_OP_QUERY_ESW_VPORT_CONTEXT = 0x752, @@ -9721,7 +9721,7 @@ struct mlx5_ifc_host_params_context_bits { u8 reserved_at_80[0x180]; }; -struct mlx5_ifc_query_host_params_in_bits { +struct mlx5_ifc_query_esw_functions_in_bits { u8 opcode[0x10]; u8 reserved_at_10[0x10]; @@ -9731,7 +9731,7 @@ struct mlx5_ifc_query_host_params_in_bits { u8 reserved_at_40[0x40]; }; -struct mlx5_ifc_query_host_params_out_bits { +struct mlx5_ifc_query_esw_functions_out_bits { u8 status[0x8]; u8 reserved_at_8[0x18]; -- cgit v1.2.3 From 6706a3b94f890145ca09797f748d2b30e1414fd3 Mon Sep 17 00:00:00 2001 From: Vu Pham Date: Wed, 29 May 2019 22:50:37 +0000 Subject: net/mlx5: E-Switch, Honor eswitch functions changed event cap Whenever device supports eswitch functions changed event, honor such device setting. Do not limit it to ECPF. Signed-off-by: Parav Pandit Signed-off-by: Vu Pham Signed-off-by: Saeed Mahameed --- include/linux/mlx5/mlx5_ifc.h | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h index 0780242a757a..6513b985c5e9 100644 --- a/include/linux/mlx5/mlx5_ifc.h +++ b/include/linux/mlx5/mlx5_ifc.h @@ -665,7 +665,9 @@ struct mlx5_ifc_e_switch_cap_bits { u8 vport_svlan_insert[0x1]; u8 vport_cvlan_insert_if_not_exist[0x1]; u8 vport_cvlan_insert_overwrite[0x1]; - u8 reserved_at_5[0x16]; + u8 reserved_at_5[0x14]; + u8 esw_functions_changed[0x1]; + u8 reserved_at_1a[0x1]; u8 ecpf_vport_exists[0x1]; u8 counter_eswitch_affinity[0x1]; u8 merged_eswitch[0x1]; -- cgit v1.2.3 From 8693115af4c24d92b971ad895c5f329761ed5d38 Mon Sep 17 00:00:00 2001 From: Parav Pandit Date: Wed, 29 May 2019 22:50:41 +0000 Subject: {IB,net}/mlx5: Constify rep ops functions pointers Currently for every representor type and for every single vport, representer function pointers copy is stored even though they don't change from one to other vport. Additionally priv data entry for the rep is not passed during registration, but its copied. It is used (set and cleared) by the user of the reps. As we want to scale vports, to simplify and also to split constants from data, 1. Rename mlx5_eswitch_rep_if to mlx5_eswitch_rep_ops as to match _ops prefix with other standard netdev, ibdev ops. 2. Constify the IB and Ethernet rep ops structure. 3. Instead of storing copy of all rep function pointers, store copy per eswitch rep type. 4. Split data and function pointers to mlx5_eswitch_rep_ops and mlx5_eswitch_rep_data. Signed-off-by: Parav Pandit Reviewed-by: Mark Bloch Signed-off-by: Saeed Mahameed --- include/linux/mlx5/eswitch.h | 20 +++++++++++--------- 1 file changed, 11 insertions(+), 9 deletions(-) (limited to 'include') diff --git a/include/linux/mlx5/eswitch.h b/include/linux/mlx5/eswitch.h index 0ca77dd1429c..d81ee4df181c 100644 --- a/include/linux/mlx5/eswitch.h +++ b/include/linux/mlx5/eswitch.h @@ -29,17 +29,19 @@ enum { }; struct mlx5_eswitch_rep; -struct mlx5_eswitch_rep_if { - int (*load)(struct mlx5_core_dev *dev, - struct mlx5_eswitch_rep *rep); - void (*unload)(struct mlx5_eswitch_rep *rep); - void *(*get_proto_dev)(struct mlx5_eswitch_rep *rep); - void *priv; - atomic_t state; +struct mlx5_eswitch_rep_ops { + int (*load)(struct mlx5_core_dev *dev, struct mlx5_eswitch_rep *rep); + void (*unload)(struct mlx5_eswitch_rep *rep); + void *(*get_proto_dev)(struct mlx5_eswitch_rep *rep); +}; + +struct mlx5_eswitch_rep_data { + void *priv; + atomic_t state; }; struct mlx5_eswitch_rep { - struct mlx5_eswitch_rep_if rep_if[NUM_REP_TYPES]; + struct mlx5_eswitch_rep_data rep_data[NUM_REP_TYPES]; u16 vport; u8 hw_id[ETH_ALEN]; u16 vlan; @@ -47,7 +49,7 @@ struct mlx5_eswitch_rep { }; void mlx5_eswitch_register_vport_reps(struct mlx5_eswitch *esw, - struct mlx5_eswitch_rep_if *rep_if, + const struct mlx5_eswitch_rep_ops *ops, u8 rep_type); void mlx5_eswitch_unregister_vport_reps(struct mlx5_eswitch *esw, u8 rep_type); void *mlx5_eswitch_get_proto_dev(struct mlx5_eswitch *esw, -- cgit v1.2.3 From 320587e6eac960591077b90271f40bfad24d6155 Mon Sep 17 00:00:00 2001 From: Russell King Date: Tue, 28 May 2019 10:57:34 +0100 Subject: net: sfp: add mandatory attach/detach methods for sfp buses Add attach and detach methods for SFP buses, which will allow us to get rid of the netdev storage in sfp-bus. Signed-off-by: Russell King Reviewed-by: Andrew Lunn Signed-off-by: David S. Miller --- include/linux/sfp.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include') diff --git a/include/linux/sfp.h b/include/linux/sfp.h index d9d9de3fcf8e..a3f0336dd703 100644 --- a/include/linux/sfp.h +++ b/include/linux/sfp.h @@ -469,6 +469,10 @@ struct sfp_bus; /** * struct sfp_upstream_ops - upstream operations structure + * @attach: called when the sfp socket driver is bound to the upstream + * (mandatory). + * @detach: called when the sfp socket driver is unbound from the upstream + * (mandatory). * @module_insert: called after a module has been detected to determine * whether the module is supported for the upstream device. * @module_remove: called after the module has been removed. @@ -481,6 +485,8 @@ struct sfp_bus; * been removed. */ struct sfp_upstream_ops { + void (*attach)(void *priv, struct sfp_bus *bus); + void (*detach)(void *priv, struct sfp_bus *bus); int (*module_insert)(void *priv, const struct sfp_eeprom_id *id); void (*module_remove)(void *priv); void (*link_down)(void *priv); -- cgit v1.2.3 From 54f70b3ba364f19291dc8b9cb096b02a00fb4461 Mon Sep 17 00:00:00 2001 From: Russell King Date: Tue, 28 May 2019 10:57:39 +0100 Subject: net: sfp: remove sfp-bus use of netdevs The sfp-bus code now no longer has any use for the network device structure, so remove its use. Signed-off-by: Russell King Reviewed-by: Andrew Lunn Signed-off-by: David S. Miller --- include/linux/sfp.h | 6 ++---- 1 file changed, 2 insertions(+), 4 deletions(-) (limited to 'include') diff --git a/include/linux/sfp.h b/include/linux/sfp.h index a3f0336dd703..1c35428e98bc 100644 --- a/include/linux/sfp.h +++ b/include/linux/sfp.h @@ -464,7 +464,6 @@ enum { struct fwnode_handle; struct ethtool_eeprom; struct ethtool_modinfo; -struct net_device; struct sfp_bus; /** @@ -510,7 +509,7 @@ int sfp_get_module_eeprom(struct sfp_bus *bus, struct ethtool_eeprom *ee, void sfp_upstream_start(struct sfp_bus *bus); void sfp_upstream_stop(struct sfp_bus *bus); struct sfp_bus *sfp_register_upstream(struct fwnode_handle *fwnode, - struct net_device *ndev, void *upstream, + void *upstream, const struct sfp_upstream_ops *ops); void sfp_unregister_upstream(struct sfp_bus *bus); #else @@ -555,8 +554,7 @@ static inline void sfp_upstream_stop(struct sfp_bus *bus) } static inline struct sfp_bus *sfp_register_upstream( - struct fwnode_handle *fwnode, - struct net_device *ndev, void *upstream, + struct fwnode_handle *fwnode, void *upstream, const struct sfp_upstream_ops *ops) { return (struct sfp_bus *)-1; -- cgit v1.2.3 From 0ccc171ea6a2fa34a6b898329c0a447c84e27057 Mon Sep 17 00:00:00 2001 From: Yevgeny Kliteynik Date: Wed, 30 Jan 2019 17:21:55 +0200 Subject: net/mlx5: Geneve, Manage Geneve TLV options Use Geneve TLV Options object to manage the flex parser matching on the 32-bit options data. When the first flow with a certain class/type values is requested to be offloaded, create a FW object with FW command (Geneve TLV Options general object) and start counting the number of flows using this object. During this time, any request with a different class/type values will fail to be offloaded. Once the refcount reaches 0, destroy the TLV options general object, and can now offload a flow with any class/type parameters. Geneve TLV Options object is added to core device. It is currently used to manage Geneve TLV options general object allocation in FW and its reference counting only. In the future it will also be used for managing geneve ports by registering callbacks for ndo_udp_tunnel_add/del. Reviewed-by: Oz Shlomo Signed-off-by: Yevgeny Kliteynik Signed-off-by: Saeed Mahameed --- include/linux/mlx5/driver.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h index b5431f7d97cb..3a810bf043fe 100644 --- a/include/linux/mlx5/driver.h +++ b/include/linux/mlx5/driver.h @@ -647,6 +647,7 @@ struct mlx5_clock { struct mlx5_fw_tracer; struct mlx5_vxlan; +struct mlx5_geneve; struct mlx5_core_dev { struct device *device; @@ -681,6 +682,7 @@ struct mlx5_core_dev { u32 issi; struct mlx5e_resources mlx5e_res; struct mlx5_vxlan *vxlan; + struct mlx5_geneve *geneve; struct { struct mlx5_rsvd_gids reserved_gids; u32 roce_en; -- cgit v1.2.3 From 1f52f6c0b0e846908e9c1082dab1b3f7088b82ac Mon Sep 17 00:00:00 2001 From: brakmo Date: Tue, 28 May 2019 16:59:35 -0700 Subject: bpf: Create BPF_PROG_CGROUP_INET_EGRESS_RUN_ARRAY Create new macro BPF_PROG_CGROUP_INET_EGRESS_RUN_ARRAY() to be used by __cgroup_bpf_run_filter_skb for EGRESS BPF progs so BPF programs can request cwr for TCP packets. Current cgroup skb programs can only return 0 or 1 (0 to drop the packet. This macro changes the behavior so the low order bit indicates whether the packet should be dropped (0) or not (1) and the next bit is used for congestion notification (cn). Hence, new allowed return values of CGROUP EGRESS BPF programs are: 0: drop packet 1: keep packet 2: drop packet and call cwr 3: keep packet and call cwr This macro then converts it to one of NET_XMIT values or -EPERM that has the effect of dropping the packet with no cn. 0: NET_XMIT_SUCCESS skb should be transmitted (no cn) 1: NET_XMIT_DROP skb should be dropped and cwr called 2: NET_XMIT_CN skb should be transmitted and cwr called 3: -EPERM skb should be dropped (no cn) Note that when more than one BPF program is called, the packet is dropped if at least one of programs requests it be dropped, and there is cn if at least one program returns cn. Signed-off-by: Lawrence Brakmo Signed-off-by: Alexei Starovoitov --- include/linux/bpf.h | 50 ++++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 50 insertions(+) (limited to 'include') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index ff3e00ff84d2..2cc58fc0f413 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -552,6 +552,56 @@ _out: \ _ret; \ }) +/* To be used by __cgroup_bpf_run_filter_skb for EGRESS BPF progs + * so BPF programs can request cwr for TCP packets. + * + * Current cgroup skb programs can only return 0 or 1 (0 to drop the + * packet. This macro changes the behavior so the low order bit + * indicates whether the packet should be dropped (0) or not (1) + * and the next bit is a congestion notification bit. This could be + * used by TCP to call tcp_enter_cwr() + * + * Hence, new allowed return values of CGROUP EGRESS BPF programs are: + * 0: drop packet + * 1: keep packet + * 2: drop packet and cn + * 3: keep packet and cn + * + * This macro then converts it to one of the NET_XMIT or an error + * code that is then interpreted as drop packet (and no cn): + * 0: NET_XMIT_SUCCESS skb should be transmitted + * 1: NET_XMIT_DROP skb should be dropped and cn + * 2: NET_XMIT_CN skb should be transmitted and cn + * 3: -EPERM skb should be dropped + */ +#define BPF_PROG_CGROUP_INET_EGRESS_RUN_ARRAY(array, ctx, func) \ + ({ \ + struct bpf_prog_array_item *_item; \ + struct bpf_prog *_prog; \ + struct bpf_prog_array *_array; \ + u32 ret; \ + u32 _ret = 1; \ + u32 _cn = 0; \ + preempt_disable(); \ + rcu_read_lock(); \ + _array = rcu_dereference(array); \ + _item = &_array->items[0]; \ + while ((_prog = READ_ONCE(_item->prog))) { \ + bpf_cgroup_storage_set(_item->cgroup_storage); \ + ret = func(_prog, ctx); \ + _ret &= (ret & 1); \ + _cn |= (ret & 2); \ + _item++; \ + } \ + rcu_read_unlock(); \ + preempt_enable(); \ + if (_ret) \ + _ret = (_cn ? NET_XMIT_CN : NET_XMIT_SUCCESS); \ + else \ + _ret = (_cn ? NET_XMIT_DROP : -EPERM); \ + _ret; \ + }) + #define BPF_PROG_RUN_ARRAY(array, ctx, func) \ __BPF_PROG_RUN_ARRAY(array, ctx, func, false) -- cgit v1.2.3 From 5cf1e91456301f8c4f6bbc63ff76cff12f92f31b Mon Sep 17 00:00:00 2001 From: brakmo Date: Tue, 28 May 2019 16:59:36 -0700 Subject: bpf: cgroup inet skb programs can return 0 to 3 Allows cgroup inet skb programs to return values in the range [0, 3]. The second bit is used to deterine if congestion occurred and higher level protocol should decrease rate. E.g. TCP would call tcp_enter_cwr() The bpf_prog must set expected_attach_type to BPF_CGROUP_INET_EGRESS at load time if it uses the new return values (i.e. 2 or 3). The expected_attach_type is currently not enforced for BPF_PROG_TYPE_CGROUP_SKB. e.g Meaning the current bpf_prog with expected_attach_type setting to BPF_CGROUP_INET_EGRESS can attach to BPF_CGROUP_INET_INGRESS. Blindly enforcing expected_attach_type will break backward compatibility. This patch adds a enforce_expected_attach_type bit to only enforce the expected_attach_type when it uses the new return value. Signed-off-by: Lawrence Brakmo Signed-off-by: Martin KaFai Lau Signed-off-by: Alexei Starovoitov --- include/linux/filter.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/filter.h b/include/linux/filter.h index ba8b65270e0d..43b45d6db36d 100644 --- a/include/linux/filter.h +++ b/include/linux/filter.h @@ -526,7 +526,8 @@ struct bpf_prog { blinded:1, /* Was blinded */ is_func:1, /* program is a bpf function */ kprobe_override:1, /* Do we override a kprobe? */ - has_callchain_buf:1; /* callchain buffer allocated? */ + has_callchain_buf:1, /* callchain buffer allocated? */ + enforce_expected_attach_type:1; /* Enforce expected_attach_type checking at attach time */ enum bpf_prog_type type; /* Type of BPF program */ enum bpf_attach_type expected_attach_type; /* For some prog types */ u32 len; /* Number of filter blocks */ -- cgit v1.2.3 From 3539b96e041c06e4317082816d90ec09160aeb11 Mon Sep 17 00:00:00 2001 From: Roman Gushchin Date: Wed, 29 May 2019 18:03:57 -0700 Subject: bpf: group memory related fields in struct bpf_map_memory Group "user" and "pages" fields of bpf_map into the bpf_map_memory structure. Later it can be extended with "memcg" and other related information. The main reason for a such change (beside cosmetics) is to pass bpf_map_memory structure to charging functions before the actual allocation of bpf_map. Signed-off-by: Roman Gushchin Acked-by: Song Liu Signed-off-by: Alexei Starovoitov --- include/linux/bpf.h | 10 +++++++--- 1 file changed, 7 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 2cc58fc0f413..2e7c1c40d949 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -66,6 +66,11 @@ struct bpf_map_ops { u64 imm, u32 *off); }; +struct bpf_map_memory { + u32 pages; + struct user_struct *user; +}; + struct bpf_map { /* The first two cachelines with read-mostly members of which some * are also accessed in fast-path (e.g. ops, max_entries). @@ -86,7 +91,7 @@ struct bpf_map { u32 btf_key_type_id; u32 btf_value_type_id; struct btf *btf; - u32 pages; + struct bpf_map_memory memory; bool unpriv_array; bool frozen; /* write-once */ /* 48 bytes hole */ @@ -94,8 +99,7 @@ struct bpf_map { /* The 3rd and 4th cacheline with misc members to avoid false sharing * particularly with refcounting. */ - struct user_struct *user ____cacheline_aligned; - atomic_t refcnt; + atomic_t refcnt ____cacheline_aligned; atomic_t usercnt; struct work_struct work; char name[BPF_OBJ_NAME_LEN]; -- cgit v1.2.3 From b936ca643ade11f265fa10e5fb71c20d9c5243f1 Mon Sep 17 00:00:00 2001 From: Roman Gushchin Date: Wed, 29 May 2019 18:03:58 -0700 Subject: bpf: rework memlock-based memory accounting for maps In order to unify the existing memlock charging code with the memcg-based memory accounting, which will be added later, let's rework the current scheme. Currently the following design is used: 1) .alloc() callback optionally checks if the allocation will likely succeed using bpf_map_precharge_memlock() 2) .alloc() performs actual allocations 3) .alloc() callback calculates map cost and sets map.memory.pages 4) map_create() calls bpf_map_init_memlock() which sets map.memory.user and performs actual charging; in case of failure the map is destroyed 1) bpf_map_free_deferred() calls bpf_map_release_memlock(), which performs uncharge and releases the user 2) .map_free() callback releases the memory The scheme can be simplified and made more robust: 1) .alloc() calculates map cost and calls bpf_map_charge_init() 2) bpf_map_charge_init() sets map.memory.user and performs actual charge 3) .alloc() performs actual allocations 1) .map_free() callback releases the memory 2) bpf_map_charge_finish() performs uncharge and releases the user The new scheme also allows to reuse bpf_map_charge_init()/finish() functions for memcg-based accounting. Because charges are performed before actual allocations and uncharges after freeing the memory, no bogus memory pressure can be created. In cases when the map structure is not available (e.g. it's not created yet, or is already destroyed), on-stack bpf_map_memory structure is used. The charge can be transferred with the bpf_map_charge_move() function. Signed-off-by: Roman Gushchin Acked-by: Song Liu Signed-off-by: Alexei Starovoitov --- include/linux/bpf.h | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 2e7c1c40d949..3c8f24f402bf 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -650,9 +650,12 @@ struct bpf_map *__bpf_map_get(struct fd f); struct bpf_map * __must_check bpf_map_inc(struct bpf_map *map, bool uref); void bpf_map_put_with_uref(struct bpf_map *map); void bpf_map_put(struct bpf_map *map); -int bpf_map_precharge_memlock(u32 pages); int bpf_map_charge_memlock(struct bpf_map *map, u32 pages); void bpf_map_uncharge_memlock(struct bpf_map *map, u32 pages); +int bpf_map_charge_init(struct bpf_map_memory *mem, u32 pages); +void bpf_map_charge_finish(struct bpf_map_memory *mem); +void bpf_map_charge_move(struct bpf_map_memory *dst, + struct bpf_map_memory *src); void *bpf_map_area_alloc(size_t size, int numa_node); void bpf_map_area_free(void *base); void bpf_map_init_from_attr(struct bpf_map *map, union bpf_attr *attr); -- cgit v1.2.3 From c85d69135a9175c50a823d04d62d932312d037b3 Mon Sep 17 00:00:00 2001 From: Roman Gushchin Date: Wed, 29 May 2019 18:03:59 -0700 Subject: bpf: move memory size checks to bpf_map_charge_init() Most bpf map types doing similar checks and bytes to pages conversion during memory allocation and charging. Let's unify these checks by moving them into bpf_map_charge_init(). Signed-off-by: Roman Gushchin Acked-by: Song Liu Signed-off-by: Alexei Starovoitov --- 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 3c8f24f402bf..e5a309e6a400 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -652,7 +652,7 @@ void bpf_map_put_with_uref(struct bpf_map *map); void bpf_map_put(struct bpf_map *map); int bpf_map_charge_memlock(struct bpf_map *map, u32 pages); void bpf_map_uncharge_memlock(struct bpf_map *map, u32 pages); -int bpf_map_charge_init(struct bpf_map_memory *mem, u32 pages); +int bpf_map_charge_init(struct bpf_map_memory *mem, size_t size); void bpf_map_charge_finish(struct bpf_map_memory *mem); void bpf_map_charge_move(struct bpf_map_memory *dst, struct bpf_map_memory *src); -- cgit v1.2.3 From ef11db3310e272d3d8dbe8739e0770820dd20e52 Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Fri, 31 May 2019 18:27:04 +0200 Subject: net: inetdevice: provide replacement iterators for in_ifaddr walk The ifa_list is protected either by rcu or rtnl lock, but the current iterators do not account for this. This adds two iterators as replacement, a later patch in the series will update them with the needed rcu/rtnl_dereference calls. Its not done in this patch yet to avoid sparse warnings -- the fields lack the proper __rcu annotation. Signed-off-by: Florian Westphal Signed-off-by: David S. Miller --- include/linux/inetdevice.h | 10 +++++++++- 1 file changed, 9 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/inetdevice.h b/include/linux/inetdevice.h index 367dc2a0f84a..d5d05503a04b 100644 --- a/include/linux/inetdevice.h +++ b/include/linux/inetdevice.h @@ -186,7 +186,7 @@ __be32 inet_confirm_addr(struct net *net, struct in_device *in_dev, __be32 dst, struct in_ifaddr *inet_ifa_byprefix(struct in_device *in_dev, __be32 prefix, __be32 mask); struct in_ifaddr *inet_lookup_ifaddr_rcu(struct net *net, __be32 addr); -static __inline__ bool inet_ifa_match(__be32 addr, struct in_ifaddr *ifa) +static inline bool inet_ifa_match(__be32 addr, const struct in_ifaddr *ifa) { return !((addr^ifa->ifa_address)&ifa->ifa_mask); } @@ -215,6 +215,14 @@ static __inline__ bool bad_mask(__be32 mask, __be32 addr) #define endfor_ifa(in_dev) } +#define in_dev_for_each_ifa_rtnl(ifa, in_dev) \ + for (ifa = (in_dev)->ifa_list; ifa; \ + ifa = ifa->ifa_next) + +#define in_dev_for_each_ifa_rcu(ifa, in_dev) \ + for (ifa = (in_dev)->ifa_list; ifa; \ + ifa = ifa->ifa_next) + static inline struct in_device *__in_dev_get_rcu(const struct net_device *dev) { return rcu_dereference(dev->ip_ptr); -- cgit v1.2.3 From 2638eb8b50cfc16240e0bb080b9afbf541a9b39d Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Fri, 31 May 2019 18:27:09 +0200 Subject: net: ipv4: provide __rcu annotation for ifa_list ifa_list is protected by rcu, yet code doesn't reflect this. Add the __rcu annotations and fix up all places that are now reported by sparse. I've done this in the same commit to not add intermediate patches that result in new warnings. Reported-by: Eric Dumazet Signed-off-by: Florian Westphal Signed-off-by: David S. Miller --- include/linux/inetdevice.h | 21 ++++++--------------- 1 file changed, 6 insertions(+), 15 deletions(-) (limited to 'include') diff --git a/include/linux/inetdevice.h b/include/linux/inetdevice.h index d5d05503a04b..3515ca64e638 100644 --- a/include/linux/inetdevice.h +++ b/include/linux/inetdevice.h @@ -26,7 +26,7 @@ struct in_device { struct net_device *dev; refcount_t refcnt; int dead; - struct in_ifaddr *ifa_list; /* IP ifaddr chain */ + struct in_ifaddr __rcu *ifa_list;/* IP ifaddr chain */ struct ip_mc_list __rcu *mc_list; /* IP multicast filter chain */ struct ip_mc_list __rcu * __rcu *mc_hash; @@ -136,7 +136,7 @@ static inline void ipv4_devconf_setall(struct in_device *in_dev) struct in_ifaddr { struct hlist_node hash; - struct in_ifaddr *ifa_next; + struct in_ifaddr __rcu *ifa_next; struct in_device *ifa_dev; struct rcu_head rcu_head; __be32 ifa_local; @@ -206,22 +206,13 @@ static __inline__ bool bad_mask(__be32 mask, __be32 addr) return false; } -#define for_primary_ifa(in_dev) { struct in_ifaddr *ifa; \ - for (ifa = (in_dev)->ifa_list; ifa && !(ifa->ifa_flags&IFA_F_SECONDARY); ifa = ifa->ifa_next) - -#define for_ifa(in_dev) { struct in_ifaddr *ifa; \ - for (ifa = (in_dev)->ifa_list; ifa; ifa = ifa->ifa_next) - - -#define endfor_ifa(in_dev) } - #define in_dev_for_each_ifa_rtnl(ifa, in_dev) \ - for (ifa = (in_dev)->ifa_list; ifa; \ - ifa = ifa->ifa_next) + for (ifa = rtnl_dereference((in_dev)->ifa_list); ifa; \ + ifa = rtnl_dereference(ifa->ifa_next)) #define in_dev_for_each_ifa_rcu(ifa, in_dev) \ - for (ifa = (in_dev)->ifa_list; ifa; \ - ifa = ifa->ifa_next) + for (ifa = rcu_dereference((in_dev)->ifa_list); ifa; \ + ifa = rcu_dereference(ifa->ifa_next)) static inline struct in_device *__in_dev_get_rcu(const struct net_device *dev) { -- cgit v1.2.3 From 1cc26450a855aa35a6d515be14c539944d5f9648 Mon Sep 17 00:00:00 2001 From: Stanislav Fomichev Date: Fri, 31 May 2019 14:05:06 -0700 Subject: flow_dissector: remove unused FLOW_DISSECTOR_F_STOP_AT_L3 flag This flag is not used by any caller, remove it. Signed-off-by: Stanislav Fomichev Signed-off-by: David S. Miller --- include/net/flow_dissector.h | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/include/net/flow_dissector.h b/include/net/flow_dissector.h index 7c5a8d9a8d2a..797e19c2fc40 100644 --- a/include/net/flow_dissector.h +++ b/include/net/flow_dissector.h @@ -229,9 +229,8 @@ enum flow_dissector_key_id { }; #define FLOW_DISSECTOR_F_PARSE_1ST_FRAG BIT(0) -#define FLOW_DISSECTOR_F_STOP_AT_L3 BIT(1) -#define FLOW_DISSECTOR_F_STOP_AT_FLOW_LABEL BIT(2) -#define FLOW_DISSECTOR_F_STOP_AT_ENCAP BIT(3) +#define FLOW_DISSECTOR_F_STOP_AT_FLOW_LABEL BIT(1) +#define FLOW_DISSECTOR_F_STOP_AT_ENCAP BIT(2) struct flow_dissector_key { enum flow_dissector_key_id key_id; -- cgit v1.2.3 From fa85999f492e227b373c20db22acfa993d770e4b Mon Sep 17 00:00:00 2001 From: Edward Cree Date: Fri, 31 May 2019 22:47:21 +0100 Subject: flow_offload: include linux/kernel.h from flow_offload.h flow_stats_update() uses max_t, so ensure we have that defined. Signed-off-by: Edward Cree Signed-off-by: David S. Miller --- include/net/flow_offload.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/net/flow_offload.h b/include/net/flow_offload.h index a2df99f9b196..36fdb85c974d 100644 --- a/include/net/flow_offload.h +++ b/include/net/flow_offload.h @@ -1,6 +1,7 @@ #ifndef _NET_FLOW_OFFLOAD_H #define _NET_FLOW_OFFLOAD_H +#include #include struct flow_match { -- cgit v1.2.3 From b7034146756b9e91cc059b19df7fe4defd4d7de7 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Sun, 2 Jun 2019 11:24:18 -0700 Subject: net: fix use-after-free in kfree_skb_list syzbot reported nasty use-after-free [1] Lets remove frag_list field from structs ip_fraglist_iter and ip6_fraglist_iter. This seens not needed anyway. [1] : BUG: KASAN: use-after-free in kfree_skb_list+0x5d/0x60 net/core/skbuff.c:706 Read of size 8 at addr ffff888085a3cbc0 by task syz-executor303/8947 CPU: 0 PID: 8947 Comm: syz-executor303 Not tainted 5.2.0-rc2+ #12 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011 Call Trace: __dump_stack lib/dump_stack.c:77 [inline] dump_stack+0x172/0x1f0 lib/dump_stack.c:113 print_address_description.cold+0x7c/0x20d mm/kasan/report.c:188 __kasan_report.cold+0x1b/0x40 mm/kasan/report.c:317 kasan_report+0x12/0x20 mm/kasan/common.c:614 __asan_report_load8_noabort+0x14/0x20 mm/kasan/generic_report.c:132 kfree_skb_list+0x5d/0x60 net/core/skbuff.c:706 ip6_fragment+0x1ef4/0x2680 net/ipv6/ip6_output.c:882 __ip6_finish_output+0x577/0xaa0 net/ipv6/ip6_output.c:144 ip6_finish_output+0x38/0x1f0 net/ipv6/ip6_output.c:156 NF_HOOK_COND include/linux/netfilter.h:294 [inline] ip6_output+0x235/0x7f0 net/ipv6/ip6_output.c:179 dst_output include/net/dst.h:433 [inline] ip6_local_out+0xbb/0x1b0 net/ipv6/output_core.c:179 ip6_send_skb+0xbb/0x350 net/ipv6/ip6_output.c:1796 ip6_push_pending_frames+0xc8/0xf0 net/ipv6/ip6_output.c:1816 rawv6_push_pending_frames net/ipv6/raw.c:617 [inline] rawv6_sendmsg+0x2993/0x35e0 net/ipv6/raw.c:947 inet_sendmsg+0x141/0x5d0 net/ipv4/af_inet.c:802 sock_sendmsg_nosec net/socket.c:652 [inline] sock_sendmsg+0xd7/0x130 net/socket.c:671 ___sys_sendmsg+0x803/0x920 net/socket.c:2292 __sys_sendmsg+0x105/0x1d0 net/socket.c:2330 __do_sys_sendmsg net/socket.c:2339 [inline] __se_sys_sendmsg net/socket.c:2337 [inline] __x64_sys_sendmsg+0x78/0xb0 net/socket.c:2337 do_syscall_64+0xfd/0x680 arch/x86/entry/common.c:301 entry_SYSCALL_64_after_hwframe+0x49/0xbe RIP: 0033:0x44add9 Code: e8 7c e6 ff ff 48 83 c4 18 c3 0f 1f 80 00 00 00 00 48 89 f8 48 89 f7 48 89 d6 48 89 ca 4d 89 c2 4d 89 c8 4c 8b 4c 24 08 0f 05 <48> 3d 01 f0 ff ff 0f 83 1b 05 fc ff c3 66 2e 0f 1f 84 00 00 00 00 RSP: 002b:00007f826f33bce8 EFLAGS: 00000246 ORIG_RAX: 000000000000002e RAX: ffffffffffffffda RBX: 00000000006e7a18 RCX: 000000000044add9 RDX: 0000000000000000 RSI: 0000000020000240 RDI: 0000000000000005 RBP: 00000000006e7a10 R08: 0000000000000000 R09: 0000000000000000 R10: 0000000000000000 R11: 0000000000000246 R12: 00000000006e7a1c R13: 00007ffcec4f7ebf R14: 00007f826f33c9c0 R15: 20c49ba5e353f7cf Allocated by task 8947: save_stack+0x23/0x90 mm/kasan/common.c:71 set_track mm/kasan/common.c:79 [inline] __kasan_kmalloc mm/kasan/common.c:489 [inline] __kasan_kmalloc.constprop.0+0xcf/0xe0 mm/kasan/common.c:462 kasan_slab_alloc+0xf/0x20 mm/kasan/common.c:497 slab_post_alloc_hook mm/slab.h:437 [inline] slab_alloc_node mm/slab.c:3269 [inline] kmem_cache_alloc_node+0x131/0x710 mm/slab.c:3579 __alloc_skb+0xd5/0x5e0 net/core/skbuff.c:199 alloc_skb include/linux/skbuff.h:1058 [inline] __ip6_append_data.isra.0+0x2a24/0x3640 net/ipv6/ip6_output.c:1519 ip6_append_data+0x1e5/0x320 net/ipv6/ip6_output.c:1688 rawv6_sendmsg+0x1467/0x35e0 net/ipv6/raw.c:940 inet_sendmsg+0x141/0x5d0 net/ipv4/af_inet.c:802 sock_sendmsg_nosec net/socket.c:652 [inline] sock_sendmsg+0xd7/0x130 net/socket.c:671 ___sys_sendmsg+0x803/0x920 net/socket.c:2292 __sys_sendmsg+0x105/0x1d0 net/socket.c:2330 __do_sys_sendmsg net/socket.c:2339 [inline] __se_sys_sendmsg net/socket.c:2337 [inline] __x64_sys_sendmsg+0x78/0xb0 net/socket.c:2337 do_syscall_64+0xfd/0x680 arch/x86/entry/common.c:301 entry_SYSCALL_64_after_hwframe+0x49/0xbe Freed by task 8947: save_stack+0x23/0x90 mm/kasan/common.c:71 set_track mm/kasan/common.c:79 [inline] __kasan_slab_free+0x102/0x150 mm/kasan/common.c:451 kasan_slab_free+0xe/0x10 mm/kasan/common.c:459 __cache_free mm/slab.c:3432 [inline] kmem_cache_free+0x86/0x260 mm/slab.c:3698 kfree_skbmem net/core/skbuff.c:625 [inline] kfree_skbmem+0xc5/0x150 net/core/skbuff.c:619 __kfree_skb net/core/skbuff.c:682 [inline] kfree_skb net/core/skbuff.c:699 [inline] kfree_skb+0xf0/0x390 net/core/skbuff.c:693 kfree_skb_list+0x44/0x60 net/core/skbuff.c:708 __dev_xmit_skb net/core/dev.c:3551 [inline] __dev_queue_xmit+0x3034/0x36b0 net/core/dev.c:3850 dev_queue_xmit+0x18/0x20 net/core/dev.c:3914 neigh_direct_output+0x16/0x20 net/core/neighbour.c:1532 neigh_output include/net/neighbour.h:511 [inline] ip6_finish_output2+0x1034/0x2550 net/ipv6/ip6_output.c:120 ip6_fragment+0x1ebb/0x2680 net/ipv6/ip6_output.c:863 __ip6_finish_output+0x577/0xaa0 net/ipv6/ip6_output.c:144 ip6_finish_output+0x38/0x1f0 net/ipv6/ip6_output.c:156 NF_HOOK_COND include/linux/netfilter.h:294 [inline] ip6_output+0x235/0x7f0 net/ipv6/ip6_output.c:179 dst_output include/net/dst.h:433 [inline] ip6_local_out+0xbb/0x1b0 net/ipv6/output_core.c:179 ip6_send_skb+0xbb/0x350 net/ipv6/ip6_output.c:1796 ip6_push_pending_frames+0xc8/0xf0 net/ipv6/ip6_output.c:1816 rawv6_push_pending_frames net/ipv6/raw.c:617 [inline] rawv6_sendmsg+0x2993/0x35e0 net/ipv6/raw.c:947 inet_sendmsg+0x141/0x5d0 net/ipv4/af_inet.c:802 sock_sendmsg_nosec net/socket.c:652 [inline] sock_sendmsg+0xd7/0x130 net/socket.c:671 ___sys_sendmsg+0x803/0x920 net/socket.c:2292 __sys_sendmsg+0x105/0x1d0 net/socket.c:2330 __do_sys_sendmsg net/socket.c:2339 [inline] __se_sys_sendmsg net/socket.c:2337 [inline] __x64_sys_sendmsg+0x78/0xb0 net/socket.c:2337 do_syscall_64+0xfd/0x680 arch/x86/entry/common.c:301 entry_SYSCALL_64_after_hwframe+0x49/0xbe The buggy address belongs to the object at ffff888085a3cbc0 which belongs to the cache skbuff_head_cache of size 224 The buggy address is located 0 bytes inside of 224-byte region [ffff888085a3cbc0, ffff888085a3cca0) The buggy address belongs to the page: page:ffffea0002168f00 refcount:1 mapcount:0 mapping:ffff88821b6f63c0 index:0x0 flags: 0x1fffc0000000200(slab) raw: 01fffc0000000200 ffffea00027bbf88 ffffea0002105b88 ffff88821b6f63c0 raw: 0000000000000000 ffff888085a3c080 000000010000000c 0000000000000000 page dumped because: kasan: bad access detected Memory state around the buggy address: ffff888085a3ca80: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 ffff888085a3cb00: 00 00 00 00 00 00 00 00 00 00 00 00 fc fc fc fc >ffff888085a3cb80: fc fc fc fc fc fc fc fc fb fb fb fb fb fb fb fb ^ ffff888085a3cc00: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb ffff888085a3cc80: fb fb fb fb fc fc fc fc fc fc fc fc fc fc fc fc Fixes: 0feca6190f88 ("net: ipv6: add skbuff fraglist splitter") Fixes: c8b17be0b7a4 ("net: ipv4: add skbuff fraglist splitter") Signed-off-by: Eric Dumazet Cc: Pablo Neira Ayuso Acked-by: Pablo Neira Ayuso Signed-off-by: David S. Miller --- include/net/ip.h | 1 - include/net/ipv6.h | 1 - 2 files changed, 2 deletions(-) (limited to 'include') diff --git a/include/net/ip.h b/include/net/ip.h index 029cc3fd26bd..cd5cde5532d5 100644 --- a/include/net/ip.h +++ b/include/net/ip.h @@ -167,7 +167,6 @@ int ip_do_fragment(struct net *net, struct sock *sk, struct sk_buff *skb, int (*output)(struct net *, struct sock *, struct sk_buff *)); struct ip_fraglist_iter { - struct sk_buff *frag_list; struct sk_buff *frag; struct iphdr *iph; int offset; diff --git a/include/net/ipv6.h b/include/net/ipv6.h index 21bb830e9679..0d34f6ed9681 100644 --- a/include/net/ipv6.h +++ b/include/net/ipv6.h @@ -156,7 +156,6 @@ struct frag_hdr { struct ip6_fraglist_iter { struct ipv6hdr *tmp_hdr; - struct sk_buff *frag_list; struct sk_buff *frag; int offset; unsigned int hlen; -- cgit v1.2.3 From 191ed2024de9fcfaab24106f9dbf7e544b07d633 Mon Sep 17 00:00:00 2001 From: Jiri Pirko Date: Tue, 4 Jun 2019 15:40:40 +0200 Subject: devlink: allow driver to update progress of flash update Introduce a function to be called from drivers during flash. It sends notification to userspace about flash update progress. Signed-off-by: Jiri Pirko Reviewed-by: Jakub Kicinski Reviewed-by: Ido Schimmel Signed-off-by: David S. Miller --- include/net/devlink.h | 8 ++++++++ include/uapi/linux/devlink.h | 5 +++++ 2 files changed, 13 insertions(+) (limited to 'include') diff --git a/include/net/devlink.h b/include/net/devlink.h index 151eb930d329..8f65356132be 100644 --- a/include/net/devlink.h +++ b/include/net/devlink.h @@ -741,6 +741,14 @@ void devlink_health_reporter_state_update(struct devlink_health_reporter *reporter, enum devlink_health_reporter_state state); +void devlink_flash_update_begin_notify(struct devlink *devlink); +void devlink_flash_update_end_notify(struct devlink *devlink); +void devlink_flash_update_status_notify(struct devlink *devlink, + const char *status_msg, + const char *component, + unsigned long done, + unsigned long total); + #if IS_ENABLED(CONFIG_NET_DEVLINK) void devlink_compat_running_version(struct net_device *dev, diff --git a/include/uapi/linux/devlink.h b/include/uapi/linux/devlink.h index 5bb4ea67d84f..5287b42c181f 100644 --- a/include/uapi/linux/devlink.h +++ b/include/uapi/linux/devlink.h @@ -104,6 +104,8 @@ enum devlink_command { DEVLINK_CMD_HEALTH_REPORTER_DUMP_CLEAR, DEVLINK_CMD_FLASH_UPDATE, + DEVLINK_CMD_FLASH_UPDATE_END, /* notification only */ + DEVLINK_CMD_FLASH_UPDATE_STATUS, /* notification only */ /* add new commands above here */ __DEVLINK_CMD_MAX, @@ -331,6 +333,9 @@ enum devlink_attr { DEVLINK_ATTR_FLASH_UPDATE_FILE_NAME, /* string */ DEVLINK_ATTR_FLASH_UPDATE_COMPONENT, /* string */ + DEVLINK_ATTR_FLASH_UPDATE_STATUS_MSG, /* string */ + DEVLINK_ATTR_FLASH_UPDATE_STATUS_DONE, /* u64 */ + DEVLINK_ATTR_FLASH_UPDATE_STATUS_TOTAL, /* u64 */ /* add new attributes above here, update the policy in devlink.c */ -- cgit v1.2.3 From da29e4b466e6916a52e0e2f60054f855c324a9c2 Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Mon, 3 Jun 2019 15:16:58 -0700 Subject: net/tls: fully initialize the msg wrapper skb If strparser gets cornered into starting a new message from an sk_buff which already has frags, it will allocate a new skb to become the "wrapper" around the fragments of the message. This new skb does not inherit any metadata fields. In case of TLS offload this may lead to unnecessarily re-encrypting the message, as skb->decrypted is not set for the wrapper skb. Try to be conservative and copy all fields of old skb strparser's user may reasonably need. Signed-off-by: Jakub Kicinski Reviewed-by: Dirk van der Merwe Reviewed-by: Simon Horman Signed-off-by: David S. Miller --- include/linux/skbuff.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 2ee5e63195c0..98ff5ac98caa 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -1063,6 +1063,7 @@ struct sk_buff *alloc_skb_with_frags(unsigned long header_len, int max_page_order, int *errcode, gfp_t gfp_mask); +struct sk_buff *alloc_skb_for_msg(struct sk_buff *first); /* Layout of fast clones : [skb1][skb2][fclone_ref] */ struct sk_buff_fclones { -- cgit v1.2.3 From f0aaa2c975617da78b80feebc87e74dba9ec1f53 Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Mon, 3 Jun 2019 15:17:04 -0700 Subject: net/tls: reorganize struct tls_context struct tls_context is slightly badly laid out. If we reorder things right we can save 16 bytes (320 -> 304) but also make all fast path data fit into two cache lines (one read only and one read/write, down from four cache lines). Signed-off-by: Jakub Kicinski Reviewed-by: Dirk van der Merwe Signed-off-by: David S. Miller --- include/net/tls.h | 26 +++++++++++++++----------- 1 file changed, 15 insertions(+), 11 deletions(-) (limited to 'include') diff --git a/include/net/tls.h b/include/net/tls.h index 39ea62f0c1f6..a463a6074e5d 100644 --- a/include/net/tls.h +++ b/include/net/tls.h @@ -236,34 +236,32 @@ struct tls_prot_info { }; struct tls_context { + /* read-only cache line */ struct tls_prot_info prot_info; - union tls_crypto_context crypto_send; - union tls_crypto_context crypto_recv; + u8 tx_conf:3; + u8 rx_conf:3; - struct list_head list; - struct net_device *netdev; - refcount_t refcount; + int (*push_pending_record)(struct sock *sk, int flags); + void (*sk_write_space)(struct sock *sk); void *priv_ctx_tx; void *priv_ctx_rx; - u8 tx_conf:3; - u8 rx_conf:3; + struct net_device *netdev; + /* rw cache line */ struct cipher_context tx; struct cipher_context rx; struct scatterlist *partially_sent_record; u16 partially_sent_offset; - unsigned long flags; bool in_tcp_sendpages; bool pending_open_record_frags; + unsigned long flags; - int (*push_pending_record)(struct sock *sk, int flags); - - void (*sk_write_space)(struct sock *sk); + /* cache cold stuff */ void (*sk_destruct)(struct sock *sk); void (*sk_proto_close)(struct sock *sk, long timeout); @@ -275,6 +273,12 @@ struct tls_context { int __user *optlen); int (*hash)(struct sock *sk); void (*unhash)(struct sock *sk); + + union tls_crypto_context crypto_send; + union tls_crypto_context crypto_recv; + + struct list_head list; + refcount_t refcount; }; enum tls_offload_ctx_dir { -- cgit v1.2.3 From fb0f886fa265f265ad126fc7cd7e8ec51e2f770f Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Mon, 3 Jun 2019 15:17:05 -0700 Subject: net/tls: don't pass version to tls_advance_record_sn() All callers pass prot->version as the last parameter of tls_advance_record_sn(), yet tls_advance_record_sn() itself needs a pointer to prot. Pass prot from callers. Signed-off-by: Jakub Kicinski Reviewed-by: Dirk van der Merwe Signed-off-by: David S. Miller --- include/net/tls.h | 10 +++------- 1 file changed, 3 insertions(+), 7 deletions(-) (limited to 'include') diff --git a/include/net/tls.h b/include/net/tls.h index a463a6074e5d..0a0072636009 100644 --- a/include/net/tls.h +++ b/include/net/tls.h @@ -446,19 +446,15 @@ static inline struct tls_context *tls_get_ctx(const struct sock *sk) } static inline void tls_advance_record_sn(struct sock *sk, - struct cipher_context *ctx, - int version) + struct tls_prot_info *prot, + struct cipher_context *ctx) { - struct tls_context *tls_ctx = tls_get_ctx(sk); - struct tls_prot_info *prot = &tls_ctx->prot_info; - if (tls_bigint_increment(ctx->rec_seq, prot->rec_seq_size)) tls_err_abort(sk, EBADMSG); - if (version != TLS_1_3_VERSION) { + if (prot->version != TLS_1_3_VERSION) tls_bigint_increment(ctx->iv + TLS_CIPHER_AES_GCM_128_SALT_SIZE, prot->iv_size); - } } static inline void tls_fill_prepend(struct tls_context *ctx, -- cgit v1.2.3 From 5481d73f81549e2a05cbbb49867a9a560c5292df Mon Sep 17 00:00:00 2001 From: David Ahern Date: Mon, 3 Jun 2019 20:19:49 -0700 Subject: ipv4: Use accessors for fib_info nexthop data Use helpers to access fib_nh and fib_nhs fields of a fib_info. Drop the fib_dev macro which is an alias for the first nexthop. Replacements: fi->fib_dev --> fib_info_nh(fi, 0)->fib_nh_dev fi->fib_nh --> fib_info_nh(fi, 0) fi->fib_nh[i] --> fib_info_nh(fi, i) fi->fib_nhs --> fib_info_num_path(fi) where fib_info_nh(fi, i) returns fi->fib_nh[nhsel] and fib_info_num_path returns fi->fib_nhs. Move the existing fib_info_nhc to nexthop.h and define the new ones there. A later patch adds a check if a fib_info uses a nexthop object, and defining the helpers in nexthop.h avoid circular header dependencies. After this all remaining open coded references to fi->fib_nhs and fi->fib_nh are in: - fib_create_info and helpers used to lookup an existing fib_info entry, and - the netdev event functions fib_sync_down_dev and fib_sync_up. The latter two will not be reused for nexthops, and the fib_create_info will be updated to handle a nexthop in a fib_info. Signed-off-by: David Ahern Signed-off-by: David S. Miller --- include/net/ip_fib.h | 6 ------ include/net/nexthop.h | 15 +++++++++++++++ 2 files changed, 15 insertions(+), 6 deletions(-) (limited to 'include') diff --git a/include/net/ip_fib.h b/include/net/ip_fib.h index 70ba0302c8c9..42b1a806f6f5 100644 --- a/include/net/ip_fib.h +++ b/include/net/ip_fib.h @@ -153,7 +153,6 @@ struct fib_info { bool nh_updated; struct rcu_head rcu; struct fib_nh fib_nh[0]; -#define fib_dev fib_nh[0].fib_nh_dev }; @@ -190,11 +189,6 @@ struct fib_result_nl { int err; }; -static inline struct fib_nh_common *fib_info_nhc(struct fib_info *fi, int nhsel) -{ - return &fi->fib_nh[nhsel].nh_common; -} - #ifdef CONFIG_IP_MULTIPLE_TABLES #define FIB_TABLE_HASHSZ 256 #else diff --git a/include/net/nexthop.h b/include/net/nexthop.h index 6e1b8f53624c..e501d77b82c8 100644 --- a/include/net/nexthop.h +++ b/include/net/nexthop.h @@ -192,4 +192,19 @@ static inline bool nexthop_is_blackhole(const struct nexthop *nh) nhi = rcu_dereference_rtnl(nh->nh_info); return nhi->reject_nh; } + +static inline unsigned int fib_info_num_path(const struct fib_info *fi) +{ + return fi->fib_nhs; +} + +static inline struct fib_nh_common *fib_info_nhc(struct fib_info *fi, int nhsel) +{ + return &fi->fib_nh[nhsel].nh_common; +} + +static inline struct fib_nh *fib_info_nh(struct fib_info *fi, int nhsel) +{ + return &fi->fib_nh[nhsel]; +} #endif -- cgit v1.2.3 From dcb1ecb50edf8219c3bd851de35897fb024c423b Mon Sep 17 00:00:00 2001 From: David Ahern Date: Mon, 3 Jun 2019 20:19:50 -0700 Subject: ipv4: Prepare for fib6_nh from a nexthop object Convert more IPv4 code to use fib_nh_common over fib_nh to enable routes to use a fib6_nh based nexthop. In the end, only code not using a nexthop object in a fib_info should directly access fib_nh in a fib_info without checking the famiy and going through fib_nh_common. Those functions will be marked when it is not directly evident. Signed-off-by: David Ahern Signed-off-by: David S. Miller --- include/net/ip_fib.h | 15 +++++++++++---- 1 file changed, 11 insertions(+), 4 deletions(-) (limited to 'include') diff --git a/include/net/ip_fib.h b/include/net/ip_fib.h index 42b1a806f6f5..7da8ea784029 100644 --- a/include/net/ip_fib.h +++ b/include/net/ip_fib.h @@ -195,8 +195,8 @@ struct fib_result_nl { #define FIB_TABLE_HASHSZ 2 #endif -__be32 fib_info_update_nh_saddr(struct net *net, struct fib_nh *nh, - unsigned char scope); +__be32 fib_info_update_nhc_saddr(struct net *net, struct fib_nh_common *nhc, + unsigned char scope); __be32 fib_result_prefsrc(struct net *net, struct fib_result *res); #define FIB_RES_NHC(res) ((res).nhc) @@ -455,11 +455,18 @@ static inline void fib_combine_itag(u32 *itag, const struct fib_result *res) { #ifdef CONFIG_IP_ROUTE_CLASSID struct fib_nh_common *nhc = res->nhc; - struct fib_nh *nh = container_of(nhc, struct fib_nh, nh_common); #ifdef CONFIG_IP_MULTIPLE_TABLES u32 rtag; #endif - *itag = nh->nh_tclassid << 16; + if (nhc->nhc_family == AF_INET) { + struct fib_nh *nh; + + nh = container_of(nhc, struct fib_nh, nh_common); + *itag = nh->nh_tclassid << 16; + } else { + *itag = 0; + } + #ifdef CONFIG_IP_MULTIPLE_TABLES rtag = res->tclassid; if (*itag == 0) -- cgit v1.2.3 From 4c7e8084fd467ddb2b0e6c6011f9c1064afb7e56 Mon Sep 17 00:00:00 2001 From: David Ahern Date: Mon, 3 Jun 2019 20:19:51 -0700 Subject: ipv4: Plumb support for nexthop object in a fib_info Add 'struct nexthop' and nh_list list_head to fib_info. nh_list is the fib_info side of the nexthop <-> fib_info relationship. Add fi_list list_head to 'struct nexthop' to track fib_info entries using a nexthop instance. Add __remove_nexthop_fib and add it to __remove_nexthop to walk the new list_head and mark those fib entries as dead when the nexthop is deleted. Add a few nexthop helpers for use when a nexthop is added to fib_info: - nexthop_cmp to determine if 2 nexthops are the same - nexthop_path_fib_result to select a path for a multipath 'struct nexthop' - nexthop_fib_nhc to select a specific fib_nh_common within a multipath 'struct nexthop' Update existing fib_info_nhc to use nexthop_fib_nhc if a fib_info uses a 'struct nexthop', and mark fib_info_nh as only used for the non-nexthop case. Update the fib_info functions to check for fi->nh and take a different path as needed: - free_fib_info_rcu - put the nexthop object reference - fib_release_info - remove the fib_info from the nexthop's fi_list - nh_comp - use nexthop_cmp when either fib_info references a nexthop object - fib_info_hashfn - use the nexthop id for the hashing vs the oif of each fib_nh in a fib_info - fib_nlmsg_size - add space for the RTA_NH_ID attribute - fib_create_info - verify nexthop reference can be taken, verify nexthop spec is valid for fib entry, and add fib_info to fi_list for a nexthop - fib_select_multipath - use the new nexthop_path_fib_result to select a path when nexthop objects are used - fib_table_lookup - if the 'struct nexthop' is a blackhole nexthop, treat it the same as a fib entry using 'blackhole' The bulk of the changes are in fib_semantics.c and most of that is moving the existing change_nexthops into an else branch. Update the nexthop code to walk fi_list on a nexthop deleted to remove fib entries referencing it. Signed-off-by: David Ahern Signed-off-by: David S. Miller --- include/net/ip_fib.h | 4 ++++ include/net/nexthop.h | 48 ++++++++++++++++++++++++++++++++++++++++++++++++ 2 files changed, 52 insertions(+) (limited to 'include') diff --git a/include/net/ip_fib.h b/include/net/ip_fib.h index 7da8ea784029..071d280de389 100644 --- a/include/net/ip_fib.h +++ b/include/net/ip_fib.h @@ -129,9 +129,12 @@ struct fib_nh { * This structure contains data shared by many of routes. */ +struct nexthop; + struct fib_info { struct hlist_node fib_hash; struct hlist_node fib_lhash; + struct list_head nh_list; struct net *fib_net; int fib_treeref; refcount_t fib_clntref; @@ -151,6 +154,7 @@ struct fib_info { int fib_nhs; bool fib_nh_is_v6; bool nh_updated; + struct nexthop *nh; struct rcu_head rcu; struct fib_nh fib_nh[0]; }; diff --git a/include/net/nexthop.h b/include/net/nexthop.h index e501d77b82c8..2912a2d7a515 100644 --- a/include/net/nexthop.h +++ b/include/net/nexthop.h @@ -77,6 +77,7 @@ struct nh_group { struct nexthop { struct rb_node rb_node; /* entry on netns rbtree */ + struct list_head fi_list; /* v4 entries using nh */ struct list_head grp_list; /* nh group entries using this nh */ struct net *net; @@ -110,6 +111,12 @@ static inline void nexthop_put(struct nexthop *nh) call_rcu(&nh->rcu, nexthop_free_rcu); } +static inline bool nexthop_cmp(const struct nexthop *nh1, + const struct nexthop *nh2) +{ + return nh1 == nh2; +} + static inline bool nexthop_is_multipath(const struct nexthop *nh) { if (nh->is_group) { @@ -193,18 +200,59 @@ static inline bool nexthop_is_blackhole(const struct nexthop *nh) return nhi->reject_nh; } +static inline void nexthop_path_fib_result(struct fib_result *res, int hash) +{ + struct nh_info *nhi; + struct nexthop *nh; + + nh = nexthop_select_path(res->fi->nh, hash); + nhi = rcu_dereference(nh->nh_info); + res->nhc = &nhi->fib_nhc; +} + +/* called with rcu read lock or rtnl held */ +static inline +struct fib_nh_common *nexthop_fib_nhc(struct nexthop *nh, int nhsel) +{ + struct nh_info *nhi; + + BUILD_BUG_ON(offsetof(struct fib_nh, nh_common) != 0); + BUILD_BUG_ON(offsetof(struct fib6_nh, nh_common) != 0); + + if (nexthop_is_multipath(nh)) { + nh = nexthop_mpath_select(nh, nhsel); + if (!nh) + return NULL; + } + + nhi = rcu_dereference_rtnl(nh->nh_info); + return &nhi->fib_nhc; +} + static inline unsigned int fib_info_num_path(const struct fib_info *fi) { + if (unlikely(fi->nh)) + return nexthop_num_path(fi->nh); + return fi->fib_nhs; } +int fib_check_nexthop(struct nexthop *nh, u8 scope, + struct netlink_ext_ack *extack); + static inline struct fib_nh_common *fib_info_nhc(struct fib_info *fi, int nhsel) { + if (unlikely(fi->nh)) + return nexthop_fib_nhc(fi->nh, nhsel); + return &fi->fib_nh[nhsel].nh_common; } +/* only used when fib_nh is built into fib_info */ static inline struct fib_nh *fib_info_nh(struct fib_info *fi, int nhsel) { + WARN_ON(fi->nh); + return &fi->fib_nh[nhsel]; } #endif -- cgit v1.2.3 From f88d8ea67fbdbac7a64bfa6ed9a2ba27bb822f74 Mon Sep 17 00:00:00 2001 From: David Ahern Date: Mon, 3 Jun 2019 20:19:52 -0700 Subject: ipv6: Plumb support for nexthop object in a fib6_info Add struct nexthop and nh_list list_head to fib6_info. nh_list is the fib6_info side of the nexthop <-> fib_info relationship. Since a fib6_info referencing a nexthop object can not have 'sibling' entries (the old way of doing multipath routes), the nh_list is a union with fib6_siblings. Add f6i_list list_head to 'struct nexthop' to track fib6_info entries using a nexthop instance. Update __remove_nexthop_fib to walk f6_list and delete fib entries using the nexthop. Add a few nexthop helpers for use when a nexthop is added to fib6_info: - nexthop_fib6_nh - return first fib6_nh in a nexthop object - fib6_info_nh_dev moved to nexthop.h and updated to use nexthop_fib6_nh if the fib6_info references a nexthop object - nexthop_path_fib6_result - similar to ipv4, select a path within a multipath nexthop object. If the nexthop is a blackhole, set fib6_result type to RTN_BLACKHOLE, and set the REJECT flag Update the fib6_info references to check for nh and take a different path as needed: - rt6_qualify_for_ecmp - if a fib entry uses a nexthop object it can NOT be coalesced with other fib entries into a multipath route - rt6_duplicate_nexthop - use nexthop_cmp if either fib6_info references a nexthop - addrconf (host routes), RA's and info entries (anything configured via ndisc) does not use nexthop objects - fib6_info_destroy_rcu - put reference to nexthop object - fib6_purge_rt - drop fib6_info from f6i_list - fib6_select_path - update to use the new nexthop_path_fib6_result when fib entry uses a nexthop object - rt6_device_match - update to catch use of nexthop object as a blackhole and set fib6_type and flags. - ip6_route_info_create - don't add space for fib6_nh if fib entry is going to reference a nexthop object, take a reference to nexthop object, disallow use of source routing - rt6_nlmsg_size - add space for RTA_NH_ID - add rt6_fill_node_nexthop to add nexthop data on a dump As with ipv4, most of the changes push existing code into the else branch of whether the fib entry uses a nexthop object. Update the nexthop code to walk f6i_list on a nexthop deleted to remove fib entries referencing it. Signed-off-by: David Ahern Signed-off-by: David S. Miller --- include/net/ip6_fib.h | 11 +++++------ include/net/ip6_route.h | 13 +++++++++++-- include/net/nexthop.h | 50 +++++++++++++++++++++++++++++++++++++++++++++++++ 3 files changed, 66 insertions(+), 8 deletions(-) (limited to 'include') diff --git a/include/net/ip6_fib.h b/include/net/ip6_fib.h index ebe5d65f97e0..1a8acd51b277 100644 --- a/include/net/ip6_fib.h +++ b/include/net/ip6_fib.h @@ -146,7 +146,10 @@ struct fib6_info { * destination, but not the same gateway. nsiblings is just a cache * to speed up lookup. */ - struct list_head fib6_siblings; + union { + struct list_head fib6_siblings; + struct list_head nh_list; + }; unsigned int fib6_nsiblings; refcount_t fib6_ref; @@ -170,6 +173,7 @@ struct fib6_info { unused:3; struct rcu_head rcu; + struct nexthop *nh; struct fib6_nh fib6_nh[0]; }; @@ -441,11 +445,6 @@ void rt6_get_prefsrc(const struct rt6_info *rt, struct in6_addr *addr) rcu_read_unlock(); } -static inline struct net_device *fib6_info_nh_dev(const struct fib6_info *f6i) -{ - return f6i->fib6_nh->fib_nh_dev; -} - int fib6_nh_init(struct net *net, struct fib6_nh *fib6_nh, struct fib6_config *cfg, gfp_t gfp_flags, struct netlink_ext_ack *extack); diff --git a/include/net/ip6_route.h b/include/net/ip6_route.h index a6ce6ea856b9..7375a165fd98 100644 --- a/include/net/ip6_route.h +++ b/include/net/ip6_route.h @@ -27,6 +27,7 @@ struct route_info { #include #include #include +#include #define RT6_LOOKUP_F_IFACE 0x00000001 #define RT6_LOOKUP_F_REACHABLE 0x00000002 @@ -66,10 +67,13 @@ static inline bool rt6_need_strict(const struct in6_addr *daddr) (IPV6_ADDR_MULTICAST | IPV6_ADDR_LINKLOCAL | IPV6_ADDR_LOOPBACK); } +/* fib entries using a nexthop object can not be coalesced into + * a multipath route + */ static inline bool rt6_qualify_for_ecmp(const struct fib6_info *f6i) { /* the RTF_ADDRCONF flag filters out RA's */ - return !(f6i->fib6_flags & RTF_ADDRCONF) && + return !(f6i->fib6_flags & RTF_ADDRCONF) && !f6i->nh && f6i->fib6_nh->fib_nh_gw_family; } @@ -275,8 +279,13 @@ static inline struct in6_addr *rt6_nexthop(struct rt6_info *rt, static inline bool rt6_duplicate_nexthop(struct fib6_info *a, struct fib6_info *b) { - struct fib6_nh *nha = a->fib6_nh, *nhb = b->fib6_nh; + struct fib6_nh *nha, *nhb; + + if (a->nh || b->nh) + return nexthop_cmp(a->nh, b->nh); + nha = a->fib6_nh; + nhb = b->fib6_nh; return nha->fib_nh_dev == nhb->fib_nh_dev && ipv6_addr_equal(&nha->fib_nh_gw6, &nhb->fib_nh_gw6) && !lwtunnel_cmp_encap(nha->fib_nh_lws, nhb->fib_nh_lws); diff --git a/include/net/nexthop.h b/include/net/nexthop.h index 2912a2d7a515..aff7b2410057 100644 --- a/include/net/nexthop.h +++ b/include/net/nexthop.h @@ -10,6 +10,7 @@ #define __LINUX_NEXTHOP_H #include +#include #include #include #include @@ -78,6 +79,7 @@ struct nh_group { struct nexthop { struct rb_node rb_node; /* entry on netns rbtree */ struct list_head fi_list; /* v4 entries using nh */ + struct list_head f6i_list; /* v6 entries using nh */ struct list_head grp_list; /* nh group entries using this nh */ struct net *net; @@ -255,4 +257,52 @@ static inline struct fib_nh *fib_info_nh(struct fib_info *fi, int nhsel) return &fi->fib_nh[nhsel]; } + +/* + * IPv6 variants + */ +int fib6_check_nexthop(struct nexthop *nh, struct fib6_config *cfg, + struct netlink_ext_ack *extack); + +static inline struct fib6_nh *nexthop_fib6_nh(struct nexthop *nh) +{ + struct nh_info *nhi; + + if (nexthop_is_multipath(nh)) { + nh = nexthop_mpath_select(nh, 0); + if (!nh) + return NULL; + } + + nhi = rcu_dereference_rtnl(nh->nh_info); + if (nhi->family == AF_INET6) + return &nhi->fib6_nh; + + return NULL; +} + +static inline struct net_device *fib6_info_nh_dev(struct fib6_info *f6i) +{ + struct fib6_nh *fib6_nh; + + fib6_nh = f6i->nh ? nexthop_fib6_nh(f6i->nh) : f6i->fib6_nh; + return fib6_nh->fib_nh_dev; +} + +static inline void nexthop_path_fib6_result(struct fib6_result *res, int hash) +{ + struct nexthop *nh = res->f6i->nh; + struct nh_info *nhi; + + nh = nexthop_select_path(nh, hash); + + nhi = rcu_dereference_rtnl(nh->nh_info); + if (nhi->reject_nh) { + res->fib6_type = RTN_BLACKHOLE; + res->fib6_flags |= RTF_REJECT; + res->nh = nexthop_fib6_nh(nh); + } else { + res->nh = &nhi->fib6_nh; + } +} #endif -- cgit v1.2.3 From bac9593515c653e9ec05df9e303cdf1b969854d4 Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Fri, 3 May 2019 17:46:14 +0200 Subject: xfrm: remove init_tempsel indirection from xfrm_state_afinfo Simple initialization, handle it in the caller. Signed-off-by: Florian Westphal Signed-off-by: Steffen Klassert --- 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 a2907873ed56..ba65434b5293 100644 --- a/include/net/xfrm.h +++ b/include/net/xfrm.h @@ -354,8 +354,6 @@ struct xfrm_state_afinfo { const struct xfrm_type_offload *type_offload_map[IPPROTO_MAX]; int (*init_flags)(struct xfrm_state *x); - void (*init_tempsel)(struct xfrm_selector *sel, - const struct flowi *fl); void (*init_temprop)(struct xfrm_state *x, const struct xfrm_tmpl *tmpl, const xfrm_address_t *daddr, -- cgit v1.2.3 From 5c1b9ab3ec81992bef9a8605b8b281b41577b475 Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Fri, 3 May 2019 17:46:15 +0200 Subject: xfrm: remove init_temprop indirection from xfrm_state_afinfo same as previous patch: just place this in the caller, no need to have an indirection for a structure initialization. Signed-off-by: Florian Westphal Signed-off-by: Steffen Klassert --- include/net/xfrm.h | 4 ---- 1 file changed, 4 deletions(-) (limited to 'include') diff --git a/include/net/xfrm.h b/include/net/xfrm.h index ba65434b5293..e8f676ce27be 100644 --- a/include/net/xfrm.h +++ b/include/net/xfrm.h @@ -354,10 +354,6 @@ struct xfrm_state_afinfo { const struct xfrm_type_offload *type_offload_map[IPPROTO_MAX]; int (*init_flags)(struct xfrm_state *x); - void (*init_temprop)(struct xfrm_state *x, - const struct xfrm_tmpl *tmpl, - const xfrm_address_t *daddr, - 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 net *net, struct sock *sk, struct sk_buff *skb); -- cgit v1.2.3 From e46817472a1d7da32e8f265f9469a4e2fa39c60f Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Fri, 3 May 2019 17:46:16 +0200 Subject: xfrm: remove init_flags indirection from xfrm_state_afinfo There is only one implementation of this function; just call it directly. Signed-off-by: Florian Westphal Signed-off-by: Steffen Klassert --- include/net/xfrm.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include') diff --git a/include/net/xfrm.h b/include/net/xfrm.h index e8f676ce27be..61214f5c3205 100644 --- a/include/net/xfrm.h +++ b/include/net/xfrm.h @@ -353,7 +353,6 @@ struct xfrm_state_afinfo { const struct xfrm_type *type_map[IPPROTO_MAX]; const struct xfrm_type_offload *type_offload_map[IPPROTO_MAX]; - int (*init_flags)(struct xfrm_state *x); 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 net *net, struct sock *sk, struct sk_buff *skb); -- cgit v1.2.3 From c54c2c72b2b90a3ba61b8cad032a578ce2bf5b35 Mon Sep 17 00:00:00 2001 From: Anirudh Venkataramanan Date: Thu, 11 Apr 2019 09:11:33 -0700 Subject: net: Add a define for LLDP ethertype Add a new define ETH_P_LLDP for Link Layer Discovery Protocol (LLDP) ethertype. Suggested-by: Bruce Allan Signed-off-by: Anirudh Venkataramanan Tested-by: Andrew Bowers Signed-off-by: Jeff Kirsher --- include/uapi/linux/if_ether.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/uapi/linux/if_ether.h b/include/uapi/linux/if_ether.h index 3158ba672b72..f6ceb2e63d1e 100644 --- a/include/uapi/linux/if_ether.h +++ b/include/uapi/linux/if_ether.h @@ -91,6 +91,7 @@ #define ETH_P_802_EX1 0x88B5 /* 802.1 Local Experimental 1. */ #define ETH_P_PREAUTH 0x88C7 /* 802.11 Preauthentication */ #define ETH_P_TIPC 0x88CA /* TIPC */ +#define ETH_P_LLDP 0x88CC /* Link Layer Discovery Protocol */ #define ETH_P_MACSEC 0x88E5 /* 802.1ae MACsec */ #define ETH_P_8021AH 0x88E7 /* 802.1ah Backbone Service Tag */ #define ETH_P_MVRP 0x88F5 /* 802.1Q MVRP */ -- cgit v1.2.3 From fe3475af3bdf38fac78787ec2fe9eedaf2518188 Mon Sep 17 00:00:00 2001 From: Zhu Yanjun Date: Mon, 3 Jun 2019 00:28:01 -0400 Subject: net: rds: add per rds connection cache statistics The variable cache_allocs is to indicate how many frags (KiB) are in one rds connection frag cache. The command "rds-info -Iv" will output the rds connection cache statistics as below: " RDS IB Connections: LocalAddr RemoteAddr Tos SL LocalDev RemoteDev 1.1.1.14 1.1.1.14 58 255 fe80::2:c903:a:7a31 fe80::2:c903:a:7a31 send_wr=256, recv_wr=1024, send_sge=8, rdma_mr_max=4096, rdma_mr_size=257, cache_allocs=12 " This means that there are about 12KiB frag in this rds connection frag cache. Since rds.h in rds-tools is not related with the kernel rds.h, the change in kernel rds.h does not affect rds-tools. rds-info in rds-tools 2.0.5 and 2.0.6 is tested with this commit. It works well. Signed-off-by: Zhu Yanjun Signed-off-by: David S. Miller --- include/uapi/linux/rds.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/uapi/linux/rds.h b/include/uapi/linux/rds.h index 5d0f76c780e5..fd6b5f66e2c5 100644 --- a/include/uapi/linux/rds.h +++ b/include/uapi/linux/rds.h @@ -250,6 +250,7 @@ struct rds_info_rdma_connection { __u32 rdma_mr_max; __u32 rdma_mr_size; __u8 tos; + __u32 cache_allocs; }; struct rds6_info_rdma_connection { @@ -264,6 +265,7 @@ struct rds6_info_rdma_connection { __u32 rdma_mr_max; __u32 rdma_mr_size; __u8 tos; + __u32 cache_allocs; }; /* RDS message Receive Path Latency points */ -- cgit v1.2.3 From 2bd229df5e2ecbc13909f71dbd196fced1d533ca Mon Sep 17 00:00:00 2001 From: Heiner Kallweit Date: Tue, 4 Jun 2019 23:02:34 +0200 Subject: net: phy: remove state PHY_FORCING In the early days of phylib we had a functionality that changed to the next lower speed in fixed mode if no link was established after a certain period of time. This functionality has been removed years ago, and state PHY_FORCING isn't needed any longer. Instead we can go from UP to RUNNING or NOLINK directly (same as in autoneg mode). Signed-off-by: Heiner Kallweit Signed-off-by: David S. Miller --- include/linux/phy.h | 11 ----------- 1 file changed, 11 deletions(-) (limited to 'include') diff --git a/include/linux/phy.h b/include/linux/phy.h index dc4b51060ebc..8caaf76685cd 100644 --- a/include/linux/phy.h +++ b/include/linux/phy.h @@ -297,12 +297,6 @@ struct phy_device *mdiobus_scan(struct mii_bus *bus, int addr); * - irq or timer will set RUNNING if link comes back * - phy_stop moves to HALTED * - * FORCING: PHY is being configured with forced settings - * - if link is up, move to RUNNING - * - If link is down, we drop to the next highest setting, and - * retry (FORCING) after a timeout - * - phy_stop moves to HALTED - * * RUNNING: PHY is currently up, running, and possibly sending * and/or receiving packets * - irq or timer will set NOLINK if link goes down @@ -319,7 +313,6 @@ enum phy_state { PHY_UP, PHY_RUNNING, PHY_NOLINK, - PHY_FORCING, }; /** @@ -347,8 +340,6 @@ struct phy_c45_device_ids { * loopback_enabled: Set true if this phy has been loopbacked successfully. * state: state of the PHY for management purposes * dev_flags: Device-specific flags used by the PHY driver. - * link_timeout: The number of timer firings to wait before the - * giving up on the current attempt at acquiring a link * irq: IRQ number of the PHY's interrupt (-1 if none) * phy_timer: The timer for handling the state machine * attached_dev: The attached enet driver's device instance ptr @@ -416,8 +407,6 @@ struct phy_device { /* Energy efficient ethernet modes which should be prohibited */ u32 eee_broken_modes; - int link_timeout; - #ifdef CONFIG_LED_TRIGGER_PHY struct phy_led_trigger *phy_led_triggers; unsigned int phy_num_led_triggers; -- cgit v1.2.3 From 3aaf3915a31aac83523d2de0191a480d3ad1e747 Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Fri, 3 May 2019 17:46:17 +0200 Subject: xfrm: remove state and template sort indirections from xfrm_state_afinfo No module dependency, placing this in xfrm_state.c avoids need for an indirection. This also removes the state spinlock -- I don't see why we would need to hold it during sorting. This in turn allows to remove the 'net' argument passed to xfrm_tmpl_sort. Last, remove the EXPORT_SYMBOL, there are no modular callers. For the CONFIG_IPV6=m case, vmlinux size increase is about 300 byte. Signed-off-by: Florian Westphal Signed-off-by: Steffen Klassert --- include/net/xfrm.h | 18 +++++++----------- 1 file changed, 7 insertions(+), 11 deletions(-) (limited to 'include') diff --git a/include/net/xfrm.h b/include/net/xfrm.h index 61214f5c3205..4325cb708ed4 100644 --- a/include/net/xfrm.h +++ b/include/net/xfrm.h @@ -353,8 +353,6 @@ struct xfrm_state_afinfo { const struct xfrm_type *type_map[IPPROTO_MAX]; const struct xfrm_type_offload *type_offload_map[IPPROTO_MAX]; - 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 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, @@ -1501,21 +1499,19 @@ struct xfrm_state *xfrm_state_lookup_byaddr(struct net *net, u32 mark, u8 proto, unsigned short family); #ifdef CONFIG_XFRM_SUB_POLICY -int xfrm_tmpl_sort(struct xfrm_tmpl **dst, struct xfrm_tmpl **src, int n, - unsigned short family, struct net *net); -int xfrm_state_sort(struct xfrm_state **dst, struct xfrm_state **src, int n, +void xfrm_tmpl_sort(struct xfrm_tmpl **dst, struct xfrm_tmpl **src, int n, unsigned short family); +void xfrm_state_sort(struct xfrm_state **dst, struct xfrm_state **src, int n, + unsigned short family); #else -static inline int xfrm_tmpl_sort(struct xfrm_tmpl **dst, struct xfrm_tmpl **src, - int n, unsigned short family, struct net *net) +static inline void xfrm_tmpl_sort(struct xfrm_tmpl **d, struct xfrm_tmpl **s, + int n, unsigned short family) { - return -ENOSYS; } -static inline int xfrm_state_sort(struct xfrm_state **dst, struct xfrm_state **src, - int n, unsigned short family) +static inline void xfrm_state_sort(struct xfrm_state **d, struct xfrm_state **s, + int n, unsigned short family) { - return -ENOSYS; } #endif -- cgit v1.2.3 From 4c203b0454b5b6bfafe2c4ab1b5472d4a7a8a0f2 Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Fri, 3 May 2019 17:46:18 +0200 Subject: xfrm: remove eth_proto value from xfrm_state_afinfo xfrm_prepare_input needs to lookup the state afinfo backend again to fetch the address family ethernet protocol value. There are only two address families, so a switch statement is simpler. While at it, use u8 for family and proto and remove the owner member -- its not used anywhere. Signed-off-by: Florian Westphal Signed-off-by: Steffen Klassert --- include/net/xfrm.h | 6 ++---- 1 file changed, 2 insertions(+), 4 deletions(-) (limited to 'include') diff --git a/include/net/xfrm.h b/include/net/xfrm.h index 4325cb708ed4..812994ad49ac 100644 --- a/include/net/xfrm.h +++ b/include/net/xfrm.h @@ -346,10 +346,8 @@ void km_state_expired(struct xfrm_state *x, int hard, u32 portid); int __xfrm_state_delete(struct xfrm_state *x); struct xfrm_state_afinfo { - unsigned int family; - unsigned int proto; - __be16 eth_proto; - struct module *owner; + u8 family; + u8 proto; const struct xfrm_type *type_map[IPPROTO_MAX]; const struct xfrm_type_offload *type_offload_map[IPPROTO_MAX]; -- cgit v1.2.3 From 4f518e802ccad30c9dccc895f2294398757b87c0 Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Fri, 3 May 2019 17:46:19 +0200 Subject: xfrm: remove type and offload_type map from xfrm_state_afinfo Only a handful of xfrm_types exist, no need to have 512 pointers for them. Reduces size of afinfo struct from 4k to 120 bytes on 64bit platforms. Also, the unregister function doesn't need to return an error, no single caller does anything useful with it. Just place a WARN_ON() where needed instead. Signed-off-by: Florian Westphal Signed-off-by: Steffen Klassert --- include/net/xfrm.h | 16 ++++++++++++---- 1 file changed, 12 insertions(+), 4 deletions(-) (limited to 'include') diff --git a/include/net/xfrm.h b/include/net/xfrm.h index 812994ad49ac..56b31676e330 100644 --- a/include/net/xfrm.h +++ b/include/net/xfrm.h @@ -348,8 +348,16 @@ int __xfrm_state_delete(struct xfrm_state *x); struct xfrm_state_afinfo { u8 family; u8 proto; - const struct xfrm_type *type_map[IPPROTO_MAX]; - const struct xfrm_type_offload *type_offload_map[IPPROTO_MAX]; + + const struct xfrm_type_offload *type_offload_esp; + + const struct xfrm_type *type_esp; + const struct xfrm_type *type_ipip; + const struct xfrm_type *type_ipip6; + const struct xfrm_type *type_comp; + const struct xfrm_type *type_ah; + const struct xfrm_type *type_routing; + const struct xfrm_type *type_dstopts; int (*output)(struct net *net, struct sock *sk, struct sk_buff *skb); int (*output_finish)(struct sock *sk, struct sk_buff *skb); @@ -401,7 +409,7 @@ struct xfrm_type { }; int xfrm_register_type(const struct xfrm_type *type, unsigned short family); -int xfrm_unregister_type(const struct xfrm_type *type, unsigned short family); +void xfrm_unregister_type(const struct xfrm_type *type, unsigned short family); struct xfrm_type_offload { char *description; @@ -413,7 +421,7 @@ struct xfrm_type_offload { }; int xfrm_register_type_offload(const struct xfrm_type_offload *type, unsigned short family); -int xfrm_unregister_type_offload(const struct xfrm_type_offload *type, unsigned short family); +void xfrm_unregister_type_offload(const struct xfrm_type_offload *type, unsigned short family); static inline int xfrm_af2proto(unsigned int family) { -- cgit v1.2.3 From fe1e0713bbe84c6796b01d50a55ce4e324141161 Mon Sep 17 00:00:00 2001 From: Litao jiao Date: Thu, 6 Jun 2019 17:57:58 +0800 Subject: vxlan: Use FDB_HASH_SIZE hash_locks to reduce contention The monolithic hash_lock could cause huge contention when inserting/deletiing vxlan_fdbs into the fdb_head. Use FDB_HASH_SIZE hash_locks to protect insertions/deletions of vxlan_fdbs into the fdb_head hash table. Suggested-by: David S. Miller Signed-off-by: Litao jiao Signed-off-by: David S. Miller --- include/net/vxlan.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/net/vxlan.h b/include/net/vxlan.h index 83b5999a2587..dc1583a1fb8a 100644 --- a/include/net/vxlan.h +++ b/include/net/vxlan.h @@ -242,7 +242,7 @@ struct vxlan_dev { struct vxlan_rdst default_dst; /* default destination */ struct timer_list age_timer; - spinlock_t hash_lock; + spinlock_t hash_lock[FDB_HASH_SIZE]; unsigned int addrcnt; struct gro_cells gro_cells; -- cgit v1.2.3 From ca72efb6bdc733006f335ca12ca615395077a873 Mon Sep 17 00:00:00 2001 From: Robert Hancock Date: Tue, 4 Jun 2019 16:15:01 -0600 Subject: net: phy: Add detection of 1000BaseX link mode support Add 1000BaseX to the link modes which are detected based on the MII_ESTATUS register as per 802.3 Clause 22. This allows PHYs which support 1000BaseX to work properly with drivers using phylink. Previously 1000BaseX support was not detected, and if that was the only mode the PHY indicated support for, phylink would refuse to attach it due to the list of supported modes being empty. Signed-off-by: Robert Hancock Signed-off-by: David S. Miller --- include/uapi/linux/mii.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/uapi/linux/mii.h b/include/uapi/linux/mii.h index a506216591d6..51b48e4be1f2 100644 --- a/include/uapi/linux/mii.h +++ b/include/uapi/linux/mii.h @@ -121,6 +121,8 @@ #define EXPANSION_MFAULTS 0x0010 /* Multiple faults detected */ #define EXPANSION_RESV 0xffe0 /* Unused... */ +#define ESTATUS_1000_XFULL 0x8000 /* Can do 1000BaseX Full */ +#define ESTATUS_1000_XHALF 0x4000 /* Can do 1000BaseX Half */ #define ESTATUS_1000_TFULL 0x2000 /* Can do 1000BT Full */ #define ESTATUS_1000_THALF 0x1000 /* Can do 1000BT Half */ -- cgit v1.2.3 From 2d6b51c6924c1bba8e4948dc4a2dbc96bf685b97 Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Wed, 5 Jun 2019 14:11:38 -0700 Subject: net/tls: split the TLS_DRIVER_STATE_SIZE and bump TX to 16 bytes 8 bytes of driver state has been enough so far, but for drivers which have to store 8 byte handle it's no longer practical to store the state directly in the context. Drivers generally don't need much extra state on RX side, while TX side has to be tracking TCP sequence numbers. Split the lengths of max driver state size on RX and TX. The struct tls_offload_context_tx currently stands at 616 bytes and struct tls_offload_context_rx stands at 368 bytes. Upcoming work will consume extra 8 bytes in both for kernel-driven resync. This means that we can bump TX side to 16 bytes and still fit into the same number of cache lines but on RX side we would be 8 bytes over. Signed-off-by: Jakub Kicinski Reviewed-by: Dirk van der Merwe Signed-off-by: David S. Miller --- include/net/tls.h | 7 ++++--- 1 file changed, 4 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/include/net/tls.h b/include/net/tls.h index 0a0072636009..3094db5398a9 100644 --- a/include/net/tls.h +++ b/include/net/tls.h @@ -202,12 +202,12 @@ struct tls_offload_context_tx { * Currently the belief is that there is not enough * driver specific state to justify another layer of indirection */ -#define TLS_DRIVER_STATE_SIZE (max_t(size_t, 8, sizeof(void *))) +#define TLS_DRIVER_STATE_SIZE_TX 16 }; #define TLS_OFFLOAD_CONTEXT_SIZE_TX \ (ALIGN(sizeof(struct tls_offload_context_tx), sizeof(void *)) + \ - TLS_DRIVER_STATE_SIZE) + TLS_DRIVER_STATE_SIZE_TX) struct cipher_context { char *iv; @@ -307,11 +307,12 @@ struct tls_offload_context_rx { * Currently the belief is that there is not enough * driver specific state to justify another layer of indirection */ +#define TLS_DRIVER_STATE_SIZE_RX 8 }; #define TLS_OFFLOAD_CONTEXT_SIZE_RX \ (ALIGN(sizeof(struct tls_offload_context_rx), sizeof(void *)) + \ - TLS_DRIVER_STATE_SIZE) + TLS_DRIVER_STATE_SIZE_RX) int wait_on_pending_writer(struct sock *sk, long *timeo); int tls_sk_query(struct sock *sk, int optname, char __user *optval, -- cgit v1.2.3 From 2e361176ea01c4b2f90b17c2264a2a794050c3f3 Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Wed, 5 Jun 2019 14:11:39 -0700 Subject: net/tls: simplify driver context retrieval Currently drivers have to ensure the alignment of their tls state structure, which leads to unnecessary layers of getters and encapsulated structures in each driver. Simplify all this by marking the driver state as aligned (driver_state members are currently aligned, so no hole is added, besides ALIGN in TLS_OFFLOAD_CONTEXT_SIZE_RX/TX would reserve this extra space, anyway.) With that we can add a common accessor to the core. Signed-off-by: Jakub Kicinski Reviewed-by: Dirk van der Merwe Signed-off-by: David S. Miller --- include/net/tls.h | 28 ++++++++++++++++++++++------ 1 file changed, 22 insertions(+), 6 deletions(-) (limited to 'include') diff --git a/include/net/tls.h b/include/net/tls.h index 3094db5398a9..3da0d941e729 100644 --- a/include/net/tls.h +++ b/include/net/tls.h @@ -40,6 +40,7 @@ #include #include #include +#include #include #include @@ -197,7 +198,7 @@ struct tls_offload_context_tx { struct scatterlist sg_tx_data[MAX_SKB_FRAGS]; void (*sk_destruct)(struct sock *sk); - u8 driver_state[]; + u8 driver_state[] __aligned(8); /* The TLS layer reserves room for driver specific state * Currently the belief is that there is not enough * driver specific state to justify another layer of indirection @@ -206,8 +207,7 @@ struct tls_offload_context_tx { }; #define TLS_OFFLOAD_CONTEXT_SIZE_TX \ - (ALIGN(sizeof(struct tls_offload_context_tx), sizeof(void *)) + \ - TLS_DRIVER_STATE_SIZE_TX) + (sizeof(struct tls_offload_context_tx) + TLS_DRIVER_STATE_SIZE_TX) struct cipher_context { char *iv; @@ -302,7 +302,7 @@ struct tls_offload_context_rx { /* sw must be the first member of tls_offload_context_rx */ struct tls_sw_context_rx sw; atomic64_t resync_req; - u8 driver_state[]; + u8 driver_state[] __aligned(8); /* The TLS layer reserves room for driver specific state * Currently the belief is that there is not enough * driver specific state to justify another layer of indirection @@ -311,8 +311,7 @@ struct tls_offload_context_rx { }; #define TLS_OFFLOAD_CONTEXT_SIZE_RX \ - (ALIGN(sizeof(struct tls_offload_context_rx), sizeof(void *)) + \ - TLS_DRIVER_STATE_SIZE_RX) + (sizeof(struct tls_offload_context_rx) + TLS_DRIVER_STATE_SIZE_RX) int wait_on_pending_writer(struct sock *sk, long *timeo); int tls_sk_query(struct sock *sk, int optname, char __user *optval, @@ -557,6 +556,23 @@ tls_offload_ctx_rx(const struct tls_context *tls_ctx) return (struct tls_offload_context_rx *)tls_ctx->priv_ctx_rx; } +#if IS_ENABLED(CONFIG_TLS_DEVICE) +static inline void *__tls_driver_ctx(struct tls_context *tls_ctx, + enum tls_offload_ctx_dir direction) +{ + if (direction == TLS_OFFLOAD_CTX_DIR_TX) + return tls_offload_ctx_tx(tls_ctx)->driver_state; + else + return tls_offload_ctx_rx(tls_ctx)->driver_state; +} + +static inline void * +tls_driver_ctx(const struct sock *sk, enum tls_offload_ctx_dir direction) +{ + return __tls_driver_ctx(tls_get_ctx(sk), direction); +} +#endif + /* The TLS context is valid until sk_destruct is called */ static inline void tls_offload_rx_resync_request(struct sock *sk, __be32 seq) { -- cgit v1.2.3 From b9727d7f957d68febb3b5f68d4be270ee6fb57e7 Mon Sep 17 00:00:00 2001 From: Dirk van der Merwe Date: Wed, 5 Jun 2019 14:11:40 -0700 Subject: net/tls: export TLS per skb encryption While offloading TLS connections, drivers need to handle the case where out of order packets need to be transmitted. Other drivers obtain the entire TLS record for the specific skb to provide as context to hardware for encryption. However, other designs may also want to keep the hardware state intact and perform the out of order encryption entirely on the host. To achieve this, export the already existing software encryption fallback path so drivers could access this. Signed-off-by: Dirk van der Merwe Reviewed-by: Jakub Kicinski Signed-off-by: David S. Miller --- include/net/tls.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/net/tls.h b/include/net/tls.h index 3da0d941e729..d1a4f365d6be 100644 --- a/include/net/tls.h +++ b/include/net/tls.h @@ -590,6 +590,7 @@ void tls_unregister_device(struct tls_device *device); int tls_device_decrypted(struct sock *sk, struct sk_buff *skb); int decrypt_skb(struct sock *sk, struct sk_buff *skb, struct scatterlist *sgout); +struct sk_buff *tls_encrypt_skb(struct sk_buff *skb); struct sk_buff *tls_validate_xmit_skb(struct sock *sk, struct net_device *dev, -- cgit v1.2.3 From 5e3f847a02aabfecea519d7b2fd48f4d6f551be6 Mon Sep 17 00:00:00 2001 From: Vladimir Oltean Date: Sat, 8 Jun 2019 15:04:28 +0300 Subject: net: dsa: Add teardown callback for drivers This is helpful for e.g. draining per-driver (not per-port) tagger queues. Signed-off-by: Vladimir Oltean Reviewed-by: Andrew Lunn Reviewed-by: Florian Fainelli Signed-off-by: David S. Miller --- include/net/dsa.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/net/dsa.h b/include/net/dsa.h index 1131d9fac20b..82a2baa2dc48 100644 --- a/include/net/dsa.h +++ b/include/net/dsa.h @@ -357,6 +357,7 @@ struct dsa_switch_ops { int port); int (*setup)(struct dsa_switch *ds); + void (*teardown)(struct dsa_switch *ds); u32 (*get_phy_flags)(struct dsa_switch *ds, int port); /* -- cgit v1.2.3 From d461933638ae9fa49ad22f60a40de5b3ed414912 Mon Sep 17 00:00:00 2001 From: Vladimir Oltean Date: Sat, 8 Jun 2019 15:04:29 +0300 Subject: net: dsa: tag_8021q: Create helper function for removing VLAN header This removes the existing implementation from tag_sja1105, which was partially incorrect (it was not changing the MAC header offset, thereby leaving it to point 4 bytes earlier than it should have). This overwrites the VLAN tag by moving the Ethernet source and destination MACs 4 bytes to the right. Then skb->data (assumed to be pointing immediately after the EtherType) is temporarily pushed to the beginning of the new Ethernet header, the new Ethernet header offset and length are recorded, then skb->data is moved back to where it was. Signed-off-by: Vladimir Oltean Signed-off-by: David S. Miller --- include/linux/dsa/8021q.h | 16 +++++++--------- 1 file changed, 7 insertions(+), 9 deletions(-) (limited to 'include') diff --git a/include/linux/dsa/8021q.h b/include/linux/dsa/8021q.h index 3911e0586478..0aa803c451a3 100644 --- a/include/linux/dsa/8021q.h +++ b/include/linux/dsa/8021q.h @@ -20,9 +20,6 @@ int dsa_port_setup_8021q_tagging(struct dsa_switch *ds, int index, struct sk_buff *dsa_8021q_xmit(struct sk_buff *skb, struct net_device *netdev, u16 tpid, u16 tci); -struct sk_buff *dsa_8021q_rcv(struct sk_buff *skb, struct net_device *netdev, - struct packet_type *pt, u16 *tpid, u16 *tci); - u16 dsa_8021q_tx_vid(struct dsa_switch *ds, int port); u16 dsa_8021q_rx_vid(struct dsa_switch *ds, int port); @@ -31,6 +28,8 @@ int dsa_8021q_rx_switch_id(u16 vid); int dsa_8021q_rx_source_port(u16 vid); +struct sk_buff *dsa_8021q_remove_header(struct sk_buff *skb); + #else int dsa_port_setup_8021q_tagging(struct dsa_switch *ds, int index, @@ -45,12 +44,6 @@ struct sk_buff *dsa_8021q_xmit(struct sk_buff *skb, struct net_device *netdev, return NULL; } -struct sk_buff *dsa_8021q_rcv(struct sk_buff *skb, struct net_device *netdev, - struct packet_type *pt, u16 *tpid, u16 *tci) -{ - return NULL; -} - u16 dsa_8021q_tx_vid(struct dsa_switch *ds, int port) { return 0; @@ -71,6 +64,11 @@ int dsa_8021q_rx_source_port(u16 vid) return 0; } +struct sk_buff *dsa_8021q_remove_header(struct sk_buff *skb) +{ + return NULL; +} + #endif /* IS_ENABLED(CONFIG_NET_DSA_TAG_8021Q) */ #endif /* _NET_DSA_8021Q_H */ -- cgit v1.2.3 From 47ed985e97f513b7746270e8c5d1f3a3f959b2da Mon Sep 17 00:00:00 2001 From: Vladimir Oltean Date: Sat, 8 Jun 2019 15:04:35 +0300 Subject: net: dsa: sja1105: Add logic for TX timestamping On TX, timestamping is performed synchronously from the port_deferred_xmit worker thread. In management routes, the switch is requested to take egress timestamps (again partial), which are reconstructed and appended to a clone of the skb that was just sent. The cloning is done by DSA and we retrieve the pointer from the structure that DSA keeps in skb->cb. Then these clones are enqueued to the socket's error queue for application-level processing. Signed-off-by: Vladimir Oltean Signed-off-by: David S. Miller --- include/linux/dsa/sja1105.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/dsa/sja1105.h b/include/linux/dsa/sja1105.h index e46e18c47d41..5a956f335022 100644 --- a/include/linux/dsa/sja1105.h +++ b/include/linux/dsa/sja1105.h @@ -22,6 +22,7 @@ struct sja1105_port { struct dsa_port *dp; + bool hwts_tx_en; int mgmt_slot; }; -- cgit v1.2.3 From d3f9b90bf19fad05889e4bead7dc1b336da56118 Mon Sep 17 00:00:00 2001 From: Vladimir Oltean Date: Sat, 8 Jun 2019 15:04:36 +0300 Subject: net: dsa: sja1105: Build a minimal understanding of meta frames Meta frames are sent on the CPU port by the switch if RX timestamping is enabled. They contain a partial timestamp of the previous frame. They are Ethernet frames with the Ethernet header constructed out of: - SJA1105_META_DMAC - SJA1105_META_SMAC - ETH_P_SJA1105_META The Ethernet payload will be decoded in a follow-up patch. Signed-off-by: Vladimir Oltean Reviewed-by: Florian Fainelli Signed-off-by: David S. Miller --- include/linux/dsa/sja1105.h | 11 +++++++++++ 1 file changed, 11 insertions(+) (limited to 'include') diff --git a/include/linux/dsa/sja1105.h b/include/linux/dsa/sja1105.h index 5a956f335022..cc4a909d1007 100644 --- a/include/linux/dsa/sja1105.h +++ b/include/linux/dsa/sja1105.h @@ -12,6 +12,7 @@ #include #define ETH_P_SJA1105 ETH_P_DSA_8021Q +#define ETH_P_SJA1105_META 0x0008 /* IEEE 802.3 Annex 57A: Slow Protocols PDUs (01:80:C2:xx:xx:xx) */ #define SJA1105_LINKLOCAL_FILTER_A 0x0180C2000000ull @@ -20,6 +21,16 @@ #define SJA1105_LINKLOCAL_FILTER_B 0x011B19000000ull #define SJA1105_LINKLOCAL_FILTER_B_MASK 0xFFFFFF000000ull +/* Source and Destination MAC of follow-up meta frames. + * Whereas the choice of SMAC only affects the unique identification of the + * switch as sender of meta frames, the DMAC must be an address that is present + * in the DSA master port's multicast MAC filter. + * 01-80-C2-00-00-0E is a good choice for this, as all profiles of IEEE 1588 + * over L2 use this address for some purpose already. + */ +#define SJA1105_META_SMAC 0x222222222222ull +#define SJA1105_META_DMAC 0x0180C200000Eull + struct sja1105_port { struct dsa_port *dp; bool hwts_tx_en; -- cgit v1.2.3 From 844d7edc6a34ae3a8236f1306e4f2615c8db1eac Mon Sep 17 00:00:00 2001 From: Vladimir Oltean Date: Sat, 8 Jun 2019 15:04:40 +0300 Subject: net: dsa: sja1105: Add a global sja1105_tagger_data structure This will be used to keep state for RX timestamping. It is global because the switch serializes timestampable and meta frames when trapping them towards the CPU port (lower port indices have higher priority) and therefore having one state machine per port would create unnecessary complications. Signed-off-by: Vladimir Oltean Signed-off-by: David S. Miller --- include/linux/dsa/sja1105.h | 15 +++++++++++++++ 1 file changed, 15 insertions(+) (limited to 'include') diff --git a/include/linux/dsa/sja1105.h b/include/linux/dsa/sja1105.h index cc4a909d1007..2c4fce4eaf0d 100644 --- a/include/linux/dsa/sja1105.h +++ b/include/linux/dsa/sja1105.h @@ -31,7 +31,22 @@ #define SJA1105_META_SMAC 0x222222222222ull #define SJA1105_META_DMAC 0x0180C200000Eull +/* Global tagger data: each struct sja1105_port has a reference to + * the structure defined in struct sja1105_private. + */ +struct sja1105_tagger_data { + struct sk_buff_head skb_rxtstamp_queue; + struct work_struct rxtstamp_work; + struct sk_buff *stampable_skb; + /* Protects concurrent access to the meta state machine + * from taggers running on multiple ports on SMP systems + */ + spinlock_t meta_lock; + bool hwts_rx_en; +}; + struct sja1105_port { + struct sja1105_tagger_data *data; struct dsa_port *dp; bool hwts_tx_en; int mgmt_slot; -- cgit v1.2.3 From f3097be21bf17ae8785eea009cbc424f16611d9a Mon Sep 17 00:00:00 2001 From: Vladimir Oltean Date: Sat, 8 Jun 2019 15:04:42 +0300 Subject: net: dsa: sja1105: Add a state machine for RX timestamping Meta frame reception relies on the hardware keeping its promise that it will send no other traffic towards the CPU port between a link-local frame and a meta frame. Otherwise there is no other way to associate the meta frame with the link-local frame it's holding a timestamp of. The receive function is made stateful, and buffers a timestampable frame until its meta frame arrives, then merges the two, drops the meta and releases the link-local frame up the stack. Signed-off-by: Vladimir Oltean Signed-off-by: David S. Miller --- include/linux/dsa/sja1105.h | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'include') diff --git a/include/linux/dsa/sja1105.h b/include/linux/dsa/sja1105.h index 2c4fce4eaf0d..79435cfc20eb 100644 --- a/include/linux/dsa/sja1105.h +++ b/include/linux/dsa/sja1105.h @@ -45,6 +45,13 @@ struct sja1105_tagger_data { bool hwts_rx_en; }; +struct sja1105_skb_cb { + u32 meta_tstamp; +}; + +#define SJA1105_SKB_CB(skb) \ + ((struct sja1105_skb_cb *)DSA_SKB_CB_PRIV(skb)) + struct sja1105_port { struct sja1105_tagger_data *data; struct dsa_port *dp; -- cgit v1.2.3 From 5237ff79b23901a5326f8e986667976861370445 Mon Sep 17 00:00:00 2001 From: Jarod Wilson Date: Fri, 7 Jun 2019 10:59:28 -0400 Subject: bonding: add slave_foo printk macros Where possible, we generally want both the bond master and the relevant slave information in message output. Standardize the format using new slave_* printk macros. Suggested-by: Joe Perches CC: Jay Vosburgh CC: Veaceslav Falico CC: Andy Gospodarek CC: netdev@vger.kernel.org Signed-off-by: Jarod Wilson Signed-off-by: David S. Miller --- include/net/bonding.h | 9 +++++++++ 1 file changed, 9 insertions(+) (limited to 'include') diff --git a/include/net/bonding.h b/include/net/bonding.h index b46d68acf701..676e7fae05a3 100644 --- a/include/net/bonding.h +++ b/include/net/bonding.h @@ -38,6 +38,15 @@ #define __long_aligned __attribute__((aligned((sizeof(long))))) #endif +#define slave_info(bond_dev, slave_dev, fmt, ...) \ + netdev_info(bond_dev, "(slave %s): " fmt, (slave_dev)->name, ##__VA_ARGS__) +#define slave_warn(bond_dev, slave_dev, fmt, ...) \ + netdev_warn(bond_dev, "(slave %s): " fmt, (slave_dev)->name, ##__VA_ARGS__) +#define slave_dbg(bond_dev, slave_dev, fmt, ...) \ + netdev_dbg(bond_dev, "(slave %s): " fmt, (slave_dev)->name, ##__VA_ARGS__) +#define slave_err(bond_dev, slave_dev, fmt, ...) \ + netdev_err(bond_dev, "(slave %s): " fmt, (slave_dev)->name, ##__VA_ARGS__) + #define BOND_MODE(bond) ((bond)->params.mode) /* slave list primitives */ -- cgit v1.2.3 From 5270041d342de6f1e6a3b6634c1ceaa67d1f87ea Mon Sep 17 00:00:00 2001 From: Dan Carpenter Date: Fri, 7 Jun 2019 18:31:07 +0300 Subject: nexthop: off by one in nexthop_mpath_select() The nhg->nh_entries[] array is allocated in nexthop_grp_alloc() and it has nhg->num_nh elements so this check should be >= instead of >. Fixes: 430a049190de ("nexthop: Add support for nexthop groups") Signed-off-by: Dan Carpenter Reviewed-by: David Ahern Signed-off-by: David S. Miller --- include/net/nexthop.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/net/nexthop.h b/include/net/nexthop.h index aff7b2410057..e019ed9b3dc3 100644 --- a/include/net/nexthop.h +++ b/include/net/nexthop.h @@ -160,7 +160,7 @@ struct nexthop *nexthop_mpath_select(const struct nexthop *nh, int nhsel) /* for_nexthops macros in fib_semantics.c grabs a pointer to * the nexthop before checking nhsel */ - if (nhsel > nhg->num_nh) + if (nhsel >= nhg->num_nh) return NULL; return nhg->nh_entries[nhsel].nh; -- cgit v1.2.3 From 6dcdd884e2a4bb57b0ed3654ff28974ae17d2a08 Mon Sep 17 00:00:00 2001 From: Sebastian Andrzej Siewior Date: Fri, 7 Jun 2019 21:20:40 +0200 Subject: net: hwbm: Make the hwbm_pool lock a mutex Based on review, `lock' is only acquired in hwbm_pool_add() which is invoked via ->probe(), ->resume() and ->ndo_change_mtu(). Based on this the lock can become a mutex and there is no need to disable interrupts during the procedure. Now that the lock is a mutex, hwbm_pool_add() no longer invokes hwbm_pool_refill() in an atomic context so we can pass GFP_KERNEL to hwbm_pool_refill() and remove the `gfp' argument from hwbm_pool_add(). Cc: Thomas Petazzoni Signed-off-by: Sebastian Andrzej Siewior Signed-off-by: David S. Miller --- include/net/hwbm.h | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/include/net/hwbm.h b/include/net/hwbm.h index 89085e2e2da5..81643cf8a1c4 100644 --- a/include/net/hwbm.h +++ b/include/net/hwbm.h @@ -12,18 +12,18 @@ struct hwbm_pool { /* constructor called during alocation */ int (*construct)(struct hwbm_pool *bm_pool, void *buf); /* protect acces to the buffer counter*/ - spinlock_t lock; + struct mutex buf_lock; /* private data */ void *priv; }; #ifdef CONFIG_HWBM void hwbm_buf_free(struct hwbm_pool *bm_pool, void *buf); int hwbm_pool_refill(struct hwbm_pool *bm_pool, gfp_t gfp); -int hwbm_pool_add(struct hwbm_pool *bm_pool, unsigned int buf_num, gfp_t gfp); +int hwbm_pool_add(struct hwbm_pool *bm_pool, unsigned int buf_num); #else void hwbm_buf_free(struct hwbm_pool *bm_pool, void *buf) {} int hwbm_pool_refill(struct hwbm_pool *bm_pool, gfp_t gfp) { return 0; } -int hwbm_pool_add(struct hwbm_pool *bm_pool, unsigned int buf_num, gfp_t gfp) +int hwbm_pool_add(struct hwbm_pool *bm_pool, unsigned int buf_num) { return 0; } #endif /* CONFIG_HWBM */ #endif /* _HWBM_H */ -- cgit v1.2.3 From c67b85558ff20cb1ff20874461d12af456bee5d0 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Sat, 8 Jun 2019 17:58:51 -0700 Subject: ipv6: tcp: send consistent autoflowlabel in TIME_WAIT state In case autoflowlabel is in action, skb_get_hash_flowi6() derives a non zero skb->hash to the flowlabel. If skb->hash is zero, a flow dissection is performed. Since all TCP skbs sent from ESTABLISH state inherit their skb->hash from sk->sk_txhash, we better keep a copy of sk->sk_txhash into the TIME_WAIT socket. After this patch, ACK or RST packets sent on behalf of a TIME_WAIT socket have the flowlabel that was previously used by the flow. Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- include/net/inet_timewait_sock.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/net/inet_timewait_sock.h b/include/net/inet_timewait_sock.h index c2f756aedc54..aef38c140014 100644 --- a/include/net/inet_timewait_sock.h +++ b/include/net/inet_timewait_sock.h @@ -70,6 +70,7 @@ struct inet_timewait_sock { tw_flowlabel : 20, tw_pad : 2, /* 2 bits hole */ tw_tos : 8; + u32 tw_txhash; struct timer_list tw_timer; struct inet_bind_bucket *tw_tb; }; -- cgit v1.2.3 From fe03d4745675cbd678cb8c50d951df0abafdcaee Mon Sep 17 00:00:00 2001 From: Jozsef Kadlecsik Date: Mon, 10 Jun 2019 13:00:24 +0200 Subject: Update my email address It's better to use my kadlec@netfilter.org email address in the source code. I might not be able to use kadlec@blackhole.kfki.hu in the future. Signed-off-by: Jozsef Kadlecsik Signed-off-by: Jozsef Kadlecsik --- include/linux/jhash.h | 2 +- include/linux/netfilter/ipset/ip_set.h | 2 +- include/linux/netfilter/ipset/ip_set_counter.h | 2 +- include/linux/netfilter/ipset/ip_set_skbinfo.h | 2 +- include/linux/netfilter/ipset/ip_set_timeout.h | 2 +- include/uapi/linux/netfilter/ipset/ip_set.h | 2 +- 6 files changed, 6 insertions(+), 6 deletions(-) (limited to 'include') diff --git a/include/linux/jhash.h b/include/linux/jhash.h index 8037850f3104..ba2f6a9776b6 100644 --- a/include/linux/jhash.h +++ b/include/linux/jhash.h @@ -17,7 +17,7 @@ * if SELF_TEST is defined. You can use this free for any purpose. It's in * the public domain. It has no warranty. * - * Copyright (C) 2009-2010 Jozsef Kadlecsik (kadlec@blackhole.kfki.hu) + * Copyright (C) 2009-2010 Jozsef Kadlecsik (kadlec@netfilter.org) * * I've modified Bob's hash to be useful in the Linux kernel, and * any bugs present are my fault. diff --git a/include/linux/netfilter/ipset/ip_set.h b/include/linux/netfilter/ipset/ip_set.h index e499d170f12d..f5c6e7cd6469 100644 --- a/include/linux/netfilter/ipset/ip_set.h +++ b/include/linux/netfilter/ipset/ip_set.h @@ -1,7 +1,7 @@ /* Copyright (C) 2000-2002 Joakim Axelsson * Patrick Schaaf * Martin Josefsson - * Copyright (C) 2003-2013 Jozsef Kadlecsik + * Copyright (C) 2003-2013 Jozsef Kadlecsik * * 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 diff --git a/include/linux/netfilter/ipset/ip_set_counter.h b/include/linux/netfilter/ipset/ip_set_counter.h index 3d33a2c3f39f..305aeda2a899 100644 --- a/include/linux/netfilter/ipset/ip_set_counter.h +++ b/include/linux/netfilter/ipset/ip_set_counter.h @@ -1,7 +1,7 @@ #ifndef _IP_SET_COUNTER_H #define _IP_SET_COUNTER_H -/* Copyright (C) 2015 Jozsef Kadlecsik +/* Copyright (C) 2015 Jozsef Kadlecsik * * 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 diff --git a/include/linux/netfilter/ipset/ip_set_skbinfo.h b/include/linux/netfilter/ipset/ip_set_skbinfo.h index 29d7ef2bc3fa..fac57ef854c2 100644 --- a/include/linux/netfilter/ipset/ip_set_skbinfo.h +++ b/include/linux/netfilter/ipset/ip_set_skbinfo.h @@ -1,7 +1,7 @@ #ifndef _IP_SET_SKBINFO_H #define _IP_SET_SKBINFO_H -/* Copyright (C) 2015 Jozsef Kadlecsik +/* Copyright (C) 2015 Jozsef Kadlecsik * * 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 diff --git a/include/linux/netfilter/ipset/ip_set_timeout.h b/include/linux/netfilter/ipset/ip_set_timeout.h index 8ce271e187b6..dc74150f3432 100644 --- a/include/linux/netfilter/ipset/ip_set_timeout.h +++ b/include/linux/netfilter/ipset/ip_set_timeout.h @@ -1,7 +1,7 @@ #ifndef _IP_SET_TIMEOUT_H #define _IP_SET_TIMEOUT_H -/* Copyright (C) 2003-2013 Jozsef Kadlecsik +/* Copyright (C) 2003-2013 Jozsef Kadlecsik * * 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 diff --git a/include/uapi/linux/netfilter/ipset/ip_set.h b/include/uapi/linux/netfilter/ipset/ip_set.h index ea69ca21ff23..eea166c52c36 100644 --- a/include/uapi/linux/netfilter/ipset/ip_set.h +++ b/include/uapi/linux/netfilter/ipset/ip_set.h @@ -2,7 +2,7 @@ /* Copyright (C) 2000-2002 Joakim Axelsson * Patrick Schaaf * Martin Josefsson - * Copyright (C) 2003-2011 Jozsef Kadlecsik + * Copyright (C) 2003-2011 Jozsef Kadlecsik * * 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 -- cgit v1.2.3 From f88c9aa12fd0cff9cbb74b490350e6f0fac68296 Mon Sep 17 00:00:00 2001 From: David Ahern Date: Sat, 8 Jun 2019 14:53:22 -0700 Subject: nexthops: Add ipv6 helper to walk all fib6_nh in a nexthop struct IPv6 has traditionally had a single fib6_nh per fib6_info. With nexthops we can have multiple fib6_nh associated with a fib6_info. Add a nexthop helper to invoke a callback for each fib6_nh in a 'struct nexthop'. If the callback returns non-0, the loop is stopped and the return value passed to the caller. Signed-off-by: David Ahern Signed-off-by: David S. Miller --- include/net/nexthop.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include') diff --git a/include/net/nexthop.h b/include/net/nexthop.h index e019ed9b3dc3..25f1f9a8419b 100644 --- a/include/net/nexthop.h +++ b/include/net/nexthop.h @@ -305,4 +305,8 @@ static inline void nexthop_path_fib6_result(struct fib6_result *res, int hash) res->nh = &nhi->fib6_nh; } } + +int nexthop_for_each_fib6_nh(struct nexthop *nh, + int (*cb)(struct fib6_nh *nh, void *arg), + void *arg); #endif -- cgit v1.2.3 From 493ced1ac47c48bb86d9d4e8e87df8592be85a0e Mon Sep 17 00:00:00 2001 From: David Ahern Date: Sat, 8 Jun 2019 14:53:32 -0700 Subject: ipv4: Allow routes to use nexthop objects Add support for RTA_NH_ID attribute to allow a user to specify a nexthop id to use with a route. fc_nh_id is added to fib_config to hold the value passed in the RTA_NH_ID attribute. If a nexthop id is given, the gateway, device, encap and multipath attributes can not be set. Update fib_nh_match to check ids on a route delete. Signed-off-by: David Ahern Signed-off-by: David S. Miller --- include/net/ip_fib.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/net/ip_fib.h b/include/net/ip_fib.h index 4cdf8bc22efd..7e1e621a56df 100644 --- a/include/net/ip_fib.h +++ b/include/net/ip_fib.h @@ -40,6 +40,7 @@ struct fib_config { u32 fc_flags; u32 fc_priority; __be32 fc_prefsrc; + u32 fc_nh_id; struct nlattr *fc_mx; struct rtnexthop *fc_mp; int fc_mx_len; -- cgit v1.2.3 From 5b98324ebe29f4494b0fc45bde2d47ee716518fd Mon Sep 17 00:00:00 2001 From: David Ahern Date: Sat, 8 Jun 2019 14:53:34 -0700 Subject: ipv6: Allow routes to use nexthop objects Add support for RTA_NH_ID attribute to allow a user to specify a nexthop id to use with a route. fc_nh_id is added to fib6_config to hold the value passed in the RTA_NH_ID attribute. If a nexthop id is given, the gateway, device, encap and multipath attributes can not be set. Update ip6_route_del to check metric and protocol before nexthop specs. If fc_nh_id is set, then it must match the id in the route entry. Since IPv6 allows delete of a cached entry (an exception), add ip6_del_cached_rt_nh to cycle through all of the fib6_nh in a fib entry if it is using a nexthop. Signed-off-by: David Ahern Signed-off-by: David S. Miller --- include/net/ip6_fib.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/net/ip6_fib.h b/include/net/ip6_fib.h index ac0427c096f3..1e92f1500b87 100644 --- a/include/net/ip6_fib.h +++ b/include/net/ip6_fib.h @@ -49,6 +49,7 @@ struct fib6_config { u16 fc_delete_all_nh : 1, fc_ignore_dev_down:1, __unused : 14; + u32 fc_nh_id; struct in6_addr fc_dst; struct in6_addr fc_src; -- cgit v1.2.3 From fada7fdc83c0bf8755956bff707c42b609223301 Mon Sep 17 00:00:00 2001 From: Jonathan Lemon Date: Thu, 6 Jun 2019 13:59:40 -0700 Subject: bpf: Allow bpf_map_lookup_elem() on an xskmap Currently, the AF_XDP code uses a separate map in order to determine if an xsk is bound to a queue. Instead of doing this, have bpf_map_lookup_elem() return a xdp_sock. Rearrange some xdp_sock members to eliminate structure holes. Remove selftest - will be added back in later patch. Signed-off-by: Jonathan Lemon Acked-by: Martin KaFai Lau Signed-off-by: Alexei Starovoitov --- include/linux/bpf.h | 8 ++++++++ include/net/xdp_sock.h | 4 ++-- include/uapi/linux/bpf.h | 4 ++++ 3 files changed, 14 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index e5a309e6a400..1fe137afa898 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -280,6 +280,7 @@ enum bpf_reg_type { PTR_TO_TCP_SOCK, /* reg points to struct tcp_sock */ PTR_TO_TCP_SOCK_OR_NULL, /* reg points to struct tcp_sock or NULL */ PTR_TO_TP_BUFFER, /* reg points to a writable raw tp's buffer */ + PTR_TO_XDP_SOCK, /* reg points to struct xdp_sock */ }; /* The information passed from prog-specific *_is_valid_access @@ -727,6 +728,13 @@ void __cpu_map_insert_ctx(struct bpf_map *map, u32 index); void __cpu_map_flush(struct bpf_map *map); int cpu_map_enqueue(struct bpf_cpu_map_entry *rcpu, struct xdp_buff *xdp, struct net_device *dev_rx); +bool bpf_xdp_sock_is_valid_access(int off, int size, enum bpf_access_type type, + struct bpf_insn_access_aux *info); +u32 bpf_xdp_sock_convert_ctx_access(enum bpf_access_type type, + const struct bpf_insn *si, + struct bpf_insn *insn_buf, + struct bpf_prog *prog, + u32 *target_size); /* Return map's numa specified by userspace */ static inline int bpf_map_attr_numa_node(const union bpf_attr *attr) diff --git a/include/net/xdp_sock.h b/include/net/xdp_sock.h index d074b6d60f8a..ae0f368a62bb 100644 --- a/include/net/xdp_sock.h +++ b/include/net/xdp_sock.h @@ -58,11 +58,11 @@ struct xdp_sock { struct xdp_umem *umem; struct list_head flush_node; u16 queue_id; - struct xsk_queue *tx ____cacheline_aligned_in_smp; - struct list_head list; bool zc; /* Protects multiple processes in the control path */ struct mutex mutex; + struct xsk_queue *tx ____cacheline_aligned_in_smp; + struct list_head list; /* Mutual exclusion of NAPI TX thread and sendmsg error paths * in the SKB destructor callback. */ diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index 7c6aef253173..ae0907d8c03a 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -3083,6 +3083,10 @@ struct bpf_sock_tuple { }; }; +struct bpf_xdp_sock { + __u32 queue_id; +}; + #define XDP_PACKET_HEADROOM 256 /* User return codes for XDP prog type. -- cgit v1.2.3 From 89fec474fa1ab2c754e48d29e1081a2c2bd22dc6 Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Mon, 10 Jun 2019 21:40:00 -0700 Subject: net/tls: pass record number as a byte array TLS offload code casts record number to a u64. The buffer should be aligned to 8 bytes, but its actually a __be64, and the rest of the TLS code treats it as big int. Make the offload callbacks take a byte array, drivers can make the choice to do the ugly cast if they want to. Prepare for copying the record number onto the stack by defining a constant for max size of the byte array. Signed-off-by: Jakub Kicinski Reviewed-by: Dirk van der Merwe Signed-off-by: David S. Miller --- include/net/tls.h | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/net/tls.h b/include/net/tls.h index 3ecf45adb707..25641e2f5b96 100644 --- a/include/net/tls.h +++ b/include/net/tls.h @@ -62,6 +62,7 @@ #define TLS_DEVICE_NAME_MAX 32 #define MAX_IV_SIZE 16 +#define TLS_MAX_REC_SEQ_SIZE 8 /* For AES-CCM, the full 16-bytes of IV is made of '4' fields of given sizes. * @@ -299,7 +300,7 @@ struct tlsdev_ops { struct tls_context *ctx, enum tls_offload_ctx_dir direction); void (*tls_dev_resync_rx)(struct net_device *netdev, - struct sock *sk, u32 seq, u64 rcd_sn); + struct sock *sk, u32 seq, u8 *rcd_sn); }; struct tls_offload_context_rx { @@ -607,6 +608,6 @@ int tls_sw_fallback_init(struct sock *sk, int tls_set_device_offload_rx(struct sock *sk, struct tls_context *ctx); void tls_device_offload_cleanup_rx(struct sock *sk); -void handle_device_resync(struct sock *sk, u32 seq, u64 rcd_sn); +void handle_device_resync(struct sock *sk, u32 seq); #endif /* _TLS_OFFLOAD_H */ -- cgit v1.2.3 From fe58a5a02cd9f49d5868539b4146ec1e5e5176e4 Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Mon, 10 Jun 2019 21:40:01 -0700 Subject: net/tls: rename handle_device_resync() handle_device_resync() doesn't describe the function very well. The function checks if resync should be issued upon parsing of a new record. Signed-off-by: Jakub Kicinski Reviewed-by: Dirk van der Merwe Signed-off-by: David S. Miller --- include/net/tls.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/net/tls.h b/include/net/tls.h index 25641e2f5b96..1c512da5e4f4 100644 --- a/include/net/tls.h +++ b/include/net/tls.h @@ -608,6 +608,6 @@ int tls_sw_fallback_init(struct sock *sk, int tls_set_device_offload_rx(struct sock *sk, struct tls_context *ctx); void tls_device_offload_cleanup_rx(struct sock *sk); -void handle_device_resync(struct sock *sk, u32 seq); +void tls_device_rx_resync_new_rec(struct sock *sk, u32 seq); #endif /* _TLS_OFFLOAD_H */ -- cgit v1.2.3 From f953d33ba1225d68cf8790b4706d8c4410b15926 Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Mon, 10 Jun 2019 21:40:02 -0700 Subject: net/tls: add kernel-driven TLS RX resync TLS offload device may lose sync with the TCP stream if packets arrive out of order. Drivers can currently request a resync at a specific TCP sequence number. When a record is found starting at that sequence number kernel will inform the device of the corresponding record number. This requires the device to constantly scan the stream for a known pattern (constant bytes of the header) after sync is lost. This patch adds an alternative approach which is entirely under the control of the kernel. Kernel tracks records it had to fully decrypt, even though TLS socket is in TLS_HW mode. If multiple records did not have any decrypted parts - it's a pretty strong indication that the device is out of sync. We choose the min number of fully encrypted records to be 2, which should hopefully be more than will get retransmitted at a time. After kernel decides the device is out of sync it schedules a resync request. If the TCP socket is empty the resync gets performed immediately. If socket is not empty we leave the record parser to resync when next record comes. Before resync in message parser we peek at the TCP socket and don't attempt the sync if the socket already has some of the next record queued. On resync failure (encrypted data continues to flow in) we retry with exponential backoff, up to once every 128 records (with a 16k record thats at most once every 2M of data). Signed-off-by: Jakub Kicinski Reviewed-by: Dirk van der Merwe Signed-off-by: David S. Miller --- include/net/tls.h | 34 ++++++++++++++++++++++++++++++++-- 1 file changed, 32 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/net/tls.h b/include/net/tls.h index 1c512da5e4f4..28eca6a3b615 100644 --- a/include/net/tls.h +++ b/include/net/tls.h @@ -303,10 +303,33 @@ struct tlsdev_ops { struct sock *sk, u32 seq, u8 *rcd_sn); }; +enum tls_offload_sync_type { + TLS_OFFLOAD_SYNC_TYPE_DRIVER_REQ = 0, + TLS_OFFLOAD_SYNC_TYPE_CORE_NEXT_HINT = 1, +}; + +#define TLS_DEVICE_RESYNC_NH_START_IVAL 2 +#define TLS_DEVICE_RESYNC_NH_MAX_IVAL 128 + struct tls_offload_context_rx { /* sw must be the first member of tls_offload_context_rx */ struct tls_sw_context_rx sw; - atomic64_t resync_req; + enum tls_offload_sync_type resync_type; + /* this member is set regardless of resync_type, to avoid branches */ + u8 resync_nh_reset:1; + /* CORE_NEXT_HINT-only member, but use the hole here */ + u8 resync_nh_do_now:1; + union { + /* TLS_OFFLOAD_SYNC_TYPE_DRIVER_REQ */ + struct { + atomic64_t resync_req; + }; + /* TLS_OFFLOAD_SYNC_TYPE_CORE_NEXT_HINT */ + struct { + u32 decrypted_failed; + u32 decrypted_tgt; + } resync_nh; + }; u8 driver_state[] __aligned(8); /* The TLS layer reserves room for driver specific state * Currently the belief is that there is not enough @@ -587,6 +610,13 @@ static inline void tls_offload_rx_resync_request(struct sock *sk, __be32 seq) atomic64_set(&rx_ctx->resync_req, ((u64)ntohl(seq) << 32) | 1); } +static inline void +tls_offload_rx_resync_set_type(struct sock *sk, enum tls_offload_sync_type type) +{ + struct tls_context *tls_ctx = tls_get_ctx(sk); + + tls_offload_ctx_rx(tls_ctx)->resync_type = type; +} int tls_proccess_cmsg(struct sock *sk, struct msghdr *msg, unsigned char *record_type); @@ -608,6 +638,6 @@ int tls_sw_fallback_init(struct sock *sk, int tls_set_device_offload_rx(struct sock *sk, struct tls_context *ctx); void tls_device_offload_cleanup_rx(struct sock *sk); -void tls_device_rx_resync_new_rec(struct sock *sk, u32 seq); +void tls_device_rx_resync_new_rec(struct sock *sk, u32 rcd_len, u32 seq); #endif /* _TLS_OFFLOAD_H */ -- cgit v1.2.3 From eeb2efaf36c75753f9028de3500669bddfac81a8 Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Mon, 10 Jun 2019 21:40:08 -0700 Subject: net/tls: generalize the resync callback Currently only RX direction is ever resynced, however, TX may also get out of sequence if packets get dropped on the way to the driver. Rename the resync callback and add a direction parameter. Signed-off-by: Jakub Kicinski Reviewed-by: Dirk van der Merwe Signed-off-by: David S. Miller --- include/net/tls.h | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/net/tls.h b/include/net/tls.h index 28eca6a3b615..9b49baecc4a8 100644 --- a/include/net/tls.h +++ b/include/net/tls.h @@ -299,8 +299,9 @@ struct tlsdev_ops { void (*tls_dev_del)(struct net_device *netdev, struct tls_context *ctx, enum tls_offload_ctx_dir direction); - void (*tls_dev_resync_rx)(struct net_device *netdev, - struct sock *sk, u32 seq, u8 *rcd_sn); + void (*tls_dev_resync)(struct net_device *netdev, + struct sock *sk, u32 seq, u8 *rcd_sn, + enum tls_offload_ctx_dir direction); }; enum tls_offload_sync_type { -- cgit v1.2.3 From 50180074099fcda752d9d56282d23242b126ebc9 Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Mon, 10 Jun 2019 21:40:09 -0700 Subject: net/tls: add kernel-driven resync mechanism for TX TLS offload drivers keep track of TCP seq numbers to make sure the packets are fed into the HW in order. When packets get dropped on the way through the stack, the driver will get out of sync and have to use fallback encryption, but unless TCP seq number is resynced it will never match the packets correctly (or even worse - use incorrect record sequence number after TCP seq wraps). Existing drivers (mlx5) feed the entire record on every out-of-order event, allowing FW/HW to always be in sync. This patch adds an alternative, more akin to the RX resync. When driver sees a frame which is past its expected sequence number the stream must have gotten out of order (if the sequence number is smaller than expected its likely a retransmission which doesn't require resync). Driver will ask the stack to perform TX sync before it submits the next full record, and fall back to software crypto until stack has performed the sync. Signed-off-by: Jakub Kicinski Reviewed-by: Dirk van der Merwe Signed-off-by: David S. Miller --- include/net/tls.h | 23 +++++++++++++++++++++++ 1 file changed, 23 insertions(+) (limited to 'include') diff --git a/include/net/tls.h b/include/net/tls.h index 9b49baecc4a8..63e473420b00 100644 --- a/include/net/tls.h +++ b/include/net/tls.h @@ -212,6 +212,11 @@ struct tls_offload_context_tx { enum tls_context_flags { TLS_RX_SYNC_RUNNING = 0, + /* Unlike RX where resync is driven entirely by the core in TX only + * the driver knows when things went out of sync, so we need the flag + * to be atomic. + */ + TLS_TX_SYNC_SCHED = 1, }; struct cipher_context { @@ -619,6 +624,24 @@ tls_offload_rx_resync_set_type(struct sock *sk, enum tls_offload_sync_type type) tls_offload_ctx_rx(tls_ctx)->resync_type = type; } +static inline void tls_offload_tx_resync_request(struct sock *sk) +{ + struct tls_context *tls_ctx = tls_get_ctx(sk); + + WARN_ON(test_and_set_bit(TLS_TX_SYNC_SCHED, &tls_ctx->flags)); +} + +/* Driver's seq tracking has to be disabled until resync succeeded */ +static inline bool tls_offload_tx_resync_pending(struct sock *sk) +{ + struct tls_context *tls_ctx = tls_get_ctx(sk); + bool ret; + + ret = test_bit(TLS_TX_SYNC_SCHED, &tls_ctx->flags); + smp_mb__after_atomic(); + return ret; +} + int tls_proccess_cmsg(struct sock *sk, struct msghdr *msg, unsigned char *record_type); void tls_register_device(struct tls_device *device); -- cgit v1.2.3 From a842fe1425cb20f457abd3f8ef98b468f83ca98b Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Wed, 12 Jun 2019 11:57:25 -0700 Subject: tcp: add optional per socket transmit delay Adding delays to TCP flows is crucial for studying behavior of TCP stacks, including congestion control modules. Linux offers netem module, but it has unpractical constraints : - Need root access to change qdisc - Hard to setup on egress if combined with non trivial qdisc like FQ - Single delay for all flows. EDT (Earliest Departure Time) adoption in TCP stack allows us to enable a per socket delay at a very small cost. Networking tools can now establish thousands of flows, each of them with a different delay, simulating real world conditions. This requires FQ packet scheduler or a EDT-enabled NIC. This patchs adds TCP_TX_DELAY socket option, to set a delay in usec units. unsigned int tx_delay = 10000; /* 10 msec */ setsockopt(fd, SOL_TCP, TCP_TX_DELAY, &tx_delay, sizeof(tx_delay)); Note that FQ packet scheduler limits might need some tweaking : man tc-fq PARAMETERS limit Hard limit on the real queue size. When this limit is reached, new packets are dropped. If the value is lowered, packets are dropped so that the new limit is met. Default is 10000 packets. flow_limit Hard limit on the maximum number of packets queued per flow. Default value is 100. Use of TCP_TX_DELAY option will increase number of skbs in FQ qdisc, so packets would be dropped if any of the previous limit is hit. Use of a jump label makes this support runtime-free, for hosts never using the option. Also note that TSQ (TCP Small Queues) limits are slightly changed with this patch : we need to account that skbs artificially delayed wont stop us providind more skbs to feed the pipe (netem uses skb_orphan_partial() for this purpose, but FQ can not use this trick) Because of that, using big delays might very well trigger old bugs in TSO auto defer logic and/or sndbuf limited detection. Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- include/linux/tcp.h | 2 ++ include/net/tcp.h | 19 +++++++++++++++++++ include/uapi/linux/tcp.h | 3 +++ 3 files changed, 24 insertions(+) (limited to 'include') diff --git a/include/linux/tcp.h b/include/linux/tcp.h index 711361af9ce0..c23019a3b264 100644 --- a/include/linux/tcp.h +++ b/include/linux/tcp.h @@ -245,6 +245,7 @@ struct tcp_sock { syn_smc:1; /* SYN includes SMC */ u32 tlp_high_seq; /* snd_nxt at the time of TLP retransmit. */ + u32 tcp_tx_delay; /* delay (in usec) added to TX packets */ u64 tcp_wstamp_ns; /* departure time for next sent data packet */ u64 tcp_clock_cache; /* cache last tcp_clock_ns() (see tcp_mstamp_refresh()) */ @@ -436,6 +437,7 @@ struct tcp_timewait_sock { u32 tw_last_oow_ack_time; int tw_ts_recent_stamp; + u32 tw_tx_delay; #ifdef CONFIG_TCP_MD5SIG struct tcp_md5sig_key *tw_md5_key; #endif diff --git a/include/net/tcp.h b/include/net/tcp.h index 204328b88412..49a178b8d5b2 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -2232,4 +2232,23 @@ void clean_acked_data_disable(struct inet_connection_sock *icsk); void clean_acked_data_flush(void); #endif +DECLARE_STATIC_KEY_FALSE(tcp_tx_delay_enabled); +static inline void tcp_add_tx_delay(struct sk_buff *skb, + const struct tcp_sock *tp) +{ + if (static_branch_unlikely(&tcp_tx_delay_enabled)) + skb->skb_mstamp_ns += (u64)tp->tcp_tx_delay * NSEC_PER_USEC; +} + +static inline void tcp_set_tx_time(struct sk_buff *skb, + const struct sock *sk) +{ + if (static_branch_unlikely(&tcp_tx_delay_enabled)) { + u32 delay = (sk->sk_state == TCP_TIME_WAIT) ? + tcp_twsk(sk)->tw_tx_delay : tcp_sk(sk)->tcp_tx_delay; + + skb->skb_mstamp_ns = tcp_clock_ns() + (u64)delay * NSEC_PER_USEC; + } +} + #endif /* _TCP_H */ diff --git a/include/uapi/linux/tcp.h b/include/uapi/linux/tcp.h index b521464ea962..b3564f85a762 100644 --- a/include/uapi/linux/tcp.h +++ b/include/uapi/linux/tcp.h @@ -127,6 +127,9 @@ enum { #define TCP_CM_INQ TCP_INQ +#define TCP_TX_DELAY 37 /* delay outgoing packets by XX usec */ + + #define TCP_REPAIR_ON 1 #define TCP_REPAIR_OFF 0 #define TCP_REPAIR_OFF_NO_WP -1 /* Turn off without window probes */ -- cgit v1.2.3 From 86eec50beaf3a45f6432d491072fa5c54284dbca Mon Sep 17 00:00:00 2001 From: Bodong Wang Date: Mon, 10 Jun 2019 23:38:19 +0000 Subject: net/mlx5: Support querying max VFs from device For ECPF with eswitch manager privilege, query the host max VF count by querying the device using query_functions command. With this enhancement: 1. flow steering entries are created only for valid vports based on the max VF count of the PF. 2. Driver only queries cap of valid vport. Eswitch requires the max VFs when doing initialization, so do sr-iov init before eswitch init. Signed-off-by: Bodong Wang Reviewed-by: Parav Pandit Signed-off-by: Saeed Mahameed --- include/linux/mlx5/driver.h | 7 ++----- include/linux/mlx5/mlx5_ifc.h | 2 +- 2 files changed, 3 insertions(+), 6 deletions(-) (limited to 'include') diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h index b5431f7d97cb..64155fe201ee 100644 --- a/include/linux/mlx5/driver.h +++ b/include/linux/mlx5/driver.h @@ -470,6 +470,7 @@ struct mlx5_core_sriov { struct mlx5_vf_context *vfs_ctx; int num_vfs; int enabled_vfs; + u16 max_vfs; }; struct mlx5_fc_stats { @@ -1103,13 +1104,9 @@ static inline bool mlx5_ecpf_vport_exists(struct mlx5_core_dev *dev) return mlx5_core_is_pf(dev) && MLX5_CAP_ESW(dev, ecpf_vport_exists); } -#define MLX5_HOST_PF_MAX_VFS (127u) static inline u16 mlx5_core_max_vfs(struct mlx5_core_dev *dev) { - if (mlx5_core_is_ecpf_esw_manager(dev)) - return MLX5_HOST_PF_MAX_VFS; - else - return pci_sriov_get_totalvfs(dev->pdev); + return dev->priv.sriov.max_vfs; } static inline int mlx5_get_gid_table_len(u16 param) diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h index 6513b985c5e9..e3c154b573a2 100644 --- a/include/linux/mlx5/mlx5_ifc.h +++ b/include/linux/mlx5/mlx5_ifc.h @@ -9711,7 +9711,7 @@ struct mlx5_ifc_host_params_context_bits { u8 reserved_at_8[0x8]; u8 host_num_of_vfs[0x10]; - u8 reserved_at_20[0x10]; + u8 host_total_vfs[0x10]; u8 host_pci_bus[0x10]; u8 reserved_at_40[0x10]; -- cgit v1.2.3 From ca390799c2aa03632c294107fa7f647bcbdff428 Mon Sep 17 00:00:00 2001 From: Yuval Avnery Date: Mon, 10 Jun 2019 23:38:23 +0000 Subject: net/mlx5: Change interrupt handler to call chain notifier Multiple EQs may share the same IRQ in subsequent patches. Instead of calling the IRQ handler directly, the EQ will register to an atomic chain notfier. The Linux built-in shared IRQ is not used because it forces the caller to disable the IRQ and clear affinity before free_irq() can be called. This patch is the first step in the separation of IRQ and EQ logic. Signed-off-by: Yuval Avnery Reviewed-by: Parav Pandit Signed-off-by: Saeed Mahameed --- include/linux/mlx5/eq.h | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/mlx5/eq.h b/include/linux/mlx5/eq.h index 00045cc4ea11..7909f1ff197c 100644 --- a/include/linux/mlx5/eq.h +++ b/include/linux/mlx5/eq.h @@ -26,8 +26,7 @@ struct mlx5_eq_param { u8 index; int nent; u64 mask; - void *context; - irq_handler_t handler; + struct notifier_block *nb; }; struct mlx5_eq * -- cgit v1.2.3 From 24163189da487b4caa751eef4e945c9333aae441 Mon Sep 17 00:00:00 2001 From: Yuval Avnery Date: Mon, 10 Jun 2019 23:38:25 +0000 Subject: net/mlx5: Separate IRQ request/free from EQ life cycle Instead of requesting IRQ with eq creation, IRQs will be requested before EQ table creation. Instead of freeing the IRQs after EQ destroy, free IRQs after eq table destroy. Signed-off-by: Yuval Avnery Reviewed-by: Parav Pandit Signed-off-by: Saeed Mahameed --- include/linux/mlx5/eq.h | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/mlx5/eq.h b/include/linux/mlx5/eq.h index 7909f1ff197c..73ab658af764 100644 --- a/include/linux/mlx5/eq.h +++ b/include/linux/mlx5/eq.h @@ -30,8 +30,7 @@ struct mlx5_eq_param { }; struct mlx5_eq * -mlx5_eq_create_generic(struct mlx5_core_dev *dev, const char *name, - struct mlx5_eq_param *param); +mlx5_eq_create_generic(struct mlx5_core_dev *dev, struct mlx5_eq_param *param); int mlx5_eq_destroy_generic(struct mlx5_core_dev *dev, struct mlx5_eq *eq); -- cgit v1.2.3 From 561aa15ad69e9d1e5a8bb277adb3209bf8091ecb Mon Sep 17 00:00:00 2001 From: Yuval Avnery Date: Mon, 10 Jun 2019 23:38:27 +0000 Subject: net/mlx5: Separate IRQ data from EQ table data IRQ table should only exist for mlx5_core_dev for PF and VF only. EQ table of mediated devices should hold a pointer to the IRQ table of the parent PCI device. Signed-off-by: Yuval Avnery Reviewed-by: Parav Pandit Signed-off-by: Saeed Mahameed --- include/linux/mlx5/driver.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include') diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h index 64155fe201ee..d8ab633406c2 100644 --- a/include/linux/mlx5/driver.h +++ b/include/linux/mlx5/driver.h @@ -492,6 +492,7 @@ struct mlx5_eswitch; struct mlx5_lag; struct mlx5_devcom; struct mlx5_eq_table; +struct mlx5_irq_table; struct mlx5_rate_limit { u32 rate; @@ -521,6 +522,8 @@ struct mlx5_core_roce { }; struct mlx5_priv { + /* IRQ table valid only for real pci devices PF or VF */ + struct mlx5_irq_table *irq_table; struct mlx5_eq_table *eq_table; /* pages stuff */ -- cgit v1.2.3 From 81bfa206032a67f0700459a64a5493c246629604 Mon Sep 17 00:00:00 2001 From: Ariel Levkovich Date: Mon, 10 Jun 2019 23:38:41 +0000 Subject: net/mlx5: Use a single IRQ for all async EQs The patch modifies the IRQ allocation so that all async EQs are assigned to the same IRQ resulting in more available IRQs for completion EQs. The changes are using the support for IRQ sharing and EQ polling budget that was introduced in previous patches so when the shared interrupt is triggered, the kernel will serially call the handler of each of the sharing EQs with a certain budget of EQEs to poll in order to prevent starvation. Signed-off-by: Ariel Levkovich Signed-off-by: Saeed Mahameed --- include/linux/mlx5/eq.h | 14 ++------------ 1 file changed, 2 insertions(+), 12 deletions(-) (limited to 'include') diff --git a/include/linux/mlx5/eq.h b/include/linux/mlx5/eq.h index 73ab658af764..4a94e04eff0a 100644 --- a/include/linux/mlx5/eq.h +++ b/include/linux/mlx5/eq.h @@ -4,17 +4,7 @@ #ifndef MLX5_CORE_EQ_H #define MLX5_CORE_EQ_H -enum { - MLX5_EQ_PAGEREQ_IDX = 0, - MLX5_EQ_CMD_IDX = 1, - MLX5_EQ_ASYNC_IDX = 2, - /* reserved to be used by mlx5_core ulps (mlx5e/mlx5_ib) */ - MLX5_EQ_PFAULT_IDX = 3, - MLX5_EQ_MAX_ASYNC_EQS, - /* completion eqs vector indices start here */ - MLX5_EQ_VEC_COMP_BASE = MLX5_EQ_MAX_ASYNC_EQS, -}; - +#define MLX5_IRQ_VEC_COMP_BASE 1 #define MLX5_NUM_CMD_EQE (32) #define MLX5_NUM_ASYNC_EQE (0x1000) #define MLX5_NUM_SPARE_EQE (0x80) @@ -23,7 +13,7 @@ struct mlx5_eq; struct mlx5_core_dev; struct mlx5_eq_param { - u8 index; + u8 irq_index; int nent; u64 mask; struct notifier_block *nb; -- cgit v1.2.3 From 1f8a7bee27e63d7c5287719049941e285e54d370 Mon Sep 17 00:00:00 2001 From: Yuval Avnery Date: Mon, 10 Jun 2019 23:38:42 +0000 Subject: net/mlx5: Add EQ enable/disable API Previously, EQ joined the chain notifier on creation. This forced the caller to be ready to handle events before creating the EQ through eq_create_generic interface. To help the caller control when the created EQ will be attached to the IRQ, add enable/disable API. Signed-off-by: Yuval Avnery Signed-off-by: Saeed Mahameed --- include/linux/mlx5/eq.h | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/mlx5/eq.h b/include/linux/mlx5/eq.h index 4a94e04eff0a..70e16dcfb4c4 100644 --- a/include/linux/mlx5/eq.h +++ b/include/linux/mlx5/eq.h @@ -16,13 +16,16 @@ struct mlx5_eq_param { u8 irq_index; int nent; u64 mask; - struct notifier_block *nb; }; struct mlx5_eq * mlx5_eq_create_generic(struct mlx5_core_dev *dev, struct mlx5_eq_param *param); int mlx5_eq_destroy_generic(struct mlx5_core_dev *dev, struct mlx5_eq *eq); +int mlx5_eq_enable(struct mlx5_core_dev *dev, struct mlx5_eq *eq, + struct notifier_block *nb); +void mlx5_eq_disable(struct mlx5_core_dev *dev, struct mlx5_eq *eq, + struct notifier_block *nb); struct mlx5_eqe *mlx5_eq_get_eqe(struct mlx5_eq *eq, u32 cc); void mlx5_eq_update_ci(struct mlx5_eq *eq, u32 cc, bool arm); -- cgit v1.2.3 From b25bbc2f24dcab9cd186ef4003c39bf51ad0454c Mon Sep 17 00:00:00 2001 From: Alex Vesker Date: Thu, 28 Jun 2018 15:05:58 +0300 Subject: net/mlx5: Add Vendor Specific Capability access gateway The Vendor Specific Capability (VSC) is used to activate a gateway interfacing with the device. The gateway is used to read or write device configurations, which are organized in different domains (spaces). A configuration access may result in multiple actions, reads, writes. Example usages are accessing the Crspace domain to read the crspace or locking a device semaphore using the Semaphore domain. The configuration access use pci_cfg_access to prevent parallel access to the VSC space by the driver and userspace calls. Signed-off-by: Alex Vesker Signed-off-by: Feras Daoud Signed-off-by: Saeed Mahameed --- 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 3a810bf043fe..f732445bcbdb 100644 --- a/include/linux/mlx5/driver.h +++ b/include/linux/mlx5/driver.h @@ -693,6 +693,7 @@ struct mlx5_core_dev { struct mlx5_clock clock; struct mlx5_ib_clock_info *clock_info; struct mlx5_fw_tracer *tracer; + u32 vsc_addr; }; struct mlx5_db { -- cgit v1.2.3 From 8b9d8baae1de7400f19058020ee8f0f27d436687 Mon Sep 17 00:00:00 2001 From: Alex Vesker Date: Tue, 17 Jul 2018 11:18:26 +0300 Subject: net/mlx5: Add Crdump support Crdump allows the driver to retrieve a dump of the FW PCI crspace. This is useful in case of catastrophic issues which may require FW reset. The crspace dump can be used for later debug. Signed-off-by: Alex Vesker Signed-off-by: Moshe Shemesh Reviewed-by: Feras Daoud Signed-off-by: Saeed Mahameed --- 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 f732445bcbdb..4ae533b3da07 100644 --- a/include/linux/mlx5/driver.h +++ b/include/linux/mlx5/driver.h @@ -435,6 +435,7 @@ struct mlx5_core_health { u32 prev; int miss_counter; bool sick; + u32 crdump_size; /* wq spinlock to synchronize draining */ spinlock_t wq_lock; struct workqueue_struct *wq; -- cgit v1.2.3 From 63cbc552eebf08818af2025aef4589a48ef849c0 Mon Sep 17 00:00:00 2001 From: Feras Daoud Date: Mon, 12 Nov 2018 15:23:02 +0200 Subject: net/mlx5: Handle SW reset of FW in error flow New mlx5 adapters allow the driver to reset the FW in the event of an error, this action called "SW Reset". When an SW reset is issued on any PF all PFs enter reset state which is a recoverable condition. The existing recovery flow was designed to allow the recovery of a VF after a PF driver reload. This patch adds the sw reset to the NIC states as a preparation for sw reset handling. When a software reset is issued the following occurs: 1. The NIC interface mode is set to 7 while the reset is in progress. 2. Once the reset completes the NIC interface mode is set to 1. Signed-off-by: Feras Daoud Signed-off-by: Moshe Shemesh Signed-off-by: Daniel Jurgens Reviewed-by: Alex Vesker Signed-off-by: Saeed Mahameed --- include/linux/mlx5/driver.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h index 4ae533b3da07..cc7fd8e62844 100644 --- a/include/linux/mlx5/driver.h +++ b/include/linux/mlx5/driver.h @@ -435,6 +435,7 @@ struct mlx5_core_health { u32 prev; int miss_counter; bool sick; + u32 fatal_error; u32 crdump_size; /* wq spinlock to synchronize draining */ spinlock_t wq_lock; @@ -906,7 +907,6 @@ void mlx5_start_health_poll(struct mlx5_core_dev *dev); void mlx5_stop_health_poll(struct mlx5_core_dev *dev, bool disable_health); void mlx5_drain_health_wq(struct mlx5_core_dev *dev); void mlx5_trigger_health_work(struct mlx5_core_dev *dev); -void mlx5_drain_health_recovery(struct mlx5_core_dev *dev); int mlx5_buf_alloc_node(struct mlx5_core_dev *dev, int size, struct mlx5_frag_buf *buf, int node); int mlx5_buf_alloc(struct mlx5_core_dev *dev, -- cgit v1.2.3 From 3e5b72ac2f298423902169db7893fef43365e0a6 Mon Sep 17 00:00:00 2001 From: Feras Daoud Date: Mon, 12 Nov 2018 16:40:17 +0200 Subject: net/mlx5: Issue SW reset on FW assert If a FW assert is considered fatal, indicated by a new bit in the health buffer, reset the FW. After the reset go through the normal recovery flow. Only one PF needs to issue the reset, so an attempt is made to prevent the 2nd function from also issuing the reset. It's not an error if that happens, it just slows recovery. Signed-off-by: Feras Daoud Signed-off-by: Alex Vesker Signed-off-by: Moshe Shemesh Signed-off-by: Daniel Jurgens Signed-off-by: Saeed Mahameed --- include/linux/mlx5/device.h | 10 +++++++++- include/linux/mlx5/driver.h | 1 + 2 files changed, 10 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/mlx5/device.h b/include/linux/mlx5/device.h index 5e760067ac41..35ed38c2ae6c 100644 --- a/include/linux/mlx5/device.h +++ b/include/linux/mlx5/device.h @@ -510,6 +510,10 @@ struct mlx5_cmd_layout { u8 status_own; }; +enum mlx5_fatal_assert_bit_offsets { + MLX5_RFR_OFFSET = 31, +}; + struct health_buffer { __be32 assert_var[5]; __be32 rsvd0[3]; @@ -518,12 +522,16 @@ struct health_buffer { __be32 rsvd1[2]; __be32 fw_ver; __be32 hw_id; - __be32 rsvd2; + __be32 rfr; u8 irisc_index; u8 synd; __be16 ext_synd; }; +enum mlx5_initializing_bit_offsets { + MLX5_FW_RESET_SUPPORTED_OFFSET = 30, +}; + enum mlx5_cmd_addr_l_sz_offset { MLX5_NIC_IFC_OFFSET = 8, }; diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h index cc7fd8e62844..89205b6cc7ef 100644 --- a/include/linux/mlx5/driver.h +++ b/include/linux/mlx5/driver.h @@ -583,6 +583,7 @@ struct mlx5_priv { }; enum mlx5_device_state { + MLX5_DEVICE_STATE_UNINITIALIZED, MLX5_DEVICE_STATE_UP, MLX5_DEVICE_STATE_INTERNAL_ERROR, }; -- cgit v1.2.3 From 1e34f3efd413a6318c3edd6e8e7e091f1214b2e6 Mon Sep 17 00:00:00 2001 From: Moshe Shemesh Date: Tue, 11 Dec 2018 16:09:53 +0200 Subject: net/mlx5: Create FW devlink_health_reporter Create mlx5_devlink_health_reporter for FW reporter. The FW reporter implements devlink_health_reporter diagnose callback. The fw reporter diagnose command can be triggered any time by the user to check current fw status. In healthy status, it will return clear syndrome. Otherwise it will return the syndrome and description of the error type. Command example and output on healthy status: $ devlink health diagnose pci/0000:82:00.0 reporter fw Syndrome: 0 Command example and output on non healthy status: $ devlink health diagnose pci/0000:82:00.0 reporter fw Syndrome: 8 Description: unrecoverable hardware error Signed-off-by: Moshe Shemesh Signed-off-by: Eran Ben Elisha Signed-off-by: Saeed Mahameed --- include/linux/mlx5/driver.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h index 89205b6cc7ef..8d5d065d1aa6 100644 --- a/include/linux/mlx5/driver.h +++ b/include/linux/mlx5/driver.h @@ -53,6 +53,7 @@ #include #include #include +#include enum { MLX5_BOARD_ID_LEN = 64, @@ -443,6 +444,7 @@ struct mlx5_core_health { unsigned long flags; struct work_struct work; struct delayed_work recover_work; + struct devlink_health_reporter *fw_reporter; }; struct mlx5_qp_table { -- cgit v1.2.3 From d1bf0e2cc4a6e66c2bff48176b8b2930098468ef Mon Sep 17 00:00:00 2001 From: Moshe Shemesh Date: Tue, 11 Dec 2018 16:09:56 +0200 Subject: net/mlx5: Report devlink health on FW issues Use devlink_health_report() to report any symptom of FW issue as FW counter miss or new health syndrome. The FW issues detected in mlx5 during poll_health which is called in timer atomic context and so health work queue is used to schedule the reports. Signed-off-by: Moshe Shemesh Signed-off-by: Eran Ben Elisha Signed-off-by: Saeed Mahameed --- include/linux/mlx5/driver.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h index 8d5d065d1aa6..1931a4080d78 100644 --- a/include/linux/mlx5/driver.h +++ b/include/linux/mlx5/driver.h @@ -435,7 +435,7 @@ struct mlx5_core_health { struct timer_list timer; u32 prev; int miss_counter; - bool sick; + u8 synd; u32 fatal_error; u32 crdump_size; /* wq spinlock to synchronize draining */ @@ -443,6 +443,7 @@ struct mlx5_core_health { struct workqueue_struct *wq; unsigned long flags; struct work_struct work; + struct work_struct report_work; struct delayed_work recover_work; struct devlink_health_reporter *fw_reporter; }; -- cgit v1.2.3 From 96c82cdfe77b5e769624af71ec0554434037b82f Mon Sep 17 00:00:00 2001 From: Moshe Shemesh Date: Tue, 11 Dec 2018 16:09:57 +0200 Subject: net/mlx5: Add fw fatal devlink_health_reporter Create mlx5_devlink_health_reporter for fw fatal reporter. The fw fatal reporter is added in addition to the fw reporter and implements the recover callback. The point of having two reporters for FW issues, is that we don't want to run FW recover on any issue, but only fatal ones. Signed-off-by: Moshe Shemesh Signed-off-by: Eran Ben Elisha Signed-off-by: Saeed Mahameed --- 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 1931a4080d78..caac96bf9c0d 100644 --- a/include/linux/mlx5/driver.h +++ b/include/linux/mlx5/driver.h @@ -446,6 +446,7 @@ struct mlx5_core_health { struct work_struct report_work; struct delayed_work recover_work; struct devlink_health_reporter *fw_reporter; + struct devlink_health_reporter *fw_fatal_reporter; }; struct mlx5_qp_table { -- cgit v1.2.3 From b3bd076f7501afea2871bb4738ab53498fd32cd5 Mon Sep 17 00:00:00 2001 From: Moshe Shemesh Date: Sun, 27 Jan 2019 18:38:39 +0200 Subject: net/mlx5: Report devlink health on FW fatal issues Report devlink health on FW fatal issues via fw_fatal_reporter. The driver recover flow for FW fatal error is now being handled by the devlink health. Having the recovery controlled by devlink health, the user has the ability to cancel the auto-recovery for debug session and run it manually. Call mlx5_enter_error_state() before calling devlink_health_report() to ensure entering device error state even if auto-recovery is off. Signed-off-by: Moshe Shemesh Signed-off-by: Saeed Mahameed --- include/linux/mlx5/driver.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h index caac96bf9c0d..25847beabd3f 100644 --- a/include/linux/mlx5/driver.h +++ b/include/linux/mlx5/driver.h @@ -442,7 +442,7 @@ struct mlx5_core_health { spinlock_t wq_lock; struct workqueue_struct *wq; unsigned long flags; - struct work_struct work; + struct work_struct fatal_report_work; struct work_struct report_work; struct delayed_work recover_work; struct devlink_health_reporter *fw_reporter; -- cgit v1.2.3 From 4368dada5b37e74a13b892ca5cef8a7d558e9a5f Mon Sep 17 00:00:00 2001 From: Shalom Toledo Date: Tue, 11 Jun 2019 18:45:09 +0300 Subject: ptp: ptp_clock: Publish scaled_ppm_to_ppb Publish scaled_ppm_to_ppb to allow drivers to use it. Signed-off-by: Shalom Toledo Reviewed-by: Petr Machata Signed-off-by: Ido Schimmel Signed-off-by: David S. Miller --- include/linux/ptp_clock_kernel.h | 8 ++++++++ 1 file changed, 8 insertions(+) (limited to 'include') diff --git a/include/linux/ptp_clock_kernel.h b/include/linux/ptp_clock_kernel.h index 28eb9c792522..93cc4f1d444a 100644 --- a/include/linux/ptp_clock_kernel.h +++ b/include/linux/ptp_clock_kernel.h @@ -212,6 +212,14 @@ extern void ptp_clock_event(struct ptp_clock *ptp, extern int ptp_clock_index(struct ptp_clock *ptp); +/** + * scaled_ppm_to_ppb() - convert scaled ppm to ppb + * + * @ppm: Parts per million, but with a 16 bit binary fractional field + */ + +extern s32 scaled_ppm_to_ppb(long ppm); + /** * ptp_find_pin() - obtain the pin index of a given auxiliary function * -- cgit v1.2.3 From 90cc4bd611903c77b29b94aa03ced6ad79229065 Mon Sep 17 00:00:00 2001 From: Alexander Wetzel Date: Mon, 6 May 2019 21:01:48 +0200 Subject: mac80211: AMPDU handling for Extended Key ID IEEE 802.11 - 2016 forbids mixing MPDUs with different keyIDs in one A-MPDU. Drivers supporting A-MPDUs and Extended Key ID must actively enforce that requirement due to the available two unicast keyIDs. Allow driver to signal mac80211 that they will not check the keyID in MPDUs when aggregating them and that they expect mac80211 to stop Tx aggregation when rekeying a connection using Extended Key ID. Signed-off-by: Alexander Wetzel 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 72080d9d617e..b7f0b56a09f4 100644 --- a/include/net/mac80211.h +++ b/include/net/mac80211.h @@ -2269,6 +2269,9 @@ struct ieee80211_txq { * @IEEE80211_HW_EXT_KEY_ID_NATIVE: Driver and hardware are supporting Extended * Key ID and can handle two unicast keys per station for Rx and Tx. * + * @IEEE80211_HW_NO_AMPDU_KEYBORDER_SUPPORT: The card/driver can't handle + * active Tx A-MPDU sessions with Extended Key IDs during rekey. + * * @NUM_IEEE80211_HW_FLAGS: number of hardware flags, used for sizing arrays */ enum ieee80211_hw_flags { @@ -2321,6 +2324,7 @@ enum ieee80211_hw_flags { IEEE80211_HW_SUPPORTS_MULTI_BSSID, IEEE80211_HW_SUPPORTS_ONLY_HE_MULTI_BSSID, IEEE80211_HW_EXT_KEY_ID_NATIVE, + IEEE80211_HW_NO_AMPDU_KEYBORDER_SUPPORT, /* keep last, obviously */ NUM_IEEE80211_HW_FLAGS -- cgit v1.2.3 From cc3e14c21ae928b3f8bce584b2c7d53d332b9738 Mon Sep 17 00:00:00 2001 From: Chung-Hsien Hsu Date: Thu, 9 May 2019 09:49:05 +0000 Subject: nl80211: add WPA3 definition for SAE authentication Add definition of WPA version 3 for SAE authentication. Signed-off-by: Chung-Hsien Hsu Signed-off-by: Chi-Hsien Lin Signed-off-by: Johannes Berg --- include/uapi/linux/nl80211.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/uapi/linux/nl80211.h b/include/uapi/linux/nl80211.h index 6f09d1500960..e9bf3d69d847 100644 --- a/include/uapi/linux/nl80211.h +++ b/include/uapi/linux/nl80211.h @@ -4406,6 +4406,7 @@ enum nl80211_mfp { enum nl80211_wpa_versions { NL80211_WPA_VERSION_1 = 1 << 0, NL80211_WPA_VERSION_2 = 1 << 1, + NL80211_WPA_VERSION_3 = 1 << 2, }; /** -- cgit v1.2.3 From 26f7044e95042daabcf1c71796a0e804a83c979f Mon Sep 17 00:00:00 2001 From: Chung-Hsien Hsu Date: Thu, 9 May 2019 09:49:06 +0000 Subject: nl80211: add support for SAE authentication offload Let drivers advertise support for station-mode SAE authentication offload with a new NL80211_EXT_FEATURE_SAE_OFFLOAD flag. Signed-off-by: Chung-Hsien Hsu Signed-off-by: Chi-Hsien Lin Signed-off-by: Johannes Berg --- include/linux/ieee80211.h | 1 + include/net/cfg80211.h | 5 +++++ include/uapi/linux/nl80211.h | 19 +++++++++++++++++++ 3 files changed, 25 insertions(+) (limited to 'include') diff --git a/include/linux/ieee80211.h b/include/linux/ieee80211.h index 61f0a316c6ac..5dfd949ade25 100644 --- a/include/linux/ieee80211.h +++ b/include/linux/ieee80211.h @@ -2612,6 +2612,7 @@ enum ieee80211_key_len { #define FILS_ERP_MAX_RRK_LEN 64 #define PMK_MAX_LEN 64 +#define SAE_PASSWORD_MAX_LEN 128 /* Public action codes (IEEE Std 802.11-2016, 9.6.8.1, Table 9-307) */ enum ieee80211_pub_actioncode { diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h index c19687833493..4b45056dbb25 100644 --- a/include/net/cfg80211.h +++ b/include/net/cfg80211.h @@ -742,6 +742,9 @@ struct survey_info { * CFG80211_MAX_WEP_KEYS WEP keys * @wep_tx_key: key index (0..3) of the default TX static WEP key * @psk: PSK (for devices supporting 4-way-handshake offload) + * @sae_pwd: password for SAE authentication (for devices supporting SAE + * offload) + * @sae_pwd_len: length of SAE password (for devices supporting SAE offload) */ struct cfg80211_crypto_settings { u32 wpa_versions; @@ -757,6 +760,8 @@ struct cfg80211_crypto_settings { struct key_params *wep_keys; int wep_tx_key; const u8 *psk; + const u8 *sae_pwd; + u8 sae_pwd_len; }; /** diff --git a/include/uapi/linux/nl80211.h b/include/uapi/linux/nl80211.h index e9bf3d69d847..8b1e43fecd25 100644 --- a/include/uapi/linux/nl80211.h +++ b/include/uapi/linux/nl80211.h @@ -234,6 +234,15 @@ * use in a FILS shared key connection with PMKSA caching. */ +/** + * DOC: SAE authentication offload + * + * By setting @NL80211_EXT_FEATURE_SAE_OFFLOAD flag drivers can indicate they + * support offloading SAE authentication for WPA3-Personal networks. In + * %NL80211_CMD_CONNECT the password for SAE should be specified using + * %NL80211_ATTR_SAE_PASSWORD. + */ + /** * enum nl80211_commands - supported nl80211 commands * @@ -2341,6 +2350,10 @@ enum nl80211_commands { * should be picking up the lowest tx power, either tx power per-interface * or per-station. * + * @NL80211_ATTR_SAE_PASSWORD: attribute for passing SAE password material. It + * is used with %NL80211_CMD_CONNECT to provide password for offloading + * SAE authentication for WPA3-Personal networks. + * * @NUM_NL80211_ATTR: total number of nl80211_attrs available * @NL80211_ATTR_MAX: highest attribute number currently defined * @__NL80211_ATTR_AFTER_LAST: internal use @@ -2794,6 +2807,8 @@ enum nl80211_attrs { NL80211_ATTR_STA_TX_POWER_SETTING, NL80211_ATTR_STA_TX_POWER, + NL80211_ATTR_SAE_PASSWORD, + /* add attributes here, update the policy in nl80211.c */ __NL80211_ATTR_AFTER_LAST, @@ -5423,6 +5438,9 @@ enum nl80211_feature_flags { * @NL80211_EXT_FEATURE_STA_TX_PWR: This driver supports controlling tx power * to a station. * + * @NL80211_EXT_FEATURE_SAE_OFFLOAD: Device wants to do SAE authentication in + * station mode (SAE password is passed as part of the connect command). + * * @NUM_NL80211_EXT_FEATURES: number of extended features. * @MAX_NL80211_EXT_FEATURES: highest extended feature index. */ @@ -5467,6 +5485,7 @@ enum nl80211_ext_feature_index { NL80211_EXT_FEATURE_SCHED_SCAN_BAND_SPECIFIC_RSSI_THOLD, NL80211_EXT_FEATURE_EXT_KEY_ID, NL80211_EXT_FEATURE_STA_TX_PWR, + NL80211_EXT_FEATURE_SAE_OFFLOAD, /* add new features before the definition below */ NUM_NL80211_EXT_FEATURES, -- cgit v1.2.3 From d7edf40c15e85b44c4bef146819b664089b827b1 Mon Sep 17 00:00:00 2001 From: John Crispin Date: Tue, 21 May 2019 17:02:58 +0200 Subject: mac80211: add ieee80211_get_he_iftype_cap() helper This function is similar to ieee80211_get_he_sta_cap() but allows passing the iftype. Also make ieee80211_get_he_sta_cap() use the new helper rather than duplicating the code. Signed-off-by: Shashidhar Lakkavalli Signed-off-by: John Crispin Signed-off-by: Johannes Berg --- include/net/cfg80211.h | 22 ++++++++++++++++++---- 1 file changed, 18 insertions(+), 4 deletions(-) (limited to 'include') diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h index 4b45056dbb25..20613b35afcd 100644 --- a/include/net/cfg80211.h +++ b/include/net/cfg80211.h @@ -382,16 +382,18 @@ ieee80211_get_sband_iftype_data(const struct ieee80211_supported_band *sband, } /** - * ieee80211_get_he_sta_cap - return HE capabilities for an sband's STA - * @sband: the sband to search for the STA on + * ieee80211_get_he_iftype_cap - return HE capabilities for an sband's iftype + * @sband: the sband to search for the iftype on + * @iftype: enum nl80211_iftype * * Return: pointer to the struct ieee80211_sta_he_cap, or NULL is none found */ static inline const struct ieee80211_sta_he_cap * -ieee80211_get_he_sta_cap(const struct ieee80211_supported_band *sband) +ieee80211_get_he_iftype_cap(const struct ieee80211_supported_band *sband, + u8 iftype) { const struct ieee80211_sband_iftype_data *data = - ieee80211_get_sband_iftype_data(sband, NL80211_IFTYPE_STATION); + ieee80211_get_sband_iftype_data(sband, iftype); if (data && data->he_cap.has_he) return &data->he_cap; @@ -399,6 +401,18 @@ ieee80211_get_he_sta_cap(const struct ieee80211_supported_band *sband) return NULL; } +/** + * ieee80211_get_he_sta_cap - return HE capabilities for an sband's STA + * @sband: the sband to search for the STA on + * + * Return: pointer to the struct ieee80211_sta_he_cap, or NULL is none found + */ +static inline const struct ieee80211_sta_he_cap * +ieee80211_get_he_sta_cap(const struct ieee80211_supported_band *sband) +{ + return ieee80211_get_he_iftype_cap(sband, NL80211_IFTYPE_STATION); +} + /** * wiphy_read_of_freq_limits - read frequency limits from device tree * -- cgit v1.2.3 From 901bb9891855164fdcfcfdd9c3d25bcc800d3f5b Mon Sep 17 00:00:00 2001 From: Johannes Berg Date: Tue, 28 May 2019 10:56:03 +0200 Subject: nl80211: require and validate vendor command policy Require that each vendor command give a policy of its sub-attributes in NL80211_ATTR_VENDOR_DATA, and then (stricly) check the contents, including the NLA_F_NESTED flag that we couldn't check on the outer layer because there we don't know yet. It is possible to use VENDOR_CMD_RAW_DATA for raw data, but then no nested data can be given (NLA_F_NESTED flag must be clear) and the data is just passed as is to the command. Signed-off-by: Johannes Berg --- include/net/cfg80211.h | 8 ++++++++ include/net/netlink.h | 9 +++++++++ 2 files changed, 17 insertions(+) (limited to 'include') diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h index 20613b35afcd..7c4aa868e7a5 100644 --- a/include/net/cfg80211.h +++ b/include/net/cfg80211.h @@ -4170,6 +4170,8 @@ struct sta_opmode_info { u8 rx_nss; }; +#define VENDOR_CMD_RAW_DATA ((const struct nla_policy *)ERR_PTR(-ENODATA)) + /** * struct wiphy_vendor_command - vendor command definition * @info: vendor command identifying information, as used in nl80211 @@ -4180,6 +4182,10 @@ struct sta_opmode_info { * @dumpit: dump callback, for transferring bigger/multiple items. The * @storage points to cb->args[5], ie. is preserved over the multiple * dumpit calls. + * @policy: policy pointer for attributes within %NL80211_ATTR_VENDOR_DATA. + * Set this to %VENDOR_CMD_RAW_DATA if no policy can be given and the + * attribute is just raw data (e.g. a firmware command). + * @maxattr: highest attribute number in policy * 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. @@ -4192,6 +4198,8 @@ struct wiphy_vendor_command { int (*dumpit)(struct wiphy *wiphy, struct wireless_dev *wdev, struct sk_buff *skb, const void *data, int data_len, unsigned long *storage); + const struct nla_policy *policy; + unsigned int maxattr; }; /** diff --git a/include/net/netlink.h b/include/net/netlink.h index 395b4406f4b0..28ece67f5312 100644 --- a/include/net/netlink.h +++ b/include/net/netlink.h @@ -1754,6 +1754,15 @@ static inline int __nla_validate_nested(const struct nlattr *start, int maxtype, validate, extack); } +static inline int +nl80211_validate_nested(const struct nlattr *start, int maxtype, + const struct nla_policy *policy, + struct netlink_ext_ack *extack) +{ + return __nla_validate_nested(start, maxtype, policy, + NL_VALIDATE_STRICT, extack); +} + static inline int nla_validate_nested_deprecated(const struct nlattr *start, int maxtype, const struct nla_policy *policy, -- cgit v1.2.3 From c9d3245e03ce20566e373b68dd24a7f2365d8dda Mon Sep 17 00:00:00 2001 From: John Crispin Date: Tue, 28 May 2019 13:49:47 +0200 Subject: mac80211: dynamically enable the TWT requester support on STA interfaces Turn TWT for STA interfaces when they associate and/or receive a beacon where the twt_responder bit has changed. Signed-off-by: Shashidhar Lakkavalli Signed-off-by: John Crispin 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 b7f0b56a09f4..e8fdb786b228 100644 --- a/include/net/mac80211.h +++ b/include/net/mac80211.h @@ -317,6 +317,7 @@ struct ieee80211_vif_chanctx_switch { * @BSS_CHANGED_MCAST_RATE: Multicast Rate setting changed for this interface * @BSS_CHANGED_FTM_RESPONDER: fime timing reasurement request responder * functionality changed for this BSS (AP mode). + * @BSS_CHANGED_TWT: TWT status changed * */ enum ieee80211_bss_change { @@ -347,6 +348,7 @@ enum ieee80211_bss_change { BSS_CHANGED_KEEP_ALIVE = 1<<24, BSS_CHANGED_MCAST_RATE = 1<<25, BSS_CHANGED_FTM_RESPONDER = 1<<26, + BSS_CHANGED_TWT = 1<<27, /* when adding here, make sure to change ieee80211_reconfig */ }; -- cgit v1.2.3 From a0de1ca383c77a1ae123d7c0cea45e327b61876a Mon Sep 17 00:00:00 2001 From: John Crispin Date: Tue, 28 May 2019 13:49:48 +0200 Subject: mac80211: allow turning TWT responder support on and off via netlink Allow the userland daemon to en/disable TWT support for an AP. Signed-off-by: Shashidhar Lakkavalli Signed-off-by: John Crispin [simplify parsing code] Signed-off-by: Johannes Berg --- include/net/cfg80211.h | 2 ++ include/net/mac80211.h | 3 +++ include/uapi/linux/nl80211.h | 4 ++++ 3 files changed, 9 insertions(+) (limited to 'include') diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h index 7c4aa868e7a5..ac758a54e971 100644 --- a/include/net/cfg80211.h +++ b/include/net/cfg80211.h @@ -897,6 +897,7 @@ enum cfg80211_ap_settings_flags { * @he_cap: HE capabilities (or %NULL if HE isn't enabled) * @ht_required: stations must support HT * @vht_required: stations must support VHT + * @twt_responder: Enable Target Wait Time * @flags: flags, as defined in enum cfg80211_ap_settings_flags */ struct cfg80211_ap_settings { @@ -923,6 +924,7 @@ struct cfg80211_ap_settings { const struct ieee80211_vht_cap *vht_cap; const struct ieee80211_he_cap_elem *he_cap; bool ht_required, vht_required; + bool twt_responder; u32 flags; }; diff --git a/include/net/mac80211.h b/include/net/mac80211.h index e8fdb786b228..ed4911306f03 100644 --- a/include/net/mac80211.h +++ b/include/net/mac80211.h @@ -506,6 +506,8 @@ struct ieee80211_ftm_responder_params { * @he_support: does this BSS support HE * @twt_requester: does this BSS support TWT requester (relevant for managed * mode only, set if the AP advertises TWT responder role) + * @twt_responder: does this BSS support TWT requester (relevant for managed + * mode only, set if the AP advertises TWT responder role) * @assoc: association status * @ibss_joined: indicates whether this station is part of an IBSS * or not @@ -613,6 +615,7 @@ struct ieee80211_bss_conf { u16 frame_time_rts_th; bool he_support; bool twt_requester; + bool twt_responder; /* association related data */ bool assoc, ibss_joined; bool ibss_creator; diff --git a/include/uapi/linux/nl80211.h b/include/uapi/linux/nl80211.h index 8b1e43fecd25..8fc3a43cac75 100644 --- a/include/uapi/linux/nl80211.h +++ b/include/uapi/linux/nl80211.h @@ -2354,6 +2354,8 @@ enum nl80211_commands { * is used with %NL80211_CMD_CONNECT to provide password for offloading * SAE authentication for WPA3-Personal networks. * + * @NL80211_ATTR_TWT_RESPONDER: Enable target wait time responder support. + * * @NUM_NL80211_ATTR: total number of nl80211_attrs available * @NL80211_ATTR_MAX: highest attribute number currently defined * @__NL80211_ATTR_AFTER_LAST: internal use @@ -2809,6 +2811,8 @@ enum nl80211_attrs { NL80211_ATTR_SAE_PASSWORD, + NL80211_ATTR_TWT_RESPONDER, + /* add attributes here, update the policy in nl80211.c */ __NL80211_ATTR_AFTER_LAST, -- cgit v1.2.3 From 4770c8f902285089ae1911de39808c808766a115 Mon Sep 17 00:00:00 2001 From: Ilan Peer Date: Wed, 29 May 2019 15:25:32 +0300 Subject: cfg80211: Add a function to iterate all BSS entries Add a function that iterates over the BSS entries associated with a given wiphy and calls a callback for each iterated BSS. This can be used by drivers in various ways, e.g., to evaluate some property for all the BSSs in the medium. Signed-off-by: Ilan Peer Signed-off-by: Luca Coelho Signed-off-by: Johannes Berg --- include/net/cfg80211.h | 20 ++++++++++++++++++++ 1 file changed, 20 insertions(+) (limited to 'include') diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h index ac758a54e971..4cd2857c06a4 100644 --- a/include/net/cfg80211.h +++ b/include/net/cfg80211.h @@ -5750,6 +5750,26 @@ void cfg80211_put_bss(struct wiphy *wiphy, struct cfg80211_bss *bss); */ void cfg80211_unlink_bss(struct wiphy *wiphy, struct cfg80211_bss *bss); +/** + * cfg80211_bss_iter - iterate all BSS entries + * + * This function iterates over the BSS entries associated with the given wiphy + * and calls the callback for the iterated BSS. The iterator function is not + * allowed to call functions that might modify the internal state of the BSS DB. + * + * @wiphy: the wiphy + * @chandef: if given, the iterator function will be called only if the channel + * of the currently iterated BSS is a subset of the given channel. + * @iter: the iterator function to call + * @iter_data: an argument to the iterator function + */ +void cfg80211_bss_iter(struct wiphy *wiphy, + struct cfg80211_chan_def *chandef, + void (*iter)(struct wiphy *wiphy, + struct cfg80211_bss *bss, + void *data), + void *iter_data); + static inline enum nl80211_bss_scan_width cfg80211_chandef_to_scan_width(const struct cfg80211_chan_def *chandef) { -- cgit v1.2.3 From cd6f34110285742ec5570f07aa2229e29f4d2092 Mon Sep 17 00:00:00 2001 From: Ilan Peer Date: Wed, 29 May 2019 15:25:33 +0300 Subject: ieee80211: Add a missing extended capability flag definition Add the "OBSS Narrow Bandwidth RU In OFDMA Tolerance Support" flag definition to the definitions of the flags covered by the Extended Capability IE. Signed-off-by: Ilan Peer Signed-off-by: Luca Coelho Signed-off-by: Johannes Berg --- include/linux/ieee80211.h | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'include') diff --git a/include/linux/ieee80211.h b/include/linux/ieee80211.h index 5dfd949ade25..2dbefeffc43c 100644 --- a/include/linux/ieee80211.h +++ b/include/linux/ieee80211.h @@ -2713,6 +2713,13 @@ enum ieee80211_tdls_actioncode { #define WLAN_EXT_CAPA10_TWT_REQUESTER_SUPPORT BIT(5) #define WLAN_EXT_CAPA10_TWT_RESPONDER_SUPPORT BIT(6) +/* + * When set, indicates that the AP is able to tolerate 26-tone RU UL + * OFDMA transmissions using HE TB PPDU from OBSS (not falsely classify the + * 26-tone RU UL OFDMA transmissions as radar pulses). + */ +#define WLAN_EXT_CAPA10_OBSS_NARROW_BW_RU_TOLERANCE_SUPPORT BIT(7) + /* Defines support for enhanced multi-bssid advertisement*/ #define WLAN_EXT_CAPA11_EMA_SUPPORT BIT(1) -- cgit v1.2.3 From 1e87fec9fa52a6f7c223998d6bfbd3464eb37e31 Mon Sep 17 00:00:00 2001 From: Johannes Berg Date: Thu, 16 May 2019 11:44:52 +0200 Subject: mac80211: call rate_control_send_low() internally There's no rate control algorithm that *doesn't* want to call it internally, and calling it internally will let us modify its behaviour in the future. Signed-off-by: Johannes Berg --- include/net/mac80211.h | 23 ----------------------- 1 file changed, 23 deletions(-) (limited to 'include') diff --git a/include/net/mac80211.h b/include/net/mac80211.h index ed4911306f03..4411120e5a9a 100644 --- a/include/net/mac80211.h +++ b/include/net/mac80211.h @@ -5960,29 +5960,6 @@ static inline int rate_supported(struct ieee80211_sta *sta, return (sta == NULL || sta->supp_rates[band] & BIT(index)); } -/** - * rate_control_send_low - helper for drivers for management/no-ack frames - * - * Rate control algorithms that agree to use the lowest rate to - * send management frames and NO_ACK data with the respective hw - * retries should use this in the beginning of their mac80211 get_rate - * callback. If true is returned the rate control can simply return. - * If false is returned we guarantee that sta and sta and priv_sta is - * not null. - * - * Rate control algorithms wishing to do more intelligent selection of - * rate for multicast/broadcast frames may choose to not use this. - * - * @sta: &struct ieee80211_sta pointer to the target destination. Note - * that this may be null. - * @priv_sta: private rate control structure. This may be null. - * @txrc: rate control information we sholud populate for mac80211. - */ -bool rate_control_send_low(struct ieee80211_sta *sta, - void *priv_sta, - struct ieee80211_tx_rate_control *txrc); - - static inline s8 rate_lowest_index(struct ieee80211_supported_band *sband, struct ieee80211_sta *sta) -- cgit v1.2.3 From 1c38c7f22068b54a7ba5f026a45663c6727ab84c Mon Sep 17 00:00:00 2001 From: James Prestwood Date: Wed, 12 Jun 2019 12:35:09 -0700 Subject: nl80211: send event when CMD_FRAME duration expires cfg80211_remain_on_channel_expired is used to notify userspace when the remain on channel duration expired by sending an event. There is no such equivalent to CMD_FRAME, where if offchannel and a duration is provided, the card will go offchannel for that duration. Currently there is no way for userspace to tell when that duration expired apart from setting an independent timeout. This timeout is quite erroneous as the kernel may not immediately send out the frame because of scheduling or work queue delays. In testing, it was found this timeout had to be quite large to accomidate any potential delays. A better solution is to have the kernel send an event when this duration has expired. There is already NL80211_CMD_FRAME_WAIT_CANCEL which can be used to cancel a NL80211_CMD_FRAME offchannel. Using this command matches perfectly to how NL80211_CMD_CANCEL_REMAIN_ON_CHANNEL works, where its both used to cancel and notify if the duration has expired. Signed-off-by: James Prestwood Signed-off-by: Johannes Berg --- include/net/cfg80211.h | 10 ++++++++++ 1 file changed, 10 insertions(+) (limited to 'include') diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h index 4cd2857c06a4..2d17e32eb438 100644 --- a/include/net/cfg80211.h +++ b/include/net/cfg80211.h @@ -6547,6 +6547,16 @@ void cfg80211_remain_on_channel_expired(struct wireless_dev *wdev, u64 cookie, struct ieee80211_channel *chan, gfp_t gfp); +/** + * cfg80211_tx_mgmt_expired - tx_mgmt duration expired + * @wdev: wireless device + * @cookie: the requested cookie + * @chan: The current channel (from tx_mgmt request) + * @gfp: allocation flags + */ +void cfg80211_tx_mgmt_expired(struct wireless_dev *wdev, u64 cookie, + struct ieee80211_channel *chan, gfp_t gfp); + /** * cfg80211_sinfo_alloc_tid_stats - allocate per-tid statistics. * -- cgit v1.2.3 From 99f3a064bc2e4bd5fe50218646c5be342f2ad18c Mon Sep 17 00:00:00 2001 From: Martin KaFai Lau Date: Thu, 13 Jun 2019 15:00:01 -0700 Subject: bpf: net: Add SO_DETACH_REUSEPORT_BPF There is SO_ATTACH_REUSEPORT_[CE]BPF but there is no DETACH. This patch adds SO_DETACH_REUSEPORT_BPF sockopt. The same sockopt can be used to undo both SO_ATTACH_REUSEPORT_[CE]BPF. reseport_detach_prog() is added and it is mostly a mirror of the existing reuseport_attach_prog(). The differences are, it does not call reuseport_alloc() and returns -ENOENT when there is no old prog. Cc: Craig Gallek Signed-off-by: Martin KaFai Lau Reviewed-by: Stanislav Fomichev Signed-off-by: Daniel Borkmann --- include/net/sock_reuseport.h | 2 ++ include/uapi/asm-generic/socket.h | 2 ++ 2 files changed, 4 insertions(+) (limited to 'include') diff --git a/include/net/sock_reuseport.h b/include/net/sock_reuseport.h index 8a5f70c7cdf2..d9112de85261 100644 --- a/include/net/sock_reuseport.h +++ b/include/net/sock_reuseport.h @@ -35,6 +35,8 @@ extern struct sock *reuseport_select_sock(struct sock *sk, struct sk_buff *skb, int hdr_len); extern int reuseport_attach_prog(struct sock *sk, struct bpf_prog *prog); +extern int reuseport_detach_prog(struct sock *sk); + int reuseport_get_id(struct sock_reuseport *reuse); #endif /* _SOCK_REUSEPORT_H */ diff --git a/include/uapi/asm-generic/socket.h b/include/uapi/asm-generic/socket.h index 8c1391c89171..77f7c1638eb1 100644 --- a/include/uapi/asm-generic/socket.h +++ b/include/uapi/asm-generic/socket.h @@ -117,6 +117,8 @@ #define SO_RCVTIMEO_NEW 66 #define SO_SNDTIMEO_NEW 67 +#define SO_DETACH_REUSEPORT_BPF 68 + #if !defined(__KERNEL__) #if __BITS_PER_LONG == 64 || (defined(__x86_64__) && defined(__ILP32__)) -- cgit v1.2.3 From fb85c4a730af221339c1dde1a434b73da0dfc3ed Mon Sep 17 00:00:00 2001 From: Stanislav Fomichev Date: Wed, 12 Jun 2019 10:30:37 -0700 Subject: bpf: export bpf_sock for BPF_PROG_TYPE_CGROUP_SOCK_ADDR prog type And let it use bpf_sk_storage_{get,delete} helpers to access socket storage. Kernel context (struct bpf_sock_addr_kern) already has sk member, so I just expose it to the BPF hooks. Using PTR_TO_SOCKET instead of PTR_TO_SOCK_COMMON should be safe because the hook is called on bind/connect. Cc: Martin Lau Signed-off-by: Stanislav Fomichev Signed-off-by: Daniel Borkmann --- include/uapi/linux/bpf.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index ae0907d8c03a..8815fc418cde 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -3247,6 +3247,7 @@ struct bpf_sock_addr { __u32 msg_src_ip6[4]; /* Allows 1,2,4-byte read an 4-byte write. * Stored in network byte order. */ + __bpf_md_ptr(struct bpf_sock *, sk); }; /* User bpf_sock_ops struct to access socket values and specify request ops -- cgit v1.2.3 From 1314ef561102e534e14cb1d37f89f5c1df0b2ea7 Mon Sep 17 00:00:00 2001 From: Stanislav Fomichev Date: Wed, 12 Jun 2019 10:30:38 -0700 Subject: bpf: export bpf_sock for BPF_PROG_TYPE_SOCK_OPS prog type And let it use bpf_sk_storage_{get,delete} helpers to access socket storage. Kernel context (struct bpf_sock_ops_kern) already has sk member, so I just expose it to the BPF hooks. I use PTR_TO_SOCKET_OR_NULL and return NULL in !is_fullsock case. I also export bpf_tcp_sock to make it possible to access tcp socket stats. Cc: Martin Lau Signed-off-by: Stanislav Fomichev Signed-off-by: Daniel Borkmann --- include/uapi/linux/bpf.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index 8815fc418cde..d0a23476f887 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -3299,6 +3299,7 @@ struct bpf_sock_ops { __u32 sk_txhash; __u64 bytes_received; __u64 bytes_acked; + __bpf_md_ptr(struct bpf_sock *, sk); }; /* Definitions for bpf_sock_ops_cb_flags */ -- cgit v1.2.3 From 7f94208c8f9a0a6d2ff0e0c0858c00ad8e5c8617 Mon Sep 17 00:00:00 2001 From: YueHaibing Date: Wed, 12 Jun 2019 17:18:47 +0800 Subject: bpf: Fix build error without CONFIG_INET If CONFIG_INET is not set, building fails: kernel/bpf/verifier.o: In function `check_mem_access': verifier.c: undefined reference to `bpf_xdp_sock_is_valid_access' kernel/bpf/verifier.o: In function `convert_ctx_accesses': verifier.c: undefined reference to `bpf_xdp_sock_convert_ctx_access' Reported-by: Hulk Robot Fixes: fada7fdc83c0 ("bpf: Allow bpf_map_lookup_elem() on an xskmap") Signed-off-by: YueHaibing Acked-by: Jonathan Lemon Signed-off-by: Daniel Borkmann --- include/linux/bpf.h | 31 ++++++++++++++++++++++++------- 1 file changed, 24 insertions(+), 7 deletions(-) (limited to 'include') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 1fe137afa898..b15fb5fcb741 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -728,13 +728,6 @@ void __cpu_map_insert_ctx(struct bpf_map *map, u32 index); void __cpu_map_flush(struct bpf_map *map); int cpu_map_enqueue(struct bpf_cpu_map_entry *rcpu, struct xdp_buff *xdp, struct net_device *dev_rx); -bool bpf_xdp_sock_is_valid_access(int off, int size, enum bpf_access_type type, - struct bpf_insn_access_aux *info); -u32 bpf_xdp_sock_convert_ctx_access(enum bpf_access_type type, - const struct bpf_insn *si, - struct bpf_insn *insn_buf, - struct bpf_prog *prog, - u32 *target_size); /* Return map's numa specified by userspace */ static inline int bpf_map_attr_numa_node(const union bpf_attr *attr) @@ -1110,6 +1103,15 @@ u32 bpf_tcp_sock_convert_ctx_access(enum bpf_access_type type, struct bpf_insn *insn_buf, struct bpf_prog *prog, u32 *target_size); + +bool bpf_xdp_sock_is_valid_access(int off, int size, enum bpf_access_type type, + struct bpf_insn_access_aux *info); + +u32 bpf_xdp_sock_convert_ctx_access(enum bpf_access_type type, + const struct bpf_insn *si, + struct bpf_insn *insn_buf, + struct bpf_prog *prog, + u32 *target_size); #else static inline bool bpf_tcp_sock_is_valid_access(int off, int size, enum bpf_access_type type, @@ -1126,6 +1128,21 @@ static inline u32 bpf_tcp_sock_convert_ctx_access(enum bpf_access_type type, { return 0; } +static inline bool bpf_xdp_sock_is_valid_access(int off, int size, + enum bpf_access_type type, + struct bpf_insn_access_aux *info) +{ + return false; +} + +static inline u32 bpf_xdp_sock_convert_ctx_access(enum bpf_access_type type, + const struct bpf_insn *si, + struct bpf_insn *insn_buf, + struct bpf_prog *prog, + u32 *target_size) +{ + return 0; +} #endif /* CONFIG_INET */ #endif /* _LINUX_BPF_H */ -- cgit v1.2.3 From 7c86f20d15b7c1132e0c24358ce240ba4cb002b7 Mon Sep 17 00:00:00 2001 From: Martin Blumenstingl Date: Wed, 12 Jun 2019 21:31:15 +0200 Subject: net: stmmac: use GPIO descriptors in stmmac_mdio_reset Switch stmmac_mdio_reset to use GPIO descriptors. GPIO core handles the "snps,reset-gpio" for GPIO descriptors so we don't need to take care of it inside the driver anymore. The advantage of this is that we now preserve the GPIO flags which are passed via devicetree. This is required on some newer Amlogic boards which use an Open Drain pin for the reset GPIO. This pin can only output a LOW signal or switch to input mode but it cannot output a HIGH signal. There are already devicetree bindings for these special cases and GPIO core already takes care of them but only if we use GPIO descriptors instead of GPIO numbers. Signed-off-by: Martin Blumenstingl Reviewed-by: Linus Walleij Reviewed-by: Andrew Lunn Signed-off-by: David S. Miller --- include/linux/stmmac.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/stmmac.h b/include/linux/stmmac.h index 4335bd771ce5..816edb545592 100644 --- a/include/linux/stmmac.h +++ b/include/linux/stmmac.h @@ -97,7 +97,7 @@ struct stmmac_mdio_bus_data { int *irqs; int probed_phy_irq; #ifdef CONFIG_OF - int reset_gpio, active_low; + int reset_gpio; u32 delays[3]; #endif }; -- cgit v1.2.3 From f01c373fbeed9f5870bb056b65750ccef42f1f20 Mon Sep 17 00:00:00 2001 From: Willem de Bruijn Date: Thu, 13 Jun 2019 11:08:15 -0400 Subject: locking/static_key: always define static_branch_deferred_inc This interface is currently only defined if CONFIG_JUMP_LABEL. Make it available also when jump labels are off. Signed-off-by: Willem de Bruijn Acked-by: Peter Zijlstra (Intel) Signed-off-by: David S. Miller --- include/linux/jump_label_ratelimit.h | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/jump_label_ratelimit.h b/include/linux/jump_label_ratelimit.h index 42710d5949ba..8c3ee291b2d8 100644 --- a/include/linux/jump_label_ratelimit.h +++ b/include/linux/jump_label_ratelimit.h @@ -60,8 +60,6 @@ extern void jump_label_update_timeout(struct work_struct *work); 0), \ } -#define static_branch_deferred_inc(x) static_branch_inc(&(x)->key) - #else /* !CONFIG_JUMP_LABEL */ struct static_key_deferred { struct static_key key; @@ -95,4 +93,7 @@ jump_label_rate_limit(struct static_key_deferred *key, STATIC_KEY_CHECK_USE(key); } #endif /* CONFIG_JUMP_LABEL */ + +#define static_branch_deferred_inc(x) static_branch_inc(&(x)->key) + #endif /* _LINUX_JUMP_LABEL_RATELIMIT_H */ -- cgit v1.2.3 From d6fb396cfaa71afc9f38d573b8ec6409fe3716de Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Thu, 13 Jun 2019 21:22:35 -0700 Subject: ipv4: tcp: fix ACK/RST sent with a transmit delay If we want to set a EDT time for the skb we want to send via ip_send_unicast_reply(), we have to pass a new parameter and initialize ipc.sockc.transmit_time with it. This fixes the EDT time for ACK/RST packets sent on behalf of a TIME_WAIT socket. Fixes: a842fe1425cb ("tcp: add optional per socket transmit delay") Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- include/net/ip.h | 2 +- include/net/tcp.h | 9 ++++++--- 2 files changed, 7 insertions(+), 4 deletions(-) (limited to 'include') diff --git a/include/net/ip.h b/include/net/ip.h index 6dbf88ea07f1..29d89de39822 100644 --- a/include/net/ip.h +++ b/include/net/ip.h @@ -279,7 +279,7 @@ void ip_send_unicast_reply(struct sock *sk, struct sk_buff *skb, const struct ip_options *sopt, __be32 daddr, __be32 saddr, const struct ip_reply_arg *arg, - unsigned int len); + unsigned int len, u64 transmit_time); #define IP_INC_STATS(net, field) SNMP_INC_STATS64((net)->mib.ip_statistics, field) #define __IP_INC_STATS(net, field) __SNMP_INC_STATS64((net)->mib.ip_statistics, field) diff --git a/include/net/tcp.h b/include/net/tcp.h index 49a178b8d5b2..96e0e53ff440 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -2240,15 +2240,18 @@ static inline void tcp_add_tx_delay(struct sk_buff *skb, skb->skb_mstamp_ns += (u64)tp->tcp_tx_delay * NSEC_PER_USEC; } -static inline void tcp_set_tx_time(struct sk_buff *skb, - const struct sock *sk) +/* Compute Earliest Departure Time for some control packets + * like ACK or RST for TIME_WAIT or non ESTABLISHED sockets. + */ +static inline u64 tcp_transmit_time(const struct sock *sk) { if (static_branch_unlikely(&tcp_tx_delay_enabled)) { u32 delay = (sk->sk_state == TCP_TIME_WAIT) ? tcp_twsk(sk)->tw_tx_delay : tcp_sk(sk)->tcp_tx_delay; - skb->skb_mstamp_ns = tcp_clock_ns() + (u64)delay * NSEC_PER_USEC; + return tcp_clock_ns() + (u64)delay * NSEC_PER_USEC; } + return 0; } #endif /* _TCP_H */ -- cgit v1.2.3 From 68b2d4a844e157c08773fcd8f412ba1a37bf45b8 Mon Sep 17 00:00:00 2001 From: Vivien Didelot Date: Fri, 14 Jun 2019 13:49:20 -0400 Subject: net: dsa: make cpu_dp non const A port may trigger operations on its dedicated CPU port, so using cpu_dp as const will raise warnings. Make cpu_dp non const. Signed-off-by: Vivien Didelot Reviewed-by: Florian Fainelli 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 82a2baa2dc48..1e8650fa8acc 100644 --- a/include/net/dsa.h +++ b/include/net/dsa.h @@ -181,7 +181,7 @@ struct dsa_port { struct dsa_switch *ds; unsigned int index; const char *name; - const struct dsa_port *cpu_dp; + struct dsa_port *cpu_dp; const char *mac; struct device_node *dn; unsigned int ageing_time; -- cgit v1.2.3 From 4838a54050284daac15dfeb1d65677e4dacf1bf5 Mon Sep 17 00:00:00 2001 From: Jose Abreu Date: Fri, 14 Jun 2019 17:06:57 +0200 Subject: net: stmmac: Fix wrapper drivers not detecting PHY Because of PHYLINK conversion we stopped parsing the phy-handle property from DT. Unfortunatelly, some wrapper drivers still rely on this phy node to configure the PHY. Let's restore the parsing of PHY handle while these wrapper drivers are not fully converted to PHYLINK. Fixes: 74371272f97f ("net: stmmac: Convert to phylink and remove phylib logic") Reported-by: Corentin Labbe Signed-off-by: Jose Abreu Cc: Joao Pinto Cc: David S. Miller Cc: Giuseppe Cavallaro Cc: Alexandre Torgue Tested-by: Corentin Labbe Signed-off-by: David S. Miller --- include/linux/stmmac.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/stmmac.h b/include/linux/stmmac.h index 816edb545592..a3c2d9945bcf 100644 --- a/include/linux/stmmac.h +++ b/include/linux/stmmac.h @@ -151,6 +151,7 @@ struct plat_stmmacenet_data { int interface; struct stmmac_mdio_bus_data *mdio_bus_data; struct device_node *phy_node; + struct device_node *phylink_node; struct device_node *mdio_node; struct stmmac_dma_cfg *dma_cfg; int clk_csr; -- cgit v1.2.3 From a51486266c3ba8e035a47fa96df67f274fe0c7d0 Mon Sep 17 00:00:00 2001 From: Jiri Pirko Date: Sat, 15 Jun 2019 11:03:49 +0200 Subject: net: sched: remove NET_CLS_IND config option This config option makes only couple of lines optional. Two small helpers and an int in couple of cls structs. Remove the config option and always compile this in. This saves the user from unexpected surprises when he adds a filter with ingress device match which is silently ignored in case the config option is not set. Signed-off-by: Jiri Pirko Signed-off-by: David S. Miller --- include/net/pkt_cls.h | 5 +---- include/uapi/linux/pkt_cls.h | 2 +- 2 files changed, 2 insertions(+), 5 deletions(-) (limited to 'include') diff --git a/include/net/pkt_cls.h b/include/net/pkt_cls.h index 514e3c80ecc1..720f2b32fc2f 100644 --- a/include/net/pkt_cls.h +++ b/include/net/pkt_cls.h @@ -7,6 +7,7 @@ #include #include #include +#include /* TC action not accessible from user space */ #define TC_ACT_REINSERT (TC_ACT_VALUE_MAX + 1) @@ -576,9 +577,6 @@ static inline int tcf_valid_offset(const struct sk_buff *skb, (ptr <= (ptr + len))); } -#ifdef CONFIG_NET_CLS_IND -#include - static inline int tcf_change_indev(struct net *net, struct nlattr *indev_tlv, struct netlink_ext_ack *extack) @@ -605,7 +603,6 @@ tcf_match_indev(struct sk_buff *skb, int ifindex) return false; return ifindex == skb->skb_iif; } -#endif /* CONFIG_NET_CLS_IND */ int tc_setup_flow_action(struct flow_action *flow_action, const struct tcf_exts *exts); diff --git a/include/uapi/linux/pkt_cls.h b/include/uapi/linux/pkt_cls.h index a93680fc4bfa..8cc6b6777b3c 100644 --- a/include/uapi/linux/pkt_cls.h +++ b/include/uapi/linux/pkt_cls.h @@ -295,7 +295,7 @@ enum { TCA_FW_UNSPEC, TCA_FW_CLASSID, TCA_FW_POLICE, - TCA_FW_INDEV, /* used by CONFIG_NET_CLS_IND */ + TCA_FW_INDEV, TCA_FW_ACT, /* used by CONFIG_NET_CLS_ACT */ TCA_FW_MASK, __TCA_FW_MAX -- cgit v1.2.3 From 98fdbea550378e0153092bce21261df86a8ccc57 Mon Sep 17 00:00:00 2001 From: Leon Romanovsky Date: Wed, 12 Jun 2019 15:20:11 +0300 Subject: net/mlx5: Declare more strictly devlink encap mode Devlink has UAPI declaration for encap mode, so there is no need to be loose on the data get/set by drivers. Update call sites to use enum devlink_eswitch_encap_mode instead of plain u8. Suggested-by: Parav Pandit Signed-off-by: Leon Romanovsky Acked-by: Jiri Pirko Reviewed-by: Parav Pandit Reviewed-by: Petr Vorel --- include/net/devlink.h | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/net/devlink.h b/include/net/devlink.h index 1c4adfb4195a..7a34fc586def 100644 --- a/include/net/devlink.h +++ b/include/net/devlink.h @@ -530,8 +530,10 @@ struct devlink_ops { int (*eswitch_inline_mode_get)(struct devlink *devlink, u8 *p_inline_mode); int (*eswitch_inline_mode_set)(struct devlink *devlink, u8 inline_mode, struct netlink_ext_ack *extack); - int (*eswitch_encap_mode_get)(struct devlink *devlink, u8 *p_encap_mode); - int (*eswitch_encap_mode_set)(struct devlink *devlink, u8 encap_mode, + int (*eswitch_encap_mode_get)(struct devlink *devlink, + enum devlink_eswitch_encap_mode *p_encap_mode); + int (*eswitch_encap_mode_set)(struct devlink *devlink, + enum devlink_eswitch_encap_mode encap_mode, struct netlink_ext_ack *extack); int (*info_get)(struct devlink *devlink, struct devlink_info_req *req, struct netlink_ext_ack *extack); -- cgit v1.2.3 From 82b11f071936a11094e1c44730030cd3d894e0b4 Mon Sep 17 00:00:00 2001 From: Maor Gottlieb Date: Wed, 12 Jun 2019 15:20:12 +0300 Subject: net/mlx5: Expose eswitch encap mode Add API to get the current Eswitch encap mode. It will be used in downstream patches to check if flow table can be created with encap support or not. Signed-off-by: Maor Gottlieb Reviewed-by: Petr Vorel Signed-off-by: Leon Romanovsky Reviewed-by: Parav Pandit --- include/linux/mlx5/eswitch.h | 12 ++++++++++++ 1 file changed, 12 insertions(+) (limited to 'include') diff --git a/include/linux/mlx5/eswitch.h b/include/linux/mlx5/eswitch.h index d81ee4df181c..174eec0871d9 100644 --- a/include/linux/mlx5/eswitch.h +++ b/include/linux/mlx5/eswitch.h @@ -7,6 +7,7 @@ #define _MLX5_ESWITCH_ #include +#include #define MLX5_ESWITCH_MANAGER(mdev) MLX5_CAP_GEN(mdev, eswitch_manager) @@ -62,4 +63,15 @@ u8 mlx5_eswitch_mode(struct mlx5_eswitch *esw); struct mlx5_flow_handle * mlx5_eswitch_add_send_to_vport_rule(struct mlx5_eswitch *esw, int vport, u32 sqn); + +#ifdef CONFIG_MLX5_ESWITCH +enum devlink_eswitch_encap_mode +mlx5_eswitch_get_encap_mode(const struct mlx5_core_dev *dev); +#else /* CONFIG_MLX5_ESWITCH */ +static inline enum devlink_eswitch_encap_mode +mlx5_eswitch_get_encap_mode(const struct mlx5_core_dev *dev) +{ + return DEVLINK_ESWITCH_ENCAP_MODE_NONE; +} +#endif /* CONFIG_MLX5_ESWITCH */ #endif -- cgit v1.2.3 From 7e770b252a62e7498cfa9411018100fd86e56d47 Mon Sep 17 00:00:00 2001 From: Martin Blumenstingl Date: Sat, 15 Jun 2019 12:09:30 +0200 Subject: net: stmmac: drop the reset GPIO from struct stmmac_mdio_bus_data No platform uses the "reset_gpio" field from stmmac_mdio_bus_data anymore. Drop it so we don't get any new consumers either. Plain GPIO numbers are being deprecated in favor of GPIO descriptors. If needed any new non-OF platform can add a GPIO descriptor lookup table. devm_gpiod_get_optional() will find the GPIO in that case. Suggested-by: Linus Walleij Signed-off-by: Martin Blumenstingl Signed-off-by: David S. Miller --- include/linux/stmmac.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include') diff --git a/include/linux/stmmac.h b/include/linux/stmmac.h index a3c2d9945bcf..a0cc6fa4965b 100644 --- a/include/linux/stmmac.h +++ b/include/linux/stmmac.h @@ -97,7 +97,6 @@ struct stmmac_mdio_bus_data { int *irqs; int probed_phy_irq; #ifdef CONFIG_OF - int reset_gpio; u32 delays[3]; #endif }; -- cgit v1.2.3 From ce4ab73ab0c27c6a3853695aa8ec0f453c6329cd Mon Sep 17 00:00:00 2001 From: Martin Blumenstingl Date: Sat, 15 Jun 2019 12:09:31 +0200 Subject: net: stmmac: drop the reset delays from struct stmmac_mdio_bus_data Only OF platforms use the reset delays and these delays are only read in stmmac_mdio_reset(). Move them from struct stmmac_mdio_bus_data to a stack variable inside stmmac_mdio_reset() because that's the only usage of these delays. Signed-off-by: Martin Blumenstingl Signed-off-by: David S. Miller --- include/linux/stmmac.h | 3 --- 1 file changed, 3 deletions(-) (limited to 'include') diff --git a/include/linux/stmmac.h b/include/linux/stmmac.h index a0cc6fa4965b..7c8328edd501 100644 --- a/include/linux/stmmac.h +++ b/include/linux/stmmac.h @@ -96,9 +96,6 @@ struct stmmac_mdio_bus_data { unsigned int phy_mask; int *irqs; int probed_phy_irq; -#ifdef CONFIG_OF - u32 delays[3]; -#endif }; struct stmmac_dma_cfg { -- cgit v1.2.3 From fead5b1b5838ba2f231d76e1b8ed31a4e9449382 Mon Sep 17 00:00:00 2001 From: Martin Blumenstingl Date: Sat, 15 Jun 2019 12:09:32 +0200 Subject: net: stmmac: drop the phy_reset hook from struct stmmac_mdio_bus_data The phy_reset hook is not set anywhere. Drop it to make stmmac_mdio_reset() smaller. Signed-off-by: Martin Blumenstingl Signed-off-by: David S. Miller --- include/linux/stmmac.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include') diff --git a/include/linux/stmmac.h b/include/linux/stmmac.h index 7c8328edd501..6dfb5aa75b0c 100644 --- a/include/linux/stmmac.h +++ b/include/linux/stmmac.h @@ -92,7 +92,6 @@ /* Platfrom data for platform device structure's platform_data field */ struct stmmac_mdio_bus_data { - int (*phy_reset)(void *priv); unsigned int phy_mask; int *irqs; int probed_phy_irq; -- cgit v1.2.3 From 857b46027d6f91150797295752581b7155b9d0e1 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?St=C3=A9phane=20Veyret?= Date: Sat, 25 May 2019 15:30:58 +0200 Subject: netfilter: nft_ct: add ct expectations support MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit This patch allows to add, list and delete expectations via nft objref infrastructure and assigning these expectations via nft rule. This allows manual port triggering when no helper is defined to manage a specific protocol. For example, if I have an online game which protocol is based on initial connection to TCP port 9753 of the server, and where the server opens a connection to port 9876, I can set rules as follow: table ip filter { ct expectation mygame { protocol udp; dport 9876; timeout 2m; size 1; } chain input { type filter hook input priority 0; policy drop; tcp dport 9753 ct expectation set "mygame"; } chain output { type filter hook output priority 0; policy drop; udp dport 9876 ct status expected accept; } } Signed-off-by: Stéphane Veyret Signed-off-by: Pablo Neira Ayuso --- include/uapi/linux/netfilter/nf_tables.h | 14 +++++++++++++- 1 file changed, 13 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/uapi/linux/netfilter/nf_tables.h b/include/uapi/linux/netfilter/nf_tables.h index 505393c6e959..31a6b8f7ff73 100644 --- a/include/uapi/linux/netfilter/nf_tables.h +++ b/include/uapi/linux/netfilter/nf_tables.h @@ -1445,6 +1445,17 @@ enum nft_ct_timeout_timeout_attributes { }; #define NFTA_CT_TIMEOUT_MAX (__NFTA_CT_TIMEOUT_MAX - 1) +enum nft_ct_expectation_attributes { + NFTA_CT_EXPECT_UNSPEC, + NFTA_CT_EXPECT_L3PROTO, + NFTA_CT_EXPECT_L4PROTO, + NFTA_CT_EXPECT_DPORT, + NFTA_CT_EXPECT_TIMEOUT, + NFTA_CT_EXPECT_SIZE, + __NFTA_CT_EXPECT_MAX, +}; +#define NFTA_CT_EXPECT_MAX (__NFTA_CT_EXPECT_MAX - 1) + #define NFT_OBJECT_UNSPEC 0 #define NFT_OBJECT_COUNTER 1 #define NFT_OBJECT_QUOTA 2 @@ -1454,7 +1465,8 @@ enum nft_ct_timeout_timeout_attributes { #define NFT_OBJECT_TUNNEL 6 #define NFT_OBJECT_CT_TIMEOUT 7 #define NFT_OBJECT_SECMARK 8 -#define __NFT_OBJECT_MAX 9 +#define NFT_OBJECT_CT_EXPECT 9 +#define __NFT_OBJECT_MAX 10 #define NFT_OBJECT_MAX (__NFT_OBJECT_MAX - 1) /** -- cgit v1.2.3 From 87e389b4c20091b562bd65d90272f9d7c67eb437 Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Tue, 4 Jun 2019 14:14:04 +0200 Subject: netfilter: conntrack: small conntrack lookup optimization ____nf_conntrack_find() performs checks on the conntrack objects in this order: 1. if (nf_ct_is_expired(ct)) This fetches ct->timeout, in third cache line. The hnnode that is used to store the list pointers resides in the first (origin) or second (reply tuple) cache lines. This test rarely passes, but its necessary to reap obsolete entries. 2. if (nf_ct_is_dying(ct)) This fetches ct->status, also in third cache line. The test is useless, and can be removed: Consider: cpu0 cpu1 ct = ____nf_conntrack_find() atomic_inc_not_zero(ct) -> ok nf_ct_key_equal -> ok is_dying -> DYING bit not set, ok set_bit(ct, DYING); ... unhash ... etc. return ct -> returning a ct with dying bit set, despite having a test for it. This (unlikely) case is fine - refcount prevents ct from getting free'd. 3. if (nf_ct_key_equal(h, tuple, zone, net)) nf_ct_key_equal checks in following order: 1. Tuple equal (first or second cacheline) 2. Zone equal (third cacheline) 3. confirmed bit set (->status, third cacheline) 4. net namespace match (third cacheline). Swapping "timeout" and "cpu" places timeout in the first cacheline. This has two advantages: 1. For a conntrack that won't even match the original tuple, we will now only fetch the first and maybe the second cacheline instead of always accessing the 3rd one as well. 2. in case of TCP ct->timeout changes frequently because we reduce/increase it when there are packets outstanding in the network. The first cacheline contains both the reference count and the ct spinlock, i.e. moving timeout there avoids writes to 3rd cacheline. The restart sequence in __nf_conntrack_find() is removed, if we found a candidate, but then fail to increment the refcount or discover the tuple has changed (object recycling), just pretend we did not find an entry. A second lookup won't find anything until another CPU adds a new conntrack with identical tuple into the hash table, which is very unlikely. We have the confirmation-time checks (when we hold hash lock) that deal with identical entries and even perform clash resolution in some cases. Signed-off-by: Florian Westphal Signed-off-by: Pablo Neira Ayuso --- include/net/netfilter/nf_conntrack.h | 7 +++---- 1 file changed, 3 insertions(+), 4 deletions(-) (limited to 'include') diff --git a/include/net/netfilter/nf_conntrack.h b/include/net/netfilter/nf_conntrack.h index 5cb19ce454d1..c86657d99630 100644 --- a/include/net/netfilter/nf_conntrack.h +++ b/include/net/netfilter/nf_conntrack.h @@ -70,7 +70,8 @@ struct nf_conn { struct nf_conntrack ct_general; spinlock_t lock; - u16 cpu; + /* jiffies32 when this ct is considered dead */ + u32 timeout; #ifdef CONFIG_NF_CONNTRACK_ZONES struct nf_conntrack_zone zone; @@ -82,9 +83,7 @@ struct nf_conn { /* Have we seen traffic both ways yet? (bitset) */ unsigned long status; - /* jiffies32 when this ct is considered dead */ - u32 timeout; - + u16 cpu; possible_net_t ct_net; #if IS_ENABLED(CONFIG_NF_NAT) -- cgit v1.2.3 From 9911c1139fd072594ac259c2ce055b004ca92f49 Mon Sep 17 00:00:00 2001 From: Pablo Neira Ayuso Date: Fri, 7 Jun 2019 16:37:30 +0200 Subject: netfilter: xt_owner: bail out with EINVAL in case of unsupported flags Reject flags that are not supported with EINVAL. Signed-off-by: Pablo Neira Ayuso --- include/uapi/linux/netfilter/xt_owner.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include') diff --git a/include/uapi/linux/netfilter/xt_owner.h b/include/uapi/linux/netfilter/xt_owner.h index 9e98c09eda32..5108df4d0313 100644 --- a/include/uapi/linux/netfilter/xt_owner.h +++ b/include/uapi/linux/netfilter/xt_owner.h @@ -11,6 +11,11 @@ enum { XT_OWNER_SUPPL_GROUPS = 1 << 3, }; +#define XT_OWNER_MASK (XT_OWNER_UID | \ + XT_OWNER_GID | \ + XT_OWNER_SOCKET | \ + XT_OWNER_SUPPL_GROUPS) + struct xt_owner_match_info { __u32 uid_min, uid_max; __u32 gid_min, gid_max; -- cgit v1.2.3 From ff6d090d0db41425aef0cfe5dc58bb3cc12514a2 Mon Sep 17 00:00:00 2001 From: Christian Brauner Date: Mon, 10 Jun 2019 23:26:05 +0200 Subject: netfilter: bridge: port sysctls to use brnf_net This ports the sysctls to use struct brnf_net. With this patch we make it possible to namespace the br_netfilter module in the following patch. Signed-off-by: Christian Brauner Signed-off-by: Pablo Neira Ayuso --- include/net/netfilter/br_netfilter.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/net/netfilter/br_netfilter.h b/include/net/netfilter/br_netfilter.h index 89808ce293c4..302fcd3aade2 100644 --- a/include/net/netfilter/br_netfilter.h +++ b/include/net/netfilter/br_netfilter.h @@ -42,7 +42,8 @@ static inline struct rtable *bridge_parent_rtable(const struct net_device *dev) return port ? &port->br->fake_rtable : NULL; } -struct net_device *setup_pre_routing(struct sk_buff *skb); +struct net_device *setup_pre_routing(struct sk_buff *skb, + const struct net *net); #if IS_ENABLED(CONFIG_IPV6) int br_validate_ipv6(struct net *net, struct sk_buff *skb); -- cgit v1.2.3 From 5fcc88ecf681b64da6c2c918352e2451db6a97ec Mon Sep 17 00:00:00 2001 From: Fernando Fernandez Mancera Date: Fri, 7 Jun 2019 02:36:02 +0200 Subject: netfilter: synproxy: add common uapi for SYNPROXY infrastructure This new UAPI file is going to be used by the xt and nft common SYNPROXY infrastructure. It is needed to avoid duplicated code. Signed-off-by: Fernando Fernandez Mancera Signed-off-by: Pablo Neira Ayuso --- include/uapi/linux/netfilter/nf_SYNPROXY.h | 19 +++++++++++++++++++ include/uapi/linux/netfilter/xt_SYNPROXY.h | 18 +++++++----------- 2 files changed, 26 insertions(+), 11 deletions(-) create mode 100644 include/uapi/linux/netfilter/nf_SYNPROXY.h (limited to 'include') diff --git a/include/uapi/linux/netfilter/nf_SYNPROXY.h b/include/uapi/linux/netfilter/nf_SYNPROXY.h new file mode 100644 index 000000000000..068d1b3a6f06 --- /dev/null +++ b/include/uapi/linux/netfilter/nf_SYNPROXY.h @@ -0,0 +1,19 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _NF_SYNPROXY_H +#define _NF_SYNPROXY_H + +#include + +#define NF_SYNPROXY_OPT_MSS 0x01 +#define NF_SYNPROXY_OPT_WSCALE 0x02 +#define NF_SYNPROXY_OPT_SACK_PERM 0x04 +#define NF_SYNPROXY_OPT_TIMESTAMP 0x08 +#define NF_SYNPROXY_OPT_ECN 0x10 + +struct nf_synproxy_info { + __u8 options; + __u8 wscale; + __u16 mss; +}; + +#endif /* _NF_SYNPROXY_H */ diff --git a/include/uapi/linux/netfilter/xt_SYNPROXY.h b/include/uapi/linux/netfilter/xt_SYNPROXY.h index ea5eba15d4c1..4d5611d647df 100644 --- a/include/uapi/linux/netfilter/xt_SYNPROXY.h +++ b/include/uapi/linux/netfilter/xt_SYNPROXY.h @@ -2,18 +2,14 @@ #ifndef _XT_SYNPROXY_H #define _XT_SYNPROXY_H -#include +#include -#define XT_SYNPROXY_OPT_MSS 0x01 -#define XT_SYNPROXY_OPT_WSCALE 0x02 -#define XT_SYNPROXY_OPT_SACK_PERM 0x04 -#define XT_SYNPROXY_OPT_TIMESTAMP 0x08 -#define XT_SYNPROXY_OPT_ECN 0x10 +#define XT_SYNPROXY_OPT_MSS NF_SYNPROXY_OPT_MSS +#define XT_SYNPROXY_OPT_WSCALE NF_SYNPROXY_OPT_WSCALE +#define XT_SYNPROXY_OPT_SACK_PERM NF_SYNPROXY_OPT_SACK_PERM +#define XT_SYNPROXY_OPT_TIMESTAMP NF_SYNPROXY_OPT_TIMESTAMP +#define XT_SYNPROXY_OPT_ECN NF_SYNPROXY_OPT_ECN -struct xt_synproxy_info { - __u8 options; - __u8 wscale; - __u16 mss; -}; +#define xt_synproxy_info nf_synproxy_info #endif /* _XT_SYNPROXY_H */ -- cgit v1.2.3 From 3006a5224f15cf68edc4878799ac6d6089861518 Mon Sep 17 00:00:00 2001 From: Fernando Fernandez Mancera Date: Fri, 7 Jun 2019 02:36:05 +0200 Subject: netfilter: synproxy: remove module dependency on IPv6 SYNPROXY This is a prerequisite for the infrastructure module NETFILTER_SYNPROXY. The new module is needed to avoid duplicated code for the SYNPROXY nftables support. Signed-off-by: Fernando Fernandez Mancera Signed-off-by: Pablo Neira Ayuso --- include/linux/netfilter_ipv6.h | 36 ++++++++++++++++++++++++++++++++++++ 1 file changed, 36 insertions(+) (limited to 'include') diff --git a/include/linux/netfilter_ipv6.h b/include/linux/netfilter_ipv6.h index 3a3dc4b1f0e7..35b12525ee45 100644 --- a/include/linux/netfilter_ipv6.h +++ b/include/linux/netfilter_ipv6.h @@ -8,6 +8,7 @@ #define __LINUX_IP6_NETFILTER_H #include +#include /* Extra routing may needed on local out, as the QUEUE target never returns * control to the table. @@ -35,6 +36,10 @@ struct nf_ipv6_ops { struct in6_addr *saddr); int (*route)(struct net *net, struct dst_entry **dst, struct flowi *fl, bool strict); + u32 (*cookie_init_sequence)(const struct ipv6hdr *iph, + const struct tcphdr *th, u16 *mssp); + int (*cookie_v6_check)(const struct ipv6hdr *iph, + const struct tcphdr *th, __u32 cookie); #endif void (*route_input)(struct sk_buff *skb); int (*fragment)(struct net *net, struct sock *sk, struct sk_buff *skb, @@ -154,6 +159,37 @@ static inline int nf_ip6_route_me_harder(struct net *net, struct sk_buff *skb) #endif } +static inline u32 nf_ipv6_cookie_init_sequence(const struct ipv6hdr *iph, + const struct tcphdr *th, + u16 *mssp) +{ +#if IS_MODULE(CONFIG_IPV6) + const struct nf_ipv6_ops *v6_ops = nf_get_ipv6_ops(); + + if (v6_ops) + return v6_ops->cookie_init_sequence(iph, th, mssp); + + return 0; +#else + return __cookie_v6_init_sequence(iph, th, mssp); +#endif +} + +static inline int nf_cookie_v6_check(const struct ipv6hdr *iph, + const struct tcphdr *th, __u32 cookie) +{ +#if IS_MODULE(CONFIG_IPV6) + const struct nf_ipv6_ops *v6_ops = nf_get_ipv6_ops(); + + if (v6_ops) + return v6_ops->cookie_v6_check(iph, th, cookie); + + return 0; +#else + return __cookie_v6_check(iph, th, cookie); +#endif +} + __sum16 nf_ip6_checksum(struct sk_buff *skb, unsigned int hook, unsigned int dataoff, u_int8_t protocol); -- cgit v1.2.3 From d7f9b2f18eaef74b4f948c7e24e3a8f796f0c90d Mon Sep 17 00:00:00 2001 From: Fernando Fernandez Mancera Date: Fri, 7 Jun 2019 02:36:07 +0200 Subject: netfilter: synproxy: extract SYNPROXY infrastructure from {ipt, ip6t}_SYNPROXY Add common functions into nf_synproxy_core.c to prepare for nftables support. The prototypes of the functions used by {ipt, ip6t}_SYNPROXY are in the new file nf_synproxy.h Signed-off-by: Fernando Fernandez Mancera Signed-off-by: Pablo Neira Ayuso --- include/net/netfilter/nf_conntrack_synproxy.h | 13 ++------ include/net/netfilter/nf_synproxy.h | 44 +++++++++++++++++++++++++++ 2 files changed, 46 insertions(+), 11 deletions(-) create mode 100644 include/net/netfilter/nf_synproxy.h (limited to 'include') diff --git a/include/net/netfilter/nf_conntrack_synproxy.h b/include/net/netfilter/nf_conntrack_synproxy.h index 2c7559a54092..c5659dcf5b1a 100644 --- a/include/net/netfilter/nf_conntrack_synproxy.h +++ b/include/net/netfilter/nf_conntrack_synproxy.h @@ -72,21 +72,12 @@ struct synproxy_options { }; struct tcphdr; -struct xt_synproxy_info; +struct nf_synproxy_info; bool synproxy_parse_options(const struct sk_buff *skb, unsigned int doff, const struct tcphdr *th, struct synproxy_options *opts); -unsigned int synproxy_options_size(const struct synproxy_options *opts); -void synproxy_build_options(struct tcphdr *th, - const struct synproxy_options *opts); -void synproxy_init_timestamp_cookie(const struct xt_synproxy_info *info, +void synproxy_init_timestamp_cookie(const struct nf_synproxy_info *info, struct synproxy_options *opts); -void synproxy_check_timestamp_cookie(struct synproxy_options *opts); - -unsigned int synproxy_tstamp_adjust(struct sk_buff *skb, unsigned int protoff, - struct tcphdr *th, struct nf_conn *ct, - enum ip_conntrack_info ctinfo, - const struct nf_conn_synproxy *synproxy); #endif /* _NF_CONNTRACK_SYNPROXY_H */ diff --git a/include/net/netfilter/nf_synproxy.h b/include/net/netfilter/nf_synproxy.h new file mode 100644 index 000000000000..3e8b3f03b687 --- /dev/null +++ b/include/net/netfilter/nf_synproxy.h @@ -0,0 +1,44 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _NF_SYNPROXY_SHARED_H +#define _NF_SYNPROXY_SHARED_H + +#include +#include +#include +#include +#include + +#include +#include + +void synproxy_send_client_synack(struct net *net, const struct sk_buff *skb, + const struct tcphdr *th, + const struct synproxy_options *opts); + +bool synproxy_recv_client_ack(struct net *net, + const struct sk_buff *skb, + const struct tcphdr *th, + struct synproxy_options *opts, u32 recv_seq); + +unsigned int ipv4_synproxy_hook(void *priv, struct sk_buff *skb, + const struct nf_hook_state *nhs); +int nf_synproxy_ipv4_init(struct synproxy_net *snet, struct net *net); +void nf_synproxy_ipv4_fini(struct synproxy_net *snet, struct net *net); + +#if IS_ENABLED(CONFIG_IPV6) +void synproxy_send_client_synack_ipv6(struct net *net, + const struct sk_buff *skb, + const struct tcphdr *th, + const struct synproxy_options *opts); + +bool synproxy_recv_client_ack_ipv6(struct net *net, const struct sk_buff *skb, + const struct tcphdr *th, + struct synproxy_options *opts, u32 recv_seq); + +unsigned int ipv6_synproxy_hook(void *priv, struct sk_buff *skb, + const struct nf_hook_state *nhs); +int nf_synproxy_ipv6_init(struct synproxy_net *snet, struct net *net); +void nf_synproxy_ipv6_fini(struct synproxy_net *snet, struct net *net); +#endif /* CONFIG_IPV6 */ + +#endif /* _NF_SYNPROXY_SHARED_H */ -- cgit v1.2.3 From c681edae33e86ff27be2d6cc717663d91df20b0e Mon Sep 17 00:00:00 2001 From: Ard Biesheuvel Date: Mon, 17 Jun 2019 10:09:33 +0200 Subject: net: ipv4: move tcp_fastopen server side code to SipHash library Using a bare block cipher in non-crypto code is almost always a bad idea, not only for security reasons (and we've seen some examples of this in the kernel in the past), but also for performance reasons. In the TCP fastopen case, we call into the bare AES block cipher one or two times (depending on whether the connection is IPv4 or IPv6). On most systems, this results in a call chain such as crypto_cipher_encrypt_one(ctx, dst, src) crypto_cipher_crt(tfm)->cit_encrypt_one(crypto_cipher_tfm(tfm), ...); aesni_encrypt kernel_fpu_begin(); aesni_enc(ctx, dst, src); // asm routine kernel_fpu_end(); It is highly unlikely that the use of special AES instructions has a benefit in this case, especially since we are doing the above twice for IPv6 connections, instead of using a transform which can process the entire input in one go. We could switch to the cbcmac(aes) shash, which would at least get rid of the duplicated overhead in *some* cases (i.e., today, only arm64 has an accelerated implementation of cbcmac(aes), while x86 will end up using the generic cbcmac template wrapping the AES-NI cipher, which basically ends up doing exactly the above). However, in the given context, it makes more sense to use a light-weight MAC algorithm that is more suitable for the purpose at hand, such as SipHash. Since the output size of SipHash already matches our chosen value for TCP_FASTOPEN_COOKIE_SIZE, and given that it accepts arbitrary input sizes, this greatly simplifies the code as well. NOTE: Server farms backing a single server IP for load balancing purposes and sharing a single fastopen key will be adversely affected by this change unless all systems in the pool receive their kernel upgrades at the same time. Signed-off-by: Ard Biesheuvel Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- include/linux/tcp.h | 7 +------ include/net/tcp.h | 10 ++++------ 2 files changed, 5 insertions(+), 12 deletions(-) (limited to 'include') diff --git a/include/linux/tcp.h b/include/linux/tcp.h index c23019a3b264..9ea0e71f5c6a 100644 --- a/include/linux/tcp.h +++ b/include/linux/tcp.h @@ -58,12 +58,7 @@ static inline unsigned int tcp_optlen(const struct sk_buff *skb) /* TCP Fast Open Cookie as stored in memory */ struct tcp_fastopen_cookie { - union { - u8 val[TCP_FASTOPEN_COOKIE_MAX]; -#if IS_ENABLED(CONFIG_IPV6) - struct in6_addr addr; -#endif - }; + u64 val[TCP_FASTOPEN_COOKIE_MAX / sizeof(u64)]; s8 len; bool exp; /* In RFC6994 experimental option format */ }; diff --git a/include/net/tcp.h b/include/net/tcp.h index 96e0e53ff440..184930b02779 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -1628,9 +1628,9 @@ bool tcp_fastopen_defer_connect(struct sock *sk, int *err); /* Fastopen key context */ struct tcp_fastopen_context { - struct crypto_cipher *tfm[TCP_FASTOPEN_KEY_MAX]; - __u8 key[TCP_FASTOPEN_KEY_BUF_LENGTH]; - struct rcu_head rcu; + __u8 key[TCP_FASTOPEN_KEY_MAX][TCP_FASTOPEN_KEY_LENGTH]; + int num; + struct rcu_head rcu; }; extern unsigned int sysctl_tcp_fastopen_blackhole_timeout; @@ -1665,9 +1665,7 @@ bool tcp_fastopen_cookie_match(const struct tcp_fastopen_cookie *foc, static inline int tcp_fastopen_context_len(const struct tcp_fastopen_context *ctx) { - if (ctx->tfm[1]) - return 2; - return 1; + return ctx->num; } /* Latencies incurred by various limits for a sender. They are -- cgit v1.2.3 From 3de205cde4ee8e36416f8b1a1510658abb14f408 Mon Sep 17 00:00:00 2001 From: Ido Schimmel Date: Tue, 18 Jun 2019 18:12:43 +0300 Subject: netlink: Document all fields of 'struct nl_info' Some fields were not documented. Add documentation. Signed-off-by: Ido Schimmel Acked-by: Jiri Pirko Reviewed-by: David Ahern Signed-off-by: David S. Miller --- include/net/netlink.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/net/netlink.h b/include/net/netlink.h index 28ece67f5312..ce66e43b9b6a 100644 --- a/include/net/netlink.h +++ b/include/net/netlink.h @@ -378,7 +378,9 @@ struct nla_policy { /** * struct nl_info - netlink source information * @nlh: Netlink message header of original request + * @nl_net: Network namespace * @portid: Netlink PORTID of requesting application + * @skip_notify: Skip netlink notifications to user space */ struct nl_info { struct nlmsghdr *nlh; -- cgit v1.2.3 From c82481f7ea21be8ec960a28aef07bf258f6820b7 Mon Sep 17 00:00:00 2001 From: Ido Schimmel Date: Tue, 18 Jun 2019 18:12:44 +0300 Subject: netlink: Add field to skip in-kernel notifications The struct includes a 'skip_notify' flag that indicates if netlink notifications to user space should be suppressed. As explained in commit 3b1137fe7482 ("net: ipv6: Change notifications for multipath add to RTA_MULTIPATH"), this is useful to suppress per-nexthop RTM_NEWROUTE notifications when an IPv6 multipath route is added / deleted. Instead, one notification is sent for the entire multipath route. This concept is also useful for in-kernel notifications. Sending one in-kernel notification for the addition / deletion of an IPv6 multipath route - instead of one per-nexthop - provides a significant increase in the insertion / deletion rate to underlying devices. Add a 'skip_notify_kernel' flag to suppress in-kernel notifications. Signed-off-by: Ido Schimmel Acked-by: Jiri Pirko Reviewed-by: David Ahern Signed-off-by: David S. Miller --- include/net/netlink.h | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/net/netlink.h b/include/net/netlink.h index ce66e43b9b6a..e4650e5b64a1 100644 --- a/include/net/netlink.h +++ b/include/net/netlink.h @@ -381,12 +381,14 @@ struct nla_policy { * @nl_net: Network namespace * @portid: Netlink PORTID of requesting application * @skip_notify: Skip netlink notifications to user space + * @skip_notify_kernel: Skip selected in-kernel notifications */ struct nl_info { struct nlmsghdr *nlh; struct net *nl_net; u32 portid; - bool skip_notify; + u8 skip_notify:1, + skip_notify_kernel:1; }; /** -- cgit v1.2.3 From d4b96c7b51e8fe9bcf94c8ab8cd5717d2f005b04 Mon Sep 17 00:00:00 2001 From: Ido Schimmel Date: Tue, 18 Jun 2019 18:12:45 +0300 Subject: ipv6: Extend notifier info for multipath routes Extend the IPv6 FIB notifier info with number of sibling routes being notified. This will later allow listeners to process one notification for a multipath routes instead of N, where N is the number of nexthops. Signed-off-by: Ido Schimmel Acked-by: Jiri Pirko Reviewed-by: David Ahern Signed-off-by: David S. Miller --- include/net/ip6_fib.h | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'include') diff --git a/include/net/ip6_fib.h b/include/net/ip6_fib.h index 1e92f1500b87..7c3d5ab05879 100644 --- a/include/net/ip6_fib.h +++ b/include/net/ip6_fib.h @@ -377,6 +377,8 @@ typedef struct rt6_info *(*pol_lookup_t)(struct net *, struct fib6_entry_notifier_info { struct fib_notifier_info info; /* must be first */ struct fib6_info *rt; + unsigned int nsiblings; + bool multipath_rt; }; /* @@ -450,6 +452,11 @@ int call_fib6_entry_notifiers(struct net *net, enum fib_event_type event_type, struct fib6_info *rt, struct netlink_ext_ack *extack); +int call_fib6_multipath_entry_notifiers(struct net *net, + enum fib_event_type event_type, + struct fib6_info *rt, + unsigned int nsiblings, + struct netlink_ext_ack *extack); void fib6_rt_update(struct net *net, struct fib6_info *rt, struct nl_info *info); void inet6_rt_notify(int event, struct fib6_info *rt, struct nl_info *info, -- cgit v1.2.3 From d5382fef70ce273608d6fc652c24f075de3737ef Mon Sep 17 00:00:00 2001 From: Ido Schimmel Date: Tue, 18 Jun 2019 18:12:57 +0300 Subject: ipv6: Stop sending in-kernel notifications for each nexthop Both listeners - mlxsw and netdevsim - of IPv6 FIB notifications are now ready to handle IPv6 multipath notifications. Therefore, stop ignoring such notifications in both drivers and stop sending notification for each added / deleted nexthop. v2: * Remove 'multipath_rt' from 'struct fib6_entry_notifier_info' Signed-off-by: Ido Schimmel Acked-by: Jiri Pirko Reviewed-by: David Ahern Signed-off-by: David S. Miller --- include/net/ip6_fib.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include') diff --git a/include/net/ip6_fib.h b/include/net/ip6_fib.h index 7c3d5ab05879..87331f2c4af0 100644 --- a/include/net/ip6_fib.h +++ b/include/net/ip6_fib.h @@ -378,7 +378,6 @@ struct fib6_entry_notifier_info { struct fib_notifier_info info; /* must be first */ struct fib6_info *rt; unsigned int nsiblings; - bool multipath_rt; }; /* -- cgit v1.2.3 From 75345f888f700c4ab2448287e35d48c760b202e6 Mon Sep 17 00:00:00 2001 From: Denis Kirjanov Date: Mon, 17 Jun 2019 10:53:41 +0200 Subject: ipoib: show VF broadcast address in IPoIB case we can't see a VF broadcast address for but can see for PF Before: 11: ib1: mtu 2044 qdisc pfifo_fast state UP mode DEFAULT group default qlen 256 link/infiniband 80:00:00:66:fe:80:00:00:00:00:00:00:24:8a:07:03:00:a4:3e:7c brd 00:ff:ff:ff:ff:12:40:1b:ff:ff:00:00:00:00:00:00:ff:ff:ff:ff vf 0 MAC 14:80:00:00:66:fe, spoof checking off, link-state disable, trust off, query_rss off ... After: 11: ib1: mtu 2044 qdisc pfifo_fast state UP mode DEFAULT group default qlen 256 link/infiniband 80:00:00:66:fe:80:00:00:00:00:00:00:24:8a:07:03:00:a4:3e:7c brd 00:ff:ff:ff:ff:12:40:1b:ff:ff:00:00:00:00:00:00:ff:ff:ff:ff vf 0 link/infiniband 80:00:00:66:fe:80:00:00:00:00:00:00:24:8a:07:03:00:a4:3e:7c brd 00:ff:ff:ff:ff:12:40:1b:ff:ff:00:00:00:00:00:00:ff:ff:ff:ff, spoof checking off, link-state disable, trust off, query_rss off v1->v2: add the IFLA_VF_BROADCAST constant v2->v3: put IFLA_VF_BROADCAST at the end to avoid KABI breakage and set NLA_REJECT dev_setlink Signed-off-by: Denis Kirjanov Acked-by: Doug Ledford Signed-off-by: David S. Miller --- include/uapi/linux/if_link.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include') diff --git a/include/uapi/linux/if_link.h b/include/uapi/linux/if_link.h index 5b225ff63b48..6f75bda2c2d7 100644 --- a/include/uapi/linux/if_link.h +++ b/include/uapi/linux/if_link.h @@ -694,6 +694,7 @@ enum { IFLA_VF_IB_NODE_GUID, /* VF Infiniband node GUID */ IFLA_VF_IB_PORT_GUID, /* VF Infiniband port GUID */ IFLA_VF_VLAN_LIST, /* nested list of vlans, option for QinQ */ + IFLA_VF_BROADCAST, /* VF broadcast */ __IFLA_VF_MAX, }; @@ -704,6 +705,10 @@ struct ifla_vf_mac { __u8 mac[32]; /* MAX_ADDR_LEN */ }; +struct ifla_vf_broadcast { + __u8 broadcast[32]; +}; + struct ifla_vf_vlan { __u32 vf; __u32 vlan; /* 0 - 4095, 0 disables VLAN filter */ -- cgit v1.2.3 From 2589726d12a1b12eaaa93c7f1ea64287e383c7a5 Mon Sep 17 00:00:00 2001 From: Alexei Starovoitov Date: Sat, 15 Jun 2019 12:12:20 -0700 Subject: bpf: introduce bounded loops Allow the verifier to validate the loops by simulating their execution. Exisiting programs have used '#pragma unroll' to unroll the loops by the compiler. Instead let the verifier simulate all iterations of the loop. In order to do that introduce parentage chain of bpf_verifier_state and 'branches' counter for the number of branches left to explore. See more detailed algorithm description in bpf_verifier.h This algorithm borrows the key idea from Edward Cree approach: https://patchwork.ozlabs.org/patch/877222/ Additional state pruning heuristics make such brute force loop walk practical even for large loops. Signed-off-by: Alexei Starovoitov Acked-by: Andrii Nakryiko Signed-off-by: Daniel Borkmann --- include/linux/bpf_verifier.h | 51 +++++++++++++++++++++++++++++++++++++++++++- 1 file changed, 50 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/bpf_verifier.h b/include/linux/bpf_verifier.h index 704ed7971472..03037373b447 100644 --- a/include/linux/bpf_verifier.h +++ b/include/linux/bpf_verifier.h @@ -194,6 +194,53 @@ struct bpf_func_state { struct bpf_verifier_state { /* call stack tracking */ struct bpf_func_state *frame[MAX_CALL_FRAMES]; + struct bpf_verifier_state *parent; + /* + * 'branches' field is the number of branches left to explore: + * 0 - all possible paths from this state reached bpf_exit or + * were safely pruned + * 1 - at least one path is being explored. + * This state hasn't reached bpf_exit + * 2 - at least two paths are being explored. + * This state is an immediate parent of two children. + * One is fallthrough branch with branches==1 and another + * state is pushed into stack (to be explored later) also with + * branches==1. The parent of this state has branches==1. + * The verifier state tree connected via 'parent' pointer looks like: + * 1 + * 1 + * 2 -> 1 (first 'if' pushed into stack) + * 1 + * 2 -> 1 (second 'if' pushed into stack) + * 1 + * 1 + * 1 bpf_exit. + * + * Once do_check() reaches bpf_exit, it calls update_branch_counts() + * and the verifier state tree will look: + * 1 + * 1 + * 2 -> 1 (first 'if' pushed into stack) + * 1 + * 1 -> 1 (second 'if' pushed into stack) + * 0 + * 0 + * 0 bpf_exit. + * After pop_stack() the do_check() will resume at second 'if'. + * + * If is_state_visited() sees a state with branches > 0 it means + * there is a loop. If such state is exactly equal to the current state + * it's an infinite loop. Note states_equal() checks for states + * equvalency, so two states being 'states_equal' does not mean + * infinite loop. The exact comparison is provided by + * states_maybe_looping() function. It's a stronger pre-check and + * much faster than states_equal(). + * + * This algorithm may not find all possible infinite loops or + * loop iteration count may be too high. + * In such cases BPF_COMPLEXITY_LIMIT_INSNS limit kicks in. + */ + u32 branches; u32 insn_idx; u32 curframe; u32 active_spin_lock; @@ -312,7 +359,9 @@ struct bpf_verifier_env { } cfg; u32 subprog_cnt; /* number of instructions analyzed by the verifier */ - u32 insn_processed; + u32 prev_insn_processed, insn_processed; + /* number of jmps, calls, exits analyzed so far */ + u32 prev_jmps_processed, jmps_processed; /* total verification time */ u64 verification_time; /* maximum number of verifier states kept in 'branching' instructions */ -- cgit v1.2.3 From b5dc0163d8fd78e64a7e21f309cf932fda34353e Mon Sep 17 00:00:00 2001 From: Alexei Starovoitov Date: Sat, 15 Jun 2019 12:12:25 -0700 Subject: bpf: precise scalar_value tracking Introduce precision tracking logic that helps cilium programs the most: old clang old clang new clang new clang with all patches with all patches bpf_lb-DLB_L3.o 1838 2283 1923 1863 bpf_lb-DLB_L4.o 3218 2657 3077 2468 bpf_lb-DUNKNOWN.o 1064 545 1062 544 bpf_lxc-DDROP_ALL.o 26935 23045 166729 22629 bpf_lxc-DUNKNOWN.o 34439 35240 174607 28805 bpf_netdev.o 9721 8753 8407 6801 bpf_overlay.o 6184 7901 5420 4754 bpf_lxc_jit.o 39389 50925 39389 50925 Consider code: 654: (85) call bpf_get_hash_recalc#34 655: (bf) r7 = r0 656: (15) if r8 == 0x0 goto pc+29 657: (bf) r2 = r10 658: (07) r2 += -48 659: (18) r1 = 0xffff8881e41e1b00 661: (85) call bpf_map_lookup_elem#1 662: (15) if r0 == 0x0 goto pc+23 663: (69) r1 = *(u16 *)(r0 +0) 664: (15) if r1 == 0x0 goto pc+21 665: (bf) r8 = r7 666: (57) r8 &= 65535 667: (bf) r2 = r8 668: (3f) r2 /= r1 669: (2f) r2 *= r1 670: (bf) r1 = r8 671: (1f) r1 -= r2 672: (57) r1 &= 255 673: (25) if r1 > 0x1e goto pc+12 R0=map_value(id=0,off=0,ks=20,vs=64,imm=0) R1_w=inv(id=0,umax_value=30,var_off=(0x0; 0x1f)) 674: (67) r1 <<= 1 675: (0f) r0 += r1 At this point the verifier will notice that scalar R1 is used in map pointer adjustment. R1 has to be precise for later operations on R0 to be validated properly. The verifier will backtrack the above code in the following way: last_idx 675 first_idx 664 regs=2 stack=0 before 675: (0f) r0 += r1 // started backtracking R1 regs=2 is a bitmask regs=2 stack=0 before 674: (67) r1 <<= 1 regs=2 stack=0 before 673: (25) if r1 > 0x1e goto pc+12 regs=2 stack=0 before 672: (57) r1 &= 255 regs=2 stack=0 before 671: (1f) r1 -= r2 // now both R1 and R2 has to be precise -> regs=6 mask regs=6 stack=0 before 670: (bf) r1 = r8 // after this insn R8 and R2 has to be precise regs=104 stack=0 before 669: (2f) r2 *= r1 // after this one R8, R2, and R1 regs=106 stack=0 before 668: (3f) r2 /= r1 regs=106 stack=0 before 667: (bf) r2 = r8 regs=102 stack=0 before 666: (57) r8 &= 65535 regs=102 stack=0 before 665: (bf) r8 = r7 regs=82 stack=0 before 664: (15) if r1 == 0x0 goto pc+21 // this is the end of verifier state. The following regs will be marked precised: R1_rw=invP(id=0,umax_value=65535,var_off=(0x0; 0xffff)) R7_rw=invP(id=0) parent didn't have regs=82 stack=0 marks // so backtracking continues into parent state last_idx 663 first_idx 655 regs=82 stack=0 before 663: (69) r1 = *(u16 *)(r0 +0) // R1 was assigned no need to track it further regs=80 stack=0 before 662: (15) if r0 == 0x0 goto pc+23 // keep tracking R7 regs=80 stack=0 before 661: (85) call bpf_map_lookup_elem#1 // keep tracking R7 regs=80 stack=0 before 659: (18) r1 = 0xffff8881e41e1b00 regs=80 stack=0 before 658: (07) r2 += -48 regs=80 stack=0 before 657: (bf) r2 = r10 regs=80 stack=0 before 656: (15) if r8 == 0x0 goto pc+29 regs=80 stack=0 before 655: (bf) r7 = r0 // here the assignment into R7 // mark R0 to be precise: R0_rw=invP(id=0) parent didn't have regs=1 stack=0 marks // regs=1 -> tracking R0 last_idx 654 first_idx 644 regs=1 stack=0 before 654: (85) call bpf_get_hash_recalc#34 // and in the parent frame it was a return value // nothing further to backtrack Two scalar registers not marked precise are equivalent from state pruning point of view. More details in the patch comments. It doesn't support bpf2bpf calls yet and enabled for root only. Signed-off-by: Alexei Starovoitov Acked-by: Andrii Nakryiko Signed-off-by: Daniel Borkmann --- include/linux/bpf_verifier.h | 18 ++++++++++++++++++ 1 file changed, 18 insertions(+) (limited to 'include') diff --git a/include/linux/bpf_verifier.h b/include/linux/bpf_verifier.h index 03037373b447..19393b0964a8 100644 --- a/include/linux/bpf_verifier.h +++ b/include/linux/bpf_verifier.h @@ -139,6 +139,8 @@ struct bpf_reg_state { */ s32 subreg_def; enum bpf_reg_liveness live; + /* if (!precise && SCALAR_VALUE) min/max/tnum don't affect safety */ + bool precise; }; enum bpf_stack_slot_type { @@ -190,6 +192,11 @@ struct bpf_func_state { struct bpf_stack_state *stack; }; +struct bpf_idx_pair { + u32 prev_idx; + u32 idx; +}; + #define MAX_CALL_FRAMES 8 struct bpf_verifier_state { /* call stack tracking */ @@ -245,6 +252,17 @@ struct bpf_verifier_state { u32 curframe; u32 active_spin_lock; bool speculative; + + /* first and last insn idx of this verifier state */ + u32 first_insn_idx; + u32 last_insn_idx; + /* jmp history recorded from first to last. + * backtracking is using it to go from last to first. + * For most states jmp_history_cnt is [0-3]. + * For loops can go up to ~40. + */ + struct bpf_idx_pair *jmp_history; + u32 jmp_history_cnt; }; #define bpf_get_spilled_reg(slot, frame) \ -- cgit v1.2.3 From 82828b88f081a0084cd65f90a4a1d3652f5adb66 Mon Sep 17 00:00:00 2001 From: Jiri Pirko Date: Wed, 19 Jun 2019 09:41:02 +0300 Subject: flow_dissector: add support for ingress ifindex dissection Add new key meta that contains ingress ifindex value and add a function to dissect this from skb. The key and function is prepared to cover other potential skb metadata values dissection. Signed-off-by: Jiri Pirko Signed-off-by: Ido Schimmel Signed-off-by: David S. Miller --- include/linux/skbuff.h | 4 ++++ include/net/flow_dissector.h | 9 +++++++++ 2 files changed, 13 insertions(+) (limited to 'include') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 28bdaf978e72..b5d427b149c9 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -1320,6 +1320,10 @@ skb_flow_dissect_flow_keys_basic(const struct net *net, data, proto, nhoff, hlen, flags); } +void skb_flow_dissect_meta(const struct sk_buff *skb, + struct flow_dissector *flow_dissector, + void *target_container); + void skb_flow_dissect_tunnel_info(const struct sk_buff *skb, struct flow_dissector *flow_dissector, diff --git a/include/net/flow_dissector.h b/include/net/flow_dissector.h index d7ce647a8ca9..02478e48fae4 100644 --- a/include/net/flow_dissector.h +++ b/include/net/flow_dissector.h @@ -200,6 +200,14 @@ struct flow_dissector_key_ip { __u8 ttl; }; +/** + * struct flow_dissector_key_meta: + * @ingress_ifindex: ingress ifindex + */ +struct flow_dissector_key_meta { + int ingress_ifindex; +}; + enum flow_dissector_key_id { FLOW_DISSECTOR_KEY_CONTROL, /* struct flow_dissector_key_control */ FLOW_DISSECTOR_KEY_BASIC, /* struct flow_dissector_key_basic */ @@ -225,6 +233,7 @@ enum flow_dissector_key_id { FLOW_DISSECTOR_KEY_CVLAN, /* struct flow_dissector_key_vlan */ FLOW_DISSECTOR_KEY_ENC_IP, /* struct flow_dissector_key_ip */ FLOW_DISSECTOR_KEY_ENC_OPTS, /* struct flow_dissector_key_enc_opts */ + FLOW_DISSECTOR_KEY_META, /* struct flow_dissector_key_meta */ FLOW_DISSECTOR_KEY_MAX, }; -- cgit v1.2.3 From 9558a83aee62be7c3ce9eddd6484a5da16aad4cf Mon Sep 17 00:00:00 2001 From: Jiri Pirko Date: Wed, 19 Jun 2019 09:41:04 +0300 Subject: net: flow_offload: implement support for meta key Implement support for previously added flow dissector meta key. Signed-off-by: Jiri Pirko Signed-off-by: Ido Schimmel Signed-off-by: David S. Miller --- include/net/flow_offload.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include') diff --git a/include/net/flow_offload.h b/include/net/flow_offload.h index 36fdb85c974d..36127c1858a4 100644 --- a/include/net/flow_offload.h +++ b/include/net/flow_offload.h @@ -10,6 +10,10 @@ struct flow_match { void *key; }; +struct flow_match_meta { + struct flow_dissector_key_meta *key, *mask; +}; + struct flow_match_basic { struct flow_dissector_key_basic *key, *mask; }; @@ -64,6 +68,8 @@ struct flow_match_enc_opts { struct flow_rule; +void flow_rule_match_meta(const struct flow_rule *rule, + struct flow_match_meta *out); void flow_rule_match_basic(const struct flow_rule *rule, struct flow_match_basic *out); void flow_rule_match_control(const struct flow_rule *rule, -- cgit v1.2.3 From 23cdf8752b26d4edbd60a6293bca492d83192d4d Mon Sep 17 00:00:00 2001 From: "David S. Miller" Date: Wed, 19 Jun 2019 10:12:58 -0400 Subject: act_ctinfo: Don't use BIT() in UAPI headers. Use _BITUL() instead. Reported-by: Stephen Rothwell Signed-off-by: David S. Miller --- include/uapi/linux/tc_act/tc_ctinfo.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/uapi/linux/tc_act/tc_ctinfo.h b/include/uapi/linux/tc_act/tc_ctinfo.h index da803e05a89b..32337304fbe5 100644 --- a/include/uapi/linux/tc_act/tc_ctinfo.h +++ b/include/uapi/linux/tc_act/tc_ctinfo.h @@ -27,8 +27,8 @@ enum { #define TCA_CTINFO_MAX (__TCA_CTINFO_MAX - 1) enum { - CTINFO_MODE_DSCP = BIT(0), - CTINFO_MODE_CPMARK = BIT(1) + CTINFO_MODE_DSCP = _BITUL(0), + CTINFO_MODE_CPMARK = _BITUL(1) }; #endif -- cgit v1.2.3 From 0afdeeed08b5f59148069e9f7a52d2ab0eba5d49 Mon Sep 17 00:00:00 2001 From: Ilias Apalodimas Date: Tue, 18 Jun 2019 15:05:12 +0200 Subject: net: page_pool: add helper function to retrieve dma addresses On a previous patch dma addr was stored in 'struct page'. Use that to retrieve DMA addresses used by network drivers Signed-off-by: Ilias Apalodimas Signed-off-by: Jesper Dangaard Brouer Signed-off-by: David S. Miller --- include/net/page_pool.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include') diff --git a/include/net/page_pool.h b/include/net/page_pool.h index 694d055e01ef..b885d86cb7a1 100644 --- a/include/net/page_pool.h +++ b/include/net/page_pool.h @@ -132,6 +132,11 @@ static inline void page_pool_recycle_direct(struct page_pool *pool, __page_pool_put_page(pool, page, true); } +static inline dma_addr_t page_pool_get_dma_addr(struct page *page) +{ + return page->dma_addr; +} + static inline bool is_page_pool_compiled_in(void) { #ifdef CONFIG_PAGE_POOL -- cgit v1.2.3 From a25d50bfe645b3ed6b2cb3773e7025db14a608f3 Mon Sep 17 00:00:00 2001 From: Ilias Apalodimas Date: Tue, 18 Jun 2019 15:05:17 +0200 Subject: net: page_pool: add helper function to unmap dma addresses On a previous patch dma addr was stored in 'struct page'. Use that to unmap DMA addresses used by network drivers Signed-off-by: Ilias Apalodimas Signed-off-by: Jesper Dangaard Brouer Signed-off-by: David S. Miller --- include/net/page_pool.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/net/page_pool.h b/include/net/page_pool.h index b885d86cb7a1..ad218cef88c5 100644 --- a/include/net/page_pool.h +++ b/include/net/page_pool.h @@ -110,6 +110,7 @@ static inline struct page *page_pool_dev_alloc_pages(struct page_pool *pool) struct page_pool *page_pool_create(const struct page_pool_params *params); void page_pool_destroy(struct page_pool *pool); +void page_pool_unmap_page(struct page_pool *pool, struct page *page); /* Never call this directly, use helpers below */ void __page_pool_put_page(struct page_pool *pool, -- cgit v1.2.3 From 6bf071bf09d4b2ff3ee8783531e2ce814f0870cb Mon Sep 17 00:00:00 2001 From: Jesper Dangaard Brouer Date: Tue, 18 Jun 2019 15:05:27 +0200 Subject: xdp: page_pool related fix to cpumap When converting an xdp_frame into an SKB, and sending this into the network stack, then the underlying XDP memory model need to release associated resources, because the network stack don't have callbacks for XDP memory models. The only memory model that needs this is page_pool, when a driver use the DMA-mapping feature. Introduce page_pool_release_page(), which basically does the same as page_pool_unmap_page(). Add xdp_release_frame() as the XDP memory model interface for calling it, if the memory model match MEM_TYPE_PAGE_POOL, to save the function call overhead for others. Have cpumap call xdp_release_frame() before xdp_scrub_frame(). Signed-off-by: Jesper Dangaard Brouer Signed-off-by: David S. Miller --- include/net/page_pool.h | 15 ++++++++++++++- include/net/xdp.h | 15 +++++++++++++++ 2 files changed, 29 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/net/page_pool.h b/include/net/page_pool.h index ad218cef88c5..e240fac4c5b9 100644 --- a/include/net/page_pool.h +++ b/include/net/page_pool.h @@ -110,7 +110,6 @@ static inline struct page *page_pool_dev_alloc_pages(struct page_pool *pool) struct page_pool *page_pool_create(const struct page_pool_params *params); void page_pool_destroy(struct page_pool *pool); -void page_pool_unmap_page(struct page_pool *pool, struct page *page); /* Never call this directly, use helpers below */ void __page_pool_put_page(struct page_pool *pool, @@ -133,6 +132,20 @@ static inline void page_pool_recycle_direct(struct page_pool *pool, __page_pool_put_page(pool, page, true); } +/* Disconnects a page (from a page_pool). API users can have a need + * to disconnect a page (from a page_pool), to allow it to be used as + * a regular page (that will eventually be returned to the normal + * page-allocator via put_page). + */ +void page_pool_unmap_page(struct page_pool *pool, struct page *page); +static inline void page_pool_release_page(struct page_pool *pool, + struct page *page) +{ +#ifdef CONFIG_PAGE_POOL + page_pool_unmap_page(pool, page); +#endif +} + static inline dma_addr_t page_pool_get_dma_addr(struct page *page) { return page->dma_addr; diff --git a/include/net/xdp.h b/include/net/xdp.h index 8e0deddef35c..40c6d3398458 100644 --- a/include/net/xdp.h +++ b/include/net/xdp.h @@ -129,6 +129,21 @@ void xdp_return_frame(struct xdp_frame *xdpf); void xdp_return_frame_rx_napi(struct xdp_frame *xdpf); void xdp_return_buff(struct xdp_buff *xdp); +/* When sending xdp_frame into the network stack, then there is no + * return point callback, which is needed to release e.g. DMA-mapping + * resources with page_pool. Thus, have explicit function to release + * frame resources. + */ +void __xdp_release_frame(void *data, struct xdp_mem_info *mem); +static inline void xdp_release_frame(struct xdp_frame *xdpf) +{ + struct xdp_mem_info *mem = &xdpf->mem; + + /* Curr only page_pool needs this */ + if (mem->type == MEM_TYPE_PAGE_POOL) + __xdp_release_frame(xdpf->data, mem); +} + int xdp_rxq_info_reg(struct xdp_rxq_info *xdp_rxq, struct net_device *dev, u32 queue_index); void xdp_rxq_info_unreg(struct xdp_rxq_info *xdp_rxq); -- cgit v1.2.3 From e54cfd7e1745e52eb6c67ee9c77aefb8e4666a88 Mon Sep 17 00:00:00 2001 From: Jesper Dangaard Brouer Date: Tue, 18 Jun 2019 15:05:37 +0200 Subject: page_pool: introduce page_pool_free and use in mlx5 In case driver fails to register the page_pool with XDP return API (via xdp_rxq_info_reg_mem_model()), then the driver can free the page_pool resources more directly than calling page_pool_destroy(), which does a unnecessarily RCU free procedure. This patch is preparing for removing page_pool_destroy(), from driver invocation. Signed-off-by: Jesper Dangaard Brouer Reviewed-by: Tariq Toukan Signed-off-by: David S. Miller --- include/net/page_pool.h | 11 +++++++++++ 1 file changed, 11 insertions(+) (limited to 'include') diff --git a/include/net/page_pool.h b/include/net/page_pool.h index e240fac4c5b9..754d980700df 100644 --- a/include/net/page_pool.h +++ b/include/net/page_pool.h @@ -111,6 +111,17 @@ struct page_pool *page_pool_create(const struct page_pool_params *params); void page_pool_destroy(struct page_pool *pool); +void __page_pool_free(struct page_pool *pool); +static inline void page_pool_free(struct page_pool *pool) +{ + /* When page_pool isn't compiled-in, net/core/xdp.c doesn't + * allow registering MEM_TYPE_PAGE_POOL, but shield linker. + */ +#ifdef CONFIG_PAGE_POOL + __page_pool_free(pool); +#endif +} + /* Never call this directly, use helpers below */ void __page_pool_put_page(struct page_pool *pool, struct page *page, bool allow_direct); -- cgit v1.2.3 From 99c07c43c4ea0bc101331401a0fabfc51933c6a3 Mon Sep 17 00:00:00 2001 From: Jesper Dangaard Brouer Date: Tue, 18 Jun 2019 15:05:47 +0200 Subject: xdp: tracking page_pool resources and safe removal This patch is needed before we can allow drivers to use page_pool for DMA-mappings. Today with page_pool and XDP return API, it is possible to remove the page_pool object (from rhashtable), while there are still in-flight packet-pages. This is safely handled via RCU and failed lookups in __xdp_return() fallback to call put_page(), when page_pool object is gone. In-case page is still DMA mapped, this will result in page note getting correctly DMA unmapped. To solve this, the page_pool is extended with tracking in-flight pages. And XDP disconnect system queries page_pool and waits, via workqueue, for all in-flight pages to be returned. To avoid killing performance when tracking in-flight pages, the implement use two (unsigned) counters, that in placed on different cache-lines, and can be used to deduct in-flight packets. This is done by mapping the unsigned "sequence" counters onto signed Two's complement arithmetic operations. This is e.g. used by kernel's time_after macros, described in kernel commit 1ba3aab3033b and 5a581b367b5, and also explained in RFC1982. The trick is these two incrementing counters only need to be read and compared, when checking if it's safe to free the page_pool structure. Which will only happen when driver have disconnected RX/alloc side. Thus, on a non-fast-path. It is chosen that page_pool tracking is also enabled for the non-DMA use-case, as this can be used for statistics later. After this patch, using page_pool requires more strict resource "release", e.g. via page_pool_release_page() that was introduced in this patchset, and previous patches implement/fix this more strict requirement. Drivers no-longer call page_pool_destroy(). Drivers already call xdp_rxq_info_unreg() which call xdp_rxq_info_unreg_mem_model(), which will attempt to disconnect the mem id, and if attempt fails schedule the disconnect for later via delayed workqueue. Signed-off-by: Jesper Dangaard Brouer Reviewed-by: Ilias Apalodimas Signed-off-by: David S. Miller --- include/net/page_pool.h | 41 +++++++++++++++++++++++++++++++---------- 1 file changed, 31 insertions(+), 10 deletions(-) (limited to 'include') diff --git a/include/net/page_pool.h b/include/net/page_pool.h index 754d980700df..f09b3f1994e6 100644 --- a/include/net/page_pool.h +++ b/include/net/page_pool.h @@ -16,14 +16,16 @@ * page_pool_alloc_pages() call. Drivers should likely use * page_pool_dev_alloc_pages() replacing dev_alloc_pages(). * - * If page_pool handles DMA mapping (use page->private), then API user - * is responsible for invoking page_pool_put_page() once. In-case of - * elevated refcnt, the DMA state is released, assuming other users of - * the page will eventually call put_page(). + * API keeps track of in-flight pages, in-order to let API user know + * when it is safe to dealloactor page_pool object. Thus, API users + * must make sure to call page_pool_release_page() when a page is + * "leaving" the page_pool. Or call page_pool_put_page() where + * appropiate. For maintaining correct accounting. * - * If no DMA mapping is done, then it can act as shim-layer that - * fall-through to alloc_page. As no state is kept on the page, the - * regular put_page() call is sufficient. + * API user must only call page_pool_put_page() once on a page, as it + * will either recycle the page, or in case of elevated refcnt, it + * will release the DMA mapping and in-flight state accounting. We + * hope to lift this requirement in the future. */ #ifndef _NET_PAGE_POOL_H #define _NET_PAGE_POOL_H @@ -66,9 +68,10 @@ struct page_pool_params { }; struct page_pool { - struct rcu_head rcu; struct page_pool_params p; + u32 pages_state_hold_cnt; + /* * Data structure for allocation side * @@ -96,6 +99,8 @@ struct page_pool { * TODO: Implement bulk return pages into this structure. */ struct ptr_ring ring; + + atomic_t pages_state_release_cnt; }; struct page *page_pool_alloc_pages(struct page_pool *pool, gfp_t gfp); @@ -109,8 +114,6 @@ static inline struct page *page_pool_dev_alloc_pages(struct page_pool *pool) struct page_pool *page_pool_create(const struct page_pool_params *params); -void page_pool_destroy(struct page_pool *pool); - void __page_pool_free(struct page_pool *pool); static inline void page_pool_free(struct page_pool *pool) { @@ -143,6 +146,24 @@ static inline void page_pool_recycle_direct(struct page_pool *pool, __page_pool_put_page(pool, page, true); } +/* API user MUST have disconnected alloc-side (not allowed to call + * page_pool_alloc_pages()) before calling this. The free-side can + * still run concurrently, to handle in-flight packet-pages. + * + * A request to shutdown can fail (with false) if there are still + * in-flight packet-pages. + */ +bool __page_pool_request_shutdown(struct page_pool *pool); +static inline bool page_pool_request_shutdown(struct page_pool *pool) +{ + /* When page_pool isn't compiled-in, net/core/xdp.c doesn't + * allow registering MEM_TYPE_PAGE_POOL, but shield linker. + */ +#ifdef CONFIG_PAGE_POOL + return __page_pool_request_shutdown(pool); +#endif +} + /* Disconnects a page (from a page_pool). API users can have a need * to disconnect a page (from a page_pool), to allow it to be used as * a regular page (that will eventually be returned to the normal -- cgit v1.2.3 From f033b688c1ede5ec78c9a718fa9f0b374049bc31 Mon Sep 17 00:00:00 2001 From: Jesper Dangaard Brouer Date: Tue, 18 Jun 2019 15:05:58 +0200 Subject: xdp: add tracepoints for XDP mem These tracepoints make it easier to troubleshoot XDP mem id disconnect. The xdp:mem_disconnect tracepoint cannot be replaced via kprobe. It is placed at the last stable place for the pointer to struct xdp_mem_allocator, just before it's scheduled for RCU removal. It also extract info on 'safe_to_remove' and 'force'. Detailed info about in-flight pages is not available at this layer. The next patch will added tracepoints needed at the page_pool layer for this. Signed-off-by: Jesper Dangaard Brouer Signed-off-by: David S. Miller --- include/net/xdp_priv.h | 23 +++++++++ include/trace/events/xdp.h | 115 +++++++++++++++++++++++++++++++++++++++++++++ 2 files changed, 138 insertions(+) create mode 100644 include/net/xdp_priv.h (limited to 'include') diff --git a/include/net/xdp_priv.h b/include/net/xdp_priv.h new file mode 100644 index 000000000000..6a8cba6ea79a --- /dev/null +++ b/include/net/xdp_priv.h @@ -0,0 +1,23 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef __LINUX_NET_XDP_PRIV_H__ +#define __LINUX_NET_XDP_PRIV_H__ + +#include + +/* Private to net/core/xdp.c, but used by trace/events/xdp.h */ +struct xdp_mem_allocator { + struct xdp_mem_info mem; + union { + void *allocator; + struct page_pool *page_pool; + struct zero_copy_allocator *zc_alloc; + }; + int disconnect_cnt; + unsigned long defer_start; + struct rhash_head node; + struct rcu_head rcu; + struct delayed_work defer_wq; + unsigned long defer_warn; +}; + +#endif /* __LINUX_NET_XDP_PRIV_H__ */ diff --git a/include/trace/events/xdp.h b/include/trace/events/xdp.h index e95cb86b65cf..bb5e380e2ef3 100644 --- a/include/trace/events/xdp.h +++ b/include/trace/events/xdp.h @@ -269,6 +269,121 @@ TRACE_EVENT(xdp_devmap_xmit, __entry->from_ifindex, __entry->to_ifindex, __entry->err) ); +/* Expect users already include , but not xdp_priv.h */ +#include + +#define __MEM_TYPE_MAP(FN) \ + FN(PAGE_SHARED) \ + FN(PAGE_ORDER0) \ + FN(PAGE_POOL) \ + FN(ZERO_COPY) + +#define __MEM_TYPE_TP_FN(x) \ + TRACE_DEFINE_ENUM(MEM_TYPE_##x); +#define __MEM_TYPE_SYM_FN(x) \ + { MEM_TYPE_##x, #x }, +#define __MEM_TYPE_SYM_TAB \ + __MEM_TYPE_MAP(__MEM_TYPE_SYM_FN) { -1, 0 } +__MEM_TYPE_MAP(__MEM_TYPE_TP_FN) + +TRACE_EVENT(mem_disconnect, + + TP_PROTO(const struct xdp_mem_allocator *xa, + bool safe_to_remove, bool force), + + TP_ARGS(xa, safe_to_remove, force), + + TP_STRUCT__entry( + __field(const struct xdp_mem_allocator *, xa) + __field(u32, mem_id) + __field(u32, mem_type) + __field(const void *, allocator) + __field(bool, safe_to_remove) + __field(bool, force) + __field(int, disconnect_cnt) + ), + + TP_fast_assign( + __entry->xa = xa; + __entry->mem_id = xa->mem.id; + __entry->mem_type = xa->mem.type; + __entry->allocator = xa->allocator; + __entry->safe_to_remove = safe_to_remove; + __entry->force = force; + __entry->disconnect_cnt = xa->disconnect_cnt; + ), + + TP_printk("mem_id=%d mem_type=%s allocator=%p" + " safe_to_remove=%s force=%s disconnect_cnt=%d", + __entry->mem_id, + __print_symbolic(__entry->mem_type, __MEM_TYPE_SYM_TAB), + __entry->allocator, + __entry->safe_to_remove ? "true" : "false", + __entry->force ? "true" : "false", + __entry->disconnect_cnt + ) +); + +TRACE_EVENT(mem_connect, + + TP_PROTO(const struct xdp_mem_allocator *xa, + const struct xdp_rxq_info *rxq), + + TP_ARGS(xa, rxq), + + TP_STRUCT__entry( + __field(const struct xdp_mem_allocator *, xa) + __field(u32, mem_id) + __field(u32, mem_type) + __field(const void *, allocator) + __field(const struct xdp_rxq_info *, rxq) + __field(int, ifindex) + ), + + TP_fast_assign( + __entry->xa = xa; + __entry->mem_id = xa->mem.id; + __entry->mem_type = xa->mem.type; + __entry->allocator = xa->allocator; + __entry->rxq = rxq; + __entry->ifindex = rxq->dev->ifindex; + ), + + TP_printk("mem_id=%d mem_type=%s allocator=%p" + " ifindex=%d", + __entry->mem_id, + __print_symbolic(__entry->mem_type, __MEM_TYPE_SYM_TAB), + __entry->allocator, + __entry->ifindex + ) +); + +TRACE_EVENT(mem_return_failed, + + TP_PROTO(const struct xdp_mem_info *mem, + const struct page *page), + + TP_ARGS(mem, page), + + TP_STRUCT__entry( + __field(const struct page *, page) + __field(u32, mem_id) + __field(u32, mem_type) + ), + + TP_fast_assign( + __entry->page = page; + __entry->mem_id = mem->id; + __entry->mem_type = mem->type; + ), + + TP_printk("mem_id=%d mem_type=%s page=%p", + __entry->mem_id, + __print_symbolic(__entry->mem_type, __MEM_TYPE_SYM_TAB), + __entry->page + ) +); + #endif /* _TRACE_XDP_H */ #include -- cgit v1.2.3 From 32c28f7e413981c7dd4a3ad9bbb1151e4b654261 Mon Sep 17 00:00:00 2001 From: Jesper Dangaard Brouer Date: Tue, 18 Jun 2019 15:06:03 +0200 Subject: page_pool: add tracepoints for page_pool with details need by XDP The xdp tracepoints for mem id disconnect don't carry information about, why it was not safe_to_remove. The tracepoint page_pool:page_pool_inflight in this patch can be used for extract this info for further debugging. This patchset also adds tracepoint for the pages_state_* release/hold transitions, including a pointer to the page. This can be used for stats about in-flight pages, or used to debug page leakage via keeping track of page pointer and combining this with kprobe for __put_page(). Signed-off-by: Jesper Dangaard Brouer Signed-off-by: David S. Miller --- include/trace/events/page_pool.h | 87 ++++++++++++++++++++++++++++++++++++++++ 1 file changed, 87 insertions(+) create mode 100644 include/trace/events/page_pool.h (limited to 'include') diff --git a/include/trace/events/page_pool.h b/include/trace/events/page_pool.h new file mode 100644 index 000000000000..47b5ee880aa9 --- /dev/null +++ b/include/trace/events/page_pool.h @@ -0,0 +1,87 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#undef TRACE_SYSTEM +#define TRACE_SYSTEM page_pool + +#if !defined(_TRACE_PAGE_POOL_H) || defined(TRACE_HEADER_MULTI_READ) +#define _TRACE_PAGE_POOL_H + +#include +#include + +#include + +TRACE_EVENT(page_pool_inflight, + + TP_PROTO(const struct page_pool *pool, + s32 inflight, u32 hold, u32 release), + + TP_ARGS(pool, inflight, hold, release), + + TP_STRUCT__entry( + __field(const struct page_pool *, pool) + __field(s32, inflight) + __field(u32, hold) + __field(u32, release) + ), + + TP_fast_assign( + __entry->pool = pool; + __entry->inflight = inflight; + __entry->hold = hold; + __entry->release = release; + ), + + TP_printk("page_pool=%p inflight=%d hold=%u release=%u", + __entry->pool, __entry->inflight, __entry->hold, __entry->release) +); + +TRACE_EVENT(page_pool_state_release, + + TP_PROTO(const struct page_pool *pool, + const struct page *page, u32 release), + + TP_ARGS(pool, page, release), + + TP_STRUCT__entry( + __field(const struct page_pool *, pool) + __field(const struct page *, page) + __field(u32, release) + ), + + TP_fast_assign( + __entry->pool = pool; + __entry->page = page; + __entry->release = release; + ), + + TP_printk("page_pool=%p page=%p release=%u", + __entry->pool, __entry->page, __entry->release) +); + +TRACE_EVENT(page_pool_state_hold, + + TP_PROTO(const struct page_pool *pool, + const struct page *page, u32 hold), + + TP_ARGS(pool, page, hold), + + TP_STRUCT__entry( + __field(const struct page_pool *, pool) + __field(const struct page *, page) + __field(u32, hold) + ), + + TP_fast_assign( + __entry->pool = pool; + __entry->page = page; + __entry->hold = hold; + ), + + TP_printk("page_pool=%p page=%p hold=%u", + __entry->pool, __entry->page, __entry->hold) +); + +#endif /* _TRACE_PAGE_POOL_H */ + +/* This part must be outside protection */ +#include -- cgit v1.2.3 From d7d99872c144a2c2f5d9c9d83627fa833836cba5 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Tue, 18 Jun 2019 11:08:59 -0700 Subject: netns: add pre_exit method to struct pernet_operations Current struct pernet_operations exit() handlers are highly discouraged to call synchronize_rcu(). There are cases where we need them, and exit_batch() does not help the common case where a single netns is dismantled. This patch leverages the existing synchronize_rcu() call in cleanup_net() Calling optional ->pre_exit() method before ->exit() or ->exit_batch() allows to benefit from a single synchronize_rcu() call. Note that the synchronize_rcu() calls added in this patch are only in error paths or slow paths. Tested: $ time for i in {1..1000}; do unshare -n /bin/false;done real 0m2.612s user 0m0.171s sys 0m2.216s Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- include/net/net_namespace.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include') diff --git a/include/net/net_namespace.h b/include/net/net_namespace.h index abb4f92456e1..ad9243afac67 100644 --- a/include/net/net_namespace.h +++ b/include/net/net_namespace.h @@ -355,8 +355,13 @@ struct pernet_operations { * synchronize_rcu() related to these pernet_operations, * instead of separate synchronize_rcu() for every net. * Please, avoid synchronize_rcu() at all, where it's possible. + * + * Note that a combination of pre_exit() and exit() can + * be used, since a synchronize_rcu() is guaranteed between + * the calls. */ int (*init)(struct net *net); + void (*pre_exit)(struct net *net); void (*exit)(struct net *net); void (*exit_batch)(struct list_head *net_exit_list); unsigned int *id; -- cgit v1.2.3 From d5dd88794a13c2f24cce31abad7a0a6c5e0ed2db Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Tue, 18 Jun 2019 11:09:00 -0700 Subject: inet: fix various use-after-free in defrags units syzbot reported another issue caused by my recent patches. [1] The issue here is that fqdir_exit() is initiating a work queue and immediately returns. A bit later cleanup_net() was able to free the MIB (percpu data) and the whole struct net was freed, but we had active frag timers that fired and triggered use-after-free. We need to make sure that timers can catch fqdir->dead being set, to bailout. Since RCU is used for the reader side, this means we want to respect an RCU grace period between these operations : 1) qfdir->dead = 1; 2) netns dismantle (freeing of various data structure) This patch uses new new (struct pernet_operations)->pre_exit infrastructure to ensures a full RCU grace period happens between fqdir_pre_exit() and fqdir_exit() This also means we can use a regular work queue, we no longer need rcu_work. Tested: $ time for i in {1..1000}; do unshare -n /bin/false;done real 0m2.585s user 0m0.160s sys 0m2.214s [1] BUG: KASAN: use-after-free in ip_expire+0x73e/0x800 net/ipv4/ip_fragment.c:152 Read of size 8 at addr ffff88808b9fe330 by task syz-executor.4/11860 CPU: 1 PID: 11860 Comm: syz-executor.4 Not tainted 5.2.0-rc2+ #22 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011 Call Trace: __dump_stack lib/dump_stack.c:77 [inline] dump_stack+0x172/0x1f0 lib/dump_stack.c:113 print_address_description.cold+0x7c/0x20d mm/kasan/report.c:188 __kasan_report.cold+0x1b/0x40 mm/kasan/report.c:317 kasan_report+0x12/0x20 mm/kasan/common.c:614 __asan_report_load8_noabort+0x14/0x20 mm/kasan/generic_report.c:132 ip_expire+0x73e/0x800 net/ipv4/ip_fragment.c:152 call_timer_fn+0x193/0x720 kernel/time/timer.c:1322 expire_timers kernel/time/timer.c:1366 [inline] __run_timers kernel/time/timer.c:1685 [inline] __run_timers kernel/time/timer.c:1653 [inline] run_timer_softirq+0x66f/0x1740 kernel/time/timer.c:1698 __do_softirq+0x25c/0x94c kernel/softirq.c:293 invoke_softirq kernel/softirq.c:374 [inline] irq_exit+0x180/0x1d0 kernel/softirq.c:414 exiting_irq arch/x86/include/asm/apic.h:536 [inline] smp_apic_timer_interrupt+0x13b/0x550 arch/x86/kernel/apic/apic.c:1068 apic_timer_interrupt+0xf/0x20 arch/x86/entry/entry_64.S:806 RIP: 0010:tomoyo_domain_quota_is_ok+0x131/0x540 security/tomoyo/util.c:1035 Code: 24 4c 3b 65 d0 0f 84 9c 00 00 00 e8 19 1d 73 fe 49 8d 7c 24 18 48 ba 00 00 00 00 00 fc ff df 48 89 f8 48 c1 e8 03 0f b6 04 10 <48> 89 fa 83 e2 07 38 d0 7f 08 84 c0 0f 85 69 03 00 00 41 0f b6 5c RSP: 0018:ffff88806ae079c0 EFLAGS: 00000a02 ORIG_RAX: ffffffffffffff13 RAX: 0000000000000000 RBX: 0000000000000010 RCX: ffffc9000e655000 RDX: dffffc0000000000 RSI: ffffffff82fd88a7 RDI: ffff888086202398 RBP: ffff88806ae07a00 R08: ffff88808b6c8700 R09: ffffed100d5c0f4d R10: ffffed100d5c0f4c R11: 0000000000000000 R12: ffff888086202380 R13: 0000000000000030 R14: 00000000000000d3 R15: 0000000000000000 tomoyo_supervisor+0x2e8/0xef0 security/tomoyo/common.c:2087 tomoyo_audit_path_number_log security/tomoyo/file.c:235 [inline] tomoyo_path_number_perm+0x42f/0x520 security/tomoyo/file.c:734 tomoyo_file_ioctl+0x23/0x30 security/tomoyo/tomoyo.c:335 security_file_ioctl+0x77/0xc0 security/security.c:1370 ksys_ioctl+0x57/0xd0 fs/ioctl.c:711 __do_sys_ioctl fs/ioctl.c:720 [inline] __se_sys_ioctl fs/ioctl.c:718 [inline] __x64_sys_ioctl+0x73/0xb0 fs/ioctl.c:718 do_syscall_64+0xfd/0x680 arch/x86/entry/common.c:301 entry_SYSCALL_64_after_hwframe+0x49/0xbe RIP: 0033:0x4592c9 Code: fd b7 fb ff c3 66 2e 0f 1f 84 00 00 00 00 00 66 90 48 89 f8 48 89 f7 48 89 d6 48 89 ca 4d 89 c2 4d 89 c8 4c 8b 4c 24 08 0f 05 <48> 3d 01 f0 ff ff 0f 83 cb b7 fb ff c3 66 2e 0f 1f 84 00 00 00 00 RSP: 002b:00007f8db5e44c78 EFLAGS: 00000246 ORIG_RAX: 0000000000000010 RAX: ffffffffffffffda RBX: 0000000000000003 RCX: 00000000004592c9 RDX: 0000000020000080 RSI: 00000000000089f1 RDI: 0000000000000006 RBP: 000000000075bf20 R08: 0000000000000000 R09: 0000000000000000 R10: 0000000000000000 R11: 0000000000000246 R12: 00007f8db5e456d4 R13: 00000000004cc770 R14: 00000000004d5cd8 R15: 00000000ffffffff Allocated by task 9047: save_stack+0x23/0x90 mm/kasan/common.c:71 set_track mm/kasan/common.c:79 [inline] __kasan_kmalloc mm/kasan/common.c:489 [inline] __kasan_kmalloc.constprop.0+0xcf/0xe0 mm/kasan/common.c:462 kasan_slab_alloc+0xf/0x20 mm/kasan/common.c:497 slab_post_alloc_hook mm/slab.h:437 [inline] slab_alloc mm/slab.c:3326 [inline] kmem_cache_alloc+0x11a/0x6f0 mm/slab.c:3488 kmem_cache_zalloc include/linux/slab.h:732 [inline] net_alloc net/core/net_namespace.c:386 [inline] copy_net_ns+0xed/0x340 net/core/net_namespace.c:426 create_new_namespaces+0x400/0x7b0 kernel/nsproxy.c:107 unshare_nsproxy_namespaces+0xc2/0x200 kernel/nsproxy.c:206 ksys_unshare+0x440/0x980 kernel/fork.c:2692 __do_sys_unshare kernel/fork.c:2760 [inline] __se_sys_unshare kernel/fork.c:2758 [inline] __x64_sys_unshare+0x31/0x40 kernel/fork.c:2758 do_syscall_64+0xfd/0x680 arch/x86/entry/common.c:301 entry_SYSCALL_64_after_hwframe+0x49/0xbe Freed by task 2541: save_stack+0x23/0x90 mm/kasan/common.c:71 set_track mm/kasan/common.c:79 [inline] __kasan_slab_free+0x102/0x150 mm/kasan/common.c:451 kasan_slab_free+0xe/0x10 mm/kasan/common.c:459 __cache_free mm/slab.c:3432 [inline] kmem_cache_free+0x86/0x260 mm/slab.c:3698 net_free net/core/net_namespace.c:402 [inline] net_drop_ns.part.0+0x70/0x90 net/core/net_namespace.c:409 net_drop_ns net/core/net_namespace.c:408 [inline] cleanup_net+0x538/0x960 net/core/net_namespace.c:571 process_one_work+0x989/0x1790 kernel/workqueue.c:2269 worker_thread+0x98/0xe40 kernel/workqueue.c:2415 kthread+0x354/0x420 kernel/kthread.c:255 ret_from_fork+0x24/0x30 arch/x86/entry/entry_64.S:352 The buggy address belongs to the object at ffff88808b9fe100 which belongs to the cache net_namespace of size 6784 The buggy address is located 560 bytes inside of 6784-byte region [ffff88808b9fe100, ffff88808b9ffb80) The buggy address belongs to the page: page:ffffea00022e7f80 refcount:1 mapcount:0 mapping:ffff88821b6f60c0 index:0x0 compound_mapcount: 0 flags: 0x1fffc0000010200(slab|head) raw: 01fffc0000010200 ffffea000256f288 ffffea0001bbef08 ffff88821b6f60c0 raw: 0000000000000000 ffff88808b9fe100 0000000100000001 0000000000000000 page dumped because: kasan: bad access detected Memory state around the buggy address: ffff88808b9fe200: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb ffff88808b9fe280: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb >ffff88808b9fe300: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb ^ ffff88808b9fe380: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb ffff88808b9fe400: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb Fixes: 3c8fc8782044 ("inet: frags: rework rhashtable dismantle") Signed-off-by: Eric Dumazet Reported-by: syzbot Signed-off-by: David S. Miller --- include/net/inet_frag.h | 8 +++++++- include/net/ipv6_frag.h | 2 ++ 2 files changed, 9 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/net/inet_frag.h b/include/net/inet_frag.h index e91b79ad4e4a..46574d996f1d 100644 --- a/include/net/inet_frag.h +++ b/include/net/inet_frag.h @@ -20,7 +20,7 @@ struct fqdir { /* Keep atomic mem on separate cachelines in structs that include it */ atomic_long_t mem ____cacheline_aligned_in_smp; - struct rcu_work destroy_rwork; + struct work_struct destroy_work; }; /** @@ -113,6 +113,12 @@ int inet_frags_init(struct inet_frags *); void inet_frags_fini(struct inet_frags *); int fqdir_init(struct fqdir **fqdirp, struct inet_frags *f, struct net *net); + +static void inline fqdir_pre_exit(struct fqdir *fqdir) +{ + fqdir->high_thresh = 0; /* prevent creation of new frags */ + fqdir->dead = true; +} void fqdir_exit(struct fqdir *fqdir); void inet_frag_kill(struct inet_frag_queue *q); diff --git a/include/net/ipv6_frag.h b/include/net/ipv6_frag.h index 1f77fb4dc79d..a21e8b1381a1 100644 --- a/include/net/ipv6_frag.h +++ b/include/net/ipv6_frag.h @@ -67,6 +67,8 @@ ip6frag_expire_frag_queue(struct net *net, struct frag_queue *fq) struct sk_buff *head; rcu_read_lock(); + if (fq->q.fqdir->dead) + goto out_rcu_unlock; spin_lock(&fq->q.lock); if (fq->q.flags & INET_FRAG_COMPLETE) -- cgit v1.2.3 From 79ebb5bb4e38a58ca796dd242b855a4982e101d7 Mon Sep 17 00:00:00 2001 From: Laura Garcia Liebana Date: Tue, 18 Jun 2019 11:11:02 +0200 Subject: netfilter: nf_tables: enable set expiration time for set elements Currently, the expiration of every element in a set or map is a read-only parameter generated at kernel side. This change will permit to set a certain expiration date per element that will be required, for example, during stateful replication among several nodes. This patch handles the NFTA_SET_ELEM_EXPIRATION in order to configure the expiration parameter per element, or will use the timeout in the case that the expiration is not set. Signed-off-by: Laura Garcia Liebana Signed-off-by: Pablo Neira Ayuso --- include/net/netfilter/nf_tables.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/net/netfilter/nf_tables.h b/include/net/netfilter/nf_tables.h index 5b8624ae4a27..9e8493aad49d 100644 --- a/include/net/netfilter/nf_tables.h +++ b/include/net/netfilter/nf_tables.h @@ -636,7 +636,7 @@ static inline struct nft_object **nft_set_ext_obj(const struct nft_set_ext *ext) void *nft_set_elem_init(const struct nft_set *set, const struct nft_set_ext_tmpl *tmpl, const u32 *key, const u32 *data, - u64 timeout, gfp_t gfp); + u64 timeout, u64 expiration, gfp_t gfp); void nft_set_elem_destroy(const struct nft_set *set, void *elem, bool destroy_expr); -- cgit v1.2.3 From 16e5a266f51639492ac30761d043525d7d43f4c8 Mon Sep 17 00:00:00 2001 From: Kevin Darbyshire-Bryant Date: Wed, 19 Jun 2019 18:41:10 +0100 Subject: net: sched: act_ctinfo: tidy UAPI definition Remove some enums from the UAPI definition that were only used internally and are NOT part of the UAPI. Signed-off-by: Kevin Darbyshire-Bryant Signed-off-by: David S. Miller --- include/net/tc_act/tc_ctinfo.h | 5 +++++ include/uapi/linux/tc_act/tc_ctinfo.h | 5 ----- 2 files changed, 5 insertions(+), 5 deletions(-) (limited to 'include') diff --git a/include/net/tc_act/tc_ctinfo.h b/include/net/tc_act/tc_ctinfo.h index d6a688571672..f071c1d70a25 100644 --- a/include/net/tc_act/tc_ctinfo.h +++ b/include/net/tc_act/tc_ctinfo.h @@ -23,6 +23,11 @@ struct tcf_ctinfo { u64 stats_cpmark_set; }; +enum { + CTINFO_MODE_DSCP = BIT(0), + CTINFO_MODE_CPMARK = BIT(1) +}; + #define to_ctinfo(a) ((struct tcf_ctinfo *)a) #endif /* __NET_TC_CTINFO_H */ diff --git a/include/uapi/linux/tc_act/tc_ctinfo.h b/include/uapi/linux/tc_act/tc_ctinfo.h index 32337304fbe5..f5f26d95d0e7 100644 --- a/include/uapi/linux/tc_act/tc_ctinfo.h +++ b/include/uapi/linux/tc_act/tc_ctinfo.h @@ -26,9 +26,4 @@ enum { #define TCA_CTINFO_MAX (__TCA_CTINFO_MAX - 1) -enum { - CTINFO_MODE_DSCP = _BITUL(0), - CTINFO_MODE_CPMARK = _BITUL(1) -}; - #endif -- cgit v1.2.3 From 497ad9f5b2dc86b733761b9afa44ecfa2f17be65 Mon Sep 17 00:00:00 2001 From: Jesper Dangaard Brouer Date: Thu, 20 Jun 2019 00:15:52 +0200 Subject: page_pool: fix compile warning when CONFIG_PAGE_POOL is disabled Kbuild test robot reported compile warning: warning: no return statement in function returning non-void in function page_pool_request_shutdown, when CONFIG_PAGE_POOL is disabled. The fix makes the code a little more verbose, with a descriptive variable. Fixes: 99c07c43c4ea ("xdp: tracking page_pool resources and safe removal") Signed-off-by: Jesper Dangaard Brouer Reported-by: kbuild test robot Signed-off-by: David S. Miller --- include/net/page_pool.h | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) (limited to 'include') diff --git a/include/net/page_pool.h b/include/net/page_pool.h index f09b3f1994e6..f07c518ef8a5 100644 --- a/include/net/page_pool.h +++ b/include/net/page_pool.h @@ -156,12 +156,12 @@ static inline void page_pool_recycle_direct(struct page_pool *pool, bool __page_pool_request_shutdown(struct page_pool *pool); static inline bool page_pool_request_shutdown(struct page_pool *pool) { - /* When page_pool isn't compiled-in, net/core/xdp.c doesn't - * allow registering MEM_TYPE_PAGE_POOL, but shield linker. - */ + bool safe_to_remove = false; + #ifdef CONFIG_PAGE_POOL - return __page_pool_request_shutdown(pool); + safe_to_remove = __page_pool_request_shutdown(pool); #endif + return safe_to_remove; } /* Disconnects a page (from a page_pool). API users can have a need -- cgit v1.2.3 From 8527fa6cc68a489f735823e61b31ec6cb266274a Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Wed, 19 Jun 2019 14:54:36 +0200 Subject: netfilter: synproxy: fix building syncookie calls When either CONFIG_IPV6 or CONFIG_SYN_COOKIES are disabled, the kernel fails to build: include/linux/netfilter_ipv6.h:180:9: error: implicit declaration of function '__cookie_v6_init_sequence' [-Werror,-Wimplicit-function-declaration] return __cookie_v6_init_sequence(iph, th, mssp); include/linux/netfilter_ipv6.h:194:9: error: implicit declaration of function '__cookie_v6_check' [-Werror,-Wimplicit-function-declaration] return __cookie_v6_check(iph, th, cookie); net/ipv6/netfilter.c:237:26: error: use of undeclared identifier '__cookie_v6_init_sequence'; did you mean 'cookie_init_sequence'? net/ipv6/netfilter.c:238:21: error: use of undeclared identifier '__cookie_v6_check'; did you mean '__cookie_v4_check'? Fix the IS_ENABLED() checks to match the function declaration and definitions for these. Fixes: 3006a5224f15 ("netfilter: synproxy: remove module dependency on IPv6 SYNPROXY") Signed-off-by: Arnd Bergmann Signed-off-by: Pablo Neira Ayuso --- include/linux/netfilter_ipv6.h | 14 ++++++++------ 1 file changed, 8 insertions(+), 6 deletions(-) (limited to 'include') diff --git a/include/linux/netfilter_ipv6.h b/include/linux/netfilter_ipv6.h index 35b12525ee45..22e6398bc482 100644 --- a/include/linux/netfilter_ipv6.h +++ b/include/linux/netfilter_ipv6.h @@ -163,31 +163,33 @@ static inline u32 nf_ipv6_cookie_init_sequence(const struct ipv6hdr *iph, const struct tcphdr *th, u16 *mssp) { +#if IS_ENABLED(CONFIG_SYN_COOKIES) #if IS_MODULE(CONFIG_IPV6) const struct nf_ipv6_ops *v6_ops = nf_get_ipv6_ops(); if (v6_ops) return v6_ops->cookie_init_sequence(iph, th, mssp); - - return 0; -#else +#elif IS_BUILTIN(CONFIG_IPV6) return __cookie_v6_init_sequence(iph, th, mssp); #endif +#endif + return 0; } static inline int nf_cookie_v6_check(const struct ipv6hdr *iph, const struct tcphdr *th, __u32 cookie) { +#if IS_ENABLED(CONFIG_SYN_COOKIES) #if IS_MODULE(CONFIG_IPV6) const struct nf_ipv6_ops *v6_ops = nf_get_ipv6_ops(); if (v6_ops) return v6_ops->cookie_v6_check(iph, th, cookie); - - return 0; -#else +#elif IS_BUILTIN(CONFIG_IPV6) return __cookie_v6_check(iph, th, cookie); #endif +#endif + return 0; } __sum16 nf_ip6_checksum(struct sk_buff *skb, unsigned int hook, -- cgit v1.2.3 From 43a38c3f318082839d7e613352d4dae7bbdfcdec Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Mon, 17 Jun 2019 15:15:04 +0200 Subject: netfilter: fix nf_conntrack_bridge/ipv6 link error When CONFIG_IPV6 is disabled, the bridge netfilter code produces a link error: ERROR: "br_ip6_fragment" [net/bridge/netfilter/nf_conntrack_bridge.ko] undefined! ERROR: "nf_ct_frag6_gather" [net/bridge/netfilter/nf_conntrack_bridge.ko] undefined! The problem is that it assumes that whenever IPV6 is not a loadable module, we can call the functions direction. This is clearly not true when IPV6 is disabled. There are two other functions defined like this in linux/netfilter_ipv6.h, so change them all the same way. Fixes: 764dd163ac92 ("netfilter: nf_conntrack_bridge: add support for IPv6") Signed-off-by: Arnd Bergmann Signed-off-by: Pablo Neira Ayuso --- include/linux/netfilter_ipv6.h | 16 ++++++++++++---- 1 file changed, 12 insertions(+), 4 deletions(-) (limited to 'include') diff --git a/include/linux/netfilter_ipv6.h b/include/linux/netfilter_ipv6.h index 22e6398bc482..7beb681e1ce5 100644 --- a/include/linux/netfilter_ipv6.h +++ b/include/linux/netfilter_ipv6.h @@ -75,8 +75,10 @@ static inline int nf_ipv6_chk_addr(struct net *net, const struct in6_addr *addr, return 1; return v6_ops->chk_addr(net, addr, dev, strict); -#else +#elif IS_BUILTIN(CONFIG_IPV6) return ipv6_chk_addr(net, addr, dev, strict); +#else + return 1; #endif } @@ -113,8 +115,10 @@ static inline int nf_ipv6_br_defrag(struct net *net, struct sk_buff *skb, return 1; return v6_ops->br_defrag(net, skb, user); -#else +#elif IS_BUILTIN(CONFIG_IPV6) return nf_ct_frag6_gather(net, skb, user); +#else + return 1; #endif } @@ -138,8 +142,10 @@ static inline int nf_br_ip6_fragment(struct net *net, struct sock *sk, return 1; return v6_ops->br_fragment(net, sk, skb, data, output); -#else +#elif IS_BUILTIN(CONFIG_IPV6) return br_ip6_fragment(net, sk, skb, data, output); +#else + return 1; #endif } @@ -154,8 +160,10 @@ static inline int nf_ip6_route_me_harder(struct net *net, struct sk_buff *skb) return -EHOSTUNREACH; return v6_ops->route_me_harder(net, skb); -#else +#elif IS_BUILTIN(CONFIG_IPV6) return ip6_route_me_harder(net, skb); +#else + return -EHOSTUNREACH; #endif } -- cgit v1.2.3 From dbb5281a1f84b2f93032d4864c211ce8a20811a7 Mon Sep 17 00:00:00 2001 From: Stephen Suryaputra Date: Thu, 20 Jun 2019 12:19:59 -0400 Subject: netfilter: nf_tables: add support for matching IPv4 options This is the kernel change for the overall changes with this description: Add capability to have rules matching IPv4 options. This is developed mainly to support dropping of IP packets with loose and/or strict source route route options. Signed-off-by: Stephen Suryaputra Signed-off-by: Pablo Neira Ayuso --- include/uapi/linux/netfilter/nf_tables.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/uapi/linux/netfilter/nf_tables.h b/include/uapi/linux/netfilter/nf_tables.h index 31a6b8f7ff73..c6c8ec5c7c00 100644 --- a/include/uapi/linux/netfilter/nf_tables.h +++ b/include/uapi/linux/netfilter/nf_tables.h @@ -730,10 +730,12 @@ enum nft_exthdr_flags { * * @NFT_EXTHDR_OP_IPV6: match against ipv6 extension headers * @NFT_EXTHDR_OP_TCP: match against tcp options + * @NFT_EXTHDR_OP_IPV4: match against ipv4 options */ enum nft_exthdr_op { NFT_EXTHDR_OP_IPV6, NFT_EXTHDR_OP_TCPOPT, + NFT_EXTHDR_OP_IPV4, __NFT_EXTHDR_OP_MAX }; #define NFT_EXTHDR_OP_MAX (__NFT_EXTHDR_OP_MAX - 1) -- cgit v1.2.3 From 4cfd218855923a07dc02a5bec3d3bb37a118ebc2 Mon Sep 17 00:00:00 2001 From: Heiner Kallweit Date: Tue, 18 Jun 2019 23:13:48 +0200 Subject: PCI: let pci_disable_link_state propagate errors Drivers may rely on pci_disable_link_state() having disabled certain ASPM link states. If OS can't control ASPM then pci_disable_link_state() turns into a no-op w/o informing the caller. The driver therefore may falsely assume the respective ASPM link states are disabled. Let pci_disable_link_state() propagate errors to the caller, enabling the caller to react accordingly. Signed-off-by: Heiner Kallweit Acked-by: Bjorn Helgaas Signed-off-by: David S. Miller --- include/linux/pci-aspm.h | 7 ++++--- 1 file changed, 4 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/include/linux/pci-aspm.h b/include/linux/pci-aspm.h index df28af5cef21..67064145d76e 100644 --- a/include/linux/pci-aspm.h +++ b/include/linux/pci-aspm.h @@ -24,11 +24,12 @@ #define PCIE_LINK_STATE_CLKPM 4 #ifdef CONFIG_PCIEASPM -void pci_disable_link_state(struct pci_dev *pdev, int state); -void pci_disable_link_state_locked(struct pci_dev *pdev, int state); +int pci_disable_link_state(struct pci_dev *pdev, int state); +int pci_disable_link_state_locked(struct pci_dev *pdev, int state); void pcie_no_aspm(void); #else -static inline void pci_disable_link_state(struct pci_dev *pdev, int state) { } +static inline int pci_disable_link_state(struct pci_dev *pdev, int state) +{ return 0; } static inline void pcie_no_aspm(void) { } #endif -- cgit v1.2.3 From 438ac88009bcb10f9ced07fbb4b32d5377ee936b Mon Sep 17 00:00:00 2001 From: Ard Biesheuvel Date: Wed, 19 Jun 2019 23:46:28 +0200 Subject: net: fastopen: robustness and endianness fixes for SipHash Some changes to the TCP fastopen code to make it more robust against future changes in the choice of key/cookie size, etc. - Instead of keeping the SipHash key in an untyped u8[] buffer and casting it to the right type upon use, use the correct type directly. This ensures that the key will appear at the correct alignment if we ever change the way these data structures are allocated. (Currently, they are only allocated via kmalloc so they always appear at the correct alignment) - Use DIV_ROUND_UP when sizing the u64[] array to hold the cookie, so it is always of sufficient size, even if TCP_FASTOPEN_COOKIE_MAX is no longer a multiple of 8. - Drop the 'len' parameter from the tcp_fastopen_reset_cipher() function, which is no longer used. - Add endian swabbing when setting the keys and calculating the hash, to ensure that cookie values are the same for a given key and source/destination address pair regardless of the endianness of the server. Note that none of these are functional changes wrt the current state of the code, with the exception of the swabbing, which only affects big endian systems. Signed-off-by: Ard Biesheuvel Signed-off-by: David S. Miller --- include/linux/tcp.h | 2 +- include/net/tcp.h | 8 ++++---- 2 files changed, 5 insertions(+), 5 deletions(-) (limited to 'include') diff --git a/include/linux/tcp.h b/include/linux/tcp.h index 2689b0b0b68a..f3a85a7fb4b1 100644 --- a/include/linux/tcp.h +++ b/include/linux/tcp.h @@ -58,7 +58,7 @@ static inline unsigned int tcp_optlen(const struct sk_buff *skb) /* TCP Fast Open Cookie as stored in memory */ struct tcp_fastopen_cookie { - u64 val[TCP_FASTOPEN_COOKIE_MAX / sizeof(u64)]; + __le64 val[DIV_ROUND_UP(TCP_FASTOPEN_COOKIE_MAX, sizeof(u64))]; s8 len; bool exp; /* In RFC6994 experimental option format */ }; diff --git a/include/net/tcp.h b/include/net/tcp.h index 573c9e9b0d72..9d36cc88d043 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -43,6 +43,7 @@ #include #include #include +#include extern struct inet_hashinfo tcp_hashinfo; @@ -1612,8 +1613,7 @@ void tcp_free_fastopen_req(struct tcp_sock *tp); void tcp_fastopen_destroy_cipher(struct sock *sk); void tcp_fastopen_ctx_destroy(struct net *net); int tcp_fastopen_reset_cipher(struct net *net, struct sock *sk, - void *primary_key, void *backup_key, - unsigned int len); + void *primary_key, void *backup_key); void tcp_fastopen_add_skb(struct sock *sk, struct sk_buff *skb); struct sock *tcp_try_fastopen(struct sock *sk, struct sk_buff *skb, struct request_sock *req, @@ -1623,14 +1623,14 @@ void tcp_fastopen_init_key_once(struct net *net); bool tcp_fastopen_cookie_check(struct sock *sk, u16 *mss, struct tcp_fastopen_cookie *cookie); bool tcp_fastopen_defer_connect(struct sock *sk, int *err); -#define TCP_FASTOPEN_KEY_LENGTH 16 +#define TCP_FASTOPEN_KEY_LENGTH sizeof(siphash_key_t) #define TCP_FASTOPEN_KEY_MAX 2 #define TCP_FASTOPEN_KEY_BUF_LENGTH \ (TCP_FASTOPEN_KEY_LENGTH * TCP_FASTOPEN_KEY_MAX) /* Fastopen key context */ struct tcp_fastopen_context { - __u8 key[TCP_FASTOPEN_KEY_MAX][TCP_FASTOPEN_KEY_LENGTH]; + siphash_key_t key[TCP_FASTOPEN_KEY_MAX]; int num; struct rcu_head rcu; }; -- cgit v1.2.3 From 08003d0b63a63bebaccca90e2f1d628dfd66cd4d Mon Sep 17 00:00:00 2001 From: Qian Cai Date: Thu, 20 Jun 2019 10:52:40 -0400 Subject: inet: fix compilation warnings in fqdir_pre_exit() The linux-next commit "inet: fix various use-after-free in defrags units" [1] introduced compilation warnings, ./include/net/inet_frag.h:117:1: warning: 'inline' is not at beginning of declaration [-Wold-style-declaration] static void inline fqdir_pre_exit(struct fqdir *fqdir) ^~~~~~ In file included from ./include/net/netns/ipv4.h:10, from ./include/net/net_namespace.h:20, from ./include/linux/netdevice.h:38, from ./include/linux/icmpv6.h:13, from ./include/linux/ipv6.h:86, from ./include/net/ipv6.h:12, from ./include/rdma/ib_verbs.h:51, from ./include/linux/mlx5/device.h:37, from ./include/linux/mlx5/driver.h:51, from drivers/net/ethernet/mellanox/mlx5/core/pagealloc.c:37: [1] https://lore.kernel.org/netdev/20190618180900.88939-3-edumazet@google.com/ Signed-off-by: Qian Cai Signed-off-by: David S. Miller --- include/net/inet_frag.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/net/inet_frag.h b/include/net/inet_frag.h index 46574d996f1d..010f26b31c89 100644 --- a/include/net/inet_frag.h +++ b/include/net/inet_frag.h @@ -114,7 +114,7 @@ void inet_frags_fini(struct inet_frags *); int fqdir_init(struct fqdir **fqdirp, struct inet_frags *f, struct net *net); -static void inline fqdir_pre_exit(struct fqdir *fqdir) +static inline void fqdir_pre_exit(struct fqdir *fqdir) { fqdir->high_thresh = 0; /* prevent creation of new frags */ fqdir->dead = true; -- cgit v1.2.3 From 0e09edcce7ad9c8120eb8462334e1c9e8f3be09a Mon Sep 17 00:00:00 2001 From: Wei Wang Date: Thu, 20 Jun 2019 17:36:37 -0700 Subject: ipv6: introduce RT6_LOOKUP_F_DST_NOREF flag in ip6_pol_route() This new flag is to instruct the route lookup function to not take refcnt on the dst entry. The user which does route lookup with this flag must properly use rcu protection. ip6_pol_route() is the major route lookup function for both tx and rx path. In this function: Do not take refcnt on dst if RT6_LOOKUP_F_DST_NOREF flag is set, and directly return the route entry. The caller should be holding rcu lock when using this flag, and decide whether to take refcnt or not. One note on the dst cache in the uncached_list: As uncached_list does not consume refcnt, one refcnt is always returned back to the caller even if RT6_LOOKUP_F_DST_NOREF flag is set. Uncached dst is only possible in the output path. So in such call path, caller MUST check if the dst is in the uncached_list before assuming that there is no refcnt taken on the returned dst. Signed-off-by: Wei Wang Acked-by: Eric Dumazet Acked-by: Mahesh Bandewar Signed-off-by: David S. Miller --- include/net/ip6_route.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/net/ip6_route.h b/include/net/ip6_route.h index 7375a165fd98..82bced2fc1e3 100644 --- a/include/net/ip6_route.h +++ b/include/net/ip6_route.h @@ -36,6 +36,7 @@ struct route_info { #define RT6_LOOKUP_F_SRCPREF_PUBLIC 0x00000010 #define RT6_LOOKUP_F_SRCPREF_COA 0x00000020 #define RT6_LOOKUP_F_IGNORE_LINKSTATE 0x00000040 +#define RT6_LOOKUP_F_DST_NOREF 0x00000080 /* We do not (yet ?) support IPv6 jumbograms (RFC 2675) * Unlike IPv4, hdr->seg_len doesn't include the IPv6 header -- cgit v1.2.3 From d64a1f574a2957b4bcb06452d36cc1c6bf16e9fc Mon Sep 17 00:00:00 2001 From: Wei Wang Date: Thu, 20 Jun 2019 17:36:39 -0700 Subject: ipv6: honor RT6_LOOKUP_F_DST_NOREF in rule lookup logic This patch specifically converts the rule lookup logic to honor this flag and not release refcnt when traversing each rule and calling lookup() on each routing table. Similar to previous patch, we also need some special handling of dst entries in uncached list because there is always 1 refcnt taken for them even if RT6_LOOKUP_F_DST_NOREF flag is set. Signed-off-by: Wei Wang Signed-off-by: David S. Miller --- include/net/ip6_route.h | 10 ++++++++++ 1 file changed, 10 insertions(+) (limited to 'include') diff --git a/include/net/ip6_route.h b/include/net/ip6_route.h index 82bced2fc1e3..0709835c01ad 100644 --- a/include/net/ip6_route.h +++ b/include/net/ip6_route.h @@ -94,6 +94,16 @@ static inline struct dst_entry *ip6_route_output(struct net *net, return ip6_route_output_flags(net, sk, fl6, 0); } +/* Only conditionally release dst if flags indicates + * !RT6_LOOKUP_F_DST_NOREF or dst is in uncached_list. + */ +static inline void ip6_rt_put_flags(struct rt6_info *rt, int flags) +{ + if (!(flags & RT6_LOOKUP_F_DST_NOREF) || + !list_empty(&rt->rt6i_uncached)) + ip6_rt_put(rt); +} + struct dst_entry *ip6_route_lookup(struct net *net, struct flowi6 *fl6, const struct sk_buff *skb, int flags); struct rt6_info *ip6_pol_route(struct net *net, struct fib6_table *table, -- cgit v1.2.3 From 7d9e5f422150ed00de744e02a80734d74cc9704d Mon Sep 17 00:00:00 2001 From: Wei Wang Date: Thu, 20 Jun 2019 17:36:41 -0700 Subject: ipv6: convert major tx path to use RT6_LOOKUP_F_DST_NOREF For tx path, in most cases, we still have to take refcnt on the dst cause the caller is caching the dst somewhere. But it still is beneficial to make use of RT6_LOOKUP_F_DST_NOREF flag while doing the route lookup. It is cause this flag prevents manipulating refcnt on net->ipv6.ip6_null_entry when doing fib6_rule_lookup() to traverse each routing table. The null_entry is a shared object and constant updates on it cause false sharing. We converted the current major lookup function ip6_route_output_flags() to make use of RT6_LOOKUP_F_DST_NOREF. Together with the change in the rx path, we see noticable performance boost: I ran synflood tests between 2 hosts under the same switch. Both hosts have 20G mlx NIC, and 8 tx/rx queues. Sender sends pure SYN flood with random src IPs and ports using trafgen. Receiver has a simple TCP listener on the target port. Both hosts have multiple custom rules: - For incoming packets, only local table is traversed. - For outgoing packets, 3 tables are traversed to find the route. The packet processing rate on the receiver is as follows: - Before the fix: 3.78Mpps - After the fix: 5.50Mpps Signed-off-by: Wei Wang Signed-off-by: David S. Miller --- include/net/ip6_route.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include') diff --git a/include/net/ip6_route.h b/include/net/ip6_route.h index 0709835c01ad..89ad7917b98d 100644 --- a/include/net/ip6_route.h +++ b/include/net/ip6_route.h @@ -84,6 +84,10 @@ struct dst_entry *ip6_route_input_lookup(struct net *net, struct flowi6 *fl6, const struct sk_buff *skb, int flags); +struct dst_entry *ip6_route_output_flags_noref(struct net *net, + const struct sock *sk, + struct flowi6 *fl6, int flags); + struct dst_entry *ip6_route_output_flags(struct net *net, const struct sock *sk, struct flowi6 *fl6, int flags); -- cgit v1.2.3 From 564c91f7e563256be835f31db97a60908702c9ec Mon Sep 17 00:00:00 2001 From: Stefano Brivio Date: Fri, 21 Jun 2019 17:45:20 +0200 Subject: fib_frontend, ip6_fib: Select routes or exceptions dump from RTM_F_CLONED The following patches add back the ability to dump IPv4 and IPv6 exception routes, and we need to allow selection of regular routes or exceptions. Use RTM_F_CLONED as filter to decide whether to dump routes or exceptions: iproute2 passes it in dump requests (except for IPv6 cache flush requests, this will be fixed in iproute2) and this used to work as long as exceptions were stored directly in the FIB, for both IPv4 and IPv6. Caveat: if strict checking is not requested (that is, if the dump request doesn't go through ip_valid_fib_dump_req()), we can't filter on protocol, tables or route types. In this case, filtering on RTM_F_CLONED would be inconsistent: we would fix 'ip route list cache' by returning exception routes and at the same time introduce another bug in case another selector is present, e.g. on 'ip route list cache table main' we would return all exception routes, without filtering on tables. Keep this consistent by applying no filters at all, and dumping both routes and exceptions, if strict checking is not requested. iproute2 currently filters results anyway, and no unwanted results will be presented to the user. The kernel will just dump more data than needed. v7: No changes v6: Rebase onto net-next, no changes v5: New patch: add dump_routes and dump_exceptions flags in filter and simply clear the unwanted one if strict checking is enabled, don't ignore NLM_F_MATCH and don't set filter_set if NLM_F_MATCH is set. Skip filtering altogether if no strict checking is requested: selecting routes or exceptions only would be inconsistent with the fact we can't filter on tables. Signed-off-by: Stefano Brivio Reviewed-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 7e1e621a56df..4c81846ccce8 100644 --- a/include/net/ip_fib.h +++ b/include/net/ip_fib.h @@ -245,6 +245,8 @@ struct fib_dump_filter { /* filter_set is an optimization that an entry is set */ bool filter_set; bool dump_all_families; + bool dump_routes; + bool dump_exceptions; unsigned char protocol; unsigned char rt_type; unsigned int flags; -- cgit v1.2.3 From ee28906fd7a1437ca77a60a99b6b9c6d676220f8 Mon Sep 17 00:00:00 2001 From: Stefano Brivio Date: Fri, 21 Jun 2019 17:45:23 +0200 Subject: ipv4: Dump route exceptions if requested Since commit 4895c771c7f0 ("ipv4: Add FIB nexthop exceptions."), cached exception routes are stored as a separate entity, so they are not dumped on a FIB dump, even if the RTM_F_CLONED flag is passed. This implies that the command 'ip route list cache' doesn't return any result anymore. If the RTM_F_CLONED is passed, and strict checking requested, retrieve nexthop exception routes and dump them. If no strict checking is requested, filtering can't be performed consistently: dump everything in that case. With this, we need to add an argument to the netlink callback in order to track how many entries were already dumped for the last leaf included in a partial netlink dump. A single additional argument is sufficient, even if we traverse logically nested structures (nexthop objects, hash table buckets, bucket chains): it doesn't matter if we stop in the middle of any of those, because they are always traversed the same way. As an example, s_i values in [], s_fa values in (): node (fa) #1 [1] nexthop #1 bucket #1 -> #0 in chain (1) bucket #2 -> #0 in chain (2) -> #1 in chain (3) -> #2 in chain (4) bucket #3 -> #0 in chain (5) -> #1 in chain (6) nexthop #2 bucket #1 -> #0 in chain (7) -> #1 in chain (8) bucket #2 -> #0 in chain (9) -- node (fa) #2 [2] nexthop #1 bucket #1 -> #0 in chain (1) -> #1 in chain (2) bucket #2 -> #0 in chain (3) it doesn't matter if we stop at (3), (4), (7) for "node #1", or at (2) for "node #2": walking flattens all that. It would even be possible to drop the distinction between the in-tree (s_i) and in-node (s_fa) counter, but a further improvement might advise against this. This is only as accurate as the existing tracking mechanism for leaves: if a partial dump is restarted after exceptions are removed or expired, we might skip some non-dumped entries. To improve this, we could attach a 'sernum' attribute (similar to the one used for IPv6) to nexthop entities, and bump this counter whenever exceptions change: having a distinction between the two counters would make this more convenient. Listing of exception routes (modified routes pre-3.5) was tested against these versions of kernel and iproute2: iproute2 kernel 4.14.0 4.15.0 4.19.0 5.0.0 5.1.0 3.5-rc4 + + + + + 4.4 4.9 4.14 4.15 4.19 5.0 5.1 fixed + + + + + v7: - Move loop over nexthop objects to route.c, and pass struct fib_info and table ID to it, not a struct fib_alias (suggested by David Ahern) - While at it, note that the NULL check on fa->fa_info is redundant, and the check on RTNH_F_DEAD is also not consistent with what's done with regular route listing: just keep it for nhc_flags - Rename entry point function for dumping exceptions to fib_dump_info_fnhe(), and rearrange arguments for consistency with fib_dump_info() - Rename fnhe_dump_buckets() to fnhe_dump_bucket() and make it handle one bucket at a time - Expand commit message to describe why we can have a single "skip" counter for all exceptions stored in bucket chains in nexthop objects (suggested by David Ahern) v6: - Rebased onto net-next - Loop over nexthop paths too. Move loop over fnhe buckets to route.c, avoids need to export rt_fill_info() and to touch exceptions from fib_trie.c. Pass NULL as flow to rt_fill_info(), it now allows that (suggested by David Ahern) Fixes: 4895c771c7f0 ("ipv4: Add FIB nexthop exceptions.") Signed-off-by: Stefano Brivio Reviewed-by: David Ahern Signed-off-by: David S. Miller --- include/net/route.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include') diff --git a/include/net/route.h b/include/net/route.h index 065b47754f05..cfcd0f5980f9 100644 --- a/include/net/route.h +++ b/include/net/route.h @@ -230,6 +230,10 @@ void fib_modify_prefix_metric(struct in_ifaddr *ifa, u32 new_metric); void rt_add_uncached_list(struct rtable *rt); void rt_del_uncached_list(struct rtable *rt); +int fib_dump_info_fnhe(struct sk_buff *skb, struct netlink_callback *cb, + u32 table_id, struct fib_info *fi, + int *fa_index, int fa_start); + static inline void ip_rt_put(struct rtable *rt) { /* dst_release() accepts a NULL parameter. -- cgit v1.2.3 From 1e47b4837f3bdaa425727cfe09f5ae3b6c4c41a9 Mon Sep 17 00:00:00 2001 From: Stefano Brivio Date: Fri, 21 Jun 2019 17:45:27 +0200 Subject: ipv6: Dump route exceptions if requested Since commit 2b760fcf5cfb ("ipv6: hook up exception table to store dst cache"), route exceptions reside in a separate hash table, and won't be found by walking the FIB, so they won't be dumped to userspace on a RTM_GETROUTE message. This causes 'ip -6 route list cache' and 'ip -6 route flush cache' to have no function anymore: # ip -6 route get fc00:3::1 fc00:3::1 via fc00:1::2 dev veth_A-R1 src fc00:1::1 metric 1024 expires 539sec mtu 1400 pref medium # ip -6 route get fc00:4::1 fc00:4::1 via fc00:2::2 dev veth_A-R2 src fc00:2::1 metric 1024 expires 536sec mtu 1500 pref medium # ip -6 route list cache # ip -6 route flush cache # ip -6 route get fc00:3::1 fc00:3::1 via fc00:1::2 dev veth_A-R1 src fc00:1::1 metric 1024 expires 520sec mtu 1400 pref medium # ip -6 route get fc00:4::1 fc00:4::1 via fc00:2::2 dev veth_A-R2 src fc00:2::1 metric 1024 expires 519sec mtu 1500 pref medium because iproute2 lists cached routes using RTM_GETROUTE, and flushes them by listing all the routes, and deleting them with RTM_DELROUTE one by one. If cached routes are requested using the RTM_F_CLONED flag together with strict checking, or if no strict checking is requested (and hence we can't consistently apply filters), look up exceptions in the hash table associated with the current fib6_info in rt6_dump_route(), and, if present and not expired, add them to the dump. We might be unable to dump all the entries for a given node in a single message, so keep track of how many entries were handled for the current node in fib6_walker, and skip that amount in case we start from the same partially dumped node. When a partial dump restarts, as the starting node might change when 'sernum' changes, we have no guarantee that we need to skip the same amount of in-node entries. Therefore, we need two counters, and we need to zero the in-node counter if the node from which the dump is resumed differs. Note that, with the current version of iproute2, this only fixes the 'ip -6 route list cache': on a flush command, iproute2 doesn't pass RTM_F_CLONED and, due to this inconsistency, 'ip -6 route flush cache' is still unable to fetch the routes to be flushed. This will be addressed in a patch for iproute2. To flush cached routes, a procfs entry could be introduced instead: that's how it works for IPv4. We already have a rt6_flush_exception() function ready to be wired to it. However, this would not solve the issue for listing. Versions of iproute2 and kernel tested: iproute2 kernel 4.14.0 4.15.0 4.19.0 5.0.0 5.1.0 5.1.0, patched 3.18 list + + + + + + flush + + + + + + 4.4 list + + + + + + flush + + + + + + 4.9 list + + + + + + flush + + + + + + 4.14 list + + + + + + flush + + + + + + 4.15 list flush 4.19 list flush 5.0 list flush 5.1 list flush with list + + + + + + fix flush + + + + v7: - Explain usage of "skip" counters in commit message (suggested by David Ahern) v6: - Rebase onto net-next, use recently introduced nexthop walker - Make rt6_nh_dump_exceptions() a separate function (suggested by David Ahern) v5: - Use dump_routes and dump_exceptions from filter, ignore NLM_F_MATCH, update test results (flushing works with iproute2 < 5.0.0 now) v4: - Split NLM_F_MATCH and strict check handling in separate patches - Filter routes using RTM_F_CLONED: if it's not set, only return non-cached routes, and if it's set, only return cached routes: change requested by David Ahern and Martin Lau. This implies that iproute2 needs a separate patch to be able to flush IPv6 cached routes. This is not ideal because we can't fix the breakage caused by 2b760fcf5cfb entirely in kernel. However, two years have passed since then, and this makes it more tolerable v3: - More descriptive comment about expired exceptions in rt6_dump_route() - Swap return values of rt6_dump_route() (suggested by Martin Lau) - Don't zero skip_in_node in case we don't dump anything in a given pass (also suggested by Martin Lau) - Remove check on RTM_F_CLONED altogether: in the current UAPI semantic, it's just a flag to indicate the route was cloned, not to filter on routes v2: Add tracking of number of entries to be skipped in current node after a partial dump. As we restart from the same node, if not all the exceptions for a given node fit in a single message, the dump will not terminate, as suggested by Martin Lau. This is a concrete possibility, setting up a big number of exceptions for the same route actually causes the issue, suggested by David Ahern. Reported-by: Jianlin Shi Fixes: 2b760fcf5cfb ("ipv6: hook up exception table to store dst cache") Signed-off-by: Stefano Brivio Reviewed-by: David Ahern Signed-off-by: David S. Miller --- include/net/ip6_fib.h | 1 + include/net/ip6_route.h | 2 +- 2 files changed, 2 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/net/ip6_fib.h b/include/net/ip6_fib.h index 87331f2c4af0..4b5656c71abc 100644 --- a/include/net/ip6_fib.h +++ b/include/net/ip6_fib.h @@ -316,6 +316,7 @@ struct fib6_walker { enum fib6_walk_state state; unsigned int skip; unsigned int count; + unsigned int skip_in_node; int (*func)(struct fib6_walker *); void *args; }; diff --git a/include/net/ip6_route.h b/include/net/ip6_route.h index 89ad7917b98d..c8bba0c28286 100644 --- a/include/net/ip6_route.h +++ b/include/net/ip6_route.h @@ -197,7 +197,7 @@ struct rt6_rtnl_dump_arg { struct fib_dump_filter filter; }; -int rt6_dump_route(struct fib6_info *f6i, void *p_arg); +int rt6_dump_route(struct fib6_info *f6i, void *p_arg, unsigned int skip); void rt6_mtu_change(struct net_device *dev, unsigned int mtu); void rt6_remove_prefsrc(struct inet6_ifaddr *ifp); void rt6_clean_tohost(struct net *net, struct in6_addr *gateway); -- cgit v1.2.3 From 792c4e9d0bbb53b34bf1c07c2ef25609d746c57d Mon Sep 17 00:00:00 2001 From: Matthew Wilcox Date: Thu, 20 Jun 2019 07:03:47 +0000 Subject: net/mlx5: Convert mkey_table to XArray The lock protecting the data structure does not need to be an rwlock. The only read access to the lock is in an error path, and if that's limiting your scalability, you have bigger performance problems. Eliminate mlx5_mkey_table in favour of using the xarray directly. reg_mr_callback must use GFP_ATOMIC for allocating XArray nodes as it may be called in interrupt context. This also fixes a minor bug where SRCU locking was being used on the radix tree read side, when RCU was needed too. Signed-off-by: Matthew Wilcox Signed-off-by: Jason Gunthorpe Signed-off-by: Saeed Mahameed --- include/linux/mlx5/driver.h | 13 ++----------- include/linux/mlx5/qp.h | 5 ----- 2 files changed, 2 insertions(+), 16 deletions(-) (limited to 'include') diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h index d8ab633406c2..87f77ded78d4 100644 --- a/include/linux/mlx5/driver.h +++ b/include/linux/mlx5/driver.h @@ -41,7 +41,7 @@ #include #include #include -#include +#include #include #include #include @@ -452,13 +452,6 @@ struct mlx5_qp_table { struct radix_tree_root tree; }; -struct mlx5_mkey_table { - /* protect radix tree - */ - rwlock_t lock; - struct radix_tree_root tree; -}; - struct mlx5_vf_context { int enabled; u64 port_guid; @@ -546,9 +539,7 @@ struct mlx5_priv { struct dentry *cmdif_debugfs; /* end: qp staff */ - /* start: mkey staff */ - struct mlx5_mkey_table mkey_table; - /* end: mkey staff */ + struct xarray mkey_table; /* start: alloc staff */ /* protect buffer alocation according to numa node */ diff --git a/include/linux/mlx5/qp.h b/include/linux/mlx5/qp.h index 3ba4edbd17a6..d1f353c64797 100644 --- a/include/linux/mlx5/qp.h +++ b/include/linux/mlx5/qp.h @@ -551,11 +551,6 @@ static inline struct mlx5_core_qp *__mlx5_qp_lookup(struct mlx5_core_dev *dev, u return radix_tree_lookup(&dev->priv.qp_table.tree, qpn); } -static inline struct mlx5_core_mkey *__mlx5_mr_lookup(struct mlx5_core_dev *dev, u32 key) -{ - return radix_tree_lookup(&dev->priv.mkey_table.tree, key); -} - int mlx5_core_create_dct(struct mlx5_core_dev *dev, struct mlx5_core_dct *qp, u32 *in, int inlen, -- cgit v1.2.3 From 5db7c8b9f9fc2aeec671ae3ca6375752c162e0e7 Mon Sep 17 00:00:00 2001 From: Julian Anastasov Date: Tue, 18 Jun 2019 23:07:36 +0300 Subject: ipvs: fix tinfo memory leak in start_sync_thread syzkaller reports for memory leak in start_sync_thread [1] As Eric points out, kthread may start and stop before the threadfn function is called, so there is no chance the data (tinfo in our case) to be released in thread. Fix this by releasing tinfo in the controlling code instead. [1] BUG: memory leak unreferenced object 0xffff8881206bf700 (size 32): comm "syz-executor761", pid 7268, jiffies 4294943441 (age 20.470s) hex dump (first 32 bytes): 00 40 7c 09 81 88 ff ff 80 45 b8 21 81 88 ff ff .@|......E.!.... 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 ................ backtrace: [<0000000057619e23>] kmemleak_alloc_recursive include/linux/kmemleak.h:55 [inline] [<0000000057619e23>] slab_post_alloc_hook mm/slab.h:439 [inline] [<0000000057619e23>] slab_alloc mm/slab.c:3326 [inline] [<0000000057619e23>] kmem_cache_alloc_trace+0x13d/0x280 mm/slab.c:3553 [<0000000086ce5479>] kmalloc include/linux/slab.h:547 [inline] [<0000000086ce5479>] start_sync_thread+0x5d2/0xe10 net/netfilter/ipvs/ip_vs_sync.c:1862 [<000000001a9229cc>] do_ip_vs_set_ctl+0x4c5/0x780 net/netfilter/ipvs/ip_vs_ctl.c:2402 [<00000000ece457c8>] nf_sockopt net/netfilter/nf_sockopt.c:106 [inline] [<00000000ece457c8>] nf_setsockopt+0x4c/0x80 net/netfilter/nf_sockopt.c:115 [<00000000942f62d4>] ip_setsockopt net/ipv4/ip_sockglue.c:1258 [inline] [<00000000942f62d4>] ip_setsockopt+0x9b/0xb0 net/ipv4/ip_sockglue.c:1238 [<00000000a56a8ffd>] udp_setsockopt+0x4e/0x90 net/ipv4/udp.c:2616 [<00000000fa895401>] sock_common_setsockopt+0x38/0x50 net/core/sock.c:3130 [<0000000095eef4cf>] __sys_setsockopt+0x98/0x120 net/socket.c:2078 [<000000009747cf88>] __do_sys_setsockopt net/socket.c:2089 [inline] [<000000009747cf88>] __se_sys_setsockopt net/socket.c:2086 [inline] [<000000009747cf88>] __x64_sys_setsockopt+0x26/0x30 net/socket.c:2086 [<00000000ded8ba80>] do_syscall_64+0x76/0x1a0 arch/x86/entry/common.c:301 [<00000000893b4ac8>] entry_SYSCALL_64_after_hwframe+0x44/0xa9 Reported-by: syzbot+7e2e50c8adfccd2e5041@syzkaller.appspotmail.com Suggested-by: Eric Biggers Fixes: 998e7a76804b ("ipvs: Use kthread_run() instead of doing a double-fork via kernel_thread()") Signed-off-by: Julian Anastasov Acked-by: Simon Horman Signed-off-by: Pablo Neira Ayuso --- 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 2ac40135b576..b36a1df93e7c 100644 --- a/include/net/ip_vs.h +++ b/include/net/ip_vs.h @@ -808,11 +808,12 @@ struct ipvs_master_sync_state { struct ip_vs_sync_buff *sync_buff; unsigned long sync_queue_len; unsigned int sync_queue_delay; - struct task_struct *master_thread; struct delayed_work master_wakeup_work; struct netns_ipvs *ipvs; }; +struct ip_vs_sync_thread_data; + /* How much time to keep dests in trash */ #define IP_VS_DEST_TRASH_PERIOD (120 * HZ) @@ -943,7 +944,8 @@ struct netns_ipvs { spinlock_t sync_lock; struct ipvs_master_sync_state *ms; spinlock_t sync_buff_lock; - struct task_struct **backup_threads; + struct ip_vs_sync_thread_data *master_tinfo; + struct ip_vs_sync_thread_data *backup_tinfo; int threads_mask; volatile int sync_state; struct mutex sync_mutex; -- cgit v1.2.3 From e7d4798960b3ebcd243ae6a59e04d4fe6518c96c Mon Sep 17 00:00:00 2001 From: Toshiaki Makita Date: Thu, 13 Jun 2019 18:39:58 +0900 Subject: xdp: Add tracepoint for bulk XDP_TX This is introduced for admins to check what is happening on XDP_TX when bulk XDP_TX is in use, which will be first introduced in veth in next commit. v3: - Add act field to be in line with other XDP tracepoints. Signed-off-by: Toshiaki Makita Acked-by: Jesper Dangaard Brouer Signed-off-by: Daniel Borkmann --- include/trace/events/xdp.h | 29 +++++++++++++++++++++++++++++ 1 file changed, 29 insertions(+) (limited to 'include') diff --git a/include/trace/events/xdp.h b/include/trace/events/xdp.h index bb5e380e2ef3..81e708c4b513 100644 --- a/include/trace/events/xdp.h +++ b/include/trace/events/xdp.h @@ -50,6 +50,35 @@ TRACE_EVENT(xdp_exception, __entry->ifindex) ); +TRACE_EVENT(xdp_bulk_tx, + + TP_PROTO(const struct net_device *dev, + int sent, int drops, int err), + + TP_ARGS(dev, sent, drops, err), + + TP_STRUCT__entry( + __field(int, ifindex) + __field(u32, act) + __field(int, drops) + __field(int, sent) + __field(int, err) + ), + + TP_fast_assign( + __entry->ifindex = dev->ifindex; + __entry->act = XDP_TX; + __entry->drops = drops; + __entry->sent = sent; + __entry->err = err; + ), + + TP_printk("ifindex=%d action=%s sent=%d drops=%d err=%d", + __entry->ifindex, + __print_symbolic(__entry->act, __XDP_ACT_SYM_TAB), + __entry->sent, __entry->drops, __entry->err) +); + DECLARE_EVENT_CLASS(xdp_redirect_template, TP_PROTO(const struct net_device *dev, -- cgit v1.2.3 From 0e58983de0d89f6ee75daab1b0ea918cfcf6ddbf Mon Sep 17 00:00:00 2001 From: Tal Gilboa Date: Sun, 4 Nov 2018 19:07:02 +0200 Subject: linux/dim: Move logic to dim.h In preparation for supporting more implementations of the DIM algorithm, I'm moving what would become common logic to a common library. Downstream DIM implementations will use the common lib for their implementation. Signed-off-by: Tal Gilboa Signed-off-by: Saeed Mahameed --- include/linux/dim.h | 153 ++++++++++++++++++++++++++++++++++++++++++++++++ include/linux/net_dim.h | 148 +--------------------------------------------- 2 files changed, 155 insertions(+), 146 deletions(-) create mode 100644 include/linux/dim.h (limited to 'include') diff --git a/include/linux/dim.h b/include/linux/dim.h new file mode 100644 index 000000000000..67d7ca40f3dd --- /dev/null +++ b/include/linux/dim.h @@ -0,0 +1,153 @@ +/* SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB */ +/* Copyright (c) 2019 Mellanox Technologies. */ + +#ifndef DIM_H +#define DIM_H + +#include + +#define NET_DIM_NEVENTS 64 + +/* more than 10% difference */ +#define IS_SIGNIFICANT_DIFF(val, ref) \ + (((100UL * abs((val) - (ref))) / (ref)) > 10) +#define BIT_GAP(bits, end, start) ((((end) - (start)) + BIT_ULL(bits)) \ +& (BIT_ULL(bits) - 1)) + +struct net_dim_cq_moder { + u16 usec; + u16 pkts; + u8 cq_period_mode; +}; + +struct net_dim_sample { + ktime_t time; + u32 pkt_ctr; + u32 byte_ctr; + u16 event_ctr; +}; + +struct net_dim_stats { + int ppms; /* packets per msec */ + int bpms; /* bytes per msec */ + int epms; /* events per msec */ +}; + +struct net_dim { /* Dynamic Interrupt Moderation */ + u8 state; + struct net_dim_stats prev_stats; + struct net_dim_sample start_sample; + struct work_struct work; + u8 profile_ix; + u8 mode; + u8 tune_state; + u8 steps_right; + u8 steps_left; + u8 tired; +}; + +enum { + NET_DIM_CQ_PERIOD_MODE_START_FROM_EQE = 0x0, + NET_DIM_CQ_PERIOD_MODE_START_FROM_CQE = 0x1, + NET_DIM_CQ_PERIOD_NUM_MODES +}; + +enum { + NET_DIM_START_MEASURE, + NET_DIM_MEASURE_IN_PROGRESS, + NET_DIM_APPLY_NEW_PROFILE, +}; + +enum { + NET_DIM_PARKING_ON_TOP, + NET_DIM_PARKING_TIRED, + NET_DIM_GOING_RIGHT, + NET_DIM_GOING_LEFT, +}; + +enum { + NET_DIM_STATS_WORSE, + NET_DIM_STATS_SAME, + NET_DIM_STATS_BETTER, +}; + +enum { + NET_DIM_STEPPED, + NET_DIM_TOO_TIRED, + NET_DIM_ON_EDGE, +}; + +static inline bool net_dim_on_top(struct net_dim *net_dim) +{ + switch (net_dim->tune_state) { + case NET_DIM_PARKING_ON_TOP: + case NET_DIM_PARKING_TIRED: + return true; + case NET_DIM_GOING_RIGHT: + return (net_dim->steps_left > 1) && (net_dim->steps_right == 1); + default: /* NET_DIM_GOING_LEFT */ + return (net_dim->steps_right > 1) && (net_dim->steps_left == 1); + } +} + +static inline void net_dim_turn(struct net_dim *net_dim) +{ + switch (net_dim->tune_state) { + case NET_DIM_PARKING_ON_TOP: + case NET_DIM_PARKING_TIRED: + break; + case NET_DIM_GOING_RIGHT: + net_dim->tune_state = NET_DIM_GOING_LEFT; + net_dim->steps_left = 0; + break; + case NET_DIM_GOING_LEFT: + net_dim->tune_state = NET_DIM_GOING_RIGHT; + net_dim->steps_right = 0; + break; + } +} + +static inline void net_dim_park_on_top(struct net_dim *net_dim) +{ + net_dim->steps_right = 0; + net_dim->steps_left = 0; + net_dim->tired = 0; + net_dim->tune_state = NET_DIM_PARKING_ON_TOP; +} + +static inline void net_dim_park_tired(struct net_dim *net_dim) +{ + net_dim->steps_right = 0; + net_dim->steps_left = 0; + net_dim->tune_state = NET_DIM_PARKING_TIRED; +} + +static inline void +net_dim_sample(u16 event_ctr, u64 packets, u64 bytes, struct net_dim_sample *s) +{ + s->time = ktime_get(); + s->pkt_ctr = packets; + s->byte_ctr = bytes; + s->event_ctr = event_ctr; +} + +static inline void +net_dim_calc_stats(struct net_dim_sample *start, struct net_dim_sample *end, + struct net_dim_stats *curr_stats) +{ + /* u32 holds up to 71 minutes, should be enough */ + u32 delta_us = ktime_us_delta(end->time, start->time); + u32 npkts = BIT_GAP(BITS_PER_TYPE(u32), end->pkt_ctr, start->pkt_ctr); + u32 nbytes = BIT_GAP(BITS_PER_TYPE(u32), end->byte_ctr, + start->byte_ctr); + + if (!delta_us) + return; + + curr_stats->ppms = DIV_ROUND_UP(npkts * USEC_PER_MSEC, delta_us); + curr_stats->bpms = DIV_ROUND_UP(nbytes * USEC_PER_MSEC, delta_us); + curr_stats->epms = DIV_ROUND_UP(NET_DIM_NEVENTS * USEC_PER_MSEC, + delta_us); +} + +#endif /* DIM_H */ diff --git a/include/linux/net_dim.h b/include/linux/net_dim.h index fd458389f7d1..373cda74b167 100644 --- a/include/linux/net_dim.h +++ b/include/linux/net_dim.h @@ -35,73 +35,10 @@ #define NET_DIM_H #include - -struct net_dim_cq_moder { - u16 usec; - u16 pkts; - u8 cq_period_mode; -}; - -struct net_dim_sample { - ktime_t time; - u32 pkt_ctr; - u32 byte_ctr; - u16 event_ctr; -}; - -struct net_dim_stats { - int ppms; /* packets per msec */ - int bpms; /* bytes per msec */ - int epms; /* events per msec */ -}; - -struct net_dim { /* Adaptive Moderation */ - u8 state; - struct net_dim_stats prev_stats; - struct net_dim_sample start_sample; - struct work_struct work; - u8 profile_ix; - u8 mode; - u8 tune_state; - u8 steps_right; - u8 steps_left; - u8 tired; -}; - -enum { - NET_DIM_CQ_PERIOD_MODE_START_FROM_EQE = 0x0, - NET_DIM_CQ_PERIOD_MODE_START_FROM_CQE = 0x1, - NET_DIM_CQ_PERIOD_NUM_MODES -}; - -/* Adaptive moderation logic */ -enum { - NET_DIM_START_MEASURE, - NET_DIM_MEASURE_IN_PROGRESS, - NET_DIM_APPLY_NEW_PROFILE, -}; - -enum { - NET_DIM_PARKING_ON_TOP, - NET_DIM_PARKING_TIRED, - NET_DIM_GOING_RIGHT, - NET_DIM_GOING_LEFT, -}; - -enum { - NET_DIM_STATS_WORSE, - NET_DIM_STATS_SAME, - NET_DIM_STATS_BETTER, -}; - -enum { - NET_DIM_STEPPED, - NET_DIM_TOO_TIRED, - NET_DIM_ON_EDGE, -}; +#include #define NET_DIM_PARAMS_NUM_PROFILES 5 -/* Adaptive moderation profiles */ +/* Netdev dynamic interrupt moderation profiles */ #define NET_DIM_DEFAULT_RX_CQ_MODERATION_PKTS_FROM_EQE 256 #define NET_DIM_DEFAULT_TX_CQ_MODERATION_PKTS_FROM_EQE 128 #define NET_DIM_DEF_PROFILE_CQE 1 @@ -188,36 +125,6 @@ net_dim_get_def_tx_moderation(u8 cq_period_mode) return net_dim_get_tx_moderation(cq_period_mode, profile_ix); } -static inline bool net_dim_on_top(struct net_dim *dim) -{ - switch (dim->tune_state) { - case NET_DIM_PARKING_ON_TOP: - case NET_DIM_PARKING_TIRED: - return true; - case NET_DIM_GOING_RIGHT: - return (dim->steps_left > 1) && (dim->steps_right == 1); - default: /* NET_DIM_GOING_LEFT */ - return (dim->steps_right > 1) && (dim->steps_left == 1); - } -} - -static inline void net_dim_turn(struct net_dim *dim) -{ - switch (dim->tune_state) { - case NET_DIM_PARKING_ON_TOP: - case NET_DIM_PARKING_TIRED: - break; - case NET_DIM_GOING_RIGHT: - dim->tune_state = NET_DIM_GOING_LEFT; - dim->steps_left = 0; - break; - case NET_DIM_GOING_LEFT: - dim->tune_state = NET_DIM_GOING_RIGHT; - dim->steps_right = 0; - break; - } -} - static inline int net_dim_step(struct net_dim *dim) { if (dim->tired == (NET_DIM_PARAMS_NUM_PROFILES * 2)) @@ -245,21 +152,6 @@ static inline int net_dim_step(struct net_dim *dim) return NET_DIM_STEPPED; } -static inline void net_dim_park_on_top(struct net_dim *dim) -{ - dim->steps_right = 0; - dim->steps_left = 0; - dim->tired = 0; - dim->tune_state = NET_DIM_PARKING_ON_TOP; -} - -static inline void net_dim_park_tired(struct net_dim *dim) -{ - dim->steps_right = 0; - dim->steps_left = 0; - dim->tune_state = NET_DIM_PARKING_TIRED; -} - static inline void net_dim_exit_parking(struct net_dim *dim) { dim->tune_state = dim->profile_ix ? NET_DIM_GOING_LEFT : @@ -267,9 +159,6 @@ static inline void net_dim_exit_parking(struct net_dim *dim) net_dim_step(dim); } -#define IS_SIGNIFICANT_DIFF(val, ref) \ - (((100UL * abs((val) - (ref))) / (ref)) > 10) /* more than 10% difference */ - static inline int net_dim_stats_compare(struct net_dim_stats *curr, struct net_dim_stats *prev) { @@ -351,39 +240,6 @@ static inline bool net_dim_decision(struct net_dim_stats *curr_stats, return dim->profile_ix != prev_ix; } -static inline void net_dim_sample(u16 event_ctr, - u64 packets, - u64 bytes, - struct net_dim_sample *s) -{ - s->time = ktime_get(); - s->pkt_ctr = packets; - s->byte_ctr = bytes; - s->event_ctr = event_ctr; -} - -#define NET_DIM_NEVENTS 64 -#define BIT_GAP(bits, end, start) ((((end) - (start)) + BIT_ULL(bits)) & (BIT_ULL(bits) - 1)) - -static inline void net_dim_calc_stats(struct net_dim_sample *start, - struct net_dim_sample *end, - struct net_dim_stats *curr_stats) -{ - /* u32 holds up to 71 minutes, should be enough */ - u32 delta_us = ktime_us_delta(end->time, start->time); - u32 npkts = BIT_GAP(BITS_PER_TYPE(u32), end->pkt_ctr, start->pkt_ctr); - u32 nbytes = BIT_GAP(BITS_PER_TYPE(u32), end->byte_ctr, - start->byte_ctr); - - if (!delta_us) - return; - - curr_stats->ppms = DIV_ROUND_UP(npkts * USEC_PER_MSEC, delta_us); - curr_stats->bpms = DIV_ROUND_UP(nbytes * USEC_PER_MSEC, delta_us); - curr_stats->epms = DIV_ROUND_UP(NET_DIM_NEVENTS * USEC_PER_MSEC, - delta_us); -} - static inline void net_dim(struct net_dim *dim, struct net_dim_sample end_sample) { -- cgit v1.2.3 From 449986ea92412727e8c553eaa5c8d3ed884253c4 Mon Sep 17 00:00:00 2001 From: Tal Gilboa Date: Mon, 5 Nov 2018 11:57:10 +0200 Subject: linux/dim: Remove "net" prefix from internal DIM members Only renaming functions and structs which aren't used by an external code. Signed-off-by: Tal Gilboa Signed-off-by: Saeed Mahameed --- include/linux/dim.h | 86 ++++++++++++++++++++++++------------------------ include/linux/net_dim.h | 87 ++++++++++++++++++++++++------------------------- 2 files changed, 86 insertions(+), 87 deletions(-) (limited to 'include') diff --git a/include/linux/dim.h b/include/linux/dim.h index 67d7ca40f3dd..6ee991681d62 100644 --- a/include/linux/dim.h +++ b/include/linux/dim.h @@ -6,7 +6,7 @@ #include -#define NET_DIM_NEVENTS 64 +#define DIM_NEVENTS 64 /* more than 10% difference */ #define IS_SIGNIFICANT_DIFF(val, ref) \ @@ -27,7 +27,7 @@ struct net_dim_sample { u16 event_ctr; }; -struct net_dim_stats { +struct dim_stats { int ppms; /* packets per msec */ int bpms; /* bytes per msec */ int epms; /* events per msec */ @@ -35,7 +35,7 @@ struct net_dim_stats { struct net_dim { /* Dynamic Interrupt Moderation */ u8 state; - struct net_dim_stats prev_stats; + struct dim_stats prev_stats; struct net_dim_sample start_sample; struct work_struct work; u8 profile_ix; @@ -59,67 +59,67 @@ enum { }; enum { - NET_DIM_PARKING_ON_TOP, - NET_DIM_PARKING_TIRED, - NET_DIM_GOING_RIGHT, - NET_DIM_GOING_LEFT, + DIM_PARKING_ON_TOP, + DIM_PARKING_TIRED, + DIM_GOING_RIGHT, + DIM_GOING_LEFT, }; enum { - NET_DIM_STATS_WORSE, - NET_DIM_STATS_SAME, - NET_DIM_STATS_BETTER, + DIM_STATS_WORSE, + DIM_STATS_SAME, + DIM_STATS_BETTER, }; enum { - NET_DIM_STEPPED, - NET_DIM_TOO_TIRED, - NET_DIM_ON_EDGE, + DIM_STEPPED, + DIM_TOO_TIRED, + DIM_ON_EDGE, }; -static inline bool net_dim_on_top(struct net_dim *net_dim) +static inline bool dim_on_top(struct net_dim *dim) { - switch (net_dim->tune_state) { - case NET_DIM_PARKING_ON_TOP: - case NET_DIM_PARKING_TIRED: + switch (dim->tune_state) { + case DIM_PARKING_ON_TOP: + case DIM_PARKING_TIRED: return true; - case NET_DIM_GOING_RIGHT: - return (net_dim->steps_left > 1) && (net_dim->steps_right == 1); - default: /* NET_DIM_GOING_LEFT */ - return (net_dim->steps_right > 1) && (net_dim->steps_left == 1); + case DIM_GOING_RIGHT: + return (dim->steps_left > 1) && (dim->steps_right == 1); + default: /* DIM_GOING_LEFT */ + return (dim->steps_right > 1) && (dim->steps_left == 1); } } -static inline void net_dim_turn(struct net_dim *net_dim) +static inline void dim_turn(struct net_dim *dim) { - switch (net_dim->tune_state) { - case NET_DIM_PARKING_ON_TOP: - case NET_DIM_PARKING_TIRED: + switch (dim->tune_state) { + case DIM_PARKING_ON_TOP: + case DIM_PARKING_TIRED: break; - case NET_DIM_GOING_RIGHT: - net_dim->tune_state = NET_DIM_GOING_LEFT; - net_dim->steps_left = 0; + case DIM_GOING_RIGHT: + dim->tune_state = DIM_GOING_LEFT; + dim->steps_left = 0; break; - case NET_DIM_GOING_LEFT: - net_dim->tune_state = NET_DIM_GOING_RIGHT; - net_dim->steps_right = 0; + case DIM_GOING_LEFT: + dim->tune_state = DIM_GOING_RIGHT; + dim->steps_right = 0; break; } } -static inline void net_dim_park_on_top(struct net_dim *net_dim) +static inline void dim_park_on_top(struct net_dim *dim) { - net_dim->steps_right = 0; - net_dim->steps_left = 0; - net_dim->tired = 0; - net_dim->tune_state = NET_DIM_PARKING_ON_TOP; + dim->steps_right = 0; + dim->steps_left = 0; + dim->tired = 0; + dim->tune_state = DIM_PARKING_ON_TOP; } -static inline void net_dim_park_tired(struct net_dim *net_dim) +static inline void dim_park_tired(struct net_dim *dim) { - net_dim->steps_right = 0; - net_dim->steps_left = 0; - net_dim->tune_state = NET_DIM_PARKING_TIRED; + dim->steps_right = 0; + dim->steps_left = 0; + dim->tune_state = DIM_PARKING_TIRED; } static inline void @@ -132,8 +132,8 @@ net_dim_sample(u16 event_ctr, u64 packets, u64 bytes, struct net_dim_sample *s) } static inline void -net_dim_calc_stats(struct net_dim_sample *start, struct net_dim_sample *end, - struct net_dim_stats *curr_stats) +dim_calc_stats(struct net_dim_sample *start, struct net_dim_sample *end, + struct dim_stats *curr_stats) { /* u32 holds up to 71 minutes, should be enough */ u32 delta_us = ktime_us_delta(end->time, start->time); @@ -146,7 +146,7 @@ net_dim_calc_stats(struct net_dim_sample *start, struct net_dim_sample *end, curr_stats->ppms = DIV_ROUND_UP(npkts * USEC_PER_MSEC, delta_us); curr_stats->bpms = DIV_ROUND_UP(nbytes * USEC_PER_MSEC, delta_us); - curr_stats->epms = DIV_ROUND_UP(NET_DIM_NEVENTS * USEC_PER_MSEC, + curr_stats->epms = DIV_ROUND_UP(DIM_NEVENTS * USEC_PER_MSEC, delta_us); } diff --git a/include/linux/net_dim.h b/include/linux/net_dim.h index 373cda74b167..f89fa4fdfb46 100644 --- a/include/linux/net_dim.h +++ b/include/linux/net_dim.h @@ -128,67 +128,67 @@ net_dim_get_def_tx_moderation(u8 cq_period_mode) static inline int net_dim_step(struct net_dim *dim) { if (dim->tired == (NET_DIM_PARAMS_NUM_PROFILES * 2)) - return NET_DIM_TOO_TIRED; + return DIM_TOO_TIRED; switch (dim->tune_state) { - case NET_DIM_PARKING_ON_TOP: - case NET_DIM_PARKING_TIRED: + case DIM_PARKING_ON_TOP: + case DIM_PARKING_TIRED: break; - case NET_DIM_GOING_RIGHT: + case DIM_GOING_RIGHT: if (dim->profile_ix == (NET_DIM_PARAMS_NUM_PROFILES - 1)) - return NET_DIM_ON_EDGE; + return DIM_ON_EDGE; dim->profile_ix++; dim->steps_right++; break; - case NET_DIM_GOING_LEFT: + case DIM_GOING_LEFT: if (dim->profile_ix == 0) - return NET_DIM_ON_EDGE; + return DIM_ON_EDGE; dim->profile_ix--; dim->steps_left++; break; } dim->tired++; - return NET_DIM_STEPPED; + return DIM_STEPPED; } static inline void net_dim_exit_parking(struct net_dim *dim) { - dim->tune_state = dim->profile_ix ? NET_DIM_GOING_LEFT : - NET_DIM_GOING_RIGHT; + dim->tune_state = dim->profile_ix ? DIM_GOING_LEFT : + DIM_GOING_RIGHT; net_dim_step(dim); } -static inline int net_dim_stats_compare(struct net_dim_stats *curr, - struct net_dim_stats *prev) +static inline int net_dim_stats_compare(struct dim_stats *curr, + struct dim_stats *prev) { if (!prev->bpms) - return curr->bpms ? NET_DIM_STATS_BETTER : - NET_DIM_STATS_SAME; + return curr->bpms ? DIM_STATS_BETTER : + DIM_STATS_SAME; if (IS_SIGNIFICANT_DIFF(curr->bpms, prev->bpms)) - return (curr->bpms > prev->bpms) ? NET_DIM_STATS_BETTER : - NET_DIM_STATS_WORSE; + return (curr->bpms > prev->bpms) ? DIM_STATS_BETTER : + DIM_STATS_WORSE; if (!prev->ppms) - return curr->ppms ? NET_DIM_STATS_BETTER : - NET_DIM_STATS_SAME; + return curr->ppms ? DIM_STATS_BETTER : + DIM_STATS_SAME; if (IS_SIGNIFICANT_DIFF(curr->ppms, prev->ppms)) - return (curr->ppms > prev->ppms) ? NET_DIM_STATS_BETTER : - NET_DIM_STATS_WORSE; + return (curr->ppms > prev->ppms) ? DIM_STATS_BETTER : + DIM_STATS_WORSE; if (!prev->epms) - return NET_DIM_STATS_SAME; + return DIM_STATS_SAME; if (IS_SIGNIFICANT_DIFF(curr->epms, prev->epms)) - return (curr->epms < prev->epms) ? NET_DIM_STATS_BETTER : - NET_DIM_STATS_WORSE; + return (curr->epms < prev->epms) ? DIM_STATS_BETTER : + DIM_STATS_WORSE; - return NET_DIM_STATS_SAME; + return DIM_STATS_SAME; } -static inline bool net_dim_decision(struct net_dim_stats *curr_stats, +static inline bool net_dim_decision(struct dim_stats *curr_stats, struct net_dim *dim) { int prev_state = dim->tune_state; @@ -197,44 +197,44 @@ static inline bool net_dim_decision(struct net_dim_stats *curr_stats, int step_res; switch (dim->tune_state) { - case NET_DIM_PARKING_ON_TOP: + case DIM_PARKING_ON_TOP: stats_res = net_dim_stats_compare(curr_stats, &dim->prev_stats); - if (stats_res != NET_DIM_STATS_SAME) + if (stats_res != DIM_STATS_SAME) net_dim_exit_parking(dim); break; - case NET_DIM_PARKING_TIRED: + case DIM_PARKING_TIRED: dim->tired--; if (!dim->tired) net_dim_exit_parking(dim); break; - case NET_DIM_GOING_RIGHT: - case NET_DIM_GOING_LEFT: + case DIM_GOING_RIGHT: + case DIM_GOING_LEFT: stats_res = net_dim_stats_compare(curr_stats, &dim->prev_stats); - if (stats_res != NET_DIM_STATS_BETTER) - net_dim_turn(dim); + if (stats_res != DIM_STATS_BETTER) + dim_turn(dim); - if (net_dim_on_top(dim)) { - net_dim_park_on_top(dim); + if (dim_on_top(dim)) { + dim_park_on_top(dim); break; } step_res = net_dim_step(dim); switch (step_res) { - case NET_DIM_ON_EDGE: - net_dim_park_on_top(dim); + case DIM_ON_EDGE: + dim_park_on_top(dim); break; - case NET_DIM_TOO_TIRED: - net_dim_park_tired(dim); + case DIM_TOO_TIRED: + dim_park_tired(dim); break; } break; } - if ((prev_state != NET_DIM_PARKING_ON_TOP) || - (dim->tune_state != NET_DIM_PARKING_ON_TOP)) + if (prev_state != DIM_PARKING_ON_TOP || + dim->tune_state != DIM_PARKING_ON_TOP) dim->prev_stats = *curr_stats; return dim->profile_ix != prev_ix; @@ -243,7 +243,7 @@ static inline bool net_dim_decision(struct net_dim_stats *curr_stats, static inline void net_dim(struct net_dim *dim, struct net_dim_sample end_sample) { - struct net_dim_stats curr_stats; + struct dim_stats curr_stats; u16 nevents; switch (dim->state) { @@ -251,10 +251,9 @@ static inline void net_dim(struct net_dim *dim, nevents = BIT_GAP(BITS_PER_TYPE(u16), end_sample.event_ctr, dim->start_sample.event_ctr); - if (nevents < NET_DIM_NEVENTS) + if (nevents < DIM_NEVENTS) break; - net_dim_calc_stats(&dim->start_sample, &end_sample, - &curr_stats); + dim_calc_stats(&dim->start_sample, &end_sample, &curr_stats); if (net_dim_decision(&curr_stats, dim)) { dim->state = NET_DIM_APPLY_NEW_PROFILE; schedule_work(&dim->work); -- cgit v1.2.3 From c002bd529d719858d4cc233431c88c9efa844053 Mon Sep 17 00:00:00 2001 From: Tal Gilboa Date: Mon, 5 Nov 2018 12:07:52 +0200 Subject: linux/dim: Rename externally exposed macros Renamed macros in use by external drivers. Signed-off-by: Tal Gilboa Signed-off-by: Saeed Mahameed --- include/linux/dim.h | 12 ++++++------ include/linux/net_dim.h | 18 +++++++++--------- 2 files changed, 15 insertions(+), 15 deletions(-) (limited to 'include') diff --git a/include/linux/dim.h b/include/linux/dim.h index 6ee991681d62..989dbbdf9d45 100644 --- a/include/linux/dim.h +++ b/include/linux/dim.h @@ -47,15 +47,15 @@ struct net_dim { /* Dynamic Interrupt Moderation */ }; enum { - NET_DIM_CQ_PERIOD_MODE_START_FROM_EQE = 0x0, - NET_DIM_CQ_PERIOD_MODE_START_FROM_CQE = 0x1, - NET_DIM_CQ_PERIOD_NUM_MODES + DIM_CQ_PERIOD_MODE_START_FROM_EQE = 0x0, + DIM_CQ_PERIOD_MODE_START_FROM_CQE = 0x1, + DIM_CQ_PERIOD_NUM_MODES }; enum { - NET_DIM_START_MEASURE, - NET_DIM_MEASURE_IN_PROGRESS, - NET_DIM_APPLY_NEW_PROFILE, + DIM_START_MEASURE, + DIM_MEASURE_IN_PROGRESS, + DIM_APPLY_NEW_PROFILE, }; enum { diff --git a/include/linux/net_dim.h b/include/linux/net_dim.h index f89fa4fdfb46..e0c97f824dd0 100644 --- a/include/linux/net_dim.h +++ b/include/linux/net_dim.h @@ -78,13 +78,13 @@ } static const struct net_dim_cq_moder -rx_profile[NET_DIM_CQ_PERIOD_NUM_MODES][NET_DIM_PARAMS_NUM_PROFILES] = { +rx_profile[DIM_CQ_PERIOD_NUM_MODES][NET_DIM_PARAMS_NUM_PROFILES] = { NET_DIM_RX_EQE_PROFILES, NET_DIM_RX_CQE_PROFILES, }; static const struct net_dim_cq_moder -tx_profile[NET_DIM_CQ_PERIOD_NUM_MODES][NET_DIM_PARAMS_NUM_PROFILES] = { +tx_profile[DIM_CQ_PERIOD_NUM_MODES][NET_DIM_PARAMS_NUM_PROFILES] = { NET_DIM_TX_EQE_PROFILES, NET_DIM_TX_CQE_PROFILES, }; @@ -101,7 +101,7 @@ net_dim_get_rx_moderation(u8 cq_period_mode, int ix) static inline struct net_dim_cq_moder net_dim_get_def_rx_moderation(u8 cq_period_mode) { - u8 profile_ix = cq_period_mode == NET_DIM_CQ_PERIOD_MODE_START_FROM_CQE ? + u8 profile_ix = cq_period_mode == DIM_CQ_PERIOD_MODE_START_FROM_CQE ? NET_DIM_DEF_PROFILE_CQE : NET_DIM_DEF_PROFILE_EQE; return net_dim_get_rx_moderation(cq_period_mode, profile_ix); @@ -119,7 +119,7 @@ net_dim_get_tx_moderation(u8 cq_period_mode, int ix) static inline struct net_dim_cq_moder net_dim_get_def_tx_moderation(u8 cq_period_mode) { - u8 profile_ix = cq_period_mode == NET_DIM_CQ_PERIOD_MODE_START_FROM_CQE ? + u8 profile_ix = cq_period_mode == DIM_CQ_PERIOD_MODE_START_FROM_CQE ? NET_DIM_DEF_PROFILE_CQE : NET_DIM_DEF_PROFILE_EQE; return net_dim_get_tx_moderation(cq_period_mode, profile_ix); @@ -247,7 +247,7 @@ static inline void net_dim(struct net_dim *dim, u16 nevents; switch (dim->state) { - case NET_DIM_MEASURE_IN_PROGRESS: + case DIM_MEASURE_IN_PROGRESS: nevents = BIT_GAP(BITS_PER_TYPE(u16), end_sample.event_ctr, dim->start_sample.event_ctr); @@ -255,17 +255,17 @@ static inline void net_dim(struct net_dim *dim, break; dim_calc_stats(&dim->start_sample, &end_sample, &curr_stats); if (net_dim_decision(&curr_stats, dim)) { - dim->state = NET_DIM_APPLY_NEW_PROFILE; + dim->state = DIM_APPLY_NEW_PROFILE; schedule_work(&dim->work); break; } /* fall through */ - case NET_DIM_START_MEASURE: + case DIM_START_MEASURE: net_dim_sample(end_sample.event_ctr, end_sample.pkt_ctr, end_sample.byte_ctr, &dim->start_sample); - dim->state = NET_DIM_MEASURE_IN_PROGRESS; + dim->state = DIM_MEASURE_IN_PROGRESS; break; - case NET_DIM_APPLY_NEW_PROFILE: + case DIM_APPLY_NEW_PROFILE: break; } } -- cgit v1.2.3 From e5b6ab02d7aa4118c9a36491633812dcc442acbe Mon Sep 17 00:00:00 2001 From: Tal Gilboa Date: Mon, 14 Jan 2019 15:32:49 +0200 Subject: linux/dim: Rename net_dim_sample() to net_dim_update_sample() In order to avoid confusion between the function and the similarly named struct. In preparation for removing the 'net' prefix from dim members. Signed-off-by: Tal Gilboa Signed-off-by: Saeed Mahameed --- include/linux/dim.h | 3 ++- include/linux/net_dim.h | 4 ++-- 2 files changed, 4 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/include/linux/dim.h b/include/linux/dim.h index 989dbbdf9d45..f0f20ed25497 100644 --- a/include/linux/dim.h +++ b/include/linux/dim.h @@ -123,7 +123,8 @@ static inline void dim_park_tired(struct net_dim *dim) } static inline void -net_dim_sample(u16 event_ctr, u64 packets, u64 bytes, struct net_dim_sample *s) +net_dim_update_sample(u16 event_ctr, u64 packets, u64 bytes, + struct net_dim_sample *s) { s->time = ktime_get(); s->pkt_ctr = packets; diff --git a/include/linux/net_dim.h b/include/linux/net_dim.h index e0c97f824dd0..d4b40adc7fa1 100644 --- a/include/linux/net_dim.h +++ b/include/linux/net_dim.h @@ -261,8 +261,8 @@ static inline void net_dim(struct net_dim *dim, } /* fall through */ case DIM_START_MEASURE: - net_dim_sample(end_sample.event_ctr, end_sample.pkt_ctr, end_sample.byte_ctr, - &dim->start_sample); + net_dim_update_sample(end_sample.event_ctr, end_sample.pkt_ctr, + end_sample.byte_ctr, &dim->start_sample); dim->state = DIM_MEASURE_IN_PROGRESS; break; case DIM_APPLY_NEW_PROFILE: -- cgit v1.2.3 From 8960b38932bee8db0bc9c4d8c135f21df6cdd297 Mon Sep 17 00:00:00 2001 From: Tal Gilboa Date: Thu, 31 Jan 2019 16:44:48 +0200 Subject: linux/dim: Rename externally used net_dim members Removed 'net' prefix from functions and structs used by external drivers. Signed-off-by: Tal Gilboa Signed-off-by: Saeed Mahameed --- include/linux/dim.h | 21 ++++++++++----------- include/linux/net_dim.h | 30 +++++++++++++++--------------- 2 files changed, 25 insertions(+), 26 deletions(-) (limited to 'include') diff --git a/include/linux/dim.h b/include/linux/dim.h index f0f20ed25497..60e5074a7cc0 100644 --- a/include/linux/dim.h +++ b/include/linux/dim.h @@ -14,13 +14,13 @@ #define BIT_GAP(bits, end, start) ((((end) - (start)) + BIT_ULL(bits)) \ & (BIT_ULL(bits) - 1)) -struct net_dim_cq_moder { +struct dim_cq_moder { u16 usec; u16 pkts; u8 cq_period_mode; }; -struct net_dim_sample { +struct dim_sample { ktime_t time; u32 pkt_ctr; u32 byte_ctr; @@ -33,10 +33,10 @@ struct dim_stats { int epms; /* events per msec */ }; -struct net_dim { /* Dynamic Interrupt Moderation */ +struct dim { /* Dynamic Interrupt Moderation */ u8 state; struct dim_stats prev_stats; - struct net_dim_sample start_sample; + struct dim_sample start_sample; struct work_struct work; u8 profile_ix; u8 mode; @@ -77,7 +77,7 @@ enum { DIM_ON_EDGE, }; -static inline bool dim_on_top(struct net_dim *dim) +static inline bool dim_on_top(struct dim *dim) { switch (dim->tune_state) { case DIM_PARKING_ON_TOP: @@ -90,7 +90,7 @@ static inline bool dim_on_top(struct net_dim *dim) } } -static inline void dim_turn(struct net_dim *dim) +static inline void dim_turn(struct dim *dim) { switch (dim->tune_state) { case DIM_PARKING_ON_TOP: @@ -107,7 +107,7 @@ static inline void dim_turn(struct net_dim *dim) } } -static inline void dim_park_on_top(struct net_dim *dim) +static inline void dim_park_on_top(struct dim *dim) { dim->steps_right = 0; dim->steps_left = 0; @@ -115,7 +115,7 @@ static inline void dim_park_on_top(struct net_dim *dim) dim->tune_state = DIM_PARKING_ON_TOP; } -static inline void dim_park_tired(struct net_dim *dim) +static inline void dim_park_tired(struct dim *dim) { dim->steps_right = 0; dim->steps_left = 0; @@ -123,8 +123,7 @@ static inline void dim_park_tired(struct net_dim *dim) } static inline void -net_dim_update_sample(u16 event_ctr, u64 packets, u64 bytes, - struct net_dim_sample *s) +dim_update_sample(u16 event_ctr, u64 packets, u64 bytes, struct dim_sample *s) { s->time = ktime_get(); s->pkt_ctr = packets; @@ -133,7 +132,7 @@ net_dim_update_sample(u16 event_ctr, u64 packets, u64 bytes, } static inline void -dim_calc_stats(struct net_dim_sample *start, struct net_dim_sample *end, +dim_calc_stats(struct dim_sample *start, struct dim_sample *end, struct dim_stats *curr_stats) { /* u32 holds up to 71 minutes, should be enough */ diff --git a/include/linux/net_dim.h b/include/linux/net_dim.h index d4b40adc7fa1..4e009ec193ef 100644 --- a/include/linux/net_dim.h +++ b/include/linux/net_dim.h @@ -77,28 +77,28 @@ {64, 32} \ } -static const struct net_dim_cq_moder +static const struct dim_cq_moder rx_profile[DIM_CQ_PERIOD_NUM_MODES][NET_DIM_PARAMS_NUM_PROFILES] = { NET_DIM_RX_EQE_PROFILES, NET_DIM_RX_CQE_PROFILES, }; -static const struct net_dim_cq_moder +static const struct dim_cq_moder tx_profile[DIM_CQ_PERIOD_NUM_MODES][NET_DIM_PARAMS_NUM_PROFILES] = { NET_DIM_TX_EQE_PROFILES, NET_DIM_TX_CQE_PROFILES, }; -static inline struct net_dim_cq_moder +static inline struct dim_cq_moder net_dim_get_rx_moderation(u8 cq_period_mode, int ix) { - struct net_dim_cq_moder cq_moder = rx_profile[cq_period_mode][ix]; + struct dim_cq_moder cq_moder = rx_profile[cq_period_mode][ix]; cq_moder.cq_period_mode = cq_period_mode; return cq_moder; } -static inline struct net_dim_cq_moder +static inline struct dim_cq_moder net_dim_get_def_rx_moderation(u8 cq_period_mode) { u8 profile_ix = cq_period_mode == DIM_CQ_PERIOD_MODE_START_FROM_CQE ? @@ -107,16 +107,16 @@ net_dim_get_def_rx_moderation(u8 cq_period_mode) return net_dim_get_rx_moderation(cq_period_mode, profile_ix); } -static inline struct net_dim_cq_moder +static inline struct dim_cq_moder net_dim_get_tx_moderation(u8 cq_period_mode, int ix) { - struct net_dim_cq_moder cq_moder = tx_profile[cq_period_mode][ix]; + struct dim_cq_moder cq_moder = tx_profile[cq_period_mode][ix]; cq_moder.cq_period_mode = cq_period_mode; return cq_moder; } -static inline struct net_dim_cq_moder +static inline struct dim_cq_moder net_dim_get_def_tx_moderation(u8 cq_period_mode) { u8 profile_ix = cq_period_mode == DIM_CQ_PERIOD_MODE_START_FROM_CQE ? @@ -125,7 +125,7 @@ net_dim_get_def_tx_moderation(u8 cq_period_mode) return net_dim_get_tx_moderation(cq_period_mode, profile_ix); } -static inline int net_dim_step(struct net_dim *dim) +static inline int net_dim_step(struct dim *dim) { if (dim->tired == (NET_DIM_PARAMS_NUM_PROFILES * 2)) return DIM_TOO_TIRED; @@ -152,7 +152,7 @@ static inline int net_dim_step(struct net_dim *dim) return DIM_STEPPED; } -static inline void net_dim_exit_parking(struct net_dim *dim) +static inline void net_dim_exit_parking(struct dim *dim) { dim->tune_state = dim->profile_ix ? DIM_GOING_LEFT : DIM_GOING_RIGHT; @@ -189,7 +189,7 @@ static inline int net_dim_stats_compare(struct dim_stats *curr, } static inline bool net_dim_decision(struct dim_stats *curr_stats, - struct net_dim *dim) + struct dim *dim) { int prev_state = dim->tune_state; int prev_ix = dim->profile_ix; @@ -240,8 +240,8 @@ static inline bool net_dim_decision(struct dim_stats *curr_stats, return dim->profile_ix != prev_ix; } -static inline void net_dim(struct net_dim *dim, - struct net_dim_sample end_sample) +static inline void net_dim(struct dim *dim, + struct dim_sample end_sample) { struct dim_stats curr_stats; u16 nevents; @@ -261,8 +261,8 @@ static inline void net_dim(struct net_dim *dim, } /* fall through */ case DIM_START_MEASURE: - net_dim_update_sample(end_sample.event_ctr, end_sample.pkt_ctr, - end_sample.byte_ctr, &dim->start_sample); + dim_update_sample(end_sample.event_ctr, end_sample.pkt_ctr, + end_sample.byte_ctr, &dim->start_sample); dim->state = DIM_MEASURE_IN_PROGRESS; break; case DIM_APPLY_NEW_PROFILE: -- cgit v1.2.3 From 4f75da3666c0c572967729a2401ac650be5581b6 Mon Sep 17 00:00:00 2001 From: Tal Gilboa Date: Thu, 10 Jan 2019 17:33:17 +0200 Subject: linux/dim: Move implementation to .c files Moved all logic from dim.h and net_dim.h to dim.c and net_dim.c. This is both more structurally appealing and would allow to only expose externally used functions. Signed-off-by: Tal Gilboa Signed-off-by: Saeed Mahameed --- include/linux/dim.h | 319 ++++++++++++++++++++++++++++++++++++++---------- include/linux/net_dim.h | 273 ----------------------------------------- 2 files changed, 255 insertions(+), 337 deletions(-) delete mode 100644 include/linux/net_dim.h (limited to 'include') diff --git a/include/linux/dim.h b/include/linux/dim.h index 60e5074a7cc0..f48ede3e0322 100644 --- a/include/linux/dim.h +++ b/include/linux/dim.h @@ -6,20 +6,49 @@ #include +/** + * Number of events between DIM iterations. + * Causes a moderation of the algorithm run. + */ #define DIM_NEVENTS 64 -/* more than 10% difference */ +/** + * Is a difference between values justifies taking an action. + * We consider 10% difference as significant. + */ #define IS_SIGNIFICANT_DIFF(val, ref) \ (((100UL * abs((val) - (ref))) / (ref)) > 10) + +/** + * Calculate the gap between two values. + * Take wrap-around and variable size into consideration. + */ #define BIT_GAP(bits, end, start) ((((end) - (start)) + BIT_ULL(bits)) \ -& (BIT_ULL(bits) - 1)) + & (BIT_ULL(bits) - 1)) +/** + * Structure for CQ moderation values. + * Used for communications between DIM and its consumer. + * + * @usec: CQ timer suggestion (by DIM) + * @pkts: CQ packet counter suggestion (by DIM) + * @cq_period_mode: CQ priod count mode (from CQE/EQE) + */ struct dim_cq_moder { u16 usec; u16 pkts; u8 cq_period_mode; }; +/** + * Structure for DIM sample data. + * Used for communications between DIM and its consumer. + * + * @time: Sample timestamp + * @pkt_ctr: Number of packets + * @byte_ctr: Number of bytes + * @event_ctr: Number of events + */ struct dim_sample { ktime_t time; u32 pkt_ctr; @@ -27,13 +56,36 @@ struct dim_sample { u16 event_ctr; }; +/** + * Structure for DIM stats. + * Used for holding current measured rates. + * + * @ppms: Packets per msec + * @bpms: Bytes per msec + * @epms: Events per msec + */ struct dim_stats { - int ppms; /* packets per msec */ - int bpms; /* bytes per msec */ - int epms; /* events per msec */ + int ppms; + int bpms; + int epms; }; -struct dim { /* Dynamic Interrupt Moderation */ +/** + * Main structure for dynamic interrupt moderation (DIM). + * Used for holding all information about a specific DIM instance. + * + * @state: Algorithm state (see below) + * @prev_stats: Measured rates from previous iteration (for comparison) + * @start_sample: Sampled data at start of current iteration + * @work: Work to perform on action required + * @profile_ix: Current moderation profile + * @mode: CQ period count mode + * @tune_state: Algorithm tuning state (see below) + * @steps_right: Number of steps taken towards higher moderation + * @steps_left: Number of steps taken towards lower moderation + * @tired: Parking depth counter + */ +struct dim { u8 state; struct dim_stats prev_stats; struct dim_sample start_sample; @@ -46,18 +98,49 @@ struct dim { /* Dynamic Interrupt Moderation */ u8 tired; }; +/** + * enum dim_cq_period_mode + * + * These are the modes for CQ period count. + * + * @DIM_CQ_PERIOD_MODE_START_FROM_EQE: Start counting from EQE + * @DIM_CQ_PERIOD_MODE_START_FROM_CQE: Start counting from CQE (implies timer reset) + * @DIM_CQ_PERIOD_NUM_MODES: Number of modes + */ enum { DIM_CQ_PERIOD_MODE_START_FROM_EQE = 0x0, DIM_CQ_PERIOD_MODE_START_FROM_CQE = 0x1, DIM_CQ_PERIOD_NUM_MODES }; +/** + * enum dim_state + * + * These are the DIM algorithm states. + * These will determine if the algorithm is in a valid state to start an iteration. + * + * @DIM_START_MEASURE: This is the first iteration (also after applying a new profile) + * @DIM_MEASURE_IN_PROGRESS: Algorithm is already in progress - check if + * need to perform an action + * @DIM_APPLY_NEW_PROFILE: DIM consumer is currently applying a profile - no need to measure + */ enum { DIM_START_MEASURE, DIM_MEASURE_IN_PROGRESS, DIM_APPLY_NEW_PROFILE, }; +/** + * enum dim_tune_state + * + * These are the DIM algorithm tune states. + * These will determine which action the algorithm should perform. + * + * @DIM_PARKING_ON_TOP: Algorithm found a local top point - exit on significant difference + * @DIM_PARKING_TIRED: Algorithm found a deep top point - don't exit if tired > 0 + * @DIM_GOING_RIGHT: Algorithm is currently trying higher moderation levels + * @DIM_GOING_LEFT: Algorithm is currently trying lower moderation levels + */ enum { DIM_PARKING_ON_TOP, DIM_PARKING_TIRED, @@ -65,63 +148,95 @@ enum { DIM_GOING_LEFT, }; +/** + * enum dim_stats_state + * + * These are the DIM algorithm statistics states. + * These will determine the verdict of current iteration. + * + * @DIM_STATS_WORSE: Current iteration shows worse performance than before + * @DIM_STATS_WORSE: Current iteration shows same performance than before + * @DIM_STATS_WORSE: Current iteration shows better performance than before + */ enum { DIM_STATS_WORSE, DIM_STATS_SAME, DIM_STATS_BETTER, }; +/** + * enum dim_step_result + * + * These are the DIM algorithm step results. + * These describe the result of a step. + * + * @DIM_STEPPED: Performed a regular step + * @DIM_TOO_TIRED: Same kind of step was done multiple times - should go to + * tired parking + * @DIM_ON_EDGE: Stepped to the most left/right profile + */ enum { DIM_STEPPED, DIM_TOO_TIRED, DIM_ON_EDGE, }; -static inline bool dim_on_top(struct dim *dim) -{ - switch (dim->tune_state) { - case DIM_PARKING_ON_TOP: - case DIM_PARKING_TIRED: - return true; - case DIM_GOING_RIGHT: - return (dim->steps_left > 1) && (dim->steps_right == 1); - default: /* DIM_GOING_LEFT */ - return (dim->steps_right > 1) && (dim->steps_left == 1); - } -} +/** + * dim_on_top - check if current state is a good place to stop (top location) + * @dim: DIM context + * + * Check if current profile is a good place to park at. + * This will result in reducing the DIM checks frequency as we assume we + * shouldn't probably change profiles, unless traffic pattern wasn't changed. + */ +bool dim_on_top(struct dim *dim); -static inline void dim_turn(struct dim *dim) -{ - switch (dim->tune_state) { - case DIM_PARKING_ON_TOP: - case DIM_PARKING_TIRED: - break; - case DIM_GOING_RIGHT: - dim->tune_state = DIM_GOING_LEFT; - dim->steps_left = 0; - break; - case DIM_GOING_LEFT: - dim->tune_state = DIM_GOING_RIGHT; - dim->steps_right = 0; - break; - } -} +/** + * dim_turn - change profile alterning direction + * @dim: DIM context + * + * Go left if we were going right and vice-versa. + * Do nothing if currently parking. + */ +void dim_turn(struct dim *dim); -static inline void dim_park_on_top(struct dim *dim) -{ - dim->steps_right = 0; - dim->steps_left = 0; - dim->tired = 0; - dim->tune_state = DIM_PARKING_ON_TOP; -} +/** + * dim_park_on_top - enter a parking state on a top location + * @dim: DIM context + * + * Enter parking state. + * Clear all movement history. + */ +void dim_park_on_top(struct dim *dim); -static inline void dim_park_tired(struct dim *dim) -{ - dim->steps_right = 0; - dim->steps_left = 0; - dim->tune_state = DIM_PARKING_TIRED; -} +/** + * dim_park_tired - enter a tired parking state + * @dim: DIM context + * + * Enter parking state. + * Clear all movement history and cause DIM checks frequency to reduce. + */ +void dim_park_tired(struct dim *dim); + +/** + * dim_calc_stats - calculate the difference between two samples + * @start: start sample + * @end: end sample + * @curr_stats: delta between samples + * + * Calculate the delta between two samples (in data rates). + * Takes into consideration counter wrap-around. + */ +void dim_calc_stats(struct dim_sample *start, struct dim_sample *end, + struct dim_stats *curr_stats); +/** + * dim_update_sample - set a sample's fields with give values + * @event_ctr: number of events to set + * @packets: number of packets to set + * @bytes: number of bytes to set + * @s: DIM sample + */ static inline void dim_update_sample(u16 event_ctr, u64 packets, u64 bytes, struct dim_sample *s) { @@ -131,23 +246,99 @@ dim_update_sample(u16 event_ctr, u64 packets, u64 bytes, struct dim_sample *s) s->event_ctr = event_ctr; } -static inline void -dim_calc_stats(struct dim_sample *start, struct dim_sample *end, - struct dim_stats *curr_stats) -{ - /* u32 holds up to 71 minutes, should be enough */ - u32 delta_us = ktime_us_delta(end->time, start->time); - u32 npkts = BIT_GAP(BITS_PER_TYPE(u32), end->pkt_ctr, start->pkt_ctr); - u32 nbytes = BIT_GAP(BITS_PER_TYPE(u32), end->byte_ctr, - start->byte_ctr); - - if (!delta_us) - return; - - curr_stats->ppms = DIV_ROUND_UP(npkts * USEC_PER_MSEC, delta_us); - curr_stats->bpms = DIV_ROUND_UP(nbytes * USEC_PER_MSEC, delta_us); - curr_stats->epms = DIV_ROUND_UP(DIM_NEVENTS * USEC_PER_MSEC, - delta_us); +/* Net DIM */ + +/* + * Net DIM profiles: + * There are different set of profiles for each CQ period mode. + * There are different set of profiles for RX/TX CQs. + * Each profile size must be of NET_DIM_PARAMS_NUM_PROFILES + */ +#define NET_DIM_PARAMS_NUM_PROFILES 5 +#define NET_DIM_DEFAULT_RX_CQ_MODERATION_PKTS_FROM_EQE 256 +#define NET_DIM_DEFAULT_TX_CQ_MODERATION_PKTS_FROM_EQE 128 +#define NET_DIM_DEF_PROFILE_CQE 1 +#define NET_DIM_DEF_PROFILE_EQE 1 + +#define NET_DIM_RX_EQE_PROFILES { \ + {1, NET_DIM_DEFAULT_RX_CQ_MODERATION_PKTS_FROM_EQE}, \ + {8, NET_DIM_DEFAULT_RX_CQ_MODERATION_PKTS_FROM_EQE}, \ + {64, NET_DIM_DEFAULT_RX_CQ_MODERATION_PKTS_FROM_EQE}, \ + {128, NET_DIM_DEFAULT_RX_CQ_MODERATION_PKTS_FROM_EQE}, \ + {256, NET_DIM_DEFAULT_RX_CQ_MODERATION_PKTS_FROM_EQE}, \ } +#define NET_DIM_RX_CQE_PROFILES { \ + {2, 256}, \ + {8, 128}, \ + {16, 64}, \ + {32, 64}, \ + {64, 64} \ +} + +#define NET_DIM_TX_EQE_PROFILES { \ + {1, NET_DIM_DEFAULT_TX_CQ_MODERATION_PKTS_FROM_EQE}, \ + {8, NET_DIM_DEFAULT_TX_CQ_MODERATION_PKTS_FROM_EQE}, \ + {32, NET_DIM_DEFAULT_TX_CQ_MODERATION_PKTS_FROM_EQE}, \ + {64, NET_DIM_DEFAULT_TX_CQ_MODERATION_PKTS_FROM_EQE}, \ + {128, NET_DIM_DEFAULT_TX_CQ_MODERATION_PKTS_FROM_EQE} \ +} + +#define NET_DIM_TX_CQE_PROFILES { \ + {5, 128}, \ + {8, 64}, \ + {16, 32}, \ + {32, 32}, \ + {64, 32} \ +} + +static const struct dim_cq_moder +rx_profile[DIM_CQ_PERIOD_NUM_MODES][NET_DIM_PARAMS_NUM_PROFILES] = { + NET_DIM_RX_EQE_PROFILES, + NET_DIM_RX_CQE_PROFILES, +}; + +static const struct dim_cq_moder +tx_profile[DIM_CQ_PERIOD_NUM_MODES][NET_DIM_PARAMS_NUM_PROFILES] = { + NET_DIM_TX_EQE_PROFILES, + NET_DIM_TX_CQE_PROFILES, +}; + +/** + * net_dim_get_rx_moderation - provide a CQ moderation object for the given RX profile + * @cq_period_mode: CQ period mode + * @ix: Profile index + */ +struct dim_cq_moder net_dim_get_rx_moderation(u8 cq_period_mode, int ix); + +/** + * net_dim_get_def_rx_moderation - provide the default RX moderation + * @cq_period_mode: CQ period mode + */ +struct dim_cq_moder net_dim_get_def_rx_moderation(u8 cq_period_mode); + +/** + * net_dim_get_tx_moderation - provide a CQ moderation object for the given TX profile + * @cq_period_mode: CQ period mode + * @ix: Profile index + */ +struct dim_cq_moder net_dim_get_tx_moderation(u8 cq_period_mode, int ix); + +/** + * net_dim_get_def_tx_moderation - provide the default TX moderation + * @cq_period_mode: CQ period mode + */ +struct dim_cq_moder net_dim_get_def_tx_moderation(u8 cq_period_mode); + +/** + * net_dim - main DIM algorithm entry point + * @dim: DIM instance information + * @end_sample: Current data measurement + * + * Called by the consumer. + * This is the main logic of the algorithm, where data is processed in order to decide on next + * required action. + */ +void net_dim(struct dim *dim, struct dim_sample end_sample); + #endif /* DIM_H */ diff --git a/include/linux/net_dim.h b/include/linux/net_dim.h deleted file mode 100644 index 4e009ec193ef..000000000000 --- a/include/linux/net_dim.h +++ /dev/null @@ -1,273 +0,0 @@ -/* - * Copyright (c) 2016, Mellanox Technologies. All rights reserved. - * Copyright (c) 2017-2018, Broadcom Limited. All rights reserved. - * - * This software is available to you under a choice of one of two - * licenses. You may choose to be licensed 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, or the - * OpenIB.org BSD license below: - * - * Redistribution and use in source and binary forms, with or - * without modification, are permitted provided that the following - * conditions are met: - * - * - Redistributions of source code must retain the above - * copyright notice, this list of conditions and the following - * disclaimer. - * - * - Redistributions in binary form must reproduce the above - * copyright notice, this list of conditions and the following - * disclaimer in the documentation and/or other materials - * provided with the distribution. - * - * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, - * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF - * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND - * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS - * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN - * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN - * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE - * SOFTWARE. - */ - -#ifndef NET_DIM_H -#define NET_DIM_H - -#include -#include - -#define NET_DIM_PARAMS_NUM_PROFILES 5 -/* Netdev dynamic interrupt moderation profiles */ -#define NET_DIM_DEFAULT_RX_CQ_MODERATION_PKTS_FROM_EQE 256 -#define NET_DIM_DEFAULT_TX_CQ_MODERATION_PKTS_FROM_EQE 128 -#define NET_DIM_DEF_PROFILE_CQE 1 -#define NET_DIM_DEF_PROFILE_EQE 1 - -/* All profiles sizes must be NET_PARAMS_DIM_NUM_PROFILES */ -#define NET_DIM_RX_EQE_PROFILES { \ - {1, NET_DIM_DEFAULT_RX_CQ_MODERATION_PKTS_FROM_EQE}, \ - {8, NET_DIM_DEFAULT_RX_CQ_MODERATION_PKTS_FROM_EQE}, \ - {64, NET_DIM_DEFAULT_RX_CQ_MODERATION_PKTS_FROM_EQE}, \ - {128, NET_DIM_DEFAULT_RX_CQ_MODERATION_PKTS_FROM_EQE}, \ - {256, NET_DIM_DEFAULT_RX_CQ_MODERATION_PKTS_FROM_EQE}, \ -} - -#define NET_DIM_RX_CQE_PROFILES { \ - {2, 256}, \ - {8, 128}, \ - {16, 64}, \ - {32, 64}, \ - {64, 64} \ -} - -#define NET_DIM_TX_EQE_PROFILES { \ - {1, NET_DIM_DEFAULT_TX_CQ_MODERATION_PKTS_FROM_EQE}, \ - {8, NET_DIM_DEFAULT_TX_CQ_MODERATION_PKTS_FROM_EQE}, \ - {32, NET_DIM_DEFAULT_TX_CQ_MODERATION_PKTS_FROM_EQE}, \ - {64, NET_DIM_DEFAULT_TX_CQ_MODERATION_PKTS_FROM_EQE}, \ - {128, NET_DIM_DEFAULT_TX_CQ_MODERATION_PKTS_FROM_EQE} \ -} - -#define NET_DIM_TX_CQE_PROFILES { \ - {5, 128}, \ - {8, 64}, \ - {16, 32}, \ - {32, 32}, \ - {64, 32} \ -} - -static const struct dim_cq_moder -rx_profile[DIM_CQ_PERIOD_NUM_MODES][NET_DIM_PARAMS_NUM_PROFILES] = { - NET_DIM_RX_EQE_PROFILES, - NET_DIM_RX_CQE_PROFILES, -}; - -static const struct dim_cq_moder -tx_profile[DIM_CQ_PERIOD_NUM_MODES][NET_DIM_PARAMS_NUM_PROFILES] = { - NET_DIM_TX_EQE_PROFILES, - NET_DIM_TX_CQE_PROFILES, -}; - -static inline struct dim_cq_moder -net_dim_get_rx_moderation(u8 cq_period_mode, int ix) -{ - struct dim_cq_moder cq_moder = rx_profile[cq_period_mode][ix]; - - cq_moder.cq_period_mode = cq_period_mode; - return cq_moder; -} - -static inline struct dim_cq_moder -net_dim_get_def_rx_moderation(u8 cq_period_mode) -{ - u8 profile_ix = cq_period_mode == DIM_CQ_PERIOD_MODE_START_FROM_CQE ? - NET_DIM_DEF_PROFILE_CQE : NET_DIM_DEF_PROFILE_EQE; - - return net_dim_get_rx_moderation(cq_period_mode, profile_ix); -} - -static inline struct dim_cq_moder -net_dim_get_tx_moderation(u8 cq_period_mode, int ix) -{ - struct dim_cq_moder cq_moder = tx_profile[cq_period_mode][ix]; - - cq_moder.cq_period_mode = cq_period_mode; - return cq_moder; -} - -static inline struct dim_cq_moder -net_dim_get_def_tx_moderation(u8 cq_period_mode) -{ - u8 profile_ix = cq_period_mode == DIM_CQ_PERIOD_MODE_START_FROM_CQE ? - NET_DIM_DEF_PROFILE_CQE : NET_DIM_DEF_PROFILE_EQE; - - return net_dim_get_tx_moderation(cq_period_mode, profile_ix); -} - -static inline int net_dim_step(struct dim *dim) -{ - if (dim->tired == (NET_DIM_PARAMS_NUM_PROFILES * 2)) - return DIM_TOO_TIRED; - - switch (dim->tune_state) { - case DIM_PARKING_ON_TOP: - case DIM_PARKING_TIRED: - break; - case DIM_GOING_RIGHT: - if (dim->profile_ix == (NET_DIM_PARAMS_NUM_PROFILES - 1)) - return DIM_ON_EDGE; - dim->profile_ix++; - dim->steps_right++; - break; - case DIM_GOING_LEFT: - if (dim->profile_ix == 0) - return DIM_ON_EDGE; - dim->profile_ix--; - dim->steps_left++; - break; - } - - dim->tired++; - return DIM_STEPPED; -} - -static inline void net_dim_exit_parking(struct dim *dim) -{ - dim->tune_state = dim->profile_ix ? DIM_GOING_LEFT : - DIM_GOING_RIGHT; - net_dim_step(dim); -} - -static inline int net_dim_stats_compare(struct dim_stats *curr, - struct dim_stats *prev) -{ - if (!prev->bpms) - return curr->bpms ? DIM_STATS_BETTER : - DIM_STATS_SAME; - - if (IS_SIGNIFICANT_DIFF(curr->bpms, prev->bpms)) - return (curr->bpms > prev->bpms) ? DIM_STATS_BETTER : - DIM_STATS_WORSE; - - if (!prev->ppms) - return curr->ppms ? DIM_STATS_BETTER : - DIM_STATS_SAME; - - if (IS_SIGNIFICANT_DIFF(curr->ppms, prev->ppms)) - return (curr->ppms > prev->ppms) ? DIM_STATS_BETTER : - DIM_STATS_WORSE; - - if (!prev->epms) - return DIM_STATS_SAME; - - if (IS_SIGNIFICANT_DIFF(curr->epms, prev->epms)) - return (curr->epms < prev->epms) ? DIM_STATS_BETTER : - DIM_STATS_WORSE; - - return DIM_STATS_SAME; -} - -static inline bool net_dim_decision(struct dim_stats *curr_stats, - struct dim *dim) -{ - int prev_state = dim->tune_state; - int prev_ix = dim->profile_ix; - int stats_res; - int step_res; - - switch (dim->tune_state) { - case DIM_PARKING_ON_TOP: - stats_res = net_dim_stats_compare(curr_stats, &dim->prev_stats); - if (stats_res != DIM_STATS_SAME) - net_dim_exit_parking(dim); - break; - - case DIM_PARKING_TIRED: - dim->tired--; - if (!dim->tired) - net_dim_exit_parking(dim); - break; - - case DIM_GOING_RIGHT: - case DIM_GOING_LEFT: - stats_res = net_dim_stats_compare(curr_stats, &dim->prev_stats); - if (stats_res != DIM_STATS_BETTER) - dim_turn(dim); - - if (dim_on_top(dim)) { - dim_park_on_top(dim); - break; - } - - step_res = net_dim_step(dim); - switch (step_res) { - case DIM_ON_EDGE: - dim_park_on_top(dim); - break; - case DIM_TOO_TIRED: - dim_park_tired(dim); - break; - } - - break; - } - - if (prev_state != DIM_PARKING_ON_TOP || - dim->tune_state != DIM_PARKING_ON_TOP) - dim->prev_stats = *curr_stats; - - return dim->profile_ix != prev_ix; -} - -static inline void net_dim(struct dim *dim, - struct dim_sample end_sample) -{ - struct dim_stats curr_stats; - u16 nevents; - - switch (dim->state) { - case DIM_MEASURE_IN_PROGRESS: - nevents = BIT_GAP(BITS_PER_TYPE(u16), - end_sample.event_ctr, - dim->start_sample.event_ctr); - if (nevents < DIM_NEVENTS) - break; - dim_calc_stats(&dim->start_sample, &end_sample, &curr_stats); - if (net_dim_decision(&curr_stats, dim)) { - dim->state = DIM_APPLY_NEW_PROFILE; - schedule_work(&dim->work); - break; - } - /* fall through */ - case DIM_START_MEASURE: - dim_update_sample(end_sample.event_ctr, end_sample.pkt_ctr, - end_sample.byte_ctr, &dim->start_sample); - dim->state = DIM_MEASURE_IN_PROGRESS; - break; - case DIM_APPLY_NEW_PROFILE: - break; - } -} - -#endif /* NET_DIM_H */ -- cgit v1.2.3 From 398c2b05bbee21cc172dfff017c0351d4d14e04c Mon Sep 17 00:00:00 2001 From: Yamin Friedman Date: Thu, 22 Nov 2018 09:51:17 +0200 Subject: linux/dim: Add completions count to dim_sample Added a measurement of completions per/msec to allow for completion based dim algorithms. In order to use dynamic interrupt moderation with RDMA we need to have a different measurment than packets per second. This change is meant to prepare for adding a new DIM method. All drivers that use net_dim and thus do not need a completion count will have the completions set to 0. Signed-off-by: Yamin Friedman Reviewed-by: Max Gurtovoy Signed-off-by: Saeed Mahameed --- include/linux/dim.h | 28 +++++++++++++++++++++++++--- 1 file changed, 25 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/include/linux/dim.h b/include/linux/dim.h index f48ede3e0322..aa9bdd47a648 100644 --- a/include/linux/dim.h +++ b/include/linux/dim.h @@ -37,6 +37,7 @@ struct dim_cq_moder { u16 usec; u16 pkts; + u16 comps; u8 cq_period_mode; }; @@ -54,6 +55,7 @@ struct dim_sample { u32 pkt_ctr; u32 byte_ctr; u16 event_ctr; + u32 comp_ctr; }; /** @@ -65,9 +67,11 @@ struct dim_sample { * @epms: Events per msec */ struct dim_stats { - int ppms; - int bpms; - int epms; + int ppms; /* packets per msec */ + int bpms; /* bytes per msec */ + int epms; /* events per msec */ + int cpms; /* completions per msec */ + int cpe_ratio; /* ratio of completions to events */ }; /** @@ -89,6 +93,7 @@ struct dim { u8 state; struct dim_stats prev_stats; struct dim_sample start_sample; + struct dim_sample measuring_sample; struct work_struct work; u8 profile_ix; u8 mode; @@ -246,6 +251,23 @@ dim_update_sample(u16 event_ctr, u64 packets, u64 bytes, struct dim_sample *s) s->event_ctr = event_ctr; } +/** + * dim_update_sample_with_comps - set a sample's fields with given + * values including the completion parameter + * @event_ctr: number of events to set + * @packets: number of packets to set + * @bytes: number of bytes to set + * @comps: number of completions to set + * @s: DIM sample + */ +static inline void +dim_update_sample_with_comps(u16 event_ctr, u64 packets, u64 bytes, u64 comps, + struct dim_sample *s) +{ + dim_update_sample(event_ctr, packets, bytes, s); + s->comp_ctr = comps; +} + /* Net DIM */ /* -- cgit v1.2.3 From 4ae4916b56435d1d5066616120f9ff907bd96b86 Mon Sep 17 00:00:00 2001 From: Aleksandr Loktionov Date: Tue, 28 May 2019 10:59:15 -0700 Subject: i40e: fix 'Unknown bps' in dmesg for 2.5Gb/5Gb speeds This patch fixes 'NIC Link is Up, Unknown bps' message in dmesg for 2.5Gb/5Gb speeds. This problem is fixed by adding constants for VIRTCHNL_LINK_SPEED_2_5GB and VIRTCHNL_LINK_SPEED_5GB cases in the i40e_virtchnl_link_speed() function. Signed-off-by: Aleksandr Loktionov Tested-by: Andrew Bowers Signed-off-by: Jeff Kirsher --- include/linux/avf/virtchnl.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include') diff --git a/include/linux/avf/virtchnl.h b/include/linux/avf/virtchnl.h index 191621ff7594..ca956b672ac0 100644 --- a/include/linux/avf/virtchnl.h +++ b/include/linux/avf/virtchnl.h @@ -61,12 +61,14 @@ enum virtchnl_status_code { #define VIRTCHNL_ERR_PARAM VIRTCHNL_STATUS_ERR_PARAM #define VIRTCHNL_STATUS_NOT_SUPPORTED VIRTCHNL_STATUS_ERR_NOT_SUPPORTED +#define VIRTCHNL_LINK_SPEED_2_5GB_SHIFT 0x0 #define VIRTCHNL_LINK_SPEED_100MB_SHIFT 0x1 #define VIRTCHNL_LINK_SPEED_1000MB_SHIFT 0x2 #define VIRTCHNL_LINK_SPEED_10GB_SHIFT 0x3 #define VIRTCHNL_LINK_SPEED_40GB_SHIFT 0x4 #define VIRTCHNL_LINK_SPEED_20GB_SHIFT 0x5 #define VIRTCHNL_LINK_SPEED_25GB_SHIFT 0x6 +#define VIRTCHNL_LINK_SPEED_5GB_SHIFT 0x7 enum virtchnl_link_speed { VIRTCHNL_LINK_SPEED_UNKNOWN = 0, @@ -76,6 +78,8 @@ enum virtchnl_link_speed { VIRTCHNL_LINK_SPEED_40GB = BIT(VIRTCHNL_LINK_SPEED_40GB_SHIFT), VIRTCHNL_LINK_SPEED_20GB = BIT(VIRTCHNL_LINK_SPEED_20GB_SHIFT), VIRTCHNL_LINK_SPEED_25GB = BIT(VIRTCHNL_LINK_SPEED_25GB_SHIFT), + VIRTCHNL_LINK_SPEED_2_5GB = BIT(VIRTCHNL_LINK_SPEED_2_5GB_SHIFT), + VIRTCHNL_LINK_SPEED_5GB = BIT(VIRTCHNL_LINK_SPEED_5GB_SHIFT), }; /* for hsplit_0 field of Rx HMC context */ -- cgit v1.2.3 From 65c0f2c1663649217455a73d48b1c303f133180a Mon Sep 17 00:00:00 2001 From: Jianbo Liu Date: Tue, 25 Jun 2019 17:47:50 +0000 Subject: net/mlx5: Introduce vport metadata matching bits and enum constants When a dual-port VHCA sends a RoCE packet on its non-native port, and the packet arrives to its affiliated vport FDB, a mismatch might occur on the rules that match the packet source vport. So we replace the match on source port with the match on metadata that was configured in ingress ACL, and that metadata will be passed further also to the NIC RX table of the eswitch manager. Introduce vport metadata matching bits and enum constants as a pre-step towards metadata matching. o metadata type C registers in the misc parameters 2 fields. o esw_uplink_ingress_acl bit in esw cap. If it set, the device supports ingress ACL for the uplink vport. o fdb_to_vport_reg_* bits in flow table cap and esw vport context, to support propagating the metadata to the nic rx through the loopback path. o flow_source in flow context, to indicate the known origin of packets. o enum constants, to support the above bits. Signed-off-by: Jianbo Liu Reviewed-by: Eli Britstein Reviewed-by: Roi Dayan Reviewed-by: Mark Bloch Signed-off-by: Saeed Mahameed --- include/linux/mlx5/mlx5_ifc.h | 56 +++++++++++++++++++++++++++++++++++++------ 1 file changed, 49 insertions(+), 7 deletions(-) (limited to 'include') diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h index e3c154b573a2..d4409654f760 100644 --- a/include/linux/mlx5/mlx5_ifc.h +++ b/include/linux/mlx5/mlx5_ifc.h @@ -528,7 +528,21 @@ struct mlx5_ifc_fte_match_set_misc2_bits { struct mlx5_ifc_fte_match_mpls_bits outer_first_mpls_over_udp; - u8 reserved_at_80[0x100]; + u8 metadata_reg_c_7[0x20]; + + u8 metadata_reg_c_6[0x20]; + + u8 metadata_reg_c_5[0x20]; + + u8 metadata_reg_c_4[0x20]; + + u8 metadata_reg_c_3[0x20]; + + u8 metadata_reg_c_2[0x20]; + + u8 metadata_reg_c_1[0x20]; + + u8 metadata_reg_c_0[0x20]; u8 metadata_reg_a[0x20]; @@ -636,8 +650,22 @@ struct mlx5_ifc_flow_table_nic_cap_bits { u8 reserved_at_e00[0x7200]; }; +enum { + MLX5_FDB_TO_VPORT_REG_C_0 = 0x01, + MLX5_FDB_TO_VPORT_REG_C_1 = 0x02, + MLX5_FDB_TO_VPORT_REG_C_2 = 0x04, + MLX5_FDB_TO_VPORT_REG_C_3 = 0x08, + MLX5_FDB_TO_VPORT_REG_C_4 = 0x10, + MLX5_FDB_TO_VPORT_REG_C_5 = 0x20, + MLX5_FDB_TO_VPORT_REG_C_6 = 0x40, + MLX5_FDB_TO_VPORT_REG_C_7 = 0x80, +}; + struct mlx5_ifc_flow_table_eswitch_cap_bits { - u8 reserved_at_0[0x1a]; + u8 fdb_to_vport_reg_c_id[0x8]; + u8 reserved_at_8[0xf]; + u8 flow_source[0x1]; + u8 reserved_at_18[0x2]; u8 multi_fdb_encap[0x1]; u8 reserved_at_1b[0x1]; u8 fdb_multi_path_to_table[0x1]; @@ -665,7 +693,9 @@ struct mlx5_ifc_e_switch_cap_bits { u8 vport_svlan_insert[0x1]; u8 vport_cvlan_insert_if_not_exist[0x1]; u8 vport_cvlan_insert_overwrite[0x1]; - u8 reserved_at_5[0x14]; + u8 reserved_at_5[0x3]; + u8 esw_uplink_ingress_acl[0x1]; + u8 reserved_at_9[0x10]; u8 esw_functions_changed[0x1]; u8 reserved_at_1a[0x1]; u8 ecpf_vport_exists[0x1]; @@ -2555,6 +2585,12 @@ enum { MLX5_FLOW_CONTEXT_ACTION_VLAN_PUSH_2 = 0x800, }; +enum { + MLX5_FLOW_CONTEXT_FLOW_SOURCE_ANY_VPORT = 0x0, + MLX5_FLOW_CONTEXT_FLOW_SOURCE_UPLINK = 0x1, + MLX5_FLOW_CONTEXT_FLOW_SOURCE_LOCAL_VPORT = 0x2, +}; + struct mlx5_ifc_vlan_bits { u8 ethtype[0x10]; u8 prio[0x3]; @@ -2574,7 +2610,9 @@ struct mlx5_ifc_flow_context_bits { u8 action[0x10]; u8 extended_destination[0x1]; - u8 reserved_at_80[0x7]; + u8 reserved_at_81[0x1]; + u8 flow_source[0x2]; + u8 reserved_at_84[0x4]; u8 destination_list_size[0x18]; u8 reserved_at_a0[0x8]; @@ -3099,12 +3137,14 @@ struct mlx5_ifc_hca_vport_context_bits { }; struct mlx5_ifc_esw_vport_context_bits { - u8 reserved_at_0[0x3]; + u8 fdb_to_vport_reg_c[0x1]; + u8 reserved_at_1[0x2]; u8 vport_svlan_strip[0x1]; u8 vport_cvlan_strip[0x1]; u8 vport_svlan_insert[0x1]; u8 vport_cvlan_insert[0x2]; - u8 reserved_at_8[0x18]; + u8 fdb_to_vport_reg_c_id[0x8]; + u8 reserved_at_10[0x10]; u8 reserved_at_20[0x20]; @@ -4985,7 +5025,8 @@ struct mlx5_ifc_modify_esw_vport_context_out_bits { }; struct mlx5_ifc_esw_vport_context_fields_select_bits { - u8 reserved_at_0[0x1c]; + u8 reserved_at_0[0x1b]; + u8 fdb_to_vport_reg_c_id[0x1]; u8 vport_cvlan_insert[0x1]; u8 vport_svlan_insert[0x1]; u8 vport_cvlan_strip[0x1]; @@ -5182,6 +5223,7 @@ enum { MLX5_ACTION_IN_FIELD_OUT_DIPV4 = 0x16, MLX5_ACTION_IN_FIELD_OUT_FIRST_VID = 0x17, MLX5_ACTION_IN_FIELD_OUT_IPV6_HOPLIMIT = 0x47, + MLX5_ACTION_IN_FIELD_METADATA_REG_C_0 = 0x51, }; struct mlx5_ifc_alloc_modify_header_context_out_bits { -- cgit v1.2.3 From bb0ee7dcc4ecd6af39823b80ae3995ddc119c373 Mon Sep 17 00:00:00 2001 From: Jianbo Liu Date: Tue, 25 Jun 2019 17:47:58 +0000 Subject: net/mlx5: Add flow context for flow tag Refactor the flow data structures, add new flow_context and move flow_tag into it, as flow_tag doesn't belong to the rule action. Signed-off-by: Jianbo Liu Reviewed-by: Mark Bloch Signed-off-by: Saeed Mahameed --- include/linux/mlx5/fs.h | 15 +++++++++++---- 1 file changed, 11 insertions(+), 4 deletions(-) (limited to 'include') diff --git a/include/linux/mlx5/fs.h b/include/linux/mlx5/fs.h index 2ddaa97f2179..9bf49ce218fa 100644 --- a/include/linux/mlx5/fs.h +++ b/include/linux/mlx5/fs.h @@ -88,10 +88,20 @@ struct mlx5_flow_group; struct mlx5_flow_namespace; struct mlx5_flow_handle; +enum { + FLOW_CONTEXT_HAS_TAG = BIT(0), +}; + +struct mlx5_flow_context { + u32 flags; + u32 flow_tag; +}; + struct mlx5_flow_spec { u8 match_criteria_enable; u32 match_criteria[MLX5_ST_SZ_DW(fte_match_param)]; u32 match_value[MLX5_ST_SZ_DW(fte_match_param)]; + struct mlx5_flow_context flow_context; }; enum { @@ -173,13 +183,11 @@ struct mlx5_fs_vlan { #define MLX5_FS_VLAN_DEPTH 2 enum { - FLOW_ACT_HAS_TAG = BIT(0), - FLOW_ACT_NO_APPEND = BIT(1), + FLOW_ACT_NO_APPEND = BIT(0), }; struct mlx5_flow_act { u32 action; - u32 flow_tag; u32 reformat_id; u32 modify_id; uintptr_t esp_id; @@ -190,7 +198,6 @@ struct mlx5_flow_act { #define MLX5_DECLARE_FLOW_ACT(name) \ struct mlx5_flow_act name = { .action = MLX5_FLOW_CONTEXT_ACTION_FWD_DEST,\ - .flow_tag = MLX5_FS_DEFAULT_FLOW_TAG, \ .reformat_id = 0, \ .modify_id = 0, \ .flags = 0, } -- cgit v1.2.3 From 7445cfb1169cebf8f79763acf65f85d850850461 Mon Sep 17 00:00:00 2001 From: Jianbo Liu Date: Tue, 25 Jun 2019 17:48:00 +0000 Subject: net/mlx5: E-Switch, Tag packet with vport number in VF vports and uplink ingress ACLs When a dual-port VHCA sends a RoCE packet on its non-native port, and the packet arrives to its affiliated vport FDB, a mismatch might occur on the rules that match the packet source vport as it is not represented by single VHCA only in this case. So we change to match on metadata instead of source vport. To do that, a rule is created in all vports and uplink ingress ACLs, to save the source vport number and vhca id in the packet's metadata in order to match on it later. The metadata register used is the first of the 32-bit type C registers. It can be used for matching and header modify operations. The higher 16 bits of this register are for vhca id, and the lower 16 ones is for vport number. This change is not for dual-port RoCE only. If HW and FW allow, the vport metadata matching is enabled by default. Signed-off-by: Jianbo Liu Reviewed-by: Eli Britstein Reviewed-by: Roi Dayan Reviewed-by: Mark Bloch Signed-off-by: Saeed Mahameed --- include/linux/mlx5/eswitch.h | 17 +++++++++++++++++ 1 file changed, 17 insertions(+) (limited to 'include') diff --git a/include/linux/mlx5/eswitch.h b/include/linux/mlx5/eswitch.h index 174eec0871d9..aece3ae1902d 100644 --- a/include/linux/mlx5/eswitch.h +++ b/include/linux/mlx5/eswitch.h @@ -67,11 +67,28 @@ mlx5_eswitch_add_send_to_vport_rule(struct mlx5_eswitch *esw, #ifdef CONFIG_MLX5_ESWITCH enum devlink_eswitch_encap_mode mlx5_eswitch_get_encap_mode(const struct mlx5_core_dev *dev); + +bool mlx5_eswitch_vport_match_metadata_enabled(const struct mlx5_eswitch *esw); +u32 mlx5_eswitch_get_vport_metadata_for_match(const struct mlx5_eswitch *esw, + u16 vport_num); #else /* CONFIG_MLX5_ESWITCH */ static inline enum devlink_eswitch_encap_mode mlx5_eswitch_get_encap_mode(const struct mlx5_core_dev *dev) { return DEVLINK_ESWITCH_ENCAP_MODE_NONE; } + +static inline bool +mlx5_eswitch_vport_match_metadata_enabled(const struct mlx5_eswitch *esw) +{ + return false; +}; + +static inline u32 +mlx5_eswitch_get_vport_metadata_for_match(const struct mlx5_eswitch *esw, + int vport_num) +{ + return 0; +}; #endif /* CONFIG_MLX5_ESWITCH */ #endif -- cgit v1.2.3 From 8d212ff057f8b81ed6ed418874b54ded3bf97ad4 Mon Sep 17 00:00:00 2001 From: Jianbo Liu Date: Tue, 25 Jun 2019 17:48:02 +0000 Subject: net/mlx5e: Specifying known origin of packets matching the flow In vport metadata matching, source port number is replaced by metadata. While FW has no idea about what it is in the metadata, a syndrome will happen. Specify a known origin to avoid the syndrome. However, there is no functional change because ANY_VPORT (0) is filled in flow_source, the same default value as before, as a pre-step towards metadata matching for fast path. There are two other values can be filled in flow_source. When setting 0x1, packet matching this rule is from uplink, while 0x2 is for packet from other local vports. Signed-off-by: Jianbo Liu Reviewed-by: Mark Bloch Signed-off-by: Saeed Mahameed --- include/linux/mlx5/fs.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/mlx5/fs.h b/include/linux/mlx5/fs.h index 9bf49ce218fa..dc7e7aa53a13 100644 --- a/include/linux/mlx5/fs.h +++ b/include/linux/mlx5/fs.h @@ -95,6 +95,7 @@ enum { struct mlx5_flow_context { u32 flags; u32 flow_tag; + u32 flow_source; }; struct mlx5_flow_spec { -- cgit v1.2.3 From 96125bf9985a75db00496dd2bc9249b777d2b19b Mon Sep 17 00:00:00 2001 From: Dave Taht Date: Sat, 22 Jun 2019 10:07:34 -0700 Subject: Allow 0.0.0.0/8 as a valid address range MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The longstanding prohibition against using 0.0.0.0/8 dates back to two issues with the early internet. There was an interoperability problem with BSD 4.2 in 1984, fixed in BSD 4.3 in 1986. BSD 4.2 has long since been retired. Secondly, addresses of the form 0.x.y.z were initially defined only as a source address in an ICMP datagram, indicating "node number x.y.z on this IPv4 network", by nodes that know their address on their local network, but do not yet know their network prefix, in RFC0792 (page 19). This usage of 0.x.y.z was later repealed in RFC1122 (section 3.2.2.7), because the original ICMP-based mechanism for learning the network prefix was unworkable on many networks such as Ethernet (which have longer addresses that would not fit into the 24 "node number" bits). Modern networks use reverse ARP (RFC0903) or BOOTP (RFC0951) or DHCP (RFC2131) to find their full 32-bit address and CIDR netmask (and other parameters such as default gateways). 0.x.y.z has had 16,777,215 addresses in 0.0.0.0/8 space left unused and reserved for future use, since 1989. This patch allows for these 16m new IPv4 addresses to appear within a box or on the wire. Layer 2 switches don't care. 0.0.0.0/32 is still prohibited, of course. Signed-off-by: Dave Taht Signed-off-by: John Gilmore Acked-by: Toke Høiland-Jørgensen Signed-off-by: David S. Miller --- include/linux/in.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/in.h b/include/linux/in.h index 4d2fedfb753a..1873ef642605 100644 --- a/include/linux/in.h +++ b/include/linux/in.h @@ -63,7 +63,7 @@ static inline bool ipv4_is_all_snoopers(__be32 addr) static inline bool ipv4_is_zeronet(__be32 addr) { - return (addr & htonl(0xff000000)) == htonl(0x00000000); + return (addr == 0); } /* Special-Use IPv4 Addresses (RFC3330) */ -- cgit v1.2.3 From 61caf3d109f5411a7f5b433f1eb73ead7e0789fa Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Linus=20L=C3=BCssing?= Date: Tue, 11 Jun 2019 22:58:40 +0200 Subject: batman-adv: mcast: detect, distribute and maintain multicast router presence MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit To be able to apply our group aware multicast optimizations to packets with a scope greater than link-local we need to not only keep track of multicast listeners but also multicast routers. With this patch a node detects the presence of multicast routers on its segment by checking if /proc/sys/net/ipv{4,6}/conf//mc_forwarding is set for one thing. This option is enabled by multicast routing daemons and needed for the kernel's multicast routing tables to receive and route packets. For another thing if a bridge is configured on top of bat0 then the presence of an IPv6 multicast router behind this bridge is currently detected by checking for an IPv6 multicast "All Routers Address" (ff02::2). This should later be replaced by querying the bridge, which performs proper, RFC4286 compliant Multicast Router Discovery (our simplified approach includes more hosts than necessary, most notably not just multicast routers but also unicast ones and is not applicable for IPv4). If no multicast router is detected then this is signalized via the new BATADV_MCAST_WANT_NO_RTR4 and BATADV_MCAST_WANT_NO_RTR6 multicast tvlv flags. Signed-off-by: Linus Lüssing Signed-off-by: Sven Eckelmann Signed-off-by: Simon Wunderlich --- include/uapi/linux/batadv_packet.h | 8 ++++++++ 1 file changed, 8 insertions(+) (limited to 'include') diff --git a/include/uapi/linux/batadv_packet.h b/include/uapi/linux/batadv_packet.h index 4ebc2135e950..2a15f01c2243 100644 --- a/include/uapi/linux/batadv_packet.h +++ b/include/uapi/linux/batadv_packet.h @@ -107,12 +107,20 @@ enum batadv_icmp_packettype { * @BATADV_MCAST_WANT_ALL_UNSNOOPABLES: we want all packets destined for * 224.0.0.0/24 or ff02::1 * @BATADV_MCAST_WANT_ALL_IPV4: we want all IPv4 multicast packets + * (both link-local and routable ones) * @BATADV_MCAST_WANT_ALL_IPV6: we want all IPv6 multicast packets + * (both link-local and routable ones) + * @BATADV_MCAST_WANT_NO_RTR4: we have no IPv4 multicast router and therefore + * only need routable IPv4 multicast packets we signed up for explicitly + * @BATADV_MCAST_WANT_NO_RTR6: we have no IPv6 multicast router and therefore + * only need routable IPv6 multicast packets we signed up for explicitly */ enum batadv_mcast_flags { BATADV_MCAST_WANT_ALL_UNSNOOPABLES = 1UL << 0, BATADV_MCAST_WANT_ALL_IPV4 = 1UL << 1, BATADV_MCAST_WANT_ALL_IPV6 = 1UL << 2, + BATADV_MCAST_WANT_NO_RTR4 = 1UL << 3, + BATADV_MCAST_WANT_NO_RTR6 = 1UL << 4, }; /* tt data subtypes */ -- cgit v1.2.3 From d57d76428ae9abca51fb89f9326da9d4b1cf8270 Mon Sep 17 00:00:00 2001 From: Maxim Mikityanskiy Date: Wed, 26 Jun 2019 17:35:24 +0300 Subject: xsk: Add API to check for available entries in FQ MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Add a function that checks whether the Fill Ring has the specified amount of descriptors available. It will be useful for mlx5e that wants to check in advance, whether it can allocate a bulk of RX descriptors, to get the best performance. Signed-off-by: Maxim Mikityanskiy Signed-off-by: Tariq Toukan Acked-by: Saeed Mahameed Acked-by: Björn Töpel Signed-off-by: Daniel Borkmann --- include/net/xdp_sock.h | 21 +++++++++++++++++++++ 1 file changed, 21 insertions(+) (limited to 'include') diff --git a/include/net/xdp_sock.h b/include/net/xdp_sock.h index ae0f368a62bb..b6f5ebae43a1 100644 --- a/include/net/xdp_sock.h +++ b/include/net/xdp_sock.h @@ -77,6 +77,7 @@ int xsk_rcv(struct xdp_sock *xs, struct xdp_buff *xdp); void xsk_flush(struct xdp_sock *xs); bool xsk_is_setup_for_bpf_map(struct xdp_sock *xs); /* Used from netdev driver */ +bool xsk_umem_has_addrs(struct xdp_umem *umem, u32 cnt); u64 *xsk_umem_peek_addr(struct xdp_umem *umem, u64 *addr); void xsk_umem_discard_addr(struct xdp_umem *umem); void xsk_umem_complete_tx(struct xdp_umem *umem, u32 nb_entries); @@ -99,6 +100,16 @@ static inline dma_addr_t xdp_umem_get_dma(struct xdp_umem *umem, u64 addr) } /* Reuse-queue aware version of FILL queue helpers */ +static inline bool xsk_umem_has_addrs_rq(struct xdp_umem *umem, u32 cnt) +{ + struct xdp_umem_fq_reuse *rq = umem->fq_reuse; + + if (rq->length >= cnt) + return true; + + return xsk_umem_has_addrs(umem, cnt - rq->length); +} + static inline u64 *xsk_umem_peek_addr_rq(struct xdp_umem *umem, u64 *addr) { struct xdp_umem_fq_reuse *rq = umem->fq_reuse; @@ -146,6 +157,11 @@ static inline bool xsk_is_setup_for_bpf_map(struct xdp_sock *xs) return false; } +static inline bool xsk_umem_has_addrs(struct xdp_umem *umem, u32 cnt) +{ + return false; +} + static inline u64 *xsk_umem_peek_addr(struct xdp_umem *umem, u64 *addr) { return NULL; @@ -200,6 +216,11 @@ static inline dma_addr_t xdp_umem_get_dma(struct xdp_umem *umem, u64 addr) return 0; } +static inline bool xsk_umem_has_addrs_rq(struct xdp_umem *umem, u32 cnt) +{ + return false; +} + static inline u64 *xsk_umem_peek_addr_rq(struct xdp_umem *umem, u64 *addr) { return NULL; -- cgit v1.2.3 From 2640d3c8123223e0a205b2a25a446df6f072b3ea Mon Sep 17 00:00:00 2001 From: Maxim Mikityanskiy Date: Wed, 26 Jun 2019 17:35:25 +0300 Subject: xsk: Add getsockopt XDP_OPTIONS MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Make it possible for the application to determine whether the AF_XDP socket is running in zero-copy mode. To achieve this, add a new getsockopt option XDP_OPTIONS that returns flags. The only flag supported for now is the zero-copy mode indicator. Signed-off-by: Maxim Mikityanskiy Signed-off-by: Tariq Toukan Acked-by: Saeed Mahameed Acked-by: Björn Töpel Signed-off-by: Daniel Borkmann --- include/uapi/linux/if_xdp.h | 8 ++++++++ 1 file changed, 8 insertions(+) (limited to 'include') diff --git a/include/uapi/linux/if_xdp.h b/include/uapi/linux/if_xdp.h index caed8b1614ff..faaa5ca2a117 100644 --- a/include/uapi/linux/if_xdp.h +++ b/include/uapi/linux/if_xdp.h @@ -46,6 +46,7 @@ struct xdp_mmap_offsets { #define XDP_UMEM_FILL_RING 5 #define XDP_UMEM_COMPLETION_RING 6 #define XDP_STATISTICS 7 +#define XDP_OPTIONS 8 struct xdp_umem_reg { __u64 addr; /* Start of packet data area */ @@ -60,6 +61,13 @@ struct xdp_statistics { __u64 tx_invalid_descs; /* Dropped due to invalid descriptor */ }; +struct xdp_options { + __u32 flags; +}; + +/* Flags for the flags field of struct xdp_options */ +#define XDP_OPTIONS_ZEROCOPY (1 << 0) + /* Pgoff for mmaping the rings */ #define XDP_PGOFF_RX_RING 0 #define XDP_PGOFF_TX_RING 0x80000000 -- cgit v1.2.3 From 4bce4e5cb65587f805655ec6808a20af2036627a Mon Sep 17 00:00:00 2001 From: Maxim Mikityanskiy Date: Wed, 26 Jun 2019 17:35:28 +0300 Subject: xsk: Return the whole xdp_desc from xsk_umem_consume_tx MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Some drivers want to access the data transmitted in order to implement acceleration features of the NICs. It is also useful in AF_XDP TX flow. Change the xsk_umem_consume_tx API to return the whole xdp_desc, that contains the data pointer, length and DMA address, instead of only the latter two. Adapt the implementation of i40e and ixgbe to this change. Signed-off-by: Maxim Mikityanskiy Signed-off-by: Tariq Toukan Acked-by: Saeed Mahameed Cc: Björn Töpel Cc: Magnus Karlsson Acked-by: Björn Töpel Signed-off-by: Daniel Borkmann --- include/net/xdp_sock.h | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/include/net/xdp_sock.h b/include/net/xdp_sock.h index b6f5ebae43a1..057b159ff8b9 100644 --- a/include/net/xdp_sock.h +++ b/include/net/xdp_sock.h @@ -81,7 +81,7 @@ bool xsk_umem_has_addrs(struct xdp_umem *umem, u32 cnt); u64 *xsk_umem_peek_addr(struct xdp_umem *umem, u64 *addr); void xsk_umem_discard_addr(struct xdp_umem *umem); void xsk_umem_complete_tx(struct xdp_umem *umem, u32 nb_entries); -bool xsk_umem_consume_tx(struct xdp_umem *umem, dma_addr_t *dma, u32 *len); +bool xsk_umem_consume_tx(struct xdp_umem *umem, struct xdp_desc *desc); void xsk_umem_consume_tx_done(struct xdp_umem *umem); struct xdp_umem_fq_reuse *xsk_reuseq_prepare(u32 nentries); struct xdp_umem_fq_reuse *xsk_reuseq_swap(struct xdp_umem *umem, @@ -175,8 +175,8 @@ static inline void xsk_umem_complete_tx(struct xdp_umem *umem, u32 nb_entries) { } -static inline bool xsk_umem_consume_tx(struct xdp_umem *umem, dma_addr_t *dma, - u32 *len) +static inline bool xsk_umem_consume_tx(struct xdp_umem *umem, + struct xdp_desc *desc) { return false; } -- cgit v1.2.3 From 0d01da6afc5402f60325c5da31b22f7d56689b49 Mon Sep 17 00:00:00 2001 From: Stanislav Fomichev Date: Thu, 27 Jun 2019 13:38:47 -0700 Subject: bpf: implement getsockopt and setsockopt hooks Implement new BPF_PROG_TYPE_CGROUP_SOCKOPT program type and BPF_CGROUP_{G,S}ETSOCKOPT cgroup hooks. BPF_CGROUP_SETSOCKOPT can modify user setsockopt arguments before passing them down to the kernel or bypass kernel completely. BPF_CGROUP_GETSOCKOPT can can inspect/modify getsockopt arguments that kernel returns. Both hooks reuse existing PTR_TO_PACKET{,_END} infrastructure. The buffer memory is pre-allocated (because I don't think there is a precedent for working with __user memory from bpf). This might be slow to do for each {s,g}etsockopt call, that's why I've added __cgroup_bpf_prog_array_is_empty that exits early if there is nothing attached to a cgroup. Note, however, that there is a race between __cgroup_bpf_prog_array_is_empty and BPF_PROG_RUN_ARRAY where cgroup program layout might have changed; this should not be a problem because in general there is a race between multiple calls to {s,g}etsocktop and user adding/removing bpf progs from a cgroup. The return code of the BPF program is handled as follows: * 0: EPERM * 1: success, continue with next BPF program in the cgroup chain v9: * allow overwriting setsockopt arguments (Alexei Starovoitov): * use set_fs (same as kernel_setsockopt) * buffer is always kzalloc'd (no small on-stack buffer) v8: * use s32 for optlen (Andrii Nakryiko) v7: * return only 0 or 1 (Alexei Starovoitov) * always run all progs (Alexei Starovoitov) * use optval=0 as kernel bypass in setsockopt (Alexei Starovoitov) (decided to use optval=-1 instead, optval=0 might be a valid input) * call getsockopt hook after kernel handlers (Alexei Starovoitov) v6: * rework cgroup chaining; stop as soon as bpf program returns 0 or 2; see patch with the documentation for the details * drop Andrii's and Martin's Acked-by (not sure they are comfortable with the new state of things) v5: * skip copy_to_user() and put_user() when ret == 0 (Martin Lau) v4: * don't export bpf_sk_fullsock helper (Martin Lau) * size != sizeof(__u64) for uapi pointers (Martin Lau) * offsetof instead of bpf_ctx_range when checking ctx access (Martin Lau) v3: * typos in BPF_PROG_CGROUP_SOCKOPT_RUN_ARRAY comments (Andrii Nakryiko) * reverse christmas tree in BPF_PROG_CGROUP_SOCKOPT_RUN_ARRAY (Andrii Nakryiko) * use __bpf_md_ptr instead of __u32 for optval{,_end} (Martin Lau) * use BPF_FIELD_SIZEOF() for consistency (Martin Lau) * new CG_SOCKOPT_ACCESS macro to wrap repeated parts v2: * moved bpf_sockopt_kern fields around to remove a hole (Martin Lau) * aligned bpf_sockopt_kern->buf to 8 bytes (Martin Lau) * bpf_prog_array_is_empty instead of bpf_prog_array_length (Martin Lau) * added [0,2] return code check to verifier (Martin Lau) * dropped unused buf[64] from the stack (Martin Lau) * use PTR_TO_SOCKET for bpf_sockopt->sk (Martin Lau) * dropped bpf_target_off from ctx rewrites (Martin Lau) * use return code for kernel bypass (Martin Lau & Andrii Nakryiko) Cc: Andrii Nakryiko Cc: Martin Lau Signed-off-by: Stanislav Fomichev Signed-off-by: Alexei Starovoitov --- include/linux/bpf-cgroup.h | 45 +++++++++++++++++++++++++++++++++++++++++++++ include/linux/bpf.h | 2 ++ include/linux/bpf_types.h | 1 + include/linux/filter.h | 10 ++++++++++ include/uapi/linux/bpf.h | 14 ++++++++++++++ 5 files changed, 72 insertions(+) (limited to 'include') diff --git a/include/linux/bpf-cgroup.h b/include/linux/bpf-cgroup.h index bd79ae32909a..169fd25f6bc2 100644 --- a/include/linux/bpf-cgroup.h +++ b/include/linux/bpf-cgroup.h @@ -124,6 +124,14 @@ int __cgroup_bpf_run_filter_sysctl(struct ctl_table_header *head, loff_t *ppos, void **new_buf, enum bpf_attach_type type); +int __cgroup_bpf_run_filter_setsockopt(struct sock *sock, int *level, + int *optname, char __user *optval, + int *optlen, char **kernel_optval); +int __cgroup_bpf_run_filter_getsockopt(struct sock *sk, int level, + int optname, char __user *optval, + int __user *optlen, int max_optlen, + int retval); + static inline enum bpf_cgroup_storage_type cgroup_storage_type( struct bpf_map *map) { @@ -286,6 +294,38 @@ int bpf_percpu_cgroup_storage_update(struct bpf_map *map, void *key, __ret; \ }) +#define BPF_CGROUP_RUN_PROG_SETSOCKOPT(sock, level, optname, optval, optlen, \ + kernel_optval) \ +({ \ + int __ret = 0; \ + if (cgroup_bpf_enabled) \ + __ret = __cgroup_bpf_run_filter_setsockopt(sock, level, \ + optname, optval, \ + optlen, \ + kernel_optval); \ + __ret; \ +}) + +#define BPF_CGROUP_GETSOCKOPT_MAX_OPTLEN(optlen) \ +({ \ + int __ret = 0; \ + if (cgroup_bpf_enabled) \ + get_user(__ret, optlen); \ + __ret; \ +}) + +#define BPF_CGROUP_RUN_PROG_GETSOCKOPT(sock, level, optname, optval, optlen, \ + max_optlen, retval) \ +({ \ + int __ret = retval; \ + if (cgroup_bpf_enabled) \ + __ret = __cgroup_bpf_run_filter_getsockopt(sock, level, \ + optname, optval, \ + optlen, max_optlen, \ + retval); \ + __ret; \ +}) + int cgroup_bpf_prog_attach(const union bpf_attr *attr, enum bpf_prog_type ptype, struct bpf_prog *prog); int cgroup_bpf_prog_detach(const union bpf_attr *attr, @@ -357,6 +397,11 @@ static inline int bpf_percpu_cgroup_storage_update(struct bpf_map *map, #define BPF_CGROUP_RUN_PROG_SOCK_OPS(sock_ops) ({ 0; }) #define BPF_CGROUP_RUN_PROG_DEVICE_CGROUP(type,major,minor,access) ({ 0; }) #define BPF_CGROUP_RUN_PROG_SYSCTL(head,table,write,buf,count,pos,nbuf) ({ 0; }) +#define BPF_CGROUP_GETSOCKOPT_MAX_OPTLEN(optlen) ({ 0; }) +#define BPF_CGROUP_RUN_PROG_GETSOCKOPT(sock, level, optname, optval, \ + optlen, max_optlen, retval) ({ retval; }) +#define BPF_CGROUP_RUN_PROG_SETSOCKOPT(sock, level, optname, optval, optlen, \ + kernel_optval) ({ 0; }) #define for_each_cgroup_storage_type(stype) for (; false; ) diff --git a/include/linux/bpf.h b/include/linux/bpf.h index a62e7889b0b6..18f4cc2c6acd 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -518,6 +518,7 @@ struct bpf_prog_array { struct bpf_prog_array *bpf_prog_array_alloc(u32 prog_cnt, gfp_t flags); void bpf_prog_array_free(struct bpf_prog_array *progs); int bpf_prog_array_length(struct bpf_prog_array *progs); +bool bpf_prog_array_is_empty(struct bpf_prog_array *array); int bpf_prog_array_copy_to_user(struct bpf_prog_array *progs, __u32 __user *prog_ids, u32 cnt); @@ -1051,6 +1052,7 @@ extern const struct bpf_func_proto bpf_spin_unlock_proto; extern const struct bpf_func_proto bpf_get_local_storage_proto; extern const struct bpf_func_proto bpf_strtol_proto; extern const struct bpf_func_proto bpf_strtoul_proto; +extern const struct bpf_func_proto bpf_tcp_sock_proto; /* Shared helpers among cBPF and eBPF. */ void bpf_user_rnd_init_once(void); diff --git a/include/linux/bpf_types.h b/include/linux/bpf_types.h index 5a9975678d6f..eec5aeeeaf92 100644 --- a/include/linux/bpf_types.h +++ b/include/linux/bpf_types.h @@ -30,6 +30,7 @@ BPF_PROG_TYPE(BPF_PROG_TYPE_RAW_TRACEPOINT_WRITABLE, raw_tracepoint_writable) #ifdef CONFIG_CGROUP_BPF BPF_PROG_TYPE(BPF_PROG_TYPE_CGROUP_DEVICE, cg_dev) BPF_PROG_TYPE(BPF_PROG_TYPE_CGROUP_SYSCTL, cg_sysctl) +BPF_PROG_TYPE(BPF_PROG_TYPE_CGROUP_SOCKOPT, cg_sockopt) #endif #ifdef CONFIG_BPF_LIRC_MODE2 BPF_PROG_TYPE(BPF_PROG_TYPE_LIRC_MODE2, lirc_mode2) diff --git a/include/linux/filter.h b/include/linux/filter.h index 43b45d6db36d..340f7d648974 100644 --- a/include/linux/filter.h +++ b/include/linux/filter.h @@ -1199,4 +1199,14 @@ struct bpf_sysctl_kern { u64 tmp_reg; }; +struct bpf_sockopt_kern { + struct sock *sk; + u8 *optval; + u8 *optval_end; + s32 level; + s32 optname; + s32 optlen; + s32 retval; +}; + #endif /* __LINUX_FILTER_H__ */ diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index b077507efa3f..a396b516a2b2 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -170,6 +170,7 @@ enum bpf_prog_type { BPF_PROG_TYPE_FLOW_DISSECTOR, BPF_PROG_TYPE_CGROUP_SYSCTL, BPF_PROG_TYPE_RAW_TRACEPOINT_WRITABLE, + BPF_PROG_TYPE_CGROUP_SOCKOPT, }; enum bpf_attach_type { @@ -194,6 +195,8 @@ enum bpf_attach_type { BPF_CGROUP_SYSCTL, BPF_CGROUP_UDP4_RECVMSG, BPF_CGROUP_UDP6_RECVMSG, + BPF_CGROUP_GETSOCKOPT, + BPF_CGROUP_SETSOCKOPT, __MAX_BPF_ATTACH_TYPE }; @@ -3541,4 +3544,15 @@ struct bpf_sysctl { */ }; +struct bpf_sockopt { + __bpf_md_ptr(struct bpf_sock *, sk); + __bpf_md_ptr(void *, optval); + __bpf_md_ptr(void *, optval_end); + + __s32 level; + __s32 optname; + __s32 optlen; + __s32 retval; +}; + #endif /* _UAPI__LINUX_BPF_H__ */ -- cgit v1.2.3 From d2ce8d6bfcfed014fd281e06c9b1d4638ddf3f1e Mon Sep 17 00:00:00 2001 From: Jiunn Chang Date: Thu, 27 Jun 2019 00:04:26 -0500 Subject: nl80211: Fix undefined behavior in bit shift Shifting signed 32-bit value by 31 bits is undefined. Changing most significant bit to unsigned. Signed-off-by: Jiunn Chang Signed-off-by: Johannes Berg --- include/uapi/linux/nl80211.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/uapi/linux/nl80211.h b/include/uapi/linux/nl80211.h index 6f09d1500960..fa7ebbc6ff27 100644 --- a/include/uapi/linux/nl80211.h +++ b/include/uapi/linux/nl80211.h @@ -5314,7 +5314,7 @@ enum nl80211_feature_flags { NL80211_FEATURE_TDLS_CHANNEL_SWITCH = 1 << 28, NL80211_FEATURE_SCAN_RANDOM_MAC_ADDR = 1 << 29, NL80211_FEATURE_SCHED_SCAN_RANDOM_MAC_ADDR = 1 << 30, - NL80211_FEATURE_ND_RANDOM_MAC_ADDR = 1 << 31, + NL80211_FEATURE_ND_RANDOM_MAC_ADDR = 1U << 31, }; /** -- cgit v1.2.3 From 720f22fed81bc6fd1765db7014651b6718887bea Mon Sep 17 00:00:00 2001 From: John Hurley Date: Mon, 24 Jun 2019 23:13:35 +0100 Subject: net: sched: refactor reinsert action The TC_ACT_REINSERT return type was added as an in-kernel only option to allow a packet ingress or egress redirect. This is used to avoid unnecessary skb clones in situations where they are not required. If a TC hook returns this code then the packet is 'reinserted' and no skb consume is carried out as no clone took place. This return type is only used in act_mirred. Rather than have the reinsert called from the main datapath, call it directly in act_mirred. Instead of returning TC_ACT_REINSERT, change the type to the new TC_ACT_CONSUMED which tells the caller that the packet has been stolen by another process and that no consume call is required. Moving all redirect calls to the act_mirred code is in preparation for tracking recursion created by act_mirred. Signed-off-by: John Hurley Reviewed-by: Simon Horman Signed-off-by: David S. Miller --- include/net/pkt_cls.h | 2 +- include/net/sch_generic.h | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/net/pkt_cls.h b/include/net/pkt_cls.h index 720f2b32fc2f..1a7596ba0dbe 100644 --- a/include/net/pkt_cls.h +++ b/include/net/pkt_cls.h @@ -10,7 +10,7 @@ #include /* TC action not accessible from user space */ -#define TC_ACT_REINSERT (TC_ACT_VALUE_MAX + 1) +#define TC_ACT_CONSUMED (TC_ACT_VALUE_MAX + 1) /* Basic packet classifier frontend definitions. */ diff --git a/include/net/sch_generic.h b/include/net/sch_generic.h index 21f434f3ac9e..855167bbc372 100644 --- a/include/net/sch_generic.h +++ b/include/net/sch_generic.h @@ -279,7 +279,7 @@ struct tcf_result { }; const struct tcf_proto *goto_tp; - /* used by the TC_ACT_REINSERT action */ + /* used in the skb_tc_reinsert function */ struct { bool ingress; struct gnet_stats_queue *qstats; -- cgit v1.2.3 From 32e454efbb2279b0fa5874abb0944a9d42080ad1 Mon Sep 17 00:00:00 2001 From: Russell King Date: Tue, 25 Jun 2019 10:44:33 +0100 Subject: net: phylink: further documentation clarifications Clarify the validate() behaviour in a few cases which weren't mentioned in the documentation, but which are necessary for users to get the correct behaviour. Signed-off-by: Russell King Reviewed-by: Andrew Lunn Reviewed-by: Florian Fainelli Signed-off-by: David S. Miller --- include/linux/phylink.h | 11 +++++++++-- 1 file changed, 9 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/phylink.h b/include/linux/phylink.h index 2d2e55dfea94..5b130140fb8f 100644 --- a/include/linux/phylink.h +++ b/include/linux/phylink.h @@ -93,12 +93,19 @@ struct phylink_mac_ops { * Note that the PHY may be able to transform from one connection * technology to another, so, eg, don't clear 1000BaseX just * because the MAC is unable to BaseX mode. This is more about - * clearing unsupported speeds and duplex settings. + * clearing unsupported speeds and duplex settings. The port modes + * should not be cleared; phylink_set_port_modes() will help with this. * * If the @state->interface mode is %PHY_INTERFACE_MODE_1000BASEX * or %PHY_INTERFACE_MODE_2500BASEX, select the appropriate mode * based on @state->advertising and/or @state->speed and update - * @state->interface accordingly. + * @state->interface accordingly. See phylink_helper_basex_speed(). + * + * When @state->interface is %PHY_INTERFACE_MODE_NA, phylink expects the + * MAC driver to return all supported link modes. + * + * If the @state->interface mode is not supported, then the @supported + * mask must be cleared. */ void validate(struct net_device *ndev, unsigned long *supported, struct phylink_link_state *state); -- cgit v1.2.3 From 9903c8dc734265689d5770ff28c84a7228fe5890 Mon Sep 17 00:00:00 2001 From: Vedang Patel Date: Tue, 25 Jun 2019 15:07:13 -0700 Subject: etf: Don't use BIT() in UAPI headers. The BIT() macro isn't exported as part of the UAPI interface. So, the compile-test to ensure they are self contained fails. So, use _BITUL() instead. Signed-off-by: Vedang Patel Signed-off-by: David S. Miller --- include/uapi/linux/pkt_sched.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/uapi/linux/pkt_sched.h b/include/uapi/linux/pkt_sched.h index 8b2f993cbb77..f88c4e0bd9e5 100644 --- a/include/uapi/linux/pkt_sched.h +++ b/include/uapi/linux/pkt_sched.h @@ -988,8 +988,8 @@ struct tc_etf_qopt { __s32 delta; __s32 clockid; __u32 flags; -#define TC_ETF_DEADLINE_MODE_ON BIT(0) -#define TC_ETF_OFFLOAD_ON BIT(1) +#define TC_ETF_DEADLINE_MODE_ON _BITUL(0) +#define TC_ETF_OFFLOAD_ON _BITUL(1) }; enum { -- cgit v1.2.3 From d14d2b20680f02fa739c2cbbb59e3629e487f359 Mon Sep 17 00:00:00 2001 From: Vedang Patel Date: Tue, 25 Jun 2019 15:07:14 -0700 Subject: etf: Add skip_sock_check Currently, etf expects a socket with SO_TXTIME option set for each packet it encounters. So, it will drop all other packets. But, in the future commits we are planning to add functionality where tstamp value will be set by another qdisc. Also, some packets which are generated from within the kernel (e.g. ICMP packets) do not have any socket associated with them. So, this commit adds support for skip_sock_check. When this option is set, etf will skip checking for a socket and other associated options for all skbs. Signed-off-by: Vedang Patel Signed-off-by: David S. Miller --- include/uapi/linux/pkt_sched.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/uapi/linux/pkt_sched.h b/include/uapi/linux/pkt_sched.h index f88c4e0bd9e5..127ac6d2888c 100644 --- a/include/uapi/linux/pkt_sched.h +++ b/include/uapi/linux/pkt_sched.h @@ -990,6 +990,7 @@ struct tc_etf_qopt { __u32 flags; #define TC_ETF_DEADLINE_MODE_ON _BITUL(0) #define TC_ETF_OFFLOAD_ON _BITUL(1) +#define TC_ETF_SKIP_SOCK_CHECK _BITUL(2) }; enum { -- cgit v1.2.3 From 4cfd5779bd6efe8c76b4494aec63a063be0d2ff2 Mon Sep 17 00:00:00 2001 From: Vedang Patel Date: Tue, 25 Jun 2019 15:07:17 -0700 Subject: taprio: Add support for txtime-assist mode Currently, we are seeing non-critical packets being transmitted outside of their timeslice. We can confirm that the packets are being dequeued at the right time. So, the delay is induced in the hardware side. The most likely reason is the hardware queues are starving the lower priority queues. In order to improve the performance of taprio, we will be making use of the txtime feature provided by the ETF qdisc. For all the packets which do not have the SO_TXTIME option set, taprio will set the transmit timestamp (set in skb->tstamp) in this mode. TAPrio Qdisc will ensure that the transmit time for the packet is set to when the gate is open. If SO_TXTIME is set, the TAPrio qdisc will validate whether the timestamp (in skb->tstamp) occurs when the gate corresponding to skb's traffic class is open. Following two parameters added to support this mode: - flags: used to enable txtime-assist mode. Will also be used to enable other modes (like hardware offloading) later. - txtime-delay: This indicates the minimum time it will take for the packet to hit the wire. This is useful in determining whether we can transmit the packet in the remaining time if the gate corresponding to the packet is currently open. An example configuration for enabling txtime-assist: tc qdisc replace dev eth0 parent root handle 100 taprio \\ num_tc 3 \\ map 2 2 1 0 2 2 2 2 2 2 2 2 2 2 2 2 \\ queues 1@0 1@0 1@0 \\ base-time 1558653424279842568 \\ sched-entry S 01 300000 \\ sched-entry S 02 300000 \\ sched-entry S 04 400000 \\ flags 0x1 \\ txtime-delay 40000 \\ clockid CLOCK_TAI tc qdisc replace dev $IFACE parent 100:1 etf skip_sock_check \\ offload delta 200000 clockid CLOCK_TAI Note that all the traffic classes are mapped to the same queue. This is only possible in taprio when txtime-assist is enabled. Also, note that the ETF Qdisc is enabled with offload mode set. In this mode, if the packet's traffic class is open and the complete packet can be transmitted, taprio will try to transmit the packet immediately. This will be done by setting skb->tstamp to current_time + the time delta indicated in the txtime-delay parameter. This parameter indicates the time taken (in software) for packet to reach the network adapter. If the packet cannot be transmitted in the current interval or if the packet's traffic is not currently transmitting, the skb->tstamp is set to the next available timestamp value. This is tracked in the next_launchtime parameter in the struct sched_entry. The behaviour w.r.t admin and oper schedules is not changed from what is present in software mode. The transmit time is already known in advance. So, we do not need the HR timers to advance the schedule and wakeup the dequeue side of taprio. So, HR timer won't be run when this mode is enabled. Signed-off-by: Vedang Patel Signed-off-by: David S. Miller --- include/uapi/linux/pkt_sched.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include') diff --git a/include/uapi/linux/pkt_sched.h b/include/uapi/linux/pkt_sched.h index 127ac6d2888c..390efb54b2e0 100644 --- a/include/uapi/linux/pkt_sched.h +++ b/include/uapi/linux/pkt_sched.h @@ -1159,6 +1159,8 @@ enum { * [TCA_TAPRIO_ATTR_SCHED_ENTRY_INTERVAL] */ +#define TCA_TAPRIO_ATTR_FLAG_TXTIME_ASSIST 0x1 + enum { TCA_TAPRIO_ATTR_UNSPEC, TCA_TAPRIO_ATTR_PRIOMAP, /* struct tc_mqprio_qopt */ @@ -1170,6 +1172,8 @@ enum { TCA_TAPRIO_ATTR_ADMIN_SCHED, /* The admin sched, only used in dump */ TCA_TAPRIO_ATTR_SCHED_CYCLE_TIME, /* s64 */ TCA_TAPRIO_ATTR_SCHED_CYCLE_TIME_EXTENSION, /* s64 */ + TCA_TAPRIO_ATTR_FLAGS, /* u32 */ + TCA_TAPRIO_ATTR_TXTIME_DELAY, /* s32 */ __TCA_TAPRIO_ATTR_MAX, }; -- cgit v1.2.3 From 5233794b179136d597b84188c1285148f07012e6 Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Tue, 18 Jun 2019 13:15:06 +0200 Subject: net/mlx5e: reduce stack usage in mlx5_eswitch_termtbl_create Putting an empty 'mlx5_flow_spec' structure on the stack is a bit wasteful and causes a warning on 32-bit architectures when building with clang -fsanitize-coverage: drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads_termtbl.c: In function 'mlx5_eswitch_termtbl_create': drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads_termtbl.c:90:1: error: the frame size of 1032 bytes is larger than 1024 bytes [-Werror=frame-larger-than=] Since the structure is never written to, we can statically allocate it to avoid the stack usage. To be on the safe side, mark all subsequent function arguments that we pass it into as 'const' as well. Fixes: 10caabdaad5a ("net/mlx5e: Use termination table for VLAN push actions") Signed-off-by: Arnd Bergmann Acked-by: Saeed Mahameed Acked-by: Mark Bloch Signed-off-by: Saeed Mahameed --- include/linux/mlx5/fs.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/mlx5/fs.h b/include/linux/mlx5/fs.h index dc7e7aa53a13..04a569568eac 100644 --- a/include/linux/mlx5/fs.h +++ b/include/linux/mlx5/fs.h @@ -208,7 +208,7 @@ struct mlx5_flow_act { */ struct mlx5_flow_handle * mlx5_add_flow_rules(struct mlx5_flow_table *ft, - struct mlx5_flow_spec *spec, + const struct mlx5_flow_spec *spec, struct mlx5_flow_act *flow_act, struct mlx5_flow_destination *dest, int num_dest); -- cgit v1.2.3 From c8af5cd75e2411d5a5aacf115f59a5ff6b87f3fa Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Toke=20H=C3=B8iland-J=C3=B8rgensen?= Date: Fri, 28 Jun 2019 11:12:34 +0200 Subject: xskmap: Move non-standard list manipulation to helper MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Add a helper in list.h for the non-standard way of clearing a list that is used in xskmap. This makes it easier to reuse it in the other map types, and also makes sure this usage is not forgotten in any list refactorings in the future. Signed-off-by: Toke Høiland-Jørgensen Signed-off-by: Daniel Borkmann --- include/linux/list.h | 14 ++++++++++++++ 1 file changed, 14 insertions(+) (limited to 'include') diff --git a/include/linux/list.h b/include/linux/list.h index e951228db4b2..85c92555e31f 100644 --- a/include/linux/list.h +++ b/include/linux/list.h @@ -106,6 +106,20 @@ static inline void __list_del(struct list_head * prev, struct list_head * next) WRITE_ONCE(prev->next, next); } +/* + * Delete a list entry and clear the 'prev' pointer. + * + * This is a special-purpose list clearing method used in the networking code + * for lists allocated as per-cpu, where we don't want to incur the extra + * WRITE_ONCE() overhead of a regular list_del_init(). The code that uses this + * needs to check the node 'prev' pointer instead of calling list_empty(). + */ +static inline void __list_del_clearprev(struct list_head *entry) +{ + __list_del(entry->prev, entry->next); + entry->prev = NULL; +} + /** * list_del - deletes entry from list. * @entry: the element to delete from the list. -- cgit v1.2.3 From 4b55cf290dc6bd3a9e5da26d1ad60e77aa88c8cf Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Toke=20H=C3=B8iland-J=C3=B8rgensen?= Date: Fri, 28 Jun 2019 11:12:34 +0200 Subject: devmap: Rename ifindex member in bpf_redirect_info MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The bpf_redirect_info struct has an 'ifindex' member which was named back when the redirects could only target egress interfaces. Now that we can also redirect to sockets and CPUs, this is a bit misleading, so rename the member to tgt_index. Reorder the struct members so we can have 'tgt_index' and 'tgt_value' next to each other in a subsequent patch. Signed-off-by: Toke Høiland-Jørgensen Signed-off-by: Daniel Borkmann --- 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 340f7d648974..92bd192f7786 100644 --- a/include/linux/filter.h +++ b/include/linux/filter.h @@ -578,8 +578,8 @@ struct bpf_skb_data_end { }; struct bpf_redirect_info { - u32 ifindex; u32 flags; + u32 tgt_index; struct bpf_map *map; struct bpf_map *map_to_flush; u32 kern_flags; -- cgit v1.2.3 From 43e74c0267a35d6f5127218054b2d80c7fe801f5 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Toke=20H=C3=B8iland-J=C3=B8rgensen?= Date: Fri, 28 Jun 2019 11:12:34 +0200 Subject: bpf_xdp_redirect_map: Perform map lookup in eBPF helper MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The bpf_redirect_map() helper used by XDP programs doesn't return any indication of whether it can successfully redirect to the map index it was given. Instead, BPF programs have to track this themselves, leading to programs using duplicate maps to track which entries are populated in the devmap. This patch fixes this by moving the map lookup into the bpf_redirect_map() helper, which makes it possible to return failure to the eBPF program. The lower bits of the flags argument is used as the return code, which means that existing users who pass a '0' flag argument will get XDP_ABORTED. With this, a BPF program can check the return code from the helper call and react by, for instance, substituting a different redirect. This works for any type of map used for redirect. Signed-off-by: Toke Høiland-Jørgensen Acked-by: Jonathan Lemon Acked-by: Andrii Nakryiko Signed-off-by: Daniel Borkmann --- include/linux/filter.h | 1 + include/trace/events/xdp.h | 5 ++--- include/uapi/linux/bpf.h | 7 +++++-- 3 files changed, 8 insertions(+), 5 deletions(-) (limited to 'include') diff --git a/include/linux/filter.h b/include/linux/filter.h index 92bd192f7786..1fe53e78c7e3 100644 --- a/include/linux/filter.h +++ b/include/linux/filter.h @@ -580,6 +580,7 @@ struct bpf_skb_data_end { struct bpf_redirect_info { u32 flags; u32 tgt_index; + void *tgt_value; struct bpf_map *map; struct bpf_map *map_to_flush; u32 kern_flags; diff --git a/include/trace/events/xdp.h b/include/trace/events/xdp.h index 81e708c4b513..68899fdc985b 100644 --- a/include/trace/events/xdp.h +++ b/include/trace/events/xdp.h @@ -175,9 +175,8 @@ struct _bpf_dtab_netdev { #endif /* __DEVMAP_OBJ_TYPE */ #define devmap_ifindex(fwd, map) \ - (!fwd ? 0 : \ - ((map->map_type == BPF_MAP_TYPE_DEVMAP) ? \ - ((struct _bpf_dtab_netdev *)fwd)->dev->ifindex : 0)) + ((map->map_type == BPF_MAP_TYPE_DEVMAP) ? \ + ((struct _bpf_dtab_netdev *)fwd)->dev->ifindex : 0) #define _trace_xdp_redirect_map(dev, xdp, fwd, map, idx) \ trace_xdp_redirect_map(dev, xdp, devmap_ifindex(fwd, map), \ diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index a396b516a2b2..cffea1826a1f 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -1571,8 +1571,11 @@ union bpf_attr { * but this is only implemented for native XDP (with driver * support) as of this writing). * - * All values for *flags* are reserved for future usage, and must - * be left at zero. + * The lower two bits of *flags* are used as the return code if + * the map lookup fails. This is so that the return value can be + * one of the XDP program return codes up to XDP_TX, as chosen by + * the caller. Any higher bits in the *flags* argument must be + * unset. * * When used to redirect packets to net devices, this helper * provides a high performance increase over **bpf_redirect**\ (). -- cgit v1.2.3 From 0472301a28f6cf53a6bc5783e48a2d0bbff4682f Mon Sep 17 00:00:00 2001 From: Baruch Siach Date: Fri, 28 Jun 2019 07:08:45 +0300 Subject: bpf: fix uapi bpf_prog_info fields alignment Merge commit 1c8c5a9d38f60 ("Merge git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next") undid the fix from commit 36f9814a494 ("bpf: fix uapi hole for 32 bit compat applications") by taking the gpl_compatible 1-bit field definition from commit b85fab0e67b162 ("bpf: Add gpl_compatible flag to struct bpf_prog_info") as is. That breaks architectures with 16-bit alignment like m68k. Add 31-bit pad after gpl_compatible to restore alignment of following fields. Thanks to Dmitry V. Levin his analysis of this bug history. Signed-off-by: Baruch Siach Acked-by: Song Liu Cc: Jiri Olsa Cc: Daniel Borkmann Cc: Geert Uytterhoeven Cc: Linus Torvalds Signed-off-by: Daniel Borkmann --- include/uapi/linux/bpf.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index a8b823c30b43..29a5bc3d5c66 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -3143,6 +3143,7 @@ struct bpf_prog_info { char name[BPF_OBJ_NAME_LEN]; __u32 ifindex; __u32 gpl_compatible:1; + __u32 :31; /* alignment pad */ __u64 netns_dev; __u64 netns_ino; __u32 nr_jited_ksyms; -- cgit v1.2.3 From b60a77386b1d4868f72f6353d35dabe5fbe981f2 Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Wed, 26 Jun 2019 20:40:45 +0200 Subject: net: make skb_dst_force return true when dst is refcounted netfilter did not expect that skb_dst_force() can cause skb to lose its dst entry. I got a bug report with a skb->dst NULL dereference in netfilter output path. The backtrace contains nf_reinject(), so the dst might have been cleared when skb got queued to userspace. Other users were fixed via if (skb_dst(skb)) { skb_dst_force(skb); if (!skb_dst(skb)) goto handle_err; } But I think its preferable to make the 'dst might be cleared' part of the function explicit. In netfilter case, skb with a null dst is expected when queueing in prerouting hook, so drop skb for the other hooks. v2: v1 of this patch returned true in case skb had no dst entry. Eric said: Say if we have two skb_dst_force() calls for some reason on the same skb, only the first one will return false. This now returns false even when skb had no dst, as per Erics suggestion, so callers might need to check skb_dst() first before skb_dst_force(). Signed-off-by: Florian Westphal Signed-off-by: David S. Miller --- include/net/dst.h | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/net/dst.h b/include/net/dst.h index 12b31c602cb0..f8206d3fed2f 100644 --- a/include/net/dst.h +++ b/include/net/dst.h @@ -302,8 +302,9 @@ static inline bool dst_hold_safe(struct dst_entry *dst) * @skb: buffer * * If dst is not yet refcounted and not destroyed, grab a ref on it. + * Returns true if dst is refcounted. */ -static inline void skb_dst_force(struct sk_buff *skb) +static inline bool skb_dst_force(struct sk_buff *skb) { if (skb_dst_is_noref(skb)) { struct dst_entry *dst = skb_dst(skb); @@ -314,6 +315,8 @@ static inline void skb_dst_force(struct sk_buff *skb) skb->_skb_refdst = (unsigned long)dst; } + + return skb->_skb_refdst != 0UL; } -- cgit v1.2.3 From 79293f49677e2e703ef0d0efc9919319adacb3fb Mon Sep 17 00:00:00 2001 From: Jiunn Chang Date: Wed, 26 Jun 2019 22:25:30 -0500 Subject: packet: Fix undefined behavior in bit shift Shifting signed 32-bit value by 31 bits is undefined. Changing most significant bit to unsigned. Changes included in v2: - use subsystem specific subject lines - CC required mailing lists Signed-off-by: Jiunn Chang Signed-off-by: David S. Miller --- include/uapi/linux/if_packet.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/uapi/linux/if_packet.h b/include/uapi/linux/if_packet.h index 467b654bd4c7..3d884d68eb30 100644 --- a/include/uapi/linux/if_packet.h +++ b/include/uapi/linux/if_packet.h @@ -123,7 +123,7 @@ struct tpacket_auxdata { /* Rx and Tx ring - header status */ #define TP_STATUS_TS_SOFTWARE (1 << 29) #define TP_STATUS_TS_SYS_HARDWARE (1 << 30) /* deprecated, never set */ -#define TP_STATUS_TS_RAW_HARDWARE (1 << 31) +#define TP_STATUS_TS_RAW_HARDWARE (1U << 31) /* Rx ring - feature request bits */ #define TP_FT_REQ_FILL_RXHASH 0x1 -- cgit v1.2.3 From c7b37c769d2a5e711106a3c793140a4f46768e04 Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Mon, 24 Jun 2019 22:04:48 +0200 Subject: xfrm: remove get_mtu indirection from xfrm_type esp4_get_mtu and esp6_get_mtu are exactly the same, the only difference is a single sizeof() (ipv4 vs. ipv6 header). Merge both into xfrm_state_mtu() and remove the indirection. Signed-off-by: Florian Westphal Signed-off-by: Steffen Klassert --- include/net/xfrm.h | 4 +--- 1 file changed, 1 insertion(+), 3 deletions(-) (limited to 'include') diff --git a/include/net/xfrm.h b/include/net/xfrm.h index 56b31676e330..b22db30c3d88 100644 --- a/include/net/xfrm.h +++ b/include/net/xfrm.h @@ -404,8 +404,6 @@ struct xfrm_type { int (*reject)(struct xfrm_state *, struct sk_buff *, const struct flowi *); int (*hdr_offset)(struct xfrm_state *, struct sk_buff *, u8 **); - /* Estimate maximal size of result of transformation of a dgram */ - u32 (*get_mtu)(struct xfrm_state *, int size); }; int xfrm_register_type(const struct xfrm_type *type, unsigned short family); @@ -1546,7 +1544,7 @@ void xfrm_sad_getinfo(struct net *net, struct xfrmk_sadinfo *si); void xfrm_spd_getinfo(struct net *net, struct xfrmk_spdinfo *si); u32 xfrm_replay_seqhi(struct xfrm_state *x, __be32 net_seq); int xfrm_init_replay(struct xfrm_state *x); -int xfrm_state_mtu(struct xfrm_state *x, int mtu); +u32 xfrm_state_mtu(struct xfrm_state *x, int mtu); int __xfrm_init_state(struct xfrm_state *x, bool init_replay, bool offload); int xfrm_init_state(struct xfrm_state *x); int xfrm_input(struct sk_buff *skb, int nexthdr, __be32 spi, int encap_type); -- cgit v1.2.3 From 40f6a2cb9cfc5da713f745b23bcc2c6761e5eb5e Mon Sep 17 00:00:00 2001 From: Vandana BN Date: Mon, 1 Jul 2019 17:25:39 +0530 Subject: net: dst.h: Fix shifting signed 32-bit value by 31 bits problem Fix DST_FEATURE_ECN_CA to use "U" cast to avoid shifting signed 32-bit value by 31 bits problem. Signed-off-by: Vandana BN Signed-off-by: David S. Miller --- include/net/dst.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/net/dst.h b/include/net/dst.h index f8206d3fed2f..fe62fe2eb781 100644 --- a/include/net/dst.h +++ b/include/net/dst.h @@ -183,7 +183,7 @@ static inline void dst_metric_set(struct dst_entry *dst, int metric, u32 val) } /* Kernel-internal feature bits that are unallocated in user space. */ -#define DST_FEATURE_ECN_CA (1 << 31) +#define DST_FEATURE_ECN_CA (1U << 31) #define DST_FEATURE_MASK (DST_FEATURE_ECN_CA) #define DST_FEATURE_ECN_MASK (DST_FEATURE_ECN_CA | RTAX_FEATURE_ECN) -- cgit v1.2.3 From a346abe051bd2bd0d5d0140b2da9ec95639acad7 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Mon, 1 Jul 2019 06:39:36 -0700 Subject: ipv6: icmp: allow flowlabel reflection in echo replies Extend flowlabel_reflect bitmask to allow conditional reflection of incoming flowlabels in echo replies. Note this has precedence against auto flowlabels. Add flowlabel_reflect enum to replace hard coded values. Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- include/net/ipv6.h | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'include') diff --git a/include/net/ipv6.h b/include/net/ipv6.h index b41f6a0fa903..8eca5fb30376 100644 --- a/include/net/ipv6.h +++ b/include/net/ipv6.h @@ -301,6 +301,13 @@ struct ipv6_txoptions { /* Option buffer, as read by IPV6_PKTOPTIONS, starts here. */ }; +/* flowlabel_reflect sysctl values */ +enum flowlabel_reflect { + FLOWLABEL_REFLECT_ESTABLISHED = 1, + FLOWLABEL_REFLECT_TCP_RESET = 2, + FLOWLABEL_REFLECT_ICMPV6_ECHO_REPLIES = 4, +}; + struct ip6_flowlabel { struct ip6_flowlabel __rcu *next; __be32 label; -- cgit v1.2.3 From 88405680ec57c35f5886dbb81b3f6f638f74f40d Mon Sep 17 00:00:00 2001 From: Vandana BN Date: Mon, 1 Jul 2019 19:46:10 +0530 Subject: net:gue.h:Fix shifting signed 32-bit value by 31 bits problem Fix GUE_PFLAG_REMCSUM to use "U" cast to avoid shifting signed 32-bit value by 31 bits problem. Signed-off-by: Vandana BN Signed-off-by: David S. Miller --- include/net/gue.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/net/gue.h b/include/net/gue.h index fdad41469b65..3a6595bfa641 100644 --- a/include/net/gue.h +++ b/include/net/gue.h @@ -60,7 +60,7 @@ struct guehdr { /* Private flags in the private option extension */ -#define GUE_PFLAG_REMCSUM htonl(1 << 31) +#define GUE_PFLAG_REMCSUM htonl(1U << 31) #define GUE_PLEN_REMCSUM 4 #define GUE_PFLAGS_ALL (GUE_PFLAG_REMCSUM) -- cgit v1.2.3 From 1759d322f4bad2f82c376856363b725cac12e61d Mon Sep 17 00:00:00 2001 From: Parav Pandit Date: Fri, 28 Jun 2019 22:35:48 +0000 Subject: net/mlx5: Add hardware definitions for sub functions Update mlx5 device interface data structures for: 1. New command definitions for allocating, deallocating SF 2. Query SF partition 3. Eswitch SF fields 4. HCA CAP SF fields 5. Extend Eswitch functions command for SF Signed-off-by: Parav Pandit Signed-off-by: Vu Pham Signed-off-by: Saeed Mahameed --- include/linux/mlx5/mlx5_ifc.h | 99 +++++++++++++++++++++++++++++++++++++++++-- 1 file changed, 96 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h index d4409654f760..db00effaa83a 100644 --- a/include/linux/mlx5/mlx5_ifc.h +++ b/include/linux/mlx5/mlx5_ifc.h @@ -106,6 +106,9 @@ enum { MLX5_CMD_OP_QUERY_ISSI = 0x10a, MLX5_CMD_OP_SET_ISSI = 0x10b, MLX5_CMD_OP_SET_DRIVER_VERSION = 0x10d, + MLX5_CMD_OP_QUERY_SF_PARTITION = 0x111, + MLX5_CMD_OP_ALLOC_SF = 0x113, + MLX5_CMD_OP_DEALLOC_SF = 0x114, MLX5_CMD_OP_CREATE_MKEY = 0x200, MLX5_CMD_OP_QUERY_MKEY = 0x201, MLX5_CMD_OP_DESTROY_MKEY = 0x202, @@ -713,7 +716,11 @@ struct mlx5_ifc_e_switch_cap_bits { u8 reserved_2b[0x6]; u8 max_encap_header_size[0xa]; - u8 reserved_40[0x7c0]; + u8 reserved_at_40[0xb]; + u8 log_max_esw_sf[0x5]; + u8 esw_sf_base_id[0x10]; + + u8 reserved_at_60[0x7a0]; }; @@ -1330,13 +1337,24 @@ struct mlx5_ifc_cmd_hca_cap_bits { u8 reserved_at_640[0x10]; u8 num_q_monitor_counters[0x10]; - u8 reserved_at_660[0x40]; + u8 reserved_at_660[0x20]; + + u8 sf[0x1]; + u8 sf_set_partition[0x1]; + u8 reserved_at_682[0x1]; + u8 log_max_sf[0x5]; + u8 reserved_at_688[0x8]; + u8 log_min_sf_size[0x8]; + u8 max_num_sf_partitions[0x8]; u8 uctx_cap[0x20]; u8 reserved_at_6c0[0x4]; u8 flex_parser_id_geneve_tlv_option_0[0x4]; - u8 reserved_at_6c8[0x138]; + u8 reserved_at_6c8[0x28]; + u8 sf_base_id[0x10]; + + u8 reserved_at_700[0x100]; }; enum mlx5_flow_destination_type { @@ -9786,6 +9804,81 @@ struct mlx5_ifc_query_esw_functions_out_bits { struct mlx5_ifc_host_params_context_bits host_params_context; u8 reserved_at_280[0x180]; + u8 host_sf_enable[0][0x40]; +}; + +struct mlx5_ifc_sf_partition_bits { + u8 reserved_at_0[0x10]; + u8 log_num_sf[0x8]; + u8 log_sf_bar_size[0x8]; +}; + +struct mlx5_ifc_query_sf_partitions_out_bits { + u8 status[0x8]; + u8 reserved_at_8[0x18]; + + u8 syndrome[0x20]; + + u8 reserved_at_40[0x18]; + u8 num_sf_partitions[0x8]; + + u8 reserved_at_60[0x20]; + + struct mlx5_ifc_sf_partition_bits sf_partition[0]; +}; + +struct mlx5_ifc_query_sf_partitions_in_bits { + u8 opcode[0x10]; + u8 reserved_at_10[0x10]; + + u8 reserved_at_20[0x10]; + u8 op_mod[0x10]; + + u8 reserved_at_40[0x40]; +}; + +struct mlx5_ifc_dealloc_sf_out_bits { + u8 status[0x8]; + u8 reserved_at_8[0x18]; + + u8 syndrome[0x20]; + + u8 reserved_at_40[0x40]; +}; + +struct mlx5_ifc_dealloc_sf_in_bits { + u8 opcode[0x10]; + u8 reserved_at_10[0x10]; + + u8 reserved_at_20[0x10]; + u8 op_mod[0x10]; + + u8 reserved_at_40[0x10]; + u8 function_id[0x10]; + + u8 reserved_at_60[0x20]; +}; + +struct mlx5_ifc_alloc_sf_out_bits { + u8 status[0x8]; + u8 reserved_at_8[0x18]; + + u8 syndrome[0x20]; + + u8 reserved_at_40[0x40]; +}; + +struct mlx5_ifc_alloc_sf_in_bits { + u8 opcode[0x10]; + u8 reserved_at_10[0x10]; + + u8 reserved_at_20[0x10]; + u8 op_mod[0x10]; + + u8 reserved_at_40[0x10]; + u8 function_id[0x10]; + + u8 reserved_at_60[0x20]; }; #endif /* MLX5_IFC_H */ -- cgit v1.2.3 From a82e0b5bdac29d9719d3ca2df01494a7947351aa Mon Sep 17 00:00:00 2001 From: Shay Agroskin Date: Fri, 28 Jun 2019 22:35:50 +0000 Subject: net/mlx5: Added MCQI and MCQS registers' description to ifc Given a fw component index, the MCQI register allows us to query this component's information (e.g. its version and capabilities). Given a fw component index, the MCQS register allows us to query the status of a fw component, including its type and state (e.g. PRESET/IN_USE). It can be used to find the index of a component of a specific type, by sequentially increasing the component index, and querying each time the type of the returned component. If max component index is reached, 'last_index_flag' is set by the HCA. These registers' description was added to query the running and pending fw version of the HCA. Signed-off-by: Shay Agroskin Signed-off-by: Saeed Mahameed --- include/linux/mlx5/driver.h | 1 + include/linux/mlx5/mlx5_ifc.h | 59 +++++++++++++++++++++++++++++++++++++++++-- 2 files changed, 58 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h index 87f77ded78d4..2ff624a91e3d 100644 --- a/include/linux/mlx5/driver.h +++ b/include/linux/mlx5/driver.h @@ -138,6 +138,7 @@ enum { MLX5_REG_MTPPS = 0x9053, MLX5_REG_MTPPSE = 0x9054, MLX5_REG_MPEGC = 0x9056, + MLX5_REG_MCQS = 0x9060, MLX5_REG_MCQI = 0x9061, MLX5_REG_MCC = 0x9062, MLX5_REG_MCDA = 0x9063, diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h index db00effaa83a..e2a77b5152a8 100644 --- a/include/linux/mlx5/mlx5_ifc.h +++ b/include/linux/mlx5/mlx5_ifc.h @@ -8542,7 +8542,7 @@ struct mlx5_ifc_mcam_access_reg_bits { u8 mcda[0x1]; u8 mcc[0x1]; u8 mcqi[0x1]; - u8 reserved_at_1f[0x1]; + u8 mcqs[0x1]; u8 regs_95_to_87[0x9]; u8 mpegc[0x1]; @@ -9034,6 +9034,24 @@ struct mlx5_ifc_mtppse_reg_bits { u8 reserved_at_40[0x40]; }; +struct mlx5_ifc_mcqs_reg_bits { + u8 last_index_flag[0x1]; + u8 reserved_at_1[0x7]; + u8 fw_device[0x8]; + u8 component_index[0x10]; + + u8 reserved_at_20[0x10]; + u8 identifier[0x10]; + + u8 reserved_at_40[0x17]; + u8 component_status[0x5]; + u8 component_update_state[0x4]; + + u8 last_update_state_changer_type[0x4]; + u8 last_update_state_changer_host_id[0x4]; + u8 reserved_at_68[0x18]; +}; + struct mlx5_ifc_mcqi_cap_bits { u8 supported_info_bitmask[0x20]; @@ -9054,6 +9072,43 @@ struct mlx5_ifc_mcqi_cap_bits { u8 reserved_at_86[0x1a]; }; +struct mlx5_ifc_mcqi_version_bits { + u8 reserved_at_0[0x2]; + u8 build_time_valid[0x1]; + u8 user_defined_time_valid[0x1]; + u8 reserved_at_4[0x14]; + u8 version_string_length[0x8]; + + u8 version[0x20]; + + u8 build_time[0x40]; + + u8 user_defined_time[0x40]; + + u8 build_tool_version[0x20]; + + u8 reserved_at_e0[0x20]; + + u8 version_string[92][0x8]; +}; + +struct mlx5_ifc_mcqi_activation_method_bits { + u8 pending_server_ac_power_cycle[0x1]; + u8 pending_server_dc_power_cycle[0x1]; + u8 pending_server_reboot[0x1]; + u8 pending_fw_reset[0x1]; + u8 auto_activate[0x1]; + u8 all_hosts_sync[0x1]; + u8 device_hw_reset[0x1]; + u8 reserved_at_7[0x19]; +}; + +union mlx5_ifc_mcqi_reg_data_bits { + struct mlx5_ifc_mcqi_cap_bits mcqi_caps; + struct mlx5_ifc_mcqi_version_bits mcqi_version; + struct mlx5_ifc_mcqi_activation_method_bits mcqi_activation_mathod; +}; + struct mlx5_ifc_mcqi_reg_bits { u8 read_pending_component[0x1]; u8 reserved_at_1[0xf]; @@ -9071,7 +9126,7 @@ struct mlx5_ifc_mcqi_reg_bits { u8 reserved_at_a0[0x10]; u8 data_size[0x10]; - u8 data[0][0x20]; + union mlx5_ifc_mcqi_reg_data_bits data[0]; }; struct mlx5_ifc_mcc_reg_bits { -- cgit v1.2.3 From 2f69e591e4531d3192841a4eb2bd9b512f5a8b66 Mon Sep 17 00:00:00 2001 From: Bodong Wang Date: Fri, 28 Jun 2019 22:35:53 +0000 Subject: {IB, net}/mlx5: E-Switch, Use index of rep for vport to IB port mapping In the single IB device mode, the mapping between vport number and rep relies on a counter. However for dynamic vport allocation, it is desired to keep consistent map of eswitch vport and IB port. Hence, simplify code to remove the free running counter and instead use the available vport index during load/unload sequence from the eswitch. Signed-off-by: Bodong Wang Suggested-by: Parav Pandit Reviewed-by: Parav Pandit Reviewed-by: Mark Bloch Signed-off-by: Saeed Mahameed --- include/linux/mlx5/eswitch.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/linux/mlx5/eswitch.h b/include/linux/mlx5/eswitch.h index aece3ae1902d..36cb641188b0 100644 --- a/include/linux/mlx5/eswitch.h +++ b/include/linux/mlx5/eswitch.h @@ -46,6 +46,8 @@ struct mlx5_eswitch_rep { u16 vport; u8 hw_id[ETH_ALEN]; u16 vlan; + /* Only IB rep is using vport_index */ + u16 vport_index; u32 vlan_refcount; }; -- cgit v1.2.3 From 386e75af995c3aec475a2185b919bf46af396bfc Mon Sep 17 00:00:00 2001 From: Huy Nguyen Date: Fri, 28 Jun 2019 22:35:58 +0000 Subject: net/mlx5: Rename mlx5_pci_dev_type to mlx5_coredev_type Rename mlx5_pci_dev_type to mlx5_coredev_type to distinguish different mlx5 device types. mlx5_coredev_type represents mlx5_core_dev instance type. Hence keep mlx5_coredev_type in mlx5_core_dev structure. Signed-off-by: Huy Nguyen Signed-off-by: Vu Pham Signed-off-by: Parav Pandit Reviewed-by: Parav Pandit Signed-off-by: Saeed Mahameed --- include/linux/mlx5/driver.h | 11 ++++++++--- 1 file changed, 8 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h index 2ff624a91e3d..155b8cbe1cc9 100644 --- a/include/linux/mlx5/driver.h +++ b/include/linux/mlx5/driver.h @@ -182,6 +182,11 @@ enum port_state_policy { MLX5_POLICY_INVALID = 0xffffffff }; +enum mlx5_coredev_type { + MLX5_COREDEV_PF, + MLX5_COREDEV_VF +}; + struct mlx5_field_desc { struct dentry *dent; int i; @@ -567,7 +572,6 @@ struct mlx5_priv { struct mlx5_core_sriov sriov; struct mlx5_lag *lag; struct mlx5_devcom *devcom; - unsigned long pci_dev_data; struct mlx5_core_roce roce; struct mlx5_fc_stats fc_stats; struct mlx5_rl_table rl_table; @@ -646,6 +650,7 @@ struct mlx5_vxlan; struct mlx5_core_dev { struct device *device; + enum mlx5_coredev_type coredev_type; struct pci_dev *pdev; /* sync pci state */ struct mutex pci_status_mutex; @@ -1079,9 +1084,9 @@ enum { MLX5_PCI_DEV_IS_VF = 1 << 0, }; -static inline int mlx5_core_is_pf(struct mlx5_core_dev *dev) +static inline bool mlx5_core_is_pf(struct mlx5_core_dev *dev) { - return !(dev->priv.pci_dev_data & MLX5_PCI_DEV_IS_VF); + return dev->coredev_type == MLX5_COREDEV_PF; } static inline bool mlx5_core_is_ecpf(struct mlx5_core_dev *dev) -- cgit v1.2.3 From 5ccf2770e83bf8739f0a7c8bed9186d7e5d2ecbc Mon Sep 17 00:00:00 2001 From: Bodong Wang Date: Fri, 28 Jun 2019 22:36:04 +0000 Subject: net/mlx5: Don't handle VF func change if host PF is disabled When ECPF eswitch manager is at offloads mode, it monitors functions changed event from host PF side and acts according to the number of VFs enabled/disabled. As ECPF and host PF work in two independent hosts, it's possible that host PF OS reboots but ECPF system is still kept on and continues monitoring events from host PF. When kernel from host PF side is booting, PCI iov driver does sriov_init and compute_max_vf_buses by iterating over all valid num of VFs. This triggers FLR and generates functions changed events, even though host PF HCA is not enabled at this time. However, ECPF is not aware of this information, and still handles these events as usual. ECPF system will see massive number of reps are created, but destroyed immediately once creation finished. To eliminate this noise, a bit is added to host parameter context to indicate host PF is disabled. ECPF will not handle the VF changed event if this bit is set. Signed-off-by: Bodong Wang Reviewed-by: Daniel Jurgens Signed-off-by: Saeed Mahameed --- include/linux/mlx5/mlx5_ifc.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h index e2a77b5152a8..031db53e94ce 100644 --- a/include/linux/mlx5/mlx5_ifc.h +++ b/include/linux/mlx5/mlx5_ifc.h @@ -9823,7 +9823,8 @@ struct mlx5_ifc_mtrc_ctrl_bits { struct mlx5_ifc_host_params_context_bits { u8 host_number[0x8]; - u8 reserved_at_8[0x8]; + u8 reserved_at_8[0x7]; + u8 host_pf_disabled[0x1]; u8 host_num_of_vfs[0x10]; u8 host_total_vfs[0x10]; -- cgit v1.2.3 From d886aba677a0a75ad7fdb06e08418b481e09b036 Mon Sep 17 00:00:00 2001 From: Parav Pandit Date: Fri, 28 Jun 2019 22:36:06 +0000 Subject: net/mlx5: Reduce dependency on enabled_vfs counter and num_vfs While enabling SR-IOV, PCI core already checks that if SR-IOV is already enabled, it returns failure error code. Hence, remove such duplicate check from mlx5_core driver. While at it, make mlx5_device_disable_sriov() to perform cleanup of VFs in reverse order of mlx5_device_enable_sriov(). Signed-off-by: Parav Pandit Signed-off-by: Saeed Mahameed --- include/linux/mlx5/driver.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include') diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h index 155b8cbe1cc9..7658a4908431 100644 --- a/include/linux/mlx5/driver.h +++ b/include/linux/mlx5/driver.h @@ -468,7 +468,6 @@ struct mlx5_vf_context { struct mlx5_core_sriov { struct mlx5_vf_context *vfs_ctx; int num_vfs; - int enabled_vfs; u16 max_vfs; }; -- cgit v1.2.3 From e1d974d03e590cf8370d4820e8b467ee700925c3 Mon Sep 17 00:00:00 2001 From: Bodong Wang Date: Fri, 28 Jun 2019 22:36:13 +0000 Subject: net/mlx5: Handle host PF vport mac/guid for ECPF When ECPF is eswitch manager, it has the privilege to query and configure the mac and node guid of host PF. While vport number of host PF is 0, the vport command should be issued with other_vport set in this case as the cmd is issued by ECPF vport(0xfffe). Add a specific function to query own vport mac. Low level functions are used by vport manager to query/modify any vport mac and node guid. Signed-off-by: Bodong Wang Signed-off-by: Saeed Mahameed --- include/linux/mlx5/vport.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/mlx5/vport.h b/include/linux/mlx5/vport.h index 3d1c6cdbbba7..c147acc7bf70 100644 --- a/include/linux/mlx5/vport.h +++ b/include/linux/mlx5/vport.h @@ -69,7 +69,8 @@ u8 mlx5_query_vport_state(struct mlx5_core_dev *mdev, u8 opmod, u16 vport); int mlx5_modify_vport_admin_state(struct mlx5_core_dev *mdev, u8 opmod, u16 vport, u8 other_vport, u8 state); int mlx5_query_nic_vport_mac_address(struct mlx5_core_dev *mdev, - u16 vport, u8 *addr); + u16 vport, bool other, u8 *addr); +int mlx5_query_mac_address(struct mlx5_core_dev *mdev, u8 *addr); int mlx5_query_nic_vport_min_inline(struct mlx5_core_dev *mdev, u16 vport, u8 *min_inline); void mlx5_query_min_inline(struct mlx5_core_dev *mdev, u8 *min_inline); -- cgit v1.2.3 From f6455de0b0e52dcb11aeb503151b12ec87f9c5e4 Mon Sep 17 00:00:00 2001 From: Bodong Wang Date: Fri, 28 Jun 2019 22:36:15 +0000 Subject: net/mlx5: E-Switch, Refactor eswitch SR-IOV interface Devlink eswitch mode is not necessarily related to SR-IOV, e.g, ECPF can be at offload mode when SR-IOV is not enabled. Rename the interface and eswitch mode names to decouple from SR-IOV, and cleanup eswitch messages accordingly. Signed-off-by: Bodong Wang Signed-off-by: Saeed Mahameed --- include/linux/mlx5/eswitch.h | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/include/linux/mlx5/eswitch.h b/include/linux/mlx5/eswitch.h index 36cb641188b0..d4731199edb4 100644 --- a/include/linux/mlx5/eswitch.h +++ b/include/linux/mlx5/eswitch.h @@ -12,9 +12,9 @@ #define MLX5_ESWITCH_MANAGER(mdev) MLX5_CAP_GEN(mdev, eswitch_manager) enum { - SRIOV_NONE, - SRIOV_LEGACY, - SRIOV_OFFLOADS + MLX5_ESWITCH_NONE, + MLX5_ESWITCH_LEGACY, + MLX5_ESWITCH_OFFLOADS }; enum { -- cgit v1.2.3 From 411ec9e0b45792e2ac7c55f94a635d5ce894910b Mon Sep 17 00:00:00 2001 From: Bodong Wang Date: Fri, 28 Jun 2019 22:36:22 +0000 Subject: net/mlx5: E-Switch, Consider host PF for inline mode and vlan pop When ECPF is the eswitch manager, host PF is treated like other VFs. Driver should do the same for inline mode and vlan pop. Add new iterators to include host PF if ECPF is the eswitch manager. Signed-off-by: Bodong Wang Signed-off-by: Saeed Mahameed --- include/linux/mlx5/vport.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/mlx5/vport.h b/include/linux/mlx5/vport.h index c147acc7bf70..6cbf29229749 100644 --- a/include/linux/mlx5/vport.h +++ b/include/linux/mlx5/vport.h @@ -58,6 +58,7 @@ enum { MLX5_CAP_INLINE_MODE_NOT_REQUIRED, }; +/* Vport number for each function must keep unchanged */ enum { MLX5_VPORT_PF = 0x0, MLX5_VPORT_FIRST_VF = 0x1, -- cgit v1.2.3 From 362b87f5b1c6603b72699e8bb18661ecc4efc0bb Mon Sep 17 00:00:00 2001 From: "Jason A. Donenfeld" Date: Fri, 28 Jun 2019 16:40:21 +0200 Subject: netlink: use 48 byte ctx instead of 6 signed longs for callback People are inclined to stuff random things into cb->args[n] because it looks like an array of integers. Sometimes people even put u64s in there with comments noting that a certain member takes up two slots. The horror! Really this should mirror the usage of skb->cb, which are just 48 opaque bytes suitable for casting a struct. Then people can create their usual casting macros for accessing strongly typed members of a struct. As a plus, this also gives us the same amount of space on 32bit and 64bit. Signed-off-by: Jason A. Donenfeld Reviewed-by: Johannes Berg Signed-off-by: David S. Miller --- include/linux/netlink.h | 9 ++++++++- 1 file changed, 8 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/netlink.h b/include/linux/netlink.h index 593d1b9c33a8..205fa7b1f07a 100644 --- a/include/linux/netlink.h +++ b/include/linux/netlink.h @@ -192,7 +192,14 @@ struct netlink_callback { bool strict_check; u16 answer_flags; unsigned int prev_seq, seq; - long args[6]; + union { + u8 ctx[48]; + + /* args is deprecated. Cast a struct over ctx instead + * for proper type safety. + */ + long args[6]; + }; }; struct netlink_notify { -- cgit v1.2.3 From e33d2b74d805af0e4c8060f41040595ba105a520 Mon Sep 17 00:00:00 2001 From: Cong Wang Date: Fri, 28 Jun 2019 11:03:41 -0700 Subject: idr: fix overflow case for idr_for_each_entry_ul() idr_for_each_entry_ul() is buggy as it can't handle overflow case correctly. When we have an ID == UINT_MAX, it becomes an infinite loop. This happens when running on 32-bit CPU where unsigned long has the same size with unsigned int. There is no better way to fix this than casting it to a larger integer, but we can't just 64 bit integer on 32 bit CPU. Instead we could just use an additional integer to help us to detect this overflow case, that is, adding a new parameter to this macro. Fortunately tc action is its only user right now. Fixes: 65a206c01e8e ("net/sched: Change act_api and act_xxx modules to use IDR") Reported-by: Li Shuang Tested-by: Davide Caratti Cc: Matthew Wilcox Cc: Chris Mi Signed-off-by: Cong Wang Signed-off-by: David S. Miller --- include/linux/idr.h | 7 +++++-- 1 file changed, 5 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/idr.h b/include/linux/idr.h index ee7abae143d3..68528a72d10d 100644 --- a/include/linux/idr.h +++ b/include/linux/idr.h @@ -191,14 +191,17 @@ static inline void idr_preload_end(void) * idr_for_each_entry_ul() - Iterate over an IDR's elements of a given type. * @idr: IDR handle. * @entry: The type * to use as cursor. + * @tmp: A temporary placeholder for ID. * @id: Entry ID. * * @entry and @id do not need to be initialized before the loop, and * after normal termination @entry is left with the value NULL. This * is convenient for a "not found" value. */ -#define idr_for_each_entry_ul(idr, entry, id) \ - for (id = 0; ((entry) = idr_get_next_ul(idr, &(id))) != NULL; ++id) +#define idr_for_each_entry_ul(idr, entry, tmp, id) \ + for (tmp = 0, id = 0; \ + tmp <= id && ((entry) = idr_get_next_ul(idr, &(id))) != NULL; \ + tmp = id, ++id) /** * idr_for_each_entry_continue() - Continue iteration over an IDR's elements of a given type -- cgit v1.2.3 From d39d714969cda5cbda291402c8c6b1fb1047f42e Mon Sep 17 00:00:00 2001 From: Cong Wang Date: Fri, 28 Jun 2019 11:03:42 -0700 Subject: idr: introduce idr_for_each_entry_continue_ul() Similarly, other callers of idr_get_next_ul() suffer the same overflow bug as they don't handle it properly either. Introduce idr_for_each_entry_continue_ul() to help these callers iterate from a given ID. cls_flower needs more care here because it still has overflow when does arg->cookie++, we have to fold its nested loops into one and remove the arg->cookie++. Fixes: 01683a146999 ("net: sched: refactor flower walk to iterate over idr") Fixes: 12d6066c3b29 ("net/mlx5: Add flow counters idr") Reported-by: Li Shuang Cc: Davide Caratti Cc: Vlad Buslov Cc: Chris Mi Cc: Matthew Wilcox Signed-off-by: Cong Wang Tested-by: Davide Caratti Signed-off-by: David S. Miller --- include/linux/idr.h | 14 ++++++++++++++ 1 file changed, 14 insertions(+) (limited to 'include') diff --git a/include/linux/idr.h b/include/linux/idr.h index 68528a72d10d..4ec8986e5dfb 100644 --- a/include/linux/idr.h +++ b/include/linux/idr.h @@ -216,6 +216,20 @@ static inline void idr_preload_end(void) entry; \ ++id, (entry) = idr_get_next((idr), &(id))) +/** + * idr_for_each_entry_continue_ul() - Continue iteration over an IDR's elements of a given type + * @idr: IDR handle. + * @entry: The type * to use as a cursor. + * @tmp: A temporary placeholder for ID. + * @id: Entry ID. + * + * Continue to iterate over entries, continuing after the current position. + */ +#define idr_for_each_entry_continue_ul(idr, entry, tmp, id) \ + for (tmp = id; \ + tmp <= id && ((entry) = idr_get_next_ul(idr, &(id))) != NULL; \ + tmp = id, ++id) + /* * IDA - ID Allocator, use when translation from id to pointer isn't necessary. */ -- cgit v1.2.3 From acd3e96d53a24d219f720ed4012b62723ae05da1 Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Fri, 28 Jun 2019 16:11:39 -0700 Subject: net/tls: make sure offload also gets the keys wiped Commit 86029d10af18 ("tls: zero the crypto information from tls_context before freeing") added memzero_explicit() calls to clear the key material before freeing struct tls_context, but it missed tls_device.c has its own way of freeing this structure. Replace the missing free. Fixes: 86029d10af18 ("tls: zero the crypto information from tls_context before freeing") Signed-off-by: Jakub Kicinski Reviewed-by: Dirk van der Merwe Signed-off-by: David S. Miller --- include/net/tls.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/net/tls.h b/include/net/tls.h index 53d96bca220d..889df0312cd1 100644 --- a/include/net/tls.h +++ b/include/net/tls.h @@ -313,6 +313,7 @@ struct tls_offload_context_rx { (ALIGN(sizeof(struct tls_offload_context_rx), sizeof(void *)) + \ TLS_DRIVER_STATE_SIZE) +void tls_ctx_free(struct tls_context *ctx); int wait_on_pending_writer(struct sock *sk, long *timeo); int tls_sk_query(struct sock *sk, int optname, char __user *optval, int __user *optlen); -- cgit v1.2.3 From bb005f2a70742d66f8fe44d57e217c696e805d97 Mon Sep 17 00:00:00 2001 From: Ilias Apalodimas Date: Sat, 29 Jun 2019 08:23:24 +0300 Subject: net: page_pool: add helper function for retrieving dma direction Since the dma direction is stored in page pool params, offer an API helper for driver that choose not to keep track of it locally Signed-off-by: Ilias Apalodimas Acked-by: Jesper Dangaard Brouer Signed-off-by: David S. Miller --- include/net/page_pool.h | 9 +++++++++ 1 file changed, 9 insertions(+) (limited to 'include') diff --git a/include/net/page_pool.h b/include/net/page_pool.h index f07c518ef8a5..ee9c871d2043 100644 --- a/include/net/page_pool.h +++ b/include/net/page_pool.h @@ -112,6 +112,15 @@ static inline struct page *page_pool_dev_alloc_pages(struct page_pool *pool) return page_pool_alloc_pages(pool, gfp); } +/* get the stored dma direction. A driver might decide to treat this locally and + * avoid the extra cache line from page_pool to determine the direction + */ +static +inline enum dma_data_direction page_pool_get_dma_dir(struct page_pool *pool) +{ + return pool->p.dma_dir; +} + struct page_pool *page_pool_create(const struct page_pool_params *params); void __page_pool_free(struct page_pool *pool); -- cgit v1.2.3 From 4de83b88c66a1e4dba426b29766fb68e61d93792 Mon Sep 17 00:00:00 2001 From: Mahesh Bandewar Date: Mon, 1 Jul 2019 14:38:49 -0700 Subject: loopback: create blackhole net device similar to loopack. Create a blackhole net device that can be used for "dead" dst entries instead of loopback device. This blackhole device differs from loopback in few aspects: (a) It's not per-ns. (b) MTU on this device is ETH_MIN_MTU (c) The xmit function is essentially kfree_skb(). and (d) since it's not registered it won't have ifindex. Lower MTU effectively make the device not pass the MTU check during the route check when a dst associated with the skb is dead. Signed-off-by: Mahesh Bandewar Signed-off-by: David S. Miller --- include/linux/netdevice.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index eeacebd7debb..88292953aa6f 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -4870,4 +4870,6 @@ do { \ #define PTYPE_HASH_SIZE (16) #define PTYPE_HASH_MASK (PTYPE_HASH_SIZE - 1) +extern struct net_device *blackhole_netdev; + #endif /* _LINUX_NETDEVICE_H */ -- cgit v1.2.3 From 99f0eae653b2db64917d0b58099eb51e300b311d Mon Sep 17 00:00:00 2001 From: David Howells Date: Tue, 2 Jul 2019 16:04:19 +0100 Subject: rxrpc: Fix oops in tracepoint If the rxrpc_eproto tracepoint is enabled, an oops will be cause by the trace line that rxrpc_extract_header() tries to emit when a protocol error occurs (typically because the packet is short) because the call argument is NULL. Fix this by using ?: to assume 0 as the debug_id if call is NULL. This can then be induced by: echo -e '\0\0\0\0\0\0\0\0' | ncat -4u --send-only 20001 where addr has the following program running on it: #include #include #include #include #include #include #include int main(void) { struct sockaddr_rxrpc srx; int fd; memset(&srx, 0, sizeof(srx)); srx.srx_family = AF_RXRPC; srx.srx_service = 0; srx.transport_type = AF_INET; srx.transport_len = sizeof(srx.transport.sin); srx.transport.sin.sin_family = AF_INET; srx.transport.sin.sin_port = htons(0x4e21); fd = socket(AF_RXRPC, SOCK_DGRAM, AF_INET6); bind(fd, (struct sockaddr *)&srx, sizeof(srx)); sleep(20); return 0; } It results in the following oops. BUG: kernel NULL pointer dereference, address: 0000000000000340 #PF: supervisor read access in kernel mode #PF: error_code(0x0000) - not-present page ... RIP: 0010:trace_event_raw_event_rxrpc_rx_eproto+0x47/0xac ... Call Trace: rxrpc_extract_header+0x86/0x171 ? rcu_read_lock_sched_held+0x5d/0x63 ? rxrpc_new_skb+0xd4/0x109 rxrpc_input_packet+0xef/0x14fc ? rxrpc_input_data+0x986/0x986 udp_queue_rcv_one_skb+0xbf/0x3d0 udp_unicast_rcv_skb.isra.8+0x64/0x71 ip_protocol_deliver_rcu+0xe4/0x1b4 ip_local_deliver+0xf0/0x154 __netif_receive_skb_one_core+0x50/0x6c netif_receive_skb_internal+0x26b/0x2e9 napi_gro_receive+0xf8/0x1da rtl8169_poll+0x303/0x4c4 net_rx_action+0x10e/0x333 __do_softirq+0x1a5/0x38f irq_exit+0x54/0xc4 do_IRQ+0xda/0xf8 common_interrupt+0xf/0xf ... ? cpuidle_enter_state+0x23c/0x34d cpuidle_enter+0x2a/0x36 do_idle+0x163/0x1ea cpu_startup_entry+0x1d/0x1f start_secondary+0x157/0x172 secondary_startup_64+0xa4/0xb0 Fixes: a25e21f0bcd2 ("rxrpc, afs: Use debug_ids rather than pointers in traces") Signed-off-by: David Howells Reviewed-by: Marc Dionne Signed-off-by: David S. Miller --- include/trace/events/rxrpc.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/trace/events/rxrpc.h b/include/trace/events/rxrpc.h index d85816878a52..cc1d060cbf13 100644 --- a/include/trace/events/rxrpc.h +++ b/include/trace/events/rxrpc.h @@ -1379,7 +1379,7 @@ TRACE_EVENT(rxrpc_rx_eproto, ), TP_fast_assign( - __entry->call = call->debug_id; + __entry->call = call ? call->debug_id : 0; __entry->serial = serial; __entry->why = why; ), -- cgit v1.2.3 From 455302d1c9ae9318660aaeb9748a01ff414c9741 Mon Sep 17 00:00:00 2001 From: Ilya Maximets Date: Fri, 28 Jun 2019 11:04:07 +0300 Subject: xdp: fix hang while unregistering device bound to xdp socket Device that bound to XDP socket will not have zero refcount until the userspace application will not close it. This leads to hang inside 'netdev_wait_allrefs()' if device unregistering requested: # ip link del p1 < hang on recvmsg on netlink socket > # ps -x | grep ip 5126 pts/0 D+ 0:00 ip link del p1 # journalctl -b Jun 05 07:19:16 kernel: unregister_netdevice: waiting for p1 to become free. Usage count = 1 Jun 05 07:19:27 kernel: unregister_netdevice: waiting for p1 to become free. Usage count = 1 ... Fix that by implementing NETDEV_UNREGISTER event notification handler to properly clean up all the resources and unref device. This should also allow socket killing via ss(8) utility. Fixes: 965a99098443 ("xsk: add support for bind for Rx") Signed-off-by: Ilya Maximets Acked-by: Jonathan Lemon Signed-off-by: Daniel Borkmann --- include/net/xdp_sock.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include') diff --git a/include/net/xdp_sock.h b/include/net/xdp_sock.h index d074b6d60f8a..7da155164947 100644 --- a/include/net/xdp_sock.h +++ b/include/net/xdp_sock.h @@ -61,6 +61,11 @@ struct xdp_sock { struct xsk_queue *tx ____cacheline_aligned_in_smp; struct list_head list; bool zc; + enum { + XSK_READY = 0, + XSK_BOUND, + XSK_UNBOUND, + } state; /* Protects multiple processes in the control path */ struct mutex mutex; /* Mutual exclusion of NAPI TX thread and sendmsg error paths -- cgit v1.2.3 From 23729ff23186424e54b4d6678fcd526cdacef4d3 Mon Sep 17 00:00:00 2001 From: Stanislav Fomichev Date: Tue, 2 Jul 2019 09:13:56 -0700 Subject: bpf: add BPF_CGROUP_SOCK_OPS callback that is executed on every RTT Performance impact should be minimal because it's under a new BPF_SOCK_OPS_RTT_CB_FLAG flag that has to be explicitly enabled. Suggested-by: Eric Dumazet Cc: Eric Dumazet Cc: Priyaranjan Jha Cc: Yuchung Cheng Cc: Soheil Hassas Yeganeh Acked-by: Soheil Hassas Yeganeh Acked-by: Yuchung Cheng Signed-off-by: Stanislav Fomichev Signed-off-by: Daniel Borkmann --- include/net/tcp.h | 8 ++++++++ include/uapi/linux/bpf.h | 6 +++++- 2 files changed, 13 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/net/tcp.h b/include/net/tcp.h index 9d36cc88d043..e16d8a3fd3b4 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -2221,6 +2221,14 @@ static inline bool tcp_bpf_ca_needs_ecn(struct sock *sk) return (tcp_call_bpf(sk, BPF_SOCK_OPS_NEEDS_ECN, 0, NULL) == 1); } +static inline void tcp_bpf_rtt(struct sock *sk) +{ + struct tcp_sock *tp = tcp_sk(sk); + + if (BPF_SOCK_OPS_TEST_FLAG(tp, BPF_SOCK_OPS_RTT_CB_FLAG)) + tcp_call_bpf(sk, BPF_SOCK_OPS_RTT_CB, 0, NULL); +} + #if IS_ENABLED(CONFIG_SMC) extern struct static_key_false tcp_have_smc; #endif diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index cffea1826a1f..9cdd0aaeba06 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -1770,6 +1770,7 @@ union bpf_attr { * * **BPF_SOCK_OPS_RTO_CB_FLAG** (retransmission time out) * * **BPF_SOCK_OPS_RETRANS_CB_FLAG** (retransmission) * * **BPF_SOCK_OPS_STATE_CB_FLAG** (TCP state change) + * * **BPF_SOCK_OPS_RTT_CB_FLAG** (every RTT) * * Therefore, this function can be used to clear a callback flag by * setting the appropriate bit to zero. e.g. to disable the RTO @@ -3314,7 +3315,8 @@ struct bpf_sock_ops { #define BPF_SOCK_OPS_RTO_CB_FLAG (1<<0) #define BPF_SOCK_OPS_RETRANS_CB_FLAG (1<<1) #define BPF_SOCK_OPS_STATE_CB_FLAG (1<<2) -#define BPF_SOCK_OPS_ALL_CB_FLAGS 0x7 /* Mask of all currently +#define BPF_SOCK_OPS_RTT_CB_FLAG (1<<3) +#define BPF_SOCK_OPS_ALL_CB_FLAGS 0xF /* Mask of all currently * supported cb flags */ @@ -3369,6 +3371,8 @@ enum { BPF_SOCK_OPS_TCP_LISTEN_CB, /* Called on listen(2), right after * socket transition to LISTEN state. */ + BPF_SOCK_OPS_RTT_CB, /* Called on every RTT. + */ }; /* List of TCP states. There is a build check in net/ipv4/tcp.c to detect -- cgit v1.2.3 From 0357746d1e40a8226f68a42c8d7222a12d7c451f Mon Sep 17 00:00:00 2001 From: Stanislav Fomichev Date: Tue, 2 Jul 2019 09:13:58 -0700 Subject: bpf: add dsack_dups/delivered{, _ce} to bpf_tcp_sock Add more fields to bpf_tcp_sock that might be useful for debugging congestion control issues. Cc: Eric Dumazet Cc: Priyaranjan Jha Cc: Yuchung Cheng Cc: Soheil Hassas Yeganeh Acked-by: Soheil Hassas Yeganeh Acked-by: Yuchung Cheng Signed-off-by: Stanislav Fomichev Signed-off-by: Daniel Borkmann --- include/uapi/linux/bpf.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include') diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index 9cdd0aaeba06..bfb0b1a76684 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -3073,6 +3073,11 @@ struct bpf_tcp_sock { * sum(delta(snd_una)), or how many bytes * were acked. */ + __u32 dsack_dups; /* RFC4898 tcpEStatsStackDSACKDups + * total number of DSACK blocks received + */ + __u32 delivered; /* Total data packets delivered incl. rexmits */ + __u32 delivered_ce; /* Like the above but only ECE marked packets */ }; struct bpf_sock_tuple { -- cgit v1.2.3 From c2cb5e82a720c05b707701c75dfeb356fe184787 Mon Sep 17 00:00:00 2001 From: Stanislav Fomichev Date: Tue, 2 Jul 2019 09:13:59 -0700 Subject: bpf: add icsk_retransmits to bpf_tcp_sock Add some inet_connection_sock fields to bpf_tcp_sock that might be useful for debugging congestion control issues. Cc: Eric Dumazet Cc: Priyaranjan Jha Cc: Yuchung Cheng Cc: Soheil Hassas Yeganeh Acked-by: Soheil Hassas Yeganeh Acked-by: Yuchung Cheng Signed-off-by: Stanislav Fomichev Signed-off-by: Daniel Borkmann --- include/uapi/linux/bpf.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index bfb0b1a76684..ead27aebf491 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -3078,6 +3078,7 @@ struct bpf_tcp_sock { */ __u32 delivered; /* Total data packets delivered incl. rexmits */ __u32 delivered_ce; /* Like the above but only ECE marked packets */ + __u32 icsk_retransmits; /* Number of unrecovered [RTO] timeouts */ }; struct bpf_sock_tuple { -- cgit v1.2.3 From b9a7ba5562074855e8a3f92ea7e1174b61a3e87d Mon Sep 17 00:00:00 2001 From: Yishai Hadas Date: Sun, 30 Jun 2019 19:23:23 +0300 Subject: net/mlx5: Use event mask based on device capabilities Use the reported device capabilities for the supported user events (i.e. affiliated and un-affiliated) to set the EQ mask. As the event mask can be up to 256 defined by 4 entries of u64 change the applicable code to work accordingly. Signed-off-by: Yishai Hadas Acked-by: Saeed Mahameed Signed-off-by: Leon Romanovsky --- include/linux/mlx5/device.h | 6 +++++- include/linux/mlx5/eq.h | 2 +- include/linux/mlx5/mlx5_ifc.h | 13 ++++++++++--- 3 files changed, 16 insertions(+), 5 deletions(-) (limited to 'include') diff --git a/include/linux/mlx5/device.h b/include/linux/mlx5/device.h index 5e760067ac41..0d1abe097627 100644 --- a/include/linux/mlx5/device.h +++ b/include/linux/mlx5/device.h @@ -351,7 +351,7 @@ enum mlx5_event { MLX5_EVENT_TYPE_DEVICE_TRACER = 0x26, - MLX5_EVENT_TYPE_MAX = MLX5_EVENT_TYPE_DEVICE_TRACER + 1, + MLX5_EVENT_TYPE_MAX = 0x100, }; enum { @@ -1077,6 +1077,7 @@ enum mlx5_cap_type { MLX5_CAP_DEBUG, MLX5_CAP_RESERVED_14, MLX5_CAP_DEV_MEM, + MLX5_CAP_DEV_EVENT = 0x14, /* NUM OF CAP Types */ MLX5_CAP_NUM }; @@ -1255,6 +1256,9 @@ enum mlx5_qcam_feature_groups { #define MLX5_CAP64_DEV_MEM(mdev, cap)\ MLX5_GET64(device_mem_cap, mdev->caps.hca_cur[MLX5_CAP_DEV_MEM], cap) +#define MLX5_CAP_DEV_EVENT(mdev, cap)\ + MLX5_ADDR_OF(device_event_cap, (mdev)->caps.hca_cur[MLX5_CAP_DEV_EVENT], cap) + enum { MLX5_CMD_STAT_OK = 0x0, MLX5_CMD_STAT_INT_ERR = 0x1, diff --git a/include/linux/mlx5/eq.h b/include/linux/mlx5/eq.h index 70e16dcfb4c4..e49d8c0d4f26 100644 --- a/include/linux/mlx5/eq.h +++ b/include/linux/mlx5/eq.h @@ -15,7 +15,7 @@ struct mlx5_core_dev; struct mlx5_eq_param { u8 irq_index; int nent; - u64 mask; + u64 mask[4]; }; struct mlx5_eq * diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h index 031db53e94ce..4148c47a65ed 100644 --- a/include/linux/mlx5/mlx5_ifc.h +++ b/include/linux/mlx5/mlx5_ifc.h @@ -860,6 +860,12 @@ struct mlx5_ifc_device_mem_cap_bits { u8 reserved_at_180[0x680]; }; +struct mlx5_ifc_device_event_cap_bits { + u8 user_affiliated_events[4][0x40]; + + u8 user_unaffiliated_events[4][0x40]; +}; + enum { MLX5_ATOMIC_CAPS_ATOMIC_SIZE_QP_1_BYTE = 0x0, MLX5_ATOMIC_CAPS_ATOMIC_SIZE_QP_2_BYTES = 0x2, @@ -1017,7 +1023,8 @@ struct mlx5_ifc_cmd_hca_cap_bits { u8 log_max_srq_sz[0x8]; u8 log_max_qp_sz[0x8]; - u8 reserved_at_90[0x8]; + u8 event_cap[0x1]; + u8 reserved_at_91[0x7]; u8 prio_tag_required[0x1]; u8 reserved_at_99[0x2]; u8 log_max_qp[0x5]; @@ -7422,9 +7429,9 @@ struct mlx5_ifc_create_eq_in_bits { u8 reserved_at_280[0x40]; - u8 event_bitmask[0x40]; + u8 event_bitmask[4][0x40]; - u8 reserved_at_300[0x580]; + u8 reserved_at_3c0[0x4c0]; u8 pas[0][0x40]; }; -- cgit v1.2.3 From c0670781f54839fb9d0b2c0eaee58862601981bf Mon Sep 17 00:00:00 2001 From: Yishai Hadas Date: Sun, 30 Jun 2019 19:23:24 +0300 Subject: net/mlx5: Expose the API to register for ANY event Expose the API to register for ANY event, mlx5_ib will be able to use this functionality for its needs. Signed-off-by: Yishai Hadas Acked-by: Saeed Mahameed Signed-off-by: Leon Romanovsky --- include/linux/mlx5/driver.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h index 7658a4908431..24b02ab206c3 100644 --- a/include/linux/mlx5/driver.h +++ b/include/linux/mlx5/driver.h @@ -1043,6 +1043,8 @@ int mlx5_register_interface(struct mlx5_interface *intf); void mlx5_unregister_interface(struct mlx5_interface *intf); int mlx5_notifier_register(struct mlx5_core_dev *dev, struct notifier_block *nb); int mlx5_notifier_unregister(struct mlx5_core_dev *dev, struct notifier_block *nb); +int mlx5_eq_notifier_register(struct mlx5_core_dev *dev, struct mlx5_nb *nb); +int mlx5_eq_notifier_unregister(struct mlx5_core_dev *dev, struct mlx5_nb *nb); int mlx5_core_query_vendor_id(struct mlx5_core_dev *mdev, u32 *vendor_id); -- cgit v1.2.3 From 38164b771947be9baf06e78ffdfb650f8f3e908e Mon Sep 17 00:00:00 2001 From: Yishai Hadas Date: Sun, 30 Jun 2019 19:23:25 +0300 Subject: net/mlx5: mlx5_core_create_cq() enhancements Enhance mlx5_core_create_cq() to get the command out buffer from the callers to let them use the output. Signed-off-by: Yishai Hadas Acked-by: Saeed Mahameed Signed-off-by: Leon Romanovsky --- include/linux/mlx5/cq.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/mlx5/cq.h b/include/linux/mlx5/cq.h index 769326ea1d9b..e44157a2b7db 100644 --- a/include/linux/mlx5/cq.h +++ b/include/linux/mlx5/cq.h @@ -185,7 +185,7 @@ static inline void mlx5_cq_put(struct mlx5_core_cq *cq) } int mlx5_core_create_cq(struct mlx5_core_dev *dev, struct mlx5_core_cq *cq, - u32 *in, int inlen); + u32 *in, int inlen, u32 *out, int outlen); int mlx5_core_destroy_cq(struct mlx5_core_dev *dev, struct mlx5_core_cq *cq); int mlx5_core_query_cq(struct mlx5_core_dev *dev, struct mlx5_core_cq *cq, u32 *out, int outlen); -- cgit v1.2.3 From 4e0e2ea1886afe8c001971ff767f6670312a9b04 Mon Sep 17 00:00:00 2001 From: Yishai Hadas Date: Sun, 30 Jun 2019 19:23:27 +0300 Subject: net/mlx5: Report EQE data upon CQ completion Report EQE data upon CQ completion to let upper layers use this data. Signed-off-by: Yishai Hadas Acked-by: Saeed Mahameed Signed-off-by: Leon Romanovsky --- include/linux/mlx5/cq.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/mlx5/cq.h b/include/linux/mlx5/cq.h index e44157a2b7db..40748fc1b11b 100644 --- a/include/linux/mlx5/cq.h +++ b/include/linux/mlx5/cq.h @@ -47,7 +47,7 @@ struct mlx5_core_cq { struct completion free; unsigned vector; unsigned int irqn; - void (*comp) (struct mlx5_core_cq *); + void (*comp)(struct mlx5_core_cq *cq, struct mlx5_eqe *eqe); void (*event) (struct mlx5_core_cq *, enum mlx5_event); u32 cons_index; unsigned arm_sn; @@ -55,7 +55,7 @@ struct mlx5_core_cq { int pid; struct { struct list_head list; - void (*comp)(struct mlx5_core_cq *); + void (*comp)(struct mlx5_core_cq *cq, struct mlx5_eqe *eqe); void *priv; } tasklet_ctx; int reset_notify_added; -- cgit v1.2.3 From e4075c44287638b9a99430fea79a2d1468fbc27d Mon Sep 17 00:00:00 2001 From: Yishai Hadas Date: Sun, 30 Jun 2019 19:23:28 +0300 Subject: net/mlx5: Expose device definitions for object events Expose an extra device definitions for objects events. It includes: object_type values for legacy objects and generic data header for any other object. Signed-off-by: Yishai Hadas Acked-by: Saeed Mahameed Signed-off-by: Leon Romanovsky --- include/linux/mlx5/mlx5_ifc.h | 21 +++++++++++++++++++++ 1 file changed, 21 insertions(+) (limited to 'include') diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h index 4148c47a65ed..be92401a25a0 100644 --- a/include/linux/mlx5/mlx5_ifc.h +++ b/include/linux/mlx5/mlx5_ifc.h @@ -91,6 +91,20 @@ enum { enum { MLX5_OBJ_TYPE_GENEVE_TLV_OPT = 0x000b, + MLX5_OBJ_TYPE_MKEY = 0xff01, + MLX5_OBJ_TYPE_QP = 0xff02, + MLX5_OBJ_TYPE_PSV = 0xff03, + MLX5_OBJ_TYPE_RMP = 0xff04, + MLX5_OBJ_TYPE_XRC_SRQ = 0xff05, + MLX5_OBJ_TYPE_RQ = 0xff06, + MLX5_OBJ_TYPE_SQ = 0xff07, + MLX5_OBJ_TYPE_TIR = 0xff08, + MLX5_OBJ_TYPE_TIS = 0xff09, + MLX5_OBJ_TYPE_DCT = 0xff0a, + MLX5_OBJ_TYPE_XRQ = 0xff0b, + MLX5_OBJ_TYPE_RQT = 0xff0e, + MLX5_OBJ_TYPE_FLOW_COUNTER = 0xff0f, + MLX5_OBJ_TYPE_CQ = 0xff10, }; enum { @@ -9944,4 +9958,11 @@ struct mlx5_ifc_alloc_sf_in_bits { u8 reserved_at_60[0x20]; }; +struct mlx5_ifc_affiliated_event_header_bits { + u8 reserved_at_0[0x10]; + u8 obj_type[0x10]; + + u8 obj_id[0x20]; +}; + #endif /* MLX5_IFC_H */ -- cgit v1.2.3 From 2752b823169b216db142c4466b43269281962dcf Mon Sep 17 00:00:00 2001 From: Parav Pandit Date: Wed, 15 May 2019 00:04:27 -0500 Subject: net/mlx5: Introduce and use mlx5_eswitch_get_total_vports() Instead MLX5_TOTAL_VPORTS, use mlx5_eswitch_get_total_vports(). mlx5_eswitch_get_total_vports() in subsequent patch accounts for SF vports as well. Expanding MLX5_TOTAL_VPORTS macro would require exposing SF internals to more generic vport.h header file. Such exposure is not desired. Hence a mlx5_eswitch_get_total_vports() is introduced. Given that mlx5_eswitch_get_total_vports() API wants to work on const mlx5_core_dev*, change its helper functions also to accept const *dev. Signed-off-by: Parav Pandit Signed-off-by: Saeed Mahameed --- include/linux/mlx5/driver.h | 9 +++++---- include/linux/mlx5/eswitch.h | 3 +++ include/linux/mlx5/vport.h | 3 --- 3 files changed, 8 insertions(+), 7 deletions(-) (limited to 'include') diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h index 24b02ab206c3..031043341ed5 100644 --- a/include/linux/mlx5/driver.h +++ b/include/linux/mlx5/driver.h @@ -1085,7 +1085,7 @@ enum { MLX5_PCI_DEV_IS_VF = 1 << 0, }; -static inline bool mlx5_core_is_pf(struct mlx5_core_dev *dev) +static inline bool mlx5_core_is_pf(const struct mlx5_core_dev *dev) { return dev->coredev_type == MLX5_COREDEV_PF; } @@ -1095,17 +1095,18 @@ static inline bool mlx5_core_is_ecpf(struct mlx5_core_dev *dev) return dev->caps.embedded_cpu; } -static inline bool mlx5_core_is_ecpf_esw_manager(struct mlx5_core_dev *dev) +static inline bool +mlx5_core_is_ecpf_esw_manager(const struct mlx5_core_dev *dev) { return dev->caps.embedded_cpu && MLX5_CAP_GEN(dev, eswitch_manager); } -static inline bool mlx5_ecpf_vport_exists(struct mlx5_core_dev *dev) +static inline bool mlx5_ecpf_vport_exists(const struct mlx5_core_dev *dev) { return mlx5_core_is_pf(dev) && MLX5_CAP_ESW(dev, ecpf_vport_exists); } -static inline u16 mlx5_core_max_vfs(struct mlx5_core_dev *dev) +static inline u16 mlx5_core_max_vfs(const struct mlx5_core_dev *dev) { return dev->priv.sriov.max_vfs; } diff --git a/include/linux/mlx5/eswitch.h b/include/linux/mlx5/eswitch.h index d4731199edb4..61db37aa9642 100644 --- a/include/linux/mlx5/eswitch.h +++ b/include/linux/mlx5/eswitch.h @@ -66,6 +66,8 @@ struct mlx5_flow_handle * mlx5_eswitch_add_send_to_vport_rule(struct mlx5_eswitch *esw, int vport, u32 sqn); +u16 mlx5_eswitch_get_total_vports(const struct mlx5_core_dev *dev); + #ifdef CONFIG_MLX5_ESWITCH enum devlink_eswitch_encap_mode mlx5_eswitch_get_encap_mode(const struct mlx5_core_dev *dev); @@ -93,4 +95,5 @@ mlx5_eswitch_get_vport_metadata_for_match(const struct mlx5_eswitch *esw, return 0; }; #endif /* CONFIG_MLX5_ESWITCH */ + #endif diff --git a/include/linux/mlx5/vport.h b/include/linux/mlx5/vport.h index 6cbf29229749..16060fb9b5e5 100644 --- a/include/linux/mlx5/vport.h +++ b/include/linux/mlx5/vport.h @@ -44,9 +44,6 @@ MLX5_VPORT_UPLINK_PLACEHOLDER + \ MLX5_VPORT_ECPF_PLACEHOLDER(mdev)) -#define MLX5_TOTAL_VPORTS(mdev) (MLX5_SPECIAL_VPORTS(mdev) + \ - mlx5_core_max_vfs(mdev)) - #define MLX5_VPORT_MANAGER(mdev) \ (MLX5_CAP_GEN(mdev, vport_group_manager) && \ (MLX5_CAP_GEN(mdev, port_type) == MLX5_CAP_PORT_TYPE_ETH) && \ -- cgit v1.2.3 From a12ff35e0fb770b4d060298be147189313ec002c Mon Sep 17 00:00:00 2001 From: Eran Ben Elisha Date: Wed, 3 Apr 2019 13:05:50 +0300 Subject: net/mlx5: Introduce TLS TX offload hardware bits and structures Add TLS offload related IFC structs, layouts and enumerations. Signed-off-by: Eran Ben Elisha Signed-off-by: Tariq Toukan Signed-off-by: Saeed Mahameed --- include/linux/mlx5/device.h | 14 ++++++ include/linux/mlx5/mlx5_ifc.h | 104 ++++++++++++++++++++++++++++++++++++++++-- 2 files changed, 114 insertions(+), 4 deletions(-) (limited to 'include') diff --git a/include/linux/mlx5/device.h b/include/linux/mlx5/device.h index 0d1abe097627..7358d64e76fa 100644 --- a/include/linux/mlx5/device.h +++ b/include/linux/mlx5/device.h @@ -437,6 +437,7 @@ enum { MLX5_OPCODE_SET_PSV = 0x20, MLX5_OPCODE_GET_PSV = 0x21, MLX5_OPCODE_CHECK_PSV = 0x22, + MLX5_OPCODE_DUMP = 0x23, MLX5_OPCODE_RGET_PSV = 0x26, MLX5_OPCODE_RCHECK_PSV = 0x27, @@ -444,6 +445,14 @@ enum { }; +enum { + MLX5_OPC_MOD_TLS_TIS_STATIC_PARAMS = 0x20, +}; + +enum { + MLX5_OPC_MOD_TLS_TIS_PROGRESS_PARAMS = 0x20, +}; + enum { MLX5_SET_PORT_RESET_QKEY = 0, MLX5_SET_PORT_GUID0 = 16, @@ -1077,6 +1086,8 @@ enum mlx5_cap_type { MLX5_CAP_DEBUG, MLX5_CAP_RESERVED_14, MLX5_CAP_DEV_MEM, + MLX5_CAP_RESERVED_16, + MLX5_CAP_TLS, MLX5_CAP_DEV_EVENT = 0x14, /* NUM OF CAP Types */ MLX5_CAP_NUM @@ -1256,6 +1267,9 @@ enum mlx5_qcam_feature_groups { #define MLX5_CAP64_DEV_MEM(mdev, cap)\ MLX5_GET64(device_mem_cap, mdev->caps.hca_cur[MLX5_CAP_DEV_MEM], cap) +#define MLX5_CAP_TLS(mdev, cap) \ + MLX5_GET(tls_cap, (mdev)->caps.hca_cur[MLX5_CAP_TLS], cap) + #define MLX5_CAP_DEV_EVENT(mdev, cap)\ MLX5_ADDR_OF(device_event_cap, (mdev)->caps.hca_cur[MLX5_CAP_DEV_EVENT], cap) diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h index be92401a25a0..f03ec31e3232 100644 --- a/include/linux/mlx5/mlx5_ifc.h +++ b/include/linux/mlx5/mlx5_ifc.h @@ -973,6 +973,16 @@ struct mlx5_ifc_vector_calc_cap_bits { u8 reserved_at_c0[0x720]; }; +struct mlx5_ifc_tls_cap_bits { + u8 tls_1_2_aes_gcm_128[0x1]; + u8 tls_1_3_aes_gcm_128[0x1]; + u8 tls_1_2_aes_gcm_256[0x1]; + u8 tls_1_3_aes_gcm_256[0x1]; + u8 reserved_at_4[0x1c]; + + u8 reserved_at_20[0x7e0]; +}; + enum { MLX5_WQ_TYPE_LINKED_LIST = 0x0, MLX5_WQ_TYPE_CYCLIC = 0x1, @@ -1303,7 +1313,8 @@ struct mlx5_ifc_cmd_hca_cap_bits { u8 reserved_at_440[0x20]; - u8 reserved_at_460[0x3]; + u8 tls[0x1]; + u8 reserved_at_461[0x2]; u8 log_max_uctx[0x5]; u8 reserved_at_468[0x3]; u8 log_max_umem[0x5]; @@ -1328,7 +1339,9 @@ struct mlx5_ifc_cmd_hca_cap_bits { u8 max_geneve_tlv_option_data_len[0x5]; u8 reserved_at_570[0x10]; - u8 reserved_at_580[0x3c]; + u8 reserved_at_580[0x33]; + u8 log_max_dek[0x5]; + u8 reserved_at_5b8[0x4]; u8 mini_cqe_resp_stride_index[0x1]; u8 cqe_128_always[0x1]; u8 cqe_compression_128[0x1]; @@ -2607,6 +2620,7 @@ union mlx5_ifc_hca_cap_union_bits { struct mlx5_ifc_qos_cap_bits qos_cap; struct mlx5_ifc_debug_cap_bits debug_cap; struct mlx5_ifc_fpga_cap_bits fpga_cap; + struct mlx5_ifc_tls_cap_bits tls_cap; u8 reserved_at_0[0x8000]; }; @@ -2746,7 +2760,8 @@ struct mlx5_ifc_traffic_counter_bits { struct mlx5_ifc_tisc_bits { u8 strict_lag_tx_port_affinity[0x1]; - u8 reserved_at_1[0x3]; + u8 tls_en[0x1]; + u8 reserved_at_1[0x2]; u8 lag_tx_port_affinity[0x04]; u8 reserved_at_8[0x4]; @@ -2760,7 +2775,11 @@ struct mlx5_ifc_tisc_bits { u8 reserved_at_140[0x8]; u8 underlay_qpn[0x18]; - u8 reserved_at_160[0x3a0]; + + u8 reserved_at_160[0x8]; + u8 pd[0x18]; + + u8 reserved_at_180[0x380]; }; enum { @@ -9965,4 +9984,81 @@ struct mlx5_ifc_affiliated_event_header_bits { u8 obj_id[0x20]; }; +enum { + MLX5_HCA_CAP_GENERAL_OBJECT_TYPES_ENCRYPTION_KEY = BIT(0xc), +}; + +enum { + MLX5_GENERAL_OBJECT_TYPES_ENCRYPTION_KEY = 0xc, +}; + +struct mlx5_ifc_encryption_key_obj_bits { + u8 modify_field_select[0x40]; + + u8 reserved_at_40[0x14]; + u8 key_size[0x4]; + u8 reserved_at_58[0x4]; + u8 key_type[0x4]; + + u8 reserved_at_60[0x8]; + u8 pd[0x18]; + + u8 reserved_at_80[0x180]; + u8 key[8][0x20]; + + u8 reserved_at_300[0x500]; +}; + +struct mlx5_ifc_create_encryption_key_in_bits { + struct mlx5_ifc_general_obj_in_cmd_hdr_bits general_obj_in_cmd_hdr; + struct mlx5_ifc_encryption_key_obj_bits encryption_key_object; +}; + +enum { + MLX5_GENERAL_OBJECT_TYPE_ENCRYPTION_KEY_KEY_SIZE_128 = 0x0, + MLX5_GENERAL_OBJECT_TYPE_ENCRYPTION_KEY_KEY_SIZE_256 = 0x1, +}; + +enum { + MLX5_GENERAL_OBJECT_TYPE_ENCRYPTION_KEY_TYPE_DEK = 0x1, +}; + +struct mlx5_ifc_tls_static_params_bits { + u8 const_2[0x2]; + u8 tls_version[0x4]; + u8 const_1[0x2]; + u8 reserved_at_8[0x14]; + u8 encryption_standard[0x4]; + + u8 reserved_at_20[0x20]; + + u8 initial_record_number[0x40]; + + u8 resync_tcp_sn[0x20]; + + u8 gcm_iv[0x20]; + + u8 implicit_iv[0x40]; + + u8 reserved_at_100[0x8]; + u8 dek_index[0x18]; + + u8 reserved_at_120[0xe0]; +}; + +struct mlx5_ifc_tls_progress_params_bits { + u8 valid[0x1]; + u8 reserved_at_1[0x7]; + u8 pd[0x18]; + + u8 next_record_tcp_sn[0x20]; + + u8 hw_resync_tcp_sn[0x20]; + + u8 record_tracker_state[0x2]; + u8 auth_state[0x2]; + u8 reserved_at_64[0x4]; + u8 hw_offset_record_number[0x18]; +}; + #endif /* MLX5_IFC_H */ -- cgit v1.2.3 From 0718edf528c552c66a5dc3525ffb145971efa766 Mon Sep 17 00:00:00 2001 From: Tariq Toukan Date: Tue, 2 Jul 2019 17:12:09 +0300 Subject: net/mlx5: Properly name the generic WQE control field A generic WQE control field is used for different purposes in different cases. Use union to allow using the proper name in each case. Signed-off-by: Tariq Toukan Signed-off-by: Saeed Mahameed --- include/linux/mlx5/qp.h | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/mlx5/qp.h b/include/linux/mlx5/qp.h index d1f353c64797..127d224443e3 100644 --- a/include/linux/mlx5/qp.h +++ b/include/linux/mlx5/qp.h @@ -202,7 +202,12 @@ struct mlx5_wqe_ctrl_seg { u8 signature; u8 rsvd[2]; u8 fm_ce_se; - __be32 imm; + union { + __be32 general_id; + __be32 imm; + __be32 umr_mkey; + __be32 tisn; + }; }; #define MLX5_WQE_CTRL_DS_MASK 0x3f -- cgit v1.2.3 From e473093639945cb0a07ad4d51d5fd3fc3c3708cf Mon Sep 17 00:00:00 2001 From: Paolo Abeni Date: Wed, 3 Jul 2019 16:06:52 +0200 Subject: inet: factor out inet_send_prepare() The same code is replicated verbatim in multiple places, and the next patches will introduce an additional user for it. Factor out a helper and use it where appropriate. No functional change intended. Signed-off-by: Paolo Abeni Signed-off-by: David S. Miller --- include/net/inet_common.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/net/inet_common.h b/include/net/inet_common.h index 975901a95c0f..ae2ba897675c 100644 --- a/include/net/inet_common.h +++ b/include/net/inet_common.h @@ -25,6 +25,7 @@ int inet_dgram_connect(struct socket *sock, struct sockaddr *uaddr, int addr_len, int flags); int inet_accept(struct socket *sock, struct socket *newsock, int flags, bool kern); +int inet_send_prepare(struct sock *sk); int inet_sendmsg(struct socket *sock, struct msghdr *msg, size_t size); ssize_t inet_sendpage(struct socket *sock, struct page *page, int offset, size_t size, int flags); -- cgit v1.2.3 From f0c1aab2bd1ad131d9d7528b9dcbf9253a74e5da Mon Sep 17 00:00:00 2001 From: Pablo Neira Ayuso Date: Fri, 21 Jun 2019 17:37:48 +0200 Subject: netfilter: rename nf_SYNPROXY.h to nf_synproxy.h Uppercase is a reminiscence from the iptables infrastructure, rename this header before this is included in stable kernels. Signed-off-by: Pablo Neira Ayuso --- include/uapi/linux/netfilter/nf_SYNPROXY.h | 19 ------------------- include/uapi/linux/netfilter/nf_synproxy.h | 19 +++++++++++++++++++ include/uapi/linux/netfilter/xt_SYNPROXY.h | 2 +- 3 files changed, 20 insertions(+), 20 deletions(-) delete mode 100644 include/uapi/linux/netfilter/nf_SYNPROXY.h create mode 100644 include/uapi/linux/netfilter/nf_synproxy.h (limited to 'include') diff --git a/include/uapi/linux/netfilter/nf_SYNPROXY.h b/include/uapi/linux/netfilter/nf_SYNPROXY.h deleted file mode 100644 index 068d1b3a6f06..000000000000 --- a/include/uapi/linux/netfilter/nf_SYNPROXY.h +++ /dev/null @@ -1,19 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -#ifndef _NF_SYNPROXY_H -#define _NF_SYNPROXY_H - -#include - -#define NF_SYNPROXY_OPT_MSS 0x01 -#define NF_SYNPROXY_OPT_WSCALE 0x02 -#define NF_SYNPROXY_OPT_SACK_PERM 0x04 -#define NF_SYNPROXY_OPT_TIMESTAMP 0x08 -#define NF_SYNPROXY_OPT_ECN 0x10 - -struct nf_synproxy_info { - __u8 options; - __u8 wscale; - __u16 mss; -}; - -#endif /* _NF_SYNPROXY_H */ diff --git a/include/uapi/linux/netfilter/nf_synproxy.h b/include/uapi/linux/netfilter/nf_synproxy.h new file mode 100644 index 000000000000..068d1b3a6f06 --- /dev/null +++ b/include/uapi/linux/netfilter/nf_synproxy.h @@ -0,0 +1,19 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _NF_SYNPROXY_H +#define _NF_SYNPROXY_H + +#include + +#define NF_SYNPROXY_OPT_MSS 0x01 +#define NF_SYNPROXY_OPT_WSCALE 0x02 +#define NF_SYNPROXY_OPT_SACK_PERM 0x04 +#define NF_SYNPROXY_OPT_TIMESTAMP 0x08 +#define NF_SYNPROXY_OPT_ECN 0x10 + +struct nf_synproxy_info { + __u8 options; + __u8 wscale; + __u16 mss; +}; + +#endif /* _NF_SYNPROXY_H */ diff --git a/include/uapi/linux/netfilter/xt_SYNPROXY.h b/include/uapi/linux/netfilter/xt_SYNPROXY.h index 4d5611d647df..19c04ed86172 100644 --- a/include/uapi/linux/netfilter/xt_SYNPROXY.h +++ b/include/uapi/linux/netfilter/xt_SYNPROXY.h @@ -2,7 +2,7 @@ #ifndef _XT_SYNPROXY_H #define _XT_SYNPROXY_H -#include +#include #define XT_SYNPROXY_OPT_MSS NF_SYNPROXY_OPT_MSS #define XT_SYNPROXY_OPT_WSCALE NF_SYNPROXY_OPT_WSCALE -- cgit v1.2.3 From 0d9cb300acad29f25ea23d2592e69970bc61f14c Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Tue, 2 Jul 2019 20:41:14 +0200 Subject: netfilter: nf_queue: remove unused hook entries pointer Its not used anywhere, so remove this. Signed-off-by: Florian Westphal Signed-off-by: Pablo Neira Ayuso --- include/net/netfilter/nf_queue.h | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) (limited to 'include') diff --git a/include/net/netfilter/nf_queue.h b/include/net/netfilter/nf_queue.h index 7239105d9d2e..3cb6dcf53a4e 100644 --- a/include/net/netfilter/nf_queue.h +++ b/include/net/netfilter/nf_queue.h @@ -120,6 +120,5 @@ nfqueue_hash(const struct sk_buff *skb, u16 queue, u16 queues_total, u8 family, } int nf_queue(struct sk_buff *skb, struct nf_hook_state *state, - const struct nf_hook_entries *entries, unsigned int index, - unsigned int verdict); + unsigned int index, unsigned int verdict); #endif /* _NF_QUEUE_H */ -- cgit v1.2.3 From 6f7b841bc939e7c811ad32427b58d54edbcfa6ed Mon Sep 17 00:00:00 2001 From: Vadim Fedorenko Date: Mon, 1 Jul 2019 19:49:34 +0300 Subject: ipvs: allow tunneling with gre encapsulation windows real servers can handle gre tunnels, this patch allows gre encapsulation with the tunneling method, thereby letting ipvs be load balancer for windows-based services Signed-off-by: Vadim Fedorenko Acked-by: Julian Anastasov Signed-off-by: Simon Horman Signed-off-by: Pablo Neira Ayuso --- include/uapi/linux/ip_vs.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/uapi/linux/ip_vs.h b/include/uapi/linux/ip_vs.h index e4f18061a4fd..4102ddcb4e14 100644 --- a/include/uapi/linux/ip_vs.h +++ b/include/uapi/linux/ip_vs.h @@ -128,6 +128,7 @@ enum { IP_VS_CONN_F_TUNNEL_TYPE_IPIP = 0, /* IPIP */ IP_VS_CONN_F_TUNNEL_TYPE_GUE, /* GUE */ + IP_VS_CONN_F_TUNNEL_TYPE_GRE, /* GRE */ IP_VS_CONN_F_TUNNEL_TYPE_MAX, }; -- cgit v1.2.3 From f8efee08dd9d41ab71010e9b16c9ead51753b7d6 Mon Sep 17 00:00:00 2001 From: Mark Zhang Date: Tue, 2 Jul 2019 13:02:30 +0300 Subject: net/mlx5: Add rts2rts_qp_counters_set_id field in hca cap Add rts2rts_qp_counters_set_id field in hca cap so that RTS2RTS qp modification can be used to change the counter of a QP. Signed-off-by: Mark Zhang Reviewed-by: Majd Dibbiny Acked-by: Saeed Mahameed Signed-off-by: Leon Romanovsky --- include/linux/mlx5/mlx5_ifc.h | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h index f03ec31e3232..06881b79167e 100644 --- a/include/linux/mlx5/mlx5_ifc.h +++ b/include/linux/mlx5/mlx5_ifc.h @@ -1096,7 +1096,9 @@ struct mlx5_ifc_cmd_hca_cap_bits { u8 cc_modify_allowed[0x1]; u8 start_pad[0x1]; u8 cache_line_128byte[0x1]; - u8 reserved_at_165[0xa]; + u8 reserved_at_165[0x4]; + u8 rts2rts_qp_counters_set_id[0x1]; + u8 reserved_at_16a[0x5]; u8 qcam_reg[0x1]; u8 gid_table_size[0x10]; -- cgit v1.2.3 From 07a4ddec3ce9b0a533b5f90f582f1057390d5e63 Mon Sep 17 00:00:00 2001 From: Vincent Bernat Date: Tue, 2 Jul 2019 19:43:54 +0200 Subject: bonding: add an option to specify a delay between peer notifications Currently, gratuitous ARP/ND packets are sent every `miimon' milliseconds. This commit allows a user to specify a custom delay through a new option, `peer_notif_delay'. Like for `updelay' and `downdelay', this delay should be a multiple of `miimon' to avoid managing an additional work queue. The configuration logic is copied from `updelay' and `downdelay'. However, the default value cannot be set using a module parameter: Netlink or sysfs should be used to configure this feature. When setting `miimon' to 100 and `peer_notif_delay' to 500, we can observe the 500 ms delay is respected: 20:30:19.354693 ARP, Request who-has 203.0.113.10 tell 203.0.113.10, length 28 20:30:19.874892 ARP, Request who-has 203.0.113.10 tell 203.0.113.10, length 28 20:30:20.394919 ARP, Request who-has 203.0.113.10 tell 203.0.113.10, length 28 20:30:20.914963 ARP, Request who-has 203.0.113.10 tell 203.0.113.10, length 28 In bond_mii_monitor(), I have tried to keep the lock logic readable. The change is due to the fact we cannot rely on a notification to lower the value of `bond->send_peer_notif' as `NETDEV_NOTIFY_PEERS' is only triggered once every N times, while we need to decrement the counter each time. iproute2 also needs to be updated to be able to specify this new attribute through `ip link'. Signed-off-by: Vincent Bernat Signed-off-by: David S. Miller --- include/net/bond_options.h | 1 + include/net/bonding.h | 1 + include/uapi/linux/if_link.h | 1 + 3 files changed, 3 insertions(+) (limited to 'include') diff --git a/include/net/bond_options.h b/include/net/bond_options.h index 2a05cc349018..9d382f2f0bc5 100644 --- a/include/net/bond_options.h +++ b/include/net/bond_options.h @@ -63,6 +63,7 @@ enum { BOND_OPT_AD_ACTOR_SYSTEM, BOND_OPT_AD_USER_PORT_KEY, BOND_OPT_NUM_PEER_NOTIF_ALIAS, + BOND_OPT_PEER_NOTIF_DELAY, BOND_OPT_LAST }; diff --git a/include/net/bonding.h b/include/net/bonding.h index 676e7fae05a3..f7fe45689142 100644 --- a/include/net/bonding.h +++ b/include/net/bonding.h @@ -123,6 +123,7 @@ struct bond_params { int fail_over_mac; int updelay; int downdelay; + int peer_notif_delay; int lacp_fast; unsigned int min_links; int ad_select; diff --git a/include/uapi/linux/if_link.h b/include/uapi/linux/if_link.h index 6f75bda2c2d7..4a8c02cafa9a 100644 --- a/include/uapi/linux/if_link.h +++ b/include/uapi/linux/if_link.h @@ -636,6 +636,7 @@ enum { IFLA_BOND_AD_USER_PORT_KEY, IFLA_BOND_AD_ACTOR_SYSTEM, IFLA_BOND_TLB_DYNAMIC_LB, + IFLA_BOND_PEER_NOTIF_DELAY, __IFLA_BOND_MAX, }; -- cgit v1.2.3 From ad49d86e07a497e834cb06f2b151dccd75f8e148 Mon Sep 17 00:00:00 2001 From: Fernando Fernandez Mancera Date: Wed, 26 Jun 2019 12:59:19 +0200 Subject: netfilter: nf_tables: Add synproxy support Add synproxy support for nf_tables. This behaves like the iptables synproxy target but it is structured in a way that allows us to propose improvements in the future. Signed-off-by: Fernando Fernandez Mancera Signed-off-by: Pablo Neira Ayuso --- include/net/netfilter/nf_conntrack_synproxy.h | 1 + include/net/netfilter/nf_synproxy.h | 5 +++++ include/uapi/linux/netfilter/nf_synproxy.h | 4 ++++ include/uapi/linux/netfilter/nf_tables.h | 16 ++++++++++++++++ 4 files changed, 26 insertions(+) (limited to 'include') diff --git a/include/net/netfilter/nf_conntrack_synproxy.h b/include/net/netfilter/nf_conntrack_synproxy.h index c5659dcf5b1a..8f00125b06f4 100644 --- a/include/net/netfilter/nf_conntrack_synproxy.h +++ b/include/net/netfilter/nf_conntrack_synproxy.h @@ -2,6 +2,7 @@ #ifndef _NF_CONNTRACK_SYNPROXY_H #define _NF_CONNTRACK_SYNPROXY_H +#include #include struct nf_conn_synproxy { diff --git a/include/net/netfilter/nf_synproxy.h b/include/net/netfilter/nf_synproxy.h index 3e8b3f03b687..87d73fb5279d 100644 --- a/include/net/netfilter/nf_synproxy.h +++ b/include/net/netfilter/nf_synproxy.h @@ -39,6 +39,11 @@ unsigned int ipv6_synproxy_hook(void *priv, struct sk_buff *skb, const struct nf_hook_state *nhs); int nf_synproxy_ipv6_init(struct synproxy_net *snet, struct net *net); void nf_synproxy_ipv6_fini(struct synproxy_net *snet, struct net *net); +#else +static inline int +nf_synproxy_ipv6_init(struct synproxy_net *snet, struct net *net) { return 0; } +static inline void +nf_synproxy_ipv6_fini(struct synproxy_net *snet, struct net *net) {}; #endif /* CONFIG_IPV6 */ #endif /* _NF_SYNPROXY_SHARED_H */ diff --git a/include/uapi/linux/netfilter/nf_synproxy.h b/include/uapi/linux/netfilter/nf_synproxy.h index 068d1b3a6f06..6f3791c8946f 100644 --- a/include/uapi/linux/netfilter/nf_synproxy.h +++ b/include/uapi/linux/netfilter/nf_synproxy.h @@ -9,6 +9,10 @@ #define NF_SYNPROXY_OPT_SACK_PERM 0x04 #define NF_SYNPROXY_OPT_TIMESTAMP 0x08 #define NF_SYNPROXY_OPT_ECN 0x10 +#define NF_SYNPROXY_OPT_MASK (NF_SYNPROXY_OPT_MSS | \ + NF_SYNPROXY_OPT_WSCALE | \ + NF_SYNPROXY_OPT_SACK_PERM | \ + NF_SYNPROXY_OPT_TIMESTAMP) struct nf_synproxy_info { __u8 options; diff --git a/include/uapi/linux/netfilter/nf_tables.h b/include/uapi/linux/netfilter/nf_tables.h index c6c8ec5c7c00..c53d581643fe 100644 --- a/include/uapi/linux/netfilter/nf_tables.h +++ b/include/uapi/linux/netfilter/nf_tables.h @@ -1551,6 +1551,22 @@ enum nft_osf_flags { NFT_OSF_F_VERSION = (1 << 0), }; +/** + * enum nft_synproxy_attributes - nf_tables synproxy expression netlink attributes + * + * @NFTA_SYNPROXY_MSS: mss value sent to the backend (NLA_U16) + * @NFTA_SYNPROXY_WSCALE: wscale value sent to the backend (NLA_U8) + * @NFTA_SYNPROXY_FLAGS: flags (NLA_U32) + */ +enum nft_synproxy_attributes { + NFTA_SYNPROXY_UNSPEC, + NFTA_SYNPROXY_MSS, + NFTA_SYNPROXY_WSCALE, + NFTA_SYNPROXY_FLAGS, + __NFTA_SYNPROXY_MAX, +}; +#define NFTA_SYNPROXY_MAX (__NFTA_SYNPROXY_MAX - 1) + /** * enum nft_device_attributes - nf_tables device netlink attributes * -- cgit v1.2.3 From 30e103fe24debce6f35f2e53cc763ed7be292df3 Mon Sep 17 00:00:00 2001 From: wenxu Date: Fri, 5 Jul 2019 21:16:32 +0800 Subject: netfilter: nft_meta: move bridge meta keys into nft_meta_bridge Separate bridge meta key from nft_meta to meta_bridge to avoid a dependency between the bridge module and nft_meta when using the bridge API available through include/linux/if_bridge.h Signed-off-by: wenxu Reviewed-by: Nikolay Aleksandrov Signed-off-by: Pablo Neira Ayuso --- include/net/netfilter/nft_meta.h | 44 ++++++++++++++++++++++++++++++++++++++++ 1 file changed, 44 insertions(+) create mode 100644 include/net/netfilter/nft_meta.h (limited to 'include') diff --git a/include/net/netfilter/nft_meta.h b/include/net/netfilter/nft_meta.h new file mode 100644 index 000000000000..5c69e9b09388 --- /dev/null +++ b/include/net/netfilter/nft_meta.h @@ -0,0 +1,44 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _NFT_META_H_ +#define _NFT_META_H_ + +struct nft_meta { + enum nft_meta_keys key:8; + union { + enum nft_registers dreg:8; + enum nft_registers sreg:8; + }; +}; + +extern const struct nla_policy nft_meta_policy[]; + +int nft_meta_get_init(const struct nft_ctx *ctx, + const struct nft_expr *expr, + const struct nlattr * const tb[]); + +int nft_meta_set_init(const struct nft_ctx *ctx, + const struct nft_expr *expr, + const struct nlattr * const tb[]); + +int nft_meta_get_dump(struct sk_buff *skb, + const struct nft_expr *expr); + +int nft_meta_set_dump(struct sk_buff *skb, + const struct nft_expr *expr); + +void nft_meta_get_eval(const struct nft_expr *expr, + struct nft_regs *regs, + const struct nft_pktinfo *pkt); + +void nft_meta_set_eval(const struct nft_expr *expr, + struct nft_regs *regs, + const struct nft_pktinfo *pkt); + +void nft_meta_set_destroy(const struct nft_ctx *ctx, + const struct nft_expr *expr); + +int nft_meta_set_validate(const struct nft_ctx *ctx, + const struct nft_expr *expr, + const struct nft_data **data); + +#endif -- cgit v1.2.3 From 7582f5b70f9a2335f3713edb9a2614a50f1f1a90 Mon Sep 17 00:00:00 2001 From: Pablo Neira Ayuso Date: Fri, 5 Jul 2019 21:16:34 +0800 Subject: bridge: add br_vlan_get_pvid_rcu() This new function allows you to fetch bridge pvid from packet path. Signed-off-by: Pablo Neira Ayuso Acked-by: Nikolay Aleksandrov --- 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 f3fab5d0ea97..950db1dad830 100644 --- a/include/linux/if_bridge.h +++ b/include/linux/if_bridge.h @@ -88,6 +88,7 @@ static inline bool br_multicast_router(const struct net_device *dev) #if IS_ENABLED(CONFIG_BRIDGE) && IS_ENABLED(CONFIG_BRIDGE_VLAN_FILTERING) bool br_vlan_enabled(const struct net_device *dev); int br_vlan_get_pvid(const struct net_device *dev, u16 *p_pvid); +int br_vlan_get_pvid_rcu(const struct net_device *dev, u16 *p_pvid); int br_vlan_get_info(const struct net_device *dev, u16 vid, struct bridge_vlan_info *p_vinfo); #else @@ -101,6 +102,11 @@ static inline int br_vlan_get_pvid(const struct net_device *dev, u16 *p_pvid) return -EINVAL; } +static inline int br_vlan_get_pvid_rcu(const struct net_device *dev, u16 *p_pvid) +{ + return -EINVAL; +} + static inline int br_vlan_get_info(const struct net_device *dev, u16 vid, struct bridge_vlan_info *p_vinfo) { -- cgit v1.2.3 From c54c7c685494fc0f1662091d4d0c4fc26e810471 Mon Sep 17 00:00:00 2001 From: wenxu Date: Fri, 5 Jul 2019 21:16:35 +0800 Subject: netfilter: nft_meta_bridge: add NFT_META_BRI_IIFPVID support This patch allows you to match on the bridge port pvid, eg. nft add rule bridge firewall zones counter meta ibrpvid 10 Signed-off-by: wenxu Reviewed-by: Nikolay Aleksandrov Signed-off-by: Pablo Neira Ayuso --- include/uapi/linux/netfilter/nf_tables.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/uapi/linux/netfilter/nf_tables.h b/include/uapi/linux/netfilter/nf_tables.h index c53d581643fe..87474920615a 100644 --- a/include/uapi/linux/netfilter/nf_tables.h +++ b/include/uapi/linux/netfilter/nf_tables.h @@ -795,6 +795,7 @@ enum nft_exthdr_attributes { * @NFT_META_SECPATH: boolean, secpath_exists (!!skb->sp) * @NFT_META_IIFKIND: packet input interface kind name (dev->rtnl_link_ops->kind) * @NFT_META_OIFKIND: packet output interface kind name (dev->rtnl_link_ops->kind) + * @NFT_META_BRI_IIFPVID: packet input bridge port pvid */ enum nft_meta_keys { NFT_META_LEN, @@ -825,6 +826,7 @@ enum nft_meta_keys { NFT_META_SECPATH, NFT_META_IIFKIND, NFT_META_OIFKIND, + NFT_META_BRI_IIFPVID, }; /** -- cgit v1.2.3 From 31aed46fedbba65abece57e14d24f00b52389c4f Mon Sep 17 00:00:00 2001 From: wenxu Date: Fri, 5 Jul 2019 21:16:36 +0800 Subject: bridge: add br_vlan_get_proto() This new function allows you to fetch the bridge port vlan protocol. Signed-off-by: wenxu Acked-by: Nikolay Aleksandrov Signed-off-by: Pablo Neira Ayuso --- 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 950db1dad830..9e57c4411734 100644 --- a/include/linux/if_bridge.h +++ b/include/linux/if_bridge.h @@ -89,6 +89,7 @@ static inline bool br_multicast_router(const struct net_device *dev) bool br_vlan_enabled(const struct net_device *dev); int br_vlan_get_pvid(const struct net_device *dev, u16 *p_pvid); int br_vlan_get_pvid_rcu(const struct net_device *dev, u16 *p_pvid); +int br_vlan_get_proto(const struct net_device *dev, u16 *p_proto); int br_vlan_get_info(const struct net_device *dev, u16 vid, struct bridge_vlan_info *p_vinfo); #else @@ -102,6 +103,11 @@ static inline int br_vlan_get_pvid(const struct net_device *dev, u16 *p_pvid) return -EINVAL; } +static inline int br_vlan_get_proto(const struct net_device *dev, u16 *p_proto) +{ + return -EINVAL; +} + static inline int br_vlan_get_pvid_rcu(const struct net_device *dev, u16 *p_pvid) { return -EINVAL; -- cgit v1.2.3 From 2a3a93ef0ba5166e8b5766bb232f216fd412d40b Mon Sep 17 00:00:00 2001 From: wenxu Date: Fri, 5 Jul 2019 21:16:37 +0800 Subject: netfilter: nft_meta_bridge: Add NFT_META_BRI_IIFVPROTO support This patch allows you to match on bridge vlan protocol, eg. nft add rule bridge firewall zones counter meta ibrvproto 0x8100 Signed-off-by: wenxu Reviewed-by: Nikolay Aleksandrov Signed-off-by: Pablo Neira Ayuso --- include/uapi/linux/netfilter/nf_tables.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/uapi/linux/netfilter/nf_tables.h b/include/uapi/linux/netfilter/nf_tables.h index 87474920615a..0e3462dfb182 100644 --- a/include/uapi/linux/netfilter/nf_tables.h +++ b/include/uapi/linux/netfilter/nf_tables.h @@ -796,6 +796,7 @@ enum nft_exthdr_attributes { * @NFT_META_IIFKIND: packet input interface kind name (dev->rtnl_link_ops->kind) * @NFT_META_OIFKIND: packet output interface kind name (dev->rtnl_link_ops->kind) * @NFT_META_BRI_IIFPVID: packet input bridge port pvid + * @NFT_META_BRI_IIFVPROTO: packet input bridge vlan proto */ enum nft_meta_keys { NFT_META_LEN, @@ -827,6 +828,7 @@ enum nft_meta_keys { NFT_META_IIFKIND, NFT_META_OIFKIND, NFT_META_BRI_IIFPVID, + NFT_META_BRI_IIFVPROTO, }; /** -- cgit v1.2.3 From e4aa33ad595936391f7356f25c0c839011f14ead Mon Sep 17 00:00:00 2001 From: Li RongQing Date: Thu, 4 Jul 2019 17:03:26 +0800 Subject: net: remove unused parameter from skb_checksum_try_convert the check parameter is never used Signed-off-by: Li RongQing Signed-off-by: David S. Miller --- include/linux/skbuff.h | 8 +++----- 1 file changed, 3 insertions(+), 5 deletions(-) (limited to 'include') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index b5d427b149c9..7ece49d5f8ef 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -3919,18 +3919,16 @@ static inline bool __skb_checksum_convert_check(struct sk_buff *skb) return (skb->ip_summed == CHECKSUM_NONE && skb->csum_valid); } -static inline void __skb_checksum_convert(struct sk_buff *skb, - __sum16 check, __wsum pseudo) +static inline void __skb_checksum_convert(struct sk_buff *skb, __wsum pseudo) { skb->csum = ~pseudo; skb->ip_summed = CHECKSUM_COMPLETE; } -#define skb_checksum_try_convert(skb, proto, check, compute_pseudo) \ +#define skb_checksum_try_convert(skb, proto, compute_pseudo) \ do { \ if (__skb_checksum_convert_check(skb)) \ - __skb_checksum_convert(skb, check, \ - compute_pseudo(skb, proto)); \ + __skb_checksum_convert(skb, compute_pseudo(skb, proto)); \ } while (0) static inline void skb_remcsum_adjust_partial(struct sk_buff *skb, void *ptr, -- cgit v1.2.3 From e2869fb2068be603b46cd62bc980b4765948c6ed Mon Sep 17 00:00:00 2001 From: Tariq Toukan Date: Fri, 5 Jul 2019 18:30:12 +0300 Subject: net/mlx5: Kconfig, Better organize compilation flags Always contain all acceleration functions declarations in 'accel' files, independent to the flags setting. For this, introduce new flags CONFIG_FPGA_{IPSEC/TLS} and use stubs where needed. This obsoletes the need for stubs in 'fpga' files. Remove them. Also use the new flags in Makefile, to decide whether to compile TLS-specific or IPSEC-specific objects, or not. Signed-off-by: Tariq Toukan Signed-off-by: Saeed Mahameed Signed-off-by: David S. Miller --- include/linux/mlx5/accel.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/mlx5/accel.h b/include/linux/mlx5/accel.h index 70e7e5673ce9..5613e677a5f9 100644 --- a/include/linux/mlx5/accel.h +++ b/include/linux/mlx5/accel.h @@ -114,7 +114,7 @@ enum mlx5_accel_ipsec_cap { MLX5_ACCEL_IPSEC_CAP_TX_IV_IS_ESN = 1 << 7, }; -#ifdef CONFIG_MLX5_ACCEL +#ifdef CONFIG_MLX5_FPGA_IPSEC u32 mlx5_accel_ipsec_device_caps(struct mlx5_core_dev *mdev); -- cgit v1.2.3 From 302975cba1a4244d84e645773c82edbcfae1875f Mon Sep 17 00:00:00 2001 From: Spoorthi Ravishankar Koppad Date: Fri, 21 Jun 2019 14:51:56 +0530 Subject: Bluetooth: Add support for LE ping feature Changes made to add HCI Write Authenticated Payload timeout command for LE Ping feature. As per the Core Specification 5.0 Volume 2 Part E Section 7.3.94, the following code changes implements HCI Write Authenticated Payload timeout command for LE Ping feature. Signed-off-by: Spoorthi Ravishankar Koppad Signed-off-by: Marcel Holtmann --- include/net/bluetooth/hci.h | 20 ++++++++++++++++++++ include/net/bluetooth/hci_core.h | 4 ++++ 2 files changed, 24 insertions(+) (limited to 'include') diff --git a/include/net/bluetooth/hci.h b/include/net/bluetooth/hci.h index 9a5330eed794..5bc1e30dedde 100644 --- a/include/net/bluetooth/hci.h +++ b/include/net/bluetooth/hci.h @@ -1143,6 +1143,26 @@ struct hci_cp_write_sc_support { __u8 support; } __packed; +#define HCI_OP_READ_AUTH_PAYLOAD_TO 0x0c7b +struct hci_cp_read_auth_payload_to { + __le16 handle; +} __packed; +struct hci_rp_read_auth_payload_to { + __u8 status; + __le16 handle; + __le16 timeout; +} __packed; + +#define HCI_OP_WRITE_AUTH_PAYLOAD_TO 0x0c7c +struct hci_cp_write_auth_payload_to { + __le16 handle; + __le16 timeout; +} __packed; +struct hci_rp_write_auth_payload_to { + __u8 status; + __le16 handle; +} __packed; + #define HCI_OP_READ_LOCAL_OOB_EXT_DATA 0x0c7d struct hci_rp_read_local_oob_ext_data { __u8 status; diff --git a/include/net/bluetooth/hci_core.h b/include/net/bluetooth/hci_core.h index 05b1b96f4d9e..ded574b32c20 100644 --- a/include/net/bluetooth/hci_core.h +++ b/include/net/bluetooth/hci_core.h @@ -199,6 +199,8 @@ struct adv_info { /* Default min/max age of connection information (1s/3s) */ #define DEFAULT_CONN_INFO_MIN_AGE 1000 #define DEFAULT_CONN_INFO_MAX_AGE 3000 +/* Default authenticated payload timeout 30s */ +#define DEFAULT_AUTH_PAYLOAD_TIMEOUT 0x0bb8 struct amp_assoc { __u16 len; @@ -275,6 +277,7 @@ struct hci_dev { __u16 discov_interleaved_timeout; __u16 conn_info_min_age; __u16 conn_info_max_age; + __u16 auth_payload_timeout; __u8 ssp_debug_mode; __u8 hw_error_code; __u32 clock; @@ -481,6 +484,7 @@ struct hci_conn { __u16 disc_timeout; __u16 conn_timeout; __u16 setting; + __u16 auth_payload_timeout; __u16 le_conn_min_interval; __u16 le_conn_max_interval; __u16 le_conn_interval; -- cgit v1.2.3 From 600c70bad6594cb124c641ed05355ca134650ea4 Mon Sep 17 00:00:00 2001 From: Stanislav Fomichev Date: Mon, 1 Jul 2019 10:38:39 -0700 Subject: bpf: allow wide (u64) aligned stores for some fields of bpf_sock_addr Since commit cd17d7770578 ("bpf/tools: sync bpf.h") clang decided that it can do a single u64 store into user_ip6[2] instead of two separate u32 ones: # 17: (18) r2 = 0x100000000000000 # ; ctx->user_ip6[2] = bpf_htonl(DST_REWRITE_IP6_2); # 19: (7b) *(u64 *)(r1 +16) = r2 # invalid bpf_context access off=16 size=8 >From the compiler point of view it does look like a correct thing to do, so let's support it on the kernel side. Credit to Andrii Nakryiko for a proper implementation of bpf_ctx_wide_store_ok. Cc: Andrii Nakryiko Cc: Yonghong Song Fixes: cd17d7770578 ("bpf/tools: sync bpf.h") Reported-by: kernel test robot Acked-by: Yonghong Song Acked-by: Andrii Nakryiko Signed-off-by: Stanislav Fomichev Signed-off-by: Daniel Borkmann --- include/linux/filter.h | 6 ++++++ include/uapi/linux/bpf.h | 6 +++--- 2 files changed, 9 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/include/linux/filter.h b/include/linux/filter.h index 1fe53e78c7e3..6d944369ca87 100644 --- a/include/linux/filter.h +++ b/include/linux/filter.h @@ -747,6 +747,12 @@ bpf_ctx_narrow_access_ok(u32 off, u32 size, u32 size_default) return size <= size_default && (size & (size - 1)) == 0; } +#define bpf_ctx_wide_store_ok(off, size, type, field) \ + (size == sizeof(__u64) && \ + off >= offsetof(type, field) && \ + off + sizeof(__u64) <= offsetofend(type, field) && \ + off % sizeof(__u64) == 0) + #define bpf_classic_proglen(fprog) (fprog->len * sizeof(fprog->filter[0])) static inline void bpf_prog_lock_ro(struct bpf_prog *fp) diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index ead27aebf491..c318385aba51 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -3247,7 +3247,7 @@ struct bpf_sock_addr { __u32 user_ip4; /* Allows 1,2,4-byte read and 4-byte write. * Stored in network byte order. */ - __u32 user_ip6[4]; /* Allows 1,2,4-byte read an 4-byte write. + __u32 user_ip6[4]; /* Allows 1,2,4-byte read and 4,8-byte write. * Stored in network byte order. */ __u32 user_port; /* Allows 4-byte read and write. @@ -3256,10 +3256,10 @@ struct bpf_sock_addr { __u32 family; /* Allows 4-byte read, but no write */ __u32 type; /* Allows 4-byte read, but no write */ __u32 protocol; /* Allows 4-byte read, but no write */ - __u32 msg_src_ip4; /* Allows 1,2,4-byte read an 4-byte write. + __u32 msg_src_ip4; /* Allows 1,2,4-byte read and 4-byte write. * Stored in network byte order. */ - __u32 msg_src_ip6[4]; /* Allows 1,2,4-byte read an 4-byte write. + __u32 msg_src_ip6[4]; /* Allows 1,2,4-byte read and 4,8-byte write. * Stored in network byte order. */ __bpf_md_ptr(struct bpf_sock *, sk); -- cgit v1.2.3 From bef8e2639242e7f7214f1ab3b37ace1415a4f750 Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Mon, 8 Jul 2019 14:57:21 +0200 Subject: bpf: avoid unused variable warning in tcp_bpf_rtt() When CONFIG_BPF is disabled, we get a warning for an unused variable: In file included from drivers/target/target_core_device.c:26: include/net/tcp.h:2226:19: error: unused variable 'tp' [-Werror,-Wunused-variable] struct tcp_sock *tp = tcp_sk(sk); The variable is only used in one place, so it can be replaced with its value there to avoid the warning. Fixes: 23729ff23186 ("bpf: add BPF_CGROUP_SOCK_OPS callback that is executed on every RTT") Signed-off-by: Arnd Bergmann Acked-by: Soheil Hassas Yeganeh Signed-off-by: Daniel Borkmann --- include/net/tcp.h | 4 +--- 1 file changed, 1 insertion(+), 3 deletions(-) (limited to 'include') diff --git a/include/net/tcp.h b/include/net/tcp.h index e16d8a3fd3b4..cca3c59b98bf 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -2223,9 +2223,7 @@ static inline bool tcp_bpf_ca_needs_ecn(struct sock *sk) static inline void tcp_bpf_rtt(struct sock *sk) { - struct tcp_sock *tp = tcp_sk(sk); - - if (BPF_SOCK_OPS_TEST_FLAG(tp, BPF_SOCK_OPS_RTT_CB_FLAG)) + if (BPF_SOCK_OPS_TEST_FLAG(tcp_sk(sk), BPF_SOCK_OPS_RTT_CB_FLAG)) tcp_call_bpf(sk, BPF_SOCK_OPS_RTT_CB, 0, NULL); } -- cgit v1.2.3 From 1da4bbeffe41ba318812d7590955faee8636668b Mon Sep 17 00:00:00 2001 From: Ivan Khoronzhuk Date: Tue, 9 Jul 2019 00:34:28 +0300 Subject: net: core: page_pool: add user refcnt and reintroduce page_pool_destroy Jesper recently removed page_pool_destroy() (from driver invocation) and moved shutdown and free of page_pool into xdp_rxq_info_unreg(), in-order to handle in-flight packets/pages. This created an asymmetry in drivers create/destroy pairs. This patch reintroduce page_pool_destroy and add page_pool user refcnt. This serves the purpose to simplify drivers error handling as driver now drivers always calls page_pool_destroy() and don't need to track if xdp_rxq_info_reg_mem_model() was unsuccessful. This could be used for a special cases where a single RX-queue (with a single page_pool) provides packets for two net_device'es, and thus needs to register the same page_pool twice with two xdp_rxq_info structures. This patch is primarily to ease API usage for drivers. The recently merged netsec driver, actually have a bug in this area, which is solved by this API change. This patch is a modified version of Ivan Khoronzhuk's original patch. Link: https://lore.kernel.org/netdev/20190625175948.24771-2-ivan.khoronzhuk@linaro.org/ Fixes: 5c67bf0ec4d0 ("net: netsec: Use page_pool API") Signed-off-by: Jesper Dangaard Brouer Reviewed-by: Ilias Apalodimas Acked-by: Jesper Dangaard Brouer Reviewed-by: Saeed Mahameed Signed-off-by: Ivan Khoronzhuk Signed-off-by: David S. Miller --- include/net/page_pool.h | 25 +++++++++++++++++++++++++ 1 file changed, 25 insertions(+) (limited to 'include') diff --git a/include/net/page_pool.h b/include/net/page_pool.h index ee9c871d2043..2cbcdbdec254 100644 --- a/include/net/page_pool.h +++ b/include/net/page_pool.h @@ -101,6 +101,12 @@ struct page_pool { struct ptr_ring ring; atomic_t pages_state_release_cnt; + + /* A page_pool is strictly tied to a single RX-queue being + * protected by NAPI, due to above pp_alloc_cache. This + * refcnt serves purpose is to simplify drivers error handling. + */ + refcount_t user_cnt; }; struct page *page_pool_alloc_pages(struct page_pool *pool, gfp_t gfp); @@ -134,6 +140,15 @@ static inline void page_pool_free(struct page_pool *pool) #endif } +/* Drivers use this instead of page_pool_free */ +static inline void page_pool_destroy(struct page_pool *pool) +{ + if (!pool) + return; + + page_pool_free(pool); +} + /* Never call this directly, use helpers below */ void __page_pool_put_page(struct page_pool *pool, struct page *page, bool allow_direct); @@ -201,4 +216,14 @@ static inline bool is_page_pool_compiled_in(void) #endif } +static inline void page_pool_get(struct page_pool *pool) +{ + refcount_inc(&pool->user_cnt); +} + +static inline bool page_pool_put(struct page_pool *pool) +{ + return refcount_dec_and_test(&pool->user_cnt); +} + #endif /* _NET_PAGE_POOL_H */ -- cgit v1.2.3 From d4117d63a30876a3654f587c3a419db63d8b529d Mon Sep 17 00:00:00 2001 From: Kweh Hock Leong Date: Sat, 6 Jul 2019 01:33:27 +0800 Subject: net: stmmac: enable clause 45 mdio support DWMAC4 is capable to support clause 45 mdio communication. This patch enable the feature on stmmac_mdio_write() and stmmac_mdio_read() by following phy_write_mmd() and phy_read_mmd() mdiobus read write implementation format. Reviewed-by: Li, Yifan Signed-off-by: Kweh Hock Leong Signed-off-by: Ong Boon Leong Signed-off-by: Voon Weifeng Reviewed-by: Andrew Lunn 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 d0af7d37fdf9..1739c6dc470e 100644 --- a/include/linux/phy.h +++ b/include/linux/phy.h @@ -195,6 +195,8 @@ static inline const char *phy_modes(phy_interface_t interface) /* Or MII_ADDR_C45 into regnum for read/write on mii_bus to enable the 21 bit IEEE 802.3ae clause 45 addressing mode used by 10GIGE phy chips. */ #define MII_ADDR_C45 (1<<30) +#define MII_DEVADDR_C45_SHIFT 16 +#define MII_REGADDR_C45_MASK GENMASK(15, 0) struct device; struct phylink; -- cgit v1.2.3 From bf0bdd1343efbbf65b4d53aef1fce14acbd79d50 Mon Sep 17 00:00:00 2001 From: Ilya Maximets Date: Wed, 3 Jul 2019 15:09:16 +0300 Subject: xdp: fix race on generic receive path Unlike driver mode, generic xdp receive could be triggered by different threads on different CPU cores at the same time leading to the fill and rx queue breakage. For example, this could happen while sending packets from two processes to the first interface of veth pair while the second part of it is open with AF_XDP socket. Need to take a lock for each generic receive to avoid race. Fixes: c497176cb2e4 ("xsk: add Rx receive functions and poll support") Signed-off-by: Ilya Maximets Acked-by: Magnus Karlsson Tested-by: William Tu Signed-off-by: Daniel Borkmann --- include/net/xdp_sock.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/net/xdp_sock.h b/include/net/xdp_sock.h index 057b159ff8b9..de4e3a353df3 100644 --- a/include/net/xdp_sock.h +++ b/include/net/xdp_sock.h @@ -67,6 +67,8 @@ struct xdp_sock { * in the SKB destructor callback. */ spinlock_t tx_completion_lock; + /* Protects generic receive. */ + spinlock_t rx_lock; u64 rx_dropped; }; -- cgit v1.2.3 From 333f7909a8573145811c4ab7d8c9092301707721 Mon Sep 17 00:00:00 2001 From: Al Viro Date: Fri, 5 Jul 2019 20:14:16 +0100 Subject: coallocate socket_wq with socket itself socket->wq is assign-once, set when we are initializing both struct socket it's in and struct socket_wq it points to. As the matter of fact, the only reason for separate allocation was the ability to RCU-delay freeing of socket_wq. RCU-delaying the freeing of socket itself gets rid of that need, so we can just fold struct socket_wq into the end of struct socket and simplify the life both for sock_alloc_inode() (one allocation instead of two) and for tun/tap oddballs, where we used to embed struct socket and struct socket_wq into the same structure (now - embedding just the struct socket). Note that reference to struct socket_wq in struct sock does remain a reference - that's unchanged. Signed-off-by: Al Viro Signed-off-by: David S. Miller --- include/linux/if_tap.h | 1 - include/linux/net.h | 4 ++-- include/net/sock.h | 4 ++-- 3 files changed, 4 insertions(+), 5 deletions(-) (limited to 'include') diff --git a/include/linux/if_tap.h b/include/linux/if_tap.h index 8e66866c11be..915a187cfabd 100644 --- a/include/linux/if_tap.h +++ b/include/linux/if_tap.h @@ -62,7 +62,6 @@ struct tap_dev { struct tap_queue { struct sock sk; struct socket sock; - struct socket_wq wq; int vnet_hdr_sz; struct tap_dev __rcu *tap; struct file *file; diff --git a/include/linux/net.h b/include/linux/net.h index f7d672cf25b5..9cafb5f353a9 100644 --- a/include/linux/net.h +++ b/include/linux/net.h @@ -116,11 +116,11 @@ struct socket { unsigned long flags; - struct socket_wq *wq; - struct file *file; struct sock *sk; const struct proto_ops *ops; + + struct socket_wq wq; }; struct vm_area_struct; diff --git a/include/net/sock.h b/include/net/sock.h index 6cbc16136357..228db3998e46 100644 --- a/include/net/sock.h +++ b/include/net/sock.h @@ -1822,7 +1822,7 @@ static inline void sock_graft(struct sock *sk, struct socket *parent) { WARN_ON(parent->sk); write_lock_bh(&sk->sk_callback_lock); - rcu_assign_pointer(sk->sk_wq, parent->wq); + rcu_assign_pointer(sk->sk_wq, &parent->wq); parent->sk = sk; sk_set_socket(sk, parent); sk->sk_uid = SOCK_INODE(parent)->i_uid; @@ -2100,7 +2100,7 @@ static inline void sock_poll_wait(struct file *filp, struct socket *sock, poll_table *p) { if (!poll_does_not_wait(p)) { - poll_wait(filp, &sock->wq->wait, p); + poll_wait(filp, &sock->wq.wait, p); /* We need to be sure we are in sync with the * socket flags modification. * -- cgit v1.2.3 From 59c820b2317f0ffe1ab9b5d2c0515cdbfe714e6e Mon Sep 17 00:00:00 2001 From: Willem de Bruijn Date: Sun, 7 Jul 2019 05:34:45 -0400 Subject: ipv6: elide flowlabel check if no exclusive leases exist Processes can request ipv6 flowlabels with cmsg IPV6_FLOWINFO. If not set, by default an autogenerated flowlabel is selected. Explicit flowlabels require a control operation per label plus a datapath check on every connection (every datagram if unconnected). This is particularly expensive on unconnected sockets multiplexing many flows, such as QUIC. In the common case, where no lease is exclusive, the check can be safely elided, as both lease request and check trivially succeed. Indeed, autoflowlabel does the same even with exclusive leases. Elide the check if no process has requested an exclusive lease. fl6_sock_lookup previously returns either a reference to a lease or NULL to denote failure. Modify to return a real error and update all callers. On return NULL, they can use the label and will elide the atomic_dec in fl6_sock_release. This is an optimization. Robust applications still have to revert to requesting leases if the fast path fails due to an exclusive lease. Changes RFC->v1: - use static_key_false_deferred to rate limit jump label operations - call static_key_deferred_flush to stop timers on exit - move decrement out of RCU context - defer optimization also if opt data is associated with a lease - updated all fp6_sock_lookup callers, not just udp Signed-off-by: Willem de Bruijn Signed-off-by: David S. Miller --- include/net/ipv6.h | 14 +++++++++++++- 1 file changed, 13 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/net/ipv6.h b/include/net/ipv6.h index 8eca5fb30376..8dfc65639aa4 100644 --- a/include/net/ipv6.h +++ b/include/net/ipv6.h @@ -13,6 +13,7 @@ #include #include #include +#include #include #include #include @@ -389,7 +390,18 @@ static inline void txopt_put(struct ipv6_txoptions *opt) kfree_rcu(opt, rcu); } -struct ip6_flowlabel *fl6_sock_lookup(struct sock *sk, __be32 label); +struct ip6_flowlabel *__fl6_sock_lookup(struct sock *sk, __be32 label); + +extern struct static_key_false_deferred ipv6_flowlabel_exclusive; +static inline struct ip6_flowlabel *fl6_sock_lookup(struct sock *sk, + __be32 label) +{ + if (static_branch_unlikely(&ipv6_flowlabel_exclusive.key)) + return __fl6_sock_lookup(sk, label) ? : ERR_PTR(-ENOENT); + + return NULL; +} + struct ipv6_txoptions *fl6_merge_options(struct ipv6_txoptions *opt_space, struct ip6_flowlabel *fl, struct ipv6_txoptions *fopt); -- cgit v1.2.3 From 6413139dfc641aaaa30580b59696a5f7ea274194 Mon Sep 17 00:00:00 2001 From: Willem de Bruijn Date: Sun, 7 Jul 2019 05:51:55 -0400 Subject: skbuff: increase verbosity when dumping skb data skb_warn_bad_offload and netdev_rx_csum_fault trigger on hard to debug issues. Dump more state and the header. Optionally dump the entire packet and linear segment. This is required to debug checksum bugs that may include bytes past skb_tail_pointer(). Both call sites call this function inside a net_ratelimit() block. Limit full packet log further to a hard limit of can_dump_full (5). Based on an earlier patch by Cong Wang, see link below. Changes v1 -> v2 - dump frag_list only on full_pkt Link: https://patchwork.ozlabs.org/patch/1000841/ Signed-off-by: Willem de Bruijn Signed-off-by: David S. Miller --- include/linux/skbuff.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 7ece49d5f8ef..1fdfdbb34e8e 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -1024,6 +1024,7 @@ static inline bool skb_unref(struct sk_buff *skb) void skb_release_head_state(struct sk_buff *skb); void kfree_skb(struct sk_buff *skb); void kfree_skb_list(struct sk_buff *segs); +void skb_dump(const char *level, const struct sk_buff *skb, bool full_pkt); void skb_tx_error(struct sk_buff *skb); void consume_skb(struct sk_buff *skb); void __consume_stateless_skb(struct sk_buff *skb); -- cgit v1.2.3 From 8822e270d697010e6a4fd42a319dbefc33db91e1 Mon Sep 17 00:00:00 2001 From: John Hurley Date: Sun, 7 Jul 2019 15:01:54 +0100 Subject: net: core: move push MPLS functionality from OvS to core helper Open vSwitch provides code to push an MPLS header to a packet. In preparation for supporting this in TC, move the push code to an skb helper that can be reused. Signed-off-by: John Hurley Reviewed-by: Jakub Kicinski Reviewed-by: Simon Horman Reviewed-by: Willem de Bruijn Acked-by: Cong Wang Signed-off-by: David S. Miller --- include/linux/skbuff.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 1fdfdbb34e8e..1dc55000710c 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -3447,6 +3447,7 @@ int skb_ensure_writable(struct sk_buff *skb, int write_len); int __skb_vlan_pop(struct sk_buff *skb, u16 *vlan_tci); int skb_vlan_pop(struct sk_buff *skb); int skb_vlan_push(struct sk_buff *skb, __be16 vlan_proto, u16 vlan_tci); +int skb_mpls_push(struct sk_buff *skb, __be32 mpls_lse, __be16 mpls_proto); struct sk_buff *pskb_extract(struct sk_buff *skb, int off, int to_copy, gfp_t gfp); -- cgit v1.2.3 From ed246cee09b9865145a2e1e34f63ec0e31dd83a5 Mon Sep 17 00:00:00 2001 From: John Hurley Date: Sun, 7 Jul 2019 15:01:55 +0100 Subject: net: core: move pop MPLS functionality from OvS to core helper Open vSwitch provides code to pop an MPLS header to a packet. In preparation for supporting this in TC, move the pop code to an skb helper that can be reused. Remove the, now unused, update_ethertype static function from OvS. Signed-off-by: John Hurley Reviewed-by: Jakub Kicinski Reviewed-by: Simon Horman Reviewed-by: Willem de Bruijn Acked-by: Cong Wang Signed-off-by: David S. Miller --- include/linux/skbuff.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 1dc55000710c..08d1c8e70540 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -3448,6 +3448,7 @@ int __skb_vlan_pop(struct sk_buff *skb, u16 *vlan_tci); int skb_vlan_pop(struct sk_buff *skb); int skb_vlan_push(struct sk_buff *skb, __be16 vlan_proto, u16 vlan_tci); int skb_mpls_push(struct sk_buff *skb, __be32 mpls_lse, __be16 mpls_proto); +int skb_mpls_pop(struct sk_buff *skb, __be16 next_proto); struct sk_buff *pskb_extract(struct sk_buff *skb, int off, int to_copy, gfp_t gfp); -- cgit v1.2.3 From d27cf5c59a12f66425df29cd81f61aa73ef14ac1 Mon Sep 17 00:00:00 2001 From: John Hurley Date: Sun, 7 Jul 2019 15:01:56 +0100 Subject: net: core: add MPLS update core helper and use in OvS Open vSwitch allows the updating of an existing MPLS header on a packet. In preparation for supporting similar functionality in TC, move this to a common skb helper function. Signed-off-by: John Hurley Reviewed-by: Jakub Kicinski Reviewed-by: Simon Horman Reviewed-by: Willem de Bruijn Acked-by: Cong Wang Signed-off-by: David S. Miller --- include/linux/skbuff.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 08d1c8e70540..9f7e01f2be83 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -3449,6 +3449,7 @@ int skb_vlan_pop(struct sk_buff *skb); int skb_vlan_push(struct sk_buff *skb, __be16 vlan_proto, u16 vlan_tci); int skb_mpls_push(struct sk_buff *skb, __be32 mpls_lse, __be16 mpls_proto); int skb_mpls_pop(struct sk_buff *skb, __be16 next_proto); +int skb_mpls_update_lse(struct sk_buff *skb, __be32 mpls_lse); struct sk_buff *pskb_extract(struct sk_buff *skb, int off, int to_copy, gfp_t gfp); -- cgit v1.2.3 From 2a2ea50870baa3fb4de0872c5b60828138654ca7 Mon Sep 17 00:00:00 2001 From: John Hurley Date: Sun, 7 Jul 2019 15:01:57 +0100 Subject: net: sched: add mpls manipulation actions to TC Currently, TC offers the ability to match on the MPLS fields of a packet through the use of the flow_dissector_key_mpls struct. However, as yet, TC actions do not allow the modification or manipulation of such fields. Add a new module that registers TC action ops to allow manipulation of MPLS. This includes the ability to push and pop headers as well as modify the contents of new or existing headers. A further action to decrement the TTL field of an MPLS header is also provided with a new helper added to support this. Examples of the usage of the new action with flower rules to push and pop MPLS labels are: tc filter add dev eth0 protocol ip parent ffff: flower \ action mpls push protocol mpls_uc label 123 \ action mirred egress redirect dev eth1 tc filter add dev eth0 protocol mpls_uc parent ffff: flower \ action mpls pop protocol ipv4 \ action mirred egress redirect dev eth1 Signed-off-by: John Hurley Reviewed-by: Jakub Kicinski Reviewed-by: Simon Horman Reviewed-by: Willem de Bruijn Acked-by: Cong Wang Signed-off-by: David S. Miller --- include/linux/skbuff.h | 1 + include/net/tc_act/tc_mpls.h | 30 ++++++++++++++++++++++++++++++ include/uapi/linux/pkt_cls.h | 3 ++- include/uapi/linux/tc_act/tc_mpls.h | 33 +++++++++++++++++++++++++++++++++ 4 files changed, 66 insertions(+), 1 deletion(-) create mode 100644 include/net/tc_act/tc_mpls.h create mode 100644 include/uapi/linux/tc_act/tc_mpls.h (limited to 'include') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 9f7e01f2be83..9d7a2c28ea35 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -3450,6 +3450,7 @@ int skb_vlan_push(struct sk_buff *skb, __be16 vlan_proto, u16 vlan_tci); int skb_mpls_push(struct sk_buff *skb, __be32 mpls_lse, __be16 mpls_proto); int skb_mpls_pop(struct sk_buff *skb, __be16 next_proto); int skb_mpls_update_lse(struct sk_buff *skb, __be32 mpls_lse); +int skb_mpls_dec_ttl(struct sk_buff *skb); struct sk_buff *pskb_extract(struct sk_buff *skb, int off, int to_copy, gfp_t gfp); diff --git a/include/net/tc_act/tc_mpls.h b/include/net/tc_act/tc_mpls.h new file mode 100644 index 000000000000..4bc3d9250ef0 --- /dev/null +++ b/include/net/tc_act/tc_mpls.h @@ -0,0 +1,30 @@ +/* SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) */ +/* Copyright (C) 2019 Netronome Systems, Inc. */ + +#ifndef __NET_TC_MPLS_H +#define __NET_TC_MPLS_H + +#include +#include + +struct tcf_mpls_params { + int tcfm_action; + u32 tcfm_label; + u8 tcfm_tc; + u8 tcfm_ttl; + u8 tcfm_bos; + __be16 tcfm_proto; + struct rcu_head rcu; +}; + +#define ACT_MPLS_TC_NOT_SET 0xff +#define ACT_MPLS_BOS_NOT_SET 0xff +#define ACT_MPLS_LABEL_NOT_SET 0xffffffff + +struct tcf_mpls { + struct tc_action common; + struct tcf_mpls_params __rcu *mpls_p; +}; +#define to_mpls(a) ((struct tcf_mpls *)a) + +#endif /* __NET_TC_MPLS_H */ diff --git a/include/uapi/linux/pkt_cls.h b/include/uapi/linux/pkt_cls.h index 8cc6b6777b3c..e22ef4a940bc 100644 --- a/include/uapi/linux/pkt_cls.h +++ b/include/uapi/linux/pkt_cls.h @@ -104,8 +104,9 @@ enum tca_id { TCA_ID_SIMP = TCA_ACT_SIMP, TCA_ID_IFE = TCA_ACT_IFE, TCA_ID_SAMPLE = TCA_ACT_SAMPLE, - /* other actions go here */ TCA_ID_CTINFO, + TCA_ID_MPLS, + /* other actions go here */ __TCA_ID_MAX = 255 }; diff --git a/include/uapi/linux/tc_act/tc_mpls.h b/include/uapi/linux/tc_act/tc_mpls.h new file mode 100644 index 000000000000..9360e95273c7 --- /dev/null +++ b/include/uapi/linux/tc_act/tc_mpls.h @@ -0,0 +1,33 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ +/* Copyright (C) 2019 Netronome Systems, Inc. */ + +#ifndef __LINUX_TC_MPLS_H +#define __LINUX_TC_MPLS_H + +#include + +#define TCA_MPLS_ACT_POP 1 +#define TCA_MPLS_ACT_PUSH 2 +#define TCA_MPLS_ACT_MODIFY 3 +#define TCA_MPLS_ACT_DEC_TTL 4 + +struct tc_mpls { + tc_gen; /* generic TC action fields. */ + int m_action; /* action of type TCA_MPLS_ACT_*. */ +}; + +enum { + TCA_MPLS_UNSPEC, + TCA_MPLS_TM, /* struct tcf_t; time values associated with action. */ + TCA_MPLS_PARMS, /* struct tc_mpls; action type and general TC fields. */ + TCA_MPLS_PAD, + TCA_MPLS_PROTO, /* be16; eth_type of pushed or next (for pop) header. */ + TCA_MPLS_LABEL, /* u32; MPLS label. Lower 20 bits are used. */ + TCA_MPLS_TC, /* u8; MPLS TC field. Lower 3 bits are used. */ + TCA_MPLS_TTL, /* u8; MPLS TTL field. Must not be 0. */ + TCA_MPLS_BOS, /* u8; MPLS BOS field. Either 1 or 0. */ + __TCA_MPLS_MAX, +}; +#define TCA_MPLS_MAX (__TCA_MPLS_MAX - 1) + +#endif -- cgit v1.2.3 From a96701fb3534c45bd6fe5e6f6d3a91e3acc19b59 Mon Sep 17 00:00:00 2001 From: Xin Long Date: Tue, 9 Jul 2019 00:57:04 +0800 Subject: sctp: remove reconf_enable from asoc asoc's reconf support is actually decided by the 4-shakehand negotiation, not something that users can set by sockopt. asoc->peer.reconf_capable is working for this. So remove it from asoc. Signed-off-by: Xin Long Signed-off-by: David S. Miller --- include/net/sctp/structs.h | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) (limited to 'include') diff --git a/include/net/sctp/structs.h b/include/net/sctp/structs.h index 0767701ef362..d9e0e1a53f99 100644 --- a/include/net/sctp/structs.h +++ b/include/net/sctp/structs.h @@ -2051,8 +2051,7 @@ struct sctp_association { temp:1, /* Is it a temporary association? */ force_delay:1, intl_enable:1, - prsctp_enable:1, - reconf_enable:1; + prsctp_enable:1; __u8 strreset_enable; __u8 strreset_outstanding; /* request param count on the fly */ -- cgit v1.2.3 From 1c13475368b697d4fc9c0630b5d4ee51d5ca0790 Mon Sep 17 00:00:00 2001 From: Xin Long Date: Tue, 9 Jul 2019 00:57:05 +0800 Subject: sctp: remove prsctp_enable from asoc Like reconf_enable, prsctp_enable should also be removed from asoc, as asoc->peer.prsctp_capable has taken its job. Signed-off-by: Xin Long Signed-off-by: David S. Miller --- include/net/sctp/structs.h | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) (limited to 'include') diff --git a/include/net/sctp/structs.h b/include/net/sctp/structs.h index d9e0e1a53f99..7f35b8ee9f65 100644 --- a/include/net/sctp/structs.h +++ b/include/net/sctp/structs.h @@ -2050,8 +2050,7 @@ struct sctp_association { __u8 need_ecne:1, /* Need to send an ECNE Chunk? */ temp:1, /* Is it a temporary association? */ force_delay:1, - intl_enable:1, - prsctp_enable:1; + intl_enable:1; __u8 strreset_enable; __u8 strreset_outstanding; /* request param count on the fly */ -- cgit v1.2.3 From da1f6d4de7b743c86cb49015ea05b184fea1388c Mon Sep 17 00:00:00 2001 From: Xin Long Date: Tue, 9 Jul 2019 00:57:06 +0800 Subject: sctp: rename asoc intl_enable to asoc peer.intl_capable To keep consistent with other asoc features, we move intl_enable to peer.intl_capable in asoc. Signed-off-by: Xin Long Signed-off-by: David S. Miller --- include/net/sctp/structs.h | 33 +++++++++++++++++---------------- 1 file changed, 17 insertions(+), 16 deletions(-) (limited to 'include') diff --git a/include/net/sctp/structs.h b/include/net/sctp/structs.h index 7f35b8ee9f65..c41b57ba04bb 100644 --- a/include/net/sctp/structs.h +++ b/include/net/sctp/structs.h @@ -1679,28 +1679,30 @@ struct sctp_association { __be16 addip_disabled_mask; /* These are capabilities which our peer advertised. */ - __u8 ecn_capable:1, /* Can peer do ECN? */ + __u16 ecn_capable:1, /* Can peer do ECN? */ ipv4_address:1, /* Peer understands IPv4 addresses? */ ipv6_address:1, /* Peer understands IPv6 addresses? */ hostname_address:1, /* Peer understands DNS addresses? */ asconf_capable:1, /* Does peer support ADDIP? */ prsctp_capable:1, /* Can peer do PR-SCTP? */ reconf_capable:1, /* Can peer do RE-CONFIG? */ - auth_capable:1; /* Is peer doing SCTP-AUTH? */ - - /* sack_needed : This flag indicates if the next received - * : packet is to be responded to with a - * : SACK. This is initialized to 0. When a packet - * : is received sack_cnt is incremented. If this value - * : reaches 2 or more, a SACK is sent and the - * : value is reset to 0. Note: This is used only - * : when no DATA chunks are received out of - * : order. When DATA chunks are out of order, - * : SACK's are not delayed (see Section 6). - */ - __u8 sack_needed:1, /* Do we need to sack the peer? */ + intl_capable:1, /* Can peer do INTERLEAVE */ + auth_capable:1, /* Is peer doing SCTP-AUTH? */ + /* sack_needed: + * This flag indicates if the next received + * packet is to be responded to with a + * SACK. This is initialized to 0. When a packet + * is received sack_cnt is incremented. If this value + * reaches 2 or more, a SACK is sent and the + * value is reset to 0. Note: This is used only + * when no DATA chunks are received out of + * order. When DATA chunks are out of order, + * SACK's are not delayed (see Section 6). + */ + sack_needed:1, /* Do we need to sack the peer? */ sack_generation:1, zero_window_announced:1; + __u32 sack_cnt; __u32 adaptation_ind; /* Adaptation Code point. */ @@ -2049,8 +2051,7 @@ struct sctp_association { __u8 need_ecne:1, /* Need to send an ECNE Chunk? */ temp:1, /* Is it a temporary association? */ - force_delay:1, - intl_enable:1; + force_delay:1; __u8 strreset_enable; __u8 strreset_outstanding; /* request param count on the fly */ -- cgit v1.2.3 From e55f4b8bf4622103badac8694cdabceec06f9b38 Mon Sep 17 00:00:00 2001 From: Xin Long Date: Tue, 9 Jul 2019 00:57:07 +0800 Subject: sctp: rename sp strm_interleave to ep intl_enable Like other endpoint features, strm_interleave should be moved to sctp_endpoint and renamed to intl_enable. Signed-off-by: Xin Long Signed-off-by: David S. Miller --- include/net/sctp/structs.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/net/sctp/structs.h b/include/net/sctp/structs.h index c41b57ba04bb..ba5c4f6eede5 100644 --- a/include/net/sctp/structs.h +++ b/include/net/sctp/structs.h @@ -219,7 +219,6 @@ struct sctp_sock { disable_fragments:1, v4mapped:1, frag_interleave:1, - strm_interleave:1, recvrcvinfo:1, recvnxtinfo:1, data_ready_signalled:1; @@ -1324,6 +1323,7 @@ struct sctp_endpoint { struct list_head endpoint_shared_keys; __u16 active_key_id; __u8 auth_enable:1, + intl_enable:1, prsctp_enable:1, reconf_enable:1; -- cgit v1.2.3 From b5d9a834f4fd1b6abfa527ec351c871084dd23a3 Mon Sep 17 00:00:00 2001 From: Dirk van der Merwe Date: Mon, 8 Jul 2019 19:53:13 -0700 Subject: net/tls: don't clear TX resync flag on error Introduce a return code for the tls_dev_resync callback. When the driver TX resync fails, kernel can retry the resync again until it succeeds. This prevents drivers from attempting to offload TLS packets if the connection is known to be out of sync. We don't worry about the RX resync since they will be retried naturally as more encrypted records get received. Signed-off-by: Dirk van der Merwe Reviewed-by: Jakub Kicinski Signed-off-by: David S. Miller --- include/net/tls.h | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/include/net/tls.h b/include/net/tls.h index 176d0b039f32..584609174fe0 100644 --- a/include/net/tls.h +++ b/include/net/tls.h @@ -304,9 +304,9 @@ struct tlsdev_ops { void (*tls_dev_del)(struct net_device *netdev, struct tls_context *ctx, enum tls_offload_ctx_dir direction); - void (*tls_dev_resync)(struct net_device *netdev, - struct sock *sk, u32 seq, u8 *rcd_sn, - enum tls_offload_ctx_dir direction); + int (*tls_dev_resync)(struct net_device *netdev, + struct sock *sk, u32 seq, u8 *rcd_sn, + enum tls_offload_ctx_dir direction); }; enum tls_offload_sync_type { -- cgit v1.2.3 From 378ef01b5f75e6c485b8f16b4f6a7842a312aa07 Mon Sep 17 00:00:00 2001 From: Parav Pandit Date: Mon, 8 Jul 2019 23:17:35 -0500 Subject: devlink: Refactor physical port attributes To support additional devlink port flavours and to support few common and few different port attributes, move physical port attributes to a different structure. Acked-by: Jiri Pirko Signed-off-by: Parav Pandit Signed-off-by: David S. Miller --- include/net/devlink.h | 13 +++++++++++-- 1 file changed, 11 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/net/devlink.h b/include/net/devlink.h index 6625ea068d5e..4538c80fe293 100644 --- a/include/net/devlink.h +++ b/include/net/devlink.h @@ -38,14 +38,23 @@ struct devlink { char priv[0] __aligned(NETDEV_ALIGN); }; +struct devlink_port_phys_attrs { + u32 port_number; /* Same value as "split group". + * A physical port which is visible to the user + * for a given port flavour. + */ + u32 split_subport_number; +}; + struct devlink_port_attrs { u8 set:1, split:1, switch_port:1; enum devlink_port_flavour flavour; - u32 port_number; /* same value as "split group" */ - u32 split_subport_number; struct netdev_phys_item_id switch_id; + union { + struct devlink_port_phys_attrs phys; + }; }; struct devlink_port { -- cgit v1.2.3 From 98fd2d6563fe4a799934a2a74d632601cd089beb Mon Sep 17 00:00:00 2001 From: Parav Pandit Date: Mon, 8 Jul 2019 23:17:37 -0500 Subject: devlink: Introduce PCI PF port flavour and port attribute In an eswitch, PCI PF may have port which is normally represented using a representor netdevice. To have better visibility of eswitch port, its association with PF and a representor netdevice, introduce a PCI PF port flavour and port attriute. When devlink port flavour is PCI PF, fill up PCI PF attributes of the port. Extend port name creation using PCI PF number on best effort basis. So that vendor drivers can skip defining their own scheme. $ devlink port show pci/0000:05:00.0/0: type eth netdev eth0 flavour pcipf pfnum 0 Acked-by: Jiri Pirko Signed-off-by: Parav Pandit Signed-off-by: David S. Miller --- include/net/devlink.h | 8 ++++++++ include/uapi/linux/devlink.h | 5 +++++ 2 files changed, 13 insertions(+) (limited to 'include') diff --git a/include/net/devlink.h b/include/net/devlink.h index 4538c80fe293..97cef896e4d0 100644 --- a/include/net/devlink.h +++ b/include/net/devlink.h @@ -46,6 +46,10 @@ struct devlink_port_phys_attrs { u32 split_subport_number; }; +struct devlink_port_pci_pf_attrs { + u16 pf; /* Associated PCI PF for this port. */ +}; + struct devlink_port_attrs { u8 set:1, split:1, @@ -54,6 +58,7 @@ struct devlink_port_attrs { struct netdev_phys_item_id switch_id; union { struct devlink_port_phys_attrs phys; + struct devlink_port_pci_pf_attrs pci_pf; }; }; @@ -599,6 +604,9 @@ void devlink_port_attrs_set(struct devlink_port *devlink_port, u32 split_subport_number, const unsigned char *switch_id, unsigned char switch_id_len); +void devlink_port_attrs_pci_pf_set(struct devlink_port *devlink_port, + const unsigned char *switch_id, + unsigned char switch_id_len, u16 pf); int devlink_sb_register(struct devlink *devlink, unsigned int sb_index, u32 size, u16 ingress_pools_count, u16 egress_pools_count, u16 ingress_tc_count, diff --git a/include/uapi/linux/devlink.h b/include/uapi/linux/devlink.h index 5287b42c181f..f7323884c3fe 100644 --- a/include/uapi/linux/devlink.h +++ b/include/uapi/linux/devlink.h @@ -169,6 +169,10 @@ enum devlink_port_flavour { DEVLINK_PORT_FLAVOUR_DSA, /* Distributed switch architecture * interconnect port. */ + DEVLINK_PORT_FLAVOUR_PCI_PF, /* Represents eswitch port for + * the PCI PF. It is an internal + * port that faces the PCI PF. + */ }; enum devlink_param_cmode { @@ -337,6 +341,7 @@ enum devlink_attr { DEVLINK_ATTR_FLASH_UPDATE_STATUS_DONE, /* u64 */ DEVLINK_ATTR_FLASH_UPDATE_STATUS_TOTAL, /* u64 */ + DEVLINK_ATTR_PORT_PCI_PF_NUMBER, /* u16 */ /* add new attributes above here, update the policy in devlink.c */ __DEVLINK_ATTR_MAX, -- cgit v1.2.3 From e41b6bf3cdd474dc9c587cb55906b0256835bf6d Mon Sep 17 00:00:00 2001 From: Parav Pandit Date: Mon, 8 Jul 2019 23:17:38 -0500 Subject: devlink: Introduce PCI VF port flavour and port attribute In an eswitch, PCI VF may have port which is normally represented using a representor netdevice. To have better visibility of eswitch port, its association with VF, and its representor netdevice, introduce a PCI VF port flavour. When devlink port flavour is PCI VF, fill up PCI VF attributes of the port. Extend port name creation using PCI PF and VF number scheme on best effort basis, so that vendor drivers can skip defining their own scheme. $ devlink port show pci/0000:05:00.0/0: type eth netdev eth0 flavour pcipf pfnum 0 pci/0000:05:00.0/1: type eth netdev eth1 flavour pcivf pfnum 0 vfnum 0 pci/0000:05:00.0/2: type eth netdev eth2 flavour pcivf pfnum 0 vfnum 1 Acked-by: Jiri Pirko Signed-off-by: Parav Pandit Signed-off-by: David S. Miller --- include/net/devlink.h | 10 ++++++++++ include/uapi/linux/devlink.h | 6 ++++++ 2 files changed, 16 insertions(+) (limited to 'include') diff --git a/include/net/devlink.h b/include/net/devlink.h index 97cef896e4d0..bc36f942a7d5 100644 --- a/include/net/devlink.h +++ b/include/net/devlink.h @@ -50,6 +50,11 @@ struct devlink_port_pci_pf_attrs { u16 pf; /* Associated PCI PF for this port. */ }; +struct devlink_port_pci_vf_attrs { + u16 pf; /* Associated PCI PF for this port. */ + u16 vf; /* Associated PCI VF for of the PCI PF for this port. */ +}; + struct devlink_port_attrs { u8 set:1, split:1, @@ -59,6 +64,7 @@ struct devlink_port_attrs { union { struct devlink_port_phys_attrs phys; struct devlink_port_pci_pf_attrs pci_pf; + struct devlink_port_pci_vf_attrs pci_vf; }; }; @@ -607,6 +613,10 @@ void devlink_port_attrs_set(struct devlink_port *devlink_port, void devlink_port_attrs_pci_pf_set(struct devlink_port *devlink_port, const unsigned char *switch_id, unsigned char switch_id_len, u16 pf); +void devlink_port_attrs_pci_vf_set(struct devlink_port *devlink_port, + const unsigned char *switch_id, + unsigned char switch_id_len, + u16 pf, u16 vf); int devlink_sb_register(struct devlink *devlink, unsigned int sb_index, u32 size, u16 ingress_pools_count, u16 egress_pools_count, u16 ingress_tc_count, diff --git a/include/uapi/linux/devlink.h b/include/uapi/linux/devlink.h index f7323884c3fe..ffc993256527 100644 --- a/include/uapi/linux/devlink.h +++ b/include/uapi/linux/devlink.h @@ -173,6 +173,10 @@ enum devlink_port_flavour { * the PCI PF. It is an internal * port that faces the PCI PF. */ + DEVLINK_PORT_FLAVOUR_PCI_VF, /* Represents eswitch port + * for the PCI VF. It is an internal + * port that faces the PCI VF. + */ }; enum devlink_param_cmode { @@ -342,6 +346,8 @@ enum devlink_attr { DEVLINK_ATTR_FLASH_UPDATE_STATUS_TOTAL, /* u64 */ DEVLINK_ATTR_PORT_PCI_PF_NUMBER, /* u16 */ + DEVLINK_ATTR_PORT_PCI_VF_NUMBER, /* u16 */ + /* add new attributes above here, update the policy in devlink.c */ __DEVLINK_ATTR_MAX, -- cgit v1.2.3 From b57dc7c13ea90e09ae15f821d2583fa0231b4935 Mon Sep 17 00:00:00 2001 From: Paul Blakey Date: Tue, 9 Jul 2019 10:30:48 +0300 Subject: net/sched: Introduce action ct Allow sending a packet to conntrack module for connection tracking. The packet will be marked with conntrack connection's state, and any metadata such as conntrack mark and label. This state metadata can later be matched against with tc classifers, for example with the flower classifier as below. In addition to committing new connections the user can optionally specific a zone to track within, set a mark/label and configure nat with an address range and port range. Usage is as follows: $ tc qdisc add dev ens1f0_0 ingress $ tc qdisc add dev ens1f0_1 ingress $ tc filter add dev ens1f0_0 ingress \ prio 1 chain 0 proto ip \ flower ip_proto tcp ct_state -trk \ action ct zone 2 pipe \ action goto chain 2 $ tc filter add dev ens1f0_0 ingress \ prio 1 chain 2 proto ip \ flower ct_state +trk+new \ action ct zone 2 commit mark 0xbb nat src addr 5.5.5.7 pipe \ action mirred egress redirect dev ens1f0_1 $ tc filter add dev ens1f0_0 ingress \ prio 1 chain 2 proto ip \ flower ct_zone 2 ct_mark 0xbb ct_state +trk+est \ action ct nat pipe \ action mirred egress redirect dev ens1f0_1 $ tc filter add dev ens1f0_1 ingress \ prio 1 chain 0 proto ip \ flower ip_proto tcp ct_state -trk \ action ct zone 2 pipe \ action goto chain 1 $ tc filter add dev ens1f0_1 ingress \ prio 1 chain 1 proto ip \ flower ct_zone 2 ct_mark 0xbb ct_state +trk+est \ action ct nat pipe \ action mirred egress redirect dev ens1f0_0 Signed-off-by: Paul Blakey Signed-off-by: Marcelo Ricardo Leitner Signed-off-by: Yossi Kuperman Acked-by: Jiri Pirko Changelog: V5->V6: Added CONFIG_NF_DEFRAG_IPV6 in handle fragments ipv6 case V4->V5: Reordered nf_conntrack_put() in tcf_ct_skb_nfct_cached() V3->V4: Added strict_start_type for act_ct policy V2->V3: Fixed david's comments: Removed extra newline after rcu in tcf_ct_params , and indent of break in act_ct.c V1->V2: Fixed parsing of ranges TCA_CT_NAT_IPV6_MAX as 'else' case overwritten ipv4 max Refactored NAT_PORT_MIN_MAX range handling as well Added ipv4/ipv6 defragmentation Removed extra skb pull push of nw offset in exectute nat Refactored tcf_ct_skb_network_trim after pull Removed TCA_ACT_CT define Signed-off-by: David S. Miller --- include/net/flow_offload.h | 5 ++++ include/net/tc_act/tc_ct.h | 63 +++++++++++++++++++++++++++++++++++++++ include/uapi/linux/pkt_cls.h | 1 + include/uapi/linux/tc_act/tc_ct.h | 41 +++++++++++++++++++++++++ 4 files changed, 110 insertions(+) create mode 100644 include/net/tc_act/tc_ct.h create mode 100644 include/uapi/linux/tc_act/tc_ct.h (limited to 'include') diff --git a/include/net/flow_offload.h b/include/net/flow_offload.h index 36127c1858a4..a09e256d2b27 100644 --- a/include/net/flow_offload.h +++ b/include/net/flow_offload.h @@ -129,6 +129,7 @@ enum flow_action_id { FLOW_ACTION_QUEUE, FLOW_ACTION_SAMPLE, FLOW_ACTION_POLICE, + FLOW_ACTION_CT, }; /* This is mirroring enum pedit_header_type definition for easy mapping between @@ -178,6 +179,10 @@ struct flow_action_entry { s64 burst; u64 rate_bytes_ps; } police; + struct { /* FLOW_ACTION_CT */ + int action; + u16 zone; + } ct; }; }; diff --git a/include/net/tc_act/tc_ct.h b/include/net/tc_act/tc_ct.h new file mode 100644 index 000000000000..bdc20ab3b88d --- /dev/null +++ b/include/net/tc_act/tc_ct.h @@ -0,0 +1,63 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef __NET_TC_CT_H +#define __NET_TC_CT_H + +#include +#include + +#if IS_ENABLED(CONFIG_NF_CONNTRACK) +#include +#include + +struct tcf_ct_params { + struct nf_conn *tmpl; + u16 zone; + + u32 mark; + u32 mark_mask; + + u32 labels[NF_CT_LABELS_MAX_SIZE / sizeof(u32)]; + u32 labels_mask[NF_CT_LABELS_MAX_SIZE / sizeof(u32)]; + + struct nf_nat_range2 range; + bool ipv4_range; + + u16 ct_action; + + struct rcu_head rcu; +}; + +struct tcf_ct { + struct tc_action common; + struct tcf_ct_params __rcu *params; +}; + +#define to_ct(a) ((struct tcf_ct *)a) +#define to_ct_params(a) ((struct tcf_ct_params *) \ + rtnl_dereference((to_ct(a)->params))) + +static inline uint16_t tcf_ct_zone(const struct tc_action *a) +{ + return to_ct_params(a)->zone; +} + +static inline int tcf_ct_action(const struct tc_action *a) +{ + return to_ct_params(a)->ct_action; +} + +#else +static inline uint16_t tcf_ct_zone(const struct tc_action *a) { return 0; } +static inline int tcf_ct_action(const struct tc_action *a) { return 0; } +#endif /* CONFIG_NF_CONNTRACK */ + +static inline bool is_tcf_ct(const struct tc_action *a) +{ +#if defined(CONFIG_NET_CLS_ACT) && IS_ENABLED(CONFIG_NF_CONNTRACK) + if (a->ops && a->ops->id == TCA_ID_CT) + return true; +#endif + return false; +} + +#endif /* __NET_TC_CT_H */ diff --git a/include/uapi/linux/pkt_cls.h b/include/uapi/linux/pkt_cls.h index e22ef4a940bc..31db5589b7ca 100644 --- a/include/uapi/linux/pkt_cls.h +++ b/include/uapi/linux/pkt_cls.h @@ -106,6 +106,7 @@ enum tca_id { TCA_ID_SAMPLE = TCA_ACT_SAMPLE, TCA_ID_CTINFO, TCA_ID_MPLS, + TCA_ID_CT, /* other actions go here */ __TCA_ID_MAX = 255 }; diff --git a/include/uapi/linux/tc_act/tc_ct.h b/include/uapi/linux/tc_act/tc_ct.h new file mode 100644 index 000000000000..5fb1d7ac1027 --- /dev/null +++ b/include/uapi/linux/tc_act/tc_ct.h @@ -0,0 +1,41 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ +#ifndef __UAPI_TC_CT_H +#define __UAPI_TC_CT_H + +#include +#include + +enum { + TCA_CT_UNSPEC, + TCA_CT_PARMS, + TCA_CT_TM, + TCA_CT_ACTION, /* u16 */ + TCA_CT_ZONE, /* u16 */ + TCA_CT_MARK, /* u32 */ + TCA_CT_MARK_MASK, /* u32 */ + TCA_CT_LABELS, /* u128 */ + TCA_CT_LABELS_MASK, /* u128 */ + TCA_CT_NAT_IPV4_MIN, /* be32 */ + TCA_CT_NAT_IPV4_MAX, /* be32 */ + TCA_CT_NAT_IPV6_MIN, /* struct in6_addr */ + TCA_CT_NAT_IPV6_MAX, /* struct in6_addr */ + TCA_CT_NAT_PORT_MIN, /* be16 */ + TCA_CT_NAT_PORT_MAX, /* be16 */ + TCA_CT_PAD, + __TCA_CT_MAX +}; + +#define TCA_CT_MAX (__TCA_CT_MAX - 1) + +#define TCA_CT_ACT_COMMIT (1 << 0) +#define TCA_CT_ACT_FORCE (1 << 1) +#define TCA_CT_ACT_CLEAR (1 << 2) +#define TCA_CT_ACT_NAT (1 << 3) +#define TCA_CT_ACT_NAT_SRC (1 << 4) +#define TCA_CT_ACT_NAT_DST (1 << 5) + +struct tc_ct { + tc_gen; +}; + +#endif /* __UAPI_TC_CT_H */ -- cgit v1.2.3 From 75a56758d6390ea6db523ad26ce378f34b907b0c Mon Sep 17 00:00:00 2001 From: Paul Blakey Date: Tue, 9 Jul 2019 10:30:49 +0300 Subject: net/flow_dissector: add connection tracking dissection Retreives connection tracking zone, mark, label, and state from a SKB. Signed-off-by: Paul Blakey Signed-off-by: Marcelo Ricardo Leitner Acked-by: Jiri Pirko Signed-off-by: David S. Miller --- include/linux/skbuff.h | 10 ++++++++++ include/net/flow_dissector.h | 15 +++++++++++++++ 2 files changed, 25 insertions(+) (limited to 'include') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 9d7a2c28ea35..d8af86d995d6 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -1325,6 +1325,16 @@ void skb_flow_dissect_meta(const struct sk_buff *skb, struct flow_dissector *flow_dissector, void *target_container); +/* Gets a skb connection tracking info, ctinfo map should be a + * a map of mapsize to translate enum ip_conntrack_info states + * to user states. + */ +void +skb_flow_dissect_ct(const struct sk_buff *skb, + struct flow_dissector *flow_dissector, + void *target_container, + u16 *ctinfo_map, + size_t mapsize); void skb_flow_dissect_tunnel_info(const struct sk_buff *skb, struct flow_dissector *flow_dissector, diff --git a/include/net/flow_dissector.h b/include/net/flow_dissector.h index 02478e48fae4..90bd210be060 100644 --- a/include/net/flow_dissector.h +++ b/include/net/flow_dissector.h @@ -208,6 +208,20 @@ struct flow_dissector_key_meta { int ingress_ifindex; }; +/** + * struct flow_dissector_key_ct: + * @ct_state: conntrack state after converting with map + * @ct_mark: conttrack mark + * @ct_zone: conntrack zone + * @ct_labels: conntrack labels + */ +struct flow_dissector_key_ct { + u16 ct_state; + u16 ct_zone; + u32 ct_mark; + u32 ct_labels[4]; +}; + enum flow_dissector_key_id { FLOW_DISSECTOR_KEY_CONTROL, /* struct flow_dissector_key_control */ FLOW_DISSECTOR_KEY_BASIC, /* struct flow_dissector_key_basic */ @@ -234,6 +248,7 @@ enum flow_dissector_key_id { FLOW_DISSECTOR_KEY_ENC_IP, /* struct flow_dissector_key_ip */ FLOW_DISSECTOR_KEY_ENC_OPTS, /* struct flow_dissector_key_enc_opts */ FLOW_DISSECTOR_KEY_META, /* struct flow_dissector_key_meta */ + FLOW_DISSECTOR_KEY_CT, /* struct flow_dissector_key_ct */ FLOW_DISSECTOR_KEY_MAX, }; -- cgit v1.2.3 From e0ace68af2acfe474bc89a3d9a2e24d700bf245d Mon Sep 17 00:00:00 2001 From: Paul Blakey Date: Tue, 9 Jul 2019 10:30:50 +0300 Subject: net/sched: cls_flower: Add matching on conntrack info New matches for conntrack mark, label, zone, and state. Signed-off-by: Paul Blakey Signed-off-by: Marcelo Ricardo Leitner Signed-off-by: Yossi Kuperman Acked-by: Jiri Pirko Signed-off-by: David S. Miller --- include/uapi/linux/pkt_cls.h | 16 ++++++++++++++++ 1 file changed, 16 insertions(+) (limited to 'include') diff --git a/include/uapi/linux/pkt_cls.h b/include/uapi/linux/pkt_cls.h index 31db5589b7ca..b057aeeb6338 100644 --- a/include/uapi/linux/pkt_cls.h +++ b/include/uapi/linux/pkt_cls.h @@ -537,11 +537,27 @@ enum { TCA_FLOWER_KEY_PORT_DST_MIN, /* be16 */ TCA_FLOWER_KEY_PORT_DST_MAX, /* be16 */ + TCA_FLOWER_KEY_CT_STATE, /* u16 */ + TCA_FLOWER_KEY_CT_STATE_MASK, /* u16 */ + TCA_FLOWER_KEY_CT_ZONE, /* u16 */ + TCA_FLOWER_KEY_CT_ZONE_MASK, /* u16 */ + TCA_FLOWER_KEY_CT_MARK, /* u32 */ + TCA_FLOWER_KEY_CT_MARK_MASK, /* u32 */ + TCA_FLOWER_KEY_CT_LABELS, /* u128 */ + TCA_FLOWER_KEY_CT_LABELS_MASK, /* u128 */ + __TCA_FLOWER_MAX, }; #define TCA_FLOWER_MAX (__TCA_FLOWER_MAX - 1) +enum { + TCA_FLOWER_KEY_CT_FLAGS_NEW = 1 << 0, /* Beginning of a new connection. */ + TCA_FLOWER_KEY_CT_FLAGS_ESTABLISHED = 1 << 1, /* Part of an existing connection. */ + TCA_FLOWER_KEY_CT_FLAGS_RELATED = 1 << 2, /* Related to an established connection. */ + TCA_FLOWER_KEY_CT_FLAGS_TRACKED = 1 << 3, /* Conntrack has occurred. */ +}; + enum { TCA_FLOWER_KEY_ENC_OPTS_UNSPEC, TCA_FLOWER_KEY_ENC_OPTS_GENEVE, /* Nested -- cgit v1.2.3 From 4e95bc268b915c3a19ec8b9110f61e4ea41a1ed0 Mon Sep 17 00:00:00 2001 From: Pablo Neira Ayuso Date: Tue, 9 Jul 2019 22:55:39 +0200 Subject: net: flow_offload: add flow_block_cb_setup_simple() Most drivers do the same thing to set up the flow block callbacks, this patch adds a helper function to do this. This preparation patch reduces the number of changes to adapt the existing drivers to use the flow block callback API. This new helper function takes a flow block list per-driver, which is set to NULL until this driver list is used. This patch also introduces the flow_block_command and flow_block_binder_type enumerations, which are renamed to use FLOW_BLOCK_* in follow up patches. There are three definitions (aliases) in order to reduce the number of updates in this patch, which go away once drivers are fully adapted to use this flow block API. Signed-off-by: Pablo Neira Ayuso Reviewed-by: Jakub Kicinski Signed-off-by: David S. Miller --- include/net/flow_offload.h | 27 +++++++++++++++++++++++++++ include/net/pkt_cls.h | 20 +++----------------- 2 files changed, 30 insertions(+), 17 deletions(-) (limited to 'include') diff --git a/include/net/flow_offload.h b/include/net/flow_offload.h index a09e256d2b27..2430e4907fe9 100644 --- a/include/net/flow_offload.h +++ b/include/net/flow_offload.h @@ -3,6 +3,7 @@ #include #include +#include struct flow_match { struct flow_dissector *dissector; @@ -237,4 +238,30 @@ static inline void flow_stats_update(struct flow_stats *flow_stats, flow_stats->lastused = max_t(u64, flow_stats->lastused, lastused); } +enum flow_block_command { + TC_BLOCK_BIND, + TC_BLOCK_UNBIND, +}; + +enum flow_block_binder_type { + TCF_BLOCK_BINDER_TYPE_UNSPEC, + TCF_BLOCK_BINDER_TYPE_CLSACT_INGRESS, + TCF_BLOCK_BINDER_TYPE_CLSACT_EGRESS, +}; + +struct tcf_block; +struct netlink_ext_ack; + +struct flow_block_offload { + enum flow_block_command command; + enum flow_block_binder_type binder_type; + struct tcf_block *block; + struct list_head *driver_block_list; + struct netlink_ext_ack *extack; +}; + +int flow_block_cb_setup_simple(struct flow_block_offload *f, + struct list_head *driver_list, tc_setup_cb_t *cb, + void *cb_ident, void *cb_priv, bool ingress_only); + #endif /* _NET_FLOW_OFFLOAD_H */ diff --git a/include/net/pkt_cls.h b/include/net/pkt_cls.h index 1a7596ba0dbe..b6c306fa9541 100644 --- a/include/net/pkt_cls.h +++ b/include/net/pkt_cls.h @@ -26,11 +26,9 @@ struct tcf_walker { int register_tcf_proto_ops(struct tcf_proto_ops *ops); int unregister_tcf_proto_ops(struct tcf_proto_ops *ops); -enum tcf_block_binder_type { - TCF_BLOCK_BINDER_TYPE_UNSPEC, - TCF_BLOCK_BINDER_TYPE_CLSACT_INGRESS, - TCF_BLOCK_BINDER_TYPE_CLSACT_EGRESS, -}; +#define tc_block_offload flow_block_offload +#define tc_block_command flow_block_command +#define tcf_block_binder_type flow_block_binder_type struct tcf_block_ext_info { enum tcf_block_binder_type binder_type; @@ -610,18 +608,6 @@ int tc_setup_cb_call(struct tcf_block *block, enum tc_setup_type type, void *type_data, bool err_stop); unsigned int tcf_exts_num_actions(struct tcf_exts *exts); -enum tc_block_command { - TC_BLOCK_BIND, - TC_BLOCK_UNBIND, -}; - -struct tc_block_offload { - enum tc_block_command command; - enum tcf_block_binder_type binder_type; - struct tcf_block *block; - struct netlink_ext_ack *extack; -}; - struct tc_cls_common_offload { u32 chain_index; __be16 protocol; -- cgit v1.2.3 From 9c0e189ec988f306331036bc3f71085582b24fdc Mon Sep 17 00:00:00 2001 From: Pablo Neira Ayuso Date: Tue, 9 Jul 2019 22:55:40 +0200 Subject: net: flow_offload: rename TC_BLOCK_{UN}BIND to FLOW_BLOCK_{UN}BIND Rename from TC_BLOCK_{UN}BIND to FLOW_BLOCK_{UN}BIND and remove temporary tc_block_command alias. Signed-off-by: Pablo Neira Ayuso Signed-off-by: David S. Miller --- include/net/flow_offload.h | 4 ++-- include/net/pkt_cls.h | 1 - 2 files changed, 2 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/include/net/flow_offload.h b/include/net/flow_offload.h index 2430e4907fe9..7c9f7a2ac7ce 100644 --- a/include/net/flow_offload.h +++ b/include/net/flow_offload.h @@ -239,8 +239,8 @@ static inline void flow_stats_update(struct flow_stats *flow_stats, } enum flow_block_command { - TC_BLOCK_BIND, - TC_BLOCK_UNBIND, + FLOW_BLOCK_BIND, + FLOW_BLOCK_UNBIND, }; enum flow_block_binder_type { diff --git a/include/net/pkt_cls.h b/include/net/pkt_cls.h index b6c306fa9541..1a96f469164f 100644 --- a/include/net/pkt_cls.h +++ b/include/net/pkt_cls.h @@ -27,7 +27,6 @@ int register_tcf_proto_ops(struct tcf_proto_ops *ops); int unregister_tcf_proto_ops(struct tcf_proto_ops *ops); #define tc_block_offload flow_block_offload -#define tc_block_command flow_block_command #define tcf_block_binder_type flow_block_binder_type struct tcf_block_ext_info { -- cgit v1.2.3 From 32f8c4093ac353a5f1b36cfed0ce0138faf8e15f Mon Sep 17 00:00:00 2001 From: Pablo Neira Ayuso Date: Tue, 9 Jul 2019 22:55:41 +0200 Subject: net: flow_offload: rename TCF_BLOCK_BINDER_TYPE_* to FLOW_BLOCK_BINDER_TYPE_* Rename from TCF_BLOCK_BINDER_TYPE_* to FLOW_BLOCK_BINDER_TYPE_* and remove temporary tcf_block_binder_type alias. Signed-off-by: Pablo Neira Ayuso Signed-off-by: David S. Miller --- include/net/flow_offload.h | 6 +++--- include/net/pkt_cls.h | 3 +-- 2 files changed, 4 insertions(+), 5 deletions(-) (limited to 'include') diff --git a/include/net/flow_offload.h b/include/net/flow_offload.h index 7c9f7a2ac7ce..f12b905ad95e 100644 --- a/include/net/flow_offload.h +++ b/include/net/flow_offload.h @@ -244,9 +244,9 @@ enum flow_block_command { }; enum flow_block_binder_type { - TCF_BLOCK_BINDER_TYPE_UNSPEC, - TCF_BLOCK_BINDER_TYPE_CLSACT_INGRESS, - TCF_BLOCK_BINDER_TYPE_CLSACT_EGRESS, + FLOW_BLOCK_BINDER_TYPE_UNSPEC, + FLOW_BLOCK_BINDER_TYPE_CLSACT_INGRESS, + FLOW_BLOCK_BINDER_TYPE_CLSACT_EGRESS, }; struct tcf_block; diff --git a/include/net/pkt_cls.h b/include/net/pkt_cls.h index 1a96f469164f..e4499526fde8 100644 --- a/include/net/pkt_cls.h +++ b/include/net/pkt_cls.h @@ -27,10 +27,9 @@ int register_tcf_proto_ops(struct tcf_proto_ops *ops); int unregister_tcf_proto_ops(struct tcf_proto_ops *ops); #define tc_block_offload flow_block_offload -#define tcf_block_binder_type flow_block_binder_type struct tcf_block_ext_info { - enum tcf_block_binder_type binder_type; + enum flow_block_binder_type binder_type; tcf_chain_head_change_t *chain_head_change; void *chain_head_change_priv; u32 block_index; -- cgit v1.2.3 From d63db30c8537ba45208c156d71125db73d0fe522 Mon Sep 17 00:00:00 2001 From: Pablo Neira Ayuso Date: Tue, 9 Jul 2019 22:55:42 +0200 Subject: net: flow_offload: add flow_block_cb_alloc() and flow_block_cb_free() Add a new helper function to allocate flow_block_cb objects. Signed-off-by: Pablo Neira Ayuso Signed-off-by: David S. Miller --- include/net/flow_offload.h | 14 ++++++++++++++ 1 file changed, 14 insertions(+) (limited to 'include') diff --git a/include/net/flow_offload.h b/include/net/flow_offload.h index f12b905ad95e..45d74cb542cd 100644 --- a/include/net/flow_offload.h +++ b/include/net/flow_offload.h @@ -260,6 +260,20 @@ struct flow_block_offload { struct netlink_ext_ack *extack; }; +struct flow_block_cb { + struct list_head list; + tc_setup_cb_t *cb; + void *cb_ident; + void *cb_priv; + void (*release)(void *cb_priv); + unsigned int refcnt; +}; + +struct flow_block_cb *flow_block_cb_alloc(struct net *net, tc_setup_cb_t *cb, + void *cb_ident, void *cb_priv, + void (*release)(void *cb_priv)); +void flow_block_cb_free(struct flow_block_cb *block_cb); + int flow_block_cb_setup_simple(struct flow_block_offload *f, struct list_head *driver_list, tc_setup_cb_t *cb, void *cb_ident, void *cb_priv, bool ingress_only); -- cgit v1.2.3 From da3eeb904ff432ec22cf7b4db17a47647428873a Mon Sep 17 00:00:00 2001 From: Pablo Neira Ayuso Date: Tue, 9 Jul 2019 22:55:43 +0200 Subject: net: flow_offload: add list handling functions This patch adds the list handling functions for the flow block API: * flow_block_cb_lookup() allows drivers to look up for existing flow blocks. * flow_block_cb_add() adds a flow block to the per driver list to be registered by the core. * flow_block_cb_remove() to remove a flow block from the list of existing flow blocks per driver and to request the core to unregister this. The flow block API also annotates the netns this flow block belongs to. Signed-off-by: Pablo Neira Ayuso Signed-off-by: David S. Miller --- include/net/flow_offload.h | 19 +++++++++++++++++++ 1 file changed, 19 insertions(+) (limited to 'include') diff --git a/include/net/flow_offload.h b/include/net/flow_offload.h index 45d74cb542cd..563d7dc7afc1 100644 --- a/include/net/flow_offload.h +++ b/include/net/flow_offload.h @@ -256,12 +256,16 @@ struct flow_block_offload { enum flow_block_command command; enum flow_block_binder_type binder_type; struct tcf_block *block; + struct net *net; + struct list_head cb_list; struct list_head *driver_block_list; struct netlink_ext_ack *extack; }; struct flow_block_cb { + struct list_head driver_list; struct list_head list; + struct net *net; tc_setup_cb_t *cb; void *cb_ident; void *cb_priv; @@ -274,6 +278,21 @@ struct flow_block_cb *flow_block_cb_alloc(struct net *net, tc_setup_cb_t *cb, void (*release)(void *cb_priv)); void flow_block_cb_free(struct flow_block_cb *block_cb); +struct flow_block_cb *flow_block_cb_lookup(struct flow_block_offload *offload, + tc_setup_cb_t *cb, void *cb_ident); + +static inline void flow_block_cb_add(struct flow_block_cb *block_cb, + struct flow_block_offload *offload) +{ + list_add_tail(&block_cb->list, &offload->cb_list); +} + +static inline void flow_block_cb_remove(struct flow_block_cb *block_cb, + struct flow_block_offload *offload) +{ + list_move(&block_cb->list, &offload->cb_list); +} + int flow_block_cb_setup_simple(struct flow_block_offload *f, struct list_head *driver_list, tc_setup_cb_t *cb, void *cb_ident, void *cb_priv, bool ingress_only); -- cgit v1.2.3 From 67bd0d5ea7974d9dc9c502c7b4096e16a80a553d Mon Sep 17 00:00:00 2001 From: Pablo Neira Ayuso Date: Tue, 9 Jul 2019 22:55:44 +0200 Subject: net: flow_offload: add flow_block_cb_{priv, incref, decref}() This patch completes the flow block API to introduce: * flow_block_cb_priv() to access callback private data. * flow_block_cb_incref() to bump reference counter on this flow block. * flow_block_cb_decref() to decrement the reference counter. These functions are taken from the existing tcf_block_cb_priv(), tcf_block_cb_incref() and tcf_block_cb_decref(). Signed-off-by: Pablo Neira Ayuso Signed-off-by: David S. Miller --- include/net/flow_offload.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include') diff --git a/include/net/flow_offload.h b/include/net/flow_offload.h index 563d7dc7afc1..3fb9cc4da63e 100644 --- a/include/net/flow_offload.h +++ b/include/net/flow_offload.h @@ -281,6 +281,10 @@ void flow_block_cb_free(struct flow_block_cb *block_cb); struct flow_block_cb *flow_block_cb_lookup(struct flow_block_offload *offload, tc_setup_cb_t *cb, void *cb_ident); +void *flow_block_cb_priv(struct flow_block_cb *block_cb); +void flow_block_cb_incref(struct flow_block_cb *block_cb); +unsigned int flow_block_cb_decref(struct flow_block_cb *block_cb); + static inline void flow_block_cb_add(struct flow_block_cb *block_cb, struct flow_block_offload *offload) { -- cgit v1.2.3 From 955bcb6ea0df0d9ace89ac475405f1295ced5962 Mon Sep 17 00:00:00 2001 From: Pablo Neira Ayuso Date: Tue, 9 Jul 2019 22:55:46 +0200 Subject: drivers: net: use flow block API This patch updates flow_block_cb_setup_simple() to use the flow block API. Several drivers are also adjusted to use it. This patch introduces the per-driver list of flow blocks to account for blocks that are already in use. Remove tc_block_offload alias. Signed-off-by: Pablo Neira Ayuso Signed-off-by: David S. Miller --- include/net/flow_offload.h | 3 +-- include/net/pkt_cls.h | 2 -- 2 files changed, 1 insertion(+), 4 deletions(-) (limited to 'include') diff --git a/include/net/flow_offload.h b/include/net/flow_offload.h index 3fb9cc4da63e..377ba0004370 100644 --- a/include/net/flow_offload.h +++ b/include/net/flow_offload.h @@ -249,13 +249,12 @@ enum flow_block_binder_type { FLOW_BLOCK_BINDER_TYPE_CLSACT_EGRESS, }; -struct tcf_block; struct netlink_ext_ack; struct flow_block_offload { enum flow_block_command command; enum flow_block_binder_type binder_type; - struct tcf_block *block; + bool block_shared; struct net *net; struct list_head cb_list; struct list_head *driver_block_list; diff --git a/include/net/pkt_cls.h b/include/net/pkt_cls.h index e4499526fde8..9cf606b88526 100644 --- a/include/net/pkt_cls.h +++ b/include/net/pkt_cls.h @@ -26,8 +26,6 @@ struct tcf_walker { int register_tcf_proto_ops(struct tcf_proto_ops *ops); int unregister_tcf_proto_ops(struct tcf_proto_ops *ops); -#define tc_block_offload flow_block_offload - struct tcf_block_ext_info { enum flow_block_binder_type binder_type; tcf_chain_head_change_t *chain_head_change; -- cgit v1.2.3 From 722d36e6e29e50c640c9f5ce186b8d8709cae1a6 Mon Sep 17 00:00:00 2001 From: Pablo Neira Ayuso Date: Tue, 9 Jul 2019 22:55:47 +0200 Subject: net: sched: remove tcf block API Unused, now replaced by flow block API. Signed-off-by: Pablo Neira Ayuso Signed-off-by: David S. Miller --- include/net/pkt_cls.h | 69 --------------------------------------------------- 1 file changed, 69 deletions(-) (limited to 'include') diff --git a/include/net/pkt_cls.h b/include/net/pkt_cls.h index 9cf606b88526..17c388090c3c 100644 --- a/include/net/pkt_cls.h +++ b/include/net/pkt_cls.h @@ -66,22 +66,6 @@ static inline struct Qdisc *tcf_block_q(struct tcf_block *block) return block->q; } -void *tcf_block_cb_priv(struct tcf_block_cb *block_cb); -struct tcf_block_cb *tcf_block_cb_lookup(struct tcf_block *block, - tc_setup_cb_t *cb, void *cb_ident); -void tcf_block_cb_incref(struct tcf_block_cb *block_cb); -unsigned int tcf_block_cb_decref(struct tcf_block_cb *block_cb); -struct tcf_block_cb *__tcf_block_cb_register(struct tcf_block *block, - tc_setup_cb_t *cb, void *cb_ident, - void *cb_priv, - struct netlink_ext_ack *extack); -int tcf_block_cb_register(struct tcf_block *block, - tc_setup_cb_t *cb, void *cb_ident, - void *cb_priv, struct netlink_ext_ack *extack); -void __tcf_block_cb_unregister(struct tcf_block *block, - struct tcf_block_cb *block_cb); -void tcf_block_cb_unregister(struct tcf_block *block, - tc_setup_cb_t *cb, void *cb_ident); int __tc_indr_block_cb_register(struct net_device *dev, void *cb_priv, tc_indr_block_bind_cb_t *cb, void *cb_ident); int tc_indr_block_cb_register(struct net_device *dev, void *cb_priv, @@ -144,59 +128,6 @@ void tc_setup_cb_block_unregister(struct tcf_block *block, tc_setup_cb_t *cb, { } -static inline -void *tcf_block_cb_priv(struct tcf_block_cb *block_cb) -{ - return NULL; -} - -static inline -struct tcf_block_cb *tcf_block_cb_lookup(struct tcf_block *block, - tc_setup_cb_t *cb, void *cb_ident) -{ - return NULL; -} - -static inline -void tcf_block_cb_incref(struct tcf_block_cb *block_cb) -{ -} - -static inline -unsigned int tcf_block_cb_decref(struct tcf_block_cb *block_cb) -{ - return 0; -} - -static inline -struct tcf_block_cb *__tcf_block_cb_register(struct tcf_block *block, - tc_setup_cb_t *cb, void *cb_ident, - void *cb_priv, - struct netlink_ext_ack *extack) -{ - return NULL; -} - -static inline -int tcf_block_cb_register(struct tcf_block *block, - tc_setup_cb_t *cb, void *cb_ident, - void *cb_priv, struct netlink_ext_ack *extack) -{ - return 0; -} - -static inline -void __tcf_block_cb_unregister(struct tcf_block *block, - struct tcf_block_cb *block_cb) -{ -} - -static inline -void tcf_block_cb_unregister(struct tcf_block *block, - tc_setup_cb_t *cb, void *cb_ident) -{ -} - static inline int __tc_indr_block_cb_register(struct net_device *dev, void *cb_priv, tc_indr_block_bind_cb_t *cb, void *cb_ident) -- cgit v1.2.3 From 0d4fd02e7199fbf57c0d175dd1890c82cd4a6f4f Mon Sep 17 00:00:00 2001 From: Pablo Neira Ayuso Date: Tue, 9 Jul 2019 22:55:48 +0200 Subject: net: flow_offload: add flow_block_cb_is_busy() and use it This patch adds a function to check if flow block callback is already in use. Call this new function from flow_block_cb_setup_simple() and from drivers. Signed-off-by: Pablo Neira Ayuso Signed-off-by: David S. Miller --- include/net/flow_offload.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include') diff --git a/include/net/flow_offload.h b/include/net/flow_offload.h index 377ba0004370..42a36a346003 100644 --- a/include/net/flow_offload.h +++ b/include/net/flow_offload.h @@ -296,6 +296,9 @@ static inline void flow_block_cb_remove(struct flow_block_cb *block_cb, list_move(&block_cb->list, &offload->cb_list); } +bool flow_block_cb_is_busy(tc_setup_cb_t *cb, void *cb_ident, + struct list_head *driver_block_list); + int flow_block_cb_setup_simple(struct flow_block_offload *f, struct list_head *driver_list, tc_setup_cb_t *cb, void *cb_ident, void *cb_priv, bool ingress_only); -- cgit v1.2.3 From f9e30088d20016a224d8110d45356da253eaa26a Mon Sep 17 00:00:00 2001 From: Pablo Neira Ayuso Date: Tue, 9 Jul 2019 22:55:49 +0200 Subject: net: flow_offload: rename tc_cls_flower_offload to flow_cls_offload And any other existing fields in this structure that refer to tc. Specifically: * tc_cls_flower_offload_flow_rule() to flow_cls_offload_flow_rule(). * TC_CLSFLOWER_* to FLOW_CLS_*. * tc_cls_common_offload to tc_cls_common_offload. Signed-off-by: Pablo Neira Ayuso Signed-off-by: David S. Miller --- include/net/flow_offload.h | 30 ++++++++++++++++++++++++++++++ include/net/pkt_cls.h | 40 +++++----------------------------------- 2 files changed, 35 insertions(+), 35 deletions(-) (limited to 'include') diff --git a/include/net/flow_offload.h b/include/net/flow_offload.h index 42a36a346003..db337299e81e 100644 --- a/include/net/flow_offload.h +++ b/include/net/flow_offload.h @@ -303,4 +303,34 @@ int flow_block_cb_setup_simple(struct flow_block_offload *f, struct list_head *driver_list, tc_setup_cb_t *cb, void *cb_ident, void *cb_priv, bool ingress_only); +enum flow_cls_command { + FLOW_CLS_REPLACE, + FLOW_CLS_DESTROY, + FLOW_CLS_STATS, + FLOW_CLS_TMPLT_CREATE, + FLOW_CLS_TMPLT_DESTROY, +}; + +struct flow_cls_common_offload { + u32 chain_index; + __be16 protocol; + u32 prio; + struct netlink_ext_ack *extack; +}; + +struct flow_cls_offload { + struct flow_cls_common_offload common; + enum flow_cls_command command; + unsigned long cookie; + struct flow_rule *rule; + struct flow_stats stats; + u32 classid; +}; + +static inline struct flow_rule * +flow_cls_offload_flow_rule(struct flow_cls_offload *flow_cmd) +{ + return flow_cmd->rule; +} + #endif /* _NET_FLOW_OFFLOAD_H */ diff --git a/include/net/pkt_cls.h b/include/net/pkt_cls.h index 17c388090c3c..b03d466182db 100644 --- a/include/net/pkt_cls.h +++ b/include/net/pkt_cls.h @@ -535,13 +535,6 @@ int tc_setup_cb_call(struct tcf_block *block, enum tc_setup_type type, void *type_data, bool err_stop); unsigned int tcf_exts_num_actions(struct tcf_exts *exts); -struct tc_cls_common_offload { - u32 chain_index; - __be16 protocol; - u32 prio; - struct netlink_ext_ack *extack; -}; - struct tc_cls_u32_knode { struct tcf_exts *exts; struct tcf_result *res; @@ -569,7 +562,7 @@ enum tc_clsu32_command { }; struct tc_cls_u32_offload { - struct tc_cls_common_offload common; + struct flow_cls_common_offload common; /* knode values */ enum tc_clsu32_command command; union { @@ -596,7 +589,7 @@ static inline bool tc_can_offload_extack(const struct net_device *dev, static inline bool tc_cls_can_offload_and_chain0(const struct net_device *dev, - struct tc_cls_common_offload *common) + struct flow_cls_common_offload *common) { if (!tc_can_offload_extack(dev, common->extack)) return false; @@ -638,7 +631,7 @@ static inline bool tc_in_hw(u32 flags) } static inline void -tc_cls_common_offload_init(struct tc_cls_common_offload *cls_common, +tc_cls_common_offload_init(struct flow_cls_common_offload *cls_common, const struct tcf_proto *tp, u32 flags, struct netlink_ext_ack *extack) { @@ -649,29 +642,6 @@ tc_cls_common_offload_init(struct tc_cls_common_offload *cls_common, cls_common->extack = extack; } -enum tc_fl_command { - TC_CLSFLOWER_REPLACE, - TC_CLSFLOWER_DESTROY, - TC_CLSFLOWER_STATS, - TC_CLSFLOWER_TMPLT_CREATE, - TC_CLSFLOWER_TMPLT_DESTROY, -}; - -struct tc_cls_flower_offload { - struct tc_cls_common_offload common; - enum tc_fl_command command; - unsigned long cookie; - struct flow_rule *rule; - struct flow_stats stats; - u32 classid; -}; - -static inline struct flow_rule * -tc_cls_flower_offload_flow_rule(struct tc_cls_flower_offload *tc_flow_cmd) -{ - return tc_flow_cmd->rule; -} - enum tc_matchall_command { TC_CLSMATCHALL_REPLACE, TC_CLSMATCHALL_DESTROY, @@ -679,7 +649,7 @@ enum tc_matchall_command { }; struct tc_cls_matchall_offload { - struct tc_cls_common_offload common; + struct flow_cls_common_offload common; enum tc_matchall_command command; struct flow_rule *rule; struct flow_stats stats; @@ -692,7 +662,7 @@ enum tc_clsbpf_command { }; struct tc_cls_bpf_offload { - struct tc_cls_common_offload common; + struct flow_cls_common_offload common; enum tc_clsbpf_command command; struct tcf_exts *exts; struct bpf_prog *prog; -- cgit v1.2.3 From c9626a2cbdb20e26587b3fad99960520a023432b Mon Sep 17 00:00:00 2001 From: Pablo Neira Ayuso Date: Tue, 9 Jul 2019 23:00:43 +0200 Subject: netfilter: nf_tables: add hardware offload support This patch adds hardware offload support for nftables through the existing netdev_ops->ndo_setup_tc() interface, the TC_SETUP_CLSFLOWER classifier and the flow rule API. This hardware offload support is available for the NFPROTO_NETDEV family and the ingress hook. Each nftables expression has a new ->offload interface, that is used to populate the flow rule object that is attached to the transaction object. There is a new per-table NFT_TABLE_F_HW flag, that is set on to offload an entire table, including all of its chains. This patch supports for basic metadata (layer 3 and 4 protocol numbers), 5-tuple payload matching and the accept/drop actions; this also includes basechain hardware offload only. Signed-off-by: Pablo Neira Ayuso Signed-off-by: David S. Miller --- include/net/netfilter/nf_tables.h | 14 ++++++ include/net/netfilter/nf_tables_offload.h | 76 +++++++++++++++++++++++++++++++ include/uapi/linux/netfilter/nf_tables.h | 2 + 3 files changed, 92 insertions(+) create mode 100644 include/net/netfilter/nf_tables_offload.h (limited to 'include') diff --git a/include/net/netfilter/nf_tables.h b/include/net/netfilter/nf_tables.h index 9e8493aad49d..35dfdd9f69b3 100644 --- a/include/net/netfilter/nf_tables.h +++ b/include/net/netfilter/nf_tables.h @@ -161,6 +161,7 @@ struct nft_ctx { const struct nlattr * const *nla; u32 portid; u32 seq; + u16 flags; u8 family; u8 level; bool report; @@ -735,6 +736,9 @@ enum nft_trans_phase { NFT_TRANS_RELEASE }; +struct nft_flow_rule; +struct nft_offload_ctx; + /** * struct nft_expr_ops - nf_tables expression operations * @@ -777,6 +781,10 @@ struct nft_expr_ops { const struct nft_data **data); bool (*gc)(struct net *net, const struct nft_expr *expr); + int (*offload)(struct nft_offload_ctx *ctx, + struct nft_flow_rule *flow, + const struct nft_expr *expr); + u32 offload_flags; const struct nft_expr_type *type; void *data; }; @@ -859,6 +867,7 @@ static inline struct nft_userdata *nft_userdata(const struct nft_rule *rule) enum nft_chain_flags { NFT_BASE_CHAIN = 0x1, + NFT_CHAIN_HW_OFFLOAD = 0x2, }; /** @@ -942,6 +951,7 @@ struct nft_stats { * @stats: per-cpu chain stats * @chain: the chain * @dev_name: device name that this base chain is attached to (if any) + * @cb_list: list of flow block callbacks (for hardware offload) */ struct nft_base_chain { struct nf_hook_ops ops; @@ -951,6 +961,7 @@ struct nft_base_chain { struct nft_stats __percpu *stats; struct nft_chain chain; char dev_name[IFNAMSIZ]; + struct list_head cb_list; }; static inline struct nft_base_chain *nft_base_chain(const struct nft_chain *chain) @@ -1322,11 +1333,14 @@ struct nft_trans { struct nft_trans_rule { struct nft_rule *rule; + struct nft_flow_rule *flow; u32 rule_id; }; #define nft_trans_rule(trans) \ (((struct nft_trans_rule *)trans->data)->rule) +#define nft_trans_flow_rule(trans) \ + (((struct nft_trans_rule *)trans->data)->flow) #define nft_trans_rule_id(trans) \ (((struct nft_trans_rule *)trans->data)->rule_id) diff --git a/include/net/netfilter/nf_tables_offload.h b/include/net/netfilter/nf_tables_offload.h new file mode 100644 index 000000000000..3196663a10e3 --- /dev/null +++ b/include/net/netfilter/nf_tables_offload.h @@ -0,0 +1,76 @@ +#ifndef _NET_NF_TABLES_OFFLOAD_H +#define _NET_NF_TABLES_OFFLOAD_H + +#include +#include + +struct nft_offload_reg { + u32 key; + u32 len; + u32 base_offset; + u32 offset; + struct nft_data mask; +}; + +enum nft_offload_dep_type { + NFT_OFFLOAD_DEP_UNSPEC = 0, + NFT_OFFLOAD_DEP_NETWORK, + NFT_OFFLOAD_DEP_TRANSPORT, +}; + +struct nft_offload_ctx { + struct { + enum nft_offload_dep_type type; + __be16 l3num; + u8 protonum; + } dep; + unsigned int num_actions; + struct nft_offload_reg regs[NFT_REG32_15 + 1]; +}; + +void nft_offload_set_dependency(struct nft_offload_ctx *ctx, + enum nft_offload_dep_type type); +void nft_offload_update_dependency(struct nft_offload_ctx *ctx, + const void *data, u32 len); + +struct nft_flow_key { + struct flow_dissector_key_basic basic; + union { + struct flow_dissector_key_ipv4_addrs ipv4; + struct flow_dissector_key_ipv6_addrs ipv6; + }; + struct flow_dissector_key_ports tp; + struct flow_dissector_key_ip ip; + struct flow_dissector_key_vlan vlan; + struct flow_dissector_key_eth_addrs eth_addrs; +} __aligned(BITS_PER_LONG / 8); /* Ensure that we can do comparisons as longs. */ + +struct nft_flow_match { + struct flow_dissector dissector; + struct nft_flow_key key; + struct nft_flow_key mask; +}; + +struct nft_flow_rule { + __be16 proto; + struct nft_flow_match match; + struct flow_rule *rule; +}; + +#define NFT_OFFLOAD_F_ACTION (1 << 0) + +struct nft_rule; +struct nft_flow_rule *nft_flow_rule_create(const struct nft_rule *rule); +void nft_flow_rule_destroy(struct nft_flow_rule *flow); +int nft_flow_rule_offload_commit(struct net *net); + +#define NFT_OFFLOAD_MATCH(__key, __base, __field, __len, __reg) \ + (__reg)->base_offset = \ + offsetof(struct nft_flow_key, __base); \ + (__reg)->offset = \ + offsetof(struct nft_flow_key, __base.__field); \ + (__reg)->len = __len; \ + (__reg)->key = __key; \ + memset(&(__reg)->mask, 0xff, (__reg)->len); + +#endif diff --git a/include/uapi/linux/netfilter/nf_tables.h b/include/uapi/linux/netfilter/nf_tables.h index 0e3462dfb182..82abaa183fc3 100644 --- a/include/uapi/linux/netfilter/nf_tables.h +++ b/include/uapi/linux/netfilter/nf_tables.h @@ -192,6 +192,7 @@ enum nft_table_attributes { * @NFTA_CHAIN_USE: number of references to this chain (NLA_U32) * @NFTA_CHAIN_TYPE: type name of the string (NLA_NUL_STRING) * @NFTA_CHAIN_COUNTERS: counter specification of the chain (NLA_NESTED: nft_counter_attributes) + * @NFTA_CHAIN_FLAGS: chain flags */ enum nft_chain_attributes { NFTA_CHAIN_UNSPEC, @@ -204,6 +205,7 @@ enum nft_chain_attributes { NFTA_CHAIN_TYPE, NFTA_CHAIN_COUNTERS, NFTA_CHAIN_PAD, + NFTA_CHAIN_FLAGS, __NFTA_CHAIN_MAX }; #define NFTA_CHAIN_MAX (__NFTA_CHAIN_MAX - 1) -- cgit v1.2.3 From fbc697796e358d1ed8ed25758b19bdb3a1f8e9f9 Mon Sep 17 00:00:00 2001 From: David Ahern Date: Tue, 9 Jul 2019 14:45:17 -0700 Subject: pkt_sched: Include const.h Commit 9903c8dc7342 changed TC_ETF defines to use _BITUL instead of BIT but did not add the dependecy on linux/const.h. As a consequence, importing the uapi headers into iproute2 causes builds to fail. Add the dependency. Fixes: 9903c8dc7342 ("etf: Don't use BIT() in UAPI headers.") Cc: Vedang Patel Signed-off-by: David Ahern Signed-off-by: David S. Miller --- include/uapi/linux/pkt_sched.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/uapi/linux/pkt_sched.h b/include/uapi/linux/pkt_sched.h index 390efb54b2e0..1f623252abe8 100644 --- a/include/uapi/linux/pkt_sched.h +++ b/include/uapi/linux/pkt_sched.h @@ -2,6 +2,7 @@ #ifndef __LINUX_PKT_SCHED_H #define __LINUX_PKT_SCHED_H +#include #include /* Logical priority bands not depending on specific packet scheduler. -- cgit v1.2.3