From dce4551cb2adb1ac9a30f8ab5299d614392b3cff Mon Sep 17 00:00:00 2001 From: Paolo Abeni Date: Tue, 25 Jul 2017 17:57:47 +0200 Subject: udp: preserve head state for IP_CMSG_PASSSEC Paul Moore reported a SELinux/IP_PASSSEC regression caused by missing skb->sp at recvmsg() time. We need to preserve the skb head state to process the IP_CMSG_PASSSEC cmsg. With this commit we avoid releasing the skb head state in the BH even if a secpath is attached to the current skb, and stores the skb status (with/without head states) in the scratch area, so that we can access it at skb deallocation time, without incurring in cache-miss penalties. This also avoids misusing the skb CB for ipv6 packets, as introduced by the commit 0ddf3fb2c43d ("udp: preserve skb->dst if required for IP options processing"). Clean a bit the scratch area helpers implementation, to reduce the code differences between 32 and 64 bits build. Reported-by: Paul Moore Fixes: 0a463c78d25b ("udp: avoid a cache miss on dequeue") Fixes: 0ddf3fb2c43d ("udp: preserve skb->dst if required for IP options processing") Signed-off-by: Paolo Abeni Tested-by: Paul Moore Signed-off-by: David S. Miller --- include/net/udp.h | 33 ++++++++++++++++++++++----------- 1 file changed, 22 insertions(+), 11 deletions(-) (limited to 'include') diff --git a/include/net/udp.h b/include/net/udp.h index 972ce4baab6b..56ce2d2a612d 100644 --- a/include/net/udp.h +++ b/include/net/udp.h @@ -305,33 +305,44 @@ struct sock *udp6_lib_lookup_skb(struct sk_buff *skb, /* UDP uses skb->dev_scratch to cache as much information as possible and avoid * possibly multiple cache miss on dequeue() */ -#if BITS_PER_LONG == 64 - -/* truesize, len and the bit needed to compute skb_csum_unnecessary will be on - * cold cache lines at recvmsg time. - * skb->len can be stored on 16 bits since the udp header has been already - * validated and pulled. - */ struct udp_dev_scratch { - u32 truesize; + /* skb->truesize and the stateless bit are embedded in a single field; + * do not use a bitfield since the compiler emits better/smaller code + * this way + */ + u32 _tsize_state; + +#if BITS_PER_LONG == 64 + /* len and the bit needed to compute skb_csum_unnecessary + * will be on cold cache lines at recvmsg time. + * skb->len can be stored on 16 bits since the udp header has been + * already validated and pulled. + */ u16 len; bool is_linear; bool csum_unnecessary; +#endif }; +static inline struct udp_dev_scratch *udp_skb_scratch(struct sk_buff *skb) +{ + return (struct udp_dev_scratch *)&skb->dev_scratch; +} + +#if BITS_PER_LONG == 64 static inline unsigned int udp_skb_len(struct sk_buff *skb) { - return ((struct udp_dev_scratch *)&skb->dev_scratch)->len; + return udp_skb_scratch(skb)->len; } static inline bool udp_skb_csum_unnecessary(struct sk_buff *skb) { - return ((struct udp_dev_scratch *)&skb->dev_scratch)->csum_unnecessary; + return udp_skb_scratch(skb)->csum_unnecessary; } static inline bool udp_skb_is_linear(struct sk_buff *skb) { - return ((struct udp_dev_scratch *)&skb->dev_scratch)->is_linear; + return udp_skb_scratch(skb)->is_linear; } #else -- cgit v1.2.3 From 2eaa38d9fcba5294182268b8d11770cf3fdc9bc9 Mon Sep 17 00:00:00 2001 From: Marc Gonzalez Date: Tue, 25 Jul 2017 11:08:15 +0200 Subject: net: phy: Remove trailing semicolon in macro definition Commit e5a03bfd873c2 ("phy: Add an mdio_device structure") introduced a spurious trailing semicolon. Remove it. Signed-off-by: Marc Gonzalez 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 2a9567bb8186..0bb5b212ab42 100644 --- a/include/linux/phy.h +++ b/include/linux/phy.h @@ -830,7 +830,7 @@ static inline int phy_read_status(struct phy_device *phydev) dev_err(&_phydev->mdio.dev, format, ##args) #define phydev_dbg(_phydev, format, args...) \ - dev_dbg(&_phydev->mdio.dev, format, ##args); + dev_dbg(&_phydev->mdio.dev, format, ##args) static inline const char *phydev_name(const struct phy_device *phydev) { -- cgit v1.2.3 From 6b84202c946cd3da3a8daa92c682510e9ed80321 Mon Sep 17 00:00:00 2001 From: Xin Long Date: Wed, 26 Jul 2017 16:24:59 +0800 Subject: sctp: fix the check for _sctp_walk_params and _sctp_walk_errors Commit b1f5bfc27a19 ("sctp: don't dereference ptr before leaving _sctp_walk_{params, errors}()") tried to fix the issue that it may overstep the chunk end for _sctp_walk_{params, errors} with 'chunk_end > offset(length) + sizeof(length)'. But it introduced a side effect: When processing INIT, it verifies the chunks with 'param.v == chunk_end' after iterating all params by sctp_walk_params(). With the check 'chunk_end > offset(length) + sizeof(length)', it would return when the last param is not yet accessed. Because the last param usually is fwdtsn supported param whose size is 4 and 'chunk_end == offset(length) + sizeof(length)' This is a badly issue even causing sctp couldn't process 4-shakes. Client would always get abort when connecting to server, due to the failure of INIT chunk verification on server. The patch is to use 'chunk_end <= offset(length) + sizeof(length)' instead of 'chunk_end < offset(length) + sizeof(length)' for both _sctp_walk_params and _sctp_walk_errors. Fixes: b1f5bfc27a19 ("sctp: don't dereference ptr before leaving _sctp_walk_{params, errors}()") Signed-off-by: Xin Long Acked-by: Neil Horman Signed-off-by: David S. Miller --- include/net/sctp/sctp.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/net/sctp/sctp.h b/include/net/sctp/sctp.h index 980807d7506f..45fd4c6056b5 100644 --- a/include/net/sctp/sctp.h +++ b/include/net/sctp/sctp.h @@ -469,7 +469,7 @@ _sctp_walk_params((pos), (chunk), ntohs((chunk)->chunk_hdr.length), member) #define _sctp_walk_params(pos, chunk, end, member)\ for (pos.v = chunk->member;\ - (pos.v + offsetof(struct sctp_paramhdr, length) + sizeof(pos.p->length) <\ + (pos.v + offsetof(struct sctp_paramhdr, length) + sizeof(pos.p->length) <=\ (void *)chunk + end) &&\ pos.v <= (void *)chunk + end - ntohs(pos.p->length) &&\ ntohs(pos.p->length) >= sizeof(struct sctp_paramhdr);\ @@ -481,7 +481,7 @@ _sctp_walk_errors((err), (chunk_hdr), ntohs((chunk_hdr)->length)) #define _sctp_walk_errors(err, chunk_hdr, end)\ for (err = (sctp_errhdr_t *)((void *)chunk_hdr + \ sizeof(struct sctp_chunkhdr));\ - ((void *)err + offsetof(sctp_errhdr_t, length) + sizeof(err->length) <\ + ((void *)err + offsetof(sctp_errhdr_t, length) + sizeof(err->length) <=\ (void *)chunk_hdr + end) &&\ (void *)err <= (void *)chunk_hdr + end - ntohs(err->length) &&\ ntohs(err->length) >= sizeof(sctp_errhdr_t); \ -- cgit v1.2.3 From 0b794ffae7afa7c4e5accac8791c4b78e8d080ce Mon Sep 17 00:00:00 2001 From: Eugenia Emantayev Date: Thu, 25 May 2017 15:11:26 +0300 Subject: net/mlx5: Fix mlx5_ifc_mtpps_reg_bits structure size Fix miscalculation in reserved_at_1a0 field. Fixes: ee7f12205abc ('net/mlx5e: Implement 1PPS support') Signed-off-by: Eugenia Emantayev Signed-off-by: Saeed Mahameed --- include/linux/mlx5/mlx5_ifc.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h index 87869c04849a..fd98aef4545c 100644 --- a/include/linux/mlx5/mlx5_ifc.h +++ b/include/linux/mlx5/mlx5_ifc.h @@ -8175,7 +8175,7 @@ struct mlx5_ifc_mtpps_reg_bits { u8 out_pulse_duration[0x10]; u8 out_periodic_adjustment[0x10]; - u8 reserved_at_1a0[0x60]; + u8 reserved_at_1a0[0x40]; }; struct mlx5_ifc_mtppse_reg_bits { -- cgit v1.2.3 From fa3676885e3b5be1edfa1b2cc775e20a45b34a19 Mon Sep 17 00:00:00 2001 From: Eugenia Emantayev Date: Thu, 25 May 2017 16:09:34 +0300 Subject: net/mlx5e: Add field select to MTPPS register In order to mark relevant fields while setting the MTPPS register add field select. Otherwise it can cause a misconfiguration in firmware. Fixes: ee7f12205abc ('net/mlx5e: Implement 1PPS support') Signed-off-by: Eugenia Emantayev Signed-off-by: Saeed Mahameed --- include/linux/mlx5/mlx5_ifc.h | 10 +++++++--- 1 file changed, 7 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h index fd98aef4545c..3030121b4746 100644 --- a/include/linux/mlx5/mlx5_ifc.h +++ b/include/linux/mlx5/mlx5_ifc.h @@ -7749,8 +7749,10 @@ struct mlx5_ifc_pcam_reg_bits { }; struct mlx5_ifc_mcam_enhanced_features_bits { - u8 reserved_at_0[0x7f]; + u8 reserved_at_0[0x7d]; + u8 mtpps_enh_out_per_adj[0x1]; + u8 mtpps_fs[0x1]; u8 pcie_performance_group[0x1]; }; @@ -8159,7 +8161,8 @@ struct mlx5_ifc_mtpps_reg_bits { u8 reserved_at_78[0x4]; u8 cap_pin_4_mode[0x4]; - u8 reserved_at_80[0x80]; + u8 field_select[0x20]; + u8 reserved_at_a0[0x60]; u8 enable[0x1]; u8 reserved_at_101[0xb]; @@ -8174,8 +8177,9 @@ struct mlx5_ifc_mtpps_reg_bits { u8 out_pulse_duration[0x10]; u8 out_periodic_adjustment[0x10]; + u8 enhanced_out_periodic_adjustment[0x20]; - u8 reserved_at_1a0[0x40]; + u8 reserved_at_1c0[0x20]; }; struct mlx5_ifc_mtppse_reg_bits { -- cgit v1.2.3 From c9f2c1ae123a751d4e4f949144500219354d5ee1 Mon Sep 17 00:00:00 2001 From: Paolo Abeni Date: Thu, 27 Jul 2017 14:45:09 +0200 Subject: udp6: fix socket leak on early demux When an early demuxed packet reaches __udp6_lib_lookup_skb(), the sk reference is retrieved and used, but the relevant reference count is leaked and the socket destructor is never called. Beyond leaking the sk memory, if there are pending UDP packets in the receive queue, even the related accounted memory is leaked. In the long run, this will cause persistent forward allocation errors and no UDP skbs (both ipv4 and ipv6) will be able to reach the user-space. Fix this by explicitly accessing the early demux reference before the lookup, and properly decreasing the socket reference count after usage. Also drop the skb_steal_sock() in __udp6_lib_lookup_skb(), and the now obsoleted comment about "socket cache". The newly added code is derived from the current ipv4 code for the similar path. v1 -> v2: fixed the __udp6_lib_rcv() return code for resubmission, as suggested by Eric Reported-by: Sam Edwards Reported-by: Marc Haber Fixes: 5425077d73e0 ("net: ipv6: Add early demux handler for UDP unicast") Signed-off-by: Paolo Abeni Acked-by: Eric Dumazet Signed-off-by: David S. Miller --- include/net/udp.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/net/udp.h b/include/net/udp.h index 56ce2d2a612d..cc8036987dcb 100644 --- a/include/net/udp.h +++ b/include/net/udp.h @@ -260,6 +260,7 @@ static inline struct sk_buff *skb_recv_udp(struct sock *sk, unsigned int flags, } void udp_v4_early_demux(struct sk_buff *skb); +void udp_sk_rx_dst_set(struct sock *sk, struct dst_entry *dst); int udp_get_port(struct sock *sk, unsigned short snum, int (*saddr_cmp)(const struct sock *, const struct sock *)); -- cgit v1.2.3 From cb891fa6a1d5f52c5f5c07b6f7f4c6d65ea55fc0 Mon Sep 17 00:00:00 2001 From: Paolo Abeni Date: Mon, 31 Jul 2017 16:52:36 +0200 Subject: udp6: fix jumbogram reception Since commit 67a51780aebb ("ipv6: udp: leverage scratch area helpers") udp6_recvmsg() read the skb len from the scratch area, to avoid a cache miss. But the UDP6 rx path support RFC 2675 UDPv6 jumbograms, and their length exceeds the 16 bits available in the scratch area. As a side effect the length returned by recvmsg() is: % (1<<16) This commit addresses the issue allocating one more bit in the IP6CB flags field and setting it for incoming jumbograms. Such field is still in the first cacheline, so at recvmsg() time we can check it and fallback to access skb->len if required, without a measurable overhead. Fixes: 67a51780aebb ("ipv6: udp: leverage scratch area helpers") Signed-off-by: Paolo Abeni Signed-off-by: David S. Miller --- include/linux/ipv6.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include') diff --git a/include/linux/ipv6.h b/include/linux/ipv6.h index e1b442996f81..474d6bbc158c 100644 --- a/include/linux/ipv6.h +++ b/include/linux/ipv6.h @@ -128,6 +128,7 @@ struct inet6_skb_parm { #define IP6SKB_FRAGMENTED 16 #define IP6SKB_HOPBYHOP 32 #define IP6SKB_L3SLAVE 64 +#define IP6SKB_JUMBOGRAM 128 }; #if defined(CONFIG_NET_L3_MASTER_DEV) @@ -152,6 +153,11 @@ static inline int inet6_iif(const struct sk_buff *skb) return l3_slave ? skb->skb_iif : IP6CB(skb)->iif; } +static inline bool inet6_is_jumbogram(const struct sk_buff *skb) +{ + return !!(IP6CB(skb)->flags & IP6SKB_JUMBOGRAM); +} + /* can not be used in TCP layer after tcp_v6_fill_cb */ static inline bool inet6_exact_dif_match(struct net *net, struct sk_buff *skb) { -- cgit v1.2.3