From d8616ee2affcff37c5d315310da557a694a3303d Mon Sep 17 00:00:00 2001 From: Wang Yufen Date: Tue, 24 May 2022 15:53:11 +0800 Subject: bpf, sockmap: Fix sk->sk_forward_alloc warn_on in sk_stream_kill_queues During TCP sockmap redirect pressure test, the following warning is triggered: WARNING: CPU: 3 PID: 2145 at net/core/stream.c:205 sk_stream_kill_queues+0xbc/0xd0 CPU: 3 PID: 2145 Comm: iperf Kdump: loaded Tainted: G W 5.10.0+ #9 Call Trace: inet_csk_destroy_sock+0x55/0x110 inet_csk_listen_stop+0xbb/0x380 tcp_close+0x41b/0x480 inet_release+0x42/0x80 __sock_release+0x3d/0xa0 sock_close+0x11/0x20 __fput+0x9d/0x240 task_work_run+0x62/0x90 exit_to_user_mode_prepare+0x110/0x120 syscall_exit_to_user_mode+0x27/0x190 entry_SYSCALL_64_after_hwframe+0x44/0xa9 The reason we observed is that: When the listener is closing, a connection may have completed the three-way handshake but not accepted, and the client has sent some packets. The child sks in accept queue release by inet_child_forget()->inet_csk_destroy_sock(), but psocks of child sks have not released. To fix, add sock_map_destroy to release psocks. Signed-off-by: Wang Yufen Signed-off-by: Daniel Borkmann Signed-off-by: Andrii Nakryiko Acked-by: Jakub Sitnicki Acked-by: John Fastabend Link: https://lore.kernel.org/bpf/20220524075311.649153-1-wangyufen@huawei.com --- include/linux/bpf.h | 1 + include/linux/skmsg.h | 1 + 2 files changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 2b914a56a2c5..8e6092d0ea95 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -2104,6 +2104,7 @@ int sock_map_bpf_prog_query(const union bpf_attr *attr, union bpf_attr __user *uattr); void sock_map_unhash(struct sock *sk); +void sock_map_destroy(struct sock *sk); void sock_map_close(struct sock *sk, long timeout); #else static inline int bpf_prog_offload_init(struct bpf_prog *prog, diff --git a/include/linux/skmsg.h b/include/linux/skmsg.h index c5a2d6f50f25..153b6dec9b6a 100644 --- a/include/linux/skmsg.h +++ b/include/linux/skmsg.h @@ -95,6 +95,7 @@ struct sk_psock { spinlock_t link_lock; refcount_t refcnt; void (*saved_unhash)(struct sock *sk); + void (*saved_destroy)(struct sock *sk); void (*saved_close)(struct sock *sk, long timeout); void (*saved_write_space)(struct sock *sk); void (*saved_data_ready)(struct sock *sk); -- cgit v1.2.3 From ff8372a467fa28752610f57a6512c5365413faa2 Mon Sep 17 00:00:00 2001 From: Menglong Dong Date: Mon, 6 Jun 2022 10:24:34 +0800 Subject: net: skb: move enum skb_drop_reason to standalone header file As the skb drop reasons are getting more and more, move the enum 'skb_drop_reason' and related function to the standalone header 'dropreason.h', as Jakub Kicinski suggested. Signed-off-by: Menglong Dong Signed-off-by: Paolo Abeni --- include/linux/skbuff.h | 179 +------------------------------------------------ 1 file changed, 1 insertion(+), 178 deletions(-) (limited to 'include/linux') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index d3d10556f0fa..82edf0359ab3 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -43,6 +43,7 @@ #include #endif #include +#include /** * DOC: skb checksums @@ -337,184 +338,6 @@ struct sk_buff_head { struct sk_buff; -/* The reason of skb drop, which is used in kfree_skb_reason(). - * en...maybe they should be splited by group? - * - * Each item here should also be in 'TRACE_SKB_DROP_REASON', which is - * used to translate the reason to string. - */ -enum skb_drop_reason { - SKB_NOT_DROPPED_YET = 0, - SKB_DROP_REASON_NOT_SPECIFIED, /* drop reason is not specified */ - SKB_DROP_REASON_NO_SOCKET, /* socket not found */ - SKB_DROP_REASON_PKT_TOO_SMALL, /* packet size is too small */ - SKB_DROP_REASON_TCP_CSUM, /* TCP checksum error */ - SKB_DROP_REASON_SOCKET_FILTER, /* dropped by socket filter */ - SKB_DROP_REASON_UDP_CSUM, /* UDP checksum error */ - SKB_DROP_REASON_NETFILTER_DROP, /* dropped by netfilter */ - SKB_DROP_REASON_OTHERHOST, /* packet don't belong to current - * host (interface is in promisc - * mode) - */ - SKB_DROP_REASON_IP_CSUM, /* IP checksum error */ - SKB_DROP_REASON_IP_INHDR, /* there is something wrong with - * IP header (see - * IPSTATS_MIB_INHDRERRORS) - */ - SKB_DROP_REASON_IP_RPFILTER, /* IP rpfilter validate failed. - * see the document for rp_filter - * in ip-sysctl.rst for more - * information - */ - SKB_DROP_REASON_UNICAST_IN_L2_MULTICAST, /* destination address of L2 - * is multicast, but L3 is - * unicast. - */ - SKB_DROP_REASON_XFRM_POLICY, /* xfrm policy check failed */ - SKB_DROP_REASON_IP_NOPROTO, /* no support for IP protocol */ - SKB_DROP_REASON_SOCKET_RCVBUFF, /* socket receive buff is full */ - SKB_DROP_REASON_PROTO_MEM, /* proto memory limition, such as - * udp packet drop out of - * udp_memory_allocated. - */ - SKB_DROP_REASON_TCP_MD5NOTFOUND, /* no MD5 hash and one - * expected, corresponding - * to LINUX_MIB_TCPMD5NOTFOUND - */ - SKB_DROP_REASON_TCP_MD5UNEXPECTED, /* MD5 hash and we're not - * expecting one, corresponding - * to LINUX_MIB_TCPMD5UNEXPECTED - */ - SKB_DROP_REASON_TCP_MD5FAILURE, /* MD5 hash and its wrong, - * corresponding to - * LINUX_MIB_TCPMD5FAILURE - */ - SKB_DROP_REASON_SOCKET_BACKLOG, /* failed to add skb to socket - * backlog (see - * LINUX_MIB_TCPBACKLOGDROP) - */ - SKB_DROP_REASON_TCP_FLAGS, /* TCP flags invalid */ - SKB_DROP_REASON_TCP_ZEROWINDOW, /* TCP receive window size is zero, - * see LINUX_MIB_TCPZEROWINDOWDROP - */ - SKB_DROP_REASON_TCP_OLD_DATA, /* the TCP data reveived is already - * received before (spurious retrans - * may happened), see - * LINUX_MIB_DELAYEDACKLOST - */ - SKB_DROP_REASON_TCP_OVERWINDOW, /* the TCP data is out of window, - * the seq of the first byte exceed - * the right edges of receive - * window - */ - SKB_DROP_REASON_TCP_OFOMERGE, /* the data of skb is already in - * the ofo queue, corresponding to - * LINUX_MIB_TCPOFOMERGE - */ - SKB_DROP_REASON_TCP_RFC7323_PAWS, /* PAWS check, corresponding to - * LINUX_MIB_PAWSESTABREJECTED - */ - SKB_DROP_REASON_TCP_INVALID_SEQUENCE, /* Not acceptable SEQ field */ - SKB_DROP_REASON_TCP_RESET, /* Invalid RST packet */ - SKB_DROP_REASON_TCP_INVALID_SYN, /* Incoming packet has unexpected SYN flag */ - SKB_DROP_REASON_TCP_CLOSE, /* TCP socket in CLOSE state */ - SKB_DROP_REASON_TCP_FASTOPEN, /* dropped by FASTOPEN request socket */ - SKB_DROP_REASON_TCP_OLD_ACK, /* TCP ACK is old, but in window */ - SKB_DROP_REASON_TCP_TOO_OLD_ACK, /* TCP ACK is too old */ - SKB_DROP_REASON_TCP_ACK_UNSENT_DATA, /* TCP ACK for data we haven't sent yet */ - SKB_DROP_REASON_TCP_OFO_QUEUE_PRUNE, /* pruned from TCP OFO queue */ - SKB_DROP_REASON_TCP_OFO_DROP, /* data already in receive queue */ - SKB_DROP_REASON_IP_OUTNOROUTES, /* route lookup failed */ - SKB_DROP_REASON_BPF_CGROUP_EGRESS, /* dropped by - * BPF_PROG_TYPE_CGROUP_SKB - * eBPF program - */ - SKB_DROP_REASON_IPV6DISABLED, /* IPv6 is disabled on the device */ - SKB_DROP_REASON_NEIGH_CREATEFAIL, /* failed to create neigh - * entry - */ - SKB_DROP_REASON_NEIGH_FAILED, /* neigh entry in failed state */ - SKB_DROP_REASON_NEIGH_QUEUEFULL, /* arp_queue for neigh - * entry is full - */ - SKB_DROP_REASON_NEIGH_DEAD, /* neigh entry is dead */ - SKB_DROP_REASON_TC_EGRESS, /* dropped in TC egress HOOK */ - SKB_DROP_REASON_QDISC_DROP, /* dropped by qdisc when packet - * outputting (failed to enqueue to - * current qdisc) - */ - SKB_DROP_REASON_CPU_BACKLOG, /* failed to enqueue the skb to - * the per CPU backlog queue. This - * can be caused by backlog queue - * full (see netdev_max_backlog in - * net.rst) or RPS flow limit - */ - SKB_DROP_REASON_XDP, /* dropped by XDP in input path */ - SKB_DROP_REASON_TC_INGRESS, /* dropped in TC ingress HOOK */ - SKB_DROP_REASON_UNHANDLED_PROTO, /* protocol not implemented - * or not supported - */ - SKB_DROP_REASON_SKB_CSUM, /* sk_buff checksum computation - * error - */ - SKB_DROP_REASON_SKB_GSO_SEG, /* gso segmentation error */ - SKB_DROP_REASON_SKB_UCOPY_FAULT, /* failed to copy data from - * user space, e.g., via - * zerocopy_sg_from_iter() - * or skb_orphan_frags_rx() - */ - SKB_DROP_REASON_DEV_HDR, /* device driver specific - * header/metadata is invalid - */ - /* the device is not ready to xmit/recv due to any of its data - * structure that is not up/ready/initialized, e.g., the IFF_UP is - * not set, or driver specific tun->tfiles[txq] is not initialized - */ - SKB_DROP_REASON_DEV_READY, - SKB_DROP_REASON_FULL_RING, /* ring buffer is full */ - SKB_DROP_REASON_NOMEM, /* error due to OOM */ - SKB_DROP_REASON_HDR_TRUNC, /* failed to trunc/extract the header - * from networking data, e.g., failed - * to pull the protocol header from - * frags via pskb_may_pull() - */ - SKB_DROP_REASON_TAP_FILTER, /* dropped by (ebpf) filter directly - * attached to tun/tap, e.g., via - * TUNSETFILTEREBPF - */ - SKB_DROP_REASON_TAP_TXFILTER, /* dropped by tx filter implemented - * at tun/tap, e.g., check_filter() - */ - SKB_DROP_REASON_ICMP_CSUM, /* ICMP checksum error */ - SKB_DROP_REASON_INVALID_PROTO, /* the packet doesn't follow RFC - * 2211, such as a broadcasts - * ICMP_TIMESTAMP - */ - SKB_DROP_REASON_IP_INADDRERRORS, /* host unreachable, corresponding - * to IPSTATS_MIB_INADDRERRORS - */ - SKB_DROP_REASON_IP_INNOROUTES, /* network unreachable, corresponding - * to IPSTATS_MIB_INADDRERRORS - */ - SKB_DROP_REASON_PKT_TOO_BIG, /* packet size is too big (maybe exceed - * the MTU) - */ - SKB_DROP_REASON_MAX, -}; - -#define SKB_DR_INIT(name, reason) \ - enum skb_drop_reason name = SKB_DROP_REASON_##reason -#define SKB_DR(name) \ - SKB_DR_INIT(name, NOT_SPECIFIED) -#define SKB_DR_SET(name, reason) \ - (name = SKB_DROP_REASON_##reason) -#define SKB_DR_OR(name, reason) \ - do { \ - if (name == SKB_DROP_REASON_NOT_SPECIFIED || \ - name == SKB_NOT_DROPPED_YET) \ - SKB_DR_SET(name, reason); \ - } while (0) - /* To allow 64K frame to be packed as single skb without frag_list we * require 64K/PAGE_SIZE pages plus 1 additional page to allow for * buffers which do not start on a page boundary. -- cgit v1.2.3 From 6089fb325cf737eeb2c4d236c94697112ca860da Mon Sep 17 00:00:00 2001 From: Yonghong Song Date: Mon, 6 Jun 2022 23:26:00 -0700 Subject: bpf: Add btf enum64 support Currently, BTF only supports upto 32bit enum value with BTF_KIND_ENUM. But in kernel, some enum indeed has 64bit values, e.g., in uapi bpf.h, we have enum { BPF_F_INDEX_MASK = 0xffffffffULL, BPF_F_CURRENT_CPU = BPF_F_INDEX_MASK, BPF_F_CTXLEN_MASK = (0xfffffULL << 32), }; In this case, BTF_KIND_ENUM will encode the value of BPF_F_CTXLEN_MASK as 0, which certainly is incorrect. This patch added a new btf kind, BTF_KIND_ENUM64, which permits 64bit value to cover the above use case. The BTF_KIND_ENUM64 has the following three fields followed by the common type: struct bpf_enum64 { __u32 nume_off; __u32 val_lo32; __u32 val_hi32; }; Currently, btf type section has an alignment of 4 as all element types are u32. Representing the value with __u64 will introduce a pad for bpf_enum64 and may also introduce misalignment for the 64bit value. Hence, two members of val_hi32 and val_lo32 are chosen to avoid these issues. The kflag is also introduced for BTF_KIND_ENUM and BTF_KIND_ENUM64 to indicate whether the value is signed or unsigned. The kflag intends to provide consistent output of BTF C fortmat with the original source code. For example, the original BTF_KIND_ENUM bit value is 0xffffffff. The format C has two choices, printing out 0xffffffff or -1 and current libbpf prints out as unsigned value. But if the signedness is preserved in btf, the value can be printed the same as the original source code. The kflag value 0 means unsigned values, which is consistent to the default by libbpf and should also cover most cases as well. The new BTF_KIND_ENUM64 is intended to support the enum value represented as 64bit value. But it can represent all BTF_KIND_ENUM values as well. The compiler ([1]) and pahole will generate BTF_KIND_ENUM64 only if the value has to be represented with 64 bits. In addition, a static inline function btf_kind_core_compat() is introduced which will be used later when libbpf relo_core.c changed. Here the kernel shares the same relo_core.c with libbpf. [1] https://reviews.llvm.org/D124641 Acked-by: Andrii Nakryiko Signed-off-by: Yonghong Song Link: https://lore.kernel.org/r/20220607062600.3716578-1-yhs@fb.com Signed-off-by: Alexei Starovoitov --- include/linux/btf.h | 28 ++++++++++++++++++++++++++++ 1 file changed, 28 insertions(+) (limited to 'include/linux') diff --git a/include/linux/btf.h b/include/linux/btf.h index 2611cea2c2b6..1bfed7fa0428 100644 --- a/include/linux/btf.h +++ b/include/linux/btf.h @@ -177,6 +177,19 @@ static inline bool btf_type_is_enum(const struct btf_type *t) return BTF_INFO_KIND(t->info) == BTF_KIND_ENUM; } +static inline bool btf_is_any_enum(const struct btf_type *t) +{ + return BTF_INFO_KIND(t->info) == BTF_KIND_ENUM || + BTF_INFO_KIND(t->info) == BTF_KIND_ENUM64; +} + +static inline bool btf_kind_core_compat(const struct btf_type *t1, + const struct btf_type *t2) +{ + return BTF_INFO_KIND(t1->info) == BTF_INFO_KIND(t2->info) || + (btf_is_any_enum(t1) && btf_is_any_enum(t2)); +} + static inline bool str_is_empty(const char *s) { return !s || !s[0]; @@ -192,6 +205,16 @@ static inline bool btf_is_enum(const struct btf_type *t) return btf_kind(t) == BTF_KIND_ENUM; } +static inline bool btf_is_enum64(const struct btf_type *t) +{ + return btf_kind(t) == BTF_KIND_ENUM64; +} + +static inline u64 btf_enum64_value(const struct btf_enum64 *e) +{ + return ((u64)e->val_hi32 << 32) | e->val_lo32; +} + static inline bool btf_is_composite(const struct btf_type *t) { u16 kind = btf_kind(t); @@ -332,6 +355,11 @@ static inline struct btf_enum *btf_enum(const struct btf_type *t) return (struct btf_enum *)(t + 1); } +static inline struct btf_enum64 *btf_enum64(const struct btf_type *t) +{ + return (struct btf_enum64 *)(t + 1); +} + static inline const struct btf_var_secinfo *btf_type_var_secinfo( const struct btf_type *t) { -- cgit v1.2.3 From d62607c3fe45911b2331fac073355a8c914bbde2 Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Tue, 7 Jun 2022 21:39:55 -0700 Subject: net: rename reference+tracking helpers Netdev reference helpers have a dev_ prefix for historic reasons. Renaming the old helpers would be too much churn but we can rename the tracking ones which are relatively recent and should be the default for new code. Rename: dev_hold_track() -> netdev_hold() dev_put_track() -> netdev_put() dev_replace_track() -> netdev_ref_replace() Link: https://lore.kernel.org/r/20220608043955.919359-1-kuba@kernel.org Signed-off-by: Jakub Kicinski --- include/linux/netdevice.h | 24 ++++++++++++------------ 1 file changed, 12 insertions(+), 12 deletions(-) (limited to 'include/linux') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index f615a66c89e9..e2e5088888b1 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -3981,8 +3981,8 @@ static inline void netdev_tracker_free(struct net_device *dev, #endif } -static inline void dev_hold_track(struct net_device *dev, - netdevice_tracker *tracker, gfp_t gfp) +static inline void netdev_hold(struct net_device *dev, + netdevice_tracker *tracker, gfp_t gfp) { if (dev) { __dev_hold(dev); @@ -3990,8 +3990,8 @@ static inline void dev_hold_track(struct net_device *dev, } } -static inline void dev_put_track(struct net_device *dev, - netdevice_tracker *tracker) +static inline void netdev_put(struct net_device *dev, + netdevice_tracker *tracker) { if (dev) { netdev_tracker_free(dev, tracker); @@ -4004,11 +4004,11 @@ static inline void dev_put_track(struct net_device *dev, * @dev: network device * * Hold reference to device to keep it from being freed. - * Try using dev_hold_track() instead. + * Try using netdev_hold() instead. */ static inline void dev_hold(struct net_device *dev) { - dev_hold_track(dev, NULL, GFP_ATOMIC); + netdev_hold(dev, NULL, GFP_ATOMIC); } /** @@ -4016,17 +4016,17 @@ static inline void dev_hold(struct net_device *dev) * @dev: network device * * Release reference to device to allow it to be freed. - * Try using dev_put_track() instead. + * Try using netdev_put() instead. */ static inline void dev_put(struct net_device *dev) { - dev_put_track(dev, NULL); + netdev_put(dev, NULL); } -static inline void dev_replace_track(struct net_device *odev, - struct net_device *ndev, - netdevice_tracker *tracker, - gfp_t gfp) +static inline void netdev_ref_replace(struct net_device *odev, + struct net_device *ndev, + netdevice_tracker *tracker, + gfp_t gfp) { if (odev) netdev_tracker_free(odev, tracker); -- cgit v1.2.3 From 09cca53c1656960c38c04bb12da30f61952ca660 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Wed, 8 Jun 2022 08:46:32 -0700 Subject: vlan: adopt u64_stats_t As explained in commit 316580b69d0a ("u64_stats: provide u64_stats_t type") we should use u64_stats_t and related accessors to avoid load/store tearing. Add READ_ONCE() when reading rx_errors & tx_dropped. Signed-off-by: Eric Dumazet Signed-off-by: Jakub Kicinski --- include/linux/if_macvlan.h | 6 +++--- include/linux/if_vlan.h | 10 +++++----- 2 files changed, 8 insertions(+), 8 deletions(-) (limited to 'include/linux') diff --git a/include/linux/if_macvlan.h b/include/linux/if_macvlan.h index b42294739063..523025106a64 100644 --- a/include/linux/if_macvlan.h +++ b/include/linux/if_macvlan.h @@ -46,10 +46,10 @@ static inline void macvlan_count_rx(const struct macvlan_dev *vlan, pcpu_stats = get_cpu_ptr(vlan->pcpu_stats); u64_stats_update_begin(&pcpu_stats->syncp); - pcpu_stats->rx_packets++; - pcpu_stats->rx_bytes += len; + u64_stats_inc(&pcpu_stats->rx_packets); + u64_stats_add(&pcpu_stats->rx_bytes, len); if (multicast) - pcpu_stats->rx_multicast++; + u64_stats_inc(&pcpu_stats->rx_multicast); u64_stats_update_end(&pcpu_stats->syncp); put_cpu_ptr(vlan->pcpu_stats); } else { diff --git a/include/linux/if_vlan.h b/include/linux/if_vlan.h index 2be4dd7e90a9..e00c4ee81ff7 100644 --- a/include/linux/if_vlan.h +++ b/include/linux/if_vlan.h @@ -118,11 +118,11 @@ static inline void vlan_drop_rx_stag_filter_info(struct net_device *dev) * @tx_dropped: number of tx drops */ struct vlan_pcpu_stats { - u64 rx_packets; - u64 rx_bytes; - u64 rx_multicast; - u64 tx_packets; - u64 tx_bytes; + u64_stats_t rx_packets; + u64_stats_t rx_bytes; + u64_stats_t rx_multicast; + u64_stats_t tx_packets; + u64_stats_t tx_bytes; struct u64_stats_sync syncp; u32 rx_errors; u32 tx_dropped; -- cgit v1.2.3 From 9962acefbcb92736c268aafe5f52200948f60f3e Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Wed, 8 Jun 2022 08:46:37 -0700 Subject: net: adopt u64_stats_t in struct pcpu_sw_netstats As explained in commit 316580b69d0a ("u64_stats: provide u64_stats_t type") we should use u64_stats_t and related accessors to avoid load/store tearing. Signed-off-by: Eric Dumazet Signed-off-by: Jakub Kicinski --- include/linux/netdevice.h | 16 ++++++++-------- 1 file changed, 8 insertions(+), 8 deletions(-) (limited to 'include/linux') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index e2e5088888b1..89afa4f7747d 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -2636,10 +2636,10 @@ struct packet_offload { /* often modified stats are per-CPU, other are shared (netdev->stats) */ struct pcpu_sw_netstats { - u64 rx_packets; - u64 rx_bytes; - u64 tx_packets; - u64 tx_bytes; + u64_stats_t rx_packets; + u64_stats_t rx_bytes; + u64_stats_t tx_packets; + u64_stats_t tx_bytes; struct u64_stats_sync syncp; } __aligned(4 * sizeof(u64)); @@ -2656,8 +2656,8 @@ static inline void dev_sw_netstats_rx_add(struct net_device *dev, unsigned int l struct pcpu_sw_netstats *tstats = this_cpu_ptr(dev->tstats); u64_stats_update_begin(&tstats->syncp); - tstats->rx_bytes += len; - tstats->rx_packets++; + u64_stats_add(&tstats->rx_bytes, len); + u64_stats_inc(&tstats->rx_packets); u64_stats_update_end(&tstats->syncp); } @@ -2668,8 +2668,8 @@ static inline void dev_sw_netstats_tx_add(struct net_device *dev, struct pcpu_sw_netstats *tstats = this_cpu_ptr(dev->tstats); u64_stats_update_begin(&tstats->syncp); - tstats->tx_bytes += len; - tstats->tx_packets += packets; + u64_stats_add(&tstats->tx_bytes, len); + u64_stats_add(&tstats->tx_packets, packets); u64_stats_update_end(&tstats->syncp); } -- cgit v1.2.3 From 9ec321aba2eaca109139a2a67c65ede7f07bd8ec Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Wed, 8 Jun 2022 08:46:40 -0700 Subject: team: adopt u64_stats_t As explained in commit 316580b69d0a ("u64_stats: provide u64_stats_t type") we should use u64_stats_t and related accessors to avoid load/store tearing. Signed-off-by: Eric Dumazet Signed-off-by: Jakub Kicinski --- include/linux/if_team.h | 10 +++++----- 1 file changed, 5 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/if_team.h b/include/linux/if_team.h index add607943c95..fc985e5c739d 100644 --- a/include/linux/if_team.h +++ b/include/linux/if_team.h @@ -12,11 +12,11 @@ #include struct team_pcpu_stats { - u64 rx_packets; - u64 rx_bytes; - u64 rx_multicast; - u64 tx_packets; - u64 tx_bytes; + u64_stats_t rx_packets; + u64_stats_t rx_bytes; + u64_stats_t rx_multicast; + u64_stats_t tx_packets; + u64_stats_t tx_bytes; struct u64_stats_sync syncp; u32 rx_dropped; u32 tx_dropped; -- cgit v1.2.3 From 21ab562c1f65e583b5d89081acaf096805522482 Mon Sep 17 00:00:00 2001 From: Po Hao Huang Date: Wed, 8 Jun 2022 19:32:22 +0800 Subject: ieee80211: add trigger frame definition Define trigger stype of control frame, and its checking function, struct and trigger type within common_info of trigger. Signed-off-by: Po Hao Huang Signed-off-by: Ping-Ke Shih Signed-off-by: Kalle Valo Link: https://lore.kernel.org/r/20220608113224.11193-2-pkshih@realtek.com --- include/linux/ieee80211.h | 31 +++++++++++++++++++++++++++++++ 1 file changed, 31 insertions(+) (limited to 'include/linux') diff --git a/include/linux/ieee80211.h b/include/linux/ieee80211.h index 75d40acb60c1..5c65ae6b8154 100644 --- a/include/linux/ieee80211.h +++ b/include/linux/ieee80211.h @@ -76,6 +76,7 @@ #define IEEE80211_STYPE_ACTION 0x00D0 /* control */ +#define IEEE80211_STYPE_TRIGGER 0x0020 #define IEEE80211_STYPE_CTL_EXT 0x0060 #define IEEE80211_STYPE_BACK_REQ 0x0080 #define IEEE80211_STYPE_BACK 0x0090 @@ -295,6 +296,17 @@ static inline u16 ieee80211_sn_sub(u16 sn1, u16 sn2) #define IEEE80211_HT_CTL_LEN 4 +/* trigger type within common_info of trigger frame */ +#define IEEE80211_TRIGGER_TYPE_MASK 0xf +#define IEEE80211_TRIGGER_TYPE_BASIC 0x0 +#define IEEE80211_TRIGGER_TYPE_BFRP 0x1 +#define IEEE80211_TRIGGER_TYPE_MU_BAR 0x2 +#define IEEE80211_TRIGGER_TYPE_MU_RTS 0x3 +#define IEEE80211_TRIGGER_TYPE_BSRP 0x4 +#define IEEE80211_TRIGGER_TYPE_GCR_MU_BAR 0x5 +#define IEEE80211_TRIGGER_TYPE_BQRP 0x6 +#define IEEE80211_TRIGGER_TYPE_NFRP 0x7 + struct ieee80211_hdr { __le16 frame_control; __le16 duration_id; @@ -324,6 +336,15 @@ struct ieee80211_qos_hdr { __le16 qos_ctrl; } __packed __aligned(2); +struct ieee80211_trigger { + __le16 frame_control; + __le16 duration; + u8 ra[ETH_ALEN]; + u8 ta[ETH_ALEN]; + __le64 common_info; + u8 variable[]; +} __packed __aligned(2); + /** * ieee80211_has_tods - check if IEEE80211_FCTL_TODS is set * @fc: frame control bytes in little-endian byteorder @@ -729,6 +750,16 @@ static inline bool ieee80211_is_qos_nullfunc(__le16 fc) cpu_to_le16(IEEE80211_FTYPE_DATA | IEEE80211_STYPE_QOS_NULLFUNC); } +/** + * ieee80211_is_trigger - check if frame is trigger frame + * @fc: frame control field in little-endian byteorder + */ +static inline bool ieee80211_is_trigger(__le16 fc) +{ + return (fc & cpu_to_le16(IEEE80211_FCTL_FTYPE | IEEE80211_FCTL_STYPE)) == + cpu_to_le16(IEEE80211_FTYPE_CTL | IEEE80211_STYPE_TRIGGER); +} + /** * ieee80211_is_any_nullfunc - check if frame is regular or QoS nullfunc frame * @fc: frame control bytes in little-endian byteorder -- cgit v1.2.3 From ccd8a9351f7b44bc1c0c8e4d39c0d6593b106fc4 Mon Sep 17 00:00:00 2001 From: Vincent Mailhol Date: Fri, 10 Jun 2022 23:30:08 +0900 Subject: can: skb: move can_dropped_invalid_skb() and can_skb_headroom_valid() to skb.c The functions can_dropped_invalid_skb() and can_skb_headroom_valid() grew a lot over the years to a point which it does not make much sense to have them defined as static inline in header files. Move those two functions to the .c counterpart of skb.h. can_skb_headroom_valid()'s only caller being can_dropped_invalid_skb(), the declaration is removed from the header. Only can_dropped_invalid_skb() gets its symbol exported. While doing so, do a small cleanup: add brackets around the else block in can_dropped_invalid_skb(). Link: https://lore.kernel.org/all/20220610143009.323579-7-mailhol.vincent@wanadoo.fr Signed-off-by: Vincent Mailhol Reported-by: kernel test robot Acked-by: Max Staudt Tested-by: Oliver Hartkopp Signed-off-by: Marc Kleine-Budde --- include/linux/can/skb.h | 59 +------------------------------------------------ 1 file changed, 1 insertion(+), 58 deletions(-) (limited to 'include/linux') diff --git a/include/linux/can/skb.h b/include/linux/can/skb.h index fdb22b00674a..182749e858b3 100644 --- a/include/linux/can/skb.h +++ b/include/linux/can/skb.h @@ -31,6 +31,7 @@ struct sk_buff *alloc_canfd_skb(struct net_device *dev, struct canfd_frame **cfd); struct sk_buff *alloc_can_err_skb(struct net_device *dev, struct can_frame **cf); +bool can_dropped_invalid_skb(struct net_device *dev, struct sk_buff *skb); /* * The struct can_skb_priv is used to transport additional information along @@ -96,64 +97,6 @@ static inline struct sk_buff *can_create_echo_skb(struct sk_buff *skb) return nskb; } -/* Check for outgoing skbs that have not been created by the CAN subsystem */ -static inline bool can_skb_headroom_valid(struct net_device *dev, - struct sk_buff *skb) -{ - /* af_packet creates a headroom of HH_DATA_MOD bytes which is fine */ - if (WARN_ON_ONCE(skb_headroom(skb) < sizeof(struct can_skb_priv))) - return false; - - /* af_packet does not apply CAN skb specific settings */ - if (skb->ip_summed == CHECKSUM_NONE) { - /* init headroom */ - can_skb_prv(skb)->ifindex = dev->ifindex; - can_skb_prv(skb)->skbcnt = 0; - - skb->ip_summed = CHECKSUM_UNNECESSARY; - - /* perform proper loopback on capable devices */ - if (dev->flags & IFF_ECHO) - skb->pkt_type = PACKET_LOOPBACK; - else - skb->pkt_type = PACKET_HOST; - - skb_reset_mac_header(skb); - skb_reset_network_header(skb); - skb_reset_transport_header(skb); - } - - return true; -} - -/* Drop a given socketbuffer if it does not contain a valid CAN frame. */ -static inline bool can_dropped_invalid_skb(struct net_device *dev, - struct sk_buff *skb) -{ - const struct canfd_frame *cfd = (struct canfd_frame *)skb->data; - - if (skb->protocol == htons(ETH_P_CAN)) { - if (unlikely(skb->len != CAN_MTU || - cfd->len > CAN_MAX_DLEN)) - goto inval_skb; - } else if (skb->protocol == htons(ETH_P_CANFD)) { - if (unlikely(skb->len != CANFD_MTU || - cfd->len > CANFD_MAX_DLEN)) - goto inval_skb; - } else - goto inval_skb; - - if (!can_skb_headroom_valid(dev, skb)) - goto inval_skb; - - return false; - -inval_skb: - kfree_skb(skb); - dev->stats.tx_dropped++; - return true; -} - static inline bool can_is_canfd_skb(const struct sk_buff *skb) { /* the CAN specific type of skb is identified by its data length */ -- cgit v1.2.3 From c04245328dd7e915e21ac6395ffd218616e22754 Mon Sep 17 00:00:00 2001 From: Yajun Deng Date: Fri, 10 Jun 2022 17:10:17 +0800 Subject: net: make __sys_accept4_file() static __sys_accept4_file() isn't used outside of the file, make it static. As the same time, move file_flags and nofile parameters into __sys_accept4_file(). Signed-off-by: Yajun Deng Signed-off-by: David S. Miller --- include/linux/socket.h | 4 ---- 1 file changed, 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/socket.h b/include/linux/socket.h index 17311ad9f9af..414b8c7bb8f7 100644 --- a/include/linux/socket.h +++ b/include/linux/socket.h @@ -428,10 +428,6 @@ extern int __sys_recvfrom(int fd, void __user *ubuf, size_t size, extern int __sys_sendto(int fd, void __user *buff, size_t len, unsigned int flags, struct sockaddr __user *addr, int addr_len); -extern int __sys_accept4_file(struct file *file, unsigned file_flags, - struct sockaddr __user *upeer_sockaddr, - int __user *upeer_addrlen, int flags, - unsigned long nofile); extern struct file *do_accept(struct file *file, unsigned file_flags, struct sockaddr __user *upeer_sockaddr, int __user *upeer_addrlen, int flags); -- cgit v1.2.3 From 795e10b450a88b2943a241a5eaa6e86ae4f47694 Mon Sep 17 00:00:00 2001 From: Yevgeny Kliteynik Date: Tue, 7 Jun 2022 15:47:43 +0300 Subject: net/mlx5: Introduce header-modify-pattern ICM properties Added new fields for device memory capabilities, in order to support creation of ICM memory for modify header patterns. Signed-off-by: Erez Shitrit Signed-off-by: Yevgeny Kliteynik Signed-off-by: Leon Romanovsky Acked-by: Saeed Mahameed Signed-off-by: Saeed Mahameed --- include/linux/mlx5/mlx5_ifc.h | 7 +++++-- 1 file changed, 5 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h index fd7d083a34d3..789d64400744 100644 --- a/include/linux/mlx5/mlx5_ifc.h +++ b/include/linux/mlx5/mlx5_ifc.h @@ -1086,11 +1086,14 @@ struct mlx5_ifc_device_mem_cap_bits { u8 log_sw_icm_alloc_granularity[0x6]; u8 log_steering_sw_icm_size[0x8]; - u8 reserved_at_120[0x20]; + u8 reserved_at_120[0x18]; + u8 log_header_modify_pattern_sw_icm_size[0x8]; u8 header_modify_sw_icm_start_address[0x40]; - u8 reserved_at_180[0x80]; + u8 reserved_at_180[0x40]; + + u8 header_modify_pattern_sw_icm_start_address[0x40]; u8 memic_operations[0x20]; -- cgit v1.2.3 From 667658364b2056f344a2769280b939a5e45610be Mon Sep 17 00:00:00 2001 From: Yevgeny Kliteynik Date: Tue, 7 Jun 2022 15:47:44 +0300 Subject: net/mlx5: Manage ICM of type modify-header pattern Added support for managing new type of ICM for devices that support sw_owner_v2. Signed-off-by: Erez Shitrit Signed-off-by: Yevgeny Kliteynik Signed-off-by: Leon Romanovsky Acked-by: Saeed Mahameed Signed-off-by: Saeed Mahameed --- include/linux/mlx5/driver.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h index 5040cd774c5a..76d7661e3e63 100644 --- a/include/linux/mlx5/driver.h +++ b/include/linux/mlx5/driver.h @@ -676,6 +676,7 @@ struct mlx5e_resources { enum mlx5_sw_icm_type { MLX5_SW_ICM_TYPE_STEERING, MLX5_SW_ICM_TYPE_HEADER_MODIFY, + MLX5_SW_ICM_TYPE_HEADER_MODIFY_PATTERN, }; #define MLX5_MAX_RESERVED_GIDS 8 -- cgit v1.2.3 From f5d23ee137e51b4e5cd5d263b144d5e6719f6e52 Mon Sep 17 00:00:00 2001 From: Jianbo Liu Date: Wed, 8 Jun 2022 13:04:47 -0700 Subject: net/mlx5: Add IFC bits and enums for flow meter Add/extend structure layouts and defines for flow meter. Signed-off-by: Jianbo Liu Reviewed-by: Ariel Levkovich Signed-off-by: Saeed Mahameed --- include/linux/mlx5/device.h | 1 + include/linux/mlx5/mlx5_ifc.h | 114 ++++++++++++++++++++++++++++++++++++++++-- 2 files changed, 111 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mlx5/device.h b/include/linux/mlx5/device.h index 604b85dd770a..15ac02eeed4f 100644 --- a/include/linux/mlx5/device.h +++ b/include/linux/mlx5/device.h @@ -455,6 +455,7 @@ enum { MLX5_OPCODE_UMR = 0x25, + MLX5_OPCODE_ACCESS_ASO = 0x2d, }; enum { diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h index 789d64400744..91872afb2bfe 100644 --- a/include/linux/mlx5/mlx5_ifc.h +++ b/include/linux/mlx5/mlx5_ifc.h @@ -442,7 +442,9 @@ struct mlx5_ifc_flow_table_prop_layout_bits { u8 max_modify_header_actions[0x8]; u8 max_ft_level[0x8]; - u8 reserved_at_40[0x20]; + u8 reserved_at_40[0x6]; + u8 execute_aso[0x1]; + u8 reserved_at_47[0x19]; u8 reserved_at_60[0x2]; u8 reformat_insert[0x1]; @@ -940,7 +942,17 @@ struct mlx5_ifc_qos_cap_bits { u8 max_tsar_bw_share[0x20]; - u8 reserved_at_100[0x700]; + u8 reserved_at_100[0x20]; + + u8 reserved_at_120[0x3]; + u8 log_meter_aso_granularity[0x5]; + u8 reserved_at_128[0x3]; + u8 log_meter_aso_max_alloc[0x5]; + u8 reserved_at_130[0x3]; + u8 log_max_num_meter_aso[0x5]; + u8 reserved_at_138[0x8]; + + u8 reserved_at_140[0x6c0]; }; struct mlx5_ifc_debug_cap_bits { @@ -3280,6 +3292,7 @@ enum { MLX5_FLOW_CONTEXT_ACTION_VLAN_PUSH_2 = 0x800, MLX5_FLOW_CONTEXT_ACTION_IPSEC_DECRYPT = 0x1000, MLX5_FLOW_CONTEXT_ACTION_IPSEC_ENCRYPT = 0x2000, + MLX5_FLOW_CONTEXT_ACTION_EXECUTE_ASO = 0x4000, }; enum { @@ -3295,6 +3308,38 @@ struct mlx5_ifc_vlan_bits { u8 vid[0xc]; }; +enum { + MLX5_FLOW_METER_COLOR_RED = 0x0, + MLX5_FLOW_METER_COLOR_YELLOW = 0x1, + MLX5_FLOW_METER_COLOR_GREEN = 0x2, + MLX5_FLOW_METER_COLOR_UNDEFINED = 0x3, +}; + +enum { + MLX5_EXE_ASO_FLOW_METER = 0x2, +}; + +struct mlx5_ifc_exe_aso_ctrl_flow_meter_bits { + u8 return_reg_id[0x4]; + u8 aso_type[0x4]; + u8 reserved_at_8[0x14]; + u8 action[0x1]; + u8 init_color[0x2]; + u8 meter_id[0x1]; +}; + +union mlx5_ifc_exe_aso_ctrl { + struct mlx5_ifc_exe_aso_ctrl_flow_meter_bits exe_aso_ctrl_flow_meter; +}; + +struct mlx5_ifc_execute_aso_bits { + u8 valid[0x1]; + u8 reserved_at_1[0x7]; + u8 aso_object_id[0x18]; + + union mlx5_ifc_exe_aso_ctrl exe_aso_ctrl; +}; + struct mlx5_ifc_flow_context_bits { struct mlx5_ifc_vlan_bits push_vlan; @@ -3326,7 +3371,9 @@ struct mlx5_ifc_flow_context_bits { struct mlx5_ifc_fte_match_param_bits match_value; - u8 reserved_at_1200[0x600]; + struct mlx5_ifc_execute_aso_bits execute_aso[4]; + + u8 reserved_at_1300[0x500]; union mlx5_ifc_dest_format_struct_flow_counter_list_auto_bits destination[]; }; @@ -5973,7 +6020,9 @@ struct mlx5_ifc_general_obj_in_cmd_hdr_bits { u8 obj_id[0x20]; - u8 reserved_at_60[0x20]; + u8 reserved_at_60[0x3]; + u8 log_obj_range[0x5]; + u8 reserved_at_68[0x18]; }; struct mlx5_ifc_general_obj_out_cmd_hdr_bits { @@ -11373,12 +11422,14 @@ enum { MLX5_HCA_CAP_GENERAL_OBJECT_TYPES_ENCRYPTION_KEY = BIT_ULL(0xc), MLX5_HCA_CAP_GENERAL_OBJECT_TYPES_IPSEC = BIT_ULL(0x13), MLX5_HCA_CAP_GENERAL_OBJECT_TYPES_SAMPLER = BIT_ULL(0x20), + MLX5_HCA_CAP_GENERAL_OBJECT_TYPES_FLOW_METER_ASO = BIT_ULL(0x24), }; enum { MLX5_GENERAL_OBJECT_TYPES_ENCRYPTION_KEY = 0xc, MLX5_GENERAL_OBJECT_TYPES_IPSEC = 0x13, MLX5_GENERAL_OBJECT_TYPES_SAMPLER = 0x20, + MLX5_GENERAL_OBJECT_TYPES_FLOW_METER_ASO = 0x24, }; enum { @@ -11451,6 +11502,61 @@ struct mlx5_ifc_create_encryption_key_in_bits { struct mlx5_ifc_encryption_key_obj_bits encryption_key_object; }; +enum { + MLX5_FLOW_METER_MODE_BYTES_IP_LENGTH = 0x0, + MLX5_FLOW_METER_MODE_BYTES_CALC_WITH_L2 = 0x1, + MLX5_FLOW_METER_MODE_BYTES_CALC_WITH_L2_IPG = 0x2, + MLX5_FLOW_METER_MODE_NUM_PACKETS = 0x3, +}; + +struct mlx5_ifc_flow_meter_parameters_bits { + u8 valid[0x1]; + u8 bucket_overflow[0x1]; + u8 start_color[0x2]; + u8 both_buckets_on_green[0x1]; + u8 reserved_at_5[0x1]; + u8 meter_mode[0x2]; + u8 reserved_at_8[0x18]; + + u8 reserved_at_20[0x20]; + + u8 reserved_at_40[0x3]; + u8 cbs_exponent[0x5]; + u8 cbs_mantissa[0x8]; + u8 reserved_at_50[0x3]; + u8 cir_exponent[0x5]; + u8 cir_mantissa[0x8]; + + u8 reserved_at_60[0x20]; + + u8 reserved_at_80[0x3]; + u8 ebs_exponent[0x5]; + u8 ebs_mantissa[0x8]; + u8 reserved_at_90[0x3]; + u8 eir_exponent[0x5]; + u8 eir_mantissa[0x8]; + + u8 reserved_at_a0[0x60]; +}; + +struct mlx5_ifc_flow_meter_aso_obj_bits { + u8 modify_field_select[0x40]; + + u8 reserved_at_40[0x40]; + + u8 reserved_at_80[0x8]; + u8 meter_aso_access_pd[0x18]; + + u8 reserved_at_a0[0x160]; + + struct mlx5_ifc_flow_meter_parameters_bits flow_meter_parameters[2]; +}; + +struct mlx5_ifc_create_flow_meter_aso_obj_in_bits { + struct mlx5_ifc_general_obj_in_cmd_hdr_bits hdr; + struct mlx5_ifc_flow_meter_aso_obj_bits flow_meter_aso_obj; +}; + struct mlx5_ifc_sampler_obj_bits { u8 modify_field_select[0x40]; -- cgit v1.2.3 From 3e94e61bd44d90070dcda53b647fdc826097ef26 Mon Sep 17 00:00:00 2001 From: Saeed Mahameed Date: Wed, 8 Jun 2022 13:04:48 -0700 Subject: net/mlx5: Add HW definitions of vport debug counters total_q_under_processor_handle - number of queues in error state due to an async error or errored command. send_queue_priority_update_flow - number of QP/SQ priority/SL update events. cq_overrun - number of times CQ entered an error state due to an overflow. async_eq_overrun -number of time an EQ mapped to async events was overrun. comp_eq_overrun - number of time an EQ mapped to completion events was overrun. quota_exceeded_command - number of commands issued and failed due to quota exceeded. invalid_command - number of commands issued and failed dues to any reason other than quota exceeded. Signed-off-by: Saeed Mahameed Signed-off-by: Michael Guralnik Signed-off-by: Saeed Mahameed --- include/linux/mlx5/mlx5_ifc.h | 23 +++++++++++++++++++---- 1 file changed, 19 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h index 91872afb2bfe..f678ad88a7d5 100644 --- a/include/linux/mlx5/mlx5_ifc.h +++ b/include/linux/mlx5/mlx5_ifc.h @@ -1441,7 +1441,8 @@ struct mlx5_ifc_cmd_hca_cap_bits { u8 reserved_at_120[0xa]; u8 log_max_ra_req_dc[0x6]; - u8 reserved_at_130[0xa]; + u8 reserved_at_130[0x9]; + u8 vnic_env_cq_overrun[0x1]; u8 log_max_ra_res_dc[0x6]; u8 reserved_at_140[0x5]; @@ -1636,7 +1637,11 @@ struct mlx5_ifc_cmd_hca_cap_bits { u8 nic_receive_steering_discard[0x1]; u8 receive_discard_vport_down[0x1]; u8 transmit_discard_vport_down[0x1]; - u8 reserved_at_343[0x5]; + u8 eq_overrun_count[0x1]; + u8 reserved_at_344[0x1]; + u8 invalid_command_count[0x1]; + u8 quota_exceeded_count[0x1]; + u8 reserved_at_347[0x1]; u8 log_max_flow_counter_bulk[0x8]; u8 max_flow_counter_15_0[0x10]; @@ -3441,11 +3446,21 @@ struct mlx5_ifc_vnic_diagnostic_statistics_bits { u8 transmit_discard_vport_down[0x40]; - u8 reserved_at_140[0xa0]; + u8 async_eq_overrun[0x20]; + + u8 comp_eq_overrun[0x20]; + + u8 reserved_at_180[0x20]; + + u8 invalid_command[0x20]; + + u8 quota_exceeded_command[0x20]; u8 internal_rq_out_of_buffer[0x20]; - u8 reserved_at_200[0xe00]; + u8 cq_overrun[0x20]; + + u8 reserved_at_220[0xde0]; }; struct mlx5_ifc_traffic_counter_bits { -- cgit v1.2.3 From 91707779a481aab9c7f1d7a5ea3033ce87dc4fd6 Mon Sep 17 00:00:00 2001 From: Jianbo Liu Date: Wed, 8 Jun 2022 13:04:49 -0700 Subject: net/mlx5: Add support EXECUTE_ASO action for flow entry Attach flow meter to FTE with object id and index. Use metadata register C5 to store the packet color meter result. Signed-off-by: Jianbo Liu Reviewed-by: Roi Dayan Signed-off-by: Saeed Mahameed --- include/linux/mlx5/fs.h | 14 ++++++++++++++ 1 file changed, 14 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mlx5/fs.h b/include/linux/mlx5/fs.h index 8135713b0d2d..ece3e35622d7 100644 --- a/include/linux/mlx5/fs.h +++ b/include/linux/mlx5/fs.h @@ -212,6 +212,19 @@ struct mlx5_flow_group * mlx5_create_flow_group(struct mlx5_flow_table *ft, u32 *in); void mlx5_destroy_flow_group(struct mlx5_flow_group *fg); +struct mlx5_exe_aso { + u32 object_id; + u8 type; + u8 return_reg_id; + union { + u32 ctrl_data; + struct { + u8 meter_idx; + u8 init_color; + } flow_meter; + }; +}; + struct mlx5_fs_vlan { u16 ethtype; u16 vid; @@ -237,6 +250,7 @@ struct mlx5_flow_act { struct mlx5_fs_vlan vlan[MLX5_FS_VLAN_DEPTH]; struct ib_counters *counters; struct mlx5_flow_group *fg; + struct mlx5_exe_aso exe_aso; }; #define MLX5_DECLARE_FLOW_ACT(name) \ -- cgit v1.2.3 From d107ba1f7c067b08eb4b8ca7c51187fb7c4d97f2 Mon Sep 17 00:00:00 2001 From: Shay Drory Date: Wed, 8 Jun 2022 13:04:51 -0700 Subject: net/mlx5: Remove not used MLX5_CAP_BITS_RW_MASK Remove not used MLX5_CAP_BITS_RW_MASK. While at it, remove CAP_MASK, MLX5_CAP_OFF_CMDIF_CSUM and MLX5_DEV_CAP_FLAG_*, since MLX5_CAP_BITS_RW_MASK was their only user. Signed-off-by: Shay Drory Signed-off-by: Saeed Mahameed --- include/linux/mlx5/device.h | 19 ------------------- 1 file changed, 19 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mlx5/device.h b/include/linux/mlx5/device.h index 15ac02eeed4f..95a4fa0fd40a 100644 --- a/include/linux/mlx5/device.h +++ b/include/linux/mlx5/device.h @@ -386,21 +386,6 @@ enum { MLX5_PORT_CHANGE_SUBTYPE_CLIENT_REREG = 9, }; -enum { - MLX5_DEV_CAP_FLAG_XRC = 1LL << 3, - MLX5_DEV_CAP_FLAG_BAD_PKEY_CNTR = 1LL << 8, - MLX5_DEV_CAP_FLAG_BAD_QKEY_CNTR = 1LL << 9, - MLX5_DEV_CAP_FLAG_APM = 1LL << 17, - MLX5_DEV_CAP_FLAG_ATOMIC = 1LL << 18, - MLX5_DEV_CAP_FLAG_BLOCK_MCAST = 1LL << 23, - MLX5_DEV_CAP_FLAG_ON_DMND_PG = 1LL << 24, - MLX5_DEV_CAP_FLAG_CQ_MODER = 1LL << 29, - MLX5_DEV_CAP_FLAG_RESIZE_CQ = 1LL << 30, - MLX5_DEV_CAP_FLAG_DCT = 1LL << 37, - MLX5_DEV_CAP_FLAG_SIG_HAND_OVER = 1LL << 40, - MLX5_DEV_CAP_FLAG_CMDIF_CSUM = 3LL << 46, -}; - enum { MLX5_ROCE_VERSION_1 = 0, MLX5_ROCE_VERSION_2 = 2, @@ -496,10 +481,6 @@ enum { MLX5_MAX_PAGE_SHIFT = 31 }; -enum { - MLX5_CAP_OFF_CMDIF_CSUM = 46, -}; - enum { /* * Max wqe size for rdma read is 512 bytes, so this -- cgit v1.2.3 From cdcdce948d64139aea1c6dfea4b04f5c8ad2784e Mon Sep 17 00:00:00 2001 From: Ofer Levi Date: Wed, 8 Jun 2022 13:04:52 -0700 Subject: net/mlx5: Add bits and fields to support enhanced CQE compression Expose ifc bits and add needed structure fields and methods to support enhanced CQE compression feature. The enhanced CQE compression feature improves cpu utiliziation with better packet latency from nic to host. Signed-off-by: Ofer Levi Signed-off-by: Saeed Mahameed --- include/linux/mlx5/device.h | 16 +++++++++++++++- include/linux/mlx5/mlx5_ifc.h | 7 +++++-- 2 files changed, 20 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mlx5/device.h b/include/linux/mlx5/device.h index 95a4fa0fd40a..b5f58fd37a0f 100644 --- a/include/linux/mlx5/device.h +++ b/include/linux/mlx5/device.h @@ -822,7 +822,10 @@ struct mlx5_cqe64 { __be32 timestamp_l; __be32 sop_drop_qpn; __be16 wqe_counter; - u8 signature; + union { + u8 signature; + u8 validity_iteration_count; + }; u8 op_own; }; @@ -854,6 +857,11 @@ enum { MLX5_CQE_FORMAT_CSUM_STRIDX = 0x3, }; +enum { + MLX5_CQE_COMPRESS_LAYOUT_BASIC = 0, + MLX5_CQE_COMPRESS_LAYOUT_ENHANCED = 1, +}; + #define MLX5_MINI_CQE_ARRAY_SIZE 8 static inline u8 mlx5_get_cqe_format(struct mlx5_cqe64 *cqe) @@ -866,6 +874,12 @@ static inline u8 get_cqe_opcode(struct mlx5_cqe64 *cqe) return cqe->op_own >> 4; } +static inline u8 get_cqe_enhanced_num_mini_cqes(struct mlx5_cqe64 *cqe) +{ + /* num_of_mini_cqes is zero based */ + return get_cqe_opcode(cqe) + 1; +} + static inline u8 get_cqe_lro_tcppsh(struct mlx5_cqe64 *cqe) { return (cqe->lro.tcppsh_abort_dupack >> 6) & 1; diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h index f678ad88a7d5..8e87eb47f9dc 100644 --- a/include/linux/mlx5/mlx5_ifc.h +++ b/include/linux/mlx5/mlx5_ifc.h @@ -1739,7 +1739,9 @@ struct mlx5_ifc_cmd_hca_cap_bits { u8 log_max_dci_errored_streams[0x5]; u8 reserved_at_598[0x8]; - u8 reserved_at_5a0[0x13]; + u8 reserved_at_5a0[0x10]; + u8 enhanced_cqe_compression[0x1]; + u8 reserved_at_5b1[0x2]; u8 log_max_dek[0x5]; u8 reserved_at_5b8[0x4]; u8 mini_cqe_resp_stride_index[0x1]; @@ -4139,7 +4141,8 @@ struct mlx5_ifc_cqc_bits { u8 cqe_comp_en[0x1]; u8 mini_cqe_res_format[0x2]; u8 st[0x4]; - u8 reserved_at_18[0x8]; + u8 reserved_at_18[0x6]; + u8 cqe_compression_layout[0x2]; u8 reserved_at_20[0x20]; -- cgit v1.2.3 From 6dbdc9f35360d4ef4704462c265f63b32fcb5354 Mon Sep 17 00:00:00 2001 From: Hongyi Lu Date: Mon, 13 Jun 2022 21:16:33 +0000 Subject: bpf: Fix spelling in bpf_verifier.h Minor spelling fix spotted in bpf_verifier.h. Spelling is no big deal, but it is still an improvement when reading through the code. Signed-off-by: Hongyi Lu Signed-off-by: Daniel Borkmann Link: https://lore.kernel.org/bpf/20220613211633.58647-1-jwnhy0@gmail.com --- include/linux/bpf_verifier.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/bpf_verifier.h b/include/linux/bpf_verifier.h index e8439f6cbe57..3930c963fa67 100644 --- a/include/linux/bpf_verifier.h +++ b/include/linux/bpf_verifier.h @@ -299,7 +299,7 @@ struct bpf_verifier_state { * 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 + * equivalency, 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(). -- cgit v1.2.3 From d687f621c518d791b5fffde8add3112d869b0b1b Mon Sep 17 00:00:00 2001 From: Delyan Kratunov Date: Tue, 14 Jun 2022 23:10:42 +0000 Subject: bpf: move bpf_prog to bpf.h In order to add a version of bpf_prog_run_array which accesses the bpf_prog->aux member, bpf_prog needs to be more than a forward declaration inside bpf.h. Given that filter.h already includes bpf.h, this merely reorders the type declarations for filter.h users. bpf.h users now have access to bpf_prog internals. Signed-off-by: Delyan Kratunov Link: https://lore.kernel.org/r/3ed7824e3948f22d84583649ccac0ff0d38b6b58.1655248076.git.delyank@fb.com Signed-off-by: Alexei Starovoitov --- include/linux/bpf.h | 36 ++++++++++++++++++++++++++++++++++++ include/linux/filter.h | 34 ---------------------------------- 2 files changed, 36 insertions(+), 34 deletions(-) (limited to 'include/linux') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 8e6092d0ea95..69106ae46464 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -5,6 +5,7 @@ #define _LINUX_BPF_H 1 #include +#include #include #include @@ -22,6 +23,7 @@ #include #include #include +#include #include #include @@ -1084,6 +1086,40 @@ struct bpf_prog_aux { }; }; +struct bpf_prog { + u16 pages; /* Number of allocated pages */ + u16 jited:1, /* Is our filter JIT'ed? */ + jit_requested:1,/* archs need to JIT the prog */ + gpl_compatible:1, /* Is filter GPL compatible? */ + cb_access:1, /* Is control block accessed? */ + dst_needed:1, /* Do we need dst entry? */ + blinding_requested:1, /* needs constant blinding */ + 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? */ + enforce_expected_attach_type:1, /* Enforce expected_attach_type checking at attach time */ + call_get_stack:1, /* Do we call bpf_get_stack() or bpf_get_stackid() */ + call_get_func_ip:1, /* Do we call get_func_ip() */ + tstamp_type_access:1; /* Accessed __sk_buff->tstamp_type */ + 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 */ + u32 jited_len; /* Size of jited insns in bytes */ + u8 tag[BPF_TAG_SIZE]; + struct bpf_prog_stats __percpu *stats; + int __percpu *active; + unsigned int (*bpf_func)(const void *ctx, + const struct bpf_insn *insn); + struct bpf_prog_aux *aux; /* Auxiliary fields */ + struct sock_fprog_kern *orig_prog; /* Original BPF program */ + /* Instructions for interpreter */ + union { + DECLARE_FLEX_ARRAY(struct sock_filter, insns); + DECLARE_FLEX_ARRAY(struct bpf_insn, insnsi); + }; +}; + struct bpf_array_aux { /* Programs with direct jumps into programs part of this array. */ struct list_head poke_progs; diff --git a/include/linux/filter.h b/include/linux/filter.h index ed0c0ff42ad5..d0cbb31b1b4d 100644 --- a/include/linux/filter.h +++ b/include/linux/filter.h @@ -559,40 +559,6 @@ struct bpf_prog_stats { struct u64_stats_sync syncp; } __aligned(2 * sizeof(u64)); -struct bpf_prog { - u16 pages; /* Number of allocated pages */ - u16 jited:1, /* Is our filter JIT'ed? */ - jit_requested:1,/* archs need to JIT the prog */ - gpl_compatible:1, /* Is filter GPL compatible? */ - cb_access:1, /* Is control block accessed? */ - dst_needed:1, /* Do we need dst entry? */ - blinding_requested:1, /* needs constant blinding */ - 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? */ - enforce_expected_attach_type:1, /* Enforce expected_attach_type checking at attach time */ - call_get_stack:1, /* Do we call bpf_get_stack() or bpf_get_stackid() */ - call_get_func_ip:1, /* Do we call get_func_ip() */ - tstamp_type_access:1; /* Accessed __sk_buff->tstamp_type */ - 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 */ - u32 jited_len; /* Size of jited insns in bytes */ - u8 tag[BPF_TAG_SIZE]; - struct bpf_prog_stats __percpu *stats; - int __percpu *active; - unsigned int (*bpf_func)(const void *ctx, - const struct bpf_insn *insn); - struct bpf_prog_aux *aux; /* Auxiliary fields */ - struct sock_fprog_kern *orig_prog; /* Original BPF program */ - /* Instructions for interpreter */ - union { - DECLARE_FLEX_ARRAY(struct sock_filter, insns); - DECLARE_FLEX_ARRAY(struct bpf_insn, insnsi); - }; -}; - struct sk_filter { refcount_t refcnt; struct rcu_head rcu; -- cgit v1.2.3 From 8c7dcb84e3b744b2b70baa7a44a9b1881c33a9c9 Mon Sep 17 00:00:00 2001 From: Delyan Kratunov Date: Tue, 14 Jun 2022 23:10:46 +0000 Subject: bpf: implement sleepable uprobes by chaining gps uprobes work by raising a trap, setting a task flag from within the interrupt handler, and processing the actual work for the uprobe on the way back to userspace. As a result, uprobe handlers already execute in a might_fault/_sleep context. The primary obstacle to sleepable bpf uprobe programs is therefore on the bpf side. Namely, the bpf_prog_array attached to the uprobe is protected by normal rcu. In order for uprobe bpf programs to become sleepable, it has to be protected by the tasks_trace rcu flavor instead (and kfree() called after a corresponding grace period). Therefore, the free path for bpf_prog_array now chains a tasks_trace and normal grace periods one after the other. Users who iterate under tasks_trace read section would be safe, as would users who iterate under normal read sections (from non-sleepable locations). The downside is that the tasks_trace latency affects all perf_event-attached bpf programs (and not just uprobe ones). This is deemed safe given the possible attach rates for kprobe/uprobe/tp programs. Separately, non-sleepable programs need access to dynamically sized rcu-protected maps, so bpf_run_prog_array_sleepables now conditionally takes an rcu read section, in addition to the overarching tasks_trace section. Signed-off-by: Delyan Kratunov Link: https://lore.kernel.org/r/ce844d62a2fd0443b08c5ab02e95bc7149f9aeb1.1655248076.git.delyank@fb.com Signed-off-by: Alexei Starovoitov --- include/linux/bpf.h | 52 ++++++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 52 insertions(+) (limited to 'include/linux') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 69106ae46464..f3e88afdaffe 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -26,6 +26,7 @@ #include #include #include +#include struct bpf_verifier_env; struct bpf_verifier_log; @@ -1372,6 +1373,8 @@ extern struct bpf_empty_prog_array bpf_empty_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); +/* Use when traversal over the bpf_prog_array uses tasks_trace rcu */ +void bpf_prog_array_free_sleepable(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, @@ -1463,6 +1466,55 @@ bpf_prog_run_array(const struct bpf_prog_array *array, return ret; } +/* Notes on RCU design for bpf_prog_arrays containing sleepable programs: + * + * We use the tasks_trace rcu flavor read section to protect the bpf_prog_array + * overall. As a result, we must use the bpf_prog_array_free_sleepable + * in order to use the tasks_trace rcu grace period. + * + * When a non-sleepable program is inside the array, we take the rcu read + * section and disable preemption for that program alone, so it can access + * rcu-protected dynamically sized maps. + */ +static __always_inline u32 +bpf_prog_run_array_sleepable(const struct bpf_prog_array __rcu *array_rcu, + const void *ctx, bpf_prog_run_fn run_prog) +{ + const struct bpf_prog_array_item *item; + const struct bpf_prog *prog; + const struct bpf_prog_array *array; + struct bpf_run_ctx *old_run_ctx; + struct bpf_trace_run_ctx run_ctx; + u32 ret = 1; + + might_fault(); + + rcu_read_lock_trace(); + migrate_disable(); + + array = rcu_dereference_check(array_rcu, rcu_read_lock_trace_held()); + if (unlikely(!array)) + goto out; + old_run_ctx = bpf_set_run_ctx(&run_ctx.run_ctx); + item = &array->items[0]; + while ((prog = READ_ONCE(item->prog))) { + if (!prog->aux->sleepable) + rcu_read_lock(); + + run_ctx.bpf_cookie = item->bpf_cookie; + ret &= run_prog(prog, ctx); + item++; + + if (!prog->aux->sleepable) + rcu_read_unlock(); + } + bpf_reset_run_ctx(old_run_ctx); +out: + migrate_enable(); + rcu_read_unlock_trace(); + return ret; +} + #ifdef CONFIG_BPF_SYSCALL DECLARE_PER_CPU(int, bpf_prog_active); extern struct mutex bpf_stats_enabled_mutex; -- cgit v1.2.3 From a793679827a87b01f9d973ea30b923cd5a3ff2c5 Mon Sep 17 00:00:00 2001 From: Rasmus Villemoes Date: Tue, 14 Jun 2022 10:46:11 +0200 Subject: linux/phy.h: add phydev_err_probe() wrapper for dev_err_probe() The dev_err_probe() function is quite useful to avoid boilerplate related to -EPROBE_DEFER handling. Add a phydev_err_probe() helper to simplify making use of that from phy drivers which otherwise use the phydev_* helpers. Signed-off-by: Rasmus Villemoes Signed-off-by: Jakub Kicinski --- include/linux/phy.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/phy.h b/include/linux/phy.h index 508f1149665b..bed9a347481b 100644 --- a/include/linux/phy.h +++ b/include/linux/phy.h @@ -1539,6 +1539,9 @@ static inline void phy_device_reset(struct phy_device *phydev, int value) #define phydev_err(_phydev, format, args...) \ dev_err(&_phydev->mdio.dev, format, ##args) +#define phydev_err_probe(_phydev, err, format, args...) \ + dev_err_probe(&_phydev->mdio.dev, err, format, ##args) + #define phydev_info(_phydev, format, args...) \ dev_info(&_phydev->mdio.dev, format, ##args) -- cgit v1.2.3 From 508362ac66b0478affb4e52cb8da98478312d72d Mon Sep 17 00:00:00 2001 From: Maxim Mikityanskiy Date: Wed, 15 Jun 2022 16:48:43 +0300 Subject: bpf: Allow helpers to accept pointers with a fixed size Before this commit, the BPF verifier required ARG_PTR_TO_MEM arguments to be followed by ARG_CONST_SIZE holding the size of the memory region. The helpers had to check that size in runtime. There are cases where the size expected by a helper is a compile-time constant. Checking it in runtime is an unnecessary overhead and waste of BPF registers. This commit allows helpers to accept pointers to memory without the corresponding ARG_CONST_SIZE, given that they define the memory region size in struct bpf_func_proto and use ARG_PTR_TO_FIXED_SIZE_MEM type. arg_size is unionized with arg_btf_id to reduce the kernel image size, and it's valid because they are used by different argument types. Signed-off-by: Maxim Mikityanskiy Reviewed-by: Tariq Toukan Link: https://lore.kernel.org/r/20220615134847.3753567-3-maximmi@nvidia.com Signed-off-by: Alexei Starovoitov --- include/linux/bpf.h | 13 +++++++++++++ 1 file changed, 13 insertions(+) (limited to 'include/linux') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index f3e88afdaffe..a94531971a7a 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -401,6 +401,9 @@ enum bpf_type_flag { /* DYNPTR points to a ringbuf record. */ DYNPTR_TYPE_RINGBUF = BIT(9 + BPF_BASE_TYPE_BITS), + /* Size is known at compile time. */ + MEM_FIXED_SIZE = BIT(10 + BPF_BASE_TYPE_BITS), + __BPF_TYPE_FLAG_MAX, __BPF_TYPE_LAST_FLAG = __BPF_TYPE_FLAG_MAX - 1, }; @@ -464,6 +467,8 @@ enum bpf_arg_type { * all bytes or clear them in error case. */ ARG_PTR_TO_UNINIT_MEM = MEM_UNINIT | ARG_PTR_TO_MEM, + /* Pointer to valid memory of size known at compile time. */ + ARG_PTR_TO_FIXED_SIZE_MEM = MEM_FIXED_SIZE | ARG_PTR_TO_MEM, /* This must be the last entry. Its purpose is to ensure the enum is * wide enough to hold the higher bits reserved for bpf_type_flag. @@ -529,6 +534,14 @@ struct bpf_func_proto { u32 *arg5_btf_id; }; u32 *arg_btf_id[5]; + struct { + size_t arg1_size; + size_t arg2_size; + size_t arg3_size; + size_t arg4_size; + size_t arg5_size; + }; + size_t arg_size[5]; }; int *ret_btf_id; /* return value btf_id */ bool (*allowed)(const struct bpf_prog *prog); -- cgit v1.2.3 From fa9c562f9735d24c3253747eb21f3f0c0f6de48e Mon Sep 17 00:00:00 2001 From: Ong Boon Leong Date: Wed, 15 Jun 2022 16:39:04 +0800 Subject: net: make xpcs_do_config to accept advertising for pcs-xpcs and sja1105 xpcs_config() has 'advertising' input that is required for C37 1000BASE-X AN in later patch series. So, we prepare xpcs_do_config() for it. For sja1105, xpcs_do_config() is used for xpcs configuration without depending on advertising input, so set to NULL. Reported-by: kernel test robot Signed-off-by: Ong Boon Leong Signed-off-by: David S. Miller --- include/linux/pcs/pcs-xpcs.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/pcs/pcs-xpcs.h b/include/linux/pcs/pcs-xpcs.h index 266eb26fb029..37eb97cc2283 100644 --- a/include/linux/pcs/pcs-xpcs.h +++ b/include/linux/pcs/pcs-xpcs.h @@ -30,7 +30,7 @@ int xpcs_get_an_mode(struct dw_xpcs *xpcs, phy_interface_t interface); void xpcs_link_up(struct phylink_pcs *pcs, unsigned int mode, phy_interface_t interface, int speed, int duplex); int xpcs_do_config(struct dw_xpcs *xpcs, phy_interface_t interface, - unsigned int mode); + unsigned int mode, const unsigned long *advertising); void xpcs_get_interfaces(struct dw_xpcs *xpcs, unsigned long *interfaces); int xpcs_config_eee(struct dw_xpcs *xpcs, int mult_fact_100ns, int enable); -- cgit v1.2.3 From b47aec885bcd672ebca2108a8b7e9ce3e3982775 Mon Sep 17 00:00:00 2001 From: Ong Boon Leong Date: Wed, 15 Jun 2022 16:39:06 +0800 Subject: net: pcs: xpcs: add CL37 1000BASE-X AN support For CL37 1000BASE-X AN, DW xPCS does not support C22 method but offers C45 vendor-specific MII MMD for programming. We also add the ability to disable Autoneg (through ethtool for certain network switch that supports 1000BASE-X (1000Mbps and Full-Duplex) but not Autoneg capability. v4: Fixes to comment from Russell King. Thanks! https://patchwork.kernel.org/comment/24894239/ Make xpcs_modify_changed() as private, change to use mdiodev_modify_changed() for cleaner code. v3: Fixes to issues spotted by Russell King. Thanks! https://patchwork.kernel.org/comment/24890210/ Use phylink_mii_c22_pcs_decode_state(), remove unnecessary interrupt clearing and skip speed & duplex setting if AN is enabled. v2: Fixes to issues spotted by Russell King in v1. Thanks! https://patchwork.kernel.org/comment/24826650/ Use phylink_mii_c22_pcs_encode_advertisement() and implement C45 MII ADV handling since IP only support C45 access. Tested-by: Emilio Riva Signed-off-by: Ong Boon Leong Reviewed-by: Russell King (Oracle) Signed-off-by: David S. Miller --- include/linux/pcs/pcs-xpcs.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/pcs/pcs-xpcs.h b/include/linux/pcs/pcs-xpcs.h index 37eb97cc2283..d2da1e0b4a92 100644 --- a/include/linux/pcs/pcs-xpcs.h +++ b/include/linux/pcs/pcs-xpcs.h @@ -17,6 +17,7