From d8e18a516f8f67404c0d21af8c93d0474fba0876 Mon Sep 17 00:00:00 2001 From: "Matthew Wilcox (Oracle)" Date: Mon, 22 Jul 2019 20:08:26 -0700 Subject: net: Use skb accessors in network core In preparation for unifying the skb_frag and bio_vec, use the fine accessors which already exist and use skb_frag_t instead of struct skb_frag_struct. Signed-off-by: Matthew Wilcox (Oracle) Signed-off-by: David S. Miller --- include/linux/skbuff.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index d8af86d995d6..f9078e7edb53 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -3166,7 +3166,7 @@ static inline bool skb_can_coalesce(struct sk_buff *skb, int i, if (skb_zcopy(skb)) return false; if (i) { - const struct skb_frag_struct *frag = &skb_shinfo(skb)->frags[i - 1]; + const skb_frag_t *frag = &skb_shinfo(skb)->frags[i - 1]; return page == skb_frag_page(frag) && off == frag->page_offset + skb_frag_size(frag); -- cgit v1.2.3 From b656722906efe434f0befe1d4ae4bb7a66fdc124 Mon Sep 17 00:00:00 2001 From: "Matthew Wilcox (Oracle)" Date: Mon, 22 Jul 2019 20:08:27 -0700 Subject: net: Increase the size of skb_frag_t To increase commonality between block and net, we are going to replace the skb_frag_t with the bio_vec. This patch increases the size of skb_frag_t on 32-bit machines from 8 bytes to 12 bytes. The size is unchanged on 64-bit machines. Signed-off-by: Matthew Wilcox (Oracle) Signed-off-by: David S. Miller --- include/linux/skbuff.h | 5 ----- 1 file changed, 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index f9078e7edb53..7910935410e6 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -314,13 +314,8 @@ struct skb_frag_struct { struct { struct page *p; } page; -#if (BITS_PER_LONG > 32) || (PAGE_SIZE >= 65536) __u32 page_offset; __u32 size; -#else - __u16 page_offset; - __u16 size; -#endif }; /** -- cgit v1.2.3 From f58ecf1b7d58911921014ffd12c77a4ad33ade71 Mon Sep 17 00:00:00 2001 From: "Matthew Wilcox (Oracle)" Date: Mon, 22 Jul 2019 20:08:28 -0700 Subject: net: Reorder the contents of skb_frag_t Match the layout of bio_vec. Signed-off-by: Matthew Wilcox (Oracle) Signed-off-by: David S. Miller --- include/linux/skbuff.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 7910935410e6..b9dc8b4f24b1 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -314,8 +314,8 @@ struct skb_frag_struct { struct { struct page *p; } page; - __u32 page_offset; __u32 size; + __u32 page_offset; }; /** -- cgit v1.2.3 From 1dfa5bd38545c6f6a8b6c496e58db93f80da1076 Mon Sep 17 00:00:00 2001 From: "Matthew Wilcox (Oracle)" Date: Mon, 22 Jul 2019 20:08:29 -0700 Subject: net: Rename skb_frag page to bv_page One step closer to turning the skb_frag_t into a bio_vec. Signed-off-by: Matthew Wilcox (Oracle) Signed-off-by: David S. Miller --- include/linux/skbuff.h | 12 +++++------- net/core/skbuff.c | 2 +- 2 files changed, 6 insertions(+), 8 deletions(-) (limited to 'include/linux') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index b9dc8b4f24b1..8076e2ba8349 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -311,9 +311,7 @@ extern int sysctl_max_skb_frags; typedef struct skb_frag_struct skb_frag_t; struct skb_frag_struct { - struct { - struct page *p; - } page; + struct page *bv_page; __u32 size; __u32 page_offset; }; @@ -374,7 +372,7 @@ static inline bool skb_frag_must_loop(struct page *p) * skb_frag_foreach_page - loop over pages in a fragment * * @f: skb frag to operate on - * @f_off: offset from start of f->page.p + * @f_off: offset from start of f->bv_page * @f_len: length from f_off to loop over * @p: (temp var) current page * @p_off: (temp var) offset from start of current page, @@ -2084,7 +2082,7 @@ static inline void __skb_fill_page_desc(struct sk_buff *skb, int i, * that not all callers have unique ownership of the page but rely * on page_is_pfmemalloc doing the right thing(tm). */ - frag->page.p = page; + frag->bv_page = page; frag->page_offset = off; skb_frag_size_set(frag, size); @@ -2872,7 +2870,7 @@ static inline void skb_propagate_pfmemalloc(struct page *page, */ static inline struct page *skb_frag_page(const skb_frag_t *frag) { - return frag->page.p; + return frag->bv_page; } /** @@ -2958,7 +2956,7 @@ static inline void *skb_frag_address_safe(const skb_frag_t *frag) */ static inline void __skb_frag_set_page(skb_frag_t *frag, struct page *page) { - frag->page.p = page; + frag->bv_page = page; } /** diff --git a/net/core/skbuff.c b/net/core/skbuff.c index ba9a36903503..0b788df5a75b 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -3364,7 +3364,7 @@ int skb_shift(struct sk_buff *tgt, struct sk_buff *skb, int shiftlen) } else { __skb_frag_ref(fragfrom); - fragto->page = fragfrom->page; + fragto->bv_page = fragfrom->bv_page; fragto->page_offset = fragfrom->page_offset; skb_frag_size_set(fragto, todo); -- cgit v1.2.3 From b8b576a16f79efbdde49348147f491b176537d88 Mon Sep 17 00:00:00 2001 From: "Matthew Wilcox (Oracle)" Date: Mon, 22 Jul 2019 20:08:30 -0700 Subject: net: Rename skb_frag_t size to bv_len Improved compatibility with bvec Signed-off-by: Matthew Wilcox (Oracle) Signed-off-by: David S. Miller --- include/linux/skbuff.h | 10 +++++----- 1 file changed, 5 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 8076e2ba8349..e849e411d1f3 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -312,7 +312,7 @@ typedef struct skb_frag_struct skb_frag_t; struct skb_frag_struct { struct page *bv_page; - __u32 size; + unsigned int bv_len; __u32 page_offset; }; @@ -322,7 +322,7 @@ struct skb_frag_struct { */ static inline unsigned int skb_frag_size(const skb_frag_t *frag) { - return frag->size; + return frag->bv_len; } /** @@ -332,7 +332,7 @@ static inline unsigned int skb_frag_size(const skb_frag_t *frag) */ static inline void skb_frag_size_set(skb_frag_t *frag, unsigned int size) { - frag->size = size; + frag->bv_len = size; } /** @@ -342,7 +342,7 @@ static inline void skb_frag_size_set(skb_frag_t *frag, unsigned int size) */ static inline void skb_frag_size_add(skb_frag_t *frag, int delta) { - frag->size += delta; + frag->bv_len += delta; } /** @@ -352,7 +352,7 @@ static inline void skb_frag_size_add(skb_frag_t *frag, int delta) */ static inline void skb_frag_size_sub(skb_frag_t *frag, int delta) { - frag->size -= delta; + frag->bv_len -= delta; } /** -- cgit v1.2.3 From 8842d285bafa9ff7719f4107b6545a11dcd41995 Mon Sep 17 00:00:00 2001 From: "Matthew Wilcox (Oracle)" Date: Mon, 22 Jul 2019 20:08:31 -0700 Subject: net: Convert skb_frag_t to bio_vec There are a lot of users of frag->page_offset, so use a union to avoid converting those users today. Signed-off-by: Matthew Wilcox (Oracle) Signed-off-by: David S. Miller --- include/linux/bvec.h | 5 ++++- include/linux/skbuff.h | 9 ++------- 2 files changed, 6 insertions(+), 8 deletions(-) (limited to 'include/linux') diff --git a/include/linux/bvec.h b/include/linux/bvec.h index a032f01e928c..7f2b2ea9399c 100644 --- a/include/linux/bvec.h +++ b/include/linux/bvec.h @@ -18,7 +18,10 @@ struct bio_vec { struct page *bv_page; unsigned int bv_len; - unsigned int bv_offset; + union { + __u32 page_offset; + unsigned int bv_offset; + }; }; struct bvec_iter { diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index e849e411d1f3..718742b1c505 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -14,6 +14,7 @@ #include #include #include +#include #include #include #include @@ -308,13 +309,7 @@ extern int sysctl_max_skb_frags; */ #define GSO_BY_FRAGS 0xFFFF -typedef struct skb_frag_struct skb_frag_t; - -struct skb_frag_struct { - struct page *bv_page; - unsigned int bv_len; - __u32 page_offset; -}; +typedef struct bio_vec skb_frag_t; /** * skb_frag_size - Returns the size of a skb fragment -- cgit v1.2.3 From 60649d4e0af6c26b6c423dea9c57f39e823fc0c5 Mon Sep 17 00:00:00 2001 From: Oliver Hartkopp Date: Tue, 23 Jul 2019 14:08:47 +0200 Subject: can: remove obsolete empty ioctl() handler With commit c7cbdbf29f488a ("net: rework SIOCGSTAMP ioctl handling") the only ioctl function in can_ioctl() has been removed. As this SIOCGSTAMP ioctl command is now handled in net/socket.c we can entirely remove the CAN specific ioctl functions. Signed-off-by: Oliver Hartkopp Signed-off-by: Marc Kleine-Budde --- include/linux/can/core.h | 1 - net/can/af_can.c | 9 --------- net/can/bcm.c | 2 +- net/can/raw.c | 2 +- 4 files changed, 2 insertions(+), 12 deletions(-) (limited to 'include/linux') diff --git a/include/linux/can/core.h b/include/linux/can/core.h index 6099bc18bd0c..f8284a94a13d 100644 --- a/include/linux/can/core.h +++ b/include/linux/can/core.h @@ -57,6 +57,5 @@ extern void can_rx_unregister(struct net *net, struct net_device *dev, void *data); extern int can_send(struct sk_buff *skb, int loop); -extern int can_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg); #endif /* !_CAN_CORE_H */ diff --git a/net/can/af_can.c b/net/can/af_can.c index 80281ef2ccbd..9c86de2da45e 100644 --- a/net/can/af_can.c +++ b/net/can/af_can.c @@ -87,15 +87,6 @@ static atomic_t skbcounter = ATOMIC_INIT(0); * af_can socket functions */ -int can_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg) -{ - switch (cmd) { - default: - return -ENOIOCTLCMD; - } -} -EXPORT_SYMBOL(can_ioctl); - static void can_sock_destruct(struct sock *sk) { skb_queue_purge(&sk->sk_receive_queue); diff --git a/net/can/bcm.c b/net/can/bcm.c index a34ee52f19ea..1eecf4d3e8d2 100644 --- a/net/can/bcm.c +++ b/net/can/bcm.c @@ -1688,7 +1688,7 @@ static const struct proto_ops bcm_ops = { .accept = sock_no_accept, .getname = sock_no_getname, .poll = datagram_poll, - .ioctl = can_ioctl, /* use can_ioctl() from af_can.c */ + .ioctl = sock_no_ioctl, .gettstamp = sock_gettstamp, .listen = sock_no_listen, .shutdown = sock_no_shutdown, diff --git a/net/can/raw.c b/net/can/raw.c index afcbff063a67..bbbe3dd0abe9 100644 --- a/net/can/raw.c +++ b/net/can/raw.c @@ -845,7 +845,7 @@ static const struct proto_ops raw_ops = { .accept = sock_no_accept, .getname = raw_getname, .poll = datagram_poll, - .ioctl = can_ioctl, /* use can_ioctl() from af_can.c */ + .ioctl = sock_no_ioctl, .gettstamp = sock_gettstamp, .listen = sock_no_listen, .shutdown = sock_no_shutdown, -- cgit v1.2.3 From fba76a58452694b9b13c07e48839fa84c75f57af Mon Sep 17 00:00:00 2001 From: Oliver Hartkopp Date: Tue, 23 Jul 2019 15:17:55 +0200 Subject: can: Add SPDX license identifiers for CAN subsystem Add missing SPDX identifiers for the CAN network layer and correct the SPDX license for two of its include files to make sure the BSD-3-Clause applies for the entire subsystem. Signed-off-by: Oliver Hartkopp Signed-off-by: Marc Kleine-Budde --- include/linux/can/core.h | 2 +- include/linux/can/skb.h | 2 +- net/can/af_can.c | 1 + net/can/af_can.h | 1 + net/can/bcm.c | 1 + net/can/gw.c | 1 + net/can/proc.c | 1 + net/can/raw.c | 1 + 8 files changed, 8 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/can/core.h b/include/linux/can/core.h index f8284a94a13d..708c10d3417a 100644 --- a/include/linux/can/core.h +++ b/include/linux/can/core.h @@ -1,4 +1,4 @@ -/* SPDX-License-Identifier: GPL-2.0 */ +/* SPDX-License-Identifier: (GPL-2.0 OR BSD-3-Clause) */ /* * linux/can/core.h * diff --git a/include/linux/can/skb.h b/include/linux/can/skb.h index b3379a97245c..a954def26c0d 100644 --- a/include/linux/can/skb.h +++ b/include/linux/can/skb.h @@ -1,4 +1,4 @@ -/* SPDX-License-Identifier: GPL-2.0 */ +/* SPDX-License-Identifier: (GPL-2.0 OR BSD-3-Clause) */ /* * linux/can/skb.h * diff --git a/net/can/af_can.c b/net/can/af_can.c index 9c86de2da45e..76cf83b2bd40 100644 --- a/net/can/af_can.c +++ b/net/can/af_can.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: (GPL-2.0 OR BSD-3-Clause) /* * af_can.c - Protocol family CAN core module * (used by different CAN protocol modules) diff --git a/net/can/af_can.h b/net/can/af_can.h index 9cb3719632bd..ef21f7c6bc80 100644 --- a/net/can/af_can.h +++ b/net/can/af_can.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: (GPL-2.0 OR BSD-3-Clause) */ /* * Copyright (c) 2002-2007 Volkswagen Group Electronic Research * All rights reserved. diff --git a/net/can/bcm.c b/net/can/bcm.c index 1eecf4d3e8d2..8da986b19d88 100644 --- a/net/can/bcm.c +++ b/net/can/bcm.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: ((GPL-2.0 WITH Linux-syscall-note) OR BSD-3-Clause) /* * bcm.c - Broadcast Manager to filter/send (cyclic) CAN content * diff --git a/net/can/gw.c b/net/can/gw.c index 5275ddf580bc..8abae841d504 100644 --- a/net/can/gw.c +++ b/net/can/gw.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: ((GPL-2.0 WITH Linux-syscall-note) OR BSD-3-Clause) /* * gw.c - CAN frame Gateway/Router/Bridge with netlink interface * diff --git a/net/can/proc.c b/net/can/proc.c index 70fea17bb04c..edb822c31902 100644 --- a/net/can/proc.c +++ b/net/can/proc.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: ((GPL-2.0 WITH Linux-syscall-note) OR BSD-3-Clause) /* * proc.c - procfs support for Protocol family CAN core module * diff --git a/net/can/raw.c b/net/can/raw.c index bbbe3dd0abe9..ff720272f7b7 100644 --- a/net/can/raw.c +++ b/net/can/raw.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: ((GPL-2.0 WITH Linux-syscall-note) OR BSD-3-Clause) /* * raw.c - Raw sockets for protocol family CAN * -- cgit v1.2.3 From 086f95682114fd2d1790bd3226e76cbae9a2d192 Mon Sep 17 00:00:00 2001 From: Stanislav Fomichev Date: Thu, 25 Jul 2019 15:52:25 -0700 Subject: bpf/flow_dissector: pass input flags to BPF flow dissector program C flow dissector supports input flags that tell it to customize parsing by either stopping early or trying to parse as deep as possible. Pass those flags to the BPF flow dissector so it can make the same decisions. In the next commits I'll add support for those flags to our reference bpf_flow.c v3: * Export copy of flow dissector flags instead of moving (Alexei Starovoitov) Acked-by: Petar Penkov Acked-by: Willem de Bruijn Acked-by: Song Liu Cc: Song Liu Cc: Willem de Bruijn Cc: Petar Penkov Signed-off-by: Stanislav Fomichev Signed-off-by: Alexei Starovoitov --- include/linux/skbuff.h | 2 +- include/uapi/linux/bpf.h | 5 +++++ net/bpf/test_run.c | 2 +- net/core/flow_dissector.c | 12 ++++++++++-- 4 files changed, 17 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 718742b1c505..9b7a8038beec 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -1271,7 +1271,7 @@ static inline int skb_flow_dissector_bpf_prog_detach(const union bpf_attr *attr) struct bpf_flow_dissector; bool bpf_flow_dissect(struct bpf_prog *prog, struct bpf_flow_dissector *ctx, - __be16 proto, int nhoff, int hlen); + __be16 proto, int nhoff, int hlen, unsigned int flags); bool __skb_flow_dissect(const struct net *net, const struct sk_buff *skb, diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index fa1c753dcdbc..88b9d743036f 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -3507,6 +3507,10 @@ enum bpf_task_fd_type { BPF_FD_TYPE_URETPROBE, /* filename + offset */ }; +#define BPF_FLOW_DISSECTOR_F_PARSE_1ST_FRAG (1U << 0) +#define BPF_FLOW_DISSECTOR_F_STOP_AT_FLOW_LABEL (1U << 1) +#define BPF_FLOW_DISSECTOR_F_STOP_AT_ENCAP (1U << 2) + struct bpf_flow_keys { __u16 nhoff; __u16 thoff; @@ -3528,6 +3532,7 @@ struct bpf_flow_keys { __u32 ipv6_dst[4]; /* in6_addr; network order */ }; }; + __u32 flags; }; struct bpf_func_info { diff --git a/net/bpf/test_run.c b/net/bpf/test_run.c index 80e6f3a6864d..4e41d15a1098 100644 --- a/net/bpf/test_run.c +++ b/net/bpf/test_run.c @@ -419,7 +419,7 @@ int bpf_prog_test_run_flow_dissector(struct bpf_prog *prog, time_start = ktime_get_ns(); for (i = 0; i < repeat; i++) { retval = bpf_flow_dissect(prog, &ctx, eth->h_proto, ETH_HLEN, - size); + size, 0); if (signal_pending(current)) { preempt_enable(); diff --git a/net/core/flow_dissector.c b/net/core/flow_dissector.c index 3e6fedb57bc1..50ed1a688709 100644 --- a/net/core/flow_dissector.c +++ b/net/core/flow_dissector.c @@ -784,7 +784,7 @@ static void __skb_flow_bpf_to_target(const struct bpf_flow_keys *flow_keys, } bool bpf_flow_dissect(struct bpf_prog *prog, struct bpf_flow_dissector *ctx, - __be16 proto, int nhoff, int hlen) + __be16 proto, int nhoff, int hlen, unsigned int flags) { struct bpf_flow_keys *flow_keys = ctx->flow_keys; u32 result; @@ -795,6 +795,14 @@ bool bpf_flow_dissect(struct bpf_prog *prog, struct bpf_flow_dissector *ctx, flow_keys->nhoff = nhoff; flow_keys->thoff = flow_keys->nhoff; + BUILD_BUG_ON((int)BPF_FLOW_DISSECTOR_F_PARSE_1ST_FRAG != + (int)FLOW_DISSECTOR_F_PARSE_1ST_FRAG); + BUILD_BUG_ON((int)BPF_FLOW_DISSECTOR_F_STOP_AT_FLOW_LABEL != + (int)FLOW_DISSECTOR_F_STOP_AT_FLOW_LABEL); + BUILD_BUG_ON((int)BPF_FLOW_DISSECTOR_F_STOP_AT_ENCAP != + (int)FLOW_DISSECTOR_F_STOP_AT_ENCAP); + flow_keys->flags = flags; + preempt_disable(); result = BPF_PROG_RUN(prog, ctx); preempt_enable(); @@ -914,7 +922,7 @@ bool __skb_flow_dissect(const struct net *net, } ret = bpf_flow_dissect(attached, &ctx, n_proto, nhoff, - hlen); + hlen, flags); __skb_flow_bpf_to_target(&flow_keys, flow_dissector, target_container); rcu_read_unlock(); -- cgit v1.2.3 From 2aa485e1148557215337731b2c79f5569edcbbab Mon Sep 17 00:00:00 2001 From: John Crispin Date: Sat, 13 Jul 2019 18:36:41 +0200 Subject: mac80211: add support for parsing ADDBA_EXT IEs ADDBA_EXT IEs can be used to negotiate the BA fragmentation level. Signed-off-by: John Crispin Link: https://lore.kernel.org/r/20190713163642.18491-2-john@phrozen.org Signed-off-by: Johannes Berg --- include/linux/ieee80211.h | 8 ++++++++ net/mac80211/ieee80211_i.h | 1 + net/mac80211/util.c | 7 +++++++ 3 files changed, 16 insertions(+) (limited to 'include/linux') diff --git a/include/linux/ieee80211.h b/include/linux/ieee80211.h index 8511fadc0935..f36144eda5d6 100644 --- a/include/linux/ieee80211.h +++ b/include/linux/ieee80211.h @@ -881,6 +881,14 @@ struct ieee80211_tpc_report_ie { u8 link_margin; } __packed; +#define IEEE80211_ADDBA_EXT_FRAG_LEVEL_MASK GENMASK(2, 1) +#define IEEE80211_ADDBA_EXT_FRAG_LEVEL_SHIFT 1 +#define IEEE80211_ADDBA_EXT_NO_FRAG BIT(0) + +struct ieee80211_addba_ext_ie { + u8 data; +} __packed; + struct ieee80211_mgmt { __le16 frame_control; __le16 duration; diff --git a/net/mac80211/ieee80211_i.h b/net/mac80211/ieee80211_i.h index 004e2e3adb88..c67da3575e74 100644 --- a/net/mac80211/ieee80211_i.h +++ b/net/mac80211/ieee80211_i.h @@ -1506,6 +1506,7 @@ struct ieee802_11_elems { u8 max_bssid_indicator; u8 dtim_count; u8 dtim_period; + const struct ieee80211_addba_ext_ie *addba_ext_ie; /* length of them, respectively */ u8 ext_capab_len; diff --git a/net/mac80211/util.c b/net/mac80211/util.c index 1b224fa27367..3441558ef2d2 100644 --- a/net/mac80211/util.c +++ b/net/mac80211/util.c @@ -1200,6 +1200,13 @@ _ieee802_11_parse_elems_crc(const u8 *start, size_t len, bool action, elems->cisco_dtpc_elem = pos; break; + case WLAN_EID_ADDBA_EXT: + if (elen != sizeof(struct ieee80211_addba_ext_ie)) { + elem_parse_failed = true; + break; + } + elems->addba_ext_ie = (void *)pos; + break; case WLAN_EID_TIMEOUT_INTERVAL: if (elen >= sizeof(struct ieee80211_timeout_interval_ie)) elems->timeout_int = (void *)pos; -- cgit v1.2.3 From ef11a931bd1c57b02fe2603ff95a392a73041f9e Mon Sep 17 00:00:00 2001 From: John Crispin Date: Tue, 18 Jun 2019 08:19:14 +0200 Subject: mac80211: HE: add Spatial Reuse element parsing support Add support to mac80211 for parsing SPR elements as per P802.11ax_D4.0 section 9.4.2.241. Signed-off-by: Shashidhar Lakkavalli Signed-off-by: John Crispin Link: https://lore.kernel.org/r/20190618061915.7102-2-john@phrozen.org Signed-off-by: Johannes Berg --- include/linux/ieee80211.h | 49 ++++++++++++++++++++++++++++++++++++++++++++++ net/mac80211/ieee80211_i.h | 1 + net/mac80211/util.c | 4 ++++ 3 files changed, 54 insertions(+) (limited to 'include/linux') diff --git a/include/linux/ieee80211.h b/include/linux/ieee80211.h index f36144eda5d6..a656f31262f1 100644 --- a/include/linux/ieee80211.h +++ b/include/linux/ieee80211.h @@ -1633,6 +1633,18 @@ struct ieee80211_he_operation { u8 optional[0]; } __packed; +/** + * struct ieee80211_he_spr - HE spatial reuse element + * + * This structure is the "HE spatial reuse element" element as + * described in P802.11ax_D4.0 section 9.4.2.241 + */ +struct ieee80211_he_spr { + u8 he_sr_control; + /* Optional 0 to 19 bytes: depends on @he_sr_control */ + u8 optional[0]; +} __packed; + /** * struct ieee80211_he_mu_edca_param_ac_rec - MU AC Parameter Record field * @@ -2071,6 +2083,42 @@ ieee80211_he_oper_size(const u8 *he_oper_ie) return oper_len; } +/* HE Spatial Reuse defines */ +#define IEEE80211_HE_SPR_NON_SRG_OFFSET_PRESENT 0x4 +#define IEEE80211_HE_SPR_SRG_INFORMATION_PRESENT 0x8 + +/* + * ieee80211_he_spr_size - calculate 802.11ax HE Spatial Reuse IE size + * @he_spr_ie: byte data of the He Spatial Reuse IE, stating from the the byte + * after the ext ID byte. It is assumed that he_spr_ie has at least + * sizeof(struct ieee80211_he_spr) bytes, the caller must have validated + * this + * @return the actual size of the IE data (not including header), or 0 on error + */ +static inline u8 +ieee80211_he_spr_size(const u8 *he_spr_ie) +{ + struct ieee80211_he_spr *he_spr = (void *)he_spr_ie; + u8 spr_len = sizeof(struct ieee80211_he_spr); + u32 he_spr_params; + + /* Make sure the input is not NULL */ + if (!he_spr_ie) + return 0; + + /* Calc required length */ + he_spr_params = le32_to_cpu(he_spr->he_sr_control); + if (he_spr_params & IEEE80211_HE_SPR_NON_SRG_OFFSET_PRESENT) + spr_len++; + if (he_spr_params & IEEE80211_HE_SPR_SRG_INFORMATION_PRESENT) + spr_len += 18; + + /* Add the first byte (extension ID) to the total length */ + spr_len++; + + return spr_len; +} + /* Authentication algorithms */ #define WLAN_AUTH_OPEN 0 #define WLAN_AUTH_SHARED_KEY 1 @@ -2493,6 +2541,7 @@ enum ieee80211_eid_ext { WLAN_EID_EXT_HE_OPERATION = 36, WLAN_EID_EXT_UORA = 37, WLAN_EID_EXT_HE_MU_EDCA = 38, + WLAN_EID_EXT_HE_SPR = 39, WLAN_EID_EXT_MAX_CHANNEL_SWITCH_TIME = 52, WLAN_EID_EXT_MULTIPLE_BSSID_CONFIGURATION = 55, WLAN_EID_EXT_NON_INHERITANCE = 56, diff --git a/net/mac80211/ieee80211_i.h b/net/mac80211/ieee80211_i.h index 4c80c0ed67a7..472c5a40317d 100644 --- a/net/mac80211/ieee80211_i.h +++ b/net/mac80211/ieee80211_i.h @@ -1480,6 +1480,7 @@ struct ieee802_11_elems { const struct ieee80211_meshconf_ie *mesh_config; const u8 *he_cap; const struct ieee80211_he_operation *he_operation; + const struct ieee80211_he_spr *he_spr; const struct ieee80211_mu_edca_param_set *mu_edca_param_set; const u8 *uora_element; const u8 *mesh_id; diff --git a/net/mac80211/util.c b/net/mac80211/util.c index 3441558ef2d2..3e2aeb1a75b4 100644 --- a/net/mac80211/util.c +++ b/net/mac80211/util.c @@ -1240,6 +1240,10 @@ _ieee802_11_parse_elems_crc(const u8 *start, size_t len, bool action, WLAN_EID_EXT_MULTIPLE_BSSID_CONFIGURATION && elen == 3) { elems->mbssid_config_ie = (void *)&pos[1]; + } else if (pos[0] == WLAN_EID_EXT_HE_SPR && + elen >= sizeof(*elems->he_spr) && + elen >= ieee80211_he_spr_size(&pos[1])) { + elems->he_spr = (void *)&pos[1]; } break; default: -- cgit v1.2.3 From 1a981c0586c038710227eb740350f291e77ce365 Mon Sep 17 00:00:00 2001 From: Thierry Reding Date: Fri, 26 Jul 2019 12:27:40 +0200 Subject: net: stmmac: Make MDIO bus reset optional The Tegra EQOS driver already resets the MDIO bus at probe time via the reset GPIO specified in the phy-reset-gpios device tree property. There is no need to reset the bus again later on. This avoids the need to query the device tree for the snps,reset GPIO, which is not part of the Tegra EQOS device tree bindings. This quiesces an error message from the generic bus reset code if it doesn't find the snps,reset related delays. Signed-off-by: Thierry Reding Signed-off-by: David S. Miller --- drivers/net/ethernet/stmicro/stmmac/dwmac-dwc-qos-eth.c | 3 +++ drivers/net/ethernet/stmicro/stmmac/stmmac_mdio.c | 4 +++- drivers/net/ethernet/stmicro/stmmac/stmmac_pci.c | 1 + drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c | 8 +++++++- include/linux/stmmac.h | 1 + 5 files changed, 15 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-dwc-qos-eth.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-dwc-qos-eth.c index 3a14cdd01f5f..66933332c68e 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac-dwc-qos-eth.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-dwc-qos-eth.c @@ -333,6 +333,9 @@ static void *tegra_eqos_probe(struct platform_device *pdev, usleep_range(2000, 4000); gpiod_set_value(eqos->reset, 0); + /* MDIO bus was already reset just above */ + data->mdio_bus_data->needs_reset = false; + eqos->rst = devm_reset_control_get(&pdev->dev, "eqos"); if (IS_ERR(eqos->rst)) { err = PTR_ERR(eqos->rst); diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_mdio.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_mdio.c index 4304c1abc5d1..40c42637ad75 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_mdio.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_mdio.c @@ -348,7 +348,9 @@ int stmmac_mdio_register(struct net_device *ndev) max_addr = PHY_MAX_ADDR; } - new_bus->reset = &stmmac_mdio_reset; + if (mdio_bus_data->needs_reset) + new_bus->reset = &stmmac_mdio_reset; + snprintf(new_bus->id, MII_BUS_ID_SIZE, "%s-%x", new_bus->name, priv->plat->bus_id); new_bus->priv = ndev; diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_pci.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_pci.c index 86f9c07a38cf..d5d08e11c353 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_pci.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_pci.c @@ -63,6 +63,7 @@ static void common_default_data(struct plat_stmmacenet_data *plat) plat->has_gmac = 1; plat->force_sf_dma_mode = 1; + plat->mdio_bus_data->needs_reset = true; plat->mdio_bus_data->phy_mask = 0; /* Set default value for multicast hash bins */ diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c index 73fc2524372e..333b09564b88 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c @@ -342,10 +342,16 @@ static int stmmac_dt_phy(struct plat_stmmacenet_data *plat, mdio = true; } - if (mdio) + if (mdio) { plat->mdio_bus_data = devm_kzalloc(dev, sizeof(struct stmmac_mdio_bus_data), GFP_KERNEL); + if (!plat->mdio_bus_data) + return -ENOMEM; + + plat->mdio_bus_data->needs_reset = true; + } + return 0; } diff --git a/include/linux/stmmac.h b/include/linux/stmmac.h index 7d06241582dd..7b3e354bcd3c 100644 --- a/include/linux/stmmac.h +++ b/include/linux/stmmac.h @@ -81,6 +81,7 @@ struct stmmac_mdio_bus_data { unsigned int phy_mask; int *irqs; int probed_phy_irq; + bool needs_reset; }; struct stmmac_dma_cfg { -- cgit v1.2.3 From 90d4962cfc87a6994a19db0d76e1fa214dd67267 Mon Sep 17 00:00:00 2001 From: John Crispin Date: Mon, 29 Jul 2019 12:23:41 +0200 Subject: mac80211: fix ieee80211_he_oper_size() comment Johannes mentioned that the comment should not reference mac80211 as other subsystems might call the helper. Signed-off-by: John Crispin Signed-off-by: Kalle Valo Link: https://lore.kernel.org/r/20190729102342.8659-1-john@phrozen.org Signed-off-by: Johannes Berg --- include/linux/ieee80211.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ieee80211.h b/include/linux/ieee80211.h index a656f31262f1..9c81895c63c1 100644 --- a/include/linux/ieee80211.h +++ b/include/linux/ieee80211.h @@ -2053,8 +2053,8 @@ ieee80211_he_ppe_size(u8 ppe_thres_hdr, const u8 *phy_cap_info) * ieee80211_he_oper_size - calculate 802.11ax HE Operations IE size * @he_oper_ie: byte data of the He Operations IE, stating from the the byte * after the ext ID byte. It is assumed that he_oper_ie has at least - * sizeof(struct ieee80211_he_operation) bytes, checked already in - * ieee802_11_parse_elems_crc() + * sizeof(struct ieee80211_he_operation) bytes, the caller must have + * validated this. * @return the actual size of the IE data (not including header), or 0 on error */ static inline u8 -- cgit v1.2.3 From 2ab45876756fb6c132ae801b0939e0474f84c426 Mon Sep 17 00:00:00 2001 From: John Crispin Date: Mon, 29 Jul 2019 12:45:12 +0200 Subject: mac80211: add support for the ADDBA extension element HE allows peers to negotiate the aggregation fragmentation level to be used during transmission. The level can be 1-3. The Ext element is added behind the ADDBA request inside the action frame. The responder will then reply with the same level or a lower one if the requested one is not supported. This patch only handles the negotiation part as the ADDBA frames get passed to the ATH11k firmware, which does the rest of the magic for us aswell as generating the requests. Signed-off-by: Shashidhar Lakkavalli Signed-off-by: John Crispin Link: https://lore.kernel.org/r/20190729104512.27615-1-john@phrozen.org Signed-off-by: Johannes Berg --- include/linux/ieee80211.h | 2 ++ net/mac80211/agg-rx.c | 70 ++++++++++++++++++++++++++++++++++++++++------ net/mac80211/ht.c | 2 +- net/mac80211/ieee80211_i.h | 3 +- 4 files changed, 66 insertions(+), 11 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ieee80211.h b/include/linux/ieee80211.h index 9c81895c63c1..7d3f2ced92d1 100644 --- a/include/linux/ieee80211.h +++ b/include/linux/ieee80211.h @@ -981,6 +981,8 @@ struct ieee80211_mgmt { __le16 capab; __le16 timeout; __le16 start_seq_num; + /* followed by BA Extension */ + u8 variable[0]; } __packed addba_req; struct{ u8 action_code; diff --git a/net/mac80211/agg-rx.c b/net/mac80211/agg-rx.c index 01b0dad24500..0e1bb43973b8 100644 --- a/net/mac80211/agg-rx.c +++ b/net/mac80211/agg-rx.c @@ -178,17 +178,52 @@ static void sta_rx_agg_reorder_timer_expired(struct timer_list *t) rcu_read_unlock(); } -static void ieee80211_send_addba_resp(struct ieee80211_sub_if_data *sdata, u8 *da, u16 tid, +static void ieee80211_add_addbaext(struct ieee80211_sub_if_data *sdata, + struct sk_buff *skb, + const struct ieee80211_addba_ext_ie *req) +{ + struct ieee80211_supported_band *sband; + struct ieee80211_addba_ext_ie *resp; + const struct ieee80211_sta_he_cap *he_cap; + u8 frag_level, cap_frag_level; + u8 *pos; + + sband = ieee80211_get_sband(sdata); + he_cap = ieee80211_get_he_iftype_cap(sband, sdata->vif.type); + if (!he_cap) + return; + + pos = skb_put_zero(skb, 2 + sizeof(struct ieee80211_addba_ext_ie)); + *pos++ = WLAN_EID_ADDBA_EXT; + *pos++ = sizeof(struct ieee80211_addba_ext_ie); + resp = (struct ieee80211_addba_ext_ie *)pos; + resp->data = req->data & IEEE80211_ADDBA_EXT_NO_FRAG; + + frag_level = u32_get_bits(req->data, + IEEE80211_ADDBA_EXT_FRAG_LEVEL_MASK); + cap_frag_level = u32_get_bits(he_cap->he_cap_elem.mac_cap_info[0], + IEEE80211_HE_MAC_CAP0_DYNAMIC_FRAG_MASK); + if (frag_level > cap_frag_level) + frag_level = cap_frag_level; + resp->data |= u8_encode_bits(frag_level, + IEEE80211_ADDBA_EXT_FRAG_LEVEL_MASK); +} + +static void ieee80211_send_addba_resp(struct sta_info *sta, u8 *da, u16 tid, u8 dialog_token, u16 status, u16 policy, - u16 buf_size, u16 timeout) + u16 buf_size, u16 timeout, + const struct ieee80211_addba_ext_ie *addbaext) { + struct ieee80211_sub_if_data *sdata = sta->sdata; struct ieee80211_local *local = sdata->local; struct sk_buff *skb; struct ieee80211_mgmt *mgmt; bool amsdu = ieee80211_hw_check(&local->hw, SUPPORTS_AMSDU_IN_AMPDU); u16 capab; - skb = dev_alloc_skb(sizeof(*mgmt) + local->hw.extra_tx_headroom); + skb = dev_alloc_skb(sizeof(*mgmt) + + 2 + sizeof(struct ieee80211_addba_ext_ie) + + local->hw.extra_tx_headroom); if (!skb) return; @@ -222,13 +257,17 @@ static void ieee80211_send_addba_resp(struct ieee80211_sub_if_data *sdata, u8 *d mgmt->u.action.u.addba_resp.timeout = cpu_to_le16(timeout); mgmt->u.action.u.addba_resp.status = cpu_to_le16(status); + if (sta->sta.he_cap.has_he && addbaext) + ieee80211_add_addbaext(sdata, skb, addbaext); + ieee80211_tx_skb(sdata, skb); } void ___ieee80211_start_rx_ba_session(struct sta_info *sta, u8 dialog_token, u16 timeout, u16 start_seq_num, u16 ba_policy, u16 tid, - u16 buf_size, bool tx, bool auto_seq) + u16 buf_size, bool tx, bool auto_seq, + const struct ieee80211_addba_ext_ie *addbaext) { struct ieee80211_local *local = sta->sdata->local; struct tid_ampdu_rx *tid_agg_rx; @@ -410,21 +449,22 @@ end: } if (tx) - ieee80211_send_addba_resp(sta->sdata, sta->sta.addr, tid, + ieee80211_send_addba_resp(sta, sta->sta.addr, tid, dialog_token, status, 1, buf_size, - timeout); + timeout, addbaext); } static void __ieee80211_start_rx_ba_session(struct sta_info *sta, u8 dialog_token, u16 timeout, u16 start_seq_num, u16 ba_policy, u16 tid, u16 buf_size, bool tx, - bool auto_seq) + bool auto_seq, + const struct ieee80211_addba_ext_ie *addbaext) { mutex_lock(&sta->ampdu_mlme.mtx); ___ieee80211_start_rx_ba_session(sta, dialog_token, timeout, start_seq_num, ba_policy, tid, - buf_size, tx, auto_seq); + buf_size, tx, auto_seq, addbaext); mutex_unlock(&sta->ampdu_mlme.mtx); } @@ -434,7 +474,9 @@ void ieee80211_process_addba_request(struct ieee80211_local *local, size_t len) { u16 capab, tid, timeout, ba_policy, buf_size, start_seq_num; + struct ieee802_11_elems elems = { 0 }; u8 dialog_token; + int ies_len; /* extract session parameters from addba request frame */ dialog_token = mgmt->u.action.u.addba_req.dialog_token; @@ -447,9 +489,19 @@ void ieee80211_process_addba_request(struct ieee80211_local *local, tid = (capab & IEEE80211_ADDBA_PARAM_TID_MASK) >> 2; buf_size = (capab & IEEE80211_ADDBA_PARAM_BUF_SIZE_MASK) >> 6; + ies_len = len - offsetof(struct ieee80211_mgmt, + u.action.u.addba_req.variable); + if (ies_len) { + ieee802_11_parse_elems(mgmt->u.action.u.addba_req.variable, + ies_len, true, &elems, mgmt->bssid, NULL); + if (elems.parse_error) + return; + } + __ieee80211_start_rx_ba_session(sta, dialog_token, timeout, start_seq_num, ba_policy, tid, - buf_size, true, false); + buf_size, true, false, + elems.addba_ext_ie); } void ieee80211_manage_rx_ba_offl(struct ieee80211_vif *vif, diff --git a/net/mac80211/ht.c b/net/mac80211/ht.c index d5a500b2a448..a2e4d6b8fd98 100644 --- a/net/mac80211/ht.c +++ b/net/mac80211/ht.c @@ -359,7 +359,7 @@ void ieee80211_ba_session_work(struct work_struct *work) sta->ampdu_mlme.tid_rx_manage_offl)) ___ieee80211_start_rx_ba_session(sta, 0, 0, 0, 1, tid, IEEE80211_MAX_AMPDU_BUF_HT, - false, true); + false, true, NULL); if (test_and_clear_bit(tid + IEEE80211_NUM_TIDS, sta->ampdu_mlme.tid_rx_manage_offl)) diff --git a/net/mac80211/ieee80211_i.h b/net/mac80211/ieee80211_i.h index ba1bc245678e..38769f5c3da4 100644 --- a/net/mac80211/ieee80211_i.h +++ b/net/mac80211/ieee80211_i.h @@ -1807,7 +1807,8 @@ void __ieee80211_stop_rx_ba_session(struct sta_info *sta, u16 tid, void ___ieee80211_start_rx_ba_session(struct sta_info *sta, u8 dialog_token, u16 timeout, u16 start_seq_num, u16 ba_policy, u16 tid, - u16 buf_size, bool tx, bool auto_seq); + u16 buf_size, bool tx, bool auto_seq, + const struct ieee80211_addba_ext_ie *addbaext); void ieee80211_sta_tear_down_BA_sessions(struct sta_info *sta, enum ieee80211_agg_stop_reason reason); void ieee80211_process_delba(struct ieee80211_sub_if_data *sdata, -- cgit v1.2.3 From 3b0b278312ba7d6c1eb8b2fb48d459fb7f341a20 Mon Sep 17 00:00:00 2001 From: Andy Shevchenko Date: Mon, 29 Jul 2019 16:35:03 +0300 Subject: NFC: nxp-nci: Get rid of platform data Legacy platform data must go away. We are on the safe side here since there are no users of it in the kernel. If anyone by any odd reason needs it the GPIO lookup tables and built-in device properties at your service. Signed-off-by: Andy Shevchenko Tested-by: Sedat Dilek Signed-off-by: David S. Miller --- MAINTAINERS | 1 - drivers/nfc/nxp-nci/core.c | 1 - drivers/nfc/nxp-nci/i2c.c | 9 +-------- drivers/nfc/nxp-nci/nxp-nci.h | 1 - include/linux/platform_data/nxp-nci.h | 19 ------------------- 5 files changed, 1 insertion(+), 30 deletions(-) delete mode 100644 include/linux/platform_data/nxp-nci.h (limited to 'include/linux') diff --git a/MAINTAINERS b/MAINTAINERS index 9cc156c58f0c..ee663e0e2f2e 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -11327,7 +11327,6 @@ F: include/net/nfc/ F: include/uapi/linux/nfc.h F: drivers/nfc/ F: include/linux/platform_data/nfcmrvl.h -F: include/linux/platform_data/nxp-nci.h F: Documentation/devicetree/bindings/net/nfc/ NFS, SUNRPC, AND LOCKD CLIENTS diff --git a/drivers/nfc/nxp-nci/core.c b/drivers/nfc/nxp-nci/core.c index 8dafc696719f..aed18ca60170 100644 --- a/drivers/nfc/nxp-nci/core.c +++ b/drivers/nfc/nxp-nci/core.c @@ -14,7 +14,6 @@ #include #include #include -#include #include diff --git a/drivers/nfc/nxp-nci/i2c.c b/drivers/nfc/nxp-nci/i2c.c index 5db71869f04b..47b3b7e612e6 100644 --- a/drivers/nfc/nxp-nci/i2c.c +++ b/drivers/nfc/nxp-nci/i2c.c @@ -23,7 +23,6 @@ #include #include #include -#include #include #include @@ -304,7 +303,6 @@ static int nxp_nci_i2c_probe(struct i2c_client *client, const struct i2c_device_id *id) { struct nxp_nci_i2c_phy *phy; - struct nxp_nci_nfc_platform_data *pdata; int r; if (!i2c_check_functionality(client->adapter, I2C_FUNC_I2C)) { @@ -323,17 +321,12 @@ static int nxp_nci_i2c_probe(struct i2c_client *client, phy->i2c_dev = client; i2c_set_clientdata(client, phy); - pdata = client->dev.platform_data; - - if (!pdata && client->dev.of_node) { + if (client->dev.of_node) { r = nxp_nci_i2c_parse_devtree(client); if (r < 0) { nfc_err(&client->dev, "Failed to get DT data\n"); goto probe_exit; } - } else if (pdata) { - phy->gpio_en = pdata->gpio_en; - phy->gpio_fw = pdata->gpio_fw; } else if (ACPI_HANDLE(&client->dev)) { r = nxp_nci_i2c_acpi_config(phy); if (r < 0) diff --git a/drivers/nfc/nxp-nci/nxp-nci.h b/drivers/nfc/nxp-nci/nxp-nci.h index 6fe7c45544bf..ae3fb2735a4e 100644 --- a/drivers/nfc/nxp-nci/nxp-nci.h +++ b/drivers/nfc/nxp-nci/nxp-nci.h @@ -14,7 +14,6 @@ #include #include #include -#include #include diff --git a/include/linux/platform_data/nxp-nci.h b/include/linux/platform_data/nxp-nci.h deleted file mode 100644 index 97827ad468e2..000000000000 --- a/include/linux/platform_data/nxp-nci.h +++ /dev/null @@ -1,19 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0-only */ -/* - * Generic platform data for the NXP NCI NFC chips. - * - * Copyright (C) 2014 NXP Semiconductors All rights reserved. - * - * Authors: Clément Perrochaud - */ - -#ifndef _NXP_NCI_H_ -#define _NXP_NCI_H_ - -struct nxp_nci_nfc_platform_data { - unsigned int gpio_en; - unsigned int gpio_fw; - unsigned int irq; -}; - -#endif /* _NXP_NCI_H_ */ -- cgit v1.2.3 From 6dbff13ca8a2ad2fddd904c2e789dd5e59a8644c Mon Sep 17 00:00:00 2001 From: Toke Høiland-Jørgensen Date: Fri, 26 Jul 2019 18:06:52 +0200 Subject: include/bpf.h: Remove map_insert_ctx() stubs MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit When we changed the device and CPU maps to use linked lists instead of bitmaps, we also removed the need for the map_insert_ctx() helpers to keep track of the bitmaps inside each map. However, it seems I forgot to remove the function definitions stubs, so remove those here. Signed-off-by: Toke Høiland-Jørgensen Acked-by: Yonghong Song Acked-by: Jesper Dangaard Brouer Signed-off-by: Alexei Starovoitov --- include/linux/bpf.h | 10 ---------- 1 file changed, 10 deletions(-) (limited to 'include/linux') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 18f4cc2c6acd..bfdb54dd2ad1 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -713,7 +713,6 @@ struct xdp_buff; struct sk_buff; struct bpf_dtab_netdev *__dev_map_lookup_elem(struct bpf_map *map, u32 key); -void __dev_map_insert_ctx(struct bpf_map *map, u32 index); void __dev_map_flush(struct bpf_map *map); int dev_map_enqueue(struct bpf_dtab_netdev *dst, struct xdp_buff *xdp, struct net_device *dev_rx); @@ -721,7 +720,6 @@ int dev_map_generic_redirect(struct bpf_dtab_netdev *dst, struct sk_buff *skb, struct bpf_prog *xdp_prog); struct bpf_cpu_map_entry *__cpu_map_lookup_elem(struct bpf_map *map, u32 key); -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); @@ -801,10 +799,6 @@ static inline struct net_device *__dev_map_lookup_elem(struct bpf_map *map, return NULL; } -static inline void __dev_map_insert_ctx(struct bpf_map *map, u32 index) -{ -} - static inline void __dev_map_flush(struct bpf_map *map) { } @@ -834,10 +828,6 @@ struct bpf_cpu_map_entry *__cpu_map_lookup_elem(struct bpf_map *map, u32 key) return NULL; } -static inline void __cpu_map_insert_ctx(struct bpf_map *map, u32 index) -{ -} - static inline void __cpu_map_flush(struct bpf_map *map) { } -- cgit v1.2.3 From 6f9d451ab1a33728adb72d7ff66a7b374d665176 Mon Sep 17 00:00:00 2001 From: Toke Høiland-Jørgensen Date: Fri, 26 Jul 2019 18:06:55 +0200 Subject: xdp: Add devmap_hash map type for looking up devices by hashed index MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit A common pattern when using xdp_redirect_map() is to create a device map where the lookup key is simply ifindex. Because device maps are arrays, this leaves holes in the map, and the map has to be sized to fit the largest ifindex, regardless of how many devices actually are actually needed in the map. This patch adds a second type of device map where the key is looked up using a hashmap, instead of being used as an array index. This allows maps to be densely packed, so they can be smaller. Signed-off-by: Toke Høiland-Jørgensen Acked-by: Yonghong Song Acked-by: Jesper Dangaard Brouer Signed-off-by: Alexei Starovoitov --- include/linux/bpf.h | 7 ++ include/linux/bpf_types.h | 1 + include/trace/events/xdp.h | 3 +- include/uapi/linux/bpf.h | 1 + kernel/bpf/devmap.c | 200 +++++++++++++++++++++++++++++++++++++++++++++ kernel/bpf/verifier.c | 2 + net/core/filter.c | 9 +- 7 files changed, 220 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index bfdb54dd2ad1..f9a506147c8a 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -713,6 +713,7 @@ struct xdp_buff; struct sk_buff; struct bpf_dtab_netdev *__dev_map_lookup_elem(struct bpf_map *map, u32 key); +struct bpf_dtab_netdev *__dev_map_hash_lookup_elem(struct bpf_map *map, u32 key); void __dev_map_flush(struct bpf_map *map); int dev_map_enqueue(struct bpf_dtab_netdev *dst, struct xdp_buff *xdp, struct net_device *dev_rx); @@ -799,6 +800,12 @@ static inline struct net_device *__dev_map_lookup_elem(struct bpf_map *map, return NULL; } +static inline struct net_device *__dev_map_hash_lookup_elem(struct bpf_map *map, + u32 key) +{ + return NULL; +} + static inline void __dev_map_flush(struct bpf_map *map) { } diff --git a/include/linux/bpf_types.h b/include/linux/bpf_types.h index eec5aeeeaf92..36a9c2325176 100644 --- a/include/linux/bpf_types.h +++ b/include/linux/bpf_types.h @@ -62,6 +62,7 @@ BPF_MAP_TYPE(BPF_MAP_TYPE_ARRAY_OF_MAPS, array_of_maps_map_ops) BPF_MAP_TYPE(BPF_MAP_TYPE_HASH_OF_MAPS, htab_of_maps_map_ops) #ifdef CONFIG_NET BPF_MAP_TYPE(BPF_MAP_TYPE_DEVMAP, dev_map_ops) +BPF_MAP_TYPE(BPF_MAP_TYPE_DEVMAP_HASH, dev_map_hash_ops) BPF_MAP_TYPE(BPF_MAP_TYPE_SK_STORAGE, sk_storage_map_ops) #if defined(CONFIG_BPF_STREAM_PARSER) BPF_MAP_TYPE(BPF_MAP_TYPE_SOCKMAP, sock_map_ops) diff --git a/include/trace/events/xdp.h b/include/trace/events/xdp.h index 68899fdc985b..8c8420230a10 100644 --- a/include/trace/events/xdp.h +++ b/include/trace/events/xdp.h @@ -175,7 +175,8 @@ struct _bpf_dtab_netdev { #endif /* __DEVMAP_OBJ_TYPE */ #define devmap_ifindex(fwd, map) \ - ((map->map_type == BPF_MAP_TYPE_DEVMAP) ? \ + ((map->map_type == BPF_MAP_TYPE_DEVMAP || \ + map->map_type == BPF_MAP_TYPE_DEVMAP_HASH) ? \ ((struct _bpf_dtab_netdev *)fwd)->dev->ifindex : 0) #define _trace_xdp_redirect_map(dev, xdp, fwd, map, idx) \ diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index e985f07a98ed..6bbef0c7f585 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -134,6 +134,7 @@ enum bpf_map_type { BPF_MAP_TYPE_QUEUE, BPF_MAP_TYPE_STACK, BPF_MAP_TYPE_SK_STORAGE, + BPF_MAP_TYPE_DEVMAP_HASH, }; /* Note that tracing related programs such as diff --git a/kernel/bpf/devmap.c b/kernel/bpf/devmap.c index a0501266bdb8..9af048a932b5 100644 --- a/kernel/bpf/devmap.c +++ b/kernel/bpf/devmap.c @@ -37,6 +37,12 @@ * notifier hook walks the map we know that new dev references can not be * added by the user because core infrastructure ensures dev_get_by_index() * calls will fail at this point. + * + * The devmap_hash type is a map type which interprets keys as ifindexes and + * indexes these using a hashmap. This allows maps that use ifindex as key to be + * densely packed instead of having holes in the lookup array for unused + * ifindexes. The setup and packet enqueue/send code is shared between the two + * types of devmap; only the lookup and insertion is different. */ #include #include @@ -59,6 +65,7 @@ struct xdp_bulk_queue { struct bpf_dtab_netdev { struct net_device *dev; /* must be first member, due to tracepoint */ + struct hlist_node index_hlist; struct bpf_dtab *dtab; struct xdp_bulk_queue __percpu *bulkq; struct rcu_head rcu; @@ -70,11 +77,30 @@ struct bpf_dtab { struct bpf_dtab_netdev **netdev_map; struct list_head __percpu *flush_list; struct list_head list; + + /* these are only used for DEVMAP_HASH type maps */ + struct hlist_head *dev_index_head; + spinlock_t index_lock; + unsigned int items; + u32 n_buckets; }; static DEFINE_SPINLOCK(dev_map_lock); static LIST_HEAD(dev_map_list); +static struct hlist_head *dev_map_create_hash(unsigned int entries) +{ + int i; + struct hlist_head *hash; + + hash = kmalloc_array(entries, sizeof(*hash), GFP_KERNEL); + if (hash != NULL) + for (i = 0; i < entries; i++) + INIT_HLIST_HEAD(&hash[i]); + + return hash; +} + static int dev_map_init_map(struct bpf_dtab *dtab, union bpf_attr *attr) { int err, cpu; @@ -97,6 +123,14 @@ static int dev_map_init_map(struct bpf_dtab *dtab, union bpf_attr *attr) cost = (u64) dtab->map.max_entries * sizeof(struct bpf_dtab_netdev *); cost += sizeof(struct list_head) * num_possible_cpus(); + if (attr->map_type == BPF_MAP_TYPE_DEVMAP_HASH) { + dtab->n_buckets = roundup_pow_of_two(dtab->map.max_entries); + + if (!dtab->n_buckets) /* Overflow check */ + return -EINVAL; + cost += sizeof(struct hlist_head) * dtab->n_buckets; + } + /* if map size is larger than memlock limit, reject it */ err = bpf_map_charge_init(&dtab->map.memory, cost); if (err) @@ -115,8 +149,18 @@ static int dev_map_init_map(struct bpf_dtab *dtab, union bpf_attr *attr) if (!dtab->netdev_map) goto free_percpu; + if (attr->map_type == BPF_MAP_TYPE_DEVMAP_HASH) { + dtab->dev_index_head = dev_map_create_hash(dtab->n_buckets); + if (!dtab->dev_index_head) + goto free_map_area; + + spin_lock_init(&dtab->index_lock); + } + return 0; +free_map_area: + bpf_map_area_free(dtab->netdev_map); free_percpu: free_percpu(dtab->flush_list); free_charge: @@ -198,6 +242,7 @@ static void dev_map_free(struct bpf_map *map) free_percpu(dtab->flush_list); bpf_map_area_free(dtab->netdev_map); + kfree(dtab->dev_index_head); kfree(dtab); } @@ -218,6 +263,70 @@ static int dev_map_get_next_key(struct bpf_map *map, void *key, void *next_key) return 0; } +static inline struct hlist_head *dev_map_index_hash(struct bpf_dtab *dtab, + int idx) +{ + return &dtab->dev_index_head[idx & (dtab->n_buckets - 1)]; +} + +struct bpf_dtab_netdev *__dev_map_hash_lookup_elem(struct bpf_map *map, u32 key) +{ + struct bpf_dtab *dtab = container_of(map, struct bpf_dtab, map); + struct hlist_head *head = dev_map_index_hash(dtab, key); + struct bpf_dtab_netdev *dev; + + hlist_for_each_entry_rcu(dev, head, index_hlist) + if (dev->idx == key) + return dev; + + return NULL; +} + +static int dev_map_hash_get_next_key(struct bpf_map *map, void *key, + void *next_key) +{ + struct bpf_dtab *dtab = container_of(map, struct bpf_dtab, map); + u32 idx, *next = next_key; + struct bpf_dtab_netdev *dev, *next_dev; + struct hlist_head *head; + int i = 0; + + if (!key) + goto find_first; + + idx = *(u32 *)key; + + dev = __dev_map_hash_lookup_elem(map, idx); + if (!dev) + goto find_first; + + next_dev = hlist_entry_safe(rcu_dereference_raw(hlist_next_rcu(&dev->index_hlist)), + struct bpf_dtab_netdev, index_hlist); + + if (next_dev) { + *next = next_dev->idx; + return 0; + } + + i = idx & (dtab->n_buckets - 1); + i++; + + find_first: + for (; i < dtab->n_buckets; i++) { + head = dev_map_index_hash(dtab, i); + + next_dev = hlist_entry_safe(rcu_dereference_raw(hlist_first_rcu(head)), + struct bpf_dtab_netdev, + index_hlist); + if (next_dev) { + *next = next_dev->idx; + return 0; + } + } + + return -ENOENT; +} + static int bq_xmit_all(struct xdp_bulk_queue *bq, u32 flags, bool in_napi_ctx) { @@ -373,6 +482,15 @@ static void *dev_map_lookup_elem(struct bpf_map *map, void *key) return dev ? &dev->ifindex : NULL; } +static void *dev_map_hash_lookup_elem(struct bpf_map *map, void *key) +{ + struct bpf_dtab_netdev *obj = __dev_map_hash_lookup_elem(map, + *(u32 *)key); + struct net_device *dev = obj ? obj->dev : NULL; + + return dev ? &dev->ifindex : NULL; +} + static void dev_map_flush_old(struct bpf_dtab_netdev *dev) { if (dev->dev->netdev_ops->ndo_xdp_xmit) { @@ -422,6 +540,28 @@ static int dev_map_delete_elem(struct bpf_map *map, void *key) return 0; } +static int dev_map_hash_delete_elem(struct bpf_map *map, void *key) +{ + struct bpf_dtab *dtab = container_of(map, struct bpf_dtab, map); + struct bpf_dtab_netdev *old_dev; + int k = *(u32 *)key; + unsigned long flags; + int ret = -ENOENT; + + spin_lock_irqsave(&dtab->index_lock, flags); + + old_dev = __dev_map_hash_lookup_elem(map, k); + if (old_dev) { + dtab->items--; + hlist_del_init_rcu(&old_dev->index_hlist); + call_rcu(&old_dev->rcu, __dev_map_entry_free); + ret = 0; + } + spin_unlock_irqrestore(&dtab->index_lock, flags); + + return ret; +} + static struct bpf_dtab_netdev *__dev_map_alloc_node(struct net *net, struct bpf_dtab *dtab, u32 ifindex, @@ -502,6 +642,56 @@ static int dev_map_update_elem(struct bpf_map *map, void *key, void *value, map, key, value, map_flags); } +static int __dev_map_hash_update_elem(struct net *net, struct bpf_map *map, + void *key, void *value, u64 map_flags) +{ + struct bpf_dtab *dtab = container_of(map, struct bpf_dtab, map); + struct bpf_dtab_netdev *dev, *old_dev; + u32 ifindex = *(u32 *)value; + u32 idx = *(u32 *)key; + unsigned long flags; + + if (unlikely(map_flags > BPF_EXIST || !ifindex)) + return -EINVAL; + + old_dev = __dev_map_hash_lookup_elem(map, idx); + if (old_dev && (map_flags & BPF_NOEXIST)) + return -EEXIST; + + dev = __dev_map_alloc_node(net, dtab, ifindex, idx); + if (IS_ERR(dev)) + return PTR_ERR(dev); + + spin_lock_irqsave(&dtab->index_lock, flags); + + if (old_dev) { + hlist_del_rcu(&old_dev->index_hlist); + } else { + if (dtab->items >= dtab->map.max_entries) { + spin_unlock_irqrestore(&dtab->index_lock, flags); + call_rcu(&dev->rcu, __dev_map_entry_free); + return -E2BIG; + } + dtab->items++; + } + + hlist_add_head_rcu(&dev->index_hlist, + dev_map_index_hash(dtab, idx)); + spin_unlock_irqrestore(&dtab->index_lock, flags); + + if (old_dev) + call_rcu(&old_dev->rcu, __dev_map_entry_free); + + return 0; +} + +static int dev_map_hash_update_elem(struct bpf_map *map, void *key, void *value, + u64 map_flags) +{ + return __dev_map_hash_update_elem(current->nsproxy->net_ns, + map, key, value, map_flags); +} + const struct bpf_map_ops dev_map_ops = { .map_alloc = dev_map_alloc, .map_free = dev_map_free, @@ -512,6 +702,16 @@ const struct bpf_map_ops dev_map_ops = { .map_check_btf = map_check_no_btf, }; +const struct bpf_map_ops dev_map_hash_ops = { + .map_alloc = dev_map_alloc, + .map_free = dev_map_free, + .map_get_next_key = dev_map_hash_get_next_key, + .map_lookup_elem = dev_map_hash_lookup_elem, + .map_update_elem = dev_map_hash_update_elem, + .map_delete_elem = dev_map_hash_delete_elem, + .map_check_btf = map_check_no_btf, +}; + static int dev_map_notification(struct notifier_block *notifier, ulong event, void *ptr) { diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index 5900cbb966b1..cef851cd5c36 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -3457,6 +3457,7 @@ static int check_map_func_compatibility(struct bpf_verifier_env *env, goto error; break; case BPF_MAP_TYPE_DEVMAP: + case BPF_MAP_TYPE_DEVMAP_HASH: if (func_id != BPF_FUNC_redirect_map && func_id != BPF_FUNC_map_lookup_elem) goto error; @@ -3539,6 +3540,7 @@ static int check_map_func_compatibility(struct bpf_verifier_env *env, break; case BPF_FUNC_redirect_map: if (map->map_type != BPF_MAP_TYPE_DEVMAP && + map->map_type != BPF_MAP_TYPE_DEVMAP_HASH && map->map_type != BPF_MAP_TYPE_CPUMAP && map->map_type != BPF_MAP_TYPE_XSKMAP) goto error; diff --git a/net/core/filter.c b/net/core/filter.c index 3961437ccc50..1eee70f80fba 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -3517,7 +3517,8 @@ static int __bpf_tx_xdp_map(struct net_device *dev_rx, void *fwd, int err; switch (map->map_type) { - case BPF_MAP_TYPE_DEVMAP: { + case BPF_MAP_TYPE_DEVMAP: + case BPF_MAP_TYPE_DEVMAP_HASH: { struct bpf_dtab_netdev *dst = fwd; err = dev_map_enqueue(dst, xdp, dev_rx); @@ -3554,6 +3555,7 @@ void xdp_do_flush_map(void) if (map) { switch (map->map_type) { case BPF_MAP_TYPE_DEVMAP: + case BPF_MAP_TYPE_DEVMAP_HASH: __dev_map_flush(map); break; case BPF_MAP_TYPE_CPUMAP: @@ -3574,6 +3576,8 @@ static inline void *__xdp_map_lookup_elem(struct bpf_map *map, u32 index) switch (map->map_type) { case BPF_MAP_TYPE_DEVMAP: return __dev_map_lookup_elem(map, index); + case BPF_MAP_TYPE_DEVMAP_HASH: + return __dev_map_hash_lookup_elem(map, index); case BPF_MAP_TYPE_CPUMAP: return __cpu_map_lookup_elem(map, index); case BPF_MAP_TYPE_XSKMAP: @@ -3655,7 +3659,8 @@ static int xdp_do_generic_redirect_map(struct net_device *dev, ri->tgt_value = NULL; WRITE_ONCE(ri->map, NULL); - if (map->map_type == BPF_MAP_TYPE_DEVMAP) { + if (map->map_type == BPF_MAP_TYPE_DEVMAP || + map->map_type == BPF_MAP_TYPE_DEVMAP_HASH) { struct bpf_dtab_netdev *dst = fwd; err = dev_map_generic_redirect(dst, skb, xdp_prog); -- cgit v1.2.3 From 7240b60c98d6309363a9f8d5a4ecd5b0626f2aff Mon Sep 17 00:00:00 2001 From: Jonathan Lemon Date: Tue, 30 Jul 2019 07:40:32 -0700 Subject: linux: Add skb_frag_t page_offset accessors Add skb_frag_off(), skb_frag_off_add(), skb_frag_off_set(), and skb_frag_off_copy() accessors for page_offset. Signed-off-by: Jonathan Lemon Signed-off-by: David S. Miller --- include/linux/skbuff.h | 67 ++++++++++++++++++++++++++++++++++++++++++++------ 1 file changed, 59 insertions(+), 8 deletions(-) (limited to 'include/linux') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 718742b1c505..2957cdd6c032 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -312,7 +312,7 @@ extern int sysctl_max_skb_frags; typedef struct bio_vec skb_frag_t; /** - * skb_frag_size - Returns the size of a skb fragment + * skb_frag_size() - Returns the size of a skb fragment * @frag: skb fragment */ static inline unsigned int skb_frag_size(const skb_frag_t *frag) @@ -321,7 +321,7 @@ static inline unsigned int skb_frag_size(const skb_frag_t *frag) } /** - * skb_frag_size_set - Sets the size of a skb fragment + * skb_frag_size_set() - Sets the size of a skb fragment * @frag: skb fragment * @size: size of fragment */ @@ -331,7 +331,7 @@ static inline void skb_frag_size_set(skb_frag_t *frag, unsigned int size) } /** - * skb_frag_size_add - Incrementes the size of a skb fragment by %delta + * skb_frag_size_add() - Increments the size of a skb fragment by @delta * @frag: skb fragment * @delta: value to add */ @@ -341,7 +341,7 @@ static inline void skb_frag_size_add(skb_frag_t *frag, int delta) } /** - * skb_frag_size_sub - Decrements the size of a skb fragment by %delta + * skb_frag_size_sub() - Decrements the size of a skb fragment by @delta * @frag: skb fragment * @delta: value to subtract */ @@ -2857,6 +2857,46 @@ static inline void skb_propagate_pfmemalloc(struct page *page, skb->pfmemalloc = true; } +/** + * skb_frag_off() - Returns the offset of a skb fragment + * @frag: the paged fragment + */ +static inline unsigned int skb_frag_off(const skb_frag_t *frag) +{ + return frag->page_offset; +} + +/** + * skb_frag_off_add() - Increments the offset of a skb fragment by @delta + * @frag: skb fragment + * @delta: value to add + */ +static inline void skb_frag_off_add(skb_frag_t *frag, int delta) +{ + frag->page_offset += delta; +} + +/** + * skb_frag_off_set() - Sets the offset of a skb fragment + * @frag: skb fragment + * @offset: offset of fragment + */ +static inline void skb_frag_off_set(skb_frag_t *frag, unsigned int offset) +{ + frag->page_offset = offset; +} + +/** + * skb_frag_off_copy() - Sets the offset of a skb fragment from another fragment + * @fragto: skb fragment where offset is set + * @fragfrom: skb fragment offset is copied from + */ +static inline void skb_frag_off_copy(skb_frag_t *fragto, + const skb_frag_t *fragfrom) +{ + fragto->page_offset = fragfrom->page_offset; +} + /** * skb_frag_page - retrieve the page referred to by a paged fragment * @frag: the paged fragment @@ -2923,7 +2963,7 @@ static inline void skb_frag_unref(struct sk_buff *skb, int f) */ static inline void *skb_frag_address(const skb_frag_t *frag) { - return page_address(skb_frag_page(frag)) + frag->page_offset; + return page_address(skb_frag_page(frag)) + skb_frag_off(frag); } /** @@ -2939,7 +2979,18 @@ static inline void *skb_frag_address_safe(const skb_frag_t *frag) if (unlikely(!ptr)) return NULL; - return ptr + frag->page_offset; + return ptr + skb_frag_off(frag); +} + +/** + * skb_frag_page_copy() - sets the page in a fragment from another fragment + * @fragto: skb fragment where page is set + * @fragfrom: skb fragment page is copied from + */ +static inline void skb_frag_page_copy(skb_frag_t *fragto, + const skb_frag_t *fragfrom) +{ + fragto->bv_page = fragfrom->bv_page; } /** @@ -2987,7 +3038,7 @@ static inline dma_addr_t skb_frag_dma_map(struct device *dev, enum dma_data_direction dir) { return dma_map_page(dev, skb_frag_page(frag), - frag->page_offset + offset, size, dir); + skb_frag_off(frag) + offset, size, dir); } static inline struct sk_buff *pskb_copy(struct sk_buff *skb, @@ -3157,7 +3208,7 @@ static inline bool skb_can_coalesce(struct sk_buff *skb, int i, const skb_frag_t *frag = &skb_shinfo(skb)->frags[i - 1]; return page == skb_frag_page(frag) && - off == frag->page_offset + skb_frag_size(frag); + off == skb_frag_off(frag) + skb_frag_size(frag); } return false; } -- cgit v1.2.3 From 65c84f148e359ed398dcc9ed736131103f40896b Mon Sep 17 00:00:00 2001 From: Jonathan Lemon Date: Tue, 30 Jul 2019 07:40:34 -0700 Subject: linux: Remove bvec page_offset, use bv_offset Now that page_offset is referenced through accessors, remove the union, and use bv_offset. Signed-off-by: Jonathan Lemon Signed-off-by: David S. Miller --- include/linux/bvec.h | 5 +---- include/linux/skbuff.h | 10 +++++----- 2 files changed, 6 insertions(+), 9 deletions(-) (limited to 'include/linux') diff --git a/include/linux/bvec.h b/include/linux/bvec.h index 7f2b2ea9399c..a032f01e928c 100644 --- a/include/linux/bvec.h +++ b/include/linux/bvec.h @@ -18,10 +18,7 @@ struct bio_vec { struct page *bv_page; unsigned int bv_len; - union { - __u32 page_offset; - unsigned int bv_offset; - }; + unsigned int bv_offset; }; struct bvec_iter { diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 2957cdd6c032..3aef8d82ea59 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -2078,7 +2078,7 @@ static inline void __skb_fill_page_desc(struct sk_buff *skb, int i, * on page_is_pfmemalloc doing the right thing(tm). */ frag->bv_page = page; - frag->page_offset = off; + frag->bv_offset = off; skb_frag_size_set(frag, size); page = compound_head(page); @@ -2863,7 +2863,7 @@ static inline void skb_propagate_pfmemalloc(struct page *page, */ static inline unsigned int skb_frag_off(const skb_frag_t *frag) { - return frag->page_offset; + return frag->bv_offset; } /** @@ -2873,7 +2873,7 @@ static inline unsigned int skb_frag_off(const skb_frag_t *frag) */ static inline void skb_frag_off_add(skb_frag_t *frag, int delta) { - frag->page_offset += delta; + frag->bv_offset += delta; } /** @@ -2883,7 +2883,7 @@ static inline void skb_frag_off_add(skb_frag_t *frag, int delta) */ static inline void skb_frag_off_set(skb_frag_t *frag, unsigned int offset) { - frag->page_offset = offset; + frag->bv_offset = offset; } /** @@ -2894,7 +2894,7 @@ static inline void skb_frag_off_set(skb_frag_t *frag, unsigned int offset) static inline void skb_frag_off_copy(skb_frag_t *fragto, const skb_frag_t *fragfrom) { - fragto->page_offset = fragfrom->page_offset; + fragto->bv_offset = fragfrom->bv_offset; } /** -- cgit v1.2.3 From 473c7391ce731adb482c03e420964676ed8b494d Mon Sep 17 00:00:00 2001 From: Stefano Garzarella Date: Tue, 30 Jul 2019 17:43:30 +0200 Subject: vsock/virtio: limit the memory used per-socket Since virtio-vsock was introduced, the buffers filled by the host and pushed to the guest using the vring, are directly queued in a per-socket list. These buffers are preallocated by the guest with a fixed size (4 KB). The maximum amount of memory used by each socket should be controlled by the credit mechanism. The default credit available per-socket is 256 KB, but if we use only 1 byte per packet, the guest can queue up to 262144 of 4 KB buffers, using up to 1 GB of memory per-socket. In addition, the guest will continue to fill the vring with new 4 KB free buffers to avoid starvation of other sockets. This patch mitigates this issue copying the payload of small packets (< 128 bytes) into the buffer of last packet queued, in order to avoid wasting memory. Signed-off-by: Stefano Garzarella Reviewed-by: Stefan Hajnoczi Acked-by: Michael S. Tsirkin Signed-off-by: David S. Miller --- drivers/vhost/vsock.c | 2 ++ include/linux/virtio_vsock.h | 1 + net/vmw_vsock/virtio_transport.c | 1 + net/vmw_vsock/virtio_transport_common.c | 60 ++++++++++++++++++++++++++++----- 4 files changed, 55 insertions(+), 9 deletions(-) (limited to 'include/linux') diff --git a/drivers/vhost/vsock.c b/drivers/vhost/vsock.c index 6a50e1d0529c..6c8390a2af52 100644 --- a/drivers/vhost/vsock.c +++ b/drivers/vhost/vsock.c @@ -329,6 +329,8 @@ vhost_vsock_alloc_pkt(struct vhost_virtqueue *vq, return NULL; } + pkt->buf_len = pkt->len; + nbytes = copy_from_iter(pkt->buf, pkt->len, &iov_iter); if (nbytes != pkt->len) { vq_err(vq, "Expected %u byte payload, got %zu bytes\n", diff --git a/include/linux/virtio_vsock.h b/include/linux/virtio_vsock.h index e223e2632edd..7d973903f52e 100644 --- a/include/linux/virtio_vsock.h +++ b/include/linux/virtio_vsock.h @@ -52,6 +52,7 @@ struct virtio_vsock_pkt { /* socket refcnt not held, only use for cancellation */ struct vsock_sock *vsk; void *buf; + u32 buf_len; u32 len; u32 off; bool reply; diff --git a/net/vmw_vsock/virtio_transport.c b/net/vmw_vsock/virtio_transport.c index 0815d1357861..082a30936690 100644 --- a/net/vmw_vsock/virtio_transport.c +++ b/net/vmw_vsock/virtio_transport.c @@ -307,6 +307,7 @@ static void virtio_vsock_rx_fill(struct virtio_vsock *vsock) break; } + pkt->buf_len = buf_len; pkt->len = buf_len; sg_init_one(&hdr, &pkt->hdr, sizeof(pkt->hdr)); diff --git a/net/vmw_vsock/virtio_transport_common.c b/net/vmw_vsock/virtio_transport_common.c index 6f1a8aff65c5..095221f94786 100644 --- a/net/vmw_vsock/virtio_transport_common.c +++ b/net/vmw_vsock/virtio_transport_common.c @@ -26,6 +26,9 @@ /* How long to wait for graceful shutdown of a connection */ #define VSOCK_CLOSE_TIMEOUT (8 * HZ) +/* Threshold for detecting small packets to copy */ +#define GOOD_COPY_LEN 128 + static const struct virtio_transport *virtio_transport_get_ops(void) { const struct vsock_transport *t = vsock_core_get_transport(); @@ -64,6 +67,9 @@ virtio_transport_alloc_pkt(struct virtio_vsock_pkt_info *info, pkt->buf = kmalloc(len, GFP_KERNEL); if (!pkt->buf) goto out_pkt; + + pkt->buf_len = len; + err = memcpy_from_msg(pkt->buf, info->msg, len); if (err) goto out; @@ -841,24 +847,60 @@ destroy: return err; } +static void +virtio_transport_recv_enqueue(struct vsock_sock *vsk, + struct virtio_vsock_pkt *pkt) +{ + struct virtio_vsock_sock *vvs = vsk->trans; + bool free_pkt = false; + + pkt->len = le32_to_cpu(pkt->hdr.len); + pkt->off = 0; + + spin_lock_bh(&vvs->rx_lock); + + virtio_transport_inc_rx_pkt(vvs, pkt); + + /* Try to copy small packets into the buffer of last packet queued, + * to avoid wasting memory queueing the entire buffer with a small + * payload. + */ + if (pkt->len <= GOOD_COPY_LEN && !list_empty(&vvs->rx_queue)) { + struct virtio_vsock_pkt *last_pkt; + + last_pkt = list_last_entry(&vvs->rx_queue, + struct virtio_vsock_pkt, list); + + /* If there is space in the last packet queued, we copy the + * new packet in its buffer. + */ + if (pkt->len <= last_pkt->buf_len - last_pkt->len) { + memcpy(last_pkt->buf + last_pkt->len, pkt->buf, + pkt->len); + last_pkt->len += pkt->len; + free_pkt = true; + goto out; + } + } + + list_add_tail(&pkt->list, &vvs->rx_queue); + +out: + spin_unlock_bh(&vvs->rx_lock); + if (free_pkt) + virtio_transport_free_pkt(pkt); +} + static int virtio_transport_recv_connected(struct sock *sk, struct virtio_vsock_pkt *pkt) { struct vsock_sock *vsk = vsock_sk(sk); - struct virtio_vsock_sock *vvs = vsk->trans; int err = 0; switch (le16_to_cpu(pkt->hdr.op)) { case VIRTIO_VSOCK_OP_RW: - pkt->len = le32_to_cpu(pkt->hdr.len); - pkt->off = 0; - - spin_lock_bh(&vvs->rx_lock); - virtio_transport_inc_rx_pkt(vvs, pkt); - list_add_tail(&pkt->list, &vvs->rx_queue); - spin_unlock_bh(&vvs->rx_lock); - + virtio_transport_recv_enqueue(vsk, pkt); sk->sk_data_ready(sk); return err; case VIRTIO_VSOCK_OP_CREDIT_UPDATE: -- cgit v1.2.3 From b89d882dc9fc279c8acbf1df71d51b22394186d5 Mon Sep 17 00:00:00 2001 From: Stefano Garzarella Date: Tue, 30 Jul 2019 17:43:31 +0200 Subject: vsock/virtio: reduce credit update messages In order to reduce the number of credit update messages, we send them only when the space available seen by the transmitter is less than VIRTIO_VSOCK_MAX_PKT_BUF_SIZE. Signed-off-by: Stefano Garzarella Reviewed-by: Stefan Hajnoczi Acked-by: Michael S. Tsirkin Signed-off-by: David S. Miller --- include/linux/virtio_vsock.h | 1 + net/vmw_vsock/virtio_transport_common.c | 16 +++++++++++++--- 2 files changed, 14 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/virtio_vsock.h b/include/linux/virtio_vsock.h index 7d973903f52e..49fc9d20bc43 100644 --- a/include/linux/virtio_vsock.h +++ b/include/linux/virtio_vsock.h @@ -41,6 +41,7 @@ struct virtio_vsock_sock { /* Protected by rx_lock */ u32 fwd_cnt; + u32 last_fwd_cnt; u32 rx_bytes; struct list_head rx_queue; }; diff --git a/net/vmw_vsock/virtio_transport_common.c b/net/vmw_vsock/virtio_transport_common.c index 095221f94786..a85559d4d974 100644 --- a/net/vmw_vsock/virtio_transport_common.c +++ b/net/vmw_vsock/virtio_transport_common.c @@ -211,6 +211,7 @@ static void virtio_transport_dec_rx_pkt(struct virtio_vsock_sock *vvs, void virtio_transport_inc_tx_pkt(struct virtio_vsock_sock *vvs, struct virtio_vsock_pkt *pkt) { spin_lock_bh(&vvs->tx_lock); + vvs->last_fwd_cnt = vvs->fwd_cnt; pkt->hdr.fwd_cnt = cpu_to_le32(vvs->fwd_cnt); pkt->hdr.buf_alloc = cpu_to_le32(vvs->buf_alloc); spin_unlock_bh(&vvs->tx_lock); @@ -261,6 +262,7 @@ virtio_transport_stream_do_dequeue(struct vsock_sock *vsk, struct virtio_vsock_sock *vvs = vsk->trans; struct virtio_vsock_pkt *pkt; size_t bytes, total = 0; + u32 free_space; int err = -EFAULT; spin_lock_bh(&vvs->rx_lock); @@ -291,11 +293,19 @@ virtio_transport_stream_do_dequeue(struct vsock_sock *vsk, virtio_transport_free_pkt(pkt); } } + + free_space = vvs->buf_alloc - (vvs->fwd_cnt - vvs->last_fwd_cnt); + spin_unlock_bh(&vvs->rx_lock); - /* Send a credit pkt to peer */ - virtio_transport_send_credit_update(vsk, VIRTIO_VSOCK_TYPE_STREAM, - NULL); + /* We send a credit update only when the space available seen + * by the transmitter is less than VIRTIO_VSOCK_MAX_PKT_BUF_SIZE + */ + if (free_space < VIRTIO_VSOCK_MAX_PKT_BUF_SIZE) { + virtio_transport_send_credit_update(vsk, + VIRTIO_VSOCK_TYPE_STREAM, + NULL); + } return total; -- cgit v1.2.3 From 9632e9f61bc4191411c47933abe5f2d93c578f5e Mon Sep 17 00:00:00 2001 From: Stefano Garzarella Date: Tue, 30 Jul 2019 17:43:32 +0200 Subject: vsock/virtio: fix locking in virtio_transport_inc_tx_pkt() fwd_cnt and last_fwd_cnt are protected by rx_lock, so we should use the same spinlock also if we are in the TX path. Move also buf_alloc under the same lock. Signed-off-by: Stefano Garzarella Reviewed-by: Stefan Hajnoczi Acked-by: Michael S. Tsirkin Signed-off-by: David S. Miller --- include/linux/virtio_vsock.h | 2 +- net/vmw_vsock/virtio_transport_common.c | 4 ++-- 2 files changed, 3 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/virtio_vsock.h b/include/linux/virtio_vsock.h index 49fc9d20bc43..4c7781f4b29b 100644 --- a/include/linux/virtio_vsock.h +++ b/include/linux/virtio_vsock.h @@ -35,7 +35,6 @@ struct virtio_vsock_sock { /* Protected by tx_lock */ u32 tx_cnt; - u32 buf_alloc; u32 peer_fwd_cnt; u32 peer_buf_alloc; @@ -43,6 +42,7 @@ struct virtio_vsock_sock { u32 fwd_cnt; u32 last_fwd_cnt; u32 rx_bytes; + u32 buf_alloc; struct list_head rx_queue; }; diff --git a/net/vmw_vsock/virtio_transport_common.c b/net/vmw_vsock/virtio_transport_common.c index a85559d4d974..34a2b42313b7 100644 --- a/net/vmw_vsock/virtio_transport_common.c +++ b/net/vmw_vsock/virtio_transport_common.c @@ -210,11 +210,11 @@ static void virtio_transport_dec_rx_pkt(struct virtio_vsock_sock *vvs, void virtio_transport_inc_tx_pkt(struct virtio_vsock_sock *vvs, struct virtio_vsock_pkt *pkt) { - spin_lock_bh(&vvs->tx_lock); + spin_lock_bh(&vvs->rx_lock); vvs->last_fwd_cnt = vvs->fwd_cnt; pkt->hdr.fwd_cnt = cpu_to_le32(vvs->fwd_cnt); pkt->hdr.buf_alloc = cpu_to_le32(vvs->buf_alloc); - spin_unlock_bh(&vvs->tx_lock); + spin_unlock_bh(&vvs->rx_lock); } EXPORT_SYMBOL_GPL(virtio_transport_inc_tx_pkt); -- cgit v1.2.3 From 6f06e04b67baa1c9da61c8b15b1335a1dbb98bcb Mon Sep 17 00:00:00 2001 From: Gavi Teitz Date: Mon, 29 Jul 2019 21:12:52 +0000 Subject: net/mlx5: Refactor and optimize flow counter bulk query Towards introducing the ability to allocate bulks of flow counters, refactor the flow counter bulk query process, removing functions and structs whose names indicated being used for flow counter bulk allocation FW commands, despite them actually only being used to support bulk querying, and migrate their functionality to correctly named functions in their natural location, fs_counters.c. Additionally, optimize the bulk query process by: * Extracting the memory used for the query to mlx5_fc_stats so that it is only allocated once, and not for each bulk query. * Querying all the counters in one function call. Signed-off-by: Gavi Teitz Reviewed-by: Vlad Buslov Signed-off-by: Saeed Mahameed --- drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.c | 61 ++-------- drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.h | 13 +-- .../net/ethernet/mellanox/mlx5/core/fs_counters.c | 125 +++++++++++---------- include/linux/mlx5/driver.h | 1 + 4 files changed, 81 insertions(+), 119 deletions(-) (limited to 'include/linux') diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.c b/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.c index 7ac1249eadc3..51f6972f4c70 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.c @@ -615,67 +615,24 @@ int mlx5_cmd_fc_query(struct mlx5_core_dev *dev, u32 id, return 0; } -struct mlx5_cmd_fc_bulk { - u32 id; - int num; - int outlen; - u32 out[0]; -}; - -struct mlx5_cmd_fc_bulk * -mlx5_cmd_fc_bulk_alloc(struct mlx5_core_dev *dev, u32 id, int num) +int mlx5_cmd_fc_get_bulk_query_out_len(int bulk_len) { - struct mlx5_cmd_fc_bulk *b; - int outlen = - MLX5_ST_SZ_BYTES(query_flow_counter_out) + - MLX5_ST_SZ_BYTES(traffic_counter) * num; - - b = kzalloc(sizeof(*b) + outlen, GFP_KERNEL); - if (!b) - return NULL; - - b->id = id; - b->num = num; - b->outlen = outlen; - - return b; + return MLX5_ST_SZ_BYTES(query_flow_counter_out) + + MLX5_ST_SZ_BYTES(traffic_counter) * bulk_len; } -void mlx5_cmd_fc_bulk_free(struct mlx5_cmd_fc_bulk *b) -{ - kfree(b); -} - -int -mlx5_cmd_fc_bulk_query(struct mlx5_core_dev *dev, struct mlx5_cmd_fc_bulk *b) +int mlx5_cmd_fc_bulk_query(struct mlx5_core_dev *dev, u32 base_id, int bulk_len, + u32 *out) { + int outlen = mlx5_cmd_fc_get_bulk_query_out_len(bulk_len); u32 in[MLX5_ST_SZ_DW(query_flow_counter_in)] = {0}; MLX5_SET(query_flow_counter_in, in, opcode, MLX5_CMD_OP_QUERY_FLOW_COUNTER); MLX5_SET(query_flow_counter_in, in, op_mod, 0); - MLX5_SET(query_flow_counter_in, in, flow_counter_id, b->id); - MLX5_SET(query_flow_counter_in, in, num_of_counters, b->num); - return mlx5_cmd_exec(dev, in, sizeof(in), b->out, b->outlen); -} - -void mlx5_cmd_fc_bulk_get(struct mlx5_core_dev *dev, - struct mlx5_cmd_fc_bulk *b, u32 id, - u64 *packets, u64 *bytes) -{ - int index = id - b->id; - void *stats; - - if (index < 0 || index >= b->num) { - mlx5_core_warn(dev, "Flow counter id (0x%x) out of range (0x%x..0x%x). Counter ignored.\n", - id, b->id, b->id + b->num - 1); - return; - } - - stats = MLX5_ADDR_OF(query_flow_counter_out, b->out, - flow_statistics[index]); - *packets = MLX5_GET64(traffic_counter, stats, packets); - *bytes = MLX5_GET64(traffic_counter, stats, octets); + MLX5_SET(query_flow_counter_in, in, flow_counter_id, base_id); + MLX5_SET(query_flow_counter_in, in, num_of_counters, bulk_len); + return mlx5_cmd_exec(dev, in, sizeof(in), out, outlen); } int mlx5_packet_reformat_alloc(struct mlx5_core_dev *dev, diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.h b/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.h index e340f9af2f5a..db49eabba98d 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.h @@ -82,16 +82,9 @@ int mlx5_cmd_fc_free(struct mlx5_core_dev *dev, u32 id); int mlx5_cmd_fc_query(struct mlx5_core_dev *dev, u32 id, u64 *packets, u64 *bytes); -struct mlx5_cmd_fc_bulk; - -struct mlx5_cmd_fc_bulk * -mlx5_cmd_fc_bulk_alloc(struct mlx5_core_dev *dev, u32 id, int num); -void mlx5_cmd_fc_bulk_free(struct mlx5_cmd_fc_bulk *b); -int -mlx5_cmd_fc_bulk_query(struct mlx5_core_dev *dev, struct mlx5_cmd_fc_bulk *b); -void mlx5_cmd_fc_bulk_get(struct mlx5_core_dev *dev, - struct mlx5_cmd_fc_bulk *b, u32 id, - u64 *packets, u64 *bytes); +int mlx5_cmd_fc_get_bulk_query_out_len(int bulk_len); +int mlx5_cmd_fc_bulk_query(struct mlx5_core_dev *dev, u32 base_id, int bulk_len, + u32 *out); const struct mlx5_flow_cmds *mlx5_fs_cmd_get_default(enum fs_flow_table_type type); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_counters.c b/drivers/net/ethernet/mellanox/mlx5/core/fs_counters.c index b3762123a69c..067a4b56498b 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/fs_counters.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_counters.c @@ -75,7 +75,7 @@ struct mlx5_fc { * access to counter list: * - create (user context) * - mlx5_fc_create() only adds to an addlist to be used by - * mlx5_fc_stats_query_work(). addlist is a lockless single linked list + * mlx5_fc_stats_work(). addlist is a lockless single linked list * that doesn't require any additional synchronization when adding single * node. * - spawn thread to do the actual destroy @@ -136,72 +136,69 @@ static void mlx5_fc_stats_remove(struct mlx5_core_dev *dev, spin_unlock(&fc_stats->counters_idr_lock); } -/* The function returns the last counter that was queried so the caller - * function can continue calling it till all counters are queried. - */ -static struct mlx5_fc *mlx5_fc_stats_query(struct mlx5_core_dev *dev, - struct mlx5_fc *first, - u32 last_id) +static int get_max_bulk_query_len(struct mlx5_core_dev *dev) { - struct mlx5_fc_stats *fc_stats = &dev->priv.fc_stats; - struct mlx5_fc *counter = NULL; - struct mlx5_cmd_fc_bulk *b; - bool more = false; - u32 afirst_id; - int num; - int err; + return min_t(int, MLX5_SW_MAX_COUNTERS_BULK, + (1 << MLX5_CAP_GEN(dev, log_max_flow_counter_bulk))); +} - int max_bulk = min_t(int, MLX5_SW_MAX_COUNTERS_BULK, - (1 << MLX5_CAP_GEN(dev, log_max_flow_counter_bulk))); +static void update_counter_cache(int index, u32 *bulk_raw_data, + struct mlx5_fc_cache *cache) +{ + void *stats = MLX5_ADDR_OF(query_flow_counter_out, bulk_raw_data, + flow_statistics[index]); + u64 packets = MLX5_GET64(traffic_counter, stats, packets); + u64 bytes = MLX5_GET64(traffic_counter, stats, octets); - /* first id must be aligned to 4 when using bulk query */ - afirst_id = first->id & ~0x3; + if (cache->packets == packets) + return; - /* number of counters to query inc. the last counter */ - num = ALIGN(last_id - afirst_id + 1, 4); - if (num > max_bulk) { - num = max_bulk; - last_id = afirst_id + num - 1; - } + cache->packets = packets; + cache->bytes = bytes; + cache->lastuse = jiffies; +} - b = mlx5_cmd_fc_bulk_alloc(dev, afirst_id, num); - if (!b) { - mlx5_core_err(dev, "Error allocating resources for bulk query\n"); - return NULL; - } +static void mlx5_fc_stats_query_counter_range(struct mlx5_core_dev *dev, + struct mlx5_fc *first, + u32 last_id) +{ + struct mlx5_fc_stats *fc_stats = &dev->priv.fc_stats; + bool query_more_counters = (first->id <= last_id); + int max_bulk_len = get_max_bulk_query_len(dev); + u32 *data = fc_stats->bulk_query_out; + struct mlx5_fc *counter = first; + u32 bulk_base_id; + int bulk_len; + int err; - err = mlx5_cmd_fc_bulk_query(dev, b); - if (err) { - mlx5_core_err(dev, "Error doing bulk query: %d\n", err); - goto out; - } + while (query_more_counters) { + /* first id must be aligned to 4 when using bulk query */ + bulk_base_id = counter->id & ~0x3; - counter = first; - list_for_each_entry_from(counter, &fc_stats->counters, list) { - struct mlx5_fc_cache *c = &counter->cache; - u64 packets; - u64 bytes; + /* number of counters to query inc. the last counter */ + bulk_len = min_t(int, max_bulk_len, + ALIGN(last_id - bulk_base_id + 1, 4)); - if (counter->id > last_id) { - more = true; - break; + err = mlx5_cmd_fc_bulk_query(dev, bulk_base_id, bulk_len, + data); + if (err) { + mlx5_core_err(dev, "Error doing bulk query: %d\n", err); + return; } + query_more_counters = false; - mlx5_cmd_fc_bulk_get(dev, b, - counter->id, &packets, &bytes); + list_for_each_entry_from(counter, &fc_stats->counters, list) { + int counter_index = counter->id - bulk_base_id; + struct mlx5_fc_cache *cache = &counter->cache; - if (c->packets == packets) - continue; + if (counter->id >= bulk_base_id + bulk_len) { + query_more_counters = true; + break; + } - c->packets = packets; - c->bytes = bytes; - c->lastuse = jiffies; + update_counter_cache(counter_index, data, cache); + } } - -out: - mlx5_cmd_fc_bulk_free(b); - - return more ? counter : NULL; } static void mlx5_free_fc(struct mlx5_core_dev *dev, @@ -244,8 +241,8 @@ static void mlx5_fc_stats_work(struct work_struct *work) counter = list_first_entry(&fc_stats->counters, struct mlx5_fc, list); - while (counter) - counter = mlx5_fc_stats_query(dev, counter, last->id); + if (counter) + mlx5_fc_stats_query_counter_range(dev, counter, last->id); fc_stats->next_query = now + fc_stats->sampling_interval; } @@ -324,6 +321,8 @@ EXPORT_SYMBOL(mlx5_fc_destroy); int mlx5_init_fc_stats(struct mlx5_core_dev *dev) { struct mlx5_fc_stats *fc_stats = &dev->priv.fc_stats; + int max_bulk_len; + int max_out_len; spin_lock_init(&fc_stats->counters_idr_lock); idr_init(&fc_stats->counters_idr); @@ -331,14 +330,24 @@ int mlx5_init_fc_stats(struct mlx5_core_dev *dev) init_llist_head(&fc_stats->addlist); init_llist_head(&fc_stats->dellist); + max_bulk_len = get_max_bulk_query_len(dev); + max_out_len = mlx5_cmd_fc_get_bulk_query_out_len(max_bulk_len); + fc_stats->bulk_query_out = kzalloc(max_out_len, GFP_KERNEL); + if (!fc_stats->bulk_query_out) + return -ENOMEM; + fc_stats->wq = create_singlethread_workqueue("mlx5_fc"); if (!fc_stats->wq) - return -ENOMEM; + goto err_wq_create; fc_stats->sampling_interval = MLX5_FC_STATS_PERIOD; INIT_DELAYED_WORK(&fc_stats->work, mlx5_fc_stats_work); return 0; + +err_wq_create: + kfree(fc_stats->bulk_query_out); + return -ENOMEM; } void mlx5_cleanup_fc_stats(struct mlx5_core_dev *dev) @@ -352,6 +361,8 @@ void mlx5_cleanup_fc_stats(struct mlx5_core_dev *dev) destroy_workqueue(dev->priv.fc_stats.wq); dev->priv.fc_stats.wq = NULL; + kfree(fc_stats->bulk_query_out); + idr_destroy(&fc_stats->counters_idr); tmplist = llist_del_all(&fc_stats->addlist); diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h index 0e6da1840c7d..267b2bc0ca4a 100644 --- a/include/linux/mlx5/driver.h +++ b/include/linux/mlx5/driver.h @@ -488,6 +488,7 @@ struct mlx5_fc_stats { struct delayed_work work; unsigned long next_query; unsigned long sampling_interval; /* jiffies */ + u32 *bulk_query_out; }; struct mlx5_events; -- cgit v1.2.3 From 8536a6bf2ea1f3bf4e3159b590fbecce4d854796 Mon Sep 17 00:00:00 2001 From: Gavi Teitz Date: Mon, 29 Jul 2019 21:12:54 +0000 Subject: net/mlx5: Add flow counter bulk allocation hardware bits and command Add a handle to invoke the new FW capability of allocating a bulk of flow counters. Signed-off-by: Gavi Teitz Reviewed-by: Vlad Buslov Signed-off-by: Saeed Mahameed --- drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.c | 10 +++++++++- drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.h | 3 +++ include/linux/mlx5/mlx5_ifc.h | 21 +++++++++++++++++++-- 3 files changed, 31 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.c b/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.c index 51f6972f4c70..b84a225bbe86 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.c @@ -566,7 +566,9 @@ static int mlx5_cmd_delete_fte(struct mlx5_flow_root_namespace *ns, return mlx5_cmd_exec(dev, in, sizeof(in), out, sizeof(out)); } -int mlx5_cmd_fc_alloc(struct mlx5_core_dev *dev, u32 *id) +int mlx5_cmd_fc_bulk_alloc(struct mlx5_core_dev *dev, + enum mlx5_fc_bulk_alloc_bitmask alloc_bitmask, + u32 *id) { u32 in[MLX5_ST_SZ_DW(alloc_flow_counter_in)] = {0}; u32 out[MLX5_ST_SZ_DW(alloc_flow_counter_out)] = {0}; @@ -574,6 +576,7 @@ int mlx5_cmd_fc_alloc(struct mlx5_core_dev *dev, u32 *id) MLX5_SET(alloc_flow_counter_in, in, opcode, MLX5_CMD_OP_ALLOC_FLOW_COUNTER); + MLX5_SET(alloc_flow_counter_in, in, flow_counter_bulk, alloc_bitmask); err = mlx5_cmd_exec(dev, in, sizeof(in), out, sizeof(out)); if (!err) @@ -581,6 +584,11 @@ int mlx5_cmd_fc_alloc(struct mlx5_core_dev *dev, u32 *id) return err; } +int mlx5_cmd_fc_alloc(struct mlx5_core_dev *dev, u32 *id) +{ + return mlx5_cmd_fc_bulk_alloc(dev, 0, id); +} + int mlx5_cmd_fc_free(struct mlx5_core_dev *dev, u32 id) { u32 in[MLX5_ST_SZ_DW(dealloc_flow_counter_in)] = {0}; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.h b/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.h index db49eabba98d..bc4606306009 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.h @@ -78,6 +78,9 @@ struct mlx5_flow_cmds { }; int mlx5_cmd_fc_alloc(struct mlx5_core_dev *dev, u32 *id); +int mlx5_cmd_fc_bulk_alloc(struct mlx5_core_dev *dev, + enum mlx5_fc_bulk_alloc_bitmask alloc_bitmask, + u32 *id); int mlx5_cmd_fc_free(struct mlx5_core_dev *dev, u32 id); int mlx5_cmd_fc_query(struct mlx5_core_dev *dev, u32 id, u64 *packets, u64 *bytes); diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h index b3d5752657d9..196987f14a3f 100644 --- a/include/linux/mlx5/mlx5_ifc.h +++ b/include/linux/mlx5/mlx5_ifc.h @@ -1040,6 +1040,21 @@ enum { MLX5_UCTX_CAP_INTERNAL_DEV_RES = 1UL << 1, }; +#define MLX5_FC_BULK_SIZE_FACTOR 128 + +enum mlx5_fc_bulk_alloc_bitmask { + MLX5_FC_BULK_128 = (1 << 0), + MLX5_FC_BULK_256 = (1 << 1), + MLX5_FC_BULK_512 = (1 << 2), + MLX5_FC_BULK_1024 = (1 << 3), + MLX5_FC_BULK_2048 = (1 << 4), + MLX5_FC_BULK_4096 = (1 << 5), + MLX5_FC_BULK_8192 = (1 << 6), + MLX5_FC_BULK_16384 = (1 << 7), +}; + +#define MLX5_FC_BULK_NUM_FCS(fc_enum) (MLX5_FC_BULK_SIZE_FACTOR * (fc_enum)) + struct mlx5_ifc_cmd_hca_cap_bits { u8 reserved_at_0[0x30]; u8 vhca_id[0x10]; @@ -1244,7 +1259,8 @@ struct mlx5_ifc_cmd_hca_cap_bits { u8 reserved_at_2e0[0x7]; u8 max_qp_mcg[0x19]; - u8 reserved_at_300[0x18]; + u8 reserved_at_300[0x10]; + u8 flow_counter_bulk_alloc[0x8]; u8 log_max_mcg[0x8]; u8 reserved_at_320[0x3]; @@ -7815,7 +7831,8 @@ struct mlx5_ifc_alloc_flow_counter_in_bits { u8 reserved_at_20[0x10]; u8 op_mod[0x10]; - u8 reserved_at_40[0x40]; + u8 reserved_at_40[0x38]; + u8 flow_counter_bulk[0x8]; }; struct mlx5_ifc_add_vxlan_udp_dport_out_bits { -- cgit v1.2.3 From 7761f9eef3f09f2f4c579313e0c536770b5ecff4 Mon Sep 17 00:00:00 2001 From: Saeed Mahameed Date: Mon, 29 Jul 2019 21:12:56 +0000 Subject: net/mlx5: Fix offset of tisc bits reserved field First reserved field is off by one instead of reserved_at_1 it should be reserved_at_2, fix that. Fixes: a12ff35e0fb7 ("net/mlx5: Introduce TLS TX offload hardware bits and structures") Signed-off-by: Saeed Mahameed Reviewed-by: Leon Romanovsky Signed-off-by: Saeed Mahameed --- include/linux/mlx5/mlx5_ifc.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h index 196987f14a3f..9265c84ad353 100644 --- a/include/linux/mlx5/mlx5_ifc.h +++ b/include/linux/mlx5/mlx5_ifc.h @@ -2782,7 +2782,7 @@ struct mlx5_ifc_traffic_counter_bits { struct mlx5_ifc_tisc_bits { u8 strict_lag_tx_port_affinity[0x1]; u8 tls_en[0x1]; - u8 reserved_at_1[0x2]; + u8 reserved_at_2[0x2]; u8 lag_tx_port_affinity[0x04]; u8 reserved_at_8[0x4]; -- cgit v1.2.3 From 6cedde4513990af7191afa43528533f80e92c989 Mon Sep 17 00:00:00 2001 From: Eli Cohen Date: Mon, 29 Jul 2019 21:13:00 +0000 Subject: net/mlx5: E-Switch, Verify support QoS element type Check if firmware supports the requested element type before attempting to create the element type. In addition, explicitly specify the request element type and tsar type. Signed-off-by: Eli Cohen Reviewed-by: Paul Blakey Signed-off-by: Saeed Mahameed --- drivers/net/ethernet/mellanox/mlx5/core/eswitch.c | 31 +++++++++++++++++++++++ include/linux/mlx5/mlx5_ifc.h | 7 +++++ 2 files changed, 38 insertions(+) (limited to 'include/linux') diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c index 1f3891fde2eb..2927fa1da92f 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c @@ -1393,19 +1393,50 @@ out: return err; } +static bool element_type_supported(struct mlx5_eswitch *esw, int type) +{ + struct mlx5_core_dev *dev = esw->dev = esw->dev; + + switch (type) { + case SCHEDULING_CONTEXT_ELEMENT_TYPE_TSAR: + return MLX5_CAP_QOS(dev, esw_element_type) & + ELEMENT_TYPE_CAP_MASK_TASR; + case SCHEDULING_CONTEXT_ELEMENT_TYPE_VPORT: + return MLX5_CAP_QOS(dev, esw_element_type) & + ELEMENT_TYPE_CAP_MASK_VPORT; + case SCHEDULING_CONTEXT_ELEMENT_TYPE_VPORT_TC: + return MLX5_CAP_QOS(dev, esw_element_type) & + ELEMENT_TYPE_CAP_MASK_VPORT_TC; + case SCHEDULING_CONTEXT_ELEMENT_TYPE_PARA_VPORT_TC: + return MLX5_CAP_QOS(dev, esw_element_type) & + ELEMENT_TYPE_CAP_MASK_PARA_VPORT_TC; + } + return false; +} + /* Vport QoS management */ static int esw_create_tsar(struct mlx5_eswitch *esw) { u32 tsar_ctx[MLX5_ST_SZ_DW(scheduling_context)] = {0}; struct mlx5_core_dev *dev = esw->dev; + __be32 *attr; int err; if (!MLX5_CAP_GEN(dev, qos) || !MLX5_CAP_QOS(dev, esw_scheduling)) return 0; + if (!element_type_supported(esw, SCHEDULING_CONTEXT_ELEMENT_TYPE_TSAR)) + return 0; + if (esw->qos.enabled) return -EEXIST; + MLX5_SET(scheduling_context, tsar_ctx, element_type, + SCHEDULING_CONTEXT_ELEMENT_TYPE_TSAR); + + attr = MLX5_ADDR_OF(scheduling_context, tsar_ctx, element_attributes); + *attr = cpu_to_be32(TSAR_ELEMENT_TSAR_TYPE_DWRR << 16); + err = mlx5_create_scheduling_element_cmd(dev, SCHEDULING_HIERARCHY_E_SWITCH, tsar_ctx, diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h index 9265c84ad353..30d15e80bcc7 100644 --- a/include/linux/mlx5/mlx5_ifc.h +++ b/include/linux/mlx5/mlx5_ifc.h @@ -2957,6 +2957,13 @@ enum { SCHEDULING_CONTEXT_ELEMENT_TYPE_PARA_VPORT_TC = 0x3, }; +enum { + ELEMENT_TYPE_CAP_MASK_TASR = 1 << 0, + ELEMENT_TYPE_CAP_MASK_VPORT = 1 << 1, + ELEMENT_TYPE_CAP_MASK_VPORT_TC = 1 << 2, + ELEMENT_TYPE_CAP_MASK_PARA_VPORT_TC = 1 << 3, +}; + struct mlx5_ifc_scheduling_context_bits { u8 element_type[0x8]; u8 reserved_at_8[0x18]; -- cgit v1.2.3 From 558101f1b9807b34d8eeefb352d11e642b7e98dd Mon Sep 17 00:00:00 2001 From: Gavi Teitz Date: Thu, 27 Jun 2019 20:53:03 +0300 Subject: net/mlx5: Add flow counter pool Add a pool of flow counters, based on flow counter bulks, removing the need to allocate a new counter via a costly FW command during the flow creation process. The time it takes to acquire/release a flow counter is cut from ~50 [us] to ~50 [ns]. The pool is part of the mlx5 driver instance, and provides flow counters for aging flows. mlx5_fc_create() was modified to provide counters for aging flows from the pool by default, and mlx5_destroy_fc() was modified to release counters back to the pool for later reuse. If bulk allocation is not supported or fails, and for non-aging flows, the fallback behavior is to allocate and free individual counters. The pool is comprised of three lists of flow counter bulks, one of fully used bulks, one of partially used bulks, and one of unused bulks. Counters are provided from the partially used bulks first, to help limit bulk fragmentation. The pool maintains a threshold, and strives to maintain the amount of available counters below it. The pool is increased in size when a counter acquisition request is made and there are no available counters, and it is decreased in size when the last counter in a bulk is released and there are more available counters than the threshold. All pool size changes are done in the context of the acquiring/releasing process. The value of the threshold is directly correlated to the amount of used counters the pool is providing, while constrained by a hard maximum, and is recalculated every time a bulk is allocated/freed. This ensures that the pool only consumes large amounts of memory for available counters if the pool is being used heavily. When fully populated and at the hard maximum, the buffer of available counters consumes ~40 [MB]. Signed-off-by: Gavi Teitz Reviewed-by: Vlad Buslov Signed-off-by: Saeed Mahameed --- .../net/ethernet/mellanox/mlx5/core/fs_counters.c | 231 ++++++++++++++++++--- include/linux/mlx5/driver.h | 12 ++ 2 files changed, 218 insertions(+), 25 deletions(-) (limited to 'include/linux') diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_counters.c b/drivers/net/ethernet/mellanox/mlx5/core/fs_counters.c index 3e734e62a6cd..51f1736c455d 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/fs_counters.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_counters.c @@ -40,6 +40,8 @@ #define MLX5_FC_STATS_PERIOD msecs_to_jiffies(1000) /* Max number of counters to query in bulk read is 32K */ #define MLX5_SW_MAX_COUNTERS_BULK BIT(15) +#define MLX5_FC_POOL_MAX_THRESHOLD BIT(18) +#define MLX5_FC_POOL_USED_BUFF_RATIO 10 struct mlx5_fc_cache { u64 packets; @@ -65,6 +67,11 @@ struct mlx5_fc { struct mlx5_fc_cache cache ____cacheline_aligned_in_smp; }; +static void mlx5_fc_pool_init(struct mlx5_fc_pool *fc_pool, struct mlx5_core_dev *dev); +static void mlx5_fc_pool_cleanup(struct mlx5_fc_pool *fc_pool); +static struct mlx5_fc *mlx5_fc_pool_acquire_counter(struct mlx5_fc_pool *fc_pool); +static void mlx5_fc_pool_release_counter(struct mlx5_fc_pool *fc_pool, struct mlx5_fc *fc); + /* locking scheme: * * It is the responsibility of the user to prevent concurrent calls or bad @@ -202,13 +209,22 @@ static void mlx5_fc_stats_query_counter_range(struct mlx5_core_dev *dev, } } -static void mlx5_free_fc(struct mlx5_core_dev *dev, - struct mlx5_fc *counter) +static void mlx5_fc_free(struct mlx5_core_dev *dev, struct mlx5_fc *counter) { mlx5_cmd_fc_free(dev, counter->id); kfree(counter); } +static void mlx5_fc_release(struct mlx5_core_dev *dev, struct mlx5_fc *counter) +{ + struct mlx5_fc_stats *fc_stats = &dev->priv.fc_stats; + + if (counter->bulk) + mlx5_fc_pool_release_counter(&fc_stats->fc_pool, counter); + else + mlx5_fc_free(dev, counter); +} + static void mlx5_fc_stats_work(struct work_struct *work) { struct mlx5_core_dev *dev = container_of(work, struct mlx5_core_dev, @@ -232,7 +248,7 @@ static void mlx5_fc_stats_work(struct work_struct *work) llist_for_each_entry_safe(counter, tmp, dellist, dellist) { mlx5_fc_stats_remove(dev, counter); - mlx5_free_fc(dev, counter); + mlx5_fc_release(dev, counter); } if (time_before(now, fc_stats->next_query) || @@ -248,26 +264,56 @@ static void mlx5_fc_stats_work(struct work_struct *work) fc_stats->next_query = now + fc_stats->sampling_interval; } -struct mlx5_fc *mlx5_fc_create(struct mlx5_core_dev *dev, bool aging) +static struct mlx5_fc *mlx5_fc_single_alloc(struct mlx5_core_dev *dev) { - struct mlx5_fc_stats *fc_stats = &dev->priv.fc_stats; struct mlx5_fc *counter; int err; counter = kzalloc(sizeof(*counter), GFP_KERNEL); if (!counter) return ERR_PTR(-ENOMEM); - INIT_LIST_HEAD(&counter->list); err = mlx5_cmd_fc_alloc(dev, &counter->id); - if (err) - goto err_out; + if (err) { + kfree(counter); + return ERR_PTR(err); + } + + return counter; +} + +static struct mlx5_fc *mlx5_fc_acquire(struct mlx5_core_dev *dev, bool aging) +{ + struct mlx5_fc_stats *fc_stats = &dev->priv.fc_stats; + struct mlx5_fc *counter; + + if (aging && MLX5_CAP_GEN(dev, flow_counter_bulk_alloc) != 0) { + counter = mlx5_fc_pool_acquire_counter(&fc_stats->fc_pool); + if (!IS_ERR(counter)) + return counter; + } + + return mlx5_fc_single_alloc(dev); +} + +struct mlx5_fc *mlx5_fc_create(struct mlx5_core_dev *dev, bool aging) +{ + struct mlx5_fc *counter = mlx5_fc_acquire(dev, aging); + struct mlx5_fc_stats *fc_stats = &dev->priv.fc_stats; + int err; + + if (IS_ERR(counter)) + return counter; + + INIT_LIST_HEAD(&counter->list); + counter->aging = aging; if (aging) { u32 id = counter->id; counter->cache.lastuse = jiffies; - counter->aging = true; + counter->lastbytes = counter->cache.bytes; + counter->lastpackets = counter->cache.packets; idr_preload(GFP_KERNEL); spin_lock(&fc_stats->counters_idr_lock); @@ -288,10 +334,7 @@ struct mlx5_fc *mlx5_fc_create(struct mlx5_core_dev *dev, bool aging) return counter; err_out_alloc: - mlx5_cmd_fc_free(dev, counter->id); -err_out: - kfree(counter); - + mlx5_fc_release(dev, counter); return ERR_PTR(err); } EXPORT_SYMBOL(mlx5_fc_create); @@ -315,7 +358,7 @@ void mlx5_fc_destroy(struct mlx5_core_dev *dev, struct mlx5_fc *counter) return; } - mlx5_free_fc(dev, counter); + mlx5_fc_release(dev, counter); } EXPORT_SYMBOL(mlx5_fc_destroy); @@ -344,6 +387,7 @@ int mlx5_init_fc_stats(struct mlx5_core_dev *dev) fc_stats->sampling_interval = MLX5_FC_STATS_PERIOD; INIT_DELAYED_WORK(&fc_stats->work, mlx5_fc_stats_work); + mlx5_fc_pool_init(&fc_stats->fc_pool, dev); return 0; err_wq_create: @@ -358,6 +402,7 @@ void mlx5_cleanup_fc_stats(struct mlx5_core_dev *dev) struct mlx5_fc *counter; struct mlx5_fc *tmp; + mlx5_fc_pool_cleanup(&fc_stats->fc_pool); cancel_delayed_work_sync(&dev->priv.fc_stats.work); destroy_workqueue(dev->priv.fc_stats.wq); dev->priv.fc_stats.wq = NULL; @@ -368,10 +413,10 @@ void mlx5_cleanup_fc_stats(struct mlx5_core_dev *dev) tmplist = llist_del_all(&fc_stats->addlist); llist_for_each_entry_safe(counter, tmp, tmplist, addlist) - mlx5_free_fc(dev, counter); + mlx5_fc_release(dev, counter); list_for_each_entry_safe(counter, tmp, &fc_stats->counters, list) - mlx5_free_fc(dev, counter); + mlx5_fc_release(dev, counter); } int mlx5_fc_query(struct mlx5_core_dev *dev, struct mlx5_fc *counter, @@ -417,14 +462,15 @@ void mlx5_fc_update_sampling_interval(struct mlx5_core_dev *dev, /* Flow counter bluks */ struct mlx5_fc_bulk { + struct list_head pool_list; u32 base_id; int bulk_len; unsigned long *bitmask; struct mlx5_fc fcs[0]; }; -static void -mlx5_fc_init(struct mlx5_fc *counter, struct mlx5_fc_bulk *bulk, u32 id) +static void mlx5_fc_init(struct mlx5_fc *counter, struct mlx5_fc_bulk *bulk, + u32 id) { counter->bulk = bulk; counter->id = id; @@ -435,8 +481,7 @@ static int mlx5_fc_bulk_get_free_fcs_amount(struct mlx5_fc_bulk *bulk) return bitmap_weight(bulk->bitmask, bulk->bulk_len); } -static struct mlx5_fc_bulk __attribute__((unused)) -*mlx5_fc_bulk_create(struct mlx5_core_dev *dev) +static struct mlx5_fc_bulk *mlx5_fc_bulk_create(struct mlx5_core_dev *dev) { enum mlx5_fc_bulk_alloc_bitmask alloc_bitmask; struct mlx5_fc_bulk *bulk; @@ -479,7 +524,7 @@ err_alloc_bulk: return ERR_PTR(err); } -static int __attribute__((unused)) +static int mlx5_fc_bulk_destroy(struct mlx5_core_dev *dev, struct mlx5_fc_bulk *bulk) { if (mlx5_fc_bulk_get_free_fcs_amount(bulk) < bulk->bulk_len) { @@ -494,8 +539,7 @@ mlx5_fc_bulk_destroy(struct mlx5_core_dev *dev, struct mlx5_fc_bulk *bulk) return 0; } -static struct mlx5_fc __attribute__((unused)) -*mlx5_fc_bulk_acquire_fc(struct mlx5_fc_bulk *bulk) +static struct mlx5_fc *mlx5_fc_bulk_acquire_fc(struct mlx5_fc_bulk *bulk) { int free_fc_index = find_first_bit(bulk->bitmask, bulk->bulk_len); @@ -506,8 +550,7 @@ static struct mlx5_fc __attribute__((unused)) return &bulk->fcs[free_fc_index]; } -static int __attribute__((unused)) -mlx5_fc_bulk_release_fc(struct mlx5_fc_bulk *bulk, struct mlx5_fc *fc) +static int mlx5_fc_bulk_release_fc(struct mlx5_fc_bulk *bulk, struct mlx5_fc *fc) { int fc_index = fc->id - bulk->base_id; @@ -517,3 +560,141 @@ mlx5_fc_bulk_release_fc(struct mlx5_fc_bulk *bulk, struct mlx5_fc *fc) set_bit(fc_index, bulk->bitmask); return 0; } + +/* Flow counters pool API */ + +static void mlx5_fc_pool_init(struct mlx5_fc_pool *fc_pool, struct mlx5_core_dev *dev) +{ + fc_pool->dev = dev; + mutex_init(&fc_pool->pool_lock); + INIT_LIST_HEAD(&fc_pool->fully_used); + INIT_LIST_HEAD(&fc_pool->partially_used); + INIT_LIST_HEAD(&fc_pool->unused); + fc_pool->available_fcs = 0; + fc_pool->used_fcs = 0; + fc_pool->threshold = 0; +} + +static void mlx5_fc_pool_cleanup(struct mlx5_fc_pool *fc_pool) +{ + struct mlx5_core_dev *dev = fc_pool->dev; + struct mlx5_fc_bulk *bulk; + struct mlx5_fc_bulk *tmp; + + list_for_each_entry_safe(bulk, tmp, &fc_pool->fully_used, pool_list) + mlx5_fc_bulk_destroy(dev, bulk); + list_for_each_entry_safe(bulk, tmp, &fc_pool->partially_used, pool_list) + mlx5_fc_bulk_destroy(dev, bulk); + list_for_each_entry_safe(bulk, tmp, &fc_pool->unused, pool_list) + mlx5_fc_bulk_destroy(dev, bulk); +} + +static void mlx5_fc_pool_update_threshold(struct mlx5_fc_pool *fc_pool) +{ + fc_pool->threshold = min_t(int, MLX5_FC_POOL_MAX_THRESHOLD, + fc_pool->used_fcs / MLX5_FC_POOL_USED_BUFF_RATIO); +} + +static struct mlx5_fc_bulk * +mlx5_fc_pool_alloc_new_bulk(struct mlx5_fc_pool *fc_pool) +{ + struct mlx5_core_dev *dev = fc_pool->dev; + struct mlx5_fc_bulk *new_bulk; + + new_bulk = mlx5_fc_bulk_create(dev); + if (!IS_ERR(new_bulk)) + fc_pool->available_fcs += new_bulk->bulk_len; + mlx5_fc_pool_update_threshold(fc_pool); + return new_bulk; +} + +static void +mlx5_fc_pool_free_bulk(struct mlx5_fc_pool *fc_pool, struct mlx5_fc_bulk *bulk) +{ + struct mlx5_core_dev *dev = fc_pool->dev; + + fc_pool->available_fcs -= bulk->bulk_len; + mlx5_fc_bulk_destroy(dev, bulk); + mlx5_fc_pool_update_threshold(fc_pool); +} + +static struct mlx5_fc * +mlx5_fc_pool_acquire_from_list(struct list_head *src_list, + struct list_head *next_list, + bool move_non_full_bulk) +{ + struct mlx5_fc_bulk *bulk; + struct mlx5_fc *fc; + + if (list_empty(src_list)) + return ERR_PTR(-ENODATA); + + bulk = list_first_entry(src_list, struct mlx5_fc_bulk, pool_list); + fc = mlx5_fc_bulk_acquire_fc(bulk); + if (move_non_full_bulk || mlx5_fc_bulk_get_free_fcs_amount(bulk) == 0) + list_move(&bulk->pool_list, next_list); + return fc; +} + +static struct mlx5_fc * +mlx5_fc_pool_acquire_counter(struct mlx5_fc_pool *fc_pool) +{ + struct mlx5_fc_bulk *new_bulk; + struct mlx5_fc *fc; + + mutex_lock(&fc_pool->pool_lock); + + fc = mlx5_fc_pool_acquire_from_list(&fc_pool->partially_used, + &fc_pool->fully_used, false); + if (IS_ERR(fc)) + fc = mlx5_fc_pool_acquire_from_list(&fc_pool->unused, + &fc_pool->partially_used, + true); + if (IS_ERR(fc)) { + new_bulk = mlx5_fc_pool_alloc_new_bulk(fc_pool); + if (IS_ERR(new_bulk)) { + fc = ERR_CAST(new_bulk); + goto out; + } + fc = mlx5_fc_bulk_acquire_fc(new_bulk); + list_add(&new_bulk->pool_list, &fc_pool->partially_used); + } + fc_pool->available_fcs--; + fc_pool->used_fcs++; + +out: + mutex_unlock(&fc_pool->pool_lock); + return fc; +} + +static void +mlx5_fc_pool_release_counter(struct mlx5_fc_pool *fc_pool, struct mlx5_fc *fc) +{ + struct mlx5_core_dev *dev = fc_pool->dev; + struct mlx5_fc_bulk *bulk = fc->bulk; + int bulk_free_fcs_amount; + + mutex_lock(&fc_pool->pool_lock); + + if (mlx5_fc_bulk_release_fc(bulk, fc)) { + mlx5_core_warn(dev, "Attempted to release a counter which is not acquired\n"); + goto unlock; + } + + fc_pool->available_fcs++; + fc_pool->used_fcs--; + + bulk_free_fcs_amount = mlx5_fc_bulk_get_free_fcs_amount(bulk); + if (bulk_free_fcs_amount == 1) + list_move_tail(&bulk->pool_list, &fc_pool->partially_used); + if (bulk_free_fcs_amount == bulk->bulk_len) { + list_del(&bulk->pool_list); + if (fc_pool->available_fcs > fc_pool->threshold) + mlx5_fc_pool_free_bulk(fc_pool, bulk); + else + list_add(&bulk->pool_list, &fc_pool->unused); + } + +unlock: + mutex_unlock(&fc_pool->pool_lock); +} diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h index 267b2bc0ca4a..d8f348ef9c33 100644 --- a/include/linux/mlx5/driver.h +++ b/include/linux/mlx5/driver.h @@ -477,6 +477,17 @@ struct mlx5_core_sriov { u16 max_vfs; }; +struct mlx5_fc_pool { + struct mlx5_core_dev *dev; + struct mutex pool_lock; /* protects pool lists */ + struct list_head fully_used; + struct list_head partially_used; + struct list_head unused; + int available_fcs; + int used_fcs; + int threshold; +}; + struct mlx5_fc_stats { spinlock_t counters_idr_lock; /* protects counters_idr */ struct idr counters_idr; @@ -489,6 +500,7 @@ struct mlx5_fc_stats { unsigned long next_query; unsigned long sampling_interval; /* jiffies */ u32 *bulk_query_out; + struct mlx5_fc_pool fc_pool; }; struct mlx5_events; -- cgit v1.2.3 From ea77388b02270b0af8dc57f668f311235ea068f0 Mon Sep 17 00:00:00 2001 From: Mark Zhang Date: Wed, 31 Jul 2019 14:40:13 +0300 Subject: net/mlx5: Fix mlx5_ifc_query_lag_out_bits Remove the "reserved_at_40" field to match the device specification. Fixes: 84df61ebc69b ("net/mlx5: Add HW interfaces used by LAG") Signed-off-by: Mark Zhang Reviewed-by: Yishai Hadas Signed-off-by: Leon Romanovsky --- include/linux/mlx5/mlx5_ifc.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h index 30d15e80bcc7..1f9d4a8e6227 100644 --- a/include/linux/mlx5/mlx5_ifc.h +++ b/include/linux/mlx5/mlx5_ifc.h @@ -9592,8 +9592,6 @@ struct mlx5_ifc_query_lag_out_bits { u8 syndrome[0x20]; - u8 reserved_at_40[0x40]; - struct mlx5_ifc_lagc_bits ctx; }; -- cgit v1.2.3 From 94f3e14e00fd43024b1c4d8e0c1e442db9b4d964 Mon Sep 17 00:00:00 2001 From: Chuhong Yuan Date: Tue, 6 Aug 2019 09:59:50 +0800 Subject: mlx5: Use refcount_t for refcount Reference counters are preferred to use refcount_t instead of atomic_t. This is because the implementation of refcount_t can prevent overflows and detect possible use-after-free. So convert atomic_t ref counters to refcount_t. Signed-off-by: Chuhong Yuan Acked-by: Leon Romanovsky Signed-off-by: Saeed Mahameed --- drivers/infiniband/hw/mlx5/srq_cmd.c | 6 +++--- drivers/net/ethernet/mellanox/mlx5/core/qp.c | 6 +++--- include/linux/mlx5/driver.h | 3 ++- 3 files changed, 8 insertions(+), 7 deletions(-) (limited to 'include/linux') diff --git a/drivers/infiniband/hw/mlx5/srq_cmd.c b/drivers/infiniband/hw/mlx5/srq_cmd.c index b0d0687c7a68..8fc3630a9d4c 100644 --- a/drivers/infiniband/hw/mlx5/srq_cmd.c +++ b/drivers/infiniband/hw/mlx5/srq_cmd.c @@ -86,7 +86,7 @@ struct mlx5_core_srq *mlx5_cmd_get_srq(struct mlx5_ib_dev *dev, u32 srqn) xa_lock(&table->array); srq = xa_load(&table->array, srqn); if (srq) - atomic_inc(&srq->common.refcount); + refcount_inc(&srq->common.refcount); xa_unlock(&table->array); return srq; @@ -592,7 +592,7 @@ int mlx5_cmd_create_srq(struct mlx5_ib_dev *dev, struct mlx5_core_srq *srq, if (err) return err; - atomic_set(&srq->common.refcount, 1); + refcount_set(&srq->common.refcount, 1); init_completion(&srq->common.free); err = xa_err(xa_store_irq(&table->array, srq->srqn, srq, GFP_KERNEL)); @@ -675,7 +675,7 @@ static int srq_event_notifier(struct notifier_block *nb, xa_lock(&table->array); srq = xa_load(&table->array, srqn); if (srq) - atomic_inc(&srq->common.refcount); + refcount_inc(&srq->common.refcount); xa_unlock(&table->array); if (!srq) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/qp.c b/drivers/net/ethernet/mellanox/mlx5/core/qp.c index b8ba74de9555..7b44d1e49604 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/qp.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/qp.c @@ -53,7 +53,7 @@ mlx5_get_rsc(struct mlx5_qp_table *table, u32 rsn) common = radix_tree_lookup(&table->tree, rsn); if (common) - atomic_inc(&common->refcount); + refcount_inc(&common->refcount); spin_unlock_irqrestore(&table->lock, flags); @@ -62,7 +62,7 @@ mlx5_get_rsc(struct mlx5_qp_table *table, u32 rsn) void mlx5_core_put_rsc(struct mlx5_core_rsc_common *common) { - if (atomic_dec_and_test(&common->refcount)) + if (refcount_dec_and_test(&common->refcount)) complete(&common->free); } @@ -209,7 +209,7 @@ static int create_resource_common(struct mlx5_core_dev *dev, if (err) return err; - atomic_set(&qp->common.refcount, 1); + refcount_set(&qp->common.refcount, 1); init_completion(&qp->common.free); qp->pid = current->pid; diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h index 267b2bc0ca4a..0acd28f2e62c 100644 --- a/include/linux/mlx5/driver.h +++ b/include/linux/mlx5/driver.h @@ -47,6 +47,7 @@ #include #include #include +#include #include #include @@ -398,7 +399,7 @@ enum mlx5_res_type { struct mlx5_core_rsc_common { enum mlx5_res_type res; - atomic_t refcount; + refcount_t refcount; struct completion free; }; -- cgit v1.2.3 From 5e6d9fc76190aa70db9cbfb18a6f44f4ee83b7f5 Mon Sep 17 00:00:00 2001 From: Rahul Verma Date: Mon, 5 Aug 2019 23:59:50 -0700 Subject: qed: Add new ethtool supported port types based on media. Supported ports in ethtool are displayed based on media type. For media type fibre and twinaxial, port type is "FIBRE". Media type Base-T is "TP" and media KR is "Backplane". V1->V2: Corrected the subject. Signed-off-by: Rahul Verma Signed-off-by: Michal Kalderon Signed-off-by: David S. Miller --- drivers/net/ethernet/qlogic/qed/qed_main.c | 6 +++++- drivers/net/ethernet/qlogic/qede/qede_ethtool.c | 3 ++- include/linux/qed/qed_if.h | 2 +- 3 files changed, 8 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/drivers/net/ethernet/qlogic/qed/qed_main.c b/drivers/net/ethernet/qlogic/qed/qed_main.c index 829dd60ab937..e5ac8bd4fd14 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_main.c +++ b/drivers/net/ethernet/qlogic/qed/qed_main.c @@ -1688,6 +1688,7 @@ static void qed_fill_link_capability(struct qed_hwfn *hwfn, switch (media_type) { case MEDIA_DA_TWINAX: + *if_capability |= QED_LM_FIBRE_BIT; if (capability & NVM_CFG1_PORT_DRV_SPEED_CAPABILITY_MASK_20G) *if_capability |= QED_LM_20000baseKR2_Full_BIT; /* For DAC media multiple speed capabilities are supported*/ @@ -1707,6 +1708,7 @@ static void qed_fill_link_capability(struct qed_hwfn *hwfn, *if_capability |= QED_LM_100000baseCR4_Full_BIT; break; case MEDIA_BASE_T: + *if_capability |= QED_LM_TP_BIT; if (board_cfg & NVM_CFG1_PORT_PORT_TYPE_EXT_PHY) { if (capability & NVM_CFG1_PORT_DRV_SPEED_CAPABILITY_MASK_1G) { @@ -1718,6 +1720,7 @@ static void qed_fill_link_capability(struct qed_hwfn *hwfn, } } if (board_cfg & NVM_CFG1_PORT_PORT_TYPE_MODULE) { + *if_capability |= QED_LM_FIBRE_BIT; if (tcvr_type == ETH_TRANSCEIVER_TYPE_1000BASET) *if_capability |= QED_LM_1000baseT_Full_BIT; if (tcvr_type == ETH_TRANSCEIVER_TYPE_10G_BASET) @@ -1728,6 +1731,7 @@ static void qed_fill_link_capability(struct qed_hwfn *hwfn, case MEDIA_SFPP_10G_FIBER: case MEDIA_XFP_FIBER: case MEDIA_MODULE_FIBER: + *if_capability |= QED_LM_FIBRE_BIT; if (capability & NVM_CFG1_PORT_DRV_SPEED_CAPABILITY_MASK_1G) { if ((tcvr_type == ETH_TRANSCEIVER_TYPE_1G_LX) || @@ -1770,6 +1774,7 @@ static void qed_fill_link_capability(struct qed_hwfn *hwfn, break; case MEDIA_KR: + *if_capability |= QED_LM_Backplane_BIT; if (capability & NVM_CFG1_PORT_DRV_SPEED_CAPABILITY_MASK_20G) *if_capability |= QED_LM_20000baseKR2_Full_BIT; if (capability & @@ -1821,7 +1826,6 @@ static void qed_fill_link(struct qed_hwfn *hwfn, if_link->link_up = true; /* TODO - at the moment assume supported and advertised speed equal */ - if_link->supported_caps = QED_LM_FIBRE_BIT; if (link_caps.default_speed_autoneg) if_link->supported_caps |= QED_LM_Autoneg_BIT; if (params.pause.autoneg || diff --git a/drivers/net/ethernet/qlogic/qede/qede_ethtool.c b/drivers/net/ethernet/qlogic/qede/qede_ethtool.c index e85f9fef930c..abcee474909a 100644 --- a/drivers/net/ethernet/qlogic/qede/qede_ethtool.c +++ b/drivers/net/ethernet/qlogic/qede/qede_ethtool.c @@ -424,12 +424,13 @@ struct qede_link_mode_mapping { }; static const struct qede_link_mode_mapping qed_lm_map[] = { + {QED_LM_FIBRE_BIT, ETHTOOL_LINK_MODE_FIBRE_BIT}, {QED_LM_Autoneg_BIT, ETHTOOL_LINK_MODE_Autoneg_BIT}, {QED_LM_Asym_Pause_BIT, ETHTOOL_LINK_MODE_Asym_Pause_BIT}, {QED_LM_Pause_BIT, ETHTOOL_LINK_MODE_Pause_BIT}, {QED_LM_1000baseT_Full_BIT, ETHTOOL_LINK_MODE_1000baseT_Full_BIT}, {QED_LM_10000baseT_Full_BIT, ETHTOOL_LINK_MODE_10000baseT_Full_BIT}, - {QED_LM_2500baseX_Full_BIT, ETHTOOL_LINK_MODE_2500baseX_Full_BIT}, + {QED_LM_TP_BIT, ETHTOOL_LINK_MODE_TP_BIT}, {QED_LM_Backplane_BIT, ETHTOOL_LINK_MODE_Backplane_BIT}, {QED_LM_1000baseKX_Full_BIT, ETHTOOL_LINK_MODE_1000baseKX_Full_BIT}, {QED_LM_10000baseKX4_Full_BIT, ETHTOOL_LINK_MODE_10000baseKX4_Full_BIT}, diff --git a/include/linux/qed/qed_if.h b/include/linux/qed/qed_if.h index eef02e64b422..23021366a4e5 100644 --- a/include/linux/qed/qed_if.h +++ b/include/linux/qed/qed_if.h @@ -689,7 +689,7 @@ enum qed_link_mode_bits { QED_LM_40000baseLR4_Full_BIT = BIT(9), QED_LM_50000baseKR2_Full_BIT = BIT(10), QED_LM_100000baseKR4_Full_BIT = BIT(11), - QED_LM_2500baseX_Full_BIT = BIT(12), + QED_LM_TP_BIT = BIT(12), QED_LM_Backplane_BIT = BIT(13), QED_LM_1000baseKX_Full_BIT = BIT(14), QED_LM_10000baseKX4_Full_BIT = BIT(15), -- cgit v1.2.3 From 323ebb61e32b478e2432c5a3cbf9e2ca678a9609 Mon Sep 17 00:00:00 2001 From: Edward Cree Date: Tue, 6 Aug 2019 14:53:55 +0100 Subject: net: use listified RX for handling GRO_NORMAL skbs When GRO decides not to coalesce a packet, in napi_frags_finish(), instead of passing it to the stack immediately, place it on a list in the napi struct. Then, at flush time (napi_complete_done(), napi_poll(), or napi_busy_loop()), call netif_receive_skb_list_internal() on the list. We'd like to do that in napi_gro_flush(), but it's not called if !napi->gro_bitmask, so we have to do it in the callers instead. (There are a handful of drivers that call napi_gro_flush() themselves, but it's not clear why, or whether this will affect them.) Because a full 64 packets is an inefficiently large batch, also consume the list whenever it exceeds gro_normal_batch, a new net/core sysctl that defaults to 8. Signed-off-by: Edward Cree Signed-off-by: David S. Miller --- include/linux/netdevice.h | 3 +++ net/core/dev.c | 44 +++++++++++++++++++++++++++++++++++++++++--- net/core/sysctl_net_core.c | 8 ++++++++ 3 files changed, 52 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 88292953aa6f..55ac223553f8 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -332,6 +332,8 @@ struct napi_struct { struct net_device *dev; struct gro_list gro_hash[GRO_HASH_BUCKETS]; struct sk_buff *skb; + struct list_head rx_list; /* Pending GRO_NORMAL skbs */ + int rx_count; /* length of rx_list */ struct hrtimer timer; struct list_head dev_list; struct hlist_node napi_hash_node; @@ -4239,6 +4241,7 @@ extern int dev_weight_rx_bias; extern int dev_weight_tx_bias; extern int dev_rx_weight; extern int dev_tx_weight; +extern int gro_normal_batch; bool netdev_has_upper_dev(struct net_device *dev, struct net_device *upper_dev); struct net_device *netdev_upper_get_next_dev_rcu(struct net_device *dev, diff --git a/net/core/dev.c b/net/core/dev.c index af071b0ce88e..49589ed2018d 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -3963,6 +3963,8 @@ int dev_weight_rx_bias __read_mostly = 1; /* bias for backlog weight */ int dev_weight_tx_bias __read_mostly = 1; /* bias for output_queue quota */ int dev_rx_weight __read_mostly = 64; int dev_tx_weight __read_mostly = 64; +/* Maximum number of GRO_NORMAL skbs to batch up for list-RX */ +int gro_normal_batch __read_mostly = 8; /* Called with irq disabled */ static inline void ____napi_schedule(struct softnet_data *sd, @@ -5747,6 +5749,26 @@ struct sk_buff *napi_get_frags(struct napi_struct *napi) } EXPORT_SYMBOL(napi_get_frags); +/* Pass the currently batched GRO_NORMAL SKBs up to the stack. */ +static void gro_normal_list(struct napi_struct *napi) +{ + if (!napi->rx_count) + return; + netif_receive_skb_list_internal(&napi->rx_list); + INIT_LIST_HEAD(&napi->rx_list); + napi->rx_count = 0; +} + +/* Queue one GRO_NORMAL SKB up for list processing. If batch size exceeded, + * pass the whole batch up to the stack. + */ +static void gro_normal_one(struct napi_struct *napi, struct sk_buff *skb) +{ + list_add_tail(&skb->list, &napi->rx_list); + if (++napi->rx_count >= gro_normal_batch) + gro_normal_list(napi); +} + static gro_result_t napi_frags_finish(struct napi_struct *napi, struct sk_buff *skb, gro_result_t ret) @@ -5756,8 +5778,8 @@ static gro_result_t napi_frags_finish(struct napi_struct *napi, case GRO_HELD: __skb_push(skb, ETH_HLEN); skb->protocol = eth_type_trans(skb, skb->dev); - if (ret == GRO_NORMAL && netif_receive_skb_internal(skb)) - ret = GRO_DROP; + if (ret == GRO_NORMAL) + gro_normal_one(napi, skb); break; case GRO_DROP: @@ -6034,6 +6056,8 @@ bool napi_complete_done(struct napi_struct *n, int work_done) NAPIF_STATE_IN_BUSY_POLL))) return false; + gro_normal_list(n); + if (n->gro_bitmask) { unsigned long timeout = 0; @@ -6119,10 +6143,19 @@ static void busy_poll_stop(struct napi_struct *napi, void *have_poll_lock) * Ideally, a new ndo_busy_poll_stop() could avoid another round. */ rc = napi->poll(napi, BUSY_POLL_BUDGET); + /* We can't gro_normal_list() here, because napi->poll() might have + * rearmed the napi (napi_complete_done()) in which case it could + * already be running on another CPU. + */ trace_napi_poll(napi, rc, BUSY_POLL_BUDGET); netpoll_poll_unlock(have_poll_lock); - if (rc == BUSY_POLL_BUDGET) + if (rc == BUSY_POLL_BUDGET) { + /* As the whole budget was spent, we still own the napi so can + * safely handle the rx_list. + */ + gro_normal_list(napi); __napi_schedule(napi); + } local_bh_enable(); } @@ -6167,6 +6200,7 @@ restart: } work = napi_poll(napi, BUSY_POLL_BUDGET); trace_napi_poll(napi, work, BUSY_POLL_BUDGET); + gro_normal_list(napi); count: if (work > 0) __NET_ADD_STATS(dev_net(napi->dev), @@ -6272,6 +6306,8 @@ void netif_napi_add(struct net_device *dev, struct napi_struct *napi, napi->timer.function = napi_watchdog; init_gro_hash(napi); napi->skb = NULL; + INIT_LIST_HEAD(&napi->rx_list); + napi->rx_count = 0; napi->poll = poll; if (weight > NAPI_POLL_WEIGHT) netdev_err_once(dev, "%s() called with weight %d\n", __func__, @@ -6368,6 +6404,8 @@ static int napi_poll(struct napi_struct *n, struct list_head *repoll) goto out_unlock; } + gro_normal_list(n); + if (n->gro_bitmask) { /* flush too old packets * If HZ < 1000, flush all packets. diff --git a/net/core/sysctl_net_core.c b/net/core/sysctl_net_core.c index 8da5b3a54dac..eb29e5adc84d 100644 --- a/net/core/sysctl_net_core.c +++ b/net/core/sysctl_net_core.c @@ -567,6 +567,14 @@ static struct ctl_table net_core_table[] = { .mode = 0644, .proc_handler = proc_do_static_key, }, + { + .procname = "gro_normal_batch", + .data = &gro_normal_batch, + .maxlen = sizeof(unsigned int), + .mode = 0644, + .proc_handler = proc_dointvec_minmax, + .extra1 = SYSCTL_ONE, + }, { } }; -- cgit v1.2.3 From 76067459c686c4fc6352613e5a6a54e4ffef2861 Mon Sep 17 00:00:00 2001 From: Jose Abreu Date: Wed, 7 Aug 2019 10:03:12 +0200 Subject: net: stmmac: Implement RSS and enable it in XGMAC core Implement the RSS functionality and add the corresponding callbacks in XGMAC core. Changes from v1: - Do not use magic constants (Jakub) - Use ethtool_rxfh_indir_default() (Jakub) Signed-off-by: Jose Abreu Signed-off-by: David S. Miller --- drivers/net/ethernet/stmicro/stmmac/common.h | 5 ++ drivers/net/ethernet/stmicro/stmmac/dwxgmac2.h | 22 ++++++- .../net/ethernet/stmicro/stmmac/dwxgmac2_core.c | 52 +++++++++++++++ .../net/ethernet/stmicro/stmmac/dwxgmac2_descs.c | 29 +++++++++ drivers/net/ethernet/stmicro/stmmac/dwxgmac2_dma.c | 1 + drivers/net/ethernet/stmicro/stmmac/hwif.h | 11 ++++ drivers/net/ethernet/stmicro/stmmac/stmmac.h | 9 +++ .../net/ethernet/stmicro/stmmac/stmmac_ethtool.c | 75 ++++++++++++++++++++++ drivers/net/ethernet/stmicro/stmmac/stmmac_main.c | 41 +++++++++++- include/linux/stmmac.h | 1 + 10 files changed, 242 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/drivers/net/ethernet/stmicro/stmmac/common.h b/drivers/net/ethernet/stmicro/stmmac/common.h index ed872eed1cab..45a997fe571c 100644 --- a/drivers/net/ethernet/stmicro/stmmac/common.h +++ b/drivers/net/ethernet/stmicro/stmmac/common.h @@ -354,6 +354,7 @@ struct dma_features { unsigned int frpbs; unsigned int frpes; unsigned int addr64; + unsigned int rssen; }; /* GMAC TX FIFO is 8K, Rx FIFO is 16K */ @@ -381,6 +382,10 @@ struct dma_features { #define JUMBO_LEN 9000 +/* Receive Side Scaling */ +#define STMMAC_RSS_HASH_KEY_SIZE 40 +#define STMMAC_RSS_MAX_TABLE_SIZE 256 + extern const struct stmmac_desc_ops enh_desc_ops; extern const struct stmmac_desc_ops ndesc_ops; diff --git a/drivers/net/ethernet/stmicro/stmmac/dwxgmac2.h b/drivers/net/ethernet/stmicro/stmmac/dwxgmac2.h index b77091161765..ed3a85f73a72 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwxgmac2.h +++ b/drivers/net/ethernet/stmicro/stmmac/dwxgmac2.h @@ -89,6 +89,7 @@ #define XGMAC_HWFEAT_RWKSEL BIT(6) #define XGMAC_HWFEAT_GMIISEL BIT(1) #define XGMAC_HW_FEATURE1 0x00000120 +#define XGMAC_HWFEAT_RSSEN BIT(20) #define XGMAC_HWFEAT_TSOEN BIT(18) #define XGMAC_HWFEAT_ADDR64 GENMASK(15, 14) #define XGMAC_HWFEAT_TXFIFOSIZE GENMASK(10, 6) @@ -109,6 +110,17 @@ #define XGMAC_DCS_SHIFT 16 #define XGMAC_ADDRx_LOW(x) (0x00000304 + (x) * 0x8) #define XGMAC_ARP_ADDR 0x00000c10 +#define XGMAC_RSS_CTRL 0x00000c80 +#define XGMAC_UDP4TE BIT(3) +#define XGMAC_TCP4TE BIT(2) +#define XGMAC_IP2TE BIT(1) +#define XGMAC_RSSE BIT(0) +#define XGMAC_RSS_ADDR 0x00000c88 +#define XGMAC_RSSIA_SHIFT 8 +#define XGMAC_ADDRT BIT(2) +#define XGMAC_CT BIT(1) +#define XGMAC_OB BIT(0) +#define XGMAC_RSS_DATA 0x00000c8c #define XGMAC_TIMESTAMP_STATUS 0x00000d20 #define XGMAC_TXTSC BIT(15) #define XGMAC_TXTIMESTAMP_NSEC 0x00000d30 @@ -125,8 +137,9 @@ #define XGMAC_MTL_INT_STATUS 0x00001020 #define XGMAC_MTL_RXQ_DMA_MAP0 0x00001030 #define XGMAC_MTL_RXQ_DMA_MAP1 0x00001034 -#define XGMAC_QxMDMACH(x) GENMASK((x) * 8 + 3, (x) * 8) +#define XGMAC_QxMDMACH(x) GENMASK((x) * 8 + 7, (x) * 8) #define XGMAC_QxMDMACH_SHIFT(x) ((x) * 8) +#define XGMAC_QDDMACH BIT(7) #define XGMAC_TC_PRTY_MAP0 0x00001040 #define XGMAC_TC_PRTY_MAP1 0x00001044 #define XGMAC_PSTC(x) GENMASK((x) * 8 + 7, (x) * 8) @@ -261,6 +274,13 @@ #define XGMAC_RDES3_IOC BIT(30) #define XGMAC_RDES3_LD BIT(28) #define XGMAC_RDES3_CDA BIT(27) +#define XGMAC_RDES3_RSV BIT(26) +#define XGMAC_RDES3_L34T GENMASK(23, 20) +#define XGMAC_RDES3_L34T_SHIFT 20 +#define XGMAC_L34T_IP4TCP 0x1 +#define XGMAC_L34T_IP4UDP 0x2 +#define XGMAC_L34T_IP6TCP 0x9 +#define XGMAC_L34T_IP6UDP 0xA #define XGMAC_RDES3_ES BIT(15) #define XGMAC_RDES3_PL GENMASK(13, 0) #define XGMAC_RDES3_TSD BIT(6) diff --git a/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_core.c b/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_core.c index bfbd5ae11540..04eec85acc59 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_core.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_core.c @@ -6,6 +6,7 @@ #include #include +#include #include "stmmac.h" #include "dwxgmac2.h" @@ -439,6 +440,56 @@ static void dwxgmac2_set_mac_loopback(void __iomem *ioaddr, bool enable) writel(value, ioaddr + XGMAC_RX_CONFIG); } +static int dwxgmac2_rss_write_reg(void __iomem *ioaddr, bool is_key, int idx, + u32 val) +{ + u32 ctrl = 0; + + writel(val, ioaddr + XGMAC_RSS_DATA); + ctrl |= idx << XGMAC_RSSIA_SHIFT; + ctrl |= is_key ? XGMAC_ADDRT : 0x0; + ctrl |= XGMAC_OB; + writel(ctrl, ioaddr + XGMAC_RSS_ADDR); + + return readl_poll_timeout(ioaddr + XGMAC_RSS_ADDR, ctrl, + !(ctrl & XGMAC_OB), 100, 10000); +} + +static int dwxgmac2_rss_configure(struct mac_device_info *hw, + struct stmmac_rss *cfg, u32 num_rxq) +{ + void __iomem *ioaddr = hw->pcsr; + u32 *key = (u32 *)cfg->key; + int i, ret; + u32 value; + + value = readl(ioaddr + XGMAC_RSS_CTRL); + if (!cfg->enable) { + value &= ~XGMAC_RSSE; + writel(value, ioaddr + XGMAC_RSS_CTRL); + return 0; + } + + for (i = 0; i < (sizeof(cfg->key) / sizeof(u32)); i++) { + ret = dwxgmac2_rss_write_reg(ioaddr, true, i, *key++); + if (ret) + return ret; + } + + for (i = 0; i < ARRAY_SIZE(cfg->table); i++) { + ret = dwxgmac2_rss_write_reg(ioaddr, false, i, cfg->table[i]); + if (ret) + return ret; + } + + for (i = 0; i < num_rxq; i++) + dwxgmac2_map_mtl_to_dma(hw, i, XGMAC_QDDMACH); + + value |= XGMAC_UDP4TE | XGMAC_TCP4TE | XGMAC_IP2TE | XGMAC_RSSE; + writel(value, ioaddr + XGMAC_RSS_CTRL); + return 0; +} + const struct stmmac_ops dwxgmac210_ops = { .core_init = dwxgmac2_core_init, .set_mac = dwxgmac2_set_mac, @@ -469,6 +520,7 @@ const struct stmmac_ops dwxgmac210_ops = { .debug = NULL, .set_filter = dwxgmac2_set_filter, .set_mac_loopback = dwxgmac2_set_mac_loopback, + .rss_configure = dwxgmac2_rss_configure, }; int dwxgmac2_setup(struct stmmac_priv *priv) diff --git a/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_descs.c b/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_descs.c index c4c45402b8f8..8c5dd6a36157 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_descs.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_descs.c @@ -254,6 +254,34 @@ static void dwxgmac2_clear(struct dma_desc *p) p->des3 = 0; } +static int dwxgmac2_get_rx_hash(struct dma_desc *p, u32 *hash, + enum pkt_hash_types *type) +{ + unsigned int rdes3 = le32_to_cpu(p->des3); + u32 ptype; + + if (rdes3 & XGMAC_RDES3_RSV) { + ptype = (rdes3 & XGMAC_RDES3_L34T) >> XGMAC_RDES3_L34T_SHIFT; + + switch (ptype) { + case XGMAC_L34T_IP4TCP: + case XGMAC_L34T_IP4UDP: + case XGMAC_L34T_IP6TCP: + case XGMAC_L34T_IP6UDP: + *type = PKT_HASH_TYPE_L4; + break; + default: + *type = PKT_HASH_TYPE_L3; + break; + } + + *hash = le32_to_cpu(p->des1); + return 0; + } + + return -EINVAL; +} + const struct stmmac_desc_ops dwxgmac210_desc_ops = { .tx_status = dwxgmac2_get_tx_status, .rx_status = dwxgmac2_get_rx_status, @@ -277,4 +305,5 @@ const struct stmmac_desc_ops dwxgmac210_desc_ops = { .get_addr = dwxgmac2_get_addr, .set_addr = dwxgmac2_set_addr, .clear = dwxgmac2_clear, + .get_rx_hash = dwxgmac2_get_rx_hash, }; diff --git a/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_dma.c b/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_dma.c index 0f1c772e892a..45a6634ee397 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_dma.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_dma.c @@ -363,6 +363,7 @@ static void dwxgmac2_get_hw_feature(void __iomem *ioaddr, /* MAC HW feature 1 */ hw_cap = readl(ioaddr + XGMAC_HW_FEATURE1); + dma_cap->rssen = (hw_cap & XGMAC_HWFEAT_RSSEN) >> 20; dma_cap->tsoen = (hw_cap & XGMAC_HWFEAT_TSOEN) >> 18; dma_cap->addr64 = (hw_cap & XGMAC_HWFEAT_ADDR64) >> 14; diff --git a/drivers/net/ethernet/stmicro/stmmac/hwif.h b/drivers/net/ethernet/stmicro/stmmac/hwif.h index 00539a09d1db..bfe7efee9481 100644 --- a/drivers/net/ethernet/stmicro/stmmac/hwif.h +++ b/drivers/net/ethernet/stmicro/stmmac/hwif.h @@ -86,6 +86,9 @@ struct stmmac_desc_ops { void (*set_addr)(struct dma_desc *p, dma_addr_t addr); /* clear descriptor */ void (*clear)(struct dma_desc *p); + /* RSS */ + int (*get_rx_hash)(struct dma_desc *p, u32 *hash, + enum pkt_hash_types *type); }; #define stmmac_init_rx_desc(__priv, __args...) \ @@ -136,6 +139,8 @@ struct stmmac_desc_ops { stmmac_do_void_callback(__priv, desc, set_addr, __args) #define stmmac_clear_desc(__priv, __args...) \ stmmac_do_void_callback(__priv, desc, clear, __args) +#define stmmac_get_rx_hash(__priv, __args...) \ + stmmac_do_callback(__priv, desc, get_rx_hash, __args) struct stmmac_dma_cfg; struct dma_features; @@ -249,6 +254,7 @@ struct rgmii_adv; struct stmmac_safety_stats; struct stmmac_tc_entry; struct stmmac_pps_cfg; +struct stmmac_rss; /* Helpers to program the MAC core */ struct stmmac_ops { @@ -327,6 +333,9 @@ struct stmmac_ops { u32 sub_second_inc, u32 systime_flags); /* Loopback for selftests */ void (*set_mac_loopback)(void __iomem *ioaddr, bool enable); + /* RSS */ + int (*rss_configure)(struct mac_device_info *hw, + struct stmmac_rss *cfg, u32 num_rxq); }; #define stmmac_core_init(__priv, __args...) \ @@ -397,6 +406,8 @@ struct stmmac_ops { stmmac_do_callback(__priv, mac, flex_pps_config, __args) #define stmmac_set_mac_loopback(__priv, __args...) \ stmmac_do_void_callback(__priv, mac, set_mac_loopback, __args) +#define stmmac_rss_configure(__priv, __args...) \ + stmmac_do_callback(__priv, mac, rss_configure, __args) /* PTP and HW Timer helpers */ struct stmmac_hwtimestamp { diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac.h b/drivers/net/ethernet/stmicro/stmmac/stmmac.h index 5cd966c154f3..d2f6f56ae29c 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac.h +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac.h @@ -113,6 +113,12 @@ struct stmmac_pps_cfg { struct timespec64 period; }; +struct stmmac_rss { + int enable; + u8 key[STMMAC_RSS_HASH_KEY_SIZE]; + u32 table[STMMAC_RSS_MAX_TABLE_SIZE]; +}; + struct stmmac_priv { /* Frequently used values are kept adjacent for cache effect */ u32 tx_coal_frames; @@ -203,6 +209,9 @@ struct stmmac_priv { /* Pulse Per Second output */ struct stmmac_pps_cfg pps[STMMAC_PPS_MAX]; + + /* Receive Side Scaling */ + struct stmmac_rss rss; }; enum stmmac_state { diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_ethtool.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_ethtool.c index d294590cba27..2423160ab582 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_ethtool.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_ethtool.c @@ -764,6 +764,76 @@ static int stmmac_set_coalesce(struct net_device *dev, return 0; } +static int stmmac_get_rxnfc(struct net_device *dev, + struct ethtool_rxnfc *rxnfc, u32 *rule_locs) +{ + struct stmmac_priv *priv = netdev_priv(dev); + + switch (rxnfc->cmd) { + case ETHTOOL_GRXRINGS: + rxnfc->data = priv->plat->rx_queues_to_use; + break; + default: + return -EOPNOTSUPP; + } + + return 0; +} + +static u32 stmmac_get_rxfh_key_size(struct net_device *dev) +{ + struct stmmac_priv *priv = netdev_priv(dev); + + return sizeof(priv->rss.key); +} + +static u32 stmmac_get_rxfh_indir_size(struct net_device *dev) +{ + struct stmmac_priv *priv = netdev_priv(dev); + + return ARRAY_SIZE(priv->rss.table); +} + +static int stmmac_get_rxfh(struct net_device *dev, u32 *indir, u8 *key, + u8 *hfunc) +{ + struct stmmac_priv *priv = netdev_priv(dev); + int i; + + if (indir) { + for (i = 0; i < ARRAY_SIZE(priv->rss.table); i++) + indir[i] = priv->rss.table[i]; + } + + if (key) + memcpy(key, priv->rss.key, sizeof(priv->rss.key)); + if (hfunc) + *hfunc = ETH_RSS_HASH_TOP; + + return 0; +} + +static int stmmac_set_rxfh(struct net_device *dev, const u32 *indir, + const u8 *key, const u8 hfunc) +{ + struct stmmac_priv *priv = netdev_priv(dev); + int i; + + if ((hfunc != ETH_RSS_HASH_NO_CHANGE) && (hfunc != ETH_RSS_HASH_TOP)) + return -EOPNOTSUPP; + + if (indir) { + for (i = 0; i < ARRAY_SIZE(priv->rss.table); i++) + priv->rss.table[i] = indir[i]; + } + + if (key) + memcpy(priv->rss.key, key, sizeof(priv->rss.key)); + + return stmmac_rss_configure(priv, priv->hw, &priv->rss, + priv->plat->rx_queues_to_use); +} + static int stmmac_get_ts_info(struct net_device *dev, struct ethtool_ts_info *info) { @@ -855,6 +925,11 @@ static const struct ethtool_ops stmmac_ethtool_ops = { .get_eee = stmmac_ethtool_op_get_eee, .set_eee = stmmac_ethtool_op_set_eee, .get_sset_count = stmmac_get_sset_count, + .get_rxnfc = stmmac_get_rxnfc, + .get_rxfh_key_size = stmmac_get_rxfh_key_size, + .get_rxfh_indir_size = stmmac_get_rxfh_indir_size, + .get_rxfh = stmmac_get_rxfh, + .set_rxfh = stmmac_set_rxfh, .get_ts_info = stmmac_get_ts_info, .get_coalesce = stmmac_get_coalesce, .set_coalesce = stmmac_set_coalesce, diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c index fd54c7c87485..404a0548f213 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c @@ -2417,6 +2417,22 @@ static void stmmac_mac_config_rx_queues_routing(struct stmmac_priv *priv) } } +static void stmmac_mac_config_rss(struct stmmac_priv *priv) +{ + if (!priv->dma_cap.rssen || !priv->plat->rss_en) { + priv->rss.enable = false; + return; + } + + if (priv->dev->features & NETIF_F_RXHASH) + priv->rss.enable = true; + else + priv->rss.enable = false; + + stmmac_rss_configure(priv, priv->hw, &priv->rss, + priv->plat->rx_queues_to_use); +} + /** * stmmac_mtl_configuration - Configure MTL * @priv: driver private structure @@ -2461,6 +2477,10 @@ static void stmmac_mtl_configuration(struct stmmac_priv *priv) /* Set RX routing */ if (rx_queues_count > 1) stmmac_mac_config_rx_queues_routing(priv); + + /* Receive Side Scaling */ + if (rx_queues_count > 1) + stmmac_mac_config_rss(priv); } static void stmmac_safety_feat_configuration(struct stmmac_priv *priv) @@ -3385,9 +3405,11 @@ static int stmmac_rx(struct stmmac_priv *priv, int limit, u32 queue) priv->dev->stats.rx_errors++; buf->page = NULL; } else { + enum pkt_hash_types hash_type; struct sk_buff *skb; - int frame_len; unsigned int des; + int frame_len; + u32 hash; stmmac_get_desc_addr(priv, p, &des); frame_len = stmmac_get_rx_frame_len(priv, p, coe); @@ -3452,6 +3474,10 @@ static int stmmac_rx(struct stmmac_priv *priv, int limit, u32 queue) else skb->ip_summed = CHECKSUM_UNNECESSARY; + if (!stmmac_get_rx_hash(priv, p, &hash, &hash_type)) + skb_set_hash(skb, hash, hash_type); + + skb_record_rx_queue(skb, queue); napi_gro_receive(&ch->rx_napi, skb); /* Data payload copied into SKB, page ready for recycle */ @@ -4175,8 +4201,8 @@ int stmmac_dvr_probe(struct device *device, { struct net_device *ndev = NULL; struct stmmac_priv *priv; - u32 queue, maxq; - int ret = 0; + u32 queue, rxq, maxq; + int i, ret = 0; ndev = devm_alloc_etherdev_mqs(device, sizeof(struct stmmac_priv), MTL_MAX_TX_QUEUES, MTL_MAX_RX_QUEUES); @@ -4284,6 +4310,15 @@ int stmmac_dvr_probe(struct device *device, #endif priv->msg_enable = netif_msg_init(debug, default_msg_level); + /* Initialize RSS */ + rxq = priv->plat->rx_queues_to_use; + netdev_rss_key_fill(priv->rss.key, sizeof(priv->rss.key)); + for (i = 0; i < ARRAY_SIZE(priv->rss.table); i++) + priv->rss.table[i] = ethtool_rxfh_indir_default(i, rxq); + + if (priv->dma_cap.rssen && priv->plat->rss_en) + ndev->features |= NETIF_F_RXHASH; + /* MTU range: 46 - hw-specific max */ ndev->min_mtu = ETH_ZLEN - ETH_HLEN; if ((priv->plat->enh_desc) || (priv->synopsys_id >= DWMAC_CORE_4_00)) diff --git a/include/linux/stmmac.h b/include/linux/stmmac.h index 7b3e354bcd3c..5cc6b6faf359 100644 --- a/include/linux/stmmac.h +++ b/include/linux/stmmac.h @@ -173,6 +173,7 @@ struct plat_stmmacenet_data { int has_gmac4; bool has_sun8i; bool tso_en; + int rss_en; int mac_port_sel_speed; bool en_tx_lpi_clockgating; int has_xgmac; -- cgit v1.2.3 From dd58edc328cec1a0d837f3f2f41e9955ec623e3e Mon Sep 17 00:00:00 2001 From: Vlad Buslov Date: Fri, 1 Jun 2018 21:47:43 +0300 Subject: net/mlx5e: Extend mod header entry with reference counter List of flows attached to mod header entry is used as implicit reference counter (mod header entry is deallocated when list becomes free) and as a mechanism to obtain mod header entry that flow is attached to (through list head). This is not safe when concurrent modification of list of flows attached to mod header entry is possible. Proper atomic reference counter is required to support concurrent access. As a preparation for extending mod header with reference counting, extract code that lookups and deletes mod header entry into standalone put/get helpers. In order to remove this dependency on external locking, extend mod header entry with reference counter to manage its lifetime and extend flow structure with direct pointer to mod header entry that flow is attached to. To remove code duplication between legacy and switchdev mode implementations that both support mod_hdr functionality, store mod_hdr table in dedicated structure used by both fdb and kernel namespaces. New table structure is extended with table lock by one of the following patches in this series. Implement helper function to get correct mod_hdr table depending on flow namespace. Signed-off-by: Vlad Buslov Reviewed-by: Jianbo Liu Reviewed-by: Roi Dayan Signed-off-by: Saeed Mahameed --- drivers/net/ethernet/mellanox/mlx5/core/en/fs.h | 2 +- drivers/net/ethernet/mellanox/mlx5/core/en_tc.c | 94 +++++++++++++---------- drivers/net/ethernet/mellanox/mlx5/core/eswitch.c | 2 +- drivers/net/ethernet/mellanox/mlx5/core/eswitch.h | 2 +- include/linux/mlx5/fs.h | 4 + 5 files changed, 61 insertions(+), 43 deletions(-) (limited to 'include/linux') diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/fs.h b/drivers/net/ethernet/mellanox/mlx5/core/en/fs.h index 100506a3dd58..ca2161b42c7f 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/fs.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/fs.h @@ -16,7 +16,7 @@ struct mlx5e_tc_table { struct rhashtable ht; - DECLARE_HASHTABLE(mod_hdr_tbl, 8); + struct mod_hdr_tbl mod_hdr; struct mutex hairpin_tbl_lock; /* protects hairpin_tbl */ DECLARE_HASHTABLE(hairpin_tbl, 8); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c index b6a91e3054c0..fe1b04aa910a 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c @@ -119,6 +119,7 @@ struct mlx5e_tc_flow { */ struct encap_flow_item encaps[MLX5_MAX_FLOW_FWD_VPORTS]; struct mlx5e_tc_flow *peer_flow; + struct mlx5e_mod_hdr_entry *mh; /* attached mod header instance */ struct list_head mod_hdr; /* flows sharing the same mod hdr ID */ struct mlx5e_hairpin_entry *hpe; /* attached hairpin instance */ struct list_head hairpin; /* flows sharing the same hairpin */ @@ -194,6 +195,8 @@ struct mlx5e_mod_hdr_entry { struct mod_hdr_key key; u32 mod_hdr_id; + + refcount_t refcnt; }; #define MLX5_MH_ACT_SZ MLX5_UN_SZ_BYTES(set_action_in_add_action_in_auto) @@ -284,14 +287,51 @@ static inline int cmp_mod_hdr_info(struct mod_hdr_key *a, return memcmp(a->actions, b->actions, a->num_actions * MLX5_MH_ACT_SZ); } +static struct mod_hdr_tbl * +get_mod_hdr_table(struct mlx5e_priv *priv, int namespace) +{ + struct mlx5_eswitch *esw = priv->mdev->priv.eswitch; + + return namespace == MLX5_FLOW_NAMESPACE_FDB ? &esw->offloads.mod_hdr : + &priv->fs.tc.mod_hdr; +} + +static struct mlx5e_mod_hdr_entry * +mlx5e_mod_hdr_get(struct mod_hdr_tbl *tbl, struct mod_hdr_key *key, u32 hash_key) +{ + struct mlx5e_mod_hdr_entry *mh, *found = NULL; + + hash_for_each_possible(tbl->hlist, mh, mod_hdr_hlist, hash_key) { + if (!cmp_mod_hdr_info(&mh->key, key)) { + refcount_inc(&mh->refcnt); + found = mh; + break; + } + } + + return found; +} + +static void mlx5e_mod_hdr_put(struct mlx5e_priv *priv, + struct mlx5e_mod_hdr_entry *mh) +{ + if (!refcount_dec_and_test(&mh->refcnt)) + return; + + WARN_ON(!list_empty(&mh->flows)); + mlx5_modify_header_dealloc(priv->mdev, mh->mod_hdr_id); + hash_del(&mh->mod_hdr_hlist); + kfree(mh); +} + static int mlx5e_attach_mod_hdr(struct mlx5e_priv *priv, struct mlx5e_tc_flow *flow, struct mlx5e_tc_flow_parse_attr *parse_attr) { - struct mlx5_eswitch *esw = priv->mdev->priv.eswitch; + bool is_eswitch_flow = mlx5e_is_eswitch_flow(flow); int num_actions, actions_size, namespace, err; - bool found = false, is_eswitch_flow; struct mlx5e_mod_hdr_entry *mh; + struct mod_hdr_tbl *tbl; struct mod_hdr_key key; u32 hash_key; @@ -303,28 +343,12 @@ static int mlx5e_attach_mod_hdr(struct mlx5e_priv *priv, hash_key = hash_mod_hdr_info(&key); - is_eswitch_flow = mlx5e_is_eswitch_flow(flow); - if (is_eswitch_flow) { - namespace = MLX5_FLOW_NAMESPACE_FDB; - hash_for_each_possible(esw->offloads.mod_hdr_tbl, mh, - mod_hdr_hlist, hash_key) { - if (!cmp_mod_hdr_info(&mh->key, &key)) { - found = true; - break; - } - } - } else { - namespace = MLX5_FLOW_NAMESPACE_KERNEL; - hash_for_each_possible(priv->fs.tc.mod_hdr_tbl, mh, - mod_hdr_hlist, hash_key) { - if (!cmp_mod_hdr_info(&mh->key, &key)) { - found = true; - break; - } - } - } + namespace = is_eswitch_flow ? + MLX5_FLOW_NAMESPACE_FDB : MLX5_FLOW_NAMESPACE_KERNEL; + tbl = get_mod_hdr_table(priv, namespace); - if (found) + mh = mlx5e_mod_hdr_get(tbl, &key, hash_key); + if (mh) goto attach_flow; mh = kzalloc(sizeof(*mh) + actions_size, GFP_KERNEL); @@ -335,6 +359,7 @@ static int mlx5e_attach_mod_hdr(struct mlx5e_priv *priv, memcpy(mh->key.actions, key.actions, actions_size); mh->key.num_actions = num_actions; INIT_LIST_HEAD(&mh->flows); + refcount_set(&mh->refcnt, 1); err = mlx5_modify_header_alloc(priv->mdev, namespace, mh->key.num_actions, @@ -343,12 +368,10 @@ static int mlx5e_attach_mod_hdr(struct mlx5e_priv *priv, if (err) goto out_err; - if (is_eswitch_flow) - hash_add(esw->offloads.mod_hdr_tbl, &mh->mod_hdr_hlist, hash_key); - else - hash_add(priv->fs.tc.mod_hdr_tbl, &mh->mod_hdr_hlist, hash_key); + hash_add(tbl->hlist, &mh->mod_hdr_hlist, hash_key); attach_flow: + flow->mh = mh; list_add(&flow->mod_hdr, &mh->flows); if (is_eswitch_flow) flow->esw_attr->mod_hdr_id = mh->mod_hdr_id; @@ -365,23 +388,14 @@ out_err: static void mlx5e_detach_mod_hdr(struct mlx5e_priv *priv, struct mlx5e_tc_flow *flow) { - struct list_head *next = flow->mod_hdr.next; - /* flow wasn't fully initialized */ - if (list_empty(&flow->mod_hdr)) + if (!flow->mh) return; list_del(&flow->mod_hdr); - if (list_empty(next)) { - struct mlx5e_mod_hdr_entry *mh; - - mh = list_entry(next, struct mlx5e_mod_hdr_entry, flows); - - mlx5_modify_header_dealloc(priv->mdev, mh->mod_hdr_id); - hash_del(&mh->mod_hdr_hlist); - kfree(mh); - } + mlx5e_mod_hdr_put(priv, flow->mh); + flow->mh = NULL; } static @@ -3844,7 +3858,7 @@ int mlx5e_tc_nic_init(struct mlx5e_priv *priv) int err; mutex_init(&tc->t_lock); - hash_init(tc->mod_hdr_tbl); + hash_init(tc->mod_hdr.hlist); mutex_init(&tc->hairpin_tbl_lock); hash_init(tc->hairpin_tbl); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c index 5fbebee7254d..5ce3c81e3083 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c @@ -2000,7 +2000,7 @@ int mlx5_eswitch_init(struct mlx5_core_dev *dev) goto abort; hash_init(esw->offloads.encap_tbl); - hash_init(esw->offloads.mod_hdr_tbl); + hash_init(esw->offloads.mod_hdr.hlist); atomic64_set(&esw->offloads.num_flows, 0); mutex_init(&esw->state_lock); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h index 804912e38dee..fd63ba4ed0da 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h @@ -182,7 +182,7 @@ struct mlx5_esw_offload { struct list_head peer_flows; struct mutex peer_mutex; DECLARE_HASHTABLE(encap_tbl, 8); - DECLARE_HASHTABLE(mod_hdr_tbl, 8); + struct mod_hdr_tbl mod_hdr; DECLARE_HASHTABLE(termtbl_tbl, 8); struct mutex termtbl_mutex; /* protects termtbl hash */ const struct mlx5_eswitch_rep_ops *rep_ops[NUM_REP_TYPES]; diff --git a/include/linux/mlx5/fs.h b/include/linux/mlx5/fs.h index f049af3f3cd8..96650a33aa91 100644 --- a/include/linux/mlx5/fs.h +++ b/include/linux/mlx5/fs.h @@ -126,6 +126,10 @@ struct mlx5_flow_destination { }; }; +struct mod_hdr_tbl { + DECLARE_HASHTABLE(hlist, 8); +}; + struct mlx5_flow_namespace * mlx5_get_fdb_sub_ns(struct mlx5_core_dev *dev, int n); struct mlx5_flow_namespace * -- cgit v1.2.3 From d2faae25c3050a87c8ff965a7939e999e3154b62 Mon Sep 17 00:00:00 2001 From: Vlad Buslov Date: Fri, 9 Aug 2019 13:20:48 +0300 Subject: net/mlx5e: Protect mod_hdr hash table with mutex To remove dependency on rtnl lock, protect mod_hdr hash table from concurrent modifications with new mutex. Implement helper function to get flow namespace to prevent code duplication. Signed-off-by: Vlad Buslov Reviewed-by: Roi Dayan Signed-off-by: Saeed Mahameed --- drivers/net/ethernet/mellanox/mlx5/core/en_tc.c | 35 ++++++++++++++++------- drivers/net/ethernet/mellanox/mlx5/core/eswitch.c | 2 ++ include/linux/mlx5/fs.h | 1 + 3 files changed, 28 insertions(+), 10 deletions(-) (limited to 'include/linux') diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c index 09d5cc700297..0600b7878600 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c @@ -315,22 +315,31 @@ mlx5e_mod_hdr_get(struct mod_hdr_tbl *tbl, struct mod_hdr_key *key, u32 hash_key } static void mlx5e_mod_hdr_put(struct mlx5e_priv *priv, - struct mlx5e_mod_hdr_entry *mh) + struct mlx5e_mod_hdr_entry *mh, + int namespace) { - if (!refcount_dec_and_test(&mh->refcnt)) + struct mod_hdr_tbl *tbl = get_mod_hdr_table(priv, namespace); + + if (!refcount_dec_and_mutex_lock(&mh->refcnt, &tbl->lock)) return; + hash_del(&mh->mod_hdr_hlist); + mutex_unlock(&tbl->lock); WARN_ON(!list_empty(&mh->flows)); mlx5_modify_header_dealloc(priv->mdev, mh->mod_hdr_id); - hash_del(&mh->mod_hdr_hlist); + kfree(mh); } +static int get_flow_name_space(struct mlx5e_tc_flow *flow) +{ + return mlx5e_is_eswitch_flow(flow) ? + MLX5_FLOW_NAMESPACE_FDB : MLX5_FLOW_NAMESPACE_KERNEL; +} static int mlx5e_attach_mod_hdr(struct mlx5e_priv *priv, struct mlx5e_tc_flow *flow, struct mlx5e_tc_flow_parse_attr *parse_attr) { - bool is_eswitch_flow = mlx5e_is_eswitch_flow(flow); int num_actions, actions_size, namespace, err; struct mlx5e_mod_hdr_entry *mh; struct mod_hdr_tbl *tbl; @@ -345,17 +354,19 @@ static int mlx5e_attach_mod_hdr(struct mlx5e_priv *priv, hash_key = hash_mod_hdr_info(&key); - namespace = is_eswitch_flow ? - MLX5_FLOW_NAMESPACE_FDB : MLX5_FLOW_NAMESPACE_KERNEL; + namespace = get_flow_name_space(flow); tbl = get_mod_hdr_table(priv, namespace); + mutex_lock(&tbl->lock); mh = mlx5e_mod_hdr_get(tbl, &key, hash_key); if (mh) goto attach_flow; mh = kzalloc(sizeof(*mh) + actions_size, GFP_KERNEL); - if (!mh) - return -ENOMEM; + if (!mh) { + err = -ENOMEM; + goto out_err; + } mh->key.actions = (void *)mh + sizeof(*mh); memcpy(mh->key.actions, key.actions, actions_size); @@ -374,11 +385,12 @@ static int mlx5e_attach_mod_hdr(struct mlx5e_priv *priv, hash_add(tbl->hlist, &mh->mod_hdr_hlist, hash_key); attach_flow: + mutex_unlock(&tbl->lock); flow->mh = mh; spin_lock(&mh->flows_lock); list_add(&flow->mod_hdr, &mh->flows); spin_unlock(&mh->flows_lock); - if (is_eswitch_flow) + if (mlx5e_is_eswitch_flow(flow)) flow->esw_attr->mod_hdr_id = mh->mod_hdr_id; else flow->nic_attr->mod_hdr_id = mh->mod_hdr_id; @@ -386,6 +398,7 @@ attach_flow: return 0; out_err: + mutex_unlock(&tbl->lock); kfree(mh); return err; } @@ -401,7 +414,7 @@ static void mlx5e_detach_mod_hdr(struct mlx5e_priv *priv, list_del(&flow->mod_hdr); spin_unlock(&flow->mh->flows_lock); - mlx5e_mod_hdr_put(priv, flow->mh); + mlx5e_mod_hdr_put(priv, flow->mh, get_flow_name_space(flow)); flow->mh = NULL; } @@ -3865,6 +3878,7 @@ int mlx5e_tc_nic_init(struct mlx5e_priv *priv) int err; mutex_init(&tc->t_lock); + mutex_init(&tc->mod_hdr.lock); hash_init(tc->mod_hdr.hlist); mutex_init(&tc->hairpin_tbl_lock); hash_init(tc->hairpin_tbl); @@ -3898,6 +3912,7 @@ void mlx5e_tc_nic_cleanup(struct mlx5e_priv *priv) if (tc->netdevice_nb.notifier_call) unregister_netdevice_notifier(&tc->netdevice_nb); + mutex_destroy(&tc->mod_hdr.lock); mutex_destroy(&tc->hairpin_tbl_lock); rhashtable_destroy(&tc->ht); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c index 5ce3c81e3083..2d734ecae719 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c @@ -2000,6 +2000,7 @@ int mlx5_eswitch_init(struct mlx5_core_dev *dev) goto abort; hash_init(esw->offloads.encap_tbl); + mutex_init(&esw->offloads.mod_hdr.lock); hash_init(esw->offloads.mod_hdr.hlist); atomic64_set(&esw->offloads.num_flows, 0); mutex_init(&esw->state_lock); @@ -2037,6 +2038,7 @@ void mlx5_eswitch_cleanup(struct mlx5_eswitch *esw) esw->dev->priv.eswitch = NULL; destroy_workqueue(esw->work_queue); esw_offloads_cleanup_reps(esw); + mutex_destroy(&esw->offloads.mod_hdr.lock); kfree(esw->vports); kfree(esw); } diff --git a/include/linux/mlx5/fs.h b/include/linux/mlx5/fs.h index 96650a33aa91..1cb1045ce313 100644 --- a/include/linux/mlx5/fs.h +++ b/include/linux/mlx5/fs.h @@ -127,6 +127,7 @@ struct mlx5_flow_destination { }; struct mod_hdr_tbl { + struct mutex lock; /* protects hlist */ DECLARE_HASHTABLE(hlist, 8); }; -- cgit v1.2.3 From ef2e4094e076858343ea1202046443f642a245cd Mon Sep 17 00:00:00 2001 From: Parav Pandit Date: Fri, 26 Jul 2019 08:26:52 -0500 Subject: net/mlx5: E-switch, Removed unused hwid Currently mlx5_eswitch_rep stores same hw ID for all representors. However it is never used from this structure. It is always used from mlx5_vport. Hence, remove unused field. Signed-off-by: Parav Pandit Reviewed-by: Vu Pham Signed-off-by: Saeed Mahameed --- drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c | 6 +----- include/linux/mlx5/eswitch.h | 1 - 2 files changed, 1 insertion(+), 6 deletions(-) (limited to 'include/linux') diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c index 8fe5dddf18d0..42cc5001255b 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c @@ -1393,10 +1393,9 @@ void esw_offloads_cleanup_reps(struct mlx5_eswitch *esw) int esw_offloads_init_reps(struct mlx5_eswitch *esw) { int total_vports = esw->total_vports; - struct mlx5_core_dev *dev = esw->dev; struct mlx5_eswitch_rep *rep; - u8 hw_id[ETH_ALEN], rep_type; int vport_index; + u8 rep_type; esw->offloads.vport_reps = kcalloc(total_vports, sizeof(struct mlx5_eswitch_rep), @@ -1404,12 +1403,9 @@ int esw_offloads_init_reps(struct mlx5_eswitch *esw) if (!esw->offloads.vport_reps) return -ENOMEM; - mlx5_query_mac_address(dev, hw_id); - mlx5_esw_for_all_reps(esw, vport_index, rep) { rep->vport = mlx5_eswitch_index_to_vport_num(esw, vport_index); rep->vport_index = vport_index; - ether_addr_copy(rep->hw_id, hw_id); for (rep_type = 0; rep_type < NUM_REP_TYPES; rep_type++) atomic_set(&rep->rep_data[rep_type].state, diff --git a/include/linux/mlx5/eswitch.h b/include/linux/mlx5/eswitch.h index 46b5ba029802..38a70d16d8d5 100644 --- a/include/linux/mlx5/eswitch.h +++ b/include/linux/mlx5/eswitch.h @@ -44,7 +44,6 @@ struct mlx5_eswitch_rep_data { struct mlx5_eswitch_rep { struct mlx5_eswitch_rep_data rep_data[NUM_REP_TYPES]; u16 vport; - u8 hw_id[ETH_ALEN]; u16 vlan; /* Only IB rep is using vport_index */ u16 vport_index; -- cgit v1.2.3 From a62052ba2aecb9269a32efeb3e22f96b83a13304 Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Sat, 10 Aug 2019 12:17:16 +0200 Subject: wimax: no need to check return value of debugfs_create functions When calling debugfs functions, there is no need to ever check the return value. The function can work or not, but the code logic should never do something different based on this. This cleans up a lot of unneeded code and logic around the debugfs wimax files, making all of this much simpler and easier to understand. Cc: Inaky Perez-Gonzalez Cc: linux-wimax@intel.com Cc: netdev@vger.kernel.org Signed-off-by: Greg Kroah-Hartman Signed-off-by: David S. Miller --- drivers/net/wimax/i2400m/debugfs.c | 150 ++++++------------------------------- drivers/net/wimax/i2400m/driver.c | 7 +- drivers/net/wimax/i2400m/i2400m.h | 7 +- drivers/net/wimax/i2400m/usb.c | 64 +++------------- include/linux/wimax/debug.h | 20 +---- net/wimax/debugfs.c | 42 ++--------- net/wimax/stack.c | 11 +-- net/wimax/wimax-internal.h | 7 +- 8 files changed, 51 insertions(+), 257 deletions(-) (limited to 'include/linux') diff --git a/drivers/net/wimax/i2400m/debugfs.c b/drivers/net/wimax/i2400m/debugfs.c index 6544ac9df047..73f5892ce6c1 100644 --- a/drivers/net/wimax/i2400m/debugfs.c +++ b/drivers/net/wimax/i2400m/debugfs.c @@ -30,15 +30,6 @@ DEFINE_SIMPLE_ATTRIBUTE(fops_netdev_queue_stopped, debugfs_netdev_queue_stopped_get, NULL, "%llu\n"); - -static -struct dentry *debugfs_create_netdev_queue_stopped( - const char *name, struct dentry *parent, struct i2400m *i2400m) -{ - return debugfs_create_file(name, 0400, parent, i2400m, - &fops_netdev_queue_stopped); -} - /* * We don't allow partial reads of this file, as then the reader would * get weirdly confused data as it is updated. @@ -167,15 +158,6 @@ DEFINE_SIMPLE_ATTRIBUTE(fops_i2400m_suspend, NULL, debugfs_i2400m_suspend_set, "%llu\n"); -static -struct dentry *debugfs_create_i2400m_suspend( - const char *name, struct dentry *parent, struct i2400m *i2400m) -{ - return debugfs_create_file(name, 0200, parent, i2400m, - &fops_i2400m_suspend); -} - - /* * Reset the device * @@ -205,73 +187,25 @@ DEFINE_SIMPLE_ATTRIBUTE(fops_i2400m_reset, NULL, debugfs_i2400m_reset_set, "%llu\n"); -static -struct dentry *debugfs_create_i2400m_reset( - const char *name, struct dentry *parent, struct i2400m *i2400m) +void i2400m_debugfs_add(struct i2400m *i2400m) { - return debugfs_create_file(name, 0200, parent, i2400m, - &fops_i2400m_reset); -} - - -#define __debugfs_register(prefix, name, parent) \ -do { \ - result = d_level_register_debugfs(prefix, name, parent); \ - if (result < 0) \ - goto error; \ -} while (0) - - -int i2400m_debugfs_add(struct i2400m *i2400m) -{ - int result; - struct device *dev = i2400m_dev(i2400m); struct dentry *dentry = i2400m->wimax_dev.debugfs_dentry; - struct dentry *fd; dentry = debugfs_create_dir("i2400m", dentry); - result = PTR_ERR(dentry); - if (IS_ERR(dentry)) { - if (result == -ENODEV) - result = 0; /* No debugfs support */ - goto error; - } i2400m->debugfs_dentry = dentry; - __debugfs_register("dl_", control, dentry); - __debugfs_register("dl_", driver, dentry); - __debugfs_register("dl_", debugfs, dentry); - __debugfs_register("dl_", fw, dentry); - __debugfs_register("dl_", netdev, dentry); - __debugfs_register("dl_", rfkill, dentry); - __debugfs_register("dl_", rx, dentry); - __debugfs_register("dl_", tx, dentry); - - fd = debugfs_create_size_t("tx_in", 0400, dentry, - &i2400m->tx_in); - result = PTR_ERR(fd); - if (IS_ERR(fd) && result != -ENODEV) { - dev_err(dev, "Can't create debugfs entry " - "tx_in: %d\n", result); - goto error; - } - fd = debugfs_create_size_t("tx_out", 0400, dentry, - &i2400m->tx_out); - result = PTR_ERR(fd); - if (IS_ERR(fd) && result != -ENODEV) { - dev_err(dev, "Can't create debugfs entry " - "tx_out: %d\n", result); - goto error; - } + d_level_register_debugfs("dl_", control, dentry); + d_level_register_debugfs("dl_", driver, dentry); + d_level_register_debugfs("dl_", debugfs, dentry); + d_level_register_debugfs("dl_", fw, dentry); + d_level_register_debugfs("dl_", netdev, dentry); + d_level_register_debugfs("dl_", rfkill, dentry); + d_level_register_debugfs("dl_", rx, dentry); + d_level_register_debugfs("dl_", tx, dentry); - fd = debugfs_create_u32("state", 0600, dentry, - &i2400m->state); - result = PTR_ERR(fd); - if (IS_ERR(fd) && result != -ENODEV) { - dev_err(dev, "Can't create debugfs entry " - "state: %d\n", result); - goto error; - } + debugfs_create_size_t("tx_in", 0400, dentry, &i2400m->tx_in); + debugfs_create_size_t("tx_out", 0400, dentry, &i2400m->tx_out); + debugfs_create_u32("state", 0600, dentry, &i2400m->state); /* * Trace received messages from user space @@ -295,60 +229,22 @@ int i2400m_debugfs_add(struct i2400m *i2400m) * It is not really very atomic, but it is also not too * critical. */ - fd = debugfs_create_u8("trace_msg_from_user", 0600, dentry, - &i2400m->trace_msg_from_user); - result = PTR_ERR(fd); - if (IS_ERR(fd) && result != -ENODEV) { - dev_err(dev, "Can't create debugfs entry " - "trace_msg_from_user: %d\n", result); - goto error; - } + debugfs_create_u8("trace_msg_from_user", 0600, dentry, + &i2400m->trace_msg_from_user); - fd = debugfs_create_netdev_queue_stopped("netdev_queue_stopped", - dentry, i2400m); - result = PTR_ERR(fd); - if (IS_ERR(fd) && result != -ENODEV) { - dev_err(dev, "Can't create debugfs entry " - "netdev_queue_stopped: %d\n", result); - goto error; - } + debugfs_create_file("netdev_queue_stopped", 0400, dentry, i2400m, + &fops_netdev_queue_stopped); - fd = debugfs_create_file("rx_stats", 0600, dentry, i2400m, - &i2400m_rx_stats_fops); - result = PTR_ERR(fd); - if (IS_ERR(fd) && result != -ENODEV) { - dev_err(dev, "Can't create debugfs entry " - "rx_stats: %d\n", result); - goto error; - } + debugfs_create_file("rx_stats", 0600, dentry, i2400m, + &i2400m_rx_stats_fops); - fd = debugfs_create_file("tx_stats", 0600, dentry, i2400m, - &i2400m_tx_stats_fops); - result = PTR_ERR(fd); - if (IS_ERR(fd) && result != -ENODEV) { - dev_err(dev, "Can't create debugfs entry " - "tx_stats: %d\n", result); - goto error; - } + debugfs_create_file("tx_stats", 0600, dentry, i2400m, + &i2400m_tx_stats_fops); - fd = debugfs_create_i2400m_suspend("suspend", dentry, i2400m); - result = PTR_ERR(fd); - if (IS_ERR(fd) && result != -ENODEV) { - dev_err(dev, "Can't create debugfs entry suspend: %d\n", - result); - goto error; - } + debugfs_create_file("suspend", 0200, dentry, i2400m, + &fops_i2400m_suspend); - fd = debugfs_create_i2400m_reset("reset", dentry, i2400m); - result = PTR_ERR(fd); - if (IS_ERR(fd) && result != -ENODEV) { - dev_err(dev, "Can't create debugfs entry reset: %d\n", result); - goto error; - } - - result = 0; -error: - return result; + debugfs_create_file("reset", 0200, dentry, i2400m, &fops_i2400m_reset); } void i2400m_debugfs_rm(struct i2400m *i2400m) diff --git a/drivers/net/wimax/i2400m/driver.c b/drivers/net/wimax/i2400m/driver.c index 0a29222a1bf9..f66c0f8f6f4a 100644 --- a/drivers/net/wimax/i2400m/driver.c +++ b/drivers/net/wimax/i2400m/driver.c @@ -905,11 +905,7 @@ int i2400m_setup(struct i2400m *i2400m, enum i2400m_bri bm_flags) goto error_sysfs_setup; } - result = i2400m_debugfs_add(i2400m); - if (result < 0) { - dev_err(dev, "cannot setup i2400m's debugfs: %d\n", result); - goto error_debugfs_setup; - } + i2400m_debugfs_add(i2400m); result = i2400m_dev_start(i2400m, bm_flags); if (result < 0) @@ -919,7 +915,6 @@ int i2400m_setup(struct i2400m *i2400m, enum i2400m_bri bm_flags) error_dev_start: i2400m_debugfs_rm(i2400m); -error_debugfs_setup: sysfs_remove_group(&i2400m->wimax_dev.net_dev->dev.kobj, &i2400m_dev_attr_group); error_sysfs_setup: diff --git a/drivers/net/wimax/i2400m/i2400m.h b/drivers/net/wimax/i2400m/i2400m.h index 5a34e72bab9a..a3733a6d14f5 100644 --- a/drivers/net/wimax/i2400m/i2400m.h +++ b/drivers/net/wimax/i2400m/i2400m.h @@ -812,13 +812,10 @@ enum i2400m_pt; int i2400m_tx(struct i2400m *, const void *, size_t, enum i2400m_pt); #ifdef CONFIG_DEBUG_FS -int i2400m_debugfs_add(struct i2400m *); +void i2400m_debugfs_add(struct i2400m *); void i2400m_debugfs_rm(struct i2400m *); #else -static inline int i2400m_debugfs_add(struct i2400m *i2400m) -{ - return 0; -} +static inline void i2400m_debugfs_add(struct i2400m *i2400m) {} static inline void i2400m_debugfs_rm(struct i2400m *i2400m) {} #endif diff --git a/drivers/net/wimax/i2400m/usb.c b/drivers/net/wimax/i2400m/usb.c index 2075e7b1fff6..6953f904232f 100644 --- a/drivers/net/wimax/i2400m/usb.c +++ b/drivers/net/wimax/i2400m/usb.c @@ -366,61 +366,25 @@ struct d_level D_LEVEL[] = { }; size_t D_LEVEL_SIZE = ARRAY_SIZE(D_LEVEL); - -#define __debugfs_register(prefix, name, parent) \ -do { \ - result = d_level_register_debugfs(prefix, name, parent); \ - if (result < 0) \ - goto error; \ -} while (0) - - static -int i2400mu_debugfs_add(struct i2400mu *i2400mu) +void i2400mu_debugfs_add(struct i2400mu *i2400mu) { - int result; - struct device *dev = &i2400mu->usb_iface->dev; struct dentry *dentry = i2400mu->i2400m.wimax_dev.debugfs_dentry; - struct dentry *fd; dentry = debugfs_create_dir("i2400m-usb", dentry); - result = PTR_ERR(dentry); - if (IS_ERR(dentry)) { - if (result == -ENODEV) - result = 0; /* No debugfs support */ - goto error; - } i2400mu->debugfs_dentry = dentry; - __debugfs_register("dl_", usb, dentry); - __debugfs_register("dl_", fw, dentry); - __debugfs_register("dl_", notif, dentry); - __debugfs_register("dl_", rx, dentry); - __debugfs_register("dl_", tx, dentry); - /* Don't touch these if you don't know what you are doing */ - fd = debugfs_create_u8("rx_size_auto_shrink", 0600, dentry, - &i2400mu->rx_size_auto_shrink); - result = PTR_ERR(fd); - if (IS_ERR(fd) && result != -ENODEV) { - dev_err(dev, "Can't create debugfs entry " - "rx_size_auto_shrink: %d\n", result); - goto error; - } + d_level_register_debugfs("dl_", usb, dentry); + d_level_register_debugfs("dl_", fw, dentry); + d_level_register_debugfs("dl_", notif, dentry); + d_level_register_debugfs("dl_", rx, dentry); + d_level_register_debugfs("dl_", tx, dentry); - fd = debugfs_create_size_t("rx_size", 0600, dentry, - &i2400mu->rx_size); - result = PTR_ERR(fd); - if (IS_ERR(fd) && result != -ENODEV) { - dev_err(dev, "Can't create debugfs entry " - "rx_size: %d\n", result); - goto error; - } - - return 0; + /* Don't touch these if you don't know what you are doing */ + debugfs_create_u8("rx_size_auto_shrink", 0600, dentry, + &i2400mu->rx_size_auto_shrink); -error: - debugfs_remove_recursive(i2400mu->debugfs_dentry); - return result; + debugfs_create_size_t("rx_size", 0600, dentry, &i2400mu->rx_size); } @@ -534,15 +498,9 @@ int i2400mu_probe(struct usb_interface *iface, dev_err(dev, "cannot setup device: %d\n", result); goto error_setup; } - result = i2400mu_debugfs_add(i2400mu); - if (result < 0) { - dev_err(dev, "Can't register i2400mu's debugfs: %d\n", result); - goto error_debugfs_add; - } + i2400mu_debugfs_add(i2400mu); return 0; -error_debugfs_add: - i2400m_release(i2400m); error_setup: usb_set_intfdata(iface, NULL); usb_put_dev(i2400mu->usb_dev); diff --git a/include/linux/wimax/debug.h b/include/linux/wimax/debug.h index 7cb63e4ec0ae..4dd2c1cea6a9 100644 --- a/include/linux/wimax/debug.h +++ b/include/linux/wimax/debug.h @@ -98,9 +98,7 @@ * To manipulate from user space the levels, create a debugfs dentry * and then register each submodule with: * - * result = d_level_register_debugfs("PREFIX_", submodule_X, parent); - * if (result < 0) - * goto error; + * d_level_register_debugfs("PREFIX_", submodule_X, parent); * * Where PREFIX_ is a name of your chosing. This will create debugfs * file with a single numeric value that can be use to tweak it. To @@ -408,25 +406,13 @@ do { \ * @submodule: name of submodule (not a string, just the name) * @dentry: debugfs parent dentry * - * Returns: 0 if ok, < 0 errno on error. - * * For removing, just use debugfs_remove_recursive() on the parent. */ #define d_level_register_debugfs(prefix, name, parent) \ ({ \ - int rc; \ - struct dentry *fd; \ - struct dentry *verify_parent_type = parent; \ - fd = debugfs_create_u8( \ - prefix #name, 0600, verify_parent_type, \ + debugfs_create_u8( \ + prefix #name, 0600, parent, \ &(D_LEVEL[__D_SUBMODULE_ ## name].level)); \ - rc = PTR_ERR(fd); \ - if (IS_ERR(fd) && rc != -ENODEV) \ - printk(KERN_ERR "%s: Can't create debugfs entry %s: " \ - "%d\n", __func__, prefix #name, rc); \ - else \ - rc = 0; \ - rc; \ }) diff --git a/net/wimax/debugfs.c b/net/wimax/debugfs.c index 1af56df30276..3c54bb6b925a 100644 --- a/net/wimax/debugfs.c +++ b/net/wimax/debugfs.c @@ -13,49 +13,23 @@ #define D_SUBMODULE debugfs #include "debug-levels.h" - -#define __debugfs_register(prefix, name, parent) \ -do { \ - result = d_level_register_debugfs(prefix, name, parent); \ - if (result < 0) \ - goto error; \ -} while (0) - - -int wimax_debugfs_add(struct wimax_dev *wimax_dev) +void wimax_debugfs_add(struct wimax_dev *wimax_dev) { - int result; struct net_device *net_dev = wimax_dev->net_dev; - struct device *dev = net_dev->dev.parent; struct dentry *dentry; char buf[128]; snprintf(buf, sizeof(buf), "wimax:%s", net_dev->name); dentry = debugfs_create_dir(buf, NULL); - result = PTR_ERR(dentry); - if (IS_ERR(dentry)) { - if (result == -ENODEV) - result = 0; /* No debugfs support */ - else - dev_err(dev, "Can't create debugfs dentry: %d\n", - result); - goto out; - } wimax_dev->debugfs_dentry = dentry; - __debugfs_register("wimax_dl_", debugfs, dentry); - __debugfs_register("wimax_dl_", id_table, dentry); - __debugfs_register("wimax_dl_", op_msg, dentry); - __debugfs_register("wimax_dl_", op_reset, dentry); - __debugfs_register("wimax_dl_", op_rfkill, dentry); - __debugfs_register("wimax_dl_", op_state_get, dentry); - __debugfs_register("wimax_dl_", stack, dentry); - result = 0; -out: - return result; -error: - debugfs_remove_recursive(wimax_dev->debugfs_dentry); - return result; + d_level_register_debugfs("wimax_dl_", debugfs, dentry); + d_level_register_debugfs("wimax_dl_", id_table, dentry); + d_level_register_debugfs("wimax_dl_", op_msg, dentry); + d_level_register_debugfs("wimax_dl_", op_reset, dentry); + d_level_register_debugfs("wimax_dl_", op_rfkill, dentry); + d_level_register_debugfs("wimax_dl_", op_state_get, dentry); + d_level_register_debugfs("wimax_dl_", stack, dentry); } void wimax_debugfs_rm(struct wimax_dev *wimax_dev) diff --git a/net/wimax/stack.c b/net/wimax/stack.c index 1ba99d65feca..4b9b1c5e8f3a 100644 --- a/net/wimax/stack.c +++ b/net/wimax/stack.c @@ -481,12 +481,7 @@ int wimax_dev_add(struct wimax_dev *wimax_dev, struct net_device *net_dev) /* Set up user-space interaction */ mutex_lock(&wimax_dev->mutex); wimax_id_table_add(wimax_dev); - result = wimax_debugfs_add(wimax_dev); - if (result < 0) { - dev_err(dev, "cannot initialize debugfs: %d\n", - result); - goto error_debugfs_add; - } + wimax_debugfs_add(wimax_dev); __wimax_state_set(wimax_dev, WIMAX_ST_DOWN); mutex_unlock(&wimax_dev->mutex); @@ -498,10 +493,6 @@ int wimax_dev_add(struct wimax_dev *wimax_dev, struct net_device *net_dev) d_fnend(3, dev, "(wimax_dev %p net_dev %p) = 0\n", wimax_dev, net_dev); return 0; -error_debugfs_add: - wimax_id_table_rm(wimax_dev); - mutex_unlock(&wimax_dev->mutex); - wimax_rfkill_rm(wimax_dev); error_rfkill_add: d_fnend(3, dev, "(wimax_dev %p net_dev %p) = %d\n", wimax_dev, net_dev, result); diff --git a/net/wimax/wimax-internal.h b/net/wimax/wimax-internal.h index e819a09337ee..40751207296c 100644 --- a/net/wimax/wimax-internal.h +++ b/net/wimax/wimax-internal.h @@ -57,13 +57,10 @@ void __wimax_state_set(struct wimax_dev *wimax_dev, enum wimax_st state) void __wimax_state_change(struct wimax_dev *, enum wimax_st); #ifdef CONFIG_DEBUG_FS -int wimax_debugfs_add(struct wimax_dev *); +void wimax_debugfs_add(struct wimax_dev *); void wimax_debugfs_rm(struct wimax_dev *); #else -static inline int wimax_debugfs_add(struct wimax_dev *wimax_dev) -{ - return 0; -} +static inline void wimax_debugfs_add(struct wimax_dev *wimax_dev) {} static inline void wimax_debugfs_rm(struct wimax_dev *wimax_dev) {} #endif -- cgit v1.2.3 From 9f818c8a7388ad1a5c60ace50be6f658c058a5f2 Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Sat, 10 Aug 2019 12:17:18 +0200 Subject: mlx5: no need to check return value of debugfs_create functions When calling debugfs functions, there is no need to ever check the return value. The function can work or not, but the code logic should never do something different based on this. This cleans up a lot of unneeded code and logic around the debugfs files, making all of this much simpler and easier to understand as we don't need to keep the dentries saved anymore. Cc: Saeed Mahameed Cc: Leon Romanovsky Cc: netdev@vger.kernel.org Signed-off-by: Greg Kroah-Hartman Signed-off-by: David S. Miller --- drivers/net/ethernet/mellanox/mlx5/core/cmd.c | 51 ++--------- drivers/net/ethernet/mellanox/mlx5/core/debugfs.c | 102 ++------------------- drivers/net/ethernet/mellanox/mlx5/core/eq.c | 11 +-- drivers/net/ethernet/mellanox/mlx5/core/lib/eq.h | 2 +- drivers/net/ethernet/mellanox/mlx5/core/main.c | 7 +- .../net/ethernet/mellanox/mlx5/core/mlx5_core.h | 2 +- include/linux/mlx5/driver.h | 12 +-- 7 files changed, 24 insertions(+), 163 deletions(-) (limited to 'include/linux') diff --git a/drivers/net/ethernet/mellanox/mlx5/core/cmd.c b/drivers/net/ethernet/mellanox/mlx5/core/cmd.c index 8cdd7e66f8df..973f90888b1f 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/cmd.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/cmd.c @@ -1368,49 +1368,19 @@ static void clean_debug_files(struct mlx5_core_dev *dev) debugfs_remove_recursive(dbg->dbg_root); } -static int create_debugfs_files(struct mlx5_core_dev *dev) +static void create_debugfs_files(struct mlx5_core_dev *dev) { struct mlx5_cmd_debug *dbg = &dev->cmd.dbg; - int err = -ENOMEM; - - if (!mlx5_debugfs_root) - return 0; dbg->dbg_root = debugfs_create_dir("cmd", dev->priv.dbg_root); - if (!dbg->dbg_root) - return err; - - dbg->dbg_in = debugfs_create_file("in", 0400, dbg->dbg_root, - dev, &dfops); - if (!dbg->dbg_in) - goto err_dbg; - dbg->dbg_out = debugfs_create_file("out", 0200, dbg->dbg_root, - dev, &dfops); - if (!dbg->dbg_out) - goto err_dbg; - - dbg->dbg_outlen = debugfs_create_file("out_len", 0600, dbg->dbg_root, - dev, &olfops); - if (!dbg->dbg_outlen) - goto err_dbg; - - dbg->dbg_status = debugfs_create_u8("status", 0600, dbg->dbg_root, - &dbg->status); - if (!dbg->dbg_status) - goto err_dbg; - - dbg->dbg_run = debugfs_create_file("run", 0200, dbg->dbg_root, dev, &fops); - if (!dbg->dbg_run) - goto err_dbg; + debugfs_create_file("in", 0400, dbg->dbg_root, dev, &dfops); + debugfs_create_file("out", 0200, dbg->dbg_root, dev, &dfops); + debugfs_create_file("out_len", 0600, dbg->dbg_root, dev, &olfops); + debugfs_create_u8("status", 0600, dbg->dbg_root, &dbg->status); + debugfs_create_file("run", 0200, dbg->dbg_root, dev, &fops); mlx5_cmdif_debugfs_init(dev); - - return 0; - -err_dbg: - clean_debug_files(dev); - return err; } static void mlx5_cmd_change_mod(struct mlx5_core_dev *dev, int mode) @@ -2007,17 +1977,10 @@ int mlx5_cmd_init(struct mlx5_core_dev *dev) goto err_cache; } - err = create_debugfs_files(dev); - if (err) { - err = -ENOMEM; - goto err_wq; - } + create_debugfs_files(dev); return 0; -err_wq: - destroy_workqueue(cmd->wq); - err_cache: destroy_msg_cache(dev); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/debugfs.c b/drivers/net/ethernet/mellanox/mlx5/core/debugfs.c index a11e22d0b0cc..04854e5fbcd7 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/debugfs.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/debugfs.c @@ -92,8 +92,6 @@ EXPORT_SYMBOL(mlx5_debugfs_root); void mlx5_register_debugfs(void) { mlx5_debugfs_root = debugfs_create_dir("mlx5", NULL); - if (IS_ERR_OR_NULL(mlx5_debugfs_root)) - mlx5_debugfs_root = NULL; } void mlx5_unregister_debugfs(void) @@ -101,45 +99,25 @@ void mlx5_unregister_debugfs(void) debugfs_remove(mlx5_debugfs_root); } -int mlx5_qp_debugfs_init(struct mlx5_core_dev *dev) +void mlx5_qp_debugfs_init(struct mlx5_core_dev *dev) { - if (!mlx5_debugfs_root) - return 0; - atomic_set(&dev->num_qps, 0); dev->priv.qp_debugfs = debugfs_create_dir("QPs", dev->priv.dbg_root); - if (!dev->priv.qp_debugfs) - return -ENOMEM; - - return 0; } void mlx5_qp_debugfs_cleanup(struct mlx5_core_dev *dev) { - if (!mlx5_debugfs_root) - return; - debugfs_remove_recursive(dev->priv.qp_debugfs); } -int mlx5_eq_debugfs_init(struct mlx5_core_dev *dev) +void mlx5_eq_debugfs_init(struct mlx5_core_dev *dev) { - if (!mlx5_debugfs_root) - return 0; - dev->priv.eq_debugfs = debugfs_create_dir("EQs", dev->priv.dbg_root); - if (!dev->priv.eq_debugfs) - return -ENOMEM; - - return 0; } void mlx5_eq_debugfs_cleanup(struct mlx5_core_dev *dev) { - if (!mlx5_debugfs_root) - return; - debugfs_remove_recursive(dev->priv.eq_debugfs); } @@ -183,85 +161,41 @@ static const struct file_operations stats_fops = { .write = average_write, }; -int mlx5_cmdif_debugfs_init(struct mlx5_core_dev *dev) +void mlx5_cmdif_debugfs_init(struct mlx5_core_dev *dev) { struct mlx5_cmd_stats *stats; struct dentry **cmd; const char *namep; - int err; int i; - if (!mlx5_debugfs_root) - return 0; - cmd = &dev->priv.cmdif_debugfs; *cmd = debugfs_create_dir("commands", dev->priv.dbg_root); - if (!*cmd) - return -ENOMEM; for (i = 0; i < ARRAY_SIZE(dev->cmd.stats); i++) { stats = &dev->cmd.stats[i]; namep = mlx5_command_str(i); if (strcmp(namep, "unknown command opcode")) { stats->root = debugfs_create_dir(namep, *cmd); - if (!stats->root) { - mlx5_core_warn(dev, "failed adding command %d\n", - i); - err = -ENOMEM; - goto out; - } - - stats->avg = debugfs_create_file("average", 0400, - stats->root, stats, - &stats_fops); - if (!stats->avg) { - mlx5_core_warn(dev, "failed creating debugfs file\n"); - err = -ENOMEM; - goto out; - } - - stats->count = debugfs_create_u64("n", 0400, - stats->root, - &stats->n); - if (!stats->count) { - mlx5_core_warn(dev, "failed creating debugfs file\n"); - err = -ENOMEM; - goto out; - } + + debugfs_create_file("average", 0400, stats->root, stats, + &stats_fops); + debugfs_create_u64("n", 0400, stats->root, &stats->n); } } - - return 0; -out: - debugfs_remove_recursive(dev->priv.cmdif_debugfs); - return err; } void mlx5_cmdif_debugfs_cleanup(struct mlx5_core_dev *dev) { - if (!mlx5_debugfs_root) - return; - debugfs_remove_recursive(dev->priv.cmdif_debugfs); } -int mlx5_cq_debugfs_init(struct mlx5_core_dev *dev) +void mlx5_cq_debugfs_init(struct mlx5_core_dev *dev) { - if (!mlx5_debugfs_root) - return 0; - dev->priv.cq_debugfs = debugfs_create_dir("CQs", dev->priv.dbg_root); - if (!dev->priv.cq_debugfs) - return -ENOMEM; - - return 0; } void mlx5_cq_debugfs_cleanup(struct mlx5_core_dev *dev) { - if (!mlx5_debugfs_root) - return; - debugfs_remove_recursive(dev->priv.cq_debugfs); } @@ -484,7 +418,6 @@ static int add_res_tree(struct mlx5_core_dev *dev, enum dbg_rsc_type type, { struct mlx5_rsc_debug *d; char resn[32]; - int err; int i; d = kzalloc(struct_size(d, fields, nfile), GFP_KERNEL); @@ -496,30 +429,15 @@ static int add_res_tree(struct mlx5_core_dev *dev, enum dbg_rsc_type type, d->type = type; sprintf(resn, "0x%x", rsn); d->root = debugfs_create_dir(resn, root); - if (!d->root) { - err = -ENOMEM; - goto out_free; - } for (i = 0; i < nfile; i++) { d->fields[i].i = i; - d->fields[i].dent = debugfs_create_file(field[i], 0400, - d->root, &d->fields[i], - &fops); - if (!d->fields[i].dent) { - err = -ENOMEM; - goto out_rem; - } + debugfs_create_file(field[i], 0400, d->root, &d->fields[i], + &fops); } *dbg = d; return 0; -out_rem: - debugfs_remove_recursive(d->root); - -out_free: - kfree(d); - return err; } static void rem_res_tree(struct mlx5_rsc_debug *d) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eq.c b/drivers/net/ethernet/mellanox/mlx5/core/eq.c index 2df9aaa421c6..09d4c64b6e73 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/eq.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/eq.c @@ -411,7 +411,7 @@ void mlx5_eq_del_cq(struct mlx5_eq *eq, struct mlx5_core_cq *cq) int mlx5_eq_table_init(struct mlx5_core_dev *dev) { struct mlx5_eq_table *eq_table; - int i, err; + int i; eq_table = kvzalloc(sizeof(*eq_table), GFP_KERNEL); if (!eq_table) @@ -419,9 +419,7 @@ int mlx5_eq_table_init(struct mlx5_core_dev *dev) dev->priv.eq_table = eq_table; - err = mlx5_eq_debugfs_init(dev); - if (err) - goto kvfree_eq_table; + mlx5_eq_debugfs_init(dev); mutex_init(&eq_table->lock); for (i = 0; i < MLX5_EVENT_TYPE_MAX; i++) @@ -429,11 +427,6 @@ int mlx5_eq_table_init(struct mlx5_core_dev *dev) eq_table->irq_table = dev->priv.irq_table; return 0; - -kvfree_eq_table: - kvfree(eq_table); - dev->priv.eq_table = NULL; - return err; } void mlx5_eq_table_cleanup(struct mlx5_core_dev *dev) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lib/eq.h b/drivers/net/ethernet/mellanox/mlx5/core/lib/eq.h index 3dfab91ae5f2..4be4d2d36218 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/lib/eq.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/lib/eq.h @@ -87,7 +87,7 @@ void mlx5_eq_synchronize_cmd_irq(struct mlx5_core_dev *dev); int mlx5_debug_eq_add(struct mlx5_core_dev *dev, struct mlx5_eq *eq); void mlx5_debug_eq_remove(struct mlx5_core_dev *dev, struct mlx5_eq *eq); -int mlx5_eq_debugfs_init(struct mlx5_core_dev *dev); +void mlx5_eq_debugfs_init(struct mlx5_core_dev *dev); void mlx5_eq_debugfs_cleanup(struct mlx5_core_dev *dev); /* This function should only be called after mlx5_cmd_force_teardown_hca */ diff --git a/drivers/net/ethernet/mellanox/mlx5/core/main.c b/drivers/net/ethernet/mellanox/mlx5/core/main.c index fa0e991f1983..0b70b1d6338d 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/main.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/main.c @@ -826,11 +826,7 @@ static int mlx5_init_once(struct mlx5_core_dev *dev) goto err_eq_cleanup; } - err = mlx5_cq_debugfs_init(dev); - if (err) { - mlx5_core_err(dev, "failed to initialize cq debugfs\n"); - goto err_events_cleanup; - } + mlx5_cq_debugfs_init(dev); mlx5_init_qp_table(dev); @@ -891,7 +887,6 @@ err_tables_cleanup: mlx5_cleanup_mkey_table(dev); mlx5_cleanup_qp_table(dev); mlx5_cq_debugfs_cleanup(dev); -err_events_cleanup: mlx5_events_cleanup(dev); err_eq_cleanup: mlx5_eq_table_cleanup(dev); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h b/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h index 471bbc48bc1f..87b75b2207c4 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h @@ -146,7 +146,7 @@ u64 mlx5_read_internal_timer(struct mlx5_core_dev *dev, void mlx5_cmd_trigger_completions(struct mlx5_core_dev *dev); void mlx5_cmd_flush(struct mlx5_core_dev *dev); -int mlx5_cq_debugfs_init(struct mlx5_core_dev *dev); +void mlx5_cq_debugfs_init(struct mlx5_core_dev *dev); void mlx5_cq_debugfs_cleanup(struct mlx5_core_dev *dev); int mlx5_query_pcam_reg(struct mlx5_core_dev *dev, u32 *pcam, u8 feature_group, diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h index d8f348ef9c33..df23f17eed64 100644 --- a/include/linux/mlx5/driver.h +++ b/include/linux/mlx5/driver.h @@ -189,7 +189,6 @@ enum mlx5_coredev_type { }; struct mlx5_field_desc { - struct dentry *dent; int i; }; @@ -242,11 +241,6 @@ struct mlx5_cmd_msg { struct mlx5_cmd_debug { struct dentry *dbg_root; - struct dentry *dbg_in; - struct dentry *dbg_out; - struct dentry *dbg_outlen; - struct dentry *dbg_status; - struct dentry *dbg_run; void *in_msg; void *out_msg; u8 status; @@ -271,8 +265,6 @@ struct mlx5_cmd_stats { u64 sum; u64 n; struct dentry *root; - struct dentry *avg; - struct dentry *count; /* protect command average calculations */ spinlock_t lock; }; @@ -972,7 +964,7 @@ int mlx5_vector2eqn(struct mlx5_core_dev *dev, int vector, int *eqn, int mlx5_core_attach_mcg(struct mlx5_core_dev *dev, union ib_gid *mgid, u32 qpn); int mlx5_core_detach_mcg(struct mlx5_core_dev *dev, union ib_gid *mgid, u32 qpn); -int mlx5_qp_debugfs_init(struct mlx5_core_dev *dev); +void mlx5_qp_debugfs_init(struct mlx5_core_dev *dev); void mlx5_qp_debugfs_cleanup(struct mlx5_core_dev *dev); int mlx5_core_access_reg(struct mlx5_core_dev *dev, void *data_in, int size_in, void *data_out, int size_out, @@ -984,7 +976,7 @@ int mlx5_db_alloc_node(struct mlx5_core_dev *dev, struct mlx5_db *db, void mlx5_db_free(struct mlx5_core_dev *dev, struct mlx5_db *db); const char *mlx5_command_str(int command); -int mlx5_cmdif_debugfs_init(struct mlx5_core_dev *dev); +void mlx5_cmdif_debugfs_init(struct mlx5_core_dev *dev); void mlx5_cmdif_debugfs_cleanup(struct mlx5_core_dev *dev); int mlx5_core_create_psv(struct mlx5_core_dev *dev, u32 pdn, int npsvs, u32 *sig_index); -- cgit v1.2.3 From f4069cd7fa6583e7094001c6fce6f426d17a4c76 Mon Sep 17 00:00:00 2001 From: Heiner Kallweit Date: Fri, 9 Aug 2019 20:43:50 +0200 Subject: net: phy: prepare phylib to deal with PHY's extending Clause 22 The integrated PHY in 2.5Gbps chip RTL8125 is the first (known to me) PHY that uses standard Clause 22 for all modes up to 1Gbps and adds 2.5Gbps control using vendor-specific registers. To use phylib for the standard part little extensions are needed: - Move most of genphy_config_aneg to a new function __genphy_config_aneg that takes a parameter whether restarting auto-negotiation is needed (depending on whether content of vendor-specific advertisement register changed). - Don't clear phydev->lp_advertising in genphy_read_status so that we can set non-C22 mode flags before. Basically both changes mimic the behavior of the equivalent Clause 45 functions. Signed-off-by: Heiner Kallweit Signed-off-by: David S. Miller --- drivers/net/phy/phy_device.c | 27 ++++++++++++--------------- include/linux/phy.h | 8 +++++++- 2 files changed, 19 insertions(+), 16 deletions(-) (limited to 'include/linux') diff --git a/drivers/net/phy/phy_device.c b/drivers/net/phy/phy_device.c index a70a98dc9879..b039632de73a 100644 --- a/drivers/net/phy/phy_device.c +++ b/drivers/net/phy/phy_device.c @@ -1671,18 +1671,20 @@ int genphy_restart_aneg(struct phy_device *phydev) EXPORT_SYMBOL(genphy_restart_aneg); /** - * genphy_config_aneg - restart auto-negotiation or write BMCR + * __genphy_config_aneg - restart auto-negotiation or write BMCR * @phydev: target phy_device struct + * @changed: whether autoneg is requested * * Description: If auto-negotiation is enabled, we configure the * advertising, and then restart auto-negotiation. If it is not * enabled, then we write the BMCR. */ -int genphy_config_aneg(struct phy_device *phydev) +int __genphy_config_aneg(struct phy_device *phydev, bool changed) { - int err, changed; + int err; - changed = genphy_config_eee_advert(phydev); + if (genphy_config_eee_advert(phydev)) + changed = true; if (AUTONEG_ENABLE != phydev->autoneg) return genphy_setup_forced(phydev); @@ -1690,10 +1692,10 @@ int genphy_config_aneg(struct phy_device *phydev) err = genphy_config_advert(phydev); if (err < 0) /* error */ return err; + else if (err) + changed = true; - changed |= err; - - if (changed == 0) { + if (!changed) { /* Advertisement hasn't changed, but maybe aneg was never on to * begin with? Or maybe phy was isolated? */ @@ -1703,18 +1705,15 @@ int genphy_config_aneg(struct phy_device *phydev) return ctl; if (!(ctl & BMCR_ANENABLE) || (ctl & BMCR_ISOLATE)) - changed = 1; /* do restart aneg */ + changed = true; /* do restart aneg */ } /* Only restart aneg if we are advertising something different * than we were before. */ - if (changed > 0) - return genphy_restart_aneg(phydev); - - return 0; + return changed ? genphy_restart_aneg(phydev) : 0; } -EXPORT_SYMBOL(genphy_config_aneg); +EXPORT_SYMBOL(__genphy_config_aneg); /** * genphy_aneg_done - return auto-negotiation status @@ -1801,8 +1800,6 @@ int genphy_read_status(struct phy_device *phydev) phydev->pause = 0; phydev->asym_pause = 0; - linkmode_zero(phydev->lp_advertising); - if (phydev->autoneg == AUTONEG_ENABLE && phydev->autoneg_complete) { if (phydev->is_gigabit_capable) { lpagb = phy_read(phydev, MII_STAT1000); diff --git a/include/linux/phy.h b/include/linux/phy.h index 462b90b73f93..7117825ee57a 100644 --- a/include/linux/phy.h +++ b/include/linux/phy.h @@ -1069,7 +1069,7 @@ int genphy_read_abilities(struct phy_device *phydev); int genphy_setup_forced(struct phy_device *phydev); int genphy_restart_aneg(struct phy_device *phydev); int genphy_config_eee_advert(struct phy_device *phydev); -int genphy_config_aneg(struct phy_device *phydev); +int __genphy_config_aneg(struct phy_device *phydev, bool changed); int genphy_aneg_done(struct phy_device *phydev); int genphy_update_link(struct phy_device *phydev); int genphy_read_status(struct phy_device *phydev); @@ -1077,6 +1077,12 @@ int genphy_suspend(struct phy_device *phydev); int genphy_resume(struct phy_device *phydev); int genphy_loopback(struct phy_device *phydev, bool enable); int genphy_soft_reset(struct phy_device *phydev); + +static inline int genphy_config_aneg(struct phy_device *phydev) +{ + return __genphy_config_aneg(phydev, false); +} + static inline int genphy_no_soft_reset(struct phy_device *phydev) { return 0; -- cgit v1.2.3 From bf22b343ca800aac076ccf986e762b28545aa6bb Mon Sep 17 00:00:00 2001 From: Heiner Kallweit Date: Fri, 9 Aug 2019 20:44:22 +0200 Subject: net: phy: add phy_modify_paged_changed Add helper function phy_modify_paged_changed, behavios is the same as for phy_modify_changed. Signed-off-by: Heiner Kallweit Reviewed-by: Andrew Lunn Signed-off-by: David S. Miller --- drivers/net/phy/phy-core.c | 29 ++++++++++++++++++++++++----- include/linux/phy.h | 2 ++ 2 files changed, 26 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/drivers/net/phy/phy-core.c b/drivers/net/phy/phy-core.c index 16667fbac8bf..9ae3abb2daca 100644 --- a/drivers/net/phy/phy-core.c +++ b/drivers/net/phy/phy-core.c @@ -783,24 +783,43 @@ int phy_write_paged(struct phy_device *phydev, int page, u32 regnum, u16 val) EXPORT_SYMBOL(phy_write_paged); /** - * phy_modify_paged() - Convenience function for modifying a paged register + * phy_modify_paged_changed() - Function for modifying a paged register * @phydev: a pointer to a &struct phy_device * @page: the page for the phy * @regnum: register number * @mask: bit mask of bits to clear * @set: bit mask of bits to set * - * Same rules as for phy_read() and phy_write(). + * Returns negative errno, 0 if there was no change, and 1 in case of change */ -int phy_modify_paged(struct phy_device *phydev, int page, u32 regnum, - u16 mask, u16 set) +int phy_modify_paged_changed(struct phy_device *phydev, int page, u32 regnum, + u16 mask, u16 set) { int ret = 0, oldpage; oldpage = phy_select_page(phydev, page); if (oldpage >= 0) - ret = __phy_modify(phydev, regnum, mask, set); + ret = __phy_modify_changed(phydev, regnum, mask, set); return phy_restore_page(phydev, oldpage, ret); } +EXPORT_SYMBOL(phy_modify_paged_changed); + +/** + * phy_modify_paged() - Convenience function for modifying a paged register + * @phydev: a pointer to a &struct phy_device + * @page: the page for the phy + * @regnum: register number + * @mask: bit mask of bits to clear + * @set: bit mask of bits to set + * + * Same rules as for phy_read() and phy_write(). + */ +int phy_modify_paged(struct phy_device *phydev, int page, u32 regnum, + u16 mask, u16 set) +{ + int ret = phy_modify_paged_changed(phydev, page, regnum, mask, set); + + return ret < 0 ? ret : 0; +} EXPORT_SYMBOL(phy_modify_paged); diff --git a/include/linux/phy.h b/include/linux/phy.h index 7117825ee57a..781f4810ceba 100644 --- a/include/linux/phy.h +++ b/include/linux/phy.h @@ -984,6 +984,8 @@ int phy_select_page(struct phy_device *phydev, int page); int phy_restore_page(struct phy_device *phydev, int oldpage, int ret); int phy_read_paged(struct phy_device *phydev, int page, u32 regnum); int phy_write_paged(struct phy_device *phydev, int page, u32 regnum, u16 val); +int phy_modify_paged_changed(struct phy_device *phydev, int page, u32 regnum, + u16 mask, u16 set); int phy_modify_paged(struct phy_device *phydev, int page, u32 regnum, u16 mask, u16 set); -- cgit v1.2.3 From b1635ee6120cbeb3de6ab270432b2a2b839c9c56 Mon Sep 17 00:00:00 2001 From: Yishai Hadas Date: Thu, 8 Aug 2019 11:43:56 +0300 Subject: net/mlx5: Add XRQ legacy commands opcodes Add XRQ legacy commands opcodes, will be used via the DEVX interface. Signed-off-by: Yishai Hadas Reviewed-by: Saeed Mahameed Signed-off-by: Leon Romanovsky --- drivers/net/ethernet/mellanox/mlx5/core/cmd.c | 4 ++++ include/linux/mlx5/mlx5_ifc.h | 2 ++ 2 files changed, 6 insertions(+) (limited to 'include/linux') diff --git a/drivers/net/ethernet/mellanox/mlx5/core/cmd.c b/drivers/net/ethernet/mellanox/mlx5/core/cmd.c index 8cdd7e66f8df..53d09620e215 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/cmd.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/cmd.c @@ -446,6 +446,8 @@ static int mlx5_internal_err_ret_value(struct mlx5_core_dev *dev, u16 op, case MLX5_CMD_OP_CREATE_UMEM: case MLX5_CMD_OP_DESTROY_UMEM: case MLX5_CMD_OP_ALLOC_MEMIC: + case MLX5_CMD_OP_MODIFY_XRQ: + case MLX5_CMD_OP_RELEASE_XRQ_ERROR: *status = MLX5_DRIVER_STATUS_ABORTED; *synd = MLX5_DRIVER_SYND; return -EIO; @@ -637,6 +639,8 @@ const char *mlx5_command_str(int command) MLX5_COMMAND_STR_CASE(DESTROY_UCTX); MLX5_COMMAND_STR_CASE(CREATE_UMEM); MLX5_COMMAND_STR_CASE(DESTROY_UMEM); + MLX5_COMMAND_STR_CASE(RELEASE_XRQ_ERROR); + MLX5_COMMAND_STR_CASE(MODIFY_XRQ); default: return "unknown command opcode"; } } diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h index 1f9d4a8e6227..ab6ae723aae6 100644 --- a/include/linux/mlx5/mlx5_ifc.h +++ b/include/linux/mlx5/mlx5_ifc.h @@ -172,6 +172,8 @@ 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_RELEASE_XRQ_ERROR = 0x729, + MLX5_CMD_OP_MODIFY_XRQ = 0x72a, MLX5_CMD_OP_QUERY_ESW_FUNCTIONS = 0x740, MLX5_CMD_OP_QUERY_VPORT_STATE = 0x750, MLX5_CMD_OP_MODIFY_VPORT_STATE = 0x751, -- cgit v1.2.3 From bd96b4c75675e616eefef6d85d163530eef9c5e5 Mon Sep 17 00:00:00 2001 From: Jeremy Sowden Date: Wed, 7 Aug 2019 15:16:58 +0100 Subject: netfilter: inline four headers files into another one. linux/netfilter/ipset/ip_set.h included four other header files: include/linux/netfilter/ipset/ip_set_comment.h include/linux/netfilter/ipset/ip_set_counter.h include/linux/netfilter/ipset/ip_set_skbinfo.h include/linux/netfilter/ipset/ip_set_timeout.h Of these the first three were not included anywhere else. The last, ip_set_timeout.h, was included in a couple of other places, but defined inline functions which call other inline functions defined in ip_set.h, so ip_set.h had to be included before it. Inlined all four into ip_set.h, and updated the other files that included ip_set_timeout.h. Signed-off-by: Jeremy Sowden Acked-by: Jozsef Kadlecsik Signed-off-by: Pablo Neira Ayuso --- include/linux/netfilter/ipset/ip_set.h | 238 ++++++++++++++++++++++++- include/linux/netfilter/ipset/ip_set_comment.h | 73 -------- include/linux/netfilter/ipset/ip_set_counter.h | 84 --------- include/linux/netfilter/ipset/ip_set_skbinfo.h | 42 ----- include/linux/netfilter/ipset/ip_set_timeout.h | 77 -------- net/netfilter/ipset/ip_set_hash_gen.h | 2 +- net/netfilter/xt_set.c | 1 - 7 files changed, 235 insertions(+), 282 deletions(-) delete mode 100644 include/linux/netfilter/ipset/ip_set_comment.h delete mode 100644 include/linux/netfilter/ipset/ip_set_counter.h delete mode 100644 include/linux/netfilter/ipset/ip_set_skbinfo.h delete mode 100644 include/linux/netfilter/ipset/ip_set_timeout.h (limited to 'include/linux') diff --git a/include/linux/netfilter/ipset/ip_set.h b/include/linux/netfilter/ipset/ip_set.h index 12ad9b1853b4..9bc255a8461b 100644 --- a/include/linux/netfilter/ipset/ip_set.h +++ b/include/linux/netfilter/ipset/ip_set.h @@ -452,10 +452,240 @@ bitmap_bytes(u32 a, u32 b) return 4 * ((((b - a + 8) / 8) + 3) / 4); } -#include -#include -#include -#include +/* How often should the gc be run by default */ +#define IPSET_GC_TIME (3 * 60) + +/* Timeout period depending on the timeout value of the given set */ +#define IPSET_GC_PERIOD(timeout) \ + ((timeout/3) ? min_t(u32, (timeout)/3, IPSET_GC_TIME) : 1) + +/* Entry is set with no timeout value */ +#define IPSET_ELEM_PERMANENT 0 + +/* Set is defined with timeout support: timeout value may be 0 */ +#define IPSET_NO_TIMEOUT UINT_MAX + +/* Max timeout value, see msecs_to_jiffies() in jiffies.h */ +#define IPSET_MAX_TIMEOUT (UINT_MAX >> 1)/MSEC_PER_SEC + +#define ip_set_adt_opt_timeout(opt, set) \ +((opt)->ext.timeout != IPSET_NO_TIMEOUT ? (opt)->ext.timeout : (set)->timeout) + +static inline unsigned int +ip_set_timeout_uget(struct nlattr *tb) +{ + unsigned int timeout = ip_set_get_h32(tb); + + /* Normalize to fit into jiffies */ + if (timeout > IPSET_MAX_TIMEOUT) + timeout = IPSET_MAX_TIMEOUT; + + return timeout; +} + +static inline bool +ip_set_timeout_expired(const unsigned long *t) +{ + return *t != IPSET_ELEM_PERMANENT && time_is_before_jiffies(*t); +} + +static inline void +ip_set_timeout_set(unsigned long *timeout, u32 value) +{ + unsigned long t; + + if (!value) { + *timeout = IPSET_ELEM_PERMANENT; + return; + } + + t = msecs_to_jiffies(value * MSEC_PER_SEC) + jiffies; + if (t == IPSET_ELEM_PERMANENT) + /* Bingo! :-) */ + t--; + *timeout = t; +} + +static inline u32 +ip_set_timeout_get(const unsigned long *timeout) +{ + u32 t; + + if (*timeout == IPSET_ELEM_PERMANENT) + return 0; + + t = jiffies_to_msecs(*timeout - jiffies)/MSEC_PER_SEC; + /* Zero value in userspace means no timeout */ + return t == 0 ? 1 : t; +} + +static inline char* +ip_set_comment_uget(struct nlattr *tb) +{ + return nla_data(tb); +} + +/* Called from uadd only, protected by the set spinlock. + * The kadt functions don't use the comment extensions in any way. + */ +static inline void +ip_set_init_comment(struct ip_set *set, struct ip_set_comment *comment, + const struct ip_set_ext *ext) +{ + struct ip_set_comment_rcu *c = rcu_dereference_protected(comment->c, 1); + size_t len = ext->comment ? strlen(ext->comment) : 0; + + if (unlikely(c)) { + set->ext_size -= sizeof(*c) + strlen(c->str) + 1; + kfree_rcu(c, rcu); + rcu_assign_pointer(comment->c, NULL); + } + if (!len) + return; + if (unlikely(len > IPSET_MAX_COMMENT_SIZE)) + len = IPSET_MAX_COMMENT_SIZE; + c = kmalloc(sizeof(*c) + len + 1, GFP_ATOMIC); + if (unlikely(!c)) + return; + strlcpy(c->str, ext->comment, len + 1); + set->ext_size += sizeof(*c) + strlen(c->str) + 1; + rcu_assign_pointer(comment->c, c); +} + +/* Used only when dumping a set, protected by rcu_read_lock() */ +static inline int +ip_set_put_comment(struct sk_buff *skb, const struct ip_set_comment *comment) +{ + struct ip_set_comment_rcu *c = rcu_dereference(comment->c); + + if (!c) + return 0; + return nla_put_string(skb, IPSET_ATTR_COMMENT, c->str); +} + +/* Called from uadd/udel, flush or the garbage collectors protected + * by the set spinlock. + * Called when the set is destroyed and when there can't be any user + * of the set data anymore. + */ +static inline void +ip_set_comment_free(struct ip_set *set, struct ip_set_comment *comment) +{ + struct ip_set_comment_rcu *c; + + c = rcu_dereference_protected(comment->c, 1); + if (unlikely(!c)) + return; + set->ext_size -= sizeof(*c) + strlen(c->str) + 1; + kfree_rcu(c, rcu); + rcu_assign_pointer(comment->c, NULL); +} + +static inline void +ip_set_add_bytes(u64 bytes, struct ip_set_counter *counter) +{ + atomic64_add((long long)bytes, &(counter)->bytes); +} + +static inline void +ip_set_add_packets(u64 packets, struct ip_set_counter *counter) +{ + atomic64_add((long long)packets, &(counter)->packets); +} + +static inline u64 +ip_set_get_bytes(const struct ip_set_counter *counter) +{ + return (u64)atomic64_read(&(counter)->bytes); +} + +static inline u64 +ip_set_get_packets(const struct ip_set_counter *counter) +{ + return (u64)atomic64_read(&(counter)->packets); +} + +static inline bool +ip_set_match_counter(u64 counter, u64 match, u8 op) +{ + switch (op) { + case IPSET_COUNTER_NONE: + return true; + case IPSET_COUNTER_EQ: + return counter == match; + case IPSET_COUNTER_NE: + return counter != match; + case IPSET_COUNTER_LT: + return counter < match; + case IPSET_COUNTER_GT: + return counter > match; + } + return false; +} + +static inline void +ip_set_update_counter(struct ip_set_counter *counter, + const struct ip_set_ext *ext, u32 flags) +{ + if (ext->packets != ULLONG_MAX && + !(flags & IPSET_FLAG_SKIP_COUNTER_UPDATE)) { + ip_set_add_bytes(ext->bytes, counter); + ip_set_add_packets(ext->packets, counter); + } +} + +static inline bool +ip_set_put_counter(struct sk_buff *skb, const struct ip_set_counter *counter) +{ + return nla_put_net64(skb, IPSET_ATTR_BYTES, + cpu_to_be64(ip_set_get_bytes(counter)), + IPSET_ATTR_PAD) || + nla_put_net64(skb, IPSET_ATTR_PACKETS, + cpu_to_be64(ip_set_get_packets(counter)), + IPSET_ATTR_PAD); +} + +static inline void +ip_set_init_counter(struct ip_set_counter *counter, + const struct ip_set_ext *ext) +{ + if (ext->bytes != ULLONG_MAX) + atomic64_set(&(counter)->bytes, (long long)(ext->bytes)); + if (ext->packets != ULLONG_MAX) + atomic64_set(&(counter)->packets, (long long)(ext->packets)); +} + +static inline void +ip_set_get_skbinfo(struct ip_set_skbinfo *skbinfo, + const struct ip_set_ext *ext, + struct ip_set_ext *mext, u32 flags) +{ + mext->skbinfo = *skbinfo; +} + +static inline bool +ip_set_put_skbinfo(struct sk_buff *skb, const struct ip_set_skbinfo *skbinfo) +{ + /* Send nonzero parameters only */ + return ((skbinfo->skbmark || skbinfo->skbmarkmask) && + nla_put_net64(skb, IPSET_ATTR_SKBMARK, + cpu_to_be64((u64)skbinfo->skbmark << 32 | + skbinfo->skbmarkmask), + IPSET_ATTR_PAD)) || + (skbinfo->skbprio && + nla_put_net32(skb, IPSET_ATTR_SKBPRIO, + cpu_to_be32(skbinfo->skbprio))) || + (skbinfo->skbqueue && + nla_put_net16(skb, IPSET_ATTR_SKBQUEUE, + cpu_to_be16(skbinfo->skbqueue))); +} + +static inline void +ip_set_init_skbinfo(struct ip_set_skbinfo *skbinfo, + const struct ip_set_ext *ext) +{ + *skbinfo = ext->skbinfo; +} #define IP_SET_INIT_KEXT(skb, opt, set) \ { .bytes = (skb)->len, .packets = 1, \ diff --git a/include/linux/netfilter/ipset/ip_set_comment.h b/include/linux/netfilter/ipset/ip_set_comment.h deleted file mode 100644 index 0b894d81bbf2..000000000000 --- a/include/linux/netfilter/ipset/ip_set_comment.h +++ /dev/null @@ -1,73 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0-only */ -#ifndef _IP_SET_COMMENT_H -#define _IP_SET_COMMENT_H - -/* Copyright (C) 2013 Oliver Smith - */ - -#ifdef __KERNEL__ - -static inline char* -ip_set_comment_uget(struct nlattr *tb) -{ - return nla_data(tb); -} - -/* Called from uadd only, protected by the set spinlock. - * The kadt functions don't use the comment extensions in any way. - */ -static inline void -ip_set_init_comment(struct ip_set *set, struct ip_set_comment *comment, - const struct ip_set_ext *ext) -{ - struct ip_set_comment_rcu *c = rcu_dereference_protected(comment->c, 1); - size_t len = ext->comment ? strlen(ext->comment) : 0; - - if (unlikely(c)) { - set->ext_size -= sizeof(*c) + strlen(c->str) + 1; - kfree_rcu(c, rcu); - rcu_assign_pointer(comment->c, NULL); - } - if (!len) - return; - if (unlikely(len > IPSET_MAX_COMMENT_SIZE)) - len = IPSET_MAX_COMMENT_SIZE; - c = kmalloc(sizeof(*c) + len + 1, GFP_ATOMIC); - if (unlikely(!c)) - return; - strlcpy(c->str, ext->comment, len + 1); - set->ext_size += sizeof(*c) + strlen(c->str) + 1; - rcu_assign_pointer(comment->c, c); -} - -/* Used only when dumping a set, protected by rcu_read_lock() */ -static inline int -ip_set_put_comment(struct sk_buff *skb, const struct ip_set_comment *comment) -{ - struct ip_set_comment_rcu *c = rcu_dereference(comment->c); - - if (!c) - return 0; - return nla_put_string(skb, IPSET_ATTR_COMMENT, c->str); -} - -/* Called from uadd/udel, flush or the garbage collectors protected - * by the set spinlock. - * Called when the set is destroyed and when there can't be any user - * of the set data anymore. - */ -static inline void -ip_set_comment_free(struct ip_set *set, struct ip_set_comment *comment) -{ - struct ip_set_comment_rcu *c; - - c = rcu_dereference_protected(comment->c, 1); - if (unlikely(!c)) - return; - set->ext_size -= sizeof(*c) + strlen(c->str) + 1; - kfree_rcu(c, rcu); - rcu_assign_pointer(comment->c, NULL); -} - -#endif -#endif diff --git a/include/linux/netfilter/ipset/ip_set_counter.h b/include/linux/netfilter/ipset/ip_set_counter.h deleted file mode 100644 index 3400958c07be..000000000000 --- a/include/linux/netfilter/ipset/ip_set_counter.h +++ /dev/null @@ -1,84 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0-only */ -#ifndef _IP_SET_COUNTER_H -#define _IP_SET_COUNTER_H - -/* Copyright (C) 2015 Jozsef Kadlecsik */ - -#ifdef __KERNEL__ - -static inline void -ip_set_add_bytes(u64 bytes, struct ip_set_counter *counter) -{ - atomic64_add((long long)bytes, &(counter)->bytes); -} - -static inline void -ip_set_add_packets(u64 packets, struct ip_set_counter *counter) -{ - atomic64_add((long long)packets, &(counter)->packets); -} - -static inline u64 -ip_set_get_bytes(const struct ip_set_counter *counter) -{ - return (u64)atomic64_read(&(counter)->bytes); -} - -static inline u64 -ip_set_get_packets(const struct ip_set_counter *counter) -{ - return (u64)atomic64_read(&(counter)->packets); -} - -static inline bool -ip_set_match_counter(u64 counter, u64 match, u8 op) -{ - switch (op) { - case IPSET_COUNTER_NONE: - return true; - case IPSET_COUNTER_EQ: - return counter == match; - case IPSET_COUNTER_NE: - return counter != match; - case IPSET_COUNTER_LT: - return counter < match; - case IPSET_COUNTER_GT: - return counter > match; - } - return false; -} - -static inline void -ip_set_update_counter(struct ip_set_counter *counter, - const struct ip_set_ext *ext, u32 flags) -{ - if (ext->packets != ULLONG_MAX && - !(flags & IPSET_FLAG_SKIP_COUNTER_UPDATE)) { - ip_set_add_bytes(ext->bytes, counter); - ip_set_add_packets(ext->packets, counter); - } -} - -static inline bool -ip_set_put_counter(struct sk_buff *skb, const struct ip_set_counter *counter) -{ - return nla_put_net64(skb, IPSET_ATTR_BYTES, - cpu_to_be64(ip_set_get_bytes(counter)), - IPSET_ATTR_PAD) || - nla_put_net64(skb, IPSET_ATTR_PACKETS, - cpu_to_be64(ip_set_get_packets(counter)), - IPSET_ATTR_PAD); -} - -static inline void -ip_set_init_counter(struct ip_set_counter *counter, - const struct ip_set_ext *ext) -{ - if (ext->bytes != ULLONG_MAX) - atomic64_set(&(counter)->bytes, (long long)(ext->bytes)); - if (ext->packets != ULLONG_MAX) - atomic64_set(&(counter)->packets, (long long)(ext->packets)); -} - -#endif /* __KERNEL__ */ -#endif /* _IP_SET_COUNTER_H */ diff --git a/include/linux/netfilter/ipset/ip_set_skbinfo.h b/include/linux/netfilter/ipset/ip_set_skbinfo.h deleted file mode 100644 index 3a2df02dbd55..000000000000 --- a/include/linux/netfilter/ipset/ip_set_skbinfo.h +++ /dev/null @@ -1,42 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0-only */ -#ifndef _IP_SET_SKBINFO_H -#define _IP_SET_SKBINFO_H - -/* Copyright (C) 2015 Jozsef Kadlecsik */ - -#ifdef __KERNEL__ - -static inline void -ip_set_get_skbinfo(struct ip_set_skbinfo *skbinfo, - const struct ip_set_ext *ext, - struct ip_set_ext *mext, u32 flags) -{ - mext->skbinfo = *skbinfo; -} - -static inline bool -ip_set_put_skbinfo(struct sk_buff *skb, const struct ip_set_skbinfo *skbinfo) -{ - /* Send nonzero parameters only */ - return ((skbinfo->skbmark || skbinfo->skbmarkmask) && - nla_put_net64(skb, IPSET_ATTR_SKBMARK, - cpu_to_be64((u64)skbinfo->skbmark << 32 | - skbinfo->skbmarkmask), - IPSET_ATTR_PAD)) || - (skbinfo->skbprio && - nla_put_net32(skb, IPSET_ATTR_SKBPRIO, - cpu_to_be32(skbinfo->skbprio))) || - (skbinfo->skbqueue && - nla_put_net16(skb, IPSET_ATTR_SKBQUEUE, - cpu_to_be16(skbinfo->skbqueue))); -} - -static inline void -ip_set_init_skbinfo(struct ip_set_skbinfo *skbinfo, - const struct ip_set_ext *ext) -{ - *skbinfo = ext->skbinfo; -} - -#endif /* __KERNEL__ */ -#endif /* _IP_SET_SKBINFO_H */ diff --git a/include/linux/netfilter/ipset/ip_set_timeout.h b/include/linux/netfilter/ipset/ip_set_timeout.h deleted file mode 100644 index 2be60e379ecf..000000000000 --- a/include/linux/netfilter/ipset/ip_set_timeout.h +++ /dev/null @@ -1,77 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0-only */ -#ifndef _IP_SET_TIMEOUT_H -#define _IP_SET_TIMEOUT_H - -/* Copyright (C) 2003-2013 Jozsef Kadlecsik */ - -#ifdef __KERNEL__ - -/* How often should the gc be run by default */ -#define IPSET_GC_TIME (3 * 60) - -/* Timeout period depending on the timeout value of the given set */ -#define IPSET_GC_PERIOD(timeout) \ - ((timeout/3) ? min_t(u32, (timeout)/3, IPSET_GC_TIME) : 1) - -/* Entry is set with no timeout value */ -#define IPSET_ELEM_PERMANENT 0 - -/* Set is defined with timeout support: timeout value may be 0 */ -#define IPSET_NO_TIMEOUT UINT_MAX - -/* Max timeout value, see msecs_to_jiffies() in jiffies.h */ -#define IPSET_MAX_TIMEOUT (UINT_MAX >> 1)/MSEC_PER_SEC - -#define ip_set_adt_opt_timeout(opt, set) \ -((opt)->ext.timeout != IPSET_NO_TIMEOUT ? (opt)->ext.timeout : (set)->timeout) - -static inline unsigned int -ip_set_timeout_uget(struct nlattr *tb) -{ - unsigned int timeout = ip_set_get_h32(tb); - - /* Normalize to fit into jiffies */ - if (timeout > IPSET_MAX_TIMEOUT) - timeout = IPSET_MAX_TIMEOUT; - - return timeout; -} - -static inline bool -ip_set_timeout_expired(const unsigned long *t) -{ - return *t != IPSET_ELEM_PERMANENT && time_is_before_jiffies(*t); -} - -static inline void -ip_set_timeout_set(unsigned long *timeout, u32 value) -{ - unsigned long t; - - if (!value) { - *timeout = IPSET_ELEM_PERMANENT; - return; - } - - t = msecs_to_jiffies(value * MSEC_PER_SEC) + jiffies; - if (t == IPSET_ELEM_PERMANENT) - /* Bingo! :-) */ - t--; - *timeout = t; -} - -static inline u32 -ip_set_timeout_get(const unsigned long *timeout) -{ - u32 t; - - if (*timeout == IPSET_ELEM_PERMANENT) - return 0; - - t = jiffies_to_msecs(*timeout - jiffies)/MSEC_PER_SEC; - /* Zero value in userspace means no timeout */ - return t == 0 ? 1 : t; -} - -#endif /* __KERNEL__ */ -#endif /* _IP_SET_TIMEOUT_H */ diff --git a/net/netfilter/ipset/ip_set_hash_gen.h b/net/netfilter/ipset/ip_set_hash_gen.h index 3fced06ab752..d098d87bc331 100644 --- a/net/netfilter/ipset/ip_set_hash_gen.h +++ b/net/netfilter/ipset/ip_set_hash_gen.h @@ -7,7 +7,7 @@ #include #include #include -#include +#include #define __ipset_dereference_protected(p, c) rcu_dereference_protected(p, c) #define ipset_dereference_protected(p, set) \ diff --git a/net/netfilter/xt_set.c b/net/netfilter/xt_set.c index ecbfa291fb70..731bc2cafae4 100644 --- a/net/netfilter/xt_set.c +++ b/net/netfilter/xt_set.c @@ -14,7 +14,6 @@ #include #include -#include #include MODULE_LICENSE("GPL"); -- cgit v1.2.3 From a1b2f04ea527397fcacacd09e0d690927feef429 Mon Sep 17 00:00:00 2001 From: Jeremy Sowden Date: Wed, 7 Aug 2019 15:16:59 +0100 Subject: netfilter: add missing includes to a number of header-files. A number of netfilter header-files used declarations and definitions from other headers without including them. Added include directives to make those declarations and definitions available. Signed-off-by: Jeremy Sowden Signed-off-by: Pablo Neira Ayuso --- include/linux/netfilter/ipset/ip_set_getport.h | 4 ++++ include/linux/netfilter/nf_conntrack_amanda.h | 4 ++++ include/linux/netfilter/nf_conntrack_ftp.h | 8 +++++--- include/linux/netfilter/nf_conntrack_h323.h | 7 +++++-- include/linux/netfilter/nf_conntrack_h323_asn1.h | 2 ++ include/linux/netfilter/nf_conntrack_irc.h | 4 ++++ include/linux/netfilter/nf_conntrack_pptp.h | 9 +++++---- include/linux/netfilter/nf_conntrack_sip.h | 4 ++-- include/linux/netfilter/nf_conntrack_snmp.h | 3 +++ include/linux/netfilter/nf_conntrack_tftp.h | 5 +++++ include/net/netfilter/br_netfilter.h | 2 ++ include/net/netfilter/ipv4/nf_dup_ipv4.h | 3 +++ include/net/netfilter/ipv6/nf_defrag_ipv6.h | 4 +++- include/net/netfilter/ipv6/nf_dup_ipv6.h | 2 ++ include/net/netfilter/nf_conntrack_bridge.h | 4 ++++ include/net/netfilter/nf_conntrack_count.h | 3 +++ include/net/netfilter/nf_dup_netdev.h | 2 ++ include/net/netfilter/nf_flow_table.h | 1 + include/net/netfilter/nf_nat_helper.h | 4 ++-- include/net/netfilter/nf_nat_redirect.h | 3 +++ include/net/netfilter/nf_queue.h | 2 ++ include/net/netfilter/nf_reject.h | 3 +++ include/net/netfilter/nf_tables_ipv6.h | 1 + include/net/netfilter/nft_fib.h | 2 ++ include/net/netfilter/nft_meta.h | 2 ++ include/net/netfilter/nft_reject.h | 5 +++++ include/uapi/linux/netfilter/xt_policy.h | 1 + 27 files changed, 80 insertions(+), 14 deletions(-) (limited to 'include/linux') diff --git a/include/linux/netfilter/ipset/ip_set_getport.h b/include/linux/netfilter/ipset/ip_set_getport.h index ac6a11d38a19..a906df06948b 100644 --- a/include/linux/netfilter/ipset/ip_set_getport.h +++ b/include/linux/netfilter/ipset/ip_set_getport.h @@ -2,6 +2,10 @@ #ifndef _IP_SET_GETPORT_H #define _IP_SET_GETPORT_H +#include +#include +#include + extern bool ip_set_get_ip4_port(const struct sk_buff *skb, bool src, __be16 *port, u8 *proto); diff --git a/include/linux/netfilter/nf_conntrack_amanda.h b/include/linux/netfilter/nf_conntrack_amanda.h index 34345e543ba2..6f0ac896fcc9 100644 --- a/include/linux/netfilter/nf_conntrack_amanda.h +++ b/include/linux/netfilter/nf_conntrack_amanda.h @@ -3,6 +3,10 @@ #define _NF_CONNTRACK_AMANDA_H /* AMANDA tracking. */ +#include +#include +#include + extern unsigned int (*nf_nat_amanda_hook)(struct sk_buff *skb, enum ip_conntrack_info ctinfo, unsigned int protoff, diff --git a/include/linux/netfilter/nf_conntrack_ftp.h b/include/linux/netfilter/nf_conntrack_ftp.h index 73a296dfd019..0e38302820b9 100644 --- a/include/linux/netfilter/nf_conntrack_ftp.h +++ b/include/linux/netfilter/nf_conntrack_ftp.h @@ -2,8 +2,12 @@ #ifndef _NF_CONNTRACK_FTP_H #define _NF_CONNTRACK_FTP_H +#include +#include +#include +#include #include - +#include #define FTP_PORT 21 @@ -20,8 +24,6 @@ struct nf_ct_ftp_master { u_int16_t flags[IP_CT_DIR_MAX]; }; -struct nf_conntrack_expect; - /* For NAT to hook in when we find a packet which describes what other * connection we should expect. */ extern unsigned int (*nf_nat_ftp_hook)(struct sk_buff *skb, diff --git a/include/linux/netfilter/nf_conntrack_h323.h b/include/linux/netfilter/nf_conntrack_h323.h index f76ed373a2a5..96dfa886f8c0 100644 --- a/include/linux/netfilter/nf_conntrack_h323.h +++ b/include/linux/netfilter/nf_conntrack_h323.h @@ -4,7 +4,12 @@ #ifdef __KERNEL__ +#include +#include +#include #include +#include +#include #define RAS_PORT 1719 #define Q931_PORT 1720 @@ -28,8 +33,6 @@ struct nf_ct_h323_master { }; }; -struct nf_conn; - int get_h225_addr(struct nf_conn *ct, unsigned char *data, TransportAddress *taddr, union nf_inet_addr *addr, __be16 *port); diff --git a/include/linux/netfilter/nf_conntrack_h323_asn1.h b/include/linux/netfilter/nf_conntrack_h323_asn1.h index 19df78341fb3..bd6797f823b2 100644 --- a/include/linux/netfilter/nf_conntrack_h323_asn1.h +++ b/include/linux/netfilter/nf_conntrack_h323_asn1.h @@ -37,6 +37,8 @@ /***************************************************************************** * H.323 Types ****************************************************************************/ + +#include #include typedef struct { diff --git a/include/linux/netfilter/nf_conntrack_irc.h b/include/linux/netfilter/nf_conntrack_irc.h index 00c2b74206e1..f75e005db969 100644 --- a/include/linux/netfilter/nf_conntrack_irc.h +++ b/include/linux/netfilter/nf_conntrack_irc.h @@ -4,6 +4,10 @@ #ifdef __KERNEL__ +#include +#include +#include + #define IRC_PORT 6667 extern unsigned int (*nf_nat_irc_hook)(struct sk_buff *skb, diff --git a/include/linux/netfilter/nf_conntrack_pptp.h b/include/linux/netfilter/nf_conntrack_pptp.h index 833a5b2255ea..3f10e806f0dc 100644 --- a/include/linux/netfilter/nf_conntrack_pptp.h +++ b/include/linux/netfilter/nf_conntrack_pptp.h @@ -3,7 +3,12 @@ #ifndef _NF_CONNTRACK_PPTP_H #define _NF_CONNTRACK_PPTP_H +#include +#include +#include #include +#include +#include extern const char *const pptp_msg_name[]; @@ -297,10 +302,6 @@ union pptp_ctrl_union { struct PptpSetLinkInfo setlink; }; -/* crap needed for nf_conntrack_compat.h */ -struct nf_conn; -struct nf_conntrack_expect; - extern int (*nf_nat_pptp_hook_outbound)(struct sk_buff *skb, struct nf_conn *ct, enum ip_conntrack_info ctinfo, diff --git a/include/linux/netfilter/nf_conntrack_sip.h b/include/linux/netfilter/nf_conntrack_sip.h index c7fc38807a33..f6437f7841af 100644 --- a/include/linux/netfilter/nf_conntrack_sip.h +++ b/include/linux/netfilter/nf_conntrack_sip.h @@ -3,9 +3,9 @@ #define __NF_CONNTRACK_SIP_H__ #ifdef __KERNEL__ -#include - +#include #include +#include #define SIP_PORT 5060 #define SIP_TIMEOUT 3600 diff --git a/include/linux/netfilter/nf_conntrack_snmp.h b/include/linux/netfilter/nf_conntrack_snmp.h index 818088c47475..87e4f33eb55f 100644 --- a/include/linux/netfilter/nf_conntrack_snmp.h +++ b/include/linux/netfilter/nf_conntrack_snmp.h @@ -2,6 +2,9 @@ #ifndef _NF_CONNTRACK_SNMP_H #define _NF_CONNTRACK_SNMP_H +#include +#include + extern int (*nf_nat_snmp_hook)(struct sk_buff *skb, unsigned int protoff, struct nf_conn *ct, diff --git a/include/linux/netfilter/nf_conntrack_tftp.h b/include/linux/netfilter/nf_conntrack_tftp.h index 5769e12dd0a2..dc4c1b9beac0 100644 --- a/include/linux/netfilter/nf_conntrack_tftp.h +++ b/include/linux/netfilter/nf_conntrack_tftp.h @@ -4,6 +4,11 @@ #define TFTP_PORT 69 +#include +#include +#include +#include + struct tftphdr { __be16 opcode; }; diff --git a/include/net/netfilter/br_netfilter.h b/include/net/netfilter/br_netfilter.h index 302fcd3aade2..ca121ed906df 100644 --- a/include/net/netfilter/br_netfilter.h +++ b/include/net/netfilter/br_netfilter.h @@ -2,6 +2,8 @@ #ifndef _BR_NETFILTER_H_ #define _BR_NETFILTER_H_ +#include + #include "../../../net/bridge/br_private.h" static inline struct nf_bridge_info *nf_bridge_alloc(struct sk_buff *skb) diff --git a/include/net/netfilter/ipv4/nf_dup_ipv4.h b/include/net/netfilter/ipv4/nf_dup_ipv4.h index c962e0be3549..a2bc16cdbcd3 100644 --- a/include/net/netfilter/ipv4/nf_dup_ipv4.h +++ b/include/net/netfilter/ipv4/nf_dup_ipv4.h @@ -2,6 +2,9 @@ #ifndef _NF_DUP_IPV4_H_ #define _NF_DUP_IPV4_H_ +#include +#include + void nf_dup_ipv4(struct net *net, struct sk_buff *skb, unsigned int hooknum, const struct in_addr *gw, int oif); diff --git a/include/net/netfilter/ipv6/nf_defrag_ipv6.h b/include/net/netfilter/ipv6/nf_defrag_ipv6.h index 9d7e28736da9..6d31cd041143 100644 --- a/include/net/netfilter/ipv6/nf_defrag_ipv6.h +++ b/include/net/netfilter/ipv6/nf_defrag_ipv6.h @@ -2,7 +2,9 @@ #ifndef _NF_DEFRAG_IPV6_H #define _NF_DEFRAG_IPV6_H -struct net; +#include +#include + int nf_defrag_ipv6_enable(struct net *); int nf_ct_frag6_init(void); diff --git a/include/net/netfilter/ipv6/nf_dup_ipv6.h b/include/net/netfilter/ipv6/nf_dup_ipv6.h index caf0c2dd8ee7..f6312bb04a13 100644 --- a/include/net/netfilter/ipv6/nf_dup_ipv6.h +++ b/include/net/netfilter/ipv6/nf_dup_ipv6.h @@ -2,6 +2,8 @@ #ifndef _NF_DUP_IPV6_H_ #define _NF_DUP_IPV6_H_ +#include + void nf_dup_ipv6(struct net *net, struct sk_buff *skb, unsigned int hooknum, const struct in6_addr *gw, int oif); diff --git a/include/net/netfilter/nf_conntrack_bridge.h b/include/net/netfilter/nf_conntrack_bridge.h index 9a5514d5bc51..8f2e5b2ab523 100644 --- a/include/net/netfilter/nf_conntrack_bridge.h +++ b/include/net/netfilter/nf_conntrack_bridge.h @@ -1,6 +1,10 @@ #ifndef NF_CONNTRACK_BRIDGE_ #define NF_CONNTRACK_BRIDGE_ +#include +#include +#include + struct nf_ct_bridge_info { struct nf_hook_ops *ops; unsigned int ops_size; diff --git a/include/net/netfilter/nf_conntrack_count.h b/include/net/netfilter/nf_conntrack_count.h index f32fc8289473..9645b47fa7e4 100644 --- a/include/net/netfilter/nf_conntrack_count.h +++ b/include/net/netfilter/nf_conntrack_count.h @@ -2,6 +2,9 @@ #define _NF_CONNTRACK_COUNT_H #include +#include +#include +#include struct nf_conncount_data; diff --git a/include/net/netfilter/nf_dup_netdev.h b/include/net/netfilter/nf_dup_netdev.h index 2a6f6dcad3d9..181672672160 100644 --- a/include/net/netfilter/nf_dup_netdev.h +++ b/include/net/netfilter/nf_dup_netdev.h @@ -2,6 +2,8 @@ #ifndef _NF_DUP_NETDEV_H_ #define _NF_DUP_NETDEV_H_ +#include + void nf_dup_netdev_egress(const struct nft_pktinfo *pkt, int oif); void nf_fwd_netdev_egress(const struct nft_pktinfo *pkt, int oif); diff --git a/include/net/netfilter/nf_flow_table.h b/include/net/netfilter/nf_flow_table.h index d8c187936bec..7249e331bd0b 100644 --- a/include/net/netfilter/nf_flow_table.h +++ b/include/net/netfilter/nf_flow_table.h @@ -6,6 +6,7 @@ #include #include #include +#include #include #include diff --git a/include/net/netfilter/nf_nat_helper.h b/include/net/netfilter/nf_nat_helper.h index 97d7033e93a4..efae84646353 100644 --- a/include/net/netfilter/nf_nat_helper.h +++ b/include/net/netfilter/nf_nat_helper.h @@ -3,9 +3,9 @@ #define _NF_NAT_HELPER_H /* NAT protocol helper routines. */ +#include #include - -struct sk_buff; +#include /* These return true or false. */ bool __nf_nat_mangle_tcp_packet(struct sk_buff *skb, struct nf_conn *ct, diff --git a/include/net/netfilter/nf_nat_redirect.h b/include/net/netfilter/nf_nat_redirect.h index c129aacc8ae8..2418653a66db 100644 --- a/include/net/netfilter/nf_nat_redirect.h +++ b/include/net/netfilter/nf_nat_redirect.h @@ -2,6 +2,9 @@ #ifndef _NF_NAT_REDIRECT_H_ #define _NF_NAT_REDIRECT_H_ +#include +#include + unsigned int nf_nat_redirect_ipv4(struct sk_buff *skb, const struct nf_nat_ipv4_multi_range_compat *mr, diff --git a/include/net/netfilter/nf_queue.h b/include/net/netfilter/nf_queue.h index 3cb6dcf53a4e..359b80b43169 100644 --- a/include/net/netfilter/nf_queue.h +++ b/include/net/netfilter/nf_queue.h @@ -5,6 +5,8 @@ #include #include #include +#include +#include /* Each queued (to userspace) skbuff has one of these. */ struct nf_queue_entry { diff --git a/include/net/netfilter/nf_reject.h b/include/net/netfilter/nf_reject.h index 221f877f29d1..9051c3a0c8e7 100644 --- a/include/net/netfilter/nf_reject.h +++ b/include/net/netfilter/nf_reject.h @@ -2,6 +2,9 @@ #ifndef _NF_REJECT_H #define _NF_REJECT_H +#include +#include + static inline bool nf_reject_verify_csum(__u8 proto) { /* Skip protocols that don't use 16-bit one's complement checksum diff --git a/include/net/netfilter/nf_tables_ipv6.h b/include/net/netfilter/nf_tables_ipv6.h index dabe6fdb553a..d0f1c537b017 100644 --- a/include/net/netfilter/nf_tables_ipv6.h +++ b/include/net/netfilter/nf_tables_ipv6.h @@ -4,6 +4,7 @@ #include #include +#include static inline void nft_set_pktinfo_ipv6(struct nft_pktinfo *pkt, struct sk_buff *skb) diff --git a/include/net/netfilter/nft_fib.h b/include/net/netfilter/nft_fib.h index e4c4d8eaca8c..628b6fa579cd 100644 --- a/include/net/netfilter/nft_fib.h +++ b/include/net/netfilter/nft_fib.h @@ -2,6 +2,8 @@ #ifndef _NFT_FIB_H_ #define _NFT_FIB_H_ +#include + struct nft_fib { enum nft_registers dreg:8; u8 result; diff --git a/include/net/netfilter/nft_meta.h b/include/net/netfilter/nft_meta.h index 5c69e9b09388..07e2fd507963 100644 --- a/include/net/netfilter/nft_meta.h +++ b/include/net/netfilter/nft_meta.h @@ -2,6 +2,8 @@ #ifndef _NFT_META_H_ #define _NFT_META_H_ +#include + struct nft_meta { enum nft_meta_keys key:8; union { diff --git a/include/net/netfilter/nft_reject.h b/include/net/netfilter/nft_reject.h index de80c50761f0..56b123a42220 100644 --- a/include/net/netfilter/nft_reject.h +++ b/include/net/netfilter/nft_reject.h @@ -2,6 +2,11 @@ #ifndef _NFT_REJECT_H_ #define _NFT_REJECT_H_ +#include +#include +#include +#include + struct nft_reject { enum nft_reject_types type:8; u8 icmp_code; diff --git a/include/uapi/linux/netfilter/xt_policy.h b/include/uapi/linux/netfilter/xt_policy.h index 323bfa3074c5..4cf2ce2a8a44 100644 --- a/include/uapi/linux/netfilter/xt_policy.h +++ b/include/uapi/linux/netfilter/xt_policy.h @@ -2,6 +2,7 @@ #ifndef _XT_POLICY_H #define _XT_POLICY_H +#include #include #include #include -- cgit v1.2.3 From 78458e3e08cda2aacaec9fde8c295dfc2f88618a Mon Sep 17 00:00:00 2001 From: Jeremy Sowden Date: Wed, 7 Aug 2019 15:17:03 +0100 Subject: netfilter: add missing IS_ENABLED(CONFIG_NETFILTER) checks to some header-files. linux/netfilter.h defines a number of struct and inline function definitions which are only available is CONFIG_NETFILTER is enabled. These structs and functions are used in declarations and definitions in other header-files. Added preprocessor checks to make sure these headers will compile if CONFIG_NETFILTER is disabled. Signed-off-by: Jeremy Sowden Signed-off-by: Pablo Neira Ayuso --- include/linux/netfilter/x_tables.h | 6 ++++++ include/linux/netfilter_arp/arp_tables.h | 2 ++ include/linux/netfilter_bridge/ebtables.h | 2 ++ include/linux/netfilter_ipv4/ip_tables.h | 4 ++++ include/linux/netfilter_ipv6/ip6_tables.h | 2 ++ include/net/netfilter/br_netfilter.h | 2 ++ include/net/netfilter/nf_conntrack_bridge.h | 2 ++ include/net/netfilter/nf_conntrack_core.h | 3 +++ include/net/netfilter/nf_conntrack_l4proto.h | 2 ++ include/net/netfilter/nf_conntrack_tuple.h | 2 ++ include/net/netfilter/nf_flow_table.h | 4 ++++ include/net/netfilter/nf_nat.h | 4 ++++ include/net/netfilter/nf_queue.h | 5 +++++ include/net/netfilter/nf_synproxy.h | 4 ++++ include/net/netfilter/nf_tables.h | 8 ++++++++ 15 files changed, 52 insertions(+) (limited to 'include/linux') diff --git a/include/linux/netfilter/x_tables.h b/include/linux/netfilter/x_tables.h index 1f852ef7b098..ae62bf1c6824 100644 --- a/include/linux/netfilter/x_tables.h +++ b/include/linux/netfilter/x_tables.h @@ -35,12 +35,15 @@ struct xt_action_param { union { const void *matchinfo, *targinfo; }; +#if IS_ENABLED(CONFIG_NETFILTER) const struct nf_hook_state *state; +#endif int fragoff; unsigned int thoff; bool hotdrop; }; +#if IS_ENABLED(CONFIG_NETFILTER) static inline struct net *xt_net(const struct xt_action_param *par) { return par->state->net; @@ -75,6 +78,7 @@ static inline u_int8_t xt_family(const struct xt_action_param *par) { return par->state->pf; } +#endif /** * struct xt_mtchk_param - parameters for match extensions' @@ -446,7 +450,9 @@ xt_get_per_cpu_counter(struct xt_counters *cnt, unsigned int cpu) return cnt; } +#if IS_ENABLED(CONFIG_NETFILTER) struct nf_hook_ops *xt_hook_ops_alloc(const struct xt_table *, nf_hookfn *); +#endif #ifdef CONFIG_COMPAT #include diff --git a/include/linux/netfilter_arp/arp_tables.h b/include/linux/netfilter_arp/arp_tables.h index e98028f00e47..1b7b35bb9c27 100644 --- a/include/linux/netfilter_arp/arp_tables.h +++ b/include/linux/netfilter_arp/arp_tables.h @@ -49,6 +49,7 @@ struct arpt_error { } extern void *arpt_alloc_initial_table(const struct xt_table *); +#if IS_ENABLED(CONFIG_NETFILTER) int arpt_register_table(struct net *net, const struct xt_table *table, const struct arpt_replace *repl, const struct nf_hook_ops *ops, struct xt_table **res); @@ -57,6 +58,7 @@ void arpt_unregister_table(struct net *net, struct xt_table *table, extern unsigned int arpt_do_table(struct sk_buff *skb, const struct nf_hook_state *state, struct xt_table *table); +#endif #ifdef CONFIG_COMPAT #include diff --git a/include/linux/netfilter_bridge/ebtables.h b/include/linux/netfilter_bridge/ebtables.h index c6935be7c6ca..b5b2d371f0ef 100644 --- a/include/linux/netfilter_bridge/ebtables.h +++ b/include/linux/netfilter_bridge/ebtables.h @@ -105,6 +105,7 @@ struct ebt_table { #define EBT_ALIGN(s) (((s) + (__alignof__(struct _xt_align)-1)) & \ ~(__alignof__(struct _xt_align)-1)) +#if IS_ENABLED(CONFIG_NETFILTER) extern int ebt_register_table(struct net *net, const struct ebt_table *table, const struct nf_hook_ops *ops, @@ -114,6 +115,7 @@ extern void ebt_unregister_table(struct net *net, struct ebt_table *table, extern unsigned int ebt_do_table(struct sk_buff *skb, const struct nf_hook_state *state, struct ebt_table *table); +#endif /* True if the hook mask denotes that the rule is in a base chain, * used in the check() functions */ diff --git a/include/linux/netfilter_ipv4/ip_tables.h b/include/linux/netfilter_ipv4/ip_tables.h index d026e63a5aa4..f40a65481df4 100644 --- a/include/linux/netfilter_ipv4/ip_tables.h +++ b/include/linux/netfilter_ipv4/ip_tables.h @@ -25,11 +25,13 @@ extern void ipt_init(void) __init; +#if IS_ENABLED(CONFIG_NETFILTER) int ipt_register_table(struct net *net, const struct xt_table *table, const struct ipt_replace *repl, const struct nf_hook_ops *ops, struct xt_table **res); void ipt_unregister_table(struct net *net, struct xt_table *table, const struct nf_hook_ops *ops); +#endif /* Standard entry. */ struct ipt_standard { @@ -65,9 +67,11 @@ struct ipt_error { } extern void *ipt_alloc_initial_table(const struct xt_table *); +#if IS_ENABLED(CONFIG_NETFILTER) extern unsigned int ipt_do_table(struct sk_buff *skb, const struct nf_hook_state *state, struct xt_table *table); +#endif #ifdef CONFIG_COMPAT #include diff --git a/include/linux/netfilter_ipv6/ip6_tables.h b/include/linux/netfilter_ipv6/ip6_tables.h index 99cbfd3add40..53b7309613bf 100644 --- a/include/linux/netfilter_ipv6/ip6_tables.h +++ b/include/linux/netfilter_ipv6/ip6_tables.h @@ -26,6 +26,7 @@ extern void ip6t_init(void) __init; extern void *ip6t_alloc_initial_table(const struct xt_table *); +#if IS_ENABLED(CONFIG_NETFILTER) int ip6t_register_table(struct net *net, const struct xt_table *table, const struct ip6t_replace *repl, const struct nf_hook_ops *ops, struct xt_table **res); @@ -34,6 +35,7 @@ void ip6t_unregister_table(struct net *net, struct xt_table *table, extern unsigned int ip6t_do_table(struct sk_buff *skb, const struct nf_hook_state *state, struct xt_table *table); +#endif /* Check for an extension */ static inline int diff --git a/include/net/netfilter/br_netfilter.h b/include/net/netfilter/br_netfilter.h index 33533ea852a1..2a613c84d49f 100644 --- a/include/net/netfilter/br_netfilter.h +++ b/include/net/netfilter/br_netfilter.h @@ -55,6 +55,7 @@ static inline struct rtable *bridge_parent_rtable(const struct net_device *dev) struct net_device *setup_pre_routing(struct sk_buff *skb, const struct net *net); +#if IS_ENABLED(CONFIG_NETFILTER) #if IS_ENABLED(CONFIG_IPV6) int br_validate_ipv6(struct net *net, struct sk_buff *skb); unsigned int br_nf_pre_routing_ipv6(void *priv, @@ -73,5 +74,6 @@ br_nf_pre_routing_ipv6(const struct nf_hook_ops *ops, struct sk_buff *skb, return NF_ACCEPT; } #endif +#endif #endif /* _BR_NETFILTER_H_ */ diff --git a/include/net/netfilter/nf_conntrack_bridge.h b/include/net/netfilter/nf_conntrack_bridge.h index 8f2e5b2ab523..34c28f248b18 100644 --- a/include/net/netfilter/nf_conntrack_bridge.h +++ b/include/net/netfilter/nf_conntrack_bridge.h @@ -6,7 +6,9 @@ #include struct nf_ct_bridge_info { +#if IS_ENABLED(CONFIG_NETFILTER) struct nf_hook_ops *ops; +#endif unsigned int ops_size; struct module *me; }; diff --git a/include/net/netfilter/nf_conntrack_core.h b/include/net/netfilter/nf_conntrack_core.h index de10faf2ce91..71a2d9cb64ea 100644 --- a/include/net/netfilter/nf_conntrack_core.h +++ b/include/net/netfilter/nf_conntrack_core.h @@ -20,7 +20,10 @@ /* This header is used to share core functionality between the standalone connection tracking module, and the compatibility layer's use of connection tracking. */ + +#if IS_ENABLED(CONFIG_NETFILTER) unsigned int nf_conntrack_in(struct sk_buff *skb, const struct nf_hook_state *state); +#endif int nf_conntrack_init_net(struct net *net); void nf_conntrack_cleanup_net(struct net *net); diff --git a/include/net/netfilter/nf_conntrack_l4proto.h b/include/net/netfilter/nf_conntrack_l4proto.h index 1990d54bf8f2..c200b95d27ae 100644 --- a/include/net/netfilter/nf_conntrack_l4proto.h +++ b/include/net/netfilter/nf_conntrack_l4proto.h @@ -75,6 +75,7 @@ bool nf_conntrack_invert_icmp_tuple(struct nf_conntrack_tuple *tuple, bool nf_conntrack_invert_icmpv6_tuple(struct nf_conntrack_tuple *tuple, const struct nf_conntrack_tuple *orig); +#if IS_ENABLED(CONFIG_NETFILTER) int nf_conntrack_inet_error(struct nf_conn *tmpl, struct sk_buff *skb, unsigned int dataoff, const struct nf_hook_state *state, @@ -131,6 +132,7 @@ int nf_conntrack_gre_packet(struct nf_conn *ct, unsigned int dataoff, enum ip_conntrack_info ctinfo, const struct nf_hook_state *state); +#endif void nf_conntrack_generic_init_net(struct net *net); void nf_conntrack_tcp_init_net(struct net *net); diff --git a/include/net/netfilter/nf_conntrack_tuple.h b/include/net/netfilter/nf_conntrack_tuple.h index bf0444e111a6..480c87b44a96 100644 --- a/include/net/netfilter/nf_conntrack_tuple.h +++ b/include/net/netfilter/nf_conntrack_tuple.h @@ -121,6 +121,7 @@ struct nf_conntrack_tuple_hash { struct nf_conntrack_tuple tuple; }; +#if IS_ENABLED(CONFIG_NETFILTER) static inline bool __nf_ct_tuple_src_equal(const struct nf_conntrack_tuple *t1, const struct nf_conntrack_tuple *t2) { @@ -183,5 +184,6 @@ nf_ct_tuple_mask_cmp(const struct nf_conntrack_tuple *t, return nf_ct_tuple_src_mask_cmp(t, tuple, mask) && __nf_ct_tuple_dst_equal(t, tuple); } +#endif #endif /* _NF_CONNTRACK_TUPLE_H */ diff --git a/include/net/netfilter/nf_flow_table.h b/include/net/netfilter/nf_flow_table.h index 7249e331bd0b..609df33b1209 100644 --- a/include/net/netfilter/nf_flow_table.h +++ b/include/net/netfilter/nf_flow_table.h @@ -17,7 +17,9 @@ struct nf_flowtable_type { int family; int (*init)(struct nf_flowtable *ft); void (*free)(struct nf_flowtable *ft); +#if IS_ENABLED(CONFIG_NETFILTER) nf_hookfn *hook; +#endif struct module *owner; }; @@ -115,10 +117,12 @@ struct flow_ports { __be16 source, dest; }; +#if IS_ENABLED(CONFIG_NETFILTER) unsigned int nf_flow_offload_ip_hook(void *priv, struct sk_buff *skb, const struct nf_hook_state *state); unsigned int nf_flow_offload_ipv6_hook(void *priv, struct sk_buff *skb, const struct nf_hook_state *state); +#endif #define MODULE_ALIAS_NF_FLOWTABLE(family) \ MODULE_ALIAS("nf-flowtable-" __stringify(family)) diff --git a/include/net/netfilter/nf_nat.h b/include/net/netfilter/nf_nat.h index 423cda2c6542..eec208fb9c23 100644 --- a/include/net/netfilter/nf_nat.h +++ b/include/net/netfilter/nf_nat.h @@ -69,10 +69,12 @@ static inline bool nf_nat_oif_changed(unsigned int hooknum, #endif } +#if IS_ENABLED(CONFIG_NETFILTER) int nf_nat_register_fn(struct net *net, u8 pf, const struct nf_hook_ops *ops, const struct nf_hook_ops *nat_ops, unsigned int ops_count); void nf_nat_unregister_fn(struct net *net, u8 pf, const struct nf_hook_ops *ops, unsigned int ops_count); +#endif unsigned int nf_nat_packet(struct nf_conn *ct, enum ip_conntrack_info ctinfo, unsigned int hooknum, struct sk_buff *skb); @@ -92,6 +94,7 @@ int nf_nat_icmpv6_reply_translation(struct sk_buff *skb, struct nf_conn *ct, enum ip_conntrack_info ctinfo, unsigned int hooknum, unsigned int hdrlen); +#if IS_ENABLED(CONFIG_NETFILTER) int nf_nat_ipv4_register_fn(struct net *net, const struct nf_hook_ops *ops); void nf_nat_ipv4_unregister_fn(struct net *net, const struct nf_hook_ops *ops); @@ -104,6 +107,7 @@ void nf_nat_inet_unregister_fn(struct net *net, const struct nf_hook_ops *ops); unsigned int nf_nat_inet_fn(void *priv, struct sk_buff *skb, const struct nf_hook_state *state); +#endif int nf_xfrm_me_harder(struct net *n, struct sk_buff *s, unsigned int family); diff --git a/include/net/netfilter/nf_queue.h b/include/net/netfilter/nf_queue.h index 359b80b43169..80edb46a1bbc 100644 --- a/include/net/netfilter/nf_queue.h +++ b/include/net/netfilter/nf_queue.h @@ -15,7 +15,9 @@ struct nf_queue_entry { unsigned int id; unsigned int hook_index; /* index in hook_entries->hook[] */ +#if IS_ENABLED(CONFIG_NETFILTER) struct nf_hook_state state; +#endif u16 size; /* sizeof(entry) + saved route keys */ /* extra space to store route keys */ @@ -121,6 +123,9 @@ nfqueue_hash(const struct sk_buff *skb, u16 queue, u16 queues_total, u8 family, return queue; } +#if IS_ENABLED(CONFIG_NETFILTER) int nf_queue(struct sk_buff *skb, struct nf_hook_state *state, unsigned int index, unsigned int verdict); +#endif + #endif /* _NF_QUEUE_H */ diff --git a/include/net/netfilter/nf_synproxy.h b/include/net/netfilter/nf_synproxy.h index 87d73fb5279d..dc420b47e3aa 100644 --- a/include/net/netfilter/nf_synproxy.h +++ b/include/net/netfilter/nf_synproxy.h @@ -20,8 +20,10 @@ bool synproxy_recv_client_ack(struct net *net, const struct tcphdr *th, struct synproxy_options *opts, u32 recv_seq); +#if IS_ENABLED(CONFIG_NETFILTER) unsigned int ipv4_synproxy_hook(void *priv, struct sk_buff *skb, const struct nf_hook_state *nhs); +#endif int nf_synproxy_ipv4_init(struct synproxy_net *snet, struct net *net); void nf_synproxy_ipv4_fini(struct synproxy_net *snet, struct net *net); @@ -35,8 +37,10 @@ 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); +#if IS_ENABLED(CONFIG_NETFILTER) unsigned int ipv6_synproxy_hook(void *priv, struct sk_buff *skb, const struct nf_hook_state *nhs); +#endif 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 diff --git a/include/net/netfilter/nf_tables.h b/include/net/netfilter/nf_tables.h index 66edf76301d3..dc301e3d6739 100644 --- a/include/net/netfilter/nf_tables.h +++ b/include/net/netfilter/nf_tables.h @@ -25,6 +25,7 @@ struct nft_pktinfo { struct xt_action_param xt; }; +#if IS_ENABLED(CONFIG_NETFILTER) static inline struct net *nft_net(const struct nft_pktinfo *pkt) { return pkt->xt.state->net; @@ -57,6 +58,7 @@ static inline void nft_set_pktinfo(struct nft_pktinfo *pkt, pkt->skb = skb; pkt->xt.state = state; } +#endif static inline void nft_set_pktinfo_unspec(struct nft_pktinfo *pkt, struct sk_buff *skb) @@ -927,9 +929,11 @@ struct nft_chain_type { int family; struct module *owner; unsigned int hook_mask; +#if IS_ENABLED(CONFIG_NETFILTER) nf_hookfn *hooks[NF_MAX_HOOKS]; int (*ops_register)(struct net *net, const struct nf_hook_ops *ops); void (*ops_unregister)(struct net *net, const struct nf_hook_ops *ops); +#endif }; int nft_chain_validate_dependency(const struct nft_chain *chain, @@ -955,7 +959,9 @@ struct nft_stats { * @flow_block: flow block (for hardware offload) */ struct nft_base_chain { +#if IS_ENABLED(CONFIG_NETFILTER) struct nf_hook_ops ops; +#endif const struct nft_chain_type *type; u8 policy; u8 flags; @@ -1152,7 +1158,9 @@ struct nft_flowtable { use:30; u64 handle; /* runtime data below here */ +#if IS_ENABLED(CONFIG_NETFILTER) struct nf_hook_ops *ops ____cacheline_aligned; +#endif struct nf_flowtable data; }; -- cgit v1.2.3 From 20a9379d9a03ee0712d225035308973ecc5f6783 Mon Sep 17 00:00:00 2001 From: Jeremy Sowden Date: Wed, 7 Aug 2019 15:17:04 +0100 Subject: netfilter: remove "#ifdef __KERNEL__" guards from some headers. A number of non-UAPI Netfilter header-files contained superfluous "#ifdef __KERNEL__" guards. Removed them. Signed-off-by: Jeremy Sowden Signed-off-by: Pablo Neira Ayuso --- include/linux/netfilter/nf_conntrack_dccp.h | 3 --- include/linux/netfilter/nf_conntrack_h323.h | 4 ---- include/linux/netfilter/nf_conntrack_irc.h | 3 --- include/linux/netfilter/nf_conntrack_pptp.h | 3 --- include/linux/netfilter/nf_conntrack_proto_gre.h | 2 -- include/linux/netfilter/nf_conntrack_sane.h | 4 ---- include/linux/netfilter/nf_conntrack_sip.h | 2 -- 7 files changed, 21 deletions(-) (limited to 'include/linux') diff --git a/include/linux/netfilter/nf_conntrack_dccp.h b/include/linux/netfilter/nf_conntrack_dccp.h index ace0f952d50f..c509ed76e714 100644 --- a/include/linux/netfilter/nf_conntrack_dccp.h +++ b/include/linux/netfilter/nf_conntrack_dccp.h @@ -25,7 +25,6 @@ enum ct_dccp_roles { }; #define CT_DCCP_ROLE_MAX (__CT_DCCP_ROLE_MAX - 1) -#ifdef __KERNEL__ #include struct nf_ct_dccp { @@ -36,6 +35,4 @@ struct nf_ct_dccp { u_int64_t handshake_seq; }; -#endif /* __KERNEL__ */ - #endif /* _NF_CONNTRACK_DCCP_H */ diff --git a/include/linux/netfilter/nf_conntrack_h323.h b/include/linux/netfilter/nf_conntrack_h323.h index 96dfa886f8c0..4561ec0fcea4 100644 --- a/include/linux/netfilter/nf_conntrack_h323.h +++ b/include/linux/netfilter/nf_conntrack_h323.h @@ -2,8 +2,6 @@ #ifndef _NF_CONNTRACK_H323_H #define _NF_CONNTRACK_H323_H -#ifdef __KERNEL__ - #include #include #include @@ -97,5 +95,3 @@ extern int (*nat_q931_hook) (struct sk_buff *skb, struct nf_conn *ct, struct nf_conntrack_expect *exp); #endif - -#endif diff --git a/include/linux/netfilter/nf_conntrack_irc.h b/include/linux/netfilter/nf_conntrack_irc.h index f75e005db969..d02255f721e1 100644 --- a/include/linux/netfilter/nf_conntrack_irc.h +++ b/include/linux/netfilter/nf_conntrack_irc.h @@ -2,8 +2,6 @@ #ifndef _NF_CONNTRACK_IRC_H #define _NF_CONNTRACK_IRC_H -#ifdef __KERNEL__ - #include #include #include @@ -17,5 +15,4 @@ extern unsigned int (*nf_nat_irc_hook)(struct sk_buff *skb, unsigned int matchlen, struct nf_conntrack_expect *exp); -#endif /* __KERNEL__ */ #endif /* _NF_CONNTRACK_IRC_H */ diff --git a/include/linux/netfilter/nf_conntrack_pptp.h b/include/linux/netfilter/nf_conntrack_pptp.h index 3f10e806f0dc..fcc409de31a4 100644 --- a/include/linux/netfilter/nf_conntrack_pptp.h +++ b/include/linux/netfilter/nf_conntrack_pptp.h @@ -50,8 +50,6 @@ struct nf_nat_pptp { __be16 pac_call_id; /* NAT'ed PAC call id */ }; -#ifdef __KERNEL__ - #define PPTP_CONTROL_PORT 1723 #define PPTP_PACKET_CONTROL 1 @@ -324,5 +322,4 @@ extern void (*nf_nat_pptp_hook_expectfn)(struct nf_conn *ct, struct nf_conntrack_expect *exp); -#endif /* __KERNEL__ */ #endif /* _NF_CONNTRACK_PPTP_H */ diff --git a/include/linux/netfilter/nf_conntrack_proto_gre.h b/include/linux/netfilter/nf_conntrack_proto_gre.h index 25f9a770fb84..f33aa6021364 100644 --- a/include/linux/netfilter/nf_conntrack_proto_gre.h +++ b/include/linux/netfilter/nf_conntrack_proto_gre.h @@ -10,7 +10,6 @@ struct nf_ct_gre { unsigned int timeout; }; -#ifdef __KERNEL__ #include struct nf_conn; @@ -32,5 +31,4 @@ void nf_ct_gre_keymap_destroy(struct nf_conn *ct); bool gre_pkt_to_tuple(const struct sk_buff *skb, unsigned int dataoff, struct net *net, struct nf_conntrack_tuple *tuple); -#endif /* __KERNEL__ */ #endif /* _CONNTRACK_PROTO_GRE_H */ diff --git a/include/linux/netfilter/nf_conntrack_sane.h b/include/linux/netfilter/nf_conntrack_sane.h index 7d2de44edce3..46c7acd1b4a7 100644 --- a/include/linux/netfilter/nf_conntrack_sane.h +++ b/include/linux/netfilter/nf_conntrack_sane.h @@ -3,8 +3,6 @@ #define _NF_CONNTRACK_SANE_H /* SANE tracking. */ -#ifdef __KERNEL__ - #define SANE_PORT 6566 enum sane_state { @@ -17,6 +15,4 @@ struct nf_ct_sane_master { enum sane_state state; }; -#endif /* __KERNEL__ */ - #endif /* _NF_CONNTRACK_SANE_H */ diff --git a/include/linux/netfilter/nf_conntrack_sip.h b/include/linux/netfilter/nf_conntrack_sip.h index f6437f7841af..c620521c42bc 100644 --- a/include/linux/netfilter/nf_conntrack_sip.h +++ b/include/linux/netfilter/nf_conntrack_sip.h @@ -1,7 +1,6 @@ /* SPDX-License-Identifier: GPL-2.0 */ #ifndef __NF_CONNTRACK_SIP_H__ #define __NF_CONNTRACK_SIP_H__ -#ifdef __KERNEL__ #include #include @@ -196,5 +195,4 @@ int ct_sip_get_sdp_header(const struct nf_conn *ct, const char *dptr, enum sdp_header_types term, unsigned int *matchoff, unsigned int *matchlen); -#endif /* __KERNEL__ */ #endif /* __NF_CONNTRACK_SIP_H__ */ -- cgit v1.2.3 From 331c56ac73846fa267c04ee6aa9a00bb5fed9440 Mon Sep 17 00:00:00 2001 From: Heiner Kallweit Date: Mon, 12 Aug 2019 23:51:27 +0200 Subject: net: phy: add phy_speed_down_core and phy_resolve_min_speed phy_speed_down_core provides most of the functionality for phy_speed_down. It makes use of new helper phy_resolve_min_speed that is based on the sorting of the settings[] array. In certain cases it may be helpful to be able to exclude legacy half duplex modes, therefore prepare phy_resolve_min_speed() for it. v2: - rename __phy_speed_down to phy_speed_down_core Signed-off-by: Heiner Kallweit Reviewed-by: Andrew Lunn Signed-off-by: Jakub Kicinski --- drivers/net/phy/phy-core.c | 28 ++++++++++++++++++++++++++++ include/linux/phy.h | 1 + 2 files changed, 29 insertions(+) (limited to 'include/linux') diff --git a/drivers/net/phy/phy-core.c b/drivers/net/phy/phy-core.c index 95f1e85d0d87..369903d9b6ec 100644 --- a/drivers/net/phy/phy-core.c +++ b/drivers/net/phy/phy-core.c @@ -315,6 +315,34 @@ void phy_resolve_aneg_linkmode(struct phy_device *phydev) } EXPORT_SYMBOL_GPL(phy_resolve_aneg_linkmode); +static int phy_resolve_min_speed(struct phy_device *phydev, bool fdx_only) +{ + __ETHTOOL_DECLARE_LINK_MODE_MASK(common); + int i = ARRAY_SIZE(settings); + + linkmode_and(common, phydev->lp_advertising, phydev->advertising); + + while (--i >= 0) { + if (test_bit(settings[i].bit, common)) { + if (fdx_only && settings[i].duplex != DUPLEX_FULL) + continue; + return settings[i].speed; + } + } + + return SPEED_UNKNOWN; +} + +int phy_speed_down_core(struct phy_device *phydev) +{ + int min_common_speed = phy_resolve_min_speed(phydev, true); + + if (min_common_speed == SPEED_UNKNOWN) + return -EINVAL; + + return __set_linkmode_max_speed(min_common_speed, phydev->advertising); +} + static void mmd_phy_indirect(struct mii_bus *bus, int phy_addr, int devad, u16 regnum) { diff --git a/include/linux/phy.h b/include/linux/phy.h index 781f4810ceba..62fdc7ff2b24 100644 --- a/include/linux/phy.h +++ b/include/linux/phy.h @@ -665,6 +665,7 @@ size_t phy_speeds(unsigned int *speeds, size_t size, unsigned long *mask); void of_set_phy_supported(struct phy_device *phydev); void of_set_phy_eee_broken(struct phy_device *phydev); +int phy_speed_down_core(struct phy_device *phydev); /** * phy_is_started - Convenience function to check whether PHY is started -- cgit v1.2.3 From 65b27995a4ab8fc51b4adc6b4dcdca20f7a595bb Mon Sep 17 00:00:00 2001 From: Heiner Kallweit Date: Mon, 12 Aug 2019 23:52:19 +0200 Subject: net: phy: let phy_speed_down/up support speeds >1Gbps So far phy_speed_down/up can be used up to 1Gbps only. Remove this restriction by using new helper __phy_speed_down. New member adv_old in struct phy_device is used by phy_speed_up to restore the advertised modes before calling phy_speed_down. Don't simply advertise what is supported because a user may have intentionally removed modes from advertisement. Signed-off-by: Heiner Kallweit Reviewed-by: Andrew Lunn Signed-off-by: Jakub Kicinski --- drivers/net/phy/phy.c | 60 ++++++++++++++------------------------------------- include/linux/phy.h | 2 ++ 2 files changed, 18 insertions(+), 44 deletions(-) (limited to 'include/linux') diff --git a/drivers/net/phy/phy.c b/drivers/net/phy/phy.c index ef7aa738e0dc..f3adea9ef400 100644 --- a/drivers/net/phy/phy.c +++ b/drivers/net/phy/phy.c @@ -608,38 +608,21 @@ static int phy_poll_aneg_done(struct phy_device *phydev) */ int phy_speed_down(struct phy_device *phydev, bool sync) { - __ETHTOOL_DECLARE_LINK_MODE_MASK(adv_old); - __ETHTOOL_DECLARE_LINK_MODE_MASK(adv); + __ETHTOOL_DECLARE_LINK_MODE_MASK(adv_tmp); int ret; if (phydev->autoneg != AUTONEG_ENABLE) return 0; - linkmode_copy(adv_old, phydev->advertising); - linkmode_copy(adv, phydev->lp_advertising); - linkmode_and(adv, adv, phydev->supported); - - if (linkmode_test_bit(ETHTOOL_LINK_MODE_10baseT_Half_BIT, adv) || - linkmode_test_bit(ETHTOOL_LINK_MODE_10baseT_Full_BIT, adv)) { - linkmode_clear_bit(ETHTOOL_LINK_MODE_100baseT_Half_BIT, - phydev->advertising); - linkmode_clear_bit(ETHTOOL_LINK_MODE_100baseT_Full_BIT, - phydev->advertising); - linkmode_clear_bit(ETHTOOL_LINK_MODE_1000baseT_Half_BIT, - phydev->advertising); - linkmode_clear_bit(ETHTOOL_LINK_MODE_1000baseT_Full_BIT, - phydev->advertising); - } else if (linkmode_test_bit(ETHTOOL_LINK_MODE_100baseT_Half_BIT, - adv) || - linkmode_test_bit(ETHTOOL_LINK_MODE_100baseT_Full_BIT, - adv)) { - linkmode_clear_bit(ETHTOOL_LINK_MODE_1000baseT_Half_BIT, - phydev->advertising); - linkmode_clear_bit(ETHTOOL_LINK_MODE_1000baseT_Full_BIT, - phydev->advertising); - } + linkmode_copy(adv_tmp, phydev->advertising); + + ret = phy_speed_down_core(phydev); + if (ret) + return ret; - if (linkmode_equal(phydev->advertising, adv_old)) + linkmode_copy(phydev->adv_old, adv_tmp); + + if (linkmode_equal(phydev->advertising, adv_tmp)) return 0; ret = phy_config_aneg(phydev); @@ -658,30 +641,19 @@ EXPORT_SYMBOL_GPL(phy_speed_down); */ int phy_speed_up(struct phy_device *phydev) { - __ETHTOOL_DECLARE_LINK_MODE_MASK(all_speeds) = { 0, }; - __ETHTOOL_DECLARE_LINK_MODE_MASK(not_speeds); - __ETHTOOL_DECLARE_LINK_MODE_MASK(supported); - __ETHTOOL_DECLARE_LINK_MODE_MASK(adv_old); - __ETHTOOL_DECLARE_LINK_MODE_MASK(speeds); - - linkmode_copy(adv_old, phydev->advertising); + __ETHTOOL_DECLARE_LINK_MODE_MASK(adv_tmp); if (phydev->autoneg != AUTONEG_ENABLE) return 0; - linkmode_set_bit(ETHTOOL_LINK_MODE_10baseT_Half_BIT, all_speeds); - linkmode_set_bit(ETHTOOL_LINK_MODE_10baseT_Full_BIT, all_speeds); - linkmode_set_bit(ETHTOOL_LINK_MODE_100baseT_Half_BIT, all_speeds); - linkmode_set_bit(ETHTOOL_LINK_MODE_100baseT_Full_BIT, all_speeds); - linkmode_set_bit(ETHTOOL_LINK_MODE_1000baseT_Half_BIT, all_speeds); - linkmode_set_bit(ETHTOOL_LINK_MODE_1000baseT_Full_BIT, all_speeds); + if (linkmode_empty(phydev->adv_old)) + return 0; - linkmode_andnot(not_speeds, adv_old, all_speeds); - linkmode_copy(supported, phydev->supported); - linkmode_and(speeds, supported, all_speeds); - linkmode_or(phydev->advertising, not_speeds, speeds); + linkmode_copy(adv_tmp, phydev->advertising); + linkmode_copy(phydev->advertising, phydev->adv_old); + linkmode_zero(phydev->adv_old); - if (linkmode_equal(phydev->advertising, adv_old)) + if (linkmode_equal(phydev->advertising, adv_tmp)) return 0; return phy_config_aneg(phydev); diff --git a/include/linux/phy.h b/include/linux/phy.h index 62fdc7ff2b24..5ac7d21375ac 100644 --- a/include/linux/phy.h +++ b/include/linux/phy.h @@ -403,6 +403,8 @@ struct phy_device { __ETHTOOL_DECLARE_LINK_MODE_MASK(supported); __ETHTOOL_DECLARE_LINK_MODE_MASK(advertising); __ETHTOOL_DECLARE_LINK_MODE_MASK(lp_advertising); + /* used with phy_speed_down */ + __ETHTOOL_DECLARE_LINK_MODE_MASK(adv_old); /* Energy efficient ethernet modes which should be prohibited */ u32 eee_broken_modes; -- cgit v1.2.3 From 0dabbe1bb3a4cf47d0cf52828355293f18acdae9 Mon Sep 17 00:00:00 2001 From: Sudarsana Reddy Kalluru Date: Wed, 14 Aug 2019 01:11:53 -0700 Subject: qed: Add driver API for flashing the config attributes. The patch adds driver interface for reading the config attributes from user provided buffer, and updates these values on nvm config flash partition. This is basically an expansion of our existing ethtool -f implementation. The management FW has exposed an additional method of configuring some of the nvram options, and this makes use of that. This implementation will come into use when newer FW files which contain configuration directives employing this API will be provided to ethtool -f. Signed-off-by: Sudarsana Reddy Kalluru Signed-off-by: Ariel Elior Signed-off-by: David S. Miller --- drivers/net/ethernet/qlogic/qed/qed_main.c | 68 ++++++++++++++++++++++++++++++ include/linux/qed/qed_if.h | 1 + 2 files changed, 69 insertions(+) (limited to 'include/linux') diff --git a/drivers/net/ethernet/qlogic/qed/qed_main.c b/drivers/net/ethernet/qlogic/qed/qed_main.c index e5ac8bd4fd14..0a7645937412 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_main.c +++ b/drivers/net/ethernet/qlogic/qed/qed_main.c @@ -67,6 +67,8 @@ #define QED_ROCE_QPS (8192) #define QED_ROCE_DPIS (8) #define QED_RDMA_SRQS QED_ROCE_QPS +#define QED_NVM_CFG_SET_FLAGS 0xE +#define QED_NVM_CFG_SET_PF_FLAGS 0x1E static char version[] = "QLogic FastLinQ 4xxxx Core Module qed " DRV_MODULE_VERSION "\n"; @@ -2231,6 +2233,69 @@ static int qed_nvm_flash_image_validate(struct qed_dev *cdev, return 0; } +/* Binary file format - + * /----------------------------------------------------------------------\ + * 0B | 0x5 [command index] | + * 4B | Entity ID | Reserved | Number of config attributes | + * 8B | Config ID | Length | Value | + * | | + * \----------------------------------------------------------------------/ + * There can be several cfg_id-Length-Value sets as specified by 'Number of...'. + * Entity ID - A non zero entity value for which the config need to be updated. + * + * The API parses config attributes from the user provided buffer and flashes + * them to the respective NVM path using Management FW inerface. + */ +static int qed_nvm_flash_cfg_write(struct qed_dev *cdev, const u8 **data) +{ + struct qed_hwfn *hwfn = QED_LEADING_HWFN(cdev); + u8 entity_id, len, buf[32]; + struct qed_ptt *ptt; + u16 cfg_id, count; + int rc = 0, i; + u32 flags; + + ptt = qed_ptt_acquire(hwfn); + if (!ptt) + return -EAGAIN; + + /* NVM CFG ID attribute header */ + *data += 4; + entity_id = **data; + *data += 2; + count = *((u16 *)*data); + *data += 2; + + DP_VERBOSE(cdev, NETIF_MSG_DRV, + "Read config ids: entity id %02x num _attrs = %0d\n", + entity_id, count); + /* NVM CFG ID attributes */ + for (i = 0; i < count; i++) { + cfg_id = *((u16 *)*data); + *data += 2; + len = **data; + (*data)++; + memcpy(buf, *data, len); + *data += len; + + flags = entity_id ? QED_NVM_CFG_SET_PF_FLAGS : + QED_NVM_CFG_SET_FLAGS; + + DP_VERBOSE(cdev, NETIF_MSG_DRV, + "cfg_id = %d len = %d\n", cfg_id, len); + rc = qed_mcp_nvm_set_cfg(hwfn, ptt, cfg_id, entity_id, flags, + buf, len); + if (rc) { + DP_ERR(cdev, "Error %d configuring %d\n", rc, cfg_id); + break; + } + } + + qed_ptt_release(hwfn, ptt); + + return rc; +} + static int qed_nvm_flash(struct qed_dev *cdev, const char *name) { const struct firmware *image; @@ -2272,6 +2337,9 @@ static int qed_nvm_flash(struct qed_dev *cdev, const char *name) rc = qed_nvm_flash_image_access(cdev, &data, &check_resp); break; + case QED_NVM_FLASH_CMD_NVM_CFG_ID: + rc = qed_nvm_flash_cfg_write(cdev, &data); + break; default: DP_ERR(cdev, "Unknown command %08x\n", cmd_type); rc = -EINVAL; diff --git a/include/linux/qed/qed_if.h b/include/linux/qed/qed_if.h index 23021366a4e5..e366399874f3 100644 --- a/include/linux/qed/qed_if.h +++ b/include/linux/qed/qed_if.h @@ -804,6 +804,7 @@ enum qed_nvm_flash_cmd { QED_NVM_FLASH_CMD_FILE_DATA = 0x2, QED_NVM_FLASH_CMD_FILE_START = 0x3, QED_NVM_FLASH_CMD_NVM_CHANGE = 0x4, + QED_NVM_FLASH_CMD_NVM_CFG_ID = 0x5, QED_NVM_FLASH_CMD_NVM_MAX, }; -- cgit v1.2.3 From 4b9cb2a5ceedd7f715d92570b773fad024ca9950 Mon Sep 17 00:00:00 2001 From: Heiner Kallweit Date: Sat, 17 Aug 2019 12:30:39 +0200 Subject: net: phy: remove genphy_config_init Now that all users have been removed we can remove genphy_config_init. Signed-off-by: Heiner Kallweit Signed-off-by: David S. Miller --- drivers/net/phy/phy_device.c | 51 -------------------------------------------- include/linux/phy.h | 1 - 2 files changed, 52 deletions(-) (limited to 'include/linux') diff --git a/drivers/net/phy/phy_device.c b/drivers/net/phy/phy_device.c index 9c546bae9ec9..d5db7604d7c4 100644 --- a/drivers/net/phy/phy_device.c +++ b/drivers/net/phy/phy_device.c @@ -1885,57 +1885,6 @@ int genphy_soft_reset(struct phy_device *phydev) } EXPORT_SYMBOL(genphy_soft_reset); -int genphy_config_init(struct phy_device *phydev) -{ - int val; - __ETHTOOL_DECLARE_LINK_MODE_MASK(features) = { 0, }; - - linkmode_set_bit_array(phy_basic_ports_array, - ARRAY_SIZE(phy_basic_ports_array), - features); - linkmode_set_bit(ETHTOOL_LINK_MODE_Pause_BIT, features); - linkmode_set_bit(ETHTOOL_LINK_MODE_Asym_Pause_BIT, features); - - /* Do we support autonegotiation? */ - val = phy_read(phydev, MII_BMSR); - if (val < 0) - return val; - - if (val & BMSR_ANEGCAPABLE) - linkmode_set_bit(ETHTOOL_LINK_MODE_Autoneg_BIT, features); - - if (val & BMSR_100FULL) - linkmode_set_bit(ETHTOOL_LINK_MODE_100baseT_Full_BIT, features); - if (val & BMSR_100HALF) - linkmode_set_bit(ETHTOOL_LINK_MODE_100baseT_Half_BIT, features); - if (val & BMSR_10FULL) - linkmode_set_bit(ETHTOOL_LINK_MODE_10baseT_Full_BIT, features); - if (val & BMSR_10HALF) - linkmode_set_bit(ETHTOOL_LINK_MODE_10baseT_Half_BIT, features); - - if (val & BMSR_ESTATEN) { - val = phy_read(phydev, MII_ESTATUS); - if (val < 0) - return val; - - if (val & ESTATUS_1000_TFULL) - linkmode_set_bit(ETHTOOL_LINK_MODE_1000baseT_Full_BIT, - features); - if (val & ESTATUS_1000_THALF) - linkmode_set_bit(ETHTOOL_LINK_MODE_1000baseT_Half_BIT, - features); - if (val & ESTATUS_1000_XFULL) - linkmode_set_bit(ETHTOOL_LINK_MODE_1000baseX_Full_BIT, - features); - } - - linkmode_and(phydev->supported, phydev->supported, features); - linkmode_and(phydev->advertising, phydev->advertising, features); - - return 0; -} -EXPORT_SYMBOL(genphy_config_init); - /** * genphy_read_abilities - read PHY abilities from Clause 22 registers * @phydev: target phy_device struct diff --git a/include/linux/phy.h b/include/linux/phy.h index 5ac7d21375ac..d26779f1fb6b 100644 --- a/include/linux/phy.h +++ b/include/linux/phy.h @@ -1069,7 +1069,6 @@ void phy_attached_print(struct phy_device *phydev, const char *fmt, ...) void phy_attached_info(struct phy_device *phydev); /* Clause 22 PHY */ -int genphy_config_init(struct phy_device *phydev); int genphy_read_abilities(struct phy_device *phydev); int genphy_setup_forced(struct phy_device *phydev); int genphy_restart_aneg(struct phy_device *phydev); -- cgit v1.2.3 From 9116e5e2b1fff71dce501d971e86a3695acc3dba Mon Sep 17 00:00:00 2001 From: Magnus Karlsson Date: Wed, 14 Aug 2019 09:27:16 +0200 Subject: xsk: replace ndo_xsk_async_xmit with ndo_xsk_wakeup This commit replaces ndo_xsk_async_xmit with ndo_xsk_wakeup. This new ndo provides the same functionality as before but with the addition of a new flags field that is used to specifiy if Rx, Tx or both should be woken up. The previous ndo only woke up Tx, as implied by the name. The i40e and ixgbe drivers (which are all the supported ones) are updated with this new interface. This new ndo will be used by the new need_wakeup functionality of XDP sockets that need to be able to wake up both Rx and Tx driver processing. Signed-off-by: Magnus Karlsson Acked-by: Jonathan Lemon Signed-off-by: Daniel Borkmann --- drivers/net/ethernet/intel/i40e/i40e_main.c | 5 +++-- drivers/net/ethernet/intel/i40e/i40e_xsk.c | 7 ++++--- drivers/net/ethernet/intel/i40e/i40e_xsk.h | 2 +- drivers/net/ethernet/intel/ixgbe/ixgbe_main.c | 5 +++-- drivers/net/ethernet/intel/ixgbe/ixgbe_txrx_common.h | 2 +- drivers/net/ethernet/intel/ixgbe/ixgbe_xsk.c | 4 ++-- drivers/net/ethernet/mellanox/mlx5/core/en/xsk/tx.c | 2 +- drivers/net/ethernet/mellanox/mlx5/core/en/xsk/tx.h | 2 +- drivers/net/ethernet/mellanox/mlx5/core/en_main.c | 2 +- include/linux/netdevice.h | 14 ++++++++++++-- net/xdp/xdp_umem.c | 3 +-- net/xdp/xsk.c | 3 ++- 12 files changed, 32 insertions(+), 19 deletions(-) (limited to 'include/linux') diff --git a/drivers/net/ethernet/intel/i40e/i40e_main.c b/drivers/net/ethernet/intel/i40e/i40e_main.c index 6d456e579314..a75c66c8679d 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_main.c +++ b/drivers/net/ethernet/intel/i40e/i40e_main.c @@ -12570,7 +12570,8 @@ static int i40e_xdp_setup(struct i40e_vsi *vsi, if (need_reset && prog) for (i = 0; i < vsi->num_queue_pairs; i++) if (vsi->xdp_rings[i]->xsk_umem) - (void)i40e_xsk_async_xmit(vsi->netdev, i); + (void)i40e_xsk_wakeup(vsi->netdev, i, + XDP_WAKEUP_RX); return 0; } @@ -12892,7 +12893,7 @@ static const struct net_device_ops i40e_netdev_ops = { .ndo_bridge_setlink = i40e_ndo_bridge_setlink, .ndo_bpf = i40e_xdp, .ndo_xdp_xmit = i40e_xdp_xmit, - .ndo_xsk_async_xmit = i40e_xsk_async_xmit, + .ndo_xsk_wakeup = i40e_xsk_wakeup, .ndo_dfwd_add_station = i40e_fwd_add, .ndo_dfwd_del_station = i40e_fwd_del, }; diff --git a/drivers/net/ethernet/intel/i40e/i40e_xsk.c b/drivers/net/ethernet/intel/i40e/i40e_xsk.c index 32bad014d76c..d0ff5d8b297b 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_xsk.c +++ b/drivers/net/ethernet/intel/i40e/i40e_xsk.c @@ -116,7 +116,7 @@ static int i40e_xsk_umem_enable(struct i40e_vsi *vsi, struct xdp_umem *umem, return err; /* Kick start the NAPI context so that receiving will start */ - err = i40e_xsk_async_xmit(vsi->netdev, qid); + err = i40e_xsk_wakeup(vsi->netdev, qid, XDP_WAKEUP_RX); if (err) return err; } @@ -765,13 +765,14 @@ out_xmit: } /** - * i40e_xsk_async_xmit - Implements the ndo_xsk_async_xmit + * i40e_xsk_wakeup - Implements the ndo_xsk_wakeup * @dev: the netdevice * @queue_id: queue id to wake up + * @flags: ignored in our case since we have Rx and Tx in the same NAPI. * * Returns <0 for errors, 0 otherwise. **/ -int i40e_xsk_async_xmit(struct net_device *dev, u32 queue_id) +int i40e_xsk_wakeup(struct net_device *dev, u32 queue_id, u32 flags) { struct i40e_netdev_priv *np = netdev_priv(dev); struct i40e_vsi *vsi = np->vsi; diff --git a/drivers/net/ethernet/intel/i40e/i40e_xsk.h b/drivers/net/ethernet/intel/i40e/i40e_xsk.h index 8cc0a2e7d9a2..9ed59c14eb55 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_xsk.h +++ b/drivers/net/ethernet/intel/i40e/i40e_xsk.h @@ -18,6 +18,6 @@ int i40e_clean_rx_irq_zc(struct i40e_ring *rx_ring, int budget); bool i40e_clean_xdp_tx_irq(struct i40e_vsi *vsi, struct i40e_ring *tx_ring, int napi_budget); -int i40e_xsk_async_xmit(struct net_device *dev, u32 queue_id); +int i40e_xsk_wakeup(struct net_device *dev, u32 queue_id, u32 flags); #endif /* _I40E_XSK_H_ */ diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c index dc7b128c780e..05729b448612 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c @@ -10263,7 +10263,8 @@ static int ixgbe_xdp_setup(struct net_device *dev, struct bpf_prog *prog) if (need_reset && prog) for (i = 0; i < adapter->num_rx_queues; i++) if (adapter->xdp_ring[i]->xsk_umem) - (void)ixgbe_xsk_async_xmit(adapter->netdev, i); + (void)ixgbe_xsk_wakeup(adapter->netdev, i, + XDP_WAKEUP_RX); return 0; } @@ -10382,7 +10383,7 @@ static const struct net_device_ops ixgbe_netdev_ops = { .ndo_features_check = ixgbe_features_check, .ndo_bpf = ixgbe_xdp, .ndo_xdp_xmit = ixgbe_xdp_xmit, - .ndo_xsk_async_xmit = ixgbe_xsk_async_xmit, + .ndo_xsk_wakeup = ixgbe_xsk_wakeup, }; static void ixgbe_disable_txr_hw(struct ixgbe_adapter *adapter, diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_txrx_common.h b/drivers/net/ethernet/intel/ixgbe/ixgbe_txrx_common.h index d93a690aff74..6d01700b46bc 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_txrx_common.h +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_txrx_common.h @@ -42,7 +42,7 @@ int ixgbe_clean_rx_irq_zc(struct ixgbe_q_vector *q_vector, void ixgbe_xsk_clean_rx_ring(struct ixgbe_ring *rx_ring); bool ixgbe_clean_xdp_tx_irq(struct ixgbe_q_vector *q_vector, struct ixgbe_ring *tx_ring, int napi_budget); -int ixgbe_xsk_async_xmit(struct net_device *dev, u32 queue_id); +int ixgbe_xsk_wakeup(struct net_device *dev, u32 queue_id, u32 flags); void ixgbe_xsk_clean_tx_ring(struct ixgbe_ring *tx_ring); #endif /* #define _IXGBE_TXRX_COMMON_H_ */ diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_xsk.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_xsk.c index 6b609553329f..e598af9faced 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_xsk.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_xsk.c @@ -100,7 +100,7 @@ static int ixgbe_xsk_umem_enable(struct ixgbe_adapter *adapter, ixgbe_txrx_ring_enable(adapter, qid); /* Kick start the NAPI context so that receiving will start */ - err = ixgbe_xsk_async_xmit(adapter->netdev, qid); + err = ixgbe_xsk_wakeup(adapter->netdev, qid, XDP_WAKEUP_RX); if (err) return err; } @@ -692,7 +692,7 @@ bool ixgbe_clean_xdp_tx_irq(struct ixgbe_q_vector *q_vector, return budget > 0 && xmit_done; } -int ixgbe_xsk_async_xmit(struct net_device *dev, u32 qid) +int ixgbe_xsk_wakeup(struct net_device *dev, u32 qid, u32 flags) { struct ixgbe_adapter *adapter = netdev_priv(dev); struct ixgbe_ring *ring; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/tx.c b/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/tx.c index 35e188cf4ea4..9704634a87aa 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/tx.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/tx.c @@ -7,7 +7,7 @@ #include "en/params.h" #include -int mlx5e_xsk_async_xmit(struct net_device *dev, u32 qid) +int mlx5e_xsk_wakeup(struct net_device *dev, u32 qid, u32 flags) { struct mlx5e_priv *priv = netdev_priv(dev); struct mlx5e_params *params = &priv->channels.params; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/tx.h b/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/tx.h index 7add18bf78d8..9c505158b975 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/tx.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/tx.h @@ -8,7 +8,7 @@ /* TX data path */ -int mlx5e_xsk_async_xmit(struct net_device *dev, u32 qid); +int mlx5e_xsk_wakeup(struct net_device *dev, u32 qid, u32 flags); bool mlx5e_xsk_tx(struct mlx5e_xdpsq *sq, unsigned int budget); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c index 9a2fcef6e7f0..9df7e5c3c4cc 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c @@ -4540,7 +4540,7 @@ const struct net_device_ops mlx5e_netdev_ops = { .ndo_tx_timeout = mlx5e_tx_timeout, .ndo_bpf = mlx5e_xdp, .ndo_xdp_xmit = mlx5e_xdp_xmit, - .ndo_xsk_async_xmit = mlx5e_xsk_async_xmit, + .ndo_xsk_wakeup = mlx5e_xsk_wakeup, #ifdef CONFIG_MLX5_EN_ARFS .ndo_rx_flow_steer = mlx5e_rx_flow_steer, #endif diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 55ac223553f8..0ef0570386a2 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -901,6 +901,10 @@ struct netdev_bpf { }; }; +/* Flags for ndo_xsk_wakeup. */ +#define XDP_WAKEUP_RX (1 << 0) +#define XDP_WAKEUP_TX (1 << 1) + #ifdef CONFIG_XFRM_OFFLOAD struct xfrmdev_ops { int (*xdo_dev_state_add) (struct xfrm_state *x); @@ -1227,6 +1231,12 @@ struct tlsdev_ops; * that got dropped are freed/returned via xdp_return_frame(). * Returns negative number, means general error invoking ndo, meaning * no frames were xmit'ed and core-caller will free all frames. + * int (*ndo_xsk_wakeup)(struct net_device *dev, u32 queue_id, u32 flags); + * This function is used to wake up the softirq, ksoftirqd or kthread + * responsible for sending and/or receiving packets on a specific + * queue id bound to an AF_XDP socket. The flags field specifies if + * only RX, only Tx, or both should be woken up using the flags + * XDP_WAKEUP_RX and XDP_WAKEUP_TX. * struct devlink_port *(*ndo_get_devlink_port)(struct net_device *dev); * Get devlink port instance associated with a given netdev. * Called with a reference on the netdevice and devlink locks only, @@ -1426,8 +1436,8 @@ struct net_device_ops { int (*ndo_xdp_xmit)(struct net_device *dev, int n, struct xdp_frame **xdp, u32 flags); - int (*ndo_xsk_async_xmit)(struct net_device *dev, - u32 queue_id); + int (*ndo_xsk_wakeup)(struct net_device *dev, + u32 queue_id, u32 flags); struct devlink_port * (*ndo_get_devlink_port)(struct net_device *dev); }; diff --git a/net/xdp/xdp_umem.c b/net/xdp/xdp_umem.c index a0607969f8c0..6e2d4da4cdcd 100644 --- a/net/xdp/xdp_umem.c +++ b/net/xdp/xdp_umem.c @@ -112,8 +112,7 @@ int xdp_umem_assign_dev(struct xdp_umem *umem, struct net_device *dev, /* For copy-mode, we are done. */ return 0; - if (!dev->netdev_ops->ndo_bpf || - !dev->netdev_ops->ndo_xsk_async_xmit) { + if (!dev->netdev_ops->ndo_bpf || !dev->netdev_ops->ndo_xsk_wakeup) { err = -EOPNOTSUPP; goto err_unreg_umem; } diff --git a/net/xdp/xsk.c b/net/xdp/xsk.c index 59b57d708697..1fe40a936456 100644 --- a/net/xdp/xsk.c +++ b/net/xdp/xsk.c @@ -212,7 +212,8 @@ static int xsk_zc_xmit(struct sock *sk) struct xdp_sock *xs = xdp_sk(sk); struct net_device *dev = xs->dev; - return dev->netdev_ops->ndo_xsk_async_xmit(dev, xs->queue_id); + return dev->netdev_ops->ndo_xsk_wakeup(dev, xs->queue_id, + XDP_WAKEUP_TX); } static void xsk_destruct_skb(struct sk_buff *skb) -- cgit v1.2.3 From b0e4701ce15d0381cdea0643c7f0a35dc529cec2 Mon Sep 17 00:00:00 2001 From: Stanislav Fomichev Date: Wed, 14 Aug 2019 10:37:48 -0700 Subject: bpf: export bpf_map_inc_not_zero Rename existing bpf_map_inc_not_zero to __bpf_map_inc_not_zero to indicate that it's caller's responsibility to do proper locking. Create and export bpf_map_inc_not_zero wrapper that properly locks map_idr_lock. Will be used in the next commit to hold a map while cloning a socket. Cc: Martin KaFai Lau Cc: Yonghong Song Acked-by: Martin KaFai Lau Acked-by: Yonghong Song Signed-off-by: Stanislav Fomichev Signed-off-by: Daniel Borkmann --- include/linux/bpf.h | 2 ++ kernel/bpf/syscall.c | 16 +++++++++++++--- 2 files changed, 15 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index f9a506147c8a..15ae49862b82 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -647,6 +647,8 @@ void bpf_map_free_id(struct bpf_map *map, bool do_idr_lock); struct bpf_map *bpf_map_get_with_uref(u32 ufd); struct bpf_map *__bpf_map_get(struct fd f); struct bpf_map * __must_check bpf_map_inc(struct bpf_map *map, bool uref); +struct bpf_map * __must_check bpf_map_inc_not_zero(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_charge_memlock(struct bpf_map *map, u32 pages); diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c index 5d141f16f6fa..cf8052b016e7 100644 --- a/kernel/bpf/syscall.c +++ b/kernel/bpf/syscall.c @@ -683,8 +683,8 @@ struct bpf_map *bpf_map_get_with_uref(u32 ufd) } /* map_idr_lock should have been held */ -static struct bpf_map *bpf_map_inc_not_zero(struct bpf_map *map, - bool uref) +static struct bpf_map *__bpf_map_inc_not_zero(struct bpf_map *map, + bool uref) { int refold; @@ -704,6 +704,16 @@ static struct bpf_map *bpf_map_inc_not_zero(struct bpf_map *map, return map; } +struct bpf_map *bpf_map_inc_not_zero(struct bpf_map *map, bool uref) +{ + spin_lock_bh(&map_idr_lock); + map = __bpf_map_inc_not_zero(map, uref); + spin_unlock_bh(&map_idr_lock); + + return map; +} +EXPORT_SYMBOL_GPL(bpf_map_inc_not_zero); + int __weak bpf_stackmap_copy(struct bpf_map *map, void *key, void *value) { return -ENOTSUPP; @@ -2177,7 +2187,7 @@ static int bpf_map_get_fd_by_id(const union bpf_attr *attr) spin_lock_bh(&map_idr_lock); map = idr_find(&map_idr, id); if (map) - map = bpf_map_inc_not_zero(map, true); + map = __bpf_map_inc_not_zero(map, true); else map = ERR_PTR(-ENOENT); spin_unlock_bh(&map_idr_lock); -- cgit v1.2.3 From 30cc0ed73e3390af7c5573b159826e8162f09fe7 Mon Sep 17 00:00:00 2001 From: Geert Uytterhoeven Date: Wed, 14 Aug 2019 11:22:21 +0200 Subject: can: rcar_can: Remove unused platform data support All R-Car platforms use DT for describing CAN controllers. R-Car CAN platform data support was never used in any upstream kernel. Move the Clock Select Register settings enum into the driver, and remove platform data support and the corresponding header file. Signed-off-by: Geert Uytterhoeven Reviewed-by: Wolfram Sang Signed-off-by: Marc Kleine-Budde --- drivers/net/can/rcar/rcar_can.c | 22 +++++++++------------- include/linux/can/platform/rcar_can.h | 18 ------------------ 2 files changed, 9 insertions(+), 31 deletions(-) delete mode 100644 include/linux/can/platform/rcar_can.h (limited to 'include/linux') diff --git a/drivers/net/can/rcar/rcar_can.c b/drivers/net/can/rcar/rcar_can.c index cf218949a8fb..bf5adea9c0a3 100644 --- a/drivers/net/can/rcar/rcar_can.c +++ b/drivers/net/can/rcar/rcar_can.c @@ -15,11 +15,17 @@ #include #include #include -#include #include #define RCAR_CAN_DRV_NAME "rcar_can" +/* Clock Select Register settings */ +enum CLKR { + CLKR_CLKP1 = 0, /* Peripheral clock (clkp1) */ + CLKR_CLKP2 = 1, /* Peripheral clock (clkp2) */ + CLKR_CLKEXT = 3, /* Externally input clock */ +}; + #define RCAR_SUPPORTED_CLOCKS (BIT(CLKR_CLKP1) | BIT(CLKR_CLKP2) | \ BIT(CLKR_CLKEXT)) @@ -736,7 +742,6 @@ static const char * const clock_names[] = { static int rcar_can_probe(struct platform_device *pdev) { - struct rcar_can_platform_data *pdata; struct rcar_can_priv *priv; struct net_device *ndev; struct resource *mem; @@ -745,17 +750,8 @@ static int rcar_can_probe(struct platform_device *pdev) int err = -ENODEV; int irq; - if (pdev->dev.of_node) { - of_property_read_u32(pdev->dev.of_node, - "renesas,can-clock-select", &clock_select); - } else { - pdata = dev_get_platdata(&pdev->dev); - if (!pdata) { - dev_err(&pdev->dev, "No platform data provided!\n"); - goto fail; - } - clock_select = pdata->clock_select; - } + of_property_read_u32(pdev->dev.of_node, "renesas,can-clock-select", + &clock_select); irq = platform_get_irq(pdev, 0); if (irq < 0) { diff --git a/include/linux/can/platform/rcar_can.h b/include/linux/can/platform/rcar_can.h deleted file mode 100644 index a43dcd0cf79e..000000000000 --- a/include/linux/can/platform/rcar_can.h +++ /dev/null @@ -1,18 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -#ifndef _CAN_PLATFORM_RCAR_CAN_H_ -#define _CAN_PLATFORM_RCAR_CAN_H_ - -#include - -/* Clock Select Register settings */ -enum CLKR { - CLKR_CLKP1 = 0, /* Peripheral clock (clkp1) */ - CLKR_CLKP2 = 1, /* Peripheral clock (clkp2) */ - CLKR_CLKEXT = 3 /* Externally input clock */ -}; - -struct rcar_can_platform_data { - enum CLKR clock_select; /* Clock source select */ -}; - -#endif /* !_CAN_PLATFORM_RCAR_CAN_H_ */ -- cgit v1.2.3 From 69ecfdaa534943efd95ee12b53fbb0f344e42e7e Mon Sep 17 00:00:00 2001 From: Masahiro Yamada Date: Tue, 20 Aug 2019 01:10:35 +0900 Subject: bpf: add include guard to tnum.h Add a header include guard just in case. Signed-off-by: Masahiro Yamada Signed-off-by: Daniel Borkmann --- include/linux/tnum.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include/linux') diff --git a/include/linux/tnum.h b/include/linux/tnum.h index c7dc2b5902c0..c17af77f3fae 100644 --- a/include/linux/tnum.h +++ b/include/linux/tnum.h @@ -5,6 +5,10 @@ * propagate the unknown bits such that the tnum result represents all the * possible results for possible values of the operands. */ + +#ifndef _LINUX_TNUM_H +#define _LINUX_TNUM_H + #include struct tnum { @@ -81,3 +85,5 @@ bool tnum_in(struct tnum a, struct tnum b); int tnum_strn(char *str, size_t size, struct tnum a); /* Format a tnum as tristate binary expansion */ int tnum_sbin(char *str, size_t size, struct tnum a); + +#endif /* _LINUX_TNUM_H */ -- cgit v1.2.3 From 1b9ed84ecf268904d89edf2908426a8eb3b5a4ba Mon Sep 17 00:00:00 2001 From: Quentin Monnet Date: Tue, 20 Aug 2019 10:31:50 +0100 Subject: bpf: add new BPF_BTF_GET_NEXT_ID syscall command Add a new command for the bpf() system call: BPF_BTF_GET_NEXT_ID is used to cycle through all BTF objects loaded on the system. The motivation is to be able to inspect (list) all BTF objects presents on the system. Signed-off-by: Quentin Monnet Reviewed-by: Jakub Kicinski Signed-off-by: Alexei Starovoitov --- include/linux/bpf.h | 3 +++ include/uapi/linux/bpf.h | 1 + kernel/bpf/btf.c | 4 ++-- kernel/bpf/syscall.c | 4 ++++ 4 files changed, 10 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 15ae49862b82..5b9d22338606 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -24,6 +24,9 @@ struct seq_file; struct btf; struct btf_type; +extern struct idr btf_idr; +extern spinlock_t btf_idr_lock; + /* map is generic key/value storage optionally accesible by eBPF programs */ struct bpf_map_ops { /* funcs callable from userspace (via syscall) */ diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index 0ef594ac3899..8aa6126f0b6e 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -106,6 +106,7 @@ enum bpf_cmd { BPF_TASK_FD_QUERY, BPF_MAP_LOOKUP_AND_DELETE_ELEM, BPF_MAP_FREEZE, + BPF_BTF_GET_NEXT_ID, }; enum bpf_map_type { diff --git a/kernel/bpf/btf.c b/kernel/bpf/btf.c index 6b403dc18486..adb3adcebe3c 100644 --- a/kernel/bpf/btf.c +++ b/kernel/bpf/btf.c @@ -195,8 +195,8 @@ i < btf_type_vlen(struct_type); \ i++, member++) -static DEFINE_IDR(btf_idr); -static DEFINE_SPINLOCK(btf_idr_lock); +DEFINE_IDR(btf_idr); +DEFINE_SPINLOCK(btf_idr_lock); struct btf { void *data; diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c index cf8052b016e7..c0f62fd67c6b 100644 --- a/kernel/bpf/syscall.c +++ b/kernel/bpf/syscall.c @@ -2884,6 +2884,10 @@ SYSCALL_DEFINE3(bpf, int, cmd, union bpf_attr __user *, uattr, unsigned int, siz err = bpf_obj_get_next_id(&attr, uattr, &map_idr, &map_idr_lock); break; + case BPF_BTF_GET_NEXT_ID: + err = bpf_obj_get_next_id(&attr, uattr, + &btf_idr, &btf_idr_lock); + break; case BPF_PROG_GET_FD_BY_ID: err = bpf_prog_get_fd_by_id(&attr); break; -- cgit v1.2.3 From 30b10e89f2ae2c7b7b32548e04f57ab7eb030dfb Mon Sep 17 00:00:00 2001 From: Moshe Shemesh Date: Thu, 15 Aug 2019 19:46:11 +0000 Subject: net/mlx5: Add support for VNIC_ENV internal rq counter Add mlx5 interface support for reading internal rq out of buffer counter as part of QUERY_VNIC_ENV command. The command is used by the driver to query vnic diagnostic statistics from FW. Signed-off-by: Moshe Shemesh Signed-off-by: Saeed Mahameed --- include/linux/mlx5/mlx5_ifc.h | 10 ++++++++-- 1 file changed, 8 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h index ab6ae723aae6..c788f895b350 100644 --- a/include/linux/mlx5/mlx5_ifc.h +++ b/include/linux/mlx5/mlx5_ifc.h @@ -1116,7 +1116,9 @@ struct mlx5_ifc_cmd_hca_cap_bits { u8 cache_line_128byte[0x1]; u8 reserved_at_165[0x4]; u8 rts2rts_qp_counters_set_id[0x1]; - u8 reserved_at_16a[0x5]; + u8 reserved_at_16a[0x2]; + u8 vnic_env_int_rq_oob[0x1]; + u8 reserved_at_16d[0x2]; u8 qcam_reg[0x1]; u8 gid_table_size[0x10]; @@ -2772,7 +2774,11 @@ struct mlx5_ifc_vnic_diagnostic_statistics_bits { u8 transmit_discard_vport_down[0x40]; - u8 reserved_at_140[0xec0]; + u8 reserved_at_140[0xa0]; + + u8 internal_rq_out_of_buffer[0x20]; + + u8 reserved_at_200[0xe00]; }; struct mlx5_ifc_traffic_counter_bits { -- cgit v1.2.3 From caa1854735449d7afac6781679621fb9142fe810 Mon Sep 17 00:00:00 2001 From: Aya Levin Date: Thu, 15 Aug 2019 19:46:14 +0000 Subject: net/mlx5: Expose IP-in-IP capability bit Expose Fw indication that it supports Stateless Offloads for IP over IP tunneled packets. The following offloads are supported for the inner packets: RSS, RX & TX Checksum Offloads, LSO and Flow Steering. Signed-off-by: Aya Levin Reviewed-by: Tariq Toukan Signed-off-by: Saeed Mahameed --- include/linux/mlx5/mlx5_ifc.h | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h index c788f895b350..2837fe4d8901 100644 --- a/include/linux/mlx5/mlx5_ifc.h +++ b/include/linux/mlx5/mlx5_ifc.h @@ -808,7 +808,9 @@ struct mlx5_ifc_per_protocol_networking_offload_caps_bits { u8 swp_csum[0x1]; u8 swp_lso[0x1]; u8 cqe_checksum_full[0x1]; - u8 reserved_at_24[0xc]; + u8 reserved_at_24[0x5]; + u8 tunnel_stateless_ip_over_ip[0x1]; + u8 reserved_at_2a[0x6]; u8 max_vxlan_udp_ports[0x8]; u8 reserved_at_38[0x6]; u8 max_geneve_opt_len[0x1]; -- cgit v1.2.3 From 1eba383f4e36637ba859cb82b40e198c415db802 Mon Sep 17 00:00:00 2001 From: Maxim Mikityanskiy Date: Thu, 15 Aug 2019 19:46:16 +0000 Subject: net/mlx5: Add lag_tx_port_affinity capability bit Add the lag_tx_port_affinity HCA capability bit that indicates that setting port affinity of TISes is supported. Signed-off-by: Maxim Mikityanskiy Reviewed-by: Tariq Toukan Signed-off-by: Saeed Mahameed --- include/linux/mlx5/mlx5_ifc.h | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h index 2837fe4d8901..1e55cf73e88c 100644 --- a/include/linux/mlx5/mlx5_ifc.h +++ b/include/linux/mlx5/mlx5_ifc.h @@ -1249,7 +1249,9 @@ struct mlx5_ifc_cmd_hca_cap_bits { u8 reserved_at_263[0x8]; u8 log_bf_reg_size[0x5]; - u8 reserved_at_270[0xb]; + u8 reserved_at_270[0x8]; + u8 lag_tx_port_affinity[0x1]; + u8 reserved_at_279[0x2]; u8 lag_master[0x1]; u8 num_lag_ports[0x4]; -- cgit v1.2.3 From e6806e9a63a759e445383915bb9d2ec85a90aebf Mon Sep 17 00:00:00 2001 From: Mark Zhang Date: Mon, 19 Aug 2019 14:36:25 +0300 Subject: net/mlx5: Create bypass and loopback flow steering namespaces for RDMA RX Use different namespaces for bypass and switchdev loopback because they have different priorities and default table miss action requirement: 1. bypass: with multiple priorities support, and MLX5_FLOW_TABLE_MISS_ACTION_DEF as the default table miss action; 2. switchdev loopback: with single priority support, and MLX5_FLOW_TABLE_MISS_ACTION_SWITCH_DOMAIN as the default table miss action. Signed-off-by: Mark Zhang Reviewed-by: Mark Bloch Signed-off-by: Leon Romanovsky --- drivers/net/ethernet/mellanox/mlx5/core/fs_core.c | 49 ++++++++++++++++++----- drivers/net/ethernet/mellanox/mlx5/core/rdma.c | 2 +- include/linux/mlx5/fs.h | 1 + 3 files changed, 41 insertions(+), 11 deletions(-) (limited to 'include/linux') diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c index fb3cfdfbafbe..7bdec442f0ac 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c @@ -182,6 +182,26 @@ static struct init_tree_node egress_root_fs = { } }; +#define RDMA_RX_BYPASS_PRIO 0 +#define RDMA_RX_KERNEL_PRIO 1 +static struct init_tree_node rdma_rx_root_fs = { + .type = FS_TYPE_NAMESPACE, + .ar_size = 2, + .children = (struct init_tree_node[]) { + [RDMA_RX_BYPASS_PRIO] = + ADD_PRIO(0, MLX5_BY_PASS_NUM_REGULAR_PRIOS, 0, + FS_CHAINING_CAPS, + ADD_NS(MLX5_FLOW_TABLE_MISS_ACTION_DEF, + ADD_MULTIPLE_PRIO(MLX5_BY_PASS_NUM_REGULAR_PRIOS, + BY_PASS_PRIO_NUM_LEVELS))), + [RDMA_RX_KERNEL_PRIO] = + ADD_PRIO(0, MLX5_BY_PASS_NUM_REGULAR_PRIOS + 1, 0, + FS_CHAINING_CAPS, + ADD_NS(MLX5_FLOW_TABLE_MISS_ACTION_SWITCH_DOMAIN, + ADD_MULTIPLE_PRIO(1, 1))), + } +}; + enum fs_i_lock_class { FS_LOCK_GRANDPARENT, FS_LOCK_PARENT, @@ -2067,16 +2087,18 @@ struct mlx5_flow_namespace *mlx5_get_flow_namespace(struct mlx5_core_dev *dev, if (steering->sniffer_tx_root_ns) return &steering->sniffer_tx_root_ns->ns; return NULL; - case MLX5_FLOW_NAMESPACE_RDMA_RX: - if (steering->rdma_rx_root_ns) - return &steering->rdma_rx_root_ns->ns; - return NULL; default: break; } if (type == MLX5_FLOW_NAMESPACE_EGRESS) { root_ns = steering->egress_root_ns; + } else if (type == MLX5_FLOW_NAMESPACE_RDMA_RX) { + root_ns = steering->rdma_rx_root_ns; + prio = RDMA_RX_BYPASS_PRIO; + } else if (type == MLX5_FLOW_NAMESPACE_RDMA_RX_KERNEL) { + root_ns = steering->rdma_rx_root_ns; + prio = RDMA_RX_KERNEL_PRIO; } else { /* Must be NIC RX */ root_ns = steering->root_ns; prio = type; @@ -2507,18 +2529,25 @@ static int init_sniffer_rx_root_ns(struct mlx5_flow_steering *steering) static int init_rdma_rx_root_ns(struct mlx5_flow_steering *steering) { - struct fs_prio *prio; + int err; steering->rdma_rx_root_ns = create_root_ns(steering, FS_FT_RDMA_RX); if (!steering->rdma_rx_root_ns) return -ENOMEM; - steering->rdma_rx_root_ns->ns.def_miss_action = - MLX5_FLOW_TABLE_MISS_ACTION_SWITCH_DOMAIN; + err = init_root_tree(steering, &rdma_rx_root_fs, + &steering->rdma_rx_root_ns->ns.node); + if (err) + goto out_err; - /* Create single prio */ - prio = fs_create_prio(&steering->rdma_rx_root_ns->ns, 0, 1); - return PTR_ERR_OR_ZERO(prio); + set_prio_attrs(steering->rdma_rx_root_ns); + + return 0; + +out_err: + cleanup_root_ns(steering->rdma_rx_root_ns); + steering->rdma_rx_root_ns = NULL; + return err; } static int init_fdb_root_ns(struct mlx5_flow_steering *steering) { diff --git a/drivers/net/ethernet/mellanox/mlx5/core/rdma.c b/drivers/net/ethernet/mellanox/mlx5/core/rdma.c index 17ce9dd56b13..18af6981e0be 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/rdma.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/rdma.c @@ -51,7 +51,7 @@ static int mlx5_rdma_enable_roce_steering(struct mlx5_core_dev *dev) return -ENOMEM; } - ns = mlx5_get_flow_namespace(dev, MLX5_FLOW_NAMESPACE_RDMA_RX); + ns = mlx5_get_flow_namespace(dev, MLX5_FLOW_NAMESPACE_RDMA_RX_KERNEL); if (!ns) { mlx5_core_err(dev, "Failed to get RDMA RX namespace"); err = -EOPNOTSUPP; diff --git a/include/linux/mlx5/fs.h b/include/linux/mlx5/fs.h index 04a569568eac..5235b09a8ef3 100644 --- a/include/linux/mlx5/fs.h +++ b/include/linux/mlx5/fs.h @@ -75,6 +75,7 @@ enum mlx5_flow_namespace_type { MLX5_FLOW_NAMESPACE_SNIFFER_TX, MLX5_FLOW_NAMESPACE_EGRESS, MLX5_FLOW_NAMESPACE_RDMA_RX, + MLX5_FLOW_NAMESPACE_RDMA_RX_KERNEL, }; enum { -- cgit v1.2.3 From e5d2f910cfeca852f6e2dc19dfa8dab264ce0cde Mon Sep 17 00:00:00 2001 From: Dexuan Cui Date: Thu, 22 Aug 2019 05:05:37 +0000 Subject: PCI: hv: Add a paravirtual backchannel in software Windows SR-IOV provides a backchannel mechanism in software for communication between a VF driver and a PF driver. These "configuration blocks" are similar in concept to PCI configuration space, but instead of doing reads and writes in 32-bit chunks through a very slow path, packets of up to 128 bytes can be sent or received asynchronously. Nearly every SR-IOV device contains just such a communications channel in hardware, so using this one in software is usually optional. Using the software channel, however, allows driver implementers to leverage software tools that fuzz the communications channel looking for vulnerabilities. The usage model for these packets puts the responsibility for reading or writing on the VF driver. The VF driver sends a read or a write packet, indicating which "block" is being referred to by number. If the PF driver wishes to initiate communication, it can "invalidate" one or more of the first 64 blocks. This invalidation is delivered via a callback supplied by the VF driver by this driver. No protocol is implied, except that supplied by the PF and VF drivers. Signed-off-by: Jake Oshins Signed-off-by: Dexuan Cui Cc: Haiyang Zhang Cc: K. Y. Srinivasan Cc: Stephen Hemminger Signed-off-by: Saeed Mahameed Signed-off-by: Haiyang Zhang Signed-off-by: David S. Miller --- drivers/pci/controller/pci-hyperv.c | 302 ++++++++++++++++++++++++++++++++++++ include/linux/hyperv.h | 15 ++ 2 files changed, 317 insertions(+) (limited to 'include/linux') diff --git a/drivers/pci/controller/pci-hyperv.c b/drivers/pci/controller/pci-hyperv.c index 40b625458afa..57adeca7bda9 100644 --- a/drivers/pci/controller/pci-hyperv.c +++ b/drivers/pci/controller/pci-hyperv.c @@ -365,6 +365,39 @@ struct pci_delete_interrupt { struct tran_int_desc int_desc; } __packed; +/* + * Note: the VM must pass a valid block id, wslot and bytes_requested. + */ +struct pci_read_block { + struct pci_message message_type; + u32 block_id; + union win_slot_encoding wslot; + u32 bytes_requested; +} __packed; + +struct pci_read_block_response { + struct vmpacket_descriptor hdr; + u32 status; + u8 bytes[HV_CONFIG_BLOCK_SIZE_MAX]; +} __packed; + +/* + * Note: the VM must pass a valid block id, wslot and byte_count. + */ +struct pci_write_block { + struct pci_message message_type; + u32 block_id; + union win_slot_encoding wslot; + u32 byte_count; + u8 bytes[HV_CONFIG_BLOCK_SIZE_MAX]; +} __packed; + +struct pci_dev_inval_block { + struct pci_incoming_message incoming; + union win_slot_encoding wslot; + u64 block_mask; +} __packed; + struct pci_dev_incoming { struct pci_incoming_message incoming; union win_slot_encoding wslot; @@ -499,6 +532,9 @@ struct hv_pci_dev { struct hv_pcibus_device *hbus; struct work_struct wrk; + void (*block_invalidate)(void *context, u64 block_mask); + void *invalidate_context; + /* * What would be observed if one wrote 0xFFFFFFFF to a BAR and then * read it back, for each of the BAR offsets within config space. @@ -817,6 +853,256 @@ static struct pci_ops hv_pcifront_ops = { .write = hv_pcifront_write_config, }; +/* + * Paravirtual backchannel + * + * Hyper-V SR-IOV provides a backchannel mechanism in software for + * communication between a VF driver and a PF driver. These + * "configuration blocks" are similar in concept to PCI configuration space, + * but instead of doing reads and writes in 32-bit chunks through a very slow + * path, packets of up to 128 bytes can be sent or received asynchronously. + * + * Nearly every SR-IOV device contains just such a communications channel in + * hardware, so using this one in software is usually optional. Using the + * software channel, however, allows driver implementers to leverage software + * tools that fuzz the communications channel looking for vulnerabilities. + * + * The usage model for these packets puts the responsibility for reading or + * writing on the VF driver. The VF driver sends a read or a write packet, + * indicating which "block" is being referred to by number. + * + * If the PF driver wishes to initiate communication, it can "invalidate" one or + * more of the first 64 blocks. This invalidation is delivered via a callback + * supplied by the VF driver by this driver. + * + * No protocol is implied, except that supplied by the PF and VF drivers. + */ + +struct hv_read_config_compl { + struct hv_pci_compl comp_pkt; + void *buf; + unsigned int len; + unsigned int bytes_returned; +}; + +/** + * hv_pci_read_config_compl() - Invoked when a response packet + * for a read config block operation arrives. + * @context: Identifies the read config operation + * @resp: The response packet itself + * @resp_packet_size: Size in bytes of the response packet + */ +static void hv_pci_read_config_compl(void *context, struct pci_response *resp, + int resp_packet_size) +{ + struct hv_read_config_compl *comp = context; + struct pci_read_block_response *read_resp = + (struct pci_read_block_response *)resp; + unsigned int data_len, hdr_len; + + hdr_len = offsetof(struct pci_read_block_response, bytes); + if (resp_packet_size < hdr_len) { + comp->comp_pkt.completion_status = -1; + goto out; + } + + data_len = resp_packet_size - hdr_len; + if (data_len > 0 && read_resp->status == 0) { + comp->bytes_returned = min(comp->len, data_len); + memcpy(comp->buf, read_resp->bytes, comp->bytes_returned); + } else { + comp->bytes_returned = 0; + } + + comp->comp_pkt.completion_status = read_resp->status; +out: + complete(&comp->comp_pkt.host_event); +} + +/** + * hv_read_config_block() - Sends a read config block request to + * the back-end driver running in the Hyper-V parent partition. + * @pdev: The PCI driver's representation for this device. + * @buf: Buffer into which the config block will be copied. + * @len: Size in bytes of buf. + * @block_id: Identifies the config block which has been requested. + * @bytes_returned: Size which came back from the back-end driver. + * + * Return: 0 on success, -errno on failure + */ +int hv_read_config_block(struct pci_dev *pdev, void *buf, unsigned int len, + unsigned int block_id, unsigned int *bytes_returned) +{ + struct hv_pcibus_device *hbus = + container_of(pdev->bus->sysdata, struct hv_pcibus_device, + sysdata); + struct { + struct pci_packet pkt; + char buf[sizeof(struct pci_read_block)]; + } pkt; + struct hv_read_config_compl comp_pkt; + struct pci_read_block *read_blk; + int ret; + + if (len == 0 || len > HV_CONFIG_BLOCK_SIZE_MAX) + return -EINVAL; + + init_completion(&comp_pkt.comp_pkt.host_event); + comp_pkt.buf = buf; + comp_pkt.len = len; + + memset(&pkt, 0, sizeof(pkt)); + pkt.pkt.completion_func = hv_pci_read_config_compl; + pkt.pkt.compl_ctxt = &comp_pkt; + read_blk = (struct pci_read_block *)&pkt.pkt.message; + read_blk->message_type.type = PCI_READ_BLOCK; + read_blk->wslot.slot = devfn_to_wslot(pdev->devfn); + read_blk->block_id = block_id; + read_blk->bytes_requested = len; + + ret = vmbus_sendpacket(hbus->hdev->channel, read_blk, + sizeof(*read_blk), (unsigned long)&pkt.pkt, + VM_PKT_DATA_INBAND, + VMBUS_DATA_PACKET_FLAG_COMPLETION_REQUESTED); + if (ret) + return ret; + + ret = wait_for_response(hbus->hdev, &comp_pkt.comp_pkt.host_event); + if (ret) + return ret; + + if (comp_pkt.comp_pkt.completion_status != 0 || + comp_pkt.bytes_returned == 0) { + dev_err(&hbus->hdev->device, + "Read Config Block failed: 0x%x, bytes_returned=%d\n", + comp_pkt.comp_pkt.completion_status, + comp_pkt.bytes_returned); + return -EIO; + } + + *bytes_returned = comp_pkt.bytes_returned; + return 0; +} +EXPORT_SYMBOL(hv_read_config_block); + +/** + * hv_pci_write_config_compl() - Invoked when a response packet for a write + * config block operation arrives. + * @context: Identifies the write config operation + * @resp: The response packet itself + * @resp_packet_size: Size in bytes of the response packet + */ +static void hv_pci_write_config_compl(void *context, struct pci_response *resp, + int resp_packet_size) +{ + struct hv_pci_compl *comp_pkt = context; + + comp_pkt->completion_status = resp->status; + complete(&comp_pkt->host_event); +} + +/** + * hv_write_config_block() - Sends a write config block request to the + * back-end driver running in the Hyper-V parent partition. + * @pdev: The PCI driver's representation for this device. + * @buf: Buffer from which the config block will be copied. + * @len: Size in bytes of buf. + * @block_id: Identifies the config block which is being written. + * + * Return: 0 on success, -errno on failure + */ +int hv_write_config_block(struct pci_dev *pdev, void *buf, unsigned int len, + unsigned int block_id) +{ + struct hv_pcibus_device *hbus = + container_of(pdev->bus->sysdata, struct hv_pcibus_device, + sysdata); + struct { + struct pci_packet pkt; + char buf[sizeof(struct pci_write_block)]; + u32 reserved; + } pkt; + struct hv_pci_compl comp_pkt; + struct pci_write_block *write_blk; + u32 pkt_size; + int ret; + + if (len == 0 || len > HV_CONFIG_BLOCK_SIZE_MAX) + return -EINVAL; + + init_completion(&comp_pkt.host_event); + + memset(&pkt, 0, sizeof(pkt)); + pkt.pkt.completion_func = hv_pci_write_config_compl; + pkt.pkt.compl_ctxt = &comp_pkt; + write_blk = (struct pci_write_block *)&pkt.pkt.message; + write_blk->message_type.type = PCI_WRITE_BLOCK; + write_blk->wslot.slot = devfn_to_wslot(pdev->devfn); + write_blk->block_id = block_id; + write_blk->byte_count = len; + memcpy(write_blk->bytes, buf, len); + pkt_size = offsetof(struct pci_write_block, bytes) + len; + /* + * This quirk is required on some hosts shipped around 2018, because + * these hosts don't check the pkt_size correctly (new hosts have been + * fixed since early 2019). The quirk is also safe on very old hosts + * and new hosts, because, on them, what really matters is the length + * specified in write_blk->byte_count. + */ + pkt_size += sizeof(pkt.reserved); + + ret = vmbus_sendpacket(hbus->hdev->channel, write_blk, pkt_size, + (unsigned long)&pkt.pkt, VM_PKT_DATA_INBAND, + VMBUS_DATA_PACKET_FLAG_COMPLETION_REQUESTED); + if (ret) + return ret; + + ret = wait_for_response(hbus->hdev, &comp_pkt.host_event); + if (ret) + return ret; + + if (comp_pkt.completion_status != 0) { + dev_err(&hbus->hdev->device, + "Write Config Block failed: 0x%x\n", + comp_pkt.completion_status); + return -EIO; + } + + return 0; +} +EXPORT_SYMBOL(hv_write_config_block); + +/** + * hv_register_block_invalidate() - Invoked when a config block invalidation + * arrives from the back-end driver. + * @pdev: The PCI driver's representation for this device. + * @context: Identifies the device. + * @block_invalidate: Identifies all of the blocks being invalidated. + * + * Return: 0 on success, -errno on failure + */ +int hv_register_block_invalidate(struct pci_dev *pdev, void *context, + void (*block_invalidate)(void *context, + u64 block_mask)) +{ + struct hv_pcibus_device *hbus = + container_of(pdev->bus->sysdata, struct hv_pcibus_device, + sysdata); + struct hv_pci_dev *hpdev; + + hpdev = get_pcichild_wslot(hbus, devfn_to_wslot(pdev->devfn)); + if (!hpdev) + return -ENODEV; + + hpdev->block_invalidate = block_invalidate; + hpdev->invalidate_context = context; + + put_pcichild(hpdev); + return 0; + +} +EXPORT_SYMBOL(hv_register_block_invalidate); + /* Interrupt management hooks */ static void hv_int_desc_free(struct hv_pci_dev *hpdev, struct tran_int_desc *int_desc) @@ -1968,6 +2254,7 @@ static void hv_pci_onchannelcallback(void *context) struct pci_response *response; struct pci_incoming_message *new_message; struct pci_bus_relations *bus_rel; + struct pci_dev_inval_block *inval; struct pci_dev_incoming *dev_message; struct hv_pci_dev *hpdev; @@ -2045,6 +2332,21 @@ static void hv_pci_onchannelcallback(void *context) } break; + case PCI_INVALIDATE_BLOCK: + + inval = (struct pci_dev_inval_block *)buffer; + hpdev = get_pcichild_wslot(hbus, + inval->wslot.slot); + if (hpdev) { + if (hpdev->block_invalidate) { + hpdev->block_invalidate( + hpdev->invalidate_context, + inval->block_mask); + } + put_pcichild(hpdev); + } + break; + default: dev_warn(&hbus->hdev->device, "Unimplemented protocol message %x\n", diff --git a/include/linux/hyperv.h b/include/linux/hyperv.h index 6256cc34c4a6..9d37f8cf1245 100644 --- a/include/linux/hyperv.h +++ b/include/linux/hyperv.h @@ -1578,4 +1578,19 @@ hv_pkt_iter_next(struct vmbus_channel *channel, for (pkt = hv_pkt_iter_first(channel); pkt; \ pkt = hv_pkt_iter_next(channel, pkt)) +/* + * Functions for passing data between SR-IOV PF and VF drivers. The VF driver + * sends requests to read and write blocks. Each block must be 128 bytes or + * smaller. Optionally, the VF driver can register a callback function which + * will be invoked when the host says that one or more of the first 64 block + * IDs is "invalid" which means that the VF driver should reread them. + */ +#define HV_CONFIG_BLOCK_SIZE_MAX 128 +int hv_read_config_block(struct pci_dev *dev, void *buf, unsigned int buf_len, + unsigned int block_id, unsigned int *bytes_returned); +int hv_write_config_block(struct pci_dev *dev, void *buf, unsigned int len, + unsigned int block_id); +int hv_register_block_invalidate(struct pci_dev *dev, void *context, + void (*block_invalidate)(void *context, + u64 block_mask)); #endif /* _HYPERV_H */ -- cgit v1.2.3 From 348dd93e40c112afda3cd07daa6f470e474d29dc Mon Sep 17 00:00:00 2001 From: Haiyang Zhang Date: Thu, 22 Aug 2019 05:05:41 +0000 Subject: PCI: hv: Add a Hyper-V PCI interface driver for software backchannel interface This interface driver is a helper driver allows other drivers to have a common interface with the Hyper-V PCI frontend driver. Signed-off-by: Haiyang Zhang Signed-off-by: Saeed Mahameed Signed-off-by: David S. Miller --- MAINTAINERS | 1 + drivers/pci/Kconfig | 1 + drivers/pci/controller/Kconfig | 7 ++++ drivers/pci/controller/Makefile | 1 + drivers/pci/controller/pci-hyperv-intf.c | 67 ++++++++++++++++++++++++++++++++ drivers/pci/controller/pci-hyperv.c | 12 ++++-- include/linux/hyperv.h | 30 ++++++++++---- 7 files changed, 108 insertions(+), 11 deletions(-) create mode 100644 drivers/pci/controller/pci-hyperv-intf.c (limited to 'include/linux') diff --git a/MAINTAINERS b/MAINTAINERS index a406947b369e..986085351d79 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -7469,6 +7469,7 @@ F: drivers/hid/hid-hyperv.c F: drivers/hv/ F: drivers/input/serio/hyperv-keyboard.c F: drivers/pci/controller/pci-hyperv.c +F: drivers/pci/controller/pci-hyperv-intf.c F: drivers/net/hyperv/ F: drivers/scsi/storvsc_drv.c F: drivers/uio/uio_hv_generic.c diff --git a/drivers/pci/Kconfig b/drivers/pci/Kconfig index 2ab92409210a..c313de96a357 100644 --- a/drivers/pci/Kconfig +++ b/drivers/pci/Kconfig @@ -182,6 +182,7 @@ config PCI_LABEL config PCI_HYPERV tristate "Hyper-V PCI Frontend" depends on X86 && HYPERV && PCI_MSI && PCI_MSI_IRQ_DOMAIN && X86_64 + select PCI_HYPERV_INTERFACE help The PCI device frontend driver allows the kernel to import arbitrary PCI devices from a PCI backend to support PCI driver domains. diff --git a/drivers/pci/controller/Kconfig b/drivers/pci/controller/Kconfig index fe9f9f13ce11..70e078238899 100644 --- a/drivers/pci/controller/Kconfig +++ b/drivers/pci/controller/Kconfig @@ -281,5 +281,12 @@ config VMD To compile this driver as a module, choose M here: the module will be called vmd. +config PCI_HYPERV_INTERFACE + tristate "Hyper-V PCI Interface" + depends on X86 && HYPERV && PCI_MSI && PCI_MSI_IRQ_DOMAIN && X86_64 + help + The Hyper-V PCI Interface is a helper driver allows other drivers to + have a common interface with the Hyper-V PCI frontend driver. + source "drivers/pci/controller/dwc/Kconfig" endmenu diff --git a/drivers/pci/controller/Makefile b/drivers/pci/controller/Makefile index d56a507495c5..a2a22c9d91af 100644 --- a/drivers/pci/controller/Makefile +++ b/drivers/pci/controller/Makefile @@ -4,6 +4,7 @@ obj-$(CONFIG_PCIE_CADENCE_HOST) += pcie-cadence-host.o obj-$(CONFIG_PCIE_CADENCE_EP) += pcie-cadence-ep.o obj-$(CONFIG_PCI_FTPCI100) += pci-ftpci100.o obj-$(CONFIG_PCI_HYPERV) += pci-hyperv.o +obj-$(CONFIG_PCI_HYPERV_INTERFACE) += pci-hyperv-intf.o obj-$(CONFIG_PCI_MVEBU) += pci-mvebu.o obj-$(CONFIG_PCI_AARDVARK) += pci-aardvark.o obj-$(CONFIG_PCI_TEGRA) += pci-tegra.o diff --git a/drivers/pci/controller/pci-hyperv-intf.c b/drivers/pci/controller/pci-hyperv-intf.c new file mode 100644 index 000000000000..cc96be450360 --- /dev/null +++ b/drivers/pci/controller/pci-hyperv-intf.c @@ -0,0 +1,67 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (c) Microsoft Corporation. + * + * Author: + * Haiyang Zhang + * + * This small module is a helper driver allows other drivers to + * have a common interface with the Hyper-V PCI frontend driver. + */ + +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt + +#include +#include +#include + +struct hyperv_pci_block_ops hvpci_block_ops; +EXPORT_SYMBOL_GPL(hvpci_block_ops); + +int hyperv_read_cfg_blk(struct pci_dev *dev, void *buf, unsigned int buf_len, + unsigned int block_id, unsigned int *bytes_returned) +{ + if (!hvpci_block_ops.read_block) + return -EOPNOTSUPP; + + return hvpci_block_ops.read_block(dev, buf, buf_len, block_id, + bytes_returned); +} +EXPORT_SYMBOL_GPL(hyperv_read_cfg_blk); + +int hyperv_write_cfg_blk(struct pci_dev *dev, void *buf, unsigned int len, + unsigned int block_id) +{ + if (!hvpci_block_ops.write_block) + return -EOPNOTSUPP; + + return hvpci_block_ops.write_block(dev, buf, len, block_id); +} +EXPORT_SYMBOL_GPL(hyperv_write_cfg_blk); + +int hyperv_reg_block_invalidate(struct pci_dev *dev, void *context, + void (*block_invalidate)(void *context, + u64 block_mask)) +{ + if (!hvpci_block_ops.reg_blk_invalidate) + return -EOPNOTSUPP; + + return hvpci_block_ops.reg_blk_invalidate(dev, context, + block_invalidate); +} +EXPORT_SYMBOL_GPL(hyperv_reg_block_invalidate); + +static void __exit exit_hv_pci_intf(void) +{ +} + +static int __init init_hv_pci_intf(void) +{ + return 0; +} + +module_init(init_hv_pci_intf); +module_exit(exit_hv_pci_intf); + +MODULE_DESCRIPTION("Hyper-V PCI Interface"); +MODULE_LICENSE("GPL v2"); diff --git a/drivers/pci/controller/pci-hyperv.c b/drivers/pci/controller/pci-hyperv.c index 57adeca7bda9..9c93ac2215b7 100644 --- a/drivers/pci/controller/pci-hyperv.c +++ b/drivers/pci/controller/pci-hyperv.c @@ -983,7 +983,6 @@ int hv_read_config_block(struct pci_dev *pdev, void *buf, unsigned int len, *bytes_returned = comp_pkt.bytes_returned; return 0; } -EXPORT_SYMBOL(hv_read_config_block); /** * hv_pci_write_config_compl() - Invoked when a response packet for a write @@ -1070,7 +1069,6 @@ int hv_write_config_block(struct pci_dev *pdev, void *buf, unsigned int len, return 0; } -EXPORT_SYMBOL(hv_write_config_block); /** * hv_register_block_invalidate() - Invoked when a config block invalidation @@ -1101,7 +1099,6 @@ int hv_register_block_invalidate(struct pci_dev *pdev, void *context, return 0; } -EXPORT_SYMBOL(hv_register_block_invalidate); /* Interrupt management hooks */ static void hv_int_desc_free(struct hv_pci_dev *hpdev, @@ -3045,10 +3042,19 @@ static struct hv_driver hv_pci_drv = { static void __exit exit_hv_pci_drv(void) { vmbus_driver_unregister(&hv_pci_drv); + + hvpci_block_ops.read_block = NULL; + hvpci_block_ops.write_block = NULL; + hvpci_block_ops.reg_blk_invalidate = NULL; } static int __init init_hv_pci_drv(void) { + /* Initialize PCI block r/w interface */ + hvpci_block_ops.read_block = hv_read_config_block; + hvpci_block_ops.write_block = hv_write_config_block; + hvpci_block_ops.reg_blk_invalidate = hv_register_block_invalidate; + return vmbus_driver_register(&hv_pci_drv); } diff --git a/include/linux/hyperv.h b/include/linux/hyperv.h index 9d37f8cf1245..2afe6fdc1dda 100644 --- a/include/linux/hyperv.h +++ b/include/linux/hyperv.h @@ -1579,18 +1579,32 @@ hv_pkt_iter_next(struct vmbus_channel *channel, pkt = hv_pkt_iter_next(channel, pkt)) /* - * Functions for passing data between SR-IOV PF and VF drivers. The VF driver + * Interface for passing data between SR-IOV PF and VF drivers. The VF driver * sends requests to read and write blocks. Each block must be 128 bytes or * smaller. Optionally, the VF driver can register a callback function which * will be invoked when the host says that one or more of the first 64 block * IDs is "invalid" which means that the VF driver should reread them. */ #define HV_CONFIG_BLOCK_SIZE_MAX 128 -int hv_read_config_block(struct pci_dev *dev, void *buf, unsigned int buf_len, - unsigned int block_id, unsigned int *bytes_returned); -int hv_write_config_block(struct pci_dev *dev, void *buf, unsigned int len, - unsigned int block_id); -int hv_register_block_invalidate(struct pci_dev *dev, void *context, - void (*block_invalidate)(void *context, - u64 block_mask)); + +int hyperv_read_cfg_blk(struct pci_dev *dev, void *buf, unsigned int buf_len, + unsigned int block_id, unsigned int *bytes_returned); +int hyperv_write_cfg_blk(struct pci_dev *dev, void *buf, unsigned int len, + unsigned int block_id); +int hyperv_reg_block_invalidate(struct pci_dev *dev, void *context, + void (*block_invalidate)(void *context, + u64 block_mask)); + +struct hyperv_pci_block_ops { + int (*read_block)(struct pci_dev *dev, void *buf, unsigned int buf_len, + unsigned int block_id, unsigned int *bytes_returned); + int (*write_block)(struct pci_dev *dev, void *buf, unsigned int len, + unsigned int block_id); + int (*reg_blk_invalidate)(struct pci_dev *dev, void *context, + void (*block_invalidate)(void *context, + u64 block_mask)); +}; + +extern struct hyperv_pci_block_ops hvpci_block_ops; + #endif /* _HYPERV_H */ -- cgit v1.2.3 From 87175120defd2907d42592653c35feea9de0437a Mon Sep 17 00:00:00 2001 From: Eran Ben Elisha Date: Thu, 22 Aug 2019 05:05:51 +0000 Subject: net/mlx5: Add HV VHCA infrastructure HV VHCA is a layer which provides PF to VF communication channel based on HyperV PCI config channel. It implements Mellanox's Inter VHCA control communication protocol. The protocol contains control block in order to pass messages between the PF and VF drivers, and data blocks in order to pass actual data. The infrastructure is agent based. Each agent will be responsible of contiguous buffer blocks in the VHCA config space. This infrastructure will bind agents to their blocks, and those agents can only access read/write the buffer blocks assigned to them. Each agent will provide three callbacks (control, invalidate, cleanup). Control will be invoked when block-0 is invalidated with a command that concerns this agent. Invalidate callback will be invoked if one of the blocks assigned to this agent was invalidated. Cleanup will be invoked before the agent is being freed in order to clean all of its open resources or deferred works. Block-0 serves as the control block. All execution commands from the PF will be written by the PF over this block. VF will ack on those by writing on block-0 as well. Its format is described by struct mlx5_hv_vhca_control_block layout. Signed-off-by: Eran Ben Elisha Signed-off-by: Saeed Mahameed Signed-off-by: Haiyang Zhang Signed-off-by: David S. Miller --- drivers/net/ethernet/mellanox/mlx5/core/Makefile | 2 +- .../net/ethernet/mellanox/mlx5/core/lib/hv_vhca.c | 253 +++++++++++++++++++++ .../net/ethernet/mellanox/mlx5/core/lib/hv_vhca.h | 102 +++++++++ drivers/net/ethernet/mellanox/mlx5/core/main.c | 7 + include/linux/mlx5/driver.h | 2 + 5 files changed, 365 insertions(+), 1 deletion(-) create mode 100644 drivers/net/ethernet/mellanox/mlx5/core/lib/hv_vhca.c create mode 100644 drivers/net/ethernet/mellanox/mlx5/core/lib/hv_vhca.h (limited to 'include/linux') diff --git a/drivers/net/ethernet/mellanox/mlx5/core/Makefile b/drivers/net/ethernet/mellanox/mlx5/core/Makefile index fd32a5beba72..8d443fca199e 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/Makefile +++ b/drivers/net/ethernet/mellanox/mlx5/core/Makefile @@ -45,7 +45,7 @@ mlx5_core-$(CONFIG_MLX5_ESWITCH) += eswitch.o eswitch_offloads.o eswitch_offlo mlx5_core-$(CONFIG_MLX5_MPFS) += lib/mpfs.o mlx5_core-$(CONFIG_VXLAN) += lib/vxlan.o mlx5_core-$(CONFIG_PTP_1588_CLOCK) += lib/clock.o -mlx5_core-$(CONFIG_PCI_HYPERV_INTERFACE) += lib/hv.o +mlx5_core-$(CONFIG_PCI_HYPERV_INTERFACE) += lib/hv.o lib/hv_vhca.o # # Ipoib netdev diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lib/hv_vhca.c b/drivers/net/ethernet/mellanox/mlx5/core/lib/hv_vhca.c new file mode 100644 index 000000000000..84d1d75a1608 --- /dev/null +++ b/drivers/net/ethernet/mellanox/mlx5/core/lib/hv_vhca.c @@ -0,0 +1,253 @@ +// SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB +// Copyright (c) 2018 Mellanox Technologies + +#include +#include "mlx5_core.h" +#include "lib/hv.h" +#include "lib/hv_vhca.h" + +struct mlx5_hv_vhca { + struct mlx5_core_dev *dev; + struct workqueue_struct *work_queue; + struct mlx5_hv_vhca_agent *agents[MLX5_HV_VHCA_AGENT_MAX]; + struct mutex agents_lock; /* Protect agents array */ +}; + +struct mlx5_hv_vhca_work { + struct work_struct invalidate_work; + struct mlx5_hv_vhca *hv_vhca; + u64 block_mask; +}; + +struct mlx5_hv_vhca_data_block { + u16 sequence; + u16 offset; + u8 reserved[4]; + u64 data[15]; +}; + +struct mlx5_hv_vhca_agent { + enum mlx5_hv_vhca_agent_type type; + struct mlx5_hv_vhca *hv_vhca; + void *priv; + u16 seq; + void (*control)(struct mlx5_hv_vhca_agent *agent, + struct mlx5_hv_vhca_control_block *block); + void (*invalidate)(struct mlx5_hv_vhca_agent *agent, + u64 block_mask); + void (*cleanup)(struct mlx5_hv_vhca_agent *agent); +}; + +struct mlx5_hv_vhca *mlx5_hv_vhca_create(struct mlx5_core_dev *dev) +{ + struct mlx5_hv_vhca *hv_vhca = NULL; + + hv_vhca = kzalloc(sizeof(*hv_vhca), GFP_KERNEL); + if (!hv_vhca) + return ERR_PTR(-ENOMEM); + + hv_vhca->work_queue = create_singlethread_workqueue("mlx5_hv_vhca"); + if (!hv_vhca->work_queue) { + kfree(hv_vhca); + return ERR_PTR(-ENOMEM); + } + + hv_vhca->dev = dev; + mutex_init(&hv_vhca->agents_lock); + + return hv_vhca; +} + +void mlx5_hv_vhca_destroy(struct mlx5_hv_vhca *hv_vhca) +{ + if (IS_ERR_OR_NULL(hv_vhca)) + return; + + destroy_workqueue(hv_vhca->work_queue); + kfree(hv_vhca); +} + +static void mlx5_hv_vhca_invalidate_work(struct work_struct *work) +{ + struct mlx5_hv_vhca_work *hwork; + struct mlx5_hv_vhca *hv_vhca; + int i; + + hwork = container_of(work, struct mlx5_hv_vhca_work, invalidate_work); + hv_vhca = hwork->hv_vhca; + + mutex_lock(&hv_vhca->agents_lock); + for (i = 0; i < MLX5_HV_VHCA_AGENT_MAX; i++) { + struct mlx5_hv_vhca_agent *agent = hv_vhca->agents[i]; + + if (!agent || !agent->invalidate) + continue; + + if (!(BIT(agent->type) & hwork->block_mask)) + continue; + + agent->invalidate(agent, hwork->block_mask); + } + mutex_unlock(&hv_vhca->agents_lock); + + kfree(hwork); +} + +void mlx5_hv_vhca_invalidate(void *context, u64 block_mask) +{ + struct mlx5_hv_vhca *hv_vhca = (struct mlx5_hv_vhca *)context; + struct mlx5_hv_vhca_work *work; + + work = kzalloc(sizeof(*work), GFP_ATOMIC); + if (!work) + return; + + INIT_WORK(&work->invalidate_work, mlx5_hv_vhca_invalidate_work); + work->hv_vhca = hv_vhca; + work->block_mask = block_mask; + + queue_work(hv_vhca->work_queue, &work->invalidate_work); +} + +int mlx5_hv_vhca_init(struct mlx5_hv_vhca *hv_vhca) +{ + if (IS_ERR_OR_NULL(hv_vhca)) + return IS_ERR_OR_NULL(hv_vhca); + + return mlx5_hv_register_invalidate(hv_vhca->dev, hv_vhca, + mlx5_hv_vhca_invalidate); +} + +void mlx5_hv_vhca_cleanup(struct mlx5_hv_vhca *hv_vhca) +{ + int i; + + if (IS_ERR_OR_NULL(hv_vhca)) + return; + + mutex_lock(&hv_vhca->agents_lock); + for (i = 0; i < MLX5_HV_VHCA_AGENT_MAX; i++) + WARN_ON(hv_vhca->agents[i]); + + mutex_unlock(&hv_vhca->agents_lock); + + mlx5_hv_unregister_invalidate(hv_vhca->dev); +} + +struct mlx5_hv_vhca_agent * +mlx5_hv_vhca_agent_create(struct mlx5_hv_vhca *hv_vhca, + enum mlx5_hv_vhca_agent_type type, + void (*control)(struct mlx5_hv_vhca_agent*, + struct mlx5_hv_vhca_control_block *block), + void (*invalidate)(struct mlx5_hv_vhca_agent*, + u64 block_mask), + void (*cleaup)(struct mlx5_hv_vhca_agent *agent), + void *priv) +{ + struct mlx5_hv_vhca_agent *agent; + + if (IS_ERR_OR_NULL(hv_vhca)) + return ERR_PTR(-ENOMEM); + + if (type >= MLX5_HV_VHCA_AGENT_MAX) + return ERR_PTR(-EINVAL); + + mutex_lock(&hv_vhca->agents_lock); + if (hv_vhca->agents[type]) { + mutex_unlock(&hv_vhca->agents_lock); + return ERR_PTR(-EINVAL); + } + mutex_unlock(&hv_vhca->agents_lock); + + agent = kzalloc(sizeof(*agent), GFP_KERNEL); + if (!agent) + return ERR_PTR(-ENOMEM); + + agent->type = type; + agent->hv_vhca = hv_vhca; + agent->priv = priv; + agent->control = control; + agent->invalidate = invalidate; + agent->cleanup = cleaup; + + mutex_lock(&hv_vhca->agents_lock); + hv_vhca->agents[type] = agent; + mutex_unlock(&hv_vhca->agents_lock); + + return agent; +} + +void mlx5_hv_vhca_agent_destroy(struct mlx5_hv_vhca_agent *agent) +{ + struct mlx5_hv_vhca *hv_vhca = agent->hv_vhca; + + mutex_lock(&hv_vhca->agents_lock); + + if (WARN_ON(agent != hv_vhca->agents[agent->type])) { + mutex_unlock(&hv_vhca->agents_lock); + return; + } + + hv_vhca->agents[agent->type] = NULL; + mutex_unlock(&hv_vhca->agents_lock); + + if (agent->cleanup) + agent->cleanup(agent); + + kfree(agent); +} + +static int mlx5_hv_vhca_data_block_prepare(struct mlx5_hv_vhca_agent *agent, + struct mlx5_hv_vhca_data_block *data_block, + void *src, int len, int *offset) +{ + int bytes = min_t(int, (int)sizeof(data_block->data), len); + + data_block->sequence = agent->seq; + data_block->offset = (*offset)++; + memcpy(data_block->data, src, bytes); + + return bytes; +} + +static void mlx5_hv_vhca_agent_seq_update(struct mlx5_hv_vhca_agent *agent) +{ + agent->seq++; +} + +int mlx5_hv_vhca_agent_write(struct mlx5_hv_vhca_agent *agent, + void *buf, int len) +{ + int offset = agent->type * HV_CONFIG_BLOCK_SIZE_MAX; + int block_offset = 0; + int total = 0; + int err; + + while (len) { + struct mlx5_hv_vhca_data_block data_block = {0}; + int bytes; + + bytes = mlx5_hv_vhca_data_block_prepare(agent, &data_block, + buf + total, + len, &block_offset); + if (!bytes) + return -ENOMEM; + + err = mlx5_hv_write_config(agent->hv_vhca->dev, &data_block, + sizeof(data_block), offset); + if (err) + return err; + + total += bytes; + len -= bytes; + } + + mlx5_hv_vhca_agent_seq_update(agent); + + return 0; +} + +void *mlx5_hv_vhca_agent_priv(struct mlx5_hv_vhca_agent *agent) +{ + return agent->priv; +} diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lib/hv_vhca.h b/drivers/net/ethernet/mellanox/mlx5/core/lib/hv_vhca.h new file mode 100644 index 000000000000..cdf13039489c --- /dev/null +++ b/drivers/net/ethernet/mellanox/mlx5/core/lib/hv_vhca.h @@ -0,0 +1,102 @@ +/* SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB */ +/* Copyright (c) 2019 Mellanox Technologies. */ + +#ifndef __LIB_HV_VHCA_H__ +#define __LIB_HV_VHCA_H__ + +#include "en.h" +#include "lib/hv.h" + +struct mlx5_hv_vhca_agent; +struct mlx5_hv_vhca; +struct mlx5_hv_vhca_control_block; + +enum mlx5_hv_vhca_agent_type { + MLX5_HV_VHCA_AGENT_MAX = 32, +}; + +#if IS_ENABLED(CONFIG_PCI_HYPERV_INTERFACE) + +struct mlx5_hv_vhca_control_block { + u32 capabilities; + u32 control; + u16 command; + u16 command_ack; + u16 version; + u16 rings; + u32 reserved1[28]; +}; + +struct mlx5_hv_vhca *mlx5_hv_vhca_create(struct mlx5_core_dev *dev); +void mlx5_hv_vhca_destroy(struct mlx5_hv_vhca *hv_vhca); +int mlx5_hv_vhca_init(struct mlx5_hv_vhca *hv_vhca); +void mlx5_hv_vhca_cleanup(struct mlx5_hv_vhca *hv_vhca); +void mlx5_hv_vhca_invalidate(void *context, u64 block_mask); + +struct mlx5_hv_vhca_agent * +mlx5_hv_vhca_agent_create(struct mlx5_hv_vhca *hv_vhca, + enum mlx5_hv_vhca_agent_type type, + void (*control)(struct mlx5_hv_vhca_agent*, + struct mlx5_hv_vhca_control_block *block), + void (*invalidate)(struct mlx5_hv_vhca_agent*, + u64 block_mask), + void (*cleanup)(struct mlx5_hv_vhca_agent *agent), + void *context); + +void mlx5_hv_vhca_agent_destroy(struct mlx5_hv_vhca_agent *agent); +int mlx5_hv_vhca_agent_write(struct mlx5_hv_vhca_agent *agent, + void *buf, int len); +void *mlx5_hv_vhca_agent_priv(struct mlx5_hv_vhca_agent *agent); + +#else + +static inline struct mlx5_hv_vhca * +mlx5_hv_vhca_create(struct mlx5_core_dev *dev) +{ + return NULL; +} + +static inline void mlx5_hv_vhca_destroy(struct mlx5_hv_vhca *hv_vhca) +{ +} + +static inline int mlx5_hv_vhca_init(struct mlx5_hv_vhca *hv_vhca) +{ + return 0; +} + +static inline void mlx5_hv_vhca_cleanup(struct mlx5_hv_vhca *hv_vhca) +{ +} + +static inline void mlx5_hv_vhca_invalidate(void *context, + u64 block_mask) +{ +} + +static inline struct mlx5_hv_vhca_agent * +mlx5_hv_vhca_agent_create(struct mlx5_hv_vhca *hv_vhca, + enum mlx5_hv_vhca_agent_type type, + void (*control)(struct mlx5_hv_vhca_agent*, + struct mlx5_hv_vhca_control_block *block), + void (*invalidate)(struct mlx5_hv_vhca_agent*, + u64 block_mask), + void (*cleanup)(struct mlx5_hv_vhca_agent *agent), + void *context) +{ + return NULL; +} + +static inline void mlx5_hv_vhca_agent_destroy(struct mlx5_hv_vhca_agent *agent) +{ +} + +static inline int +mlx5_hv_vhca_write_agent(struct mlx5_hv_vhca_agent *agent, + void *buf, int len) +{ + return 0; +} +#endif + +#endif /* __LIB_HV_VHCA_H__ */ diff --git a/drivers/net/ethernet/mellanox/mlx5/core/main.c b/drivers/net/ethernet/mellanox/mlx5/core/main.c index 0b70b1d6338d..61388ca7233b 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/main.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/main.c @@ -69,6 +69,7 @@ #include "lib/pci_vsc.h" #include "diag/fw_tracer.h" #include "ecpf.h" +#include "lib/hv_vhca.h" MODULE_AUTHOR("Eli Cohen "); MODULE_DESCRIPTION("Mellanox 5th generation network adapters (ConnectX series) core driver"); @@ -870,6 +871,7 @@ static int mlx5_init_once(struct mlx5_core_dev *dev) } dev->tracer = mlx5_fw_tracer_create(dev); + dev->hv_vhca = mlx5_hv_vhca_create(dev); return 0; @@ -900,6 +902,7 @@ err_devcom: static void mlx5_cleanup_once(struct mlx5_core_dev *dev) { + mlx5_hv_vhca_destroy(dev->hv_vhca); mlx5_fw_tracer_destroy(dev->tracer); mlx5_fpga_cleanup(dev); mlx5_eswitch_cleanup(dev->priv.eswitch); @@ -1067,6 +1070,8 @@ static int mlx5_load(struct mlx5_core_dev *dev) goto err_fw_tracer; } + mlx5_hv_vhca_init(dev->hv_vhca); + err = mlx5_fpga_device_start(dev); if (err) { mlx5_core_err(dev, "fpga device start failed %d\n", err); @@ -1122,6 +1127,7 @@ err_tls_start: err_ipsec_start: mlx5_fpga_device_stop(dev); err_fpga_start: + mlx5_hv_vhca_cleanup(dev->hv_vhca); mlx5_fw_tracer_cleanup(dev->tracer); err_fw_tracer: mlx5_eq_table_destroy(dev); @@ -1142,6 +1148,7 @@ static void mlx5_unload(struct mlx5_core_dev *dev) mlx5_accel_ipsec_cleanup(dev); mlx5_accel_tls_cleanup(dev); mlx5_fpga_device_stop(dev); + mlx5_hv_vhca_cleanup(dev->hv_vhca); mlx5_fw_tracer_cleanup(dev->tracer); mlx5_eq_table_destroy(dev); mlx5_irq_table_destroy(dev); diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h index df23f17eed64..13b4cf22f3ab 100644 --- a/include/linux/mlx5/driver.h +++ b/include/linux/mlx5/driver.h @@ -659,6 +659,7 @@ struct mlx5_clock { struct mlx5_fw_tracer; struct mlx5_vxlan; struct mlx5_geneve; +struct mlx5_hv_vhca; struct mlx5_core_dev { struct device *device; @@ -706,6 +707,7 @@ struct mlx5_core_dev { struct mlx5_ib_clock_info *clock_info; struct mlx5_fw_tracer *tracer; u32 vsc_addr; + struct mlx5_hv_vhca *hv_vhca; }; struct mlx5_db { -- cgit v1.2.3 From f3acd33d840d3ea3e1233d234605c85cbbf26054 Mon Sep 17 00:00:00 2001 From: xiaolinkui Date: Thu, 22 Aug 2019 14:58:16 +0800 Subject: net: use unlikely for dql_avail case This is an unlikely case, use unlikely() on it seems logical. Signed-off-by: xiaolinkui Signed-off-by: David S. Miller --- include/linux/netdevice.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 55ac223553f8..b5d28dadf964 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -3272,7 +3272,7 @@ static inline void netdev_tx_completed_queue(struct netdev_queue *dev_queue, */ smp_mb(); - if (dql_avail(&dev_queue->dql) < 0) + if (unlikely(dql_avail(&dev_queue->dql) < 0)) return; if (test_and_clear_bit(__QUEUE_STATE_STACK_XOFF, &dev_queue->state)) -- cgit v1.2.3 From 10d274e880eb208ec6a76261a9f8f8155020f771 Mon Sep 17 00:00:00 2001 From: Alexei Starovoitov Date: Thu, 22 Aug 2019 22:52:12 -0700 Subject: bpf: introduce verifier internal test flag Introduce BPF_F_TEST_STATE_FREQ flag to stress test parentage chain and state pruning. Signed-off-by: Alexei Starovoitov Acked-by: Song Liu Signed-off-by: Daniel Borkmann --- include/linux/bpf_verifier.h | 1 + include/uapi/linux/bpf.h | 3 +++ kernel/bpf/syscall.c | 1 + kernel/bpf/verifier.c | 5 ++++- 4 files changed, 9 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/bpf_verifier.h b/include/linux/bpf_verifier.h index 5fe99f322b1c..26a6d58ca78c 100644 --- a/include/linux/bpf_verifier.h +++ b/include/linux/bpf_verifier.h @@ -355,6 +355,7 @@ struct bpf_verifier_env { struct bpf_verifier_stack_elem *head; /* stack of verifier states to be processed */ int stack_size; /* number of states to be processed */ bool strict_alignment; /* perform strict pointer alignment checks */ + bool test_state_freq; /* test verifier with different pruning frequency */ struct bpf_verifier_state *cur_state; /* current verifier state */ struct bpf_verifier_state_list **explored_states; /* search pruning optimization */ struct bpf_verifier_state_list *free_list; diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index b5889257cc33..5d2fb183ee2d 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -285,6 +285,9 @@ enum bpf_attach_type { */ #define BPF_F_TEST_RND_HI32 (1U << 2) +/* The verifier internal test flag. Behavior is undefined */ +#define BPF_F_TEST_STATE_FREQ (1U << 3) + /* When BPF ldimm64's insn[0].src_reg != 0 then this can have * two extensions: * diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c index c0f62fd67c6b..ca60eafa6922 100644 --- a/kernel/bpf/syscall.c +++ b/kernel/bpf/syscall.c @@ -1629,6 +1629,7 @@ static int bpf_prog_load(union bpf_attr *attr, union bpf_attr __user *uattr) if (attr->prog_flags & ~(BPF_F_STRICT_ALIGNMENT | BPF_F_ANY_ALIGNMENT | + BPF_F_TEST_STATE_FREQ | BPF_F_TEST_RND_HI32)) return -EINVAL; diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index 10c0ff93f52b..f340cfe53c6e 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -7222,7 +7222,7 @@ static int is_state_visited(struct bpf_verifier_env *env, int insn_idx) struct bpf_verifier_state_list *sl, **pprev; struct bpf_verifier_state *cur = env->cur_state, *new; int i, j, err, states_cnt = 0; - bool add_new_state = false; + bool add_new_state = env->test_state_freq ? true : false; cur->last_insn_idx = env->prev_insn_idx; if (!env->insn_aux_data[insn_idx].prune_point) @@ -9262,6 +9262,9 @@ int bpf_check(struct bpf_prog **prog, union bpf_attr *attr, env->allow_ptr_leaks = is_priv; + if (is_priv) + env->test_state_freq = attr->prog_flags & BPF_F_TEST_STATE_FREQ; + ret = replace_map_fd_with_map_ptr(env); if (ret < 0) goto skip_full_check; -- cgit v1.2.3 From 190f73ab4c43ecfc8e93843fe249efeff7d69a90 Mon Sep 17 00:00:00 2001 From: Voon Weifeng Date: Tue, 27 Aug 2019 09:38:11 +0800 Subject: net: stmmac: setup higher frequency clk support for EHL & TGL EHL DW EQOS is running on a 200MHz clock. Setting up stmmac-clk, ptp clock and ptp_max_adj to 200MHz. Signed-off-by: Voon Weifeng Signed-off-by: Ong Boon Leong Signed-off-by: David S. Miller --- drivers/net/ethernet/stmicro/stmmac/stmmac_pci.c | 21 +++++++++++++++++++++ drivers/net/ethernet/stmicro/stmmac/stmmac_ptp.c | 3 +++ include/linux/stmmac.h | 1 + 3 files changed, 25 insertions(+) (limited to 'include/linux') diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_pci.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_pci.c index e969dc9bb9f0..20906287b6d4 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_pci.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_pci.c @@ -9,6 +9,7 @@ Author: Giuseppe Cavallaro *******************************************************************************/ +#include #include #include @@ -174,6 +175,19 @@ static int intel_mgbe_common_data(struct pci_dev *pdev, plat->axi->axi_blen[1] = 8; plat->axi->axi_blen[2] = 16; + plat->ptp_max_adj = plat->clk_ptp_rate; + + /* Set system clock */ + plat->stmmac_clk = clk_register_fixed_rate(&pdev->dev, + "stmmac-clk", NULL, 0, + plat->clk_ptp_rate); + + if (IS_ERR(plat->stmmac_clk)) { + dev_warn(&pdev->dev, "Fail to register stmmac-clk\n"); + plat->stmmac_clk = NULL; + } + clk_prepare_enable(plat->stmmac_clk); + /* Set default value for multicast hash bins */ plat->multicast_filter_bins = HASH_TABLE_SIZE; @@ -193,6 +207,7 @@ static int ehl_common_data(struct pci_dev *pdev, plat->rx_queues_to_use = 8; plat->tx_queues_to_use = 8; + plat->clk_ptp_rate = 200000000; ret = intel_mgbe_common_data(pdev, plat); if (ret) return ret; @@ -233,6 +248,7 @@ static int tgl_common_data(struct pci_dev *pdev, plat->rx_queues_to_use = 6; plat->tx_queues_to_use = 4; + plat->clk_ptp_rate = 200000000; ret = intel_mgbe_common_data(pdev, plat); if (ret) return ret; @@ -438,10 +454,15 @@ static int stmmac_pci_probe(struct pci_dev *pdev, */ static void stmmac_pci_remove(struct pci_dev *pdev) { + struct net_device *ndev = dev_get_drvdata(&pdev->dev); + struct stmmac_priv *priv = netdev_priv(ndev); int i; stmmac_dvr_remove(&pdev->dev); + if (priv->plat->stmmac_clk) + clk_unregister_fixed_rate(priv->plat->stmmac_clk); + for (i = 0; i <= PCI_STD_RESOURCE_END; i++) { if (pci_resource_len(pdev, i) == 0) continue; diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_ptp.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_ptp.c index c48224973a37..173493db038c 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_ptp.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_ptp.c @@ -194,6 +194,9 @@ void stmmac_ptp_register(struct stmmac_priv *priv) priv->pps[i].available = true; } + if (priv->plat->ptp_max_adj) + stmmac_ptp_clock_ops.max_adj = priv->plat->ptp_max_adj; + stmmac_ptp_clock_ops.n_per_out = priv->dma_cap.pps_out_num; spin_lock_init(&priv->ptp_lock); diff --git a/include/linux/stmmac.h b/include/linux/stmmac.h index 5cc6b6faf359..7ad7ae35cf88 100644 --- a/include/linux/stmmac.h +++ b/include/linux/stmmac.h @@ -168,6 +168,7 @@ struct plat_stmmacenet_data { struct clk *clk_ptp_ref; unsigned int clk_ptp_rate; unsigned int clk_ref_rate; + s32 ptp_max_adj; struct reset_control *stmmac_rst; struct stmmac_axi *axi; int has_gmac4; -- cgit v1.2.3 From 00679b631eddaa0aa0ceba719fcb1f60c65da5a3 Mon Sep 17 00:00:00 2001 From: Michael Guralnik Date: Mon, 19 Aug 2019 15:08:13 +0300 Subject: net/mlx5: Set ODP capabilities for DC transport to max In mlx5_core initialization, query max ODP capabilities for DC transport from FW and set as current capabilities. Signed-off-by: Michael Guralnik Signed-off-by: Leon Romanovsky --- drivers/net/ethernet/mellanox/mlx5/core/main.c | 6 ++++++ include/linux/mlx5/mlx5_ifc.h | 4 +++- 2 files changed, 9 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/drivers/net/ethernet/mellanox/mlx5/core/main.c b/drivers/net/ethernet/mellanox/mlx5/core/main.c index fa0e991f1983..7f70ecb1db6d 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/main.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/main.c @@ -495,6 +495,12 @@ static int handle_hca_cap_odp(struct mlx5_core_dev *dev) ODP_CAP_SET_MAX(dev, xrc_odp_caps.write); ODP_CAP_SET_MAX(dev, xrc_odp_caps.read); ODP_CAP_SET_MAX(dev, xrc_odp_caps.atomic); + ODP_CAP_SET_MAX(dev, dc_odp_caps.srq_receive); + ODP_CAP_SET_MAX(dev, dc_odp_caps.send); + ODP_CAP_SET_MAX(dev, dc_odp_caps.receive); + ODP_CAP_SET_MAX(dev, dc_odp_caps.write); + ODP_CAP_SET_MAX(dev, dc_odp_caps.read); + ODP_CAP_SET_MAX(dev, dc_odp_caps.atomic); if (do_set) err = set_caps(dev, set_ctx, set_sz, diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h index 1e55cf73e88c..4e278114d8b3 100644 --- a/include/linux/mlx5/mlx5_ifc.h +++ b/include/linux/mlx5/mlx5_ifc.h @@ -948,7 +948,9 @@ struct mlx5_ifc_odp_cap_bits { struct mlx5_ifc_odp_per_transport_service_cap_bits xrc_odp_caps; - u8 reserved_at_100[0x700]; + struct mlx5_ifc_odp_per_transport_service_cap_bits dc_odp_caps; + + u8 reserved_at_120[0x6E0]; }; struct mlx5_ifc_calc_op { -- cgit v1.2.3 From 2d4c849530a9771ed38d4046d2b631c1a4e2f9a6 Mon Sep 17 00:00:00 2001 From: Sudarsana Reddy Kalluru Date: Fri, 30 Aug 2019 00:42:03 -0700 Subject: qed: Add APIs for reading config id attributes. The patch adds driver support for reading the config id attributes from NVM flash partition. Signed-off-by: Sudarsana Reddy Kalluru Signed-off-by: Ariel Elior Signed-off-by: David S. Miller --- drivers/net/ethernet/qlogic/qed/qed_main.c | 27 +++++++++++++++++++++++++++ drivers/net/ethernet/qlogic/qed/qed_mcp.c | 29 +++++++++++++++++++++++++++++ drivers/net/ethernet/qlogic/qed/qed_mcp.h | 15 +++++++++++++++ include/linux/qed/qed_if.h | 11 +++++++++++ 4 files changed, 82 insertions(+) (limited to 'include/linux') diff --git a/drivers/net/ethernet/qlogic/qed/qed_main.c b/drivers/net/ethernet/qlogic/qed/qed_main.c index 7891f8c5a1bc..c9a757177366 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_main.c +++ b/drivers/net/ethernet/qlogic/qed/qed_main.c @@ -69,6 +69,8 @@ #define QED_RDMA_SRQS QED_ROCE_QPS #define QED_NVM_CFG_SET_FLAGS 0xE #define QED_NVM_CFG_SET_PF_FLAGS 0x1E +#define QED_NVM_CFG_GET_FLAGS 0xA +#define QED_NVM_CFG_GET_PF_FLAGS 0x1A static char version[] = "QLogic FastLinQ 4xxxx Core Module qed " DRV_MODULE_VERSION "\n"; @@ -2298,6 +2300,30 @@ static int qed_nvm_flash_cfg_write(struct qed_dev *cdev, const u8 **data) return rc; } +static int qed_nvm_flash_cfg_read(struct qed_dev *cdev, u8 **data, + u32 cmd, u32 entity_id) +{ + struct qed_hwfn *hwfn = QED_LEADING_HWFN(cdev); + struct qed_ptt *ptt; + u32 flags, len; + int rc = 0; + + ptt = qed_ptt_acquire(hwfn); + if (!ptt) + return -EAGAIN; + + DP_VERBOSE(cdev, NETIF_MSG_DRV, + "Read config cmd = %d entity id %d\n", cmd, entity_id); + flags = entity_id ? QED_NVM_CFG_GET_PF_FLAGS : QED_NVM_CFG_GET_FLAGS; + rc = qed_mcp_nvm_get_cfg(hwfn, ptt, cmd, entity_id, flags, *data, &len); + if (rc) + DP_ERR(cdev, "Error %d reading %d\n", rc, cmd); + + qed_ptt_release(hwfn, ptt); + + return rc; +} + static int qed_nvm_flash(struct qed_dev *cdev, const char *name) { const struct firmware *image; @@ -2610,6 +2636,7 @@ const struct qed_common_ops qed_common_ops_pass = { .db_recovery_del = &qed_db_recovery_del, .read_module_eeprom = &qed_read_module_eeprom, .get_affin_hwfn_idx = &qed_get_affin_hwfn_idx, + .read_nvm_cfg = &qed_nvm_flash_cfg_read, }; void qed_get_protocol_stats(struct qed_dev *cdev, diff --git a/drivers/net/ethernet/qlogic/qed/qed_mcp.c b/drivers/net/ethernet/qlogic/qed/qed_mcp.c index 89462c4a5022..36ddb89856a8 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_mcp.c +++ b/drivers/net/ethernet/qlogic/qed/qed_mcp.c @@ -3751,6 +3751,35 @@ int qed_mcp_get_ppfid_bitmap(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt) return 0; } +int qed_mcp_nvm_get_cfg(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt, + u16 option_id, u8 entity_id, u16 flags, u8 *p_buf, + u32 *p_len) +{ + u32 mb_param = 0, resp, param; + int rc; + + QED_MFW_SET_FIELD(mb_param, DRV_MB_PARAM_NVM_CFG_OPTION_ID, option_id); + if (flags & QED_NVM_CFG_OPTION_INIT) + QED_MFW_SET_FIELD(mb_param, + DRV_MB_PARAM_NVM_CFG_OPTION_INIT, 1); + if (flags & QED_NVM_CFG_OPTION_FREE) + QED_MFW_SET_FIELD(mb_param, + DRV_MB_PARAM_NVM_CFG_OPTION_FREE, 1); + if (flags & QED_NVM_CFG_OPTION_ENTITY_SEL) { + QED_MFW_SET_FIELD(mb_param, + DRV_MB_PARAM_NVM_CFG_OPTION_ENTITY_SEL, 1); + QED_MFW_SET_FIELD(mb_param, + DRV_MB_PARAM_NVM_CFG_OPTION_ENTITY_ID, + entity_id); + } + + rc = qed_mcp_nvm_rd_cmd(p_hwfn, p_ptt, + DRV_MSG_CODE_GET_NVM_CFG_OPTION, + mb_param, &resp, ¶m, p_len, (u32 *)p_buf); + + return rc; +} + int qed_mcp_nvm_set_cfg(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt, u16 option_id, u8 entity_id, u16 flags, u8 *p_buf, u32 len) diff --git a/drivers/net/ethernet/qlogic/qed/qed_mcp.h b/drivers/net/ethernet/qlogic/qed/qed_mcp.h index 83649a82977b..9c4c2763de8d 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_mcp.h +++ b/drivers/net/ethernet/qlogic/qed/qed_mcp.h @@ -1208,6 +1208,21 @@ int qed_mcp_get_engine_config(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt); */ int qed_mcp_get_ppfid_bitmap(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt); +/** + * @brief Get NVM config attribute value. + * + * @param p_hwfn + * @param p_ptt + * @param option_id + * @param entity_id + * @param flags + * @param p_buf + * @param p_len + */ +int qed_mcp_nvm_get_cfg(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt, + u16 option_id, u8 entity_id, u16 flags, u8 *p_buf, + u32 *p_len); + /** * @brief Set NVM config attribute value. * diff --git a/include/linux/qed/qed_if.h b/include/linux/qed/qed_if.h index e366399874f3..06fd9580c9e5 100644 --- a/include/linux/qed/qed_if.h +++ b/include/linux/qed/qed_if.h @@ -1132,6 +1132,17 @@ struct qed_common_ops { * @param cdev */ u8 (*get_affin_hwfn_idx)(struct qed_dev *cdev); + +/** + * @brief read_nvm_cfg - Read NVM config attribute value. + * @param cdev + * @param buf - buffer + * @param cmd - NVM CFG command id + * @param entity_id - Entity id + * + */ + int (*read_nvm_cfg)(struct qed_dev *cdev, u8 **buf, u32 cmd, + u32 entity_id); }; #define MASK_FIELD(_name, _value) \ -- cgit v1.2.3 From 3b86bd076284724489381e391f84a34078b3d5bc Mon Sep 17 00:00:00 2001 From: Sudarsana Reddy Kalluru Date: Fri, 30 Aug 2019 00:42:05 -0700 Subject: qed: Add APIs for configuring grc dump config flags. The patch adds driver support for configuring the grc dump config flags. Signed-off-by: Sudarsana Reddy Kalluru Signed-off-by: Ariel Elior Signed-off-by: David S. Miller --- drivers/net/ethernet/qlogic/qed/qed_debug.c | 82 +++++++++++++++++++++++++++++ drivers/net/ethernet/qlogic/qed/qed_hsi.h | 15 ++++++ drivers/net/ethernet/qlogic/qed/qed_main.c | 21 ++++++++ include/linux/qed/qed_if.h | 9 ++++ 4 files changed, 127 insertions(+) (limited to 'include/linux') diff --git a/drivers/net/ethernet/qlogic/qed/qed_debug.c b/drivers/net/ethernet/qlogic/qed/qed_debug.c index 5ea6c4fc6050..859caa6c1a1f 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_debug.c +++ b/drivers/net/ethernet/qlogic/qed/qed_debug.c @@ -1756,6 +1756,15 @@ static u32 qed_read_unaligned_dword(u8 *buf) return dword; } +/* Sets the value of the specified GRC param */ +static void qed_grc_set_param(struct qed_hwfn *p_hwfn, + enum dbg_grc_params grc_param, u32 val) +{ + struct dbg_tools_data *dev_data = &p_hwfn->dbg_info; + + dev_data->grc.param_val[grc_param] = val; +} + /* Returns the value of the specified GRC param */ static u32 qed_grc_get_param(struct qed_hwfn *p_hwfn, enum dbg_grc_params grc_param) @@ -5119,6 +5128,69 @@ bool qed_read_fw_info(struct qed_hwfn *p_hwfn, return false; } +enum dbg_status qed_dbg_grc_config(struct qed_hwfn *p_hwfn, + struct qed_ptt *p_ptt, + enum dbg_grc_params grc_param, u32 val) +{ + enum dbg_status status; + int i; + + DP_VERBOSE(p_hwfn, QED_MSG_DEBUG, + "dbg_grc_config: paramId = %d, val = %d\n", grc_param, val); + + status = qed_dbg_dev_init(p_hwfn, p_ptt); + if (status != DBG_STATUS_OK) + return status; + + /* Initializes the GRC parameters (if not initialized). Needed in order + * to set the default parameter values for the first time. + */ + qed_dbg_grc_init_params(p_hwfn); + + if (grc_param >= MAX_DBG_GRC_PARAMS) + return DBG_STATUS_INVALID_ARGS; + if (val < s_grc_param_defs[grc_param].min || + val > s_grc_param_defs[grc_param].max) + return DBG_STATUS_INVALID_ARGS; + + if (s_grc_param_defs[grc_param].is_preset) { + /* Preset param */ + + /* Disabling a preset is not allowed. Call + * dbg_grc_set_params_default instead. + */ + if (!val) + return DBG_STATUS_INVALID_ARGS; + + /* Update all params with the preset values */ + for (i = 0; i < MAX_DBG_GRC_PARAMS; i++) { + u32 preset_val; + + /* Skip persistent params */ + if (s_grc_param_defs[i].is_persistent) + continue; + + /* Find preset value */ + if (grc_param == DBG_GRC_PARAM_EXCLUDE_ALL) + preset_val = + s_grc_param_defs[i].exclude_all_preset_val; + else if (grc_param == DBG_GRC_PARAM_CRASH) + preset_val = + s_grc_param_defs[i].crash_preset_val; + else + return DBG_STATUS_INVALID_ARGS; + + qed_grc_set_param(p_hwfn, + (enum dbg_grc_params)i, preset_val); + } + } else { + /* Regular param - set its value */ + qed_grc_set_param(p_hwfn, grc_param, val); + } + + return DBG_STATUS_OK; +} + /* Assign default GRC param values */ void qed_dbg_grc_set_params_default(struct qed_hwfn *p_hwfn) { @@ -7997,9 +8069,16 @@ static u32 qed_calc_regdump_header(enum debug_print_features feature, int qed_dbg_all_data(struct qed_dev *cdev, void *buffer) { u8 cur_engine, omit_engine = 0, org_engine; + struct qed_hwfn *p_hwfn = + &cdev->hwfns[cdev->dbg_params.engine_for_debug]; + struct dbg_tools_data *dev_data = &p_hwfn->dbg_info; + int grc_params[MAX_DBG_GRC_PARAMS], i; u32 offset = 0, feature_size; int rc; + for (i = 0; i < MAX_DBG_GRC_PARAMS; i++) + grc_params[i] = dev_data->grc.param_val[i]; + if (cdev->num_hwfns == 1) omit_engine = 1; @@ -8087,6 +8166,9 @@ int qed_dbg_all_data(struct qed_dev *cdev, void *buffer) rc); } + for (i = 0; i < MAX_DBG_GRC_PARAMS; i++) + dev_data->grc.param_val[i] = grc_params[i]; + /* GRC dump - must be last because when mcp stuck it will * clutter idle_chk, reg_fifo, ... */ diff --git a/drivers/net/ethernet/qlogic/qed/qed_hsi.h b/drivers/net/ethernet/qlogic/qed/qed_hsi.h index 557a12ef9815..cf3ceb62e397 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_hsi.h +++ b/drivers/net/ethernet/qlogic/qed/qed_hsi.h @@ -3024,6 +3024,21 @@ void qed_read_regs(struct qed_hwfn *p_hwfn, */ bool qed_read_fw_info(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt, struct fw_info *fw_info); +/** + * @brief qed_dbg_grc_config - Sets the value of a GRC parameter. + * + * @param p_hwfn - HW device data + * @param grc_param - GRC parameter + * @param val - Value to set. + * + * @return error if one of the following holds: + * - the version wasn't set + * - grc_param is invalid + * - val is outside the allowed boundaries + */ +enum dbg_status qed_dbg_grc_config(struct qed_hwfn *p_hwfn, + struct qed_ptt *p_ptt, + enum dbg_grc_params grc_param, u32 val); /** * @brief qed_dbg_grc_set_params_default - Reverts all GRC parameters to their diff --git a/drivers/net/ethernet/qlogic/qed/qed_main.c b/drivers/net/ethernet/qlogic/qed/qed_main.c index c9a757177366..ac1511a834d8 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_main.c +++ b/drivers/net/ethernet/qlogic/qed/qed_main.c @@ -2583,6 +2583,26 @@ static int qed_read_module_eeprom(struct qed_dev *cdev, char *buf, return rc; } +static int qed_set_grc_config(struct qed_dev *cdev, u32 cfg_id, u32 val) +{ + struct qed_hwfn *hwfn = QED_LEADING_HWFN(cdev); + struct qed_ptt *ptt; + int rc = 0; + + if (IS_VF(cdev)) + return 0; + + ptt = qed_ptt_acquire(hwfn); + if (!ptt) + return -EAGAIN; + + rc = qed_dbg_grc_config(hwfn, ptt, cfg_id, val); + + qed_ptt_release(hwfn, ptt); + + return rc; +} + static u8 qed_get_affin_hwfn_idx(struct qed_dev *cdev) { return QED_AFFIN_HWFN_IDX(cdev); @@ -2637,6 +2657,7 @@ const struct qed_common_ops qed_common_ops_pass = { .read_module_eeprom = &qed_read_module_eeprom, .get_affin_hwfn_idx = &qed_get_affin_hwfn_idx, .read_nvm_cfg = &qed_nvm_flash_cfg_read, + .set_grc_config = &qed_set_grc_config, }; void qed_get_protocol_stats(struct qed_dev *cdev, diff --git a/include/linux/qed/qed_if.h b/include/linux/qed/qed_if.h index 06fd9580c9e5..e35463860c84 100644 --- a/include/linux/qed/qed_if.h +++ b/include/linux/qed/qed_if.h @@ -1143,6 +1143,15 @@ struct qed_common_ops { */ int (*read_nvm_cfg)(struct qed_dev *cdev, u8 **buf, u32 cmd, u32 entity_id); + +/** + * @brief set_grc_config - Configure value for grc config id. + * @param cdev + * @param cfg_id - grc config id + * @param val - grc config value + * + */ + int (*set_grc_config)(struct qed_dev *cdev, u32 cfg_id, u32 val); }; #define MASK_FIELD(_name, _value) \ -- cgit v1.2.3 From c9b9dcb430b3cd0ad2b04c360c4e528d73430481 Mon Sep 17 00:00:00 2001 From: Ariel Levkovich Date: Thu, 29 Aug 2019 23:42:30 +0000 Subject: net/mlx5: Move device memory management to mlx5_core Move the device memory allocation and deallocation commands SW ICM memory to mlx5_core to expose this API for all mlx5_core users. This comes as preparation for supporting SW steering in kernel where it will be required to allocate and register device memory for direct rule insertion. In addition, an API to register this device memory for future remote access operations is introduced using the create_mkey commands. Signed-off-by: Ariel Levkovich Reviewed-by: Mark Bloch Signed-off-by: Saeed Mahameed --- drivers/infiniband/hw/mlx5/cmd.c | 130 ------------ drivers/infiniband/hw/mlx5/cmd.h | 4 - drivers/infiniband/hw/mlx5/main.c | 102 +++------- drivers/infiniband/hw/mlx5/mlx5_ib.h | 2 - drivers/net/ethernet/mellanox/mlx5/core/Makefile | 2 +- drivers/net/ethernet/mellanox/mlx5/core/lib/dm.c | 223 +++++++++++++++++++++ drivers/net/ethernet/mellanox/mlx5/core/main.c | 5 + .../net/ethernet/mellanox/mlx5/core/mlx5_core.h | 3 + include/linux/mlx5/driver.h | 14 ++ 9 files changed, 276 insertions(+), 209 deletions(-) create mode 100644 drivers/net/ethernet/mellanox/mlx5/core/lib/dm.c (limited to 'include/linux') diff --git a/drivers/infiniband/hw/mlx5/cmd.c b/drivers/infiniband/hw/mlx5/cmd.c index 6c8645033102..4937947400cd 100644 --- a/drivers/infiniband/hw/mlx5/cmd.c +++ b/drivers/infiniband/hw/mlx5/cmd.c @@ -186,136 +186,6 @@ int mlx5_cmd_dealloc_memic(struct mlx5_dm *dm, phys_addr_t addr, u64 length) return err; } -int mlx5_cmd_alloc_sw_icm(struct mlx5_dm *dm, int type, u64 length, - u16 uid, phys_addr_t *addr, u32 *obj_id) -{ - struct mlx5_core_dev *dev = dm->dev; - u32 out[MLX5_ST_SZ_DW(general_obj_out_cmd_hdr)] = {}; - u32 in[MLX5_ST_SZ_DW(create_sw_icm_in)] = {}; - unsigned long *block_map; - u64 icm_start_addr; - u32 log_icm_size; - u32 num_blocks; - u32 max_blocks; - u64 block_idx; - void *sw_icm; - int ret; - - MLX5_SET(general_obj_in_cmd_hdr, in, opcode, - MLX5_CMD_OP_CREATE_GENERAL_OBJECT); - MLX5_SET(general_obj_in_cmd_hdr, in, obj_type, MLX5_OBJ_TYPE_SW_ICM); - MLX5_SET(general_obj_in_cmd_hdr, in, uid, uid); - - switch (type) { - case MLX5_IB_UAPI_DM_TYPE_STEERING_SW_ICM: - icm_start_addr = MLX5_CAP64_DEV_MEM(dev, - steering_sw_icm_start_address); - log_icm_size = MLX5_CAP_DEV_MEM(dev, log_steering_sw_icm_size); - block_map = dm->steering_sw_icm_alloc_blocks; - break; - case MLX5_IB_UAPI_DM_TYPE_HEADER_MODIFY_SW_ICM: - icm_start_addr = MLX5_CAP64_DEV_MEM(dev, - header_modify_sw_icm_start_address); - log_icm_size = MLX5_CAP_DEV_MEM(dev, - log_header_modify_sw_icm_size); - block_map = dm->header_modify_sw_icm_alloc_blocks; - break; - default: - return -EINVAL; - } - - num_blocks = (length + MLX5_SW_ICM_BLOCK_SIZE(dev) - 1) >> - MLX5_LOG_SW_ICM_BLOCK_SIZE(dev); - max_blocks = BIT(log_icm_size - MLX5_LOG_SW_ICM_BLOCK_SIZE(dev)); - spin_lock(&dm->lock); - block_idx = bitmap_find_next_zero_area(block_map, - max_blocks, - 0, - num_blocks, 0); - - if (block_idx < max_blocks) - bitmap_set(block_map, - block_idx, num_blocks); - - spin_unlock(&dm->lock); - - if (block_idx >= max_blocks) - return -ENOMEM; - - sw_icm = MLX5_ADDR_OF(create_sw_icm_in, in, sw_icm); - icm_start_addr += block_idx << MLX5_LOG_SW_ICM_BLOCK_SIZE(dev); - MLX5_SET64(sw_icm, sw_icm, sw_icm_start_addr, - icm_start_addr); - MLX5_SET(sw_icm, sw_icm, log_sw_icm_size, ilog2(length)); - - ret = mlx5_cmd_exec(dev, in, sizeof(in), out, sizeof(out)); - if (ret) { - spin_lock(&dm->lock); - bitmap_clear(block_map, - block_idx, num_blocks); - spin_unlock(&dm->lock); - - return ret; - } - - *addr = icm_start_addr; - *obj_id = MLX5_GET(general_obj_out_cmd_hdr, out, obj_id); - - return 0; -} - -int mlx5_cmd_dealloc_sw_icm(struct mlx5_dm *dm, int type, u64 length, - u16 uid, phys_addr_t addr, u32 obj_id) -{ - struct mlx5_core_dev *dev = dm->dev; - u32 out[MLX5_ST_SZ_DW(general_obj_out_cmd_hdr)] = {}; - u32 in[MLX5_ST_SZ_DW(general_obj_in_cmd_hdr)] = {}; - unsigned long *block_map; - u32 num_blocks; - u64 start_idx; - int err; - - num_blocks = (length + MLX5_SW_ICM_BLOCK_SIZE(dev) - 1) >> - MLX5_LOG_SW_ICM_BLOCK_SIZE(dev); - - switch (type) { - case MLX5_IB_UAPI_DM_TYPE_STEERING_SW_ICM: - start_idx = - (addr - MLX5_CAP64_DEV_MEM( - dev, steering_sw_icm_start_address)) >> - MLX5_LOG_SW_ICM_BLOCK_SIZE(dev); - block_map = dm->steering_sw_icm_alloc_blocks; - break; - case MLX5_IB_UAPI_DM_TYPE_HEADER_MODIFY_SW_ICM: - start_idx = - (addr - - MLX5_CAP64_DEV_MEM( - dev, header_modify_sw_icm_start_address)) >> - MLX5_LOG_SW_ICM_BLOCK_SIZE(dev); - block_map = dm->header_modify_sw_icm_alloc_blocks; - break; - default: - return -EINVAL; - } - - MLX5_SET(general_obj_in_cmd_hdr, in, opcode, - MLX5_CMD_OP_DESTROY_GENERAL_OBJECT); - MLX5_SET(general_obj_in_cmd_hdr, in, obj_type, MLX5_OBJ_TYPE_SW_ICM); - MLX5_SET(general_obj_in_cmd_hdr, in, obj_id, obj_id); - MLX5_SET(general_obj_in_cmd_hdr, in, uid, uid); - - err = mlx5_cmd_exec(dev, in, sizeof(in), out, sizeof(out)); - if (err) - return err; - - spin_lock(&dm->lock); - bitmap_clear(block_map, - start_idx, num_blocks); - spin_unlock(&dm->lock); - - return 0; -} - int mlx5_cmd_query_ext_ppcnt_counters(struct mlx5_core_dev *dev, void *out) { u32 in[MLX5_ST_SZ_DW(ppcnt_reg)] = {}; diff --git a/drivers/infiniband/hw/mlx5/cmd.h b/drivers/infiniband/hw/mlx5/cmd.h index 0572dcba6eae..169cab4915e3 100644 --- a/drivers/infiniband/hw/mlx5/cmd.h +++ b/drivers/infiniband/hw/mlx5/cmd.h @@ -65,8 +65,4 @@ int mlx5_cmd_alloc_q_counter(struct mlx5_core_dev *dev, u16 *counter_id, u16 uid); int mlx5_cmd_mad_ifc(struct mlx5_core_dev *dev, const void *inb, void *outb, u16 opmod, u8 port); -int mlx5_cmd_alloc_sw_icm(struct mlx5_dm *dm, int type, u64 length, - u16 uid, phys_addr_t *addr, u32 *obj_id); -int mlx5_cmd_dealloc_sw_icm(struct mlx5_dm *dm, int type, u64 length, - u16 uid, phys_addr_t addr, u32 obj_id); #endif /* MLX5_IB_CMD_H */ diff --git a/drivers/infiniband/hw/mlx5/main.c b/drivers/infiniband/hw/mlx5/main.c index c2a5780cb394..42fdbbea06f0 100644 --- a/drivers/infiniband/hw/mlx5/main.c +++ b/drivers/infiniband/hw/mlx5/main.c @@ -2280,6 +2280,7 @@ static inline int check_dm_type_support(struct mlx5_ib_dev *dev, return -EOPNOTSUPP; break; case MLX5_IB_UAPI_DM_TYPE_STEERING_SW_ICM: + case MLX5_IB_UAPI_DM_TYPE_HEADER_MODIFY_SW_ICM: if (!capable(CAP_SYS_RAWIO) || !capable(CAP_NET_RAW)) return -EPERM; @@ -2344,20 +2345,20 @@ static int handle_alloc_dm_sw_icm(struct ib_ucontext *ctx, struct uverbs_attr_bundle *attrs, int type) { - struct mlx5_dm *dm_db = &to_mdev(ctx->device)->dm; + struct mlx5_core_dev *dev = to_mdev(ctx->device)->mdev; u64 act_size; int err; /* Allocation size must a multiple of the basic block size * and a power of 2. */ - act_size = round_up(attr->length, MLX5_SW_ICM_BLOCK_SIZE(dm_db->dev)); + act_size = round_up(attr->length, MLX5_SW_ICM_BLOCK_SIZE(dev)); act_size = roundup_pow_of_two(act_size); dm->size = act_size; - err = mlx5_cmd_alloc_sw_icm(dm_db, type, act_size, - to_mucontext(ctx)->devx_uid, &dm->dev_addr, - &dm->icm_dm.obj_id); + err = mlx5_dm_sw_icm_alloc(dev, type, act_size, + to_mucontext(ctx)->devx_uid, &dm->dev_addr, + &dm->icm_dm.obj_id); if (err) return err; @@ -2365,9 +2366,9 @@ static int handle_alloc_dm_sw_icm(struct ib_ucontext *ctx, MLX5_IB_ATTR_ALLOC_DM_RESP_START_OFFSET, &dm->dev_addr, sizeof(dm->dev_addr)); if (err) - mlx5_cmd_dealloc_sw_icm(dm_db, type, dm->size, - to_mucontext(ctx)->devx_uid, - dm->dev_addr, dm->icm_dm.obj_id); + mlx5_dm_sw_icm_dealloc(dev, type, dm->size, + to_mucontext(ctx)->devx_uid, dm->dev_addr, + dm->icm_dm.obj_id); return err; } @@ -2407,8 +2408,14 @@ struct ib_dm *mlx5_ib_alloc_dm(struct ib_device *ibdev, attrs); break; case MLX5_IB_UAPI_DM_TYPE_STEERING_SW_ICM: + err = handle_alloc_dm_sw_icm(context, dm, + attr, attrs, + MLX5_SW_ICM_TYPE_STEERING); + break; case MLX5_IB_UAPI_DM_TYPE_HEADER_MODIFY_SW_ICM: - err = handle_alloc_dm_sw_icm(context, dm, attr, attrs, type); + err = handle_alloc_dm_sw_icm(context, dm, + attr, attrs, + MLX5_SW_ICM_TYPE_HEADER_MODIFY); break; default: err = -EOPNOTSUPP; @@ -2428,6 +2435,7 @@ int mlx5_ib_dealloc_dm(struct ib_dm *ibdm, struct uverbs_attr_bundle *attrs) { struct mlx5_ib_ucontext *ctx = rdma_udata_to_drv_context( &attrs->driver_udata, struct mlx5_ib_ucontext, ibucontext); + struct mlx5_core_dev *dev = to_mdev(ibdm->device)->mdev; struct mlx5_dm *dm_db = &to_mdev(ibdm->device)->dm; struct mlx5_ib_dm *dm = to_mdm(ibdm); u32 page_idx; @@ -2439,19 +2447,23 @@ int mlx5_ib_dealloc_dm(struct ib_dm *ibdm, struct uverbs_attr_bundle *attrs) if (ret) return ret; - page_idx = (dm->dev_addr - - pci_resource_start(dm_db->dev->pdev, 0) - - MLX5_CAP64_DEV_MEM(dm_db->dev, - memic_bar_start_addr)) >> - PAGE_SHIFT; + page_idx = (dm->dev_addr - pci_resource_start(dev->pdev, 0) - + MLX5_CAP64_DEV_MEM(dev, memic_bar_start_addr)) >> + PAGE_SHIFT; bitmap_clear(ctx->dm_pages, page_idx, DIV_ROUND_UP(dm->size, PAGE_SIZE)); break; case MLX5_IB_UAPI_DM_TYPE_STEERING_SW_ICM: + ret = mlx5_dm_sw_icm_dealloc(dev, MLX5_SW_ICM_TYPE_STEERING, + dm->size, ctx->devx_uid, dm->dev_addr, + dm->icm_dm.obj_id); + if (ret) + return ret; + break; case MLX5_IB_UAPI_DM_TYPE_HEADER_MODIFY_SW_ICM: - ret = mlx5_cmd_dealloc_sw_icm(dm_db, dm->type, dm->size, - ctx->devx_uid, dm->dev_addr, - dm->icm_dm.obj_id); + ret = mlx5_dm_sw_icm_dealloc(dev, MLX5_SW_ICM_TYPE_HEADER_MODIFY, + dm->size, ctx->devx_uid, dm->dev_addr, + dm->icm_dm.obj_id); if (ret) return ret; break; @@ -6097,8 +6109,6 @@ static struct ib_counters *mlx5_ib_create_counters(struct ib_device *device, static void mlx5_ib_stage_init_cleanup(struct mlx5_ib_dev *dev) { - struct mlx5_core_dev *mdev = dev->mdev; - mlx5_ib_cleanup_multiport_master(dev); if (IS_ENABLED(CONFIG_INFINIBAND_ON_DEMAND_PAGING)) { srcu_barrier(&dev->mr_srcu); @@ -6106,29 +6116,11 @@ static void mlx5_ib_stage_init_cleanup(struct mlx5_ib_dev *dev) } WARN_ON(!bitmap_empty(dev->dm.memic_alloc_pages, MLX5_MAX_MEMIC_PAGES)); - - WARN_ON(dev->dm.steering_sw_icm_alloc_blocks && - !bitmap_empty( - dev->dm.steering_sw_icm_alloc_blocks, - BIT(MLX5_CAP_DEV_MEM(mdev, log_steering_sw_icm_size) - - MLX5_LOG_SW_ICM_BLOCK_SIZE(mdev)))); - - kfree(dev->dm.steering_sw_icm_alloc_blocks); - - WARN_ON(dev->dm.header_modify_sw_icm_alloc_blocks && - !bitmap_empty(dev->dm.header_modify_sw_icm_alloc_blocks, - BIT(MLX5_CAP_DEV_MEM( - mdev, log_header_modify_sw_icm_size) - - MLX5_LOG_SW_ICM_BLOCK_SIZE(mdev)))); - - kfree(dev->dm.header_modify_sw_icm_alloc_blocks); } static int mlx5_ib_stage_init_init(struct mlx5_ib_dev *dev) { struct mlx5_core_dev *mdev = dev->mdev; - u64 header_modify_icm_blocks = 0; - u64 steering_icm_blocks = 0; int err; int i; @@ -6173,51 +6165,17 @@ static int mlx5_ib_stage_init_init(struct mlx5_ib_dev *dev) INIT_LIST_HEAD(&dev->qp_list); spin_lock_init(&dev->reset_flow_resource_lock); - if (MLX5_CAP_GEN_64(mdev, general_obj_types) & - MLX5_GENERAL_OBJ_TYPES_CAP_SW_ICM) { - if (MLX5_CAP64_DEV_MEM(mdev, steering_sw_icm_start_address)) { - steering_icm_blocks = - BIT(MLX5_CAP_DEV_MEM(mdev, - log_steering_sw_icm_size) - - MLX5_LOG_SW_ICM_BLOCK_SIZE(mdev)); - - dev->dm.steering_sw_icm_alloc_blocks = - kcalloc(BITS_TO_LONGS(steering_icm_blocks), - sizeof(unsigned long), GFP_KERNEL); - if (!dev->dm.steering_sw_icm_alloc_blocks) - goto err_mp; - } - - if (MLX5_CAP64_DEV_MEM(mdev, - header_modify_sw_icm_start_address)) { - header_modify_icm_blocks = BIT( - MLX5_CAP_DEV_MEM( - mdev, log_header_modify_sw_icm_size) - - MLX5_LOG_SW_ICM_BLOCK_SIZE(mdev)); - - dev->dm.header_modify_sw_icm_alloc_blocks = - kcalloc(BITS_TO_LONGS(header_modify_icm_blocks), - sizeof(unsigned long), GFP_KERNEL); - if (!dev->dm.header_modify_sw_icm_alloc_blocks) - goto err_dm; - } - } - spin_lock_init(&dev->dm.lock); dev->dm.dev = mdev; if (IS_ENABLED(CONFIG_INFINIBAND_ON_DEMAND_PAGING)) { err = init_srcu_struct(&dev->mr_srcu); if (err) - goto err_dm; + goto err_mp; } return 0; -err_dm: - kfree(dev->dm.steering_sw_icm_alloc_blocks); - kfree(dev->dm.header_modify_sw_icm_alloc_blocks); - err_mp: mlx5_ib_cleanup_multiport_master(dev); diff --git a/drivers/infiniband/hw/mlx5/mlx5_ib.h b/drivers/infiniband/hw/mlx5/mlx5_ib.h index c482f19958b3..afd69ba33b2b 100644 --- a/drivers/infiniband/hw/mlx5/mlx5_ib.h +++ b/drivers/infiniband/hw/mlx5/mlx5_ib.h @@ -880,8 +880,6 @@ struct mlx5_dm { */ spinlock_t lock; DECLARE_BITMAP(memic_alloc_pages, MLX5_MAX_MEMIC_PAGES); - unsigned long *steering_sw_icm_alloc_blocks; - unsigned long *header_modify_sw_icm_alloc_blocks; }; struct mlx5_read_counters_attr { diff --git a/drivers/net/ethernet/mellanox/mlx5/core/Makefile b/drivers/net/ethernet/mellanox/mlx5/core/Makefile index 57d2cc666fe3..4eb52e8500c3 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/Makefile +++ b/drivers/net/ethernet/mellanox/mlx5/core/Makefile @@ -15,7 +15,7 @@ mlx5_core-y := main.o cmd.o debugfs.o fw.o eq.o uar.o pagealloc.o \ health.o mcg.o cq.o alloc.o qp.o port.o mr.o pd.o \ transobj.o vport.o sriov.o fs_cmd.o fs_core.o pci_irq.o \ fs_counters.o rl.o lag.o dev.o events.o wq.o lib/gid.o \ - lib/devcom.o lib/pci_vsc.o diag/fs_tracepoint.o \ + lib/devcom.o lib/pci_vsc.o lib/dm.o diag/fs_tracepoint.o \ diag/fw_tracer.o diag/crdump.o devlink.o # diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lib/dm.c b/drivers/net/ethernet/mellanox/mlx5/core/lib/dm.c new file mode 100644 index 000000000000..e065c2f68f5a --- /dev/null +++ b/drivers/net/ethernet/mellanox/mlx5/core/lib/dm.c @@ -0,0 +1,223 @@ +// SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB +// Copyright (c) 2019 Mellanox Technologies + +#include +#include + +#include "mlx5_core.h" +#include "lib/mlx5.h" + +struct mlx5_dm { + /* protect access to icm bitmask */ + spinlock_t lock; + unsigned long *steering_sw_icm_alloc_blocks; + unsigned long *header_modify_sw_icm_alloc_blocks; +}; + +struct mlx5_dm *mlx5_dm_create(struct mlx5_core_dev *dev) +{ + u64 header_modify_icm_blocks = 0; + u64 steering_icm_blocks = 0; + struct mlx5_dm *dm; + + if (!(MLX5_CAP_GEN_64(dev, general_obj_types) & MLX5_GENERAL_OBJ_TYPES_CAP_SW_ICM)) + return 0; + + dm = kzalloc(sizeof(*dm), GFP_KERNEL); + if (!dm) + return ERR_PTR(-ENOMEM); + + spin_lock_init(&dm->lock); + + if (MLX5_CAP64_DEV_MEM(dev, steering_sw_icm_start_address)) { + steering_icm_blocks = + BIT(MLX5_CAP_DEV_MEM(dev, log_steering_sw_icm_size) - + MLX5_LOG_SW_ICM_BLOCK_SIZE(dev)); + + dm->steering_sw_icm_alloc_blocks = + kcalloc(BITS_TO_LONGS(steering_icm_blocks), + sizeof(unsigned long), GFP_KERNEL); + if (!dm->steering_sw_icm_alloc_blocks) + goto err_steering; + } + + if (MLX5_CAP64_DEV_MEM(dev, header_modify_sw_icm_start_address)) { + header_modify_icm_blocks = + BIT(MLX5_CAP_DEV_MEM(dev, log_header_modify_sw_icm_size) - + MLX5_LOG_SW_ICM_BLOCK_SIZE(dev)); + + dm->header_modify_sw_icm_alloc_blocks = + kcalloc(BITS_TO_LONGS(header_modify_icm_blocks), + sizeof(unsigned long), GFP_KERNEL); + if (!dm->header_modify_sw_icm_alloc_blocks) + goto err_modify_hdr; + } + + return dm; + +err_modify_hdr: + kfree(dm->steering_sw_icm_alloc_blocks); + +err_steering: + kfree(dm); + + return ERR_PTR(-ENOMEM); +} + +void mlx5_dm_cleanup(struct mlx5_core_dev *dev) +{ + struct mlx5_dm *dm = dev->dm; + + if (!dev->dm) + return; + + if (dm->steering_sw_icm_alloc_blocks) { + WARN_ON(!bitmap_empty(dm->steering_sw_icm_alloc_blocks, + BIT(MLX5_CAP_DEV_MEM(dev, log_steering_sw_icm_size) - + MLX5_LOG_SW_ICM_BLOCK_SIZE(dev)))); + kfree(dm->steering_sw_icm_alloc_blocks); + } + + if (dm->header_modify_sw_icm_alloc_blocks) { + WARN_ON(!bitmap_empty(dm->header_modify_sw_icm_alloc_blocks, + BIT(MLX5_CAP_DEV_MEM(dev, + log_header_modify_sw_icm_size) - + MLX5_LOG_SW_ICM_BLOCK_SIZE(dev)))); + kfree(dm->header_modify_sw_icm_alloc_blocks); + } + + kfree(dm); +} + +int mlx5_dm_sw_icm_alloc(struct mlx5_core_dev *dev, enum mlx5_sw_icm_type type, + u64 length, u16 uid, phys_addr_t *addr, u32 *obj_id) +{ + u32 num_blocks = DIV_ROUND_UP_ULL(length, MLX5_SW_ICM_BLOCK_SIZE(dev)); + u32 out[MLX5_ST_SZ_DW(general_obj_out_cmd_hdr)] = {}; + u32 in[MLX5_ST_SZ_DW(create_sw_icm_in)] = {}; + struct mlx5_dm *dm = dev->dm; + unsigned long *block_map; + u64 icm_start_addr; + u32 log_icm_size; + u32 max_blocks; + u64 block_idx; + void *sw_icm; + int ret; + + if (!dev->dm) + return -EOPNOTSUPP; + + if (!length || (length & (length - 1)) || + length & (MLX5_SW_ICM_BLOCK_SIZE(dev) - 1)) + return -EINVAL; + + MLX5_SET(general_obj_in_cmd_hdr, in, opcode, + MLX5_CMD_OP_CREATE_GENERAL_OBJECT); + MLX5_SET(general_obj_in_cmd_hdr, in, obj_type, MLX5_OBJ_TYPE_SW_ICM); + MLX5_SET(general_obj_in_cmd_hdr, in, uid, uid); + + switch (type) { + case MLX5_SW_ICM_TYPE_STEERING: + icm_start_addr = MLX5_CAP64_DEV_MEM(dev, steering_sw_icm_start_address); + log_icm_size = MLX5_CAP_DEV_MEM(dev, log_steering_sw_icm_size); + block_map = dm->steering_sw_icm_alloc_blocks; + break; + case MLX5_SW_ICM_TYPE_HEADER_MODIFY: + icm_start_addr = MLX5_CAP64_DEV_MEM(dev, header_modify_sw_icm_start_address); + log_icm_size = MLX5_CAP_DEV_MEM(dev, + log_header_modify_sw_icm_size); + block_map = dm->header_modify_sw_icm_alloc_blocks; + break; + default: + return -EINVAL; + } + + if (!block_map) + return -EOPNOTSUPP; + + max_blocks = BIT(log_icm_size - MLX5_LOG_SW_ICM_BLOCK_SIZE(dev)); + spin_lock(&dm->lock); + block_idx = bitmap_find_next_zero_area(block_map, + max_blocks, + 0, + num_blocks, 0); + + if (block_idx < max_blocks) + bitmap_set(block_map, + block_idx, num_blocks); + + spin_unlock(&dm->lock); + + if (block_idx >= max_blocks) + return -ENOMEM; + + sw_icm = MLX5_ADDR_OF(create_sw_icm_in, in, sw_icm); + icm_start_addr += block_idx << MLX5_LOG_SW_ICM_BLOCK_SIZE(dev); + MLX5_SET64(sw_icm, sw_icm, sw_icm_start_addr, + icm_start_addr); + MLX5_SET(sw_icm, sw_icm, log_sw_icm_size, ilog2(length)); + + ret = mlx5_cmd_exec(dev, in, sizeof(in), out, sizeof(out)); + if (ret) { + spin_lock(&dm->lock); + bitmap_clear(block_map, + block_idx, num_blocks); + spin_unlock(&dm->lock); + + return ret; + } + + *addr = icm_start_addr; + *obj_id = MLX5_GET(general_obj_out_cmd_hdr, out, obj_id); + + return 0; +} +EXPORT_SYMBOL_GPL(mlx5_dm_sw_icm_alloc); + +int mlx5_dm_sw_icm_dealloc(struct mlx5_core_dev *dev, enum mlx5_sw_icm_type type, + u64 length, u16 uid, phys_addr_t addr, u32 obj_id) +{ + u32 num_blocks = DIV_ROUND_UP_ULL(length, MLX5_SW_ICM_BLOCK_SIZE(dev)); + u32 out[MLX5_ST_SZ_DW(general_obj_out_cmd_hdr)] = {}; + u32 in[MLX5_ST_SZ_DW(general_obj_in_cmd_hdr)] = {}; + struct mlx5_dm *dm = dev->dm; + unsigned long *block_map; + u64 icm_start_addr; + u64 start_idx; + int err; + + if (!dev->dm) + return -EOPNOTSUPP; + + switch (type) { + case MLX5_SW_ICM_TYPE_STEERING: + icm_start_addr = MLX5_CAP64_DEV_MEM(dev, steering_sw_icm_start_address); + block_map = dm->steering_sw_icm_alloc_blocks; + break; + case MLX5_SW_ICM_TYPE_HEADER_MODIFY: + icm_start_addr = MLX5_CAP64_DEV_MEM(dev, header_modify_sw_icm_start_address); + block_map = dm->header_modify_sw_icm_alloc_blocks; + break; + default: + return -EINVAL; + } + + MLX5_SET(general_obj_in_cmd_hdr, in, opcode, + MLX5_CMD_OP_DESTROY_GENERAL_OBJECT); + MLX5_SET(general_obj_in_cmd_hdr, in, obj_type, MLX5_OBJ_TYPE_SW_ICM); + MLX5_SET(general_obj_in_cmd_hdr, in, obj_id, obj_id); + MLX5_SET(general_obj_in_cmd_hdr, in, uid, uid); + + err = mlx5_cmd_exec(dev, in, sizeof(in), out, sizeof(out)); + if (err) + return err; + + start_idx = (addr - icm_start_addr) >> MLX5_LOG_SW_ICM_BLOCK_SIZE(dev); + spin_lock(&dm->lock); + bitmap_clear(block_map, + start_idx, num_blocks); + spin_unlock(&dm->lock); + + return 0; +} +EXPORT_SYMBOL_GPL(mlx5_dm_sw_icm_dealloc); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/main.c b/drivers/net/ethernet/mellanox/mlx5/core/main.c index 7f70ecb1db6d..c1679d11d71f 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/main.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/main.c @@ -879,6 +879,10 @@ static int mlx5_init_once(struct mlx5_core_dev *dev) goto err_eswitch_cleanup; } + dev->dm = mlx5_dm_create(dev); + if (IS_ERR(dev->dm)) + mlx5_core_warn(dev, "Failed to init device memory%d\n", err); + dev->tracer = mlx5_fw_tracer_create(dev); return 0; @@ -912,6 +916,7 @@ err_devcom: static void mlx5_cleanup_once(struct mlx5_core_dev *dev) { mlx5_fw_tracer_destroy(dev->tracer); + mlx5_dm_cleanup(dev); mlx5_fpga_cleanup(dev); mlx5_eswitch_cleanup(dev->priv.eswitch); mlx5_sriov_cleanup(dev); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h b/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h index 471bbc48bc1f..bbcf4ee40ad5 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h @@ -198,6 +198,9 @@ int mlx5_set_mtpps(struct mlx5_core_dev *mdev, u32 *mtpps, u32 mtpps_size); int mlx5_query_mtppse(struct mlx5_core_dev *mdev, u8 pin, u8 *arm, u8 *mode); int mlx5_set_mtppse(struct mlx5_core_dev *mdev, u8 pin, u8 arm, u8 mode); +struct mlx5_dm *mlx5_dm_create(struct mlx5_core_dev *dev); +void mlx5_dm_cleanup(struct mlx5_core_dev *dev); + #define MLX5_PPS_CAP(mdev) (MLX5_CAP_GEN((mdev), pps) && \ MLX5_CAP_GEN((mdev), pps_modify) && \ MLX5_CAP_MCAM_FEATURE((mdev), mtpps_fs) && \ diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h index 0acd28f2e62c..72bc6ce44b55 100644 --- a/include/linux/mlx5/driver.h +++ b/include/linux/mlx5/driver.h @@ -622,6 +622,11 @@ struct mlx5e_resources { struct mlx5_sq_bfreg bfreg; }; +enum mlx5_sw_icm_type { + MLX5_SW_ICM_TYPE_STEERING, + MLX5_SW_ICM_TYPE_HEADER_MODIFY, +}; + #define MLX5_MAX_RESERVED_GIDS 8 struct mlx5_rsvd_gids { @@ -653,10 +658,14 @@ struct mlx5_clock { struct mlx5_pps pps_info; }; +struct mlx5_dm; struct mlx5_fw_tracer; struct mlx5_vxlan; struct mlx5_geneve; +#define MLX5_LOG_SW_ICM_BLOCK_SIZE(dev) (MLX5_CAP_DEV_MEM(dev, log_sw_icm_alloc_granularity)) +#define MLX5_SW_ICM_BLOCK_SIZE(dev) (1 << MLX5_LOG_SW_ICM_BLOCK_SIZE(dev)) + struct mlx5_core_dev { struct device *device; enum mlx5_coredev_type coredev_type; @@ -690,6 +699,7 @@ struct mlx5_core_dev { atomic_t num_qps; u32 issi; struct mlx5e_resources mlx5e_res; + struct mlx5_dm *dm; struct mlx5_vxlan *vxlan; struct mlx5_geneve *geneve; struct { @@ -1072,6 +1082,10 @@ int mlx5_lag_query_cong_counters(struct mlx5_core_dev *dev, size_t *offsets); struct mlx5_uars_page *mlx5_get_uars_page(struct mlx5_core_dev *mdev); void mlx5_put_uars_page(struct mlx5_core_dev *mdev, struct mlx5_uars_page *up); +int mlx5_dm_sw_icm_alloc(struct mlx5_core_dev *dev, enum mlx5_sw_icm_type type, + u64 length, u16 uid, phys_addr_t *addr, u32 *obj_id); +int mlx5_dm_sw_icm_dealloc(struct mlx5_core_dev *dev, enum mlx5_sw_icm_type type, + u64 length, u16 uid, phys_addr_t addr, u32 obj_id); #ifdef CONFIG_MLX5_CORE_IPOIB struct net_device *mlx5_rdma_netdev_alloc(struct mlx5_core_dev *mdev, -- cgit v1.2.3 From 97b5484ed608605dca9e461c0289d1195ba9608d Mon Sep 17 00:00:00 2001 From: Alex Vesker Date: Thu, 29 Aug 2019 23:42:32 +0000 Subject: net/mlx5: Add HW bits and definitions required for SW steering Add the required Software Steering hardware definitions and bits to mlx5_ifc. Signed-off-by: Alex Vesker Signed-off-by: Yevgeny Klitenik Reviewed-by: Mark Bloch Signed-off-by: Saeed Mahameed --- include/linux/mlx5/device.h | 7 ++ include/linux/mlx5/mlx5_ifc.h | 235 +++++++++++++++++++++++++++++++++++------- 2 files changed, 205 insertions(+), 37 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mlx5/device.h b/include/linux/mlx5/device.h index ce9839c8bc1a..5767d7fab5f3 100644 --- a/include/linux/mlx5/device.h +++ b/include/linux/mlx5/device.h @@ -1162,6 +1162,9 @@ enum mlx5_qcam_feature_groups { #define MLX5_CAP_FLOWTABLE(mdev, cap) \ MLX5_GET(flow_table_nic_cap, mdev->caps.hca_cur[MLX5_CAP_FLOW_TABLE], cap) +#define MLX5_CAP64_FLOWTABLE(mdev, cap) \ + MLX5_GET64(flow_table_nic_cap, (mdev)->caps.hca_cur[MLX5_CAP_FLOW_TABLE], cap) + #define MLX5_CAP_FLOWTABLE_MAX(mdev, cap) \ MLX5_GET(flow_table_nic_cap, mdev->caps.hca_max[MLX5_CAP_FLOW_TABLE], cap) @@ -1225,6 +1228,10 @@ enum mlx5_qcam_feature_groups { MLX5_GET(e_switch_cap, \ mdev->caps.hca_cur[MLX5_CAP_ESWITCH], cap) +#define MLX5_CAP64_ESW_FLOWTABLE(mdev, cap) \ + MLX5_GET64(flow_table_eswitch_cap, \ + (mdev)->caps.hca_cur[MLX5_CAP_ESWITCH_FLOW_TABLE], cap) + #define MLX5_CAP_ESW_MAX(mdev, cap) \ MLX5_GET(e_switch_cap, \ mdev->caps.hca_max[MLX5_CAP_ESWITCH], cap) diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h index 4e278114d8b3..76e945dbc7ed 100644 --- a/include/linux/mlx5/mlx5_ifc.h +++ b/include/linux/mlx5/mlx5_ifc.h @@ -282,6 +282,7 @@ enum { MLX5_CMD_OP_ALLOC_MODIFY_HEADER_CONTEXT = 0x940, MLX5_CMD_OP_DEALLOC_MODIFY_HEADER_CONTEXT = 0x941, MLX5_CMD_OP_QUERY_MODIFY_HEADER_CONTEXT = 0x942, + MLX5_CMD_OP_SYNC_STEERING = 0xb00, MLX5_CMD_OP_FPGA_CREATE_QP = 0x960, MLX5_CMD_OP_FPGA_MODIFY_QP = 0x961, MLX5_CMD_OP_FPGA_QUERY_QP = 0x962, @@ -485,7 +486,11 @@ union mlx5_ifc_gre_key_bits { }; struct mlx5_ifc_fte_match_set_misc_bits { - u8 reserved_at_0[0x8]; + u8 gre_c_present[0x1]; + u8 reserved_auto1[0x1]; + u8 gre_k_present[0x1]; + u8 gre_s_present[0x1]; + u8 source_vhca_port[0x4]; u8 source_sqn[0x18]; u8 source_eswitch_owner_vhca_id[0x10]; @@ -565,12 +570,38 @@ struct mlx5_ifc_fte_match_set_misc2_bits { u8 metadata_reg_a[0x20]; - u8 reserved_at_1a0[0x60]; + u8 metadata_reg_b[0x20]; + + u8 reserved_at_1c0[0x40]; }; struct mlx5_ifc_fte_match_set_misc3_bits { - u8 reserved_at_0[0x120]; + u8 inner_tcp_seq_num[0x20]; + + u8 outer_tcp_seq_num[0x20]; + + u8 inner_tcp_ack_num[0x20]; + + u8 outer_tcp_ack_num[0x20]; + + u8 reserved_at_80[0x8]; + u8 outer_vxlan_gpe_vni[0x18]; + + u8 outer_vxlan_gpe_next_protocol[0x8]; + u8 outer_vxlan_gpe_flags[0x8]; + u8 reserved_at_b0[0x10]; + + u8 icmp_header_data[0x20]; + + u8 icmpv6_header_data[0x20]; + + u8 icmp_type[0x8]; + u8 icmp_code[0x8]; + u8 icmpv6_type[0x8]; + u8 icmpv6_code[0x8]; + u8 geneve_tlv_option_0_data[0x20]; + u8 reserved_at_140[0xc0]; }; @@ -666,7 +697,15 @@ struct mlx5_ifc_flow_table_nic_cap_bits { struct mlx5_ifc_flow_table_prop_layout_bits flow_table_properties_nic_transmit_sniffer; - u8 reserved_at_e00[0x7200]; + u8 reserved_at_e00[0x1200]; + + u8 sw_steering_nic_rx_action_drop_icm_address[0x40]; + + u8 sw_steering_nic_tx_action_drop_icm_address[0x40]; + + u8 sw_steering_nic_tx_action_allow_icm_address[0x40]; + + u8 reserved_at_20c0[0x5f40]; }; enum { @@ -698,7 +737,17 @@ struct mlx5_ifc_flow_table_eswitch_cap_bits { struct mlx5_ifc_flow_table_prop_layout_bits flow_table_properties_esw_acl_egress; - u8 reserved_at_800[0x7800]; + u8 reserved_at_800[0x1000]; + + u8 sw_steering_fdb_action_drop_icm_address_rx[0x40]; + + u8 sw_steering_fdb_action_drop_icm_address_tx[0x40]; + + u8 sw_steering_uplink_icm_address_rx[0x40]; + + u8 sw_steering_uplink_icm_address_tx[0x40]; + + u8 reserved_at_1900[0x6700]; }; enum { @@ -849,6 +898,25 @@ struct mlx5_ifc_roce_cap_bits { u8 reserved_at_100[0x700]; }; +struct mlx5_ifc_sync_steering_in_bits { + u8 opcode[0x10]; + u8 uid[0x10]; + + u8 reserved_at_20[0x10]; + u8 op_mod[0x10]; + + u8 reserved_at_40[0xc0]; +}; + +struct mlx5_ifc_sync_steering_out_bits { + u8 status[0x8]; + u8 reserved_at_8[0x18]; + + u8 syndrome[0x20]; + + u8 reserved_at_40[0x40]; +}; + struct mlx5_ifc_device_mem_cap_bits { u8 memic[0x1]; u8 reserved_at_1[0x1f]; @@ -1041,6 +1109,12 @@ enum { MLX5_CAP_UMR_FENCE_NONE = 0x2, }; +enum { + MLX5_FLEX_PARSER_VXLAN_GPE_ENABLED = 1 << 7, + MLX5_FLEX_PARSER_ICMP_V4_ENABLED = 1 << 8, + MLX5_FLEX_PARSER_ICMP_V6_ENABLED = 1 << 9, +}; + enum { MLX5_UCTX_CAP_RAW_TX = 1UL << 0, MLX5_UCTX_CAP_INTERNAL_DEV_RES = 1UL << 1, @@ -1414,7 +1488,14 @@ struct mlx5_ifc_cmd_hca_cap_bits { u8 reserved_at_6c0[0x4]; u8 flex_parser_id_geneve_tlv_option_0[0x4]; - u8 reserved_at_6c8[0x28]; + u8 flex_parser_id_icmp_dw1[0x4]; + u8 flex_parser_id_icmp_dw0[0x4]; + u8 flex_parser_id_icmpv6_dw1[0x4]; + u8 flex_parser_id_icmpv6_dw0[0x4]; + u8 flex_parser_id_outer_first_mpls_over_gre[0x4]; + u8 flex_parser_id_outer_first_mpls_over_udp_label[0x4]; + + u8 reserved_at_6e0[0x10]; u8 sf_base_id[0x10]; u8 reserved_at_700[0x80]; @@ -2652,6 +2733,7 @@ union mlx5_ifc_hca_cap_union_bits { struct mlx5_ifc_debug_cap_bits debug_cap; struct mlx5_ifc_fpga_cap_bits fpga_cap; struct mlx5_ifc_tls_cap_bits tls_cap; + struct mlx5_ifc_device_mem_cap_bits device_mem_cap; u8 reserved_at_0[0x8000]; }; @@ -3255,7 +3337,11 @@ struct mlx5_ifc_esw_vport_context_bits { u8 cvlan_pcp[0x3]; u8 cvlan_id[0xc]; - u8 reserved_at_60[0x7a0]; + u8 reserved_at_60[0x720]; + + u8 sw_steering_vport_icm_address_rx[0x40]; + + u8 sw_steering_vport_icm_address_tx[0x40]; }; enum { @@ -4941,23 +5027,98 @@ struct mlx5_ifc_query_hca_cap_in_bits { u8 reserved_at_20[0x10]; u8 op_mod[0x10]; - u8 reserved_at_40[0x40]; + u8 other_function[0x1]; + u8 reserved_at_41[0xf]; + u8 function_id[0x10]; + + u8 reserved_at_60[0x20]; }; -struct mlx5_ifc_query_flow_table_out_bits { +struct mlx5_ifc_other_hca_cap_bits { + u8 roce[0x1]; + u8 reserved_0[0x27f]; +}; + +struct mlx5_ifc_query_other_hca_cap_out_bits { u8 status[0x8]; - u8 reserved_at_8[0x18]; + u8 reserved_0[0x18]; u8 syndrome[0x20]; - u8 reserved_at_40[0x80]; + u8 reserved_1[0x40]; - u8 reserved_at_c0[0x8]; + struct mlx5_ifc_other_hca_cap_bits other_capability; +}; + +struct mlx5_ifc_query_other_hca_cap_in_bits { + u8 opcode[0x10]; + u8 reserved_0[0x10]; + + u8 reserved_1[0x10]; + u8 op_mod[0x10]; + + u8 reserved_2[0x10]; + u8 function_id[0x10]; + + u8 reserved_3[0x20]; +}; + +struct mlx5_ifc_modify_other_hca_cap_out_bits { + u8 status[0x8]; + u8 reserved_0[0x18]; + + u8 syndrome[0x20]; + + u8 reserved_1[0x40]; +}; + +struct mlx5_ifc_modify_other_hca_cap_in_bits { + u8 opcode[0x10]; + u8 reserved_0[0x10]; + + u8 reserved_1[0x10]; + u8 op_mod[0x10]; + + u8 reserved_2[0x10]; + u8 function_id[0x10]; + u8 field_select[0x20]; + + struct mlx5_ifc_other_hca_cap_bits other_capability; +}; + +struct mlx5_ifc_flow_table_context_bits { + u8 reformat_en[0x1]; + u8 decap_en[0x1]; + u8 sw_owner[0x1]; + u8 termination_table[0x1]; + u8 table_miss_action[0x4]; u8 level[0x8]; - u8 reserved_at_d0[0x8]; + u8 reserved_at_10[0x8]; u8 log_size[0x8]; - u8 reserved_at_e0[0x120]; + u8 reserved_at_20[0x8]; + u8 table_miss_id[0x18]; + + u8 reserved_at_40[0x8]; + u8 lag_master_next_table_id[0x18]; + + u8 reserved_at_60[0x60]; + + u8 sw_owner_icm_root_1[0x40]; + + u8 sw_owner_icm_root_0[0x40]; + +}; + +struct mlx5_ifc_query_flow_table_out_bits { + u8 status[0x8]; + u8 reserved_at_8[0x18]; + + u8 syndrome[0x20]; + + u8 reserved_at_40[0x80]; + + struct mlx5_ifc_flow_table_context_bits flow_table_context; }; struct mlx5_ifc_query_flow_table_in_bits { @@ -5227,7 +5388,7 @@ struct mlx5_ifc_alloc_packet_reformat_context_out_bits { u8 reserved_at_60[0x20]; }; -enum { +enum mlx5_reformat_ctx_type { MLX5_REFORMAT_TYPE_L2_TO_VXLAN = 0x0, MLX5_REFORMAT_TYPE_L2_TO_NVGRE = 0x1, MLX5_REFORMAT_TYPE_L2_TO_L2_TUNNEL = 0x2, @@ -5323,7 +5484,16 @@ 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_A = 0x49, + MLX5_ACTION_IN_FIELD_METADATA_REG_B = 0x50, MLX5_ACTION_IN_FIELD_METADATA_REG_C_0 = 0x51, + MLX5_ACTION_IN_FIELD_METADATA_REG_C_1 = 0x52, + MLX5_ACTION_IN_FIELD_METADATA_REG_C_2 = 0x53, + MLX5_ACTION_IN_FIELD_METADATA_REG_C_3 = 0x54, + MLX5_ACTION_IN_FIELD_METADATA_REG_C_4 = 0x55, + MLX5_ACTION_IN_FIELD_METADATA_REG_C_5 = 0x56, + MLX5_ACTION_IN_FIELD_OUT_TCP_SEQ_NUM = 0x59, + MLX5_ACTION_IN_FIELD_OUT_TCP_ACK_NUM = 0x5B, }; struct mlx5_ifc_alloc_modify_header_context_out_bits { @@ -7369,35 +7539,26 @@ struct mlx5_ifc_create_mkey_in_bits { u8 klm_pas_mtt[0][0x20]; }; +enum { + MLX5_FLOW_TABLE_TYPE_NIC_RX = 0x0, + MLX5_FLOW_TABLE_TYPE_NIC_TX = 0x1, + MLX5_FLOW_TABLE_TYPE_ESW_EGRESS_ACL = 0x2, + MLX5_FLOW_TABLE_TYPE_ESW_INGRESS_ACL = 0x3, + MLX5_FLOW_TABLE_TYPE_FDB = 0X4, + MLX5_FLOW_TABLE_TYPE_SNIFFER_RX = 0X5, + MLX5_FLOW_TABLE_TYPE_SNIFFER_TX = 0X6, +}; + struct mlx5_ifc_create_flow_table_out_bits { u8 status[0x8]; - u8 reserved_at_8[0x18]; + u8 icm_address_63_40[0x18]; u8 syndrome[0x20]; - u8 reserved_at_40[0x8]; + u8 icm_address_39_32[0x8]; u8 table_id[0x18]; - u8 reserved_at_60[0x20]; -}; - -struct mlx5_ifc_flow_table_context_bits { - u8 reformat_en[0x1]; - u8 decap_en[0x1]; - u8 reserved_at_2[0x1]; - u8 termination_table[0x1]; - u8 table_miss_action[0x4]; - u8 level[0x8]; - u8 reserved_at_10[0x8]; - u8 log_size[0x8]; - - u8 reserved_at_20[0x8]; - u8 table_miss_id[0x18]; - - u8 reserved_at_40[0x8]; - u8 lag_master_next_table_id[0x18]; - - u8 reserved_at_60[0xe0]; + u8 icm_address_31_0[0x20]; }; struct mlx5_ifc_create_flow_table_in_bits { -- cgit v1.2.3 From f813cb506b8c9abc106314e1f95c9f2ebf260988 Mon Sep 17 00:00:00 2001 From: Maor Gottlieb Date: Thu, 29 Aug 2019 23:42:36 +0000 Subject: net/mlx5: Add stub for mlx5_eswitch_mode Return MLX5_ESWITCH_NONE when CONFIG_MLX5_ESWITCH is not selected. Signed-off-by: Maor Gottlieb Reviewed-by: Mark Bloch Signed-off-by: Saeed Mahameed --- include/linux/mlx5/eswitch.h | 8 +++++++- 1 file changed, 7 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mlx5/eswitch.h b/include/linux/mlx5/eswitch.h index 46b5ba029802..825920d3ca40 100644 --- a/include/linux/mlx5/eswitch.h +++ b/include/linux/mlx5/eswitch.h @@ -61,7 +61,6 @@ void *mlx5_eswitch_get_proto_dev(struct mlx5_eswitch *esw, struct mlx5_eswitch_rep *mlx5_eswitch_vport_rep(struct mlx5_eswitch *esw, u16 vport_num); void *mlx5_eswitch_uplink_get_proto_dev(struct mlx5_eswitch *esw, u8 rep_type); -u8 mlx5_eswitch_mode(struct mlx5_eswitch *esw); struct mlx5_flow_handle * mlx5_eswitch_add_send_to_vport_rule(struct mlx5_eswitch *esw, u16 vport_num, u32 sqn); @@ -75,7 +74,14 @@ 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); +u8 mlx5_eswitch_mode(struct mlx5_eswitch *esw); #else /* CONFIG_MLX5_ESWITCH */ + +static inline u8 mlx5_eswitch_mode(struct mlx5_eswitch *esw) +{ + return MLX5_ESWITCH_NONE; +} + static inline enum devlink_eswitch_encap_mode mlx5_eswitch_get_encap_mode(const struct mlx5_core_dev *dev) { -- cgit v1.2.3 From d7bda73070201514d0d254f451c11bcc9b5890f1 Mon Sep 17 00:00:00 2001 From: Marc Kleine-Budde Date: Tue, 27 Aug 2019 13:53:18 +0200 Subject: can: dev: avoid long lines This patch fixes long lines in the generic CAN device infrastructure. Signed-off-by: Marc Kleine-Budde --- drivers/net/can/dev.c | 43 ++++++++++++++++++++++++++---------------- include/linux/can/dev.h | 3 ++- include/linux/can/rx-offload.h | 13 +++++++++---- 3 files changed, 38 insertions(+), 21 deletions(-) (limited to 'include/linux') diff --git a/drivers/net/can/dev.c b/drivers/net/can/dev.c index b6fe39a26a9b..9f58c4f0344d 100644 --- a/drivers/net/can/dev.c +++ b/drivers/net/can/dev.c @@ -73,10 +73,11 @@ EXPORT_SYMBOL_GPL(can_len2dlc); * registers of the CAN controller. You can find more information * in the header file linux/can/netlink.h. */ -static int can_update_sample_point(const struct can_bittiming_const *btc, - unsigned int sample_point_nominal, unsigned int tseg, - unsigned int *tseg1_ptr, unsigned int *tseg2_ptr, - unsigned int *sample_point_error_ptr) +static int +can_update_sample_point(const struct can_bittiming_const *btc, + unsigned int sample_point_nominal, unsigned int tseg, + unsigned int *tseg1_ptr, unsigned int *tseg2_ptr, + unsigned int *sample_point_error_ptr) { unsigned int sample_point_error, best_sample_point_error = UINT_MAX; unsigned int sample_point, best_sample_point = 0; @@ -84,7 +85,9 @@ static int can_update_sample_point(const struct can_bittiming_const *btc, int i; for (i = 0; i <= 1; i++) { - tseg2 = tseg + CAN_CALC_SYNC_SEG - (sample_point_nominal * (tseg + CAN_CALC_SYNC_SEG)) / 1000 - i; + tseg2 = tseg + CAN_CALC_SYNC_SEG - + (sample_point_nominal * (tseg + CAN_CALC_SYNC_SEG)) / + 1000 - i; tseg2 = clamp(tseg2, btc->tseg2_min, btc->tseg2_max); tseg1 = tseg - tseg2; if (tseg1 > btc->tseg1_max) { @@ -92,10 +95,12 @@ static int can_update_sample_point(const struct can_bittiming_const *btc, tseg2 = tseg - tseg1; } - sample_point = 1000 * (tseg + CAN_CALC_SYNC_SEG - tseg2) / (tseg + CAN_CALC_SYNC_SEG); + sample_point = 1000 * (tseg + CAN_CALC_SYNC_SEG - tseg2) / + (tseg + CAN_CALC_SYNC_SEG); sample_point_error = abs(sample_point_nominal - sample_point); - if ((sample_point <= sample_point_nominal) && (sample_point_error < best_sample_point_error)) { + if ((sample_point <= sample_point_nominal) && + (sample_point_error < best_sample_point_error)) { best_sample_point = sample_point; best_sample_point_error = sample_point_error; *tseg1_ptr = tseg1; @@ -160,7 +165,8 @@ static int can_calc_bittiming(struct net_device *dev, struct can_bittiming *bt, if (bitrate_error < best_bitrate_error) best_sample_point_error = UINT_MAX; - can_update_sample_point(btc, sample_point_nominal, tseg / 2, &tseg1, &tseg2, &sample_point_error); + can_update_sample_point(btc, sample_point_nominal, tseg / 2, + &tseg1, &tseg2, &sample_point_error); if (sample_point_error > best_sample_point_error) continue; @@ -189,8 +195,9 @@ static int can_calc_bittiming(struct net_device *dev, struct can_bittiming *bt, } /* real sample point */ - bt->sample_point = can_update_sample_point(btc, sample_point_nominal, best_tseg, - &tseg1, &tseg2, NULL); + bt->sample_point = can_update_sample_point(btc, sample_point_nominal, + best_tseg, &tseg1, &tseg2, + NULL); v64 = (u64)best_brp * 1000 * 1000 * 1000; do_div(v64, priv->clock.freq); @@ -214,7 +221,8 @@ static int can_calc_bittiming(struct net_device *dev, struct can_bittiming *bt, bt->brp = best_brp; /* real bitrate */ - bt->bitrate = priv->clock.freq / (bt->brp * (CAN_CALC_SYNC_SEG + tseg1 + tseg2)); + bt->bitrate = priv->clock.freq / + (bt->brp * (CAN_CALC_SYNC_SEG + tseg1 + tseg2)); return 0; } @@ -267,9 +275,10 @@ static int can_fixup_bittiming(struct net_device *dev, struct can_bittiming *bt, } /* Checks the validity of predefined bitrate settings */ -static int can_validate_bitrate(struct net_device *dev, struct can_bittiming *bt, - const u32 *bitrate_const, - const unsigned int bitrate_const_cnt) +static int +can_validate_bitrate(struct net_device *dev, struct can_bittiming *bt, + const u32 *bitrate_const, + const unsigned int bitrate_const_cnt) { struct can_priv *priv = netdev_priv(dev); unsigned int i; @@ -460,7 +469,8 @@ void can_put_echo_skb(struct sk_buff *skb, struct net_device *dev, } EXPORT_SYMBOL_GPL(can_put_echo_skb); -struct sk_buff *__can_get_echo_skb(struct net_device *dev, unsigned int idx, u8 *len_ptr) +struct sk_buff * +__can_get_echo_skb(struct net_device *dev, unsigned int idx, u8 *len_ptr) { struct can_priv *priv = netdev_priv(dev); @@ -569,7 +579,8 @@ restart: static void can_restart_work(struct work_struct *work) { struct delayed_work *dwork = to_delayed_work(work); - struct can_priv *priv = container_of(dwork, struct can_priv, restart_work); + struct can_priv *priv = container_of(dwork, struct can_priv, + restart_work); can_restart(priv->dev); } diff --git a/include/linux/can/dev.h b/include/linux/can/dev.h index f01623aef2f7..9b3c720a31b1 100644 --- a/include/linux/can/dev.h +++ b/include/linux/can/dev.h @@ -169,7 +169,8 @@ void can_change_state(struct net_device *dev, struct can_frame *cf, void can_put_echo_skb(struct sk_buff *skb, struct net_device *dev, unsigned int idx); -struct sk_buff *__can_get_echo_skb(struct net_device *dev, unsigned int idx, u8 *len_ptr); +struct sk_buff *__can_get_echo_skb(struct net_device *dev, unsigned int idx, + u8 *len_ptr); unsigned int can_get_echo_skb(struct net_device *dev, unsigned int idx); void can_free_echo_skb(struct net_device *dev, unsigned int idx); diff --git a/include/linux/can/rx-offload.h b/include/linux/can/rx-offload.h index 9daa1119ea42..01219f2902bf 100644 --- a/include/linux/can/rx-offload.h +++ b/include/linux/can/rx-offload.h @@ -15,7 +15,8 @@ struct can_rx_offload { struct net_device *dev; - unsigned int (*mailbox_read)(struct can_rx_offload *offload, struct can_frame *cf, + unsigned int (*mailbox_read)(struct can_rx_offload *offload, + struct can_frame *cf, u32 *timestamp, unsigned int mb); struct sk_buff_head skb_queue; @@ -29,9 +30,13 @@ struct can_rx_offload { bool inc; }; -int can_rx_offload_add_timestamp(struct net_device *dev, struct can_rx_offload *offload); -int can_rx_offload_add_fifo(struct net_device *dev, struct can_rx_offload *offload, unsigned int weight); -int can_rx_offload_irq_offload_timestamp(struct can_rx_offload *offload, u64 reg); +int can_rx_offload_add_timestamp(struct net_device *dev, + struct can_rx_offload *offload); +int can_rx_offload_add_fifo(struct net_device *dev, + struct can_rx_offload *offload, + unsigned int weight); +int can_rx_offload_irq_offload_timestamp(struct can_rx_offload *offload, + u64 reg); int can_rx_offload_irq_offload_fifo(struct can_rx_offload *offload); int can_rx_offload_queue_sorted(struct can_rx_offload *offload, struct sk_buff *skb, u32 timestamp); -- cgit v1.2.3 From 2b688ea5efdee2868ed23eddfdbe27dbd232edac Mon Sep 17 00:00:00 2001 From: Maor Gottlieb Date: Thu, 15 Aug 2019 13:54:17 +0300 Subject: net/mlx5: Add flow steering actions to fs_cmd shim layer Add flow steering actions: modify header and packet reformat to the fs_cmd shim layer. This allows each namespace to define possibly different functionality for alloc/dealloc action commands. Signed-off-by: Maor Gottlieb Reviewed-by: Mark Bloch Signed-off-by: Saeed Mahameed --- drivers/infiniband/hw/mlx5/flow.c | 21 +++-- drivers/infiniband/hw/mlx5/main.c | 7 +- drivers/infiniband/hw/mlx5/mlx5_ib.h | 5 +- .../net/ethernet/mellanox/mlx5/core/en/tc_tun.c | 27 +++--- drivers/net/ethernet/mellanox/mlx5/core/en_rep.h | 2 +- drivers/net/ethernet/mellanox/mlx5/core/en_tc.c | 46 +++++---- drivers/net/ethernet/mellanox/mlx5/core/eswitch.h | 6 +- .../ethernet/mellanox/mlx5/core/eswitch_offloads.c | 26 ++--- drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.c | 92 +++++++++++++----- drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.h | 18 ++++ drivers/net/ethernet/mellanox/mlx5/core/fs_core.c | 105 ++++++++++++++++++++- drivers/net/ethernet/mellanox/mlx5/core/fs_core.h | 11 +++ include/linux/mlx5/fs.h | 33 ++++--- 13 files changed, 289 insertions(+), 110 deletions(-) (limited to 'include/linux') diff --git a/drivers/infiniband/hw/mlx5/flow.c b/drivers/infiniband/hw/mlx5/flow.c index b8841355fcd5..1c8f04abee0c 100644 --- a/drivers/infiniband/hw/mlx5/flow.c +++ b/drivers/infiniband/hw/mlx5/flow.c @@ -322,11 +322,11 @@ void mlx5_ib_destroy_flow_action_raw(struct mlx5_ib_flow_action *maction) switch (maction->flow_action_raw.sub_type) { case MLX5_IB_FLOW_ACTION_MODIFY_HEADER: mlx5_modify_header_dealloc(maction->flow_action_raw.dev->mdev, - maction->flow_action_raw.action_id); + maction->flow_action_raw.modify_hdr); break; case MLX5_IB_FLOW_ACTION_PACKET_REFORMAT: mlx5_packet_reformat_dealloc(maction->flow_action_raw.dev->mdev, - maction->flow_action_raw.action_id); + maction->flow_action_raw.pkt_reformat); break; case MLX5_IB_FLOW_ACTION_DECAP: break; @@ -352,10 +352,11 @@ mlx5_ib_create_modify_header(struct mlx5_ib_dev *dev, if (!maction) return ERR_PTR(-ENOMEM); - ret = mlx5_modify_header_alloc(dev->mdev, namespace, num_actions, in, - &maction->flow_action_raw.action_id); + maction->flow_action_raw.modify_hdr = + mlx5_modify_header_alloc(dev->mdev, namespace, num_actions, in); - if (ret) { + if (IS_ERR(maction->flow_action_raw.modify_hdr)) { + ret = PTR_ERR(maction->flow_action_raw.modify_hdr); kfree(maction); return ERR_PTR(ret); } @@ -479,11 +480,13 @@ static int mlx5_ib_flow_action_create_packet_reformat_ctx( if (ret) return ret; - ret = mlx5_packet_reformat_alloc(dev->mdev, prm_prt, len, - in, namespace, - &maction->flow_action_raw.action_id); - if (ret) + maction->flow_action_raw.pkt_reformat = + mlx5_packet_reformat_alloc(dev->mdev, prm_prt, len, + in, namespace); + if (IS_ERR(maction->flow_action_raw.pkt_reformat)) { + ret = PTR_ERR(maction->flow_action_raw.pkt_reformat); return ret; + } maction->flow_action_raw.sub_type = MLX5_IB_FLOW_ACTION_PACKET_REFORMAT; diff --git a/drivers/infiniband/hw/mlx5/main.c b/drivers/infiniband/hw/mlx5/main.c index 016373d1d27e..4e9f1507ffd9 100644 --- a/drivers/infiniband/hw/mlx5/main.c +++ b/drivers/infiniband/hw/mlx5/main.c @@ -2658,7 +2658,8 @@ int parse_flow_flow_action(struct mlx5_ib_flow_action *maction, if (action->action & MLX5_FLOW_CONTEXT_ACTION_MOD_HDR) return -EINVAL; action->action |= MLX5_FLOW_CONTEXT_ACTION_MOD_HDR; - action->modify_id = maction->flow_action_raw.action_id; + action->modify_hdr = + maction->flow_action_raw.modify_hdr; return 0; } if (maction->flow_action_raw.sub_type == @@ -2675,8 +2676,8 @@ int parse_flow_flow_action(struct mlx5_ib_flow_action *maction, return -EINVAL; action->action |= MLX5_FLOW_CONTEXT_ACTION_PACKET_REFORMAT; - action->reformat_id = - maction->flow_action_raw.action_id; + action->pkt_reformat = + maction->flow_action_raw.pkt_reformat; return 0; } /* fall through */ diff --git a/drivers/infiniband/hw/mlx5/mlx5_ib.h b/drivers/infiniband/hw/mlx5/mlx5_ib.h index a20d2ee08a3b..125a507c10ed 100644 --- a/drivers/infiniband/hw/mlx5/mlx5_ib.h +++ b/drivers/infiniband/hw/mlx5/mlx5_ib.h @@ -868,7 +868,10 @@ struct mlx5_ib_flow_action { struct { struct mlx5_ib_dev *dev; u32 sub_type; - u32 action_id; + union { + struct mlx5_modify_hdr *modify_hdr; + struct mlx5_pkt_reformat *pkt_reformat; + }; } flow_action_raw; }; }; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun.c b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun.c index 4c4620db3d31..f8ee18b4da6f 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun.c @@ -291,14 +291,14 @@ int mlx5e_tc_tun_create_header_ipv4(struct mlx5e_priv *priv, */ goto out; } - - err = mlx5_packet_reformat_alloc(priv->mdev, - e->reformat_type, - ipv4_encap_size, encap_header, - MLX5_FLOW_NAMESPACE_FDB, - &e->encap_id); - if (err) + e->pkt_reformat = mlx5_packet_reformat_alloc(priv->mdev, + e->reformat_type, + ipv4_encap_size, encap_header, + MLX5_FLOW_NAMESPACE_FDB); + if (IS_ERR(e->pkt_reformat)) { + err = PTR_ERR(e->pkt_reformat); goto destroy_neigh_entry; + } e->flags |= MLX5_ENCAP_ENTRY_VALID; mlx5e_rep_queue_neigh_stats_work(netdev_priv(out_dev)); @@ -407,13 +407,14 @@ int mlx5e_tc_tun_create_header_ipv6(struct mlx5e_priv *priv, goto out; } - err = mlx5_packet_reformat_alloc(priv->mdev, - e->reformat_type, - ipv6_encap_size, encap_header, - MLX5_FLOW_NAMESPACE_FDB, - &e->encap_id); - if (err) + e->pkt_reformat = mlx5_packet_reformat_alloc(priv->mdev, + e->reformat_type, + ipv6_encap_size, encap_header, + MLX5_FLOW_NAMESPACE_FDB); + if (IS_ERR(e->pkt_reformat)) { + err = PTR_ERR(e->pkt_reformat); goto destroy_neigh_entry; + } e->flags |= MLX5_ENCAP_ENTRY_VALID; mlx5e_rep_queue_neigh_stats_work(netdev_priv(out_dev)); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.h b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.h index a0ae5069d8c3..8e512216deb8 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.h @@ -161,7 +161,7 @@ struct mlx5e_encap_entry { */ struct hlist_node encap_hlist; struct list_head flows; - u32 encap_id; + struct mlx5_pkt_reformat *pkt_reformat; const struct ip_tunnel_info *tun_info; unsigned char h_dest[ETH_ALEN]; /* destination eth addr */ diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c index 67f66412a33c..30d26eba75a3 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c @@ -61,7 +61,7 @@ struct mlx5_nic_flow_attr { u32 action; u32 flow_tag; - u32 mod_hdr_id; + struct mlx5_modify_hdr *modify_hdr; u32 hairpin_tirn; u8 match_level; struct mlx5_flow_table *hairpin_ft; @@ -201,7 +201,7 @@ struct mlx5e_mod_hdr_entry { struct mod_hdr_key key; - u32 mod_hdr_id; + struct mlx5_modify_hdr *modify_hdr; refcount_t refcnt; struct completion res_ready; @@ -334,7 +334,7 @@ static void mlx5e_mod_hdr_put(struct mlx5e_priv *priv, WARN_ON(!list_empty(&mh->flows)); if (mh->compl_result > 0) - mlx5_modify_header_dealloc(priv->mdev, mh->mod_hdr_id); + mlx5_modify_header_dealloc(priv->mdev, mh->modify_hdr); kfree(mh); } @@ -395,11 +395,11 @@ static int mlx5e_attach_mod_hdr(struct mlx5e_priv *priv, hash_add(tbl->hlist, &mh->mod_hdr_hlist, hash_key); mutex_unlock(&tbl->lock); - err = mlx5_modify_header_alloc(priv->mdev, namespace, - mh->key.num_actions, - mh->key.actions, - &mh->mod_hdr_id); - if (err) { + mh->modify_hdr = mlx5_modify_header_alloc(priv->mdev, namespace, + mh->key.num_actions, + mh->key.actions); + if (IS_ERR(mh->modify_hdr)) { + err = PTR_ERR(mh->modify_hdr); mh->compl_result = err; goto alloc_header_err; } @@ -412,9 +412,9 @@ attach_flow: list_add(&flow->mod_hdr, &mh->flows); spin_unlock(&mh->flows_lock); if (mlx5e_is_eswitch_flow(flow)) - flow->esw_attr->mod_hdr_id = mh->mod_hdr_id; + flow->esw_attr->modify_hdr = mh->modify_hdr; else - flow->nic_attr->mod_hdr_id = mh->mod_hdr_id; + flow->nic_attr->modify_hdr = mh->modify_hdr; return 0; @@ -906,7 +906,6 @@ mlx5e_tc_add_nic_flow(struct mlx5e_priv *priv, struct mlx5_flow_destination dest[2] = {}; struct mlx5_flow_act flow_act = { .action = attr->action, - .reformat_id = 0, .flags = FLOW_ACT_NO_APPEND, }; struct mlx5_fc *counter = NULL; @@ -947,7 +946,7 @@ mlx5e_tc_add_nic_flow(struct mlx5e_priv *priv, if (attr->action & MLX5_FLOW_CONTEXT_ACTION_MOD_HDR) { err = mlx5e_attach_mod_hdr(priv, flow, parse_attr); - flow_act.modify_id = attr->mod_hdr_id; + flow_act.modify_hdr = attr->modify_hdr; kfree(parse_attr->mod_hdr_actions); if (err) return err; @@ -1304,14 +1303,13 @@ void mlx5e_tc_encap_flows_add(struct mlx5e_priv *priv, struct mlx5e_tc_flow *flow; int err; - err = mlx5_packet_reformat_alloc(priv->mdev, - e->reformat_type, - e->encap_size, e->encap_header, - MLX5_FLOW_NAMESPACE_FDB, - &e->encap_id); - if (err) { - mlx5_core_warn(priv->mdev, "Failed to offload cached encapsulation header, %d\n", - err); + e->pkt_reformat = mlx5_packet_reformat_alloc(priv->mdev, + e->reformat_type, + e->encap_size, e->encap_header, + MLX5_FLOW_NAMESPACE_FDB); + if (IS_ERR(e->pkt_reformat)) { + mlx5_core_warn(priv->mdev, "Failed to offload cached encapsulation header, %lu\n", + PTR_ERR(e->pkt_reformat)); return; } e->flags |= MLX5_ENCAP_ENTRY_VALID; @@ -1326,7 +1324,7 @@ void mlx5e_tc_encap_flows_add(struct mlx5e_priv *priv, esw_attr = flow->esw_attr; spec = &esw_attr->parse_attr->spec; - esw_attr->dests[flow->tmp_efi_index].encap_id = e->encap_id; + esw_attr->dests[flow->tmp_efi_index].pkt_reformat = e->pkt_reformat; esw_attr->dests[flow->tmp_efi_index].flags |= MLX5_ESW_DEST_ENCAP_VALID; /* Flow can be associated with multiple encap entries. * Before offloading the flow verify that all of them have @@ -1395,7 +1393,7 @@ void mlx5e_tc_encap_flows_del(struct mlx5e_priv *priv, /* we know that the encap is valid */ e->flags &= ~MLX5_ENCAP_ENTRY_VALID; - mlx5_packet_reformat_dealloc(priv->mdev, e->encap_id); + mlx5_packet_reformat_dealloc(priv->mdev, e->pkt_reformat); } static struct mlx5_fc *mlx5e_tc_get_counter(struct mlx5e_tc_flow *flow) @@ -1561,7 +1559,7 @@ static void mlx5e_encap_dealloc(struct mlx5e_priv *priv, struct mlx5e_encap_entr mlx5e_rep_encap_entry_detach(netdev_priv(e->out_dev), e); if (e->flags & MLX5_ENCAP_ENTRY_VALID) - mlx5_packet_reformat_dealloc(priv->mdev, e->encap_id); + mlx5_packet_reformat_dealloc(priv->mdev, e->pkt_reformat); } kfree(e->encap_header); @@ -3048,7 +3046,7 @@ attach_flow: flow->encaps[out_index].index = out_index; *encap_dev = e->out_dev; if (e->flags & MLX5_ENCAP_ENTRY_VALID) { - attr->dests[out_index].encap_id = e->encap_id; + attr->dests[out_index].pkt_reformat = e->pkt_reformat; attr->dests[out_index].flags |= MLX5_ESW_DEST_ENCAP_VALID; *encap_valid = true; } else { diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h index aba9e7a6ad3c..4f70202db6af 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h @@ -69,7 +69,7 @@ struct vport_ingress { struct mlx5_flow_group *allow_spoofchk_only_grp; struct mlx5_flow_group *allow_untagged_only_grp; struct mlx5_flow_group *drop_grp; - int modify_metadata_id; + struct mlx5_modify_hdr *modify_metadata; struct mlx5_flow_handle *modify_metadata_rule; struct mlx5_flow_handle *allow_rule; struct mlx5_flow_handle *drop_rule; @@ -385,11 +385,11 @@ struct mlx5_esw_flow_attr { struct { u32 flags; struct mlx5_eswitch_rep *rep; + struct mlx5_pkt_reformat *pkt_reformat; struct mlx5_core_dev *mdev; - u32 encap_id; struct mlx5_termtbl_handle *termtbl; } dests[MLX5_MAX_FLOW_FWD_VPORTS]; - u32 mod_hdr_id; + struct mlx5_modify_hdr *modify_hdr; u8 inner_match_level; u8 outer_match_level; struct mlx5_fc *counter; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c index 7d3582ee66b7..bee67ff58137 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c @@ -190,10 +190,10 @@ mlx5_eswitch_add_offloaded_rule(struct mlx5_eswitch *esw, MLX5_FLOW_DEST_VPORT_VHCA_ID; if (attr->dests[j].flags & MLX5_ESW_DEST_ENCAP) { flow_act.action |= MLX5_FLOW_CONTEXT_ACTION_PACKET_REFORMAT; - flow_act.reformat_id = attr->dests[j].encap_id; + flow_act.pkt_reformat = attr->dests[j].pkt_reformat; dest[i].vport.flags |= MLX5_FLOW_DEST_VPORT_REFORMAT_ID; - dest[i].vport.reformat_id = - attr->dests[j].encap_id; + dest[i].vport.pkt_reformat = + attr->dests[j].pkt_reformat; } i++; } @@ -213,7 +213,7 @@ mlx5_eswitch_add_offloaded_rule(struct mlx5_eswitch *esw, spec->match_criteria_enable |= MLX5_MATCH_INNER_HEADERS; if (flow_act.action & MLX5_FLOW_CONTEXT_ACTION_MOD_HDR) - flow_act.modify_id = attr->mod_hdr_id; + flow_act.modify_hdr = attr->modify_hdr; fdb = esw_get_prio_table(esw, attr->chain, attr->prio, !!split); if (IS_ERR(fdb)) { @@ -276,7 +276,7 @@ mlx5_eswitch_add_fwd_rule(struct mlx5_eswitch *esw, dest[i].vport.flags |= MLX5_FLOW_DEST_VPORT_VHCA_ID; if (attr->dests[i].flags & MLX5_ESW_DEST_ENCAP) { dest[i].vport.flags |= MLX5_FLOW_DEST_VPORT_REFORMAT_ID; - dest[i].vport.reformat_id = attr->dests[i].encap_id; + dest[i].vport.pkt_reformat = attr->dests[i].pkt_reformat; } } dest[i].type = MLX5_FLOW_DESTINATION_TYPE_FLOW_TABLE; @@ -1734,7 +1734,7 @@ static int esw_vport_ingress_prio_tag_config(struct mlx5_eswitch *esw, if (vport->ingress.modify_metadata_rule) { flow_act.action |= MLX5_FLOW_CONTEXT_ACTION_MOD_HDR; - flow_act.modify_id = vport->ingress.modify_metadata_id; + flow_act.modify_hdr = vport->ingress.modify_metadata; } vport->ingress.allow_rule = @@ -1770,9 +1770,11 @@ static int esw_vport_add_ingress_acl_modify_metadata(struct mlx5_eswitch *esw, MLX5_SET(set_action_in, action, data, mlx5_eswitch_get_vport_metadata_for_match(esw, vport->vport)); - err = mlx5_modify_header_alloc(esw->dev, MLX5_FLOW_NAMESPACE_ESW_INGRESS, - 1, action, &vport->ingress.modify_metadata_id); - if (err) { + vport->ingress.modify_metadata = + mlx5_modify_header_alloc(esw->dev, MLX5_FLOW_NAMESPACE_ESW_INGRESS, + 1, action); + if (IS_ERR(vport->ingress.modify_metadata)) { + err = PTR_ERR(vport->ingress.modify_metadata); esw_warn(esw->dev, "failed to alloc modify header for vport %d ingress acl (%d)\n", vport->vport, err); @@ -1780,7 +1782,7 @@ static int esw_vport_add_ingress_acl_modify_metadata(struct mlx5_eswitch *esw, } flow_act.action = MLX5_FLOW_CONTEXT_ACTION_MOD_HDR | MLX5_FLOW_CONTEXT_ACTION_ALLOW; - flow_act.modify_id = vport->ingress.modify_metadata_id; + flow_act.modify_hdr = vport->ingress.modify_metadata; vport->ingress.modify_metadata_rule = mlx5_add_flow_rules(vport->ingress.acl, &spec, &flow_act, NULL, 0); if (IS_ERR(vport->ingress.modify_metadata_rule)) { @@ -1794,7 +1796,7 @@ static int esw_vport_add_ingress_acl_modify_metadata(struct mlx5_eswitch *esw, out: if (err) - mlx5_modify_header_dealloc(esw->dev, vport->ingress.modify_metadata_id); + mlx5_modify_header_dealloc(esw->dev, vport->ingress.modify_metadata); return err; } @@ -1803,7 +1805,7 @@ void esw_vport_del_ingress_acl_modify_metadata(struct mlx5_eswitch *esw, { if (vport->ingress.modify_metadata_rule) { mlx5_del_flow_rules(vport->ingress.modify_metadata_rule); - mlx5_modify_header_dealloc(esw->dev, vport->ingress.modify_metadata_id); + mlx5_modify_header_dealloc(esw->dev, vport->ingress.modify_metadata); vport->ingress.modify_metadata_rule = NULL; } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.c b/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.c index 1e3381604b3d..488f50dfb404 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.c @@ -107,6 +107,34 @@ static int mlx5_cmd_stub_delete_fte(struct mlx5_flow_root_namespace *ns, return 0; } +static int mlx5_cmd_stub_packet_reformat_alloc(struct mlx5_flow_root_namespace *ns, + int reformat_type, + size_t size, + void *reformat_data, + enum mlx5_flow_namespace_type namespace, + struct mlx5_pkt_reformat *pkt_reformat) +{ + return 0; +} + +static void mlx5_cmd_stub_packet_reformat_dealloc(struct mlx5_flow_root_namespace *ns, + struct mlx5_pkt_reformat *pkt_reformat) +{ +} + +static int mlx5_cmd_stub_modify_header_alloc(struct mlx5_flow_root_namespace *ns, + u8 namespace, u8 num_actions, + void *modify_actions, + struct mlx5_modify_hdr *modify_hdr) +{ + return 0; +} + +static void mlx5_cmd_stub_modify_header_dealloc(struct mlx5_flow_root_namespace *ns, + struct mlx5_modify_hdr *modify_hdr) +{ +} + static int mlx5_cmd_update_root_ft(struct mlx5_flow_root_namespace *ns, struct mlx5_flow_table *ft, u32 underlay_qpn, bool disconnect) @@ -412,11 +440,13 @@ static int mlx5_cmd_set_fte(struct mlx5_core_dev *dev, } else { MLX5_SET(flow_context, in_flow_context, action, fte->action.action); - MLX5_SET(flow_context, in_flow_context, packet_reformat_id, - fte->action.reformat_id); + if (fte->action.pkt_reformat) + MLX5_SET(flow_context, in_flow_context, packet_reformat_id, + fte->action.pkt_reformat->id); } - MLX5_SET(flow_context, in_flow_context, modify_header_id, - fte->action.modify_id); + if (fte->action.modify_hdr) + MLX5_SET(flow_context, in_flow_context, modify_header_id, + fte->action.modify_hdr->id); vlan = MLX5_ADDR_OF(flow_context, in_flow_context, push_vlan); @@ -468,7 +498,7 @@ static int mlx5_cmd_set_fte(struct mlx5_core_dev *dev, MLX5_FLOW_DEST_VPORT_REFORMAT_ID)); MLX5_SET(extended_dest_format, in_dests, packet_reformat_id, - dst->dest_attr.vport.reformat_id); + dst->dest_attr.vport.pkt_reformat->id); } break; default: @@ -643,14 +673,15 @@ int mlx5_cmd_fc_bulk_query(struct mlx5_core_dev *dev, u32 base_id, int bulk_len, return mlx5_cmd_exec(dev, in, sizeof(in), out, outlen); } -int mlx5_packet_reformat_alloc(struct mlx5_core_dev *dev, - int reformat_type, - size_t size, - void *reformat_data, - enum mlx5_flow_namespace_type namespace, - u32 *packet_reformat_id) +static int mlx5_cmd_packet_reformat_alloc(struct mlx5_flow_root_namespace *ns, + int reformat_type, + size_t size, + void *reformat_data, + enum mlx5_flow_namespace_type namespace, + struct mlx5_pkt_reformat *pkt_reformat) { u32 out[MLX5_ST_SZ_DW(alloc_packet_reformat_context_out)]; + struct mlx5_core_dev *dev = ns->dev; void *packet_reformat_context_in; int max_encap_size; void *reformat; @@ -693,35 +724,36 @@ int mlx5_packet_reformat_alloc(struct mlx5_core_dev *dev, memset(out, 0, sizeof(out)); err = mlx5_cmd_exec(dev, in, inlen, out, sizeof(out)); - *packet_reformat_id = MLX5_GET(alloc_packet_reformat_context_out, - out, packet_reformat_id); + pkt_reformat->id = MLX5_GET(alloc_packet_reformat_context_out, + out, packet_reformat_id); kfree(in); return err; } -EXPORT_SYMBOL(mlx5_packet_reformat_alloc); -void mlx5_packet_reformat_dealloc(struct mlx5_core_dev *dev, - u32 packet_reformat_id) +static void mlx5_cmd_packet_reformat_dealloc(struct mlx5_flow_root_namespace *ns, + struct mlx5_pkt_reformat *pkt_reformat) { u32 in[MLX5_ST_SZ_DW(dealloc_packet_reformat_context_in)]; u32 out[MLX5_ST_SZ_DW(dealloc_packet_reformat_context_out)]; + struct mlx5_core_dev *dev = ns->dev; memset(in, 0, sizeof(in)); MLX5_SET(dealloc_packet_reformat_context_in, in, opcode, MLX5_CMD_OP_DEALLOC_PACKET_REFORMAT_CONTEXT); MLX5_SET(dealloc_packet_reformat_context_in, in, packet_reformat_id, - packet_reformat_id); + pkt_reformat->id); mlx5_cmd_exec(dev, in, sizeof(in), out, sizeof(out)); } -EXPORT_SYMBOL(mlx5_packet_reformat_dealloc); -int mlx5_modify_header_alloc(struct mlx5_core_dev *dev, - u8 namespace, u8 num_actions, - void *modify_actions, u32 *modify_header_id) +static int mlx5_cmd_modify_header_alloc(struct mlx5_flow_root_namespace *ns, + u8 namespace, u8 num_actions, + void *modify_actions, + struct mlx5_modify_hdr *modify_hdr) { u32 out[MLX5_ST_SZ_DW(alloc_modify_header_context_out)]; int max_actions, actions_size, inlen, err; + struct mlx5_core_dev *dev = ns->dev; void *actions_in; u8 table_type; u32 *in; @@ -772,26 +804,26 @@ int mlx5_modify_header_alloc(struct mlx5_core_dev *dev, memset(out, 0, sizeof(out)); err = mlx5_cmd_exec(dev, in, inlen, out, sizeof(out)); - *modify_header_id = MLX5_GET(alloc_modify_header_context_out, out, modify_header_id); + modify_hdr->id = MLX5_GET(alloc_modify_header_context_out, out, modify_header_id); kfree(in); return err; } -EXPORT_SYMBOL(mlx5_modify_header_alloc); -void mlx5_modify_header_dealloc(struct mlx5_core_dev *dev, u32 modify_header_id) +static void mlx5_cmd_modify_header_dealloc(struct mlx5_flow_root_namespace *ns, + struct mlx5_modify_hdr *modify_hdr) { u32 in[MLX5_ST_SZ_DW(dealloc_modify_header_context_in)]; u32 out[MLX5_ST_SZ_DW(dealloc_modify_header_context_out)]; + struct mlx5_core_dev *dev = ns->dev; memset(in, 0, sizeof(in)); MLX5_SET(dealloc_modify_header_context_in, in, opcode, MLX5_CMD_OP_DEALLOC_MODIFY_HEADER_CONTEXT); MLX5_SET(dealloc_modify_header_context_in, in, modify_header_id, - modify_header_id); + modify_hdr->id); mlx5_cmd_exec(dev, in, sizeof(in), out, sizeof(out)); } -EXPORT_SYMBOL(mlx5_modify_header_dealloc); static const struct mlx5_flow_cmds mlx5_flow_cmds = { .create_flow_table = mlx5_cmd_create_flow_table, @@ -803,6 +835,10 @@ static const struct mlx5_flow_cmds mlx5_flow_cmds = { .update_fte = mlx5_cmd_update_fte, .delete_fte = mlx5_cmd_delete_fte, .update_root_ft = mlx5_cmd_update_root_ft, + .packet_reformat_alloc = mlx5_cmd_packet_reformat_alloc, + .packet_reformat_dealloc = mlx5_cmd_packet_reformat_dealloc, + .modify_header_alloc = mlx5_cmd_modify_header_alloc, + .modify_header_dealloc = mlx5_cmd_modify_header_dealloc }; static const struct mlx5_flow_cmds mlx5_flow_cmd_stubs = { @@ -815,6 +851,10 @@ static const struct mlx5_flow_cmds mlx5_flow_cmd_stubs = { .update_fte = mlx5_cmd_stub_update_fte, .delete_fte = mlx5_cmd_stub_delete_fte, .update_root_ft = mlx5_cmd_stub_update_root_ft, + .packet_reformat_alloc = mlx5_cmd_stub_packet_reformat_alloc, + .packet_reformat_dealloc = mlx5_cmd_stub_packet_reformat_dealloc, + .modify_header_alloc = mlx5_cmd_stub_modify_header_alloc, + .modify_header_dealloc = mlx5_cmd_stub_modify_header_dealloc }; static const struct mlx5_flow_cmds *mlx5_fs_cmd_get_fw_cmds(void) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.h b/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.h index bc4606306009..3268654d6748 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.h @@ -75,6 +75,24 @@ struct mlx5_flow_cmds { struct mlx5_flow_table *ft, u32 underlay_qpn, bool disconnect); + + int (*packet_reformat_alloc)(struct mlx5_flow_root_namespace *ns, + int reformat_type, + size_t size, + void *reformat_data, + enum mlx5_flow_namespace_type namespace, + struct mlx5_pkt_reformat *pkt_reformat); + + void (*packet_reformat_dealloc)(struct mlx5_flow_root_namespace *ns, + struct mlx5_pkt_reformat *pkt_reformat); + + int (*modify_header_alloc)(struct mlx5_flow_root_namespace *ns, + u8 namespace, u8 num_actions, + void *modify_actions, + struct mlx5_modify_hdr *modify_hdr); + + void (*modify_header_dealloc)(struct mlx5_flow_root_namespace *ns, + struct mlx5_modify_hdr *modify_hdr); }; int mlx5_cmd_fc_alloc(struct mlx5_core_dev *dev, u32 *id); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c index 7bdec442f0ac..1d2333fd3080 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c @@ -1415,7 +1415,8 @@ static bool mlx5_flow_dests_cmp(struct mlx5_flow_destination *d1, ((d1->vport.flags & MLX5_FLOW_DEST_VPORT_VHCA_ID) ? (d1->vport.vhca_id == d2->vport.vhca_id) : true) && ((d1->vport.flags & MLX5_FLOW_DEST_VPORT_REFORMAT_ID) ? - (d1->vport.reformat_id == d2->vport.reformat_id) : true)) || + (d1->vport.pkt_reformat->id == + d2->vport.pkt_reformat->id) : true)) || (d1->type == MLX5_FLOW_DESTINATION_TYPE_FLOW_TABLE && d1->ft == d2->ft) || (d1->type == MLX5_FLOW_DESTINATION_TYPE_TIR && @@ -2888,3 +2889,105 @@ out: return err; } EXPORT_SYMBOL(mlx5_fs_remove_rx_underlay_qpn); + +static struct mlx5_flow_root_namespace +*get_root_namespace(struct mlx5_core_dev *dev, enum mlx5_flow_namespace_type ns_type) +{ + struct mlx5_flow_namespace *ns; + + if (ns_type == MLX5_FLOW_NAMESPACE_ESW_EGRESS || + ns_type == MLX5_FLOW_NAMESPACE_ESW_INGRESS) + ns = mlx5_get_flow_vport_acl_namespace(dev, ns_type, 0); + else + ns = mlx5_get_flow_namespace(dev, ns_type); + if (!ns) + return NULL; + + return find_root(&ns->node); +} + +struct mlx5_modify_hdr *mlx5_modify_header_alloc(struct mlx5_core_dev *dev, + u8 ns_type, u8 num_actions, + void *modify_actions) +{ + struct mlx5_flow_root_namespace *root; + struct mlx5_modify_hdr *modify_hdr; + int err; + + root = get_root_namespace(dev, ns_type); + if (!root) + return ERR_PTR(-EOPNOTSUPP); + + modify_hdr = kzalloc(sizeof(*modify_hdr), GFP_KERNEL); + if (!modify_hdr) + return ERR_PTR(-ENOMEM); + + modify_hdr->ns_type = ns_type; + err = root->cmds->modify_header_alloc(root, ns_type, num_actions, + modify_actions, modify_hdr); + if (err) { + kfree(modify_hdr); + return ERR_PTR(err); + } + + return modify_hdr; +} +EXPORT_SYMBOL(mlx5_modify_header_alloc); + +void mlx5_modify_header_dealloc(struct mlx5_core_dev *dev, + struct mlx5_modify_hdr *modify_hdr) +{ + struct mlx5_flow_root_namespace *root; + + root = get_root_namespace(dev, modify_hdr->ns_type); + if (WARN_ON(!root)) + return; + root->cmds->modify_header_dealloc(root, modify_hdr); + kfree(modify_hdr); +} +EXPORT_SYMBOL(mlx5_modify_header_dealloc); + +struct mlx5_pkt_reformat *mlx5_packet_reformat_alloc(struct mlx5_core_dev *dev, + int reformat_type, + size_t size, + void *reformat_data, + enum mlx5_flow_namespace_type ns_type) +{ + struct mlx5_pkt_reformat *pkt_reformat; + struct mlx5_flow_root_namespace *root; + int err; + + root = get_root_namespace(dev, ns_type); + if (!root) + return ERR_PTR(-EOPNOTSUPP); + + pkt_reformat = kzalloc(sizeof(*pkt_reformat), GFP_KERNEL); + if (!pkt_reformat) + return ERR_PTR(-ENOMEM); + + pkt_reformat->ns_type = ns_type; + pkt_reformat->reformat_type = reformat_type; + err = root->cmds->packet_reformat_alloc(root, reformat_type, size, + reformat_data, ns_type, + pkt_reformat); + if (err) { + kfree(pkt_reformat); + return ERR_PTR(err); + } + + return pkt_reformat; +} +EXPORT_SYMBOL(mlx5_packet_reformat_alloc); + +void mlx5_packet_reformat_dealloc(struct mlx5_core_dev *dev, + struct mlx5_pkt_reformat *pkt_reformat) +{ + struct mlx5_flow_root_namespace *root; + + root = get_root_namespace(dev, pkt_reformat->ns_type); + if (WARN_ON(!root)) + return; + root->cmds->packet_reformat_dealloc(root, pkt_reformat); + kfree(pkt_reformat); +} +EXPORT_SYMBOL(mlx5_packet_reformat_dealloc); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.h b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.h index 0d16b4b5ab83..ea0f221685ab 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.h @@ -38,6 +38,17 @@ #include #include +struct mlx5_modify_hdr { + enum mlx5_flow_namespace_type ns_type; + u32 id; +}; + +struct mlx5_pkt_reformat { + enum mlx5_flow_namespace_type ns_type; + int reformat_type; /* from mlx5_ifc */ + u32 id; +}; + /* FS_TYPE_PRIO_CHAINS is a PRIO that will have namespaces only, * and those are in parallel to one another when going over them to connect * a new flow table. Meaning the last flow table in a TYPE_PRIO prio in one diff --git a/include/linux/mlx5/fs.h b/include/linux/mlx5/fs.h index 97ec6be62ac4..724d276ea133 100644 --- a/include/linux/mlx5/fs.h +++ b/include/linux/mlx5/fs.h @@ -84,6 +84,8 @@ enum { FDB_SLOW_PATH, }; +struct mlx5_pkt_reformat; +struct mlx5_modify_hdr; struct mlx5_flow_table; struct mlx5_flow_group; struct mlx5_flow_namespace; @@ -121,7 +123,7 @@ struct mlx5_flow_destination { struct { u16 num; u16 vhca_id; - u32 reformat_id; + struct mlx5_pkt_reformat *pkt_reformat; u8 flags; } vport; }; @@ -195,8 +197,8 @@ enum { struct mlx5_flow_act { u32 action; - u32 reformat_id; - u32 modify_id; + struct mlx5_modify_hdr *modify_hdr; + struct mlx5_pkt_reformat *pkt_reformat; uintptr_t esp_id; u32 flags; struct mlx5_fs_vlan vlan[MLX5_FS_VLAN_DEPTH]; @@ -205,8 +207,6 @@ struct mlx5_flow_act { #define MLX5_DECLARE_FLOW_ACT(name) \ struct mlx5_flow_act name = { .action = MLX5_FLOW_CONTEXT_ACTION_FWD_DEST,\ - .reformat_id = 0, \ - .modify_id = 0, \ .flags = 0, } /* Single destination per rule. @@ -236,19 +236,18 @@ u32 mlx5_fc_id(struct mlx5_fc *counter); int mlx5_fs_add_rx_underlay_qpn(struct mlx5_core_dev *dev, u32 underlay_qpn); int mlx5_fs_remove_rx_underlay_qpn(struct mlx5_core_dev *dev, u32 underlay_qpn); -int mlx5_modify_header_alloc(struct mlx5_core_dev *dev, - u8 namespace, u8 num_actions, - void *modify_actions, u32 *modify_header_id); +struct mlx5_modify_hdr *mlx5_modify_header_alloc(struct mlx5_core_dev *dev, + u8 ns_type, u8 num_actions, + void *modify_actions); void mlx5_modify_header_dealloc(struct mlx5_core_dev *dev, - u32 modify_header_id); - -int mlx5_packet_reformat_alloc(struct mlx5_core_dev *dev, - int reformat_type, - size_t size, - void *reformat_data, - enum mlx5_flow_namespace_type namespace, - u32 *packet_reformat_id); + struct mlx5_modify_hdr *modify_hdr); + +struct mlx5_pkt_reformat *mlx5_packet_reformat_alloc(struct mlx5_core_dev *dev, + int reformat_type, + size_t size, + void *reformat_data, + enum mlx5_flow_namespace_type ns_type); void mlx5_packet_reformat_dealloc(struct mlx5_core_dev *dev, - u32 packet_reformat_id); + struct mlx5_pkt_reformat *reformat); #endif -- cgit v1.2.3 From ffd956eef69b212a724b1cc4cdc61828f3ad9104 Mon Sep 17 00:00:00 2001 From: Marc Kleine-Budde Date: Mon, 8 Oct 2018 09:02:38 +0200 Subject: can: introduce CAN midlayer private and allocate it automatically This patch introduces the CAN midlayer private structure ("struct can_ml_priv") which should be used to hold protocol specific per device data structures. For now it's only member is "struct can_dev_rcv_lists". The CAN midlayer private is allocated via alloc_netdev()'s private and assigned to "struct net_device::ml_priv" during device creation. This is done transparently for CAN drivers using alloc_candev(). The slcan, vcan and vxcan drivers which are not using alloc_candev() have been adopted manually. The memory layout of the netdev_priv allocated via alloc_candev() will looke like this: +-------------------------+ | driver's priv | +-------------------------+ | struct can_ml_priv | +-------------------------+ | array of struct sk_buff | +-------------------------+ Signed-off-by: Oleksij Rempel Signed-off-by: Oliver Hartkopp Signed-off-by: Marc Kleine-Budde --- drivers/net/can/dev.c | 22 +++++++++++++--- drivers/net/can/slcan.c | 5 +++- drivers/net/can/vcan.c | 6 +++-- drivers/net/can/vxcan.c | 3 ++- include/linux/can/can-ml.h | 66 ++++++++++++++++++++++++++++++++++++++++++++++ net/can/af_can.c | 1 + net/can/af_can.h | 15 ----------- net/can/proc.c | 1 + 8 files changed, 96 insertions(+), 23 deletions(-) create mode 100644 include/linux/can/can-ml.h (limited to 'include/linux') diff --git a/drivers/net/can/dev.c b/drivers/net/can/dev.c index 483d270664cc..9e688dc29521 100644 --- a/drivers/net/can/dev.c +++ b/drivers/net/can/dev.c @@ -12,6 +12,7 @@ #include #include #include +#include #include #include #include @@ -718,11 +719,24 @@ struct net_device *alloc_candev_mqs(int sizeof_priv, unsigned int echo_skb_max, struct can_priv *priv; int size; + /* We put the driver's priv, the CAN mid layer priv and the + * echo skb into the netdevice's priv. The memory layout for + * the netdev_priv is like this: + * + * +-------------------------+ + * | driver's priv | + * +-------------------------+ + * | struct can_ml_priv | + * +-------------------------+ + * | array of struct sk_buff | + * +-------------------------+ + */ + + size = ALIGN(sizeof_priv, NETDEV_ALIGN) + sizeof(struct can_ml_priv); + if (echo_skb_max) - size = ALIGN(sizeof_priv, sizeof(struct sk_buff *)) + + size = ALIGN(size, sizeof(struct sk_buff *)) + echo_skb_max * sizeof(struct sk_buff *); - else - size = sizeof_priv; dev = alloc_netdev_mqs(size, "can%d", NET_NAME_UNKNOWN, can_setup, txqs, rxqs); @@ -735,7 +749,7 @@ struct net_device *alloc_candev_mqs(int sizeof_priv, unsigned int echo_skb_max, if (echo_skb_max) { priv->echo_skb_max = echo_skb_max; priv->echo_skb = (void *)priv + - ALIGN(sizeof_priv, sizeof(struct sk_buff *)); + (size - echo_skb_max * sizeof(struct sk_buff *)); } priv->state = CAN_STATE_STOPPED; diff --git a/drivers/net/can/slcan.c b/drivers/net/can/slcan.c index aa97dbc797b6..5b2e95425e69 100644 --- a/drivers/net/can/slcan.c +++ b/drivers/net/can/slcan.c @@ -55,6 +55,7 @@ #include #include #include +#include MODULE_ALIAS_LDISC(N_SLCAN); MODULE_DESCRIPTION("serial line CAN interface"); @@ -514,6 +515,7 @@ static struct slcan *slc_alloc(void) char name[IFNAMSIZ]; struct net_device *dev = NULL; struct slcan *sl; + int size; for (i = 0; i < maxdev; i++) { dev = slcan_devs[i]; @@ -527,7 +529,8 @@ static struct slcan *slc_alloc(void) return NULL; sprintf(name, "slcan%d", i); - dev = alloc_netdev(sizeof(*sl), name, NET_NAME_UNKNOWN, slc_setup); + size = ALIGN(sizeof(*sl), NETDEV_ALIGN) + sizeof(struct can_ml_priv); + dev = alloc_netdev(size, name, NET_NAME_UNKNOWN, slc_setup); if (!dev) return NULL; diff --git a/drivers/net/can/vcan.c b/drivers/net/can/vcan.c index daf27133887b..6973ae09a37a 100644 --- a/drivers/net/can/vcan.c +++ b/drivers/net/can/vcan.c @@ -46,6 +46,7 @@ #include #include #include +#include #include #include #include @@ -162,8 +163,9 @@ static void vcan_setup(struct net_device *dev) } static struct rtnl_link_ops vcan_link_ops __read_mostly = { - .kind = DRV_NAME, - .setup = vcan_setup, + .kind = DRV_NAME, + .priv_size = sizeof(struct can_ml_priv), + .setup = vcan_setup, }; static __init int vcan_init_module(void) diff --git a/drivers/net/can/vxcan.c b/drivers/net/can/vxcan.c index b2106292230e..4c3eed796432 100644 --- a/drivers/net/can/vxcan.c +++ b/drivers/net/can/vxcan.c @@ -18,6 +18,7 @@ #include #include #include +#include #include #include @@ -281,7 +282,7 @@ static struct net *vxcan_get_link_net(const struct net_device *dev) static struct rtnl_link_ops vxcan_link_ops = { .kind = DRV_NAME, - .priv_size = sizeof(struct vxcan_priv), + .priv_size = ALIGN(sizeof(struct vxcan_priv), NETDEV_ALIGN) + sizeof(struct can_ml_priv), .setup = vxcan_setup, .newlink = vxcan_newlink, .dellink = vxcan_dellink, diff --git a/include/linux/can/can-ml.h b/include/linux/can/can-ml.h new file mode 100644 index 000000000000..0a9d778de8af --- /dev/null +++ b/include/linux/can/can-ml.h @@ -0,0 +1,66 @@ +/* SPDX-License-Identifier: (GPL-2.0 OR BSD-3-Clause) */ +/* Copyright (c) 2002-2007 Volkswagen Group Electronic Research + * Copyright (c) 2017 Pengutronix, Marc Kleine-Budde + * + * All rights reserved. + * + * Redistribution and use in source and binary forms, with or without + * modification, are permitted provided that the following conditions + * are met: + * 1. Redistributions of source code must retain the above copyright + * notice, this list of conditions and the following disclaimer. + * 2. 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. + * 3. Neither the name of Volkswagen nor the names of its contributors + * may be used to endorse or promote products derived from this software + * without specific prior written permission. + * + * Alternatively, provided that this notice is retained in full, this + * software may be distributed under the terms of the GNU General + * Public License ("GPL") version 2, in which case the provisions of the + * GPL apply INSTEAD OF those given above. + * + * The provided data structures and external interfaces from this code + * are not restricted to be used by modules with a GPL compatible license. + * + * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS + * "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT + * LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR + * A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT + * OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, + * SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT + * LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, + * DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY + * THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT + * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE + * OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH + * DAMAGE. + * + */ + +#ifndef CAN_ML_H +#define CAN_ML_H + +#include +#include + +#define CAN_SFF_RCV_ARRAY_SZ (1 << CAN_SFF_ID_BITS) +#define CAN_EFF_RCV_HASH_BITS 10 +#define CAN_EFF_RCV_ARRAY_SZ (1 << CAN_EFF_RCV_HASH_BITS) + +enum { RX_ERR, RX_ALL, RX_FIL, RX_INV, RX_MAX }; + +struct can_dev_rcv_lists { + struct hlist_head rx[RX_MAX]; + struct hlist_head rx_sff[CAN_SFF_RCV_ARRAY_SZ]; + struct hlist_head rx_eff[CAN_EFF_RCV_ARRAY_SZ]; + int remove_on_zero_entries; + int entries; +}; + +struct can_ml_priv { + struct can_dev_rcv_lists dev_rcv_lists; +}; + +#endif /* CAN_ML_H */ diff --git a/net/can/af_can.c b/net/can/af_can.c index d65b19003a24..723299daa04e 100644 --- a/net/can/af_can.c +++ b/net/can/af_can.c @@ -58,6 +58,7 @@ #include #include #include +#include #include #include #include diff --git a/net/can/af_can.h b/net/can/af_can.h index 25d22e534506..7c2d9161e224 100644 --- a/net/can/af_can.h +++ b/net/can/af_can.h @@ -60,21 +60,6 @@ struct receiver { struct rcu_head rcu; }; -#define CAN_SFF_RCV_ARRAY_SZ (1 << CAN_SFF_ID_BITS) -#define CAN_EFF_RCV_HASH_BITS 10 -#define CAN_EFF_RCV_ARRAY_SZ (1 << CAN_EFF_RCV_HASH_BITS) - -enum { RX_ERR, RX_ALL, RX_FIL, RX_INV, RX_MAX }; - -/* per device receive filters linked at dev->ml_priv */ -struct can_dev_rcv_lists { - struct hlist_head rx[RX_MAX]; - struct hlist_head rx_sff[CAN_SFF_RCV_ARRAY_SZ]; - struct hlist_head rx_eff[CAN_EFF_RCV_ARRAY_SZ]; - int remove_on_zero_entries; - int entries; -}; - /* statistic structures */ /* can be reset e.g. by can_init_stats() */ diff --git a/net/can/proc.c b/net/can/proc.c index 560fa3c132bf..e6881bfc3ed1 100644 --- a/net/can/proc.c +++ b/net/can/proc.c @@ -45,6 +45,7 @@ #include #include #include +#include #include #include "af_can.h" -- cgit v1.2.3 From 8df9ffb888c021fa68f9075d545f2ec5eca37200 Mon Sep 17 00:00:00 2001 From: Marc Kleine-Budde Date: Mon, 8 Oct 2018 09:02:39 +0200 Subject: can: make use of preallocated can_ml_priv for per device struct can_dev_rcv_lists This patch removes the old method of allocating the per device protocol specific memory via a netdevice_notifier. This had the drawback, that the allocation can fail, leading to a lot of null pointer checks in the code. This also makes the live cycle management of this memory quite complicated. This patch switches from the allocating the struct can_dev_rcv_lists in a NETDEV_REGISTER call to using the dev->ml_priv, which is allocated by the driver since the previous patch. Signed-off-by: Oleksij Rempel Acked-by: Oliver Hartkopp Signed-off-by: Marc Kleine-Budde --- drivers/net/can/dev.c | 2 ++ drivers/net/can/slcan.c | 1 + drivers/net/can/vcan.c | 1 + drivers/net/can/vxcan.c | 1 + include/linux/can/can-ml.h | 1 - net/can/af_can.c | 45 +++++++-------------------------------------- 6 files changed, 12 insertions(+), 39 deletions(-) (limited to 'include/linux') diff --git a/drivers/net/can/dev.c b/drivers/net/can/dev.c index 9e688dc29521..b429550c4cc2 100644 --- a/drivers/net/can/dev.c +++ b/drivers/net/can/dev.c @@ -746,6 +746,8 @@ struct net_device *alloc_candev_mqs(int sizeof_priv, unsigned int echo_skb_max, priv = netdev_priv(dev); priv->dev = dev; + dev->ml_priv = (void *)priv + ALIGN(sizeof_priv, NETDEV_ALIGN); + if (echo_skb_max) { priv->echo_skb_max = echo_skb_max; priv->echo_skb = (void *)priv + diff --git a/drivers/net/can/slcan.c b/drivers/net/can/slcan.c index 5b2e95425e69..bb6032211043 100644 --- a/drivers/net/can/slcan.c +++ b/drivers/net/can/slcan.c @@ -536,6 +536,7 @@ static struct slcan *slc_alloc(void) dev->base_addr = i; sl = netdev_priv(dev); + dev->ml_priv = (void *)sl + ALIGN(sizeof(*sl), NETDEV_ALIGN); /* Initialize channel control data */ sl->magic = SLCAN_MAGIC; diff --git a/drivers/net/can/vcan.c b/drivers/net/can/vcan.c index 6973ae09a37a..39ca14b0585d 100644 --- a/drivers/net/can/vcan.c +++ b/drivers/net/can/vcan.c @@ -153,6 +153,7 @@ static void vcan_setup(struct net_device *dev) dev->addr_len = 0; dev->tx_queue_len = 0; dev->flags = IFF_NOARP; + dev->ml_priv = netdev_priv(dev); /* set flags according to driver capabilities */ if (echo) diff --git a/drivers/net/can/vxcan.c b/drivers/net/can/vxcan.c index 4c3eed796432..d6ba9426be4d 100644 --- a/drivers/net/can/vxcan.c +++ b/drivers/net/can/vxcan.c @@ -147,6 +147,7 @@ static void vxcan_setup(struct net_device *dev) dev->flags = (IFF_NOARP|IFF_ECHO); dev->netdev_ops = &vxcan_netdev_ops; dev->needs_free_netdev = true; + dev->ml_priv = netdev_priv(dev) + ALIGN(sizeof(struct vxcan_priv), NETDEV_ALIGN); } /* forward declaration for rtnl_create_link() */ diff --git a/include/linux/can/can-ml.h b/include/linux/can/can-ml.h index 0a9d778de8af..79ccf6bfa232 100644 --- a/include/linux/can/can-ml.h +++ b/include/linux/can/can-ml.h @@ -55,7 +55,6 @@ struct can_dev_rcv_lists { struct hlist_head rx[RX_MAX]; struct hlist_head rx_sff[CAN_SFF_RCV_ARRAY_SZ]; struct hlist_head rx_eff[CAN_EFF_RCV_ARRAY_SZ]; - int remove_on_zero_entries; int entries; }; diff --git a/net/can/af_can.c b/net/can/af_can.c index 723299daa04e..6ed85e2f72f0 100644 --- a/net/can/af_can.c +++ b/net/can/af_can.c @@ -302,10 +302,12 @@ EXPORT_SYMBOL(can_send); static struct can_dev_rcv_lists *can_dev_rcv_lists_find(struct net *net, struct net_device *dev) { - if (!dev) + if (dev) { + struct can_ml_priv *ml_priv = dev->ml_priv; + return &ml_priv->dev_rcv_lists; + } else { return net->can.rx_alldev_list; - else - return (struct can_dev_rcv_lists *)dev->ml_priv; + } } /** @@ -561,12 +563,6 @@ void can_rx_unregister(struct net *net, struct net_device *dev, canid_t can_id, if (rcv_lists_stats->rcv_entries > 0) rcv_lists_stats->rcv_entries--; - /* remove device structure requested by NETDEV_UNREGISTER */ - if (dev_rcv_lists->remove_on_zero_entries && !dev_rcv_lists->entries) { - kfree(dev_rcv_lists); - dev->ml_priv = NULL; - } - out: spin_unlock(&net->can.rcvlists_lock); @@ -788,41 +784,14 @@ static int can_notifier(struct notifier_block *nb, unsigned long msg, void *ptr) { struct net_device *dev = netdev_notifier_info_to_dev(ptr); - struct can_dev_rcv_lists *dev_rcv_lists; if (dev->type != ARPHRD_CAN) return NOTIFY_DONE; switch (msg) { case NETDEV_REGISTER: - - /* create new dev_rcv_lists for this device */ - dev_rcv_lists = kzalloc(sizeof(*dev_rcv_lists), GFP_KERNEL); - if (!dev_rcv_lists) - return NOTIFY_DONE; - BUG_ON(dev->ml_priv); - dev->ml_priv = dev_rcv_lists; - - break; - - case NETDEV_UNREGISTER: - spin_lock(&dev_net(dev)->can.rcvlists_lock); - - dev_rcv_lists = dev->ml_priv; - if (dev_rcv_lists) { - if (dev_rcv_lists->entries) - dev_rcv_lists->remove_on_zero_entries = 1; - else { - kfree(dev_rcv_lists); - dev->ml_priv = NULL; - } - } else { - pr_err("can: notifier: receive list not found for dev %s\n", - dev->name); - } - - spin_unlock(&dev_net(dev)->can.rcvlists_lock); - + WARN(!dev->ml_priv, + "No CAN mid layer private allocated, please fix your driver and use alloc_candev()!\n"); break; } -- cgit v1.2.3 From 9868b5d44f3df9dd75247acd23dddff0a42f79be Mon Sep 17 00:00:00 2001 From: Kurt Van Dijck Date: Mon, 8 Oct 2018 11:48:33 +0200 Subject: can: introduce CAN_REQUIRED_SIZE macro The size of this structure will be increased with J1939 support. To stay binary compatible, the CAN_REQUIRED_SIZE macro is introduced for existing CAN protocols. Signed-off-by: Kurt Van Dijck Signed-off-by: Oleksij Rempel Acked-by: Oliver Hartkopp Signed-off-by: Marc Kleine-Budde --- include/linux/can/core.h | 8 ++++++++ net/can/bcm.c | 4 ++-- net/can/raw.c | 4 ++-- 3 files changed, 12 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/can/core.h b/include/linux/can/core.h index 708c10d3417a..8339071ab08b 100644 --- a/include/linux/can/core.h +++ b/include/linux/can/core.h @@ -41,6 +41,14 @@ struct can_proto { struct proto *prot; }; +/* required_size + * macro to find the minimum size of a struct + * that includes a requested member + */ +#define CAN_REQUIRED_SIZE(struct_type, member) \ + (offsetof(typeof(struct_type), member) + \ + sizeof(((typeof(struct_type) *)(NULL))->member)) + /* function prototypes for the CAN networklayer core (af_can.c) */ extern int can_proto_register(const struct can_proto *cp); diff --git a/net/can/bcm.c b/net/can/bcm.c index 28fd1a1c8487..c96fa0f33db3 100644 --- a/net/can/bcm.c +++ b/net/can/bcm.c @@ -1294,7 +1294,7 @@ static int bcm_sendmsg(struct socket *sock, struct msghdr *msg, size_t size) /* no bound device as default => check msg_name */ DECLARE_SOCKADDR(struct sockaddr_can *, addr, msg->msg_name); - if (msg->msg_namelen < sizeof(*addr)) + if (msg->msg_namelen < CAN_REQUIRED_SIZE(*addr, can_ifindex)) return -EINVAL; if (addr->can_family != AF_CAN) @@ -1536,7 +1536,7 @@ static int bcm_connect(struct socket *sock, struct sockaddr *uaddr, int len, struct net *net = sock_net(sk); int ret = 0; - if (len < sizeof(*addr)) + if (len < CAN_REQUIRED_SIZE(*addr, can_ifindex)) return -EINVAL; lock_sock(sk); diff --git a/net/can/raw.c b/net/can/raw.c index fdbc36140e9b..59c039d73c6d 100644 --- a/net/can/raw.c +++ b/net/can/raw.c @@ -396,7 +396,7 @@ static int raw_bind(struct socket *sock, struct sockaddr *uaddr, int len) int err = 0; int notify_enetdown = 0; - if (len < sizeof(*addr)) + if (len < CAN_REQUIRED_SIZE(*addr, can_ifindex)) return -EINVAL; if (addr->can_family != AF_CAN) return -EINVAL; @@ -733,7 +733,7 @@ static int raw_sendmsg(struct socket *sock, struct msghdr *msg, size_t size) if (msg->msg_name) { DECLARE_SOCKADDR(struct sockaddr_can *, addr, msg->msg_name); - if (msg->msg_namelen < sizeof(*addr)) + if (msg->msg_namelen < CAN_REQUIRED_SIZE(*addr, can_ifindex)) return -EINVAL; if (addr->can_family != AF_CAN) -- cgit v1.2.3 From 9d71dd0c70099914fcd063135da3c580865e924c Mon Sep 17 00:00:00 2001 From: The j1939 authors Date: Mon, 8 Oct 2018 11:48:36 +0200 Subject: can: add support of SAE J1939 protocol SAE J1939 is the vehicle bus recommended practice used for communication and diagnostics among vehicle components. Originating in the car and heavy-duty truck industry in the United States, it is now widely used in other parts of the world. J1939, ISO 11783 and NMEA 2000 all share the same high level protocol. SAE J1939 can be considered the replacement for the older SAE J1708 and SAE J1587 specifications. Acked-by: Oliver Hartkopp Signed-off-by: Bastian Stender Signed-off-by: Elenita Hinds Signed-off-by: kbuild test robot Signed-off-by: Kurt Van Dijck Signed-off-by: Maxime Jayat Signed-off-by: Robin van der Gracht Signed-off-by: Oleksij Rempel Signed-off-by: Marc Kleine-Budde --- Documentation/networking/index.rst | 1 + Documentation/networking/j1939.rst | 422 ++++++++ MAINTAINERS | 10 + include/linux/can/can-ml.h | 3 + include/uapi/linux/can/j1939.h | 99 ++ net/can/Kconfig | 2 + net/can/Makefile | 2 + net/can/j1939/Kconfig | 15 + net/can/j1939/Makefile | 10 + net/can/j1939/address-claim.c | 230 ++++ net/can/j1939/bus.c | 333 ++++++ net/can/j1939/j1939-priv.h | 338 ++++++ net/can/j1939/main.c | 403 +++++++ net/can/j1939/socket.c | 1160 +++++++++++++++++++++ net/can/j1939/transport.c | 2027 ++++++++++++++++++++++++++++++++++++ 15 files changed, 5055 insertions(+) create mode 100644 Documentation/networking/j1939.rst create mode 100644 include/uapi/linux/can/j1939.h create mode 100644 net/can/j1939/Kconfig create mode 100644 net/can/j1939/Makefile create mode 100644 net/can/j1939/address-claim.c create mode 100644 net/can/j1939/bus.c create mode 100644 net/can/j1939/j1939-priv.h create mode 100644 net/can/j1939/main.c create mode 100644 net/can/j1939/socket.c create mode 100644 net/can/j1939/transport.c (limited to 'include/linux') diff --git a/Documentation/networking/index.rst b/Documentation/networking/index.rst index 37eabc17894c..0481d0ffebed 100644 --- a/Documentation/networking/index.rst +++ b/Documentation/networking/index.rst @@ -17,6 +17,7 @@ Contents: devlink-trap devlink-trap-netdevsim ieee802154 + j1939 kapi z8530book msg_zerocopy diff --git a/Documentation/networking/j1939.rst b/Documentation/networking/j1939.rst new file mode 100644 index 000000000000..ce7e7a044e08 --- /dev/null +++ b/Documentation/networking/j1939.rst @@ -0,0 +1,422 @@ +.. SPDX-License-Identifier: (GPL-2.0 OR MIT) + +=================== +J1939 Documentation +=================== + +Overview / What Is J1939 +======================== + +SAE J1939 defines a higher layer protocol on CAN. It implements a more +sophisticated addressing scheme and extends the maximum packet size above 8 +bytes. Several derived specifications exist, which differ from the original +J1939 on the application level, like MilCAN A, NMEA2000 and especially +ISO-11783 (ISOBUS). This last one specifies the so-called ETP (Extended +Transport Protocol) which is has been included in this implementation. This +results in a maximum packet size of ((2 ^ 24) - 1) * 7 bytes == 111 MiB. + +Specifications used +------------------- + +* SAE J1939-21 : data link layer +* SAE J1939-81 : network management +* ISO 11783-6 : Virtual Terminal (Extended Transport Protocol) + +.. _j1939-motivation: + +Motivation +========== + +Given the fact there's something like SocketCAN with an API similar to BSD +sockets, we found some reasons to justify a kernel implementation for the +addressing and transport methods used by J1939. + +* **Addressing:** when a process on an ECU communicates via J1939, it should + not necessarily know its source address. Although at least one process per + ECU should know the source address. Other processes should be able to reuse + that address. This way, address parameters for different processes + cooperating for the same ECU, are not duplicated. This way of working is + closely related to the UNIX concept where programs do just one thing, and do + it well. + +* **Dynamic addressing:** Address Claiming in J1939 is time critical. + Furthermore data transport should be handled properly during the address + negotiation. Putting this functionality in the kernel eliminates it as a + requirement for _every_ user space process that communicates via J1939. This + results in a consistent J1939 bus with proper addressing. + +* **Transport:** both TP & ETP reuse some PGNs to relay big packets over them. + Different processes may thus use the same TP & ETP PGNs without actually + knowing it. The individual TP & ETP sessions _must_ be serialized + (synchronized) between different processes. The kernel solves this problem + properly and eliminates the serialization (synchronization) as a requirement + for _every_ user space process that communicates via J1939. + +J1939 defines some other features (relaying, gateway, fast packet transport, +...). In-kernel code for these would not contribute to protocol stability. +Therefore, these parts are left to user space. + +The J1939 sockets operate on CAN network devices (see SocketCAN). Any J1939 +user space library operating on CAN raw sockets will still operate properly. +Since such library does not communicate with the in-kernel implementation, care +must be taken that these two do not interfere. In practice, this means they +cannot share ECU addresses. A single ECU (or virtual ECU) address is used by +the library exclusively, or by the in-kernel system exclusively. + +J1939 concepts +============== + +PGN +--- + +The PGN (Parameter Group Number) is a number to identify a packet. The PGN +is composed as follows: +1 bit : Reserved Bit +1 bit : Data Page +8 bits : PF (PDU Format) +8 bits : PS (PDU Specific) + +In J1939-21 distinction is made between PDU1 format (where PF < 240) and PDU2 +format (where PF >= 240). Furthermore, when using PDU2 format, the PS-field +contains a so-called Group Extension, which is part of the PGN. When using PDU2 +format, the Group Extension is set in the PS-field. + +On the other hand, when using PDU1 format, the PS-field contains a so-called +Destination Address, which is _not_ part of the PGN. When communicating a PGN +from user space to kernel (or visa versa) and PDU2 format is used, the PS-field +of the PGN shall be set to zero. The Destination Address shall be set +elsewhere. + +Regarding PGN mapping to 29-bit CAN identifier, the Destination Address shall +be get/set from/to the appropriate bits of the identifier by the kernel. + + +Addressing +---------- + +Both static and dynamic addressing methods can be used. + +For static addresses, no extra checks are made by the kernel, and provided +addresses are considered right. This responsibility is for the OEM or system +integrator. + +For dynamic addressing, so-called Address Claiming, extra support is foreseen +in the kernel. In J1939 any ECU is known by it's 64-bit NAME. At the moment of +a successful address claim, the kernel keeps track of both NAME and source +address being claimed. This serves as a base for filter schemes. By default, +packets with a destination that is not locally, will be rejected. + +Mixed mode packets (from a static to a dynamic address or vice versa) are +allowed. The BSD sockets define separate API calls for getting/setting the +local & remote address and are applicable for J1939 sockets. + +Filtering +--------- + +J1939 defines white list filters per socket that a user can set in order to +receive a subset of the J1939 traffic. Filtering can be based on: + +* SA +* SOURCE_NAME +* PGN + +When multiple filters are in place for a single socket, and a packet comes in +that matches several of those filters, the packet is only received once for +that socket. + +How to Use J1939 +================ + +API Calls +--------- + +On CAN, you first need to open a socket for communicating over a CAN network. +To use J1939, #include . From there, will be +included too. To open a socket, use: + +.. code-block:: C + + s = socket(PF_CAN, SOCK_DGRAM, CAN_J1939); + +J1939 does use SOCK_DGRAM sockets. In the J1939 specification, connections are +mentioned in the context of transport protocol sessions. These still deliver +packets to the other end (using several CAN packets). SOCK_STREAM is not +supported. + +After the successful creation of the socket, you would normally use the bind(2) +and/or connect(2) system call to bind the socket to a CAN interface. After +binding and/or connecting the socket, you can read(2) and write(2) from/to the +socket or use send(2), sendto(2), sendmsg(2) and the recv*() counterpart +operations on the socket as usual. There are also J1939 specific socket options +described below. + +In order to send data, a bind(2) must have been successful. bind(2) assigns a +local address to a socket. + +Different from CAN is that the payload data is just the data that get send, +without it's header info. The header info is derived from the sockaddr supplied +to bind(2), connect(2), sendto(2) and recvfrom(2). A write(2) with size 4 will +result in a packet with 4 bytes. + +The sockaddr structure has extensions for use with J1939 as specified below: + +.. code-block:: C + + struct sockaddr_can { + sa_family_t can_family; + int can_ifindex; + union { + struct { + __u64 name; + /* pgn: + * 8 bit: PS in PDU2 case, else 0 + * 8 bit: PF + * 1 bit: DP + * 1 bit: reserved + */ + __u32 pgn; + __u8 addr; + } j1939; + } can_addr; + } + +can_family & can_ifindex serve the same purpose as for other SocketCAN sockets. + +can_addr.j1939.pgn specifies the PGN (max 0x3ffff). Individual bits are +specified above. + +can_addr.j1939.name contains the 64-bit J1939 NAME. + +can_addr.j1939.addr contains the address. + +The bind(2) system call assigns the local address, i.e. the source address when +sending packages. If a PGN during bind(2) is set, it's used as a RX filter. +I.e. only packets with a matching PGN are received. If an ADDR or NAME is set +it is used as a receive filter, too. It will match the destination NAME or ADDR +of the incoming packet. The NAME filter will work only if appropriate Address +Claiming for this name was done on the CAN bus and registered/cached by the +kernel. + +On the other hand connect(2) assigns the remote address, i.e. the destination +address. The PGN from connect(2) is used as the default PGN when sending +packets. If ADDR or NAME is set it will be used as the default destination ADDR +or NAME. Further a set ADDR or NAME during connect(2) is used as a receive +filter. It will match the source NAME or ADDR of the incoming packet. + +Both write(2) and send(2) will send a packet with local address from bind(2) and +the remote address from connect(2). Use sendto(2) to overwrite the destination +address. + +If can_addr.j1939.name is set (!= 0) the NAME is looked up by the kernel and +the corresponding ADDR is used. If can_addr.j1939.name is not set (== 0), +can_addr.j1939.addr is used. + +When creating a socket, reasonable defaults are set. Some options can be +modified with setsockopt(2) & getsockopt(2). + +RX path related options: + +- SO_J1939_FILTER - configure array of filters +- SO_J1939_PROMISC - disable filters set by bind(2) and connect(2) + +By default no broadcast packets can be send or received. To enable sending or +receiving broadcast packets use the socket option SO_BROADCAST: + +.. code-block:: C + + int value = 1; + setsockopt(sock, SOL_SOCKET, SO_BROADCAST, &value, sizeof(value)); + +The following diagram illustrates the RX path: + +.. code:: + + +--------------------+ + | incoming packet | + +--------------------+ + | + V + +--------------------+ + | SO_J1939_PROMISC? | + +--------------------+ + | | + no | | yes + | | + .---------' `---------. + | | + +---------------------------+ | + | bind() + connect() + | | + | SOCK_BROADCAST filter | | + +---------------------------+ | + | | + |<---------------------' + V + +---------------------------+ + | SO_J1939_FILTER | + +---------------------------+ + | + V + +---------------------------+ + | socket recv() | + +---------------------------+ + +TX path related options: +SO_J1939_SEND_PRIO - change default send priority for the socket + +Message Flags during send() and Related System Calls +^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ + +send(2), sendto(2) and sendmsg(2) take a 'flags' argument. Currently +supported flags are: + +* MSG_DONTWAIT, i.e. non-blocking operation. + +recvmsg(2) +^^^^^^^^^ + +In most cases recvmsg(2) is needed if you want to extract more information than +recvfrom(2) can provide. For example package priority and timestamp. The +Destination Address, name and packet priority (if applicable) are attached to +the msghdr in the recvmsg(2) call. They can be extracted using cmsg(3) macros, +with cmsg_level == SOL_J1939 && cmsg_type == SCM_J1939_DEST_ADDR, +SCM_J1939_DEST_NAME or SCM_J1939_PRIO. The returned data is a uint8_t for +priority and dst_addr, and uint64_t for dst_name. + +.. code-block:: C + + uint8_t priority, dst_addr; + uint64_t dst_name; + + for (cmsg = CMSG_FIRSTHDR(&msg); cmsg; cmsg = CMSG_NXTHDR(&msg, cmsg)) { + switch (cmsg->cmsg_level) { + case SOL_CAN_J1939: + if (cmsg->cmsg_type == SCM_J1939_DEST_ADDR) + dst_addr = *CMSG_DATA(cmsg); + else if (cmsg->cmsg_type == SCM_J1939_DEST_NAME) + memcpy(&dst_name, CMSG_DATA(cmsg), cmsg->cmsg_len - CMSG_LEN(0)); + else if (cmsg->cmsg_type == SCM_J1939_PRIO) + priority = *CMSG_DATA(cmsg); + break; + } + } + +Dynamic Addressing +------------------ + +Distinction has to be made between using the claimed address and doing an +address claim. To use an already claimed address, one has to fill in the +j1939.name member and provide it to bind(2). If the name had claimed an address +earlier, all further messages being sent will use that address. And the +j1939.addr member will be ignored. + +An exception on this is PGN 0x0ee00. This is the "Address Claim/Cannot Claim +Address" message and the kernel will use the j1939.addr member for that PGN if +necessary. + +To claim an address following code example can be used: + +.. code-block:: C + + struct sockaddr_can baddr = { + .can_family = AF_CAN, + .can_addr.j1939 = { + .name = name, + .addr = J1939_IDLE_ADDR, + .pgn = J1939_NO_PGN, /* to disable bind() rx filter for PGN */ + }, + .can_ifindex = if_nametoindex("can0"), + }; + + bind(sock, (struct sockaddr *)&baddr, sizeof(baddr)); + + /* for Address Claiming broadcast must be allowed */ + int value = 1; + setsockopt(sock, SOL_SOCKET, SO_BROADCAST, &value, sizeof(value)); + + /* configured advanced RX filter with PGN needed for Address Claiming */ + const struct j1939_filter filt[] = { + { + .pgn = J1939_PGN_ADDRESS_CLAIMED, + .pgn_mask = J1939_PGN_PDU1_MAX, + }, { + .pgn = J1939_PGN_ADDRESS_REQUEST, + .pgn_mask = J1939_PGN_PDU1_MAX, + }, { + .pgn = J1939_PGN_ADDRESS_COMMANDED, + .pgn_mask = J1939_PGN_MAX, + }, + }; + + setsockopt(sock, SOL_CAN_J1939, SO_J1939_FILTER, &filt, sizeof(filt)); + + uint64_t dat = htole64(name); + const struct sockaddr_can saddr = { + .can_family = AF_CAN, + .can_addr.j1939 = { + .pgn = J1939_PGN_ADDRESS_CLAIMED, + .addr = J1939_NO_ADDR, + }, + }; + + /* Afterwards do a sendto(2) with data set to the NAME (Little Endian). If the + * NAME provided, does not match the j1939.name provided to bind(2), EPROTO + * will be returned. + */ + sendto(sock, dat, sizeof(dat), 0, (const struct sockaddr *)&saddr, sizeof(saddr)); + +If no-one else contests the address claim within 250ms after transmission, the +kernel marks the NAME-SA assignment as valid. The valid assignment will be kept +among other valid NAME-SA assignments. From that point, any socket bound to the +NAME can send packets. + +If another ECU claims the address, the kernel will mark the NAME-SA expired. +No socket bound to the NAME can send packets (other than address claims). To +claim another address, some socket bound to NAME, must bind(2) again, but with +only j1939.addr changed to the new SA, and must then send a valid address claim +packet. This restarts the state machine in the kernel (and any other +participant on the bus) for this NAME. + +can-utils also include the jacd tool, so it can be used as code example or as +default Address Claiming daemon. + +Send Examples +------------- + +Static Addressing +^^^^^^^^^^^^^^^^^ + +This example will send a PGN (0x12300) from SA 0x20 to DA 0x30. + +Bind: + +.. code-block:: C + + struct sockaddr_can baddr = { + .can_family = AF_CAN, + .can_addr.j1939 = { + .name = J1939_NO_NAME, + .addr = 0x20, + .pgn = J1939_NO_PGN, + }, + .can_ifindex = if_nametoindex("can0"), + }; + + bind(sock, (struct sockaddr *)&baddr, sizeof(baddr)); + +Now, the socket 'sock' is bound to the SA 0x20. Since no connect(2) was called, +at this point we can use only sendto(2) or sendmsg(2). + +Send: + +.. code-block:: C + + const struct sockaddr_can saddr = { + .can_family = AF_CAN, + .can_addr.j1939 = { + .name = J1939_NO_NAME; + .pgn = 0x30, + .addr = 0x12300, + }, + }; + + sendto(sock, dat, sizeof(dat), 0, (const struct sockaddr *)&saddr, sizeof(saddr)); diff --git a/MAINTAINERS b/MAINTAINERS index a081c477d1d1..844f416437c4 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -3669,6 +3669,16 @@ F: include/uapi/linux/can/bcm.h F: include/uapi/linux/can/raw.h F: include/uapi/linux/can/gw.h +CAN-J1939 NETWORK LAYER +M: Robin van der Gracht +M: Oleksij Rempel +R: Pengutronix Kernel Team +L: linux-can@vger.kernel.org +S: Maintained +F: Documentation/networking/j1939.txt +F: net/can/j1939/ +F: include/uapi/linux/can/j1939.h + CAPABILITIES M: Serge Hallyn L: linux-security-module@vger.kernel.org diff --git a/include/linux/can/can-ml.h b/include/linux/can/can-ml.h index 79ccf6bfa232..2f5d731ae251 100644 --- a/include/linux/can/can-ml.h +++ b/include/linux/can/can-ml.h @@ -60,6 +60,9 @@ struct can_dev_rcv_lists { struct can_ml_priv { struct can_dev_rcv_lists dev_rcv_lists; +#ifdef CAN_J1939 + struct j1939_priv *j1939_priv; +#endif }; #endif /* CAN_ML_H */ diff --git a/include/uapi/linux/can/j1939.h b/include/uapi/linux/can/j1939.h new file mode 100644 index 000000000000..c32325342d30 --- /dev/null +++ b/include/uapi/linux/can/j1939.h @@ -0,0 +1,99 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ +/* + * j1939.h + * + * Copyright (c) 2010-2011 EIA Electronics + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + */ + +#ifndef _UAPI_CAN_J1939_H_ +#define _UAPI_CAN_J1939_H_ + +#include +#include +#include + +#define J1939_MAX_UNICAST_ADDR 0xfd +#define J1939_IDLE_ADDR 0xfe +#define J1939_NO_ADDR 0xff /* == broadcast or no addr */ +#define J1939_NO_NAME 0 +#define J1939_PGN_REQUEST 0x0ea00 /* Request PG */ +#define J1939_PGN_ADDRESS_CLAIMED 0x0ee00 /* Address Claimed */ +#define J1939_PGN_ADDRESS_COMMANDED 0x0fed8 /* Commanded Address */ +#define J1939_PGN_PDU1_MAX 0x3ff00 +#define J1939_PGN_MAX 0x3ffff +#define J1939_NO_PGN 0x40000 + +/* J1939 Parameter Group Number + * + * bit 0-7 : PDU Specific (PS) + * bit 8-15 : PDU Format (PF) + * bit 16 : Data Page (DP) + * bit 17 : Reserved (R) + * bit 19-31 : set to zero + */ +typedef __u32 pgn_t; + +/* J1939 Priority + * + * bit 0-2 : Priority (P) + * bit 3-7 : set to zero + */ +typedef __u8 priority_t; + +/* J1939 NAME + * + * bit 0-20 : Identity Number + * bit 21-31 : Manufacturer Code + * bit 32-34 : ECU Instance + * bit 35-39 : Function Instance + * bit 40-47 : Function + * bit 48 : Reserved + * bit 49-55 : Vehicle System + * bit 56-59 : Vehicle System Instance + * bit 60-62 : Industry Group + * bit 63 : Arbitrary Address Capable + */ +typedef __u64 name_t; + +/* J1939 socket options */ +#define SOL_CAN_J1939 (SOL_CAN_BASE + CAN_J1939) +enum { + SO_J1939_FILTER = 1, /* set filters */ + SO_J1939_PROMISC = 2, /* set/clr promiscuous mode */ + SO_J1939_SEND_PRIO = 3, + SO_J1939_ERRQUEUE = 4, +}; + +enum { + SCM_J1939_DEST_ADDR = 1, + SCM_J1939_DEST_NAME = 2, + SCM_J1939_PRIO = 3, + SCM_J1939_ERRQUEUE = 4, +}; + +enum { + J1939_NLA_PAD, + J1939_NLA_BYTES_ACKED, +}; + +enum { + J1939_EE_INFO_NONE, + J1939_EE_INFO_TX_ABORT, +}; + +struct j1939_filter { + name_t name; + name_t name_mask; + pgn_t pgn; + pgn_t pgn_mask; + __u8 addr; + __u8 addr_mask; +}; + +#define J1939_FILTER_MAX 512 /* maximum number of j1939_filter set via setsockopt() */ + +#endif /* !_UAPI_CAN_J1939_H_ */ diff --git a/net/can/Kconfig b/net/can/Kconfig index d4319aa3e1b1..d77042752457 100644 --- a/net/can/Kconfig +++ b/net/can/Kconfig @@ -53,6 +53,8 @@ config CAN_GW They can be modified with AND/OR/XOR/SET operations as configured by the netlink configuration interface known e.g. from iptables. +source "net/can/j1939/Kconfig" + source "drivers/net/can/Kconfig" endif diff --git a/net/can/Makefile b/net/can/Makefile index 1242bbbfe57f..08bd217fc051 100644 --- a/net/can/Makefile +++ b/net/can/Makefile @@ -15,3 +15,5 @@ can-bcm-y := bcm.o obj-$(CONFIG_CAN_GW) += can-gw.o can-gw-y := gw.o + +obj-$(CONFIG_CAN_J1939) += j1939/ diff --git a/net/can/j1939/Kconfig b/net/can/j1939/Kconfig new file mode 100644 index 000000000000..2998298b71ec --- /dev/null +++ b/net/can/j1939/Kconfig @@ -0,0 +1,15 @@ +# SPDX-License-Identifier: GPL-2.0 +# +# SAE J1939 network layer core configuration +# + +config CAN_J1939 + tristate "SAE J1939" + depends on CAN + help + SAE J1939 + Say Y to have in-kernel support for j1939 socket type. This + allows communication according to SAE j1939. + The relevant parts in kernel are + SAE j1939-21 (datalink & transport protocol) + & SAE j1939-81 (network management). diff --git a/net/can/j1939/Makefile b/net/can/j1939/Makefile new file mode 100644 index 000000000000..19181bdae173 --- /dev/null +++ b/net/can/j1939/Makefile @@ -0,0 +1,10 @@ +# SPDX-License-Identifier: GPL-2.0 + +obj-$(CONFIG_CAN_J1939) += can-j1939.o + +can-j1939-objs := \ + address-claim.o \ + bus.o \ + main.o \ + socket.o \ + transport.o diff --git a/net/can/j1939/address-claim.c b/net/can/j1939/address-claim.c new file mode 100644 index 000000000000..f33c47327927 --- /dev/null +++ b/net/can/j1939/address-claim.c @@ -0,0 +1,230 @@ +// SPDX-License-Identifier: GPL-2.0 +// Copyright (c) 2010-2011 EIA Electronics, +// Kurt Van Dijck +// Copyright (c) 2010-2011 EIA Electronics, +// Pieter Beyens +// Copyright (c) 2017-2019 Pengutronix, +// Marc Kleine-Budde +// Copyright (c) 2017-2019 Pengutronix, +// Oleksij Rempel + +/* J1939 Address Claiming. + * Address Claiming in the kernel + * - keeps track of the AC states of ECU's, + * - resolves NAME<=>SA taking into account the AC states of ECU's. + * + * All Address Claim msgs (including host-originated msg) are processed + * at the receive path (a sent msg is always received again via CAN echo). + * As such, the processing of AC msgs is done in the order on which msgs + * are sent on the bus. + * + * This module doesn't send msgs itself (e.g. replies on Address Claims), + * this is the responsibility of a user space application or daemon. + */ + +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt + +#include +#include + +#include "j1939-priv.h" + +static inline name_t j1939_skb_to_name(const struct sk_buff *skb) +{ + return le64_to_cpup((__le64 *)skb->data); +} + +static inline bool j1939_ac_msg_is_request(struct sk_buff *skb) +{ + struct j1939_sk_buff_cb *skcb = j1939_skb_to_cb(skb); + int req_pgn; + + if (skb->len < 3 || skcb->addr.pgn != J1939_PGN_REQUEST) + return false; + + req_pgn = skb->data[0] | (skb->data[1] << 8) | (skb->data[2] << 16); + + return req_pgn == J1939_PGN_ADDRESS_CLAIMED; +} + +static int j1939_ac_verify_outgoing(struct j1939_priv *priv, + struct sk_buff *skb) +{ + struct j1939_sk_buff_cb *skcb = j1939_skb_to_cb(skb); + + if (skb->len != 8) { + netdev_notice(priv->ndev, "tx address claim with dlc %i\n", + skb->len); + return -EPROTO; + } + + if (skcb->addr.src_name != j1939_skb_to_name(skb)) { + netdev_notice(priv->ndev, "tx address claim with different name\n"); + return -EPROTO; + } + + if (skcb->addr.sa == J1939_NO_ADDR) { + netdev_notice(priv->ndev, "tx address claim with broadcast sa\n"); + return -EPROTO; + } + + /* ac must always be a broadcast */ + if (skcb->addr.dst_name || skcb->addr.da != J1939_NO_ADDR) { + netdev_notice(priv->ndev, "tx address claim with dest, not broadcast\n"); + return -EPROTO; + } + return 0; +} + +int j1939_ac_fixup(struct j1939_priv *priv, struct sk_buff *skb) +{ + struct j1939_sk_buff_cb *skcb = j1939_skb_to_cb(skb); + int ret; + u8 addr; + + /* network mgmt: address claiming msgs */ + if (skcb->addr.pgn == J1939_PGN_ADDRESS_CLAIMED) { + struct j1939_ecu *ecu; + + ret = j1939_ac_verify_outgoing(priv, skb); + /* return both when failure & when successful */ + if (ret < 0) + return ret; + ecu = j1939_ecu_get_by_name(priv, skcb->addr.src_name); + if (!ecu) + return -ENODEV; + + if (ecu->addr != skcb->addr.sa) + /* hold further traffic for ecu, remove from parent */ + j1939_ecu_unmap(ecu); + j1939_ecu_put(ecu); + } else if (skcb->addr.src_name) { + /* assign source address */ + addr = j1939_name_to_addr(priv, skcb->addr.src_name); + if (!j1939_address_is_unicast(addr) && + !j1939_ac_msg_is_request(skb)) { + netdev_notice(priv->ndev, "tx drop: invalid sa for name 0x%016llx\n", + skcb->addr.src_name); + return -EADDRNOTAVAIL; + } + skcb->addr.sa = addr; + } + + /* assign destination address */ + if (skcb->addr.dst_name) { + addr = j1939_name_to_addr(priv, skcb->addr.dst_name); + if (!j1939_address_is_unicast(addr)) { + netdev_notice(priv->ndev, "tx drop: invalid da for name 0x%016llx\n", + skcb->addr.dst_name); + return -EADDRNOTAVAIL; + } + skcb->addr.da = addr; + } + return 0; +} + +static void j1939_ac_process(struct j1939_priv *priv, struct sk_buff *skb) +{ + struct j1939_sk_buff_cb *skcb = j1939_skb_to_cb(skb); + struct j1939_ecu *ecu, *prev; + name_t name; + + if (skb->len != 8) { + netdev_notice(priv->ndev, "rx address claim with wrong dlc %i\n", + skb->len); + return; + } + + name = j1939_skb_to_name(skb); + skcb->addr.src_name = name; + if (!name) { + netdev_notice(priv->ndev, "rx address claim without name\n"); + return; + } + + if (!j1939_address_is_valid(skcb->addr.sa)) { + netdev_notice(priv->ndev, "rx address claim with broadcast sa\n"); + return; + } + + write_lock_bh(&priv->lock); + + /* Few words on the ECU ref counting: + * + * First we get an ECU handle, either with + * j1939_ecu_get_by_name_locked() (increments the ref counter) + * or j1939_ecu_create_locked() (initializes an ECU object + * with a ref counter of 1). + * + * j1939_ecu_unmap_locked() will decrement the ref counter, + * but only if the ECU was mapped before. So "ecu" still + * belongs to us. + * + * j1939_ecu_timer_start() will increment the ref counter + * before it starts the timer, so we can put the ecu when + * leaving this function. + */ + ecu = j1939_ecu_get_by_name_locked(priv, name); + if (!ecu && j1939_address_is_unicast(skcb->addr.sa)) + ecu = j1939_ecu_create_locked(priv, name); + + if (IS_ERR_OR_NULL(ecu)) + goto out_unlock_bh; + + /* cancel pending (previous) address claim */ + j1939_ecu_timer_cancel(ecu); + + if (j1939_address_is_idle(skcb->addr.sa)) { + j1939_ecu_unmap_locked(ecu); + goto out_ecu_put; + } + + /* save new addr */ + if (ecu->addr != skcb->addr.sa) + j1939_ecu_unmap_locked(ecu); + ecu->addr = skcb->addr.sa; + + prev = j1939_ecu_get_by_addr_locked(priv, skcb->addr.sa); + if (prev) { + if (ecu->name > prev->name) { + j1939_ecu_unmap_locked(ecu); + j1939_ecu_put(prev); + goto out_ecu_put; + } else { + /* kick prev if less or equal */ + j1939_ecu_unmap_locked(prev); + j1939_ecu_put(prev); + } + } + + j1939_ecu_timer_start(ecu); + out_ecu_put: + j1939_ecu_put(ecu); + out_unlock_bh: + write_unlock_bh(&priv->lock); +} + +void j1939_ac_recv(struct j1939_priv *priv, struct sk_buff *skb) +{ + struct j1939_sk_buff_cb *skcb = j1939_skb_to_cb(skb); + struct j1939_ecu *ecu; + + /* network mgmt */ + if (skcb->addr.pgn == J1939_PGN_ADDRESS_CLAIMED) { + j1939_ac_process(priv, skb); + } else if (j1939_address_is_unicast(skcb->addr.sa)) { + /* assign source name */ + ecu = j1939_ecu_get_by_addr(priv, skcb->addr.sa); + if (ecu) { + skcb->addr.src_name = ecu->name; + j1939_ecu_put(ecu); + } + } + + /* assign destination name */ + ecu = j1939_ecu_get_by_addr(priv, skcb->addr.da); + if (ecu) { + skcb->addr.dst_name = ecu->name; + j1939_ecu_put(ecu); + } +} diff --git a/net/can/j1939/bus.c b/net/can/j1939/bus.c new file mode 100644 index 000000000000..486687901602 --- /dev/null +++ b/net/can/j1939/bus.c @@ -0,0 +1,333 @@ +// SPDX-License-Identifier: GPL-2.0 +// Copyright (c) 2010-2011 EIA Electronics, +// Kurt Van Dijck +// Copyright (c) 2017-2019 Pengutronix, +// Marc Kleine-Budde +// Copyright (c) 2017-2019 Pengutronix, +// Oleksij Rempel + +/* bus for j1939 remote devices + * Since rtnetlink, no real bus is used. + */ + +#include + +#include "j1939-priv.h" + +static void __j1939_ecu_release(struct kref *kref) +{ + struct j1939_ecu *ecu = container_of(kref, struct j1939_ecu, kref); + struct j1939_priv *priv = ecu->priv; + + list_del(&ecu->list); + kfree(ecu); + j1939_priv_put(priv); +} + +void j1939_ecu_put(struct j1939_ecu *ecu) +{ + kref_put(&ecu->kref, __j1939_ecu_release); +} + +static void j1939_ecu_get(struct j1939_ecu *ecu) +{ + kref_get(&ecu->kref); +} + +static bool j1939_ecu_is_mapped_locked(struct j1939_ecu *ecu) +{ + struct j1939_priv *priv = ecu->priv; + + lockdep_assert_held(&priv->lock); + + return j1939_ecu_find_by_addr_locked(priv, ecu->addr) == ecu; +} + +/* ECU device interface */ +/* map ECU to a bus address space */ +static void j1939_ecu_map_locked(struct j1939_ecu *ecu) +{ + struct j1939_priv *priv = ecu->priv; + struct j1939_addr_ent *ent; + + lockdep_assert_held(&priv->lock); + + if (!j1939_address_is_unicast(ecu->addr)) + return; + + ent = &priv->ents[ecu->addr]; + + if (ent->ecu) { + netdev_warn(priv->ndev, "Trying to map already mapped ECU, addr: 0x%02x, name: 0x%016llx. Skip it.\n", + ecu->addr, ecu->name); + return; + } + + j1939_ecu_get(ecu); + ent->ecu = ecu; + ent->nusers += ecu->nusers; +} + +/* unmap ECU from a bus address space */ +void j1939_ecu_unmap_locked(struct j1939_ecu *ecu) +{ + struct j1939_priv *priv = ecu->priv; + struct j1939_addr_ent *ent; + + lockdep_assert_held(&priv->lock); + + if (!j1939_address_is_unicast(ecu->addr)) + return; + + if (!j1939_ecu_is_mapped_locked(ecu)) + return; + + ent = &priv->ents[ecu->addr]; + ent->ecu = NULL; + ent->nusers -= ecu->nusers; + j1939_ecu_put(ecu); +} + +void j1939_ecu_unmap(struct j1939_ecu *ecu) +{ + write_lock_bh(&ecu->priv->lock); + j1939_ecu_unmap_locked(ecu); + write_unlock_bh(&ecu->priv->lock); +} + +void j1939_ecu_unmap_all(struct j1939_priv *priv) +{ + int i; + + write_lock_bh(&priv->lock); + for (i = 0; i < ARRAY_SIZE(priv->ents); i++) + if (priv->ents[i].ecu) + j1939_ecu_unmap_locked(priv->ents[i].ecu); + write_unlock_bh(&priv->lock); +} + +void j1939_ecu_timer_start(struct j1939_ecu *ecu) +{ + /* The ECU is held here and released in the + * j1939_ecu_timer_handler() or j1939_ecu_timer_cancel(). + */ + j1939_ecu_get(ecu); + + /* Schedule timer in 250 msec to commit address change. */ + hrtimer_start(&ecu->ac_timer, ms_to_ktime(250), + HRTIMER_MODE_REL_SOFT); +} + +void j1939_ecu_timer_cancel(struct j1939_ecu *ecu) +{ + if (hrtimer_cancel(&ecu->ac_timer)) + j1939_ecu_put(ecu); +} + +static enum hrtimer_restart j1939_ecu_timer_handler(struct hrtimer *hrtimer) +{ + struct j1939_ecu *ecu = + container_of(hrtimer, struct j1939_ecu, ac_timer); + struct j1939_priv *priv = ecu->priv; + + write_lock_bh(&priv->lock); + /* TODO: can we test if ecu->addr is unicast before starting + * the timer? + */ + j1939_ecu_map_locked(ecu); + + /* The corresponding j1939_ecu_get() is in + * j1939_ecu_timer_start(). + */ + j1939_ecu_put(ecu); + write_unlock_bh(&priv->lock); + + return HRTIMER_NORESTART; +} + +struct j1939_ecu *j1939_ecu_create_locked(struct j1939_priv *priv, name_t name) +{ + struct j1939_ecu *ecu; + + lockdep_assert_held(&priv->lock); + + ecu = kzalloc(sizeof(*ecu), gfp_any()); + if (!ecu) + return ERR_PTR(-ENOMEM); + kref_init(&ecu->kref); + ecu->addr = J1939_IDLE_ADDR; + ecu->name = name; + + hrtimer_init(&ecu->ac_timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL_SOFT); + ecu->ac_timer.function = j1939_ecu_timer_handler; + INIT_LIST_HEAD(&ecu->list); + + j1939_priv_get(priv); + ecu->priv = priv; + list_add_tail(&ecu->list, &priv->ecus); + + return ecu; +} + +struct j1939_ecu *j1939_ecu_find_by_addr_locked(struct j1939_priv *priv, + u8 addr) +{ + lockdep_assert_held(&priv->lock); + + return priv->ents[addr].ecu; +} + +struct j1939_ecu *j1939_ecu_get_by_addr_locked(struct j1939_priv *priv, u8 addr) +{ + struct j1939_ecu *ecu; + + lockdep_assert_held(&priv->lock); + + if (!j1939_address_is_unicast(addr)) + return NULL; + + ecu = j1939_ecu_find_by_addr_locked(priv, addr); + if (ecu) + j1939_ecu_get(ecu); + + return ecu; +} + +struct j1939_ecu *j1939_ecu_get_by_addr(struct j1939_priv *priv, u8 addr) +{ + struct j1939_ecu *ecu; + + read_lock_bh(&priv->lock); + ecu = j1939_ecu_get_by_addr_locked(priv, addr); + read_unlock_bh(&priv->lock); + + return ecu; +} + +/* get pointer to ecu without increasing ref counter */ +static struct j1939_ecu *j1939_ecu_find_by_name_locked(struct j1939_priv *priv, + name_t name) +{ + struct j1939_ecu *ecu; + + lockdep_assert_held(&priv->lock); + + list_for_each_entry(ecu, &priv->ecus, list) { + if (ecu->name == name) + return ecu; + } + + return NULL; +} + +struct j1939_ecu *j1939_ecu_get_by_name_locked(struct j1939_priv *priv, + name_t name) +{ + struct j1939_ecu *ecu; + + lockdep_assert_held(&priv->lock); + + if (!name) + return NULL; + + ecu = j1939_ecu_find_by_name_locked(priv, name); + if (ecu) + j1939_ecu_get(ecu); + + return ecu; +} + +struct j1939_ecu *j1939_ecu_get_by_name(struct j1939_priv *priv, name_t name) +{ + struct j1939_ecu *ecu; + + read_lock_bh(&priv->lock); + ecu = j1939_ecu_get_by_name_locked(priv, name); + read_unlock_bh(&priv->lock); + + return ecu; +} + +u8 j1939_name_to_addr(struct j1939_priv *priv, name_t name) +{ + struct j1939_ecu *ecu; + int addr = J1939_IDLE_ADDR; + + if (!name) + return J1939_NO_ADDR; + + read_lock_bh(&priv->lock); + ecu = j1939_ecu_find_by_name_locked(priv, name); + if (ecu && j1939_ecu_is_mapped_locked(ecu)) + /* ecu's SA is registered */ + addr = ecu->addr; + + read_unlock_bh(&priv->lock); + + return addr; +} + +/* TX addr/name accounting + * Transport protocol needs to know if a SA is local or not + * These functions originate from userspace manipulating sockets, + * so locking is straigforward + */ + +int j1939_local_ecu_get(struct j1939_priv *priv, name_t name, u8 sa) +{ + struct j1939_ecu *ecu; + int err = 0; + + write_lock_bh(&priv->lock); + + if (j1939_address_is_unicast(sa)) + priv->ents[sa].nusers++; + + if (!name) + goto done; + + ecu = j1939_ecu_get_by_name_locked(priv, name); + if (!ecu) + ecu = j1939_ecu_create_locked(priv, name); + err = PTR_ERR_OR_ZERO(ecu); + if (err) + goto done; + + ecu->nusers++; + /* TODO: do we care if ecu->addr != sa? */ + if (j1939_ecu_is_mapped_locked(ecu)) + /* ecu's sa is active already */ + priv->ents[ecu->addr].nusers++; + + done: + write_unlock_bh(&priv->lock); + + return err; +} + +void j1939_local_ecu_put(struct j1939_priv *priv, name_t name, u8 sa) +{ + struct j1939_ecu *ecu; + + write_lock_bh(&priv->lock); + + if (j1939_address_is_unicast(sa)) + priv->ents[sa].nusers--; + + if (!name) + goto done; + + ecu = j1939_ecu_find_by_name_locked(priv, name); + if (WARN_ON_ONCE(!ecu)) + goto done; + + ecu->nusers--; + /* TODO: do we care if ecu->addr != sa? */ + if (j1939_ecu_is_mapped_locked(ecu)) + /* ecu's sa is active already */ + priv->ents[ecu->addr].nusers--; + j1939_ecu_put(ecu); + + done: + write_unlock_bh(&priv->lock); +} diff --git a/net/can/j1939/j1939-priv.h b/net/can/j1939/j1939-priv.h new file mode 100644 index 000000000000..12369b604ce9 --- /dev/null +++ b/net/can/j1939/j1939-priv.h @@ -0,0 +1,338 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +// Copyright (c) 2010-2011 EIA Electronics, +// Kurt Van Dijck +// Copyright (c) 2017-2019 Pengutronix, +// Marc Kleine-Budde +// Copyright (c) 2017-2019 Pengutronix, +// Oleksij Rempel + +#ifndef _J1939_PRIV_H_ +#define _J1939_PRIV_H_ + +#include +#include + +/* Timeout to receive the abort signal over loop back. In case CAN + * bus is open, the timeout should be triggered. + */ +#define J1939_XTP_ABORT_TIMEOUT_MS 500 +#define J1939_SIMPLE_ECHO_TIMEOUT_MS (10 * 1000) + +struct j1939_session; +enum j1939_sk_errqueue_type { + J1939_ERRQUEUE_ACK, + J1939_ERRQUEUE_SCHED, + J1939_ERRQUEUE_ABORT, +}; + +/* j1939 devices */ +struct j1939_ecu { + struct list_head list; + name_t name; + u8 addr; + + /* indicates that this ecu successfully claimed @sa as its address */ + struct hrtimer ac_timer; + struct kref kref; + struct j1939_priv *priv; + + /* count users, to help transport protocol decide for interaction */ + int nusers; +}; + +struct j1939_priv { + struct list_head ecus; + /* local list entry in priv + * These allow irq (& softirq) context lookups on j1939 devices + * This approach (separate lists) is done as the other 2 alternatives + * are not easier or even wrong + * 1) using the pure kobject methods involves mutexes, which are not + * allowed in irq context. + * 2) duplicating data structures would require a lot of synchronization + * code + * usage: + */ + + /* segments need a lock to protect the above list */ + rwlock_t lock; + + struct net_device *ndev; + + /* list of 256 ecu ptrs, that cache the claimed addresses. + * also protected by the above lock + */ + struct j1939_addr_ent { + struct j1939_ecu *ecu; + /* count users, to help transport protocol */ + int nusers; + } ents[256]; + + struct kref kref; + + /* List of active sessions to prevent start of conflicting + * one. + * + * Do not start two sessions of same type, addresses and + * direction. + */ + struct list_head active_session_list; + + /* protects active_session_list */ + spinlock_t active_session_list_lock; + + unsigned int tp_max_packet_size; + + /* lock for j1939_socks list */ + spinlock_t j1939_socks_lock; + struct list_head j1939_socks; + + struct kref rx_kref; +}; + +void j1939_ecu_put(struct j1939_ecu *ecu); + +/* keep the cache of what is local */ +int j1939_local_ecu_get(struct j1939_priv *priv, name_t name, u8 sa); +void j1939_local_ecu_put(struct j1939_priv *priv, name_t name, u8 sa); + +static inline bool j1939_address_is_unicast(u8 addr) +{ + return addr <= J1939_MAX_UNICAST_ADDR; +} + +static inline bool j1939_address_is_idle(u8 addr) +{ + return addr == J1939_IDLE_ADDR; +} + +static inline bool j1939_address_is_valid(u8 addr) +{ + return addr != J1939_NO_ADDR; +} + +static inline bool j1939_pgn_is_pdu1(pgn_t pgn) +{ + /* ignore dp & res bits for this */ + return (pgn & 0xff00) < 0xf000; +} + +/* utility to correctly unmap an ECU */ +void j1939_ecu_unmap_locked(struct j1939_ecu *ecu); +void j1939_ecu_unmap(struct j1939_ecu *ecu); + +u8 j1939_name_to_addr(struct j1939_priv *priv, name_t name); +struct j1939_ecu *j1939_ecu_find_by_addr_locked(struct j1939_priv *priv, + u8 addr); +struct j1939_ecu *j1939_ecu_get_by_addr(struct j1939_priv *priv, u8 addr); +struct j1939_ecu *j1939_ecu_get_by_addr_locked(struct j1939_priv *priv, + u8 addr); +struct j1939_ecu *j1939_ecu_get_by_name(struct j1939_priv *priv, name_t name); +struct j1939_ecu *j1939_ecu_get_by_name_locked(struct j1939_priv *priv, + name_t name); + +enum j1939_transfer_type { + J1939_TP, + J1939_ETP, + J1939_SIMPLE, +}; + +struct j1939_addr { + name_t src_name; + name_t dst_name; + pgn_t pgn; + + u8 sa; + u8 da; + + u8 type; +}; + +/* control buffer of the sk_buff */ +struct j1939_sk_buff_cb { + /* Offset in bytes within one ETP session */ + u32 offset; + + /* for tx, MSG_SYN will be used to sync on sockets */ + u32 msg_flags; + u32 tskey; + + struct j1939_addr addr; + + /* Flags for quick lookups during skb processing. + * These are set in the receive path only. + */ +#define J1939_ECU_LOCAL_SRC BIT(0) +#define J1939_ECU_LOCAL_DST BIT(1) + u8 flags; + + priority_t priority; +}; + +static inline +struct j1939_sk_buff_cb *j1939_skb_to_cb(const struct sk_buff *skb) +{ + BUILD_BUG_ON(sizeof(struct j1939_sk_buff_cb) > sizeof(skb->cb)); + + return (struct j1939_sk_buff_cb *)skb->cb; +} + +int j1939_send_one(struct j1939_priv *priv, struct sk_buff *skb); +void j1939_sk_recv(struct j1939_priv *priv, struct sk_buff *skb); +bool j1939_sk_recv_match(struct j1939_priv *priv, + struct j1939_sk_buff_cb *skcb); +void j1939_sk_send_loop_abort(struct sock *sk, int err); +void j1939_sk_errqueue(struct j1939_session *session, + enum j1939_sk_errqueue_type type); +void j1939_sk_queue_activate_next(struct j1939_session *session); + +/* stack entries */ +struct j1939_session *j1939_tp_send(struct j1939_priv *priv, + struct sk_buff *skb, size_t size); +int j1939_tp_recv(struct j1939_priv *priv, struct sk_buff *skb); +int j1939_ac_fixup(struct j1939_priv *priv, struct sk_buff *skb); +void j1939_ac_recv(struct j1939_priv *priv, struct sk_buff *skb); +void j1939_simple_recv(struct j1939_priv *priv, struct sk_buff *skb); + +/* network management */ +struct j1939_ecu *j1939_ecu_create_locked(struct j1939_priv *priv, name_t name); + +void j1939_ecu_timer_start(struct j1939_ecu *ecu); +void j1939_ecu_timer_cancel(struct j1939_ecu *ecu); +void j1939_ecu_unmap_all(struct j1939_priv *priv); + +struct j1939_priv *j1939_netdev_start(struct net_device *ndev); +void j1939_netdev_stop(struct j1939_priv *priv); + +void j1939_priv_put(struct j1939_priv *priv); +void j1939_priv_get(struct j1939_priv *priv); + +/* notify/alert all j1939 sockets bound to ifindex */ +void j1939_sk_netdev_event_netdown(struct j1939_priv *priv); +int j1939_cancel_active_session(struct j1939_priv *priv, struct sock *sk); +void j1939_tp_init(struct j1939_priv *priv); + +/* decrement pending skb for a j1939 socket */ +void j1939_sock_pending_del(struct sock *sk); + +enum j1939_session_state { + J1939_SESSION_NEW, + J1939_SESSION_ACTIVE, + /* waiting for abort signal on the bus */ + J1939_SESSION_WAITING_ABORT, + J1939_SESSION_ACTIVE_MAX, + J1939_SESSION_DONE, +}; + +struct j1939_session { + struct j1939_priv *priv; + struct list_head active_session_list_entry; + struct list_head sk_session_queue_entry; + struct kref kref; + struct sock *sk; + + /* ifindex, src, dst, pgn define the session block + * the are _never_ modified after insertion in the list + * this decreases locking problems a _lot_ + */ + struct j1939_sk_buff_cb skcb; + struct sk_buff_head skb_queue; + + /* all tx related stuff (last_txcmd, pkt.tx) + * is protected (modified only) with the txtimer hrtimer + * 'total' & 'block' are never changed, + * last_cmd, last & block are protected by ->lock + * this means that the tx may run after cts is received that should + * have stopped tx, but this time discrepancy is never avoided anyhow + */ + u8 last_cmd, last_txcmd; + bool transmission; + bool extd; + /* Total message size, number of bytes */ + unsigned int total_message_size; + /* Total number of bytes queue from socket to the session */ + unsigned int total_queued_size; + unsigned int tx_retry; + + int err; + u32 tskey; + enum j1939_session_state state; + + /* Packets counters for a (extended) transfer session. The packet is + * maximal of 7 bytes. + */ + struct { + /* total - total number of packets for this session */ + unsigned int total; + /* last - last packet of a transfer block after which + * responder should send ETP.CM_CTS and originator + * ETP.CM_DPO + */ + unsigned int last; + /* tx - number of packets send by originator node. + * this counter can be set back if responder node + * didn't received all packets send by originator. + */ + unsigned int tx; + unsigned int tx_acked; + /* rx - number of packets received */ + unsigned int rx; + /* block - amount of packets expected in one block */ + unsigned int block; + /* dpo - ETP.CM_DPO, Data Packet Offset */ + unsigned int dpo; + } pkt; + struct hrtimer txtimer, rxtimer; +}; + +struct j1939_sock { + struct sock sk; /* must be first to skip with memset */ + struct j1939_priv *priv; + struct list_head list; + +#define J1939_SOCK_BOUND BIT(0) +#define J1939_SOCK_CONNECTED BIT(1) +#define J1939_SOCK_PROMISC BIT(2) +#define J1939_SOCK_ERRQUEUE BIT(3) + int state; + + int ifindex; + struct j1939_addr addr; + struct j1939_filter *filters; + int nfilters; + pgn_t pgn_rx_filter; + + /* j1939 may emit equal PGN (!= equal CAN-id's) out of order + * when transport protocol comes in. + * To allow emitting in order, keep a 'pending' nr. of packets + */ + atomic_t skb_pending; + wait_queue_head_t waitq; + + /* lock for the sk_session_queue list */ + spinlock_t sk_session_queue_lock; + struct list_head sk_session_queue; +}; + +static inline struct j1939_sock *j1939_sk(const struct sock *sk) +{ + return container_of(sk, struct j1939_sock, sk); +} + +void j1939_session_get(struct j1939_session *session); +void j1939_session_put(struct j1939_session *session); +void j1939_session_skb_queue(struct j1939_session *session, + struct sk_buff *skb); +int j1939_session_activate(struct j1939_session *session); +void j1939_tp_schedule_txtimer(struct j1939_session *session, int msec); +void j1939_session_timers_cancel(struct j1939_session *session); + +#define J1939_MAX_TP_PACKET_SIZE (7 * 0xff) +#define J1939_MAX_ETP_PACKET_SIZE (7 * 0x00ffffff) + +#define J1939_REGULAR 0 +#define J1939_EXTENDED 1 + +/* CAN protocol */ +extern const struct can_proto j1939_can_proto; + +#endif /* _J1939_PRIV_H_ */ diff --git a/net/can/j1939/main.c b/net/can/j1939/main.c new file mode 100644 index 000000000000..def2f813ffce --- /dev/null +++ b/net/can/j1939/main.c @@ -0,0 +1,403 @@ +// SPDX-License-Identifier: GPL-2.0 +// Copyright (c) 2010-2011 EIA Electronics, +// Pieter Beyens +// Copyright (c) 2010-2011 EIA Electronics, +// Kurt Van Dijck +// Copyright (c) 2018 Protonic, +// Robin van der Gracht +// Copyright (c) 2017-2019 Pengutronix, +// Marc Kleine-Budde +// Copyright (c) 2017-2019 Pengutronix, +// Oleksij Rempel + +/* Core of can-j1939 that links j1939 to CAN. */ + +#include +#include +#include +#include +#include + +#include "j1939-priv.h" + +MODULE_DESCRIPTION("PF_CAN SAE J1939"); +MODULE_LICENSE("GPL v2"); +MODULE_AUTHOR("EIA Electronics (Kurt Van Dijck & Pieter Beyens)"); +MODULE_ALIAS("can-proto-" __stringify(CAN_J1939)); + +/* LOWLEVEL CAN interface */ + +/* CAN_HDR: #bytes before can_frame data part */ +#define J1939_CAN_HDR (offsetof(struct can_frame, data)) + +/* CAN_FTR: #bytes beyond data part */ +#define J1939_CAN_FTR (sizeof(struct can_frame) - J1939_CAN_HDR - \ + sizeof(((struct can_frame *)0)->data)) + +/* lowest layer */ +static void j1939_can_recv(struct sk_buff *iskb, void *data) +{ + struct j1939_priv *priv = data; + struct sk_buff *skb; + struct j1939_sk_buff_cb *skcb, *iskcb; + struct can_frame *cf; + + /* create a copy of the skb + * j1939 only delivers the real data bytes, + * the header goes into sockaddr. + * j1939 may not touch the incoming skb in such way + */ + skb = skb_clone(iskb, GFP_ATOMIC); + if (!skb) + return; + + can_skb_set_owner(skb, iskb->sk); + + /* get a pointer to the header of the skb + * the skb payload (pointer) is moved, so that the next skb_data + * returns the actual payload + */ + cf = (void *)skb->data; + skb_pull(skb, J1939_CAN_HDR); + + /* fix length, set to dlc, with 8 maximum */ + skb_trim(skb, min_t(uint8_t, cf->can_dlc, 8)); + + /* set addr */ + skcb = j1939_skb_to_cb(skb); + memset(skcb, 0, sizeof(*skcb)); + + iskcb = j1939_skb_to_cb(iskb); + skcb->tskey = iskcb->tskey; + skcb->priority = (cf->can_id >> 26) & 0x7; + skcb->addr.sa = cf->can_id; + skcb->addr.pgn = (cf->can_id >> 8) & J1939_PGN_MAX; + /* set default message type */ + skcb->addr.type = J1939_TP; + if (j1939_pgn_is_pdu1(skcb->addr.pgn)) { + /* Type 1: with destination address */ + skcb->addr.da = skcb->addr.pgn; + /* normalize pgn: strip dst address */ + skcb->addr.pgn &= 0x3ff00; + } else { + /* set broadcast address */ + skcb->addr.da = J1939_NO_ADDR; + } + + /* update localflags */ + read_lock_bh(&priv->lock); + if (j1939_address_is_unicast(skcb->addr.sa) && + priv->ents[skcb->addr.sa].nusers) + skcb->flags |= J1939_ECU_LOCAL_SRC; + if (j1939_address_is_unicast(skcb->addr.da) && + priv->ents[skcb->addr.da].nusers) + skcb->flags |= J1939_ECU_LOCAL_DST; + read_unlock_bh(&priv->lock); + + /* deliver into the j1939 stack ... */ + j1939_ac_recv(priv, skb); + + if (j1939_tp_recv(priv, skb)) + /* this means the transport layer processed the message */ + goto done; + + j1939_simple_recv(priv, skb); + j1939_sk_recv(priv, skb); + done: + kfree_skb(skb); +} + +/* NETDEV MANAGEMENT */ + +/* values for can_rx_(un)register */ +#define J1939_CAN_ID CAN_EFF_FLAG +#define J1939_CAN_MASK (CAN_EFF_FLAG | CAN_RTR_FLAG) + +static DEFINE_SPINLOCK(j1939_netdev_lock); + +static struct j1939_priv *j1939_priv_create(struct net_device *ndev) +{ + struct j1939_priv *priv; + + priv = kzalloc(sizeof(*priv), GFP_KERNEL); + if (!priv) + return NULL; + + rwlock_init(&priv->lock); + INIT_LIST_HEAD(&priv->ecus); + priv->ndev = ndev; + kref_init(&priv->kref); + kref_init(&priv->rx_kref); + dev_hold(ndev); + + netdev_dbg(priv->ndev, "%s : 0x%p\n", __func__, priv); + + return priv; +} + +static inline void j1939_priv_set(struct net_device *ndev, + struct j1939_priv *priv) +{ + struct can_ml_priv *can_ml_priv = ndev->ml_priv; + + can_ml_priv->j1939_priv = priv; +} + +static void __j1939_priv_release(struct kref *kref) +{ + struct j1939_priv *priv = container_of(kref, struct j1939_priv, kref); + struct net_device *ndev = priv->ndev; + + netdev_dbg(priv->ndev, "%s: 0x%p\n", __func__, priv); + + dev_put(ndev); + kfree(priv); +} + +void j1939_priv_put(struct j1939_priv *priv) +{ + kref_put(&priv->kref, __j1939_priv_release); +} + +void j1939_priv_get(struct j1939_priv *priv) +{ + kref_get(&priv->kref); +} + +static int j1939_can_rx_register(struct j1939_priv *priv) +{ + struct net_device *ndev = priv->ndev; + int ret; + + j1939_priv_get(priv); + ret = can_rx_register(dev_net(ndev), ndev, J1939_CAN_ID, J1939_CAN_MASK, + j1939_can_recv, priv, "j1939", NULL); + if (ret < 0) { + j1939_priv_put(priv); + return ret; + } + + return 0; +} + +static void j1939_can_rx_unregister(struct j1939_priv *priv) +{ + struct net_device *ndev = priv->ndev; + + can_rx_unregister(dev_net(ndev), ndev, J1939_CAN_ID, J1939_CAN_MASK, + j1939_can_recv, priv); + + j1939_priv_put(priv); +} + +static void __j1939_rx_release(struct kref *kref) + __releases(&j1939_netdev_lock) +{ + struct j1939_priv *priv = container_of(kref, struct j1939_priv, + rx_kref); + + j1939_can_rx_unregister(priv); + j1939_ecu_unmap_all(priv); + j1939_priv_set(priv->ndev, NULL); + spin_unlock(&j1939_netdev_lock); +} + +/* get pointer to priv without increasing ref counter */ +static inline struct j1939_priv *j1939_ndev_to_priv(struct net_device *ndev) +{ + struct can_ml_priv *can_ml_priv = ndev->ml_priv; + + return can_ml_priv->j1939_priv; +} + +static struct j1939_priv *j1939_priv_get_by_ndev_locked(struct net_device *ndev) +{ + struct j1939_priv *priv; + + lockdep_assert_held(&j1939_netdev_lock); + + if (ndev->type != ARPHRD_CAN) + return NULL; + + priv = j1939_ndev_to_priv(ndev); + if (priv) + j1939_priv_get(priv); + + return priv; +} + +static struct j1939_priv *j1939_priv_get_by_ndev(struct net_device *ndev) +{ + struct j1939_priv *priv; + + spin_lock(&j1939_netdev_lock); + priv = j1939_priv_get_by_ndev_locked(ndev); + spin_unlock(&j1939_netdev_lock); + + return priv; +} + +struct j1939_priv *j1939_netdev_start(struct net_device *ndev) +{ + struct j1939_priv *priv, *priv_new; + int ret; + + priv = j1939_priv_get_by_ndev(ndev); + if (priv) { + kref_get(&priv->rx_kref); + return priv; + } + + priv = j1939_priv_create(ndev); + if (!priv) + return ERR_PTR(-ENOMEM); + + j1939_tp_init(priv); + spin_lock_init(&priv->j1939_socks_lock); + INIT_LIST_HEAD(&priv->j1939_socks); + + spin_lock(&j1939_netdev_lock); + priv_new = j1939_priv_get_by_ndev_locked(ndev); + if (priv_new) { + /* Someone was faster than us, use their priv and roll + * back our's. + */ + spin_unlock(&j1939_netdev_lock); + dev_put(ndev); + kfree(priv); + kref_get(&priv_new->rx_kref); + return priv_new; + } + j1939_priv_set(ndev, priv); + spin_unlock(&j1939_netdev_lock); + + ret = j1939_can_rx_register(priv); + if (ret < 0) + goto out_priv_put; + + return priv; + + out_priv_put: + j1939_priv_set(ndev, NULL); + dev_put(ndev); + kfree(priv); + + return ERR_PTR(ret); +} + +void j1939_netdev_stop(struct j1939_priv *priv) +{ + kref_put_lock(&priv->rx_kref, __j1939_rx_release, &j1939_netdev_lock); + j1939_priv_put(priv); +} + +int j1939_send_one(struct j1939_priv *priv, struct sk_buff *skb) +{ + int ret, dlc; + canid_t canid; + struct j1939_sk_buff_cb *skcb = j1939_skb_to_cb(skb); + struct can_frame *cf; + + /* apply sanity checks */ + if (j1939_pgn_is_pdu1(skcb->addr.pgn)) + skcb->addr.pgn &= J1939_PGN_PDU1_MAX; + else + skcb->addr.pgn &= J1939_PGN_MAX; + + if (skcb->priority > 7) + skcb->priority = 6; + + ret = j1939_ac_fixup(priv, skb); + if (unlikely(ret)) + goto failed; + dlc = skb->len; + + /* re-claim the CAN_HDR from the SKB */ + cf = skb_push(skb, J1939_CAN_HDR); + + /* make it a full can frame again */ + skb_put(skb, J1939_CAN_FTR + (8 - dlc)); + + canid = CAN_EFF_FLAG | + (skcb->priority << 26) | + (skcb->addr.pgn << 8) | + skcb->addr.sa; + if (j1939_pgn_is_pdu1(skcb->addr.pgn)) + canid |= skcb->addr.da << 8; + + cf->can_id = canid; + cf->can_dlc = dlc; + + return can_send(skb, 1); + + failed: + kfree_skb(skb); + return ret; +} + +static int j1939_netdev_notify(struct notifier_block *nb, + unsigned long msg, void *data) +{ + struct net_device *ndev = netdev_notifier_info_to_dev(data); + struct j1939_priv *priv; + + priv = j1939_priv_get_by_ndev(ndev); + if (!priv) + goto notify_done; + + if (ndev->type != ARPHRD_CAN) + goto notify_put; + + switch (msg) { + case NETDEV_DOWN: + j1939_cancel_active_session(priv, NULL); + j1939_sk_netdev_event_netdown(priv); + j1939_ecu_unmap_all(priv); + break; + } + +notify_put: + j1939_priv_put(priv); + +notify_done: + return NOTIFY_DONE; +} + +static struct notifier_block j1939_netdev_notifier = { + .notifier_call = j1939_netdev_notify, +}; + +/* MODULE interface */ +static __init int j1939_module_init(void) +{ + int ret; + + pr_info("can: SAE J1939\n"); + + ret = register_netdevice_notifier(&j1939_netdev_notifier); + if (ret) + goto fail_notifier; + + ret = can_proto_register(&j1939_can_proto); + if (ret < 0) { + pr_err("can: registration of j1939 protocol failed\n"); + goto fail_sk; + } + + return 0; + + fail_sk: + unregister_netdevice_notifier(&j1939_netdev_notifier); + fail_notifier: + return ret; +} + +static __exit void j1939_module_exit(void) +{ + can_proto_unregister(&j1939_can_proto); + + unregister_netdevice_notifier(&j1939_netdev_notifier); +} + +module_init(j1939_module_init); +module_exit(j1939_module_exit); diff --git a/net/can/j1939/socket.c b/net/can/j1939/socket.c new file mode 100644 index 000000000000..37c1040bcb9c --- /dev/null +++ b/net/can/j1939/socket.c @@ -0,0 +1,1160 @@ +// SPDX-License-Identifier: GPL-2.0 +// Copyright (c) 2010-2011 EIA Electronics, +// Pieter Beyens +// Copyright (c) 2010-2011 EIA Electronics, +// Kurt Van Dijck +// Copyright (c) 2018 Protonic, +// Robin van der Gracht +// Copyright (c) 2017-2019 Pengutronix, +// Marc Kleine-Budde +// Copyright (c) 2017-2019 Pengutronix, +// Oleksij Rempel + +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt + +#include +#include +#include +#include + +#include "j1939-priv.h" + +#define J1939_MIN_NAMELEN CAN_REQUIRED_SIZE(struct sockaddr_can, can_addr.j1939) + +/* conversion function between struct sock::sk_priority from linux and + * j1939 priority field + */ +static inline priority_t j1939_prio(u32 sk_priority) +{ + sk_priority = min(sk_priority, 7U); + + return 7 - sk_priority; +} + +static inline u32 j1939_to_sk_priority(priority_t prio) +{ + return 7 - prio; +} + +/* function to see if pgn is to be evaluated */ +static inline bool j1939_pgn_is_valid(pgn_t pgn) +{ + return pgn <= J1939_PGN_MAX; +} + +/* test function to avoid non-zero DA placeholder for pdu1 pgn's */ +static inline bool j1939_pgn_is_clean_pdu(pgn_t pgn) +{ + if (j1939_pgn_is_pdu1(pgn)) + return !(pgn & 0xff); + else + return true; +} + +static inline void j1939_sock_pending_add(struct sock *sk) +{ + struct j1939_sock *jsk = j1939_sk(sk); + + atomic_inc(&jsk->skb_pending); +} + +static int j1939_sock_pending_get(struct sock *sk) +{ + struct j1939_sock *jsk = j1939_sk(sk); + + return atomic_read(&jsk->skb_pending); +} + +void j1939_sock_pending_del(struct sock *sk) +{ + struct j1939_sock *jsk = j1939_sk(sk); + + /* atomic_dec_return returns the new value */ + if (!atomic_dec_return(&jsk->skb_pending)) + wake_up(&jsk->waitq); /* no pending SKB's */ +} + +static void j1939_jsk_add(struct j1939_priv *priv, struct j1939_sock *jsk) +{ + jsk->state |= J1939_SOCK_BOUND; + j1939_priv_get(priv); + jsk->priv = priv; + + spin_lock_bh(&priv->j1939_socks_lock); + list_add_tail(&jsk->list, &priv->j1939_socks); + spin_unlock_bh(&priv->j1939_socks_lock); +} + +static void j1939_jsk_del(struct j1939_priv *priv, struct j1939_sock *jsk) +{ + spin_lock_bh(&priv->j1939_socks_lock); + list_del_init(&jsk->list); + spin_unlock_bh(&priv->j1939_socks_lock); + + jsk->priv = NULL; + j1939_priv_put(priv); + jsk->state &= ~J1939_SOCK_BOUND; +} + +static bool j1939_sk_queue_session(struct j1939_session *session) +{ + struct j1939_sock *jsk = j1939_sk(session->sk); + bool empty; + + spin_lock_bh(&jsk->sk_session_queue_lock); + empty = list_empty(&jsk->sk_session_queue); + j1939_session_get(session); + list_add_tail(&session->sk_session_queue_entry, &jsk->sk_session_queue); + spin_unlock_bh(&jsk->sk_session_queue_lock); + j1939_sock_pending_add(&jsk->sk); + + return empty; +} + +static struct +j1939_session *j1939_sk_get_incomplete_session(struct j1939_sock *jsk) +{ + struct j1939_session *session = NULL; + + spin_lock_bh(&jsk->sk_session_queue_lock); + if (!list_empty(&jsk->sk_session_queue)) { + session = list_last_entry(&jsk->sk_session_queue, + struct j1939_session, + sk_session_queue_entry); + if (session->total_queued_size == session->total_message_size) + session = NULL; + else + j1939_session_get(session); + } + spin_unlock_bh(&jsk->sk_session_queue_lock); + + return session; +} + +static void j1939_sk_queue_drop_all(struct j1939_priv *priv, + struct j1939_sock *jsk, int err) +{ + struct j1939_session *session, *tmp; + + netdev_dbg(priv->ndev, "%s: err: %i\n", __func__, err); + spin_lock_bh(&jsk->sk_session_queue_lock); + list_for_each_entry_safe(session, tmp, &jsk->sk_session_queue, + sk_session_queue_entry) { + list_del_init(&session->sk_session_queue_entry); + session->err = err; + j1939_session_put(session); + } + spin_unlock_bh(&jsk->sk_session_queue_lock); +} + +static void j1939_sk_queue_activate_next_locked(struct j1939_session *session) +{ + struct j1939_sock *jsk; + struct j1939_session *first; + int err; + + /* RX-Session don't have a socket (yet) */ + if (!session->sk) + return; + + jsk = j1939_sk(session->sk); + lockdep_assert_held(&jsk->sk_session_queue_lock); + + err = session->err; + + first = list_first_entry_or_null(&jsk->sk_session_queue, + struct j1939_session, + sk_session_queue_entry); + + /* Some else has already activated the next session */ + if (first != session) + return; + +activate_next: + list_del_init(&first->sk_session_queue_entry); + j1939_session_put(first); + first = list_first_entry_or_null(&jsk->sk_session_queue, + struct j1939_session, + sk_session_queue_entry); + if (!first) + return; + + if (WARN_ON_ONCE(j1939_session_activate(first))) { + first->err = -EBUSY; + goto activate_next; + } else { + /* Give receiver some time (arbitrary chosen) to recover */ + int time_ms = 0; + + if (err) + time_ms = 10 + prandom_u32_max(16); + + j1939_tp_schedule_txtimer(first, time_ms); + } +} + +void j1939_sk_queue_activate_next(struct j1939_session *session) +{ + struct j1939_sock *jsk; + + if (!session->sk) + return; + + jsk = j1939_sk(session->sk); + + spin_lock_bh(&jsk->sk_session_queue_lock); + j1939_sk_queue_activate_next_locked(session); + spin_unlock_bh(&jsk->sk_session_queue_lock); +} + +static bool j1939_sk_match_dst(struct j1939_sock *jsk, + const struct j1939_sk_buff_cb *skcb) +{ + if ((jsk->state & J1939_SOCK_PROMISC)) + return true; + + /* Destination address filter */ + if (jsk->addr.src_name && skcb->addr.dst_name) { + if (jsk->addr.src_name != skcb->addr.dst_name) + return false; + } else { + /* receive (all sockets) if + * - all packages that match our bind() address + * - all broadcast on a socket if SO_BROADCAST + * is set + */ + if (j1939_address_is_unicast(skcb->addr.da)) { + if (jsk->addr.sa != skcb->addr.da) + return false; + } else if (!sock_flag(&jsk->sk, SOCK_BROADCAST)) { + /* receiving broadcast without SO_BROADCAST + * flag is not allowed + */ + return false; + } + } + + /* Source address filter */ + if (jsk->state & J1939_SOCK_CONNECTED) { + /* receive (all sockets) if + * - all packages that match our connect() name or address + */ + if (jsk->addr.dst_name && skcb->addr.src_name) { + if (jsk->addr.dst_name != skcb->addr.src_name) + return false; + } else { + if (jsk->addr.da != skcb->addr.sa) + return false; + } + } + + /* PGN filter */ + if (j1939_pgn_is_valid(jsk->pgn_rx_filter) && + jsk->pgn_rx_filter != skcb->addr.pgn) + return false; + + return true; +} + +/* matches skb control buffer (addr) with a j1939 filter */ +static bool j1939_sk_match_filter(struct j1939_sock *jsk, + const struct j1939_sk_buff_cb *skcb) +{ + const struct j1939_filter *f = jsk->filters; + int nfilter = jsk->nfilters; + + if (!nfilter) + /* receive all when no filters are assigned */ + return true; + + for (; nfilter; ++f, --nfilter) { + if ((skcb->addr.pgn & f->pgn_mask) != f->pgn) + continue; + if ((skcb->addr.sa & f->addr_mask) != f->addr) + continue; + if ((skcb->addr.src_name & f->name_mask) != f->name) + continue; + return true; + } + return false; +} + +static bool j1939_sk_recv_match_one(struct j1939_sock *jsk, + const struct j1939_sk_buff_cb *skcb) +{ + if (!(jsk->state & J1939_SOCK_BOUND)) + return false; + + if (!j1939_sk_match_dst(jsk, skcb)) + return false; + + if (!j1939_sk_match_filter(jsk, skcb)) + return false; + + return true; +} + +static void j1939_sk_recv_one(struct j1939_sock *jsk, struct sk_buff *oskb) +{ + const struct j1939_sk_buff_cb *oskcb = j1939_skb_to_cb(oskb); + struct j1939_sk_buff_cb *skcb; + struct sk_buff *skb; + + if (oskb->sk == &jsk->sk) + return; + + if (!j1939_sk_recv_match_one(jsk, oskcb)) + return; + + skb = skb_clone(oskb, GFP_ATOMIC); + if (!skb) { + pr_warn("skb clone failed\n"); + return; + } + can_skb_set_owner(skb, oskb->sk); + + skcb = j1939_skb_to_cb(skb); + skcb->msg_flags &= ~(MSG_DONTROUTE); + if (skb->sk) + skcb->msg_flags |= MSG_DONTROUTE; + + if (sock_queue_rcv_skb(&jsk->sk, skb) < 0) + kfree_skb(skb); +} + +bool j1939_sk_recv_match(struct j1939_priv *priv, struct j1939_sk_buff_cb *skcb) +{ + struct j1939_sock *jsk; + bool match = false; + + spin_lock_bh(&priv->j1939_socks_lock); + list_for_each_entry(jsk, &priv->j1939_socks, list) { + match = j1939_sk_recv_match_one(jsk, skcb); + if (match) + break; + } + spin_unlock_bh(&priv->j1939_socks_lock); + + return match; +} + +void j1939_sk_recv(struct j1939_priv *priv, struct sk_buff *skb) +{ + struct j1939_sock *jsk; + + spin_lock_bh(&priv->j1939_socks_lock); + list_for_each_entry(jsk, &priv->j1939_socks, list) { + j1939_sk_recv_one(jsk, skb); + } + spin_unlock_bh(&priv->j1939_socks_lock); +} + +static int j1939_sk_init(struct sock *sk) +{ + struct j1939_sock *jsk = j1939_sk(sk); + + /* Ensure that "sk" is first member in "struct j1939_sock", so that we + * can skip it during memset(). + */ + BUILD_BUG_ON(offsetof(struct j1939_sock, sk) != 0); + memset((void *)jsk + sizeof(jsk->sk), 0x0, + sizeof(*jsk) - sizeof(jsk->sk)); + + INIT_LIST_HEAD(&jsk->list); + init_waitqueue_head(&jsk->waitq); + jsk->sk.sk_priority = j1939_to_sk_priority(6); + jsk->sk.sk_reuse = 1; /* per default */ + jsk->addr.sa = J1939_NO_ADDR; + jsk->addr.da = J1939_NO_ADDR; + jsk->addr.pgn = J1939_NO_PGN; + jsk->pgn_rx_filter = J1939_NO_PGN; + atomic_set(&jsk->skb_pending, 0); + spin_lock_init(&jsk->sk_session_queue_lock); + INIT_LIST_HEAD(&jsk->sk_session_queue); + + return 0; +} + +static int j1939_sk_sanity_check(struct sockaddr_can *addr, int len) +{ + if (!addr) + return -EDESTADDRREQ; + if (len < J1939_MIN_NAMELEN) + return -EINVAL; + if (addr->can_family != AF_CAN) + return -EINVAL; + if (!addr->can_ifindex) + return -ENODEV; + if (j1939_pgn_is_valid(addr->can_addr.j1939.pgn) && + !j1939_pgn_is_clean_pdu(addr->can_addr.j1939.pgn)) + return -EINVAL; + + return 0; +} + +static int j1939_sk_bind(struct socket *sock, struct sockaddr *uaddr, int len) +{ + struct sockaddr_can *addr = (struct sockaddr_can *)uaddr; + struct j1939_sock *jsk = j1939_sk(sock->sk); + struct j1939_priv *priv = jsk->priv; + struct sock *sk = sock->sk; + struct net *net = sock_net(sk); + int ret = 0; + + ret = j1939_sk_sanity_check(addr, len); + if (ret) + return ret; + + lock_sock(sock->sk); + + /* Already bound to an interface? */ + if (jsk->state & J1939_SOCK_BOUND) { + /* A re-bind() to a different interface is not + * supported. + */ + if (jsk->ifindex != addr->can_ifindex) { + ret = -EINVAL; + goto out_release_sock; + } + + /* drop old references */ + j1939_jsk_del(priv, jsk); + j1939_local_ecu_put(priv, jsk->addr.src_name, jsk->addr.sa); + } else { + struct net_device *ndev; + + ndev = dev_get_by_index(net, addr->can_ifindex); + if (!ndev) { + ret = -ENODEV; + goto out_release_sock; + } + + if (ndev->type != ARPHRD_CAN) { + dev_put(ndev); + ret = -ENODEV; + goto out_release_sock; + } + + priv = j1939_netdev_start(ndev); + dev_put(ndev); + if (IS_ERR(priv)) { + ret = PTR_ERR(priv); + goto out_release_sock; + } + + jsk->ifindex = addr->can_ifindex; + } + + /* set default transmit pgn */ + if (j1939_pgn_is_valid(addr->can_addr.j1939.pgn)) + jsk->pgn_rx_filter = addr->can_addr.j1939.pgn; + jsk->addr.src_name = addr->can_addr.j1939.name; + jsk->addr.sa = addr->can_addr.j1939.addr; + + /* get new references */ + ret = j1939_local_ecu_get(priv, jsk->addr.src_name, jsk->addr.sa); + if (ret) { + j1939_netdev_stop(priv); + goto out_release_sock; + } + + j1939_jsk_add(priv, jsk); + + out_release_sock: /* fall through */ + release_sock(sock->sk); + + return ret; +} + +static int j1939_sk_connect(struct socket *sock, struct sockaddr *uaddr, + int len, int flags) +{ + struct sockaddr_can *addr = (struct sockaddr_can *)uaddr; + struct j1939_sock *jsk = j1939_sk(sock->sk); + int ret = 0; + + ret = j1939_sk_sanity_check(addr, len); + if (ret) + return ret; + + lock_sock(sock->sk); + + /* bind() before connect() is mandatory */ + if (!(jsk->state & J1939_SOCK_BOUND)) { + ret = -EINVAL; + goto out_release_sock; + } + + /* A connect() to a different interface is not supported. */ + if (jsk->ifindex != addr->can_ifindex) { + ret = -EINVAL; + goto out_release_sock; + } + + if (!addr->can_addr.j1939.name && + addr->can_addr.j1939.addr == J1939_NO_ADDR && + !sock_flag(&jsk->sk, SOCK_BROADCAST)) { + /* broadcast, but SO_BROADCAST not set */ + ret = -EACCES; + goto out_release_sock; + } + + jsk->addr.dst_name = addr->can_addr.j1939.name; + jsk->addr.da = addr->can_addr.j1939.addr; + + if (j1939_pgn_is_valid(addr->can_addr.j1939.pgn)) + jsk->addr.pgn = addr->can_addr.j1939.pgn; + + jsk->state |= J1939_SOCK_CONNECTED; + + out_release_sock: /* fall through */ + release_sock(sock->sk); + + return ret; +} + +static void j1939_sk_sock2sockaddr_can(struct sockaddr_can *addr, + const struct j1939_sock *jsk, int peer) +{ + addr->can_family = AF_CAN; + addr->can_ifindex = jsk->ifindex; + addr->can_addr.j1939.pgn = jsk->addr.pgn; + if (peer) { + addr->can_addr.j1939.name = jsk->addr.dst_name; + addr->can_addr.j1939.addr = jsk->addr.da; + } else { + addr->can_addr.j1939.name = jsk->addr.src_name; + addr->can_addr.j1939.addr = jsk->addr.sa; + } +} + +static int j1939_sk_getname(struct socket *sock, struct sockaddr *uaddr, + int peer) +{ + struct sockaddr_can *addr = (struct sockaddr_can *)uaddr; + struct sock *sk = sock->sk; + struct j1939_sock *jsk = j1939_sk(sk); + int ret = 0; + + lock_sock(sk); + + if (peer && !(jsk->state & J1939_SOCK_CONNECTED)) { + ret = -EADDRNOTAVAIL; + goto failure; + } + + j1939_sk_sock2sockaddr_can(addr, jsk, peer); + ret = J1939_MIN_NAMELEN; + + failure: + release_sock(sk); + + return ret; +} + +static int j1939_sk_release(struct socket *sock) +{ + struct sock *sk = sock->sk; + struct j1939_sock *jsk; + + if (!sk) + return 0; + + jsk = j1939_sk(sk); + lock_sock(sk); + + if (jsk->state & J1939_SOCK_BOUND) { + struct j1939_priv *priv = jsk->priv; + + if (wait_event_interruptible(jsk->waitq, + !j1939_sock_pending_get(&jsk->sk))) { + j1939_cancel_active_session(priv, sk); + j1939_sk_queue_drop_all(priv, jsk, ESHUTDOWN); + } + + j1939_jsk_del(priv, jsk); + + j1939_local_ecu_put(priv, jsk->addr.src_name, + jsk->addr.sa); + + j1939_netdev_stop(priv); + } + + sock_orphan(sk); + sock->sk = NULL; + + release_sock(sk); + sock_put(sk); + + return 0; +} + +static int j1939_sk_setsockopt_flag(struct j1939_sock *jsk, char __user *optval, + unsigned int optlen, int flag) +{ + int tmp; + + if (optlen != sizeof(tmp)) + return -EINVAL; + if (copy_from_user(&tmp, optval, optlen)) + return -EFAULT; + lock_sock(&jsk->sk); + if (tmp) + jsk->state |= flag; + else + jsk->state &= ~flag; + release_sock(&jsk->sk); + return tmp; +} + +static int j1939_sk_setsockopt(struct socket *sock, int level, int optname, + char __user *optval, unsigned int optlen) +{ + struct sock *sk = sock->sk; + struct j1939_sock *jsk = j1939_sk(sk); + int tmp, count = 0, ret = 0; + struct j1939_filter *filters = NULL, *ofilters; + + if (level != SOL_CAN_J1939) + return -EINVAL; + + switch (optname) { + case SO_J1939_FILTER: + if (optval) { + struct j1939_filter *f; + int c; + + if (optlen % sizeof(*filters) != 0) + return -EINVAL; + + if (optlen > J1939_FILTER_MAX * + sizeof(struct j1939_filter)) + return -EINVAL; + + count = optlen / sizeof(*filters); + filters = memdup_user(optval, optlen); + if (IS_ERR(filters)) + return PTR_ERR(filters); + + for (f = filters, c = count; c; f++, c--) { + f->name &= f->name_mask; + f->pgn &= f->pgn_mask; + f->addr &= f->addr_mask; + } + } + + lock_sock(&jsk->sk); + ofilters = jsk->filters; + jsk->filters = filters; + jsk->nfilters = count; + release_sock(&jsk->sk); + kfree(ofilters); + return 0; + case SO_J1939_PROMISC: + return j1939_sk_setsockopt_flag(jsk, optval, optlen, + J1939_SOCK_PROMISC); + case SO_J1939_ERRQUEUE: + ret = j1939_sk_setsockopt_flag(jsk, optval, optlen, + J1939_SOCK_ERRQUEUE); + if (ret < 0) + return ret; + + if (!(jsk->state & J1939_SOCK_ERRQUEUE)) + skb_queue_purge(&sk->sk_error_queue); + return ret; + case SO_J1939_SEND_PRIO: + if (optlen != sizeof(tmp)) + return -EINVAL; + if (copy_from_user(&tmp, optval, optlen)) + return -EFAULT; + if (tmp < 0 || tmp > 7) + return -EDOM; + if (tmp < 2 && !capable(CAP_NET_ADMIN)) + return -EPERM; + lock_sock(&jsk->sk); + jsk->sk.sk_priority = j1939_to_sk_priority(tmp); + release_sock(&jsk->sk); + return 0; + default: + return -ENOPROTOOPT; + } +} + +static int j1939_sk_getsockopt(struct socket *sock, int level, int optname, + char __user *optval, int __user *optlen) +{ + struct sock *sk = sock->sk; + struct j1939_sock *jsk = j1939_sk(sk); + int ret, ulen; + /* set defaults for using 'int' properties */ + int tmp = 0; + int len = sizeof(tmp); + void *val = &tmp; + + if (level != SOL_CAN_J1939) + return -EINVAL; + if (get_user(ulen, optlen)) + return -EFAULT; + if (ulen < 0) + return -EINVAL; + + lock_sock(&jsk->sk); + switch (optname) { + case SO_J1939_PROMISC: + tmp = (jsk->state & J1939_SOCK_PROMISC) ? 1 : 0; + break; + case SO_J1939_ERRQUEUE: + tmp = (jsk->state & J1939_SOCK_ERRQUEUE) ? 1 : 0; + break; + case SO_J1939_SEND_PRIO: + tmp = j1939_prio(jsk->sk.sk_priority); + break; + default: + ret = -ENOPROTOOPT; + goto no_copy; + } + + /* copy to user, based on 'len' & 'val' + * but most sockopt's are 'int' properties, and have 'len' & 'val' + * left unchanged, but instead modified 'tmp' + */ + if (len > ulen) + ret = -EFAULT; + else if (put_user(len, optlen)) + ret = -EFAULT; + else if (copy_to_user(optval, val, len)) + ret = -EFAULT; + else + ret = 0; + no_copy: + release_sock(&jsk->sk); + return ret; +} + +static int j1939_sk_recvmsg(struct socket *sock, struct msghdr *msg, + size_t size, int flags) +{ + struct sock *sk = sock->sk; + struct sk_buff *skb; + struct j1939_sk_buff_cb *skcb; + int ret = 0; + + if (flags & ~(MSG_DONTWAIT | MSG_ERRQUEUE)) + return -EINVAL; + + if (flags & MSG_ERRQUEUE) + return sock_recv_errqueue(sock->sk, msg, size, SOL_CAN_J1939, + SCM_J1939_ERRQUEUE); + + skb = skb_recv_datagram(sk, flags, 0, &ret); + if (!skb) + return ret; + + if (size < skb->len) + msg->msg_flags |= MSG_TRUNC; + else + size = skb->len; + + ret = memcpy_to_msg(msg, skb->data, size); + if (ret < 0) { + skb_free_datagram(sk, skb); + return ret; + } + + skcb = j1939_skb_to_cb(skb); + if (j1939_address_is_valid(skcb->addr.da)) + put_cmsg(msg, SOL_CAN_J1939, SCM_J1939_DEST_ADDR, + sizeof(skcb->addr.da), &skcb->addr.da); + + if (skcb->addr.dst_name) + put_cmsg(msg, SOL_CAN_J1939, SCM_J1939_DEST_NAME, + sizeof(skcb->addr.dst_name), &skcb->addr.dst_name); + + put_cmsg(msg, SOL_CAN_J1939, SCM_J1939_PRIO, + sizeof(skcb->priority), &skcb->priority); + + if (msg->msg_name) { + struct sockaddr_can *paddr = msg->msg_name; + + msg->msg_namelen = J1939_MIN_NAMELEN; + memset(msg->msg_name, 0, msg->msg_namelen); + paddr->can_family = AF_CAN; + paddr->can_ifindex = skb->skb_iif; + paddr->can_addr.j1939.name = skcb->addr.src_name; + paddr->can_addr.j1939.addr = skcb->addr.sa; + paddr->can_addr.j1939.pgn = skcb->addr.pgn; + } + + sock_recv_ts_and_drops(msg, sk, skb); + msg->msg_flags |= skcb->msg_flags; + skb_free_datagram(sk, skb); + + return size; +} + +static struct sk_buff *j1939_sk_alloc_skb(struct net_device *ndev, + struct sock *sk, + struct msghdr *msg, size_t size, + int *errcode) +{ + struct j1939_sock *jsk = j1939_sk(sk); + struct j1939_sk_buff_cb *skcb; + struct sk_buff *skb; + int ret; + + skb = sock_alloc_send_skb(sk, + size + + sizeof(struct can_frame) - + sizeof(((struct can_frame *)NULL)->data) + + sizeof(struct can_skb_priv), + msg->msg_flags & MSG_DONTWAIT, &ret); + if (!skb) + goto failure; + + can_skb_reserve(skb); + can_skb_prv(skb)->ifindex = ndev->ifindex; + can_skb_prv(skb)->skbcnt = 0; + skb_reserve(skb, offsetof(struct can_frame, data)); + + ret = memcpy_from_msg(skb_put(skb, size), msg, size); + if (ret < 0) + goto free_skb; + + skb->dev = ndev; + + skcb = j1939_skb_to_cb(skb); + memset(skcb, 0, sizeof(*skcb)); + skcb->addr = jsk->addr; + skcb->priority = j1939_prio(sk->sk_priority); + + if (msg->msg_name) { + struct sockaddr_can *addr = msg->msg_name; + + if (addr->can_addr.j1939.name || + addr->can_addr.j1939.addr != J1939_NO_ADDR) { + skcb->addr.dst_name = addr->can_addr.j1939.name; + skcb->addr.da = addr->can_addr.j1939.addr; + } + if (j1939_pgn_is_valid(addr->can_addr.j1939.pgn)) + skcb->addr.pgn = addr->can_addr.j1939.pgn; + } + + *errcode = ret; + return skb; + +free_skb: + kfree_skb(skb); +failure: + *errcode = ret; + return NULL; +} + +static size_t j1939_sk_opt_stats_get_size(void) +{ + return + nla_total_size(sizeof(u32)) + /* J1939_NLA_BYTES_ACKED */ + 0; +} + +static struct sk_buff * +j1939_sk_get_timestamping_opt_stats(struct j1939_session *session) +{ + struct sk_buff *stats; + u32 size; + + stats = alloc_skb(j1939_sk_opt_stats_get_size(), GFP_ATOMIC); + if (!stats) + return NULL; + + if (session->skcb.addr.type == J1939_SIMPLE) + size = session->total_message_size; + else + size = min(session->pkt.tx_acked * 7, + session->total_message_size); + + nla_put_u32(stats, J1939_NLA_BYTES_ACKED, size); + + return stats; +} + +void j1939_sk_errqueue(struct j1939_session *session, + enum j1939_sk_errqueue_type type) +{ + struct j1939_priv *priv = session->priv; + struct sock *sk = session->sk; + struct j1939_sock *jsk; + struct sock_exterr_skb *serr; + struct sk_buff *skb; + char *state = "UNK"; + int err; + + /* currently we have no sk for the RX session */ + if (!sk) + return; + + jsk = j1939_sk(sk); + + if (!(jsk->state & J1939_SOCK_ERRQUEUE)) + return; + + skb = j1939_sk_get_timestamping_opt_stats(session); + if (!skb) + return; + + skb->tstamp = ktime_get_real(); + + BUILD_BUG_ON(sizeof(struct sock_exterr_skb) > sizeof(skb->cb)); + + serr = SKB_EXT_ERR(skb); + memset(serr, 0, sizeof(*serr)); + switch (type) { + case J1939_ERRQUEUE_ACK: + if (!(sk->sk_tsflags & SOF_TIMESTAMPING_TX_ACK)) + return; + + serr->ee.ee_errno = ENOMSG; + serr->ee.ee_origin = SO_EE_ORIGIN_TIMESTAMPING; + serr->ee.ee_info = SCM_TSTAMP_ACK; + state = "ACK"; + break; + case J1939_ERRQUEUE_SCHED: + if (!(sk->sk_tsflags & SOF_TIMESTAMPING_TX_SCHED)) + return; + + serr->ee.ee_errno = ENOMSG; + serr->ee.ee_origin = SO_EE_ORIGIN_TIMESTAMPING; + serr->ee.ee_info = SCM_TSTAMP_SCHED; + state = "SCH"; + break; + case J1939_ERRQUEUE_ABORT: + serr->ee.ee_errno = session->err; + serr->ee.ee_origin = SO_EE_ORIGIN_LOCAL; + serr->ee.ee_info = J1939_EE_INFO_TX_ABORT; + state = "ABT"; + break; + default: + netdev_err(priv->ndev, "Unknown errqueue type %i\n", type); + } + + serr->opt_stats = true; + if (sk->sk_tsflags & SOF_TIMESTAMPING_OPT_ID) + serr->ee.ee_data = session->tskey; + + netdev_dbg(session->priv->ndev, "%s: 0x%p tskey: %i, state: %s\n", + __func__, session, session->tskey, state); + err = sock_queue_err_skb(sk, skb); + + if (err) + kfree_skb(skb); +}; + +void j1939_sk_send_loop_abort(struct sock *sk, int err) +{ + sk->sk_err = err; + + sk->sk_error_report(sk); +} + +static int j1939_sk_send_loop(struct j1939_priv *priv, struct sock *sk, + struct msghdr *msg, size_t size) + +{ + struct j1939_sock *jsk = j1939_sk(sk); + struct j1939_session *session = j1939_sk_get_incomplete_session(jsk); + struct sk_buff *skb; + size_t segment_size, todo_size; + int ret = 0; + + if (session && + session->total_message_size != session->total_queued_size + size) { + j1939_session_put(session); + return -EIO; + } + + todo_size = size; + + while (todo_size) { + struct j1939_sk_buff_cb *skcb; + + segment_size = min_t(size_t, J1939_MAX_TP_PACKET_SIZE, + todo_size); + + /* Allocate skb for one segment */ + skb = j1939_sk_alloc_skb(priv->ndev, sk, msg, segment_size, + &ret); + if (ret) + break; + + skcb = j1939_skb_to_cb(skb); + + if (!session) { + /* at this point the size should be full size + * of the session + */ + skcb->offset = 0; + session = j1939_tp_send(priv, skb, size); + if (IS_ERR(session)) { + ret = PTR_ERR(session); + goto kfree_skb; + } + if (j1939_sk_queue_session(session)) { + /* try to activate session if we a + * fist in the queue + */ + if (!j1939_session_activate(session)) { + j1939_tp_schedule_txtimer(session, 0); + } else { + ret = -EBUSY; + session->err = ret; + j1939_sk_queue_drop_all(priv, jsk, + EBUSY); + break; + } + } + } else { + skcb->offset = session->total_queued_size; + j1939_session_skb_queue(session, skb); + } + + todo_size -= segment_size; + session->total_queued_size += segment_size; + } + + switch (ret) { + case 0: /* OK */ + if (todo_size) + netdev_warn(priv->ndev, + "no error found and not completely queued?! %zu\n", + todo_size); + ret = size; + break; + case -ERESTARTSYS: + ret = -EINTR; + /* fall through */ + case -EAGAIN: /* OK */ + if (todo_size != size) + ret = size - todo_size; + break; + default: /* ERROR */ + break; + } + + if (session) + j1939_session_put(session); + + return ret; + + kfree_skb: + kfree_skb(skb); + return ret; +} + +static int j1939_sk_sendmsg(struct socket *sock, struct msghdr *msg, + size_t size) +{ + struct sock *sk = sock->sk; + struct j1939_sock *jsk = j1939_sk(sk); + struct j1939_priv *priv = jsk->priv; + int ifindex; + int ret; + + /* various socket state tests */ + if (!(jsk->state & J1939_SOCK_BOUND)) + return -EBADFD; + + ifindex = jsk->ifindex; + + if (!jsk->addr.src_name && jsk->addr.sa == J1939_NO_ADDR) + /* no source address assigned yet */ + return -EBADFD; + + /* deal with provided destination address info */ + if (msg->msg_name) { + struct sockaddr_can *addr = msg->msg_name; + + if (msg->msg_namelen < J1939_MIN_NAMELEN) + return -EINVAL; + + if (addr->can_family != AF_CAN) + return -EINVAL; + + if (addr->can_ifindex && addr->can_ifindex != ifindex) + return -EBADFD; + + if (j1939_pgn_is_valid(addr->can_addr.j1939.pgn) && + !j1939_pgn_is_clean_pdu(addr->can_addr.j1939.pgn)) + return -EINVAL; + + if (!addr->can_addr.j1939.name && + addr->can_addr.j1939.addr == J1939_NO_ADDR && + !sock_flag(sk, SOCK_BROADCAST)) + /* broadcast, but SO_BROADCAST not set */ + return -EACCES; + } else { + if (!jsk->addr.dst_name && jsk->addr.da == J1939_NO_ADDR && + !sock_flag(sk, SOCK_BROADCAST)) + /* broadcast, but SO_BROADCAST not set */ + return -EACCES; + } + + ret = j1939_sk_send_loop(priv, sk, msg, size); + + return ret; +} + +void j1939_sk_netdev_event_netdown(struct j1939_priv *priv) +{ + struct j1939_sock *jsk; + int error_code = ENETDOWN; + + spin_lock_bh(&priv->j1939_socks_lock); + list_for_each_entry(jsk, &priv->j1939_socks, list) { + jsk->sk.sk_err = error_code; + if (!sock_flag(&jsk->sk, SOCK_DEAD)) + jsk->sk.sk_error_report(&jsk->sk); + + j1939_sk_queue_drop_all(priv, jsk, error_code); + } + spin_unlock_bh(&priv->j1939_socks_lock); +} + +static int j1939_sk_no_ioctlcmd(struct socket *sock, unsigned int cmd, + unsigned long arg) +{ + /* no ioctls for socket layer -> hand it down to NIC layer */ + return -ENOIOCTLCMD; +} + +static const struct proto_ops j1939_ops = { + .family = PF_CAN, + .release = j1939_sk_release, + .bind = j1939_sk_bind, + .connect = j1939_sk_connect, + .socketpair = sock_no_socketpair, + .accept = sock_no_accept, + .getname = j1939_sk_getname, + .poll = datagram_poll, + .ioctl = j1939_sk_no_ioctlcmd, + .listen = sock_no_listen, + .shutdown = sock_no_shutdown, + .setsockopt = j1939_sk_setsockopt, + .getsockopt = j1939_sk_getsockopt, + .sendmsg = j1939_sk_sendmsg, + .recvmsg = j1939_sk_recvmsg, + .mmap = sock_no_mmap, + .sendpage = sock_no_sendpage, +}; + +static struct proto j1939_proto __read_mostly = { + .name = "CAN_J1939", + .owner = THIS_MODULE, + .obj_size = sizeof(struct j1939_sock), + .init = j1939_sk_init, +}; + +const struct can_proto j1939_can_proto = { + .type = SOCK_DGRAM, + .protocol = CAN_J1939, + .ops = &j1939_ops, + .prot = &j1939_proto, +}; diff --git a/net/can/j1939/transport.c b/net/can/j1939/transport.c new file mode 100644 index 000000000000..fe000ea757ea --- /dev/null +++ b/net/can/j1939/transport.c @@ -0,0 +1,2027 @@ +// SPDX-License-Identifier: GPL-2.0 +// Copyright (c) 2010-2011 EIA Electronics, +// Kurt Van Dijck +// Copyright (c) 2018 Protonic, +// Robin van der Gracht +// Copyright (c) 2017-2019 Pengutronix, +// Marc Kleine-Budde +// Copyright (c) 2017-2019 Pengutronix, +// Oleksij Rempel + +#include + +#include "j1939-priv.h" + +#define J1939_XTP_TX_RETRY_LIMIT 100 + +#define J1939_ETP_PGN_CTL 0xc800 +#define J1939_ETP_PGN_DAT 0xc700 +#define J1939_TP_PGN_CTL 0xec00 +#define J1939_TP_PGN_DAT 0xeb00 + +#define J1939_TP_CMD_RTS 0x10 +#define J1939_TP_CMD_CTS 0x11 +#define J1939_TP_CMD_EOMA 0x13 +#define J1939_TP_CMD_BAM 0x20 +#define J1939_TP_CMD_ABORT 0xff + +#define J1939_ETP_CMD_RTS 0x14 +#define J1939_ETP_CMD_CTS 0x15 +#define J1939_ETP_CMD_DPO 0x16 +#define J1939_ETP_CMD_EOMA 0x17 +#define J1939_ETP_CMD_ABORT 0xff + +enum j1939_xtp_abort { + J1939_XTP_NO_ABORT = 0, + J1939_XTP_ABORT_BUSY = 1, + /* Already in one or more connection managed sessions and + * cannot support another. + * + * EALREADY: + * Operation already in progress + */ + + J1939_XTP_ABORT_RESOURCE = 2, + /* System resources were needed for another task so this + * connection managed session was terminated. + * + * EMSGSIZE: + * The socket type requires that message be sent atomically, + * and the size of the message to be sent made this + * impossible. + */ + + J1939_XTP_ABORT_TIMEOUT = 3, + /* A timeout occurred and this is the connection abort to + * close the session. + * + * EHOSTUNREACH: + * The destination host cannot be reached (probably because + * the host is down or a remote router cannot reach it). + */ + + J1939_XTP_ABORT_GENERIC = 4, + /* CTS messages received when data transfer is in progress + * + * EBADMSG: + * Not a data message + */ + + J1939_XTP_ABORT_FAULT = 5, + /* Maximal retransmit request limit reached + * + * ENOTRECOVERABLE: + * State not recoverable + */ + + J1939_XTP_ABORT_UNEXPECTED_DATA = 6, + /* Unexpected data transfer packet + * + * ENOTCONN: + * Transport endpoint is not connected + */ + + J1939_XTP_ABORT_BAD_SEQ = 7, + /* Bad sequence number (and software is not able to recover) + * + * EILSEQ: + * Illegal byte sequence + */ + + J1939_XTP_ABORT_DUP_SEQ = 8, + /* Duplicate sequence number (and software is not able to + * recover) + */ + + J1939_XTP_ABORT_EDPO_UNEXPECTED = 9, + /* Unexpected EDPO packet (ETP) or Message size > 1785 bytes + * (TP) + */ + + J1939_XTP_ABORT_BAD_EDPO_PGN = 10, + /* Unexpected EDPO PGN (PGN in EDPO is bad) */ + + J1939_XTP_ABORT_EDPO_OUTOF_CTS = 11, + /* EDPO number of packets is greater than CTS */ + + J1939_XTP_ABORT_BAD_EDPO_OFFSET = 12, + /* Bad EDPO offset */ + + J1939_XTP_ABORT_OTHER_DEPRECATED = 13, + /* Deprecated. Use 250 instead (Any other reason) */ + + J1939_XTP_ABORT_ECTS_UNXPECTED_PGN = 14, + /* Unexpected ECTS PGN (PGN in ECTS is bad) */ + + J1939_XTP_ABORT_ECTS_TOO_BIG = 15, + /* ECTS requested packets exceeds message size */ + + J1939_XTP_ABORT_OTHER = 250, + /* Any other reason (if a Connection Abort reason is + * identified that is not listed in the table use code 250) + */ +}; + +static unsigned int j1939_tp_block = 255; +static unsigned int j1939_tp_packet_delay; +static unsigned int j1939_tp_padding = 1; + +/* helpers */ +static const char *j1939_xtp_abort_to_str(enum j1939_xtp_abort abort) +{ + switch (abort) { + case J1939_XTP_ABORT_BUSY: + return "Already in one or more connection managed sessions and cannot support another."; + case J1939_XTP_ABORT_RESOURCE: + return "System resources were needed for another task so this connection managed session was terminated."; + case J1939_XTP_ABORT_TIMEOUT: + return "A timeout occurred and this is the connection abort to close the session."; + case J1939_XTP_ABORT_GENERIC: + return "CTS messages received when data transfer is in progress"; + case J1939_XTP_ABORT_FAULT: + return "Maximal retransmit request limit reached"; + case J1939_XTP_ABORT_UNEXPECTED_DATA: + return "Unexpected data transfer packet"; + case J1939_XTP_ABORT_BAD_SEQ: + return "Bad sequence number (and software is not able to recover)"; + case J1939_XTP_ABORT_DUP_SEQ: + return "Duplicate sequence number (and software is not able to recover)"; + case J1939_XTP_ABORT_EDPO_UNEXPECTED: + return "Unexpected EDPO packet (ETP) or Message size > 1785 bytes (TP)"; + case J1939_XTP_ABORT_BAD_EDPO_PGN: + return "Unexpected EDPO PGN (PGN in EDPO is bad)"; + case J1939_XTP_ABORT_EDPO_OUTOF_CTS: + return "EDPO number of packets is greater than CTS"; + case J1939_XTP_ABORT_BAD_EDPO_OFFSET: + return "Bad EDPO offset"; + case J1939_XTP_ABORT_OTHER_DEPRECATED: + return "Deprecated. Use 250 instead (Any other reason)"; + case J1939_XTP_ABORT_ECTS_UNXPECTED_PGN: + return "Unexpected ECTS PGN (PGN in ECTS is bad)"; + case J1939_XTP_ABORT_ECTS_TOO_BIG: + return "ECTS requested packets exceeds message size"; + case J1939_XTP_ABORT_OTHER: + return "Any other reason (if a Connection Abort reason is identified that is not listed in the table use code 250)"; + default: + return ""; + } +} + +static int j1939_xtp_abort_to_errno(struct j1939_priv *priv, + enum j1939_xtp_abort abort) +{ + int err; + + switch (abort) { + case J1939_XTP_NO_ABORT: + WARN_ON_ONCE(abort == J1939_XTP_NO_ABORT); + err = 0; + break; + case J1939_XTP_ABORT_BUSY: + err = EALREADY; + break; + case J1939_XTP_ABORT_RESOURCE: + err = EMSGSIZE; + break; + case J1939_XTP_ABORT_TIMEOUT: + err = EHOSTUNREACH; + break; + case J1939_XTP_ABORT_GENERIC: + err = EBADMSG; + break; + case J1939_XTP_ABORT_FAULT: + err = ENOTRECOVERABLE; + break; + case J1939_XTP_ABORT_UNEXPECTED_DATA: + err = ENOTCONN; + break; + case J1939_XTP_ABORT_BAD_SEQ: + err = EILSEQ; + break; + case J1939_XTP_ABORT_DUP_SEQ: + err = EPROTO; + break; + case J1939_XTP_ABORT_EDPO_UNEXPECTED: + err = EPROTO; + break; + case J1939_XTP_ABORT_BAD_EDPO_PGN: + err = EPROTO; + break; + case J1939_XTP_ABORT_EDPO_OUTOF_CTS: + err = EPROTO; + break; + case J1939_XTP_ABORT_BAD_EDPO_OFFSET: + err = EPROTO; + break; + case J1939_XTP_ABORT_OTHER_DEPRECATED: + err = EPROTO; + break; + case J1939_XTP_ABORT_ECTS_UNXPECTED_PGN: + err = EPROTO; + break; + case J1939_XTP_ABORT_ECTS_TOO_BIG: + err = EPROTO; + break; + case J1939_XTP_ABORT_OTHER: + err = EPROTO; + break; + default: + netdev_warn(priv->ndev, "Unknown abort code %i", abort); + err = EPROTO; + } + + return err; +} + +static inline void j1939_session_list_lock(struct j1939_priv *priv) +{ + spin_lock_bh(&priv->active_session_list_lock); +} + +static inline void j1939_session_list_unlock(struct j1939_priv *priv) +{ + spin_unlock_bh(&priv->active_session_list_lock); +} + +void j1939_session_get(struct j1939_session *session) +{ + kref_get(&session->kref); +} + +/* session completion functions */ +static void __j1939_session_drop(struct j1939_session *session) +{ + if (!session->transmission) + return; + + j1939_sock_pending_del(session->sk); +} + +static void j1939_session_destroy(struct j1939_session *session) +{ + if (session->err) + j1939_sk_errqueue(session, J1939_ERRQUEUE_ABORT); + else + j1939_sk_errqueue(session, J1939_ERRQUEUE_ACK); + + netdev_dbg(session->priv->ndev, "%s: 0x%p\n", __func__, session); + + skb_queue_purge(&session->skb_queue); + __j1939_session_drop(session); + j1939_priv_put(session->priv); + kfree(session); +} + +static void __j1939_session_release(struct kref *kref) +{ + struct j1939_session *session = container_of(kref, struct j1939_session, + kref); + + j1939_session_destroy(session); +} + +void j1939_session_put(struct j1939_session *session) +{ + kref_put(&session->kref, __j1939_session_release); +} + +static void j1939_session_txtimer_cancel(struct j1939_session *session) +{ + if (hrtimer_cancel(&session->txtimer)) + j1939_session_put(session); +} + +static void j1939_session_rxtimer_cancel(struct j1939_session *session) +{ + if (hrtimer_cancel(&session->rxtimer)) + j1939_session_put(session); +} + +void j1939_session_timers_cancel(struct j1939_session *session) +{ + j1939_session_txtimer_cancel(session); + j1939_session_rxtimer_cancel(session); +} + +static inline bool j1939_cb_is_broadcast(const struct j1939_sk_buff_cb *skcb) +{ + return (!skcb->addr.dst_name && (skcb->addr.da == 0xff)); +} + +static void j1939_session_skb_drop_old(struct j1939_session *session) +{ + struct sk_buff *do_skb; + struct j1939_sk_buff_cb *do_skcb; + unsigned int offset_start; + unsigned long flags; + + if (skb_queue_len(&session->skb_queue) < 2) + return; + + offset_start = session->pkt.tx_acked * 7; + + spin_lock_irqsave(&session->skb_queue.lock, flags); + do_skb = skb_peek(&session->skb_queue); + do_skcb = j1939_skb_to_cb(do_skb); + + if ((do_skcb->offset + do_skb->len) < offset_start) { + __skb_unlink(do_skb, &session->skb_queue); + kfree_skb(do_skb); + } + spin_unlock_irqrestore(&session->skb_queue.lock, flags); +} + +void j1939_session_skb_queue(struct j1939_session *session, + struct sk_buff *skb) +{ + struct j1939_sk_buff_cb *skcb = j1939_skb_to_cb(skb); + struct j1939_priv *priv = session->priv; + + j1939_ac_fixup(priv, skb); + + if (j1939_address_is_unicast(skcb->addr.da) && + priv->ents[skcb->addr.da].nusers) + skcb->flags |= J1939_ECU_LOCAL_DST; + + skcb->flags |= J1939_ECU_LOCAL_SRC; + + skb_queue_tail(&session->skb_queue, skb); +} + +static struct sk_buff *j1939_session_skb_find(struct j1939_session *session) +{ + struct j1939_priv *priv = session->priv; + struct sk_buff *skb = NULL; + struct sk_buff *do_skb; + struct j1939_sk_buff_cb *do_skcb; + unsigned int offset_start; + unsigned long flags; + + offset_start = session->pkt.dpo * 7; + + spin_lock_irqsave(&session->skb_queue.lock, flags); + skb_queue_walk(&session->skb_queue, do_skb) { + do_skcb = j1939_skb_to_cb(do_skb); + + if (offset_start >= do_skcb->offset && + offset_start < (do_skcb->offset + do_skb->len)) { + skb = do_skb; + } + } + spin_unlock_irqrestore(&session->skb_queue.lock, flags); + + if (!skb) + netdev_dbg(priv->ndev, "%s: 0x%p: no skb found for start: %i, queue size: %i\n", + __func__, session, offset_start, + skb_queue_len(&session->skb_queue)); + + return skb; +} + +/* see if we are receiver + * returns 0 for broadcasts, although we will receive them + */ +static inline int j1939_tp_im_receiver(const struct j1939_sk_buff_cb *skcb) +{ + return skcb->flags & J1939_ECU_LOCAL_DST; +} + +/* see if we are sender */ +static inline int j1939_tp_im_transmitter(const struct j1939_sk_buff_cb *skcb) +{ + return skcb->flags & J1939_ECU_LOCAL_SRC; +} + +/* see if we are involved as either receiver or transmitter */ +static int j1939_tp_im_involved(const struct j1939_sk_buff_cb *skcb, bool swap) +{ + if (swap) + return j1939_tp_im_receiver(skcb); + else + return j1939_tp_im_transmitter(skcb); +} + +static int j1939_tp_im_involved_anydir(struct j1939_sk_buff_cb *skcb) +{ + return skcb->flags & (J1939_ECU_LOCAL_SRC | J1939_ECU_LOCAL_DST); +} + +/* extract pgn from flow-ctl message */ +static inline pgn_t j1939_xtp_ctl_to_pgn(const u8 *dat) +{ + pgn_t pgn; + + pgn = (dat[7] << 16) | (dat[6] << 8) | (dat[5] << 0); + if (j1939_pgn_is_pdu1(pgn)) + pgn &= 0xffff00; + return pgn; +} + +static inline unsigned int j1939_tp_ctl_to_size(const u8 *dat) +{ + return (dat[2] << 8) + (dat[1] << 0); +} + +static inline unsigned int j1939_etp_ctl_to_packet(const u8 *dat) +{ + return (dat[4] << 16) | (dat[3] << 8) | (dat[2] << 0); +} + +static inline unsigned int j1939_etp_ctl_to_size(const u8 *dat) +{ + return (dat[4] << 24) | (dat[3] << 16) | + (dat[2] << 8) | (dat[1] << 0); +} + +/* find existing session: + * reverse: swap cb's src & dst + * there is no problem with matching broadcasts, since + * broadcasts (no dst, no da) would never call this + * with reverse == true + */ +static bool j1939_session_match(struct j1939_addr *se_addr, + struct j1939_addr *sk_addr, bool reverse) +{ + if (se_addr->type != sk_addr->type) + return false; + + if (reverse) { + if (se_addr->src_name) { + if (se_addr->src_name != sk_addr->dst_name) + return false; + } else if (se_addr->sa != sk_addr->da) { + return false; + } + + if (se_addr->dst_name) { + if (se_addr->dst_name != sk_addr->src_name) + return false; + } else if (se_addr->da != sk_addr->sa) { + return false; + } + } else { + if (se_addr->src_name) { + if (se_addr->src_name != sk_addr->src_name) + return false; + } else if (se_addr->sa != sk_addr->sa) { + return false; + } + + if (se_addr->dst_name) { + if (se_addr->dst_name != sk_addr->dst_name) + return false; + } else if (se_addr->da != sk_addr->da) { + return false; + } + } + + return true; +} + +static struct +j1939_session *j1939_session_get_by_addr_locked(struct j1939_priv *priv, + struct list_head *root, + struct j1939_addr *addr, + bool reverse, bool transmitter) +{ + struct j1939_session *session; + + lockdep_assert_held(&priv->active_session_list_lock); + + list_for_each_entry(session, root, active_session_list_entry) { + j1939_session_get(session); + if (j1939_session_match(&session->skcb.addr, addr, reverse) && + session->transmission == transmitter) + return session; + j1939_session_put(session); + } + + return NULL; +} + +static struct +j1939_session *j1939_session_get_simple(struct j1939_priv *priv, + struct sk_buff *skb) +{ + struct j1939_sk_buff_cb *skcb = j1939_skb_to_cb(skb); + struct j1939_session *session; + + lockdep_assert_held(&priv->active_session_list_lock); + + list_for_each_entry(session, &priv->active_session_list, + active_session_list_entry) { + j1939_session_get(session); + if (session->skcb.addr.type == J1939_SIMPLE && + session->tskey == skcb->tskey && session->sk == skb->sk) + return session; + j1939_session_put(session); + } + + return NULL; +} + +static struct +j1939_session *j1939_session_get_by_addr(struct j1939_priv *priv, + struct j1939_addr *addr, + bool reverse, bool transmitter) +{ + struct j1939_session *session; + + j1939_session_list_lock(priv); + session = j1939_session_get_by_addr_locked(priv, + &priv->active_session_list, + addr, reverse, transmitter); + j1939_session_list_unlock(priv); + + return session; +} + +static void j1939_skbcb_swap(struct j1939_sk_buff_cb *skcb) +{ + u8 tmp = 0; + + swap(skcb->addr.dst_name, skcb->addr.src_name); + swap(skcb->addr.da, skcb->addr.sa); + + /* swap SRC and DST flags, leave other untouched */ + if (skcb->flags & J1939_ECU_LOCAL_SRC) + tmp |= J1939_ECU_LOCAL_DST; + if (skcb->flags & J1939_ECU_LOCAL_DST) + tmp |= J1939_ECU_LOCAL_SRC; + skcb->flags &= ~(J1939_ECU_LOCAL_SRC | J1939_ECU_LOCAL_DST); + skcb->flags |= tmp; +} + +static struct +sk_buff *j1939_tp_tx_dat_new(struct j1939_priv *priv, + const struct j1939_sk_buff_cb *re_skcb, + bool ctl, + bool swap_src_dst) +{ + struct sk_buff *skb; + struct j1939_sk_buff_cb *skcb; + + skb = alloc_skb(sizeof(struct can_frame) + sizeof(struct can_skb_priv), + GFP_ATOMIC); + if (unlikely(!skb)) + return ERR_PTR(-ENOMEM); + + skb->dev = priv->ndev; + can_skb_reserve(skb); + can_skb_prv(skb)->ifindex = priv->ndev->ifindex; + /* reserve CAN header */ + skb_reserve(skb, offsetof(struct can_frame, data)); + + memcpy(skb->cb, re_skcb, sizeof(skb->cb)); + skcb = j1939_skb_to_cb(skb); + if (swap_src_dst) + j1939_skbcb_swap(skcb); + + if (ctl) { + if (skcb->addr.type == J1939_ETP) + skcb->addr.pgn = J1939_ETP_PGN_CTL; + else + skcb->addr.pgn = J1939_TP_PGN_CTL; + } else { + if (skcb->addr.type == J1939_ETP) + skcb->addr.pgn = J1939_ETP_PGN_DAT; + else + skcb->addr.pgn = J1939_TP_PGN_DAT; + } + + return skb; +} + +/* TP transmit packet functions */ +static int j1939_tp_tx_dat(struct j1939_session *session, + const u8 *dat, int len) +{ + struct j1939_priv *priv = session->priv; + struct sk_buff *skb; + + skb = j1939_tp_tx_dat_new(priv, &session->skcb, + false, false); + if (IS_ERR(skb)) + return PTR_ERR(skb); + + skb_put_data(skb, dat, len); + if (j1939_tp_padding && len < 8) + memset(skb_put(skb, 8 - len), 0xff, 8 - len); + + return j1939_send_one(priv, skb); +} + +static int j1939_xtp_do_tx_ctl(struct j1939_priv *priv, + const struct j1939_sk_buff_cb *re_skcb, + bool swap_src_dst, pgn_t pgn, const u8 *dat) +{ + struct sk_buff *skb; + u8 *skdat; + + if (!j1939_tp_im_involved(re_skcb, swap_src_dst)) + return 0; + + skb = j1939_tp_tx_dat_new(priv, re_skcb, true, swap_src_dst); + if (IS_ERR(skb)) + return PTR_ERR(skb); + + skdat = skb_put(skb, 8); + memcpy(skdat, dat, 5); + skdat[5] = (pgn >> 0); + skdat[6] = (pgn >> 8); + skdat[7] = (pgn >> 16); + + return j1939_send_one(priv, skb); +} + +static inline int j1939_tp_tx_ctl(struct j1939_session *session, + bool swap_src_dst, const u8 *dat) +{ + struct j1939_priv *priv = session->priv; + + return j1939_xtp_do_tx_ctl(priv, &session->skcb, + swap_src_dst, + session->skcb.addr.pgn, dat); +} + +static int j1939_xtp_tx_abort(struct j1939_priv *priv, + const struct j1939_sk_buff_cb *re_skcb, + bool swap_src_dst, + enum j1939_xtp_abort err, + pgn_t pgn) +{ + u8 dat[5]; + + if (!j1939_tp_im_involved(re_skcb, swap_src_dst)) + return 0; + + memset(dat, 0xff, sizeof(dat)); + dat[0] = J1939_TP_CMD_ABORT; + dat[1] = err; + return j1939_xtp_do_tx_ctl(priv, re_skcb, swap_src_dst, pgn, dat); +} + +void j1939_tp_schedule_txtimer(struct j1939_session *session, int msec) +{ + j1939_session_get(session); + hrtimer_start(&session->txtimer, ms_to_ktime(msec), + HRTIMER_MODE_REL_SOFT); +} + +static inline void j1939_tp_set_rxtimeout(struct j1939_session *session, + int msec) +{ + j1939_session_rxtimer_cancel(session); + j1939_session_get(session); + hrtimer_start(&session->rxtimer, ms_to_ktime(msec), + HRTIMER_MODE_REL_SOFT); +} + +static int j1939_session_tx_rts(struct j1939_session *session) +{ + u8 dat[8]; + int ret; + + memset(dat, 0xff, sizeof(dat)); + + dat[1] = (session->total_message_size >> 0); + dat[2] = (session->total_message_size >> 8); + dat[3] = session->pkt.total; + + if (session->skcb.addr.type == J1939_ETP) { + dat[0] = J1939_ETP_CMD_RTS; + dat[1] = (session->total_message_size >> 0); + dat[2] = (session->total_message_size >> 8); + dat[3] = (session->total_message_size >> 16); + dat[4] = (session->total_message_size >> 24); + } else if (j1939_cb_is_broadcast(&session->skcb)) { + dat[0] = J1939_TP_CMD_BAM; + /* fake cts for broadcast */ + session->pkt.tx = 0; + } else { + dat[0] = J1939_TP_CMD_RTS; + dat[4] = dat[3]; + } + + if (dat[0] == session->last_txcmd) + /* done already */ + return 0; + + ret = j1939_tp_tx_ctl(session, false, dat); + if (ret < 0) + return ret; + + session->last_txcmd = dat[0]; + if (dat[0] == J1939_TP_CMD_BAM) + j1939_tp_schedule_txtimer(session, 50); + + j1939_tp_set_rxtimeout(session, 1250); + + netdev_dbg(session->priv->ndev, "%s: 0x%p\n", __func__, session); + + return 0; +} + +static int j1939_session_tx_dpo(struct j1939_session *session) +{ + unsigned int pkt; + u8 dat[8]; + int ret; + + memset(dat, 0xff, sizeof(dat)); + + dat[0] = J1939_ETP_CMD_DPO; + session->pkt.dpo = session->pkt.tx_acked; + pkt = session->pkt.dpo; + dat[1] = session->pkt.last - session->pkt.tx_acked; + dat[2] = (pkt >> 0); + dat[3] = (pkt >> 8); + dat[4] = (pkt >> 16); + + ret = j1939_tp_tx_ctl(session, false, dat); + if (ret < 0) + return ret; + + session->last_txcmd = dat[0]; + j1939_tp_set_rxtimeout(session, 1250); + session->pkt.tx = session->pkt.tx_acked; + + netdev_dbg(session->priv->ndev, "%s: 0x%p\n", __func__, session); + + return 0; +} + +static int j1939_session_tx_dat(struct j1939_session *session) +{ + struct j1939_priv *priv = session->priv; + struct j1939_sk_buff_cb *skcb; + int offset, pkt_done, pkt_end; + unsigned int len, pdelay; + struct sk_buff *se_skb; + const u8 *tpdat; + int ret = 0; + u8 dat[8]; + + se_skb = j1939_session_skb_find(session); + if (!se_skb) + return -ENOBUFS; + + skcb = j1939_skb_to_cb(se_skb); + tpdat = se_skb->data; + ret = 0; + pkt_done = 0; + if (session->skcb.addr.type != J1939_ETP && + j1939_cb_is_broadcast(&session->skcb)) + pkt_end = session->pkt.total; + else + pkt_end = session->pkt.last; + + while (session->pkt.tx < pkt_end) { + dat[0] = session->pkt.tx - session->pkt.dpo + 1; + offset = (session->pkt.tx * 7) - skcb->offset; + len = se_skb->len - offset; + if (len > 7) + len = 7; + + memcpy(&dat[1], &tpdat[offset], len); + ret = j1939_tp_tx_dat(session, dat, len + 1); + if (ret < 0) { + /* ENOBUS == CAN interface TX queue is full */ + if (ret != -ENOBUFS) + netdev_alert(priv->ndev, + "%s: 0x%p: queue data error: %i\n", + __func__, session, ret); + break; + } + + session->last_txcmd = 0xff; + pkt_done++; + session->pkt.tx++; + pdelay = j1939_cb_is_broadcast(&session->skcb) ? 50 : + j1939_tp_packet_delay; + + if (session->pkt.tx < session->pkt.total && pdelay) { + j1939_tp_schedule_txtimer(session, pdelay); + break; + } + } + + if (pkt_done) + j1939_tp_set_rxtimeout(session, 250); + + return ret; +} + +static int j1939_xtp_txnext_transmiter(struct j1939_session *session) +{ + struct j1939_priv *priv = session->priv; + int ret = 0; + + if (!j1939_tp_im_transmitter(&session->skcb)) { + netdev_alert(priv->ndev, "%s: 0x%p: called by not transmitter!\n", + __func__, session); + return -EINVAL; + } + + switch (session->last_cmd) { + case 0: + ret = j1939_session_tx_rts(session); + break; + + case J1939_ETP_CMD_CTS: + if (session->last_txcmd != J1939_ETP_CMD_DPO) { + ret = j1939_session_tx_dpo(session); + if (ret) + return ret; + } + + /* fall through */ + case J1939_TP_CMD_CTS: + case 0xff: /* did some data */ + case J1939_ETP_CMD_DPO: + case J1939_TP_CMD_BAM: + ret = j1939_session_tx_dat(session); + + break; + default: + netdev_alert(priv->ndev, "%s: 0x%p: unexpected last_cmd: %x\n", + __func__, session, session->last_cmd); + } + + return ret; +} + +static int j1939_session_tx_cts(struct j1939_session *session) +{ + struct j1939_priv *priv = session->priv; + unsigned int pkt, len; + int ret; + u8 dat[8]; + + if (!j1939_sk_recv_match(priv, &session->skcb)) + return -ENOENT; + + len = session->pkt.total - session->pkt.rx; + len = min3(len, session->pkt.block, j1939_tp_block ?: 255); + memset(dat, 0xff, sizeof(dat)); + + if (session->skcb.addr.type == J1939_ETP) { + pkt = session->pkt.rx + 1; + dat[0] = J1939_ETP_CMD_CTS; + dat[1] = len; + dat[2] = (pkt >> 0); + dat[3] = (pkt >> 8); + dat[4] = (pkt >> 16); + } else { + dat[0] = J1939_TP_CMD_CTS; + dat[1] = len; + dat[2] = session->pkt.rx + 1; + } + + if (dat[0] == session->last_txcmd) + /* done already */ + return 0; + + ret = j1939_tp_tx_ctl(session, true, dat); + if (ret < 0) + return ret; + + if (len) + /* only mark cts done when len is set */ + session->last_txcmd = dat[0]; + j1939_tp_set_rxtimeout(session, 1250); + + netdev_dbg(session->priv->ndev, "%s: 0x%p\n", __func__, session); + + return 0; +} + +static int j1939_session_tx_eoma(struct j1939_session *session) +{ + struct j1939_priv *priv = session->priv; + u8 dat[8]; + int ret; + + if (!j1939_sk_recv_match(priv, &session->skcb)) + return -ENOENT; + + memset(dat, 0xff, sizeof(dat)); + + if (session->skcb.addr.type == J1939_ETP) { + dat[0] = J1939_ETP_CMD_EOMA; + dat[1] = session->total_message_size >> 0; + dat[2] = session->total_message_size >> 8; + dat[3] = session->total_message_size >> 16; + dat[4] = session->total_message_size >> 24; + } else { + dat[0] = J1939_TP_CMD_EOMA; + dat[1] = session->total_message_size; + dat[2] = session->total_message_size >> 8; + dat[3] = session->pkt.total; + } + + if (dat[0] == session->last_txcmd) + /* done already */ + return 0; + + ret = j1939_tp_tx_ctl(session, true, dat); + if (ret < 0) + return ret; + + session->last_txcmd = dat[0]; + + /* wait for the EOMA packet to come in */ + j1939_tp_set_rxtimeout(session, 1250); + + netdev_dbg(session->priv->ndev, "%p: 0x%p\n", __func__, session); + + return 0; +} + +static int j1939_xtp_txnext_receiver(struct j1939_session *session) +{ + struct j1939_priv *priv = session->priv; + int ret = 0; + + if (!j1939_tp_im_receiver(&session->skcb)) { + netdev_alert(priv->ndev, "%s: 0x%p: called by not receiver!\n", + __func__, session); + return -EINVAL; + } + + switch (session->last_cmd) { + case J1939_TP_CMD_RTS: + case J1939_ETP_CMD_RTS: + ret = j1939_session_tx_cts(session); + break; + + case J1939_ETP_CMD_CTS: + case J1939_TP_CMD_CTS: + case 0xff: /* did some data */ + case J1939_ETP_CMD_DPO: + if ((session->skcb.addr.type == J1939_TP && + j1939_cb_is_broadcast(&session->skcb))) + break; + + if (session->pkt.rx >= session->pkt.total) { + ret = j1939_session_tx_eoma(session); + } else if (session->pkt.rx >= session->pkt.last) { + session->last_txcmd = 0; + ret = j1939_session_tx_cts(session); + } + break; + default: + netdev_alert(priv->ndev, "%s: 0x%p: unexpected last_cmd: %x\n", + __func__, session, session->last_cmd); + } + + return ret; +} + +static int j1939_simple_txnext(struct j1939_session *session) +{ + struct j1939_priv *priv = session->priv; + struct sk_buff *se_skb = j1939_session_skb_find(session); + struct sk_buff *skb; + int ret; + + if (!se_skb) + return 0; + + skb = skb_clone(se_skb, GFP_ATOMIC); + if (!skb) + return -ENOMEM; + + can_skb_set_owner(skb, se_skb->sk); + + j1939_tp_set_rxtimeout(session, J1939_SIMPLE_ECHO_TIMEOUT_MS); + + ret = j1939_send_one(priv, skb); + if (ret) + return ret; + + j1939_sk_errqueue(session, J1939_ERRQUEUE_SCHED); + j1939_sk_queue_activate_next(session); + + return 0; +} + +static bool j1939_session_deactivate_locked(struct j1939_session *session) +{ + bool active = false; + + lockdep_assert_held(&session->priv->active_session_list_lock); + + if (session->state >= J1939_SESSION_ACTIVE && + session->state < J1939_SESSION_ACTIVE_MAX) { + active = true; + + list_del_init(&session->active_session_list_entry); + session->state = J1939_SESSION_DONE; + j1939_session_put(session); + } + + return active; +} + +static bool j1939_session_deactivate(struct j1939_session *session) +{ + bool active; + + j1939_session_list_lock(session->priv); + active = j1939_session_deactivate_locked(session); + j1939_session_list_unlock(session->priv); + + return active; +} + +static void +j1939_session_deactivate_activate_next(struct j1939_session *session) +{ + if (j1939_session_deactivate(session)) + j1939_sk_queue_activate_next(session); +} + +static void j1939_session_cancel(struct j1939_session *session, + enum j1939_xtp_abort err) +{ + struct j1939_priv *priv = session->priv; + + WARN_ON_ONCE(!err); + + session->err = j1939_xtp_abort_to_errno(priv, err); + /* do not send aborts on incoming broadcasts */ + if (!j1939_cb_is_broadcast(&session->skcb)) { + session->state = J1939_SESSION_WAITING_ABORT; + j1939_xtp_tx_abort(priv, &session->skcb, + !session->transmission, + err, session->skcb.addr.pgn); + } + + if (session->sk) + j1939_sk_send_loop_abort(session->sk, session->err); +} + +static enum hrtimer_restart j1939_tp_txtimer(struct hrtimer *hrtimer) +{ + struct j1939_session *session = + container_of(hrtimer, struct j1939_session, txtimer); + struct j1939_priv *priv = session->priv; + int ret = 0; + + if (session->skcb.addr.type == J1939_SIMPLE) { + ret = j1939_simple_txnext(session); + } else { + if (session->transmission) + ret = j1939_xtp_txnext_transmiter(session); + else + ret = j1939_xtp_txnext_receiver(session); + } + + switch (ret) { + case -ENOBUFS: + /* Retry limit is currently arbitrary chosen */ + if (session->tx_retry < J1939_XTP_TX_RETRY_LIMIT) { + session->tx_retry++; + j1939_tp_schedule_txtimer(session, + 10 + prandom_u32_max(16)); + } else { + netdev_alert(priv->ndev, "%s: 0x%p: tx retry count reached\n", + __func__, session); + session->err = -ENETUNREACH; + j1939_session_rxtimer_cancel(session); + j1939_session_deactivate_activate_next(session); + } + break; + case -ENETDOWN: + /* In this case we should get a netdev_event(), all active + * sessions will be cleared by + * j1939_cancel_all_active_sessions(). So handle this as an + * error, but let j1939_cancel_all_active_sessions() do the + * cleanup including propagation of the error to user space. + */ + break; + case 0: + session->tx_retry = 0; + break; + default: + netdev_alert(priv->ndev, "%s: 0x%p: tx aborted with unknown reason: %i\n", + __func__, session, ret); + if (session->skcb.addr.type != J1939_SIMPLE) { + j1939_tp_set_rxtimeout(session, + J1939_XTP_ABORT_TIMEOUT_MS); + j1939_session_cancel(session, J1939_XTP_ABORT_OTHER); + } else { + session->err = ret; + j1939_session_rxtimer_cancel(session); + j1939_session_deactivate_activate_next(session); + } + } + + j1939_session_put(session); + + return HRTIMER_NORESTART; +} + +static void j1939_session_completed(struct j1939_session *session) +{ + struct sk_buff *skb; + + if (!session->transmission) { + skb = j1939_session_skb_find(session); + /* distribute among j1939 receivers */ + j1939_sk_recv(session->priv, skb); + } + + j1939_session_deactivate_activate_next(session); +} + +static enum hrtimer_restart j1939_tp_rxtimer(struct hrtimer *hrtimer) +{ + struct j1939_session *session = container_of(hrtimer, + struct j1939_session, + rxtimer); + struct j1939_priv *priv = session->priv; + + if (session->state == J1939_SESSION_WAITING_ABORT) { + netdev_alert(priv->ndev, "%s: 0x%p: abort rx timeout. Force session deactivation\n", + __func__, session); + + j1939_session_deactivate_activate_next(session); + + } else if (session->skcb.addr.type == J1939_SIMPLE) { + netdev_alert(priv->ndev, "%s: 0x%p: Timeout. Failed to send simple message.\n", + __func__, session); + + /* The message is probably stuck in the CAN controller and can + * be send as soon as CAN bus is in working state again. + */ + session->err = -ETIME; + j1939_session_deactivate(session); + } else { + netdev_alert(priv->ndev, "%s: 0x%p: rx timeout, send abort\n", + __func__, session); + + j1939_session_list_lock(session->priv); + if (session->state >= J1939_SESSION_ACTIVE && + session->state < J1939_SESSION_ACTIVE_MAX) { + j1939_session_get(session); + hrtimer_start(&session->rxtimer, + ms_to_ktime(J1939_XTP_ABORT_TIMEOUT_MS), + HRTIMER_MODE_REL_SOFT); + j1939_session_cancel(session, J1939_XTP_ABORT_TIMEOUT); + } + j1939_session_list_unlock(session->priv); + } + + j1939_session_put(session); + + return HRTIMER_NORESTART; +} + +static bool j1939_xtp_rx_cmd_bad_pgn(struct j1939_session *session, + const struct sk_buff *skb) +{ + const struct j1939_sk_buff_cb *skcb = j1939_skb_to_cb(skb); + pgn_t pgn = j1939_xtp_ctl_to_pgn(skb->data); + struct j1939_priv *priv = session->priv; + enum j1939_xtp_abort abort = J1939_XTP_NO_ABORT; + u8 cmd = skb->data[0]; + + if (session->skcb.addr.pgn == pgn) + return false; + + switch (cmd) { + case J1939_TP_CMD_BAM: + abort = J1939_XTP_NO_ABORT; + break; + + case J1939_ETP_CMD_RTS: + case J1939_TP_CMD_RTS: /* fall through */ + abort = J1939_XTP_ABORT_BUSY; + break; + + case J1939_ETP_CMD_CTS: + case J1939_TP_CMD_CTS: /* fall through */ + abort = J1939_XTP_ABORT_ECTS_UNXPECTED_PGN; + break; + + case J1939_ETP_CMD_DPO: + abort = J1939_XTP_ABORT_BAD_EDPO_PGN; + break; + + case J1939_ETP_CMD_EOMA: + case J1939_TP_CMD_EOMA: /* fall through */ + abort = J1939_XTP_ABORT_OTHER; + break; + + case J1939_ETP_CMD_ABORT: /* && J1939_TP_CMD_ABORT */ + abort = J1939_XTP_NO_ABORT; + break; + + default: + WARN_ON_ONCE(1); + break; + } + + netdev_warn(priv->ndev, "%s: 0x%p: CMD 0x%02x with PGN 0x%05x for running session with different PGN 0x%05x.\n", + __func__, session, cmd, pgn, session->skcb.addr.pgn); + if (abort != J1939_XTP_NO_ABORT) + j1939_xtp_tx_abort(priv, skcb, true, abort, pgn); + + return true; +} + +static void j1939_xtp_rx_abort_one(struct j1939_priv *priv, struct sk_buff *skb, + bool reverse, bool transmitter) +{ + struct j1939_sk_buff_cb *skcb = j1939_skb_to_cb(skb); + struct j1939_session *session; + u8 abort = skb->data[1]; + + session = j1939_session_get_by_addr(priv, &skcb->addr, reverse, + transmitter); + if (!session) + return; + + if (j1939_xtp_rx_cmd_bad_pgn(session, skb)) + goto abort_put; + + netdev_info(priv->ndev, "%s: 0x%p: 0x%05x: (%u) %s\n", __func__, + session, j1939_xtp_ctl_to_pgn(skb->data), abort, + j1939_xtp_abort_to_str(abort)); + + j1939_session_timers_cancel(session); + session->err = j1939_xtp_abort_to_errno(priv, abort); + if (session->sk) + j1939_sk_send_loop_abort(session->sk, session->err); + j1939_session_deactivate_activate_next(session); + +abort_put: + j1939_session_put(session); +} + +/* abort packets may come in 2 directions */ +static void +j1939_xtp_rx_abort(struct j1939_priv *priv, struct sk_buff *skb, + bool transmitter) +{ + j1939_xtp_rx_abort_one(priv, skb, false, transmitter); + j1939_xtp_rx_abort_one(priv, skb, true, transmitter); +} + +static void +j1939_xtp_rx_eoma_one(struct j1939_session *session, struct sk_buff *skb) +{ + if (j1939_xtp_rx_cmd_bad_pgn(session, skb)) + return; + + netdev_dbg(session->priv->ndev, "%s: 0x%p\n", __func__, session); + + session->pkt.tx_acked = session->pkt.total; + j1939_session_timers_cancel(session); + /* transmitted without problems */ + j1939_session_completed(session); +} + +static void +j1939_xtp_rx_eoma(struct j1939_priv *priv, struct sk_buff *skb, + bool transmitter) +{ + struct j1939_sk_buff_cb *skcb = j1939_skb_to_cb(skb); + struct j1939_session *session; + + session = j1939_session_get_by_addr(priv, &skcb->addr, true, + transmitter); + if (!session) + return; + + j1939_xtp_rx_eoma_one(session, skb); + j1939_session_put(session); +} + +static void +j1939_xtp_rx_cts_one(struct j1939_session *session, struct sk_buff *skb) +{ + enum j1939_xtp_abort err = J1939_XTP_ABORT_FAULT; + unsigned int pkt; + const u8 *dat; + + dat = skb->data; + + if (j1939_xtp_rx_cmd_bad_pgn(session, skb)) + return; + + netdev_dbg(session->priv->ndev, "%s: 0x%p\n", __func__, session); + + if (session->last_cmd == dat[0]) { + err = J1939_XTP_ABORT_DUP_SEQ; + goto out_session_cancel; + } + + if (session->skcb.addr.type == J1939_ETP) + pkt = j1939_etp_ctl_to_packet(dat); + else + pkt = dat[2]; + + if (!pkt) + goto out_session_cancel; + else if (dat[1] > session->pkt.block /* 0xff for etp */) + goto out_session_cancel; + + /* set packet counters only when not CTS(0) */ + session->pkt.tx_acked = pkt - 1; + j1939_session_skb_drop_old(session); + session->pkt.last = session->pkt.tx_acked + dat[1]; + if (session->pkt.last > session->pkt.total) + /* safety measure */ + session->pkt.last = session->pkt.total; + /* TODO: do not set tx here, do it in txtimer */ + session->pkt.tx = session->pkt.tx_acked; + + session->last_cmd = dat[0]; + if (dat[1]) { + j1939_tp_set_rxtimeout(session, 1250); + if (session->transmission) { + if (session->pkt.tx_acked) + j1939_sk_errqueue(session, + J1939_ERRQUEUE_SCHED); + j1939_session_txtimer_cancel(session); + j1939_tp_schedule_txtimer(session, 0); + } + } else { + /* CTS(0) */ + j1939_tp_set_rxtimeout(session, 550); + } + return; + + out_session_cancel: + j1939_session_timers_cancel(session); + j1939_tp_set_rxtimeout(session, J1939_XTP_ABORT_TIMEOUT_MS); + j1939_session_cancel(session, err); +} + +static void +j1939_xtp_rx_cts(struct j1939_priv *priv, struct sk_buff *skb, bool transmitter) +{ + struct j1939_sk_buff_cb *skcb = j1939_skb_to_cb(skb); + struct j1939_session *session; + + session = j1939_session_get_by_addr(priv, &skcb->addr, true, + transmitter); + if (!session) + return; + j1939_xtp_rx_cts_one(session, skb); + j1939_session_put(session); +} + +static struct j1939_session *j1939_session_new(struct j1939_priv *priv, + struct sk_buff *skb, size_t size) +{ + struct j1939_session *session; + struct j1939_sk_buff_cb *skcb; + + session = kzalloc(sizeof(*session), gfp_any()); + if (!session) + return NULL; + + INIT_LIST_HEAD(&session->active_session_list_entry); + INIT_LIST_HEAD(&session->sk_session_queue_entry); + kref_init(&session->kref); + + j1939_priv_get(priv); + session->priv = priv; + session->total_message_size = size; + session->state = J1939_SESSION_NEW; + + skb_queue_head_init(&session->skb_queue); + skb_queue_tail(&session->skb_queue, skb); + + skcb = j1939_skb_to_cb(skb); + memcpy(&session->skcb, skcb, sizeof(session->skcb)); + + hrtimer_init(&session->txtimer, CLOCK_MONOTONIC, + HRTIMER_MODE_REL_SOFT); + session->txtimer.function = j1939_tp_txtimer; + hrtimer_init(&session->rxtimer, CLOCK_MONOTONIC, + HRTIMER_MODE_REL_SOFT); + session->rxtimer.function = j1939_tp_rxtimer; + + netdev_dbg(priv->ndev, "%s: 0x%p: sa: %02x, da: %02x\n", + __func__, session, skcb->addr.sa, skcb->addr.da); + + return session; +} + +static struct +j1939_session *j1939_session_fresh_new(struct j1939_priv *priv, + int size, + const struct j1939_sk_buff_cb *rel_skcb) +{ + struct sk_buff *skb; + struct j1939_sk_buff_cb *skcb; + struct j1939_session *session; + + skb = alloc_skb(size + sizeof(struct can_skb_priv), GFP_ATOMIC); + if (unlikely(!skb)) + return NULL; + + skb->dev = priv->ndev; + can_skb_reserve(skb); + can_skb_prv(skb)->ifindex = priv->ndev->ifindex; + skcb = j1939_skb_to_cb(skb); + memcpy(skcb, rel_skcb, sizeof(*skcb)); + + session = j1939_session_new(priv, skb, skb->len); + if (!session) { + kfree_skb(skb); + return NULL; + } + + /* alloc data area */ + skb_put(skb, size); + /* skb is recounted in j1939_session_new() */ + return session; +} + +int j1939_session_activate(struct j1939_session *session) +{ + struct j1939_priv *priv = session->priv; + struct j1939_session *active = NULL; + int ret = 0; + + j1939_session_list_lock(priv); + if (session->skcb.addr.type != J1939_SIMPLE) + active = j1939_session_get_by_addr_locked(priv, + &priv->active_session_list, + &session->skcb.addr, false, + session->transmission); + if (active) { + j1939_session_put(active); + ret = -EAGAIN; + } else { + WARN_ON_ONCE(session->state != J1939_SESSION_NEW); + list_add_tail(&session->active_session_list_entry, + &priv->active_session_list); + j1939_session_get(session); + session->state = J1939_SESSION_ACTIVE; + + netdev_dbg(session->priv->ndev, "%s: 0x%p\n", + __func__, session); + } + j1939_session_list_unlock(priv); + + return ret; +} + +static struct +j1939_session *j1939_xtp_rx_rts_session_new(struct j1939_priv *priv, + struct sk_buff *skb) +{ + enum j1939_xtp_abort abort = J1939_XTP_NO_ABORT; + struct j1939_sk_buff_cb skcb = *j1939_skb_to_cb(skb); + struct j1939_session *session; + const u8 *dat; + pgn_t pgn; + int len; + + netdev_dbg(priv->ndev, "%s\n", __func__); + + dat = skb->data; + pgn = j1939_xtp_ctl_to_pgn(dat); + skcb.addr.pgn = pgn; + + if (!j1939_sk_recv_match(priv, &skcb)) + return NULL; + + if (skcb.addr.type == J1939_ETP) { + len = j1939_etp_ctl_to_size(dat); + if (len > J1939_MAX_ETP_PACKET_SIZE) + abort = J1939_XTP_ABORT_FAULT; + else if (len > priv->tp_max_packet_size) + abort = J1939_XTP_ABORT_RESOURCE; + else if (len <= J1939_MAX_TP_PACKET_SIZE) + abort = J1939_XTP_ABORT_FAULT; + } else { + len = j1939_tp_ctl_to_size(dat); + if (len > J1939_MAX_TP_PACKET_SIZE) + abort = J1939_XTP_ABORT_FAULT; + else if (len > priv->tp_max_packet_size) + abort = J1939_XTP_ABORT_RESOURCE; + } + + if (abort != J1939_XTP_NO_ABORT) { + j1939_xtp_tx_abort(priv, &skcb, true, abort, pgn); + return NULL; + } + + session = j1939_session_fresh_new(priv, len, &skcb); + if (!session) { + j1939_xtp_tx_abort(priv, &skcb, true, + J1939_XTP_ABORT_RESOURCE, pgn); + return NULL; + } + + /* initialize the control buffer: plain copy */ + session->pkt.total = (len + 6) / 7; + session->pkt.block = 0xff; + if (skcb.addr.type != J1939_ETP) { + if (dat[3] != session->pkt.total) + netdev_alert(priv->ndev, "%s: 0x%p: strange total, %u != %u\n", + __func__, session, session->pkt.total, + dat[3]); + session->pkt.total = dat[3]; + session->pkt.block = min(dat[3], dat[4]); + } + + session->pkt.rx = 0; + session->pkt.tx = 0; + + WARN_ON_ONCE(j1939_session_activate(session)); + + return session; +} + +static int j1939_xtp_rx_rts_session_active(struct j1939_session *session, + struct sk_buff *skb) +{ + struct j1939_sk_buff_cb *skcb = j1939_skb_to_cb(skb); + struct j1939_priv *priv = session->priv; + + if (!session->transmission) { + if (j1939_xtp_rx_cmd_bad_pgn(session, skb)) + return -EBUSY; + + /* RTS on active session */ + j1939_session_timers_cancel(session); + j1939_tp_set_rxtimeout(session, J1939_XTP_ABORT_TIMEOUT_MS); + j1939_session_cancel(session, J1939_XTP_ABORT_BUSY); + } + + if (session->last_cmd != 0) { + /* we received a second rts on the same connection */ + netdev_alert(priv->ndev, "%s: 0x%p: connection exists (%02x %02x). last cmd: %x\n", + __func__, session, skcb->addr.sa, skcb->addr.da, + session->last_cmd); + + j1939_session_timers_cancel(session); + j1939_tp_set_rxtimeout(session, J1939_XTP_ABORT_TIMEOUT_MS); + j1939_session_cancel(session, J1939_XTP_ABORT_BUSY); + + return -EBUSY; + } + + if (session->skcb.addr.sa != skcb->addr.sa || + session->skcb.addr.da != skcb->addr.da) + netdev_warn(priv->ndev, "%s: 0x%p: session->skcb.addr.sa=0x%02x skcb->addr.sa=0x%02x session->skcb.addr.da=0x%02x skcb->addr.da=0x%02x\n", + __func__, session, + session->skcb.addr.sa, skcb->addr.sa, + session->skcb.addr.da, skcb->addr.da); + /* make sure 'sa' & 'da' are correct ! + * They may be 'not filled in yet' for sending + * skb's, since they did not pass the Address Claim ever. + */ + session->skcb.addr.sa = skcb->addr.sa; + session->skcb.addr.da = skcb->addr.da; + + netdev_dbg(session->priv->ndev, "%s: 0x%p\n", __func__, session); + + return 0; +} + +static void j1939_xtp_rx_rts(struct j1939_priv *priv, struct sk_buff *skb, + bool transmitter) +{ + struct j1939_sk_buff_cb *skcb = j1939_skb_to_cb(skb); + struct j1939_session *session; + u8 cmd = skb->data[0]; + + session = j1939_session_get_by_addr(priv, &skcb->addr, false, + transmitter); + + if (!session) { + if (transmitter) { + /* If we're the transmitter and this function is called, + * we received our own RTS. A session has already been + * created. + * + * For some reasons however it might have been destroyed + * already. So don't create a new one here (using + * "j1939_xtp_rx_rts_session_new()") as this will be a + * receiver session. + * + * The reasons the session is already destroyed might + * be: + * - user space closed socket was and the session was + * aborted + * - session was aborted due to external abort message + */ + return; + } + session = j1939_xtp_rx_rts_session_new(priv, skb); + if (!session) + return; + } else { + if (j1939_xtp_rx_rts_session_active(session, skb)) { + j1939_session_put(session); + return; + } + } + session->last_cmd = cmd; + + j1939_tp_set_rxtimeout(session, 1250); + + if (cmd != J1939_TP_CMD_BAM && !session->transmission) { + j1939_session_txtimer_cancel(session); + j1939_tp_schedule_txtimer(session, 0); + } + + j1939_session_put(session); +} + +static void j1939_xtp_rx_dpo_one(struct j1939_session *session, + struct sk_buff *skb) +{ + const u8 *dat = skb->data; + + if (j1939_xtp_rx_cmd_bad_pgn(session, skb)) + return; + + netdev_dbg(session->priv->ndev, "%s: 0x%p\n", __func__, session); + + /* transmitted without problems */ + session->pkt.dpo = j1939_etp_ctl_to_packet(skb->data); + session->last_cmd = dat[0]; + j1939_tp_set_rxtimeout(session, 750); +} + +static void j1939_xtp_rx_dpo(struct j1939_priv *priv, struct sk_buff *skb, + bool transmitter) +{ + struct j1939_sk_buff_cb *skcb = j1939_skb_to_cb(skb); + struct j1939_session *session; + + session = j1939_session_get_by_addr(priv, &skcb->addr, false, + transmitter); + if (!session) { + netdev_info(priv->ndev, + "%s: no connection found\n", __func__); + return; + } + + j1939_xtp_rx_dpo_one(session, skb); + j1939_session_put(session); +} + +static void j1939_xtp_rx_dat_one(struct j1939_session *session, + struct sk_buff *skb) +{ + struct j1939_priv *priv = session->priv; + struct j1939_sk_buff_cb *skcb; + struct sk_buff *se_skb; + const u8 *dat; + u8 *tpdat; + int offset; + int nbytes; + bool final = false; + bool do_cts_eoma = false; + int packet; + + skcb = j1939_skb_to_cb(skb); + dat = skb->data; + if (skb->len <= 1) + /* makes no sense */ + goto out_session_cancel; + + switch (session->last_cmd) { + case 0xff: + break; + case J1939_ETP_CMD_DPO: + if (skcb->addr.type == J1939_ETP) + break; + /* fall through */ + case J1939_TP_CMD_BAM: /* fall through */ + case J1939_TP_CMD_CTS: /* fall through */ + if (skcb->addr.type != J1939_ETP) + break; + /* fall through */ + default: + netdev_info(priv->ndev, "%s: 0x%p: last %02x\n", __func__, + session, session->last_cmd); + goto out_session_cancel; + } + + packet = (dat[0] - 1 + session->pkt.dpo); + if (packet > session->pkt.total || + (session->pkt.rx + 1) > session->pkt.total) { + netdev_info(priv->ndev, "%s: 0x%p: should have been completed\n", + __func__, session); + goto out_session_cancel; + } + se_skb = j1939_session_skb_find(session); + if (!se_skb) { + netdev_warn(priv->ndev, "%s: 0x%p: no skb found\n", __func__, + session); + goto out_session_cancel; + } + + skcb = j1939_skb_to_cb(se_skb); + offset = packet * 7 - skcb->offset; + nbytes = se_skb->len - offset; + if (nbytes > 7) + nbytes = 7; + if (nbytes <= 0 || (nbytes + 1) > skb->len) { + netdev_info(priv->ndev, "%s: 0x%p: nbytes %i, len %i\n", + __func__, session, nbytes, skb->len); + goto out_session_cancel; + } + + tpdat = se_skb->data; + memcpy(&tpdat[offset], &dat[1], nbytes); + if (packet == session->pkt.rx) + session->pkt.rx++; + + if (skcb->addr.type != J1939_ETP && + j1939_cb_is_broadcast(&session->skcb)) { + if (session->pkt.rx >= session->pkt.total) + final = true; + } else { + /* never final, an EOMA must follow */ + if (session->pkt.rx >= session->pkt.last) + do_cts_eoma = true; + } + + if (final) { + j1939_session_completed(session); + } else if (do_cts_eoma) { + j1939_tp_set_rxtimeout(session, 1250); + if (!session->transmission) + j1939_tp_schedule_txtimer(session, 0); + } else { + j1939_tp_set_rxtimeout(session, 250); + } + session->last_cmd = 0xff; + j1939_session_put(session); + + return; + + out_session_cancel: + j1939_session_timers_cancel(session); + j1939_tp_set_rxtimeout(session, J1939_XTP_ABORT_TIMEOUT_MS); + j1939_session_cancel(session, J1939_XTP_ABORT_FAULT); + j1939_session_put(session); +} + +static void j1939_xtp_rx_dat(struct j1939_priv *priv, struct sk_buff *skb) +{ + struct j1939_sk_buff_cb *skcb; + struct j1939_session *session; + + skcb = j1939_skb_to_cb(skb); + + if (j1939_tp_im_transmitter(skcb)) { + session = j1939_session_get_by_addr(priv, &skcb->addr, false, + true); + if (!session) + netdev_info(priv->ndev, "%s: no tx connection found\n", + __func__); + else + j1939_xtp_rx_dat_one(session, skb); + } + + if (j1939_tp_im_receiver(skcb)) { + session = j1939_session_get_by_addr(priv, &skcb->addr, false, + false); + if (!session) + netdev_info(priv->ndev, "%s: no rx connection found\n", + __func__); + else + j1939_xtp_rx_dat_one(session, skb); + } +} + +/* j1939 main intf */ +struct j1939_session *j1939_tp_send(struct j1939_priv *priv, + struct sk_buff *skb, size_t size) +{ + struct j1939_sk_buff_cb *skcb = j1939_skb_to_cb(skb); + struct j1939_session *session; + int ret; + + if (skcb->addr.pgn == J1939_TP_PGN_DAT || + skcb->addr.pgn == J1939_TP_PGN_CTL || + skcb->addr.pgn == J1939_ETP_PGN_DAT || + skcb->addr.pgn == J1939_ETP_PGN_CTL) + /* avoid conflict */ + return ERR_PTR(-EDOM); + + if (size > priv->tp_max_packet_size) + return ERR_PTR(-EMSGSIZE); + + if (size <= 8) + skcb->addr.type = J1939_SIMPLE; + else if (size > J1939_MAX_TP_PACKET_SIZE) + skcb->addr.type = J1939_ETP; + else + skcb->addr.type = J1939_TP; + + if (skcb->addr.type == J1939_ETP && + j1939_cb_is_broadcast(skcb)) + return ERR_PTR(-EDESTADDRREQ); + + /* fill in addresses from names */ + ret = j1939_ac_fixup(priv, skb); + if (unlikely(ret)) + return ERR_PTR(ret); + + /* fix DST flags, it may be used there soon */ + if (j1939_address_is_unicast(skcb->addr.da) && + priv->ents[skcb->addr.da].nusers) + skcb->flags |= J1939_ECU_LOCAL_DST; + + /* src is always local, I'm sending ... */ + skcb->flags |= J1939_ECU_LOCAL_SRC; + + /* prepare new session */ + session = j1939_session_new(priv, skb, size); + if (!session) + return ERR_PTR(-ENOMEM); + + /* skb is recounted in j1939_session_new() */ + session->sk = skb->sk; + session->transmission = true; + session->pkt.total = (size + 6) / 7; + session->pkt.block = skcb->addr.type == J1939_ETP ? 255 : + min(j1939_tp_block ?: 255, session->pkt.total); + + if (j1939_cb_is_broadcast(&session->skcb)) + /* set the end-packet for broadcast */ + session->pkt.last = session->pkt.total; + + skcb->tskey = session->sk->sk_tskey++; + session->tskey = skcb->tskey; + + return session; +} + +static void j1939_tp_cmd_recv(struct j1939_priv *priv, struct sk_buff *skb) +{ + struct j1939_sk_buff_cb *skcb = j1939_skb_to_cb(skb); + int extd = J1939_TP; + u8 cmd = skb->data[0]; + + switch (cmd) { + case J1939_ETP_CMD_RTS: + extd = J1939_ETP; + /* fall through */ + case J1939_TP_CMD_BAM: /* fall through */ + case J1939_TP_CMD_RTS: /* fall through */ + if (skcb->addr.type != extd) + return; + + if (cmd == J1939_TP_CMD_RTS && j1939_cb_is_broadcast(skcb)) { + netdev_alert(priv->ndev, "%s: rts without destination (%02x)\n", + __func__, skcb->addr.sa); + return; + } + + if (j1939_tp_im_transmitter(skcb)) + j1939_xtp_rx_rts(priv, skb, true); + + if (j1939_tp_im_receiver(skcb)) + j1939_xtp_rx_rts(priv, skb, false); + + break; + + case J1939_ETP_CMD_CTS: + extd = J1939_ETP; + /* fall through */ + case J1939_TP_CMD_CTS: + if (skcb->addr.type != extd) + return; + + if (j1939_tp_im_transmitter(skcb)) + j1939_xtp_rx_cts(priv, skb, false); + + if (j1939_tp_im_receiver(skcb)) + j1939_xtp_rx_cts(priv, skb, true); + + break; + + case J1939_ETP_CMD_DPO: + if (skcb->addr.type != J1939_ETP) + return; + + if (j1939_tp_im_transmitter(skcb)) + j1939_xtp_rx_dpo(priv, skb, true); + + if (j1939_tp_im_receiver(skcb)) + j1939_xtp_rx_dpo(priv, skb, false); + + break; + + case J1939_ETP_CMD_EOMA: + extd = J1939_ETP; + /* fall through */ + case J1939_TP_CMD_EOMA: + if (skcb->addr.type != extd) + return; + + if (j1939_tp_im_transmitter(skcb)) + j1939_xtp_rx_eoma(priv, skb, false); + + if (j1939_tp_im_receiver(skcb)) + j1939_xtp_rx_eoma(priv, skb, true); + + break; + + case J1939_ETP_CMD_ABORT: /* && J1939_TP_CMD_ABORT */ + if (j1939_tp_im_transmitter(skcb)) + j1939_xtp_rx_abort(priv, skb, true); + + if (j1939_tp_im_receiver(skcb)) + j1939_xtp_rx_abort(priv, skb, false); + + break; + default: + return; + } +} + +int j1939_tp_recv(struct j1939_priv *priv, struct sk_buff *skb) +{ + struct j1939_sk_buff_cb *skcb = j1939_skb_to_cb(skb); + + if (!j1939_tp_im_involved_anydir(skcb)) + return 0; + + switch (skcb->addr.pgn) { + case J1939_ETP_PGN_DAT: + skcb->addr.type = J1939_ETP; + /* fall through */ + case J1939_TP_PGN_DAT: + j1939_xtp_rx_dat(priv, skb); + break; + + case J1939_ETP_PGN_CTL: + skcb->addr.type = J1939_ETP; + /* fall through */ + case J1939_TP_PGN_CTL: + if (skb->len < 8) + return 0; /* Don't care. Nothing to extract here */ + + j1939_tp_cmd_recv(priv, skb); + break; + default: + return 0; /* no problem */ + } + return 1; /* "I processed the message" */ +} + +void j1939_simple_recv(struct j1939_priv *priv, struct sk_buff *skb) +{ + struct j1939_session *session; + + if (!skb->sk) + return; + + j1939_session_list_lock(priv); + session = j1939_session_get_simple(priv, skb); + j1939_session_list_unlock(priv); + if (!session) { + netdev_warn(priv->ndev, + "%s: Received already invalidated message\n", + __func__); + return; + } + + j1939_session_timers_cancel(session); + j1939_session_deactivate(session); + j1939_session_put(session); +} + +int j1939_cancel_active_session(struct j1939_priv *priv, struct sock *sk) +{ + struct j1939_session *session, *saved; + + netdev_dbg(priv->ndev, "%s, sk: %p\n", __func__, sk); + j1939_session_list_lock(priv); + list_for_each_entry_safe(session, saved, + &priv->active_session_list, + active_session_list_entry) { + if (!sk || sk == session->sk) { + j1939_session_timers_cancel(session); + session->err = ESHUTDOWN; + j1939_session_deactivate_locked(session); + } + } + j1939_session_list_unlock(priv); + return NOTIFY_DONE; +} + +void j1939_tp_init(struct j1939_priv *priv) +{ + spin_lock_init(&priv->active_session_list_lock); + INIT_LIST_HEAD(&priv->active_session_list); + priv->tp_max_packet_size = J1939_MAX_ETP_PACKET_SIZE; +} -- cgit v1.2.3 From 36b1a2fcd0d263cec3d1a896386611195329af84 Mon Sep 17 00:00:00 2001 From: Harini Katakam Date: Wed, 4 Sep 2019 19:30:20 +0530 Subject: include: mdio: Add driver data helpers Add set/get drv_data helpers for mdio device. Signed-off-by: Harini Katakam Reviewed-by: Andrew Lunn Reviewed-by: Florian Fainelli Signed-off-by: David S. Miller --- include/linux/mdio.h | 11 +++++++++++ 1 file changed, 11 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mdio.h b/include/linux/mdio.h index e8242ad88c81..a7604248777b 100644 --- a/include/linux/mdio.h +++ b/include/linux/mdio.h @@ -68,6 +68,17 @@ struct mdio_driver { #define to_mdio_driver(d) \ container_of(to_mdio_common_driver(d), struct mdio_driver, mdiodrv) +/* device driver data */ +static inline void mdiodev_set_drvdata(struct mdio_device *mdio, void *data) +{ + dev_set_drvdata(&mdio->dev, data); +} + +static inline void *mdiodev_get_drvdata(struct mdio_device *mdio) +{ + return dev_get_drvdata(&mdio->dev); +} + void mdio_device_free(struct mdio_device *mdiodev); struct mdio_device *mdio_device_create(struct mii_bus *bus, int addr); int mdio_device_register(struct mdio_device *mdiodev); -- cgit v1.2.3 From 948d3f90e9e2f385556f9ebbf792713e5b497b7a Mon Sep 17 00:00:00 2001 From: Aya Levin Date: Sun, 1 Sep 2019 14:10:35 +0300 Subject: net/mlx5: Expose HW capability bits for port buffer per priority congestion counters Map capability bit indicating that HCA supports port buffer's congestion counters. Also map registers with the corresponding counters. Signed-off-by: Aya Levin Reviewed-by: Moshe Shemesh Signed-off-by: Saeed Mahameed --- include/linux/mlx5/device.h | 1 + include/linux/mlx5/mlx5_ifc.h | 29 ++++++++++++++++++++++++----- 2 files changed, 25 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mlx5/device.h b/include/linux/mlx5/device.h index 8dd081051a79..f3773e8536bb 100644 --- a/include/linux/mlx5/device.h +++ b/include/linux/mlx5/device.h @@ -1316,6 +1316,7 @@ enum { MLX5_PER_PRIORITY_COUNTERS_GROUP = 0x10, MLX5_PER_TRAFFIC_CLASS_COUNTERS_GROUP = 0x11, MLX5_PHYSICAL_LAYER_COUNTERS_GROUP = 0x12, + MLX5_PER_TRAFFIC_CLASS_CONGESTION_GROUP = 0x13, MLX5_PHYSICAL_LAYER_STATISTICAL_GROUP = 0x16, MLX5_INFINIBAND_PORT_COUNTERS_GROUP = 0x20, }; diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h index 7d65c0578ac9..a487b681b516 100644 --- a/include/linux/mlx5/mlx5_ifc.h +++ b/include/linux/mlx5/mlx5_ifc.h @@ -1196,7 +1196,8 @@ struct mlx5_ifc_cmd_hca_cap_bits { u8 rts2rts_qp_counters_set_id[0x1]; u8 reserved_at_16a[0x2]; u8 vnic_env_int_rq_oob[0x1]; - u8 reserved_at_16d[0x2]; + u8 sbcam_reg[0x1]; + u8 reserved_at_16e[0x1]; u8 qcam_reg[0x1]; u8 gid_table_size[0x10]; @@ -1960,12 +1961,28 @@ struct mlx5_ifc_ib_port_cntrs_grp_data_layout_bits { u8 port_xmit_wait[0x20]; }; -struct mlx5_ifc_eth_per_traffic_grp_data_layout_bits { +struct mlx5_ifc_eth_per_tc_prio_grp_data_layout_bits { u8 transmit_queue_high[0x20]; u8 transmit_queue_low[0x20]; - u8 reserved_at_40[0x780]; + u8 no_buffer_discard_uc_high[0x20]; + + u8 no_buffer_discard_uc_low[0x20]; + + u8 reserved_at_80[0x740]; +}; + +struct mlx5_ifc_eth_per_tc_congest_prio_grp_data_layout_bits { + u8 wred_discard_high[0x20]; + + u8 wred_discard_low[0x20]; + + u8 ecn_marked_tc_high[0x20]; + + u8 ecn_marked_tc_low[0x20]; + + u8 reserved_at_80[0x740]; }; struct mlx5_ifc_eth_per_prio_grp_data_layout_bits { @@ -3642,7 +3659,8 @@ union mlx5_ifc_eth_cntrs_grp_data_layout_auto_bits { struct mlx5_ifc_eth_3635_cntrs_grp_data_layout_bits eth_3635_cntrs_grp_data_layout; struct mlx5_ifc_eth_extended_cntrs_grp_data_layout_bits eth_extended_cntrs_grp_data_layout; struct mlx5_ifc_eth_per_prio_grp_data_layout_bits eth_per_prio_grp_data_layout; - struct mlx5_ifc_eth_per_traffic_grp_data_layout_bits eth_per_traffic_grp_data_layout; + struct mlx5_ifc_eth_per_tc_prio_grp_data_layout_bits eth_per_tc_prio_grp_data_layout; + struct mlx5_ifc_eth_per_tc_congest_prio_grp_data_layout_bits eth_per_tc_congest_prio_grp_data_layout; struct mlx5_ifc_ib_port_cntrs_grp_data_layout_bits ib_port_cntrs_grp_data_layout; struct mlx5_ifc_phys_layer_cntrs_bits phys_layer_cntrs; struct mlx5_ifc_phys_layer_statistical_cntrs_bits phys_layer_statistical_cntrs; @@ -9422,7 +9440,8 @@ union mlx5_ifc_ports_control_registers_document_bits { struct mlx5_ifc_eth_802_3_cntrs_grp_data_layout_bits eth_802_3_cntrs_grp_data_layout; struct mlx5_ifc_eth_extended_cntrs_grp_data_layout_bits eth_extended_cntrs_grp_data_layout; struct mlx5_ifc_eth_per_prio_grp_data_layout_bits eth_per_prio_grp_data_layout; - struct mlx5_ifc_eth_per_traffic_grp_data_layout_bits eth_per_traffic_grp_data_layout; + struct mlx5_ifc_eth_per_tc_prio_grp_data_layout_bits eth_per_tc_prio_grp_data_layout; + struct mlx5_ifc_eth_per_tc_congest_prio_grp_data_layout_bits eth_per_tc_congest_prio_grp_data_layout; struct mlx5_ifc_lane_2_module_mapping_bits lane_2_module_mapping; struct mlx5_ifc_pamp_reg_bits pamp_reg; struct mlx5_ifc_paos_reg_bits paos_reg; -- cgit v1.2.3 From 95a7233c452a58a4c2310c456c73997853b2ec46 Mon Sep 17 00:00:00 2001 From: Paul Blakey Date: Wed, 4 Sep 2019 16:56:37 +0300 Subject: net: openvswitch: Set OvS recirc_id from tc chain index Offloaded OvS datapath rules are translated one to one to tc rules, for example the following simplified OvS rule: recirc_id(0),in_port(dev1),eth_type(0x0800),ct_state(-trk) actions:ct(),recirc(2) Will be translated to the following tc rule: $ tc filter add dev dev1 ingress \ prio 1 chain 0 proto ip \ flower tcp ct_state -trk \ action ct pipe \ action goto chain 2 Received packets will first travel though tc, and if they aren't stolen by it, like in the above rule, they will continue to OvS datapath. Since we already did some actions (action ct in this case) which might modify the packets, and updated action stats, we would like to continue the proccessing with the correct recirc_id in OvS (here recirc_id(2)) where we left off. To support this, introduce a new skb extension for tc, which will be used for translating tc chain to ovs recirc_id to handle these miss cases. Last tc chain index will be set by tc goto chain action and read by OvS datapath. Signed-off-by: Paul Blakey Signed-off-by: Vlad Buslov Acked-by: Jiri Pirko Acked-by: Pravin B Shelar Signed-off-by: David S. Miller --- include/linux/skbuff.h | 13 +++++++++++++ include/uapi/linux/openvswitch.h | 3 +++ net/core/skbuff.c | 6 ++++++ net/openvswitch/datapath.c | 38 +++++++++++++++++++++++++++++++++----- net/openvswitch/datapath.h | 2 ++ net/openvswitch/flow.c | 13 +++++++++++++ net/sched/Kconfig | 13 +++++++++++++ net/sched/cls_api.c | 12 ++++++++++++ 8 files changed, 95 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 77c6dc88e95d..028e684fa974 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -279,6 +279,16 @@ struct nf_bridge_info { }; #endif +#if IS_ENABLED(CONFIG_NET_TC_SKB_EXT) +/* Chain in tc_skb_ext will be used to share the tc chain with + * ovs recirc_id. It will be set to the current chain by tc + * and read by ovs to recirc_id. + */ +struct tc_skb_ext { + __u32 chain; +}; +#endif + struct sk_buff_head { /* These two members must be first. */ struct sk_buff *next; @@ -4057,6 +4067,9 @@ enum skb_ext_id { #endif #ifdef CONFIG_XFRM SKB_EXT_SEC_PATH, +#endif +#if IS_ENABLED(CONFIG_NET_TC_SKB_EXT) + TC_SKB_EXT, #endif SKB_EXT_NUM, /* must be last */ }; diff --git a/include/uapi/linux/openvswitch.h b/include/uapi/linux/openvswitch.h index f271f1ec50ae..1887a451c388 100644 --- a/include/uapi/linux/openvswitch.h +++ b/include/uapi/linux/openvswitch.h @@ -123,6 +123,9 @@ struct ovs_vport_stats { /* Allow datapath to associate multiple Netlink PIDs to each vport */ #define OVS_DP_F_VPORT_PIDS (1 << 1) +/* Allow tc offload recirc sharing */ +#define OVS_DP_F_TC_RECIRC_SHARING (1 << 2) + /* Fixed logical ports. */ #define OVSP_LOCAL ((__u32)0) diff --git a/net/core/skbuff.c b/net/core/skbuff.c index ea8e8d332d85..2b40b5a9425b 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -4087,6 +4087,9 @@ static const u8 skb_ext_type_len[] = { #ifdef CONFIG_XFRM [SKB_EXT_SEC_PATH] = SKB_EXT_CHUNKSIZEOF(struct sec_path), #endif +#if IS_ENABLED(CONFIG_NET_TC_SKB_EXT) + [TC_SKB_EXT] = SKB_EXT_CHUNKSIZEOF(struct tc_skb_ext), +#endif }; static __always_inline unsigned int skb_ext_total_length(void) @@ -4097,6 +4100,9 @@ static __always_inline unsigned int skb_ext_total_length(void) #endif #ifdef CONFIG_XFRM skb_ext_type_len[SKB_EXT_SEC_PATH] + +#endif +#if IS_ENABLED(CONFIG_NET_TC_SKB_EXT) + skb_ext_type_len[TC_SKB_EXT] + #endif 0; } diff --git a/net/openvswitch/datapath.c b/net/openvswitch/datapath.c index 65122bbccd27..dde9d762edee 100644 --- a/net/openvswitch/datapath.c +++ b/net/openvswitch/datapath.c @@ -1545,10 +1545,34 @@ static void ovs_dp_reset_user_features(struct sk_buff *skb, struct genl_info *in dp->user_features = 0; } -static void ovs_dp_change(struct datapath *dp, struct nlattr *a[]) +DEFINE_STATIC_KEY_FALSE(tc_recirc_sharing_support); + +static int ovs_dp_change(struct datapath *dp, struct nlattr *a[]) { - if (a[OVS_DP_ATTR_USER_FEATURES]) - dp->user_features = nla_get_u32(a[OVS_DP_ATTR_USER_FEATURES]); + u32 user_features = 0; + + if (a[OVS_DP_ATTR_USER_FEATURES]) { + user_features = nla_get_u32(a[OVS_DP_ATTR_USER_FEATURES]); + + if (user_features & ~(OVS_DP_F_VPORT_PIDS | + OVS_DP_F_UNALIGNED | + OVS_DP_F_TC_RECIRC_SHARING)) + return -EOPNOTSUPP; + +#if !IS_ENABLED(CONFIG_NET_TC_SKB_EXT) + if (user_features & OVS_DP_F_TC_RECIRC_SHARING) + return -EOPNOTSUPP; +#endif + } + + dp->user_features = user_features; + + if (dp->user_features & OVS_DP_F_TC_RECIRC_SHARING) + static_branch_enable(&tc_recirc_sharing_support); + else + static_branch_disable(&tc_recirc_sharing_support); + + return 0; } static int ovs_dp_cmd_new(struct sk_buff *skb, struct genl_info *info) @@ -1610,7 +1634,9 @@ static int ovs_dp_cmd_new(struct sk_buff *skb, struct genl_info *info) parms.port_no = OVSP_LOCAL; parms.upcall_portids = a[OVS_DP_ATTR_UPCALL_PID]; - ovs_dp_change(dp, a); + err = ovs_dp_change(dp, a); + if (err) + goto err_destroy_meters; /* So far only local changes have been made, now need the lock. */ ovs_lock(); @@ -1736,7 +1762,9 @@ static int ovs_dp_cmd_set(struct sk_buff *skb, struct genl_info *info) if (IS_ERR(dp)) goto err_unlock_free; - ovs_dp_change(dp, info->attrs); + err = ovs_dp_change(dp, info->attrs); + if (err) + goto err_unlock_free; err = ovs_dp_cmd_fill_info(dp, reply, info->snd_portid, info->snd_seq, 0, OVS_DP_CMD_SET); diff --git a/net/openvswitch/datapath.h b/net/openvswitch/datapath.h index 751d34accdf9..81e85dde8217 100644 --- a/net/openvswitch/datapath.h +++ b/net/openvswitch/datapath.h @@ -218,6 +218,8 @@ static inline struct datapath *get_dp(struct net *net, int dp_ifindex) extern struct notifier_block ovs_dp_device_notifier; extern struct genl_family dp_vport_genl_family; +DECLARE_STATIC_KEY_FALSE(tc_recirc_sharing_support); + void ovs_dp_process_packet(struct sk_buff *skb, struct sw_flow_key *key); void ovs_dp_detach_port(struct vport *); int ovs_dp_upcall(struct datapath *, struct sk_buff *, diff --git a/net/openvswitch/flow.c b/net/openvswitch/flow.c index 9d81d2c7bf82..38147e6a20f5 100644 --- a/net/openvswitch/flow.c +++ b/net/openvswitch/flow.c @@ -842,6 +842,9 @@ static int key_extract_mac_proto(struct sk_buff *skb) int ovs_flow_key_extract(const struct ip_tunnel_info *tun_info, struct sk_buff *skb, struct sw_flow_key *key) { +#if IS_ENABLED(CONFIG_NET_TC_SKB_EXT) + struct tc_skb_ext *tc_ext; +#endif int res, err; /* Extract metadata from packet. */ @@ -874,7 +877,17 @@ int ovs_flow_key_extract(const struct ip_tunnel_info *tun_info, if (res < 0) return res; key->mac_proto = res; + +#if IS_ENABLED(CONFIG_NET_TC_SKB_EXT) + if (static_branch_unlikely(&tc_recirc_sharing_support)) { + tc_ext = skb_ext_find(skb, TC_SKB_EXT); + key->recirc_id = tc_ext ? tc_ext->chain : 0; + } else { + key->recirc_id = 0; + } +#else key->recirc_id = 0; +#endif err = key_extract(skb, key); if (!err) diff --git a/net/sched/Kconfig b/net/sched/Kconfig index afd2ba157a13..b3faafeafab9 100644 --- a/net/sched/Kconfig +++ b/net/sched/Kconfig @@ -963,6 +963,19 @@ config NET_IFE_SKBTCINDEX tristate "Support to encoding decoding skb tcindex on IFE action" depends on NET_ACT_IFE +config NET_TC_SKB_EXT + bool "TC recirculation support" + depends on NET_CLS_ACT + default y if NET_CLS_ACT + select SKB_EXTENSIONS + + help + Say Y here to allow tc chain misses to continue in OvS datapath in + the correct recirc_id, and hardware chain misses to continue in + the correct chain in tc software datapath. + + Say N here if you won't be using tc<->ovs offload or tc chains offload. + endif # NET_SCHED config NET_SCH_FIFO diff --git a/net/sched/cls_api.c b/net/sched/cls_api.c index 671ca905dbb5..05c4fe1c3ca2 100644 --- a/net/sched/cls_api.c +++ b/net/sched/cls_api.c @@ -1514,6 +1514,18 @@ reclassify: goto reset; } else if (unlikely(TC_ACT_EXT_CMP(err, TC_ACT_GOTO_CHAIN))) { first_tp = res->goto_tp; + +#if IS_ENABLED(CONFIG_NET_TC_SKB_EXT) + { + struct tc_skb_ext *ext; + + ext = skb_ext_add(skb, TC_SKB_EXT); + if (WARN_ON_ONCE(!ext)) + return TC_ACT_SHOT; + + ext->chain = err & TC_ACT_EXT_VAL_MASK; + } +#endif goto reset; } #endif -- cgit v1.2.3 From 9e54ba7c3752f27456ca691acc3f154e2597478c Mon Sep 17 00:00:00 2001 From: Sudarsana Reddy Kalluru Date: Wed, 11 Sep 2019 04:42:50 -0700 Subject: qed*: Fix size of config attribute dump. Driver currently returns max-buf-size as size of the config attribute. This patch incorporates changes to read this value from MFW (if available) and provide it to the user. Also did a trivial clean up in this path. Fixes: d44a3ced7023 ("qede: Add support for reading the config id attributes.") Signed-off-by: Sudarsana Reddy Kalluru Signed-off-by: Ariel Elior Signed-off-by: David S. Miller --- drivers/net/ethernet/qlogic/qed/qed_main.c | 26 +++++++++++++++++++++++++ drivers/net/ethernet/qlogic/qede/qede_ethtool.c | 14 +++++++------ include/linux/qed/qed_if.h | 8 ++++++++ 3 files changed, 42 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/drivers/net/ethernet/qlogic/qed/qed_main.c b/drivers/net/ethernet/qlogic/qed/qed_main.c index ac1511a834d8..38c0ec3841e0 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_main.c +++ b/drivers/net/ethernet/qlogic/qed/qed_main.c @@ -2300,6 +2300,31 @@ static int qed_nvm_flash_cfg_write(struct qed_dev *cdev, const u8 **data) return rc; } +#define QED_MAX_NVM_BUF_LEN 32 +static int qed_nvm_flash_cfg_len(struct qed_dev *cdev, u32 cmd) +{ + struct qed_hwfn *hwfn = QED_LEADING_HWFN(cdev); + u8 buf[QED_MAX_NVM_BUF_LEN]; + struct qed_ptt *ptt; + u32 len; + int rc; + + ptt = qed_ptt_acquire(hwfn); + if (!ptt) + return QED_MAX_NVM_BUF_LEN; + + rc = qed_mcp_nvm_get_cfg(hwfn, ptt, cmd, 0, QED_NVM_CFG_GET_FLAGS, buf, + &len); + if (rc || !len) { + DP_ERR(cdev, "Error %d reading %d\n", rc, cmd); + len = QED_MAX_NVM_BUF_LEN; + } + + qed_ptt_release(hwfn, ptt); + + return len; +} + static int qed_nvm_flash_cfg_read(struct qed_dev *cdev, u8 **data, u32 cmd, u32 entity_id) { @@ -2657,6 +2682,7 @@ const struct qed_common_ops qed_common_ops_pass = { .read_module_eeprom = &qed_read_module_eeprom, .get_affin_hwfn_idx = &qed_get_affin_hwfn_idx, .read_nvm_cfg = &qed_nvm_flash_cfg_read, + .read_nvm_cfg_len = &qed_nvm_flash_cfg_len, .set_grc_config = &qed_set_grc_config, }; diff --git a/drivers/net/ethernet/qlogic/qede/qede_ethtool.c b/drivers/net/ethernet/qlogic/qede/qede_ethtool.c index ec27a43230d7..8a426afb6a55 100644 --- a/drivers/net/ethernet/qlogic/qede/qede_ethtool.c +++ b/drivers/net/ethernet/qlogic/qede/qede_ethtool.c @@ -49,7 +49,6 @@ #define QEDE_SELFTEST_POLL_COUNT 100 #define QEDE_DUMP_VERSION 0x1 -#define QEDE_DUMP_NVM_BUF_LEN 32 #define QEDE_DUMP_NVM_ARG_COUNT 2 static const struct { @@ -2026,7 +2025,8 @@ static int qede_get_dump_flag(struct net_device *dev, switch (edev->dump_info.cmd) { case QEDE_DUMP_CMD_NVM_CFG: dump->flag = QEDE_DUMP_CMD_NVM_CFG; - dump->len = QEDE_DUMP_NVM_BUF_LEN; + dump->len = edev->ops->common->read_nvm_cfg_len(edev->cdev, + edev->dump_info.args[0]); break; case QEDE_DUMP_CMD_GRCDUMP: dump->flag = QEDE_DUMP_CMD_GRCDUMP; @@ -2051,9 +2051,8 @@ static int qede_get_dump_data(struct net_device *dev, if (!edev->ops || !edev->ops->common) { DP_ERR(edev, "Edev ops not populated\n"); - edev->dump_info.cmd = QEDE_DUMP_CMD_NONE; - edev->dump_info.num_args = 0; - return -EINVAL; + rc = -EINVAL; + goto err; } switch (edev->dump_info.cmd) { @@ -2062,7 +2061,8 @@ static int qede_get_dump_data(struct net_device *dev, DP_ERR(edev, "Arg count = %d required = %d\n", edev->dump_info.num_args, QEDE_DUMP_NVM_ARG_COUNT); - return -EINVAL; + rc = -EINVAL; + goto err; } rc = edev->ops->common->read_nvm_cfg(edev->cdev, (u8 **)&buf, edev->dump_info.args[0], @@ -2078,8 +2078,10 @@ static int qede_get_dump_data(struct net_device *dev, break; } +err: edev->dump_info.cmd = QEDE_DUMP_CMD_NONE; edev->dump_info.num_args = 0; + memset(edev->dump_info.args, 0, sizeof(edev->dump_info.args)); return rc; } diff --git a/include/linux/qed/qed_if.h b/include/linux/qed/qed_if.h index e35463860c84..b5db1ee96d78 100644 --- a/include/linux/qed/qed_if.h +++ b/include/linux/qed/qed_if.h @@ -1143,6 +1143,14 @@ struct qed_common_ops { */ int (*read_nvm_cfg)(struct qed_dev *cdev, u8 **buf, u32 cmd, u32 entity_id); +/** + * @brief read_nvm_cfg - Read NVM config attribute value. + * @param cdev + * @param cmd - NVM CFG command id + * + * @return config id length, 0 on error. + */ + int (*read_nvm_cfg_len)(struct qed_dev *cdev, u32 cmd); /** * @brief set_grc_config - Configure value for grc config id. -- cgit v1.2.3 From 0060c8783330ab60deb96f9d6bb7abfe4664765d Mon Sep 17 00:00:00 2001 From: Alexandru Ardelean Date: Fri, 6 Sep 2019 16:02:55 +0300 Subject: net: stmmac: implement support for passive mode converters via dt In-between the MAC & PHY there can be a mode converter, which converts one mode to another (e.g. GMII-to-RGMII). The converter, can be passive (i.e. no driver or OS/SW information required), so the MAC & PHY need to be configured differently. For the `stmmac` driver, this is implemented via a `mac-mode` property in the device-tree, which configures the MAC into a certain mode, and for the PHY a `phy_interface` field will hold the mode of the PHY. The mode of the PHY will be passed to the PHY and from there-on it work in a different mode. If unspecified, the default `phy-mode` will be used for both. Signed-off-by: Alexandru Ardelean Signed-off-by: David S. Miller --- drivers/net/ethernet/stmicro/stmmac/stmmac_main.c | 2 +- .../net/ethernet/stmicro/stmmac/stmmac_platform.c | 34 +++++++++++++++++++++- include/linux/stmmac.h | 1 + 3 files changed, 35 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c index 6e44013b20cc..c61d702fe83a 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c @@ -1036,7 +1036,7 @@ static int stmmac_init_phy(struct net_device *dev) static int stmmac_phy_setup(struct stmmac_priv *priv) { struct fwnode_handle *fwnode = of_fwnode_handle(priv->plat->phylink_node); - int mode = priv->plat->interface; + int mode = priv->plat->phy_interface; struct phylink *phylink; priv->phylink_config.dev = &priv->dev->dev; diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c index 5de754a9fae9..170c3a052b14 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c @@ -358,6 +358,32 @@ static int stmmac_dt_phy(struct plat_stmmacenet_data *plat, return 0; } +/** + * stmmac_of_get_mac_mode - retrieves the interface of the MAC + * @np - device-tree node + * Description: + * Similar to `of_get_phy_mode()`, this function will retrieve (from + * the device-tree) the interface mode on the MAC side. This assumes + * that there is mode converter in-between the MAC & PHY + * (e.g. GMII-to-RGMII). + */ +static int stmmac_of_get_mac_mode(struct device_node *np) +{ + const char *pm; + int err, i; + + err = of_property_read_string(np, "mac-mode", &pm); + if (err < 0) + return err; + + for (i = 0; i < PHY_INTERFACE_MODE_MAX; i++) { + if (!strcasecmp(pm, phy_modes(i))) + return i; + } + + return -ENODEV; +} + /** * stmmac_probe_config_dt - parse device-tree driver parameters * @pdev: platform_device structure @@ -386,7 +412,13 @@ stmmac_probe_config_dt(struct platform_device *pdev, const char **mac) *mac = NULL; } - plat->interface = of_get_phy_mode(np); + plat->phy_interface = of_get_phy_mode(np); + if (plat->phy_interface < 0) + return ERR_PTR(plat->phy_interface); + + plat->interface = stmmac_of_get_mac_mode(np); + if (plat->interface < 0) + plat->interface = plat->phy_interface; /* Some wrapper drivers still rely on phy_node. Let's save it while * they are not converted to phylink. */ diff --git a/include/linux/stmmac.h b/include/linux/stmmac.h index 7ad7ae35cf88..dc60d03c4b60 100644 --- a/include/linux/stmmac.h +++ b/include/linux/stmmac.h @@ -131,6 +131,7 @@ struct plat_stmmacenet_data { int bus_id; int phy_addr; int interface; + int phy_interface; struct stmmac_mdio_bus_data *mdio_bus_data; struct device_node *phy_node; struct device_node *phylink_node; -- cgit v1.2.3 From b0edba2af7154c82c28a4828f483c102ab201326 Mon Sep 17 00:00:00 2001 From: Jeremy Sowden Date: Fri, 13 Sep 2019 09:13:02 +0100 Subject: netfilter: fix coding-style errors. Several header-files, Kconfig files and Makefiles have trailing white-space. Remove it. In netfilter/Kconfig, indent the type of CONFIG_NETFILTER_NETLINK_ACCT correctly. There are semicolons at the end of two function definitions in include/net/netfilter/nf_conntrack_acct.h and include/net/netfilter/nf_conntrack_ecache.h. Remove them. Fix indentation in nf_conntrack_l4proto.h. Signed-off-by: Jeremy Sowden Signed-off-by: Pablo Neira Ayuso --- include/linux/netfilter/x_tables.h | 2 +- include/linux/netfilter_ipv6.h | 2 +- include/net/netfilter/nf_conntrack_acct.h | 2 +- include/net/netfilter/nf_conntrack_ecache.h | 2 +- include/net/netfilter/nf_conntrack_expect.h | 2 +- include/net/netfilter/nf_conntrack_l4proto.h | 14 +++++++------- include/net/netfilter/nf_conntrack_tuple.h | 2 +- net/ipv4/netfilter/Kconfig | 8 ++++---- net/ipv4/netfilter/Makefile | 2 +- net/netfilter/Kconfig | 8 ++++---- net/netfilter/Makefile | 2 +- 11 files changed, 23 insertions(+), 23 deletions(-) (limited to 'include/linux') diff --git a/include/linux/netfilter/x_tables.h b/include/linux/netfilter/x_tables.h index ae62bf1c6824..b9bc25f57c8e 100644 --- a/include/linux/netfilter/x_tables.h +++ b/include/linux/netfilter/x_tables.h @@ -340,7 +340,7 @@ void xt_free_table_info(struct xt_table_info *info); /** * xt_recseq - recursive seqcount for netfilter use - * + * * Packet processing changes the seqcount only if no recursion happened * get_counters() can use read_seqcount_begin()/read_seqcount_retry(), * because we use the normal seqcount convention : diff --git a/include/linux/netfilter_ipv6.h b/include/linux/netfilter_ipv6.h index 7beb681e1ce5..a889e376d197 100644 --- a/include/linux/netfilter_ipv6.h +++ b/include/linux/netfilter_ipv6.h @@ -1,7 +1,7 @@ /* IPv6-specific defines for netfilter. * (C)1998 Rusty Russell -- This code is GPL. * (C)1999 David Jeffery - * this header was blatantly ripped from netfilter_ipv4.h + * this header was blatantly ripped from netfilter_ipv4.h * it's amazing what adding a bunch of 6s can do =8^) */ #ifndef __LINUX_IP6_NETFILTER_H diff --git a/include/net/netfilter/nf_conntrack_acct.h b/include/net/netfilter/nf_conntrack_acct.h index ad9f2172dee1..5b5287bb49db 100644 --- a/include/net/netfilter/nf_conntrack_acct.h +++ b/include/net/netfilter/nf_conntrack_acct.h @@ -45,7 +45,7 @@ struct nf_conn_acct *nf_ct_acct_ext_add(struct nf_conn *ct, gfp_t gfp) #else return NULL; #endif -}; +} /* Check if connection tracking accounting is enabled */ static inline bool nf_ct_acct_enabled(struct net *net) diff --git a/include/net/netfilter/nf_conntrack_ecache.h b/include/net/netfilter/nf_conntrack_ecache.h index 52b44192b43f..0815bfadfefe 100644 --- a/include/net/netfilter/nf_conntrack_ecache.h +++ b/include/net/netfilter/nf_conntrack_ecache.h @@ -61,7 +61,7 @@ nf_ct_ecache_ext_add(struct nf_conn *ct, u16 ctmask, u16 expmask, gfp_t gfp) #else return NULL; #endif -}; +} #ifdef CONFIG_NF_CONNTRACK_EVENTS /* This structure is passed to event handler */ diff --git a/include/net/netfilter/nf_conntrack_expect.h b/include/net/netfilter/nf_conntrack_expect.h index 573429be4d59..0855b60fba17 100644 --- a/include/net/netfilter/nf_conntrack_expect.h +++ b/include/net/netfilter/nf_conntrack_expect.h @@ -126,7 +126,7 @@ void nf_ct_expect_init(struct nf_conntrack_expect *, unsigned int, u_int8_t, const union nf_inet_addr *, u_int8_t, const __be16 *, const __be16 *); void nf_ct_expect_put(struct nf_conntrack_expect *exp); -int nf_ct_expect_related_report(struct nf_conntrack_expect *expect, +int nf_ct_expect_related_report(struct nf_conntrack_expect *expect, u32 portid, int report, unsigned int flags); static inline int nf_ct_expect_related(struct nf_conntrack_expect *expect, unsigned int flags) diff --git a/include/net/netfilter/nf_conntrack_l4proto.h b/include/net/netfilter/nf_conntrack_l4proto.h index c200b95d27ae..97240f1a3f5f 100644 --- a/include/net/netfilter/nf_conntrack_l4proto.h +++ b/include/net/netfilter/nf_conntrack_l4proto.h @@ -181,41 +181,41 @@ void nf_ct_l4proto_log_invalid(const struct sk_buff *skb, #if IS_ENABLED(CONFIG_NF_CONNTRACK) static inline struct nf_generic_net *nf_generic_pernet(struct net *net) { - return &net->ct.nf_ct_proto.generic; + return &net->ct.nf_ct_proto.generic; } static inline struct nf_tcp_net *nf_tcp_pernet(struct net *net) { - return &net->ct.nf_ct_proto.tcp; + return &net->ct.nf_ct_proto.tcp; } static inline struct nf_udp_net *nf_udp_pernet(struct net *net) { - return &net->ct.nf_ct_proto.udp; + return &net->ct.nf_ct_proto.udp; } static inline struct nf_icmp_net *nf_icmp_pernet(struct net *net) { - return &net->ct.nf_ct_proto.icmp; + return &net->ct.nf_ct_proto.icmp; } static inline struct nf_icmp_net *nf_icmpv6_pernet(struct net *net) { - return &net->ct.nf_ct_proto.icmpv6; + return &net->ct.nf_ct_proto.icmpv6; } #endif #ifdef CONFIG_NF_CT_PROTO_DCCP static inline struct nf_dccp_net *nf_dccp_pernet(struct net *net) { - return &net->ct.nf_ct_proto.dccp; + return &net->ct.nf_ct_proto.dccp; } #endif #ifdef CONFIG_NF_CT_PROTO_SCTP static inline struct nf_sctp_net *nf_sctp_pernet(struct net *net) { - return &net->ct.nf_ct_proto.sctp; + return &net->ct.nf_ct_proto.sctp; } #endif diff --git a/include/net/netfilter/nf_conntrack_tuple.h b/include/net/netfilter/nf_conntrack_tuple.h index 480c87b44a96..68ea9b932736 100644 --- a/include/net/netfilter/nf_conntrack_tuple.h +++ b/include/net/netfilter/nf_conntrack_tuple.h @@ -124,7 +124,7 @@ struct nf_conntrack_tuple_hash { #if IS_ENABLED(CONFIG_NETFILTER) static inline bool __nf_ct_tuple_src_equal(const struct nf_conntrack_tuple *t1, const struct nf_conntrack_tuple *t2) -{ +{ return (nf_inet_addr_cmp(&t1->src.u3, &t2->src.u3) && t1->src.u.all == t2->src.u.all && t1->src.l3num == t2->src.l3num); diff --git a/net/ipv4/netfilter/Kconfig b/net/ipv4/netfilter/Kconfig index 69e76d677f9e..f17b402111ce 100644 --- a/net/ipv4/netfilter/Kconfig +++ b/net/ipv4/netfilter/Kconfig @@ -272,7 +272,7 @@ config IP_NF_TARGET_CLUSTERIP The CLUSTERIP target allows you to build load-balancing clusters of network servers without having a dedicated load-balancing router/server/switch. - + To compile it as a module, choose M here. If unsure, say N. config IP_NF_TARGET_ECN @@ -281,7 +281,7 @@ config IP_NF_TARGET_ECN depends on NETFILTER_ADVANCED ---help--- This option adds a `ECN' target, which can be used in the iptables mangle - table. + table. You can use this target to remove the ECN bits from the IPv4 header of an IP packet. This is particularly useful, if you need to work around @@ -306,7 +306,7 @@ config IP_NF_RAW This option adds a `raw' table to iptables. This table is the very first in the netfilter framework and hooks in at the PREROUTING and OUTPUT chains. - + If you want to compile it as a module, say M here and read . If unsure, say `N'. @@ -318,7 +318,7 @@ config IP_NF_SECURITY help This option adds a `security' table to iptables, for use with Mandatory Access Control (MAC) policy. - + If unsure, say N. endif # IP_NF_IPTABLES diff --git a/net/ipv4/netfilter/Makefile b/net/ipv4/netfilter/Makefile index c50e0ec095d2..7c497c78105f 100644 --- a/net/ipv4/netfilter/Makefile +++ b/net/ipv4/netfilter/Makefile @@ -31,7 +31,7 @@ obj-$(CONFIG_NFT_DUP_IPV4) += nft_dup_ipv4.o # flow table support obj-$(CONFIG_NF_FLOW_TABLE_IPV4) += nf_flow_table_ipv4.o -# generic IP tables +# generic IP tables obj-$(CONFIG_IP_NF_IPTABLES) += ip_tables.o # the three instances of ip_tables diff --git a/net/netfilter/Kconfig b/net/netfilter/Kconfig index 0d65f4d39494..34ec7afec116 100644 --- a/net/netfilter/Kconfig +++ b/net/netfilter/Kconfig @@ -20,7 +20,7 @@ config NETFILTER_FAMILY_ARP bool config NETFILTER_NETLINK_ACCT -tristate "Netfilter NFACCT over NFNETLINK interface" + tristate "Netfilter NFACCT over NFNETLINK interface" depends on NETFILTER_ADVANCED select NETFILTER_NETLINK help @@ -34,7 +34,7 @@ config NETFILTER_NETLINK_QUEUE help If this option is enabled, the kernel will include support for queueing packets via NFNETLINK. - + config NETFILTER_NETLINK_LOG tristate "Netfilter LOG over NFNETLINK interface" default m if NETFILTER_ADVANCED=n @@ -1502,7 +1502,7 @@ config NETFILTER_XT_MATCH_REALM This option adds a `realm' match, which allows you to use the realm key from the routing subsystem inside iptables. - This match pretty much resembles the CONFIG_NET_CLS_ROUTE4 option + This match pretty much resembles the CONFIG_NET_CLS_ROUTE4 option in tc world. If you want to compile it as a module, say M here and read @@ -1523,7 +1523,7 @@ config NETFILTER_XT_MATCH_SCTP depends on NETFILTER_ADVANCED default IP_SCTP help - With this option enabled, you will be able to use the + With this option enabled, you will be able to use the `sctp' match in order to match on SCTP source/destination ports and SCTP chunk types. diff --git a/net/netfilter/Makefile b/net/netfilter/Makefile index 9270a7fae484..4fc075b612fe 100644 --- a/net/netfilter/Makefile +++ b/net/netfilter/Makefile @@ -124,7 +124,7 @@ nf_flow_table-objs := nf_flow_table_core.o nf_flow_table_ip.o obj-$(CONFIG_NF_FLOW_TABLE_INET) += nf_flow_table_inet.o -# generic X tables +# generic X tables obj-$(CONFIG_NETFILTER_XTABLES) += x_tables.o xt_tcpudp.o # combos -- cgit v1.2.3 From f5d65c197531e9abb7ede82b052459c1a3cf13c3 Mon Sep 17 00:00:00 2001 From: Jeremy Sowden Date: Fri, 13 Sep 2019 09:13:03 +0100 Subject: netfilter: ip_tables: remove unused function declarations. Two headers include declarations of functions which are never defined. Remove them. Signed-off-by: Jeremy Sowden Signed-off-by: Pablo Neira Ayuso --- include/linux/netfilter_ipv4/ip_tables.h | 2 -- include/linux/netfilter_ipv6/ip6_tables.h | 3 +-- 2 files changed, 1 insertion(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/netfilter_ipv4/ip_tables.h b/include/linux/netfilter_ipv4/ip_tables.h index f40a65481df4..0b0d43ad9ed9 100644 --- a/include/linux/netfilter_ipv4/ip_tables.h +++ b/include/linux/netfilter_ipv4/ip_tables.h @@ -23,8 +23,6 @@ #include #include -extern void ipt_init(void) __init; - #if IS_ENABLED(CONFIG_NETFILTER) int ipt_register_table(struct net *net, const struct xt_table *table, const struct ipt_replace *repl, diff --git a/include/linux/netfilter_ipv6/ip6_tables.h b/include/linux/netfilter_ipv6/ip6_tables.h index 53b7309613bf..666450c117bf 100644 --- a/include/linux/netfilter_ipv6/ip6_tables.h +++ b/include/linux/netfilter_ipv6/ip6_tables.h @@ -23,9 +23,8 @@ #include #include -extern void ip6t_init(void) __init; - extern void *ip6t_alloc_initial_table(const struct xt_table *); + #if IS_ENABLED(CONFIG_NETFILTER) int ip6t_register_table(struct net *net, const struct xt_table *table, const struct ip6t_replace *repl, -- cgit v1.2.3 From 85cfbc25e5c5ee83307aba05eec4b04517890038 Mon Sep 17 00:00:00 2001 From: Jeremy Sowden Date: Fri, 13 Sep 2019 09:13:04 +0100 Subject: netfilter: inline xt_hashlimit, ebt_802_3 and xt_physdev headers Three netfilter headers are only included once. Inline their contents at those sites and remove them. Signed-off-by: Jeremy Sowden Signed-off-by: Pablo Neira Ayuso --- include/linux/netfilter/xt_hashlimit.h | 11 ----------- include/linux/netfilter/xt_physdev.h | 8 -------- include/linux/netfilter_bridge/ebt_802_3.h | 12 ------------ net/bridge/netfilter/ebt_802_3.c | 8 +++++++- net/netfilter/xt_hashlimit.c | 7 ++++++- net/netfilter/xt_physdev.c | 5 +++-- 6 files changed, 16 insertions(+), 35 deletions(-) delete mode 100644 include/linux/netfilter/xt_hashlimit.h delete mode 100644 include/linux/netfilter/xt_physdev.h delete mode 100644 include/linux/netfilter_bridge/ebt_802_3.h (limited to 'include/linux') diff --git a/include/linux/netfilter/xt_hashlimit.h b/include/linux/netfilter/xt_hashlimit.h deleted file mode 100644 index 169d03983589..000000000000 --- a/include/linux/netfilter/xt_hashlimit.h +++ /dev/null @@ -1,11 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -#ifndef _XT_HASHLIMIT_H -#define _XT_HASHLIMIT_H - -#include - -#define XT_HASHLIMIT_ALL (XT_HASHLIMIT_HASH_DIP | XT_HASHLIMIT_HASH_DPT | \ - XT_HASHLIMIT_HASH_SIP | XT_HASHLIMIT_HASH_SPT | \ - XT_HASHLIMIT_INVERT | XT_HASHLIMIT_BYTES |\ - XT_HASHLIMIT_RATE_MATCH) -#endif /*_XT_HASHLIMIT_H*/ diff --git a/include/linux/netfilter/xt_physdev.h b/include/linux/netfilter/xt_physdev.h deleted file mode 100644 index 4ca0593949cd..000000000000 --- a/include/linux/netfilter/xt_physdev.h +++ /dev/null @@ -1,8 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -#ifndef _XT_PHYSDEV_H -#define _XT_PHYSDEV_H - -#include -#include - -#endif /*_XT_PHYSDEV_H*/ diff --git a/include/linux/netfilter_bridge/ebt_802_3.h b/include/linux/netfilter_bridge/ebt_802_3.h deleted file mode 100644 index c6147f9c0d80..000000000000 --- a/include/linux/netfilter_bridge/ebt_802_3.h +++ /dev/null @@ -1,12 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -#ifndef __LINUX_BRIDGE_EBT_802_3_H -#define __LINUX_BRIDGE_EBT_802_3_H - -#include -#include - -static inline struct ebt_802_3_hdr *ebt_802_3_hdr(const struct sk_buff *skb) -{ - return (struct ebt_802_3_hdr *)skb_mac_header(skb); -} -#endif diff --git a/net/bridge/netfilter/ebt_802_3.c b/net/bridge/netfilter/ebt_802_3.c index 2c8fe24400e5..68c2519bdc52 100644 --- a/net/bridge/netfilter/ebt_802_3.c +++ b/net/bridge/netfilter/ebt_802_3.c @@ -11,7 +11,13 @@ #include #include #include -#include +#include +#include + +static struct ebt_802_3_hdr *ebt_802_3_hdr(const struct sk_buff *skb) +{ + return (struct ebt_802_3_hdr *)skb_mac_header(skb); +} static bool ebt_802_3_mt(const struct sk_buff *skb, struct xt_action_param *par) diff --git a/net/netfilter/xt_hashlimit.c b/net/netfilter/xt_hashlimit.c index 2d2691dd51e0..ced3fc8fad7c 100644 --- a/net/netfilter/xt_hashlimit.c +++ b/net/netfilter/xt_hashlimit.c @@ -34,9 +34,14 @@ #include #include #include -#include #include #include +#include + +#define XT_HASHLIMIT_ALL (XT_HASHLIMIT_HASH_DIP | XT_HASHLIMIT_HASH_DPT | \ + XT_HASHLIMIT_HASH_SIP | XT_HASHLIMIT_HASH_SPT | \ + XT_HASHLIMIT_INVERT | XT_HASHLIMIT_BYTES |\ + XT_HASHLIMIT_RATE_MATCH) MODULE_LICENSE("GPL"); MODULE_AUTHOR("Harald Welte "); diff --git a/net/netfilter/xt_physdev.c b/net/netfilter/xt_physdev.c index b92b22ce8abd..ec6ed6fda96c 100644 --- a/net/netfilter/xt_physdev.c +++ b/net/netfilter/xt_physdev.c @@ -5,12 +5,13 @@ /* (C) 2001-2003 Bart De Schuymer */ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt + +#include #include #include #include -#include #include -#include +#include MODULE_LICENSE("GPL"); MODULE_AUTHOR("Bart De Schuymer "); -- cgit v1.2.3 From 44dde23698a7a8a807d974a5124cf64b7ab2c9d5 Mon Sep 17 00:00:00 2001 From: Jeremy Sowden Date: Fri, 13 Sep 2019 09:13:07 +0100 Subject: netfilter: move inline nf_ip6_ext_hdr() function to a more appropriate header. There is an inline function in ip6_tables.h which is not specific to ip6tables and is used elswhere in netfilter. Move it into netfilter_ipv6.h and update the callers. Signed-off-by: Jeremy Sowden Signed-off-by: Pablo Neira Ayuso --- include/linux/netfilter_ipv6.h | 12 ++++++++++++ include/linux/netfilter_ipv6/ip6_tables.h | 12 ------------ net/ipv6/netfilter/ip6t_ipv6header.c | 4 ++-- net/ipv6/netfilter/nf_log_ipv6.c | 4 ++-- 4 files changed, 16 insertions(+), 16 deletions(-) (limited to 'include/linux') diff --git a/include/linux/netfilter_ipv6.h b/include/linux/netfilter_ipv6.h index a889e376d197..c1500209cfaf 100644 --- a/include/linux/netfilter_ipv6.h +++ b/include/linux/netfilter_ipv6.h @@ -10,6 +10,18 @@ #include #include +/* Check for an extension */ +static inline int +nf_ip6_ext_hdr(u8 nexthdr) +{ return (nexthdr == IPPROTO_HOPOPTS) || + (nexthdr == IPPROTO_ROUTING) || + (nexthdr == IPPROTO_FRAGMENT) || + (nexthdr == IPPROTO_ESP) || + (nexthdr == IPPROTO_AH) || + (nexthdr == IPPROTO_NONE) || + (nexthdr == IPPROTO_DSTOPTS); +} + /* Extra routing may needed on local out, as the QUEUE target never returns * control to the table. */ diff --git a/include/linux/netfilter_ipv6/ip6_tables.h b/include/linux/netfilter_ipv6/ip6_tables.h index 666450c117bf..3a0a2bd054cc 100644 --- a/include/linux/netfilter_ipv6/ip6_tables.h +++ b/include/linux/netfilter_ipv6/ip6_tables.h @@ -36,18 +36,6 @@ extern unsigned int ip6t_do_table(struct sk_buff *skb, struct xt_table *table); #endif -/* Check for an extension */ -static inline int -ip6t_ext_hdr(u8 nexthdr) -{ return (nexthdr == IPPROTO_HOPOPTS) || - (nexthdr == IPPROTO_ROUTING) || - (nexthdr == IPPROTO_FRAGMENT) || - (nexthdr == IPPROTO_ESP) || - (nexthdr == IPPROTO_AH) || - (nexthdr == IPPROTO_NONE) || - (nexthdr == IPPROTO_DSTOPTS); -} - #ifdef CONFIG_COMPAT #include diff --git a/net/ipv6/netfilter/ip6t_ipv6header.c b/net/ipv6/netfilter/ip6t_ipv6header.c index 0fc6326ef499..c52ff929c93b 100644 --- a/net/ipv6/netfilter/ip6t_ipv6header.c +++ b/net/ipv6/netfilter/ip6t_ipv6header.c @@ -16,7 +16,7 @@ #include #include -#include +#include #include MODULE_LICENSE("GPL"); @@ -42,7 +42,7 @@ ipv6header_mt6(const struct sk_buff *skb, struct xt_action_param *par) len = skb->len - ptr; temp = 0; - while (ip6t_ext_hdr(nexthdr)) { + while (nf_ip6_ext_hdr(nexthdr)) { const struct ipv6_opt_hdr *hp; struct ipv6_opt_hdr _hdr; int hdrlen; diff --git a/net/ipv6/netfilter/nf_log_ipv6.c b/net/ipv6/netfilter/nf_log_ipv6.c index f53bd8f01219..22b80db6d882 100644 --- a/net/ipv6/netfilter/nf_log_ipv6.c +++ b/net/ipv6/netfilter/nf_log_ipv6.c @@ -18,7 +18,7 @@ #include #include -#include +#include #include #include @@ -70,7 +70,7 @@ static void dump_ipv6_packet(struct net *net, struct nf_log_buf *m, fragment = 0; ptr = ip6hoff + sizeof(struct ipv6hdr); currenthdr = ih->nexthdr; - while (currenthdr != NEXTHDR_NONE && ip6t_ext_hdr(currenthdr)) { + while (currenthdr != NEXTHDR_NONE && nf_ip6_ext_hdr(currenthdr)) { struct ipv6_opt_hdr _hdr; const struct ipv6_opt_hdr *hp; -- cgit v1.2.3 From 46705b070c279b352bbbe8118d78aa31b0768245 Mon Sep 17 00:00:00 2001 From: Jeremy Sowden Date: Fri, 13 Sep 2019 09:13:09 +0100 Subject: netfilter: move nf_bridge_frag_data struct definition to a more appropriate header. There is a struct definition function in nf_conntrack_bridge.h which is not specific to conntrack and is used elswhere in netfilter. Move it into netfilter_bridge.h. Signed-off-by: Jeremy Sowden Signed-off-by: Pablo Neira Ayuso --- include/linux/netfilter_bridge.h | 7 +++++++ include/linux/netfilter_ipv6.h | 14 +++++++------- include/net/netfilter/nf_conntrack_bridge.h | 7 ------- net/bridge/netfilter/nf_conntrack_bridge.c | 14 +++++++------- net/ipv6/netfilter.c | 4 ++-- 5 files changed, 23 insertions(+), 23 deletions(-) (limited to 'include/linux') diff --git a/include/linux/netfilter_bridge.h b/include/linux/netfilter_bridge.h index 5f2614d02e03..f980edfdd278 100644 --- a/include/linux/netfilter_bridge.h +++ b/include/linux/netfilter_bridge.h @@ -5,6 +5,13 @@ #include #include +struct nf_bridge_frag_data { + char mac[ETH_HLEN]; + bool vlan_present; + u16 vlan_tci; + __be16 vlan_proto; +}; + #if IS_ENABLED(CONFIG_BRIDGE_NETFILTER) int br_handle_frame_finish(struct net *net, struct sock *sk, struct sk_buff *skb); diff --git a/include/linux/netfilter_ipv6.h b/include/linux/netfilter_ipv6.h index c1500209cfaf..aac42c28fe62 100644 --- a/include/linux/netfilter_ipv6.h +++ b/include/linux/netfilter_ipv6.h @@ -32,7 +32,7 @@ struct ip6_rt_info { }; struct nf_queue_entry; -struct nf_ct_bridge_frag_data; +struct nf_bridge_frag_data; /* * Hook functions for ipv6 to allow xt_* modules to be built-in even @@ -61,9 +61,9 @@ struct nf_ipv6_ops { 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, + struct nf_bridge_frag_data *data, int (*output)(struct net *, struct sock *sk, - const struct nf_ct_bridge_frag_data *data, + const struct nf_bridge_frag_data *data, struct sk_buff *)); #endif }; @@ -135,16 +135,16 @@ static inline int nf_ipv6_br_defrag(struct net *net, struct sk_buff *skb, } int br_ip6_fragment(struct net *net, struct sock *sk, struct sk_buff *skb, - struct nf_ct_bridge_frag_data *data, + struct nf_bridge_frag_data *data, int (*output)(struct net *, struct sock *sk, - const struct nf_ct_bridge_frag_data *data, + const struct nf_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, + struct nf_bridge_frag_data *data, int (*output)(struct net *, struct sock *sk, - const struct nf_ct_bridge_frag_data *data, + const struct nf_bridge_frag_data *data, struct sk_buff *)) { #if IS_MODULE(CONFIG_IPV6) diff --git a/include/net/netfilter/nf_conntrack_bridge.h b/include/net/netfilter/nf_conntrack_bridge.h index 34c28f248b18..01b62fd5efa2 100644 --- a/include/net/netfilter/nf_conntrack_bridge.h +++ b/include/net/netfilter/nf_conntrack_bridge.h @@ -16,11 +16,4 @@ 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/net/bridge/netfilter/nf_conntrack_bridge.c b/net/bridge/netfilter/nf_conntrack_bridge.c index c9ce321fcac1..8842798c29e6 100644 --- a/net/bridge/netfilter/nf_conntrack_bridge.c +++ b/net/bridge/netfilter/nf_conntrack_bridge.c @@ -26,9 +26,9 @@ */ static int nf_br_ip_fragment(struct net *net, struct sock *sk, struct sk_buff *skb, - struct nf_ct_bridge_frag_data *data, + struct nf_bridge_frag_data *data, int (*output)(struct net *, struct sock *sk, - const struct nf_ct_bridge_frag_data *data, + const struct nf_bridge_frag_data *data, struct sk_buff *)) { int frag_max_size = BR_INPUT_SKB_CB(skb)->frag_max_size; @@ -278,7 +278,7 @@ static unsigned int nf_ct_bridge_pre(void *priv, struct sk_buff *skb, } static void nf_ct_bridge_frag_save(struct sk_buff *skb, - struct nf_ct_bridge_frag_data *data) + struct nf_bridge_frag_data *data) { if (skb_vlan_tag_present(skb)) { data->vlan_present = true; @@ -293,10 +293,10 @@ static void nf_ct_bridge_frag_save(struct sk_buff *skb, static unsigned int nf_ct_bridge_refrag(struct sk_buff *skb, const struct nf_hook_state *state, int (*output)(struct net *, struct sock *sk, - const struct nf_ct_bridge_frag_data *data, + const struct nf_bridge_frag_data *data, struct sk_buff *)) { - struct nf_ct_bridge_frag_data data; + struct nf_bridge_frag_data data; if (!BR_INPUT_SKB_CB(skb)->frag_max_size) return NF_ACCEPT; @@ -319,7 +319,7 @@ nf_ct_bridge_refrag(struct sk_buff *skb, const struct nf_hook_state *state, /* Actually only slow path refragmentation needs this. */ static int nf_ct_bridge_frag_restore(struct sk_buff *skb, - const struct nf_ct_bridge_frag_data *data) + const struct nf_bridge_frag_data *data) { int err; @@ -340,7 +340,7 @@ static int nf_ct_bridge_frag_restore(struct sk_buff *skb, } static int nf_ct_bridge_refrag_post(struct net *net, struct sock *sk, - const struct nf_ct_bridge_frag_data *data, + const struct nf_bridge_frag_data *data, struct sk_buff *skb) { int err; diff --git a/net/ipv6/netfilter.c b/net/ipv6/netfilter.c index 61819ed858b1..a9bff556d3b2 100644 --- a/net/ipv6/netfilter.c +++ b/net/ipv6/netfilter.c @@ -113,9 +113,9 @@ int __nf_ip6_route(struct net *net, struct dst_entry **dst, EXPORT_SYMBOL_GPL(__nf_ip6_route); int br_ip6_fragment(struct net *net, struct sock *sk, struct sk_buff *skb, - struct nf_ct_bridge_frag_data *data, + struct nf_bridge_frag_data *data, int (*output)(struct net *, struct sock *sk, - const struct nf_ct_bridge_frag_data *data, + const struct nf_bridge_frag_data *data, struct sk_buff *)) { int frag_max_size = BR_INPUT_SKB_CB(skb)->frag_max_size; -- cgit v1.2.3 From 25d7cbcd2bb5d919b9ba6fcdfe788e72c2df7e6e Mon Sep 17 00:00:00 2001 From: Jeremy Sowden Date: Fri, 13 Sep 2019 09:13:11 +0100 Subject: netfilter: replace defined(CONFIG...) || defined(CONFIG...MODULE) with IS_ENABLED(CONFIG...). A few headers contain instances of: #if defined(CONFIG_XXX) or defined(CONFIG_XXX_MODULE) Replace them with: #if IS_ENABLED(CONFIG_XXX) Signed-off-by: Jeremy Sowden Signed-off-by: Pablo Neira Ayuso --- include/linux/netfilter.h | 2 +- include/linux/netfilter/ipset/ip_set_getport.h | 2 +- include/net/netfilter/nf_conntrack_extend.h | 2 +- include/net/netfilter/nf_nat.h | 4 ++-- 4 files changed, 5 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/netfilter.h b/include/linux/netfilter.h index 049aeb40fa35..754995d028e2 100644 --- a/include/linux/netfilter.h +++ b/include/linux/netfilter.h @@ -422,7 +422,7 @@ nf_nat_decode_session(struct sk_buff *skb, struct flowi *fl, u_int8_t family) } #endif /*CONFIG_NETFILTER*/ -#if defined(CONFIG_NF_CONNTRACK) || defined(CONFIG_NF_CONNTRACK_MODULE) +#if IS_ENABLED(CONFIG_NF_CONNTRACK) #include extern void (*ip_ct_attach)(struct sk_buff *, const struct sk_buff *) __rcu; diff --git a/include/linux/netfilter/ipset/ip_set_getport.h b/include/linux/netfilter/ipset/ip_set_getport.h index a906df06948b..d74cd112b88a 100644 --- a/include/linux/netfilter/ipset/ip_set_getport.h +++ b/include/linux/netfilter/ipset/ip_set_getport.h @@ -9,7 +9,7 @@ extern bool ip_set_get_ip4_port(const struct sk_buff *skb, bool src, __be16 *port, u8 *proto); -#if defined(CONFIG_IP6_NF_IPTABLES) || defined(CONFIG_IP6_NF_IPTABLES_MODULE) +#if IS_ENABLED(CONFIG_IP6_NF_IPTABLES) extern bool ip_set_get_ip6_port(const struct sk_buff *skb, bool src, __be16 *port, u8 *proto); #else diff --git a/include/net/netfilter/nf_conntrack_extend.h b/include/net/netfilter/nf_conntrack_extend.h index 21f887c5058c..112a6f40dfaf 100644 --- a/include/net/netfilter/nf_conntrack_extend.h +++ b/include/net/netfilter/nf_conntrack_extend.h @@ -8,7 +8,7 @@ enum nf_ct_ext_id { NF_CT_EXT_HELPER, -#if defined(CONFIG_NF_NAT) || defined(CONFIG_NF_NAT_MODULE) +#if IS_ENABLED(CONFIG_NF_NAT) NF_CT_EXT_NAT, #endif NF_CT_EXT_SEQADJ, diff --git a/include/net/netfilter/nf_nat.h b/include/net/netfilter/nf_nat.h index eeb336809679..362ff94fa6b0 100644 --- a/include/net/netfilter/nf_nat.h +++ b/include/net/netfilter/nf_nat.h @@ -22,7 +22,7 @@ enum nf_nat_manip_type { /* per conntrack: nat application helper private data */ union nf_conntrack_nat_help { /* insert nat helper private data here */ -#if defined(CONFIG_NF_NAT_PPTP) || defined(CONFIG_NF_NAT_PPTP_MODULE) +#if IS_ENABLED(CONFIG_NF_NAT_PPTP) struct nf_nat_pptp nat_pptp_info; #endif }; @@ -47,7 +47,7 @@ struct nf_conn_nat *nf_ct_nat_ext_add(struct nf_conn *ct); static inline struct nf_conn_nat *nfct_nat(const struct nf_conn *ct) { -#if defined(CONFIG_NF_NAT) || defined(CONFIG_NF_NAT_MODULE) +#if IS_ENABLED(CONFIG_NF_NAT) return nf_ct_ext_find(ct, NF_CT_EXT_NAT); #else return NULL; -- cgit v1.2.3 From 261db6c2fbd64a2e649fdfa5f75cf161c384d110 Mon Sep 17 00:00:00 2001 From: Jeremy Sowden Date: Fri, 13 Sep 2019 09:13:14 +0100 Subject: netfilter: conntrack: move code to linux/nf_conntrack_common.h. Move some `struct nf_conntrack` code from linux/skbuff.h to linux/nf_conntrack_common.h. Together with a couple of helpers for getting and setting skb->_nfct, it allows us to remove CONFIG_NF_CONNTRACK checks from net/netfilter/nf_conntrack.h. Signed-off-by: Jeremy Sowden Signed-off-by: Pablo Neira Ayuso --- include/linux/netfilter/nf_conntrack_common.h | 20 +++++++++++++++++ include/linux/skbuff.h | 32 +++++++++++++-------------- include/net/netfilter/nf_conntrack.h | 24 +++++--------------- net/netfilter/nf_conntrack_standalone.c | 1 - 4 files changed, 40 insertions(+), 37 deletions(-) (limited to 'include/linux') diff --git a/include/linux/netfilter/nf_conntrack_common.h b/include/linux/netfilter/nf_conntrack_common.h index e142b2b5f1ea..1db83c931d9c 100644 --- a/include/linux/netfilter/nf_conntrack_common.h +++ b/include/linux/netfilter/nf_conntrack_common.h @@ -2,6 +2,7 @@ #ifndef _NF_CONNTRACK_COMMON_H #define _NF_CONNTRACK_COMMON_H +#include #include struct ip_conntrack_stat { @@ -19,4 +20,23 @@ struct ip_conntrack_stat { unsigned int search_restart; }; +#define NFCT_INFOMASK 7UL +#define NFCT_PTRMASK ~(NFCT_INFOMASK) + +struct nf_conntrack { + atomic_t use; +}; + +void nf_conntrack_destroy(struct nf_conntrack *nfct); +static inline void nf_conntrack_put(struct nf_conntrack *nfct) +{ + if (nfct && atomic_dec_and_test(&nfct->use)) + nf_conntrack_destroy(nfct); +} +static inline void nf_conntrack_get(struct nf_conntrack *nfct) +{ + if (nfct) + atomic_inc(&nfct->use); +} + #endif /* _NF_CONNTRACK_COMMON_H */ diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 028e684fa974..907209c0794e 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -37,6 +37,9 @@ #include #include #include +#if IS_ENABLED(CONFIG_NF_CONNTRACK) +#include +#endif /* The interface for checksum offload between the stack and networking drivers * is as follows... @@ -244,12 +247,6 @@ struct bpf_prog; union bpf_attr; struct skb_ext; -#if defined(CONFIG_NF_CONNTRACK) || defined(CONFIG_NF_CONNTRACK_MODULE) -struct nf_conntrack { - atomic_t use; -}; -#endif - #if IS_ENABLED(CONFIG_BRIDGE_NETFILTER) struct nf_bridge_info { enum { @@ -914,7 +911,6 @@ static inline bool skb_pfmemalloc(const struct sk_buff *skb) #define SKB_DST_NOREF 1UL #define SKB_DST_PTRMASK ~(SKB_DST_NOREF) -#define SKB_NFCT_PTRMASK ~(7UL) /** * skb_dst - returns skb dst_entry * @skb: buffer @@ -4040,25 +4036,27 @@ static inline void skb_remcsum_process(struct sk_buff *skb, void *ptr, static inline struct nf_conntrack *skb_nfct(const struct sk_buff *skb) { #if IS_ENABLED(CONFIG_NF_CONNTRACK) - return (void *)(skb->_nfct & SKB_NFCT_PTRMASK); + return (void *)(skb->_nfct & NFCT_PTRMASK); #else return NULL; #endif } -#if defined(CONFIG_NF_CONNTRACK) || defined(CONFIG_NF_CONNTRACK_MODULE) -void nf_conntrack_destroy(struct nf_conntrack *nfct); -static inline void nf_conntrack_put(struct nf_conntrack *nfct) +static inline unsigned long skb_get_nfct(const struct sk_buff *skb) { - if (nfct && atomic_dec_and_test(&nfct->use)) - nf_conntrack_destroy(nfct); +#if IS_ENABLED(CONFIG_NF_CONNTRACK) + return skb->_nfct; +#else + return 0UL; +#endif } -static inline void nf_conntrack_get(struct nf_conntrack *nfct) + +static inline void skb_set_nfct(struct sk_buff *skb, unsigned long nfct) { - if (nfct) - atomic_inc(&nfct->use); -} +#if IS_ENABLED(CONFIG_NF_CONNTRACK) + skb->_nfct = nfct; #endif +} #ifdef CONFIG_SKB_EXTENSIONS enum skb_ext_id { diff --git a/include/net/netfilter/nf_conntrack.h b/include/net/netfilter/nf_conntrack.h index 22275f42f0bb..9f551f3b69c6 100644 --- a/include/net/netfilter/nf_conntrack.h +++ b/include/net/netfilter/nf_conntrack.h @@ -13,12 +13,10 @@ #ifndef _NF_CONNTRACK_H #define _NF_CONNTRACK_H -#include - #include #include -#include +#include #include #include #include @@ -58,7 +56,6 @@ struct nf_conntrack_net { #include struct nf_conn { -#if IS_ENABLED(CONFIG_NF_CONNTRACK) /* Usage count in here is 1 for hash table, 1 per skb, * plus 1 for any connection(s) we are `master' for * @@ -68,7 +65,6 @@ struct nf_conn { * beware nf_ct_get() is different and don't inc refcnt. */ struct nf_conntrack ct_general; -#endif spinlock_t lock; /* jiffies32 when this ct is considered dead */ @@ -149,18 +145,14 @@ void nf_conntrack_alter_reply(struct nf_conn *ct, int nf_conntrack_tuple_taken(const struct nf_conntrack_tuple *tuple, const struct nf_conn *ignored_conntrack); -#if IS_ENABLED(CONFIG_NF_CONNTRACK) - -#define NFCT_INFOMASK 7UL -#define NFCT_PTRMASK ~(NFCT_INFOMASK) - /* Return conntrack_info and tuple hash for given skb. */ static inline struct nf_conn * nf_ct_get(const struct sk_buff *skb, enum ip_conntrack_info *ctinfo) { - *ctinfo = skb->_nfct & NFCT_INFOMASK; + unsigned long nfct = skb_get_nfct(skb); - return (struct nf_conn *)(skb->_nfct & NFCT_PTRMASK); + *ctinfo = nfct & NFCT_INFOMASK; + return (struct nf_conn *)(nfct & NFCT_PTRMASK); } /* decrement reference count on a conntrack */ @@ -170,8 +162,6 @@ static inline void nf_ct_put(struct nf_conn *ct) nf_conntrack_put(&ct->ct_general); } -#endif - /* Protocol module loading */ int nf_ct_l3proto_try_module_get(unsigned short l3proto); void nf_ct_l3proto_module_put(unsigned short l3proto); @@ -323,16 +313,12 @@ void nf_ct_tmpl_free(struct nf_conn *tmpl); u32 nf_ct_get_id(const struct nf_conn *ct); -#if IS_ENABLED(CONFIG_NF_CONNTRACK) - static inline void nf_ct_set(struct sk_buff *skb, struct nf_conn *ct, enum ip_conntrack_info info) { - skb->_nfct = (unsigned long)ct | info; + skb_set_nfct(skb, (unsigned long)ct | info); } -#endif - #define NF_CT_STAT_INC(net, count) __this_cpu_inc((net)->ct.stat->count) #define NF_CT_STAT_INC_ATOMIC(net, count) this_cpu_inc((net)->ct.stat->count) #define NF_CT_STAT_ADD_ATOMIC(net, count, v) this_cpu_add((net)->ct.stat->count, (v)) diff --git a/net/netfilter/nf_conntrack_standalone.c b/net/netfilter/nf_conntrack_standalone.c index 88d4127df863..410809c669e1 100644 --- a/net/netfilter/nf_conntrack_standalone.c +++ b/net/netfilter/nf_conntrack_standalone.c @@ -1167,7 +1167,6 @@ static int __init nf_conntrack_standalone_init(void) if (ret < 0) goto out_start; - BUILD_BUG_ON(SKB_NFCT_PTRMASK != NFCT_PTRMASK); BUILD_BUG_ON(NFCT_INFOMASK <= IP_CT_NUMBER); #ifdef CONFIG_SYSCTL -- cgit v1.2.3 From f19438bdd4bfbfdaac441034c1aaecf02c116e68 Mon Sep 17 00:00:00 2001 From: Jeremy Sowden Date: Fri, 13 Sep 2019 09:13:16 +0100 Subject: netfilter: remove CONFIG_NETFILTER checks from headers. `struct nf_hook_ops`, `struct nf_hook_state` and the `nf_hookfn` function typedef appear in function and struct declarations and definitions in a number of netfilter headers. The structs and typedef themselves are defined by linux/netfilter.h but only when CONFIG_NETFILTER is enabled. Define them unconditionally and add forward declarations in order to remove CONFIG_NETFILTER conditionals from the other headers. Signed-off-by: Jeremy Sowden Signed-off-by: Pablo Neira Ayuso --- include/linux/netfilter.h | 2 +- include/linux/netfilter/x_tables.h | 6 ------ include/linux/netfilter_arp/arp_tables.h | 2 -- include/linux/netfilter_bridge/ebtables.h | 3 +-- include/linux/netfilter_ipv4/ip_tables.h | 7 +------ include/linux/netfilter_ipv6/ip6_tables.h | 5 +---- include/net/netfilter/br_netfilter.h | 2 -- include/net/netfilter/nf_conntrack_bridge.h | 4 ++-- include/net/netfilter/nf_conntrack_core.h | 5 ++--- include/net/netfilter/nf_conntrack_l4proto.h | 2 -- include/net/netfilter/nf_conntrack_tuple.h | 2 -- include/net/netfilter/nf_flow_table.h | 4 ---- include/net/netfilter/nf_nat.h | 4 ---- include/net/netfilter/nf_queue.h | 4 ---- include/net/netfilter/nf_synproxy.h | 6 ++---- include/net/netfilter/nf_tables.h | 8 -------- 16 files changed, 10 insertions(+), 56 deletions(-) (limited to 'include/linux') diff --git a/include/linux/netfilter.h b/include/linux/netfilter.h index 754995d028e2..77ebb61faf48 100644 --- a/include/linux/netfilter.h +++ b/include/linux/netfilter.h @@ -15,7 +15,6 @@ #include #include -#ifdef CONFIG_NETFILTER static inline int NF_DROP_GETERR(int verdict) { return -(verdict >> NF_VERDICT_QBITS); @@ -118,6 +117,7 @@ struct nf_hook_entries { */ }; +#ifdef CONFIG_NETFILTER static inline struct nf_hook_ops **nf_hook_entries_get_hook_ops(const struct nf_hook_entries *e) { unsigned int n = e->num_hook_entries; diff --git a/include/linux/netfilter/x_tables.h b/include/linux/netfilter/x_tables.h index b9bc25f57c8e..1b261c51b3a3 100644 --- a/include/linux/netfilter/x_tables.h +++ b/include/linux/netfilter/x_tables.h @@ -35,15 +35,12 @@ struct xt_action_param { union { const void *matchinfo, *targinfo; }; -#if IS_ENABLED(CONFIG_NETFILTER) const struct nf_hook_state *state; -#endif int fragoff; unsigned int thoff; bool hotdrop; }; -#if IS_ENABLED(CONFIG_NETFILTER) static inline struct net *xt_net(const struct xt_action_param *par) { return par->state->net; @@ -78,7 +75,6 @@ static inline u_int8_t xt_family(const struct xt_action_param *par) { return par->state->pf; } -#endif /** * struct xt_mtchk_param - parameters for match extensions' @@ -450,9 +446,7 @@ xt_get_per_cpu_counter(struct xt_counters *cnt, unsigned int cpu) return cnt; } -#if IS_ENABLED(CONFIG_NETFILTER) struct nf_hook_ops *xt_hook_ops_alloc(const struct xt_table *, nf_hookfn *); -#endif #ifdef CONFIG_COMPAT #include diff --git a/include/linux/netfilter_arp/arp_tables.h b/include/linux/netfilter_arp/arp_tables.h index 1b7b35bb9c27..e98028f00e47 100644 --- a/include/linux/netfilter_arp/arp_tables.h +++ b/include/linux/netfilter_arp/arp_tables.h @@ -49,7 +49,6 @@ struct arpt_error { } extern void *arpt_alloc_initial_table(const struct xt_table *); -#if IS_ENABLED(CONFIG_NETFILTER) int arpt_register_table(struct net *net, const struct xt_table *table, const struct arpt_replace *repl, const struct nf_hook_ops *ops, struct xt_table **res); @@ -58,7 +57,6 @@ void arpt_unregister_table(struct net *net, struct xt_table *table, extern unsigned int arpt_do_table(struct sk_buff *skb, const struct nf_hook_state *state, struct xt_table *table); -#endif #ifdef CONFIG_COMPAT #include diff --git a/include/linux/netfilter_bridge/ebtables.h b/include/linux/netfilter_bridge/ebtables.h index b5b2d371f0ef..162f59d0d17a 100644 --- a/include/linux/netfilter_bridge/ebtables.h +++ b/include/linux/netfilter_bridge/ebtables.h @@ -105,7 +105,7 @@ struct ebt_table { #define EBT_ALIGN(s) (((s) + (__alignof__(struct _xt_align)-1)) & \ ~(__alignof__(struct _xt_align)-1)) -#if IS_ENABLED(CONFIG_NETFILTER) + extern int ebt_register_table(struct net *net, const struct ebt_table *table, const struct nf_hook_ops *ops, @@ -115,7 +115,6 @@ extern void ebt_unregister_table(struct net *net, struct ebt_table *table, extern unsigned int ebt_do_table(struct sk_buff *skb, const struct nf_hook_state *state, struct ebt_table *table); -#endif /* True if the hook mask denotes that the rule is in a base chain, * used in the check() functions */ diff --git a/include/linux/netfilter_ipv4/ip_tables.h b/include/linux/netfilter_ipv4/ip_tables.h index 0b0d43ad9ed9..e9e1ed74cdf1 100644 --- a/include/linux/netfilter_ipv4/ip_tables.h +++ b/include/linux/netfilter_ipv4/ip_tables.h @@ -17,19 +17,16 @@ #include #include +#include #include #include - -#include #include -#if IS_ENABLED(CONFIG_NETFILTER) int ipt_register_table(struct net *net, const struct xt_table *table, const struct ipt_replace *repl, const struct nf_hook_ops *ops, struct xt_table **res); void ipt_unregister_table(struct net *net, struct xt_table *table, const struct nf_hook_ops *ops); -#endif /* Standard entry. */ struct ipt_standard { @@ -65,11 +62,9 @@ struct ipt_error { } extern void *ipt_alloc_initial_table(const struct xt_table *); -#if IS_ENABLED(CONFIG_NETFILTER) extern unsigned int ipt_do_table(struct sk_buff *skb, const struct nf_hook_state *state, struct xt_table *table); -#endif #ifdef CONFIG_COMPAT #include diff --git a/include/linux/netfilter_ipv6/ip6_tables.h b/include/linux/netfilter_ipv6/ip6_tables.h index 3a0a2bd054cc..78ab959c4575 100644 --- a/include/linux/netfilter_ipv6/ip6_tables.h +++ b/include/linux/netfilter_ipv6/ip6_tables.h @@ -17,15 +17,13 @@ #include #include +#include #include #include - -#include #include extern void *ip6t_alloc_initial_table(const struct xt_table *); -#if IS_ENABLED(CONFIG_NETFILTER) int ip6t_register_table(struct net *net, const struct xt_table *table, const struct ip6t_replace *repl, const struct nf_hook_ops *ops, struct xt_table **res); @@ -34,7 +32,6 @@ void ip6t_unregister_table(struct net *net, struct xt_table *table, extern unsigned int ip6t_do_table(struct sk_buff *skb, const struct nf_hook_state *state, struct xt_table *table); -#endif #ifdef CONFIG_COMPAT #include diff --git a/include/net/netfilter/br_netfilter.h b/include/net/netfilter/br_netfilter.h index c53909fd22cd..371696ec11b2 100644 --- a/include/net/netfilter/br_netfilter.h +++ b/include/net/netfilter/br_netfilter.h @@ -55,7 +55,6 @@ static inline struct rtable *bridge_parent_rtable(const struct net_device *dev) struct net_device *setup_pre_routing(struct sk_buff *skb, const struct net *net); -#if IS_ENABLED(CONFIG_NETFILTER) #if IS_ENABLED(CONFIG_IPV6) int br_validate_ipv6(struct net *net, struct sk_buff *skb); unsigned int br_nf_pre_routing_ipv6(void *priv, @@ -74,6 +73,5 @@ br_nf_pre_routing_ipv6(void *priv, struct sk_buff *skb, return NF_ACCEPT; } #endif -#endif #endif /* _BR_NETFILTER_H_ */ diff --git a/include/net/netfilter/nf_conntrack_bridge.h b/include/net/netfilter/nf_conntrack_bridge.h index 01b62fd5efa2..c564281ede5e 100644 --- a/include/net/netfilter/nf_conntrack_bridge.h +++ b/include/net/netfilter/nf_conntrack_bridge.h @@ -5,10 +5,10 @@ #include #include +struct nf_hook_ops; + struct nf_ct_bridge_info { -#if IS_ENABLED(CONFIG_NETFILTER) struct nf_hook_ops *ops; -#endif unsigned int ops_size; struct module *me; }; diff --git a/include/net/netfilter/nf_conntrack_core.h b/include/net/netfilter/nf_conntrack_core.h index d340886e012d..09f2efea0b97 100644 --- a/include/net/netfilter/nf_conntrack_core.h +++ b/include/net/netfilter/nf_conntrack_core.h @@ -22,9 +22,8 @@ standalone connection tracking module, and the compatibility layer's use of connection tracking. */ -#if IS_ENABLED(CONFIG_NETFILTER) -unsigned int nf_conntrack_in(struct sk_buff *skb, const struct nf_hook_state *state); -#endif +unsigned int nf_conntrack_in(struct sk_buff *skb, + const struct nf_hook_state *state); int nf_conntrack_init_net(struct net *net); void nf_conntrack_cleanup_net(struct net *net); diff --git a/include/net/netfilter/nf_conntrack_l4proto.h b/include/net/netfilter/nf_conntrack_l4proto.h index 97240f1a3f5f..4cad1f0a327a 100644 --- a/include/net/netfilter/nf_conntrack_l4proto.h +++ b/include/net/netfilter/nf_conntrack_l4proto.h @@ -75,7 +75,6 @@ bool nf_conntrack_invert_icmp_tuple(struct nf_conntrack_tuple *tuple, bool nf_conntrack_invert_icmpv6_tuple(struct nf_conntrack_tuple *tuple, const struct nf_conntrack_tuple *orig); -#if IS_ENABLED(CONFIG_NETFILTER) int nf_conntrack_inet_error(struct nf_conn *tmpl, struct sk_buff *skb, unsigned int dataoff, const struct nf_hook_state *state, @@ -132,7 +131,6 @@ int nf_conntrack_gre_packet(struct nf_conn *ct, unsigned int dataoff, enum ip_conntrack_info ctinfo, const struct nf_hook_state *state); -#endif void nf_conntrack_generic_init_net(struct net *net); void nf_conntrack_tcp_init_net(struct net *net); diff --git a/include/net/netfilter/nf_conntrack_tuple.h b/include/net/netfilter/nf_conntrack_tuple.h index 68ea9b932736..9334371c94e2 100644 --- a/include/net/netfilter/nf_conntrack_tuple.h +++ b/include/net/netfilter/nf_conntrack_tuple.h @@ -121,7 +121,6 @@ struct nf_conntrack_tuple_hash { struct nf_conntrack_tuple tuple; }; -#if IS_ENABLED(CONFIG_NETFILTER) static inline bool __nf_ct_tuple_src_equal(const struct nf_conntrack_tuple *t1, const struct nf_conntrack_tuple *t2) { @@ -184,6 +183,5 @@ nf_ct_tuple_mask_cmp(const struct nf_conntrack_tuple *t, return nf_ct_tuple_src_mask_cmp(t, tuple, mask) && __nf_ct_tuple_dst_equal(t, tuple); } -#endif #endif /* _NF_CONNTRACK_TUPLE_H */ diff --git a/include/net/netfilter/nf_flow_table.h b/include/net/netfilter/nf_flow_table.h index d875be62cdf0..b37a7d608134 100644 --- a/include/net/netfilter/nf_flow_table.h +++ b/include/net/netfilter/nf_flow_table.h @@ -17,9 +17,7 @@ struct nf_flowtable_type { int family; int (*init)(struct nf_flowtable *ft); void (*free)(struct nf_flowtable *ft); -#if IS_ENABLED(CONFIG_NETFILTER) nf_hookfn *hook; -#endif struct module *owner; }; @@ -117,12 +115,10 @@ struct flow_ports { __be16 source, dest; }; -#if IS_ENABLED(CONFIG_NETFILTER) unsigned int nf_flow_offload_ip_hook(void *priv, struct sk_buff *skb, const struct nf_hook_state *state); unsigned int nf_flow_offload_ipv6_hook(void *priv, struct sk_buff *skb, const struct nf_hook_state *state); -#endif #define MODULE_ALIAS_NF_FLOWTABLE(family) \ MODULE_ALIAS("nf-flowtable-" __stringify(family)) diff --git a/include/net/netfilter/nf_nat.h b/include/net/netfilter/nf_nat.h index 362ff94fa6b0..0d412dd63707 100644 --- a/include/net/netfilter/nf_nat.h +++ b/include/net/netfilter/nf_nat.h @@ -68,12 +68,10 @@ static inline bool nf_nat_oif_changed(unsigned int hooknum, #endif } -#if IS_ENABLED(CONFIG_NETFILTER) int nf_nat_register_fn(struct net *net, u8 pf, const struct nf_hook_ops *ops, const struct nf_hook_ops *nat_ops, unsigned int ops_count); void nf_nat_unregister_fn(struct net *net, u8 pf, const struct nf_hook_ops *ops, unsigned int ops_count); -#endif unsigned int nf_nat_packet(struct nf_conn *ct, enum ip_conntrack_info ctinfo, unsigned int hooknum, struct sk_buff *skb); @@ -93,7 +91,6 @@ int nf_nat_icmpv6_reply_translation(struct sk_buff *skb, struct nf_conn *ct, enum ip_conntrack_info ctinfo, unsigned int hooknum, unsigned int hdrlen); -#if IS_ENABLED(CONFIG_NETFILTER) int nf_nat_ipv4_register_fn(struct net *net, const struct nf_hook_ops *ops); void nf_nat_ipv4_unregister_fn(struct net *net, const struct nf_hook_ops *ops); @@ -106,7 +103,6 @@ void nf_nat_inet_unregister_fn(struct net *net, const struct nf_hook_ops *ops); unsigned int nf_nat_inet_fn(void *priv, struct sk_buff *skb, const struct nf_hook_state *state); -#endif int nf_xfrm_me_harder(struct net *n, struct sk_buff *s, unsigned int family); diff --git a/include/net/netfilter/nf_queue.h b/include/net/netfilter/nf_queue.h index 80edb46a1bbc..47088083667b 100644 --- a/include/net/netfilter/nf_queue.h +++ b/include/net/netfilter/nf_queue.h @@ -15,9 +15,7 @@ struct nf_queue_entry { unsigned int id; unsigned int hook_index; /* index in hook_entries->hook[] */ -#if IS_ENABLED(CONFIG_NETFILTER) struct nf_hook_state state; -#endif u16 size; /* sizeof(entry) + saved route keys */ /* extra space to store route keys */ @@ -123,9 +121,7 @@ nfqueue_hash(const struct sk_buff *skb, u16 queue, u16 queues_total, u8 family, return queue; } -#if IS_ENABLED(CONFIG_NETFILTER) int nf_queue(struct sk_buff *skb, struct nf_hook_state *state, unsigned int index, unsigned int verdict); -#endif #endif /* _NF_QUEUE_H */ diff --git a/include/net/netfilter/nf_synproxy.h b/include/net/netfilter/nf_synproxy.h index 19d1af7a0348..a336f9434e73 100644 --- a/include/net/netfilter/nf_synproxy.h +++ b/include/net/netfilter/nf_synproxy.h @@ -58,10 +58,10 @@ bool synproxy_recv_client_ack(struct net *net, const struct tcphdr *th, struct synproxy_options *opts, u32 recv_seq); -#if IS_ENABLED(CONFIG_NETFILTER) +struct nf_hook_state; + unsigned int ipv4_synproxy_hook(void *priv, struct sk_buff *skb, const struct nf_hook_state *nhs); -#endif int nf_synproxy_ipv4_init(struct synproxy_net *snet, struct net *net); void nf_synproxy_ipv4_fini(struct synproxy_net *snet, struct net *net); @@ -75,10 +75,8 @@ 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); -#if IS_ENABLED(CONFIG_NETFILTER) unsigned int ipv6_synproxy_hook(void *priv, struct sk_buff *skb, const struct nf_hook_state *nhs); -#endif 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 diff --git a/include/net/netfilter/nf_tables.h b/include/net/netfilter/nf_tables.h index 3d9e66aa0139..2655e03dbe1b 100644 --- a/include/net/netfilter/nf_tables.h +++ b/include/net/netfilter/nf_tables.h @@ -26,7 +26,6 @@ struct nft_pktinfo { struct xt_action_param xt; }; -#if IS_ENABLED(CONFIG_NETFILTER) static inline struct net *nft_net(const struct nft_pktinfo *pkt) { return pkt->xt.state->net; @@ -59,7 +58,6 @@ static inline void nft_set_pktinfo(struct nft_pktinfo *pkt, pkt->skb = skb; pkt->xt.state = state; } -#endif static inline void nft_set_pktinfo_unspec(struct nft_pktinfo *pkt, struct sk_buff *skb) @@ -947,11 +945,9 @@ struct nft_chain_type { int family; struct module *owner; unsigned int hook_mask; -#if IS_ENABLED(CONFIG_NETFILTER) nf_hookfn *hooks[NF_MAX_HOOKS]; int (*ops_register)(struct net *net, const struct nf_hook_ops *ops); void (*ops_unregister)(struct net *net, const struct nf_hook_ops *ops); -#endif }; int nft_chain_validate_dependency(const struct nft_chain *chain, @@ -977,9 +973,7 @@ struct nft_stats { * @flow_block: flow block (for hardware offload) */ struct nft_base_chain { -#if IS_ENABLED(CONFIG_NETFILTER) struct nf_hook_ops ops; -#endif const struct nft_chain_type *type; u8 policy; u8 flags; @@ -1179,9 +1173,7 @@ struct nft_flowtable { use:30; u64 handle; /* runtime data below here */ -#if IS_ENABLED(CONFIG_NETFILTER) struct nf_hook_ops *ops ____cacheline_aligned; -#endif struct nf_flowtable data; }; -- cgit v1.2.3 From d895a0f16fadb26d22ab531c49768f7642ae5c3e Mon Sep 17 00:00:00 2001 From: Ilya Leoshkevich Date: Fri, 16 Aug 2019 12:53:00 +0200 Subject: bpf: fix accessing bpf_sysctl.file_pos on s390 "ctx:file_pos sysctl:read write ok" fails on s390 with "Read value != nux". This is because verifier rewrites a complete 32-bit bpf_sysctl.file_pos update to a partial update of the first 32 bits of 64-bit *bpf_sysctl_kern.ppos, which is not correct on big-endian systems. Fix by using an offset on big-endian systems. Ditto for bpf_sysctl.file_pos reads. Currently the test does not detect a problem there, since it expects to see 0, which it gets with high probability in error cases, so change it to seek to offset 3 and expect 3 in bpf_sysctl.file_pos. Fixes: e1550bfe0de4 ("bpf: Add file_pos field to bpf_sysctl ctx") Signed-off-by: Ilya Leoshkevich Acked-by: Yonghong Song Signed-off-by: Daniel Borkmann Link: https://lore.kernel.org/bpf/20190816105300.49035-1-iii@linux.ibm.com/ --- include/linux/filter.h | 8 ++++---- kernel/bpf/cgroup.c | 10 ++++++++-- kernel/bpf/verifier.c | 4 ++-- tools/testing/selftests/bpf/test_sysctl.c | 9 ++++++++- 4 files changed, 22 insertions(+), 9 deletions(-) (limited to 'include/linux') diff --git a/include/linux/filter.h b/include/linux/filter.h index 92c6e31fb008..2ce57645f3cd 100644 --- a/include/linux/filter.h +++ b/include/linux/filter.h @@ -749,14 +749,14 @@ bpf_ctx_narrow_access_ok(u32 off, u32 size, u32 size_default) } static inline u8 -bpf_ctx_narrow_load_shift(u32 off, u32 size, u32 size_default) +bpf_ctx_narrow_access_offset(u32 off, u32 size, u32 size_default) { - u8 load_off = off & (size_default - 1); + u8 access_off = off & (size_default - 1); #ifdef __LITTLE_ENDIAN - return load_off * 8; + return access_off; #else - return (size_default - (load_off + size)) * 8; + return size_default - (access_off + size); #endif } diff --git a/kernel/bpf/cgroup.c b/kernel/bpf/cgroup.c index 6a6a154cfa7b..ddd8addcdb5c 100644 --- a/kernel/bpf/cgroup.c +++ b/kernel/bpf/cgroup.c @@ -1334,6 +1334,7 @@ static u32 sysctl_convert_ctx_access(enum bpf_access_type type, struct bpf_prog *prog, u32 *target_size) { struct bpf_insn *insn = insn_buf; + u32 read_size; switch (si->off) { case offsetof(struct bpf_sysctl, write): @@ -1365,7 +1366,9 @@ static u32 sysctl_convert_ctx_access(enum bpf_access_type type, treg, si->dst_reg, offsetof(struct bpf_sysctl_kern, ppos)); *insn++ = BPF_STX_MEM( - BPF_SIZEOF(u32), treg, si->src_reg, 0); + BPF_SIZEOF(u32), treg, si->src_reg, + bpf_ctx_narrow_access_offset( + 0, sizeof(u32), sizeof(loff_t))); *insn++ = BPF_LDX_MEM( BPF_DW, treg, si->dst_reg, offsetof(struct bpf_sysctl_kern, tmp_reg)); @@ -1374,8 +1377,11 @@ static u32 sysctl_convert_ctx_access(enum bpf_access_type type, BPF_FIELD_SIZEOF(struct bpf_sysctl_kern, ppos), si->dst_reg, si->src_reg, offsetof(struct bpf_sysctl_kern, ppos)); + read_size = bpf_size_to_bytes(BPF_SIZE(si->code)); *insn++ = BPF_LDX_MEM( - BPF_SIZE(si->code), si->dst_reg, si->dst_reg, 0); + BPF_SIZE(si->code), si->dst_reg, si->dst_reg, + bpf_ctx_narrow_access_offset( + 0, read_size, sizeof(loff_t))); } *target_size = sizeof(u32); break; diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index 3fb50757e812..92a4332b041d 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -8619,8 +8619,8 @@ static int convert_ctx_accesses(struct bpf_verifier_env *env) } if (is_narrower_load && size < target_size) { - u8 shift = bpf_ctx_narrow_load_shift(off, size, - size_default); + u8 shift = bpf_ctx_narrow_access_offset( + off, size, size_default) * 8; if (ctx_field_size <= 4) { if (shift) insn_buf[cnt++] = BPF_ALU32_IMM(BPF_RSH, diff --git a/tools/testing/selftests/bpf/test_sysctl.c b/tools/testing/selftests/bpf/test_sysctl.c index fc33ae36b760..4f8ec1f10a80 100644 --- a/tools/testing/selftests/bpf/test_sysctl.c +++ b/tools/testing/selftests/bpf/test_sysctl.c @@ -32,6 +32,7 @@ struct sysctl_test { enum bpf_attach_type attach_type; const char *sysctl; int open_flags; + int seek; const char *newval; const char *oldval; enum { @@ -140,7 +141,7 @@ static struct sysctl_test tests[] = { /* If (file_pos == X) */ BPF_LDX_MEM(BPF_W, BPF_REG_7, BPF_REG_1, offsetof(struct bpf_sysctl, file_pos)), - BPF_JMP_IMM(BPF_JNE, BPF_REG_7, 0, 2), + BPF_JMP_IMM(BPF_JNE, BPF_REG_7, 3, 2), /* return ALLOW; */ BPF_MOV64_IMM(BPF_REG_0, 1), @@ -153,6 +154,7 @@ static struct sysctl_test tests[] = { .attach_type = BPF_CGROUP_SYSCTL, .sysctl = "kernel/ostype", .open_flags = O_RDONLY, + .seek = 3, .result = SUCCESS, }, { @@ -1481,6 +1483,11 @@ static int access_sysctl(const char *sysctl_path, if (fd < 0) return fd; + if (test->seek && lseek(fd, test->seek, SEEK_SET) == -1) { + log_err("lseek(%d) failed", test->seek); + goto err; + } + if (test->open_flags == O_RDONLY) { char buf[128]; -- cgit v1.2.3 From f9af2dbbfe01def62765a58af7fbc488351893c3 Mon Sep 17 00:00:00 2001 From: Thomas Higdon Date: Fri, 13 Sep 2019 23:23:34 +0000 Subject: tcp: Add TCP_INFO counter for packets received out-of-order For receive-heavy cases on the server-side, we want to track the connection quality for individual client IPs. This counter, similar to the existing system-wide TCPOFOQueue counter in /proc/net/netstat, tracks out-of-order packet reception. By providing this counter in TCP_INFO, it will allow understanding to what degree receive-heavy sockets are experiencing out-of-order delivery and packet drops indicating congestion. Please note that this is similar to the counter in NetBSD TCP_INFO, and has the same name. Also note that we avoid increasing the size of the tcp_sock struct by taking advantage of a hole. Signed-off-by: Thomas Higdon Acked-by: Neal Cardwell Signed-off-by: David S. Miller --- include/linux/tcp.h | 2 ++ include/uapi/linux/tcp.h | 2 ++ net/ipv4/tcp.c | 2 ++ net/ipv4/tcp_input.c | 1 + 4 files changed, 7 insertions(+) (limited to 'include/linux') diff --git a/include/linux/tcp.h b/include/linux/tcp.h index f3a85a7fb4b1..99617e528ea2 100644 --- a/include/linux/tcp.h +++ b/include/linux/tcp.h @@ -354,6 +354,8 @@ struct tcp_sock { #define BPF_SOCK_OPS_TEST_FLAG(TP, ARG) 0 #endif + u32 rcv_ooopack; /* Received out-of-order packets, for tcpinfo */ + /* Receiver side RTT estimation */ u32 rcv_rtt_last_tsecr; struct { diff --git a/include/uapi/linux/tcp.h b/include/uapi/linux/tcp.h index b3564f85a762..20237987ccc8 100644 --- a/include/uapi/linux/tcp.h +++ b/include/uapi/linux/tcp.h @@ -270,6 +270,8 @@ struct tcp_info { __u64 tcpi_bytes_retrans; /* RFC4898 tcpEStatsPerfOctetsRetrans */ __u32 tcpi_dsack_dups; /* RFC4898 tcpEStatsStackDSACKDups */ __u32 tcpi_reord_seen; /* reordering events seen */ + + __u32 tcpi_rcv_ooopack; /* Out-of-order packets received */ }; /* netlink attributes types for SCM_TIMESTAMPING_OPT_STATS */ diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index 94df48bcecc2..4cf58208270e 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -2653,6 +2653,7 @@ int tcp_disconnect(struct sock *sk, int flags) tp->rx_opt.saw_tstamp = 0; tp->rx_opt.dsack = 0; tp->rx_opt.num_sacks = 0; + tp->rcv_ooopack = 0; /* Clean up fastopen related fields */ @@ -3295,6 +3296,7 @@ void tcp_get_info(struct sock *sk, struct tcp_info *info) info->tcpi_bytes_retrans = tp->bytes_retrans; info->tcpi_dsack_dups = tp->dsack_dups; info->tcpi_reord_seen = tp->reord_seen; + info->tcpi_rcv_ooopack = tp->rcv_ooopack; unlock_sock_fast(sk, slow); } EXPORT_SYMBOL_GPL(tcp_get_info); diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index 7e94223fdb2b..3578357abe30 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -4555,6 +4555,7 @@ static void tcp_data_queue_ofo(struct sock *sk, struct sk_buff *skb) tp->pred_flags = 0; inet_csk_schedule_ack(sk); + tp->rcv_ooopack += max_t(u16, 1, skb_shinfo(skb)->gso_segs); NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPOFOQUEUE); seq = TCP_SKB_CB(skb)->seq; end_seq = TCP_SKB_CB(skb)->end_seq; -- cgit v1.2.3 From 9c66d15646760eb8982242b4531c4d4fd36118fd Mon Sep 17 00:00:00 2001 From: Vinicius Costa Gomes Date: Sun, 15 Sep 2019 04:59:58 +0300 Subject: taprio: Add support for hardware offloading This allows taprio to offload the schedule enforcement to capable network cards, resulting in more precise windows and less CPU usage. The gate mask acts on traffic classes (groups of queues of same priority), as specified in IEEE 802.1Q-2018, and following the existing taprio and mqprio semantics. It is up to the driver to perform conversion between tc and individual netdev queues if for some reason it needs to make that distinction. Full offload is requested from the network interface by specifying "flags 2" in the tc qdisc creation command, which in turn corresponds to the TCA_TAPRIO_ATTR_FLAG_FULL_OFFLOAD bit. The important detail here is the clockid which is implicitly /dev/ptpN for full offload, and hence not configurable. A reference counting API is added to support the use case where Ethernet drivers need to keep the taprio offload structure locally (i.e. they are a multi-port switch driver, and configuring a port depends on the settings of other ports as well). The refcount_t variable is kept in a private structure (__tc_taprio_qopt_offload) and not exposed to drivers. In the future, the private structure might also be expanded with a backpointer to taprio_sched *q, to implement the notification system described in the patch (of when admin became oper, or an error occurred, etc, so the offload can be monitored with 'tc qdisc show'). Signed-off-by: Vinicius Costa Gomes Signed-off-by: Voon Weifeng Signed-off-by: Vladimir Oltean Signed-off-by: David S. Miller --- include/linux/netdevice.h | 1 + include/net/pkt_sched.h | 23 +++ include/uapi/linux/pkt_sched.h | 3 +- net/sched/sch_taprio.c | 409 ++++++++++++++++++++++++++++++++++++----- 4 files changed, 392 insertions(+), 44 deletions(-) (limited to 'include/linux') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index d7d5626002e9..9eda1c31d1f7 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -847,6 +847,7 @@ enum tc_setup_type { TC_SETUP_QDISC_ETF, TC_SETUP_ROOT_QDISC, TC_SETUP_QDISC_GRED, + TC_SETUP_QDISC_TAPRIO, }; /* These structures hold the attributes of bpf state that are being passed diff --git a/include/net/pkt_sched.h b/include/net/pkt_sched.h index a16fbe9a2a67..d1632979622e 100644 --- a/include/net/pkt_sched.h +++ b/include/net/pkt_sched.h @@ -161,4 +161,27 @@ struct tc_etf_qopt_offload { s32 queue; }; +struct tc_taprio_sched_entry { + u8 command; /* TC_TAPRIO_CMD_* */ + + /* The gate_mask in the offloading side refers to traffic classes */ + u32 gate_mask; + u32 interval; +}; + +struct tc_taprio_qopt_offload { + u8 enable; + ktime_t base_time; + u64 cycle_time; + u64 cycle_time_extension; + + size_t num_entries; + struct tc_taprio_sched_entry entries[0]; +}; + +/* Reference counting */ +struct tc_taprio_qopt_offload *taprio_offload_get(struct tc_taprio_qopt_offload + *offload); +void taprio_offload_free(struct tc_taprio_qopt_offload *offload); + #endif diff --git a/include/uapi/linux/pkt_sched.h b/include/uapi/linux/pkt_sched.h index 18f185299f47..5011259b8f67 100644 --- a/include/uapi/linux/pkt_sched.h +++ b/include/uapi/linux/pkt_sched.h @@ -1160,7 +1160,8 @@ enum { * [TCA_TAPRIO_ATTR_SCHED_ENTRY_INTERVAL] */ -#define TCA_TAPRIO_ATTR_FLAG_TXTIME_ASSIST 0x1 +#define TCA_TAPRIO_ATTR_FLAG_TXTIME_ASSIST BIT(0) +#define TCA_TAPRIO_ATTR_FLAG_FULL_OFFLOAD BIT(1) enum { TCA_TAPRIO_ATTR_UNSPEC, diff --git a/net/sched/sch_taprio.c b/net/sched/sch_taprio.c index 84b863e2bdbd..2f7b34205c82 100644 --- a/net/sched/sch_taprio.c +++ b/net/sched/sch_taprio.c @@ -29,8 +29,8 @@ static DEFINE_SPINLOCK(taprio_list_lock); #define TAPRIO_ALL_GATES_OPEN -1 -#define FLAGS_VALID(flags) (!((flags) & ~TCA_TAPRIO_ATTR_FLAG_TXTIME_ASSIST)) #define TXTIME_ASSIST_IS_ENABLED(flags) ((flags) & TCA_TAPRIO_ATTR_FLAG_TXTIME_ASSIST) +#define FULL_OFFLOAD_IS_ENABLED(flags) ((flags) & TCA_TAPRIO_ATTR_FLAG_FULL_OFFLOAD) struct sched_entry { struct list_head list; @@ -75,9 +75,16 @@ struct taprio_sched { struct sched_gate_list __rcu *admin_sched; struct hrtimer advance_timer; struct list_head taprio_list; + struct sk_buff *(*dequeue)(struct Qdisc *sch); + struct sk_buff *(*peek)(struct Qdisc *sch); u32 txtime_delay; }; +struct __tc_taprio_qopt_offload { + refcount_t users; + struct tc_taprio_qopt_offload offload; +}; + static ktime_t sched_base_time(const struct sched_gate_list *sched) { if (!sched) @@ -268,6 +275,19 @@ static bool is_valid_interval(struct sk_buff *skb, struct Qdisc *sch) return entry; } +static bool taprio_flags_valid(u32 flags) +{ + /* Make sure no other flag bits are set. */ + if (flags & ~(TCA_TAPRIO_ATTR_FLAG_TXTIME_ASSIST | + TCA_TAPRIO_ATTR_FLAG_FULL_OFFLOAD)) + return false; + /* txtime-assist and full offload are mutually exclusive */ + if ((flags & TCA_TAPRIO_ATTR_FLAG_TXTIME_ASSIST) && + (flags & TCA_TAPRIO_ATTR_FLAG_FULL_OFFLOAD)) + return false; + return true; +} + /* This returns the tstamp value set by TCP in terms of the set clock. */ static ktime_t get_tcp_tstamp(struct taprio_sched *q, struct sk_buff *skb) { @@ -417,7 +437,7 @@ static int taprio_enqueue(struct sk_buff *skb, struct Qdisc *sch, return qdisc_enqueue(skb, child, to_free); } -static struct sk_buff *taprio_peek(struct Qdisc *sch) +static struct sk_buff *taprio_peek_soft(struct Qdisc *sch) { struct taprio_sched *q = qdisc_priv(sch); struct net_device *dev = qdisc_dev(sch); @@ -461,6 +481,36 @@ static struct sk_buff *taprio_peek(struct Qdisc *sch) return NULL; } +static struct sk_buff *taprio_peek_offload(struct Qdisc *sch) +{ + struct taprio_sched *q = qdisc_priv(sch); + struct net_device *dev = qdisc_dev(sch); + struct sk_buff *skb; + int i; + + for (i = 0; i < dev->num_tx_queues; i++) { + struct Qdisc *child = q->qdiscs[i]; + + if (unlikely(!child)) + continue; + + skb = child->ops->peek(child); + if (!skb) + continue; + + return skb; + } + + return NULL; +} + +static struct sk_buff *taprio_peek(struct Qdisc *sch) +{ + struct taprio_sched *q = qdisc_priv(sch); + + return q->peek(sch); +} + static void taprio_set_budget(struct taprio_sched *q, struct sched_entry *entry) { atomic_set(&entry->budget, @@ -468,7 +518,7 @@ static void taprio_set_budget(struct taprio_sched *q, struct sched_entry *entry) atomic64_read(&q->picos_per_byte))); } -static struct sk_buff *taprio_dequeue(struct Qdisc *sch) +static struct sk_buff *taprio_dequeue_soft(struct Qdisc *sch) { struct taprio_sched *q = qdisc_priv(sch); struct net_device *dev = qdisc_dev(sch); @@ -550,6 +600,40 @@ done: return skb; } +static struct sk_buff *taprio_dequeue_offload(struct Qdisc *sch) +{ + struct taprio_sched *q = qdisc_priv(sch); + struct net_device *dev = qdisc_dev(sch); + struct sk_buff *skb; + int i; + + for (i = 0; i < dev->num_tx_queues; i++) { + struct Qdisc *child = q->qdiscs[i]; + + if (unlikely(!child)) + continue; + + skb = child->ops->dequeue(child); + if (unlikely(!skb)) + continue; + + qdisc_bstats_update(sch, skb); + qdisc_qstats_backlog_dec(sch, skb); + sch->q.qlen--; + + return skb; + } + + return NULL; +} + +static struct sk_buff *taprio_dequeue(struct Qdisc *sch) +{ + struct taprio_sched *q = qdisc_priv(sch); + + return q->dequeue(sch); +} + static bool should_restart_cycle(const struct sched_gate_list *oper, const struct sched_entry *entry) { @@ -932,6 +1016,9 @@ static void taprio_start_sched(struct Qdisc *sch, struct taprio_sched *q = qdisc_priv(sch); ktime_t expires; + if (FULL_OFFLOAD_IS_ENABLED(q->flags)) + return; + expires = hrtimer_get_expires(&q->advance_timer); if (expires == 0) expires = KTIME_MAX; @@ -1011,6 +1098,254 @@ static void setup_txtime(struct taprio_sched *q, } } +static struct tc_taprio_qopt_offload *taprio_offload_alloc(int num_entries) +{ + size_t size = sizeof(struct tc_taprio_sched_entry) * num_entries + + sizeof(struct __tc_taprio_qopt_offload); + struct __tc_taprio_qopt_offload *__offload; + + __offload = kzalloc(size, GFP_KERNEL); + if (!__offload) + return NULL; + + refcount_set(&__offload->users, 1); + + return &__offload->offload; +} + +struct tc_taprio_qopt_offload *taprio_offload_get(struct tc_taprio_qopt_offload + *offload) +{ + struct __tc_taprio_qopt_offload *__offload; + + __offload = container_of(offload, struct __tc_taprio_qopt_offload, + offload); + + refcount_inc(&__offload->users); + + return offload; +} +EXPORT_SYMBOL_GPL(taprio_offload_get); + +void taprio_offload_free(struct tc_taprio_qopt_offload *offload) +{ + struct __tc_taprio_qopt_offload *__offload; + + __offload = container_of(offload, struct __tc_taprio_qopt_offload, + offload); + + if (!refcount_dec_and_test(&__offload->users)) + return; + + kfree(__offload); +} +EXPORT_SYMBOL_GPL(taprio_offload_free); + +/* The function will only serve to keep the pointers to the "oper" and "admin" + * schedules valid in relation to their base times, so when calling dump() the + * users looks at the right schedules. + * When using full offload, the admin configuration is promoted to oper at the + * base_time in the PHC time domain. But because the system time is not + * necessarily in sync with that, we can't just trigger a hrtimer to call + * switch_schedules at the right hardware time. + * At the moment we call this by hand right away from taprio, but in the future + * it will be useful to create a mechanism for drivers to notify taprio of the + * offload state (PENDING, ACTIVE, INACTIVE) so it can be visible in dump(). + * This is left as TODO. + */ +void taprio_offload_config_changed(struct taprio_sched *q) +{ + struct sched_gate_list *oper, *admin; + + spin_lock(&q->current_entry_lock); + + oper = rcu_dereference_protected(q->oper_sched, + lockdep_is_held(&q->current_entry_lock)); + admin = rcu_dereference_protected(q->admin_sched, + lockdep_is_held(&q->current_entry_lock)); + + switch_schedules(q, &admin, &oper); + + spin_unlock(&q->current_entry_lock); +} + +static void taprio_sched_to_offload(struct taprio_sched *q, + struct sched_gate_list *sched, + const struct tc_mqprio_qopt *mqprio, + struct tc_taprio_qopt_offload *offload) +{ + struct sched_entry *entry; + int i = 0; + + offload->base_time = sched->base_time; + offload->cycle_time = sched->cycle_time; + offload->cycle_time_extension = sched->cycle_time_extension; + + list_for_each_entry(entry, &sched->entries, list) { + struct tc_taprio_sched_entry *e = &offload->entries[i]; + + e->command = entry->command; + e->interval = entry->interval; + e->gate_mask = entry->gate_mask; + i++; + } + + offload->num_entries = i; +} + +static int taprio_enable_offload(struct net_device *dev, + struct tc_mqprio_qopt *mqprio, + struct taprio_sched *q, + struct sched_gate_list *sched, + struct netlink_ext_ack *extack) +{ + const struct net_device_ops *ops = dev->netdev_ops; + struct tc_taprio_qopt_offload *offload; + int err = 0; + + if (!ops->ndo_setup_tc) { + NL_SET_ERR_MSG(extack, + "Device does not support taprio offload"); + return -EOPNOTSUPP; + } + + offload = taprio_offload_alloc(sched->num_entries); + if (!offload) { + NL_SET_ERR_MSG(extack, + "Not enough memory for enabling offload mode"); + return -ENOMEM; + } + offload->enable = 1; + taprio_sched_to_offload(q, sched, mqprio, offload); + + err = ops->ndo_setup_tc(dev, TC_SETUP_QDISC_TAPRIO, offload); + if (err < 0) { + NL_SET_ERR_MSG(extack, + "Device failed to setup taprio offload"); + goto done; + } + + taprio_offload_config_changed(q); + +done: + taprio_offload_free(offload); + + return err; +} + +static int taprio_disable_offload(struct net_device *dev, + struct taprio_sched *q, + struct netlink_ext_ack *extack) +{ + const struct net_device_ops *ops = dev->netdev_ops; + struct tc_taprio_qopt_offload *offload; + int err; + + if (!FULL_OFFLOAD_IS_ENABLED(q->flags)) + return 0; + + if (!ops->ndo_setup_tc) + return -EOPNOTSUPP; + + offload = taprio_offload_alloc(0); + if (!offload) { + NL_SET_ERR_MSG(extack, + "Not enough memory to disable offload mode"); + return -ENOMEM; + } + offload->enable = 0; + + err = ops->ndo_setup_tc(dev, TC_SETUP_QDISC_TAPRIO, offload); + if (err < 0) { + NL_SET_ERR_MSG(extack, + "Device failed to disable offload"); + goto out; + } + +out: + taprio_offload_free(offload); + + return err; +} + +/* If full offload is enabled, the only possible clockid is the net device's + * PHC. For that reason, specifying a clockid through netlink is incorrect. + * For txtime-assist, it is implicitly assumed that the device's PHC is kept + * in sync with the specified clockid via a user space daemon such as phc2sys. + * For both software taprio and txtime-assist, the clockid is used for the + * hrtimer that advances the schedule and hence mandatory. + */ +static int taprio_parse_clockid(struct Qdisc *sch, struct nlattr **tb, + struct netlink_ext_ack *extack) +{ + struct taprio_sched *q = qdisc_priv(sch); + struct net_device *dev = qdisc_dev(sch); + int err = -EINVAL; + + if (FULL_OFFLOAD_IS_ENABLED(q->flags)) { + const struct ethtool_ops *ops = dev->ethtool_ops; + struct ethtool_ts_info info = { + .cmd = ETHTOOL_GET_TS_INFO, + .phc_index = -1, + }; + + if (tb[TCA_TAPRIO_ATTR_SCHED_CLOCKID]) { + NL_SET_ERR_MSG(extack, + "The 'clockid' cannot be specified for full offload"); + goto out; + } + + if (ops && ops->get_ts_info) + err = ops->get_ts_info(dev, &info); + + if (err || info.phc_index < 0) { + NL_SET_ERR_MSG(extack, + "Device does not have a PTP clock"); + err = -ENOTSUPP; + goto out; + } + } else if (tb[TCA_TAPRIO_ATTR_SCHED_CLOCKID]) { + int clockid = nla_get_s32(tb[TCA_TAPRIO_ATTR_SCHED_CLOCKID]); + + /* We only support static clockids and we don't allow + * for it to be modified after the first init. + */ + if (clockid < 0 || + (q->clockid != -1 && q->clockid != clockid)) { + NL_SET_ERR_MSG(extack, + "Changing the 'clockid' of a running schedule is not supported"); + err = -ENOTSUPP; + goto out; + } + + switch (clockid) { + case CLOCK_REALTIME: + q->tk_offset = TK_OFFS_REAL; + break; + case CLOCK_MONOTONIC: + q->tk_offset = TK_OFFS_MAX; + break; + case CLOCK_BOOTTIME: + q->tk_offset = TK_OFFS_BOOT; + break; + case CLOCK_TAI: + q->tk_offset = TK_OFFS_TAI; + break; + default: + NL_SET_ERR_MSG(extack, "Invalid 'clockid'"); + err = -EINVAL; + goto out; + } + + q->clockid = clockid; + } else { + NL_SET_ERR_MSG(extack, "Specifying a 'clockid' is mandatory"); + goto out; + } +out: + return err; +} + static int taprio_change(struct Qdisc *sch, struct nlattr *opt, struct netlink_ext_ack *extack) { @@ -1020,9 +1355,9 @@ static int taprio_change(struct Qdisc *sch, struct nlattr *opt, struct net_device *dev = qdisc_dev(sch); struct tc_mqprio_qopt *mqprio = NULL; u32 taprio_flags = 0; - int i, err, clockid; unsigned long flags; ktime_t start; + int i, err; err = nla_parse_nested_deprecated(tb, TCA_TAPRIO_ATTR_MAX, opt, taprio_policy, extack); @@ -1038,7 +1373,7 @@ static int taprio_change(struct Qdisc *sch, struct nlattr *opt, if (q->flags != 0 && q->flags != taprio_flags) { NL_SET_ERR_MSG_MOD(extack, "Changing 'flags' of a running schedule is not supported"); return -EOPNOTSUPP; - } else if (!FLAGS_VALID(taprio_flags)) { + } else if (!taprio_flags_valid(taprio_flags)) { NL_SET_ERR_MSG_MOD(extack, "Specified 'flags' are not valid"); return -EINVAL; } @@ -1078,30 +1413,19 @@ static int taprio_change(struct Qdisc *sch, struct nlattr *opt, goto free_sched; } - if (tb[TCA_TAPRIO_ATTR_SCHED_CLOCKID]) { - clockid = nla_get_s32(tb[TCA_TAPRIO_ATTR_SCHED_CLOCKID]); - - /* We only support static clockids and we don't allow - * for it to be modified after the first init. - */ - if (clockid < 0 || - (q->clockid != -1 && q->clockid != clockid)) { - NL_SET_ERR_MSG(extack, "Changing the 'clockid' of a running schedule is not supported"); - err = -ENOTSUPP; - goto free_sched; - } - - q->clockid = clockid; - } - - if (q->clockid == -1 && !tb[TCA_TAPRIO_ATTR_SCHED_CLOCKID]) { - NL_SET_ERR_MSG(extack, "Specifying a 'clockid' is mandatory"); - err = -EINVAL; + err = taprio_parse_clockid(sch, tb, extack); + if (err < 0) goto free_sched; - } taprio_set_picos_per_byte(dev, q); + if (FULL_OFFLOAD_IS_ENABLED(taprio_flags)) + err = taprio_enable_offload(dev, mqprio, q, new_admin, extack); + else + err = taprio_disable_offload(dev, q, extack); + if (err) + goto free_sched; + /* Protects against enqueue()/dequeue() */ spin_lock_bh(qdisc_lock(sch)); @@ -1116,6 +1440,7 @@ static int taprio_change(struct Qdisc *sch, struct nlattr *opt, } if (!TXTIME_ASSIST_IS_ENABLED(taprio_flags) && + !FULL_OFFLOAD_IS_ENABLED(taprio_flags) && !hrtimer_active(&q->advance_timer)) { hrtimer_init(&q->advance_timer, q->clockid, HRTIMER_MODE_ABS); q->advance_timer.function = advance_sched; @@ -1134,23 +1459,15 @@ static int taprio_change(struct Qdisc *sch, struct nlattr *opt, mqprio->prio_tc_map[i]); } - switch (q->clockid) { - case CLOCK_REALTIME: - q->tk_offset = TK_OFFS_REAL; - break; - case CLOCK_MONOTONIC: - q->tk_offset = TK_OFFS_MAX; - break; - case CLOCK_BOOTTIME: - q->tk_offset = TK_OFFS_BOOT; - break; - case CLOCK_TAI: - q->tk_offset = TK_OFFS_TAI; - break; - default: - NL_SET_ERR_MSG(extack, "Invalid 'clockid'"); - err = -EINVAL; - goto unlock; + if (FULL_OFFLOAD_IS_ENABLED(taprio_flags)) { + q->dequeue = taprio_dequeue_offload; + q->peek = taprio_peek_offload; + } else { + /* Be sure to always keep the function pointers + * in a consistent state. + */ + q->dequeue = taprio_dequeue_soft; + q->peek = taprio_peek_soft; } err = taprio_get_start_time(sch, new_admin, &start); @@ -1212,6 +1529,8 @@ static void taprio_destroy(struct Qdisc *sch) hrtimer_cancel(&q->advance_timer); + taprio_disable_offload(dev, q, NULL); + if (q->qdiscs) { for (i = 0; i < dev->num_tx_queues && q->qdiscs[i]; i++) qdisc_put(q->qdiscs[i]); @@ -1241,6 +1560,9 @@ static int taprio_init(struct Qdisc *sch, struct nlattr *opt, hrtimer_init(&q->advance_timer, CLOCK_TAI, HRTIMER_MODE_ABS); q->advance_timer.function = advance_sched; + q->dequeue = taprio_dequeue_soft; + q->peek = taprio_peek_soft; + q->root = sch; /* We only support static clockids. Use an invalid value as default @@ -1423,7 +1745,8 @@ static int taprio_dump(struct Qdisc *sch, struct sk_buff *skb) if (nla_put(skb, TCA_TAPRIO_ATTR_PRIOMAP, sizeof(opt), &opt)) goto options_error; - if (nla_put_s32(skb, TCA_TAPRIO_ATTR_SCHED_CLOCKID, q->clockid)) + if (!FULL_OFFLOAD_IS_ENABLED(q->flags) && + nla_put_s32(skb, TCA_TAPRIO_ATTR_SCHED_CLOCKID, q->clockid)) goto options_error; if (q->flags && nla_put_u32(skb, TCA_TAPRIO_ATTR_FLAGS, q->flags)) -- cgit v1.2.3