From 2125715635053d4207a756a35aa718f548824e58 Mon Sep 17 00:00:00 2001 From: Nikolay Aleksandrov Date: Tue, 16 Feb 2016 12:46:54 +0100 Subject: bridge: mdb: add support for more attributes and export timer Currently mdb entries are exported directly as a structure inside MDBA_MDB_ENTRY_INFO attribute, we can't really extend it without breaking user-space. In order to export new mdb fields, I've converted the MDBA_MDB_ENTRY_INFO into a nested attribute which starts like before with struct br_mdb_entry (without header, as it's casted directly in iproute2) and continues with MDBA_MDB_EATTR_ attributes. This way we keep compatibility with older users and can export new data. I've tested this with iproute2, both with and without support for the added attribute and it works fine. So basically we again have MDBA_MDB_ENTRY_INFO with struct br_mdb_entry inside but it may contain also some additional MDBA_MDB_EATTR_ attributes such as MDBA_MDB_EATTR_TIMER which can be parsed by user-space. So the new structure is: [MDBA_MDB] = { [MDBA_MDB_ENTRY] = { [MDBA_MDB_ENTRY_INFO] [MDBA_MDB_ENTRY_INFO] { <- Nested attribute struct br_mdb_entry <- nla_put_nohdr() [MDBA_MDB_ENTRY attributes] <- normal netlink attributes } } } Signed-off-by: Nikolay Aleksandrov Signed-off-by: David S. Miller --- include/uapi/linux/if_bridge.h | 13 ++++++++++++- 1 file changed, 12 insertions(+), 1 deletion(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/if_bridge.h b/include/uapi/linux/if_bridge.h index ec3547234998..0890b217580d 100644 --- a/include/uapi/linux/if_bridge.h +++ b/include/uapi/linux/if_bridge.h @@ -137,7 +137,10 @@ struct bridge_vlan_info { /* Bridge multicast database attributes * [MDBA_MDB] = { * [MDBA_MDB_ENTRY] = { - * [MDBA_MDB_ENTRY_INFO] + * [MDBA_MDB_ENTRY_INFO] { + * struct br_mdb_entry + * [MDBA_MDB_EATTR attributes] + * } * } * } * [MDBA_ROUTER] = { @@ -166,6 +169,14 @@ enum { }; #define MDBA_MDB_ENTRY_MAX (__MDBA_MDB_ENTRY_MAX - 1) +/* per mdb entry additional attributes */ +enum { + MDBA_MDB_EATTR_UNSPEC, + MDBA_MDB_EATTR_TIMER, + __MDBA_MDB_EATTR_MAX +}; +#define MDBA_MDB_EATTR_MAX (__MDBA_MDB_EATTR_MAX - 1) + enum { MDBA_ROUTER_UNSPEC, MDBA_ROUTER_PORT, -- cgit v1.3-18-gd494 From ac2c7ad0e5d6030452c9af2fafd192e17fd04264 Mon Sep 17 00:00:00 2001 From: Kan Liang Date: Fri, 19 Feb 2016 09:24:01 -0500 Subject: net/ethtool: introduce a new ioctl for per queue setting Introduce a new ioctl ETHTOOL_PERQUEUE for per queue parameters setting. The following patches will enable some SUB_COMMANDs for per queue setting. Signed-off-by: Kan Liang Reviewed-by: Ben Hutchings Signed-off-by: David S. Miller --- include/uapi/linux/ethtool.h | 17 +++++++++++++++++ net/core/ethtool.c | 27 +++++++++++++++++++++++++-- 2 files changed, 42 insertions(+), 2 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/ethtool.h b/include/uapi/linux/ethtool.h index 190aea0faaf4..f15ae02621a1 100644 --- a/include/uapi/linux/ethtool.h +++ b/include/uapi/linux/ethtool.h @@ -1202,6 +1202,21 @@ enum ethtool_sfeatures_retval_bits { #define ETHTOOL_F_WISH (1 << ETHTOOL_F_WISH__BIT) #define ETHTOOL_F_COMPAT (1 << ETHTOOL_F_COMPAT__BIT) +#define MAX_NUM_QUEUE 4096 + +/** + * struct ethtool_per_queue_op - apply sub command to the queues in mask. + * @cmd: ETHTOOL_PERQUEUE + * @sub_command: the sub command which apply to each queues + * @queue_mask: Bitmap of the queues which sub command apply to + * @data: A complete command structure following for each of the queues addressed + */ +struct ethtool_per_queue_op { + __u32 cmd; + __u32 sub_command; + __u32 queue_mask[DIV_ROUND_UP(MAX_NUM_QUEUE, 32)]; + char data[]; +}; /* CMDs currently supported */ #define ETHTOOL_GSET 0x00000001 /* Get settings. */ @@ -1285,6 +1300,8 @@ enum ethtool_sfeatures_retval_bits { #define ETHTOOL_STUNABLE 0x00000049 /* Set tunable configuration */ #define ETHTOOL_GPHYSTATS 0x0000004a /* get PHY-specific statistics */ +#define ETHTOOL_PERQUEUE 0x0000004b /* Set per queue options */ + /* compatibility with older code */ #define SPARC_ETH_GSET ETHTOOL_GSET #define SPARC_ETH_SSET ETHTOOL_SSET diff --git a/net/core/ethtool.c b/net/core/ethtool.c index c2d3118b1395..d640ecf71e74 100644 --- a/net/core/ethtool.c +++ b/net/core/ethtool.c @@ -1888,13 +1888,27 @@ out: return ret; } +static int ethtool_set_per_queue(struct net_device *dev, void __user *useraddr) +{ + struct ethtool_per_queue_op per_queue_opt; + + if (copy_from_user(&per_queue_opt, useraddr, sizeof(per_queue_opt))) + return -EFAULT; + + switch (per_queue_opt.sub_command) { + + default: + return -EOPNOTSUPP; + }; +} + /* The main entry point in this file. Called from net/core/dev_ioctl.c */ int dev_ethtool(struct net *net, struct ifreq *ifr) { struct net_device *dev = __dev_get_by_name(net, ifr->ifr_name); void __user *useraddr = ifr->ifr_data; - u32 ethcmd; + u32 ethcmd, sub_cmd; int rc; netdev_features_t old_features; @@ -1904,8 +1918,14 @@ int dev_ethtool(struct net *net, struct ifreq *ifr) if (copy_from_user(ðcmd, useraddr, sizeof(ethcmd))) return -EFAULT; + if (ethcmd == ETHTOOL_PERQUEUE) { + if (copy_from_user(&sub_cmd, useraddr + sizeof(ethcmd), sizeof(sub_cmd))) + return -EFAULT; + } else { + sub_cmd = ethcmd; + } /* Allow some commands to be done by anyone */ - switch (ethcmd) { + switch (sub_cmd) { case ETHTOOL_GSET: case ETHTOOL_GDRVINFO: case ETHTOOL_GMSGLVL: @@ -2135,6 +2155,9 @@ int dev_ethtool(struct net *net, struct ifreq *ifr) case ETHTOOL_GPHYSTATS: rc = ethtool_get_phy_stats(dev, useraddr); break; + case ETHTOOL_PERQUEUE: + rc = ethtool_set_per_queue(dev, useraddr); + break; default: rc = -EOPNOTSUPP; } -- cgit v1.3-18-gd494 From d5a3b1f691865be576c2bffa708549b8cdccda19 Mon Sep 17 00:00:00 2001 From: Alexei Starovoitov Date: Wed, 17 Feb 2016 19:58:58 -0800 Subject: bpf: introduce BPF_MAP_TYPE_STACK_TRACE add new map type to store stack traces and corresponding helper bpf_get_stackid(ctx, map, flags) - walk user or kernel stack and return id @ctx: struct pt_regs* @map: pointer to stack_trace map @flags: bits 0-7 - numer of stack frames to skip bit 8 - collect user stack instead of kernel bit 9 - compare stacks by hash only bit 10 - if two different stacks hash into the same stackid discard old other bits - reserved Return: >= 0 stackid on success or negative error stackid is a 32-bit integer handle that can be further combined with other data (including other stackid) and used as a key into maps. Userspace will access stackmap using standard lookup/delete syscall commands to retrieve full stack trace for given stackid. Signed-off-by: Alexei Starovoitov Signed-off-by: David S. Miller --- include/linux/bpf.h | 1 + include/uapi/linux/bpf.h | 21 +++++ kernel/bpf/Makefile | 3 + kernel/bpf/stackmap.c | 237 +++++++++++++++++++++++++++++++++++++++++++++++ kernel/bpf/verifier.c | 6 +- kernel/trace/bpf_trace.c | 2 + 6 files changed, 269 insertions(+), 1 deletion(-) create mode 100644 kernel/bpf/stackmap.c (limited to 'include/uapi/linux') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 90ee6ab24bc5..0cadbb7456c0 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -237,6 +237,7 @@ extern const struct bpf_func_proto bpf_get_current_uid_gid_proto; extern const struct bpf_func_proto bpf_get_current_comm_proto; extern const struct bpf_func_proto bpf_skb_vlan_push_proto; extern const struct bpf_func_proto bpf_skb_vlan_pop_proto; +extern const struct bpf_func_proto bpf_get_stackid_proto; /* Shared helpers among cBPF and eBPF. */ void bpf_user_rnd_init_once(void); diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index 2ee0fde1bf96..d3e77da8e9e8 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -83,6 +83,7 @@ enum bpf_map_type { BPF_MAP_TYPE_PERF_EVENT_ARRAY, BPF_MAP_TYPE_PERCPU_HASH, BPF_MAP_TYPE_PERCPU_ARRAY, + BPF_MAP_TYPE_STACK_TRACE, }; enum bpf_prog_type { @@ -272,6 +273,20 @@ enum bpf_func_id { */ BPF_FUNC_perf_event_output, BPF_FUNC_skb_load_bytes, + + /** + * bpf_get_stackid(ctx, map, flags) - walk user or kernel stack and return id + * @ctx: struct pt_regs* + * @map: pointer to stack_trace map + * @flags: bits 0-7 - numer of stack frames to skip + * bit 8 - collect user stack instead of kernel + * bit 9 - compare stacks by hash only + * bit 10 - if two different stacks hash into the same stackid + * discard old + * other bits - reserved + * Return: >= 0 stackid on success or negative error + */ + BPF_FUNC_get_stackid, __BPF_FUNC_MAX_ID, }; @@ -294,6 +309,12 @@ enum bpf_func_id { /* BPF_FUNC_skb_set_tunnel_key and BPF_FUNC_skb_get_tunnel_key flags. */ #define BPF_F_TUNINFO_IPV6 (1ULL << 0) +/* BPF_FUNC_get_stackid flags. */ +#define BPF_F_SKIP_FIELD_MASK 0xffULL +#define BPF_F_USER_STACK (1ULL << 8) +#define BPF_F_FAST_STACK_CMP (1ULL << 9) +#define BPF_F_REUSE_STACKID (1ULL << 10) + /* user accessible mirror of in-kernel sk_buff. * new fields can only be added to the end of this structure */ diff --git a/kernel/bpf/Makefile b/kernel/bpf/Makefile index 13272582eee0..8a932d079c24 100644 --- a/kernel/bpf/Makefile +++ b/kernel/bpf/Makefile @@ -2,3 +2,6 @@ obj-y := core.o obj-$(CONFIG_BPF_SYSCALL) += syscall.o verifier.o inode.o helpers.o obj-$(CONFIG_BPF_SYSCALL) += hashtab.o arraymap.o +ifeq ($(CONFIG_PERF_EVENTS),y) +obj-$(CONFIG_BPF_SYSCALL) += stackmap.o +endif diff --git a/kernel/bpf/stackmap.c b/kernel/bpf/stackmap.c new file mode 100644 index 000000000000..8a60ee14a977 --- /dev/null +++ b/kernel/bpf/stackmap.c @@ -0,0 +1,237 @@ +/* Copyright (c) 2016 Facebook + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of version 2 of the GNU General Public + * License as published by the Free Software Foundation. + */ +#include +#include +#include +#include +#include +#include + +struct stack_map_bucket { + struct rcu_head rcu; + u32 hash; + u32 nr; + u64 ip[]; +}; + +struct bpf_stack_map { + struct bpf_map map; + u32 n_buckets; + struct stack_map_bucket __rcu *buckets[]; +}; + +/* Called from syscall */ +static struct bpf_map *stack_map_alloc(union bpf_attr *attr) +{ + u32 value_size = attr->value_size; + struct bpf_stack_map *smap; + u64 cost, n_buckets; + int err; + + if (!capable(CAP_SYS_ADMIN)) + return ERR_PTR(-EPERM); + + /* check sanity of attributes */ + if (attr->max_entries == 0 || attr->key_size != 4 || + value_size < 8 || value_size % 8 || + value_size / 8 > PERF_MAX_STACK_DEPTH) + return ERR_PTR(-EINVAL); + + /* hash table size must be power of 2 */ + n_buckets = roundup_pow_of_two(attr->max_entries); + + cost = n_buckets * sizeof(struct stack_map_bucket *) + sizeof(*smap); + if (cost >= U32_MAX - PAGE_SIZE) + return ERR_PTR(-E2BIG); + + smap = kzalloc(cost, GFP_USER | __GFP_NOWARN); + if (!smap) { + smap = vzalloc(cost); + if (!smap) + return ERR_PTR(-ENOMEM); + } + + err = -E2BIG; + cost += n_buckets * (value_size + sizeof(struct stack_map_bucket)); + if (cost >= U32_MAX - PAGE_SIZE) + goto free_smap; + + smap->map.map_type = attr->map_type; + smap->map.key_size = attr->key_size; + smap->map.value_size = value_size; + smap->map.max_entries = attr->max_entries; + smap->n_buckets = n_buckets; + smap->map.pages = round_up(cost, PAGE_SIZE) >> PAGE_SHIFT; + + err = get_callchain_buffers(); + if (err) + goto free_smap; + + return &smap->map; + +free_smap: + kvfree(smap); + return ERR_PTR(err); +} + +static u64 bpf_get_stackid(u64 r1, u64 r2, u64 flags, u64 r4, u64 r5) +{ + struct pt_regs *regs = (struct pt_regs *) (long) r1; + struct bpf_map *map = (struct bpf_map *) (long) r2; + struct bpf_stack_map *smap = container_of(map, struct bpf_stack_map, map); + struct perf_callchain_entry *trace; + struct stack_map_bucket *bucket, *new_bucket, *old_bucket; + u32 max_depth = map->value_size / 8; + /* stack_map_alloc() checks that max_depth <= PERF_MAX_STACK_DEPTH */ + u32 init_nr = PERF_MAX_STACK_DEPTH - max_depth; + u32 skip = flags & BPF_F_SKIP_FIELD_MASK; + u32 hash, id, trace_nr, trace_len; + bool user = flags & BPF_F_USER_STACK; + bool kernel = !user; + u64 *ips; + + if (unlikely(flags & ~(BPF_F_SKIP_FIELD_MASK | BPF_F_USER_STACK | + BPF_F_FAST_STACK_CMP | BPF_F_REUSE_STACKID))) + return -EINVAL; + + trace = get_perf_callchain(regs, init_nr, kernel, user, false, false); + + if (unlikely(!trace)) + /* couldn't fetch the stack trace */ + return -EFAULT; + + /* get_perf_callchain() guarantees that trace->nr >= init_nr + * and trace-nr <= PERF_MAX_STACK_DEPTH, so trace_nr <= max_depth + */ + trace_nr = trace->nr - init_nr; + + if (trace_nr <= skip) + /* skipping more than usable stack trace */ + return -EFAULT; + + trace_nr -= skip; + trace_len = trace_nr * sizeof(u64); + ips = trace->ip + skip + init_nr; + hash = jhash2((u32 *)ips, trace_len / sizeof(u32), 0); + id = hash & (smap->n_buckets - 1); + bucket = rcu_dereference(smap->buckets[id]); + + if (bucket && bucket->hash == hash) { + if (flags & BPF_F_FAST_STACK_CMP) + return id; + if (bucket->nr == trace_nr && + memcmp(bucket->ip, ips, trace_len) == 0) + return id; + } + + /* this call stack is not in the map, try to add it */ + if (bucket && !(flags & BPF_F_REUSE_STACKID)) + return -EEXIST; + + new_bucket = kmalloc(sizeof(struct stack_map_bucket) + map->value_size, + GFP_ATOMIC | __GFP_NOWARN); + if (unlikely(!new_bucket)) + return -ENOMEM; + + memcpy(new_bucket->ip, ips, trace_len); + memset(new_bucket->ip + trace_len / 8, 0, map->value_size - trace_len); + new_bucket->hash = hash; + new_bucket->nr = trace_nr; + + old_bucket = xchg(&smap->buckets[id], new_bucket); + if (old_bucket) + kfree_rcu(old_bucket, rcu); + return id; +} + +const struct bpf_func_proto bpf_get_stackid_proto = { + .func = bpf_get_stackid, + .gpl_only = true, + .ret_type = RET_INTEGER, + .arg1_type = ARG_PTR_TO_CTX, + .arg2_type = ARG_CONST_MAP_PTR, + .arg3_type = ARG_ANYTHING, +}; + +/* Called from syscall or from eBPF program */ +static void *stack_map_lookup_elem(struct bpf_map *map, void *key) +{ + struct bpf_stack_map *smap = container_of(map, struct bpf_stack_map, map); + struct stack_map_bucket *bucket; + u32 id = *(u32 *)key; + + if (unlikely(id >= smap->n_buckets)) + return NULL; + bucket = rcu_dereference(smap->buckets[id]); + return bucket ? bucket->ip : NULL; +} + +static int stack_map_get_next_key(struct bpf_map *map, void *key, void *next_key) +{ + return -EINVAL; +} + +static int stack_map_update_elem(struct bpf_map *map, void *key, void *value, + u64 map_flags) +{ + return -EINVAL; +} + +/* Called from syscall or from eBPF program */ +static int stack_map_delete_elem(struct bpf_map *map, void *key) +{ + struct bpf_stack_map *smap = container_of(map, struct bpf_stack_map, map); + struct stack_map_bucket *old_bucket; + u32 id = *(u32 *)key; + + if (unlikely(id >= smap->n_buckets)) + return -E2BIG; + + old_bucket = xchg(&smap->buckets[id], NULL); + if (old_bucket) { + kfree_rcu(old_bucket, rcu); + return 0; + } else { + return -ENOENT; + } +} + +/* Called when map->refcnt goes to zero, either from workqueue or from syscall */ +static void stack_map_free(struct bpf_map *map) +{ + struct bpf_stack_map *smap = container_of(map, struct bpf_stack_map, map); + int i; + + synchronize_rcu(); + + for (i = 0; i < smap->n_buckets; i++) + if (smap->buckets[i]) + kfree_rcu(smap->buckets[i], rcu); + kvfree(smap); + put_callchain_buffers(); +} + +static const struct bpf_map_ops stack_map_ops = { + .map_alloc = stack_map_alloc, + .map_free = stack_map_free, + .map_get_next_key = stack_map_get_next_key, + .map_lookup_elem = stack_map_lookup_elem, + .map_update_elem = stack_map_update_elem, + .map_delete_elem = stack_map_delete_elem, +}; + +static struct bpf_map_type_list stack_map_type __read_mostly = { + .ops = &stack_map_ops, + .type = BPF_MAP_TYPE_STACK_TRACE, +}; + +static int __init register_stack_map(void) +{ + bpf_register_map_type(&stack_map_type); + return 0; +} +late_initcall(register_stack_map); diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index d1d3e8f57de9..42ba4ccc020b 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -246,6 +246,7 @@ static const struct { {BPF_MAP_TYPE_PROG_ARRAY, BPF_FUNC_tail_call}, {BPF_MAP_TYPE_PERF_EVENT_ARRAY, BPF_FUNC_perf_event_read}, {BPF_MAP_TYPE_PERF_EVENT_ARRAY, BPF_FUNC_perf_event_output}, + {BPF_MAP_TYPE_STACK_TRACE, BPF_FUNC_get_stackid}, }; static void print_verifier_state(struct verifier_env *env) @@ -911,8 +912,11 @@ static int check_map_func_compatibility(struct bpf_map *map, int func_id) * don't allow any other map type to be passed into * the special func; */ - if (bool_func && bool_map != bool_func) + if (bool_func && bool_map != bool_func) { + verbose("cannot pass map_type %d into func %d\n", + map->map_type, func_id); return -EINVAL; + } } return 0; diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c index 326a75e884db..4b8caa392b86 100644 --- a/kernel/trace/bpf_trace.c +++ b/kernel/trace/bpf_trace.c @@ -299,6 +299,8 @@ static const struct bpf_func_proto *kprobe_prog_func_proto(enum bpf_func_id func return &bpf_perf_event_read_proto; case BPF_FUNC_perf_event_output: return &bpf_perf_event_output_proto; + case BPF_FUNC_get_stackid: + return &bpf_get_stackid_proto; default: return NULL; } -- cgit v1.3-18-gd494 From 7d672345ed295b1356a5d9f7111da1d1d7d65867 Mon Sep 17 00:00:00 2001 From: Daniel Borkmann Date: Fri, 19 Feb 2016 23:05:23 +0100 Subject: bpf: add generic bpf_csum_diff helper For L4 checksums, we currently have bpf_l4_csum_replace() helper. It's currently limited to handle 2 and 4 byte changes in a header and feeds the from/to into inet_proto_csum_replace{2,4}() helpers of the kernel. When working with IPv6, for example, this makes it rather cumbersome to deal with, similarly when editing larger parts of a header. Instead, extend the API in a more generic way: For bpf_l4_csum_replace(), add a case for header field mask of 0 to change the checksum at a given offset through inet_proto_csum_replace_by_diff(), and provide a helper bpf_csum_diff() that can generically calculate a from/to diff for arbitrary amounts of data. This can be used in multiple ways: for the bpf_l4_csum_replace() only part, this even provides us with the option to insert precalculated diffs from user space f.e. from a map, or from bpf_csum_diff() during runtime. bpf_csum_diff() has a optional from/to stack buffer input, so we can calculate a diff by using a scratchbuffer for scenarios where we're inserting (from is NULL), removing (to is NULL) or diffing (from/to buffers don't need to be of equal size) data. Also, bpf_csum_diff() allows to feed a previous csum into csum_partial(), so the function can also be cascaded. Signed-off-by: Daniel Borkmann Acked-by: Alexei Starovoitov Signed-off-by: David S. Miller --- include/uapi/linux/bpf.h | 11 ++++++++++ net/core/filter.c | 53 ++++++++++++++++++++++++++++++++++++++++++++++++ 2 files changed, 64 insertions(+) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index d3e77da8e9e8..48d0a6c54609 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -287,6 +287,17 @@ enum bpf_func_id { * Return: >= 0 stackid on success or negative error */ BPF_FUNC_get_stackid, + + /** + * bpf_csum_diff(from, from_size, to, to_size, seed) - calculate csum diff + * @from: raw from buffer + * @from_size: length of from buffer + * @to: raw to buffer + * @to_size: length of to buffer + * @seed: optional seed + * Return: csum result + */ + BPF_FUNC_csum_diff, __BPF_FUNC_MAX_ID, }; diff --git a/net/core/filter.c b/net/core/filter.c index 2a6e9562f1ab..bf504f8fbe15 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -1491,6 +1491,12 @@ static u64 bpf_l4_csum_replace(u64 r1, u64 r2, u64 from, u64 to, u64 flags) return -EFAULT; switch (flags & BPF_F_HDR_FIELD_MASK) { + case 0: + if (unlikely(from != 0)) + return -EINVAL; + + inet_proto_csum_replace_by_diff(ptr, skb, to, is_pseudo); + break; case 2: inet_proto_csum_replace2(ptr, skb, from, to, is_pseudo); break; @@ -1519,6 +1525,51 @@ const struct bpf_func_proto bpf_l4_csum_replace_proto = { .arg5_type = ARG_ANYTHING, }; +struct bpf_csum_scratchpad { + __be32 diff[128]; +}; + +static DEFINE_PER_CPU(struct bpf_csum_scratchpad, bpf_csum_sp); + +static u64 bpf_csum_diff(u64 r1, u64 from_size, u64 r3, u64 to_size, u64 seed) +{ + struct bpf_csum_scratchpad *sp = this_cpu_ptr(&bpf_csum_sp); + u64 diff_size = from_size + to_size; + __be32 *from = (__be32 *) (long) r1; + __be32 *to = (__be32 *) (long) r3; + int i, j = 0; + + /* This is quite flexible, some examples: + * + * from_size == 0, to_size > 0, seed := csum --> pushing data + * from_size > 0, to_size == 0, seed := csum --> pulling data + * from_size > 0, to_size > 0, seed := 0 --> diffing data + * + * Even for diffing, from_size and to_size don't need to be equal. + */ + if (unlikely(((from_size | to_size) & (sizeof(__be32) - 1)) || + diff_size > sizeof(sp->diff))) + return -EINVAL; + + for (i = 0; i < from_size / sizeof(__be32); i++, j++) + sp->diff[j] = ~from[i]; + for (i = 0; i < to_size / sizeof(__be32); i++, j++) + sp->diff[j] = to[i]; + + return csum_partial(sp->diff, diff_size, seed); +} + +const struct bpf_func_proto bpf_csum_diff_proto = { + .func = bpf_csum_diff, + .gpl_only = false, + .ret_type = RET_INTEGER, + .arg1_type = ARG_PTR_TO_STACK, + .arg2_type = ARG_CONST_STACK_SIZE_OR_ZERO, + .arg3_type = ARG_PTR_TO_STACK, + .arg4_type = ARG_CONST_STACK_SIZE_OR_ZERO, + .arg5_type = ARG_ANYTHING, +}; + static u64 bpf_clone_redirect(u64 r1, u64 ifindex, u64 flags, u64 r4, u64 r5) { struct sk_buff *skb = (struct sk_buff *) (long) r1, *skb2; @@ -1849,6 +1900,8 @@ tc_cls_act_func_proto(enum bpf_func_id func_id) return &bpf_skb_store_bytes_proto; case BPF_FUNC_skb_load_bytes: return &bpf_skb_load_bytes_proto; + case BPF_FUNC_csum_diff: + return &bpf_csum_diff_proto; case BPF_FUNC_l3_csum_replace: return &bpf_l3_csum_replace_proto; case BPF_FUNC_l4_csum_replace: -- cgit v1.3-18-gd494 From 2f72959a9c1260ade234f353ccca91118151af66 Mon Sep 17 00:00:00 2001 From: Daniel Borkmann Date: Fri, 19 Feb 2016 23:05:26 +0100 Subject: bpf: fix csum update in bpf_l4_csum_replace helper for udp When using this helper for updating UDP checksums, we need to extend this in order to write CSUM_MANGLED_0 for csum computations that result into 0 as sum. Reason we need this is because packets with a checksum could otherwise become incorrectly marked as a packet without a checksum. Likewise, if the user indicates BPF_F_MARK_MANGLED_0, then we should not turn packets without a checksum into ones with a checksum. Signed-off-by: Daniel Borkmann Acked-by: Alexei Starovoitov Signed-off-by: David S. Miller --- include/uapi/linux/bpf.h | 1 + net/core/filter.c | 8 +++++++- 2 files changed, 8 insertions(+), 1 deletion(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index 48d0a6c54609..6496f98d3d68 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -313,6 +313,7 @@ enum bpf_func_id { /* BPF_FUNC_l4_csum_replace flags. */ #define BPF_F_PSEUDO_HDR (1ULL << 4) +#define BPF_F_MARK_MANGLED_0 (1ULL << 5) /* BPF_FUNC_clone_redirect and BPF_FUNC_redirect flags. */ #define BPF_F_INGRESS (1ULL << 0) diff --git a/net/core/filter.c b/net/core/filter.c index f031b82128f3..8a0b8c3eb189 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -1477,10 +1477,12 @@ static u64 bpf_l4_csum_replace(u64 r1, u64 r2, u64 from, u64 to, u64 flags) { struct sk_buff *skb = (struct sk_buff *) (long) r1; bool is_pseudo = flags & BPF_F_PSEUDO_HDR; + bool is_mmzero = flags & BPF_F_MARK_MANGLED_0; int offset = (int) r2; __sum16 sum, *ptr; - if (unlikely(flags & ~(BPF_F_PSEUDO_HDR | BPF_F_HDR_FIELD_MASK))) + if (unlikely(flags & ~(BPF_F_MARK_MANGLED_0 | BPF_F_PSEUDO_HDR | + BPF_F_HDR_FIELD_MASK))) return -EINVAL; if (unlikely((u32) offset > 0xffff)) return -EFAULT; @@ -1490,6 +1492,8 @@ static u64 bpf_l4_csum_replace(u64 r1, u64 r2, u64 from, u64 to, u64 flags) ptr = skb_header_pointer(skb, offset, sizeof(sum), &sum); if (unlikely(!ptr)) return -EFAULT; + if (is_mmzero && !*ptr) + return 0; switch (flags & BPF_F_HDR_FIELD_MASK) { case 0: @@ -1508,6 +1512,8 @@ static u64 bpf_l4_csum_replace(u64 r1, u64 r2, u64 from, u64 to, u64 flags) return -EINVAL; } + if (is_mmzero && !*ptr) + *ptr = CSUM_MANGLED_0; if (ptr == &sum) /* skb_store_bits guaranteed to not return -EFAULT here */ skb_store_bits(skb, offset, ptr, sizeof(sum)); -- cgit v1.3-18-gd494 From d4634e8dea13ccc969dd3f33dab3873cfdf3bc51 Mon Sep 17 00:00:00 2001 From: João Paulo Rechi Vita Date: Tue, 19 Jan 2016 10:42:42 -0500 Subject: rfkill: Update userspace API documentation MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Add a note to userspace on the effect of RFKILL_OP_CHANGE_ALL also updating the default state for hotplugged devices. Signed-off-by: João Paulo Rechi Vita [reword a bit] Signed-off-by: Johannes Berg --- include/uapi/linux/rfkill.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/rfkill.h b/include/uapi/linux/rfkill.h index 058757f7a733..2e00dcebebd0 100644 --- a/include/uapi/linux/rfkill.h +++ b/include/uapi/linux/rfkill.h @@ -59,6 +59,8 @@ enum rfkill_type { * @RFKILL_OP_DEL: a device was removed * @RFKILL_OP_CHANGE: a device's state changed -- userspace changes one device * @RFKILL_OP_CHANGE_ALL: userspace changes all devices (of a type, or all) + * into a state, also updating the default state used for devices that + * are hot-plugged later. */ enum rfkill_operation { RFKILL_OP_ADD = 0, -- cgit v1.3-18-gd494 From 34d505193bd10668acf1caba02d2f66bddc23fea Mon Sep 17 00:00:00 2001 From: Lior David Date: Thu, 28 Jan 2016 10:58:25 +0200 Subject: cfg80211: basic support for PBSS network type PBSS (Personal Basic Service Set) is a new BSS type for DMG networks. It is similar to infrastructure BSS, having an AP-like entity called PCP (PBSS Control Point), but it has few differences. PBSS support is mandatory for 11ad devices. Add support for PBSS by introducing a new PBSS flag attribute. The PBSS flag is used in the START_AP command to request starting a PCP instead of an AP, and in the CONNECT command to request connecting to a PCP instead of an AP. Signed-off-by: Lior David Signed-off-by: Johannes Berg --- drivers/net/wireless/ath/wil6210/cfg80211.c | 10 ++++++++++ include/net/cfg80211.h | 8 ++++++++ include/uapi/linux/nl80211.h | 6 ++++++ net/wireless/nl80211.c | 11 +++++++++++ net/wireless/sme.c | 9 ++++++--- 5 files changed, 41 insertions(+), 3 deletions(-) (limited to 'include/uapi/linux') diff --git a/drivers/net/wireless/ath/wil6210/cfg80211.c b/drivers/net/wireless/ath/wil6210/cfg80211.c index 20d07ef679e8..1f231cd08138 100644 --- a/drivers/net/wireless/ath/wil6210/cfg80211.c +++ b/drivers/net/wireless/ath/wil6210/cfg80211.c @@ -422,6 +422,11 @@ static int wil_cfg80211_connect(struct wiphy *wiphy, if (sme->privacy && !rsn_eid) wil_info(wil, "WSC connection\n"); + if (sme->pbss) { + wil_err(wil, "connect - PBSS not yet supported\n"); + return -EOPNOTSUPP; + } + bss = cfg80211_get_bss(wiphy, sme->channel, sme->bssid, sme->ssid, sme->ssid_len, IEEE80211_BSS_TYPE_ESS, IEEE80211_PRIVACY_ANY); @@ -870,6 +875,11 @@ static int wil_cfg80211_start_ap(struct wiphy *wiphy, return -EINVAL; } + if (info->pbss) { + wil_err(wil, "AP: PBSS not yet supported\n"); + return -EOPNOTSUPP; + } + switch (info->hidden_ssid) { case NL80211_HIDDEN_SSID_NOT_IN_USE: hidden_ssid = WMI_HIDDEN_SSID_DISABLED; diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h index 9bcaaf7cd15a..9e1b24c29f0c 100644 --- a/include/net/cfg80211.h +++ b/include/net/cfg80211.h @@ -712,6 +712,8 @@ struct cfg80211_acl_data { * @p2p_opp_ps: P2P opportunistic PS * @acl: ACL configuration used by the drivers which has support for * MAC address based access control + * @pbss: If set, start as a PCP instead of AP. Relevant for DMG + * networks. */ struct cfg80211_ap_settings { struct cfg80211_chan_def chandef; @@ -730,6 +732,7 @@ struct cfg80211_ap_settings { u8 p2p_ctwindow; bool p2p_opp_ps; const struct cfg80211_acl_data *acl; + bool pbss; }; /** @@ -1888,6 +1891,8 @@ struct cfg80211_ibss_params { * @ht_capa_mask: The bits of ht_capa which are to be used. * @vht_capa: VHT Capability overrides * @vht_capa_mask: The bits of vht_capa which are to be used. + * @pbss: if set, connect to a PCP instead of AP. Valid for DMG + * networks. */ struct cfg80211_connect_params { struct ieee80211_channel *channel; @@ -1910,6 +1915,7 @@ struct cfg80211_connect_params { struct ieee80211_ht_cap ht_capa_mask; struct ieee80211_vht_cap vht_capa; struct ieee80211_vht_cap vht_capa_mask; + bool pbss; }; /** @@ -3489,6 +3495,7 @@ struct cfg80211_cached_keys; * registered for unexpected class 3 frames (AP mode) * @conn: (private) cfg80211 software SME connection state machine data * @connect_keys: (private) keys to set after connection is established + * @conn_bss_type: connecting/connected BSS type * @ibss_fixed: (private) IBSS is using fixed BSSID * @ibss_dfs_possible: (private) IBSS may change to a DFS channel * @event_list: (private) list for internal event processing @@ -3519,6 +3526,7 @@ struct wireless_dev { u8 ssid_len, mesh_id_len, mesh_id_up_len; struct cfg80211_conn *conn; struct cfg80211_cached_keys *connect_keys; + enum ieee80211_bss_type conn_bss_type; struct list_head event_list; spinlock_t event_lock; diff --git a/include/uapi/linux/nl80211.h b/include/uapi/linux/nl80211.h index 5b7b5ebe7ca8..7758969a2a8e 100644 --- a/include/uapi/linux/nl80211.h +++ b/include/uapi/linux/nl80211.h @@ -1789,6 +1789,10 @@ enum nl80211_commands { * thus it must not specify the number of iterations, only the interval * between scans. The scan plans are executed sequentially. * Each scan plan is a nested attribute of &enum nl80211_sched_scan_plan. + * @NL80211_ATTR_PBSS: flag attribute. If set it means operate + * in a PBSS. Specified in %NL80211_CMD_CONNECT to request + * connecting to a PCP, and in %NL80211_CMD_START_AP to start + * a PCP instead of AP. Relevant for DMG networks only. * * @NUM_NL80211_ATTR: total number of nl80211_attrs available * @NL80211_ATTR_MAX: highest attribute number currently defined @@ -2164,6 +2168,8 @@ enum nl80211_attrs { NL80211_ATTR_MAX_SCAN_PLAN_ITERATIONS, NL80211_ATTR_SCHED_SCAN_PLANS, + NL80211_ATTR_PBSS, + /* add attributes here, update the policy in nl80211.c */ __NL80211_ATTR_AFTER_LAST, diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c index d4786f2802aa..268cb493f6a5 100644 --- a/net/wireless/nl80211.c +++ b/net/wireless/nl80211.c @@ -401,6 +401,7 @@ static const struct nla_policy nl80211_policy[NUM_NL80211_ATTR] = { [NL80211_ATTR_NETNS_FD] = { .type = NLA_U32 }, [NL80211_ATTR_SCHED_SCAN_DELAY] = { .type = NLA_U32 }, [NL80211_ATTR_REG_INDOOR] = { .type = NLA_FLAG }, + [NL80211_ATTR_PBSS] = { .type = NLA_FLAG }, }; /* policy for the key attributes */ @@ -3461,6 +3462,10 @@ static int nl80211_start_ap(struct sk_buff *skb, struct genl_info *info) return PTR_ERR(params.acl); } + params.pbss = nla_get_flag(info->attrs[NL80211_ATTR_PBSS]); + if (params.pbss && !rdev->wiphy.bands[IEEE80211_BAND_60GHZ]) + return -EOPNOTSUPP; + wdev_lock(wdev); err = rdev_start_ap(rdev, dev, ¶ms); if (!err) { @@ -7980,6 +7985,12 @@ static int nl80211_connect(struct sk_buff *skb, struct genl_info *info) connect.flags |= ASSOC_REQ_USE_RRM; } + connect.pbss = nla_get_flag(info->attrs[NL80211_ATTR_PBSS]); + if (connect.pbss && !rdev->wiphy.bands[IEEE80211_BAND_60GHZ]) { + kzfree(connkeys); + return -EOPNOTSUPP; + } + wdev_lock(dev->ieee80211_ptr); err = cfg80211_connect(rdev, dev, &connect, connkeys, NULL); wdev_unlock(dev->ieee80211_ptr); diff --git a/net/wireless/sme.c b/net/wireless/sme.c index 8020b5b094d4..79bd3a171caa 100644 --- a/net/wireless/sme.c +++ b/net/wireless/sme.c @@ -264,7 +264,7 @@ static struct cfg80211_bss *cfg80211_get_conn_bss(struct wireless_dev *wdev) wdev->conn->params.bssid, wdev->conn->params.ssid, wdev->conn->params.ssid_len, - IEEE80211_BSS_TYPE_ESS, + wdev->conn_bss_type, IEEE80211_PRIVACY(wdev->conn->params.privacy)); if (!bss) return NULL; @@ -687,7 +687,7 @@ void __cfg80211_connect_result(struct net_device *dev, const u8 *bssid, WARN_ON_ONCE(!wiphy_to_rdev(wdev->wiphy)->ops->connect); bss = cfg80211_get_bss(wdev->wiphy, NULL, bssid, wdev->ssid, wdev->ssid_len, - IEEE80211_BSS_TYPE_ESS, + wdev->conn_bss_type, IEEE80211_PRIVACY_ANY); if (bss) cfg80211_hold_bss(bss_from_pub(bss)); @@ -846,7 +846,7 @@ void cfg80211_roamed(struct net_device *dev, bss = cfg80211_get_bss(wdev->wiphy, channel, bssid, wdev->ssid, wdev->ssid_len, - IEEE80211_BSS_TYPE_ESS, IEEE80211_PRIVACY_ANY); + wdev->conn_bss_type, IEEE80211_PRIVACY_ANY); if (WARN_ON(!bss)) return; @@ -1017,6 +1017,9 @@ int cfg80211_connect(struct cfg80211_registered_device *rdev, memcpy(wdev->ssid, connect->ssid, connect->ssid_len); wdev->ssid_len = connect->ssid_len; + wdev->conn_bss_type = connect->pbss ? IEEE80211_BSS_TYPE_PBSS : + IEEE80211_BSS_TYPE_ESS; + if (!rdev->ops->connect) err = cfg80211_sme_connect(wdev, connect, prev_bssid); else -- cgit v1.3-18-gd494 From 0c9ca11b1ae8eb16c1b6bbae91991392d2321372 Mon Sep 17 00:00:00 2001 From: Beni Lev Date: Wed, 17 Feb 2016 20:30:00 +0200 Subject: cfg80211: Add global RRM capability Today, the supplicant will add the RRM capabilities Information Element in the association request only if Quiet period is supported (NL80211_FEATURE_QUIET). Quiet is one of many RRM features, and there are other RRM features that are not related to Quiet (e.g. neighbor report). Therefore, requiring Quiet to enable RRM is too restrictive. Some of the features, like neighbor report, can be supported by user space without any help from the kernel. Hence adding the RRM capabilities IE to association request should be the sole user space's decision. Removing the RRM dependency on Quiet in the driver solves this problem, but using an old driver with a user space tool that would not require Quiet feature would be problematic: the user space would add NL80211_ATTR_USE_RRM in the association request even if the kernel doesn't advertize NL80211_FEATURE_QUIET and the association would be denied by the kernel. This solution adds a global RRM capability, that tells user space that it can request RRM capabilities IE publishment without any specific feature support in the kernel. Signed-off-by: Beni Lev Signed-off-by: Emmanuel Grumbach Signed-off-by: Johannes Berg --- include/uapi/linux/nl80211.h | 8 ++++++++ net/wireless/nl80211.c | 18 +++++++++++------- 2 files changed, 19 insertions(+), 7 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/nl80211.h b/include/uapi/linux/nl80211.h index 7758969a2a8e..5a30a7563633 100644 --- a/include/uapi/linux/nl80211.h +++ b/include/uapi/linux/nl80211.h @@ -1727,6 +1727,8 @@ enum nl80211_commands { * underlying device supports these minimal RRM features: * %NL80211_FEATURE_DS_PARAM_SET_IE_IN_PROBES, * %NL80211_FEATURE_QUIET, + * Or, if global RRM is supported, see: + * %NL80211_EXT_FEATURE_RRM * If this flag is used, driver must add the Power Capabilities IE to the * association request. In addition, it must also set the RRM capability * flag in the association request's Capability Info field. @@ -4402,12 +4404,18 @@ enum nl80211_feature_flags { /** * enum nl80211_ext_feature_index - bit index of extended features. * @NL80211_EXT_FEATURE_VHT_IBSS: This driver supports IBSS with VHT datarates. + * @NL80211_EXT_FEATURE_RRM: This driver supports RRM. When featured, user can + * can request to use RRM (see %NL80211_ATTR_USE_RRM) with + * %NL80211_CMD_ASSOCIATE and %NL80211_CMD_CONNECT requests, which will set + * the ASSOC_REQ_USE_RRM flag in the association request even if + * NL80211_FEATURE_QUIET is not advertized. * * @NUM_NL80211_EXT_FEATURES: number of extended features. * @MAX_NL80211_EXT_FEATURES: highest extended feature index. */ enum nl80211_ext_feature_index { NL80211_EXT_FEATURE_VHT_IBSS, + NL80211_EXT_FEATURE_RRM, /* add new features before the definition below */ NUM_NL80211_EXT_FEATURES, diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c index 268cb493f6a5..90890f183c0e 100644 --- a/net/wireless/nl80211.c +++ b/net/wireless/nl80211.c @@ -3,7 +3,7 @@ * * Copyright 2006-2010 Johannes Berg * Copyright 2013-2014 Intel Mobile Communications GmbH - * Copyright 2015 Intel Deutschland GmbH + * Copyright 2015-2016 Intel Deutschland GmbH */ #include @@ -7286,9 +7286,11 @@ static int nl80211_associate(struct sk_buff *skb, struct genl_info *info) } if (nla_get_flag(info->attrs[NL80211_ATTR_USE_RRM])) { - if (!(rdev->wiphy.features & - NL80211_FEATURE_DS_PARAM_SET_IE_IN_PROBES) || - !(rdev->wiphy.features & NL80211_FEATURE_QUIET)) + if (!((rdev->wiphy.features & + NL80211_FEATURE_DS_PARAM_SET_IE_IN_PROBES) && + (rdev->wiphy.features & NL80211_FEATURE_QUIET)) && + !wiphy_ext_feature_isset(&rdev->wiphy, + NL80211_EXT_FEATURE_RRM)) return -EINVAL; req.flags |= ASSOC_REQ_USE_RRM; } @@ -7976,9 +7978,11 @@ static int nl80211_connect(struct sk_buff *skb, struct genl_info *info) } if (nla_get_flag(info->attrs[NL80211_ATTR_USE_RRM])) { - if (!(rdev->wiphy.features & - NL80211_FEATURE_DS_PARAM_SET_IE_IN_PROBES) || - !(rdev->wiphy.features & NL80211_FEATURE_QUIET)) { + if (!((rdev->wiphy.features & + NL80211_FEATURE_DS_PARAM_SET_IE_IN_PROBES) && + (rdev->wiphy.features & NL80211_FEATURE_QUIET)) && + !wiphy_ext_feature_isset(&rdev->wiphy, + NL80211_EXT_FEATURE_RRM)) { kzfree(connkeys); return -EINVAL; } -- cgit v1.3-18-gd494 From f1705ec197e705b79ea40fe7a2cc5acfa1d3bfac Mon Sep 17 00:00:00 2001 From: David Ahern Date: Wed, 24 Feb 2016 09:25:37 -0800 Subject: net: ipv6: Make address flushing on ifdown optional Currently, all ipv6 addresses are flushed when the interface is configured down, including global, static addresses: $ ip -6 addr show dev eth1 3: eth1: mtu 1500 state UP qlen 1000 inet6 2100:1::2/120 scope global valid_lft forever preferred_lft forever inet6 fe80::e0:f9ff:fe79:34bd/64 scope link valid_lft forever preferred_lft forever $ ip link set dev eth1 down $ ip -6 addr show dev eth1 << nothing; all addresses have been flushed>> Add a new sysctl to make this behavior optional. The new setting defaults to flush all addresses to maintain backwards compatibility. When the set global addresses with no expire times are not flushed on an admin down. The sysctl is per-interface or system-wide for all interfaces $ sysctl -w net.ipv6.conf.eth1.keep_addr_on_down=1 or $ sysctl -w net.ipv6.conf.all.keep_addr_on_down=1 Will keep addresses on eth1 on an admin down. $ ip -6 addr show dev eth1 3: eth1: mtu 1500 state UP qlen 1000 inet6 2100:1::2/120 scope global valid_lft forever preferred_lft forever inet6 fe80::e0:f9ff:fe79:34bd/64 scope link valid_lft forever preferred_lft forever $ ip link set dev eth1 down $ ip -6 addr show dev eth1 3: eth1: mtu 1500 state DOWN qlen 1000 inet6 2100:1::2/120 scope global tentative valid_lft forever preferred_lft forever inet6 fe80::e0:f9ff:fe79:34bd/64 scope link tentative valid_lft forever preferred_lft forever Signed-off-by: David Ahern Signed-off-by: David S. Miller --- Documentation/networking/ip-sysctl.txt | 9 +++ include/linux/ipv6.h | 1 + include/uapi/linux/ipv6.h | 1 + net/ipv6/addrconf.c | 136 +++++++++++++++++++++++++++++---- 4 files changed, 132 insertions(+), 15 deletions(-) (limited to 'include/uapi/linux') diff --git a/Documentation/networking/ip-sysctl.txt b/Documentation/networking/ip-sysctl.txt index 24ce97f42d35..d5df40c75aa4 100644 --- a/Documentation/networking/ip-sysctl.txt +++ b/Documentation/networking/ip-sysctl.txt @@ -1563,6 +1563,15 @@ temp_prefered_lft - INTEGER Preferred lifetime (in seconds) for temporary addresses. Default: 86400 (1 day) +keep_addr_on_down - INTEGER + Keep all IPv6 addresses on an interface down event. If set static + global addresses with no expiration time are not flushed. + >0 : enabled + 0 : system default + <0 : disabled + + Default: 0 (addresses are removed) + max_desync_factor - INTEGER Maximum value for DESYNC_FACTOR, which is a random value that ensures that clients don't synchronize with each diff --git a/include/linux/ipv6.h b/include/linux/ipv6.h index 4b2267e1b7c3..7edc14fb66b6 100644 --- a/include/linux/ipv6.h +++ b/include/linux/ipv6.h @@ -62,6 +62,7 @@ struct ipv6_devconf { struct in6_addr secret; } stable_secret; __s32 use_oif_addrs_only; + __s32 keep_addr_on_down; void *sysctl; }; diff --git a/include/uapi/linux/ipv6.h b/include/uapi/linux/ipv6.h index ec117b65d5a5..395876060f50 100644 --- a/include/uapi/linux/ipv6.h +++ b/include/uapi/linux/ipv6.h @@ -176,6 +176,7 @@ enum { DEVCONF_IGNORE_ROUTES_WITH_LINKDOWN, DEVCONF_DROP_UNICAST_IN_L2_MULTICAST, DEVCONF_DROP_UNSOLICITED_NA, + DEVCONF_KEEP_ADDR_ON_DOWN, DEVCONF_MAX }; diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c index 4751f8922362..a2d6f6c242af 100644 --- a/net/ipv6/addrconf.c +++ b/net/ipv6/addrconf.c @@ -216,6 +216,7 @@ static struct ipv6_devconf ipv6_devconf __read_mostly = { }, .use_oif_addrs_only = 0, .ignore_routes_with_linkdown = 0, + .keep_addr_on_down = 0, }; static struct ipv6_devconf ipv6_devconf_dflt __read_mostly = { @@ -260,6 +261,7 @@ static struct ipv6_devconf ipv6_devconf_dflt __read_mostly = { }, .use_oif_addrs_only = 0, .ignore_routes_with_linkdown = 0, + .keep_addr_on_down = 0, }; /* Check if a valid qdisc is available */ @@ -3168,6 +3170,55 @@ static void addrconf_gre_config(struct net_device *dev) } #endif +static int fixup_permanent_addr(struct inet6_dev *idev, + struct inet6_ifaddr *ifp) +{ + if (!ifp->rt) { + struct rt6_info *rt; + + rt = addrconf_dst_alloc(idev, &ifp->addr, false); + if (unlikely(IS_ERR(rt))) + return PTR_ERR(rt); + + ifp->rt = rt; + } + + if (!(ifp->flags & IFA_F_NOPREFIXROUTE)) { + addrconf_prefix_route(&ifp->addr, ifp->prefix_len, + idev->dev, 0, 0); + } + + addrconf_dad_start(ifp); + + return 0; +} + +static void addrconf_permanent_addr(struct net_device *dev) +{ + struct inet6_ifaddr *ifp, *tmp; + struct inet6_dev *idev; + + idev = __in6_dev_get(dev); + if (!idev) + return; + + write_lock_bh(&idev->lock); + + list_for_each_entry_safe(ifp, tmp, &idev->addr_list, if_list) { + if ((ifp->flags & IFA_F_PERMANENT) && + fixup_permanent_addr(idev, ifp) < 0) { + write_unlock_bh(&idev->lock); + ipv6_del_addr(ifp); + write_lock_bh(&idev->lock); + + net_info_ratelimited("%s: Failed to add prefix route for address %pI6c; dropping\n", + idev->dev->name, &ifp->addr); + } + } + + write_unlock_bh(&idev->lock); +} + static int addrconf_notify(struct notifier_block *this, unsigned long event, void *ptr) { @@ -3253,6 +3304,9 @@ static int addrconf_notify(struct notifier_block *this, unsigned long event, run_pending = 1; } + /* restore routes for permanent addresses */ + addrconf_permanent_addr(dev); + switch (dev->type) { #if IS_ENABLED(CONFIG_IPV6_SIT) case ARPHRD_SIT: @@ -3356,7 +3410,10 @@ static int addrconf_ifdown(struct net_device *dev, int how) { struct net *net = dev_net(dev); struct inet6_dev *idev; - struct inet6_ifaddr *ifa; + struct inet6_ifaddr *ifa, *tmp; + struct list_head del_list; + int _keep_addr; + bool keep_addr; int state, i; ASSERT_RTNL(); @@ -3383,6 +3440,16 @@ static int addrconf_ifdown(struct net_device *dev, int how) } + /* aggregate the system setting and interface setting */ + _keep_addr = net->ipv6.devconf_all->keep_addr_on_down; + if (!_keep_addr) + _keep_addr = idev->cnf.keep_addr_on_down; + + /* combine the user config with event to determine if permanent + * addresses are to be removed from address hash table + */ + keep_addr = !(how || _keep_addr <= 0); + /* Step 2: clear hash table */ for (i = 0; i < IN6_ADDR_HSIZE; i++) { struct hlist_head *h = &inet6_addr_lst[i]; @@ -3391,9 +3458,15 @@ static int addrconf_ifdown(struct net_device *dev, int how) restart: hlist_for_each_entry_rcu(ifa, h, addr_lst) { if (ifa->idev == idev) { - hlist_del_init_rcu(&ifa->addr_lst); addrconf_del_dad_work(ifa); - goto restart; + /* combined flag + permanent flag decide if + * address is retained on a down event + */ + if (!keep_addr || + !(ifa->flags & IFA_F_PERMANENT)) { + hlist_del_init_rcu(&ifa->addr_lst); + goto restart; + } } } spin_unlock_bh(&addrconf_hash_lock); @@ -3427,31 +3500,53 @@ restart: write_lock_bh(&idev->lock); } - while (!list_empty(&idev->addr_list)) { - ifa = list_first_entry(&idev->addr_list, - struct inet6_ifaddr, if_list); - addrconf_del_dad_work(ifa); + /* re-combine the user config with event to determine if permanent + * addresses are to be removed from the interface list + */ + keep_addr = (!how && _keep_addr > 0); - list_del(&ifa->if_list); + INIT_LIST_HEAD(&del_list); + list_for_each_entry_safe(ifa, tmp, &idev->addr_list, if_list) { + addrconf_del_dad_work(ifa); write_unlock_bh(&idev->lock); - spin_lock_bh(&ifa->lock); - state = ifa->state; - ifa->state = INET6_IFADDR_STATE_DEAD; + + if (keep_addr && (ifa->flags & IFA_F_PERMANENT)) { + /* set state to skip the notifier below */ + state = INET6_IFADDR_STATE_DEAD; + ifa->state = 0; + if (!(ifa->flags & IFA_F_NODAD)) + ifa->flags |= IFA_F_TENTATIVE; + } else { + state = ifa->state; + ifa->state = INET6_IFADDR_STATE_DEAD; + + list_del(&ifa->if_list); + list_add(&ifa->if_list, &del_list); + } + spin_unlock_bh(&ifa->lock); if (state != INET6_IFADDR_STATE_DEAD) { __ipv6_ifa_notify(RTM_DELADDR, ifa); inet6addr_notifier_call_chain(NETDEV_DOWN, ifa); } - in6_ifa_put(ifa); write_lock_bh(&idev->lock); } write_unlock_bh(&idev->lock); + /* now clean up addresses to be removed */ + while (!list_empty(&del_list)) { + ifa = list_first_entry(&del_list, + struct inet6_ifaddr, if_list); + list_del(&ifa->if_list); + + in6_ifa_put(ifa); + } + /* Step 5: Discard anycast and multicast list */ if (how) { ipv6_ac_destroy_dev(idev); @@ -4716,6 +4811,7 @@ static inline void ipv6_store_devconf(struct ipv6_devconf *cnf, array[DEVCONF_USE_OIF_ADDRS_ONLY] = cnf->use_oif_addrs_only; array[DEVCONF_DROP_UNICAST_IN_L2_MULTICAST] = cnf->drop_unicast_in_l2_multicast; array[DEVCONF_DROP_UNSOLICITED_NA] = cnf->drop_unsolicited_na; + array[DEVCONF_KEEP_ADDR_ON_DOWN] = cnf->keep_addr_on_down; } static inline size_t inet6_ifla6_size(void) @@ -5197,10 +5293,12 @@ static void __ipv6_ifa_notify(int event, struct inet6_ifaddr *ifp) if (rt) ip6_del_rt(rt); } - dst_hold(&ifp->rt->dst); - - ip6_del_rt(ifp->rt); + if (ifp->rt) { + dst_hold(&ifp->rt->dst); + ip6_del_rt(ifp->rt); + ifp->rt = NULL; + } rt_genid_bump_ipv6(net); break; } @@ -5803,6 +5901,14 @@ static struct addrconf_sysctl_table .mode = 0644, .proc_handler = proc_dointvec, }, + { + .procname = "keep_addr_on_down", + .data = &ipv6_devconf.keep_addr_on_down, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec, + + }, { /* sentinel */ } -- cgit v1.3-18-gd494 From 3f1ac7a700d039c61d8d8b99f28d605d489a60cf Mon Sep 17 00:00:00 2001 From: David Decotigny Date: Wed, 24 Feb 2016 10:57:59 -0800 Subject: net: ethtool: add new ETHTOOL_xLINKSETTINGS API This patch defines a new ETHTOOL_GLINKSETTINGS/SLINKSETTINGS API, handled by the new get_link_ksettings/set_link_ksettings callbacks. This API provides support for most legacy ethtool_cmd fields, adds support for larger link mode masks (up to 4064 bits, variable length), and removes ethtool_cmd deprecated fields (transceiver/maxrxpkt/maxtxpkt). This API is deprecating the legacy ETHTOOL_GSET/SSET API and provides the following backward compatibility properties: - legacy ethtool with legacy drivers: no change, still using the get_settings/set_settings callbacks. - legacy ethtool with new get/set_link_ksettings drivers: the new driver callbacks are used, data internally converted to legacy ethtool_cmd. ETHTOOL_GSET will return only the 1st 32b of each link mode mask. ETHTOOL_SSET will fail if user tries to set the ethtool_cmd deprecated fields to non-0 (transceiver/maxrxpkt/maxtxpkt). A kernel warning is logged if driver sets higher bits. - future ethtool with legacy drivers: no change, still using the get_settings/set_settings callbacks, internally converted to new data structure. Deprecated fields (transceiver/maxrxpkt/maxtxpkt) will be ignored and seen as 0 from user space. Note that that "future" ethtool tool will not allow changes to these deprecated fields. - future ethtool with new drivers: direct call to the new callbacks. By "future" ethtool, what is meant is: - query: first try ETHTOOL_GLINKSETTINGS, and revert to ETHTOOL_GSET if fails - set: query first and remember which of ETHTOOL_GLINKSETTINGS or ETHTOOL_GSET was successful + if ETHTOOL_GLINKSETTINGS was successful, then change config with ETHTOOL_SLINKSETTINGS. A failure there is final (do not try ETHTOOL_SSET). + otherwise ETHTOOL_GSET was successful, change config with ETHTOOL_SSET. A failure there is final (do not try ETHTOOL_SLINKSETTINGS). The interaction user/kernel via the new API requires a small ETHTOOL_GLINKSETTINGS handshake first to agree on the length of the link mode bitmaps. If kernel doesn't agree with user, it returns the bitmap length it is expecting from user as a negative length (and cmd field is 0). When kernel and user agree, kernel returns valid info in all fields (ie. link mode length > 0 and cmd is ETHTOOL_GLINKSETTINGS). Data structure crossing user/kernel boundary is 32/64-bit agnostic. Converted internally to a legal kernel bitmap. The internal __ethtool_get_settings kernel helper will gradually be replaced by __ethtool_get_link_ksettings by the time the first "link_settings" drivers start to appear. So this patch doesn't change it, it will be removed before it needs to be changed. Signed-off-by: David Decotigny Signed-off-by: David S. Miller --- include/linux/ethtool.h | 91 ++++++++- include/uapi/linux/ethtool.h | 322 +++++++++++++++++++++++------- net/core/ethtool.c | 453 ++++++++++++++++++++++++++++++++++++++++++- 3 files changed, 786 insertions(+), 80 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/linux/ethtool.h b/include/linux/ethtool.h index 472d7d7b01c2..8a400a54c92e 100644 --- a/include/linux/ethtool.h +++ b/include/linux/ethtool.h @@ -12,6 +12,7 @@ #ifndef _LINUX_ETHTOOL_H #define _LINUX_ETHTOOL_H +#include #include #include @@ -40,9 +41,6 @@ struct compat_ethtool_rxnfc { #include -extern int __ethtool_get_settings(struct net_device *dev, - struct ethtool_cmd *cmd); - /** * enum ethtool_phys_id_state - indicator state for physical identification * @ETHTOOL_ID_INACTIVE: Physical ID indicator should be deactivated @@ -97,13 +95,74 @@ static inline u32 ethtool_rxfh_indir_default(u32 index, u32 n_rx_rings) return index % n_rx_rings; } +/* number of link mode bits/ulongs handled internally by kernel */ +#define __ETHTOOL_LINK_MODE_MASK_NBITS \ + (__ETHTOOL_LINK_MODE_LAST + 1) + +/* declare a link mode bitmap */ +#define __ETHTOOL_DECLARE_LINK_MODE_MASK(name) \ + DECLARE_BITMAP(name, __ETHTOOL_LINK_MODE_MASK_NBITS) + +/* drivers must ignore base.cmd and base.link_mode_masks_nwords + * fields, but they are allowed to overwrite them (will be ignored). + */ +struct ethtool_link_ksettings { + struct ethtool_link_settings base; + struct { + __ETHTOOL_DECLARE_LINK_MODE_MASK(supported); + __ETHTOOL_DECLARE_LINK_MODE_MASK(advertising); + __ETHTOOL_DECLARE_LINK_MODE_MASK(lp_advertising); + } link_modes; +}; + +/** + * ethtool_link_ksettings_zero_link_mode - clear link_ksettings link mode mask + * @ptr : pointer to struct ethtool_link_ksettings + * @name : one of supported/advertising/lp_advertising + */ +#define ethtool_link_ksettings_zero_link_mode(ptr, name) \ + bitmap_zero((ptr)->link_modes.name, __ETHTOOL_LINK_MODE_MASK_NBITS) + +/** + * ethtool_link_ksettings_add_link_mode - set bit in link_ksettings + * link mode mask + * @ptr : pointer to struct ethtool_link_ksettings + * @name : one of supported/advertising/lp_advertising + * @mode : one of the ETHTOOL_LINK_MODE_*_BIT + * (not atomic, no bound checking) + */ +#define ethtool_link_ksettings_add_link_mode(ptr, name, mode) \ + __set_bit(ETHTOOL_LINK_MODE_ ## mode ## _BIT, (ptr)->link_modes.name) + +/** + * ethtool_link_ksettings_test_link_mode - test bit in ksettings link mode mask + * @ptr : pointer to struct ethtool_link_ksettings + * @name : one of supported/advertising/lp_advertising + * @mode : one of the ETHTOOL_LINK_MODE_*_BIT + * (not atomic, no bound checking) + * + * Returns true/false. + */ +#define ethtool_link_ksettings_test_link_mode(ptr, name, mode) \ + test_bit(ETHTOOL_LINK_MODE_ ## mode ## _BIT, (ptr)->link_modes.name) + +extern int +__ethtool_get_link_ksettings(struct net_device *dev, + struct ethtool_link_ksettings *link_ksettings); + +/* DEPRECATED, use __ethtool_get_link_ksettings */ +extern int __ethtool_get_settings(struct net_device *dev, + struct ethtool_cmd *cmd); + /** * struct ethtool_ops - optional netdev operations - * @get_settings: Get various device settings including Ethernet link + * @get_settings: DEPRECATED, use %get_link_ksettings/%set_link_ksettings + * API. Get various device settings including Ethernet link * settings. The @cmd parameter is expected to have been cleared - * before get_settings is called. Returns a negative error code or - * zero. - * @set_settings: Set various device settings including Ethernet link + * before get_settings is called. Returns a negative error code + * or zero. + * @set_settings: DEPRECATED, use %get_link_ksettings/%set_link_ksettings + * API. Set various device settings including Ethernet link * settings. Returns a negative error code or zero. * @get_drvinfo: Report driver/device information. Should only set the * @driver, @version, @fw_version and @bus_info fields. If not @@ -211,6 +270,19 @@ static inline u32 ethtool_rxfh_indir_default(u32 index, u32 n_rx_rings) * a TX queue has this number, return -EINVAL. If only a RX queue or a TX * queue has this number, ignore the inapplicable fields. * Returns a negative error code or zero. + * @get_link_ksettings: When defined, takes precedence over the + * %get_settings method. Get various device settings + * including Ethernet link settings. The %cmd and + * %link_mode_masks_nwords fields should be ignored (use + * %__ETHTOOL_LINK_MODE_MASK_NBITS instead of the latter), any + * change to them will be overwritten by kernel. Returns a + * negative error code or zero. + * @set_link_ksettings: When defined, takes precedence over the + * %set_settings method. Set various device settings including + * Ethernet link settings. The %cmd and %link_mode_masks_nwords + * fields should be ignored (use %__ETHTOOL_LINK_MODE_MASK_NBITS + * instead of the latter), any change to them will be overwritten + * by kernel. Returns a negative error code or zero. * * All operations are optional (i.e. the function pointer may be set * to %NULL) and callers must take this into account. Callers must @@ -293,6 +365,9 @@ struct ethtool_ops { struct ethtool_coalesce *); int (*set_per_queue_coalesce)(struct net_device *, u32, struct ethtool_coalesce *); - + int (*get_link_ksettings)(struct net_device *, + struct ethtool_link_ksettings *); + int (*set_link_ksettings)(struct net_device *, + const struct ethtool_link_ksettings *); }; #endif /* _LINUX_ETHTOOL_H */ diff --git a/include/uapi/linux/ethtool.h b/include/uapi/linux/ethtool.h index f15ae02621a1..37fd6dc33de4 100644 --- a/include/uapi/linux/ethtool.h +++ b/include/uapi/linux/ethtool.h @@ -21,7 +21,8 @@ */ /** - * struct ethtool_cmd - link control and status + * struct ethtool_cmd - DEPRECATED, link control and status + * This structure is DEPRECATED, please use struct ethtool_link_settings. * @cmd: Command number = %ETHTOOL_GSET or %ETHTOOL_SSET * @supported: Bitmask of %SUPPORTED_* flags for the link modes, * physical connectors and other link features for which the @@ -1219,8 +1220,12 @@ struct ethtool_per_queue_op { }; /* CMDs currently supported */ -#define ETHTOOL_GSET 0x00000001 /* Get settings. */ -#define ETHTOOL_SSET 0x00000002 /* Set settings. */ +#define ETHTOOL_GSET 0x00000001 /* DEPRECATED, Get settings. + * Please use ETHTOOL_GLINKSETTINGS + */ +#define ETHTOOL_SSET 0x00000002 /* DEPRECATED, Set settings. + * Please use ETHTOOL_SLINKSETTINGS + */ #define ETHTOOL_GDRVINFO 0x00000003 /* Get driver info. */ #define ETHTOOL_GREGS 0x00000004 /* Get NIC registers. */ #define ETHTOOL_GWOL 0x00000005 /* Get wake-on-lan options. */ @@ -1302,73 +1307,139 @@ struct ethtool_per_queue_op { #define ETHTOOL_PERQUEUE 0x0000004b /* Set per queue options */ +#define ETHTOOL_GLINKSETTINGS 0x0000004c /* Get ethtool_link_settings */ +#define ETHTOOL_SLINKSETTINGS 0x0000004d /* Set ethtool_link_settings */ + + /* compatibility with older code */ #define SPARC_ETH_GSET ETHTOOL_GSET #define SPARC_ETH_SSET ETHTOOL_SSET -#define SUPPORTED_10baseT_Half (1 << 0) -#define SUPPORTED_10baseT_Full (1 << 1) -#define SUPPORTED_100baseT_Half (1 << 2) -#define SUPPORTED_100baseT_Full (1 << 3) -#define SUPPORTED_1000baseT_Half (1 << 4) -#define SUPPORTED_1000baseT_Full (1 << 5) -#define SUPPORTED_Autoneg (1 << 6) -#define SUPPORTED_TP (1 << 7) -#define SUPPORTED_AUI (1 << 8) -#define SUPPORTED_MII (1 << 9) -#define SUPPORTED_FIBRE (1 << 10) -#define SUPPORTED_BNC (1 << 11) -#define SUPPORTED_10000baseT_Full (1 << 12) -#define SUPPORTED_Pause (1 << 13) -#define SUPPORTED_Asym_Pause (1 << 14) -#define SUPPORTED_2500baseX_Full (1 << 15) -#define SUPPORTED_Backplane (1 << 16) -#define SUPPORTED_1000baseKX_Full (1 << 17) -#define SUPPORTED_10000baseKX4_Full (1 << 18) -#define SUPPORTED_10000baseKR_Full (1 << 19) -#define SUPPORTED_10000baseR_FEC (1 << 20) -#define SUPPORTED_20000baseMLD2_Full (1 << 21) -#define SUPPORTED_20000baseKR2_Full (1 << 22) -#define SUPPORTED_40000baseKR4_Full (1 << 23) -#define SUPPORTED_40000baseCR4_Full (1 << 24) -#define SUPPORTED_40000baseSR4_Full (1 << 25) -#define SUPPORTED_40000baseLR4_Full (1 << 26) -#define SUPPORTED_56000baseKR4_Full (1 << 27) -#define SUPPORTED_56000baseCR4_Full (1 << 28) -#define SUPPORTED_56000baseSR4_Full (1 << 29) -#define SUPPORTED_56000baseLR4_Full (1 << 30) - -#define ADVERTISED_10baseT_Half (1 << 0) -#define ADVERTISED_10baseT_Full (1 << 1) -#define ADVERTISED_100baseT_Half (1 << 2) -#define ADVERTISED_100baseT_Full (1 << 3) -#define ADVERTISED_1000baseT_Half (1 << 4) -#define ADVERTISED_1000baseT_Full (1 << 5) -#define ADVERTISED_Autoneg (1 << 6) -#define ADVERTISED_TP (1 << 7) -#define ADVERTISED_AUI (1 << 8) -#define ADVERTISED_MII (1 << 9) -#define ADVERTISED_FIBRE (1 << 10) -#define ADVERTISED_BNC (1 << 11) -#define ADVERTISED_10000baseT_Full (1 << 12) -#define ADVERTISED_Pause (1 << 13) -#define ADVERTISED_Asym_Pause (1 << 14) -#define ADVERTISED_2500baseX_Full (1 << 15) -#define ADVERTISED_Backplane (1 << 16) -#define ADVERTISED_1000baseKX_Full (1 << 17) -#define ADVERTISED_10000baseKX4_Full (1 << 18) -#define ADVERTISED_10000baseKR_Full (1 << 19) -#define ADVERTISED_10000baseR_FEC (1 << 20) -#define ADVERTISED_20000baseMLD2_Full (1 << 21) -#define ADVERTISED_20000baseKR2_Full (1 << 22) -#define ADVERTISED_40000baseKR4_Full (1 << 23) -#define ADVERTISED_40000baseCR4_Full (1 << 24) -#define ADVERTISED_40000baseSR4_Full (1 << 25) -#define ADVERTISED_40000baseLR4_Full (1 << 26) -#define ADVERTISED_56000baseKR4_Full (1 << 27) -#define ADVERTISED_56000baseCR4_Full (1 << 28) -#define ADVERTISED_56000baseSR4_Full (1 << 29) -#define ADVERTISED_56000baseLR4_Full (1 << 30) +/* Link mode bit indices */ +enum ethtool_link_mode_bit_indices { + ETHTOOL_LINK_MODE_10baseT_Half_BIT = 0, + ETHTOOL_LINK_MODE_10baseT_Full_BIT = 1, + ETHTOOL_LINK_MODE_100baseT_Half_BIT = 2, + ETHTOOL_LINK_MODE_100baseT_Full_BIT = 3, + ETHTOOL_LINK_MODE_1000baseT_Half_BIT = 4, + ETHTOOL_LINK_MODE_1000baseT_Full_BIT = 5, + ETHTOOL_LINK_MODE_Autoneg_BIT = 6, + ETHTOOL_LINK_MODE_TP_BIT = 7, + ETHTOOL_LINK_MODE_AUI_BIT = 8, + ETHTOOL_LINK_MODE_MII_BIT = 9, + ETHTOOL_LINK_MODE_FIBRE_BIT = 10, + ETHTOOL_LINK_MODE_BNC_BIT = 11, + ETHTOOL_LINK_MODE_10000baseT_Full_BIT = 12, + ETHTOOL_LINK_MODE_Pause_BIT = 13, + ETHTOOL_LINK_MODE_Asym_Pause_BIT = 14, + ETHTOOL_LINK_MODE_2500baseX_Full_BIT = 15, + ETHTOOL_LINK_MODE_Backplane_BIT = 16, + ETHTOOL_LINK_MODE_1000baseKX_Full_BIT = 17, + ETHTOOL_LINK_MODE_10000baseKX4_Full_BIT = 18, + ETHTOOL_LINK_MODE_10000baseKR_Full_BIT = 19, + ETHTOOL_LINK_MODE_10000baseR_FEC_BIT = 20, + ETHTOOL_LINK_MODE_20000baseMLD2_Full_BIT = 21, + ETHTOOL_LINK_MODE_20000baseKR2_Full_BIT = 22, + ETHTOOL_LINK_MODE_40000baseKR4_Full_BIT = 23, + ETHTOOL_LINK_MODE_40000baseCR4_Full_BIT = 24, + ETHTOOL_LINK_MODE_40000baseSR4_Full_BIT = 25, + ETHTOOL_LINK_MODE_40000baseLR4_Full_BIT = 26, + ETHTOOL_LINK_MODE_56000baseKR4_Full_BIT = 27, + ETHTOOL_LINK_MODE_56000baseCR4_Full_BIT = 28, + ETHTOOL_LINK_MODE_56000baseSR4_Full_BIT = 29, + ETHTOOL_LINK_MODE_56000baseLR4_Full_BIT = 30, + + /* Last allowed bit for __ETHTOOL_LINK_MODE_LEGACY_MASK is bit + * 31. Please do NOT define any SUPPORTED_* or ADVERTISED_* + * macro for bits > 31. The only way to use indices > 31 is to + * use the new ETHTOOL_GLINKSETTINGS/ETHTOOL_SLINKSETTINGS API. + */ + + __ETHTOOL_LINK_MODE_LAST + = ETHTOOL_LINK_MODE_56000baseLR4_Full_BIT, +}; + +#define __ETHTOOL_LINK_MODE_LEGACY_MASK(base_name) \ + (1UL << (ETHTOOL_LINK_MODE_ ## base_name ## _BIT)) + +/* DEPRECATED macros. Please migrate to + * ETHTOOL_GLINKSETTINGS/ETHTOOL_SLINKSETTINGS API. Please do NOT + * define any new SUPPORTED_* macro for bits > 31. + */ +#define SUPPORTED_10baseT_Half __ETHTOOL_LINK_MODE_LEGACY_MASK(10baseT_Half) +#define SUPPORTED_10baseT_Full __ETHTOOL_LINK_MODE_LEGACY_MASK(10baseT_Full) +#define SUPPORTED_100baseT_Half __ETHTOOL_LINK_MODE_LEGACY_MASK(100baseT_Half) +#define SUPPORTED_100baseT_Full __ETHTOOL_LINK_MODE_LEGACY_MASK(100baseT_Full) +#define SUPPORTED_1000baseT_Half __ETHTOOL_LINK_MODE_LEGACY_MASK(1000baseT_Half) +#define SUPPORTED_1000baseT_Full __ETHTOOL_LINK_MODE_LEGACY_MASK(1000baseT_Full) +#define SUPPORTED_Autoneg __ETHTOOL_LINK_MODE_LEGACY_MASK(Autoneg) +#define SUPPORTED_TP __ETHTOOL_LINK_MODE_LEGACY_MASK(TP) +#define SUPPORTED_AUI __ETHTOOL_LINK_MODE_LEGACY_MASK(AUI) +#define SUPPORTED_MII __ETHTOOL_LINK_MODE_LEGACY_MASK(MII) +#define SUPPORTED_FIBRE __ETHTOOL_LINK_MODE_LEGACY_MASK(FIBRE) +#define SUPPORTED_BNC __ETHTOOL_LINK_MODE_LEGACY_MASK(BNC) +#define SUPPORTED_10000baseT_Full __ETHTOOL_LINK_MODE_LEGACY_MASK(10000baseT_Full) +#define SUPPORTED_Pause __ETHTOOL_LINK_MODE_LEGACY_MASK(Pause) +#define SUPPORTED_Asym_Pause __ETHTOOL_LINK_MODE_LEGACY_MASK(Asym_Pause) +#define SUPPORTED_2500baseX_Full __ETHTOOL_LINK_MODE_LEGACY_MASK(2500baseX_Full) +#define SUPPORTED_Backplane __ETHTOOL_LINK_MODE_LEGACY_MASK(Backplane) +#define SUPPORTED_1000baseKX_Full __ETHTOOL_LINK_MODE_LEGACY_MASK(1000baseKX_Full) +#define SUPPORTED_10000baseKX4_Full __ETHTOOL_LINK_MODE_LEGACY_MASK(10000baseKX4_Full) +#define SUPPORTED_10000baseKR_Full __ETHTOOL_LINK_MODE_LEGACY_MASK(10000baseKR_Full) +#define SUPPORTED_10000baseR_FEC __ETHTOOL_LINK_MODE_LEGACY_MASK(10000baseR_FEC) +#define SUPPORTED_20000baseMLD2_Full __ETHTOOL_LINK_MODE_LEGACY_MASK(20000baseMLD2_Full) +#define SUPPORTED_20000baseKR2_Full __ETHTOOL_LINK_MODE_LEGACY_MASK(20000baseKR2_Full) +#define SUPPORTED_40000baseKR4_Full __ETHTOOL_LINK_MODE_LEGACY_MASK(40000baseKR4_Full) +#define SUPPORTED_40000baseCR4_Full __ETHTOOL_LINK_MODE_LEGACY_MASK(40000baseCR4_Full) +#define SUPPORTED_40000baseSR4_Full __ETHTOOL_LINK_MODE_LEGACY_MASK(40000baseSR4_Full) +#define SUPPORTED_40000baseLR4_Full __ETHTOOL_LINK_MODE_LEGACY_MASK(40000baseLR4_Full) +#define SUPPORTED_56000baseKR4_Full __ETHTOOL_LINK_MODE_LEGACY_MASK(56000baseKR4_Full) +#define SUPPORTED_56000baseCR4_Full __ETHTOOL_LINK_MODE_LEGACY_MASK(56000baseCR4_Full) +#define SUPPORTED_56000baseSR4_Full __ETHTOOL_LINK_MODE_LEGACY_MASK(56000baseSR4_Full) +#define SUPPORTED_56000baseLR4_Full __ETHTOOL_LINK_MODE_LEGACY_MASK(56000baseLR4_Full) +/* Please do not define any new SUPPORTED_* macro for bits > 31, see + * notice above. + */ + +/* + * DEPRECATED macros. Please migrate to + * ETHTOOL_GLINKSETTINGS/ETHTOOL_SLINKSETTINGS API. Please do NOT + * define any new ADERTISE_* macro for bits > 31. + */ +#define ADVERTISED_10baseT_Half __ETHTOOL_LINK_MODE_LEGACY_MASK(10baseT_Half) +#define ADVERTISED_10baseT_Full __ETHTOOL_LINK_MODE_LEGACY_MASK(10baseT_Full) +#define ADVERTISED_100baseT_Half __ETHTOOL_LINK_MODE_LEGACY_MASK(100baseT_Half) +#define ADVERTISED_100baseT_Full __ETHTOOL_LINK_MODE_LEGACY_MASK(100baseT_Full) +#define ADVERTISED_1000baseT_Half __ETHTOOL_LINK_MODE_LEGACY_MASK(1000baseT_Half) +#define ADVERTISED_1000baseT_Full __ETHTOOL_LINK_MODE_LEGACY_MASK(1000baseT_Full) +#define ADVERTISED_Autoneg __ETHTOOL_LINK_MODE_LEGACY_MASK(Autoneg) +#define ADVERTISED_TP __ETHTOOL_LINK_MODE_LEGACY_MASK(TP) +#define ADVERTISED_AUI __ETHTOOL_LINK_MODE_LEGACY_MASK(AUI) +#define ADVERTISED_MII __ETHTOOL_LINK_MODE_LEGACY_MASK(MII) +#define ADVERTISED_FIBRE __ETHTOOL_LINK_MODE_LEGACY_MASK(FIBRE) +#define ADVERTISED_BNC __ETHTOOL_LINK_MODE_LEGACY_MASK(BNC) +#define ADVERTISED_10000baseT_Full __ETHTOOL_LINK_MODE_LEGACY_MASK(10000baseT_Full) +#define ADVERTISED_Pause __ETHTOOL_LINK_MODE_LEGACY_MASK(Pause) +#define ADVERTISED_Asym_Pause __ETHTOOL_LINK_MODE_LEGACY_MASK(Asym_Pause) +#define ADVERTISED_2500baseX_Full __ETHTOOL_LINK_MODE_LEGACY_MASK(2500baseX_Full) +#define ADVERTISED_Backplane __ETHTOOL_LINK_MODE_LEGACY_MASK(Backplane) +#define ADVERTISED_1000baseKX_Full __ETHTOOL_LINK_MODE_LEGACY_MASK(1000baseKX_Full) +#define ADVERTISED_10000baseKX4_Full __ETHTOOL_LINK_MODE_LEGACY_MASK(10000baseKX4_Full) +#define ADVERTISED_10000baseKR_Full __ETHTOOL_LINK_MODE_LEGACY_MASK(10000baseKR_Full) +#define ADVERTISED_10000baseR_FEC __ETHTOOL_LINK_MODE_LEGACY_MASK(10000baseR_FEC) +#define ADVERTISED_20000baseMLD2_Full __ETHTOOL_LINK_MODE_LEGACY_MASK(20000baseMLD2_Full) +#define ADVERTISED_20000baseKR2_Full __ETHTOOL_LINK_MODE_LEGACY_MASK(20000baseKR2_Full) +#define ADVERTISED_40000baseKR4_Full __ETHTOOL_LINK_MODE_LEGACY_MASK(40000baseKR4_Full) +#define ADVERTISED_40000baseCR4_Full __ETHTOOL_LINK_MODE_LEGACY_MASK(40000baseCR4_Full) +#define ADVERTISED_40000baseSR4_Full __ETHTOOL_LINK_MODE_LEGACY_MASK(40000baseSR4_Full) +#define ADVERTISED_40000baseLR4_Full __ETHTOOL_LINK_MODE_LEGACY_MASK(40000baseLR4_Full) +#define ADVERTISED_56000baseKR4_Full __ETHTOOL_LINK_MODE_LEGACY_MASK(56000baseKR4_Full) +#define ADVERTISED_56000baseCR4_Full __ETHTOOL_LINK_MODE_LEGACY_MASK(56000baseCR4_Full) +#define ADVERTISED_56000baseSR4_Full __ETHTOOL_LINK_MODE_LEGACY_MASK(56000baseSR4_Full) +#define ADVERTISED_56000baseLR4_Full __ETHTOOL_LINK_MODE_LEGACY_MASK(56000baseLR4_Full) +/* Please do not define any new ADVERTISED_* macro for bits > 31, see + * notice above. + */ /* The following are all involved in forcing a particular link * mode for the device for setting things. When getting the @@ -1533,4 +1604,123 @@ enum ethtool_reset_flags { }; #define ETH_RESET_SHARED_SHIFT 16 + +/** + * struct ethtool_link_settings - link control and status + * + * IMPORTANT, Backward compatibility notice: When implementing new + * user-space tools, please first try %ETHTOOL_GLINKSETTINGS, and + * if it succeeds use %ETHTOOL_SLINKSETTINGS to change link + * settings; do not use %ETHTOOL_SSET if %ETHTOOL_GLINKSETTINGS + * succeeded: stick to %ETHTOOL_GLINKSETTINGS/%SLINKSETTINGS in + * that case. Conversely, if %ETHTOOL_GLINKSETTINGS fails, use + * %ETHTOOL_GSET to query and %ETHTOOL_SSET to change link + * settings; do not use %ETHTOOL_SLINKSETTINGS if + * %ETHTOOL_GLINKSETTINGS failed: stick to + * %ETHTOOL_GSET/%ETHTOOL_SSET in that case. + * + * @cmd: Command number = %ETHTOOL_GLINKSETTINGS or %ETHTOOL_SLINKSETTINGS + * @speed: Link speed (Mbps) + * @duplex: Duplex mode; one of %DUPLEX_* + * @port: Physical connector type; one of %PORT_* + * @phy_address: MDIO address of PHY (transceiver); 0 or 255 if not + * applicable. For clause 45 PHYs this is the PRTAD. + * @autoneg: Enable/disable autonegotiation and auto-detection; + * either %AUTONEG_DISABLE or %AUTONEG_ENABLE + * @mdio_support: Bitmask of %ETH_MDIO_SUPPORTS_* flags for the MDIO + * protocols supported by the interface; 0 if unknown. + * Read-only. + * @eth_tp_mdix: Ethernet twisted-pair MDI(-X) status; one of + * %ETH_TP_MDI_*. If the status is unknown or not applicable, the + * value will be %ETH_TP_MDI_INVALID. Read-only. + * @eth_tp_mdix_ctrl: Ethernet twisted pair MDI(-X) control; one of + * %ETH_TP_MDI_*. If MDI(-X) control is not implemented, reads + * yield %ETH_TP_MDI_INVALID and writes may be ignored or rejected. + * When written successfully, the link should be renegotiated if + * necessary. + * @link_mode_masks_nwords: Number of 32-bit words for each of the + * supported, advertising, lp_advertising link mode bitmaps. For + * %ETHTOOL_GLINKSETTINGS: on entry, number of words passed by user + * (>= 0); on return, if handshake in progress, negative if + * request size unsupported by kernel: absolute value indicates + * kernel recommended size and cmd field is 0, as well as all the + * other fields; otherwise (handshake completed), strictly + * positive to indicate size used by kernel and cmd field is + * %ETHTOOL_GLINKSETTINGS, all other fields populated by driver. For + * %ETHTOOL_SLINKSETTINGS: must be valid on entry, ie. a positive + * value returned previously by %ETHTOOL_GLINKSETTINGS, otherwise + * refused. For drivers: ignore this field (use kernel's + * __ETHTOOL_LINK_MODE_MASK_NBITS instead), any change to it will + * be overwritten by kernel. + * @supported: Bitmap with each bit meaning given by + * %ethtool_link_mode_bit_indices for the link modes, physical + * connectors and other link features for which the interface + * supports autonegotiation or auto-detection. Read-only. + * @advertising: Bitmap with each bit meaning given by + * %ethtool_link_mode_bit_indices for the link modes, physical + * connectors and other link features that are advertised through + * autonegotiation or enabled for auto-detection. + * @lp_advertising: Bitmap with each bit meaning given by + * %ethtool_link_mode_bit_indices for the link modes, and other + * link features that the link partner advertised through + * autonegotiation; 0 if unknown or not applicable. Read-only. + * + * If autonegotiation is disabled, the speed and @duplex represent the + * fixed link mode and are writable if the driver supports multiple + * link modes. If it is enabled then they are read-only; if the link + * is up they represent the negotiated link mode; if the link is down, + * the speed is 0, %SPEED_UNKNOWN or the highest enabled speed and + * @duplex is %DUPLEX_UNKNOWN or the best enabled duplex mode. + * + * Some hardware interfaces may have multiple PHYs and/or physical + * connectors fitted or do not allow the driver to detect which are + * fitted. For these interfaces @port and/or @phy_address may be + * writable, possibly dependent on @autoneg being %AUTONEG_DISABLE. + * Otherwise, attempts to write different values may be ignored or + * rejected. + * + * Deprecated %ethtool_cmd fields transceiver, maxtxpkt and maxrxpkt + * are not available in %ethtool_link_settings. Until all drivers are + * converted to ignore them or to the new %ethtool_link_settings API, + * for both queries and changes, users should always try + * %ETHTOOL_GLINKSETTINGS first, and if it fails with -ENOTSUPP stick + * only to %ETHTOOL_GSET and %ETHTOOL_SSET consistently. If it + * succeeds, then users should stick to %ETHTOOL_GLINKSETTINGS and + * %ETHTOOL_SLINKSETTINGS (which would support drivers implementing + * either %ethtool_cmd or %ethtool_link_settings). + * + * Users should assume that all fields not marked read-only are + * writable and subject to validation by the driver. They should use + * %ETHTOOL_GLINKSETTINGS to get the current values before making specific + * changes and then applying them with %ETHTOOL_SLINKSETTINGS. + * + * Drivers that implement %get_link_ksettings and/or + * %set_link_ksettings should ignore the @cmd + * and @link_mode_masks_nwords fields (any change to them overwritten + * by kernel), and rely only on kernel's internal + * %__ETHTOOL_LINK_MODE_MASK_NBITS and + * %ethtool_link_mode_mask_t. Drivers that implement + * %set_link_ksettings() should validate all fields other than @cmd + * and @link_mode_masks_nwords that are not described as read-only or + * deprecated, and must ignore all fields described as read-only. + */ +struct ethtool_link_settings { + __u32 cmd; + __u32 speed; + __u8 duplex; + __u8 port; + __u8 phy_address; + __u8 autoneg; + __u8 mdio_support; + __u8 eth_tp_mdix; + __u8 eth_tp_mdix_ctrl; + __s8 link_mode_masks_nwords; + __u32 reserved[8]; + __u32 link_mode_masks[0]; + /* layout of link_mode_masks fields: + * __u32 map_supported[link_mode_masks_nwords]; + * __u32 map_advertising[link_mode_masks_nwords]; + * __u32 map_lp_advertising[link_mode_masks_nwords]; + */ +}; #endif /* _UAPI_LINUX_ETHTOOL_H */ diff --git a/net/core/ethtool.c b/net/core/ethtool.c index 2406101002b1..edcec56ed228 100644 --- a/net/core/ethtool.c +++ b/net/core/ethtool.c @@ -387,6 +387,359 @@ static int __ethtool_set_flags(struct net_device *dev, u32 data) return 0; } +static void convert_legacy_u32_to_link_mode(unsigned long *dst, u32 legacy_u32) +{ + bitmap_zero(dst, __ETHTOOL_LINK_MODE_MASK_NBITS); + dst[0] = legacy_u32; +} + +/* return false if src had higher bits set. lower bits always updated. */ +static bool convert_link_mode_to_legacy_u32(u32 *legacy_u32, + const unsigned long *src) +{ + bool retval = true; + + /* TODO: following test will soon always be true */ + if (__ETHTOOL_LINK_MODE_MASK_NBITS > 32) { + __ETHTOOL_DECLARE_LINK_MODE_MASK(ext); + + bitmap_zero(ext, __ETHTOOL_LINK_MODE_MASK_NBITS); + bitmap_fill(ext, 32); + bitmap_complement(ext, ext, __ETHTOOL_LINK_MODE_MASK_NBITS); + if (bitmap_intersects(ext, src, + __ETHTOOL_LINK_MODE_MASK_NBITS)) { + /* src mask goes beyond bit 31 */ + retval = false; + } + } + *legacy_u32 = src[0]; + return retval; +} + +/* return false if legacy contained non-0 deprecated fields + * transceiver/maxtxpkt/maxrxpkt. rest of ksettings always updated + */ +static bool +convert_legacy_settings_to_link_ksettings( + struct ethtool_link_ksettings *link_ksettings, + const struct ethtool_cmd *legacy_settings) +{ + bool retval = true; + + memset(link_ksettings, 0, sizeof(*link_ksettings)); + + /* This is used to tell users that driver is still using these + * deprecated legacy fields, and they should not use + * %ETHTOOL_GLINKSETTINGS/%ETHTOOL_SLINKSETTINGS + */ + if (legacy_settings->transceiver || + legacy_settings->maxtxpkt || + legacy_settings->maxrxpkt) + retval = false; + + convert_legacy_u32_to_link_mode( + link_ksettings->link_modes.supported, + legacy_settings->supported); + convert_legacy_u32_to_link_mode( + link_ksettings->link_modes.advertising, + legacy_settings->advertising); + convert_legacy_u32_to_link_mode( + link_ksettings->link_modes.lp_advertising, + legacy_settings->lp_advertising); + link_ksettings->base.speed + = ethtool_cmd_speed(legacy_settings); + link_ksettings->base.duplex + = legacy_settings->duplex; + link_ksettings->base.port + = legacy_settings->port; + link_ksettings->base.phy_address + = legacy_settings->phy_address; + link_ksettings->base.autoneg + = legacy_settings->autoneg; + link_ksettings->base.mdio_support + = legacy_settings->mdio_support; + link_ksettings->base.eth_tp_mdix + = legacy_settings->eth_tp_mdix; + link_ksettings->base.eth_tp_mdix_ctrl + = legacy_settings->eth_tp_mdix_ctrl; + return retval; +} + +/* return false if ksettings link modes had higher bits + * set. legacy_settings always updated (best effort) + */ +static bool +convert_link_ksettings_to_legacy_settings( + struct ethtool_cmd *legacy_settings, + const struct ethtool_link_ksettings *link_ksettings) +{ + bool retval = true; + + memset(legacy_settings, 0, sizeof(*legacy_settings)); + /* this also clears the deprecated fields in legacy structure: + * __u8 transceiver; + * __u32 maxtxpkt; + * __u32 maxrxpkt; + */ + + retval &= convert_link_mode_to_legacy_u32( + &legacy_settings->supported, + link_ksettings->link_modes.supported); + retval &= convert_link_mode_to_legacy_u32( + &legacy_settings->advertising, + link_ksettings->link_modes.advertising); + retval &= convert_link_mode_to_legacy_u32( + &legacy_settings->lp_advertising, + link_ksettings->link_modes.lp_advertising); + ethtool_cmd_speed_set(legacy_settings, link_ksettings->base.speed); + legacy_settings->duplex + = link_ksettings->base.duplex; + legacy_settings->port + = link_ksettings->base.port; + legacy_settings->phy_address + = link_ksettings->base.phy_address; + legacy_settings->autoneg + = link_ksettings->base.autoneg; + legacy_settings->mdio_support + = link_ksettings->base.mdio_support; + legacy_settings->eth_tp_mdix + = link_ksettings->base.eth_tp_mdix; + legacy_settings->eth_tp_mdix_ctrl + = link_ksettings->base.eth_tp_mdix_ctrl; + return retval; +} + +/* number of 32-bit words to store the user's link mode bitmaps */ +#define __ETHTOOL_LINK_MODE_MASK_NU32 \ + DIV_ROUND_UP(__ETHTOOL_LINK_MODE_MASK_NBITS, 32) + +/* layout of the struct passed from/to userland */ +struct ethtool_link_usettings { + struct ethtool_link_settings base; + struct { + __u32 supported[__ETHTOOL_LINK_MODE_MASK_NU32]; + __u32 advertising[__ETHTOOL_LINK_MODE_MASK_NU32]; + __u32 lp_advertising[__ETHTOOL_LINK_MODE_MASK_NU32]; + } link_modes; +}; + +/* Internal kernel helper to query a device ethtool_link_settings. + * + * Backward compatibility note: for compatibility with legacy drivers + * that implement only the ethtool_cmd API, this has to work with both + * drivers implementing get_link_ksettings API and drivers + * implementing get_settings API. When drivers implement get_settings + * and report ethtool_cmd deprecated fields + * (transceiver/maxrxpkt/maxtxpkt), these fields are silently ignored + * because the resulting struct ethtool_link_settings does not report them. + */ +int __ethtool_get_link_ksettings(struct net_device *dev, + struct ethtool_link_ksettings *link_ksettings) +{ + int err; + struct ethtool_cmd cmd; + + ASSERT_RTNL(); + + if (dev->ethtool_ops->get_link_ksettings) { + memset(link_ksettings, 0, sizeof(*link_ksettings)); + return dev->ethtool_ops->get_link_ksettings(dev, + link_ksettings); + } + + /* driver doesn't support %ethtool_link_ksettings API. revert to + * legacy %ethtool_cmd API, unless it's not supported either. + * TODO: remove when ethtool_ops::get_settings disappears internally + */ + err = __ethtool_get_settings(dev, &cmd); + if (err < 0) + return err; + + /* we ignore deprecated fields transceiver/maxrxpkt/maxtxpkt + */ + convert_legacy_settings_to_link_ksettings(link_ksettings, &cmd); + return err; +} +EXPORT_SYMBOL(__ethtool_get_link_ksettings); + +/* convert ethtool_link_usettings in user space to a kernel internal + * ethtool_link_ksettings. return 0 on success, errno on error. + */ +static int load_link_ksettings_from_user(struct ethtool_link_ksettings *to, + const void __user *from) +{ + struct ethtool_link_usettings link_usettings; + + if (copy_from_user(&link_usettings, from, sizeof(link_usettings))) + return -EFAULT; + + memcpy(&to->base, &link_usettings.base, sizeof(to->base)); + bitmap_from_u32array(to->link_modes.supported, + __ETHTOOL_LINK_MODE_MASK_NBITS, + link_usettings.link_modes.supported, + __ETHTOOL_LINK_MODE_MASK_NU32); + bitmap_from_u32array(to->link_modes.advertising, + __ETHTOOL_LINK_MODE_MASK_NBITS, + link_usettings.link_modes.advertising, + __ETHTOOL_LINK_MODE_MASK_NU32); + bitmap_from_u32array(to->link_modes.lp_advertising, + __ETHTOOL_LINK_MODE_MASK_NBITS, + link_usettings.link_modes.lp_advertising, + __ETHTOOL_LINK_MODE_MASK_NU32); + + return 0; +} + +/* convert a kernel internal ethtool_link_ksettings to + * ethtool_link_usettings in user space. return 0 on success, errno on + * error. + */ +static int +store_link_ksettings_for_user(void __user *to, + const struct ethtool_link_ksettings *from) +{ + struct ethtool_link_usettings link_usettings; + + memcpy(&link_usettings.base, &from->base, sizeof(link_usettings)); + bitmap_to_u32array(link_usettings.link_modes.supported, + __ETHTOOL_LINK_MODE_MASK_NU32, + from->link_modes.supported, + __ETHTOOL_LINK_MODE_MASK_NBITS); + bitmap_to_u32array(link_usettings.link_modes.advertising, + __ETHTOOL_LINK_MODE_MASK_NU32, + from->link_modes.advertising, + __ETHTOOL_LINK_MODE_MASK_NBITS); + bitmap_to_u32array(link_usettings.link_modes.lp_advertising, + __ETHTOOL_LINK_MODE_MASK_NU32, + from->link_modes.lp_advertising, + __ETHTOOL_LINK_MODE_MASK_NBITS); + + if (copy_to_user(to, &link_usettings, sizeof(link_usettings))) + return -EFAULT; + + return 0; +} + +/* Query device for its ethtool_link_settings. + * + * Backward compatibility note: this function must fail when driver + * does not implement ethtool::get_link_ksettings, even if legacy + * ethtool_ops::get_settings is implemented. This tells new versions + * of ethtool that they should use the legacy API %ETHTOOL_GSET for + * this driver, so that they can correctly access the ethtool_cmd + * deprecated fields (transceiver/maxrxpkt/maxtxpkt), until no driver + * implements ethtool_ops::get_settings anymore. + */ +static int ethtool_get_link_ksettings(struct net_device *dev, + void __user *useraddr) +{ + int err = 0; + struct ethtool_link_ksettings link_ksettings; + + ASSERT_RTNL(); + + if (!dev->ethtool_ops->get_link_ksettings) + return -EOPNOTSUPP; + + /* handle bitmap nbits handshake */ + if (copy_from_user(&link_ksettings.base, useraddr, + sizeof(link_ksettings.base))) + return -EFAULT; + + if (__ETHTOOL_LINK_MODE_MASK_NU32 + != link_ksettings.base.link_mode_masks_nwords) { + /* wrong link mode nbits requested */ + memset(&link_ksettings, 0, sizeof(link_ksettings)); + /* keep cmd field reset to 0 */ + /* send back number of words required as negative val */ + compiletime_assert(__ETHTOOL_LINK_MODE_MASK_NU32 <= S8_MAX, + "need too many bits for link modes!"); + link_ksettings.base.link_mode_masks_nwords + = -((s8)__ETHTOOL_LINK_MODE_MASK_NU32); + + /* copy the base fields back to user, not the link + * mode bitmaps + */ + if (copy_to_user(useraddr, &link_ksettings.base, + sizeof(link_ksettings.base))) + return -EFAULT; + + return 0; + } + + /* handshake successful: user/kernel agree on + * link_mode_masks_nwords + */ + + memset(&link_ksettings, 0, sizeof(link_ksettings)); + err = dev->ethtool_ops->get_link_ksettings(dev, &link_ksettings); + if (err < 0) + return err; + + /* make sure we tell the right values to user */ + link_ksettings.base.cmd = ETHTOOL_GLINKSETTINGS; + link_ksettings.base.link_mode_masks_nwords + = __ETHTOOL_LINK_MODE_MASK_NU32; + + return store_link_ksettings_for_user(useraddr, &link_ksettings); +} + +/* Update device ethtool_link_settings. + * + * Backward compatibility note: this function must fail when driver + * does not implement ethtool::set_link_ksettings, even if legacy + * ethtool_ops::set_settings is implemented. This tells new versions + * of ethtool that they should use the legacy API %ETHTOOL_SSET for + * this driver, so that they can correctly update the ethtool_cmd + * deprecated fields (transceiver/maxrxpkt/maxtxpkt), until no driver + * implements ethtool_ops::get_settings anymore. + */ +static int ethtool_set_link_ksettings(struct net_device *dev, + void __user *useraddr) +{ + int err; + struct ethtool_link_ksettings link_ksettings; + + ASSERT_RTNL(); + + if (!dev->ethtool_ops->set_link_ksettings) + return -EOPNOTSUPP; + + /* make sure nbits field has expected value */ + if (copy_from_user(&link_ksettings.base, useraddr, + sizeof(link_ksettings.base))) + return -EFAULT; + + if (__ETHTOOL_LINK_MODE_MASK_NU32 + != link_ksettings.base.link_mode_masks_nwords) + return -EINVAL; + + /* copy the whole structure, now that we know it has expected + * format + */ + err = load_link_ksettings_from_user(&link_ksettings, useraddr); + if (err) + return err; + + /* re-check nwords field, just in case */ + if (__ETHTOOL_LINK_MODE_MASK_NU32 + != link_ksettings.base.link_mode_masks_nwords) + return -EINVAL; + + return dev->ethtool_ops->set_link_ksettings(dev, &link_ksettings); +} + +/* Internal kernel helper to query a device ethtool_cmd settings. + * + * Note about transition to ethtool_link_settings API: We do not need + * (or want) this function to support "dev" instances that implement + * the ethtool_link_settings API as we will update the drivers calling + * this function to call __ethtool_get_link_ksettings instead, before + * the first drivers implement ethtool_ops::get_link_ksettings. + * + * TODO 1: at least make this function static when no driver is using it + * TODO 2: remove when ethtool_ops::get_settings disappears internally + */ int __ethtool_get_settings(struct net_device *dev, struct ethtool_cmd *cmd) { ASSERT_RTNL(); @@ -400,30 +753,112 @@ int __ethtool_get_settings(struct net_device *dev, struct ethtool_cmd *cmd) } EXPORT_SYMBOL(__ethtool_get_settings); +static void +warn_incomplete_ethtool_legacy_settings_conversion(const char *details) +{ + char name[sizeof(current->comm)]; + + pr_info_once("warning: `%s' uses legacy ethtool link settings API, %s\n", + get_task_comm(name, current), details); +} + +/* Query device for its ethtool_cmd settings. + * + * Backward compatibility note: for compatibility with legacy ethtool, + * this has to work with both drivers implementing get_link_ksettings + * API and drivers implementing get_settings API. When drivers + * implement get_link_ksettings and report higher link mode bits, a + * kernel warning is logged once (with name of 1st driver/device) to + * recommend user to upgrade ethtool, but the command is successful + * (only the lower link mode bits reported back to user). + */ static int ethtool_get_settings(struct net_device *dev, void __user *useraddr) { - int err; struct ethtool_cmd cmd; - err = __ethtool_get_settings(dev, &cmd); - if (err < 0) - return err; + ASSERT_RTNL(); + + if (dev->ethtool_ops->get_link_ksettings) { + /* First, use link_ksettings API if it is supported */ + int err; + struct ethtool_link_ksettings link_ksettings; + + memset(&link_ksettings, 0, sizeof(link_ksettings)); + err = dev->ethtool_ops->get_link_ksettings(dev, + &link_ksettings); + if (err < 0) + return err; + if (!convert_link_ksettings_to_legacy_settings(&cmd, + &link_ksettings)) + warn_incomplete_ethtool_legacy_settings_conversion( + "link modes are only partially reported"); + + /* send a sensible cmd tag back to user */ + cmd.cmd = ETHTOOL_GSET; + } else { + int err; + /* TODO: return -EOPNOTSUPP when + * ethtool_ops::get_settings disappears internally + */ + + /* driver doesn't support %ethtool_link_ksettings + * API. revert to legacy %ethtool_cmd API, unless it's + * not supported either. + */ + err = __ethtool_get_settings(dev, &cmd); + if (err < 0) + return err; + } if (copy_to_user(useraddr, &cmd, sizeof(cmd))) return -EFAULT; + return 0; } +/* Update device link settings with given ethtool_cmd. + * + * Backward compatibility note: for compatibility with legacy ethtool, + * this has to work with both drivers implementing set_link_ksettings + * API and drivers implementing set_settings API. When drivers + * implement set_link_ksettings and user's request updates deprecated + * ethtool_cmd fields (transceiver/maxrxpkt/maxtxpkt), a kernel + * warning is logged once (with name of 1st driver/device) to + * recommend user to upgrade ethtool, and the request is rejected. + */ static int ethtool_set_settings(struct net_device *dev, void __user *useraddr) { struct ethtool_cmd cmd; - if (!dev->ethtool_ops->set_settings) - return -EOPNOTSUPP; + ASSERT_RTNL(); if (copy_from_user(&cmd, useraddr, sizeof(cmd))) return -EFAULT; + /* first, try new %ethtool_link_ksettings API. */ + if (dev->ethtool_ops->set_link_ksettings) { + struct ethtool_link_ksettings link_ksettings; + + if (!convert_legacy_settings_to_link_ksettings(&link_ksettings, + &cmd)) + return -EINVAL; + + link_ksettings.base.cmd = ETHTOOL_SLINKSETTINGS; + link_ksettings.base.link_mode_masks_nwords + = __ETHTOOL_LINK_MODE_MASK_NU32; + return dev->ethtool_ops->set_link_ksettings(dev, + &link_ksettings); + } + + /* legacy %ethtool_cmd API */ + + /* TODO: return -EOPNOTSUPP when ethtool_ops::get_settings + * disappears internally + */ + + if (!dev->ethtool_ops->set_settings) + return -EOPNOTSUPP; + return dev->ethtool_ops->set_settings(dev, &cmd); } @@ -2252,6 +2687,12 @@ int dev_ethtool(struct net *net, struct ifreq *ifr) case ETHTOOL_PERQUEUE: rc = ethtool_set_per_queue(dev, useraddr); break; + case ETHTOOL_GLINKSETTINGS: + rc = ethtool_get_link_ksettings(dev, useraddr); + break; + case ETHTOOL_SLINKSETTINGS: + rc = ethtool_set_link_ksettings(dev, useraddr); + break; default: rc = -EOPNOTSUPP; } -- cgit v1.3-18-gd494 From 9e8ce79cd711d4dfe09d8bba6822cd9bb7db96bd Mon Sep 17 00:00:00 2001 From: John Fastabend Date: Fri, 26 Feb 2016 07:54:39 -0800 Subject: net: sched: cls_u32 add bit to specify software only rules In the initial implementation the only way to stop a rule from being inserted into the hardware table was via the device feature flag. However this doesn't work well when working on an end host system where packets are expect to hit both the hardware and software datapaths. For example we can imagine a rule that will match an IP address and increment a field. If we install this rule in both hardware and software we may increment the field twice. To date we have only added support for the drop action so we have been able to ignore these cases. But as we extend the action support we will hit this example plus more such cases. Arguably these are not even corner cases in many working systems these cases will be common. To avoid forcing the driver to always abort (i.e. the above example) this patch adds a flag to add a rule in software only. A careful user can use this flag to build software and hardware datapaths that work together. One example we have found particularly useful is to use hardware resources to set the skb->mark on the skb when the match may be expensive to run in software but a mark lookup in a hash table is cheap. The idea here is hardware can do in one lookup what the u32 classifier may need to traverse multiple lists and hash tables to compute. The flag is only passed down on inserts. On deletion to avoid stale references in hardware we always try to remove a rule if it exists. The flags field is part of the classifier specific options. Although it is tempting to lift this into the generic structure doing this proves difficult do to how the tc netlink attributes are implemented along with how the dump/change routines are called. There is also precedence for putting seemingly generic pieces in the specific classifier options such as TCA_U32_POLICE, TCA_U32_ACT, etc. So although not ideal I've left FLAGS in the u32 options as well as it simplifies the code greatly and user space has already learned how to manage these bits ala 'tc' tool. Another thing if trying to update a rule we require the flags to be unchanged. This is to force user space, software u32 and the hardware u32 to keep in sync. Thanks to Simon Horman for catching this case. Signed-off-by: John Fastabend Acked-by: Jiri Pirko Signed-off-by: David S. Miller --- include/net/pkt_cls.h | 13 +++++++++++-- include/uapi/linux/pkt_cls.h | 1 + net/sched/cls_u32.c | 37 +++++++++++++++++++++++++++---------- 3 files changed, 39 insertions(+), 12 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/net/pkt_cls.h b/include/net/pkt_cls.h index 6096e96fb78b..bea14eee373e 100644 --- a/include/net/pkt_cls.h +++ b/include/net/pkt_cls.h @@ -392,12 +392,21 @@ struct tc_cls_u32_offload { }; }; -static inline bool tc_should_offload(struct net_device *dev) +/* tca flags definitions */ +#define TCA_CLS_FLAGS_SKIP_HW 1 + +static inline bool tc_should_offload(struct net_device *dev, u32 flags) { if (!(dev->features & NETIF_F_HW_TC)) return false; - return dev->netdev_ops->ndo_setup_tc; + if (flags & TCA_CLS_FLAGS_SKIP_HW) + return false; + + if (!dev->netdev_ops->ndo_setup_tc) + return false; + + return true; } #endif diff --git a/include/uapi/linux/pkt_cls.h b/include/uapi/linux/pkt_cls.h index 439873775d49..9874f5680926 100644 --- a/include/uapi/linux/pkt_cls.h +++ b/include/uapi/linux/pkt_cls.h @@ -172,6 +172,7 @@ enum { TCA_U32_INDEV, TCA_U32_PCNT, TCA_U32_MARK, + TCA_U32_FLAGS, __TCA_U32_MAX }; diff --git a/net/sched/cls_u32.c b/net/sched/cls_u32.c index 24e888b9b728..563cdad76448 100644 --- a/net/sched/cls_u32.c +++ b/net/sched/cls_u32.c @@ -59,6 +59,7 @@ struct tc_u_knode { #ifdef CONFIG_CLS_U32_PERF struct tc_u32_pcnt __percpu *pf; #endif + u32 flags; #ifdef CONFIG_CLS_U32_MARK u32 val; u32 mask; @@ -434,7 +435,7 @@ static void u32_remove_hw_knode(struct tcf_proto *tp, u32 handle) offload.type = TC_SETUP_CLSU32; offload.cls_u32 = &u32_offload; - if (tc_should_offload(dev)) { + if (tc_should_offload(dev, 0)) { offload.cls_u32->command = TC_CLSU32_DELETE_KNODE; offload.cls_u32->knode.handle = handle; dev->netdev_ops->ndo_setup_tc(dev, tp->q->handle, @@ -442,7 +443,9 @@ static void u32_remove_hw_knode(struct tcf_proto *tp, u32 handle) } } -static void u32_replace_hw_hnode(struct tcf_proto *tp, struct tc_u_hnode *h) +static void u32_replace_hw_hnode(struct tcf_proto *tp, + struct tc_u_hnode *h, + u32 flags) { struct net_device *dev = tp->q->dev_queue->dev; struct tc_cls_u32_offload u32_offload = {0}; @@ -451,7 +454,7 @@ static void u32_replace_hw_hnode(struct tcf_proto *tp, struct tc_u_hnode *h) offload.type = TC_SETUP_CLSU32; offload.cls_u32 = &u32_offload; - if (tc_should_offload(dev)) { + if (tc_should_offload(dev, flags)) { offload.cls_u32->command = TC_CLSU32_NEW_HNODE; offload.cls_u32->hnode.divisor = h->divisor; offload.cls_u32->hnode.handle = h->handle; @@ -471,7 +474,7 @@ static void u32_clear_hw_hnode(struct tcf_proto *tp, struct tc_u_hnode *h) offload.type = TC_SETUP_CLSU32; offload.cls_u32 = &u32_offload; - if (tc_should_offload(dev)) { + if (tc_should_offload(dev, 0)) { offload.cls_u32->command = TC_CLSU32_DELETE_HNODE; offload.cls_u32->hnode.divisor = h->divisor; offload.cls_u32->hnode.handle = h->handle; @@ -482,7 +485,9 @@ static void u32_clear_hw_hnode(struct tcf_proto *tp, struct tc_u_hnode *h) } } -static void u32_replace_hw_knode(struct tcf_proto *tp, struct tc_u_knode *n) +static void u32_replace_hw_knode(struct tcf_proto *tp, + struct tc_u_knode *n, + u32 flags) { struct net_device *dev = tp->q->dev_queue->dev; struct tc_cls_u32_offload u32_offload = {0}; @@ -491,7 +496,7 @@ static void u32_replace_hw_knode(struct tcf_proto *tp, struct tc_u_knode *n) offload.type = TC_SETUP_CLSU32; offload.cls_u32 = &u32_offload; - if (tc_should_offload(dev)) { + if (tc_should_offload(dev, flags)) { offload.cls_u32->command = TC_CLSU32_REPLACE_KNODE; offload.cls_u32->knode.handle = n->handle; offload.cls_u32->knode.fshift = n->fshift; @@ -679,6 +684,7 @@ static const struct nla_policy u32_policy[TCA_U32_MAX + 1] = { [TCA_U32_SEL] = { .len = sizeof(struct tc_u32_sel) }, [TCA_U32_INDEV] = { .type = NLA_STRING, .len = IFNAMSIZ }, [TCA_U32_MARK] = { .len = sizeof(struct tc_u32_mark) }, + [TCA_U32_FLAGS] = { .type = NLA_U32 }, }; static int u32_set_parms(struct net *net, struct tcf_proto *tp, @@ -786,6 +792,7 @@ static struct tc_u_knode *u32_init_knode(struct tcf_proto *tp, #endif new->fshift = n->fshift; new->res = n->res; + new->flags = n->flags; RCU_INIT_POINTER(new->ht_down, n->ht_down); /* bump reference count as long as we hold pointer to structure */ @@ -825,7 +832,7 @@ static int u32_change(struct net *net, struct sk_buff *in_skb, struct tc_u32_sel *s; struct nlattr *opt = tca[TCA_OPTIONS]; struct nlattr *tb[TCA_U32_MAX + 1]; - u32 htid; + u32 htid, flags = 0; int err; #ifdef CONFIG_CLS_U32_PERF size_t size; @@ -838,6 +845,9 @@ static int u32_change(struct net *net, struct sk_buff *in_skb, if (err < 0) return err; + if (tb[TCA_U32_FLAGS]) + flags = nla_get_u32(tb[TCA_U32_FLAGS]); + n = (struct tc_u_knode *)*arg; if (n) { struct tc_u_knode *new; @@ -845,6 +855,9 @@ static int u32_change(struct net *net, struct sk_buff *in_skb, if (TC_U32_KEY(n->handle) == 0) return -EINVAL; + if (n->flags != flags) + return -EINVAL; + new = u32_init_knode(tp, n); if (!new) return -ENOMEM; @@ -861,7 +874,7 @@ static int u32_change(struct net *net, struct sk_buff *in_skb, u32_replace_knode(tp, tp_c, new); tcf_unbind_filter(tp, &n->res); call_rcu(&n->rcu, u32_delete_key_rcu); - u32_replace_hw_knode(tp, new); + u32_replace_hw_knode(tp, new, flags); return 0; } @@ -889,7 +902,7 @@ static int u32_change(struct net *net, struct sk_buff *in_skb, rcu_assign_pointer(tp_c->hlist, ht); *arg = (unsigned long)ht; - u32_replace_hw_hnode(tp, ht); + u32_replace_hw_hnode(tp, ht, flags); return 0; } @@ -940,6 +953,7 @@ static int u32_change(struct net *net, struct sk_buff *in_skb, RCU_INIT_POINTER(n->ht_up, ht); n->handle = handle; n->fshift = s->hmask ? ffs(ntohl(s->hmask)) - 1 : 0; + n->flags = flags; tcf_exts_init(&n->exts, TCA_U32_ACT, TCA_U32_POLICE); n->tp = tp; @@ -972,7 +986,7 @@ static int u32_change(struct net *net, struct sk_buff *in_skb, RCU_INIT_POINTER(n->next, pins); rcu_assign_pointer(*ins, n); - u32_replace_hw_knode(tp, n); + u32_replace_hw_knode(tp, n, flags); *arg = (unsigned long)n; return 0; } @@ -1077,6 +1091,9 @@ static int u32_dump(struct net *net, struct tcf_proto *tp, unsigned long fh, nla_put_u32(skb, TCA_U32_LINK, ht_down->handle)) goto nla_put_failure; + if (n->flags && nla_put_u32(skb, TCA_U32_FLAGS, n->flags)) + goto nla_put_failure; + #ifdef CONFIG_CLS_U32_MARK if ((n->val || n->mask)) { struct tc_u32_mark mark = {.val = n->val, -- cgit v1.3-18-gd494 From bfcd3a46617209454cfc0947ab093e37fd1e84ef Mon Sep 17 00:00:00 2001 From: Jiri Pirko Date: Fri, 26 Feb 2016 17:32:23 +0100 Subject: Introduce devlink infrastructure Introduce devlink infrastructure for drivers to register and expose to userspace via generic Netlink interface. There are two basic objects defined: devlink - one instance for every "parent device", for example switch ASIC devlink port - one instance for every physical port of the device. This initial portion implements basic get/dump of objects to userspace. Also, port splitter and port type setting is implemented. Signed-off-by: Jiri Pirko Signed-off-by: David S. Miller --- MAINTAINERS | 8 + include/net/devlink.h | 140 ++++++++ include/uapi/linux/devlink.h | 72 +++++ net/Kconfig | 7 + net/core/Makefile | 1 + net/core/devlink.c | 738 +++++++++++++++++++++++++++++++++++++++++++ 6 files changed, 966 insertions(+) create mode 100644 include/net/devlink.h create mode 100644 include/uapi/linux/devlink.h create mode 100644 net/core/devlink.c (limited to 'include/uapi/linux') diff --git a/MAINTAINERS b/MAINTAINERS index 12b764f4c93c..e45682745263 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -3499,6 +3499,14 @@ F: include/linux/device-mapper.h F: include/linux/dm-*.h F: include/uapi/linux/dm-*.h +DEVLINK +M: Jiri Pirko +L: netdev@vger.kernel.org +S: Supported +F: net/core/devlink.c +F: include/net/devlink.h +F: include/uapi/linux/devlink.h + DIALOG SEMICONDUCTOR DRIVERS M: Support Opensource W: http://www.dialog-semiconductor.com/products diff --git a/include/net/devlink.h b/include/net/devlink.h new file mode 100644 index 000000000000..c37d257891d6 --- /dev/null +++ b/include/net/devlink.h @@ -0,0 +1,140 @@ +/* + * include/net/devlink.h - Network physical device Netlink interface + * Copyright (c) 2016 Mellanox Technologies. All rights reserved. + * Copyright (c) 2016 Jiri Pirko + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + */ +#ifndef _NET_DEVLINK_H_ +#define _NET_DEVLINK_H_ + +#include +#include +#include +#include +#include +#include +#include + +struct devlink_ops; + +struct devlink { + struct list_head list; + struct list_head port_list; + const struct devlink_ops *ops; + struct device *dev; + possible_net_t _net; + char priv[0] __aligned(NETDEV_ALIGN); +}; + +struct devlink_port { + struct list_head list; + struct devlink *devlink; + unsigned index; + bool registered; + enum devlink_port_type type; + enum devlink_port_type desired_type; + void *type_dev; + bool split; + u32 split_group; +}; + +struct devlink_ops { + size_t priv_size; + int (*port_type_set)(struct devlink_port *devlink_port, + enum devlink_port_type port_type); + int (*port_split)(struct devlink *devlink, unsigned int port_index, + unsigned int count); + int (*port_unsplit)(struct devlink *devlink, unsigned int port_index); +}; + +static inline void *devlink_priv(struct devlink *devlink) +{ + BUG_ON(!devlink); + return &devlink->priv; +} + +static inline struct devlink *priv_to_devlink(void *priv) +{ + BUG_ON(!priv); + return container_of(priv, struct devlink, priv); +} + +struct ib_device; + +#if IS_ENABLED(CONFIG_NET_DEVLINK) + +struct devlink *devlink_alloc(const struct devlink_ops *ops, size_t priv_size); +int devlink_register(struct devlink *devlink, struct device *dev); +void devlink_unregister(struct devlink *devlink); +void devlink_free(struct devlink *devlink); +int devlink_port_register(struct devlink *devlink, + struct devlink_port *devlink_port, + unsigned int port_index); +void devlink_port_unregister(struct devlink_port *devlink_port); +void devlink_port_type_eth_set(struct devlink_port *devlink_port, + struct net_device *netdev); +void devlink_port_type_ib_set(struct devlink_port *devlink_port, + struct ib_device *ibdev); +void devlink_port_type_clear(struct devlink_port *devlink_port); +void devlink_port_split_set(struct devlink_port *devlink_port, + u32 split_group); + +#else + +static inline struct devlink *devlink_alloc(const struct devlink_ops *ops, + size_t priv_size) +{ + return kzalloc(sizeof(struct devlink) + priv_size, GFP_KERNEL); +} + +static inline int devlink_register(struct devlink *devlink, struct device *dev) +{ + return 0; +} + +static inline void devlink_unregister(struct devlink *devlink) +{ +} + +static inline void devlink_free(struct devlink *devlink) +{ + kfree(devlink); +} + +static inline int devlink_port_register(struct devlink *devlink, + struct devlink_port *devlink_port, + unsigned int port_index) +{ + return 0; +} + +static inline void devlink_port_unregister(struct devlink_port *devlink_port) +{ +} + +static inline void devlink_port_type_eth_set(struct devlink_port *devlink_port, + struct net_device *netdev) +{ +} + +static inline void devlink_port_type_ib_set(struct devlink_port *devlink_port, + struct ib_device *ibdev) +{ +} + +static inline void devlink_port_type_clear(struct devlink_port *devlink_port) +{ +} + +static inline void devlink_port_split_set(struct devlink_port *devlink_port, + u32 split_group) +{ +} + +#endif + +#endif /* _NET_DEVLINK_H_ */ diff --git a/include/uapi/linux/devlink.h b/include/uapi/linux/devlink.h new file mode 100644 index 000000000000..c9fee5781eb1 --- /dev/null +++ b/include/uapi/linux/devlink.h @@ -0,0 +1,72 @@ +/* + * include/uapi/linux/devlink.h - Network physical device Netlink interface + * Copyright (c) 2016 Mellanox Technologies. All rights reserved. + * Copyright (c) 2016 Jiri Pirko + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + */ + +#ifndef _UAPI_LINUX_DEVLINK_H_ +#define _UAPI_LINUX_DEVLINK_H_ + +#define DEVLINK_GENL_NAME "devlink" +#define DEVLINK_GENL_VERSION 0x1 +#define DEVLINK_GENL_MCGRP_CONFIG_NAME "config" + +enum devlink_command { + /* don't change the order or add anything between, this is ABI! */ + DEVLINK_CMD_UNSPEC, + + DEVLINK_CMD_GET, /* can dump */ + DEVLINK_CMD_SET, + DEVLINK_CMD_NEW, + DEVLINK_CMD_DEL, + + DEVLINK_CMD_PORT_GET, /* can dump */ + DEVLINK_CMD_PORT_SET, + DEVLINK_CMD_PORT_NEW, + DEVLINK_CMD_PORT_DEL, + + DEVLINK_CMD_PORT_SPLIT, + DEVLINK_CMD_PORT_UNSPLIT, + + /* add new commands above here */ + + __DEVLINK_CMD_MAX, + DEVLINK_CMD_MAX = __DEVLINK_CMD_MAX - 1 +}; + +enum devlink_port_type { + DEVLINK_PORT_TYPE_NOTSET, + DEVLINK_PORT_TYPE_AUTO, + DEVLINK_PORT_TYPE_ETH, + DEVLINK_PORT_TYPE_IB, +}; + +enum devlink_attr { + /* don't change the order or add anything between, this is ABI! */ + DEVLINK_ATTR_UNSPEC, + + /* bus name + dev name together are a handle for devlink entity */ + DEVLINK_ATTR_BUS_NAME, /* string */ + DEVLINK_ATTR_DEV_NAME, /* string */ + + DEVLINK_ATTR_PORT_INDEX, /* u32 */ + DEVLINK_ATTR_PORT_TYPE, /* u16 */ + DEVLINK_ATTR_PORT_DESIRED_TYPE, /* u16 */ + DEVLINK_ATTR_PORT_NETDEV_IFINDEX, /* u32 */ + DEVLINK_ATTR_PORT_NETDEV_NAME, /* string */ + DEVLINK_ATTR_PORT_IBDEV_NAME, /* string */ + DEVLINK_ATTR_PORT_SPLIT_COUNT, /* u32 */ + DEVLINK_ATTR_PORT_SPLIT_GROUP, /* u32 */ + + /* add new attributes above here, update the policy in devlink.c */ + + __DEVLINK_ATTR_MAX, + DEVLINK_ATTR_MAX = __DEVLINK_ATTR_MAX - 1 +}; + +#endif /* _UAPI_LINUX_DEVLINK_H_ */ diff --git a/net/Kconfig b/net/Kconfig index b80efecfc1a0..6c9cfb0d7639 100644 --- a/net/Kconfig +++ b/net/Kconfig @@ -396,6 +396,13 @@ config DST_CACHE bool "dst cache" default n +config NET_DEVLINK + tristate "Network physical/parent device Netlink interface" + help + Network physical/parent device Netlink interface provides + infrastructure to support access to physical chip-wide config and + monitoring. + endif # if NET # Used by archs to tell that they support BPF_JIT diff --git a/net/core/Makefile b/net/core/Makefile index 7a8fb8aef992..014422e2561f 100644 --- a/net/core/Makefile +++ b/net/core/Makefile @@ -25,3 +25,4 @@ obj-$(CONFIG_CGROUP_NET_PRIO) += netprio_cgroup.o obj-$(CONFIG_CGROUP_NET_CLASSID) += netclassid_cgroup.o obj-$(CONFIG_LWTUNNEL) += lwtunnel.o obj-$(CONFIG_DST_CACHE) += dst_cache.o +obj-$(CONFIG_NET_DEVLINK) += devlink.o diff --git a/net/core/devlink.c b/net/core/devlink.c new file mode 100644 index 000000000000..590fa561cb7f --- /dev/null +++ b/net/core/devlink.c @@ -0,0 +1,738 @@ +/* + * net/core/devlink.c - Network physical/parent device Netlink interface + * + * Heavily inspired by net/wireless/ + * Copyright (c) 2016 Mellanox Technologies. All rights reserved. + * Copyright (c) 2016 Jiri Pirko + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + */ + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +static LIST_HEAD(devlink_list); + +/* devlink_mutex + * + * An overall lock guarding every operation coming from userspace. + * It also guards devlink devices list and it is taken when + * driver registers/unregisters it. + */ +static DEFINE_MUTEX(devlink_mutex); + +/* devlink_port_mutex + * + * Shared lock to guard lists of ports in all devlink devices. + */ +static DEFINE_MUTEX(devlink_port_mutex); + +static struct net *devlink_net(const struct devlink *devlink) +{ + return read_pnet(&devlink->_net); +} + +static void devlink_net_set(struct devlink *devlink, struct net *net) +{ + write_pnet(&devlink->_net, net); +} + +static struct devlink *devlink_get_from_attrs(struct net *net, + struct nlattr **attrs) +{ + struct devlink *devlink; + char *busname; + char *devname; + + if (!attrs[DEVLINK_ATTR_BUS_NAME] || !attrs[DEVLINK_ATTR_DEV_NAME]) + return ERR_PTR(-EINVAL); + + busname = nla_data(attrs[DEVLINK_ATTR_BUS_NAME]); + devname = nla_data(attrs[DEVLINK_ATTR_DEV_NAME]); + + list_for_each_entry(devlink, &devlink_list, list) { + if (strcmp(devlink->dev->bus->name, busname) == 0 && + strcmp(dev_name(devlink->dev), devname) == 0 && + net_eq(devlink_net(devlink), net)) + return devlink; + } + + return ERR_PTR(-ENODEV); +} + +static struct devlink *devlink_get_from_info(struct genl_info *info) +{ + return devlink_get_from_attrs(genl_info_net(info), info->attrs); +} + +static struct devlink_port *devlink_port_get_by_index(struct devlink *devlink, + int port_index) +{ + struct devlink_port *devlink_port; + + list_for_each_entry(devlink_port, &devlink->port_list, list) { + if (devlink_port->index == port_index) + return devlink_port; + } + return NULL; +} + +static bool devlink_port_index_exists(struct devlink *devlink, int port_index) +{ + return devlink_port_get_by_index(devlink, port_index); +} + +static struct devlink_port *devlink_port_get_from_attrs(struct devlink *devlink, + struct nlattr **attrs) +{ + if (attrs[DEVLINK_ATTR_PORT_INDEX]) { + u32 port_index = nla_get_u32(attrs[DEVLINK_ATTR_PORT_INDEX]); + struct devlink_port *devlink_port; + + devlink_port = devlink_port_get_by_index(devlink, port_index); + if (!devlink_port) + return ERR_PTR(-ENODEV); + return devlink_port; + } + return ERR_PTR(-EINVAL); +} + +static struct devlink_port *devlink_port_get_from_info(struct devlink *devlink, + struct genl_info *info) +{ + return devlink_port_get_from_attrs(devlink, info->attrs); +} + +#define DEVLINK_NL_FLAG_NEED_PORT BIT(0) + +static int devlink_nl_pre_doit(const struct genl_ops *ops, + struct sk_buff *skb, struct genl_info *info) +{ + struct devlink *devlink; + + mutex_lock(&devlink_mutex); + devlink = devlink_get_from_info(info); + if (IS_ERR(devlink)) { + mutex_unlock(&devlink_mutex); + return PTR_ERR(devlink); + } + info->user_ptr[0] = devlink; + if (ops->internal_flags & DEVLINK_NL_FLAG_NEED_PORT) { + struct devlink_port *devlink_port; + + mutex_lock(&devlink_port_mutex); + devlink_port = devlink_port_get_from_info(devlink, info); + if (IS_ERR(devlink_port)) { + mutex_unlock(&devlink_port_mutex); + mutex_unlock(&devlink_mutex); + return PTR_ERR(devlink_port); + } + info->user_ptr[1] = devlink_port; + } + return 0; +} + +static void devlink_nl_post_doit(const struct genl_ops *ops, + struct sk_buff *skb, struct genl_info *info) +{ + if (ops->internal_flags & DEVLINK_NL_FLAG_NEED_PORT) + mutex_unlock(&devlink_port_mutex); + mutex_unlock(&devlink_mutex); +} + +static struct genl_family devlink_nl_family = { + .id = GENL_ID_GENERATE, + .name = DEVLINK_GENL_NAME, + .version = DEVLINK_GENL_VERSION, + .maxattr = DEVLINK_ATTR_MAX, + .netnsok = true, + .pre_doit = devlink_nl_pre_doit, + .post_doit = devlink_nl_post_doit, +}; + +enum devlink_multicast_groups { + DEVLINK_MCGRP_CONFIG, +}; + +static const struct genl_multicast_group devlink_nl_mcgrps[] = { + [DEVLINK_MCGRP_CONFIG] = { .name = DEVLINK_GENL_MCGRP_CONFIG_NAME }, +}; + +static int devlink_nl_put_handle(struct sk_buff *msg, struct devlink *devlink) +{ + if (nla_put_string(msg, DEVLINK_ATTR_BUS_NAME, devlink->dev->bus->name)) + return -EMSGSIZE; + if (nla_put_string(msg, DEVLINK_ATTR_DEV_NAME, dev_name(devlink->dev))) + return -EMSGSIZE; + return 0; +} + +static int devlink_nl_fill(struct sk_buff *msg, struct devlink *devlink, + enum devlink_command cmd, u32 portid, + u32 seq, int flags) +{ + void *hdr; + + hdr = genlmsg_put(msg, portid, seq, &devlink_nl_family, flags, cmd); + if (!hdr) + return -EMSGSIZE; + + if (devlink_nl_put_handle(msg, devlink)) + goto nla_put_failure; + + genlmsg_end(msg, hdr); + return 0; + +nla_put_failure: + genlmsg_cancel(msg, hdr); + return -EMSGSIZE; +} + +static void devlink_notify(struct devlink *devlink, enum devlink_command cmd) +{ + struct sk_buff *msg; + int err; + + WARN_ON(cmd != DEVLINK_CMD_NEW && cmd != DEVLINK_CMD_DEL); + + msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); + if (!msg) + return; + + err = devlink_nl_fill(msg, devlink, cmd, 0, 0, 0); + if (err) { + nlmsg_free(msg); + return; + } + + genlmsg_multicast_netns(&devlink_nl_family, devlink_net(devlink), + msg, 0, DEVLINK_MCGRP_CONFIG, GFP_KERNEL); +} + +static int devlink_nl_port_fill(struct sk_buff *msg, struct devlink *devlink, + struct devlink_port *devlink_port, + enum devlink_command cmd, u32 portid, + u32 seq, int flags) +{ + void *hdr; + + hdr = genlmsg_put(msg, portid, seq, &devlink_nl_family, flags, cmd); + if (!hdr) + return -EMSGSIZE; + + if (devlink_nl_put_handle(msg, devlink)) + goto nla_put_failure; + if (nla_put_u32(msg, DEVLINK_ATTR_PORT_INDEX, devlink_port->index)) + goto nla_put_failure; + if (nla_put_u16(msg, DEVLINK_ATTR_PORT_TYPE, devlink_port->type)) + goto nla_put_failure; + if (devlink_port->desired_type != DEVLINK_PORT_TYPE_NOTSET && + nla_put_u16(msg, DEVLINK_ATTR_PORT_DESIRED_TYPE, + devlink_port->desired_type)) + goto nla_put_failure; + if (devlink_port->type == DEVLINK_PORT_TYPE_ETH) { + struct net_device *netdev = devlink_port->type_dev; + + if (netdev && + (nla_put_u32(msg, DEVLINK_ATTR_PORT_NETDEV_IFINDEX, + netdev->ifindex) || + nla_put_string(msg, DEVLINK_ATTR_PORT_NETDEV_NAME, + netdev->name))) + goto nla_put_failure; + } + if (devlink_port->type == DEVLINK_PORT_TYPE_IB) { + struct ib_device *ibdev = devlink_port->type_dev; + + if (ibdev && + nla_put_string(msg, DEVLINK_ATTR_PORT_IBDEV_NAME, + ibdev->name)) + goto nla_put_failure; + } + if (devlink_port->split && + nla_put_u32(msg, DEVLINK_ATTR_PORT_SPLIT_GROUP, + devlink_port->split_group)) + goto nla_put_failure; + + genlmsg_end(msg, hdr); + return 0; + +nla_put_failure: + genlmsg_cancel(msg, hdr); + return -EMSGSIZE; +} + +static void devlink_port_notify(struct devlink_port *devlink_port, + enum devlink_command cmd) +{ + struct devlink *devlink = devlink_port->devlink; + struct sk_buff *msg; + int err; + + if (!devlink_port->registered) + return; + + WARN_ON(cmd != DEVLINK_CMD_PORT_NEW && cmd != DEVLINK_CMD_PORT_DEL); + + msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); + if (!msg) + return; + + err = devlink_nl_port_fill(msg, devlink, devlink_port, cmd, 0, 0, 0); + if (err) { + nlmsg_free(msg); + return; + } + + genlmsg_multicast_netns(&devlink_nl_family, devlink_net(devlink), + msg, 0, DEVLINK_MCGRP_CONFIG, GFP_KERNEL); +} + +static int devlink_nl_cmd_get_doit(struct sk_buff *skb, struct genl_info *info) +{ + struct devlink *devlink = info->user_ptr[0]; + struct sk_buff *msg; + int err; + + msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); + if (!msg) + return -ENOMEM; + + err = devlink_nl_fill(msg, devlink, DEVLINK_CMD_NEW, + info->snd_portid, info->snd_seq, 0); + if (err) { + nlmsg_free(msg); + return err; + } + + return genlmsg_reply(msg, info); +} + +static int devlink_nl_cmd_get_dumpit(struct sk_buff *msg, + struct netlink_callback *cb) +{ + struct devlink *devlink; + int start = cb->args[0]; + int idx = 0; + int err; + + mutex_lock(&devlink_mutex); + list_for_each_entry(devlink, &devlink_list, list) { + if (!net_eq(devlink_net(devlink), sock_net(msg->sk))) + continue; + if (idx < start) { + idx++; + continue; + } + err = devlink_nl_fill(msg, devlink, DEVLINK_CMD_NEW, + NETLINK_CB(cb->skb).portid, + cb->nlh->nlmsg_seq, NLM_F_MULTI); + if (err) + goto out; + idx++; + } +out: + mutex_unlock(&devlink_mutex); + + cb->args[0] = idx; + return msg->len; +} + +static int devlink_nl_cmd_port_get_doit(struct sk_buff *skb, + struct genl_info *info) +{ + struct devlink *devlink = info->user_ptr[0]; + struct devlink_port *devlink_port = info->user_ptr[1]; + struct sk_buff *msg; + int err; + + msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); + if (!msg) + return -ENOMEM; + + err = devlink_nl_port_fill(msg, devlink, devlink_port, + DEVLINK_CMD_PORT_NEW, + info->snd_portid, info->snd_seq, 0); + if (err) { + nlmsg_free(msg); + return err; + } + + return genlmsg_reply(msg, info); +} + +static int devlink_nl_cmd_port_get_dumpit(struct sk_buff *msg, + struct netlink_callback *cb) +{ + struct devlink *devlink; + struct devlink_port *devlink_port; + int start = cb->args[0]; + int idx = 0; + int err; + + mutex_lock(&devlink_mutex); + mutex_lock(&devlink_port_mutex); + list_for_each_entry(devlink, &devlink_list, list) { + if (!net_eq(devlink_net(devlink), sock_net(msg->sk))) + continue; + list_for_each_entry(devlink_port, &devlink->port_list, list) { + if (idx < start) { + idx++; + continue; + } + err = devlink_nl_port_fill(msg, devlink, devlink_port, + DEVLINK_CMD_NEW, + NETLINK_CB(cb->skb).portid, + cb->nlh->nlmsg_seq, + NLM_F_MULTI); + if (err) + goto out; + idx++; + } + } +out: + mutex_unlock(&devlink_port_mutex); + mutex_unlock(&devlink_mutex); + + cb->args[0] = idx; + return msg->len; +} + +static int devlink_port_type_set(struct devlink *devlink, + struct devlink_port *devlink_port, + enum devlink_port_type port_type) + +{ + int err; + + if (devlink->ops && devlink->ops->port_type_set) { + if (port_type == DEVLINK_PORT_TYPE_NOTSET) + return -EINVAL; + err = devlink->ops->port_type_set(devlink_port, port_type); + if (err) + return err; + devlink_port->desired_type = port_type; + devlink_port_notify(devlink_port, DEVLINK_CMD_PORT_NEW); + return 0; + } + return -EOPNOTSUPP; +} + +static int devlink_nl_cmd_port_set_doit(struct sk_buff *skb, + struct genl_info *info) +{ + struct devlink *devlink = info->user_ptr[0]; + struct devlink_port *devlink_port = info->user_ptr[1]; + int err; + + if (info->attrs[DEVLINK_ATTR_PORT_TYPE]) { + enum devlink_port_type port_type; + + port_type = nla_get_u16(info->attrs[DEVLINK_ATTR_PORT_TYPE]); + err = devlink_port_type_set(devlink, devlink_port, port_type); + if (err) + return err; + } + return 0; +} + +static int devlink_port_split(struct devlink *devlink, + u32 port_index, u32 count) + +{ + if (devlink->ops && devlink->ops->port_split) + return devlink->ops->port_split(devlink, port_index, count); + return -EOPNOTSUPP; +} + +static int devlink_nl_cmd_port_split_doit(struct sk_buff *skb, + struct genl_info *info) +{ + struct devlink *devlink = info->user_ptr[0]; + u32 port_index; + u32 count; + + if (!info->attrs[DEVLINK_ATTR_PORT_INDEX] || + !info->attrs[DEVLINK_ATTR_PORT_SPLIT_COUNT]) + return -EINVAL; + + port_index = nla_get_u32(info->attrs[DEVLINK_ATTR_PORT_INDEX]); + count = nla_get_u32(info->attrs[DEVLINK_ATTR_PORT_SPLIT_COUNT]); + return devlink_port_split(devlink, port_index, count); +} + +static int devlink_port_unsplit(struct devlink *devlink, u32 port_index) + +{ + if (devlink->ops && devlink->ops->port_unsplit) + return devlink->ops->port_unsplit(devlink, port_index); + return -EOPNOTSUPP; +} + +static int devlink_nl_cmd_port_unsplit_doit(struct sk_buff *skb, + struct genl_info *info) +{ + struct devlink *devlink = info->user_ptr[0]; + u32 port_index; + + if (!info->attrs[DEVLINK_ATTR_PORT_INDEX]) + return -EINVAL; + + port_index = nla_get_u32(info->attrs[DEVLINK_ATTR_PORT_INDEX]); + return devlink_port_unsplit(devlink, port_index); +} + +static const struct nla_policy devlink_nl_policy[DEVLINK_ATTR_MAX + 1] = { + [DEVLINK_ATTR_BUS_NAME] = { .type = NLA_NUL_STRING }, + [DEVLINK_ATTR_DEV_NAME] = { .type = NLA_NUL_STRING }, + [DEVLINK_ATTR_PORT_INDEX] = { .type = NLA_U32 }, + [DEVLINK_ATTR_PORT_TYPE] = { .type = NLA_U16 }, + [DEVLINK_ATTR_PORT_SPLIT_COUNT] = { .type = NLA_U32 }, +}; + +static const struct genl_ops devlink_nl_ops[] = { + { + .cmd = DEVLINK_CMD_GET, + .doit = devlink_nl_cmd_get_doit, + .dumpit = devlink_nl_cmd_get_dumpit, + .policy = devlink_nl_policy, + /* can be retrieved by unprivileged users */ + }, + { + .cmd = DEVLINK_CMD_PORT_GET, + .doit = devlink_nl_cmd_port_get_doit, + .dumpit = devlink_nl_cmd_port_get_dumpit, + .policy = devlink_nl_policy, + .internal_flags = DEVLINK_NL_FLAG_NEED_PORT, + /* can be retrieved by unprivileged users */ + }, + { + .cmd = DEVLINK_CMD_PORT_SET, + .doit = devlink_nl_cmd_port_set_doit, + .policy = devlink_nl_policy, + .flags = GENL_ADMIN_PERM, + .internal_flags = DEVLINK_NL_FLAG_NEED_PORT, + }, + { + .cmd = DEVLINK_CMD_PORT_SPLIT, + .doit = devlink_nl_cmd_port_split_doit, + .policy = devlink_nl_policy, + .flags = GENL_ADMIN_PERM, + }, + { + .cmd = DEVLINK_CMD_PORT_UNSPLIT, + .doit = devlink_nl_cmd_port_unsplit_doit, + .policy = devlink_nl_policy, + .flags = GENL_ADMIN_PERM, + }, +}; + +/** + * devlink_alloc - Allocate new devlink instance resources + * + * @ops: ops + * @priv_size: size of user private data + * + * Allocate new devlink instance resources, including devlink index + * and name. + */ +struct devlink *devlink_alloc(const struct devlink_ops *ops, size_t priv_size) +{ + struct devlink *devlink; + + devlink = kzalloc(sizeof(*devlink) + priv_size, GFP_KERNEL); + if (!devlink) + return NULL; + devlink->ops = ops; + devlink_net_set(devlink, &init_net); + INIT_LIST_HEAD(&devlink->port_list); + return devlink; +} +EXPORT_SYMBOL_GPL(devlink_alloc); + +/** + * devlink_register - Register devlink instance + * + * @devlink: devlink + */ +int devlink_register(struct devlink *devlink, struct device *dev) +{ + mutex_lock(&devlink_mutex); + devlink->dev = dev; + list_add_tail(&devlink->list, &devlink_list); + devlink_notify(devlink, DEVLINK_CMD_NEW); + mutex_unlock(&devlink_mutex); + return 0; +} +EXPORT_SYMBOL_GPL(devlink_register); + +/** + * devlink_unregister - Unregister devlink instance + * + * @devlink: devlink + */ +void devlink_unregister(struct devlink *devlink) +{ + mutex_lock(&devlink_mutex); + devlink_notify(devlink, DEVLINK_CMD_DEL); + list_del(&devlink->list); + mutex_unlock(&devlink_mutex); +} +EXPORT_SYMBOL_GPL(devlink_unregister); + +/** + * devlink_free - Free devlink instance resources + * + * @devlink: devlink + */ +void devlink_free(struct devlink *devlink) +{ + kfree(devlink); +} +EXPORT_SYMBOL_GPL(devlink_free); + +/** + * devlink_port_register - Register devlink port + * + * @devlink: devlink + * @devlink_port: devlink port + * @port_index + * + * Register devlink port with provided port index. User can use + * any indexing, even hw-related one. devlink_port structure + * is convenient to be embedded inside user driver private structure. + * Note that the caller should take care of zeroing the devlink_port + * structure. + */ +int devlink_port_register(struct devlink *devlink, + struct devlink_port *devlink_port, + unsigned int port_index) +{ + mutex_lock(&devlink_port_mutex); + if (devlink_port_index_exists(devlink, port_index)) { + mutex_unlock(&devlink_port_mutex); + return -EEXIST; + } + devlink_port->devlink = devlink; + devlink_port->index = port_index; + devlink_port->type = DEVLINK_PORT_TYPE_NOTSET; + devlink_port->registered = true; + list_add_tail(&devlink_port->list, &devlink->port_list); + mutex_unlock(&devlink_port_mutex); + devlink_port_notify(devlink_port, DEVLINK_CMD_PORT_NEW); + return 0; +} +EXPORT_SYMBOL_GPL(devlink_port_register); + +/** + * devlink_port_unregister - Unregister devlink port + * + * @devlink_port: devlink port + */ +void devlink_port_unregister(struct devlink_port *devlink_port) +{ + devlink_port_notify(devlink_port, DEVLINK_CMD_PORT_DEL); + mutex_lock(&devlink_port_mutex); + list_del(&devlink_port->list); + mutex_unlock(&devlink_port_mutex); +} +EXPORT_SYMBOL_GPL(devlink_port_unregister); + +static void __devlink_port_type_set(struct devlink_port *devlink_port, + enum devlink_port_type type, + void *type_dev) +{ + devlink_port->type = type; + devlink_port->type_dev = type_dev; + devlink_port_notify(devlink_port, DEVLINK_CMD_PORT_NEW); +} + +/** + * devlink_port_type_eth_set - Set port type to Ethernet + * + * @devlink_port: devlink port + * @netdev: related netdevice + */ +void devlink_port_type_eth_set(struct devlink_port *devlink_port, + struct net_device *netdev) +{ + return __devlink_port_type_set(devlink_port, + DEVLINK_PORT_TYPE_ETH, netdev); +} +EXPORT_SYMBOL_GPL(devlink_port_type_eth_set); + +/** + * devlink_port_type_ib_set - Set port type to InfiniBand + * + * @devlink_port: devlink port + * @ibdev: related IB device + */ +void devlink_port_type_ib_set(struct devlink_port *devlink_port, + struct ib_device *ibdev) +{ + return __devlink_port_type_set(devlink_port, + DEVLINK_PORT_TYPE_IB, ibdev); +} +EXPORT_SYMBOL_GPL(devlink_port_type_ib_set); + +/** + * devlink_port_type_clear - Clear port type + * + * @devlink_port: devlink port + */ +void devlink_port_type_clear(struct devlink_port *devlink_port) +{ + return __devlink_port_type_set(devlink_port, + DEVLINK_PORT_TYPE_NOTSET, NULL); +} +EXPORT_SYMBOL_GPL(devlink_port_type_clear); + +/** + * devlink_port_split_set - Set port is split + * + * @devlink_port: devlink port + * @split_group: split group - identifies group split port is part of + */ +void devlink_port_split_set(struct devlink_port *devlink_port, + u32 split_group) +{ + devlink_port->split = true; + devlink_port->split_group = split_group; + devlink_port_notify(devlink_port, DEVLINK_CMD_PORT_NEW); +} +EXPORT_SYMBOL_GPL(devlink_port_split_set); + +static int __init devlink_module_init(void) +{ + return genl_register_family_with_ops_groups(&devlink_nl_family, + devlink_nl_ops, + devlink_nl_mcgrps); +} + +static void __exit devlink_module_exit(void) +{ + genl_unregister_family(&devlink_nl_family); +} + +module_init(devlink_module_init); +module_exit(devlink_module_exit); + +MODULE_LICENSE("GPL v2"); +MODULE_AUTHOR("Jiri Pirko "); +MODULE_DESCRIPTION("Network physical device Netlink interface"); +MODULE_ALIAS_GENL_FAMILY(DEVLINK_GENL_NAME); -- cgit v1.3-18-gd494 From 7f0aec7a668419bdbff12de6e8016544f874e708 Mon Sep 17 00:00:00 2001 From: Nikolay Aleksandrov Date: Fri, 26 Feb 2016 21:20:01 +0100 Subject: bridge: mcast: use names for the different multicast_router types Using raw values makes it difficult to extend and also understand the code, give them names and do explicit per-option manipulation in br_multicast_set_port_router. Signed-off-by: Nikolay Aleksandrov Signed-off-by: David S. Miller --- include/uapi/linux/if_bridge.h | 7 +++++ net/bridge/br_multicast.c | 61 +++++++++++++++++++++++------------------- 2 files changed, 40 insertions(+), 28 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/if_bridge.h b/include/uapi/linux/if_bridge.h index 0890b217580d..e47f3bc7f323 100644 --- a/include/uapi/linux/if_bridge.h +++ b/include/uapi/linux/if_bridge.h @@ -177,6 +177,13 @@ enum { }; #define MDBA_MDB_EATTR_MAX (__MDBA_MDB_EATTR_MAX - 1) +/* multicast router types */ +enum { + MDB_RTR_TYPE_DISABLED, + MDB_RTR_TYPE_TEMP_QUERY, + MDB_RTR_TYPE_PERM, +}; + enum { MDBA_ROUTER_UNSPEC, MDBA_ROUTER_PORT, diff --git a/net/bridge/br_multicast.c b/net/bridge/br_multicast.c index 8b6e4249be1b..71c109b0943f 100644 --- a/net/bridge/br_multicast.c +++ b/net/bridge/br_multicast.c @@ -759,7 +759,7 @@ static void br_multicast_router_expired(unsigned long data) struct net_bridge *br = port->br; spin_lock(&br->multicast_lock); - if (port->multicast_router != 1 || + if (port->multicast_router != MDB_RTR_TYPE_TEMP_QUERY || timer_pending(&port->multicast_router_timer) || hlist_unhashed(&port->rlist)) goto out; @@ -912,7 +912,7 @@ static void br_ip6_multicast_port_query_expired(unsigned long data) void br_multicast_add_port(struct net_bridge_port *port) { - port->multicast_router = 1; + port->multicast_router = MDB_RTR_TYPE_TEMP_QUERY; setup_timer(&port->multicast_router_timer, br_multicast_router_expired, (unsigned long)port); @@ -959,7 +959,8 @@ void br_multicast_enable_port(struct net_bridge_port *port) #if IS_ENABLED(CONFIG_IPV6) br_multicast_enable(&port->ip6_own_query); #endif - if (port->multicast_router == 2 && hlist_unhashed(&port->rlist)) + if (port->multicast_router == MDB_RTR_TYPE_PERM && + hlist_unhashed(&port->rlist)) br_multicast_add_router(br, port); out: @@ -1227,13 +1228,13 @@ static void br_multicast_mark_router(struct net_bridge *br, unsigned long now = jiffies; if (!port) { - if (br->multicast_router == 1) + if (br->multicast_router == MDB_RTR_TYPE_TEMP_QUERY) mod_timer(&br->multicast_router_timer, now + br->multicast_querier_interval); return; } - if (port->multicast_router != 1) + if (port->multicast_router != MDB_RTR_TYPE_TEMP_QUERY) return; br_multicast_add_router(br, port); @@ -1713,7 +1714,7 @@ void br_multicast_init(struct net_bridge *br) br->hash_elasticity = 4; br->hash_max = 512; - br->multicast_router = 1; + br->multicast_router = MDB_RTR_TYPE_TEMP_QUERY; br->multicast_querier = 0; br->multicast_query_use_ifaddr = 0; br->multicast_last_member_count = 2; @@ -1823,11 +1824,11 @@ int br_multicast_set_router(struct net_bridge *br, unsigned long val) spin_lock_bh(&br->multicast_lock); switch (val) { - case 0: - case 2: + case MDB_RTR_TYPE_DISABLED: + case MDB_RTR_TYPE_PERM: del_timer(&br->multicast_router_timer); /* fall through */ - case 1: + case MDB_RTR_TYPE_TEMP_QUERY: br->multicast_router = val; err = 0; break; @@ -1838,6 +1839,14 @@ int br_multicast_set_router(struct net_bridge *br, unsigned long val) return err; } +static void __del_port_router(struct net_bridge_port *p) +{ + if (hlist_unhashed(&p->rlist)) + return; + hlist_del_init_rcu(&p->rlist); + br_rtr_notify(p->br->dev, p, RTM_DELMDB); +} + int br_multicast_set_port_router(struct net_bridge_port *p, unsigned long val) { struct net_bridge *br = p->br; @@ -1846,29 +1855,25 @@ int br_multicast_set_port_router(struct net_bridge_port *p, unsigned long val) spin_lock(&br->multicast_lock); switch (val) { - case 0: - case 1: - case 2: - p->multicast_router = val; - err = 0; - - if (val < 2 && !hlist_unhashed(&p->rlist)) { - hlist_del_init_rcu(&p->rlist); - br_rtr_notify(br->dev, p, RTM_DELMDB); - } - - if (val == 1) - break; - + case MDB_RTR_TYPE_DISABLED: + p->multicast_router = MDB_RTR_TYPE_DISABLED; + __del_port_router(p); + del_timer(&p->multicast_router_timer); + break; + case MDB_RTR_TYPE_TEMP_QUERY: + p->multicast_router = MDB_RTR_TYPE_TEMP_QUERY; + __del_port_router(p); + break; + case MDB_RTR_TYPE_PERM: + p->multicast_router = MDB_RTR_TYPE_PERM; del_timer(&p->multicast_router_timer); - - if (val == 0) - break; - br_multicast_add_router(br, p); break; + default: + goto unlock; } - + err = 0; +unlock: spin_unlock(&br->multicast_lock); return err; -- cgit v1.3-18-gd494 From a55d8246abcc910346771175b521ee2bce5a69b3 Mon Sep 17 00:00:00 2001 From: Nikolay Aleksandrov Date: Fri, 26 Feb 2016 21:20:03 +0100 Subject: bridge: mcast: add support for temporary port router Add support for a temporary router port which doesn't depend only on the incoming query. It can be refreshed if set to the same value, which is a no-op for the rest. Signed-off-by: Nikolay Aleksandrov Signed-off-by: David S. Miller --- include/uapi/linux/if_bridge.h | 1 + net/bridge/br_multicast.c | 21 +++++++++++++++++++-- 2 files changed, 20 insertions(+), 2 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/if_bridge.h b/include/uapi/linux/if_bridge.h index e47f3bc7f323..74ee03a47e79 100644 --- a/include/uapi/linux/if_bridge.h +++ b/include/uapi/linux/if_bridge.h @@ -182,6 +182,7 @@ enum { MDB_RTR_TYPE_DISABLED, MDB_RTR_TYPE_TEMP_QUERY, MDB_RTR_TYPE_PERM, + MDB_RTR_TYPE_TEMP }; enum { diff --git a/net/bridge/br_multicast.c b/net/bridge/br_multicast.c index f1140cf5168d..a4c15df2b792 100644 --- a/net/bridge/br_multicast.c +++ b/net/bridge/br_multicast.c @@ -759,13 +759,17 @@ static void br_multicast_router_expired(unsigned long data) struct net_bridge *br = port->br; spin_lock(&br->multicast_lock); - if (port->multicast_router != MDB_RTR_TYPE_TEMP_QUERY || + if (port->multicast_router == MDB_RTR_TYPE_DISABLED || + port->multicast_router == MDB_RTR_TYPE_PERM || timer_pending(&port->multicast_router_timer) || hlist_unhashed(&port->rlist)) goto out; hlist_del_init_rcu(&port->rlist); br_rtr_notify(br->dev, port, RTM_DELMDB); + /* Don't allow timer refresh if the router expired */ + if (port->multicast_router == MDB_RTR_TYPE_TEMP) + port->multicast_router = MDB_RTR_TYPE_TEMP_QUERY; out: spin_unlock(&br->multicast_lock); @@ -981,6 +985,9 @@ void br_multicast_disable_port(struct net_bridge_port *port) if (!hlist_unhashed(&port->rlist)) { hlist_del_init_rcu(&port->rlist); br_rtr_notify(br->dev, port, RTM_DELMDB); + /* Don't allow timer refresh if disabling */ + if (port->multicast_router == MDB_RTR_TYPE_TEMP) + port->multicast_router = MDB_RTR_TYPE_TEMP_QUERY; } del_timer(&port->multicast_router_timer); del_timer(&port->ip4_own_query.timer); @@ -1234,7 +1241,8 @@ static void br_multicast_mark_router(struct net_bridge *br, return; } - if (port->multicast_router != MDB_RTR_TYPE_TEMP_QUERY) + if (port->multicast_router == MDB_RTR_TYPE_DISABLED || + port->multicast_router == MDB_RTR_TYPE_PERM) return; br_multicast_add_router(br, port); @@ -1850,10 +1858,15 @@ static void __del_port_router(struct net_bridge_port *p) int br_multicast_set_port_router(struct net_bridge_port *p, unsigned long val) { struct net_bridge *br = p->br; + unsigned long now = jiffies; int err = -EINVAL; spin_lock(&br->multicast_lock); if (p->multicast_router == val) { + /* Refresh the temp router port timer */ + if (p->multicast_router == MDB_RTR_TYPE_TEMP) + mod_timer(&p->multicast_router_timer, + now + br->multicast_querier_interval); err = 0; goto unlock; } @@ -1872,6 +1885,10 @@ int br_multicast_set_port_router(struct net_bridge_port *p, unsigned long val) del_timer(&p->multicast_router_timer); br_multicast_add_router(br, p); break; + case MDB_RTR_TYPE_TEMP: + p->multicast_router = MDB_RTR_TYPE_TEMP; + br_multicast_mark_router(br, p); + break; default: goto unlock; } -- cgit v1.3-18-gd494 From 59f78f9f6c2e80dcf0f520be85b660f856217b79 Mon Sep 17 00:00:00 2001 From: Nikolay Aleksandrov Date: Fri, 26 Feb 2016 21:20:04 +0100 Subject: bridge: mcast: add support for more router port information dumping Allow for more multicast router port information to be dumped such as timer and type attributes. For that that purpose we need to extend the MDBA_ROUTER_PORT attribute similar to how it was done for the mdb entries recently. The new format is thus: [MDBA_ROUTER_PORT] = { <- nested attribute u32 ifindex <- router port ifindex for user-space compatibility [MDBA_ROUTER_PATTR attributes] } This way it remains compatible with older users (they'll simply retrieve the u32 in the beginning) and new users can parse the remaining attributes. It would also allow to add future extensions to the router port without breaking compatibility. Signed-off-by: Nikolay Aleksandrov Signed-off-by: David S. Miller --- include/uapi/linux/if_bridge.h | 14 +++++++++++++- net/bridge/br_mdb.c | 16 ++++++++++++++-- 2 files changed, 27 insertions(+), 3 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/if_bridge.h b/include/uapi/linux/if_bridge.h index 74ee03a47e79..0536eefff9bf 100644 --- a/include/uapi/linux/if_bridge.h +++ b/include/uapi/linux/if_bridge.h @@ -144,7 +144,10 @@ struct bridge_vlan_info { * } * } * [MDBA_ROUTER] = { - * [MDBA_ROUTER_PORT] + * [MDBA_ROUTER_PORT] = { + * u32 ifindex + * [MDBA_ROUTER_PATTR attributes] + * } * } */ enum { @@ -192,6 +195,15 @@ enum { }; #define MDBA_ROUTER_MAX (__MDBA_ROUTER_MAX - 1) +/* router port attributes */ +enum { + MDBA_ROUTER_PATTR_UNSPEC, + MDBA_ROUTER_PATTR_TIMER, + MDBA_ROUTER_PATTR_TYPE, + __MDBA_ROUTER_PATTR_MAX +}; +#define MDBA_ROUTER_PATTR_MAX (__MDBA_ROUTER_PATTR_MAX - 1) + struct br_port_msg { __u8 family; __u32 ifindex; diff --git a/net/bridge/br_mdb.c b/net/bridge/br_mdb.c index 73786e2fe065..253bc77eda3b 100644 --- a/net/bridge/br_mdb.c +++ b/net/bridge/br_mdb.c @@ -20,7 +20,7 @@ static int br_rports_fill_info(struct sk_buff *skb, struct netlink_callback *cb, { struct net_bridge *br = netdev_priv(dev); struct net_bridge_port *p; - struct nlattr *nest; + struct nlattr *nest, *port_nest; if (!br->multicast_router || hlist_empty(&br->router_list)) return 0; @@ -30,8 +30,20 @@ static int br_rports_fill_info(struct sk_buff *skb, struct netlink_callback *cb, return -EMSGSIZE; hlist_for_each_entry_rcu(p, &br->router_list, rlist) { - if (p && nla_put_u32(skb, MDBA_ROUTER_PORT, p->dev->ifindex)) + if (!p) + continue; + port_nest = nla_nest_start(skb, MDBA_ROUTER_PORT); + if (!port_nest) goto fail; + if (nla_put_nohdr(skb, sizeof(u32), &p->dev->ifindex) || + nla_put_u32(skb, MDBA_ROUTER_PATTR_TIMER, + br_timer_value(&p->multicast_router_timer)) || + nla_put_u8(skb, MDBA_ROUTER_PATTR_TYPE, + p->multicast_router)) { + nla_nest_cancel(skb, port_nest); + goto fail; + } + nla_nest_end(skb, port_nest); } nla_nest_end(skb, nest); -- cgit v1.3-18-gd494 From ef6980b6becb1afd9d82a4f043749a10ae81bf14 Mon Sep 17 00:00:00 2001 From: Jamal Hadi Salim Date: Sat, 27 Feb 2016 08:08:54 -0500 Subject: introduce IFE action This action allows for a sending side to encapsulate arbitrary metadata which is decapsulated by the receiving end. The sender runs in encoding mode and the receiver in decode mode. Both sender and receiver must specify the same ethertype. At some point we hope to have a registered ethertype and we'll then provide a default so the user doesnt have to specify it. For now we enforce the user specify it. Lets show example usage where we encode icmp from a sender towards a receiver with an skbmark of 17; both sender and receiver use ethertype of 0xdead to interop. YYYY: Lets start with Receiver-side policy config: xxx: add an ingress qdisc sudo tc qdisc add dev $ETH ingress xxx: any packets with ethertype 0xdead will be subjected to ife decoding xxx: we then restart the classification so we can match on icmp at prio 3 sudo $TC filter add dev $ETH parent ffff: prio 2 protocol 0xdead \ u32 match u32 0 0 flowid 1:1 \ action ife decode reclassify xxx: on restarting the classification from above if it was an icmp xxx: packet, then match it here and continue to the next rule at prio 4 xxx: which will match based on skb mark of 17 sudo tc filter add dev $ETH parent ffff: prio 3 protocol ip \ u32 match ip protocol 1 0xff flowid 1:1 \ action continue xxx: match on skbmark of 0x11 (decimal 17) and accept sudo tc filter add dev $ETH parent ffff: prio 4 protocol ip \ handle 0x11 fw flowid 1:1 \ action ok xxx: Lets show the decoding policy sudo tc -s filter ls dev $ETH parent ffff: protocol 0xdead xxx: filter pref 2 u32 filter pref 2 u32 fh 800: ht divisor 1 filter pref 2 u32 fh 800::800 order 2048 key ht 800 bkt 0 flowid 1:1 (rule hit 0 success 0) match 00000000/00000000 at 0 (success 0 ) action order 1: ife decode action reclassify index 1 ref 1 bind 1 installed 14 sec used 14 sec type: 0x0 Metadata: allow mark allow hash allow prio allow qmap Action statistics: Sent 0 bytes 0 pkt (dropped 0, overlimits 0 requeues 0) backlog 0b 0p requeues 0 xxx: Observe that above lists all metadatum it can decode. Typically these submodules will already be compiled into a monolithic kernel or loaded as modules YYYY: Lets show the sender side now .. xxx: Add an egress qdisc on the sender netdev sudo tc qdisc add dev $ETH root handle 1: prio xxx: xxx: Match all icmp packets to 192.168.122.237/24, then xxx: tag the packet with skb mark of decimal 17, then xxx: Encode it with: xxx: ethertype 0xdead xxx: add skb->mark to whitelist of metadatum to send xxx: rewrite target dst MAC address to 02:15:15:15:15:15 xxx: sudo $TC filter add dev $ETH parent 1: protocol ip prio 10 u32 \ match ip dst 192.168.122.237/24 \ match ip protocol 1 0xff \ flowid 1:2 \ action skbedit mark 17 \ action ife encode \ type 0xDEAD \ allow mark \ dst 02:15:15:15:15:15 xxx: Lets show the encoding policy sudo tc -s filter ls dev $ETH parent 1: protocol ip xxx: filter pref 10 u32 filter pref 10 u32 fh 800: ht divisor 1 filter pref 10 u32 fh 800::800 order 2048 key ht 800 bkt 0 flowid 1:2 (rule hit 0 success 0) match c0a87aed/ffffffff at 16 (success 0 ) match 00010000/00ff0000 at 8 (success 0 ) action order 1: skbedit mark 17 index 6 ref 1 bind 1 Action statistics: Sent 0 bytes 0 pkt (dropped 0, overlimits 0 requeues 0) backlog 0b 0p requeues 0 action order 2: ife encode action pipe index 3 ref 1 bind 1 dst MAC: 02:15:15:15:15:15 type: 0xDEAD Metadata: allow mark Action statistics: Sent 0 bytes 0 pkt (dropped 0, overlimits 0 requeues 0) backlog 0b 0p requeues 0 xxx: test by sending ping from sender to destination Signed-off-by: Jamal Hadi Salim Acked-by: Cong Wang Signed-off-by: David S. Miller --- include/net/tc_act/tc_ife.h | 61 +++ include/uapi/linux/tc_act/tc_ife.h | 38 ++ net/sched/Kconfig | 12 + net/sched/Makefile | 1 + net/sched/act_ife.c | 870 +++++++++++++++++++++++++++++++++++++ 5 files changed, 982 insertions(+) create mode 100644 include/net/tc_act/tc_ife.h create mode 100644 include/uapi/linux/tc_act/tc_ife.h create mode 100644 net/sched/act_ife.c (limited to 'include/uapi/linux') diff --git a/include/net/tc_act/tc_ife.h b/include/net/tc_act/tc_ife.h new file mode 100644 index 000000000000..dc9a09aefb33 --- /dev/null +++ b/include/net/tc_act/tc_ife.h @@ -0,0 +1,61 @@ +#ifndef __NET_TC_IFE_H +#define __NET_TC_IFE_H + +#include +#include +#include +#include + +#define IFE_METAHDRLEN 2 +struct tcf_ife_info { + struct tcf_common common; + u8 eth_dst[ETH_ALEN]; + u8 eth_src[ETH_ALEN]; + u16 eth_type; + u16 flags; + /* list of metaids allowed */ + struct list_head metalist; +}; +#define to_ife(a) \ + container_of(a->priv, struct tcf_ife_info, common) + +struct tcf_meta_info { + const struct tcf_meta_ops *ops; + void *metaval; + u16 metaid; + struct list_head metalist; +}; + +struct tcf_meta_ops { + u16 metaid; /*Maintainer provided ID */ + u16 metatype; /*netlink attribute type (look at net/netlink.h) */ + const char *name; + const char *synopsis; + struct list_head list; + int (*check_presence)(struct sk_buff *, struct tcf_meta_info *); + int (*encode)(struct sk_buff *, void *, struct tcf_meta_info *); + int (*decode)(struct sk_buff *, void *, u16 len); + int (*get)(struct sk_buff *skb, struct tcf_meta_info *mi); + int (*alloc)(struct tcf_meta_info *, void *); + void (*release)(struct tcf_meta_info *); + int (*validate)(void *val, int len); + struct module *owner; +}; + +#define MODULE_ALIAS_IFE_META(metan) MODULE_ALIAS("ifemeta" __stringify_1(metan)) + +int ife_get_meta_u32(struct sk_buff *skb, struct tcf_meta_info *mi); +int ife_get_meta_u16(struct sk_buff *skb, struct tcf_meta_info *mi); +int ife_tlv_meta_encode(void *skbdata, u16 attrtype, u16 dlen, + const void *dval); +int ife_alloc_meta_u32(struct tcf_meta_info *mi, void *metaval); +int ife_alloc_meta_u16(struct tcf_meta_info *mi, void *metaval); +int ife_check_meta_u32(u32 metaval, struct tcf_meta_info *mi); +int ife_encode_meta_u32(u32 metaval, void *skbdata, struct tcf_meta_info *mi); +int ife_validate_meta_u32(void *val, int len); +int ife_validate_meta_u16(void *val, int len); +void ife_release_meta_gen(struct tcf_meta_info *mi); +int register_ife_op(struct tcf_meta_ops *mops); +int unregister_ife_op(struct tcf_meta_ops *mops); + +#endif /* __NET_TC_IFE_H */ diff --git a/include/uapi/linux/tc_act/tc_ife.h b/include/uapi/linux/tc_act/tc_ife.h new file mode 100644 index 000000000000..d648ff66586f --- /dev/null +++ b/include/uapi/linux/tc_act/tc_ife.h @@ -0,0 +1,38 @@ +#ifndef __UAPI_TC_IFE_H +#define __UAPI_TC_IFE_H + +#include +#include + +#define TCA_ACT_IFE 25 +/* Flag bits for now just encoding/decoding; mutually exclusive */ +#define IFE_ENCODE 1 +#define IFE_DECODE 0 + +struct tc_ife { + tc_gen; + __u16 flags; +}; + +/*XXX: We need to encode the total number of bytes consumed */ +enum { + TCA_IFE_UNSPEC, + TCA_IFE_PARMS, + TCA_IFE_TM, + TCA_IFE_DMAC, + TCA_IFE_SMAC, + TCA_IFE_TYPE, + TCA_IFE_METALST, + __TCA_IFE_MAX +}; +#define TCA_IFE_MAX (__TCA_IFE_MAX - 1) + +#define IFE_META_SKBMARK 1 +#define IFE_META_HASHID 2 +#define IFE_META_PRIO 3 +#define IFE_META_QMAP 4 +/*Can be overridden at runtime by module option*/ +#define __IFE_META_MAX 5 +#define IFE_META_MAX (__IFE_META_MAX - 1) + +#endif diff --git a/net/sched/Kconfig b/net/sched/Kconfig index 82830824fb1f..4d48ef57e564 100644 --- a/net/sched/Kconfig +++ b/net/sched/Kconfig @@ -739,6 +739,18 @@ config NET_ACT_CONNMARK To compile this code as a module, choose M here: the module will be called act_connmark. +config NET_ACT_IFE + tristate "Inter-FE action based on IETF ForCES InterFE LFB" + depends on NET_CLS_ACT + ---help--- + Say Y here to allow for sourcing and terminating metadata + For details refer to netdev01 paper: + "Distributing Linux Traffic Control Classifier-Action Subsystem" + Authors: Jamal Hadi Salim and Damascene M. Joachimpillai + + To compile this code as a module, choose M here: the + module will be called act_ife. + config NET_CLS_IND bool "Incoming device classification" depends on NET_CLS_U32 || NET_CLS_FW diff --git a/net/sched/Makefile b/net/sched/Makefile index 690c1689e090..3d176671b0e1 100644 --- a/net/sched/Makefile +++ b/net/sched/Makefile @@ -19,6 +19,7 @@ obj-$(CONFIG_NET_ACT_CSUM) += act_csum.o obj-$(CONFIG_NET_ACT_VLAN) += act_vlan.o obj-$(CONFIG_NET_ACT_BPF) += act_bpf.o obj-$(CONFIG_NET_ACT_CONNMARK) += act_connmark.o +obj-$(CONFIG_NET_ACT_IFE) += act_ife.o obj-$(CONFIG_NET_SCH_FIFO) += sch_fifo.o obj-$(CONFIG_NET_SCH_CBQ) += sch_cbq.o obj-$(CONFIG_NET_SCH_HTB) += sch_htb.o diff --git a/net/sched/act_ife.c b/net/sched/act_ife.c new file mode 100644 index 000000000000..6e7ec257790d --- /dev/null +++ b/net/sched/act_ife.c @@ -0,0 +1,870 @@ +/* + * net/sched/ife.c Inter-FE action based on ForCES WG InterFE LFB + * + * Refer to: + * draft-ietf-forces-interfelfb-03 + * and + * netdev01 paper: + * "Distributing Linux Traffic Control Classifier-Action + * Subsystem" + * Authors: Jamal Hadi Salim and Damascene M. Joachimpillai + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License + * as published by the Free Software Foundation; either version + * 2 of the License, or (at your option) any later version. + * + * copyright Jamal Hadi Salim (2015) + * +*/ + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#define IFE_TAB_MASK 15 + +static int ife_net_id; +static int max_metacnt = IFE_META_MAX + 1; + +static const struct nla_policy ife_policy[TCA_IFE_MAX + 1] = { + [TCA_IFE_PARMS] = { .len = sizeof(struct tc_ife)}, + [TCA_IFE_DMAC] = { .len = ETH_ALEN}, + [TCA_IFE_SMAC] = { .len = ETH_ALEN}, + [TCA_IFE_TYPE] = { .type = NLA_U16}, +}; + +/* Caller takes care of presenting data in network order +*/ +int ife_tlv_meta_encode(void *skbdata, u16 attrtype, u16 dlen, const void *dval) +{ + u32 *tlv = (u32 *)(skbdata); + u16 totlen = nla_total_size(dlen); /*alignment + hdr */ + char *dptr = (char *)tlv + NLA_HDRLEN; + u32 htlv = attrtype << 16 | totlen; + + *tlv = htonl(htlv); + memset(dptr, 0, totlen - NLA_HDRLEN); + memcpy(dptr, dval, dlen); + + return totlen; +} +EXPORT_SYMBOL_GPL(ife_tlv_meta_encode); + +int ife_get_meta_u32(struct sk_buff *skb, struct tcf_meta_info *mi) +{ + if (mi->metaval) + return nla_put_u32(skb, mi->metaid, *(u32 *)mi->metaval); + else + return nla_put(skb, mi->metaid, 0, NULL); +} +EXPORT_SYMBOL_GPL(ife_get_meta_u32); + +int ife_check_meta_u32(u32 metaval, struct tcf_meta_info *mi) +{ + if (metaval || mi->metaval) + return 8; /* T+L+V == 2+2+4 */ + + return 0; +} +EXPORT_SYMBOL_GPL(ife_check_meta_u32); + +int ife_encode_meta_u32(u32 metaval, void *skbdata, struct tcf_meta_info *mi) +{ + u32 edata = metaval; + + if (mi->metaval) + edata = *(u32 *)mi->metaval; + else if (metaval) + edata = metaval; + + if (!edata) /* will not encode */ + return 0; + + edata = htonl(edata); + return ife_tlv_meta_encode(skbdata, mi->metaid, 4, &edata); +} +EXPORT_SYMBOL_GPL(ife_encode_meta_u32); + +int ife_get_meta_u16(struct sk_buff *skb, struct tcf_meta_info *mi) +{ + if (mi->metaval) + return nla_put_u16(skb, mi->metaid, *(u16 *)mi->metaval); + else + return nla_put(skb, mi->metaid, 0, NULL); +} +EXPORT_SYMBOL_GPL(ife_get_meta_u16); + +int ife_alloc_meta_u32(struct tcf_meta_info *mi, void *metaval) +{ + mi->metaval = kmemdup(&metaval, sizeof(u32), GFP_KERNEL); + if (!mi->metaval) + return -ENOMEM; + + return 0; +} +EXPORT_SYMBOL_GPL(ife_alloc_meta_u32); + +int ife_alloc_meta_u16(struct tcf_meta_info *mi, void *metaval) +{ + mi->metaval = kmemdup(&metaval, sizeof(u16), GFP_KERNEL); + if (!mi->metaval) + return -ENOMEM; + + return 0; +} +EXPORT_SYMBOL_GPL(ife_alloc_meta_u16); + +void ife_release_meta_gen(struct tcf_meta_info *mi) +{ + kfree(mi->metaval); +} +EXPORT_SYMBOL_GPL(ife_release_meta_gen); + +int ife_validate_meta_u32(void *val, int len) +{ + if (len == 4) + return 0; + + return -EINVAL; +} +EXPORT_SYMBOL_GPL(ife_validate_meta_u32); + +int ife_validate_meta_u16(void *val, int len) +{ + /* length will include padding */ + if (len == NLA_ALIGN(2)) + return 0; + + return -EINVAL; +} +EXPORT_SYMBOL_GPL(ife_validate_meta_u16); + +static LIST_HEAD(ifeoplist); +static DEFINE_RWLOCK(ife_mod_lock); + +static struct tcf_meta_ops *find_ife_oplist(u16 metaid) +{ + struct tcf_meta_ops *o; + + read_lock(&ife_mod_lock); + list_for_each_entry(o, &ifeoplist, list) { + if (o->metaid == metaid) { + if (!try_module_get(o->owner)) + o = NULL; + read_unlock(&ife_mod_lock); + return o; + } + } + read_unlock(&ife_mod_lock); + + return NULL; +} + +int register_ife_op(struct tcf_meta_ops *mops) +{ + struct tcf_meta_ops *m; + + if (!mops->metaid || !mops->metatype || !mops->name || + !mops->check_presence || !mops->encode || !mops->decode || + !mops->get || !mops->alloc) + return -EINVAL; + + write_lock(&ife_mod_lock); + + list_for_each_entry(m, &ifeoplist, list) { + if (m->metaid == mops->metaid || + (strcmp(mops->name, m->name) == 0)) { + write_unlock(&ife_mod_lock); + return -EEXIST; + } + } + + if (!mops->release) + mops->release = ife_release_meta_gen; + + list_add_tail(&mops->list, &ifeoplist); + write_unlock(&ife_mod_lock); + return 0; +} +EXPORT_SYMBOL_GPL(unregister_ife_op); + +int unregister_ife_op(struct tcf_meta_ops *mops) +{ + struct tcf_meta_ops *m; + int err = -ENOENT; + + write_lock(&ife_mod_lock); + list_for_each_entry(m, &ifeoplist, list) { + if (m->metaid == mops->metaid) { + list_del(&mops->list); + err = 0; + break; + } + } + write_unlock(&ife_mod_lock); + + return err; +} +EXPORT_SYMBOL_GPL(register_ife_op); + +static int ife_validate_metatype(struct tcf_meta_ops *ops, void *val, int len) +{ + int ret = 0; + /* XXX: unfortunately cant use nla_policy at this point + * because a length of 0 is valid in the case of + * "allow". "use" semantics do enforce for proper + * length and i couldve use nla_policy but it makes it hard + * to use it just for that.. + */ + if (ops->validate) + return ops->validate(val, len); + + if (ops->metatype == NLA_U32) + ret = ife_validate_meta_u32(val, len); + else if (ops->metatype == NLA_U16) + ret = ife_validate_meta_u16(val, len); + + return ret; +} + +/* called when adding new meta information + * under ife->tcf_lock +*/ +static int load_metaops_and_vet(struct tcf_ife_info *ife, u32 metaid, + void *val, int len) +{ + struct tcf_meta_ops *ops = find_ife_oplist(metaid); + int ret = 0; + + if (!ops) { + ret = -ENOENT; +#ifdef CONFIG_MODULES + spin_unlock_bh(&ife->tcf_lock); + rtnl_unlock(); + request_module("ifemeta%u", metaid); + rtnl_lock(); + spin_lock_bh(&ife->tcf_lock); + ops = find_ife_oplist(metaid); +#endif + } + + if (ops) { + ret = 0; + if (len) + ret = ife_validate_metatype(ops, val, len); + + module_put(ops->owner); + } + + return ret; +} + +/* called when adding new meta information + * under ife->tcf_lock +*/ +static int add_metainfo(struct tcf_ife_info *ife, u32 metaid, void *metaval, + int len) +{ + struct tcf_meta_info *mi = NULL; + struct tcf_meta_ops *ops = find_ife_oplist(metaid); + int ret = 0; + + if (!ops) + return -ENOENT; + + mi = kzalloc(sizeof(*mi), GFP_KERNEL); + if (!mi) { + /*put back what find_ife_oplist took */ + module_put(ops->owner); + return -ENOMEM; + } + + mi->metaid = metaid; + mi->ops = ops; + if (len > 0) { + ret = ops->alloc(mi, metaval); + if (ret != 0) { + kfree(mi); + module_put(ops->owner); + return ret; + } + } + + list_add_tail(&mi->metalist, &ife->metalist); + + return ret; +} + +static int use_all_metadata(struct tcf_ife_info *ife) +{ + struct tcf_meta_ops *o; + int rc = 0; + int installed = 0; + + list_for_each_entry(o, &ifeoplist, list) { + rc = add_metainfo(ife, o->metaid, NULL, 0); + if (rc == 0) + installed += 1; + } + + if (installed) + return 0; + else + return -EINVAL; +} + +static int dump_metalist(struct sk_buff *skb, struct tcf_ife_info *ife) +{ + struct tcf_meta_info *e; + struct nlattr *nest; + unsigned char *b = skb_tail_pointer(skb); + int total_encoded = 0; + + /*can only happen on decode */ + if (list_empty(&ife->metalist)) + return 0; + + nest = nla_nest_start(skb, TCA_IFE_METALST); + if (!nest) + goto out_nlmsg_trim; + + list_for_each_entry(e, &ife->metalist, metalist) { + if (!e->ops->get(skb, e)) + total_encoded += 1; + } + + if (!total_encoded) + goto out_nlmsg_trim; + + nla_nest_end(skb, nest); + + return 0; + +out_nlmsg_trim: + nlmsg_trim(skb, b); + return -1; +} + +/* under ife->tcf_lock */ +static void _tcf_ife_cleanup(struct tc_action *a, int bind) +{ + struct tcf_ife_info *ife = a->priv; + struct tcf_meta_info *e, *n; + + list_for_each_entry_safe(e, n, &ife->metalist, metalist) { + module_put(e->ops->owner); + list_del(&e->metalist); + if (e->metaval) { + if (e->ops->release) + e->ops->release(e); + else + kfree(e->metaval); + } + kfree(e); + } +} + +static void tcf_ife_cleanup(struct tc_action *a, int bind) +{ + struct tcf_ife_info *ife = a->priv; + + spin_lock_bh(&ife->tcf_lock); + _tcf_ife_cleanup(a, bind); + spin_unlock_bh(&ife->tcf_lock); +} + +/* under ife->tcf_lock */ +static int populate_metalist(struct tcf_ife_info *ife, struct nlattr **tb) +{ + int len = 0; + int rc = 0; + int i = 0; + void *val; + + for (i = 1; i < max_metacnt; i++) { + if (tb[i]) { + val = nla_data(tb[i]); + len = nla_len(tb[i]); + + rc = load_metaops_and_vet(ife, i, val, len); + if (rc != 0) + return rc; + + rc = add_metainfo(ife, i, val, len); + if (rc) + return rc; + } + } + + return rc; +} + +static int tcf_ife_init(struct net *net, struct nlattr *nla, + struct nlattr *est, struct tc_action *a, + int ovr, int bind) +{ + struct tc_action_net *tn = net_generic(net, ife_net_id); + struct nlattr *tb[TCA_IFE_MAX + 1]; + struct nlattr *tb2[IFE_META_MAX + 1]; + struct tcf_ife_info *ife; + struct tc_ife *parm; + u16 ife_type = 0; + u8 *daddr = NULL; + u8 *saddr = NULL; + int ret = 0; + int err; + + err = nla_parse_nested(tb, TCA_IFE_MAX, nla, ife_policy); + if (err < 0) + return err; + + if (!tb[TCA_IFE_PARMS]) + return -EINVAL; + + parm = nla_data(tb[TCA_IFE_PARMS]); + + if (parm->flags & IFE_ENCODE) { + /* Until we get issued the ethertype, we cant have + * a default.. + **/ + if (!tb[TCA_IFE_TYPE]) { + pr_info("You MUST pass etherype for encoding\n"); + return -EINVAL; + } + } + + if (!tcf_hash_check(tn, parm->index, a, bind)) { + ret = tcf_hash_create(tn, parm->index, est, a, sizeof(*ife), + bind, false); + if (ret) + return ret; + ret = ACT_P_CREATED; + } else { + if (bind) /* dont override defaults */ + return 0; + tcf_hash_release(a, bind); + if (!ovr) + return -EEXIST; + } + + ife = to_ife(a); + ife->flags = parm->flags; + + if (parm->flags & IFE_ENCODE) { + ife_type = nla_get_u16(tb[TCA_IFE_TYPE]); + if (tb[TCA_IFE_DMAC]) + daddr = nla_data(tb[TCA_IFE_DMAC]); + if (tb[TCA_IFE_SMAC]) + saddr = nla_data(tb[TCA_IFE_SMAC]); + } + + spin_lock_bh(&ife->tcf_lock); + ife->tcf_action = parm->action; + + if (parm->flags & IFE_ENCODE) { + if (daddr) + ether_addr_copy(ife->eth_dst, daddr); + else + eth_zero_addr(ife->eth_dst); + + if (saddr) + ether_addr_copy(ife->eth_src, saddr); + else + eth_zero_addr(ife->eth_src); + + ife->eth_type = ife_type; + } + + if (ret == ACT_P_CREATED) + INIT_LIST_HEAD(&ife->metalist); + + if (tb[TCA_IFE_METALST]) { + err = nla_parse_nested(tb2, IFE_META_MAX, tb[TCA_IFE_METALST], + NULL); + if (err) { +metadata_parse_err: + if (ret == ACT_P_CREATED) + _tcf_ife_cleanup(a, bind); + + spin_unlock_bh(&ife->tcf_lock); + return err; + } + + err = populate_metalist(ife, tb2); + if (err) + goto metadata_parse_err; + + } else { + /* if no passed metadata allow list or passed allow-all + * then here we process by adding as many supported metadatum + * as we can. You better have at least one else we are + * going to bail out + */ + err = use_all_metadata(ife); + if (err) { + if (ret == ACT_P_CREATED) + _tcf_ife_cleanup(a, bind); + + spin_unlock_bh(&ife->tcf_lock); + return err; + } + } + + spin_unlock_bh(&ife->tcf_lock); + + if (ret == ACT_P_CREATED) + tcf_hash_insert(tn, a); + + return ret; +} + +static int tcf_ife_dump(struct sk_buff *skb, struct tc_action *a, int bind, + int ref) +{ + unsigned char *b = skb_tail_pointer(skb); + struct tcf_ife_info *ife = a->priv; + struct tc_ife opt = { + .index = ife->tcf_index, + .refcnt = ife->tcf_refcnt - ref, + .bindcnt = ife->tcf_bindcnt - bind, + .action = ife->tcf_action, + .flags = ife->flags, + }; + struct tcf_t t; + + if (nla_put(skb, TCA_IFE_PARMS, sizeof(opt), &opt)) + goto nla_put_failure; + + t.install = jiffies_to_clock_t(jiffies - ife->tcf_tm.install); + t.lastuse = jiffies_to_clock_t(jiffies - ife->tcf_tm.lastuse); + t.expires = jiffies_to_clock_t(ife->tcf_tm.expires); + if (nla_put(skb, TCA_IFE_TM, sizeof(t), &t)) + goto nla_put_failure; + + if (!is_zero_ether_addr(ife->eth_dst)) { + if (nla_put(skb, TCA_IFE_DMAC, ETH_ALEN, ife->eth_dst)) + goto nla_put_failure; + } + + if (!is_zero_ether_addr(ife->eth_src)) { + if (nla_put(skb, TCA_IFE_SMAC, ETH_ALEN, ife->eth_src)) + goto nla_put_failure; + } + + if (nla_put(skb, TCA_IFE_TYPE, 2, &ife->eth_type)) + goto nla_put_failure; + + if (dump_metalist(skb, ife)) { + /*ignore failure to dump metalist */ + pr_info("Failed to dump metalist\n"); + } + + return skb->len; + +nla_put_failure: + nlmsg_trim(skb, b); + return -1; +} + +int find_decode_metaid(struct sk_buff *skb, struct tcf_ife_info *ife, + u16 metaid, u16 mlen, void *mdata) +{ + struct tcf_meta_info *e; + + /* XXX: use hash to speed up */ + list_for_each_entry(e, &ife->metalist, metalist) { + if (metaid == e->metaid) { + if (e->ops) { + /* We check for decode presence already */ + return e->ops->decode(skb, mdata, mlen); + } + } + } + + return 0; +} + +struct ifeheadr { + __be16 metalen; + u8 tlv_data[]; +}; + +struct meta_tlvhdr { + __be16 type; + __be16 len; +}; + +static int tcf_ife_decode(struct sk_buff *skb, const struct tc_action *a, + struct tcf_result *res) +{ + struct tcf_ife_info *ife = a->priv; + int action = ife->tcf_action; + struct ifeheadr *ifehdr = (struct ifeheadr *)skb->data; + u16 ifehdrln = ifehdr->metalen; + struct meta_tlvhdr *tlv = (struct meta_tlvhdr *)(ifehdr->tlv_data); + + spin_lock(&ife->tcf_lock); + bstats_update(&ife->tcf_bstats, skb); + ife->tcf_tm.lastuse = jiffies; + spin_unlock(&ife->tcf_lock); + + ifehdrln = ntohs(ifehdrln); + if (unlikely(!pskb_may_pull(skb, ifehdrln))) { + spin_lock(&ife->tcf_lock); + ife->tcf_qstats.drops++; + spin_unlock(&ife->tcf_lock); + return TC_ACT_SHOT; + } + + skb_set_mac_header(skb, ifehdrln); + __skb_pull(skb, ifehdrln); + skb->protocol = eth_type_trans(skb, skb->dev); + ifehdrln -= IFE_METAHDRLEN; + + while (ifehdrln > 0) { + u8 *tlvdata = (u8 *)tlv; + u16 mtype = tlv->type; + u16 mlen = tlv->len; + + mtype = ntohs(mtype); + mlen = ntohs(mlen); + + if (find_decode_metaid(skb, ife, mtype, (mlen - 4), + (void *)(tlvdata + 4))) { + /* abuse overlimits to count when we receive metadata + * but dont have an ops for it + */ + pr_info_ratelimited("Unknown metaid %d alnlen %d\n", + mtype, mlen); + ife->tcf_qstats.overlimits++; + } + + tlvdata += mlen; + ifehdrln -= mlen; + tlv = (struct meta_tlvhdr *)tlvdata; + } + + skb_reset_network_header(skb); + return action; +} + +/*XXX: check if we can do this at install time instead of current + * send data path +**/ +static int ife_get_sz(struct sk_buff *skb, struct tcf_ife_info *ife) +{ + struct tcf_meta_info *e, *n; + int tot_run_sz = 0, run_sz = 0; + + list_for_each_entry_safe(e, n, &ife->metalist, metalist) { + if (e->ops->check_presence) { + run_sz = e->ops->check_presence(skb, e); + tot_run_sz += run_sz; + } + } + + return tot_run_sz; +} + +static int tcf_ife_encode(struct sk_buff *skb, const struct tc_action *a, + struct tcf_result *res) +{ + struct tcf_ife_info *ife = a->priv; + int action = ife->tcf_action; + struct ethhdr *oethh; /* outer ether header */ + struct ethhdr *iethh; /* inner eth header */ + struct tcf_meta_info *e; + /* + OUTERHDR:TOTMETALEN:{TLVHDR:Metadatum:TLVHDR..}:ORIGDATA + where ORIGDATA = original ethernet header ... + */ + u16 metalen = ife_get_sz(skb, ife); + int hdrm = metalen + skb->dev->hard_header_len + IFE_METAHDRLEN; + unsigned int skboff = skb->dev->hard_header_len; + u32 at = G_TC_AT(skb->tc_verd); + int new_len = skb->len + hdrm; + bool exceed_mtu = false; + int err; + + if (at & AT_EGRESS) { + if (new_len > skb->dev->mtu) + exceed_mtu = true; + } + + spin_lock(&ife->tcf_lock); + bstats_update(&ife->tcf_bstats, skb); + ife->tcf_tm.lastuse = jiffies; + + if (!metalen) { /* no metadata to send */ + /* abuse overlimits to count when we allow packet + * with no metadata + */ + ife->tcf_qstats.overlimits++; + spin_unlock(&ife->tcf_lock); + return action; + } + /* could be stupid policy setup or mtu config + * so lets be conservative.. */ + if ((action == TC_ACT_SHOT) || exceed_mtu) { + ife->tcf_qstats.drops++; + spin_unlock(&ife->tcf_lock); + return TC_ACT_SHOT; + } + + iethh = eth_hdr(skb); + + err = skb_cow_head(skb, hdrm); + if (unlikely(err)) { + ife->tcf_qstats.drops++; + spin_unlock(&ife->tcf_lock); + return TC_ACT_SHOT; + } + + if (!(at & AT_EGRESS)) + skb_push(skb, skb->dev->hard_header_len); + + __skb_push(skb, hdrm); + memcpy(skb->data, iethh, skb->mac_len); + skb_reset_mac_header(skb); + oethh = eth_hdr(skb); + + /*total metadata length */ + metalen += IFE_METAHDRLEN; + metalen = htons(metalen); + memcpy((skb->data + skboff), &metalen, IFE_METAHDRLEN); + skboff += IFE_METAHDRLEN; + + /* XXX: we dont have a clever way of telling encode to + * not repeat some of the computations that are done by + * ops->presence_check... + */ + list_for_each_entry(e, &ife->metalist, metalist) { + if (e->ops->encode) { + err = e->ops->encode(skb, (void *)(skb->data + skboff), + e); + } + if (err < 0) { + /* too corrupt to keep around if overwritten */ + ife->tcf_qstats.drops++; + spin_unlock(&ife->tcf_lock); + return TC_ACT_SHOT; + } + skboff += err; + } + + if (!is_zero_ether_addr(ife->eth_src)) + ether_addr_copy(oethh->h_source, ife->eth_src); + else + ether_addr_copy(oethh->h_source, iethh->h_source); + if (!is_zero_ether_addr(ife->eth_dst)) + ether_addr_copy(oethh->h_dest, ife->eth_dst); + else + ether_addr_copy(oethh->h_dest, iethh->h_dest); + oethh->h_proto = htons(ife->eth_type); + + if (!(at & AT_EGRESS)) + skb_pull(skb, skb->dev->hard_header_len); + + spin_unlock(&ife->tcf_lock); + + return action; +} + +static int tcf_ife_act(struct sk_buff *skb, const struct tc_action *a, + struct tcf_result *res) +{ + struct tcf_ife_info *ife = a->priv; + + if (ife->flags & IFE_ENCODE) + return tcf_ife_encode(skb, a, res); + + if (!(ife->flags & IFE_ENCODE)) + return tcf_ife_decode(skb, a, res); + + pr_info_ratelimited("unknown failure(policy neither de/encode\n"); + spin_lock(&ife->tcf_lock); + bstats_update(&ife->tcf_bstats, skb); + ife->tcf_tm.lastuse = jiffies; + ife->tcf_qstats.drops++; + spin_unlock(&ife->tcf_lock); + + return TC_ACT_SHOT; +} + +static int tcf_ife_walker(struct net *net, struct sk_buff *skb, + struct netlink_callback *cb, int type, + struct tc_action *a) +{ + struct tc_action_net *tn = net_generic(net, ife_net_id); + + return tcf_generic_walker(tn, skb, cb, type, a); +} + +static int tcf_ife_search(struct net *net, struct tc_action *a, u32 index) +{ + struct tc_action_net *tn = net_generic(net, ife_net_id); + + return tcf_hash_search(tn, a, index); +} + +static struct tc_action_ops act_ife_ops = { + .kind = "ife", + .type = TCA_ACT_IFE, + .owner = THIS_MODULE, + .act = tcf_ife_act, + .dump = tcf_ife_dump, + .cleanup = tcf_ife_cleanup, + .init = tcf_ife_init, + .walk = tcf_ife_walker, + .lookup = tcf_ife_search, +}; + +static __net_init int ife_init_net(struct net *net) +{ + struct tc_action_net *tn = net_generic(net, ife_net_id); + + return tc_action_net_init(tn, &act_ife_ops, IFE_TAB_MASK); +} + +static void __net_exit ife_exit_net(struct net *net) +{ + struct tc_action_net *tn = net_generic(net, ife_net_id); + + tc_action_net_exit(tn); +} + +static struct pernet_operations ife_net_ops = { + .init = ife_init_net, + .exit = ife_exit_net, + .id = &ife_net_id, + .size = sizeof(struct tc_action_net), +}; + +static int __init ife_init_module(void) +{ + return tcf_register_action(&act_ife_ops, &ife_net_ops); +} + +static void __exit ife_cleanup_module(void) +{ + tcf_unregister_action(&act_ife_ops, &ife_net_ops); +} + +module_init(ife_init_module); +module_exit(ife_cleanup_module); + +MODULE_AUTHOR("Jamal Hadi Salim(2015)"); +MODULE_DESCRIPTION("Inter-FE LFB action"); +MODULE_LICENSE("GPL"); -- cgit v1.3-18-gd494 From b5d3755a22e0cc4c369c0985aef0c52c2477c1e7 Mon Sep 17 00:00:00 2001 From: Nicolas Dichtel Date: Fri, 4 Mar 2016 11:52:16 +0100 Subject: uapi: define DIV_ROUND_UP for userland DIV_ROUND_UP is defined in linux/kernel.h only for the kernel. When ethtool.h is included by a userland app, we got the following error: include/linux/ethtool.h:1218:8: error: variably modified 'queue_mask' at file scope __u32 queue_mask[DIV_ROUND_UP(MAX_NUM_QUEUE, 32)]; ^ Let's add a common definition in uapi and use it everywhere. Fixes: ac2c7ad0e5d6 ("net/ethtool: introduce a new ioctl for per queue setting") CC: Kan Liang Suggested-by: Ben Hutchings Signed-off-by: Nicolas Dichtel Signed-off-by: David S. Miller --- include/linux/kernel.h | 2 +- include/uapi/linux/ethtool.h | 3 ++- include/uapi/linux/kernel.h | 1 + include/uapi/linux/mroute6.h | 9 ++------- 4 files changed, 6 insertions(+), 9 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/linux/kernel.h b/include/linux/kernel.h index f31638c6e873..ac1923957236 100644 --- a/include/linux/kernel.h +++ b/include/linux/kernel.h @@ -64,7 +64,7 @@ #define round_down(x, y) ((x) & ~__round_mask(x, y)) #define FIELD_SIZEOF(t, f) (sizeof(((t*)0)->f)) -#define DIV_ROUND_UP(n,d) (((n) + (d) - 1) / (d)) +#define DIV_ROUND_UP __KERNEL_DIV_ROUND_UP #define DIV_ROUND_UP_ULL(ll,d) \ ({ unsigned long long _tmp = (ll)+(d)-1; do_div(_tmp, d); _tmp; }) diff --git a/include/uapi/linux/ethtool.h b/include/uapi/linux/ethtool.h index 37fd6dc33de4..9c22249ebf35 100644 --- a/include/uapi/linux/ethtool.h +++ b/include/uapi/linux/ethtool.h @@ -13,6 +13,7 @@ #ifndef _UAPI_LINUX_ETHTOOL_H #define _UAPI_LINUX_ETHTOOL_H +#include #include #include @@ -1215,7 +1216,7 @@ enum ethtool_sfeatures_retval_bits { struct ethtool_per_queue_op { __u32 cmd; __u32 sub_command; - __u32 queue_mask[DIV_ROUND_UP(MAX_NUM_QUEUE, 32)]; + __u32 queue_mask[__KERNEL_DIV_ROUND_UP(MAX_NUM_QUEUE, 32)]; char data[]; }; diff --git a/include/uapi/linux/kernel.h b/include/uapi/linux/kernel.h index 321e399457f5..466073f0ce46 100644 --- a/include/uapi/linux/kernel.h +++ b/include/uapi/linux/kernel.h @@ -9,5 +9,6 @@ #define __ALIGN_KERNEL(x, a) __ALIGN_KERNEL_MASK(x, (typeof(x))(a) - 1) #define __ALIGN_KERNEL_MASK(x, mask) (((x) + (mask)) & ~(mask)) +#define __KERNEL_DIV_ROUND_UP(n, d) (((n) + (d) - 1) / (d)) #endif /* _UAPI_LINUX_KERNEL_H */ diff --git a/include/uapi/linux/mroute6.h b/include/uapi/linux/mroute6.h index ce91215cf7e6..5062fb5751e1 100644 --- a/include/uapi/linux/mroute6.h +++ b/include/uapi/linux/mroute6.h @@ -1,6 +1,7 @@ #ifndef _UAPI__LINUX_MROUTE6_H #define _UAPI__LINUX_MROUTE6_H +#include #include #include @@ -46,14 +47,8 @@ typedef unsigned short mifi_t; typedef __u32 if_mask; #define NIFBITS (sizeof(if_mask) * 8) /* bits per mask */ -#if !defined(__KERNEL__) -#if !defined(DIV_ROUND_UP) -#define DIV_ROUND_UP(x,y) (((x) + ((y) - 1)) / (y)) -#endif -#endif - typedef struct if_set { - if_mask ifs_bits[DIV_ROUND_UP(IF_SETSIZE, NIFBITS)]; + if_mask ifs_bits[__KERNEL_DIV_ROUND_UP(IF_SETSIZE, NIFBITS)]; } if_set; #define IF_SET(n, p) ((p)->ifs_bits[(n)/NIFBITS] |= (1 << ((n) % NIFBITS))) -- cgit v1.3-18-gd494 From 14e2037902d65213842b4e40305ff54a64abbcb6 Mon Sep 17 00:00:00 2001 From: Nicolas Dichtel Date: Fri, 4 Mar 2016 11:52:19 +0100 Subject: ethtool.h: define INT_MAX for userland INT_MAX needs limits.h in userland. When ethtool.h is included by a userland app, we got the following error: .../usr/include/linux/ethtool.h: In function 'ethtool_validate_speed': .../usr/include/linux/ethtool.h:1471:18: error: 'INT_MAX' undeclared (first use in this function) return speed <= INT_MAX || speed == SPEED_UNKNOWN ^ Fixes: e02564ee334a ("ethtool: make validate_speed accept all speeds between 0 and INT_MAX") CC: Nikolay Aleksandrov Signed-off-by: Nicolas Dichtel Acked-by: Nikolay Aleksandrov Signed-off-by: David S. Miller --- include/uapi/linux/ethtool.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/ethtool.h b/include/uapi/linux/ethtool.h index 9c22249ebf35..2835b07416b7 100644 --- a/include/uapi/linux/ethtool.h +++ b/include/uapi/linux/ethtool.h @@ -17,6 +17,10 @@ #include #include +#ifndef __KERNEL__ +#include /* for INT_MAX */ +#endif + /* All structures exposed to userland should be defined such that they * have the same layout for 32-bit and 64-bit userland. */ -- cgit v1.3-18-gd494