diff options
author | Linus Torvalds <torvalds@linux-foundation.org> | 2020-08-06 06:13:21 +0300 |
---|---|---|
committer | Linus Torvalds <torvalds@linux-foundation.org> | 2020-08-06 06:13:21 +0300 |
commit | 47ec5303d73ea344e84f46660fff693c57641386 (patch) | |
tree | a2252debab749de29620c43285295d60c4741119 /net/core/bpf_sk_storage.c | |
parent | 8186749621ed6b8fc42644c399e8c755a2b6f630 (diff) | |
parent | c1055b76ad00aed0e8b79417080f212d736246b6 (diff) | |
download | linux-47ec5303d73ea344e84f46660fff693c57641386.tar.xz |
Merge git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-next
Pull networking updates from David Miller:
1) Support 6Ghz band in ath11k driver, from Rajkumar Manoharan.
2) Support UDP segmentation in code TSO code, from Eric Dumazet.
3) Allow flashing different flash images in cxgb4 driver, from Vishal
Kulkarni.
4) Add drop frames counter and flow status to tc flower offloading,
from Po Liu.
5) Support n-tuple filters in cxgb4, from Vishal Kulkarni.
6) Various new indirect call avoidance, from Eric Dumazet and Brian
Vazquez.
7) Fix BPF verifier failures on 32-bit pointer arithmetic, from
Yonghong Song.
8) Support querying and setting hardware address of a port function via
devlink, use this in mlx5, from Parav Pandit.
9) Support hw ipsec offload on bonding slaves, from Jarod Wilson.
10) Switch qca8k driver over to phylink, from Jonathan McDowell.
11) In bpftool, show list of processes holding BPF FD references to
maps, programs, links, and btf objects. From Andrii Nakryiko.
12) Several conversions over to generic power management, from Vaibhav
Gupta.
13) Add support for SO_KEEPALIVE et al. to bpf_setsockopt(), from Dmitry
Yakunin.
14) Various https url conversions, from Alexander A. Klimov.
15) Timestamping and PHC support for mscc PHY driver, from Antoine
Tenart.
16) Support bpf iterating over tcp and udp sockets, from Yonghong Song.
17) Support 5GBASE-T i40e NICs, from Aleksandr Loktionov.
18) Add kTLS RX HW offload support to mlx5e, from Tariq Toukan.
19) Fix the ->ndo_start_xmit() return type to be netdev_tx_t in several
drivers. From Luc Van Oostenryck.
20) XDP support for xen-netfront, from Denis Kirjanov.
21) Support receive buffer autotuning in MPTCP, from Florian Westphal.
22) Support EF100 chip in sfc driver, from Edward Cree.
23) Add XDP support to mvpp2 driver, from Matteo Croce.
24) Support MPTCP in sock_diag, from Paolo Abeni.
25) Commonize UDP tunnel offloading code by creating udp_tunnel_nic
infrastructure, from Jakub Kicinski.
26) Several pci_ --> dma_ API conversions, from Christophe JAILLET.
27) Add FLOW_ACTION_POLICE support to mlxsw, from Ido Schimmel.
28) Add SK_LOOKUP bpf program type, from Jakub Sitnicki.
29) Refactor a lot of networking socket option handling code in order to
avoid set_fs() calls, from Christoph Hellwig.
30) Add rfc4884 support to icmp code, from Willem de Bruijn.
31) Support TBF offload in dpaa2-eth driver, from Ioana Ciornei.
32) Support XDP_REDIRECT in qede driver, from Alexander Lobakin.
33) Support PCI relaxed ordering in mlx5 driver, from Aya Levin.
34) Support TCP syncookies in MPTCP, from Flowian Westphal.
35) Fix several tricky cases of PMTU handling wrt. briding, from Stefano
Brivio.
* git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-next: (2056 commits)
net: thunderx: initialize VF's mailbox mutex before first usage
usb: hso: remove bogus check for EINPROGRESS
usb: hso: no complaint about kmalloc failure
hso: fix bailout in error case of probe
ip_tunnel_core: Fix build for archs without _HAVE_ARCH_IPV6_CSUM
selftests/net: relax cpu affinity requirement in msg_zerocopy test
mptcp: be careful on subflow creation
selftests: rtnetlink: make kci_test_encap() return sub-test result
selftests: rtnetlink: correct the final return value for the test
net: dsa: sja1105: use detected device id instead of DT one on mismatch
tipc: set ub->ifindex for local ipv6 address
ipv6: add ipv6_dev_find()
net: openvswitch: silence suspicious RCU usage warning
Revert "vxlan: fix tos value before xmit"
ptp: only allow phase values lower than 1 period
farsync: switch from 'pci_' to 'dma_' API
wan: wanxl: switch from 'pci_' to 'dma_' API
hv_netvsc: do not use VF device if link is down
dpaa2-eth: Fix passing zero to 'PTR_ERR' warning
net: macb: Properly handle phylink on at91sam9x
...
Diffstat (limited to 'net/core/bpf_sk_storage.c')
-rw-r--r-- | net/core/bpf_sk_storage.c | 260 |
1 files changed, 256 insertions, 4 deletions
diff --git a/net/core/bpf_sk_storage.c b/net/core/bpf_sk_storage.c index d2c4d16dadba..d3377c90a291 100644 --- a/net/core/bpf_sk_storage.c +++ b/net/core/bpf_sk_storage.c @@ -6,13 +6,12 @@ #include <linux/types.h> #include <linux/spinlock.h> #include <linux/bpf.h> +#include <linux/btf_ids.h> #include <net/bpf_sk_storage.h> #include <net/sock.h> #include <uapi/linux/sock_diag.h> #include <uapi/linux/btf.h> -static atomic_t cache_idx; - #define SK_STORAGE_CREATE_FLAG_MASK \ (BPF_F_NO_PREALLOC | BPF_F_CLONE) @@ -81,6 +80,9 @@ struct bpf_sk_storage_elem { #define SDATA(_SELEM) (&(_SELEM)->sdata) #define BPF_SK_STORAGE_CACHE_SIZE 16 +static DEFINE_SPINLOCK(cache_idx_lock); +static u64 cache_idx_usage_counts[BPF_SK_STORAGE_CACHE_SIZE]; + struct bpf_sk_storage { struct bpf_sk_storage_data __rcu *cache[BPF_SK_STORAGE_CACHE_SIZE]; struct hlist_head list; /* List of bpf_sk_storage_elem */ @@ -512,6 +514,37 @@ static int sk_storage_delete(struct sock *sk, struct bpf_map *map) return 0; } +static u16 cache_idx_get(void) +{ + u64 min_usage = U64_MAX; + u16 i, res = 0; + + spin_lock(&cache_idx_lock); + + for (i = 0; i < BPF_SK_STORAGE_CACHE_SIZE; i++) { + if (cache_idx_usage_counts[i] < min_usage) { + min_usage = cache_idx_usage_counts[i]; + res = i; + + /* Found a free cache_idx */ + if (!min_usage) + break; + } + } + cache_idx_usage_counts[res]++; + + spin_unlock(&cache_idx_lock); + + return res; +} + +static void cache_idx_free(u16 idx) +{ + spin_lock(&cache_idx_lock); + cache_idx_usage_counts[idx]--; + spin_unlock(&cache_idx_lock); +} + /* Called by __sk_destruct() & bpf_sk_storage_clone() */ void bpf_sk_storage_free(struct sock *sk) { @@ -560,6 +593,8 @@ static void bpf_sk_storage_map_free(struct bpf_map *map) smap = (struct bpf_sk_storage_map *)map; + cache_idx_free(smap->cache_idx); + /* Note that this map might be concurrently cloned from * bpf_sk_storage_clone. Wait for any existing bpf_sk_storage_clone * RCU read section to finish before proceeding. New RCU @@ -673,8 +708,7 @@ static struct bpf_map *bpf_sk_storage_map_alloc(union bpf_attr *attr) } smap->elem_size = sizeof(struct bpf_sk_storage_elem) + attr->value_size; - smap->cache_idx = (unsigned int)atomic_inc_return(&cache_idx) % - BPF_SK_STORAGE_CACHE_SIZE; + smap->cache_idx = cache_idx_get(); return &smap->map; } @@ -886,6 +920,7 @@ BPF_CALL_2(bpf_sk_storage_delete, struct bpf_map *, map, struct sock *, sk) return -ENOENT; } +static int sk_storage_map_btf_id; const struct bpf_map_ops sk_storage_map_ops = { .map_alloc_check = bpf_sk_storage_map_alloc_check, .map_alloc = bpf_sk_storage_map_alloc, @@ -895,6 +930,8 @@ const struct bpf_map_ops sk_storage_map_ops = { .map_update_elem = bpf_fd_sk_storage_update_elem, .map_delete_elem = bpf_fd_sk_storage_delete_elem, .map_check_btf = bpf_sk_storage_map_check_btf, + .map_btf_name = "bpf_sk_storage_map", + .map_btf_id = &sk_storage_map_btf_id, }; const struct bpf_func_proto bpf_sk_storage_get_proto = { @@ -907,6 +944,16 @@ const struct bpf_func_proto bpf_sk_storage_get_proto = { .arg4_type = ARG_ANYTHING, }; +const struct bpf_func_proto bpf_sk_storage_get_cg_sock_proto = { + .func = bpf_sk_storage_get, + .gpl_only = false, + .ret_type = RET_PTR_TO_MAP_VALUE_OR_NULL, + .arg1_type = ARG_CONST_MAP_PTR, + .arg2_type = ARG_PTR_TO_CTX, /* context is 'struct sock' */ + .arg3_type = ARG_PTR_TO_MAP_VALUE_OR_NULL, + .arg4_type = ARG_ANYTHING, +}; + const struct bpf_func_proto bpf_sk_storage_delete_proto = { .func = bpf_sk_storage_delete, .gpl_only = false, @@ -1181,3 +1228,208 @@ int bpf_sk_storage_diag_put(struct bpf_sk_storage_diag *diag, return err; } EXPORT_SYMBOL_GPL(bpf_sk_storage_diag_put); + +struct bpf_iter_seq_sk_storage_map_info { + struct bpf_map *map; + unsigned int bucket_id; + unsigned skip_elems; +}; + +static struct bpf_sk_storage_elem * +bpf_sk_storage_map_seq_find_next(struct bpf_iter_seq_sk_storage_map_info *info, + struct bpf_sk_storage_elem *prev_selem) +{ + struct bpf_sk_storage *sk_storage; + struct bpf_sk_storage_elem *selem; + u32 skip_elems = info->skip_elems; + struct bpf_sk_storage_map *smap; + u32 bucket_id = info->bucket_id; + u32 i, count, n_buckets; + struct bucket *b; + + smap = (struct bpf_sk_storage_map *)info->map; + n_buckets = 1U << smap->bucket_log; + if (bucket_id >= n_buckets) + return NULL; + + /* try to find next selem in the same bucket */ + selem = prev_selem; + count = 0; + while (selem) { + selem = hlist_entry_safe(selem->map_node.next, + struct bpf_sk_storage_elem, map_node); + if (!selem) { + /* not found, unlock and go to the next bucket */ + b = &smap->buckets[bucket_id++]; + raw_spin_unlock_bh(&b->lock); + skip_elems = 0; + break; + } + sk_storage = rcu_dereference_raw(selem->sk_storage); + if (sk_storage) { + info->skip_elems = skip_elems + count; + return selem; + } + count++; + } + + for (i = bucket_id; i < (1U << smap->bucket_log); i++) { + b = &smap->buckets[i]; + raw_spin_lock_bh(&b->lock); + count = 0; + hlist_for_each_entry(selem, &b->list, map_node) { + sk_storage = rcu_dereference_raw(selem->sk_storage); + if (sk_storage && count >= skip_elems) { + info->bucket_id = i; + info->skip_elems = count; + return selem; + } + count++; + } + raw_spin_unlock_bh(&b->lock); + skip_elems = 0; + } + + info->bucket_id = i; + info->skip_elems = 0; + return NULL; +} + +static void *bpf_sk_storage_map_seq_start(struct seq_file *seq, loff_t *pos) +{ + struct bpf_sk_storage_elem *selem; + + selem = bpf_sk_storage_map_seq_find_next(seq->private, NULL); + if (!selem) + return NULL; + + if (*pos == 0) + ++*pos; + return selem; +} + +static void *bpf_sk_storage_map_seq_next(struct seq_file *seq, void *v, + loff_t *pos) +{ + struct bpf_iter_seq_sk_storage_map_info *info = seq->private; + + ++*pos; + ++info->skip_elems; + return bpf_sk_storage_map_seq_find_next(seq->private, v); +} + +struct bpf_iter__bpf_sk_storage_map { + __bpf_md_ptr(struct bpf_iter_meta *, meta); + __bpf_md_ptr(struct bpf_map *, map); + __bpf_md_ptr(struct sock *, sk); + __bpf_md_ptr(void *, value); +}; + +DEFINE_BPF_ITER_FUNC(bpf_sk_storage_map, struct bpf_iter_meta *meta, + struct bpf_map *map, struct sock *sk, + void *value) + +static int __bpf_sk_storage_map_seq_show(struct seq_file *seq, + struct bpf_sk_storage_elem *selem) +{ + struct bpf_iter_seq_sk_storage_map_info *info = seq->private; + struct bpf_iter__bpf_sk_storage_map ctx = {}; + struct bpf_sk_storage *sk_storage; + struct bpf_iter_meta meta; + struct bpf_prog *prog; + int ret = 0; + + meta.seq = seq; + prog = bpf_iter_get_info(&meta, selem == NULL); + if (prog) { + ctx.meta = &meta; + ctx.map = info->map; + if (selem) { + sk_storage = rcu_dereference_raw(selem->sk_storage); + ctx.sk = sk_storage->sk; + ctx.value = SDATA(selem)->data; + } + ret = bpf_iter_run_prog(prog, &ctx); + } + + return ret; +} + +static int bpf_sk_storage_map_seq_show(struct seq_file *seq, void *v) +{ + return __bpf_sk_storage_map_seq_show(seq, v); +} + +static void bpf_sk_storage_map_seq_stop(struct seq_file *seq, void *v) +{ + struct bpf_iter_seq_sk_storage_map_info *info = seq->private; + struct bpf_sk_storage_map *smap; + struct bucket *b; + + if (!v) { + (void)__bpf_sk_storage_map_seq_show(seq, v); + } else { + smap = (struct bpf_sk_storage_map *)info->map; + b = &smap->buckets[info->bucket_id]; + raw_spin_unlock_bh(&b->lock); + } +} + +static int bpf_iter_init_sk_storage_map(void *priv_data, + struct bpf_iter_aux_info *aux) +{ + struct bpf_iter_seq_sk_storage_map_info *seq_info = priv_data; + + seq_info->map = aux->map; + return 0; +} + +static int bpf_iter_check_map(struct bpf_prog *prog, + struct bpf_iter_aux_info *aux) +{ + struct bpf_map *map = aux->map; + + if (map->map_type != BPF_MAP_TYPE_SK_STORAGE) + return -EINVAL; + + if (prog->aux->max_rdonly_access > map->value_size) + return -EACCES; + + return 0; +} + +static const struct seq_operations bpf_sk_storage_map_seq_ops = { + .start = bpf_sk_storage_map_seq_start, + .next = bpf_sk_storage_map_seq_next, + .stop = bpf_sk_storage_map_seq_stop, + .show = bpf_sk_storage_map_seq_show, +}; + +static const struct bpf_iter_seq_info iter_seq_info = { + .seq_ops = &bpf_sk_storage_map_seq_ops, + .init_seq_private = bpf_iter_init_sk_storage_map, + .fini_seq_private = NULL, + .seq_priv_size = sizeof(struct bpf_iter_seq_sk_storage_map_info), +}; + +static struct bpf_iter_reg bpf_sk_storage_map_reg_info = { + .target = "bpf_sk_storage_map", + .check_target = bpf_iter_check_map, + .req_linfo = BPF_ITER_LINK_MAP_FD, + .ctx_arg_info_size = 2, + .ctx_arg_info = { + { offsetof(struct bpf_iter__bpf_sk_storage_map, sk), + PTR_TO_BTF_ID_OR_NULL }, + { offsetof(struct bpf_iter__bpf_sk_storage_map, value), + PTR_TO_RDWR_BUF_OR_NULL }, + }, + .seq_info = &iter_seq_info, +}; + +static int __init bpf_sk_storage_map_iter_init(void) +{ + bpf_sk_storage_map_reg_info.ctx_arg_info[0].btf_id = + btf_sock_ids[BTF_SOCK_TYPE_SOCK]; + return bpf_iter_reg_target(&bpf_sk_storage_map_reg_info); +} +late_initcall(bpf_sk_storage_map_iter_init); |