diff options
author | Linus Torvalds <torvalds@linux-foundation.org> | 2016-08-18 02:26:58 +0200 |
---|---|---|
committer | Linus Torvalds <torvalds@linux-foundation.org> | 2016-08-18 02:26:58 +0200 |
commit | 184ca823481c99dadd7d946e5afd4bb921eab30d (patch) | |
tree | fd636fe467bf11ae3a11ea5d36d860296705b58f /kernel | |
parent | Merge tag 'for-v4.8-rc' of git://git.kernel.org/pub/scm/linux/kernel/git/sre/... (diff) | |
parent | Merge branch 'tc_action-fixes' (diff) | |
download | linux-184ca823481c99dadd7d946e5afd4bb921eab30d.tar.xz linux-184ca823481c99dadd7d946e5afd4bb921eab30d.zip |
Merge git://git.kernel.org/pub/scm/linux/kernel/git/davem/net
Pull networking fixes from David Miller:
1) Buffers powersave frame test is reversed in cfg80211, fix from Felix
Fietkau.
2) Remove bogus WARN_ON in openvswitch, from Jarno Rajahalme.
3) Fix some tg3 ethtool logic bugs, and one that would cause no
interrupts to be generated when rx-coalescing is set to 0. From
Satish Baddipadige and Siva Reddy Kallam.
4) QLCNIC mailbox corruption and napi budget handling fix from Manish
Chopra.
5) Fix fib_trie logic when walking the trie during /proc/net/route
output than can access a stale node pointer. From David Forster.
6) Several sctp_diag fixes from Phil Sutter.
7) PAUSE frame handling fixes in mlxsw driver from Ido Schimmel.
8) Checksum fixup fixes in bpf from Daniel Borkmann.
9) Memork leaks in nfnetlink, from Liping Zhang.
10) Use after free in rxrpc, from David Howells.
11) Use after free in new skb_array code of macvtap driver, from Jason
Wang.
12) Calipso resource leak, from Colin Ian King.
13) mediatek bug fixes (missing stats sync init, etc.) from Sean Wang.
14) Fix bpf non-linear packet write helpers, from Daniel Borkmann.
15) Fix lockdep splats in macsec, from Sabrina Dubroca.
16) hv_netvsc bug fixes from Vitaly Kuznetsov, mostly to do with VF
handling.
17) Various tc-action bug fixes, from CONG Wang.
* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net: (116 commits)
net_sched: allow flushing tc police actions
net_sched: unify the init logic for act_police
net_sched: convert tcf_exts from list to pointer array
net_sched: move tc offload macros to pkt_cls.h
net_sched: fix a typo in tc_for_each_action()
net_sched: remove an unnecessary list_del()
net_sched: remove the leftover cleanup_a()
mlxsw: spectrum: Allow packets to be trapped from any PG
mlxsw: spectrum: Unmap 802.1Q FID before destroying it
mlxsw: spectrum: Add missing rollbacks in error path
mlxsw: reg: Fix missing op field fill-up
mlxsw: spectrum: Trap loop-backed packets
mlxsw: spectrum: Add missing packet traps
mlxsw: spectrum: Mark port as active before registering it
mlxsw: spectrum: Create PVID vPort before registering netdevice
mlxsw: spectrum: Remove redundant errors from the code
mlxsw: spectrum: Don't return upon error in removal path
i40e: check for and deal with non-contiguous TCs
ixgbe: Re-enable ability to toggle VLAN filtering
ixgbe: Force VLNCTRL.VFE to be set in all VMDq paths
...
Diffstat (limited to 'kernel')
-rw-r--r-- | kernel/bpf/hashtab.c | 84 | ||||
-rw-r--r-- | kernel/bpf/verifier.c | 7 |
2 files changed, 77 insertions, 14 deletions
diff --git a/kernel/bpf/hashtab.c b/kernel/bpf/hashtab.c index fff3650d52fc..570eeca7bdfa 100644 --- a/kernel/bpf/hashtab.c +++ b/kernel/bpf/hashtab.c @@ -26,11 +26,18 @@ struct bpf_htab { struct bucket *buckets; void *elems; struct pcpu_freelist freelist; + void __percpu *extra_elems; atomic_t count; /* number of elements in this hashtable */ u32 n_buckets; /* number of hash buckets */ u32 elem_size; /* size of each element in bytes */ }; +enum extra_elem_state { + HTAB_NOT_AN_EXTRA_ELEM = 0, + HTAB_EXTRA_ELEM_FREE, + HTAB_EXTRA_ELEM_USED +}; + /* each htab element is struct htab_elem + key + value */ struct htab_elem { union { @@ -38,7 +45,10 @@ struct htab_elem { struct bpf_htab *htab; struct pcpu_freelist_node fnode; }; - struct rcu_head rcu; + union { + struct rcu_head rcu; + enum extra_elem_state state; + }; u32 hash; char key[0] __aligned(8); }; @@ -113,6 +123,23 @@ free_elems: return err; } +static int alloc_extra_elems(struct bpf_htab *htab) +{ + void __percpu *pptr; + int cpu; + + pptr = __alloc_percpu_gfp(htab->elem_size, 8, GFP_USER | __GFP_NOWARN); + if (!pptr) + return -ENOMEM; + + for_each_possible_cpu(cpu) { + ((struct htab_elem *)per_cpu_ptr(pptr, cpu))->state = + HTAB_EXTRA_ELEM_FREE; + } + htab->extra_elems = pptr; + return 0; +} + /* Called from syscall */ static struct bpf_map *htab_map_alloc(union bpf_attr *attr) { @@ -185,6 +212,8 @@ static struct bpf_map *htab_map_alloc(union bpf_attr *attr) if (percpu) cost += (u64) round_up(htab->map.value_size, 8) * num_possible_cpus() * htab->map.max_entries; + else + cost += (u64) htab->elem_size * num_possible_cpus(); if (cost >= U32_MAX - PAGE_SIZE) /* make sure page count doesn't overflow */ @@ -212,14 +241,22 @@ static struct bpf_map *htab_map_alloc(union bpf_attr *attr) raw_spin_lock_init(&htab->buckets[i].lock); } + if (!percpu) { + err = alloc_extra_elems(htab); + if (err) + goto free_buckets; + } + if (!(attr->map_flags & BPF_F_NO_PREALLOC)) { err = prealloc_elems_and_freelist(htab); if (err) - goto free_buckets; + goto free_extra_elems; } return &htab->map; +free_extra_elems: + free_percpu(htab->extra_elems); free_buckets: kvfree(htab->buckets); free_htab: @@ -349,7 +386,6 @@ static void htab_elem_free(struct bpf_htab *htab, struct htab_elem *l) if (htab->map.map_type == BPF_MAP_TYPE_PERCPU_HASH) free_percpu(htab_elem_get_ptr(l, htab->map.key_size)); kfree(l); - } static void htab_elem_free_rcu(struct rcu_head *head) @@ -370,6 +406,11 @@ static void htab_elem_free_rcu(struct rcu_head *head) static void free_htab_elem(struct bpf_htab *htab, struct htab_elem *l) { + if (l->state == HTAB_EXTRA_ELEM_USED) { + l->state = HTAB_EXTRA_ELEM_FREE; + return; + } + if (!(htab->map.map_flags & BPF_F_NO_PREALLOC)) { pcpu_freelist_push(&htab->freelist, &l->fnode); } else { @@ -381,25 +422,44 @@ static void free_htab_elem(struct bpf_htab *htab, struct htab_elem *l) static struct htab_elem *alloc_htab_elem(struct bpf_htab *htab, void *key, void *value, u32 key_size, u32 hash, - bool percpu, bool onallcpus) + bool percpu, bool onallcpus, + bool old_elem_exists) { u32 size = htab->map.value_size; bool prealloc = !(htab->map.map_flags & BPF_F_NO_PREALLOC); struct htab_elem *l_new; void __percpu *pptr; + int err = 0; if (prealloc) { l_new = (struct htab_elem *)pcpu_freelist_pop(&htab->freelist); if (!l_new) - return ERR_PTR(-E2BIG); + err = -E2BIG; } else { if (atomic_inc_return(&htab->count) > htab->map.max_entries) { atomic_dec(&htab->count); - return ERR_PTR(-E2BIG); + err = -E2BIG; + } else { + l_new = kmalloc(htab->elem_size, + GFP_ATOMIC | __GFP_NOWARN); + if (!l_new) + return ERR_PTR(-ENOMEM); } - l_new = kmalloc(htab->elem_size, GFP_ATOMIC | __GFP_NOWARN); - if (!l_new) - return ERR_PTR(-ENOMEM); + } + + if (err) { + if (!old_elem_exists) + return ERR_PTR(err); + + /* if we're updating the existing element and the hash table + * is full, use per-cpu extra elems + */ + l_new = this_cpu_ptr(htab->extra_elems); + if (l_new->state != HTAB_EXTRA_ELEM_FREE) + return ERR_PTR(-E2BIG); + l_new->state = HTAB_EXTRA_ELEM_USED; + } else { + l_new->state = HTAB_NOT_AN_EXTRA_ELEM; } memcpy(l_new->key, key, key_size); @@ -489,7 +549,8 @@ static int htab_map_update_elem(struct bpf_map *map, void *key, void *value, if (ret) goto err; - l_new = alloc_htab_elem(htab, key, value, key_size, hash, false, false); + l_new = alloc_htab_elem(htab, key, value, key_size, hash, false, false, + !!l_old); if (IS_ERR(l_new)) { /* all pre-allocated elements are in use or memory exhausted */ ret = PTR_ERR(l_new); @@ -563,7 +624,7 @@ static int __htab_percpu_map_update_elem(struct bpf_map *map, void *key, } } else { l_new = alloc_htab_elem(htab, key, value, key_size, - hash, true, onallcpus); + hash, true, onallcpus, false); if (IS_ERR(l_new)) { ret = PTR_ERR(l_new); goto err; @@ -652,6 +713,7 @@ static void htab_map_free(struct bpf_map *map) htab_free_elems(htab); pcpu_freelist_destroy(&htab->freelist); } + free_percpu(htab->extra_elems); kvfree(htab->buckets); kfree(htab); } diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index f72f23b8fdab..daea765d72e6 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -194,6 +194,7 @@ struct verifier_env { struct verifier_state_list **explored_states; /* search pruning optimization */ struct bpf_map *used_maps[MAX_USED_MAPS]; /* array of map's used by eBPF program */ u32 used_map_cnt; /* number of used maps */ + u32 id_gen; /* used to generate unique reg IDs */ bool allow_ptr_leaks; }; @@ -1052,7 +1053,7 @@ static int check_map_func_compatibility(struct bpf_map *map, int func_id) goto error; break; case BPF_MAP_TYPE_CGROUP_ARRAY: - if (func_id != BPF_FUNC_skb_in_cgroup) + if (func_id != BPF_FUNC_skb_under_cgroup) goto error; break; default: @@ -1074,7 +1075,7 @@ static int check_map_func_compatibility(struct bpf_map *map, int func_id) if (map->map_type != BPF_MAP_TYPE_STACK_TRACE) goto error; break; - case BPF_FUNC_skb_in_cgroup: + case BPF_FUNC_skb_under_cgroup: if (map->map_type != BPF_MAP_TYPE_CGROUP_ARRAY) goto error; break; @@ -1301,7 +1302,7 @@ add_imm: /* dst_reg stays as pkt_ptr type and since some positive * integer value was added to the pointer, increment its 'id' */ - dst_reg->id++; + dst_reg->id = ++env->id_gen; /* something was added to pkt_ptr, set range and off to zero */ dst_reg->off = 0; |