From e88a2766143a27bfe6704b4493b214de4094cf29 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Mon, 14 Nov 2016 16:28:42 -0800 Subject: gro_cells: mark napi struct as not busy poll candidates Rolf Neugebauer reported very long delays at netns dismantle. Eric W. Biederman was kind enough to look at this problem and noticed synchronize_net() occurring from netif_napi_del() that was added in linux-4.5 Busy polling makes no sense for tunnels NAPI. If busy poll is used for sessions over tunnels, the poller will need to poll the physical device queue anyway. netif_tx_napi_add() could be used here, but function name is misleading, and renaming it is not stable material, so set NAPI_STATE_NO_BUSY_POLL bit directly. This will avoid inserting gro_cells napi structures in napi_hash[] and avoid the problematic synchronize_net() (per possible cpu) that Rolf reported. Fixes: 93d05d4a320c ("net: provide generic busy polling to all NAPI drivers") Signed-off-by: Eric Dumazet Reported-by: Rolf Neugebauer Reported-by: Eric W. Biederman Acked-by: Cong Wang Tested-by: Rolf Neugebauer Signed-off-by: David S. Miller --- include/net/gro_cells.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include') diff --git a/include/net/gro_cells.h b/include/net/gro_cells.h index d15214d673b2..2a1abbf8da74 100644 --- a/include/net/gro_cells.h +++ b/include/net/gro_cells.h @@ -68,6 +68,9 @@ static inline int gro_cells_init(struct gro_cells *gcells, struct net_device *de struct gro_cell *cell = per_cpu_ptr(gcells->cells, i); __skb_queue_head_init(&cell->napi_skbs); + + set_bit(NAPI_STATE_NO_BUSY_POLL, &cell->napi.state); + netif_napi_add(dev, &cell->napi, gro_cell_poll, 64); napi_enable(&cell->napi); } -- cgit v1.2.3 From f23cc643f9baec7f71f2b74692da3cf03abbbfda Mon Sep 17 00:00:00 2001 From: Josef Bacik Date: Mon, 14 Nov 2016 15:45:36 -0500 Subject: bpf: fix range arithmetic for bpf map access I made some invalid assumptions with BPF_AND and BPF_MOD that could result in invalid accesses to bpf map entries. Fix this up by doing a few things 1) Kill BPF_MOD support. This doesn't actually get used by the compiler in real life and just adds extra complexity. 2) Fix the logic for BPF_AND, don't allow AND of negative numbers and set the minimum value to 0 for positive AND's. 3) Don't do operations on the ranges if they are set to the limits, as they are by definition undefined, and allowing arithmetic operations on those values could make them appear valid when they really aren't. This fixes the testcase provided by Jann as well as a few other theoretical problems. Reported-by: Jann Horn Signed-off-by: Josef Bacik Acked-by: Alexei Starovoitov Signed-off-by: David S. Miller --- include/linux/bpf_verifier.h | 5 ++-- kernel/bpf/verifier.c | 70 +++++++++++++++++++++++++++++--------------- 2 files changed, 50 insertions(+), 25 deletions(-) (limited to 'include') diff --git a/include/linux/bpf_verifier.h b/include/linux/bpf_verifier.h index 7035b997aaa5..6aaf425cebc3 100644 --- a/include/linux/bpf_verifier.h +++ b/include/linux/bpf_verifier.h @@ -14,7 +14,7 @@ * are obviously wrong for any sort of memory access. */ #define BPF_REGISTER_MAX_RANGE (1024 * 1024 * 1024) -#define BPF_REGISTER_MIN_RANGE -(1024 * 1024 * 1024) +#define BPF_REGISTER_MIN_RANGE -1 struct bpf_reg_state { enum bpf_reg_type type; @@ -22,7 +22,8 @@ struct bpf_reg_state { * Used to determine if any memory access using this register will * result in a bad access. */ - u64 min_value, max_value; + s64 min_value; + u64 max_value; union { /* valid when type == CONST_IMM | PTR_TO_STACK | UNKNOWN_VALUE */ s64 imm; diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index 99a7e5b388f2..6a936159c6e0 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -216,8 +216,8 @@ static void print_verifier_state(struct bpf_verifier_state *state) reg->map_ptr->key_size, reg->map_ptr->value_size); if (reg->min_value != BPF_REGISTER_MIN_RANGE) - verbose(",min_value=%llu", - (unsigned long long)reg->min_value); + verbose(",min_value=%lld", + (long long)reg->min_value); if (reg->max_value != BPF_REGISTER_MAX_RANGE) verbose(",max_value=%llu", (unsigned long long)reg->max_value); @@ -758,7 +758,7 @@ static int check_mem_access(struct bpf_verifier_env *env, u32 regno, int off, * index'es we need to make sure that whatever we use * will have a set floor within our range. */ - if ((s64)reg->min_value < 0) { + if (reg->min_value < 0) { verbose("R%d min value is negative, either use unsigned index or do a if (index >=0) check.\n", regno); return -EACCES; @@ -1468,7 +1468,8 @@ static void check_reg_overflow(struct bpf_reg_state *reg) { if (reg->max_value > BPF_REGISTER_MAX_RANGE) reg->max_value = BPF_REGISTER_MAX_RANGE; - if ((s64)reg->min_value < BPF_REGISTER_MIN_RANGE) + if (reg->min_value < BPF_REGISTER_MIN_RANGE || + reg->min_value > BPF_REGISTER_MAX_RANGE) reg->min_value = BPF_REGISTER_MIN_RANGE; } @@ -1476,7 +1477,8 @@ static void adjust_reg_min_max_vals(struct bpf_verifier_env *env, struct bpf_insn *insn) { struct bpf_reg_state *regs = env->cur_state.regs, *dst_reg; - u64 min_val = BPF_REGISTER_MIN_RANGE, max_val = BPF_REGISTER_MAX_RANGE; + s64 min_val = BPF_REGISTER_MIN_RANGE; + u64 max_val = BPF_REGISTER_MAX_RANGE; bool min_set = false, max_set = false; u8 opcode = BPF_OP(insn->code); @@ -1512,22 +1514,43 @@ static void adjust_reg_min_max_vals(struct bpf_verifier_env *env, return; } + /* If one of our values was at the end of our ranges then we can't just + * do our normal operations to the register, we need to set the values + * to the min/max since they are undefined. + */ + if (min_val == BPF_REGISTER_MIN_RANGE) + dst_reg->min_value = BPF_REGISTER_MIN_RANGE; + if (max_val == BPF_REGISTER_MAX_RANGE) + dst_reg->max_value = BPF_REGISTER_MAX_RANGE; + switch (opcode) { case BPF_ADD: - dst_reg->min_value += min_val; - dst_reg->max_value += max_val; + if (dst_reg->min_value != BPF_REGISTER_MIN_RANGE) + dst_reg->min_value += min_val; + if (dst_reg->max_value != BPF_REGISTER_MAX_RANGE) + dst_reg->max_value += max_val; break; case BPF_SUB: - dst_reg->min_value -= min_val; - dst_reg->max_value -= max_val; + if (dst_reg->min_value != BPF_REGISTER_MIN_RANGE) + dst_reg->min_value -= min_val; + if (dst_reg->max_value != BPF_REGISTER_MAX_RANGE) + dst_reg->max_value -= max_val; break; case BPF_MUL: - dst_reg->min_value *= min_val; - dst_reg->max_value *= max_val; + if (dst_reg->min_value != BPF_REGISTER_MIN_RANGE) + dst_reg->min_value *= min_val; + if (dst_reg->max_value != BPF_REGISTER_MAX_RANGE) + dst_reg->max_value *= max_val; break; case BPF_AND: - /* & is special since it could end up with 0 bits set. */ - dst_reg->min_value &= min_val; + /* Disallow AND'ing of negative numbers, ain't nobody got time + * for that. Otherwise the minimum is 0 and the max is the max + * value we could AND against. + */ + if (min_val < 0) + dst_reg->min_value = BPF_REGISTER_MIN_RANGE; + else + dst_reg->min_value = 0; dst_reg->max_value = max_val; break; case BPF_LSH: @@ -1537,24 +1560,25 @@ static void adjust_reg_min_max_vals(struct bpf_verifier_env *env, */ if (min_val > ilog2(BPF_REGISTER_MAX_RANGE)) dst_reg->min_value = BPF_REGISTER_MIN_RANGE; - else + else if (dst_reg->min_value != BPF_REGISTER_MIN_RANGE) dst_reg->min_value <<= min_val; if (max_val > ilog2(BPF_REGISTER_MAX_RANGE)) dst_reg->max_value = BPF_REGISTER_MAX_RANGE; - else + else if (dst_reg->max_value != BPF_REGISTER_MAX_RANGE) dst_reg->max_value <<= max_val; break; case BPF_RSH: - dst_reg->min_value >>= min_val; - dst_reg->max_value >>= max_val; - break; - case BPF_MOD: - /* % is special since it is an unsigned modulus, so the floor - * will always be 0. + /* RSH by a negative number is undefined, and the BPF_RSH is an + * unsigned shift, so make the appropriate casts. */ - dst_reg->min_value = 0; - dst_reg->max_value = max_val - 1; + if (min_val < 0 || dst_reg->min_value < 0) + dst_reg->min_value = BPF_REGISTER_MIN_RANGE; + else + dst_reg->min_value = + (u64)(dst_reg->min_value) >> min_val; + if (dst_reg->max_value != BPF_REGISTER_MAX_RANGE) + dst_reg->max_value >>= max_val; break; default: reset_reg_range_values(regs, insn->dst_reg); -- cgit v1.2.3 From 3b7093346b326e5d3590c7d49f6aefe6fa5b2c9a Mon Sep 17 00:00:00 2001 From: Alexander Duyck Date: Tue, 15 Nov 2016 05:46:06 -0500 Subject: ipv4: Restore fib_trie_flush_external function and fix call ordering The patch that removed the FIB offload infrastructure was a bit too aggressive and also removed code needed to clean up us splitting the table if additional rules were added. Specifically the function fib_trie_flush_external was called at the end of a new rule being added to flush the foreign trie entries from the main trie. I updated the code so that we only call fib_trie_flush_external on the main table so that we flush the entries for local from main. This way we don't call it for every rule change which is what was happening previously. Fixes: 347e3b28c1ba2 ("switchdev: remove FIB offload infrastructure") Reported-by: Eric Dumazet Cc: Jiri Pirko Signed-off-by: Alexander Duyck Acked-by: Eric Dumazet Signed-off-by: David S. Miller --- include/net/ip_fib.h | 1 + net/ipv4/fib_frontend.c | 20 +++++++++++---- net/ipv4/fib_trie.c | 65 +++++++++++++++++++++++++++++++++++++++++++++++++ 3 files changed, 81 insertions(+), 5 deletions(-) (limited to 'include') diff --git a/include/net/ip_fib.h b/include/net/ip_fib.h index b9314b48e39f..f390c3bb05c5 100644 --- a/include/net/ip_fib.h +++ b/include/net/ip_fib.h @@ -243,6 +243,7 @@ int fib_table_dump(struct fib_table *table, struct sk_buff *skb, struct netlink_callback *cb); int fib_table_flush(struct net *net, struct fib_table *table); struct fib_table *fib_trie_unmerge(struct fib_table *main_tb); +void fib_table_flush_external(struct fib_table *table); void fib_free_table(struct fib_table *tb); #ifndef CONFIG_IP_MULTIPLE_TABLES diff --git a/net/ipv4/fib_frontend.c b/net/ipv4/fib_frontend.c index c3b80478226e..161fc0f0d752 100644 --- a/net/ipv4/fib_frontend.c +++ b/net/ipv4/fib_frontend.c @@ -151,7 +151,7 @@ static void fib_replace_table(struct net *net, struct fib_table *old, int fib_unmerge(struct net *net) { - struct fib_table *old, *new; + struct fib_table *old, *new, *main_table; /* attempt to fetch local table if it has been allocated */ old = fib_get_table(net, RT_TABLE_LOCAL); @@ -162,11 +162,21 @@ int fib_unmerge(struct net *net) if (!new) return -ENOMEM; + /* table is already unmerged */ + if (new == old) + return 0; + /* replace merged table with clean table */ - if (new != old) { - fib_replace_table(net, old, new); - fib_free_table(old); - } + fib_replace_table(net, old, new); + fib_free_table(old); + + /* attempt to fetch main table if it has been allocated */ + main_table = fib_get_table(net, RT_TABLE_MAIN); + if (!main_table) + return 0; + + /* flush local entries from main table */ + fib_table_flush_external(main_table); return 0; } diff --git a/net/ipv4/fib_trie.c b/net/ipv4/fib_trie.c index 4cff74d4133f..735edc9d41a2 100644 --- a/net/ipv4/fib_trie.c +++ b/net/ipv4/fib_trie.c @@ -1760,6 +1760,71 @@ out: return NULL; } +/* Caller must hold RTNL */ +void fib_table_flush_external(struct fib_table *tb) +{ + struct trie *t = (struct trie *)tb->tb_data; + struct key_vector *pn = t->kv; + unsigned long cindex = 1; + struct hlist_node *tmp; + struct fib_alias *fa; + + /* walk trie in reverse order */ + for (;;) { + unsigned char slen = 0; + struct key_vector *n; + + if (!(cindex--)) { + t_key pkey = pn->key; + + /* cannot resize the trie vector */ + if (IS_TRIE(pn)) + break; + + /* resize completed node */ + pn = resize(t, pn); + cindex = get_index(pkey, pn); + + continue; + } + + /* grab the next available node */ + n = get_child(pn, cindex); + if (!n) + continue; + + if (IS_TNODE(n)) { + /* record pn and cindex for leaf walking */ + pn = n; + cindex = 1ul << n->bits; + + continue; + } + + hlist_for_each_entry_safe(fa, tmp, &n->leaf, fa_list) { + /* if alias was cloned to local then we just + * need to remove the local copy from main + */ + if (tb->tb_id != fa->tb_id) { + hlist_del_rcu(&fa->fa_list); + alias_free_mem_rcu(fa); + continue; + } + + /* record local slen */ + slen = fa->fa_slen; + } + + /* update leaf slen */ + n->slen = slen; + + if (hlist_empty(&n->leaf)) { + put_child_root(pn, n->key, NULL); + node_free(n); + } + } +} + /* Caller must hold RTNL. */ int fib_table_flush(struct net *net, struct fib_table *tb) { -- cgit v1.2.3 From 0f5258cd91e9d78a1ee30696314bec3c33321a93 Mon Sep 17 00:00:00 2001 From: Stefan Hajnoczi Date: Fri, 18 Nov 2016 09:41:46 +0000 Subject: netns: fix get_net_ns_by_fd(int pid) typo The argument to get_net_ns_by_fd() is a /proc/$PID/ns/net file descriptor not a pid. Fix the typo. Signed-off-by: Stefan Hajnoczi Acked-by: Rami Rosen Signed-off-by: David S. Miller --- include/net/net_namespace.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/net/net_namespace.h b/include/net/net_namespace.h index fc4f757107df..0940598c002f 100644 --- a/include/net/net_namespace.h +++ b/include/net/net_namespace.h @@ -170,7 +170,7 @@ static inline struct net *copy_net_ns(unsigned long flags, extern struct list_head net_namespace_list; struct net *get_net_ns_by_pid(pid_t pid); -struct net *get_net_ns_by_fd(int pid); +struct net *get_net_ns_by_fd(int fd); #ifdef CONFIG_SYSCTL void ipx_register_sysctl(void); -- cgit v1.2.3