From 5d839021675a2e1b76653189cc6a90cfd8e30a69 Mon Sep 17 00:00:00 2001 From: Alexei Starovoitov Date: Tue, 21 May 2019 20:17:05 -0700 Subject: [PATCH 1/3] bpf: cleanup explored_states clean up explored_states to prep for introduction of hashtable No functional changes. Signed-off-by: Alexei Starovoitov Signed-off-by: Daniel Borkmann --- kernel/bpf/verifier.c | 29 ++++++++++++++++++++--------- 1 file changed, 20 insertions(+), 9 deletions(-) diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index 3f8b5443cc67..736b5a0d4848 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -5437,6 +5437,17 @@ enum { }; #define STATE_LIST_MARK ((struct bpf_verifier_state_list *) -1L) +static struct bpf_verifier_state_list **explored_state( + struct bpf_verifier_env *env, + int idx) +{ + return &env->explored_states[idx]; +} + +static void init_explored_state(struct bpf_verifier_env *env, int idx) +{ + env->explored_states[idx] = STATE_LIST_MARK; +} /* t, w, e - match pseudo-code above: * t - index of current instruction @@ -5462,7 +5473,7 @@ static int push_insn(int t, int w, int e, struct bpf_verifier_env *env) if (e == BRANCH) /* mark branch target for state pruning */ - env->explored_states[w] = STATE_LIST_MARK; + init_explored_state(env, w); if (insn_state[w] == 0) { /* tree-edge */ @@ -5530,9 +5541,9 @@ static int check_cfg(struct bpf_verifier_env *env) else if (ret < 0) goto err_free; if (t + 1 < insn_cnt) - env->explored_states[t + 1] = STATE_LIST_MARK; + init_explored_state(env, t + 1); if (insns[t].src_reg == BPF_PSEUDO_CALL) { - env->explored_states[t] = STATE_LIST_MARK; + init_explored_state(env, t); ret = push_insn(t, t + insns[t].imm + 1, BRANCH, env); if (ret == 1) goto peek_stack; @@ -5555,10 +5566,10 @@ static int check_cfg(struct bpf_verifier_env *env) * after every call and jump */ if (t + 1 < insn_cnt) - env->explored_states[t + 1] = STATE_LIST_MARK; + init_explored_state(env, t + 1); } else { /* conditional jump with two edges */ - env->explored_states[t] = STATE_LIST_MARK; + init_explored_state(env, t); ret = push_insn(t, t + 1, FALLTHROUGH, env); if (ret == 1) goto peek_stack; @@ -6006,7 +6017,7 @@ static void clean_live_states(struct bpf_verifier_env *env, int insn, struct bpf_verifier_state_list *sl; int i; - sl = env->explored_states[insn]; + sl = *explored_state(env, insn); if (!sl) return; @@ -6365,7 +6376,7 @@ static int is_state_visited(struct bpf_verifier_env *env, int insn_idx) struct bpf_verifier_state *cur = env->cur_state, *new; int i, j, err, states_cnt = 0; - pprev = &env->explored_states[insn_idx]; + pprev = explored_state(env, insn_idx); sl = *pprev; if (!sl) @@ -6452,8 +6463,8 @@ static int is_state_visited(struct bpf_verifier_env *env, int insn_idx) kfree(new_sl); return err; } - new_sl->next = env->explored_states[insn_idx]; - env->explored_states[insn_idx] = new_sl; + new_sl->next = *explored_state(env, insn_idx); + *explored_state(env, insn_idx) = new_sl; /* connect new state to parentage chain. Current frame needs all * registers connected. Only r6 - r9 of the callers are alive (pushed * to the stack implicitly by JITs) so in callers' frames connect just From a8f500af0ccffc3d2aaf9018537981cb173865a1 Mon Sep 17 00:00:00 2001 From: Alexei Starovoitov Date: Tue, 21 May 2019 20:17:06 -0700 Subject: [PATCH 2/3] bpf: split explored_states split explored_states into prune_point boolean mark and link list of explored states. This removes STATE_LIST_MARK hack and allows marks to be separate from states. Signed-off-by: Alexei Starovoitov Signed-off-by: Daniel Borkmann --- include/linux/bpf_verifier.h | 1 + kernel/bpf/verifier.c | 31 +++++++++++++------------------ 2 files changed, 14 insertions(+), 18 deletions(-) diff --git a/include/linux/bpf_verifier.h b/include/linux/bpf_verifier.h index 1305ccbd8fe6..02bba09a0ea1 100644 --- a/include/linux/bpf_verifier.h +++ b/include/linux/bpf_verifier.h @@ -233,6 +233,7 @@ struct bpf_insn_aux_data { int sanitize_stack_off; /* stack slot to be cleared */ bool seen; /* this insn was processed by the verifier */ u8 alu_state; /* used in combination with alu_limit */ + bool prune_point; unsigned int orig_idx; /* original instruction index */ }; diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index 736b5a0d4848..6a3e69ba891e 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -5436,7 +5436,6 @@ enum { BRANCH = 2, }; -#define STATE_LIST_MARK ((struct bpf_verifier_state_list *) -1L) static struct bpf_verifier_state_list **explored_state( struct bpf_verifier_env *env, int idx) @@ -5446,7 +5445,7 @@ static struct bpf_verifier_state_list **explored_state( static void init_explored_state(struct bpf_verifier_env *env, int idx) { - env->explored_states[idx] = STATE_LIST_MARK; + env->insn_aux_data[idx].prune_point = true; } /* t, w, e - match pseudo-code above: @@ -6018,10 +6017,7 @@ static void clean_live_states(struct bpf_verifier_env *env, int insn, int i; sl = *explored_state(env, insn); - if (!sl) - return; - - while (sl != STATE_LIST_MARK) { + while (sl) { if (sl->state.curframe != cur->curframe) goto next; for (i = 0; i <= cur->curframe; i++) @@ -6376,18 +6372,18 @@ static int is_state_visited(struct bpf_verifier_env *env, int insn_idx) struct bpf_verifier_state *cur = env->cur_state, *new; int i, j, err, states_cnt = 0; - pprev = explored_state(env, insn_idx); - sl = *pprev; - - if (!sl) + if (!env->insn_aux_data[insn_idx].prune_point) /* this 'insn_idx' instruction wasn't marked, so we will not * be doing state search here */ return 0; + pprev = explored_state(env, insn_idx); + sl = *pprev; + clean_live_states(env, insn_idx, cur); - while (sl != STATE_LIST_MARK) { + while (sl) { if (states_equal(env, &sl->state, cur)) { sl->hit_cnt++; /* reached equivalent register/stack state, @@ -8145,13 +8141,12 @@ static void free_states(struct bpf_verifier_env *env) for (i = 0; i < env->prog->len; i++) { sl = env->explored_states[i]; - if (sl) - while (sl != STATE_LIST_MARK) { - sln = sl->next; - free_verifier_state(&sl->state, false); - kfree(sl); - sl = sln; - } + while (sl) { + sln = sl->next; + free_verifier_state(&sl->state, false); + kfree(sl); + sl = sln; + } } kvfree(env->explored_states); From dc2a4ebc0b44a212fcf72242210e56aa17e7317b Mon Sep 17 00:00:00 2001 From: Alexei Starovoitov Date: Tue, 21 May 2019 20:17:07 -0700 Subject: [PATCH 3/3] bpf: convert explored_states to hash table All prune points inside a callee bpf function most likely will have different callsites. For example, if function foo() is called from two callsites the half of explored states in all prune points in foo() will be useless for subsequent walking of one of those callsites. Fortunately explored_states pruning heuristics keeps the number of states per prune point small, but walking these states is still a waste of cpu time when the callsite of the current state is different from the callsite of the explored state. To improve pruning logic convert explored_states into hash table and use simple insn_idx ^ callsite hash to select hash bucket. This optimization has no effect on programs without bpf2bpf calls and drastically improves programs with calls. In the later case it reduces total memory consumption in 1M scale tests by almost 3 times (peak_states drops from 5752 to 2016). Care should be taken when comparing the states for equivalency. Since the same hash bucket can now contain states with different indices the insn_idx has to be part of verifier_state and compared. Different hash table sizes and different hash functions were explored, but the results were not significantly better vs this patch. They can be improved in the future. Hit/miss heuristic is not counting index miscompare as a miss. Otherwise verifier stats become unstable when experimenting with different hash functions. Signed-off-by: Alexei Starovoitov Signed-off-by: Daniel Borkmann --- include/linux/bpf_verifier.h | 1 + kernel/bpf/verifier.c | 23 ++++++++++++++++++----- 2 files changed, 19 insertions(+), 5 deletions(-) diff --git a/include/linux/bpf_verifier.h b/include/linux/bpf_verifier.h index 02bba09a0ea1..405b502283c5 100644 --- a/include/linux/bpf_verifier.h +++ b/include/linux/bpf_verifier.h @@ -187,6 +187,7 @@ struct bpf_func_state { struct bpf_verifier_state { /* call stack tracking */ struct bpf_func_state *frame[MAX_CALL_FRAMES]; + u32 insn_idx; u32 curframe; u32 active_spin_lock; bool speculative; diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index 6a3e69ba891e..550091c7a46a 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -5436,11 +5436,19 @@ enum { BRANCH = 2, }; +static u32 state_htab_size(struct bpf_verifier_env *env) +{ + return env->prog->len; +} + static struct bpf_verifier_state_list **explored_state( struct bpf_verifier_env *env, int idx) { - return &env->explored_states[idx]; + struct bpf_verifier_state *cur = env->cur_state; + struct bpf_func_state *state = cur->frame[cur->curframe]; + + return &env->explored_states[(idx ^ state->callsite) % state_htab_size(env)]; } static void init_explored_state(struct bpf_verifier_env *env, int idx) @@ -6018,7 +6026,8 @@ static void clean_live_states(struct bpf_verifier_env *env, int insn, sl = *explored_state(env, insn); while (sl) { - if (sl->state.curframe != cur->curframe) + if (sl->state.insn_idx != insn || + sl->state.curframe != cur->curframe) goto next; for (i = 0; i <= cur->curframe; i++) if (sl->state.frame[i]->callsite != cur->frame[i]->callsite) @@ -6384,6 +6393,9 @@ static int is_state_visited(struct bpf_verifier_env *env, int insn_idx) clean_live_states(env, insn_idx, cur); while (sl) { + states_cnt++; + if (sl->state.insn_idx != insn_idx) + goto next; if (states_equal(env, &sl->state, cur)) { sl->hit_cnt++; /* reached equivalent register/stack state, @@ -6401,7 +6413,6 @@ static int is_state_visited(struct bpf_verifier_env *env, int insn_idx) return err; return 1; } - states_cnt++; sl->miss_cnt++; /* heuristic to determine whether this state is beneficial * to keep checking from state equivalence point of view. @@ -6428,6 +6439,7 @@ static int is_state_visited(struct bpf_verifier_env *env, int insn_idx) sl = *pprev; continue; } +next: pprev = &sl->next; sl = *pprev; } @@ -6459,6 +6471,7 @@ static int is_state_visited(struct bpf_verifier_env *env, int insn_idx) kfree(new_sl); return err; } + new->insn_idx = insn_idx; new_sl->next = *explored_state(env, insn_idx); *explored_state(env, insn_idx) = new_sl; /* connect new state to parentage chain. Current frame needs all @@ -8138,7 +8151,7 @@ static void free_states(struct bpf_verifier_env *env) if (!env->explored_states) return; - for (i = 0; i < env->prog->len; i++) { + for (i = 0; i < state_htab_size(env); i++) { sl = env->explored_states[i]; while (sl) { @@ -8246,7 +8259,7 @@ int bpf_check(struct bpf_prog **prog, union bpf_attr *attr, goto skip_full_check; } - env->explored_states = kvcalloc(env->prog->len, + env->explored_states = kvcalloc(state_htab_size(env), sizeof(struct bpf_verifier_state_list *), GFP_USER); ret = -ENOMEM;