Merge branch 'bpf-verifier-scalability'

Alexei Starovoitov says:

====================
v1->v2:
- fixed typo in patch 1
- added a patch to convert kcalloc to kvcalloc
- added a patch to verbose 16-bit jump offset check
- added a test with 1m insns

This patch set is the first step to be able to accept large programs.
The verifier still suffers from its brute force algorithm and
large programs can easily hit 1M insn_processed limit.
A lot more work is necessary to be able to verify large programs.

v1:
Realize two key ideas to speed up verification speed by ~20 times
1. every 'branching' instructions records all verifier states.
   not all of them are useful for search pruning.
   add a simple heuristic to keep states that were successful in search pruning
   and remove those that were not
2. mark_reg_read walks parentage chain of registers to mark parents as LIVE_READ.
   Once the register is marked there is no need to remark it again in the future.
   Hence stop walking the chain once first LIVE_READ is seen.

1st optimization gives 10x speed up on large programs
and 2nd optimization reduces the cost of mark_reg_read from ~40% of cpu to <1%.
Combined the deliver ~20x speedup on large programs.

Faster and bounded verification time allows to increase insn_processed
limit to 1 million from 130k.
Worst case it takes 1/10 of a second to process that many instructions
and peak memory consumption is peak_states * sizeof(struct bpf_verifier_state)
which is around ~5Mbyte.

Increase insn_per_program limit for root to insn_processed limit.

Add verification stats and stress tests for verifier scalability.
====================

Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>

2 files changed, 24 insertions, 0 deletions

diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index f62897198844..a445194b5fb6 100644
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -421,6 +421,7 @@ struct bpf_array {
 	};
 };
 
+#define BPF_COMPLEXITY_LIMIT_INSNS      1000000 /* yes. 1M insns */
 #define MAX_TAIL_CALL_CNT 32
 
 struct bpf_event_entry {
diff --git a/include/linux/bpf_verifier.h b/include/linux/bpf_verifier.h
index 7d8228d1c898..fc8254d6b569 100644
--- a/include/linux/bpf_verifier.h
+++ b/include/linux/bpf_verifier.h
@@ -207,6 +207,7 @@ struct bpf_verifier_state {
 struct bpf_verifier_state_list {
 	struct bpf_verifier_state state;
 	struct bpf_verifier_state_list *next;
+	int miss_cnt, hit_cnt;
 };
 
 /* Possible states for alu_state member. */
@@ -248,6 +249,12 @@ static inline bool bpf_verifier_log_full(const struct bpf_verifier_log *log)
 	return log->len_used >= log->len_total - 1;
 }
 
+#define BPF_LOG_LEVEL1	1
+#define BPF_LOG_LEVEL2	2
+#define BPF_LOG_STATS	4
+#define BPF_LOG_LEVEL	(BPF_LOG_LEVEL1 | BPF_LOG_LEVEL2)
+#define BPF_LOG_MASK	(BPF_LOG_LEVEL | BPF_LOG_STATS)
+
 static inline bool bpf_verifier_log_needed(const struct bpf_verifier_log *log)
 {
 	return log->level && log->ubuf && !bpf_verifier_log_full(log);
@@ -274,6 +281,7 @@ struct bpf_verifier_env {
 	bool strict_alignment;		/* perform strict pointer alignment checks */
 	struct bpf_verifier_state *cur_state; /* current verifier state */
 	struct bpf_verifier_state_list **explored_states; /* search pruning optimization */
+	struct bpf_verifier_state_list *free_list;
 	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 */
@@ -284,6 +292,21 @@ struct bpf_verifier_env {
 	struct bpf_verifier_log log;
 	struct bpf_subprog_info subprog_info[BPF_MAX_SUBPROGS + 1];
 	u32 subprog_cnt;
+	/* number of instructions analyzed by the verifier */
+	u32 insn_processed;
+	/* total verification time */
+	u64 verification_time;
+	/* maximum number of verifier states kept in 'branching' instructions */
+	u32 max_states_per_insn;
+	/* total number of allocated verifier states */
+	u32 total_states;
+	/* some states are freed during program analysis.
+	 * this is peak number of states. this number dominates kernel
+	 * memory consumption during verification
+	 */
+	u32 peak_states;
+	/* longest register parentage chain walked for liveness marking */
+	u32 longest_mark_read_walk;
 };
 
 __printf(2, 0) void bpf_verifier_vlog(struct bpf_verifier_log *log,