bpf: split bpf core interpreter

split __bpf_prog_run() interpreter into stack allocation and execution parts.
The code section shrinks which helps interpreter performance in some cases.
   text	   data	    bss	    dec	    hex	filename
  26350	  10328	    624	  37302	   91b6	kernel/bpf/core.o.before
  25777	  10328	    624	  36729	   8f79	kernel/bpf/core.o.after

Very short programs got slower (due to extra function call):
Before:
test_bpf: #89 ALU64_ADD_K: 1 + 2 = 3 jited:0 7 PASS
test_bpf: #90 ALU64_ADD_K: 3 + 0 = 3 jited:0 8 PASS
test_bpf: #91 ALU64_ADD_K: 1 + 2147483646 = 2147483647 jited:0 7 PASS
test_bpf: #92 ALU64_ADD_K: 4294967294 + 2 = 4294967296 jited:0 11 PASS
test_bpf: #93 ALU64_ADD_K: 2147483646 + -2147483647 = -1 jited:0 7 PASS
After:
test_bpf: #89 ALU64_ADD_K: 1 + 2 = 3 jited:0 11 PASS
test_bpf: #90 ALU64_ADD_K: 3 + 0 = 3 jited:0 11 PASS
test_bpf: #91 ALU64_ADD_K: 1 + 2147483646 = 2147483647 jited:0 11 PASS
test_bpf: #92 ALU64_ADD_K: 4294967294 + 2 = 4294967296 jited:0 14 PASS
test_bpf: #93 ALU64_ADD_K: 2147483646 + -2147483647 = -1 jited:0 10 PASS

Longer programs got faster:
Before:
test_bpf: #266 BPF_MAXINSNS: Ctx heavy transformations jited:0 20286 20513 PASS
test_bpf: #267 BPF_MAXINSNS: Call heavy transformations jited:0 31853 31768 PASS
test_bpf: #268 BPF_MAXINSNS: Jump heavy test jited:0 9815 PASS
test_bpf: #269 BPF_MAXINSNS: Very long jump backwards jited:0 6 PASS
test_bpf: #270 BPF_MAXINSNS: Edge hopping nuthouse jited:0 13959 PASS
test_bpf: #271 BPF_MAXINSNS: Jump, gap, jump, ... jited:0 210 PASS
test_bpf: #272 BPF_MAXINSNS: ld_abs+get_processor_id jited:0 21724 PASS
test_bpf: #273 BPF_MAXINSNS: ld_abs+vlan_push/pop jited:0 19118 PASS
After:
test_bpf: #266 BPF_MAXINSNS: Ctx heavy transformations jited:0 19008 18827 PASS
test_bpf: #267 BPF_MAXINSNS: Call heavy transformations jited:0 29238 28450 PASS
test_bpf: #268 BPF_MAXINSNS: Jump heavy test jited:0 9485 PASS
test_bpf: #269 BPF_MAXINSNS: Very long jump backwards jited:0 12 PASS
test_bpf: #270 BPF_MAXINSNS: Edge hopping nuthouse jited:0 13257 PASS
test_bpf: #271 BPF_MAXINSNS: Jump, gap, jump, ... jited:0 213 PASS
test_bpf: #272 BPF_MAXINSNS: ld_abs+get_processor_id jited:0 19389 PASS
test_bpf: #273 BPF_MAXINSNS: ld_abs+vlan_push/pop jited:0 19583 PASS

For real world production programs the difference is noise.

This patch is first step towards reducing interpreter stack consumption.

Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Acked-by: Daniel Borkmann <daniel@iogearbox.net>
Signed-off-by: David S. Miller <davem@davemloft.net>

kernel/bpf/core.c

@@ -763,10 +763,10 @@ EXPORT_SYMBOL_GPL(__bpf_call_base);
  *
  * Decode and execute eBPF instructions.
  */
-static unsigned int __bpf_prog_run(void *ctx, const struct bpf_insn *insn)
+static unsigned int ___bpf_prog_run(u64 *regs, const struct bpf_insn *insn,
+				    u64 *stack)
 {
-	u64 stack[MAX_BPF_STACK / sizeof(u64)];
-	u64 regs[MAX_BPF_REG], tmp;
+	u64 tmp;
 	static const void *jumptable[256] = {
 		[0 ... 255] = &&default_label,
 		/* Now overwrite non-defaults ... */
@@ -874,9 +874,6 @@ static unsigned int __bpf_prog_run(void *ctx, const struct bpf_insn *insn)
 #define CONT	 ({ insn++; goto select_insn; })
 #define CONT_JMP ({ insn++; goto select_insn; })
 
-	FP = (u64) (unsigned long) &stack[ARRAY_SIZE(stack)];
-	ARG1 = (u64) (unsigned long) ctx;
-
 select_insn:
 	goto *jumptable[insn->code];
 
@@ -1219,7 +1216,17 @@ load_byte:
 		WARN_RATELIMIT(1, "unknown opcode %02x\n", insn->code);
 		return 0;
 }
-STACK_FRAME_NON_STANDARD(__bpf_prog_run); /* jump table */
+STACK_FRAME_NON_STANDARD(___bpf_prog_run); /* jump table */
+
+static unsigned int __bpf_prog_run(void *ctx, const struct bpf_insn *insn)
+{
+	u64 stack[MAX_BPF_STACK / sizeof(u64)];
+	u64 regs[MAX_BPF_REG];
+
+	FP = (u64) (unsigned long) &stack[ARRAY_SIZE(stack)];
+	ARG1 = (u64) (unsigned long) ctx;
+	return ___bpf_prog_run(regs, insn, stack);
+}
 
 bool bpf_prog_array_compatible(struct bpf_array *array,
 			       const struct bpf_prog *fp)