bpf: move tmp variable into ax register in interpreter

This change moves the on-stack 64 bit tmp variable in ___bpf_prog_run()
into the hidden ax register. The latter is currently only used in JITs
for constant blinding as a temporary scratch register, meaning the BPF
interpreter will never see the use of ax. Therefore it is safe to use
it for the cases where tmp has been used earlier. This is needed to later
on allow restricted hidden use of ax in both interpreter and JITs.
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Alexei Starovoitov <ast@kernel.org>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>

include/linux/filter.h

@@ -60,7 +60,8 @@ struct sock_reuseport;
  * constants. See JIT pre-step in bpf_jit_blind_constants().
  */
 #define BPF_REG_AX		MAX_BPF_REG
-#define MAX_BPF_JIT_REG		(MAX_BPF_REG + 1)
+#define MAX_BPF_EXT_REG		(MAX_BPF_REG + 1)
+#define MAX_BPF_JIT_REG		MAX_BPF_EXT_REG
 
 /* unused opcode to mark special call to bpf_tail_call() helper */
 #define BPF_TAIL_CALL	0xf0

kernel/bpf/core.c

@@ -54,6 +54,7 @@
 #define DST	regs[insn->dst_reg]
 #define SRC	regs[insn->src_reg]
 #define FP	regs[BPF_REG_FP]
+#define AX	regs[BPF_REG_AX]
 #define ARG1	regs[BPF_REG_ARG1]
 #define CTX	regs[BPF_REG_CTX]
 #define IMM	insn->imm
@@ -1188,7 +1189,6 @@ bool bpf_opcode_in_insntable(u8 code)
  */
 static u64 ___bpf_prog_run(u64 *regs, const struct bpf_insn *insn, u64 *stack)
 {
-	u64 tmp;
 #define BPF_INSN_2_LBL(x, y)    [BPF_##x | BPF_##y] = &&x##_##y
 #define BPF_INSN_3_LBL(x, y, z) [BPF_##x | BPF_##y | BPF_##z] = &&x##_##y##_##z
 	static const void *jumptable[256] = {
@@ -1268,36 +1268,36 @@ static u64 ___bpf_prog_run(u64 *regs, const struct bpf_insn *insn, u64 *stack)
 		(*(s64 *) &DST) >>= IMM;
 		CONT;
 	ALU64_MOD_X:
-		div64_u64_rem(DST, SRC, &tmp);
-		DST = tmp;
+		div64_u64_rem(DST, SRC, &AX);
+		DST = AX;
 		CONT;
 	ALU_MOD_X:
-		tmp = (u32) DST;
-		DST = do_div(tmp, (u32) SRC);
+		AX = (u32) DST;
+		DST = do_div(AX, (u32) SRC);
 		CONT;
 	ALU64_MOD_K:
-		div64_u64_rem(DST, IMM, &tmp);
-		DST = tmp;
+		div64_u64_rem(DST, IMM, &AX);
+		DST = AX;
 		CONT;
 	ALU_MOD_K:
-		tmp = (u32) DST;
-		DST = do_div(tmp, (u32) IMM);
+		AX = (u32) DST;
+		DST = do_div(AX, (u32) IMM);
 		CONT;
 	ALU64_DIV_X:
 		DST = div64_u64(DST, SRC);
 		CONT;
 	ALU_DIV_X:
-		tmp = (u32) DST;
-		do_div(tmp, (u32) SRC);
-		DST = (u32) tmp;
+		AX = (u32) DST;
+		do_div(AX, (u32) SRC);
+		DST = (u32) AX;
 		CONT;
 	ALU64_DIV_K:
 		DST = div64_u64(DST, IMM);
 		CONT;
 	ALU_DIV_K:
-		tmp = (u32) DST;
-		do_div(tmp, (u32) IMM);
-		DST = (u32) tmp;
+		AX = (u32) DST;
+		do_div(AX, (u32) IMM);
+		DST = (u32) AX;
 		CONT;
 	ALU_END_TO_BE:
 		switch (IMM) {
@@ -1553,7 +1553,7 @@ STACK_FRAME_NON_STANDARD(___bpf_prog_run); /* jump table */
 static unsigned int PROG_NAME(stack_size)(const void *ctx, const struct bpf_insn *insn) \
 { \
 	u64 stack[stack_size / sizeof(u64)]; \
-	u64 regs[MAX_BPF_REG]; \
+	u64 regs[MAX_BPF_EXT_REG]; \
 \
 	FP = (u64) (unsigned long) &stack[ARRAY_SIZE(stack)]; \
 	ARG1 = (u64) (unsigned long) ctx; \
@@ -1566,7 +1566,7 @@ static u64 PROG_NAME_ARGS(stack_size)(u64 r1, u64 r2, u64 r3, u64 r4, u64 r5, \
 				      const struct bpf_insn *insn) \
 { \
 	u64 stack[stack_size / sizeof(u64)]; \
-	u64 regs[MAX_BPF_REG]; \
+	u64 regs[MAX_BPF_EXT_REG]; \
 \
 	FP = (u64) (unsigned long) &stack[ARRAY_SIZE(stack)]; \
 	BPF_R1 = r1; \