AcoSail/kernel_optimize_test
8
0
Fork 0
forked from luck/tmp_suning_uos_patched
Code Pull Requests Activity

ARM: net: bpf: improve 64-bit store implementation

Browse Source 
Improve the 64-bit store implementation from:

  ldr     r6, [fp, #-8]
  str     r8, [r6]
  ldr     r6, [fp, #-8]
  mov     r7, #4
  add     r7, r6, r7
  str     r9, [r7]

to:

  ldr     r6, [fp, #-8]
  str     r8, [r6]
  str     r9, [r6, #4]

We leave the store as two separate STR instructions rather than using
STRD as the store may not be aligned, and STR can handle misalignment.

Signed-off-by: Russell King <rmk+kernel@armlinux.org.uk>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
This commit is contained in:
Russell King 2018-07-12 21:50:51 +01:00 committed by Daniel Borkmann
parent 077513b894
commit c5eae69257
1 changed files with 26 additions and 26 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

52
arch/arm/net/bpf_jit_32.c
View File

@ -975,29 +975,42 @@ static inline void emit_a32_mul_r64(const s8 dst[], const s8 src[],
} }
/* *(size *)(dst + off) = src */ /* *(size *)(dst + off) = src */
static inline void emit_str_r(const s8 dst, const s8 src, static inline void emit_str_r(const s8 dst, const s8 src[],
const s32 off, struct jit_ctx *ctx, const u8 sz){ s32 off, struct jit_ctx *ctx, const u8 sz){
const s8 *tmp = bpf2a32[TMP_REG_1]; const s8 *tmp = bpf2a32[TMP_REG_1];
s32 off_max;
s8 rd; s8 rd;
rd = arm_bpf_get_reg32(dst, tmp[1], ctx); rd = arm_bpf_get_reg32(dst, tmp[1], ctx);
if (off) {
if (sz == BPF_H)
off_max = 0xff;
else
off_max = 0xfff;
if (off < 0 || off > off_max) {
emit_a32_mov_i(tmp[0], off, ctx); emit_a32_mov_i(tmp[0], off, ctx);
emit(ARM_ADD_R(tmp[0], rd, tmp[0]), ctx); emit(ARM_ADD_R(tmp[0], tmp[0], rd), ctx);
rd = tmp[0]; rd = tmp[0];
off = 0;
} }
switch (sz) { switch (sz) {
case BPF_W: case BPF_B:
/* Store a Word */ /* Store a Byte */
emit(ARM_STR_I(src, rd, 0), ctx); emit(ARM_STRB_I(src_lo, rd, off), ctx);
break; break;
case BPF_H: case BPF_H:
/* Store a HalfWord */ /* Store a HalfWord */
emit(ARM_STRH_I(src, rd, 0), ctx); emit(ARM_STRH_I(src_lo, rd, off), ctx);
break; break;
case BPF_B: case BPF_W:
/* Store a Byte */ /* Store a Word */
emit(ARM_STRB_I(src, rd, 0), ctx); emit(ARM_STR_I(src_lo, rd, off), ctx);
break;
case BPF_DW:
/* Store a Double Word */
emit(ARM_STR_I(src_lo, rd, off), ctx);
emit(ARM_STR_I(src_hi, rd, off + 4), ctx);
break; break;
} }
} }
@ -1539,16 +1552,14 @@ static int build_insn(const struct bpf_insn *insn, struct jit_ctx *ctx)
case BPF_DW: case BPF_DW:
/* Sign-extend immediate value into temp reg */ /* Sign-extend immediate value into temp reg */
emit_a32_mov_se_i64(true, tmp2, imm, ctx); emit_a32_mov_se_i64(true, tmp2, imm, ctx);
emit_str_r(dst_lo, tmp2[1], off, ctx, BPF_W);
emit_str_r(dst_lo, tmp2[0], off+4, ctx, BPF_W);
break; break;
case BPF_W: case BPF_W:
case BPF_H: case BPF_H:
case BPF_B: case BPF_B:
emit_a32_mov_i(tmp2[1], imm, ctx); emit_a32_mov_i(tmp2[1], imm, ctx);
emit_str_r(dst_lo, tmp2[1], off, ctx, BPF_SIZE(code));
break; break;
} }
emit_str_r(dst_lo, tmp2, off, ctx, BPF_SIZE(code));
break; break;
/* STX XADD: lock *(u32 *)(dst + off) += src */ /* STX XADD: lock *(u32 *)(dst + off) += src */
case BPF_STX | BPF_XADD | BPF_W: case BPF_STX | BPF_XADD | BPF_W:
@ -1560,20 +1571,9 @@ static int build_insn(const struct bpf_insn *insn, struct jit_ctx *ctx)
case BPF_STX | BPF_MEM | BPF_H: case BPF_STX | BPF_MEM | BPF_H:
case BPF_STX | BPF_MEM | BPF_B: case BPF_STX | BPF_MEM | BPF_B:
case BPF_STX | BPF_MEM | BPF_DW: case BPF_STX | BPF_MEM | BPF_DW:
{
u8 sz = BPF_SIZE(code);
rs = arm_bpf_get_reg64(src, tmp2, ctx); rs = arm_bpf_get_reg64(src, tmp2, ctx);
emit_str_r(dst_lo, rs, off, ctx, BPF_SIZE(code));
/* Store the value */
if (BPF_SIZE(code) == BPF_DW) {
emit_str_r(dst_lo, rs[1], off, ctx, BPF_W);
emit_str_r(dst_lo, rs[0], off+4, ctx, BPF_W);
} else {
emit_str_r(dst_lo, rs[1], off, ctx, sz);
}
break; break;
}
/* PC += off if dst == src */ /* PC += off if dst == src */
/* PC += off if dst > src */ /* PC += off if dst > src */
/* PC += off if dst >= src */ /* PC += off if dst >= src */