Hi,
Tiezhu
On 2022/8/9 上午10:52, Tiezhu Yang wrote:
BPF programs are normally handled by a BPF interpreter, add BPF JIT
support for LoongArch to allow the kernel to generate native code
when a program is loaded into the kernel, this will significantly
speed-up processing of BPF programs.
Co-developed-by: Youling Tang <tangyouling@xxxxxxxxxxx>
Signed-off-by: Youling Tang <tangyouling@xxxxxxxxxxx>
Signed-off-by: Tiezhu Yang <yangtiezhu@xxxxxxxxxxx>
---
arch/loongarch/Kbuild | 1 +
arch/loongarch/Kconfig | 1 +
arch/loongarch/net/Makefile | 7 +
arch/loongarch/net/bpf_jit.c | 1119 ++++++++++++++++++++++++++++++++++++++++++
arch/loongarch/net/bpf_jit.h | 946 +++++++++++++++++++++++++++++++++++
5 files changed, 2074 insertions(+)
create mode 100644 arch/loongarch/net/Makefile
create mode 100644 arch/loongarch/net/bpf_jit.c
create mode 100644 arch/loongarch/net/bpf_jit.h
diff --git a/arch/loongarch/Kbuild b/arch/loongarch/Kbuild
+
[...]
+/*
+ * eBPF prog stack layout:
+ *
+ * high
+ * original $sp ------------> +-------------------------+ <--LOONGARCH_GPR_FP
+ * | $ra |
+ * +-------------------------+
+ * | $fp |
+ * +-------------------------+
+ * | $s0 |
+ * +-------------------------+
+ * | $s1 |
+ * +-------------------------+
+ * | $s2 |
+ * +-------------------------+
+ * | $s3 |
+ * +-------------------------+
+ * | $s4 |
+ * +-------------------------+
+ * | $s5 |
+ * +-------------------------+ <--BPF_REG_FP
+ * | prog->aux->stack_depth |
+ * | (optional) |
+ * current $sp -------------> +-------------------------+
+ * low
+ */
+static void build_prologue(struct jit_ctx *ctx)
+{
+ int stack_adjust = 0, store_offset, bpf_stack_adjust;
+
+ bpf_stack_adjust = round_up(ctx->prog->aux->stack_depth, 16);
+
+ stack_adjust += sizeof(long); /* LOONGARCH_GPR_RA */
+ stack_adjust += sizeof(long); /* LOONGARCH_GPR_FP */
+ stack_adjust += sizeof(long); /* LOONGARCH_GPR_S0 */
+ stack_adjust += sizeof(long); /* LOONGARCH_GPR_S1 */
+ stack_adjust += sizeof(long); /* LOONGARCH_GPR_S2 */
+ stack_adjust += sizeof(long); /* LOONGARCH_GPR_S3 */
+ stack_adjust += sizeof(long); /* LOONGARCH_GPR_S4 */
+ stack_adjust += sizeof(long); /* LOONGARCH_GPR_S5 */
+
+ stack_adjust = round_up(stack_adjust, 16);
+ stack_adjust += bpf_stack_adjust;
Maybe get the size of stack_adjust can be combined together, and only
need one comment.
Thanks,
Qing
+ /*
+ * First instruction initializes the tail call count (TCC).
+ * On tail call we skip this instruction, and the TCC is
+ * passed in REG_TCC from the caller.
+ */
+ emit_insn(ctx, addid, REG_TCC, LOONGARCH_GPR_ZERO, MAX_TAIL_CALL_CNT);
+
+ emit_insn(ctx, addid, LOONGARCH_GPR_SP, LOONGARCH_GPR_SP, -stack_adjust);
+
+ store_offset = stack_adjust - sizeof(long);
+ emit_insn(ctx, std, LOONGARCH_GPR_RA, LOONGARCH_GPR_SP, store_offset);
+
+ store_offset -= sizeof(long);
+ emit_insn(ctx, std, LOONGARCH_GPR_FP, LOONGARCH_GPR_SP, store_offset);
+
+ store_offset -= sizeof(long);
+ emit_insn(ctx, std, LOONGARCH_GPR_S0, LOONGARCH_GPR_SP, store_offset);
+
+ store_offset -= sizeof(long);
+ emit_insn(ctx, std, LOONGARCH_GPR_S1, LOONGARCH_GPR_SP, store_offset);
+
+ store_offset -= sizeof(long);
+ emit_insn(ctx, std, LOONGARCH_GPR_S2, LOONGARCH_GPR_SP, store_offset);
+
+ store_offset -= sizeof(long);
+ emit_insn(ctx, std, LOONGARCH_GPR_S3, LOONGARCH_GPR_SP, store_offset);
+
+ store_offset -= sizeof(long);
+ emit_insn(ctx, std, LOONGARCH_GPR_S4, LOONGARCH_GPR_SP, store_offset);
+
+ store_offset -= sizeof(long);
+ emit_insn(ctx, std, LOONGARCH_GPR_S5, LOONGARCH_GPR_SP, store_offset);
+
+ emit_insn(ctx, addid, LOONGARCH_GPR_FP, LOONGARCH_GPR_SP, stack_adjust);
+
+ if (bpf_stack_adjust)
+ emit_insn(ctx, addid, regmap[BPF_REG_FP], LOONGARCH_GPR_SP, bpf_stack_adjust);
+
+ /*
+ * Program contains calls and tail calls, so REG_TCC need
+ * to be saved across calls.
+ */
+ if (seen_tail_call(ctx) && seen_call(ctx))
+ move_reg(ctx, TCC_SAVED, REG_TCC);
+
+ ctx->stack_size = stack_adjust;
+}
