From: Pu Lehui <pulehui@xxxxxxxxxx> We used bpf_prog_pack to aggregate bpf programs into huge page to relieve the iTLB pressure on the system. We can apply it to bpf trampoline, as Song had been implemented it in core and x86 [0]. This patch is going to use bpf_prog_pack to RV64 bpf trampoline. Since Song and Puranjay have done a lot of work for bpf_prog_pack on RV64, implementing this function will be easy. But one thing to mention is that emit_call in RV64 will generate the maximum number of instructions during dry run, but during real patching it may be optimized to 1 instruction due to distance. This is no problem as it does not overflow the allocated RO image. Link: https://lore.kernel.org/all/20231206224054.492250-1-song@xxxxxxxxxx [0] Signed-off-by: Pu Lehui <pulehui@xxxxxxxxxx> --- arch/riscv/net/bpf_jit_comp64.c | 59 ++++++++++++++++++++++++--------- 1 file changed, 44 insertions(+), 15 deletions(-) diff --git a/arch/riscv/net/bpf_jit_comp64.c b/arch/riscv/net/bpf_jit_comp64.c index 5c4e0ac389d0..903f724cd785 100644 --- a/arch/riscv/net/bpf_jit_comp64.c +++ b/arch/riscv/net/bpf_jit_comp64.c @@ -961,7 +961,7 @@ static int __arch_prepare_bpf_trampoline(struct bpf_tramp_image *im, goto out; emit_sd(RV_REG_FP, -retval_off, RV_REG_A0, ctx); emit_sd(RV_REG_FP, -(retval_off - 8), regmap[BPF_REG_0], ctx); - im->ip_after_call = ctx->insns + ctx->ninsns; + im->ip_after_call = ctx->ro_insns + ctx->ninsns; /* 2 nops reserved for auipc+jalr pair */ emit(rv_nop(), ctx); emit(rv_nop(), ctx); @@ -982,7 +982,7 @@ static int __arch_prepare_bpf_trampoline(struct bpf_tramp_image *im, } if (flags & BPF_TRAMP_F_CALL_ORIG) { - im->ip_epilogue = ctx->insns + ctx->ninsns; + im->ip_epilogue = ctx->ro_insns + ctx->ninsns; emit_imm(RV_REG_A0, (const s64)im, ctx); ret = emit_call((const u64)__bpf_tramp_exit, true, ctx); if (ret) @@ -1044,31 +1044,60 @@ int arch_bpf_trampoline_size(struct bpf_tramp_image *im, const struct btf_func_m return ret < 0 ? ret : ninsns_rvoff(ctx.ninsns); } -int arch_prepare_bpf_trampoline(struct bpf_tramp_image *im, void *image, - void *image_end, const struct btf_func_model *m, +void *arch_alloc_bpf_trampoline(unsigned int size) +{ + return bpf_prog_pack_alloc(size, bpf_fill_ill_insns); +} + +void arch_free_bpf_trampoline(void *image, unsigned int size) +{ + bpf_prog_pack_free(image, size); +} + +void arch_protect_bpf_trampoline(void *image, unsigned int size) +{ +} + +void arch_unprotect_bpf_trampoline(void *image, unsigned int size) +{ +} + +int arch_prepare_bpf_trampoline(struct bpf_tramp_image *im, void *ro_image, + void *ro_image_end, const struct btf_func_model *m, u32 flags, struct bpf_tramp_links *tlinks, void *func_addr) { int ret; + void *image, *tmp; struct rv_jit_context ctx; + u32 size = ro_image_end - ro_image; + + image = kvmalloc(size, GFP_KERNEL); + if (!image) + return -ENOMEM; ctx.ninsns = 0; - /* - * The bpf_int_jit_compile() uses a RW buffer (ctx.insns) to write the - * JITed instructions and later copies it to a RX region (ctx.ro_insns). - * It also uses ctx.ro_insns to calculate offsets for jumps etc. As the - * trampoline image uses the same memory area for writing and execution, - * both ctx.insns and ctx.ro_insns can be set to image. - */ ctx.insns = image; - ctx.ro_insns = image; + ctx.ro_insns = ro_image; ret = __arch_prepare_bpf_trampoline(im, m, tlinks, func_addr, flags, &ctx); if (ret < 0) - return ret; + goto out; - bpf_flush_icache(ctx.insns, ctx.insns + ctx.ninsns); + if (WARN_ON(size < ninsns_rvoff(ctx.ninsns))) { + ret = -E2BIG; + goto out; + } - return ninsns_rvoff(ret); + tmp = bpf_arch_text_copy(ro_image, image, size); + if (IS_ERR(tmp)) { + ret = PTR_ERR(tmp); + goto out; + } + + bpf_flush_icache(ro_image, ro_image + size); +out: + kvfree(image); + return ret < 0 ? ret : size; } int bpf_jit_emit_insn(const struct bpf_insn *insn, struct rv_jit_context *ctx, -- 2.34.1
