From patchwork Mon Aug 26 07:16:23 2024 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Xu Kuohai X-Patchwork-Id: 13777247 X-Patchwork-Delegate: bpf@iogearbox.net Received: from dggsgout11.his.huawei.com (dggsgout11.his.huawei.com [45.249.212.51]) (using TLSv1.2 with cipher ECDHE-RSA-AES256-GCM-SHA384 (256/256 bits)) (No client certificate requested) by smtp.subspace.kernel.org (Postfix) with ESMTPS id 8AF7A770E5 for ; Mon, 26 Aug 2024 07:06:16 +0000 (UTC) Authentication-Results: smtp.subspace.kernel.org; arc=none smtp.client-ip=45.249.212.51 ARC-Seal: i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1724655980; cv=none; b=r3w70uvhdg+SqddsReFYiORmly9xP9+3dSBP6j6w/uNIKbjXOJ4qavW4Jy/zLyu9Qv2abo27EXuVCqkIJWb7dnDCrjI2vSG8m9fw3J/M/M9LZiokSelWtlHwxbY4eaCaiJS8quMmptH/fKxjE8RO4sPM22aZYGIBVJ6UWBOacco= ARC-Message-Signature: i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1724655980; c=relaxed/simple; bh=XJ24hS+/5/sRA+GM1/4DyssOfC0LuvLF7ukiyeLO+5I=; h=From:To:Cc:Subject:Date:Message-Id:In-Reply-To:References: MIME-Version; b=DTFWpMuHSuy+VbQ37ILiAQ3Kj4fYM9WuyaYeaeXQXjyu7OKSbGMtFWilOaanXDUGfD1NrGIcqxutLUOHxl8oNOZEPrQwv2SAnCDLXkP1iuQAtPHzrTE35+N2OXH6LuZr4sIh4LPuSDQcM/+jQem5/9DVShEINpTkWijQcqW3By8= ARC-Authentication-Results: i=1; smtp.subspace.kernel.org; dmarc=none (p=none dis=none) header.from=huaweicloud.com; spf=pass smtp.mailfrom=huaweicloud.com; arc=none smtp.client-ip=45.249.212.51 Authentication-Results: smtp.subspace.kernel.org; dmarc=none (p=none dis=none) header.from=huaweicloud.com Authentication-Results: smtp.subspace.kernel.org; spf=pass smtp.mailfrom=huaweicloud.com Received: from mail.maildlp.com (unknown [172.19.93.142]) by dggsgout11.his.huawei.com (SkyGuard) with ESMTP id 4WshXj5pynz4f3l23 for ; Mon, 26 Aug 2024 15:05:57 +0800 (CST) Received: from mail02.huawei.com (unknown [10.116.40.75]) by mail.maildlp.com (Postfix) with ESMTP id 2C4AB1A018D for ; Mon, 26 Aug 2024 15:06:13 +0800 (CST) Received: from k01.huawei.com (unknown [10.67.174.197]) by APP2 (Coremail) with SMTP id Syh0CgAH8L5jKcxmTz_5Cg--.20237S3; Mon, 26 Aug 2024 15:06:13 +0800 (CST) From: Xu Kuohai To: bpf@vger.kernel.org, linux-arm-kernel@lists.infradead.org Cc: Alexei Starovoitov , Daniel Borkmann , Andrii Nakryiko , Puranjay Mohan , Leon Hwang , Catalin Marinas , Will Deacon Subject: [PATCH bpf-next 1/2] bpf, arm64: Get rid of fpb Date: Mon, 26 Aug 2024 15:16:23 +0800 Message-Id: <20240826071624.350108-2-xukuohai@huaweicloud.com> X-Mailer: git-send-email 2.39.2 In-Reply-To: <20240826071624.350108-1-xukuohai@huaweicloud.com> References: <20240826071624.350108-1-xukuohai@huaweicloud.com> Precedence: bulk X-Mailing-List: bpf@vger.kernel.org List-Id: List-Subscribe: List-Unsubscribe: MIME-Version: 1.0 X-CM-TRANSID: Syh0CgAH8L5jKcxmTz_5Cg--.20237S3 X-Coremail-Antispam: 1UD129KBjvJXoW3AFWrJry5XFyUXr1UZr4kCrg_yoWxKF4xpF sxK340krWfJay5XFWktrn7XF1Skws7C3W7KryY93ySyF9F9r15WF48KayIkFW3CryxAw47 urWqvw1xCwnxJwUanT9S1TB71UUUUU7qnTZGkaVYY2UrUUUUjbIjqfuFe4nvWSU5nxnvy2 9KBjDU0xBIdaVrnRJUUU9Kb4IE77IF4wAFF20E14v26ryj6rWUM7CY07I20VC2zVCF04k2 6cxKx2IYs7xG6rWj6s0DM7CIcVAFz4kK6r1j6r18M28IrcIa0xkI8VA2jI8067AKxVWUGw A2048vs2IY020Ec7CjxVAFwI0_JFI_Gr1l8cAvFVAK0II2c7xJM28CjxkF64kEwVA0rcxS w2x7M28EF7xvwVC0I7IYx2IY67AKxVW7JVWDJwA2z4x0Y4vE2Ix0cI8IcVCY1x0267AKxV W8Jr0_Cr1UM28EF7xvwVC2z280aVAFwI0_GcCE3s1l84ACjcxK6I8E87Iv6xkF7I0E14v2 6rxl6s0DM2AIxVAIcxkEcVAq07x20xvEncxIr21l5I8CrVACY4xI64kE6c02F40Ex7xfMc Ij6xIIjxv20xvE14v26r1j6r18McIj6I8E87Iv67AKxVWUJVW8JwAm72CE4IkC6x0Yz7v_ Jr0_Gr1lF7xvr2IYc2Ij64vIr41lc7CjxVAaw2AFwI0_Jw0_GFyl42xK82IYc2Ij64vIr4 1l4I8I3I0E4IkC6x0Yz7v_Jr0_Gr1lx2IqxVAqx4xG67AKxVWUJVWUGwC20s026x8GjcxK 67AKxVWUGVWUWwC2zVAF1VAY17CE14v26r1q6r43MIIYrxkI7VAKI48JMIIF0xvE2Ix0cI 8IcVAFwI0_Jr0_JF4lIxAIcVC0I7IYx2IY6xkF7I0E14v26r4j6F4UMIIF0xvE42xK8VAv wI8IcIk0rVWUJVWUCwCI42IY6I8E87Iv67AKxVWUJVW8JwCI42IY6I8E87Iv6xkF7I0E14 v26r4j6r4UJbIYCTnIWIevJa73UjIFyTuYvjxUzGYLUUUUU X-CM-SenderInfo: 50xn30hkdlqx5xdzvxpfor3voofrz/ X-Patchwork-Delegate: bpf@iogearbox.net From: Xu Kuohai bpf prog accesses stack using BPF_FP as the base address and a negative immediate number as offset. But arm64 ldr/str instructions only support non-negative immediate number as offset. To simplify the jited result, commit 5b3d19b9bd40 ("bpf, arm64: Adjust the offset of str/ldr(immediate) to positive number") introduced FPB to represent the lowest stack address that the bpf prog being jited may access, and with this address as the baseline, it converts BPF_FP plus negative immediate offset number to FPB plus non-negative immediate offset. Considering that for a given bpf prog, the jited stack space is fixed with A64_SP as the lowest address and BPF_FP as the highest address. Thus we can get rid of FPB and converts BPF_FP plus negative immediate offset to A64_SP plus non-negative immediate offset. Signed-off-by: Xu Kuohai --- arch/arm64/net/bpf_jit_comp.c | 104 ++++------------------------------ 1 file changed, 11 insertions(+), 93 deletions(-) diff --git a/arch/arm64/net/bpf_jit_comp.c b/arch/arm64/net/bpf_jit_comp.c index 59e05a7aea56..5c9039cf261d 100644 --- a/arch/arm64/net/bpf_jit_comp.c +++ b/arch/arm64/net/bpf_jit_comp.c @@ -28,7 +28,6 @@ #define TMP_REG_2 (MAX_BPF_JIT_REG + 1) #define TCCNT_PTR (MAX_BPF_JIT_REG + 2) #define TMP_REG_3 (MAX_BPF_JIT_REG + 3) -#define FP_BOTTOM (MAX_BPF_JIT_REG + 4) #define ARENA_VM_START (MAX_BPF_JIT_REG + 5) #define check_imm(bits, imm) do { \ @@ -67,7 +66,6 @@ static const int bpf2a64[] = { [TCCNT_PTR] = A64_R(26), /* temporary register for blinding constants */ [BPF_REG_AX] = A64_R(9), - [FP_BOTTOM] = A64_R(27), /* callee saved register for kern_vm_start address */ [ARENA_VM_START] = A64_R(28), }; @@ -81,7 +79,6 @@ struct jit_ctx { __le32 *image; __le32 *ro_image; u32 stack_size; - int fpb_offset; u64 user_vm_start; }; @@ -330,7 +327,6 @@ static int build_prologue(struct jit_ctx *ctx, bool ebpf_from_cbpf, const u8 r8 = bpf2a64[BPF_REG_8]; const u8 r9 = bpf2a64[BPF_REG_9]; const u8 fp = bpf2a64[BPF_REG_FP]; - const u8 fpb = bpf2a64[FP_BOTTOM]; const u8 arena_vm_base = bpf2a64[ARENA_VM_START]; const int idx0 = ctx->idx; int cur_offset; @@ -381,7 +377,7 @@ static int build_prologue(struct jit_ctx *ctx, bool ebpf_from_cbpf, emit(A64_PUSH(r6, r7, A64_SP), ctx); emit(A64_PUSH(r8, r9, A64_SP), ctx); prepare_bpf_tail_call_cnt(ctx); - emit(A64_PUSH(fpb, A64_R(28), A64_SP), ctx); + emit(A64_PUSH(A64_R(27), A64_R(28), A64_SP), ctx); } else { /* * Exception callback receives FP of Main Program as third @@ -427,8 +423,6 @@ static int build_prologue(struct jit_ctx *ctx, bool ebpf_from_cbpf, emit(A64_PUSH(A64_R(23), A64_R(24), A64_SP), ctx); } - emit(A64_SUB_I(1, fpb, fp, ctx->fpb_offset), ctx); - /* Stack must be multiples of 16B */ ctx->stack_size = round_up(prog->aux->stack_depth, 16); @@ -745,7 +739,6 @@ static void build_epilogue(struct jit_ctx *ctx, bool is_exception_cb) const u8 r9 = bpf2a64[BPF_REG_9]; const u8 fp = bpf2a64[BPF_REG_FP]; const u8 ptr = bpf2a64[TCCNT_PTR]; - const u8 fpb = bpf2a64[FP_BOTTOM]; /* We're done with BPF stack */ emit(A64_ADD_I(1, A64_SP, A64_SP, ctx->stack_size), ctx); @@ -760,7 +753,7 @@ static void build_epilogue(struct jit_ctx *ctx, bool is_exception_cb) emit(A64_POP(A64_R(23), A64_R(24), A64_SP), ctx); /* Restore x27 and x28 */ - emit(A64_POP(fpb, A64_R(28), A64_SP), ctx); + emit(A64_POP(A64_R(27), A64_R(28), A64_SP), ctx); /* Restore fs (x25) and x26 */ emit(A64_POP(ptr, fp, A64_SP), ctx); emit(A64_POP(ptr, fp, A64_SP), ctx); @@ -887,7 +880,6 @@ static int build_insn(const struct bpf_insn *insn, struct jit_ctx *ctx, const u8 tmp = bpf2a64[TMP_REG_1]; const u8 tmp2 = bpf2a64[TMP_REG_2]; const u8 fp = bpf2a64[BPF_REG_FP]; - const u8 fpb = bpf2a64[FP_BOTTOM]; const u8 arena_vm_base = bpf2a64[ARENA_VM_START]; const s16 off = insn->off; const s32 imm = insn->imm; @@ -1339,9 +1331,9 @@ static int build_insn(const struct bpf_insn *insn, struct jit_ctx *ctx, emit(A64_ADD(1, tmp2, src, arena_vm_base), ctx); src = tmp2; } - if (ctx->fpb_offset > 0 && src == fp && BPF_MODE(insn->code) != BPF_PROBE_MEM32) { - src_adj = fpb; - off_adj = off + ctx->fpb_offset; + if (src == fp) { + src_adj = A64_SP; + off_adj = off + ctx->stack_size; } else { src_adj = src; off_adj = off; @@ -1432,9 +1424,9 @@ static int build_insn(const struct bpf_insn *insn, struct jit_ctx *ctx, emit(A64_ADD(1, tmp2, dst, arena_vm_base), ctx); dst = tmp2; } - if (ctx->fpb_offset > 0 && dst == fp && BPF_MODE(insn->code) != BPF_PROBE_MEM32) { - dst_adj = fpb; - off_adj = off + ctx->fpb_offset; + if (dst == fp) { + dst_adj = A64_SP; + off_adj = off + ctx->stack_size; } else { dst_adj = dst; off_adj = off; @@ -1494,9 +1486,9 @@ static int build_insn(const struct bpf_insn *insn, struct jit_ctx *ctx, emit(A64_ADD(1, tmp2, dst, arena_vm_base), ctx); dst = tmp2; } - if (ctx->fpb_offset > 0 && dst == fp && BPF_MODE(insn->code) != BPF_PROBE_MEM32) { - dst_adj = fpb; - off_adj = off + ctx->fpb_offset; + if (dst == fp) { + dst_adj = A64_SP; + off_adj = off + ctx->stack_size; } else { dst_adj = dst; off_adj = off; @@ -1565,79 +1557,6 @@ static int build_insn(const struct bpf_insn *insn, struct jit_ctx *ctx, return 0; } -/* - * Return 0 if FP may change at runtime, otherwise find the minimum negative - * offset to FP, converts it to positive number, and align down to 8 bytes. - */ -static int find_fpb_offset(struct bpf_prog *prog) -{ - int i; - int offset = 0; - - for (i = 0; i < prog->len; i++) { - const struct bpf_insn *insn = &prog->insnsi[i]; - const u8 class = BPF_CLASS(insn->code); - const u8 mode = BPF_MODE(insn->code); - const u8 src = insn->src_reg; - const u8 dst = insn->dst_reg; - const s32 imm = insn->imm; - const s16 off = insn->off; - - switch (class) { - case BPF_STX: - case BPF_ST: - /* fp holds atomic operation result */ - if (class == BPF_STX && mode == BPF_ATOMIC && - ((imm == BPF_XCHG || - imm == (BPF_FETCH | BPF_ADD) || - imm == (BPF_FETCH | BPF_AND) || - imm == (BPF_FETCH | BPF_XOR) || - imm == (BPF_FETCH | BPF_OR)) && - src == BPF_REG_FP)) - return 0; - - if (mode == BPF_MEM && dst == BPF_REG_FP && - off < offset) - offset = insn->off; - break; - - case BPF_JMP32: - case BPF_JMP: - break; - - case BPF_LDX: - case BPF_LD: - /* fp holds load result */ - if (dst == BPF_REG_FP) - return 0; - - if (class == BPF_LDX && mode == BPF_MEM && - src == BPF_REG_FP && off < offset) - offset = off; - break; - - case BPF_ALU: - case BPF_ALU64: - default: - /* fp holds ALU result */ - if (dst == BPF_REG_FP) - return 0; - } - } - - if (offset < 0) { - /* - * safely be converted to a positive 'int', since insn->off - * is 's16' - */ - offset = -offset; - /* align down to 8 bytes */ - offset = ALIGN_DOWN(offset, 8); - } - - return offset; -} - static int build_body(struct jit_ctx *ctx, bool extra_pass) { const struct bpf_prog *prog = ctx->prog; @@ -1774,7 +1693,6 @@ struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *prog) goto out_off; } - ctx.fpb_offset = find_fpb_offset(prog); ctx.user_vm_start = bpf_arena_get_user_vm_start(prog->aux->arena); /* From patchwork Mon Aug 26 07:16:24 2024 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Xu Kuohai X-Patchwork-Id: 13777248 X-Patchwork-Delegate: bpf@iogearbox.net Received: from dggsgout12.his.huawei.com (dggsgout12.his.huawei.com [45.249.212.56]) (using TLSv1.2 with cipher ECDHE-RSA-AES256-GCM-SHA384 (256/256 bits)) (No client certificate requested) by smtp.subspace.kernel.org (Postfix) with ESMTPS id 8F77F80BEC for ; Mon, 26 Aug 2024 07:06:18 +0000 (UTC) Authentication-Results: smtp.subspace.kernel.org; arc=none smtp.client-ip=45.249.212.56 ARC-Seal: i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1724655981; cv=none; b=ijLPupVAfJ9liRstbOBA2thKBRq9STm/wkH6GX0YGMaSVmgk7AFqWJGyjQRMYRCtKiIR8jvbHYcSTogjfkZENqUTvnf/VtpRQV4gmxD55yUsK8gMHsJfXJJ0lTWGiWB1KuHjYb0F+SUz9fKItbt8sh7jY/YlzWcRagh/D4PRcyg= ARC-Message-Signature: i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1724655981; c=relaxed/simple; bh=LCgMmkz3x1axnx2rU9sq5QNnNOs6CS/sOkW8w/+BBZk=; h=From:To:Cc:Subject:Date:Message-Id:In-Reply-To:References: MIME-Version; b=p1isN++Z0mid+W3FzuZw3kgdWqLkOLT2+uTrEJZwAKB9PoJp9GxfE/8heSz+epmRKmyFDYvp3tJ3LUWRy6HPu28n7Uj9WDzC/Hx8batgBnlsMOjN0ShRxax9OdgxPjHFztgrTj8OsQrULnLvPg1Gms5peSUgkmXjVTfbW651HLM= ARC-Authentication-Results: i=1; smtp.subspace.kernel.org; dmarc=none (p=none dis=none) header.from=huaweicloud.com; spf=pass smtp.mailfrom=huaweicloud.com; arc=none smtp.client-ip=45.249.212.56 Authentication-Results: smtp.subspace.kernel.org; dmarc=none (p=none dis=none) header.from=huaweicloud.com Authentication-Results: smtp.subspace.kernel.org; spf=pass smtp.mailfrom=huaweicloud.com Received: from mail.maildlp.com (unknown [172.19.163.235]) by dggsgout12.his.huawei.com (SkyGuard) with ESMTP id 4WshXm5kwRz4f3jXS for ; Mon, 26 Aug 2024 15:06:00 +0800 (CST) Received: from mail02.huawei.com (unknown [10.116.40.75]) by mail.maildlp.com (Postfix) with ESMTP id 419791A058E for ; Mon, 26 Aug 2024 15:06:15 +0800 (CST) Received: from k01.huawei.com (unknown [10.67.174.197]) by APP2 (Coremail) with SMTP id Syh0CgAH8L5jKcxmTz_5Cg--.20237S4; Mon, 26 Aug 2024 15:06:13 +0800 (CST) From: Xu Kuohai To: bpf@vger.kernel.org, linux-arm-kernel@lists.infradead.org Cc: Alexei Starovoitov , Daniel Borkmann , Andrii Nakryiko , Puranjay Mohan , Leon Hwang , Catalin Marinas , Will Deacon Subject: [PATCH bpf-next 2/2] bpf, arm64: Avoid blindly saving/restoring all callee-saved registers Date: Mon, 26 Aug 2024 15:16:24 +0800 Message-Id: <20240826071624.350108-3-xukuohai@huaweicloud.com> X-Mailer: git-send-email 2.39.2 In-Reply-To: <20240826071624.350108-1-xukuohai@huaweicloud.com> References: <20240826071624.350108-1-xukuohai@huaweicloud.com> Precedence: bulk X-Mailing-List: bpf@vger.kernel.org List-Id: List-Subscribe: List-Unsubscribe: MIME-Version: 1.0 X-CM-TRANSID: Syh0CgAH8L5jKcxmTz_5Cg--.20237S4 X-Coremail-Antispam: 1UD129KBjvAXoWftw4rGr13Cw1xCFW3GryxAFb_yoW8Kr45uo WfurW5Zw48Cry8ZFyfKw1UArW3Wa1Ikw17Cw45WFs8Z3WYqay5Zr4xGa1fAr4YqrW5Ca4D uFWft3WDCFs8Cr1rn29KB7ZKAUJUUUU8529EdanIXcx71UUUUU7v73VFW2AGmfu7bjvjm3 AaLaJ3UjIYCTnIWjp_UUUYL7kC6x804xWl14x267AKxVWrJVCq3wAFc2x0x2IEx4CE42xK 8VAvwI8IcIk0rVWrJVCq3wAFIxvE14AKwVWUJVWUGwA2048vs2IY020E87I2jVAFwI0_Jr yl82xGYIkIc2x26xkF7I0E14v26r4j6ryUM28lY4IEw2IIxxk0rwA2F7IY1VAKz4vEj48v e4kI8wA2z4x0Y4vE2Ix0cI8IcVAFwI0_Ar0_tr1l84ACjcxK6xIIjxv20xvEc7CjxVAFwI 0_Gr1j6F4UJwA2z4x0Y4vEx4A2jsIE14v26rxl6s0DM28EF7xvwVC2z280aVCY1x0267AK xVW0oVCq3wAS0I0E0xvYzxvE52x082IY62kv0487Mc02F40EFcxC0VAKzVAqx4xG6I80ew Av7VC0I7IYx2IY67AKxVWUJVWUGwAv7VC2z280aVAFwI0_Jr0_Gr1lOx8S6xCaFVCjc4AY 6r1j6r4UM4x0Y48IcxkI7VAKI48JMxkF7I0En4kS14v26r1q6r43MxAIw28IcxkI7VAKI4 8JMxC20s026xCaFVCjc4AY6r1j6r4UMI8I3I0E5I8CrVAFwI0_Jr0_Jr4lx2IqxVCjr7xv wVAFwI0_JrI_JrWlx4CE17CEb7AF67AKxVWUtVW8ZwCIc40Y0x0EwIxGrwCI42IY6xIIjx v20xvE14v26r1j6r1xMIIF0xvE2Ix0cI8IcVCY1x0267AKxVW8JVWxJwCI42IY6xAIw20E Y4v20xvaj40_Jr0_JF4lIxAIcVC2z280aVAFwI0_Jr0_Gr1lIxAIcVC2z280aVCY1x0267 AKxVW8JVW8JrUvcSsGvfC2KfnxnUUI43ZEXa7IU8fWrJUUUUU== X-CM-SenderInfo: 50xn30hkdlqx5xdzvxpfor3voofrz/ X-Patchwork-Delegate: bpf@iogearbox.net From: Xu Kuohai The arm64 jit blindly saves/restores all callee-saved registers, making the jited result looks a bit too compliated. For example, for an empty prog, the jited result is: 0: bti jc 4: mov x9, lr 8: nop c: paciasp 10: stp fp, lr, [sp, #-16]! 14: mov fp, sp 18: stp x19, x20, [sp, #-16]! 1c: stp x21, x22, [sp, #-16]! 20: stp x26, x25, [sp, #-16]! 24: mov x26, #0 28: stp x26, x25, [sp, #-16]! 2c: mov x26, sp 30: stp x27, x28, [sp, #-16]! 34: mov x25, sp 38: bti j // tailcall target 3c: sub sp, sp, #0 40: mov x7, #0 44: add sp, sp, #0 48: ldp x27, x28, [sp], #16 4c: ldp x26, x25, [sp], #16 50: ldp x26, x25, [sp], #16 54: ldp x21, x22, [sp], #16 58: ldp x19, x20, [sp], #16 5c: ldp fp, lr, [sp], #16 60: mov x0, x7 64: autiasp 68: ret Clearly, there is no need to save/restore unused callee-saved registers. This patch does this change, making the jited image to only save/restore the callee-saved registers it uses. Now the jited result of empty prog is: 0: bti jc 4: mov x9, lr 8: nop c: paciasp 10: stp fp, lr, [sp, #-16]! 14: mov fp, sp 18: stp xzr, x26, [sp, #-16]! 1c: mov x26, sp 20: bti j // tailcall target 24: mov x7, #0 28: ldp xzr, x26, [sp], #16 2c: ldp fp, lr, [sp], #16 30: mov x0, x7 34: autiasp 38: ret Since bpf prog saves/restores its own callee-saved registers as needed, to make tailcall work correctly, the caller needs to restore its saved registers before tailcall, and the callee needs to save its callee-saved registers after tailcall. This extra restoring/saving instructions increases preformance overhead. [1] provides 2 benchmarks for tailcall scenarios. Below is the perf number measured in an arm64 KVM guest. The result indicates that the performance difference before and after the patch in typical tailcall scenarios is negligible. - Before: Performance counter stats for './test_progs -t tailcalls' (5 runs): 4313.43 msec task-clock # 0.874 CPUs utilized ( +- 0.16% ) 574 context-switches # 133.073 /sec ( +- 1.14% ) 0 cpu-migrations # 0.000 /sec 538 page-faults # 124.727 /sec ( +- 0.57% ) 10697772784 cycles # 2.480 GHz ( +- 0.22% ) (61.19%) 25511241955 instructions # 2.38 insn per cycle ( +- 0.08% ) (66.70%) 5108910557 branches # 1.184 G/sec ( +- 0.08% ) (72.38%) 2800459 branch-misses # 0.05% of all branches ( +- 0.51% ) (72.36%) TopDownL1 # 0.60 retiring ( +- 0.09% ) (66.84%) # 0.21 frontend_bound ( +- 0.15% ) (61.31%) # 0.12 bad_speculation ( +- 0.08% ) (50.11%) # 0.07 backend_bound ( +- 0.16% ) (33.30%) 8274201819 L1-dcache-loads # 1.918 G/sec ( +- 0.18% ) (33.15%) 468268 L1-dcache-load-misses # 0.01% of all L1-dcache accesses ( +- 4.69% ) (33.16%) 385383 LLC-loads # 89.345 K/sec ( +- 5.22% ) (33.16%) 38296 LLC-load-misses # 9.94% of all LL-cache accesses ( +- 42.52% ) (38.69%) 6886576501 L1-icache-loads # 1.597 G/sec ( +- 0.35% ) (38.69%) 1848585 L1-icache-load-misses # 0.03% of all L1-icache accesses ( +- 4.52% ) (44.23%) 9043645883 dTLB-loads # 2.097 G/sec ( +- 0.10% ) (44.33%) 416672 dTLB-load-misses # 0.00% of all dTLB cache accesses ( +- 5.15% ) (49.89%) 6925626111 iTLB-loads # 1.606 G/sec ( +- 0.35% ) (55.46%) 66220 iTLB-load-misses # 0.00% of all iTLB cache accesses ( +- 1.88% ) (55.50%) L1-dcache-prefetches L1-dcache-prefetch-misses 4.9372 +- 0.0526 seconds time elapsed ( +- 1.07% ) Performance counter stats for './test_progs -t flow_dissector' (5 runs): 10924.50 msec task-clock # 0.945 CPUs utilized ( +- 0.08% ) 603 context-switches # 55.197 /sec ( +- 1.13% ) 0 cpu-migrations # 0.000 /sec 566 page-faults # 51.810 /sec ( +- 0.42% ) 27381270695 cycles # 2.506 GHz ( +- 0.18% ) (60.46%) 56996583922 instructions # 2.08 insn per cycle ( +- 0.21% ) (66.11%) 10321647567 branches # 944.816 M/sec ( +- 0.17% ) (71.79%) 3347735 branch-misses # 0.03% of all branches ( +- 3.72% ) (72.15%) TopDownL1 # 0.52 retiring ( +- 0.13% ) (66.74%) # 0.27 frontend_bound ( +- 0.14% ) (61.27%) # 0.14 bad_speculation ( +- 0.19% ) (50.36%) # 0.07 backend_bound ( +- 0.42% ) (33.89%) 18740797617 L1-dcache-loads # 1.715 G/sec ( +- 0.43% ) (33.71%) 13715669 L1-dcache-load-misses # 0.07% of all L1-dcache accesses ( +- 32.85% ) (33.34%) 4087551 LLC-loads # 374.164 K/sec ( +- 29.53% ) (33.26%) 267906 LLC-load-misses # 6.55% of all LL-cache accesses ( +- 23.90% ) (38.76%) 15811864229 L1-icache-loads # 1.447 G/sec ( +- 0.12% ) (38.73%) 2976833 L1-icache-load-misses # 0.02% of all L1-icache accesses ( +- 9.73% ) (44.22%) 20138907471 dTLB-loads # 1.843 G/sec ( +- 0.18% ) (44.15%) 732850 dTLB-load-misses # 0.00% of all dTLB cache accesses ( +- 11.18% ) (49.64%) 15895726702 iTLB-loads # 1.455 G/sec ( +- 0.15% ) (55.13%) 152075 iTLB-load-misses # 0.00% of all iTLB cache accesses ( +- 4.71% ) (54.98%) L1-dcache-prefetches L1-dcache-prefetch-misses 11.5613 +- 0.0317 seconds time elapsed ( +- 0.27% ) - After: Performance counter stats for './test_progs -t tailcalls' (5 runs): 4278.78 msec task-clock # 0.871 CPUs utilized ( +- 0.15% ) 569 context-switches # 132.982 /sec ( +- 0.58% ) 0 cpu-migrations # 0.000 /sec 539 page-faults # 125.970 /sec ( +- 0.43% ) 10588986432 cycles # 2.475 GHz ( +- 0.20% ) (60.91%) 25303825043 instructions # 2.39 insn per cycle ( +- 0.08% ) (66.48%) 5110756256 branches # 1.194 G/sec ( +- 0.07% ) (72.03%) 2719569 branch-misses # 0.05% of all branches ( +- 2.42% ) (72.03%) TopDownL1 # 0.60 retiring ( +- 0.22% ) (66.31%) # 0.22 frontend_bound ( +- 0.21% ) (60.83%) # 0.12 bad_speculation ( +- 0.26% ) (50.25%) # 0.06 backend_bound ( +- 0.17% ) (33.52%) 8163648527 L1-dcache-loads # 1.908 G/sec ( +- 0.33% ) (33.52%) 694979 L1-dcache-load-misses # 0.01% of all L1-dcache accesses ( +- 30.53% ) (33.52%) 1902347 LLC-loads # 444.600 K/sec ( +- 48.84% ) (33.69%) 96677 LLC-load-misses # 5.08% of all LL-cache accesses ( +- 43.48% ) (39.30%) 6863517589 L1-icache-loads # 1.604 G/sec ( +- 0.37% ) (39.17%) 1871519 L1-icache-load-misses # 0.03% of all L1-icache accesses ( +- 6.78% ) (44.56%) 8927782813 dTLB-loads # 2.087 G/sec ( +- 0.14% ) (44.37%) 438237 dTLB-load-misses # 0.00% of all dTLB cache accesses ( +- 6.00% ) (49.75%) 6886906831 iTLB-loads # 1.610 G/sec ( +- 0.36% ) (55.08%) 67568 iTLB-load-misses # 0.00% of all iTLB cache accesses ( +- 3.27% ) (54.86%) L1-dcache-prefetches L1-dcache-prefetch-misses 4.9114 +- 0.0309 seconds time elapsed ( +- 0.63% ) Performance counter stats for './test_progs -t flow_dissector' (5 runs): 10948.40 msec task-clock # 0.942 CPUs utilized ( +- 0.05% ) 615 context-switches # 56.173 /sec ( +- 1.65% ) 1 cpu-migrations # 0.091 /sec ( +- 31.62% ) 567 page-faults # 51.788 /sec ( +- 0.44% ) 27334194328 cycles # 2.497 GHz ( +- 0.08% ) (61.05%) 56656528828 instructions # 2.07 insn per cycle ( +- 0.08% ) (66.67%) 10270389422 branches # 938.072 M/sec ( +- 0.10% ) (72.21%) 3453837 branch-misses # 0.03% of all branches ( +- 3.75% ) (72.27%) TopDownL1 # 0.52 retiring ( +- 0.16% ) (66.55%) # 0.27 frontend_bound ( +- 0.09% ) (60.91%) # 0.14 bad_speculation ( +- 0.08% ) (49.85%) # 0.07 backend_bound ( +- 0.16% ) (33.33%) 18982866028 L1-dcache-loads # 1.734 G/sec ( +- 0.24% ) (33.34%) 8802454 L1-dcache-load-misses # 0.05% of all L1-dcache accesses ( +- 52.30% ) (33.31%) 2612962 LLC-loads # 238.661 K/sec ( +- 29.78% ) (33.45%) 264107 LLC-load-misses # 10.11% of all LL-cache accesses ( +- 18.34% ) (39.07%) 15793205997 L1-icache-loads # 1.443 G/sec ( +- 0.15% ) (39.09%) 3930802 L1-icache-load-misses # 0.02% of all L1-icache accesses ( +- 3.72% ) (44.66%) 20097828496 dTLB-loads # 1.836 G/sec ( +- 0.09% ) (44.68%) 961757 dTLB-load-misses # 0.00% of all dTLB cache accesses ( +- 3.32% ) (50.15%) 15838728506 iTLB-loads # 1.447 G/sec ( +- 0.09% ) (55.62%) 167652 iTLB-load-misses # 0.00% of all iTLB cache accesses ( +- 1.28% ) (55.52%) L1-dcache-prefetches L1-dcache-prefetch-misses 11.6173 +- 0.0268 seconds time elapsed ( +- 0.23% ) [1] https://lore.kernel.org/bpf/20200724123644.5096-1-maciej.fijalkowski@intel.com/ Signed-off-by: Xu Kuohai --- arch/arm64/net/bpf_jit_comp.c | 294 +++++++++++++++++++++------------- 1 file changed, 183 insertions(+), 111 deletions(-) diff --git a/arch/arm64/net/bpf_jit_comp.c b/arch/arm64/net/bpf_jit_comp.c index 5c9039cf261d..8aa32cb140b9 100644 --- a/arch/arm64/net/bpf_jit_comp.c +++ b/arch/arm64/net/bpf_jit_comp.c @@ -76,10 +76,14 @@ struct jit_ctx { int epilogue_offset; int *offset; int exentry_idx; + int nr_used_callee_reg; + u8 used_callee_reg[8]; /* r6~r9, fp, arena_vm_start */ __le32 *image; __le32 *ro_image; u32 stack_size; u64 user_vm_start; + u64 arena_vm_start; + bool fp_used; }; struct bpf_plt { @@ -270,41 +274,141 @@ static bool is_lsi_offset(int offset, int scale) return true; } -/* generated prologue: +/* generated main prog prologue: * bti c // if CONFIG_ARM64_BTI_KERNEL * mov x9, lr * nop // POKE_OFFSET * paciasp // if CONFIG_ARM64_PTR_AUTH_KERNEL * stp x29, lr, [sp, #-16]! * mov x29, sp - * stp x19, x20, [sp, #-16]! - * stp x21, x22, [sp, #-16]! - * stp x26, x25, [sp, #-16]! - * stp x26, x25, [sp, #-16]! - * stp x27, x28, [sp, #-16]! - * mov x25, sp - * mov tcc, #0 + * stp xzr, x26, [sp, #-16]! + * mov x26, sp * // PROLOGUE_OFFSET + * // save callee-saved registers */ - static void prepare_bpf_tail_call_cnt(struct jit_ctx *ctx) { - const struct bpf_prog *prog = ctx->prog; - const bool is_main_prog = !bpf_is_subprog(prog); + const bool is_main_prog = !bpf_is_subprog(ctx->prog); const u8 ptr = bpf2a64[TCCNT_PTR]; - const u8 fp = bpf2a64[BPF_REG_FP]; - const u8 tcc = ptr; - emit(A64_PUSH(ptr, fp, A64_SP), ctx); if (is_main_prog) { /* Initialize tail_call_cnt. */ - emit(A64_MOVZ(1, tcc, 0, 0), ctx); - emit(A64_PUSH(tcc, fp, A64_SP), ctx); + emit(A64_PUSH(A64_ZR, ptr, A64_SP), ctx); emit(A64_MOV(1, ptr, A64_SP), ctx); + } else + emit(A64_PUSH(ptr, ptr, A64_SP), ctx); +} + +static void find_used_callee_regs(struct jit_ctx *ctx) +{ + int i; + const struct bpf_prog *prog = ctx->prog; + const struct bpf_insn *insn = &prog->insnsi[0]; + int reg_used = 0; + + for (i = 0; i < prog->len; i++, insn++) { + if (insn->dst_reg == BPF_REG_6 || insn->src_reg == BPF_REG_6) + reg_used |= 1; + + if (insn->dst_reg == BPF_REG_7 || insn->src_reg == BPF_REG_7) + reg_used |= 2; + + if (insn->dst_reg == BPF_REG_8 || insn->src_reg == BPF_REG_8) + reg_used |= 4; + + if (insn->dst_reg == BPF_REG_9 || insn->src_reg == BPF_REG_9) + reg_used |= 8; + + if (insn->dst_reg == BPF_REG_FP || insn->src_reg == BPF_REG_FP) { + ctx->fp_used = true; + reg_used |= 16; + } + } + + i = 0; + if (reg_used & 1) + ctx->used_callee_reg[i++] = bpf2a64[BPF_REG_6]; + + if (reg_used & 2) + ctx->used_callee_reg[i++] = bpf2a64[BPF_REG_7]; + + if (reg_used & 4) + ctx->used_callee_reg[i++] = bpf2a64[BPF_REG_8]; + + if (reg_used & 8) + ctx->used_callee_reg[i++] = bpf2a64[BPF_REG_9]; + + if (reg_used & 16) + ctx->used_callee_reg[i++] = bpf2a64[BPF_REG_FP]; + + if (ctx->arena_vm_start) + ctx->used_callee_reg[i++] = bpf2a64[ARENA_VM_START]; + + ctx->nr_used_callee_reg = i; +} + +/* Save callee-saved registers */ +static void push_callee_regs(struct jit_ctx *ctx) +{ + int reg1, reg2, i; + + /* + * Program acting as exception boundary should save all ARM64 + * Callee-saved registers as the exception callback needs to recover + * all ARM64 Callee-saved registers in its epilogue. + */ + if (ctx->prog->aux->exception_boundary) { + emit(A64_PUSH(A64_R(19), A64_R(20), A64_SP), ctx); + emit(A64_PUSH(A64_R(21), A64_R(22), A64_SP), ctx); + emit(A64_PUSH(A64_R(23), A64_R(24), A64_SP), ctx); + emit(A64_PUSH(A64_R(25), A64_R(26), A64_SP), ctx); + emit(A64_PUSH(A64_R(27), A64_R(28), A64_SP), ctx); } else { - emit(A64_PUSH(ptr, fp, A64_SP), ctx); - emit(A64_NOP, ctx); - emit(A64_NOP, ctx); + find_used_callee_regs(ctx); + for (i = 0; i + 1 < ctx->nr_used_callee_reg; i += 2) { + reg1 = ctx->used_callee_reg[i]; + reg2 = ctx->used_callee_reg[i + 1]; + emit(A64_PUSH(reg1, reg2, A64_SP), ctx); + } + if (i < ctx->nr_used_callee_reg) { + reg1 = ctx->used_callee_reg[i]; + /* keep SP 16-byte aligned */ + emit(A64_PUSH(reg1, A64_ZR, A64_SP), ctx); + } + } +} + +/* Restore callee-saved registers */ +static void pop_callee_regs(struct jit_ctx *ctx) +{ + struct bpf_prog_aux *aux = ctx->prog->aux; + int reg1, reg2, i; + + /* + * Program acting as exception boundary pushes R23 and R24 in addition + * to BPF callee-saved registers. Exception callback uses the boundary + * program's stack frame, so recover these extra registers in the above + * two cases. + */ + if (aux->exception_boundary || aux->exception_cb) { + emit(A64_POP(A64_R(27), A64_R(28), A64_SP), ctx); + emit(A64_POP(A64_R(25), A64_R(26), A64_SP), ctx); + emit(A64_POP(A64_R(23), A64_R(24), A64_SP), ctx); + emit(A64_POP(A64_R(21), A64_R(22), A64_SP), ctx); + emit(A64_POP(A64_R(19), A64_R(20), A64_SP), ctx); + } else { + i = ctx->nr_used_callee_reg - 1; + if (ctx->nr_used_callee_reg % 2 != 0) { + reg1 = ctx->used_callee_reg[i]; + emit(A64_POP(reg1, A64_ZR, A64_SP), ctx); + i--; + } + while (i > 0) { + reg1 = ctx->used_callee_reg[i - 1]; + reg2 = ctx->used_callee_reg[i]; + emit(A64_POP(reg1, reg2, A64_SP), ctx); + i -= 2; + } } } @@ -315,17 +419,12 @@ static void prepare_bpf_tail_call_cnt(struct jit_ctx *ctx) #define POKE_OFFSET (BTI_INSNS + 1) /* Tail call offset to jump into */ -#define PROLOGUE_OFFSET (BTI_INSNS + 2 + PAC_INSNS + 10) +#define PROLOGUE_OFFSET (BTI_INSNS + 2 + PAC_INSNS + 4) -static int build_prologue(struct jit_ctx *ctx, bool ebpf_from_cbpf, - bool is_exception_cb, u64 arena_vm_start) +static int build_prologue(struct jit_ctx *ctx, bool ebpf_from_cbpf) { const struct bpf_prog *prog = ctx->prog; const bool is_main_prog = !bpf_is_subprog(prog); - const u8 r6 = bpf2a64[BPF_REG_6]; - const u8 r7 = bpf2a64[BPF_REG_7]; - const u8 r8 = bpf2a64[BPF_REG_8]; - const u8 r9 = bpf2a64[BPF_REG_9]; const u8 fp = bpf2a64[BPF_REG_FP]; const u8 arena_vm_base = bpf2a64[ARENA_VM_START]; const int idx0 = ctx->idx; @@ -365,19 +464,28 @@ static int build_prologue(struct jit_ctx *ctx, bool ebpf_from_cbpf, emit(A64_MOV(1, A64_R(9), A64_LR), ctx); emit(A64_NOP, ctx); - if (!is_exception_cb) { + if (!prog->aux->exception_cb) { /* Sign lr */ if (IS_ENABLED(CONFIG_ARM64_PTR_AUTH_KERNEL)) emit(A64_PACIASP, ctx); + /* Save FP and LR registers to stay align with ARM64 AAPCS */ emit(A64_PUSH(A64_FP, A64_LR, A64_SP), ctx); emit(A64_MOV(1, A64_FP, A64_SP), ctx); - /* Save callee-saved registers */ - emit(A64_PUSH(r6, r7, A64_SP), ctx); - emit(A64_PUSH(r8, r9, A64_SP), ctx); prepare_bpf_tail_call_cnt(ctx); - emit(A64_PUSH(A64_R(27), A64_R(28), A64_SP), ctx); + + if (!ebpf_from_cbpf && is_main_prog) { + cur_offset = ctx->idx - idx0; + if (cur_offset != PROLOGUE_OFFSET) { + pr_err_once("PROLOGUE_OFFSET = %d, expected %d!\n", + cur_offset, PROLOGUE_OFFSET); + return -1; + } + /* BTI landing pad for the tail call, done with a BR */ + emit_bti(A64_BTI_J, ctx); + } + push_callee_regs(ctx); } else { /* * Exception callback receives FP of Main Program as third @@ -394,48 +502,23 @@ static int build_prologue(struct jit_ctx *ctx, bool ebpf_from_cbpf, emit(A64_SUB_I(1, A64_SP, A64_FP, 96), ctx); } - /* Set up BPF prog stack base register */ - emit(A64_MOV(1, fp, A64_SP), ctx); - - if (!ebpf_from_cbpf && is_main_prog) { - cur_offset = ctx->idx - idx0; - if (cur_offset != PROLOGUE_OFFSET) { - pr_err_once("PROLOGUE_OFFSET = %d, expected %d!\n", - cur_offset, PROLOGUE_OFFSET); - return -1; - } - - /* BTI landing pad for the tail call, done with a BR */ - emit_bti(A64_BTI_J, ctx); - } - - /* - * Program acting as exception boundary should save all ARM64 - * Callee-saved registers as the exception callback needs to recover - * all ARM64 Callee-saved registers in its epilogue. - */ - if (prog->aux->exception_boundary) { - /* - * As we are pushing two more registers, BPF_FP should be moved - * 16 bytes - */ - emit(A64_SUB_I(1, fp, fp, 16), ctx); - emit(A64_PUSH(A64_R(23), A64_R(24), A64_SP), ctx); - } + if (ctx->fp_used) + /* Set up BPF prog stack base register */ + emit(A64_MOV(1, fp, A64_SP), ctx); /* Stack must be multiples of 16B */ ctx->stack_size = round_up(prog->aux->stack_depth, 16); /* Set up function call stack */ - emit(A64_SUB_I(1, A64_SP, A64_SP, ctx->stack_size), ctx); + if (ctx->stack_size) + emit(A64_SUB_I(1, A64_SP, A64_SP, ctx->stack_size), ctx); - if (arena_vm_start) - emit_a64_mov_i64(arena_vm_base, arena_vm_start, ctx); + if (ctx->arena_vm_start) + emit_a64_mov_i64(arena_vm_base, ctx->arena_vm_start, ctx); return 0; } -static int out_offset = -1; /* initialized on the first pass of build_body() */ static int emit_bpf_tail_call(struct jit_ctx *ctx) { /* bpf_tail_call(void *prog_ctx, struct bpf_array *array, u64 index) */ @@ -446,10 +529,10 @@ static int emit_bpf_tail_call(struct jit_ctx *ctx) const u8 prg = bpf2a64[TMP_REG_2]; const u8 tcc = bpf2a64[TMP_REG_3]; const u8 ptr = bpf2a64[TCCNT_PTR]; - const int idx0 = ctx->idx; -#define cur_offset (ctx->idx - idx0) -#define jmp_offset (out_offset - (cur_offset)) size_t off; + __le32 *branch1 = NULL; + __le32 *branch2 = NULL; + __le32 *branch3 = NULL; /* if (index >= array->map.max_entries) * goto out; @@ -459,17 +542,20 @@ static int emit_bpf_tail_call(struct jit_ctx *ctx) emit(A64_LDR32(tmp, r2, tmp), ctx); emit(A64_MOV(0, r3, r3), ctx); emit(A64_CMP(0, r3, tmp), ctx); - emit(A64_B_(A64_COND_CS, jmp_offset), ctx); + branch1 = ctx->image + ctx->idx; + emit(A64_NOP, ctx); /* * if ((*tail_call_cnt_ptr) >= MAX_TAIL_CALL_CNT) * goto out; - * (*tail_call_cnt_ptr)++; */ emit_a64_mov_i64(tmp, MAX_TAIL_CALL_CNT, ctx); emit(A64_LDR64I(tcc, ptr, 0), ctx); emit(A64_CMP(1, tcc, tmp), ctx); - emit(A64_B_(A64_COND_CS, jmp_offset), ctx); + branch2 = ctx->image + ctx->idx; + emit(A64_NOP, ctx); + + /* (*tail_call_cnt_ptr)++; */ emit(A64_ADD_I(1, tcc, tcc, 1), ctx); /* prog = array->ptrs[index]; @@ -481,30 +567,37 @@ static int emit_bpf_tail_call(struct jit_ctx *ctx) emit(A64_ADD(1, tmp, r2, tmp), ctx); emit(A64_LSL(1, prg, r3, 3), ctx); emit(A64_LDR64(prg, tmp, prg), ctx); - emit(A64_CBZ(1, prg, jmp_offset), ctx); + branch3 = ctx->image + ctx->idx; + emit(A64_NOP, ctx); /* Update tail_call_cnt if the slot is populated. */ emit(A64_STR64I(tcc, ptr, 0), ctx); + /* restore SP */ + if (ctx->stack_size) + emit(A64_ADD_I(1, A64_SP, A64_SP, ctx->stack_size), ctx); + + pop_callee_regs(ctx); + /* goto *(prog->bpf_func + prologue_offset); */ off = offsetof(struct bpf_prog, bpf_func); emit_a64_mov_i64(tmp, off, ctx); emit(A64_LDR64(tmp, prg, tmp), ctx); emit(A64_ADD_I(1, tmp, tmp, sizeof(u32) * PROLOGUE_OFFSET), ctx); - emit(A64_ADD_I(1, A64_SP, A64_SP, ctx->stack_size), ctx); emit(A64_BR(tmp), ctx); - /* out: */ - if (out_offset == -1) - out_offset = cur_offset; - if (cur_offset != out_offset) { - pr_err_once("tail_call out_offset = %d, expected %d!\n", - cur_offset, out_offset); - return -1; + if (ctx->image) { + off = &ctx->image[ctx->idx] - branch1; + *branch1 = cpu_to_le32(A64_B_(A64_COND_CS, off)); + + off = &ctx->image[ctx->idx] - branch2; + *branch2 = cpu_to_le32(A64_B_(A64_COND_CS, off)); + + off = &ctx->image[ctx->idx] - branch3; + *branch3 = cpu_to_le32(A64_CBZ(1, prg, off)); } + return 0; -#undef cur_offset -#undef jmp_offset } #ifdef CONFIG_ARM64_LSE_ATOMICS @@ -730,37 +823,18 @@ static void build_plt(struct jit_ctx *ctx) plt->target = (u64)&dummy_tramp; } -static void build_epilogue(struct jit_ctx *ctx, bool is_exception_cb) +static void build_epilogue(struct jit_ctx *ctx) { const u8 r0 = bpf2a64[BPF_REG_0]; - const u8 r6 = bpf2a64[BPF_REG_6]; - const u8 r7 = bpf2a64[BPF_REG_7]; - const u8 r8 = bpf2a64[BPF_REG_8]; - const u8 r9 = bpf2a64[BPF_REG_9]; - const u8 fp = bpf2a64[BPF_REG_FP]; const u8 ptr = bpf2a64[TCCNT_PTR]; /* We're done with BPF stack */ - emit(A64_ADD_I(1, A64_SP, A64_SP, ctx->stack_size), ctx); - - /* - * Program acting as exception boundary pushes R23 and R24 in addition - * to BPF callee-saved registers. Exception callback uses the boundary - * program's stack frame, so recover these extra registers in the above - * two cases. - */ - if (ctx->prog->aux->exception_boundary || is_exception_cb) - emit(A64_POP(A64_R(23), A64_R(24), A64_SP), ctx); + if (ctx->stack_size) + emit(A64_ADD_I(1, A64_SP, A64_SP, ctx->stack_size), ctx); - /* Restore x27 and x28 */ - emit(A64_POP(A64_R(27), A64_R(28), A64_SP), ctx); - /* Restore fs (x25) and x26 */ - emit(A64_POP(ptr, fp, A64_SP), ctx); - emit(A64_POP(ptr, fp, A64_SP), ctx); + pop_callee_regs(ctx); - /* Restore callee-saved register */ - emit(A64_POP(r8, r9, A64_SP), ctx); - emit(A64_POP(r6, r7, A64_SP), ctx); + emit(A64_POP(A64_ZR, ptr, A64_SP), ctx); /* Restore FP/LR registers */ emit(A64_POP(A64_FP, A64_LR, A64_SP), ctx); @@ -1645,7 +1719,6 @@ struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *prog) bool tmp_blinded = false; bool extra_pass = false; struct jit_ctx ctx; - u64 arena_vm_start; u8 *image_ptr; u8 *ro_image_ptr; @@ -1663,7 +1736,6 @@ struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *prog) prog = tmp; } - arena_vm_start = bpf_arena_get_kern_vm_start(prog->aux->arena); jit_data = prog->aux->jit_data; if (!jit_data) { jit_data = kzalloc(sizeof(*jit_data), GFP_KERNEL); @@ -1694,6 +1766,7 @@ struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *prog) } ctx.user_vm_start = bpf_arena_get_user_vm_start(prog->aux->arena); + ctx.arena_vm_start = bpf_arena_get_kern_vm_start(prog->aux->arena); /* * 1. Initial fake pass to compute ctx->idx and ctx->offset. @@ -1701,8 +1774,7 @@ struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *prog) * BPF line info needs ctx->offset[i] to be the offset of * instruction[i] in jited image, so build prologue first. */ - if (build_prologue(&ctx, was_classic, prog->aux->exception_cb, - arena_vm_start)) { + if (build_prologue(&ctx, was_classic)) { prog = orig_prog; goto out_off; } @@ -1713,7 +1785,7 @@ struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *prog) } ctx.epilogue_offset = ctx.idx; - build_epilogue(&ctx, prog->aux->exception_cb); + build_epilogue(&ctx); build_plt(&ctx); extable_align = __alignof__(struct exception_table_entry); @@ -1750,14 +1822,14 @@ struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *prog) ctx.idx = 0; ctx.exentry_idx = 0; - build_prologue(&ctx, was_classic, prog->aux->exception_cb, arena_vm_start); + build_prologue(&ctx, was_classic); if (build_body(&ctx, extra_pass)) { prog = orig_prog; goto out_free_hdr; } - build_epilogue(&ctx, prog->aux->exception_cb); + build_epilogue(&ctx); build_plt(&ctx); /* 3. Extra pass to validate JITed code. */