All of lore.kernel.org
 help / color / mirror / Atom feed
From: Puranjay Mohan <puranjay12@gmail.com>
To: Alexei Starovoitov <ast@kernel.org>,
	Daniel Borkmann <daniel@iogearbox.net>,
	Andrii Nakryiko <andrii@kernel.org>,
	Martin KaFai Lau <martin.lau@linux.dev>,
	Song Liu <song@kernel.org>,
	Yonghong Song <yonghong.song@linux.dev>,
	John Fastabend <john.fastabend@gmail.com>,
	KP Singh <kpsingh@kernel.org>,
	Stanislav Fomichev <sdf@google.com>, Hao Luo <haoluo@google.com>,
	Jiri Olsa <jolsa@kernel.org>,
	Shubham Bansal <illusionist.neo@gmail.com>,
	Russell King <linux@armlinux.org.uk>,
	Mykola Lysenko <mykolal@fb.com>, Shuah Khan <shuah@kernel.org>,
	bpf@vger.kernel.org, linux-kselftest@vger.kernel.org,
	linux-kernel@vger.kernel.org
Cc: puranjay12@gmail.com
Subject: [PATCH bpf-next v2 2/8] arm32, bpf: add support for sign-extension load instruction
Date: Wed,  6 Sep 2023 18:33:14 +0000	[thread overview]
Message-ID: <20230906183320.1959008-3-puranjay12@gmail.com> (raw)
In-Reply-To: <20230906183320.1959008-1-puranjay12@gmail.com>

The cpuv4 added the support of an instruction that is similar to load
but also sign-extends the result after the load.

BPF_MEMSX | <size> | BPF_LDX means dst = *(signed size *) (src + offset)
here <size> can be one of BPF_B, BPF_H, BPF_W.

ARM32 has instructions to load a byte or a half word with sign
extension into a 32bit register. As the JIT uses two 32 bit registers
to simulate a 64-bit BPF register, an extra instruction is emitted to
sign-extent the result up to the second register.

Signed-off-by: Puranjay Mohan <puranjay12@gmail.com>
---
 arch/arm/net/bpf_jit_32.c | 70 ++++++++++++++++++++++++++++++++++++++-
 arch/arm/net/bpf_jit_32.h |  2 ++
 2 files changed, 71 insertions(+), 1 deletion(-)

diff --git a/arch/arm/net/bpf_jit_32.c b/arch/arm/net/bpf_jit_32.c
index c03600fe86f6..0a272a02959b 100644
--- a/arch/arm/net/bpf_jit_32.c
+++ b/arch/arm/net/bpf_jit_32.c
@@ -333,6 +333,9 @@ static u32 arm_bpf_ldst_imm8(u32 op, u8 rt, u8 rn, s16 imm8)
 #define ARM_LDRD_I(rt, rn, off)	arm_bpf_ldst_imm8(ARM_INST_LDRD_I, rt, rn, off)
 #define ARM_LDRH_I(rt, rn, off)	arm_bpf_ldst_imm8(ARM_INST_LDRH_I, rt, rn, off)
 
+#define ARM_LDRSH_I(rt, rn, off) arm_bpf_ldst_imm8(ARM_INST_LDRSH_I, rt, rn, off)
+#define ARM_LDRSB_I(rt, rn, off) arm_bpf_ldst_imm8(ARM_INST_LDRSB_I, rt, rn, off)
+
 #define ARM_STR_I(rt, rn, off)	arm_bpf_ldst_imm12(ARM_INST_STR_I, rt, rn, off)
 #define ARM_STRB_I(rt, rn, off)	arm_bpf_ldst_imm12(ARM_INST_STRB_I, rt, rn, off)
 #define ARM_STRD_I(rt, rn, off)	arm_bpf_ldst_imm8(ARM_INST_STRD_I, rt, rn, off)
@@ -1026,6 +1029,24 @@ static bool is_ldst_imm(s16 off, const u8 size)
 	return -off_max <= off && off <= off_max;
 }
 
+static bool is_ldst_imm8(s16 off, const u8 size)
+{
+	s16 off_max = 0;
+
+	switch (size) {
+	case BPF_B:
+		off_max = 0xff;
+		break;
+	case BPF_W:
+		off_max = 0xfff;
+		break;
+	case BPF_H:
+		off_max = 0xff;
+		break;
+	}
+	return -off_max <= off && off <= off_max;
+}
+
 /* *(size *)(dst + off) = src */
 static inline void emit_str_r(const s8 dst, const s8 src[],
 			      s16 off, struct jit_ctx *ctx, const u8 sz){
@@ -1105,6 +1126,46 @@ static inline void emit_ldx_r(const s8 dst[], const s8 src,
 	arm_bpf_put_reg64(dst, rd, ctx);
 }
 
+/* dst = *(signed size*)(src + off) */
+static inline void emit_ldsx_r(const s8 dst[], const s8 src,
+			       s16 off, struct jit_ctx *ctx, const u8 sz){
+	const s8 *tmp = bpf2a32[TMP_REG_1];
+	const s8 *rd = is_stacked(dst_lo) ? tmp : dst;
+	s8 rm = src;
+	int add_off;
+
+	if (!is_ldst_imm8(off, sz)) {
+		add_off = imm8m(off);
+		if (add_off > 0) {
+			emit(ARM_ADD_I(tmp[0], src, add_off), ctx);
+			rm = tmp[0];
+		} else {
+			emit_a32_mov_i(tmp[0], off, ctx);
+			emit(ARM_ADD_R(tmp[0], tmp[0], src), ctx);
+			rm = tmp[0];
+		}
+		off = 0;
+	}
+
+	switch (sz) {
+	case BPF_B:
+		/* Load a Byte with sign extension*/
+		emit(ARM_LDRSB_I(rd[1], rm, off), ctx);
+		break;
+	case BPF_H:
+		/* Load a HalfWord with sign extension*/
+		emit(ARM_LDRSH_I(rd[1], rm, off), ctx);
+		break;
+	case BPF_W:
+		/* Load a Word*/
+		emit(ARM_LDR_I(rd[1], rm, off), ctx);
+		break;
+	}
+	/* Carry the sign extension to upper 32 bits */
+	emit(ARM_ASR_I(rd[0], rd[1], 31), ctx);
+	arm_bpf_put_reg64(dst, rd, ctx);
+}
+
 /* Arithmatic Operation */
 static inline void emit_ar_r(const u8 rd, const u8 rt, const u8 rm,
 			     const u8 rn, struct jit_ctx *ctx, u8 op,
@@ -1603,8 +1664,15 @@ static int build_insn(const struct bpf_insn *insn, struct jit_ctx *ctx)
 	case BPF_LDX | BPF_MEM | BPF_H:
 	case BPF_LDX | BPF_MEM | BPF_B:
 	case BPF_LDX | BPF_MEM | BPF_DW:
+	/* LDSX: dst = *(signed size *)(src + off) */
+	case BPF_LDX | BPF_MEMSX | BPF_B:
+	case BPF_LDX | BPF_MEMSX | BPF_H:
+	case BPF_LDX | BPF_MEMSX | BPF_W:
 		rn = arm_bpf_get_reg32(src_lo, tmp2[1], ctx);
-		emit_ldx_r(dst, rn, off, ctx, BPF_SIZE(code));
+		if (BPF_MODE(insn->code) == BPF_MEMSX)
+			emit_ldsx_r(dst, rn, off, ctx, BPF_SIZE(code));
+		else
+			emit_ldx_r(dst, rn, off, ctx, BPF_SIZE(code));
 		break;
 	/* speculation barrier */
 	case BPF_ST | BPF_NOSPEC:
diff --git a/arch/arm/net/bpf_jit_32.h b/arch/arm/net/bpf_jit_32.h
index e0b593a1498d..79c7373fadce 100644
--- a/arch/arm/net/bpf_jit_32.h
+++ b/arch/arm/net/bpf_jit_32.h
@@ -79,9 +79,11 @@
 #define ARM_INST_LDST__IMM12	0x00000fff
 #define ARM_INST_LDRB_I		0x05500000
 #define ARM_INST_LDRB_R		0x07d00000
+#define ARM_INST_LDRSB_I	0x015000d0
 #define ARM_INST_LDRD_I		0x014000d0
 #define ARM_INST_LDRH_I		0x015000b0
 #define ARM_INST_LDRH_R		0x019000b0
+#define ARM_INST_LDRSH_I	0x015000f0
 #define ARM_INST_LDR_I		0x05100000
 #define ARM_INST_LDR_R		0x07900000
 
-- 
2.39.2


  parent reply	other threads:[~2023-09-06 18:33 UTC|newest]

Thread overview: 17+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2023-09-06 18:33 [PATCH bpf-next v2 0/8] arm32, bpf: add support for cpuv4 insns Puranjay Mohan
2023-09-06 18:33 ` [PATCH bpf-next v2 1/8] arm32, bpf: add support for 32-bit offset jmp instruction Puranjay Mohan
2023-09-07  8:39   ` Russell King (Oracle)
2023-09-06 18:33 ` Puranjay Mohan [this message]
2023-09-07  8:44   ` [PATCH bpf-next v2 2/8] arm32, bpf: add support for sign-extension load instruction Russell King (Oracle)
2023-09-06 18:33 ` [PATCH bpf-next v2 3/8] arm32, bpf: add support for sign-extension mov instruction Puranjay Mohan
2023-09-07  8:45   ` Russell King (Oracle)
2023-09-06 18:33 ` [PATCH bpf-next v2 4/8] arm32, bpf: add support for unconditional bswap instruction Puranjay Mohan
2023-09-07  8:48   ` Russell King (Oracle)
2023-09-07  9:08     ` Puranjay Mohan
2023-09-07  9:15       ` Russell King (Oracle)
2023-09-06 18:33 ` [PATCH bpf-next v2 5/8] arm32, bpf: add support for 32-bit signed division Puranjay Mohan
2023-09-07  8:49   ` Russell King (Oracle)
2023-09-06 18:33 ` [PATCH bpf-next v2 6/8] arm32, bpf: add support for 64 bit division instruction Puranjay Mohan
2023-09-07  8:50   ` Russell King (Oracle)
2023-09-06 18:33 ` [PATCH bpf-next v2 7/8] selftest, bpf: enable cpu v4 tests for arm32 Puranjay Mohan
2023-09-06 18:33 ` [PATCH bpf-next v2 8/8] bpf/tests: add tests for cpuv4 instructions Puranjay Mohan

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=20230906183320.1959008-3-puranjay12@gmail.com \
    --to=puranjay12@gmail.com \
    --cc=andrii@kernel.org \
    --cc=ast@kernel.org \
    --cc=bpf@vger.kernel.org \
    --cc=daniel@iogearbox.net \
    --cc=haoluo@google.com \
    --cc=illusionist.neo@gmail.com \
    --cc=john.fastabend@gmail.com \
    --cc=jolsa@kernel.org \
    --cc=kpsingh@kernel.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-kselftest@vger.kernel.org \
    --cc=linux@armlinux.org.uk \
    --cc=martin.lau@linux.dev \
    --cc=mykolal@fb.com \
    --cc=sdf@google.com \
    --cc=shuah@kernel.org \
    --cc=song@kernel.org \
    --cc=yonghong.song@linux.dev \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.