Merge branch 'arm32-bpf-add-support-for-cpuv4-insns'

Puranjay Mohan says:

====================
arm32, bpf: add support for cpuv4 insns

Changes in V2 -> V3
- Added comments at places where there could be confustion.
- In the patch for DIV64, fix the if-else case that would never run.
- In the same patch use a single instruction to POP caller saved regs.
- Add a patch to change maintainership of ARM32 BPF JIT.

Changes in V1 -> V2:
- Fix coding style issues.
- Don't use tmp variable for src in emit_ldsx_r() as it is redundant.
- Optimize emit_ldsx_r() when offset can fit in immediate.

Add the support for cpuv4 instructions for ARM32 BPF JIT. 64-bit division
was not supported earlier so this series adds 64-bit DIV, SDIV, MOD, SMOD
instructions as well.

This series needs any one of the patches from [1] to disable zero-extension
for BPF_MEMSX to support ldsx.

The relevant selftests have passed expect ldsx_insn which needs fentry:

Tested on BeagleBone Black (ARMv7-A):

[root@alarm del]# echo 1 > /proc/sys/net/core/bpf_jit_enable
[root@alarm del]# ./test_progs -a verifier_sdiv,verifier_movsx,verifier_ldsx,verifier_gotol,verifier_bswap
#337/1   verifier_bswap/BSWAP, 16:OK
#337/2   verifier_bswap/BSWAP, 16 @unpriv:OK
#337/3   verifier_bswap/BSWAP, 32:OK
#337/4   verifier_bswap/BSWAP, 32 @unpriv:OK
#337/5   verifier_bswap/BSWAP, 64:OK
#337/6   verifier_bswap/BSWAP, 64 @unpriv:OK
#337     verifier_bswap:OK
#351/1   verifier_gotol/gotol, small_imm:OK
#351/2   verifier_gotol/gotol, small_imm @unpriv:OK
#351     verifier_gotol:OK
#359/1   verifier_ldsx/LDSX, S8:OK
#359/2   verifier_ldsx/LDSX, S8 @unpriv:OK
#359/3   verifier_ldsx/LDSX, S16:OK
#359/4   verifier_ldsx/LDSX, S16 @unpriv:OK
#359/5   verifier_ldsx/LDSX, S32:OK
#359/6   verifier_ldsx/LDSX, S32 @unpriv:OK
#359/7   verifier_ldsx/LDSX, S8 range checking, privileged:OK
#359/8   verifier_ldsx/LDSX, S16 range checking:OK
#359/9   verifier_ldsx/LDSX, S16 range checking @unpriv:OK
#359/10  verifier_ldsx/LDSX, S32 range checking:OK
#359/11  verifier_ldsx/LDSX, S32 range checking @unpriv:OK
#359     verifier_ldsx:OK
#370/1   verifier_movsx/MOV32SX, S8:OK
#370/2   verifier_movsx/MOV32SX, S8 @unpriv:OK
#370/3   verifier_movsx/MOV32SX, S16:OK
#370/4   verifier_movsx/MOV32SX, S16 @unpriv:OK
#370/5   verifier_movsx/MOV64SX, S8:OK
#370/6   verifier_movsx/MOV64SX, S8 @unpriv:OK
#370/7   verifier_movsx/MOV64SX, S16:OK
#370/8   verifier_movsx/MOV64SX, S16 @unpriv:OK
#370/9   verifier_movsx/MOV64SX, S32:OK
#370/10  verifier_movsx/MOV64SX, S32 @unpriv:OK
#370/11  verifier_movsx/MOV32SX, S8, range_check:OK
#370/12  verifier_movsx/MOV32SX, S8, range_check @unpriv:OK
#370/13  verifier_movsx/MOV32SX, S16, range_check:OK
#370/14  verifier_movsx/MOV32SX, S16, range_check @unpriv:OK
#370/15  verifier_movsx/MOV32SX, S16, range_check 2:OK
#370/16  verifier_movsx/MOV32SX, S16, range_check 2 @unpriv:OK
#370/17  verifier_movsx/MOV64SX, S8, range_check:OK
#370/18  verifier_movsx/MOV64SX, S8, range_check @unpriv:OK
#370/19  verifier_movsx/MOV64SX, S16, range_check:OK
#370/20  verifier_movsx/MOV64SX, S16, range_check @unpriv:OK
#370/21  verifier_movsx/MOV64SX, S32, range_check:OK
#370/22  verifier_movsx/MOV64SX, S32, range_check @unpriv:OK
#370/23  verifier_movsx/MOV64SX, S16, R10 Sign Extension:OK
#370/24  verifier_movsx/MOV64SX, S16, R10 Sign Extension @unpriv:OK
#370     verifier_movsx:OK
#382/1   verifier_sdiv/SDIV32, non-zero imm divisor, check 1:OK
#382/2   verifier_sdiv/SDIV32, non-zero imm divisor, check 1 @unpriv:OK
#382/3   verifier_sdiv/SDIV32, non-zero imm divisor, check 2:OK
#382/4   verifier_sdiv/SDIV32, non-zero imm divisor, check 2 @unpriv:OK
#382/5   verifier_sdiv/SDIV32, non-zero imm divisor, check 3:OK
#382/6   verifier_sdiv/SDIV32, non-zero imm divisor, check 3 @unpriv:OK
#382/7   verifier_sdiv/SDIV32, non-zero imm divisor, check 4:OK
#382/8   verifier_sdiv/SDIV32, non-zero imm divisor, check 4 @unpriv:OK
#382/9   verifier_sdiv/SDIV32, non-zero imm divisor, check 5:OK
#382/10  verifier_sdiv/SDIV32, non-zero imm divisor, check 5 @unpriv:OK
#382/11  verifier_sdiv/SDIV32, non-zero imm divisor, check 6:OK
#382/12  verifier_sdiv/SDIV32, non-zero imm divisor, check 6 @unpriv:OK
#382/13  verifier_sdiv/SDIV32, non-zero imm divisor, check 7:OK
#382/14  verifier_sdiv/SDIV32, non-zero imm divisor, check 7 @unpriv:OK
#382/15  verifier_sdiv/SDIV32, non-zero imm divisor, check 8:OK
#382/16  verifier_sdiv/SDIV32, non-zero imm divisor, check 8 @unpriv:OK
#382/17  verifier_sdiv/SDIV32, non-zero reg divisor, check 1:OK
#382/18  verifier_sdiv/SDIV32, non-zero reg divisor, check 1 @unpriv:OK
#382/19  verifier_sdiv/SDIV32, non-zero reg divisor, check 2:OK
#382/20  verifier_sdiv/SDIV32, non-zero reg divisor, check 2 @unpriv:OK
#382/21  verifier_sdiv/SDIV32, non-zero reg divisor, check 3:OK
#382/22  verifier_sdiv/SDIV32, non-zero reg divisor, check 3 @unpriv:OK
#382/23  verifier_sdiv/SDIV32, non-zero reg divisor, check 4:OK
#382/24  verifier_sdiv/SDIV32, non-zero reg divisor, check 4 @unpriv:OK
#382/25  verifier_sdiv/SDIV32, non-zero reg divisor, check 5:OK
#382/26  verifier_sdiv/SDIV32, non-zero reg divisor, check 5 @unpriv:OK
#382/27  verifier_sdiv/SDIV32, non-zero reg divisor, check 6:OK
#382/28  verifier_sdiv/SDIV32, non-zero reg divisor, check 6 @unpriv:OK
#382/29  verifier_sdiv/SDIV32, non-zero reg divisor, check 7:OK
#382/30  verifier_sdiv/SDIV32, non-zero reg divisor, check 7 @unpriv:OK
#382/31  verifier_sdiv/SDIV32, non-zero reg divisor, check 8:OK
#382/32  verifier_sdiv/SDIV32, non-zero reg divisor, check 8 @unpriv:OK
#382/33  verifier_sdiv/SDIV64, non-zero imm divisor, check 1:OK
#382/34  verifier_sdiv/SDIV64, non-zero imm divisor, check 1 @unpriv:OK
#382/35  verifier_sdiv/SDIV64, non-zero imm divisor, check 2:OK
#382/36  verifier_sdiv/SDIV64, non-zero imm divisor, check 2 @unpriv:OK
#382/37  verifier_sdiv/SDIV64, non-zero imm divisor, check 3:OK
#382/38  verifier_sdiv/SDIV64, non-zero imm divisor, check 3 @unpriv:OK
#382/39  verifier_sdiv/SDIV64, non-zero imm divisor, check 4:OK
#382/40  verifier_sdiv/SDIV64, non-zero imm divisor, check 4 @unpriv:OK
#382/41  verifier_sdiv/SDIV64, non-zero imm divisor, check 5:OK
#382/42  verifier_sdiv/SDIV64, non-zero imm divisor, check 5 @unpriv:OK
#382/43  verifier_sdiv/SDIV64, non-zero imm divisor, check 6:OK
#382/44  verifier_sdiv/SDIV64, non-zero imm divisor, check 6 @unpriv:OK
#382/45  verifier_sdiv/SDIV64, non-zero reg divisor, check 1:OK
#382/46  verifier_sdiv/SDIV64, non-zero reg divisor, check 1 @unpriv:OK
#382/47  verifier_sdiv/SDIV64, non-zero reg divisor, check 2:OK
#382/48  verifier_sdiv/SDIV64, non-zero reg divisor, check 2 @unpriv:OK
#382/49  verifier_sdiv/SDIV64, non-zero reg divisor, check 3:OK
#382/50  verifier_sdiv/SDIV64, non-zero reg divisor, check 3 @unpriv:OK
#382/51  verifier_sdiv/SDIV64, non-zero reg divisor, check 4:OK
#382/52  verifier_sdiv/SDIV64, non-zero reg divisor, check 4 @unpriv:OK
#382/53  verifier_sdiv/SDIV64, non-zero reg divisor, check 5:OK
#382/54  verifier_sdiv/SDIV64, non-zero reg divisor, check 5 @unpriv:OK
#382/55  verifier_sdiv/SDIV64, non-zero reg divisor, check 6:OK
#382/56  verifier_sdiv/SDIV64, non-zero reg divisor, check 6 @unpriv:OK
#382/57  verifier_sdiv/SMOD32, non-zero imm divisor, check 1:OK
#382/58  verifier_sdiv/SMOD32, non-zero imm divisor, check 1 @unpriv:OK
#382/59  verifier_sdiv/SMOD32, non-zero imm divisor, check 2:OK
#382/60  verifier_sdiv/SMOD32, non-zero imm divisor, check 2 @unpriv:OK
#382/61  verifier_sdiv/SMOD32, non-zero imm divisor, check 3:OK
#382/62  verifier_sdiv/SMOD32, non-zero imm divisor, check 3 @unpriv:OK
#382/63  verifier_sdiv/SMOD32, non-zero imm divisor, check 4:OK
#382/64  verifier_sdiv/SMOD32, non-zero imm divisor, check 4 @unpriv:OK
#382/65  verifier_sdiv/SMOD32, non-zero imm divisor, check 5:OK
#382/66  verifier_sdiv/SMOD32, non-zero imm divisor, check 5 @unpriv:OK
#382/67  verifier_sdiv/SMOD32, non-zero imm divisor, check 6:OK
#382/68  verifier_sdiv/SMOD32, non-zero imm divisor, check 6 @unpriv:OK
#382/69  verifier_sdiv/SMOD32, non-zero reg divisor, check 1:OK
#382/70  verifier_sdiv/SMOD32, non-zero reg divisor, check 1 @unpriv:OK
#382/71  verifier_sdiv/SMOD32, non-zero reg divisor, check 2:OK
#382/72  verifier_sdiv/SMOD32, non-zero reg divisor, check 2 @unpriv:OK
#382/73  verifier_sdiv/SMOD32, non-zero reg divisor, check 3:OK
#382/74  verifier_sdiv/SMOD32, non-zero reg divisor, check 3 @unpriv:OK
#382/75  verifier_sdiv/SMOD32, non-zero reg divisor, check 4:OK
#382/76  verifier_sdiv/SMOD32, non-zero reg divisor, check 4 @unpriv:OK
#382/77  verifier_sdiv/SMOD32, non-zero reg divisor, check 5:OK
#382/78  verifier_sdiv/SMOD32, non-zero reg divisor, check 5 @unpriv:OK
#382/79  verifier_sdiv/SMOD32, non-zero reg divisor, check 6:OK
#382/80  verifier_sdiv/SMOD32, non-zero reg divisor, check 6 @unpriv:OK
#382/81  verifier_sdiv/SMOD64, non-zero imm divisor, check 1:OK
#382/82  verifier_sdiv/SMOD64, non-zero imm divisor, check 1 @unpriv:OK
#382/83  verifier_sdiv/SMOD64, non-zero imm divisor, check 2:OK
#382/84  verifier_sdiv/SMOD64, non-zero imm divisor, check 2 @unpriv:OK
#382/85  verifier_sdiv/SMOD64, non-zero imm divisor, check 3:OK
#382/86  verifier_sdiv/SMOD64, non-zero imm divisor, check 3 @unpriv:OK
#382/87  verifier_sdiv/SMOD64, non-zero imm divisor, check 4:OK
#382/88  verifier_sdiv/SMOD64, non-zero imm divisor, check 4 @unpriv:OK
#382/89  verifier_sdiv/SMOD64, non-zero imm divisor, check 5:OK
#382/90  verifier_sdiv/SMOD64, non-zero imm divisor, check 5 @unpriv:OK
#382/91  verifier_sdiv/SMOD64, non-zero imm divisor, check 6:OK
#382/92  verifier_sdiv/SMOD64, non-zero imm divisor, check 6 @unpriv:OK
#382/93  verifier_sdiv/SMOD64, non-zero imm divisor, check 7:OK
#382/94  verifier_sdiv/SMOD64, non-zero imm divisor, check 7 @unpriv:OK
#382/95  verifier_sdiv/SMOD64, non-zero imm divisor, check 8:OK
#382/96  verifier_sdiv/SMOD64, non-zero imm divisor, check 8 @unpriv:OK
#382/97  verifier_sdiv/SMOD64, non-zero reg divisor, check 1:OK
#382/98  verifier_sdiv/SMOD64, non-zero reg divisor, check 1 @unpriv:OK
#382/99  verifier_sdiv/SMOD64, non-zero reg divisor, check 2:OK
#382/100 verifier_sdiv/SMOD64, non-zero reg divisor, check 2 @unpriv:OK
#382/101 verifier_sdiv/SMOD64, non-zero reg divisor, check 3:OK
#382/102 verifier_sdiv/SMOD64, non-zero reg divisor, check 3 @unpriv:OK
#382/103 verifier_sdiv/SMOD64, non-zero reg divisor, check 4:OK
#382/104 verifier_sdiv/SMOD64, non-zero reg divisor, check 4 @unpriv:OK
#382/105 verifier_sdiv/SMOD64, non-zero reg divisor, check 5:OK
#382/106 verifier_sdiv/SMOD64, non-zero reg divisor, check 5 @unpriv:OK
#382/107 verifier_sdiv/SMOD64, non-zero reg divisor, check 6:OK
#382/108 verifier_sdiv/SMOD64, non-zero reg divisor, check 6 @unpriv:OK
#382/109 verifier_sdiv/SMOD64, non-zero reg divisor, check 7:OK
#382/110 verifier_sdiv/SMOD64, non-zero reg divisor, check 7 @unpriv:OK
#382/111 verifier_sdiv/SMOD64, non-zero reg divisor, check 8:OK
#382/112 verifier_sdiv/SMOD64, non-zero reg divisor, check 8 @unpriv:OK
#382/113 verifier_sdiv/SDIV32, zero divisor:OK
#382/114 verifier_sdiv/SDIV32, zero divisor @unpriv:OK
#382/115 verifier_sdiv/SDIV64, zero divisor:OK
#382/116 verifier_sdiv/SDIV64, zero divisor @unpriv:OK
#382/117 verifier_sdiv/SMOD32, zero divisor:OK
#382/118 verifier_sdiv/SMOD32, zero divisor @unpriv:OK
#382/119 verifier_sdiv/SMOD64, zero divisor:OK
#382/120 verifier_sdiv/SMOD64, zero divisor @unpriv:OK
#382     verifier_sdiv:OK
Summary: 5/163 PASSED, 0 SKIPPED, 0 FAILED

As the selftests don't compile for 32-bit architectures without
modifications due to long being 32-bit,
I have added new tests to lib/test_bpf.c for cpuv4 insns, all are passing:

test_bpf: Summary: 1052 PASSED, 0 FAILED, [891/1040 JIT'ed]
test_bpf: test_tail_calls: Summary: 10 PASSED, 0 FAILED, [10/10 JIT'ed]
test_bpf: test_skb_segment: Summary: 2 PASSED, 0 FAILED

[1] https://lore.kernel.org/all/mb61p5y4u3ptd.fsf@amazon.com/
====================

Link: https://lore.kernel.org/r/20230907230550.1417590-1-puranjay12@gmail.com
Signed-off-by: Alexei Starovoitov <ast@kernel.org>

2 files changed, 264 insertions, 20 deletions

diff --git a/arch/arm/net/bpf_jit_32.c b/arch/arm/net/bpf_jit_32.c
index 6a1c9fca5260..1d672457d02f 100644
--- a/arch/arm/net/bpf_jit_32.c
+++ b/arch/arm/net/bpf_jit_32.c
@@ -2,6 +2,7 @@
 /*
  * Just-In-Time compiler for eBPF filters on 32bit ARM
  *
+ * Copyright (c) 2023 Puranjay Mohan <puranjay12@gmail.com>
  * Copyright (c) 2017 Shubham Bansal <illusionist.neo@gmail.com>
  * Copyright (c) 2011 Mircea Gherzan <mgherzan@gmail.com>
  */
@@ -15,6 +16,7 @@
 #include <linux/string.h>
 #include <linux/slab.h>
 #include <linux/if_vlan.h>
+#include <linux/math64.h>
 
 #include <asm/cacheflush.h>
 #include <asm/hwcap.h>
@@ -228,6 +230,44 @@ static u32 jit_mod32(u32 dividend, u32 divisor)
 	return dividend % divisor;
 }
 
+static s32 jit_sdiv32(s32 dividend, s32 divisor)
+{
+	return dividend / divisor;
+}
+
+static s32 jit_smod32(s32 dividend, s32 divisor)
+{
+	return dividend % divisor;
+}
+
+/* Wrappers for 64-bit div/mod */
+static u64 jit_udiv64(u64 dividend, u64 divisor)
+{
+	return div64_u64(dividend, divisor);
+}
+
+static u64 jit_mod64(u64 dividend, u64 divisor)
+{
+	u64 rem;
+
+	div64_u64_rem(dividend, divisor, &rem);
+	return rem;
+}
+
+static s64 jit_sdiv64(s64 dividend, s64 divisor)
+{
+	return div64_s64(dividend, divisor);
+}
+
+static s64 jit_smod64(s64 dividend, s64 divisor)
+{
+	u64 q;
+
+	q = div64_s64(dividend, divisor);
+
+	return dividend - q * divisor;
+}
+
 static inline void _emit(int cond, u32 inst, struct jit_ctx *ctx)
 {
 	inst |= (cond << 28);
@@ -333,6 +373,9 @@ 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)
@@ -474,17 +517,18 @@ static inline int epilogue_offset(const struct jit_ctx *ctx)
 	return to - from - 2;
 }
 
-static inline void emit_udivmod(u8 rd, u8 rm, u8 rn, struct jit_ctx *ctx, u8 op)
+static inline void emit_udivmod(u8 rd, u8 rm, u8 rn, struct jit_ctx *ctx, u8 op, u8 sign)
 {
 	const int exclude_mask = BIT(ARM_R0) | BIT(ARM_R1);
 	const s8 *tmp = bpf2a32[TMP_REG_1];
+	u32 dst;
 
 #if __LINUX_ARM_ARCH__ == 7
 	if (elf_hwcap & HWCAP_IDIVA) {
-		if (op == BPF_DIV)
-			emit(ARM_UDIV(rd, rm, rn), ctx);
-		else {
-			emit(ARM_UDIV(ARM_IP, rm, rn), ctx);
+		if (op == BPF_DIV) {
+			emit(sign ? ARM_SDIV(rd, rm, rn) : ARM_UDIV(rd, rm, rn), ctx);
+		} else {
+			emit(sign ? ARM_SDIV(ARM_IP, rm, rn) : ARM_UDIV(ARM_IP, rm, rn), ctx);
 			emit(ARM_MLS(rd, rn, ARM_IP, rm), ctx);
 		}
 		return;
@@ -512,8 +556,19 @@ static inline void emit_udivmod(u8 rd, u8 rm, u8 rn, struct jit_ctx *ctx, u8 op)
 	emit(ARM_PUSH(CALLER_MASK & ~exclude_mask), ctx);
 
 	/* Call appropriate function */
-	emit_mov_i(ARM_IP, op == BPF_DIV ?
-		   (u32)jit_udiv32 : (u32)jit_mod32, ctx);
+	if (sign) {
+		if (op == BPF_DIV)
+			dst = (u32)jit_sdiv32;
+		else
+			dst = (u32)jit_smod32;
+	} else {
+		if (op == BPF_DIV)
+			dst = (u32)jit_udiv32;
+		else
+			dst = (u32)jit_mod32;
+	}
+
+	emit_mov_i(ARM_IP, dst, ctx);
 	emit_blx_r(ARM_IP, ctx);
 
 	/* Restore caller-saved registers from stack */
@@ -530,6 +585,78 @@ static inline void emit_udivmod(u8 rd, u8 rm, u8 rn, struct jit_ctx *ctx, u8 op)
 		emit(ARM_MOV_R(ARM_R0, tmp[1]), ctx);
 }
 
+static inline void emit_udivmod64(const s8 *rd, const s8 *rm, const s8 *rn, struct jit_ctx *ctx,
+				  u8 op, u8 sign)
+{
+	u32 dst;
+
+	/* Push caller-saved registers on stack */
+	emit(ARM_PUSH(CALLER_MASK), ctx);
+
+	/*
+	 * As we are implementing 64-bit div/mod as function calls, We need to put the dividend in
+	 * R0-R1 and the divisor in R2-R3. As we have already pushed these registers on the stack,
+	 * we can recover them later after returning from the function call.
+	 */
+	if (rm[1] != ARM_R0 || rn[1] != ARM_R2) {
+		/*
+		 * Move Rm to {R1, R0} if it is not already there.
+		 */
+		if (rm[1] != ARM_R0) {
+			if (rn[1] == ARM_R0)
+				emit(ARM_PUSH(BIT(ARM_R0) | BIT(ARM_R1)), ctx);
+			emit(ARM_MOV_R(ARM_R1, rm[0]), ctx);
+			emit(ARM_MOV_R(ARM_R0, rm[1]), ctx);
+			if (rn[1] == ARM_R0) {
+				emit(ARM_POP(BIT(ARM_R2) | BIT(ARM_R3)), ctx);
+				goto cont;
+			}
+		}
+		/*
+		 * Move Rn to {R3, R2} if it is not already there.
+		 */
+		if (rn[1] != ARM_R2) {
+			emit(ARM_MOV_R(ARM_R3, rn[0]), ctx);
+			emit(ARM_MOV_R(ARM_R2, rn[1]), ctx);
+		}
+	}
+
+cont:
+
+	/* Call appropriate function */
+	if (sign) {
+		if (op == BPF_DIV)
+			dst = (u32)jit_sdiv64;
+		else
+			dst = (u32)jit_smod64;
+	} else {
+		if (op == BPF_DIV)
+			dst = (u32)jit_udiv64;
+		else
+			dst = (u32)jit_mod64;
+	}
+
+	emit_mov_i(ARM_IP, dst, ctx);
+	emit_blx_r(ARM_IP, ctx);
+
+	/* Save return value */
+	if (rd[1] != ARM_R0) {
+		emit(ARM_MOV_R(rd[0], ARM_R1), ctx);
+		emit(ARM_MOV_R(rd[1], ARM_R0), ctx);
+	}
+
+	/* Recover {R3, R2} and {R1, R0} from stack if they are not Rd */
+	if (rd[1] != ARM_R0 && rd[1] != ARM_R2) {
+		emit(ARM_POP(CALLER_MASK), ctx);
+	} else if (rd[1] != ARM_R0) {
+		emit(ARM_POP(BIT(ARM_R0) | BIT(ARM_R1)), ctx);
+		emit(ARM_ADD_I(ARM_SP, ARM_SP, 8), ctx);
+	} else {
+		emit(ARM_ADD_I(ARM_SP, ARM_SP, 8), ctx);
+		emit(ARM_POP(BIT(ARM_R2) | BIT(ARM_R3)), ctx);
+	}
+}
+
 /* Is the translated BPF register on stack? */
 static bool is_stacked(s8 reg)
 {
@@ -744,12 +871,16 @@ static inline void emit_a32_alu_r64(const bool is64, const s8 dst[],
 }
 
 /* dst = src (4 bytes)*/
-static inline void emit_a32_mov_r(const s8 dst, const s8 src,
+static inline void emit_a32_mov_r(const s8 dst, const s8 src, const u8 off,
 				  struct jit_ctx *ctx) {
 	const s8 *tmp = bpf2a32[TMP_REG_1];
 	s8 rt;
 
 	rt = arm_bpf_get_reg32(src, tmp[0], ctx);
+	if (off && off != 32) {
+		emit(ARM_LSL_I(rt, rt, 32 - off), ctx);
+		emit(ARM_ASR_I(rt, rt, 32 - off), ctx);
+	}
 	arm_bpf_put_reg32(dst, rt, ctx);
 }
 
@@ -758,15 +889,15 @@ static inline void emit_a32_mov_r64(const bool is64, const s8 dst[],
 				  const s8 src[],
 				  struct jit_ctx *ctx) {
 	if (!is64) {
-		emit_a32_mov_r(dst_lo, src_lo, ctx);
+		emit_a32_mov_r(dst_lo, src_lo, 0, ctx);
 		if (!ctx->prog->aux->verifier_zext)
 			/* Zero out high 4 bytes */
 			emit_a32_mov_i(dst_hi, 0, ctx);
 	} else if (__LINUX_ARM_ARCH__ < 6 &&
 		   ctx->cpu_architecture < CPU_ARCH_ARMv5TE) {
 		/* complete 8 byte move */
-		emit_a32_mov_r(dst_lo, src_lo, ctx);
-		emit_a32_mov_r(dst_hi, src_hi, ctx);
+		emit_a32_mov_r(dst_lo, src_lo, 0, ctx);
+		emit_a32_mov_r(dst_hi, src_hi, 0, ctx);
 	} else if (is_stacked(src_lo) && is_stacked(dst_lo)) {
 		const u8 *tmp = bpf2a32[TMP_REG_1];
 
@@ -782,6 +913,24 @@ static inline void emit_a32_mov_r64(const bool is64, const s8 dst[],
 	}
 }
 
+/* dst = (signed)src */
+static inline void emit_a32_movsx_r64(const bool is64, const u8 off, const s8 dst[], const s8 src[],
+				      struct jit_ctx *ctx) {
+	const s8 *tmp = bpf2a32[TMP_REG_1];
+	const s8 *rt;
+
+	rt = arm_bpf_get_reg64(dst, tmp, ctx);
+
+	emit_a32_mov_r(dst_lo, src_lo, off, ctx);
+	if (!is64) {
+		if (!ctx->prog->aux->verifier_zext)
+			/* Zero out high 4 bytes */
+			emit_a32_mov_i(dst_hi, 0, ctx);
+	} else {
+		emit(ARM_ASR_I(rt[0], rt[1], 31), ctx);
+	}
+}
+
 /* Shift operations */
 static inline void emit_a32_alu_i(const s8 dst, const u32 val,
 				struct jit_ctx *ctx, const u8 op) {
@@ -1026,6 +1175,24 @@ 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 +1272,50 @@ 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)) {
+		/*
+		 * offset does not fit in the load/store immediate,
+		 * construct an ADD instruction to apply the offset.
+		 */
+		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,
@@ -1385,7 +1596,10 @@ static int build_insn(const struct bpf_insn *insn, struct jit_ctx *ctx)
 				emit_a32_mov_i(dst_hi, 0, ctx);
 				break;
 			}
-			emit_a32_mov_r64(is64, dst, src, ctx);
+			if (insn->off)
+				emit_a32_movsx_r64(is64, insn->off, dst, src, ctx);
+			else
+				emit_a32_mov_r64(is64, dst, src, ctx);
 			break;
 		case BPF_K:
 			/* Sign-extend immediate value to destination reg */
@@ -1461,7 +1675,7 @@ static int build_insn(const struct bpf_insn *insn, struct jit_ctx *ctx)
 			rt = src_lo;
 			break;
 		}
-		emit_udivmod(rd_lo, rd_lo, rt, ctx, BPF_OP(code));
+		emit_udivmod(rd_lo, rd_lo, rt, ctx, BPF_OP(code), off);
 		arm_bpf_put_reg32(dst_lo, rd_lo, ctx);
 		if (!ctx->prog->aux->verifier_zext)
 			emit_a32_mov_i(dst_hi, 0, ctx);
@@ -1470,7 +1684,19 @@ static int build_insn(const struct bpf_insn *insn, struct jit_ctx *ctx)
 	case BPF_ALU64 | BPF_DIV | BPF_X:
 	case BPF_ALU64 | BPF_MOD | BPF_K:
 	case BPF_ALU64 | BPF_MOD | BPF_X:
-		goto notyet;
+		rd = arm_bpf_get_reg64(dst, tmp2, ctx);
+		switch (BPF_SRC(code)) {
+		case BPF_X:
+			rs = arm_bpf_get_reg64(src, tmp, ctx);
+			break;
+		case BPF_K:
+			rs = tmp;
+			emit_a32_mov_se_i64(is64, rs, imm, ctx);
+			break;
+		}
+		emit_udivmod64(rd, rd, rs, ctx, BPF_OP(code), off);
+		arm_bpf_put_reg64(dst, rd, ctx);
+		break;
 	/* dst = dst << imm */
 	/* dst = dst >> imm */
 	/* dst = dst >> imm (signed) */
@@ -1545,10 +1771,12 @@ static int build_insn(const struct bpf_insn *insn, struct jit_ctx *ctx)
 		break;
 	/* dst = htole(dst) */
 	/* dst = htobe(dst) */
-	case BPF_ALU | BPF_END | BPF_FROM_LE:
-	case BPF_ALU | BPF_END | BPF_FROM_BE:
+	case BPF_ALU | BPF_END | BPF_FROM_LE: /* also BPF_TO_LE */
+	case BPF_ALU | BPF_END | BPF_FROM_BE: /* also BPF_TO_BE */
+	/* dst = bswap(dst) */
+	case BPF_ALU64 | BPF_END | BPF_FROM_LE: /* also BPF_TO_LE */
 		rd = arm_bpf_get_reg64(dst, tmp, ctx);
-		if (BPF_SRC(code) == BPF_FROM_LE)
+		if (BPF_SRC(code) == BPF_FROM_LE && BPF_CLASS(code) != BPF_ALU64)
 			goto emit_bswap_uxt;
 		switch (imm) {
 		case 16:
@@ -1603,8 +1831,15 @@ exit:
 	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:
@@ -1761,10 +1996,15 @@ go_jmp:
 		break;
 	/* JMP OFF */
 	case BPF_JMP | BPF_JA:
+	case BPF_JMP32 | BPF_JA:
 	{
-		if (off == 0)
+		if (BPF_CLASS(code) == BPF_JMP32 && imm != 0)
+			jmp_offset = bpf2a32_offset(i + imm, i, ctx);
+		else if (BPF_CLASS(code) == BPF_JMP && off != 0)
+			jmp_offset = bpf2a32_offset(i + off, i, ctx);
+		else
 			break;
-		jmp_offset = bpf2a32_offset(i+off, i, ctx);
+
 		check_imm24(jmp_offset);
 		emit(ARM_B(jmp_offset), ctx);
 		break;
diff --git a/arch/arm/net/bpf_jit_32.h b/arch/arm/net/bpf_jit_32.h
index e0b593a1498d..438f0e1f91a0 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
 
@@ -137,6 +139,7 @@
 #define ARM_INST_TST_I		0x03100000
 
 #define ARM_INST_UDIV		0x0730f010
+#define ARM_INST_SDIV		0x0710f010
 
 #define ARM_INST_UMULL		0x00800090
 
@@ -265,6 +268,7 @@
 #define ARM_TST_I(rn, imm)	_AL3_I(ARM_INST_TST, 0, rn, imm)
 
 #define ARM_UDIV(rd, rn, rm)	(ARM_INST_UDIV | (rd) << 16 | (rn) | (rm) << 8)
+#define ARM_SDIV(rd, rn, rm)	(ARM_INST_SDIV | (rd) << 16 | (rn) | (rm) << 8)
 
 #define ARM_UMULL(rd_lo, rd_hi, rn, rm)	(ARM_INST_UMULL | (rd_hi) << 16 \
 					 | (rd_lo) << 12 | (rm) << 8 | rn)