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.comSigned-off-by: Alexei Starovoitov <ast@kernel.org>

MAINTAINERS

@@ -3596,9 +3596,10 @@ F:	Documentation/devicetree/bindings/iio/accel/bosch,bma400.yaml
 F:	drivers/iio/accel/bma400*
 
 BPF JIT for ARM
-M:	Shubham Bansal <illusionist.neo@gmail.com>
+M:	Russell King <linux@armlinux.org.uk>
+M:	Puranjay Mohan <puranjay12@gmail.com>
 L:	bpf@vger.kernel.org
-S:	Odd Fixes
+S:	Maintained
 F:	arch/arm/net/
 
 BPF JIT for ARM64

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)

include/linux/filter.h

@@ -117,21 +117,25 @@ struct ctl_table_header;
 
 /* ALU ops on immediates, bpf_add|sub|...: dst_reg += imm32 */
 
-#define BPF_ALU64_IMM(OP, DST, IMM)				\
+#define BPF_ALU64_IMM_OFF(OP, DST, IMM, OFF)			\
 	((struct bpf_insn) {					\
 		.code  = BPF_ALU64 | BPF_OP(OP) | BPF_K,	\
 		.dst_reg = DST,					\
 		.src_reg = 0,					\
-		.off   = 0,					\
+		.off   = OFF,					\
 		.imm   = IMM })
+#define BPF_ALU64_IMM(OP, DST, IMM)				\
+	BPF_ALU64_IMM_OFF(OP, DST, IMM, 0)
 
-#define BPF_ALU32_IMM(OP, DST, IMM)				\
+#define BPF_ALU32_IMM_OFF(OP, DST, IMM, OFF)			\
 	((struct bpf_insn) {					\
 		.code  = BPF_ALU | BPF_OP(OP) | BPF_K,		\
 		.dst_reg = DST,					\
 		.src_reg = 0,					\
-		.off   = 0,					\
+		.off   = OFF,					\
 		.imm   = IMM })
+#define BPF_ALU32_IMM(OP, DST, IMM)				\
+	BPF_ALU32_IMM_OFF(OP, DST, IMM, 0)
 
 /* Endianess conversion, cpu_to_{l,b}e(), {l,b}e_to_cpu() */
 
@@ -143,6 +147,16 @@ struct ctl_table_header;
 		.off   = 0,					\
 		.imm   = LEN })
 
+/* Byte Swap, bswap16/32/64 */
+
+#define BPF_BSWAP(DST, LEN)					\
+	((struct bpf_insn) {					\
+		.code  = BPF_ALU64 | BPF_END | BPF_SRC(BPF_TO_LE),	\
+		.dst_reg = DST,					\
+		.src_reg = 0,					\
+		.off   = 0,					\
+		.imm   = LEN })
+
 /* Short form of mov, dst_reg = src_reg */
 
 #define BPF_MOV64_REG(DST, SRC)					\
@@ -179,6 +193,24 @@ struct ctl_table_header;
 		.off   = 0,					\
 		.imm   = IMM })
 
+/* Short form of movsx, dst_reg = (s8,s16,s32)src_reg */
+
+#define BPF_MOVSX64_REG(DST, SRC, OFF)				\
+	((struct bpf_insn) {					\
+		.code  = BPF_ALU64 | BPF_MOV | BPF_X,		\
+		.dst_reg = DST,					\
+		.src_reg = SRC,					\
+		.off   = OFF,					\
+		.imm   = 0 })
+
+#define BPF_MOVSX32_REG(DST, SRC, OFF)				\
+	((struct bpf_insn) {					\
+		.code  = BPF_ALU | BPF_MOV | BPF_X,		\
+		.dst_reg = DST,					\
+		.src_reg = SRC,					\
+		.off   = OFF,					\
+		.imm   = 0 })
+
 /* Special form of mov32, used for doing explicit zero extension on dst. */
 #define BPF_ZEXT_REG(DST)					\
 	((struct bpf_insn) {					\
@@ -263,6 +295,16 @@ static inline bool insn_is_zext(const struct bpf_insn *insn)
 		.off   = OFF,					\
 		.imm   = 0 })
 
+/* Memory load, dst_reg = *(signed size *) (src_reg + off16) */
+
+#define BPF_LDX_MEMSX(SIZE, DST, SRC, OFF)			\
+	((struct bpf_insn) {					\
+		.code  = BPF_LDX | BPF_SIZE(SIZE) | BPF_MEMSX,	\
+		.dst_reg = DST,					\
+		.src_reg = SRC,					\
+		.off   = OFF,					\
+		.imm   = 0 })
+
 /* Memory store, *(uint *) (dst_reg + off16) = src_reg */
 
 #define BPF_STX_MEM(SIZE, DST, SRC, OFF)			\

lib/test_bpf.c

@@ -5111,6 +5111,104 @@ static struct bpf_test tests[] = {
 		{ },
 		{ { 0, 0xffffffff } }
 	},
+	/* MOVSX32 */
+	{
+		"ALU_MOVSX | BPF_B",
+		.u.insns_int = {
+			BPF_LD_IMM64(R2, 0x00000000ffffffefLL),
+			BPF_LD_IMM64(R3, 0xdeadbeefdeadbeefLL),
+			BPF_MOVSX32_REG(R1, R3, 8),
+			BPF_JMP_REG(BPF_JEQ, R2, R1, 2),
+			BPF_MOV32_IMM(R0, 2),
+			BPF_EXIT_INSN(),
+			BPF_MOV32_IMM(R0, 1),
+			BPF_EXIT_INSN(),
+		},
+		INTERNAL,
+		{ },
+		{ { 0, 0x1 } },
+	},
+	{
+		"ALU_MOVSX | BPF_H",
+		.u.insns_int = {
+			BPF_LD_IMM64(R2, 0x00000000ffffbeefLL),
+			BPF_LD_IMM64(R3, 0xdeadbeefdeadbeefLL),
+			BPF_MOVSX32_REG(R1, R3, 16),
+			BPF_JMP_REG(BPF_JEQ, R2, R1, 2),
+			BPF_MOV32_IMM(R0, 2),
+			BPF_EXIT_INSN(),
+			BPF_MOV32_IMM(R0, 1),
+			BPF_EXIT_INSN(),
+		},
+		INTERNAL,
+		{ },
+		{ { 0, 0x1 } },
+	},
+	{
+		"ALU_MOVSX | BPF_W",
+		.u.insns_int = {
+			BPF_LD_IMM64(R2, 0x00000000deadbeefLL),
+			BPF_LD_IMM64(R3, 0xdeadbeefdeadbeefLL),
+			BPF_MOVSX32_REG(R1, R3, 32),
+			BPF_JMP_REG(BPF_JEQ, R2, R1, 2),
+			BPF_MOV32_IMM(R0, 2),
+			BPF_EXIT_INSN(),
+			BPF_MOV32_IMM(R0, 1),
+			BPF_EXIT_INSN(),
+		},
+		INTERNAL,
+		{ },
+		{ { 0, 0x1 } },
+	},
+	/* MOVSX64 REG */
+	{
+		"ALU64_MOVSX | BPF_B",
+		.u.insns_int = {
+			BPF_LD_IMM64(R2, 0xffffffffffffffefLL),
+			BPF_LD_IMM64(R3, 0xdeadbeefdeadbeefLL),
+			BPF_MOVSX64_REG(R1, R3, 8),
+			BPF_JMP_REG(BPF_JEQ, R2, R1, 2),
+			BPF_MOV32_IMM(R0, 2),
+			BPF_EXIT_INSN(),
+			BPF_MOV32_IMM(R0, 1),
+			BPF_EXIT_INSN(),
+		},
+		INTERNAL,
+		{ },
+		{ { 0, 0x1 } },
+	},
+	{
+		"ALU64_MOVSX | BPF_H",
+		.u.insns_int = {
+			BPF_LD_IMM64(R2, 0xffffffffffffbeefLL),
+			BPF_LD_IMM64(R3, 0xdeadbeefdeadbeefLL),
+			BPF_MOVSX64_REG(R1, R3, 16),
+			BPF_JMP_REG(BPF_JEQ, R2, R1, 2),
+			BPF_MOV32_IMM(R0, 2),
+			BPF_EXIT_INSN(),
+			BPF_MOV32_IMM(R0, 1),
+			BPF_EXIT_INSN(),
+		},
+		INTERNAL,
+		{ },
+		{ { 0, 0x1 } },
+	},
+	{
+		"ALU64_MOVSX | BPF_W",
+		.u.insns_int = {
+			BPF_LD_IMM64(R2, 0xffffffffdeadbeefLL),
+			BPF_LD_IMM64(R3, 0xdeadbeefdeadbeefLL),
+			BPF_MOVSX64_REG(R1, R3, 32),
+			BPF_JMP_REG(BPF_JEQ, R2, R1, 2),
+			BPF_MOV32_IMM(R0, 2),
+			BPF_EXIT_INSN(),
+			BPF_MOV32_IMM(R0, 1),
+			BPF_EXIT_INSN(),
+		},
+		INTERNAL,
+		{ },
+		{ { 0, 0x1 } },
+	},
 	/* BPF_ALU | BPF_ADD | BPF_X */
 	{
 		"ALU_ADD_X: 1 + 2 = 3",
@@ -6105,6 +6203,106 @@ static struct bpf_test tests[] = {
 		{ },
 		{ { 0, 2 } },
 	},
+	/* BPF_ALU | BPF_DIV | BPF_X off=1 (SDIV) */
+	{
+		"ALU_SDIV_X: -6 / 2 = -3",
+		.u.insns_int = {
+			BPF_LD_IMM64(R0, -6),
+			BPF_ALU32_IMM(BPF_MOV, R1, 2),
+			BPF_ALU32_REG_OFF(BPF_DIV, R0, R1, 1),
+			BPF_EXIT_INSN(),
+		},
+		INTERNAL,
+		{ },
+		{ { 0, -3 } },
+	},
+	/* BPF_ALU | BPF_DIV | BPF_K off=1 (SDIV) */
+	{
+		"ALU_SDIV_K: -6 / 2 = -3",
+		.u.insns_int = {
+			BPF_LD_IMM64(R0, -6),
+			BPF_ALU32_IMM_OFF(BPF_DIV, R0, 2, 1),
+			BPF_EXIT_INSN(),
+		},
+		INTERNAL,
+		{ },
+		{ { 0, -3 } },
+	},
+	/* BPF_ALU64 | BPF_DIV | BPF_X off=1 (SDIV64) */
+	{
+		"ALU64_SDIV_X: -6 / 2 = -3",
+		.u.insns_int = {
+			BPF_LD_IMM64(R0, -6),
+			BPF_ALU32_IMM(BPF_MOV, R1, 2),
+			BPF_ALU64_REG_OFF(BPF_DIV, R0, R1, 1),
+			BPF_EXIT_INSN(),
+		},
+		INTERNAL,
+		{ },
+		{ { 0, -3 } },
+	},
+	/* BPF_ALU64 | BPF_DIV | BPF_K off=1 (SDIV64) */
+	{
+		"ALU64_SDIV_K: -6 / 2 = -3",
+		.u.insns_int = {
+			BPF_LD_IMM64(R0, -6),
+			BPF_ALU64_IMM_OFF(BPF_DIV, R0, 2, 1),
+			BPF_EXIT_INSN(),
+		},
+		INTERNAL,
+		{ },
+		{ { 0, -3 } },
+	},
+	/* BPF_ALU | BPF_MOD | BPF_X off=1 (SMOD) */
+	{
+		"ALU_SMOD_X: -7 % 2 = -1",
+		.u.insns_int = {
+			BPF_LD_IMM64(R0, -7),
+			BPF_ALU32_IMM(BPF_MOV, R1, 2),
+			BPF_ALU32_REG_OFF(BPF_MOD, R0, R1, 1),
+			BPF_EXIT_INSN(),
+		},
+		INTERNAL,
+		{ },
+		{ { 0, -1 } },
+	},
+	/* BPF_ALU | BPF_MOD | BPF_K off=1 (SMOD) */
+	{
+		"ALU_SMOD_K: -7 % 2 = -1",
+		.u.insns_int = {
+			BPF_LD_IMM64(R0, -7),
+			BPF_ALU32_IMM_OFF(BPF_MOD, R0, 2, 1),
+			BPF_EXIT_INSN(),
+		},
+		INTERNAL,
+		{ },
+		{ { 0, -1 } },
+	},
+	/* BPF_ALU64 | BPF_MOD | BPF_X off=1 (SMOD64) */
+	{
+		"ALU64_SMOD_X: -7 % 2 = -1",
+		.u.insns_int = {
+			BPF_LD_IMM64(R0, -7),
+			BPF_ALU32_IMM(BPF_MOV, R1, 2),
+			BPF_ALU64_REG_OFF(BPF_MOD, R0, R1, 1),
+			BPF_EXIT_INSN(),
+		},
+		INTERNAL,
+		{ },
+		{ { 0, -1 } },
+	},
+	/* BPF_ALU64 | BPF_MOD | BPF_K off=1 (SMOD64) */
+	{
+		"ALU64_SMOD_X: -7 % 2 = -1",
+		.u.insns_int = {
+			BPF_LD_IMM64(R0, -7),
+			BPF_ALU64_IMM_OFF(BPF_MOD, R0, 2, 1),
+			BPF_EXIT_INSN(),
+		},
+		INTERNAL,
+		{ },
+		{ { 0, -1 } },
+	},
 	/* BPF_ALU | BPF_AND | BPF_X */
 	{
 		"ALU_AND_X: 3 & 2 = 2",
@@ -7837,6 +8035,104 @@ static struct bpf_test tests[] = {
 		{ },
 		{ { 0, (u32) (cpu_to_le64(0xfedcba9876543210ULL) >> 32) } },
 	},
+	/* BSWAP */
+	{
+		"BSWAP 16: 0x0123456789abcdef -> 0xefcd",
+		.u.insns_int = {
+			BPF_LD_IMM64(R0, 0x0123456789abcdefLL),
+			BPF_BSWAP(R0, 16),
+			BPF_EXIT_INSN(),
+		},
+		INTERNAL,
+		{ },
+		{ { 0, 0xefcd } },
+	},
+	{
+		"BSWAP 32: 0x0123456789abcdef -> 0xefcdab89",
+		.u.insns_int = {
+			BPF_LD_IMM64(R0, 0x0123456789abcdefLL),
+			BPF_BSWAP(R0, 32),
+			BPF_ALU64_REG(BPF_MOV, R1, R0),
+			BPF_ALU64_IMM(BPF_RSH, R1, 32),
+			BPF_ALU32_REG(BPF_ADD, R0, R1), /* R1 = 0 */
+			BPF_EXIT_INSN(),
+		},
+		INTERNAL,
+		{ },
+		{ { 0, 0xefcdab89 } },
+	},
+	{
+		"BSWAP 64: 0x0123456789abcdef -> 0x67452301",
+		.u.insns_int = {
+			BPF_LD_IMM64(R0, 0x0123456789abcdefLL),
+			BPF_BSWAP(R0, 64),
+			BPF_EXIT_INSN(),
+		},
+		INTERNAL,
+		{ },
+		{ { 0, 0x67452301 } },
+	},
+	{
+		"BSWAP 64: 0x0123456789abcdef >> 32 -> 0xefcdab89",
+		.u.insns_int = {
+			BPF_LD_IMM64(R0, 0x0123456789abcdefLL),
+			BPF_BSWAP(R0, 64),
+			BPF_ALU64_IMM(BPF_RSH, R0, 32),
+			BPF_EXIT_INSN(),
+		},
+		INTERNAL,
+		{ },
+		{ { 0, 0xefcdab89 } },
+	},
+	/* BSWAP, reversed */
+	{
+		"BSWAP 16: 0xfedcba9876543210 -> 0x1032",
+		.u.insns_int = {
+			BPF_LD_IMM64(R0, 0xfedcba9876543210ULL),
+			BPF_BSWAP(R0, 16),
+			BPF_EXIT_INSN(),
+		},
+		INTERNAL,
+		{ },
+		{ { 0, 0x1032 } },
+	},
+	{
+		"BSWAP 32: 0xfedcba9876543210 -> 0x10325476",
+		.u.insns_int = {
+			BPF_LD_IMM64(R0, 0xfedcba9876543210ULL),
+			BPF_BSWAP(R0, 32),
+			BPF_ALU64_REG(BPF_MOV, R1, R0),
+			BPF_ALU64_IMM(BPF_RSH, R1, 32),
+			BPF_ALU32_REG(BPF_ADD, R0, R1), /* R1 = 0 */
+			BPF_EXIT_INSN(),
+		},
+		INTERNAL,
+		{ },
+		{ { 0, 0x10325476 } },
+	},
+	{
+		"BSWAP 64: 0xfedcba9876543210 -> 0x98badcfe",
+		.u.insns_int = {
+			BPF_LD_IMM64(R0, 0xfedcba9876543210ULL),
+			BPF_BSWAP(R0, 64),
+			BPF_EXIT_INSN(),
+		},
+		INTERNAL,
+		{ },
+		{ { 0, 0x98badcfe } },
+	},
+	{
+		"BSWAP 64: 0xfedcba9876543210 >> 32 -> 0x10325476",
+		.u.insns_int = {
+			BPF_LD_IMM64(R0, 0xfedcba9876543210ULL),
+			BPF_BSWAP(R0, 64),
+			BPF_ALU64_IMM(BPF_RSH, R0, 32),
+			BPF_EXIT_INSN(),
+		},
+		INTERNAL,
+		{ },
+		{ { 0, 0x10325476 } },
+	},
 	/* BPF_LDX_MEM B/H/W/DW */
 	{
 		"BPF_LDX_MEM | BPF_B, base",
@@ -8228,6 +8524,67 @@ static struct bpf_test tests[] = {
 		{ { 32, 0 } },
 		.stack_depth = 0,
 	},
+	/* BPF_LDX_MEMSX B/H/W */
+	{
+		"BPF_LDX_MEMSX | BPF_B",
+		.u.insns_int = {
+			BPF_LD_IMM64(R1, 0xdead0000000000f0ULL),
+			BPF_LD_IMM64(R2, 0xfffffffffffffff0ULL),
+			BPF_STX_MEM(BPF_DW, R10, R1, -8),
+#ifdef __BIG_ENDIAN
+			BPF_LDX_MEMSX(BPF_B, R0, R10, -1),
+#else
+			BPF_LDX_MEMSX(BPF_B, R0, R10, -8),
+#endif
+			BPF_JMP_REG(BPF_JNE, R0, R2, 1),
+			BPF_ALU64_IMM(BPF_MOV, R0, 0),
+			BPF_EXIT_INSN(),
+		},
+		INTERNAL,
+		{ },
+		{ { 0, 0 } },
+		.stack_depth = 8,
+	},
+	{
+		"BPF_LDX_MEMSX | BPF_H",
+		.u.insns_int = {
+			BPF_LD_IMM64(R1, 0xdead00000000f123ULL),
+			BPF_LD_IMM64(R2, 0xfffffffffffff123ULL),
+			BPF_STX_MEM(BPF_DW, R10, R1, -8),
+#ifdef __BIG_ENDIAN
+			BPF_LDX_MEMSX(BPF_H, R0, R10, -2),
+#else
+			BPF_LDX_MEMSX(BPF_H, R0, R10, -8),
+#endif
+			BPF_JMP_REG(BPF_JNE, R0, R2, 1),
+			BPF_ALU64_IMM(BPF_MOV, R0, 0),
+			BPF_EXIT_INSN(),
+		},
+		INTERNAL,
+		{ },
+		{ { 0, 0 } },
+		.stack_depth = 8,
+	},
+	{
+		"BPF_LDX_MEMSX | BPF_W",
+		.u.insns_int = {
+			BPF_LD_IMM64(R1, 0x00000000deadbeefULL),
+			BPF_LD_IMM64(R2, 0xffffffffdeadbeefULL),
+			BPF_STX_MEM(BPF_DW, R10, R1, -8),
+#ifdef __BIG_ENDIAN
+			BPF_LDX_MEMSX(BPF_W, R0, R10, -4),
+#else
+			BPF_LDX_MEMSX(BPF_W, R0, R10, -8),
+#endif
+			BPF_JMP_REG(BPF_JNE, R0, R2, 1),
+			BPF_ALU64_IMM(BPF_MOV, R0, 0),
+			BPF_EXIT_INSN(),
+		},
+		INTERNAL,
+		{ },
+		{ { 0, 0 } },
+		.stack_depth = 8,
+	},
 	/* BPF_STX_MEM B/H/W/DW */
 	{
 		"BPF_STX_MEM | BPF_B",
@@ -9474,6 +9831,20 @@ static struct bpf_test tests[] = {
 		{ },
 		{ { 0, 1 } },
 	},
+	/* BPF_JMP32 | BPF_JA */
+	{
+		"JMP32_JA: Unconditional jump: if (true) return 1",
+		.u.insns_int = {
+			BPF_ALU32_IMM(BPF_MOV, R0, 0),
+			BPF_JMP32_IMM(BPF_JA, 0, 1, 0),
+			BPF_EXIT_INSN(),
+			BPF_ALU32_IMM(BPF_MOV, R0, 1),
+			BPF_EXIT_INSN(),
+		},
+		INTERNAL,
+		{ },
+		{ { 0, 1 } },
+	},
 	/* BPF_JMP | BPF_JSLT | BPF_K */
 	{
 		"JMP_JSLT_K: Signed jump: if (-2 < -1) return 1",

tools/testing/selftests/bpf/progs/verifier_bswap.c

@@ -5,7 +5,8 @@
 #include "bpf_misc.h"
 
 #if (defined(__TARGET_ARCH_arm64) || defined(__TARGET_ARCH_x86) || \
-     (defined(__TARGET_ARCH_riscv) && __riscv_xlen == 64)) && __clang_major__ >= 18
+	(defined(__TARGET_ARCH_riscv) && __riscv_xlen == 64) || defined(__TARGET_ARCH_arm)) && \
+	__clang_major__ >= 18
 
 SEC("socket")
 __description("BSWAP, 16")

tools/testing/selftests/bpf/progs/verifier_gotol.c

@@ -5,7 +5,8 @@
 #include "bpf_misc.h"
 
 #if (defined(__TARGET_ARCH_arm64) || defined(__TARGET_ARCH_x86) || \
-     (defined(__TARGET_ARCH_riscv) && __riscv_xlen == 64)) && __clang_major__ >= 18
+	(defined(__TARGET_ARCH_riscv) && __riscv_xlen == 64) || defined(__TARGET_ARCH_arm)) && \
+	__clang_major__ >= 18
 
 SEC("socket")
 __description("gotol, small_imm")

tools/testing/selftests/bpf/progs/verifier_ldsx.c

@@ -5,7 +5,8 @@
 #include "bpf_misc.h"
 
 #if (defined(__TARGET_ARCH_arm64) || defined(__TARGET_ARCH_x86) || \
-     (defined(__TARGET_ARCH_riscv) && __riscv_xlen == 64)) && __clang_major__ >= 18
+	(defined(__TARGET_ARCH_riscv) && __riscv_xlen == 64) || defined(__TARGET_ARCH_arm)) && \
+	__clang_major__ >= 18
 
 SEC("socket")
 __description("LDSX, S8")

tools/testing/selftests/bpf/progs/verifier_movsx.c

@@ -5,7 +5,8 @@
 #include "bpf_misc.h"
 
 #if (defined(__TARGET_ARCH_arm64) || defined(__TARGET_ARCH_x86) || \
-     (defined(__TARGET_ARCH_riscv) && __riscv_xlen == 64)) && __clang_major__ >= 18
+	(defined(__TARGET_ARCH_riscv) && __riscv_xlen == 64) || defined(__TARGET_ARCH_arm)) && \
+	__clang_major__ >= 18
 
 SEC("socket")
 __description("MOV32SX, S8")

tools/testing/selftests/bpf/progs/verifier_sdiv.c

@@ -5,7 +5,8 @@
 #include "bpf_misc.h"
 
 #if (defined(__TARGET_ARCH_arm64) || defined(__TARGET_ARCH_x86) || \
-     (defined(__TARGET_ARCH_riscv) && __riscv_xlen == 64)) && __clang_major__ >= 18
+	(defined(__TARGET_ARCH_riscv) && __riscv_xlen == 64) || defined(__TARGET_ARCH_arm)) && \
+	__clang_major__ >= 18
 
 SEC("socket")
 __description("SDIV32, non-zero imm divisor, check 1")