arm64: insn: Add load-acquire and store-release instructions

Add load-acquire ("load_acq", LDAR{,B,H}) and store-release
("store_rel", STLR{,B,H}) instructions.  Breakdown of encoding:

                                size        L   (Rs)  o0 (Rt2) Rn    Rt
             mask (0x3fdffc00): 00 111111 1 1 0 11111 1  11111 00000 00000
  value, load_acq (0x08dffc00): 00 001000 1 1 0 11111 1  11111 00000 00000
 value, store_rel (0x089ffc00): 00 001000 1 0 0 11111 1  11111 00000 00000

As suggested by Xu [1], include all Should-Be-One (SBO) bits ("Rs" and
"Rt2" fields) in the "mask" and "value" numbers.

It is worth noting that we are adding the "no offset" variant of STLR
instead of the "pre-index" variant, which has a different encoding.

Reference: Arm Architecture Reference Manual (ARM DDI 0487K.a,
           ID032224),

  * C6.2.161 LDAR
  * C6.2.353 STLR

[1] https://lore.kernel.org/bpf/4e6641ce-3f1e-4251-8daf-4dd4b77d08c4@huaweicloud.com/

Acked-by: Xu Kuohai <xukuohai@huawei.com>
Signed-off-by: Peilin Ye <yepeilin@google.com>
Link: https://lore.kernel.org/r/ba92057b7502ce4c9c9b03b7d637abe5e178134e.1741049567.git.yepeilin@google.com
Signed-off-by: Alexei Starovoitov <ast@kernel.org>

Author: peilin-ye

arch/arm64/include/asm/insn.h

@@ -188,8 +188,10 @@ enum aarch64_insn_ldst_type {
 	AARCH64_INSN_LDST_STORE_PAIR_PRE_INDEX,
 	AARCH64_INSN_LDST_LOAD_PAIR_POST_INDEX,
 	AARCH64_INSN_LDST_STORE_PAIR_POST_INDEX,
+	AARCH64_INSN_LDST_LOAD_ACQ,
 	AARCH64_INSN_LDST_LOAD_EX,
 	AARCH64_INSN_LDST_LOAD_ACQ_EX,
+	AARCH64_INSN_LDST_STORE_REL,
 	AARCH64_INSN_LDST_STORE_EX,
 	AARCH64_INSN_LDST_STORE_REL_EX,
 	AARCH64_INSN_LDST_SIGNED_LOAD_IMM_OFFSET,
@@ -351,6 +353,8 @@ __AARCH64_INSN_FUNCS(ldr_imm,	0x3FC00000, 0x39400000)
 __AARCH64_INSN_FUNCS(ldr_lit,	0xBF000000, 0x18000000)
 __AARCH64_INSN_FUNCS(ldrsw_lit,	0xFF000000, 0x98000000)
 __AARCH64_INSN_FUNCS(exclusive,	0x3F800000, 0x08000000)
+__AARCH64_INSN_FUNCS(load_acq,  0x3FDFFC00, 0x08DFFC00)
+__AARCH64_INSN_FUNCS(store_rel, 0x3FDFFC00, 0x089FFC00)
 __AARCH64_INSN_FUNCS(load_ex,	0x3FC00000, 0x08400000)
 __AARCH64_INSN_FUNCS(store_ex,	0x3FC00000, 0x08000000)
 __AARCH64_INSN_FUNCS(mops,	0x3B200C00, 0x19000400)
@@ -602,6 +606,10 @@ u32 aarch64_insn_gen_load_store_pair(enum aarch64_insn_register reg1,
 				     int offset,
 				     enum aarch64_insn_variant variant,
 				     enum aarch64_insn_ldst_type type);
+u32 aarch64_insn_gen_load_acq_store_rel(enum aarch64_insn_register reg,
+					enum aarch64_insn_register base,
+					enum aarch64_insn_size_type size,
+					enum aarch64_insn_ldst_type type);
 u32 aarch64_insn_gen_load_store_ex(enum aarch64_insn_register reg,
 				   enum aarch64_insn_register base,
 				   enum aarch64_insn_register state,

arch/arm64/lib/insn.c

@@ -540,6 +540,35 @@ u32 aarch64_insn_gen_load_store_pair(enum aarch64_insn_register reg1,
 					     offset >> shift);
 }
 
+u32 aarch64_insn_gen_load_acq_store_rel(enum aarch64_insn_register reg,
+					enum aarch64_insn_register base,
+					enum aarch64_insn_size_type size,
+					enum aarch64_insn_ldst_type type)
+{
+	u32 insn;
+
+	switch (type) {
+	case AARCH64_INSN_LDST_LOAD_ACQ:
+		insn = aarch64_insn_get_load_acq_value();
+		break;
+	case AARCH64_INSN_LDST_STORE_REL:
+		insn = aarch64_insn_get_store_rel_value();
+		break;
+	default:
+		pr_err("%s: unknown load-acquire/store-release encoding %d\n",
+		       __func__, type);
+		return AARCH64_BREAK_FAULT;
+	}
+
+	insn = aarch64_insn_encode_ldst_size(size, insn);
+
+	insn = aarch64_insn_encode_register(AARCH64_INSN_REGTYPE_RT, insn,
+					    reg);
+
+	return aarch64_insn_encode_register(AARCH64_INSN_REGTYPE_RN, insn,
+					    base);
+}
+
 u32 aarch64_insn_gen_load_store_ex(enum aarch64_insn_register reg,
 				   enum aarch64_insn_register base,
 				   enum aarch64_insn_register state,