arm64: insn: Add encoder for bitwise operations using literals

We lack a way to encode operations such as AND, ORR, EOR that take
an immediate value. Doing so is quite involved, and is all about
reverse engineering the decoding algorithm described in the
pseudocode function DecodeBitMasks().

This has been tested by feeding it all the possible literal values
and comparing the output with that of GAS.

Acked-by: Christoffer Dall <christoffer.dall@linaro.org>
Acked-by: Catalin Marinas <catalin.marinas@arm.com>
Signed-off-by: Marc Zyngier <marc.zyngier@arm.com>

arch/arm64/include/asm/insn.h

@@ -315,6 +315,10 @@ __AARCH64_INSN_FUNCS(eor,	0x7F200000, 0x4A000000)
 __AARCH64_INSN_FUNCS(eon,	0x7F200000, 0x4A200000)
 __AARCH64_INSN_FUNCS(ands,	0x7F200000, 0x6A000000)
 __AARCH64_INSN_FUNCS(bics,	0x7F200000, 0x6A200000)
+__AARCH64_INSN_FUNCS(and_imm,	0x7F800000, 0x12000000)
+__AARCH64_INSN_FUNCS(orr_imm,	0x7F800000, 0x32000000)
+__AARCH64_INSN_FUNCS(eor_imm,	0x7F800000, 0x52000000)
+__AARCH64_INSN_FUNCS(ands_imm,	0x7F800000, 0x72000000)
 __AARCH64_INSN_FUNCS(b,		0xFC000000, 0x14000000)
 __AARCH64_INSN_FUNCS(bl,	0xFC000000, 0x94000000)
 __AARCH64_INSN_FUNCS(cbz,	0x7F000000, 0x34000000)
@@ -424,6 +428,11 @@ u32 aarch64_insn_gen_logical_shifted_reg(enum aarch64_insn_register dst,
 					 int shift,
 					 enum aarch64_insn_variant variant,
 					 enum aarch64_insn_logic_type type);
+u32 aarch64_insn_gen_logical_immediate(enum aarch64_insn_logic_type type,
+				       enum aarch64_insn_variant variant,
+				       enum aarch64_insn_register Rn,
+				       enum aarch64_insn_register Rd,
+				       u64 imm);
 u32 aarch64_insn_gen_prefetch(enum aarch64_insn_register base,
 			      enum aarch64_insn_prfm_type type,
 			      enum aarch64_insn_prfm_target target,

arch/arm64/kernel/insn.c

@@ -1485,3 +1485,139 @@ pstate_check_t * const aarch32_opcode_cond_checks[16] = {
 	__check_hi, __check_ls, __check_ge, __check_lt,
 	__check_gt, __check_le, __check_al, __check_al
 };
+
+static bool range_of_ones(u64 val)
+{
+	/* Doesn't handle full ones or full zeroes */
+	u64 sval = val >> __ffs64(val);
+
+	/* One of Sean Eron Anderson's bithack tricks */
+	return ((sval + 1) & (sval)) == 0;
+}
+
+static u32 aarch64_encode_immediate(u64 imm,
+				    enum aarch64_insn_variant variant,
+				    u32 insn)
+{
+	unsigned int immr, imms, n, ones, ror, esz, tmp;
+	u64 mask = ~0UL;
+
+	/* Can't encode full zeroes or full ones */
+	if (!imm || !~imm)
+		return AARCH64_BREAK_FAULT;
+
+	switch (variant) {
+	case AARCH64_INSN_VARIANT_32BIT:
+		if (upper_32_bits(imm))
+			return AARCH64_BREAK_FAULT;
+		esz = 32;
+		break;
+	case AARCH64_INSN_VARIANT_64BIT:
+		insn |= AARCH64_INSN_SF_BIT;
+		esz = 64;
+		break;
+	default:
+		pr_err("%s: unknown variant encoding %d\n", __func__, variant);
+		return AARCH64_BREAK_FAULT;
+	}
+
+	/*
+	 * Inverse of Replicate(). Try to spot a repeating pattern
+	 * with a pow2 stride.
+	 */
+	for (tmp = esz / 2; tmp >= 2; tmp /= 2) {
+		u64 emask = BIT(tmp) - 1;
+
+		if ((imm & emask) != ((imm >> tmp) & emask))
+			break;
+
+		esz = tmp;
+		mask = emask;
+	}
+
+	/* N is only set if we're encoding a 64bit value */
+	n = esz == 64;
+
+	/* Trim imm to the element size */
+	imm &= mask;
+
+	/* That's how many ones we need to encode */
+	ones = hweight64(imm);
+
+	/*
+	 * imms is set to (ones - 1), prefixed with a string of ones
+	 * and a zero if they fit. Cap it to 6 bits.
+	 */
+	imms  = ones - 1;
+	imms |= 0xf << ffs(esz);
+	imms &= BIT(6) - 1;
+
+	/* Compute the rotation */
+	if (range_of_ones(imm)) {
+		/*
+		 * Pattern: 0..01..10..0
+		 *
+		 * Compute how many rotate we need to align it right
+		 */
+		ror = __ffs64(imm);
+	} else {
+		/*
+		 * Pattern: 0..01..10..01..1
+		 *
+		 * Fill the unused top bits with ones, and check if
+		 * the result is a valid immediate (all ones with a
+		 * contiguous ranges of zeroes).
+		 */
+		imm |= ~mask;
+		if (!range_of_ones(~imm))
+			return AARCH64_BREAK_FAULT;
+
+		/*
+		 * Compute the rotation to get a continuous set of
+		 * ones, with the first bit set at position 0
+		 */
+		ror = fls(~imm);
+	}
+
+	/*
+	 * immr is the number of bits we need to rotate back to the
+	 * original set of ones. Note that this is relative to the
+	 * element size...
+	 */
+	immr = (esz - ror) % esz;
+
+	insn = aarch64_insn_encode_immediate(AARCH64_INSN_IMM_N, insn, n);
+	insn = aarch64_insn_encode_immediate(AARCH64_INSN_IMM_R, insn, immr);
+	return aarch64_insn_encode_immediate(AARCH64_INSN_IMM_S, insn, imms);
+}
+
+u32 aarch64_insn_gen_logical_immediate(enum aarch64_insn_logic_type type,
+				       enum aarch64_insn_variant variant,
+				       enum aarch64_insn_register Rn,
+				       enum aarch64_insn_register Rd,
+				       u64 imm)
+{
+	u32 insn;
+
+	switch (type) {
+	case AARCH64_INSN_LOGIC_AND:
+		insn = aarch64_insn_get_and_imm_value();
+		break;
+	case AARCH64_INSN_LOGIC_ORR:
+		insn = aarch64_insn_get_orr_imm_value();
+		break;
+	case AARCH64_INSN_LOGIC_EOR:
+		insn = aarch64_insn_get_eor_imm_value();
+		break;
+	case AARCH64_INSN_LOGIC_AND_SETFLAGS:
+		insn = aarch64_insn_get_ands_imm_value();
+		break;
+	default:
+		pr_err("%s: unknown logical encoding %d\n", __func__, type);
+		return AARCH64_BREAK_FAULT;
+	}
+
+	insn = aarch64_insn_encode_register(AARCH64_INSN_REGTYPE_RD, insn, Rd);
+	insn = aarch64_insn_encode_register(AARCH64_INSN_REGTYPE_RN, insn, Rn);
+	return aarch64_encode_immediate(imm, variant, insn);
+}