[PATCH v10 06/13] x86/insn-eval: Add support to resolve 16-bit address encodings

[Ricardo Neri]

Tasks running in virtual-8086 mode, in protected mode with code segment
descriptors that specify 16-bit default address sizes via the
D bit, or via an address override prefix will use 16-bit addressing form
encodings as described in the Intel 64 and IA-32 Architecture Software
Developer's Manual Volume 2A Section 2.1.5, Table 2-1.

16-bit addressing encodings differ in several ways from the 32-bit/64-bit
addressing form encodings: ModRM.rm points to different registers and, in
some cases, effective addresses are indicated by the addition of the value
of two registers. Also, there is no support for SIB bytes. Thus, a
separate function is needed to parse this form of addressing.

Three functions are introduced. get_reg_offset_16() obtains the
offset from the base of pt_regs of the registers indicated by the ModRM
byte of the address encoding. get_eff_addr_modrm_16() computes the
effective address from the value of the register operands.
get_addr_ref_16() computes the linear address using the obtained effective
address and the base address of the segment.

Segment limits are enforced when running in protected mode.

Cc: Dave Hansen <dave.hansen@xxxxxxxxxxxxxxx>
Cc: Adam Buchbinder <adam.buchbinder@xxxxxxxxx>
Cc: Colin Ian King <colin.king@xxxxxxxxxxxxx>
Cc: Lorenzo Stoakes <lstoakes@xxxxxxxxx>
Cc: Qiaowei Ren <qiaowei.ren@xxxxxxxxx>
Cc: Arnaldo Carvalho de Melo <acme@xxxxxxxxxx>
Cc: Masami Hiramatsu <mhiramat@xxxxxxxxxx>
Cc: Adrian Hunter <adrian.hunter@xxxxxxxxx>
Cc: Kees Cook <keescook@xxxxxxxxxxxx>
Cc: Thomas Garnier <thgarnie@xxxxxxxxxx>
Cc: Peter Zijlstra <peterz@xxxxxxxxxxxxx>
Cc: Borislav Petkov <bp@xxxxxxx>
Cc: Dmitry Vyukov <dvyukov@xxxxxxxxxx>
Cc: Ravi V. Shankar <ravi.v.shankar@xxxxxxxxx>
Cc: x86@xxxxxxxxxx
Signed-off-by: Ricardo Neri <ricardo.neri-calderon@xxxxxxxxxxxxxxx>
---
 arch/x86/lib/insn-eval.c | 213 ++++++++++++++++++++++++++++++++++++++++++++++-
 1 file changed, 212 insertions(+), 1 deletion(-)

diff --git a/arch/x86/lib/insn-eval.c b/arch/x86/lib/insn-eval.c
index 66d597d..cee168b 100644
--- a/arch/x86/lib/insn-eval.c
+++ b/arch/x86/lib/insn-eval.c
@@ -481,6 +481,80 @@ static int get_reg_offset(struct insn *insn, struct pt_regs *regs,
 }
 
 /**
+ * get_reg_offset_16() - Obtain offset of register indicated by instruction
+ * @insn:	Instruction containing ModRM byte
+ * @regs:	Register values as seen when entering kernel mode
+ * @offs1:	Offset of the first operand register
+ * @offs2:	Offset of the second opeand register, if applicable
+ *
+ * Obtain the offset, in pt_regs, of the registers indicated by the ModRM byte
+ * in @insn. This function is to be used with 16-bit address encodings. The
+ * @offs1 and @offs2 will be written with the offset of the two registers
+ * indicated by the instruction. In cases where any of the registers is not
+ * referenced by the instruction, the value will be set to -EDOM.
+ *
+ * Returns:
+ *
+ * 0 on success, -EINVAL on error.
+ */
+static int get_reg_offset_16(struct insn *insn, struct pt_regs *regs,
+			     int *offs1, int *offs2)
+{
+	/*
+	 * 16-bit addressing can use one or two registers. Specifics of
+	 * encodings are given in Table 2-1. "16-Bit Addressing Forms with the
+	 * ModR/M Byte" of the Intel Software Development Manual.
+	 */
+	static const int regoff1[] = {
+		offsetof(struct pt_regs, bx),
+		offsetof(struct pt_regs, bx),
+		offsetof(struct pt_regs, bp),
+		offsetof(struct pt_regs, bp),
+		offsetof(struct pt_regs, si),
+		offsetof(struct pt_regs, di),
+		offsetof(struct pt_regs, bp),
+		offsetof(struct pt_regs, bx),
+	};
+
+	static const int regoff2[] = {
+		offsetof(struct pt_regs, si),
+		offsetof(struct pt_regs, di),
+		offsetof(struct pt_regs, si),
+		offsetof(struct pt_regs, di),
+		-EDOM,
+		-EDOM,
+		-EDOM,
+		-EDOM,
+	};
+
+	if (!offs1 || !offs2)
+		return -EINVAL;
+
+	/* Operand is a register, use the generic function. */
+	if (X86_MODRM_MOD(insn->modrm.value) == 3) {
+		*offs1 = insn_get_modrm_rm_off(insn, regs);
+		*offs2 = -EDOM;
+		return 0;
+	}
+
+	*offs1 = regoff1[X86_MODRM_RM(insn->modrm.value)];
+	*offs2 = regoff2[X86_MODRM_RM(insn->modrm.value)];
+
+	/*
+	 * If ModRM.mod is 0 and ModRM.rm is 110b, then we use displacement-
+	 * only addressing. This means that no registers are involved in
+	 * computing the effective address. Thus, ensure that the first
+	 * register offset is invalild. The second register offset is already
+	 * invalid under the aforementioned conditions.
+	 */
+	if ((X86_MODRM_MOD(insn->modrm.value) == 0) &&
+	    (X86_MODRM_RM(insn->modrm.value) == 6))
+		*offs1 = -EDOM;
+
+	return 0;
+}
+
+/**
  * get_desc() - Obtain pointer to a segment descriptor
  * @sel:	Segment selector
  *
@@ -815,7 +889,9 @@ static int get_eff_addr_reg(struct insn *insn, struct pt_regs *regs,
 		return -EINVAL;
 
 	/* Ignore bytes that are outside the address size */
-	if (insn->addr_bytes == 4)
+	if (insn->addr_bytes == 2)
+		*eff_addr = (long)(regs_get_register(regs, *regoff) & 0xffff);
+	else if (insn->addr_bytes == 4)
 		*eff_addr = (long)(regs_get_register(regs, *regoff) &
 				   0xffffffff);
 	else /* 64-bit address */
@@ -892,6 +968,74 @@ static int get_eff_addr_modrm(struct insn *insn, struct pt_regs *regs,
 }
 
 /**
+ * get_eff_addr_modrm_16() - Obtain referenced effective address via ModRM
+ * @insn:	Instruction. Must be valid.
+ * @regs:	Register values as seen when entering kernel mode
+ * @regoff:	Obtained operand offset, in pt_regs, associated with segment
+ * @eff_addr:	Obtained effective address
+ *
+ * Obtain the 16-bit effective address referenced by the ModRM byte of @insn.
+ * After identifying the registers involved in the register-indirect memory
+ * reference, its value is obtained from the operands in @regs. The computed
+ * address is stored @eff_addr. Also, the register operand that indicates
+ * the associated segment is stored in @regoff, this parameter can later be used
+ * to determine such segment.
+ *
+ * Returns:
+ *
+ * 0 on success. @eff_addr will have the referenced effective address. @regoff
+ * will have a register, as an offset from the base of pt_regs, that can be used
+ * to resolve the associated segment.
+ *
+ * -EINVAL on error.
+ */
+static int get_eff_addr_modrm_16(struct insn *insn, struct pt_regs *regs,
+				 int *regoff, short *eff_addr)
+{
+	int addr_offset1, addr_offset2, ret;
+	short addr1 = 0, addr2 = 0;
+
+	if (insn->addr_bytes != 2)
+		return -EINVAL;
+
+	insn_get_modrm(insn);
+
+	if (!insn->modrm.nbytes)
+		return -EINVAL;
+
+	if (X86_MODRM_MOD(insn->modrm.value) > 2)
+		return -EINVAL;
+
+	ret = get_reg_offset_16(insn, regs, &addr_offset1,
+				&addr_offset2);
+	if (ret < 0)
+		return -EINVAL;
+
+	/*
+	 * Don't fail on invalid offset values. They might be invalid because
+	 * they cannot be used for this particular value of ModRM. Instead, use
+	 * them in the computation only if they contain a valid value.
+	 */
+	if (addr_offset1 != -EDOM)
+		addr1 = (short)(0xffff & regs_get_register(regs, addr_offset1));
+
+	if (addr_offset2 != -EDOM)
+		addr2 = (short)(0xffff & regs_get_register(regs, addr_offset2));
+
+	*eff_addr = addr1 + addr2 + (short)(insn->displacement.value & 0xffff);
+
+	/*
+	 * The first operand register could indicate to use of either SS or DS
+	 * registers to obtain the segment selector.  The second operand
+	 * register can only indicate the use of DS. Thus, the first operand
+	 * will be used to obtain the segment selector.
+	 */
+	*regoff = addr_offset1;
+
+	return 0;
+}
+
+/**
  * get_eff_addr_sib() - Obtain referenced effective address via SIB
  * @insn:	Instruction. Must be valid.
  * @regs:	Register values as seen when entering kernel mode
@@ -976,6 +1120,71 @@ static int get_eff_addr_sib(struct insn *insn, struct pt_regs *regs,
 }
 
 /**
+ * get_addr_ref_16() - Obtain the 16-bit address referred by instruction
+ * @insn:	Instruction containing ModRM byte and displacement
+ * @regs:	Register values as seen when entering kernel mode
+ *
+ * This function is to be used with 16-bit address encodings. Obtain the memory
+ * address referred by the instruction's ModRM and displacement bytes. Also, the
+ * segment used as base is determined by either any segment override prefixes in
+ * @insn or the default segment of the registers involved in the address
+ * computation. In protected mode, segment limits are enforced.
+ *
+ * Returns:
+ *
+ * Linear address referenced by the instruction operands on success.
+ *
+ * -1L on error.
+ */
+static void __user *get_addr_ref_16(struct insn *insn, struct pt_regs *regs)
+{
+	unsigned long linear_addr = -1L, seg_base, seg_limit;
+	int ret, regoff;
+	short eff_addr;
+	long tmp;
+
+	insn_get_modrm(insn);
+	insn_get_displacement(insn);
+
+	if (insn->addr_bytes != 2)
+		goto out;
+
+	if (X86_MODRM_MOD(insn->modrm.value) == 3) {
+		ret = get_eff_addr_reg(insn, regs, &regoff, &tmp);
+		if (ret)
+			goto out;
+
+		eff_addr = (short)tmp;
+	} else {
+		ret = get_eff_addr_modrm_16(insn, regs, &regoff, &eff_addr);
+		if (ret)
+			goto out;
+	}
+
+	ret = get_seg_base_limit(insn, regs, regoff, &seg_base, &seg_limit);
+	if (ret)
+		goto out;
+
+	/*
+	 * Before computing the linear address, make sure the effective address
+	 * is within the limits of the segment. In virtual-8086 mode, segment
+	 * limits are not enforced. In such a case, the segment limit is -1L to
+	 * reflect this fact.
+	 */
+	if ((unsigned long)(eff_addr & 0xffff) > seg_limit)
+		goto out;
+
+	linear_addr = (unsigned long)(eff_addr & 0xffff) + seg_base;
+
+	/* Limit linear address to 20 bits */
+	if (v8086_mode(regs))
+		linear_addr &= 0xfffff;
+
+out:
+	return (void __user *)linear_addr;
+}
+
+/**
  * get_addr_ref_32() - Obtain a 32-bit linear address
  * @insn:	Instruction with ModRM, SIB bytes and displacement
  * @regs:	Register values as seen when entering kernel mode
@@ -1146,6 +1355,8 @@ void __user *insn_get_addr_ref(struct insn *insn, struct pt_regs *regs)
 		return (void __user *)-1L;
 
 	switch (insn->addr_bytes) {
+	case 2:
+		return get_addr_ref_16(insn, regs);
 	case 4:
 		return get_addr_ref_32(insn, regs);
 	case 8:
-- 
2.7.4