[PATCH v7 18/26] x86/insn-eval: Add support to resolve 16-bit addressing encodings

[Ricardo Neri]

Tasks running in virtual-8086 mode or in protected mode with code
segment descriptors that specify 16-bit default address sizes via the
D bit 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. 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.

A couple of 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_addr_ref_16() computes the linear
address indicated by the instructions using the value of the registers
given by ModRM as well as the base address of the segment.

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 | 155 +++++++++++++++++++++++++++++++++++++++++++++++
 1 file changed, 155 insertions(+)

diff --git a/arch/x86/lib/insn-eval.c b/arch/x86/lib/insn-eval.c
index 9822061..928a662 100644
--- a/arch/x86/lib/insn-eval.c
+++ b/arch/x86/lib/insn-eval.c
@@ -431,6 +431,73 @@ 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 structure containing ModRM and SiB bytes
+ * @regs:	Structure with 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
+ * within 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.
+ *
+ * Return: 0 on success, -EINVAL on failure.
+ */
+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 */
+	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 no displacement is indicated in the mod part of the ModRM byte,
+	 * (mod part is 0) and the r/m part of the same byte is 6, no register
+	 * is used caculate the operand address. An r/m part of 6 means that
+	 * the second register offset is already invalid.
+	 */
+	if ((X86_MODRM_MOD(insn->modrm.value) == 0) &&
+	    (X86_MODRM_RM(insn->modrm.value) == 6))
+		*offs1 = -EDOM;
+
+	return 0;
+}
+
+/**
  * get_desc() - Obtain address of segment descriptor
  * @sel:	Segment selector
  *
@@ -689,6 +756,94 @@ int insn_get_modrm_rm_off(struct insn *insn, struct pt_regs *regs)
 }
 
 /**
+ * get_addr_ref_16() - Obtain the 16-bit address referred by instruction
+ * @insn:	Instruction structure containing ModRM byte and displacement
+ * @regs:	Structure with 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 bytes and displacement. 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.
+ *
+ * Return: linear address referenced by instruction and registers on success.
+ * -1L on failure.
+ */
+static void __user *get_addr_ref_16(struct insn *insn, struct pt_regs *regs)
+{
+	unsigned long linear_addr, seg_base_addr, seg_limit;
+	short eff_addr, addr1 = 0, addr2 = 0;
+	int addr_offset1, addr_offset2;
+	int ret;
+
+	insn_get_modrm(insn);
+	insn_get_displacement(insn);
+
+	/*
+	 * If operand is a register, the layout is the same as in
+	 * 32-bit and 64-bit addressing.
+	 */
+	if (X86_MODRM_MOD(insn->modrm.value) == 3) {
+		addr_offset1 = get_reg_offset(insn, regs, REG_TYPE_RM);
+		if (addr_offset1 < 0)
+			goto out_err;
+		eff_addr = regs_get_register(regs, addr_offset1);
+		seg_base_addr = insn_get_seg_base(regs, insn, addr_offset1);
+		if (seg_base_addr == -1L)
+			goto out_err;
+		seg_limit = get_seg_limit(regs, insn, addr_offset1);
+	} else {
+		ret = get_reg_offset_16(insn, regs, &addr_offset1,
+					&addr_offset2);
+		if (ret < 0)
+			goto out_err;
+		/*
+		 * Don't fail on invalid offset values. They might be invalid
+		 * because they cannot be used for this particular value of
+		 * the ModRM. Instead, use them in the computation only if
+		 * they contain a valid value.
+		 */
+		if (addr_offset1 != -EDOM)
+			addr1 = 0xffff & regs_get_register(regs, addr_offset1);
+		if (addr_offset2 != -EDOM)
+			addr2 = 0xffff & regs_get_register(regs, addr_offset2);
+		eff_addr = addr1 + addr2;
+		/*
+		 * The first register is in the operand implies the SS or DS
+		 * segment selectors, the second register in the operand can
+		 * only imply DS. Thus, use the first register to obtain
+		 * the segment selector.
+		 */
+		seg_base_addr = insn_get_seg_base(regs, insn, addr_offset1);
+		if (seg_base_addr == -1L)
+			goto out_err;
+		seg_limit = get_seg_limit(regs, insn, addr_offset1);
+
+		eff_addr += (insn->displacement.value & 0xffff);
+	}
+
+	linear_addr = (unsigned long)(eff_addr & 0xffff);
+
+	/*
+	 * Make sure the effective address is within the limits of the
+	 * segment. In long mode, the limit is -1L. Thus, the second part
+	 * of the check always succeeds.
+	 */
+	if (linear_addr > seg_limit)
+		goto out_err;
+
+	linear_addr += seg_base_addr;
+
+	/* Limit linear address to 20 bits */
+	if (v8086_mode(regs))
+		linear_addr &= 0xfffff;
+
+	return (void __user *)linear_addr;
+out_err:
+	return (void __user *)-1;
+}
+
+/**
  * _to_signed_long() - Cast an unsigned long into signed long
  * @val		A 32-bit or 64-bit unsigned long
  * @long_bytes	The number of bytes used to represent a long number
-- 
2.9.3