[PATCH v10 18/18] x86/insn-eval: Incorporate segment base in linear address computation

[Ricardo Neri]

insn_get_addr_ref() returns the effective address as defined by the
section 3.7.5.1 Vol 1 of the Intel 64 and IA-32 Architectures Software
Developer's Manual. In order to compute the linear address, we must add
to the effective address the segment base address as set in the segment
descriptor. The segment descriptor to use depends on the register used as
operand and segment override prefixes, if any.

In most cases, the segment base address will be 0 if the USER_DS/USER32_DS
segment is used or if segmentation is not used. However, the base address
is not necessarily zero if a user programs defines its own segments. This
is possible by using a local descriptor table.

Since the effective address is a signed quantity, the unsigned segment
base address is saved in a separate variable and added to the final,
unsigned, effective address.

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 | 55 +++++++++++++++++++++++++++++++++++++++++++++---
 1 file changed, 52 insertions(+), 3 deletions(-)

diff --git a/arch/x86/lib/insn-eval.c b/arch/x86/lib/insn-eval.c
index 6bf819f..1c23ec0 100644
--- a/arch/x86/lib/insn-eval.c
+++ b/arch/x86/lib/insn-eval.c
@@ -728,6 +728,43 @@ int insn_get_modrm_rm_off(struct insn *insn, struct pt_regs *regs)
 	return get_reg_offset(insn, regs, REG_TYPE_RM);
 }
 
+/**
+ * get_seg_base_addr() - obtain base address of a segment
+ * @insn:	Instruction. Must be valid.
+ * @regs:	Register values as seen when entering kernel mode
+ * @regoff:	Operand offset, in pt_regs, used to resolve segment descriptor
+ * @base:	Obtained segment base
+ *
+ * Obtain the base address of the segment associated with the operand @regoff
+ * and, if any or allowed, override prefixes in @insn. This function is
+ * different from insn_get_seg_base() as the latter does not resolve the segment
+ * associated with the instruction operand.
+ *
+ * Returns:
+ *
+ * 0 on success. @base will contain the base address of the resolved segment.
+ *
+ * -EINVAL on error.
+ */
+static int get_seg_base_addr(struct insn *insn, struct pt_regs *regs,
+			     int regoff, unsigned long *base)
+{
+	int seg_reg_idx;
+
+	if (!base)
+		return -EINVAL;
+
+	seg_reg_idx = resolve_seg_reg(insn, regs, regoff);
+	if (seg_reg_idx < 0)
+		return seg_reg_idx;
+
+	*base = insn_get_seg_base(regs, seg_reg_idx);
+	if (*base == -1L)
+		return -EINVAL;
+
+	return 0;
+}
+
 /*
  * return the address being referenced be instruction
  * for rm=3 returning the content of the rm reg
@@ -735,8 +772,8 @@ int insn_get_modrm_rm_off(struct insn *insn, struct pt_regs *regs)
  */
 void __user *insn_get_addr_ref(struct insn *insn, struct pt_regs *regs)
 {
-	int addr_offset, base_offset, indx_offset;
-	unsigned long linear_addr = -1L;
+	int addr_offset, base_offset, indx_offset, ret;
+	unsigned long linear_addr = -1L, seg_base;
 	long eff_addr, base, indx;
 	insn_byte_t sib;
 
@@ -750,6 +787,7 @@ void __user *insn_get_addr_ref(struct insn *insn, struct pt_regs *regs)
 			goto out;
 
 		eff_addr = regs_get_register(regs, addr_offset);
+
 	} else {
 		if (insn->sib.nbytes) {
 			/*
@@ -776,6 +814,13 @@ void __user *insn_get_addr_ref(struct insn *insn, struct pt_regs *regs)
 				indx = regs_get_register(regs, indx_offset);
 
 			eff_addr = base + indx * (1 << X86_SIB_SCALE(sib));
+
+			/*
+			 * The base determines the segment used to compute
+			 * the linear address.
+			 */
+			addr_offset = base_offset;
+
 		} else {
 			addr_offset = get_reg_offset(insn, regs, REG_TYPE_RM);
 			/*
@@ -798,7 +843,11 @@ void __user *insn_get_addr_ref(struct insn *insn, struct pt_regs *regs)
 		eff_addr += insn->displacement.value;
 	}
 
-	linear_addr = (unsigned long)eff_addr;
+	ret = get_seg_base_addr(insn, regs, addr_offset, &seg_base);
+	if (ret)
+		goto out;
+
+	linear_addr = (unsigned long)eff_addr + seg_base;
 
 out:
 	return (void __user *)linear_addr;
-- 
2.7.4