[v6 PATCH 11/21] insn/eval: Incorporate segment base in 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. Furthermore, the segment descriptor to use depends on the
register that is used as the base of the effective address. The effective
base address varies depending on whether the operand is a register or a
memory address and on whether a SiB byte is used.

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 saved in a separate variable and added to the final 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 | 10 ++++++++--
 1 file changed, 8 insertions(+), 2 deletions(-)

diff --git a/arch/x86/lib/insn-eval.c b/arch/x86/lib/insn-eval.c
index ea10b03..edb360f 100644
--- a/arch/x86/lib/insn-eval.c
+++ b/arch/x86/lib/insn-eval.c
@@ -566,7 +566,7 @@ int insn_get_reg_offset_sib_index(struct insn *insn, struct pt_regs *regs)
  */
 void __user *insn_get_addr_ref(struct insn *insn, struct pt_regs *regs)
 {
-	unsigned long linear_addr;
+	unsigned long linear_addr, seg_base_addr;
 	long eff_addr, base, indx;
 	int addr_offset, base_offset, indx_offset;
 	insn_byte_t sib;
@@ -580,6 +580,8 @@ void __user *insn_get_addr_ref(struct insn *insn, struct pt_regs *regs)
 		if (addr_offset < 0)
 			goto out_err;
 		eff_addr = regs_get_register(regs, addr_offset);
+		seg_base_addr = insn_get_seg_base(regs, insn, addr_offset,
+						  false);
 	} else {
 		if (insn->sib.nbytes) {
 			/*
@@ -605,6 +607,8 @@ 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));
+			seg_base_addr = insn_get_seg_base(regs, insn,
+							  base_offset, false);
 		} else {
 			addr_offset = get_reg_offset(insn, regs, REG_TYPE_RM);
 			/* -EDOM means that we must ignore the address_offset.
@@ -623,10 +627,12 @@ void __user *insn_get_addr_ref(struct insn *insn, struct pt_regs *regs)
 			} else {
 				eff_addr = regs_get_register(regs, addr_offset);
 			}
+			seg_base_addr = insn_get_seg_base(regs, insn,
+							  addr_offset, false);
 		}
 		eff_addr += insn->displacement.value;
 	}
-	linear_addr = (unsigned long)eff_addr;
+	linear_addr = (unsigned long)eff_addr + seg_base_addr;
 
 	return (void __user *)linear_addr;
 out_err:
-- 
2.9.3