[PATCH v9 19/29] x86/insn-eval: Add support to resolve 32-bit address encodings

[Ricardo Neri <ricardo.neri-calderon@linux.intel.com>]

32-bit and 64-bit address encodings are identical. Thus, the same logic
could be used to resolve the effective address. However, there are two key
differences: address size and enforcement of segment limits.

If running a 32-bit process on a 64-bit kernel, it is best to perform
the address calculation using 32-bit data types. In this manner hardware
is used for the arithmetic, including handling of signs and overflows.

32-bit addresses are generally used in protected mode; segment limits are
enforced in this mode. This implementation obtains the limit of the
segment associated with the instruction operands and prefixes. If the
computed address is outside the segment limits, an error is returned. It
is also possible to use 32-bit address in long mode and virtual-8086 mode
by using an address override prefix. In such cases, segment limits are not
enforced.

The new function get_addr_ref_32() is almost identical to the existing
function insn_get_addr_ref() (used for 64-bit addresses); except for the
differences mentioned above. For the sake of simplicity and readability,
it is better to use two separate functions.

Cc: Dave Hansen <dave.hansen@linux.intel.com>
Cc: Adam Buchbinder <adam.buchbinder@gmail.com>
Cc: Colin Ian King <colin.king@canonical.com>
Cc: Lorenzo Stoakes <lstoakes@gmail.com>
Cc: Qiaowei Ren <qiaowei.ren@intel.com>
Cc: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Masami Hiramatsu <mhiramat@kernel.org>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Kees Cook <keescook@chromium.org>
Cc: Thomas Garnier <thgarnie@google.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Borislav Petkov <bp@suse.de>
Cc: Dmitry Vyukov <dvyukov@google.com>
Cc: Ravi V. Shankar <ravi.v.shankar@intel.com>
Cc: x86@kernel.org
Signed-off-by: Ricardo Neri <ricardo.neri-calderon@linux.intel.com>
---
 arch/x86/lib/insn-eval.c | 160 +++++++++++++++++++++++++++++++++++++++++++++++
 1 file changed, 160 insertions(+)

diff --git a/arch/x86/lib/insn-eval.c b/arch/x86/lib/insn-eval.c
index b3aa891..945c9b7 100644
--- a/arch/x86/lib/insn-eval.c
+++ b/arch/x86/lib/insn-eval.c
@@ -712,6 +712,166 @@ int insn_get_modrm_rm_off(struct insn *insn, struct pt_regs *regs)
 	return get_reg_offset(insn, regs, REG_TYPE_RM);
 }
 
+/**
+ * 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
+ *
+ * This function is to be used with 32-bit address encodings to obtain the
+ * linear memory address referred by the instruction's ModRM, SIB,
+ * displacement bytes and segment base address, as applicable. If in protected
+ * mode, segment limits are enforced.
+ *
+ * Returns:
+ *
+ * Linear address referenced by instruction and registers on success.
+ *
+ * -1L on error.
+ */
+static void __user *get_addr_ref_32(struct insn *insn, struct pt_regs *regs)
+{
+	int eff_addr, base, indx, addr_offset, base_offset, indx_offset;
+	unsigned long linear_addr = -1L, seg_base_addr, seg_limit, tmp;
+	int seg_reg_indx;
+	insn_byte_t sib;
+
+	insn_get_modrm(insn);
+	insn_get_sib(insn);
+	sib = insn->sib.value;
+
+	if (insn->addr_bytes != 4)
+		goto out;
+
+	if (X86_MODRM_MOD(insn->modrm.value) == 3) {
+		addr_offset = get_reg_offset(insn, regs, REG_TYPE_RM);
+		if (addr_offset < 0)
+			goto out;
+
+		tmp = regs_get_register(regs, addr_offset);
+		/* The 4 most significant bytes must be zero. */
+		if (tmp & ~0xffffffffL)
+			goto out;
+
+		eff_addr = (int)(tmp & 0xffffffff);
+
+		seg_reg_indx = resolve_seg_reg(insn, regs, addr_offset);
+		if (seg_reg_indx < 0)
+			goto out;
+
+		seg_base_addr = insn_get_seg_base(regs, seg_reg_indx);
+		if (seg_base_addr == -1L)
+			goto out;
+
+		seg_limit = get_seg_limit(regs, seg_reg_indx);
+	} else {
+		if (insn->sib.nbytes) {
+			/*
+			 * Negative values in the base and index offset means
+			 * an error when decoding the SIB byte. Except -EDOM,
+			 * which means that the registers should not be used
+			 * in the address computation.
+			 */
+			base_offset = get_reg_offset(insn, regs, REG_TYPE_BASE);
+			if (base_offset == -EDOM) {
+				base = 0;
+			} else if (base_offset < 0) {
+				goto out;
+			} else {
+				tmp = regs_get_register(regs, base_offset);
+				/* The 4 most significant bytes must be zero. */
+				if (tmp & ~0xffffffffL)
+					goto out;
+
+				base = (int)(tmp & 0xffffffff);
+			}
+
+			indx_offset = get_reg_offset(insn, regs, REG_TYPE_INDEX);
+			if (indx_offset == -EDOM) {
+				indx = 0;
+			} else if (indx_offset < 0) {
+				goto out;
+			} else {
+				tmp = regs_get_register(regs, indx_offset);
+				/* The 4 most significant bytes must be zero. */
+				if (tmp & ~0xffffffffL)
+					goto out;
+
+				indx = (int)(tmp & 0xffffffff);
+			}
+
+			eff_addr = base + indx * (1 << X86_SIB_SCALE(sib));
+
+			seg_reg_indx = resolve_seg_reg(insn, regs, base_offset);
+			if (seg_reg_indx < 0)
+				goto out;
+
+			seg_base_addr = insn_get_seg_base(regs, seg_reg_indx);
+			if (seg_base_addr == -1L)
+				goto out;
+
+			seg_limit = get_seg_limit(regs, seg_reg_indx);
+		} else {
+			addr_offset = get_reg_offset(insn, regs, REG_TYPE_RM);
+
+			/*
+			 * -EDOM means that we must ignore the address_offset.
+			 * In such a case, in 64-bit mode the effective address
+			 * relative to the RIP of the following instruction.
+			 */
+			if (addr_offset == -EDOM) {
+				if (user_64bit_mode(regs))
+					eff_addr = (long)regs->ip + insn->length;
+				else
+					eff_addr = 0;
+			} else if (addr_offset < 0) {
+				goto out;
+			} else {
+				tmp = regs_get_register(regs, addr_offset);
+				/* The 4 most significant bytes must be zero. */
+				if (tmp & ~0xffffffffL)
+					goto out;
+
+				eff_addr = (int)(tmp & 0xffffffff);
+			}
+
+			seg_reg_indx = resolve_seg_reg(insn, regs, addr_offset);
+			if (seg_reg_indx < 0)
+				goto out;
+
+			seg_base_addr = insn_get_seg_base(regs, seg_reg_indx);
+			if (seg_base_addr == -1L)
+				goto out;
+
+			seg_limit = get_seg_limit(regs, seg_reg_indx);
+		}
+		eff_addr += insn->displacement.value;
+	}
+
+	/*
+	 * In protected mode, before computing the linear address, make sure
+	 * the effective address is within the limits of the segment.
+	 * 32-bit addresses can be used in long and virtual-8086 modes if an
+	 * address override prefix is used. In such cases, segment limits are
+	 * not enforced. When in virtual-8086 mode, the segment limit is -1L
+	 * to reflect this situation.
+	 *
+	 * After computed, the effective address is treated as an unsigned
+	 * quantity.
+	 */
+	if (!user_64bit_mode(regs) && ((unsigned int)eff_addr > seg_limit))
+		goto out;
+
+	/*
+	 * Data type long could be 64 bits in size. Ensure that our 32-bit
+	 * effective address is not sign-extended when computing the linear
+	 * address.
+	 */
+	linear_addr = (unsigned long)(eff_addr & 0xffffffff) + seg_base_addr;
+
+out:
+	return (void __user *)linear_addr;
+}
+
 /*
  * return the address being referenced be instruction
  * for rm=3 returning the content of the rm reg
-- 
2.7.4