[v5 04/20] x86/mpx, x86/insn: Relocate insn util functions to a new insn-kernel

[Ricardo Neri]

Other kernel submodules can benefit from using the utility functions
defined in mpx.c to obtain the addresses and values of operands contained
in the general purpose registers. An instance of this is the emulation code
used for instructions protected by the Intel User-Mode Instruction
Prevention feature.

Thus, these functions are relocated to a new insn-eval.c file. The reason
to not relocate these utilities into insn.c is that the latter solely
analyses instructions given by a struct insn without any knowledge of the
meaning of the values of instruction operands. This new utility insn-
eval.c aims to be used to resolve effective and userspace linear addresses
based on the contents of the instruction operands as well as the contents
of pt_regs structure.

These utilities come with a separate header. This is to avoid taking insn.c
out of sync from the instructions decoders under tools/obj and tools/perf.
This also avoids adding cumbersome #ifdef's for the #include'd files
required to decode instructions in a kernel context.

Functions are simply relocated. There are not functional or indentation
changes.

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/include/asm/insn-eval.h |  16 ++++
 arch/x86/lib/Makefile            |   2 +-
 arch/x86/lib/insn-eval.c         | 160 +++++++++++++++++++++++++++++++++++++++
 arch/x86/mm/mpx.c                | 153 +------------------------------------
 4 files changed, 179 insertions(+), 152 deletions(-)
 create mode 100644 arch/x86/include/asm/insn-eval.h
 create mode 100644 arch/x86/lib/insn-eval.c

diff --git a/arch/x86/include/asm/insn-eval.h b/arch/x86/include/asm/insn-eval.h
new file mode 100644
index 0000000..5cab1b1
--- /dev/null
+++ b/arch/x86/include/asm/insn-eval.h
@@ -0,0 +1,16 @@
+#ifndef _ASM_X86_INSN_EVAL_H
+#define _ASM_X86_INSN_EVAL_H
+/*
+ * A collection of utility functions for x86 instruction analysis to be
+ * used in a kernel context. Useful when, for instance, making sense
+ * of the registers indicated by operands.
+ */
+
+#include <linux/compiler.h>
+#include <linux/bug.h>
+#include <linux/err.h>
+#include <asm/ptrace.h>
+
+void __user *insn_get_addr_ref(struct insn *insn, struct pt_regs *regs);
+
+#endif /* _ASM_X86_INSN_EVAL_H */
diff --git a/arch/x86/lib/Makefile b/arch/x86/lib/Makefile
index 34a7413..675d7b0 100644
--- a/arch/x86/lib/Makefile
+++ b/arch/x86/lib/Makefile
@@ -23,7 +23,7 @@ lib-y := delay.o misc.o cmdline.o cpu.o
 lib-y += usercopy_$(BITS).o usercopy.o getuser.o putuser.o
 lib-y += memcpy_$(BITS).o
 lib-$(CONFIG_RWSEM_XCHGADD_ALGORITHM) += rwsem.o
-lib-$(CONFIG_INSTRUCTION_DECODER) += insn.o inat.o
+lib-$(CONFIG_INSTRUCTION_DECODER) += insn.o inat.o insn-eval.o
 lib-$(CONFIG_RANDOMIZE_BASE) += kaslr.o
 
 obj-y += msr.o msr-reg.o msr-reg-export.o hweight.o
diff --git a/arch/x86/lib/insn-eval.c b/arch/x86/lib/insn-eval.c
new file mode 100644
index 0000000..23cf010
--- /dev/null
+++ b/arch/x86/lib/insn-eval.c
@@ -0,0 +1,160 @@
+/*
+ * Utility functions for x86 operand and address decoding
+ *
+ * Copyright (C) Intel Corporation 2017
+ */
+#include <linux/kernel.h>
+#include <linux/string.h>
+#include <asm/inat.h>
+#include <asm/insn.h>
+#include <asm/insn-eval.h>
+
+enum reg_type {
+	REG_TYPE_RM = 0,
+	REG_TYPE_INDEX,
+	REG_TYPE_BASE,
+};
+
+static int get_reg_offset(struct insn *insn, struct pt_regs *regs,
+			  enum reg_type type)
+{
+	int regno = 0;
+
+	static const int regoff[] = {
+		offsetof(struct pt_regs, ax),
+		offsetof(struct pt_regs, cx),
+		offsetof(struct pt_regs, dx),
+		offsetof(struct pt_regs, bx),
+		offsetof(struct pt_regs, sp),
+		offsetof(struct pt_regs, bp),
+		offsetof(struct pt_regs, si),
+		offsetof(struct pt_regs, di),
+#ifdef CONFIG_X86_64
+		offsetof(struct pt_regs, r8),
+		offsetof(struct pt_regs, r9),
+		offsetof(struct pt_regs, r10),
+		offsetof(struct pt_regs, r11),
+		offsetof(struct pt_regs, r12),
+		offsetof(struct pt_regs, r13),
+		offsetof(struct pt_regs, r14),
+		offsetof(struct pt_regs, r15),
+#endif
+	};
+	int nr_registers = ARRAY_SIZE(regoff);
+	/*
+	 * Don't possibly decode a 32-bit instructions as
+	 * reading a 64-bit-only register.
+	 */
+	if (IS_ENABLED(CONFIG_X86_64) && !insn->x86_64)
+		nr_registers -= 8;
+
+	switch (type) {
+	case REG_TYPE_RM:
+		regno = X86_MODRM_RM(insn->modrm.value);
+		if (X86_REX_B(insn->rex_prefix.value))
+			regno += 8;
+		break;
+
+	case REG_TYPE_INDEX:
+		regno = X86_SIB_INDEX(insn->sib.value);
+		if (X86_REX_X(insn->rex_prefix.value))
+			regno += 8;
+		/*
+		 * If mod !=3, register R/ESP (regno=4) is not used as index in
+		 * the address computation. Check is done after looking at REX.X
+		 * This is because R12 (regno=12) can be used as an index.
+		 */
+		if (regno == 4 && X86_MODRM_MOD(insn->modrm.value) != 3)
+			return -EDOM;
+		break;
+
+	case REG_TYPE_BASE:
+		regno = X86_SIB_BASE(insn->sib.value);
+		/*
+		 * If mod is 0 and register R/EBP (regno=5) is indicated in the
+		 * base part of the SIB byte, the value of such register should
+		 * not be used in the address computation. Also, a 32-bit
+		 * displacement is expected in this case; the instruction
+		 * decoder takes care of it. This is true for both R13 and
+		 * R/EBP as REX.B will not be decoded.
+		 */
+		if (regno == 5 && X86_MODRM_MOD(insn->modrm.value) == 0)
+			return -EDOM;
+
+		if (X86_REX_B(insn->rex_prefix.value))
+			regno += 8;
+		break;
+
+	default:
+		pr_err("invalid register type");
+		BUG();
+		break;
+	}
+
+	if (regno >= nr_registers) {
+		WARN_ONCE(1, "decoded an instruction with an invalid register");
+		return -EINVAL;
+	}
+	return regoff[regno];
+}
+
+/*
+ * return the address being referenced be instruction
+ * for rm=3 returning the content of the rm reg
+ * for rm!=3 calculates the address using SIB and Disp
+ */
+void __user *insn_get_addr_ref(struct insn *insn, struct pt_regs *regs)
+{
+	unsigned long linear_addr;
+	long eff_addr, base, indx;
+	int addr_offset, base_offset, indx_offset;
+	insn_byte_t sib;
+
+	insn_get_modrm(insn);
+	insn_get_sib(insn);
+	sib = insn->sib.value;
+
+	if (X86_MODRM_MOD(insn->modrm.value) == 3) {
+		addr_offset = get_reg_offset(insn, regs, REG_TYPE_RM);
+		if (addr_offset < 0)
+			goto out_err;
+		eff_addr = regs_get_register(regs, addr_offset);
+	} 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 (unlikely(base_offset == -EDOM))
+				base = 0;
+			else if (unlikely(base_offset < 0))
+				goto out_err;
+			else
+				base = regs_get_register(regs, base_offset);
+
+			indx_offset = get_reg_offset(insn, regs, REG_TYPE_INDEX);
+			if (unlikely(indx_offset == -EDOM))
+				indx = 0;
+			else if (unlikely(indx_offset < 0))
+				goto out_err;
+			else
+				indx = regs_get_register(regs, indx_offset);
+
+			eff_addr = base + indx * (1 << X86_SIB_SCALE(sib));
+		} else {
+			addr_offset = get_reg_offset(insn, regs, REG_TYPE_RM);
+			if (addr_offset < 0)
+				goto out_err;
+			eff_addr = regs_get_register(regs, addr_offset);
+		}
+		eff_addr += insn->displacement.value;
+	}
+	linear_addr = (unsigned long)eff_addr;
+
+	return (void __user *)linear_addr;
+out_err:
+	return (void __user *)-1;
+}
diff --git a/arch/x86/mm/mpx.c b/arch/x86/mm/mpx.c
index ef7eb67..4c3efd6 100644
--- a/arch/x86/mm/mpx.c
+++ b/arch/x86/mm/mpx.c
@@ -12,6 +12,7 @@
 #include <linux/sched/sysctl.h>
 
 #include <asm/insn.h>
+#include <asm/insn-eval.h>
 #include <asm/mman.h>
 #include <asm/mmu_context.h>
 #include <asm/mpx.h>
@@ -60,156 +61,6 @@ static unsigned long mpx_mmap(unsigned long len)
 	return addr;
 }
 
-enum reg_type {
-	REG_TYPE_RM = 0,
-	REG_TYPE_INDEX,
-	REG_TYPE_BASE,
-};
-
-static int get_reg_offset(struct insn *insn, struct pt_regs *regs,
-			  enum reg_type type)
-{
-	int regno = 0;
-
-	static const int regoff[] = {
-		offsetof(struct pt_regs, ax),
-		offsetof(struct pt_regs, cx),
-		offsetof(struct pt_regs, dx),
-		offsetof(struct pt_regs, bx),
-		offsetof(struct pt_regs, sp),
-		offsetof(struct pt_regs, bp),
-		offsetof(struct pt_regs, si),
-		offsetof(struct pt_regs, di),
-#ifdef CONFIG_X86_64
-		offsetof(struct pt_regs, r8),
-		offsetof(struct pt_regs, r9),
-		offsetof(struct pt_regs, r10),
-		offsetof(struct pt_regs, r11),
-		offsetof(struct pt_regs, r12),
-		offsetof(struct pt_regs, r13),
-		offsetof(struct pt_regs, r14),
-		offsetof(struct pt_regs, r15),
-#endif
-	};
-	int nr_registers = ARRAY_SIZE(regoff);
-	/*
-	 * Don't possibly decode a 32-bit instructions as
-	 * reading a 64-bit-only register.
-	 */
-	if (IS_ENABLED(CONFIG_X86_64) && !insn->x86_64)
-		nr_registers -= 8;
-
-	switch (type) {
-	case REG_TYPE_RM:
-		regno = X86_MODRM_RM(insn->modrm.value);
-		if (X86_REX_B(insn->rex_prefix.value))
-			regno += 8;
-		break;
-
-	case REG_TYPE_INDEX:
-		regno = X86_SIB_INDEX(insn->sib.value);
-		if (X86_REX_X(insn->rex_prefix.value))
-			regno += 8;
-		/*
-		 * If mod !=3, register R/ESP (regno=4) is not used as index in
-		 * the address computation. Check is done after looking at REX.X
-		 * This is because R12 (regno=12) can be used as an index.
-		 */
-		if (regno == 4 && X86_MODRM_MOD(insn->modrm.value) != 3)
-			return -EDOM;
-		break;
-
-	case REG_TYPE_BASE:
-		regno = X86_SIB_BASE(insn->sib.value);
-		/*
-		 * If mod is 0 and register R/EBP (regno=5) is indicated in the
-		 * base part of the SIB byte, the value of such register should
-		 * not be used in the address computation. Also, a 32-bit
-		 * displacement is expected in this case; the instruction
-		 * decoder takes care of it. This is true for both R13 and
-		 * R/EBP as REX.B will not be decoded.
-		 */
-		if (regno == 5 && X86_MODRM_MOD(insn->modrm.value) == 0)
-			return -EDOM;
-
-		if (X86_REX_B(insn->rex_prefix.value))
-			regno += 8;
-		break;
-
-	default:
-		pr_err("invalid register type");
-		BUG();
-		break;
-	}
-
-	if (regno >= nr_registers) {
-		WARN_ONCE(1, "decoded an instruction with an invalid register");
-		return -EINVAL;
-	}
-	return regoff[regno];
-}
-
-/*
- * return the address being referenced be instruction
- * for rm=3 returning the content of the rm reg
- * for rm!=3 calculates the address using SIB and Disp
- */
-static void __user *mpx_get_addr_ref(struct insn *insn, struct pt_regs *regs)
-{
-	unsigned long linear_addr;
-	long eff_addr, base, indx;
-	int addr_offset, base_offset, indx_offset;
-	insn_byte_t sib;
-
-	insn_get_modrm(insn);
-	insn_get_sib(insn);
-	sib = insn->sib.value;
-
-	if (X86_MODRM_MOD(insn->modrm.value) == 3) {
-		addr_offset = get_reg_offset(insn, regs, REG_TYPE_RM);
-		if (addr_offset < 0)
-			goto out_err;
-		eff_addr = regs_get_register(regs, addr_offset);
-	} 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 (unlikely(base_offset == -EDOM))
-				base = 0;
-			else if (unlikely(base_offset < 0))
-				goto out_err;
-			else
-				base = regs_get_register(regs, base_offset);
-
-			indx_offset = get_reg_offset(insn, regs, REG_TYPE_INDEX);
-			if (unlikely(indx_offset == -EDOM))
-				indx = 0;
-			else if (unlikely(indx_offset < 0))
-				goto out_err;
-			else
-				indx = regs_get_register(regs, indx_offset);
-
-			eff_addr = base + indx * (1 << X86_SIB_SCALE(sib));
-		} else {
-			addr_offset = get_reg_offset(insn, regs, REG_TYPE_RM);
-			if (addr_offset < 0)
-				goto out_err;
-			eff_addr = regs_get_register(regs, addr_offset);
-		}
-		eff_addr += insn->displacement.value;
-	}
-	linear_addr = (unsigned long)eff_addr;
-
-	return (void __user *)linear_addr;
-out_err:
-	return (void __user *)-1;
-}
-
 static int mpx_insn_decode(struct insn *insn,
 			   struct pt_regs *regs)
 {
@@ -322,7 +173,7 @@ siginfo_t *mpx_generate_siginfo(struct pt_regs *regs)
 	info->si_signo = SIGSEGV;
 	info->si_errno = 0;
 	info->si_code = SEGV_BNDERR;
-	info->si_addr = mpx_get_addr_ref(&insn, regs);
+	info->si_addr = insn_get_addr_ref(&insn, regs);
 	/*
 	 * We were not able to extract an address from the instruction,
 	 * probably because there was something invalid in it.
-- 
2.9.3