Merge branch 'x86/mpx' into x86/asm, to pick up dependent commits

The UMIP series is based on top of changes already queued up in the x86/mpx branch,
so merge it.

Signed-off-by: Ingo Molnar <mingo@kernel.org>

6 files changed, 910 insertions, 125 deletions

diff --git a/arch/x86/include/asm/inat.h b/arch/x86/include/asm/inat.h
index 02aff0867211..1c78580e58be 100644
--- a/arch/x86/include/asm/inat.h
+++ b/arch/x86/include/asm/inat.h
@@ -97,6 +97,16 @@
 #define INAT_MAKE_GROUP(grp)	((grp << INAT_GRP_OFFS) | INAT_MODRM)
 #define INAT_MAKE_IMM(imm)	(imm << INAT_IMM_OFFS)
 
+/* Identifiers for segment registers */
+#define INAT_SEG_REG_IGNORE	0
+#define INAT_SEG_REG_DEFAULT	1
+#define INAT_SEG_REG_CS		2
+#define INAT_SEG_REG_SS		3
+#define INAT_SEG_REG_DS		4
+#define INAT_SEG_REG_ES		5
+#define INAT_SEG_REG_FS		6
+#define INAT_SEG_REG_GS		7
+
 /* Attribute search APIs */
 extern insn_attr_t inat_get_opcode_attribute(insn_byte_t opcode);
 extern int inat_get_last_prefix_id(insn_byte_t last_pfx);
diff --git a/arch/x86/include/asm/insn-eval.h b/arch/x86/include/asm/insn-eval.h
new file mode 100644
index 000000000000..e1d3b4ce8a92
--- /dev/null
+++ b/arch/x86/include/asm/insn-eval.h
@@ -0,0 +1,23 @@
+#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>
+
+#define INSN_CODE_SEG_ADDR_SZ(params) ((params >> 4) & 0xf)
+#define INSN_CODE_SEG_OPND_SZ(params) (params & 0xf)
+#define INSN_CODE_SEG_PARAMS(oper_sz, addr_sz) (oper_sz | (addr_sz << 4))
+
+void __user *insn_get_addr_ref(struct insn *insn, struct pt_regs *regs);
+int insn_get_modrm_rm_off(struct insn *insn, struct pt_regs *regs);
+unsigned long insn_get_seg_base(struct pt_regs *regs, int seg_reg_idx);
+char insn_get_code_seg_params(struct pt_regs *regs);
+
+#endif /* _ASM_X86_INSN_EVAL_H */
diff --git a/arch/x86/kernel/uprobes.c b/arch/x86/kernel/uprobes.c
index 495c776de4b4..a3755d293a48 100644
--- a/arch/x86/kernel/uprobes.c
+++ b/arch/x86/kernel/uprobes.c
@@ -271,12 +271,15 @@ static bool is_prefix_bad(struct insn *insn)
 	int i;
 
 	for (i = 0; i < insn->prefixes.nbytes; i++) {
-		switch (insn->prefixes.bytes[i]) {
-		case 0x26:	/* INAT_PFX_ES   */
-		case 0x2E:	/* INAT_PFX_CS   */
-		case 0x36:	/* INAT_PFX_DS   */
-		case 0x3E:	/* INAT_PFX_SS   */
-		case 0xF0:	/* INAT_PFX_LOCK */
+		insn_attr_t attr;
+
+		attr = inat_get_opcode_attribute(insn->prefixes.bytes[i]);
+		switch (attr) {
+		case INAT_MAKE_PREFIX(INAT_PFX_ES):
+		case INAT_MAKE_PREFIX(INAT_PFX_CS):
+		case INAT_MAKE_PREFIX(INAT_PFX_DS):
+		case INAT_MAKE_PREFIX(INAT_PFX_SS):
+		case INAT_MAKE_PREFIX(INAT_PFX_LOCK):
 			return true;
 		}
 	}
diff --git a/arch/x86/lib/Makefile b/arch/x86/lib/Makefile
index 457f681ef379..7b181b61170e 100644
--- a/arch/x86/lib/Makefile
+++ b/arch/x86/lib/Makefile
@@ -24,7 +24,7 @@ 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 000000000000..91f08aafb65e
--- /dev/null
+++ b/arch/x86/lib/insn-eval.c
@@ -0,0 +1,865 @@
+/*
+ * Utility functions for x86 operand and address decoding
+ *
+ * Copyright (C) Intel Corporation 2017
+ */
+#include <linux/kernel.h>
+#include <linux/string.h>
+#include <linux/ratelimit.h>
+#include <linux/mmu_context.h>
+#include <asm/desc_defs.h>
+#include <asm/desc.h>
+#include <asm/inat.h>
+#include <asm/insn.h>
+#include <asm/insn-eval.h>
+#include <asm/ldt.h>
+#include <asm/vm86.h>
+
+#undef pr_fmt
+#define pr_fmt(fmt) "insn: " fmt
+
+enum reg_type {
+	REG_TYPE_RM = 0,
+	REG_TYPE_INDEX,
+	REG_TYPE_BASE,
+};
+
+/**
+ * is_string_insn() - Determine if instruction is a string instruction
+ * @insn:	Instruction containing the opcode to inspect
+ *
+ * Returns:
+ *
+ * true if the instruction, determined by the opcode, is any of the
+ * string instructions as defined in the Intel Software Development manual.
+ * False otherwise.
+ */
+static bool is_string_insn(struct insn *insn)
+{
+	insn_get_opcode(insn);
+
+	/* All string instructions have a 1-byte opcode. */
+	if (insn->opcode.nbytes != 1)
+		return false;
+
+	switch (insn->opcode.bytes[0]) {
+	case 0x6c ... 0x6f:	/* INS, OUTS */
+	case 0xa4 ... 0xa7:	/* MOVS, CMPS */
+	case 0xaa ... 0xaf:	/* STOS, LODS, SCAS */
+		return true;
+	default:
+		return false;
+	}
+}
+
+/**
+ * get_seg_reg_override_idx() - obtain segment register override index
+ * @insn:	Valid instruction with segment override prefixes
+ *
+ * Inspect the instruction prefixes in @insn and find segment overrides, if any.
+ *
+ * Returns:
+ *
+ * A constant identifying the segment register to use, among CS, SS, DS,
+ * ES, FS, or GS. INAT_SEG_REG_DEFAULT is returned if no segment override
+ * prefixes were found.
+ *
+ * -EINVAL in case of error.
+ */
+static int get_seg_reg_override_idx(struct insn *insn)
+{
+	int idx = INAT_SEG_REG_DEFAULT;
+	int num_overrides = 0, i;
+
+	insn_get_prefixes(insn);
+
+	/* Look for any segment override prefixes. */
+	for (i = 0; i < insn->prefixes.nbytes; i++) {
+		insn_attr_t attr;
+
+		attr = inat_get_opcode_attribute(insn->prefixes.bytes[i]);
+		switch (attr) {
+		case INAT_MAKE_PREFIX(INAT_PFX_CS):
+			idx = INAT_SEG_REG_CS;
+			num_overrides++;
+			break;
+		case INAT_MAKE_PREFIX(INAT_PFX_SS):
+			idx = INAT_SEG_REG_SS;
+			num_overrides++;
+			break;
+		case INAT_MAKE_PREFIX(INAT_PFX_DS):
+			idx = INAT_SEG_REG_DS;
+			num_overrides++;
+			break;
+		case INAT_MAKE_PREFIX(INAT_PFX_ES):
+			idx = INAT_SEG_REG_ES;
+			num_overrides++;
+			break;
+		case INAT_MAKE_PREFIX(INAT_PFX_FS):
+			idx = INAT_SEG_REG_FS;
+			num_overrides++;
+			break;
+		case INAT_MAKE_PREFIX(INAT_PFX_GS):
+			idx = INAT_SEG_REG_GS;
+			num_overrides++;
+			break;
+		/* No default action needed. */
+		}
+	}
+
+	/* More than one segment override prefix leads to undefined behavior. */
+	if (num_overrides > 1)
+		return -EINVAL;
+
+	return idx;
+}
+
+/**
+ * check_seg_overrides() - check if segment override prefixes are allowed
+ * @insn:	Valid instruction with segment override prefixes
+ * @regoff:	Operand offset, in pt_regs, for which the check is performed
+ *
+ * For a particular register used in register-indirect addressing, determine if
+ * segment override prefixes can be used. Specifically, no overrides are allowed
+ * for rDI if used with a string instruction.
+ *
+ * Returns:
+ *
+ * True if segment override prefixes can be used with the register indicated
+ * in @regoff. False if otherwise.
+ */
+static bool check_seg_overrides(struct insn *insn, int regoff)
+{
+	if (regoff == offsetof(struct pt_regs, di) && is_string_insn(insn))
+		return false;
+
+	return true;
+}
+
+/**
+ * resolve_default_seg() - resolve default segment register index for an operand
+ * @insn:	Instruction with opcode and address size. Must be valid.
+ * @regs:	Register values as seen when entering kernel mode
+ * @off:	Operand offset, in pt_regs, for which resolution is needed
+ *
+ * Resolve the default segment register index associated with the instruction
+ * operand register indicated by @off. Such index is resolved based on defaults
+ * described in the Intel Software Development Manual.
+ *
+ * Returns:
+ *
+ * If in protected mode, a constant identifying the segment register to use,
+ * among CS, SS, ES or DS. If in long mode, INAT_SEG_REG_IGNORE.
+ *
+ * -EINVAL in case of error.
+ */
+static int resolve_default_seg(struct insn *insn, struct pt_regs *regs, int off)
+{
+	if (user_64bit_mode(regs))
+		return INAT_SEG_REG_IGNORE;
+	/*
+	 * Resolve the default segment register as described in Section 3.7.4
+	 * of the Intel Software Development Manual Vol. 1:
+	 *
+	 *  + DS for all references involving r[ABCD]X, and rSI.
+	 *  + If used in a string instruction, ES for rDI. Otherwise, DS.
+	 *  + AX, CX and DX are not valid register operands in 16-bit address
+	 *    encodings but are valid for 32-bit and 64-bit encodings.
+	 *  + -EDOM is reserved to identify for cases in which no register
+	 *    is used (i.e., displacement-only addressing). Use DS.
+	 *  + SS for rSP or rBP.
+	 *  + CS for rIP.
+	 */
+
+	switch (off) {
+	case offsetof(struct pt_regs, ax):
+	case offsetof(struct pt_regs, cx):
+	case offsetof(struct pt_regs, dx):
+		/* Need insn to verify address size. */
+		if (insn->addr_bytes == 2)
+			return -EINVAL;
+
+	case -EDOM:
+	case offsetof(struct pt_regs, bx):
+	case offsetof(struct pt_regs, si):
+		return INAT_SEG_REG_DS;
+
+	case offsetof(struct pt_regs, di):
+		if (is_string_insn(insn))
+			return INAT_SEG_REG_ES;
+		return INAT_SEG_REG_DS;
+
+	case offsetof(struct pt_regs, bp):
+	case offsetof(struct pt_regs, sp):
+		return INAT_SEG_REG_SS;
+
+	case offsetof(struct pt_regs, ip):
+		return INAT_SEG_REG_CS;
+
+	default:
+		return -EINVAL;
+	}
+}
+
+/**
+ * resolve_seg_reg() - obtain segment register index
+ * @insn:	Instruction with operands
+ * @regs:	Register values as seen when entering kernel mode
+ * @regoff:	Operand offset, in pt_regs, used to deterimine segment register
+ *
+ * Determine the segment register associated with the operands and, if
+ * applicable, prefixes and the instruction pointed by @insn.
+ *
+ * The segment register associated to an operand used in register-indirect
+ * addressing depends on:
+ *
+ * a) Whether running in long mode (in such a case segments are ignored, except
+ * if FS or GS are used).
+ *
+ * b) Whether segment override prefixes can be used. Certain instructions and
+ *    registers do not allow override prefixes.
+ *
+ * c) Whether segment overrides prefixes are found in the instruction prefixes.
+ *
+ * d) If there are not segment override prefixes or they cannot be used, the
+ *    default segment register associated with the operand register is used.
+ *
+ * The function checks first if segment override prefixes can be used with the
+ * operand indicated by @regoff. If allowed, obtain such overridden segment
+ * register index. Lastly, if not prefixes were found or cannot be used, resolve
+ * the segment register index to use based on the defaults described in the
+ * Intel documentation. In long mode, all segment register indexes will be
+ * ignored, except if overrides were found for FS or GS. All these operations
+ * are done using helper functions.
+ *
+ * The operand register, @regoff, is represented as the offset from the base of
+ * pt_regs.
+ *
+ * As stated, the main use of this function is to determine the segment register
+ * index based on the instruction, its operands and prefixes. Hence, @insn
+ * must be valid. However, if @regoff indicates rIP, we don't need to inspect
+ * @insn at all as in this case CS is used in all cases. This case is checked
+ * before proceeding further.
+ *
+ * Please note that this function does not return the value in the segment
+ * register (i.e., the segment selector) but our defined index. The segment
+ * selector needs to be obtained using get_segment_selector() and passing the
+ * segment register index resolved by this function.
+ *
+ * Returns:
+ *
+ * An index identifying the segment register to use, among CS, SS, DS,
+ * ES, FS, or GS. INAT_SEG_REG_IGNORE is returned if running in long mode.
+ *
+ * -EINVAL in case of error.
+ */
+static int resolve_seg_reg(struct insn *insn, struct pt_regs *regs, int regoff)
+{
+	int idx;
+
+	/*
+	 * In the unlikely event of having to resolve the segment register
+	 * index for rIP, do it first. Segment override prefixes should not
+	 * be used. Hence, it is not necessary to inspect the instruction,
+	 * which may be invalid at this point.
+	 */
+	if (regoff == offsetof(struct pt_regs, ip)) {
+		if (user_64bit_mode(regs))
+			return INAT_SEG_REG_IGNORE;
+		else
+			return INAT_SEG_REG_CS;
+	}
+
+	if (!insn)
+		return -EINVAL;
+
+	if (!check_seg_overrides(insn, regoff))
+		return resolve_default_seg(insn, regs, regoff);
+
+	idx = get_seg_reg_override_idx(insn);
+	if (idx < 0)
+		return idx;
+
+	if (idx == INAT_SEG_REG_DEFAULT)
+		return resolve_default_seg(insn, regs, regoff);
+
+	/*
+	 * In long mode, segment override prefixes are ignored, except for
+	 * overrides for FS and GS.
+	 */
+	if (user_64bit_mode(regs)) {
+		if (idx != INAT_SEG_REG_FS &&
+		    idx != INAT_SEG_REG_GS)
+			idx = INAT_SEG_REG_IGNORE;
+	}
+
+	return idx;
+}
+
+/**
+ * get_segment_selector() - obtain segment selector
+ * @regs:		Register values as seen when entering kernel mode
+ * @seg_reg_idx:	Segment register index to use
+ *
+ * Obtain the segment selector from any of the CS, SS, DS, ES, FS, GS segment
+ * registers. In CONFIG_X86_32, the segment is obtained from either pt_regs or
+ * kernel_vm86_regs as applicable. In CONFIG_X86_64, CS and SS are obtained
+ * from pt_regs. DS, ES, FS and GS are obtained by reading the actual CPU
+ * registers. This done for only for completeness as in CONFIG_X86_64 segment
+ * registers are ignored.
+ *
+ * Returns:
+ *
+ * Value of the segment selector, including null when running in
+ * long mode.
+ *
+ * -EINVAL on error.
+ */
+static short get_segment_selector(struct pt_regs *regs, int seg_reg_idx)
+{
+#ifdef CONFIG_X86_64
+	unsigned short sel;
+
+	switch (seg_reg_idx) {
+	case INAT_SEG_REG_IGNORE:
+		return 0;
+	case INAT_SEG_REG_CS:
+		return (unsigned short)(regs->cs & 0xffff);
+	case INAT_SEG_REG_SS:
+		return (unsigned short)(regs->ss & 0xffff);
+	case INAT_SEG_REG_DS:
+		savesegment(ds, sel);
+		return sel;
+	case INAT_SEG_REG_ES:
+		savesegment(es, sel);
+		return sel;
+	case INAT_SEG_REG_FS:
+		savesegment(fs, sel);
+		return sel;
+	case INAT_SEG_REG_GS:
+		savesegment(gs, sel);
+		return sel;
+	default:
+		return -EINVAL;
+	}
+#else /* CONFIG_X86_32 */
+	struct kernel_vm86_regs *vm86regs = (struct kernel_vm86_regs *)regs;
+
+	if (v8086_mode(regs)) {
+		switch (seg_reg_idx) {
+		case INAT_SEG_REG_CS:
+			return (unsigned short)(regs->cs & 0xffff);
+		case INAT_SEG_REG_SS:
+			return (unsigned short)(regs->ss & 0xffff);
+		case INAT_SEG_REG_DS:
+			return vm86regs->ds;
+		case INAT_SEG_REG_ES:
+			return vm86regs->es;
+		case INAT_SEG_REG_FS:
+			return vm86regs->fs;
+		case INAT_SEG_REG_GS:
+			return vm86regs->gs;
+		case INAT_SEG_REG_IGNORE:
+			/* fall through */
+		default:
+			return -EINVAL;
+		}
+	}
+
+	switch (seg_reg_idx) {
+	case INAT_SEG_REG_CS:
+		return (unsigned short)(regs->cs & 0xffff);
+	case INAT_SEG_REG_SS:
+		return (unsigned short)(regs->ss & 0xffff);
+	case INAT_SEG_REG_DS:
+		return (unsigned short)(regs->ds & 0xffff);
+	case INAT_SEG_REG_ES:
+		return (unsigned short)(regs->es & 0xffff);
+	case INAT_SEG_REG_FS:
+		return (unsigned short)(regs->fs & 0xffff);
+	case INAT_SEG_REG_GS:
+		/*
+		 * GS may or may not be in regs as per CONFIG_X86_32_LAZY_GS.
+		 * The macro below takes care of both cases.
+		 */
+		return get_user_gs(regs);
+	case INAT_SEG_REG_IGNORE:
+		/* fall through */
+	default:
+		return -EINVAL;
+	}
+#endif /* CONFIG_X86_64 */
+}
+
+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);
+
+		/*
+		 * ModRM.mod == 0 and ModRM.rm == 5 means a 32-bit displacement
+		 * follows the ModRM byte.
+		 */
+		if (!X86_MODRM_MOD(insn->modrm.value) && regno == 5)
+			return -EDOM;
+
+		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 ModRM.mod != 3 and SIB.index = 4 the scale*index
+		 * portion of the address computation is null. This is
+		 * true only if REX.X is 0. In such a case, the SIB index
+		 * is used in the address computation.
+		 */
+		if (X86_MODRM_MOD(insn->modrm.value) != 3 && regno == 4)
+			return -EDOM;
+		break;
+
+	case REG_TYPE_BASE:
+		regno = X86_SIB_BASE(insn->sib.value);
+		/*
+		 * If ModRM.mod is 0 and SIB.base == 5, the base of the
+		 * register-indirect addressing is 0. In this case, a
+		 * 32-bit displacement follows the SIB byte.
+		 */
+		if (!X86_MODRM_MOD(insn->modrm.value) && regno == 5)
+			return -EDOM;
+
+		if (X86_REX_B(insn->rex_prefix.value))
+			regno += 8;
+		break;
+
+	default:
+		pr_err_ratelimited("invalid register type: %d\n", type);
+		return -EINVAL;
+	}
+
+	if (regno >= nr_registers) {
+		WARN_ONCE(1, "decoded an instruction with an invalid register");
+		return -EINVAL;
+	}
+	return regoff[regno];
+}
+
+/**
+ * get_desc() - Obtain pointer to a segment descriptor
+ * @sel:	Segment selector
+ *
+ * Given a segment selector, obtain a pointer to the segment descriptor.
+ * Both global and local descriptor tables are supported.
+ *
+ * Returns:
+ *
+ * Pointer to segment descriptor on success.
+ *
+ * NULL on error.
+ */
+static struct desc_struct *get_desc(unsigned short sel)
+{
+	struct desc_ptr gdt_desc = {0, 0};
+	unsigned long desc_base;
+
+#ifdef CONFIG_MODIFY_LDT_SYSCALL
+	if ((sel & SEGMENT_TI_MASK) == SEGMENT_LDT) {
+		struct desc_struct *desc = NULL;
+		struct ldt_struct *ldt;
+
+		/* Bits [15:3] contain the index of the desired entry. */
+		sel >>= 3;
+
+		mutex_lock(&current->active_mm->context.lock);
+		ldt = current->active_mm->context.ldt;
+		if (ldt && sel < ldt->nr_entries)
+			desc = &ldt->entries[sel];
+
+		mutex_unlock(&current->active_mm->context.lock);
+
+		return desc;
+	}
+#endif
+	native_store_gdt(&gdt_desc);
+
+	/*
+	 * Segment descriptors have a size of 8 bytes. Thus, the index is
+	 * multiplied by 8 to obtain the memory offset of the desired descriptor
+	 * from the base of the GDT. As bits [15:3] of the segment selector
+	 * contain the index, it can be regarded as multiplied by 8 already.
+	 * All that remains is to clear bits [2:0].
+	 */
+	desc_base = sel & ~(SEGMENT_RPL_MASK | SEGMENT_TI_MASK);
+
+	if (desc_base > gdt_desc.size)
+		return NULL;
+
+	return (struct desc_struct *)(gdt_desc.address + desc_base);
+}
+
+/**
+ * insn_get_seg_base() - Obtain base address of segment descriptor.
+ * @regs:		Register values as seen when entering kernel mode
+ * @seg_reg_idx:	Index of the segment register pointing to seg descriptor
+ *
+ * Obtain the base address of the segment as indicated by the segment descriptor
+ * pointed by the segment selector. The segment selector is obtained from the
+ * input segment register index @seg_reg_idx.
+ *
+ * Returns:
+ *
+ * In protected mode, base address of the segment. Zero in long mode,
+ * except when FS or GS are used. In virtual-8086 mode, the segment
+ * selector shifted 4 bits to the right.
+ *
+ * -1L in case of error.
+ */
+unsigned long insn_get_seg_base(struct pt_regs *regs, int seg_reg_idx)
+{
+	struct desc_struct *desc;
+	short sel;
+
+	sel = get_segment_selector(regs, seg_reg_idx);
+	if (sel < 0)
+		return -1L;
+
+	if (v8086_mode(regs))
+		/*
+		 * Base is simply the segment selector shifted 4
+		 * bits to the right.
+		 */
+		return (unsigned long)(sel << 4);
+
+	if (user_64bit_mode(regs)) {
+		/*
+		 * Only FS or GS will have a base address, the rest of
+		 * the segments' bases are forced to 0.
+		 */
+		unsigned long base;
+
+		if (seg_reg_idx == INAT_SEG_REG_FS)
+			rdmsrl(MSR_FS_BASE, base);
+		else if (seg_reg_idx == INAT_SEG_REG_GS)
+			/*
+			 * swapgs was called at the kernel entry point. Thus,
+			 * MSR_KERNEL_GS_BASE will have the user-space GS base.
+			 */
+			rdmsrl(MSR_KERNEL_GS_BASE, base);
+		else
+			base = 0;
+		return base;
+	}
+
+	/* In protected mode the segment selector cannot be null. */
+	if (!sel)
+		return -1L;
+
+	desc = get_desc(sel);
+	if (!desc)
+		return -1L;
+
+	return get_desc_base(desc);
+}
+
+/**
+ * get_seg_limit() - Obtain the limit of a segment descriptor
+ * @regs:		Register values as seen when entering kernel mode
+ * @seg_reg_idx:	Index of the segment register pointing to seg descriptor
+ *
+ * Obtain the limit of the segment as indicated by the segment descriptor
+ * pointed by the segment selector. The segment selector is obtained from the
+ * input segment register index @seg_reg_idx.
+ *
+ * Returns:
+ *
+ * In protected mode, the limit of the segment descriptor in bytes.
+ * In long mode and virtual-8086 mode, segment limits are not enforced. Thus,
+ * limit is returned as -1L to imply a limit-less segment.
+ *
+ * Zero is returned on error.
+ */
+static unsigned long get_seg_limit(struct pt_regs *regs, int seg_reg_idx)
+{
+	struct desc_struct *desc;
+	unsigned long limit;
+	short sel;
+
+	sel = get_segment_selector(regs, seg_reg_idx);
+	if (sel < 0)
+		return 0;
+
+	if (user_64bit_mode(regs) || v8086_mode(regs))
+		return -1L;
+
+	if (!sel)
+		return 0;
+
+	desc = get_desc(sel);
+	if (!desc)
+		return 0;
+
+	/*
+	 * If the granularity bit is set, the limit is given in multiples
+	 * of 4096. This also means that the 12 least significant bits are
+	 * not tested when checking the segment limits. In practice,
+	 * this means that the segment ends in (limit << 12) + 0xfff.
+	 */
+	limit = get_desc_limit(desc);
+	if (desc->g)
+		limit = (limit << 12) + 0xfff;
+
+	return limit;
+}
+
+/**
+ * insn_get_code_seg_params() - Obtain code segment parameters
+ * @regs:	Structure with register values as seen when entering kernel mode
+ *
+ * Obtain address and operand sizes of the code segment. It is obtained from the
+ * selector contained in the CS register in regs. In protected mode, the default
+ * address is determined by inspecting the L and D bits of the segment
+ * descriptor. In virtual-8086 mode, the default is always two bytes for both
+ * address and operand sizes.
+ *
+ * Returns:
+ *
+ * A signed 8-bit value containing the default parameters on success.
+ *
+ * -EINVAL on error.
+ */
+char insn_get_code_seg_params(struct pt_regs *regs)
+{
+	struct desc_struct *desc;
+	short sel;
+
+	if (v8086_mode(regs))
+		/* Address and operand size are both 16-bit. */
+		return INSN_CODE_SEG_PARAMS(2, 2);
+
+	sel = get_segment_selector(regs, INAT_SEG_REG_CS);
+	if (sel < 0)
+		return sel;
+
+	desc = get_desc(sel);
+	if (!desc)
+		return -EINVAL;
+
+	/*
+	 * The most significant byte of the Type field of the segment descriptor
+	 * determines whether a segment contains data or code. If this is a data
+	 * segment, return error.
+	 */
+	if (!(desc->type & BIT(3)))
+		return -EINVAL;
+
+	switch ((desc->l << 1) | desc->d) {
+	case 0: /*
+		 * Legacy mode. CS.L=0, CS.D=0. Address and operand size are
+		 * both 16-bit.
+		 */
+		return INSN_CODE_SEG_PARAMS(2, 2);
+	case 1: /*
+		 * Legacy mode. CS.L=0, CS.D=1. Address and operand size are
+		 * both 32-bit.
+		 */
+		return INSN_CODE_SEG_PARAMS(4, 4);
+	case 2: /*
+		 * IA-32e 64-bit mode. CS.L=1, CS.D=0. Address size is 64-bit;
+		 * operand size is 32-bit.
+		 */
+		return INSN_CODE_SEG_PARAMS(4, 8);
+	case 3: /* Invalid setting. CS.L=1, CS.D=1 */
+		/* fall through */
+	default:
+		return -EINVAL;
+	}
+}
+
+/**
+ * insn_get_modrm_rm_off() - Obtain register in r/m part of the ModRM byte
+ * @insn:	Instruction containing the ModRM byte
+ * @regs:	Register values as seen when entering kernel mode
+ *
+ * Returns:
+ *
+ * The register indicated by the r/m part of the ModRM byte. The
+ * register is obtained as an offset from the base of pt_regs. In specific
+ * cases, the returned value can be -EDOM to indicate that the particular value
+ * of ModRM does not refer to a register and shall be ignored.
+ */
+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_limit() - obtain base address and limit 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
+ * @limit:	Obtained segment limit
+ *
+ * Obtain the base address and limit 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. If a limit is not needed (e.g.,
+ * when running in long mode), @limit can be NULL.
+ *
+ * Returns:
+ *
+ * 0 on success. @base and @limit will contain the base address and of the
+ * resolved segment, respectively.
+ *
+ * -EINVAL on error.
+ */
+static int get_seg_base_limit(struct insn *insn, struct pt_regs *regs,
+			      int regoff, unsigned long *base,
+			      unsigned long *limit)
+{
+	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;
+
+	if (!limit)
+		return 0;
+
+	*limit = get_seg_limit(regs, seg_reg_idx);
+	if (!(*limit))
+		return -EINVAL;
+
+	return 0;
+}
+
+/*
+ * 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)
+{
+	int addr_offset, base_offset, indx_offset, ret;
+	unsigned long linear_addr = -1L, seg_base;
+	long eff_addr, base, indx;
+	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;
+
+		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 (base_offset == -EDOM)
+				base = 0;
+			else if (base_offset < 0)
+				goto out;
+			else
+				base = regs_get_register(regs, base_offset);
+
+			indx_offset = get_reg_offset(insn, regs, REG_TYPE_INDEX);
+
+			if (indx_offset == -EDOM)
+				indx = 0;
+			else if (indx_offset < 0)
+				goto out;
+			else
+				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);
+			/*
+			 * -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 {
+				eff_addr = regs_get_register(regs, addr_offset);
+			}
+		}
+
+		eff_addr += insn->displacement.value;
+	}
+
+	ret = get_seg_base_limit(insn, regs, addr_offset, &seg_base, NULL);
+	if (ret)
+		goto out;
+
+	linear_addr = (unsigned long)eff_addr + seg_base;
+
+out:
+	return (void __user *)linear_addr;
+}
diff --git a/arch/x86/mm/mpx.c b/arch/x86/mm/mpx.c
index 7eb06701a935..e500949bae24 100644
--- a/arch/x86/mm/mpx.c
+++ b/arch/x86/mm/mpx.c
@@ -13,6 +13,7 @@
 #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>
@@ -61,123 +62,6 @@ 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;
-		break;
-
-	case REG_TYPE_BASE:
-		regno = X86_SIB_BASE(insn->sib.value);
-		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 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;
-		addr = regs_get_register(regs, addr_offset);
-	} else {
-		if (insn->sib.nbytes) {
-			base_offset = get_reg_offset(insn, regs, REG_TYPE_BASE);
-			if (base_offset < 0)
-				goto out_err;
-
-			indx_offset = get_reg_offset(insn, regs, REG_TYPE_INDEX);
-			if (indx_offset < 0)
-				goto out_err;
-
-			base = regs_get_register(regs, base_offset);
-			indx = regs_get_register(regs, indx_offset);
-			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;
-			addr = regs_get_register(regs, addr_offset);
-		}
-		addr += insn->displacement.value;
-	}
-	return (void __user *)addr;
-out_err:
-	return (void __user *)-1;
-}
-
 static int mpx_insn_decode(struct insn *insn,
 			   struct pt_regs *regs)
 {
@@ -290,7 +174,7 @@ 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.