Merge branch 'x86-mpx-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull x86 MPX support from Thomas Gleixner:
 "This enables support for x86 MPX.

  MPX is a new debug feature for bound checking in user space.  It
  requires kernel support to handle the bound tables and decode the
  bound violating instruction in the trap handler"

* 'x86-mpx-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
  asm-generic: Remove asm-generic arch_bprm_mm_init()
  mm: Make arch_unmap()/bprm_mm_init() available to all architectures
  x86: Cleanly separate use of asm-generic/mm_hooks.h
  x86 mpx: Change return type of get_reg_offset()
  fs: Do not include mpx.h in exec.c
  x86, mpx: Add documentation on Intel MPX
  x86, mpx: Cleanup unused bound tables
  x86, mpx: On-demand kernel allocation of bounds tables
  x86, mpx: Decode MPX instruction to get bound violation information
  x86, mpx: Add MPX-specific mmap interface
  x86, mpx: Introduce VM_MPX to indicate that a VMA is MPX specific
  x86, mpx: Add MPX to disabled features
  ia64: Sync struct siginfo with general version
  mips: Sync struct siginfo with general version
  mpx: Extend siginfo structure to include bound violation information
  x86, mpx: Rename cfg_reg_u and status_reg
  x86: mpx: Give bndX registers actual names
  x86: Remove arbitrary instruction size limit in instruction decoder

arch/ia64/include/uapi/asm/siginfo.h

@@ -63,6 +63,10 @@ typedef struct siginfo {
 			unsigned int _flags;	/* see below */
 			unsigned long _isr;	/* isr */
 			short _addr_lsb;	/* lsb of faulting address */
+			struct {
+				void __user *_lower;
+				void __user *_upper;
+			} _addr_bnd;
 		} _sigfault;
 
 		/* SIGPOLL */
@@ -110,9 +114,9 @@ typedef struct siginfo {
 /*
  * SIGSEGV si_codes
  */
-#define __SEGV_PSTKOVF	(__SI_FAULT|3)	/* paragraph stack overflow */
+#define __SEGV_PSTKOVF	(__SI_FAULT|4)	/* paragraph stack overflow */
 #undef NSIGSEGV
-#define NSIGSEGV	3
+#define NSIGSEGV	4
 
 #undef NSIGTRAP
 #define NSIGTRAP	4

arch/mips/include/uapi/asm/siginfo.h

@@ -92,6 +92,10 @@ typedef struct siginfo {
 			int _trapno;	/* TRAP # which caused the signal */
 #endif
 			short _addr_lsb;
+			struct {
+				void __user *_lower;
+				void __user *_upper;
+			} _addr_bnd;
 		} _sigfault;
 
 		/* SIGPOLL, SIGXFSZ (To do ...)	 */

arch/s390/include/asm/mmu_context.h

@@ -120,4 +120,15 @@ static inline void arch_exit_mmap(struct mm_struct *mm)
 {
 }
 
+static inline void arch_unmap(struct mm_struct *mm,
+			struct vm_area_struct *vma,
+			unsigned long start, unsigned long end)
+{
+}
+
+static inline void arch_bprm_mm_init(struct mm_struct *mm,
+				     struct vm_area_struct *vma)
+{
+}
+
 #endif /* __S390_MMU_CONTEXT_H */

arch/um/include/asm/mmu_context.h

@@ -10,7 +10,26 @@
 #include <asm/mmu.h>
 
 extern void uml_setup_stubs(struct mm_struct *mm);
+/*
+ * Needed since we do not use the asm-generic/mm_hooks.h:
+ */
+static inline void arch_dup_mmap(struct mm_struct *oldmm, struct mm_struct *mm)
+{
+	uml_setup_stubs(mm);
+}
 extern void arch_exit_mmap(struct mm_struct *mm);
+static inline void arch_unmap(struct mm_struct *mm,
+			struct vm_area_struct *vma,
+			unsigned long start, unsigned long end)
+{
+}
+static inline void arch_bprm_mm_init(struct mm_struct *mm,
+				     struct vm_area_struct *vma)
+{
+}
+/*
+ * end asm-generic/mm_hooks.h functions
+ */
 
 #define deactivate_mm(tsk,mm)	do { } while (0)
 
@@ -41,11 +60,6 @@ static inline void switch_mm(struct mm_struct *prev, struct mm_struct *next,
 	}
 }
 
-static inline void arch_dup_mmap(struct mm_struct *oldmm, struct mm_struct *mm)
-{
-	uml_setup_stubs(mm);
-}
-
 static inline void enter_lazy_tlb(struct mm_struct *mm, 
 				  struct task_struct *tsk)
 {

arch/unicore32/include/asm/mmu_context.h

@@ -86,4 +86,15 @@ static inline void arch_dup_mmap(struct mm_struct *oldmm,
 {
 }
 
+static inline void arch_unmap(struct mm_struct *mm,
+			struct vm_area_struct *vma,
+			unsigned long start, unsigned long end)
+{
+}
+
+static inline void arch_bprm_mm_init(struct mm_struct *mm,
+				     struct vm_area_struct *vma)
+{
+}
+
 #endif

arch/x86/Kconfig

@@ -248,6 +248,10 @@ config HAVE_INTEL_TXT
 	def_bool y
 	depends on INTEL_IOMMU && ACPI
 
+config X86_INTEL_MPX
+	def_bool y
+	depends on CPU_SUP_INTEL
+
 config X86_32_SMP
 	def_bool y
 	depends on X86_32 && SMP

arch/x86/include/asm/disabled-features.h

@@ -10,6 +10,12 @@
  * cpu_feature_enabled().
  */
 
+#ifdef CONFIG_X86_INTEL_MPX
+# define DISABLE_MPX	0
+#else
+# define DISABLE_MPX	(1<<(X86_FEATURE_MPX & 31))
+#endif
+
 #ifdef CONFIG_X86_64
 # define DISABLE_VME		(1<<(X86_FEATURE_VME & 31))
 # define DISABLE_K6_MTRR	(1<<(X86_FEATURE_K6_MTRR & 31))
@@ -34,6 +40,6 @@
 #define DISABLED_MASK6	0
 #define DISABLED_MASK7	0
 #define DISABLED_MASK8	0
-#define DISABLED_MASK9	0
+#define DISABLED_MASK9	(DISABLE_MPX)
 
 #endif /* _ASM_X86_DISABLED_FEATURES_H */

arch/x86/include/asm/insn.h

@@ -65,6 +65,7 @@ struct insn {
 	unsigned char x86_64;
 
 	const insn_byte_t *kaddr;	/* kernel address of insn to analyze */
+	const insn_byte_t *end_kaddr;	/* kernel address of last insn in buffer */
 	const insn_byte_t *next_byte;
 };
 
@@ -96,7 +97,7 @@ struct insn {
 #define X86_VEX_P(vex)	((vex) & 0x03)		/* VEX3 Byte2, VEX2 Byte1 */
 #define X86_VEX_M_MAX	0x1f			/* VEX3.M Maximum value */
 
-extern void insn_init(struct insn *insn, const void *kaddr, int x86_64);
+extern void insn_init(struct insn *insn, const void *kaddr, int buf_len, int x86_64);
 extern void insn_get_prefixes(struct insn *insn);
 extern void insn_get_opcode(struct insn *insn);
 extern void insn_get_modrm(struct insn *insn);
@@ -115,12 +116,13 @@ static inline void insn_get_attribute(struct insn *insn)
 extern int insn_rip_relative(struct insn *insn);
 
 /* Init insn for kernel text */
-static inline void kernel_insn_init(struct insn *insn, const void *kaddr)
+static inline void kernel_insn_init(struct insn *insn,
+				    const void *kaddr, int buf_len)
 {
 #ifdef CONFIG_X86_64
-	insn_init(insn, kaddr, 1);
+	insn_init(insn, kaddr, buf_len, 1);
 #else /* CONFIG_X86_32 */
-	insn_init(insn, kaddr, 0);
+	insn_init(insn, kaddr, buf_len, 0);
 #endif
 }
 

arch/x86/include/asm/mmu_context.h

@@ -10,9 +10,8 @@
 #include <asm/pgalloc.h>
 #include <asm/tlbflush.h>
 #include <asm/paravirt.h>
+#include <asm/mpx.h>
 #ifndef CONFIG_PARAVIRT
-#include <asm-generic/mm_hooks.h>
-
 static inline void paravirt_activate_mm(struct mm_struct *prev,
 					struct mm_struct *next)
 {
@@ -102,4 +101,27 @@ do {						\
 } while (0)
 #endif
 
+static inline void arch_dup_mmap(struct mm_struct *oldmm,
+				 struct mm_struct *mm)
+{
+	paravirt_arch_dup_mmap(oldmm, mm);
+}
+
+static inline void arch_exit_mmap(struct mm_struct *mm)
+{
+	paravirt_arch_exit_mmap(mm);
+}
+
+static inline void arch_bprm_mm_init(struct mm_struct *mm,
+		struct vm_area_struct *vma)
+{
+	mpx_mm_init(mm);
+}
+
+static inline void arch_unmap(struct mm_struct *mm, struct vm_area_struct *vma,
+			      unsigned long start, unsigned long end)
+{
+	mpx_notify_unmap(mm, vma, start, end);
+}
+
 #endif /* _ASM_X86_MMU_CONTEXT_H */

arch/x86/include/asm/mpx.h

+#ifndef _ASM_X86_MPX_H
+#define _ASM_X86_MPX_H
+
+#include <linux/types.h>
+#include <asm/ptrace.h>
+#include <asm/insn.h>
+
+/*
+ * NULL is theoretically a valid place to put the bounds
+ * directory, so point this at an invalid address.
+ */
+#define MPX_INVALID_BOUNDS_DIR	((void __user *)-1)
+#define MPX_BNDCFG_ENABLE_FLAG	0x1
+#define MPX_BD_ENTRY_VALID_FLAG	0x1
+
+#ifdef CONFIG_X86_64
+
+/* upper 28 bits [47:20] of the virtual address in 64-bit used to
+ * index into bounds directory (BD).
+ */
+#define MPX_BD_ENTRY_OFFSET	28
+#define MPX_BD_ENTRY_SHIFT	3
+/* bits [19:3] of the virtual address in 64-bit used to index into
+ * bounds table (BT).
+ */
+#define MPX_BT_ENTRY_OFFSET	17
+#define MPX_BT_ENTRY_SHIFT	5
+#define MPX_IGN_BITS		3
+#define MPX_BD_ENTRY_TAIL	3
+
+#else
+
+#define MPX_BD_ENTRY_OFFSET	20
+#define MPX_BD_ENTRY_SHIFT	2
+#define MPX_BT_ENTRY_OFFSET	10
+#define MPX_BT_ENTRY_SHIFT	4
+#define MPX_IGN_BITS		2
+#define MPX_BD_ENTRY_TAIL	2
+
+#endif
+
+#define MPX_BD_SIZE_BYTES (1UL<<(MPX_BD_ENTRY_OFFSET+MPX_BD_ENTRY_SHIFT))
+#define MPX_BT_SIZE_BYTES (1UL<<(MPX_BT_ENTRY_OFFSET+MPX_BT_ENTRY_SHIFT))
+
+#define MPX_BNDSTA_TAIL		2
+#define MPX_BNDCFG_TAIL		12
+#define MPX_BNDSTA_ADDR_MASK	(~((1UL<<MPX_BNDSTA_TAIL)-1))
+#define MPX_BNDCFG_ADDR_MASK	(~((1UL<<MPX_BNDCFG_TAIL)-1))
+#define MPX_BT_ADDR_MASK	(~((1UL<<MPX_BD_ENTRY_TAIL)-1))
+
+#define MPX_BNDCFG_ADDR_MASK	(~((1UL<<MPX_BNDCFG_TAIL)-1))
+#define MPX_BNDSTA_ERROR_CODE	0x3
+
+#define MPX_BD_ENTRY_MASK	((1<<MPX_BD_ENTRY_OFFSET)-1)
+#define MPX_BT_ENTRY_MASK	((1<<MPX_BT_ENTRY_OFFSET)-1)
+#define MPX_GET_BD_ENTRY_OFFSET(addr)	((((addr)>>(MPX_BT_ENTRY_OFFSET+ \
+		MPX_IGN_BITS)) & MPX_BD_ENTRY_MASK) << MPX_BD_ENTRY_SHIFT)
+#define MPX_GET_BT_ENTRY_OFFSET(addr)	((((addr)>>MPX_IGN_BITS) & \
+		MPX_BT_ENTRY_MASK) << MPX_BT_ENTRY_SHIFT)
+
+#ifdef CONFIG_X86_INTEL_MPX
+siginfo_t *mpx_generate_siginfo(struct pt_regs *regs,
+				struct xsave_struct *xsave_buf);
+int mpx_handle_bd_fault(struct xsave_struct *xsave_buf);
+static inline int kernel_managing_mpx_tables(struct mm_struct *mm)
+{
+	return (mm->bd_addr != MPX_INVALID_BOUNDS_DIR);
+}
+static inline void mpx_mm_init(struct mm_struct *mm)
+{
+	/*
+	 * NULL is theoretically a valid place to put the bounds
+	 * directory, so point this at an invalid address.
+	 */
+	mm->bd_addr = MPX_INVALID_BOUNDS_DIR;
+}
+void mpx_notify_unmap(struct mm_struct *mm, struct vm_area_struct *vma,
+		      unsigned long start, unsigned long end);
+#else
+static inline siginfo_t *mpx_generate_siginfo(struct pt_regs *regs,
+					      struct xsave_struct *xsave_buf)
+{
+	return NULL;
+}
+static inline int mpx_handle_bd_fault(struct xsave_struct *xsave_buf)
+{
+	return -EINVAL;
+}
+static inline int kernel_managing_mpx_tables(struct mm_struct *mm)
+{
+	return 0;
+}
+static inline void mpx_mm_init(struct mm_struct *mm)
+{
+}
+static inline void mpx_notify_unmap(struct mm_struct *mm,
+				    struct vm_area_struct *vma,
+				    unsigned long start, unsigned long end)
+{
+}
+#endif /* CONFIG_X86_INTEL_MPX */
+
+#endif /* _ASM_X86_MPX_H */

arch/x86/include/asm/paravirt.h

@@ -330,13 +330,13 @@ static inline void paravirt_activate_mm(struct mm_struct *prev,
 	PVOP_VCALL2(pv_mmu_ops.activate_mm, prev, next);
 }
 
-static inline void arch_dup_mmap(struct mm_struct *oldmm,
+static inline void paravirt_arch_dup_mmap(struct mm_struct *oldmm,
 					  struct mm_struct *mm)
 {
 	PVOP_VCALL2(pv_mmu_ops.dup_mmap, oldmm, mm);
 }
 
-static inline void arch_exit_mmap(struct mm_struct *mm)
+static inline void paravirt_arch_exit_mmap(struct mm_struct *mm)
 {
 	PVOP_VCALL1(pv_mmu_ops.exit_mmap, mm);
 }
@@ -986,5 +986,15 @@ extern void default_banner(void);
 #endif /* __ASSEMBLY__ */
 #else  /* CONFIG_PARAVIRT */
 # define default_banner x86_init_noop
+#ifndef __ASSEMBLY__
+static inline void paravirt_arch_dup_mmap(struct mm_struct *oldmm,
+					  struct mm_struct *mm)
+{
+}
+
+static inline void paravirt_arch_exit_mmap(struct mm_struct *mm)
+{
+}
+#endif /* __ASSEMBLY__ */
 #endif /* !CONFIG_PARAVIRT */
 #endif /* _ASM_X86_PARAVIRT_H */

arch/x86/include/asm/processor.h

@@ -374,13 +374,14 @@ struct lwp_struct {
 	u8 reserved[128];
 };
 
-struct bndregs_struct {
-	u64 bndregs[8];
+struct bndreg {
+	u64 lower_bound;
+	u64 upper_bound;
 } __packed;
 
-struct bndcsr_struct {
-	u64 cfg_reg_u;
-	u64 status_reg;
+struct bndcsr {
+	u64 bndcfgu;
+	u64 bndstatus;
 } __packed;
 
 struct xsave_hdr_struct {
@@ -394,8 +395,8 @@ struct xsave_struct {
 	struct xsave_hdr_struct xsave_hdr;
 	struct ymmh_struct ymmh;
 	struct lwp_struct lwp;
-	struct bndregs_struct bndregs;
-	struct bndcsr_struct bndcsr;
+	struct bndreg bndreg[4];
+	struct bndcsr bndcsr;
 	/* new processor state extensions will go here */
 } __attribute__ ((packed, aligned (64)));
 
@@ -953,6 +954,24 @@ extern void start_thread(struct pt_regs *regs, unsigned long new_ip,
 extern int get_tsc_mode(unsigned long adr);
 extern int set_tsc_mode(unsigned int val);
 
+/* Register/unregister a process' MPX related resource */
+#define MPX_ENABLE_MANAGEMENT(tsk)	mpx_enable_management((tsk))
+#define MPX_DISABLE_MANAGEMENT(tsk)	mpx_disable_management((tsk))
+
+#ifdef CONFIG_X86_INTEL_MPX
+extern int mpx_enable_management(struct task_struct *tsk);
+extern int mpx_disable_management(struct task_struct *tsk);
+#else
+static inline int mpx_enable_management(struct task_struct *tsk)
+{
+	return -EINVAL;
+}
+static inline int mpx_disable_management(struct task_struct *tsk)
+{
+	return -EINVAL;
+}
+#endif /* CONFIG_X86_INTEL_MPX */
+
 extern u16 amd_get_nb_id(int cpu);
 
 static inline uint32_t hypervisor_cpuid_base(const char *sig, uint32_t leaves)

arch/x86/kernel/cpu/perf_event_intel_ds.c

@@ -724,6 +724,7 @@ static int intel_pmu_pebs_fixup_ip(struct pt_regs *regs)
 	unsigned long ip = regs->ip;
 	int is_64bit = 0;
 	void *kaddr;
+	int size;
 
 	/*
 	 * We don't need to fixup if the PEBS assist is fault like
@@ -758,11 +759,12 @@ static int intel_pmu_pebs_fixup_ip(struct pt_regs *regs)
 		return 1;
 	}
 
+	size = ip - to;
 	if (!kernel_ip(ip)) {
-		int size, bytes;
+		int bytes;
 		u8 *buf = this_cpu_read(insn_buffer);
 
-		size = ip - to; /* Must fit our buffer, see above */
+		/* 'size' must fit our buffer, see above */
 		bytes = copy_from_user_nmi(buf, (void __user *)to, size);
 		if (bytes != 0)
 			return 0;
@@ -780,11 +782,20 @@ static int intel_pmu_pebs_fixup_ip(struct pt_regs *regs)
 #ifdef CONFIG_X86_64
 		is_64bit = kernel_ip(to) || !test_thread_flag(TIF_IA32);
 #endif
-		insn_init(&insn, kaddr, is_64bit);
+		insn_init(&insn, kaddr, size, is_64bit);
 		insn_get_length(&insn);
+		/*
+		 * Make sure there was not a problem decoding the
+		 * instruction and getting the length.  This is
+		 * doubly important because we have an infinite
+		 * loop if insn.length=0.
+		 */
+		if (!insn.length)
+			break;
 
 		to += insn.length;
 		kaddr += insn.length;
+		size -= insn.length;
 	} while (to < ip);
 
 	if (to == ip) {

arch/x86/kernel/cpu/perf_event_intel_lbr.c

@@ -465,7 +465,7 @@ static int branch_type(unsigned long from, unsigned long to, int abort)
 {
 	struct insn insn;
 	void *addr;
-	int bytes, size = MAX_INSN_SIZE;
+	int bytes_read, bytes_left;
 	int ret = X86_BR_NONE;
 	int ext, to_plm, from_plm;
 	u8 buf[MAX_INSN_SIZE];
@@ -493,8 +493,10 @@ static int branch_type(unsigned long from, unsigned long to, int abort)
 			return X86_BR_NONE;
 
 		/* may fail if text not present */
-		bytes = copy_from_user_nmi(buf, (void __user *)from, size);
-		if (bytes != 0)
+		bytes_left = copy_from_user_nmi(buf, (void __user *)from,
+						MAX_INSN_SIZE);
+		bytes_read = MAX_INSN_SIZE - bytes_left;
+		if (!bytes_read)
 			return X86_BR_NONE;
 
 		addr = buf;
@@ -505,11 +507,20 @@ static int branch_type(unsigned long from, unsigned long to, int abort)
 		 * Ensure we don't blindy read any address by validating it is
 		 * a known text address.
 		 */
-		if (kernel_text_address(from))
+		if (kernel_text_address(from)) {
 			addr = (void *)from;
-		else
+			/*
+			 * Assume we can get the maximum possible size
+			 * when grabbing kernel data.  This is not
+			 * _strictly_ true since we could possibly be
+			 * executing up next to a memory hole, but
+			 * it is very unlikely to be a problem.
+			 */
+			bytes_read = MAX_INSN_SIZE;
+		} else {
 			return X86_BR_NONE;
 		}
+	}
 
 	/*
 	 * decoder needs to know the ABI especially
@@ -518,8 +529,10 @@ static int branch_type(unsigned long from, unsigned long to, int abort)
 #ifdef CONFIG_X86_64
 	is64 = kernel_ip((unsigned long)addr) || !test_thread_flag(TIF_IA32);
 #endif
-	insn_init(&insn, addr, is64);
+	insn_init(&insn, addr, bytes_read, is64);
 	insn_get_opcode(&insn);
+	if (!insn.opcode.got)
+		return X86_BR_ABORT;
 
 	switch (insn.opcode.bytes[0]) {
 	case 0xf:

arch/x86/kernel/kprobes/core.c

@@ -285,7 +285,7 @@ static int can_probe(unsigned long paddr)
 		 * normally used, we just go through if there is no kprobe.
 		 */
 		__addr = recover_probed_instruction(buf, addr);
-		kernel_insn_init(&insn, (void *)__addr);
+		kernel_insn_init(&insn, (void *)__addr, MAX_INSN_SIZE);
 		insn_get_length(&insn);
 
 		/*
@@ -330,8 +330,10 @@ int __copy_instruction(u8 *dest, u8 *src)
 {
 	struct insn insn;
 	kprobe_opcode_t buf[MAX_INSN_SIZE];
+	unsigned long recovered_insn =
+		recover_probed_instruction(buf, (unsigned long)src);
 
-	kernel_insn_init(&insn, (void *)recover_probed_instruction(buf, (unsigned long)src));
+	kernel_insn_init(&insn, (void *)recovered_insn, MAX_INSN_SIZE);
 	insn_get_length(&insn);
 	/* Another subsystem puts a breakpoint, failed to recover */
 	if (insn.opcode.bytes[0] == BREAKPOINT_INSTRUCTION)
@@ -342,7 +344,7 @@ int __copy_instruction(u8 *dest, u8 *src)
 	if (insn_rip_relative(&insn)) {
 		s64 newdisp;
 		u8 *disp;
-		kernel_insn_init(&insn, dest);
+		kernel_insn_init(&insn, dest, insn.length);
 		insn_get_displacement(&insn);
 		/*
 		 * The copied instruction uses the %rip-relative addressing

arch/x86/kernel/kprobes/opt.c

@@ -251,13 +251,15 @@ static int can_optimize(unsigned long paddr)
 	/* Decode instructions */
 	addr = paddr - offset;
 	while (addr < paddr - offset + size) { /* Decode until function end */
+		unsigned long recovered_insn;
 		if (search_exception_tables(addr))
 			/*
 			 * Since some fixup code will jumps into this function,
 			 * we can't optimize kprobe in this function.
 			 */
 			return 0;
-		kernel_insn_init(&insn, (void *)recover_probed_instruction(buf, addr));
+		recovered_insn = recover_probed_instruction(buf, addr);
+		kernel_insn_init(&insn, (void *)recovered_insn, MAX_INSN_SIZE);
 		insn_get_length(&insn);
 		/* Another subsystem puts a breakpoint */
 		if (insn.opcode.bytes[0] == BREAKPOINT_INSTRUCTION)

arch/x86/kernel/setup.c

@@ -960,6 +960,8 @@ void __init setup_arch(char **cmdline_p)
 	init_mm.end_data = (unsigned long) _edata;
 	init_mm.brk = _brk_end;
 
+	mpx_mm_init(&init_mm);
+
 	code_resource.start = __pa_symbol(_text);
 	code_resource.end = __pa_symbol(_etext)-1;
 	data_resource.start = __pa_symbol(_etext);

arch/x86/kernel/traps.c

@@ -60,6 +60,7 @@
 #include <asm/fixmap.h>
 #include <asm/mach_traps.h>
 #include <asm/alternative.h>
+#include <asm/mpx.h>
 
 #ifdef CONFIG_X86_64
 #include <asm/x86_init.h>
@@ -228,7 +229,6 @@ dotraplinkage void do_##name(struct pt_regs *regs, long error_code)	\
 
 DO_ERROR(X86_TRAP_DE,     SIGFPE,  "divide error",		divide_error)
 DO_ERROR(X86_TRAP_OF,     SIGSEGV, "overflow",			overflow)
-DO_ERROR(X86_TRAP_BR,     SIGSEGV, "bounds",			bounds)
 DO_ERROR(X86_TRAP_UD,     SIGILL,  "invalid opcode",		invalid_op)
 DO_ERROR(X86_TRAP_OLD_MF, SIGFPE,  "coprocessor segment overrun",coprocessor_segment_overrun)
 DO_ERROR(X86_TRAP_TS,     SIGSEGV, "invalid TSS",		invalid_TSS)
@@ -286,6 +286,89 @@ dotraplinkage void do_double_fault(struct pt_regs *regs, long error_code)
 }
 #endif
 
+dotraplinkage void do_bounds(struct pt_regs *regs, long error_code)
+{
+	struct task_struct *tsk = current;
+	struct xsave_struct *xsave_buf;
+	enum ctx_state prev_state;
+	struct bndcsr *bndcsr;
+	siginfo_t *info;
+
+	prev_state = exception_enter();
+	if (notify_die(DIE_TRAP, "bounds", regs, error_code,
+			X86_TRAP_BR, SIGSEGV) == NOTIFY_STOP)
+		goto exit;
+	conditional_sti(regs);
+
+	if (!user_mode(regs))
+		die("bounds", regs, error_code);
+
+	if (!cpu_feature_enabled(X86_FEATURE_MPX)) {
+		/* The exception is not from Intel MPX */
+		goto exit_trap;
+	}
+
+	/*
+	 * We need to look at BNDSTATUS to resolve this exception.
+	 * It is not directly accessible, though, so we need to
+	 * do an xsave and then pull it out of the xsave buffer.
+	 */
+	fpu_save_init(&tsk->thread.fpu);
+	xsave_buf = &(tsk->thread.fpu.state->xsave);
+	bndcsr = get_xsave_addr(xsave_buf, XSTATE_BNDCSR);
+	if (!bndcsr)
+		goto exit_trap;
+
+	/*
+	 * The error code field of the BNDSTATUS register communicates status
+	 * information of a bound range exception #BR or operation involving
+	 * bound directory.
+	 */
+	switch (bndcsr->bndstatus & MPX_BNDSTA_ERROR_CODE) {
+	case 2:	/* Bound directory has invalid entry. */
+		if (mpx_handle_bd_fault(xsave_buf))
+			goto exit_trap;
+		break; /* Success, it was handled */
+	case 1: /* Bound violation. */
+		info = mpx_generate_siginfo(regs, xsave_buf);
+		if (PTR_ERR(info)) {
+			/*
+			 * We failed to decode the MPX instruction.  Act as if
+			 * the exception was not caused by MPX.
+			 */
+			goto exit_trap;
+		}
+		/*
+		 * Success, we decoded the instruction and retrieved
+		 * an 'info' containing the address being accessed
+		 * which caused the exception.  This information
+		 * allows and application to possibly handle the
+		 * #BR exception itself.
+		 */
+		do_trap(X86_TRAP_BR, SIGSEGV, "bounds", regs, error_code, info);
+		kfree(info);
+		break;
+	case 0: /* No exception caused by Intel MPX operations. */
+		goto exit_trap;
+	default:
+		die("bounds", regs, error_code);
+	}
+
+exit:
+	exception_exit(prev_state);
+	return;
+exit_trap:
+	/*
+	 * This path out is for all the cases where we could not
+	 * handle the exception in some way (like allocating a
+	 * table or telling userspace about it.  We will also end
+	 * up here if the kernel has MPX turned off at compile
+	 * time..
+	 */
+	do_trap(X86_TRAP_BR, SIGSEGV, "bounds", regs, error_code, NULL);
+	exception_exit(prev_state);
+}
+
 dotraplinkage void
 do_general_protection(struct pt_regs *regs, long error_code)
 {

arch/x86/kernel/uprobes.c

@@ -219,7 +219,7 @@ static int uprobe_init_insn(struct arch_uprobe *auprobe, struct insn *insn, bool
 {
 	u32 volatile *good_insns;
 
-	insn_init(insn, auprobe->insn, x86_64);
+	insn_init(insn, auprobe->insn, sizeof(auprobe->insn), x86_64);
 	/* has the side-effect of processing the entire instruction */
 	insn_get_length(insn);
 	if (WARN_ON_ONCE(!insn_complete(insn)))

arch/x86/lib/insn.c

@@ -28,7 +28,7 @@
 
 /* Verify next sizeof(t) bytes can be on the same instruction */
 #define validate_next(t, insn, n)	\
-	((insn)->next_byte + sizeof(t) + n - (insn)->kaddr <= MAX_INSN_SIZE)
+	((insn)->next_byte + sizeof(t) + n < (insn)->end_kaddr)
 
 #define __get_next(t, insn)	\
 	({ t r = *(t*)insn->next_byte; insn->next_byte += sizeof(t); r; })
@@ -50,10 +50,11 @@
  * @kaddr:	address (in kernel memory) of instruction (or copy thereof)
  * @x86_64:	!0 for 64-bit kernel or 64-bit app
  */
-void insn_init(struct insn *insn, const void *kaddr, int x86_64)
+void insn_init(struct insn *insn, const void *kaddr, int buf_len, int x86_64)
 {
 	memset(insn, 0, sizeof(*insn));
 	insn->kaddr = kaddr;
+	insn->end_kaddr = kaddr + buf_len;
 	insn->next_byte = kaddr;
 	insn->x86_64 = x86_64 ? 1 : 0;
 	insn->opnd_bytes = 4;

arch/x86/mm/Makefile

@@ -30,3 +30,5 @@ obj-$(CONFIG_ACPI_NUMA)		+= srat.o
 obj-$(CONFIG_NUMA_EMU)		+= numa_emulation.o
 
 obj-$(CONFIG_MEMTEST)		+= memtest.o
+
+obj-$(CONFIG_X86_INTEL_MPX)	+= mpx.o

arch/x86/tools/insn_sanity.c

@@ -254,7 +254,7 @@ int main(int argc, char **argv)
 			continue;
 
 		/* Decode an instruction */
-		insn_init(&insn, insn_buf, x86_64);
+		insn_init(&insn, insn_buf, sizeof(insn_buf), x86_64);
 		insn_get_length(&insn);
 
 		if (insn.next_byte <= insn.kaddr ||

arch/x86/tools/test_get_len.c

@@ -149,7 +149,7 @@ int main(int argc, char **argv)
 				break;
 		}
 		/* Decode an instruction */
-		insn_init(&insn, insn_buf, x86_64);
+		insn_init(&insn, insn_buf, sizeof(insn_buf), x86_64);
 		insn_get_length(&insn);
 		if (insn.length != nb) {
 			warnings++;

fs/exec.c

@@ -277,6 +277,7 @@ static int __bprm_mm_init(struct linux_binprm *bprm)
 		goto err;
 
 	mm->stack_vm = mm->total_vm = 1;
+	arch_bprm_mm_init(mm, vma);
 	up_write(&mm->mmap_sem);
 	bprm->p = vma->vm_end - sizeof(void *);
 	return 0;

fs/proc/task_mmu.c

@@ -552,6 +552,9 @@ static void show_smap_vma_flags(struct seq_file *m, struct vm_area_struct *vma)
 		[ilog2(VM_GROWSDOWN)]	= "gd",
 		[ilog2(VM_PFNMAP)]	= "pf",
 		[ilog2(VM_DENYWRITE)]	= "dw",
+#ifdef CONFIG_X86_INTEL_MPX
+		[ilog2(VM_MPX)]		= "mp",
+#endif
 		[ilog2(VM_LOCKED)]	= "lo",
 		[ilog2(VM_IO)]		= "io",
 		[ilog2(VM_SEQ_READ)]	= "sr",

include/asm-generic/mm_hooks.h

 /*
- * Define generic no-op hooks for arch_dup_mmap and arch_exit_mmap, to
- * be included in asm-FOO/mmu_context.h for any arch FOO which doesn't
- * need to hook these.
+ * Define generic no-op hooks for arch_dup_mmap, arch_exit_mmap
+ * and arch_unmap to be included in asm-FOO/mmu_context.h for any
+ * arch FOO which doesn't need to hook these.
  */
 #ifndef _ASM_GENERIC_MM_HOOKS_H
 #define _ASM_GENERIC_MM_HOOKS_H
@@ -15,4 +15,15 @@ static inline void arch_exit_mmap(struct mm_struct *mm)
 {
 }
 
+static inline void arch_unmap(struct mm_struct *mm,
+			struct vm_area_struct *vma,
+			unsigned long start, unsigned long end)
+{
+}
+
+static inline void arch_bprm_mm_init(struct mm_struct *mm,
+				     struct vm_area_struct *vma)
+{
+}
+
 #endif	/* _ASM_GENERIC_MM_HOOKS_H */

include/linux/mm.h

@@ -128,6 +128,7 @@ extern unsigned int kobjsize(const void *objp);
 #define VM_HUGETLB	0x00400000	/* Huge TLB Page VM */
 #define VM_NONLINEAR	0x00800000	/* Is non-linear (remap_file_pages) */
 #define VM_ARCH_1	0x01000000	/* Architecture-specific flag */
+#define VM_ARCH_2	0x02000000
 #define VM_DONTDUMP	0x04000000	/* Do not include in the core dump */
 
 #ifdef CONFIG_MEM_SOFT_DIRTY
@@ -155,6 +156,11 @@ extern unsigned int kobjsize(const void *objp);
 # define VM_MAPPED_COPY	VM_ARCH_1	/* T if mapped copy of data (nommu mmap) */
 #endif
 
+#if defined(CONFIG_X86)
+/* MPX specific bounds table or bounds directory */
+# define VM_MPX		VM_ARCH_2
+#endif
+
 #ifndef VM_GROWSUP
 # define VM_GROWSUP	VM_NONE
 #endif

include/linux/mm_types.h

@@ -454,6 +454,10 @@ struct mm_struct {
 	bool tlb_flush_pending;
 #endif
 	struct uprobes_state uprobes_state;
+#ifdef CONFIG_X86_INTEL_MPX
+	/* address of the bounds directory */
+	void __user *bd_addr;
+#endif
 };
 
 static inline void mm_init_cpumask(struct mm_struct *mm)

include/uapi/asm-generic/siginfo.h

@@ -91,6 +91,10 @@ typedef struct siginfo {
 			int _trapno;	/* TRAP # which caused the signal */
 #endif
 			short _addr_lsb; /* LSB of the reported address */
+			struct {
+				void __user *_lower;
+				void __user *_upper;
+			} _addr_bnd;
 		} _sigfault;
 
 		/* SIGPOLL */
@@ -131,6 +135,8 @@ typedef struct siginfo {
 #define si_trapno	_sifields._sigfault._trapno
 #endif
 #define si_addr_lsb	_sifields._sigfault._addr_lsb
+#define si_lower	_sifields._sigfault._addr_bnd._lower
+#define si_upper	_sifields._sigfault._addr_bnd._upper
 #define si_band		_sifields._sigpoll._band
 #define si_fd		_sifields._sigpoll._fd
 #ifdef __ARCH_SIGSYS
@@ -199,7 +205,8 @@ typedef struct siginfo {
  */
 #define SEGV_MAPERR	(__SI_FAULT|1)	/* address not mapped to object */
 #define SEGV_ACCERR	(__SI_FAULT|2)	/* invalid permissions for mapped object */
-#define NSIGSEGV	2
+#define SEGV_BNDERR	(__SI_FAULT|3)  /* failed address bound checks */
+#define NSIGSEGV	3
 
 /*
  * SIGBUS si_codes

include/uapi/linux/prctl.h

@@ -179,4 +179,10 @@ struct prctl_mm_map {
 #define PR_SET_THP_DISABLE	41
 #define PR_GET_THP_DISABLE	42
 
+/*
+ * Tell the kernel to start/stop helping userspace manage bounds tables.
+ */
+#define PR_MPX_ENABLE_MANAGEMENT  43
+#define PR_MPX_DISABLE_MANAGEMENT 44
+
 #endif /* _LINUX_PRCTL_H */

kernel/signal.c

@@ -2755,6 +2755,10 @@ int copy_siginfo_to_user(siginfo_t __user *to, const siginfo_t *from)
 		 */
 		if (from->si_code == BUS_MCEERR_AR || from->si_code == BUS_MCEERR_AO)
 			err |= __put_user(from->si_addr_lsb, &to->si_addr_lsb);
+#endif
+#ifdef SEGV_BNDERR
+		err |= __put_user(from->si_lower, &to->si_lower);
+		err |= __put_user(from->si_upper, &to->si_upper);
 #endif
 		break;
 	case __SI_CHLD:

kernel/sys.c

@@ -91,6 +91,12 @@
 #ifndef SET_TSC_CTL
 # define SET_TSC_CTL(a)		(-EINVAL)
 #endif
+#ifndef MPX_ENABLE_MANAGEMENT
+# define MPX_ENABLE_MANAGEMENT(a)	(-EINVAL)
+#endif
+#ifndef MPX_DISABLE_MANAGEMENT
+# define MPX_DISABLE_MANAGEMENT(a)	(-EINVAL)
+#endif
 
 /*
  * this is where the system-wide overflow UID and GID are defined, for
@@ -2203,6 +2209,12 @@ SYSCALL_DEFINE5(prctl, int, option, unsigned long, arg2, unsigned long, arg3,
 			me->mm->def_flags &= ~VM_NOHUGEPAGE;
 		up_write(&me->mm->mmap_sem);
 		break;
+	case PR_MPX_ENABLE_MANAGEMENT:
+		error = MPX_ENABLE_MANAGEMENT(me);
+		break;
+	case PR_MPX_DISABLE_MANAGEMENT:
+		error = MPX_DISABLE_MANAGEMENT(me);
+		break;
 	default:
 		error = -EINVAL;
 		break;

mm/mmap.c

@@ -2601,6 +2601,8 @@ int do_munmap(struct mm_struct *mm, unsigned long start, size_t len)
 	detach_vmas_to_be_unmapped(mm, vma, prev, end);
 	unmap_region(mm, vma, prev, start, end);
 
+	arch_unmap(mm, vma, start, end);
+
 	/* Fix up all other VM information */
 	remove_vma_list(mm, vma);