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

7 files changed, 128 insertions, 15 deletions

diff --git a/arch/x86/kernel/cpu/perf_event_intel_ds.c b/arch/x86/kernel/cpu/perf_event_intel_ds.c
index 495ae9793628..3c895d480cd7 100644
--- a/arch/x86/kernel/cpu/perf_event_intel_ds.c
+++ b/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) {
diff --git a/arch/x86/kernel/cpu/perf_event_intel_lbr.c b/arch/x86/kernel/cpu/perf_event_intel_lbr.c
index 45fa730a5283..58f1a94beaf0 100644
--- a/arch/x86/kernel/cpu/perf_event_intel_lbr.c
+++ b/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;
@@ -505,10 +507,19 @@ 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;
+		}
 	}
 
 	/*
@@ -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:
diff --git a/arch/x86/kernel/kprobes/core.c b/arch/x86/kernel/kprobes/core.c
index 67e6d19ef1be..f7e3cd50ece0 100644
--- a/arch/x86/kernel/kprobes/core.c
+++ b/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
diff --git a/arch/x86/kernel/kprobes/opt.c b/arch/x86/kernel/kprobes/opt.c
index f1314d0bcf0a..7c523bbf3dc8 100644
--- a/arch/x86/kernel/kprobes/opt.c
+++ b/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)
diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c
index ab08aa2276fb..214245d6b996 100644
--- a/arch/x86/kernel/setup.c
+++ b/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);
diff --git a/arch/x86/kernel/traps.c b/arch/x86/kernel/traps.c
index 07ab8e9733c5..a9ae20579895 100644
--- a/arch/x86/kernel/traps.c
+++ b/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)
 {
diff --git a/arch/x86/kernel/uprobes.c b/arch/x86/kernel/uprobes.c
index 5d1cbfe4ae58..8b96a947021f 100644
--- a/arch/x86/kernel/uprobes.c
+++ b/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)))