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

Pull user-space probe instrumentation from Ingo Molnar:
 "The uprobes code originates from SystemTap and has been used for years
  in Fedora and RHEL kernels.  This version is much rewritten, reviews
  from PeterZ, Oleg and myself shaped the end result.

  This tree includes uprobes support in 'perf probe' - but SystemTap
  (and other tools) can take advantage of user probe points as well.

  Sample usage of uprobes via perf, for example to profile malloc()
  calls without modifying user-space binaries.

  First boot a new kernel with CONFIG_UPROBE_EVENT=y enabled.

  If you don't know which function you want to probe you can pick one
  from 'perf top' or can get a list all functions that can be probed
  within libc (binaries can be specified as well):

	$ perf probe -F -x /lib/libc.so.6

  To probe libc's malloc():

	$ perf probe -x /lib64/libc.so.6 malloc
	Added new event:
	probe_libc:malloc    (on 0x7eac0)

  You can now use it in all perf tools, such as:

	perf record -e probe_libc:malloc -aR sleep 1

  Make use of it to create a call graph (as the flat profile is going to
  look very boring):

	$ perf record -e probe_libc:malloc -gR make
	[ perf record: Woken up 173 times to write data ]
	[ perf record: Captured and wrote 44.190 MB perf.data (~1930712

	$ perf report | less

	  32.03%            git  libc-2.15.so   [.] malloc
	                    |
	                    --- malloc

	  29.49%            cc1  libc-2.15.so   [.] malloc
	                    |
	                    --- malloc
	                       |
	                       |--0.95%-- 0x208eb1000000000
	                       |
	                       |--0.63%-- htab_traverse_noresize

	  11.04%             as  libc-2.15.so   [.] malloc
	                     |
	                     --- malloc
	                        |

	   7.15%             ld  libc-2.15.so   [.] malloc
	                     |
	                     --- malloc
	                        |

	   5.07%             sh  libc-2.15.so   [.] malloc
	                     |
	                     --- malloc
	                        |
	   4.99%  python-config  libc-2.15.so   [.] malloc
	          |
	          --- malloc
	             |
	   4.54%           make  libc-2.15.so   [.] malloc
	                   |
	                   --- malloc
	                      |
	                      |--7.34%-- glob
	                      |          |
	                      |          |--93.18%-- 0x41588f
	                      |          |
	                      |           --6.82%-- glob
	                      |                     0x41588f

	   ...

  Or:

	$ perf report -g flat | less

	# Overhead        Command  Shared Object      Symbol
	# ........  .............  .............  ..........
	#
	  32.03%            git  libc-2.15.so   [.] malloc
	          27.19%
	              malloc

	  29.49%            cc1  libc-2.15.so   [.] malloc
	          24.77%
	              malloc

	  11.04%             as  libc-2.15.so   [.] malloc
	          11.02%
	              malloc

	   7.15%             ld  libc-2.15.so   [.] malloc
	           6.57%
	              malloc

	 ...

  The core uprobes design is fairly straightforward: uprobes probe
  points register themselves at (inode:offset) addresses of
  libraries/binaries, after which all existing (or new) vmas that map
  that address will have a software breakpoint injected at that address.
  vmas are COW-ed to preserve original content.  The probe points are
  kept in an rbtree.

  If user-space executes the probed inode:offset instruction address
  then an event is generated which can be recovered from the regular
  perf event channels and mmap-ed ring-buffer.

  Multiple probes at the same address are supported, they create a
  dynamic callback list of event consumers.

  The basic model is further complicated by the XOL speedup: the
  original instruction that is probed is copied (in an architecture
  specific fashion) and executed out of line when the probe triggers.
  The XOL area is a single vma per process, with a fixed number of
  entries (which limits probe execution parallelism).

  The API: uprobes are installed/removed via
  /sys/kernel/debug/tracing/uprobe_events, the API is integrated to
  align with the kprobes interface as much as possible, but is separate
  to it.

  Injecting a probe point is privileged operation, which can be relaxed
  by setting perf_paranoid to -1.

  You can use multiple probes as well and mix them with kprobes and
  regular PMU events or tracepoints, when instrumenting a task."

Fix up trivial conflicts in mm/memory.c due to previous cleanup of
unmap_single_vma().

* 'perf-uprobes-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (21 commits)
  perf probe: Detect probe target when m/x options are absent
  perf probe: Provide perf interface for uprobes
  tracing: Fix kconfig warning due to a typo
  tracing: Provide trace events interface for uprobes
  tracing: Extract out common code for kprobes/uprobes trace events
  tracing: Modify is_delete, is_return from int to bool
  uprobes/core: Decrement uprobe count before the pages are unmapped
  uprobes/core: Make background page replacement logic account for rss_stat counters
  uprobes/core: Optimize probe hits with the help of a counter
  uprobes/core: Allocate XOL slots for uprobes use
  uprobes/core: Handle breakpoint and singlestep exceptions
  uprobes/core: Rename bkpt to swbp
  uprobes/core: Make order of function parameters consistent across functions
  uprobes/core: Make macro names consistent
  uprobes: Update copyright notices
  uprobes/core: Move insn to arch specific structure
  uprobes/core: Remove uprobe_opcode_sz
  uprobes/core: Make instruction tables volatile
  uprobes: Move to kernel/events/
  uprobes/core: Clean up, refactor and improve the code
  ...

30 files changed, 5048 insertions, 979 deletions

diff --git a/Documentation/trace/uprobetracer.txt b/Documentation/trace/uprobetracer.txt
new file mode 100644
index 000000000000..24ce6823a09e
--- /dev/null
+++ b/Documentation/trace/uprobetracer.txt
@@ -0,0 +1,113 @@
+		Uprobe-tracer: Uprobe-based Event Tracing
+		=========================================
+                 Documentation written by Srikar Dronamraju
+
+Overview
+--------
+Uprobe based trace events are similar to kprobe based trace events.
+To enable this feature, build your kernel with CONFIG_UPROBE_EVENT=y.
+
+Similar to the kprobe-event tracer, this doesn't need to be activated via
+current_tracer. Instead of that, add probe points via
+/sys/kernel/debug/tracing/uprobe_events, and enable it via
+/sys/kernel/debug/tracing/events/uprobes/<EVENT>/enabled.
+
+However unlike kprobe-event tracer, the uprobe event interface expects the
+user to calculate the offset of the probepoint in the object
+
+Synopsis of uprobe_tracer
+-------------------------
+  p[:[GRP/]EVENT] PATH:SYMBOL[+offs] [FETCHARGS]	: Set a probe
+
+ GRP		: Group name. If omitted, use "uprobes" for it.
+ EVENT		: Event name. If omitted, the event name is generated
+		  based on SYMBOL+offs.
+ PATH		: path to an executable or a library.
+ SYMBOL[+offs]	: Symbol+offset where the probe is inserted.
+
+ FETCHARGS	: Arguments. Each probe can have up to 128 args.
+  %REG		: Fetch register REG
+
+Event Profiling
+---------------
+ You can check the total number of probe hits and probe miss-hits via
+/sys/kernel/debug/tracing/uprobe_profile.
+ The first column is event name, the second is the number of probe hits,
+the third is the number of probe miss-hits.
+
+Usage examples
+--------------
+To add a probe as a new event, write a new definition to uprobe_events
+as below.
+
+  echo 'p: /bin/bash:0x4245c0' > /sys/kernel/debug/tracing/uprobe_events
+
+ This sets a uprobe at an offset of 0x4245c0 in the executable /bin/bash
+
+  echo > /sys/kernel/debug/tracing/uprobe_events
+
+ This clears all probe points.
+
+The following example shows how to dump the instruction pointer and %ax
+a register at the probed text address.  Here we are trying to probe
+function zfree in /bin/zsh
+
+    # cd /sys/kernel/debug/tracing/
+    # cat /proc/`pgrep  zsh`/maps | grep /bin/zsh | grep r-xp
+    00400000-0048a000 r-xp 00000000 08:03 130904 /bin/zsh
+    # objdump -T /bin/zsh | grep -w zfree
+    0000000000446420 g    DF .text  0000000000000012  Base        zfree
+
+0x46420 is the offset of zfree in object /bin/zsh that is loaded at
+0x00400000. Hence the command to probe would be :
+
+    # echo 'p /bin/zsh:0x46420 %ip %ax' > uprobe_events
+
+Please note: User has to explicitly calculate the offset of the probepoint
+in the object. We can see the events that are registered by looking at the
+uprobe_events file.
+
+    # cat uprobe_events
+    p:uprobes/p_zsh_0x46420 /bin/zsh:0x00046420 arg1=%ip arg2=%ax
+
+The format of events can be seen by viewing the file events/uprobes/p_zsh_0x46420/format
+
+    # cat events/uprobes/p_zsh_0x46420/format
+    name: p_zsh_0x46420
+    ID: 922
+    format:
+	field:unsigned short common_type;	offset:0;	size:2;	signed:0;
+	field:unsigned char common_flags;	offset:2;	size:1;	signed:0;
+	field:unsigned char common_preempt_count;	offset:3;	size:1;	signed:0;
+	field:int common_pid;	offset:4;	size:4;	signed:1;
+	field:int common_padding;	offset:8;	size:4;	signed:1;
+
+	field:unsigned long __probe_ip;	offset:12;	size:4;	signed:0;
+	field:u32 arg1;	offset:16;	size:4;	signed:0;
+	field:u32 arg2;	offset:20;	size:4;	signed:0;
+
+    print fmt: "(%lx) arg1=%lx arg2=%lx", REC->__probe_ip, REC->arg1, REC->arg2
+
+Right after definition, each event is disabled by default. For tracing these
+events, you need to enable it by:
+
+    # echo 1 > events/uprobes/enable
+
+Lets disable the event after sleeping for some time.
+    # sleep 20
+    # echo 0 > events/uprobes/enable
+
+And you can see the traced information via /sys/kernel/debug/tracing/trace.
+
+    # cat trace
+    # tracer: nop
+    #
+    #           TASK-PID    CPU#    TIMESTAMP  FUNCTION
+    #              | |       |          |         |
+                 zsh-24842 [006] 258544.995456: p_zsh_0x46420: (0x446420) arg1=446421 arg2=79
+                 zsh-24842 [007] 258545.000270: p_zsh_0x46420: (0x446420) arg1=446421 arg2=79
+                 zsh-24842 [002] 258545.043929: p_zsh_0x46420: (0x446420) arg1=446421 arg2=79
+                 zsh-24842 [004] 258547.046129: p_zsh_0x46420: (0x446420) arg1=446421 arg2=79
+
+Each line shows us probes were triggered for a pid 24842 with ip being
+0x446421 and contents of ax register being 79.
diff --git a/arch/Kconfig b/arch/Kconfig
index 1f9461b9cc89..e9a910876cda 100644
--- a/arch/Kconfig
+++ b/arch/Kconfig
@@ -76,6 +76,23 @@ config OPTPROBES
 	depends on KPROBES && HAVE_OPTPROBES
 	depends on !PREEMPT
 
+config UPROBES
+	bool "Transparent user-space probes (EXPERIMENTAL)"
+	depends on UPROBE_EVENT && PERF_EVENTS
+	default n
+	help
+	  Uprobes is the user-space counterpart to kprobes: they
+	  enable instrumentation applications (such as 'perf probe')
+	  to establish unintrusive probes in user-space binaries and
+	  libraries, by executing handler functions when the probes
+	  are hit by user-space applications.
+
+	  ( These probes come in the form of single-byte breakpoints,
+	    managed by the kernel and kept transparent to the probed
+	    application. )
+
+	  If in doubt, say "N".
+
 config HAVE_EFFICIENT_UNALIGNED_ACCESS
 	bool
 	help
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index d6168994e115..0b2d5f24c946 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -87,7 +87,7 @@ config X86
 	select BUILDTIME_EXTABLE_SORT
 
 config INSTRUCTION_DECODER
-	def_bool (KPROBES || PERF_EVENTS)
+	def_bool (KPROBES || PERF_EVENTS || UPROBES)
 
 config OUTPUT_FORMAT
 	string
@@ -243,6 +243,9 @@ config ARCH_CPU_PROBE_RELEASE
 	def_bool y
 	depends on HOTPLUG_CPU
 
+config ARCH_SUPPORTS_UPROBES
+	def_bool y
+
 source "init/Kconfig"
 source "kernel/Kconfig.freezer"
 
diff --git a/arch/x86/include/asm/thread_info.h b/arch/x86/include/asm/thread_info.h
index 3c9aebc00d39..5c25de07cba8 100644
--- a/arch/x86/include/asm/thread_info.h
+++ b/arch/x86/include/asm/thread_info.h
@@ -85,6 +85,7 @@ struct thread_info {
 #define TIF_SECCOMP		8	/* secure computing */
 #define TIF_MCE_NOTIFY		10	/* notify userspace of an MCE */
 #define TIF_USER_RETURN_NOTIFY	11	/* notify kernel of userspace return */
+#define TIF_UPROBE		12	/* breakpointed or singlestepping */
 #define TIF_NOTSC		16	/* TSC is not accessible in userland */
 #define TIF_IA32		17	/* IA32 compatibility process */
 #define TIF_FORK		18	/* ret_from_fork */
@@ -109,6 +110,7 @@ struct thread_info {
 #define _TIF_SECCOMP		(1 << TIF_SECCOMP)
 #define _TIF_MCE_NOTIFY		(1 << TIF_MCE_NOTIFY)
 #define _TIF_USER_RETURN_NOTIFY	(1 << TIF_USER_RETURN_NOTIFY)
+#define _TIF_UPROBE		(1 << TIF_UPROBE)
 #define _TIF_NOTSC		(1 << TIF_NOTSC)
 #define _TIF_IA32		(1 << TIF_IA32)
 #define _TIF_FORK		(1 << TIF_FORK)
diff --git a/arch/x86/include/asm/uprobes.h b/arch/x86/include/asm/uprobes.h
new file mode 100644
index 000000000000..1e9bed14f7ae
--- /dev/null
+++ b/arch/x86/include/asm/uprobes.h
@@ -0,0 +1,57 @@
+#ifndef _ASM_UPROBES_H
+#define _ASM_UPROBES_H
+/*
+ * User-space Probes (UProbes) for x86
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA.
+ *
+ * Copyright (C) IBM Corporation, 2008-2011
+ * Authors:
+ *	Srikar Dronamraju
+ *	Jim Keniston
+ */
+
+#include <linux/notifier.h>
+
+typedef u8 uprobe_opcode_t;
+
+#define MAX_UINSN_BYTES			  16
+#define UPROBE_XOL_SLOT_BYTES		 128	/* to keep it cache aligned */
+
+#define UPROBE_SWBP_INSN		0xcc
+#define UPROBE_SWBP_INSN_SIZE		   1
+
+struct arch_uprobe {
+	u16				fixups;
+	u8				insn[MAX_UINSN_BYTES];
+#ifdef CONFIG_X86_64
+	unsigned long			rip_rela_target_address;
+#endif
+};
+
+struct arch_uprobe_task {
+	unsigned long			saved_trap_nr;
+#ifdef CONFIG_X86_64
+	unsigned long			saved_scratch_register;
+#endif
+};
+
+extern int  arch_uprobe_analyze_insn(struct arch_uprobe *aup, struct mm_struct *mm);
+extern int  arch_uprobe_pre_xol(struct arch_uprobe *aup, struct pt_regs *regs);
+extern int  arch_uprobe_post_xol(struct arch_uprobe *aup, struct pt_regs *regs);
+extern bool arch_uprobe_xol_was_trapped(struct task_struct *tsk);
+extern int  arch_uprobe_exception_notify(struct notifier_block *self, unsigned long val, void *data);
+extern void arch_uprobe_abort_xol(struct arch_uprobe *aup, struct pt_regs *regs);
+#endif	/* _ASM_UPROBES_H */
diff --git a/arch/x86/kernel/Makefile b/arch/x86/kernel/Makefile
index bb8529275aab..9bba5b79902b 100644
--- a/arch/x86/kernel/Makefile
+++ b/arch/x86/kernel/Makefile
@@ -100,6 +100,7 @@ obj-$(CONFIG_X86_CHECK_BIOS_CORRUPTION) += check.o
 
 obj-$(CONFIG_SWIOTLB)			+= pci-swiotlb.o
 obj-$(CONFIG_OF)			+= devicetree.o
+obj-$(CONFIG_UPROBES)			+= uprobes.o
 
 ###
 # 64 bit specific files
diff --git a/arch/x86/kernel/signal.c b/arch/x86/kernel/signal.c
index b68ccadd2ff4..965dfda0fd5e 100644
--- a/arch/x86/kernel/signal.c
+++ b/arch/x86/kernel/signal.c
@@ -18,6 +18,7 @@
 #include <linux/personality.h>
 #include <linux/uaccess.h>
 #include <linux/user-return-notifier.h>
+#include <linux/uprobes.h>
 
 #include <asm/processor.h>
 #include <asm/ucontext.h>
@@ -814,6 +815,11 @@ do_notify_resume(struct pt_regs *regs, void *unused, __u32 thread_info_flags)
 		mce_notify_process();
 #endif /* CONFIG_X86_64 && CONFIG_X86_MCE */
 
+	if (thread_info_flags & _TIF_UPROBE) {
+		clear_thread_flag(TIF_UPROBE);
+		uprobe_notify_resume(regs);
+	}
+
 	/* deal with pending signal delivery */
 	if (thread_info_flags & _TIF_SIGPENDING)
 		do_signal(regs);
diff --git a/arch/x86/kernel/uprobes.c b/arch/x86/kernel/uprobes.c
new file mode 100644
index 000000000000..dc4e910a7d96
--- /dev/null
+++ b/arch/x86/kernel/uprobes.c
@@ -0,0 +1,674 @@
+/*
+ * User-space Probes (UProbes) for x86
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA.
+ *
+ * Copyright (C) IBM Corporation, 2008-2011
+ * Authors:
+ *	Srikar Dronamraju
+ *	Jim Keniston
+ */
+#include <linux/kernel.h>
+#include <linux/sched.h>
+#include <linux/ptrace.h>
+#include <linux/uprobes.h>
+#include <linux/uaccess.h>
+
+#include <linux/kdebug.h>
+#include <asm/processor.h>
+#include <asm/insn.h>
+
+/* Post-execution fixups. */
+
+/* No fixup needed */
+#define UPROBE_FIX_NONE		0x0
+
+/* Adjust IP back to vicinity of actual insn */
+#define UPROBE_FIX_IP		0x1
+
+/* Adjust the return address of a call insn */
+#define UPROBE_FIX_CALL	0x2
+
+#define UPROBE_FIX_RIP_AX	0x8000
+#define UPROBE_FIX_RIP_CX	0x4000
+
+#define	UPROBE_TRAP_NR		UINT_MAX
+
+/* Adaptations for mhiramat x86 decoder v14. */
+#define OPCODE1(insn)		((insn)->opcode.bytes[0])
+#define OPCODE2(insn)		((insn)->opcode.bytes[1])
+#define OPCODE3(insn)		((insn)->opcode.bytes[2])
+#define MODRM_REG(insn)		X86_MODRM_REG(insn->modrm.value)
+
+#define W(row, b0, b1, b2, b3, b4, b5, b6, b7, b8, b9, ba, bb, bc, bd, be, bf)\
+	(((b0##UL << 0x0)|(b1##UL << 0x1)|(b2##UL << 0x2)|(b3##UL << 0x3) |   \
+	  (b4##UL << 0x4)|(b5##UL << 0x5)|(b6##UL << 0x6)|(b7##UL << 0x7) |   \
+	  (b8##UL << 0x8)|(b9##UL << 0x9)|(ba##UL << 0xa)|(bb##UL << 0xb) |   \
+	  (bc##UL << 0xc)|(bd##UL << 0xd)|(be##UL << 0xe)|(bf##UL << 0xf))    \
+	 << (row % 32))
+
+/*
+ * Good-instruction tables for 32-bit apps.  This is non-const and volatile
+ * to keep gcc from statically optimizing it out, as variable_test_bit makes
+ * some versions of gcc to think only *(unsigned long*) is used.
+ */
+static volatile u32 good_insns_32[256 / 32] = {
+	/*      0  1  2  3  4  5  6  7  8  9  a  b  c  d  e  f         */
+	/*      ----------------------------------------------         */
+	W(0x00, 1, 1, 1, 1, 1, 1, 1, 0, 1, 1, 1, 1, 1, 1, 1, 0) | /* 00 */
+	W(0x10, 1, 1, 1, 1, 1, 1, 1, 0, 1, 1, 1, 1, 1, 1, 1, 0) , /* 10 */
+	W(0x20, 1, 1, 1, 1, 1, 1, 0, 1, 1, 1, 1, 1, 1, 1, 0, 1) | /* 20 */
+	W(0x30, 1, 1, 1, 1, 1, 1, 0, 1, 1, 1, 1, 1, 1, 1, 0, 1) , /* 30 */
+	W(0x40, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1) | /* 40 */
+	W(0x50, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1) , /* 50 */
+	W(0x60, 1, 1, 1, 0, 1, 1, 0, 0, 1, 1, 1, 1, 0, 0, 0, 0) | /* 60 */
+	W(0x70, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1) , /* 70 */
+	W(0x80, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1) | /* 80 */
+	W(0x90, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1) , /* 90 */
+	W(0xa0, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1) | /* a0 */
+	W(0xb0, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1) , /* b0 */
+	W(0xc0, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0, 0, 0, 0) | /* c0 */
+	W(0xd0, 1, 1, 1, 1, 1, 1, 0, 1, 1, 1, 1, 1, 1, 1, 1, 1) , /* d0 */
+	W(0xe0, 1, 1, 1, 1, 0, 0, 0, 0, 1, 1, 1, 1, 0, 0, 0, 0) | /* e0 */
+	W(0xf0, 0, 0, 1, 1, 0, 1, 1, 1, 1, 1, 0, 0, 1, 1, 1, 1)   /* f0 */
+	/*      ----------------------------------------------         */
+	/*      0  1  2  3  4  5  6  7  8  9  a  b  c  d  e  f         */
+};
+
+/* Using this for both 64-bit and 32-bit apps */
+static volatile u32 good_2byte_insns[256 / 32] = {
+	/*      0  1  2  3  4  5  6  7  8  9  a  b  c  d  e  f         */
+	/*      ----------------------------------------------         */
+	W(0x00, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 1) | /* 00 */
+	W(0x10, 1, 1, 1, 1, 1, 1, 1, 1, 0, 1, 1, 1, 1, 1, 1, 1) , /* 10 */
+	W(0x20, 1, 1, 1, 1, 0, 0, 0, 0, 1, 1, 1, 1, 1, 1, 1, 1) | /* 20 */
+	W(0x30, 0, 1, 1, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0) , /* 30 */
+	W(0x40, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1) | /* 40 */
+	W(0x50, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1) , /* 50 */
+	W(0x60, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1) | /* 60 */
+	W(0x70, 1, 1, 1, 1, 1, 1, 1, 1, 0, 0, 0, 0, 0, 0, 1, 1) , /* 70 */
+	W(0x80, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1) | /* 80 */
+	W(0x90, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1) , /* 90 */
+	W(0xa0, 1, 1, 1, 1, 1, 1, 0, 0, 1, 1, 1, 1, 1, 1, 0, 1) | /* a0 */
+	W(0xb0, 1, 1, 1, 1, 1, 1, 1, 1, 0, 1, 1, 1, 1, 1, 1, 1) , /* b0 */
+	W(0xc0, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1) | /* c0 */
+	W(0xd0, 0, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1) , /* d0 */
+	W(0xe0, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1) | /* e0 */
+	W(0xf0, 0, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0)   /* f0 */
+	/*      ----------------------------------------------         */
+	/*      0  1  2  3  4  5  6  7  8  9  a  b  c  d  e  f         */
+};
+
+#ifdef CONFIG_X86_64
+/* Good-instruction tables for 64-bit apps */
+static volatile u32 good_insns_64[256 / 32] = {
+	/*      0  1  2  3  4  5  6  7  8  9  a  b  c  d  e  f         */
+	/*      ----------------------------------------------         */
+	W(0x00, 1, 1, 1, 1, 1, 1, 0, 0, 1, 1, 1, 1, 1, 1, 0, 0) | /* 00 */
+	W(0x10, 1, 1, 1, 1, 1, 1, 0, 0, 1, 1, 1, 1, 1, 1, 0, 0) , /* 10 */
+	W(0x20, 1, 1, 1, 1, 1, 1, 0, 0, 1, 1, 1, 1, 1, 1, 0, 0) | /* 20 */
+	W(0x30, 1, 1, 1, 1, 1, 1, 0, 0, 1, 1, 1, 1, 1, 1, 0, 0) , /* 30 */
+	W(0x40, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0) | /* 40 */
+	W(0x50, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1) , /* 50 */
+	W(0x60, 0, 0, 0, 1, 1, 1, 0, 0, 1, 1, 1, 1, 0, 0, 0, 0) | /* 60 */
+	W(0x70, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1) , /* 70 */
+	W(0x80, 1, 1, 0, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1) | /* 80 */
+	W(0x90, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1) , /* 90 */
+	W(0xa0, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1) | /* a0 */
+	W(0xb0, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1) , /* b0 */
+	W(0xc0, 1, 1, 1, 1, 0, 0, 1, 1, 1, 1, 1, 1, 0, 0, 0, 0) | /* c0 */
+	W(0xd0, 1, 1, 1, 1, 0, 0, 0, 1, 1, 1, 1, 1, 1, 1, 1, 1) , /* d0 */
+	W(0xe0, 1, 1, 1, 1, 0, 0, 0, 0, 1, 1, 1, 1, 0, 0, 0, 0) | /* e0 */
+	W(0xf0, 0, 0, 1, 1, 0, 1, 1, 1, 1, 1, 0, 0, 1, 1, 1, 1)   /* f0 */
+	/*      ----------------------------------------------         */
+	/*      0  1  2  3  4  5  6  7  8  9  a  b  c  d  e  f         */
+};
+#endif
+#undef W
+
+/*
+ * opcodes we'll probably never support:
+ *
+ *  6c-6d, e4-e5, ec-ed - in
+ *  6e-6f, e6-e7, ee-ef - out
+ *  cc, cd - int3, int
+ *  cf - iret
+ *  d6 - illegal instruction
+ *  f1 - int1/icebp
+ *  f4 - hlt
+ *  fa, fb - cli, sti
+ *  0f - lar, lsl, syscall, clts, sysret, sysenter, sysexit, invd, wbinvd, ud2
+ *
+ * invalid opcodes in 64-bit mode:
+ *
+ *  06, 0e, 16, 1e, 27, 2f, 37, 3f, 60-62, 82, c4-c5, d4-d5
+ *  63 - we support this opcode in x86_64 but not in i386.
+ *
+ * opcodes we may need to refine support for:
+ *
+ *  0f - 2-byte instructions: For many of these instructions, the validity
+ *  depends on the prefix and/or the reg field.  On such instructions, we
+ *  just consider the opcode combination valid if it corresponds to any
+ *  valid instruction.
+ *
+ *  8f - Group 1 - only reg = 0 is OK
+ *  c6-c7 - Group 11 - only reg = 0 is OK
+ *  d9-df - fpu insns with some illegal encodings
+ *  f2, f3 - repnz, repz prefixes.  These are also the first byte for
+ *  certain floating-point instructions, such as addsd.
+ *
+ *  fe - Group 4 - only reg = 0 or 1 is OK
+ *  ff - Group 5 - only reg = 0-6 is OK
+ *
+ * others -- Do we need to support these?
+ *
+ *  0f - (floating-point?) prefetch instructions
+ *  07, 17, 1f - pop es, pop ss, pop ds
+ *  26, 2e, 36, 3e - es:, cs:, ss:, ds: segment prefixes --
+ *	but 64 and 65 (fs: and gs:) seem to be used, so we support them
+ *  67 - addr16 prefix
+ *  ce - into
+ *  f0 - lock prefix
+ */
+
+/*
+ * TODO:
+ * - Where necessary, examine the modrm byte and allow only valid instructions
+ * in the different Groups and fpu instructions.
+ */
+
+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 */
+			return true;
+		}
+	}
+	return false;
+}
+
+static int validate_insn_32bits(struct arch_uprobe *auprobe, struct insn *insn)
+{
+	insn_init(insn, auprobe->insn, false);
+
+	/* Skip good instruction prefixes; reject "bad" ones. */
+	insn_get_opcode(insn);
+	if (is_prefix_bad(insn))
+		return -ENOTSUPP;
+
+	if (test_bit(OPCODE1(insn), (unsigned long *)good_insns_32))
+		return 0;
+
+	if (insn->opcode.nbytes == 2) {
+		if (test_bit(OPCODE2(insn), (unsigned long *)good_2byte_insns))
+			return 0;
+	}
+
+	return -ENOTSUPP;
+}
+
+/*
+ * Figure out which fixups arch_uprobe_post_xol() will need to perform, and
+ * annotate arch_uprobe->fixups accordingly.  To start with,
+ * arch_uprobe->fixups is either zero or it reflects rip-related fixups.
+ */
+static void prepare_fixups(struct arch_uprobe *auprobe, struct insn *insn)
+{
+	bool fix_ip = true, fix_call = false;	/* defaults */
+	int reg;
+
+	insn_get_opcode(insn);	/* should be a nop */
+
+	switch (OPCODE1(insn)) {
+	case 0xc3:		/* ret/lret */
+	case 0xcb:
+	case 0xc2:
+	case 0xca:
+		/* ip is correct */
+		fix_ip = false;
+		break;
+	case 0xe8:		/* call relative - Fix return addr */
+		fix_call = true;
+		break;
+	case 0x9a:		/* call absolute - Fix return addr, not ip */
+		fix_call = true;
+		fix_ip = false;
+		break;
+	case 0xff:
+		insn_get_modrm(insn);
+		reg = MODRM_REG(insn);
+		if (reg == 2 || reg == 3) {
+			/* call or lcall, indirect */
+			/* Fix return addr; ip is correct. */
+			fix_call = true;
+			fix_ip = false;
+		} else if (reg == 4 || reg == 5) {
+			/* jmp or ljmp, indirect */
+			/* ip is correct. */
+			fix_ip = false;
+		}
+		break;
+	case 0xea:		/* jmp absolute -- ip is correct */
+		fix_ip = false;
+		break;
+	default:
+		break;
+	}
+	if (fix_ip)
+		auprobe->fixups |= UPROBE_FIX_IP;
+	if (fix_call)
+		auprobe->fixups |= UPROBE_FIX_CALL;
+}
+
+#ifdef CONFIG_X86_64
+/*
+ * If arch_uprobe->insn doesn't use rip-relative addressing, return
+ * immediately.  Otherwise, rewrite the instruction so that it accesses
+ * its memory operand indirectly through a scratch register.  Set
+ * arch_uprobe->fixups and arch_uprobe->rip_rela_target_address
+ * accordingly.  (The contents of the scratch register will be saved
+ * before we single-step the modified instruction, and restored
+ * afterward.)
+ *
+ * We do this because a rip-relative instruction can access only a
+ * relatively small area (+/- 2 GB from the instruction), and the XOL
+ * area typically lies beyond that area.  At least for instructions
+ * that store to memory, we can't execute the original instruction
+ * and "fix things up" later, because the misdirected store could be
+ * disastrous.
+ *
+ * Some useful facts about rip-relative instructions:
+ *
+ *  - There's always a modrm byte.
+ *  - There's never a SIB byte.
+ *  - The displacement is always 4 bytes.
+ */
+static void
+handle_riprel_insn(struct arch_uprobe *auprobe, struct mm_struct *mm, struct insn *insn)
+{
+	u8 *cursor;
+	u8 reg;
+
+	if (mm->context.ia32_compat)
+		return;
+
+	auprobe->rip_rela_target_address = 0x0;
+	if (!insn_rip_relative(insn))
+		return;
+
+	/*
+	 * insn_rip_relative() would have decoded rex_prefix, modrm.
+	 * Clear REX.b bit (extension of MODRM.rm field):
+	 * we want to encode rax/rcx, not r8/r9.
+	 */
+	if (insn->rex_prefix.nbytes) {
+		cursor = auprobe->insn + insn_offset_rex_prefix(insn);
+		*cursor &= 0xfe;	/* Clearing REX.B bit */
+	}
+
+	/*
+	 * Point cursor at the modrm byte.  The next 4 bytes are the
+	 * displacement.  Beyond the displacement, for some instructions,
+	 * is the immediate operand.
+	 */
+	cursor = auprobe->insn + insn_offset_modrm(insn);
+	insn_get_length(insn);
+
+	/*
+	 * Convert from rip-relative addressing to indirect addressing
+	 * via a scratch register.  Change the r/m field from 0x5 (%rip)
+	 * to 0x0 (%rax) or 0x1 (%rcx), and squeeze out the offset field.
+	 */
+	reg = MODRM_REG(insn);
+	if (reg == 0) {
+		/*
+		 * The register operand (if any) is either the A register
+		 * (%rax, %eax, etc.) or (if the 0x4 bit is set in the
+		 * REX prefix) %r8.  In any case, we know the C register
+		 * is NOT the register operand, so we use %rcx (register
+		 * #1) for the scratch register.
+		 */
+		auprobe->fixups = UPROBE_FIX_RIP_CX;
+		/* Change modrm from 00 000 101 to 00 000 001. */
+		*cursor = 0x1;
+	} else {
+		/* Use %rax (register #0) for the scratch register. */
+		auprobe->fixups = UPROBE_FIX_RIP_AX;
+		/* Change modrm from 00 xxx 101 to 00 xxx 000 */
+		*cursor = (reg << 3);
+	}
+
+	/* Target address = address of next instruction + (signed) offset */
+	auprobe->rip_rela_target_address = (long)insn->length + insn->displacement.value;
+
+	/* Displacement field is gone; slide immediate field (if any) over. */
+	if (insn->immediate.nbytes) {
+		cursor++;
+		memmove(cursor, cursor + insn->displacement.nbytes, insn->immediate.nbytes);
+	}
+	return;
+}
+
+static int validate_insn_64bits(struct arch_uprobe *auprobe, struct insn *insn)
+{
+	insn_init(insn, auprobe->insn, true);
+
+	/* Skip good instruction prefixes; reject "bad" ones. */
+	insn_get_opcode(insn);
+	if (is_prefix_bad(insn))
+		return -ENOTSUPP;
+
+	if (test_bit(OPCODE1(insn), (unsigned long *)good_insns_64))
+		return 0;
+
+	if (insn->opcode.nbytes == 2) {
+		if (test_bit(OPCODE2(insn), (unsigned long *)good_2byte_insns))
+			return 0;
+	}
+	return -ENOTSUPP;
+}
+
+static int validate_insn_bits(struct arch_uprobe *auprobe, struct mm_struct *mm, struct insn *insn)
+{
+	if (mm->context.ia32_compat)
+		return validate_insn_32bits(auprobe, insn);
+	return validate_insn_64bits(auprobe, insn);
+}
+#else /* 32-bit: */
+static void handle_riprel_insn(struct arch_uprobe *auprobe, struct mm_struct *mm, struct insn *insn)
+{
+	/* No RIP-relative addressing on 32-bit */
+}
+
+static int validate_insn_bits(struct arch_uprobe *auprobe, struct mm_struct *mm,  struct insn *insn)
+{
+	return validate_insn_32bits(auprobe, insn);
+}
+