kprobes/x86: Support kprobes jump optimization on x86

Introduce x86 arch-specific optimization code, which supports
both of x86-32 and x86-64.

This code also supports safety checking, which decodes whole of
a function in which probe is inserted, and checks following
conditions before optimization:
 - The optimized instructions which will be replaced by a jump instruction
   don't straddle the function boundary.
 - There is no indirect jump instruction, because it will jumps into
   the address range which is replaced by jump operand.
 - There is no jump/loop instruction which jumps into the address range
   which is replaced by jump operand.
 - Don't optimize kprobes if it is in functions into which fixup code will
   jumps.

This uses text_poke_multibyte() which doesn't support modifying
code on NMI/MCE handler. However, since kprobes itself doesn't
support NMI/MCE code probing, it's not a problem.

Changes in v9:
 - Use *_text_reserved() for checking the probe can be optimized.
 - Verify jump address range is in 2G range when preparing slot.
 - Backup original code when switching optimized buffer, instead of
   preparing buffer, because there can be int3 of other probes in
   preparing phase.
 - Check kprobe is disabled in arch_check_optimized_kprobe().
 - Strictly check indirect jump opcodes (ff /4, ff /5).

Changes in v6:
 - Split stop_machine-based jump patching code.
 - Update comments and coding style.

Changes in v5:
 - Introduce stop_machine-based jump replacing.
Signed-off-by: Masami Hiramatsu <mhiramat@redhat.com>
Cc: systemtap <systemtap@sources.redhat.com>
Cc: DLE <dle-develop@lists.sourceforge.net>
Cc: Ananth N Mavinakayanahalli <ananth@in.ibm.com>
Cc: Jim Keniston <jkenisto@us.ibm.com>
Cc: Srikar Dronamraju <srikar@linux.vnet.ibm.com>
Cc: Christoph Hellwig <hch@infradead.org>
Cc: Steven Rostedt <rostedt@goodmis.org>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Anders Kaseorg <andersk@ksplice.com>
Cc: Tim Abbott <tabbott@ksplice.com>
Cc: Andi Kleen <andi@firstfloor.org>
Cc: Jason Baron <jbaron@redhat.com>
Cc: Mathieu Desnoyers <compudj@krystal.dyndns.org>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Ananth N Mavinakayanahalli <ananth@in.ibm.com>
LKML-Reference: <20100225133446.6725.78994.stgit@localhost6.localdomain6>
Signed-off-by: Ingo Molnar <mingo@elte.hu>

arch/x86/Kconfig

@@ -31,6 +31,7 @@ config X86
 	select ARCH_WANT_FRAME_POINTERS
 	select HAVE_DMA_ATTRS
 	select HAVE_KRETPROBES
+	select HAVE_OPTPROBES
 	select HAVE_FTRACE_MCOUNT_RECORD
 	select HAVE_DYNAMIC_FTRACE
 	select HAVE_FUNCTION_TRACER

arch/x86/include/asm/kprobes.h

@@ -33,6 +33,9 @@ struct kprobe;
 typedef u8 kprobe_opcode_t;
 #define BREAKPOINT_INSTRUCTION	0xcc
 #define RELATIVEJUMP_OPCODE 0xe9
+#define RELATIVEJUMP_SIZE 5
+#define RELATIVECALL_OPCODE 0xe8
+#define RELATIVE_ADDR_SIZE 4
 #define MAX_INSN_SIZE 16
 #define MAX_STACK_SIZE 64
 #define MIN_STACK_SIZE(ADDR)					       \
@@ -44,6 +47,17 @@ typedef u8 kprobe_opcode_t;
 
 #define flush_insn_slot(p)	do { } while (0)
 
+/* optinsn template addresses */
+extern kprobe_opcode_t optprobe_template_entry;
+extern kprobe_opcode_t optprobe_template_val;
+extern kprobe_opcode_t optprobe_template_call;
+extern kprobe_opcode_t optprobe_template_end;
+#define MAX_OPTIMIZED_LENGTH (MAX_INSN_SIZE + RELATIVE_ADDR_SIZE)
+#define MAX_OPTINSN_SIZE 				\
+	(((unsigned long)&optprobe_template_end -	\
+	  (unsigned long)&optprobe_template_entry) +	\
+	 MAX_OPTIMIZED_LENGTH + RELATIVEJUMP_SIZE)
+
 extern const int kretprobe_blacklist_size;
 
 void arch_remove_kprobe(struct kprobe *p);
@@ -64,6 +78,21 @@ struct arch_specific_insn {
 	int boostable;
 };
 
+struct arch_optimized_insn {
+	/* copy of the original instructions */
+	kprobe_opcode_t copied_insn[RELATIVE_ADDR_SIZE];
+	/* detour code buffer */
+	kprobe_opcode_t *insn;
+	/* the size of instructions copied to detour code buffer */
+	size_t size;
+};
+
+/* Return true (!0) if optinsn is prepared for optimization. */
+static inline int arch_prepared_optinsn(struct arch_optimized_insn *optinsn)
+{
+	return optinsn->size;
+}
+
 struct prev_kprobe {
 	struct kprobe *kp;
 	unsigned long status;