Merge branch 'perf-probes-for-linus-2' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip

* 'perf-probes-for-linus-2' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip:
  x86: Issue at least one memory barrier in stop_machine_text_poke()
  perf probe: Correct probe syntax on command line help
  perf probe: Add lazy line matching support
  perf probe: Show more lines after last line
  perf probe: Check function address range strictly in line finder
  perf probe: Use libdw callback routines
  perf probe: Use elfutils-libdw for analyzing debuginfo
  perf probe: Rename probe finder functions
  perf probe: Fix bugs in line range finder
  perf probe: Update perf probe document
  perf probe: Do not show --line option without dwarf support
  kprobes: Add documents of jump optimization
  kprobes/x86: Support kprobes jump optimization on x86
  x86: Add text_poke_smp for SMP cross modifying code
  kprobes/x86: Cleanup save/restore registers
  kprobes/x86: Boost probes when reentering
  kprobes: Jump optimization sysctl interface
  kprobes: Introduce kprobes jump optimization
  kprobes: Introduce generic insn_slot framework
  kprobes/x86: Cleanup RELATIVEJUMP_INSTRUCTION to RELATIVEJUMP_OPCODE

2 files changed, 33 insertions, 2 deletions

diff --git a/arch/x86/include/asm/alternative.h b/arch/x86/include/asm/alternative.h
index f1e253ceba4..b09ec55650b 100644
--- a/arch/x86/include/asm/alternative.h
+++ b/arch/x86/include/asm/alternative.h
@@ -165,10 +165,12 @@ static inline void apply_paravirt(struct paravirt_patch_site *start,
  * invalid instruction possible) or if the instructions are changed from a
  * consistent state to another consistent state atomically.
  * More care must be taken when modifying code in the SMP case because of
- * Intel's errata.
+ * Intel's errata. text_poke_smp() takes care that errata, but still
+ * doesn't support NMI/MCE handler code modifying.
  * On the local CPU you need to be protected again NMI or MCE handlers seeing an
  * inconsistent instruction while you patch.
  */
 extern void *text_poke(void *addr, const void *opcode, size_t len);
+extern void *text_poke_smp(void *addr, const void *opcode, size_t len);
 
 #endif /* _ASM_X86_ALTERNATIVE_H */
diff --git a/arch/x86/include/asm/kprobes.h b/arch/x86/include/asm/kprobes.h
index 4fe681de1e7..4ffa345a8cc 100644
--- a/arch/x86/include/asm/kprobes.h
+++ b/arch/x86/include/asm/kprobes.h
@@ -32,7 +32,10 @@ struct kprobe;
 
 typedef u8 kprobe_opcode_t;
 #define BREAKPOINT_INSTRUCTION	0xcc
-#define RELATIVEJUMP_INSTRUCTION 0xe9
+#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;