Merge branches 'tracing/ftrace', 'tracing/markers', 'tracing/mmiotrac…

…e', 'tracing/nmisafe', 'tracing/tracepoints' and 'tracing/urgent' into tracing/core

arch/arm/include/asm/ftrace.h

@@ -1,6 +1,11 @@
 #ifndef _ASM_ARM_FTRACE
 #define _ASM_ARM_FTRACE
 
+#ifndef __ASSEMBLY__
+static inline void ftrace_nmi_enter(void) { }
+static inline void ftrace_nmi_exit(void) { }
+#endif
+
 #ifdef CONFIG_FUNCTION_TRACER
 #define MCOUNT_ADDR		((long)(mcount))
 #define MCOUNT_INSN_SIZE	4 /* sizeof mcount call */

arch/powerpc/include/asm/ftrace.h

@@ -1,6 +1,11 @@
 #ifndef _ASM_POWERPC_FTRACE
 #define _ASM_POWERPC_FTRACE
 
+#ifndef __ASSEMBLY__
+static inline void ftrace_nmi_enter(void) { }
+static inline void ftrace_nmi_exit(void) { }
+#endif
+
 #ifdef CONFIG_FUNCTION_TRACER
 #define MCOUNT_ADDR		((long)(_mcount))
 #define MCOUNT_INSN_SIZE	4 /* sizeof mcount call */

arch/sh/include/asm/ftrace.h

@@ -1,6 +1,11 @@
 #ifndef __ASM_SH_FTRACE_H
 #define __ASM_SH_FTRACE_H
 
+#ifndef __ASSEMBLY__
+static inline void ftrace_nmi_enter(void) { }
+static inline void ftrace_nmi_exit(void) { }
+#endif
+
 #ifndef __ASSEMBLY__
 extern void mcount(void);
 #endif

arch/sparc/include/asm/ftrace.h

@@ -1,6 +1,11 @@
 #ifndef _ASM_SPARC64_FTRACE
 #define _ASM_SPARC64_FTRACE
 
+#ifndef __ASSEMBLY__
+static inline void ftrace_nmi_enter(void) { }
+static inline void ftrace_nmi_exit(void) { }
+#endif
+
 #ifdef CONFIG_MCOUNT
 #define MCOUNT_ADDR		((long)(_mcount))
 #define MCOUNT_INSN_SIZE	4 /* sizeof mcount call */

arch/x86/Kconfig.debug

@@ -186,14 +186,10 @@ config IOMMU_LEAK
 	  Add a simple leak tracer to the IOMMU code. This is useful when you
 	  are debugging a buggy device driver that leaks IOMMU mappings.
 
-config MMIOTRACE_HOOKS
-	bool
-
 config MMIOTRACE
 	bool "Memory mapped IO tracing"
 	depends on DEBUG_KERNEL && PCI
 	select TRACING
-	select MMIOTRACE_HOOKS
 	help
 	  Mmiotrace traces Memory Mapped I/O access and is meant for
 	  debugging and reverse engineering. It is called from the ioremap

arch/x86/include/asm/ftrace.h

@@ -17,6 +17,21 @@ static inline unsigned long ftrace_call_adjust(unsigned long addr)
 	 */
 	return addr - 1;
 }
+
+#ifdef CONFIG_DYNAMIC_FTRACE
+extern void ftrace_nmi_enter(void);
+extern void ftrace_nmi_exit(void);
+#else
+static inline void ftrace_nmi_enter(void) { }
+static inline void ftrace_nmi_exit(void) { }
+#endif
+#endif /* __ASSEMBLY__ */
+
+#else /* CONFIG_FUNCTION_TRACER */
+
+#ifndef __ASSEMBLY__
+static inline void ftrace_nmi_enter(void) { }
+static inline void ftrace_nmi_exit(void) { }
 #endif
 
 #endif /* CONFIG_FUNCTION_TRACER */

arch/x86/kernel/ftrace.c

@@ -56,6 +56,133 @@ unsigned char *ftrace_call_replace(unsigned long ip, unsigned long addr)
 	return calc.code;
 }
 
+/*
+ * Modifying code must take extra care. On an SMP machine, if
+ * the code being modified is also being executed on another CPU
+ * that CPU will have undefined results and possibly take a GPF.
+ * We use kstop_machine to stop other CPUS from exectuing code.
+ * But this does not stop NMIs from happening. We still need
+ * to protect against that. We separate out the modification of
+ * the code to take care of this.
+ *
+ * Two buffers are added: An IP buffer and a "code" buffer.
+ *
+ * 1) Put the instruction pointer into the IP buffer
+ *    and the new code into the "code" buffer.
+ * 2) Set a flag that says we are modifying code
+ * 3) Wait for any running NMIs to finish.
+ * 4) Write the code
+ * 5) clear the flag.
+ * 6) Wait for any running NMIs to finish.
+ *
+ * If an NMI is executed, the first thing it does is to call
+ * "ftrace_nmi_enter". This will check if the flag is set to write
+ * and if it is, it will write what is in the IP and "code" buffers.
+ *
+ * The trick is, it does not matter if everyone is writing the same
+ * content to the code location. Also, if a CPU is executing code
+ * it is OK to write to that code location if the contents being written
+ * are the same as what exists.
+ */
+
+static atomic_t in_nmi = ATOMIC_INIT(0);
+static int mod_code_status;		/* holds return value of text write */
+static int mod_code_write;		/* set when NMI should do the write */
+static void *mod_code_ip;		/* holds the IP to write to */
+static void *mod_code_newcode;		/* holds the text to write to the IP */
+
+static unsigned nmi_wait_count;
+static atomic_t nmi_update_count = ATOMIC_INIT(0);
+
+int ftrace_arch_read_dyn_info(char *buf, int size)
+{
+	int r;
+
+	r = snprintf(buf, size, "%u %u",
+		     nmi_wait_count,
+		     atomic_read(&nmi_update_count));
+	return r;
+}
+
+static void ftrace_mod_code(void)
+{
+	/*
+	 * Yes, more than one CPU process can be writing to mod_code_status.
+	 *    (and the code itself)
+	 * But if one were to fail, then they all should, and if one were
+	 * to succeed, then they all should.
+	 */
+	mod_code_status = probe_kernel_write(mod_code_ip, mod_code_newcode,
+					     MCOUNT_INSN_SIZE);
+
+}
+
+void ftrace_nmi_enter(void)
+{
+	atomic_inc(&in_nmi);
+	/* Must have in_nmi seen before reading write flag */
+	smp_mb();
+	if (mod_code_write) {
+		ftrace_mod_code();
+		atomic_inc(&nmi_update_count);
+	}
+}
+
+void ftrace_nmi_exit(void)
+{
+	/* Finish all executions before clearing in_nmi */
+	smp_wmb();
+	atomic_dec(&in_nmi);
+}
+
+static void wait_for_nmi(void)
+{
+	int waited = 0;
+
+	while (atomic_read(&in_nmi)) {
+		waited = 1;
+		cpu_relax();
+	}
+
+	if (waited)
+		nmi_wait_count++;
+}
+
+static int
+do_ftrace_mod_code(unsigned long ip, void *new_code)
+{
+	mod_code_ip = (void *)ip;
+	mod_code_newcode = new_code;
+
+	/* The buffers need to be visible before we let NMIs write them */
+	smp_wmb();
+
+	mod_code_write = 1;
+
+	/* Make sure write bit is visible before we wait on NMIs */
+	smp_mb();
+
+	wait_for_nmi();
+
+	/* Make sure all running NMIs have finished before we write the code */
+	smp_mb();
+
+	ftrace_mod_code();
+
+	/* Make sure the write happens before clearing the bit */
+	smp_wmb();
+
+	mod_code_write = 0;
+
+	/* make sure NMIs see the cleared bit */
+	smp_mb();
+
+	wait_for_nmi();
+
+	return mod_code_status;
+}
+
+
 int
 ftrace_modify_code(unsigned long ip, unsigned char *old_code,
 		   unsigned char *new_code)
@@ -81,7 +208,7 @@ ftrace_modify_code(unsigned long ip, unsigned char *old_code,
 		return -EINVAL;
 
 	/* replace the text with the new text */
-	if (probe_kernel_write((void *)ip, new_code, MCOUNT_INSN_SIZE))
+	if (do_ftrace_mod_code(ip, new_code))
 		return -EPERM;
 
 	sync_core();

arch/x86/mm/Makefile

@@ -8,9 +8,8 @@ obj-$(CONFIG_X86_PTDUMP)	+= dump_pagetables.o
 
 obj-$(CONFIG_HIGHMEM)		+= highmem_32.o
 
-obj-$(CONFIG_MMIOTRACE_HOOKS)	+= kmmio.o
 obj-$(CONFIG_MMIOTRACE)		+= mmiotrace.o
-mmiotrace-y			:= pf_in.o mmio-mod.o
+mmiotrace-y			:= kmmio.o pf_in.o mmio-mod.o
 obj-$(CONFIG_MMIOTRACE_TEST)	+= testmmiotrace.o
 
 obj-$(CONFIG_NUMA)		+= numa_$(BITS).o

arch/x86/mm/fault.c

@@ -53,7 +53,7 @@
 
 static inline int kmmio_fault(struct pt_regs *regs, unsigned long addr)
 {
-#ifdef CONFIG_MMIOTRACE_HOOKS
+#ifdef CONFIG_MMIOTRACE
 	if (unlikely(is_kmmio_active()))
 		if (kmmio_handler(regs, addr) == 1)
 			return -1;

include/linux/ftrace.h

@@ -74,6 +74,9 @@ extern void ftrace_caller(void);
 extern void ftrace_call(void);
 extern void mcount_call(void);
 
+/* May be defined in arch */
+extern int ftrace_arch_read_dyn_info(char *buf, int size);
+
 /**
  * ftrace_modify_code - modify code segment
  * @ip: the address of the code segment

include/linux/hardirq.h

@@ -5,6 +5,7 @@
 #include <linux/smp_lock.h>
 #include <linux/lockdep.h>
 #include <asm/hardirq.h>
+#include <asm/ftrace.h>
 #include <asm/system.h>
 
 /*
@@ -161,7 +162,17 @@ extern void irq_enter(void);
  */
 extern void irq_exit(void);
 
-#define nmi_enter()		do { lockdep_off(); __irq_enter(); } while (0)
-#define nmi_exit()		do { __irq_exit(); lockdep_on(); } while (0)
+#define nmi_enter()				\
+	do {					\
+		ftrace_nmi_enter();		\
+		lockdep_off();			\
+		__irq_enter();			\
+	} while (0)
+#define nmi_exit()				\
+	do {					\
+		__irq_exit();			\
+		lockdep_on();			\
+		ftrace_nmi_exit();		\
+	} while (0)
 
 #endif /* LINUX_HARDIRQ_H */

include/linux/marker.h

@@ -136,8 +136,6 @@ extern marker_probe_func __mark_empty_function;
 
 extern void marker_probe_cb(const struct marker *mdata,
 	void *call_private, ...);
-extern void marker_probe_cb_noarg(const struct marker *mdata,
-	void *call_private, ...);
 
 /*
  * Connect a probe to a marker.

include/linux/tracepoint.h

@@ -112,6 +112,10 @@ extern int tracepoint_probe_register(const char *name, void *probe);
  */
 extern int tracepoint_probe_unregister(const char *name, void *probe);
 
+extern int tracepoint_probe_register_noupdate(const char *name, void *probe);
+extern int tracepoint_probe_unregister_noupdate(const char *name, void *probe);
+extern void tracepoint_probe_update_all(void);
+
 struct tracepoint_iter {
 	struct module *module;
 	struct tracepoint *tracepoint;