Merge branches 'sched/core', 'core/core' and 'tracing/core' into cpus4096

Documentation/ftrace.txt

@@ -82,7 +82,7 @@ of ftrace. Here is a list of some of the key files:
 		tracer is not adding more data, they will display
 		the same information every time they are read.
 
-  iter_ctrl: This file lets the user control the amount of data
+  trace_options: This file lets the user control the amount of data
 		that is displayed in one of the above output
 		files.
 
@@ -94,10 +94,10 @@ of ftrace. Here is a list of some of the key files:
 		only be recorded if the latency is greater than
 		the value in this file. (in microseconds)
 
-  trace_entries: This sets or displays the number of bytes each CPU
+  buffer_size_kb: This sets or displays the number of kilobytes each CPU
 		buffer can hold. The tracer buffers are the same size
 		for each CPU. The displayed number is the size of the
-		 CPU buffer and not total size of all buffers. The
+		CPU buffer and not total size of all buffers. The
 		trace buffers are allocated in pages (blocks of memory
 		that the kernel uses for allocation, usually 4 KB in size).
 		If the last page allocated has room for more bytes
@@ -316,23 +316,23 @@ The above is mostly meaningful for kernel developers.
   The rest is the same as the 'trace' file.
 
 
-iter_ctrl
----------
+trace_options
+-------------
 
-The iter_ctrl file is used to control what gets printed in the trace
+The trace_options file is used to control what gets printed in the trace
 output. To see what is available, simply cat the file:
 
-  cat /debug/tracing/iter_ctrl
+  cat /debug/tracing/trace_options
   print-parent nosym-offset nosym-addr noverbose noraw nohex nobin \
- noblock nostacktrace nosched-tree
+ noblock nostacktrace nosched-tree nouserstacktrace nosym-userobj
 
 To disable one of the options, echo in the option prepended with "no".
 
-  echo noprint-parent > /debug/tracing/iter_ctrl
+  echo noprint-parent > /debug/tracing/trace_options
 
 To enable an option, leave off the "no".
 
-  echo sym-offset > /debug/tracing/iter_ctrl
+  echo sym-offset > /debug/tracing/trace_options
 
 Here are the available options:
 
@@ -378,6 +378,20 @@ Here are the available options:
 		When a trace is recorded, so is the stack of functions.
 		This allows for back traces of trace sites.
 
+  userstacktrace - This option changes the trace.
+		   It records a stacktrace of the current userspace thread.
+
+  sym-userobj - when user stacktrace are enabled, look up which object the
+		address belongs to, and print a relative address
+		This is especially useful when ASLR is on, otherwise you don't
+		get a chance to resolve the address to object/file/line after the app is no
+		longer running
+
+		The lookup is performed when you read trace,trace_pipe,latency_trace. Example:
+
+		a.out-1623  [000] 40874.465068: /root/a.out[+0x480] <-/root/a.out[+0
+x494] <- /root/a.out[+0x4a8] <- /lib/libc-2.7.so[+0x1e1a6]
+
   sched-tree - TBD (any users??)
 
 
@@ -1299,41 +1313,29 @@ trace entries
 -------------
 
 Having too much or not enough data can be troublesome in diagnosing
-an issue in the kernel. The file trace_entries is used to modify
+an issue in the kernel. The file buffer_size_kb is used to modify
 the size of the internal trace buffers. The number listed
 is the number of entries that can be recorded per CPU. To know
 the full size, multiply the number of possible CPUS with the
 number of entries.
 
- # cat /debug/tracing/trace_entries
-65620
+ # cat /debug/tracing/buffer_size_kb
+1408 (units kilobytes)
 
 Note, to modify this, you must have tracing completely disabled. To do that,
 echo "nop" into the current_tracer. If the current_tracer is not set
 to "nop", an EINVAL error will be returned.
 
  # echo nop > /debug/tracing/current_tracer
- # echo 100000 > /debug/tracing/trace_entries
- # cat /debug/tracing/trace_entries
-100045
-
-
-Notice that we echoed in 100,000 but the size is 100,045. The entries
-are held in individual pages. It allocates the number of pages it takes
-to fulfill the request. If more entries may fit on the last page
-then they will be added.
-
- # echo 1 > /debug/tracing/trace_entries
- # cat /debug/tracing/trace_entries
-85
-
-This shows us that 85 entries can fit in a single page.
+ # echo 10000 > /debug/tracing/buffer_size_kb
+ # cat /debug/tracing/buffer_size_kb
+10000 (units kilobytes)
 
 The number of pages which will be allocated is limited to a percentage
 of available memory. Allocating too much will produce an error.
 
- # echo 1000000000000 > /debug/tracing/trace_entries
+ # echo 1000000000000 > /debug/tracing/buffer_size_kb
 -bash: echo: write error: Cannot allocate memory
- # cat /debug/tracing/trace_entries
+ # cat /debug/tracing/buffer_size_kb
 85
 

Documentation/kernel-parameters.txt

@@ -750,6 +750,14 @@ and is between 256 and 4096 characters. It is defined in the file
 			parameter will force ia64_sal_cache_flush to call
 			ia64_pal_cache_flush instead of SAL_CACHE_FLUSH.
 
+	ftrace=[tracer]
+			[ftrace] will set and start the specified tracer
+			as early as possible in order to facilitate early
+			boot debugging.
+
+	ftrace_dump_on_oops
+			[ftrace] will dump the trace buffers on oops.
+
 	gamecon.map[2|3]=
 			[HW,JOY] Multisystem joystick and NES/SNES/PSX pad
 			support via parallel port (up to 5 devices per port)

Documentation/lockstat.txt

@@ -71,35 +71,50 @@ Look at the current lock statistics:
 
 # less /proc/lock_stat
 
-01 lock_stat version 0.2
+01 lock_stat version 0.3
 02 -----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------
 03                               class name    con-bounces    contentions   waittime-min   waittime-max waittime-total    acq-bounces   acquisitions   holdtime-min   holdtime-max holdtime-total
 04 -----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------
 05
-06               &inode->i_data.tree_lock-W:            15          21657           0.18     1093295.30 11547131054.85             58          10415           0.16          87.51        6387.60
-07               &inode->i_data.tree_lock-R:             0              0           0.00           0.00           0.00          23302         231198           0.25           8.45       98023.38
-08               --------------------------
-09                 &inode->i_data.tree_lock              0          [<ffffffff8027c08f>] add_to_page_cache+0x5f/0x190
-10
-11 ...............................................................................................................................................................................................
-12
-13                              dcache_lock:          1037           1161           0.38          45.32         774.51           6611         243371           0.15         306.48       77387.24
-14                              -----------
-15                              dcache_lock            180          [<ffffffff802c0d7e>] sys_getcwd+0x11e/0x230
-16                              dcache_lock            165          [<ffffffff802c002a>] d_alloc+0x15a/0x210
-17                              dcache_lock             33          [<ffffffff8035818d>] _atomic_dec_and_lock+0x4d/0x70
-18                              dcache_lock              1          [<ffffffff802beef8>] shrink_dcache_parent+0x18/0x130
+06                          &mm->mmap_sem-W:           233            538 18446744073708       22924.27      607243.51           1342          45806           1.71        8595.89     1180582.34
+07                          &mm->mmap_sem-R:           205            587 18446744073708       28403.36      731975.00           1940         412426           0.58      187825.45     6307502.88
+08                          ---------------
+09                            &mm->mmap_sem            487          [<ffffffff8053491f>] do_page_fault+0x466/0x928
+10                            &mm->mmap_sem            179          [<ffffffff802a6200>] sys_mprotect+0xcd/0x21d
+11                            &mm->mmap_sem            279          [<ffffffff80210a57>] sys_mmap+0x75/0xce
+12                            &mm->mmap_sem             76          [<ffffffff802a490b>] sys_munmap+0x32/0x59
+13                          ---------------
+14                            &mm->mmap_sem            270          [<ffffffff80210a57>] sys_mmap+0x75/0xce
+15                            &mm->mmap_sem            431          [<ffffffff8053491f>] do_page_fault+0x466/0x928
+16                            &mm->mmap_sem            138          [<ffffffff802a490b>] sys_munmap+0x32/0x59
+17                            &mm->mmap_sem            145          [<ffffffff802a6200>] sys_mprotect+0xcd/0x21d
+18
+19 ...............................................................................................................................................................................................
+20
+21                              dcache_lock:           621            623           0.52         118.26        1053.02           6745          91930           0.29         316.29      118423.41
+22                              -----------
+23                              dcache_lock            179          [<ffffffff80378274>] _atomic_dec_and_lock+0x34/0x54
+24                              dcache_lock            113          [<ffffffff802cc17b>] d_alloc+0x19a/0x1eb
+25                              dcache_lock             99          [<ffffffff802ca0dc>] d_rehash+0x1b/0x44
+26                              dcache_lock            104          [<ffffffff802cbca0>] d_instantiate+0x36/0x8a
+27                              -----------
+28                              dcache_lock            192          [<ffffffff80378274>] _atomic_dec_and_lock+0x34/0x54
+29                              dcache_lock             98          [<ffffffff802ca0dc>] d_rehash+0x1b/0x44
+30                              dcache_lock             72          [<ffffffff802cc17b>] d_alloc+0x19a/0x1eb
+31                              dcache_lock            112          [<ffffffff802cbca0>] d_instantiate+0x36/0x8a
 
 This excerpt shows the first two lock class statistics. Line 01 shows the
 output version - each time the format changes this will be updated. Line 02-04
-show the header with column descriptions. Lines 05-10 and 13-18 show the actual
+show the header with column descriptions. Lines 05-18 and 20-31 show the actual
 statistics. These statistics come in two parts; the actual stats separated by a
-short separator (line 08, 14) from the contention points.
+short separator (line 08, 13) from the contention points.
 
-The first lock (05-10) is a read/write lock, and shows two lines above the
+The first lock (05-18) is a read/write lock, and shows two lines above the
 short separator. The contention points don't match the column descriptors,
-they have two: contentions and [<IP>] symbol.
+they have two: contentions and [<IP>] symbol. The second set of contention
+points are the points we're contending with.
 
+The integer part of the time values is in us.
 
 View the top contending locks:
 

Documentation/markers.txt

@@ -70,6 +70,20 @@ a printk warning which identifies the inconsistency:
 
 "Format mismatch for probe probe_name (format), marker (format)"
 
+Another way to use markers is to simply define the marker without generating any
+function call to actually call into the marker. This is useful in combination
+with tracepoint probes in a scheme like this :
+
+void probe_tracepoint_name(unsigned int arg1, struct task_struct *tsk);
+
+DEFINE_MARKER_TP(marker_eventname, tracepoint_name, probe_tracepoint_name,
+	"arg1 %u pid %d");
+
+notrace void probe_tracepoint_name(unsigned int arg1, struct task_struct *tsk)
+{
+	struct marker *marker = &GET_MARKER(kernel_irq_entry);
+	/* write data to trace buffers ... */
+}
 
 * Probe / marker example
 

Documentation/tracepoints.txt

@@ -3,28 +3,30 @@
 			    Mathieu Desnoyers
 
 
-This document introduces Linux Kernel Tracepoints and their use. It provides
-examples of how to insert tracepoints in the kernel and connect probe functions
-to them and provides some examples of probe functions.
+This document introduces Linux Kernel Tracepoints and their use. It
+provides examples of how to insert tracepoints in the kernel and
+connect probe functions to them and provides some examples of probe
+functions.
 
 
 * Purpose of tracepoints
 
-A tracepoint placed in code provides a hook to call a function (probe) that you
-can provide at runtime. A tracepoint can be "on" (a probe is connected to it) or
-"off" (no probe is attached). When a tracepoint is "off" it has no effect,
-except for adding a tiny time penalty (checking a condition for a branch) and
-space penalty (adding a few bytes for the function call at the end of the
-instrumented function and adds a data structure in a separate section).  When a
-tracepoint is "on", the function you provide is called each time the tracepoint
-is executed, in the execution context of the caller. When the function provided
-ends its execution, it returns to the caller (continuing from the tracepoint
-site).
+A tracepoint placed in code provides a hook to call a function (probe)
+that you can provide at runtime. A tracepoint can be "on" (a probe is
+connected to it) or "off" (no probe is attached). When a tracepoint is
+"off" it has no effect, except for adding a tiny time penalty
+(checking a condition for a branch) and space penalty (adding a few
+bytes for the function call at the end of the instrumented function
+and adds a data structure in a separate section).  When a tracepoint
+is "on", the function you provide is called each time the tracepoint
+is executed, in the execution context of the caller. When the function
+provided ends its execution, it returns to the caller (continuing from
+the tracepoint site).
 
 You can put tracepoints at important locations in the code. They are
 lightweight hooks that can pass an arbitrary number of parameters,
-which prototypes are described in a tracepoint declaration placed in a header
-file.
+which prototypes are described in a tracepoint declaration placed in a
+header file.
 
 They can be used for tracing and performance accounting.
 
@@ -42,7 +44,7 @@ In include/trace/subsys.h :
 
 #include <linux/tracepoint.h>
 
-DEFINE_TRACE(subsys_eventname,
+DECLARE_TRACE(subsys_eventname,
 	TPPTOTO(int firstarg, struct task_struct *p),
 	TPARGS(firstarg, p));
 
@@ -50,6 +52,8 @@ In subsys/file.c (where the tracing statement must be added) :
 
 #include <trace/subsys.h>
 
+DEFINE_TRACE(subsys_eventname);
+
 void somefct(void)
 {
 	...
@@ -61,31 +65,41 @@ Where :
 - subsys_eventname is an identifier unique to your event
     - subsys is the name of your subsystem.
     - eventname is the name of the event to trace.
-- TPPTOTO(int firstarg, struct task_struct *p) is the prototype of the function
-  called by this tracepoint.
-- TPARGS(firstarg, p) are the parameters names, same as found in the prototype.
 
-Connecting a function (probe) to a tracepoint is done by providing a probe
-(function to call) for the specific tracepoint through
-register_trace_subsys_eventname().  Removing a probe is done through
-unregister_trace_subsys_eventname(); it will remove the probe sure there is no
-caller left using the probe when it returns. Probe removal is preempt-safe
-because preemption is disabled around the probe call. See the "Probe example"
-section below for a sample probe module.
-
-The tracepoint mechanism supports inserting multiple instances of the same
-tracepoint, but a single definition must be made of a given tracepoint name over
-all the kernel to make sure no type conflict will occur. Name mangling of the
-tracepoints is done using the prototypes to make sure typing is correct.
-Verification of probe type correctness is done at the registration site by the
-compiler. Tracepoints can be put in inline functions, inlined static functions,
-and unrolled loops as well as regular functions.
-
-The naming scheme "subsys_event" is suggested here as a convention intended
-to limit collisions. Tracepoint names are global to the kernel: they are
-considered as being the same whether they are in the core kernel image or in
-modules.
+- TPPTOTO(int firstarg, struct task_struct *p) is the prototype of the
+  function called by this tracepoint.
 
+- TPARGS(firstarg, p) are the parameters names, same as found in the
+  prototype.
+
+Connecting a function (probe) to a tracepoint is done by providing a
+probe (function to call) for the specific tracepoint through
+register_trace_subsys_eventname().  Removing a probe is done through
+unregister_trace_subsys_eventname(); it will remove the probe.
+
+tracepoint_synchronize_unregister() must be called before the end of
+the module exit function to make sure there is no caller left using
+the probe. This, and the fact that preemption is disabled around the
+probe call, make sure that probe removal and module unload are safe.
+See the "Probe example" section below for a sample probe module.
+
+The tracepoint mechanism supports inserting multiple instances of the
+same tracepoint, but a single definition must be made of a given
+tracepoint name over all the kernel to make sure no type conflict will
+occur. Name mangling of the tracepoints is done using the prototypes
+to make sure typing is correct. Verification of probe type correctness
+is done at the registration site by the compiler. Tracepoints can be
+put in inline functions, inlined static functions, and unrolled loops
+as well as regular functions.
+
+The naming scheme "subsys_event" is suggested here as a convention
+intended to limit collisions. Tracepoint names are global to the
+kernel: they are considered as being the same whether they are in the
+core kernel image or in modules.
+
+If the tracepoint has to be used in kernel modules, an
+EXPORT_TRACEPOINT_SYMBOL_GPL() or EXPORT_TRACEPOINT_SYMBOL() can be
+used to export the defined tracepoints.
 
 * Probe / tracepoint example
 

Documentation/tracers/mmiotrace.txt

@@ -37,7 +37,7 @@ $ echo mmiotrace > /debug/tracing/current_tracer
 $ cat /debug/tracing/trace_pipe > mydump.txt &
 Start X or whatever.
 $ echo "X is up" > /debug/tracing/trace_marker
-$ echo none > /debug/tracing/current_tracer
+$ echo nop > /debug/tracing/current_tracer
 Check for lost events.
 
 
@@ -66,7 +66,7 @@ which action. It is recommended to place descriptive markers about what you
 do.
 
 Shut down mmiotrace (requires root privileges):
-$ echo none > /debug/tracing/current_tracer
+$ echo nop > /debug/tracing/current_tracer
 The 'cat' process exits. If it does not, kill it by issuing 'fg' command and
 pressing ctrl+c.
 
@@ -81,7 +81,9 @@ are:
 $ cat /debug/tracing/trace_entries
 gives you a number. Approximately double this number and write it back, for
 instance:
+$ echo 0 > /debug/tracing/tracing_enabled
 $ echo 128000 > /debug/tracing/trace_entries
+$ echo 1 > /debug/tracing/tracing_enabled
 Then start again from the top.
 
 If you are doing a trace for a driver project, e.g. Nouveau, you should also

arch/arm/mach-pxa/include/mach/pxafb.h

@@ -33,6 +33,7 @@
 #define LCD_CONN_TYPE(_x)	((_x) & 0x0f)
 #define LCD_CONN_WIDTH(_x)	(((_x) >> 4) & 0x1f)
 
+#define LCD_TYPE_MASK		0xf
 #define LCD_TYPE_UNKNOWN	0
 #define LCD_TYPE_MONO_STN	1
 #define LCD_TYPE_MONO_DSTN	2

arch/arm/mach-pxa/reset.c

@@ -90,12 +90,13 @@ void arch_reset(char mode)
 		/* Jump into ROM at address 0 */
 		cpu_reset(0);
 		break;
-	case 'h':
-		do_hw_reset();
-		break;
 	case 'g':
 		do_gpio_reset();
 		break;
+	case 'h':
+	default:
+		do_hw_reset();
+		break;
 	}
 }
 

arch/arm/mach-pxa/spitz.c

@@ -67,6 +67,7 @@
 static unsigned long spitz_pin_config[] __initdata = {
 	/* Chip Selects */
 	GPIO78_nCS_2,	/* SCOOP #2 */
+	GPIO79_nCS_3,	/* NAND */
 	GPIO80_nCS_4,	/* SCOOP #1 */
 
 	/* LCD - 16bpp Active TFT */
@@ -97,10 +98,10 @@ static unsigned long spitz_pin_config[] __initdata = {
 	GPIO51_nPIOW,
 	GPIO85_nPCE_1,
 	GPIO54_nPCE_2,
-	GPIO79_PSKTSEL,
 	GPIO55_nPREG,
 	GPIO56_nPWAIT,
 	GPIO57_nIOIS16,
+	GPIO104_PSKTSEL,
 
 	/* MMC */
 	GPIO32_MMC_CLK,
@@ -686,7 +687,6 @@ static void __init akita_init(void)
 	spitz_pcmcia_config.num_devs = 1;
 	platform_scoop_config = &spitz_pcmcia_config;
 
-	pxa_set_i2c_info(NULL);
 	i2c_register_board_info(0, ARRAY_AND_SIZE(akita_i2c_board_info));
 
 	common_init();

arch/powerpc/include/asm/ftrace.h

@@ -7,7 +7,19 @@
 
 #ifndef __ASSEMBLY__
 extern void _mcount(void);
-#endif
+
+#ifdef CONFIG_DYNAMIC_FTRACE
+static inline unsigned long ftrace_call_adjust(unsigned long addr)
+{
+       /* reloction of mcount call site is the same as the address */
+       return addr;
+}
+
+struct dyn_arch_ftrace {
+	struct module *mod;
+};
+#endif /*  CONFIG_DYNAMIC_FTRACE */
+#endif /* __ASSEMBLY__ */
 
 #endif
 

arch/powerpc/include/asm/module.h

@@ -34,11 +34,19 @@ struct mod_arch_specific {
 #ifdef __powerpc64__
 	unsigned int stubs_section;	/* Index of stubs section in module */
 	unsigned int toc_section;	/* What section is the TOC? */
-#else
+#ifdef CONFIG_DYNAMIC_FTRACE
+	unsigned long toc;
+	unsigned long tramp;
+#endif
+
+#else /* powerpc64 */
 	/* Indices of PLT sections within module. */
 	unsigned int core_plt_section;
 	unsigned int init_plt_section;
+#ifdef CONFIG_DYNAMIC_FTRACE
+	unsigned long tramp;
 #endif
+#endif /* powerpc64 */
 
 	/* List of BUG addresses, source line numbers and filenames */
 	struct list_head bug_list;
@@ -68,6 +76,12 @@ struct mod_arch_specific {
 #    endif	/* MODULE */
 #endif
 
+#ifdef CONFIG_DYNAMIC_FTRACE
+#    ifdef MODULE
+	asm(".section .ftrace.tramp,\"ax\",@nobits; .align 3; .previous");
+#    endif	/* MODULE */
+#endif
+
 
 struct exception_table_entry;
 void sort_ex_table(struct exception_table_entry *start,

arch/powerpc/kernel/ftrace.c

@@ -9,22 +9,30 @@
 
 #include <linux/spinlock.h>
 #include <linux/hardirq.h>
+#include <linux/uaccess.h>
+#include <linux/module.h>
 #include <linux/ftrace.h>
 #include <linux/percpu.h>
 #include <linux/init.h>
 #include <linux/list.h>
 
 #include <asm/cacheflush.h>
+#include <asm/code-patching.h>
 #include <asm/ftrace.h>
 
+#if 0
+#define DEBUGP printk
+#else
+#define DEBUGP(fmt , ...)	do { } while (0)
+#endif
 
-static unsigned int ftrace_nop = 0x60000000;
+static unsigned int ftrace_nop = PPC_NOP_INSTR;
 
 #ifdef CONFIG_PPC32
 # define GET_ADDR(addr) addr
 #else
 /* PowerPC64's functions are data that points to the functions */
-# define GET_ADDR(addr) *(unsigned long *)addr
+# define GET_ADDR(addr) (*(unsigned long *)addr)
 #endif
 
 
@@ -33,12 +41,12 @@ static unsigned int ftrace_calc_offset(long ip, long addr)
 	return (int)(addr - ip);
 }
 
-unsigned char *ftrace_nop_replace(void)
+static unsigned char *ftrace_nop_replace(void)
 {
 	return (char *)&ftrace_nop;
 }
 
-unsigned char *ftrace_call_replace(unsigned long ip, unsigned long addr)
+static unsigned char *ftrace_call_replace(unsigned long ip, unsigned long addr)
 {
 	static unsigned int op;
 
@@ -68,49 +76,434 @@ unsigned char *ftrace_call_replace(unsigned long ip, unsigned long addr)
 # define _ASM_PTR	" .long "
 #endif
 
-int
+static int
 ftrace_modify_code(unsigned long ip, unsigned char *old_code,
 		   unsigned char *new_code)
 {
-	unsigned replaced;
-	unsigned old = *(unsigned *)old_code;
-	unsigned new = *(unsigned *)new_code;
-	int faulted = 0;
+	unsigned char replaced[MCOUNT_INSN_SIZE];
 
 	/*
 	 * Note: Due to modules and __init, code can
 	 *  disappear and change, we need to protect against faulting
-	 *  as well as code changing.
+	 *  as well as code changing. We do this by using the
+	 *  probe_kernel_* functions.
 	 *
 	 * No real locking needed, this code is run through
-	 * kstop_machine.
+	 * kstop_machine, or before SMP starts.
 	 */
-	asm volatile (
-		"1: lwz		%1, 0(%2)\n"
-		"   cmpw	%1, %5\n"
-		"   bne		2f\n"
-		"   stwu	%3, 0(%2)\n"
-		"2:\n"
-		".section .fixup, \"ax\"\n"
-		"3:	li %0, 1\n"
-		"	b 2b\n"
-		".previous\n"
-		".section __ex_table,\"a\"\n"
-		_ASM_ALIGN "\n"
-		_ASM_PTR "1b, 3b\n"
-		".previous"
-		: "=r"(faulted), "=r"(replaced)
-		: "r"(ip), "r"(new),
-		  "0"(faulted), "r"(old)
-		: "memory");
-
-	if (replaced != old && replaced != new)
-		faulted = 2;
-
-	if (!faulted)
-		flush_icache_range(ip, ip + 8);
-
-	return faulted;
+
+	/* read the text we want to modify */
+	if (probe_kernel_read(replaced, (void *)ip, MCOUNT_INSN_SIZE))
+		return -EFAULT;
+
+	/* Make sure it is what we expect it to be */
+	if (memcmp(replaced, old_code, MCOUNT_INSN_SIZE) != 0)
+		return -EINVAL;
+
+	/* replace the text with the new text */
+	if (probe_kernel_write((void *)ip, new_code, MCOUNT_INSN_SIZE))
+		return -EPERM;
+
+	flush_icache_range(ip, ip + 8);
+
+	return 0;
+}
+
+/*
+ * Helper functions that are the same for both PPC64 and PPC32.
+ */
+static int test_24bit_addr(unsigned long ip, unsigned long addr)
+{
+	long diff;
+
+	/*
+	 * Can we get to addr from ip in 24 bits?
+	 *  (26 really, since we mulitply by 4 for 4 byte alignment)
+	 */
+	diff = addr - ip;
+
+	/*
+	 * Return true if diff is less than 1 << 25
+	 *  and greater than -1 << 26.
+	 */
+	return (diff < (1 << 25)) && (diff > (-1 << 26));
+}
+
+static int is_bl_op(unsigned int op)
+{
+	return (op & 0xfc000003) == 0x48000001;
+}
+
+static int test_offset(unsigned long offset)
+{
+	return (offset + 0x2000000 > 0x3ffffff) || ((offset & 3) != 0);
+}
+
+static unsigned long find_bl_target(unsigned long ip, unsigned int op)
+{
+	static int offset;
+
+	offset = (op & 0x03fffffc);
+	/* make it signed */
+	if (offset & 0x02000000)
+		offset |= 0xfe000000;
+
+	return ip + (long)offset;
+}
+
+static unsigned int branch_offset(unsigned long offset)
+{
+	/* return "bl ip+offset" */
+	return 0x48000001 | (offset & 0x03fffffc);
+}
+
+#ifdef CONFIG_PPC64
+static int
+__ftrace_make_nop(struct module *mod,
+		  struct dyn_ftrace *rec, unsigned long addr)
+{
+	unsigned char replaced[MCOUNT_INSN_SIZE * 2];
+	unsigned int *op = (unsigned *)&replaced;
+	unsigned char jmp[8];
+	unsigned long *ptr = (unsigned long *)&jmp;
+	unsigned long ip = rec->ip;
+	unsigned long tramp;
+	int offset;
+
+	/* read where this goes */
+	if (probe_kernel_read(replaced, (void *)ip, MCOUNT_INSN_SIZE))
+		return -EFAULT;
+
+	/* Make sure that that this is still a 24bit jump */
+	if (!is_bl_op(*op)) {
+		printk(KERN_ERR "Not expected bl: opcode is %x\n", *op);
+		return -EINVAL;
+	}
+
+	/* lets find where the pointer goes */
+	tramp = find_bl_target(ip, *op);
+
+	/*
+	 * On PPC64 the trampoline looks like:
+	 * 0x3d, 0x82, 0x00, 0x00,    addis   r12,r2, <high>
+	 * 0x39, 0x8c, 0x00, 0x00,    addi    r12,r12, <low>
+	 *   Where the bytes 2,3,6 and 7 make up the 32bit offset
+	 *   to the TOC that holds the pointer.
+	 *   to jump to.
+	 * 0xf8, 0x41, 0x00, 0x28,    std     r2,40(r1)
+	 * 0xe9, 0x6c, 0x00, 0x20,    ld      r11,32(r12)
+	 *   The actually address is 32 bytes from the offset
+	 *   into the TOC.
+	 * 0xe8, 0x4c, 0x00, 0x28,    ld      r2,40(r12)
+	 */
+
+	DEBUGP("ip:%lx jumps to %lx r2: %lx", ip, tramp, mod->arch.toc);
+
+	/* Find where the trampoline jumps to */
+	if (probe_kernel_read(jmp, (void *)tramp, 8)) {
+		printk(KERN_ERR "Failed to read %lx\n", tramp);
+		return -EFAULT;
+	}
+
+	DEBUGP(" %08x %08x",
+	       (unsigned)(*ptr >> 32),
+	       (unsigned)*ptr);
+
+	offset = (unsigned)jmp[2] << 24 |
+		(unsigned)jmp[3] << 16 |
+		(unsigned)jmp[6] << 8 |
+		(unsigned)jmp[7];
+
+	DEBUGP(" %x ", offset);
+
+	/* get the address this jumps too */
+	tramp = mod->arch.toc + offset + 32;
+	DEBUGP("toc: %lx", tramp);
+
+	if (probe_kernel_read(jmp, (void *)tramp, 8)) {
+		printk(KERN_ERR "Failed to read %lx\n", tramp);
+		return -EFAULT;
+	}
+
+	DEBUGP(" %08x %08x\n",
+	       (unsigned)(*ptr >> 32),
+	       (unsigned)*ptr);
+
+	/* This should match what was called */
+	if (*ptr != GET_ADDR(addr)) {
+		printk(KERN_ERR "addr does not match %lx\n", *ptr);
+		return -EINVAL;
+	}
+
+	/*
+	 * We want to nop the line, but the next line is
+	 *  0xe8, 0x41, 0x00, 0x28   ld r2,40(r1)
+	 * This needs to be turned to a nop too.
+	 */
+	if (probe_kernel_read(replaced, (void *)(ip+4), MCOUNT_INSN_SIZE))
+		return -EFAULT;
+
+	if (*op != 0xe8410028) {
+		printk(KERN_ERR "Next line is not ld! (%08x)\n", *op);
+		return -EINVAL;
+	}
+
+	/*
+	 * Milton Miller pointed out that we can not blindly do nops.
+	 * If a task was preempted when calling a trace function,
+	 * the nops will remove the way to restore the TOC in r2
+	 * and the r2 TOC will get corrupted.
+	 */
+
+	/*
+	 * Replace:
+	 *   bl <tramp>  <==== will be replaced with "b 1f"
+	 *   ld r2,40(r1)
+	 *  1:
+	 */
+	op[0] = 0x48000008;	/* b +8 */
+
+	if (probe_kernel_write((void *)ip, replaced, MCOUNT_INSN_SIZE))
+		return -EPERM;
+
+	return 0;
+}
+
+#else /* !PPC64 */
+static int
+__ftrace_make_nop(struct module *mod,
+		  struct dyn_ftrace *rec, unsigned long addr)
+{
+	unsigned char replaced[MCOUNT_INSN_SIZE];
+	unsigned int *op = (unsigned *)&replaced;
+	unsigned char jmp[8];
+	unsigned int *ptr = (unsigned int *)&jmp;
+	unsigned long ip = rec->ip;
+	unsigned long tramp;
+	int offset;
+
+	if (probe_kernel_read(replaced, (void *)ip, MCOUNT_INSN_SIZE))
+		return -EFAULT;
+
+	/* Make sure that that this is still a 24bit jump */
+	if (!is_bl_op(*op)) {
+		printk(KERN_ERR "Not expected bl: opcode is %x\n", *op);
+		return -EINVAL;
+	}
+
+	/* lets find where the pointer goes */
+	tramp = find_bl_target(ip, *op);
+
+	/*
+	 * On PPC32 the trampoline looks like:
+	 * lis r11,sym@ha
+	 * addi r11,r11,sym@l
+	 * mtctr r11
+	 * bctr
+	 */
+
+	DEBUGP("ip:%lx jumps to %lx", ip, tramp);
+
+	/* Find where the trampoline jumps to */
+	if (probe_kernel_read(jmp, (void *)tramp, 8)) {
+		printk(KERN_ERR "Failed to read %lx\n", tramp);
+		return -EFAULT;
+	}
+
+	DEBUGP(" %08x %08x ", ptr[0], ptr[1]);
+
+	tramp = (ptr[1] & 0xffff) |
+		((ptr[0] & 0xffff) << 16);
+	if (tramp & 0x8000)
+		tramp -= 0x10000;
+
+	DEBUGP(" %x ", tramp);
+
+	if (tramp != addr) {
+		printk(KERN_ERR
+		       "Trampoline location %08lx does not match addr\n",
+		       tramp);
+		return -EINVAL;
+	}
+
+	op[0] = PPC_NOP_INSTR;
+
+	if (probe_kernel_write((void *)ip, replaced, MCOUNT_INSN_SIZE))
+		return -EPERM;
+
+	return 0;
+}
+#endif /* PPC64 */
+
+int ftrace_make_nop(struct module *mod,
+		    struct dyn_ftrace *rec, unsigned long addr)
+{
+	unsigned char *old, *new;
+	unsigned long ip = rec->ip;
+
+	/*
+	 * If the calling address is more that 24 bits away,
+	 * then we had to use a trampoline to make the call.
+	 * Otherwise just update the call site.
+	 */
+	if (test_24bit_addr(ip, addr)) {
+		/* within range */
+		old = ftrace_call_replace(ip, addr);
+		new = ftrace_nop_replace();
+		return ftrace_modify_code(ip, old, new);
+	}
+
+	/*
+	 * Out of range jumps are called from modules.
+	 * We should either already have a pointer to the module
+	 * or it has been passed in.
+	 */
+	if (!rec->arch.mod) {
+		if (!mod) {
+			printk(KERN_ERR "No module loaded addr=%lx\n",
+			       addr);
+			return -EFAULT;
+		}
+		rec->arch.mod = mod;
+	} else if (mod) {
+		if (mod != rec->arch.mod) {
+			printk(KERN_ERR
+			       "Record mod %p not equal to passed in mod %p\n",
+			       rec->arch.mod, mod);
+			return -EINVAL;
+		}
+		/* nothing to do if mod == rec->arch.mod */
+	} else
+		mod = rec->arch.mod;
+
+	return __ftrace_make_nop(mod, rec, addr);
+
+}
+
+#ifdef CONFIG_PPC64
+static int
+__ftrace_make_call(struct dyn_ftrace *rec, unsigned long addr)
+{
+	unsigned char replaced[MCOUNT_INSN_SIZE * 2];
+	unsigned int *op = (unsigned *)&replaced;
+	unsigned long ip = rec->ip;
+	unsigned long offset;
+
+	/* read where this goes */
+	if (probe_kernel_read(replaced, (void *)ip, MCOUNT_INSN_SIZE * 2))
+		return -EFAULT;
+
+	/*
+	 * It should be pointing to two nops or
+	 *  b +8; ld r2,40(r1)
+	 */
+	if (((op[0] != 0x48000008) || (op[1] != 0xe8410028)) &&
+	    ((op[0] != PPC_NOP_INSTR) || (op[1] != PPC_NOP_INSTR))) {
+		printk(KERN_ERR "Expected NOPs but have %x %x\n", op[0], op[1]);
+		return -EINVAL;
+	}
+
+	/* If we never set up a trampoline to ftrace_caller, then bail */
+	if (!rec->arch.mod->arch.tramp) {
+		printk(KERN_ERR "No ftrace trampoline\n");
+		return -EINVAL;
+	}
+
+	/* now calculate a jump to the ftrace caller trampoline */
+	offset = rec->arch.mod->arch.tramp - ip;
+
+	if (test_offset(offset)) {
+		printk(KERN_ERR "REL24 %li out of range!\n",
+		       (long int)offset);
+		return -EINVAL;
+	}
+
+	/* Set to "bl addr" */
+	op[0] = branch_offset(offset);
+	/* ld r2,40(r1) */
+	op[1] = 0xe8410028;
+
+	DEBUGP("write to %lx\n", rec->ip);
+
+	if (probe_kernel_write((void *)ip, replaced, MCOUNT_INSN_SIZE * 2))
+		return -EPERM;
+
+	return 0;
+}
+#else
+static int
+__ftrace_make_call(struct dyn_ftrace *rec, unsigned long addr)
+{
+	unsigned char replaced[MCOUNT_INSN_SIZE];
+	unsigned int *op = (unsigned *)&replaced;
+	unsigned long ip = rec->ip;
+	unsigned long offset;
+
+	/* read where this goes */
+	if (probe_kernel_read(replaced, (void *)ip, MCOUNT_INSN_SIZE))
+		return -EFAULT;
+
+	/* It should be pointing to a nop */
+	if (op[0] != PPC_NOP_INSTR) {
+		printk(KERN_ERR "Expected NOP but have %x\n", op[0]);
+		return -EINVAL;
+	}
+
+	/* If we never set up a trampoline to ftrace_caller, then bail */
+	if (!rec->arch.mod->arch.tramp) {
+		printk(KERN_ERR "No ftrace trampoline\n");
+		return -EINVAL;
+	}
+
+	/* now calculate a jump to the ftrace caller trampoline */
+	offset = rec->arch.mod->arch.tramp - ip;
+
+	if (test_offset(offset)) {
+		printk(KERN_ERR "REL24 %li out of range!\n",
+		       (long int)offset);
+		return -EINVAL;
+	}
+
+	/* Set to "bl addr" */
+	op[0] = branch_offset(offset);
+
+	DEBUGP("write to %lx\n", rec->ip);
+
+	if (probe_kernel_write((void *)ip, replaced, MCOUNT_INSN_SIZE))
+		return -EPERM;
+
+	return 0;
+}
+#endif /* CONFIG_PPC64 */
+
+int ftrace_make_call(struct dyn_ftrace *rec, unsigned long addr)
+{
+	unsigned char *old, *new;
+	unsigned long ip = rec->ip;
+
+	/*
+	 * If the calling address is more that 24 bits away,
+	 * then we had to use a trampoline to make the call.
+	 * Otherwise just update the call site.
+	 */
+	if (test_24bit_addr(ip, addr)) {
+		/* within range */
+		old = ftrace_nop_replace();
+		new = ftrace_call_replace(ip, addr);
+		return ftrace_modify_code(ip, old, new);
+	}
+
+	/*
+	 * Out of range jumps are called from modules.
+	 * Being that we are converting from nop, it had better
+	 * already have a module defined.
+	 */
+	if (!rec->arch.mod) {
+		printk(KERN_ERR "No module loaded\n");
+		return -EINVAL;
+	}
+
+	return __ftrace_make_call(rec, addr);
 }
 
 int ftrace_update_ftrace_func(ftrace_func_t func)
@@ -128,10 +521,10 @@ int ftrace_update_ftrace_func(ftrace_func_t func)
 
 int __init ftrace_dyn_arch_init(void *data)
 {
-	/* This is running in kstop_machine */
+	/* caller expects data to be zero */
+	unsigned long *p = data;
 
-	ftrace_mcount_set(data);
+	*p = 0;
 
 	return 0;
 }
-

arch/powerpc/kernel/idle.c

@@ -69,10 +69,15 @@ void cpu_idle(void)
 				smp_mb();
 				local_irq_disable();
 
+				/* Don't trace irqs off for idle */
+				stop_critical_timings();
+
 				/* check again after disabling irqs */
 				if (!need_resched() && !cpu_should_die())
 					ppc_md.power_save();
 
+				start_critical_timings();
+
 				local_irq_enable();
 				set_thread_flag(TIF_POLLING_NRFLAG);
 

arch/powerpc/kernel/module_32.c

@@ -22,6 +22,7 @@
 #include <linux/fs.h>
 #include <linux/string.h>
 #include <linux/kernel.h>
+#include <linux/ftrace.h>
 #include <linux/cache.h>
 #include <linux/bug.h>
 #include <linux/sort.h>
@@ -53,6 +54,9 @@ static unsigned int count_relocs(const Elf32_Rela *rela, unsigned int num)
 			r_addend = rela[i].r_addend;
 		}
 
+#ifdef CONFIG_DYNAMIC_FTRACE
+	_count_relocs++;	/* add one for ftrace_caller */
+#endif
 	return _count_relocs;
 }
 
@@ -306,5 +310,11 @@ int apply_relocate_add(Elf32_Shdr *sechdrs,
 			return -ENOEXEC;
 		}
 	}
+#ifdef CONFIG_DYNAMIC_FTRACE
+	module->arch.tramp =
+		do_plt_call(module->module_core,
+			    (unsigned long)ftrace_caller,
+			    sechdrs, module);
+#endif
 	return 0;
 }

arch/powerpc/kernel/module_64.c

@@ -20,6 +20,7 @@
 #include <linux/moduleloader.h>
 #include <linux/err.h>
 #include <linux/vmalloc.h>
+#include <linux/ftrace.h>
 #include <linux/bug.h>
 #include <asm/module.h>
 #include <asm/firmware.h>
@@ -163,6 +164,11 @@ static unsigned long get_stubs_size(const Elf64_Ehdr *hdr,
 		}
 	}
 
+#ifdef CONFIG_DYNAMIC_FTRACE
+	/* make the trampoline to the ftrace_caller */
+	relocs++;
+#endif
+
 	DEBUGP("Looks like a total of %lu stubs, max\n", relocs);
 	return relocs * sizeof(struct ppc64_stub_entry);
 }
@@ -441,5 +447,12 @@ int apply_relocate_add(Elf64_Shdr *sechdrs,
 		}
 	}
 
+#ifdef CONFIG_DYNAMIC_FTRACE
+	me->arch.toc = my_r2(sechdrs, me);
+	me->arch.tramp = stub_for_addr(sechdrs,
+				       (unsigned long)ftrace_caller,
+				       me);
+#endif
+
 	return 0;
 }

arch/um/include/asm/system.h

@@ -11,21 +11,21 @@ extern int get_signals(void);
 extern void block_signals(void);
 extern void unblock_signals(void);
 
-#define local_save_flags(flags) do { typecheck(unsigned long, flags); \
+#define raw_local_save_flags(flags) do { typecheck(unsigned long, flags); \
 				     (flags) = get_signals(); } while(0)
-#define local_irq_restore(flags) do { typecheck(unsigned long, flags); \
+#define raw_local_irq_restore(flags) do { typecheck(unsigned long, flags); \
 				      set_signals(flags); } while(0)
 
-#define local_irq_save(flags) do { local_save_flags(flags); \
-                                   local_irq_disable(); } while(0)
+#define raw_local_irq_save(flags) do { raw_local_save_flags(flags); \
+                                   raw_local_irq_disable(); } while(0)
 
-#define local_irq_enable() unblock_signals()
-#define local_irq_disable() block_signals()
+#define raw_local_irq_enable() unblock_signals()
+#define raw_local_irq_disable() block_signals()
 
 #define irqs_disabled()                 \
 ({                                      \
         unsigned long flags;            \
-        local_save_flags(flags);        \
+        raw_local_save_flags(flags);        \
         (flags == 0);                   \
 })
 

arch/x86/Kconfig

@@ -29,11 +29,14 @@ config X86
 	select HAVE_FTRACE_MCOUNT_RECORD
 	select HAVE_DYNAMIC_FTRACE
 	select HAVE_FUNCTION_TRACER
+	select HAVE_FUNCTION_RET_TRACER if X86_32
+	select HAVE_FUNCTION_TRACE_MCOUNT_TEST
 	select HAVE_KVM if ((X86_32 && !X86_VOYAGER && !X86_VISWS && !X86_NUMAQ) || X86_64)
 	select HAVE_ARCH_KGDB if !X86_VOYAGER
 	select HAVE_ARCH_TRACEHOOK
 	select HAVE_GENERIC_DMA_COHERENT if X86_32
 	select HAVE_EFFICIENT_UNALIGNED_ACCESS
+	select USER_STACKTRACE_SUPPORT
 
 config ARCH_DEFCONFIG
 	string

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

@@ -17,8 +17,40 @@ static inline unsigned long ftrace_call_adjust(unsigned long addr)
 	 */
 	return addr - 1;
 }
-#endif
 
+#ifdef CONFIG_DYNAMIC_FTRACE
+
+struct dyn_arch_ftrace {
+	/* No extra data needed for x86 */
+};
+
+#endif /*  CONFIG_DYNAMIC_FTRACE */
+#endif /* __ASSEMBLY__ */
 #endif /* CONFIG_FUNCTION_TRACER */
 
+#ifdef CONFIG_FUNCTION_RET_TRACER
+
+#ifndef __ASSEMBLY__
+
+/*
+ * Stack of return addresses for functions
+ * of a thread.
+ * Used in struct thread_info
+ */
+struct ftrace_ret_stack {
+	unsigned long ret;
+	unsigned long func;
+	unsigned long long calltime;
+};
+
+/*
+ * Primary handler of a function return.
+ * It relays on ftrace_return_to_handler.
+ * Defined in entry32.S
+ */
+extern void return_to_handler(void);
+
+#endif /* __ASSEMBLY__ */
+#endif /* CONFIG_FUNCTION_RET_TRACER */
+
 #endif /* _ASM_X86_FTRACE_H */

arch/x86/include/asm/thread_info.h

@@ -20,6 +20,8 @@
 struct task_struct;
 struct exec_domain;
 #include <asm/processor.h>
+#include <asm/ftrace.h>
+#include <asm/atomic.h>
 
 struct thread_info {
 	struct task_struct	*task;		/* main task structure */

arch/x86/include/asm/uaccess.h

@@ -157,6 +157,7 @@ extern int __get_user_bad(void);
 	int __ret_gu;							\
 	unsigned long __val_gu;						\
 	__chk_user_ptr(ptr);						\
+	might_fault();							\
 	switch (sizeof(*(ptr))) {					\
 	case 1:								\
 		__get_user_x(1, __ret_gu, __val_gu, ptr);		\
@@ -241,6 +242,7 @@ extern void __put_user_8(void);
 	int __ret_pu;						\
 	__typeof__(*(ptr)) __pu_val;				\
 	__chk_user_ptr(ptr);					\
+	might_fault();						\
 	__pu_val = x;						\
 	switch (sizeof(*(ptr))) {				\
 	case 1:							\

arch/x86/include/asm/uaccess_32.h

@@ -82,8 +82,8 @@ __copy_to_user_inatomic(void __user *to, const void *from, unsigned long n)
 static __always_inline unsigned long __must_check
 __copy_to_user(void __user *to, const void *from, unsigned long n)
 {
-       might_sleep();
-       return __copy_to_user_inatomic(to, from, n);
+	might_fault();
+	return __copy_to_user_inatomic(to, from, n);
 }
 
 static __always_inline unsigned long
@@ -137,7 +137,7 @@ __copy_from_user_inatomic(void *to, const void __user *from, unsigned long n)
 static __always_inline unsigned long
 __copy_from_user(void *to, const void __user *from, unsigned long n)
 {
-	might_sleep();
+	might_fault();
 	if (__builtin_constant_p(n)) {
 		unsigned long ret;
 
@@ -159,7 +159,7 @@ __copy_from_user(void *to, const void __user *from, unsigned long n)
 static __always_inline unsigned long __copy_from_user_nocache(void *to,
 				const void __user *from, unsigned long n)
 {
-	might_sleep();
+	might_fault();
 	if (__builtin_constant_p(n)) {
 		unsigned long ret;
 

arch/x86/include/asm/uaccess_64.h

@@ -29,6 +29,8 @@ static __always_inline __must_check
 int __copy_from_user(void *dst, const void __user *src, unsigned size)
 {
 	int ret = 0;
+
+	might_fault();
 	if (!__builtin_constant_p(size))
 		return copy_user_generic(dst, (__force void *)src, size);
 	switch (size) {
@@ -71,6 +73,8 @@ static __always_inline __must_check
 int __copy_to_user(void __user *dst, const void *src, unsigned size)
 {
 	int ret = 0;
+
+	might_fault();
 	if (!__builtin_constant_p(size))
 		return copy_user_generic((__force void *)dst, src, size);
 	switch (size) {
@@ -113,6 +117,8 @@ static __always_inline __must_check
 int __copy_in_user(void __user *dst, const void __user *src, unsigned size)
 {
 	int ret = 0;
+
+	might_fault();
 	if (!__builtin_constant_p(size))
 		return copy_user_generic((__force void *)dst,
 					 (__force void *)src, size);

arch/x86/kernel/Makefile

@@ -14,6 +14,11 @@ CFLAGS_REMOVE_paravirt-spinlocks.o = -pg
 CFLAGS_REMOVE_ftrace.o = -pg
 endif
 
+ifdef CONFIG_FUNCTION_RET_TRACER
+# Don't trace __switch_to() but let it for function tracer
+CFLAGS_REMOVE_process_32.o = -pg
+endif
+
 #
 # vsyscalls (which work on the user stack) should have
 # no stack-protector checks:
@@ -65,6 +70,7 @@ obj-$(CONFIG_X86_LOCAL_APIC)	+= apic.o nmi.o
 obj-$(CONFIG_X86_IO_APIC)	+= io_apic.o
 obj-$(CONFIG_X86_REBOOTFIXUPS)	+= reboot_fixups_32.o
 obj-$(CONFIG_DYNAMIC_FTRACE)	+= ftrace.o
+obj-$(CONFIG_FUNCTION_RET_TRACER)	+= ftrace.o
 obj-$(CONFIG_KEXEC)		+= machine_kexec_$(BITS).o
 obj-$(CONFIG_KEXEC)		+= relocate_kernel_$(BITS).o crash.o
 obj-$(CONFIG_CRASH_DUMP)	+= crash_dump_$(BITS).o

arch/x86/kernel/entry_32.S

@@ -1157,6 +1157,9 @@ ENTRY(mcount)
 END(mcount)
 
 ENTRY(ftrace_caller)
+	cmpl $0, function_trace_stop
+	jne  ftrace_stub
+
 	pushl %eax
 	pushl %ecx
 	pushl %edx
@@ -1180,8 +1183,15 @@ END(ftrace_caller)
 #else /* ! CONFIG_DYNAMIC_FTRACE */
 
 ENTRY(mcount)
+	cmpl $0, function_trace_stop
+	jne  ftrace_stub
+
 	cmpl $ftrace_stub, ftrace_trace_function
 	jnz trace
+#ifdef CONFIG_FUNCTION_RET_TRACER
+	cmpl $ftrace_stub, ftrace_function_return
+	jnz ftrace_return_caller
+#endif
 .globl ftrace_stub
 ftrace_stub:
 	ret
@@ -1200,12 +1210,42 @@ trace:
 	popl %edx
 	popl %ecx
 	popl %eax
-
 	jmp ftrace_stub
 END(mcount)
 #endif /* CONFIG_DYNAMIC_FTRACE */
 #endif /* CONFIG_FUNCTION_TRACER */
 
+#ifdef CONFIG_FUNCTION_RET_TRACER
+ENTRY(ftrace_return_caller)
+	cmpl $0, function_trace_stop
+	jne ftrace_stub
+
+	pushl %eax
+	pushl %ecx
+	pushl %edx
+	movl 0xc(%esp), %edx
+	lea 0x4(%ebp), %eax
+	call prepare_ftrace_return
+	popl %edx
+	popl %ecx
+	popl %eax
+	ret
+END(ftrace_return_caller)
+
+.globl return_to_handler
+return_to_handler:
+	pushl $0
+	pushl %eax
+	pushl %ecx
+	pushl %edx
+	call ftrace_return_to_handler
+	movl %eax, 0xc(%esp)
+	popl %edx
+	popl %ecx
+	popl %eax
+	ret
+#endif
+
 .section .rodata,"a"
 #include "syscall_table_32.S"
 

arch/x86/kernel/entry_64.S

@@ -68,6 +68,8 @@ ENTRY(mcount)
 END(mcount)
 
 ENTRY(ftrace_caller)
+	cmpl $0, function_trace_stop
+	jne  ftrace_stub
 
 	/* taken from glibc */
 	subq $0x38, %rsp
@@ -103,6 +105,9 @@ END(ftrace_caller)
 
 #else /* ! CONFIG_DYNAMIC_FTRACE */
 ENTRY(mcount)
+	cmpl $0, function_trace_stop
+	jne  ftrace_stub
+
 	cmpq $ftrace_stub, ftrace_trace_function
 	jnz trace
 .globl ftrace_stub

arch/x86/kernel/ftrace.c

@@ -14,14 +14,17 @@
 #include <linux/uaccess.h>
 #include <linux/ftrace.h>
 #include <linux/percpu.h>
+#include <linux/sched.h>
 #include <linux/init.h>
 #include <linux/list.h>
 
 #include <asm/ftrace.h>
+#include <linux/ftrace.h>
 #include <asm/nops.h>
+#include <asm/nmi.h>
 
 
-static unsigned char ftrace_nop[MCOUNT_INSN_SIZE];
+#ifdef CONFIG_DYNAMIC_FTRACE
 
 union ftrace_code_union {
 	char code[MCOUNT_INSN_SIZE];
@@ -31,18 +34,12 @@ union ftrace_code_union {
 	} __attribute__((packed));
 };
 
-
 static int ftrace_calc_offset(long ip, long addr)
 {
 	return (int)(addr - ip);
 }
 
-unsigned char *ftrace_nop_replace(void)
-{
-	return ftrace_nop;
-}
-
-unsigned char *ftrace_call_replace(unsigned long ip, unsigned long addr)
+static unsigned char *ftrace_call_replace(unsigned long ip, unsigned long addr)
 {
 	static union ftrace_code_union calc;
 
@@ -56,7 +53,143 @@ unsigned char *ftrace_call_replace(unsigned long ip, unsigned long addr)
 	return calc.code;
 }
 
-int
+/*
+ * 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;
+}
+
+
+
+
+static unsigned char ftrace_nop[MCOUNT_INSN_SIZE];
+
+static unsigned char *ftrace_nop_replace(void)
+{
+	return ftrace_nop;
+}
+
+static int
 ftrace_modify_code(unsigned long ip, unsigned char *old_code,
 		   unsigned char *new_code)
 {
@@ -81,7 +214,7 @@ 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();
@@ -89,6 +222,29 @@ ftrace_modify_code(unsigned long ip, unsigned char *old_code,
 	return 0;
 }
 
+int ftrace_make_nop(struct module *mod,
+		    struct dyn_ftrace *rec, unsigned long addr)
+{
+	unsigned char *new, *old;
+	unsigned long ip = rec->ip;
+
+	old = ftrace_call_replace(ip, addr);
+	new = ftrace_nop_replace();
+
+	return ftrace_modify_code(rec->ip, old, new);
+}
+
+int ftrace_make_call(struct dyn_ftrace *rec, unsigned long addr)
+{
+	unsigned char *new, *old;
+	unsigned long ip = rec->ip;
+
+	old = ftrace_nop_replace();
+	new = ftrace_call_replace(ip, addr);
+
+	return ftrace_modify_code(rec->ip, old, new);
+}
+
 int ftrace_update_ftrace_func(ftrace_func_t func)
 {
 	unsigned long ip = (unsigned long)(&ftrace_call);
@@ -165,3 +321,139 @@ int __init ftrace_dyn_arch_init(void *data)
 
 	return 0;
 }
+#endif
+
+#ifdef CONFIG_FUNCTION_RET_TRACER
+
+#ifndef CONFIG_DYNAMIC_FTRACE
+
+/*
+ * These functions are picked from those used on
+ * this page for dynamic ftrace. They have been
+ * simplified to ignore all traces in NMI context.
+ */
+static atomic_t in_nmi;
+
+void ftrace_nmi_enter(void)
+{
+	atomic_inc(&in_nmi);
+}
+
+void ftrace_nmi_exit(void)
+{
+	atomic_dec(&in_nmi);
+}
+#endif /* !CONFIG_DYNAMIC_FTRACE */
+
+/* Add a function return address to the trace stack on thread info.*/
+static int push_return_trace(unsigned long ret, unsigned long long time,
+				unsigned long func)
+{
+	int index;
+
+	if (!current->ret_stack)
+		return -EBUSY;
+
+	/* The return trace stack is full */
+	if (current->curr_ret_stack == FTRACE_RETFUNC_DEPTH - 1) {
+		atomic_inc(&current->trace_overrun);
+		return -EBUSY;
+	}
+
+	index = ++current->curr_ret_stack;
+	barrier();
+	current->ret_stack[index].ret = ret;
+	current->ret_stack[index].func = func;
+	current->ret_stack[index].calltime = time;
+
+	return 0;
+}
+
+/* Retrieve a function return address to the trace stack on thread info.*/
+static void pop_return_trace(unsigned long *ret, unsigned long long *time,
+				unsigned long *func, unsigned long *overrun)
+{
+	int index;
+
+	index = current->curr_ret_stack;
+	*ret = current->ret_stack[index].ret;
+	*func = current->ret_stack[index].func;
+	*time = current->ret_stack[index].calltime;
+	*overrun = atomic_read(&current->trace_overrun);
+	current->curr_ret_stack--;
+}
+
+/*
+ * Send the trace to the ring-buffer.
+ * @return the original return address.
+ */
+unsigned long ftrace_return_to_handler(void)
+{
+	struct ftrace_retfunc trace;
+	pop_return_trace(&trace.ret, &trace.calltime, &trace.func,
+			&trace.overrun);
+	trace.rettime = cpu_clock(raw_smp_processor_id());
+	ftrace_function_return(&trace);
+
+	return trace.ret;
+}
+
+/*
+ * Hook the return address and push it in the stack of return addrs
+ * in current thread info.
+ */
+void prepare_ftrace_return(unsigned long *parent, unsigned long self_addr)
+{
+	unsigned long old;
+	unsigned long long calltime;
+	int faulted;
+	unsigned long return_hooker = (unsigned long)
+				&return_to_handler;
+
+	/* Nmi's are currently unsupported */
+	if (atomic_read(&in_nmi))
+		return;
+
+	/*
+	 * Protect against fault, even if it shouldn't
+	 * happen. This tool is too much intrusive to
+	 * ignore such a protection.
+	 */
+	asm volatile(
+		"1: movl (%[parent_old]), %[old]\n"
+		"2: movl %[return_hooker], (%[parent_replaced])\n"
+		"   movl $0, %[faulted]\n"
+
+		".section .fixup, \"ax\"\n"
+		"3: movl $1, %[faulted]\n"
+		".previous\n"
+
+		".section __ex_table, \"a\"\n"
+		"   .long 1b, 3b\n"
+		"   .long 2b, 3b\n"
+		".previous\n"
+
+		: [parent_replaced] "=r" (parent), [old] "=r" (old),
+		  [faulted] "=r" (faulted)
+		: [parent_old] "0" (parent), [return_hooker] "r" (return_hooker)
+		: "memory"
+	);
+
+	if (WARN_ON(faulted)) {
+		unregister_ftrace_return();
+		return;
+	}
+
+	if (WARN_ON(!__kernel_text_address(old))) {
+		unregister_ftrace_return();
+		*parent = old;
+		return;
+	}
+
+	calltime = cpu_clock(raw_smp_processor_id());
+
+	if (push_return_trace(old, calltime, self_addr) == -EBUSY)
+		*parent = old;
+}
+
+#endif /* CONFIG_FUNCTION_RET_TRACER */

arch/x86/kernel/stacktrace.c

@@ -6,6 +6,7 @@
 #include <linux/sched.h>
 #include <linux/stacktrace.h>
 #include <linux/module.h>
+#include <linux/uaccess.h>
 #include <asm/stacktrace.h>
 
 static void save_stack_warning(void *data, char *msg)
@@ -83,3 +84,66 @@ void save_stack_trace_tsk(struct task_struct *tsk, struct stack_trace *trace)
 		trace->entries[trace->nr_entries++] = ULONG_MAX;
 }
 EXPORT_SYMBOL_GPL(save_stack_trace_tsk);
+
+/* Userspace stacktrace - based on kernel/trace/trace_sysprof.c */
+
+struct stack_frame {
+	const void __user	*next_fp;
+	unsigned long		ret_addr;
+};
+
+static int copy_stack_frame(const void __user *fp, struct stack_frame *frame)
+{
+	int ret;
+
+	if (!access_ok(VERIFY_READ, fp, sizeof(*frame)))
+		return 0;
+
+	ret = 1;
+	pagefault_disable();
+	if (__copy_from_user_inatomic(frame, fp, sizeof(*frame)))
+		ret = 0;
+	pagefault_enable();
+
+	return ret;
+}
+
+static inline void __save_stack_trace_user(struct stack_trace *trace)
+{
+	const struct pt_regs *regs = task_pt_regs(current);
+	const void __user *fp = (const void __user *)regs->bp;
+
+	if (trace->nr_entries < trace->max_entries)
+		trace->entries[trace->nr_entries++] = regs->ip;
+
+	while (trace->nr_entries < trace->max_entries) {
+		struct stack_frame frame;
+
+		frame.next_fp = NULL;
+		frame.ret_addr = 0;
+		if (!copy_stack_frame(fp, &frame))
+			break;
+		if ((unsigned long)fp < regs->sp)
+			break;
+		if (frame.ret_addr) {
+			trace->entries[trace->nr_entries++] =
+				frame.ret_addr;
+		}
+		if (fp == frame.next_fp)
+			break;
+		fp = frame.next_fp;
+	}
+}
+
+void save_stack_trace_user(struct stack_trace *trace)
+{
+	/*
+	 * Trace user stack if we are not a kernel thread
+	 */
+	if (current->mm) {
+		__save_stack_trace_user(trace);
+	}
+	if (trace->nr_entries < trace->max_entries)
+		trace->entries[trace->nr_entries++] = ULONG_MAX;
+}
+

arch/x86/kernel/vsyscall_64.c

@@ -17,6 +17,9 @@
  *  want per guest time just set the kernel.vsyscall64 sysctl to 0.
  */
 
+/* Disable profiling for userspace code: */
+#define DISABLE_BRANCH_PROFILING
+
 #include <linux/time.h>
 #include <linux/init.h>
 #include <linux/kernel.h>

arch/x86/lib/usercopy_32.c

@@ -39,7 +39,7 @@ static inline int __movsl_is_ok(unsigned long a1, unsigned long a2, unsigned lon
 #define __do_strncpy_from_user(dst, src, count, res)			   \
 do {									   \
 	int __d0, __d1, __d2;						   \
-	might_sleep();							   \
+	might_fault();							   \
 	__asm__ __volatile__(						   \
 		"	testl %1,%1\n"					   \
 		"	jz 2f\n"					   \
@@ -126,7 +126,7 @@ EXPORT_SYMBOL(strncpy_from_user);
 #define __do_clear_user(addr,size)					\
 do {									\
 	int __d0;							\
-	might_sleep();							\
+	might_fault();							\
 	__asm__ __volatile__(						\
 		"0:	rep; stosl\n"					\
 		"	movl %2,%0\n"					\
@@ -155,7 +155,7 @@ do {									\
 unsigned long
 clear_user(void __user *to, unsigned long n)
 {
-	might_sleep();
+	might_fault();
 	if (access_ok(VERIFY_WRITE, to, n))
 		__do_clear_user(to, n);
 	return n;
@@ -197,7 +197,7 @@ long strnlen_user(const char __user *s, long n)
 	unsigned long mask = -__addr_ok(s);
 	unsigned long res, tmp;
 
-	might_sleep();
+	might_fault();
 
 	__asm__ __volatile__(
 		"	testl %0, %0\n"

arch/x86/lib/usercopy_64.c

@@ -15,7 +15,7 @@
 #define __do_strncpy_from_user(dst,src,count,res)			   \
 do {									   \
 	long __d0, __d1, __d2;						   \
-	might_sleep();							   \
+	might_fault();							   \
 	__asm__ __volatile__(						   \
 		"	testq %1,%1\n"					   \
 		"	jz 2f\n"					   \
@@ -64,7 +64,7 @@ EXPORT_SYMBOL(strncpy_from_user);
 unsigned long __clear_user(void __user *addr, unsigned long size)
 {
 	long __d0;
-	might_sleep();
+	might_fault();
 	/* no memory constraint because it doesn't change any memory gcc knows
 	   about */
 	asm volatile(

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;

arch/x86/vdso/vclock_gettime.c

@@ -9,6 +9,9 @@
  * Also alternative() doesn't work.
  */
 
+/* Disable profiling for userspace code: */
+#define DISABLE_BRANCH_PROFILING
+
 #include <linux/kernel.h>
 #include <linux/posix-timers.h>
 #include <linux/time.h>

drivers/char/sysrq.c

@@ -274,6 +274,22 @@ static struct sysrq_key_op sysrq_showstate_blocked_op = {
 	.enable_mask	= SYSRQ_ENABLE_DUMP,
 };
 
+#ifdef CONFIG_TRACING
+#include <linux/ftrace.h>
+
+static void sysrq_ftrace_dump(int key, struct tty_struct *tty)
+{
+	ftrace_dump();
+}
+static struct sysrq_key_op sysrq_ftrace_dump_op = {
+	.handler	= sysrq_ftrace_dump,
+	.help_msg	= "dumpZ-ftrace-buffer",
+	.action_msg	= "Dump ftrace buffer",
+	.enable_mask	= SYSRQ_ENABLE_DUMP,
+};
+#else
+#define sysrq_ftrace_dump_op (*(struct sysrq_key_op *)0)
+#endif
 
 static void sysrq_handle_showmem(int key, struct tty_struct *tty)
 {
@@ -406,7 +422,7 @@ static struct sysrq_key_op *sysrq_key_table[36] = {
 	NULL,				/* x */
 	/* y: May be registered on sparc64 for global register dump */
 	NULL,				/* y */
-	NULL				/* z */
+	&sysrq_ftrace_dump_op,		/* z */
 };
 
 /* key2index calculation, -1 on invalid index */

drivers/video/pxafb.c

@@ -804,6 +804,9 @@ static int pxafb_smart_thread(void *arg)
 
 static int pxafb_smart_init(struct pxafb_info *fbi)
 {
+	if (!(fbi->lccr0 | LCCR0_LCDT))
+		return 0;
+
 	fbi->smart_thread = kthread_run(pxafb_smart_thread, fbi,
 					"lcd_refresh");
 	if (IS_ERR(fbi->smart_thread)) {
@@ -1372,7 +1375,7 @@ static void pxafb_decode_mach_info(struct pxafb_info *fbi,
 	fbi->cmap_inverse	= inf->cmap_inverse;
 	fbi->cmap_static	= inf->cmap_static;
 
-	switch (lcd_conn & 0xf) {
+	switch (lcd_conn & LCD_TYPE_MASK) {
 	case LCD_TYPE_MONO_STN:
 		fbi->lccr0 = LCCR0_CMS;
 		break;

fs/seq_file.c

@@ -357,7 +357,18 @@ int seq_printf(struct seq_file *m, const char *f, ...)
 }
 EXPORT_SYMBOL(seq_printf);
 
-static char *mangle_path(char *s, char *p, char *esc)
+/**
+ *	mangle_path -	mangle and copy path to buffer beginning
+ *	@s: buffer start
+ *	@p: beginning of path in above buffer
+ *	@esc: set of characters that need escaping
+ *
+ *      Copy the path from @p to @s, replacing each occurrence of character from
+ *      @esc with usual octal escape.
+ *      Returns pointer past last written character in @s, or NULL in case of
+ *      failure.
+ */
+char *mangle_path(char *s, char *p, char *esc)
 {
 	while (s <= p) {
 		char c = *p++;
@@ -376,6 +387,7 @@ static char *mangle_path(char *s, char *p, char *esc)
 	}
 	return NULL;
 }
+EXPORT_SYMBOL_GPL(mangle_path);
 
 /*
  * return the absolute path of 'dentry' residing in mount 'mnt'.

include/asm-generic/vmlinux.lds.h

@@ -45,6 +45,22 @@
 #define MCOUNT_REC()
 #endif
 
+#ifdef CONFIG_TRACE_BRANCH_PROFILING
+#define LIKELY_PROFILE()	VMLINUX_SYMBOL(__start_annotated_branch_profile) = .; \
+				*(_ftrace_annotated_branch)			      \
+				VMLINUX_SYMBOL(__stop_annotated_branch_profile) = .;
+#else
+#define LIKELY_PROFILE()
+#endif
+
+#ifdef CONFIG_PROFILE_ALL_BRANCHES
+#define BRANCH_PROFILE()	VMLINUX_SYMBOL(__start_branch_profile) = .;   \
+				*(_ftrace_branch)			      \
+				VMLINUX_SYMBOL(__stop_branch_profile) = .;
+#else
+#define BRANCH_PROFILE()
+#endif
+
 /* .data section */
 #define DATA_DATA							\
 	*(.data)							\
@@ -60,9 +76,12 @@
 	VMLINUX_SYMBOL(__start___markers) = .;				\
 	*(__markers)							\
 	VMLINUX_SYMBOL(__stop___markers) = .;				\
+	. = ALIGN(32);							\
 	VMLINUX_SYMBOL(__start___tracepoints) = .;			\
 	*(__tracepoints)						\
-	VMLINUX_SYMBOL(__stop___tracepoints) = .;
+	VMLINUX_SYMBOL(__stop___tracepoints) = .;			\
+	LIKELY_PROFILE()		       				\
+	BRANCH_PROFILE()
 
 #define RO_DATA(align)							\
 	. = ALIGN((align));						\

include/linux/compiler.h

@@ -59,8 +59,88 @@ extern void __chk_io_ptr(const volatile void __iomem *);
  * specific implementations come from the above header files
  */
 
-#define likely(x)	__builtin_expect(!!(x), 1)
-#define unlikely(x)	__builtin_expect(!!(x), 0)
+struct ftrace_branch_data {
+	const char *func;
+	const char *file;
+	unsigned line;
+	union {
+		struct {
+			unsigned long correct;
+			unsigned long incorrect;
+		};
+		struct {
+			unsigned long miss;
+			unsigned long hit;
+		};
+	};
+};
+
+/*
+ * Note: DISABLE_BRANCH_PROFILING can be used by special lowlevel code
+ * to disable branch tracing on a per file basis.
+ */
+#if defined(CONFIG_TRACE_BRANCH_PROFILING) && !defined(DISABLE_BRANCH_PROFILING)
+void ftrace_likely_update(struct ftrace_branch_data *f, int val, int expect);
+
+#define likely_notrace(x)	__builtin_expect(!!(x), 1)
+#define unlikely_notrace(x)	__builtin_expect(!!(x), 0)
+
+#define __branch_check__(x, expect) ({					\
+			int ______r;					\
+			static struct ftrace_branch_data		\
+				__attribute__((__aligned__(4)))		\
+				__attribute__((section("_ftrace_annotated_branch"))) \
+				______f = {				\
+				.func = __func__,			\
+				.file = __FILE__,			\
+				.line = __LINE__,			\
+			};						\
+			______r = likely_notrace(x);			\
+			ftrace_likely_update(&______f, ______r, expect); \
+			______r;					\
+		})
+
+/*
+ * Using __builtin_constant_p(x) to ignore cases where the return
+ * value is always the same.  This idea is taken from a similar patch
+ * written by Daniel Walker.
+ */
+# ifndef likely
+#  define likely(x)	(__builtin_constant_p(x) ? !!(x) : __branch_check__(x, 1))
+# endif
+# ifndef unlikely
+#  define unlikely(x)	(__builtin_constant_p(x) ? !!(x) : __branch_check__(x, 0))
+# endif
+
+#ifdef CONFIG_PROFILE_ALL_BRANCHES
+/*
+ * "Define 'is'", Bill Clinton
+ * "Define 'if'", Steven Rostedt
+ */
+#define if(cond) if (__builtin_constant_p((cond)) ? !!(cond) :		\
+	({								\
+		int ______r;						\
+		static struct ftrace_branch_data			\
+			__attribute__((__aligned__(4)))			\
+			__attribute__((section("_ftrace_branch")))	\
+			______f = {					\
+				.func = __func__,			\
+				.file = __FILE__,			\
+				.line = __LINE__,			\
+			};						\
+		______r = !!(cond);					\
+		if (______r)						\
+			______f.hit++;					\
+		else							\
+			______f.miss++;					\
+		______r;						\
+	}))
+#endif /* CONFIG_PROFILE_ALL_BRANCHES */
+
+#else
+# define likely(x)	__builtin_expect(!!(x), 1)
+# define unlikely(x)	__builtin_expect(!!(x), 0)
+#endif
 
 /* Optimization barrier */
 #ifndef barrier

include/linux/debug_locks.h

@@ -17,7 +17,7 @@ extern int debug_locks_off(void);
 ({									\
 	int __ret = 0;							\
 									\
-	if (unlikely(c)) {						\
+	if (!oops_in_progress && unlikely(c)) {				\
 		if (debug_locks_off() && !debug_locks_silent)		\
 			WARN_ON(1);					\
 		__ret = 1;						\

include/linux/ftrace.h

@@ -23,6 +23,45 @@ struct ftrace_ops {
 	struct ftrace_ops *next;
 };
 
+extern int function_trace_stop;
+
+/*
+ * Type of the current tracing.
+ */
+enum ftrace_tracing_type_t {
+	FTRACE_TYPE_ENTER = 0, /* Hook the call of the function */
+	FTRACE_TYPE_RETURN,	/* Hook the return of the function */
+};
+
+/* Current tracing type, default is FTRACE_TYPE_ENTER */
+extern enum ftrace_tracing_type_t ftrace_tracing_type;
+
+/**
+ * ftrace_stop - stop function tracer.
+ *
+ * A quick way to stop the function tracer. Note this an on off switch,
+ * it is not something that is recursive like preempt_disable.
+ * This does not disable the calling of mcount, it only stops the
+ * calling of functions from mcount.
+ */
+static inline void ftrace_stop(void)
+{
+	function_trace_stop = 1;
+}
+
+/**
+ * ftrace_start - start the function tracer.
+ *
+ * This function is the inverse of ftrace_stop. This does not enable
+ * the function tracing if the function tracer is disabled. This only
+ * sets the function tracer flag to continue calling the functions
+ * from mcount.
+ */
+static inline void ftrace_start(void)
+{
+	function_trace_stop = 0;
+}
+
 /*
  * The ftrace_ops must be a static and should also
  * be read_mostly.  These functions do modify read_mostly variables
@@ -41,9 +80,13 @@ extern void ftrace_stub(unsigned long a0, unsigned long a1);
 # define unregister_ftrace_function(ops) do { } while (0)
 # define clear_ftrace_function(ops) do { } while (0)
 static inline void ftrace_kill(void) { }
+static inline void ftrace_stop(void) { }
+static inline void ftrace_start(void) { }
 #endif /* CONFIG_FUNCTION_TRACER */
 
 #ifdef CONFIG_DYNAMIC_FTRACE
+/* asm/ftrace.h must be defined for archs supporting dynamic ftrace */
+#include <asm/ftrace.h>
 
 enum {
 	FTRACE_FL_FREE		= (1 << 0),
@@ -59,6 +102,7 @@ struct dyn_ftrace {
 	struct list_head	list;
 	unsigned long		ip; /* address of mcount call-site */
 	unsigned long		flags;
+	struct dyn_arch_ftrace	arch;
 };
 
 int ftrace_force_update(void);
@@ -66,19 +110,43 @@ void ftrace_set_filter(unsigned char *buf, int len, int reset);
 
 /* defined in arch */
 extern int ftrace_ip_converted(unsigned long ip);
-extern unsigned char *ftrace_nop_replace(void);
-extern unsigned char *ftrace_call_replace(unsigned long ip, unsigned long addr);
 extern int ftrace_dyn_arch_init(void *data);
 extern int ftrace_update_ftrace_func(ftrace_func_t func);
 extern void ftrace_caller(void);
 extern void ftrace_call(void);
 extern void mcount_call(void);
+#ifdef CONFIG_FUNCTION_RET_TRACER
+extern void ftrace_return_caller(void);
+#endif
+
+/**
+ * ftrace_make_nop - convert code into top
+ * @mod: module structure if called by module load initialization
+ * @rec: the mcount call site record
+ * @addr: the address that the call site should be calling
+ *
+ * This is a very sensitive operation and great care needs
+ * to be taken by the arch.  The operation should carefully
+ * read the location, check to see if what is read is indeed
+ * what we expect it to be, and then on success of the compare,
+ * it should write to the location.
+ *
+ * The code segment at @rec->ip should be a caller to @addr
+ *
+ * Return must be:
+ *  0 on success
+ *  -EFAULT on error reading the location
+ *  -EINVAL on a failed compare of the contents
+ *  -EPERM  on error writing to the location
+ * Any other value will be considered a failure.
+ */
+extern int ftrace_make_nop(struct module *mod,
+			   struct dyn_ftrace *rec, unsigned long addr);
 
 /**
- * ftrace_modify_code - modify code segment
- * @ip: the address of the code segment
- * @old_code: the contents of what is expected to be there
- * @new_code: the code to patch in
+ * ftrace_make_call - convert a nop call site into a call to addr
+ * @rec: the mcount call site record
+ * @addr: the address that the call site should call
  *
  * This is a very sensitive operation and great care needs
  * to be taken by the arch.  The operation should carefully
@@ -86,6 +154,8 @@ extern void mcount_call(void);
  * what we expect it to be, and then on success of the compare,
  * it should write to the location.
  *
+ * The code segment at @rec->ip should be a nop
+ *
  * Return must be:
  *  0 on success
  *  -EFAULT on error reading the location
@@ -93,8 +163,11 @@ extern void mcount_call(void);
  *  -EPERM  on error writing to the location
  * Any other value will be considered a failure.
  */
-extern int ftrace_modify_code(unsigned long ip, unsigned char *old_code,
-			      unsigned char *new_code);
+extern int ftrace_make_call(struct dyn_ftrace *rec, unsigned long addr);
+
+
+/* May be defined in arch */
+extern int ftrace_arch_read_dyn_info(char *buf, int size);
 
 extern int skip_trace(unsigned long ip);
 
@@ -102,7 +175,6 @@ extern void ftrace_release(void *start, unsigned long size);
 
 extern void ftrace_disable_daemon(void);
 extern void ftrace_enable_daemon(void);
-
 #else
 # define skip_trace(ip)				({ 0; })
 # define ftrace_force_update()			({ 0; })
@@ -181,6 +253,12 @@ static inline void __ftrace_enabled_restore(int enabled)
 #endif
 
 #ifdef CONFIG_TRACING
+extern int ftrace_dump_on_oops;
+
+extern void tracing_start(void);
+extern void tracing_stop(void);
+extern void ftrace_off_permanent(void);
+
 extern void
 ftrace_special(unsigned long arg1, unsigned long arg2, unsigned long arg3);
 
@@ -211,6 +289,9 @@ ftrace_special(unsigned long arg1, unsigned long arg2, unsigned long arg3) { }
 static inline int
 ftrace_printk(const char *fmt, ...) __attribute__ ((format (printf, 1, 0)));
 
+static inline void tracing_start(void) { }
+static inline void tracing_stop(void) { }
+static inline void ftrace_off_permanent(void) { }
 static inline int
 ftrace_printk(const char *fmt, ...)
 {
@@ -221,33 +302,44 @@ static inline void ftrace_dump(void) { }
 
 #ifdef CONFIG_FTRACE_MCOUNT_RECORD
 extern void ftrace_init(void);
-extern void ftrace_init_module(unsigned long *start, unsigned long *end);
+extern void ftrace_init_module(struct module *mod,
+			       unsigned long *start, unsigned long *end);
 #else
 static inline void ftrace_init(void) { }
 static inline void
-ftrace_init_module(unsigned long *start, unsigned long *end) { }
+ftrace_init_module(struct module *mod,
+		   unsigned long *start, unsigned long *end) { }
 #endif
 
 
-struct boot_trace {
-	pid_t			caller;
-	char			func[KSYM_NAME_LEN];
-	int			result;
-	unsigned long long	duration;		/* usecs */
-	ktime_t			calltime;
-	ktime_t			rettime;
+/*
+ * Structure that defines a return function trace.
+ */
+struct ftrace_retfunc {
+	unsigned long ret; /* Return address */
+	unsigned long func; /* Current function */
+	unsigned long long calltime;
+	unsigned long long rettime;
+	/* Number of functions that overran the depth limit for current task */
+	unsigned long overrun;
 };
 
-#ifdef CONFIG_BOOT_TRACER
-extern void trace_boot(struct boot_trace *it, initcall_t fn);
-extern void start_boot_trace(void);
-extern void stop_boot_trace(void);
-#else
-static inline void trace_boot(struct boot_trace *it, initcall_t fn) { }
-static inline void start_boot_trace(void) { }
-static inline void stop_boot_trace(void) { }
-#endif
+#ifdef CONFIG_FUNCTION_RET_TRACER
+#define FTRACE_RETFUNC_DEPTH 50
+#define FTRACE_RETSTACK_ALLOC_SIZE 32
+/* Type of a callback handler of tracing return function */
+typedef void (*trace_function_return_t)(struct ftrace_retfunc *);
 
+extern int register_ftrace_return(trace_function_return_t func);
+/* The current handler in use */
+extern trace_function_return_t ftrace_function_return;
+extern void unregister_ftrace_return(void);
 
+extern void ftrace_retfunc_init_task(struct task_struct *t);
+extern void ftrace_retfunc_exit_task(struct task_struct *t);
+#else
+static inline void ftrace_retfunc_init_task(struct task_struct *t) { }
+static inline void ftrace_retfunc_exit_task(struct task_struct *t) { }
+#endif
 
 #endif /* _LINUX_FTRACE_H */

include/linux/ftrace_irq.h

@@ -0,0 +1,13 @@
+#ifndef _LINUX_FTRACE_IRQ_H
+#define _LINUX_FTRACE_IRQ_H
+
+
+#if defined(CONFIG_DYNAMIC_FTRACE) || defined(CONFIG_FUNCTION_RET_TRACER)
+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 /* _LINUX_FTRACE_IRQ_H */

include/linux/futex.h

@@ -164,6 +164,8 @@ union futex_key {
 	} both;
 };
 
+#define FUTEX_KEY_INIT (union futex_key) { .both = { .ptr = NULL } }
+
 #ifdef CONFIG_FUTEX
 extern void exit_robust_list(struct task_struct *curr);
 extern void exit_pi_state_list(struct task_struct *curr);

include/linux/hardirq.h

@@ -4,6 +4,7 @@
 #include <linux/preempt.h>
 #include <linux/smp_lock.h>
 #include <linux/lockdep.h>
+#include <linux/ftrace_irq.h>
 #include <asm/hardirq.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/kernel.h

@@ -141,6 +141,15 @@ extern int _cond_resched(void);
 		(__x < 0) ? -__x : __x;		\
 	})
 
+#ifdef CONFIG_PROVE_LOCKING
+void might_fault(void);
+#else
+static inline void might_fault(void)
+{
+	might_sleep();
+}
+#endif
+
 extern struct atomic_notifier_head panic_notifier_list;
 extern long (*panic_blink)(long time);
 NORET_TYPE void panic(const char * fmt, ...)
@@ -188,6 +197,8 @@ extern unsigned long long memparse(const char *ptr, char **retptr);
 extern int core_kernel_text(unsigned long addr);
 extern int __kernel_text_address(unsigned long addr);
 extern int kernel_text_address(unsigned long addr);
+extern int func_ptr_is_kernel_text(void *ptr);
+
 struct pid;
 extern struct pid *session_of_pgrp(struct pid *pgrp);
 

include/linux/lockdep.h

@@ -73,6 +73,8 @@ struct lock_class_key {
 	struct lockdep_subclass_key	subkeys[MAX_LOCKDEP_SUBCLASSES];
 };
 
+#define LOCKSTAT_POINTS		4
+
 /*
  * The lock-class itself:
  */
@@ -119,7 +121,8 @@ struct lock_class {
 	int				name_version;
 
 #ifdef CONFIG_LOCK_STAT
-	unsigned long			contention_point[4];
+	unsigned long			contention_point[LOCKSTAT_POINTS];
+	unsigned long			contending_point[LOCKSTAT_POINTS];
 #endif
 };
 
@@ -144,6 +147,7 @@ enum bounce_type {
 
 struct lock_class_stats {
 	unsigned long			contention_point[4];
+	unsigned long			contending_point[4];
 	struct lock_time		read_waittime;
 	struct lock_time		write_waittime;
 	struct lock_time		read_holdtime;
@@ -165,6 +169,7 @@ struct lockdep_map {
 	const char			*name;
 #ifdef CONFIG_LOCK_STAT
 	int				cpu;
+	unsigned long			ip;
 #endif
 };
 
@@ -356,7 +361,7 @@ struct lock_class_key { };
 #ifdef CONFIG_LOCK_STAT
 
 extern void lock_contended(struct lockdep_map *lock, unsigned long ip);
-extern void lock_acquired(struct lockdep_map *lock);
+extern void lock_acquired(struct lockdep_map *lock, unsigned long ip);
 
 #define LOCK_CONTENDED(_lock, try, lock)			\
 do {								\
@@ -364,13 +369,13 @@ do {								\
 		lock_contended(&(_lock)->dep_map, _RET_IP_);	\
 		lock(_lock);					\
 	}							\
-	lock_acquired(&(_lock)->dep_map);			\
+	lock_acquired(&(_lock)->dep_map, _RET_IP_);			\
 } while (0)
 
 #else /* CONFIG_LOCK_STAT */
 
 #define lock_contended(lockdep_map, ip) do {} while (0)
-#define lock_acquired(lockdep_map) do {} while (0)
+#define lock_acquired(lockdep_map, ip) do {} while (0)
 
 #define LOCK_CONTENDED(_lock, try, lock) \
 	lock(_lock)
@@ -481,4 +486,22 @@ static inline void print_irqtrace_events(struct task_struct *curr)
 # define lock_map_release(l)			do { } while (0)
 #endif
 
+#ifdef CONFIG_PROVE_LOCKING
+# define might_lock(lock) 						\
+do {									\
+	typecheck(struct lockdep_map *, &(lock)->dep_map);		\
+	lock_acquire(&(lock)->dep_map, 0, 0, 0, 2, NULL, _THIS_IP_);	\
+	lock_release(&(lock)->dep_map, 0, _THIS_IP_);			\
+} while (0)
+# define might_lock_read(lock) 						\
+do {									\
+	typecheck(struct lockdep_map *, &(lock)->dep_map);		\
+	lock_acquire(&(lock)->dep_map, 0, 0, 1, 2, NULL, _THIS_IP_);	\
+	lock_release(&(lock)->dep_map, 0, _THIS_IP_);			\
+} while (0)
+#else
+# define might_lock(lock) do { } while (0)
+# define might_lock_read(lock) do { } while (0)
+#endif
+
 #endif /* __LINUX_LOCKDEP_H */

include/linux/marker.h

@@ -12,6 +12,7 @@
  * See the file COPYING for more details.
  */
 
+#include <stdarg.h>
 #include <linux/types.h>
 
 struct module;
@@ -48,10 +49,28 @@ struct marker {
 	void (*call)(const struct marker *mdata, void *call_private, ...);
 	struct marker_probe_closure single;
 	struct marker_probe_closure *multi;
+	const char *tp_name;	/* Optional tracepoint name */
+	void *tp_cb;		/* Optional tracepoint callback */
 } __attribute__((aligned(8)));
 
 #ifdef CONFIG_MARKERS
 
+#define _DEFINE_MARKER(name, tp_name_str, tp_cb, format)		\
+		static const char __mstrtab_##name[]			\
+		__attribute__((section("__markers_strings")))		\
+		= #name "\0" format;					\
+		static struct marker __mark_##name			\
+		__attribute__((section("__markers"), aligned(8))) =	\
+		{ __mstrtab_##name, &__mstrtab_##name[sizeof(#name)],	\
+		  0, 0, marker_probe_cb, { __mark_empty_function, NULL},\
+		  NULL, tp_name_str, tp_cb }
+
+#define DEFINE_MARKER(name, format)					\
+		_DEFINE_MARKER(name, NULL, NULL, format)
+
+#define DEFINE_MARKER_TP(name, tp_name, tp_cb, format)			\
+		_DEFINE_MARKER(name, #tp_name, tp_cb, format)
+
 /*
  * Note : the empty asm volatile with read constraint is used here instead of a
  * "used" attribute to fix a gcc 4.1.x bug.
@@ -65,14 +84,7 @@ struct marker {
  */
 #define __trace_mark(generic, name, call_private, format, args...)	\
 	do {								\
-		static const char __mstrtab_##name[]			\
-		__attribute__((section("__markers_strings")))		\
-		= #name "\0" format;					\
-		static struct marker __mark_##name			\
-		__attribute__((section("__markers"), aligned(8))) =	\
-		{ __mstrtab_##name, &__mstrtab_##name[sizeof(#name)],	\
-		0, 0, marker_probe_cb,					\
-		{ __mark_empty_function, NULL}, NULL };			\
+		DEFINE_MARKER(name, format);				\
 		__mark_check_format(format, ## args);			\
 		if (unlikely(__mark_##name.state)) {			\
 			(*__mark_##name.call)				\
@@ -80,14 +92,39 @@ struct marker {
 		}							\
 	} while (0)
 
+#define __trace_mark_tp(name, call_private, tp_name, tp_cb, format, args...) \
+	do {								\
+		void __check_tp_type(void)				\
+		{							\
+			register_trace_##tp_name(tp_cb);		\
+		}							\
+		DEFINE_MARKER_TP(name, tp_name, tp_cb, format);		\
+		__mark_check_format(format, ## args);			\
+		(*__mark_##name.call)(&__mark_##name, call_private,	\
+					## args);			\
+	} while (0)
+
 extern void marker_update_probe_range(struct marker *begin,
 	struct marker *end);
+
+#define GET_MARKER(name)	(__mark_##name)
+
 #else /* !CONFIG_MARKERS */
+#define DEFINE_MARKER(name, tp_name, tp_cb, format)
 #define __trace_mark(generic, name, call_private, format, args...) \
 		__mark_check_format(format, ## args)
+#define __trace_mark_tp(name, call_private, tp_name, tp_cb, format, args...) \
+	do {								\
+		void __check_tp_type(void)				\
+		{							\
+			register_trace_##tp_name(tp_cb);		\
+		}							\
+		__mark_check_format(format, ## args);			\
+	} while (0)
 static inline void marker_update_probe_range(struct marker *begin,
 	struct marker *end)
 { }
+#define GET_MARKER(name)
 #endif /* CONFIG_MARKERS */
 
 /**
@@ -116,6 +153,20 @@ static inline void marker_update_probe_range(struct marker *begin,
 #define _trace_mark(name, format, args...) \
 	__trace_mark(1, name, NULL, format, ## args)
 
+/**
+ * trace_mark_tp - Marker in a tracepoint callback
+ * @name: marker name, not quoted.
+ * @tp_name: tracepoint name, not quoted.
+ * @tp_cb: tracepoint callback. Should have an associated global symbol so it
+ *         is not optimized away by the compiler (should not be static).
+ * @format: format string
+ * @args...: variable argument list
+ *
+ * Places a marker in a tracepoint callback.
+ */
+#define trace_mark_tp(name, tp_name, tp_cb, format, args...)	\
+	__trace_mark_tp(name, NULL, tp_name, tp_cb, format, ## args)
+
 /**
  * MARK_NOARGS - Format string for a marker with no argument.
  */
@@ -136,8 +187,6 @@ 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/mutex.h

@@ -144,6 +144,8 @@ extern int __must_check mutex_lock_killable(struct mutex *lock);
 /*
  * NOTE: mutex_trylock() follows the spin_trylock() convention,
  *       not the down_trylock() convention!
+ *
+ * Returns 1 if the mutex has been acquired successfully, and 0 on contention.
  */
 extern int mutex_trylock(struct mutex *lock);
 extern void mutex_unlock(struct mutex *lock);

include/linux/rcuclassic.h

@@ -41,7 +41,7 @@
 #include <linux/seqlock.h>
 
 #ifdef CONFIG_RCU_CPU_STALL_DETECTOR
-#define RCU_SECONDS_TILL_STALL_CHECK	( 3 * HZ) /* for rcp->jiffies_stall */
+#define RCU_SECONDS_TILL_STALL_CHECK	(10 * HZ) /* for rcp->jiffies_stall */
 #define RCU_SECONDS_TILL_STALL_RECHECK	(30 * HZ) /* for rcp->jiffies_stall */
 #endif /* #ifdef CONFIG_RCU_CPU_STALL_DETECTOR */
 

include/linux/rcupdate.h

@@ -142,6 +142,7 @@ struct rcu_head {
  * on the write-side to insure proper synchronization.
  */
 #define rcu_read_lock_sched() preempt_disable()
+#define rcu_read_lock_sched_notrace() preempt_disable_notrace()
 
 /*
  * rcu_read_unlock_sched - marks the end of a RCU-classic critical section
@@ -149,6 +150,7 @@ struct rcu_head {
  * See rcu_read_lock_sched for more information.
  */
 #define rcu_read_unlock_sched() preempt_enable()
+#define rcu_read_unlock_sched_notrace() preempt_enable_notrace()
 
 
 

include/linux/ring_buffer.h

@@ -122,6 +122,7 @@ void ring_buffer_normalize_time_stamp(int cpu, u64 *ts);
 
 void tracing_on(void);
 void tracing_off(void);
+void tracing_off_permanent(void);
 
 enum ring_buffer_flags {
 	RB_FL_OVERWRITE		= 1 << 0,

include/linux/sched.h

@@ -1350,6 +1350,17 @@ struct task_struct {
 	unsigned long default_timer_slack_ns;
 
 	struct list_head	*scm_work_list;
+#ifdef CONFIG_FUNCTION_RET_TRACER
+	/* Index of current stored adress in ret_stack */
+	int curr_ret_stack;
+	/* Stack of return addresses for return function tracing */
+	struct ftrace_ret_stack	*ret_stack;
+	/*
+	 * Number of functions that haven't been traced
+	 * because of depth overrun.
+	 */
+	atomic_t trace_overrun;
+#endif
 };
 
 /*

include/linux/seq_file.h

@@ -34,6 +34,7 @@ struct seq_operations {
 
 #define SEQ_SKIP 1
 
+char *mangle_path(char *s, char *p, char *esc);
 int seq_open(struct file *, const struct seq_operations *);
 ssize_t seq_read(struct file *, char __user *, size_t, loff_t *);
 loff_t seq_lseek(struct file *, loff_t, int);

include/linux/stacktrace.h

@@ -15,9 +15,17 @@ extern void save_stack_trace_tsk(struct task_struct *tsk,
 				struct stack_trace *trace);
 
 extern void print_stack_trace(struct stack_trace *trace, int spaces);
+
+#ifdef CONFIG_USER_STACKTRACE_SUPPORT
+extern void save_stack_trace_user(struct stack_trace *trace);
+#else
+# define save_stack_trace_user(trace)              do { } while (0)
+#endif
+
 #else
 # define save_stack_trace(trace)			do { } while (0)
 # define save_stack_trace_tsk(tsk, trace)		do { } while (0)
+# define save_stack_trace_user(trace)			do { } while (0)
 # define print_stack_trace(trace, spaces)		do { } while (0)
 #endif
 

include/linux/tracepoint.h

@@ -24,8 +24,12 @@ struct tracepoint {
 	const char *name;		/* Tracepoint name */
 	int state;			/* State. */
 	void **funcs;
-} __attribute__((aligned(8)));
-
+} __attribute__((aligned(32)));		/*
+					 * Aligned on 32 bytes because it is
+					 * globally visible and gcc happily
+					 * align these on the structure size.
+					 * Keep in sync with vmlinux.lds.h.
+					 */
 
 #define TPPROTO(args...)	args
 #define TPARGS(args...)		args
@@ -40,14 +44,14 @@ struct tracepoint {
 	do {								\
 		void **it_func;						\
 									\
-		rcu_read_lock_sched();					\
+		rcu_read_lock_sched_notrace();				\
 		it_func = rcu_dereference((tp)->funcs);			\
 		if (it_func) {						\
 			do {						\
 				((void(*)(proto))(*it_func))(args);	\
 			} while (*(++it_func));				\
 		}							\
-		rcu_read_unlock_sched();				\
+		rcu_read_unlock_sched_notrace();			\
 	} while (0)
 
 /*
@@ -55,35 +59,40 @@ struct tracepoint {
  * not add unwanted padding between the beginning of the section and the
  * structure. Force alignment to the same alignment as the section start.
  */
-#define DEFINE_TRACE(name, proto, args)					\
+#define DECLARE_TRACE(name, proto, args)				\
+	extern struct tracepoint __tracepoint_##name;			\
 	static inline void trace_##name(proto)				\
 	{								\
-		static const char __tpstrtab_##name[]			\
-		__attribute__((section("__tracepoints_strings")))	\
-		= #name ":" #proto;					\
-		static struct tracepoint __tracepoint_##name		\
-		__attribute__((section("__tracepoints"), aligned(8))) =	\
-		{ __tpstrtab_##name, 0, NULL };				\
 		if (unlikely(__tracepoint_##name.state))		\
 			__DO_TRACE(&__tracepoint_##name,		\
 				TPPROTO(proto), TPARGS(args));		\
 	}								\
 	static inline int register_trace_##name(void (*probe)(proto))	\
 	{								\
-		return tracepoint_probe_register(#name ":" #proto,	\
-			(void *)probe);					\
+		return tracepoint_probe_register(#name, (void *)probe);	\
 	}								\
-	static inline void unregister_trace_##name(void (*probe)(proto))\
+	static inline int unregister_trace_##name(void (*probe)(proto))	\
 	{								\
-		tracepoint_probe_unregister(#name ":" #proto,		\
-			(void *)probe);					\
+		return tracepoint_probe_unregister(#name, (void *)probe);\
 	}
 
+#define DEFINE_TRACE(name)						\
+	static const char __tpstrtab_##name[]				\
+	__attribute__((section("__tracepoints_strings"))) = #name;	\
+	struct tracepoint __tracepoint_##name				\
+	__attribute__((section("__tracepoints"), aligned(32))) =	\
+		{ __tpstrtab_##name, 0, NULL }
+
+#define EXPORT_TRACEPOINT_SYMBOL_GPL(name)				\
+	EXPORT_SYMBOL_GPL(__tracepoint_##name)
+#define EXPORT_TRACEPOINT_SYMBOL(name)					\
+	EXPORT_SYMBOL(__tracepoint_##name)
+
 extern void tracepoint_update_probe_range(struct tracepoint *begin,
 	struct tracepoint *end);
 
 #else /* !CONFIG_TRACEPOINTS */
-#define DEFINE_TRACE(name, proto, args)			\
+#define DECLARE_TRACE(name, proto, args)				\
 	static inline void _do_trace_##name(struct tracepoint *tp, proto) \
 	{ }								\
 	static inline void trace_##name(proto)				\
@@ -92,8 +101,14 @@ extern void tracepoint_update_probe_range(struct tracepoint *begin,
 	{								\
 		return -ENOSYS;						\
 	}								\
-	static inline void unregister_trace_##name(void (*probe)(proto))\
-	{ }
+	static inline int unregister_trace_##name(void (*probe)(proto))	\
+	{								\
+		return -ENOSYS;						\
+	}
+
+#define DEFINE_TRACE(name)
+#define EXPORT_TRACEPOINT_SYMBOL_GPL(name)
+#define EXPORT_TRACEPOINT_SYMBOL(name)
 
 static inline void tracepoint_update_probe_range(struct tracepoint *begin,
 	struct tracepoint *end)
@@ -112,6 +127,10 @@ 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;

include/linux/uaccess.h

@@ -78,7 +78,7 @@ static inline unsigned long __copy_from_user_nocache(void *to,
 							\
 		set_fs(KERNEL_DS);			\
 		pagefault_disable();			\
-		ret = __get_user(retval, (__force typeof(retval) __user *)(addr));		\
+		ret = __copy_from_user_inatomic(&(retval), (__force typeof(retval) __user *)(addr), sizeof(retval));		\
 		pagefault_enable();			\
 		set_fs(old_fs);				\
 		ret;					\

include/trace/boot.h

@@ -0,0 +1,56 @@
+#ifndef _LINUX_TRACE_BOOT_H
+#define _LINUX_TRACE_BOOT_H
+
+/*
+ * Structure which defines the trace of an initcall
+ * while it is called.
+ * You don't have to fill the func field since it is
+ * only used internally by the tracer.
+ */
+struct boot_trace_call {
+	pid_t			caller;
+	char			func[KSYM_NAME_LEN];
+};
+
+/*
+ * Structure which defines the trace of an initcall
+ * while it returns.
+ */
+struct boot_trace_ret {
+	char			func[KSYM_NAME_LEN];
+	int				result;
+	unsigned long long	duration;		/* nsecs */
+};
+
+#ifdef CONFIG_BOOT_TRACER
+/* Append the traces on the ring-buffer */
+extern void trace_boot_call(struct boot_trace_call *bt, initcall_t fn);
+extern void trace_boot_ret(struct boot_trace_ret *bt, initcall_t fn);
+
+/* Tells the tracer that smp_pre_initcall is finished.
+ * So we can start the tracing
+ */
+extern void start_boot_trace(void);
+
+/* Resume the tracing of other necessary events
+ * such as sched switches
+ */
+extern void enable_boot_trace(void);
+
+/* Suspend this tracing. Actually, only sched_switches tracing have
+ * to be suspended. Initcalls doesn't need it.)
+ */
+extern void disable_boot_trace(void);
+#else
+static inline
+void trace_boot_call(struct boot_trace_call *bt, initcall_t fn) { }
+
+static inline
+void trace_boot_ret(struct boot_trace_ret *bt, initcall_t fn) { }
+
+static inline void start_boot_trace(void) { }
+static inline void enable_boot_trace(void) { }
+static inline void disable_boot_trace(void) { }
+#endif /* CONFIG_BOOT_TRACER */
+
+#endif /* __LINUX_TRACE_BOOT_H */

include/trace/sched.h

@@ -4,52 +4,52 @@
 #include <linux/sched.h>
 #include <linux/tracepoint.h>
 
-DEFINE_TRACE(sched_kthread_stop,
+DECLARE_TRACE(sched_kthread_stop,
 	TPPROTO(struct task_struct *t),
 		TPARGS(t));
 
-DEFINE_TRACE(sched_kthread_stop_ret,
+DECLARE_TRACE(sched_kthread_stop_ret,
 	TPPROTO(int ret),
 		TPARGS(ret));
 
-DEFINE_TRACE(sched_wait_task,
+DECLARE_TRACE(sched_wait_task,
 	TPPROTO(struct rq *rq, struct task_struct *p),
 		TPARGS(rq, p));
 
-DEFINE_TRACE(sched_wakeup,
+DECLARE_TRACE(sched_wakeup,
 	TPPROTO(struct rq *rq, struct task_struct *p),
 		TPARGS(rq, p));
 
-DEFINE_TRACE(sched_wakeup_new,
+DECLARE_TRACE(sched_wakeup_new,
 	TPPROTO(struct rq *rq, struct task_struct *p),
 		TPARGS(rq, p));
 
-DEFINE_TRACE(sched_switch,
+DECLARE_TRACE(sched_switch,
 	TPPROTO(struct rq *rq, struct task_struct *prev,
 		struct task_struct *next),
 		TPARGS(rq, prev, next));
 
-DEFINE_TRACE(sched_migrate_task,
+DECLARE_TRACE(sched_migrate_task,
 	TPPROTO(struct rq *rq, struct task_struct *p, int dest_cpu),
 		TPARGS(rq, p, dest_cpu));
 
-DEFINE_TRACE(sched_process_free,
+DECLARE_TRACE(sched_process_free,
 	TPPROTO(struct task_struct *p),
 		TPARGS(p));
 
-DEFINE_TRACE(sched_process_exit,
+DECLARE_TRACE(sched_process_exit,
 	TPPROTO(struct task_struct *p),
 		TPARGS(p));
 
-DEFINE_TRACE(sched_process_wait,
+DECLARE_TRACE(sched_process_wait,
 	TPPROTO(struct pid *pid),
 		TPARGS(pid));
 
-DEFINE_TRACE(sched_process_fork,
+DECLARE_TRACE(sched_process_fork,
 	TPPROTO(struct task_struct *parent, struct task_struct *child),
 		TPARGS(parent, child));
 
-DEFINE_TRACE(sched_signal_send,
+DECLARE_TRACE(sched_signal_send,
 	TPPROTO(int sig, struct task_struct *p),
 		TPARGS(sig, p));
 

init/Kconfig

@@ -808,6 +808,7 @@ config TRACEPOINTS
 
 config MARKERS
 	bool "Activate markers"
+	depends on TRACEPOINTS
 	help
 	  Place an empty function call at each marker site. Can be
 	  dynamically changed for a probe function.

init/main.c

@@ -63,6 +63,7 @@
 #include <linux/signal.h>
 #include <linux/idr.h>
 #include <linux/ftrace.h>
+#include <trace/boot.h>
 
 #include <asm/io.h>
 #include <asm/bugs.h>
@@ -703,31 +704,35 @@ core_param(initcall_debug, initcall_debug, bool, 0644);
 int do_one_initcall(initcall_t fn)
 {
 	int count = preempt_count();
-	ktime_t delta;
+	ktime_t calltime, delta, rettime;
 	char msgbuf[64];
-	struct boot_trace it;
+	struct boot_trace_call call;
+	struct boot_trace_ret ret;
 
 	if (initcall_debug) {
-		it.caller = task_pid_nr(current);
-		printk("calling  %pF @ %i\n", fn, it.caller);
-		it.calltime = ktime_get();
+		call.caller = task_pid_nr(current);
+		printk("calling  %pF @ %i\n", fn, call.caller);
+		calltime = ktime_get();
+		trace_boot_call(&call, fn);
+		enable_boot_trace();
 	}
 
-	it.result = fn();
+	ret.result = fn();
 
 	if (initcall_debug) {
-		it.rettime = ktime_get();
-		delta = ktime_sub(it.rettime, it.calltime);
-		it.duration = (unsigned long long) delta.tv64 >> 10;
+		disable_boot_trace();
+		rettime = ktime_get();
+		delta = ktime_sub(rettime, calltime);
+		ret.duration = (unsigned long long) ktime_to_ns(delta) >> 10;
+		trace_boot_ret(&ret, fn);
 		printk("initcall %pF returned %d after %Ld usecs\n", fn,
-			it.result, it.duration);
-		trace_boot(&it, fn);
+			ret.result, ret.duration);
 	}
 
 	msgbuf[0] = 0;
 
-	if (it.result && it.result != -ENODEV && initcall_debug)
-		sprintf(msgbuf, "error code %d ", it.result);
+	if (ret.result && ret.result != -ENODEV && initcall_debug)
+		sprintf(msgbuf, "error code %d ", ret.result);
 
 	if (preempt_count() != count) {
 		strlcat(msgbuf, "preemption imbalance ", sizeof(msgbuf));
@@ -741,7 +746,7 @@ int do_one_initcall(initcall_t fn)
 		printk("initcall %pF returned with %s\n", fn, msgbuf);
 	}
 
-	return it.result;
+	return ret.result;
 }
 
 
@@ -882,7 +887,7 @@ static int __init kernel_init(void * unused)
 	 * we're essentially up and running. Get rid of the
 	 * initmem segments and start the user-mode stuff..
 	 */
-	stop_boot_trace();
+
 	init_post();
 	return 0;
 }

kernel/Makefile

@@ -20,6 +20,10 @@ CFLAGS_REMOVE_rtmutex-debug.o = -pg
 CFLAGS_REMOVE_cgroup-debug.o = -pg
 CFLAGS_REMOVE_sched_clock.o = -pg
 endif
+ifdef CONFIG_FUNCTION_RET_TRACER
+CFLAGS_REMOVE_extable.o = -pg # For __kernel_text_address()
+CFLAGS_REMOVE_module.o = -pg # For __module_text_address()
+endif
 
 obj-$(CONFIG_FREEZER) += freezer.o
 obj-$(CONFIG_PROFILING) += profile.o

kernel/exit.c

@@ -53,6 +53,10 @@
 #include <asm/pgtable.h>
 #include <asm/mmu_context.h>
 
+DEFINE_TRACE(sched_process_free);
+DEFINE_TRACE(sched_process_exit);
+DEFINE_TRACE(sched_process_wait);
+
 static void exit_mm(struct task_struct * tsk);
 
 static inline int task_detached(struct task_struct *p)
@@ -1123,7 +1127,6 @@ NORET_TYPE void do_exit(long code)
 	preempt_disable();
 	/* causes final put_task_struct in finish_task_switch(). */
 	tsk->state = TASK_DEAD;
-
 	schedule();
 	BUG();
 	/* Avoid "noreturn function does return".  */
@@ -1321,10 +1324,10 @@ static int wait_task_zombie(struct task_struct *p, int options,
 		 * group, which consolidates times for all threads in the
 		 * group including the group leader.
 		 */
+		thread_group_cputime(p, &cputime);
 		spin_lock_irq(&p->parent->sighand->siglock);
 		psig = p->parent->signal;
 		sig = p->signal;
-		thread_group_cputime(p, &cputime);
 		psig->cutime =
 			cputime_add(psig->cutime,
 			cputime_add(cputime.utime,

kernel/extable.c

@@ -66,3 +66,19 @@ int kernel_text_address(unsigned long addr)
 		return 1;
 	return module_text_address(addr) != NULL;
 }
+
+/*
+ * On some architectures (PPC64, IA64) function pointers
+ * are actually only tokens to some data that then holds the
+ * real function address. As a result, to find if a function
+ * pointer is part of the kernel text, we need to do some
+ * special dereferencing first.
+ */
+int func_ptr_is_kernel_text(void *ptr)
+{
+	unsigned long addr;
+	addr = (unsigned long) dereference_function_descriptor(ptr);
+	if (core_kernel_text(addr))
+		return 1;
+	return module_text_address(addr) != NULL;
+}

kernel/fork.c

@@ -47,6 +47,7 @@
 #include <linux/mount.h>
 #include <linux/audit.h>
 #include <linux/memcontrol.h>
+#include <linux/ftrace.h>
 #include <linux/profile.h>
 #include <linux/rmap.h>
 #include <linux/acct.h>
@@ -80,6 +81,8 @@ DEFINE_PER_CPU(unsigned long, process_counts) = 0;
 
 __cacheline_aligned DEFINE_RWLOCK(tasklist_lock);  /* outer */
 
+DEFINE_TRACE(sched_process_fork);
+
 int nr_processes(void)
 {
 	int cpu;
@@ -137,6 +140,7 @@ void free_task(struct task_struct *tsk)
 	prop_local_destroy_single(&tsk->dirties);
 	free_thread_info(tsk->stack);
 	rt_mutex_debug_task_free(tsk);
+	ftrace_retfunc_exit_task(tsk);
 	free_task_struct(tsk);
 }
 EXPORT_SYMBOL(free_task);
@@ -1267,6 +1271,7 @@ static struct task_struct *copy_process(unsigned long clone_flags,
 	total_forks++;
 	spin_unlock(&current->sighand->siglock);
 	write_unlock_irq(&tasklist_lock);
+	ftrace_retfunc_init_task(p);
 	proc_fork_connector(p);
 	cgroup_post_fork(p);
 	return p;

kernel/futex.c

@@ -122,24 +122,6 @@ struct futex_hash_bucket {
 
 static struct futex_hash_bucket futex_queues[1<<FUTEX_HASHBITS];
 
-/*
- * Take mm->mmap_sem, when futex is shared
- */
-static inline void futex_lock_mm(struct rw_semaphore *fshared)
-{
-	if (fshared)
-		down_read(fshared);
-}
-
-/*
- * Release mm->mmap_sem, when the futex is shared
- */
-static inline void futex_unlock_mm(struct rw_semaphore *fshared)
-{
-	if (fshared)
-		up_read(fshared);
-}
-
 /*
  * We hash on the keys returned from get_futex_key (see below).
  */
@@ -161,6 +143,45 @@ static inline int match_futex(union futex_key *key1, union futex_key *key2)
 		&& key1->both.offset == key2->both.offset);
 }
 
+/*
+ * Take a reference to the resource addressed by a key.
+ * Can be called while holding spinlocks.
+ *
+ */
+static void get_futex_key_refs(union futex_key *key)
+{
+	if (!key->both.ptr)
+		return;
+
+	switch (key->both.offset & (FUT_OFF_INODE|FUT_OFF_MMSHARED)) {
+	case FUT_OFF_INODE:
+		atomic_inc(&key->shared.inode->i_count);
+		break;
+	case FUT_OFF_MMSHARED:
+		atomic_inc(&key->private.mm->mm_count);
+		break;
+	}
+}
+
+/*
+ * Drop a reference to the resource addressed by a key.
+ * The hash bucket spinlock must not be held.
+ */
+static void drop_futex_key_refs(union futex_key *key)
+{
+	if (!key->both.ptr)
+		return;
+
+	switch (key->both.offset & (FUT_OFF_INODE|FUT_OFF_MMSHARED)) {
+	case FUT_OFF_INODE:
+		iput(key->shared.inode);
+		break;
+	case FUT_OFF_MMSHARED:
+		mmdrop(key->private.mm);
+		break;
+	}
+}
+
 /**
  * get_futex_key - Get parameters which are the keys for a futex.
  * @uaddr: virtual address of the futex
@@ -179,12 +200,10 @@ static inline int match_futex(union futex_key *key1, union futex_key *key2)
  * For other futexes, it points to &current->mm->mmap_sem and
  * caller must have taken the reader lock. but NOT any spinlocks.
  */
-static int get_futex_key(u32 __user *uaddr, struct rw_semaphore *fshared,
-			 union futex_key *key)
+static int get_futex_key(u32 __user *uaddr, int fshared, union futex_key *key)
 {
 	unsigned long address = (unsigned long)uaddr;
 	struct mm_struct *mm = current->mm;
-	struct vm_area_struct *vma;
 	struct page *page;
 	int err;
 
@@ -208,100 +227,50 @@ static int get_futex_key(u32 __user *uaddr, struct rw_semaphore *fshared,
 			return -EFAULT;
 		key->private.mm = mm;
 		key->private.address = address;
+		get_futex_key_refs(key);
 		return 0;
 	}
-	/*
-	 * The futex is hashed differently depending on whether
-	 * it's in a shared or private mapping.  So check vma first.
-	 */
-	vma = find_extend_vma(mm, address);
-	if (unlikely(!vma))
-		return -EFAULT;
 
-	/*
-	 * Permissions.
-	 */
-	if (unlikely((vma->vm_flags & (VM_IO|VM_READ)) != VM_READ))
-		return (vma->vm_flags & VM_IO) ? -EPERM : -EACCES;
+again:
+	err = get_user_pages_fast(address, 1, 0, &page);
+	if (err < 0)
+		return err;
+
+	lock_page(page);
+	if (!page->mapping) {
+		unlock_page(page);
+		put_page(page);
+		goto again;
+	}
 
 	/*
 	 * Private mappings are handled in a simple way.
 	 *
 	 * NOTE: When userspace waits on a MAP_SHARED mapping, even if
 	 * it's a read-only handle, it's expected that futexes attach to
-	 * the object not the particular process.  Therefore we use
-	 * VM_MAYSHARE here, not VM_SHARED which is restricted to shared
-	 * mappings of _writable_ handles.
+	 * the object not the particular process.
 	 */
-	if (likely(!(vma->vm_flags & VM_MAYSHARE))) {
-		key->both.offset |= FUT_OFF_MMSHARED; /* reference taken on mm */
+	if (PageAnon(page)) {
+		key->both.offset |= FUT_OFF_MMSHARED; /* ref taken on mm */
 		key->private.mm = mm;
 		key->private.address = address;
-		return 0;
+	} else {
+		key->both.offset |= FUT_OFF_INODE; /* inode-based key */
+		key->shared.inode = page->mapping->host;
+		key->shared.pgoff = page->index;
 	}
 
-	/*
-	 * Linear file mappings are also simple.
-	 */
-	key->shared.inode = vma->vm_file->f_path.dentry->d_inode;
-	key->both.offset |= FUT_OFF_INODE; /* inode-based key. */
-	if (likely(!(vma->vm_flags & VM_NONLINEAR))) {
-		key->shared.pgoff = (((address - vma->vm_start) >> PAGE_SHIFT)
-				     + vma->vm_pgoff);
-		return 0;
-	}
+	get_futex_key_refs(key);
 
-	/*
-	 * We could walk the page table to read the non-linear
-	 * pte, and get the page index without fetching the page
-	 * from swap.  But that's a lot of code to duplicate here
-	 * for a rare case, so we simply fetch the page.
-	 */
-	err = get_user_pages(current, mm, address, 1, 0, 0, &page, NULL);
-	if (err >= 0) {
-		key->shared.pgoff =
-			page->index << (PAGE_CACHE_SHIFT - PAGE_SHIFT);
-		put_page(page);
-		return 0;
-	}
-	return err;
-}
-
-/*
- * Take a reference to the resource addressed by a key.
- * Can be called while holding spinlocks.
- *
- */
-static void get_futex_key_refs(union futex_key *key)
-{
-	if (key->both.ptr == NULL)
-		return;
-	switch (key->both.offset & (FUT_OFF_INODE|FUT_OFF_MMSHARED)) {
-		case FUT_OFF_INODE:
-			atomic_inc(&key->shared.inode->i_count);
-			break;
-		case FUT_OFF_MMSHARED:
-			atomic_inc(&key->private.mm->mm_count);
-			break;
-	}
+	unlock_page(page);
+	put_page(page);
+	return 0;
 }
 
-/*
- * Drop a reference to the resource addressed by a key.
- * The hash bucket spinlock must not be held.
- */
-static void drop_futex_key_refs(union futex_key *key)
+static inline
+void put_futex_key(int fshared, union futex_key *key)
 {
-	if (!key->both.ptr)
-		return;
-	switch (key->both.offset & (FUT_OFF_INODE|FUT_OFF_MMSHARED)) {
-		case FUT_OFF_INODE:
-			iput(key->shared.inode);
-			break;
-		case FUT_OFF_MMSHARED:
-			mmdrop(key->private.mm);
-			break;
-	}
+	drop_futex_key_refs(key);
 }
 
 static u32 cmpxchg_futex_value_locked(u32 __user *uaddr, u32 uval, u32 newval)
@@ -328,10 +297,8 @@ static int get_futex_value_locked(u32 *dest, u32 __user *from)
 
 /*
  * Fault handling.
- * if fshared is non NULL, current->mm->mmap_sem is already held
  */
-static int futex_handle_fault(unsigned long address,
-			      struct rw_semaphore *fshared, int attempt)
+static int futex_handle_fault(unsigned long address, int attempt)
 {
 	struct vm_area_struct * vma;
 	struct mm_struct *mm = current->mm;
@@ -340,8 +307,7 @@ static int futex_handle_fault(unsigned long address,
 	if (attempt > 2)
 		return ret;
 
-	if (!fshared)
-		down_read(&mm->mmap_sem);
+	down_read(&mm->mmap_sem);
 	vma = find_vma(mm, address);
 	if (vma && address >= vma->vm_start &&
 	    (vma->vm_flags & VM_WRITE)) {
@@ -361,8 +327,7 @@ static int futex_handle_fault(unsigned long address,
 				current->min_flt++;
 		}
 	}
-	if (!fshared)
-		up_read(&mm->mmap_sem);
+	up_read(&mm->mmap_sem);
 	return ret;
 }
 
@@ -385,6 +350,7 @@ static int refill_pi_state_cache(void)
 	/* pi_mutex gets initialized later */
 	pi_state->owner = NULL;
 	atomic_set(&pi_state->refcount, 1);
+	pi_state->key = FUTEX_KEY_INIT;
 
 	current->pi_state_cache = pi_state;
 
@@ -462,7 +428,7 @@ void exit_pi_state_list(struct task_struct *curr)
 	struct list_head *next, *head = &curr->pi_state_list;
 	struct futex_pi_state *pi_state;
 	struct futex_hash_bucket *hb;
-	union futex_key key;
+	union futex_key key = FUTEX_KEY_INIT;
 
 	if (!futex_cmpxchg_enabled)
 		return;
@@ -719,20 +685,17 @@ double_lock_hb(struct futex_hash_bucket *hb1, struct futex_hash_bucket *hb2)
  * Wake up all waiters hashed on the physical page that is mapped
  * to this virtual address:
  */
-static int futex_wake(u32 __user *uaddr, struct rw_semaphore *fshared,
-		      int nr_wake, u32 bitset)
+static int futex_wake(u32 __user *uaddr, int fshared, int nr_wake, u32 bitset)
 {
 	struct futex_hash_bucket *hb;
 	struct futex_q *this, *next;
 	struct plist_head *head;
-	union futex_key key;
+	union futex_key key = FUTEX_KEY_INIT;
 	int ret;
 
 	if (!bitset)
 		return -EINVAL;
 
-	futex_lock_mm(fshared);
-
 	ret = get_futex_key(uaddr, fshared, &key);
 	if (unlikely(ret != 0))
 		goto out;
@@ -760,7 +723,7 @@ static int futex_wake(u32 __user *uaddr, struct rw_semaphore *fshared,
 
 	spin_unlock(&hb->lock);
 out:
-	futex_unlock_mm(fshared);
+	put_futex_key(fshared, &key);
 	return ret;
 }
 
@@ -769,19 +732,16 @@ out:
  * to this virtual address:
  */
 static int
-futex_wake_op(u32 __user *uaddr1, struct rw_semaphore *fshared,
-	      u32 __user *uaddr2,
+futex_wake_op(u32 __user *uaddr1, int fshared, u32 __user *uaddr2,
 	      int nr_wake, int nr_wake2, int op)
 {
-	union futex_key key1, key2;
+	union futex_key key1 = FUTEX_KEY_INIT, key2 = FUTEX_KEY_INIT;
 	struct futex_hash_bucket *hb1, *hb2;
 	struct plist_head *head;
 	struct futex_q *this, *next;
 	int ret, op_ret, attempt = 0;
 
 retryfull:
-	futex_lock_mm(fshared);
-
 	ret = get_futex_key(uaddr1, fshared, &key1);
 	if (unlikely(ret != 0))
 		goto out;
@@ -826,18 +786,12 @@ retry:
 		 */
 		if (attempt++) {
 			ret = futex_handle_fault((unsigned long)uaddr2,
-						 fshared, attempt);
+						 attempt);
 			if (ret)
 				goto out;
 			goto retry;
 		}
 
-		/*
-		 * If we would have faulted, release mmap_sem,
-		 * fault it in and start all over again.
-		 */
-		futex_unlock_mm(fshared);
-
 		ret = get_user(dummy, uaddr2);
 		if (ret)
 			return ret;
@@ -873,7 +827,8 @@ retry:
 	if (hb1 != hb2)
 		spin_unlock(&hb2->lock);
 out:
-	futex_unlock_mm(fshared);
+	put_futex_key(fshared, &key2);
+	put_futex_key(fshared, &key1);
 
 	return ret;
 }
@@ -882,19 +837,16 @@ out:
  * Requeue all waiters hashed on one physical page to another
  * physical page.
  */
-static int futex_requeue(u32 __user *uaddr1, struct rw_semaphore *fshared,
-			 u32 __user *uaddr2,
+static int futex_requeue(u32 __user *uaddr1, int fshared, u32 __user *uaddr2,
 			 int nr_wake, int nr_requeue, u32 *cmpval)
 {
-	union futex_key key1, key2;
+	union futex_key key1 = FUTEX_KEY_INIT, key2 = FUTEX_KEY_INIT;
 	struct futex_hash_bucket *hb1, *hb2;
 	struct plist_head *head1;
 	struct futex_q *this, *next;
 	int ret, drop_count = 0;
 
  retry:
-	futex_lock_mm(fshared);
-
 	ret = get_futex_key(uaddr1, fshared, &key1);
 	if (unlikely(ret != 0))
 		goto out;
@@ -917,12 +869,6 @@ static int futex_requeue(u32 __user *uaddr1, struct rw_semaphore *fshared,
 			if (hb1 != hb2)
 				spin_unlock(&hb2->lock);
 
-			/*
-			 * If we would have faulted, release mmap_sem, fault
-			 * it in and start all over again.
-			 */
-			futex_unlock_mm(fshared);
-
 			ret = get_user(curval, uaddr1);
 
 			if (!ret)
@@ -974,7 +920,8 @@ out_unlock:
 		drop_futex_key_refs(&key1);
 
 out:
-	futex_unlock_mm(fshared);
+	put_futex_key(fshared, &key2);
+	put_futex_key(fshared, &key1);
 	return ret;
 }
 
@@ -1096,8 +1043,7 @@ static void unqueue_me_pi(struct futex_q *q)
  * private futexes.
  */
 static int fixup_pi_state_owner(u32 __user *uaddr, struct futex_q *q,
-				struct task_struct *newowner,
-				struct rw_semaphore *fshared)
+				struct task_struct *newowner, int fshared)
 {
 	u32 newtid = task_pid_vnr(newowner) | FUTEX_WAITERS;
 	struct futex_pi_state *pi_state = q->pi_state;
@@ -1176,7 +1122,7 @@ retry:
 handle_fault:
 	spin_unlock(q->lock_ptr);
 
-	ret = futex_handle_fault((unsigned long)uaddr, fshared, attempt++);
+	ret = futex_handle_fault((unsigned long)uaddr, attempt++);
 
 	spin_lock(q->lock_ptr);
 
@@ -1200,7 +1146,7 @@ handle_fault:
 
 static long futex_wait_restart(struct restart_block *restart);
 
-static int futex_wait(u32 __user *uaddr, struct rw_semaphore *fshared,
+static int futex_wait(u32 __user *uaddr, int fshared,
 		      u32 val, ktime_t *abs_time, u32 bitset)
 {
 	struct task_struct *curr = current;
@@ -1218,8 +1164,7 @@ static int futex_wait(u32 __user *uaddr, struct rw_semaphore *fshared,
 	q.pi_state = NULL;
 	q.bitset = bitset;
  retry:
-	futex_lock_mm(fshared);
-
+	q.key = FUTEX_KEY_INIT;
 	ret = get_futex_key(uaddr, fshared, &q.key);
 	if (unlikely(ret != 0))
 		goto out_release_sem;
@@ -1251,12 +1196,6 @@ static int futex_wait(u32 __user *uaddr, struct rw_semaphore *fshared,
 	if (unlikely(ret)) {
 		queue_unlock(&q, hb);
 
-		/*
-		 * If we would have faulted, release mmap_sem, fault it in and
-		 * start all over again.
-		 */
-		futex_unlock_mm(fshared);
-
 		ret = get_user(uval, uaddr);
 
 		if (!ret)
@@ -1270,12 +1209,6 @@ static int futex_wait(u32 __user *uaddr, struct rw_semaphore *fshared,
 	/* Only actually queue if *uaddr contained val.  */
 	queue_me(&q, hb);
 
-	/*
-	 * Now the futex is queued and we have checked the data, we
-	 * don't want to hold mmap_sem while we sleep.
-	 */
-	futex_unlock_mm(fshared);
-
 	/*
 	 * There might have been scheduling since the queue_me(), as we
 	 * cannot hold a spinlock across the get_user() in case it
@@ -1363,7 +1296,7 @@ static int futex_wait(u32 __user *uaddr, struct rw_semaphore *fshared,
 	queue_unlock(&q, hb);
 
  out_release_sem:
-	futex_unlock_mm(fshared);
+	put_futex_key(fshared, &q.key);
 	return ret;
 }
 
@@ -1371,13 +1304,13 @@ static int futex_wait(u32 __user *uaddr, struct rw_semaphore *fshared,
 static long futex_wait_restart(struct restart_block *restart)
 {
 	u32 __user *uaddr = (u32 __user *)restart->futex.uaddr;
-	struct rw_semaphore *fshared = NULL;
+	int fshared = 0;
 	ktime_t t;
 
 	t.tv64 = restart->futex.time;
 	restart->fn = do_no_restart_syscall;
 	if (restart->futex.flags & FLAGS_SHARED)
-		fshared = &current->mm->mmap_sem;
+		fshared = 1;
 	return (long)futex_wait(uaddr, fshared, restart->futex.val, &t,
 				restart->futex.bitset);
 }
@@ -1389,7 +1322,7 @@ static long futex_wait_restart(struct restart_block *restart)
  * if there are waiters then it will block, it does PI, etc. (Due to
  * races the kernel might see a 0 value of the futex too.)
  */
-static int futex_lock_pi(u32 __user *uaddr, struct rw_semaphore *fshared,
+static int futex_lock_pi(u32 __user *uaddr, int fshared,
 			 int detect, ktime_t *time, int trylock)
 {
 	struct hrtimer_sleeper timeout, *to = NULL;
@@ -1412,8 +1345,7 @@ static int futex_lock_pi(u32 __user *uaddr, struct rw_semaphore *fshared,
 
 	q.pi_state = NULL;
  retry:
-	futex_lock_mm(fshared);
-
+	q.key = FUTEX_KEY_INIT;
 	ret = get_futex_key(uaddr, fshared, &q.key);
 	if (unlikely(ret != 0))
 		goto out_release_sem;
@@ -1502,7 +1434,6 @@ static int futex_lock_pi(u32 __user *uaddr, struct rw_semaphore *fshared,
 			 * exit to complete.
 			 */
 			queue_unlock(&q, hb);
-			futex_unlock_mm(fshared);
 			cond_resched();
 			goto retry;
 
@@ -1534,12 +1465,6 @@ static int futex_lock_pi(u32 __user *uaddr, struct rw_semaphore *fshared,
 	 */
 	queue_me(&q, hb);
 
-	/*
-	 * Now the futex is queued and we have checked the data, we
-	 * don't want to hold mmap_sem while we sleep.
-	 */
-	futex_unlock_mm(fshared);
-
 	WARN_ON(!q.pi_state);
 	/*
 	 * Block on the PI mutex:
@@ -1552,7 +1477,6 @@ static int futex_lock_pi(u32 __user *uaddr, struct rw_semaphore *fshared,
 		ret = ret ? 0 : -EWOULDBLOCK;
 	}
 
-	futex_lock_mm(fshared);
 	spin_lock(q.lock_ptr);
 
 	if (!ret) {
@@ -1618,7 +1542,6 @@ static int futex_lock_pi(u32 __user *uaddr, struct rw_semaphore *fshared,
 
 	/* Unqueue and drop the lock */
 	unqueue_me_pi(&q);
-	futex_unlock_mm(fshared);
 
 	if (to)
 		destroy_hrtimer_on_stack(&to->timer);
@@ -1628,7 +1551,7 @@ static int futex_lock_pi(u32 __user *uaddr, struct rw_semaphore *fshared,
 	queue_unlock(&q, hb);
 
  out_release_sem:
-	futex_unlock_mm(fshared);
+	put_futex_key(fshared, &q.key);
 	if (to)
 		destroy_hrtimer_on_stack(&to->timer);
 	return ret;
@@ -1645,15 +1568,12 @@ static int futex_lock_pi(u32 __user *uaddr, struct rw_semaphore *fshared,
 	queue_unlock(&q, hb);
 
 	if (attempt++) {
-		ret = futex_handle_fault((unsigned long)uaddr, fshared,
-					 attempt);
+		ret = futex_handle_fault((unsigned long)uaddr, attempt);
 		if (ret)
 			goto out_release_sem;
 		goto retry_unlocked;
 	}
 
-	futex_unlock_mm(fshared);
-
 	ret = get_user(uval, uaddr);
 	if (!ret && (uval != -EFAULT))
 		goto retry;
@@ -1668,13 +1588,13 @@ static int futex_lock_pi(u32 __user *uaddr, struct rw_semaphore *fshared,
  * This is the in-kernel slowpath: we look up the PI state (if any),
  * and do the rt-mutex unlock.
  */
-static int futex_unlock_pi(u32 __user *uaddr, struct rw_semaphore *fshared)
+static int futex_unlock_pi(u32 __user *uaddr, int fshared)
 {
 	struct futex_hash_bucket *hb;
 	struct futex_q *this, *next;
 	u32 uval;
 	struct plist_head *head;
-	union futex_key key;
+	union futex_key key = FUTEX_KEY_INIT;
 	int ret, attempt = 0;
 
 retry:
@@ -1685,10 +1605,6 @@ retry:
 	 */
 	if ((uval & FUTEX_TID_MASK) != task_pid_vnr(current))
 		return -EPERM;
-	/*
-	 * First take all the futex related locks:
-	 */
-	futex_lock_mm(fshared);
 
 	ret = get_futex_key(uaddr, fshared, &key);
 	if (unlikely(ret != 0))
@@ -1747,7 +1663,7 @@ retry_unlocked:
 out_unlock:
 	spin_unlock(&hb->lock);
 out:
-	futex_unlock_mm(fshared);
+	put_futex_key(fshared, &key);
 
 	return ret;
 
@@ -1763,16 +1679,13 @@ pi_faulted:
 	spin_unlock(&hb->lock);
 
 	if (attempt++) {
-		ret = futex_handle_fault((unsigned long)uaddr, fshared,
-					 attempt);
+		ret = futex_handle_fault((unsigned long)uaddr, attempt);
 		if (ret)
 			goto out;
 		uval = 0;
 		goto retry_unlocked;
 	}
 
-	futex_unlock_mm(fshared);
-
 	ret = get_user(uval, uaddr);
 	if (!ret && (uval != -EFAULT))
 		goto retry;
@@ -1898,8 +1811,7 @@ retry:
 		 * PI futexes happens in exit_pi_state():
 		 */
 		if (!pi && (uval & FUTEX_WAITERS))
-			futex_wake(uaddr, &curr->mm->mmap_sem, 1,
-				   FUTEX_BITSET_MATCH_ANY);
+			futex_wake(uaddr, 1, 1, FUTEX_BITSET_MATCH_ANY);
 	}
 	return 0;
 }
@@ -1995,10 +1907,10 @@ long do_futex(u32 __user *uaddr, int op, u32 val, ktime_t *timeout,
 {
 	int ret = -ENOSYS;
 	int cmd = op & FUTEX_CMD_MASK;
-	struct rw_semaphore *fshared = NULL;
+	int fshared = 0;
 
 	if (!(op & FUTEX_PRIVATE_FLAG))
-		fshared = &current->mm->mmap_sem;
+		fshared = 1;
 
 	switch (cmd) {
 	case FUTEX_WAIT:

kernel/kthread.c

@@ -21,6 +21,9 @@ static DEFINE_SPINLOCK(kthread_create_lock);
 static LIST_HEAD(kthread_create_list);
 struct task_struct *kthreadd_task;
 
+DEFINE_TRACE(sched_kthread_stop);
+DEFINE_TRACE(sched_kthread_stop_ret);
+
 struct kthread_create_info
 {
 	/* Information passed to kthread() from kthreadd. */

kernel/lockdep.c

@@ -136,16 +136,16 @@ static inline struct lock_class *hlock_class(struct held_lock *hlock)
 #ifdef CONFIG_LOCK_STAT
 static DEFINE_PER_CPU(struct lock_class_stats[MAX_LOCKDEP_KEYS], lock_stats);
 
-static int lock_contention_point(struct lock_class *class, unsigned long ip)
+static int lock_point(unsigned long points[], unsigned long ip)
 {
 	int i;
 
-	for (i = 0; i < ARRAY_SIZE(class->contention_point); i++) {
-		if (class->contention_point[i] == 0) {
-			class->contention_point[i] = ip;
+	for (i = 0; i < LOCKSTAT_POINTS; i++) {
+		if (points[i] == 0) {
+			points[i] = ip;
 			break;
 		}
-		if (class->contention_point[i] == ip)
+		if (points[i] == ip)
 			break;
 	}
 
@@ -185,6 +185,9 @@ struct lock_class_stats lock_stats(struct lock_class *class)
 		for (i = 0; i < ARRAY_SIZE(stats.contention_point); i++)
 			stats.contention_point[i] += pcs->contention_point[i];
 
+		for (i = 0; i < ARRAY_SIZE(stats.contending_point); i++)
+			stats.contending_point[i] += pcs->contending_point[i];
+
 		lock_time_add(&pcs->read_waittime, &stats.read_waittime);
 		lock_time_add(&pcs->write_waittime, &stats.write_waittime);
 
@@ -209,6 +212,7 @@ void clear_lock_stats(struct lock_class *class)
 		memset(cpu_stats, 0, sizeof(struct lock_class_stats));
 	}
 	memset(class->contention_point, 0, sizeof(class->contention_point));
+	memset(class->contending_point, 0, sizeof(class->contending_point));
 }
 
 static struct lock_class_stats *get_lock_stats(struct lock_class *class)
@@ -2999,7 +3003,7 @@ __lock_contended(struct lockdep_map *lock, unsigned long ip)
 	struct held_lock *hlock, *prev_hlock;
 	struct lock_class_stats *stats;
 	unsigned int depth;
-	int i, point;
+	int i, contention_point, contending_point;
 
 	depth = curr->lockdep_depth;
 	if (DEBUG_LOCKS_WARN_ON(!depth))
@@ -3023,18 +3027,22 @@ __lock_contended(struct lockdep_map *lock, unsigned long ip)
 found_it:
 	hlock->waittime_stamp = sched_clock();
 
-	point = lock_contention_point(hlock_class(hlock), ip);
+	contention_point = lock_point(hlock_class(hlock)->contention_point, ip);
+	contending_point = lock_point(hlock_class(hlock)->contending_point,
+				      lock->ip);
 
 	stats = get_lock_stats(hlock_class(hlock));
-	if (point < ARRAY_SIZE(stats->contention_point))
-		stats->contention_point[point]++;
+	if (contention_point < LOCKSTAT_POINTS)
+		stats->contention_point[contention_point]++;
+	if (contending_point < LOCKSTAT_POINTS)
+		stats->contending_point[contending_point]++;
 	if (lock->cpu != smp_processor_id())
 		stats->bounces[bounce_contended + !!hlock->read]++;
 	put_lock_stats(stats);
 }
 
 static void
-__lock_acquired(struct lockdep_map *lock)
+__lock_acquired(struct lockdep_map *lock, unsigned long ip)
 {
 	struct task_struct *curr = current;
 	struct held_lock *hlock, *prev_hlock;
@@ -3083,6 +3091,7 @@ found_it:
 	put_lock_stats(stats);
 
 	lock->cpu = cpu;
+	lock->ip = ip;
 }
 
 void lock_contended(struct lockdep_map *lock, unsigned long ip)
@@ -3104,7 +3113,7 @@ void lock_contended(struct lockdep_map *lock, unsigned long ip)
 }
 EXPORT_SYMBOL_GPL(lock_contended);
 
-void lock_acquired(struct lockdep_map *lock)
+void lock_acquired(struct lockdep_map *lock, unsigned long ip)
 {
 	unsigned long flags;
 
@@ -3117,7 +3126,7 @@ void lock_acquired(struct lockdep_map *lock)
 	raw_local_irq_save(flags);
 	check_flags(flags);
 	current->lockdep_recursion = 1;
-	__lock_acquired(lock);
+	__lock_acquired(lock, ip);
 	current->lockdep_recursion = 0;
 	raw_local_irq_restore(flags);
 }
@@ -3276,10 +3285,10 @@ void __init lockdep_info(void)
 {
 	printk("Lock dependency validator: Copyright (c) 2006 Red Hat, Inc., Ingo Molnar\n");
 
-	printk("... MAX_LOCKDEP_SUBCLASSES:    %lu\n", MAX_LOCKDEP_SUBCLASSES);
+	printk("... MAX_LOCKDEP_SUBCLASSES:  %lu\n", MAX_LOCKDEP_SUBCLASSES);
 	printk("... MAX_LOCK_DEPTH:          %lu\n", MAX_LOCK_DEPTH);
 	printk("... MAX_LOCKDEP_KEYS:        %lu\n", MAX_LOCKDEP_KEYS);
-	printk("... CLASSHASH_SIZE:           %lu\n", CLASSHASH_SIZE);
+	printk("... CLASSHASH_SIZE:          %lu\n", CLASSHASH_SIZE);
 	printk("... MAX_LOCKDEP_ENTRIES:     %lu\n", MAX_LOCKDEP_ENTRIES);
 	printk("... MAX_LOCKDEP_CHAINS:      %lu\n", MAX_LOCKDEP_CHAINS);
 	printk("... CHAINHASH_SIZE:          %lu\n", CHAINHASH_SIZE);

kernel/lockdep_proc.c

@@ -470,11 +470,12 @@ static void seq_line(struct seq_file *m, char c, int offset, int length)
 
 static void snprint_time(char *buf, size_t bufsiz, s64 nr)
 {
-	unsigned long rem;
+	s64 div;
+	s32 rem;
 
 	nr += 5; /* for display rounding */
-	rem = do_div(nr, 1000); /* XXX: do_div_signed */
-	snprintf(buf, bufsiz, "%lld.%02d", (long long)nr, (int)rem/10);
+	div = div_s64_rem(nr, 1000, &rem);
+	snprintf(buf, bufsiz, "%lld.%02d", (long long)div, (int)rem/10);
 }
 
 static void seq_time(struct seq_file *m, s64 time)
@@ -556,7 +557,7 @@ static void seq_stats(struct seq_file *m, struct lock_stat_data *data)
 	if (stats->read_holdtime.nr)
 		namelen += 2;
 
-	for (i = 0; i < ARRAY_SIZE(class->contention_point); i++) {
+	for (i = 0; i < LOCKSTAT_POINTS; i++) {
 		char sym[KSYM_SYMBOL_LEN];
 		char ip[32];
 
@@ -573,6 +574,23 @@ static void seq_stats(struct seq_file *m, struct lock_stat_data *data)
 				stats->contention_point[i],
 				ip, sym);
 	}
+	for (i = 0; i < LOCKSTAT_POINTS; i++) {
+		char sym[KSYM_SYMBOL_LEN];
+		char ip[32];
+
+		if (class->contending_point[i] == 0)
+			break;
+
+		if (!i)
+			seq_line(m, '-', 40-namelen, namelen);
+
+		sprint_symbol(sym, class->contending_point[i]);
+		snprintf(ip, sizeof(ip), "[<%p>]",
+				(void *)class->contending_point[i]);
+		seq_printf(m, "%40s %14lu %29s %s\n", name,
+				stats->contending_point[i],
+				ip, sym);
+	}
 	if (i) {
 		seq_puts(m, "\n");
 		seq_line(m, '.', 0, 40 + 1 + 10 * (14 + 1));
@@ -582,7 +600,7 @@ static void seq_stats(struct seq_file *m, struct lock_stat_data *data)
 
 static void seq_header(struct seq_file *m)
 {
-	seq_printf(m, "lock_stat version 0.2\n");
+	seq_printf(m, "lock_stat version 0.3\n");
 	seq_line(m, '-', 0, 40 + 1 + 10 * (14 + 1));
 	seq_printf(m, "%40s %14s %14s %14s %14s %14s %14s %14s %14s "
 			"%14s %14s\n",

kernel/marker.c

@@ -43,6 +43,7 @@ static DEFINE_MUTEX(markers_mutex);
  */
 #define MARKER_HASH_BITS 6
 #define MARKER_TABLE_SIZE (1 << MARKER_HASH_BITS)
+static struct hlist_head marker_table[MARKER_TABLE_SIZE];
 
 /*
  * Note about RCU :
@@ -64,11 +65,10 @@ struct marker_entry {
 	void *oldptr;
 	int rcu_pending;
 	unsigned char ptype:1;
+	unsigned char format_allocated:1;
 	char name[0];	/* Contains name'\0'format'\0' */
 };
 
-static struct hlist_head marker_table[MARKER_TABLE_SIZE];
-
 /**
  * __mark_empty_function - Empty probe callback
  * @probe_private: probe private data
@@ -81,7 +81,7 @@ static struct hlist_head marker_table[MARKER_TABLE_SIZE];
  * though the function pointer change and the marker enabling are two distinct
  * operations that modifies the execution flow of preemptible code.
  */
-void __mark_empty_function(void *probe_private, void *call_private,
+notrace void __mark_empty_function(void *probe_private, void *call_private,
 	const char *fmt, va_list *args)
 {
 }
@@ -97,7 +97,8 @@ EXPORT_SYMBOL_GPL(__mark_empty_function);
  * need to put a full smp_rmb() in this branch. This is why we do not use
  * rcu_dereference() for the pointer read.
  */
-void marker_probe_cb(const struct marker *mdata, void *call_private, ...)
+notrace void marker_probe_cb(const struct marker *mdata,
+		void *call_private, ...)
 {
 	va_list args;
 	char ptype;
@@ -107,7 +108,7 @@ void marker_probe_cb(const struct marker *mdata, void *call_private, ...)
 	 * sure the teardown of the callbacks can be done correctly when they
 	 * are in modules and they insure RCU read coherency.
 	 */
-	rcu_read_lock_sched();
+	rcu_read_lock_sched_notrace();
 	ptype = mdata->ptype;
 	if (likely(!ptype)) {
 		marker_probe_func *func;
@@ -145,7 +146,7 @@ void marker_probe_cb(const struct marker *mdata, void *call_private, ...)
 			va_end(args);
 		}
 	}
-	rcu_read_unlock_sched();
+	rcu_read_unlock_sched_notrace();
 }
 EXPORT_SYMBOL_GPL(marker_probe_cb);
 
@@ -157,12 +158,13 @@ EXPORT_SYMBOL_GPL(marker_probe_cb);
  *
  * Should be connected to markers "MARK_NOARGS".
  */
-void marker_probe_cb_noarg(const struct marker *mdata, void *call_private, ...)
+static notrace void marker_probe_cb_noarg(const struct marker *mdata,
+		void *call_private, ...)
 {
 	va_list args;	/* not initialized */
 	char ptype;
 
-	rcu_read_lock_sched();
+	rcu_read_lock_sched_notrace();
 	ptype = mdata->ptype;
 	if (likely(!ptype)) {
 		marker_probe_func *func;
@@ -195,9 +197,8 @@ void marker_probe_cb_noarg(const struct marker *mdata, void *call_private, ...)
 			multi[i].func(multi[i].probe_private, call_private,
 				mdata->format, &args);
 	}
-	rcu_read_unlock_sched();
+	rcu_read_unlock_sched_notrace();
 }
-EXPORT_SYMBOL_GPL(marker_probe_cb_noarg);
 
 static void free_old_closure(struct rcu_head *head)
 {
@@ -416,6 +417,7 @@ static struct marker_entry *add_marker(const char *name, const char *format)
 	e->single.probe_private = NULL;
 	e->multi = NULL;
 	e->ptype = 0;
+	e->format_allocated = 0;
 	e->refcount = 0;
 	e->rcu_pending = 0;
 	hlist_add_head(&e->hlist, head);
@@ -447,6 +449,8 @@ static int remove_marker(const char *name)
 	if (e->single.func != __mark_empty_function)
 		return -EBUSY;
 	hlist_del(&e->hlist);
+	if (e->format_allocated)
+		kfree(e->format);
 	/* Make sure the call_rcu has been executed */
 	if (e->rcu_pending)
 		rcu_barrier_sched();
@@ -457,57 +461,34 @@ static int remove_marker(const char *name)
 /*
  * Set the mark_entry format to the format found in the element.
  */
-static int marker_set_format(struct marker_entry **entry, const char *format)
+static int marker_set_format(struct marker_entry *entry, const char *format)
 {
-	struct marker_entry *e;
-	size_t name_len = strlen((*entry)->name) + 1;
-	size_t format_len = strlen(format) + 1;
-
-
-	e = kmalloc(sizeof(struct marker_entry) + name_len + format_len,
-			GFP_KERNEL);
-	if (!e)
+	entry->format = kstrdup(format, GFP_KERNEL);
+	if (!entry->format)
 		return -ENOMEM;
-	memcpy(&e->name[0], (*entry)->name, name_len);
-	e->format = &e->name[name_len];
-	memcpy(e->format, format, format_len);
-	if (strcmp(e->format, MARK_NOARGS) == 0)
-		e->call = marker_probe_cb_noarg;
-	else
-		e->call = marker_probe_cb;
-	e->single = (*entry)->single;
-	e->multi = (*entry)->multi;
-	e->ptype = (*entry)->ptype;
-	e->refcount = (*entry)->refcount;
-	e->rcu_pending = 0;
-	hlist_add_before(&e->hlist, &(*entry)->hlist);
-	hlist_del(&(*entry)->hlist);
-	/* Make sure the call_rcu has been executed */
-	if ((*entry)->rcu_pending)
-		rcu_barrier_sched();
-	kfree(*entry);
-	*entry = e;
+	entry->format_allocated = 1;
+
 	trace_mark(core_marker_format, "name %s format %s",
-			e->name, e->format);
+			entry->name, entry->format);
 	return 0;
 }
 
 /*
  * Sets the probe callback corresponding to one marker.
  */
-static int set_marker(struct marker_entry **entry, struct marker *elem,
+static int set_marker(struct marker_entry *entry, struct marker *elem,
 		int active)
 {
-	int ret;
-	WARN_ON(strcmp((*entry)->name, elem->name) != 0);
+	int ret = 0;
+	WARN_ON(strcmp(entry->name, elem->name) != 0);
 
-	if ((*entry)->format) {
-		if (strcmp((*entry)->format, elem->format) != 0) {
+	if (entry->format) {
+		if (strcmp(entry->format, elem->format) != 0) {
 			printk(KERN_NOTICE
 				"Format mismatch for probe %s "
 				"(%s), marker (%s)\n",
-				(*entry)->name,
-				(*entry)->format,
+				entry->name,
+				entry->format,
 				elem->format);
 			return -EPERM;
 		}
@@ -523,37 +504,67 @@ static int set_marker(struct marker_entry **entry, struct marker *elem,
 	 * pass from a "safe" callback (with argument) to an "unsafe"
 	 * callback (does not set arguments).
 	 */
-	elem->call = (*entry)->call;
+	elem->call = entry->call;
 	/*
 	 * Sanity check :
 	 * We only update the single probe private data when the ptr is
 	 * set to a _non_ single probe! (0 -> 1 and N -> 1, N != 1)
 	 */
 	WARN_ON(elem->single.func != __mark_empty_function
-		&& elem->single.probe_private
-		!= (*entry)->single.probe_private &&
-		!elem->ptype);
-	elem->single.probe_private = (*entry)->single.probe_private;
+		&& elem->single.probe_private != entry->single.probe_private
+		&& !elem->ptype);
+	elem->single.probe_private = entry->single.probe_private;
 	/*
 	 * Make sure the private data is valid when we update the
 	 * single probe ptr.
 	 */
 	smp_wmb();
-	elem->single.func = (*entry)->single.func;
+	elem->single.func = entry->single.func;
 	/*
 	 * We also make sure that the new probe callbacks array is consistent
 	 * before setting a pointer to it.
 	 */
-	rcu_assign_pointer(elem->multi, (*entry)->multi);
+	rcu_assign_pointer(elem->multi, entry->multi);
 	/*
 	 * Update the function or multi probe array pointer before setting the
 	 * ptype.
 	 */
 	smp_wmb();
-	elem->ptype = (*entry)->ptype;
+	elem->ptype = entry->ptype;
+
+	if (elem->tp_name && (active ^ elem->state)) {
+		WARN_ON(!elem->tp_cb);
+		/*
+		 * It is ok to directly call the probe registration because type
+		 * checking has been done in the __trace_mark_tp() macro.
+		 */
+
+		if (active) {
+			/*
+			 * try_module_get should always succeed because we hold
+			 * lock_module() to get the tp_cb address.
+			 */
+			ret = try_module_get(__module_text_address(
+				(unsigned long)elem->tp_cb));
+			BUG_ON(!ret);
+			ret = tracepoint_probe_register_noupdate(
+				elem->tp_name,
+				elem->tp_cb);
+		} else {
+			ret = tracepoint_probe_unregister_noupdate(
+				elem->tp_name,
+				elem->tp_cb);
+			/*
+			 * tracepoint_probe_update_all() must be called
+			 * before the module containing tp_cb is unloaded.
+			 */
+			module_put(__module_text_address(
+				(unsigned long)elem->tp_cb));
+		}
+	}
 	elem->state = active;
 
-	return 0;
+	return ret;
 }
 
 /*
@@ -564,7 +575,24 @@ static int set_marker(struct marker_entry **entry, struct marker *elem,
  */
 static void disable_marker(struct marker *elem)
 {
+	int ret;
+
 	/* leave "call" as is. It is known statically. */
+	if (elem->tp_name && elem->state) {
+		WARN_ON(!elem->tp_cb);
+		/*
+		 * It is ok to directly call the probe registration because type
+		 * checking has been done in the __trace_mark_tp() macro.
+		 */
+		ret = tracepoint_probe_unregister_noupdate(elem->tp_name,
+			elem->tp_cb);
+		WARN_ON(ret);
+		/*
+		 * tracepoint_probe_update_all() must be called
+		 * before the module containing tp_cb is unloaded.
+		 */
+		module_put(__module_text_address((unsigned long)elem->tp_cb));
+	}
 	elem->state = 0;
 	elem->single.func = __mark_empty_function;
 	/* Update the function before setting the ptype */
@@ -594,8 +622,7 @@ void marker_update_probe_range(struct marker *begin,
 	for (iter = begin; iter < end; iter++) {
 		mark_entry = get_marker(iter->name);
 		if (mark_entry) {
-			set_marker(&mark_entry, iter,
-					!!mark_entry->refcount);
+			set_marker(mark_entry, iter, !!mark_entry->refcount);
 			/*
 			 * ignore error, continue
 			 */
@@ -629,6 +656,7 @@ static void marker_update_probes(void)
 	marker_update_probe_range(__start___markers, __stop___markers);
 	/* Markers in modules. */
 	module_update_markers();
+	tracepoint_probe_update_all();
 }
 
 /**
@@ -657,7 +685,7 @@ int marker_probe_register(const char *name, const char *format,
 			ret = PTR_ERR(entry);
 	} else if (format) {
 		if (!entry->format)
-			ret = marker_set_format(&entry, format);
+			ret = marker_set_format(entry, format);
 		else if (strcmp(entry->format, format))
 			ret = -EPERM;
 	}
@@ -676,10 +704,11 @@ int marker_probe_register(const char *name, const char *format,
 		goto end;
 	}
 	mutex_unlock(&markers_mutex);
-	marker_update_probes();		/* may update entry */
+	marker_update_probes();
 	mutex_lock(&markers_mutex);
 	entry = get_marker(name);
-	WARN_ON(!entry);
+	if (!entry)
+		goto end;
 	if (entry->rcu_pending)
 		rcu_barrier_sched();
 	entry->oldptr = old;
@@ -720,7 +749,7 @@ int marker_probe_unregister(const char *name,
 		rcu_barrier_sched();
 	old = marker_entry_remove_probe(entry, probe, probe_private);
 	mutex_unlock(&markers_mutex);
-	marker_update_probes();		/* may update entry */
+	marker_update_probes();
 	mutex_lock(&markers_mutex);
 	entry = get_marker(name);
 	if (!entry)
@@ -801,10 +830,11 @@ int marker_probe_unregister_private_data(marker_probe_func *probe,
 		rcu_barrier_sched();
 	old = marker_entry_remove_probe(entry, NULL, probe_private);
 	mutex_unlock(&markers_mutex);
-	marker_update_probes();		/* may update entry */
+	marker_update_probes();
 	mutex_lock(&markers_mutex);
 	entry = get_marker_from_private_data(probe, probe_private);
-	WARN_ON(!entry);
+	if (!entry)
+		goto end;
 	if (entry->rcu_pending)
 		rcu_barrier_sched();
 	entry->oldptr = old;
@@ -848,8 +878,6 @@ void *marker_get_private_data(const char *name, marker_probe_func *probe,
 			if (!e->ptype) {
 				if (num == 0 && e->single.func == probe)
 					return e->single.probe_private;
-				else
-					break;
 			} else {
 				struct marker_probe_closure *closure;
 				int match = 0;
@@ -861,8 +889,42 @@ void *marker_get_private_data(const char *name, marker_probe_func *probe,
 						return closure[i].probe_private;
 				}
 			}
+			break;
 		}
 	}
 	return ERR_PTR(-ENOENT);
 }
 EXPORT_SYMBOL_GPL(marker_get_private_data);
+
+#ifdef CONFIG_MODULES
+
+int marker_module_notify(struct notifier_block *self,
+			 unsigned long val, void *data)
+{
+	struct module *mod = data;
+
+	switch (val) {
+	case MODULE_STATE_COMING:
+		marker_update_probe_range(mod->markers,
+			mod->markers + mod->num_markers);
+		break;
+	case MODULE_STATE_GOING:
+		marker_update_probe_range(mod->markers,
+			mod->markers + mod->num_markers);
+		break;
+	}
+	return 0;
+}
+
+struct notifier_block marker_module_nb = {
+	.notifier_call = marker_module_notify,
+	.priority = 0,
+};
+
+static int init_markers(void)
+{
+	return register_module_notifier(&marker_module_nb);
+}
+__initcall(init_markers);
+
+#endif /* CONFIG_MODULES */

kernel/module.c

@@ -2184,24 +2184,15 @@ static noinline struct module *load_module(void __user *umod,
 		struct mod_debug *debug;
 		unsigned int num_debug;
 
-#ifdef CONFIG_MARKERS
-		marker_update_probe_range(mod->markers,
-			mod->markers + mod->num_markers);
-#endif
 		debug = section_objs(hdr, sechdrs, secstrings, "__verbose",
 				     sizeof(*debug), &num_debug);
 		dynamic_printk_setup(debug, num_debug);
-
-#ifdef CONFIG_TRACEPOINTS
-		tracepoint_update_probe_range(mod->tracepoints,
-			mod->tracepoints + mod->num_tracepoints);
-#endif
 	}
 
 	/* sechdrs[0].sh_size is always zero */
 	mseg = section_objs(hdr, sechdrs, secstrings, "__mcount_loc",
 			    sizeof(*mseg), &num_mcount);
-	ftrace_init_module(mseg, mseg + num_mcount);
+	ftrace_init_module(mod, mseg, mseg + num_mcount);
 
 	err = module_finalize(hdr, sechdrs, mod);
 	if (err < 0)

kernel/mutex.c

@@ -59,7 +59,7 @@ EXPORT_SYMBOL(__mutex_init);
  * We also put the fastpath first in the kernel image, to make sure the
  * branch is predicted by the CPU as default-untaken.
  */
-static void noinline __sched
+static __used noinline void __sched
 __mutex_lock_slowpath(atomic_t *lock_count);
 
 /***
@@ -96,7 +96,7 @@ void inline __sched mutex_lock(struct mutex *lock)
 EXPORT_SYMBOL(mutex_lock);
 #endif
 
-static noinline void __sched __mutex_unlock_slowpath(atomic_t *lock_count);
+static __used noinline void __sched __mutex_unlock_slowpath(atomic_t *lock_count);
 
 /***
  * mutex_unlock - release the mutex
@@ -184,7 +184,7 @@ __mutex_lock_common(struct mutex *lock, long state, unsigned int subclass,
 	}
 
 done:
-	lock_acquired(&lock->dep_map);
+	lock_acquired(&lock->dep_map, ip);
 	/* got the lock - rejoice! */
 	mutex_remove_waiter(lock, &waiter, task_thread_info(task));
 	debug_mutex_set_owner(lock, task_thread_info(task));
@@ -268,7 +268,7 @@ __mutex_unlock_common_slowpath(atomic_t *lock_count, int nested)
 /*
  * Release the lock, slowpath:
  */
-static noinline void
+static __used noinline void
 __mutex_unlock_slowpath(atomic_t *lock_count)
 {
 	__mutex_unlock_common_slowpath(lock_count, 1);
@@ -313,7 +313,7 @@ int __sched mutex_lock_killable(struct mutex *lock)
 }
 EXPORT_SYMBOL(mutex_lock_killable);
 
-static noinline void __sched
+static __used noinline void __sched
 __mutex_lock_slowpath(atomic_t *lock_count)
 {
 	struct mutex *lock = container_of(lock_count, struct mutex, count);

kernel/notifier.c

@@ -82,6 +82,14 @@ static int __kprobes notifier_call_chain(struct notifier_block **nl,
 
 	while (nb && nr_to_call) {
 		next_nb = rcu_dereference(nb->next);
+
+#ifdef CONFIG_DEBUG_NOTIFIERS
+		if (unlikely(!func_ptr_is_kernel_text(nb->notifier_call))) {
+			WARN(1, "Invalid notifier called!");
+			nb = next_nb;
+			continue;
+		}
+#endif
 		ret = nb->notifier_call(nb, val, v);
 
 		if (nr_calls)

kernel/posix-cpu-timers.c

@@ -58,21 +58,21 @@ void thread_group_cputime(
 	struct task_struct *tsk,
 	struct task_cputime *times)
 {
-	struct signal_struct *sig;
+	struct task_cputime *totals, *tot;
 	int i;
-	struct task_cputime *tot;
 
-	sig = tsk->signal;
-	if (unlikely(!sig) || !sig->cputime.totals) {
+	totals = tsk->signal->cputime.totals;
+	if (!totals) {
 		times->utime = tsk->utime;
 		times->stime = tsk->stime;
 		times->sum_exec_runtime = tsk->se.sum_exec_runtime;
 		return;
 	}
+
 	times->stime = times->utime = cputime_zero;
 	times->sum_exec_runtime = 0;
 	for_each_possible_cpu(i) {
-		tot = per_cpu_ptr(tsk->signal->cputime.totals, i);
+		tot = per_cpu_ptr(totals, i);
 		times->utime = cputime_add(times->utime, tot->utime);
 		times->stime = cputime_add(times->stime, tot->stime);
 		times->sum_exec_runtime += tot->sum_exec_runtime;

kernel/power/disk.c

@@ -22,7 +22,6 @@
 #include <linux/console.h>
 #include <linux/cpu.h>
 #include <linux/freezer.h>
-#include <linux/ftrace.h>
 
 #include "power.h"
 
@@ -257,7 +256,7 @@ static int create_image(int platform_mode)
 
 int hibernation_snapshot(int platform_mode)
 {
-	int error, ftrace_save;
+	int error;
 
 	/* Free memory before shutting down devices. */
 	error = swsusp_shrink_memory();
@@ -269,7 +268,6 @@ int hibernation_snapshot(int platform_mode)
 		goto Close;
 
 	suspend_console();
-	ftrace_save = __ftrace_enabled_save();
 	error = device_suspend(PMSG_FREEZE);
 	if (error)
 		goto Recover_platform;
@@ -299,7 +297,6 @@ int hibernation_snapshot(int platform_mode)
  Resume_devices:
 	device_resume(in_suspend ?
 		(error ? PMSG_RECOVER : PMSG_THAW) : PMSG_RESTORE);
-	__ftrace_enabled_restore(ftrace_save);
 	resume_console();
  Close:
 	platform_end(platform_mode);
@@ -370,11 +367,10 @@ static int resume_target_kernel(void)
 
 int hibernation_restore(int platform_mode)
 {
-	int error, ftrace_save;
+	int error;
 
 	pm_prepare_console();
 	suspend_console();
-	ftrace_save = __ftrace_enabled_save();
 	error = device_suspend(PMSG_QUIESCE);
 	if (error)
 		goto Finish;
@@ -389,7 +385,6 @@ int hibernation_restore(int platform_mode)
 	platform_restore_cleanup(platform_mode);
 	device_resume(PMSG_RECOVER);
  Finish:
-	__ftrace_enabled_restore(ftrace_save);
 	resume_console();
 	pm_restore_console();
 	return error;
@@ -402,7 +397,7 @@ int hibernation_restore(int platform_mode)
 
 int hibernation_platform_enter(void)
 {
-	int error, ftrace_save;
+	int error;
 
 	if (!hibernation_ops)
 		return -ENOSYS;
@@ -417,7 +412,6 @@ int hibernation_platform_enter(void)
 		goto Close;
 
 	suspend_console();
-	ftrace_save = __ftrace_enabled_save();
 	error = device_suspend(PMSG_HIBERNATE);
 	if (error) {
 		if (hibernation_ops->recover)
@@ -452,7 +446,6 @@ int hibernation_platform_enter(void)
 	hibernation_ops->finish();
  Resume_devices:
 	device_resume(PMSG_RESTORE);
-	__ftrace_enabled_restore(ftrace_save);
 	resume_console();
  Close:
 	hibernation_ops->end();

kernel/power/main.c

@@ -22,7 +22,6 @@
 #include <linux/freezer.h>
 #include <linux/vmstat.h>
 #include <linux/syscalls.h>
-#include <linux/ftrace.h>
 
 #include "power.h"
 
@@ -317,7 +316,7 @@ static int suspend_enter(suspend_state_t state)
  */
 int suspend_devices_and_enter(suspend_state_t state)
 {
-	int error, ftrace_save;
+	int error;
 
 	if (!suspend_ops)
 		return -ENOSYS;
@@ -328,7 +327,6 @@ int suspend_devices_and_enter(suspend_state_t state)
 			goto Close;
 	}
 	suspend_console();
-	ftrace_save = __ftrace_enabled_save();
 	suspend_test_start();
 	error = device_suspend(PMSG_SUSPEND);
 	if (error) {
@@ -360,7 +358,6 @@ int suspend_devices_and_enter(suspend_state_t state)
 	suspend_test_start();
 	device_resume(PMSG_RESUME);
 	suspend_test_finish("resume devices");
-	__ftrace_enabled_restore(ftrace_save);
 	resume_console();
  Close:
 	if (suspend_ops->end)

kernel/profile.c

@@ -544,7 +544,7 @@ static const struct file_operations proc_profile_operations = {
 };
 
 #ifdef CONFIG_SMP
-static inline void profile_nop(void *unused)
+static void profile_nop(void *unused)
 {
 }
 

kernel/rcuclassic.c

@@ -191,7 +191,7 @@ static void print_other_cpu_stall(struct rcu_ctrlblk *rcp)
 
 	/* OK, time to rat on our buddy... */
 
-	printk(KERN_ERR "RCU detected CPU stalls:");
+	printk(KERN_ERR "INFO: RCU detected CPU stalls:");
 	for_each_possible_cpu(cpu) {
 		if (cpu_isset(cpu, rcp->cpumask))
 			printk(" %d", cpu);
@@ -204,7 +204,7 @@ static void print_cpu_stall(struct rcu_ctrlblk *rcp)
 {
 	unsigned long flags;
 
-	printk(KERN_ERR "RCU detected CPU %d stall (t=%lu/%lu jiffies)\n",
+	printk(KERN_ERR "INFO: RCU detected CPU %d stall (t=%lu/%lu jiffies)\n",
 			smp_processor_id(), jiffies,
 			jiffies - rcp->gp_start);
 	dump_stack();

kernel/sched.c

@@ -118,6 +118,12 @@
  */
 #define RUNTIME_INF	((u64)~0ULL)
 
+DEFINE_TRACE(sched_wait_task);
+DEFINE_TRACE(sched_wakeup);
+DEFINE_TRACE(sched_wakeup_new);
+DEFINE_TRACE(sched_switch);
+DEFINE_TRACE(sched_migrate_task);
+
 #ifdef CONFIG_SMP
 /*
  * Divide a load by a sched group cpu_power : (load / sg->__cpu_power)
@@ -4171,7 +4177,6 @@ void account_steal_time(struct task_struct *p, cputime_t steal)
 
 	if (p == rq->idle) {
 		p->stime = cputime_add(p->stime, steal);
-		account_group_system_time(p, steal);
 		if (atomic_read(&rq->nr_iowait) > 0)
 			cpustat->iowait = cputime64_add(cpustat->iowait, tmp);
 		else
@@ -4307,7 +4312,7 @@ void __kprobes sub_preempt_count(int val)
 	/*
 	 * Underflow?
 	 */
-	if (DEBUG_LOCKS_WARN_ON(val > preempt_count()))
+       if (DEBUG_LOCKS_WARN_ON(val > preempt_count() - (!!kernel_locked())))
 		return;
 	/*
 	 * Is the spinlock portion underflowing?
@@ -5864,6 +5869,7 @@ void __cpuinit init_idle(struct task_struct *idle, int cpu)
 	 * The idle tasks have their own, simple scheduling class:
 	 */
 	idle->sched_class = &idle_sched_class;
+	ftrace_retfunc_init_task(idle);
 }
 
 /*

kernel/signal.c

@@ -41,6 +41,8 @@
 
 static struct kmem_cache *sigqueue_cachep;
 
+DEFINE_TRACE(sched_signal_send);
+
 static void __user *sig_handler(struct task_struct *t, int sig)
 {
 	return t->sighand->action[sig - 1].sa.sa_handler;

kernel/softlockup.c

@@ -164,7 +164,7 @@ unsigned long __read_mostly sysctl_hung_task_check_count = 1024;
 /*
  * Zero means infinite timeout - no checking done:
  */
-unsigned long __read_mostly sysctl_hung_task_timeout_secs = 120;
+unsigned long __read_mostly sysctl_hung_task_timeout_secs = 480;
 
 unsigned long __read_mostly sysctl_hung_task_warnings = 10;
 

kernel/sys.c

@@ -858,8 +858,8 @@ void do_sys_times(struct tms *tms)
 	struct task_cputime cputime;
 	cputime_t cutime, cstime;
 
-	spin_lock_irq(&current->sighand->siglock);
 	thread_group_cputime(current, &cputime);
+	spin_lock_irq(&current->sighand->siglock);
 	cutime = current->signal->cutime;
 	cstime = current->signal->cstime;
 	spin_unlock_irq(&current->sighand->siglock);

kernel/sysctl.c

@@ -484,6 +484,16 @@ static struct ctl_table kern_table[] = {
 		.proc_handler	= &ftrace_enable_sysctl,
 	},
 #endif
+#ifdef CONFIG_TRACING
+	{
+		.ctl_name	= CTL_UNNUMBERED,
+		.procname	= "ftrace_dump_on_oops",
+		.data		= &ftrace_dump_on_oops,
+		.maxlen		= sizeof(int),
+		.mode		= 0644,
+		.proc_handler	= &proc_dointvec,
+	},
+#endif
 #ifdef CONFIG_MODULES
 	{
 		.ctl_name	= KERN_MODPROBE,

kernel/trace/Kconfig

@@ -3,12 +3,25 @@
 #  select HAVE_FUNCTION_TRACER:
 #
 
+config USER_STACKTRACE_SUPPORT
+	bool
+
 config NOP_TRACER
 	bool
 
 config HAVE_FUNCTION_TRACER
 	bool
 
+config HAVE_FUNCTION_RET_TRACER
+	bool
+
+config HAVE_FUNCTION_TRACE_MCOUNT_TEST
+	bool
+	help
+	 This gets selected when the arch tests the function_trace_stop
+	 variable at the mcount call site. Otherwise, this variable
+	 is tested by the called function.
+
 config HAVE_DYNAMIC_FTRACE
 	bool
 
@@ -47,6 +60,16 @@ config FUNCTION_TRACER
 	  (the bootup default), then the overhead of the instructions is very
 	  small and not measurable even in micro-benchmarks.
 
+config FUNCTION_RET_TRACER
+	bool "Kernel Function return Tracer"
+	depends on HAVE_FUNCTION_RET_TRACER
+	depends on FUNCTION_TRACER
+	help
+	  Enable the kernel to trace a function at its return.
+	  It's first purpose is to trace the duration of functions.
+	  This is done by setting the current return address on the thread
+	  info structure of the current task.
+
 config IRQSOFF_TRACER
 	bool "Interrupts-off Latency Tracer"
 	default n
@@ -138,6 +161,59 @@ config BOOT_TRACER
 	    selected, because the self-tests are an initcall as well and that
 	    would invalidate the boot trace. )
 
+config TRACE_BRANCH_PROFILING
+	bool "Trace likely/unlikely profiler"
+	depends on DEBUG_KERNEL
+	select TRACING
+	help
+	  This tracer profiles all the the likely and unlikely macros
+	  in the kernel. It will display the results in:
+
+	  /debugfs/tracing/profile_annotated_branch
+
+	  Note: this will add a significant overhead, only turn this
+	  on if you need to profile the system's use of these macros.
+
+	  Say N if unsure.
+
+config PROFILE_ALL_BRANCHES
+	bool "Profile all if conditionals"
+	depends on TRACE_BRANCH_PROFILING
+	help
+	  This tracer profiles all branch conditions. Every if ()
+	  taken in the kernel is recorded whether it hit or miss.
+	  The results will be displayed in:
+
+	  /debugfs/tracing/profile_branch
+
+	  This configuration, when enabled, will impose a great overhead
+	  on the system. This should only be enabled when the system
+	  is to be analyzed
+
+	  Say N if unsure.
+
+config TRACING_BRANCHES
+	bool
+	help
+	  Selected by tracers that will trace the likely and unlikely
+	  conditions. This prevents the tracers themselves from being
+	  profiled. Profiling the tracing infrastructure can only happen
+	  when the likelys and unlikelys are not being traced.
+
+config BRANCH_TRACER
+	bool "Trace likely/unlikely instances"
+	depends on TRACE_BRANCH_PROFILING
+	select TRACING_BRANCHES
+	help
+	  This traces the events of likely and unlikely condition
+	  calls in the kernel.  The difference between this and the
+	  "Trace likely/unlikely profiler" is that this is not a
+	  histogram of the callers, but actually places the calling
+	  events into a running trace buffer to see when and where the
+	  events happened, as well as their results.
+
+	  Say N if unsure.
+
 config STACK_TRACER
 	bool "Trace max stack"
 	depends on HAVE_FUNCTION_TRACER

kernel/trace/Makefile

@@ -10,6 +10,11 @@ CFLAGS_trace_selftest_dynamic.o = -pg
 obj-y += trace_selftest_dynamic.o
 endif
 
+# If unlikely tracing is enabled, do not trace these files
+ifdef CONFIG_TRACING_BRANCHES
+KBUILD_CFLAGS += -DDISABLE_BRANCH_PROFILING
+endif
+
 obj-$(CONFIG_FUNCTION_TRACER) += libftrace.o
 obj-$(CONFIG_RING_BUFFER) += ring_buffer.o
 
@@ -24,5 +29,7 @@ obj-$(CONFIG_NOP_TRACER) += trace_nop.o
 obj-$(CONFIG_STACK_TRACER) += trace_stack.o
 obj-$(CONFIG_MMIOTRACE) += trace_mmiotrace.o
 obj-$(CONFIG_BOOT_TRACER) += trace_boot.o
+obj-$(CONFIG_FUNCTION_RET_TRACER) += trace_functions_return.o
+obj-$(CONFIG_TRACE_BRANCH_PROFILING) += trace_branch.o
 
 libftrace-y := ftrace.o

kernel/trace/ftrace.c

@@ -47,6 +47,12 @@
 int ftrace_enabled __read_mostly;
 static int last_ftrace_enabled;
 
+/* Quick disabling of function tracer. */
+int function_trace_stop;
+
+/* By default, current tracing type is normal tracing. */
+enum ftrace_tracing_type_t ftrace_tracing_type = FTRACE_TYPE_ENTER;
+
 /*
  * ftrace_disabled is set when an anomaly is discovered.
  * ftrace_disabled is much stronger than ftrace_enabled.
@@ -63,6 +69,7 @@ static struct ftrace_ops ftrace_list_end __read_mostly =
 
 static struct ftrace_ops *ftrace_list __read_mostly = &ftrace_list_end;
 ftrace_func_t ftrace_trace_function __read_mostly = ftrace_stub;
+ftrace_func_t __ftrace_trace_function __read_mostly = ftrace_stub;
 
 static void ftrace_list_func(unsigned long ip, unsigned long parent_ip)
 {
@@ -88,8 +95,23 @@ static void ftrace_list_func(unsigned long ip, unsigned long parent_ip)
 void clear_ftrace_function(void)
 {
 	ftrace_trace_function = ftrace_stub;
+	__ftrace_trace_function = ftrace_stub;
 }
 
+#ifndef CONFIG_HAVE_FUNCTION_TRACE_MCOUNT_TEST
+/*
+ * For those archs that do not test ftrace_trace_stop in their
+ * mcount call site, we need to do it from C.
+ */
+static void ftrace_test_stop_func(unsigned long ip, unsigned long parent_ip)
+{
+	if (function_trace_stop)
+		return;
+
+	__ftrace_trace_function(ip, parent_ip);
+}
+#endif
+
 static int __register_ftrace_function(struct ftrace_ops *ops)
 {
 	/* should not be called from interrupt context */
@@ -110,10 +132,18 @@ static int __register_ftrace_function(struct ftrace_ops *ops)
 		 * For one func, simply call it directly.
 		 * For more than one func, call the chain.
 		 */
+#ifdef CONFIG_HAVE_FUNCTION_TRACE_MCOUNT_TEST
 		if (ops->next == &ftrace_list_end)
 			ftrace_trace_function = ops->func;
 		else
 			ftrace_trace_function = ftrace_list_func;
+#else
+		if (ops->next == &ftrace_list_end)
+			__ftrace_trace_function = ops->func;
+		else
+			__ftrace_trace_function = ftrace_list_func;
+		ftrace_trace_function = ftrace_test_stop_func;
+#endif
 	}
 
 	spin_unlock(&ftrace_lock);
@@ -152,8 +182,7 @@ static int __unregister_ftrace_function(struct ftrace_ops *ops)
 
 	if (ftrace_enabled) {
 		/* If we only have one func left, then call that directly */
-		if (ftrace_list == &ftrace_list_end ||
-		    ftrace_list->next == &ftrace_list_end)
+		if (ftrace_list->next == &ftrace_list_end)
 			ftrace_trace_function = ftrace_list->func;
 	}
 
@@ -308,7 +337,7 @@ ftrace_record_ip(unsigned long ip)
 {
 	struct dyn_ftrace *rec;
 
-	if (!ftrace_enabled || ftrace_disabled)
+	if (ftrace_disabled)
 		return NULL;
 
 	rec = ftrace_alloc_dyn_node(ip);
@@ -322,14 +351,58 @@ ftrace_record_ip(unsigned long ip)
 	return rec;
 }
 
-#define FTRACE_ADDR ((long)(ftrace_caller))
+static void print_ip_ins(const char *fmt, unsigned char *p)
+{
+	int i;
+
+	printk(KERN_CONT "%s", fmt);
+
+	for (i = 0; i < MCOUNT_INSN_SIZE; i++)
+		printk(KERN_CONT "%s%02x", i ? ":" : "", p[i]);
+}
+
+static void ftrace_bug(int failed, unsigned long ip)
+{
+	switch (failed) {
+	case -EFAULT:
+		FTRACE_WARN_ON_ONCE(1);
+		pr_info("ftrace faulted on modifying ");
+		print_ip_sym(ip);
+		break;
+	case -EINVAL:
+		FTRACE_WARN_ON_ONCE(1);
+		pr_info("ftrace failed to modify ");
+		print_ip_sym(ip);
+		print_ip_ins(" actual: ", (unsigned char *)ip);
+		printk(KERN_CONT "\n");
+		break;
+	case -EPERM:
+		FTRACE_WARN_ON_ONCE(1);
+		pr_info("ftrace faulted on writing ");
+		print_ip_sym(ip);
+		break;
+	default:
+		FTRACE_WARN_ON_ONCE(1);
+		pr_info("ftrace faulted on unknown error ");
+		print_ip_sym(ip);
+	}
+}
+
 
 static int
-__ftrace_replace_code(struct dyn_ftrace *rec,
-		      unsigned char *nop, int enable)
+__ftrace_replace_code(struct dyn_ftrace *rec, int enable)
 {
 	unsigned long ip, fl;
-	unsigned char *call, *old, *new;
+	unsigned long ftrace_addr;
+
+#ifdef CONFIG_FUNCTION_RET_TRACER
+	if (ftrace_tracing_type == FTRACE_TYPE_ENTER)
+		ftrace_addr = (unsigned long)ftrace_caller;
+	else
+		ftrace_addr = (unsigned long)ftrace_return_caller;
+#else
+	ftrace_addr = (unsigned long)ftrace_caller;
+#endif
 
 	ip = rec->ip;
 
@@ -388,34 +461,28 @@ __ftrace_replace_code(struct dyn_ftrace *rec,
 		}
 	}
 
-	call = ftrace_call_replace(ip, FTRACE_ADDR);
-
-	if (rec->flags & FTRACE_FL_ENABLED) {
-		old = nop;
-		new = call;
-	} else {
-		old = call;
-		new = nop;
-	}
-
-	return ftrace_modify_code(ip, old, new);
+	if (rec->flags & FTRACE_FL_ENABLED)
+		return ftrace_make_call(rec, ftrace_addr);
+	else
+		return ftrace_make_nop(NULL, rec, ftrace_addr);
 }
 
 static void ftrace_replace_code(int enable)
 {
 	int i, failed;
-	unsigned char *nop = NULL;
 	struct dyn_ftrace *rec;
 	struct ftrace_page *pg;
 
-	nop = ftrace_nop_replace();
-
 	for (pg = ftrace_pages_start; pg; pg = pg->next) {
 		for (i = 0; i < pg->index; i++) {
 			rec = &pg->records[i];
 
-			/* don't modify code that has already faulted */
-			if (rec->flags & FTRACE_FL_FAILED)
+			/*
+			 * Skip over free records and records that have
+			 * failed.
+			 */
+			if (rec->flags & FTRACE_FL_FREE ||
+			    rec->flags & FTRACE_FL_FAILED)
 				continue;
 
 			/* ignore updates to this record's mcount site */
@@ -426,68 +493,30 @@ static void ftrace_replace_code(int enable)
 				unfreeze_record(rec);
 			}
 
-			failed = __ftrace_replace_code(rec, nop, enable);
+			failed = __ftrace_replace_code(rec, enable);
 			if (failed && (rec->flags & FTRACE_FL_CONVERTED)) {
 				rec->flags |= FTRACE_FL_FAILED;
 				if ((system_state == SYSTEM_BOOTING) ||
 				    !core_kernel_text(rec->ip)) {
 					ftrace_free_rec(rec);
-				}
+				} else
+					ftrace_bug(failed, rec->ip);
 			}
 		}
 	}
 }
 
-static void print_ip_ins(const char *fmt, unsigned char *p)
-{
-	int i;
-
-	printk(KERN_CONT "%s", fmt);
-
-	for (i = 0; i < MCOUNT_INSN_SIZE; i++)
-		printk(KERN_CONT "%s%02x", i ? ":" : "", p[i]);
-}
-
 static int
-ftrace_code_disable(struct dyn_ftrace *rec)
+ftrace_code_disable(struct module *mod, struct dyn_ftrace *rec)
 {
 	unsigned long ip;
-	unsigned char *nop, *call;
 	int ret;
 
 	ip = rec->ip;
 
-	nop = ftrace_nop_replace();
-	call = ftrace_call_replace(ip, mcount_addr);
-
-	ret = ftrace_modify_code(ip, call, nop);
+	ret = ftrace_make_nop(mod, rec, mcount_addr);
 	if (ret) {
-		switch (ret) {
-		case -EFAULT:
-			FTRACE_WARN_ON_ONCE(1);
-			pr_info("ftrace faulted on modifying ");
-			print_ip_sym(ip);
-			break;
-		case -EINVAL:
-			FTRACE_WARN_ON_ONCE(1);
-			pr_info("ftrace failed to modify ");
-			print_ip_sym(ip);
-			print_ip_ins(" expected: ", call);
-			print_ip_ins(" actual: ", (unsigned char *)ip);
-			print_ip_ins(" replace: ", nop);
-			printk(KERN_CONT "\n");
-			break;
-		case -EPERM:
-			FTRACE_WARN_ON_ONCE(1);
-			pr_info("ftrace faulted on writing ");
-			print_ip_sym(ip);
-			break;
-		default:
-			FTRACE_WARN_ON_ONCE(1);
-			pr_info("ftrace faulted on unknown error ");
-			print_ip_sym(ip);
-		}
-
+		ftrace_bug(ret, ip);
 		rec->flags |= FTRACE_FL_FAILED;
 		return 0;
 	}
@@ -515,7 +544,7 @@ static void ftrace_run_update_code(int command)
 }
 
 static ftrace_func_t saved_ftrace_func;
-static int ftrace_start;
+static int ftrace_start_up;
 static DEFINE_MUTEX(ftrace_start_lock);
 
 static void ftrace_startup(void)
@@ -526,7 +555,7 @@ static void ftrace_startup(void)
 		return;
 
 	mutex_lock(&ftrace_start_lock);
-	ftrace_start++;
+	ftrace_start_up++;
 	command |= FTRACE_ENABLE_CALLS;
 
 	if (saved_ftrace_func != ftrace_trace_function) {
@@ -550,8 +579,8 @@ static void ftrace_shutdown(void)
 		return;
 
 	mutex_lock(&ftrace_start_lock);
-	ftrace_start--;
-	if (!ftrace_start)
+	ftrace_start_up--;
+	if (!ftrace_start_up)
 		command |= FTRACE_DISABLE_CALLS;
 
 	if (saved_ftrace_func != ftrace_trace_function) {
@@ -577,8 +606,8 @@ static void ftrace_startup_sysctl(void)
 	mutex_lock(&ftrace_start_lock);
 	/* Force update next time */
 	saved_ftrace_func = NULL;
-	/* ftrace_start is true if we want ftrace running */
-	if (ftrace_start)
+	/* ftrace_start_up is true if we want ftrace running */
+	if (ftrace_start_up)
 		command |= FTRACE_ENABLE_CALLS;
 
 	ftrace_run_update_code(command);
@@ -593,8 +622,8 @@ static void ftrace_shutdown_sysctl(void)
 		return;
 
 	mutex_lock(&ftrace_start_lock);
-	/* ftrace_start is true if ftrace is running */
-	if (ftrace_start)
+	/* ftrace_start_up is true if ftrace is running */
+	if (ftrace_start_up)
 		command |= FTRACE_DISABLE_CALLS;
 
 	ftrace_run_update_code(command);
@@ -605,7 +634,7 @@ static cycle_t		ftrace_update_time;
 static unsigned long	ftrace_update_cnt;
 unsigned long		ftrace_update_tot_cnt;
 
-static int ftrace_update_code(void)
+static int ftrace_update_code(struct module *mod)
 {
 	struct dyn_ftrace *p, *t;
 	cycle_t start, stop;
@@ -622,7 +651,7 @@ static int ftrace_update_code(void)
 		list_del_init(&p->list);
 
 		/* convert record (i.e, patch mcount-call with NOP) */
-		if (ftrace_code_disable(p)) {
+		if (ftrace_code_disable(mod, p)) {
 			p->flags |= FTRACE_FL_CONVERTED;
 			ftrace_update_cnt++;
 		} else
@@ -1181,7 +1210,7 @@ ftrace_regex_release(struct inode *inode, struct file *file, int enable)
 
 	mutex_lock(&ftrace_sysctl_lock);
 	mutex_lock(&ftrace_start_lock);
-	if (ftrace_start && ftrace_enabled)
+	if (ftrace_start_up && ftrace_enabled)
 		ftrace_run_update_code(FTRACE_ENABLE_CALLS);
 	mutex_unlock(&ftrace_start_lock);
 	mutex_unlock(&ftrace_sysctl_lock);
@@ -1268,7 +1297,8 @@ static __init int ftrace_init_debugfs(void)
 
 fs_initcall(ftrace_init_debugfs);
 
-static int ftrace_convert_nops(unsigned long *start,
+static int ftrace_convert_nops(struct module *mod,
+			       unsigned long *start,
 			       unsigned long *end)
 {
 	unsigned long *p;
@@ -1279,23 +1309,32 @@ static int ftrace_convert_nops(unsigned long *start,
 	p = start;
 	while (p < end) {
 		addr = ftrace_call_adjust(*p++);
+		/*
+		 * Some architecture linkers will pad between
+		 * the different mcount_loc sections of different
+		 * object files to satisfy alignments.
+		 * Skip any NULL pointers.
+		 */
+		if (!addr)
+			continue;
 		ftrace_record_ip(addr);
 	}
 
 	/* disable interrupts to prevent kstop machine */
 	local_irq_save(flags);
-	ftrace_update_code();
+	ftrace_update_code(mod);
 	local_irq_restore(flags);
 	mutex_unlock(&ftrace_start_lock);
 
 	return 0;
 }
 
-void ftrace_init_module(unsigned long *start, unsigned long *end)
+void ftrace_init_module(struct module *mod,
+			unsigned long *start, unsigned long *end)
 {
 	if (ftrace_disabled || start == end)
 		return;
-	ftrace_convert_nops(start, end);
+	ftrace_convert_nops(mod, start, end);
 }
 
 extern unsigned long __start_mcount_loc[];
@@ -1325,7 +1364,8 @@ void __init ftrace_init(void)
 
 	last_ftrace_enabled = ftrace_enabled = 1;
 
-	ret = ftrace_convert_nops(__start_mcount_loc,
+	ret = ftrace_convert_nops(NULL,
+				  __start_mcount_loc,
 				  __stop_mcount_loc);
 
 	return;
@@ -1381,10 +1421,17 @@ int register_ftrace_function(struct ftrace_ops *ops)
 		return -1;
 
 	mutex_lock(&ftrace_sysctl_lock);
+
+	if (ftrace_tracing_type == FTRACE_TYPE_RETURN) {
+		ret = -EBUSY;
+		goto out;
+	}
+
 	ret = __register_ftrace_function(ops);
 	ftrace_startup();
-	mutex_unlock(&ftrace_sysctl_lock);
 
+out:
+	mutex_unlock(&ftrace_sysctl_lock);
 	return ret;
 }
 
@@ -1449,3 +1496,147 @@ ftrace_enable_sysctl(struct ctl_table *table, int write,
 	return ret;
 }
 
+#ifdef CONFIG_FUNCTION_RET_TRACER
+
+static atomic_t ftrace_retfunc_active;
+
+/* The callback that hooks the return of a function */
+trace_function_return_t ftrace_function_return =
+			(trace_function_return_t)ftrace_stub;
+
+
+/* Try to assign a return stack array on FTRACE_RETSTACK_ALLOC_SIZE tasks. */
+static int alloc_retstack_tasklist(struct ftrace_ret_stack **ret_stack_list)
+{
+	int i;
+	int ret = 0;
+	unsigned long flags;
+	int start = 0, end = FTRACE_RETSTACK_ALLOC_SIZE;
+	struct task_struct *g, *t;
+
+	for (i = 0; i < FTRACE_RETSTACK_ALLOC_SIZE; i++) {
+		ret_stack_list[i] = kmalloc(FTRACE_RETFUNC_DEPTH
+					* sizeof(struct ftrace_ret_stack),
+					GFP_KERNEL);
+		if (!ret_stack_list[i]) {
+			start = 0;
+			end = i;
+			ret = -ENOMEM;
+			goto free;
+		}
+	}
+
+	read_lock_irqsave(&tasklist_lock, flags);
+	do_each_thread(g, t) {
+		if (start == end) {
+			ret = -EAGAIN;
+			goto unlock;
+		}
+
+		if (t->ret_stack == NULL) {
+			t->ret_stack = ret_stack_list[start++];
+			t->curr_ret_stack = -1;
+			atomic_set(&t->trace_overrun, 0);
+		}
+	} while_each_thread(g, t);
+
+unlock:
+	read_unlock_irqrestore(&tasklist_lock, flags);
+free:
+	for (i = start; i < end; i++)
+		kfree(ret_stack_list[i]);
+	return ret;
+}
+
+/* Allocate a return stack for each task */
+static int start_return_tracing(void)
+{
+	struct ftrace_ret_stack **ret_stack_list;
+	int ret;
+
+	ret_stack_list = kmalloc(FTRACE_RETSTACK_ALLOC_SIZE *
+				sizeof(struct ftrace_ret_stack *),
+				GFP_KERNEL);
+
+	if (!ret_stack_list)
+		return -ENOMEM;
+
+	do {
+		ret = alloc_retstack_tasklist(ret_stack_list);
+	} while (ret == -EAGAIN);
+
+	kfree(ret_stack_list);
+	return ret;
+}
+
+int register_ftrace_return(trace_function_return_t func)
+{
+	int ret = 0;
+
+	mutex_lock(&ftrace_sysctl_lock);
+
+	/*
+	 * Don't launch return tracing if normal function
+	 * tracing is already running.
+	 */
+	if (ftrace_trace_function != ftrace_stub) {
+		ret = -EBUSY;
+		goto out;
+	}
+	atomic_inc(&ftrace_retfunc_active);
+	ret = start_return_tracing();
+	if (ret) {
+		atomic_dec(&ftrace_retfunc_active);
+		goto out;
+	}
+	ftrace_tracing_type = FTRACE_TYPE_RETURN;
+	ftrace_function_return = func;
+	ftrace_startup();
+
+out:
+	mutex_unlock(&ftrace_sysctl_lock);
+	return ret;
+}
+
+void unregister_ftrace_return(void)
+{
+	mutex_lock(&ftrace_sysctl_lock);
+
+	atomic_dec(&ftrace_retfunc_active);
+	ftrace_function_return = (trace_function_return_t)ftrace_stub;
+	ftrace_shutdown();
+	/* Restore normal tracing type */
+	ftrace_tracing_type = FTRACE_TYPE_ENTER;
+
+	mutex_unlock(&ftrace_sysctl_lock);
+}
+
+/* Allocate a return stack for newly created task */
+void ftrace_retfunc_init_task(struct task_struct *t)
+{
+	if (atomic_read(&ftrace_retfunc_active)) {
+		t->ret_stack = kmalloc(FTRACE_RETFUNC_DEPTH
+				* sizeof(struct ftrace_ret_stack),
+				GFP_KERNEL);
+		if (!t->ret_stack)
+			return;
+		t->curr_ret_stack = -1;
+		atomic_set(&t->trace_overrun, 0);
+	} else
+		t->ret_stack = NULL;
+}
+
+void ftrace_retfunc_exit_task(struct task_struct *t)
+{
+	struct ftrace_ret_stack	*ret_stack = t->ret_stack;
+
+	t->ret_stack = NULL;
+	/* NULL must become visible to IRQs before we free it: */
+	barrier();
+
+	kfree(ret_stack);
+}
+#endif
+
+
+

kernel/trace/ring_buffer.c

@@ -18,8 +18,46 @@
 
 #include "trace.h"
 
-/* Global flag to disable all recording to ring buffers */
-static int ring_buffers_off __read_mostly;
+/*
+ * A fast way to enable or disable all ring buffers is to
+ * call tracing_on or tracing_off. Turning off the ring buffers
+ * prevents all ring buffers from being recorded to.
+ * Turning this switch on, makes it OK to write to the
+ * ring buffer, if the ring buffer is enabled itself.
+ *
+ * There's three layers that must be on in order to write
+ * to the ring buffer.
+ *
+ * 1) This global flag must be set.
+ * 2) The ring buffer must be enabled for recording.
+ * 3) The per cpu buffer must be enabled for recording.
+ *
+ * In case of an anomaly, this global flag has a bit set that
+ * will permantly disable all ring buffers.
+ */
+
+/*
+ * Global flag to disable all recording to ring buffers
+ *  This has two bits: ON, DISABLED
+ *
+ *  ON   DISABLED
+ * ---- ----------
+ *   0      0        : ring buffers are off
+ *   1      0        : ring buffers are on
+ *   X      1        : ring buffers are permanently disabled
+ */
+
+enum {
+	RB_BUFFERS_ON_BIT	= 0,
+	RB_BUFFERS_DISABLED_BIT	= 1,
+};
+
+enum {
+	RB_BUFFERS_ON		= 1 << RB_BUFFERS_ON_BIT,
+	RB_BUFFERS_DISABLED	= 1 << RB_BUFFERS_DISABLED_BIT,
+};
+
+static long ring_buffer_flags __read_mostly = RB_BUFFERS_ON;
 
 /**
  * tracing_on - enable all tracing buffers
@@ -29,7 +67,7 @@ static int ring_buffers_off __read_mostly;
  */
 void tracing_on(void)
 {
-	ring_buffers_off = 0;
+	set_bit(RB_BUFFERS_ON_BIT, &ring_buffer_flags);
 }
 
 /**
@@ -42,9 +80,22 @@ void tracing_on(void)
  */
 void tracing_off(void)
 {
-	ring_buffers_off = 1;
+	clear_bit(RB_BUFFERS_ON_BIT, &ring_buffer_flags);
 }
 
+/**
+ * tracing_off_permanent - permanently disable ring buffers
+ *
+ * This function, once called, will disable all ring buffers
+ * permanenty.
+ */
+void tracing_off_permanent(void)
+{
+	set_bit(RB_BUFFERS_DISABLED_BIT, &ring_buffer_flags);
+}
+
+#include "trace.h"
+
 /* Up this if you want to test the TIME_EXTENTS and normalization */
 #define DEBUG_SHIFT 0
 
@@ -187,7 +238,8 @@ static inline int test_time_stamp(u64 delta)
 struct ring_buffer_per_cpu {
 	int				cpu;
 	struct ring_buffer		*buffer;
-	spinlock_t			lock;
+	spinlock_t			reader_lock; /* serialize readers */
+	raw_spinlock_t			lock;
 	struct lock_class_key		lock_key;
 	struct list_head		pages;
 	struct buffer_page		*head_page;	/* read from head */
@@ -221,32 +273,16 @@ struct ring_buffer_iter {
 	u64				read_stamp;
 };
 
+/* buffer may be either ring_buffer or ring_buffer_per_cpu */
 #define RB_WARN_ON(buffer, cond)				\
-	do {							\
-		if (unlikely(cond)) {				\
-			atomic_inc(&buffer->record_disabled);	\
-			WARN_ON(1);				\
-		}						\
-	} while (0)
-
-#define RB_WARN_ON_RET(buffer, cond)				\
-	do {							\
-		if (unlikely(cond)) {				\
-			atomic_inc(&buffer->record_disabled);	\
-			WARN_ON(1);				\
-			return -1;				\
-		}						\
-	} while (0)
-
-#define RB_WARN_ON_ONCE(buffer, cond)				\
-	do {							\
-		static int once;				\
-		if (unlikely(cond) && !once) {			\
-			once++;					\
+	({							\
+		int _____ret = unlikely(cond);			\
+		if (_____ret) {					\
 			atomic_inc(&buffer->record_disabled);	\
 			WARN_ON(1);				\
 		}						\
-	} while (0)
+		_____ret;					\
+	})
 
 /**
  * check_pages - integrity check of buffer pages
@@ -260,14 +296,18 @@ static int rb_check_pages(struct ring_buffer_per_cpu *cpu_buffer)
 	struct list_head *head = &cpu_buffer->pages;
 	struct buffer_page *page, *tmp;
 
-	RB_WARN_ON_RET(cpu_buffer, head->next->prev != head);
-	RB_WARN_ON_RET(cpu_buffer, head->prev->next != head);
+	if (RB_WARN_ON(cpu_buffer, head->next->prev != head))
+		return -1;
+	if (RB_WARN_ON(cpu_buffer, head->prev->next != head))
+		return -1;
 
 	list_for_each_entry_safe(page, tmp, head, list) {
-		RB_WARN_ON_RET(cpu_buffer,
-			       page->list.next->prev != &page->list);
-		RB_WARN_ON_RET(cpu_buffer,
-			       page->list.prev->next != &page->list);
+		if (RB_WARN_ON(cpu_buffer,
+			       page->list.next->prev != &page->list))
+			return -1;
+		if (RB_WARN_ON(cpu_buffer,
+			       page->list.prev->next != &page->list))
+			return -1;
 	}
 
 	return 0;
@@ -324,7 +364,8 @@ rb_allocate_cpu_buffer(struct ring_buffer *buffer, int cpu)
 
 	cpu_buffer->cpu = cpu;
 	cpu_buffer->buffer = buffer;
-	spin_lock_init(&cpu_buffer->lock);
+	spin_lock_init(&cpu_buffer->reader_lock);
+	cpu_buffer->lock = (raw_spinlock_t)__RAW_SPIN_LOCK_UNLOCKED;
 	INIT_LIST_HEAD(&cpu_buffer->pages);
 
 	page = kzalloc_node(ALIGN(sizeof(*page), cache_line_size()),
@@ -473,13 +514,15 @@ rb_remove_pages(struct ring_buffer_per_cpu *cpu_buffer, unsigned nr_pages)
 	synchronize_sched();
 
 	for (i = 0; i < nr_pages; i++) {
-		BUG_ON(list_empty(&cpu_buffer->pages));
+		if (RB_WARN_ON(cpu_buffer, list_empty(&cpu_buffer->pages)))
+			return;
 		p = cpu_buffer->pages.next;
 		page = list_entry(p, struct buffer_page, list);
 		list_del_init(&page->list);
 		free_buffer_page(page);
 	}
-	BUG_ON(list_empty(&cpu_buffer->pages));
+	if (RB_WARN_ON(cpu_buffer, list_empty(&cpu_buffer->pages)))
+		return;
 
 	rb_reset_cpu(cpu_buffer);
 
@@ -501,7 +544,8 @@ rb_insert_pages(struct ring_buffer_per_cpu *cpu_buffer,
 	synchronize_sched();
 
 	for (i = 0; i < nr_pages; i++) {
-		BUG_ON(list_empty(pages));
+		if (RB_WARN_ON(cpu_buffer, list_empty(pages)))
+			return;
 		p = pages->next;
 		page = list_entry(p, struct buffer_page, list);
 		list_del_init(&page->list);
@@ -562,7 +606,10 @@ int ring_buffer_resize(struct ring_buffer *buffer, unsigned long size)
 	if (size < buffer_size) {
 
 		/* easy case, just free pages */
-		BUG_ON(nr_pages >= buffer->pages);
+		if (RB_WARN_ON(buffer, nr_pages >= buffer->pages)) {
+			mutex_unlock(&buffer->mutex);
+			return -1;
+		}
 
 		rm_pages = buffer->pages - nr_pages;
 
@@ -581,7 +628,11 @@ int ring_buffer_resize(struct ring_buffer *buffer, unsigned long size)
 	 * add these pages to the cpu_buffers. Otherwise we just free
 	 * them all and return -ENOMEM;
 	 */
-	BUG_ON(nr_pages <= buffer->pages);
+	if (RB_WARN_ON(buffer, nr_pages <= buffer->pages)) {
+		mutex_unlock(&buffer->mutex);
+		return -1;
+	}
+
 	new_pages = nr_pages - buffer->pages;
 
 	for_each_buffer_cpu(buffer, cpu) {
@@ -604,7 +655,10 @@ int ring_buffer_resize(struct ring_buffer *buffer, unsigned long size)
 		rb_insert_pages(cpu_buffer, &pages, new_pages);
 	}
 
-	BUG_ON(!list_empty(&pages));
+	if (RB_WARN_ON(buffer, !list_empty(&pages))) {
+		mutex_unlock(&buffer->mutex);
+		return -1;
+	}
 
  out:
 	buffer->pages = nr_pages;
@@ -693,7 +747,8 @@ static void rb_update_overflow(struct ring_buffer_per_cpu *cpu_buffer)
 	     head += rb_event_length(event)) {
 
 		event = __rb_page_index(cpu_buffer->head_page, head);
-		BUG_ON(rb_null_event(event));
+		if (RB_WARN_ON(cpu_buffer, rb_null_event(event)))
+			return;
 		/* Only count data entries */
 		if (event->type != RINGBUF_TYPE_DATA)
 			continue;
@@ -746,8 +801,9 @@ rb_set_commit_event(struct ring_buffer_per_cpu *cpu_buffer,
 	addr &= PAGE_MASK;
 
 	while (cpu_buffer->commit_page->page != (void *)addr) {
-		RB_WARN_ON(cpu_buffer,
-			   cpu_buffer->commit_page == cpu_buffer->tail_page);
+		if (RB_WARN_ON(cpu_buffer,
+			  cpu_buffer->commit_page == cpu_buffer->tail_page))
+			return;
 		cpu_buffer->commit_page->commit =
 			cpu_buffer->commit_page->write;
 		rb_inc_page(cpu_buffer, &cpu_buffer->commit_page);
@@ -894,7 +950,8 @@ __rb_reserve_next(struct ring_buffer_per_cpu *cpu_buffer,
 	if (write > BUF_PAGE_SIZE) {
 		struct buffer_page *next_page = tail_page;
 
-		spin_lock_irqsave(&cpu_buffer->lock, flags);
+		local_irq_save(flags);
+		__raw_spin_lock(&cpu_buffer->lock);
 
 		rb_inc_page(cpu_buffer, &next_page);
 
@@ -902,7 +959,8 @@ __rb_reserve_next(struct ring_buffer_per_cpu *cpu_buffer,
 		reader_page = cpu_buffer->reader_page;
 
 		/* we grabbed the lock before incrementing */
-		RB_WARN_ON(cpu_buffer, next_page == reader_page);
+		if (RB_WARN_ON(cpu_buffer, next_page == reader_page))
+			goto out_unlock;
 
 		/*
 		 * If for some reason, we had an interrupt storm that made
@@ -970,7 +1028,8 @@ __rb_reserve_next(struct ring_buffer_per_cpu *cpu_buffer,
 			rb_set_commit_to_write(cpu_buffer);
 		}
 
-		spin_unlock_irqrestore(&cpu_buffer->lock, flags);
+		__raw_spin_unlock(&cpu_buffer->lock);
+		local_irq_restore(flags);
 
 		/* fail and let the caller try again */
 		return ERR_PTR(-EAGAIN);
@@ -978,7 +1037,8 @@ __rb_reserve_next(struct ring_buffer_per_cpu *cpu_buffer,
 
 	/* We reserved something on the buffer */
 
-	BUG_ON(write > BUF_PAGE_SIZE);
+	if (RB_WARN_ON(cpu_buffer, write > BUF_PAGE_SIZE))
+		return NULL;
 
 	event = __rb_page_index(tail_page, tail);
 	rb_update_event(event, type, length);
@@ -993,7 +1053,8 @@ __rb_reserve_next(struct ring_buffer_per_cpu *cpu_buffer,
 	return event;
 
  out_unlock:
-	spin_unlock_irqrestore(&cpu_buffer->lock, flags);
+	__raw_spin_unlock(&cpu_buffer->lock);
+	local_irq_restore(flags);
 	return NULL;
 }
 
@@ -1076,10 +1137,8 @@ rb_reserve_next_event(struct ring_buffer_per_cpu *cpu_buffer,
 	 * storm or we have something buggy.
 	 * Bail!
 	 */
-	if (unlikely(++nr_loops > 1000)) {
-		RB_WARN_ON(cpu_buffer, 1);
+	if (RB_WARN_ON(cpu_buffer, ++nr_loops > 1000))
 		return NULL;
-	}
 
 	ts = ring_buffer_time_stamp(cpu_buffer->cpu);
 
@@ -1175,15 +1234,14 @@ ring_buffer_lock_reserve(struct ring_buffer *buffer,
 	struct ring_buffer_event *event;
 	int cpu, resched;
 
-	if (ring_buffers_off)
+	if (ring_buffer_flags != RB_BUFFERS_ON)
 		return NULL;
 
 	if (atomic_read(&buffer->record_disabled))
 		return NULL;
 
 	/* If we are tracing schedule, we don't want to recurse */
-	resched = need_resched();
-	preempt_disable_notrace();
+	resched = ftrace_preempt_disable();
 
 	cpu = raw_smp_processor_id();
 
@@ -1214,10 +1272,7 @@ ring_buffer_lock_reserve(struct ring_buffer *buffer,
 	return event;
 
  out:
-	if (resched)
-		preempt_enable_notrace();
-	else
-		preempt_enable_notrace();
+	ftrace_preempt_enable(resched);
 	return NULL;
 }
 
@@ -1259,12 +1314,9 @@ int ring_buffer_unlock_commit(struct ring_buffer *buffer,
 	/*
 	 * Only the last preempt count needs to restore preemption.
 	 */
-	if (preempt_count() == 1) {
-		if (per_cpu(rb_need_resched, cpu))
-			preempt_enable_no_resched_notrace();
-		else
-			preempt_enable_notrace();
-	} else
+	if (preempt_count() == 1)
+		ftrace_preempt_enable(per_cpu(rb_need_resched, cpu));
+	else
 		preempt_enable_no_resched_notrace();
 
 	return 0;
@@ -1294,14 +1346,13 @@ int ring_buffer_write(struct ring_buffer *buffer,
 	int ret = -EBUSY;
 	int cpu, resched;
 
-	if (ring_buffers_off)
+	if (ring_buffer_flags != RB_BUFFERS_ON)
 		return -EBUSY;
 
 	if (atomic_read(&buffer->record_disabled))
 		return -EBUSY;
 
-	resched = need_resched();
-	preempt_disable_notrace();
+	resched = ftrace_preempt_disable();
 
 	cpu = raw_smp_processor_id();
 
@@ -1327,10 +1378,7 @@ int ring_buffer_write(struct ring_buffer *buffer,
 
 	ret = 0;
  out:
-	if (resched)
-		preempt_enable_no_resched_notrace();
-	else
-		preempt_enable_notrace();
+	ftrace_preempt_enable(resched);
 
 	return ret;
 }
@@ -1489,14 +1537,7 @@ unsigned long ring_buffer_overruns(struct ring_buffer *buffer)
 	return overruns;
 }
 
-/**
- * ring_buffer_iter_reset - reset an iterator
- * @iter: The iterator to reset
- *
- * Resets the iterator, so that it will start from the beginning
- * again.
- */
-void ring_buffer_iter_reset(struct ring_buffer_iter *iter)
+static void rb_iter_reset(struct ring_buffer_iter *iter)
 {
 	struct ring_buffer_per_cpu *cpu_buffer = iter->cpu_buffer;
 
@@ -1514,6 +1555,23 @@ void ring_buffer_iter_reset(struct ring_buffer_iter *iter)
 		iter->read_stamp = iter->head_page->time_stamp;
 }
 
+/**
+ * ring_buffer_iter_reset - reset an iterator
+ * @iter: The iterator to reset
+ *
+ * Resets the iterator, so that it will start from the beginning
+ * again.
+ */
+void ring_buffer_iter_reset(struct ring_buffer_iter *iter)
+{
+	struct ring_buffer_per_cpu *cpu_buffer = iter->cpu_buffer;
+	unsigned long flags;
+
+	spin_lock_irqsave(&cpu_buffer->reader_lock, flags);
+	rb_iter_reset(iter);
+	spin_unlock_irqrestore(&cpu_buffer->reader_lock, flags);
+}
+
 /**
  * ring_buffer_iter_empty - check if an iterator has no more to read
  * @iter: The iterator to check
@@ -1597,7 +1655,8 @@ rb_get_reader_page(struct ring_buffer_per_cpu *cpu_buffer)
 	unsigned long flags;
 	int nr_loops = 0;
 
-	spin_lock_irqsave(&cpu_buffer->lock, flags);
+	local_irq_save(flags);
+	__raw_spin_lock(&cpu_buffer->lock);
 
  again:
 	/*
@@ -1606,8 +1665,7 @@ rb_get_reader_page(struct ring_buffer_per_cpu *cpu_buffer)
 	 * a case where we will loop three times. There should be no
 	 * reason to loop four times (that I know of).
 	 */
-	if (unlikely(++nr_loops > 3)) {
-		RB_WARN_ON(cpu_buffer, 1);
+	if (RB_WARN_ON(cpu_buffer, ++nr_loops > 3)) {
 		reader = NULL;
 		goto out;
 	}
@@ -1619,8 +1677,9 @@ rb_get_reader_page(struct ring_buffer_per_cpu *cpu_buffer)
 		goto out;
 
 	/* Never should we have an index greater than the size */
-	RB_WARN_ON(cpu_buffer,
-		   cpu_buffer->reader_page->read > rb_page_size(reader));
+	if (RB_WARN_ON(cpu_buffer,
+		       cpu_buffer->reader_page->read > rb_page_size(reader)))
+		goto out;
 
 	/* check if we caught up to the tail */
 	reader = NULL;
@@ -1659,7 +1718,8 @@ rb_get_reader_page(struct ring_buffer_per_cpu *cpu_buffer)
 	goto again;
 
  out:
-	spin_unlock_irqrestore(&cpu_buffer->lock, flags);
+	__raw_spin_unlock(&cpu_buffer->lock);
+	local_irq_restore(flags);
 
 	return reader;
 }
@@ -1673,7 +1733,8 @@ static void rb_advance_reader(struct ring_buffer_per_cpu *cpu_buffer)
 	reader = rb_get_reader_page(cpu_buffer);
 
 	/* This function should not be called when buffer is empty */
-	BUG_ON(!reader);
+	if (RB_WARN_ON(cpu_buffer, !reader))
+		return;
 
 	event = rb_reader_event(cpu_buffer);
 
@@ -1700,7 +1761,9 @@ static void rb_advance_iter(struct ring_buffer_iter *iter)
 	 * Check if we are at the end of the buffer.
 	 */
 	if (iter->head >= rb_page_size(iter->head_page)) {
-		BUG_ON(iter->head_page == cpu_buffer->commit_page);
+		if (RB_WARN_ON(buffer,
+			       iter->head_page == cpu_buffer->commit_page))
+			return;
 		rb_inc_iter(iter);
 		return;
 	}
@@ -1713,8 +1776,10 @@ static void rb_advance_iter(struct ring_buffer_iter *iter)
 	 * This should not be called to advance the header if we are
 	 * at the tail of the buffer.
 	 */
-	BUG_ON((iter->head_page == cpu_buffer->commit_page) &&
-	       (iter->head + length > rb_commit_index(cpu_buffer)));
+	if (RB_WARN_ON(cpu_buffer,
+		       (iter->head_page == cpu_buffer->commit_page) &&
+		       (iter->head + length > rb_commit_index(cpu_buffer))))
+		return;
 
 	rb_update_iter_read_stamp(iter, event);
 
@@ -1726,17 +1791,8 @@ static void rb_advance_iter(struct ring_buffer_iter *iter)
 		rb_advance_iter(iter);
 }
 
-/**
- * ring_buffer_peek - peek at the next event to be read
- * @buffer: The ring buffer to read
- * @cpu: The cpu to peak at
- * @ts: The timestamp counter of this event.
- *
- * This will return the event that will be read next, but does
- * not consume the data.
- */
-struct ring_buffer_event *
-ring_buffer_peek(struct ring_buffer *buffer, int cpu, u64 *ts)
+static struct ring_buffer_event *
+rb_buffer_peek(struct ring_buffer *buffer, int cpu, u64 *ts)
 {
 	struct ring_buffer_per_cpu *cpu_buffer;
 	struct ring_buffer_event *event;
@@ -1757,10 +1813,8 @@ ring_buffer_peek(struct ring_buffer *buffer, int cpu, u64 *ts)
 	 * can have.  Nesting 10 deep of interrupts is clearly
 	 * an anomaly.
 	 */
-	if (unlikely(++nr_loops > 10)) {
-		RB_WARN_ON(cpu_buffer, 1);
+	if (RB_WARN_ON(cpu_buffer, ++nr_loops > 10))
 		return NULL;
-	}
 
 	reader = rb_get_reader_page(cpu_buffer);
 	if (!reader)
@@ -1798,16 +1852,8 @@ ring_buffer_peek(struct ring_buffer *buffer, int cpu, u64 *ts)
 	return NULL;
 }
 
-/**
- * ring_buffer_iter_peek - peek at the next event to be read
- * @iter: The ring buffer iterator
- * @ts: The timestamp counter of this event.
- *
- * This will return the event that will be read next, but does
- * not increment the iterator.
- */
-struct ring_buffer_event *
-ring_buffer_iter_peek(struct ring_buffer_iter *iter, u64 *ts)
+static struct ring_buffer_event *
+rb_iter_peek(struct ring_buffer_iter *iter, u64 *ts)
 {
 	struct ring_buffer *buffer;
 	struct ring_buffer_per_cpu *cpu_buffer;
@@ -1829,10 +1875,8 @@ ring_buffer_iter_peek(struct ring_buffer_iter *iter, u64 *ts)
 	 * can have. Nesting 10 deep of interrupts is clearly
 	 * an anomaly.
 	 */
-	if (unlikely(++nr_loops > 10)) {
-		RB_WARN_ON(cpu_buffer, 1);
+	if (RB_WARN_ON(cpu_buffer, ++nr_loops > 10))
 		return NULL;
-	}
 
 	if (rb_per_cpu_empty(cpu_buffer))
 		return NULL;
@@ -1868,6 +1912,51 @@ ring_buffer_iter_peek(struct ring_buffer_iter *iter, u64 *ts)
 	return NULL;
 }
 
+/**
+ * ring_buffer_peek - peek at the next event to be read
+ * @buffer: The ring buffer to read
+ * @cpu: The cpu to peak at
+ * @ts: The timestamp counter of this event.
+ *
+ * This will return the event that will be read next, but does
+ * not consume the data.
+ */
+struct ring_buffer_event *
+ring_buffer_peek(struct ring_buffer *buffer, int cpu, u64 *ts)
+{
+	struct ring_buffer_per_cpu *cpu_buffer = buffer->buffers[cpu];
+	struct ring_buffer_event *event;
+	unsigned long flags;
+
+	spin_lock_irqsave(&cpu_buffer->reader_lock, flags);
+	event = rb_buffer_peek(buffer, cpu, ts);
+	spin_unlock_irqrestore(&cpu_buffer->reader_lock, flags);
+
+	return event;
+}
+
+/**
+ * ring_buffer_iter_peek - peek at the next event to be read
+ * @iter: The ring buffer iterator
+ * @ts: The timestamp counter of this event.
+ *
+ * This will return the event that will be read next, but does
+ * not increment the iterator.
+ */
+struct ring_buffer_event *
+ring_buffer_iter_peek(struct ring_buffer_iter *iter, u64 *ts)
+{
+	struct ring_buffer_per_cpu *cpu_buffer = iter->cpu_buffer;
+	struct ring_buffer_event *event;
+	unsigned long flags;
+
+	spin_lock_irqsave(&cpu_buffer->reader_lock, flags);
+	event = rb_iter_peek(iter, ts);
+	spin_unlock_irqrestore(&cpu_buffer->reader_lock, flags);
+
+	return event;
+}
+
 /**
  * ring_buffer_consume - return an event and consume it
  * @buffer: The ring buffer to get the next event from
@@ -1879,19 +1968,24 @@ ring_buffer_iter_peek(struct ring_buffer_iter *iter, u64 *ts)
 struct ring_buffer_event *
 ring_buffer_consume(struct ring_buffer *buffer, int cpu, u64 *ts)
 {
-	struct ring_buffer_per_cpu *cpu_buffer;
+	struct ring_buffer_per_cpu *cpu_buffer = buffer->buffers[cpu];
 	struct ring_buffer_event *event;
+	unsigned long flags;
 
 	if (!cpu_isset(cpu, buffer->cpumask))
 		return NULL;
 
-	event = ring_buffer_peek(buffer, cpu, ts);
+	spin_lock_irqsave(&cpu_buffer->reader_lock, flags);
+
+	event = rb_buffer_peek(buffer, cpu, ts);
 	if (!event)
-		return NULL;
+		goto out;
 
-	cpu_buffer = buffer->buffers[cpu];
 	rb_advance_reader(cpu_buffer);
 
+ out:
+	spin_unlock_irqrestore(&cpu_buffer->reader_lock, flags);
+
 	return event;
 }
 
@@ -1928,9 +2022,11 @@ ring_buffer_read_start(struct ring_buffer *buffer, int cpu)
 	atomic_inc(&cpu_buffer->record_disabled);
 	synchronize_sched();
 
-	spin_lock_irqsave(&cpu_buffer->lock, flags);
-	ring_buffer_iter_reset(iter);
-	spin_unlock_irqrestore(&cpu_buffer->lock, flags);
+	spin_lock_irqsave(&cpu_buffer->reader_lock, flags);
+	__raw_spin_lock(&cpu_buffer->lock);
+	rb_iter_reset(iter);
+	__raw_spin_unlock(&cpu_buffer->lock);
+	spin_unlock_irqrestore(&cpu_buffer->reader_lock, flags);
 
 	return iter;
 }
@@ -1962,12 +2058,17 @@ struct ring_buffer_event *
 ring_buffer_read(struct ring_buffer_iter *iter, u64 *ts)
 {
 	struct ring_buffer_event *event;
+	struct ring_buffer_per_cpu *cpu_buffer = iter->cpu_buffer;
+	unsigned long flags;
 
-	event = ring_buffer_iter_peek(iter, ts);
+	spin_lock_irqsave(&cpu_buffer->reader_lock, flags);
+	event = rb_iter_peek(iter, ts);
 	if (!event)
-		return NULL;
+		goto out;
 
 	rb_advance_iter(iter);
+ out:
+	spin_unlock_irqrestore(&cpu_buffer->reader_lock, flags);
 
 	return event;
 }
@@ -2016,11 +2117,15 @@ void ring_buffer_reset_cpu(struct ring_buffer *buffer, int cpu)
 	if (!cpu_isset(cpu, buffer->cpumask))
 		return;
 
-	spin_lock_irqsave(&cpu_buffer->lock, flags);
+	spin_lock_irqsave(&cpu_buffer->reader_lock, flags);
+
+	__raw_spin_lock(&cpu_buffer->lock);
 
 	rb_reset_cpu(cpu_buffer);
 
-	spin_unlock_irqrestore(&cpu_buffer->lock, flags);
+	__raw_spin_unlock(&cpu_buffer->lock);
+
+	spin_unlock_irqrestore(&cpu_buffer->reader_lock, flags);
 }
 
 /**
@@ -2122,12 +2227,14 @@ static ssize_t
 rb_simple_read(struct file *filp, char __user *ubuf,
 	       size_t cnt, loff_t *ppos)
 {
-	int *p = filp->private_data;
+	long *p = filp->private_data;
 	char buf[64];
 	int r;
 
-	/* !ring_buffers_off == tracing_on */
-	r = sprintf(buf, "%d\n", !*p);
+	if (test_bit(RB_BUFFERS_DISABLED_BIT, p))
+		r = sprintf(buf, "permanently disabled\n");
+	else
+		r = sprintf(buf, "%d\n", test_bit(RB_BUFFERS_ON_BIT, p));
 
 	return simple_read_from_buffer(ubuf, cnt, ppos, buf, r);
 }
@@ -2136,7 +2243,7 @@ static ssize_t
 rb_simple_write(struct file *filp, const char __user *ubuf,
 		size_t cnt, loff_t *ppos)
 {
-	int *p = filp->private_data;
+	long *p = filp->private_data;
 	char buf[64];
 	long val;
 	int ret;
@@ -2153,8 +2260,10 @@ rb_simple_write(struct file *filp, const char __user *ubuf,
 	if (ret < 0)
 		return ret;
 
-	/* !ring_buffers_off == tracing_on */
-	*p = !val;
+	if (val)
+		set_bit(RB_BUFFERS_ON_BIT, p);
+	else
+		clear_bit(RB_BUFFERS_ON_BIT, p);
 
 	(*ppos)++;
 
@@ -2176,7 +2285,7 @@ static __init int rb_init_debugfs(void)
 	d_tracer = tracing_init_dentry();
 
 	entry = debugfs_create_file("tracing_on", 0644, d_tracer,
-				    &ring_buffers_off, &rb_simple_fops);
+				    &ring_buffer_flags, &rb_simple_fops);
 	if (!entry)
 		pr_warning("Could not create debugfs 'tracing_on' entry\n");
 

kernel/trace/trace.h

@@ -8,6 +8,7 @@
 #include <linux/ring_buffer.h>
 #include <linux/mmiotrace.h>
 #include <linux/ftrace.h>
+#include <trace/boot.h>
 
 enum trace_type {
 	__TRACE_FIRST_TYPE = 0,
@@ -21,7 +22,11 @@ enum trace_type {
 	TRACE_SPECIAL,
 	TRACE_MMIO_RW,
 	TRACE_MMIO_MAP,
-	TRACE_BOOT,
+	TRACE_BRANCH,
+	TRACE_BOOT_CALL,
+	TRACE_BOOT_RET,
+	TRACE_FN_RET,
+	TRACE_USER_STACK,
 
 	__TRACE_LAST_TYPE
 };
@@ -38,6 +43,7 @@ struct trace_entry {
 	unsigned char		flags;
 	unsigned char		preempt_count;
 	int			pid;
+	int			tgid;
 };
 
 /*
@@ -48,6 +54,16 @@ struct ftrace_entry {
 	unsigned long		ip;
 	unsigned long		parent_ip;
 };
+
+/* Function return entry */
+struct ftrace_ret_entry {
+	struct trace_entry	ent;
+	unsigned long		ip;
+	unsigned long		parent_ip;
+	unsigned long long	calltime;
+	unsigned long long	rettime;
+	unsigned long		overrun;
+};
 extern struct tracer boot_tracer;
 
 /*
@@ -85,6 +101,11 @@ struct stack_entry {
 	unsigned long		caller[FTRACE_STACK_ENTRIES];
 };
 
+struct userstack_entry {
+	struct trace_entry	ent;
+	unsigned long		caller[FTRACE_STACK_ENTRIES];
+};
+
 /*
  * ftrace_printk entry:
  */
@@ -112,9 +133,24 @@ struct trace_mmiotrace_map {
 	struct mmiotrace_map	map;
 };
 
-struct trace_boot {
+struct trace_boot_call {
 	struct trace_entry	ent;
-	struct boot_trace	initcall;
+	struct boot_trace_call boot_call;
+};
+
+struct trace_boot_ret {
+	struct trace_entry	ent;
+	struct boot_trace_ret boot_ret;
+};
+
+#define TRACE_FUNC_SIZE 30
+#define TRACE_FILE_SIZE 20
+struct trace_branch {
+	struct trace_entry	ent;
+	unsigned	        line;
+	char			func[TRACE_FUNC_SIZE+1];
+	char			file[TRACE_FILE_SIZE+1];
+	char			correct;
 };
 
 /*
@@ -172,7 +208,6 @@ struct trace_iterator;
 struct trace_array {
 	struct ring_buffer	*buffer;
 	unsigned long		entries;
-	long			ctrl;
 	int			cpu;
 	cycle_t			time_start;
 	struct task_struct	*waiter;
@@ -212,13 +247,17 @@ extern void __ftrace_bad_type(void);
 		IF_ASSIGN(var, ent, struct ctx_switch_entry, 0);	\
 		IF_ASSIGN(var, ent, struct trace_field_cont, TRACE_CONT); \
 		IF_ASSIGN(var, ent, struct stack_entry, TRACE_STACK);	\
+		IF_ASSIGN(var, ent, struct userstack_entry, TRACE_USER_STACK);\
 		IF_ASSIGN(var, ent, struct print_entry, TRACE_PRINT);	\
 		IF_ASSIGN(var, ent, struct special_entry, 0);		\
 		IF_ASSIGN(var, ent, struct trace_mmiotrace_rw,		\
 			  TRACE_MMIO_RW);				\
 		IF_ASSIGN(var, ent, struct trace_mmiotrace_map,		\
 			  TRACE_MMIO_MAP);				\
-		IF_ASSIGN(var, ent, struct trace_boot, TRACE_BOOT);	\
+		IF_ASSIGN(var, ent, struct trace_boot_call, TRACE_BOOT_CALL);\
+		IF_ASSIGN(var, ent, struct trace_boot_ret, TRACE_BOOT_RET);\
+		IF_ASSIGN(var, ent, struct trace_branch, TRACE_BRANCH); \
+		IF_ASSIGN(var, ent, struct ftrace_ret_entry, TRACE_FN_RET);\
 		__ftrace_bad_type();					\
 	} while (0)
 
@@ -229,29 +268,55 @@ enum print_line_t {
 	TRACE_TYPE_UNHANDLED	= 2	/* Relay to other output functions */
 };
 
+
+/*
+ * An option specific to a tracer. This is a boolean value.
+ * The bit is the bit index that sets its value on the
+ * flags value in struct tracer_flags.
+ */
+struct tracer_opt {
+	const char 	*name; /* Will appear on the trace_options file */
+	u32 		bit; /* Mask assigned in val field in tracer_flags */
+};
+
+/*
+ * The set of specific options for a tracer. Your tracer
+ * have to set the initial value of the flags val.
+ */
+struct tracer_flags {
+	u32			val;
+	struct tracer_opt 	*opts;
+};
+
+/* Makes more easy to define a tracer opt */
+#define TRACER_OPT(s, b)	.name = #s, .bit = b
+
 /*
  * A specific tracer, represented by methods that operate on a trace array:
  */
 struct tracer {
 	const char		*name;
-	void			(*init)(struct trace_array *tr);
+	/* Your tracer should raise a warning if init fails */
+	int			(*init)(struct trace_array *tr);
 	void			(*reset)(struct trace_array *tr);
+	void			(*start)(struct trace_array *tr);
+	void			(*stop)(struct trace_array *tr);
 	void			(*open)(struct trace_iterator *iter);
 	void			(*pipe_open)(struct trace_iterator *iter);
 	void			(*close)(struct trace_iterator *iter);
-	void			(*start)(struct trace_iterator *iter);
-	void			(*stop)(struct trace_iterator *iter);
 	ssize_t			(*read)(struct trace_iterator *iter,
 					struct file *filp, char __user *ubuf,
 					size_t cnt, loff_t *ppos);
-	void			(*ctrl_update)(struct trace_array *tr);
 #ifdef CONFIG_FTRACE_STARTUP_TEST
 	int			(*selftest)(struct tracer *trace,
 					    struct trace_array *tr);
 #endif
 	enum print_line_t	(*print_line)(struct trace_iterator *iter);
+	/* If you handled the flag setting, return 0 */
+	int			(*set_flag)(u32 old_flags, u32 bit, int set);
 	struct tracer		*next;
 	int			print_max;
+	struct tracer_flags 	*flags;
 };
 
 struct trace_seq {
@@ -279,8 +344,11 @@ struct trace_iterator {
 	unsigned long		iter_flags;
 	loff_t			pos;
 	long			idx;
+
+	cpumask_t		started;
 };
 
+int tracing_is_enabled(void);
 void trace_wake_up(void);
 void tracing_reset(struct trace_array *tr, int cpu);
 int tracing_open_generic(struct inode *inode, struct file *filp);
@@ -320,9 +388,14 @@ void trace_function(struct trace_array *tr,
 		    unsigned long ip,
 		    unsigned long parent_ip,
 		    unsigned long flags, int pc);
+void
+trace_function_return(struct ftrace_retfunc *trace);
 
 void tracing_start_cmdline_record(void);
 void tracing_stop_cmdline_record(void);
+void tracing_sched_switch_assign_trace(struct trace_array *tr);
+void tracing_stop_sched_switch_record(void);
+void tracing_start_sched_switch_record(void);
 int register_tracer(struct tracer *type);
 void unregister_tracer(struct tracer *type);
 
@@ -383,12 +456,18 @@ extern int trace_selftest_startup_sched_switch(struct tracer *trace,
 					       struct trace_array *tr);
 extern int trace_selftest_startup_sysprof(struct tracer *trace,
 					       struct trace_array *tr);
+extern int trace_selftest_startup_branch(struct tracer *trace,
+					 struct trace_array *tr);
 #endif /* CONFIG_FTRACE_STARTUP_TEST */
 
 extern void *head_page(struct trace_array_cpu *data);
 extern int trace_seq_printf(struct trace_seq *s, const char *fmt, ...);
 extern void trace_seq_print_cont(struct trace_seq *s,
 				 struct trace_iterator *iter);
+
+extern int
+seq_print_ip_sym(struct trace_seq *s, unsigned long ip,
+		unsigned long sym_flags);
 extern ssize_t trace_seq_to_user(struct trace_seq *s, char __user *ubuf,
 				 size_t cnt);
 extern long ns2usecs(cycle_t nsec);
@@ -396,6 +475,17 @@ extern int trace_vprintk(unsigned long ip, const char *fmt, va_list args);
 
 extern unsigned long trace_flags;
 
+/* Standard output formatting function used for function return traces */
+#ifdef CONFIG_FUNCTION_RET_TRACER
+extern enum print_line_t print_return_function(struct trace_iterator *iter);
+#else
+static inline enum print_line_t
+print_return_function(struct trace_iterator *iter)
+{
+	return TRACE_TYPE_UNHANDLED;
+}
+#endif
+
 /*
  * trace_iterator_flags is an enumeration that defines bit
  * positions into trace_flags that controls the output.
@@ -415,8 +505,92 @@ enum trace_iterator_flags {
 	TRACE_ITER_STACKTRACE		= 0x100,
 	TRACE_ITER_SCHED_TREE		= 0x200,
 	TRACE_ITER_PRINTK		= 0x400,
+	TRACE_ITER_PREEMPTONLY		= 0x800,
+	TRACE_ITER_BRANCH		= 0x1000,
+	TRACE_ITER_ANNOTATE		= 0x2000,
+	TRACE_ITER_USERSTACKTRACE       = 0x4000,
+	TRACE_ITER_SYM_USEROBJ          = 0x8000
 };
 
+/*
+ * TRACE_ITER_SYM_MASK masks the options in trace_flags that
+ * control the output of kernel symbols.
+ */
+#define TRACE_ITER_SYM_MASK \
+	(TRACE_ITER_PRINT_PARENT|TRACE_ITER_SYM_OFFSET|TRACE_ITER_SYM_ADDR)
+
 extern struct tracer nop_trace;
 
+/**
+ * ftrace_preempt_disable - disable preemption scheduler safe
+ *
+ * When tracing can happen inside the scheduler, there exists
+ * cases that the tracing might happen before the need_resched
+ * flag is checked. If this happens and the tracer calls
+ * preempt_enable (after a disable), a schedule might take place
+ * causing an infinite recursion.
+ *
+ * To prevent this, we read the need_recshed flag before
+ * disabling preemption. When we want to enable preemption we
+ * check the flag, if it is set, then we call preempt_enable_no_resched.
+ * Otherwise, we call preempt_enable.
+ *
+ * The rational for doing the above is that if need resched is set
+ * and we have yet to reschedule, we are either in an atomic location
+ * (where we do not need to check for scheduling) or we are inside
+ * the scheduler and do not want to resched.
+ */
+static inline int ftrace_preempt_disable(void)
+{
+	int resched;
+
+	resched = need_resched();
+	preempt_disable_notrace();
+
+	return resched;
+}
+
+/**
+ * ftrace_preempt_enable - enable preemption scheduler safe
+ * @resched: the return value from ftrace_preempt_disable
+ *
+ * This is a scheduler safe way to enable preemption and not miss
+ * any preemption checks. The disabled saved the state of preemption.
+ * If resched is set, then we were either inside an atomic or
+ * are inside the scheduler (we would have already scheduled
+ * otherwise). In this case, we do not want to call normal
+ * preempt_enable, but preempt_enable_no_resched instead.
+ */
+static inline void ftrace_preempt_enable(int resched)
+{
+	if (resched)
+		preempt_enable_no_resched_notrace();
+	else
+		preempt_enable_notrace();
+}
+
+#ifdef CONFIG_BRANCH_TRACER
+extern int enable_branch_tracing(struct trace_array *tr);
+extern void disable_branch_tracing(void);
+static inline int trace_branch_enable(struct trace_array *tr)
+{
+	if (trace_flags & TRACE_ITER_BRANCH)
+		return enable_branch_tracing(tr);
+	return 0;
+}
+static inline void trace_branch_disable(void)
+{
+	/* due to races, always disable */
+	disable_branch_tracing();
+}
+#else
+static inline int trace_branch_enable(struct trace_array *tr)
+{
+	return 0;
+}
+static inline void trace_branch_disable(void)
+{
+}
+#endif /* CONFIG_BRANCH_TRACER */
+
 #endif /* _LINUX_KERNEL_TRACE_H */

kernel/trace/trace_boot.c

@@ -13,73 +13,117 @@
 #include "trace.h"
 
 static struct trace_array *boot_trace;
-static int trace_boot_enabled;
+static bool pre_initcalls_finished;
 
-
-/* Should be started after do_pre_smp_initcalls() in init/main.c */
+/* Tells the boot tracer that the pre_smp_initcalls are finished.
+ * So we are ready .
+ * It doesn't enable sched events tracing however.
+ * You have to call enable_boot_trace to do so.
+ */
 void start_boot_trace(void)
 {
-	trace_boot_enabled = 1;
+	pre_initcalls_finished = true;
 }
 
-void stop_boot_trace(void)
+void enable_boot_trace(void)
 {
-	trace_boot_enabled = 0;
+	if (pre_initcalls_finished)
+		tracing_start_sched_switch_record();
 }
 
-void reset_boot_trace(struct trace_array *tr)
+void disable_boot_trace(void)
 {
-	stop_boot_trace();
+	if (pre_initcalls_finished)
+		tracing_stop_sched_switch_record();
 }
 
-static void boot_trace_init(struct trace_array *tr)
+static void reset_boot_trace(struct trace_array *tr)
 {
 	int cpu;
-	boot_trace = tr;
 
-	trace_boot_enabled = 0;
+	tr->time_start = ftrace_now(tr->cpu);
+
+	for_each_online_cpu(cpu)
+		tracing_reset(tr, cpu);
+}
+
+static int boot_trace_init(struct trace_array *tr)
+{
+	int cpu;
+	boot_trace = tr;
 
 	for_each_cpu_mask(cpu, cpu_possible_map)
 		tracing_reset(tr, cpu);
+
+	tracing_sched_switch_assign_trace(tr);
+	return 0;
 }
 
-static void boot_trace_ctrl_update(struct trace_array *tr)
+static enum print_line_t
+initcall_call_print_line(struct trace_iterator *iter)
 {
-	if (tr->ctrl)
-		start_boot_trace();
+	struct trace_entry *entry = iter->ent;
+	struct trace_seq *s = &iter->seq;
+	struct trace_boot_call *field;
+	struct boot_trace_call *call;
+	u64 ts;
+	unsigned long nsec_rem;
+	int ret;
+
+	trace_assign_type(field, entry);
+	call = &field->boot_call;
+	ts = iter->ts;
+	nsec_rem = do_div(ts, 1000000000);
+
+	ret = trace_seq_printf(s, "[%5ld.%09ld] calling  %s @ %i\n",
+			(unsigned long)ts, nsec_rem, call->func, call->caller);
+
+	if (!ret)
+		return TRACE_TYPE_PARTIAL_LINE;
 	else
-		stop_boot_trace();
+		return TRACE_TYPE_HANDLED;
 }
 
-static enum print_line_t initcall_print_line(struct trace_iterator *iter)
+static enum print_line_t
+initcall_ret_print_line(struct trace_iterator *iter)
 {
-	int ret;
 	struct trace_entry *entry = iter->ent;
-	struct trace_boot *field = (struct trace_boot *)entry;
-	struct boot_trace *it = &field->initcall;
 	struct trace_seq *s = &iter->seq;
-	struct timespec calltime = ktime_to_timespec(it->calltime);
-	struct timespec rettime = ktime_to_timespec(it->rettime);
-
-	if (entry->type == TRACE_BOOT) {
-		ret = trace_seq_printf(s, "[%5ld.%09ld] calling  %s @ %i\n",
-					  calltime.tv_sec,
-					  calltime.tv_nsec,
-					  it->func, it->caller);
-		if (!ret)
-			return TRACE_TYPE_PARTIAL_LINE;
-
-		ret = trace_seq_printf(s, "[%5ld.%09ld] initcall %s "
-					  "returned %d after %lld msecs\n",
-					  rettime.tv_sec,
-					  rettime.tv_nsec,
-					  it->func, it->result, it->duration);
-
-		if (!ret)
-			return TRACE_TYPE_PARTIAL_LINE;
+	struct trace_boot_ret *field;
+	struct boot_trace_ret *init_ret;
+	u64 ts;
+	unsigned long nsec_rem;
+	int ret;
+
+	trace_assign_type(field, entry);
+	init_ret = &field->boot_ret;
+	ts = iter->ts;
+	nsec_rem = do_div(ts, 1000000000);
+
+	ret = trace_seq_printf(s, "[%5ld.%09ld] initcall %s "
+			"returned %d after %llu msecs\n",
+			(unsigned long) ts,
+			nsec_rem,
+			init_ret->func, init_ret->result, init_ret->duration);
+
+	if (!ret)
+		return TRACE_TYPE_PARTIAL_LINE;
+	else
 		return TRACE_TYPE_HANDLED;
+}
+
+static enum print_line_t initcall_print_line(struct trace_iterator *iter)
+{
+	struct trace_entry *entry = iter->ent;
+
+	switch (entry->type) {
+	case TRACE_BOOT_CALL:
+		return initcall_call_print_line(iter);
+	case TRACE_BOOT_RET:
+		return initcall_ret_print_line(iter);
+	default:
+		return TRACE_TYPE_UNHANDLED;
 	}
-	return TRACE_TYPE_UNHANDLED;
 }
 
 struct tracer boot_tracer __read_mostly =
@@ -87,27 +131,53 @@ struct tracer boot_tracer __read_mostly =
 	.name		= "initcall",
 	.init		= boot_trace_init,
 	.reset		= reset_boot_trace,
-	.ctrl_update	= boot_trace_ctrl_update,
 	.print_line	= initcall_print_line,
 };
 
-void trace_boot(struct boot_trace *it, initcall_t fn)
+void trace_boot_call(struct boot_trace_call *bt, initcall_t fn)
 {
 	struct ring_buffer_event *event;
-	struct trace_boot *entry;
-	struct trace_array_cpu *data;
+	struct trace_boot_call *entry;
 	unsigned long irq_flags;
 	struct trace_array *tr = boot_trace;
 
-	if (!trace_boot_enabled)
+	if (!pre_initcalls_finished)
 		return;
 
 	/* Get its name now since this function could
 	 * disappear because it is in the .init section.
 	 */
-	sprint_symbol(it->func, (unsigned long)fn);
+	sprint_symbol(bt->func, (unsigned long)fn);
+	preempt_disable();
+
+	event = ring_buffer_lock_reserve(tr->buffer, sizeof(*entry),
+					 &irq_flags);
+	if (!event)
+		goto out;
+	entry	= ring_buffer_event_data(event);
+	tracing_generic_entry_update(&entry->ent, 0, 0);
+	entry->ent.type = TRACE_BOOT_CALL;
+	entry->boot_call = *bt;
+	ring_buffer_unlock_commit(tr->buffer, event, irq_flags);
+
+	trace_wake_up();
+
+ out:
+	preempt_enable();
+}
+
+void trace_boot_ret(struct boot_trace_ret *bt, initcall_t fn)
+{
+	struct ring_buffer_event *event;
+	struct trace_boot_ret *entry;
+	unsigned long irq_flags;
+	struct trace_array *tr = boot_trace;
+
+	if (!pre_initcalls_finished)
+		return;
+
+	sprint_symbol(bt->func, (unsigned long)fn);
 	preempt_disable();
-	data = tr->data[smp_processor_id()];
 
 	event = ring_buffer_lock_reserve(tr->buffer, sizeof(*entry),
 					 &irq_flags);
@@ -115,8 +185,8 @@ void trace_boot(struct boot_trace *it, initcall_t fn)
 		goto out;
 	entry	= ring_buffer_event_data(event);
 	tracing_generic_entry_update(&entry->ent, 0, 0);
-	entry->ent.type = TRACE_BOOT;
-	entry->initcall = *it;
+	entry->ent.type = TRACE_BOOT_RET;
+	entry->boot_ret = *bt;
 	ring_buffer_unlock_commit(tr->buffer, event, irq_flags);
 
 	trace_wake_up();

kernel/trace/trace_branch.c

@@ -0,0 +1,341 @@
+/*
+ * unlikely profiler
+ *
+ * Copyright (C) 2008 Steven Rostedt <srostedt@redhat.com>
+ */
+#include <linux/kallsyms.h>
+#include <linux/seq_file.h>
+#include <linux/spinlock.h>
+#include <linux/debugfs.h>
+#include <linux/uaccess.h>
+#include <linux/module.h>
+#include <linux/ftrace.h>
+#include <linux/hash.h>
+#include <linux/fs.h>
+#include <asm/local.h>
+#include "trace.h"
+
+#ifdef CONFIG_BRANCH_TRACER
+
+static int branch_tracing_enabled __read_mostly;
+static DEFINE_MUTEX(branch_tracing_mutex);
+static struct trace_array *branch_tracer;
+
+static void
+probe_likely_condition(struct ftrace_branch_data *f, int val, int expect)
+{
+	struct trace_array *tr = branch_tracer;
+	struct ring_buffer_event *event;
+	struct trace_branch *entry;
+	unsigned long flags, irq_flags;
+	int cpu, pc;
+	const char *p;
+
+	/*
+	 * I would love to save just the ftrace_likely_data pointer, but
+	 * this code can also be used by modules. Ugly things can happen
+	 * if the module is unloaded, and then we go and read the
+	 * pointer.  This is slower, but much safer.
+	 */
+
+	if (unlikely(!tr))
+		return;
+
+	raw_local_irq_save(flags);
+	cpu = raw_smp_processor_id();
+	if (atomic_inc_return(&tr->data[cpu]->disabled) != 1)
+		goto out;
+
+	event = ring_buffer_lock_reserve(tr->buffer, sizeof(*entry),
+					 &irq_flags);
+	if (!event)
+		goto out;
+
+	pc = preempt_count();
+	entry	= ring_buffer_event_data(event);
+	tracing_generic_entry_update(&entry->ent, flags, pc);
+	entry->ent.type		= TRACE_BRANCH;
+
+	/* Strip off the path, only save the file */
+	p = f->file + strlen(f->file);
+	while (p >= f->file && *p != '/')
+		p--;
+	p++;
+
+	strncpy(entry->func, f->func, TRACE_FUNC_SIZE);
+	strncpy(entry->file, p, TRACE_FILE_SIZE);
+	entry->func[TRACE_FUNC_SIZE] = 0;
+	entry->file[TRACE_FILE_SIZE] = 0;
+	entry->line = f->line;
+	entry->correct = val == expect;
+
+	ring_buffer_unlock_commit(tr->buffer, event, irq_flags);
+
+ out:
+	atomic_dec(&tr->data[cpu]->disabled);
+	raw_local_irq_restore(flags);
+}
+
+static inline
+void trace_likely_condition(struct ftrace_branch_data *f, int val, int expect)
+{
+	if (!branch_tracing_enabled)
+		return;
+
+	probe_likely_condition(f, val, expect);
+}
+
+int enable_branch_tracing(struct trace_array *tr)
+{
+	int ret = 0;
+
+	mutex_lock(&branch_tracing_mutex);
+	branch_tracer = tr;
+	/*
+	 * Must be seen before enabling. The reader is a condition
+	 * where we do not need a matching rmb()
+	 */
+	smp_wmb();
+	branch_tracing_enabled++;
+	mutex_unlock(&branch_tracing_mutex);
+
+	return ret;
+}
+
+void disable_branch_tracing(void)
+{
+	mutex_lock(&branch_tracing_mutex);
+
+	if (!branch_tracing_enabled)
+		goto out_unlock;
+
+	branch_tracing_enabled--;
+
+ out_unlock:
+	mutex_unlock(&branch_tracing_mutex);
+}
+
+static void start_branch_trace(struct trace_array *tr)
+{
+	enable_branch_tracing(tr);
+}
+
+static void stop_branch_trace(struct trace_array *tr)
+{
+	disable_branch_tracing();
+}
+
+static int branch_trace_init(struct trace_array *tr)
+{
+	int cpu;
+
+	for_each_online_cpu(cpu)
+		tracing_reset(tr, cpu);
+
+	start_branch_trace(tr);
+	return 0;
+}
+
+static void branch_trace_reset(struct trace_array *tr)
+{
+	stop_branch_trace(tr);
+}
+
+struct tracer branch_trace __read_mostly =
+{
+	.name		= "branch",
+	.init		= branch_trace_init,
+	.reset		= branch_trace_reset,
+#ifdef CONFIG_FTRACE_SELFTEST
+	.selftest	= trace_selftest_startup_branch,
+#endif
+};
+
+__init static int init_branch_trace(void)
+{
+	return register_tracer(&branch_trace);
+}
+
+device_initcall(init_branch_trace);
+#else
+static inline
+void trace_likely_condition(struct ftrace_branch_data *f, int val, int expect)
+{
+}
+#endif /* CONFIG_BRANCH_TRACER */
+
+void ftrace_likely_update(struct ftrace_branch_data *f, int val, int expect)
+{
+	/*
+	 * I would love to have a trace point here instead, but the
+	 * trace point code is so inundated with unlikely and likely
+	 * conditions that the recursive nightmare that exists is too
+	 * much to try to get working. At least for now.
+	 */
+	trace_likely_condition(f, val, expect);
+
+	/* FIXME: Make this atomic! */
+	if (val == expect)
+		f->correct++;
+	else
+		f->incorrect++;
+}
+EXPORT_SYMBOL(ftrace_likely_update);
+
+struct ftrace_pointer {
+	void		*start;
+	void		*stop;
+	int		hit;
+};
+
+static void *
+t_next(struct seq_file *m, void *v, loff_t *pos)
+{
+	const struct ftrace_pointer *f = m->private;
+	struct ftrace_branch_data *p = v;
+
+	(*pos)++;
+
+	if (v == (void *)1)
+		return f->start;
+
+	++p;
+
+	if ((void *)p >= (void *)f->stop)
+		return NULL;
+
+	return p;
+}
+
+static void *t_start(struct seq_file *m, loff_t *pos)
+{
+	void *t = (void *)1;
+	loff_t l = 0;
+
+	for (; t && l < *pos; t = t_next(m, t, &l))
+		;
+
+	return t;
+}
+
+static void t_stop(struct seq_file *m, void *p)
+{
+}
+
+static int t_show(struct seq_file *m, void *v)
+{
+	const struct ftrace_pointer *fp = m->private;
+	struct ftrace_branch_data *p = v;
+	const char *f;
+	long percent;
+
+	if (v == (void *)1) {
+		if (fp->hit)
+			seq_printf(m, "   miss      hit    %% ");
+		else
+			seq_printf(m, " correct incorrect  %% ");
+		seq_printf(m, "       Function                "
+			      "  File              Line\n"
+			      " ------- ---------  - "
+			      "       --------                "
+			      "  ----              ----\n");
+		return 0;
+	}
+
+	/* Only print the file, not the path */
+	f = p->file + strlen(p->file);
+	while (f >= p->file && *f != '/')
+		f--;
+	f++;
+
+	/*
+	 * The miss is overlayed on correct, and hit on incorrect.
+	 */
+	if (p->correct) {
+		percent = p->incorrect * 100;
+		percent /= p->correct + p->incorrect;
+	} else
+		percent = p->incorrect ? 100 : -1;
+
+	seq_printf(m, "%8lu %8lu ",  p->correct, p->incorrect);
+	if (percent < 0)
+		seq_printf(m, "  X ");
+	else
+		seq_printf(m, "%3ld ", percent);
+	seq_printf(m, "%-30.30s %-20.20s %d\n", p->func, f, p->line);
+	return 0;
+}
+
+static struct seq_operations tracing_likely_seq_ops = {
+	.start		= t_start,
+	.next		= t_next,
+	.stop		= t_stop,
+	.show		= t_show,
+};
+
+static int tracing_branch_open(struct inode *inode, struct file *file)
+{
+	int ret;
+
+	ret = seq_open(file, &tracing_likely_seq_ops);
+	if (!ret) {
+		struct seq_file *m = file->private_data;
+		m->private = (void *)inode->i_private;
+	}
+
+	return ret;
+}
+
+static const struct file_operations tracing_branch_fops = {
+	.open		= tracing_branch_open,
+	.read		= seq_read,
+	.llseek		= seq_lseek,
+};
+
+#ifdef CONFIG_PROFILE_ALL_BRANCHES
+extern unsigned long __start_branch_profile[];
+extern unsigned long __stop_branch_profile[];
+
+static const struct ftrace_pointer ftrace_branch_pos = {
+	.start			= __start_branch_profile,
+	.stop			= __stop_branch_profile,
+	.hit			= 1,
+};
+
+#endif /* CONFIG_PROFILE_ALL_BRANCHES */
+
+extern unsigned long __start_annotated_branch_profile[];
+extern unsigned long __stop_annotated_branch_profile[];
+
+static const struct ftrace_pointer ftrace_annotated_branch_pos = {
+	.start			= __start_annotated_branch_profile,
+	.stop			= __stop_annotated_branch_profile,
+};
+
+static __init int ftrace_branch_init(void)
+{
+	struct dentry *d_tracer;
+	struct dentry *entry;
+
+	d_tracer = tracing_init_dentry();
+
+	entry = debugfs_create_file("profile_annotated_branch", 0444, d_tracer,
+				    (void *)&ftrace_annotated_branch_pos,
+				    &tracing_branch_fops);
+	if (!entry)
+		pr_warning("Could not create debugfs "
+			   "'profile_annotatet_branch' entry\n");
+
+#ifdef CONFIG_PROFILE_ALL_BRANCHES
+	entry = debugfs_create_file("profile_branch", 0444, d_tracer,
+				    (void *)&ftrace_branch_pos,
+				    &tracing_branch_fops);
+	if (!entry)
+		pr_warning("Could not create debugfs"
+			   " 'profile_branch' entry\n");
+#endif
+
+	return 0;
+}
+
+device_initcall(ftrace_branch_init);

kernel/trace/trace_functions.c

@@ -42,24 +42,20 @@ static void stop_function_trace(struct trace_array *tr)
 	tracing_stop_cmdline_record();
 }
 
-static void function_trace_init(struct trace_array *tr)
+static int function_trace_init(struct trace_array *tr)
 {
-	if (tr->ctrl)
-		start_function_trace(tr);
+	start_function_trace(tr);
+	return 0;
 }
 
 static void function_trace_reset(struct trace_array *tr)
 {
-	if (tr->ctrl)
-		stop_function_trace(tr);
+	stop_function_trace(tr);
 }
 
-static void function_trace_ctrl_update(struct trace_array *tr)
+static void function_trace_start(struct trace_array *tr)
 {
-	if (tr->ctrl)
-		start_function_trace(tr);
-	else
-		stop_function_trace(tr);
+	function_reset(tr);
 }
 
 static struct tracer function_trace __read_mostly =
@@ -67,7 +63,7 @@ static struct tracer function_trace __read_mostly =
 	.name	     = "function",
 	.init	     = function_trace_init,
 	.reset	     = function_trace_reset,
-	.ctrl_update = function_trace_ctrl_update,
+	.start	     = function_trace_start,
 #ifdef CONFIG_FTRACE_SELFTEST
 	.selftest    = trace_selftest_startup_function,
 #endif

kernel/trace/trace_functions_return.c

@@ -0,0 +1,98 @@
+/*
+ *
+ * Function return tracer.
+ * Copyright (c) 2008 Frederic Weisbecker <fweisbec@gmail.com>
+ * Mostly borrowed from function tracer which
+ * is Copyright (c) Steven Rostedt <srostedt@redhat.com>
+ *
+ */
+#include <linux/debugfs.h>
+#include <linux/uaccess.h>
+#include <linux/ftrace.h>
+#include <linux/fs.h>
+
+#include "trace.h"
+
+
+#define TRACE_RETURN_PRINT_OVERRUN	0x1
+static struct tracer_opt trace_opts[] = {
+	/* Display overruns or not */
+	{ TRACER_OPT(overrun, TRACE_RETURN_PRINT_OVERRUN) },
+	{ } /* Empty entry */
+};
+
+static struct tracer_flags tracer_flags = {
+	.val = 0, /* Don't display overruns by default */
+	.opts = trace_opts
+};
+
+
+static int return_trace_init(struct trace_array *tr)
+{
+	int cpu;
+	for_each_online_cpu(cpu)
+		tracing_reset(tr, cpu);
+
+	return register_ftrace_return(&trace_function_return);
+}
+
+static void return_trace_reset(struct trace_array *tr)
+{
+		unregister_ftrace_return();
+}
+
+
+enum print_line_t
+print_return_function(struct trace_iterator *iter)
+{
+	struct trace_seq *s = &iter->seq;
+	struct trace_entry *entry = iter->ent;
+	struct ftrace_ret_entry *field;
+	int ret;
+
+	if (entry->type == TRACE_FN_RET) {
+		trace_assign_type(field, entry);
+		ret = trace_seq_printf(s, "%pF -> ", (void *)field->parent_ip);
+		if (!ret)
+			return TRACE_TYPE_PARTIAL_LINE;
+
+		ret = seq_print_ip_sym(s, field->ip,
+					trace_flags & TRACE_ITER_SYM_MASK);
+		if (!ret)
+			return TRACE_TYPE_PARTIAL_LINE;
+
+		ret = trace_seq_printf(s, " (%llu ns)",
+					field->rettime - field->calltime);
+		if (!ret)
+			return TRACE_TYPE_PARTIAL_LINE;
+
+		if (tracer_flags.val & TRACE_RETURN_PRINT_OVERRUN) {
+			ret = trace_seq_printf(s, " (Overruns: %lu)",
+						field->overrun);
+			if (!ret)
+				return TRACE_TYPE_PARTIAL_LINE;
+		}
+
+		ret = trace_seq_printf(s, "\n");
+		if (!ret)
+			return TRACE_TYPE_PARTIAL_LINE;
+
+		return TRACE_TYPE_HANDLED;
+	}
+	return TRACE_TYPE_UNHANDLED;
+}
+
+static struct tracer return_trace __read_mostly = {
+	.name	     = "return",
+	.init	     = return_trace_init,
+	.reset	     = return_trace_reset,
+	.print_line = print_return_function,
+	.flags		= &tracer_flags,
+};
+
+static __init int init_return_trace(void)
+{
+	return register_tracer(&return_trace);
+}
+
+device_initcall(init_return_trace);

kernel/trace/trace_irqsoff.c

@@ -353,15 +353,28 @@ void trace_preempt_off(unsigned long a0, unsigned long a1)
 }
 #endif /* CONFIG_PREEMPT_TRACER */
 
+/*
+ * save_tracer_enabled is used to save the state of the tracer_enabled
+ * variable when we disable it when we open a trace output file.
+ */
+static int save_tracer_enabled;
+
 static void start_irqsoff_tracer(struct trace_array *tr)
 {
 	register_ftrace_function(&trace_ops);
-	tracer_enabled = 1;
+	if (tracing_is_enabled()) {
+		tracer_enabled = 1;
+		save_tracer_enabled = 1;
+	} else {
+		tracer_enabled = 0;
+		save_tracer_enabled = 0;
+	}
 }
 
 static void stop_irqsoff_tracer(struct trace_array *tr)
 {
 	tracer_enabled = 0;
+	save_tracer_enabled = 0;
 	unregister_ftrace_function(&trace_ops);
 }
 
@@ -370,53 +383,55 @@ static void __irqsoff_tracer_init(struct trace_array *tr)
 	irqsoff_trace = tr;
 	/* make sure that the tracer is visible */
 	smp_wmb();
-
-	if (tr->ctrl)
-		start_irqsoff_tracer(tr);
+	start_irqsoff_tracer(tr);
 }
 
 static void irqsoff_tracer_reset(struct trace_array *tr)
 {
-	if (tr->ctrl)
-		stop_irqsoff_tracer(tr);
+	stop_irqsoff_tracer(tr);
 }
 
-static void irqsoff_tracer_ctrl_update(struct trace_array *tr)
+static void irqsoff_tracer_start(struct trace_array *tr)
 {
-	if (tr->ctrl)
-		start_irqsoff_tracer(tr);
-	else
-		stop_irqsoff_tracer(tr);
+	tracer_enabled = 1;
+	save_tracer_enabled = 1;
+}
+
+static void irqsoff_tracer_stop(struct trace_array *tr)
+{
+	tracer_enabled = 0;
+	save_tracer_enabled = 0;
 }
 
 static void irqsoff_tracer_open(struct trace_iterator *iter)
 {
 	/* stop the trace while dumping */
-	if (iter->tr->ctrl)
-		stop_irqsoff_tracer(iter->tr);
+	tracer_enabled = 0;
 }
 
 static void irqsoff_tracer_close(struct trace_iterator *iter)
 {
-	if (iter->tr->ctrl)
-		start_irqsoff_tracer(iter->tr);
+	/* restart tracing */
+	tracer_enabled = save_tracer_enabled;
 }
 
 #ifdef CONFIG_IRQSOFF_TRACER
-static void irqsoff_tracer_init(struct trace_array *tr)
+static int irqsoff_tracer_init(struct trace_array *tr)
 {
 	trace_type = TRACER_IRQS_OFF;
 
 	__irqsoff_tracer_init(tr);
+	return 0;
 }
 static struct tracer irqsoff_tracer __read_mostly =
 {
 	.name		= "irqsoff",
 	.init		= irqsoff_tracer_init,
 	.reset		= irqsoff_tracer_reset,
+	.start		= irqsoff_tracer_start,
+	.stop		= irqsoff_tracer_stop,
 	.open		= irqsoff_tracer_open,
 	.close		= irqsoff_tracer_close,
-	.ctrl_update	= irqsoff_tracer_ctrl_update,
 	.print_max	= 1,
 #ifdef CONFIG_FTRACE_SELFTEST
 	.selftest    = trace_selftest_startup_irqsoff,
@@ -428,11 +443,12 @@ static struct tracer irqsoff_tracer __read_mostly =
 #endif
 
 #ifdef CONFIG_PREEMPT_TRACER
-static void preemptoff_tracer_init(struct trace_array *tr)
+static int preemptoff_tracer_init(struct trace_array *tr)
 {
 	trace_type = TRACER_PREEMPT_OFF;
 
 	__irqsoff_tracer_init(tr);
+	return 0;
 }
 
 static struct tracer preemptoff_tracer __read_mostly =
@@ -440,9 +456,10 @@ static struct tracer preemptoff_tracer __read_mostly =
 	.name		= "preemptoff",
 	.init		= preemptoff_tracer_init,
 	.reset		= irqsoff_tracer_reset,
+	.start		= irqsoff_tracer_start,
+	.stop		= irqsoff_tracer_stop,
 	.open		= irqsoff_tracer_open,
 	.close		= irqsoff_tracer_close,
-	.ctrl_update	= irqsoff_tracer_ctrl_update,
 	.print_max	= 1,
 #ifdef CONFIG_FTRACE_SELFTEST
 	.selftest    = trace_selftest_startup_preemptoff,
@@ -456,11 +473,12 @@ static struct tracer preemptoff_tracer __read_mostly =
 #if defined(CONFIG_IRQSOFF_TRACER) && \
 	defined(CONFIG_PREEMPT_TRACER)
 
-static void preemptirqsoff_tracer_init(struct trace_array *tr)
+static int preemptirqsoff_tracer_init(struct trace_array *tr)
 {
 	trace_type = TRACER_IRQS_OFF | TRACER_PREEMPT_OFF;
 
 	__irqsoff_tracer_init(tr);
+	return 0;
 }
 
 static struct tracer preemptirqsoff_tracer __read_mostly =
@@ -468,9 +486,10 @@ static struct tracer preemptirqsoff_tracer __read_mostly =
 	.name		= "preemptirqsoff",
 	.init		= preemptirqsoff_tracer_init,
 	.reset		= irqsoff_tracer_reset,
+	.start		= irqsoff_tracer_start,
+	.stop		= irqsoff_tracer_stop,
 	.open		= irqsoff_tracer_open,
 	.close		= irqsoff_tracer_close,
-	.ctrl_update	= irqsoff_tracer_ctrl_update,
 	.print_max	= 1,
 #ifdef CONFIG_FTRACE_SELFTEST
 	.selftest    = trace_selftest_startup_preemptirqsoff,

kernel/trace/trace_mmiotrace.c

@@ -18,46 +18,43 @@ struct header_iter {
 
 static struct trace_array *mmio_trace_array;
 static bool overrun_detected;
+static unsigned long prev_overruns;
 
 static void mmio_reset_data(struct trace_array *tr)
 {
 	int cpu;
 
 	overrun_detected = false;
+	prev_overruns = 0;
 	tr->time_start = ftrace_now(tr->cpu);
 
 	for_each_online_cpu(cpu)
 		tracing_reset(tr, cpu);
 }
 
-static void mmio_trace_init(struct trace_array *tr)
+static int mmio_trace_init(struct trace_array *tr)
 {
 	pr_debug("in %s\n", __func__);
 	mmio_trace_array = tr;
-	if (tr->ctrl) {
-		mmio_reset_data(tr);
-		enable_mmiotrace();
-	}
+
+	mmio_reset_data(tr);
+	enable_mmiotrace();
+	return 0;
 }
 
 static void mmio_trace_reset(struct trace_array *tr)
 {
 	pr_debug("in %s\n", __func__);
-	if (tr->ctrl)
-		disable_mmiotrace();
+
+	disable_mmiotrace();
 	mmio_reset_data(tr);
 	mmio_trace_array = NULL;
 }
 
-static void mmio_trace_ctrl_update(struct trace_array *tr)
+static void mmio_trace_start(struct trace_array *tr)
 {
 	pr_debug("in %s\n", __func__);
-	if (tr->ctrl) {
-		mmio_reset_data(tr);
-		enable_mmiotrace();
-	} else {
-		disable_mmiotrace();
-	}
+	mmio_reset_data(tr);
 }
 
 static int mmio_print_pcidev(struct trace_seq *s, const struct pci_dev *dev)
@@ -128,16 +125,12 @@ static void mmio_close(struct trace_iterator *iter)
 
 static unsigned long count_overruns(struct trace_iterator *iter)
 {
-	int cpu;
 	unsigned long cnt = 0;
-/* FIXME: */
-#if 0
-	for_each_online_cpu(cpu) {
-		cnt += iter->overrun[cpu];
-		iter->overrun[cpu] = 0;
-	}
-#endif
-	(void)cpu;
+	unsigned long over = ring_buffer_overruns(iter->tr->buffer);
+
+	if (over > prev_overruns)
+		cnt = over - prev_overruns;
+	prev_overruns = over;
 	return cnt;
 }
 
@@ -298,10 +291,10 @@ static struct tracer mmio_tracer __read_mostly =
 	.name		= "mmiotrace",
 	.init		= mmio_trace_init,
 	.reset		= mmio_trace_reset,
+	.start		= mmio_trace_start,
 	.pipe_open	= mmio_pipe_open,
 	.close		= mmio_close,
 	.read		= mmio_read,
-	.ctrl_update	= mmio_trace_ctrl_update,
 	.print_line	= mmio_print_line,
 };
 

kernel/trace/trace_nop.c

@@ -12,6 +12,27 @@
 
 #include "trace.h"
 
+/* Our two options */
+enum {
+	TRACE_NOP_OPT_ACCEPT = 0x1,
+	TRACE_NOP_OPT_REFUSE = 0x2
+};
+
+/* Options for the tracer (see trace_options file) */
+static struct tracer_opt nop_opts[] = {
+	/* Option that will be accepted by set_flag callback */
+	{ TRACER_OPT(test_nop_accept, TRACE_NOP_OPT_ACCEPT) },
+	/* Option that will be refused by set_flag callback */
+	{ TRACER_OPT(test_nop_refuse, TRACE_NOP_OPT_REFUSE) },
+	{ } /* Always set a last empty entry */
+};
+
+static struct tracer_flags nop_flags = {
+	/* You can check your flags value here when you want. */
+	.val = 0, /* By default: all flags disabled */
+	.opts = nop_opts
+};
+
 static struct trace_array	*ctx_trace;
 
 static void start_nop_trace(struct trace_array *tr)
@@ -24,7 +45,7 @@ static void stop_nop_trace(struct trace_array *tr)
 	/* Nothing to do! */
 }
 
-static void nop_trace_init(struct trace_array *tr)
+static int nop_trace_init(struct trace_array *tr)
 {
 	int cpu;
 	ctx_trace = tr;
@@ -32,33 +53,53 @@ static void nop_trace_init(struct trace_array *tr)
 	for_each_online_cpu(cpu)
 		tracing_reset(tr, cpu);
 
-	if (tr->ctrl)
-		start_nop_trace(tr);
+	start_nop_trace(tr);
+	return 0;
 }
 
 static void nop_trace_reset(struct trace_array *tr)
 {
-	if (tr->ctrl)
-		stop_nop_trace(tr);
+	stop_nop_trace(tr);
 }
 
-static void nop_trace_ctrl_update(struct trace_array *tr)
+/* It only serves as a signal handler and a callback to
+ * accept or refuse tthe setting of a flag.
+ * If you don't implement it, then the flag setting will be
+ * automatically accepted.
+ */
+static int nop_set_flag(u32 old_flags, u32 bit, int set)
 {
-	/* When starting a new trace, reset the buffers */
-	if (tr->ctrl)
-		start_nop_trace(tr);
-	else
-		stop_nop_trace(tr);
+	/*
+	 * Note that you don't need to update nop_flags.val yourself.
+	 * The tracing Api will do it automatically if you return 0
+	 */
+	if (bit == TRACE_NOP_OPT_ACCEPT) {
+		printk(KERN_DEBUG "nop_test_accept flag set to %d: we accept."
+			" Now cat trace_options to see the result\n",
+			set);
+		return 0;
+	}
+
+	if (bit == TRACE_NOP_OPT_REFUSE) {
+		printk(KERN_DEBUG "nop_test_refuse flag set to %d: we refuse."
+			"Now cat trace_options to see the result\n",
+			set);
+		return -EINVAL;
+	}
+
+	return 0;
 }
 
+
 struct tracer nop_trace __read_mostly =
 {
 	.name		= "nop",
 	.init		= nop_trace_init,
 	.reset		= nop_trace_reset,
-	.ctrl_update	= nop_trace_ctrl_update,
 #ifdef CONFIG_FTRACE_SELFTEST
 	.selftest	= trace_selftest_startup_nop,
 #endif
+	.flags		= &nop_flags,
+	.set_flag	= nop_set_flag
 };
 

kernel/trace/trace_sched_switch.c

@@ -16,7 +16,8 @@
 
 static struct trace_array	*ctx_trace;
 static int __read_mostly	tracer_enabled;
-static atomic_t			sched_ref;
+static int			sched_ref;
+static DEFINE_MUTEX(sched_register_mutex);
 
 static void
 probe_sched_switch(struct rq *__rq, struct task_struct *prev,
@@ -27,7 +28,7 @@ probe_sched_switch(struct rq *__rq, struct task_struct *prev,
 	int cpu;
 	int pc;
 
-	if (!atomic_read(&sched_ref))
+	if (!sched_ref)
 		return;
 
 	tracing_record_cmdline(prev);
@@ -123,20 +124,18 @@ static void tracing_sched_unregister(void)
 
 static void tracing_start_sched_switch(void)
 {
-	long ref;
-
-	ref = atomic_inc_return(&sched_ref);
-	if (ref == 1)
+	mutex_lock(&sched_register_mutex);
+	if (!(sched_ref++))
 		tracing_sched_register();
+	mutex_unlock(&sched_register_mutex);
 }
 
 static void tracing_stop_sched_switch(void)
 {
-	long ref;
-
-	ref = atomic_dec_and_test(&sched_ref);
-	if (ref)
+	mutex_lock(&sched_register_mutex);
+	if (!(--sched_ref))
 		tracing_sched_unregister();
+	mutex_unlock(&sched_register_mutex);
 }
 
 void tracing_start_cmdline_record(void)
@@ -149,40 +148,86 @@ void tracing_stop_cmdline_record(void)
 	tracing_stop_sched_switch();
 }
 
+/**
+ * tracing_start_sched_switch_record - start tracing context switches
+ *
+ * Turns on context switch tracing for a tracer.
+ */
+void tracing_start_sched_switch_record(void)
+{
+	if (unlikely(!ctx_trace)) {
+		WARN_ON(1);
+		return;
+	}
+
+	tracing_start_sched_switch();
+
+	mutex_lock(&sched_register_mutex);
+	tracer_enabled++;
+	mutex_unlock(&sched_register_mutex);
+}
+
+/**
+ * tracing_stop_sched_switch_record - start tracing context switches
+ *
+ * Turns off context switch tracing for a tracer.
+ */
+void tracing_stop_sched_switch_record(void)
+{
+	mutex_lock(&sched_register_mutex);
+	tracer_enabled--;
+	WARN_ON(tracer_enabled < 0);
+	mutex_unlock(&sched_register_mutex);
+
+	tracing_stop_sched_switch();
+}
+
+/**
+ * tracing_sched_switch_assign_trace - assign a trace array for ctx switch
+ * @tr: trace array pointer to assign
+ *
+ * Some tracers might want to record the context switches in their
+ * trace. This function lets those tracers assign the trace array
+ * to use.
+ */
+void tracing_sched_switch_assign_trace(struct trace_array *tr)
+{
+	ctx_trace = tr;
+}
+
 static void start_sched_trace(struct trace_array *tr)
 {
 	sched_switch_reset(tr);
-	tracing_start_cmdline_record();
-	tracer_enabled = 1;
+	tracing_start_sched_switch_record();
 }
 
 static void stop_sched_trace(struct trace_array *tr)
 {
-	tracer_enabled = 0;
-	tracing_stop_cmdline_record();
+	tracing_stop_sched_switch_record();
 }
 
-static void sched_switch_trace_init(struct trace_array *tr)
+static int sched_switch_trace_init(struct trace_array *tr)
 {
 	ctx_trace = tr;
-
-	if (tr->ctrl)
-		start_sched_trace(tr);
+	start_sched_trace(tr);
+	return 0;
 }
 
 static void sched_switch_trace_reset(struct trace_array *tr)
 {
-	if (tr->ctrl)
+	if (sched_ref)
 		stop_sched_trace(tr);
 }
 
-static void sched_switch_trace_ctrl_update(struct trace_array *tr)
+static void sched_switch_trace_start(struct trace_array *tr)
 {
-	/* When starting a new trace, reset the buffers */
-	if (tr->ctrl)
-		start_sched_trace(tr);
-	else
-		stop_sched_trace(tr);
+	sched_switch_reset(tr);
+	tracing_start_sched_switch();
+}
+
+static void sched_switch_trace_stop(struct trace_array *tr)
+{
+	tracing_stop_sched_switch();
 }
 
 static struct tracer sched_switch_trace __read_mostly =
@@ -190,7 +235,8 @@ static struct tracer sched_switch_trace __read_mostly =
 	.name		= "sched_switch",
 	.init		= sched_switch_trace_init,
 	.reset		= sched_switch_trace_reset,
-	.ctrl_update	= sched_switch_trace_ctrl_update,
+	.start		= sched_switch_trace_start,
+	.stop		= sched_switch_trace_stop,
 #ifdef CONFIG_FTRACE_SELFTEST
 	.selftest    = trace_selftest_startup_sched_switch,
 #endif
@@ -198,14 +244,6 @@ static struct tracer sched_switch_trace __read_mostly =
 
 __init static int init_sched_switch_trace(void)
 {
-	int ret = 0;
-
-	if (atomic_read(&sched_ref))
-		ret = tracing_sched_register();
-	if (ret) {
-		pr_info("error registering scheduler trace\n");
-		return ret;
-	}
 	return register_tracer(&sched_switch_trace);
 }
 device_initcall(init_sched_switch_trace);

kernel/trace/trace_sched_wakeup.c

@@ -50,8 +50,7 @@ wakeup_tracer_call(unsigned long ip, unsigned long parent_ip)
 		return;
 
 	pc = preempt_count();
-	resched = need_resched();
-	preempt_disable_notrace();
+	resched = ftrace_preempt_disable();
 
 	cpu = raw_smp_processor_id();
 	data = tr->data[cpu];
@@ -81,15 +80,7 @@ wakeup_tracer_call(unsigned long ip, unsigned long parent_ip)
  out:
 	atomic_dec(&data->disabled);
 
-	/*
-	 * To prevent recursion from the scheduler, if the
-	 * resched flag was set before we entered, then
-	 * don't reschedule.
-	 */
-	if (resched)
-		preempt_enable_no_resched_notrace();
-	else
-		preempt_enable_notrace();
+	ftrace_preempt_enable(resched);
 }
 
 static struct ftrace_ops trace_ops __read_mostly =
@@ -271,6 +262,12 @@ out:
 	atomic_dec(&wakeup_trace->data[cpu]->disabled);
 }
 
+/*
+ * save_tracer_enabled is used to save the state of the tracer_enabled
+ * variable when we disable it when we open a trace output file.
+ */
+static int save_tracer_enabled;
+
 static void start_wakeup_tracer(struct trace_array *tr)
 {
 	int ret;
@@ -309,7 +306,13 @@ static void start_wakeup_tracer(struct trace_array *tr)
 
 	register_ftrace_function(&trace_ops);
 
-	tracer_enabled = 1;
+	if (tracing_is_enabled()) {
+		tracer_enabled = 1;
+		save_tracer_enabled = 1;
+	} else {
+		tracer_enabled = 0;
+		save_tracer_enabled = 0;
+	}
 
 	return;
 fail_deprobe_wake_new:
@@ -321,49 +324,53 @@ fail_deprobe:
 static void stop_wakeup_tracer(struct trace_array *tr)
 {
 	tracer_enabled = 0;
+	save_tracer_enabled = 0;
 	unregister_ftrace_function(&trace_ops);
 	unregister_trace_sched_switch(probe_wakeup_sched_switch);
 	unregister_trace_sched_wakeup_new(probe_wakeup);
 	unregister_trace_sched_wakeup(probe_wakeup);
 }
 
-static void wakeup_tracer_init(struct trace_array *tr)
+static int wakeup_tracer_init(struct trace_array *tr)
 {
 	wakeup_trace = tr;
-
-	if (tr->ctrl)
-		start_wakeup_tracer(tr);
+	start_wakeup_tracer(tr);
+	return 0;
 }
 
 static void wakeup_tracer_reset(struct trace_array *tr)
 {
-	if (tr->ctrl) {
-		stop_wakeup_tracer(tr);
-		/* make sure we put back any tasks we are tracing */
-		wakeup_reset(tr);
-	}
+	stop_wakeup_tracer(tr);
+	/* make sure we put back any tasks we are tracing */
+	wakeup_reset(tr);
+}
+
+static void wakeup_tracer_start(struct trace_array *tr)
+{
+	wakeup_reset(tr);
+	tracer_enabled = 1;
+	save_tracer_enabled = 1;
 }
 
-static void wakeup_tracer_ctrl_update(struct trace_array *tr)
+static void wakeup_tracer_stop(struct trace_array *tr)
 {
-	if (tr->ctrl)
-		start_wakeup_tracer(tr);
-	else
-		stop_wakeup_tracer(tr);
+	tracer_enabled = 0;
+	save_tracer_enabled = 0;
 }
 
 static void wakeup_tracer_open(struct trace_iterator *iter)
 {
 	/* stop the trace while dumping */
-	if (iter->tr->ctrl)
-		stop_wakeup_tracer(iter->tr);
+	tracer_enabled = 0;
 }
 
 static void wakeup_tracer_close(struct trace_iterator *iter)
 {
 	/* forget about any processes we were recording */
-	if (iter->tr->ctrl)
-		start_wakeup_tracer(iter->tr);
+	if (save_tracer_enabled) {
+		wakeup_reset(iter->tr);
+		tracer_enabled = 1;
+	}
 }
 
 static struct tracer wakeup_tracer __read_mostly =
@@ -371,9 +378,10 @@ static struct tracer wakeup_tracer __read_mostly =
 	.name		= "wakeup",
 	.init		= wakeup_tracer_init,
 	.reset		= wakeup_tracer_reset,
+	.start		= wakeup_tracer_start,
+	.stop		= wakeup_tracer_stop,
 	.open		= wakeup_tracer_open,
 	.close		= wakeup_tracer_close,
-	.ctrl_update	= wakeup_tracer_ctrl_update,
 	.print_max	= 1,
 #ifdef CONFIG_FTRACE_SELFTEST
 	.selftest    = trace_selftest_startup_wakeup,

kernel/trace/trace_selftest.c

@@ -13,6 +13,7 @@ static inline int trace_valid_entry(struct trace_entry *entry)
 	case TRACE_STACK:
 	case TRACE_PRINT:
 	case TRACE_SPECIAL:
+	case TRACE_BRANCH:
 		return 1;
 	}
 	return 0;
@@ -51,7 +52,7 @@ static int trace_test_buffer(struct trace_array *tr, unsigned long *count)
 	int cpu, ret = 0;
 
 	/* Don't allow flipping of max traces now */
-	raw_local_irq_save(flags);
+	local_irq_save(flags);
 	__raw_spin_lock(&ftrace_max_lock);
 
 	cnt = ring_buffer_entries(tr->buffer);
@@ -62,7 +63,7 @@ static int trace_test_buffer(struct trace_array *tr, unsigned long *count)
 			break;
 	}
 	__raw_spin_unlock(&ftrace_max_lock);
-	raw_local_irq_restore(flags);
+	local_irq_restore(flags);
 
 	if (count)
 		*count = cnt;
@@ -70,6 +71,11 @@ static int trace_test_buffer(struct trace_array *tr, unsigned long *count)
 	return ret;
 }
 
+static inline void warn_failed_init_tracer(struct tracer *trace, int init_ret)
+{
+	printk(KERN_WARNING "Failed to init %s tracer, init returned %d\n",
+		trace->name, init_ret);
+}
 #ifdef CONFIG_FUNCTION_TRACER
 
 #ifdef CONFIG_DYNAMIC_FTRACE
@@ -110,8 +116,11 @@ int trace_selftest_startup_dynamic_tracing(struct tracer *trace,
 	ftrace_set_filter(func_name, strlen(func_name), 1);
 
 	/* enable tracing */
-	tr->ctrl = 1;
-	trace->init(tr);
+	ret = trace->init(tr);
+	if (ret) {
+		warn_failed_init_tracer(trace, ret);
+		goto out;
+	}
 
 	/* Sleep for a 1/10 of a second */
 	msleep(100);
@@ -134,13 +143,13 @@ int trace_selftest_startup_dynamic_tracing(struct tracer *trace,
 	msleep(100);
 
 	/* stop the tracing. */
-	tr->ctrl = 0;
-	trace->ctrl_update(tr);
+	tracing_stop();
 	ftrace_enabled = 0;
 
 	/* check the trace buffer */
 	ret = trace_test_buffer(tr, &count);
 	trace->reset(tr);
+	tracing_start();
 
 	/* we should only have one item */
 	if (!ret && count != 1) {
@@ -148,6 +157,7 @@ int trace_selftest_startup_dynamic_tracing(struct tracer *trace,
 		ret = -1;
 		goto out;
 	}
+
  out:
 	ftrace_enabled = save_ftrace_enabled;
 	tracer_enabled = save_tracer_enabled;
@@ -180,18 +190,22 @@ trace_selftest_startup_function(struct tracer *trace, struct trace_array *tr)
 	ftrace_enabled = 1;
 	tracer_enabled = 1;
 
-	tr->ctrl = 1;
-	trace->init(tr);
+	ret = trace->init(tr);
+	if (ret) {
+		warn_failed_init_tracer(trace, ret);
+		goto out;
+	}
+
 	/* Sleep for a 1/10 of a second */
 	msleep(100);
 	/* stop the tracing. */
-	tr->ctrl = 0;
-	trace->ctrl_update(tr);
+	tracing_stop();
 	ftrace_enabled = 0;
 
 	/* check the trace buffer */
 	ret = trace_test_buffer(tr, &count);
 	trace->reset(tr);
+	tracing_start();
 
 	if (!ret && !count) {
 		printk(KERN_CONT ".. no entries found ..");
@@ -223,8 +237,12 @@ trace_selftest_startup_irqsoff(struct tracer *trace, struct trace_array *tr)
 	int ret;
 
 	/* start the tracing */
-	tr->ctrl = 1;
-	trace->init(tr);
+	ret = trace->init(tr);
+	if (ret) {
+		warn_failed_init_tracer(trace, ret);
+		return ret;
+	}
+
 	/* reset the max latency */
 	tracing_max_latency = 0;
 	/* disable interrupts for a bit */
@@ -232,13 +250,13 @@ trace_selftest_startup_irqsoff(struct tracer *trace, struct trace_array *tr)
 	udelay(100);
 	local_irq_enable();
 	/* stop the tracing. */
-	tr->ctrl = 0;
-	trace->ctrl_update(tr);
+	tracing_stop();
 	/* check both trace buffers */
 	ret = trace_test_buffer(tr, NULL);
 	if (!ret)
 		ret = trace_test_buffer(&max_tr, &count);
 	trace->reset(tr);
+	tracing_start();
 
 	if (!ret && !count) {
 		printk(KERN_CONT ".. no entries found ..");
@@ -259,9 +277,26 @@ trace_selftest_startup_preemptoff(struct tracer *trace, struct trace_array *tr)
 	unsigned long count;
 	int ret;
 
+	/*
+	 * Now that the big kernel lock is no longer preemptable,
+	 * and this is called with the BKL held, it will always
+	 * fail. If preemption is already disabled, simply
+	 * pass the test. When the BKL is removed, or becomes
+	 * preemptible again, we will once again test this,
+	 * so keep it in.
+	 */
+	if (preempt_count()) {
+		printk(KERN_CONT "can not test ... force ");
+		return 0;
+	}
+
 	/* start the tracing */
-	tr->ctrl = 1;
-	trace->init(tr);
+	ret = trace->init(tr);
+	if (ret) {
+		warn_failed_init_tracer(trace, ret);
+		return ret;
+	}
+
 	/* reset the max latency */
 	tracing_max_latency = 0;
 	/* disable preemption for a bit */
@@ -269,13 +304,13 @@ trace_selftest_startup_preemptoff(struct tracer *trace, struct trace_array *tr)
 	udelay(100);
 	preempt_enable();
 	/* stop the tracing. */
-	tr->ctrl = 0;
-	trace->ctrl_update(tr);
+	tracing_stop();
 	/* check both trace buffers */
 	ret = trace_test_buffer(tr, NULL);
 	if (!ret)
 		ret = trace_test_buffer(&max_tr, &count);
 	trace->reset(tr);
+	tracing_start();
 
 	if (!ret && !count) {
 		printk(KERN_CONT ".. no entries found ..");
@@ -296,9 +331,25 @@ trace_selftest_startup_preemptirqsoff(struct tracer *trace, struct trace_array *
 	unsigned long count;
 	int ret;
 
+	/*
+	 * Now that the big kernel lock is no longer preemptable,
+	 * and this is called with the BKL held, it will always
+	 * fail. If preemption is already disabled, simply
+	 * pass the test. When the BKL is removed, or becomes
+	 * preemptible again, we will once again test this,
+	 * so keep it in.
+	 */
+	if (preempt_count()) {
+		printk(KERN_CONT "can not test ... force ");
+		return 0;
+	}
+
 	/* start the tracing */
-	tr->ctrl = 1;
-	trace->init(tr);
+	ret = trace->init(tr);
+	if (ret) {
+		warn_failed_init_tracer(trace, ret);
+		goto out;
+	}
 
 	/* reset the max latency */
 	tracing_max_latency = 0;
@@ -312,27 +363,30 @@ trace_selftest_startup_preemptirqsoff(struct tracer *trace, struct trace_array *
 	local_irq_enable();
 
 	/* stop the tracing. */
-	tr->ctrl = 0;
-	trace->ctrl_update(tr);
+	tracing_stop();
 	/* check both trace buffers */
 	ret = trace_test_buffer(tr, NULL);
-	if (ret)
+	if (ret) {
+		tracing_start();
 		goto out;
+	}
 
 	ret = trace_test_buffer(&max_tr, &count);
-	if (ret)
+	if (ret) {
+		tracing_start();
 		goto out;
+	}
 
 	if (!ret && !count) {
 		printk(KERN_CONT ".. no entries found ..");
 		ret = -1;
+		tracing_start();
 		goto out;
 	}
 
 	/* do the test by disabling interrupts first this time */
 	tracing_max_latency = 0;
-	tr->ctrl = 1;
-	trace->ctrl_update(tr);
+	tracing_start();
 	preempt_disable();
 	local_irq_disable();
 	udelay(100);
@@ -341,8 +395,7 @@ trace_selftest_startup_preemptirqsoff(struct tracer *trace, struct trace_array *
 	local_irq_enable();
 
 	/* stop the tracing. */
-	tr->ctrl = 0;
-	trace->ctrl_update(tr);
+	tracing_stop();
 	/* check both trace buffers */
 	ret = trace_test_buffer(tr, NULL);
 	if (ret)
@@ -358,6 +411,7 @@ trace_selftest_startup_preemptirqsoff(struct tracer *trace, struct trace_array *
 
  out:
 	trace->reset(tr);
+	tracing_start();
 	tracing_max_latency = save_max;
 
 	return ret;
@@ -423,8 +477,12 @@ trace_selftest_startup_wakeup(struct tracer *trace, struct trace_array *tr)
 	wait_for_completion(&isrt);
 
 	/* start the tracing */
-	tr->ctrl = 1;
-	trace->init(tr);
+	ret = trace->init(tr);
+	if (ret) {
+		warn_failed_init_tracer(trace, ret);
+		return ret;
+	}
+
 	/* reset the max latency */
 	tracing_max_latency = 0;
 
@@ -448,8 +506,7 @@ trace_selftest_startup_wakeup(struct tracer *trace, struct trace_array *tr)
 	msleep(100);
 
 	/* stop the tracing. */
-	tr->ctrl = 0;
-	trace->ctrl_update(tr);
+	tracing_stop();
 	/* check both trace buffers */
 	ret = trace_test_buffer(tr, NULL);
 	if (!ret)
@@ -457,6 +514,7 @@ trace_selftest_startup_wakeup(struct tracer *trace, struct trace_array *tr)
 
 
 	trace->reset(tr);
+	tracing_start();
 
 	tracing_max_latency = save_max;
 
@@ -480,16 +538,20 @@ trace_selftest_startup_sched_switch(struct tracer *trace, struct trace_array *tr
 	int ret;
 
 	/* start the tracing */
-	tr->ctrl = 1;
-	trace->init(tr);
+	ret = trace->init(tr);
+	if (ret) {
+		warn_failed_init_tracer(trace, ret);
+		return ret;
+	}
+
 	/* Sleep for a 1/10 of a second */
 	msleep(100);
 	/* stop the tracing. */
-	tr->ctrl = 0;
-	trace->ctrl_update(tr);
+	tracing_stop();
 	/* check the trace buffer */
 	ret = trace_test_buffer(tr, &count);
 	trace->reset(tr);
+	tracing_start();
 
 	if (!ret && !count) {
 		printk(KERN_CONT ".. no entries found ..");
@@ -508,17 +570,48 @@ trace_selftest_startup_sysprof(struct tracer *trace, struct trace_array *tr)
 	int ret;
 
 	/* start the tracing */
-	tr->ctrl = 1;
-	trace->init(tr);
+	ret = trace->init(tr);
+	if (ret) {
+		warn_failed_init_tracer(trace, ret);
+		return 0;
+	}
+
 	/* Sleep for a 1/10 of a second */
 	msleep(100);
 	/* stop the tracing. */
-	tr->ctrl = 0;
-	trace->ctrl_update(tr);
+	tracing_stop();
 	/* check the trace buffer */
 	ret = trace_test_buffer(tr, &count);
 	trace->reset(tr);
+	tracing_start();
 
 	return ret;
 }
 #endif /* CONFIG_SYSPROF_TRACER */
+
+#ifdef CONFIG_BRANCH_TRACER
+int
+trace_selftest_startup_branch(struct tracer *trace, struct trace_array *tr)
+{
+	unsigned long count;
+	int ret;
+
+	/* start the tracing */
+	ret = trace->init(tr);
+	if (ret) {
+		warn_failed_init_tracer(trace, ret);
+		return ret;
+	}
+
+	/* Sleep for a 1/10 of a second */
+	msleep(100);
+	/* stop the tracing. */
+	tracing_stop();
+	/* check the trace buffer */
+	ret = trace_test_buffer(tr, &count);
+	trace->reset(tr);
+	tracing_start();
+
+	return ret;
+}
+#endif /* CONFIG_BRANCH_TRACER */

kernel/trace/trace_stack.c

@@ -107,8 +107,7 @@ stack_trace_call(unsigned long ip, unsigned long parent_ip)
 	if (unlikely(!ftrace_enabled || stack_trace_disabled))
 		return;
 
-	resched = need_resched();
-	preempt_disable_notrace();
+	resched = ftrace_preempt_disable();
 
 	cpu = raw_smp_processor_id();
 	/* no atomic needed, we only modify this variable by this cpu */
@@ -120,10 +119,7 @@ stack_trace_call(unsigned long ip, unsigned long parent_ip)
  out:
 	per_cpu(trace_active, cpu)--;
 	/* prevent recursion in schedule */
-	if (resched)
-		preempt_enable_no_resched_notrace();
-	else
-		preempt_enable_notrace();
+	ftrace_preempt_enable(resched);
 }
 
 static struct ftrace_ops trace_ops __read_mostly =
@@ -184,11 +180,16 @@ static struct file_operations stack_max_size_fops = {
 static void *
 t_next(struct seq_file *m, void *v, loff_t *pos)
 {
-	long i = (long)m->private;
+	long i;
 
 	(*pos)++;
 
-	i++;
+	if (v == SEQ_START_TOKEN)
+		i = 0;
+	else {
+		i = *(long *)v;
+		i++;
+	}
 
 	if (i >= max_stack_trace.nr_entries ||
 	    stack_dump_trace[i] == ULONG_MAX)
@@ -201,12 +202,15 @@ t_next(struct seq_file *m, void *v, loff_t *pos)
 
 static void *t_start(struct seq_file *m, loff_t *pos)
 {
-	void *t = &m->private;
+	void *t = SEQ_START_TOKEN;
 	loff_t l = 0;
 
 	local_irq_disable();
 	__raw_spin_lock(&max_stack_lock);
 
+	if (*pos == 0)
+		return SEQ_START_TOKEN;
+
 	for (; t && l < *pos; t = t_next(m, t, &l))
 		;
 
@@ -235,10 +239,10 @@ static int trace_lookup_stack(struct seq_file *m, long i)
 
 static int t_show(struct seq_file *m, void *v)
 {
-	long i = *(long *)v;
+	long i;
 	int size;
 
-	if (i < 0) {
+	if (v == SEQ_START_TOKEN) {
 		seq_printf(m, "        Depth   Size      Location"
 			   "    (%d entries)\n"
 			   "        -----   ----      --------\n",
@@ -246,6 +250,8 @@ static int t_show(struct seq_file *m, void *v)
 		return 0;
 	}
 
+	i = *(long *)v;
+
 	if (i >= max_stack_trace.nr_entries ||
 	    stack_dump_trace[i] == ULONG_MAX)
 		return 0;
@@ -275,10 +281,6 @@ static int stack_trace_open(struct inode *inode, struct file *file)
 	int ret;
 
 	ret = seq_open(file, &stack_trace_seq_ops);
-	if (!ret) {
-		struct seq_file *m = file->private_data;
-		m->private = (void *)-1;
-	}
 
 	return ret;
 }

kernel/trace/trace_sysprof.c

@@ -261,27 +261,17 @@ static void stop_stack_trace(struct trace_array *tr)
 	mutex_unlock(&sample_timer_lock);
 }
 
-static void stack_trace_init(struct trace_array *tr)
+static int stack_trace_init(struct trace_array *tr)
 {
 	sysprof_trace = tr;
 
-	if (tr->ctrl)
-		start_stack_trace(tr);
+	start_stack_trace(tr);
+	return 0;
 }
 
 static void stack_trace_reset(struct trace_array *tr)
 {
-	if (tr->ctrl)
-		stop_stack_trace(tr);
-}
-
-static void stack_trace_ctrl_update(struct trace_array *tr)
-{
-	/* When starting a new trace, reset the buffers */
-	if (tr->ctrl)
-		start_stack_trace(tr);
-	else
-		stop_stack_trace(tr);
+	stop_stack_trace(tr);
 }
 
 static struct tracer stack_trace __read_mostly =
@@ -289,7 +279,6 @@ static struct tracer stack_trace __read_mostly =
 	.name		= "sysprof",
 	.init		= stack_trace_init,
 	.reset		= stack_trace_reset,
-	.ctrl_update	= stack_trace_ctrl_update,
 #ifdef CONFIG_FTRACE_SELFTEST
 	.selftest    = trace_selftest_startup_sysprof,
 #endif