Architecture Independent Markers

Index: linux-2.6-lttng/include/linux/marker.h
===================================================================
@@ -58,8 +58,12 @@ struct marker {
  * Make sure the alignment of the structure in the __markers section will
  * not add unwanted padding between the beginning of the section and the
  * structure. Force alignment to the same alignment as the section start.
+ *
+ * The "generic" argument controls which marker enabling mechanism must be used.
+ * If generic is true, a variable read is used.
+ * If generic is false, immediate values are used.
  */
-#define __trace_mark(name, call_private, format, args...)		\
+#define __trace_mark(generic, name, call_private, format, args...)	\
 	do {								\
 		static const char __mstrtab_##name[]			\
 		__attribute__((section("__markers_strings")))		\

@@ -80,7 +84,7 @@ struct marker {
 extern void marker_update_probe_range(struct marker *begin,
 	struct marker *end);
 #else /* !CONFIG_MARKERS */
-#define __trace_mark(name, call_private, format, args...) \
+#define __trace_mark(generic, name, call_private, format, args...) \
 		__mark_check_format(format, ## args)
 static inline void marker_update_probe_range(struct marker *begin,
 	struct marker *end)

@@ -88,15 +92,30 @@ static inline void marker_update_probe_r
 #endif /* CONFIG_MARKERS */
 
 /**
- * trace_mark - Marker
+ * trace_mark - Marker using code patching
  * @name: marker name, not quoted.
  * @format: format string
  * @args...: variable argument list
  *
- * Places a marker.
+ * Places a marker using optimized code patching technique (imv_read())
+ * to be enabled when immediate values are present.
  */
 #define trace_mark(name, format, args...) \
-	__trace_mark(name, NULL, format, ## args)
+	__trace_mark(1, name, NULL, format, ## args)
+
+/**
+ * _trace_mark - Marker using variable read
+ * @name: marker name, not quoted.
+ * @format: format string
+ * @args...: variable argument list
+ *
+ * Places a marker using a standard memory read (_imv_read()) to be
+ * enabled. Should be used for markers in code paths where instruction
+ * modification based enabling is not welcome. (__init and __exit functions,
+ * lockdep, some traps, printk).
+ */
+#define _trace_mark(name, format, args...) \
+	__trace_mark(0, name, NULL, format, ## args)
 
 /**
  * MARK_NOARGS - Format string for a marker with no argument.

Index: linux-2.6-lttng/fs/buffer.c
===================================================================
@@ -41,6 +41,7 @@
 #include <linux/bitops.h>
 #include <linux/mpage.h>
 #include <linux/bit_spinlock.h>
+#include <linux/marker.h>
 
 static int fsync_buffers_list(spinlock_t *lock, struct list_head *list);
 

@@ -89,7 +90,9 @@ void unlock_buffer(struct buffer_head *b
  */
 void __wait_on_buffer(struct buffer_head * bh)
 {
+	trace_mark(fs_buffer_wait_start, "bh %p", bh);
 	wait_on_bit(&bh->b_state, BH_Lock, sync_buffer, TASK_UNINTERRUPTIBLE);
+	trace_mark(fs_buffer_wait_end, "bh %p", bh);
 }
 
 static void

Index: linux-2.6-lttng/fs/compat.c
===================================================================
@@ -50,6 +50,7 @@
 #include <linux/poll.h>
 #include <linux/mm.h>
 #include <linux/eventpoll.h>
+#include <linux/marker.h>
 
 #include <asm/uaccess.h>
 #include <asm/mmu_context.h>

@@ -1401,6 +1402,7 @@ int compat_do_execve(char * filename,
 
 	retval = search_binary_handler(bprm, regs);
 	if (retval >= 0) {
+		trace_mark(fs_exec, "filename %s", filename);
 		/* execve success */
 		security_bprm_free(bprm);
 		acct_update_integrals(current);

Index: linux-2.6-lttng/fs/ioctl.c
===================================================================
@@ -13,6 +13,7 @@
 #include <linux/security.h>
 #include <linux/module.h>
 #include <linux/uaccess.h>
+#include <linux/marker.h>
 
 #include <asm/ioctls.h>
 

@@ -201,6 +202,8 @@ asmlinkage long sys_ioctl(unsigned int f
 	if (!filp)
 		goto out;
 
+	trace_mark(fs_ioctl, "fd %u cmd %u arg %lu", fd, cmd, arg);
+
 	error = security_file_ioctl(filp, cmd, arg);
 	if (error)
 		goto out_fput;

Index: linux-2.6-lttng/fs/open.c
===================================================================
@@ -27,6 +27,7 @@
 #include <linux/rcupdate.h>
 #include <linux/audit.h>
 #include <linux/falloc.h>
+#include <linux/marker.h>
 
 int vfs_statfs(struct dentry *dentry, struct kstatfs *buf)
 {

@@ -1052,6 +1053,7 @@ long do_sys_open(int dfd, const char __u
 				fsnotify_open(f->f_path.dentry);
 				fd_install(fd, f);
 			}
+			trace_mark(fs_open, "fd %d filename %s", fd, tmp);
 		}
 		putname(tmp);
 	}

@@ -1141,6 +1143,7 @@ asmlinkage long sys_close(unsigned int f
 	filp = fdt->fd[fd];
 	if (!filp)
 		goto out_unlock;
+	trace_mark(fs_close, "fd %u", fd);
 	rcu_assign_pointer(fdt->fd[fd], NULL);
 	FD_CLR(fd, fdt->close_on_exec);
 	__put_unused_fd(files, fd);

Index: linux-2.6-lttng/fs/read_write.c
===================================================================
@@ -16,6 +16,7 @@
 #include <linux/syscalls.h>
 #include <linux/pagemap.h>
 #include <linux/splice.h>
+#include <linux/marker.h>
 #include "read_write.h"
 
 #include <asm/uaccess.h>

@@ -146,6 +147,9 @@ asmlinkage off_t sys_lseek(unsigned int 
 		if (res != (loff_t)retval)
 			retval = -EOVERFLOW;	/* LFS: should only happen on 32 bit platforms */
 	}
+
+	trace_mark(fs_lseek, "fd %u offset %ld origin %u", fd, offset, origin);
+
 	fput_light(file, fput_needed);
 bad:
 	return retval;

@@ -173,6 +177,10 @@ asmlinkage long sys_llseek(unsigned int 
 	offset = vfs_llseek(file, ((loff_t) offset_high << 32) | offset_low,
 			origin);
 
+	trace_mark(fs_llseek, "fd %u offset %llu origin %u", fd,
+			(unsigned long long)offset,
+			origin);
+
 	retval = (int)offset;
 	if (offset >= 0) {
 		retval = -EFAULT;

@@ -359,6 +367,7 @@ asmlinkage ssize_t sys_read(unsigned int
 	file = fget_light(fd, &fput_needed);
 	if (file) {
 		loff_t pos = file_pos_read(file);
+		trace_mark(fs_read, "fd %u count %zu", fd, count);
 		ret = vfs_read(file, buf, count, &pos);
 		file_pos_write(file, pos);
 		fput_light(file, fput_needed);

@@ -376,6 +385,7 @@ asmlinkage ssize_t sys_write(unsigned in
 	file = fget_light(fd, &fput_needed);
 	if (file) {
 		loff_t pos = file_pos_read(file);
+		trace_mark(fs_write, "fd %u count %zu", fd, count);
 		ret = vfs_write(file, buf, count, &pos);
 		file_pos_write(file, pos);
 		fput_light(file, fput_needed);

@@ -397,8 +407,12 @@ asmlinkage ssize_t sys_pread64(unsigned 
 	file = fget_light(fd, &fput_needed);
 	if (file) {
 		ret = -ESPIPE;
-		if (file->f_mode & FMODE_PREAD)
+		if (file->f_mode & FMODE_PREAD) {
+			trace_mark(fs_pread64, "fd %u count %zu pos %llu",
+				fd, count, (unsigned long long)pos);
 			ret = vfs_read(file, buf, count, &pos);
+		}
+
 		fput_light(file, fput_needed);
 	}
 

@@ -418,8 +432,11 @@ asmlinkage ssize_t sys_pwrite64(unsigned
 	file = fget_light(fd, &fput_needed);
 	if (file) {
 		ret = -ESPIPE;
-		if (file->f_mode & FMODE_PWRITE)  
+		if (file->f_mode & FMODE_PWRITE) {
+			trace_mark(fs_pwrite64, "fd %u count %zu pos %llu",
+				fd, count, (unsigned long long)pos);
 			ret = vfs_write(file, buf, count, &pos);
+		}
 		fput_light(file, fput_needed);
 	}
 

@@ -663,6 +680,7 @@ sys_readv(unsigned long fd, const struct
 	file = fget_light(fd, &fput_needed);
 	if (file) {
 		loff_t pos = file_pos_read(file);
+		trace_mark(fs_readv, "fd %lu vlen %lu", fd, vlen);
 		ret = vfs_readv(file, vec, vlen, &pos);
 		file_pos_write(file, pos);
 		fput_light(file, fput_needed);

@@ -684,6 +702,7 @@ sys_writev(unsigned long fd, const struc
 	file = fget_light(fd, &fput_needed);
 	if (file) {
 		loff_t pos = file_pos_read(file);
+		trace_mark(fs_writev, "fd %lu vlen %lu", fd, vlen);
 		ret = vfs_writev(file, vec, vlen, &pos);
 		file_pos_write(file, pos);
 		fput_light(file, fput_needed);

Index: linux-2.6-lttng/fs/select.c
===================================================================
@@ -23,6 +23,7 @@
 #include <linux/file.h>
 #include <linux/fs.h>
 #include <linux/rcupdate.h>
+#include <linux/marker.h>
 
 #include <asm/uaccess.h>
 

@@ -231,6 +232,9 @@ int do_select(int n, fd_set_bits *fds, s
 				file = fget_light(i, &fput_needed);
 				if (file) {
 					f_op = file->f_op;
+					trace_mark(fs_select,
+							"fd %d timeout #8d%lld",
+							i, (long long)*timeout);
 					mask = DEFAULT_POLLMASK;
 					if (f_op && f_op->poll)
 						mask = (*f_op->poll)(file, retval ? NULL : wait);

@@ -559,6 +563,7 @@ static inline unsigned int do_pollfd(str
 		file = fget_light(fd, &fput_needed);
 		mask = POLLNVAL;
 		if (file != NULL) {
+			trace_mark(fs_pollfd, "fd %d", fd);
 			mask = DEFAULT_POLLMASK;
 			if (file->f_op && file->f_op->poll)
 				mask = file->f_op->poll(file, pwait);

Index: linux-2.6-lttng/fs/exec.c
===================================================================
@@ -51,6 +51,7 @@
 #include <linux/tsacct_kern.h>
 #include <linux/cn_proc.h>
 #include <linux/audit.h>
+#include <linux/marker.h>
 
 #include <asm/uaccess.h>
 #include <asm/mmu_context.h>

@@ -1338,6 +1339,7 @@ int do_execve(char * filename,
 
 	retval = search_binary_handler(bprm,regs);
 	if (retval >= 0) {
+		trace_mark(fs_exec, "filename %s", filename);
 		/* execve success */
 		free_arg_pages(bprm);
 		security_bprm_free(bprm);

Index: linux-2.6-lttng/ipc/msg.c
===================================================================
@@ -37,6 +37,7 @@
 #include <linux/rwsem.h>
 #include <linux/nsproxy.h>
 #include <linux/ipc_namespace.h>
+#include <linux/marker.h>
 
 #include <asm/current.h>
 #include <asm/uaccess.h>

@@ -293,6 +294,7 @@ asmlinkage long sys_msgget(key_t key, in
 	struct ipc_namespace *ns;
 	struct ipc_ops msg_ops;
 	struct ipc_params msg_params;
+	long ret;
 
 	ns = current->nsproxy->ipc_ns;
 

@@ -303,7 +305,9 @@ asmlinkage long sys_msgget(key_t key, in
 	msg_params.key = key;
 	msg_params.flg = msgflg;
 
-	return ipcget(ns, &msg_ids(ns), &msg_ops, &msg_params);
+	ret = ipcget(ns, &msg_ids(ns), &msg_ops, &msg_params);
+	trace_mark(ipc_msg_create, "id %ld flags %d", ret, msgflg);
+	return ret;
 }
 
 static inline unsigned long

Index: linux-2.6-lttng/ipc/sem.c
===================================================================
@@ -83,6 +83,7 @@
 #include <linux/rwsem.h>
 #include <linux/nsproxy.h>
 #include <linux/ipc_namespace.h>
+#include <linux/marker.h>
 
 #include <asm/uaccess.h>
 #include "util.h"

@@ -312,6 +313,7 @@ asmlinkage long sys_semget(key_t key, in
 	struct ipc_namespace *ns;
 	struct ipc_ops sem_ops;
 	struct ipc_params sem_params;
+	long err;
 
 	ns = current->nsproxy->ipc_ns;
 

@@ -326,7 +328,9 @@ asmlinkage long sys_semget(key_t key, in
 	sem_params.flg = semflg;
 	sem_params.u.nsems = nsems;
 
-	return ipcget(ns, &sem_ids(ns), &sem_ops, &sem_params);
+	err = ipcget(ns, &sem_ids(ns), &sem_ops, &sem_params);
+	trace_mark(ipc_sem_create, "id %ld flags %d", err, semflg);
+	return err;
 }
 
 /* Manage the doubly linked list sma->sem_pending as a FIFO:

Index: linux-2.6-lttng/ipc/shm.c
===================================================================
@@ -39,6 +39,7 @@
 #include <linux/nsproxy.h>
 #include <linux/mount.h>
 #include <linux/ipc_namespace.h>
+#include <linux/marker.h>
 
 #include <asm/uaccess.h>
 

@@ -482,6 +483,7 @@ asmlinkage long sys_shmget (key_t key, s
 	struct ipc_namespace *ns;
 	struct ipc_ops shm_ops;
 	struct ipc_params shm_params;
+	long err;
 
 	ns = current->nsproxy->ipc_ns;
 

@@ -493,7 +495,9 @@ asmlinkage long sys_shmget (key_t key, s
 	shm_params.flg = shmflg;
 	shm_params.u.size = size;
 
-	return ipcget(ns, &shm_ids(ns), &shm_ops, &shm_params);
+	err = ipcget(ns, &shm_ids(ns), &shm_ops, &shm_params);
+	trace_mark(ipc_shm_create, "id %ld flags %d", err, shmflg);
+	return err;
 }
 
 static inline unsigned long copy_shmid_to_user(void __user *buf, struct shmid64_ds *in, int version)

Index: linux-2.6-lttng/kernel/irq/handle.c
===================================================================
@@ -15,6 +15,7 @@
 #include <linux/random.h>
 #include <linux/interrupt.h>
 #include <linux/kernel_stat.h>
+#include <linux/marker.h>
 
 #include "internals.h"
 

@@ -130,6 +131,10 @@ irqreturn_t handle_IRQ_event(unsigned in
 {
 	irqreturn_t ret, retval = IRQ_NONE;
 	unsigned int status = 0;
+	struct pt_regs *regs = get_irq_regs();
+
+	trace_mark(kernel_irq_entry, "irq_id %u kernel_mode %u", irq,
+		(regs)?(!user_mode(regs)):(1));
 
 	handle_dynamic_tick(action);
 

@@ -148,6 +153,8 @@ irqreturn_t handle_IRQ_event(unsigned in
 		add_interrupt_randomness(irq);
 	local_irq_disable();
 
+	trace_mark(kernel_irq_exit, MARK_NOARGS);
+
 	return retval;
 }
 

Index: linux-2.6-lttng/kernel/itimer.c
===================================================================
@@ -12,6 +12,7 @@
 #include <linux/time.h>
 #include <linux/posix-timers.h>
 #include <linux/hrtimer.h>
+#include <linux/marker.h>
 
 #include <asm/uaccess.h>
 

@@ -132,6 +133,9 @@ enum hrtimer_restart it_real_fn(struct h
 	struct signal_struct *sig =
 		container_of(timer, struct signal_struct, real_timer);
 
+	trace_mark(kernel_timer_itimer_expired, "pid %d",
+		pid_nr(sig->leader_pid));
+
 	kill_pid_info(SIGALRM, SEND_SIG_PRIV, sig->leader_pid);
 
 	return HRTIMER_NORESTART;

@@ -157,6 +161,15 @@ int do_setitimer(int which, struct itime
 	    !timeval_valid(&value->it_interval))
 		return -EINVAL;
 
+	trace_mark(kernel_timer_itimer_set,
+			"which %d interval_sec %ld interval_usec %ld "
+			"value_sec %ld value_usec %ld",
+			which,
+			value->it_interval.tv_sec,
+			value->it_interval.tv_usec,
+			value->it_value.tv_sec,
+			value->it_value.tv_usec);
+
 	switch (which) {
 	case ITIMER_REAL:
 again:

Index: linux-2.6-lttng/kernel/kthread.c
===================================================================
@@ -13,6 +13,7 @@
 #include <linux/file.h>
 #include <linux/module.h>
 #include <linux/mutex.h>
+#include <linux/marker.h>
 #include <asm/semaphore.h>
 
 #define KTHREAD_NICE_LEVEL (-5)

@@ -205,6 +206,8 @@ int kthread_stop(struct task_struct *k)
 	/* It could exit after stop_info.k set, but before wake_up_process. */
 	get_task_struct(k);
 
+	trace_mark(kernel_kthread_stop, "pid %d", k->pid);
+
 	/* Must init completion *before* thread sees kthread_stop_info.k */
 	init_completion(&kthread_stop_info.done);
 	smp_wmb();

@@ -220,6 +223,8 @@ int kthread_stop(struct task_struct *k)
 	ret = kthread_stop_info.err;
 	mutex_unlock(&kthread_stop_lock);
 
+	trace_mark(kernel_kthread_stop_ret, "ret %d", ret);
+
 	return ret;
 }
 EXPORT_SYMBOL(kthread_stop);

Index: linux-2.6-lttng/kernel/lockdep.c
===================================================================
@@ -39,6 +39,7 @@
 #include <linux/irqflags.h>
 #include <linux/utsname.h>
 #include <linux/hash.h>
+#include <linux/marker.h>
 
 #include <asm/sections.h>
 

@@ -2018,6 +2019,9 @@ void trace_hardirqs_on(void)
 	struct task_struct *curr = current;
 	unsigned long ip;
 
+	_trace_mark(locking_hardirqs_on, "ip #p%lu",
+		(unsigned long) __builtin_return_address(0));
+
 	if (unlikely(!debug_locks || current->lockdep_recursion))
 		return;
 

@@ -2065,6 +2069,9 @@ void trace_hardirqs_off(void)
 {
 	struct task_struct *curr = current;
 
+	_trace_mark(locking_hardirqs_off, "ip #p%lu",
+		(unsigned long) __builtin_return_address(0));
+
 	if (unlikely(!debug_locks || current->lockdep_recursion))
 		return;
 

@@ -2092,6 +2099,9 @@ void trace_softirqs_on(unsigned long ip)
 {
 	struct task_struct *curr = current;
 
+	_trace_mark(locking_softirqs_on, "ip #p%lu",
+		(unsigned long) __builtin_return_address(0));
+
 	if (unlikely(!debug_locks))
 		return;
 

@@ -2126,6 +2136,9 @@ void trace_softirqs_off(unsigned long ip
 {
 	struct task_struct *curr = current;
 
+	_trace_mark(locking_softirqs_off, "ip #p%lu",
+		(unsigned long) __builtin_return_address(0));
+
 	if (unlikely(!debug_locks))
 		return;
 

@@ -2358,6 +2371,10 @@ static int __lock_acquire(struct lockdep
 	int chain_head = 0;
 	u64 chain_key;
 
+	_trace_mark(locking_lock_acquire,
+		"ip #p%lu subclass %u lock %p trylock %d",
+		ip, subclass, lock, trylock);
+
 	if (!prove_locking)
 		check = 1;
 

@@ -2631,6 +2648,9 @@ __lock_release(struct lockdep_map *lock,
 {
 	struct task_struct *curr = current;
 
+	_trace_mark(locking_lock_release, "ip #p%lu lock %p nested %d",
+		ip, lock, nested);
+
 	if (!check_unlock(curr, lock, ip))
 		return;
 

Index: linux-2.6-lttng/kernel/printk.c
===================================================================
@@ -32,6 +32,7 @@
 #include <linux/security.h>
 #include <linux/bootmem.h>
 #include <linux/syscalls.h>
+#include <linux/marker.h>
 
 #include <asm/uaccess.h>
 

@@ -607,6 +608,7 @@ asmlinkage int printk(const char *fmt, .
 	int r;
 
 	va_start(args, fmt);
+	trace_mark(kernel_printk, "ip %p", __builtin_return_address(0));
 	r = vprintk(fmt, args);
 	va_end(args);
 

@@ -671,6 +673,31 @@ asmlinkage int vprintk(const char *fmt, 
 	raw_local_irq_save(flags);
 	this_cpu = smp_processor_id();
 
+	if (printed_len > 0) {
+		unsigned int loglevel;
+		int mark_len;
+		char *mark_buf;
+		char saved_char;
+
+		if (printk_buf[0] == '<' && printk_buf[1] >= '0' &&
+		   printk_buf[1] <= '7' && printk_buf[2] == '>') {
+			loglevel = printk_buf[1] - '0';
+			mark_buf = &printk_buf[3];
+			mark_len = printed_len - 3;
+		} else {
+			loglevel = default_message_loglevel;
+			mark_buf = printk_buf;
+			mark_len = printed_len;
+		}
+		if (mark_buf[mark_len - 1] == '\n')
+			mark_len--;
+		saved_char = mark_buf[mark_len];
+		mark_buf[mark_len] = '\0';
+		_trace_mark(kernel_vprintk, "loglevel %c string %s ip %p",
+			loglevel, mark_buf, __builtin_return_address(0));
+		mark_buf[mark_len] = saved_char;
+	}
+
 	/*
 	 * Ouch, printk recursed into itself!
 	 */

Index: linux-2.6-lttng/kernel/sched.c
===================================================================
@@ -66,6 +66,7 @@
 #include <linux/unistd.h>
 #include <linux/pagemap.h>
 #include <linux/hrtimer.h>
+#include <linux/marker.h>
 
 #include <asm/tlb.h>
 #include <asm/irq_regs.h>

@@ -1563,6 +1564,8 @@ void wait_task_inactive(struct task_stru
 		 * just go back and repeat.
 		 */
 		rq = task_rq_lock(p, &flags);
+		trace_mark(kernel_sched_wait_task, "pid %d state %ld",
+			p->pid, p->state);
 		running = task_running(rq, p);
 		on_rq = p->se.on_rq;
 		task_rq_unlock(rq, &flags);

@@ -1841,6 +1844,8 @@ static int try_to_wake_up(struct task_st
 
 	smp_wmb();
 	rq = task_rq_lock(p, &flags);
+	trace_mark(kernel_sched_try_wakeup, "pid %d state %ld",
+		p->pid, p->state);
 	old_state = p->state;
 	if (!(old_state & state))
 		goto out;

@@ -2017,6 +2022,8 @@ void wake_up_new_task(struct task_struct
 	struct rq *rq;
 
 	rq = task_rq_lock(p, &flags);
+	trace_mark(kernel_sched_wakeup_new_task, "pid %d state %ld",
+		p->pid, p->state);
 	BUG_ON(p->state != TASK_RUNNING);
 	update_rq_clock(rq);
 

@@ -2204,6 +2211,9 @@ context_switch(struct rq *rq, struct tas
 	struct mm_struct *mm, *oldmm;
 
 	prepare_task_switch(rq, prev, next);
+	trace_mark(kernel_sched_schedule,
+		"prev_pid %d next_pid %d prev_state %ld",
+		prev->pid, next->pid, prev->state);
 	mm = next->mm;
 	oldmm = prev->active_mm;
 	/*

@@ -2436,6 +2446,8 @@ static void sched_migrate_task(struct ta
 	    || unlikely(cpu_is_offline(dest_cpu)))
 		goto out;
 
+	trace_mark(kernel_sched_migrate_task, "pid %d state %ld dest_cpu %d",
+		p->pid, p->state, dest_cpu);
 	/* force the process onto the specified CPU */
 	if (migrate_task(p, dest_cpu, &req)) {
 		/* Need to wait for migration thread (might exit: take ref). */

Index: linux-2.6-lttng/kernel/signal.c
===================================================================
@@ -26,6 +26,7 @@
 #include <linux/freezer.h>
 #include <linux/pid_namespace.h>
 #include <linux/nsproxy.h>
+#include <linux/marker.h>
 
 #include <asm/param.h>
 #include <asm/uaccess.h>

@@ -663,6 +664,8 @@ static int send_signal(int sig, struct s
 	struct sigqueue * q = NULL;
 	int ret = 0;
 
+	trace_mark(kernel_send_signal, "pid %d signal %d", t->pid, sig);
+
 	/*
 	 * Deliver the signal to listening signalfds. This must be called
 	 * with the sighand lock held.

Index: linux-2.6-lttng/kernel/softirq.c
===================================================================
@@ -21,6 +21,7 @@
 #include <linux/rcupdate.h>
 #include <linux/smp.h>
 #include <linux/tick.h>
+#include <linux/marker.h>
 
 #include <asm/irq.h>
 /*

@@ -231,7 +232,15 @@ restart:
 
 	do {
 		if (pending & 1) {
+			trace_mark(kernel_softirq_entry, "softirq_id %lu",
+				((unsigned long)h
+					- (unsigned long)softirq_vec)
+					/ sizeof(*h));
 			h->action(h);
+			trace_mark(kernel_softirq_exit, "softirq_id %lu",
+				((unsigned long)h
+					- (unsigned long)softirq_vec)
+					/ sizeof(*h));
 			rcu_bh_qsctr_inc(cpu);
 		}
 		h++;

@@ -323,6 +332,8 @@ void irq_exit(void)
  */
 inline void raise_softirq_irqoff(unsigned int nr)
 {
+	trace_mark(kernel_softirq_raise, "softirq_id %u", nr);
+
 	__raise_softirq_irqoff(nr);
 
 	/*

@@ -408,7 +419,13 @@ static void tasklet_action(struct softir
 			if (!atomic_read(&t->count)) {
 				if (!test_and_clear_bit(TASKLET_STATE_SCHED, &t->state))
 					BUG();
+				trace_mark(kernel_tasklet_low_entry,
+						"func %p data %lu",
+						t->func, t->data);
 				t->func(t->data);
+				trace_mark(kernel_tasklet_low_exit,
+						"func %p data %lu",
+						t->func, t->data);
 				tasklet_unlock(t);
 				continue;
 			}

@@ -441,7 +458,13 @@ static void tasklet_hi_action(struct sof
 			if (!atomic_read(&t->count)) {
 				if (!test_and_clear_bit(TASKLET_STATE_SCHED, &t->state))
 					BUG();
+				trace_mark(kernel_tasklet_high_entry,
+						"func %p data %lu",
+						t->func, t->data);
 				t->func(t->data);
+				trace_mark(kernel_tasklet_high_exit,
+						"func %p data %lu",
+						t->func, t->data);
 				tasklet_unlock(t);
 				continue;
 			}

Index: linux-2.6-lttng/kernel/timer.c
===================================================================
@@ -37,12 +37,14 @@
 #include <linux/delay.h>
 #include <linux/tick.h>
 #include <linux/kallsyms.h>
+#include <linux/marker.h>
 
 #include <asm/uaccess.h>
 #include <asm/unistd.h>
 #include <asm/div64.h>
 #include <asm/timex.h>
 #include <asm/io.h>
+#include <asm/irq_regs.h>
 
 u64 jiffies_64 __cacheline_aligned_in_smp = INITIAL_JIFFIES;
 

@@ -288,6 +290,8 @@ static void internal_add_timer(struct tv
 		i = (expires >> (TVR_BITS + 3 * TVN_BITS)) & TVN_MASK;
 		vec = base->tv5.vec + i;
 	}
+	trace_mark(kernel_timer_set, "expires %lu function %p data %lu",
+		expires, timer->function, timer->data);
 	/*
 	 * Timers are FIFO:
 	 */

@@ -940,6 +944,11 @@ void do_timer(unsigned long ticks)
 {
 	jiffies_64 += ticks;
 	update_times(ticks);
+	trace_mark(kernel_timer_update_time,
+		"jiffies #8u%llu xtime_sec %ld xtime_nsec %ld "
+		"walltomonotonic_sec %ld walltomonotonic_nsec %ld",
+		(unsigned long long)jiffies_64, xtime.tv_sec, xtime.tv_nsec,
+		wall_to_monotonic.tv_sec, wall_to_monotonic.tv_nsec);
 }
 
 #ifdef __ARCH_WANT_SYS_ALARM

@@ -1021,7 +1030,9 @@ asmlinkage long sys_getegid(void)
 
 static void process_timeout(unsigned long __data)
 {
-	wake_up_process((struct task_struct *)__data);
+	struct task_struct *task = (struct task_struct *)__data;
+	trace_mark(kernel_timer_timeout, "pid %d", task->pid);
+	wake_up_process(task);
 }
 
 /**

Index: linux-2.6-lttng/kernel/exit.c
===================================================================
@@ -44,6 +44,7 @@
 #include <linux/resource.h>
 #include <linux/blkdev.h>
 #include <linux/task_io_accounting_ops.h>
+#include <linux/marker.h>
 
 #include <asm/uaccess.h>
 #include <asm/unistd.h>

@@ -137,6 +138,8 @@ static void __exit_signal(struct task_st
 
 static void delayed_put_task_struct(struct rcu_head *rhp)
 {
+	trace_mark(kernel_process_free, "pid %d",
+		container_of(rhp, struct task_struct, rcu)->pid);
 	put_task_struct(container_of(rhp, struct task_struct, rcu));
 }
 

@@ -966,6 +969,8 @@ NORET_TYPE void do_exit(long code)
 
 	if (group_dead)
 		acct_process();
+	trace_mark(kernel_process_exit, "pid %d", tsk->pid);
+
 	exit_sem(tsk);
 	__exit_files(tsk);
 	__exit_fs(tsk);

@@ -1450,6 +1455,8 @@ static long do_wait(enum pid_type type, 
 	struct task_struct *tsk;
 	int flag, retval;
 
+	trace_mark(kernel_process_wait, "pid %d", pid_nr(pid));
+
 	add_wait_queue(&current->signal->wait_chldexit,&wait);
 repeat:
 	/* If there is nothing that can match our critier just get out */

Index: linux-2.6-lttng/kernel/fork.c
===================================================================
@@ -53,6 +53,7 @@
 #include <linux/tty.h>
 #include <linux/proc_fs.h>
 #include <linux/blkdev.h>
+#include <linux/marker.h>
 
 #include <asm/pgtable.h>
 #include <asm/pgalloc.h>

@@ -1488,6 +1489,10 @@ long do_fork(unsigned long clone_flags,
 	if (!IS_ERR(p)) {
 		struct completion vfork;
 
+		trace_mark(kernel_process_fork,
+			"parent_pid %d child_pid %d child_tgid %d",
+			current->pid, p->pid, p->tgid);
+
 		nr = task_pid_vnr(p);
 
 		if (clone_flags & CLONE_PARENT_SETTID)

Index: linux-2.6-lttng/kernel/module.c
===================================================================
@@ -47,6 +47,7 @@
 #include <asm/cacheflush.h>
 #include <linux/license.h>
 #include <asm/sections.h>
+#include <linux/marker.h>
 
 #if 0
 #define DEBUGP printk

@@ -1332,6 +1333,8 @@ static int __unlink_module(void *_mod)
 /* Free a module, remove from lists, etc (must hold module_mutex). */
 static void free_module(struct module *mod)
 {
+	trace_mark(kernel_module_free, "name %s", mod->name);
+
 	/* Delete from various lists */
 	stop_machine_run(__unlink_module, mod, NR_CPUS);
 	remove_notes_attrs(mod);

@@ -2104,6 +2107,8 @@ static struct module *load_module(void _
 	/* Get rid of temporary copy */
 	vfree(hdr);
 
+	trace_mark(kernel_module_load, "name %s", mod->name);
+
 	/* Done! */
 	return mod;
 

Index: linux-2.6-lttng/mm/filemap.c
===================================================================
@@ -33,6 +33,7 @@
 #include <linux/cpuset.h>
 #include <linux/hardirq.h> /* for BUG_ON(!in_atomic()) only */
 #include <linux/memcontrol.h>
+#include <linux/marker.h>
 #include "internal.h"
 
 /*

@@ -540,9 +541,15 @@ void wait_on_page_bit(struct page *page,
 {
 	DEFINE_WAIT_BIT(wait, &page->flags, bit_nr);
 
+	trace_mark(mm_filemap_wait_start, "pfn %lu bit_nr %d",
+		page_to_pfn(page), bit_nr);
+
 	if (test_bit(bit_nr, &page->flags))
 		__wait_on_bit(page_waitqueue(page), &wait, sync_page,
 							TASK_UNINTERRUPTIBLE);
+
+	trace_mark(mm_filemap_wait_end, "pfn %lu bit_nr %d",
+		page_to_pfn(page), bit_nr);
 }
 EXPORT_SYMBOL(wait_on_page_bit);
 

Index: linux-2.6-lttng/mm/memory.c
===================================================================
@@ -45,6 +45,7 @@
 #include <linux/swap.h>
 #include <linux/highmem.h>
 #include <linux/pagemap.h>
+#include <linux/marker.h>
 #include <linux/rmap.h>
 #include <linux/module.h>
 #include <linux/delayacct.h>

@@ -2050,6 +2051,10 @@ static int do_swap_page(struct mm_struct
 		/* Had to read the page from swap area: Major fault */
 		ret = VM_FAULT_MAJOR;
 		count_vm_event(PGMAJFAULT);
+		trace_mark(mm_swap_in, "pfn %lu filp %p offset %lu",
+			page_to_pfn(page),
+			get_swap_info_struct(swp_type(entry))->swap_file,
+			swp_offset(entry));
 	}
 
 	if (mem_cgroup_charge(page, mm, GFP_KERNEL)) {

@@ -2509,30 +2514,46 @@ unlock:
 int handle_mm_fault(struct mm_struct *mm, struct vm_area_struct *vma,
 		unsigned long address, int write_access)
 {
+	int res;
 	pgd_t *pgd;
 	pud_t *pud;
 	pmd_t *pmd;
 	pte_t *pte;
 
+	trace_mark(mm_handle_fault_entry,
+		"address %lu ip #p%ld write_access %d",
+		address, KSTK_EIP(current), write_access);
+
 	__set_current_state(TASK_RUNNING);
 
 	count_vm_event(PGFAULT);
 
-	if (unlikely(is_vm_hugetlb_page(vma)))
-		return hugetlb_fault(mm, vma, address, write_access);
+	if (unlikely(is_vm_hugetlb_page(vma))) {
+		res = hugetlb_fault(mm, vma, address, write_access);
+		goto end;
+	}
 
 	pgd = pgd_offset(mm, address);
 	pud = pud_alloc(mm, pgd, address);
-	if (!pud)
-		return VM_FAULT_OOM;
+	if (!pud) {
+		res = VM_FAULT_OOM;
+		goto end;
+	}
 	pmd = pmd_alloc(mm, pud, address);
-	if (!pmd)
-		return VM_FAULT_OOM;
+	if (!pmd) {
+		res = VM_FAULT_OOM;
+		goto end;
+	}
 	pte = pte_alloc_map(mm, pmd, address);
-	if (!pte)
-		return VM_FAULT_OOM;
+	if (!pte) {
+		res = VM_FAULT_OOM;
+		goto end;
+	}
 
-	return handle_pte_fault(mm, vma, address, pte, pmd, write_access);
+	res = handle_pte_fault(mm, vma, address, pte, pmd, write_access);
+end:
+	trace_mark(mm_handle_fault_exit, MARK_NOARGS);
+	return res;
 }
 
 #ifndef __PAGETABLE_PUD_FOLDED

Index: linux-2.6-lttng/mm/page_alloc.c
===================================================================
@@ -45,6 +45,7 @@
 #include <linux/fault-inject.h>
 #include <linux/page-isolation.h>
 #include <linux/memcontrol.h>
+#include <linux/marker.h>
 
 #include <asm/tlbflush.h>
 #include <asm/div64.h>

@@ -527,6 +528,9 @@ static void __free_pages_ok(struct page 
 	int i;
 	int reserved = 0;
 
+	trace_mark(mm_page_free, "order %u pfn %lu",
+		order, page_to_pfn(page));
+
 	for (i = 0 ; i < (1 << order) ; ++i)
 		reserved += free_pages_check(page + i);
 	if (reserved)

@@ -990,6 +994,8 @@ static void free_hot_cold_page(struct pa
 	struct per_cpu_pages *pcp;
 	unsigned long flags;
 
+	trace_mark(mm_page_free, "order %u pfn %lu", 0, page_to_pfn(page));
+
 	if (PageAnon(page))
 		page->mapping = NULL;
 	if (free_pages_check(page))

@@ -1643,6 +1649,9 @@ nopage:
 		show_mem();
 	}
 got_pg:
+	if (page)
+		trace_mark(mm_page_alloc, "order %u pfn %lu", order,
+			   page_to_pfn(page));
 	return page;
 }
 

Index: linux-2.6-lttng/mm/page_io.c
===================================================================
@@ -17,6 +17,7 @@
 #include <linux/bio.h>
 #include <linux/swapops.h>
 #include <linux/writeback.h>
+#include <linux/marker.h>
 #include <asm/pgtable.h>
 
 static struct bio *get_swap_bio(gfp_t gfp_flags, pgoff_t index,

@@ -114,6 +115,11 @@ int swap_writepage(struct page *page, st
 		rw |= (1 << BIO_RW_SYNC);
 	count_vm_event(PSWPOUT);
 	set_page_writeback(page);
+	trace_mark(mm_swap_out, "pfn %lu filp %p offset %lu",
+			page_to_pfn(page),
+			get_swap_info_struct(swp_type(
+				page_swp_entry(page)))->swap_file,
+			swp_offset(page_swp_entry(page)));
 	unlock_page(page);
 	submit_bio(rw, bio);
 out:

Index: linux-2.6-lttng/mm/hugetlb.c
===================================================================
@@ -14,6 +14,7 @@
 #include <linux/mempolicy.h>
 #include <linux/cpuset.h>
 #include <linux/mutex.h>
+#include <linux/marker.h>
 
 #include <asm/page.h>
 #include <asm/pgtable.h>

@@ -137,6 +138,7 @@ static void free_huge_page(struct page *
 	int nid = page_to_nid(page);
 	struct address_space *mapping;
 
+	trace_mark(mm_huge_page_free, "pfn %lu", page_to_pfn(page));
 	mapping = (struct address_space *) page_private(page);
 	set_page_private(page, 0);
 	BUG_ON(page_count(page));

@@ -485,6 +487,7 @@ static struct page *alloc_huge_page(stru
 	if (!IS_ERR(page)) {
 		set_page_refcounted(page);
 		set_page_private(page, (unsigned long) mapping);
+		trace_mark(mm_huge_page_alloc, "pfn %lu", page_to_pfn(page));
 	}
 	return page;
 }

Index: linux-2.6-lttng/include/linux/swapops.h
===================================================================
@@ -76,6 +76,14 @@ static inline pte_t swp_entry_to_pte(swp
 	return __swp_entry_to_pte(arch_entry);
 }
 
+static inline swp_entry_t page_swp_entry(struct page *page)
+{
+	swp_entry_t entry;
+	VM_BUG_ON(!PageSwapCache(page));
+	entry.val = page_private(page);
+	return entry;
+}
+
 #ifdef CONFIG_MIGRATION
 static inline swp_entry_t make_migration_entry(struct page *page, int write)
 {

Index: linux-2.6-lttng/mm/swapfile.c
===================================================================
@@ -28,6 +28,7 @@
 #include <linux/capability.h>
 #include <linux/syscalls.h>
 #include <linux/memcontrol.h>
+#include <linux/marker.h>
 
 #include <asm/pgtable.h>
 #include <asm/tlbflush.h>

@@ -1310,6 +1311,7 @@ asmlinkage long sys_swapoff(const char _
 	swap_map = p->swap_map;
 	p->swap_map = NULL;
 	p->flags = 0;
+	trace_mark(mm_swap_file_close, "filp %p", swap_file);
 	spin_unlock(&swap_lock);
 	mutex_unlock(&swapon_mutex);
 	vfree(swap_map);

@@ -1691,6 +1693,8 @@ asmlinkage long sys_swapon(const char __
 	} else {
 		swap_info[prev].next = p - swap_info;
 	}
+	trace_mark(mm_swap_file_open, "filp %p filename %s",
+		swap_file, name);
 	spin_unlock(&swap_lock);
 	mutex_unlock(&swapon_mutex);
 	error = 0;

@@ -1844,3 +1848,22 @@ int valid_swaphandles(swp_entry_t entry,
 	*offset = ++toff;
 	return nr_pages? ++nr_pages: 0;
 }
+
+void ltt_dump_swap_files(void *call_data)
+{
+	int type;
+	struct swap_info_struct *p = NULL;
+
+	mutex_lock(&swapon_mutex);
+	for (type = swap_list.head; type >= 0; type = swap_info[type].next) {
+		p = swap_info + type;
+		if ((p->flags & SWP_ACTIVE) != SWP_ACTIVE)
+			continue;
+		__trace_mark(0, statedump_swap_files, call_data,
+			"filp %p vfsmount %p dname %s",
+			p->swap_file, p->swap_file->f_vfsmnt,
+			p->swap_file->f_dentry->d_name.name);
+	}
+	mutex_unlock(&swapon_mutex);
+}
+EXPORT_SYMBOL_GPL(ltt_dump_swap_files);

Index: linux-2.6-lttng/net/core/dev.c
===================================================================
@@ -119,6 +119,7 @@
 #include <linux/err.h>
 #include <linux/ctype.h>
 #include <linux/if_arp.h>
+#include <linux/marker.h>
 
 #include "net-sysfs.h"
 

@@ -1643,6 +1644,8 @@ int dev_queue_xmit(struct sk_buff *skb)
 	}
 
 gso:
+	trace_mark(net_dev_xmit, "skb %p protocol #2u%hu", skb, skb->protocol);
+
 	spin_lock_prefetch(&dev->queue_lock);
 
 	/* Disable soft irqs for various locks below. Also

@@ -2043,6 +2046,9 @@ int netif_receive_skb(struct sk_buff *sk
 
 	__get_cpu_var(netdev_rx_stat).total++;
 
+	trace_mark(net_dev_receive, "skb %p protocol #2u%hu",
+		skb, skb->protocol);
+
 	skb_reset_network_header(skb);
 	skb_reset_transport_header(skb);
 	skb->mac_len = skb->network_header - skb->mac_header;

Index: linux-2.6-lttng/net/ipv4/devinet.c
===================================================================
@@ -56,6 +56,7 @@
 #include <linux/sysctl.h>
 #endif
 #include <linux/kmod.h>
+#include <linux/marker.h>
 
 #include <net/arp.h>
 #include <net/ip.h>

@@ -258,6 +259,8 @@ static void __inet_del_ifa(struct in_dev
 		struct in_ifaddr **ifap1 = &ifa1->ifa_next;
 
 		while ((ifa = *ifap1) != NULL) {
+			trace_mark(net_del_ifa_ipv4, "label %s",
+				ifa->ifa_label);
 			if (!(ifa->ifa_flags & IFA_F_SECONDARY) &&
 			    ifa1->ifa_scope <= ifa->ifa_scope)
 				last_prim = ifa;

@@ -364,6 +367,9 @@ static int __inet_insert_ifa(struct in_i
 			}
 			ifa->ifa_flags |= IFA_F_SECONDARY;
 		}
+		trace_mark(net_insert_ifa_ipv4, "label %s address #4u%lu",
+			ifa->ifa_label,
+			(unsigned long)ifa->ifa_address);
 	}
 
 	if (!(ifa->ifa_flags & IFA_F_SECONDARY)) {

Index: linux-2.6-lttng/net/socket.c
===================================================================
@@ -85,6 +85,7 @@
 #include <linux/audit.h>
 #include <linux/wireless.h>
 #include <linux/nsproxy.h>
+#include <linux/marker.h>
 
 #include <asm/uaccess.h>
 #include <asm/unistd.h>

@@ -567,6 +568,11 @@ int sock_sendmsg(struct socket *sock, st
 	struct sock_iocb siocb;
 	int ret;
 
+	trace_mark(net_socket_sendmsg,
+		"sock %p family %d type %d protocol %d size %zu",
+		sock, sock->sk->sk_family, sock->sk->sk_type,
+		sock->sk->sk_protocol, size);
+
 	init_sync_kiocb(&iocb, NULL);
 	iocb.private = &siocb;
 	ret = __sock_sendmsg(&iocb, sock, msg, size);

@@ -650,7 +656,13 @@ int sock_recvmsg(struct socket *sock, st
 	struct sock_iocb siocb;
 	int ret;
 
+	trace_mark(net_socket_recvmsg,
+		"sock %p family %d type %d protocol %d size %zu",
+		sock, sock->sk->sk_family, sock->sk->sk_type,
+		sock->sk->sk_protocol, size);
+
 	init_sync_kiocb(&iocb, NULL);
+
 	iocb.private = &siocb;
 	ret = __sock_recvmsg(&iocb, sock, msg, size, flags);
 	if (-EIOCBQUEUED == ret)

@@ -1226,6 +1238,11 @@ asmlinkage long sys_socket(int family, i
 	if (retval < 0)
 		goto out_release;
 
+	trace_mark(net_socket_create,
+		"sock %p family %d type %d protocol %d fd %d",
+		sock, sock->sk->sk_family, sock->sk->sk_type,
+		sock->sk->sk_protocol, retval);
+
 out:
 	/* It may be already another descriptor 8) Not kernel problem. */
 	return retval;

@@ -2024,6 +2041,8 @@ asmlinkage long sys_socketcall(int call,
 	a0 = a[0];
 	a1 = a[1];
 
+	trace_mark(net_socket_call, "call %d a0 %lu", call, a0);
+
 	switch (call) {
 	case SYS_SOCKET:
 		err = sys_socket(a0, a1, a[2]);

Index: linux-2.6-lttng/lib/semaphore-sleepers.c
===================================================================
@@ -15,6 +15,7 @@
 #include <linux/sched.h>
 #include <linux/err.h>
 #include <linux/init.h>
+#include <linux/marker.h>
 #include <asm/semaphore.h>
 
 /*

@@ -50,6 +51,7 @@
 
 void __up(struct semaphore *sem)
 {
+	trace_mark(sem_up, "%p", sem);
 	wake_up(&sem->wait);
 }
 

@@ -59,6 +61,7 @@ void __sched __down(struct semaphore *se
 	DECLARE_WAITQUEUE(wait, tsk);
 	unsigned long flags;
 
+	trace_mark(sem_down, "%p", sem);
 	tsk->state = TASK_UNINTERRUPTIBLE;
 	spin_lock_irqsave(&sem->wait.lock, flags);
 	add_wait_queue_exclusive_locked(&sem->wait, &wait);

@@ -73,12 +76,14 @@ void __sched __down(struct semaphore *se
 		 * the wait_queue_head.
 		 */
 		if (!atomic_add_negative(sleepers - 1, &sem->count)) {
+			trace_mark(sem_down_resume, "%p", sem);
 			sem->sleepers = 0;
 			break;
 		}
 		sem->sleepers = 1;	/* us - see -1 above */
 		spin_unlock_irqrestore(&sem->wait.lock, flags);
 
+		trace_mark(sem_down_sched, "%p", sem);
 		schedule();
 
 		spin_lock_irqsave(&sem->wait.lock, flags);

@@ -97,6 +102,7 @@ int __sched __down_interruptible(struct 
 	DECLARE_WAITQUEUE(wait, tsk);
 	unsigned long flags;
 
+	trace_mark(sem_down_intr, "%p", sem);
 	tsk->state = TASK_INTERRUPTIBLE;
 	spin_lock_irqsave(&sem->wait.lock, flags);
 	add_wait_queue_exclusive_locked(&sem->wait, &wait);

@@ -113,6 +119,7 @@ int __sched __down_interruptible(struct 
 		 * and exit.
 		 */
 		if (signal_pending(current)) {
+			trace_mark(sem_down_intr_fail, "%p", sem);
 			retval = -EINTR;
 			sem->sleepers = 0;
 			atomic_add(sleepers, &sem->count);

@@ -126,12 +133,14 @@ int __sched __down_interruptible(struct 
 		 * still hoping to get the semaphore.
 		 */
 		if (!atomic_add_negative(sleepers - 1, &sem->count)) {
+			trace_mark(sem_down_intr_resume, "%p", sem);
 			sem->sleepers = 0;
 			break;
 		}
 		sem->sleepers = 1;	/* us - see -1 above */
 		spin_unlock_irqrestore(&sem->wait.lock, flags);
 
+		trace_mark(sem_down_intr_sched, "%p", sem);
 		schedule();
 
 		spin_lock_irqsave(&sem->wait.lock, flags);

Index: linux/include/linux/sched.h
===================================================================
@@ -2031,42 +2031,6 @@ extern int sched_mc_power_savings, sched
 
 extern void normalize_rt_tasks(void);
 
-#ifdef CONFIG_CONTEXT_SWITCH_TRACER
-extern void
-ftrace_ctx_switch(struct task_struct *prev, struct task_struct *next);
-#else
-static inline void
-ftrace_ctx_switch(struct task_struct *prev, struct task_struct *next)
-{
-}
-#endif
-
-#ifdef CONFIG_SCHED_TRACER
-extern void
-ftrace_wake_up_task(struct task_struct *wakee, struct task_struct *curr);
-extern void
-ftrace_wake_up_new_task(struct task_struct *wakee, struct task_struct *curr);
-#else
-static inline void
-ftrace_wake_up_task(struct task_struct *wakee, struct task_struct *curr)
-{
-}
-static inline void
-ftrace_wake_up_new_task(struct task_struct *wakee, struct task_struct *curr)
-{
-}
-#endif
-
-#ifdef CONFIG_CONTEXT_SWITCH_TRACER
-extern void
-ftrace_ctx_switch(struct task_struct *prev, struct task_struct *next);
-#else
-static inline void
-ftrace_ctx_switch(struct task_struct *prev, struct task_struct *next)
-{
-}
-#endif
-
 #ifdef CONFIG_FAIR_GROUP_SCHED
 
 extern struct task_group init_task_group;

Index: linux/kernel/sched.c
===================================================================
@@ -1886,7 +1886,9 @@ static int try_to_wake_up(struct task_st
 
 out_activate:
 #endif /* CONFIG_SMP */
-	ftrace_wake_up_task(p, rq->curr);
+	trace_mark(kernel_sched_wakeup,
+		   "p %p rq->curr %p",
+		   p, rq->curr);
 
 	schedstat_inc(p, se.nr_wakeups);
 	if (sync)

@@ -2028,7 +2030,9 @@ void fastcall wake_up_new_task(struct ta
 		p->sched_class->task_new(rq, p);
 		inc_nr_running(rq);
 	}
-	ftrace_wake_up_new_task(p, rq->curr);
+	trace_mark(kernel_sched_wakeup_new,
+		   "p %p rq->curr %p",
+		   p, rq->curr);
 
 	check_preempt_curr(rq, p);
 #ifdef CONFIG_SMP

@@ -2202,7 +2206,8 @@ context_switch(struct rq *rq, struct tas
 	struct mm_struct *mm, *oldmm;
 
 	prepare_task_switch(rq, prev, next);
-	ftrace_ctx_switch(prev, next);
+	trace_mark(kernel_sched_schedule,
+		   "prev %p next %p", prev, next);
 	mm = next->mm;
 	oldmm = prev->active_mm;
 	/*

Index: linux/kernel/trace/trace.h
===================================================================
@@ -134,6 +134,8 @@ void tracing_start_function_trace(void);
 void tracing_stop_function_trace(void);
 int register_tracer(struct tracer *type);
 void unregister_tracer(struct tracer *type);
+void tracing_start_sched_switch(void);
+void tracing_stop_sched_switch(void);
 
 extern int tracing_sched_switch_enabled;
 extern unsigned long tracing_max_latency;

@@ -148,16 +150,6 @@ static inline notrace cycle_t now(int cp
 	return cpu_clock(cpu);
 }
 
-#ifdef CONFIG_SCHED_TRACER
-extern void notrace
-wakeup_sched_switch(struct task_struct *prev, struct task_struct *next);
-#else
-static inline void
-wakeup_sched_switch(struct task_struct *prev, struct task_struct *next)
-{
-}
-#endif
-
 #ifdef CONFIG_CONTEXT_SWITCH_TRACER
 typedef void
 (*tracer_switch_func_t)(void *private,

Index: linux/kernel/trace/trace_functions.c
===================================================================
@@ -30,10 +30,12 @@ static notrace void start_function_trace
 {
 	function_reset(tr);
 	tracing_start_function_trace();
+	tracing_start_sched_switch();
 }
 
 static notrace void stop_function_trace(struct trace_array *tr)
 {
+	tracing_stop_sched_switch();
 	tracing_stop_function_trace();
 }
 

210 lines not on this page · raw message

198 lines not on this page · raw message

Index: linux/kernel/sched.c
===================================================================
@@ -2005,53 +2005,6 @@ static int sched_balance_self(int cpu, i
 
 #endif /* CONFIG_SMP */
 
-#ifdef CONFIG_CONTEXT_SWITCH_TRACER
-
-void ftrace_task(struct task_struct *p, void *__tr, void *__data)
-{
-#if 0
-	/*  
-	 * trace timeline tree
-	 */
-	__trace_special(__tr, __data,
-			p->pid, p->se.vruntime, p->se.sum_exec_runtime);
-#else
-	/*
-	 * trace balance metrics
-	 */
-	__trace_special(__tr, __data,
-			p->pid, p->se.avg_overlap, 0);
-#endif
-}
-
-void ftrace_all_fair_tasks(void *__rq, void *__tr, void *__data)
-{
-	struct task_struct *p;
-	struct sched_entity *se;
-	struct rb_node *curr;
-	struct rq *rq = __rq;
-
-	if (rq->cfs.curr) {
-		p = task_of(rq->cfs.curr);
-		ftrace_task(p, __tr, __data);
-	}
-	if (rq->cfs.next) {
-		p = task_of(rq->cfs.next);
-		ftrace_task(p, __tr, __data);
-	}
-
-	for (curr = first_fair(&rq->cfs); curr; curr = rb_next(curr)) {
-		se = rb_entry(curr, struct sched_entity, run_node);
-		if (!entity_is_task(se))
-			continue;
-
-		p = task_of(se);
-		ftrace_task(p, __tr, __data);
-	}
-}
-
-#endif
-
 /***
  * try_to_wake_up - wake up a thread
  * @p: the to-be-woken-up thread

Index: linux/kernel/sched_fair.c
===================================================================
@@ -991,8 +991,6 @@ wake_affine(struct rq *rq, struct sched_
 	if (!(this_sd->flags & SD_WAKE_AFFINE))
 		return 0;
 
-	ftrace_special(__LINE__, curr->se.avg_overlap, sync);
-	ftrace_special(__LINE__, p->se.avg_overlap, -1);
 	/*
 	 * If the currently running task will sleep within
 	 * a reasonable amount of time then attract this newly

@@ -1118,7 +1116,6 @@ static void check_preempt_wakeup(struct 
 	if (unlikely(se == pse))
 		return;
 
-	ftrace_special(__LINE__, p->pid, se->last_wakeup);
 	cfs_rq_of(pse)->next = pse;
 
 	/*

Index: linux-2.6-lttng/include/linux/marker.h
===================================================================
@@ -44,8 +44,8 @@ struct marker {
 				 */
 	char state;		/* Marker state. */
 	char ptype;		/* probe type : 0 : single, 1 : multi */
-	void (*call)(const struct marker *mdata,	/* Probe wrapper */
-		void *call_private, const char *fmt, ...);
+				/* Probe wrapper */
+	void (*call)(const struct marker *mdata, void *call_private, ...);
 	struct marker_probe_closure single;
 	struct marker_probe_closure *multi;
 } __attribute__((aligned(8)));

@@ -72,8 +72,7 @@ struct marker {
 		__mark_check_format(format, ## args);			\
 		if (unlikely(__mark_##name.state)) {			\
 			(*__mark_##name.call)				\
-				(&__mark_##name, call_private,		\
-				format, ## args);			\
+				(&__mark_##name, call_private, ## args);\
 		}							\
 	} while (0)
 

@@ -117,9 +116,9 @@ static inline void __printf(1, 2) ___mar
 extern marker_probe_func __mark_empty_function;
 
 extern void marker_probe_cb(const struct marker *mdata,
-	void *call_private, const char *fmt, ...);
+	void *call_private, ...);
 extern void marker_probe_cb_noarg(const struct marker *mdata,
-	void *call_private, const char *fmt, ...);
+	void *call_private, ...);
 
 /*
  * Connect a probe to a marker.

Index: linux-2.6-lttng/kernel/marker.c
===================================================================
@@ -54,8 +54,8 @@ static DEFINE_MUTEX(markers_mutex);
 struct marker_entry {
 	struct hlist_node hlist;
 	char *format;
-	void (*call)(const struct marker *mdata,	/* Probe wrapper */
-		void *call_private, const char *fmt, ...);
+			/* Probe wrapper */
+	void (*call)(const struct marker *mdata, void *call_private, ...);
 	struct marker_probe_closure single;
 	struct marker_probe_closure *multi;
 	int refcount;	/* Number of times armed. 0 if disarmed. */

@@ -90,15 +90,13 @@ EXPORT_SYMBOL_GPL(__mark_empty_function)
  * marker_probe_cb Callback that prepares the variable argument list for probes.
  * @mdata: pointer of type struct marker
  * @call_private: caller site private data
- * @fmt: format string
  * @...:  Variable argument list.
  *
  * Since we do not use "typical" pointer based RCU in the 1 argument case, we
  * 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,
-	const char *fmt, ...)
+void marker_probe_cb(const struct marker *mdata, void *call_private, ...)
 {
 	va_list args;
 	char ptype;

@@ -119,8 +117,9 @@ void marker_probe_cb(const struct marker
 		/* Must read the ptr before private data. They are not data
 		 * dependant, so we put an explicit smp_rmb() here. */
 		smp_rmb();
-		va_start(args, fmt);
-		func(mdata->single.probe_private, call_private, fmt, &args);
+		va_start(args, call_private);
+		func(mdata->single.probe_private, call_private, mdata->format,
+			&args);
 		va_end(args);
 	} else {
 		struct marker_probe_closure *multi;

@@ -135,9 +134,9 @@ void marker_probe_cb(const struct marker
 		smp_read_barrier_depends();
 		multi = mdata->multi;
 		for (i = 0; multi[i].func; i++) {
-			va_start(args, fmt);
-			multi[i].func(multi[i].probe_private, call_private, fmt,
-				&args);
+			va_start(args, call_private);
+			multi[i].func(multi[i].probe_private, call_private,
+				mdata->format, &args);
 			va_end(args);
 		}
 	}

@@ -149,13 +148,11 @@ EXPORT_SYMBOL_GPL(marker_probe_cb);
  * marker_probe_cb Callback that does not prepare the variable argument list.
  * @mdata: pointer of type struct marker
  * @call_private: caller site private data
- * @fmt: format string
  * @...:  Variable argument list.
  *
  * Should be connected to markers "MARK_NOARGS".
  */
-void marker_probe_cb_noarg(const struct marker *mdata,
-	void *call_private, const char *fmt, ...)
+void marker_probe_cb_noarg(const struct marker *mdata, void *call_private, ...)
 {
 	va_list args;	/* not initialized */
 	char ptype;

@@ -171,7 +168,8 @@ void marker_probe_cb_noarg(const struct 
 		/* Must read the ptr before private data. They are not data
 		 * dependant, so we put an explicit smp_rmb() here. */
 		smp_rmb();
-		func(mdata->single.probe_private, call_private, fmt, &args);
+		func(mdata->single.probe_private, call_private, mdata->format,
+			&args);
 	} else {
 		struct marker_probe_closure *multi;
 		int i;

@@ -185,8 +183,8 @@ void marker_probe_cb_noarg(const struct 
 		smp_read_barrier_depends();
 		multi = mdata->multi;
 		for (i = 0; multi[i].func; i++)
-			multi[i].func(multi[i].probe_private, call_private, fmt,
-				&args);
+			multi[i].func(multi[i].probe_private, call_private,
+				mdata->format, &args);
 	}
 	preempt_enable();
 }

Index: linux-2.6-lttng/include/linux/marker.h
===================================================================
@@ -58,8 +58,12 @@ struct marker {
  * Make sure the alignment of the structure in the __markers section will
  * not add unwanted padding between the beginning of the section and the
  * structure. Force alignment to the same alignment as the section start.
+ *
+ * The "generic" argument controls which marker enabling mechanism must be used.
+ * If generic is true, a variable read is used.
+ * If generic is false, immediate values are used.
  */
-#define __trace_mark(name, call_private, format, args...)		\
+#define __trace_mark(generic, name, call_private, format, args...)	\
 	do {								\
 		static const char __mstrtab_##name[]			\
 		__attribute__((section("__markers_strings")))		\

@@ -79,7 +83,7 @@ struct marker {
 extern void marker_update_probe_range(struct marker *begin,
 	struct marker *end);
 #else /* !CONFIG_MARKERS */
-#define __trace_mark(name, call_private, format, args...) \
+#define __trace_mark(generic, name, call_private, format, args...) \
 		__mark_check_format(format, ## args)
 static inline void marker_update_probe_range(struct marker *begin,
 	struct marker *end)

@@ -87,15 +91,30 @@ static inline void marker_update_probe_r
 #endif /* CONFIG_MARKERS */
 
 /**
- * trace_mark - Marker
+ * trace_mark - Marker using code patching
  * @name: marker name, not quoted.
  * @format: format string
  * @args...: variable argument list
  *
- * Places a marker.
+ * Places a marker using optimized code patching technique (imv_read())
+ * to be enabled when immediate values are present.
  */
 #define trace_mark(name, format, args...) \
-	__trace_mark(name, NULL, format, ## args)
+	__trace_mark(0, name, NULL, format, ## args)
+
+/**
+ * _trace_mark - Marker using variable read
+ * @name: marker name, not quoted.
+ * @format: format string
+ * @args...: variable argument list
+ *
+ * Places a marker using a standard memory read (_imv_read()) to be
+ * enabled. Should be used for markers in code paths where instruction
+ * modification based enabling is not welcome. (__init and __exit functions,
+ * lockdep, some traps, printk).
+ */
+#define _trace_mark(name, format, args...) \
+	__trace_mark(1, name, NULL, format, ## args)
 
 /**
  * MARK_NOARGS - Format string for a marker with no argument.