From 490dea45d00f01847ebebd007685d564aaf2cd98 Mon Sep 17 00:00:00 2001
From: Peter Zijlstra <peterz@infradead.org>
Date: Mon, 24 Nov 2008 17:06:57 +0100
Subject: itimers: remove the per-cpu-ish-ness

Either we bounce once cacheline per cpu per tick, yielding n^2 bounces
or we just bounce a single..

Also, using per-cpu allocations for the thread-groups complicates the
per-cpu allocator in that its currently aimed to be a fixed sized
allocator and the only possible extention to that would be vmap based,
which is seriously constrained on 32 bit archs.

So making the per-cpu memory requirement depend on the number of
processes is an issue.

Lastly, it didn't deal with cpu-hotplug, although admittedly that might
be fixable.

Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
---
 kernel/fork.c             | 15 +++++-----
 kernel/posix-cpu-timers.c | 70 -----------------------------------------------
 kernel/sched_stats.h      | 33 ++++++++++------------
 3 files changed, 22 insertions(+), 96 deletions(-)

(limited to 'kernel')

diff --git a/kernel/fork.c b/kernel/fork.c
index 7b8f2a78be3d..7087d8c0e5e2 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -820,14 +820,15 @@ static int copy_signal(unsigned long clone_flags, struct task_struct *tsk)
 	int ret;
 
 	if (clone_flags & CLONE_THREAD) {
-		ret = thread_group_cputime_clone_thread(current);
-		if (likely(!ret)) {
-			atomic_inc(&current->signal->count);
-			atomic_inc(&current->signal->live);
-		}
-		return ret;
+		atomic_inc(&current->signal->count);
+		atomic_inc(&current->signal->live);
+		return 0;
 	}
 	sig = kmem_cache_alloc(signal_cachep, GFP_KERNEL);
+
+	if (sig)
+		posix_cpu_timers_init_group(sig);
+
 	tsk->signal = sig;
 	if (!sig)
 		return -ENOMEM;
@@ -864,8 +865,6 @@ static int copy_signal(unsigned long clone_flags, struct task_struct *tsk)
 	memcpy(sig->rlim, current->signal->rlim, sizeof sig->rlim);
 	task_unlock(current->group_leader);
 
-	posix_cpu_timers_init_group(sig);
-
 	acct_init_pacct(&sig->pacct);
 
 	tty_audit_fork(sig);
diff --git a/kernel/posix-cpu-timers.c b/kernel/posix-cpu-timers.c
index 157de3a47832..fa07da94d7be 100644
--- a/kernel/posix-cpu-timers.c
+++ b/kernel/posix-cpu-timers.c
@@ -9,76 +9,6 @@
 #include <asm/uaccess.h>
 #include <linux/kernel_stat.h>
 
-/*
- * Allocate the thread_group_cputime structure appropriately and fill in the
- * current values of the fields.  Called from copy_signal() via
- * thread_group_cputime_clone_thread() when adding a second or subsequent
- * thread to a thread group.  Assumes interrupts are enabled when called.
- */
-int thread_group_cputime_alloc(struct task_struct *tsk)
-{
-	struct signal_struct *sig = tsk->signal;
-	struct task_cputime *cputime;
-
-	/*
-	 * If we have multiple threads and we don't already have a
-	 * per-CPU task_cputime struct (checked in the caller), allocate
-	 * one and fill it in with the times accumulated so far.  We may
-	 * race with another thread so recheck after we pick up the sighand
-	 * lock.
-	 */
-	cputime = alloc_percpu(struct task_cputime);
-	if (cputime == NULL)
-		return -ENOMEM;
-	spin_lock_irq(&tsk->sighand->siglock);
-	if (sig->cputime.totals) {
-		spin_unlock_irq(&tsk->sighand->siglock);
-		free_percpu(cputime);
-		return 0;
-	}
-	sig->cputime.totals = cputime;
-	cputime = per_cpu_ptr(sig->cputime.totals, smp_processor_id());
-	cputime->utime = tsk->utime;
-	cputime->stime = tsk->stime;
-	cputime->sum_exec_runtime = tsk->se.sum_exec_runtime;
-	spin_unlock_irq(&tsk->sighand->siglock);
-	return 0;
-}
-
-/**
- * thread_group_cputime - Sum the thread group time fields across all CPUs.
- *
- * @tsk:	The task we use to identify the thread group.
- * @times:	task_cputime structure in which we return the summed fields.
- *
- * Walk the list of CPUs to sum the per-CPU time fields in the thread group
- * time structure.
- */
-void thread_group_cputime(
-	struct task_struct *tsk,
-	struct task_cputime *times)
-{
-	struct task_cputime *totals, *tot;
-	int i;
-
-	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(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;
-	}
-}
-
 /*
  * Called after updating RLIMIT_CPU to set timer expiration if necessary.
  */
diff --git a/kernel/sched_stats.h b/kernel/sched_stats.h
index f2773b5d1226..8ab0cef8ecab 100644
--- a/kernel/sched_stats.h
+++ b/kernel/sched_stats.h
@@ -296,6 +296,7 @@ sched_info_switch(struct task_struct *prev, struct task_struct *next)
 static inline void account_group_user_time(struct task_struct *tsk,
 					   cputime_t cputime)
 {
+	struct task_cputime *times;
 	struct signal_struct *sig;
 
 	/* tsk == current, ensure it is safe to use ->signal */
@@ -303,13 +304,11 @@ static inline void account_group_user_time(struct task_struct *tsk,
 		return;
 
 	sig = tsk->signal;
-	if (sig->cputime.totals) {
-		struct task_cputime *times;
+	times = &sig->cputime.totals;
 
-		times = per_cpu_ptr(sig->cputime.totals, get_cpu());
-		times->utime = cputime_add(times->utime, cputime);
-		put_cpu_no_resched();
-	}
+	spin_lock(&times->lock);
+	times->utime = cputime_add(times->utime, cputime);
+	spin_unlock(&times->lock);
 }
 
 /**
@@ -325,6 +324,7 @@ static inline void account_group_user_time(struct task_struct *tsk,
 static inline void account_group_system_time(struct task_struct *tsk,
 					     cputime_t cputime)
 {
+	struct task_cputime *times;
 	struct signal_struct *sig;
 
 	/* tsk == current, ensure it is safe to use ->signal */
@@ -332,13 +332,11 @@ static inline void account_group_system_time(struct task_struct *tsk,
 		return;
 
 	sig = tsk->signal;
-	if (sig->cputime.totals) {
-		struct task_cputime *times;
+	times = &sig->cputime.totals;
 
-		times = per_cpu_ptr(sig->cputime.totals, get_cpu());
-		times->stime = cputime_add(times->stime, cputime);
-		put_cpu_no_resched();
-	}
+	spin_lock(&times->lock);
+	times->stime = cputime_add(times->stime, cputime);
+	spin_unlock(&times->lock);
 }
 
 /**
@@ -354,6 +352,7 @@ static inline void account_group_system_time(struct task_struct *tsk,
 static inline void account_group_exec_runtime(struct task_struct *tsk,
 					      unsigned long long ns)
 {
+	struct task_cputime *times;
 	struct signal_struct *sig;
 
 	sig = tsk->signal;
@@ -362,11 +361,9 @@ static inline void account_group_exec_runtime(struct task_struct *tsk,
 	if (unlikely(!sig))
 		return;
 
-	if (sig->cputime.totals) {
-		struct task_cputime *times;
+	times = &sig->cputime.totals;
 
-		times = per_cpu_ptr(sig->cputime.totals, get_cpu());
-		times->sum_exec_runtime += ns;
-		put_cpu_no_resched();
-	}
+	spin_lock(&times->lock);
+	times->sum_exec_runtime += ns;
+	spin_unlock(&times->lock);
 }
-- 
cgit v1.2.3


From 783adf42cf039083dd3c734c07c3bdc707e2bb15 Mon Sep 17 00:00:00 2001
From: Steven Noonan <steven@uplinklabs.net>
Date: Sun, 11 Jan 2009 01:04:21 -0800
Subject: kernel/fork.c: unused variable 'ret'

Removed the unused variable.

Signed-off-by: Steven Noonan <steven@uplinklabs.net>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
---
 kernel/fork.c | 1 -
 1 file changed, 1 deletion(-)

(limited to 'kernel')

diff --git a/kernel/fork.c b/kernel/fork.c
index e995899ea83f..81da4aae85cb 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -817,7 +817,6 @@ static void posix_cpu_timers_init_group(struct signal_struct *sig)
 static int copy_signal(unsigned long clone_flags, struct task_struct *tsk)
 {
 	struct signal_struct *sig;
-	int ret;
 
 	if (clone_flags & CLONE_THREAD) {
 		atomic_inc(&current->signal->count);
-- 
cgit v1.2.3


From 01e3eb82278bf45221fc38b391bc5ee0f6a314d6 Mon Sep 17 00:00:00 2001
From: Ingo Molnar <mingo@elte.hu>
Date: Mon, 12 Jan 2009 13:00:50 +0100
Subject: Revert "sched: improve preempt debugging"

This reverts commit 7317d7b87edb41a9135e30be1ec3f7ef817c53dd.

This has been reported (and bisected) by Alexey Zaytsev and
Kamalesh Babulal to produce annoying warnings during bootup
on both x86 and powerpc.

kernel_locked() is not a valid test in IRQ context (we update the
BKL's ->lock_depth and the preempt count separately and non-atomicalyy),
so we cannot put it into the generic preempt debugging checks which
can run in IRQ contexts too.

Reported-and-bisected-by: Alexey Zaytsev <alexey.zaytsev@gmail.com>
Reported-and-bisected-by: Kamalesh Babulal <kamalesh@linux.vnet.ibm.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
---
 kernel/sched.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'kernel')

diff --git a/kernel/sched.c b/kernel/sched.c
index 8be2c13b50d0..3b630d882660 100644
--- a/kernel/sched.c
+++ b/kernel/sched.c
@@ -4440,7 +4440,7 @@ void __kprobes sub_preempt_count(int val)
 	/*
 	 * Underflow?
 	 */
-       if (DEBUG_LOCKS_WARN_ON(val > preempt_count() - (!!kernel_locked())))
+	if (DEBUG_LOCKS_WARN_ON(val > preempt_count()))
 		return;
 	/*
 	 * Is the spinlock portion underflowing?
-- 
cgit v1.2.3


From e4fa4c97016037620f9dc8bafe03e1086b665b4c Mon Sep 17 00:00:00 2001
From: Lai Jiangshan <laijs@cn.fujitsu.com>
Date: Wed, 14 Jan 2009 14:58:15 +0800
Subject: rcu: add __cpuinit to rcu_init_percpu_data()

Impact: reduce memory footprint

add __cpuinit to rcu_init_percpu_data(), and this function's text
will be discarded after boot when !CONFIG_HOTPLUG_CPU.

Signed-off-by: Lai Jiangshan <laijs@cn.fujitsu.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
---
 kernel/rcuclassic.c | 2 +-
 kernel/rcutree.c    | 2 +-
 2 files changed, 2 insertions(+), 2 deletions(-)

(limited to 'kernel')

diff --git a/kernel/rcuclassic.c b/kernel/rcuclassic.c
index 490934fc7ac3..bd5a9003497c 100644
--- a/kernel/rcuclassic.c
+++ b/kernel/rcuclassic.c
@@ -716,7 +716,7 @@ void rcu_check_callbacks(int cpu, int user)
 	raise_rcu_softirq();
 }
 
-static void rcu_init_percpu_data(int cpu, struct rcu_ctrlblk *rcp,
+static void __cpuinit rcu_init_percpu_data(int cpu, struct rcu_ctrlblk *rcp,
 						struct rcu_data *rdp)
 {
 	unsigned long flags;
diff --git a/kernel/rcutree.c b/kernel/rcutree.c
index f2d8638e6c60..b2fd602a6f6f 100644
--- a/kernel/rcutree.c
+++ b/kernel/rcutree.c
@@ -1314,7 +1314,7 @@ int rcu_needs_cpu(int cpu)
  * access due to the fact that this CPU cannot possibly have any RCU
  * callbacks in flight yet.
  */
-static void
+static void __cpuinit
 rcu_init_percpu_data(int cpu, struct rcu_state *rsp)
 {
 	unsigned long flags;
-- 
cgit v1.2.3


From baf48f6577e581a9adb8fe849dc80e24b21d171d Mon Sep 17 00:00:00 2001
From: Mandeep Singh Baines <msb@google.com>
Date: Mon, 12 Jan 2009 21:15:17 -0800
Subject: softlock: fix false panic which can occur if softlockup_thresh is
 reduced

At run-time, if softlockup_thresh is changed to a much lower value,
touch_timestamp is likely to be much older than the new softlock_thresh.

This will cause a false softlockup to be detected. If softlockup_panic
is enabled, the system will panic.

The fix is to touch all watchdogs before changing softlockup_thresh.

Signed-off-by: Mandeep Singh Baines <msb@google.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
---
 include/linux/sched.h | 3 +++
 kernel/softlockup.c   | 9 +++++++++
 kernel/sysctl.c       | 2 +-
 3 files changed, 13 insertions(+), 1 deletion(-)

(limited to 'kernel')

diff --git a/include/linux/sched.h b/include/linux/sched.h
index 4cae9b81a1f8..54cbabf3b871 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -293,6 +293,9 @@ extern void sched_show_task(struct task_struct *p);
 extern void softlockup_tick(void);
 extern void touch_softlockup_watchdog(void);
 extern void touch_all_softlockup_watchdogs(void);
+extern int proc_dosoftlockup_thresh(struct ctl_table *table, int write,
+				    struct file *filp, void __user *buffer,
+				    size_t *lenp, loff_t *ppos);
 extern unsigned int  softlockup_panic;
 extern unsigned long sysctl_hung_task_check_count;
 extern unsigned long sysctl_hung_task_timeout_secs;
diff --git a/kernel/softlockup.c b/kernel/softlockup.c
index d9188c66278a..85d5a2455103 100644
--- a/kernel/softlockup.c
+++ b/kernel/softlockup.c
@@ -16,6 +16,7 @@
 #include <linux/lockdep.h>
 #include <linux/notifier.h>
 #include <linux/module.h>
+#include <linux/sysctl.h>
 
 #include <asm/irq_regs.h>
 
@@ -88,6 +89,14 @@ void touch_all_softlockup_watchdogs(void)
 }
 EXPORT_SYMBOL(touch_all_softlockup_watchdogs);
 
+int proc_dosoftlockup_thresh(struct ctl_table *table, int write,
+			     struct file *filp, void __user *buffer,
+			     size_t *lenp, loff_t *ppos)
+{
+	touch_all_softlockup_watchdogs();
+	return proc_dointvec_minmax(table, write, filp, buffer, lenp, ppos);
+}
+
 /*
  * This callback runs from the timer interrupt, and checks
  * whether the watchdog thread has hung or not:
diff --git a/kernel/sysctl.c b/kernel/sysctl.c
index 89d74436318c..596dc31a7116 100644
--- a/kernel/sysctl.c
+++ b/kernel/sysctl.c
@@ -800,7 +800,7 @@ static struct ctl_table kern_table[] = {
 		.data		= &softlockup_thresh,
 		.maxlen		= sizeof(int),
 		.mode		= 0644,
-		.proc_handler	= &proc_dointvec_minmax,
+		.proc_handler	= &proc_dosoftlockup_thresh,
 		.strategy	= &sysctl_intvec,
 		.extra1		= &neg_one,
 		.extra2		= &sixty,
-- 
cgit v1.2.3


From 14819ea1e0bcbdc9b084cd60a6a24d5d786324ef Mon Sep 17 00:00:00 2001
From: Ingo Molnar <mingo@elte.hu>
Date: Wed, 14 Jan 2009 12:34:21 +0100
Subject: irq: export __set_irq_handler() and handle_level_irq()

Impact: build fix

ARM updates broke x86 allmodconfig builds:

 ERROR: "__set_irq_handler" [drivers/mfd/pcf50633-core.ko] undefined!
 ERROR: "handle_level_irq" [drivers/mfd/pcf50633-core.ko] undefined!

Signed-off-by: Ingo Molnar <mingo@elte.hu>
---
 kernel/irq/chip.c | 2 ++
 1 file changed, 2 insertions(+)

(limited to 'kernel')

diff --git a/kernel/irq/chip.c b/kernel/irq/chip.c
index f63c706d25e1..7de11bd64dfe 100644
--- a/kernel/irq/chip.c
+++ b/kernel/irq/chip.c
@@ -383,6 +383,7 @@ handle_level_irq(unsigned int irq, struct irq_desc *desc)
 out_unlock:
 	spin_unlock(&desc->lock);
 }
+EXPORT_SYMBOL_GPL(handle_level_irq);
 
 /**
  *	handle_fasteoi_irq - irq handler for transparent controllers
@@ -593,6 +594,7 @@ __set_irq_handler(unsigned int irq, irq_flow_handler_t handle, int is_chained,
 	}
 	spin_unlock_irqrestore(&desc->lock, flags);
 }
+EXPORT_SYMBOL_GPL(__set_irq_handler);
 
 void
 set_irq_chip_and_handler(unsigned int irq, struct irq_chip *chip,
-- 
cgit v1.2.3


From 2ed7c03ec17779afb4fcfa3b8c61df61bd4879ba Mon Sep 17 00:00:00 2001
From: Heiko Carstens <heiko.carstens@de.ibm.com>
Date: Wed, 14 Jan 2009 14:13:54 +0100
Subject: [CVE-2009-0029] Convert all system calls to return a long

Convert all system calls to return a long. This should be a NOP since all
converted types should have the same size anyway.
With the exception of sys_exit_group which returned void. But that doesn't
matter since the system call doesn't return.

Signed-off-by: Heiko Carstens <heiko.carstens@de.ibm.com>
---
 fs/read_write.c          | 18 +++++------
 fs/xattr.c               | 12 ++++----
 include/linux/syscalls.h | 79 ++++++++++++++++++++++++------------------------
 ipc/mqueue.c             |  2 +-
 kernel/exit.c            |  4 ++-
 kernel/signal.c          |  2 +-
 kernel/timer.c           |  2 +-
 mm/filemap.c             |  2 +-
 mm/mmap.c                |  2 +-
 mm/mremap.c              |  2 +-
 mm/nommu.c               |  2 +-
 11 files changed, 64 insertions(+), 63 deletions(-)

(limited to 'kernel')

diff --git a/fs/read_write.c b/fs/read_write.c
index 5cc6924eb158..940367f51f2a 100644
--- a/fs/read_write.c
+++ b/fs/read_write.c
@@ -147,7 +147,7 @@ loff_t vfs_llseek(struct file *file, loff_t offset, int origin)
 }
 EXPORT_SYMBOL(vfs_llseek);
 
-asmlinkage off_t sys_lseek(unsigned int fd, off_t offset, unsigned int origin)
+asmlinkage long sys_lseek(unsigned int fd, off_t offset, unsigned int origin)
 {
 	off_t retval;
 	struct file * file;
@@ -369,7 +369,7 @@ static inline void file_pos_write(struct file *file, loff_t pos)
 	file->f_pos = pos;
 }
 
-asmlinkage ssize_t sys_read(unsigned int fd, char __user * buf, size_t count)
+asmlinkage long sys_read(unsigned int fd, char __user * buf, size_t count)
 {
 	struct file *file;
 	ssize_t ret = -EBADF;
@@ -386,7 +386,7 @@ asmlinkage ssize_t sys_read(unsigned int fd, char __user * buf, size_t count)
 	return ret;
 }
 
-asmlinkage ssize_t sys_write(unsigned int fd, const char __user * buf, size_t count)
+asmlinkage long sys_write(unsigned int fd, const char __user * buf, size_t count)
 {
 	struct file *file;
 	ssize_t ret = -EBADF;
@@ -403,7 +403,7 @@ asmlinkage ssize_t sys_write(unsigned int fd, const char __user * buf, size_t co
 	return ret;
 }
 
-asmlinkage ssize_t sys_pread64(unsigned int fd, char __user *buf,
+asmlinkage long sys_pread64(unsigned int fd, char __user *buf,
 			     size_t count, loff_t pos)
 {
 	struct file *file;
@@ -424,7 +424,7 @@ asmlinkage ssize_t sys_pread64(unsigned int fd, char __user *buf,
 	return ret;
 }
 
-asmlinkage ssize_t sys_pwrite64(unsigned int fd, const char __user *buf,
+asmlinkage long sys_pwrite64(unsigned int fd, const char __user *buf,
 			      size_t count, loff_t pos)
 {
 	struct file *file;
@@ -672,7 +672,7 @@ ssize_t vfs_writev(struct file *file, const struct iovec __user *vec,
 
 EXPORT_SYMBOL(vfs_writev);
 
-asmlinkage ssize_t
+asmlinkage long
 sys_readv(unsigned long fd, const struct iovec __user *vec, unsigned long vlen)
 {
 	struct file *file;
@@ -693,7 +693,7 @@ sys_readv(unsigned long fd, const struct iovec __user *vec, unsigned long vlen)
 	return ret;
 }
 
-asmlinkage ssize_t
+asmlinkage long
 sys_writev(unsigned long fd, const struct iovec __user *vec, unsigned long vlen)
 {
 	struct file *file;
@@ -812,7 +812,7 @@ out:
 	return retval;
 }
 
-asmlinkage ssize_t sys_sendfile(int out_fd, int in_fd, off_t __user *offset, size_t count)
+asmlinkage long sys_sendfile(int out_fd, int in_fd, off_t __user *offset, size_t count)
 {
 	loff_t pos;
 	off_t off;
@@ -831,7 +831,7 @@ asmlinkage ssize_t sys_sendfile(int out_fd, int in_fd, off_t __user *offset, siz
 	return do_sendfile(out_fd, in_fd, NULL, count, 0);
 }
 
-asmlinkage ssize_t sys_sendfile64(int out_fd, int in_fd, loff_t __user *offset, size_t count)
+asmlinkage long sys_sendfile64(int out_fd, int in_fd, loff_t __user *offset, size_t count)
 {
 	loff_t pos;
 	ssize_t ret;
diff --git a/fs/xattr.c b/fs/xattr.c
index 237804cd6b56..d049ae27aae7 100644
--- a/fs/xattr.c
+++ b/fs/xattr.c
@@ -349,7 +349,7 @@ getxattr(struct dentry *d, const char __user *name, void __user *value,
 	return error;
 }
 
-asmlinkage ssize_t
+asmlinkage long
 sys_getxattr(const char __user *pathname, const char __user *name,
 	     void __user *value, size_t size)
 {
@@ -364,7 +364,7 @@ sys_getxattr(const char __user *pathname, const char __user *name,
 	return error;
 }
 
-asmlinkage ssize_t
+asmlinkage long
 sys_lgetxattr(const char __user *pathname, const char __user *name, void __user *value,
 	      size_t size)
 {
@@ -379,7 +379,7 @@ sys_lgetxattr(const char __user *pathname, const char __user *name, void __user
 	return error;
 }
 
-asmlinkage ssize_t
+asmlinkage long
 sys_fgetxattr(int fd, const char __user *name, void __user *value, size_t size)
 {
 	struct file *f;
@@ -424,7 +424,7 @@ listxattr(struct dentry *d, char __user *list, size_t size)
 	return error;
 }
 
-asmlinkage ssize_t
+asmlinkage long
 sys_listxattr(const char __user *pathname, char __user *list, size_t size)
 {
 	struct path path;
@@ -438,7 +438,7 @@ sys_listxattr(const char __user *pathname, char __user *list, size_t size)
 	return error;
 }
 
-asmlinkage ssize_t
+asmlinkage long
 sys_llistxattr(const char __user *pathname, char __user *list, size_t size)
 {
 	struct path path;
@@ -452,7 +452,7 @@ sys_llistxattr(const char __user *pathname, char __user *list, size_t size)
 	return error;
 }
 
-asmlinkage ssize_t
+asmlinkage long
 sys_flistxattr(int fd, char __user *list, size_t size)
 {
 	struct file *f;
diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h
index a7593f670ca6..22290eeaf553 100644
--- a/include/linux/syscalls.h
+++ b/include/linux/syscalls.h
@@ -77,7 +77,7 @@ asmlinkage long sys_times(struct tms __user *tbuf);
 
 asmlinkage long sys_gettid(void);
 asmlinkage long sys_nanosleep(struct timespec __user *rqtp, struct timespec __user *rmtp);
-asmlinkage unsigned long sys_alarm(unsigned int seconds);
+asmlinkage long sys_alarm(unsigned int seconds);
 asmlinkage long sys_getpid(void);
 asmlinkage long sys_getppid(void);
 asmlinkage long sys_getuid(void);
@@ -166,7 +166,7 @@ asmlinkage long sys_kexec_load(unsigned long entry, unsigned long nr_segments,
 				unsigned long flags);
 
 asmlinkage long sys_exit(int error_code);
-asmlinkage void sys_exit_group(int error_code);
+asmlinkage long sys_exit_group(int error_code);
 asmlinkage long sys_wait4(pid_t pid, int __user *stat_addr,
 				int options, struct rusage __user *ru);
 asmlinkage long sys_waitid(int which, pid_t pid,
@@ -196,7 +196,7 @@ asmlinkage long sys_tkill(int pid, int sig);
 asmlinkage long sys_rt_sigqueueinfo(int pid, int sig, siginfo_t __user *uinfo);
 asmlinkage long sys_sgetmask(void);
 asmlinkage long sys_ssetmask(int newmask);
-asmlinkage unsigned long sys_signal(int sig, __sighandler_t handler);
+asmlinkage long sys_signal(int sig, __sighandler_t handler);
 asmlinkage long sys_pause(void);
 
 asmlinkage long sys_sync(void);
@@ -246,29 +246,29 @@ asmlinkage long sys_lsetxattr(const char __user *path, const char __user *name,
 			      const void __user *value, size_t size, int flags);
 asmlinkage long sys_fsetxattr(int fd, const char __user *name,
 			      const void __user *value, size_t size, int flags);
-asmlinkage ssize_t sys_getxattr(const char __user *path, const char __user *name,
-				void __user *value, size_t size);
-asmlinkage ssize_t sys_lgetxattr(const char __user *path, const char __user *name,
-				void __user *value, size_t size);
-asmlinkage ssize_t sys_fgetxattr(int fd, const char __user *name,
-				void __user *value, size_t size);
-asmlinkage ssize_t sys_listxattr(const char __user *path, char __user *list,
-				size_t size);
-asmlinkage ssize_t sys_llistxattr(const char __user *path, char __user *list,
-				size_t size);
-asmlinkage ssize_t sys_flistxattr(int fd, char __user *list, size_t size);
+asmlinkage long sys_getxattr(const char __user *path, const char __user *name,
+			     void __user *value, size_t size);
+asmlinkage long sys_lgetxattr(const char __user *path, const char __user *name,
+			      void __user *value, size_t size);
+asmlinkage long sys_fgetxattr(int fd, const char __user *name,
+			      void __user *value, size_t size);
+asmlinkage long sys_listxattr(const char __user *path, char __user *list,
+			      size_t size);
+asmlinkage long sys_llistxattr(const char __user *path, char __user *list,
+			       size_t size);
+asmlinkage long sys_flistxattr(int fd, char __user *list, size_t size);
 asmlinkage long sys_removexattr(const char __user *path,
 				const char __user *name);
 asmlinkage long sys_lremovexattr(const char __user *path,
 				 const char __user *name);
 asmlinkage long sys_fremovexattr(int fd, const char __user *name);
 
-asmlinkage unsigned long sys_brk(unsigned long brk);
+asmlinkage long sys_brk(unsigned long brk);
 asmlinkage long sys_mprotect(unsigned long start, size_t len,
 				unsigned long prot);
-asmlinkage unsigned long sys_mremap(unsigned long addr,
-				unsigned long old_len, unsigned long new_len,
-				unsigned long flags, unsigned long new_addr);
+asmlinkage long sys_mremap(unsigned long addr,
+			   unsigned long old_len, unsigned long new_len,
+			   unsigned long flags, unsigned long new_addr);
 asmlinkage long sys_remap_file_pages(unsigned long start, unsigned long size,
 			unsigned long prot, unsigned long pgoff,
 			unsigned long flags);
@@ -321,10 +321,10 @@ asmlinkage long sys_io_submit(aio_context_t, long,
 				struct iocb __user * __user *);
 asmlinkage long sys_io_cancel(aio_context_t ctx_id, struct iocb __user *iocb,
 			      struct io_event __user *result);
-asmlinkage ssize_t sys_sendfile(int out_fd, int in_fd,
-				off_t __user *offset, size_t count);
-asmlinkage ssize_t sys_sendfile64(int out_fd, int in_fd,
-				loff_t __user *offset, size_t count);
+asmlinkage long sys_sendfile(int out_fd, int in_fd,
+			     off_t __user *offset, size_t count);
+asmlinkage long sys_sendfile64(int out_fd, int in_fd,
+			       loff_t __user *offset, size_t count);
 asmlinkage long sys_readlink(const char __user *path,
 				char __user *buf, int bufsiz);
 asmlinkage long sys_creat(const char __user *pathname, int mode);
@@ -368,26 +368,25 @@ asmlinkage long sys_utime(char __user *filename,
 				struct utimbuf __user *times);
 asmlinkage long sys_utimes(char __user *filename,
 				struct timeval __user *utimes);
-asmlinkage off_t sys_lseek(unsigned int fd, off_t offset,
-				unsigned int origin);
+asmlinkage long sys_lseek(unsigned int fd, off_t offset,
+			  unsigned int origin);
 asmlinkage long sys_llseek(unsigned int fd, unsigned long offset_high,
 			unsigned long offset_low, loff_t __user *result,
 			unsigned int origin);
-asmlinkage ssize_t sys_read(unsigned int fd, char __user *buf,
-				size_t count);
-asmlinkage ssize_t sys_readahead(int fd, loff_t offset, size_t count);
-asmlinkage ssize_t sys_readv(unsigned long fd,
-				const struct iovec __user *vec,
-				unsigned long vlen);
-asmlinkage ssize_t sys_write(unsigned int fd, const char __user *buf,
-				size_t count);
-asmlinkage ssize_t sys_writev(unsigned long fd,
-				const struct iovec __user *vec,
-				unsigned long vlen);
-asmlinkage ssize_t sys_pread64(unsigned int fd, char __user *buf,
-				size_t count, loff_t pos);
-asmlinkage ssize_t sys_pwrite64(unsigned int fd, const char __user *buf,
-				size_t count, loff_t pos);
+asmlinkage long sys_read(unsigned int fd, char __user *buf, size_t count);
+asmlinkage long sys_readahead(int fd, loff_t offset, size_t count);
+asmlinkage long sys_readv(unsigned long fd,
+			  const struct iovec __user *vec,
+			  unsigned long vlen);
+asmlinkage long sys_write(unsigned int fd, const char __user *buf,
+			  size_t count);
+asmlinkage long sys_writev(unsigned long fd,
+			   const struct iovec __user *vec,
+			   unsigned long vlen);
+asmlinkage long sys_pread64(unsigned int fd, char __user *buf,
+			    size_t count, loff_t pos);
+asmlinkage long sys_pwrite64(unsigned int fd, const char __user *buf,
+			     size_t count, loff_t pos);
 asmlinkage long sys_getcwd(char __user *buf, unsigned long size);
 asmlinkage long sys_mkdir(const char __user *pathname, int mode);
 asmlinkage long sys_chdir(const char __user *filename);
@@ -476,7 +475,7 @@ asmlinkage long sys_shmctl(int shmid, int cmd, struct shmid_ds __user *buf);
 asmlinkage long sys_mq_open(const char __user *name, int oflag, mode_t mode, struct mq_attr __user *attr);
 asmlinkage long sys_mq_unlink(const char __user *name);
 asmlinkage long sys_mq_timedsend(mqd_t mqdes, const char __user *msg_ptr, size_t msg_len, unsigned int msg_prio, const struct timespec __user *abs_timeout);
-asmlinkage ssize_t sys_mq_timedreceive(mqd_t mqdes, char __user *msg_ptr, size_t msg_len, unsigned int __user *msg_prio, const struct timespec __user *abs_timeout);
+asmlinkage long sys_mq_timedreceive(mqd_t mqdes, char __user *msg_ptr, size_t msg_len, unsigned int __user *msg_prio, const struct timespec __user *abs_timeout);
 asmlinkage long sys_mq_notify(mqd_t mqdes, const struct sigevent __user *notification);
 asmlinkage long sys_mq_getsetattr(mqd_t mqdes, const struct mq_attr __user *mqstat, struct mq_attr __user *omqstat);
 
diff --git a/ipc/mqueue.c b/ipc/mqueue.c
index 23fdb8492b8e..6df028b70543 100644
--- a/ipc/mqueue.c
+++ b/ipc/mqueue.c
@@ -907,7 +907,7 @@ out:
 	return ret;
 }
 
-asmlinkage ssize_t sys_mq_timedreceive(mqd_t mqdes, char __user *u_msg_ptr,
+asmlinkage long sys_mq_timedreceive(mqd_t mqdes, char __user *u_msg_ptr,
 	size_t msg_len, unsigned int __user *u_msg_prio,
 	const struct timespec __user *u_abs_timeout)
 {
diff --git a/kernel/exit.c b/kernel/exit.c
index c7740fa3252c..fac9b040af2c 100644
--- a/kernel/exit.c
+++ b/kernel/exit.c
@@ -1182,9 +1182,11 @@ do_group_exit(int exit_code)
  * wait4()-ing process will get the correct exit code - even if this
  * thread is not the thread group leader.
  */
-asmlinkage void sys_exit_group(int error_code)
+asmlinkage long sys_exit_group(int error_code)
 {
 	do_group_exit((error_code & 0xff) << 8);
+	/* NOTREACHED */
+	return 0;
 }
 
 static struct pid *task_pid_type(struct task_struct *task, enum pid_type type)
diff --git a/kernel/signal.c b/kernel/signal.c
index 3152ac3b62e2..856a5479d49d 100644
--- a/kernel/signal.c
+++ b/kernel/signal.c
@@ -2559,7 +2559,7 @@ sys_ssetmask(int newmask)
 /*
  * For backwards compatibility.  Functionality superseded by sigaction.
  */
-asmlinkage unsigned long
+asmlinkage long
 sys_signal(int sig, __sighandler_t handler)
 {
 	struct k_sigaction new_sa, old_sa;
diff --git a/kernel/timer.c b/kernel/timer.c
index dee3f641a7a7..7b8697d7f04d 100644
--- a/kernel/timer.c
+++ b/kernel/timer.c
@@ -1129,7 +1129,7 @@ void do_timer(unsigned long ticks)
  * For backwards compatibility?  This can be done in libc so Alpha
  * and all newer ports shouldn't need it.
  */
-asmlinkage unsigned long sys_alarm(unsigned int seconds)
+asmlinkage long sys_alarm(unsigned int seconds)
 {
 	return alarm_setitimer(seconds);
 }
diff --git a/mm/filemap.c b/mm/filemap.c
index ceba0bd03662..538b75ed6236 100644
--- a/mm/filemap.c
+++ b/mm/filemap.c
@@ -1374,7 +1374,7 @@ do_readahead(struct address_space *mapping, struct file *filp,
 	return 0;
 }
 
-asmlinkage ssize_t sys_readahead(int fd, loff_t offset, size_t count)
+asmlinkage long sys_readahead(int fd, loff_t offset, size_t count)
 {
 	ssize_t ret;
 	struct file *file;
diff --git a/mm/mmap.c b/mm/mmap.c
index 749623196cb9..a970d890cb21 100644
--- a/mm/mmap.c
+++ b/mm/mmap.c
@@ -245,7 +245,7 @@ static struct vm_area_struct *remove_vma(struct vm_area_struct *vma)
 	return next;
 }
 
-asmlinkage unsigned long sys_brk(unsigned long brk)
+asmlinkage long sys_brk(unsigned long brk)
 {
 	unsigned long rlim, retval;
 	unsigned long newbrk, oldbrk;
diff --git a/mm/mremap.c b/mm/mremap.c
index 646de959aa58..5572e0825d80 100644
--- a/mm/mremap.c
+++ b/mm/mremap.c
@@ -420,7 +420,7 @@ out_nc:
 	return ret;
 }
 
-asmlinkage unsigned long sys_mremap(unsigned long addr,
+asmlinkage long sys_mremap(unsigned long addr,
 	unsigned long old_len, unsigned long new_len,
 	unsigned long flags, unsigned long new_addr)
 {
diff --git a/mm/nommu.c b/mm/nommu.c
index 60ed8375c986..ee3e78927739 100644
--- a/mm/nommu.c
+++ b/mm/nommu.c
@@ -416,7 +416,7 @@ EXPORT_SYMBOL(vm_insert_page);
  *  to a regular file.  in this case, the unmapping will need
  *  to invoke file system routines that need the global lock.
  */
-asmlinkage unsigned long sys_brk(unsigned long brk)
+asmlinkage long sys_brk(unsigned long brk)
 {
 	struct mm_struct *mm = current->mm;
 
-- 
cgit v1.2.3


From f627a741d24f12955fa2d9f8831c3b12860635bd Mon Sep 17 00:00:00 2001
From: Heiko Carstens <heiko.carstens@de.ibm.com>
Date: Wed, 14 Jan 2009 14:13:58 +0100
Subject: [CVE-2009-0029] Make sys_syslog a conditional system call

Remove the -ENOSYS implementation for !CONFIG_PRINTK and use
the cond_syscall infrastructure instead.

Acked-by: Kyle McMartin <kyle@redhat.com>
Signed-off-by: Heiko Carstens <heiko.carstens@de.ibm.com>
---
 kernel/printk.c | 5 -----
 kernel/sys_ni.c | 1 +
 2 files changed, 1 insertion(+), 5 deletions(-)

(limited to 'kernel')

diff --git a/kernel/printk.c b/kernel/printk.c
index 7015733793e8..e48cf33783fc 100644
--- a/kernel/printk.c
+++ b/kernel/printk.c
@@ -742,11 +742,6 @@ EXPORT_SYMBOL(vprintk);
 
 #else
 
-asmlinkage long sys_syslog(int type, char __user *buf, int len)
-{
-	return -ENOSYS;
-}
-
 static void call_console_drivers(unsigned start, unsigned end)
 {
 }
diff --git a/kernel/sys_ni.c b/kernel/sys_ni.c
index e14a23281707..27dad2967387 100644
--- a/kernel/sys_ni.c
+++ b/kernel/sys_ni.c
@@ -131,6 +131,7 @@ cond_syscall(sys_io_destroy);
 cond_syscall(sys_io_submit);
 cond_syscall(sys_io_cancel);
 cond_syscall(sys_io_getevents);
+cond_syscall(sys_syslog);
 
 /* arch-specific weak syscall entries */
 cond_syscall(sys_pciconfig_read);
-- 
cgit v1.2.3


From 58fd3aa288939d3097fa04505b25c2f5e6e144d1 Mon Sep 17 00:00:00 2001
From: Heiko Carstens <heiko.carstens@de.ibm.com>
Date: Wed, 14 Jan 2009 14:14:03 +0100
Subject: [CVE-2009-0029] System call wrappers part 01

Signed-off-by: Heiko Carstens <heiko.carstens@de.ibm.com>
---
 kernel/hrtimer.c |  4 ++--
 kernel/sys.c     |  2 +-
 kernel/time.c    | 14 +++++++-------
 kernel/timer.c   |  6 +++---
 4 files changed, 13 insertions(+), 13 deletions(-)

(limited to 'kernel')

diff --git a/kernel/hrtimer.c b/kernel/hrtimer.c
index 1455b7651b6b..2dc30c59c5fd 100644
--- a/kernel/hrtimer.c
+++ b/kernel/hrtimer.c
@@ -1467,8 +1467,8 @@ out:
 	return ret;
 }
 
-asmlinkage long
-sys_nanosleep(struct timespec __user *rqtp, struct timespec __user *rmtp)
+SYSCALL_DEFINE2(nanosleep, struct timespec __user *, rqtp,
+		struct timespec __user *, rmtp)
 {
 	struct timespec tu;
 
diff --git a/kernel/sys.c b/kernel/sys.c
index 763c3c17ded3..37165e552331 100644
--- a/kernel/sys.c
+++ b/kernel/sys.c
@@ -919,7 +919,7 @@ void do_sys_times(struct tms *tms)
 	tms->tms_cstime = cputime_to_clock_t(cstime);
 }
 
-asmlinkage long sys_times(struct tms __user * tbuf)
+SYSCALL_DEFINE1(times, struct tms __user *, tbuf)
 {
 	if (tbuf) {
 		struct tms tmp;
diff --git a/kernel/time.c b/kernel/time.c
index 4886e3ce83a4..29511943871a 100644
--- a/kernel/time.c
+++ b/kernel/time.c
@@ -60,7 +60,7 @@ EXPORT_SYMBOL(sys_tz);
  * why not move it into the appropriate arch directory (for those
  * architectures that need it).
  */
-asmlinkage long sys_time(time_t __user * tloc)
+SYSCALL_DEFINE1(time, time_t __user *, tloc)
 {
 	time_t i = get_seconds();
 
@@ -79,7 +79,7 @@ asmlinkage long sys_time(time_t __user * tloc)
  * architectures that need it).
  */
 
-asmlinkage long sys_stime(time_t __user *tptr)
+SYSCALL_DEFINE1(stime, time_t __user *, tptr)
 {
 	struct timespec tv;
 	int err;
@@ -99,8 +99,8 @@ asmlinkage long sys_stime(time_t __user *tptr)
 
 #endif /* __ARCH_WANT_SYS_TIME */
 
-asmlinkage long sys_gettimeofday(struct timeval __user *tv,
-				 struct timezone __user *tz)
+SYSCALL_DEFINE2(gettimeofday, struct timeval __user *, tv,
+		struct timezone __user *, tz)
 {
 	if (likely(tv != NULL)) {
 		struct timeval ktv;
@@ -184,8 +184,8 @@ int do_sys_settimeofday(struct timespec *tv, struct timezone *tz)
 	return 0;
 }
 
-asmlinkage long sys_settimeofday(struct timeval __user *tv,
-				struct timezone __user *tz)
+SYSCALL_DEFINE2(settimeofday, struct timeval __user *, tv,
+		struct timezone __user *, tz)
 {
 	struct timeval user_tv;
 	struct timespec	new_ts;
@@ -205,7 +205,7 @@ asmlinkage long sys_settimeofday(struct timeval __user *tv,
 	return do_sys_settimeofday(tv ? &new_ts : NULL, tz ? &new_tz : NULL);
 }
 
-asmlinkage long sys_adjtimex(struct timex __user *txc_p)
+SYSCALL_DEFINE1(adjtimex, struct timex __user *, txc_p)
 {
 	struct timex txc;		/* Local copy of parameter */
 	int ret;
diff --git a/kernel/timer.c b/kernel/timer.c
index 7b8697d7f04d..76041df06c57 100644
--- a/kernel/timer.c
+++ b/kernel/timer.c
@@ -1129,7 +1129,7 @@ void do_timer(unsigned long ticks)
  * For backwards compatibility?  This can be done in libc so Alpha
  * and all newer ports shouldn't need it.
  */
-asmlinkage long sys_alarm(unsigned int seconds)
+SYSCALL_DEFINE1(alarm, unsigned int, seconds)
 {
 	return alarm_setitimer(seconds);
 }
@@ -1152,7 +1152,7 @@ asmlinkage long sys_alarm(unsigned int seconds)
  *
  * This is SMP safe as current->tgid does not change.
  */
-asmlinkage long sys_getpid(void)
+SYSCALL_DEFINE0(getpid)
 {
 	return task_tgid_vnr(current);
 }
@@ -1308,7 +1308,7 @@ signed long __sched schedule_timeout_uninterruptible(signed long timeout)
 EXPORT_SYMBOL(schedule_timeout_uninterruptible);
 
 /* Thread ID - the internal kernel "pid" */
-asmlinkage long sys_gettid(void)
+SYSCALL_DEFINE0(gettid)
 {
 	return task_pid_vnr(current);
 }
-- 
cgit v1.2.3


From dbf040d9d1cbf1ef6250bdb095c5c118950bcde8 Mon Sep 17 00:00:00 2001
From: Heiko Carstens <heiko.carstens@de.ibm.com>
Date: Wed, 14 Jan 2009 14:14:04 +0100
Subject: [CVE-2009-0029] System call wrappers part 02

Signed-off-by: Heiko Carstens <heiko.carstens@de.ibm.com>
---
 kernel/sys.c   | 10 +++++-----
 kernel/timer.c | 10 +++++-----
 2 files changed, 10 insertions(+), 10 deletions(-)

(limited to 'kernel')

diff --git a/kernel/sys.c b/kernel/sys.c
index 37165e552331..4c33555f8d95 100644
--- a/kernel/sys.c
+++ b/kernel/sys.c
@@ -756,7 +756,7 @@ error:
 	return retval;
 }
 
-asmlinkage long sys_getresuid(uid_t __user *ruid, uid_t __user *euid, uid_t __user *suid)
+SYSCALL_DEFINE3(getresuid, uid_t __user *, ruid, uid_t __user *, euid, uid_t __user *, suid)
 {
 	const struct cred *cred = current_cred();
 	int retval;
@@ -814,7 +814,7 @@ error:
 	return retval;
 }
 
-asmlinkage long sys_getresgid(gid_t __user *rgid, gid_t __user *egid, gid_t __user *sgid)
+SYSCALL_DEFINE3(getresgid, gid_t __user *, rgid, gid_t __user *, egid, gid_t __user *, sgid)
 {
 	const struct cred *cred = current_cred();
 	int retval;
@@ -1015,7 +1015,7 @@ out:
 	return err;
 }
 
-asmlinkage long sys_getpgid(pid_t pid)
+SYSCALL_DEFINE1(getpgid, pid_t, pid)
 {
 	struct task_struct *p;
 	struct pid *grp;
@@ -1045,14 +1045,14 @@ out:
 
 #ifdef __ARCH_WANT_SYS_GETPGRP
 
-asmlinkage long sys_getpgrp(void)
+SYSCALL_DEFINE0(getpgrp)
 {
 	return sys_getpgid(0);
 }
 
 #endif
 
-asmlinkage long sys_getsid(pid_t pid)
+SYSCALL_DEFINE1(getsid, pid_t, pid)
 {
 	struct task_struct *p;
 	struct pid *sid;
diff --git a/kernel/timer.c b/kernel/timer.c
index 76041df06c57..14a51530a4cd 100644
--- a/kernel/timer.c
+++ b/kernel/timer.c
@@ -1163,7 +1163,7 @@ SYSCALL_DEFINE0(getpid)
  * value of ->real_parent under rcu_read_lock(), see
  * release_task()->call_rcu(delayed_put_task_struct).
  */
-asmlinkage long sys_getppid(void)
+SYSCALL_DEFINE0(getppid)
 {
 	int pid;
 
@@ -1174,25 +1174,25 @@ asmlinkage long sys_getppid(void)
 	return pid;
 }
 
-asmlinkage long sys_getuid(void)
+SYSCALL_DEFINE0(getuid)
 {
 	/* Only we change this so SMP safe */
 	return current_uid();
 }
 
-asmlinkage long sys_geteuid(void)
+SYSCALL_DEFINE0(geteuid)
 {
 	/* Only we change this so SMP safe */
 	return current_euid();
 }
 
-asmlinkage long sys_getgid(void)
+SYSCALL_DEFINE0(getgid)
 {
 	/* Only we change this so SMP safe */
 	return current_gid();
 }
 
-asmlinkage long sys_getegid(void)
+SYSCALL_DEFINE0(getegid)
 {
 	/* Only we change this so SMP safe */
 	return  current_egid();
-- 
cgit v1.2.3


From ae1251ab785f6da87219df8352ffdac68bba23e4 Mon Sep 17 00:00:00 2001
From: Heiko Carstens <heiko.carstens@de.ibm.com>
Date: Wed, 14 Jan 2009 14:14:05 +0100
Subject: [CVE-2009-0029] System call wrappers part 03

Signed-off-by: Heiko Carstens <heiko.carstens@de.ibm.com>
---
 kernel/sys.c | 18 +++++++++---------
 1 file changed, 9 insertions(+), 9 deletions(-)

(limited to 'kernel')

diff --git a/kernel/sys.c b/kernel/sys.c
index 4c33555f8d95..ace9ced598b9 100644
--- a/kernel/sys.c
+++ b/kernel/sys.c
@@ -478,7 +478,7 @@ void ctrl_alt_del(void)
  * SMP: There are not races, the GIDs are checked only by filesystem
  *      operations (as far as semantic preservation is concerned).
  */
-asmlinkage long sys_setregid(gid_t rgid, gid_t egid)
+SYSCALL_DEFINE2(setregid, gid_t, rgid, gid_t, egid)
 {
 	const struct cred *old;
 	struct cred *new;
@@ -529,7 +529,7 @@ error:
  *
  * SMP: Same implicit races as above.
  */
-asmlinkage long sys_setgid(gid_t gid)
+SYSCALL_DEFINE1(setgid, gid_t, gid)
 {
 	const struct cred *old;
 	struct cred *new;
@@ -597,7 +597,7 @@ static int set_user(struct cred *new)
  * 100% compatible with BSD.  A program which uses just setuid() will be
  * 100% compatible with POSIX with saved IDs. 
  */
-asmlinkage long sys_setreuid(uid_t ruid, uid_t euid)
+SYSCALL_DEFINE2(setreuid, uid_t, ruid, uid_t, euid)
 {
 	const struct cred *old;
 	struct cred *new;
@@ -661,7 +661,7 @@ error:
  * will allow a root program to temporarily drop privileges and be able to
  * regain them by swapping the real and effective uid.  
  */
-asmlinkage long sys_setuid(uid_t uid)
+SYSCALL_DEFINE1(setuid, uid_t, uid)
 {
 	const struct cred *old;
 	struct cred *new;
@@ -705,7 +705,7 @@ error:
  * This function implements a generic ability to update ruid, euid,
  * and suid.  This allows you to implement the 4.4 compatible seteuid().
  */
-asmlinkage long sys_setresuid(uid_t ruid, uid_t euid, uid_t suid)
+SYSCALL_DEFINE3(setresuid, uid_t, ruid, uid_t, euid, uid_t, suid)
 {
 	const struct cred *old;
 	struct cred *new;
@@ -771,7 +771,7 @@ SYSCALL_DEFINE3(getresuid, uid_t __user *, ruid, uid_t __user *, euid, uid_t __u
 /*
  * Same as above, but for rgid, egid, sgid.
  */
-asmlinkage long sys_setresgid(gid_t rgid, gid_t egid, gid_t sgid)
+SYSCALL_DEFINE3(setresgid, gid_t, rgid, gid_t, egid, gid_t, sgid)
 {
 	const struct cred *old;
 	struct cred *new;
@@ -833,7 +833,7 @@ SYSCALL_DEFINE3(getresgid, gid_t __user *, rgid, gid_t __user *, egid, gid_t __u
  * whatever uid it wants to). It normally shadows "euid", except when
  * explicitly set by setfsuid() or for access..
  */
-asmlinkage long sys_setfsuid(uid_t uid)
+SYSCALL_DEFINE1(setfsuid, uid_t, uid)
 {
 	const struct cred *old;
 	struct cred *new;
@@ -870,7 +870,7 @@ change_okay:
 /*
  * Samma på svenska..
  */
-asmlinkage long sys_setfsgid(gid_t gid)
+SYSCALL_DEFINE1(setfsgid, gid_t, gid)
 {
 	const struct cred *old;
 	struct cred *new;
@@ -1311,7 +1311,7 @@ int set_current_groups(struct group_info *group_info)
 
 EXPORT_SYMBOL(set_current_groups);
 
-asmlinkage long sys_getgroups(int gidsetsize, gid_t __user *grouplist)
+SYSCALL_DEFINE2(getgroups, int, gidsetsize, gid_t __user *, grouplist)
 {
 	const struct cred *cred = current_cred();
 	int i;
-- 
cgit v1.2.3


From b290ebe2c46d01b742b948ce03f09e8a3efb9a92 Mon Sep 17 00:00:00 2001
From: Heiko Carstens <heiko.carstens@de.ibm.com>
Date: Wed, 14 Jan 2009 14:14:06 +0100
Subject: [CVE-2009-0029] System call wrappers part 04

Signed-off-by: Heiko Carstens <heiko.carstens@de.ibm.com>
---
 kernel/acct.c        | 2 +-
 kernel/capability.c  | 4 ++--
 kernel/exec_domain.c | 3 +--
 kernel/itimer.c      | 2 +-
 kernel/signal.c      | 7 +++----
 kernel/sys.c         | 6 +++---
 6 files changed, 11 insertions(+), 13 deletions(-)

(limited to 'kernel')

diff --git a/kernel/acct.c b/kernel/acct.c
index d57b7cbb98b6..7afa31564162 100644
--- a/kernel/acct.c
+++ b/kernel/acct.c
@@ -277,7 +277,7 @@ static int acct_on(char *name)
  * should be written. If the filename is NULL, accounting will be
  * shutdown.
  */
-asmlinkage long sys_acct(const char __user *name)
+SYSCALL_DEFINE1(acct, const char __user *, name)
 {
 	int error;
 
diff --git a/kernel/capability.c b/kernel/capability.c
index 688926e496be..4e17041963f5 100644
--- a/kernel/capability.c
+++ b/kernel/capability.c
@@ -161,7 +161,7 @@ static inline int cap_get_target_pid(pid_t pid, kernel_cap_t *pEp,
  *
  * Returns 0 on success and < 0 on error.
  */
-asmlinkage long sys_capget(cap_user_header_t header, cap_user_data_t dataptr)
+SYSCALL_DEFINE2(capget, cap_user_header_t, header, cap_user_data_t, dataptr)
 {
 	int ret = 0;
 	pid_t pid;
@@ -235,7 +235,7 @@ asmlinkage long sys_capget(cap_user_header_t header, cap_user_data_t dataptr)
  *
  * Returns 0 on success and < 0 on error.
  */
-asmlinkage long sys_capset(cap_user_header_t header, const cap_user_data_t data)
+SYSCALL_DEFINE2(capset, cap_user_header_t, header, const cap_user_data_t, data)
 {
 	struct __user_cap_data_struct kdata[_KERNEL_CAPABILITY_U32S];
 	unsigned i, tocopy;
diff --git a/kernel/exec_domain.c b/kernel/exec_domain.c
index 0511716e9424..667c841c2952 100644
--- a/kernel/exec_domain.c
+++ b/kernel/exec_domain.c
@@ -209,8 +209,7 @@ static int __init proc_execdomains_init(void)
 module_init(proc_execdomains_init);
 #endif
 
-asmlinkage long
-sys_personality(u_long personality)
+SYSCALL_DEFINE1(personality, u_long, personality)
 {
 	u_long old = current->personality;
 
diff --git a/kernel/itimer.c b/kernel/itimer.c
index db7c358b9a02..7e0663ea94fc 100644
--- a/kernel/itimer.c
+++ b/kernel/itimer.c
@@ -100,7 +100,7 @@ int do_getitimer(int which, struct itimerval *value)
 	return 0;
 }
 
-asmlinkage long sys_getitimer(int which, struct itimerval __user *value)
+SYSCALL_DEFINE2(getitimer, int, which, struct itimerval __user *, value)
 {
 	int error = -EFAULT;
 	struct itimerval get_buffer;
diff --git a/kernel/signal.c b/kernel/signal.c
index 856a5479d49d..3fe08eaa5dea 100644
--- a/kernel/signal.c
+++ b/kernel/signal.c
@@ -2434,8 +2434,7 @@ out:
 
 #ifdef __ARCH_WANT_SYS_SIGPENDING
 
-asmlinkage long
-sys_sigpending(old_sigset_t __user *set)
+SYSCALL_DEFINE1(sigpending, old_sigset_t __user *, set)
 {
 	return do_sigpending(set, sizeof(*set));
 }
@@ -2446,8 +2445,8 @@ sys_sigpending(old_sigset_t __user *set)
 /* Some platforms have their own version with special arguments others
    support only sys_rt_sigprocmask.  */
 
-asmlinkage long
-sys_sigprocmask(int how, old_sigset_t __user *set, old_sigset_t __user *oset)
+SYSCALL_DEFINE3(sigprocmask, int, how, old_sigset_t __user *, set,
+		old_sigset_t __user *, oset)
 {
 	int error;
 	old_sigset_t old_set, new_set;
diff --git a/kernel/sys.c b/kernel/sys.c
index ace9ced598b9..cbe4502c28a1 100644
--- a/kernel/sys.c
+++ b/kernel/sys.c
@@ -944,7 +944,7 @@ SYSCALL_DEFINE1(times, struct tms __user *, tbuf)
  * Auch. Had to add the 'did_exec' flag to conform completely to POSIX.
  * LBT 04.03.94
  */
-asmlinkage long sys_setpgid(pid_t pid, pid_t pgid)
+SYSCALL_DEFINE2(setpgid, pid_t, pid, pid_t, pgid)
 {
 	struct task_struct *p;
 	struct task_struct *group_leader = current->group_leader;
@@ -1080,7 +1080,7 @@ out:
 	return retval;
 }
 
-asmlinkage long sys_setsid(void)
+SYSCALL_DEFINE0(setsid)
 {
 	struct task_struct *group_leader = current->group_leader;
 	struct pid *sid = task_pid(group_leader);
@@ -1340,7 +1340,7 @@ out:
  *	without another task interfering.
  */
  
-asmlinkage long sys_setgroups(int gidsetsize, gid_t __user *grouplist)
+SYSCALL_DEFINE2(setgroups, int, gidsetsize, gid_t __user *, grouplist)
 {
 	struct group_info *group_info;
 	int retval;
-- 
cgit v1.2.3


From 362e9c07c7220c0a78c88826fc0d2bf7e4a4bb68 Mon Sep 17 00:00:00 2001
From: Heiko Carstens <heiko.carstens@de.ibm.com>
Date: Wed, 14 Jan 2009 14:14:07 +0100
Subject: [CVE-2009-0029] System call wrappers part 05

Signed-off-by: Heiko Carstens <heiko.carstens@de.ibm.com>
---
 kernel/itimer.c       |  5 ++---
 kernel/posix-timers.c | 43 +++++++++++++++++++------------------------
 2 files changed, 21 insertions(+), 27 deletions(-)

(limited to 'kernel')

diff --git a/kernel/itimer.c b/kernel/itimer.c
index 7e0663ea94fc..6a5fe93dd8bd 100644
--- a/kernel/itimer.c
+++ b/kernel/itimer.c
@@ -260,9 +260,8 @@ unsigned int alarm_setitimer(unsigned int seconds)
 	return it_old.it_value.tv_sec;
 }
 
-asmlinkage long sys_setitimer(int which,
-			      struct itimerval __user *value,
-			      struct itimerval __user *ovalue)
+SYSCALL_DEFINE3(setitimer, int, which, struct itimerval __user *, value,
+		struct itimerval __user *, ovalue)
 {
 	struct itimerval set_buffer, get_buffer;
 	int error;
diff --git a/kernel/posix-timers.c b/kernel/posix-timers.c
index 887c63787de6..052ec4d195c7 100644
--- a/kernel/posix-timers.c
+++ b/kernel/posix-timers.c
@@ -477,10 +477,9 @@ static void release_posix_timer(struct k_itimer *tmr, int it_id_set)
 
 /* Create a POSIX.1b interval timer. */
 
-asmlinkage long
-sys_timer_create(const clockid_t which_clock,
-		 struct sigevent __user *timer_event_spec,
-		 timer_t __user * created_timer_id)
+SYSCALL_DEFINE3(timer_create, const clockid_t, which_clock,
+		struct sigevent __user *, timer_event_spec,
+		timer_t __user *, created_timer_id)
 {
 	struct k_itimer *new_timer;
 	int error, new_timer_id;
@@ -661,8 +660,8 @@ common_timer_get(struct k_itimer *timr, struct itimerspec *cur_setting)
 }
 
 /* Get the time remaining on a POSIX.1b interval timer. */
-asmlinkage long
-sys_timer_gettime(timer_t timer_id, struct itimerspec __user *setting)
+SYSCALL_DEFINE2(timer_gettime, timer_t, timer_id,
+		struct itimerspec __user *, setting)
 {
 	struct k_itimer *timr;
 	struct itimerspec cur_setting;
@@ -691,8 +690,7 @@ sys_timer_gettime(timer_t timer_id, struct itimerspec __user *setting)
  * the call back to do_schedule_next_timer().  So all we need to do is
  * to pick up the frozen overrun.
  */
-asmlinkage long
-sys_timer_getoverrun(timer_t timer_id)
+SYSCALL_DEFINE1(timer_getoverrun, timer_t, timer_id)
 {
 	struct k_itimer *timr;
 	int overrun;
@@ -760,10 +758,9 @@ common_timer_set(struct k_itimer *timr, int flags,
 }
 
 /* Set a POSIX.1b interval timer */
-asmlinkage long
-sys_timer_settime(timer_t timer_id, int flags,
-		  const struct itimerspec __user *new_setting,
-		  struct itimerspec __user *old_setting)
+SYSCALL_DEFINE4(timer_settime, timer_t, timer_id, int, flags,
+		const struct itimerspec __user *, new_setting,
+		struct itimerspec __user *, old_setting)
 {
 	struct k_itimer *timr;
 	struct itimerspec new_spec, old_spec;
@@ -816,8 +813,7 @@ static inline int timer_delete_hook(struct k_itimer *timer)
 }
 
 /* Delete a POSIX.1b interval timer. */
-asmlinkage long
-sys_timer_delete(timer_t timer_id)
+SYSCALL_DEFINE1(timer_delete, timer_t, timer_id)
 {
 	struct k_itimer *timer;
 	unsigned long flags;
@@ -903,8 +899,8 @@ int do_posix_clock_nonanosleep(const clockid_t clock, int flags,
 }
 EXPORT_SYMBOL_GPL(do_posix_clock_nonanosleep);
 
-asmlinkage long sys_clock_settime(const clockid_t which_clock,
-				  const struct timespec __user *tp)
+SYSCALL_DEFINE2(clock_settime, const clockid_t, which_clock,
+		const struct timespec __user *, tp)
 {
 	struct timespec new_tp;
 
@@ -916,8 +912,8 @@ asmlinkage long sys_clock_settime(const clockid_t which_clock,
 	return CLOCK_DISPATCH(which_clock, clock_set, (which_clock, &new_tp));
 }
 
-asmlinkage long
-sys_clock_gettime(const clockid_t which_clock, struct timespec __user *tp)
+SYSCALL_DEFINE2(clock_gettime, const clockid_t, which_clock,
+		struct timespec __user *,tp)
 {
 	struct timespec kernel_tp;
 	int error;
@@ -933,8 +929,8 @@ sys_clock_gettime(const clockid_t which_clock, struct timespec __user *tp)
 
 }
 
-asmlinkage long
-sys_clock_getres(const clockid_t which_clock, struct timespec __user *tp)
+SYSCALL_DEFINE2(clock_getres, const clockid_t, which_clock,
+		struct timespec __user *, tp)
 {
 	struct timespec rtn_tp;
 	int error;
@@ -963,10 +959,9 @@ static int common_nsleep(const clockid_t which_clock, int flags,
 				 which_clock);
 }
 
-asmlinkage long
-sys_clock_nanosleep(const clockid_t which_clock, int flags,
-		    const struct timespec __user *rqtp,
-		    struct timespec __user *rmtp)
+SYSCALL_DEFINE4(clock_nanosleep, const clockid_t, which_clock, int, flags,
+		const struct timespec __user *, rqtp,
+		struct timespec __user *, rmtp)
 {
 	struct timespec t;
 
-- 
cgit v1.2.3


From 5add95d4f7cf08f6f62510f19576992912387501 Mon Sep 17 00:00:00 2001
From: Heiko Carstens <heiko.carstens@de.ibm.com>
Date: Wed, 14 Jan 2009 14:14:08 +0100
Subject: [CVE-2009-0029] System call wrappers part 06

Signed-off-by: Heiko Carstens <heiko.carstens@de.ibm.com>
---
 kernel/sched.c | 26 +++++++++++++-------------
 1 file changed, 13 insertions(+), 13 deletions(-)

(limited to 'kernel')

diff --git a/kernel/sched.c b/kernel/sched.c
index 8be2c13b50d0..1a0fdfa5ddf9 100644
--- a/kernel/sched.c
+++ b/kernel/sched.c
@@ -5126,7 +5126,7 @@ int can_nice(const struct task_struct *p, const int nice)
  * sys_setpriority is a more generic, but much slower function that
  * does similar things.
  */
-asmlinkage long sys_nice(int increment)
+SYSCALL_DEFINE1(nice, int, increment)
 {
 	long nice, retval;
 
@@ -5433,8 +5433,8 @@ do_sched_setscheduler(pid_t pid, int policy, struct sched_param __user *param)
  * @policy: new policy.
  * @param: structure containing the new RT priority.
  */
-asmlinkage long
-sys_sched_setscheduler(pid_t pid, int policy, struct sched_param __user *param)
+SYSCALL_DEFINE3(sched_setscheduler, pid_t, pid, int, policy,
+		struct sched_param __user *, param)
 {
 	/* negative values for policy are not valid */
 	if (policy < 0)
@@ -5448,7 +5448,7 @@ sys_sched_setscheduler(pid_t pid, int policy, struct sched_param __user *param)
  * @pid: the pid in question.
  * @param: structure containing the new RT priority.
  */
-asmlinkage long sys_sched_setparam(pid_t pid, struct sched_param __user *param)
+SYSCALL_DEFINE2(sched_setparam, pid_t, pid, struct sched_param __user *, param)
 {
 	return do_sched_setscheduler(pid, -1, param);
 }
@@ -5457,7 +5457,7 @@ asmlinkage long sys_sched_setparam(pid_t pid, struct sched_param __user *param)
  * sys_sched_getscheduler - get the policy (scheduling class) of a thread
  * @pid: the pid in question.
  */
-asmlinkage long sys_sched_getscheduler(pid_t pid)
+SYSCALL_DEFINE1(sched_getscheduler, pid_t, pid)
 {
 	struct task_struct *p;
 	int retval;
@@ -5482,7 +5482,7 @@ asmlinkage long sys_sched_getscheduler(pid_t pid)
  * @pid: the pid in question.
  * @param: structure containing the RT priority.
  */
-asmlinkage long sys_sched_getparam(pid_t pid, struct sched_param __user *param)
+SYSCALL_DEFINE2(sched_getparam, pid_t, pid, struct sched_param __user *, param)
 {
 	struct sched_param lp;
 	struct task_struct *p;
@@ -5600,8 +5600,8 @@ static int get_user_cpu_mask(unsigned long __user *user_mask_ptr, unsigned len,
  * @len: length in bytes of the bitmask pointed to by user_mask_ptr
  * @user_mask_ptr: user-space pointer to the new cpu mask
  */
-asmlinkage long sys_sched_setaffinity(pid_t pid, unsigned int len,
-				      unsigned long __user *user_mask_ptr)
+SYSCALL_DEFINE3(sched_setaffinity, pid_t, pid, unsigned int, len,
+		unsigned long __user *, user_mask_ptr)
 {
 	cpumask_var_t new_mask;
 	int retval;
@@ -5648,8 +5648,8 @@ out_unlock:
  * @len: length in bytes of the bitmask pointed to by user_mask_ptr
  * @user_mask_ptr: user-space pointer to hold the current cpu mask
  */
-asmlinkage long sys_sched_getaffinity(pid_t pid, unsigned int len,
-				      unsigned long __user *user_mask_ptr)
+SYSCALL_DEFINE3(sched_getaffinity, pid_t, pid, unsigned int, len,
+		unsigned long __user *, user_mask_ptr)
 {
 	int ret;
 	cpumask_var_t mask;
@@ -5678,7 +5678,7 @@ asmlinkage long sys_sched_getaffinity(pid_t pid, unsigned int len,
  * This function yields the current CPU to other tasks. If there are no
  * other threads running on this CPU then this function will return.
  */
-asmlinkage long sys_sched_yield(void)
+SYSCALL_DEFINE0(sched_yield)
 {
 	struct rq *rq = this_rq_lock();
 
@@ -5819,7 +5819,7 @@ long __sched io_schedule_timeout(long timeout)
  * this syscall returns the maximum rt_priority that can be used
  * by a given scheduling class.
  */
-asmlinkage long sys_sched_get_priority_max(int policy)
+SYSCALL_DEFINE1(sched_get_priority_max, int, policy)
 {
 	int ret = -EINVAL;
 
@@ -5844,7 +5844,7 @@ asmlinkage long sys_sched_get_priority_max(int policy)
  * this syscall returns the minimum rt_priority that can be used
  * by a given scheduling class.
  */
-asmlinkage long sys_sched_get_priority_min(int policy)
+SYSCALL_DEFINE1(sched_get_priority_min, int, policy)
 {
 	int ret = -EINVAL;
 
-- 
cgit v1.2.3


From 754fe8d297bfae7b77f7ce866e2fb0c5fb186506 Mon Sep 17 00:00:00 2001
From: Heiko Carstens <heiko.carstens@de.ibm.com>
Date: Wed, 14 Jan 2009 14:14:09 +0100
Subject: [CVE-2009-0029] System call wrappers part 07

Signed-off-by: Heiko Carstens <heiko.carstens@de.ibm.com>
---
 kernel/exit.c   | 8 ++++----
 kernel/kexec.c  | 5 ++---
 kernel/sched.c  | 4 ++--
 kernel/signal.c | 2 +-
 kernel/sys.c    | 7 ++++---
 net/socket.c    | 2 +-
 6 files changed, 14 insertions(+), 14 deletions(-)

(limited to 'kernel')

diff --git a/kernel/exit.c b/kernel/exit.c
index fac9b040af2c..08895df0eab3 100644
--- a/kernel/exit.c
+++ b/kernel/exit.c
@@ -1141,7 +1141,7 @@ NORET_TYPE void complete_and_exit(struct completion *comp, long code)
 
 EXPORT_SYMBOL(complete_and_exit);
 
-asmlinkage long sys_exit(int error_code)
+SYSCALL_DEFINE1(exit, int, error_code)
 {
 	do_exit((error_code&0xff)<<8);
 }
@@ -1182,7 +1182,7 @@ do_group_exit(int exit_code)
  * wait4()-ing process will get the correct exit code - even if this
  * thread is not the thread group leader.
  */
-asmlinkage long sys_exit_group(int error_code)
+SYSCALL_DEFINE1(exit_group, int, error_code)
 {
 	do_group_exit((error_code & 0xff) << 8);
 	/* NOTREACHED */
@@ -1795,8 +1795,8 @@ asmlinkage long sys_waitid(int which, pid_t upid,
 	return ret;
 }
 
-asmlinkage long sys_wait4(pid_t upid, int __user *stat_addr,
-			  int options, struct rusage __user *ru)
+SYSCALL_DEFINE4(wait4, pid_t, upid, int __user *, stat_addr,
+		int, options, struct rusage __user *, ru)
 {
 	struct pid *pid = NULL;
 	enum pid_type type;
diff --git a/kernel/kexec.c b/kernel/kexec.c
index 3fb855ad6aa0..8a6d7b08864e 100644
--- a/kernel/kexec.c
+++ b/kernel/kexec.c
@@ -934,9 +934,8 @@ struct kimage *kexec_crash_image;
 
 static DEFINE_MUTEX(kexec_mutex);
 
-asmlinkage long sys_kexec_load(unsigned long entry, unsigned long nr_segments,
-				struct kexec_segment __user *segments,
-				unsigned long flags)
+SYSCALL_DEFINE4(kexec_load, unsigned long, entry, unsigned long, nr_segments,
+		struct kexec_segment __user *, segments, unsigned long, flags)
 {
 	struct kimage **dest_image, *image;
 	int result;
diff --git a/kernel/sched.c b/kernel/sched.c
index 1a0fdfa5ddf9..65c02037b052 100644
--- a/kernel/sched.c
+++ b/kernel/sched.c
@@ -5869,8 +5869,8 @@ SYSCALL_DEFINE1(sched_get_priority_min, int, policy)
  * this syscall writes the default timeslice value of a given process
  * into the user-space timespec buffer. A value of '0' means infinity.
  */
-asmlinkage
-long sys_sched_rr_get_interval(pid_t pid, struct timespec __user *interval)
+SYSCALL_DEFINE4(sched_rr_get_interval, pid_t, pid,
+		struct timespec __user *, interval)
 {
 	struct task_struct *p;
 	unsigned int time_slice;
diff --git a/kernel/signal.c b/kernel/signal.c
index 3fe08eaa5dea..41f32e08615e 100644
--- a/kernel/signal.c
+++ b/kernel/signal.c
@@ -1961,7 +1961,7 @@ EXPORT_SYMBOL(unblock_all_signals);
  * System call entry points.
  */
 
-asmlinkage long sys_restart_syscall(void)
+SYSCALL_DEFINE0(restart_syscall)
 {
 	struct restart_block *restart = &current_thread_info()->restart_block;
 	return restart->fn(restart);
diff --git a/kernel/sys.c b/kernel/sys.c
index cbe4502c28a1..39b192b40034 100644
--- a/kernel/sys.c
+++ b/kernel/sys.c
@@ -143,7 +143,7 @@ out:
 	return error;
 }
 
-asmlinkage long sys_setpriority(int which, int who, int niceval)
+SYSCALL_DEFINE3(setpriority, int, which, int, who, int, niceval)
 {
 	struct task_struct *g, *p;
 	struct user_struct *user;
@@ -208,7 +208,7 @@ out:
  * has been offset by 20 (ie it returns 40..1 instead of -20..19)
  * to stay compatible.
  */
-asmlinkage long sys_getpriority(int which, int who)
+SYSCALL_DEFINE2(getpriority, int, which, int, who)
 {
 	struct task_struct *g, *p;
 	struct user_struct *user;
@@ -355,7 +355,8 @@ EXPORT_SYMBOL_GPL(kernel_power_off);
  *
  * reboot doesn't sync: do that yourself before calling this.
  */
-asmlinkage long sys_reboot(int magic1, int magic2, unsigned int cmd, void __user * arg)
+SYSCALL_DEFINE4(reboot, int, magic1, int, magic2, unsigned int, cmd,
+		void __user *, arg)
 {
 	char buffer[256];
 
diff --git a/net/socket.c b/net/socket.c
index 06603d73c411..cc9b666e58f6 100644
--- a/net/socket.c
+++ b/net/socket.c
@@ -1789,7 +1789,7 @@ out_put:
  *	Shutdown a socket.
  */
 
-asmlinkage long sys_shutdown(int fd, int how)
+SYSCALL_DEFINE2(shutdown, int, fd, int, how)
 {
 	int err, fput_needed;
 	struct socket *sock;
-- 
cgit v1.2.3


From 17da2bd90abf428523de0fb98f7075e00e3ed42e Mon Sep 17 00:00:00 2001
From: Heiko Carstens <heiko.carstens@de.ibm.com>
Date: Wed, 14 Jan 2009 14:14:10 +0100
Subject: [CVE-2009-0029] System call wrappers part 08

Signed-off-by: Heiko Carstens <heiko.carstens@de.ibm.com>
---
 kernel/exit.c   |  7 +++----
 kernel/fork.c   |  2 +-
 kernel/futex.c  |  6 +++---
 kernel/module.c | 10 ++++------
 kernel/sched.c  |  2 +-
 kernel/signal.c | 18 +++++++-----------
 6 files changed, 19 insertions(+), 26 deletions(-)

(limited to 'kernel')

diff --git a/kernel/exit.c b/kernel/exit.c
index 08895df0eab3..f80dec3f1875 100644
--- a/kernel/exit.c
+++ b/kernel/exit.c
@@ -1754,9 +1754,8 @@ end:
 	return retval;
 }
 
-asmlinkage long sys_waitid(int which, pid_t upid,
-			   struct siginfo __user *infop, int options,
-			   struct rusage __user *ru)
+SYSCALL_DEFINE5(waitid, int, which, pid_t, upid, struct siginfo __user *,
+		infop, int, options, struct rusage __user *, ru)
 {
 	struct pid *pid = NULL;
 	enum pid_type type;
@@ -1833,7 +1832,7 @@ SYSCALL_DEFINE4(wait4, pid_t, upid, int __user *, stat_addr,
  * sys_waitpid() remains for compatibility. waitpid() should be
  * implemented by calling sys_wait4() from libc.a.
  */
-asmlinkage long sys_waitpid(pid_t pid, int __user *stat_addr, int options)
+SYSCALL_DEFINE3(waitpid, pid_t, pid, int __user *, stat_addr, int, options)
 {
 	return sys_wait4(pid, stat_addr, options, NULL);
 }
diff --git a/kernel/fork.c b/kernel/fork.c
index 1d68f1255dd8..8eb37d38c6a4 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -901,7 +901,7 @@ static void copy_flags(unsigned long clone_flags, struct task_struct *p)
 	clear_freeze_flag(p);
 }
 
-asmlinkage long sys_set_tid_address(int __user *tidptr)
+SYSCALL_DEFINE1(set_tid_address, int __user *, tidptr)
 {
 	current->clear_child_tid = tidptr;
 
diff --git a/kernel/futex.c b/kernel/futex.c
index 002aa189eb09..e86931d8d4e9 100644
--- a/kernel/futex.c
+++ b/kernel/futex.c
@@ -1978,9 +1978,9 @@ long do_futex(u32 __user *uaddr, int op, u32 val, ktime_t *timeout,
 }
 
 
-asmlinkage long sys_futex(u32 __user *uaddr, int op, u32 val,
-			  struct timespec __user *utime, u32 __user *uaddr2,
-			  u32 val3)
+SYSCALL_DEFINE6(futex, u32 __user *, uaddr, int, op, u32, val,
+		struct timespec __user *, utime, u32 __user *, uaddr2,
+		u32, val3)
 {
 	struct timespec ts;
 	ktime_t t, *tp = NULL;
diff --git a/kernel/module.c b/kernel/module.c
index c9332c90d5a0..e8b51d41dd72 100644
--- a/kernel/module.c
+++ b/kernel/module.c
@@ -743,8 +743,8 @@ static void wait_for_zero_refcount(struct module *mod)
 	mutex_lock(&module_mutex);
 }
 
-asmlinkage long
-sys_delete_module(const char __user *name_user, unsigned int flags)
+SYSCALL_DEFINE2(delete_module, const char __user *, name_user,
+		unsigned int, flags)
 {
 	struct module *mod;
 	char name[MODULE_NAME_LEN];
@@ -2296,10 +2296,8 @@ static noinline struct module *load_module(void __user *umod,
 }
 
 /* This is where the real work happens */
-asmlinkage long
-sys_init_module(void __user *umod,
-		unsigned long len,
-		const char __user *uargs)
+SYSCALL_DEFINE3(init_module, void __user *, umod,
+		unsigned long, len, const char __user *, uargs)
 {
 	struct module *mod;
 	int ret = 0;
diff --git a/kernel/sched.c b/kernel/sched.c
index 65c02037b052..eb1931eef587 100644
--- a/kernel/sched.c
+++ b/kernel/sched.c
@@ -5869,7 +5869,7 @@ SYSCALL_DEFINE1(sched_get_priority_min, int, policy)
  * this syscall writes the default timeslice value of a given process
  * into the user-space timespec buffer. A value of '0' means infinity.
  */
-SYSCALL_DEFINE4(sched_rr_get_interval, pid_t, pid,
+SYSCALL_DEFINE2(sched_rr_get_interval, pid_t, pid,
 		struct timespec __user *, interval)
 {
 	struct task_struct *p;
diff --git a/kernel/signal.c b/kernel/signal.c
index 41f32e08615e..278cc8737f17 100644
--- a/kernel/signal.c
+++ b/kernel/signal.c
@@ -2014,8 +2014,8 @@ int sigprocmask(int how, sigset_t *set, sigset_t *oldset)
 	return error;
 }
 
-asmlinkage long
-sys_rt_sigprocmask(int how, sigset_t __user *set, sigset_t __user *oset, size_t sigsetsize)
+SYSCALL_DEFINE4(rt_sigprocmask, int, how, sigset_t __user *, set,
+		sigset_t __user *, oset, size_t, sigsetsize)
 {
 	int error = -EINVAL;
 	sigset_t old_set, new_set;
@@ -2074,8 +2074,7 @@ out:
 	return error;
 }	
 
-asmlinkage long
-sys_rt_sigpending(sigset_t __user *set, size_t sigsetsize)
+SYSCALL_DEFINE2(rt_sigpending, sigset_t __user *, set, size_t, sigsetsize)
 {
 	return do_sigpending(set, sigsetsize);
 }
@@ -2146,11 +2145,9 @@ int copy_siginfo_to_user(siginfo_t __user *to, siginfo_t *from)
 
 #endif
 
-asmlinkage long
-sys_rt_sigtimedwait(const sigset_t __user *uthese,
-		    siginfo_t __user *uinfo,
-		    const struct timespec __user *uts,
-		    size_t sigsetsize)
+SYSCALL_DEFINE4(rt_sigtimedwait, const sigset_t __user *, uthese,
+		siginfo_t __user *, uinfo, const struct timespec __user *, uts,
+		size_t, sigsetsize)
 {
 	int ret, sig;
 	sigset_t these;
@@ -2223,8 +2220,7 @@ sys_rt_sigtimedwait(const sigset_t __user *uthese,
 	return ret;
 }
 
-asmlinkage long
-sys_kill(pid_t pid, int sig)
+SYSCALL_DEFINE2(kill, pid_t, pid, int, sig)
 {
 	struct siginfo info;
 
-- 
cgit v1.2.3


From a5f8fa9e9ba5ef3305e147f41ad6e1e84ac1f0bd Mon Sep 17 00:00:00 2001
From: Heiko Carstens <heiko.carstens@de.ibm.com>
Date: Wed, 14 Jan 2009 14:14:11 +0100
Subject: [CVE-2009-0029] System call wrappers part 09

Signed-off-by: Heiko Carstens <heiko.carstens@de.ibm.com>
---
 fs/sync.c       |  6 +++---
 kernel/signal.c | 21 ++++++++-------------
 2 files changed, 11 insertions(+), 16 deletions(-)

(limited to 'kernel')

diff --git a/fs/sync.c b/fs/sync.c
index 23ebbd72ecc9..a16d53e5fe9d 100644
--- a/fs/sync.c
+++ b/fs/sync.c
@@ -36,7 +36,7 @@ static void do_sync(unsigned long wait)
 		laptop_sync_completion();
 }
 
-asmlinkage long sys_sync(void)
+SYSCALL_DEFINE0(sync)
 {
 	do_sync(1);
 	return 0;
@@ -144,12 +144,12 @@ static int do_fsync(unsigned int fd, int datasync)
 	return ret;
 }
 
-asmlinkage long sys_fsync(unsigned int fd)
+SYSCALL_DEFINE1(fsync, unsigned int, fd)
 {
 	return do_fsync(fd, 0);
 }
 
-asmlinkage long sys_fdatasync(unsigned int fd)
+SYSCALL_DEFINE1(fdatasync, unsigned int, fd)
 {
 	return do_fsync(fd, 1);
 }
diff --git a/kernel/signal.c b/kernel/signal.c
index 278cc8737f17..e2333929611a 100644
--- a/kernel/signal.c
+++ b/kernel/signal.c
@@ -2279,7 +2279,7 @@ static int do_tkill(pid_t tgid, pid_t pid, int sig)
  *  exists but it's not belonging to the target process anymore. This
  *  method solves the problem of threads exiting and PIDs getting reused.
  */
-asmlinkage long sys_tgkill(pid_t tgid, pid_t pid, int sig)
+SYSCALL_DEFINE3(tgkill, pid_t, tgid, pid_t, pid, int, sig)
 {
 	/* This is only valid for single tasks */
 	if (pid <= 0 || tgid <= 0)
@@ -2291,8 +2291,7 @@ asmlinkage long sys_tgkill(pid_t tgid, pid_t pid, int sig)
 /*
  *  Send a signal to only one task, even if it's a CLONE_THREAD task.
  */
-asmlinkage long
-sys_tkill(pid_t pid, int sig)
+SYSCALL_DEFINE2(tkill, pid_t, pid, int, sig)
 {
 	/* This is only valid for single tasks */
 	if (pid <= 0)
@@ -2301,8 +2300,8 @@ sys_tkill(pid_t pid, int sig)
 	return do_tkill(0, pid, sig);
 }
 
-asmlinkage long
-sys_rt_sigqueueinfo(pid_t pid, int sig, siginfo_t __user *uinfo)
+SYSCALL_DEFINE3(rt_sigqueueinfo, pid_t, pid, int, sig,
+		siginfo_t __user *, uinfo)
 {
 	siginfo_t info;
 
@@ -2526,15 +2525,13 @@ out:
 /*
  * For backwards compatibility.  Functionality superseded by sigprocmask.
  */
-asmlinkage long
-sys_sgetmask(void)
+SYSCALL_DEFINE0(sgetmask)
 {
 	/* SMP safe */
 	return current->blocked.sig[0];
 }
 
-asmlinkage long
-sys_ssetmask(int newmask)
+SYSCALL_DEFINE1(ssetmask, int, newmask)
 {
 	int old;
 
@@ -2554,8 +2551,7 @@ sys_ssetmask(int newmask)
 /*
  * For backwards compatibility.  Functionality superseded by sigaction.
  */
-asmlinkage long
-sys_signal(int sig, __sighandler_t handler)
+SYSCALL_DEFINE2(signal, int, sig, __sighandler_t, handler)
 {
 	struct k_sigaction new_sa, old_sa;
 	int ret;
@@ -2572,8 +2568,7 @@ sys_signal(int sig, __sighandler_t handler)
 
 #ifdef __ARCH_WANT_SYS_PAUSE
 
-asmlinkage long
-sys_pause(void)
+SYSCALL_DEFINE0(pause)
 {
 	current->state = TASK_INTERRUPTIBLE;
 	schedule();
-- 
cgit v1.2.3


From ca013e945b1ba5828b151ee646946f1297b67a4c Mon Sep 17 00:00:00 2001
From: Heiko Carstens <heiko.carstens@de.ibm.com>
Date: Wed, 14 Jan 2009 14:14:19 +0100
Subject: [CVE-2009-0029] System call wrappers part 17

Signed-off-by: Heiko Carstens <heiko.carstens@de.ibm.com>
---
 fs/open.c      | 16 +++++++---------
 kernel/uid16.c |  6 +++---
 2 files changed, 10 insertions(+), 12 deletions(-)

(limited to 'kernel')

diff --git a/fs/open.c b/fs/open.c
index 293408b1c165..4a6d80064746 100644
--- a/fs/open.c
+++ b/fs/open.c
@@ -517,7 +517,7 @@ out:
 	return res;
 }
 
-asmlinkage long sys_access(const char __user *filename, int mode)
+SYSCALL_DEFINE2(access, const char __user *, filename, int, mode)
 {
 	return sys_faccessat(AT_FDCWD, filename, mode);
 }
@@ -688,7 +688,7 @@ static int chown_common(struct dentry * dentry, uid_t user, gid_t group)
 	return error;
 }
 
-asmlinkage long sys_chown(const char __user * filename, uid_t user, gid_t group)
+SYSCALL_DEFINE3(chown, const char __user *, filename, uid_t, user, gid_t, group)
 {
 	struct path path;
 	int error;
@@ -732,7 +732,7 @@ out:
 	return error;
 }
 
-asmlinkage long sys_lchown(const char __user * filename, uid_t user, gid_t group)
+SYSCALL_DEFINE3(lchown, const char __user *, filename, uid_t, user, gid_t, group)
 {
 	struct path path;
 	int error;
@@ -751,8 +751,7 @@ out:
 	return error;
 }
 
-
-asmlinkage long sys_fchown(unsigned int fd, uid_t user, gid_t group)
+SYSCALL_DEFINE3(fchown, unsigned int, fd, uid_t, user, gid_t, group)
 {
 	struct file * file;
 	int error = -EBADF;
@@ -1048,7 +1047,7 @@ long do_sys_open(int dfd, const char __user *filename, int flags, int mode)
 	return fd;
 }
 
-asmlinkage long sys_open(const char __user *filename, int flags, int mode)
+SYSCALL_DEFINE3(open, const char __user *, filename, int, flags, int, mode)
 {
 	long ret;
 
@@ -1117,7 +1116,7 @@ EXPORT_SYMBOL(filp_close);
  * releasing the fd. This ensures that one clone task can't release
  * an fd while another clone is opening it.
  */
-asmlinkage long sys_close(unsigned int fd)
+SYSCALL_DEFINE1(close, unsigned int, fd)
 {
 	struct file * filp;
 	struct files_struct *files = current->files;
@@ -1150,14 +1149,13 @@ out_unlock:
 	spin_unlock(&files->file_lock);
 	return -EBADF;
 }
-
 EXPORT_SYMBOL(sys_close);
 
 /*
  * This routine simulates a hangup on the tty, to arrange that users
  * are given clean terminals at login time.
  */
-asmlinkage long sys_vhangup(void)
+SYSCALL_DEFINE0(vhangup)
 {
 	if (capable(CAP_SYS_TTY_CONFIG)) {
 		tty_vhangup_self();
diff --git a/kernel/uid16.c b/kernel/uid16.c
index 2460c3199b5a..37f48c049a2a 100644
--- a/kernel/uid16.c
+++ b/kernel/uid16.c
@@ -17,7 +17,7 @@
 
 #include <asm/uaccess.h>
 
-asmlinkage long sys_chown16(const char __user * filename, old_uid_t user, old_gid_t group)
+SYSCALL_DEFINE3(chown16, const char __user *, filename, old_uid_t, user, old_gid_t, group)
 {
 	long ret = sys_chown(filename, low2highuid(user), low2highgid(group));
 	/* avoid REGPARM breakage on x86: */
@@ -25,7 +25,7 @@ asmlinkage long sys_chown16(const char __user * filename, old_uid_t user, old_gi
 	return ret;
 }
 
-asmlinkage long sys_lchown16(const char __user * filename, old_uid_t user, old_gid_t group)
+SYSCALL_DEFINE3(lchown16, const char __user *, filename, old_uid_t, user, old_gid_t, group)
 {
 	long ret = sys_lchown(filename, low2highuid(user), low2highgid(group));
 	/* avoid REGPARM breakage on x86: */
@@ -33,7 +33,7 @@ asmlinkage long sys_lchown16(const char __user * filename, old_uid_t user, old_g
 	return ret;
 }
 
-asmlinkage long sys_fchown16(unsigned int fd, old_uid_t user, old_gid_t group)
+SYSCALL_DEFINE3(fchown16, unsigned int, fd, old_uid_t, user, old_gid_t, group)
 {
 	long ret = sys_fchown(fd, low2highuid(user), low2highgid(group));
 	/* avoid REGPARM breakage on x86: */
-- 
cgit v1.2.3


From a6b42e83f249aad723589b2bdf6d1dfb2b0997c8 Mon Sep 17 00:00:00 2001
From: Heiko Carstens <heiko.carstens@de.ibm.com>
Date: Wed, 14 Jan 2009 14:14:20 +0100
Subject: [CVE-2009-0029] System call wrappers part 18

Signed-off-by: Heiko Carstens <heiko.carstens@de.ibm.com>
---
 kernel/uid16.c | 21 +++++++++++----------
 1 file changed, 11 insertions(+), 10 deletions(-)

(limited to 'kernel')

diff --git a/kernel/uid16.c b/kernel/uid16.c
index 37f48c049a2a..221894e6e980 100644
--- a/kernel/uid16.c
+++ b/kernel/uid16.c
@@ -41,7 +41,7 @@ SYSCALL_DEFINE3(fchown16, unsigned int, fd, old_uid_t, user, old_gid_t, group)
 	return ret;
 }
 
-asmlinkage long sys_setregid16(old_gid_t rgid, old_gid_t egid)
+SYSCALL_DEFINE2(setregid16, old_gid_t, rgid, old_gid_t, egid)
 {
 	long ret = sys_setregid(low2highgid(rgid), low2highgid(egid));
 	/* avoid REGPARM breakage on x86: */
@@ -49,7 +49,7 @@ asmlinkage long sys_setregid16(old_gid_t rgid, old_gid_t egid)
 	return ret;
 }
 
-asmlinkage long sys_setgid16(old_gid_t gid)
+SYSCALL_DEFINE1(setgid16, old_gid_t, gid)
 {
 	long ret = sys_setgid(low2highgid(gid));
 	/* avoid REGPARM breakage on x86: */
@@ -57,7 +57,7 @@ asmlinkage long sys_setgid16(old_gid_t gid)
 	return ret;
 }
 
-asmlinkage long sys_setreuid16(old_uid_t ruid, old_uid_t euid)
+SYSCALL_DEFINE2(setreuid16, old_uid_t, ruid, old_uid_t, euid)
 {
 	long ret = sys_setreuid(low2highuid(ruid), low2highuid(euid));
 	/* avoid REGPARM breakage on x86: */
@@ -65,7 +65,7 @@ asmlinkage long sys_setreuid16(old_uid_t ruid, old_uid_t euid)
 	return ret;
 }
 
-asmlinkage long sys_setuid16(old_uid_t uid)
+SYSCALL_DEFINE1(setuid16, old_uid_t, uid)
 {
 	long ret = sys_setuid(low2highuid(uid));
 	/* avoid REGPARM breakage on x86: */
@@ -73,7 +73,7 @@ asmlinkage long sys_setuid16(old_uid_t uid)
 	return ret;
 }
 
-asmlinkage long sys_setresuid16(old_uid_t ruid, old_uid_t euid, old_uid_t suid)
+SYSCALL_DEFINE3(setresuid16, old_uid_t, ruid, old_uid_t, euid, old_uid_t, suid)
 {
 	long ret = sys_setresuid(low2highuid(ruid), low2highuid(euid),
 				 low2highuid(suid));
@@ -82,7 +82,7 @@ asmlinkage long sys_setresuid16(old_uid_t ruid, old_uid_t euid, old_uid_t suid)
 	return ret;
 }
 
-asmlinkage long sys_getresuid16(old_uid_t __user *ruid, old_uid_t __user *euid, old_uid_t __user *suid)
+SYSCALL_DEFINE3(getresuid16, old_uid_t __user *, ruid, old_uid_t __user *, euid, old_uid_t __user *, suid)
 {
 	const struct cred *cred = current_cred();
 	int retval;
@@ -94,7 +94,7 @@ asmlinkage long sys_getresuid16(old_uid_t __user *ruid, old_uid_t __user *euid,
 	return retval;
 }
 
-asmlinkage long sys_setresgid16(old_gid_t rgid, old_gid_t egid, old_gid_t sgid)
+SYSCALL_DEFINE3(setresgid16, old_gid_t, rgid, old_gid_t, egid, old_gid_t, sgid)
 {
 	long ret = sys_setresgid(low2highgid(rgid), low2highgid(egid),
 				 low2highgid(sgid));
@@ -103,7 +103,8 @@ asmlinkage long sys_setresgid16(old_gid_t rgid, old_gid_t egid, old_gid_t sgid)
 	return ret;
 }
 
-asmlinkage long sys_getresgid16(old_gid_t __user *rgid, old_gid_t __user *egid, old_gid_t __user *sgid)
+
+SYSCALL_DEFINE3(getresgid16, old_gid_t __user *, rgid, old_gid_t __user *, egid, old_gid_t __user *, sgid)
 {
 	const struct cred *cred = current_cred();
 	int retval;
@@ -115,7 +116,7 @@ asmlinkage long sys_getresgid16(old_gid_t __user *rgid, old_gid_t __user *egid,
 	return retval;
 }
 
-asmlinkage long sys_setfsuid16(old_uid_t uid)
+SYSCALL_DEFINE1(setfsuid16, old_uid_t, uid)
 {
 	long ret = sys_setfsuid(low2highuid(uid));
 	/* avoid REGPARM breakage on x86: */
@@ -123,7 +124,7 @@ asmlinkage long sys_setfsuid16(old_uid_t uid)
 	return ret;
 }
 
-asmlinkage long sys_setfsgid16(old_gid_t gid)
+SYSCALL_DEFINE1(setfsgid16, old_gid_t, gid)
 {
 	long ret = sys_setfsgid(low2highgid(gid));
 	/* avoid REGPARM breakage on x86: */
-- 
cgit v1.2.3


From 003d7ab479168132a2b2c6700fe682b08f08ab0c Mon Sep 17 00:00:00 2001
From: Heiko Carstens <heiko.carstens@de.ibm.com>
Date: Wed, 14 Jan 2009 14:14:21 +0100
Subject: [CVE-2009-0029] System call wrappers part 19

Signed-off-by: Heiko Carstens <heiko.carstens@de.ibm.com>
---
 fs/read_write.c |  8 ++++----
 fs/utimes.c     |  5 +++--
 kernel/uid16.c  | 12 ++++++------
 3 files changed, 13 insertions(+), 12 deletions(-)

(limited to 'kernel')

diff --git a/fs/read_write.c b/fs/read_write.c
index 0671aa016b6f..fad10af59d95 100644
--- a/fs/read_write.c
+++ b/fs/read_write.c
@@ -147,7 +147,7 @@ loff_t vfs_llseek(struct file *file, loff_t offset, int origin)
 }
 EXPORT_SYMBOL(vfs_llseek);
 
-asmlinkage long sys_lseek(unsigned int fd, off_t offset, unsigned int origin)
+SYSCALL_DEFINE3(lseek, unsigned int, fd, off_t, offset, unsigned int, origin)
 {
 	off_t retval;
 	struct file * file;
@@ -171,9 +171,9 @@ bad:
 }
 
 #ifdef __ARCH_WANT_SYS_LLSEEK
-asmlinkage long sys_llseek(unsigned int fd, unsigned long offset_high,
-			   unsigned long offset_low, loff_t __user * result,
-			   unsigned int origin)
+SYSCALL_DEFINE5(llseek, unsigned int, fd, unsigned long, offset_high,
+		unsigned long, offset_low, loff_t __user *, result,
+		unsigned int, origin)
 {
 	int retval;
 	struct file * file;
diff --git a/fs/utimes.c b/fs/utimes.c
index 6929e3e91d05..ee853615798a 100644
--- a/fs/utimes.c
+++ b/fs/utimes.c
@@ -24,7 +24,7 @@
  * must be owner or have write permission.
  * Else, update from *times, must be owner or super user.
  */
-asmlinkage long sys_utime(char __user *filename, struct utimbuf __user *times)
+SYSCALL_DEFINE2(utime, char __user *, filename, struct utimbuf __user *, times)
 {
 	struct timespec tv[2];
 
@@ -214,7 +214,8 @@ asmlinkage long sys_futimesat(int dfd, char __user *filename, struct timeval __u
 	return do_utimes(dfd, filename, utimes ? tstimes : NULL, 0);
 }
 
-asmlinkage long sys_utimes(char __user *filename, struct timeval __user *utimes)
+SYSCALL_DEFINE2(utimes, char __user *, filename,
+		struct timeval __user *, utimes)
 {
 	return sys_futimesat(AT_FDCWD, filename, utimes);
 }
diff --git a/kernel/uid16.c b/kernel/uid16.c
index 221894e6e980..0314501688b9 100644
--- a/kernel/uid16.c
+++ b/kernel/uid16.c
@@ -162,7 +162,7 @@ static int groups16_from_user(struct group_info *group_info,
 	return 0;
 }
 
-asmlinkage long sys_getgroups16(int gidsetsize, old_gid_t __user *grouplist)
+SYSCALL_DEFINE2(getgroups16, int, gidsetsize, old_gid_t __user *, grouplist)
 {
 	const struct cred *cred = current_cred();
 	int i;
@@ -185,7 +185,7 @@ out:
 	return i;
 }
 
-asmlinkage long sys_setgroups16(int gidsetsize, old_gid_t __user *grouplist)
+SYSCALL_DEFINE2(setgroups16, int, gidsetsize, old_gid_t __user *, grouplist)
 {
 	struct group_info *group_info;
 	int retval;
@@ -210,22 +210,22 @@ asmlinkage long sys_setgroups16(int gidsetsize, old_gid_t __user *grouplist)
 	return retval;
 }
 
-asmlinkage long sys_getuid16(void)
+SYSCALL_DEFINE0(getuid16)
 {
 	return high2lowuid(current_uid());
 }
 
-asmlinkage long sys_geteuid16(void)
+SYSCALL_DEFINE0(geteuid16)
 {
 	return high2lowuid(current_euid());
 }
 
-asmlinkage long sys_getgid16(void)
+SYSCALL_DEFINE0(getgid16)
 {
 	return high2lowgid(current_gid());
 }
 
-asmlinkage long sys_getegid16(void)
+SYSCALL_DEFINE0(getegid16)
 {
 	return high2lowgid(current_egid());
 }
-- 
cgit v1.2.3


From 5a8a82b1d306a325d899b67715618413657efda4 Mon Sep 17 00:00:00 2001
From: Heiko Carstens <heiko.carstens@de.ibm.com>
Date: Wed, 14 Jan 2009 14:14:25 +0100
Subject: [CVE-2009-0029] System call wrappers part 23

Signed-off-by: Heiko Carstens <heiko.carstens@de.ibm.com>
---
 fs/eventpoll.c | 18 +++++++++---------
 fs/select.c    |  8 ++++----
 kernel/sys.c   |  6 +++---
 3 files changed, 16 insertions(+), 16 deletions(-)

(limited to 'kernel')

diff --git a/fs/eventpoll.c b/fs/eventpoll.c
index 96355d505347..ba2f9ec71192 100644
--- a/fs/eventpoll.c
+++ b/fs/eventpoll.c
@@ -1110,7 +1110,7 @@ retry:
 /*
  * Open an eventpoll file descriptor.
  */
-asmlinkage long sys_epoll_create1(int flags)
+SYSCALL_DEFINE1(epoll_create1, int, flags)
 {
 	int error, fd = -1;
 	struct eventpoll *ep;
@@ -1150,7 +1150,7 @@ error_return:
 	return fd;
 }
 
-asmlinkage long sys_epoll_create(int size)
+SYSCALL_DEFINE1(epoll_create, int, size)
 {
 	if (size < 0)
 		return -EINVAL;
@@ -1163,8 +1163,8 @@ asmlinkage long sys_epoll_create(int size)
  * the eventpoll file that enables the insertion/removal/change of
  * file descriptors inside the interest set.
  */
-asmlinkage long sys_epoll_ctl(int epfd, int op, int fd,
-			      struct epoll_event __user *event)
+SYSCALL_DEFINE4(epoll_ctl, int, epfd, int, op, int, fd,
+		struct epoll_event __user *, event)
 {
 	int error;
 	struct file *file, *tfile;
@@ -1261,8 +1261,8 @@ error_return:
  * Implement the event wait interface for the eventpoll file. It is the kernel
  * part of the user space epoll_wait(2).
  */
-asmlinkage long sys_epoll_wait(int epfd, struct epoll_event __user *events,
-			       int maxevents, int timeout)
+SYSCALL_DEFINE4(epoll_wait, int, epfd, struct epoll_event __user *, events,
+		int, maxevents, int, timeout)
 {
 	int error;
 	struct file *file;
@@ -1319,9 +1319,9 @@ error_return:
  * Implement the event wait interface for the eventpoll file. It is the kernel
  * part of the user space epoll_pwait(2).
  */
-asmlinkage long sys_epoll_pwait(int epfd, struct epoll_event __user *events,
-		int maxevents, int timeout, const sigset_t __user *sigmask,
-		size_t sigsetsize)
+SYSCALL_DEFINE6(epoll_pwait, int, epfd, struct epoll_event __user *, events,
+		int, maxevents, int, timeout, const sigset_t __user *, sigmask,
+		size_t, sigsetsize)
 {
 	int error;
 	sigset_t ksigmask, sigsaved;
diff --git a/fs/select.c b/fs/select.c
index d1651648be11..338f703403af 100644
--- a/fs/select.c
+++ b/fs/select.c
@@ -557,8 +557,8 @@ out_nofds:
 	return ret;
 }
 
-asmlinkage long sys_select(int n, fd_set __user *inp, fd_set __user *outp,
-			fd_set __user *exp, struct timeval __user *tvp)
+SYSCALL_DEFINE5(select, int, n, fd_set __user *, inp, fd_set __user *, outp,
+		fd_set __user *, exp, struct timeval __user *, tvp)
 {
 	struct timespec end_time, *to = NULL;
 	struct timeval tv;
@@ -854,8 +854,8 @@ static long do_restart_poll(struct restart_block *restart_block)
 	return ret;
 }
 
-asmlinkage long sys_poll(struct pollfd __user *ufds, unsigned int nfds,
-			long timeout_msecs)
+SYSCALL_DEFINE3(poll, struct pollfd __user *, ufds, unsigned int, nfds,
+		long, timeout_msecs)
 {
 	struct timespec end_time, *to = NULL;
 	int ret;
diff --git a/kernel/sys.c b/kernel/sys.c
index 39b192b40034..5292f2119da4 100644
--- a/kernel/sys.c
+++ b/kernel/sys.c
@@ -1406,7 +1406,7 @@ asmlinkage long sys_newuname(struct new_utsname __user * name)
 	return errno;
 }
 
-asmlinkage long sys_sethostname(char __user *name, int len)
+SYSCALL_DEFINE2(sethostname, char __user *, name, int, len)
 {
 	int errno;
 	char tmp[__NEW_UTS_LEN];
@@ -1430,7 +1430,7 @@ asmlinkage long sys_sethostname(char __user *name, int len)
 
 #ifdef __ARCH_WANT_SYS_GETHOSTNAME
 
-asmlinkage long sys_gethostname(char __user *name, int len)
+SYSCALL_DEFINE2(gethostname, char __user *, name, int, len)
 {
 	int i, errno;
 	struct new_utsname *u;
@@ -1455,7 +1455,7 @@ asmlinkage long sys_gethostname(char __user *name, int len)
  * Only setdomainname; getdomainname can be implemented by calling
  * uname()
  */
-asmlinkage long sys_setdomainname(char __user *name, int len)
+SYSCALL_DEFINE2(setdomainname, char __user *, name, int, len)
 {
 	int errno;
 	char tmp[__NEW_UTS_LEN];
-- 
cgit v1.2.3


From e48fbb699f82ef1e80bd7126046394d2dc9ca7e6 Mon Sep 17 00:00:00 2001
From: Heiko Carstens <heiko.carstens@de.ibm.com>
Date: Wed, 14 Jan 2009 14:14:26 +0100
Subject: [CVE-2009-0029] System call wrappers part 24

Signed-off-by: Heiko Carstens <heiko.carstens@de.ibm.com>
---
 ipc/msg.c    | 12 ++++++------
 kernel/sys.c | 13 +++++++------
 2 files changed, 13 insertions(+), 12 deletions(-)

(limited to 'kernel')

diff --git a/ipc/msg.c b/ipc/msg.c
index b4eee1c6101d..2ceab7f12fcb 100644
--- a/ipc/msg.c
+++ b/ipc/msg.c
@@ -309,7 +309,7 @@ static inline int msg_security(struct kern_ipc_perm *ipcp, int msgflg)
 	return security_msg_queue_associate(msq, msgflg);
 }
 
-asmlinkage long sys_msgget(key_t key, int msgflg)
+SYSCALL_DEFINE2(msgget, key_t, key, int, msgflg)
 {
 	struct ipc_namespace *ns;
 	struct ipc_ops msg_ops;
@@ -466,7 +466,7 @@ out_up:
 	return err;
 }
 
-asmlinkage long sys_msgctl(int msqid, int cmd, struct msqid_ds __user *buf)
+SYSCALL_DEFINE3(msgctl, int, msqid, int, cmd, struct msqid_ds __user *, buf)
 {
 	struct msg_queue *msq;
 	int err, version;
@@ -723,8 +723,8 @@ out_free:
 	return err;
 }
 
-asmlinkage long
-sys_msgsnd(int msqid, struct msgbuf __user *msgp, size_t msgsz, int msgflg)
+SYSCALL_DEFINE4(msgsnd, int, msqid, struct msgbuf __user *, msgp, size_t, msgsz,
+		int, msgflg)
 {
 	long mtype;
 
@@ -904,8 +904,8 @@ out_unlock:
 	return msgsz;
 }
 
-asmlinkage long sys_msgrcv(int msqid, struct msgbuf __user *msgp, size_t msgsz,
-			   long msgtyp, int msgflg)
+SYSCALL_DEFINE5(msgrcv, int, msqid, struct msgbuf __user *, msgp, size_t, msgsz,
+		long, msgtyp, int, msgflg)
 {
 	long err, mtype;
 
diff --git a/kernel/sys.c b/kernel/sys.c
index 5292f2119da4..70ffa8408cd4 100644
--- a/kernel/sys.c
+++ b/kernel/sys.c
@@ -1395,7 +1395,7 @@ EXPORT_SYMBOL(in_egroup_p);
 
 DECLARE_RWSEM(uts_sem);
 
-asmlinkage long sys_newuname(struct new_utsname __user * name)
+SYSCALL_DEFINE1(newuname, struct new_utsname __user *, name)
 {
 	int errno = 0;
 
@@ -1478,7 +1478,7 @@ SYSCALL_DEFINE2(setdomainname, char __user *, name, int, len)
 	return errno;
 }
 
-asmlinkage long sys_getrlimit(unsigned int resource, struct rlimit __user *rlim)
+SYSCALL_DEFINE2(getrlimit, unsigned int, resource, struct rlimit __user *, rlim)
 {
 	if (resource >= RLIM_NLIMITS)
 		return -EINVAL;
@@ -1497,7 +1497,8 @@ asmlinkage long sys_getrlimit(unsigned int resource, struct rlimit __user *rlim)
  *	Back compatibility for getrlimit. Needed for some apps.
  */
  
-asmlinkage long sys_old_getrlimit(unsigned int resource, struct rlimit __user *rlim)
+SYSCALL_DEFINE2(old_getrlimit, unsigned int, resource,
+		struct rlimit __user *, rlim)
 {
 	struct rlimit x;
 	if (resource >= RLIM_NLIMITS)
@@ -1515,7 +1516,7 @@ asmlinkage long sys_old_getrlimit(unsigned int resource, struct rlimit __user *r
 
 #endif
 
-asmlinkage long sys_setrlimit(unsigned int resource, struct rlimit __user *rlim)
+SYSCALL_DEFINE2(setrlimit, unsigned int, resource, struct rlimit __user *, rlim)
 {
 	struct rlimit new_rlim, *old_rlim;
 	int retval;
@@ -1688,7 +1689,7 @@ int getrusage(struct task_struct *p, int who, struct rusage __user *ru)
 	return copy_to_user(ru, &r, sizeof(r)) ? -EFAULT : 0;
 }
 
-asmlinkage long sys_getrusage(int who, struct rusage __user *ru)
+SYSCALL_DEFINE2(getrusage, int, who, struct rusage __user *, ru)
 {
 	if (who != RUSAGE_SELF && who != RUSAGE_CHILDREN &&
 	    who != RUSAGE_THREAD)
@@ -1696,7 +1697,7 @@ asmlinkage long sys_getrusage(int who, struct rusage __user *ru)
 	return getrusage(current, who, ru);
 }
 
-asmlinkage long sys_umask(int mask)
+SYSCALL_DEFINE1(umask, int, mask)
 {
 	mask = xchg(&current->fs->umask, mask & S_IRWXUGO);
 	return mask;
-- 
cgit v1.2.3


From c4ea37c26a691ad0b7e86aa5884aab27830e95c9 Mon Sep 17 00:00:00 2001
From: Heiko Carstens <heiko.carstens@de.ibm.com>
Date: Wed, 14 Jan 2009 14:14:28 +0100
Subject: [CVE-2009-0029] System call wrappers part 26

Signed-off-by: Heiko Carstens <heiko.carstens@de.ibm.com>
---
 drivers/pci/syscall.c | 12 ++++--------
 ipc/mqueue.c          | 22 +++++++++++-----------
 kernel/sys.c          |  4 ++--
 mm/swapfile.c         |  4 ++--
 4 files changed, 19 insertions(+), 23 deletions(-)

(limited to 'kernel')

diff --git a/drivers/pci/syscall.c b/drivers/pci/syscall.c
index 645d7a60e412..ec22284eed30 100644
--- a/drivers/pci/syscall.c
+++ b/drivers/pci/syscall.c
@@ -14,10 +14,8 @@
 #include <asm/uaccess.h>
 #include "pci.h"
 
-asmlinkage long
-sys_pciconfig_read(unsigned long bus, unsigned long dfn,
-		   unsigned long off, unsigned long len,
-		   void __user *buf)
+SYSCALL_DEFINE5(pciconfig_read, unsigned long, bus, unsigned long, dfn,
+		unsigned long, off, unsigned long, len, void __user *, buf)
 {
 	struct pci_dev *dev;
 	u8 byte;
@@ -86,10 +84,8 @@ error:
 	return err;
 }
 
-asmlinkage long
-sys_pciconfig_write(unsigned long bus, unsigned long dfn,
-		    unsigned long off, unsigned long len,
-		    void __user *buf)
+SYSCALL_DEFINE5(pciconfig_write, unsigned long, bus, unsigned long, dfn,
+		unsigned long, off, unsigned long, len, void __user *, buf)
 {
 	struct pci_dev *dev;
 	u8 byte;
diff --git a/ipc/mqueue.c b/ipc/mqueue.c
index faac04c85e74..54b4077fed79 100644
--- a/ipc/mqueue.c
+++ b/ipc/mqueue.c
@@ -814,9 +814,9 @@ static inline void pipelined_receive(struct mqueue_inode_info *info)
 	sender->state = STATE_READY;
 }
 
-asmlinkage long sys_mq_timedsend(mqd_t mqdes, const char __user *u_msg_ptr,
-	size_t msg_len, unsigned int msg_prio,
-	const struct timespec __user *u_abs_timeout)
+SYSCALL_DEFINE5(mq_timedsend, mqd_t, mqdes, const char __user *, u_msg_ptr,
+		size_t, msg_len, unsigned int, msg_prio,
+		const struct timespec __user *, u_abs_timeout)
 {
 	struct file *filp;
 	struct inode *inode;
@@ -907,9 +907,9 @@ out:
 	return ret;
 }
 
-asmlinkage long sys_mq_timedreceive(mqd_t mqdes, char __user *u_msg_ptr,
-	size_t msg_len, unsigned int __user *u_msg_prio,
-	const struct timespec __user *u_abs_timeout)
+SYSCALL_DEFINE5(mq_timedreceive, mqd_t, mqdes, char __user *, u_msg_ptr,
+		size_t, msg_len, unsigned int __user *, u_msg_prio,
+		const struct timespec __user *, u_abs_timeout)
 {
 	long timeout;
 	ssize_t ret;
@@ -997,8 +997,8 @@ out:
  * and he isn't currently owner of notification, will be silently discarded.
  * It isn't explicitly defined in the POSIX.
  */
-asmlinkage long sys_mq_notify(mqd_t mqdes,
-				const struct sigevent __user *u_notification)
+SYSCALL_DEFINE2(mq_notify, mqd_t, mqdes,
+		const struct sigevent __user *, u_notification)
 {
 	int ret;
 	struct file *filp;
@@ -1123,9 +1123,9 @@ out:
 	return ret;
 }
 
-asmlinkage long sys_mq_getsetattr(mqd_t mqdes,
-			const struct mq_attr __user *u_mqstat,
-			struct mq_attr __user *u_omqstat)
+SYSCALL_DEFINE3(mq_getsetattr, mqd_t, mqdes,
+		const struct mq_attr __user *, u_mqstat,
+		struct mq_attr __user *, u_omqstat)
 {
 	int ret;
 	struct mq_attr mqstat, omqstat;
diff --git a/kernel/sys.c b/kernel/sys.c
index 70ffa8408cd4..59aadcdad6ce 100644
--- a/kernel/sys.c
+++ b/kernel/sys.c
@@ -1703,8 +1703,8 @@ SYSCALL_DEFINE1(umask, int, mask)
 	return mask;
 }
 
-asmlinkage long sys_prctl(int option, unsigned long arg2, unsigned long arg3,
-			  unsigned long arg4, unsigned long arg5)
+SYSCALL_DEFINE5(prctl, int, option, unsigned long, arg2, unsigned long, arg3,
+		unsigned long, arg4, unsigned long, arg5)
 {
 	struct task_struct *me = current;
 	unsigned char comm[sizeof(me->comm)];
diff --git a/mm/swapfile.c b/mm/swapfile.c
index da422c47e2ee..f48b831e5e5c 100644
--- a/mm/swapfile.c
+++ b/mm/swapfile.c
@@ -1377,7 +1377,7 @@ out:
 	return ret;
 }
 
-asmlinkage long sys_swapoff(const char __user * specialfile)
+SYSCALL_DEFINE1(swapoff, const char __user *, specialfile)
 {
 	struct swap_info_struct * p = NULL;
 	unsigned short *swap_map;
@@ -1633,7 +1633,7 @@ late_initcall(max_swapfiles_check);
  *
  * The swapon system call
  */
-asmlinkage long sys_swapon(const char __user * specialfile, int swap_flags)
+SYSCALL_DEFINE2(swapon, const char __user *, specialfile, int, swap_flags)
 {
 	struct swap_info_struct * p;
 	char *name = NULL;
-- 
cgit v1.2.3


From 1e7bfb2134dfec37ce04fb3a4ca89299e892d10c Mon Sep 17 00:00:00 2001
From: Heiko Carstens <heiko.carstens@de.ibm.com>
Date: Wed, 14 Jan 2009 14:14:29 +0100
Subject: [CVE-2009-0029] System call wrappers part 27

Signed-off-by: Heiko Carstens <heiko.carstens@de.ibm.com>
---
 fs/exec.c              |  2 +-
 fs/filesystems.c       |  2 +-
 fs/nfsctl.c            |  4 ++--
 kernel/printk.c        |  2 +-
 kernel/ptrace.c        |  2 +-
 kernel/sysctl.c        |  4 ++--
 kernel/timer.c         |  2 +-
 security/keys/keyctl.c | 18 +++++++++---------
 8 files changed, 18 insertions(+), 18 deletions(-)

(limited to 'kernel')

diff --git a/fs/exec.c b/fs/exec.c
index 71a6efe5d8bd..0dd60a01f1b4 100644
--- a/fs/exec.c
+++ b/fs/exec.c
@@ -99,7 +99,7 @@ static inline void put_binfmt(struct linux_binfmt * fmt)
  *
  * Also note that we take the address to load from from the file itself.
  */
-asmlinkage long sys_uselib(const char __user * library)
+SYSCALL_DEFINE1(uselib, const char __user *, library)
 {
 	struct file *file;
 	struct nameidata nd;
diff --git a/fs/filesystems.c b/fs/filesystems.c
index d488dcd7f2bb..1aa70260e6d1 100644
--- a/fs/filesystems.c
+++ b/fs/filesystems.c
@@ -179,7 +179,7 @@ static int fs_maxindex(void)
 /*
  * Whee.. Weird sysv syscall. 
  */
-asmlinkage long sys_sysfs(int option, unsigned long arg1, unsigned long arg2)
+SYSCALL_DEFINE3(sysfs, int, option, unsigned long, arg1, unsigned long, arg2)
 {
 	int retval = -EINVAL;
 
diff --git a/fs/nfsctl.c b/fs/nfsctl.c
index b27451909dff..8f9a20556f79 100644
--- a/fs/nfsctl.c
+++ b/fs/nfsctl.c
@@ -86,8 +86,8 @@ static struct {
 	},
 };
 
-long
-asmlinkage sys_nfsservctl(int cmd, struct nfsctl_arg __user *arg, void __user *res)
+SYSCALL_DEFINE3(nfsservctl, int, cmd, struct nfsctl_arg __user *, arg,
+		void __user *, res)
 {
 	struct file *file;
 	void __user *p = &arg->u;
diff --git a/kernel/printk.c b/kernel/printk.c
index e48cf33783fc..69188f226a93 100644
--- a/kernel/printk.c
+++ b/kernel/printk.c
@@ -382,7 +382,7 @@ out:
 	return error;
 }
 
-asmlinkage long sys_syslog(int type, char __user *buf, int len)
+SYSCALL_DEFINE3(syslog, int, type, char __user *, buf, int, len)
 {
 	return do_syslog(type, buf, len);
 }
diff --git a/kernel/ptrace.c b/kernel/ptrace.c
index 29dc700e198c..c9cf48b21f05 100644
--- a/kernel/ptrace.c
+++ b/kernel/ptrace.c
@@ -574,7 +574,7 @@ struct task_struct *ptrace_get_task_struct(pid_t pid)
 #define arch_ptrace_attach(child)	do { } while (0)
 #endif
 
-asmlinkage long sys_ptrace(long request, long pid, long addr, long data)
+SYSCALL_DEFINE4(ptrace, long, request, long, pid, long, addr, long, data)
 {
 	struct task_struct *child;
 	long ret;
diff --git a/kernel/sysctl.c b/kernel/sysctl.c
index 89d74436318c..3e38b74b6124 100644
--- a/kernel/sysctl.c
+++ b/kernel/sysctl.c
@@ -1688,7 +1688,7 @@ int do_sysctl(int __user *name, int nlen, void __user *oldval, size_t __user *ol
 	return error;
 }
 
-asmlinkage long sys_sysctl(struct __sysctl_args __user *args)
+SYSCALL_DEFINE1(sysctl, struct __sysctl_args __user *, args)
 {
 	struct __sysctl_args tmp;
 	int error;
@@ -2989,7 +2989,7 @@ int sysctl_ms_jiffies(struct ctl_table *table,
 #else /* CONFIG_SYSCTL_SYSCALL */
 
 
-asmlinkage long sys_sysctl(struct __sysctl_args __user *args)
+SYSCALL_DEFINE1(sysctl, struct __sysctl_args __user *, args)
 {
 	struct __sysctl_args tmp;
 	int error;
diff --git a/kernel/timer.c b/kernel/timer.c
index 14a51530a4cd..13dd64fe143d 100644
--- a/kernel/timer.c
+++ b/kernel/timer.c
@@ -1400,7 +1400,7 @@ out:
 	return 0;
 }
 
-asmlinkage long sys_sysinfo(struct sysinfo __user *info)
+SYSCALL_DEFINE1(sysinfo, struct sysinfo __user *, info)
 {
 	struct sysinfo val;
 
diff --git a/security/keys/keyctl.c b/security/keys/keyctl.c
index 09796797d122..070a53eab80f 100644
--- a/security/keys/keyctl.c
+++ b/security/keys/keyctl.c
@@ -54,11 +54,11 @@ static int key_get_type_from_user(char *type,
  * - returns the new key's serial number
  * - implements add_key()
  */
-asmlinkage long sys_add_key(const char __user *_type,
-			    const char __user *_description,
-			    const void __user *_payload,
-			    size_t plen,
-			    key_serial_t ringid)
+SYSCALL_DEFINE5(add_key, const char __user *, _type,
+		const char __user *, _description,
+		const void __user *, _payload,
+		size_t, plen,
+		key_serial_t, ringid)
 {
 	key_ref_t keyring_ref, key_ref;
 	char type[32], *description;
@@ -146,10 +146,10 @@ asmlinkage long sys_add_key(const char __user *_type,
  *   - if the _callout_info string is empty, it will be rendered as "-"
  * - implements request_key()
  */
-asmlinkage long sys_request_key(const char __user *_type,
-				const char __user *_description,
-				const char __user *_callout_info,
-				key_serial_t destringid)
+SYSCALL_DEFINE4(request_key, const char __user *, _type,
+		const char __user *, _description,
+		const char __user *, _callout_info,
+		key_serial_t, destringid)
 {
 	struct key_type *ktype;
 	struct key *key;
-- 
cgit v1.2.3


From 6559eed8ca7db0531a207cd80be5e28cd6f213c5 Mon Sep 17 00:00:00 2001
From: Heiko Carstens <heiko.carstens@de.ibm.com>
Date: Wed, 14 Jan 2009 14:14:32 +0100
Subject: [CVE-2009-0029] System call wrappers part 30

Signed-off-by: Heiko Carstens <heiko.carstens@de.ibm.com>
---
 fs/open.c     | 13 ++++++-------
 fs/stat.c     | 12 ++++++------
 fs/utimes.c   |  6 ++++--
 kernel/fork.c |  2 +-
 4 files changed, 17 insertions(+), 16 deletions(-)

(limited to 'kernel')

diff --git a/fs/open.c b/fs/open.c
index bc49e3c388d9..a3a78ceb2a2b 100644
--- a/fs/open.c
+++ b/fs/open.c
@@ -447,7 +447,7 @@ SYSCALL_ALIAS(sys_fallocate, SyS_fallocate);
  * We do this by temporarily clearing all FS-related capabilities and
  * switching the fsuid/fsgid around to the real ones.
  */
-asmlinkage long sys_faccessat(int dfd, const char __user *filename, int mode)
+SYSCALL_DEFINE3(faccessat, int, dfd, const char __user *, filename, int, mode)
 {
 	const struct cred *old_cred;
 	struct cred *override_cred;
@@ -628,8 +628,7 @@ out:
 	return err;
 }
 
-asmlinkage long sys_fchmodat(int dfd, const char __user *filename,
-			     mode_t mode)
+SYSCALL_DEFINE3(fchmodat, int, dfd, const char __user *, filename, mode_t, mode)
 {
 	struct path path;
 	struct inode *inode;
@@ -707,8 +706,8 @@ out:
 	return error;
 }
 
-asmlinkage long sys_fchownat(int dfd, const char __user *filename, uid_t user,
-			     gid_t group, int flag)
+SYSCALL_DEFINE5(fchownat, int, dfd, const char __user *, filename, uid_t, user,
+		gid_t, group, int, flag)
 {
 	struct path path;
 	int error = -EINVAL;
@@ -1060,8 +1059,8 @@ SYSCALL_DEFINE3(open, const char __user *, filename, int, flags, int, mode)
 	return ret;
 }
 
-asmlinkage long sys_openat(int dfd, const char __user *filename, int flags,
-			   int mode)
+SYSCALL_DEFINE4(openat, int, dfd, const char __user *, filename, int, flags,
+		int, mode)
 {
 	long ret;
 
diff --git a/fs/stat.c b/fs/stat.c
index d712a0dfb50f..2db740a0cfb5 100644
--- a/fs/stat.c
+++ b/fs/stat.c
@@ -260,8 +260,8 @@ SYSCALL_DEFINE2(newlstat, char __user *, filename, struct stat __user *, statbuf
 }
 
 #if !defined(__ARCH_WANT_STAT64) || defined(__ARCH_WANT_SYS_NEWFSTATAT)
-asmlinkage long sys_newfstatat(int dfd, char __user *filename,
-				struct stat __user *statbuf, int flag)
+SYSCALL_DEFINE4(newfstatat, int, dfd, char __user *, filename,
+		struct stat __user *, statbuf, int, flag)
 {
 	struct kstat stat;
 	int error = -EINVAL;
@@ -293,8 +293,8 @@ SYSCALL_DEFINE2(newfstat, unsigned int, fd, struct stat __user *, statbuf)
 	return error;
 }
 
-asmlinkage long sys_readlinkat(int dfd, const char __user *pathname,
-				char __user *buf, int bufsiz)
+SYSCALL_DEFINE4(readlinkat, int, dfd, const char __user *, pathname,
+		char __user *, buf, int, bufsiz)
 {
 	struct path path;
 	int error;
@@ -400,8 +400,8 @@ SYSCALL_DEFINE2(fstat64, unsigned long, fd, struct stat64 __user *, statbuf)
 	return error;
 }
 
-asmlinkage long sys_fstatat64(int dfd, char __user *filename,
-			       struct stat64 __user *statbuf, int flag)
+SYSCALL_DEFINE4(fstatat64, int, dfd, char __user *, filename,
+		struct stat64 __user *, statbuf, int, flag)
 {
 	struct kstat stat;
 	int error = -EINVAL;
diff --git a/fs/utimes.c b/fs/utimes.c
index ee853615798a..e4c75db5d373 100644
--- a/fs/utimes.c
+++ b/fs/utimes.c
@@ -170,7 +170,8 @@ out:
 	return error;
 }
 
-asmlinkage long sys_utimensat(int dfd, char __user *filename, struct timespec __user *utimes, int flags)
+SYSCALL_DEFINE4(utimensat, int, dfd, char __user *, filename,
+		struct timespec __user *, utimes, int, flags)
 {
 	struct timespec tstimes[2];
 
@@ -187,7 +188,8 @@ asmlinkage long sys_utimensat(int dfd, char __user *filename, struct timespec __
 	return do_utimes(dfd, filename, utimes ? tstimes : NULL, flags);
 }
 
-asmlinkage long sys_futimesat(int dfd, char __user *filename, struct timeval __user *utimes)
+SYSCALL_DEFINE3(futimesat, int, dfd, char __user *, filename,
+		struct timeval __user *, utimes)
 {
 	struct timeval times[2];
 	struct timespec tstimes[2];
diff --git a/kernel/fork.c b/kernel/fork.c
index 8eb37d38c6a4..bf0cef8bbdf2 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -1603,7 +1603,7 @@ static int unshare_fd(unsigned long unshare_flags, struct files_struct **new_fdp
  * constructed. Here we are modifying the current, active,
  * task_struct.
  */
-asmlinkage long sys_unshare(unsigned long unshare_flags)
+SYSCALL_DEFINE1(unshare, unsigned long, unshare_flags)
 {
 	int err = 0;
 	struct fs_struct *fs, *new_fs = NULL;
-- 
cgit v1.2.3


From 836f92adf121f806e9beb5b6b88bd5c9c4ea3f24 Mon Sep 17 00:00:00 2001
From: Heiko Carstens <heiko.carstens@de.ibm.com>
Date: Wed, 14 Jan 2009 14:14:33 +0100
Subject: [CVE-2009-0029] System call wrappers part 31

Signed-off-by: Heiko Carstens <heiko.carstens@de.ibm.com>
---
 fs/signalfd.c  |  8 ++++----
 fs/splice.c    | 12 ++++++------
 fs/timerfd.c   |  8 ++++----
 kernel/futex.c | 11 +++++------
 kernel/sys.c   |  4 ++--
 5 files changed, 21 insertions(+), 22 deletions(-)

(limited to 'kernel')

diff --git a/fs/signalfd.c b/fs/signalfd.c
index 9c39bc7f8431..b07565c94386 100644
--- a/fs/signalfd.c
+++ b/fs/signalfd.c
@@ -205,8 +205,8 @@ static const struct file_operations signalfd_fops = {
 	.read		= signalfd_read,
 };
 
-asmlinkage long sys_signalfd4(int ufd, sigset_t __user *user_mask,
-			      size_t sizemask, int flags)
+SYSCALL_DEFINE4(signalfd4, int, ufd, sigset_t __user *, user_mask,
+		size_t, sizemask, int, flags)
 {
 	sigset_t sigmask;
 	struct signalfd_ctx *ctx;
@@ -259,8 +259,8 @@ asmlinkage long sys_signalfd4(int ufd, sigset_t __user *user_mask,
 	return ufd;
 }
 
-asmlinkage long sys_signalfd(int ufd, sigset_t __user *user_mask,
-			     size_t sizemask)
+SYSCALL_DEFINE3(signalfd, int, ufd, sigset_t __user *, user_mask,
+		size_t, sizemask)
 {
 	return sys_signalfd4(ufd, user_mask, sizemask, 0);
 }
diff --git a/fs/splice.c b/fs/splice.c
index a54b3e3f10a7..4ed0ba44a966 100644
--- a/fs/splice.c
+++ b/fs/splice.c
@@ -1435,8 +1435,8 @@ static long vmsplice_to_pipe(struct file *file, const struct iovec __user *iov,
  * Currently we punt and implement it as a normal copy, see pipe_to_user().
  *
  */
-asmlinkage long sys_vmsplice(int fd, const struct iovec __user *iov,
-			     unsigned long nr_segs, unsigned int flags)
+SYSCALL_DEFINE4(vmsplice, int, fd, const struct iovec __user *, iov,
+		unsigned long, nr_segs, unsigned int, flags)
 {
 	struct file *file;
 	long error;
@@ -1461,9 +1461,9 @@ asmlinkage long sys_vmsplice(int fd, const struct iovec __user *iov,
 	return error;
 }
 
-asmlinkage long sys_splice(int fd_in, loff_t __user *off_in,
-			   int fd_out, loff_t __user *off_out,
-			   size_t len, unsigned int flags)
+SYSCALL_DEFINE6(splice, int, fd_in, loff_t __user *, off_in,
+		int, fd_out, loff_t __user *, off_out,
+		size_t, len, unsigned int, flags)
 {
 	long error;
 	struct file *in, *out;
@@ -1685,7 +1685,7 @@ static long do_tee(struct file *in, struct file *out, size_t len,
 	return ret;
 }
 
-asmlinkage long sys_tee(int fdin, int fdout, size_t len, unsigned int flags)
+SYSCALL_DEFINE4(tee, int, fdin, int, fdout, size_t, len, unsigned int, flags)
 {
 	struct file *in;
 	int error, fput_in;
diff --git a/fs/timerfd.c b/fs/timerfd.c
index 0862f0e49d0c..c8c14f58b96f 100644
--- a/fs/timerfd.c
+++ b/fs/timerfd.c
@@ -177,7 +177,7 @@ static struct file *timerfd_fget(int fd)
 	return file;
 }
 
-asmlinkage long sys_timerfd_create(int clockid, int flags)
+SYSCALL_DEFINE2(timerfd_create, int, clockid, int, flags)
 {
 	int ufd;
 	struct timerfd_ctx *ctx;
@@ -208,9 +208,9 @@ asmlinkage long sys_timerfd_create(int clockid, int flags)
 	return ufd;
 }
 
-asmlinkage long sys_timerfd_settime(int ufd, int flags,
-				    const struct itimerspec __user *utmr,
-				    struct itimerspec __user *otmr)
+SYSCALL_DEFINE4(timerfd_settime, int, ufd, int, flags,
+		const struct itimerspec __user *, utmr,
+		struct itimerspec __user *, otmr)
 {
 	struct file *file;
 	struct timerfd_ctx *ctx;
diff --git a/kernel/futex.c b/kernel/futex.c
index e86931d8d4e9..f89d373a9c6d 100644
--- a/kernel/futex.c
+++ b/kernel/futex.c
@@ -1733,9 +1733,8 @@ pi_faulted:
  * @head: pointer to the list-head
  * @len: length of the list-head, as userspace expects
  */
-asmlinkage long
-sys_set_robust_list(struct robust_list_head __user *head,
-		    size_t len)
+SYSCALL_DEFINE2(set_robust_list, struct robust_list_head __user *, head,
+		size_t, len)
 {
 	if (!futex_cmpxchg_enabled)
 		return -ENOSYS;
@@ -1756,9 +1755,9 @@ sys_set_robust_list(struct robust_list_head __user *head,
  * @head_ptr: pointer to a list-head pointer, the kernel fills it in
  * @len_ptr: pointer to a length field, the kernel fills in the header size
  */
-asmlinkage long
-sys_get_robust_list(int pid, struct robust_list_head __user * __user *head_ptr,
-		    size_t __user *len_ptr)
+SYSCALL_DEFINE3(get_robust_list, int, pid,
+		struct robust_list_head __user * __user *, head_ptr,
+		size_t __user *, len_ptr)
 {
 	struct robust_list_head __user *head;
 	unsigned long ret;
diff --git a/kernel/sys.c b/kernel/sys.c
index 59aadcdad6ce..e7dc0e10a485 100644
--- a/kernel/sys.c
+++ b/kernel/sys.c
@@ -1817,8 +1817,8 @@ SYSCALL_DEFINE5(prctl, int, option, unsigned long, arg2, unsigned long, arg3,
 	return error;
 }
 
-asmlinkage long sys_getcpu(unsigned __user *cpup, unsigned __user *nodep,
-			   struct getcpu_cache __user *unused)
+SYSCALL_DEFINE3(getcpu, unsigned __user *, cpup, unsigned __user *, nodep,
+		struct getcpu_cache __user *, unused)
 {
 	int err = 0;
 	int cpu = raw_smp_processor_id();
-- 
cgit v1.2.3


From d4e82042c4cfa87a7d51710b71f568fe80132551 Mon Sep 17 00:00:00 2001
From: Heiko Carstens <heiko.carstens@de.ibm.com>
Date: Wed, 14 Jan 2009 14:14:34 +0100
Subject: [CVE-2009-0029] System call wrappers part 32

Signed-off-by: Heiko Carstens <heiko.carstens@de.ibm.com>
---
 fs/eventfd.c             |  5 ++---
 fs/pipe.c                |  2 +-
 fs/readdir.c             |  3 ++-
 fs/select.c              | 11 ++++++-----
 fs/timerfd.c             |  2 +-
 include/linux/syscalls.h |  7 +++++++
 kernel/signal.c          | 11 +++++------
 7 files changed, 24 insertions(+), 17 deletions(-)

(limited to 'kernel')

diff --git a/fs/eventfd.c b/fs/eventfd.c
index 08bf558d0408..5de2c2db3aa2 100644
--- a/fs/eventfd.c
+++ b/fs/eventfd.c
@@ -198,7 +198,7 @@ struct file *eventfd_fget(int fd)
 	return file;
 }
 
-asmlinkage long sys_eventfd2(unsigned int count, int flags)
+SYSCALL_DEFINE2(eventfd2, unsigned int, count, int, flags)
 {
 	int fd;
 	struct eventfd_ctx *ctx;
@@ -228,8 +228,7 @@ asmlinkage long sys_eventfd2(unsigned int count, int flags)
 	return fd;
 }
 
-asmlinkage long sys_eventfd(unsigned int count)
+SYSCALL_DEFINE1(eventfd, unsigned int, count)
 {
 	return sys_eventfd2(count, 0);
 }
-
diff --git a/fs/pipe.c b/fs/pipe.c
index 0c64db86c919..b89c878588a9 100644
--- a/fs/pipe.c
+++ b/fs/pipe.c
@@ -1043,7 +1043,7 @@ int do_pipe(int *fd)
  * sys_pipe() is the normal C calling standard for creating
  * a pipe. It's not the way Unix traditionally does this, though.
  */
-asmlinkage long sys_pipe2(int __user *fildes, int flags)
+SYSCALL_DEFINE2(pipe2, int __user *, fildes, int, flags)
 {
 	int fd[2];
 	int error;
diff --git a/fs/readdir.c b/fs/readdir.c
index cf6a0e39819a..7723401f8d8b 100644
--- a/fs/readdir.c
+++ b/fs/readdir.c
@@ -102,7 +102,8 @@ efault:
 	return -EFAULT;
 }
 
-asmlinkage long sys_old_readdir(unsigned int fd, struct old_linux_dirent __user * dirent, unsigned int count)
+SYSCALL_DEFINE3(old_readdir, unsigned int, fd,
+		struct old_linux_dirent __user *, dirent, unsigned int, count)
 {
 	int error;
 	struct file * file;
diff --git a/fs/select.c b/fs/select.c
index 338f703403af..0fe0e1469df3 100644
--- a/fs/select.c
+++ b/fs/select.c
@@ -636,8 +636,9 @@ static long do_pselect(int n, fd_set __user *inp, fd_set __user *outp,
  * which has a pointer to the sigset_t itself followed by a size_t containing
  * the sigset size.
  */
-asmlinkage long sys_pselect6(int n, fd_set __user *inp, fd_set __user *outp,
-	fd_set __user *exp, struct timespec __user *tsp, void __user *sig)
+SYSCALL_DEFINE6(pselect6, int, n, fd_set __user *, inp, fd_set __user *, outp,
+		fd_set __user *, exp, struct timespec __user *, tsp,
+		void __user *, sig)
 {
 	size_t sigsetsize = 0;
 	sigset_t __user *up = NULL;
@@ -889,9 +890,9 @@ SYSCALL_DEFINE3(poll, struct pollfd __user *, ufds, unsigned int, nfds,
 }
 
 #ifdef HAVE_SET_RESTORE_SIGMASK
-asmlinkage long sys_ppoll(struct pollfd __user *ufds, unsigned int nfds,
-	struct timespec __user *tsp, const sigset_t __user *sigmask,
-	size_t sigsetsize)
+SYSCALL_DEFINE5(ppoll, struct pollfd __user *, ufds, unsigned int, nfds,
+		struct timespec __user *, tsp, const sigset_t __user *, sigmask,
+		size_t, sigsetsize)
 {
 	sigset_t ksigmask, sigsaved;
 	struct timespec ts, end_time, *to = NULL;
diff --git a/fs/timerfd.c b/fs/timerfd.c
index c8c14f58b96f..6a123b8ff3f5 100644
--- a/fs/timerfd.c
+++ b/fs/timerfd.c
@@ -265,7 +265,7 @@ SYSCALL_DEFINE4(timerfd_settime, int, ufd, int, flags,
 	return 0;
 }
 
-asmlinkage long sys_timerfd_gettime(int ufd, struct itimerspec __user *otmr)
+SYSCALL_DEFINE2(timerfd_gettime, int, ufd, struct itimerspec __user *, otmr)
 {
 	struct file *file;
 	struct timerfd_ctx *ctx;
diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h
index 90aa5eba87a2..56c400138b05 100644
--- a/include/linux/syscalls.h
+++ b/include/linux/syscalls.h
@@ -678,6 +678,13 @@ asmlinkage long sys_eventfd(unsigned int count);
 asmlinkage long sys_eventfd2(unsigned int count, int flags);
 asmlinkage long sys_fallocate(int fd, int mode, loff_t offset, loff_t len);
 asmlinkage long sys_old_readdir(unsigned int, struct old_linux_dirent __user *, unsigned int);
+asmlinkage long sys_pselect6(int, fd_set __user *, fd_set __user *,
+			     fd_set __user *, struct timespec __user *,
+			     void __user *);
+asmlinkage long sys_ppoll(struct pollfd __user *, unsigned int,
+			  struct timespec __user *, const sigset_t __user *,
+			  size_t);
+asmlinkage long sys_pipe2(int __user *, int);
 
 int kernel_execve(const char *filename, char *const argv[], char *const envp[]);
 
diff --git a/kernel/signal.c b/kernel/signal.c
index e2333929611a..e73759783dc8 100644
--- a/kernel/signal.c
+++ b/kernel/signal.c
@@ -2491,11 +2491,10 @@ out:
 #endif /* __ARCH_WANT_SYS_SIGPROCMASK */
 
 #ifdef __ARCH_WANT_SYS_RT_SIGACTION
-asmlinkage long
-sys_rt_sigaction(int sig,
-		 const struct sigaction __user *act,
-		 struct sigaction __user *oact,
-		 size_t sigsetsize)
+SYSCALL_DEFINE4(rt_sigaction, int, sig,
+		const struct sigaction __user *, act,
+		struct sigaction __user *, oact,
+		size_t, sigsetsize)
 {
 	struct k_sigaction new_sa, old_sa;
 	int ret = -EINVAL;
@@ -2578,7 +2577,7 @@ SYSCALL_DEFINE0(pause)
 #endif
 
 #ifdef __ARCH_WANT_SYS_RT_SIGSUSPEND
-asmlinkage long sys_rt_sigsuspend(sigset_t __user *unewset, size_t sigsetsize)
+SYSCALL_DEFINE2(rt_sigsuspend, sigset_t __user *, unewset, size_t, sigsetsize)
 {
 	sigset_t newset;
 
-- 
cgit v1.2.3


From 9316fcacb89c59fe556c48587ac02cd7f5d38045 Mon Sep 17 00:00:00 2001
From: Andrew Morton <akpm@linux-foundation.org>
Date: Wed, 14 Jan 2009 09:35:44 -0800
Subject: kernel/up.c: omit it if SMP=y, USE_GENERIC_SMP_HELPERS=n

Fix the sparc build - we were including `up.o' on SMP builds, when
CONFIG_USE_GENERIC_SMP_HELPERS=n.

Tested-by: Robert Reif <reif@earthlink.net>
Fixed-by: Robert Reif <reif@earthlink.net>
Cc: David Miller <davem@davemloft.net>
Cc: Ingo Molnar <mingo@elte.hu>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 kernel/Makefile | 5 ++---
 1 file changed, 2 insertions(+), 3 deletions(-)

(limited to 'kernel')

diff --git a/kernel/Makefile b/kernel/Makefile
index 2aebc4cd7878..170a9213c1b6 100644
--- a/kernel/Makefile
+++ b/kernel/Makefile
@@ -40,9 +40,8 @@ obj-$(CONFIG_RT_MUTEXES) += rtmutex.o
 obj-$(CONFIG_DEBUG_RT_MUTEXES) += rtmutex-debug.o
 obj-$(CONFIG_RT_MUTEX_TESTER) += rtmutex-tester.o
 obj-$(CONFIG_GENERIC_ISA_DMA) += dma.o
-ifeq ($(CONFIG_USE_GENERIC_SMP_HELPERS),y)
-obj-y += smp.o
-else
+obj-$(CONFIG_USE_GENERIC_SMP_HELPERS) += smp.o
+ifneq ($(CONFIG_SMP),y)
 obj-y += up.o
 endif
 obj-$(CONFIG_SMP) += spinlock.o
-- 
cgit v1.2.3


From 2ea038917bbdd51a7ae4a898c6a04641324dd033 Mon Sep 17 00:00:00 2001
From: Sam Ravnborg <sam@ravnborg.org>
Date: Wed, 14 Jan 2009 21:38:20 +0100
Subject: Revert "kbuild: strip generated symbols from *.ko"

This reverts commit ad7a953c522ceb496611d127e51e278bfe0ff483.

And commit: ("allow stripping of generated symbols under CONFIG_KALLSYMS_ALL")
            9bb482476c6c9d1ae033306440c51ceac93ea80c

These stripping patches has caused a set of issues:

1) People have reported compatibility issues with binutils due to
   lack of support for `--strip-unneeded-symbols' with objcopy 2.15.92.0.2
   Reported by: Wenji
2) ccache and distcc no longer works as expeced
   Reported by: Ted, Roland, + others
3) The installed modules increased a lot in size
   Reported by: Ted, Davej + others

Reported-by: Wenji Huang <wenji.huang@oracle.com>
Reported-by: "Theodore Ts'o" <tytso@mit.edu>
Reported-by: Dave Jones <davej@redhat.com>
Reported-by: Roland McGrath <roland@redhat.com>
Signed-off-by: Sam Ravnborg <sam@ravnborg.org>
---
 Makefile                            |  59 ++++-------
 arch/x86/scripts/strip-symbols      |   1 -
 init/Kconfig                        |   7 --
 kernel/kallsyms.c                   |  16 +--
 scripts/Makefile.build              |  55 ++++-------
 scripts/Makefile.modinst            |   3 +-
 scripts/genksyms/genksyms.c         |  21 ++--
 scripts/genksyms/keywords.c_shipped | 189 ++++++++++++++++++------------------
 scripts/genksyms/keywords.gperf     |   2 -
 scripts/kallsyms.c                  |  21 ++--
 scripts/mksysmap                    |   7 +-
 scripts/strip-symbols               |  22 -----
 12 files changed, 166 insertions(+), 237 deletions(-)
 delete mode 100644 arch/x86/scripts/strip-symbols
 delete mode 100644 scripts/strip-symbols

(limited to 'kernel')

diff --git a/Makefile b/Makefile
index c06e250eca18..c2c4bbeef59d 100644
--- a/Makefile
+++ b/Makefile
@@ -606,25 +606,20 @@ export	INSTALL_PATH ?= /boot
 MODLIB	= $(INSTALL_MOD_PATH)/lib/modules/$(KERNELRELEASE)
 export MODLIB
 
-strip-symbols := $(srctree)/scripts/strip-symbols \
-		 $(wildcard $(srctree)/arch/$(ARCH)/scripts/strip-symbols)
-
 #
-# INSTALL_MOD_STRIP, if defined, will cause modules to be stripped while
-# they get installed.  If INSTALL_MOD_STRIP is '1', then the default
-# options (see below) will be used.  Otherwise, INSTALL_MOD_STRIP will
-# be used as the option(s) to the objcopy command.
+#  INSTALL_MOD_STRIP, if defined, will cause modules to be
+#  stripped after they are installed.  If INSTALL_MOD_STRIP is '1', then
+#  the default option --strip-debug will be used.  Otherwise,
+#  INSTALL_MOD_STRIP will used as the options to the strip command.
+
 ifdef INSTALL_MOD_STRIP
 ifeq ($(INSTALL_MOD_STRIP),1)
-mod_strip_cmd = $(OBJCOPY) --strip-debug
-ifeq ($(CONFIG_KALLSYMS_ALL),$(CONFIG_KALLSYMS_STRIP_GENERATED))
-mod_strip_cmd += --wildcard $(addprefix --strip-symbols ,$(strip-symbols))
-endif
+mod_strip_cmd = $(STRIP) --strip-debug
 else
-mod_strip_cmd = $(OBJCOPY) $(INSTALL_MOD_STRIP)
+mod_strip_cmd = $(STRIP) $(INSTALL_MOD_STRIP)
 endif # INSTALL_MOD_STRIP=1
 else
-mod_strip_cmd = false
+mod_strip_cmd = true
 endif # INSTALL_MOD_STRIP
 export mod_strip_cmd
 
@@ -754,7 +749,6 @@ last_kallsyms := 2
 endif
 
 kallsyms.o := .tmp_kallsyms$(last_kallsyms).o
-kallsyms.h := $(wildcard include/config/kallsyms/*.h) $(wildcard include/config/kallsyms/*/*.h)
 
 define verify_kallsyms
 	$(Q)$(if $($(quiet)cmd_sysmap),                                      \
@@ -779,41 +773,24 @@ endef
 
 # Generate .S file with all kernel symbols
 quiet_cmd_kallsyms = KSYM    $@
-      cmd_kallsyms = { test $* -eq 0 || $(NM) -n $<; } \
-		     | $(KALLSYMS) $(if $(CONFIG_KALLSYMS_ALL),--all-symbols) >$@
-
-quiet_cmd_kstrip = STRIP   $@
-      cmd_kstrip = $(OBJCOPY) --wildcard $(addprefix --strip$(if $(CONFIG_RELOCATABLE),-unneeded)-symbols ,$(filter %/scripts/strip-symbols,$^)) $< $@
+      cmd_kallsyms = $(NM) -n $< | $(KALLSYMS) \
+                     $(if $(CONFIG_KALLSYMS_ALL),--all-symbols) > $@
 
-$(foreach n,0 1 2 3,.tmp_kallsyms$(n).o): KBUILD_AFLAGS += -Wa,--strip-local-absolute
-$(foreach n,0 1 2 3,.tmp_kallsyms$(n).o): %.o: %.S scripts FORCE
+.tmp_kallsyms1.o .tmp_kallsyms2.o .tmp_kallsyms3.o: %.o: %.S scripts FORCE
 	$(call if_changed_dep,as_o_S)
 
-ifeq ($(CONFIG_KALLSYMS_STRIP_GENERATED),y)
-strip-ext := .stripped
-endif
-
-.tmp_kallsyms%.S: .tmp_vmlinux%$(strip-ext) $(KALLSYMS) $(kallsyms.h)
+.tmp_kallsyms%.S: .tmp_vmlinux% $(KALLSYMS)
 	$(call cmd,kallsyms)
 
-# make -jN seems to have problems with intermediate files, see bug #3330.
-.SECONDARY: $(foreach n,1 2 3,.tmp_vmlinux$(n).stripped)
-.tmp_vmlinux%.stripped: .tmp_vmlinux% $(strip-symbols) $(kallsyms.h)
-	$(call cmd,kstrip)
-
-ifneq ($(CONFIG_DEBUG_INFO),y)
-.tmp_vmlinux%: LDFLAGS_vmlinux += -S
-endif
 # .tmp_vmlinux1 must be complete except kallsyms, so update vmlinux version
-.tmp_vmlinux%: $(vmlinux-lds) $(vmlinux-all) FORCE
-	$(if $(filter 1,$*),$(call if_changed_rule,ksym_ld),$(call if_changed,vmlinux__))
+.tmp_vmlinux1: $(vmlinux-lds) $(vmlinux-all) FORCE
+	$(call if_changed_rule,ksym_ld)
 
-.tmp_vmlinux0$(strip-ext):
-	$(Q)echo "placeholder" >$@
+.tmp_vmlinux2: $(vmlinux-lds) $(vmlinux-all) .tmp_kallsyms1.o FORCE
+	$(call if_changed,vmlinux__)
 
-.tmp_vmlinux1: .tmp_kallsyms0.o
-.tmp_vmlinux2: .tmp_kallsyms1.o
-.tmp_vmlinux3: .tmp_kallsyms2.o
+.tmp_vmlinux3: $(vmlinux-lds) $(vmlinux-all) .tmp_kallsyms2.o FORCE
+	$(call if_changed,vmlinux__)
 
 # Needs to visit scripts/ before $(KALLSYMS) can be used.
 $(KALLSYMS): scripts ;
diff --git a/arch/x86/scripts/strip-symbols b/arch/x86/scripts/strip-symbols
deleted file mode 100644
index a2f1ccb827c7..000000000000
--- a/arch/x86/scripts/strip-symbols
+++ /dev/null
@@ -1 +0,0 @@
-__cpu_vendor_dev_X86_VENDOR_*
diff --git a/init/Kconfig b/init/Kconfig
index a724a149bf3f..0e9924743a17 100644
--- a/init/Kconfig
+++ b/init/Kconfig
@@ -626,13 +626,6 @@ config KALLSYMS_ALL
 
 	   Say N.
 
-config KALLSYMS_STRIP_GENERATED
-	bool "Strip machine generated symbols from kallsyms"
-	depends on KALLSYMS_ALL
-	default y
-	help
-	  Say N if you want kallsyms to retain even machine generated symbols.
-
 config KALLSYMS_EXTRA_PASS
 	bool "Do an extra kallsyms pass"
 	depends on KALLSYMS
diff --git a/kernel/kallsyms.c b/kernel/kallsyms.c
index e694afa0eb8c..7b8b0f21a5b1 100644
--- a/kernel/kallsyms.c
+++ b/kernel/kallsyms.c
@@ -30,19 +30,20 @@
 #define all_var 0
 #endif
 
-extern const unsigned long kallsyms_addresses[];
-extern const u8 kallsyms_names[];
+/* These will be re-linked against their real values during the second link stage */
+extern const unsigned long kallsyms_addresses[] __attribute__((weak));
+extern const u8 kallsyms_names[] __attribute__((weak));
 
 /* tell the compiler that the count isn't in the small data section if the arch
  * has one (eg: FRV)
  */
 extern const unsigned long kallsyms_num_syms
-	__attribute__((__section__(".rodata")));
+__attribute__((weak, section(".rodata")));
 
-extern const u8 kallsyms_token_table[];
-extern const u16 kallsyms_token_index[];
+extern const u8 kallsyms_token_table[] __attribute__((weak));
+extern const u16 kallsyms_token_index[] __attribute__((weak));
 
-extern const unsigned long kallsyms_markers[];
+extern const unsigned long kallsyms_markers[] __attribute__((weak));
 
 static inline int is_kernel_inittext(unsigned long addr)
 {
@@ -167,6 +168,9 @@ static unsigned long get_symbol_pos(unsigned long addr,
 	unsigned long symbol_start = 0, symbol_end = 0;
 	unsigned long i, low, high, mid;
 
+	/* This kernel should never had been booted. */
+	BUG_ON(!kallsyms_addresses);
+
 	/* do a binary search on the sorted kallsyms_addresses array */
 	low = 0;
 	high = kallsyms_num_syms;
diff --git a/scripts/Makefile.build b/scripts/Makefile.build
index 5d900307de3e..c7de8b39fcf1 100644
--- a/scripts/Makefile.build
+++ b/scripts/Makefile.build
@@ -151,16 +151,16 @@ cmd_cc_i_c       = $(CPP) $(c_flags)   -o $@ $<
 $(obj)/%.i: $(src)/%.c FORCE
 	$(call if_changed_dep,cc_i_c)
 
-cmd_genksyms =                                                              \
+cmd_gensymtypes =                                                           \
     $(CPP) -D__GENKSYMS__ $(c_flags) $< |                                   \
-    $(GENKSYMS) -T $@ -A -a $(ARCH)                                         \
+    $(GENKSYMS) -T $@ -a $(ARCH)                                            \
      $(if $(KBUILD_PRESERVE),-p)                                            \
      $(if $(1),-r $(firstword $(wildcard $(@:.symtypes=.symref) /dev/null)))
 
 quiet_cmd_cc_symtypes_c = SYM $(quiet_modtag) $@
 cmd_cc_symtypes_c =                                                         \
     set -e;                                                                 \
-    $(call cmd_genksyms, true) >/dev/null;                                  \
+    $(call cmd_gensymtypes, true) >/dev/null;                               \
     test -s $@ || rm -f $@
 
 $(obj)/%.symtypes : $(src)/%.c FORCE
@@ -177,38 +177,28 @@ cmd_cc_o_c = $(CC) $(c_flags) -c -o $@ $<
 
 else
 # When module versioning is enabled the following steps are executed:
-# o compile a .tmp_<file>.s from <file>.c
-# o if .tmp_<file>.s doesn't contain a __ksymtab version, i.e. does
-#   not export symbols, we just assemble .tmp_<file>.s to <file>.o and
+# o compile a .tmp_<file>.o from <file>.c
+# o if .tmp_<file>.o doesn't contain a __ksymtab version, i.e. does
+#   not export symbols, we just rename .tmp_<file>.o to <file>.o and
 #   are done.
 # o otherwise, we calculate symbol versions using the good old
 #   genksyms on the preprocessed source and postprocess them in a way
-#   that they are usable as assembly source
-# o assemble <file>.o from .tmp_<file>.s forcing inclusion of directives
-#   defining the actual values of __crc_*, followed by objcopy-ing them
-#   to force these symbols to be local to permit stripping them later.
-s_file = $(@D)/.tmp_$(@F:.o=.s)
-v_file = $(@D)/.tmp_$(@F:.o=.v)
-tmp_o_file = $(@D)/.tmp_$(@F)
-no_g_c_flags = $(filter-out -g%,$(c_flags))
-
-cmd_cc_o_c = $(CC) $(c_flags) -S -o $(s_file) $<
+#   that they are usable as a linker script
+# o generate <file>.o from .tmp_<file>.o using the linker to
+#   replace the unresolved symbols __crc_exported_symbol with
+#   the actual value of the checksum generated by genksyms
 
+cmd_cc_o_c = $(CC) $(c_flags) -c -o $(@D)/.tmp_$(@F) $<
 cmd_modversions =							\
-	if grep -q __ksymtab $(s_file); then				\
-		if $(call cmd_genksyms, $(KBUILD_SYMTYPES)) > $(v_file) \
-		   && $(CC) $(no_g_c_flags) -c -Wa,$(v_file)		\
-			    -o $(tmp_o_file) $(s_file)			\
-		   && $(OBJCOPY) -L '__crc_*' -L '___crc_*' -w		\
-				 $(tmp_o_file) $@;			\
-		then							\
-			: ;						\
-		else							\
-			rm -f $@; exit 1;				\
-		fi;							\
+	if $(OBJDUMP) -h $(@D)/.tmp_$(@F) | grep -q __ksymtab; then	\
+		$(call cmd_gensymtypes, $(KBUILD_SYMTYPES))		\
+		    > $(@D)/.tmp_$(@F:.o=.ver);				\
+									\
+		$(LD) $(LDFLAGS) -r -o $@ $(@D)/.tmp_$(@F) 		\
+			-T $(@D)/.tmp_$(@F:.o=.ver);			\
+		rm -f $(@D)/.tmp_$(@F) $(@D)/.tmp_$(@F:.o=.ver);	\
 	else								\
-		rm -f $(v_file);					\
-		$(CC) $(no_g_c_flags) -c -o $@ $(s_file);		\
+		mv -f $(@D)/.tmp_$(@F) $@;				\
 	fi;
 endif
 
@@ -225,12 +215,7 @@ define rule_cc_o_c
 	$(cmd_record_mcount)						  \
 	scripts/basic/fixdep $(depfile) $@ '$(call make-cmd,cc_o_c)' >    \
 	                                              $(dot-target).tmp;  \
-	if [ -r $(@D)/.tmp_$(@F:.o=.v) ]; then				  \
-		echo >> $(dot-target).tmp;				  \
-		echo '$@: $(GENKSYMS)' >> $(dot-target).tmp;		  \
-		echo '$(GENKSYMS):: ;' >> $(dot-target).tmp;		  \
-	fi;								  \
-	rm -f $(depfile) $(@D)/.tmp_$(@F:.o=.?);			  \
+	rm -f $(depfile);						  \
 	mv -f $(dot-target).tmp $(dot-target).cmd
 endef
 
diff --git a/scripts/Makefile.modinst b/scripts/Makefile.modinst
index a5122dce1264..efa5d940e632 100644
--- a/scripts/Makefile.modinst
+++ b/scripts/Makefile.modinst
@@ -17,8 +17,7 @@ __modinst: $(modules)
 	@:
 
 quiet_cmd_modules_install = INSTALL $@
-      cmd_modules_install = mkdir -p $(2); \
-			    $(mod_strip_cmd) $@ $(2)/$(notdir $@) || cp $@ $(2)
+      cmd_modules_install = mkdir -p $(2); cp $@ $(2) ; $(mod_strip_cmd) $(2)/$(notdir $@)
 
 # Modules built outside the kernel source tree go into extra by default
 INSTALL_MOD_DIR ?= extra
diff --git a/scripts/genksyms/genksyms.c b/scripts/genksyms/genksyms.c
index f8bb4cabd62d..3a8297b5184c 100644
--- a/scripts/genksyms/genksyms.c
+++ b/scripts/genksyms/genksyms.c
@@ -43,7 +43,7 @@ int cur_line = 1;
 char *cur_filename;
 
 static int flag_debug, flag_dump_defs, flag_reference, flag_dump_types,
-	   flag_preserve, flag_warnings, flag_asm;
+	   flag_preserve, flag_warnings;
 static const char *arch = "";
 static const char *mod_prefix = "";
 
@@ -610,11 +610,8 @@ void export_symbol(const char *name)
 		if (flag_dump_defs)
 			fputs(">\n", debugfile);
 
-		/* Used as assembly source or a linker script. */
-		printf(flag_asm
-		       ? ".equiv %s__crc_%s, %#08lx\n"
-		       : "%s__crc_%s = %#08lx ;\n",
-		       mod_prefix, name, crc);
+		/* Used as a linker script. */
+		printf("%s__crc_%s = 0x%08lx ;\n", mod_prefix, name, crc);
 	}
 }
 
@@ -651,10 +648,9 @@ void error_with_pos(const char *fmt, ...)
 
 static void genksyms_usage(void)
 {
-	fputs("Usage:\n" "genksyms [-aAdDTwqhV] > /path/to/.tmp_obj.ver\n" "\n"
+	fputs("Usage:\n" "genksyms [-adDTwqhV] > /path/to/.tmp_obj.ver\n" "\n"
 #ifdef __GNU_LIBRARY__
 	      "  -a, --arch            Select architecture\n"
-	      "  -A, --asm             Generate assembly rather than linker script\n"
 	      "  -d, --debug           Increment the debug level (repeatable)\n"
 	      "  -D, --dump            Dump expanded symbol defs (for debugging only)\n"
 	      "  -r, --reference file  Read reference symbols from a file\n"
@@ -666,7 +662,6 @@ static void genksyms_usage(void)
 	      "  -V, --version         Print the release version\n"
 #else				/* __GNU_LIBRARY__ */
 	      "  -a                    Select architecture\n"
-	      "  -A                    Generate assembly rather than linker script\n"
 	      "  -d                    Increment the debug level (repeatable)\n"
 	      "  -D                    Dump expanded symbol defs (for debugging only)\n"
 	      "  -r file               Read reference symbols from a file\n"
@@ -688,7 +683,6 @@ int main(int argc, char **argv)
 #ifdef __GNU_LIBRARY__
 	struct option long_opts[] = {
 		{"arch", 1, 0, 'a'},
-		{"asm", 0, 0, 'A'},
 		{"debug", 0, 0, 'd'},
 		{"warnings", 0, 0, 'w'},
 		{"quiet", 0, 0, 'q'},
@@ -701,10 +695,10 @@ int main(int argc, char **argv)
 		{0, 0, 0, 0}
 	};
 
-	while ((o = getopt_long(argc, argv, "a:dwqVADr:T:ph",
+	while ((o = getopt_long(argc, argv, "a:dwqVDr:T:ph",
 				&long_opts[0], NULL)) != EOF)
 #else				/* __GNU_LIBRARY__ */
-	while ((o = getopt(argc, argv, "a:dwqVADr:T:ph")) != EOF)
+	while ((o = getopt(argc, argv, "a:dwqVDr:T:ph")) != EOF)
 #endif				/* __GNU_LIBRARY__ */
 		switch (o) {
 		case 'a':
@@ -722,9 +716,6 @@ int main(int argc, char **argv)
 		case 'V':
 			fputs("genksyms version 2.5.60\n", stderr);
 			break;
-		case 'A':
-			flag_asm = 1;
-			break;
 		case 'D':
 			flag_dump_defs = 1;
 			break;
diff --git a/scripts/genksyms/keywords.c_shipped b/scripts/genksyms/keywords.c_shipped
index 83484fe93ede..971e0113ae7a 100644
--- a/scripts/genksyms/keywords.c_shipped
+++ b/scripts/genksyms/keywords.c_shipped
@@ -1,4 +1,4 @@
-/* ANSI-C code produced by gperf version 3.0.1 */
+/* ANSI-C code produced by gperf version 3.0.2 */
 /* Command-line: gperf -L ANSI-C -a -C -E -g -H is_reserved_hash -k '1,3,$' -N is_reserved_word -p -t scripts/genksyms/keywords.gperf  */
 
 #if !((' ' == 32) && ('!' == 33) && ('"' == 34) && ('#' == 35) \
@@ -32,7 +32,7 @@
 
 #line 3 "scripts/genksyms/keywords.gperf"
 struct resword { const char *name; int token; };
-/* maximum key range = 64, duplicates = 0 */
+/* maximum key range = 62, duplicates = 0 */
 
 #ifdef __GNUC__
 __inline
@@ -46,32 +46,32 @@ is_reserved_hash (register const char *str, register unsigned int len)
 {
   static const unsigned char asso_values[] =
     {
-      67, 67, 67, 67, 67, 67, 67, 67, 67, 67,
-      67, 67, 67, 67, 67, 67, 67, 67, 67, 67,
-      67, 67, 67, 67, 67, 67, 67, 67, 67, 67,
-      67, 67, 67, 67, 67, 67, 67, 67, 67, 67,
-      67, 67, 67, 67, 67, 67, 67, 67, 67, 67,
-      67, 67, 67, 67, 67, 67, 67, 67, 67, 67,
-      67, 67, 67, 67, 67, 67, 67, 67, 67,  0,
-      67, 67, 67, 67, 67, 67, 15, 67, 67, 67,
-       0, 67, 67, 67, 67, 67, 67, 67, 67, 67,
-      67, 67, 67, 67, 67,  0, 67,  0, 67,  5,
-      25, 20, 15, 30, 67, 15, 67, 67, 10,  0,
-      10, 40, 20, 67, 10,  5,  0, 10, 15, 67,
-      67, 67, 67, 67, 67, 67, 67, 67, 67, 67,
-      67, 67, 67, 67, 67, 67, 67, 67, 67, 67,
-      67, 67, 67, 67, 67, 67, 67, 67, 67, 67,
-      67, 67, 67, 67, 67, 67, 67, 67, 67, 67,
-      67, 67, 67, 67, 67, 67, 67, 67, 67, 67,
-      67, 67, 67, 67, 67, 67, 67, 67, 67, 67,
-      67, 67, 67, 67, 67, 67, 67, 67, 67, 67,
-      67, 67, 67, 67, 67, 67, 67, 67, 67, 67,
-      67, 67, 67, 67, 67, 67, 67, 67, 67, 67,
-      67, 67, 67, 67, 67, 67, 67, 67, 67, 67,
-      67, 67, 67, 67, 67, 67, 67, 67, 67, 67,
-      67, 67, 67, 67, 67, 67, 67, 67, 67, 67,
-      67, 67, 67, 67, 67, 67, 67, 67, 67, 67,
-      67, 67, 67, 67, 67, 67
+      65, 65, 65, 65, 65, 65, 65, 65, 65, 65,
+      65, 65, 65, 65, 65, 65, 65, 65, 65, 65,
+      65, 65, 65, 65, 65, 65, 65, 65, 65, 65,
+      65, 65, 65, 65, 65, 65, 65, 65, 65, 65,
+      65, 65, 65, 65, 65, 65, 65, 65, 65, 65,
+      65, 65, 65, 65, 65, 65, 65, 65, 65, 65,
+      65, 65, 65, 65, 65, 65, 65, 65, 65,  5,
+      65, 65, 65, 65, 65, 65, 35, 65, 65, 65,
+       0, 65, 65, 65, 65, 65, 65, 65, 65, 65,
+      65, 65, 65, 65, 65,  0, 65,  0, 65,  5,
+      20, 15, 10, 30, 65, 15, 65, 65, 20,  0,
+      10, 35, 20, 65, 10,  5,  0, 10,  5, 65,
+      65, 65, 65, 65, 65, 65, 65, 65, 65, 65,
+      65, 65, 65, 65, 65, 65, 65, 65, 65, 65,
+      65, 65, 65, 65, 65, 65, 65, 65, 65, 65,
+      65, 65, 65, 65, 65, 65, 65, 65, 65, 65,
+      65, 65, 65, 65, 65, 65, 65, 65, 65, 65,
+      65, 65, 65, 65, 65, 65, 65, 65, 65, 65,
+      65, 65, 65, 65, 65, 65, 65, 65, 65, 65,
+      65, 65, 65, 65, 65, 65, 65, 65, 65, 65,
+      65, 65, 65, 65, 65, 65, 65, 65, 65, 65,
+      65, 65, 65, 65, 65, 65, 65, 65, 65, 65,
+      65, 65, 65, 65, 65, 65, 65, 65, 65, 65,
+      65, 65, 65, 65, 65, 65, 65, 65, 65, 65,
+      65, 65, 65, 65, 65, 65, 65, 65, 65, 65,
+      65, 65, 65, 65, 65, 65
     };
   return len + asso_values[(unsigned char)str[2]] + asso_values[(unsigned char)str[0]] + asso_values[(unsigned char)str[len - 1]];
 }
@@ -84,119 +84,116 @@ is_reserved_word (register const char *str, register unsigned int len)
 {
   enum
     {
-      TOTAL_KEYWORDS = 45,
+      TOTAL_KEYWORDS = 43,
       MIN_WORD_LENGTH = 3,
       MAX_WORD_LENGTH = 24,
       MIN_HASH_VALUE = 3,
-      MAX_HASH_VALUE = 66
+      MAX_HASH_VALUE = 64
     };
 
   static const struct resword wordlist[] =
     {
       {""}, {""}, {""},
-#line 28 "scripts/genksyms/keywords.gperf"
+#line 26 "scripts/genksyms/keywords.gperf"
       {"asm", ASM_KEYW},
       {""},
-#line 10 "scripts/genksyms/keywords.gperf"
+#line 8 "scripts/genksyms/keywords.gperf"
       {"__asm", ASM_KEYW},
       {""},
-#line 11 "scripts/genksyms/keywords.gperf"
+#line 9 "scripts/genksyms/keywords.gperf"
       {"__asm__", ASM_KEYW},
       {""}, {""},
-#line 54 "scripts/genksyms/keywords.gperf"
+#line 52 "scripts/genksyms/keywords.gperf"
       {"__typeof__", TYPEOF_KEYW},
       {""},
-#line 14 "scripts/genksyms/keywords.gperf"
+#line 12 "scripts/genksyms/keywords.gperf"
       {"__const", CONST_KEYW},
-#line 13 "scripts/genksyms/keywords.gperf"
+#line 11 "scripts/genksyms/keywords.gperf"
       {"__attribute__", ATTRIBUTE_KEYW},
-#line 15 "scripts/genksyms/keywords.gperf"
+#line 13 "scripts/genksyms/keywords.gperf"
       {"__const__", CONST_KEYW},
-#line 20 "scripts/genksyms/keywords.gperf"
+#line 18 "scripts/genksyms/keywords.gperf"
       {"__signed__", SIGNED_KEYW},
-#line 46 "scripts/genksyms/keywords.gperf"
+#line 44 "scripts/genksyms/keywords.gperf"
       {"static", STATIC_KEYW},
-      {""},
-#line 41 "scripts/genksyms/keywords.gperf"
+#line 20 "scripts/genksyms/keywords.gperf"
+      {"__volatile__", VOLATILE_KEYW},
+#line 39 "scripts/genksyms/keywords.gperf"
       {"int", INT_KEYW},
-#line 34 "scripts/genksyms/keywords.gperf"
+#line 32 "scripts/genksyms/keywords.gperf"
       {"char", CHAR_KEYW},
-#line 35 "scripts/genksyms/keywords.gperf"
+#line 33 "scripts/genksyms/keywords.gperf"
       {"const", CONST_KEYW},
-#line 47 "scripts/genksyms/keywords.gperf"
+#line 45 "scripts/genksyms/keywords.gperf"
       {"struct", STRUCT_KEYW},
-#line 26 "scripts/genksyms/keywords.gperf"
+#line 24 "scripts/genksyms/keywords.gperf"
       {"__restrict__", RESTRICT_KEYW},
-#line 27 "scripts/genksyms/keywords.gperf"
-      {"restrict", RESTRICT_KEYW},
-#line 7 "scripts/genksyms/keywords.gperf"
-      {"EXPORT_SYMBOL_GPL_FUTURE", EXPORT_SYMBOL_KEYW},
-#line 18 "scripts/genksyms/keywords.gperf"
-      {"__inline__", INLINE_KEYW},
-      {""},
-#line 22 "scripts/genksyms/keywords.gperf"
-      {"__volatile__", VOLATILE_KEYW},
-#line 5 "scripts/genksyms/keywords.gperf"
-      {"EXPORT_SYMBOL", EXPORT_SYMBOL_KEYW},
 #line 25 "scripts/genksyms/keywords.gperf"
+      {"restrict", RESTRICT_KEYW},
+#line 23 "scripts/genksyms/keywords.gperf"
       {"_restrict", RESTRICT_KEYW},
-      {""},
-#line 12 "scripts/genksyms/keywords.gperf"
-      {"__attribute", ATTRIBUTE_KEYW},
-#line 6 "scripts/genksyms/keywords.gperf"
-      {"EXPORT_SYMBOL_GPL", EXPORT_SYMBOL_KEYW},
 #line 16 "scripts/genksyms/keywords.gperf"
+      {"__inline__", INLINE_KEYW},
+#line 10 "scripts/genksyms/keywords.gperf"
+      {"__attribute", ATTRIBUTE_KEYW},
+      {""},
+#line 14 "scripts/genksyms/keywords.gperf"
       {"__extension__", EXTENSION_KEYW},
-#line 37 "scripts/genksyms/keywords.gperf"
+#line 35 "scripts/genksyms/keywords.gperf"
       {"enum", ENUM_KEYW},
-#line 8 "scripts/genksyms/keywords.gperf"
-      {"EXPORT_UNUSED_SYMBOL", EXPORT_SYMBOL_KEYW},
-#line 38 "scripts/genksyms/keywords.gperf"
+#line 19 "scripts/genksyms/keywords.gperf"
+      {"__volatile", VOLATILE_KEYW},
+#line 36 "scripts/genksyms/keywords.gperf"
       {"extern", EXTERN_KEYW},
       {""},
-#line 19 "scripts/genksyms/keywords.gperf"
+#line 17 "scripts/genksyms/keywords.gperf"
       {"__signed", SIGNED_KEYW},
-#line 9 "scripts/genksyms/keywords.gperf"
-      {"EXPORT_UNUSED_SYMBOL_GPL", EXPORT_SYMBOL_KEYW},
-#line 49 "scripts/genksyms/keywords.gperf"
-      {"union", UNION_KEYW},
-#line 53 "scripts/genksyms/keywords.gperf"
+#line 7 "scripts/genksyms/keywords.gperf"
+      {"EXPORT_SYMBOL_GPL_FUTURE", EXPORT_SYMBOL_KEYW},
+      {""},
+#line 51 "scripts/genksyms/keywords.gperf"
       {"typeof", TYPEOF_KEYW},
-#line 48 "scripts/genksyms/keywords.gperf"
+#line 46 "scripts/genksyms/keywords.gperf"
       {"typedef", TYPEDEF_KEYW},
-#line 17 "scripts/genksyms/keywords.gperf"
+#line 15 "scripts/genksyms/keywords.gperf"
       {"__inline", INLINE_KEYW},
-#line 33 "scripts/genksyms/keywords.gperf"
+#line 31 "scripts/genksyms/keywords.gperf"
       {"auto", AUTO_KEYW},
-#line 21 "scripts/genksyms/keywords.gperf"
-      {"__volatile", VOLATILE_KEYW},
+#line 47 "scripts/genksyms/keywords.gperf"
+      {"union", UNION_KEYW},
       {""}, {""},
-#line 50 "scripts/genksyms/keywords.gperf"
+#line 48 "scripts/genksyms/keywords.gperf"
       {"unsigned", UNSIGNED_KEYW},
-      {""},
-#line 44 "scripts/genksyms/keywords.gperf"
+#line 49 "scripts/genksyms/keywords.gperf"
+      {"void", VOID_KEYW},
+#line 42 "scripts/genksyms/keywords.gperf"
       {"short", SHORT_KEYW},
-#line 40 "scripts/genksyms/keywords.gperf"
+      {""}, {""},
+#line 50 "scripts/genksyms/keywords.gperf"
+      {"volatile", VOLATILE_KEYW},
+      {""},
+#line 37 "scripts/genksyms/keywords.gperf"
+      {"float", FLOAT_KEYW},
+#line 34 "scripts/genksyms/keywords.gperf"
+      {"double", DOUBLE_KEYW},
+      {""},
+#line 5 "scripts/genksyms/keywords.gperf"
+      {"EXPORT_SYMBOL", EXPORT_SYMBOL_KEYW},
+      {""}, {""},
+#line 38 "scripts/genksyms/keywords.gperf"
       {"inline", INLINE_KEYW},
+#line 6 "scripts/genksyms/keywords.gperf"
+      {"EXPORT_SYMBOL_GPL", EXPORT_SYMBOL_KEYW},
+#line 41 "scripts/genksyms/keywords.gperf"
+      {"register", REGISTER_KEYW},
       {""},
-#line 52 "scripts/genksyms/keywords.gperf"
-      {"volatile", VOLATILE_KEYW},
-#line 42 "scripts/genksyms/keywords.gperf"
-      {"long", LONG_KEYW},
-#line 24 "scripts/genksyms/keywords.gperf"
+#line 22 "scripts/genksyms/keywords.gperf"
       {"_Bool", BOOL_KEYW},
-      {""}, {""},
 #line 43 "scripts/genksyms/keywords.gperf"
-      {"register", REGISTER_KEYW},
-#line 51 "scripts/genksyms/keywords.gperf"
-      {"void", VOID_KEYW},
-#line 39 "scripts/genksyms/keywords.gperf"
-      {"float", FLOAT_KEYW},
-#line 36 "scripts/genksyms/keywords.gperf"
-      {"double", DOUBLE_KEYW},
-      {""}, {""}, {""}, {""},
-#line 45 "scripts/genksyms/keywords.gperf"
-      {"signed", SIGNED_KEYW}
+      {"signed", SIGNED_KEYW},
+      {""}, {""},
+#line 40 "scripts/genksyms/keywords.gperf"
+      {"long", LONG_KEYW}
     };
 
   if (len <= MAX_WORD_LENGTH && len >= MIN_WORD_LENGTH)
diff --git a/scripts/genksyms/keywords.gperf b/scripts/genksyms/keywords.gperf
index 8abe7ab8d88f..5ef3733225fb 100644
--- a/scripts/genksyms/keywords.gperf
+++ b/scripts/genksyms/keywords.gperf
@@ -5,8 +5,6 @@ struct resword { const char *name; int token; }
 EXPORT_SYMBOL, EXPORT_SYMBOL_KEYW
 EXPORT_SYMBOL_GPL, EXPORT_SYMBOL_KEYW
 EXPORT_SYMBOL_GPL_FUTURE, EXPORT_SYMBOL_KEYW
-EXPORT_UNUSED_SYMBOL, EXPORT_SYMBOL_KEYW
-EXPORT_UNUSED_SYMBOL_GPL, EXPORT_SYMBOL_KEYW
 __asm, ASM_KEYW
 __asm__, ASM_KEYW
 __attribute, ATTRIBUTE_KEYW
diff --git a/scripts/kallsyms.c b/scripts/kallsyms.c
index 92758120a767..ad2434b26970 100644
--- a/scripts/kallsyms.c
+++ b/scripts/kallsyms.c
@@ -130,9 +130,18 @@ static int read_symbol(FILE *in, struct sym_entry *s)
 static int symbol_valid(struct sym_entry *s)
 {
 	/* Symbols which vary between passes.  Passes 1 and 2 must have
-	 * identical symbol lists.
+	 * identical symbol lists.  The kallsyms_* symbols below are only added
+	 * after pass 1, they would be included in pass 2 when --all-symbols is
+	 * specified so exclude them to get a stable symbol list.
 	 */
 	static char *special_symbols[] = {
+		"kallsyms_addresses",
+		"kallsyms_num_syms",
+		"kallsyms_names",
+		"kallsyms_markers",
+		"kallsyms_token_table",
+		"kallsyms_token_index",
+
 	/* Exclude linker generated symbols which vary between passes */
 		"_SDA_BASE_",		/* ppc */
 		"_SDA2_BASE_",		/* ppc */
@@ -164,9 +173,7 @@ static int symbol_valid(struct sym_entry *s)
 	}
 
 	/* Exclude symbols which vary between passes. */
-	if (strstr((char *)s->sym + offset, "_compiled.") ||
-	    strncmp((char*)s->sym + offset, "__compound_literal.", 19) == 0 ||
-	    strncmp((char*)s->sym + offset, "__compound_literal$", 19) == 0)
+	if (strstr((char *)s->sym + offset, "_compiled."))
 		return 0;
 
 	for (i = 0; special_symbols[i]; i++)
@@ -543,10 +550,8 @@ int main(int argc, char **argv)
 		usage();
 
 	read_map(stdin);
-	if (table_cnt) {
-		sort_symbols();
-		optimize_token_table();
-	}
+	sort_symbols();
+	optimize_token_table();
 	write_src();
 
 	return 0;
diff --git a/scripts/mksysmap b/scripts/mksysmap
index 1db316a3712b..6e133a0bae7a 100644
--- a/scripts/mksysmap
+++ b/scripts/mksysmap
@@ -37,6 +37,9 @@
 
 # readprofile starts reading symbols when _stext is found, and
 # continue until it finds a symbol which is not either of 'T', 't',
-# 'W' or 'w'.
+# 'W' or 'w'. __crc_ are 'A' and placed in the middle
+# so we just ignore them to let readprofile continue to work.
+# (At least sparc64 has __crc_ in the middle).
+
+$NM -n $1 | grep -v '\( [aNUw] \)\|\(__crc_\)\|\( \$[adt]\)' > $2
 
-$NM -n $1 | grep -v '\( [aNUw] \)\|\( \$[adt]\)' > $2
diff --git a/scripts/strip-symbols b/scripts/strip-symbols
deleted file mode 100644
index 29ee8c1a014b..000000000000
--- a/scripts/strip-symbols
+++ /dev/null
@@ -1,22 +0,0 @@
-<*>
-*.h
-__compound_literal[$.][0-9]*
-__crc_[a-zA-Z_]*
-__exitcall_[a-zA-Z_]*
-__func__[$.][0-9]*
-__FUNCTION__[$.][0-9]*
-gcc[0-9]_compiled[$.]
-__initcall_[a-zA-Z_]*
-__kcrctab_[a-zA-Z_]*
-__kstrtab_[a-zA-Z_]*
-__ksymtab_[a-zA-Z_]*
-__mod_[a-zA-Z_]*[0-9]
-__module_depends
-__param_[a-zA-Z_]*
-__pci_fixup_*PCI_ANY_IDPCI_ANY_ID*
-__pci_fixup_*PCI_ANY_IDPCI_DEVICE_ID_*
-__pci_fixup_*PCI_VENDOR_ID_*PCI_ANY_ID*
-__pci_fixup_*PCI_VENDOR_ID_*PCI_DEVICE_ID_*
-__PRETTY_FUNCTION__[$.][0-9]*
-__setup_[a-zA-Z_]*
-____versions
-- 
cgit v1.2.3


From 934d96eafadcf3eb3ccd094af9919f020907fc41 Mon Sep 17 00:00:00 2001
From: Jaswinder Singh Rajput <jaswinder@infradead.org>
Date: Wed, 14 Jan 2009 20:38:17 +0530
Subject: time-sched.c: tick_nohz_update_jiffies should be static

Impact: cleanup, reduce kernel size a bit, avoid sparse warning

Fixes sparse warning:

 kernel/time/tick-sched.c:137:6: warning: symbol 'tick_nohz_update_jiffies' was not declared. Should it be static?

Signed-off-by: Jaswinder Singh Rajput <jaswinderrajput@gmail.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
---
 kernel/time/tick-sched.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'kernel')

diff --git a/kernel/time/tick-sched.c b/kernel/time/tick-sched.c
index 1b6c05bd0d0a..d3f1ef4d5cbe 100644
--- a/kernel/time/tick-sched.c
+++ b/kernel/time/tick-sched.c
@@ -134,7 +134,7 @@ __setup("nohz=", setup_tick_nohz);
  * value. We do this unconditionally on any cpu, as we don't know whether the
  * cpu, which has the update task assigned is in a long sleep.
  */
-void tick_nohz_update_jiffies(void)
+static void tick_nohz_update_jiffies(void)
 {
 	int cpu = smp_processor_id();
 	struct tick_sched *ts = &per_cpu(tick_cpu_sched, cpu);
-- 
cgit v1.2.3


From 98a4826b99bc4bcc34c604b2fc4fcf4d771600ec Mon Sep 17 00:00:00 2001
From: Peter Zijlstra <peterz@infradead.org>
Date: Wed, 14 Jan 2009 10:56:32 +0100
Subject: sched: fix bandwidth validation for UID grouping

Impact: make rt-limit tunables work again

Mark Glines reported:

> I've got an issue on x86-64 where I can't configure the system to allow
> RT tasks for a non-root user.
>
> In 2.6.26.5, I was able to do the following to set things up nicely:
> echo 450000 >/sys/kernel/uids/0/cpu_rt_runtime
> echo 450000 >/sys/kernel/uids/1000/cpu_rt_runtime
>
> Seems like every value I try to echo into the /sys files returns EINVAL.

For UID grouping we initialize the root group with infinite bandwidth
which by default is actually more than the global limit, therefore the
bandwidth check always fails.

Because the root group is a phantom group (for UID grouping) we cannot
runtime adjust it, therefore we let it reflect the global bandwidth
settings.

Reported-by: Mark Glines <mark@glines.org>
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
---
 kernel/sched.c | 7 +++++++
 1 file changed, 7 insertions(+)

(limited to 'kernel')

diff --git a/kernel/sched.c b/kernel/sched.c
index 3b630d882660..ed62d1cee05c 100644
--- a/kernel/sched.c
+++ b/kernel/sched.c
@@ -9050,6 +9050,13 @@ static int tg_schedulable(struct task_group *tg, void *data)
 		runtime = d->rt_runtime;
 	}
 
+#ifdef CONFIG_USER_SCHED
+	if (tg == &root_task_group) {
+		period = global_rt_period();
+		runtime = global_rt_runtime();
+	}
+#endif
+
 	/*
 	 * Cannot have more runtime than the period.
 	 */
-- 
cgit v1.2.3


From cce7ade803699463ecc62a065ca522004f7ccb3d Mon Sep 17 00:00:00 2001
From: Peter Zijlstra <a.p.zijlstra@chello.nl>
Date: Thu, 15 Jan 2009 14:53:37 +0100
Subject: sched: SCHED_IDLE weight change

Increase the SCHED_IDLE weight from 2 to 3, this gives much more stable
vruntime numbers.

time advanced in 100ms:

 weight=2

 64765.988352
 67012.881408
 88501.412352

 weight=3

 35496.181411
 34130.971298
 35497.411573

Signed-off-by: Mike Galbraith <efault@gmx.de>
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
---
 kernel/sched.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

(limited to 'kernel')

diff --git a/kernel/sched.c b/kernel/sched.c
index ed62d1cee05c..6acfb3c2398b 100644
--- a/kernel/sched.c
+++ b/kernel/sched.c
@@ -1323,8 +1323,8 @@ static inline void update_load_sub(struct load_weight *lw, unsigned long dec)
  * slice expiry etc.
  */
 
-#define WEIGHT_IDLEPRIO		2
-#define WMULT_IDLEPRIO		(1 << 31)
+#define WEIGHT_IDLEPRIO                3
+#define WMULT_IDLEPRIO         1431655765
 
 /*
  * Nice levels are multiplicative, with a gentle 10% change for every
-- 
cgit v1.2.3


From 6bc912b71b6f33b041cfde93ca3f019cbaa852bc Mon Sep 17 00:00:00 2001
From: Peter Zijlstra <a.p.zijlstra@chello.nl>
Date: Thu, 15 Jan 2009 14:53:38 +0100
Subject: sched: SCHED_OTHER vs SCHED_IDLE isolation

Stronger SCHED_IDLE isolation:

 - no SCHED_IDLE buddies
 - never let SCHED_IDLE preempt on wakeup
 - always preempt SCHED_IDLE on wakeup
 - limit SLEEPER fairness for SCHED_IDLE.

Signed-off-by: Mike Galbraith <efault@gmx.de>
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
---
 kernel/sched_fair.c | 30 ++++++++++++++++++++++--------
 1 file changed, 22 insertions(+), 8 deletions(-)

(limited to 'kernel')

diff --git a/kernel/sched_fair.c b/kernel/sched_fair.c
index 8e1352c75557..cdebd8089cb0 100644
--- a/kernel/sched_fair.c
+++ b/kernel/sched_fair.c
@@ -677,9 +677,13 @@ place_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int initial)
 			unsigned long thresh = sysctl_sched_latency;
 
 			/*
-			 * convert the sleeper threshold into virtual time
+			 * Convert the sleeper threshold into virtual time.
+			 * SCHED_IDLE is a special sub-class.  We care about
+			 * fairness only relative to other SCHED_IDLE tasks,
+			 * all of which have the same weight.
 			 */
-			if (sched_feat(NORMALIZED_SLEEPER))
+			if (sched_feat(NORMALIZED_SLEEPER) &&
+					task_of(se)->policy != SCHED_IDLE)
 				thresh = calc_delta_fair(thresh, se);
 
 			vruntime -= thresh;
@@ -1340,14 +1344,18 @@ wakeup_preempt_entity(struct sched_entity *curr, struct sched_entity *se)
 
 static void set_last_buddy(struct sched_entity *se)
 {
-	for_each_sched_entity(se)
-		cfs_rq_of(se)->last = se;
+	if (likely(task_of(se)->policy != SCHED_IDLE)) {
+		for_each_sched_entity(se)
+			cfs_rq_of(se)->last = se;
+	}
 }
 
 static void set_next_buddy(struct sched_entity *se)
 {
-	for_each_sched_entity(se)
-		cfs_rq_of(se)->next = se;
+	if (likely(task_of(se)->policy != SCHED_IDLE)) {
+		for_each_sched_entity(se)
+			cfs_rq_of(se)->next = se;
+	}
 }
 
 /*
@@ -1393,12 +1401,18 @@ static void check_preempt_wakeup(struct rq *rq, struct task_struct *p, int sync)
 		return;
 
 	/*
-	 * Batch tasks do not preempt (their preemption is driven by
+	 * Batch and idle tasks do not preempt (their preemption is driven by
 	 * the tick):
 	 */
-	if (unlikely(p->policy == SCHED_BATCH))
+	if (unlikely(p->policy != SCHED_NORMAL))
 		return;
 
+	/* Idle tasks are by definition preempted by everybody. */
+	if (unlikely(curr->policy == SCHED_IDLE)) {
+		resched_task(curr);
+		return;
+	}
+
 	if (!sched_feat(WAKEUP_PREEMPT))
 		return;
 
-- 
cgit v1.2.3


From e17036dac189dd034c092a91df56aa740db7146d Mon Sep 17 00:00:00 2001
From: Peter Zijlstra <a.p.zijlstra@chello.nl>
Date: Thu, 15 Jan 2009 14:53:39 +0100
Subject: sched: fix update_min_vruntime

Impact: fix SCHED_IDLE latency problems

OK, so we have 1 running task A (which is obviously curr and the tree is
equally obviously empty).

'A' nicely chugs along, doing its thing, carrying min_vruntime along as it
goes.

Then some whacko speed freak SCHED_IDLE task gets inserted due to SMP
balancing, which is very likely far right, in that case

update_curr
  update_min_vruntime
    cfs_rq->rb_leftmost := true (the crazy task sitting in a tree)
      vruntime = se->vruntime

and voila, min_vruntime is waaay right of where it ought to be.

OK, so why did I write it like that to begin with...

Aah, yes.

Say we've just dequeued current

schedule
  deactivate_task(prev)
    dequeue_entity
      update_min_vruntime

Then we'll set

  vruntime = cfs_rq->min_vruntime;

we find !cfs_rq->curr, but do find someone in the tree. Then we _must_
do vruntime = se->vruntime, because

 vruntime = min_vruntime(vruntime := cfs_rq->min_vruntime, se->vruntime)

will not advance vruntime, and cause lags the other way around (which we
fixed with that initial patch: 1af5f730fc1bf7c62ec9fb2d307206e18bf40a69
(sched: more accurate min_vruntime accounting).

Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Tested-by: Mike Galbraith <efault@gmx.de>
Acked-by: Mike Galbraith <efault@gmx.de>
Cc: <stable@kernel.org>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
---
 kernel/sched_fair.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'kernel')

diff --git a/kernel/sched_fair.c b/kernel/sched_fair.c
index cdebd8089cb0..16b419bb8b0a 100644
--- a/kernel/sched_fair.c
+++ b/kernel/sched_fair.c
@@ -283,7 +283,7 @@ static void update_min_vruntime(struct cfs_rq *cfs_rq)
 						   struct sched_entity,
 						   run_node);
 
-		if (vruntime == cfs_rq->min_vruntime)
+		if (!cfs_rq->curr)
 			vruntime = se->vruntime;
 		else
 			vruntime = min_vruntime(vruntime, se->vruntime);
-- 
cgit v1.2.3


From 88fc241f54459ac3d86c5e13b449730199f66061 Mon Sep 17 00:00:00 2001
From: Doug Chapman <doug.chapman@hp.com>
Date: Thu, 15 Jan 2009 10:38:56 -0800
Subject: [IA64] dump stack on kernel unaligned warnings

Often the cause of kernel unaligned access warnings is not
obvious from just the ip displayed in the warning.  This adds
the option via proc to dump the stack in addition to the warning.
The default is off (just display the 1 line warning).  To enable
the stack to be shown: echo 1 > /proc/sys/kernel/unaligned-dump-stack

Signed-off-by: Doug Chapman <doug.chapman@hp.com>
Signed-off-by: Tony Luck <tony.luck@intel.com>
---
 arch/ia64/kernel/unaligned.c | 6 +++++-
 kernel/sysctl.c              | 9 +++++++++
 2 files changed, 14 insertions(+), 1 deletion(-)

(limited to 'kernel')

diff --git a/arch/ia64/kernel/unaligned.c b/arch/ia64/kernel/unaligned.c
index ff0e7c10faa7..6db08599ebbc 100644
--- a/arch/ia64/kernel/unaligned.c
+++ b/arch/ia64/kernel/unaligned.c
@@ -59,6 +59,7 @@ dump (const char *str, void *vp, size_t len)
  *  (i.e. don't allow attacker to fill up logs with unaligned accesses).
  */
 int no_unaligned_warning;
+int unaligned_dump_stack;
 static int noprint_warning;
 
 /*
@@ -1371,9 +1372,12 @@ ia64_handle_unaligned (unsigned long ifa, struct pt_regs *regs)
 			}
 		}
 	} else {
-		if (within_logging_rate_limit())
+		if (within_logging_rate_limit()) {
 			printk(KERN_WARNING "kernel unaligned access to 0x%016lx, ip=0x%016lx\n",
 			       ifa, regs->cr_iip + ipsr->ri);
+			if (unaligned_dump_stack)
+				dump_stack();
+		}
 		set_fs(KERNEL_DS);
 	}
 
diff --git a/kernel/sysctl.c b/kernel/sysctl.c
index 3e38b74b6124..368d1638ee78 100644
--- a/kernel/sysctl.c
+++ b/kernel/sysctl.c
@@ -144,6 +144,7 @@ extern int acct_parm[];
 
 #ifdef CONFIG_IA64
 extern int no_unaligned_warning;
+extern int unaligned_dump_stack;
 #endif
 
 #ifdef CONFIG_RT_MUTEXES
@@ -781,6 +782,14 @@ static struct ctl_table kern_table[] = {
 	 	.mode		= 0644,
 		.proc_handler	= &proc_dointvec,
 	},
+	{
+		.ctl_name	= CTL_UNNUMBERED,
+		.procname	= "unaligned-dump-stack",
+		.data		= &unaligned_dump_stack,
+		.maxlen		= sizeof (int),
+		.mode		= 0644,
+		.proc_handler	= &proc_dointvec,
+	},
 #endif
 #ifdef CONFIG_DETECT_SOFTLOCKUP
 	{
-- 
cgit v1.2.3


From 6272d68cc6a5f90c6b1a2228cf0f67b895305d17 Mon Sep 17 00:00:00 2001
From: Lin Ming <ming.m.lin@intel.com>
Date: Thu, 15 Jan 2009 17:17:15 +0100
Subject: sched: sched_slice() fixlet

Mike's change: 0a582440f "sched: fix sched_slice())" broke group
scheduling by forgetting to reload cfs_rq on each loop.

This patch fixes aim7 regression and specjbb2005 regression becomes
less than 1.5% on 8-core stokley.

Signed-off-by: Lin Ming <ming.m.lin@intel.com>
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Tested-by: Jayson King <dev@jaysonking.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
---
 kernel/sched_fair.c | 5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)

(limited to 'kernel')

diff --git a/kernel/sched_fair.c b/kernel/sched_fair.c
index 16b419bb8b0a..5cc1c162044f 100644
--- a/kernel/sched_fair.c
+++ b/kernel/sched_fair.c
@@ -429,7 +429,10 @@ static u64 sched_slice(struct cfs_rq *cfs_rq, struct sched_entity *se)
 	u64 slice = __sched_period(cfs_rq->nr_running + !se->on_rq);
 
 	for_each_sched_entity(se) {
-		struct load_weight *load = &cfs_rq->load;
+		struct load_weight *load;
+
+		cfs_rq = cfs_rq_of(se);
+		load = &cfs_rq->load;
 
 		if (unlikely(!se->on_rq)) {
 			struct load_weight lw = cfs_rq->load;
-- 
cgit v1.2.3


From 45ce80fb6b6f9594d1396d44dd7e7c02d596fef8 Mon Sep 17 00:00:00 2001
From: Li Zefan <lizf@cn.fujitsu.com>
Date: Thu, 15 Jan 2009 13:50:59 -0800
Subject: cgroups: consolidate cgroup documents

Move Documentation/cpusets.txt and Documentation/controllers/* to
Documentation/cgroups/

Signed-off-by: Li Zefan <lizf@cn.fujitsu.com>
Acked-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
Acked-by: Balbir Singh <balbir@linux.vnet.ibm.com>
Acked-by: Paul Menage <menage@google.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 Documentation/cgroups/cgroups.txt              |   5 +-
 Documentation/cgroups/cpuacct.txt              |  32 +
 Documentation/cgroups/cpusets.txt              | 808 +++++++++++++++++++++++++
 Documentation/cgroups/devices.txt              |  52 ++
 Documentation/cgroups/memcg_test.txt           | 342 +++++++++++
 Documentation/cgroups/memory.txt               | 399 ++++++++++++
 Documentation/cgroups/resource_counter.txt     | 181 ++++++
 Documentation/controllers/cpuacct.txt          |  32 -
 Documentation/controllers/devices.txt          |  52 --
 Documentation/controllers/memcg_test.txt       | 342 -----------
 Documentation/controllers/memory.txt           | 399 ------------
 Documentation/controllers/resource_counter.txt | 181 ------
 Documentation/cpusets.txt                      | 808 -------------------------
 Documentation/scheduler/sched-design-CFS.txt   |   2 +-
 include/linux/res_counter.h                    |   2 +-
 init/Kconfig                                   |   9 +-
 kernel/cpuset.c                                |   2 +-
 17 files changed, 1824 insertions(+), 1824 deletions(-)
 create mode 100644 Documentation/cgroups/cpuacct.txt
 create mode 100644 Documentation/cgroups/cpusets.txt
 create mode 100644 Documentation/cgroups/devices.txt
 create mode 100644 Documentation/cgroups/memcg_test.txt
 create mode 100644 Documentation/cgroups/memory.txt
 create mode 100644 Documentation/cgroups/resource_counter.txt
 delete mode 100644 Documentation/controllers/cpuacct.txt
 delete mode 100644 Documentation/controllers/devices.txt
 delete mode 100644 Documentation/controllers/memcg_test.txt
 delete mode 100644 Documentation/controllers/memory.txt
 delete mode 100644 Documentation/controllers/resource_counter.txt
 delete mode 100644 Documentation/cpusets.txt

(limited to 'kernel')

diff --git a/Documentation/cgroups/cgroups.txt b/Documentation/cgroups/cgroups.txt
index e33ee74eee77..d9e5d6f41b92 100644
--- a/Documentation/cgroups/cgroups.txt
+++ b/Documentation/cgroups/cgroups.txt
@@ -1,7 +1,8 @@
 				CGROUPS
 				-------
 
-Written by Paul Menage <menage@google.com> based on Documentation/cpusets.txt
+Written by Paul Menage <menage@google.com> based on
+Documentation/cgroups/cpusets.txt
 
 Original copyright statements from cpusets.txt:
 Portions Copyright (C) 2004 BULL SA.
@@ -68,7 +69,7 @@ On their own, the only use for cgroups is for simple job
 tracking. The intention is that other subsystems hook into the generic
 cgroup support to provide new attributes for cgroups, such as
 accounting/limiting the resources which processes in a cgroup can
-access. For example, cpusets (see Documentation/cpusets.txt) allows
+access. For example, cpusets (see Documentation/cgroups/cpusets.txt) allows
 you to associate a set of CPUs and a set of memory nodes with the
 tasks in each cgroup.
 
diff --git a/Documentation/cgroups/cpuacct.txt b/Documentation/cgroups/cpuacct.txt
new file mode 100644
index 000000000000..bb775fbe43d7
--- /dev/null
+++ b/Documentation/cgroups/cpuacct.txt
@@ -0,0 +1,32 @@
+CPU Accounting Controller
+-------------------------
+
+The CPU accounting controller is used to group tasks using cgroups and
+account the CPU usage of these groups of tasks.
+
+The CPU accounting controller supports multi-hierarchy groups. An accounting
+group accumulates the CPU usage of all of its child groups and the tasks
+directly present in its group.
+
+Accounting groups can be created by first mounting the cgroup filesystem.
+
+# mkdir /cgroups
+# mount -t cgroup -ocpuacct none /cgroups
+
+With the above step, the initial or the parent accounting group
+becomes visible at /cgroups. At bootup, this group includes all the
+tasks in the system. /cgroups/tasks lists the tasks in this cgroup.
+/cgroups/cpuacct.usage gives the CPU time (in nanoseconds) obtained by
+this group which is essentially the CPU time obtained by all the tasks
+in the system.
+
+New accounting groups can be created under the parent group /cgroups.
+
+# cd /cgroups
+# mkdir g1
+# echo $$ > g1
+
+The above steps create a new group g1 and move the current shell
+process (bash) into it. CPU time consumed by this bash and its children
+can be obtained from g1/cpuacct.usage and the same is accumulated in
+/cgroups/cpuacct.usage also.
diff --git a/Documentation/cgroups/cpusets.txt b/Documentation/cgroups/cpusets.txt
new file mode 100644
index 000000000000..5c86c258c791
--- /dev/null
+++ b/Documentation/cgroups/cpusets.txt
@@ -0,0 +1,808 @@
+				CPUSETS
+				-------
+
+Copyright (C) 2004 BULL SA.
+Written by Simon.Derr@bull.net
+
+Portions Copyright (c) 2004-2006 Silicon Graphics, Inc.
+Modified by Paul Jackson <pj@sgi.com>
+Modified by Christoph Lameter <clameter@sgi.com>
+Modified by Paul Menage <menage@google.com>
+Modified by Hidetoshi Seto <seto.hidetoshi@jp.fujitsu.com>
+
+CONTENTS:
+=========
+
+1. Cpusets
+  1.1 What are cpusets ?
+  1.2 Why are cpusets needed ?
+  1.3 How are cpusets implemented ?
+  1.4 What are exclusive cpusets ?
+  1.5 What is memory_pressure ?
+  1.6 What is memory spread ?
+  1.7 What is sched_load_balance ?
+  1.8 What is sched_relax_domain_level ?
+  1.9 How do I use cpusets ?
+2. Usage Examples and Syntax
+  2.1 Basic Usage
+  2.2 Adding/removing cpus
+  2.3 Setting flags
+  2.4 Attaching processes
+3. Questions
+4. Contact
+
+1. Cpusets
+==========
+
+1.1 What are cpusets ?
+----------------------
+
+Cpusets provide a mechanism for assigning a set of CPUs and Memory
+Nodes to a set of tasks.   In this document "Memory Node" refers to
+an on-line node that contains memory.
+
+Cpusets constrain the CPU and Memory placement of tasks to only
+the resources within a tasks current cpuset.  They form a nested
+hierarchy visible in a virtual file system.  These are the essential
+hooks, beyond what is already present, required to manage dynamic
+job placement on large systems.
+
+Cpusets use the generic cgroup subsystem described in
+Documentation/cgroups/cgroups.txt.
+
+Requests by a task, using the sched_setaffinity(2) system call to
+include CPUs in its CPU affinity mask, and using the mbind(2) and
+set_mempolicy(2) system calls to include Memory Nodes in its memory
+policy, are both filtered through that tasks cpuset, filtering out any
+CPUs or Memory Nodes not in that cpuset.  The scheduler will not
+schedule a task on a CPU that is not allowed in its cpus_allowed
+vector, and the kernel page allocator will not allocate a page on a
+node that is not allowed in the requesting tasks mems_allowed vector.
+
+User level code may create and destroy cpusets by name in the cgroup
+virtual file system, manage the attributes and permissions of these
+cpusets and which CPUs and Memory Nodes are assigned to each cpuset,
+specify and query to which cpuset a task is assigned, and list the
+task pids assigned to a cpuset.
+
+
+1.2 Why are cpusets needed ?
+----------------------------
+
+The management of large computer systems, with many processors (CPUs),
+complex memory cache hierarchies and multiple Memory Nodes having
+non-uniform access times (NUMA) presents additional challenges for
+the efficient scheduling and memory placement of processes.
+
+Frequently more modest sized systems can be operated with adequate
+efficiency just by letting the operating system automatically share
+the available CPU and Memory resources amongst the requesting tasks.
+
+But larger systems, which benefit more from careful processor and
+memory placement to reduce memory access times and contention,
+and which typically represent a larger investment for the customer,
+can benefit from explicitly placing jobs on properly sized subsets of
+the system.
+
+This can be especially valuable on:
+
+    * Web Servers running multiple instances of the same web application,
+    * Servers running different applications (for instance, a web server
+      and a database), or
+    * NUMA systems running large HPC applications with demanding
+      performance characteristics.
+
+These subsets, or "soft partitions" must be able to be dynamically
+adjusted, as the job mix changes, without impacting other concurrently
+executing jobs. The location of the running jobs pages may also be moved
+when the memory locations are changed.
+
+The kernel cpuset patch provides the minimum essential kernel
+mechanisms required to efficiently implement such subsets.  It
+leverages existing CPU and Memory Placement facilities in the Linux
+kernel to avoid any additional impact on the critical scheduler or
+memory allocator code.
+
+
+1.3 How are cpusets implemented ?
+---------------------------------
+
+Cpusets provide a Linux kernel mechanism to constrain which CPUs and
+Memory Nodes are used by a process or set of processes.
+
+The Linux kernel already has a pair of mechanisms to specify on which
+CPUs a task may be scheduled (sched_setaffinity) and on which Memory
+Nodes it may obtain memory (mbind, set_mempolicy).
+
+Cpusets extends these two mechanisms as follows:
+
+ - Cpusets are sets of allowed CPUs and Memory Nodes, known to the
+   kernel.
+ - Each task in the system is attached to a cpuset, via a pointer
+   in the task structure to a reference counted cgroup structure.
+ - Calls to sched_setaffinity are filtered to just those CPUs
+   allowed in that tasks cpuset.
+ - Calls to mbind and set_mempolicy are filtered to just
+   those Memory Nodes allowed in that tasks cpuset.
+ - The root cpuset contains all the systems CPUs and Memory
+   Nodes.
+ - For any cpuset, one can define child cpusets containing a subset
+   of the parents CPU and Memory Node resources.
+ - The hierarchy of cpusets can be mounted at /dev/cpuset, for
+   browsing and manipulation from user space.
+ - A cpuset may be marked exclusive, which ensures that no other
+   cpuset (except direct ancestors and descendents) may contain
+   any overlapping CPUs or Memory Nodes.
+ - You can list all the tasks (by pid) attached to any cpuset.
+
+The implementation of cpusets requires a few, simple hooks
+into the rest of the kernel, none in performance critical paths:
+
+ - in init/main.c, to initialize the root cpuset at system boot.
+ - in fork and exit, to attach and detach a task from its cpuset.
+ - in sched_setaffinity, to mask the requested CPUs by what's
+   allowed in that tasks cpuset.
+ - in sched.c migrate_all_tasks(), to keep migrating tasks within
+   the CPUs allowed by their cpuset, if possible.
+ - in the mbind and set_mempolicy system calls, to mask the requested
+   Memory Nodes by what's allowed in that tasks cpuset.
+ - in page_alloc.c, to restrict memory to allowed nodes.
+ - in vmscan.c, to restrict page recovery to the current cpuset.
+
+You should mount the "cgroup" filesystem type in order to enable
+browsing and modifying the cpusets presently known to the kernel.  No
+new system calls are added for cpusets - all support for querying and
+modifying cpusets is via this cpuset file system.
+
+The /proc/<pid>/status file for each task has four added lines,
+displaying the tasks cpus_allowed (on which CPUs it may be scheduled)
+and mems_allowed (on which Memory Nodes it may obtain memory),
+in the two formats seen in the following example:
+
+  Cpus_allowed:   ffffffff,ffffffff,ffffffff,ffffffff
+  Cpus_allowed_list:      0-127
+  Mems_allowed:   ffffffff,ffffffff
+  Mems_allowed_list:      0-63
+
+Each cpuset is represented by a directory in the cgroup file system
+containing (on top of the standard cgroup files) the following
+files describing that cpuset:
+
+ - cpus: list of CPUs in that cpuset
+ - mems: list of Memory Nodes in that cpuset
+ - memory_migrate flag: if set, move pages to cpusets nodes
+ - cpu_exclusive flag: is cpu placement exclusive?
+ - mem_exclusive flag: is memory placement exclusive?
+ - mem_hardwall flag:  is memory allocation hardwalled
+ - memory_pressure: measure of how much paging pressure in cpuset
+
+In addition, the root cpuset only has the following file:
+ - memory_pressure_enabled flag: compute memory_pressure?
+
+New cpusets are created using the mkdir system call or shell
+command.  The properties of a cpuset, such as its flags, allowed
+CPUs and Memory Nodes, and attached tasks, are modified by writing
+to the appropriate file in that cpusets directory, as listed above.
+
+The named hierarchical structure of nested cpusets allows partitioning
+a large system into nested, dynamically changeable, "soft-partitions".
+
+The attachment of each task, automatically inherited at fork by any
+children of that task, to a cpuset allows organizing the work load
+on a system into related sets of tasks such that each set is constrained
+to using the CPUs and Memory Nodes of a particular cpuset.  A task
+may be re-attached to any other cpuset, if allowed by the permissions
+on the necessary cpuset file system directories.
+
+Such management of a system "in the large" integrates smoothly with
+the detailed placement done on individual tasks and memory regions
+using the sched_setaffinity, mbind and set_mempolicy system calls.
+
+The following rules apply to each cpuset:
+
+ - Its CPUs and Memory Nodes must be a subset of its parents.
+ - It can't be marked exclusive unless its parent is.
+ - If its cpu or memory is exclusive, they may not overlap any sibling.
+
+These rules, and the natural hierarchy of cpusets, enable efficient
+enforcement of the exclusive guarantee, without having to scan all
+cpusets every time any of them change to ensure nothing overlaps a
+exclusive cpuset.  Also, the use of a Linux virtual file system (vfs)
+to represent the cpuset hierarchy provides for a familiar permission
+and name space for cpusets, with a minimum of additional kernel code.
+
+The cpus and mems files in the root (top_cpuset) cpuset are
+read-only.  The cpus file automatically tracks the value of
+cpu_online_map using a CPU hotplug notifier, and the mems file
+automatically tracks the value of node_states[N_HIGH_MEMORY]--i.e.,
+nodes with memory--using the cpuset_track_online_nodes() hook.
+
+
+1.4 What are exclusive cpusets ?
+--------------------------------
+
+If a cpuset is cpu or mem exclusive, no other cpuset, other than
+a direct ancestor or descendent, may share any of the same CPUs or
+Memory Nodes.
+
+A cpuset that is mem_exclusive *or* mem_hardwall is "hardwalled",
+i.e. it restricts kernel allocations for page, buffer and other data
+commonly shared by the kernel across multiple users.  All cpusets,
+whether hardwalled or not, restrict allocations of memory for user
+space.  This enables configuring a system so that several independent
+jobs can share common kernel data, such as file system pages, while
+isolating each job's user allocation in its own cpuset.  To do this,
+construct a large mem_exclusive cpuset to hold all the jobs, and
+construct child, non-mem_exclusive cpusets for each individual job.
+Only a small amount of typical kernel memory, such as requests from
+interrupt handlers, is allowed to be taken outside even a
+mem_exclusive cpuset.
+
+
+1.5 What is memory_pressure ?
+-----------------------------
+The memory_pressure of a cpuset provides a simple per-cpuset metric
+of the rate that the tasks in a cpuset are attempting to free up in
+use memory on the nodes of the cpuset to satisfy additional memory
+requests.
+
+This enables batch managers monitoring jobs running in dedicated
+cpusets to efficiently detect what level of memory pressure that job
+is causing.
+
+This is useful both on tightly managed systems running a wide mix of
+submitted jobs, which may choose to terminate or re-prioritize jobs that
+are trying to use more memory than allowed on the nodes assigned them,
+and with tightly coupled, long running, massively parallel scientific
+computing jobs that will dramatically fail to meet required performance
+goals if they start to use more memory than allowed to them.
+
+This mechanism provides a very economical way for the batch manager
+to monitor a cpuset for signs of memory pressure.  It's up to the
+batch manager or other user code to decide what to do about it and
+take action.
+
+==> Unless this feature is enabled by writing "1" to the special file
+    /dev/cpuset/memory_pressure_enabled, the hook in the rebalance
+    code of __alloc_pages() for this metric reduces to simply noticing
+    that the cpuset_memory_pressure_enabled flag is zero.  So only
+    systems that enable this feature will compute the metric.
+
+Why a per-cpuset, running average:
+
+    Because this meter is per-cpuset, rather than per-task or mm,
+    the system load imposed by a batch scheduler monitoring this
+    metric is sharply reduced on large systems, because a scan of
+    the tasklist can be avoided on each set of queries.
+
+    Because this meter is a running average, instead of an accumulating
+    counter, a batch scheduler can detect memory pressure with a
+    single read, instead of having to read and accumulate results
+    for a period of time.
+
+    Because this meter is per-cpuset rather than per-task or mm,
+    the batch scheduler can obtain the key information, memory
+    pressure in a cpuset, with a single read, rather than having to
+    query and accumulate results over all the (dynamically changing)
+    set of tasks in the cpuset.
+
+A per-cpuset simple digital filter (requires a spinlock and 3 words
+of data per-cpuset) is kept, and updated by any task attached to that
+cpuset, if it enters the synchronous (direct) page reclaim code.
+
+A per-cpuset file provides an integer number representing the recent
+(half-life of 10 seconds) rate of direct page reclaims caused by
+the tasks in the cpuset, in units of reclaims attempted per second,
+times 1000.
+
+
+1.6 What is memory spread ?
+---------------------------
+There are two boolean flag files per cpuset that control where the
+kernel allocates pages for the file system buffers and related in
+kernel data structures.  They are called 'memory_spread_page' and
+'memory_spread_slab'.
+
+If the per-cpuset boolean flag file 'memory_spread_page' is set, then
+the kernel will spread the file system buffers (page cache) evenly
+over all the nodes that the faulting task is allowed to use, instead
+of preferring to put those pages on the node where the task is running.
+
+If the per-cpuset boolean flag file 'memory_spread_slab' is set,
+then the kernel will spread some file system related slab caches,
+such as for inodes and dentries evenly over all the nodes that the
+faulting task is allowed to use, instead of preferring to put those
+pages on the node where the task is running.
+
+The setting of these flags does not affect anonymous data segment or
+stack segment pages of a task.
+
+By default, both kinds of memory spreading are off, and memory
+pages are allocated on the node local to where the task is running,
+except perhaps as modified by the tasks NUMA mempolicy or cpuset
+configuration, so long as sufficient free memory pages are available.
+
+When new cpusets are created, they inherit the memory spread settings
+of their parent.
+
+Setting memory spreading causes allocations for the affected page
+or slab caches to ignore the tasks NUMA mempolicy and be spread
+instead.    Tasks using mbind() or set_mempolicy() calls to set NUMA
+mempolicies will not notice any change in these calls as a result of
+their containing tasks memory spread settings.  If memory spreading
+is turned off, then the currently specified NUMA mempolicy once again
+applies to memory page allocations.
+
+Both 'memory_spread_page' and 'memory_spread_slab' are boolean flag
+files.  By default they contain "0", meaning that the feature is off
+for that cpuset.  If a "1" is written to that file, then that turns
+the named feature on.
+
+The implementation is simple.
+
+Setting the flag 'memory_spread_page' turns on a per-process flag
+PF_SPREAD_PAGE for each task that is in that cpuset or subsequently
+joins that cpuset.  The page allocation calls for the page cache
+is modified to perform an inline check for this PF_SPREAD_PAGE task
+flag, and if set, a call to a new routine cpuset_mem_spread_node()
+returns the node to prefer for the allocation.
+
+Similarly, setting 'memory_spread_slab' turns on the flag
+PF_SPREAD_SLAB, and appropriately marked slab caches will allocate
+pages from the node returned by cpuset_mem_spread_node().
+
+The cpuset_mem_spread_node() routine is also simple.  It uses the
+value of a per-task rotor cpuset_mem_spread_rotor to select the next
+node in the current tasks mems_allowed to prefer for the allocation.
+
+This memory placement policy is also known (in other contexts) as
+round-robin or interleave.
+
+This policy can provide substantial improvements for jobs that need
+to place thread local data on the corresponding node, but that need
+to access large file system data sets that need to be spread across
+the several nodes in the jobs cpuset in order to fit.  Without this
+policy, especially for jobs that might have one thread reading in the
+data set, the memory allocation across the nodes in the jobs cpuset
+can become very uneven.
+
+1.7 What is sched_load_balance ?
+--------------------------------
+
+The kernel scheduler (kernel/sched.c) automatically load balances
+tasks.  If one CPU is underutilized, kernel code running on that
+CPU will look for tasks on other more overloaded CPUs and move those
+tasks to itself, within the constraints of such placement mechanisms
+as cpusets and sched_setaffinity.
+
+The algorithmic cost of load balancing and its impact on key shared
+kernel data structures such as the task list increases more than
+linearly with the number of CPUs being balanced.  So the scheduler
+has support to  partition the systems CPUs into a number of sched
+domains such that it only load balances within each sched domain.
+Each sched domain covers some subset of the CPUs in the system;
+no two sched domains overlap; some CPUs might not be in any sched
+domain and hence won't be load balanced.
+
+Put simply, it costs less to balance between two smaller sched domains
+than one big one, but doing so means that overloads in one of the
+two domains won't be load balanced to the other one.
+
+By default, there is one sched domain covering all CPUs, except those
+marked isolated using the kernel boot time "isolcpus=" argument.
+
+This default load balancing across all CPUs is not well suited for
+the following two situations:
+ 1) On large systems, load balancing across many CPUs is expensive.
+    If the system is managed using cpusets to place independent jobs
+    on separate sets of CPUs, full load balancing is unnecessary.
+ 2) Systems supporting realtime on some CPUs need to minimize
+    system overhead on those CPUs, including avoiding task load
+    balancing if that is not needed.
+
+When the per-cpuset flag "sched_load_balance" is enabled (the default
+setting), it requests that all the CPUs in that cpusets allowed 'cpus'
+be contained in a single sched domain, ensuring that load balancing
+can move a task (not otherwised pinned, as by sched_setaffinity)
+from any CPU in that cpuset to any other.
+
+When the per-cpuset flag "sched_load_balance" is disabled, then the
+scheduler will avoid load balancing across the CPUs in that cpuset,
+--except-- in so far as is necessary because some overlapping cpuset
+has "sched_load_balance" enabled.
+
+So, for example, if the top cpuset has the flag "sched_load_balance"
+enabled, then the scheduler will have one sched domain covering all
+CPUs, and the setting of the "sched_load_balance" flag in any other
+cpusets won't matter, as we're already fully load balancing.
+
+Therefore in the above two situations, the top cpuset flag
+"sched_load_balance" should be disabled, and only some of the smaller,
+child cpusets have this flag enabled.
+
+When doing this, you don't usually want to leave any unpinned tasks in
+the top cpuset that might use non-trivial amounts of CPU, as such tasks
+may be artificially constrained to some subset of CPUs, depending on
+the particulars of this flag setting in descendent cpusets.  Even if
+such a task could use spare CPU cycles in some other CPUs, the kernel
+scheduler might not consider the possibility of load balancing that
+task to that underused CPU.
+
+Of course, tasks pinned to a particular CPU can be left in a cpuset
+that disables "sched_load_balance" as those tasks aren't going anywhere
+else anyway.
+
+There is an impedance mismatch here, between cpusets and sched domains.
+Cpusets are hierarchical and nest.  Sched domains are flat; they don't
+overlap and each CPU is in at most one sched domain.
+
+It is necessary for sched domains to be flat because load balancing
+across partially overlapping sets of CPUs would risk unstable dynamics
+that would be beyond our understanding.  So if each of two partially
+overlapping cpusets enables the flag 'sched_load_balance', then we
+form a single sched domain that is a superset of both.  We won't move
+a task to a CPU outside it cpuset, but the scheduler load balancing
+code might waste some compute cycles considering that possibility.
+
+This mismatch is why there is not a simple one-to-one relation
+between which cpusets have the flag "sched_load_balance" enabled,
+and the sched domain configuration.  If a cpuset enables the flag, it
+will get balancing across all its CPUs, but if it disables the flag,
+it will only be assured of no load balancing if no other overlapping
+cpuset enables the flag.
+
+If two cpusets have partially overlapping 'cpus' allowed, and only
+one of them has this flag enabled, then the other may find its
+tasks only partially load balanced, just on the overlapping CPUs.
+This is just the general case of the top_cpuset example given a few
+paragraphs above.  In the general case, as in the top cpuset case,
+don't leave tasks that might use non-trivial amounts of CPU in
+such partially load balanced cpusets, as they may be artificially
+constrained to some subset of the CPUs allowed to them, for lack of
+load balancing to the other CPUs.
+
+1.7.1 sched_load_balance implementation details.
+------------------------------------------------
+
+The per-cpuset flag 'sched_load_balance' defaults to enabled (contrary
+to most cpuset flags.)  When enabled for a cpuset, the kernel will
+ensure that it can load balance across all the CPUs in that cpuset
+(makes sure that all the CPUs in the cpus_allowed of that cpuset are
+in the same sched domain.)
+
+If two overlapping cpusets both have 'sched_load_balance' enabled,
+then they will be (must be) both in the same sched domain.
+
+If, as is the default, the top cpuset has 'sched_load_balance' enabled,
+then by the above that means there is a single sched domain covering
+the whole system, regardless of any other cpuset settings.
+
+The kernel commits to user space that it will avoid load balancing
+where it can.  It will pick as fine a granularity partition of sched
+domains as it can while still providing load balancing for any set
+of CPUs allowed to a cpuset having 'sched_load_balance' enabled.
+
+The internal kernel cpuset to scheduler interface passes from the
+cpuset code to the scheduler code a partition of the load balanced
+CPUs in the system. This partition is a set of subsets (represented
+as an array of cpumask_t) of CPUs, pairwise disjoint, that cover all
+the CPUs that must be load balanced.
+
+Whenever the 'sched_load_balance' flag changes, or CPUs come or go
+from a cpuset with this flag enabled, or a cpuset with this flag
+enabled is removed, the cpuset code builds a new such partition and
+passes it to the scheduler sched domain setup code, to have the sched
+domains rebuilt as necessary.
+
+This partition exactly defines what sched domains the scheduler should
+setup - one sched domain for each element (cpumask_t) in the partition.
+
+The scheduler remembers the currently active sched domain partitions.
+When the scheduler routine partition_sched_domains() is invoked from
+the cpuset code to update these sched domains, it compares the new
+partition requested with the current, and updates its sched domains,
+removing the old and adding the new, for each change.
+
+
+1.8 What is sched_relax_domain_level ?
+--------------------------------------
+
+In sched domain, the scheduler migrates tasks in 2 ways; periodic load
+balance on tick, and at time of some schedule events.
+
+When a task is woken up, scheduler try to move the task on idle CPU.
+For example, if a task A running on CPU X activates another task B
+on the same CPU X, and if CPU Y is X's sibling and performing idle,
+then scheduler migrate task B to CPU Y so that task B can start on
+CPU Y without waiting task A on CPU X.
+
+And if a CPU run out of tasks in its runqueue, the CPU try to pull
+extra tasks from other busy CPUs to help them before it is going to
+be idle.
+
+Of course it takes some searching cost to find movable tasks and/or
+idle CPUs, the scheduler might not search all CPUs in the domain
+everytime.  In fact, in some architectures, the searching ranges on
+events are limited in the same socket or node where the CPU locates,
+while the load balance on tick searchs all.
+
+For example, assume CPU Z is relatively far from CPU X.  Even if CPU Z
+is idle while CPU X and the siblings are busy, scheduler can't migrate
+woken task B from X to Z since it is out of its searching range.
+As the result, task B on CPU X need to wait task A or wait load balance
+on the next tick.  For some applications in special situation, waiting
+1 tick may be too long.
+
+The 'sched_relax_domain_level' file allows you to request changing
+this searching range as you like.  This file takes int value which
+indicates size of searching range in levels ideally as follows,
+otherwise initial value -1 that indicates the cpuset has no request.
+
+  -1  : no request. use system default or follow request of others.
+   0  : no search.
+   1  : search siblings (hyperthreads in a core).
+   2  : search cores in a package.
+   3  : search cpus in a node [= system wide on non-NUMA system]
+ ( 4  : search nodes in a chunk of node [on NUMA system] )
+ ( 5  : search system wide [on NUMA system] )
+
+The system default is architecture dependent.  The system default
+can be changed using the relax_domain_level= boot parameter.
+
+This file is per-cpuset and affect the sched domain where the cpuset
+belongs to.  Therefore if the flag 'sched_load_balance' of a cpuset
+is disabled, then 'sched_relax_domain_level' have no effect since
+there is no sched domain belonging the cpuset.
+
+If multiple cpusets are overlapping and hence they form a single sched
+domain, the largest value among those is used.  Be careful, if one
+requests 0 and others are -1 then 0 is used.
+
+Note that modifying this file will have both good and bad effects,
+and whether it is acceptable or not will be depend on your situation.
+Don't modify this file if you are not sure.
+
+If your situation is:
+ - The migration costs between each cpu can be assumed considerably
+   small(for you) due to your special application's behavior or
+   special hardware support for CPU cache etc.
+ - The searching cost doesn't have impact(for you) or you can make
+   the searching cost enough small by managing cpuset to compact etc.
+ - The latency is required even it sacrifices cache hit rate etc.
+then increasing 'sched_relax_domain_level' would benefit you.
+
+
+1.9 How do I use cpusets ?
+--------------------------
+
+In order to minimize the impact of cpusets on critical kernel
+code, such as the scheduler, and due to the fact that the kernel
+does not support one task updating the memory placement of another
+task directly, the impact on a task of changing its cpuset CPU
+or Memory Node placement, or of changing to which cpuset a task
+is attached, is subtle.
+
+If a cpuset has its Memory Nodes modified, then for each task attached
+to that cpuset, the next time that the kernel attempts to allocate
+a page of memory for that task, the kernel will notice the change
+in the tasks cpuset, and update its per-task memory placement to
+remain within the new cpusets memory placement.  If the task was using
+mempolicy MPOL_BIND, and the nodes to which it was bound overlap with
+its new cpuset, then the task will continue to use whatever subset
+of MPOL_BIND nodes are still allowed in the new cpuset.  If the task
+was using MPOL_BIND and now none of its MPOL_BIND nodes are allowed
+in the new cpuset, then the task will be essentially treated as if it
+was MPOL_BIND bound to the new cpuset (even though its numa placement,
+as queried by get_mempolicy(), doesn't change).  If a task is moved
+from one cpuset to another, then the kernel will adjust the tasks
+memory placement, as above, the next time that the kernel attempts
+to allocate a page of memory for that task.
+
+If a cpuset has its 'cpus' modified, then each task in that cpuset
+will have its allowed CPU placement changed immediately.  Similarly,
+if a tasks pid is written to a cpusets 'tasks' file, in either its
+current cpuset or another cpuset, then its allowed CPU placement is
+changed immediately.  If such a task had been bound to some subset
+of its cpuset using the sched_setaffinity() call, the task will be
+allowed to run on any CPU allowed in its new cpuset, negating the
+affect of the prior sched_setaffinity() call.
+
+In summary, the memory placement of a task whose cpuset is changed is
+updated by the kernel, on the next allocation of a page for that task,
+but the processor placement is not updated, until that tasks pid is
+rewritten to the 'tasks' file of its cpuset.  This is done to avoid
+impacting the scheduler code in the kernel with a check for changes
+in a tasks processor placement.
+
+Normally, once a page is allocated (given a physical page
+of main memory) then that page stays on whatever node it
+was allocated, so long as it remains allocated, even if the
+cpusets memory placement policy 'mems' subsequently changes.
+If the cpuset flag file 'memory_migrate' is set true, then when
+tasks are attached to that cpuset, any pages that task had
+allocated to it on nodes in its previous cpuset are migrated
+to the tasks new cpuset. The relative placement of the page within
+the cpuset is preserved during these migration operations if possible.
+For example if the page was on the second valid node of the prior cpuset
+then the page will be placed on the second valid node of the new cpuset.
+
+Also if 'memory_migrate' is set true, then if that cpusets
+'mems' file is modified, pages allocated to tasks in that
+cpuset, that were on nodes in the previous setting of 'mems',
+will be moved to nodes in the new setting of 'mems.'
+Pages that were not in the tasks prior cpuset, or in the cpusets
+prior 'mems' setting, will not be moved.
+
+There is an exception to the above.  If hotplug functionality is used
+to remove all the CPUs that are currently assigned to a cpuset,
+then all the tasks in that cpuset will be moved to the nearest ancestor
+with non-empty cpus.  But the moving of some (or all) tasks might fail if
+cpuset is bound with another cgroup subsystem which has some restrictions
+on task attaching.  In this failing case, those tasks will stay
+in the original cpuset, and the kernel will automatically update
+their cpus_allowed to allow all online CPUs.  When memory hotplug
+functionality for removing Memory Nodes is available, a similar exception
+is expected to apply there as well.  In general, the kernel prefers to
+violate cpuset placement, over starving a task that has had all
+its allowed CPUs or Memory Nodes taken offline.
+
+There is a second exception to the above.  GFP_ATOMIC requests are
+kernel internal allocations that must be satisfied, immediately.
+The kernel may drop some request, in rare cases even panic, if a
+GFP_ATOMIC alloc fails.  If the request cannot be satisfied within
+the current tasks cpuset, then we relax the cpuset, and look for
+memory anywhere we can find it.  It's better to violate the cpuset
+than stress the kernel.
+
+To start a new job that is to be contained within a cpuset, the steps are:
+
+ 1) mkdir /dev/cpuset
+ 2) mount -t cgroup -ocpuset cpuset /dev/cpuset
+ 3) Create the new cpuset by doing mkdir's and write's (or echo's) in
+    the /dev/cpuset virtual file system.
+ 4) Start a task that will be the "founding father" of the new job.
+ 5) Attach that task to the new cpuset by writing its pid to the
+    /dev/cpuset tasks file for that cpuset.
+ 6) fork, exec or clone the job tasks from this founding father task.
+
+For example, the following sequence of commands will setup a cpuset
+named "Charlie", containing just CPUs 2 and 3, and Memory Node 1,
+and then start a subshell 'sh' in that cpuset:
+
+  mount -t cgroup -ocpuset cpuset /dev/cpuset
+  cd /dev/cpuset
+  mkdir Charlie
+  cd Charlie
+  /bin/echo 2-3 > cpus
+  /bin/echo 1 > mems
+  /bin/echo $$ > tasks
+  sh
+  # The subshell 'sh' is now running in cpuset Charlie
+  # The next line should display '/Charlie'
+  cat /proc/self/cpuset
+
+In the future, a C library interface to cpusets will likely be
+available.  For now, the only way to query or modify cpusets is
+via the cpuset file system, using the various cd, mkdir, echo, cat,
+rmdir commands from the shell, or their equivalent from C.
+
+The sched_setaffinity calls can also be done at the shell prompt using
+SGI's runon or Robert Love's taskset.  The mbind and set_mempolicy
+calls can be done at the shell prompt using the numactl command
+(part of Andi Kleen's numa package).
+
+2. Usage Examples and Syntax
+============================
+
+2.1 Basic Usage
+---------------
+
+Creating, modifying, using the cpusets can be done through the cpuset
+virtual filesystem.
+
+To mount it, type:
+# mount -t cgroup -o cpuset cpuset /dev/cpuset
+
+Then under /dev/cpuset you can find a tree that corresponds to the
+tree of the cpusets in the system. For instance, /dev/cpuset
+is the cpuset that holds the whole system.
+
+If you want to create a new cpuset under /dev/cpuset:
+# cd /dev/cpuset
+# mkdir my_cpuset
+
+Now you want to do something with this cpuset.
+# cd my_cpuset
+
+In this directory you can find several files:
+# ls
+cpu_exclusive  memory_migrate      mems                      tasks
+cpus           memory_pressure     notify_on_release
+mem_exclusive  memory_spread_page  sched_load_balance
+mem_hardwall   memory_spread_slab  sched_relax_domain_level
+
+Reading them will give you information about the state of this cpuset:
+the CPUs and Memory Nodes it can use, the processes that are using
+it, its properties.  By writing to these files you can manipulate
+the cpuset.
+
+Set some flags:
+# /bin/echo 1 > cpu_exclusive
+
+Add some cpus:
+# /bin/echo 0-7 > cpus
+
+Add some mems:
+# /bin/echo 0-7 > mems
+
+Now attach your shell to this cpuset:
+# /bin/echo $$ > tasks
+
+You can also create cpusets inside your cpuset by using mkdir in this
+directory.
+# mkdir my_sub_cs
+
+To remove a cpuset, just use rmdir:
+# rmdir my_sub_cs
+This will fail if the cpuset is in use (has cpusets inside, or has
+processes attached).
+
+Note that for legacy reasons, the "cpuset" filesystem exists as a
+wrapper around the cgroup filesystem.
+
+The command
+
+mount -t cpuset X /dev/cpuset
+
+is equivalent to
+
+mount -t cgroup -ocpuset X /dev/cpuset
+echo "/sbin/cpuset_release_agent" > /dev/cpuset/release_agent
+
+2.2 Adding/removing cpus
+------------------------
+
+This is the syntax to use when writing in the cpus or mems files
+in cpuset directories:
+
+# /bin/echo 1-4 > cpus		-> set cpus list to cpus 1,2,3,4
+# /bin/echo 1,2,3,4 > cpus	-> set cpus list to cpus 1,2,3,4
+
+2.3 Setting flags
+-----------------
+
+The syntax is very simple:
+
+# /bin/echo 1 > cpu_exclusive 	-> set flag 'cpu_exclusive'
+# /bin/echo 0 > cpu_exclusive 	-> unset flag 'cpu_exclusive'
+
+2.4 Attaching processes
+-----------------------
+
+# /bin/echo PID > tasks
+
+Note that it is PID, not PIDs. You can only attach ONE task at a time.
+If you have several tasks to attach, you have to do it one after another:
+
+# /bin/echo PID1 > tasks
+# /bin/echo PID2 > tasks
+	...
+# /bin/echo PIDn > tasks
+
+
+3. Questions
+============
+
+Q: what's up with this '/bin/echo' ?
+A: bash's builtin 'echo' command does not check calls to write() against
+   errors. If you use it in the cpuset file system, you won't be
+   able to tell whether a command succeeded or failed.
+
+Q: When I attach processes, only the first of the line gets really attached !
+A: We can only return one error code per call to write(). So you should also
+   put only ONE pid.
+
+4. Contact
+==========
+
+Web: http://www.bullopensource.org/cpuset
diff --git a/Documentation/cgroups/devices.txt b/Documentation/cgroups/devices.txt
new file mode 100644
index 000000000000..7cc6e6a60672
--- /dev/null
+++ b/Documentation/cgroups/devices.txt
@@ -0,0 +1,52 @@
+Device Whitelist Controller
+
+1. Description:
+
+Implement a cgroup to track and enforce open and mknod restrictions
+on device files.  A device cgroup associates a device access
+whitelist with each cgroup.  A whitelist entry has 4 fields.
+'type' is a (all), c (char), or b (block).  'all' means it applies
+to all types and all major and minor numbers.  Major and minor are
+either an integer or * for all.  Access is a composition of r
+(read), w (write), and m (mknod).
+
+The root device cgroup starts with rwm to 'all'.  A child device
+cgroup gets a copy of the parent.  Administrators can then remove
+devices from the whitelist or add new entries.  A child cgroup can
+never receive a device access which is denied by its parent.  However
+when a device access is removed from a parent it will not also be
+removed from the child(ren).
+
+2. User Interface
+
+An entry is added using devices.allow, and removed using
+devices.deny.  For instance
+
+	echo 'c 1:3 mr' > /cgroups/1/devices.allow
+
+allows cgroup 1 to read and mknod the device usually known as
+/dev/null.  Doing
+
+	echo a > /cgroups/1/devices.deny
+
+will remove the default 'a *:* rwm' entry. Doing
+
+	echo a > /cgroups/1/devices.allow
+
+will add the 'a *:* rwm' entry to the whitelist.
+
+3. Security
+
+Any task can move itself between cgroups.  This clearly won't
+suffice, but we can decide the best way to adequately restrict
+movement as people get some experience with this.  We may just want
+to require CAP_SYS_ADMIN, which at least is a separate bit from
+CAP_MKNOD.  We may want to just refuse moving to a cgroup which
+isn't a descendent of the current one.  Or we may want to use
+CAP_MAC_ADMIN, since we really are trying to lock down root.
+
+CAP_SYS_ADMIN is needed to modify the whitelist or move another
+task to a new cgroup.  (Again we'll probably want to change that).
+
+A cgroup may not be granted more permissions than the cgroup's
+parent has.
diff --git a/Documentation/cgroups/memcg_test.txt b/Documentation/cgroups/memcg_test.txt
new file mode 100644
index 000000000000..19533f93b7a2
--- /dev/null
+++ b/Documentation/cgroups/memcg_test.txt
@@ -0,0 +1,342 @@
+Memory Resource Controller(Memcg)  Implementation Memo.
+Last Updated: 2008/12/15
+Base Kernel Version: based on 2.6.28-rc8-mm.
+
+Because VM is getting complex (one of reasons is memcg...), memcg's behavior
+is complex. This is a document for memcg's internal behavior.
+Please note that implementation details can be changed.
+
+(*) Topics on API should be in Documentation/cgroups/memory.txt)
+
+0. How to record usage ?
+   2 objects are used.
+
+   page_cgroup ....an object per page.
+	Allocated at boot or memory hotplug. Freed at memory hot removal.
+
+   swap_cgroup ... an entry per swp_entry.
+	Allocated at swapon(). Freed at swapoff().
+
+   The page_cgroup has USED bit and double count against a page_cgroup never
+   occurs. swap_cgroup is used only when a charged page is swapped-out.
+
+1. Charge
+
+   a page/swp_entry may be charged (usage += PAGE_SIZE) at
+
+	mem_cgroup_newpage_charge()
+	  Called at new page fault and Copy-On-Write.
+
+	mem_cgroup_try_charge_swapin()
+	  Called at do_swap_page() (page fault on swap entry) and swapoff.
+	  Followed by charge-commit-cancel protocol. (With swap accounting)
+	  At commit, a charge recorded in swap_cgroup is removed.
+
+	mem_cgroup_cache_charge()
+	  Called at add_to_page_cache()
+
+	mem_cgroup_cache_charge_swapin()
+	  Called at shmem's swapin.
+
+	mem_cgroup_prepare_migration()
+	  Called before migration. "extra" charge is done and followed by
+	  charge-commit-cancel protocol.
+	  At commit, charge against oldpage or newpage will be committed.
+
+2. Uncharge
+  a page/swp_entry may be uncharged (usage -= PAGE_SIZE) by
+
+	mem_cgroup_uncharge_page()
+	  Called when an anonymous page is fully unmapped. I.e., mapcount goes
+	  to 0. If the page is SwapCache, uncharge is delayed until
+	  mem_cgroup_uncharge_swapcache().
+
+	mem_cgroup_uncharge_cache_page()
+	  Called when a page-cache is deleted from radix-tree. If the page is
+	  SwapCache, uncharge is delayed until mem_cgroup_uncharge_swapcache().
+
+	mem_cgroup_uncharge_swapcache()
+	  Called when SwapCache is removed from radix-tree. The charge itself
+	  is moved to swap_cgroup. (If mem+swap controller is disabled, no
+	  charge to swap occurs.)
+
+	mem_cgroup_uncharge_swap()
+	  Called when swp_entry's refcnt goes down to 0. A charge against swap
+	  disappears.
+
+	mem_cgroup_end_migration(old, new)
+	At success of migration old is uncharged (if necessary), a charge
+	to new page is committed. At failure, charge to old page is committed.
+
+3. charge-commit-cancel
+	In some case, we can't know this "charge" is valid or not at charging
+	(because of races).
+	To handle such case, there are charge-commit-cancel functions.
+		mem_cgroup_try_charge_XXX
+		mem_cgroup_commit_charge_XXX
+		mem_cgroup_cancel_charge_XXX
+	these are used in swap-in and migration.
+
+	At try_charge(), there are no flags to say "this page is charged".
+	at this point, usage += PAGE_SIZE.
+
+	At commit(), the function checks the page should be charged or not
+	and set flags or avoid charging.(usage -= PAGE_SIZE)
+
+	At cancel(), simply usage -= PAGE_SIZE.
+
+Under below explanation, we assume CONFIG_MEM_RES_CTRL_SWAP=y.
+
+4. Anonymous
+	Anonymous page is newly allocated at
+		  - page fault into MAP_ANONYMOUS mapping.
+		  - Copy-On-Write.
+ 	It is charged right after it's allocated before doing any page table
+	related operations. Of course, it's uncharged when another page is used
+	for the fault address.
+
+	At freeing anonymous page (by exit() or munmap()), zap_pte() is called
+	and pages for ptes are freed one by one.(see mm/memory.c). Uncharges
+	are done at page_remove_rmap() when page_mapcount() goes down to 0.
+
+	Another page freeing is by page-reclaim (vmscan.c) and anonymous
+	pages are swapped out. In this case, the page is marked as
+	PageSwapCache(). uncharge() routine doesn't uncharge the page marked
+	as SwapCache(). It's delayed until __delete_from_swap_cache().
+
+	4.1 Swap-in.
+	At swap-in, the page is taken from swap-cache. There are 2 cases.
+
+	(a) If the SwapCache is newly allocated and read, it has no charges.
+	(b) If the SwapCache has been mapped by processes, it has been
+	    charged already.
+
+	This swap-in is one of the most complicated work. In do_swap_page(),
+	following events occur when pte is unchanged.
+
+	(1) the page (SwapCache) is looked up.
+	(2) lock_page()
+	(3) try_charge_swapin()
+	(4) reuse_swap_page() (may call delete_swap_cache())
+	(5) commit_charge_swapin()
+	(6) swap_free().
+
+	Considering following situation for example.
+
+	(A) The page has not been charged before (2) and reuse_swap_page()
+	    doesn't call delete_from_swap_cache().
+	(B) The page has not been charged before (2) and reuse_swap_page()
+	    calls delete_from_swap_cache().
+	(C) The page has been charged before (2) and reuse_swap_page() doesn't
+	    call delete_from_swap_cache().
+	(D) The page has been charged before (2) and reuse_swap_page() calls
+	    delete_from_swap_cache().
+
+	    memory.usage/memsw.usage changes to this page/swp_entry will be
+	 Case          (A)      (B)       (C)     (D)
+         Event
+       Before (2)     0/ 1     0/ 1      1/ 1    1/ 1
+          ===========================================
+          (3)        +1/+1    +1/+1     +1/+1   +1/+1
+          (4)          -       0/ 0       -     -1/ 0
+          (5)         0/-1     0/ 0     -1/-1    0/ 0
+          (6)          -       0/-1       -      0/-1
+          ===========================================
+       Result         1/ 1     1/ 1      1/ 1    1/ 1
+
+       In any cases, charges to this page should be 1/ 1.
+
+	4.2 Swap-out.
+	At swap-out, typical state transition is below.
+
+	(a) add to swap cache. (marked as SwapCache)
+	    swp_entry's refcnt += 1.
+	(b) fully unmapped.
+	    swp_entry's refcnt += # of ptes.
+	(c) write back to swap.
+	(d) delete from swap cache. (remove from SwapCache)
+	    swp_entry's refcnt -= 1.
+
+
+	At (b), the page is marked as SwapCache and not uncharged.
+	At (d), the page is removed from SwapCache and a charge in page_cgroup
+	is moved to swap_cgroup.
+
+	Finally, at task exit,
+	(e) zap_pte() is called and swp_entry's refcnt -=1 -> 0.
+	Here, a charge in swap_cgroup disappears.
+
+5. Page Cache
+   	Page Cache is charged at
+	- add_to_page_cache_locked().
+
+	uncharged at
+	- __remove_from_page_cache().
+
+	The logic is very clear. (About migration, see below)
+	Note: __remove_from_page_cache() is called by remove_from_page_cache()
+	and __remove_mapping().
+
+6. Shmem(tmpfs) Page Cache
+	Memcg's charge/uncharge have special handlers of shmem. The best way
+	to understand shmem's page state transition is to read mm/shmem.c.
+	But brief explanation of the behavior of memcg around shmem will be
+	helpful to understand the logic.
+
+	Shmem's page (just leaf page, not direct/indirect block) can be on
+		- radix-tree of shmem's inode.
+		- SwapCache.
+		- Both on radix-tree and SwapCache. This happens at swap-in
+		  and swap-out,
+
+	It's charged when...
+	- A new page is added to shmem's radix-tree.
+	- A swp page is read. (move a charge from swap_cgroup to page_cgroup)
+	It's uncharged when
+	- A page is removed from radix-tree and not SwapCache.
+	- When SwapCache is removed, a charge is moved to swap_cgroup.
+	- When swp_entry's refcnt goes down to 0, a charge in swap_cgroup
+	  disappears.
+
+7. Page Migration
+   	One of the most complicated functions is page-migration-handler.
+	Memcg has 2 routines. Assume that we are migrating a page's contents
+	from OLDPAGE to NEWPAGE.
+
+	Usual migration logic is..
+	(a) remove the page from LRU.
+	(b) allocate NEWPAGE (migration target)
+	(c) lock by lock_page().
+	(d) unmap all mappings.
+	(e-1) If necessary, replace entry in radix-tree.
+	(e-2) move contents of a page.
+	(f) map all mappings again.
+	(g) pushback the page to LRU.
+	(-) OLDPAGE will be freed.
+
+	Before (g), memcg should complete all necessary charge/uncharge to
+	NEWPAGE/OLDPAGE.
+
+	The point is....
+	- If OLDPAGE is anonymous, all charges will be dropped at (d) because
+          try_to_unmap() drops all mapcount and the page will not be
+	  SwapCache.
+
+	- If OLDPAGE is SwapCache, charges will be kept at (g) because
+	  __delete_from_swap_cache() isn't called at (e-1)
+
+	- If OLDPAGE is page-cache, charges will be kept at (g) because
+	  remove_from_swap_cache() isn't called at (e-1)
+
+	memcg provides following hooks.
+
+	- mem_cgroup_prepare_migration(OLDPAGE)
+	  Called after (b) to account a charge (usage += PAGE_SIZE) against
+	  memcg which OLDPAGE belongs to.
+
+        - mem_cgroup_end_migration(OLDPAGE, NEWPAGE)
+	  Called after (f) before (g).
+	  If OLDPAGE is used, commit OLDPAGE again. If OLDPAGE is already
+	  charged, a charge by prepare_migration() is automatically canceled.
+	  If NEWPAGE is used, commit NEWPAGE and uncharge OLDPAGE.
+
+	  But zap_pte() (by exit or munmap) can be called while migration,
+	  we have to check if OLDPAGE/NEWPAGE is a valid page after commit().
+
+8. LRU
+        Each memcg has its own private LRU. Now, it's handling is under global
+	VM's control (means that it's handled under global zone->lru_lock).
+	Almost all routines around memcg's LRU is called by global LRU's
+	list management functions under zone->lru_lock().
+
+	A special function is mem_cgroup_isolate_pages(). This scans
+	memcg's private LRU and call __isolate_lru_page() to extract a page
+	from LRU.
+	(By __isolate_lru_page(), the page is removed from both of global and
+	 private LRU.)
+
+
+9. Typical Tests.
+
+ Tests for racy cases.
+
+ 9.1 Small limit to memcg.
+	When you do test to do racy case, it's good test to set memcg's limit
+	to be very small rather than GB. Many races found in the test under
+	xKB or xxMB limits.
+	(Memory behavior under GB and Memory behavior under MB shows very
+	 different situation.)
+
+ 9.2 Shmem
+	Historically, memcg's shmem handling was poor and we saw some amount
+	of troubles here. This is because shmem is page-cache but can be
+	SwapCache. Test with shmem/tmpfs is always good test.
+
+ 9.3 Migration
+	For NUMA, migration is an another special case. To do easy test, cpuset
+	is useful. Following is a sample script to do migration.
+
+	mount -t cgroup -o cpuset none /opt/cpuset
+
+	mkdir /opt/cpuset/01
+	echo 1 > /opt/cpuset/01/cpuset.cpus
+	echo 0 > /opt/cpuset/01/cpuset.mems
+	echo 1 > /opt/cpuset/01/cpuset.memory_migrate
+	mkdir /opt/cpuset/02
+	echo 1 > /opt/cpuset/02/cpuset.cpus
+	echo 1 > /opt/cpuset/02/cpuset.mems
+	echo 1 > /opt/cpuset/02/cpuset.memory_migrate
+
+	In above set, when you moves a task from 01 to 02, page migration to
+	node 0 to node 1 will occur. Following is a script to migrate all
+	under cpuset.
+	--
+	move_task()
+	{
+	for pid in $1
+        do
+                /bin/echo $pid >$2/tasks 2>/dev/null
+		echo -n $pid
+		echo -n " "
+        done
+	echo END
+	}
+
+	G1_TASK=`cat ${G1}/tasks`
+	G2_TASK=`cat ${G2}/tasks`
+	move_task "${G1_TASK}" ${G2} &
+	--
+ 9.4 Memory hotplug.
+	memory hotplug test is one of good test.
+	to offline memory, do following.
+	# echo offline > /sys/devices/system/memory/memoryXXX/state
+	(XXX is the place of memory)
+	This is an easy way to test page migration, too.
+
+ 9.5 mkdir/rmdir
+	When using hierarchy, mkdir/rmdir test should be done.
+	Use tests like the following.
+
+	echo 1 >/opt/cgroup/01/memory/use_hierarchy
+	mkdir /opt/cgroup/01/child_a
+	mkdir /opt/cgroup/01/child_b
+
+	set limit to 01.
+	add limit to 01/child_b
+	run jobs under child_a and child_b
+
+	create/delete following groups at random while jobs are running.
+	/opt/cgroup/01/child_a/child_aa
+	/opt/cgroup/01/child_b/child_bb
+	/opt/cgroup/01/child_c
+
+	running new jobs in new group is also good.
+
+ 9.6 Mount with other subsystems.
+	Mounting with other subsystems is a good test because there is a
+	race and lock dependency with other cgroup subsystems.
+
+	example)
+	# mount -t cgroup none /cgroup -t cpuset,memory,cpu,devices
+
+	and do task move, mkdir, rmdir etc...under this.
diff --git a/Documentation/cgroups/memory.txt b/Documentation/cgroups/memory.txt
new file mode 100644
index 000000000000..e1501964df1e
--- /dev/null
+++ b/Documentation/cgroups/memory.txt
@@ -0,0 +1,399 @@
+Memory Resource Controller
+
+NOTE: The Memory Resource Controller has been generically been referred
+to as the memory controller in this document. Do not confuse memory controller
+used here with the memory controller that is used in hardware.
+
+Salient features
+
+a. Enable control of both RSS (mapped) and Page Cache (unmapped) pages
+b. The infrastructure allows easy addition of other types of memory to control
+c. Provides *zero overhead* for non memory controller users
+d. Provides a double LRU: global memory pressure causes reclaim from the
+   global LRU; a cgroup on hitting a limit, reclaims from the per
+   cgroup LRU
+
+NOTE: Swap Cache (unmapped) is not accounted now.
+
+Benefits and Purpose of the memory controller
+
+The memory controller isolates the memory behaviour of a group of tasks
+from the rest of the system. The article on LWN [12] mentions some probable
+uses of the memory controller. The memory controller can be used to
+
+a. Isolate an application or a group of applications
+   Memory hungry applications can be isolated and limited to a smaller
+   amount of memory.
+b. Create a cgroup with limited amount of memory, this can be used
+   as a good alternative to booting with mem=XXXX.
+c. Virtualization solutions can control the amount of memory they want
+   to assign to a virtual machine instance.
+d. A CD/DVD burner could control the amount of memory used by the
+   rest of the system to ensure that burning does not fail due to lack
+   of available memory.
+e. There are several other use cases, find one or use the controller just
+   for fun (to learn and hack on the VM subsystem).
+
+1. History
+
+The memory controller has a long history. A request for comments for the memory
+controller was posted by Balbir Singh [1]. At the time the RFC was posted
+there were several implementations for memory control. The goal of the
+RFC was to build consensus and agreement for the minimal features required
+for memory control. The first RSS controller was posted by Balbir Singh[2]
+in Feb 2007. Pavel Emelianov [3][4][5] has since posted three versions of the
+RSS controller. At OLS, at the resource management BoF, everyone suggested
+that we handle both page cache and RSS together. Another request was raised
+to allow user space handling of OOM. The current memory controller is
+at version 6; it combines both mapped (RSS) and unmapped Page
+Cache Control [11].
+
+2. Memory Control
+
+Memory is a unique resource in the sense that it is present in a limited
+amount. If a task requires a lot of CPU processing, the task can spread
+its processing over a period of hours, days, months or years, but with
+memory, the same physical memory needs to be reused to accomplish the task.
+
+The memory controller implementation has been divided into phases. These
+are:
+
+1. Memory controller
+2. mlock(2) controller
+3. Kernel user memory accounting and slab control
+4. user mappings length controller
+
+The memory controller is the first controller developed.
+
+2.1. Design
+
+The core of the design is a counter called the res_counter. The res_counter
+tracks the current memory usage and limit of the group of processes associated
+with the controller. Each cgroup has a memory controller specific data
+structure (mem_cgroup) associated with it.
+
+2.2. Accounting
+
+		+--------------------+
+		|  mem_cgroup     |
+		|  (res_counter)     |
+		+--------------------+
+		 /            ^      \
+		/             |       \
+           +---------------+  |        +---------------+
+           | mm_struct     |  |....    | mm_struct     |
+           |               |  |        |               |
+           +---------------+  |        +---------------+
+                              |
+                              + --------------+
+                                              |
+           +---------------+           +------+--------+
+           | page          +---------->  page_cgroup|
+           |               |           |               |
+           +---------------+           +---------------+
+
+             (Figure 1: Hierarchy of Accounting)
+
+
+Figure 1 shows the important aspects of the controller
+
+1. Accounting happens per cgroup
+2. Each mm_struct knows about which cgroup it belongs to
+3. Each page has a pointer to the page_cgroup, which in turn knows the
+   cgroup it belongs to
+
+The accounting is done as follows: mem_cgroup_charge() is invoked to setup
+the necessary data structures and check if the cgroup that is being charged
+is over its limit. If it is then reclaim is invoked on the cgroup.
+More details can be found in the reclaim section of this document.
+If everything goes well, a page meta-data-structure called page_cgroup is
+allocated and associated with the page.  This routine also adds the page to
+the per cgroup LRU.
+
+2.2.1 Accounting details
+
+All mapped anon pages (RSS) and cache pages (Page Cache) are accounted.
+(some pages which never be reclaimable and will not be on global LRU
+ are not accounted. we just accounts pages under usual vm management.)
+
+RSS pages are accounted at page_fault unless they've already been accounted
+for earlier. A file page will be accounted for as Page Cache when it's
+inserted into inode (radix-tree). While it's mapped into the page tables of
+processes, duplicate accounting is carefully avoided.
+
+A RSS page is unaccounted when it's fully unmapped. A PageCache page is
+unaccounted when it's removed from radix-tree.
+
+At page migration, accounting information is kept.
+
+Note: we just account pages-on-lru because our purpose is to control amount
+of used pages. not-on-lru pages are tend to be out-of-control from vm view.
+
+2.3 Shared Page Accounting
+
+Shared pages are accounted on the basis of the first touch approach. The
+cgroup that first touches a page is accounted for the page. The principle
+behind this approach is that a cgroup that aggressively uses a shared
+page will eventually get charged for it (once it is uncharged from
+the cgroup that brought it in -- this will happen on memory pressure).
+
+Exception: If CONFIG_CGROUP_CGROUP_MEM_RES_CTLR_SWAP is not used..
+When you do swapoff and make swapped-out pages of shmem(tmpfs) to
+be backed into memory in force, charges for pages are accounted against the
+caller of swapoff rather than the users of shmem.
+
+
+2.4 Swap Extension (CONFIG_CGROUP_MEM_RES_CTLR_SWAP)
+Swap Extension allows you to record charge for swap. A swapped-in page is
+charged back to original page allocator if possible.
+
+When swap is accounted, following files are added.
+ - memory.memsw.usage_in_bytes.
+ - memory.memsw.limit_in_bytes.
+
+usage of mem+swap is limited by memsw.limit_in_bytes.
+
+Note: why 'mem+swap' rather than swap.
+The global LRU(kswapd) can swap out arbitrary pages. Swap-out means
+to move account from memory to swap...there is no change in usage of
+mem+swap.
+
+In other words, when we want to limit the usage of swap without affecting
+global LRU, mem+swap limit is better than just limiting swap from OS point
+of view.
+
+2.5 Reclaim
+
+Each cgroup maintains a per cgroup LRU that consists of an active
+and inactive list. When a cgroup goes over its limit, we first try
+to reclaim memory from the cgroup so as to make space for the new
+pages that the cgroup has touched. If the reclaim is unsuccessful,
+an OOM routine is invoked to select and kill the bulkiest task in the
+cgroup.
+
+The reclaim algorithm has not been modified for cgroups, except that
+pages that are selected for reclaiming come from the per cgroup LRU
+list.
+
+2. Locking
+
+The memory controller uses the following hierarchy
+
+1. zone->lru_lock is used for selecting pages to be isolated
+2. mem->per_zone->lru_lock protects the per cgroup LRU (per zone)
+3. lock_page_cgroup() is used to protect page->page_cgroup
+
+3. User Interface
+
+0. Configuration
+
+a. Enable CONFIG_CGROUPS
+b. Enable CONFIG_RESOURCE_COUNTERS
+c. Enable CONFIG_CGROUP_MEM_RES_CTLR
+
+1. Prepare the cgroups
+# mkdir -p /cgroups
+# mount -t cgroup none /cgroups -o memory
+
+2. Make the new group and move bash into it
+# mkdir /cgroups/0
+# echo $$ >  /cgroups/0/tasks
+
+Since now we're in the 0 cgroup,
+We can alter the memory limit:
+# echo 4M > /cgroups/0/memory.limit_in_bytes
+
+NOTE: We can use a suffix (k, K, m, M, g or G) to indicate values in kilo,
+mega or gigabytes.
+
+# cat /cgroups/0/memory.limit_in_bytes
+4194304
+
+NOTE: The interface has now changed to display the usage in bytes
+instead of pages
+
+We can check the usage:
+# cat /cgroups/0/memory.usage_in_bytes
+1216512
+
+A successful write to this file does not guarantee a successful set of
+this limit to the value written into the file.  This can be due to a
+number of factors, such as rounding up to page boundaries or the total
+availability of memory on the system.  The user is required to re-read
+this file after a write to guarantee the value committed by the kernel.
+
+# echo 1 > memory.limit_in_bytes
+# cat memory.limit_in_bytes
+4096
+
+The memory.failcnt field gives the number of times that the cgroup limit was
+exceeded.
+
+The memory.stat file gives accounting information. Now, the number of
+caches, RSS and Active pages/Inactive pages are shown.
+
+4. Testing
+
+Balbir posted lmbench, AIM9, LTP and vmmstress results [10] and [11].
+Apart from that v6 has been tested with several applications and regular
+daily use. The controller has also been tested on the PPC64, x86_64 and
+UML platforms.
+
+4.1 Troubleshooting
+
+Sometimes a user might find that the application under a cgroup is
+terminated. There are several causes for this:
+
+1. The cgroup limit is too low (just too low to do anything useful)
+2. The user is using anonymous memory and swap is turned off or too low
+
+A sync followed by echo 1 > /proc/sys/vm/drop_caches will help get rid of
+some of the pages cached in the cgroup (page cache pages).
+
+4.2 Task migration
+
+When a task migrates from one cgroup to another, it's charge is not
+carried forward. The pages allocated from the original cgroup still
+remain charged to it, the charge is dropped when the page is freed or
+reclaimed.
+
+4.3 Removing a cgroup
+
+A cgroup can be removed by rmdir, but as discussed in sections 4.1 and 4.2, a
+cgroup might have some charge associated with it, even though all
+tasks have migrated away from it.
+Such charges are freed(at default) or moved to its parent. When moved,
+both of RSS and CACHES are moved to parent.
+If both of them are busy, rmdir() returns -EBUSY. See 5.1 Also.
+
+Charges recorded in swap information is not updated at removal of cgroup.
+Recorded information is discarded and a cgroup which uses swap (swapcache)
+will be charged as a new owner of it.
+
+
+5. Misc. interfaces.
+
+5.1 force_empty
+  memory.force_empty interface is provided to make cgroup's memory usage empty.
+  You can use this interface only when the cgroup has no tasks.
+  When writing anything to this
+
+  # echo 0 > memory.force_empty
+
+  Almost all pages tracked by this memcg will be unmapped and freed. Some of
+  pages cannot be freed because it's locked or in-use. Such pages are moved
+  to parent and this cgroup will be empty. But this may return -EBUSY in
+  some too busy case.
+
+  Typical use case of this interface is that calling this before rmdir().
+  Because rmdir() moves all pages to parent, some out-of-use page caches can be
+  moved to the parent. If you want to avoid that, force_empty will be useful.
+
+5.2 stat file
+  memory.stat file includes following statistics (now)
+	cache			- # of pages from page-cache and shmem.
+	rss			- # of pages from anonymous memory.
+	pgpgin			- # of event of charging
+	pgpgout			- # of event of uncharging
+	active_anon		- # of pages on active lru of anon, shmem.
+	inactive_anon 		- # of pages on active lru of anon, shmem
+	active_file		- # of pages on active lru of file-cache
+	inactive_file		- # of pages on inactive lru of file cache
+	unevictable		- # of pages cannot be reclaimed.(mlocked etc)
+
+	Below is depend on CONFIG_DEBUG_VM.
+	inactive_ratio		- VM inernal parameter. (see mm/page_alloc.c)
+	recent_rotated_anon	- VM internal parameter. (see mm/vmscan.c)
+	recent_rotated_file	- VM internal parameter. (see mm/vmscan.c)
+	recent_scanned_anon 	- VM internal parameter. (see mm/vmscan.c)
+	recent_scanned_file 	- VM internal parameter. (see mm/vmscan.c)
+
+  Memo:
+	recent_rotated means recent frequency of lru rotation.
+	recent_scanned means recent # of scans to lru.
+	showing for better debug please see the code for meanings.
+
+
+5.3 swappiness
+  Similar to /proc/sys/vm/swappiness, but affecting a hierarchy of groups only.
+
+  Following cgroup's swapiness can't be changed.
+  - root cgroup (uses /proc/sys/vm/swappiness).
+  - a cgroup which uses hierarchy and it has child cgroup.
+  - a cgroup which uses hierarchy and not the root of hierarchy.
+
+
+6. Hierarchy support
+
+The memory controller supports a deep hierarchy and hierarchical accounting.
+The hierarchy is created by creating the appropriate cgroups in the
+cgroup filesystem. Consider for example, the following cgroup filesystem
+hierarchy
+
+		root
+	     /  |   \
+           /	|    \
+	  a	b	c
+			| \
+			|  \
+			d   e
+
+In the diagram above, with hierarchical accounting enabled, all memory
+usage of e, is accounted to its ancestors up until the root (i.e, c and root),
+that has memory.use_hierarchy enabled.  If one of the ancestors goes over its
+limit, the reclaim algorithm reclaims from the tasks in the ancestor and the
+children of the ancestor.
+
+6.1 Enabling hierarchical accounting and reclaim
+
+The memory controller by default disables the hierarchy feature. Support
+can be enabled by writing 1 to memory.use_hierarchy file of the root cgroup
+
+# echo 1 > memory.use_hierarchy
+
+The feature can be disabled by
+
+# echo 0 > memory.use_hierarchy
+
+NOTE1: Enabling/disabling will fail if the cgroup already has other
+cgroups created below it.
+
+NOTE2: This feature can be enabled/disabled per subtree.
+
+7. TODO
+
+1. Add support for accounting huge pages (as a separate controller)
+2. Make per-cgroup scanner reclaim not-shared pages first
+3. Teach controller to account for shared-pages
+4. Start reclamation in the background when the limit is
+   not yet hit but the usage is getting closer
+
+Summary
+
+Overall, the memory controller has been a stable controller and has been
+commented and discussed quite extensively in the community.
+
+References
+
+1. Singh, Balbir. RFC: Memory Controller, http://lwn.net/Articles/206697/
+2. Singh, Balbir. Memory Controller (RSS Control),
+   http://lwn.net/Articles/222762/
+3. Emelianov, Pavel. Resource controllers based on process cgroups
+   http://lkml.org/lkml/2007/3/6/198
+4. Emelianov, Pavel. RSS controller based on process cgroups (v2)
+   http://lkml.org/lkml/2007/4/9/78
+5. Emelianov, Pavel. RSS controller based on process cgroups (v3)
+   http://lkml.org/lkml/2007/5/30/244
+6. Menage, Paul. Control Groups v10, http://lwn.net/Articles/236032/
+7. Vaidyanathan, Srinivasan, Control Groups: Pagecache accounting and control
+   subsystem (v3), http://lwn.net/Articles/235534/
+8. Singh, Balbir. RSS controller v2 test results (lmbench),
+   http://lkml.org/lkml/2007/5/17/232
+9. Singh, Balbir. RSS controller v2 AIM9 results
+   http://lkml.org/lkml/2007/5/18/1
+10. Singh, Balbir. Memory controller v6 test results,
+    http://lkml.org/lkml/2007/8/19/36
+11. Singh, Balbir. Memory controller introduction (v6),
+    http://lkml.org/lkml/2007/8/17/69
+12. Corbet, Jonathan, Controlling memory use in cgroups,
+    http://lwn.net/Articles/243795/
diff --git a/Documentation/cgroups/resource_counter.txt b/Documentation/cgroups/resource_counter.txt
new file mode 100644
index 000000000000..f196ac1d7d25
--- /dev/null
+++ b/Documentation/cgroups/resource_counter.txt
@@ -0,0 +1,181 @@
+
+		The Resource Counter
+
+The resource counter, declared at include/linux/res_counter.h,
+is supposed to facilitate the resource management by controllers
+by providing common stuff for accounting.
+
+This "stuff" includes the res_counter structure and routines
+to work with it.
+
+
+
+1. Crucial parts of the res_counter structure
+
+ a. unsigned long long usage
+
+ 	The usage value shows the amount of a resource that is consumed
+	by a group at a given time. The units of measurement should be
+	determined by the controller that uses this counter. E.g. it can
+	be bytes, items or any other unit the controller operates on.
+
+ b. unsigned long long max_usage
+
+ 	The maximal value of the usage over time.
+
+ 	This value is useful when gathering statistical information about
+	the particular group, as it shows the actual resource requirements
+	for a particular group, not just some usage snapshot.
+
+ c. unsigned long long limit
+
+ 	The maximal allowed amount of resource to consume by the group. In
+	case the group requests for more resources, so that the usage value
+	would exceed the limit, the resource allocation is rejected (see
+	the next section).
+
+ d. unsigned long long failcnt
+
+ 	The failcnt stands for "failures counter". This is the number of
+	resource allocation attempts that failed.
+
+ c. spinlock_t lock
+
+ 	Protects changes of the above values.
+
+
+
+2. Basic accounting routines
+
+ a. void res_counter_init(struct res_counter *rc)
+
+ 	Initializes the resource counter. As usual, should be the first
+	routine called for a new counter.
+
+ b. int res_counter_charge[_locked]
+			(struct res_counter *rc, unsigned long val)
+
+	When a resource is about to be allocated it has to be accounted
+	with the appropriate resource counter (controller should determine
+	which one to use on its own). This operation is called "charging".
+
+	This is not very important which operation - resource allocation
+	or charging - is performed first, but
+	  * if the allocation is performed first, this may create a
+	    temporary resource over-usage by the time resource counter is
+	    charged;
+	  * if the charging is performed first, then it should be uncharged
+	    on error path (if the one is called).
+
+ c. void res_counter_uncharge[_locked]
+			(struct res_counter *rc, unsigned long val)
+
+	When a resource is released (freed) it should be de-accounted
+	from the resource counter it was accounted to.  This is called
+	"uncharging".
+
+    The _locked routines imply that the res_counter->lock is taken.
+
+
+ 2.1 Other accounting routines
+
+    There are more routines that may help you with common needs, like
+    checking whether the limit is reached or resetting the max_usage
+    value. They are all declared in include/linux/res_counter.h.
+
+
+
+3. Analyzing the resource counter registrations
+
+ a. If the failcnt value constantly grows, this means that the counter's
+    limit is too tight. Either the group is misbehaving and consumes too
+    many resources, or the configuration is not suitable for the group
+    and the limit should be increased.
+
+ b. The max_usage value can be used to quickly tune the group. One may
+    set the limits to maximal values and either load the container with
+    a common pattern or leave one for a while. After this the max_usage
+    value shows the amount of memory the container would require during
+    its common activity.
+
+    Setting the limit a bit above this value gives a pretty good
+    configuration that works in most of the cases.
+
+ c. If the max_usage is much less than the limit, but the failcnt value
+    is growing, then the group tries to allocate a big chunk of resource
+    at once.
+
+ d. If the max_usage is much less than the limit, but the failcnt value
+    is 0, then this group is given too high limit, that it does not
+    require. It is better to lower the limit a bit leaving more resource
+    for other groups.
+
+
+
+4. Communication with the control groups subsystem (cgroups)
+
+All the resource controllers that are using cgroups and resource counters
+should provide files (in the cgroup filesystem) to work with the resource
+counter fields. They are recommended to adhere to the following rules:
+
+ a. File names
+
+ 	Field name	File name
+	---------------------------------------------------
+	usage		usage_in_<unit_of_measurement>
+	max_usage	max_usage_in_<unit_of_measurement>
+	limit		limit_in_<unit_of_measurement>
+	failcnt		failcnt
+	lock		no file :)
+
+ b. Reading from file should show the corresponding field value in the
+    appropriate format.
+
+ c. Writing to file
+
+ 	Field		Expected behavior
+	----------------------------------
+	usage		prohibited
+	max_usage	reset to usage
+	limit		set the limit
+	failcnt		reset to zero
+
+
+
+5. Usage example
+
+ a. Declare a task group (take a look at cgroups subsystem for this) and
+    fold a res_counter into it
+
+	struct my_group {
+		struct res_counter res;
+
+		<other fields>
+	}
+
+ b. Put hooks in resource allocation/release paths
+
+ 	int alloc_something(...)
+	{
+		if (res_counter_charge(res_counter_ptr, amount) < 0)
+			return -ENOMEM;
+
+		<allocate the resource and return to the caller>
+	}
+
+	void release_something(...)
+	{
+		res_counter_uncharge(res_counter_ptr, amount);
+
+		<release the resource>
+	}
+
+    In order to keep the usage value self-consistent, both the
+    "res_counter_ptr" and the "amount" in release_something() should be
+    the same as they were in the alloc_something() when the releasing
+    resource was allocated.
+
+ c. Provide the way to read res_counter values and set them (the cgroups
+    still can help with it).
+
+ c. Compile and run :)
diff --git a/Documentation/controllers/cpuacct.txt b/Documentation/controllers/cpuacct.txt
deleted file mode 100644
index bb775fbe43d7..000000000000
--- a/Documentation/controllers/cpuacct.txt
+++ /dev/null
@@ -1,32 +0,0 @@
-CPU Accounting Controller
--------------------------
-
-The CPU accounting controller is used to group tasks using cgroups and
-account the CPU usage of these groups of tasks.
-
-The CPU accounting controller supports multi-hierarchy groups. An accounting
-group accumulates the CPU usage of all of its child groups and the tasks
-directly present in its group.
-
-Accounting groups can be created by first mounting the cgroup filesystem.
-
-# mkdir /cgroups
-# mount -t cgroup -ocpuacct none /cgroups
-
-With the above step, the initial or the parent accounting group
-becomes visible at /cgroups. At bootup, this group includes all the
-tasks in the system. /cgroups/tasks lists the tasks in this cgroup.
-/cgroups/cpuacct.usage gives the CPU time (in nanoseconds) obtained by
-this group which is essentially the CPU time obtained by all the tasks
-in the system.
-
-New accounting groups can be created under the parent group /cgroups.
-
-# cd /cgroups
-# mkdir g1
-# echo $$ > g1
-
-The above steps create a new group g1 and move the current shell
-process (bash) into it. CPU time consumed by this bash and its children
-can be obtained from g1/cpuacct.usage and the same is accumulated in
-/cgroups/cpuacct.usage also.
diff --git a/Documentation/controllers/devices.txt b/Documentation/controllers/devices.txt
deleted file mode 100644
index 7cc6e6a60672..000000000000
--- a/Documentation/controllers/devices.txt
+++ /dev/null
@@ -1,52 +0,0 @@
-Device Whitelist Controller
-
-1. Description:
-
-Implement a cgroup to track and enforce open and mknod restrictions
-on device files.  A device cgroup associates a device access
-whitelist with each cgroup.  A whitelist entry has 4 fields.
-'type' is a (all), c (char), or b (block).  'all' means it applies
-to all types and all major and minor numbers.  Major and minor are
-either an integer or * for all.  Access is a composition of r
-(read), w (write), and m (mknod).
-
-The root device cgroup starts with rwm to 'all'.  A child device
-cgroup gets a copy of the parent.  Administrators can then remove
-devices from the whitelist or add new entries.  A child cgroup can
-never receive a device access which is denied by its parent.  However
-when a device access is removed from a parent it will not also be
-removed from the child(ren).
-
-2. User Interface
-
-An entry is added using devices.allow, and removed using
-devices.deny.  For instance
-
-	echo 'c 1:3 mr' > /cgroups/1/devices.allow
-
-allows cgroup 1 to read and mknod the device usually known as
-/dev/null.  Doing
-
-	echo a > /cgroups/1/devices.deny
-
-will remove the default 'a *:* rwm' entry. Doing
-
-	echo a > /cgroups/1/devices.allow
-
-will add the 'a *:* rwm' entry to the whitelist.
-
-3. Security
-
-Any task can move itself between cgroups.  This clearly won't
-suffice, but we can decide the best way to adequately restrict
-movement as people get some experience with this.  We may just want
-to require CAP_SYS_ADMIN, which at least is a separate bit from
-CAP_MKNOD.  We may want to just refuse moving to a cgroup which
-isn't a descendent of the current one.  Or we may want to use
-CAP_MAC_ADMIN, since we really are trying to lock down root.
-
-CAP_SYS_ADMIN is needed to modify the whitelist or move another
-task to a new cgroup.  (Again we'll probably want to change that).
-
-A cgroup may not be granted more permissions than the cgroup's
-parent has.
diff --git a/Documentation/controllers/memcg_test.txt b/Documentation/controllers/memcg_test.txt
deleted file mode 100644
index 08d4d3ea0d79..000000000000
--- a/Documentation/controllers/memcg_test.txt
+++ /dev/null
@@ -1,342 +0,0 @@
-Memory Resource Controller(Memcg)  Implementation Memo.
-Last Updated: 2008/12/15
-Base Kernel Version: based on 2.6.28-rc8-mm.
-
-Because VM is getting complex (one of reasons is memcg...), memcg's behavior
-is complex. This is a document for memcg's internal behavior.
-Please note that implementation details can be changed.
-
-(*) Topics on API should be in Documentation/controllers/memory.txt)
-
-0. How to record usage ?
-   2 objects are used.
-
-   page_cgroup ....an object per page.
-	Allocated at boot or memory hotplug. Freed at memory hot removal.
-
-   swap_cgroup ... an entry per swp_entry.
-	Allocated at swapon(). Freed at swapoff().
-
-   The page_cgroup has USED bit and double count against a page_cgroup never
-   occurs. swap_cgroup is used only when a charged page is swapped-out.
-
-1. Charge
-
-   a page/swp_entry may be charged (usage += PAGE_SIZE) at
-
-	mem_cgroup_newpage_charge()
-	  Called at new page fault and Copy-On-Write.
-
-	mem_cgroup_try_charge_swapin()
-	  Called at do_swap_page() (page fault on swap entry) and swapoff.
-	  Followed by charge-commit-cancel protocol. (With swap accounting)
-	  At commit, a charge recorded in swap_cgroup is removed.
-
-	mem_cgroup_cache_charge()
-	  Called at add_to_page_cache()
-
-	mem_cgroup_cache_charge_swapin()
-	  Called at shmem's swapin.
-
-	mem_cgroup_prepare_migration()
-	  Called before migration. "extra" charge is done and followed by
-	  charge-commit-cancel protocol.
-	  At commit, charge against oldpage or newpage will be committed.
-
-2. Uncharge
-  a page/swp_entry may be uncharged (usage -= PAGE_SIZE) by
-
-	mem_cgroup_uncharge_page()
-	  Called when an anonymous page is fully unmapped. I.e., mapcount goes
-	  to 0. If the page is SwapCache, uncharge is delayed until
-	  mem_cgroup_uncharge_swapcache().
-
-	mem_cgroup_uncharge_cache_page()
-	  Called when a page-cache is deleted from radix-tree. If the page is
-	  SwapCache, uncharge is delayed until mem_cgroup_uncharge_swapcache().
-
-	mem_cgroup_uncharge_swapcache()
-	  Called when SwapCache is removed from radix-tree. The charge itself
-	  is moved to swap_cgroup. (If mem+swap controller is disabled, no
-	  charge to swap occurs.)
-
-	mem_cgroup_uncharge_swap()
-	  Called when swp_entry's refcnt goes down to 0. A charge against swap
-	  disappears.
-
-	mem_cgroup_end_migration(old, new)
-	At success of migration old is uncharged (if necessary), a charge
-	to new page is committed. At failure, charge to old page is committed.
-
-3. charge-commit-cancel
-	In some case, we can't know this "charge" is valid or not at charging
-	(because of races).
-	To handle such case, there are charge-commit-cancel functions.
-		mem_cgroup_try_charge_XXX
-		mem_cgroup_commit_charge_XXX
-		mem_cgroup_cancel_charge_XXX
-	these are used in swap-in and migration.
-
-	At try_charge(), there are no flags to say "this page is charged".
-	at this point, usage += PAGE_SIZE.
-
-	At commit(), the function checks the page should be charged or not
-	and set flags or avoid charging.(usage -= PAGE_SIZE)
-
-	At cancel(), simply usage -= PAGE_SIZE.
-
-Under below explanation, we assume CONFIG_MEM_RES_CTRL_SWAP=y.
-
-4. Anonymous
-	Anonymous page is newly allocated at
-		  - page fault into MAP_ANONYMOUS mapping.
-		  - Copy-On-Write.
- 	It is charged right after it's allocated before doing any page table
-	related operations. Of course, it's uncharged when another page is used
-	for the fault address.
-
-	At freeing anonymous page (by exit() or munmap()), zap_pte() is called
-	and pages for ptes are freed one by one.(see mm/memory.c). Uncharges
-	are done at page_remove_rmap() when page_mapcount() goes down to 0.
-
-	Another page freeing is by page-reclaim (vmscan.c) and anonymous
-	pages are swapped out. In this case, the page is marked as
-	PageSwapCache(). uncharge() routine doesn't uncharge the page marked
-	as SwapCache(). It's delayed until __delete_from_swap_cache().
-
-	4.1 Swap-in.
-	At swap-in, the page is taken from swap-cache. There are 2 cases.
-
-	(a) If the SwapCache is newly allocated and read, it has no charges.
-	(b) If the SwapCache has been mapped by processes, it has been
-	    charged already.
-
-	This swap-in is one of the most complicated work. In do_swap_page(),
-	following events occur when pte is unchanged.
-
-	(1) the page (SwapCache) is looked up.
-	(2) lock_page()
-	(3) try_charge_swapin()
-	(4) reuse_swap_page() (may call delete_swap_cache())
-	(5) commit_charge_swapin()
-	(6) swap_free().
-
-	Considering following situation for example.
-
-	(A) The page has not been charged before (2) and reuse_swap_page()
-	    doesn't call delete_from_swap_cache().
-	(B) The page has not been charged before (2) and reuse_swap_page()
-	    calls delete_from_swap_cache().
-	(C) The page has been charged before (2) and reuse_swap_page() doesn't
-	    call delete_from_swap_cache().
-	(D) The page has been charged before (2) and reuse_swap_page() calls
-	    delete_from_swap_cache().
-
-	    memory.usage/memsw.usage changes to this page/swp_entry will be
-	 Case          (A)      (B)       (C)     (D)
-         Event
-       Before (2)     0/ 1     0/ 1      1/ 1    1/ 1
-          ===========================================
-          (3)        +1/+1    +1/+1     +1/+1   +1/+1
-          (4)          -       0/ 0       -     -1/ 0
-          (5)         0/-1     0/ 0     -1/-1    0/ 0
-          (6)          -       0/-1       -      0/-1
-          ===========================================
-       Result         1/ 1     1/ 1      1/ 1    1/ 1
-
-       In any cases, charges to this page should be 1/ 1.
-
-	4.2 Swap-out.
-	At swap-out, typical state transition is below.
-
-	(a) add to swap cache. (marked as SwapCache)
-	    swp_entry's refcnt += 1.
-	(b) fully unmapped.
-	    swp_entry's refcnt += # of ptes.
-	(c) write back to swap.
-	(d) delete from swap cache. (remove from SwapCache)
-	    swp_entry's refcnt -= 1.
-
-
-	At (b), the page is marked as SwapCache and not uncharged.
-	At (d), the page is removed from SwapCache and a charge in page_cgroup
-	is moved to swap_cgroup.
-
-	Finally, at task exit,
-	(e) zap_pte() is called and swp_entry's refcnt -=1 -> 0.
-	Here, a charge in swap_cgroup disappears.
-
-5. Page Cache
-   	Page Cache is charged at
-	- add_to_page_cache_locked().
-
-	uncharged at
-	- __remove_from_page_cache().
-
-	The logic is very clear. (About migration, see below)
-	Note: __remove_from_page_cache() is called by remove_from_page_cache()
-	and __remove_mapping().
-
-6. Shmem(tmpfs) Page Cache
-	Memcg's charge/uncharge have special handlers of shmem. The best way
-	to understand shmem's page state transition is to read mm/shmem.c.
-	But brief explanation of the behavior of memcg around shmem will be
-	helpful to understand the logic.
-
-	Shmem's page (just leaf page, not direct/indirect block) can be on
-		- radix-tree of shmem's inode.
-		- SwapCache.
-		- Both on radix-tree and SwapCache. This happens at swap-in
-		  and swap-out,
-
-	It's charged when...
-	- A new page is added to shmem's radix-tree.
-	- A swp page is read. (move a charge from swap_cgroup to page_cgroup)
-	It's uncharged when
-	- A page is removed from radix-tree and not SwapCache.
-	- When SwapCache is removed, a charge is moved to swap_cgroup.
-	- When swp_entry's refcnt goes down to 0, a charge in swap_cgroup
-	  disappears.
-
-7. Page Migration
-   	One of the most complicated functions is page-migration-handler.
-	Memcg has 2 routines. Assume that we are migrating a page's contents
-	from OLDPAGE to NEWPAGE.
-
-	Usual migration logic is..
-	(a) remove the page from LRU.
-	(b) allocate NEWPAGE (migration target)
-	(c) lock by lock_page().
-	(d) unmap all mappings.
-	(e-1) If necessary, replace entry in radix-tree.
-	(e-2) move contents of a page.
-	(f) map all mappings again.
-	(g) pushback the page to LRU.
-	(-) OLDPAGE will be freed.
-
-	Before (g), memcg should complete all necessary charge/uncharge to
-	NEWPAGE/OLDPAGE.
-
-	The point is....
-	- If OLDPAGE is anonymous, all charges will be dropped at (d) because
-          try_to_unmap() drops all mapcount and the page will not be
-	  SwapCache.
-
-	- If OLDPAGE is SwapCache, charges will be kept at (g) because
-	  __delete_from_swap_cache() isn't called at (e-1)
-
-	- If OLDPAGE is page-cache, charges will be kept at (g) because
-	  remove_from_swap_cache() isn't called at (e-1)
-
-	memcg provides following hooks.
-
-	- mem_cgroup_prepare_migration(OLDPAGE)
-	  Called after (b) to account a charge (usage += PAGE_SIZE) against
-	  memcg which OLDPAGE belongs to.
-
-        - mem_cgroup_end_migration(OLDPAGE, NEWPAGE)
-	  Called after (f) before (g).
-	  If OLDPAGE is used, commit OLDPAGE again. If OLDPAGE is already
-	  charged, a charge by prepare_migration() is automatically canceled.
-	  If NEWPAGE is used, commit NEWPAGE and uncharge OLDPAGE.
-
-	  But zap_pte() (by exit or munmap) can be called while migration,
-	  we have to check if OLDPAGE/NEWPAGE is a valid page after commit().
-
-8. LRU
-        Each memcg has its own private LRU. Now, it's handling is under global
-	VM's control (means that it's handled under global zone->lru_lock).
-	Almost all routines around memcg's LRU is called by global LRU's
-	list management functions under zone->lru_lock().
-
-	A special function is mem_cgroup_isolate_pages(). This scans
-	memcg's private LRU and call __isolate_lru_page() to extract a page
-	from LRU.
-	(By __isolate_lru_page(), the page is removed from both of global and
-	 private LRU.)
-
-
-9. Typical Tests.
-
- Tests for racy cases.
-
- 9.1 Small limit to memcg.
-	When you do test to do racy case, it's good test to set memcg's limit
-	to be very small rather than GB. Many races found in the test under
-	xKB or xxMB limits.
-	(Memory behavior under GB and Memory behavior under MB shows very
-	 different situation.)
-
- 9.2 Shmem
-	Historically, memcg's shmem handling was poor and we saw some amount
-	of troubles here. This is because shmem is page-cache but can be
-	SwapCache. Test with shmem/tmpfs is always good test.
-
- 9.3 Migration
-	For NUMA, migration is an another special case. To do easy test, cpuset
-	is useful. Following is a sample script to do migration.
-
-	mount -t cgroup -o cpuset none /opt/cpuset
-
-	mkdir /opt/cpuset/01
-	echo 1 > /opt/cpuset/01/cpuset.cpus
-	echo 0 > /opt/cpuset/01/cpuset.mems
-	echo 1 > /opt/cpuset/01/cpuset.memory_migrate
-	mkdir /opt/cpuset/02
-	echo 1 > /opt/cpuset/02/cpuset.cpus
-	echo 1 > /opt/cpuset/02/cpuset.mems
-	echo 1 > /opt/cpuset/02/cpuset.memory_migrate
-
-	In above set, when you moves a task from 01 to 02, page migration to
-	node 0 to node 1 will occur. Following is a script to migrate all
-	under cpuset.
-	--
-	move_task()
-	{
-	for pid in $1
-        do
-                /bin/echo $pid >$2/tasks 2>/dev/null
-		echo -n $pid
-		echo -n " "
-        done
-	echo END
-	}
-
-	G1_TASK=`cat ${G1}/tasks`
-	G2_TASK=`cat ${G2}/tasks`
-	move_task "${G1_TASK}" ${G2} &
-	--
- 9.4 Memory hotplug.
-	memory hotplug test is one of good test.
-	to offline memory, do following.
-	# echo offline > /sys/devices/system/memory/memoryXXX/state
-	(XXX is the place of memory)
-	This is an easy way to test page migration, too.
-
- 9.5 mkdir/rmdir
-	When using hierarchy, mkdir/rmdir test should be done.
-	Use tests like the following.
-
-	echo 1 >/opt/cgroup/01/memory/use_hierarchy
-	mkdir /opt/cgroup/01/child_a
-	mkdir /opt/cgroup/01/child_b
-
-	set limit to 01.
-	add limit to 01/child_b
-	run jobs under child_a and child_b
-
-	create/delete following groups at random while jobs are running.
-	/opt/cgroup/01/child_a/child_aa
-	/opt/cgroup/01/child_b/child_bb
-	/opt/cgroup/01/child_c
-
-	running new jobs in new group is also good.
-
- 9.6 Mount with other subsystems.
-	Mounting with other subsystems is a good test because there is a
-	race and lock dependency with other cgroup subsystems.
-
-	example)
-	# mount -t cgroup none /cgroup -t cpuset,memory,cpu,devices
-
-	and do task move, mkdir, rmdir etc...under this.
diff --git a/Documentation/controllers/memory.txt b/Documentation/controllers/memory.txt
deleted file mode 100644
index e1501964df1e..000000000000
--- a/Documentation/controllers/memory.txt
+++ /dev/null
@@ -1,399 +0,0 @@
-Memory Resource Controller
-
-NOTE: The Memory Resource Controller has been generically been referred
-to as the memory controller in this document. Do not confuse memory controller
-used here with the memory controller that is used in hardware.
-
-Salient features
-
-a. Enable control of both RSS (mapped) and Page Cache (unmapped) pages
-b. The infrastructure allows easy addition of other types of memory to control
-c. Provides *zero overhead* for non memory controller users
-d. Provides a double LRU: global memory pressure causes reclaim from the
-   global LRU; a cgroup on hitting a limit, reclaims from the per
-   cgroup LRU
-
-NOTE: Swap Cache (unmapped) is not accounted now.
-
-Benefits and Purpose of the memory controller
-
-The memory controller isolates the memory behaviour of a group of tasks
-from the rest of the system. The article on LWN [12] mentions some probable
-uses of the memory controller. The memory controller can be used to
-
-a. Isolate an application or a group of applications
-   Memory hungry applications can be isolated and limited to a smaller
-   amount of memory.
-b. Create a cgroup with limited amount of memory, this can be used
-   as a good alternative to booting with mem=XXXX.
-c. Virtualization solutions can control the amount of memory they want
-   to assign to a virtual machine instance.
-d. A CD/DVD burner could control the amount of memory used by the
-   rest of the system to ensure that burning does not fail due to lack
-   of available memory.
-e. There are several other use cases, find one or use the controller just
-   for fun (to learn and hack on the VM subsystem).
-
-1. History
-
-The memory controller has a long history. A request for comments for the memory
-controller was posted by Balbir Singh [1]. At the time the RFC was posted
-there were several implementations for memory control. The goal of the
-RFC was to build consensus and agreement for the minimal features required
-for memory control. The first RSS controller was posted by Balbir Singh[2]
-in Feb 2007. Pavel Emelianov [3][4][5] has since posted three versions of the
-RSS controller. At OLS, at the resource management BoF, everyone suggested
-that we handle both page cache and RSS together. Another request was raised
-to allow user space handling of OOM. The current memory controller is
-at version 6; it combines both mapped (RSS) and unmapped Page
-Cache Control [11].
-
-2. Memory Control
-
-Memory is a unique resource in the sense that it is present in a limited
-amount. If a task requires a lot of CPU processing, the task can spread
-its processing over a period of hours, days, months or years, but with
-memory, the same physical memory needs to be reused to accomplish the task.
-
-The memory controller implementation has been divided into phases. These
-are:
-
-1. Memory controller
-2. mlock(2) controller
-3. Kernel user memory accounting and slab control
-4. user mappings length controller
-
-The memory controller is the first controller developed.
-
-2.1. Design
-
-The core of the design is a counter called the res_counter. The res_counter
-tracks the current memory usage and limit of the group of processes associated
-with the controller. Each cgroup has a memory controller specific data
-structure (mem_cgroup) associated with it.
-
-2.2. Accounting
-
-		+--------------------+
-		|  mem_cgroup     |
-		|  (res_counter)     |
-		+--------------------+
-		 /            ^      \
-		/             |       \
-           +---------------+  |        +---------------+
-           | mm_struct     |  |....    | mm_struct     |
-           |               |  |        |               |
-           +---------------+  |        +---------------+
-                              |
-                              + --------------+
-                                              |
-           +---------------+           +------+--------+
-           | page          +---------->  page_cgroup|
-           |               |           |               |
-           +---------------+           +---------------+
-
-             (Figure 1: Hierarchy of Accounting)
-
-
-Figure 1 shows the important aspects of the controller
-
-1. Accounting happens per cgroup
-2. Each mm_struct knows about which cgroup it belongs to
-3. Each page has a pointer to the page_cgroup, which in turn knows the
-   cgroup it belongs to
-
-The accounting is done as follows: mem_cgroup_charge() is invoked to setup
-the necessary data structures and check if the cgroup that is being charged
-is over its limit. If it is then reclaim is invoked on the cgroup.
-More details can be found in the reclaim section of this document.
-If everything goes well, a page meta-data-structure called page_cgroup is
-allocated and associated with the page.  This routine also adds the page to
-the per cgroup LRU.
-
-2.2.1 Accounting details
-
-All mapped anon pages (RSS) and cache pages (Page Cache) are accounted.
-(some pages which never be reclaimable and will not be on global LRU
- are not accounted. we just accounts pages under usual vm management.)
-
-RSS pages are accounted at page_fault unless they've already been accounted
-for earlier. A file page will be accounted for as Page Cache when it's
-inserted into inode (radix-tree). While it's mapped into the page tables of
-processes, duplicate accounting is carefully avoided.
-
-A RSS page is unaccounted when it's fully unmapped. A PageCache page is
-unaccounted when it's removed from radix-tree.
-
-At page migration, accounting information is kept.
-
-Note: we just account pages-on-lru because our purpose is to control amount
-of used pages. not-on-lru pages are tend to be out-of-control from vm view.
-
-2.3 Shared Page Accounting
-
-Shared pages are accounted on the basis of the first touch approach. The
-cgroup that first touches a page is accounted for the page. The principle
-behind this approach is that a cgroup that aggressively uses a shared
-page will eventually get charged for it (once it is uncharged from
-the cgroup that brought it in -- this will happen on memory pressure).
-
-Exception: If CONFIG_CGROUP_CGROUP_MEM_RES_CTLR_SWAP is not used..
-When you do swapoff and make swapped-out pages of shmem(tmpfs) to
-be backed into memory in force, charges for pages are accounted against the
-caller of swapoff rather than the users of shmem.
-
-
-2.4 Swap Extension (CONFIG_CGROUP_MEM_RES_CTLR_SWAP)
-Swap Extension allows you to record charge for swap. A swapped-in page is
-charged back to original page allocator if possible.
-
-When swap is accounted, following files are added.
- - memory.memsw.usage_in_bytes.
- - memory.memsw.limit_in_bytes.
-
-usage of mem+swap is limited by memsw.limit_in_bytes.
-
-Note: why 'mem+swap' rather than swap.
-The global LRU(kswapd) can swap out arbitrary pages. Swap-out means
-to move account from memory to swap...there is no change in usage of
-mem+swap.
-
-In other words, when we want to limit the usage of swap without affecting
-global LRU, mem+swap limit is better than just limiting swap from OS point
-of view.
-
-2.5 Reclaim
-
-Each cgroup maintains a per cgroup LRU that consists of an active
-and inactive list. When a cgroup goes over its limit, we first try
-to reclaim memory from the cgroup so as to make space for the new
-pages that the cgroup has touched. If the reclaim is unsuccessful,
-an OOM routine is invoked to select and kill the bulkiest task in the
-cgroup.
-
-The reclaim algorithm has not been modified for cgroups, except that
-pages that are selected for reclaiming come from the per cgroup LRU
-list.
-
-2. Locking
-
-The memory controller uses the following hierarchy
-
-1. zone->lru_lock is used for selecting pages to be isolated
-2. mem->per_zone->lru_lock protects the per cgroup LRU (per zone)
-3. lock_page_cgroup() is used to protect page->page_cgroup
-
-3. User Interface
-
-0. Configuration
-
-a. Enable CONFIG_CGROUPS
-b. Enable CONFIG_RESOURCE_COUNTERS
-c. Enable CONFIG_CGROUP_MEM_RES_CTLR
-
-1. Prepare the cgroups
-# mkdir -p /cgroups
-# mount -t cgroup none /cgroups -o memory
-
-2. Make the new group and move bash into it
-# mkdir /cgroups/0
-# echo $$ >  /cgroups/0/tasks
-
-Since now we're in the 0 cgroup,
-We can alter the memory limit:
-# echo 4M > /cgroups/0/memory.limit_in_bytes
-
-NOTE: We can use a suffix (k, K, m, M, g or G) to indicate values in kilo,
-mega or gigabytes.
-
-# cat /cgroups/0/memory.limit_in_bytes
-4194304
-
-NOTE: The interface has now changed to display the usage in bytes
-instead of pages
-
-We can check the usage:
-# cat /cgroups/0/memory.usage_in_bytes
-1216512
-
-A successful write to this file does not guarantee a successful set of
-this limit to the value written into the file.  This can be due to a
-number of factors, such as rounding up to page boundaries or the total
-availability of memory on the system.  The user is required to re-read
-this file after a write to guarantee the value committed by the kernel.
-
-# echo 1 > memory.limit_in_bytes
-# cat memory.limit_in_bytes
-4096
-
-The memory.failcnt field gives the number of times that the cgroup limit was
-exceeded.
-
-The memory.stat file gives accounting information. Now, the number of
-caches, RSS and Active pages/Inactive pages are shown.
-
-4. Testing
-
-Balbir posted lmbench, AIM9, LTP and vmmstress results [10] and [11].
-Apart from that v6 has been tested with several applications and regular
-daily use. The controller has also been tested on the PPC64, x86_64 and
-UML platforms.
-
-4.1 Troubleshooting
-
-Sometimes a user might find that the application under a cgroup is
-terminated. There are several causes for this:
-
-1. The cgroup limit is too low (just too low to do anything useful)
-2. The user is using anonymous memory and swap is turned off or too low
-
-A sync followed by echo 1 > /proc/sys/vm/drop_caches will help get rid of
-some of the pages cached in the cgroup (page cache pages).
-
-4.2 Task migration
-
-When a task migrates from one cgroup to another, it's charge is not
-carried forward. The pages allocated from the original cgroup still
-remain charged to it, the charge is dropped when the page is freed or
-reclaimed.
-
-4.3 Removing a cgroup
-
-A cgroup can be removed by rmdir, but as discussed in sections 4.1 and 4.2, a
-cgroup might have some charge associated with it, even though all
-tasks have migrated away from it.
-Such charges are freed(at default) or moved to its parent. When moved,
-both of RSS and CACHES are moved to parent.
-If both of them are busy, rmdir() returns -EBUSY. See 5.1 Also.
-
-Charges recorded in swap information is not updated at removal of cgroup.
-Recorded information is discarded and a cgroup which uses swap (swapcache)
-will be charged as a new owner of it.
-
-
-5. Misc. interfaces.
-
-5.1 force_empty
-  memory.force_empty interface is provided to make cgroup's memory usage empty.
-  You can use this interface only when the cgroup has no tasks.
-  When writing anything to this
-
-  # echo 0 > memory.force_empty
-
-  Almost all pages tracked by this memcg will be unmapped and freed. Some of
-  pages cannot be freed because it's locked or in-use. Such pages are moved
-  to parent and this cgroup will be empty. But this may return -EBUSY in
-  some too busy case.
-
-  Typical use case of this interface is that calling this before rmdir().
-  Because rmdir() moves all pages to parent, some out-of-use page caches can be
-  moved to the parent. If you want to avoid that, force_empty will be useful.
-
-5.2 stat file
-  memory.stat file includes following statistics (now)
-	cache			- # of pages from page-cache and shmem.
-	rss			- # of pages from anonymous memory.
-	pgpgin			- # of event of charging
-	pgpgout			- # of event of uncharging
-	active_anon		- # of pages on active lru of anon, shmem.
-	inactive_anon 		- # of pages on active lru of anon, shmem
-	active_file		- # of pages on active lru of file-cache
-	inactive_file		- # of pages on inactive lru of file cache
-	unevictable		- # of pages cannot be reclaimed.(mlocked etc)
-
-	Below is depend on CONFIG_DEBUG_VM.
-	inactive_ratio		- VM inernal parameter. (see mm/page_alloc.c)
-	recent_rotated_anon	- VM internal parameter. (see mm/vmscan.c)
-	recent_rotated_file	- VM internal parameter. (see mm/vmscan.c)
-	recent_scanned_anon 	- VM internal parameter. (see mm/vmscan.c)
-	recent_scanned_file 	- VM internal parameter. (see mm/vmscan.c)
-
-  Memo:
-	recent_rotated means recent frequency of lru rotation.
-	recent_scanned means recent # of scans to lru.
-	showing for better debug please see the code for meanings.
-
-
-5.3 swappiness
-  Similar to /proc/sys/vm/swappiness, but affecting a hierarchy of groups only.
-
-  Following cgroup's swapiness can't be changed.
-  - root cgroup (uses /proc/sys/vm/swappiness).
-  - a cgroup which uses hierarchy and it has child cgroup.
-  - a cgroup which uses hierarchy and not the root of hierarchy.
-
-
-6. Hierarchy support
-
-The memory controller supports a deep hierarchy and hierarchical accounting.
-The hierarchy is created by creating the appropriate cgroups in the
-cgroup filesystem. Consider for example, the following cgroup filesystem
-hierarchy
-
-		root
-	     /  |   \
-           /	|    \
-	  a	b	c
-			| \
-			|  \
-			d   e
-
-In the diagram above, with hierarchical accounting enabled, all memory
-usage of e, is accounted to its ancestors up until the root (i.e, c and root),
-that has memory.use_hierarchy enabled.  If one of the ancestors goes over its
-limit, the reclaim algorithm reclaims from the tasks in the ancestor and the
-children of the ancestor.
-
-6.1 Enabling hierarchical accounting and reclaim
-
-The memory controller by default disables the hierarchy feature. Support
-can be enabled by writing 1 to memory.use_hierarchy file of the root cgroup
-
-# echo 1 > memory.use_hierarchy
-
-The feature can be disabled by
-
-# echo 0 > memory.use_hierarchy
-
-NOTE1: Enabling/disabling will fail if the cgroup already has other
-cgroups created below it.
-
-NOTE2: This feature can be enabled/disabled per subtree.
-
-7. TODO
-
-1. Add support for accounting huge pages (as a separate controller)
-2. Make per-cgroup scanner reclaim not-shared pages first
-3. Teach controller to account for shared-pages
-4. Start reclamation in the background when the limit is
-   not yet hit but the usage is getting closer
-
-Summary
-
-Overall, the memory controller has been a stable controller and has been
-commented and discussed quite extensively in the community.
-
-References
-
-1. Singh, Balbir. RFC: Memory Controller, http://lwn.net/Articles/206697/
-2. Singh, Balbir. Memory Controller (RSS Control),
-   http://lwn.net/Articles/222762/
-3. Emelianov, Pavel. Resource controllers based on process cgroups
-   http://lkml.org/lkml/2007/3/6/198
-4. Emelianov, Pavel. RSS controller based on process cgroups (v2)
-   http://lkml.org/lkml/2007/4/9/78
-5. Emelianov, Pavel. RSS controller based on process cgroups (v3)
-   http://lkml.org/lkml/2007/5/30/244
-6. Menage, Paul. Control Groups v10, http://lwn.net/Articles/236032/
-7. Vaidyanathan, Srinivasan, Control Groups: Pagecache accounting and control
-   subsystem (v3), http://lwn.net/Articles/235534/
-8. Singh, Balbir. RSS controller v2 test results (lmbench),
-   http://lkml.org/lkml/2007/5/17/232
-9. Singh, Balbir. RSS controller v2 AIM9 results
-   http://lkml.org/lkml/2007/5/18/1
-10. Singh, Balbir. Memory controller v6 test results,
-    http://lkml.org/lkml/2007/8/19/36
-11. Singh, Balbir. Memory controller introduction (v6),
-    http://lkml.org/lkml/2007/8/17/69
-12. Corbet, Jonathan, Controlling memory use in cgroups,
-    http://lwn.net/Articles/243795/
diff --git a/Documentation/controllers/resource_counter.txt b/Documentation/controllers/resource_counter.txt
deleted file mode 100644
index f196ac1d7d25..000000000000
--- a/Documentation/controllers/resource_counter.txt
+++ /dev/null
@@ -1,181 +0,0 @@
-
-		The Resource Counter
-
-The resource counter, declared at include/linux/res_counter.h,
-is supposed to facilitate the resource management by controllers
-by providing common stuff for accounting.
-
-This "stuff" includes the res_counter structure and routines
-to work with it.
-
-
-
-1. Crucial parts of the res_counter structure
-
- a. unsigned long long usage
-
- 	The usage value shows the amount of a resource that is consumed
-	by a group at a given time. The units of measurement should be
-	determined by the controller that uses this counter. E.g. it can
-	be bytes, items or any other unit the controller operates on.
-
- b. unsigned long long max_usage
-
- 	The maximal value of the usage over time.
-
- 	This value is useful when gathering statistical information about
-	the particular group, as it shows the actual resource requirements
-	for a particular group, not just some usage snapshot.
-
- c. unsigned long long limit
-
- 	The maximal allowed amount of resource to consume by the group. In
-	case the group requests for more resources, so that the usage value
-	would exceed the limit, the resource allocation is rejected (see
-	the next section).
-
- d. unsigned long long failcnt
-
- 	The failcnt stands for "failures counter". This is the number of
-	resource allocation attempts that failed.
-
- c. spinlock_t lock
-
- 	Protects changes of the above values.
-
-
-
-2. Basic accounting routines
-
- a. void res_counter_init(struct res_counter *rc)
-
- 	Initializes the resource counter. As usual, should be the first
-	routine called for a new counter.
-
- b. int res_counter_charge[_locked]
-			(struct res_counter *rc, unsigned long val)
-
-	When a resource is about to be allocated it has to be accounted
-	with the appropriate resource counter (controller should determine
-	which one to use on its own). This operation is called "charging".
-
-	This is not very important which operation - resource allocation
-	or charging - is performed first, but
-	  * if the allocation is performed first, this may create a
-	    temporary resource over-usage by the time resource counter is
-	    charged;
-	  * if the charging is performed first, then it should be uncharged
-	    on error path (if the one is called).
-
- c. void res_counter_uncharge[_locked]
-			(struct res_counter *rc, unsigned long val)
-
-	When a resource is released (freed) it should be de-accounted
-	from the resource counter it was accounted to.  This is called
-	"uncharging".
-
-    The _locked routines imply that the res_counter->lock is taken.
-
-
- 2.1 Other accounting routines
-
-    There are more routines that may help you with common needs, like
-    checking whether the limit is reached or resetting the max_usage
-    value. They are all declared in include/linux/res_counter.h.
-
-
-
-3. Analyzing the resource counter registrations
-
- a. If the failcnt value constantly grows, this means that the counter's
-    limit is too tight. Either the group is misbehaving and consumes too
-    many resources, or the configuration is not suitable for the group
-    and the limit should be increased.
-
- b. The max_usage value can be used to quickly tune the group. One may
-    set the limits to maximal values and either load the container with
-    a common pattern or leave one for a while. After this the max_usage
-    value shows the amount of memory the container would require during
-    its common activity.
-
-    Setting the limit a bit above this value gives a pretty good
-    configuration that works in most of the cases.
-
- c. If the max_usage is much less than the limit, but the failcnt value
-    is growing, then the group tries to allocate a big chunk of resource
-    at once.
-
- d. If the max_usage is much less than the limit, but the failcnt value
-    is 0, then this group is given too high limit, that it does not
-    require. It is better to lower the limit a bit leaving more resource
-    for other groups.
-
-
-
-4. Communication with the control groups subsystem (cgroups)
-
-All the resource controllers that are using cgroups and resource counters
-should provide files (in the cgroup filesystem) to work with the resource
-counter fields. They are recommended to adhere to the following rules:
-
- a. File names
-
- 	Field name	File name
-	---------------------------------------------------
-	usage		usage_in_<unit_of_measurement>
-	max_usage	max_usage_in_<unit_of_measurement>
-	limit		limit_in_<unit_of_measurement>
-	failcnt		failcnt
-	lock		no file :)
-
- b. Reading from file should show the corresponding field value in the
-    appropriate format.
-
- c. Writing to file
-
- 	Field		Expected behavior
-	----------------------------------
-	usage		prohibited
-	max_usage	reset to usage
-	limit		set the limit
-	failcnt		reset to zero
-
-
-
-5. Usage example
-
- a. Declare a task group (take a look at cgroups subsystem for this) and
-    fold a res_counter into it
-
-	struct my_group {
-		struct res_counter res;
-
-		<other fields>
-	}
-
- b. Put hooks in resource allocation/release paths
-
- 	int alloc_something(...)
-	{
-		if (res_counter_charge(res_counter_ptr, amount) < 0)
-			return -ENOMEM;
-
-		<allocate the resource and return to the caller>
-	}
-
-	void release_something(...)
-	{
-		res_counter_uncharge(res_counter_ptr, amount);
-
-		<release the resource>
-	}
-
-    In order to keep the usage value self-consistent, both the
-    "res_counter_ptr" and the "amount" in release_something() should be
-    the same as they were in the alloc_something() when the releasing
-    resource was allocated.
-
- c. Provide the way to read res_counter values and set them (the cgroups
-    still can help with it).
-
- c. Compile and run :)
diff --git a/Documentation/cpusets.txt b/Documentation/cpusets.txt
deleted file mode 100644
index 5c86c258c791..000000000000
--- a/Documentation/cpusets.txt
+++ /dev/null
@@ -1,808 +0,0 @@
-				CPUSETS
-				-------
-
-Copyright (C) 2004 BULL SA.
-Written by Simon.Derr@bull.net
-
-Portions Copyright (c) 2004-2006 Silicon Graphics, Inc.
-Modified by Paul Jackson <pj@sgi.com>
-Modified by Christoph Lameter <clameter@sgi.com>
-Modified by Paul Menage <menage@google.com>
-Modified by Hidetoshi Seto <seto.hidetoshi@jp.fujitsu.com>
-
-CONTENTS:
-=========
-
-1. Cpusets
-  1.1 What are cpusets ?
-  1.2 Why are cpusets needed ?
-  1.3 How are cpusets implemented ?
-  1.4 What are exclusive cpusets ?
-  1.5 What is memory_pressure ?
-  1.6 What is memory spread ?
-  1.7 What is sched_load_balance ?
-  1.8 What is sched_relax_domain_level ?
-  1.9 How do I use cpusets ?
-2. Usage Examples and Syntax
-  2.1 Basic Usage
-  2.2 Adding/removing cpus
-  2.3 Setting flags
-  2.4 Attaching processes
-3. Questions
-4. Contact
-
-1. Cpusets
-==========
-
-1.1 What are cpusets ?
-----------------------
-
-Cpusets provide a mechanism for assigning a set of CPUs and Memory
-Nodes to a set of tasks.   In this document "Memory Node" refers to
-an on-line node that contains memory.
-
-Cpusets constrain the CPU and Memory placement of tasks to only
-the resources within a tasks current cpuset.  They form a nested
-hierarchy visible in a virtual file system.  These are the essential
-hooks, beyond what is already present, required to manage dynamic
-job placement on large systems.
-
-Cpusets use the generic cgroup subsystem described in
-Documentation/cgroups/cgroups.txt.
-
-Requests by a task, using the sched_setaffinity(2) system call to
-include CPUs in its CPU affinity mask, and using the mbind(2) and
-set_mempolicy(2) system calls to include Memory Nodes in its memory
-policy, are both filtered through that tasks cpuset, filtering out any
-CPUs or Memory Nodes not in that cpuset.  The scheduler will not
-schedule a task on a CPU that is not allowed in its cpus_allowed
-vector, and the kernel page allocator will not allocate a page on a
-node that is not allowed in the requesting tasks mems_allowed vector.
-
-User level code may create and destroy cpusets by name in the cgroup
-virtual file system, manage the attributes and permissions of these
-cpusets and which CPUs and Memory Nodes are assigned to each cpuset,
-specify and query to which cpuset a task is assigned, and list the
-task pids assigned to a cpuset.
-
-
-1.2 Why are cpusets needed ?
-----------------------------
-
-The management of large computer systems, with many processors (CPUs),
-complex memory cache hierarchies and multiple Memory Nodes having
-non-uniform access times (NUMA) presents additional challenges for
-the efficient scheduling and memory placement of processes.
-
-Frequently more modest sized systems can be operated with adequate
-efficiency just by letting the operating system automatically share
-the available CPU and Memory resources amongst the requesting tasks.
-
-But larger systems, which benefit more from careful processor and
-memory placement to reduce memory access times and contention,
-and which typically represent a larger investment for the customer,
-can benefit from explicitly placing jobs on properly sized subsets of
-the system.
-
-This can be especially valuable on:
-
-    * Web Servers running multiple instances of the same web application,
-    * Servers running different applications (for instance, a web server
-      and a database), or
-    * NUMA systems running large HPC applications with demanding
-      performance characteristics.
-
-These subsets, or "soft partitions" must be able to be dynamically
-adjusted, as the job mix changes, without impacting other concurrently
-executing jobs. The location of the running jobs pages may also be moved
-when the memory locations are changed.
-
-The kernel cpuset patch provides the minimum essential kernel
-mechanisms required to efficiently implement such subsets.  It
-leverages existing CPU and Memory Placement facilities in the Linux
-kernel to avoid any additional impact on the critical scheduler or
-memory allocator code.
-
-
-1.3 How are cpusets implemented ?
----------------------------------
-
-Cpusets provide a Linux kernel mechanism to constrain which CPUs and
-Memory Nodes are used by a process or set of processes.
-
-The Linux kernel already has a pair of mechanisms to specify on which
-CPUs a task may be scheduled (sched_setaffinity) and on which Memory
-Nodes it may obtain memory (mbind, set_mempolicy).
-
-Cpusets extends these two mechanisms as follows:
-
- - Cpusets are sets of allowed CPUs and Memory Nodes, known to the
-   kernel.
- - Each task in the system is attached to a cpuset, via a pointer
-   in the task structure to a reference counted cgroup structure.
- - Calls to sched_setaffinity are filtered to just those CPUs
-   allowed in that tasks cpuset.
- - Calls to mbind and set_mempolicy are filtered to just
-   those Memory Nodes allowed in that tasks cpuset.
- - The root cpuset contains all the systems CPUs and Memory
-   Nodes.
- - For any cpuset, one can define child cpusets containing a subset
-   of the parents CPU and Memory Node resources.
- - The hierarchy of cpusets can be mounted at /dev/cpuset, for
-   browsing and manipulation from user space.
- - A cpuset may be marked exclusive, which ensures that no other
-   cpuset (except direct ancestors and descendents) may contain
-   any overlapping CPUs or Memory Nodes.
- - You can list all the tasks (by pid) attached to any cpuset.
-
-The implementation of cpusets requires a few, simple hooks
-into the rest of the kernel, none in performance critical paths:
-
- - in init/main.c, to initialize the root cpuset at system boot.
- - in fork and exit, to attach and detach a task from its cpuset.
- - in sched_setaffinity, to mask the requested CPUs by what's
-   allowed in that tasks cpuset.
- - in sched.c migrate_all_tasks(), to keep migrating tasks within
-   the CPUs allowed by their cpuset, if possible.
- - in the mbind and set_mempolicy system calls, to mask the requested
-   Memory Nodes by what's allowed in that tasks cpuset.
- - in page_alloc.c, to restrict memory to allowed nodes.
- - in vmscan.c, to restrict page recovery to the current cpuset.
-
-You should mount the "cgroup" filesystem type in order to enable
-browsing and modifying the cpusets presently known to the kernel.  No
-new system calls are added for cpusets - all support for querying and
-modifying cpusets is via this cpuset file system.
-
-The /proc/<pid>/status file for each task has four added lines,
-displaying the tasks cpus_allowed (on which CPUs it may be scheduled)
-and mems_allowed (on which Memory Nodes it may obtain memory),
-in the two formats seen in the following example:
-
-  Cpus_allowed:   ffffffff,ffffffff,ffffffff,ffffffff
-  Cpus_allowed_list:      0-127
-  Mems_allowed:   ffffffff,ffffffff
-  Mems_allowed_list:      0-63
-
-Each cpuset is represented by a directory in the cgroup file system
-containing (on top of the standard cgroup files) the following
-files describing that cpuset:
-
- - cpus: list of CPUs in that cpuset
- - mems: list of Memory Nodes in that cpuset
- - memory_migrate flag: if set, move pages to cpusets nodes
- - cpu_exclusive flag: is cpu placement exclusive?
- - mem_exclusive flag: is memory placement exclusive?
- - mem_hardwall flag:  is memory allocation hardwalled
- - memory_pressure: measure of how much paging pressure in cpuset
-
-In addition, the root cpuset only has the following file:
- - memory_pressure_enabled flag: compute memory_pressure?
-
-New cpusets are created using the mkdir system call or shell
-command.  The properties of a cpuset, such as its flags, allowed
-CPUs and Memory Nodes, and attached tasks, are modified by writing
-to the appropriate file in that cpusets directory, as listed above.
-
-The named hierarchical structure of nested cpusets allows partitioning
-a large system into nested, dynamically changeable, "soft-partitions".
-
-The attachment of each task, automatically inherited at fork by any
-children of that task, to a cpuset allows organizing the work load
-on a system into related sets of tasks such that each set is constrained
-to using the CPUs and Memory Nodes of a particular cpuset.  A task
-may be re-attached to any other cpuset, if allowed by the permissions
-on the necessary cpuset file system directories.
-
-Such management of a system "in the large" integrates smoothly with
-the detailed placement done on individual tasks and memory regions
-using the sched_setaffinity, mbind and set_mempolicy system calls.
-
-The following rules apply to each cpuset:
-
- - Its CPUs and Memory Nodes must be a subset of its parents.
- - It can't be marked exclusive unless its parent is.
- - If its cpu or memory is exclusive, they may not overlap any sibling.
-
-These rules, and the natural hierarchy of cpusets, enable efficient
-enforcement of the exclusive guarantee, without having to scan all
-cpusets every time any of them change to ensure nothing overlaps a
-exclusive cpuset.  Also, the use of a Linux virtual file system (vfs)
-to represent the cpuset hierarchy provides for a familiar permission
-and name space for cpusets, with a minimum of additional kernel code.
-
-The cpus and mems files in the root (top_cpuset) cpuset are
-read-only.  The cpus file automatically tracks the value of
-cpu_online_map using a CPU hotplug notifier, and the mems file
-automatically tracks the value of node_states[N_HIGH_MEMORY]--i.e.,
-nodes with memory--using the cpuset_track_online_nodes() hook.
-
-
-1.4 What are exclusive cpusets ?
---------------------------------
-
-If a cpuset is cpu or mem exclusive, no other cpuset, other than
-a direct ancestor or descendent, may share any of the same CPUs or
-Memory Nodes.
-
-A cpuset that is mem_exclusive *or* mem_hardwall is "hardwalled",
-i.e. it restricts kernel allocations for page, buffer and other data
-commonly shared by the kernel across multiple users.  All cpusets,
-whether hardwalled or not, restrict allocations of memory for user
-space.  This enables configuring a system so that several independent
-jobs can share common kernel data, such as file system pages, while
-isolating each job's user allocation in its own cpuset.  To do this,
-construct a large mem_exclusive cpuset to hold all the jobs, and
-construct child, non-mem_exclusive cpusets for each individual job.
-Only a small amount of typical kernel memory, such as requests from
-interrupt handlers, is allowed to be taken outside even a
-mem_exclusive cpuset.
-
-
-1.5 What is memory_pressure ?
------------------------------
-The memory_pressure of a cpuset provides a simple per-cpuset metric
-of the rate that the tasks in a cpuset are attempting to free up in
-use memory on the nodes of the cpuset to satisfy additional memory
-requests.
-
-This enables batch managers monitoring jobs running in dedicated
-cpusets to efficiently detect what level of memory pressure that job
-is causing.
-
-This is useful both on tightly managed systems running a wide mix of
-submitted jobs, which may choose to terminate or re-prioritize jobs that
-are trying to use more memory than allowed on the nodes assigned them,
-and with tightly coupled, long running, massively parallel scientific
-computing jobs that will dramatically fail to meet required performance
-goals if they start to use more memory than allowed to them.
-
-This mechanism provides a very economical way for the batch manager
-to monitor a cpuset for signs of memory pressure.  It's up to the
-batch manager or other user code to decide what to do about it and
-take action.
-
-==> Unless this feature is enabled by writing "1" to the special file
-    /dev/cpuset/memory_pressure_enabled, the hook in the rebalance
-    code of __alloc_pages() for this metric reduces to simply noticing
-    that the cpuset_memory_pressure_enabled flag is zero.  So only
-    systems that enable this feature will compute the metric.
-
-Why a per-cpuset, running average:
-
-    Because this meter is per-cpuset, rather than per-task or mm,
-    the system load imposed by a batch scheduler monitoring this
-    metric is sharply reduced on large systems, because a scan of
-    the tasklist can be avoided on each set of queries.
-
-    Because this meter is a running average, instead of an accumulating
-    counter, a batch scheduler can detect memory pressure with a
-    single read, instead of having to read and accumulate results
-    for a period of time.
-
-    Because this meter is per-cpuset rather than per-task or mm,
-    the batch scheduler can obtain the key information, memory
-    pressure in a cpuset, with a single read, rather than having to
-    query and accumulate results over all the (dynamically changing)
-    set of tasks in the cpuset.
-
-A per-cpuset simple digital filter (requires a spinlock and 3 words
-of data per-cpuset) is kept, and updated by any task attached to that
-cpuset, if it enters the synchronous (direct) page reclaim code.
-
-A per-cpuset file provides an integer number representing the recent
-(half-life of 10 seconds) rate of direct page reclaims caused by
-the tasks in the cpuset, in units of reclaims attempted per second,
-times 1000.
-
-
-1.6 What is memory spread ?
----------------------------
-There are two boolean flag files per cpuset that control where the
-kernel allocates pages for the file system buffers and related in
-kernel data structures.  They are called 'memory_spread_page' and
-'memory_spread_slab'.
-
-If the per-cpuset boolean flag file 'memory_spread_page' is set, then
-the kernel will spread the file system buffers (page cache) evenly
-over all the nodes that the faulting task is allowed to use, instead
-of preferring to put those pages on the node where the task is running.
-
-If the per-cpuset boolean flag file 'memory_spread_slab' is set,
-then the kernel will spread some file system related slab caches,
-such as for inodes and dentries evenly over all the nodes that the
-faulting task is allowed to use, instead of preferring to put those
-pages on the node where the task is running.
-
-The setting of these flags does not affect anonymous data segment or
-stack segment pages of a task.
-
-By default, both kinds of memory spreading are off, and memory
-pages are allocated on the node local to where the task is running,
-except perhaps as modified by the tasks NUMA mempolicy or cpuset
-configuration, so long as sufficient free memory pages are available.
-
-When new cpusets are created, they inherit the memory spread settings
-of their parent.
-
-Setting memory spreading causes allocations for the affected page
-or slab caches to ignore the tasks NUMA mempolicy and be spread
-instead.    Tasks using mbind() or set_mempolicy() calls to set NUMA
-mempolicies will not notice any change in these calls as a result of
-their containing tasks memory spread settings.  If memory spreading
-is turned off, then the currently specified NUMA mempolicy once again
-applies to memory page allocations.
-
-Both 'memory_spread_page' and 'memory_spread_slab' are boolean flag
-files.  By default they contain "0", meaning that the feature is off
-for that cpuset.  If a "1" is written to that file, then that turns
-the named feature on.
-
-The implementation is simple.
-
-Setting the flag 'memory_spread_page' turns on a per-process flag
-PF_SPREAD_PAGE for each task that is in that cpuset or subsequently
-joins that cpuset.  The page allocation calls for the page cache
-is modified to perform an inline check for this PF_SPREAD_PAGE task
-flag, and if set, a call to a new routine cpuset_mem_spread_node()
-returns the node to prefer for the allocation.
-
-Similarly, setting 'memory_spread_slab' turns on the flag
-PF_SPREAD_SLAB, and appropriately marked slab caches will allocate
-pages from the node returned by cpuset_mem_spread_node().
-
-The cpuset_mem_spread_node() routine is also simple.  It uses the
-value of a per-task rotor cpuset_mem_spread_rotor to select the next
-node in the current tasks mems_allowed to prefer for the allocation.
-
-This memory placement policy is also known (in other contexts) as
-round-robin or interleave.
-
-This policy can provide substantial improvements for jobs that need
-to place thread local data on the corresponding node, but that need
-to access large file system data sets that need to be spread across
-the several nodes in the jobs cpuset in order to fit.  Without this
-policy, especially for jobs that might have one thread reading in the
-data set, the memory allocation across the nodes in the jobs cpuset
-can become very uneven.
-
-1.7 What is sched_load_balance ?
---------------------------------
-
-The kernel scheduler (kernel/sched.c) automatically load balances
-tasks.  If one CPU is underutilized, kernel code running on that
-CPU will look for tasks on other more overloaded CPUs and move those
-tasks to itself, within the constraints of such placement mechanisms
-as cpusets and sched_setaffinity.
-
-The algorithmic cost of load balancing and its impact on key shared
-kernel data structures such as the task list increases more than
-linearly with the number of CPUs being balanced.  So the scheduler
-has support to  partition the systems CPUs into a number of sched
-domains such that it only load balances within each sched domain.
-Each sched domain covers some subset of the CPUs in the system;
-no two sched domains overlap; some CPUs might not be in any sched
-domain and hence won't be load balanced.
-
-Put simply, it costs less to balance between two smaller sched domains
-than one big one, but doing so means that overloads in one of the
-two domains won't be load balanced to the other one.
-
-By default, there is one sched domain covering all CPUs, except those
-marked isolated using the kernel boot time "isolcpus=" argument.
-
-This default load balancing across all CPUs is not well suited for
-the following two situations:
- 1) On large systems, load balancing across many CPUs is expensive.
-    If the system is managed using cpusets to place independent jobs
-    on separate sets of CPUs, full load balancing is unnecessary.
- 2) Systems supporting realtime on some CPUs need to minimize
-    system overhead on those CPUs, including avoiding task load
-    balancing if that is not needed.
-
-When the per-cpuset flag "sched_load_balance" is enabled (the default
-setting), it requests that all the CPUs in that cpusets allowed 'cpus'
-be contained in a single sched domain, ensuring that load balancing
-can move a task (not otherwised pinned, as by sched_setaffinity)
-from any CPU in that cpuset to any other.
-
-When the per-cpuset flag "sched_load_balance" is disabled, then the
-scheduler will avoid load balancing across the CPUs in that cpuset,
---except-- in so far as is necessary because some overlapping cpuset
-has "sched_load_balance" enabled.
-
-So, for example, if the top cpuset has the flag "sched_load_balance"
-enabled, then the scheduler will have one sched domain covering all
-CPUs, and the setting of the "sched_load_balance" flag in any other
-cpusets won't matter, as we're already fully load balancing.
-
-Therefore in the above two situations, the top cpuset flag
-"sched_load_balance" should be disabled, and only some of the smaller,
-child cpusets have this flag enabled.
-
-When doing this, you don't usually want to leave any unpinned tasks in
-the top cpuset that might use non-trivial amounts of CPU, as such tasks
-may be artificially constrained to some subset of CPUs, depending on
-the particulars of this flag setting in descendent cpusets.  Even if
-such a task could use spare CPU cycles in some other CPUs, the kernel
-scheduler might not consider the possibility of load balancing that
-task to that underused CPU.
-
-Of course, tasks pinned to a particular CPU can be left in a cpuset
-that disables "sched_load_balance" as those tasks aren't going anywhere
-else anyway.
-
-There is an impedance mismatch here, between cpusets and sched domains.
-Cpusets are hierarchical and nest.  Sched domains are flat; they don't
-overlap and each CPU is in at most one sched domain.
-
-It is necessary for sched domains to be flat because load balancing
-across partially overlapping sets of CPUs would risk unstable dynamics
-that would be beyond our understanding.  So if each of two partially
-overlapping cpusets enables the flag 'sched_load_balance', then we
-form a single sched domain that is a superset of both.  We won't move
-a task to a CPU outside it cpuset, but the scheduler load balancing
-code might waste some compute cycles considering that possibility.
-
-This mismatch is why there is not a simple one-to-one relation
-between which cpusets have the flag "sched_load_balance" enabled,
-and the sched domain configuration.  If a cpuset enables the flag, it
-will get balancing across all its CPUs, but if it disables the flag,
-it will only be assured of no load balancing if no other overlapping
-cpuset enables the flag.
-
-If two cpusets have partially overlapping 'cpus' allowed, and only
-one of them has this flag enabled, then the other may find its
-tasks only partially load balanced, just on the overlapping CPUs.
-This is just the general case of the top_cpuset example given a few
-paragraphs above.  In the general case, as in the top cpuset case,
-don't leave tasks that might use non-trivial amounts of CPU in
-such partially load balanced cpusets, as they may be artificially
-constrained to some subset of the CPUs allowed to them, for lack of
-load balancing to the other CPUs.
-
-1.7.1 sched_load_balance implementation details.
-------------------------------------------------
-
-The per-cpuset flag 'sched_load_balance' defaults to enabled (contrary
-to most cpuset flags.)  When enabled for a cpuset, the kernel will
-ensure that it can load balance across all the CPUs in that cpuset
-(makes sure that all the CPUs in the cpus_allowed of that cpuset are
-in the same sched domain.)
-
-If two overlapping cpusets both have 'sched_load_balance' enabled,
-then they will be (must be) both in the same sched domain.
-
-If, as is the default, the top cpuset has 'sched_load_balance' enabled,
-then by the above that means there is a single sched domain covering
-the whole system, regardless of any other cpuset settings.
-
-The kernel commits to user space that it will avoid load balancing
-where it can.  It will pick as fine a granularity partition of sched
-domains as it can while still providing load balancing for any set
-of CPUs allowed to a cpuset having 'sched_load_balance' enabled.
-
-The internal kernel cpuset to scheduler interface passes from the
-cpuset code to the scheduler code a partition of the load balanced
-CPUs in the system. This partition is a set of subsets (represented
-as an array of cpumask_t) of CPUs, pairwise disjoint, that cover all
-the CPUs that must be load balanced.
-
-Whenever the 'sched_load_balance' flag changes, or CPUs come or go
-from a cpuset with this flag enabled, or a cpuset with this flag
-enabled is removed, the cpuset code builds a new such partition and
-passes it to the scheduler sched domain setup code, to have the sched
-domains rebuilt as necessary.
-
-This partition exactly defines what sched domains the scheduler should
-setup - one sched domain for each element (cpumask_t) in the partition.
-
-The scheduler remembers the currently active sched domain partitions.
-When the scheduler routine partition_sched_domains() is invoked from
-the cpuset code to update these sched domains, it compares the new
-partition requested with the current, and updates its sched domains,
-removing the old and adding the new, for each change.
-
-
-1.8 What is sched_relax_domain_level ?
---------------------------------------
-
-In sched domain, the scheduler migrates tasks in 2 ways; periodic load
-balance on tick, and at time of some schedule events.
-
-When a task is woken up, scheduler try to move the task on idle CPU.
-For example, if a task A running on CPU X activates another task B
-on the same CPU X, and if CPU Y is X's sibling and performing idle,
-then scheduler migrate task B to CPU Y so that task B can start on
-CPU Y without waiting task A on CPU X.
-
-And if a CPU run out of tasks in its runqueue, the CPU try to pull
-extra tasks from other busy CPUs to help them before it is going to
-be idle.
-
-Of course it takes some searching cost to find movable tasks and/or
-idle CPUs, the scheduler might not search all CPUs in the domain
-everytime.  In fact, in some architectures, the searching ranges on
-events are limited in the same socket or node where the CPU locates,
-while the load balance on tick searchs all.
-
-For example, assume CPU Z is relatively far from CPU X.  Even if CPU Z
-is idle while CPU X and the siblings are busy, scheduler can't migrate
-woken task B from X to Z since it is out of its searching range.
-As the result, task B on CPU X need to wait task A or wait load balance
-on the next tick.  For some applications in special situation, waiting
-1 tick may be too long.
-
-The 'sched_relax_domain_level' file allows you to request changing
-this searching range as you like.  This file takes int value which
-indicates size of searching range in levels ideally as follows,
-otherwise initial value -1 that indicates the cpuset has no request.
-
-  -1  : no request. use system default or follow request of others.
-   0  : no search.
-   1  : search siblings (hyperthreads in a core).
-   2  : search cores in a package.
-   3  : search cpus in a node [= system wide on non-NUMA system]
- ( 4  : search nodes in a chunk of node [on NUMA system] )
- ( 5  : search system wide [on NUMA system] )
-
-The system default is architecture dependent.  The system default
-can be changed using the relax_domain_level= boot parameter.
-
-This file is per-cpuset and affect the sched domain where the cpuset
-belongs to.  Therefore if the flag 'sched_load_balance' of a cpuset
-is disabled, then 'sched_relax_domain_level' have no effect since
-there is no sched domain belonging the cpuset.
-
-If multiple cpusets are overlapping and hence they form a single sched
-domain, the largest value among those is used.  Be careful, if one
-requests 0 and others are -1 then 0 is used.
-
-Note that modifying this file will have both good and bad effects,
-and whether it is acceptable or not will be depend on your situation.
-Don't modify this file if you are not sure.
-
-If your situation is:
- - The migration costs between each cpu can be assumed considerably
-   small(for you) due to your special application's behavior or
-   special hardware support for CPU cache etc.
- - The searching cost doesn't have impact(for you) or you can make
-   the searching cost enough small by managing cpuset to compact etc.
- - The latency is required even it sacrifices cache hit rate etc.
-then increasing 'sched_relax_domain_level' would benefit you.
-
-
-1.9 How do I use cpusets ?
---------------------------
-
-In order to minimize the impact of cpusets on critical kernel
-code, such as the scheduler, and due to the fact that the kernel
-does not support one task updating the memory placement of another
-task directly, the impact on a task of changing its cpuset CPU
-or Memory Node placement, or of changing to which cpuset a task
-is attached, is subtle.
-
-If a cpuset has its Memory Nodes modified, then for each task attached
-to that cpuset, the next time that the kernel attempts to allocate
-a page of memory for that task, the kernel will notice the change
-in the tasks cpuset, and update its per-task memory placement to
-remain within the new cpusets memory placement.  If the task was using
-mempolicy MPOL_BIND, and the nodes to which it was bound overlap with
-its new cpuset, then the task will continue to use whatever subset
-of MPOL_BIND nodes are still allowed in the new cpuset.  If the task
-was using MPOL_BIND and now none of its MPOL_BIND nodes are allowed
-in the new cpuset, then the task will be essentially treated as if it
-was MPOL_BIND bound to the new cpuset (even though its numa placement,
-as queried by get_mempolicy(), doesn't change).  If a task is moved
-from one cpuset to another, then the kernel will adjust the tasks
-memory placement, as above, the next time that the kernel attempts
-to allocate a page of memory for that task.
-
-If a cpuset has its 'cpus' modified, then each task in that cpuset
-will have its allowed CPU placement changed immediately.  Similarly,
-if a tasks pid is written to a cpusets 'tasks' file, in either its
-current cpuset or another cpuset, then its allowed CPU placement is
-changed immediately.  If such a task had been bound to some subset
-of its cpuset using the sched_setaffinity() call, the task will be
-allowed to run on any CPU allowed in its new cpuset, negating the
-affect of the prior sched_setaffinity() call.
-
-In summary, the memory placement of a task whose cpuset is changed is
-updated by the kernel, on the next allocation of a page for that task,
-but the processor placement is not updated, until that tasks pid is
-rewritten to the 'tasks' file of its cpuset.  This is done to avoid
-impacting the scheduler code in the kernel with a check for changes
-in a tasks processor placement.
-
-Normally, once a page is allocated (given a physical page
-of main memory) then that page stays on whatever node it
-was allocated, so long as it remains allocated, even if the
-cpusets memory placement policy 'mems' subsequently changes.
-If the cpuset flag file 'memory_migrate' is set true, then when
-tasks are attached to that cpuset, any pages that task had
-allocated to it on nodes in its previous cpuset are migrated
-to the tasks new cpuset. The relative placement of the page within
-the cpuset is preserved during these migration operations if possible.
-For example if the page was on the second valid node of the prior cpuset
-then the page will be placed on the second valid node of the new cpuset.
-
-Also if 'memory_migrate' is set true, then if that cpusets
-'mems' file is modified, pages allocated to tasks in that
-cpuset, that were on nodes in the previous setting of 'mems',
-will be moved to nodes in the new setting of 'mems.'
-Pages that were not in the tasks prior cpuset, or in the cpusets
-prior 'mems' setting, will not be moved.
-
-There is an exception to the above.  If hotplug functionality is used
-to remove all the CPUs that are currently assigned to a cpuset,
-then all the tasks in that cpuset will be moved to the nearest ancestor
-with non-empty cpus.  But the moving of some (or all) tasks might fail if
-cpuset is bound with another cgroup subsystem which has some restrictions
-on task attaching.  In this failing case, those tasks will stay
-in the original cpuset, and the kernel will automatically update
-their cpus_allowed to allow all online CPUs.  When memory hotplug
-functionality for removing Memory Nodes is available, a similar exception
-is expected to apply there as well.  In general, the kernel prefers to
-violate cpuset placement, over starving a task that has had all
-its allowed CPUs or Memory Nodes taken offline.
-
-There is a second exception to the above.  GFP_ATOMIC requests are
-kernel internal allocations that must be satisfied, immediately.
-The kernel may drop some request, in rare cases even panic, if a
-GFP_ATOMIC alloc fails.  If the request cannot be satisfied within
-the current tasks cpuset, then we relax the cpuset, and look for
-memory anywhere we can find it.  It's better to violate the cpuset
-than stress the kernel.
-
-To start a new job that is to be contained within a cpuset, the steps are:
-
- 1) mkdir /dev/cpuset
- 2) mount -t cgroup -ocpuset cpuset /dev/cpuset
- 3) Create the new cpuset by doing mkdir's and write's (or echo's) in
-    the /dev/cpuset virtual file system.
- 4) Start a task that will be the "founding father" of the new job.
- 5) Attach that task to the new cpuset by writing its pid to the
-    /dev/cpuset tasks file for that cpuset.
- 6) fork, exec or clone the job tasks from this founding father task.
-
-For example, the following sequence of commands will setup a cpuset
-named "Charlie", containing just CPUs 2 and 3, and Memory Node 1,
-and then start a subshell 'sh' in that cpuset:
-
-  mount -t cgroup -ocpuset cpuset /dev/cpuset
-  cd /dev/cpuset
-  mkdir Charlie
-  cd Charlie
-  /bin/echo 2-3 > cpus
-  /bin/echo 1 > mems
-  /bin/echo $$ > tasks
-  sh
-  # The subshell 'sh' is now running in cpuset Charlie
-  # The next line should display '/Charlie'
-  cat /proc/self/cpuset
-
-In the future, a C library interface to cpusets will likely be
-available.  For now, the only way to query or modify cpusets is
-via the cpuset file system, using the various cd, mkdir, echo, cat,
-rmdir commands from the shell, or their equivalent from C.
-
-The sched_setaffinity calls can also be done at the shell prompt using
-SGI's runon or Robert Love's taskset.  The mbind and set_mempolicy
-calls can be done at the shell prompt using the numactl command
-(part of Andi Kleen's numa package).
-
-2. Usage Examples and Syntax
-============================
-
-2.1 Basic Usage
----------------
-
-Creating, modifying, using the cpusets can be done through the cpuset
-virtual filesystem.
-
-To mount it, type:
-# mount -t cgroup -o cpuset cpuset /dev/cpuset
-
-Then under /dev/cpuset you can find a tree that corresponds to the
-tree of the cpusets in the system. For instance, /dev/cpuset
-is the cpuset that holds the whole system.
-
-If you want to create a new cpuset under /dev/cpuset:
-# cd /dev/cpuset
-# mkdir my_cpuset
-
-Now you want to do something with this cpuset.
-# cd my_cpuset
-
-In this directory you can find several files:
-# ls
-cpu_exclusive  memory_migrate      mems                      tasks
-cpus           memory_pressure     notify_on_release
-mem_exclusive  memory_spread_page  sched_load_balance
-mem_hardwall   memory_spread_slab  sched_relax_domain_level
-
-Reading them will give you information about the state of this cpuset:
-the CPUs and Memory Nodes it can use, the processes that are using
-it, its properties.  By writing to these files you can manipulate
-the cpuset.
-
-Set some flags:
-# /bin/echo 1 > cpu_exclusive
-
-Add some cpus:
-# /bin/echo 0-7 > cpus
-
-Add some mems:
-# /bin/echo 0-7 > mems
-
-Now attach your shell to this cpuset:
-# /bin/echo $$ > tasks
-
-You can also create cpusets inside your cpuset by using mkdir in this
-directory.
-# mkdir my_sub_cs
-
-To remove a cpuset, just use rmdir:
-# rmdir my_sub_cs
-This will fail if the cpuset is in use (has cpusets inside, or has
-processes attached).
-
-Note that for legacy reasons, the "cpuset" filesystem exists as a
-wrapper around the cgroup filesystem.
-
-The command
-
-mount -t cpuset X /dev/cpuset
-
-is equivalent to
-
-mount -t cgroup -ocpuset X /dev/cpuset
-echo "/sbin/cpuset_release_agent" > /dev/cpuset/release_agent
-
-2.2 Adding/removing cpus
-------------------------
-
-This is the syntax to use when writing in the cpus or mems files
-in cpuset directories:
-
-# /bin/echo 1-4 > cpus		-> set cpus list to cpus 1,2,3,4
-# /bin/echo 1,2,3,4 > cpus	-> set cpus list to cpus 1,2,3,4
-
-2.3 Setting flags
------------------
-
-The syntax is very simple:
-
-# /bin/echo 1 > cpu_exclusive 	-> set flag 'cpu_exclusive'
-# /bin/echo 0 > cpu_exclusive 	-> unset flag 'cpu_exclusive'
-
-2.4 Attaching processes
------------------------
-
-# /bin/echo PID > tasks
-
-Note that it is PID, not PIDs. You can only attach ONE task at a time.
-If you have several tasks to attach, you have to do it one after another:
-
-# /bin/echo PID1 > tasks
-# /bin/echo PID2 > tasks
-	...
-# /bin/echo PIDn > tasks
-
-
-3. Questions
-============
-
-Q: what's up with this '/bin/echo' ?
-A: bash's builtin 'echo' command does not check calls to write() against
-   errors. If you use it in the cpuset file system, you won't be
-   able to tell whether a command succeeded or failed.
-
-Q: When I attach processes, only the first of the line gets really attached !
-A: We can only return one error code per call to write(). So you should also
-   put only ONE pid.
-
-4. Contact
-==========
-
-Web: http://www.bullopensource.org/cpuset
diff --git a/Documentation/scheduler/sched-design-CFS.txt b/Documentation/scheduler/sched-design-CFS.txt
index 8398ca4ff4ed..6f33593e59e2 100644
--- a/Documentation/scheduler/sched-design-CFS.txt
+++ b/Documentation/scheduler/sched-design-CFS.txt
@@ -231,7 +231,7 @@ CPU bandwidth control purposes:
 
    This options needs CONFIG_CGROUPS to be defined, and lets the administrator
    create arbitrary groups of tasks, using the "cgroup" pseudo filesystem.  See
-   Documentation/cgroups.txt for more information about this filesystem.
+   Documentation/cgroups/cgroups.txt for more information about this filesystem.
 
 Only one of these options to group tasks can be chosen and not both.
 
diff --git a/include/linux/res_counter.h b/include/linux/res_counter.h
index dede0a2cfc45..4c5bcf6ca7e8 100644
--- a/include/linux/res_counter.h
+++ b/include/linux/res_counter.h
@@ -9,7 +9,7 @@
  *
  * Author: Pavel Emelianov <xemul@openvz.org>
  *
- * See Documentation/controllers/resource_counter.txt for more
+ * See Documentation/cgroups/resource_counter.txt for more
  * info about what this counter is.
  */
 
diff --git a/init/Kconfig b/init/Kconfig
index 56fd93c63c77..2af83825634e 100644
--- a/init/Kconfig
+++ b/init/Kconfig
@@ -323,8 +323,8 @@ config CGROUP_SCHED
 	  This option allows you to create arbitrary task groups
 	  using the "cgroup" pseudo filesystem and control
 	  the cpu bandwidth allocated to each such task group.
-	  Refer to Documentation/cgroups.txt for more information
-	  on "cgroup" pseudo filesystem.
+	  Refer to Documentation/cgroups/cgroups.txt for more
+	  information on "cgroup" pseudo filesystem.
 
 endchoice
 
@@ -335,10 +335,9 @@ menuconfig CGROUPS
 	  use with process control subsystems such as Cpusets, CFS, memory
 	  controls or device isolation.
 	  See
-		- Documentation/cpusets.txt	(Cpusets)
 		- Documentation/scheduler/sched-design-CFS.txt	(CFS)
-		- Documentation/cgroups/ (features for grouping, isolation)
-		- Documentation/controllers/ (features for resource control)
+		- Documentation/cgroups/ (features for grouping, isolation
+					  and resource control)
 
 	  Say N if unsure.
 
diff --git a/kernel/cpuset.c b/kernel/cpuset.c
index 647c77a88fcb..a85678865c5e 100644
--- a/kernel/cpuset.c
+++ b/kernel/cpuset.c
@@ -568,7 +568,7 @@ update_domain_attr_tree(struct sched_domain_attr *dattr, struct cpuset *c)
  * load balancing domains (sched domains) as specified by that partial
  * partition.
  *
- * See "What is sched_load_balance" in Documentation/cpusets.txt
+ * See "What is sched_load_balance" in Documentation/cgroups/cpusets.txt
  * for a background explanation of this.
  *
  * Does not return errors, on the theory that the callers of this
-- 
cgit v1.2.3


From 6ae301e85c9c58d2f430a8a7057ce488b7ff76df Mon Sep 17 00:00:00 2001
From: Randy Dunlap <randy.dunlap@oracle.com>
Date: Thu, 15 Jan 2009 13:51:01 -0800
Subject: resources: fix parameter name and kernel-doc

Fix __request_region() parameter kernel-doc notation and parameter name:

Warning(linux-2.6.28-git10//kernel/resource.c:627): No description found for parameter 'flags'

Signed-off-by: Randy Dunlap <randy.dunlap@oracle.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/ioport.h | 3 ++-
 kernel/resource.c      | 1 +
 2 files changed, 3 insertions(+), 1 deletion(-)

(limited to 'kernel')

diff --git a/include/linux/ioport.h b/include/linux/ioport.h
index f6bb2ca8e3ba..32e4b2f72294 100644
--- a/include/linux/ioport.h
+++ b/include/linux/ioport.h
@@ -143,7 +143,8 @@ static inline unsigned long resource_type(struct resource *res)
 
 extern struct resource * __request_region(struct resource *,
 					resource_size_t start,
-					resource_size_t n, const char *name, int relaxed);
+					resource_size_t n,
+					const char *name, int flags);
 
 /* Compatibility cruft */
 #define release_region(start,n)	__release_region(&ioport_resource, (start), (n))
diff --git a/kernel/resource.c b/kernel/resource.c
index ca6a1536b205..fd5d7d574bb9 100644
--- a/kernel/resource.c
+++ b/kernel/resource.c
@@ -620,6 +620,7 @@ resource_size_t resource_alignment(struct resource *res)
  * @start: resource start address
  * @n: resource region size
  * @name: reserving caller's ID string
+ * @flags: IO resource flags
  */
 struct resource * __request_region(struct resource *parent,
 				   resource_size_t start, resource_size_t n,
-- 
cgit v1.2.3


From 33f1d7ecc6cffff3c618a02295de969ebbacd95d Mon Sep 17 00:00:00 2001
From: "Rafael J. Wysocki" <rjw@sisk.pl>
Date: Tue, 6 Jan 2009 21:14:04 +0100
Subject: PM: Fix freezer compilation if PM_SLEEP is unset

Freezer fails to compile if with the following configuration
settings:

CONFIG_CGROUPS=y
CONFIG_CGROUP_FREEZER=y
CONFIG_MODULES=y
CONFIG_FREEZER=y
CONFIG_PM=y
CONFIG_PM_SLEEP=n

Fix this by making process.o compilation depend on CONFIG_FREEZER.

Reported-by: Cheng Renquan <crquan@gmail.com>
Signed-off-by: Rafael J. Wysocki <rjw@sisk.pl>
Acked-by: Pavel Machek <pavel@suse.cz>
Signed-off-by: Len Brown <len.brown@intel.com>
---
 kernel/power/Makefile | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

(limited to 'kernel')

diff --git a/kernel/power/Makefile b/kernel/power/Makefile
index 597823b5b700..d7a10167a25b 100644
--- a/kernel/power/Makefile
+++ b/kernel/power/Makefile
@@ -4,7 +4,8 @@ EXTRA_CFLAGS	+=	-DDEBUG
 endif
 
 obj-y				:= main.o
-obj-$(CONFIG_PM_SLEEP)		+= process.o console.o
+obj-$(CONFIG_PM_SLEEP)		+= console.o
+obj-$(CONFIG_FREEZER)		+= process.o
 obj-$(CONFIG_HIBERNATION)	+= swsusp.o disk.o snapshot.o swap.o user.o
 
 obj-$(CONFIG_MAGIC_SYSRQ)	+= poweroff.o
-- 
cgit v1.2.3


From 5a4ccaf37ffece09ef33f1cfec67efa8ee56f967 Mon Sep 17 00:00:00 2001
From: Masami Hiramatsu <mhiramat@redhat.com>
Date: Tue, 6 Jan 2009 21:15:32 +0100
Subject: kprobes: check CONFIG_FREEZER instead of CONFIG_PM

Check CONFIG_FREEZER instead of CONFIG_PM because kprobe booster
depends on freeze_processes() and thaw_processes() when CONFIG_PREEMPT=y.

This fixes a linkage error which occurs when CONFIG_PREEMPT=y, CONFIG_PM=y
and CONFIG_FREEZER=n.

Reported-by: Cheng Renquan <crquan@gmail.com>
Signed-off-by: Masami Hiramatsu <mhiramat@redhat.com>
Signed-off-by: Rafael J. Wysocki <rjw@sisk.pl>
Acked-by: Ingo Molnar <mingo@elte.hu>
Signed-off-by: Len Brown <len.brown@intel.com>
---
 arch/ia64/kernel/kprobes.c | 2 +-
 arch/x86/kernel/kprobes.c  | 2 +-
 kernel/kprobes.c           | 2 +-
 3 files changed, 3 insertions(+), 3 deletions(-)

(limited to 'kernel')

diff --git a/arch/ia64/kernel/kprobes.c b/arch/ia64/kernel/kprobes.c
index f90be51b1123..9adac441ac9b 100644
--- a/arch/ia64/kernel/kprobes.c
+++ b/arch/ia64/kernel/kprobes.c
@@ -870,7 +870,7 @@ static int __kprobes pre_kprobes_handler(struct die_args *args)
 		return 1;
 
 ss_probe:
-#if !defined(CONFIG_PREEMPT) || defined(CONFIG_PM)
+#if !defined(CONFIG_PREEMPT) || defined(CONFIG_FREEZER)
 	if (p->ainsn.inst_flag == INST_FLAG_BOOSTABLE && !p->post_handler) {
 		/* Boost up -- we can execute copied instructions directly */
 		ia64_psr(regs)->ri = p->ainsn.slot;
diff --git a/arch/x86/kernel/kprobes.c b/arch/x86/kernel/kprobes.c
index 884d985b8b82..e948b28a5a9a 100644
--- a/arch/x86/kernel/kprobes.c
+++ b/arch/x86/kernel/kprobes.c
@@ -446,7 +446,7 @@ void __kprobes arch_prepare_kretprobe(struct kretprobe_instance *ri,
 static void __kprobes setup_singlestep(struct kprobe *p, struct pt_regs *regs,
 				       struct kprobe_ctlblk *kcb)
 {
-#if !defined(CONFIG_PREEMPT) || defined(CONFIG_PM)
+#if !defined(CONFIG_PREEMPT) || defined(CONFIG_FREEZER)
 	if (p->ainsn.boostable == 1 && !p->post_handler) {
 		/* Boost up -- we can execute copied instructions directly */
 		reset_current_kprobe();
diff --git a/kernel/kprobes.c b/kernel/kprobes.c
index 1b9cbdc0127a..7ba8cd9845cb 100644
--- a/kernel/kprobes.c
+++ b/kernel/kprobes.c
@@ -123,7 +123,7 @@ static int collect_garbage_slots(void);
 static int __kprobes check_safety(void)
 {
 	int ret = 0;
-#if defined(CONFIG_PREEMPT) && defined(CONFIG_PM)
+#if defined(CONFIG_PREEMPT) && defined(CONFIG_FREEZER)
 	ret = freeze_processes();
 	if (ret == 0) {
 		struct task_struct *p, *q;
-- 
cgit v1.2.3


From b786c6a98ef6fa81114ba7b9fbfc0d67060775e3 Mon Sep 17 00:00:00 2001
From: Jiri Slaby <jirislaby@gmail.com>
Date: Sat, 17 Jan 2009 12:04:36 +0100
Subject: relay: fix lock imbalance in relay_late_setup_files

One fail path in relay_late_setup_files() omits
mutex_unlock(&relay_channels_mutex);
Add it.

Signed-off-by: Jiri Slaby <jirislaby@gmail.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
---
 kernel/relay.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

(limited to 'kernel')

diff --git a/kernel/relay.c b/kernel/relay.c
index 09ac2008f77b..9d79b7854fa6 100644
--- a/kernel/relay.c
+++ b/kernel/relay.c
@@ -663,8 +663,10 @@ int relay_late_setup_files(struct rchan *chan,
 
 	mutex_lock(&relay_channels_mutex);
 	/* Is chan already set up? */
-	if (unlikely(chan->has_base_filename))
+	if (unlikely(chan->has_base_filename)) {
+		mutex_unlock(&relay_channels_mutex);
 		return -EEXIST;
+	}
 	chan->has_base_filename = 1;
 	chan->parent = parent;
 	curr_cpu = get_cpu();
-- 
cgit v1.2.3


From 1d4a7f1c4faf53eb9e822743ec8a70b3019a26d2 Mon Sep 17 00:00:00 2001
From: Peter Zijlstra <peterz@infradead.org>
Date: Sun, 18 Jan 2009 16:39:29 +0100
Subject: hrtimers: fix inconsistent lock state on resume in hres_timers_resume

Andrey Borzenkov reported this lockdep assert:

> [17854.688347] =================================
> [17854.688347] [ INFO: inconsistent lock state ]
> [17854.688347] 2.6.29-rc2-1avb #1
> [17854.688347] ---------------------------------
> [17854.688347] inconsistent {in-hardirq-W} -> {hardirq-on-W} usage.
> [17854.688347] pm-suspend/18240 [HC0[0]:SC0[0]:HE1:SE1] takes:
> [17854.688347]  (&cpu_base->lock){++..}, at: [<c0136fcc>] retrigger_next_event+0x5c/0xa0
> [17854.688347] {in-hardirq-W} state was registered at:
> [17854.688347]   [<c01443cd>] __lock_acquire+0x79d/0x1930
> [17854.688347]   [<c01455bc>] lock_acquire+0x5c/0x80
> [17854.688347]   [<c03092e5>] _spin_lock+0x35/0x70
> [17854.688347]   [<c0136e61>] hrtimer_run_queues+0x31/0x140
> [17854.688347]   [<c0128d98>] run_local_timers+0x8/0x20
> [17854.688347]   [<c0128dd3>] update_process_times+0x23/0x60
> [17854.688347]   [<c013e274>] tick_periodic+0x24/0x80
> [17854.688347]   [<c013e2e2>] tick_handle_periodic+0x12/0x70
> [17854.688347]   [<c0104e24>] timer_interrupt+0x14/0x20
> [17854.688347]   [<c01607b9>] handle_IRQ_event+0x29/0x60
> [17854.688347]   [<c0161c59>] handle_level_irq+0x69/0xe0
> [17854.688347]   [<ffffffff>] 0xffffffff
> [17854.688347] irq event stamp: 55771
> [17854.688347] hardirqs last  enabled at (55771): [<c0309125>] _spin_unlock_irqrestore+0x35/0x60
> [17854.688347] hardirqs last disabled at (55770): [<c0309419>] _spin_lock_irqsave+0x19/0x80
> [17854.688347] softirqs last  enabled at (54836): [<c0124f54>] __do_softirq+0xc4/0x110
> [17854.688347] softirqs last disabled at (54831): [<c01049ae>] do_softirq+0x8e/0xe0
> [17854.688347]
> [17854.688347] other info that might help us debug this:
> [17854.688347] 3 locks held by pm-suspend/18240:
> [17854.688347]  #0:  (&buffer->mutex){--..}, at: [<c01dd4c5>] sysfs_write_file+0x25/0x100
> [17854.688347]  #1:  (pm_mutex){--..}, at: [<c015056f>] enter_state+0x4f/0x140
> [17854.688347]  #2:  (dpm_list_mtx){--..}, at: [<c027880f>] device_pm_lock+0xf/0x20
> [17854.688347]
> [17854.688347] stack backtrace:
> [17854.688347] Pid: 18240, comm: pm-suspend Not tainted 2.6.29-rc2-1avb #1
> [17854.688347] Call Trace:
> [17854.688347]  [<c0306248>] ? printk+0x18/0x20
> [17854.688347]  [<c0141fac>] print_usage_bug+0x16c/0x1d0
> [17854.688347]  [<c0142bcf>] mark_lock+0x8bf/0xc90
> [17854.688347]  [<c0106b8f>] ? pit_next_event+0x2f/0x40
> [17854.688347]  [<c01441b0>] __lock_acquire+0x580/0x1930
> [17854.688347]  [<c030916d>] ? _spin_unlock+0x1d/0x20
> [17854.688347]  [<c0106b8f>] ? pit_next_event+0x2f/0x40
> [17854.688347]  [<c013dd38>] ? clockevents_program_event+0x98/0x160
> [17854.688347]  [<c0142fe8>] ? mark_held_locks+0x48/0x90
> [17854.688347]  [<c0309125>] ? _spin_unlock_irqrestore+0x35/0x60
> [17854.688347]  [<c0143229>] ? trace_hardirqs_on_caller+0x139/0x190
> [17854.688347]  [<c014328b>] ? trace_hardirqs_on+0xb/0x10
> [17854.688347]  [<c01455bc>] lock_acquire+0x5c/0x80
> [17854.688347]  [<c0136fcc>] ? retrigger_next_event+0x5c/0xa0
> [17854.688347]  [<c03092e5>] _spin_lock+0x35/0x70
> [17854.688347]  [<c0136fcc>] ? retrigger_next_event+0x5c/0xa0
> [17854.688347]  [<c0136fcc>] retrigger_next_event+0x5c/0xa0
> [17854.688347]  [<c013711a>] hres_timers_resume+0xa/0x10
> [17854.688347]  [<c013aa8e>] timekeeping_resume+0xee/0x150
> [17854.688347]  [<c0273384>] __sysdev_resume+0x14/0x50
> [17854.688347]  [<c0273407>] sysdev_resume+0x47/0x80
> [17854.688347]  [<c02791ab>] device_power_up+0xb/0x20
> [17854.688347]  [<c015043f>] suspend_devices_and_enter+0xcf/0x150
> [17854.688347]  [<c0150c2f>] ? freeze_processes+0x3f/0x90
> [17854.688347]  [<c0150614>] enter_state+0xf4/0x140
> [17854.688347]  [<c01506dd>] state_store+0x7d/0xc0
> [17854.688347]  [<c0150660>] ? state_store+0x0/0xc0
> [17854.688347]  [<c0202da4>] kobj_attr_store+0x24/0x30
> [17854.688347]  [<c01dd53c>] sysfs_write_file+0x9c/0x100
> [17854.688347]  [<c019916c>] vfs_write+0x9c/0x160
> [17854.688347]  [<c0103494>] ? restore_nocheck_notrace+0x0/0xe
> [17854.688347]  [<c01dd4a0>] ? sysfs_write_file+0x0/0x100
> [17854.688347]  [<c01992ed>] sys_write+0x3d/0x70
> [17854.688347]  [<c0103371>] sysenter_do_call+0x12/0x31

Andrey's analysis:

> timekeeping_resume() is called via class ->resume
> method; and according to comments in sysdev_resume() and
> device_power_up(), they are called with interrupts disabled.
>
> Looking at suspend_enter, irqs *are* disabled at this point.
>
> So it actually looks like something (may be some driver)
> unconditionally enabled irqs in resume path.

Add a debug check to test this theory. If it triggers then it
triggers because the resume code calls it with irqs enabled,
which is a no-no not just for timekeeping_resume(), but also
bad for a number of other resume handlers.

Reported-by: Andrey Borzenkov <arvidjaar@mail.ru>
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
---
 kernel/hrtimer.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

(limited to 'kernel')

diff --git a/kernel/hrtimer.c b/kernel/hrtimer.c
index 1455b7651b6b..cb83c6d4c07c 100644
--- a/kernel/hrtimer.c
+++ b/kernel/hrtimer.c
@@ -614,7 +614,9 @@ void clock_was_set(void)
  */
 void hres_timers_resume(void)
 {
-	/* Retrigger the CPU local events: */
+	WARN_ONCE(!irqs_disabled(),
+		  KERN_INFO "hres_timers_resume() called with IRQs enabled!");
+
 	retrigger_next_event(NULL);
 }
 
-- 
cgit v1.2.3


From f90d4118bacef87894621a3e8aba853fa0c89abc Mon Sep 17 00:00:00 2001
From: Miao Xie <miaox@cn.fujitsu.com>
Date: Fri, 16 Jan 2009 10:24:10 +0800
Subject: cpuset: fix possible deadlock in async_rebuild_sched_domains

Lockdep reported some possible circular locking info when we tested cpuset on
NUMA/fake NUMA box.

=======================================================
[ INFO: possible circular locking dependency detected ]
2.6.29-rc1-00224-ga652504 #111
-------------------------------------------------------
bash/2968 is trying to acquire lock:
 (events){--..}, at: [<ffffffff8024c8cd>] flush_work+0x24/0xd8

but task is already holding lock:
 (cgroup_mutex){--..}, at: [<ffffffff8026ad1e>] cgroup_lock_live_group+0x12/0x29

which lock already depends on the new lock.
......
-------------------------------------------------------

Steps to reproduce:
# mkdir /dev/cpuset
# mount -t cpuset xxx /dev/cpuset
# mkdir /dev/cpuset/0
# echo 0 > /dev/cpuset/0/cpus
# echo 0 > /dev/cpuset/0/mems
# echo 1 > /dev/cpuset/0/memory_migrate
# cat /dev/zero > /dev/null &
# echo $! > /dev/cpuset/0/tasks

This is because async_rebuild_sched_domains has the following lock sequence:
run_workqueue(async_rebuild_sched_domains)
	-> do_rebuild_sched_domains -> cgroup_lock

But, attaching tasks when memory_migrate is set has following:
cgroup_lock_live_group(cgroup_tasks_write)
	-> do_migrate_pages -> flush_work

This patch fixes it by using a separate workqueue thread.

Signed-off-by: Miao Xie <miaox@cn.fujitsu.com>
Signed-off-by: Lai Jiangshan <laijs@cn.fujitsu.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
---
 kernel/cpuset.c | 13 ++++++++++++-
 1 file changed, 12 insertions(+), 1 deletion(-)

(limited to 'kernel')

diff --git a/kernel/cpuset.c b/kernel/cpuset.c
index a85678865c5e..f76db9dcaa05 100644
--- a/kernel/cpuset.c
+++ b/kernel/cpuset.c
@@ -60,6 +60,14 @@
 #include <linux/workqueue.h>
 #include <linux/cgroup.h>
 
+/*
+ * Workqueue for cpuset related tasks.
+ *
+ * Using kevent workqueue may cause deadlock when memory_migrate
+ * is set. So we create a separate workqueue thread for cpuset.
+ */
+static struct workqueue_struct *cpuset_wq;
+
 /*
  * Tracks how many cpusets are currently defined in system.
  * When there is only one cpuset (the root cpuset) we can
@@ -831,7 +839,7 @@ static DECLARE_WORK(rebuild_sched_domains_work, do_rebuild_sched_domains);
  */
 static void async_rebuild_sched_domains(void)
 {
-	schedule_work(&rebuild_sched_domains_work);
+	queue_work(cpuset_wq, &rebuild_sched_domains_work);
 }
 
 /*
@@ -2111,6 +2119,9 @@ void __init cpuset_init_smp(void)
 
 	hotcpu_notifier(cpuset_track_online_cpus, 0);
 	hotplug_memory_notifier(cpuset_track_online_nodes, 10);
+
+	cpuset_wq = create_singlethread_workqueue("cpuset");
+	BUG_ON(!cpuset_wq);
 }
 
 /**
-- 
cgit v1.2.3


From 31ad9081200c06ccc350625d41d1f8b2d1cef29f Mon Sep 17 00:00:00 2001
From: Rusty Russell <rusty@rustcorp.com.au>
Date: Fri, 16 Jan 2009 15:31:15 -0800
Subject: work_on_cpu: don't try to get_online_cpus() in work_on_cpu.

Impact: remove potential circular lock dependency with cpu hotplug lock

This has caused more problems than it solved, with a pile of cpu
hotplug locking issues.

Followup patches will get_online_cpus() in callers that need it, but
if they don't do it they're no worse than before when they were using
set_cpus_allowed without locking.

Signed-off-by: Rusty Russell <rusty@rustcorp.com.au>
Signed-off-by: Mike Travis <travis@sgi.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
---
 kernel/workqueue.c | 14 ++++----------
 1 file changed, 4 insertions(+), 10 deletions(-)

(limited to 'kernel')

diff --git a/kernel/workqueue.c b/kernel/workqueue.c
index 2f445833ae37..a35afdbc0161 100644
--- a/kernel/workqueue.c
+++ b/kernel/workqueue.c
@@ -991,8 +991,8 @@ static void do_work_for_cpu(struct work_struct *w)
  * @fn: the function to run
  * @arg: the function arg
  *
- * This will return -EINVAL in the cpu is not online, or the return value
- * of @fn otherwise.
+ * This will return the value @fn returns.
+ * It is up to the caller to ensure that the cpu doesn't go offline.
  */
 long work_on_cpu(unsigned int cpu, long (*fn)(void *), void *arg)
 {
@@ -1001,14 +1001,8 @@ long work_on_cpu(unsigned int cpu, long (*fn)(void *), void *arg)
 	INIT_WORK(&wfc.work, do_work_for_cpu);
 	wfc.fn = fn;
 	wfc.arg = arg;
-	get_online_cpus();
-	if (unlikely(!cpu_online(cpu)))
-		wfc.ret = -EINVAL;
-	else {
-		schedule_work_on(cpu, &wfc.work);
-		flush_work(&wfc.work);
-	}
-	put_online_cpus();
+	schedule_work_on(cpu, &wfc.work);
+	flush_work(&wfc.work);
 
 	return wfc.ret;
 }
-- 
cgit v1.2.3


From 8ccad40df8d314f786fdb06bdbedd4f43f3257cd Mon Sep 17 00:00:00 2001
From: Rusty Russell <rusty@rustcorp.com.au>
Date: Fri, 16 Jan 2009 15:31:15 -0800
Subject: work_on_cpu: Use our own workqueue.

Impact: remove potential clashes with generic kevent workqueue

Annoyingly, some places we want to use work_on_cpu are already in
workqueues.  As per Ingo's suggestion, we create a different workqueue
for work_on_cpu.

Signed-off-by: Rusty Russell <rusty@rustcorp.com.au>
Signed-off-by: Mike Travis <travis@sgi.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
---
 kernel/workqueue.c | 8 +++++++-
 1 file changed, 7 insertions(+), 1 deletion(-)

(limited to 'kernel')

diff --git a/kernel/workqueue.c b/kernel/workqueue.c
index a35afdbc0161..1f0c509b40d3 100644
--- a/kernel/workqueue.c
+++ b/kernel/workqueue.c
@@ -971,6 +971,8 @@ undo:
 }
 
 #ifdef CONFIG_SMP
+static struct workqueue_struct *work_on_cpu_wq __read_mostly;
+
 struct work_for_cpu {
 	struct work_struct work;
 	long (*fn)(void *);
@@ -1001,7 +1003,7 @@ long work_on_cpu(unsigned int cpu, long (*fn)(void *), void *arg)
 	INIT_WORK(&wfc.work, do_work_for_cpu);
 	wfc.fn = fn;
 	wfc.arg = arg;
-	schedule_work_on(cpu, &wfc.work);
+	queue_work_on(cpu, work_on_cpu_wq, &wfc.work);
 	flush_work(&wfc.work);
 
 	return wfc.ret;
@@ -1019,4 +1021,8 @@ void __init init_workqueues(void)
 	hotcpu_notifier(workqueue_cpu_callback, 0);
 	keventd_wq = create_workqueue("events");
 	BUG_ON(!keventd_wq);
+#ifdef CONFIG_SMP
+	work_on_cpu_wq = create_workqueue("work_on_cpu");
+	BUG_ON(!work_on_cpu_wq);
+#endif
 }
-- 
cgit v1.2.3


From 082605de5f82eb692cc90f7fda071cc01bb5ac34 Mon Sep 17 00:00:00 2001
From: Steven Rostedt <srostedt@redhat.com>
Date: Mon, 19 Jan 2009 14:32:51 -0500
Subject: ring-buffer: fix alignment problem

Impact: fix to allow some archs to use the ring buffer

Commits in the ring buffer are checked by pointer arithmetic.
If the calculation is incorrect, then the commits will never take
place and the buffer will simply fill up and report an error.

Each page in the ring buffer has a small header:

struct buffer_data_page {
	u64		time_stamp;
	local_t		commit;
	unsigned char	data[];
};

Unfortuntely, some of the calculations used sizeof(struct buffer_data_page)
to know the size of the header. But this is incorrect on some archs,
where sizeof(struct buffer_data_page) does not equal
offsetof(struct buffer_data_page, data), and on those archs, the commits
are never processed.

This patch replaces the sizeof with offsetof.

Signed-off-by: Steven Rostedt <srostedt@redhat.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
---
 kernel/trace/ring_buffer.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'kernel')

diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c
index 8b0daf0662ef..1d6526361d06 100644
--- a/kernel/trace/ring_buffer.c
+++ b/kernel/trace/ring_buffer.c
@@ -246,7 +246,7 @@ static inline int test_time_stamp(u64 delta)
 	return 0;
 }
 
-#define BUF_PAGE_SIZE (PAGE_SIZE - sizeof(struct buffer_data_page))
+#define BUF_PAGE_SIZE (PAGE_SIZE - offsetof(struct buffer_data_page, data))
 
 /*
  * head_page == tail_page && head == tail then buffer is empty.
-- 
cgit v1.2.3


From cdf57cab27aef72f13a19c86858c6cac9951dc24 Mon Sep 17 00:00:00 2001
From: Adrian McMenamin <adrian@mcmen.demon.co.uk>
Date: Wed, 21 Jan 2009 18:47:38 +0900
Subject: dma-coherent: per-device coherent area is in pages, not bytes.

Commit 58c6d3dfe436eb8cfb451981d8fdc9044eaf42da ("dma-coherent: catch
oversized requests to dma_alloc_from_coherent()") attempted to add a
sanity check to bail out on allocations larger than the coherent area.

Unfortunately when this was implemented, the fact the coherent area
is tracked in pages rather than bytes was overlooked, which subsequently
broke every single dma_alloc_from_coherent() user, forcing the allocation
silently through generic memory instead.

Signed-off-by: Adrian McMenamin <adrian@mcmen.demon.co.uk >
Signed-off-by: Paul Mundt <lethal@linux-sh.org>
---
 kernel/dma-coherent.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

(limited to 'kernel')

diff --git a/kernel/dma-coherent.c b/kernel/dma-coherent.c
index 038707404b76..38fa292c6aa9 100644
--- a/kernel/dma-coherent.c
+++ b/kernel/dma-coherent.c
@@ -118,8 +118,8 @@ int dma_alloc_from_coherent(struct device *dev, ssize_t size,
 	mem = dev->dma_mem;
 	if (!mem)
 		return 0;
-	if (unlikely(size > mem->size))
- 		return 0;
+	if (unlikely(size > (mem->size << PAGE_SHIFT)))
+		return 0;
 
 	pageno = bitmap_find_free_region(mem->bitmap, mem->size, order);
 	if (pageno >= 0) {
-- 
cgit v1.2.3


From 0609697eab9775564845d4c94f9e3780fb791ffd Mon Sep 17 00:00:00 2001
From: Paul Mundt <lethal@linux-sh.org>
Date: Wed, 21 Jan 2009 18:51:53 +0900
Subject: dma-coherent: Restore dma_alloc_from_coherent() large alloc fall back
 policy.

When doing large allocations (larger than the per-device coherent area)
the generic memory allocators are silently fallen back on regardless of
consideration for the per-device constraints.

In the DMA_MEMORY_EXCLUSIVE case falling back on generic memory is not
an option, as it tends not to be addressable by the DMA hardware in
question. This issue showed up with the 8139too breakage on the
Dreamcast, where non-addressable buffers were silently allocated due to
the size mismatch calculation -- while it should have simply errored out
upon being unable to satisfy the allocation with the given device
constraints.

This restores fall back behaviour to what it was before the oversized
request change caused multiple regressions.

Signed-off-by: Paul Mundt <lethal@linux-sh.org>
---
 kernel/dma-coherent.c | 45 +++++++++++++++++++++++----------------------
 1 file changed, 23 insertions(+), 22 deletions(-)

(limited to 'kernel')

diff --git a/kernel/dma-coherent.c b/kernel/dma-coherent.c
index 38fa292c6aa9..962a3b574f21 100644
--- a/kernel/dma-coherent.c
+++ b/kernel/dma-coherent.c
@@ -98,7 +98,7 @@ EXPORT_SYMBOL(dma_mark_declared_memory_occupied);
  * @size:	size of requested memory area
  * @dma_handle:	This will be filled with the correct dma handle
  * @ret:	This pointer will be filled with the virtual address
- * 		to allocated area.
+ *		to allocated area.
  *
  * This function should be only called from per-arch dma_alloc_coherent()
  * to support allocation from per-device coherent memory pools.
@@ -118,31 +118,32 @@ int dma_alloc_from_coherent(struct device *dev, ssize_t size,
 	mem = dev->dma_mem;
 	if (!mem)
 		return 0;
+
+	*ret = NULL;
+
 	if (unlikely(size > (mem->size << PAGE_SHIFT)))
-		return 0;
+		goto err;
 
 	pageno = bitmap_find_free_region(mem->bitmap, mem->size, order);
-	if (pageno >= 0) {
-		/*
-		 * Memory was found in the per-device arena.
-		 */
-		*dma_handle = mem->device_base + (pageno << PAGE_SHIFT);
-		*ret = mem->virt_base + (pageno << PAGE_SHIFT);
-		memset(*ret, 0, size);
-	} else if (mem->flags & DMA_MEMORY_EXCLUSIVE) {
-		/*
-		 * The per-device arena is exhausted and we are not
-		 * permitted to fall back to generic memory.
-		 */
-		*ret = NULL;
-	} else {
-		/*
-		 * The per-device arena is exhausted and we are
-		 * permitted to fall back to generic memory.
-		 */
-		 return 0;
-	}
+	if (unlikely(pageno < 0))
+		goto err;
+
+	/*
+	 * Memory was found in the per-device area.
+	 */
+	*dma_handle = mem->device_base + (pageno << PAGE_SHIFT);
+	*ret = mem->virt_base + (pageno << PAGE_SHIFT);
+	memset(*ret, 0, size);
+
 	return 1;
+
+err:
+	/*
+	 * In the case where the allocation can not be satisfied from the
+	 * per-device area, try to fall back to generic memory if the
+	 * constraints allow it.
+	 */
+	return mem->flags & DMA_MEMORY_EXCLUSIVE;
 }
 EXPORT_SYMBOL(dma_alloc_from_coherent);
 
-- 
cgit v1.2.3


From 00f57f545afa422db3003b0d0b30a30f8de7ecb2 Mon Sep 17 00:00:00 2001
From: Frederic Weisbecker <fweisbec@gmail.com>
Date: Wed, 14 Jan 2009 13:33:27 -0800
Subject: tracing/function-graph-tracer: fix a regression while suspend to disk

Impact: fix a crash while kernel image restore

When the function graph tracer is running and while suspend to disk, some racy
and dangerous things happen against this tracer.

The current task will save its registers including the stack pointer which
contains the return address hooked by the tracer. But the current task will
continue to enter other functions after that to save the memory, and then
it will store other return addresses, and finally loose the old depth which
matches the return address saved in the old stack (during the registers saving).

So on image restore, the code will return to wrong addresses.
And there are other things: on restore, the task will have it's "current"
pointer overwritten during registers restoring....switching from one task to
another... That would be insane to try to trace function graphs at these
stages.

This patch makes the function graph tracer listening on power events, making
it's tracing disabled for the current task (the one that performs the
hibernation work) while suspend/resume to disk, making the tracing safe
during hibernation.

Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com>
Signed-off-by: Steven Rostedt <srostedt@redhat.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
---
 kernel/trace/ftrace.c | 27 +++++++++++++++++++++++++++
 1 file changed, 27 insertions(+)

(limited to 'kernel')

diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c
index 2f32969c09df..7dcf6e9f2b04 100644
--- a/kernel/trace/ftrace.c
+++ b/kernel/trace/ftrace.c
@@ -17,6 +17,7 @@
 #include <linux/clocksource.h>
 #include <linux/kallsyms.h>
 #include <linux/seq_file.h>
+#include <linux/suspend.h>
 #include <linux/debugfs.h>
 #include <linux/hardirq.h>
 #include <linux/kthread.h>
@@ -1965,6 +1966,7 @@ ftrace_enable_sysctl(struct ctl_table *table, int write,
 #ifdef CONFIG_FUNCTION_GRAPH_TRACER
 
 static atomic_t ftrace_graph_active;
+static struct notifier_block ftrace_suspend_notifier;
 
 int ftrace_graph_entry_stub(struct ftrace_graph_ent *trace)
 {
@@ -2043,6 +2045,27 @@ static int start_graph_tracing(void)
 	return ret;
 }
 
+/*
+ * Hibernation protection.
+ * The state of the current task is too much unstable during
+ * suspend/restore to disk. We want to protect against that.
+ */
+static int
+ftrace_suspend_notifier_call(struct notifier_block *bl, unsigned long state,
+							void *unused)
+{
+	switch (state) {
+	case PM_HIBERNATION_PREPARE:
+		pause_graph_tracing();
+		break;
+
+	case PM_POST_HIBERNATION:
+		unpause_graph_tracing();
+		break;
+	}
+	return NOTIFY_DONE;
+}
+
 int register_ftrace_graph(trace_func_graph_ret_t retfunc,
 			trace_func_graph_ent_t entryfunc)
 {
@@ -2050,6 +2073,9 @@ int register_ftrace_graph(trace_func_graph_ret_t retfunc,
 
 	mutex_lock(&ftrace_sysctl_lock);
 
+	ftrace_suspend_notifier.notifier_call = ftrace_suspend_notifier_call;
+	register_pm_notifier(&ftrace_suspend_notifier);
+
 	atomic_inc(&ftrace_graph_active);
 	ret = start_graph_tracing();
 	if (ret) {
@@ -2075,6 +2101,7 @@ void unregister_ftrace_graph(void)
 	ftrace_graph_return = (trace_func_graph_ret_t)ftrace_stub;
 	ftrace_graph_entry = ftrace_graph_entry_stub;
 	ftrace_shutdown(FTRACE_STOP_FUNC_RET);
+	unregister_pm_notifier(&ftrace_suspend_notifier);
 
 	mutex_unlock(&ftrace_sysctl_lock);
 }
-- 
cgit v1.2.3


From 551b4048b3d4acf15aff9fe4aed89b892c135b02 Mon Sep 17 00:00:00 2001
From: Lai Jiangshan <laijs@cn.fujitsu.com>
Date: Mon, 12 Jan 2009 11:06:18 +0800
Subject: ring_buffer: reset write when reserve buffer fail

Impact: reset struct buffer_page.write when interrupt storm

if struct buffer_page.write is not reset, any succedent committing
will corrupted ring_buffer:

static inline void
rb_set_commit_to_write(struct ring_buffer_per_cpu *cpu_buffer)
{
	......
		cpu_buffer->commit_page->commit =
			cpu_buffer->commit_page->write;
	......
}

when "if (RB_WARN_ON(cpu_buffer, next_page == reader_page))", ring_buffer
is disabled, but some reserved buffers may haven't been committed.
we need reset struct buffer_page.write.

when "if (unlikely(next_page == cpu_buffer->commit_page))", ring_buffer
is still available, we should not corrupt it.

Signed-off-by: Lai Jiangshan <laijs@cn.fujitsu.com>
Signed-off-by: Steven Rostedt <srostedt@redhat.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
---
 kernel/trace/ring_buffer.c | 10 +++++-----
 1 file changed, 5 insertions(+), 5 deletions(-)

(limited to 'kernel')

diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c
index 1d6526361d06..9c1e73da4e30 100644
--- a/kernel/trace/ring_buffer.c
+++ b/kernel/trace/ring_buffer.c
@@ -1025,12 +1025,8 @@ __rb_reserve_next(struct ring_buffer_per_cpu *cpu_buffer,
 		}
 
 		if (next_page == head_page) {
-			if (!(buffer->flags & RB_FL_OVERWRITE)) {
-				/* reset write */
-				if (tail <= BUF_PAGE_SIZE)
-					local_set(&tail_page->write, tail);
+			if (!(buffer->flags & RB_FL_OVERWRITE))
 				goto out_unlock;
-			}
 
 			/* tail_page has not moved yet? */
 			if (tail_page == cpu_buffer->tail_page) {
@@ -1105,6 +1101,10 @@ __rb_reserve_next(struct ring_buffer_per_cpu *cpu_buffer,
 	return event;
 
  out_unlock:
+	/* reset write */
+	if (tail <= BUF_PAGE_SIZE)
+		local_set(&tail_page->write, tail);
+
 	__raw_spin_unlock(&cpu_buffer->lock);
 	local_irq_restore(flags);
 	return NULL;
-- 
cgit v1.2.3


From faf6861ebd776871e77b761c43ec045cd20b5716 Mon Sep 17 00:00:00 2001
From: Steven Rostedt <srostedt@redhat.com>
Date: Wed, 14 Jan 2009 12:24:42 -0500
Subject: trace: print ftrace_dump at KERN_EMERG log level

Impact: fix to print out ftrace_dump when expected

I was debugging a hard race condition to only find out that
after I hit the race, my log level was not at level to show
KERN_INFO. The time it took to trigger the race was wasted because
I did not capture the trace.

Since ftrace_dump is only called from kernel oops (and only when
it is set in the kernel command line to do so), or when a
developer adds it to their own local tree, the log level of
the print should be at KERN_EMERG to make sure the print appears.

ftrace_dump is not called by a normal user setup, and will not
add extra unwanted print out to the console. There is no reason
it should be at KERN_INFO.

Signed-off-by: Steven Rostedt <srostedt@redhat.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
---
 kernel/trace/trace.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'kernel')

diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index c580233add95..1a1c5a6ab24e 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -3736,7 +3736,7 @@ static struct notifier_block trace_die_notifier = {
  * it if we decide to change what log level the ftrace dump
  * should be at.
  */
-#define KERN_TRACE		KERN_INFO
+#define KERN_TRACE		KERN_EMERG
 
 static void
 trace_printk_seq(struct trace_seq *s)
-- 
cgit v1.2.3


From a442e5e0a2011af5b2d1f118fee0a8f9079f1d88 Mon Sep 17 00:00:00 2001
From: Steven Rostedt <srostedt@redhat.com>
Date: Wed, 14 Jan 2009 14:50:19 -0500
Subject: trace: stop all recording to ring buffer on ftrace_dump

Impact: limit ftrace dump output

Currently ftrace_dump only calls ftrace_kill that is a fast way
to prevent the function tracer functions from being called (just sets
a flag and clears the function to call, nothing else). It is better
to also turn off any recording to the ring buffers as well.

Signed-off-by: Steven Rostedt <srostedt@redhat.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
---
 kernel/trace/trace.c | 1 +
 1 file changed, 1 insertion(+)

(limited to 'kernel')

diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index 1a1c5a6ab24e..4d89e84f0f4b 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -3770,6 +3770,7 @@ void ftrace_dump(void)
 	dump_ran = 1;
 
 	/* No turning back! */
+	tracing_off();
 	ftrace_kill();
 
 	for_each_tracing_cpu(cpu) {
-- 
cgit v1.2.3


From 1092307d582a7566d23779c304cf86f3075ac5f0 Mon Sep 17 00:00:00 2001
From: Steven Rostedt <srostedt@redhat.com>
Date: Thu, 15 Jan 2009 23:40:11 -0500
Subject: trace: set max latency variable to zero on default

Impact: trace max latencies on start of latency tracing

This patch sets the max latency to zero whenever one of the
irq variant tracers or the wakeup tracer is set to current tracer.

Most developers expect to see output when starting up a latency
tracer. But since the max_latency is already set to max, and
it takes a latency greater than max_latency to be recorded, there
is no trace. This is not the expected behavior and has even confused
myself.

Signed-off-by: Steven Rostedt <srostedt@redhat.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
---
 kernel/trace/trace.c              | 2 +-
 kernel/trace/trace_irqsoff.c      | 1 +
 kernel/trace/trace_sched_wakeup.c | 1 +
 3 files changed, 3 insertions(+), 1 deletion(-)

(limited to 'kernel')

diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index 4d89e84f0f4b..17bb88d86ac2 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -40,7 +40,7 @@
 
 #define TRACE_BUFFER_FLAGS	(RB_FL_OVERWRITE)
 
-unsigned long __read_mostly	tracing_max_latency = (cycle_t)ULONG_MAX;
+unsigned long __read_mostly	tracing_max_latency;
 unsigned long __read_mostly	tracing_thresh;
 
 /*
diff --git a/kernel/trace/trace_irqsoff.c b/kernel/trace/trace_irqsoff.c
index 7c2e326bbc8b..62a78d943534 100644
--- a/kernel/trace/trace_irqsoff.c
+++ b/kernel/trace/trace_irqsoff.c
@@ -380,6 +380,7 @@ static void stop_irqsoff_tracer(struct trace_array *tr)
 
 static void __irqsoff_tracer_init(struct trace_array *tr)
 {
+	tracing_max_latency = 0;
 	irqsoff_trace = tr;
 	/* make sure that the tracer is visible */
 	smp_wmb();
diff --git a/kernel/trace/trace_sched_wakeup.c b/kernel/trace/trace_sched_wakeup.c
index 43586b689e31..42ae1e77b6b3 100644
--- a/kernel/trace/trace_sched_wakeup.c
+++ b/kernel/trace/trace_sched_wakeup.c
@@ -333,6 +333,7 @@ static void stop_wakeup_tracer(struct trace_array *tr)
 
 static int wakeup_tracer_init(struct trace_array *tr)
 {
+	tracing_max_latency = 0;
 	wakeup_trace = tr;
 	start_wakeup_tracer(tr);
 	return 0;
-- 
cgit v1.2.3


From 91a8d07d82cac3aae3ef2ea1aaba5c9c4a934e91 Mon Sep 17 00:00:00 2001
From: Steven Rostedt <srostedt@redhat.com>
Date: Wed, 21 Jan 2009 18:45:57 -0500
Subject: ring-buffer: reset timestamps when ring buffer is reset

Impact: fix bad times of recent resets

The ring buffer needs to reset its timestamps when reseting of the
buffer, otherwise the timestamps are stale and might be used to
calculate times in the buffer causing funny timestamps to appear.

Signed-off-by: Steven Rostedt <srostedt@redhat.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
---
 kernel/trace/ring_buffer.c | 3 +++
 1 file changed, 3 insertions(+)

(limited to 'kernel')

diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c
index 9c1e73da4e30..bd38c5cfd8ad 100644
--- a/kernel/trace/ring_buffer.c
+++ b/kernel/trace/ring_buffer.c
@@ -2174,6 +2174,9 @@ rb_reset_cpu(struct ring_buffer_per_cpu *cpu_buffer)
 
 	cpu_buffer->overrun = 0;
 	cpu_buffer->entries = 0;
+
+	cpu_buffer->write_stamp = 0;
+	cpu_buffer->read_stamp = 0;
 }
 
 /**
-- 
cgit v1.2.3


From 3a9f84d354ce1e19956083c8e691727dea33bd5a Mon Sep 17 00:00:00 2001
From: Ed Swierk <eswierk@aristanetworks.com>
Date: Mon, 26 Jan 2009 15:33:31 -0800
Subject: signals, debug: fix BUG: using smp_processor_id() in preemptible code
 in print_fatal_signal()

With print-fatal-signals=1 on a kernel with CONFIG_PREEMPT=y, sending an
unexpected signal to a process causes a BUG: using smp_processor_id() in
preemptible code.

get_signal_to_deliver() releases the siglock before calling
print_fatal_signal(), which calls show_regs(), which calls
smp_processor_id(), which is not supposed to be called from a
preemptible thread.

Make sure show_regs() runs with preemption disabled.

Signed-off-by: Ed Swierk <eswierk@aristanetworks.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
---
 kernel/signal.c | 2 ++
 1 file changed, 2 insertions(+)

(limited to 'kernel')

diff --git a/kernel/signal.c b/kernel/signal.c
index e73759783dc8..b6b36768b758 100644
--- a/kernel/signal.c
+++ b/kernel/signal.c
@@ -909,7 +909,9 @@ static void print_fatal_signal(struct pt_regs *regs, int signr)
 	}
 #endif
 	printk("\n");
+	preempt_disable();
 	show_regs(regs);
+	preempt_enable();
 }
 
 static int __init setup_print_fatal_signals(char *str)
-- 
cgit v1.2.3


From abfe2d7b915c872f3a1fd203267cedebf90daa45 Mon Sep 17 00:00:00 2001
From: "Rafael J. Wysocki" <rjw@sisk.pl>
Date: Mon, 19 Jan 2009 20:54:54 +0100
Subject: Hibernation: Introduce system_entering_hibernation

Introduce boolean function system_entering_hibernation() returning
'true' during the last phase of hibernation, in which devices are
being put into low power states and the sleep state (for example,
ACPI S4) is finally entered.

Some device drivers need such a function to check if the system is
in the final phase of hibernation.  In particular, some SATA drivers
are going to use it for blacklisting systems in which the disks
should not be spun down during the last phase of hibernation (the
BIOS will do that anyway).

Signed-off-by: Rafael J. Wysocki <rjw@sisk.pl>
Signed-off-by: Jeff Garzik <jgarzik@redhat.com>
---
 include/linux/suspend.h |  2 ++
 kernel/power/disk.c     | 10 ++++++++++
 2 files changed, 12 insertions(+)

(limited to 'kernel')

diff --git a/include/linux/suspend.h b/include/linux/suspend.h
index 2b409c44db83..c7d9bb1832ba 100644
--- a/include/linux/suspend.h
+++ b/include/linux/suspend.h
@@ -237,6 +237,7 @@ extern int hibernate_nvs_alloc(void);
 extern void hibernate_nvs_free(void);
 extern void hibernate_nvs_save(void);
 extern void hibernate_nvs_restore(void);
+extern bool system_entering_hibernation(void);
 #else /* CONFIG_HIBERNATION */
 static inline int swsusp_page_is_forbidden(struct page *p) { return 0; }
 static inline void swsusp_set_page_free(struct page *p) {}
@@ -252,6 +253,7 @@ static inline int hibernate_nvs_alloc(void) { return 0; }
 static inline void hibernate_nvs_free(void) {}
 static inline void hibernate_nvs_save(void) {}
 static inline void hibernate_nvs_restore(void) {}
+static inline bool system_entering_hibernation(void) { return false; }
 #endif /* CONFIG_HIBERNATION */
 
 #ifdef CONFIG_PM_SLEEP
diff --git a/kernel/power/disk.c b/kernel/power/disk.c
index 45e8541ab7e3..432ee575c9ee 100644
--- a/kernel/power/disk.c
+++ b/kernel/power/disk.c
@@ -71,6 +71,14 @@ void hibernation_set_ops(struct platform_hibernation_ops *ops)
 	mutex_unlock(&pm_mutex);
 }
 
+static bool entering_platform_hibernation;
+
+bool system_entering_hibernation(void)
+{
+	return entering_platform_hibernation;
+}
+EXPORT_SYMBOL(system_entering_hibernation);
+
 #ifdef CONFIG_PM_DEBUG
 static void hibernation_debug_sleep(void)
 {
@@ -411,6 +419,7 @@ int hibernation_platform_enter(void)
 	if (error)
 		goto Close;
 
+	entering_platform_hibernation = true;
 	suspend_console();
 	error = device_suspend(PMSG_HIBERNATE);
 	if (error) {
@@ -445,6 +454,7 @@ int hibernation_platform_enter(void)
  Finish:
 	hibernation_ops->finish();
  Resume_devices:
+	entering_platform_hibernation = false;
 	device_resume(PMSG_RESTORE);
 	resume_console();
  Close:
-- 
cgit v1.2.3


From 1267a8df209c7453d65acbdd56e3588954bf890b Mon Sep 17 00:00:00 2001
From: David Daney <ddaney@caviumnetworks.com>
Date: Tue, 27 Jan 2009 09:53:21 -0800
Subject: Make irq_*_affinity depend on CONFIG_GENERIC_HARDIRQS too.

In interrupt.h these functions are declared only if
CONFIG_GENERIC_HARDIRQS is set.  We should define them under identical
conditions.

Signed-off-by: David Daney <ddaney@caviumnetworks.com>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 kernel/irq/manage.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'kernel')

diff --git a/kernel/irq/manage.c b/kernel/irq/manage.c
index cd0cd8dcb345..618a64f1915a 100644
--- a/kernel/irq/manage.c
+++ b/kernel/irq/manage.c
@@ -15,7 +15,7 @@
 
 #include "internals.h"
 
-#ifdef CONFIG_SMP
+#if defined(CONFIG_SMP) && defined(CONFIG_GENERIC_HARDIRQS)
 cpumask_var_t irq_default_affinity;
 
 static int init_irq_default_affinity(void)
-- 
cgit v1.2.3


From 97179fd46da7ddedd18e95388130ed3e06c5a0c7 Mon Sep 17 00:00:00 2001
From: David Daney <ddaney@caviumnetworks.com>
Date: Tue, 27 Jan 2009 09:53:22 -0800
Subject: cpumask fallout: Initialize irq_default_affinity earlier

Move the initialization of irq_default_affinity to early_irq_init as
core_initcall is too late.

irq_default_affinity can be used in init_IRQ and potentially timer and
SMP init as well.  All of these happen before core_initcall.  Moving
the initialization to early_irq_init ensures that it is initialized
before it is used.

Signed-off-by: David Daney <ddaney@caviumnetworks.com>
Acked-by: Mike Travis <travis@sgi.com>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 kernel/irq/handle.c | 16 ++++++++++++++++
 kernel/irq/manage.c |  8 --------
 2 files changed, 16 insertions(+), 8 deletions(-)

(limited to 'kernel')

diff --git a/kernel/irq/handle.c b/kernel/irq/handle.c
index c20db0be9173..3aba8d12f328 100644
--- a/kernel/irq/handle.c
+++ b/kernel/irq/handle.c
@@ -39,6 +39,18 @@ void handle_bad_irq(unsigned int irq, struct irq_desc *desc)
 	ack_bad_irq(irq);
 }
 
+#if defined(CONFIG_SMP) && defined(CONFIG_GENERIC_HARDIRQS)
+static void __init init_irq_default_affinity(void)
+{
+	alloc_bootmem_cpumask_var(&irq_default_affinity);
+	cpumask_setall(irq_default_affinity);
+}
+#else
+static void __init init_irq_default_affinity(void)
+{
+}
+#endif
+
 /*
  * Linux has a controller-independent interrupt architecture.
  * Every controller has a 'controller-template', that is used
@@ -134,6 +146,8 @@ int __init early_irq_init(void)
 	int legacy_count;
 	int i;
 
+	init_irq_default_affinity();
+
 	desc = irq_desc_legacy;
 	legacy_count = ARRAY_SIZE(irq_desc_legacy);
 
@@ -219,6 +233,8 @@ int __init early_irq_init(void)
 	int count;
 	int i;
 
+	init_irq_default_affinity();
+
 	desc = irq_desc;
 	count = ARRAY_SIZE(irq_desc);
 
diff --git a/kernel/irq/manage.c b/kernel/irq/manage.c
index 618a64f1915a..291f03664552 100644
--- a/kernel/irq/manage.c
+++ b/kernel/irq/manage.c
@@ -18,14 +18,6 @@
 #if defined(CONFIG_SMP) && defined(CONFIG_GENERIC_HARDIRQS)
 cpumask_var_t irq_default_affinity;
 
-static int init_irq_default_affinity(void)
-{
-	alloc_cpumask_var(&irq_default_affinity, GFP_KERNEL);
-	cpumask_setall(irq_default_affinity);
-	return 0;
-}
-core_initcall(init_irq_default_affinity);
-
 /**
  *	synchronize_irq - wait for pending IRQ handlers (on other CPUs)
  *	@irq: interrupt number to wait for
-- 
cgit v1.2.3


From baef99a08a2e23d9386b47e53fa5f0d44fc98f66 Mon Sep 17 00:00:00 2001
From: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
Date: Thu, 29 Jan 2009 14:25:10 -0800
Subject: cgroups: use hierarchy mutex in creation failure path

Now, cgrp->sibling is handled under hierarchy mutex.
error route should do so, too.

Signed-off-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
Cc: Li Zefan <lizf@cn.fujitsu.com>
Acked-by Paul Menage <menage@google.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 kernel/cgroup.c | 2 ++
 1 file changed, 2 insertions(+)

(limited to 'kernel')

diff --git a/kernel/cgroup.c b/kernel/cgroup.c
index c29831076e7a..2ae7cb47dbfa 100644
--- a/kernel/cgroup.c
+++ b/kernel/cgroup.c
@@ -2434,7 +2434,9 @@ static long cgroup_create(struct cgroup *parent, struct dentry *dentry,
 
  err_remove:
 
+	cgroup_lock_hierarchy(root);
 	list_del(&cgrp->sibling);
+	cgroup_unlock_hierarchy(root);
 	root->number_of_cgroups--;
 
  err_destroy:
-- 
cgit v1.2.3


From 1404f06565ee89e0ce04d4a5859c00b0e3a0dc8d Mon Sep 17 00:00:00 2001
From: Li Zefan <lizf@cn.fujitsu.com>
Date: Thu, 29 Jan 2009 14:25:21 -0800
Subject: cgroups: fix lock inconsistency in cgroup_clone()

I fixed a bug in cgroup_clone() in Linus' tree in commit 7b574b7
("cgroups: fix a race between cgroup_clone and umount") without noticing
there was a cleanup patch in -mm tree that should be rebased (now commit
104cbd5, "cgroups: use task_lock() for access tsk->cgroups safe in
cgroup_clone()"), thus resulted in lock inconsistency.

Signed-off-by: Li Zefan <lizf@cn.fujitsu.com>
Acked-by: Paul Menage <menage@google.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 kernel/cgroup.c | 13 +++++++------
 1 file changed, 7 insertions(+), 6 deletions(-)

(limited to 'kernel')

diff --git a/kernel/cgroup.c b/kernel/cgroup.c
index 2ae7cb47dbfa..0066092de19a 100644
--- a/kernel/cgroup.c
+++ b/kernel/cgroup.c
@@ -2993,20 +2993,21 @@ int cgroup_clone(struct task_struct *tsk, struct cgroup_subsys *subsys,
 		mutex_unlock(&cgroup_mutex);
 		return 0;
 	}
-	task_lock(tsk);
-	cg = tsk->cgroups;
-	parent = task_cgroup(tsk, subsys->subsys_id);
 
 	/* Pin the hierarchy */
-	if (!atomic_inc_not_zero(&parent->root->sb->s_active)) {
+	if (!atomic_inc_not_zero(&root->sb->s_active)) {
 		/* We race with the final deactivate_super() */
 		mutex_unlock(&cgroup_mutex);
 		return 0;
 	}
 
 	/* Keep the cgroup alive */
+	task_lock(tsk);
+	parent = task_cgroup(tsk, subsys->subsys_id);
+	cg = tsk->cgroups;
 	get_css_set(cg);
 	task_unlock(tsk);
+
 	mutex_unlock(&cgroup_mutex);
 
 	/* Now do the VFS work to create a cgroup */
@@ -3045,7 +3046,7 @@ int cgroup_clone(struct task_struct *tsk, struct cgroup_subsys *subsys,
 		mutex_unlock(&inode->i_mutex);
 		put_css_set(cg);
 
-		deactivate_super(parent->root->sb);
+		deactivate_super(root->sb);
 		/* The cgroup is still accessible in the VFS, but
 		 * we're not going to try to rmdir() it at this
 		 * point. */
@@ -3071,7 +3072,7 @@ int cgroup_clone(struct task_struct *tsk, struct cgroup_subsys *subsys,
 	mutex_lock(&cgroup_mutex);
 	put_css_set(cg);
 	mutex_unlock(&cgroup_mutex);
-	deactivate_super(parent->root->sb);
+	deactivate_super(root->sb);
 	return ret;
 }
 
-- 
cgit v1.2.3


From 804b3c28a4e4fa1c224571bf76edb534b9c4b1ed Mon Sep 17 00:00:00 2001
From: Paul Menage <menage@google.com>
Date: Thu, 29 Jan 2009 14:25:21 -0800
Subject: cgroups: add cpu_relax() calls in css_tryget() and
 cgroup_clear_css_refs()

css_tryget() and cgroup_clear_css_refs() contain polling loops; these
loops should have cpu_relax calls in them to reduce cross-cache traffic.

Signed-off-by: Paul Menage <menage@google.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/cgroup.h | 1 +
 kernel/cgroup.c        | 7 +++++--
 2 files changed, 6 insertions(+), 2 deletions(-)

(limited to 'kernel')

diff --git a/include/linux/cgroup.h b/include/linux/cgroup.h
index e267e62827bb..e4e8e117d27d 100644
--- a/include/linux/cgroup.h
+++ b/include/linux/cgroup.h
@@ -99,6 +99,7 @@ static inline bool css_tryget(struct cgroup_subsys_state *css)
 	while (!atomic_inc_not_zero(&css->refcnt)) {
 		if (test_bit(CSS_REMOVED, &css->flags))
 			return false;
+		cpu_relax();
 	}
 	return true;
 }
diff --git a/kernel/cgroup.c b/kernel/cgroup.c
index 0066092de19a..492215d67fa5 100644
--- a/kernel/cgroup.c
+++ b/kernel/cgroup.c
@@ -2509,7 +2509,7 @@ static int cgroup_clear_css_refs(struct cgroup *cgrp)
 	for_each_subsys(cgrp->root, ss) {
 		struct cgroup_subsys_state *css = cgrp->subsys[ss->subsys_id];
 		int refcnt;
-		do {
+		while (1) {
 			/* We can only remove a CSS with a refcnt==1 */
 			refcnt = atomic_read(&css->refcnt);
 			if (refcnt > 1) {
@@ -2523,7 +2523,10 @@ static int cgroup_clear_css_refs(struct cgroup *cgrp)
 			 * css_tryget() to spin until we set the
 			 * CSS_REMOVED bits or abort
 			 */
-		} while (atomic_cmpxchg(&css->refcnt, refcnt, 0) != refcnt);
+			if (atomic_cmpxchg(&css->refcnt, refcnt, 0) == refcnt)
+				break;
+			cpu_relax();
+		}
 	}
  done:
 	for_each_subsys(cgrp->root, ss) {
-- 
cgit v1.2.3


From 839ec5452ebfd5905b9c69b20ceb640903a8ea1a Mon Sep 17 00:00:00 2001
From: Paul Menage <menage@google.com>
Date: Thu, 29 Jan 2009 14:25:22 -0800
Subject: cgroup: fix root_count when mount fails due to busy subsystem

root_count was being incremented in cgroup_get_sb() after all error
checking was complete, but decremented in cgroup_kill_sb(), which can be
called on a superblock that we gave up on due to an error.  This patch
changes cgroup_kill_sb() to only decrement root_count if the root was
previously linked into the list of roots.

Signed-off-by: Paul Menage <menage@google.com>
Tested-by: Serge Hallyn <serue@us.ibm.com>
Cc: Ingo Molnar <mingo@elte.hu>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 kernel/cgroup.c | 6 ++++--
 1 file changed, 4 insertions(+), 2 deletions(-)

(limited to 'kernel')

diff --git a/kernel/cgroup.c b/kernel/cgroup.c
index 492215d67fa5..5a54ff42874e 100644
--- a/kernel/cgroup.c
+++ b/kernel/cgroup.c
@@ -1115,8 +1115,10 @@ static void cgroup_kill_sb(struct super_block *sb) {
 	}
 	write_unlock(&css_set_lock);
 
-	list_del(&root->root_list);
-	root_count--;
+	if (!list_empty(&root->root_list)) {
+		list_del(&root->root_list);
+		root_count--;
+	}
 
 	mutex_unlock(&cgroup_mutex);
 
-- 
cgit v1.2.3


From d7240b988017521ebf89edfadd42c0942f166850 Mon Sep 17 00:00:00 2001
From: Steven Rostedt <rostedt@goodmis.org>
Date: Thu, 29 Jan 2009 10:08:01 -0500
Subject: generic-ipi: use per cpu data for single cpu ipi calls

The smp_call_function can be passed a wait parameter telling it to
wait for all the functions running on other CPUs to complete before
returning, or to return without waiting. Unfortunately, this is
currently just a suggestion and not manditory. That is, the
smp_call_function can decide not to return and wait instead.

The reason for this is because it uses kmalloc to allocate storage
to send to the called CPU and that CPU will free it when it is done.
But if we fail to allocate the storage, the stack is used instead.
This means we must wait for the called CPU to finish before
continuing.

Unfortunatly, some callers do no abide by this hint and act as if
the non-wait option is mandatory. The MTRR code for instance will
deadlock if the smp_call_function is set to wait. This is because
the smp_call_function will wait for the other CPUs to finish their
called functions, but those functions are waiting on the caller to
continue.

This patch changes the generic smp_call_function code to use per cpu
variables if the allocation of the data fails for a single CPU call. The
smp_call_function_many will fall back to the smp_call_function_single
if it fails its alloc. The smp_call_function_single is modified
to not force the wait state.

Since we now are using a single data per cpu we must synchronize the
callers to prevent a second caller modifying the data before the
first called IPI functions complete. To do so, I added a flag to
the call_single_data called CSD_FLAG_LOCK. When the single CPU is
called (which can be called when a many call fails an alloc), we
set the LOCK bit on this per cpu data. When the caller finishes
it clears the LOCK bit.

The caller must wait till the LOCK bit is cleared before setting
it. When it is cleared, there is no IPI function using it.

Signed-off-by: Steven Rostedt <srostedt@redhat.com>
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Acked-by: Jens Axboe <jens.axboe@oracle.com>
Acked-by: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
---
 kernel/smp.c | 36 +++++++++++++++++++++++++++++++++---
 1 file changed, 33 insertions(+), 3 deletions(-)

(limited to 'kernel')

diff --git a/kernel/smp.c b/kernel/smp.c
index 5cfa0e5e3e88..bbedbb7efe32 100644
--- a/kernel/smp.c
+++ b/kernel/smp.c
@@ -18,6 +18,7 @@ __cacheline_aligned_in_smp DEFINE_SPINLOCK(call_function_lock);
 enum {
 	CSD_FLAG_WAIT		= 0x01,
 	CSD_FLAG_ALLOC		= 0x02,
+	CSD_FLAG_LOCK		= 0x04,
 };
 
 struct call_function_data {
@@ -186,6 +187,9 @@ void generic_smp_call_function_single_interrupt(void)
 			if (data_flags & CSD_FLAG_WAIT) {
 				smp_wmb();
 				data->flags &= ~CSD_FLAG_WAIT;
+			} else if (data_flags & CSD_FLAG_LOCK) {
+				smp_wmb();
+				data->flags &= ~CSD_FLAG_LOCK;
 			} else if (data_flags & CSD_FLAG_ALLOC)
 				kfree(data);
 		}
@@ -196,6 +200,8 @@ void generic_smp_call_function_single_interrupt(void)
 	}
 }
 
+static DEFINE_PER_CPU(struct call_single_data, csd_data);
+
 /*
  * smp_call_function_single - Run a function on a specific CPU
  * @func: The function to run. This must be fast and non-blocking.
@@ -224,14 +230,38 @@ int smp_call_function_single(int cpu, void (*func) (void *info), void *info,
 		func(info);
 		local_irq_restore(flags);
 	} else if ((unsigned)cpu < nr_cpu_ids && cpu_online(cpu)) {
-		struct call_single_data *data = NULL;
+		struct call_single_data *data;
 
 		if (!wait) {
+			/*
+			 * We are calling a function on a single CPU
+			 * and we are not going to wait for it to finish.
+			 * We first try to allocate the data, but if we
+			 * fail, we fall back to use a per cpu data to pass
+			 * the information to that CPU. Since all callers
+			 * of this code will use the same data, we must
+			 * synchronize the callers to prevent a new caller
+			 * from corrupting the data before the callee
+			 * can access it.
+			 *
+			 * The CSD_FLAG_LOCK is used to let us know when
+			 * the IPI handler is done with the data.
+			 * The first caller will set it, and the callee
+			 * will clear it. The next caller must wait for
+			 * it to clear before we set it again. This
+			 * will make sure the callee is done with the
+			 * data before a new caller will use it.
+			 */
 			data = kmalloc(sizeof(*data), GFP_ATOMIC);
 			if (data)
 				data->flags = CSD_FLAG_ALLOC;
-		}
-		if (!data) {
+			else {
+				data = &per_cpu(csd_data, me);
+				while (data->flags & CSD_FLAG_LOCK)
+					cpu_relax();
+				data->flags = CSD_FLAG_LOCK;
+			}
+		} else {
 			data = &d;
 			data->flags = CSD_FLAG_WAIT;
 		}
-- 
cgit v1.2.3


From 7f22391cbe82a80a9f891d8bd10fc28ff248d1e2 Mon Sep 17 00:00:00 2001
From: Frederic Weisbecker <fweisbec@gmail.com>
Date: Mon, 22 Dec 2008 02:24:48 +0100
Subject: hrtimers: increase clock min delta threshold while interrupt hanging

Impact: avoid timer IRQ hanging slow systems

While using the function graph tracer on a virtualized system, the
hrtimer_interrupt can hang the system on an infinite loop.

This can be caused in several situations:

 - the hardware is very slow and HZ is set too high

 - something intrusive is slowing the system down (tracing under emulation)

... and the next clock events to program are always before the current time.

This patch implements a reasonable compromise: if such a situation is
detected, we share the CPUs time in 1/4 to process the hrtimer interrupts.
This is enough to let the system running without serious starvation.

It has been successfully tested under VirtualBox with 1000 HZ and 100 HZ
with function graph tracer launched. On both cases, the clock events were
increased until about 25 ms periodic ticks, which means 40 HZ.

So we change a hard to debug hang into a warning message and a system that
still manages to limp along.

Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
---
 kernel/hrtimer.c | 30 +++++++++++++++++++++++++++++-
 1 file changed, 29 insertions(+), 1 deletion(-)

(limited to 'kernel')

diff --git a/kernel/hrtimer.c b/kernel/hrtimer.c
index f33afb0407bc..8fea312ca36c 100644
--- a/kernel/hrtimer.c
+++ b/kernel/hrtimer.c
@@ -1158,6 +1158,29 @@ static void __run_hrtimer(struct hrtimer *timer)
 
 #ifdef CONFIG_HIGH_RES_TIMERS
 
+static int force_clock_reprogram;
+
+/*
+ * After 5 iteration's attempts, we consider that hrtimer_interrupt()
+ * is hanging, which could happen with something that slows the interrupt
+ * such as the tracing. Then we force the clock reprogramming for each future
+ * hrtimer interrupts to avoid infinite loops and use the min_delta_ns
+ * threshold that we will overwrite.
+ * The next tick event will be scheduled to 3 times we currently spend on
+ * hrtimer_interrupt(). This gives a good compromise, the cpus will spend
+ * 1/4 of their time to process the hrtimer interrupts. This is enough to
+ * let it running without serious starvation.
+ */
+
+static inline void
+hrtimer_interrupt_hanging(struct clock_event_device *dev,
+			ktime_t try_time)
+{
+	force_clock_reprogram = 1;
+	dev->min_delta_ns = (unsigned long)try_time.tv64 * 3;
+	printk(KERN_WARNING "hrtimer: interrupt too slow, "
+		"forcing clock min delta to %lu ns\n", dev->min_delta_ns);
+}
 /*
  * High resolution timer interrupt
  * Called with interrupts disabled
@@ -1167,6 +1190,7 @@ void hrtimer_interrupt(struct clock_event_device *dev)
 	struct hrtimer_cpu_base *cpu_base = &__get_cpu_var(hrtimer_bases);
 	struct hrtimer_clock_base *base;
 	ktime_t expires_next, now;
+	int nr_retries = 0;
 	int i;
 
 	BUG_ON(!cpu_base->hres_active);
@@ -1174,6 +1198,10 @@ void hrtimer_interrupt(struct clock_event_device *dev)
 	dev->next_event.tv64 = KTIME_MAX;
 
  retry:
+	/* 5 retries is enough to notice a hang */
+	if (!(++nr_retries % 5))
+		hrtimer_interrupt_hanging(dev, ktime_sub(ktime_get(), now));
+
 	now = ktime_get();
 
 	expires_next.tv64 = KTIME_MAX;
@@ -1226,7 +1254,7 @@ void hrtimer_interrupt(struct clock_event_device *dev)
 
 	/* Reprogramming necessary ? */
 	if (expires_next.tv64 != KTIME_MAX) {
-		if (tick_program_event(expires_next, 0))
+		if (tick_program_event(expires_next, force_clock_reprogram))
 			goto retry;
 	}
 }
-- 
cgit v1.2.3


From 94df7de0289bc2df3d6e85cd2ece52bf42682f45 Mon Sep 17 00:00:00 2001
From: Sebastien Dugue <sebastien.dugue@bull.net>
Date: Mon, 1 Dec 2008 14:09:07 +0100
Subject: hrtimers: allow the hot-unplugging of all cpus

Impact: fix CPU hotplug hang on Power6 testbox

On architectures that support offlining all cpus (at least powerpc/pseries),
hot-unpluging the tick_do_timer_cpu can result in a system hang.

This comes from the fact that if the cpu going down happens to be the
cpu doing the tick, then as the tick_do_timer_cpu handover happens after the
cpu is dead (via the CPU_DEAD notification), we're left without ticks,
jiffies are frozen and any task relying on timers (msleep, ...) is stuck.
That's particularly the case for the cpu looping in __cpu_die() waiting
for the dying cpu to be dead.

This patch addresses this by having the tick_do_timer_cpu handover happen
earlier during the CPU_DYING notification. For this, a new clockevent
notification type is introduced (CLOCK_EVT_NOTIFY_CPU_DYING) which is triggered
in hrtimer_cpu_notify().

Signed-off-by: Sebastien Dugue <sebastien.dugue@bull.net>
Cc: <stable@kernel.org>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
---
 include/linux/clockchips.h |  1 +
 kernel/hrtimer.c           |  4 ++++
 kernel/time/tick-common.c  | 26 +++++++++++++++++++-------
 3 files changed, 24 insertions(+), 7 deletions(-)

(limited to 'kernel')

diff --git a/include/linux/clockchips.h b/include/linux/clockchips.h
index cea153697ec7..3a1dbba4d3ae 100644
--- a/include/linux/clockchips.h
+++ b/include/linux/clockchips.h
@@ -36,6 +36,7 @@ enum clock_event_nofitiers {
 	CLOCK_EVT_NOTIFY_BROADCAST_EXIT,
 	CLOCK_EVT_NOTIFY_SUSPEND,
 	CLOCK_EVT_NOTIFY_RESUME,
+	CLOCK_EVT_NOTIFY_CPU_DYING,
 	CLOCK_EVT_NOTIFY_CPU_DEAD,
 };
 
diff --git a/kernel/hrtimer.c b/kernel/hrtimer.c
index 8fea312ca36c..647a40e2fea1 100644
--- a/kernel/hrtimer.c
+++ b/kernel/hrtimer.c
@@ -1608,6 +1608,10 @@ static int __cpuinit hrtimer_cpu_notify(struct notifier_block *self,
 		break;
 
 #ifdef CONFIG_HOTPLUG_CPU
+	case CPU_DYING:
+	case CPU_DYING_FROZEN:
+		clockevents_notify(CLOCK_EVT_NOTIFY_CPU_DYING, &scpu);
+		break;
 	case CPU_DEAD:
 	case CPU_DEAD_FROZEN:
 	{
diff --git a/kernel/time/tick-common.c b/kernel/time/tick-common.c
index 63e05d423a09..21a5ca849514 100644
--- a/kernel/time/tick-common.c
+++ b/kernel/time/tick-common.c
@@ -273,6 +273,21 @@ out_bc:
 	return ret;
 }
 
+/*
+ * Transfer the do_timer job away from a dying cpu.
+ *
+ * Called with interrupts disabled.
+ */
+static void tick_handover_do_timer(int *cpup)
+{
+	if (*cpup == tick_do_timer_cpu) {
+		int cpu = cpumask_first(cpu_online_mask);
+
+		tick_do_timer_cpu = (cpu < nr_cpu_ids) ? cpu :
+			TICK_DO_TIMER_NONE;
+	}
+}
+
 /*
  * Shutdown an event device on a given cpu:
  *
@@ -297,13 +312,6 @@ static void tick_shutdown(unsigned int *cpup)
 		clockevents_exchange_device(dev, NULL);
 		td->evtdev = NULL;
 	}
-	/* Transfer the do_timer job away from this cpu */
-	if (*cpup == tick_do_timer_cpu) {
-		int cpu = cpumask_first(cpu_online_mask);
-
-		tick_do_timer_cpu = (cpu < nr_cpu_ids) ? cpu :
-			TICK_DO_TIMER_NONE;
-	}
 	spin_unlock_irqrestore(&tick_device_lock, flags);
 }
 
@@ -357,6 +365,10 @@ static int tick_notify(struct notifier_block *nb, unsigned long reason,
 		tick_broadcast_oneshot_control(reason);
 		break;
 
+	case CLOCK_EVT_NOTIFY_CPU_DYING:
+		tick_handover_do_timer(dev);
+		break;
+
 	case CLOCK_EVT_NOTIFY_CPU_DEAD:
 		tick_shutdown_broadcast_oneshot(dev);
 		tick_shutdown_broadcast(dev);
-- 
cgit v1.2.3


From b0a9b5111abf60ef07eade834f480e89004c7920 Mon Sep 17 00:00:00 2001
From: Thomas Gleixner <tglx@linutronix.de>
Date: Sun, 25 Jan 2009 11:31:36 +0100
Subject: hrtimer: prevent negative expiry value after clock_was_set()

Impact: prevent false positive WARN_ON() in clockevents_program_event()

clock_was_set() changes the base->offset of CLOCK_REALTIME and
enforces the reprogramming of the clockevent device to expire timers
which are based on CLOCK_REALTIME. If the clock change is large enough
then the subtraction of the timer expiry value and base->offset can
become negative which triggers the warning in
clockevents_program_event().

Check the subtraction result and set a negative value to 0.

Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
---
 kernel/hrtimer.c | 7 +++++++
 1 file changed, 7 insertions(+)

(limited to 'kernel')

diff --git a/kernel/hrtimer.c b/kernel/hrtimer.c
index 647a40e2fea1..f394d2a42ca3 100644
--- a/kernel/hrtimer.c
+++ b/kernel/hrtimer.c
@@ -501,6 +501,13 @@ static void hrtimer_force_reprogram(struct hrtimer_cpu_base *cpu_base)
 			continue;
 		timer = rb_entry(base->first, struct hrtimer, node);
 		expires = ktime_sub(hrtimer_get_expires(timer), base->offset);
+		/*
+		 * clock_was_set() has changed base->offset so the
+		 * result might be negative. Fix it up to prevent a
+		 * false positive in clockevents_program_event()
+		 */
+		if (expires.tv64 < 0)
+			expires.tv64 = 0;
 		if (expires.tv64 < cpu_base->expires_next.tv64)
 			cpu_base->expires_next = expires;
 	}
-- 
cgit v1.2.3


From d942fb6c7d391baba3dddb566eb735fbf3df8528 Mon Sep 17 00:00:00 2001
From: Peter Zijlstra <a.p.zijlstra@chello.nl>
Date: Mon, 26 Jan 2009 17:56:17 +0100
Subject: sched: fix sync wakeups

Pawel Dziekonski reported that the openssl benchmark and his
quantum chemistry application both show slowdowns due to the
scheduler under-parallelizing execution.

The reason are pipe wakeups still doing 'sync' wakeups which
overrides the normal buddy wakeup logic - even if waker and
wakee are loosely coupled.

Fix an inversion of logic in the buddy wakeup code.

Reported-by: Pawel Dziekonski <dzieko@gmail.com>
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
---
 kernel/sched.c      |  4 ++++
 kernel/sched_fair.c | 11 ++---------
 2 files changed, 6 insertions(+), 9 deletions(-)

(limited to 'kernel')

diff --git a/kernel/sched.c b/kernel/sched.c
index 52bbf1c842a8..770b1f9ebe14 100644
--- a/kernel/sched.c
+++ b/kernel/sched.c
@@ -2266,6 +2266,10 @@ static int try_to_wake_up(struct task_struct *p, unsigned int state, int sync)
 	if (!sched_feat(SYNC_WAKEUPS))
 		sync = 0;
 
+	if (!sync && (current->se.avg_overlap < sysctl_sched_migration_cost &&
+			    p->se.avg_overlap < sysctl_sched_migration_cost))
+		sync = 1;
+
 #ifdef CONFIG_SMP
 	if (sched_feat(LB_WAKEUP_UPDATE)) {
 		struct sched_domain *sd;
diff --git a/kernel/sched_fair.c b/kernel/sched_fair.c
index 5cc1c162044f..fdc417504681 100644
--- a/kernel/sched_fair.c
+++ b/kernel/sched_fair.c
@@ -1179,20 +1179,15 @@ wake_affine(struct sched_domain *this_sd, struct rq *this_rq,
 	    int idx, unsigned long load, unsigned long this_load,
 	    unsigned int imbalance)
 {
-	struct task_struct *curr = this_rq->curr;
-	struct task_group *tg;
 	unsigned long tl = this_load;
 	unsigned long tl_per_task;
+	struct task_group *tg;
 	unsigned long weight;
 	int balanced;
 
 	if (!(this_sd->flags & SD_WAKE_AFFINE) || !sched_feat(AFFINE_WAKEUPS))
 		return 0;
 
-	if (sync && (curr->se.avg_overlap > sysctl_sched_migration_cost ||
-			p->se.avg_overlap > sysctl_sched_migration_cost))
-		sync = 0;
-
 	/*
 	 * If sync wakeup then subtract the (maximum possible)
 	 * effect of the currently running task from the load
@@ -1419,9 +1414,7 @@ static void check_preempt_wakeup(struct rq *rq, struct task_struct *p, int sync)
 	if (!sched_feat(WAKEUP_PREEMPT))
 		return;
 
-	if (sched_feat(WAKEUP_OVERLAP) && (sync ||
-			(se->avg_overlap < sysctl_sched_migration_cost &&
-			 pse->avg_overlap < sysctl_sched_migration_cost))) {
+	if (sched_feat(WAKEUP_OVERLAP) && sync) {
 		resched_task(curr);
 		return;
 	}
-- 
cgit v1.2.3


From 1596e29773eadd96b0a5fc6e736afa52394cafda Mon Sep 17 00:00:00 2001
From: Peter Zijlstra <a.p.zijlstra@chello.nl>
Date: Wed, 28 Jan 2009 14:51:38 +0100
Subject: sched: symmetric sync vs avg_overlap

Reinstate the weakening of the sync hint if set. This yields a more
symmetric usage of avg_overlap.

Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
---
 kernel/sched.c | 12 +++++++++---
 1 file changed, 9 insertions(+), 3 deletions(-)

(limited to 'kernel')

diff --git a/kernel/sched.c b/kernel/sched.c
index 770b1f9ebe14..242d0d47a70d 100644
--- a/kernel/sched.c
+++ b/kernel/sched.c
@@ -2266,9 +2266,15 @@ static int try_to_wake_up(struct task_struct *p, unsigned int state, int sync)
 	if (!sched_feat(SYNC_WAKEUPS))
 		sync = 0;
 
-	if (!sync && (current->se.avg_overlap < sysctl_sched_migration_cost &&
-			    p->se.avg_overlap < sysctl_sched_migration_cost))
-		sync = 1;
+	if (!sync) {
+		if (current->se.avg_overlap < sysctl_sched_migration_cost &&
+			  p->se.avg_overlap < sysctl_sched_migration_cost)
+			sync = 1;
+	} else {
+		if (current->se.avg_overlap >= sysctl_sched_migration_cost ||
+			  p->se.avg_overlap >= sysctl_sched_migration_cost)
+			sync = 0;
+	}
 
 #ifdef CONFIG_SMP
 	if (sched_feat(LB_WAKEUP_UPDATE)) {
-- 
cgit v1.2.3


From a9f3e2b549f83a9cdab873abf4140be27c05a3f2 Mon Sep 17 00:00:00 2001
From: Mike Galbraith <efault@gmx.de>
Date: Wed, 28 Jan 2009 14:51:39 +0100
Subject: sched: clear buddies more aggressively

It was noticed that a task could get re-elected past its run quota due to buddy
affinities. This could increase latency a little. Cure it by more aggresively
clearing buddy state.

We do so in two situations:
 - when we force preempt
 - when we select a buddy to run

Signed-off-by: Mike Galbraith <efault@gmx.de>
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
---
 kernel/sched_fair.c | 13 ++++++++++++-
 1 file changed, 12 insertions(+), 1 deletion(-)

(limited to 'kernel')

diff --git a/kernel/sched_fair.c b/kernel/sched_fair.c
index fdc417504681..75248b9ff4c1 100644
--- a/kernel/sched_fair.c
+++ b/kernel/sched_fair.c
@@ -768,8 +768,14 @@ check_preempt_tick(struct cfs_rq *cfs_rq, struct sched_entity *curr)
 
 	ideal_runtime = sched_slice(cfs_rq, curr);
 	delta_exec = curr->sum_exec_runtime - curr->prev_sum_exec_runtime;
-	if (delta_exec > ideal_runtime)
+	if (delta_exec > ideal_runtime) {
 		resched_task(rq_of(cfs_rq)->curr);
+		/*
+		 * The current task ran long enough, ensure it doesn't get
+		 * re-elected due to buddy favours.
+		 */
+		clear_buddies(cfs_rq, curr);
+	}
 }
 
 static void
@@ -1445,6 +1451,11 @@ static struct task_struct *pick_next_task_fair(struct rq *rq)
 
 	do {
 		se = pick_next_entity(cfs_rq);
+		/*
+		 * If se was a buddy, clear it so that it will have to earn
+		 * the favour again.
+		 */
+		clear_buddies(cfs_rq, se);
 		set_next_entity(cfs_rq, se);
 		cfs_rq = group_cfs_rq(se);
 	} while (cfs_rq);
-- 
cgit v1.2.3


From a571bbeafbcc501d9989fbce1cddcd810bd51d71 Mon Sep 17 00:00:00 2001
From: Peter Zijlstra <a.p.zijlstra@chello.nl>
Date: Wed, 28 Jan 2009 14:51:40 +0100
Subject: sched: fix buddie group latency

Similar to the previous patch, by not clearing buddies we can select entities
past their run quota, which can increase latency. This means we have to clear
group buddies as well.

Do not use the group clear for pick_next_task(), otherwise that'll get O(n^2).

Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
---
 kernel/sched_fair.c | 10 ++++++++--
 1 file changed, 8 insertions(+), 2 deletions(-)

(limited to 'kernel')

diff --git a/kernel/sched_fair.c b/kernel/sched_fair.c
index 75248b9ff4c1..a7e50ba185ac 100644
--- a/kernel/sched_fair.c
+++ b/kernel/sched_fair.c
@@ -719,7 +719,7 @@ enqueue_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int wakeup)
 		__enqueue_entity(cfs_rq, se);
 }
 
-static void clear_buddies(struct cfs_rq *cfs_rq, struct sched_entity *se)
+static void __clear_buddies(struct cfs_rq *cfs_rq, struct sched_entity *se)
 {
 	if (cfs_rq->last == se)
 		cfs_rq->last = NULL;
@@ -728,6 +728,12 @@ static void clear_buddies(struct cfs_rq *cfs_rq, struct sched_entity *se)
 		cfs_rq->next = NULL;
 }
 
+static void clear_buddies(struct cfs_rq *cfs_rq, struct sched_entity *se)
+{
+	for_each_sched_entity(se)
+		__clear_buddies(cfs_rq_of(se), se);
+}
+
 static void
 dequeue_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int sleep)
 {
@@ -1455,7 +1461,7 @@ static struct task_struct *pick_next_task_fair(struct rq *rq)
 		 * If se was a buddy, clear it so that it will have to earn
 		 * the favour again.
 		 */
-		clear_buddies(cfs_rq, se);
+		__clear_buddies(cfs_rq, se);
 		set_next_entity(cfs_rq, se);
 		cfs_rq = group_cfs_rq(se);
 	} while (cfs_rq);
-- 
cgit v1.2.3


From 3d398703ef06fd97b4c28c86b580546d5b57e7b7 Mon Sep 17 00:00:00 2001
From: Rusty Russell <rusty@rustcorp.com.au>
Date: Sat, 31 Jan 2009 23:21:24 +1030
Subject: sched_rt: don't use first_cpu on cpumask created with cpumask_and

cpumask_and() only initializes nr_cpu_ids bits, so the (deprecated)
first_cpu() might find one of those uninitialized bits if nr_cpu_ids
is less than NR_CPUS (as it can be for CONFIG_CPUMASK_OFFSTACK).

Signed-off-by: Rusty Russell <rusty@rustcorp.com.au>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
---
 kernel/sched_rt.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

(limited to 'kernel')

diff --git a/kernel/sched_rt.c b/kernel/sched_rt.c
index 954e1a81b796..bac1061cea2f 100644
--- a/kernel/sched_rt.c
+++ b/kernel/sched_rt.c
@@ -968,8 +968,8 @@ static inline int pick_optimal_cpu(int this_cpu, cpumask_t *mask)
 	if ((this_cpu != -1) && cpu_isset(this_cpu, *mask))
 		return this_cpu;
 
-	first = first_cpu(*mask);
-	if (first != NR_CPUS)
+	first = cpumask_first(mask);
+	if (first < nr_cpu_ids)
 		return first;
 
 	return -1;
-- 
cgit v1.2.3


From 10b888d6cec2688e65e9e128b14bf98ecd199da2 Mon Sep 17 00:00:00 2001
From: Yinghai Lu <yinghai@kernel.org>
Date: Sat, 31 Jan 2009 14:50:07 -0800
Subject: irq, x86: fix lock status with numa_migrate_irq_desc

Eric Paris reported:

> I have an hp dl785g5 which is unable to successfully run
> 2.6.29-0.66.rc3.fc11.x86_64 or 2.6.29-rc2-next-20090126.  During bootup
> (early in userspace daemons starting) I get the below BUG, which quickly
> renders the machine dead.  I assume it is because sparse_irq_lock never
> gets released when the BUG kills that task.

Adjust lock sequence when migrating a descriptor with
CONFIG_NUMA_MIGRATE_IRQ_DESC enabled.

Signed-off-by: Yinghai Lu <yinghai@kernel.org>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
---
 arch/x86/kernel/io_apic.c | 5 +++--
 kernel/irq/numa_migrate.c | 7 ++++++-
 2 files changed, 9 insertions(+), 3 deletions(-)

(limited to 'kernel')

diff --git a/arch/x86/kernel/io_apic.c b/arch/x86/kernel/io_apic.c
index 1c4a1302536c..9b0c480c383b 100644
--- a/arch/x86/kernel/io_apic.c
+++ b/arch/x86/kernel/io_apic.c
@@ -2528,14 +2528,15 @@ static void irq_complete_move(struct irq_desc **descp)
 
 	vector = ~get_irq_regs()->orig_ax;
 	me = smp_processor_id();
+
+	if (vector == cfg->vector && cpumask_test_cpu(me, cfg->domain)) {
 #ifdef CONFIG_NUMA_MIGRATE_IRQ_DESC
 		*descp = desc = move_irq_desc(desc, me);
 		/* get the new one */
 		cfg = desc->chip_data;
 #endif
-
-	if (vector == cfg->vector && cpumask_test_cpu(me, cfg->domain))
 		send_cleanup_vector(cfg);
+	}
 }
 #else
 static inline void irq_complete_move(struct irq_desc **descp) {}
diff --git a/kernel/irq/numa_migrate.c b/kernel/irq/numa_migrate.c
index ecf765c6a77a..acd88356ac76 100644
--- a/kernel/irq/numa_migrate.c
+++ b/kernel/irq/numa_migrate.c
@@ -71,7 +71,7 @@ static struct irq_desc *__real_move_irq_desc(struct irq_desc *old_desc,
 	desc = irq_desc_ptrs[irq];
 
 	if (desc && old_desc != desc)
-			goto out_unlock;
+		goto out_unlock;
 
 	node = cpu_to_node(cpu);
 	desc = kzalloc_node(sizeof(*desc), GFP_ATOMIC, node);
@@ -84,10 +84,15 @@ static struct irq_desc *__real_move_irq_desc(struct irq_desc *old_desc,
 	init_copy_one_irq_desc(irq, old_desc, desc, cpu);
 
 	irq_desc_ptrs[irq] = desc;
+	spin_unlock_irqrestore(&sparse_irq_lock, flags);
 
 	/* free the old one */
 	free_one_irq_desc(old_desc, desc);
+	spin_unlock(&old_desc->lock);
 	kfree(old_desc);
+	spin_lock(&desc->lock);
+
+	return desc;
 
 out_unlock:
 	spin_unlock_irqrestore(&sparse_irq_lock, flags);
-- 
cgit v1.2.3


From 720eba31f47aeade8ec130ca7f4353223c49170f Mon Sep 17 00:00:00 2001
From: Eric Dumazet <dada1@cosmosbay.com>
Date: Tue, 3 Feb 2009 13:31:36 +1030
Subject: modules: Use a better scheme for refcounting

Current refcounting for modules (done if CONFIG_MODULE_UNLOAD=y) is
using a lot of memory.

Each 'struct module' contains an [NR_CPUS] array of full cache lines.

This patch uses existing infrastructure (percpu_modalloc() &
percpu_modfree()) to allocate percpu space for the refcount storage.

Instead of wasting NR_CPUS*128 bytes (on i386), we now use
nr_cpu_ids*sizeof(local_t) bytes.

On a typical distro, where NR_CPUS=8, shiping 2000 modules, we reduce
size of module files by about 2 Mbytes. (1Kb per module)

Instead of having all refcounters in the same memory node - with TLB misses
because of vmalloc() - this new implementation permits to have better
NUMA properties, since each  CPU will use storage on its preferred node,
thanks to percpu storage.

Signed-off-by: Eric Dumazet <dada1@cosmosbay.com>
Signed-off-by: Rusty Russell <rusty@rustcorp.com.au>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/module.h | 25 ++++++++++++++++---------
 kernel/module.c        | 35 +++++++++++++++++++++++++----------
 2 files changed, 41 insertions(+), 19 deletions(-)

(limited to 'kernel')

diff --git a/include/linux/module.h b/include/linux/module.h
index 4f7ea12463d3..f3b8329eb5b8 100644
--- a/include/linux/module.h
+++ b/include/linux/module.h
@@ -219,11 +219,6 @@ void *__symbol_get_gpl(const char *symbol);
 
 #endif
 
-struct module_ref
-{
-	local_t count;
-} ____cacheline_aligned;
-
 enum module_state
 {
 	MODULE_STATE_LIVE,
@@ -344,8 +339,11 @@ struct module
 	/* Destruction function. */
 	void (*exit)(void);
 
-	/* Reference counts */
-	struct module_ref ref[NR_CPUS];
+#ifdef CONFIG_SMP
+	char *refptr;
+#else
+	local_t ref;
+#endif
 #endif
 };
 #ifndef MODULE_ARCH_INIT
@@ -395,13 +393,22 @@ void __symbol_put(const char *symbol);
 #define symbol_put(x) __symbol_put(MODULE_SYMBOL_PREFIX #x)
 void symbol_put_addr(void *addr);
 
+static inline local_t *__module_ref_addr(struct module *mod, int cpu)
+{
+#ifdef CONFIG_SMP
+	return (local_t *) (mod->refptr + per_cpu_offset(cpu));
+#else
+	return &mod->ref;
+#endif
+}
+
 /* Sometimes we know we already have a refcount, and it's easier not
    to handle the error case (which only happens with rmmod --wait). */
 static inline void __module_get(struct module *module)
 {
 	if (module) {
 		BUG_ON(module_refcount(module) == 0);
-		local_inc(&module->ref[get_cpu()].count);
+		local_inc(__module_ref_addr(module, get_cpu()));
 		put_cpu();
 	}
 }
@@ -413,7 +420,7 @@ static inline int try_module_get(struct module *module)
 	if (module) {
 		unsigned int cpu = get_cpu();
 		if (likely(module_is_live(module)))
-			local_inc(&module->ref[cpu].count);
+			local_inc(__module_ref_addr(module, cpu));
 		else
 			ret = 0;
 		put_cpu();
diff --git a/kernel/module.c b/kernel/module.c
index e8b51d41dd72..ba22484a987e 100644
--- a/kernel/module.c
+++ b/kernel/module.c
@@ -573,13 +573,13 @@ static char last_unloaded_module[MODULE_NAME_LEN+1];
 /* Init the unload section of the module. */
 static void module_unload_init(struct module *mod)
 {
-	unsigned int i;
+	int cpu;
 
 	INIT_LIST_HEAD(&mod->modules_which_use_me);
-	for (i = 0; i < NR_CPUS; i++)
-		local_set(&mod->ref[i].count, 0);
+	for_each_possible_cpu(cpu)
+		local_set(__module_ref_addr(mod, cpu), 0);
 	/* Hold reference count during initialization. */
-	local_set(&mod->ref[raw_smp_processor_id()].count, 1);
+	local_set(__module_ref_addr(mod, raw_smp_processor_id()), 1);
 	/* Backwards compatibility macros put refcount during init. */
 	mod->waiter = current;
 }
@@ -717,10 +717,11 @@ static int try_stop_module(struct module *mod, int flags, int *forced)
 
 unsigned int module_refcount(struct module *mod)
 {
-	unsigned int i, total = 0;
+	unsigned int total = 0;
+	int cpu;
 
-	for (i = 0; i < NR_CPUS; i++)
-		total += local_read(&mod->ref[i].count);
+	for_each_possible_cpu(cpu)
+		total += local_read(__module_ref_addr(mod, cpu));
 	return total;
 }
 EXPORT_SYMBOL(module_refcount);
@@ -894,7 +895,7 @@ void module_put(struct module *module)
 {
 	if (module) {
 		unsigned int cpu = get_cpu();
-		local_dec(&module->ref[cpu].count);
+		local_dec(__module_ref_addr(module, cpu));
 		/* Maybe they're waiting for us to drop reference? */
 		if (unlikely(!module_is_live(module)))
 			wake_up_process(module->waiter);
@@ -1464,7 +1465,10 @@ static void free_module(struct module *mod)
 	kfree(mod->args);
 	if (mod->percpu)
 		percpu_modfree(mod->percpu);
-
+#if defined(CONFIG_MODULE_UNLOAD) && defined(CONFIG_SMP)
+	if (mod->refptr)
+		percpu_modfree(mod->refptr);
+#endif
 	/* Free lock-classes: */
 	lockdep_free_key_range(mod->module_core, mod->core_size);
 
@@ -2011,6 +2015,14 @@ static noinline struct module *load_module(void __user *umod,
 	if (err < 0)
 		goto free_mod;
 
+#if defined(CONFIG_MODULE_UNLOAD) && defined(CONFIG_SMP)
+	mod->refptr = percpu_modalloc(sizeof(local_t), __alignof__(local_t),
+				      mod->name);
+	if (!mod->refptr) {
+		err = -ENOMEM;
+		goto free_mod;
+	}
+#endif
 	if (pcpuindex) {
 		/* We have a special allocation for this section. */
 		percpu = percpu_modalloc(sechdrs[pcpuindex].sh_size,
@@ -2018,7 +2030,7 @@ static noinline struct module *load_module(void __user *umod,
 					 mod->name);
 		if (!percpu) {
 			err = -ENOMEM;
-			goto free_mod;
+			goto free_percpu;
 		}
 		sechdrs[pcpuindex].sh_flags &= ~(unsigned long)SHF_ALLOC;
 		mod->percpu = percpu;
@@ -2282,6 +2294,9 @@ static noinline struct module *load_module(void __user *umod,
  free_percpu:
 	if (percpu)
 		percpu_modfree(percpu);
+#if defined(CONFIG_MODULE_UNLOAD) && defined(CONFIG_SMP)
+	percpu_modfree(mod->refptr);
+#endif
  free_mod:
 	kfree(args);
  free_hdr:
-- 
cgit v1.2.3


From 229c4ef8ae56d69f8dec64533bf1c7f8070c1a4a Mon Sep 17 00:00:00 2001
From: Oleg Nesterov <oleg@redhat.com>
Date: Tue, 3 Feb 2009 20:39:04 +0100
Subject: ftrace: do_each_pid_task() needs rcu lock

"ftrace: use struct pid" commit 978f3a45d9499c7a447ca7615455cefb63d44165
converted ftrace_pid_trace to "struct pid*".

But we can't use do_each_pid_task() without rcu_read_lock() even if
we know the pid itself can't go away (it was pinned in ftrace_pid_write).
The exiting task can detach itself from this pid at any moment.

Signed-off-by: Oleg Nesterov <oleg@redhat.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
---
 kernel/trace/ftrace.c | 5 +++++
 1 file changed, 5 insertions(+)

(limited to 'kernel')

diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c
index 7dcf6e9f2b04..9a236ffe2aa4 100644
--- a/kernel/trace/ftrace.c
+++ b/kernel/trace/ftrace.c
@@ -1737,9 +1737,12 @@ static void clear_ftrace_pid(struct pid *pid)
 {
 	struct task_struct *p;
 
+	rcu_read_lock();
 	do_each_pid_task(pid, PIDTYPE_PID, p) {
 		clear_tsk_trace_trace(p);
 	} while_each_pid_task(pid, PIDTYPE_PID, p);
+	rcu_read_unlock();
+
 	put_pid(pid);
 }
 
@@ -1747,9 +1750,11 @@ static void set_ftrace_pid(struct pid *pid)
 {
 	struct task_struct *p;
 
+	rcu_read_lock();
 	do_each_pid_task(pid, PIDTYPE_PID, p) {
 		set_tsk_trace_trace(p);
 	} while_each_pid_task(pid, PIDTYPE_PID, p);
+	rcu_read_unlock();
 }
 
 static void clear_ftrace_pid_task(struct pid **pid)
-- 
cgit v1.2.3


From 58763a297405024d23d8f1d0bba3e6603660c4b6 Mon Sep 17 00:00:00 2001
From: Andrew Morton <akpm@linux-foundation.org>
Date: Wed, 4 Feb 2009 15:11:58 -0800
Subject: kernel/async.c: fix printk warnings

alpha:

kernel/async.c: In function 'run_one_entry':
kernel/async.c:141: warning: format '%lli' expects type 'long long int', but argument 2 has type 'async_cookie_t'
kernel/async.c:149: warning: format '%lli' expects type 'long long int', but argument 2 has type 'async_cookie_t'
kernel/async.c:149: warning: format '%lld' expects type 'long long int', but argument 4 has type 's64'
kernel/async.c: In function 'async_synchronize_cookie_special':
kernel/async.c:250: warning: format '%lli' expects type 'long long int', but argument 3 has type 's64'

Cc: Arjan van de Ven <arjan@infradead.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 kernel/async.c | 12 ++++++++----
 1 file changed, 8 insertions(+), 4 deletions(-)

(limited to 'kernel')

diff --git a/kernel/async.c b/kernel/async.c
index 608b32b42812..67a2be71f517 100644
--- a/kernel/async.c
+++ b/kernel/async.c
@@ -138,15 +138,18 @@ static void run_one_entry(void)
 
 	/* 3) run it (and print duration)*/
 	if (initcall_debug && system_state == SYSTEM_BOOTING) {
-		printk("calling  %lli_%pF @ %i\n", entry->cookie, entry->func, task_pid_nr(current));
+		printk("calling  %lli_%pF @ %i\n", (long long)entry->cookie,
+			entry->func, task_pid_nr(current));
 		calltime = ktime_get();
 	}
 	entry->func(entry->data, entry->cookie);
 	if (initcall_debug && system_state == SYSTEM_BOOTING) {
 		rettime = ktime_get();
 		delta = ktime_sub(rettime, calltime);
-		printk("initcall %lli_%pF returned 0 after %lld usecs\n", entry->cookie,
-			entry->func, ktime_to_ns(delta) >> 10);
+		printk("initcall %lli_%pF returned 0 after %lld usecs\n",
+			(long long)entry->cookie,
+			entry->func,
+			(long long)ktime_to_ns(delta) >> 10);
 	}
 
 	/* 4) remove it from the running queue */
@@ -247,7 +250,8 @@ void async_synchronize_cookie_special(async_cookie_t cookie, struct list_head *r
 		delta = ktime_sub(endtime, starttime);
 
 		printk("async_continuing @ %i after %lli usec\n",
-			task_pid_nr(current), ktime_to_ns(delta) >> 10);
+			task_pid_nr(current),
+			(long long)ktime_to_ns(delta) >> 10);
 	}
 }
 EXPORT_SYMBOL_GPL(async_synchronize_cookie_special);
-- 
cgit v1.2.3


From 60fd760fb9ff7034360bab7137c917c0330628c2 Mon Sep 17 00:00:00 2001
From: Andrew Morton <akpm@linux-foundation.org>
Date: Wed, 4 Feb 2009 15:12:06 -0800
Subject: revert "rlimit: permit setting RLIMIT_NOFILE to RLIM_INFINITY"

Revert commit 0c2d64fb6cae9aae480f6a46cfe79f8d7d48b59f because it causes
(arguably poorly designed) existing userspace to spend interminable
periods closing billions of not-open file descriptors.

We could bring this back, with some sort of opt-in tunable in /proc, which
defaults to "off".

Peter's alanysis follows:

: I spent several hours trying to get to the bottom of a serious
: performance issue that appeared on one of our servers after upgrading to
: 2.6.28.  In the end it's what could be considered a userspace bug that
: was triggered by a change in 2.6.28.  Since this might also affect other
: people I figured I'd at least document what I found here, and maybe we
: can even do something about it:
:
:
: So, I upgraded some of debian.org's machines to 2.6.28.1 and immediately
: the team maintaining our ftp archive complained that one of their
: scripts that previously ran in a few minutes still hadn't even come
: close to being done after an hour or so.  Downgrading to 2.6.27 fixed
: that.
:
: Turns out that script is forking a lot and something in it or python or
: whereever closes all the file descriptors it doesn't want to pass on.
: That is, it starts at zero and goes up to ulimit -n/RLIMIT_NOFILE and
: closes them all with a few exceptions.
:
: Turns out that takes a long time when your limit -n is now 2^20 (1048576).
:
: With 2.6.27.* the ulimit -n was the standard 1024, but with 2.6.28 it is
: now a thousand times that.
:
: 2.6.28 included a patch titled "rlimit: permit setting RLIMIT_NOFILE to
: RLIM_INFINITY" (0c2d64fb6cae9aae480f6a46cfe79f8d7d48b59f)[1] that
: allows, as the title implies, to set the limit for number of files to
: infinity.
:
: Closer investigation showed that the broken default ulimit did not apply
: to "system" processes (like stuff started from init).  In the end I
: could establish that all processes that passed through pam_limit at one
: point had the bad resource limit.
:
: Apparently the pam library in Debian etch (4.0) initializes the limits
: to some default values when it doesn't have any settings in limit.conf
: to override them.  Turns out that for nofiles this is RLIM_INFINITY.
: Commenting out "case RLIMIT_NOFILE" in pam_limit.c:267 of our pam
: package version 0.79-5 fixes that - tho I'm not sure what side effects
: that has.
:
: Debian lenny (the upcoming 5.0 version) doesn't have this issue as it
: uses a different pam (version).

Reported-by: Peter Palfrader <weasel@debian.org>
Cc: Adam Tkac <vonsch@gmail.com>
Cc: Michael Kerrisk <mtk.manpages@googlemail.com>
Cc: <stable@kernel.org>		[2.6.28.x]
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 kernel/sys.c | 16 ++++------------
 1 file changed, 4 insertions(+), 12 deletions(-)

(limited to 'kernel')

diff --git a/kernel/sys.c b/kernel/sys.c
index e7dc0e10a485..f145c415bc16 100644
--- a/kernel/sys.c
+++ b/kernel/sys.c
@@ -1525,22 +1525,14 @@ SYSCALL_DEFINE2(setrlimit, unsigned int, resource, struct rlimit __user *, rlim)
 		return -EINVAL;
 	if (copy_from_user(&new_rlim, rlim, sizeof(*rlim)))
 		return -EFAULT;
+	if (new_rlim.rlim_cur > new_rlim.rlim_max)
+		return -EINVAL;
 	old_rlim = current->signal->rlim + resource;
 	if ((new_rlim.rlim_max > old_rlim->rlim_max) &&
 	    !capable(CAP_SYS_RESOURCE))
 		return -EPERM;
-
-	if (resource == RLIMIT_NOFILE) {
-		if (new_rlim.rlim_max == RLIM_INFINITY)
-			new_rlim.rlim_max = sysctl_nr_open;
-		if (new_rlim.rlim_cur == RLIM_INFINITY)
-			new_rlim.rlim_cur = sysctl_nr_open;
-		if (new_rlim.rlim_max > sysctl_nr_open)
-			return -EPERM;
-	}
-
-	if (new_rlim.rlim_cur > new_rlim.rlim_max)
-		return -EINVAL;
+	if (resource == RLIMIT_NOFILE && new_rlim.rlim_max > sysctl_nr_open)
+		return -EPERM;
 
 	retval = security_task_setrlimit(resource, &new_rlim);
 	if (retval)
-- 
cgit v1.2.3


From 777c6c5f1f6e757ae49ecca2ed72d6b1f523c007 Mon Sep 17 00:00:00 2001
From: Johannes Weiner <hannes@cmpxchg.org>
Date: Wed, 4 Feb 2009 15:12:14 -0800
Subject: wait: prevent exclusive waiter starvation

With exclusive waiters, every process woken up through the wait queue must
ensure that the next waiter down the line is woken when it has finished.

Interruptible waiters don't do that when aborting due to a signal.  And if
an aborting waiter is concurrently woken up through the waitqueue, noone
will ever wake up the next waiter.

This has been observed with __wait_on_bit_lock() used by
lock_page_killable(): the first contender on the queue was aborting when
the actual lock holder woke it up concurrently.  The aborted contender
didn't acquire the lock and therefor never did an unlock followed by
waking up the next waiter.

Add abort_exclusive_wait() which removes the process' wait descriptor from
the waitqueue, iff still queued, or wakes up the next waiter otherwise.
It does so under the waitqueue lock.  Racing with a wake up means the
aborting process is either already woken (removed from the queue) and will
wake up the next waiter, or it will remove itself from the queue and the
concurrent wake up will apply to the next waiter after it.

Use abort_exclusive_wait() in __wait_event_interruptible_exclusive() and
__wait_on_bit_lock() when they were interrupted by other means than a wake
up through the queue.

[akpm@linux-foundation.org: coding-style fixes]
Reported-by: Chris Mason <chris.mason@oracle.com>
Signed-off-by: Johannes Weiner <hannes@cmpxchg.org>
Mentored-by: Oleg Nesterov <oleg@redhat.com>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Matthew Wilcox <matthew@wil.cx>
Cc: Chuck Lever <cel@citi.umich.edu>
Cc: Nick Piggin <nickpiggin@yahoo.com.au>
Cc: Ingo Molnar <mingo@elte.hu>
Cc: <stable@kernel.org>		["after some testing"]
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/wait.h | 11 ++++++++--
 kernel/sched.c       |  4 ++--
 kernel/wait.c        | 59 +++++++++++++++++++++++++++++++++++++++++++++-------
 3 files changed, 63 insertions(+), 11 deletions(-)

(limited to 'kernel')

diff --git a/include/linux/wait.h b/include/linux/wait.h
index ef609f842fac..a210ede73b56 100644
--- a/include/linux/wait.h
+++ b/include/linux/wait.h
@@ -132,6 +132,8 @@ static inline void __remove_wait_queue(wait_queue_head_t *head,
 	list_del(&old->task_list);
 }
 
+void __wake_up_common(wait_queue_head_t *q, unsigned int mode,
+			int nr_exclusive, int sync, void *key);
 void __wake_up(wait_queue_head_t *q, unsigned int mode, int nr, void *key);
 extern void __wake_up_locked(wait_queue_head_t *q, unsigned int mode);
 extern void __wake_up_sync(wait_queue_head_t *q, unsigned int mode, int nr);
@@ -333,16 +335,19 @@ do {									\
 	for (;;) {							\
 		prepare_to_wait_exclusive(&wq, &__wait,			\
 					TASK_INTERRUPTIBLE);		\
-		if (condition)						\
+		if (condition) {					\
+			finish_wait(&wq, &__wait);			\
 			break;						\
+		}							\
 		if (!signal_pending(current)) {				\
 			schedule();					\
 			continue;					\
 		}							\
 		ret = -ERESTARTSYS;					\
+		abort_exclusive_wait(&wq, &__wait, 			\
+				TASK_INTERRUPTIBLE, NULL);		\
 		break;							\
 	}								\
-	finish_wait(&wq, &__wait);					\
 } while (0)
 
 #define wait_event_interruptible_exclusive(wq, condition)		\
@@ -431,6 +436,8 @@ extern long interruptible_sleep_on_timeout(wait_queue_head_t *q,
 void prepare_to_wait(wait_queue_head_t *q, wait_queue_t *wait, int state);
 void prepare_to_wait_exclusive(wait_queue_head_t *q, wait_queue_t *wait, int state);
 void finish_wait(wait_queue_head_t *q, wait_queue_t *wait);
+void abort_exclusive_wait(wait_queue_head_t *q, wait_queue_t *wait,
+			unsigned int mode, void *key);
 int autoremove_wake_function(wait_queue_t *wait, unsigned mode, int sync, void *key);
 int wake_bit_function(wait_queue_t *wait, unsigned mode, int sync, void *key);
 
diff --git a/kernel/sched.c b/kernel/sched.c
index 242d0d47a70d..8ee437a5ec1d 100644
--- a/kernel/sched.c
+++ b/kernel/sched.c
@@ -4697,8 +4697,8 @@ EXPORT_SYMBOL(default_wake_function);
  * started to run but is not in state TASK_RUNNING. try_to_wake_up() returns
  * zero in this (rare) case, and we handle it by continuing to scan the queue.
  */
-static void __wake_up_common(wait_queue_head_t *q, unsigned int mode,
-			     int nr_exclusive, int sync, void *key)
+void __wake_up_common(wait_queue_head_t *q, unsigned int mode,
+			int nr_exclusive, int sync, void *key)
 {
 	wait_queue_t *curr, *next;
 
diff --git a/kernel/wait.c b/kernel/wait.c
index cd87131f2fc2..42a2dbc181c8 100644
--- a/kernel/wait.c
+++ b/kernel/wait.c
@@ -91,6 +91,15 @@ prepare_to_wait_exclusive(wait_queue_head_t *q, wait_queue_t *wait, int state)
 }
 EXPORT_SYMBOL(prepare_to_wait_exclusive);
 
+/*
+ * finish_wait - clean up after waiting in a queue
+ * @q: waitqueue waited on
+ * @wait: wait descriptor
+ *
+ * Sets current thread back to running state and removes
+ * the wait descriptor from the given waitqueue if still
+ * queued.
+ */
 void finish_wait(wait_queue_head_t *q, wait_queue_t *wait)
 {
 	unsigned long flags;
@@ -117,6 +126,39 @@ void finish_wait(wait_queue_head_t *q, wait_queue_t *wait)
 }
 EXPORT_SYMBOL(finish_wait);
 
+/*
+ * abort_exclusive_wait - abort exclusive waiting in a queue
+ * @q: waitqueue waited on
+ * @wait: wait descriptor
+ * @state: runstate of the waiter to be woken
+ * @key: key to identify a wait bit queue or %NULL
+ *
+ * Sets current thread back to running state and removes
+ * the wait descriptor from the given waitqueue if still
+ * queued.
+ *
+ * Wakes up the next waiter if the caller is concurrently
+ * woken up through the queue.
+ *
+ * This prevents waiter starvation where an exclusive waiter
+ * aborts and is woken up concurrently and noone wakes up
+ * the next waiter.
+ */
+void abort_exclusive_wait(wait_queue_head_t *q, wait_queue_t *wait,
+			unsigned int mode, void *key)
+{
+	unsigned long flags;
+
+	__set_current_state(TASK_RUNNING);
+	spin_lock_irqsave(&q->lock, flags);
+	if (!list_empty(&wait->task_list))
+		list_del_init(&wait->task_list);
+	else if (waitqueue_active(q))
+		__wake_up_common(q, mode, 1, 0, key);
+	spin_unlock_irqrestore(&q->lock, flags);
+}
+EXPORT_SYMBOL(abort_exclusive_wait);
+
 int autoremove_wake_function(wait_queue_t *wait, unsigned mode, int sync, void *key)
 {
 	int ret = default_wake_function(wait, mode, sync, key);
@@ -177,17 +219,20 @@ int __sched
 __wait_on_bit_lock(wait_queue_head_t *wq, struct wait_bit_queue *q,
 			int (*action)(void *), unsigned mode)
 {
-	int ret = 0;
-
 	do {
+		int ret;
+
 		prepare_to_wait_exclusive(wq, &q->wait, mode);
-		if (test_bit(q->key.bit_nr, q->key.flags)) {
-			if ((ret = (*action)(q->key.flags)))
-				break;
-		}
+		if (!test_bit(q->key.bit_nr, q->key.flags))
+			continue;
+		ret = action(q->key.flags);
+		if (!ret)
+			continue;
+		abort_exclusive_wait(wq, &q->wait, mode, &q->key);
+		return ret;
 	} while (test_and_set_bit(q->key.bit_nr, q->key.flags));
 	finish_wait(wq, &q->wait);
-	return ret;
+	return 0;
 }
 EXPORT_SYMBOL(__wait_on_bit_lock);
 
-- 
cgit v1.2.3


From 04ec93fe9bc98e3bd8560f79f56fed66dfae40d5 Mon Sep 17 00:00:00 2001
From: Li Zefan <lizf@cn.fujitsu.com>
Date: Fri, 6 Feb 2009 08:17:19 +0000
Subject: fork.c: fix NULL pointer dereference when nr_threads == threads-max

I happened to forked lots of processes, and hit NULL pointer dereference.
It is because in copy_process() after checking max_threads, 0 is returned
but not -EAGAIN.

The bug is introduced by "CRED: Detach the credentials from task_struct"
(commit f1752eec6145c97163dbce62d17cf5d928e28a27).

Signed-off-by: Li Zefan <lizf@cn.fujitsu.com>
Signed-off-by: David Howells <dhowells@redhat.com>
Acked-by: James Morris <jmorris@namei.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 kernel/fork.c | 1 +
 1 file changed, 1 insertion(+)

(limited to 'kernel')

diff --git a/kernel/fork.c b/kernel/fork.c
index 242a706e7721..6d5dbb7a13e2 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -1005,6 +1005,7 @@ static struct task_struct *copy_process(unsigned long clone_flags,
 	 * triggers too late. This doesn't hurt, the check is only there
 	 * to stop root fork bombs.
 	 */
+	retval = -EAGAIN;
 	if (nr_threads >= max_threads)
 		goto bad_fork_cleanup_count;
 
-- 
cgit v1.2.3