From 76aac0e9a17742e60d408be1a706e9aaad370891 Mon Sep 17 00:00:00 2001
From: David Howells <dhowells@redhat.com>
Date: Fri, 14 Nov 2008 10:39:12 +1100
Subject: CRED: Wrap task credential accesses in the core kernel

Wrap access to task credentials so that they can be separated more easily from
the task_struct during the introduction of COW creds.

Change most current->(|e|s|fs)[ug]id to current_(|e|s|fs)[ug]id().

Change some task->e?[ug]id to task_e?[ug]id().  In some places it makes more
sense to use RCU directly rather than a convenient wrapper; these will be
addressed by later patches.

Signed-off-by: David Howells <dhowells@redhat.com>
Reviewed-by: James Morris <jmorris@namei.org>
Acked-by: Serge Hallyn <serue@us.ibm.com>
Cc: Al Viro <viro@zeniv.linux.org.uk>
Cc: linux-audit@redhat.com
Cc: containers@lists.linux-foundation.org
Cc: linux-mm@kvack.org
Signed-off-by: James Morris <jmorris@namei.org>
---
 kernel/timer.c | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

(limited to 'kernel/timer.c')

diff --git a/kernel/timer.c b/kernel/timer.c
index 56becf373c58..b54e4646cee7 100644
--- a/kernel/timer.c
+++ b/kernel/timer.c
@@ -1123,25 +1123,25 @@ asmlinkage long sys_getppid(void)
 asmlinkage long sys_getuid(void)
 {
 	/* Only we change this so SMP safe */
-	return current->uid;
+	return current_uid();
 }
 
 asmlinkage long sys_geteuid(void)
 {
 	/* Only we change this so SMP safe */
-	return current->euid;
+	return current_euid();
 }
 
 asmlinkage long sys_getgid(void)
 {
 	/* Only we change this so SMP safe */
-	return current->gid;
+	return current_gid();
 }
 
 asmlinkage long sys_getegid(void)
 {
 	/* Only we change this so SMP safe */
-	return  current->egid;
+	return  current_egid();
 }
 
 #endif
-- 
cgit v1.2.3-71-gd317


From 457533a7d3402d1d91fbc125c8bd1bd16dcd3cd4 Mon Sep 17 00:00:00 2001
From: Martin Schwidefsky <schwidefsky@de.ibm.com>
Date: Wed, 31 Dec 2008 15:11:37 +0100
Subject: [PATCH] fix scaled & unscaled cputime accounting

The utimescaled / stimescaled fields in the task structure and the
global cpustat should be set on all architectures. On s390 the calls
to account_user_time_scaled and account_system_time_scaled never have
been added. In addition system time that is accounted as guest time
to the user time of a process is accounted to the scaled system time
instead of the scaled user time.
To fix the bugs and to prevent future forgetfulness this patch merges
account_system_time_scaled into account_system_time and
account_user_time_scaled into account_user_time.

Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Cc: Hidetoshi Seto <seto.hidetoshi@jp.fujitsu.com>
Cc: Tony Luck <tony.luck@intel.com>
Cc: Jeremy Fitzhardinge <jeremy@xensource.com>
Cc: Chris Wright <chrisw@sous-sol.org>
Cc: Michael Neuling <mikey@neuling.org>
Acked-by: Paul Mackerras <paulus@samba.org>
Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com>
---
 arch/ia64/kernel/time.c     | 12 ++++--------
 arch/powerpc/kernel/time.c  |  7 ++-----
 arch/s390/kernel/vtime.c    | 10 +++++-----
 include/linux/kernel_stat.h |  6 ++----
 kernel/sched.c              | 41 ++++++++++++++++-------------------------
 kernel/time/tick-sched.c    |  5 +++--
 kernel/timer.c              | 12 +++++-------
 7 files changed, 37 insertions(+), 56 deletions(-)

(limited to 'kernel/timer.c')

diff --git a/arch/ia64/kernel/time.c b/arch/ia64/kernel/time.c
index 65c10a42c88f..4ee367817049 100644
--- a/arch/ia64/kernel/time.c
+++ b/arch/ia64/kernel/time.c
@@ -93,13 +93,11 @@ void ia64_account_on_switch(struct task_struct *prev, struct task_struct *next)
 	now = ia64_get_itc();
 
 	delta_stime = cycle_to_cputime(pi->ac_stime + (now - pi->ac_stamp));
-	account_system_time(prev, 0, delta_stime);
-	account_system_time_scaled(prev, delta_stime);
+	account_system_time(prev, 0, delta_stime, delta_stime);
 
 	if (pi->ac_utime) {
 		delta_utime = cycle_to_cputime(pi->ac_utime);
-		account_user_time(prev, delta_utime);
-		account_user_time_scaled(prev, delta_utime);
+		account_user_time(prev, delta_utime, delta_utime);
 	}
 
 	pi->ac_stamp = ni->ac_stamp = now;
@@ -122,8 +120,7 @@ void account_system_vtime(struct task_struct *tsk)
 	now = ia64_get_itc();
 
 	delta_stime = cycle_to_cputime(ti->ac_stime + (now - ti->ac_stamp));
-	account_system_time(tsk, 0, delta_stime);
-	account_system_time_scaled(tsk, delta_stime);
+	account_system_time(tsk, 0, delta_stime, delta_stime);
 	ti->ac_stime = 0;
 
 	ti->ac_stamp = now;
@@ -143,8 +140,7 @@ void account_process_tick(struct task_struct *p, int user_tick)
 
 	if (ti->ac_utime) {
 		delta_utime = cycle_to_cputime(ti->ac_utime);
-		account_user_time(p, delta_utime);
-		account_user_time_scaled(p, delta_utime);
+		account_user_time(p, delta_utime, delta_utime);
 		ti->ac_utime = 0;
 	}
 }
diff --git a/arch/powerpc/kernel/time.c b/arch/powerpc/kernel/time.c
index e1f3a5140429..92650ccad2e1 100644
--- a/arch/powerpc/kernel/time.c
+++ b/arch/powerpc/kernel/time.c
@@ -256,8 +256,7 @@ void account_system_vtime(struct task_struct *tsk)
 		delta += sys_time;
 		get_paca()->system_time = 0;
 	}
-	account_system_time(tsk, 0, delta);
-	account_system_time_scaled(tsk, deltascaled);
+	account_system_time(tsk, 0, delta, deltascaled);
 	per_cpu(cputime_last_delta, smp_processor_id()) = delta;
 	per_cpu(cputime_scaled_last_delta, smp_processor_id()) = deltascaled;
 	local_irq_restore(flags);
@@ -275,10 +274,8 @@ void account_process_tick(struct task_struct *tsk, int user_tick)
 
 	utime = get_paca()->user_time;
 	get_paca()->user_time = 0;
-	account_user_time(tsk, utime);
-
 	utimescaled = cputime_to_scaled(utime);
-	account_user_time_scaled(tsk, utimescaled);
+	account_user_time(tsk, utime, utimescaled);
 }
 
 /*
diff --git a/arch/s390/kernel/vtime.c b/arch/s390/kernel/vtime.c
index 75a6e62ea973..07283aea2e56 100644
--- a/arch/s390/kernel/vtime.c
+++ b/arch/s390/kernel/vtime.c
@@ -50,12 +50,12 @@ void account_process_tick(struct task_struct *tsk, int user_tick)
 	rcu_user_flag = cputime != 0;
 	S390_lowcore.user_timer -= cputime << 12;
 	S390_lowcore.steal_clock -= cputime << 12;
-	account_user_time(tsk, cputime);
+	account_user_time(tsk, cputime, cputime);
 
 	cputime =  S390_lowcore.system_timer >> 12;
 	S390_lowcore.system_timer -= cputime << 12;
 	S390_lowcore.steal_clock -= cputime << 12;
-	account_system_time(tsk, HARDIRQ_OFFSET, cputime);
+	account_system_time(tsk, HARDIRQ_OFFSET, cputime, cputime);
 
 	cputime = S390_lowcore.steal_clock;
 	if ((__s64) cputime > 0) {
@@ -82,12 +82,12 @@ void account_vtime(struct task_struct *tsk)
 	cputime = S390_lowcore.user_timer >> 12;
 	S390_lowcore.user_timer -= cputime << 12;
 	S390_lowcore.steal_clock -= cputime << 12;
-	account_user_time(tsk, cputime);
+	account_user_time(tsk, cputime, cputime);
 
 	cputime =  S390_lowcore.system_timer >> 12;
 	S390_lowcore.system_timer -= cputime << 12;
 	S390_lowcore.steal_clock -= cputime << 12;
-	account_system_time(tsk, 0, cputime);
+	account_system_time(tsk, 0, cputime, cputime);
 }
 
 /*
@@ -107,7 +107,7 @@ void account_system_vtime(struct task_struct *tsk)
 	cputime =  S390_lowcore.system_timer >> 12;
 	S390_lowcore.system_timer -= cputime << 12;
 	S390_lowcore.steal_clock -= cputime << 12;
-	account_system_time(tsk, 0, cputime);
+	account_system_time(tsk, 0, cputime, cputime);
 }
 EXPORT_SYMBOL_GPL(account_system_vtime);
 
diff --git a/include/linux/kernel_stat.h b/include/linux/kernel_stat.h
index 4ee4b3d2316f..c78a459662a6 100644
--- a/include/linux/kernel_stat.h
+++ b/include/linux/kernel_stat.h
@@ -79,10 +79,8 @@ static inline unsigned int kstat_irqs(unsigned int irq)
 }
 
 extern unsigned long long task_delta_exec(struct task_struct *);
-extern void account_user_time(struct task_struct *, cputime_t);
-extern void account_user_time_scaled(struct task_struct *, cputime_t);
-extern void account_system_time(struct task_struct *, int, cputime_t);
-extern void account_system_time_scaled(struct task_struct *, cputime_t);
+extern void account_user_time(struct task_struct *, cputime_t, cputime_t);
+extern void account_system_time(struct task_struct *, int, cputime_t, cputime_t);
 extern void account_steal_time(struct task_struct *, cputime_t);
 
 #endif /* _LINUX_KERNEL_STAT_H */
diff --git a/kernel/sched.c b/kernel/sched.c
index fff1c4a20b65..5b03679ff712 100644
--- a/kernel/sched.c
+++ b/kernel/sched.c
@@ -4080,13 +4080,17 @@ unsigned long long task_delta_exec(struct task_struct *p)
  * Account user cpu time to a process.
  * @p: the process that the cpu time gets accounted to
  * @cputime: the cpu time spent in user space since the last update
+ * @cputime_scaled: cputime scaled by cpu frequency
  */
-void account_user_time(struct task_struct *p, cputime_t cputime)
+void account_user_time(struct task_struct *p, cputime_t cputime,
+		       cputime_t cputime_scaled)
 {
 	struct cpu_usage_stat *cpustat = &kstat_this_cpu.cpustat;
 	cputime64_t tmp;
 
+	/* Add user time to process. */
 	p->utime = cputime_add(p->utime, cputime);
+	p->utimescaled = cputime_add(p->utimescaled, cputime_scaled);
 	account_group_user_time(p, cputime);
 
 	/* Add user time to cpustat. */
@@ -4103,51 +4107,49 @@ void account_user_time(struct task_struct *p, cputime_t cputime)
  * Account guest cpu time to a process.
  * @p: the process that the cpu time gets accounted to
  * @cputime: the cpu time spent in virtual machine since the last update
+ * @cputime_scaled: cputime scaled by cpu frequency
  */
-static void account_guest_time(struct task_struct *p, cputime_t cputime)
+static void account_guest_time(struct task_struct *p, cputime_t cputime,
+			       cputime_t cputime_scaled)
 {
 	cputime64_t tmp;
 	struct cpu_usage_stat *cpustat = &kstat_this_cpu.cpustat;
 
 	tmp = cputime_to_cputime64(cputime);
 
+	/* Add guest time to process. */
 	p->utime = cputime_add(p->utime, cputime);
+	p->utimescaled = cputime_add(p->utimescaled, cputime_scaled);
 	account_group_user_time(p, cputime);
 	p->gtime = cputime_add(p->gtime, cputime);
 
+	/* Add guest time to cpustat. */
 	cpustat->user = cputime64_add(cpustat->user, tmp);
 	cpustat->guest = cputime64_add(cpustat->guest, tmp);
 }
 
-/*
- * Account scaled user cpu time to a process.
- * @p: the process that the cpu time gets accounted to
- * @cputime: the cpu time spent in user space since the last update
- */
-void account_user_time_scaled(struct task_struct *p, cputime_t cputime)
-{
-	p->utimescaled = cputime_add(p->utimescaled, cputime);
-}
-
 /*
  * Account system cpu time to a process.
  * @p: the process that the cpu time gets accounted to
  * @hardirq_offset: the offset to subtract from hardirq_count()
  * @cputime: the cpu time spent in kernel space since the last update
+ * @cputime_scaled: cputime scaled by cpu frequency
  */
 void account_system_time(struct task_struct *p, int hardirq_offset,
-			 cputime_t cputime)
+			 cputime_t cputime, cputime_t cputime_scaled)
 {
 	struct cpu_usage_stat *cpustat = &kstat_this_cpu.cpustat;
 	struct rq *rq = this_rq();
 	cputime64_t tmp;
 
 	if ((p->flags & PF_VCPU) && (irq_count() - hardirq_offset == 0)) {
-		account_guest_time(p, cputime);
+		account_guest_time(p, cputime, cputime_scaled);
 		return;
 	}
 
+	/* Add system time to process. */
 	p->stime = cputime_add(p->stime, cputime);
+	p->stimescaled = cputime_add(p->stimescaled, cputime_scaled);
 	account_group_system_time(p, cputime);
 
 	/* Add system time to cpustat. */
@@ -4166,17 +4168,6 @@ void account_system_time(struct task_struct *p, int hardirq_offset,
 	acct_update_integrals(p);
 }
 
-/*
- * Account scaled system cpu time to a process.
- * @p: the process that the cpu time gets accounted to
- * @hardirq_offset: the offset to subtract from hardirq_count()
- * @cputime: the cpu time spent in kernel space since the last update
- */
-void account_system_time_scaled(struct task_struct *p, cputime_t cputime)
-{
-	p->stimescaled = cputime_add(p->stimescaled, cputime);
-}
-
 /*
  * Account for involuntary wait time.
  * @p: the process from which the cpu time has been stolen
diff --git a/kernel/time/tick-sched.c b/kernel/time/tick-sched.c
index 8f3fc2582d38..1f2fce2479fe 100644
--- a/kernel/time/tick-sched.c
+++ b/kernel/time/tick-sched.c
@@ -420,6 +420,7 @@ void tick_nohz_restart_sched_tick(void)
 	int cpu = smp_processor_id();
 	struct tick_sched *ts = &per_cpu(tick_cpu_sched, cpu);
 	unsigned long ticks;
+	cputime_t cputime;
 	ktime_t now;
 
 	local_irq_disable();
@@ -452,8 +453,8 @@ void tick_nohz_restart_sched_tick(void)
 	 */
 	if (ticks && ticks < LONG_MAX) {
 		add_preempt_count(HARDIRQ_OFFSET);
-		account_system_time(current, HARDIRQ_OFFSET,
-				    jiffies_to_cputime(ticks));
+		cputime = jiffies_to_cputime(ticks);
+		account_system_time(current, HARDIRQ_OFFSET, cputime, cputime);
 		sub_preempt_count(HARDIRQ_OFFSET);
 	}
 
diff --git a/kernel/timer.c b/kernel/timer.c
index 566257d1dc10..b5efb528aa1d 100644
--- a/kernel/timer.c
+++ b/kernel/timer.c
@@ -1023,13 +1023,11 @@ void account_process_tick(struct task_struct *p, int user_tick)
 {
 	cputime_t one_jiffy = jiffies_to_cputime(1);
 
-	if (user_tick) {
-		account_user_time(p, one_jiffy);
-		account_user_time_scaled(p, cputime_to_scaled(one_jiffy));
-	} else {
-		account_system_time(p, HARDIRQ_OFFSET, one_jiffy);
-		account_system_time_scaled(p, cputime_to_scaled(one_jiffy));
-	}
+	if (user_tick)
+		account_user_time(p, one_jiffy, cputime_to_scaled(one_jiffy));
+	else
+		account_system_time(p, HARDIRQ_OFFSET, one_jiffy,
+				    cputime_to_scaled(one_jiffy));
 }
 #endif
 
-- 
cgit v1.2.3-71-gd317


From 79741dd35713ff4f6fd0eafd59fa94e8a4ba922d Mon Sep 17 00:00:00 2001
From: Martin Schwidefsky <schwidefsky@de.ibm.com>
Date: Wed, 31 Dec 2008 15:11:38 +0100
Subject: [PATCH] idle cputime accounting

The cpu time spent by the idle process actually doing something is
currently accounted as idle time. This is plain wrong, the architectures
that support VIRT_CPU_ACCOUNTING=y can do better: distinguish between the
time spent doing nothing and the time spent by idle doing work. The first
is accounted with account_idle_time and the second with account_system_time.
The architectures that use the account_xxx_time interface directly and not
the account_xxx_ticks interface now need to do the check for the idle
process in their arch code. In particular to improve the system vs true
idle time accounting the arch code needs to measure the true idle time
instead of just testing for the idle process.
To improve the tick based accounting as well we would need an architecture
primitive that can tell us if the pt_regs of the interrupted context
points to the magic instruction that halts the cpu.

In addition idle time is no more added to the stime of the idle process.
This field now contains the system time of the idle process as it should
be. On systems without VIRT_CPU_ACCOUNTING this will always be zero as
every tick that occurs while idle is running will be accounted as idle
time.

This patch contains the necessary common code changes to be able to
distinguish idle system time and true idle time. The architectures with
support for VIRT_CPU_ACCOUNTING need some changes to exploit this.

Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com>
---
 arch/ia64/kernel/time.c       | 10 ++++--
 arch/powerpc/kernel/process.c |  1 +
 arch/powerpc/kernel/time.c    | 13 +++++--
 arch/s390/kernel/vtime.c      | 20 ++++++++---
 arch/x86/xen/time.c           | 10 +++---
 include/linux/kernel_stat.h   |  7 +++-
 include/linux/sched.h         |  1 -
 kernel/sched.c                | 80 ++++++++++++++++++++++++++++++++++---------
 kernel/time/tick-sched.c      | 13 ++++---
 kernel/timer.c                | 13 -------
 10 files changed, 114 insertions(+), 54 deletions(-)

(limited to 'kernel/timer.c')

diff --git a/arch/ia64/kernel/time.c b/arch/ia64/kernel/time.c
index 4ee367817049..f0ebb342409d 100644
--- a/arch/ia64/kernel/time.c
+++ b/arch/ia64/kernel/time.c
@@ -93,7 +93,10 @@ void ia64_account_on_switch(struct task_struct *prev, struct task_struct *next)
 	now = ia64_get_itc();
 
 	delta_stime = cycle_to_cputime(pi->ac_stime + (now - pi->ac_stamp));
-	account_system_time(prev, 0, delta_stime, delta_stime);
+	if (idle_task(smp_processor_id()) != prev)
+		account_system_time(prev, 0, delta_stime, delta_stime);
+	else
+		account_idle_time(delta_stime);
 
 	if (pi->ac_utime) {
 		delta_utime = cycle_to_cputime(pi->ac_utime);
@@ -120,7 +123,10 @@ void account_system_vtime(struct task_struct *tsk)
 	now = ia64_get_itc();
 
 	delta_stime = cycle_to_cputime(ti->ac_stime + (now - ti->ac_stamp));
-	account_system_time(tsk, 0, delta_stime, delta_stime);
+	if (irq_count() || idle_task(smp_processor_id()) != tsk)
+		account_system_time(tsk, 0, delta_stime, delta_stime);
+	else
+		account_idle_time(delta_stime);
 	ti->ac_stime = 0;
 
 	ti->ac_stamp = now;
diff --git a/arch/powerpc/kernel/process.c b/arch/powerpc/kernel/process.c
index 51b201ddf9a1..fb7049c054c0 100644
--- a/arch/powerpc/kernel/process.c
+++ b/arch/powerpc/kernel/process.c
@@ -33,6 +33,7 @@
 #include <linux/mqueue.h>
 #include <linux/hardirq.h>
 #include <linux/utsname.h>
+#include <linux/kernel_stat.h>
 
 #include <asm/pgtable.h>
 #include <asm/uaccess.h>
diff --git a/arch/powerpc/kernel/time.c b/arch/powerpc/kernel/time.c
index 92650ccad2e1..3be355c1cfa7 100644
--- a/arch/powerpc/kernel/time.c
+++ b/arch/powerpc/kernel/time.c
@@ -256,7 +256,10 @@ void account_system_vtime(struct task_struct *tsk)
 		delta += sys_time;
 		get_paca()->system_time = 0;
 	}
-	account_system_time(tsk, 0, delta, deltascaled);
+	if (in_irq() || idle_task(smp_processor_id()) != tsk)
+		account_system_time(tsk, 0, delta, deltascaled);
+	else
+		account_idle_time(delta);
 	per_cpu(cputime_last_delta, smp_processor_id()) = delta;
 	per_cpu(cputime_scaled_last_delta, smp_processor_id()) = deltascaled;
 	local_irq_restore(flags);
@@ -335,8 +338,12 @@ void calculate_steal_time(void)
 	tb = mftb();
 	purr = mfspr(SPRN_PURR);
 	stolen = (tb - pme->tb) - (purr - pme->purr);
-	if (stolen > 0)
-		account_steal_time(current, stolen);
+	if (stolen > 0) {
+		if (idle_task(smp_processor_id()) != current)
+			account_steal_time(stolen);
+		else
+			account_idle_time(stolen);
+	}
 	pme->tb = tb;
 	pme->purr = purr;
 }
diff --git a/arch/s390/kernel/vtime.c b/arch/s390/kernel/vtime.c
index 07283aea2e56..4a4a34caec55 100644
--- a/arch/s390/kernel/vtime.c
+++ b/arch/s390/kernel/vtime.c
@@ -55,13 +55,19 @@ void account_process_tick(struct task_struct *tsk, int user_tick)
 	cputime =  S390_lowcore.system_timer >> 12;
 	S390_lowcore.system_timer -= cputime << 12;
 	S390_lowcore.steal_clock -= cputime << 12;
-	account_system_time(tsk, HARDIRQ_OFFSET, cputime, cputime);
+	if (idle_task(smp_processor_id()) != current)
+		account_system_time(tsk, HARDIRQ_OFFSET, cputime, cputime);
+	else
+		account_idle_time(cputime);
 
 	cputime = S390_lowcore.steal_clock;
 	if ((__s64) cputime > 0) {
 		cputime >>= 12;
 		S390_lowcore.steal_clock -= cputime << 12;
-		account_steal_time(tsk, cputime);
+		if (idle_task(smp_processor_id()) != current)
+			account_steal_time(cputime);
+		else
+			account_idle_time(cputime);
 	}
 }
 
@@ -87,7 +93,10 @@ void account_vtime(struct task_struct *tsk)
 	cputime =  S390_lowcore.system_timer >> 12;
 	S390_lowcore.system_timer -= cputime << 12;
 	S390_lowcore.steal_clock -= cputime << 12;
-	account_system_time(tsk, 0, cputime, cputime);
+	if (idle_task(smp_processor_id()) != current)
+		account_system_time(tsk, 0, cputime, cputime);
+	else
+		account_idle_time(cputime);
 }
 
 /*
@@ -107,7 +116,10 @@ void account_system_vtime(struct task_struct *tsk)
 	cputime =  S390_lowcore.system_timer >> 12;
 	S390_lowcore.system_timer -= cputime << 12;
 	S390_lowcore.steal_clock -= cputime << 12;
-	account_system_time(tsk, 0, cputime, cputime);
+	if (in_irq() || idle_task(smp_processor_id()) != current)
+		account_system_time(tsk, 0, cputime, cputime);
+	else
+		account_idle_time(cputime);
 }
 EXPORT_SYMBOL_GPL(account_system_vtime);
 
diff --git a/arch/x86/xen/time.c b/arch/x86/xen/time.c
index c9f7cda48ed7..732e52dc991a 100644
--- a/arch/x86/xen/time.c
+++ b/arch/x86/xen/time.c
@@ -132,8 +132,7 @@ static void do_stolen_accounting(void)
 	*snap = state;
 
 	/* Add the appropriate number of ticks of stolen time,
-	   including any left-overs from last time.  Passing NULL to
-	   account_steal_time accounts the time as stolen. */
+	   including any left-overs from last time. */
 	stolen = runnable + offline + __get_cpu_var(residual_stolen);
 
 	if (stolen < 0)
@@ -141,11 +140,10 @@ static void do_stolen_accounting(void)
 
 	ticks = iter_div_u64_rem(stolen, NS_PER_TICK, &stolen);
 	__get_cpu_var(residual_stolen) = stolen;
-	account_steal_time(NULL, ticks);
+	account_steal_ticks(ticks);
 
 	/* Add the appropriate number of ticks of blocked time,
-	   including any left-overs from last time.  Passing idle to
-	   account_steal_time accounts the time as idle/wait. */
+	   including any left-overs from last time. */
 	blocked += __get_cpu_var(residual_blocked);
 
 	if (blocked < 0)
@@ -153,7 +151,7 @@ static void do_stolen_accounting(void)
 
 	ticks = iter_div_u64_rem(blocked, NS_PER_TICK, &blocked);
 	__get_cpu_var(residual_blocked) = blocked;
-	account_steal_time(idle_task(smp_processor_id()), ticks);
+	account_idle_ticks(ticks);
 }
 
 /*
diff --git a/include/linux/kernel_stat.h b/include/linux/kernel_stat.h
index c78a459662a6..570d20413119 100644
--- a/include/linux/kernel_stat.h
+++ b/include/linux/kernel_stat.h
@@ -81,6 +81,11 @@ static inline unsigned int kstat_irqs(unsigned int irq)
 extern unsigned long long task_delta_exec(struct task_struct *);
 extern void account_user_time(struct task_struct *, cputime_t, cputime_t);
 extern void account_system_time(struct task_struct *, int, cputime_t, cputime_t);
-extern void account_steal_time(struct task_struct *, cputime_t);
+extern void account_steal_time(cputime_t);
+extern void account_idle_time(cputime_t);
+
+extern void account_process_tick(struct task_struct *, int user);
+extern void account_steal_ticks(unsigned long ticks);
+extern void account_idle_ticks(unsigned long ticks);
 
 #endif /* _LINUX_KERNEL_STAT_H */
diff --git a/include/linux/sched.h b/include/linux/sched.h
index 8395e715809d..b475d4db8053 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -284,7 +284,6 @@ long io_schedule_timeout(long timeout);
 
 extern void cpu_init (void);
 extern void trap_init(void);
-extern void account_process_tick(struct task_struct *task, int user);
 extern void update_process_times(int user);
 extern void scheduler_tick(void);
 
diff --git a/kernel/sched.c b/kernel/sched.c
index 5b03679ff712..635eaffe1e4c 100644
--- a/kernel/sched.c
+++ b/kernel/sched.c
@@ -4139,7 +4139,6 @@ void account_system_time(struct task_struct *p, int hardirq_offset,
 			 cputime_t cputime, cputime_t cputime_scaled)
 {
 	struct cpu_usage_stat *cpustat = &kstat_this_cpu.cpustat;
-	struct rq *rq = this_rq();
 	cputime64_t tmp;
 
 	if ((p->flags & PF_VCPU) && (irq_count() - hardirq_offset == 0)) {
@@ -4158,37 +4157,84 @@ void account_system_time(struct task_struct *p, int hardirq_offset,
 		cpustat->irq = cputime64_add(cpustat->irq, tmp);
 	else if (softirq_count())
 		cpustat->softirq = cputime64_add(cpustat->softirq, tmp);
-	else if (p != rq->idle)
-		cpustat->system = cputime64_add(cpustat->system, tmp);
-	else if (atomic_read(&rq->nr_iowait) > 0)
-		cpustat->iowait = cputime64_add(cpustat->iowait, tmp);
 	else
-		cpustat->idle = cputime64_add(cpustat->idle, tmp);
+		cpustat->system = cputime64_add(cpustat->system, tmp);
+
 	/* Account for system time used */
 	acct_update_integrals(p);
 }
 
 /*
  * Account for involuntary wait time.
- * @p: the process from which the cpu time has been stolen
  * @steal: the cpu time spent in involuntary wait
  */
-void account_steal_time(struct task_struct *p, cputime_t steal)
+void account_steal_time(cputime_t cputime)
+{
+	struct cpu_usage_stat *cpustat = &kstat_this_cpu.cpustat;
+	cputime64_t cputime64 = cputime_to_cputime64(cputime);
+
+	cpustat->steal = cputime64_add(cpustat->steal, cputime64);
+}
+
+/*
+ * Account for idle time.
+ * @cputime: the cpu time spent in idle wait
+ */
+void account_idle_time(cputime_t cputime)
 {
 	struct cpu_usage_stat *cpustat = &kstat_this_cpu.cpustat;
-	cputime64_t tmp = cputime_to_cputime64(steal);
+	cputime64_t cputime64 = cputime_to_cputime64(cputime);
 	struct rq *rq = this_rq();
 
-	if (p == rq->idle) {
-		p->stime = cputime_add(p->stime, steal);
-		if (atomic_read(&rq->nr_iowait) > 0)
-			cpustat->iowait = cputime64_add(cpustat->iowait, tmp);
-		else
-			cpustat->idle = cputime64_add(cpustat->idle, tmp);
-	} else
-		cpustat->steal = cputime64_add(cpustat->steal, tmp);
+	if (atomic_read(&rq->nr_iowait) > 0)
+		cpustat->iowait = cputime64_add(cpustat->iowait, cputime64);
+	else
+		cpustat->idle = cputime64_add(cpustat->idle, cputime64);
+}
+
+#ifndef CONFIG_VIRT_CPU_ACCOUNTING
+
+/*
+ * Account a single tick of cpu time.
+ * @p: the process that the cpu time gets accounted to
+ * @user_tick: indicates if the tick is a user or a system tick
+ */
+void account_process_tick(struct task_struct *p, int user_tick)
+{
+	cputime_t one_jiffy = jiffies_to_cputime(1);
+	cputime_t one_jiffy_scaled = cputime_to_scaled(one_jiffy);
+	struct rq *rq = this_rq();
+
+	if (user_tick)
+		account_user_time(p, one_jiffy, one_jiffy_scaled);
+	else if (p != rq->idle)
+		account_system_time(p, HARDIRQ_OFFSET, one_jiffy,
+				    one_jiffy_scaled);
+	else
+		account_idle_time(one_jiffy);
+}
+
+/*
+ * Account multiple ticks of steal time.
+ * @p: the process from which the cpu time has been stolen
+ * @ticks: number of stolen ticks
+ */
+void account_steal_ticks(unsigned long ticks)
+{
+	account_steal_time(jiffies_to_cputime(ticks));
+}
+
+/*
+ * Account multiple ticks of idle time.
+ * @ticks: number of stolen ticks
+ */
+void account_idle_ticks(unsigned long ticks)
+{
+	account_idle_time(jiffies_to_cputime(ticks));
 }
 
+#endif
+
 /*
  * Use precise platform statistics if available:
  */
diff --git a/kernel/time/tick-sched.c b/kernel/time/tick-sched.c
index 1f2fce2479fe..611fa4c0baab 100644
--- a/kernel/time/tick-sched.c
+++ b/kernel/time/tick-sched.c
@@ -419,8 +419,9 @@ void tick_nohz_restart_sched_tick(void)
 {
 	int cpu = smp_processor_id();
 	struct tick_sched *ts = &per_cpu(tick_cpu_sched, cpu);
+#ifndef CONFIG_VIRT_CPU_ACCOUNTING
 	unsigned long ticks;
-	cputime_t cputime;
+#endif
 	ktime_t now;
 
 	local_irq_disable();
@@ -442,6 +443,7 @@ void tick_nohz_restart_sched_tick(void)
 	tick_do_update_jiffies64(now);
 	cpu_clear(cpu, nohz_cpu_mask);
 
+#ifndef CONFIG_VIRT_CPU_ACCOUNTING
 	/*
 	 * We stopped the tick in idle. Update process times would miss the
 	 * time we slept as update_process_times does only a 1 tick
@@ -451,12 +453,9 @@ void tick_nohz_restart_sched_tick(void)
 	/*
 	 * We might be one off. Do not randomly account a huge number of ticks!
 	 */
-	if (ticks && ticks < LONG_MAX) {
-		add_preempt_count(HARDIRQ_OFFSET);
-		cputime = jiffies_to_cputime(ticks);
-		account_system_time(current, HARDIRQ_OFFSET, cputime, cputime);
-		sub_preempt_count(HARDIRQ_OFFSET);
-	}
+	if (ticks && ticks < LONG_MAX)
+		account_idle_ticks(ticks);
+#endif
 
 	touch_softlockup_watchdog();
 	/*
diff --git a/kernel/timer.c b/kernel/timer.c
index b5efb528aa1d..dee3f641a7a7 100644
--- a/kernel/timer.c
+++ b/kernel/timer.c
@@ -1018,19 +1018,6 @@ unsigned long get_next_timer_interrupt(unsigned long now)
 }
 #endif
 
-#ifndef CONFIG_VIRT_CPU_ACCOUNTING
-void account_process_tick(struct task_struct *p, int user_tick)
-{
-	cputime_t one_jiffy = jiffies_to_cputime(1);
-
-	if (user_tick)
-		account_user_time(p, one_jiffy, cputime_to_scaled(one_jiffy));
-	else
-		account_system_time(p, HARDIRQ_OFFSET, one_jiffy,
-				    cputime_to_scaled(one_jiffy));
-}
-#endif
-
 /*
  * Called from the timer interrupt handler to charge one tick to the current
  * process.  user_tick is 1 if the tick is user time, 0 for system.
-- 
cgit v1.2.3-71-gd317


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/timer.c')

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 v1.2.3-71-gd317


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/timer.c')

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 v1.2.3-71-gd317


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/timer.c')

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 v1.2.3-71-gd317


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/timer.c')

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 v1.2.3-71-gd317