From c9d557c19f94df42db78d4a5de4d25feee694bad Mon Sep 17 00:00:00 2001
From: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com>
Date: Wed, 7 Jan 2009 14:33:30 -0800
Subject: rcu: fix bug in rcutorture system-shutdown code

This patch fixes an rcutorture bug found by Eric Sesterhenn that
resulted in oopses in response to "rmmod rcutorture".  The problem
was in some new code that attempted to handle the case where a system
is shut down while rcutorture is still running, for example, when
rcutorture is built into the kernel so that it cannot be removed.
The fix causes the rcutorture threads to "park" in an
schedule_timeout_uninterruptible(MAX_SCHEDULE_TIMEOUT) rather than
trying to get them to terminate cleanly.  Concurrent shutdown and
rmmod is illegal.

I believe that this is 2.6.29 material, as it is used in some testing
setups.

For reference, here are the rcutorture operating modes:

CONFIG_RCU_TORTURE_TEST=m

	This is the normal rcutorture build.  Use "modprobe rcutorture"
	(with optional arguments) to start, and "rmmod rcutorture" to
	stop.  If you shut the system down without doing the rmmod, you
	should see console output like:

	rcutorture thread rcu_torture_writer parking due to system shutdown

	One for each rcutorture kthread.

CONFIG_RCU_TORTURE_TEST=y
CONFIG_RCU_TORTURE_TEST_RUNNABLE=n

	Use this if you want rcutorture built in, but don't want the
	test to start running during early boot.  To start the
	torturing:

		echo 1 > /proc/sys/kernel/rcutorture_runnable

	To stop the torturing, s/1/0/

	You will get "parking" console messages as noted above when
	you shut the system down.

CONFIG_RCU_TORTURE_TEST=y
CONFIG_RCU_TORTURE_TEST_RUNNABLE=y

	Same as above, except that the torturing starts during early
	boot.  Only for the stout of heart and strong of stomach.
	The same /proc entry noted above may be used to control the
	test.

Located-by: Eric Sesterhenn <snakebyte@gmx.de>
Tested-by: Eric Sesterhenn <snakebyte@gmx.de>
Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
---
 kernel/rcutorture.c | 113 +++++++++++++++++++++++++++++++---------------------
 1 file changed, 68 insertions(+), 45 deletions(-)

(limited to 'kernel')

diff --git a/kernel/rcutorture.c b/kernel/rcutorture.c
index 1cff28db56b..7c4142a79f0 100644
--- a/kernel/rcutorture.c
+++ b/kernel/rcutorture.c
@@ -136,28 +136,46 @@ static int stutter_pause_test = 0;
 #endif
 int rcutorture_runnable = RCUTORTURE_RUNNABLE_INIT;
 
-#define FULLSTOP_SHUTDOWN 1	/* Bail due to system shutdown/panic. */
-#define FULLSTOP_CLEANUP  2	/* Orderly shutdown. */
-static int fullstop;		/* stop generating callbacks at test end. */
-DEFINE_MUTEX(fullstop_mutex);	/* protect fullstop transitions and */
-				/*  spawning of kthreads. */
+/* Mediate rmmod and system shutdown.  Concurrent rmmod & shutdown illegal! */
+
+#define FULLSTOP_DONTSTOP 0	/* Normal operation. */
+#define FULLSTOP_SHUTDOWN 1	/* System shutdown with rcutorture running. */
+#define FULLSTOP_RMMOD    2	/* Normal rmmod of rcutorture. */
+static int fullstop = FULLSTOP_RMMOD;
+DEFINE_MUTEX(fullstop_mutex);	/* Protect fullstop transitions and spawning */
+				/*  of kthreads. */
 
 /*
- * Detect and respond to a signal-based shutdown.
+ * Detect and respond to a system shutdown.
  */
 static int
 rcutorture_shutdown_notify(struct notifier_block *unused1,
 			   unsigned long unused2, void *unused3)
 {
-	if (fullstop)
-		return NOTIFY_DONE;
 	mutex_lock(&fullstop_mutex);
-	if (!fullstop)
+	if (fullstop == FULLSTOP_DONTSTOP)
 		fullstop = FULLSTOP_SHUTDOWN;
+	else
+		printk(KERN_WARNING /* but going down anyway, so... */
+		       "Concurrent 'rmmod rcutorture' and shutdown illegal!\n");
 	mutex_unlock(&fullstop_mutex);
 	return NOTIFY_DONE;
 }
 
+/*
+ * Absorb kthreads into a kernel function that won't return, so that
+ * they won't ever access module text or data again.
+ */
+static void rcutorture_shutdown_absorb(char *title)
+{
+	if (ACCESS_ONCE(fullstop) == FULLSTOP_SHUTDOWN) {
+		printk(KERN_NOTICE
+		       "rcutorture thread %s parking due to system shutdown\n",
+		       title);
+		schedule_timeout_uninterruptible(MAX_SCHEDULE_TIMEOUT);
+	}
+}
+
 /*
  * Allocate an element from the rcu_tortures pool.
  */
@@ -219,13 +237,14 @@ rcu_random(struct rcu_random_state *rrsp)
 }
 
 static void
-rcu_stutter_wait(void)
+rcu_stutter_wait(char *title)
 {
-	while ((stutter_pause_test || !rcutorture_runnable) && !fullstop) {
+	while (stutter_pause_test || !rcutorture_runnable) {
 		if (rcutorture_runnable)
 			schedule_timeout_interruptible(1);
 		else
 			schedule_timeout_interruptible(round_jiffies_relative(HZ));
+		rcutorture_shutdown_absorb(title);
 	}
 }
 
@@ -287,7 +306,7 @@ rcu_torture_cb(struct rcu_head *p)
 	int i;
 	struct rcu_torture *rp = container_of(p, struct rcu_torture, rtort_rcu);
 
-	if (fullstop) {
+	if (fullstop != FULLSTOP_DONTSTOP) {
 		/* Test is ending, just drop callbacks on the floor. */
 		/* The next initialization will pick up the pieces. */
 		return;
@@ -619,10 +638,11 @@ rcu_torture_writer(void *arg)
 		}
 		rcu_torture_current_version++;
 		oldbatch = cur_ops->completed();
-		rcu_stutter_wait();
-	} while (!kthread_should_stop() && !fullstop);
+		rcu_stutter_wait("rcu_torture_writer");
+	} while (!kthread_should_stop() && fullstop == FULLSTOP_DONTSTOP);
 	VERBOSE_PRINTK_STRING("rcu_torture_writer task stopping");
-	while (!kthread_should_stop() && fullstop != FULLSTOP_SHUTDOWN)
+	rcutorture_shutdown_absorb("rcu_torture_writer");
+	while (!kthread_should_stop())
 		schedule_timeout_uninterruptible(1);
 	return 0;
 }
@@ -643,11 +663,12 @@ rcu_torture_fakewriter(void *arg)
 		schedule_timeout_uninterruptible(1 + rcu_random(&rand)%10);
 		udelay(rcu_random(&rand) & 0x3ff);
 		cur_ops->sync();
-		rcu_stutter_wait();
-	} while (!kthread_should_stop() && !fullstop);
+		rcu_stutter_wait("rcu_torture_fakewriter");
+	} while (!kthread_should_stop() && fullstop == FULLSTOP_DONTSTOP);
 
 	VERBOSE_PRINTK_STRING("rcu_torture_fakewriter task stopping");
-	while (!kthread_should_stop() && fullstop != FULLSTOP_SHUTDOWN)
+	rcutorture_shutdown_absorb("rcu_torture_fakewriter");
+	while (!kthread_should_stop())
 		schedule_timeout_uninterruptible(1);
 	return 0;
 }
@@ -752,12 +773,13 @@ rcu_torture_reader(void *arg)
 		preempt_enable();
 		cur_ops->readunlock(idx);
 		schedule();
-		rcu_stutter_wait();
-	} while (!kthread_should_stop() && !fullstop);
+		rcu_stutter_wait("rcu_torture_reader");
+	} while (!kthread_should_stop() && fullstop == FULLSTOP_DONTSTOP);
 	VERBOSE_PRINTK_STRING("rcu_torture_reader task stopping");
+	rcutorture_shutdown_absorb("rcu_torture_reader");
 	if (irqreader && cur_ops->irqcapable)
 		del_timer_sync(&t);
-	while (!kthread_should_stop() && fullstop != FULLSTOP_SHUTDOWN)
+	while (!kthread_should_stop())
 		schedule_timeout_uninterruptible(1);
 	return 0;
 }
@@ -854,7 +876,8 @@ rcu_torture_stats(void *arg)
 	do {
 		schedule_timeout_interruptible(stat_interval * HZ);
 		rcu_torture_stats_print();
-	} while (!kthread_should_stop() && !fullstop);
+		rcutorture_shutdown_absorb("rcu_torture_stats");
+	} while (!kthread_should_stop());
 	VERBOSE_PRINTK_STRING("rcu_torture_stats task stopping");
 	return 0;
 }
@@ -866,52 +889,49 @@ static int rcu_idle_cpu;	/* Force all torture tasks off this CPU */
  */
 static void rcu_torture_shuffle_tasks(void)
 {
-	cpumask_var_t tmp_mask;
+	cpumask_t tmp_mask;
 	int i;
 
-	if (!alloc_cpumask_var(&tmp_mask, GFP_KERNEL))
-		BUG();
-
-	cpumask_setall(tmp_mask);
+	cpus_setall(tmp_mask);
 	get_online_cpus();
 
 	/* No point in shuffling if there is only one online CPU (ex: UP) */
-	if (num_online_cpus() == 1)
-		goto out;
+	if (num_online_cpus() == 1) {
+		put_online_cpus();
+		return;
+	}
 
 	if (rcu_idle_cpu != -1)
-		cpumask_clear_cpu(rcu_idle_cpu, tmp_mask);
+		cpu_clear(rcu_idle_cpu, tmp_mask);
 
-	set_cpus_allowed_ptr(current, tmp_mask);
+	set_cpus_allowed_ptr(current, &tmp_mask);
 
 	if (reader_tasks) {
 		for (i = 0; i < nrealreaders; i++)
 			if (reader_tasks[i])
 				set_cpus_allowed_ptr(reader_tasks[i],
-						     tmp_mask);
+						     &tmp_mask);
 	}
 
 	if (fakewriter_tasks) {
 		for (i = 0; i < nfakewriters; i++)
 			if (fakewriter_tasks[i])
 				set_cpus_allowed_ptr(fakewriter_tasks[i],
-						     tmp_mask);
+						     &tmp_mask);
 	}
 
 	if (writer_task)
-		set_cpus_allowed_ptr(writer_task, tmp_mask);
+		set_cpus_allowed_ptr(writer_task, &tmp_mask);
 
 	if (stats_task)
-		set_cpus_allowed_ptr(stats_task, tmp_mask);
+		set_cpus_allowed_ptr(stats_task, &tmp_mask);
 
 	if (rcu_idle_cpu == -1)
 		rcu_idle_cpu = num_online_cpus() - 1;
 	else
 		rcu_idle_cpu--;
 
-out:
 	put_online_cpus();
-	free_cpumask_var(tmp_mask);
 }
 
 /* Shuffle tasks across CPUs, with the intent of allowing each CPU in the
@@ -925,7 +945,8 @@ rcu_torture_shuffle(void *arg)
 	do {
 		schedule_timeout_interruptible(shuffle_interval * HZ);
 		rcu_torture_shuffle_tasks();
-	} while (!kthread_should_stop() && !fullstop);
+		rcutorture_shutdown_absorb("rcu_torture_shuffle");
+	} while (!kthread_should_stop());
 	VERBOSE_PRINTK_STRING("rcu_torture_shuffle task stopping");
 	return 0;
 }
@@ -940,10 +961,11 @@ rcu_torture_stutter(void *arg)
 	do {
 		schedule_timeout_interruptible(stutter * HZ);
 		stutter_pause_test = 1;
-		if (!kthread_should_stop() && !fullstop)
+		if (!kthread_should_stop())
 			schedule_timeout_interruptible(stutter * HZ);
 		stutter_pause_test = 0;
-	} while (!kthread_should_stop() && !fullstop);
+		rcutorture_shutdown_absorb("rcu_torture_stutter");
+	} while (!kthread_should_stop());
 	VERBOSE_PRINTK_STRING("rcu_torture_stutter task stopping");
 	return 0;
 }
@@ -970,15 +992,16 @@ rcu_torture_cleanup(void)
 	int i;
 
 	mutex_lock(&fullstop_mutex);
-	if (!fullstop) {
-		/* If being signaled, let it happen, then exit. */
+	if (fullstop == FULLSTOP_SHUTDOWN) {
+		printk(KERN_WARNING /* but going down anyway, so... */
+		       "Concurrent 'rmmod rcutorture' and shutdown illegal!\n");
 		mutex_unlock(&fullstop_mutex);
-		schedule_timeout_interruptible(10 * HZ);
+		schedule_timeout_uninterruptible(10);
 		if (cur_ops->cb_barrier != NULL)
 			cur_ops->cb_barrier();
 		return;
 	}
-	fullstop = FULLSTOP_CLEANUP;
+	fullstop = FULLSTOP_RMMOD;
 	mutex_unlock(&fullstop_mutex);
 	unregister_reboot_notifier(&rcutorture_nb);
 	if (stutter_task) {
@@ -1078,7 +1101,7 @@ rcu_torture_init(void)
 	else
 		nrealreaders = 2 * num_online_cpus();
 	rcu_torture_print_module_parms("Start of test");
-	fullstop = 0;
+	fullstop = FULLSTOP_DONTSTOP;
 
 	/* Set up the freelist. */
 
-- 
cgit v1.2.3-70-g09d2


From 62ea9ceb17a74bc7544211bfeecf4170c554ac4f Mon Sep 17 00:00:00 2001
From: Rusty Russell <rusty@rustcorp.com.au>
Date: Sun, 11 Jan 2009 01:04:16 +0100
Subject: cpumask: fix CONFIG_NUMA=y sched.c

Impact: fix panic on ia64 with NR_CPUS=1024

struct sched_domain is now a dangling structure; where we really want
static ones, we need to use static_sched_domain.

(As the FIXME in this file says, cpumask_var_t would be better, but
this code is hairy enough without trying to add initialization code to
the right places).

Reported-by: Mike Travis <travis@sgi.com>
Signed-off-by: Rusty Russell <rusty@rustcorp.com.au>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
---
 kernel/sched.c | 10 +++++-----
 1 file changed, 5 insertions(+), 5 deletions(-)

(limited to 'kernel')

diff --git a/kernel/sched.c b/kernel/sched.c
index deb5ac8c12f..f0c0a81d763 100644
--- a/kernel/sched.c
+++ b/kernel/sched.c
@@ -7282,10 +7282,10 @@ cpu_to_phys_group(int cpu, const struct cpumask *cpu_map,
  * groups, so roll our own. Now each node has its own list of groups which
  * gets dynamically allocated.
  */
-static DEFINE_PER_CPU(struct sched_domain, node_domains);
+static DEFINE_PER_CPU(struct static_sched_domain, node_domains);
 static struct sched_group ***sched_group_nodes_bycpu;
 
-static DEFINE_PER_CPU(struct sched_domain, allnodes_domains);
+static DEFINE_PER_CPU(struct static_sched_domain, allnodes_domains);
 static DEFINE_PER_CPU(struct static_sched_group, sched_group_allnodes);
 
 static int cpu_to_allnodes_group(int cpu, const struct cpumask *cpu_map,
@@ -7560,7 +7560,7 @@ static int __build_sched_domains(const struct cpumask *cpu_map,
 #ifdef CONFIG_NUMA
 		if (cpumask_weight(cpu_map) >
 				SD_NODES_PER_DOMAIN*cpumask_weight(nodemask)) {
-			sd = &per_cpu(allnodes_domains, i);
+			sd = &per_cpu(allnodes_domains, i).sd;
 			SD_INIT(sd, ALLNODES);
 			set_domain_attribute(sd, attr);
 			cpumask_copy(sched_domain_span(sd), cpu_map);
@@ -7570,7 +7570,7 @@ static int __build_sched_domains(const struct cpumask *cpu_map,
 		} else
 			p = NULL;
 
-		sd = &per_cpu(node_domains, i);
+		sd = &per_cpu(node_domains, i).sd;
 		SD_INIT(sd, NODE);
 		set_domain_attribute(sd, attr);
 		sched_domain_node_span(cpu_to_node(i), sched_domain_span(sd));
@@ -7688,7 +7688,7 @@ static int __build_sched_domains(const struct cpumask *cpu_map,
 		for_each_cpu(j, nodemask) {
 			struct sched_domain *sd;
 
-			sd = &per_cpu(node_domains, j);
+			sd = &per_cpu(node_domains, j).sd;
 			sd->groups = sg;
 		}
 		sg->__cpu_power = 0;
-- 
cgit v1.2.3-70-g09d2


From 805194c35b91999b139e4d6b6145f4f84fd4c814 Mon Sep 17 00:00:00 2001
From: Li Zefan <lizf@cn.fujitsu.com>
Date: Sat, 10 Jan 2009 15:43:15 +0800
Subject: sched: partly revert "sched debug: remove NULL checking in
 print_cfs_rt_rq()"

Impact: avoid accessing NULL tg.css->cgroup

In commit 0a0db8f5c9d4bbb9bbfcc2b6cb6bce2d0ef4d73d, I removed checking
NULL tg.css->cgroup, but I realized I was wrong when I found reading
/proc/sched_debug can race with cgroup_create().

Signed-off-by: Li Zefan <lizf@cn.fujitsu.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
---
 kernel/sched_debug.c | 21 +++++++++++++++++----
 1 file changed, 17 insertions(+), 4 deletions(-)

(limited to 'kernel')

diff --git a/kernel/sched_debug.c b/kernel/sched_debug.c
index 4293cfa9681..16eeba4e416 100644
--- a/kernel/sched_debug.c
+++ b/kernel/sched_debug.c
@@ -145,6 +145,19 @@ static void print_rq(struct seq_file *m, struct rq *rq, int rq_cpu)
 	read_unlock_irqrestore(&tasklist_lock, flags);
 }
 
+#if defined(CONFIG_CGROUP_SCHED) && \
+	(defined(CONFIG_FAIR_GROUP_SCHED) || defined(CONFIG_RT_GROUP_SCHED))
+static void task_group_path(struct task_group *tg, char *buf, int buflen)
+{
+	/* may be NULL if the underlying cgroup isn't fully-created yet */
+	if (!tg->css.cgroup) {
+		buf[0] = '\0';
+		return;
+	}
+	cgroup_path(tg->css.cgroup, buf, buflen);
+}
+#endif
+
 void print_cfs_rq(struct seq_file *m, int cpu, struct cfs_rq *cfs_rq)
 {
 	s64 MIN_vruntime = -1, min_vruntime, max_vruntime = -1,
@@ -154,10 +167,10 @@ void print_cfs_rq(struct seq_file *m, int cpu, struct cfs_rq *cfs_rq)
 	unsigned long flags;
 
 #if defined(CONFIG_CGROUP_SCHED) && defined(CONFIG_FAIR_GROUP_SCHED)
-	char path[128] = "";
+	char path[128];
 	struct task_group *tg = cfs_rq->tg;
 
-	cgroup_path(tg->css.cgroup, path, sizeof(path));
+	task_group_path(tg, path, sizeof(path));
 
 	SEQ_printf(m, "\ncfs_rq[%d]:%s\n", cpu, path);
 #elif defined(CONFIG_USER_SCHED) && defined(CONFIG_FAIR_GROUP_SCHED)
@@ -208,10 +221,10 @@ void print_cfs_rq(struct seq_file *m, int cpu, struct cfs_rq *cfs_rq)
 void print_rt_rq(struct seq_file *m, int cpu, struct rt_rq *rt_rq)
 {
 #if defined(CONFIG_CGROUP_SCHED) && defined(CONFIG_RT_GROUP_SCHED)
-	char path[128] = "";
+	char path[128];
 	struct task_group *tg = rt_rq->tg;
 
-	cgroup_path(tg->css.cgroup, path, sizeof(path));
+	task_group_path(tg, path, sizeof(path));
 
 	SEQ_printf(m, "\nrt_rq[%d]:%s\n", cpu, path);
 #else
-- 
cgit v1.2.3-70-g09d2


From 53ce3d9564908794ae7dd32969089b57df5fc098 Mon Sep 17 00:00:00 2001
From: Andrew Morton <akpm@linux-foundation.org>
Date: Fri, 9 Jan 2009 12:27:08 -0800
Subject: smp_call_function_single(): be slightly less stupid

If you do

	smp_call_function_single(expression-with-side-effects, ...)

then expression-with-side-effects never gets evaluated on UP builds.

As always, implementing it in C is the correct thing to do.

While we're there, uninline it for size and possible header dependency
reasons.

And create a new kernel/up.c, as a place in which to put
uniprocessor-specific code and storage.  It should mirror kernel/smp.c.

Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
---
 include/linux/smp.h | 13 +++----------
 kernel/Makefile     |  6 +++++-
 kernel/up.c         | 18 ++++++++++++++++++
 3 files changed, 26 insertions(+), 11 deletions(-)
 create mode 100644 kernel/up.c

(limited to 'kernel')

diff --git a/include/linux/smp.h b/include/linux/smp.h
index b8246696810..715196b09d6 100644
--- a/include/linux/smp.h
+++ b/include/linux/smp.h
@@ -24,6 +24,9 @@ struct call_single_data {
 /* total number of cpus in this system (may exceed NR_CPUS) */
 extern unsigned int total_cpus;
 
+int smp_call_function_single(int cpuid, void (*func) (void *info), void *info,
+				int wait);
+
 #ifdef CONFIG_SMP
 
 #include <linux/preempt.h>
@@ -79,8 +82,6 @@ smp_call_function_mask(cpumask_t mask, void(*func)(void *info), void *info,
 	return 0;
 }
 
-int smp_call_function_single(int cpuid, void (*func) (void *info), void *info,
-				int wait);
 void __smp_call_function_single(int cpuid, struct call_single_data *data);
 
 /*
@@ -140,14 +141,6 @@ static inline int up_smp_call_function(void (*func)(void *), void *info)
 static inline void smp_send_reschedule(int cpu) { }
 #define num_booting_cpus()			1
 #define smp_prepare_boot_cpu()			do {} while (0)
-#define smp_call_function_single(cpuid, func, info, wait) \
-({ \
-	WARN_ON(cpuid != 0);	\
-	local_irq_disable();	\
-	(func)(info);		\
-	local_irq_enable();	\
-	0;			\
-})
 #define smp_call_function_mask(mask, func, info, wait) \
 			(up_smp_call_function(func, info))
 #define smp_call_function_many(mask, func, info, wait) \
diff --git a/kernel/Makefile b/kernel/Makefile
index 2921d90ce32..2aebc4cd787 100644
--- a/kernel/Makefile
+++ b/kernel/Makefile
@@ -40,7 +40,11 @@ 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
-obj-$(CONFIG_USE_GENERIC_SMP_HELPERS) += smp.o
+ifeq ($(CONFIG_USE_GENERIC_SMP_HELPERS),y)
+obj-y += smp.o
+else
+obj-y += up.o
+endif
 obj-$(CONFIG_SMP) += spinlock.o
 obj-$(CONFIG_DEBUG_SPINLOCK) += spinlock.o
 obj-$(CONFIG_PROVE_LOCKING) += spinlock.o
diff --git a/kernel/up.c b/kernel/up.c
new file mode 100644
index 00000000000..ce62cc9e9f7
--- /dev/null
+++ b/kernel/up.c
@@ -0,0 +1,18 @@
+/*
+ * Uniprocessor-only support functions.  The counterpart to kernel/smp.c
+ */
+
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/smp.h>
+
+int smp_call_function_single(int cpu, void (*func) (void *info), void *info,
+				int wait)
+{
+	WARN_ON(cpuid != 0);
+	local_irq_disable();
+	(func)(info);
+	local_irq_enable();
+	return 0;
+}
+EXPORT_SYMBOL(smp_call_function_single);
-- 
cgit v1.2.3-70-g09d2


From 93423b8665f43a0c7a006a1d5be048b99db56d32 Mon Sep 17 00:00:00 2001
From: Ingo Molnar <mingo@elte.hu>
Date: Sun, 11 Jan 2009 05:15:21 +0100
Subject: smp_call_function_single(): be slightly less stupid, fix

Impact: build fix on Alpha

 kernel/up.c: In function 'smp_call_function_single':
 kernel/up.c:12: error: 'cpuid' undeclared (first use in this function)
 kernel/up.c:12: error: (Each undeclared identifier is reported only once
 kernel/up.c:12: error: for each function it appears in.)

The typo didnt show up on x86 because 'cpuid' happens to be a
function address as well ...

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

(limited to 'kernel')

diff --git a/kernel/up.c b/kernel/up.c
index ce62cc9e9f7..c04b9dcfceb 100644
--- a/kernel/up.c
+++ b/kernel/up.c
@@ -9,10 +9,12 @@
 int smp_call_function_single(int cpu, void (*func) (void *info), void *info,
 				int wait)
 {
-	WARN_ON(cpuid != 0);
+	WARN_ON(cpu != 0);
+
 	local_irq_disable();
 	(func)(info);
 	local_irq_enable();
+
 	return 0;
 }
 EXPORT_SYMBOL(smp_call_function_single);
-- 
cgit v1.2.3-70-g09d2


From fd2ab30b65e961b974ae0bc71e0d47d6b35e0968 Mon Sep 17 00:00:00 2001
From: Steven Noonan <steven@uplinklabs.net>
Date: Sun, 11 Jan 2009 01:04:22 -0800
Subject: kernel/sched.c: add missing forward declaration for 'double_rq_lock'

Impact: build fix on certain configs

Added 'double_rq_lock' forward declaration, allowing double_rq_lock
to be used in _double_lock_balance().

Signed-off-by: Steven Noonan <steven@uplinklabs.net>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
---
 kernel/sched.c | 3 +++
 1 file changed, 3 insertions(+)

(limited to 'kernel')

diff --git a/kernel/sched.c b/kernel/sched.c
index f0c0a81d763..8be2c13b50d 100644
--- a/kernel/sched.c
+++ b/kernel/sched.c
@@ -125,6 +125,9 @@ DEFINE_TRACE(sched_switch);
 DEFINE_TRACE(sched_migrate_task);
 
 #ifdef CONFIG_SMP
+
+static void double_rq_lock(struct rq *rq1, struct rq *rq2);
+
 /*
  * Divide a load by a sched group cpu_power : (load / sg->__cpu_power)
  * Since cpu_power is a 'constant', we can use a reciprocal divide.
-- 
cgit v1.2.3-70-g09d2


From 7f7ace0cda64c99599c23785f8979a072e118058 Mon Sep 17 00:00:00 2001
From: Mike Travis <travis@sgi.com>
Date: Sat, 10 Jan 2009 21:58:08 -0800
Subject: cpumask: update irq_desc to use cpumask_var_t

Impact: reduce memory usage, use new cpumask API.

Replace the affinity and pending_masks with cpumask_var_t's.  This adds
to the significant size reduction done with the SPARSE_IRQS changes.

The added functions (init_alloc_desc_masks & init_copy_desc_masks) are
in the include file so they can be inlined (and optimized out for the
!CONFIG_CPUMASKS_OFFSTACK case.)  [Naming chosen to be consistent with
the other init*irq functions, as well as the backwards arg declaration
of "from, to" instead of the more common "to, from" standard.]

Includes a slight change to the declaration of struct irq_desc to embed
the pending_mask within ifdef(CONFIG_SMP) to be consistent with other
references, and some small changes to Xen.

Tested: sparse/non-sparse/cpumask_offstack/non-cpumask_offstack/nonuma/nosmp on x86_64

Signed-off-by: Mike Travis <travis@sgi.com>
Cc: Chris Wright <chrisw@sous-sol.org>
Cc: Jeremy Fitzhardinge <jeremy@xensource.com>
Cc: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com>
Cc: Venkatesh Pallipadi <venkatesh.pallipadi@intel.com>
Cc: virtualization@lists.osdl.org
Cc: xen-devel@lists.xensource.com
Cc: Yinghai Lu <yhlu.kernel@gmail.com>
---
 arch/x86/kernel/io_apic.c | 20 ++++++------
 arch/x86/kernel/irq_32.c  |  2 +-
 arch/x86/kernel/irq_64.c  |  2 +-
 drivers/xen/events.c      |  4 +--
 include/linux/irq.h       | 81 +++++++++++++++++++++++++++++++++++++++++++++--
 kernel/irq/chip.c         |  5 ++-
 kernel/irq/handle.c       | 26 ++++++++-------
 kernel/irq/manage.c       | 12 +++----
 kernel/irq/migration.c    | 12 +++----
 kernel/irq/numa_migrate.c | 12 ++++++-
 kernel/irq/proc.c         |  4 +--
 11 files changed, 135 insertions(+), 45 deletions(-)

(limited to 'kernel')

diff --git a/arch/x86/kernel/io_apic.c b/arch/x86/kernel/io_apic.c
index 1c4a1302536..1337eab60ec 100644
--- a/arch/x86/kernel/io_apic.c
+++ b/arch/x86/kernel/io_apic.c
@@ -356,7 +356,7 @@ set_extra_move_desc(struct irq_desc *desc, const struct cpumask *mask)
 
 	if (!cfg->move_in_progress) {
 		/* it means that domain is not changed */
-		if (!cpumask_intersects(&desc->affinity, mask))
+		if (!cpumask_intersects(desc->affinity, mask))
 			cfg->move_desc_pending = 1;
 	}
 }
@@ -579,9 +579,9 @@ set_desc_affinity(struct irq_desc *desc, const struct cpumask *mask)
 	if (assign_irq_vector(irq, cfg, mask))
 		return BAD_APICID;
 
-	cpumask_and(&desc->affinity, cfg->domain, mask);
+	cpumask_and(desc->affinity, cfg->domain, mask);
 	set_extra_move_desc(desc, mask);
-	return cpu_mask_to_apicid_and(&desc->affinity, cpu_online_mask);
+	return cpu_mask_to_apicid_and(desc->affinity, cpu_online_mask);
 }
 
 static void
@@ -2383,7 +2383,7 @@ migrate_ioapic_irq_desc(struct irq_desc *desc, const struct cpumask *mask)
 	if (cfg->move_in_progress)
 		send_cleanup_vector(cfg);
 
-	cpumask_copy(&desc->affinity, mask);
+	cpumask_copy(desc->affinity, mask);
 }
 
 static int migrate_irq_remapped_level_desc(struct irq_desc *desc)
@@ -2405,11 +2405,11 @@ static int migrate_irq_remapped_level_desc(struct irq_desc *desc)
 	}
 
 	/* everthing is clear. we have right of way */
-	migrate_ioapic_irq_desc(desc, &desc->pending_mask);
+	migrate_ioapic_irq_desc(desc, desc->pending_mask);
 
 	ret = 0;
 	desc->status &= ~IRQ_MOVE_PENDING;
-	cpumask_clear(&desc->pending_mask);
+	cpumask_clear(desc->pending_mask);
 
 unmask:
 	unmask_IO_APIC_irq_desc(desc);
@@ -2434,7 +2434,7 @@ static void ir_irq_migration(struct work_struct *work)
 				continue;
 			}
 
-			desc->chip->set_affinity(irq, &desc->pending_mask);
+			desc->chip->set_affinity(irq, desc->pending_mask);
 			spin_unlock_irqrestore(&desc->lock, flags);
 		}
 	}
@@ -2448,7 +2448,7 @@ static void set_ir_ioapic_affinity_irq_desc(struct irq_desc *desc,
 {
 	if (desc->status & IRQ_LEVEL) {
 		desc->status |= IRQ_MOVE_PENDING;
-		cpumask_copy(&desc->pending_mask, mask);
+		cpumask_copy(desc->pending_mask, mask);
 		migrate_irq_remapped_level_desc(desc);
 		return;
 	}
@@ -2516,7 +2516,7 @@ static void irq_complete_move(struct irq_desc **descp)
 
 		/* domain has not changed, but affinity did */
 		me = smp_processor_id();
-		if (cpu_isset(me, desc->affinity)) {
+		if (cpumask_test_cpu(me, desc->affinity)) {
 			*descp = desc = move_irq_desc(desc, me);
 			/* get the new one */
 			cfg = desc->chip_data;
@@ -4039,7 +4039,7 @@ void __init setup_ioapic_dest(void)
 			 */
 			if (desc->status &
 			    (IRQ_NO_BALANCING | IRQ_AFFINITY_SET))
-				mask = &desc->affinity;
+				mask = desc->affinity;
 			else
 				mask = TARGET_CPUS;
 
diff --git a/arch/x86/kernel/irq_32.c b/arch/x86/kernel/irq_32.c
index 74b9ff7341e..e0f29be8ab0 100644
--- a/arch/x86/kernel/irq_32.c
+++ b/arch/x86/kernel/irq_32.c
@@ -248,7 +248,7 @@ void fixup_irqs(void)
 		if (irq == 2)
 			continue;
 
-		affinity = &desc->affinity;
+		affinity = desc->affinity;
 		if (cpumask_any_and(affinity, cpu_online_mask) >= nr_cpu_ids) {
 			printk("Breaking affinity for irq %i\n", irq);
 			affinity = cpu_all_mask;
diff --git a/arch/x86/kernel/irq_64.c b/arch/x86/kernel/irq_64.c
index 63c88e6ec02..0b21cb1ea11 100644
--- a/arch/x86/kernel/irq_64.c
+++ b/arch/x86/kernel/irq_64.c
@@ -100,7 +100,7 @@ void fixup_irqs(void)
 		/* interrupt's are disabled at this point */
 		spin_lock(&desc->lock);
 
-		affinity = &desc->affinity;
+		affinity = desc->affinity;
 		if (!irq_has_action(irq) ||
 		    cpumask_equal(affinity, cpu_online_mask)) {
 			spin_unlock(&desc->lock);
diff --git a/drivers/xen/events.c b/drivers/xen/events.c
index eb0dfdeaa94..e0767ff35d6 100644
--- a/drivers/xen/events.c
+++ b/drivers/xen/events.c
@@ -125,7 +125,7 @@ static void bind_evtchn_to_cpu(unsigned int chn, unsigned int cpu)
 
 	BUG_ON(irq == -1);
 #ifdef CONFIG_SMP
-	irq_to_desc(irq)->affinity = cpumask_of_cpu(cpu);
+	cpumask_copy(irq_to_desc(irq)->affinity, cpumask_of(cpu));
 #endif
 
 	__clear_bit(chn, cpu_evtchn_mask[cpu_evtchn[chn]]);
@@ -142,7 +142,7 @@ static void init_evtchn_cpu_bindings(void)
 
 	/* By default all event channels notify CPU#0. */
 	for_each_irq_desc(i, desc) {
-		desc->affinity = cpumask_of_cpu(0);
+		cpumask_copy(desc->affinity, cpumask_of(0));
 	}
 #endif
 
diff --git a/include/linux/irq.h b/include/linux/irq.h
index f899b502f18..fa27210f1df 100644
--- a/include/linux/irq.h
+++ b/include/linux/irq.h
@@ -182,11 +182,11 @@ struct irq_desc {
 	unsigned int		irqs_unhandled;
 	spinlock_t		lock;
 #ifdef CONFIG_SMP
-	cpumask_t		affinity;
+	cpumask_var_t		affinity;
 	unsigned int		cpu;
-#endif
 #ifdef CONFIG_GENERIC_PENDING_IRQ
-	cpumask_t		pending_mask;
+	cpumask_var_t		pending_mask;
+#endif
 #endif
 #ifdef CONFIG_PROC_FS
 	struct proc_dir_entry	*dir;
@@ -422,4 +422,79 @@ extern int set_irq_msi(unsigned int irq, struct msi_desc *entry);
 
 #endif /* !CONFIG_S390 */
 
+#ifdef CONFIG_SMP
+/**
+ * init_alloc_desc_masks - allocate cpumasks for irq_desc
+ * @desc:	pointer to irq_desc struct
+ * @boot:	true if need bootmem
+ *
+ * Allocates affinity and pending_mask cpumask if required.
+ * Returns true if successful (or not required).
+ * Side effect: affinity has all bits set, pending_mask has all bits clear.
+ */
+static inline bool init_alloc_desc_masks(struct irq_desc *desc, int node,
+								bool boot)
+{
+	if (boot) {
+		alloc_bootmem_cpumask_var(&desc->affinity);
+		cpumask_setall(desc->affinity);
+
+#ifdef CONFIG_GENERIC_PENDING_IRQ
+		alloc_bootmem_cpumask_var(&desc->pending_mask);
+		cpumask_clear(desc->pending_mask);
+#endif
+		return true;
+	}
+
+	if (!alloc_cpumask_var_node(&desc->affinity, GFP_ATOMIC, node))
+		return false;
+	cpumask_setall(desc->affinity);
+
+#ifdef CONFIG_GENERIC_PENDING_IRQ
+	if (!alloc_cpumask_var_node(&desc->pending_mask, GFP_ATOMIC, node)) {
+		free_cpumask_var(desc->affinity);
+		return false;
+	}
+	cpumask_clear(desc->pending_mask);
+#endif
+	return true;
+}
+
+/**
+ * init_copy_desc_masks - copy cpumasks for irq_desc
+ * @old_desc:	pointer to old irq_desc struct
+ * @new_desc:	pointer to new irq_desc struct
+ *
+ * Insures affinity and pending_masks are copied to new irq_desc.
+ * If !CONFIG_CPUMASKS_OFFSTACK the cpumasks are embedded in the
+ * irq_desc struct so the copy is redundant.
+ */
+
+static inline void init_copy_desc_masks(struct irq_desc *old_desc,
+					struct irq_desc *new_desc)
+{
+#ifdef CONFIG_CPUMASKS_OFFSTACK
+	cpumask_copy(new_desc->affinity, old_desc->affinity);
+
+#ifdef CONFIG_GENERIC_PENDING_IRQ
+	cpumask_copy(new_desc->pending_mask, old_desc->pending_mask);
+#endif
+#endif
+}
+
+#else /* !CONFIG_SMP */
+
+static inline bool init_alloc_desc_masks(struct irq_desc *desc, int node,
+								bool boot)
+{
+	return true;
+}
+
+static inline void init_copy_desc_masks(struct irq_desc *old_desc,
+					struct irq_desc *new_desc)
+{
+}
+
+#endif	/* CONFIG_SMP */
+
 #endif /* _LINUX_IRQ_H */
diff --git a/kernel/irq/chip.c b/kernel/irq/chip.c
index f63c706d25e..c248eba98b4 100644
--- a/kernel/irq/chip.c
+++ b/kernel/irq/chip.c
@@ -46,7 +46,10 @@ void dynamic_irq_init(unsigned int irq)
 	desc->irq_count = 0;
 	desc->irqs_unhandled = 0;
 #ifdef CONFIG_SMP
-	cpumask_setall(&desc->affinity);
+	cpumask_setall(desc->affinity);
+#ifdef CONFIG_GENERIC_PENDING_IRQ
+	cpumask_clear(desc->pending_mask);
+#endif
 #endif
 	spin_unlock_irqrestore(&desc->lock, flags);
 }
diff --git a/kernel/irq/handle.c b/kernel/irq/handle.c
index c20db0be917..b8fa1354f01 100644
--- a/kernel/irq/handle.c
+++ b/kernel/irq/handle.c
@@ -64,9 +64,6 @@ static struct irq_desc irq_desc_init = {
 	.handle_irq = handle_bad_irq,
 	.depth      = 1,
 	.lock       = __SPIN_LOCK_UNLOCKED(irq_desc_init.lock),
-#ifdef CONFIG_SMP
-	.affinity   = CPU_MASK_ALL
-#endif
 };
 
 void init_kstat_irqs(struct irq_desc *desc, int cpu, int nr)
@@ -88,6 +85,8 @@ void init_kstat_irqs(struct irq_desc *desc, int cpu, int nr)
 
 static void init_one_irq_desc(int irq, struct irq_desc *desc, int cpu)
 {
+	int node = cpu_to_node(cpu);
+
 	memcpy(desc, &irq_desc_init, sizeof(struct irq_desc));
 
 	spin_lock_init(&desc->lock);
@@ -101,6 +100,10 @@ static void init_one_irq_desc(int irq, struct irq_desc *desc, int cpu)
 		printk(KERN_ERR "can not alloc kstat_irqs\n");
 		BUG_ON(1);
 	}
+	if (!init_alloc_desc_masks(desc, node, false)) {
+		printk(KERN_ERR "can not alloc irq_desc cpumasks\n");
+		BUG_ON(1);
+	}
 	arch_init_chip_data(desc, cpu);
 }
 
@@ -119,9 +122,6 @@ static struct irq_desc irq_desc_legacy[NR_IRQS_LEGACY] __cacheline_aligned_in_sm
 		.handle_irq = handle_bad_irq,
 		.depth	    = 1,
 		.lock	    = __SPIN_LOCK_UNLOCKED(irq_desc_init.lock),
-#ifdef CONFIG_SMP
-		.affinity   = CPU_MASK_ALL
-#endif
 	}
 };
 
@@ -141,7 +141,7 @@ int __init early_irq_init(void)
 		desc[i].irq = i;
 		desc[i].kstat_irqs = kstat_irqs_legacy[i];
 		lockdep_set_class(&desc[i].lock, &irq_desc_lock_class);
-
+		init_alloc_desc_masks(&desc[i], 0, true);
 		irq_desc_ptrs[i] = desc + i;
 	}
 
@@ -188,6 +188,10 @@ struct irq_desc *irq_to_desc_alloc_cpu(unsigned int irq, int cpu)
 		printk(KERN_ERR "can not alloc irq_desc\n");
 		BUG_ON(1);
 	}
+	if (!init_alloc_desc_masks(desc, node, false)) {
+		printk(KERN_ERR "can not alloc irq_desc cpumasks\n");
+		BUG_ON(1);
+	}
 	init_one_irq_desc(irq, desc, cpu);
 
 	irq_desc_ptrs[irq] = desc;
@@ -207,9 +211,6 @@ struct irq_desc irq_desc[NR_IRQS] __cacheline_aligned_in_smp = {
 		.handle_irq = handle_bad_irq,
 		.depth = 1,
 		.lock = __SPIN_LOCK_UNLOCKED(irq_desc->lock),
-#ifdef CONFIG_SMP
-		.affinity = CPU_MASK_ALL
-#endif
 	}
 };
 
@@ -222,9 +223,10 @@ int __init early_irq_init(void)
 	desc = irq_desc;
 	count = ARRAY_SIZE(irq_desc);
 
-	for (i = 0; i < count; i++)
+	for (i = 0; i < count; i++) {
 		desc[i].irq = i;
-
+		init_alloc_desc_masks(&desc[i], 0, true);
+	}
 	return arch_early_irq_init();
 }
 
diff --git a/kernel/irq/manage.c b/kernel/irq/manage.c
index cd0cd8dcb34..b98739af455 100644
--- a/kernel/irq/manage.c
+++ b/kernel/irq/manage.c
@@ -98,14 +98,14 @@ int irq_set_affinity(unsigned int irq, const struct cpumask *cpumask)
 
 #ifdef CONFIG_GENERIC_PENDING_IRQ
 	if (desc->status & IRQ_MOVE_PCNTXT || desc->status & IRQ_DISABLED) {
-		cpumask_copy(&desc->affinity, cpumask);
+		cpumask_copy(desc->affinity, cpumask);
 		desc->chip->set_affinity(irq, cpumask);
 	} else {
 		desc->status |= IRQ_MOVE_PENDING;
-		cpumask_copy(&desc->pending_mask, cpumask);
+		cpumask_copy(desc->pending_mask, cpumask);
 	}
 #else
-	cpumask_copy(&desc->affinity, cpumask);
+	cpumask_copy(desc->affinity, cpumask);
 	desc->chip->set_affinity(irq, cpumask);
 #endif
 	desc->status |= IRQ_AFFINITY_SET;
@@ -127,16 +127,16 @@ int do_irq_select_affinity(unsigned int irq, struct irq_desc *desc)
 	 * one of the targets is online.
 	 */
 	if (desc->status & (IRQ_AFFINITY_SET | IRQ_NO_BALANCING)) {
-		if (cpumask_any_and(&desc->affinity, cpu_online_mask)
+		if (cpumask_any_and(desc->affinity, cpu_online_mask)
 		    < nr_cpu_ids)
 			goto set_affinity;
 		else
 			desc->status &= ~IRQ_AFFINITY_SET;
 	}
 
-	cpumask_and(&desc->affinity, cpu_online_mask, irq_default_affinity);
+	cpumask_and(desc->affinity, cpu_online_mask, irq_default_affinity);
 set_affinity:
-	desc->chip->set_affinity(irq, &desc->affinity);
+	desc->chip->set_affinity(irq, desc->affinity);
 
 	return 0;
 }
diff --git a/kernel/irq/migration.c b/kernel/irq/migration.c
index bd72329e630..e05ad9be43b 100644
--- a/kernel/irq/migration.c
+++ b/kernel/irq/migration.c
@@ -18,7 +18,7 @@ void move_masked_irq(int irq)
 
 	desc->status &= ~IRQ_MOVE_PENDING;
 
-	if (unlikely(cpumask_empty(&desc->pending_mask)))
+	if (unlikely(cpumask_empty(desc->pending_mask)))
 		return;
 
 	if (!desc->chip->set_affinity)
@@ -38,13 +38,13 @@ void move_masked_irq(int irq)
 	 * For correct operation this depends on the caller
 	 * masking the irqs.
 	 */
-	if (likely(cpumask_any_and(&desc->pending_mask, cpu_online_mask)
+	if (likely(cpumask_any_and(desc->pending_mask, cpu_online_mask)
 		   < nr_cpu_ids)) {
-		cpumask_and(&desc->affinity,
-			    &desc->pending_mask, cpu_online_mask);
-		desc->chip->set_affinity(irq, &desc->affinity);
+		cpumask_and(desc->affinity,
+			    desc->pending_mask, cpu_online_mask);
+		desc->chip->set_affinity(irq, desc->affinity);
 	}
-	cpumask_clear(&desc->pending_mask);
+	cpumask_clear(desc->pending_mask);
 }
 
 void move_native_irq(int irq)
diff --git a/kernel/irq/numa_migrate.c b/kernel/irq/numa_migrate.c
index ecf765c6a77..f001a4ea641 100644
--- a/kernel/irq/numa_migrate.c
+++ b/kernel/irq/numa_migrate.c
@@ -46,6 +46,7 @@ static void init_copy_one_irq_desc(int irq, struct irq_desc *old_desc,
 	desc->cpu = cpu;
 	lockdep_set_class(&desc->lock, &irq_desc_lock_class);
 	init_copy_kstat_irqs(old_desc, desc, cpu, nr_cpu_ids);
+	init_copy_desc_masks(old_desc, desc);
 	arch_init_copy_chip_data(old_desc, desc, cpu);
 }
 
@@ -76,11 +77,20 @@ static struct irq_desc *__real_move_irq_desc(struct irq_desc *old_desc,
 	node = cpu_to_node(cpu);
 	desc = kzalloc_node(sizeof(*desc), GFP_ATOMIC, node);
 	if (!desc) {
-		printk(KERN_ERR "irq %d: can not get new irq_desc for migration.\n", irq);
+		printk(KERN_ERR "irq %d: can not get new irq_desc "
+				"for migration.\n", irq);
 		/* still use old one */
 		desc = old_desc;
 		goto out_unlock;
 	}
+	if (!init_alloc_desc_masks(desc, node, false)) {
+		printk(KERN_ERR "irq %d: can not get new irq_desc cpumask "
+				"for migration.\n", irq);
+		/* still use old one */
+		kfree(desc);
+		desc = old_desc;
+		goto out_unlock;
+	}
 	init_copy_one_irq_desc(irq, old_desc, desc, cpu);
 
 	irq_desc_ptrs[irq] = desc;
diff --git a/kernel/irq/proc.c b/kernel/irq/proc.c
index aae3f742bce..692363dd591 100644
--- a/kernel/irq/proc.c
+++ b/kernel/irq/proc.c
@@ -20,11 +20,11 @@ static struct proc_dir_entry *root_irq_dir;
 static int irq_affinity_proc_show(struct seq_file *m, void *v)
 {
 	struct irq_desc *desc = irq_to_desc((long)m->private);
-	const struct cpumask *mask = &desc->affinity;
+	const struct cpumask *mask = desc->affinity;
 
 #ifdef CONFIG_GENERIC_PENDING_IRQ
 	if (desc->status & IRQ_MOVE_PENDING)
-		mask = &desc->pending_mask;
+		mask = desc->pending_mask;
 #endif
 	seq_cpumask(m, mask);
 	seq_putc(m, '\n');
-- 
cgit v1.2.3-70-g09d2


From 802bf931f2688ad125b73db597ce63cc842fb27a Mon Sep 17 00:00:00 2001
From: Mike Travis <travis@sgi.com>
Date: Sat, 10 Jan 2009 21:58:09 -0800
Subject: cpumask: fix bug in use cpumask_var_t in irq_desc

Impact: fix bug where new irq_desc uses old cpumask pointers which are freed.

As Yinghai pointed out, init_copy_one_irq_desc() copies the old desc to
the new desc overwriting the cpumask pointers.  Since the old_desc and
the cpumask pointers are freed, then memory corruption will occur if
these old pointers are used.

Move the allocation of these pointers to after the copy.

Signed-off-by: Mike Travis <travis@sgi.com>
Cc: Yinghai Lu <yinghai@kernel.org>
---
 include/linux/irq.h       |  9 +++++++--
 kernel/irq/handle.c       |  8 +-------
 kernel/irq/numa_migrate.c | 13 ++++++++-----
 3 files changed, 16 insertions(+), 14 deletions(-)

(limited to 'kernel')

diff --git a/include/linux/irq.h b/include/linux/irq.h
index fa27210f1df..27a67536511 100644
--- a/include/linux/irq.h
+++ b/include/linux/irq.h
@@ -426,15 +426,18 @@ extern int set_irq_msi(unsigned int irq, struct msi_desc *entry);
 /**
  * init_alloc_desc_masks - allocate cpumasks for irq_desc
  * @desc:	pointer to irq_desc struct
+ * @cpu:	cpu which will be handling the cpumasks
  * @boot:	true if need bootmem
  *
  * Allocates affinity and pending_mask cpumask if required.
  * Returns true if successful (or not required).
  * Side effect: affinity has all bits set, pending_mask has all bits clear.
  */
-static inline bool init_alloc_desc_masks(struct irq_desc *desc, int node,
+static inline bool init_alloc_desc_masks(struct irq_desc *desc, int cpu,
 								bool boot)
 {
+	int node;
+
 	if (boot) {
 		alloc_bootmem_cpumask_var(&desc->affinity);
 		cpumask_setall(desc->affinity);
@@ -446,6 +449,8 @@ static inline bool init_alloc_desc_masks(struct irq_desc *desc, int node,
 		return true;
 	}
 
+	node = cpu_to_node(cpu);
+
 	if (!alloc_cpumask_var_node(&desc->affinity, GFP_ATOMIC, node))
 		return false;
 	cpumask_setall(desc->affinity);
@@ -484,7 +489,7 @@ static inline void init_copy_desc_masks(struct irq_desc *old_desc,
 
 #else /* !CONFIG_SMP */
 
-static inline bool init_alloc_desc_masks(struct irq_desc *desc, int node,
+static inline bool init_alloc_desc_masks(struct irq_desc *desc, int cpu,
 								bool boot)
 {
 	return true;
diff --git a/kernel/irq/handle.c b/kernel/irq/handle.c
index b8fa1354f01..f01c0a30cb4 100644
--- a/kernel/irq/handle.c
+++ b/kernel/irq/handle.c
@@ -85,8 +85,6 @@ void init_kstat_irqs(struct irq_desc *desc, int cpu, int nr)
 
 static void init_one_irq_desc(int irq, struct irq_desc *desc, int cpu)
 {
-	int node = cpu_to_node(cpu);
-
 	memcpy(desc, &irq_desc_init, sizeof(struct irq_desc));
 
 	spin_lock_init(&desc->lock);
@@ -100,7 +98,7 @@ static void init_one_irq_desc(int irq, struct irq_desc *desc, int cpu)
 		printk(KERN_ERR "can not alloc kstat_irqs\n");
 		BUG_ON(1);
 	}
-	if (!init_alloc_desc_masks(desc, node, false)) {
+	if (!init_alloc_desc_masks(desc, cpu, false)) {
 		printk(KERN_ERR "can not alloc irq_desc cpumasks\n");
 		BUG_ON(1);
 	}
@@ -188,10 +186,6 @@ struct irq_desc *irq_to_desc_alloc_cpu(unsigned int irq, int cpu)
 		printk(KERN_ERR "can not alloc irq_desc\n");
 		BUG_ON(1);
 	}
-	if (!init_alloc_desc_masks(desc, node, false)) {
-		printk(KERN_ERR "can not alloc irq_desc cpumasks\n");
-		BUG_ON(1);
-	}
 	init_one_irq_desc(irq, desc, cpu);
 
 	irq_desc_ptrs[irq] = desc;
diff --git a/kernel/irq/numa_migrate.c b/kernel/irq/numa_migrate.c
index f001a4ea641..666260e4c06 100644
--- a/kernel/irq/numa_migrate.c
+++ b/kernel/irq/numa_migrate.c
@@ -38,16 +38,22 @@ static void free_kstat_irqs(struct irq_desc *old_desc, struct irq_desc *desc)
 	old_desc->kstat_irqs = NULL;
 }
 
-static void init_copy_one_irq_desc(int irq, struct irq_desc *old_desc,
+static bool init_copy_one_irq_desc(int irq, struct irq_desc *old_desc,
 		 struct irq_desc *desc, int cpu)
 {
 	memcpy(desc, old_desc, sizeof(struct irq_desc));
+	if (!init_alloc_desc_masks(desc, cpu, false)) {
+		printk(KERN_ERR "irq %d: can not get new irq_desc cpumask "
+				"for migration.\n", irq);
+		return false;
+	}
 	spin_lock_init(&desc->lock);
 	desc->cpu = cpu;
 	lockdep_set_class(&desc->lock, &irq_desc_lock_class);
 	init_copy_kstat_irqs(old_desc, desc, cpu, nr_cpu_ids);
 	init_copy_desc_masks(old_desc, desc);
 	arch_init_copy_chip_data(old_desc, desc, cpu);
+	return true;
 }
 
 static void free_one_irq_desc(struct irq_desc *old_desc, struct irq_desc *desc)
@@ -83,15 +89,12 @@ static struct irq_desc *__real_move_irq_desc(struct irq_desc *old_desc,
 		desc = old_desc;
 		goto out_unlock;
 	}
-	if (!init_alloc_desc_masks(desc, node, false)) {
-		printk(KERN_ERR "irq %d: can not get new irq_desc cpumask "
-				"for migration.\n", irq);
+	if (!init_copy_one_irq_desc(irq, old_desc, desc, cpu)) {
 		/* still use old one */
 		kfree(desc);
 		desc = old_desc;
 		goto out_unlock;
 	}
-	init_copy_one_irq_desc(irq, old_desc, desc, cpu);
 
 	irq_desc_ptrs[irq] = desc;
 
-- 
cgit v1.2.3-70-g09d2


From d38b223c86db3162dc85b5a1997ac8a210e1660b Mon Sep 17 00:00:00 2001
From: Mike Travis <travis@sgi.com>
Date: Sat, 10 Jan 2009 21:58:11 -0800
Subject: cpumask: reduce stack usage in find_lowest_rq

Impact: reduce stack usage, cleanup

Use a cpumask_var_t in find_lowest_rq() and clean up other old
cpumask_t calls.

Signed-off-by: Mike Travis <travis@sgi.com>
---
 kernel/sched_rt.c | 36 ++++++++++++++++++++++--------------
 1 file changed, 22 insertions(+), 14 deletions(-)

(limited to 'kernel')

diff --git a/kernel/sched_rt.c b/kernel/sched_rt.c
index 954e1a81b79..da932f4c852 100644
--- a/kernel/sched_rt.c
+++ b/kernel/sched_rt.c
@@ -960,16 +960,17 @@ static struct task_struct *pick_next_highest_task_rt(struct rq *rq, int cpu)
 
 static DEFINE_PER_CPU(cpumask_var_t, local_cpu_mask);
 
-static inline int pick_optimal_cpu(int this_cpu, cpumask_t *mask)
+static inline int pick_optimal_cpu(int this_cpu,
+				   const struct cpumask *mask)
 {
 	int first;
 
 	/* "this_cpu" is cheaper to preempt than a remote processor */
-	if ((this_cpu != -1) && cpu_isset(this_cpu, *mask))
+	if ((this_cpu != -1) && cpumask_test_cpu(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;
@@ -981,6 +982,7 @@ static int find_lowest_rq(struct task_struct *task)
 	struct cpumask *lowest_mask = __get_cpu_var(local_cpu_mask);
 	int this_cpu = smp_processor_id();
 	int cpu      = task_cpu(task);
+	cpumask_var_t domain_mask;
 
 	if (task->rt.nr_cpus_allowed == 1)
 		return -1; /* No other targets possible */
@@ -1013,19 +1015,25 @@ static int find_lowest_rq(struct task_struct *task)
 	if (this_cpu == cpu)
 		this_cpu = -1; /* Skip this_cpu opt if the same */
 
-	for_each_domain(cpu, sd) {
-		if (sd->flags & SD_WAKE_AFFINE) {
-			cpumask_t domain_mask;
-			int       best_cpu;
+	if (alloc_cpumask_var(&domain_mask, GFP_ATOMIC)) {
+		for_each_domain(cpu, sd) {
+			if (sd->flags & SD_WAKE_AFFINE) {
+				int best_cpu;
 
-			cpumask_and(&domain_mask, sched_domain_span(sd),
-				    lowest_mask);
+				cpumask_and(domain_mask,
+					    sched_domain_span(sd),
+					    lowest_mask);
 
-			best_cpu = pick_optimal_cpu(this_cpu,
-						    &domain_mask);
-			if (best_cpu != -1)
-				return best_cpu;
+				best_cpu = pick_optimal_cpu(this_cpu,
+							    domain_mask);
+
+				if (best_cpu != -1) {
+					free_cpumask_var(domain_mask);
+					return best_cpu;
+				}
+			}
 		}
+		free_cpumask_var(domain_mask);
 	}
 
 	/*
-- 
cgit v1.2.3-70-g09d2


From 9594949b060efe86ecaa1a66839232a3b9800bc9 Mon Sep 17 00:00:00 2001
From: Mike Travis <travis@sgi.com>
Date: Sat, 10 Jan 2009 22:24:06 -0800
Subject: irq: change references from NR_IRQS to nr_irqs

Impact: preparation, cleanup, add KERN_INFO printk

Modify references from NR_IRQS to nr_irqs as the later will become
variable-sized based on nr_cpu_ids when CONFIG_SPARSE_IRQS=y.

Signed-off-by: Mike Travis <travis@sgi.com>
---
 arch/x86/kernel/io_apic.c |  2 +-
 kernel/irq/handle.c       | 14 +++++++++-----
 2 files changed, 10 insertions(+), 6 deletions(-)

(limited to 'kernel')

diff --git a/arch/x86/kernel/io_apic.c b/arch/x86/kernel/io_apic.c
index 1337eab60ec..ae80638012d 100644
--- a/arch/x86/kernel/io_apic.c
+++ b/arch/x86/kernel/io_apic.c
@@ -3183,7 +3183,7 @@ unsigned int create_irq_nr(unsigned int irq_want)
 
 	irq = 0;
 	spin_lock_irqsave(&vector_lock, flags);
-	for (new = irq_want; new < NR_IRQS; new++) {
+	for (new = irq_want; new < nr_irqs; new++) {
 		if (platform_legacy_irq(new))
 			continue;
 
diff --git a/kernel/irq/handle.c b/kernel/irq/handle.c
index f01c0a30cb4..790c5fa7ea3 100644
--- a/kernel/irq/handle.c
+++ b/kernel/irq/handle.c
@@ -132,6 +132,8 @@ int __init early_irq_init(void)
 	int legacy_count;
 	int i;
 
+	printk(KERN_INFO "NR_IRQS:%d nr_irqs:%d\n", NR_IRQS, nr_irqs);
+
 	desc = irq_desc_legacy;
 	legacy_count = ARRAY_SIZE(irq_desc_legacy);
 
@@ -143,7 +145,7 @@ int __init early_irq_init(void)
 		irq_desc_ptrs[i] = desc + i;
 	}
 
-	for (i = legacy_count; i < NR_IRQS; i++)
+	for (i = legacy_count; i < nr_irqs; i++)
 		irq_desc_ptrs[i] = NULL;
 
 	return arch_early_irq_init();
@@ -151,7 +153,7 @@ int __init early_irq_init(void)
 
 struct irq_desc *irq_to_desc(unsigned int irq)
 {
-	return (irq < NR_IRQS) ? irq_desc_ptrs[irq] : NULL;
+	return (irq < nr_irqs) ? irq_desc_ptrs[irq] : NULL;
 }
 
 struct irq_desc *irq_to_desc_alloc_cpu(unsigned int irq, int cpu)
@@ -160,9 +162,9 @@ struct irq_desc *irq_to_desc_alloc_cpu(unsigned int irq, int cpu)
 	unsigned long flags;
 	int node;
 
-	if (irq >= NR_IRQS) {
-		printk(KERN_WARNING "irq >= NR_IRQS in irq_to_desc_alloc: %d %d\n",
-				irq, NR_IRQS);
+	if (irq >= nr_irqs) {
+		printk(KERN_WARNING "irq >= nr_irqs in irq_to_desc_alloc: %d %d\n",
+				irq, nr_irqs);
 		WARN_ON(1);
 		return NULL;
 	}
@@ -214,6 +216,8 @@ int __init early_irq_init(void)
 	int count;
 	int i;
 
+	printk(KERN_INFO "NR_IRQS:%d\n", NR_IRQS);
+
 	desc = irq_desc;
 	count = ARRAY_SIZE(irq_desc);
 
-- 
cgit v1.2.3-70-g09d2


From e2f4d06545ec1f29b0e838ee34cbf3500ea5b9a4 Mon Sep 17 00:00:00 2001
From: Mike Travis <travis@sgi.com>
Date: Sat, 10 Jan 2009 22:24:06 -0800
Subject: irq: use WARN() instead of WARN_ON().

Impact: cleanup WARN msg.

Ingo requested:
> While at it, could you please also convert this to a WARN() construct
> instead? (in a separate commit)

... and it shall be done.  ;-)

Signed-off-by: Mike Travis <travis@sgi.com>
---
 kernel/irq/handle.c | 5 ++---
 1 file changed, 2 insertions(+), 3 deletions(-)

(limited to 'kernel')

diff --git a/kernel/irq/handle.c b/kernel/irq/handle.c
index 790c5fa7ea3..fd1ef16252f 100644
--- a/kernel/irq/handle.c
+++ b/kernel/irq/handle.c
@@ -163,9 +163,8 @@ struct irq_desc *irq_to_desc_alloc_cpu(unsigned int irq, int cpu)
 	int node;
 
 	if (irq >= nr_irqs) {
-		printk(KERN_WARNING "irq >= nr_irqs in irq_to_desc_alloc: %d %d\n",
-				irq, nr_irqs);
-		WARN_ON(1);
+		WARN(1, "irq (%d) >= nr_irqs (%d) in irq_to_desc_alloc\n",
+			irq, nr_irqs);
 		return NULL;
 	}
 
-- 
cgit v1.2.3-70-g09d2


From 0fa0ebbf15addc1be8f73325d809c8547a9de304 Mon Sep 17 00:00:00 2001
From: Mike Travis <travis@sgi.com>
Date: Sat, 10 Jan 2009 22:24:06 -0800
Subject: irq: allocate irq_desc_ptrs array based on nr_irqs

Impact: allocate irq_desc_ptrs in preparation for making it variable-sized.

This addresses this memory usage bump when NR_CPUS bumped from 128 to 4096:

    34816   +229376    264192  +658%  irq_desc_ptrs(.data.read_mostly)

The patch is split into two parts, the first simply allocates the
irq_desc_ptrs array.  Then next will deal with making it variable.
This is only when CONFIG_SPARSE_IRQS=y.

Signed-off-by: Mike Travis <travis@sgi.com>
---
 kernel/irq/handle.c    | 11 +++++++++--
 kernel/irq/internals.h |  7 +++++++
 2 files changed, 16 insertions(+), 2 deletions(-)

(limited to 'kernel')

diff --git a/kernel/irq/handle.c b/kernel/irq/handle.c
index fd1ef16252f..d0b8f7e7279 100644
--- a/kernel/irq/handle.c
+++ b/kernel/irq/handle.c
@@ -17,6 +17,7 @@
 #include <linux/kernel_stat.h>
 #include <linux/rculist.h>
 #include <linux/hash.h>
+#include <linux/bootmem.h>
 
 #include "internals.h"
 
@@ -110,7 +111,7 @@ static void init_one_irq_desc(int irq, struct irq_desc *desc, int cpu)
  */
 DEFINE_SPINLOCK(sparse_irq_lock);
 
-struct irq_desc *irq_desc_ptrs[NR_IRQS] __read_mostly;
+struct irq_desc **irq_desc_ptrs __read_mostly;
 
 static struct irq_desc irq_desc_legacy[NR_IRQS_LEGACY] __cacheline_aligned_in_smp = {
 	[0 ... NR_IRQS_LEGACY-1] = {
@@ -137,6 +138,9 @@ int __init early_irq_init(void)
 	desc = irq_desc_legacy;
 	legacy_count = ARRAY_SIZE(irq_desc_legacy);
 
+	/* allocate irq_desc_ptrs array based on nr_irqs */
+	irq_desc_ptrs = alloc_bootmem(nr_irqs * sizeof(void *));
+
 	for (i = 0; i < legacy_count; i++) {
 		desc[i].irq = i;
 		desc[i].kstat_irqs = kstat_irqs_legacy[i];
@@ -153,7 +157,10 @@ int __init early_irq_init(void)
 
 struct irq_desc *irq_to_desc(unsigned int irq)
 {
-	return (irq < nr_irqs) ? irq_desc_ptrs[irq] : NULL;
+	if (irq_desc_ptrs && irq < nr_irqs)
+		return irq_desc_ptrs[irq];
+
+	return NULL;
 }
 
 struct irq_desc *irq_to_desc_alloc_cpu(unsigned int irq, int cpu)
diff --git a/kernel/irq/internals.h b/kernel/irq/internals.h
index e6d0a43cc12..40416a81a0f 100644
--- a/kernel/irq/internals.h
+++ b/kernel/irq/internals.h
@@ -16,7 +16,14 @@ extern int __irq_set_trigger(struct irq_desc *desc, unsigned int irq,
 extern struct lock_class_key irq_desc_lock_class;
 extern void init_kstat_irqs(struct irq_desc *desc, int cpu, int nr);
 extern spinlock_t sparse_irq_lock;
+
+#ifdef CONFIG_SPARSE_IRQ
+/* irq_desc_ptrs allocated at boot time */
+extern struct irq_desc **irq_desc_ptrs;
+#else
+/* irq_desc_ptrs is a fixed size array */
 extern struct irq_desc *irq_desc_ptrs[NR_IRQS];
+#endif
 
 #ifdef CONFIG_PROC_FS
 extern void register_irq_proc(unsigned int irq, struct irq_desc *desc);
-- 
cgit v1.2.3-70-g09d2


From 9332fccdedf8e09448f3b69b624211ae879f6c45 Mon Sep 17 00:00:00 2001
From: Mike Travis <travis@sgi.com>
Date: Sat, 10 Jan 2009 22:24:07 -0800
Subject: irq: initialize nr_irqs based on nr_cpu_ids

Impact: Reduce memory usage.

This is the second half of the changes to make the irq_desc_ptrs be
variable sized based on nr_cpu_ids.  This is done by adding a new
"max_nr_irqs" macro to irq_vectors.h (and a dummy in irqnr.h) to
return a max NR_IRQS value based on NR_CPUS or nr_cpu_ids.

This necessitated moving the define of MAX_IO_APICS to a separate
file (asm/apicnum.h) so it could be included without the baggage
of the other asm/apicdef.h declarations.

Signed-off-by: Mike Travis <travis@sgi.com>
---
 arch/x86/include/asm/apicdef.h     |  8 ++------
 arch/x86/include/asm/apicnum.h     | 12 ++++++++++++
 arch/x86/include/asm/irq_vectors.h | 16 +++++++++++-----
 include/linux/irqnr.h              |  7 +++++++
 kernel/irq/handle.c                |  3 +++
 5 files changed, 35 insertions(+), 11 deletions(-)
 create mode 100644 arch/x86/include/asm/apicnum.h

(limited to 'kernel')

diff --git a/arch/x86/include/asm/apicdef.h b/arch/x86/include/asm/apicdef.h
index 63134e31e8b..1a6454ef7f6 100644
--- a/arch/x86/include/asm/apicdef.h
+++ b/arch/x86/include/asm/apicdef.h
@@ -132,12 +132,8 @@
 #define APIC_BASE_MSR	0x800
 #define X2APIC_ENABLE	(1UL << 10)
 
-#ifdef CONFIG_X86_32
-# define MAX_IO_APICS 64
-#else
-# define MAX_IO_APICS 128
-# define MAX_LOCAL_APIC 32768
-#endif
+/* get MAX_IO_APICS */
+#include <asm/apicnum.h>
 
 /*
  * All x86-64 systems are xAPIC compatible.
diff --git a/arch/x86/include/asm/apicnum.h b/arch/x86/include/asm/apicnum.h
new file mode 100644
index 00000000000..82f613c607c
--- /dev/null
+++ b/arch/x86/include/asm/apicnum.h
@@ -0,0 +1,12 @@
+#ifndef _ASM_X86_APICNUM_H
+#define _ASM_X86_APICNUM_H
+
+/* define MAX_IO_APICS */
+#ifdef CONFIG_X86_32
+# define MAX_IO_APICS 64
+#else
+# define MAX_IO_APICS 128
+# define MAX_LOCAL_APIC 32768
+#endif
+
+#endif /* _ASM_X86_APICNUM_H */
diff --git a/arch/x86/include/asm/irq_vectors.h b/arch/x86/include/asm/irq_vectors.h
index f7ff65032b9..602361ad0e7 100644
--- a/arch/x86/include/asm/irq_vectors.h
+++ b/arch/x86/include/asm/irq_vectors.h
@@ -105,6 +105,8 @@
 
 #if defined(CONFIG_X86_IO_APIC) && !defined(CONFIG_X86_VOYAGER)
 
+#include <asm/apicnum.h>	/* need MAX_IO_APICS */
+
 #ifndef CONFIG_SPARSE_IRQ
 # if NR_CPUS < MAX_IO_APICS
 #  define NR_IRQS (NR_VECTORS + (32 * NR_CPUS))
@@ -112,11 +114,15 @@
 #  define NR_IRQS (NR_VECTORS + (32 * MAX_IO_APICS))
 # endif
 #else
-# if (8 * NR_CPUS) > (32 * MAX_IO_APICS)
-#  define NR_IRQS (NR_VECTORS + (8 * NR_CPUS))
-# else
-#  define NR_IRQS (NR_VECTORS + (32 * MAX_IO_APICS))
-# endif
+
+/* defined as a macro so nr_irqs = max_nr_irqs(nr_cpu_ids) can be used */
+# define max_nr_irqs(nr_cpus)				\
+	((8 * nr_cpus) > (32 * MAX_IO_APICS) ?		\
+		(NR_VECTORS + (8 * NR_CPUS)) :		\
+		(NR_VECTORS + (32 * MAX_IO_APICS)))	\
+
+# define NR_IRQS max_nr_irqs(NR_CPUS)
+
 #endif
 
 #elif defined(CONFIG_X86_VOYAGER)
diff --git a/include/linux/irqnr.h b/include/linux/irqnr.h
index 86af92e9e84..de66e4e1040 100644
--- a/include/linux/irqnr.h
+++ b/include/linux/irqnr.h
@@ -20,11 +20,18 @@
 
 # define for_each_irq_desc_reverse(irq, desc)                          \
 	for (irq = nr_irqs - 1; irq >= 0; irq--)
+
 #else /* CONFIG_GENERIC_HARDIRQS */
 
+#include <asm/irq_vectors.h>	/* need possible max_nr_irqs() */
+
 extern int nr_irqs;
 extern struct irq_desc *irq_to_desc(unsigned int irq);
 
+# ifndef max_nr_irqs
+#  define max_nr_irqs(nr_cpus)	NR_IRQS
+# endif
+
 # define for_each_irq_desc(irq, desc)					\
 	for (irq = 0, desc = irq_to_desc(irq); irq < nr_irqs;		\
 	     irq++, desc = irq_to_desc(irq))				\
diff --git a/kernel/irq/handle.c b/kernel/irq/handle.c
index d0b8f7e7279..ebba7a116f1 100644
--- a/kernel/irq/handle.c
+++ b/kernel/irq/handle.c
@@ -133,6 +133,9 @@ int __init early_irq_init(void)
 	int legacy_count;
 	int i;
 
+	/* initialize nr_irqs based on nr_cpu_ids */
+	nr_irqs = max_nr_irqs(nr_cpu_ids);
+
 	printk(KERN_INFO "NR_IRQS:%d nr_irqs:%d\n", NR_IRQS, nr_irqs);
 
 	desc = irq_desc_legacy;
-- 
cgit v1.2.3-70-g09d2


From 542d865bbed4ce1f050f586e53cf1cfadda93766 Mon Sep 17 00:00:00 2001
From: Mike Travis <travis@sgi.com>
Date: Sat, 10 Jan 2009 22:24:07 -0800
Subject: kstat: modify kstat_irqs_legacy to be variable sized

Impact: reduce memory usage.

Allocate kstat_irqs_legacy based on nr_cpu_ids to deal with this
memory usage bump when NR_CPUS bumped from 128 to 4096:

     8192   +253952    262144 +3100%  kstat_irqs_legacy(.bss)

This is only when CONFIG_SPARSE_IRQS=y.

Signed-off-by: Mike Travis <travis@sgi.com>
---
 kernel/irq/handle.c | 10 +++++++---
 1 file changed, 7 insertions(+), 3 deletions(-)

(limited to 'kernel')

diff --git a/kernel/irq/handle.c b/kernel/irq/handle.c
index ebba7a116f1..b39f32ac8f8 100644
--- a/kernel/irq/handle.c
+++ b/kernel/irq/handle.c
@@ -124,8 +124,7 @@ static struct irq_desc irq_desc_legacy[NR_IRQS_LEGACY] __cacheline_aligned_in_sm
 	}
 };
 
-/* FIXME: use bootmem alloc ...*/
-static unsigned int kstat_irqs_legacy[NR_IRQS_LEGACY][NR_CPUS];
+static unsigned int *kstat_irqs_legacy;
 
 int __init early_irq_init(void)
 {
@@ -144,9 +143,14 @@ int __init early_irq_init(void)
 	/* allocate irq_desc_ptrs array based on nr_irqs */
 	irq_desc_ptrs = alloc_bootmem(nr_irqs * sizeof(void *));
 
+	/* allocate based on nr_cpu_ids */
+	/* FIXME: invert kstat_irgs, and it'd be a per_cpu_alloc'd thing */
+	kstat_irqs_legacy = alloc_bootmem(NR_IRQS_LEGACY * nr_cpu_ids *
+					  sizeof(int));
+
 	for (i = 0; i < legacy_count; i++) {
 		desc[i].irq = i;
-		desc[i].kstat_irqs = kstat_irqs_legacy[i];
+		desc[i].kstat_irqs = kstat_irqs_legacy + i * nr_cpu_ids;
 		lockdep_set_class(&desc[i].lock, &irq_desc_lock_class);
 		init_alloc_desc_masks(&desc[i], 0, true);
 		irq_desc_ptrs[i] = desc + i;
-- 
cgit v1.2.3-70-g09d2


From 92296c6d6e908c35fca287a21af27be814af9c75 Mon Sep 17 00:00:00 2001
From: Mike Travis <travis@sgi.com>
Date: Sun, 11 Jan 2009 09:22:58 -0800
Subject: cpumask, irq: non-x86 build failures

Ingo Molnar wrote:

> All non-x86 architectures fail to build:
>
> In file included from /home/mingo/tip/include/linux/random.h:11,
>                  from /home/mingo/tip/include/linux/stackprotector.h:6,
>                  from /home/mingo/tip/init/main.c:17:
> /home/mingo/tip/include/linux/irqnr.h:26:63: error: asm/irq_vectors.h: No such file or directory

Do not include asm/irq_vectors.h in generic code - it's not available
on all architectures.

Signed-off-by: Ingo Molnar <mingo@elte.hu>
---
 arch/x86/include/asm/apicdef.h | 8 ++++++--
 include/linux/irqnr.h          | 6 ------
 kernel/irq/handle.c            | 5 +++++
 3 files changed, 11 insertions(+), 8 deletions(-)

(limited to 'kernel')

diff --git a/arch/x86/include/asm/apicdef.h b/arch/x86/include/asm/apicdef.h
index 1a6454ef7f6..63134e31e8b 100644
--- a/arch/x86/include/asm/apicdef.h
+++ b/arch/x86/include/asm/apicdef.h
@@ -132,8 +132,12 @@
 #define APIC_BASE_MSR	0x800
 #define X2APIC_ENABLE	(1UL << 10)
 
-/* get MAX_IO_APICS */
-#include <asm/apicnum.h>
+#ifdef CONFIG_X86_32
+# define MAX_IO_APICS 64
+#else
+# define MAX_IO_APICS 128
+# define MAX_LOCAL_APIC 32768
+#endif
 
 /*
  * All x86-64 systems are xAPIC compatible.
diff --git a/include/linux/irqnr.h b/include/linux/irqnr.h
index de66e4e1040..887477bc2ab 100644
--- a/include/linux/irqnr.h
+++ b/include/linux/irqnr.h
@@ -23,15 +23,9 @@
 
 #else /* CONFIG_GENERIC_HARDIRQS */
 
-#include <asm/irq_vectors.h>	/* need possible max_nr_irqs() */
-
 extern int nr_irqs;
 extern struct irq_desc *irq_to_desc(unsigned int irq);
 
-# ifndef max_nr_irqs
-#  define max_nr_irqs(nr_cpus)	NR_IRQS
-# endif
-
 # define for_each_irq_desc(irq, desc)					\
 	for (irq = 0, desc = irq_to_desc(irq); irq < nr_irqs;		\
 	     irq++, desc = irq_to_desc(irq))				\
diff --git a/kernel/irq/handle.c b/kernel/irq/handle.c
index b39f32ac8f8..04d3e46031e 100644
--- a/kernel/irq/handle.c
+++ b/kernel/irq/handle.c
@@ -58,6 +58,11 @@ int nr_irqs = NR_IRQS;
 EXPORT_SYMBOL_GPL(nr_irqs);
 
 #ifdef CONFIG_SPARSE_IRQ
+
+#ifndef max_nr_irqs
+#define max_nr_irqs(nr_cpus)	NR_IRQS
+#endif
+
 static struct irq_desc irq_desc_init = {
 	.irq	    = -1,
 	.status	    = IRQ_DISABLED,
-- 
cgit v1.2.3-70-g09d2


From 6e96281412f2f757abe623e08a9577e2bbd3402f Mon Sep 17 00:00:00 2001
From: Ingo Molnar <mingo@elte.hu>
Date: Mon, 12 Jan 2009 16:04:37 +0100
Subject: smp_call_function_single(): be slightly less stupid, fix #2

fix m68k build failure:

 tip/kernel/up.c: In function 'smp_call_function_single':
 tip/kernel/up.c:16: error: dereferencing pointer to incomplete type
 make[2]: *** [kernel/up.o] Error 1

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

(limited to 'kernel')

diff --git a/kernel/up.c b/kernel/up.c
index c04b9dcfceb..1ff27a28bb7 100644
--- a/kernel/up.c
+++ b/kernel/up.c
@@ -2,6 +2,7 @@
  * Uniprocessor-only support functions.  The counterpart to kernel/smp.c
  */
 
+#include <linux/interrupt.h>
 #include <linux/kernel.h>
 #include <linux/module.h>
 #include <linux/smp.h>
-- 
cgit v1.2.3-70-g09d2


From 37a76bd4f1b716949fc38a6842e89f0ccb8384d0 Mon Sep 17 00:00:00 2001
From: Arjan van de Ven <arjan@linux.intel.com>
Date: Sun, 11 Jan 2009 15:35:01 +0000
Subject: async: fix __lowest_in_progress()

At 37000 feet somewhere near Greenland I woke up from a half-sleep with the
realisation that __lowest_in_progress() is buggy. After landing I checked
and there were indeed 2 problems with it; this patch fixes both:
* The order of the list checks was wrong
* The locking was not correct.

Signed-off-by: Arjan van de Ven <arjan@linux.intel.com>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 kernel/async.c | 21 ++++++++++++++++-----
 1 file changed, 16 insertions(+), 5 deletions(-)

(limited to 'kernel')

diff --git a/kernel/async.c b/kernel/async.c
index f286e9f2b73..608b32b4281 100644
--- a/kernel/async.c
+++ b/kernel/async.c
@@ -90,12 +90,12 @@ extern int initcall_debug;
 static async_cookie_t  __lowest_in_progress(struct list_head *running)
 {
 	struct async_entry *entry;
-	if (!list_empty(&async_pending)) {
-		entry = list_first_entry(&async_pending,
+	if (!list_empty(running)) {
+		entry = list_first_entry(running,
 			struct async_entry, list);
 		return entry->cookie;
-	} else if (!list_empty(running)) {
-		entry = list_first_entry(running,
+	} else if (!list_empty(&async_pending)) {
+		entry = list_first_entry(&async_pending,
 			struct async_entry, list);
 		return entry->cookie;
 	} else {
@@ -104,6 +104,17 @@ static async_cookie_t  __lowest_in_progress(struct list_head *running)
 	}
 
 }
+
+static async_cookie_t  lowest_in_progress(struct list_head *running)
+{
+	unsigned long flags;
+	async_cookie_t ret;
+
+	spin_lock_irqsave(&async_lock, flags);
+	ret = __lowest_in_progress(running);
+	spin_unlock_irqrestore(&async_lock, flags);
+	return ret;
+}
 /*
  * pick the first pending entry and run it
  */
@@ -229,7 +240,7 @@ void async_synchronize_cookie_special(async_cookie_t cookie, struct list_head *r
 		starttime = ktime_get();
 	}
 
-	wait_event(async_done, __lowest_in_progress(running) >= cookie);
+	wait_event(async_done, lowest_in_progress(running) >= cookie);
 
 	if (initcall_debug && system_state == SYSTEM_BOOTING) {
 		endtime = ktime_get();
-- 
cgit v1.2.3-70-g09d2


From 4a046d1754ee6ebb6f399696805ed61ea0444d4c Mon Sep 17 00:00:00 2001
From: Yinghai Lu <yinghai@kernel.org>
Date: Mon, 12 Jan 2009 17:39:24 -0800
Subject: x86: arch_probe_nr_irqs

Impact: save RAM with large NR_CPUS, get smaller nr_irqs

Signed-off-by: Yinghai Lu <yinghai@kernel.org>
Signed-off-by: Mike Travis <travis@sgi.com>
---
 arch/x86/include/asm/irq_vectors.h |  7 ++-----
 arch/x86/kernel/io_apic.c          | 16 ++++++++++++++++
 include/linux/interrupt.h          |  1 +
 kernel/irq/handle.c                |  9 ++-------
 kernel/softirq.c                   |  5 +++++
 5 files changed, 26 insertions(+), 12 deletions(-)

(limited to 'kernel')

diff --git a/arch/x86/include/asm/irq_vectors.h b/arch/x86/include/asm/irq_vectors.h
index 602361ad0e7..a16a2ab2b42 100644
--- a/arch/x86/include/asm/irq_vectors.h
+++ b/arch/x86/include/asm/irq_vectors.h
@@ -115,14 +115,11 @@
 # endif
 #else
 
-/* defined as a macro so nr_irqs = max_nr_irqs(nr_cpu_ids) can be used */
-# define max_nr_irqs(nr_cpus)				\
-	((8 * nr_cpus) > (32 * MAX_IO_APICS) ?		\
+# define NR_IRQS					\
+	((8 * NR_CPUS) > (32 * MAX_IO_APICS) ?		\
 		(NR_VECTORS + (8 * NR_CPUS)) :		\
 		(NR_VECTORS + (32 * MAX_IO_APICS)))	\
 
-# define NR_IRQS max_nr_irqs(NR_CPUS)
-
 #endif
 
 #elif defined(CONFIG_X86_VOYAGER)
diff --git a/arch/x86/kernel/io_apic.c b/arch/x86/kernel/io_apic.c
index ae80638012d..157986916cd 100644
--- a/arch/x86/kernel/io_apic.c
+++ b/arch/x86/kernel/io_apic.c
@@ -3850,6 +3850,22 @@ void __init probe_nr_irqs_gsi(void)
 		nr_irqs_gsi = nr;
 }
 
+#ifdef CONFIG_SPARSE_IRQ
+int __init arch_probe_nr_irqs(void)
+{
+	int nr;
+
+	nr = ((8 * nr_cpu_ids) > (32 * nr_ioapics) ?
+		(NR_VECTORS + (8 * nr_cpu_ids)) :
+		(NR_VECTORS + (32 * nr_ioapics)));
+
+	if (nr < nr_irqs && nr > nr_irqs_gsi)
+		nr_irqs = nr;
+
+	return 0;
+}
+#endif
+
 /* --------------------------------------------------------------------------
                           ACPI-based IOAPIC Configuration
    -------------------------------------------------------------------------- */
diff --git a/include/linux/interrupt.h b/include/linux/interrupt.h
index 9127f6b51a3..472f11765f6 100644
--- a/include/linux/interrupt.h
+++ b/include/linux/interrupt.h
@@ -467,6 +467,7 @@ int show_interrupts(struct seq_file *p, void *v);
 struct irq_desc;
 
 extern int early_irq_init(void);
+extern int arch_probe_nr_irqs(void);
 extern int arch_early_irq_init(void);
 extern int arch_init_chip_data(struct irq_desc *desc, int cpu);
 
diff --git a/kernel/irq/handle.c b/kernel/irq/handle.c
index 04d3e46031e..375d68cd5bf 100644
--- a/kernel/irq/handle.c
+++ b/kernel/irq/handle.c
@@ -59,10 +59,6 @@ EXPORT_SYMBOL_GPL(nr_irqs);
 
 #ifdef CONFIG_SPARSE_IRQ
 
-#ifndef max_nr_irqs
-#define max_nr_irqs(nr_cpus)	NR_IRQS
-#endif
-
 static struct irq_desc irq_desc_init = {
 	.irq	    = -1,
 	.status	    = IRQ_DISABLED,
@@ -137,9 +133,8 @@ int __init early_irq_init(void)
 	int legacy_count;
 	int i;
 
-	/* initialize nr_irqs based on nr_cpu_ids */
-	nr_irqs = max_nr_irqs(nr_cpu_ids);
-
+	 /* initialize nr_irqs based on nr_cpu_ids */
+	arch_probe_nr_irqs();
 	printk(KERN_INFO "NR_IRQS:%d nr_irqs:%d\n", NR_IRQS, nr_irqs);
 
 	desc = irq_desc_legacy;
diff --git a/kernel/softirq.c b/kernel/softirq.c
index bdbe9de9cd8..0365b4899a3 100644
--- a/kernel/softirq.c
+++ b/kernel/softirq.c
@@ -795,6 +795,11 @@ int __init __weak early_irq_init(void)
 	return 0;
 }
 
+int __init __weak arch_probe_nr_irqs(void)
+{
+	return 0;
+}
+
 int __init __weak arch_early_irq_init(void)
 {
 	return 0;
-- 
cgit v1.2.3-70-g09d2