sched/preempt, mm/fault: Count pagefault_disable() levels in pagefault_disabled

Until now, pagefault_disable()/pagefault_enabled() used the preempt
count to track whether in an environment with pagefaults disabled (can
be queried via in_atomic()).

This patch introduces a separate counter in task_struct to count the
level of pagefault_disable() calls. We'll keep manipulating the preempt
count to retain compatibility to existing pagefault handlers.

It is now possible to verify whether in a pagefault_disable() envionment
by calling pagefault_disabled(). In contrast to in_atomic() it will not
be influenced by preempt_enable()/preempt_disable().

This patch is based on a patch from Ingo Molnar.

Reviewed-and-tested-by: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: David Hildenbrand <dahi@linux.vnet.ibm.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: David.Laight@ACULAB.COM
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: airlied@linux.ie
Cc: akpm@linux-foundation.org
Cc: benh@kernel.crashing.org
Cc: bigeasy@linutronix.de
Cc: borntraeger@de.ibm.com
Cc: daniel.vetter@intel.com
Cc: heiko.carstens@de.ibm.com
Cc: herbert@gondor.apana.org.au
Cc: hocko@suse.cz
Cc: hughd@google.com
Cc: mst@redhat.com
Cc: paulus@samba.org
Cc: ralf@linux-mips.org
Cc: schwidefsky@de.ibm.com
Cc: yang.shi@windriver.com
Link: http://lkml.kernel.org/r/1431359540-32227-2-git-send-email-dahi@linux.vnet.ibm.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>

include/linux/sched.h

@@ -1788,6 +1788,7 @@ struct task_struct {
 #ifdef CONFIG_DEBUG_ATOMIC_SLEEP
 	unsigned long	task_state_change;
 #endif
+	int pagefault_disabled;
 };
 
 /* Future-safe accessor for struct task_struct's cpus_allowed. */

include/linux/uaccess.h

@@ -2,20 +2,36 @@
 #define __LINUX_UACCESS_H__
 
 #include <linux/preempt.h>
+#include <linux/sched.h>
 #include <asm/uaccess.h>
 
+static __always_inline void pagefault_disabled_inc(void)
+{
+	current->pagefault_disabled++;
+}
+
+static __always_inline void pagefault_disabled_dec(void)
+{
+	current->pagefault_disabled--;
+	WARN_ON(current->pagefault_disabled < 0);
+}
+
 /*
- * These routines enable/disable the pagefault handler in that
- * it will not take any locks and go straight to the fixup table.
+ * These routines enable/disable the pagefault handler. If disabled, it will
+ * not take any locks and go straight to the fixup table.
+ *
+ * We increase the preempt and the pagefault count, to be able to distinguish
+ * whether we run in simple atomic context or in a real pagefault_disable()
+ * context.
+ *
+ * For now, after pagefault_disabled() has been called, we run in atomic
+ * context. User access methods will not sleep.
  *
- * They have great resemblance to the preempt_disable/enable calls
- * and in fact they are identical; this is because currently there is
- * no other way to make the pagefault handlers do this. So we do
- * disable preemption but we don't necessarily care about that.
  */
 static inline void pagefault_disable(void)
 {
 	preempt_count_inc();
+	pagefault_disabled_inc();
 	/*
 	 * make sure to have issued the store before a pagefault
 	 * can hit.
@@ -25,18 +41,24 @@ static inline void pagefault_disable(void)
 
 static inline void pagefault_enable(void)
 {
-#ifndef CONFIG_PREEMPT
 	/*
 	 * make sure to issue those last loads/stores before enabling
 	 * the pagefault handler again.
 	 */
 	barrier();
+	pagefault_disabled_dec();
+#ifndef CONFIG_PREEMPT
 	preempt_count_dec();
 #else
 	preempt_enable();
 #endif
 }
 
+/*
+ * Is the pagefault handler disabled? If so, user access methods will not sleep.
+ */
+#define pagefault_disabled() (current->pagefault_disabled != 0)
+
 #ifndef ARCH_HAS_NOCACHE_UACCESS
 
 static inline unsigned long __copy_from_user_inatomic_nocache(void *to,

kernel/fork.c

@@ -1393,6 +1393,9 @@ static struct task_struct *copy_process(unsigned long clone_flags,
 	p->hardirq_context = 0;
 	p->softirq_context = 0;
 #endif
+
+	p->pagefault_disabled = 0;
+
 #ifdef CONFIG_LOCKDEP
 	p->lockdep_depth = 0; /* no locks held yet */
 	p->curr_chain_key = 0;