Merge branch 'akpm' (updates from Andrew Morton)

Merge first patch-bomb from Andrew Morton:
 - various misc bits
 - I'm been patchmonkeying ocfs2 for a while, as Joel and Mark have been
   distracted.  There has been quite a bit of activity.
 - About half the MM queue
 - Some backlight bits
 - Various lib/ updates
 - checkpatch updates
 - zillions more little rtc patches
 - ptrace
 - signals
 - exec
 - procfs
 - rapidio
 - nbd
 - aoe
 - pps
 - memstick
 - tools/testing/selftests updates

* emailed patches from Andrew Morton <akpm@linux-foundation.org>: (445 commits)
  tools/testing/selftests: don't assume the x bit is set on scripts
  selftests: add .gitignore for kcmp
  selftests: fix clean target in kcmp Makefile
  selftests: add .gitignore for vm
  selftests: add hugetlbfstest
  self-test: fix make clean
  selftests: exit 1 on failure
  kernel/resource.c: remove the unneeded assignment in function __find_resource
  aio: fix wrong comment in aio_complete()
  drivers/w1/slaves/w1_ds2408.c: add magic sequence to disable P0 test mode
  drivers/memstick/host/r592.c: convert to module_pci_driver
  drivers/memstick/host/jmb38x_ms: convert to module_pci_driver
  pps-gpio: add device-tree binding and support
  drivers/pps/clients/pps-gpio.c: convert to module_platform_driver
  drivers/pps/clients/pps-gpio.c: convert to devm_* helpers
  drivers/parport/share.c: use kzalloc
  Documentation/accounting/getdelays.c: avoid strncpy in accounting tool
  aoe: update internal version number to v83
  aoe: update copyright date
  aoe: perform I/O completions in parallel
  ...

3 files changed, 48 insertions, 8 deletions

diff --git a/lib/dump_stack.c b/lib/dump_stack.c
index 53bad099ebd6..c03154173cc7 100644
--- a/lib/dump_stack.c
+++ b/lib/dump_stack.c
@@ -6,15 +6,58 @@
 #include <linux/kernel.h>
 #include <linux/export.h>
 #include <linux/sched.h>
+#include <linux/smp.h>
+#include <linux/atomic.h>
+
+static void __dump_stack(void)
+{
+        dump_stack_print_info(KERN_DEFAULT);
+        show_stack(NULL, NULL);
+}
 
 /**
  * dump_stack - dump the current task information and its stack trace
  *
  * Architectures can override this implementation by implementing its own.
  */
+#ifdef CONFIG_SMP
+static atomic_t dump_lock = ATOMIC_INIT(-1);
+
 void dump_stack(void)
 {
-        dump_stack_print_info(KERN_DEFAULT);
-        show_stack(NULL, NULL);
+        int was_locked;
+        int old;
+        int cpu;
+
+        /*
+         * Permit this cpu to perform nested stack dumps while serialising
+         * against other CPUs
+         */
+        preempt_disable();
+
+retry:
+        cpu = smp_processor_id();
+        old = atomic_cmpxchg(&dump_lock, -1, cpu);
+        if (old == -1) {
+                was_locked = 0;
+        } else if (old == cpu) {
+                was_locked = 1;
+        } else {
+                cpu_relax();
+                goto retry;
+        }
+
+        __dump_stack();
+
+        if (!was_locked)
+                atomic_set(&dump_lock, -1);
+
+        preempt_enable();
+}
+#else
+void dump_stack(void)
+{
+        __dump_stack();
 }
+#endif
 EXPORT_SYMBOL(dump_stack);
diff --git a/lib/idr.c b/lib/idr.c
index cca4b9302a71..bfe4db4e165f 100644
--- a/lib/idr.c
+++ b/lib/idr.c
@@ -524,9 +524,7 @@ EXPORT_SYMBOL(idr_alloc_cyclic);
 
 static void idr_remove_warning(int id)
 {
-        printk(KERN_WARNING
-                "idr_remove called for id=%d which is not allocated.\n", id);
-        dump_stack();
+        WARN(1, "idr_remove called for id=%d which is not allocated.\n", id);
 }
 
 static void sub_remove(struct idr *idp, int shift, int id)
@@ -1064,8 +1062,7 @@ void ida_remove(struct ida *ida, int id)
         return;
 
  err:
-        printk(KERN_WARNING
-               "ida_remove called for id=%d which is not allocated.\n", id);
+        WARN(1, "ida_remove called for id=%d which is not allocated.\n", id);
 }
 EXPORT_SYMBOL(ida_remove);
 
diff --git a/lib/percpu_counter.c b/lib/percpu_counter.c
index ba6085d9c741..1fc23a3277e1 100644
--- a/lib/percpu_counter.c
+++ b/lib/percpu_counter.c
@@ -80,8 +80,8 @@ void __percpu_counter_add(struct percpu_counter *fbc, s64 amount, s32 batch)
         if (count >= batch || count <= -batch) {
                 raw_spin_lock(&fbc->lock);
                 fbc->count += count;
-                __this_cpu_write(*fbc->counters, 0);
                 raw_spin_unlock(&fbc->lock);
+                __this_cpu_write(*fbc->counters, 0);
         } else {
                 __this_cpu_write(*fbc->counters, count);
         }