4 files changed, 23 insertions, 5 deletions

diff --git a/lib/Kconfig.debug b/lib/Kconfig.debug
index d2099f41aa1e..c459e8547bd8 100644
--- a/lib/Kconfig.debug
+++ b/lib/Kconfig.debug
@@ -419,7 +419,6 @@ config DEBUG_LOCKING_API_SELFTESTS
 
 config STACKTRACE
         bool
-        depends on DEBUG_KERNEL
         depends on STACKTRACE_SUPPORT
 
 config DEBUG_KOBJECT
@@ -563,6 +562,9 @@ config BACKTRACE_SELF_TEST
           for distributions or general kernels, but only for kernel
           developers working on architecture code.
 
+          Note that if you want to also test saved backtraces, you will
+          have to enable STACKTRACE as well.
+
           Say N if you are unsure.
 
 config LKDTM
@@ -634,6 +636,8 @@ config LATENCYTOP
           Enable this option if you want to use the LatencyTOP tool
           to find out which userspace is blocking on what kernel operations.
 
+source kernel/trace/Kconfig
+
 config PROVIDE_OHCI1394_DMA_INIT
         bool "Remote debugging over FireWire early on boot"
         depends on PCI && X86
diff --git a/lib/Makefile b/lib/Makefile
index 74b0cfb1fcc3..4b836a53c08f 100644
--- a/lib/Makefile
+++ b/lib/Makefile
@@ -8,6 +8,15 @@ lib-y := ctype.o string.o vsprintf.o cmdline.o \
          sha1.o irq_regs.o reciprocal_div.o argv_split.o \
          proportions.o prio_heap.o ratelimit.o
 
+ifdef CONFIG_FTRACE
+# Do not profile string.o, since it may be used in early boot or vdso
+CFLAGS_REMOVE_string.o = -pg
+# Also do not profile any debug utilities
+CFLAGS_REMOVE_spinlock_debug.o = -pg
+CFLAGS_REMOVE_list_debug.o = -pg
+CFLAGS_REMOVE_debugobjects.o = -pg
+endif
+
 lib-$(CONFIG_MMU) += ioremap.o
 lib-$(CONFIG_SMP) += cpumask.o
 
diff --git a/lib/percpu_counter.c b/lib/percpu_counter.c
index 119174494cb5..4a8ba4bf5f6f 100644
--- a/lib/percpu_counter.c
+++ b/lib/percpu_counter.c
@@ -52,7 +52,7 @@ EXPORT_SYMBOL(__percpu_counter_add);
  * Add up all the per-cpu counts, return the result.  This is a more accurate
  * but much slower version of percpu_counter_read_positive()
  */
-s64 __percpu_counter_sum(struct percpu_counter *fbc)
+s64 __percpu_counter_sum(struct percpu_counter *fbc, int set)
 {
         s64 ret;
         int cpu;
@@ -62,7 +62,12 @@ s64 __percpu_counter_sum(struct percpu_counter *fbc)
         for_each_online_cpu(cpu) {
                 s32 *pcount = per_cpu_ptr(fbc->counters, cpu);
                 ret += *pcount;
+                if (set)
+                        *pcount = 0;
         }
+        if (set)
+                fbc->count = ret;
+
         spin_unlock(&fbc->lock);
         return ret;
 }
diff --git a/lib/smp_processor_id.c b/lib/smp_processor_id.c
index 6c90fb90e19c..3b4dc098181e 100644
--- a/lib/smp_processor_id.c
+++ b/lib/smp_processor_id.c
@@ -7,7 +7,7 @@
 #include <linux/kallsyms.h>
 #include <linux/sched.h>
 
-unsigned int debug_smp_processor_id(void)
+notrace unsigned int debug_smp_processor_id(void)
 {
         unsigned long preempt_count = preempt_count();
         int this_cpu = raw_smp_processor_id();
@@ -37,7 +37,7 @@ unsigned int debug_smp_processor_id(void)
         /*
          * Avoid recursion:
          */
-        preempt_disable();
+        preempt_disable_notrace();
 
         if (!printk_ratelimit())
                 goto out_enable;
@@ -49,7 +49,7 @@ unsigned int debug_smp_processor_id(void)
         dump_stack();
 
 out_enable:
-        preempt_enable_no_resched();
+        preempt_enable_no_resched_notrace();
 out:
         return this_cpu;
 }