2 files changed, 10 insertions, 2 deletions

diff --git a/arch/x86_64/kernel/process.c b/arch/x86_64/kernel/process.c
index 49f7fac6229e..f6226055d53d 100644
--- a/arch/x86_64/kernel/process.c
+++ b/arch/x86_64/kernel/process.c
@@ -88,9 +88,8 @@ void enter_idle(void)
 
 static void __exit_idle(void)
 {
-        if (read_pda(isidle) == 0)
+        if (test_and_clear_bit_pda(0, isidle) == 0)
                 return;
-        write_pda(isidle, 0);
         atomic_notifier_call_chain(&idle_notifier, IDLE_END, NULL);
 }
 
diff --git a/include/asm-x86_64/pda.h b/include/asm-x86_64/pda.h
index 14996d962bac..5642634843c4 100644
--- a/include/asm-x86_64/pda.h
+++ b/include/asm-x86_64/pda.h
@@ -109,6 +109,15 @@ extern struct x8664_pda _proxy_pda;
 #define sub_pda(field,val) pda_to_op("sub",field,val)
 #define or_pda(field,val) pda_to_op("or",field,val)
 
+/* This is not atomic against other CPUs -- CPU preemption needs to be off */
+#define test_and_clear_bit_pda(bit,field) ({            \
+        int old__;                                              \
+        asm volatile("btr %2,%%gs:%c3\n\tsbbl %0,%0"            \
+            : "=r" (old__), "+m" (_proxy_pda.field)             \
+            : "dIr" (bit), "i" (pda_offset(field)) : "memory"); \
+        old__;                                                  \
+})
+
 #endif
 
 #define PDA_STACKOFFSET (5*8)