3 files changed, 29 insertions, 28 deletions

diff --git a/include/linux/cpuset.h b/include/linux/cpuset.h
index e9eaec522655..7a7e5fd2a277 100644
--- a/include/linux/cpuset.h
+++ b/include/linux/cpuset.h
@@ -89,42 +89,33 @@ extern void rebuild_sched_domains(void);
 extern void cpuset_print_task_mems_allowed(struct task_struct *p);
 
 /*
- * reading current mems_allowed and mempolicy in the fastpath must protected
- * by get_mems_allowed()
+ * get_mems_allowed is required when making decisions involving mems_allowed
+ * such as during page allocation. mems_allowed can be updated in parallel
+ * and depending on the new value an operation can fail potentially causing
+ * process failure. A retry loop with get_mems_allowed and put_mems_allowed
+ * prevents these artificial failures.
  */
-static inline void get_mems_allowed(void)
+static inline unsigned int get_mems_allowed(void)
 {
-        current->mems_allowed_change_disable++;
-
-        /*
-         * ensure that reading mems_allowed and mempolicy happens after the
-         * update of ->mems_allowed_change_disable.
-         *
-         * the write-side task finds ->mems_allowed_change_disable is not 0,
-         * and knows the read-side task is reading mems_allowed or mempolicy,
-         * so it will clear old bits lazily.
-         */
-        smp_mb();
+        return read_seqcount_begin(&current->mems_allowed_seq);
 }
 
-static inline void put_mems_allowed(void)
+/*
+ * If this returns false, the operation that took place after get_mems_allowed
+ * may have failed. It is up to the caller to retry the operation if
+ * appropriate.
+ */
+static inline bool put_mems_allowed(unsigned int seq)
 {
-        /*
-         * ensure that reading mems_allowed and mempolicy before reducing
-         * mems_allowed_change_disable.
-         *
-         * the write-side task will know that the read-side task is still
-         * reading mems_allowed or mempolicy, don't clears old bits in the
-         * nodemask.
-         */
-        smp_mb();
-        --ACCESS_ONCE(current->mems_allowed_change_disable);
+        return !read_seqcount_retry(&current->mems_allowed_seq, seq);
 }
 
 static inline void set_mems_allowed(nodemask_t nodemask)
 {
         task_lock(current);
+        write_seqcount_begin(&current->mems_allowed_seq);
         current->mems_allowed = nodemask;
+        write_seqcount_end(&current->mems_allowed_seq);
         task_unlock(current);
 }
 
@@ -234,12 +225,14 @@ static inline void set_mems_allowed(nodemask_t nodemask)
 {
 }
 
-static inline void get_mems_allowed(void)
+static inline unsigned int get_mems_allowed(void)
 {
+        return 0;
 }
 
-static inline void put_mems_allowed(void)
+static inline bool put_mems_allowed(unsigned int seq)
 {
+        return true;
 }
 
 #endif /* !CONFIG_CPUSETS */
diff --git a/include/linux/init_task.h b/include/linux/init_task.h
index f994d51f70f2..e4baff5f7ff4 100644
--- a/include/linux/init_task.h
+++ b/include/linux/init_task.h
@@ -29,6 +29,13 @@ extern struct fs_struct init_fs;
 #define INIT_GROUP_RWSEM(sig)
 #endif
 
+#ifdef CONFIG_CPUSETS
+#define INIT_CPUSET_SEQ                                                 \
+        .mems_allowed_seq = SEQCNT_ZERO,
+#else
+#define INIT_CPUSET_SEQ
+#endif
+
 #define INIT_SIGNALS(sig) {                                             \
         .nr_threads     = 1,                                            \
         .wait_chldexit  = __WAIT_QUEUE_HEAD_INITIALIZER(sig.wait_chldexit),\
@@ -192,6 +199,7 @@ extern struct cred init_cred;
         INIT_FTRACE_GRAPH                                               \
         INIT_TRACE_RECURSION                                            \
         INIT_TASK_RCU_PREEMPT(tsk)                                      \
+        INIT_CPUSET_SEQ                                                 \
 }
 
 
diff --git a/include/linux/sched.h b/include/linux/sched.h
index e074e1e54f85..0c147a4260a5 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -1514,7 +1514,7 @@ struct task_struct {
 #endif
 #ifdef CONFIG_CPUSETS
         nodemask_t mems_allowed;        /* Protected by alloc_lock */
-        int mems_allowed_change_disable;
+        seqcount_t mems_allowed_seq;    /* Seqence no to catch updates */
         int cpuset_mem_spread_rotor;
         int cpuset_slab_spread_rotor;
 #endif