Merge tag 'v3.15-rc1' into patchwork

Linux 3.15-rc1

* tag 'v3.15-rc1': (12180 commits)
  Linux 3.15-rc1
  mm: Initialize error in shmem_file_aio_read()
  cifs: Use min_t() when comparing "size_t" and "unsigned long"
  sym53c8xx_2: Set DID_REQUEUE return code when aborting squeue
  powerpc: Don't try to set LPCR unless we're in hypervisor mode
  futex: update documentation for ordering guarantees
  ceph: fix pr_fmt() redefinition
  vti: don't allow to add the same tunnel twice
  gre: don't allow to add the same tunnel twice
  drivers: net: xen-netfront: fix array initialization bug
  missing bits of "splice: fix racy pipe->buffers uses"
  cifs: fix the race in cifs_writev()
  ceph_sync_{,direct_}write: fix an oops on ceph_osdc_new_request() failure
  pktgen: be friendly to LLTX devices
  r8152: check RTL8152_UNPLUG
  net: sun4i-emac: add promiscuous support
  net/apne: replace IS_ERR and PTR_ERR with PTR_ERR_OR_ZERO
  blackfin: cleanup board files
  bf609: clock: drop unused clock bit set/clear functions
  Blackfin: bf537: rename "CONFIG_ADT75"
  ...

1 files changed, 66 insertions, 14 deletions

diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c
index b3d116cd072d..0c47e300210a 100644
--- a/kernel/rcu/tree.c
+++ b/kernel/rcu/tree.c
@@ -12,8 +12,8 @@
  * GNU General Public License for more details.
  *
  * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA.
+ * along with this program; if not, you can access it online at
+ * http://www.gnu.org/licenses/gpl-2.0.html.
  *
  * Copyright IBM Corporation, 2008
  *
@@ -58,8 +58,6 @@
 #include <linux/suspend.h>
 
 #include "tree.h"
-#include <trace/events/rcu.h>
-
 #include "rcu.h"
 
 MODULE_ALIAS("rcutree");
@@ -837,7 +835,7 @@ static int rcu_implicit_dynticks_qs(struct rcu_data *rdp,
          * to the next.  Only do this for the primary flavor of RCU.
          */
         if (rdp->rsp == rcu_state &&
-            ULONG_CMP_GE(ACCESS_ONCE(jiffies), rdp->rsp->jiffies_resched)) {
+            ULONG_CMP_GE(jiffies, rdp->rsp->jiffies_resched)) {
                 rdp->rsp->jiffies_resched += 5;
                 resched_cpu(rdp->cpu);
         }
@@ -847,7 +845,7 @@ static int rcu_implicit_dynticks_qs(struct rcu_data *rdp,
 
 static void record_gp_stall_check_time(struct rcu_state *rsp)
 {
-        unsigned long j = ACCESS_ONCE(jiffies);
+        unsigned long j = jiffies;
         unsigned long j1;
 
         rsp->gp_start = j;
@@ -1005,7 +1003,7 @@ static void check_cpu_stall(struct rcu_state *rsp, struct rcu_data *rdp)
 
         if (rcu_cpu_stall_suppress || !rcu_gp_in_progress(rsp))
                 return;
-        j = ACCESS_ONCE(jiffies);
+        j = jiffies;
 
         /*
          * Lots of memory barriers to reject false positives.
@@ -1423,13 +1421,14 @@ static int rcu_gp_init(struct rcu_state *rsp)
 
         /* Advance to a new grace period and initialize state. */
         record_gp_stall_check_time(rsp);
-        smp_wmb(); /* Record GP times before starting GP. */
-        rsp->gpnum++;
+        /* Record GP times before starting GP, hence smp_store_release(). */
+        smp_store_release(&rsp->gpnum, rsp->gpnum + 1);
         trace_rcu_grace_period(rsp->name, rsp->gpnum, TPS("start"));
         raw_spin_unlock_irq(&rnp->lock);
 
         /* Exclude any concurrent CPU-hotplug operations. */
         mutex_lock(&rsp->onoff_mutex);
+        smp_mb__after_unlock_lock(); /* ->gpnum increment before GP! */
 
         /*
          * Set the quiescent-state-needed bits in all the rcu_node
@@ -1557,10 +1556,11 @@ static void rcu_gp_cleanup(struct rcu_state *rsp)
         }
         rnp = rcu_get_root(rsp);
         raw_spin_lock_irq(&rnp->lock);
-        smp_mb__after_unlock_lock();
+        smp_mb__after_unlock_lock(); /* Order GP before ->completed update. */
         rcu_nocb_gp_set(rnp, nocb);
 
-        rsp->completed = rsp->gpnum; /* Declare grace period done. */
+        /* Declare grace period done. */
+        ACCESS_ONCE(rsp->completed) = rsp->gpnum;
         trace_rcu_grace_period(rsp->name, rsp->completed, TPS("end"));
         rsp->fqs_state = RCU_GP_IDLE;
         rdp = this_cpu_ptr(rsp->rda);
@@ -2304,7 +2304,7 @@ static void force_quiescent_state(struct rcu_state *rsp)
                 if (rnp_old != NULL)
                         raw_spin_unlock(&rnp_old->fqslock);
                 if (ret) {
-                        rsp->n_force_qs_lh++;
+                        ACCESS_ONCE(rsp->n_force_qs_lh)++;
                         return;
                 }
                 rnp_old = rnp;
@@ -2316,7 +2316,7 @@ static void force_quiescent_state(struct rcu_state *rsp)
         smp_mb__after_unlock_lock();
         raw_spin_unlock(&rnp_old->fqslock);
         if (ACCESS_ONCE(rsp->gp_flags) & RCU_GP_FLAG_FQS) {
-                rsp->n_force_qs_lh++;
+                ACCESS_ONCE(rsp->n_force_qs_lh)++;
                 raw_spin_unlock_irqrestore(&rnp_old->lock, flags);
                 return;  /* Someone beat us to it. */
         }
@@ -2639,6 +2639,58 @@ void synchronize_rcu_bh(void)
 }
 EXPORT_SYMBOL_GPL(synchronize_rcu_bh);
 
+/**
+ * get_state_synchronize_rcu - Snapshot current RCU state
+ *
+ * Returns a cookie that is used by a later call to cond_synchronize_rcu()
+ * to determine whether or not a full grace period has elapsed in the
+ * meantime.
+ */
+unsigned long get_state_synchronize_rcu(void)
+{
+        /*
+         * Any prior manipulation of RCU-protected data must happen
+         * before the load from ->gpnum.
+         */
+        smp_mb();  /* ^^^ */
+
+        /*
+         * Make sure this load happens before the purportedly
+         * time-consuming work between get_state_synchronize_rcu()
+         * and cond_synchronize_rcu().
+         */
+        return smp_load_acquire(&rcu_state->gpnum);
+}
+EXPORT_SYMBOL_GPL(get_state_synchronize_rcu);
+
+/**
+ * cond_synchronize_rcu - Conditionally wait for an RCU grace period
+ *
+ * @oldstate: return value from earlier call to get_state_synchronize_rcu()
+ *
+ * If a full RCU grace period has elapsed since the earlier call to
+ * get_state_synchronize_rcu(), just return.  Otherwise, invoke
+ * synchronize_rcu() to wait for a full grace period.
+ *
+ * Yes, this function does not take counter wrap into account.  But
+ * counter wrap is harmless.  If the counter wraps, we have waited for
+ * more than 2 billion grace periods (and way more on a 64-bit system!),
+ * so waiting for one additional grace period should be just fine.
+ */
+void cond_synchronize_rcu(unsigned long oldstate)
+{
+        unsigned long newstate;
+
+        /*
+         * Ensure that this load happens before any RCU-destructive
+         * actions the caller might carry out after we return.
+         */
+        newstate = smp_load_acquire(&rcu_state->completed);
+        if (ULONG_CMP_GE(oldstate, newstate))
+                synchronize_rcu();
+}
+EXPORT_SYMBOL_GPL(cond_synchronize_rcu);
+
 static int synchronize_sched_expedited_cpu_stop(void *data)
 {
         /*
@@ -2880,7 +2932,7 @@ static int rcu_pending(int cpu)
  * non-NULL, store an indication of whether all callbacks are lazy.
  * (If there are no callbacks, all of them are deemed to be lazy.)
  */
-static int rcu_cpu_has_callbacks(int cpu, bool *all_lazy)
+static int __maybe_unused rcu_cpu_has_callbacks(int cpu, bool *all_lazy)
 {
         bool al = true;
         bool hc = false;