Merge remote-tracking branch 'stable/linux-3.10.y' into linux-linaro-lsk

Conflicts:
	arch/arm64/kernel/smp.c

Signed-off-by: Alex Shi <alex.shi@linaro.org>

5 files changed, 64 insertions, 5 deletions

diff --git a/include/linux/auxvec.h b/include/linux/auxvec.h
index 669fef5c745..3e0fbe44176 100644
--- a/include/linux/auxvec.h
+++ b/include/linux/auxvec.h
@@ -3,6 +3,6 @@
 
 #include <uapi/linux/auxvec.h>
 
-#define AT_VECTOR_SIZE_BASE 19 /* NEW_AUX_ENT entries in auxiliary table */
+#define AT_VECTOR_SIZE_BASE 20 /* NEW_AUX_ENT entries in auxiliary table */
   /* number of "#define AT_.*" above, minus {AT_NULL, AT_IGNORE, AT_NOTELF} */
 #endif /* _LINUX_AUXVEC_H */
diff --git a/include/linux/ceph/osd_client.h b/include/linux/ceph/osd_client.h
index 186db0bf495..8f47625a066 100644
--- a/include/linux/ceph/osd_client.h
+++ b/include/linux/ceph/osd_client.h
@@ -145,7 +145,6 @@ struct ceph_osd_request {
 	s32               r_reply_op_result[CEPH_OSD_MAX_OP];
 	int               r_got_reply;
 	int		  r_linger;
-	int		  r_completed;
 
 	struct ceph_osd_client *r_osdc;
 	struct kref       r_kref;
@@ -336,6 +335,8 @@ extern int ceph_osdc_wait_request(struct ceph_osd_client *osdc,
 				  struct ceph_osd_request *req);
 extern void ceph_osdc_sync(struct ceph_osd_client *osdc);
 
+extern void ceph_osdc_flush_notifies(struct ceph_osd_client *osdc);
+
 extern int ceph_osdc_readpages(struct ceph_osd_client *osdc,
 			       struct ceph_vino vino,
 			       struct ceph_file_layout *layout,
diff --git a/include/linux/libata.h b/include/linux/libata.h
index eae7a053dc5..9a4c194ebc8 100644
--- a/include/linux/libata.h
+++ b/include/linux/libata.h
@@ -399,6 +399,7 @@ enum {
 	ATA_HORKAGE_BROKEN_FPDMA_AA	= (1 << 15),	/* skip AA */
 	ATA_HORKAGE_DUMP_ID	= (1 << 16),	/* dump IDENTIFY data */
 	ATA_HORKAGE_MAX_SEC_LBA48 = (1 << 17),	/* Set max sects to 65535 */
+	ATA_HORKAGE_ATAPI_DMADIR = (1 << 18),	/* device requires dmadir */
 
 	 /* DMA mask for user DMA control: User visible values; DO NOT
 	    renumber */
diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h
index 4a189ba6b12..10a9a17342f 100644
--- a/include/linux/mm_types.h
+++ b/include/linux/mm_types.h
@@ -437,6 +437,14 @@ struct mm_struct {
 	 */
 	int first_nid;
 #endif
+#if defined(CONFIG_NUMA_BALANCING) || defined(CONFIG_COMPACTION)
+	/*
+	 * An operation with batched TLB flushing is going on. Anything that
+	 * can move process memory needs to flush the TLB when moving a
+	 * PROT_NONE or PROT_NUMA mapped page.
+	 */
+	bool tlb_flush_pending;
+#endif
 	struct uprobes_state uprobes_state;
 };
 
@@ -457,4 +465,45 @@ static inline cpumask_t *mm_cpumask(struct mm_struct *mm)
 	return mm->cpu_vm_mask_var;
 }
 
+#if defined(CONFIG_NUMA_BALANCING) || defined(CONFIG_COMPACTION)
+/*
+ * Memory barriers to keep this state in sync are graciously provided by
+ * the page table locks, outside of which no page table modifications happen.
+ * The barriers below prevent the compiler from re-ordering the instructions
+ * around the memory barriers that are already present in the code.
+ */
+static inline bool mm_tlb_flush_pending(struct mm_struct *mm)
+{
+	barrier();
+	return mm->tlb_flush_pending;
+}
+static inline void set_tlb_flush_pending(struct mm_struct *mm)
+{
+	mm->tlb_flush_pending = true;
+
+	/*
+	 * Guarantee that the tlb_flush_pending store does not leak into the
+	 * critical section updating the page tables
+	 */
+	smp_mb__before_spinlock();
+}
+/* Clearing is done after a TLB flush, which also provides a barrier. */
+static inline void clear_tlb_flush_pending(struct mm_struct *mm)
+{
+	barrier();
+	mm->tlb_flush_pending = false;
+}
+#else
+static inline bool mm_tlb_flush_pending(struct mm_struct *mm)
+{
+	return false;
+}
+static inline void set_tlb_flush_pending(struct mm_struct *mm)
+{
+}
+static inline void clear_tlb_flush_pending(struct mm_struct *mm)
+{
+}
+#endif
+
 #endif /* _LINUX_MM_TYPES_H */
diff --git a/include/linux/spinlock.h b/include/linux/spinlock.h
index 7d537ced949..75f34949d9a 100644
--- a/include/linux/spinlock.h
+++ b/include/linux/spinlock.h
@@ -117,9 +117,17 @@ do {								\
 #endif /*arch_spin_is_contended*/
 #endif
 
-/* The lock does not imply full memory barrier. */
-#ifndef ARCH_HAS_SMP_MB_AFTER_LOCK
-static inline void smp_mb__after_lock(void) { smp_mb(); }
+/*
+ * Despite its name it doesn't necessarily has to be a full barrier.
+ * It should only guarantee that a STORE before the critical section
+ * can not be reordered with a LOAD inside this section.
+ * spin_lock() is the one-way barrier, this LOAD can not escape out
+ * of the region. So the default implementation simply ensures that
+ * a STORE can not move into the critical section, smp_wmb() should
+ * serialize it with another STORE done by spin_lock().
+ */
+#ifndef smp_mb__before_spinlock
+#define smp_mb__before_spinlock()	smp_wmb()
 #endif
 
 /**