Merge tag 'v3.8-rc3' into v4l_for_linus

Linux 3.8-rc3

* tag 'v3.8-rc3': (11110 commits)
  Linux 3.8-rc3
  mm: reinstante dropped pmd_trans_splitting() check
  cred: Remove tgcred pointer from struct cred
  drm/ttm: fix fence locking in ttm_buffer_object_transfer
  ARM: clps711x: Fix bad merge of clockevents setup
  ARM: highbank: save and restore L2 cache and GIC on suspend
  ARM: highbank: add a power request clear
  ARM: highbank: fix secondary boot and hotplug
  ARM: highbank: fix typos with hignbank in power request functions
  ARM: dts: fix highbank cpu mpidr values
  ARM: dts: add device_type prop to cpu nodes on Calxeda platforms
  drm/prime: drop reference on imported dma-buf come from gem
  xen/netfront: improve truesize tracking
  ARM: mx5: Fix MX53 flexcan2 clock
  ARM: OMAP2+: am33xx-hwmod: Fix wrongly terminated am33xx_usbss_mpu_irqs array
  sctp: fix Kconfig bug in default cookie hmac selection
  EDAC: Cleanup device deregistering path
  EDAC: Fix EDAC Kconfig menu
  EDAC: Fix kernel panic on module unloading
  ALSA: hda - add mute LED for HP Pavilion 17 (Realtek codec)
  ...

1 files changed, 47 insertions, 24 deletions

diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h
index a23923ba826..73b64a38b98 100644
--- a/include/linux/mmzone.h
+++ b/include/linux/mmzone.h
@@ -63,10 +63,8 @@ enum {
 
 #ifdef CONFIG_CMA
 #  define is_migrate_cma(migratetype) unlikely((migratetype) == MIGRATE_CMA)
-#  define cma_wmark_pages(zone)	zone->min_cma_pages
 #else
 #  define is_migrate_cma(migratetype) false
-#  define cma_wmark_pages(zone) 0
 #endif
 
 #define for_each_migratetype_order(order, type) \
@@ -383,13 +381,6 @@ struct zone {
 	/* see spanned/present_pages for more description */
 	seqlock_t		span_seqlock;
 #endif
-#ifdef CONFIG_CMA
-	/*
-	 * CMA needs to increase watermark levels during the allocation
-	 * process to make sure that the system is not starved.
-	 */
-	unsigned long		min_cma_pages;
-#endif
 	struct free_area	free_area[MAX_ORDER];
 
 #ifndef CONFIG_SPARSEMEM
@@ -469,30 +460,49 @@ struct zone {
 	unsigned long		zone_start_pfn;
 
 	/*
-	 * zone_start_pfn, spanned_pages and present_pages are all
-	 * protected by span_seqlock.  It is a seqlock because it has
-	 * to be read outside of zone->lock, and it is done in the main
-	 * allocator path.  But, it is written quite infrequently.
+	 * spanned_pages is the total pages spanned by the zone, including
+	 * holes, which is calculated as:
+	 * 	spanned_pages = zone_end_pfn - zone_start_pfn;
+	 *
+	 * present_pages is physical pages existing within the zone, which
+	 * is calculated as:
+	 *	present_pages = spanned_pages - absent_pages(pags in holes);
+	 *
+	 * managed_pages is present pages managed by the buddy system, which
+	 * is calculated as (reserved_pages includes pages allocated by the
+	 * bootmem allocator):
+	 *	managed_pages = present_pages - reserved_pages;
+	 *
+	 * So present_pages may be used by memory hotplug or memory power
+	 * management logic to figure out unmanaged pages by checking
+	 * (present_pages - managed_pages). And managed_pages should be used
+	 * by page allocator and vm scanner to calculate all kinds of watermarks
+	 * and thresholds.
+	 *
+	 * Locking rules:
+	 *
+	 * zone_start_pfn and spanned_pages are protected by span_seqlock.
+	 * It is a seqlock because it has to be read outside of zone->lock,
+	 * and it is done in the main allocator path.  But, it is written
+	 * quite infrequently.
 	 *
-	 * The lock is declared along with zone->lock because it is
+	 * The span_seq lock is declared along with zone->lock because it is
 	 * frequently read in proximity to zone->lock.  It's good to
 	 * give them a chance of being in the same cacheline.
+	 *
+	 * Write access to present_pages and managed_pages at runtime should
+	 * be protected by lock_memory_hotplug()/unlock_memory_hotplug().
+	 * Any reader who can't tolerant drift of present_pages and
+	 * managed_pages should hold memory hotplug lock to get a stable value.
 	 */
-	unsigned long		spanned_pages;	/* total size, including holes */
-	unsigned long		present_pages;	/* amount of memory (excluding holes) */
+	unsigned long		spanned_pages;
+	unsigned long		present_pages;
+	unsigned long		managed_pages;
 
 	/*
 	 * rarely used fields:
 	 */
 	const char		*name;
-#ifdef CONFIG_MEMORY_ISOLATION
-	/*
-	 * the number of MIGRATE_ISOLATE *pageblock*.
-	 * We need this for free page counting. Look at zone_watermark_ok_safe.
-	 * It's protected by zone->lock
-	 */
-	int		nr_pageblock_isolate;
-#endif
 } ____cacheline_internodealigned_in_smp;
 
 typedef enum {
@@ -717,6 +727,19 @@ typedef struct pglist_data {
 	struct task_struct *kswapd;	/* Protected by lock_memory_hotplug() */
 	int kswapd_max_order;
 	enum zone_type classzone_idx;
+#ifdef CONFIG_NUMA_BALANCING
+	/*
+	 * Lock serializing the per destination node AutoNUMA memory
+	 * migration rate limiting data.
+	 */
+	spinlock_t numabalancing_migrate_lock;
+
+	/* Rate limiting time interval */
+	unsigned long numabalancing_migrate_next_window;
+
+	/* Number of pages migrated during the rate limiting time interval */
+	unsigned long numabalancing_migrate_nr_pages;
+#endif
 } pg_data_t;
 
 #define node_present_pages(nid)	(NODE_DATA(nid)->node_present_pages)