revert "Revert "mm: remove __GFP_NO_KSWAPD""

It apepars that this patch was innocent, and we hope that "mm: avoid
waking kswapd for THP allocations when compaction is deferred or
contended" will fix the final kswapd-spinning cause.

Cc: Zdenek Kabelac <zkabelac@redhat.com>
Cc: Seth Jennings <sjenning@linux.vnet.ibm.com>
Cc: Valdis Kletnieks <Valdis.Kletnieks@vt.edu>
Cc: Jiri Slaby <jirislaby@gmail.com>
Cc: Rik van Riel <riel@redhat.com>
Cc: Robert Jennings <rcj@linux.vnet.ibm.com>
Cc: Mel Gorman <mgorman@suse.de>
Signed-off-by: NAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>

drivers/mtd/mtdcore.c

@@ -1077,8 +1077,7 @@ EXPORT_SYMBOL_GPL(mtd_writev);
  * until the request succeeds or until the allocation size falls below
  * the system page size. This attempts to make sure it does not adversely
  * impact system performance, so when allocating more than one page, we
- * ask the memory allocator to avoid re-trying, swapping, writing back
- * or performing I/O.
+ * ask the memory allocator to avoid re-trying.
  *
  * Note, this function also makes sure that the allocated buffer is aligned to
  * the MTD device's min. I/O unit, i.e. the "mtd->writesize" value.
@@ -1092,8 +1091,7 @@ EXPORT_SYMBOL_GPL(mtd_writev);
  */
 void *mtd_kmalloc_up_to(const struct mtd_info *mtd, size_t *size)
 {
-	gfp_t flags = __GFP_NOWARN | __GFP_WAIT |
-		       __GFP_NORETRY | __GFP_NO_KSWAPD;
+	gfp_t flags = __GFP_NOWARN | __GFP_WAIT | __GFP_NORETRY;
 	size_t min_alloc = max_t(size_t, mtd->writesize, PAGE_SIZE);
 	void *kbuf;
 

include/linux/gfp.h

@@ -30,10 +30,9 @@ struct vm_area_struct;
 #define ___GFP_HARDWALL		0x20000u
 #define ___GFP_THISNODE		0x40000u
 #define ___GFP_RECLAIMABLE	0x80000u
-#define ___GFP_NOTRACK		0x200000u
-#define ___GFP_NO_KSWAPD	0x400000u
-#define ___GFP_OTHER_NODE	0x800000u
-#define ___GFP_WRITE		0x1000000u
+#define ___GFP_NOTRACK		0x100000u
+#define ___GFP_OTHER_NODE	0x200000u
+#define ___GFP_WRITE		0x400000u
 
 /*
  * GFP bitmasks..
@@ -86,7 +85,6 @@ struct vm_area_struct;
 #define __GFP_RECLAIMABLE ((__force gfp_t)___GFP_RECLAIMABLE) /* Page is reclaimable */
 #define __GFP_NOTRACK	((__force gfp_t)___GFP_NOTRACK)  /* Don't track with kmemcheck */
 
-#define __GFP_NO_KSWAPD	((__force gfp_t)___GFP_NO_KSWAPD)
 #define __GFP_OTHER_NODE ((__force gfp_t)___GFP_OTHER_NODE) /* On behalf of other node */
 #define __GFP_WRITE	((__force gfp_t)___GFP_WRITE)	/* Allocator intends to dirty page */
 
@@ -96,7 +94,7 @@ struct vm_area_struct;
  */
 #define __GFP_NOTRACK_FALSE_POSITIVE (__GFP_NOTRACK)
 
-#define __GFP_BITS_SHIFT 25	/* Room for N __GFP_FOO bits */
+#define __GFP_BITS_SHIFT 23	/* Room for N __GFP_FOO bits */
 #define __GFP_BITS_MASK ((__force gfp_t)((1 << __GFP_BITS_SHIFT) - 1))
 
 /* This equals 0, but use constants in case they ever change */
@@ -116,8 +114,7 @@ struct vm_area_struct;
 				 __GFP_MOVABLE)
 #define GFP_IOFS	(__GFP_IO | __GFP_FS)
 #define GFP_TRANSHUGE	(GFP_HIGHUSER_MOVABLE | __GFP_COMP | \
-			 __GFP_NOMEMALLOC | __GFP_NORETRY | __GFP_NOWARN | \
-			 __GFP_NO_KSWAPD)
+			 __GFP_NOMEMALLOC | __GFP_NORETRY | __GFP_NOWARN)
 
 #ifdef CONFIG_NUMA
 #define GFP_THISNODE	(__GFP_THISNODE | __GFP_NOWARN | __GFP_NORETRY)

include/trace/events/gfpflags.h

@@ -36,7 +36,6 @@
 	{(unsigned long)__GFP_RECLAIMABLE,	"GFP_RECLAIMABLE"},	\
 	{(unsigned long)__GFP_MOVABLE,		"GFP_MOVABLE"},		\
 	{(unsigned long)__GFP_NOTRACK,		"GFP_NOTRACK"},		\
-	{(unsigned long)__GFP_NO_KSWAPD,	"GFP_NO_KSWAPD"},	\
 	{(unsigned long)__GFP_OTHER_NODE,	"GFP_OTHER_NODE"}	\
 	) : "GFP_NOWAIT"
 

mm/page_alloc.c

@@ -2416,9 +2416,8 @@ __alloc_pages_slowpath(gfp_t gfp_mask, unsigned int order,
 		goto nopage;
 
 restart:
-	if (!(gfp_mask & __GFP_NO_KSWAPD))
-		wake_all_kswapd(order, zonelist, high_zoneidx,
-						zone_idx(preferred_zone));
+	wake_all_kswapd(order, zonelist, high_zoneidx,
+					zone_idx(preferred_zone));
 
 	/*
 	 * OK, we're below the kswapd watermark and have kicked background
@@ -2495,7 +2494,7 @@ __alloc_pages_slowpath(gfp_t gfp_mask, unsigned int order,
 	 * system then fail the allocation instead of entering direct reclaim.
 	 */
 	if ((deferred_compaction || contended_compaction) &&
-						(gfp_mask & __GFP_NO_KSWAPD))
+	    (gfp_mask & (__GFP_MOVABLE|__GFP_REPEAT)) == __GFP_MOVABLE)
 		goto nopage;
 
 	/* Try direct reclaim and then allocating */