Revert "revert "Revert "mm: remove __GFP_NO_KSWAPD""" and associated damage

This reverts commits a50915394f1fc02c2861d3b7ce7014788aa5066e and
d7c3b937bdf45f0b844400b7bf6fd3ed50bac604.

This is a revert of a revert of a revert.  In addition, it reverts the
even older i915 change to stop using the __GFP_NO_KSWAPD flag due to the
original commits in linux-next.

It turns out that the original patch really was bogus, and that the
original revert was the correct thing to do after all.  We thought we
had fixed the problem, and then reverted the revert, but the problem
really is fundamental: waking up kswapd simply isn't the right thing to
do, and direct reclaim sometimes simply _is_ the right thing to do.

When certain allocations fail, we simply should try some direct reclaim,
and if that fails, fail the allocation.  That's the right thing to do
for THP allocations, which can easily fail, and the GPU allocations want
to do that too.

So starting kswapd is sometimes simply wrong, and removing the flag that
said "don't start kswapd" was a mistake.  Let's hope we never revisit
this mistake again - and certainly not this many times ;)

Acked-by: Mel Gorman <mgorman@suse.de>
Acked-by: Johannes Weiner <hannes@cmpxchg.org>
Cc: Rik van Riel <riel@redhat.com>
Cc: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c
index 107f09befe929540e9ad801ff2bbdfe97a6b651d..9b285da4449b005c3c38a2ac7001c3c222b2deed 100644 (file)
--- a/drivers/gpu/drm/i915/i915_gem.c
+++ b/drivers/gpu/drm/i915/i915_gem.c
@@ -1796,7 +1796,7 @@ i915_gem_object_get_pages_gtt(struct drm_i915_gem_object *obj)
         */
        mapping = obj->base.filp->f_path.dentry->d_inode->i_mapping;
        gfp = mapping_gfp_mask(mapping);
-       gfp |= __GFP_NORETRY | __GFP_NOWARN;
+       gfp |= __GFP_NORETRY | __GFP_NOWARN | __GFP_NO_KSWAPD;
        gfp &= ~(__GFP_IO | __GFP_WAIT);
        for_each_sg(st->sgl, sg, page_count, i) {
                page = shmem_read_mapping_page_gfp(mapping, i, gfp);
@@ -1809,7 +1809,7 @@ i915_gem_object_get_pages_gtt(struct drm_i915_gem_object *obj)
                         * our own buffer, now let the real VM do its job and
                         * go down in flames if truly OOM.
                         */
-                       gfp &= ~(__GFP_NORETRY | __GFP_NOWARN);
+                       gfp &= ~(__GFP_NORETRY | __GFP_NOWARN | __GFP_NO_KSWAPD);
                        gfp |= __GFP_IO | __GFP_WAIT;
 
                        i915_gem_shrink_all(dev_priv);
@@ -1817,7 +1817,7 @@ i915_gem_object_get_pages_gtt(struct drm_i915_gem_object *obj)
                        if (IS_ERR(page))
                                goto err_pages;
 
-                       gfp |= __GFP_NORETRY | __GFP_NOWARN;
+                       gfp |= __GFP_NORETRY | __GFP_NOWARN | __GFP_NO_KSWAPD;
                        gfp &= ~(__GFP_IO | __GFP_WAIT);
                }
 

diff --git a/drivers/mtd/mtdcore.c b/drivers/mtd/mtdcore.c
index 374c46dff7dd65d3aea7eef69b22a332d727ad0f..ec794a72975dd886205f2460e2eaba08089a8daf 100644 (file)
--- a/drivers/mtd/mtdcore.c
+++ b/drivers/mtd/mtdcore.c
@@ -1077,7 +1077,8 @@ 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.
+ * ask the memory allocator to avoid re-trying, swapping, writing back
+ * or performing I/O.
  *
  * 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.
@@ -1091,7 +1092,8 @@ 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_t flags = __GFP_NOWARN | __GFP_WAIT |
+                      __GFP_NORETRY | __GFP_NO_KSWAPD;
        size_t min_alloc = max_t(size_t, mtd->writesize, PAGE_SIZE);
        void *kbuf;
 

diff --git a/include/linux/gfp.h b/include/linux/gfp.h
index 76e1aa206f574d34cdcf0a69682b5d34332c5b87..d0a79678f169f8c9a7675e4343419975cbb29142 100644 (file)
--- a/include/linux/gfp.h
+++ b/include/linux/gfp.h
@@ -30,9 +30,10 @@ struct vm_area_struct;
 #define ___GFP_HARDWALL                0x20000u
 #define ___GFP_THISNODE                0x40000u
 #define ___GFP_RECLAIMABLE     0x80000u
-#define ___GFP_NOTRACK         0x100000u
-#define ___GFP_OTHER_NODE      0x200000u
-#define ___GFP_WRITE           0x400000u
+#define ___GFP_NOTRACK         0x200000u
+#define ___GFP_NO_KSWAPD       0x400000u
+#define ___GFP_OTHER_NODE      0x800000u
+#define ___GFP_WRITE           0x1000000u
 
 /*
  * GFP bitmasks..
@@ -85,6 +86,7 @@ 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 */
 
@@ -94,7 +96,7 @@ struct vm_area_struct;
  */
 #define __GFP_NOTRACK_FALSE_POSITIVE (__GFP_NOTRACK)
 
-#define __GFP_BITS_SHIFT 23    /* Room for N __GFP_FOO bits */
+#define __GFP_BITS_SHIFT 25    /* 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 */
@@ -114,7 +116,8 @@ 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_NOMEMALLOC | __GFP_NORETRY | __GFP_NOWARN | \
+                        __GFP_NO_KSWAPD)
 
 #ifdef CONFIG_NUMA
 #define GFP_THISNODE   (__GFP_THISNODE | __GFP_NOWARN | __GFP_NORETRY)

diff --git a/include/trace/events/gfpflags.h b/include/trace/events/gfpflags.h
index 9391706e92541d2b5d865610a88525bf8215a599..d6fd8e5b14b76c41bfd532c3fa86255e4e92b0f3 100644 (file)
--- a/include/trace/events/gfpflags.h
+++ b/include/trace/events/gfpflags.h
@@ -36,6 +36,7 @@
        {(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"
 

diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 8193809f3de0e683b1bcfb95954f37316768c851..7e208f0ad68ccb1468b408b5a50a981be8beb3a5 100644 (file)
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -2416,8 +2416,9 @@ __alloc_pages_slowpath(gfp_t gfp_mask, unsigned int order,
                goto nopage;
 
 restart:
-       wake_all_kswapd(order, zonelist, high_zoneidx,
-                                       zone_idx(preferred_zone));
+       if (!(gfp_mask & __GFP_NO_KSWAPD))
+               wake_all_kswapd(order, zonelist, high_zoneidx,
+                                               zone_idx(preferred_zone));
 
        /*
         * OK, we're below the kswapd watermark and have kicked background
@@ -2494,7 +2495,7 @@ rebalance:
         * system then fail the allocation instead of entering direct reclaim.
         */
        if ((deferred_compaction || contended_compaction) &&
-           (gfp_mask & (__GFP_MOVABLE|__GFP_REPEAT)) == __GFP_MOVABLE)
+                                               (gfp_mask & __GFP_NO_KSWAPD))
                goto nopage;
 
        /* Try direct reclaim and then allocating */