mm, page_alloc: distinguish between being unable to sleep, unwilling to sleep and avoiding waking kswapd

__GFP_WAIT has been used to identify atomic context in callers that hold
spinlocks or are in interrupts.  They are expected to be high priority and
have access one of two watermarks lower than "min" which can be referred
to as the "atomic reserve".  __GFP_HIGH users get access to the first
lower watermark and can be called the "high priority reserve".

Over time, callers had a requirement to not block when fallback options
were available.  Some have abused __GFP_WAIT leading to a situation where
an optimisitic allocation with a fallback option can access atomic
reserves.

This patch uses __GFP_ATOMIC to identify callers that are truely atomic,
cannot sleep and have no alternative.  High priority users continue to use
__GFP_HIGH.  __GFP_DIRECT_RECLAIM identifies callers that can sleep and
are willing to enter direct reclaim.  __GFP_KSWAPD_RECLAIM to identify
callers that want to wake kswapd for background reclaim.  __GFP_WAIT is
redefined as a caller that is willing to enter direct reclaim and wake
kswapd for background reclaim.

This patch then converts a number of sites

o __GFP_ATOMIC is used by callers that are high priority and have memory
  pools for those requests. GFP_ATOMIC uses this flag.

o Callers that have a limited mempool to guarantee forward progress clear
  __GFP_DIRECT_RECLAIM but keep __GFP_KSWAPD_RECLAIM. bio allocations fall
  into this category where kswapd will still be woken but atomic reserves
  are not used as there is a one-entry mempool to guarantee progress.

o Callers that are checking if they are non-blocking should use the
  helper gfpflags_allow_blocking() where possible. This is because
  checking for __GFP_WAIT as was done historically now can trigger false
  positives. Some exceptions like dm-crypt.c exist where the code intent
  is clearer if __GFP_DIRECT_RECLAIM is used instead of the helper due to
  flag manipulations.

o Callers that built their own GFP flags instead of starting with GFP_KERNEL
  and friends now also need to specify __GFP_KSWAPD_RECLAIM.

The first key hazard to watch out for is callers that removed __GFP_WAIT
and was depending on access to atomic reserves for inconspicuous reasons.
In some cases it may be appropriate for them to use __GFP_HIGH.

The second key hazard is callers that assembled their own combination of
GFP flags instead of starting with something like GFP_KERNEL.  They may
now wish to specify __GFP_KSWAPD_RECLAIM.  It's almost certainly harmless
if it's missed in most cases as other activity will wake kswapd.

Signed-off-by: Mel Gorman <mgorman@techsingularity.net>
Acked-by: Vlastimil Babka <vbabka@suse.cz>
Acked-by: Michal Hocko <mhocko@suse.com>
Acked-by: Johannes Weiner <hannes@cmpxchg.org>
Cc: Christoph Lameter <cl@linux.com>
Cc: David Rientjes <rientjes@google.com>
Cc: Vitaly Wool <vitalywool@gmail.com>
Cc: Rik van Riel <riel@redhat.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

11 files changed, 58 insertions, 46 deletions

diff --git a/mm/backing-dev.c b/mm/backing-dev.c
index 619984fc07ec..8ed2ffd963c5 100644
--- a/mm/backing-dev.c
+++ b/mm/backing-dev.c
@@ -637,7 +637,7 @@ struct bdi_writeback *wb_get_create(struct backing_dev_info *bdi,
 {
         struct bdi_writeback *wb;
 
-        might_sleep_if(gfp & __GFP_WAIT);
+        might_sleep_if(gfpflags_allow_blocking(gfp));
 
         if (!memcg_css->parent)
                 return &bdi->wb;
diff --git a/mm/dmapool.c b/mm/dmapool.c
index 312a716fa14c..57312b5d6e12 100644
--- a/mm/dmapool.c
+++ b/mm/dmapool.c
@@ -326,7 +326,7 @@ void *dma_pool_alloc(struct dma_pool *pool, gfp_t mem_flags,
         size_t offset;
         void *retval;
 
-        might_sleep_if(mem_flags & __GFP_WAIT);
+        might_sleep_if(gfpflags_allow_blocking(mem_flags));
 
         spin_lock_irqsave(&pool->lock, flags);
         list_for_each_entry(page, &pool->page_list, page_list) {
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index bc502e590366..05374f09339c 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -2046,7 +2046,7 @@ retry:
         if (unlikely(task_in_memcg_oom(current)))
                 goto nomem;
 
-        if (!(gfp_mask & __GFP_WAIT))
+        if (!gfpflags_allow_blocking(gfp_mask))
                 goto nomem;
 
         mem_cgroup_events(mem_over_limit, MEMCG_MAX, 1);
@@ -4364,8 +4364,8 @@ static int mem_cgroup_do_precharge(unsigned long count)
 {
         int ret;
 
-        /* Try a single bulk charge without reclaim first */
-        ret = try_charge(mc.to, GFP_KERNEL & ~__GFP_WAIT, count);
+        /* Try a single bulk charge without reclaim first, kswapd may wake */
+        ret = try_charge(mc.to, GFP_KERNEL & ~__GFP_DIRECT_RECLAIM, count);
         if (!ret) {
                 mc.precharge += count;
                 return ret;
diff --git a/mm/mempool.c b/mm/mempool.c
index 4c533bc51d73..004d42b1dfaf 100644
--- a/mm/mempool.c
+++ b/mm/mempool.c
@@ -320,13 +320,13 @@ void * mempool_alloc(mempool_t *pool, gfp_t gfp_mask)
         gfp_t gfp_temp;
 
         VM_WARN_ON_ONCE(gfp_mask & __GFP_ZERO);
-        might_sleep_if(gfp_mask & __GFP_WAIT);
+        might_sleep_if(gfp_mask & __GFP_DIRECT_RECLAIM);
 
         gfp_mask |= __GFP_NOMEMALLOC;   /* don't allocate emergency reserves */
         gfp_mask |= __GFP_NORETRY;      /* don't loop in __alloc_pages */
         gfp_mask |= __GFP_NOWARN;       /* failures are OK */
 
-        gfp_temp = gfp_mask & ~(__GFP_WAIT|__GFP_IO);
+        gfp_temp = gfp_mask & ~(__GFP_DIRECT_RECLAIM|__GFP_IO);
 
 repeat_alloc:
 
@@ -349,7 +349,7 @@ repeat_alloc:
         }
 
         /*
-         * We use gfp mask w/o __GFP_WAIT or IO for the first round.  If
+         * We use gfp mask w/o direct reclaim or IO for the first round.  If
          * alloc failed with that and @pool was empty, retry immediately.
          */
         if (gfp_temp != gfp_mask) {
@@ -358,8 +358,8 @@ repeat_alloc:
                 goto repeat_alloc;
         }
 
-        /* We must not sleep if !__GFP_WAIT */
-        if (!(gfp_mask & __GFP_WAIT)) {
+        /* We must not sleep if !__GFP_DIRECT_RECLAIM */
+        if (!(gfp_mask & __GFP_DIRECT_RECLAIM)) {
                 spin_unlock_irqrestore(&pool->lock, flags);
                 return NULL;
         }
diff --git a/mm/migrate.c b/mm/migrate.c
index 2834faba719a..e60379eb23f8 100644
--- a/mm/migrate.c
+++ b/mm/migrate.c
@@ -1578,7 +1578,7 @@ static struct page *alloc_misplaced_dst_page(struct page *page,
                                          (GFP_HIGHUSER_MOVABLE |
                                           __GFP_THISNODE | __GFP_NOMEMALLOC |
                                           __GFP_NORETRY | __GFP_NOWARN) &
-                                         ~GFP_IOFS, 0);
+                                         ~(__GFP_IO | __GFP_FS), 0);
 
         return newpage;
 }
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 67390988881a..70461f3e3378 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -169,12 +169,12 @@ void pm_restrict_gfp_mask(void)
         WARN_ON(!mutex_is_locked(&pm_mutex));
         WARN_ON(saved_gfp_mask);
         saved_gfp_mask = gfp_allowed_mask;
-        gfp_allowed_mask &= ~GFP_IOFS;
+        gfp_allowed_mask &= ~(__GFP_IO | __GFP_FS);
 }
 
 bool pm_suspended_storage(void)
 {
-        if ((gfp_allowed_mask & GFP_IOFS) == GFP_IOFS)
+        if ((gfp_allowed_mask & (__GFP_IO | __GFP_FS)) == (__GFP_IO | __GFP_FS))
                 return false;
         return true;
 }
@@ -2183,7 +2183,7 @@ static bool should_fail_alloc_page(gfp_t gfp_mask, unsigned int order)
                 return false;
         if (fail_page_alloc.ignore_gfp_highmem && (gfp_mask & __GFP_HIGHMEM))
                 return false;
-        if (fail_page_alloc.ignore_gfp_wait && (gfp_mask & __GFP_WAIT))
+        if (fail_page_alloc.ignore_gfp_wait && (gfp_mask & __GFP_DIRECT_RECLAIM))
                 return false;
 
         return should_fail(&fail_page_alloc.attr, 1 << order);
@@ -2685,7 +2685,7 @@ void warn_alloc_failed(gfp_t gfp_mask, int order, const char *fmt, ...)
                 if (test_thread_flag(TIF_MEMDIE) ||
                     (current->flags & (PF_MEMALLOC | PF_EXITING)))
                         filter &= ~SHOW_MEM_FILTER_NODES;
-        if (in_interrupt() || !(gfp_mask & __GFP_WAIT))
+        if (in_interrupt() || !(gfp_mask & __GFP_DIRECT_RECLAIM))
                 filter &= ~SHOW_MEM_FILTER_NODES;
 
         if (fmt) {
@@ -2945,7 +2945,6 @@ static inline int
 gfp_to_alloc_flags(gfp_t gfp_mask)
 {
         int alloc_flags = ALLOC_WMARK_MIN | ALLOC_CPUSET;
-        const bool atomic = !(gfp_mask & (__GFP_WAIT | __GFP_NO_KSWAPD));
 
         /* __GFP_HIGH is assumed to be the same as ALLOC_HIGH to save a branch. */
         BUILD_BUG_ON(__GFP_HIGH != (__force gfp_t) ALLOC_HIGH);
@@ -2954,11 +2953,11 @@ gfp_to_alloc_flags(gfp_t gfp_mask)
          * The caller may dip into page reserves a bit more if the caller
          * cannot run direct reclaim, or if the caller has realtime scheduling
          * policy or is asking for __GFP_HIGH memory.  GFP_ATOMIC requests will
-         * set both ALLOC_HARDER (atomic == true) and ALLOC_HIGH (__GFP_HIGH).
+         * set both ALLOC_HARDER (__GFP_ATOMIC) and ALLOC_HIGH (__GFP_HIGH).
          */
         alloc_flags |= (__force int) (gfp_mask & __GFP_HIGH);
 
-        if (atomic) {
+        if (gfp_mask & __GFP_ATOMIC) {
                 /*
                  * Not worth trying to allocate harder for __GFP_NOMEMALLOC even
                  * if it can't schedule.
@@ -2995,11 +2994,16 @@ bool gfp_pfmemalloc_allowed(gfp_t gfp_mask)
         return !!(gfp_to_alloc_flags(gfp_mask) & ALLOC_NO_WATERMARKS);
 }
 
+static inline bool is_thp_gfp_mask(gfp_t gfp_mask)
+{
+        return (gfp_mask & (GFP_TRANSHUGE | __GFP_KSWAPD_RECLAIM)) == GFP_TRANSHUGE;
+}
+
 static inline struct page *
 __alloc_pages_slowpath(gfp_t gfp_mask, unsigned int order,
                                                 struct alloc_context *ac)
 {
-        const gfp_t wait = gfp_mask & __GFP_WAIT;
+        bool can_direct_reclaim = gfp_mask & __GFP_DIRECT_RECLAIM;
         struct page *page = NULL;
         int alloc_flags;
         unsigned long pages_reclaimed = 0;
@@ -3020,15 +3024,23 @@ __alloc_pages_slowpath(gfp_t gfp_mask, unsigned int order,
         }
 
         /*
+         * We also sanity check to catch abuse of atomic reserves being used by
+         * callers that are not in atomic context.
+         */
+        if (WARN_ON_ONCE((gfp_mask & (__GFP_ATOMIC|__GFP_DIRECT_RECLAIM)) ==
+                                (__GFP_ATOMIC|__GFP_DIRECT_RECLAIM)))
+                gfp_mask &= ~__GFP_ATOMIC;
+
+        /*
          * If this allocation cannot block and it is for a specific node, then
          * fail early.  There's no need to wakeup kswapd or retry for a
          * speculative node-specific allocation.
          */
-        if (IS_ENABLED(CONFIG_NUMA) && (gfp_mask & __GFP_THISNODE) && !wait)
+        if (IS_ENABLED(CONFIG_NUMA) && (gfp_mask & __GFP_THISNODE) && !can_direct_reclaim)
                 goto nopage;
 
 retry:
-        if (!(gfp_mask & __GFP_NO_KSWAPD))
+        if (gfp_mask & __GFP_KSWAPD_RECLAIM)
                 wake_all_kswapds(order, ac);
 
         /*
@@ -3071,8 +3083,8 @@ retry:
                 }
         }
 
-        /* Atomic allocations - we can't balance anything */
-        if (!wait) {
+        /* Caller is not willing to reclaim, we can't balance anything */
+        if (!can_direct_reclaim) {
                 /*
                  * All existing users of the deprecated __GFP_NOFAIL are
                  * blockable, so warn of any new users that actually allow this
@@ -3102,7 +3114,7 @@ retry:
                 goto got_pg;
 
         /* Checks for THP-specific high-order allocations */
-        if ((gfp_mask & GFP_TRANSHUGE) == GFP_TRANSHUGE) {
+        if (is_thp_gfp_mask(gfp_mask)) {
                 /*
                  * If compaction is deferred for high-order allocations, it is
                  * because sync compaction recently failed. If this is the case
@@ -3137,8 +3149,7 @@ retry:
          * fault, so use asynchronous memory compaction for THP unless it is
          * khugepaged trying to collapse.
          */
-        if ((gfp_mask & GFP_TRANSHUGE) != GFP_TRANSHUGE ||
-                                                (current->flags & PF_KTHREAD))
+        if (!is_thp_gfp_mask(gfp_mask) || (current->flags & PF_KTHREAD))
                 migration_mode = MIGRATE_SYNC_LIGHT;
 
         /* Try direct reclaim and then allocating */
@@ -3209,7 +3220,7 @@ __alloc_pages_nodemask(gfp_t gfp_mask, unsigned int order,
 
         lockdep_trace_alloc(gfp_mask);
 
-        might_sleep_if(gfp_mask & __GFP_WAIT);
+        might_sleep_if(gfp_mask & __GFP_DIRECT_RECLAIM);
 
         if (should_fail_alloc_page(gfp_mask, order))
                 return NULL;
diff --git a/mm/slab.c b/mm/slab.c
index 272e809404d5..a9ef77d19a9a 100644
--- a/mm/slab.c
+++ b/mm/slab.c
@@ -1031,12 +1031,12 @@ static inline int cache_free_alien(struct kmem_cache *cachep, void *objp)
 }
 
 /*
- * Construct gfp mask to allocate from a specific node but do not invoke reclaim
- * or warn about failures.
+ * Construct gfp mask to allocate from a specific node but do not direct reclaim
+ * or warn about failures. kswapd may still wake to reclaim in the background.
  */
 static inline gfp_t gfp_exact_node(gfp_t flags)
 {
-        return (flags | __GFP_THISNODE | __GFP_NOWARN) & ~__GFP_WAIT;
+        return (flags | __GFP_THISNODE | __GFP_NOWARN) & ~__GFP_DIRECT_RECLAIM;
 }
 #endif
 
@@ -2633,7 +2633,7 @@ static int cache_grow(struct kmem_cache *cachep,
 
         offset *= cachep->colour_off;
 
-        if (local_flags & __GFP_WAIT)
+        if (gfpflags_allow_blocking(local_flags))
                 local_irq_enable();
 
         /*
@@ -2663,7 +2663,7 @@ static int cache_grow(struct kmem_cache *cachep,
 
         cache_init_objs(cachep, page);
 
-        if (local_flags & __GFP_WAIT)
+        if (gfpflags_allow_blocking(local_flags))
                 local_irq_disable();
         check_irq_off();
         spin_lock(&n->list_lock);
@@ -2677,7 +2677,7 @@ static int cache_grow(struct kmem_cache *cachep,
 opps1:
         kmem_freepages(cachep, page);
 failed:
-        if (local_flags & __GFP_WAIT)
+        if (gfpflags_allow_blocking(local_flags))
                 local_irq_disable();
         return 0;
 }
@@ -2869,7 +2869,7 @@ force_grow:
 static inline void cache_alloc_debugcheck_before(struct kmem_cache *cachep,
                                                 gfp_t flags)
 {
-        might_sleep_if(flags & __GFP_WAIT);
+        might_sleep_if(gfpflags_allow_blocking(flags));
 #if DEBUG
         kmem_flagcheck(cachep, flags);
 #endif
@@ -3057,11 +3057,11 @@ retry:
                  */
                 struct page *page;
 
-                if (local_flags & __GFP_WAIT)
+                if (gfpflags_allow_blocking(local_flags))
                         local_irq_enable();
                 kmem_flagcheck(cache, flags);
                 page = kmem_getpages(cache, local_flags, numa_mem_id());
-                if (local_flags & __GFP_WAIT)
+                if (gfpflags_allow_blocking(local_flags))
                         local_irq_disable();
                 if (page) {
                         /*
diff --git a/mm/slub.c b/mm/slub.c
index 75a5fa92ac2a..97695622a858 100644
--- a/mm/slub.c
+++ b/mm/slub.c
@@ -1265,7 +1265,7 @@ static inline struct kmem_cache *slab_pre_alloc_hook(struct kmem_cache *s,
 {
         flags &= gfp_allowed_mask;
         lockdep_trace_alloc(flags);
-        might_sleep_if(flags & __GFP_WAIT);
+        might_sleep_if(gfpflags_allow_blocking(flags));
 
         if (should_failslab(s->object_size, flags, s->flags))
                 return NULL;
@@ -1353,7 +1353,7 @@ static struct page *allocate_slab(struct kmem_cache *s, gfp_t flags, int node)
 
         flags &= gfp_allowed_mask;
 
-        if (flags & __GFP_WAIT)
+        if (gfpflags_allow_blocking(flags))
                 local_irq_enable();
 
         flags |= s->allocflags;
@@ -1363,8 +1363,8 @@ static struct page *allocate_slab(struct kmem_cache *s, gfp_t flags, int node)
          * so we fall-back to the minimum order allocation.
          */
         alloc_gfp = (flags | __GFP_NOWARN | __GFP_NORETRY) & ~__GFP_NOFAIL;
-        if ((alloc_gfp & __GFP_WAIT) && oo_order(oo) > oo_order(s->min))
-                alloc_gfp = (alloc_gfp | __GFP_NOMEMALLOC) & ~__GFP_WAIT;
+        if ((alloc_gfp & __GFP_DIRECT_RECLAIM) && oo_order(oo) > oo_order(s->min))
+                alloc_gfp = (alloc_gfp | __GFP_NOMEMALLOC) & ~__GFP_DIRECT_RECLAIM;
 
         page = alloc_slab_page(s, alloc_gfp, node, oo);
         if (unlikely(!page)) {
@@ -1424,7 +1424,7 @@ static struct page *allocate_slab(struct kmem_cache *s, gfp_t flags, int node)
         page->frozen = 1;
 
 out:
-        if (flags & __GFP_WAIT)
+        if (gfpflags_allow_blocking(flags))
                 local_irq_disable();
         if (!page)
                 return NULL;
diff --git a/mm/vmalloc.c b/mm/vmalloc.c
index 9db9ef5e8481..7ee94dc10000 100644
--- a/mm/vmalloc.c
+++ b/mm/vmalloc.c
@@ -1617,7 +1617,7 @@ static void *__vmalloc_area_node(struct vm_struct *area, gfp_t gfp_mask,
                         goto fail;
                 }
                 area->pages[i] = page;
-                if (gfp_mask & __GFP_WAIT)
+                if (gfpflags_allow_blocking(gfp_mask))
                         cond_resched();
         }
 
diff --git a/mm/vmscan.c b/mm/vmscan.c
index e0cd7eed4e38..2aec4241b42a 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -1476,7 +1476,7 @@ static int too_many_isolated(struct zone *zone, int file,
          * won't get blocked by normal direct-reclaimers, forming a circular
          * deadlock.
          */
-        if ((sc->gfp_mask & GFP_IOFS) == GFP_IOFS)
+        if ((sc->gfp_mask & (__GFP_IO | __GFP_FS)) == (__GFP_IO | __GFP_FS))
                 inactive >>= 3;
 
         return isolated > inactive;
@@ -3791,7 +3791,7 @@ int zone_reclaim(struct zone *zone, gfp_t gfp_mask, unsigned int order)
         /*
          * Do not scan if the allocation should not be delayed.
          */
-        if (!(gfp_mask & __GFP_WAIT) || (current->flags & PF_MEMALLOC))
+        if (!gfpflags_allow_blocking(gfp_mask) || (current->flags & PF_MEMALLOC))
                 return ZONE_RECLAIM_NOSCAN;
 
         /*
diff --git a/mm/zswap.c b/mm/zswap.c
index 4043df7c672f..e54166d3732e 100644
--- a/mm/zswap.c
+++ b/mm/zswap.c
@@ -571,7 +571,7 @@ static struct zswap_pool *zswap_pool_find_get(char *type, char *compressor)
 static struct zswap_pool *zswap_pool_create(char *type, char *compressor)
 {
         struct zswap_pool *pool;
-        gfp_t gfp = __GFP_NORETRY | __GFP_NOWARN;
+        gfp_t gfp = __GFP_NORETRY | __GFP_NOWARN | __GFP_KSWAPD_RECLAIM;
 
         pool = kzalloc(sizeof(*pool), GFP_KERNEL);
         if (!pool) {
@@ -1011,7 +1011,8 @@ static int zswap_frontswap_store(unsigned type, pgoff_t offset,
         /* store */
         len = dlen + sizeof(struct zswap_header);
         ret = zpool_malloc(entry->pool->zpool, len,
-                           __GFP_NORETRY | __GFP_NOWARN, &handle);
+                           __GFP_NORETRY | __GFP_NOWARN | __GFP_KSWAPD_RECLAIM,
+                           &handle);
         if (ret == -ENOSPC) {
                 zswap_reject_compress_poor++;
                 goto put_dstmem;