mm/page_alloc: explicitly define what alloc flags deplete min reserves

As there are more ALLOC_ flags that affect reserves, define what flags
affect reserves and clarify the effect of each flag.

Link: https://lkml.kernel.org/r/20230113111217.14134-5-mgorman@techsingularity.net
Signed-off-by: Mel Gorman <mgorman@techsingularity.net>
Acked-by: Vlastimil Babka <vbabka@suse.cz>
Acked-by: Michal Hocko <mhocko@suse.com>
Cc: Matthew Wilcox <willy@infradead.org>
Cc: NeilBrown <neilb@suse.de>
Cc: Thierry Reding <thierry.reding@gmail.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>

diff --git a/mm/internal.h b/mm/internal.h
index 62428467d7cf4cbd674e8a6ca812e44b2d0fd4a9..f7c3bc80c475b471cca8cae5c28ff186c7740e2f 100644 (file)
--- a/mm/internal.h
+++ b/mm/internal.h
@@ -792,6 +792,9 @@ unsigned int reclaim_clean_pages_from_list(struct zone *zone,
 #define ALLOC_HIGHATOMIC       0x200 /* Allows access to MIGRATE_HIGHATOMIC */
 #define ALLOC_KSWAPD           0x800 /* allow waking of kswapd, __GFP_KSWAPD_RECLAIM set */
 
+/* Flags that allow allocations below the min watermark. */
+#define ALLOC_RESERVES (ALLOC_HARDER|ALLOC_MIN_RESERVE|ALLOC_HIGHATOMIC|ALLOC_OOM)
+
 enum ttu_flags;
 struct tlbflush_unmap_batch;
 

diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 8a7e1cfa8353c569f9071e02806225a15b0bea10..ffe2151d11eea10abf01e42aac231adb448b55b8 100644 (file)
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -3967,15 +3967,14 @@ ALLOW_ERROR_INJECTION(should_fail_alloc_page, TRUE);
 static inline long __zone_watermark_unusable_free(struct zone *z,
                                unsigned int order, unsigned int alloc_flags)
 {
-       const bool alloc_harder = (alloc_flags & (ALLOC_HARDER|ALLOC_OOM));
        long unusable_free = (1 << order) - 1;
 
        /*
-        * If the caller does not have rights to ALLOC_HARDER then subtract
-        * the high-atomic reserves. This will over-estimate the size of the
-        * atomic reserve but it avoids a search.
+        * If the caller does not have rights to reserves below the min
+        * watermark then subtract the high-atomic reserves. This will
+        * over-estimate the size of the atomic reserve but it avoids a search.
         */
-       if (likely(!alloc_harder))
+       if (likely(!(alloc_flags & ALLOC_RESERVES)))
                unusable_free += z->nr_reserved_highatomic;
 
 #ifdef CONFIG_CMA
@@ -3999,25 +3998,36 @@ bool __zone_watermark_ok(struct zone *z, unsigned int order, unsigned long mark,
 {
        long min = mark;
        int o;
-       const bool alloc_harder = (alloc_flags & (ALLOC_HARDER|ALLOC_OOM));
 
        /* free_pages may go negative - that's OK */
        free_pages -= __zone_watermark_unusable_free(z, order, alloc_flags);
 
-       if (alloc_flags & ALLOC_MIN_RESERVE)
-               min -= min / 2;
+       if (unlikely(alloc_flags & ALLOC_RESERVES)) {
+               /*
+                * __GFP_HIGH allows access to 50% of the min reserve as well
+                * as OOM.
+                */
+               if (alloc_flags & ALLOC_MIN_RESERVE)
+                       min -= min / 2;
 
-       if (unlikely(alloc_harder)) {
                /*
-                * OOM victims can try even harder than normal ALLOC_HARDER
+                * Non-blocking allocations can access some of the reserve
+                * with more access if also __GFP_HIGH. The reasoning is that
+                * a non-blocking caller may incur a more severe penalty
+                * if it cannot get memory quickly, particularly if it's
+                * also __GFP_HIGH.
+                */
+               if (alloc_flags & ALLOC_HARDER)
+                       min -= min / 4;
+
+               /*
+                * OOM victims can try even harder than the normal reserve
                 * users on the grounds that it's definitely going to be in
                 * the exit path shortly and free memory. Any allocation it
                 * makes during the free path will be small and short-lived.
                 */
                if (alloc_flags & ALLOC_OOM)
                        min -= min / 2;
-               else
-                       min -= min / 4;
        }
 
        /*