mm: rename and change semantics of nr_indirectly_reclaimable_bytes

The vmstat counter NR_INDIRECTLY_RECLAIMABLE_BYTES was introduced by
commit eb59254608bc ("mm: introduce NR_INDIRECTLY_RECLAIMABLE_BYTES") with
the goal of accounting objects that can be reclaimed, but cannot be
allocated via a SLAB_RECLAIM_ACCOUNT cache.  This is now possible via
kmalloc() with __GFP_RECLAIMABLE flag, and the dcache external names user
is converted.

The counter is however still useful for accounting direct page allocations
(i.e.  not slab) with a shrinker, such as the ION page pool.  So keep it,
and:

- change granularity to pages to be more like other counters; sub-page
  allocations should be able to use kmalloc
- rename the counter to NR_KERNEL_MISC_RECLAIMABLE
- expose the counter again in vmstat as "nr_kernel_misc_reclaimable"; we can
  again remove the check for not printing "hidden" counters

Link: http://lkml.kernel.org/r/20180731090649.16028-5-vbabka@suse.cz
Signed-off-by: Vlastimil Babka <vbabka@suse.cz>
Acked-by: Christoph Lameter <cl@linux.com>
Acked-by: Roman Gushchin <guro@fb.com>
Cc: Vijayanand Jitta <vjitta@codeaurora.org>
Cc: Laura Abbott <labbott@redhat.com>
Cc: Sumit Semwal <sumit.semwal@linaro.org>
Cc: David Rientjes <rientjes@google.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Joonsoo Kim <iamjoonsoo.kim@lge.com>
Cc: Matthew Wilcox <willy@infradead.org>
Cc: Mel Gorman <mgorman@techsingularity.net>
Cc: Michal Hocko <mhocko@kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

diff --git a/drivers/staging/android/ion/ion_page_pool.c b/drivers/staging/android/ion/ion_page_pool.c
index 9bc56eb..0d2a959 100644 (file)
--- a/drivers/staging/android/ion/ion_page_pool.c
+++ b/drivers/staging/android/ion/ion_page_pool.c
@@ -33,8 +33,8 @@ static void ion_page_pool_add(struct ion_page_pool *pool, struct page *page)
                pool->low_count++;
        }
 
-       mod_node_page_state(page_pgdat(page), NR_INDIRECTLY_RECLAIMABLE_BYTES,
-                           (1 << (PAGE_SHIFT + pool->order)));
+       mod_node_page_state(page_pgdat(page), NR_KERNEL_MISC_RECLAIMABLE,
+                                                       1 << pool->order);
        mutex_unlock(&pool->mutex);
 }
 
@@ -53,8 +53,8 @@ static struct page *ion_page_pool_remove(struct ion_page_pool *pool, bool high)
        }
 
        list_del(&page->lru);
-       mod_node_page_state(page_pgdat(page), NR_INDIRECTLY_RECLAIMABLE_BYTES,
-                           -(1 << (PAGE_SHIFT + pool->order)));
+       mod_node_page_state(page_pgdat(page), NR_KERNEL_MISC_RECLAIMABLE,
+                                                       -(1 << pool->order));
        return page;
 }
 

diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h
index d4b0c79..7bbeba2 100644 (file)
--- a/include/linux/mmzone.h
+++ b/include/linux/mmzone.h
@@ -180,7 +180,7 @@ enum node_stat_item {
        NR_VMSCAN_IMMEDIATE,    /* Prioritise for reclaim when writeback ends */
        NR_DIRTIED,             /* page dirtyings since bootup */
        NR_WRITTEN,             /* page writings since bootup */
-       NR_INDIRECTLY_RECLAIMABLE_BYTES, /* measured in bytes */
+       NR_KERNEL_MISC_RECLAIMABLE,     /* reclaimable non-slab kernel pages */
        NR_VM_NODE_STAT_ITEMS
 };
 

diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 747031c..20f25d0 100644 (file)
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -4701,6 +4701,7 @@ long si_mem_available(void)
        unsigned long pagecache;
        unsigned long wmark_low = 0;
        unsigned long pages[NR_LRU_LISTS];
+       unsigned long reclaimable;
        struct zone *zone;
        int lru;
 
@@ -4726,19 +4727,13 @@ long si_mem_available(void)
        available += pagecache;
 
        /*
-        * Part of the reclaimable slab consists of items that are in use,
-        * and cannot be freed. Cap this estimate at the low watermark.
+        * Part of the reclaimable slab and other kernel memory consists of
+        * items that are in use, and cannot be freed. Cap this estimate at the
+        * low watermark.
         */
-       available += global_node_page_state(NR_SLAB_RECLAIMABLE) -
-                    min(global_node_page_state(NR_SLAB_RECLAIMABLE) / 2,
-                        wmark_low);
-
-       /*
-        * Part of the kernel memory, which can be released under memory
-        * pressure.
-        */
-       available += global_node_page_state(NR_INDIRECTLY_RECLAIMABLE_BYTES) >>
-               PAGE_SHIFT;
+       reclaimable = global_node_page_state(NR_SLAB_RECLAIMABLE) +
+                       global_node_page_state(NR_KERNEL_MISC_RECLAIMABLE);
+       available += reclaimable - min(reclaimable / 2, wmark_low);
 
        if (available < 0)
                available = 0;

diff --git a/mm/util.c b/mm/util.c
index 470f5cd..f740754 100644 (file)
--- a/mm/util.c
+++ b/mm/util.c
@@ -678,8 +678,7 @@ int __vm_enough_memory(struct mm_struct *mm, long pages, int cap_sys_admin)
                 * Part of the kernel memory, which can be released
                 * under memory pressure.
                 */
-               free += global_node_page_state(
-                       NR_INDIRECTLY_RECLAIMABLE_BYTES) >> PAGE_SHIFT;
+               free += global_node_page_state(NR_KERNEL_MISC_RECLAIMABLE);
 
                /*
                 * Leave reserved pages. The pages are not for anonymous pages.

diff --git a/mm/vmstat.c b/mm/vmstat.c
index 7878da7..2cec2fa 100644 (file)
--- a/mm/vmstat.c
+++ b/mm/vmstat.c
@@ -1161,7 +1161,7 @@ const char * const vmstat_text[] = {
        "nr_vmscan_immediate_reclaim",
        "nr_dirtied",
        "nr_written",
-       "", /* nr_indirectly_reclaimable */
+       "nr_kernel_misc_reclaimable",
 
        /* enum writeback_stat_item counters */
        "nr_dirty_threshold",
@@ -1706,10 +1706,6 @@ static int vmstat_show(struct seq_file *m, void *arg)
        unsigned long *l = arg;
        unsigned long off = l - (unsigned long *)m->private;
 
-       /* Skip hidden vmstat items. */
-       if (*vmstat_text[off] == '\0')
-               return 0;
-
        seq_puts(m, vmstat_text[off]);
        seq_put_decimal_ull(m, " ", *l);
        seq_putc(m, '\n');