Linux: Stop using NR_FILE_PAGES for ARC scaling

I've found that QEMU/KVM guest memory accounted as shared also
included into NR_FILE_PAGES.  But it is actually a non-evictable
anonymous memory.  Using it as a base for zfs_arc_pc_percent
parameter makes ARC to ignore shrinker requests while page cache
does not really have anything to evict, ending up in OOM killer
killing the QEMU process.

Instead use of NR_ACTIVE_FILE + NR_INACTIVE_FILE should represent
the part of a page cache that is actually evictable, which should
be safer to use as a reference for ARC scaling.

Reviewed-by: Brian Behlendorf <[email protected]>
Reviewed-by: Ameer Hamza <[email protected]>
Reviewed-by: Pavel Snajdr <[email protected]>
Signed-off-by:	Alexander Motin <[email protected]>
Sponsored by:	iXsystems, Inc.
Closes #17334
(cherry picked from commit 0aa83dc)

Author: amotin

include/os/linux/kernel/linux/page_compat.h

@@ -4,8 +4,8 @@
 /*
  * Create our own accessor functions to follow the Linux API changes
  */
-#define	nr_file_pages() global_node_page_state(NR_FILE_PAGES)
-#define	nr_inactive_anon_pages() global_node_page_state(NR_INACTIVE_ANON)
+#define	nr_file_pages() (global_node_page_state(NR_ACTIVE_FILE) + \
+			global_node_page_state(NR_INACTIVE_FILE))
 #define	nr_inactive_file_pages() global_node_page_state(NR_INACTIVE_FILE)
 
 #endif /* _ZFS_PAGE_COMPAT_H */

man/man4/zfs.4

@@ -862,7 +862,9 @@ pressure on the pagecache, yet still allows the ARC to be reclaimed down to
 .Sy zfs_arc_min
 if necessary.
 This value is specified as percent of pagecache size (as measured by
-.Sy NR_FILE_PAGES ) ,
+.Sy NR_ACTIVE_FILE
++
+.Sy NR_INACTIVE_FILE ) ,
 where that percent may exceed
 .Sy 100 .
 This