summaryrefslogtreecommitdiff
path: root/mm/vmscan.c
diff options
context:
space:
mode:
authorMinchan Kim <minchan@kernel.org>2019-09-25 16:49:15 -0700
committerLinus Torvalds <torvalds@linux-foundation.org>2019-09-25 17:51:41 -0700
commit1a4e58cce84ee88129d5d49c064bd2852b481357 (patch)
treedbada87e6437233779c7d7b0c4434ddbb04a8830 /mm/vmscan.c
parent8940b34a4e082ae11498ddae8432f2ac07685d1c (diff)
mm: introduce MADV_PAGEOUT
When a process expects no accesses to a certain memory range for a long time, it could hint kernel that the pages can be reclaimed instantly but data should be preserved for future use. This could reduce workingset eviction so it ends up increasing performance. This patch introduces the new MADV_PAGEOUT hint to madvise(2) syscall. MADV_PAGEOUT can be used by a process to mark a memory range as not expected to be used for a long time so that kernel reclaims *any LRU* pages instantly. The hint can help kernel in deciding which pages to evict proactively. A note: It doesn't apply SWAP_CLUSTER_MAX LRU page isolation limit intentionally because it's automatically bounded by PMD size. If PMD size(e.g., 256) makes some trouble, we could fix it later by limit it to SWAP_CLUSTER_MAX[1]. - man-page material MADV_PAGEOUT (since Linux x.x) Do not expect access in the near future so pages in the specified regions could be reclaimed instantly regardless of memory pressure. Thus, access in the range after successful operation could cause major page fault but never lose the up-to-date contents unlike MADV_DONTNEED. Pages belonging to a shared mapping are only processed if a write access is allowed for the calling process. MADV_PAGEOUT cannot be applied to locked pages, Huge TLB pages, or VM_PFNMAP pages. [1] https://lore.kernel.org/lkml/20190710194719.GS29695@dhcp22.suse.cz/ [minchan@kernel.org: clear PG_active on MADV_PAGEOUT] Link: http://lkml.kernel.org/r/20190802200643.GA181880@google.com [akpm@linux-foundation.org: resolve conflicts with hmm.git] Link: http://lkml.kernel.org/r/20190726023435.214162-5-minchan@kernel.org Signed-off-by: Minchan Kim <minchan@kernel.org> Reported-by: kbuild test robot <lkp@intel.com> Acked-by: Michal Hocko <mhocko@suse.com> Cc: James E.J. Bottomley <James.Bottomley@HansenPartnership.com> Cc: Richard Henderson <rth@twiddle.net> Cc: Ralf Baechle <ralf@linux-mips.org> Cc: Chris Zankel <chris@zankel.net> Cc: Daniel Colascione <dancol@google.com> Cc: Dave Hansen <dave.hansen@intel.com> Cc: Hillf Danton <hdanton@sina.com> Cc: Joel Fernandes (Google) <joel@joelfernandes.org> Cc: Johannes Weiner <hannes@cmpxchg.org> Cc: Kirill A. Shutemov <kirill.shutemov@linux.intel.com> Cc: Oleksandr Natalenko <oleksandr@redhat.com> Cc: Shakeel Butt <shakeelb@google.com> Cc: Sonny Rao <sonnyrao@google.com> Cc: Suren Baghdasaryan <surenb@google.com> Cc: Tim Murray <timmurray@google.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Diffstat (limited to 'mm/vmscan.c')
-rw-r--r--mm/vmscan.c56
1 files changed, 56 insertions, 0 deletions
diff --git a/mm/vmscan.c b/mm/vmscan.c
index d8bbaf068c35..e5d52d6a24af 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -2145,6 +2145,62 @@ static void shrink_active_list(unsigned long nr_to_scan,
nr_deactivate, nr_rotated, sc->priority, file);
}
+unsigned long reclaim_pages(struct list_head *page_list)
+{
+ int nid = -1;
+ unsigned long nr_reclaimed = 0;
+ LIST_HEAD(node_page_list);
+ struct reclaim_stat dummy_stat;
+ struct page *page;
+ struct scan_control sc = {
+ .gfp_mask = GFP_KERNEL,
+ .priority = DEF_PRIORITY,
+ .may_writepage = 1,
+ .may_unmap = 1,
+ .may_swap = 1,
+ };
+
+ while (!list_empty(page_list)) {
+ page = lru_to_page(page_list);
+ if (nid == -1) {
+ nid = page_to_nid(page);
+ INIT_LIST_HEAD(&node_page_list);
+ }
+
+ if (nid == page_to_nid(page)) {
+ ClearPageActive(page);
+ list_move(&page->lru, &node_page_list);
+ continue;
+ }
+
+ nr_reclaimed += shrink_page_list(&node_page_list,
+ NODE_DATA(nid),
+ &sc, 0,
+ &dummy_stat, false);
+ while (!list_empty(&node_page_list)) {
+ page = lru_to_page(&node_page_list);
+ list_del(&page->lru);
+ putback_lru_page(page);
+ }
+
+ nid = -1;
+ }
+
+ if (!list_empty(&node_page_list)) {
+ nr_reclaimed += shrink_page_list(&node_page_list,
+ NODE_DATA(nid),
+ &sc, 0,
+ &dummy_stat, false);
+ while (!list_empty(&node_page_list)) {
+ page = lru_to_page(&node_page_list);
+ list_del(&page->lru);
+ putback_lru_page(page);
+ }
+ }
+
+ return nr_reclaimed;
+}
+
/*
* The inactive anon list should be small enough that the VM never has
* to do too much work.