mm: don't be stuck to rmap lock on reclaim path

The rmap locks(i_mmap_rwsem and anon_vma->root->rwsem) could be contended
under memory pressure if processes keep working on their vmas(e.g., fork,
mmap, munmap).  It makes reclaim path stuck.  In our real workload traces,
we see kswapd is waiting the lock for 300ms+(worst case, a sec) and it
makes other processes entering direct reclaim, which were also stuck on
the lock.

This patch makes lru aging path try_lock mode like shink_page_list so the
reclaim context will keep working with next lru pages without being stuck.
if it found the rmap lock contended, it rotates the page back to head of
lru in both active/inactive lrus to make them consistent behavior, which
is basic starting point rather than adding more heristic.

Since this patch introduces a new "contended" field as out-param along
with try_lock in-param in rmap_walk_control, it's not immutable any longer
if the try_lock is set so remove const keywords on rmap related functions.
Since rmap walking is already expensive operation, I doubt the const
would help sizable benefit( And we didn't have it until 5.17).

In a heavy app workload in Android, trace shows following statistics.  It
almost removes rmap lock contention from reclaim path.

Martin Liu reported:

Before:

   max_dur(ms)  min_dur(ms)  max-min(dur)ms  avg_dur(ms)  sum_dur(ms)  count blocked_function
         1632            0            1631   151.542173        31672    209  page_lock_anon_vma_read
          601            0             601   145.544681        28817    198  rmap_walk_file

After:

   max_dur(ms)  min_dur(ms)  max-min(dur)ms  avg_dur(ms)  sum_dur(ms)  count blocked_function
          NaN          NaN              NaN          NaN          NaN    0.0             NaN
            0            0                0     0.127645            1     12  rmap_walk_file

[minchan@kernel.org: add comment, per Matthew]
  Link: https://lkml.kernel.org/r/YnNqeB5tUf6LZ57b@google.com
Link: https://lkml.kernel.org/r/20220510215423.164547-1-minchan@kernel.org
Signed-off-by: Minchan Kim <minchan@kernel.org>
Acked-by: Johannes Weiner <hannes@cmpxchg.org>
Cc: Suren Baghdasaryan <surenb@google.com>
Cc: Michal Hocko <mhocko@suse.com>
Cc: John Dias <joaodias@google.com>
Cc: Tim Murray <timmurray@google.com>
Cc: Matthew Wilcox <willy@infradead.org>
Cc: Vladimir Davydov <vdavydov.dev@gmail.com>
Cc: Martin Liu <liumartin@google.com>
Cc: Minchan Kim <minchan@kernel.org>
Cc: Matthew Wilcox <willy@infradead.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>

1 files changed, 20 insertions, 8 deletions

diff --git a/include/linux/rmap.h b/include/linux/rmap.h
index cbe279a6f0de..9ec23138e410 100644
--- a/include/linux/rmap.h
+++ b/include/linux/rmap.h
@@ -128,6 +128,11 @@ static inline void anon_vma_lock_read(struct anon_vma *anon_vma)
 	down_read(&anon_vma->root->rwsem);
 }
 
+static inline int anon_vma_trylock_read(struct anon_vma *anon_vma)
+{
+	return down_read_trylock(&anon_vma->root->rwsem);
+}
+
 static inline void anon_vma_unlock_read(struct anon_vma *anon_vma)
 {
 	up_read(&anon_vma->root->rwsem);
@@ -366,17 +371,14 @@ int pfn_mkclean_range(unsigned long pfn, unsigned long nr_pages, pgoff_t pgoff,
 
 void remove_migration_ptes(struct folio *src, struct folio *dst, bool locked);
 
-/*
- * Called by memory-failure.c to kill processes.
- */
-struct anon_vma *folio_lock_anon_vma_read(struct folio *folio);
-void page_unlock_anon_vma_read(struct anon_vma *anon_vma);
 int page_mapped_in_vma(struct page *page, struct vm_area_struct *vma);
 
 /*
  * rmap_walk_control: To control rmap traversing for specific needs
  *
  * arg: passed to rmap_one() and invalid_vma()
+ * try_lock: bail out if the rmap lock is contended
+ * contended: indicate the rmap traversal bailed out due to lock contention
  * rmap_one: executed on each vma where page is mapped
  * done: for checking traversing termination condition
  * anon_lock: for getting anon_lock by optimized way rather than default
@@ -384,6 +386,8 @@ int page_mapped_in_vma(struct page *page, struct vm_area_struct *vma);
  */
 struct rmap_walk_control {
 	void *arg;
+	bool try_lock;
+	bool contended;
 	/*
 	 * Return false if page table scanning in rmap_walk should be stopped.
 	 * Otherwise, return true.
@@ -391,12 +395,20 @@ struct rmap_walk_control {
 	bool (*rmap_one)(struct folio *folio, struct vm_area_struct *vma,
 					unsigned long addr, void *arg);
 	int (*done)(struct folio *folio);
-	struct anon_vma *(*anon_lock)(struct folio *folio);
+	struct anon_vma *(*anon_lock)(struct folio *folio,
+				      struct rmap_walk_control *rwc);
 	bool (*invalid_vma)(struct vm_area_struct *vma, void *arg);
 };
 
-void rmap_walk(struct folio *folio, const struct rmap_walk_control *rwc);
-void rmap_walk_locked(struct folio *folio, const struct rmap_walk_control *rwc);
+void rmap_walk(struct folio *folio, struct rmap_walk_control *rwc);
+void rmap_walk_locked(struct folio *folio, struct rmap_walk_control *rwc);
+
+/*
+ * Called by memory-failure.c to kill processes.
+ */
+struct anon_vma *folio_lock_anon_vma_read(struct folio *folio,
+					  struct rmap_walk_control *rwc);
+void page_unlock_anon_vma_read(struct anon_vma *anon_vma);
 
 #else	/* !CONFIG_MMU */