mm, truncate: do not check mapping for every page being truncated

During truncation, the mapping has already been checked for shmem and
dax so it's known that workingset_update_node is required.

This patch avoids the checks on mapping for each page being truncated.
In all other cases, a lookup helper is used to determine if
workingset_update_node() needs to be called.  The one danger is that the
API is slightly harder to use as calling workingset_update_node directly
without checking for dax or shmem mappings could lead to surprises.
However, the API rarely needs to be used and hopefully the comment is
enough to give people the hint.

sparsetruncate (tiny)
                              4.14.0-rc4             4.14.0-rc4
                             oneirq-v1r1        pickhelper-v1r1
Min          Time      141.00 (   0.00%)      140.00 (   0.71%)
1st-qrtle    Time      142.00 (   0.00%)      141.00 (   0.70%)
2nd-qrtle    Time      142.00 (   0.00%)      142.00 (   0.00%)
3rd-qrtle    Time      143.00 (   0.00%)      143.00 (   0.00%)
Max-90%      Time      144.00 (   0.00%)      144.00 (   0.00%)
Max-95%      Time      147.00 (   0.00%)      145.00 (   1.36%)
Max-99%      Time      195.00 (   0.00%)      191.00 (   2.05%)
Max          Time      230.00 (   0.00%)      205.00 (  10.87%)
Amean        Time      144.37 (   0.00%)      143.82 (   0.38%)
Stddev       Time       10.44 (   0.00%)        9.00 (  13.74%)
Coeff        Time        7.23 (   0.00%)        6.26 (  13.41%)
Best99%Amean Time      143.72 (   0.00%)      143.34 (   0.26%)
Best95%Amean Time      142.37 (   0.00%)      142.00 (   0.26%)
Best90%Amean Time      142.19 (   0.00%)      141.85 (   0.24%)
Best75%Amean Time      141.92 (   0.00%)      141.58 (   0.24%)
Best50%Amean Time      141.69 (   0.00%)      141.31 (   0.27%)
Best25%Amean Time      141.38 (   0.00%)      140.97 (   0.29%)

As you'd expect, the gain is marginal but it can be detected.  The
differences in bonnie are all within the noise which is not surprising
given the impact on the microbenchmark.

radix_tree_update_node_t is a callback for some radix operations that
optionally passes in a private field.  The only user of the callback is
workingset_update_node and as it no longer requires a mapping, the
private field is removed.

Link: http://lkml.kernel.org/r/20171018075952.10627-3-mgorman@techsingularity.net
Signed-off-by: Mel Gorman <mgorman@techsingularity.net>
Acked-by: Johannes Weiner <hannes@cmpxchg.org>
Reviewed-by: Jan Kara <jack@suse.cz>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: Dave Chinner <david@fromorbit.com>
Cc: Dave Hansen <dave.hansen@intel.com>
Cc: Vlastimil Babka <vbabka@suse.cz>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

2 files changed, 15 insertions, 5 deletions

diff --git a/include/linux/radix-tree.h b/include/linux/radix-tree.h
index 567ebb5eaab0..0ca448c1cb42 100644
--- a/include/linux/radix-tree.h
+++ b/include/linux/radix-tree.h
@@ -301,18 +301,17 @@ void *__radix_tree_lookup(const struct radix_tree_root *, unsigned long index,
 void *radix_tree_lookup(const struct radix_tree_root *, unsigned long);
 void __rcu **radix_tree_lookup_slot(const struct radix_tree_root *,
 					unsigned long index);
-typedef void (*radix_tree_update_node_t)(struct radix_tree_node *, void *);
+typedef void (*radix_tree_update_node_t)(struct radix_tree_node *);
 void __radix_tree_replace(struct radix_tree_root *, struct radix_tree_node *,
 			  void __rcu **slot, void *entry,
-			  radix_tree_update_node_t update_node, void *private);
+			  radix_tree_update_node_t update_node);
 void radix_tree_iter_replace(struct radix_tree_root *,
 		const struct radix_tree_iter *, void __rcu **slot, void *entry);
 void radix_tree_replace_slot(struct radix_tree_root *,
 			     void __rcu **slot, void *entry);
 void __radix_tree_delete_node(struct radix_tree_root *,
 			      struct radix_tree_node *,
-			      radix_tree_update_node_t update_node,
-			      void *private);
+			      radix_tree_update_node_t update_node);
 void radix_tree_iter_delete(struct radix_tree_root *,
 			struct radix_tree_iter *iter, void __rcu **slot);
 void *radix_tree_delete_item(struct radix_tree_root *, unsigned long, void *);
diff --git a/include/linux/swap.h b/include/linux/swap.h
index 8b8a6f965785..454f042bcdd5 100644
--- a/include/linux/swap.h
+++ b/include/linux/swap.h
@@ -298,7 +298,18 @@ struct vma_swap_readahead {
 void *workingset_eviction(struct address_space *mapping, struct page *page);
 bool workingset_refault(void *shadow);
 void workingset_activation(struct page *page);
-void workingset_update_node(struct radix_tree_node *node, void *private);
+
+/* Do not use directly, use workingset_lookup_update */
+void workingset_update_node(struct radix_tree_node *node);
+
+/* Returns workingset_update_node() if the mapping has shadow entries. */
+#define workingset_lookup_update(mapping)				\
+({									\
+	radix_tree_update_node_t __helper = workingset_update_node;	\
+	if (dax_mapping(mapping) || shmem_mapping(mapping))		\
+		__helper = NULL;					\
+	__helper;							\
+})
 
 /* linux/mm/page_alloc.c */
 extern unsigned long totalram_pages;