mm: support madvise(MADV_FREE)

Linux doesn't have an ability to free pages lazy while other OS already
have been supported that named by madvise(MADV_FREE).

The gain is clear that kernel can discard freed pages rather than swapping
out or OOM if memory pressure happens.

Without memory pressure, freed pages would be reused by userspace without
another additional overhead(ex, page fault + allocation + zeroing).

How to work is following as.

When madvise syscall is called, VM clears dirty bit of ptes of the range.
If memory pressure happens, VM checks dirty bit of page table and if it
found still "clean", it means it's a "lazyfree pages" so VM could discard
the page instead of swapping out.  Once there was store operation for the
page before VM peek a page to reclaim, dirty bit is set so VM can swap out
the page instead of discarding.

Firstly, heavy users would be general allocators(ex, jemalloc, tcmalloc
and hope glibc supports it) and jemalloc/tcmalloc already have supported
the feature for other OS(ex, FreeBSD)

barrios@blaptop:~/benchmark/ebizzy$ lscpu
Architecture:          x86_64
CPU op-mode(s):        32-bit, 64-bit
Byte Order:            Little Endian
CPU(s):                12
On-line CPU(s) list:   0-11
Thread(s) per core:    1
Core(s) per socket:    1
Socket(s):             12
NUMA node(s):          1
Vendor ID:             GenuineIntel
CPU family:            6
Model:                 2
Stepping:              3
CPU MHz:               3200.185
BogoMIPS:              6400.53
Virtualization:        VT-x
Hypervisor vendor:     KVM
Virtualization type:   full
L1d cache:             32K
L1i cache:             32K
L2 cache:              4096K
NUMA node0 CPU(s):     0-11
ebizzy benchmark(./ebizzy -S 10 -n 512)

Higher avg is better.

 vanilla-jemalloc		MADV_free-jemalloc

1 thread
records: 10			    records: 10
avg:	2961.90			    avg:   12069.70
std:	  71.96(2.43%)		    std:     186.68(1.55%)
max:	3070.00			    max:   12385.00
min:	2796.00			    min:   11746.00

2 thread
records: 10			    records: 10
avg:	5020.00			    avg:   17827.00
std:	 264.87(5.28%)		    std:     358.52(2.01%)
max:	5244.00			    max:   18760.00
min:	4251.00			    min:   17382.00

4 thread
records: 10			    records: 10
avg:	8988.80			    avg:   27930.80
std:	1175.33(13.08%)		    std:    3317.33(11.88%)
max:	9508.00			    max:   30879.00
min:	5477.00			    min:   21024.00

8 thread
records: 10			    records: 10
avg:   13036.50			    avg:   33739.40
std:	 170.67(1.31%)		    std:    5146.22(15.25%)
max:   13371.00			    max:   40572.00
min:   12785.00			    min:   24088.00

16 thread
records: 10			    records: 10
avg:   11092.40			    avg:   31424.20
std:	 710.60(6.41%)		    std:    3763.89(11.98%)
max:   12446.00			    max:   36635.00
min:	9949.00			    min:   25669.00

32 thread
records: 10			    records: 10
avg:   11067.00			    avg:   34495.80
std:	 971.06(8.77%)		    std:    2721.36(7.89%)
max:   12010.00			    max:   38598.00
min:	9002.00			    min:   30636.00

In summary, MADV_FREE is about much faster than MADV_DONTNEED.

Signed-off-by: Minchan Kim <minchan@kernel.org>
Reviewed-by: Michal Hocko <mhocko@suse.cz>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>

1 files changed, 32 insertions, 8 deletions

diff --git a/mm/vmscan.c b/mm/vmscan.c
index 175a145bd73a..0c89c6ca7f76 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -754,13 +754,17 @@ enum page_references {
 };
 
 static enum page_references page_check_references(struct page *page,
-						  struct scan_control *sc)
+						  struct scan_control *sc,
+						  bool *freeable)
 {
 	int referenced_ptes, referenced_page;
 	unsigned long vm_flags;
+	int pte_dirty;
+
+	VM_BUG_ON_PAGE(!PageLocked(page), page);
 
 	referenced_ptes = page_referenced(page, 1, sc->target_mem_cgroup,
-					  &vm_flags);
+					  &vm_flags, &pte_dirty);
 	referenced_page = TestClearPageReferenced(page);
 
 	/*
@@ -801,6 +805,10 @@ static enum page_references page_check_references(struct page *page,
 		return PAGEREF_KEEP;
 	}
 
+	if (PageAnon(page) && !pte_dirty && !PageSwapCache(page) &&
+			!PageDirty(page))
+		*freeable = true;
+
 	/* Reclaim if clean, defer dirty pages to writeback */
 	if (referenced_page && !PageSwapBacked(page))
 		return PAGEREF_RECLAIM_CLEAN;
@@ -869,6 +877,7 @@ static unsigned long shrink_page_list(struct list_head *page_list,
 		int may_enter_fs;
 		enum page_references references = PAGEREF_RECLAIM_CLEAN;
 		bool dirty, writeback;
+		bool freeable = false;
 
 		cond_resched();
 
@@ -992,7 +1001,8 @@ static unsigned long shrink_page_list(struct list_head *page_list,
 		}
 
 		if (!force_reclaim)
-			references = page_check_references(page, sc);
+			references = page_check_references(page, sc,
+							&freeable);
 
 		switch (references) {
 		case PAGEREF_ACTIVATE:
@@ -1008,7 +1018,7 @@ static unsigned long shrink_page_list(struct list_head *page_list,
 		 * Anonymous process memory has backing store?
 		 * Try to allocate it some swap space here.
 		 */
-		if (PageAnon(page) && !PageSwapCache(page)) {
+		if (PageAnon(page) && !PageSwapCache(page) && !freeable) {
 			if (!(sc->gfp_mask & __GFP_IO))
 				goto keep_locked;
 			if (!add_to_swap(page, page_list))
@@ -1023,8 +1033,9 @@ static unsigned long shrink_page_list(struct list_head *page_list,
 		 * The page is mapped into the page tables of one or more
 		 * processes. Try to unmap it here.
 		 */
-		if (page_mapped(page) && mapping) {
-			switch (try_to_unmap(page, ttu_flags)) {
+		if (page_mapped(page) && (mapping || freeable)) {
+			switch (try_to_unmap(page,
+				freeable ? TTU_FREE : ttu_flags)) {
 			case SWAP_FAIL:
 				goto activate_locked;
 			case SWAP_AGAIN:
@@ -1032,7 +1043,20 @@ static unsigned long shrink_page_list(struct list_head *page_list,
 			case SWAP_MLOCK:
 				goto cull_mlocked;
 			case SWAP_SUCCESS:
-				; /* try to free the page below */
+				/* try to free the page below */
+				if (!freeable)
+					break;
+				/*
+				 * Freeable anon page doesn't have mapping
+				 * due to skipping of swapcache so we free
+				 * page in here rather than __remove_mapping.
+				 */
+				VM_BUG_ON_PAGE(PageSwapCache(page), page);
+				if (!page_freeze_refs(page, 1))
+					goto keep_locked;
+				__clear_page_locked(page);
+				count_vm_event(PGLAZYFREED);
+				goto free_it;
 			}
 		}
 
@@ -1789,7 +1813,7 @@ static void shrink_active_list(unsigned long nr_to_scan,
 		}
 
 		if (page_referenced(page, 0, sc->target_mem_cgroup,
-				    &vm_flags)) {
+				    &vm_flags, NULL)) {
 			nr_rotated += hpage_nr_pages(page);
 			/*
 			 * Identify referenced, file-backed active pages and