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, 140 insertions, 0 deletions

diff --git a/mm/madvise.c b/mm/madvise.c
index 10f62b72bbae..6b1a7cdf4cb2 100644
--- a/mm/madvise.c
+++ b/mm/madvise.c
@@ -19,6 +19,14 @@
 #include <linux/blkdev.h>
 #include <linux/swap.h>
 #include <linux/swapops.h>
+#include <linux/mmu_notifier.h>
+
+#include <asm/tlb.h>
+
+struct madvise_free_private {
+	struct vm_area_struct *vma;
+	struct mmu_gather *tlb;
+};
 
 /*
  * Any behaviour which results in changes to the vma->vm_flags needs to
@@ -31,6 +39,7 @@ static int madvise_need_mmap_write(int behavior)
 	case MADV_REMOVE:
 	case MADV_WILLNEED:
 	case MADV_DONTNEED:
+	case MADV_FREE:
 		return 0;
 	default:
 		/* be safe, default to 1. list exceptions explicitly */
@@ -255,6 +264,128 @@ static long madvise_willneed(struct vm_area_struct *vma,
 	return 0;
 }
 
+static int madvise_free_pte_range(pmd_t *pmd, unsigned long addr,
+				unsigned long end, struct mm_walk *walk)
+
+{
+	struct madvise_free_private *fp = walk->private;
+	struct mmu_gather *tlb = fp->tlb;
+	struct mm_struct *mm = tlb->mm;
+	struct vm_area_struct *vma = fp->vma;
+	spinlock_t *ptl;
+	pte_t *pte, ptent;
+	struct page *page;
+
+	split_huge_page_pmd(vma, addr, pmd);
+	if (pmd_trans_unstable(pmd))
+		return 0;
+
+	pte = pte_offset_map_lock(mm, pmd, addr, &ptl);
+	arch_enter_lazy_mmu_mode();
+	for (; addr != end; pte++, addr += PAGE_SIZE) {
+		ptent = *pte;
+
+		if (!pte_present(ptent))
+			continue;
+
+		page = vm_normal_page(vma, addr, ptent);
+		if (!page)
+			continue;
+
+		if (PageSwapCache(page)) {
+			if (!trylock_page(page))
+				continue;
+
+			if (!try_to_free_swap(page)) {
+				unlock_page(page);
+				continue;
+			}
+
+			ClearPageDirty(page);
+			unlock_page(page);
+		}
+
+		/*
+		 * Some of architecture(ex, PPC) don't update TLB
+		 * with set_pte_at and tlb_remove_tlb_entry so for
+		 * the portability, remap the pte with old|clean
+		 * after pte clearing.
+		 */
+		ptent = ptep_get_and_clear_full(mm, addr, pte,
+						tlb->fullmm);
+		ptent = pte_mkold(ptent);
+		ptent = pte_mkclean(ptent);
+		set_pte_at(mm, addr, pte, ptent);
+		tlb_remove_tlb_entry(tlb, pte, addr);
+	}
+	arch_leave_lazy_mmu_mode();
+	pte_unmap_unlock(pte - 1, ptl);
+	cond_resched();
+	return 0;
+}
+
+static void madvise_free_page_range(struct mmu_gather *tlb,
+			     struct vm_area_struct *vma,
+			     unsigned long addr, unsigned long end)
+{
+	struct madvise_free_private fp = {
+		.vma = vma,
+		.tlb = tlb,
+	};
+
+	struct mm_walk free_walk = {
+		.pmd_entry = madvise_free_pte_range,
+		.mm = vma->vm_mm,
+		.private = &fp,
+	};
+
+	BUG_ON(addr >= end);
+	tlb_start_vma(tlb, vma);
+	walk_page_range(addr, end, &free_walk);
+	tlb_end_vma(tlb, vma);
+}
+
+static int madvise_free_single_vma(struct vm_area_struct *vma,
+			unsigned long start_addr, unsigned long end_addr)
+{
+	unsigned long start, end;
+	struct mm_struct *mm = vma->vm_mm;
+	struct mmu_gather tlb;
+
+	if (vma->vm_flags & (VM_LOCKED|VM_HUGETLB|VM_PFNMAP))
+		return -EINVAL;
+
+	/* MADV_FREE works for only anon vma at the moment */
+	if (vma->vm_file)
+		return -EINVAL;
+
+	start = max(vma->vm_start, start_addr);
+	if (start >= vma->vm_end)
+		return -EINVAL;
+	end = min(vma->vm_end, end_addr);
+	if (end <= vma->vm_start)
+		return -EINVAL;
+
+	lru_add_drain();
+	tlb_gather_mmu(&tlb, mm, start, end);
+	update_hiwater_rss(mm);
+
+	mmu_notifier_invalidate_range_start(mm, start, end);
+	madvise_free_page_range(&tlb, vma, start, end);
+	mmu_notifier_invalidate_range_end(mm, start, end);
+	tlb_finish_mmu(&tlb, start, end);
+
+	return 0;
+}
+
+static long madvise_free(struct vm_area_struct *vma,
+			     struct vm_area_struct **prev,
+			     unsigned long start, unsigned long end)
+{
+	*prev = vma;
+	return madvise_free_single_vma(vma, start, end);
+}
+
 /*
  * Application no longer needs these pages.  If the pages are dirty,
  * it's OK to just throw them away.  The app will be more careful about
@@ -378,6 +509,14 @@ madvise_vma(struct vm_area_struct *vma, struct vm_area_struct **prev,
 		return madvise_remove(vma, prev, start, end);
 	case MADV_WILLNEED:
 		return madvise_willneed(vma, prev, start, end);
+	case MADV_FREE:
+		/*
+		 * XXX: In this implementation, MADV_FREE works like
+		 * MADV_DONTNEED on swapless system or full swap.
+		 */
+		if (get_nr_swap_pages() > 0)
+			return madvise_free(vma, prev, start, end);
+		/* passthrough */
 	case MADV_DONTNEED:
 		return madvise_dontneed(vma, prev, start, end);
 	default:
@@ -397,6 +536,7 @@ madvise_behavior_valid(int behavior)
 	case MADV_REMOVE:
 	case MADV_WILLNEED:
 	case MADV_DONTNEED:
+	case MADV_FREE:
 #ifdef CONFIG_KSM
 	case MADV_MERGEABLE:
 	case MADV_UNMERGEABLE: