On Thu, 23 Jan 2020 11:20:07 +0100 Alexander Graf wrote:
>
> The big problem I see is that what I really want from a user's point of
> view is a tuneable that says "Automatically free clean page cache pages
> that were not accessed in the last X minutes".
A diff is made on top of 1a4e58cce84e ("mm: introduce MADV_PAGEOUT") without
test in any form, assuming it goes in line with the tunable above but without
"X minutes" taken into account.
[BTW, please take a look at
Content-Type: text/plain; charset="utf-8"; format="flowed"
Content-Transfer-Encoding: base64
and ensure pure text message.]
--- a/include/uapi/asm-generic/mman-common.h
+++ b/include/uapi/asm-generic/mman-common.h
@@ -69,6 +69,7 @@
#define MADV_COLD 20 /* deactivate these pages */
#define MADV_PAGEOUT 21 /* reclaim these pages */
+#define MADV_CCPC 22 /* reclaim cold & clean page cache pages */
/* compatibility flags */
#define MAP_FILE 0
--- a/mm/madvise.c
+++ b/mm/madvise.c
@@ -35,6 +35,7 @@
struct madvise_walk_private {
struct mmu_gather *tlb;
bool pageout;
+ int behavior;
};
/*
@@ -50,6 +51,7 @@ static int madvise_need_mmap_write(int b
case MADV_DONTNEED:
case MADV_COLD:
case MADV_PAGEOUT:
+ case MADV_CCPC:
case MADV_FREE:
return 0;
default:
@@ -304,6 +306,7 @@ static int madvise_cold_or_pageout_pte_r
struct madvise_walk_private *private = walk->private;
struct mmu_gather *tlb = private->tlb;
bool pageout = private->pageout;
+ bool ccpc = private->behavior == MADV_CCPC;
struct mm_struct *mm = tlb->mm;
struct vm_area_struct *vma = walk->vma;
pte_t *orig_pte, *pte, ptent;
@@ -429,6 +432,8 @@ regular_page:
VM_BUG_ON_PAGE(PageTransCompound(page), page);
if (pte_young(ptent)) {
+ if (ccpc)
+ continue;
ptent = ptep_get_and_clear_full(mm, addr, pte,
tlb->fullmm);
ptent = pte_mkold(ptent);
@@ -436,6 +441,10 @@ regular_page:
tlb_remove_tlb_entry(tlb, pte, addr);
}
+ if (ccpc)
+ if (PageDirty(page))
+ continue;
+
/*
* We are deactivating a page for accelerating reclaiming.
* VM couldn't reclaim the page unless we clear PG_young.
@@ -502,12 +511,13 @@ static long madvise_cold(struct vm_area_
}
static void madvise_pageout_page_range(struct mmu_gather *tlb,
- struct vm_area_struct *vma,
+ struct vm_area_struct *vma, int behavior,
unsigned long addr, unsigned long end)
{
struct madvise_walk_private walk_private = {
.pageout = true,
.tlb = tlb,
+ .behavior = behavior,
};
tlb_start_vma(tlb, vma);
@@ -515,10 +525,10 @@ static void madvise_pageout_page_range(s
tlb_end_vma(tlb, vma);
}
-static inline bool can_do_pageout(struct vm_area_struct *vma)
+static inline bool can_do_pageout(struct vm_area_struct *vma, int behavior)
{
if (vma_is_anonymous(vma))
- return true;
+ return behavior != MADV_CCPC;
if (!vma->vm_file)
return false;
/*
@@ -531,7 +541,7 @@ static inline bool can_do_pageout(struct
inode_permission(file_inode(vma->vm_file), MAY_WRITE) == 0;
}
-static long madvise_pageout(struct vm_area_struct *vma,
+static long madvise_pageout(struct vm_area_struct *vma, int behavior,
struct vm_area_struct **prev,
unsigned long start_addr, unsigned long end_addr)
{
@@ -542,12 +552,12 @@ static long madvise_pageout(struct vm_ar
if (!can_madv_lru_vma(vma))
return -EINVAL;
- if (!can_do_pageout(vma))
+ if (!can_do_pageout(vma, behavior))
return 0;
lru_add_drain();
tlb_gather_mmu(&tlb, mm, start_addr, end_addr);
- madvise_pageout_page_range(&tlb, vma, start_addr, end_addr);
+ madvise_pageout_page_range(&tlb, vma, behavior, start_addr, end_addr);
tlb_finish_mmu(&tlb, start_addr, end_addr);
return 0;
@@ -936,7 +946,8 @@ madvise_vma(struct vm_area_struct *vma,
case MADV_COLD:
return madvise_cold(vma, prev, start, end);
case MADV_PAGEOUT:
- return madvise_pageout(vma, prev, start, end);
+ case MADV_CCPC:
+ return madvise_pageout(vma, behavior, prev, start, end);
case MADV_FREE:
case MADV_DONTNEED:
return madvise_dontneed_free(vma, prev, start, end, behavior);
@@ -960,6 +971,7 @@ madvise_behavior_valid(int behavior)
case MADV_FREE:
case MADV_COLD:
case MADV_PAGEOUT:
+ case MADV_CCPC:
#ifdef CONFIG_KSM
case MADV_MERGEABLE:
case MADV_UNMERGEABLE:
--
