summaryrefslogtreecommitdiffstats
path: root/mm/madvise.c
diff options
context:
space:
mode:
authorMinchan Kim <minchan@kernel.org>2016-01-15 16:55:42 -0800
committerLinus Torvalds <torvalds@linux-foundation.org>2016-01-15 17:56:32 -0800
commitb8d3c4c3009d42869dc03a1da0efc2aa687d0ab4 (patch)
treecb6f2ea3edac92a70426e1f2e332bac48d31db66 /mm/madvise.c
parent05ee26d9e7e29ab026995eab79be3c6e8351908c (diff)
downloadlinux-b8d3c4c3009d42869dc03a1da0efc2aa687d0ab4.tar.bz2
mm/huge_memory.c: don't split THP page when MADV_FREE syscall is called
We don't need to split THP page when MADV_FREE syscall is called if [start, len] is aligned with THP size. The split could be done when VM decide to free it in reclaim path if memory pressure is heavy. With that, we could avoid unnecessary THP split. For the feature, this patch changes pte dirtness marking logic of THP. Now, it marks every ptes of pages dirty unconditionally in splitting, which makes MADV_FREE void. So, instead, this patch propagates pmd dirtiness to all pages via PG_dirty and restores pte dirtiness from PG_dirty. With this, if pmd is clean(ie, MADV_FREEed) when split happens(e,g, shrink_page_list), all of pages are clean too so we could discard them. Signed-off-by: Minchan Kim <minchan@kernel.org> Cc: Kirill A. Shutemov <kirill@shutemov.name> Cc: Hugh Dickins <hughd@google.com> Cc: Andrea Arcangeli <aarcange@redhat.com> Cc: "James E.J. Bottomley" <jejb@parisc-linux.org> Cc: "Kirill A. Shutemov" <kirill@shutemov.name> Cc: Shaohua Li <shli@kernel.org> Cc: <yalin.wang2010@gmail.com> Cc: Andy Lutomirski <luto@amacapital.net> Cc: Arnd Bergmann <arnd@arndb.de> Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org> Cc: Catalin Marinas <catalin.marinas@arm.com> Cc: Chen Gang <gang.chen.5i5j@gmail.com> Cc: Chris Zankel <chris@zankel.net> Cc: Daniel Micay <danielmicay@gmail.com> Cc: Darrick J. Wong <darrick.wong@oracle.com> Cc: David S. Miller <davem@davemloft.net> Cc: Helge Deller <deller@gmx.de> Cc: Ivan Kokshaysky <ink@jurassic.park.msu.ru> Cc: Jason Evans <je@fb.com> Cc: Johannes Weiner <hannes@cmpxchg.org> Cc: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com> Cc: Matt Turner <mattst88@gmail.com> Cc: Max Filippov <jcmvbkbc@gmail.com> Cc: Mel Gorman <mgorman@suse.de> Cc: Michael Kerrisk <mtk.manpages@gmail.com> Cc: Michal Hocko <mhocko@suse.com> Cc: Mika Penttil <mika.penttila@nextfour.com> Cc: Ralf Baechle <ralf@linux-mips.org> Cc: Richard Henderson <rth@twiddle.net> Cc: Rik van Riel <riel@redhat.com> Cc: Roland Dreier <roland@kernel.org> Cc: Russell King <rmk@arm.linux.org.uk> Cc: Shaohua Li <shli@kernel.org> Cc: Will Deacon <will.deacon@arm.com> Cc: Wu Fengguang <fengguang.wu@intel.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Diffstat (limited to 'mm/madvise.c')
-rw-r--r--mm/madvise.c8
1 files changed, 7 insertions, 1 deletions
diff --git a/mm/madvise.c b/mm/madvise.c
index 4e9454622801..f56825b6d2e1 100644
--- a/mm/madvise.c
+++ b/mm/madvise.c
@@ -271,8 +271,13 @@ static int madvise_free_pte_range(pmd_t *pmd, unsigned long addr,
pte_t *orig_pte, *pte, ptent;
struct page *page;
int nr_swap = 0;
+ unsigned long next;
+
+ next = pmd_addr_end(addr, end);
+ if (pmd_trans_huge(*pmd))
+ if (madvise_free_huge_pmd(tlb, vma, pmd, addr, next))
+ goto next;
- split_huge_pmd(vma, pmd, addr);
if (pmd_trans_unstable(pmd))
return 0;
@@ -383,6 +388,7 @@ out:
arch_leave_lazy_mmu_mode();
pte_unmap_unlock(orig_pte, ptl);
cond_resched();
+next:
return 0;
}