From 3f04f62f90d46a82dd73027c5fd7a15daed5c33d Mon Sep 17 00:00:00 2001 From: Andrea Arcangeli Date: Thu, 13 Jan 2011 15:46:47 -0800 Subject: thp: split_huge_page paging Paging logic that splits the page before it is unmapped and added to swap to ensure backwards compatibility with the legacy swap code. Eventually swap should natively pageout the hugepages to increase performance and decrease seeking and fragmentation of swap space. swapoff can just skip over huge pmd as they cannot be part of swap yet. In add_to_swap be careful to split the page only if we got a valid swap entry so we don't split hugepages with a full swap. In theory we could split pages before isolating them during the lru scan, but for khugepaged to be safe, I'm relying on either mmap_sem write mode, or PG_lock taken, so split_huge_page has to run either with mmap_sem read/write mode or PG_lock taken. Calling it from isolate_lru_page would make locking more complicated, in addition to that split_huge_page would deadlock if called by __isolate_lru_page because it has to take the lru lock to add the tail pages. Signed-off-by: Andrea Arcangeli Acked-by: Mel Gorman Acked-by: Rik van Riel Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/memory-failure.c | 2 ++ mm/rmap.c | 1 + mm/swap_state.c | 6 ++++++ mm/swapfile.c | 2 ++ 4 files changed, 11 insertions(+) diff --git a/mm/memory-failure.c b/mm/memory-failure.c index 2323a8039a9..6a283cc9317 100644 --- a/mm/memory-failure.c +++ b/mm/memory-failure.c @@ -386,6 +386,8 @@ static void collect_procs_anon(struct page *page, struct list_head *to_kill, struct task_struct *tsk; struct anon_vma *av; + if (unlikely(split_huge_page(page))) + return; read_lock(&tasklist_lock); av = page_lock_anon_vma(page); if (av == NULL) /* Not actually mapped anymore */ diff --git a/mm/rmap.c b/mm/rmap.c index c95d2ba27a0..a3197a8a295 100644 --- a/mm/rmap.c +++ b/mm/rmap.c @@ -1400,6 +1400,7 @@ int try_to_unmap(struct page *page, enum ttu_flags flags) int ret; BUG_ON(!PageLocked(page)); + BUG_ON(PageTransHuge(page)); if (unlikely(PageKsm(page))) ret = try_to_unmap_ksm(page, flags); diff --git a/mm/swap_state.c b/mm/swap_state.c index e10f5833167..5c8cfabbc9b 100644 --- a/mm/swap_state.c +++ b/mm/swap_state.c @@ -157,6 +157,12 @@ int add_to_swap(struct page *page) if (!entry.val) return 0; + if (unlikely(PageTransHuge(page))) + if (unlikely(split_huge_page(page))) { + swapcache_free(entry, NULL); + return 0; + } + /* * Radix-tree node allocations from PF_MEMALLOC contexts could * completely exhaust the page allocator. __GFP_NOMEMALLOC diff --git a/mm/swapfile.c b/mm/swapfile.c index b6adcfbf6f4..07a458d72fa 100644 --- a/mm/swapfile.c +++ b/mm/swapfile.c @@ -964,6 +964,8 @@ static inline int unuse_pmd_range(struct vm_area_struct *vma, pud_t *pud, pmd = pmd_offset(pud, addr); do { next = pmd_addr_end(addr, end); + if (unlikely(pmd_trans_huge(*pmd))) + continue; if (pmd_none_or_clear_bad(pmd)) continue; ret = unuse_pte_range(vma, pmd, addr, next, entry, page); -- cgit v1.2.3-18-g5258