From 101d2be7646b7dd1c367d50208a59b29fce61398 Mon Sep 17 00:00:00 2001 From: Hugh Dickins Date: Mon, 21 Nov 2005 21:32:16 -0800 Subject: [PATCH] unpaged: VM_NONLINEAR VM_RESERVED There's one peculiar use of VM_RESERVED which the previous patch left behind: because VM_NONLINEAR's try_to_unmap_cluster uses vm_private_data as a swapout cursor, but should never meet VM_RESERVED vmas, it was a way of extending VM_NONLINEAR to VM_RESERVED vmas using vm_private_data for some other purpose. But that's an empty set - they don't have the populate function required. So just throw away those VM_RESERVED tests. But one more interesting in rmap.c has to go too: try_to_unmap_one will want to swap out an anonymous page from VM_RESERVED or VM_UNPAGED area. Signed-off-by: Hugh Dickins Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/rmap.c | 15 +++++---------- 1 file changed, 5 insertions(+), 10 deletions(-) (limited to 'mm/rmap.c') diff --git a/mm/rmap.c b/mm/rmap.c index 914d04b98bee..377d417ec15f 100644 --- a/mm/rmap.c +++ b/mm/rmap.c @@ -529,10 +529,8 @@ static int try_to_unmap_one(struct page *page, struct vm_area_struct *vma) * If the page is mlock()d, we cannot swap it out. * If it's recently referenced (perhaps page_referenced * skipped over this mm) then we should reactivate it. - * - * Pages belonging to VM_RESERVED regions should not happen here. */ - if ((vma->vm_flags & (VM_LOCKED|VM_RESERVED)) || + if ((vma->vm_flags & VM_LOCKED) || ptep_clear_flush_young(vma, address, pte)) { ret = SWAP_FAIL; goto out_unmap; @@ -727,7 +725,7 @@ static int try_to_unmap_file(struct page *page) list_for_each_entry(vma, &mapping->i_mmap_nonlinear, shared.vm_set.list) { - if (vma->vm_flags & (VM_LOCKED|VM_RESERVED)) + if (vma->vm_flags & VM_LOCKED) continue; cursor = (unsigned long) vma->vm_private_data; if (cursor > max_nl_cursor) @@ -761,7 +759,7 @@ static int try_to_unmap_file(struct page *page) do { list_for_each_entry(vma, &mapping->i_mmap_nonlinear, shared.vm_set.list) { - if (vma->vm_flags & (VM_LOCKED|VM_RESERVED)) + if (vma->vm_flags & VM_LOCKED) continue; cursor = (unsigned long) vma->vm_private_data; while ( cursor < max_nl_cursor && @@ -783,11 +781,8 @@ static int try_to_unmap_file(struct page *page) * in locked vmas). Reset cursor on all unreserved nonlinear * vmas, now forgetting on which ones it had fallen behind. */ - list_for_each_entry(vma, &mapping->i_mmap_nonlinear, - shared.vm_set.list) { - if (!(vma->vm_flags & VM_RESERVED)) - vma->vm_private_data = NULL; - } + list_for_each_entry(vma, &mapping->i_mmap_nonlinear, shared.vm_set.list) + vma->vm_private_data = NULL; out: spin_unlock(&mapping->i_mmap_lock); return ret; -- cgit v1.2.3 From ee498ed730283e9cdfc8913f12b90a2246f1a8cc Mon Sep 17 00:00:00 2001 From: Hugh Dickins Date: Mon, 21 Nov 2005 21:32:18 -0800 Subject: [PATCH] unpaged: anon in VM_UNPAGED copy_one_pte needs to copy the anonymous COWed pages in a VM_UNPAGED area, zap_pte_range needs to free them, do_wp_page needs to COW them: just like ordinary pages, not like the unpaged. But recognizing them is a little subtle: because PageReserved is no longer a condition for remap_pfn_range, we can now mmap all of /dev/mem (whether the distro permits, and whether it's advisable on this or that architecture, is another matter). So if we can see a PageAnon, it may not be ours to mess with (or may be ours from elsewhere in the address space). I suspect there's an entertaining insoluble self-referential problem here, but the page_is_anon function does a good practical job, and MAP_PRIVATE PROT_WRITE VM_UNPAGED will always be an odd choice. In updating the comment on page_address_in_vma, noticed a potential NULL dereference, in a path we don't actually take, but fixed it. Signed-off-by: Hugh Dickins Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/rmap.c | 7 +++++-- 1 file changed, 5 insertions(+), 2 deletions(-) (limited to 'mm/rmap.c') diff --git a/mm/rmap.c b/mm/rmap.c index 377d417ec15f..2e034a0b89ab 100644 --- a/mm/rmap.c +++ b/mm/rmap.c @@ -225,7 +225,9 @@ vma_address(struct page *page, struct vm_area_struct *vma) /* * At what user virtual address is page expected in vma? checking that the - * page matches the vma: currently only used by unuse_process, on anon pages. + * page matches the vma: currently only used on anon pages, by unuse_vma; + * and by extraordinary checks on anon pages in VM_UNPAGED vmas, taking + * care that an mmap of /dev/mem might window free and foreign pages. */ unsigned long page_address_in_vma(struct page *page, struct vm_area_struct *vma) { @@ -234,7 +236,8 @@ unsigned long page_address_in_vma(struct page *page, struct vm_area_struct *vma) (void *)page->mapping - PAGE_MAPPING_ANON) return -EFAULT; } else if (page->mapping && !(vma->vm_flags & VM_NONLINEAR)) { - if (vma->vm_file->f_mapping != page->mapping) + if (!vma->vm_file || + vma->vm_file->f_mapping != page->mapping) return -EFAULT; } else return -EFAULT; -- cgit v1.2.3 From 6aab341e0a28aff100a09831c5300a2994b8b986 Mon Sep 17 00:00:00 2001 From: Linus Torvalds Date: Mon, 28 Nov 2005 14:34:23 -0800 Subject: mm: re-architect the VM_UNPAGED logic This replaces the (in my opinion horrible) VM_UNMAPPED logic with very explicit support for a "remapped page range" aka VM_PFNMAP. It allows a VM area to contain an arbitrary range of page table entries that the VM never touches, and never considers to be normal pages. Any user of "remap_pfn_range()" automatically gets this new functionality, and doesn't even have to mark the pages reserved or indeed mark them any other way. It just works. As a side effect, doing mmap() on /dev/mem works for arbitrary ranges. Sparc update from David in the next commit. Signed-off-by: Linus Torvalds --- mm/rmap.c | 14 ++------------ 1 file changed, 2 insertions(+), 12 deletions(-) (limited to 'mm/rmap.c') diff --git a/mm/rmap.c b/mm/rmap.c index 2e034a0b89ab..6389cda02a20 100644 --- a/mm/rmap.c +++ b/mm/rmap.c @@ -226,8 +226,6 @@ vma_address(struct page *page, struct vm_area_struct *vma) /* * At what user virtual address is page expected in vma? checking that the * page matches the vma: currently only used on anon pages, by unuse_vma; - * and by extraordinary checks on anon pages in VM_UNPAGED vmas, taking - * care that an mmap of /dev/mem might window free and foreign pages. */ unsigned long page_address_in_vma(struct page *page, struct vm_area_struct *vma) { @@ -614,7 +612,6 @@ static void try_to_unmap_cluster(unsigned long cursor, struct page *page; unsigned long address; unsigned long end; - unsigned long pfn; address = (vma->vm_start + cursor) & CLUSTER_MASK; end = address + CLUSTER_SIZE; @@ -643,15 +640,8 @@ static void try_to_unmap_cluster(unsigned long cursor, for (; address < end; pte++, address += PAGE_SIZE) { if (!pte_present(*pte)) continue; - - pfn = pte_pfn(*pte); - if (unlikely(!pfn_valid(pfn))) { - print_bad_pte(vma, *pte, address); - continue; - } - - page = pfn_to_page(pfn); - BUG_ON(PageAnon(page)); + page = vm_normal_page(vma, address, *pte); + BUG_ON(!page || PageAnon(page)); if (ptep_clear_flush_young(vma, address, pte)) continue; -- cgit v1.2.3 From f7b7fd8f3ebbb2810d6893295aa984acd0fd30db Mon Sep 17 00:00:00 2001 From: Rik van Riel Date: Mon, 28 Nov 2005 13:44:07 -0800 Subject: [PATCH] temporarily disable swap token on memory pressure Some users (hi Zwane) have seen a problem when running a workload that eats nearly all of physical memory - th system does an OOM kill, even when there is still a lot of swap free. The problem appears to be a very big task that is holding the swap token, and the VM has a very hard time finding any other page in the system that is swappable. Instead of ignoring the swap token when sc->priority reaches 0, we could simply take the swap token away from the memory hog and make sure we don't give it back to the memory hog for a few seconds. This patch resolves the problem Zwane ran into. Signed-off-by: Rik van Riel Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/rmap.c | 26 ++++++++++---------------- 1 file changed, 10 insertions(+), 16 deletions(-) (limited to 'mm/rmap.c') diff --git a/mm/rmap.c b/mm/rmap.c index 6389cda02a20..491ac350048f 100644 --- a/mm/rmap.c +++ b/mm/rmap.c @@ -290,7 +290,7 @@ pte_t *page_check_address(struct page *page, struct mm_struct *mm, * repeatedly from either page_referenced_anon or page_referenced_file. */ static int page_referenced_one(struct page *page, - struct vm_area_struct *vma, unsigned int *mapcount, int ignore_token) + struct vm_area_struct *vma, unsigned int *mapcount) { struct mm_struct *mm = vma->vm_mm; unsigned long address; @@ -311,7 +311,7 @@ static int page_referenced_one(struct page *page, /* Pretend the page is referenced if the task has the swap token and is in the middle of a page fault. */ - if (mm != current->mm && !ignore_token && has_swap_token(mm) && + if (mm != current->mm && has_swap_token(mm) && rwsem_is_locked(&mm->mmap_sem)) referenced++; @@ -321,7 +321,7 @@ out: return referenced; } -static int page_referenced_anon(struct page *page, int ignore_token) +static int page_referenced_anon(struct page *page) { unsigned int mapcount; struct anon_vma *anon_vma; @@ -334,8 +334,7 @@ static int page_referenced_anon(struct page *page, int ignore_token) mapcount = page_mapcount(page); list_for_each_entry(vma, &anon_vma->head, anon_vma_node) { - referenced += page_referenced_one(page, vma, &mapcount, - ignore_token); + referenced += page_referenced_one(page, vma, &mapcount); if (!mapcount) break; } @@ -354,7 +353,7 @@ static int page_referenced_anon(struct page *page, int ignore_token) * * This function is only called from page_referenced for object-based pages. */ -static int page_referenced_file(struct page *page, int ignore_token) +static int page_referenced_file(struct page *page) { unsigned int mapcount; struct address_space *mapping = page->mapping; @@ -392,8 +391,7 @@ static int page_referenced_file(struct page *page, int ignore_token) referenced++; break; } - referenced += page_referenced_one(page, vma, &mapcount, - ignore_token); + referenced += page_referenced_one(page, vma, &mapcount); if (!mapcount) break; } @@ -410,13 +408,10 @@ static int page_referenced_file(struct page *page, int ignore_token) * Quick test_and_clear_referenced for all mappings to a page, * returns the number of ptes which referenced the page. */ -int page_referenced(struct page *page, int is_locked, int ignore_token) +int page_referenced(struct page *page, int is_locked) { int referenced = 0; - if (!swap_token_default_timeout) - ignore_token = 1; - if (page_test_and_clear_young(page)) referenced++; @@ -425,15 +420,14 @@ int page_referenced(struct page *page, int is_locked, int ignore_token) if (page_mapped(page) && page->mapping) { if (PageAnon(page)) - referenced += page_referenced_anon(page, ignore_token); + referenced += page_referenced_anon(page); else if (is_locked) - referenced += page_referenced_file(page, ignore_token); + referenced += page_referenced_file(page); else if (TestSetPageLocked(page)) referenced++; else { if (page->mapping) - referenced += page_referenced_file(page, - ignore_token); + referenced += page_referenced_file(page); unlock_page(page); } } -- cgit v1.2.3