From 7906d00cd1f687268f0a3599442d113767795ae6 Mon Sep 17 00:00:00 2001 From: Andrea Arcangeli Date: Mon, 28 Jul 2008 15:46:26 -0700 Subject: mmu-notifiers: add mm_take_all_locks() operation mm_take_all_locks holds off reclaim from an entire mm_struct. This allows mmu notifiers to register into the mm at any time with the guarantee that no mmu operation is in progress on the mm. This operation locks against the VM for all pte/vma/mm related operations that could ever happen on a certain mm. This includes vmtruncate, try_to_unmap, and all page faults. The caller must take the mmap_sem in write mode before calling mm_take_all_locks(). The caller isn't allowed to release the mmap_sem until mm_drop_all_locks() returns. mmap_sem in write mode is required in order to block all operations that could modify pagetables and free pages without need of altering the vma layout (for example populate_range() with nonlinear vmas). It's also needed in write mode to avoid new anon_vmas to be associated with existing vmas. A single task can't take more than one mm_take_all_locks() in a row or it would deadlock. mm_take_all_locks() and mm_drop_all_locks are expensive operations that may have to take thousand of locks. mm_take_all_locks() can fail if it's interrupted by signals. When mmu_notifier_register returns, we must be sure that the driver is notified if some task is in the middle of a vmtruncate for the 'mm' where the mmu notifier was registered (mmu_notifier_invalidate_range_start/end is run around the vmtruncation but mmu_notifier_register can run after mmu_notifier_invalidate_range_start and before mmu_notifier_invalidate_range_end). Same problem for rmap paths. And we've to remove page pinning to avoid replicating the tlb_gather logic inside KVM (and GRU doesn't work well with page pinning regardless of needing tlb_gather), so without mm_take_all_locks when vmtruncate frees the page, kvm would have no way to notice that it mapped into sptes a page that is going into the freelist without a chance of any further mmu_notifier notification. [akpm@linux-foundation.org: coding-style fixes] Signed-off-by: Andrea Arcangeli Acked-by: Linus Torvalds Cc: Christoph Lameter Cc: Jack Steiner Cc: Robin Holt Cc: Nick Piggin Cc: Peter Zijlstra Cc: Kanoj Sarcar Cc: Roland Dreier Cc: Steve Wise Cc: Avi Kivity Cc: Hugh Dickins Cc: Rusty Russell Cc: Anthony Liguori Cc: Chris Wright Cc: Marcelo Tosatti Cc: Eric Dumazet Cc: "Paul E. McKenney" Cc: Izik Eidus Cc: Anthony Liguori Cc: Rik van Riel Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mm.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux/mm.h') diff --git a/include/linux/mm.h b/include/linux/mm.h index 6e695eaab4ce..866a3dbe5c75 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -1104,6 +1104,9 @@ extern struct vm_area_struct *copy_vma(struct vm_area_struct **, unsigned long addr, unsigned long len, pgoff_t pgoff); extern void exit_mmap(struct mm_struct *); +extern int mm_take_all_locks(struct mm_struct *mm); +extern void mm_drop_all_locks(struct mm_struct *mm); + #ifdef CONFIG_PROC_FS /* From fs/proc/base.c. callers must _not_ hold the mm's exe_file_lock */ extern void added_exe_file_vma(struct mm_struct *mm); -- cgit v1.2.3 From 1d1958f05095a7e9ecbba86235122784a3d1b561 Mon Sep 17 00:00:00 2001 From: Yinghai Lu Date: Tue, 29 Jul 2008 22:33:16 -0700 Subject: mm: remove find_max_pfn_with_active_regions It has no user now Also print out info about adding/removing active regions. Signed-off-by: Yinghai Lu Acked-by: Mel Gorman Acked-by: Ingo Molnar Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mm.h | 1 - mm/page_alloc.c | 17 ----------------- 2 files changed, 18 deletions(-) (limited to 'include/linux/mm.h') diff --git a/include/linux/mm.h b/include/linux/mm.h index 866a3dbe5c75..5e2c8af49998 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -1041,7 +1041,6 @@ extern unsigned long absent_pages_in_range(unsigned long start_pfn, extern void get_pfn_range_for_nid(unsigned int nid, unsigned long *start_pfn, unsigned long *end_pfn); extern unsigned long find_min_pfn_with_active_regions(void); -extern unsigned long find_max_pfn_with_active_regions(void); extern void free_bootmem_with_active_regions(int nid, unsigned long max_low_pfn); typedef int (*work_fn_t)(unsigned long, unsigned long, void *); diff --git a/mm/page_alloc.c b/mm/page_alloc.c index 3cf3d05b6bd4..401d104d2bb6 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -3753,23 +3753,6 @@ unsigned long __init find_min_pfn_with_active_regions(void) return find_min_pfn_for_node(MAX_NUMNODES); } -/** - * find_max_pfn_with_active_regions - Find the maximum PFN registered - * - * It returns the maximum PFN based on information provided via - * add_active_range(). - */ -unsigned long __init find_max_pfn_with_active_regions(void) -{ - int i; - unsigned long max_pfn = 0; - - for (i = 0; i < nr_nodemap_entries; i++) - max_pfn = max(max_pfn, early_node_map[i].end_pfn); - - return max_pfn; -} - /* * early_calculate_totalpages() * Sum pages in active regions for movable zone. -- cgit v1.2.3 From c627f9cc046c7cd93b4525d89377fb409e170a18 Mon Sep 17 00:00:00 2001 From: Jack Steiner Date: Tue, 29 Jul 2008 22:33:53 -0700 Subject: mm: add zap_vma_ptes(): a library function to unmap driver ptes zap_vma_ptes() is intended to be used by drivers to unmap ptes assigned to the driver private vmas. This interface is similar to zap_page_range() but is less general & less likely to be abused. Needed by the GRU driver. Signed-off-by: Jack Steiner Cc: Nick Piggin Cc: Hugh Dickins Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mm.h | 2 ++ mm/memory.c | 23 +++++++++++++++++++++++ 2 files changed, 25 insertions(+) (limited to 'include/linux/mm.h') diff --git a/include/linux/mm.h b/include/linux/mm.h index 5e2c8af49998..335288bff1b7 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -744,6 +744,8 @@ struct zap_details { struct page *vm_normal_page(struct vm_area_struct *vma, unsigned long addr, pte_t pte); +int zap_vma_ptes(struct vm_area_struct *vma, unsigned long address, + unsigned long size); unsigned long zap_page_range(struct vm_area_struct *vma, unsigned long address, unsigned long size, struct zap_details *); unsigned long unmap_vmas(struct mmu_gather **tlb, diff --git a/mm/memory.c b/mm/memory.c index 67f0ab9077d9..6793b9c68107 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -994,6 +994,29 @@ unsigned long zap_page_range(struct vm_area_struct *vma, unsigned long address, return end; } +/** + * zap_vma_ptes - remove ptes mapping the vma + * @vma: vm_area_struct holding ptes to be zapped + * @address: starting address of pages to zap + * @size: number of bytes to zap + * + * This function only unmaps ptes assigned to VM_PFNMAP vmas. + * + * The entire address range must be fully contained within the vma. + * + * Returns 0 if successful. + */ +int zap_vma_ptes(struct vm_area_struct *vma, unsigned long address, + unsigned long size) +{ + if (address < vma->vm_start || address + size > vma->vm_end || + !(vma->vm_flags & VM_PFNMAP)) + return -1; + zap_page_range(vma, address, size, NULL); + return 0; +} +EXPORT_SYMBOL_GPL(zap_vma_ptes); + /* * Do a quick page-table lookup for a single page. */ -- cgit v1.2.3