From e732ff707743e5ceba6ae2bfc7e799a0bac30ffa Mon Sep 17 00:00:00 2001 From: "Figo.zhang" Date: Tue, 26 Oct 2010 21:01:47 +0800 Subject: mmu_notifier.h: fix comment spelling Signed-off-by: Figo.zhang Signed-off-by: Linus Torvalds --- include/linux/mmu_notifier.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux/mmu_notifier.h') diff --git a/include/linux/mmu_notifier.h b/include/linux/mmu_notifier.h index 4e02ee2b071e..43dcfbdc39de 100644 --- a/include/linux/mmu_notifier.h +++ b/include/linux/mmu_notifier.h @@ -227,7 +227,7 @@ static inline void mmu_notifier_mm_destroy(struct mm_struct *mm) /* * These two macros will sometime replace ptep_clear_flush. - * ptep_clear_flush is impleemnted as macro itself, so this also is + * ptep_clear_flush is implemented as macro itself, so this also is * implemented as a macro until ptep_clear_flush will converted to an * inline function, to diminish the risk of compilation failure. The * invalidate_page method over time can be moved outside the PT lock -- cgit v1.2.2 From 91a4ee2670e0ee2b0630a0eb24fb9a87ea3acd0a Mon Sep 17 00:00:00 2001 From: Andrea Arcangeli Date: Thu, 13 Jan 2011 15:46:44 -0800 Subject: thp: add pmd mmu_notifier helpers Add mmu notifier helpers to handle pmd huge operations. Signed-off-by: Andrea Arcangeli Acked-by: Rik van Riel Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mmu_notifier.h | 40 ++++++++++++++++++++++++++++++++++++++++ 1 file changed, 40 insertions(+) (limited to 'include/linux/mmu_notifier.h') diff --git a/include/linux/mmu_notifier.h b/include/linux/mmu_notifier.h index 43dcfbdc39de..cbfab1e9957d 100644 --- a/include/linux/mmu_notifier.h +++ b/include/linux/mmu_notifier.h @@ -243,6 +243,32 @@ static inline void mmu_notifier_mm_destroy(struct mm_struct *mm) __pte; \ }) +#define pmdp_clear_flush_notify(__vma, __address, __pmdp) \ +({ \ + pmd_t __pmd; \ + struct vm_area_struct *___vma = __vma; \ + unsigned long ___address = __address; \ + VM_BUG_ON(__address & ~HPAGE_PMD_MASK); \ + mmu_notifier_invalidate_range_start(___vma->vm_mm, ___address, \ + (__address)+HPAGE_PMD_SIZE);\ + __pmd = pmdp_clear_flush(___vma, ___address, __pmdp); \ + mmu_notifier_invalidate_range_end(___vma->vm_mm, ___address, \ + (__address)+HPAGE_PMD_SIZE); \ + __pmd; \ +}) + +#define pmdp_splitting_flush_notify(__vma, __address, __pmdp) \ +({ \ + struct vm_area_struct *___vma = __vma; \ + unsigned long ___address = __address; \ + VM_BUG_ON(__address & ~HPAGE_PMD_MASK); \ + mmu_notifier_invalidate_range_start(___vma->vm_mm, ___address, \ + (__address)+HPAGE_PMD_SIZE);\ + pmdp_splitting_flush(___vma, ___address, __pmdp); \ + mmu_notifier_invalidate_range_end(___vma->vm_mm, ___address, \ + (__address)+HPAGE_PMD_SIZE); \ +}) + #define ptep_clear_flush_young_notify(__vma, __address, __ptep) \ ({ \ int __young; \ @@ -254,6 +280,17 @@ static inline void mmu_notifier_mm_destroy(struct mm_struct *mm) __young; \ }) +#define pmdp_clear_flush_young_notify(__vma, __address, __pmdp) \ +({ \ + int __young; \ + struct vm_area_struct *___vma = __vma; \ + unsigned long ___address = __address; \ + __young = pmdp_clear_flush_young(___vma, ___address, __pmdp); \ + __young |= mmu_notifier_clear_flush_young(___vma->vm_mm, \ + ___address); \ + __young; \ +}) + #define set_pte_at_notify(__mm, __address, __ptep, __pte) \ ({ \ struct mm_struct *___mm = __mm; \ @@ -305,7 +342,10 @@ static inline void mmu_notifier_mm_destroy(struct mm_struct *mm) } #define ptep_clear_flush_young_notify ptep_clear_flush_young +#define pmdp_clear_flush_young_notify pmdp_clear_flush_young #define ptep_clear_flush_notify ptep_clear_flush +#define pmdp_clear_flush_notify pmdp_clear_flush +#define pmdp_splitting_flush_notify pmdp_splitting_flush #define set_pte_at_notify set_pte_at #endif /* CONFIG_MMU_NOTIFIER */ -- cgit v1.2.2 From 8ee53820edfd1f3b6554c593f337148dd3d7fc91 Mon Sep 17 00:00:00 2001 From: Andrea Arcangeli Date: Thu, 13 Jan 2011 15:47:10 -0800 Subject: thp: mmu_notifier_test_young For GRU and EPT, we need gup-fast to set referenced bit too (this is why it's correct to return 0 when shadow_access_mask is zero, it requires gup-fast to set the referenced bit). qemu-kvm access already sets the young bit in the pte if it isn't zero-copy, if it's zero copy or a shadow paging EPT minor fault we relay on gup-fast to signal the page is in use... We also need to check the young bits on the secondary pagetables for NPT and not nested shadow mmu as the data may never get accessed again by the primary pte. Without this closer accuracy, we'd have to remove the heuristic that avoids collapsing hugepages in hugepage virtual regions that have not even a single subpage in use. ->test_young is full backwards compatible with GRU and other usages that don't have young bits in pagetables set by the hardware and that should nuke the secondary mmu mappings when ->clear_flush_young runs just like EPT does. Removing the heuristic that checks the young bit in khugepaged/collapse_huge_page completely isn't so bad either probably but I thought it was worth it and this makes it reliable. Signed-off-by: Andrea Arcangeli Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mmu_notifier.h | 26 ++++++++++++++++++++++++++ 1 file changed, 26 insertions(+) (limited to 'include/linux/mmu_notifier.h') diff --git a/include/linux/mmu_notifier.h b/include/linux/mmu_notifier.h index cbfab1e9957d..cc2e7dfea9d7 100644 --- a/include/linux/mmu_notifier.h +++ b/include/linux/mmu_notifier.h @@ -61,6 +61,16 @@ struct mmu_notifier_ops { struct mm_struct *mm, unsigned long address); + /* + * test_young is called to check the young/accessed bitflag in + * the secondary pte. This is used to know if the page is + * frequently used without actually clearing the flag or tearing + * down the secondary mapping on the page. + */ + int (*test_young)(struct mmu_notifier *mn, + struct mm_struct *mm, + unsigned long address); + /* * change_pte is called in cases that pte mapping to page is changed: * for example, when ksm remaps pte to point to a new shared page. @@ -163,6 +173,8 @@ extern void __mmu_notifier_mm_destroy(struct mm_struct *mm); extern void __mmu_notifier_release(struct mm_struct *mm); extern int __mmu_notifier_clear_flush_young(struct mm_struct *mm, unsigned long address); +extern int __mmu_notifier_test_young(struct mm_struct *mm, + unsigned long address); extern void __mmu_notifier_change_pte(struct mm_struct *mm, unsigned long address, pte_t pte); extern void __mmu_notifier_invalidate_page(struct mm_struct *mm, @@ -186,6 +198,14 @@ static inline int mmu_notifier_clear_flush_young(struct mm_struct *mm, return 0; } +static inline int mmu_notifier_test_young(struct mm_struct *mm, + unsigned long address) +{ + if (mm_has_notifiers(mm)) + return __mmu_notifier_test_young(mm, address); + return 0; +} + static inline void mmu_notifier_change_pte(struct mm_struct *mm, unsigned long address, pte_t pte) { @@ -313,6 +333,12 @@ static inline int mmu_notifier_clear_flush_young(struct mm_struct *mm, return 0; } +static inline int mmu_notifier_test_young(struct mm_struct *mm, + unsigned long address) +{ + return 0; +} + static inline void mmu_notifier_change_pte(struct mm_struct *mm, unsigned long address, pte_t pte) { -- cgit v1.2.2 From 3d48ae45e72390ddf8cc5256ac32ed6f7a19cbea Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Tue, 24 May 2011 17:12:06 -0700 Subject: mm: Convert i_mmap_lock to a mutex Straightforward conversion of i_mmap_lock to a mutex. Signed-off-by: Peter Zijlstra Acked-by: Hugh Dickins Cc: Benjamin Herrenschmidt Cc: David Miller Cc: Martin Schwidefsky Cc: Russell King Cc: Paul Mundt Cc: Jeff Dike Cc: Richard Weinberger Cc: Tony Luck Cc: KAMEZAWA Hiroyuki Cc: Mel Gorman Cc: KOSAKI Motohiro Cc: Nick Piggin Cc: Namhyung Kim Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mmu_notifier.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux/mmu_notifier.h') diff --git a/include/linux/mmu_notifier.h b/include/linux/mmu_notifier.h index cc2e7dfea9d7..a877dfc243eb 100644 --- a/include/linux/mmu_notifier.h +++ b/include/linux/mmu_notifier.h @@ -150,7 +150,7 @@ struct mmu_notifier_ops { * Therefore notifier chains can only be traversed when either * * 1. mmap_sem is held. - * 2. One of the reverse map locks is held (i_mmap_lock or anon_vma->lock). + * 2. One of the reverse map locks is held (i_mmap_mutex or anon_vma->lock). * 3. No other concurrent thread can access the list (release) */ struct mmu_notifier { -- cgit v1.2.2 From 2b575eb64f7a9c701fb4bfdb12388ac547f6c2b6 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Tue, 24 May 2011 17:12:11 -0700 Subject: mm: convert anon_vma->lock to a mutex Straightforward conversion of anon_vma->lock to a mutex. Signed-off-by: Peter Zijlstra Acked-by: Hugh Dickins Reviewed-by: KOSAKI Motohiro Cc: Benjamin Herrenschmidt Cc: David Miller Cc: Martin Schwidefsky Cc: Russell King Cc: Paul Mundt Cc: Jeff Dike Cc: Richard Weinberger Cc: Tony Luck Cc: KAMEZAWA Hiroyuki Cc: Mel Gorman Cc: Nick Piggin Cc: Namhyung Kim Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mmu_notifier.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux/mmu_notifier.h') diff --git a/include/linux/mmu_notifier.h b/include/linux/mmu_notifier.h index a877dfc243eb..1d1b1e13f79f 100644 --- a/include/linux/mmu_notifier.h +++ b/include/linux/mmu_notifier.h @@ -150,7 +150,7 @@ struct mmu_notifier_ops { * Therefore notifier chains can only be traversed when either * * 1. mmap_sem is held. - * 2. One of the reverse map locks is held (i_mmap_mutex or anon_vma->lock). + * 2. One of the reverse map locks is held (i_mmap_mutex or anon_vma->mutex). * 3. No other concurrent thread can access the list (release) */ struct mmu_notifier { -- cgit v1.2.2