From 47f29df7db78ee4fcdb104cf36918d987ddd0278 Mon Sep 17 00:00:00 2001 From: Marek Szyprowski Date: Wed, 29 Oct 2014 14:50:29 -0700 Subject: drivers: of: add return value to of_reserved_mem_device_init() Driver calling of_reserved_mem_device_init() might be interested if the initialization has been successful or not, so add support for returning error code. This fixes a build warining caused by commit 7bfa5ab6fa1b ("drivers: dma-coherent: add initialization from device tree"), which has been merged without this change and without fixing function return value. Fixes: 7bfa5ab6fa1b1 ("drivers: dma-coherent: add initialization from device tree") Signed-off-by: Marek Szyprowski Acked-by: Arnd Bergmann Cc: Michal Nazarewicz Cc: Grant Likely Cc: Laura Abbott Cc: Josh Cartwright Cc: Joonsoo Kim Cc: Kyungmin Park Cc: Russell King Cc: Stephen Rothwell Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/of_reserved_mem.h | 9 ++++++--- 1 file changed, 6 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/of_reserved_mem.h b/include/linux/of_reserved_mem.h index 5b5efae09135..ad2f67054372 100644 --- a/include/linux/of_reserved_mem.h +++ b/include/linux/of_reserved_mem.h @@ -16,7 +16,7 @@ struct reserved_mem { }; struct reserved_mem_ops { - void (*device_init)(struct reserved_mem *rmem, + int (*device_init)(struct reserved_mem *rmem, struct device *dev); void (*device_release)(struct reserved_mem *rmem, struct device *dev); @@ -28,14 +28,17 @@ typedef int (*reservedmem_of_init_fn)(struct reserved_mem *rmem); _OF_DECLARE(reservedmem, name, compat, init, reservedmem_of_init_fn) #ifdef CONFIG_OF_RESERVED_MEM -void of_reserved_mem_device_init(struct device *dev); +int of_reserved_mem_device_init(struct device *dev); void of_reserved_mem_device_release(struct device *dev); void fdt_init_reserved_mem(void); void fdt_reserved_mem_save_node(unsigned long node, const char *uname, phys_addr_t base, phys_addr_t size); #else -static inline void of_reserved_mem_device_init(struct device *dev) { } +static inline int of_reserved_mem_device_init(struct device *dev) +{ + return -ENOSYS; +} static inline void of_reserved_mem_device_release(struct device *pdev) { } static inline void fdt_init_reserved_mem(void) { } -- cgit v1.2.3 From 6d50e60cd2edb5a57154db5a6f64eef5aa59b751 Mon Sep 17 00:00:00 2001 From: David Rientjes Date: Wed, 29 Oct 2014 14:50:31 -0700 Subject: mm, thp: fix collapsing of hugepages on madvise If an anonymous mapping is not allowed to fault thp memory and then madvise(MADV_HUGEPAGE) is used after fault, khugepaged will never collapse this memory into thp memory. This occurs because the madvise(2) handler for thp, hugepage_madvise(), clears VM_NOHUGEPAGE on the stack and it isn't stored in vma->vm_flags until the final action of madvise_behavior(). This causes the khugepaged_enter_vma_merge() to be a no-op in hugepage_madvise() when the vma had previously had VM_NOHUGEPAGE set. Fix this by passing the correct vma flags to the khugepaged mm slot handler. There's no chance khugepaged can run on this vma until after madvise_behavior() returns since we hold mm->mmap_sem. It would be possible to clear VM_NOHUGEPAGE directly from vma->vm_flags in hugepage_advise(), but I didn't want to introduce special case behavior into madvise_behavior(). I think it's best to just let it always set vma->vm_flags itself. Signed-off-by: David Rientjes Reported-by: Suleiman Souhlal Cc: "Kirill A. Shutemov" Cc: Andrea Arcangeli Cc: Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/khugepaged.h | 17 ++++++++++------- 1 file changed, 10 insertions(+), 7 deletions(-) (limited to 'include/linux') diff --git a/include/linux/khugepaged.h b/include/linux/khugepaged.h index 6b394f0b5148..eeb307985715 100644 --- a/include/linux/khugepaged.h +++ b/include/linux/khugepaged.h @@ -6,7 +6,8 @@ #ifdef CONFIG_TRANSPARENT_HUGEPAGE extern int __khugepaged_enter(struct mm_struct *mm); extern void __khugepaged_exit(struct mm_struct *mm); -extern int khugepaged_enter_vma_merge(struct vm_area_struct *vma); +extern int khugepaged_enter_vma_merge(struct vm_area_struct *vma, + unsigned long vm_flags); #define khugepaged_enabled() \ (transparent_hugepage_flags & \ @@ -35,13 +36,13 @@ static inline void khugepaged_exit(struct mm_struct *mm) __khugepaged_exit(mm); } -static inline int khugepaged_enter(struct vm_area_struct *vma) +static inline int khugepaged_enter(struct vm_area_struct *vma, + unsigned long vm_flags) { if (!test_bit(MMF_VM_HUGEPAGE, &vma->vm_mm->flags)) if ((khugepaged_always() || - (khugepaged_req_madv() && - vma->vm_flags & VM_HUGEPAGE)) && - !(vma->vm_flags & VM_NOHUGEPAGE)) + (khugepaged_req_madv() && (vm_flags & VM_HUGEPAGE))) && + !(vm_flags & VM_NOHUGEPAGE)) if (__khugepaged_enter(vma->vm_mm)) return -ENOMEM; return 0; @@ -54,11 +55,13 @@ static inline int khugepaged_fork(struct mm_struct *mm, struct mm_struct *oldmm) static inline void khugepaged_exit(struct mm_struct *mm) { } -static inline int khugepaged_enter(struct vm_area_struct *vma) +static inline int khugepaged_enter(struct vm_area_struct *vma, + unsigned long vm_flags) { return 0; } -static inline int khugepaged_enter_vma_merge(struct vm_area_struct *vma) +static inline int khugepaged_enter_vma_merge(struct vm_area_struct *vma, + unsigned long vm_flags) { return 0; } -- cgit v1.2.3 From 3a3c02ecf7f2852f122d6d16fb9b3d9cb0c6f201 Mon Sep 17 00:00:00 2001 From: Johannes Weiner Date: Wed, 29 Oct 2014 14:50:46 -0700 Subject: mm: page-writeback: inline account_page_dirtied() into single caller A follow-up patch would have changed the call signature. To save the trouble, just fold it instead. Signed-off-by: Johannes Weiner Acked-by: Michal Hocko Cc: Vladimir Davydov Cc: [3.17.x] Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mm.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mm.h b/include/linux/mm.h index 27eb1bfbe704..b46461116cd2 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -1235,7 +1235,6 @@ int __set_page_dirty_no_writeback(struct page *page); int redirty_page_for_writepage(struct writeback_control *wbc, struct page *page); void account_page_dirtied(struct page *page, struct address_space *mapping); -void account_page_writeback(struct page *page); int set_page_dirty(struct page *page); int set_page_dirty_lock(struct page *page); int clear_page_dirty_for_io(struct page *page); -- cgit v1.2.3 From d7365e783edb858279be1d03f61bc8d5d3383d90 Mon Sep 17 00:00:00 2001 From: Johannes Weiner Date: Wed, 29 Oct 2014 14:50:48 -0700 Subject: mm: memcontrol: fix missed end-writeback page accounting Commit 0a31bc97c80c ("mm: memcontrol: rewrite uncharge API") changed page migration to uncharge the old page right away. The page is locked, unmapped, truncated, and off the LRU, but it could race with writeback ending, which then doesn't unaccount the page properly: test_clear_page_writeback() migration wait_on_page_writeback() TestClearPageWriteback() mem_cgroup_migrate() clear PCG_USED mem_cgroup_update_page_stat() if (PageCgroupUsed(pc)) decrease memcg pages under writeback release pc->mem_cgroup->move_lock The per-page statistics interface is heavily optimized to avoid a function call and a lookup_page_cgroup() in the file unmap fast path, which means it doesn't verify whether a page is still charged before clearing PageWriteback() and it has to do it in the stat update later. Rework it so that it looks up the page's memcg once at the beginning of the transaction and then uses it throughout. The charge will be verified before clearing PageWriteback() and migration can't uncharge the page as long as that is still set. The RCU lock will protect the memcg past uncharge. As far as losing the optimization goes, the following test results are from a microbenchmark that maps, faults, and unmaps a 4GB sparse file three times in a nested fashion, so that there are two negative passes that don't account but still go through the new transaction overhead. There is no actual difference: old: 33.195102545 seconds time elapsed ( +- 0.01% ) new: 33.199231369 seconds time elapsed ( +- 0.03% ) The time spent in page_remove_rmap()'s callees still adds up to the same, but the time spent in the function itself seems reduced: # Children Self Command Shared Object Symbol old: 0.12% 0.11% filemapstress [kernel.kallsyms] [k] page_remove_rmap new: 0.12% 0.08% filemapstress [kernel.kallsyms] [k] page_remove_rmap Signed-off-by: Johannes Weiner Acked-by: Michal Hocko Cc: Vladimir Davydov Cc: [3.17.x] Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/memcontrol.h | 58 ++++++++++++++-------------------------------- 1 file changed, 17 insertions(+), 41 deletions(-) (limited to 'include/linux') diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h index 19df5d857411..6b75640ef5ab 100644 --- a/include/linux/memcontrol.h +++ b/include/linux/memcontrol.h @@ -139,48 +139,23 @@ static inline bool mem_cgroup_disabled(void) return false; } -void __mem_cgroup_begin_update_page_stat(struct page *page, bool *locked, - unsigned long *flags); - -extern atomic_t memcg_moving; - -static inline void mem_cgroup_begin_update_page_stat(struct page *page, - bool *locked, unsigned long *flags) -{ - if (mem_cgroup_disabled()) - return; - rcu_read_lock(); - *locked = false; - if (atomic_read(&memcg_moving)) - __mem_cgroup_begin_update_page_stat(page, locked, flags); -} - -void __mem_cgroup_end_update_page_stat(struct page *page, - unsigned long *flags); -static inline void mem_cgroup_end_update_page_stat(struct page *page, - bool *locked, unsigned long *flags) -{ - if (mem_cgroup_disabled()) - return; - if (*locked) - __mem_cgroup_end_update_page_stat(page, flags); - rcu_read_unlock(); -} - -void mem_cgroup_update_page_stat(struct page *page, - enum mem_cgroup_stat_index idx, - int val); - -static inline void mem_cgroup_inc_page_stat(struct page *page, +struct mem_cgroup *mem_cgroup_begin_page_stat(struct page *page, bool *locked, + unsigned long *flags); +void mem_cgroup_end_page_stat(struct mem_cgroup *memcg, bool locked, + unsigned long flags); +void mem_cgroup_update_page_stat(struct mem_cgroup *memcg, + enum mem_cgroup_stat_index idx, int val); + +static inline void mem_cgroup_inc_page_stat(struct mem_cgroup *memcg, enum mem_cgroup_stat_index idx) { - mem_cgroup_update_page_stat(page, idx, 1); + mem_cgroup_update_page_stat(memcg, idx, 1); } -static inline void mem_cgroup_dec_page_stat(struct page *page, +static inline void mem_cgroup_dec_page_stat(struct mem_cgroup *memcg, enum mem_cgroup_stat_index idx) { - mem_cgroup_update_page_stat(page, idx, -1); + mem_cgroup_update_page_stat(memcg, idx, -1); } unsigned long mem_cgroup_soft_limit_reclaim(struct zone *zone, int order, @@ -315,13 +290,14 @@ mem_cgroup_print_oom_info(struct mem_cgroup *memcg, struct task_struct *p) { } -static inline void mem_cgroup_begin_update_page_stat(struct page *page, +static inline struct mem_cgroup *mem_cgroup_begin_page_stat(struct page *page, bool *locked, unsigned long *flags) { + return NULL; } -static inline void mem_cgroup_end_update_page_stat(struct page *page, - bool *locked, unsigned long *flags) +static inline void mem_cgroup_end_page_stat(struct mem_cgroup *memcg, + bool locked, unsigned long flags) { } @@ -343,12 +319,12 @@ static inline bool mem_cgroup_oom_synchronize(bool wait) return false; } -static inline void mem_cgroup_inc_page_stat(struct page *page, +static inline void mem_cgroup_inc_page_stat(struct mem_cgroup *memcg, enum mem_cgroup_stat_index idx) { } -static inline void mem_cgroup_dec_page_stat(struct page *page, +static inline void mem_cgroup_dec_page_stat(struct mem_cgroup *memcg, enum mem_cgroup_stat_index idx) { } -- cgit v1.2.3