From c177c81e09e517bbf75b67762cdab1b83aba6976 Mon Sep 17 00:00:00 2001 From: Naoya Horiguchi Date: Wed, 4 Jun 2014 16:05:35 -0700 Subject: hugetlb: restrict hugepage_migration_support() to x86_64 Currently hugepage migration is available for all archs which support pmd-level hugepage, but testing is done only for x86_64 and there're bugs for other archs. So to avoid breaking such archs, this patch limits the availability strictly to x86_64 until developers of other archs get interested in enabling this feature. Simply disabling hugepage migration on non-x86_64 archs is not enough to fix the reported problem where sys_move_pages() hits the BUG_ON() in follow_page(FOLL_GET), so let's fix this by checking if hugepage migration is supported in vma_migratable(). Signed-off-by: Naoya Horiguchi Reported-by: Michael Ellerman Tested-by: Michael Ellerman Acked-by: Hugh Dickins Cc: Benjamin Herrenschmidt Cc: Tony Luck Cc: Russell King Cc: Martin Schwidefsky Cc: James Hogan Cc: Ralf Baechle Cc: David Miller Cc: [3.12+] Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/hugetlb.h | 13 +++++-------- include/linux/mempolicy.h | 6 ++++++ 2 files changed, 11 insertions(+), 8 deletions(-) (limited to 'include/linux') diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h index b65166de1d9d..d0bad1a8b0bd 100644 --- a/include/linux/hugetlb.h +++ b/include/linux/hugetlb.h @@ -392,15 +392,13 @@ static inline pgoff_t basepage_index(struct page *page) extern void dissolve_free_huge_pages(unsigned long start_pfn, unsigned long end_pfn); -int pmd_huge_support(void); -/* - * Currently hugepage migration is enabled only for pmd-based hugepage. - * This function will be updated when hugepage migration is more widely - * supported. - */ static inline int hugepage_migration_support(struct hstate *h) { - return pmd_huge_support() && (huge_page_shift(h) == PMD_SHIFT); +#ifdef CONFIG_ARCH_ENABLE_HUGEPAGE_MIGRATION + return huge_page_shift(h) == PMD_SHIFT; +#else + return 0; +#endif } static inline spinlock_t *huge_pte_lockptr(struct hstate *h, @@ -450,7 +448,6 @@ static inline pgoff_t basepage_index(struct page *page) return page->index; } #define dissolve_free_huge_pages(s, e) do {} while (0) -#define pmd_huge_support() 0 #define hugepage_migration_support(h) 0 static inline spinlock_t *huge_pte_lockptr(struct hstate *h, diff --git a/include/linux/mempolicy.h b/include/linux/mempolicy.h index 3c1b968da0ca..f230a978e6ba 100644 --- a/include/linux/mempolicy.h +++ b/include/linux/mempolicy.h @@ -175,6 +175,12 @@ static inline int vma_migratable(struct vm_area_struct *vma) { if (vma->vm_flags & (VM_IO | VM_PFNMAP)) return 0; + +#ifndef CONFIG_ARCH_ENABLE_HUGEPAGE_MIGRATION + if (vma->vm_flags & VM_HUGETLB) + return 0; +#endif + /* * Migration allocates pages in the highest zone. If we cannot * do so then migration (at least from node to node) is not -- cgit v1.2.3-71-gd317 From ac13a829f6adb674015ab399594c089990104af7 Mon Sep 17 00:00:00 2001 From: Fabian Frederick Date: Wed, 4 Jun 2014 16:06:27 -0700 Subject: fs/libfs.c: add generic data flush to fsync Description by Jan Kara: "A lot of older filesystems don't properly flush volatile disk caches on fsync(2) which can lead to loss of fsynced data after power failure. This patch makes generic_file_fsync() issue proper cache flush to fix the problem. Sysadmin can use /sys/devices/.../cache_type to tell the system it should not send the cache flush." [akpm@linux-foundation.org: nuke ifdef] [akpm@linux-foundation.org: fix warning] Signed-off-by: Fabian Frederick Suggested-by: Jan Kara Suggested-by: Christoph Hellwig Cc: Jan Kara Cc: Christoph Hellwig Cc: Alexander Viro Cc: "Theodore Ts'o" Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- fs/libfs.c | 34 +++++++++++++++++++++++++++++++--- include/linux/blkdev.h | 9 +++++++++ include/linux/fs.h | 1 + 3 files changed, 41 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/fs/libfs.c b/fs/libfs.c index a1844244246f..88e3e00e2eca 100644 --- a/fs/libfs.c +++ b/fs/libfs.c @@ -3,6 +3,7 @@ * Library for filesystems writers. */ +#include #include #include #include @@ -923,16 +924,19 @@ struct dentry *generic_fh_to_parent(struct super_block *sb, struct fid *fid, EXPORT_SYMBOL_GPL(generic_fh_to_parent); /** - * generic_file_fsync - generic fsync implementation for simple filesystems + * __generic_file_fsync - generic fsync implementation for simple filesystems + * * @file: file to synchronize + * @start: start offset in bytes + * @end: end offset in bytes (inclusive) * @datasync: only synchronize essential metadata if true * * This is a generic implementation of the fsync method for simple * filesystems which track all non-inode metadata in the buffers list * hanging off the address_space structure. */ -int generic_file_fsync(struct file *file, loff_t start, loff_t end, - int datasync) +int __generic_file_fsync(struct file *file, loff_t start, loff_t end, + int datasync) { struct inode *inode = file->f_mapping->host; int err; @@ -952,10 +956,34 @@ int generic_file_fsync(struct file *file, loff_t start, loff_t end, err = sync_inode_metadata(inode, 1); if (ret == 0) ret = err; + out: mutex_unlock(&inode->i_mutex); return ret; } +EXPORT_SYMBOL(__generic_file_fsync); + +/** + * generic_file_fsync - generic fsync implementation for simple filesystems + * with flush + * @file: file to synchronize + * @start: start offset in bytes + * @end: end offset in bytes (inclusive) + * @datasync: only synchronize essential metadata if true + * + */ + +int generic_file_fsync(struct file *file, loff_t start, loff_t end, + int datasync) +{ + struct inode *inode = file->f_mapping->host; + int err; + + err = __generic_file_fsync(file, start, end, datasync); + if (err) + return err; + return blkdev_issue_flush(inode->i_sb->s_bdev, GFP_KERNEL, NULL); +} EXPORT_SYMBOL(generic_file_fsync); /** diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 8aba35f46f87..45cf6e537c83 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -1607,6 +1607,9 @@ struct block_device_operations { extern int __blkdev_driver_ioctl(struct block_device *, fmode_t, unsigned int, unsigned long); #else /* CONFIG_BLOCK */ + +struct block_device; + /* * stubs for when the block layer is configured out */ @@ -1642,6 +1645,12 @@ static inline bool blk_needs_flush_plug(struct task_struct *tsk) return false; } +static inline int blkdev_issue_flush(struct block_device *bdev, gfp_t gfp_mask, + sector_t *error_sector) +{ + return 0; +} + #endif /* CONFIG_BLOCK */ #endif diff --git a/include/linux/fs.h b/include/linux/fs.h index 878031227c57..c3f46e499dd0 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -2590,6 +2590,7 @@ extern ssize_t simple_read_from_buffer(void __user *to, size_t count, extern ssize_t simple_write_to_buffer(void *to, size_t available, loff_t *ppos, const void __user *from, size_t count); +extern int __generic_file_fsync(struct file *, loff_t, loff_t, int); extern int generic_file_fsync(struct file *, loff_t, loff_t, int); extern int generic_check_addressable(unsigned, u64); -- cgit v1.2.3-71-gd317 From c46a7c817e662a820373bb76b88d0ad67d6abe5d Mon Sep 17 00:00:00 2001 From: Mel Gorman Date: Wed, 4 Jun 2014 16:06:30 -0700 Subject: x86: define _PAGE_NUMA by reusing software bits on the PMD and PTE levels _PAGE_NUMA is currently an alias of _PROT_PROTNONE to trap NUMA hinting faults on x86. Care is taken such that _PAGE_NUMA is used only in situations where the VMA flags distinguish between NUMA hinting faults and prot_none faults. This decision was x86-specific and conceptually it is difficult requiring special casing to distinguish between PROTNONE and NUMA ptes based on context. Fundamentally, we only need the _PAGE_NUMA bit to tell the difference between an entry that is really unmapped and a page that is protected for NUMA hinting faults as if the PTE is not present then a fault will be trapped. Swap PTEs on x86-64 use the bits after _PAGE_GLOBAL for the offset. This patch shrinks the maximum possible swap size and uses the bit to uniquely distinguish between NUMA hinting ptes and swap ptes. Signed-off-by: Mel Gorman Cc: David Vrabel Cc: Ingo Molnar Cc: Peter Anvin Cc: Fengguang Wu Cc: Linus Torvalds Cc: Steven Noonan Cc: Rik van Riel Cc: Peter Zijlstra Cc: Andrea Arcangeli Cc: Dave Hansen Cc: Srikar Dronamraju Cc: Cyrill Gorcunov Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- arch/powerpc/include/asm/pgtable.h | 6 ++++ arch/x86/include/asm/pgtable.h | 15 +++++--- arch/x86/include/asm/pgtable_64.h | 8 +++++ arch/x86/include/asm/pgtable_types.h | 66 +++++++++++++++++++----------------- arch/x86/mm/pageattr-test.c | 2 +- include/asm-generic/pgtable.h | 8 +++-- include/linux/swapops.h | 2 +- mm/memory.c | 17 ++++------ 8 files changed, 75 insertions(+), 49 deletions(-) (limited to 'include/linux') diff --git a/arch/powerpc/include/asm/pgtable.h b/arch/powerpc/include/asm/pgtable.h index 3ebb188c3ff5..d98c1ecc3266 100644 --- a/arch/powerpc/include/asm/pgtable.h +++ b/arch/powerpc/include/asm/pgtable.h @@ -44,6 +44,12 @@ static inline int pte_present(pte_t pte) return pte_val(pte) & (_PAGE_PRESENT | _PAGE_NUMA); } +#define pte_present_nonuma pte_present_nonuma +static inline int pte_present_nonuma(pte_t pte) +{ + return pte_val(pte) & (_PAGE_PRESENT); +} + #define pte_numa pte_numa static inline int pte_numa(pte_t pte) { diff --git a/arch/x86/include/asm/pgtable.h b/arch/x86/include/asm/pgtable.h index b459ddf27d64..66276c1d23bb 100644 --- a/arch/x86/include/asm/pgtable.h +++ b/arch/x86/include/asm/pgtable.h @@ -131,7 +131,8 @@ static inline int pte_exec(pte_t pte) static inline int pte_special(pte_t pte) { - return pte_flags(pte) & _PAGE_SPECIAL; + return (pte_flags(pte) & (_PAGE_PRESENT|_PAGE_SPECIAL)) == + (_PAGE_PRESENT|_PAGE_SPECIAL); } static inline unsigned long pte_pfn(pte_t pte) @@ -452,6 +453,12 @@ static inline int pte_present(pte_t a) _PAGE_NUMA); } +#define pte_present_nonuma pte_present_nonuma +static inline int pte_present_nonuma(pte_t a) +{ + return pte_flags(a) & (_PAGE_PRESENT | _PAGE_PROTNONE); +} + #define pte_accessible pte_accessible static inline bool pte_accessible(struct mm_struct *mm, pte_t a) { @@ -860,19 +867,19 @@ static inline void update_mmu_cache_pmd(struct vm_area_struct *vma, static inline pte_t pte_swp_mksoft_dirty(pte_t pte) { - VM_BUG_ON(pte_present(pte)); + VM_BUG_ON(pte_present_nonuma(pte)); return pte_set_flags(pte, _PAGE_SWP_SOFT_DIRTY); } static inline int pte_swp_soft_dirty(pte_t pte) { - VM_BUG_ON(pte_present(pte)); + VM_BUG_ON(pte_present_nonuma(pte)); return pte_flags(pte) & _PAGE_SWP_SOFT_DIRTY; } static inline pte_t pte_swp_clear_soft_dirty(pte_t pte) { - VM_BUG_ON(pte_present(pte)); + VM_BUG_ON(pte_present_nonuma(pte)); return pte_clear_flags(pte, _PAGE_SWP_SOFT_DIRTY); } diff --git a/arch/x86/include/asm/pgtable_64.h b/arch/x86/include/asm/pgtable_64.h index e22c1dbf7feb..6d6ecd09883c 100644 --- a/arch/x86/include/asm/pgtable_64.h +++ b/arch/x86/include/asm/pgtable_64.h @@ -145,8 +145,16 @@ static inline int pgd_large(pgd_t pgd) { return 0; } /* Encode and de-code a swap entry */ #if _PAGE_BIT_FILE < _PAGE_BIT_PROTNONE #define SWP_TYPE_BITS (_PAGE_BIT_FILE - _PAGE_BIT_PRESENT - 1) +#ifdef CONFIG_NUMA_BALANCING +/* Automatic NUMA balancing needs to be distinguishable from swap entries */ +#define SWP_OFFSET_SHIFT (_PAGE_BIT_PROTNONE + 2) +#else #define SWP_OFFSET_SHIFT (_PAGE_BIT_PROTNONE + 1) +#endif #else +#ifdef CONFIG_NUMA_BALANCING +#error Incompatible format for automatic NUMA balancing +#endif #define SWP_TYPE_BITS (_PAGE_BIT_PROTNONE - _PAGE_BIT_PRESENT - 1) #define SWP_OFFSET_SHIFT (_PAGE_BIT_FILE + 1) #endif diff --git a/arch/x86/include/asm/pgtable_types.h b/arch/x86/include/asm/pgtable_types.h index eb3d44945133..f216963760e5 100644 --- a/arch/x86/include/asm/pgtable_types.h +++ b/arch/x86/include/asm/pgtable_types.h @@ -16,15 +16,26 @@ #define _PAGE_BIT_PSE 7 /* 4 MB (or 2MB) page */ #define _PAGE_BIT_PAT 7 /* on 4KB pages */ #define _PAGE_BIT_GLOBAL 8 /* Global TLB entry PPro+ */ -#define _PAGE_BIT_UNUSED1 9 /* available for programmer */ -#define _PAGE_BIT_IOMAP 10 /* flag used to indicate IO mapping */ -#define _PAGE_BIT_HIDDEN 11 /* hidden by kmemcheck */ +#define _PAGE_BIT_SOFTW1 9 /* available for programmer */ +#define _PAGE_BIT_SOFTW2 10 /* " */ +#define _PAGE_BIT_SOFTW3 11 /* " */ #define _PAGE_BIT_PAT_LARGE 12 /* On 2MB or 1GB pages */ -#define _PAGE_BIT_SPECIAL _PAGE_BIT_UNUSED1 -#define _PAGE_BIT_CPA_TEST _PAGE_BIT_UNUSED1 -#define _PAGE_BIT_SPLITTING _PAGE_BIT_UNUSED1 /* only valid on a PSE pmd */ +#define _PAGE_BIT_SPECIAL _PAGE_BIT_SOFTW1 +#define _PAGE_BIT_CPA_TEST _PAGE_BIT_SOFTW1 +#define _PAGE_BIT_SPLITTING _PAGE_BIT_SOFTW2 /* only valid on a PSE pmd */ +#define _PAGE_BIT_IOMAP _PAGE_BIT_SOFTW2 /* flag used to indicate IO mapping */ +#define _PAGE_BIT_HIDDEN _PAGE_BIT_SOFTW3 /* hidden by kmemcheck */ +#define _PAGE_BIT_SOFT_DIRTY _PAGE_BIT_SOFTW3 /* software dirty tracking */ #define _PAGE_BIT_NX 63 /* No execute: only valid after cpuid check */ +/* + * Swap offsets on configurations that allow automatic NUMA balancing use the + * bits after _PAGE_BIT_GLOBAL. To uniquely distinguish NUMA hinting PTEs from + * swap entries, we use the first bit after _PAGE_BIT_GLOBAL and shrink the + * maximum possible swap space from 16TB to 8TB. + */ +#define _PAGE_BIT_NUMA (_PAGE_BIT_GLOBAL+1) + /* If _PAGE_BIT_PRESENT is clear, we use these: */ /* - if the user mapped it with PROT_NONE; pte_present gives true */ #define _PAGE_BIT_PROTNONE _PAGE_BIT_GLOBAL @@ -40,7 +51,7 @@ #define _PAGE_DIRTY (_AT(pteval_t, 1) << _PAGE_BIT_DIRTY) #define _PAGE_PSE (_AT(pteval_t, 1) << _PAGE_BIT_PSE) #define _PAGE_GLOBAL (_AT(pteval_t, 1) << _PAGE_BIT_GLOBAL) -#define _PAGE_UNUSED1 (_AT(pteval_t, 1) << _PAGE_BIT_UNUSED1) +#define _PAGE_SOFTW1 (_AT(pteval_t, 1) << _PAGE_BIT_SOFTW1) #define _PAGE_IOMAP (_AT(pteval_t, 1) << _PAGE_BIT_IOMAP) #define _PAGE_PAT (_AT(pteval_t, 1) << _PAGE_BIT_PAT) #define _PAGE_PAT_LARGE (_AT(pteval_t, 1) << _PAGE_BIT_PAT_LARGE) @@ -61,14 +72,27 @@ * they do not conflict with each other. */ -#define _PAGE_BIT_SOFT_DIRTY _PAGE_BIT_HIDDEN - #ifdef CONFIG_MEM_SOFT_DIRTY #define _PAGE_SOFT_DIRTY (_AT(pteval_t, 1) << _PAGE_BIT_SOFT_DIRTY) #else #define _PAGE_SOFT_DIRTY (_AT(pteval_t, 0)) #endif +/* + * _PAGE_NUMA distinguishes between a numa hinting minor fault and a page + * that is not present. The hinting fault gathers numa placement statistics + * (see pte_numa()). The bit is always zero when the PTE is not present. + * + * The bit picked must be always zero when the pmd is present and not + * present, so that we don't lose information when we set it while + * atomically clearing the present bit. + */ +#ifdef CONFIG_NUMA_BALANCING +#define _PAGE_NUMA (_AT(pteval_t, 1) << _PAGE_BIT_NUMA) +#else +#define _PAGE_NUMA (_AT(pteval_t, 0)) +#endif + /* * Tracking soft dirty bit when a page goes to a swap is tricky. * We need a bit which can be stored in pte _and_ not conflict @@ -94,26 +118,6 @@ #define _PAGE_FILE (_AT(pteval_t, 1) << _PAGE_BIT_FILE) #define _PAGE_PROTNONE (_AT(pteval_t, 1) << _PAGE_BIT_PROTNONE) -/* - * _PAGE_NUMA indicates that this page will trigger a numa hinting - * minor page fault to gather numa placement statistics (see - * pte_numa()). The bit picked (8) is within the range between - * _PAGE_FILE (6) and _PAGE_PROTNONE (8) bits. Therefore, it doesn't - * require changes to the swp entry format because that bit is always - * zero when the pte is not present. - * - * The bit picked must be always zero when the pmd is present and not - * present, so that we don't lose information when we set it while - * atomically clearing the present bit. - * - * Because we shared the same bit (8) with _PAGE_PROTNONE this can be - * interpreted as _PAGE_NUMA only in places that _PAGE_PROTNONE - * couldn't reach, like handle_mm_fault() (see access_error in - * arch/x86/mm/fault.c, the vma protection must not be PROT_NONE for - * handle_mm_fault() to be invoked). - */ -#define _PAGE_NUMA _PAGE_PROTNONE - #define _PAGE_TABLE (_PAGE_PRESENT | _PAGE_RW | _PAGE_USER | \ _PAGE_ACCESSED | _PAGE_DIRTY) #define _KERNPG_TABLE (_PAGE_PRESENT | _PAGE_RW | _PAGE_ACCESSED | \ @@ -122,8 +126,8 @@ /* Set of bits not changed in pte_modify */ #define _PAGE_CHG_MASK (PTE_PFN_MASK | _PAGE_PCD | _PAGE_PWT | \ _PAGE_SPECIAL | _PAGE_ACCESSED | _PAGE_DIRTY | \ - _PAGE_SOFT_DIRTY) -#define _HPAGE_CHG_MASK (_PAGE_CHG_MASK | _PAGE_PSE) + _PAGE_SOFT_DIRTY | _PAGE_NUMA) +#define _HPAGE_CHG_MASK (_PAGE_CHG_MASK | _PAGE_PSE | _PAGE_NUMA) #define _PAGE_CACHE_MASK (_PAGE_PCD | _PAGE_PWT) #define _PAGE_CACHE_WB (0) diff --git a/arch/x86/mm/pageattr-test.c b/arch/x86/mm/pageattr-test.c index 461bc8289024..6629f397b467 100644 --- a/arch/x86/mm/pageattr-test.c +++ b/arch/x86/mm/pageattr-test.c @@ -35,7 +35,7 @@ enum { static int pte_testbit(pte_t pte) { - return pte_flags(pte) & _PAGE_UNUSED1; + return pte_flags(pte) & _PAGE_SOFTW1; } struct split_state { diff --git a/include/asm-generic/pgtable.h b/include/asm-generic/pgtable.h index a8015a7a55bb..53b2acc38213 100644 --- a/include/asm-generic/pgtable.h +++ b/include/asm-generic/pgtable.h @@ -233,6 +233,10 @@ static inline int pmd_same(pmd_t pmd_a, pmd_t pmd_b) # define pte_accessible(mm, pte) ((void)(pte), 1) #endif +#ifndef pte_present_nonuma +#define pte_present_nonuma(pte) pte_present(pte) +#endif + #ifndef flush_tlb_fix_spurious_fault #define flush_tlb_fix_spurious_fault(vma, address) flush_tlb_page(vma, address) #endif @@ -670,7 +674,7 @@ static inline int pmd_trans_unstable(pmd_t *pmd) static inline int pte_numa(pte_t pte) { return (pte_flags(pte) & - (_PAGE_NUMA|_PAGE_PRESENT)) == _PAGE_NUMA; + (_PAGE_NUMA|_PAGE_PROTNONE|_PAGE_PRESENT)) == _PAGE_NUMA; } #endif @@ -678,7 +682,7 @@ static inline int pte_numa(pte_t pte) static inline int pmd_numa(pmd_t pmd) { return (pmd_flags(pmd) & - (_PAGE_NUMA|_PAGE_PRESENT)) == _PAGE_NUMA; + (_PAGE_NUMA|_PAGE_PROTNONE|_PAGE_PRESENT)) == _PAGE_NUMA; } #endif diff --git a/include/linux/swapops.h b/include/linux/swapops.h index c0f75261a728..6adfb7bfbf44 100644 --- a/include/linux/swapops.h +++ b/include/linux/swapops.h @@ -54,7 +54,7 @@ static inline pgoff_t swp_offset(swp_entry_t entry) /* check whether a pte points to a swap entry */ static inline int is_swap_pte(pte_t pte) { - return !pte_none(pte) && !pte_present(pte) && !pte_file(pte); + return !pte_none(pte) && !pte_present_nonuma(pte) && !pte_file(pte); } #endif diff --git a/mm/memory.c b/mm/memory.c index e302ae1dcce0..0897830011f3 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -756,7 +756,7 @@ struct page *vm_normal_page(struct vm_area_struct *vma, unsigned long addr, unsigned long pfn = pte_pfn(pte); if (HAVE_PTE_SPECIAL) { - if (likely(!pte_special(pte))) + if (likely(!pte_special(pte) || pte_numa(pte))) goto check_pfn; if (vma->vm_flags & (VM_PFNMAP | VM_MIXEDMAP)) return NULL; @@ -782,14 +782,15 @@ struct page *vm_normal_page(struct vm_area_struct *vma, unsigned long addr, } } - if (is_zero_pfn(pfn)) - return NULL; check_pfn: if (unlikely(pfn > highest_memmap_pfn)) { print_bad_pte(vma, addr, pte, NULL); return NULL; } + if (is_zero_pfn(pfn)) + return NULL; + /* * NOTE! We still have PageReserved() pages in the page tables. * eg. VDSO mappings can cause them to exist. @@ -1722,13 +1723,9 @@ long __get_user_pages(struct task_struct *tsk, struct mm_struct *mm, VM_BUG_ON(!!pages != !!(gup_flags & FOLL_GET)); /* - * If FOLL_FORCE and FOLL_NUMA are both set, handle_mm_fault - * would be called on PROT_NONE ranges. We must never invoke - * handle_mm_fault on PROT_NONE ranges or the NUMA hinting - * page faults would unprotect the PROT_NONE ranges if - * _PAGE_NUMA and _PAGE_PROTNONE are sharing the same pte/pmd - * bitflag. So to avoid that, don't set FOLL_NUMA if - * FOLL_FORCE is set. + * If FOLL_FORCE is set then do not force a full fault as the hinting + * fault information is unrelated to the reference behaviour of a task + * using the address space */ if (!(gup_flags & FOLL_FORCE)) gup_flags |= FOLL_NUMA; -- cgit v1.2.3-71-gd317 From 5dfb417509921eb90ee123a4d1525e8916b4ace4 Mon Sep 17 00:00:00 2001 From: Vladimir Davydov Date: Wed, 4 Jun 2014 16:06:38 -0700 Subject: sl[au]b: charge slabs to kmemcg explicitly We have only a few places where we actually want to charge kmem so instead of intruding into the general page allocation path with __GFP_KMEMCG it's better to explictly charge kmem there. All kmem charges will be easier to follow that way. This is a step towards removing __GFP_KMEMCG. It removes __GFP_KMEMCG from memcg caches' allocflags. Instead it makes slab allocation path call memcg_charge_kmem directly getting memcg to charge from the cache's memcg params. This also eliminates any possibility of misaccounting an allocation going from one memcg's cache to another memcg, because now we always charge slabs against the memcg the cache belongs to. That's why this patch removes the big comment to memcg_kmem_get_cache. Signed-off-by: Vladimir Davydov Acked-by: Greg Thelen Cc: Johannes Weiner Acked-by: Michal Hocko Cc: Glauber Costa Cc: Christoph Lameter Cc: Pekka Enberg Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/memcontrol.h | 15 ++++----------- mm/memcontrol.c | 4 ++-- mm/slab.c | 7 ++++++- mm/slab.h | 29 +++++++++++++++++++++++++++++ mm/slab_common.c | 6 +----- mm/slub.c | 24 +++++++++++++++++------- 6 files changed, 59 insertions(+), 26 deletions(-) (limited to 'include/linux') diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h index b569b8be5c5a..96e5d2573eb0 100644 --- a/include/linux/memcontrol.h +++ b/include/linux/memcontrol.h @@ -506,6 +506,9 @@ void memcg_update_array_size(int num_groups); struct kmem_cache * __memcg_kmem_get_cache(struct kmem_cache *cachep, gfp_t gfp); +int memcg_charge_kmem(struct mem_cgroup *memcg, gfp_t gfp, u64 size); +void memcg_uncharge_kmem(struct mem_cgroup *memcg, u64 size); + void mem_cgroup_destroy_cache(struct kmem_cache *cachep); int __kmem_cache_destroy_memcg_children(struct kmem_cache *s); @@ -583,17 +586,7 @@ memcg_kmem_commit_charge(struct page *page, struct mem_cgroup *memcg, int order) * @cachep: the original global kmem cache * @gfp: allocation flags. * - * This function assumes that the task allocating, which determines the memcg - * in the page allocator, belongs to the same cgroup throughout the whole - * process. Misacounting can happen if the task calls memcg_kmem_get_cache() - * while belonging to a cgroup, and later on changes. This is considered - * acceptable, and should only happen upon task migration. - * - * Before the cache is created by the memcg core, there is also a possible - * imbalance: the task belongs to a memcg, but the cache being allocated from - * is the global cache, since the child cache is not yet guaranteed to be - * ready. This case is also fine, since in this case the GFP_KMEMCG will not be - * passed and the page allocator will not attempt any cgroup accounting. + * All memory allocated from a per-memcg cache is charged to the owner memcg. */ static __always_inline struct kmem_cache * memcg_kmem_get_cache(struct kmem_cache *cachep, gfp_t gfp) diff --git a/mm/memcontrol.c b/mm/memcontrol.c index 5177c6d4a2dd..56a768b3d5a8 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -2953,7 +2953,7 @@ static int mem_cgroup_slabinfo_read(struct seq_file *m, void *v) } #endif -static int memcg_charge_kmem(struct mem_cgroup *memcg, gfp_t gfp, u64 size) +int memcg_charge_kmem(struct mem_cgroup *memcg, gfp_t gfp, u64 size) { struct res_counter *fail_res; int ret = 0; @@ -2991,7 +2991,7 @@ static int memcg_charge_kmem(struct mem_cgroup *memcg, gfp_t gfp, u64 size) return ret; } -static void memcg_uncharge_kmem(struct mem_cgroup *memcg, u64 size) +void memcg_uncharge_kmem(struct mem_cgroup *memcg, u64 size) { res_counter_uncharge(&memcg->res, size); if (do_swap_account) diff --git a/mm/slab.c b/mm/slab.c index 5c846d25c17d..944ac58cfcf8 100644 --- a/mm/slab.c +++ b/mm/slab.c @@ -1688,8 +1688,12 @@ static struct page *kmem_getpages(struct kmem_cache *cachep, gfp_t flags, if (cachep->flags & SLAB_RECLAIM_ACCOUNT) flags |= __GFP_RECLAIMABLE; + if (memcg_charge_slab(cachep, flags, cachep->gfporder)) + return NULL; + page = alloc_pages_exact_node(nodeid, flags | __GFP_NOTRACK, cachep->gfporder); if (!page) { + memcg_uncharge_slab(cachep, cachep->gfporder); slab_out_of_memory(cachep, flags, nodeid); return NULL; } @@ -1747,7 +1751,8 @@ static void kmem_freepages(struct kmem_cache *cachep, struct page *page) memcg_release_pages(cachep, cachep->gfporder); if (current->reclaim_state) current->reclaim_state->reclaimed_slab += nr_freed; - __free_memcg_kmem_pages(page, cachep->gfporder); + __free_pages(page, cachep->gfporder); + memcg_uncharge_slab(cachep, cachep->gfporder); } static void kmem_rcu_free(struct rcu_head *head) diff --git a/mm/slab.h b/mm/slab.h index 6bd4c353704f..863e67b8c8c9 100644 --- a/mm/slab.h +++ b/mm/slab.h @@ -192,6 +192,26 @@ static inline struct kmem_cache *memcg_root_cache(struct kmem_cache *s) return s; return s->memcg_params->root_cache; } + +static __always_inline int memcg_charge_slab(struct kmem_cache *s, + gfp_t gfp, int order) +{ + if (!memcg_kmem_enabled()) + return 0; + if (is_root_cache(s)) + return 0; + return memcg_charge_kmem(s->memcg_params->memcg, gfp, + PAGE_SIZE << order); +} + +static __always_inline void memcg_uncharge_slab(struct kmem_cache *s, int order) +{ + if (!memcg_kmem_enabled()) + return; + if (is_root_cache(s)) + return; + memcg_uncharge_kmem(s->memcg_params->memcg, PAGE_SIZE << order); +} #else static inline bool is_root_cache(struct kmem_cache *s) { @@ -227,6 +247,15 @@ static inline struct kmem_cache *memcg_root_cache(struct kmem_cache *s) { return s; } + +static inline int memcg_charge_slab(struct kmem_cache *s, gfp_t gfp, int order) +{ + return 0; +} + +static inline void memcg_uncharge_slab(struct kmem_cache *s, int order) +{ +} #endif static inline struct kmem_cache *cache_from_obj(struct kmem_cache *s, void *x) diff --git a/mm/slab_common.c b/mm/slab_common.c index 102cc6fca3d3..06f0c6125632 100644 --- a/mm/slab_common.c +++ b/mm/slab_common.c @@ -290,12 +290,8 @@ void kmem_cache_create_memcg(struct mem_cgroup *memcg, struct kmem_cache *root_c root_cache->size, root_cache->align, root_cache->flags, root_cache->ctor, memcg, root_cache); - if (IS_ERR(s)) { + if (IS_ERR(s)) kfree(cache_name); - goto out_unlock; - } - - s->allocflags |= __GFP_KMEMCG; out_unlock: mutex_unlock(&slab_mutex); diff --git a/mm/slub.c b/mm/slub.c index d05a5483106d..fc9831851be6 100644 --- a/mm/slub.c +++ b/mm/slub.c @@ -1312,17 +1312,26 @@ static inline void slab_free_hook(struct kmem_cache *s, void *x) /* * Slab allocation and freeing */ -static inline struct page *alloc_slab_page(gfp_t flags, int node, - struct kmem_cache_order_objects oo) +static inline struct page *alloc_slab_page(struct kmem_cache *s, + gfp_t flags, int node, struct kmem_cache_order_objects oo) { + struct page *page; int order = oo_order(oo); flags |= __GFP_NOTRACK; + if (memcg_charge_slab(s, flags, order)) + return NULL; + if (node == NUMA_NO_NODE) - return alloc_pages(flags, order); + page = alloc_pages(flags, order); else - return alloc_pages_exact_node(node, flags, order); + page = alloc_pages_exact_node(node, flags, order); + + if (!page) + memcg_uncharge_slab(s, order); + + return page; } static struct page *allocate_slab(struct kmem_cache *s, gfp_t flags, int node) @@ -1344,7 +1353,7 @@ static struct page *allocate_slab(struct kmem_cache *s, gfp_t flags, int node) */ alloc_gfp = (flags | __GFP_NOWARN | __GFP_NORETRY) & ~__GFP_NOFAIL; - page = alloc_slab_page(alloc_gfp, node, oo); + page = alloc_slab_page(s, alloc_gfp, node, oo); if (unlikely(!page)) { oo = s->min; alloc_gfp = flags; @@ -1352,7 +1361,7 @@ static struct page *allocate_slab(struct kmem_cache *s, gfp_t flags, int node) * Allocation may have failed due to fragmentation. * Try a lower order alloc if possible */ - page = alloc_slab_page(alloc_gfp, node, oo); + page = alloc_slab_page(s, alloc_gfp, node, oo); if (page) stat(s, ORDER_FALLBACK); @@ -1468,7 +1477,8 @@ static void __free_slab(struct kmem_cache *s, struct page *page) page_mapcount_reset(page); if (current->reclaim_state) current->reclaim_state->reclaimed_slab += pages; - __free_memcg_kmem_pages(page, order); + __free_pages(page, order); + memcg_uncharge_slab(s, order); } #define need_reserve_slab_rcu \ -- cgit v1.2.3-71-gd317 From 52383431b37cdbec63944e953ffc2698a7ad9722 Mon Sep 17 00:00:00 2001 From: Vladimir Davydov Date: Wed, 4 Jun 2014 16:06:39 -0700 Subject: mm: get rid of __GFP_KMEMCG Currently to allocate a page that should be charged to kmemcg (e.g. threadinfo), we pass __GFP_KMEMCG flag to the page allocator. The page allocated is then to be freed by free_memcg_kmem_pages. Apart from looking asymmetrical, this also requires intrusion to the general allocation path. So let's introduce separate functions that will alloc/free pages charged to kmemcg. The new functions are called alloc_kmem_pages and free_kmem_pages. They should be used when the caller actually would like to use kmalloc, but has to fall back to the page allocator for the allocation is large. They only differ from alloc_pages and free_pages in that besides allocating or freeing pages they also charge them to the kmem resource counter of the current memory cgroup. [sfr@canb.auug.org.au: export kmalloc_order() to modules] Signed-off-by: Vladimir Davydov Acked-by: Greg Thelen Cc: Johannes Weiner Acked-by: Michal Hocko Cc: Glauber Costa Cc: Christoph Lameter Cc: Pekka Enberg Signed-off-by: Stephen Rothwell Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/gfp.h | 10 +++++--- include/linux/memcontrol.h | 2 +- include/linux/slab.h | 11 +------- include/linux/thread_info.h | 2 -- include/trace/events/gfpflags.h | 1 - kernel/fork.c | 6 ++--- mm/memcontrol.c | 11 ++++---- mm/page_alloc.c | 56 +++++++++++++++++++++++++---------------- mm/slab_common.c | 13 ++++++++++ mm/slub.c | 6 ++--- 10 files changed, 68 insertions(+), 50 deletions(-) (limited to 'include/linux') diff --git a/include/linux/gfp.h b/include/linux/gfp.h index 39b81dc7d01a..d382db71e300 100644 --- a/include/linux/gfp.h +++ b/include/linux/gfp.h @@ -31,7 +31,6 @@ struct vm_area_struct; #define ___GFP_HARDWALL 0x20000u #define ___GFP_THISNODE 0x40000u #define ___GFP_RECLAIMABLE 0x80000u -#define ___GFP_KMEMCG 0x100000u #define ___GFP_NOTRACK 0x200000u #define ___GFP_NO_KSWAPD 0x400000u #define ___GFP_OTHER_NODE 0x800000u @@ -91,7 +90,6 @@ struct vm_area_struct; #define __GFP_NO_KSWAPD ((__force gfp_t)___GFP_NO_KSWAPD) #define __GFP_OTHER_NODE ((__force gfp_t)___GFP_OTHER_NODE) /* On behalf of other node */ -#define __GFP_KMEMCG ((__force gfp_t)___GFP_KMEMCG) /* Allocation comes from a memcg-accounted resource */ #define __GFP_WRITE ((__force gfp_t)___GFP_WRITE) /* Allocator intends to dirty page */ /* @@ -353,6 +351,10 @@ extern struct page *alloc_pages_vma(gfp_t gfp_mask, int order, #define alloc_page_vma_node(gfp_mask, vma, addr, node) \ alloc_pages_vma(gfp_mask, 0, vma, addr, node) +extern struct page *alloc_kmem_pages(gfp_t gfp_mask, unsigned int order); +extern struct page *alloc_kmem_pages_node(int nid, gfp_t gfp_mask, + unsigned int order); + extern unsigned long __get_free_pages(gfp_t gfp_mask, unsigned int order); extern unsigned long get_zeroed_page(gfp_t gfp_mask); @@ -372,8 +374,8 @@ extern void free_pages(unsigned long addr, unsigned int order); extern void free_hot_cold_page(struct page *page, int cold); extern void free_hot_cold_page_list(struct list_head *list, int cold); -extern void __free_memcg_kmem_pages(struct page *page, unsigned int order); -extern void free_memcg_kmem_pages(unsigned long addr, unsigned int order); +extern void __free_kmem_pages(struct page *page, unsigned int order); +extern void free_kmem_pages(unsigned long addr, unsigned int order); #define __free_page(page) __free_pages((page), 0) #define free_page(addr) free_pages((addr), 0) diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h index 96e5d2573eb0..5155d09e749d 100644 --- a/include/linux/memcontrol.h +++ b/include/linux/memcontrol.h @@ -537,7 +537,7 @@ memcg_kmem_newpage_charge(gfp_t gfp, struct mem_cgroup **memcg, int order) * res_counter_charge_nofail, but we hope those allocations are rare, * and won't be worth the trouble. */ - if (!(gfp & __GFP_KMEMCG) || (gfp & __GFP_NOFAIL)) + if (gfp & __GFP_NOFAIL) return true; if (in_interrupt() || (!current->mm) || (current->flags & PF_KTHREAD)) return true; diff --git a/include/linux/slab.h b/include/linux/slab.h index 307bfbe62387..a6aab2c0dfc5 100644 --- a/include/linux/slab.h +++ b/include/linux/slab.h @@ -369,16 +369,7 @@ kmem_cache_alloc_node_trace(struct kmem_cache *s, #include #endif -static __always_inline void * -kmalloc_order(size_t size, gfp_t flags, unsigned int order) -{ - void *ret; - - flags |= (__GFP_COMP | __GFP_KMEMCG); - ret = (void *) __get_free_pages(flags, order); - kmemleak_alloc(ret, size, 1, flags); - return ret; -} +extern void *kmalloc_order(size_t size, gfp_t flags, unsigned int order); #ifdef CONFIG_TRACING extern void *kmalloc_order_trace(size_t size, gfp_t flags, unsigned int order); diff --git a/include/linux/thread_info.h b/include/linux/thread_info.h index cb0cec94fda3..ff307b548ed3 100644 --- a/include/linux/thread_info.h +++ b/include/linux/thread_info.h @@ -61,8 +61,6 @@ extern long do_no_restart_syscall(struct restart_block *parm); # define THREADINFO_GFP (GFP_KERNEL | __GFP_NOTRACK) #endif -#define THREADINFO_GFP_ACCOUNTED (THREADINFO_GFP | __GFP_KMEMCG) - /* * flag set/clear/test wrappers * - pass TIF_xxxx constants to these functions diff --git a/include/trace/events/gfpflags.h b/include/trace/events/gfpflags.h index 1eddbf1557f2..d6fd8e5b14b7 100644 --- a/include/trace/events/gfpflags.h +++ b/include/trace/events/gfpflags.h @@ -34,7 +34,6 @@ {(unsigned long)__GFP_HARDWALL, "GFP_HARDWALL"}, \ {(unsigned long)__GFP_THISNODE, "GFP_THISNODE"}, \ {(unsigned long)__GFP_RECLAIMABLE, "GFP_RECLAIMABLE"}, \ - {(unsigned long)__GFP_KMEMCG, "GFP_KMEMCG"}, \ {(unsigned long)__GFP_MOVABLE, "GFP_MOVABLE"}, \ {(unsigned long)__GFP_NOTRACK, "GFP_NOTRACK"}, \ {(unsigned long)__GFP_NO_KSWAPD, "GFP_NO_KSWAPD"}, \ diff --git a/kernel/fork.c b/kernel/fork.c index 54a8d26f612f..59e3dcc5b8f2 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -150,15 +150,15 @@ void __weak arch_release_thread_info(struct thread_info *ti) static struct thread_info *alloc_thread_info_node(struct task_struct *tsk, int node) { - struct page *page = alloc_pages_node(node, THREADINFO_GFP_ACCOUNTED, - THREAD_SIZE_ORDER); + struct page *page = alloc_kmem_pages_node(node, THREADINFO_GFP, + THREAD_SIZE_ORDER); return page ? page_address(page) : NULL; } static inline void free_thread_info(struct thread_info *ti) { - free_memcg_kmem_pages((unsigned long)ti, THREAD_SIZE_ORDER); + free_kmem_pages((unsigned long)ti, THREAD_SIZE_ORDER); } # else static struct kmem_cache *thread_info_cache; diff --git a/mm/memcontrol.c b/mm/memcontrol.c index 56a768b3d5a8..7bab1de50f48 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -3540,11 +3540,12 @@ __memcg_kmem_newpage_charge(gfp_t gfp, struct mem_cgroup **_memcg, int order) /* * Disabling accounting is only relevant for some specific memcg * internal allocations. Therefore we would initially not have such - * check here, since direct calls to the page allocator that are marked - * with GFP_KMEMCG only happen outside memcg core. We are mostly - * concerned with cache allocations, and by having this test at - * memcg_kmem_get_cache, we are already able to relay the allocation to - * the root cache and bypass the memcg cache altogether. + * check here, since direct calls to the page allocator that are + * accounted to kmemcg (alloc_kmem_pages and friends) only happen + * outside memcg core. We are mostly concerned with cache allocations, + * and by having this test at memcg_kmem_get_cache, we are already able + * to relay the allocation to the root cache and bypass the memcg cache + * altogether. * * There is one exception, though: the SLUB allocator does not create * large order caches, but rather service large kmallocs directly from diff --git a/mm/page_alloc.c b/mm/page_alloc.c index 5dba2933c9c0..7cfdcd808f52 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -2697,7 +2697,6 @@ __alloc_pages_nodemask(gfp_t gfp_mask, unsigned int order, int migratetype = allocflags_to_migratetype(gfp_mask); unsigned int cpuset_mems_cookie; int alloc_flags = ALLOC_WMARK_LOW|ALLOC_CPUSET|ALLOC_FAIR; - struct mem_cgroup *memcg = NULL; gfp_mask &= gfp_allowed_mask; @@ -2716,13 +2715,6 @@ __alloc_pages_nodemask(gfp_t gfp_mask, unsigned int order, if (unlikely(!zonelist->_zonerefs->zone)) return NULL; - /* - * Will only have any effect when __GFP_KMEMCG is set. This is - * verified in the (always inline) callee - */ - if (!memcg_kmem_newpage_charge(gfp_mask, &memcg, order)) - return NULL; - retry_cpuset: cpuset_mems_cookie = read_mems_allowed_begin(); @@ -2782,8 +2774,6 @@ out: if (unlikely(!page && read_mems_allowed_retry(cpuset_mems_cookie))) goto retry_cpuset; - memcg_kmem_commit_charge(page, memcg, order); - return page; } EXPORT_SYMBOL(__alloc_pages_nodemask); @@ -2837,27 +2827,51 @@ void free_pages(unsigned long addr, unsigned int order) EXPORT_SYMBOL(free_pages); /* - * __free_memcg_kmem_pages and free_memcg_kmem_pages will free - * pages allocated with __GFP_KMEMCG. + * alloc_kmem_pages charges newly allocated pages to the kmem resource counter + * of the current memory cgroup. * - * Those pages are accounted to a particular memcg, embedded in the - * corresponding page_cgroup. To avoid adding a hit in the allocator to search - * for that information only to find out that it is NULL for users who have no - * interest in that whatsoever, we provide these functions. - * - * The caller knows better which flags it relies on. + * It should be used when the caller would like to use kmalloc, but since the + * allocation is large, it has to fall back to the page allocator. + */ +struct page *alloc_kmem_pages(gfp_t gfp_mask, unsigned int order) +{ + struct page *page; + struct mem_cgroup *memcg = NULL; + + if (!memcg_kmem_newpage_charge(gfp_mask, &memcg, order)) + return NULL; + page = alloc_pages(gfp_mask, order); + memcg_kmem_commit_charge(page, memcg, order); + return page; +} + +struct page *alloc_kmem_pages_node(int nid, gfp_t gfp_mask, unsigned int order) +{ + struct page *page; + struct mem_cgroup *memcg = NULL; + + if (!memcg_kmem_newpage_charge(gfp_mask, &memcg, order)) + return NULL; + page = alloc_pages_node(nid, gfp_mask, order); + memcg_kmem_commit_charge(page, memcg, order); + return page; +} + +/* + * __free_kmem_pages and free_kmem_pages will free pages allocated with + * alloc_kmem_pages. */ -void __free_memcg_kmem_pages(struct page *page, unsigned int order) +void __free_kmem_pages(struct page *page, unsigned int order) { memcg_kmem_uncharge_pages(page, order); __free_pages(page, order); } -void free_memcg_kmem_pages(unsigned long addr, unsigned int order) +void free_kmem_pages(unsigned long addr, unsigned int order) { if (addr != 0) { VM_BUG_ON(!virt_addr_valid((void *)addr)); - __free_memcg_kmem_pages(virt_to_page((void *)addr), order); + __free_kmem_pages(virt_to_page((void *)addr), order); } } diff --git a/mm/slab_common.c b/mm/slab_common.c index 06f0c6125632..1950c8f4d1a6 100644 --- a/mm/slab_common.c +++ b/mm/slab_common.c @@ -582,6 +582,19 @@ void __init create_kmalloc_caches(unsigned long flags) } #endif /* !CONFIG_SLOB */ +void *kmalloc_order(size_t size, gfp_t flags, unsigned int order) +{ + void *ret; + struct page *page; + + flags |= __GFP_COMP; + page = alloc_kmem_pages(flags, order); + ret = page ? page_address(page) : NULL; + kmemleak_alloc(ret, size, 1, flags); + return ret; +} +EXPORT_SYMBOL(kmalloc_order); + #ifdef CONFIG_TRACING void *kmalloc_order_trace(size_t size, gfp_t flags, unsigned int order) { diff --git a/mm/slub.c b/mm/slub.c index fc9831851be6..ddb60795f373 100644 --- a/mm/slub.c +++ b/mm/slub.c @@ -3311,8 +3311,8 @@ static void *kmalloc_large_node(size_t size, gfp_t flags, int node) struct page *page; void *ptr = NULL; - flags |= __GFP_COMP | __GFP_NOTRACK | __GFP_KMEMCG; - page = alloc_pages_node(node, flags, get_order(size)); + flags |= __GFP_COMP | __GFP_NOTRACK; + page = alloc_kmem_pages_node(node, flags, get_order(size)); if (page) ptr = page_address(page); @@ -3381,7 +3381,7 @@ void kfree(const void *x) if (unlikely(!PageSlab(page))) { BUG_ON(!PageCompound(page)); kfree_hook(x); - __free_memcg_kmem_pages(page, compound_order(page)); + __free_kmem_pages(page, compound_order(page)); return; } slab_free(page->slab_cache, page, object, _RET_IP_); -- cgit v1.2.3-71-gd317 From 4f115147ff802267d0aa41e361c5aa5bd933d896 Mon Sep 17 00:00:00 2001 From: Davidlohr Bueso Date: Wed, 4 Jun 2014 16:06:46 -0700 Subject: mm,vmacache: add debug data Introduce a CONFIG_DEBUG_VM_VMACACHE option to enable counting the cache hit rate -- exported in /proc/vmstat. Any updates to the caching scheme needs this kind of data, thus it can save some work re-implementing the counting all the time. Signed-off-by: Davidlohr Bueso Cc: Aswin Chandramouleeswaran Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/vm_event_item.h | 4 ++++ include/linux/vmstat.h | 6 ++++++ lib/Kconfig.debug | 10 ++++++++++ mm/vmacache.c | 12 ++++++++++-- mm/vmstat.c | 4 ++++ 5 files changed, 34 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/vm_event_item.h b/include/linux/vm_event_item.h index 486c3972c0be..ced92345c963 100644 --- a/include/linux/vm_event_item.h +++ b/include/linux/vm_event_item.h @@ -80,6 +80,10 @@ enum vm_event_item { PGPGIN, PGPGOUT, PSWPIN, PSWPOUT, NR_TLB_LOCAL_FLUSH_ALL, NR_TLB_LOCAL_FLUSH_ONE, #endif /* CONFIG_DEBUG_TLBFLUSH */ +#ifdef CONFIG_DEBUG_VM_VMACACHE + VMACACHE_FIND_CALLS, + VMACACHE_FIND_HITS, +#endif NR_VM_EVENT_ITEMS }; diff --git a/include/linux/vmstat.h b/include/linux/vmstat.h index 45c9cd1daf7a..82e7db7f7100 100644 --- a/include/linux/vmstat.h +++ b/include/linux/vmstat.h @@ -95,6 +95,12 @@ static inline void vm_events_fold_cpu(int cpu) #define count_vm_tlb_events(x, y) do { (void)(y); } while (0) #endif +#ifdef CONFIG_DEBUG_VM_VMACACHE +#define count_vm_vmacache_event(x) count_vm_event(x) +#else +#define count_vm_vmacache_event(x) do {} while (0) +#endif + #define __count_zone_vm_events(item, zone, delta) \ __count_vm_events(item##_NORMAL - ZONE_NORMAL + \ zone_idx(zone), delta) diff --git a/lib/Kconfig.debug b/lib/Kconfig.debug index 99c8bfee1b00..c2de65045a40 100644 --- a/lib/Kconfig.debug +++ b/lib/Kconfig.debug @@ -501,6 +501,16 @@ config DEBUG_VM If unsure, say N. +config DEBUG_VM_VMACACHE + bool "Debug VMA caching" + depends on DEBUG_VM + help + Enable this to turn on VMA caching debug information. Doing so + can cause significant overhead, so only enable it in non-production + environments. + + If unsure, say N. + config DEBUG_VM_RB bool "Debug VM red-black trees" depends on DEBUG_VM diff --git a/mm/vmacache.c b/mm/vmacache.c index 1037a3bab505..658ed3b3e38d 100644 --- a/mm/vmacache.c +++ b/mm/vmacache.c @@ -78,6 +78,8 @@ struct vm_area_struct *vmacache_find(struct mm_struct *mm, unsigned long addr) if (!vmacache_valid(mm)) return NULL; + count_vm_vmacache_event(VMACACHE_FIND_CALLS); + for (i = 0; i < VMACACHE_SIZE; i++) { struct vm_area_struct *vma = current->vmacache[i]; @@ -85,8 +87,10 @@ struct vm_area_struct *vmacache_find(struct mm_struct *mm, unsigned long addr) continue; if (WARN_ON_ONCE(vma->vm_mm != mm)) break; - if (vma->vm_start <= addr && vma->vm_end > addr) + if (vma->vm_start <= addr && vma->vm_end > addr) { + count_vm_vmacache_event(VMACACHE_FIND_HITS); return vma; + } } return NULL; @@ -102,11 +106,15 @@ struct vm_area_struct *vmacache_find_exact(struct mm_struct *mm, if (!vmacache_valid(mm)) return NULL; + count_vm_vmacache_event(VMACACHE_FIND_CALLS); + for (i = 0; i < VMACACHE_SIZE; i++) { struct vm_area_struct *vma = current->vmacache[i]; - if (vma && vma->vm_start == start && vma->vm_end == end) + if (vma && vma->vm_start == start && vma->vm_end == end) { + count_vm_vmacache_event(VMACACHE_FIND_HITS); return vma; + } } return NULL; diff --git a/mm/vmstat.c b/mm/vmstat.c index 302dd076b8bf..82ce17ce58c4 100644 --- a/mm/vmstat.c +++ b/mm/vmstat.c @@ -866,6 +866,10 @@ const char * const vmstat_text[] = { "nr_tlb_local_flush_one", #endif /* CONFIG_DEBUG_TLBFLUSH */ +#ifdef CONFIG_DEBUG_VM_VMACACHE + "vmacache_find_calls", + "vmacache_find_hits", +#endif #endif /* CONFIG_VM_EVENTS_COUNTERS */ }; #endif /* CONFIG_PROC_FS || CONFIG_SYSFS || CONFIG_NUMA */ -- cgit v1.2.3-71-gd317 From 9c5a3621427da68afe6a078cadf807d2c8cc1d12 Mon Sep 17 00:00:00 2001 From: Akinobu Mita Date: Wed, 4 Jun 2014 16:06:50 -0700 Subject: x86: enable DMA CMA with swiotlb The DMA Contiguous Memory Allocator support on x86 is disabled when swiotlb config option is enabled. So DMA CMA is always disabled on x86_64 because swiotlb is always enabled. This attempts to support for DMA CMA with enabling swiotlb config option. The contiguous memory allocator on x86 is integrated in the function dma_generic_alloc_coherent() which is .alloc callback in nommu_dma_ops for dma_alloc_coherent(). x86_swiotlb_alloc_coherent() which is .alloc callback in swiotlb_dma_ops tries to allocate with dma_generic_alloc_coherent() firstly and then swiotlb_alloc_coherent() is called as a fallback. The main part of supporting DMA CMA with swiotlb is that changing x86_swiotlb_free_coherent() which is .free callback in swiotlb_dma_ops for dma_free_coherent() so that it can distinguish memory allocated by dma_generic_alloc_coherent() from one allocated by swiotlb_alloc_coherent() and release it with dma_generic_free_coherent() which can handle contiguous memory. This change requires making is_swiotlb_buffer() global function. This also needs to change .free callback in the dma_map_ops for amd_gart and sta2x11, because these dma_ops are also using dma_generic_alloc_coherent(). Signed-off-by: Akinobu Mita Acked-by: Marek Szyprowski Acked-by: Konrad Rzeszutek Wilk Cc: David Woodhouse Cc: Don Dutile Cc: Thomas Gleixner Cc: Ingo Molnar Cc: "H. Peter Anvin" Cc: Andi Kleen Cc: Yinghai Lu Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- arch/x86/Kconfig | 2 +- arch/x86/include/asm/swiotlb.h | 7 +++++++ arch/x86/kernel/amd_gart_64.c | 2 +- arch/x86/kernel/pci-swiotlb.c | 9 ++++++--- arch/x86/pci/sta2x11-fixup.c | 6 ++---- include/linux/swiotlb.h | 2 ++ lib/swiotlb.c | 2 +- 7 files changed, 20 insertions(+), 10 deletions(-) (limited to 'include/linux') diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index 896a411a4584..4a0137f6f032 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -41,7 +41,7 @@ config X86 select ARCH_WANT_OPTIONAL_GPIOLIB select ARCH_WANT_FRAME_POINTERS select HAVE_DMA_ATTRS - select HAVE_DMA_CONTIGUOUS if !SWIOTLB + select HAVE_DMA_CONTIGUOUS select HAVE_KRETPROBES select GENERIC_EARLY_IOREMAP select HAVE_OPTPROBES diff --git a/arch/x86/include/asm/swiotlb.h b/arch/x86/include/asm/swiotlb.h index 977f1761a25d..ab05d73e2bb7 100644 --- a/arch/x86/include/asm/swiotlb.h +++ b/arch/x86/include/asm/swiotlb.h @@ -29,4 +29,11 @@ static inline void pci_swiotlb_late_init(void) static inline void dma_mark_clean(void *addr, size_t size) {} +extern void *x86_swiotlb_alloc_coherent(struct device *hwdev, size_t size, + dma_addr_t *dma_handle, gfp_t flags, + struct dma_attrs *attrs); +extern void x86_swiotlb_free_coherent(struct device *dev, size_t size, + void *vaddr, dma_addr_t dma_addr, + struct dma_attrs *attrs); + #endif /* _ASM_X86_SWIOTLB_H */ diff --git a/arch/x86/kernel/amd_gart_64.c b/arch/x86/kernel/amd_gart_64.c index b574b295a2f9..8e3842fc8bea 100644 --- a/arch/x86/kernel/amd_gart_64.c +++ b/arch/x86/kernel/amd_gart_64.c @@ -512,7 +512,7 @@ gart_free_coherent(struct device *dev, size_t size, void *vaddr, dma_addr_t dma_addr, struct dma_attrs *attrs) { gart_unmap_page(dev, dma_addr, size, DMA_BIDIRECTIONAL, NULL); - free_pages((unsigned long)vaddr, get_order(size)); + dma_generic_free_coherent(dev, size, vaddr, dma_addr, attrs); } static int gart_mapping_error(struct device *dev, dma_addr_t dma_addr) diff --git a/arch/x86/kernel/pci-swiotlb.c b/arch/x86/kernel/pci-swiotlb.c index 6c483ba98b9c..77dd0ad58be4 100644 --- a/arch/x86/kernel/pci-swiotlb.c +++ b/arch/x86/kernel/pci-swiotlb.c @@ -14,7 +14,7 @@ #include int swiotlb __read_mostly; -static void *x86_swiotlb_alloc_coherent(struct device *hwdev, size_t size, +void *x86_swiotlb_alloc_coherent(struct device *hwdev, size_t size, dma_addr_t *dma_handle, gfp_t flags, struct dma_attrs *attrs) { @@ -28,11 +28,14 @@ static void *x86_swiotlb_alloc_coherent(struct device *hwdev, size_t size, return swiotlb_alloc_coherent(hwdev, size, dma_handle, flags); } -static void x86_swiotlb_free_coherent(struct device *dev, size_t size, +void x86_swiotlb_free_coherent(struct device *dev, size_t size, void *vaddr, dma_addr_t dma_addr, struct dma_attrs *attrs) { - swiotlb_free_coherent(dev, size, vaddr, dma_addr); + if (is_swiotlb_buffer(dma_to_phys(dev, dma_addr))) + swiotlb_free_coherent(dev, size, vaddr, dma_addr); + else + dma_generic_free_coherent(dev, size, vaddr, dma_addr, attrs); } static struct dma_map_ops swiotlb_dma_ops = { diff --git a/arch/x86/pci/sta2x11-fixup.c b/arch/x86/pci/sta2x11-fixup.c index 9d8a509c9730..5ceda85b8687 100644 --- a/arch/x86/pci/sta2x11-fixup.c +++ b/arch/x86/pci/sta2x11-fixup.c @@ -173,9 +173,7 @@ static void *sta2x11_swiotlb_alloc_coherent(struct device *dev, { void *vaddr; - vaddr = dma_generic_alloc_coherent(dev, size, dma_handle, flags, attrs); - if (!vaddr) - vaddr = swiotlb_alloc_coherent(dev, size, dma_handle, flags); + vaddr = x86_swiotlb_alloc_coherent(dev, size, dma_handle, flags, attrs); *dma_handle = p2a(*dma_handle, to_pci_dev(dev)); return vaddr; } @@ -183,7 +181,7 @@ static void *sta2x11_swiotlb_alloc_coherent(struct device *dev, /* We have our own dma_ops: the same as swiotlb but from alloc (above) */ static struct dma_map_ops sta2x11_dma_ops = { .alloc = sta2x11_swiotlb_alloc_coherent, - .free = swiotlb_free_coherent, + .free = x86_swiotlb_free_coherent, .map_page = swiotlb_map_page, .unmap_page = swiotlb_unmap_page, .map_sg = swiotlb_map_sg_attrs, diff --git a/include/linux/swiotlb.h b/include/linux/swiotlb.h index a5ffd32642fd..e7a018eaf3a2 100644 --- a/include/linux/swiotlb.h +++ b/include/linux/swiotlb.h @@ -116,4 +116,6 @@ static inline void swiotlb_free(void) { } #endif extern void swiotlb_print_info(void); +extern int is_swiotlb_buffer(phys_addr_t paddr); + #endif /* __LINUX_SWIOTLB_H */ diff --git a/lib/swiotlb.c b/lib/swiotlb.c index b604b831f4d1..649d097853a1 100644 --- a/lib/swiotlb.c +++ b/lib/swiotlb.c @@ -374,7 +374,7 @@ void __init swiotlb_free(void) io_tlb_nslabs = 0; } -static int is_swiotlb_buffer(phys_addr_t paddr) +int is_swiotlb_buffer(phys_addr_t paddr) { return paddr >= io_tlb_start && paddr < io_tlb_end; } -- cgit v1.2.3-71-gd317 From 2bfc2862c4fe38379a2fb2cfba33fad32ccb4ff4 Mon Sep 17 00:00:00 2001 From: Akinobu Mita Date: Wed, 4 Jun 2014 16:06:53 -0700 Subject: memblock: introduce memblock_alloc_range() This introduces memblock_alloc_range() which allocates memblock from the specified range of physical address. I would like to use this function to specify the location of CMA. Signed-off-by: Akinobu Mita Cc: Marek Szyprowski Cc: Konrad Rzeszutek Wilk Cc: David Woodhouse Cc: Don Dutile Cc: Thomas Gleixner Cc: Ingo Molnar Cc: "H. Peter Anvin" Cc: Andi Kleen Cc: Yinghai Lu Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/memblock.h | 2 ++ mm/memblock.c | 21 +++++++++++++++++---- 2 files changed, 19 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/memblock.h b/include/linux/memblock.h index 73dc382e72d8..b660e05b63d4 100644 --- a/include/linux/memblock.h +++ b/include/linux/memblock.h @@ -272,6 +272,8 @@ static inline bool memblock_bottom_up(void) { return false; } #define MEMBLOCK_ALLOC_ANYWHERE (~(phys_addr_t)0) #define MEMBLOCK_ALLOC_ACCESSIBLE 0 +phys_addr_t __init memblock_alloc_range(phys_addr_t size, phys_addr_t align, + phys_addr_t start, phys_addr_t end); phys_addr_t memblock_alloc_base(phys_addr_t size, phys_addr_t align, phys_addr_t max_addr); phys_addr_t __memblock_alloc_base(phys_addr_t size, phys_addr_t align, diff --git a/mm/memblock.c b/mm/memblock.c index a810ba923cdd..146736411318 100644 --- a/mm/memblock.c +++ b/mm/memblock.c @@ -1033,22 +1033,35 @@ int __init_memblock memblock_set_node(phys_addr_t base, phys_addr_t size, } #endif /* CONFIG_HAVE_MEMBLOCK_NODE_MAP */ -static phys_addr_t __init memblock_alloc_base_nid(phys_addr_t size, - phys_addr_t align, phys_addr_t max_addr, - int nid) +static phys_addr_t __init memblock_alloc_range_nid(phys_addr_t size, + phys_addr_t align, phys_addr_t start, + phys_addr_t end, int nid) { phys_addr_t found; if (!align) align = SMP_CACHE_BYTES; - found = memblock_find_in_range_node(size, align, 0, max_addr, nid); + found = memblock_find_in_range_node(size, align, start, end, nid); if (found && !memblock_reserve(found, size)) return found; return 0; } +phys_addr_t __init memblock_alloc_range(phys_addr_t size, phys_addr_t align, + phys_addr_t start, phys_addr_t end) +{ + return memblock_alloc_range_nid(size, align, start, end, NUMA_NO_NODE); +} + +static phys_addr_t __init memblock_alloc_base_nid(phys_addr_t size, + phys_addr_t align, phys_addr_t max_addr, + int nid) +{ + return memblock_alloc_range_nid(size, align, 0, max_addr, nid); +} + phys_addr_t __init memblock_alloc_nid(phys_addr_t size, phys_addr_t align, int nid) { return memblock_alloc_base_nid(size, align, MEMBLOCK_ALLOC_ACCESSIBLE, nid); -- cgit v1.2.3-71-gd317 From 5ea3b1b2f8ad9162684431ce6188102ca4c64b7a Mon Sep 17 00:00:00 2001 From: Akinobu Mita Date: Wed, 4 Jun 2014 16:06:54 -0700 Subject: cma: add placement specifier for "cma=" kernel parameter Currently, "cma=" kernel parameter is used to specify the size of CMA, but we can't specify where it is located. We want to locate CMA below 4GB for devices only supporting 32-bit addressing on 64-bit systems without iommu. This enables to specify the placement of CMA by extending "cma=" kernel parameter. Examples: 1. locate 64MB CMA below 4GB by "cma=64M@0-4G" 2. locate 64MB CMA exact at 512MB by "cma=64M@512M" Note that the DMA contiguous memory allocator on x86 assumes that page_address() works for the pages to allocate. So this change requires to limit end address of contiguous memory area upto max_pfn_mapped to prevent from locating it on highmem area by the argument of dma_contiguous_reserve(). Signed-off-by: Akinobu Mita Cc: Marek Szyprowski Cc: Konrad Rzeszutek Wilk Cc: David Woodhouse Cc: Don Dutile Cc: Thomas Gleixner Cc: Ingo Molnar Cc: "H. Peter Anvin" Cc: Andi Kleen Cc: Yinghai Lu Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- Documentation/kernel-parameters.txt | 7 +++++-- arch/x86/kernel/setup.c | 2 +- drivers/base/dma-contiguous.c | 42 ++++++++++++++++++++++++++++--------- include/linux/dma-contiguous.h | 9 +++++--- 4 files changed, 44 insertions(+), 16 deletions(-) (limited to 'include/linux') diff --git a/Documentation/kernel-parameters.txt b/Documentation/kernel-parameters.txt index af55e13ace8f..adea3a22fa00 100644 --- a/Documentation/kernel-parameters.txt +++ b/Documentation/kernel-parameters.txt @@ -630,8 +630,11 @@ bytes respectively. Such letter suffixes can also be entirely omitted. Also note the kernel might malfunction if you disable some critical bits. - cma=nn[MG] [ARM,KNL] - Sets the size of kernel global memory area for contiguous + cma=nn[MG]@[start[MG][-end[MG]]] + [ARM,X86,KNL] + Sets the size of kernel global memory area for + contiguous memory allocations and optionally the + placement constraint by the physical address range of memory allocations. For more information, see include/linux/dma-contiguous.h diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c index 09c76d265550..78a0e6298922 100644 --- a/arch/x86/kernel/setup.c +++ b/arch/x86/kernel/setup.c @@ -1119,7 +1119,7 @@ void __init setup_arch(char **cmdline_p) setup_real_mode(); memblock_set_current_limit(get_max_mapped()); - dma_contiguous_reserve(0); + dma_contiguous_reserve(max_pfn_mapped << PAGE_SHIFT); /* * NOTE: On x86-32, only from this point on, fixmaps are ready for use. diff --git a/drivers/base/dma-contiguous.c b/drivers/base/dma-contiguous.c index c34ec3364243..83969f8c5727 100644 --- a/drivers/base/dma-contiguous.c +++ b/drivers/base/dma-contiguous.c @@ -60,11 +60,22 @@ struct cma *dma_contiguous_default_area; */ static const phys_addr_t size_bytes = CMA_SIZE_MBYTES * SZ_1M; static phys_addr_t size_cmdline = -1; +static phys_addr_t base_cmdline; +static phys_addr_t limit_cmdline; static int __init early_cma(char *p) { pr_debug("%s(%s)\n", __func__, p); size_cmdline = memparse(p, &p); + if (*p != '@') + return 0; + base_cmdline = memparse(p + 1, &p); + if (*p != '-') { + limit_cmdline = base_cmdline + size_cmdline; + return 0; + } + limit_cmdline = memparse(p + 1, &p); + return 0; } early_param("cma", early_cma); @@ -108,11 +119,18 @@ static inline __maybe_unused phys_addr_t cma_early_percent_memory(void) void __init dma_contiguous_reserve(phys_addr_t limit) { phys_addr_t selected_size = 0; + phys_addr_t selected_base = 0; + phys_addr_t selected_limit = limit; + bool fixed = false; pr_debug("%s(limit %08lx)\n", __func__, (unsigned long)limit); if (size_cmdline != -1) { selected_size = size_cmdline; + selected_base = base_cmdline; + selected_limit = min_not_zero(limit_cmdline, limit); + if (base_cmdline + size_cmdline == limit_cmdline) + fixed = true; } else { #ifdef CONFIG_CMA_SIZE_SEL_MBYTES selected_size = size_bytes; @@ -129,10 +147,12 @@ void __init dma_contiguous_reserve(phys_addr_t limit) pr_debug("%s: reserving %ld MiB for global area\n", __func__, (unsigned long)selected_size / SZ_1M); - dma_contiguous_reserve_area(selected_size, 0, limit, - &dma_contiguous_default_area); + dma_contiguous_reserve_area(selected_size, selected_base, + selected_limit, + &dma_contiguous_default_area, + fixed); } -}; +} static DEFINE_MUTEX(cma_mutex); @@ -189,15 +209,20 @@ core_initcall(cma_init_reserved_areas); * @base: Base address of the reserved area optional, use 0 for any * @limit: End address of the reserved memory (optional, 0 for any). * @res_cma: Pointer to store the created cma region. + * @fixed: hint about where to place the reserved area * * This function reserves memory from early allocator. It should be * called by arch specific code once the early allocator (memblock or bootmem) * has been activated and all other subsystems have already allocated/reserved * memory. This function allows to create custom reserved areas for specific * devices. + * + * If @fixed is true, reserve contiguous area at exactly @base. If false, + * reserve in range from @base to @limit. */ int __init dma_contiguous_reserve_area(phys_addr_t size, phys_addr_t base, - phys_addr_t limit, struct cma **res_cma) + phys_addr_t limit, struct cma **res_cma, + bool fixed) { struct cma *cma = &cma_areas[cma_area_count]; phys_addr_t alignment; @@ -223,18 +248,15 @@ int __init dma_contiguous_reserve_area(phys_addr_t size, phys_addr_t base, limit &= ~(alignment - 1); /* Reserve memory */ - if (base) { + if (base && fixed) { if (memblock_is_region_reserved(base, size) || memblock_reserve(base, size) < 0) { ret = -EBUSY; goto err; } } else { - /* - * Use __memblock_alloc_base() since - * memblock_alloc_base() panic()s. - */ - phys_addr_t addr = __memblock_alloc_base(size, alignment, limit); + phys_addr_t addr = memblock_alloc_range(size, alignment, base, + limit); if (!addr) { ret = -ENOMEM; goto err; diff --git a/include/linux/dma-contiguous.h b/include/linux/dma-contiguous.h index 3b28f937d959..772eab5d524a 100644 --- a/include/linux/dma-contiguous.h +++ b/include/linux/dma-contiguous.h @@ -88,7 +88,8 @@ static inline void dma_contiguous_set_default(struct cma *cma) void dma_contiguous_reserve(phys_addr_t addr_limit); int __init dma_contiguous_reserve_area(phys_addr_t size, phys_addr_t base, - phys_addr_t limit, struct cma **res_cma); + phys_addr_t limit, struct cma **res_cma, + bool fixed); /** * dma_declare_contiguous() - reserve area for contiguous memory handling @@ -108,7 +109,7 @@ static inline int dma_declare_contiguous(struct device *dev, phys_addr_t size, { struct cma *cma; int ret; - ret = dma_contiguous_reserve_area(size, base, limit, &cma); + ret = dma_contiguous_reserve_area(size, base, limit, &cma, true); if (ret == 0) dev_set_cma_area(dev, cma); @@ -136,7 +137,9 @@ static inline void dma_contiguous_set_default(struct cma *cma) { } static inline void dma_contiguous_reserve(phys_addr_t limit) { } static inline int dma_contiguous_reserve_area(phys_addr_t size, phys_addr_t base, - phys_addr_t limit, struct cma **res_cma) { + phys_addr_t limit, struct cma **res_cma, + bool fixed) +{ return -ENOSYS; } -- cgit v1.2.3-71-gd317 From 02a8efeda894d3541c7143ed818b25b299504190 Mon Sep 17 00:00:00 2001 From: Andrew Morton Date: Wed, 4 Jun 2014 16:06:59 -0700 Subject: include/linux/mmdebug.h: add VM_WARN_ON() and VM_WARN_ON_ONCE() WARN_ON() and WARN_ON_ONCE(), dependent on CONFIG_DEBUG_VM Cc: Sebastian Ott Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mmdebug.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mmdebug.h b/include/linux/mmdebug.h index 2d57efa64cc1..a3499d7b0e8a 100644 --- a/include/linux/mmdebug.h +++ b/include/linux/mmdebug.h @@ -11,9 +11,13 @@ extern void dump_page_badflags(struct page *page, const char *reason, #define VM_BUG_ON(cond) BUG_ON(cond) #define VM_BUG_ON_PAGE(cond, page) \ do { if (unlikely(cond)) { dump_page(page, NULL); BUG(); } } while (0) +#define VM_WARN_ON(cond) WARN_ON(cond) +#define VM_WARN_ON_ONCE(cond) WARN_ON_ONCE(cond) #else #define VM_BUG_ON(cond) BUILD_BUG_ON_INVALID(cond) #define VM_BUG_ON_PAGE(cond, page) VM_BUG_ON(cond) +#define VM_WARN_ON(cond) BUILD_BUG_ON_INVALID(cond) +#define VM_WARN_ON_ONCE(cond) BUILD_BUG_ON_INVALID(cond) #endif #ifdef CONFIG_DEBUG_VIRTUAL -- cgit v1.2.3-71-gd317 From e4f674229ce63dac60be0c4ddfb5ef8d1225d30d Mon Sep 17 00:00:00 2001 From: Dave Hansen Date: Wed, 4 Jun 2014 16:07:02 -0700 Subject: mm: pass VM_BUG_ON() reason to dump_page() I recently added a patch to let folks pass a "reason" string dump_page() which gets dumped out along with the page's data. This essentially saves the bug-reader a trip in to the source to figure out why we BUG_ON()'d. The new VM_BUG_ON_PAGE() passes in NULL for "reason". It seems like we might as well pass the BUG_ON() condition if we have it. This will bloat kernels a bit with ~160 new strings, but this is all under a debugging option anyway. page:ffffea0008560280 count:1 mapcount:0 mapping:(null) index:0x0 page flags: 0xbfffc0000000001(locked) page dumped because: VM_BUG_ON_PAGE(PageLocked(page)) ------------[ cut here ]------------ kernel BUG at /home/davehans/linux.git/mm/filemap.c:464! invalid opcode: 0000 [#1] SMP CPU: 0 PID: 1 Comm: swapper/0 Not tainted 3.14.0+ #251 Hardware name: Bochs Bochs, BIOS Bochs 01/01/2011 ... [akpm@linux-foundation.org: include stringify.h] Signed-off-by: Dave Hansen Acked-by: Kirill A. Shutemov Acked-by: Davidlohr Bueso Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mmdebug.h | 11 +++++++++-- 1 file changed, 9 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mmdebug.h b/include/linux/mmdebug.h index a3499d7b0e8a..edd82a105220 100644 --- a/include/linux/mmdebug.h +++ b/include/linux/mmdebug.h @@ -1,6 +1,8 @@ #ifndef LINUX_MM_DEBUG_H #define LINUX_MM_DEBUG_H 1 +#include + struct page; extern void dump_page(struct page *page, const char *reason); @@ -9,8 +11,13 @@ extern void dump_page_badflags(struct page *page, const char *reason, #ifdef CONFIG_DEBUG_VM #define VM_BUG_ON(cond) BUG_ON(cond) -#define VM_BUG_ON_PAGE(cond, page) \ - do { if (unlikely(cond)) { dump_page(page, NULL); BUG(); } } while (0) +#define VM_BUG_ON_PAGE(cond, page) \ + do { \ + if (unlikely(cond)) { \ + dump_page(page, "VM_BUG_ON_PAGE(" __stringify(cond)")");\ + BUG(); \ + } \ + } while (0) #define VM_WARN_ON(cond) WARN_ON(cond) #define VM_WARN_ON_ONCE(cond) WARN_ON_ONCE(cond) #else -- cgit v1.2.3-71-gd317 From bae7f4ae14d47008a11b4358b167cb0ae186c06a Mon Sep 17 00:00:00 2001 From: Luiz Capitulino Date: Wed, 4 Jun 2014 16:07:08 -0700 Subject: hugetlb: add hstate_is_gigantic() Signed-off-by: Luiz Capitulino Reviewed-by: Andrea Arcangeli Reviewed-by: Naoya Horiguchi Reviewed-by: Yasuaki Ishimatsu Reviewed-by: Davidlohr Bueso Acked-by: Kirill A. Shutemov Reviewed-by: Zhang Yanfei Cc: David Rientjes Cc: Marcelo Tosatti Cc: Rik van Riel Cc: Yinghai Lu Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/hugetlb.h | 5 +++++ mm/hugetlb.c | 28 ++++++++++++++-------------- 2 files changed, 19 insertions(+), 14 deletions(-) (limited to 'include/linux') diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h index d0bad1a8b0bd..35786ee36f06 100644 --- a/include/linux/hugetlb.h +++ b/include/linux/hugetlb.h @@ -343,6 +343,11 @@ static inline unsigned huge_page_shift(struct hstate *h) return h->order + PAGE_SHIFT; } +static inline bool hstate_is_gigantic(struct hstate *h) +{ + return huge_page_order(h) >= MAX_ORDER; +} + static inline unsigned int pages_per_huge_page(struct hstate *h) { return 1 << h->order; diff --git a/mm/hugetlb.c b/mm/hugetlb.c index 5d54d4b8df01..a66310586894 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -611,7 +611,7 @@ static void update_and_free_page(struct hstate *h, struct page *page) { int i; - VM_BUG_ON(h->order >= MAX_ORDER); + VM_BUG_ON(hstate_is_gigantic(h)); h->nr_huge_pages--; h->nr_huge_pages_node[page_to_nid(page)]--; @@ -664,7 +664,7 @@ static void free_huge_page(struct page *page) if (restore_reserve) h->resv_huge_pages++; - if (h->surplus_huge_pages_node[nid] && huge_page_order(h) < MAX_ORDER) { + if (h->surplus_huge_pages_node[nid] && !hstate_is_gigantic(h)) { /* remove the page from active list */ list_del(&page->lru); update_and_free_page(h, page); @@ -768,7 +768,7 @@ static struct page *alloc_fresh_huge_page_node(struct hstate *h, int nid) { struct page *page; - if (h->order >= MAX_ORDER) + if (hstate_is_gigantic(h)) return NULL; page = alloc_pages_exact_node(nid, @@ -962,7 +962,7 @@ static struct page *alloc_buddy_huge_page(struct hstate *h, int nid) struct page *page; unsigned int r_nid; - if (h->order >= MAX_ORDER) + if (hstate_is_gigantic(h)) return NULL; /* @@ -1155,7 +1155,7 @@ static void return_unused_surplus_pages(struct hstate *h, h->resv_huge_pages -= unused_resv_pages; /* Cannot return gigantic pages currently */ - if (h->order >= MAX_ORDER) + if (hstate_is_gigantic(h)) return; nr_pages = min(unused_resv_pages, h->surplus_huge_pages); @@ -1355,7 +1355,7 @@ static void __init gather_bootmem_prealloc(void) * fix confusing memory reports from free(1) and another * side-effects, like CommitLimit going negative. */ - if (h->order > (MAX_ORDER - 1)) + if (hstate_is_gigantic(h)) adjust_managed_page_count(page, 1 << h->order); } } @@ -1365,7 +1365,7 @@ static void __init hugetlb_hstate_alloc_pages(struct hstate *h) unsigned long i; for (i = 0; i < h->max_huge_pages; ++i) { - if (h->order >= MAX_ORDER) { + if (hstate_is_gigantic(h)) { if (!alloc_bootmem_huge_page(h)) break; } else if (!alloc_fresh_huge_page(h, @@ -1381,7 +1381,7 @@ static void __init hugetlb_init_hstates(void) for_each_hstate(h) { /* oversize hugepages were init'ed in early boot */ - if (h->order < MAX_ORDER) + if (!hstate_is_gigantic(h)) hugetlb_hstate_alloc_pages(h); } } @@ -1415,7 +1415,7 @@ static void try_to_free_low(struct hstate *h, unsigned long count, { int i; - if (h->order >= MAX_ORDER) + if (hstate_is_gigantic(h)) return; for_each_node_mask(i, *nodes_allowed) { @@ -1478,7 +1478,7 @@ static unsigned long set_max_huge_pages(struct hstate *h, unsigned long count, { unsigned long min_count, ret; - if (h->order >= MAX_ORDER) + if (hstate_is_gigantic(h)) return h->max_huge_pages; /* @@ -1605,7 +1605,7 @@ static ssize_t nr_hugepages_store_common(bool obey_mempolicy, goto out; h = kobj_to_hstate(kobj, &nid); - if (h->order >= MAX_ORDER) { + if (hstate_is_gigantic(h)) { err = -EINVAL; goto out; } @@ -1688,7 +1688,7 @@ static ssize_t nr_overcommit_hugepages_store(struct kobject *kobj, unsigned long input; struct hstate *h = kobj_to_hstate(kobj, NULL); - if (h->order >= MAX_ORDER) + if (hstate_is_gigantic(h)) return -EINVAL; err = kstrtoul(buf, 10, &input); @@ -2112,7 +2112,7 @@ static int hugetlb_sysctl_handler_common(bool obey_mempolicy, tmp = h->max_huge_pages; - if (write && h->order >= MAX_ORDER) + if (write && hstate_is_gigantic(h)) return -EINVAL; table->data = &tmp; @@ -2168,7 +2168,7 @@ int hugetlb_overcommit_handler(struct ctl_table *table, int write, tmp = h->nr_overcommit_huge_pages; - if (write && h->order >= MAX_ORDER) + if (write && hstate_is_gigantic(h)) return -EINVAL; table->data = &tmp; -- cgit v1.2.3-71-gd317 From 4f9b16a64753d0bb607454347036dc997fd03b82 Mon Sep 17 00:00:00 2001 From: Mel Gorman Date: Wed, 4 Jun 2014 16:07:14 -0700 Subject: mm: disable zone_reclaim_mode by default When it was introduced, zone_reclaim_mode made sense as NUMA distances punished and workloads were generally partitioned to fit into a NUMA node. NUMA machines are now common but few of the workloads are NUMA-aware and it's routine to see major performance degradation due to zone_reclaim_mode being enabled but relatively few can identify the problem. Those that require zone_reclaim_mode are likely to be able to detect when it needs to be enabled and tune appropriately so lets have a sensible default for the bulk of users. This patch (of 2): zone_reclaim_mode causes processes to prefer reclaiming memory from local node instead of spilling over to other nodes. This made sense initially when NUMA machines were almost exclusively HPC and the workload was partitioned into nodes. The NUMA penalties were sufficiently high to justify reclaiming the memory. On current machines and workloads it is often the case that zone_reclaim_mode destroys performance but not all users know how to detect this. Favour the common case and disable it by default. Users that are sophisticated enough to know they need zone_reclaim_mode will detect it. Signed-off-by: Mel Gorman Acked-by: Johannes Weiner Reviewed-by: Zhang Yanfei Acked-by: Michal Hocko Reviewed-by: Christoph Lameter Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- Documentation/sysctl/vm.txt | 17 +++++++++-------- arch/ia64/include/asm/topology.h | 3 ++- arch/powerpc/include/asm/topology.h | 8 ++------ include/linux/topology.h | 3 ++- mm/page_alloc.c | 2 -- 5 files changed, 15 insertions(+), 18 deletions(-) (limited to 'include/linux') diff --git a/Documentation/sysctl/vm.txt b/Documentation/sysctl/vm.txt index dd9d0e33b443..5b6da0fb5fbf 100644 --- a/Documentation/sysctl/vm.txt +++ b/Documentation/sysctl/vm.txt @@ -772,16 +772,17 @@ This is value ORed together of 2 = Zone reclaim writes dirty pages out 4 = Zone reclaim swaps pages -zone_reclaim_mode is set during bootup to 1 if it is determined that pages -from remote zones will cause a measurable performance reduction. The -page allocator will then reclaim easily reusable pages (those page -cache pages that are currently not used) before allocating off node pages. - -It may be beneficial to switch off zone reclaim if the system is -used for a file server and all of memory should be used for caching files -from disk. In that case the caching effect is more important than +zone_reclaim_mode is disabled by default. For file servers or workloads +that benefit from having their data cached, zone_reclaim_mode should be +left disabled as the caching effect is likely to be more important than data locality. +zone_reclaim may be enabled if it's known that the workload is partitioned +such that each partition fits within a NUMA node and that accessing remote +memory would cause a measurable performance reduction. The page allocator +will then reclaim easily reusable pages (those page cache pages that are +currently not used) before allocating off node pages. + Allowing zone reclaim to write out pages stops processes that are writing large amounts of data from dirtying pages on other nodes. Zone reclaim will write out dirty pages if a zone fills up and so effectively diff --git a/arch/ia64/include/asm/topology.h b/arch/ia64/include/asm/topology.h index 3202aa74e0d6..6437ca21f61b 100644 --- a/arch/ia64/include/asm/topology.h +++ b/arch/ia64/include/asm/topology.h @@ -21,7 +21,8 @@ #define PENALTY_FOR_NODE_WITH_CPUS 255 /* - * Distance above which we begin to use zone reclaim + * Nodes within this distance are eligible for reclaim by zone_reclaim() when + * zone_reclaim_mode is enabled. */ #define RECLAIM_DISTANCE 15 diff --git a/arch/powerpc/include/asm/topology.h b/arch/powerpc/include/asm/topology.h index c9202151079f..6c8a8c5a37a1 100644 --- a/arch/powerpc/include/asm/topology.h +++ b/arch/powerpc/include/asm/topology.h @@ -9,12 +9,8 @@ struct device_node; #ifdef CONFIG_NUMA /* - * Before going off node we want the VM to try and reclaim from the local - * node. It does this if the remote distance is larger than RECLAIM_DISTANCE. - * With the default REMOTE_DISTANCE of 20 and the default RECLAIM_DISTANCE of - * 20, we never reclaim and go off node straight away. - * - * To fix this we choose a smaller value of RECLAIM_DISTANCE. + * If zone_reclaim_mode is enabled, a RECLAIM_DISTANCE of 10 will mean that + * all zones on all nodes will be eligible for zone_reclaim(). */ #define RECLAIM_DISTANCE 10 diff --git a/include/linux/topology.h b/include/linux/topology.h index 973671ff9e7d..dda6ee521e74 100644 --- a/include/linux/topology.h +++ b/include/linux/topology.h @@ -58,7 +58,8 @@ int arch_update_cpu_topology(void); /* * If the distance between nodes in a system is larger than RECLAIM_DISTANCE * (in whatever arch specific measurement units returned by node_distance()) - * then switch on zone reclaim on boot. + * and zone_reclaim_mode is enabled then the VM will only call zone_reclaim() + * on nodes within this distance. */ #define RECLAIM_DISTANCE 30 #endif diff --git a/mm/page_alloc.c b/mm/page_alloc.c index 7cfdcd808f52..dfe954fbb48a 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -1860,8 +1860,6 @@ static void __paginginit init_zone_allows_reclaim(int nid) for_each_node_state(i, N_MEMORY) if (node_distance(nid, i) <= RECLAIM_DISTANCE) node_set(i, NODE_DATA(nid)->reclaim_nodes); - else - zone_reclaim_mode = 1; } #else /* CONFIG_NUMA */ -- cgit v1.2.3-71-gd317 From 5f7a75acdb24c7b9c436b3a0a66eec12e101d19c Mon Sep 17 00:00:00 2001 From: Mel Gorman Date: Wed, 4 Jun 2014 16:07:15 -0700 Subject: mm: page_alloc: do not cache reclaim distances pgdat->reclaim_nodes tracks if a remote node is allowed to be reclaimed by zone_reclaim due to its distance. As it is expected that zone_reclaim_mode will be rarely enabled it is unreasonable for all machines to take a penalty. Fortunately, the zone_reclaim_mode() path is already slow and it is the path that takes the hit. Signed-off-by: Mel Gorman Acked-by: Johannes Weiner Reviewed-by: Zhang Yanfei Acked-by: Michal Hocko Reviewed-by: Christoph Lameter Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mmzone.h | 1 - mm/page_alloc.c | 17 ++--------------- 2 files changed, 2 insertions(+), 16 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h index fac5509c18f0..c1dbe0ba9f82 100644 --- a/include/linux/mmzone.h +++ b/include/linux/mmzone.h @@ -763,7 +763,6 @@ typedef struct pglist_data { unsigned long node_spanned_pages; /* total size of physical page range, including holes */ int node_id; - nodemask_t reclaim_nodes; /* Nodes allowed to reclaim from */ wait_queue_head_t kswapd_wait; wait_queue_head_t pfmemalloc_wait; struct task_struct *kswapd; /* Protected by lock_memory_hotplug() */ diff --git a/mm/page_alloc.c b/mm/page_alloc.c index dfe954fbb48a..9f13bcfb6762 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -1850,16 +1850,8 @@ static bool zone_local(struct zone *local_zone, struct zone *zone) static bool zone_allows_reclaim(struct zone *local_zone, struct zone *zone) { - return node_isset(local_zone->node, zone->zone_pgdat->reclaim_nodes); -} - -static void __paginginit init_zone_allows_reclaim(int nid) -{ - int i; - - for_each_node_state(i, N_MEMORY) - if (node_distance(nid, i) <= RECLAIM_DISTANCE) - node_set(i, NODE_DATA(nid)->reclaim_nodes); + return node_distance(zone_to_nid(local_zone), zone_to_nid(zone)) < + RECLAIM_DISTANCE; } #else /* CONFIG_NUMA */ @@ -1893,9 +1885,6 @@ static bool zone_allows_reclaim(struct zone *local_zone, struct zone *zone) return true; } -static inline void init_zone_allows_reclaim(int nid) -{ -} #endif /* CONFIG_NUMA */ /* @@ -4933,8 +4922,6 @@ void __paginginit free_area_init_node(int nid, unsigned long *zones_size, pgdat->node_id = nid; pgdat->node_start_pfn = node_start_pfn; - if (node_state(nid, N_MEMORY)) - init_zone_allows_reclaim(nid); #ifdef CONFIG_HAVE_MEMBLOCK_NODE_MAP get_pfn_range_for_nid(nid, &start_pfn, &end_pfn); #endif -- cgit v1.2.3-71-gd317 From bfc8c90139ebd049b9801a951db3b9a4a00bed9c Mon Sep 17 00:00:00 2001 From: Vladimir Davydov Date: Wed, 4 Jun 2014 16:07:18 -0700 Subject: mem-hotplug: implement get/put_online_mems kmem_cache_{create,destroy,shrink} need to get a stable value of cpu/node online mask, because they init/destroy/access per-cpu/node kmem_cache parts, which can be allocated or destroyed on cpu/mem hotplug. To protect against cpu hotplug, these functions use {get,put}_online_cpus. However, they do nothing to synchronize with memory hotplug - taking the slab_mutex does not eliminate the possibility of race as described in patch 2. What we need there is something like get_online_cpus, but for memory. We already have lock_memory_hotplug, which serves for the purpose, but it's a bit of a hammer right now, because it's backed by a mutex. As a result, it imposes some limitations to locking order, which are not desirable, and can't be used just like get_online_cpus. That's why in patch 1 I substitute it with get/put_online_mems, which work exactly like get/put_online_cpus except they block not cpu, but memory hotplug. [ v1 can be found at https://lkml.org/lkml/2014/4/6/68. I NAK'ed it by myself, because it used an rw semaphore for get/put_online_mems, making them dead lock prune. ] This patch (of 2): {un}lock_memory_hotplug, which is used to synchronize against memory hotplug, is currently backed by a mutex, which makes it a bit of a hammer - threads that only want to get a stable value of online nodes mask won't be able to proceed concurrently. Also, it imposes some strong locking ordering rules on it, which narrows down the set of its usage scenarios. This patch introduces get/put_online_mems, which are the same as get/put_online_cpus, but for memory hotplug, i.e. executing a code inside a get/put_online_mems section will guarantee a stable value of online nodes, present pages, etc. lock_memory_hotplug()/unlock_memory_hotplug() are removed altogether. Signed-off-by: Vladimir Davydov Cc: Christoph Lameter Cc: Pekka Enberg Cc: Tang Chen Cc: Zhang Yanfei Cc: Toshi Kani Cc: Xishi Qiu Cc: Jiang Liu Cc: Rafael J. Wysocki Cc: David Rientjes Cc: Wen Congyang Cc: Yasuaki Ishimatsu Cc: Lai Jiangshan Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/memory_hotplug.h | 14 ++-- include/linux/mmzone.h | 8 +-- mm/kmemleak.c | 4 +- mm/memory-failure.c | 8 +-- mm/memory_hotplug.c | 142 +++++++++++++++++++++++++++++------------ mm/slub.c | 4 +- mm/vmscan.c | 2 +- 7 files changed, 116 insertions(+), 66 deletions(-) (limited to 'include/linux') diff --git a/include/linux/memory_hotplug.h b/include/linux/memory_hotplug.h index 4ca3d951fe91..010d125bffbf 100644 --- a/include/linux/memory_hotplug.h +++ b/include/linux/memory_hotplug.h @@ -187,14 +187,8 @@ extern void put_page_bootmem(struct page *page); extern void get_page_bootmem(unsigned long ingo, struct page *page, unsigned long type); -/* - * Lock for memory hotplug guarantees 1) all callbacks for memory hotplug - * notifier will be called under this. 2) offline/online/add/remove memory - * will not run simultaneously. - */ - -void lock_memory_hotplug(void); -void unlock_memory_hotplug(void); +void get_online_mems(void); +void put_online_mems(void); #else /* ! CONFIG_MEMORY_HOTPLUG */ /* @@ -232,8 +226,8 @@ static inline int try_online_node(int nid) return 0; } -static inline void lock_memory_hotplug(void) {} -static inline void unlock_memory_hotplug(void) {} +static inline void get_online_mems(void) {} +static inline void put_online_mems(void) {} #endif /* ! CONFIG_MEMORY_HOTPLUG */ diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h index c1dbe0ba9f82..ae693e1ad0f9 100644 --- a/include/linux/mmzone.h +++ b/include/linux/mmzone.h @@ -481,9 +481,8 @@ struct zone { * give them a chance of being in the same cacheline. * * Write access to present_pages at runtime should be protected by - * lock_memory_hotplug()/unlock_memory_hotplug(). Any reader who can't - * tolerant drift of present_pages should hold memory hotplug lock to - * get a stable value. + * mem_hotplug_begin/end(). Any reader who can't tolerant drift of + * present_pages should get_online_mems() to get a stable value. * * Read access to managed_pages should be safe because it's unsigned * long. Write access to zone->managed_pages and totalram_pages are @@ -765,7 +764,8 @@ typedef struct pglist_data { int node_id; wait_queue_head_t kswapd_wait; wait_queue_head_t pfmemalloc_wait; - struct task_struct *kswapd; /* Protected by lock_memory_hotplug() */ + struct task_struct *kswapd; /* Protected by + mem_hotplug_begin/end() */ int kswapd_max_order; enum zone_type classzone_idx; #ifdef CONFIG_NUMA_BALANCING diff --git a/mm/kmemleak.c b/mm/kmemleak.c index 8d2fcdfeff7f..736ade31d1dc 100644 --- a/mm/kmemleak.c +++ b/mm/kmemleak.c @@ -1300,7 +1300,7 @@ static void kmemleak_scan(void) /* * Struct page scanning for each node. */ - lock_memory_hotplug(); + get_online_mems(); for_each_online_node(i) { unsigned long start_pfn = node_start_pfn(i); unsigned long end_pfn = node_end_pfn(i); @@ -1318,7 +1318,7 @@ static void kmemleak_scan(void) scan_block(page, page + 1, NULL, 1); } } - unlock_memory_hotplug(); + put_online_mems(); /* * Scanning the task stacks (may introduce false negatives). diff --git a/mm/memory-failure.c b/mm/memory-failure.c index 9ccef39a9de2..6917f799412b 100644 --- a/mm/memory-failure.c +++ b/mm/memory-failure.c @@ -1664,11 +1664,7 @@ int soft_offline_page(struct page *page, int flags) } } - /* - * The lock_memory_hotplug prevents a race with memory hotplug. - * This is a big hammer, a better would be nicer. - */ - lock_memory_hotplug(); + get_online_mems(); /* * Isolate the page, so that it doesn't get reallocated if it @@ -1679,7 +1675,7 @@ int soft_offline_page(struct page *page, int flags) set_migratetype_isolate(page, true); ret = get_any_page(page, pfn, flags); - unlock_memory_hotplug(); + put_online_mems(); if (ret > 0) { /* for in-use pages */ if (PageHuge(page)) ret = soft_offline_huge_page(page, flags); diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c index a650db29606f..2906873a1502 100644 --- a/mm/memory_hotplug.c +++ b/mm/memory_hotplug.c @@ -46,19 +46,84 @@ static void generic_online_page(struct page *page); static online_page_callback_t online_page_callback = generic_online_page; +static DEFINE_MUTEX(online_page_callback_lock); -DEFINE_MUTEX(mem_hotplug_mutex); +/* The same as the cpu_hotplug lock, but for memory hotplug. */ +static struct { + struct task_struct *active_writer; + struct mutex lock; /* Synchronizes accesses to refcount, */ + /* + * Also blocks the new readers during + * an ongoing mem hotplug operation. + */ + int refcount; + +#ifdef CONFIG_DEBUG_LOCK_ALLOC + struct lockdep_map dep_map; +#endif +} mem_hotplug = { + .active_writer = NULL, + .lock = __MUTEX_INITIALIZER(mem_hotplug.lock), + .refcount = 0, +#ifdef CONFIG_DEBUG_LOCK_ALLOC + .dep_map = {.name = "mem_hotplug.lock" }, +#endif +}; + +/* Lockdep annotations for get/put_online_mems() and mem_hotplug_begin/end() */ +#define memhp_lock_acquire_read() lock_map_acquire_read(&mem_hotplug.dep_map) +#define memhp_lock_acquire() lock_map_acquire(&mem_hotplug.dep_map) +#define memhp_lock_release() lock_map_release(&mem_hotplug.dep_map) + +void get_online_mems(void) +{ + might_sleep(); + if (mem_hotplug.active_writer == current) + return; + memhp_lock_acquire_read(); + mutex_lock(&mem_hotplug.lock); + mem_hotplug.refcount++; + mutex_unlock(&mem_hotplug.lock); + +} -void lock_memory_hotplug(void) +void put_online_mems(void) { - mutex_lock(&mem_hotplug_mutex); + if (mem_hotplug.active_writer == current) + return; + mutex_lock(&mem_hotplug.lock); + + if (WARN_ON(!mem_hotplug.refcount)) + mem_hotplug.refcount++; /* try to fix things up */ + + if (!--mem_hotplug.refcount && unlikely(mem_hotplug.active_writer)) + wake_up_process(mem_hotplug.active_writer); + mutex_unlock(&mem_hotplug.lock); + memhp_lock_release(); + } -void unlock_memory_hotplug(void) +static void mem_hotplug_begin(void) { - mutex_unlock(&mem_hotplug_mutex); + mem_hotplug.active_writer = current; + + memhp_lock_acquire(); + for (;;) { + mutex_lock(&mem_hotplug.lock); + if (likely(!mem_hotplug.refcount)) + break; + __set_current_state(TASK_UNINTERRUPTIBLE); + mutex_unlock(&mem_hotplug.lock); + schedule(); + } } +static void mem_hotplug_done(void) +{ + mem_hotplug.active_writer = NULL; + mutex_unlock(&mem_hotplug.lock); + memhp_lock_release(); +} /* add this memory to iomem resource */ static struct resource *register_memory_resource(u64 start, u64 size) @@ -727,14 +792,16 @@ int set_online_page_callback(online_page_callback_t callback) { int rc = -EINVAL; - lock_memory_hotplug(); + get_online_mems(); + mutex_lock(&online_page_callback_lock); if (online_page_callback == generic_online_page) { online_page_callback = callback; rc = 0; } - unlock_memory_hotplug(); + mutex_unlock(&online_page_callback_lock); + put_online_mems(); return rc; } @@ -744,14 +811,16 @@ int restore_online_page_callback(online_page_callback_t callback) { int rc = -EINVAL; - lock_memory_hotplug(); + get_online_mems(); + mutex_lock(&online_page_callback_lock); if (online_page_callback == callback) { online_page_callback = generic_online_page; rc = 0; } - unlock_memory_hotplug(); + mutex_unlock(&online_page_callback_lock); + put_online_mems(); return rc; } @@ -899,7 +968,7 @@ int __ref online_pages(unsigned long pfn, unsigned long nr_pages, int online_typ int ret; struct memory_notify arg; - lock_memory_hotplug(); + mem_hotplug_begin(); /* * This doesn't need a lock to do pfn_to_page(). * The section can't be removed here because of the @@ -907,23 +976,18 @@ int __ref online_pages(unsigned long pfn, unsigned long nr_pages, int online_typ */ zone = page_zone(pfn_to_page(pfn)); + ret = -EINVAL; if ((zone_idx(zone) > ZONE_NORMAL || online_type == ONLINE_MOVABLE) && - !can_online_high_movable(zone)) { - unlock_memory_hotplug(); - return -EINVAL; - } + !can_online_high_movable(zone)) + goto out; if (online_type == ONLINE_KERNEL && zone_idx(zone) == ZONE_MOVABLE) { - if (move_pfn_range_left(zone - 1, zone, pfn, pfn + nr_pages)) { - unlock_memory_hotplug(); - return -EINVAL; - } + if (move_pfn_range_left(zone - 1, zone, pfn, pfn + nr_pages)) + goto out; } if (online_type == ONLINE_MOVABLE && zone_idx(zone) == ZONE_MOVABLE - 1) { - if (move_pfn_range_right(zone, zone + 1, pfn, pfn + nr_pages)) { - unlock_memory_hotplug(); - return -EINVAL; - } + if (move_pfn_range_right(zone, zone + 1, pfn, pfn + nr_pages)) + goto out; } /* Previous code may changed the zone of the pfn range */ @@ -939,8 +1003,7 @@ int __ref online_pages(unsigned long pfn, unsigned long nr_pages, int online_typ ret = notifier_to_errno(ret); if (ret) { memory_notify(MEM_CANCEL_ONLINE, &arg); - unlock_memory_hotplug(); - return ret; + goto out; } /* * If this zone is not populated, then it is not in zonelist. @@ -964,8 +1027,7 @@ int __ref online_pages(unsigned long pfn, unsigned long nr_pages, int online_typ (((unsigned long long) pfn + nr_pages) << PAGE_SHIFT) - 1); memory_notify(MEM_CANCEL_ONLINE, &arg); - unlock_memory_hotplug(); - return ret; + goto out; } zone->present_pages += onlined_pages; @@ -995,9 +1057,9 @@ int __ref online_pages(unsigned long pfn, unsigned long nr_pages, int online_typ if (onlined_pages) memory_notify(MEM_ONLINE, &arg); - unlock_memory_hotplug(); - - return 0; +out: + mem_hotplug_done(); + return ret; } #endif /* CONFIG_MEMORY_HOTPLUG_SPARSE */ @@ -1055,7 +1117,7 @@ int try_online_node(int nid) if (node_online(nid)) return 0; - lock_memory_hotplug(); + mem_hotplug_begin(); pgdat = hotadd_new_pgdat(nid, 0); if (!pgdat) { pr_err("Cannot online node %d due to NULL pgdat\n", nid); @@ -1073,7 +1135,7 @@ int try_online_node(int nid) } out: - unlock_memory_hotplug(); + mem_hotplug_done(); return ret; } @@ -1117,7 +1179,7 @@ int __ref add_memory(int nid, u64 start, u64 size) new_pgdat = !p; } - lock_memory_hotplug(); + mem_hotplug_begin(); new_node = !node_online(nid); if (new_node) { @@ -1158,7 +1220,7 @@ error: release_memory_resource(res); out: - unlock_memory_hotplug(); + mem_hotplug_done(); return ret; } EXPORT_SYMBOL_GPL(add_memory); @@ -1565,7 +1627,7 @@ static int __ref __offline_pages(unsigned long start_pfn, if (!test_pages_in_a_zone(start_pfn, end_pfn)) return -EINVAL; - lock_memory_hotplug(); + mem_hotplug_begin(); zone = page_zone(pfn_to_page(start_pfn)); node = zone_to_nid(zone); @@ -1672,7 +1734,7 @@ repeat: writeback_set_ratelimit(); memory_notify(MEM_OFFLINE, &arg); - unlock_memory_hotplug(); + mem_hotplug_done(); return 0; failed_removal: @@ -1684,7 +1746,7 @@ failed_removal: undo_isolate_page_range(start_pfn, end_pfn, MIGRATE_MOVABLE); out: - unlock_memory_hotplug(); + mem_hotplug_done(); return ret; } @@ -1888,7 +1950,7 @@ void __ref remove_memory(int nid, u64 start, u64 size) BUG_ON(check_hotplug_memory_range(start, size)); - lock_memory_hotplug(); + mem_hotplug_begin(); /* * All memory blocks must be offlined before removing memory. Check @@ -1897,10 +1959,8 @@ void __ref remove_memory(int nid, u64 start, u64 size) */ ret = walk_memory_range(PFN_DOWN(start), PFN_UP(start + size - 1), NULL, check_memblock_offlined_cb); - if (ret) { - unlock_memory_hotplug(); + if (ret) BUG(); - } /* remove memmap entry */ firmware_map_remove(start, start + size, "System RAM"); @@ -1909,7 +1969,7 @@ void __ref remove_memory(int nid, u64 start, u64 size) try_offline_node(nid); - unlock_memory_hotplug(); + mem_hotplug_done(); } EXPORT_SYMBOL_GPL(remove_memory); #endif /* CONFIG_MEMORY_HOTREMOVE */ diff --git a/mm/slub.c b/mm/slub.c index ddb60795f373..9cb2501a2960 100644 --- a/mm/slub.c +++ b/mm/slub.c @@ -4332,7 +4332,7 @@ static ssize_t show_slab_objects(struct kmem_cache *s, } } - lock_memory_hotplug(); + get_online_mems(); #ifdef CONFIG_SLUB_DEBUG if (flags & SO_ALL) { for_each_node_state(node, N_NORMAL_MEMORY) { @@ -4372,7 +4372,7 @@ static ssize_t show_slab_objects(struct kmem_cache *s, x += sprintf(buf + x, " N%d=%lu", node, nodes[node]); #endif - unlock_memory_hotplug(); + put_online_mems(); kfree(nodes); return x + sprintf(buf + x, "\n"); } diff --git a/mm/vmscan.c b/mm/vmscan.c index 7901cb749e17..fbcf46076c4f 100644 --- a/mm/vmscan.c +++ b/mm/vmscan.c @@ -3434,7 +3434,7 @@ int kswapd_run(int nid) /* * Called by memory hotplug when all memory in a node is offlined. Caller must - * hold lock_memory_hotplug(). + * hold mem_hotplug_begin/end(). */ void kswapd_stop(int nid) { -- cgit v1.2.3-71-gd317 From 2329d3751b082b4fd354f334a88662d72abac52d Mon Sep 17 00:00:00 2001 From: Jianyu Zhan Date: Wed, 4 Jun 2014 16:07:31 -0700 Subject: mm/swap.c: clean up *lru_cache_add* functions In mm/swap.c, __lru_cache_add() is exported, but actually there are no users outside this file. This patch unexports __lru_cache_add(), and makes it static. It also exports lru_cache_add_file(), as it is use by cifs and fuse, which can loaded as modules. Signed-off-by: Jianyu Zhan Cc: Minchan Kim Cc: Johannes Weiner Cc: Shaohua Li Cc: Bob Liu Cc: Seth Jennings Cc: Joonsoo Kim Cc: Rafael Aquini Cc: Mel Gorman Acked-by: Rik van Riel Cc: Andrea Arcangeli Cc: Khalid Aziz Cc: Christoph Hellwig Reviewed-by: Zhang Yanfei Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/swap.h | 19 ++----------------- mm/swap.c | 31 +++++++++++++++++++++++-------- 2 files changed, 25 insertions(+), 25 deletions(-) (limited to 'include/linux') diff --git a/include/linux/swap.h b/include/linux/swap.h index 350711560753..5a14b928164e 100644 --- a/include/linux/swap.h +++ b/include/linux/swap.h @@ -308,8 +308,9 @@ extern unsigned long nr_free_pagecache_pages(void); /* linux/mm/swap.c */ -extern void __lru_cache_add(struct page *); extern void lru_cache_add(struct page *); +extern void lru_cache_add_anon(struct page *page); +extern void lru_cache_add_file(struct page *page); extern void lru_add_page_tail(struct page *page, struct page *page_tail, struct lruvec *lruvec, struct list_head *head); extern void activate_page(struct page *); @@ -323,22 +324,6 @@ extern void swap_setup(void); extern void add_page_to_unevictable_list(struct page *page); -/** - * lru_cache_add: add a page to the page lists - * @page: the page to add - */ -static inline void lru_cache_add_anon(struct page *page) -{ - ClearPageActive(page); - __lru_cache_add(page); -} - -static inline void lru_cache_add_file(struct page *page) -{ - ClearPageActive(page); - __lru_cache_add(page); -} - /* linux/mm/vmscan.c */ extern unsigned long try_to_free_pages(struct zonelist *zonelist, int order, gfp_t gfp_mask, nodemask_t *mask); diff --git a/mm/swap.c b/mm/swap.c index 9ce43ba4498b..c0ed4d65438f 100644 --- a/mm/swap.c +++ b/mm/swap.c @@ -582,13 +582,7 @@ void mark_page_accessed(struct page *page) } EXPORT_SYMBOL(mark_page_accessed); -/* - * Queue the page for addition to the LRU via pagevec. The decision on whether - * to add the page to the [in]active [file|anon] list is deferred until the - * pagevec is drained. This gives a chance for the caller of __lru_cache_add() - * have the page added to the active list using mark_page_accessed(). - */ -void __lru_cache_add(struct page *page) +static void __lru_cache_add(struct page *page) { struct pagevec *pvec = &get_cpu_var(lru_add_pvec); @@ -598,11 +592,32 @@ void __lru_cache_add(struct page *page) pagevec_add(pvec, page); put_cpu_var(lru_add_pvec); } -EXPORT_SYMBOL(__lru_cache_add); + +/** + * lru_cache_add: add a page to the page lists + * @page: the page to add + */ +void lru_cache_add_anon(struct page *page) +{ + ClearPageActive(page); + __lru_cache_add(page); +} + +void lru_cache_add_file(struct page *page) +{ + ClearPageActive(page); + __lru_cache_add(page); +} +EXPORT_SYMBOL(lru_cache_add_file); /** * lru_cache_add - add a page to a page list * @page: the page to be added to the LRU. + * + * Queue the page for addition to the LRU via pagevec. The decision on whether + * to add the page to the [in]active [file|anon] list is deferred until the + * pagevec is drained. This gives a chance for the caller of lru_cache_add() + * have the page added to the active list using mark_page_accessed(). */ void lru_cache_add(struct page *page) { -- cgit v1.2.3-71-gd317 From f98bafa06a28fdfdd5c49f820f4d6560f636fc46 Mon Sep 17 00:00:00 2001 From: Oleg Nesterov Date: Wed, 4 Jun 2014 16:07:34 -0700 Subject: memcg: kill CONFIG_MM_OWNER CONFIG_MM_OWNER makes no sense. It is not user-selectable, it is only selected by CONFIG_MEMCG automatically. So we can kill this option in init/Kconfig and do s/CONFIG_MM_OWNER/CONFIG_MEMCG/ globally. Signed-off-by: Oleg Nesterov Acked-by: Michal Hocko Acked-by: Johannes Weiner Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mm_types.h | 2 +- include/linux/sched.h | 4 ++-- init/Kconfig | 7 ------- kernel/exit.c | 4 ++-- kernel/fork.c | 4 ++-- 5 files changed, 7 insertions(+), 14 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h index 8967e20cbe57..de1627232af0 100644 --- a/include/linux/mm_types.h +++ b/include/linux/mm_types.h @@ -406,7 +406,7 @@ struct mm_struct { spinlock_t ioctx_lock; struct kioctx_table __rcu *ioctx_table; #endif -#ifdef CONFIG_MM_OWNER +#ifdef CONFIG_MEMCG /* * "owner" points to a task that is regarded as the canonical * user/owner of this mm. All of the following must be true in diff --git a/include/linux/sched.h b/include/linux/sched.h index 70f67e4e6156..2f2dd7d932a2 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -2967,7 +2967,7 @@ static inline void inc_syscw(struct task_struct *tsk) #define TASK_SIZE_OF(tsk) TASK_SIZE #endif -#ifdef CONFIG_MM_OWNER +#ifdef CONFIG_MEMCG extern void mm_update_next_owner(struct mm_struct *mm); extern void mm_init_owner(struct mm_struct *mm, struct task_struct *p); #else @@ -2978,7 +2978,7 @@ static inline void mm_update_next_owner(struct mm_struct *mm) static inline void mm_init_owner(struct mm_struct *mm, struct task_struct *p) { } -#endif /* CONFIG_MM_OWNER */ +#endif /* CONFIG_MEMCG */ static inline unsigned long task_rlimit(const struct task_struct *tsk, unsigned int limit) diff --git a/init/Kconfig b/init/Kconfig index 4a1822a1a680..0a2f09a80e90 100644 --- a/init/Kconfig +++ b/init/Kconfig @@ -933,7 +933,6 @@ config RESOURCE_COUNTERS config MEMCG bool "Memory Resource Controller for Control Groups" depends on RESOURCE_COUNTERS - select MM_OWNER select EVENTFD help Provides a memory resource controller that manages both anonymous @@ -951,9 +950,6 @@ config MEMCG disable memory resource controller and you can avoid overheads. (and lose benefits of memory resource controller) - This config option also selects MM_OWNER config option, which - could in turn add some fork/exit overhead. - config MEMCG_SWAP bool "Memory Resource Controller Swap Extension" depends on MEMCG && SWAP @@ -1179,9 +1175,6 @@ config SCHED_AUTOGROUP desktop applications. Task group autogeneration is currently based upon task session. -config MM_OWNER - bool - config SYSFS_DEPRECATED bool "Enable deprecated sysfs features to support old userspace tools" depends on SYSFS diff --git a/kernel/exit.c b/kernel/exit.c index 6ed6a1d552b5..da1b838de8a6 100644 --- a/kernel/exit.c +++ b/kernel/exit.c @@ -352,7 +352,7 @@ int disallow_signal(int sig) EXPORT_SYMBOL(disallow_signal); -#ifdef CONFIG_MM_OWNER +#ifdef CONFIG_MEMCG /* * A task is exiting. If it owned this mm, find a new owner for the mm. */ @@ -434,7 +434,7 @@ assign_new_owner: task_unlock(c); put_task_struct(c); } -#endif /* CONFIG_MM_OWNER */ +#endif /* CONFIG_MEMCG */ /* * Turn us into a lazy TLB process if we diff --git a/kernel/fork.c b/kernel/fork.c index 59e3dcc5b8f2..0d53eb0dfb6f 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -1099,12 +1099,12 @@ static void rt_mutex_init_task(struct task_struct *p) #endif } -#ifdef CONFIG_MM_OWNER +#ifdef CONFIG_MEMCG void mm_init_owner(struct mm_struct *mm, struct task_struct *p) { mm->owner = p; } -#endif /* CONFIG_MM_OWNER */ +#endif /* CONFIG_MEMCG */ /* * Initialize POSIX timer handling for a single task. -- cgit v1.2.3-71-gd317 From 1e32e77f95d60b121b6072e3e3a650a7f93068f9 Mon Sep 17 00:00:00 2001 From: Vladimir Davydov Date: Wed, 4 Jun 2014 16:07:37 -0700 Subject: memcg, slab: do not schedule cache destruction when last page goes away This patchset is a part of preparations for kmemcg re-parenting. It targets at simplifying kmemcg work-flows and synchronization. First, it removes async per memcg cache destruction (see patches 1, 2). Now caches are only destroyed on memcg offline. That means the caches that are not empty on memcg offline will be leaked. However, they are already leaked, because memcg_cache_params::nr_pages normally never drops to 0 so the destruction work is never scheduled except kmem_cache_shrink is called explicitly. In the future I'm planning reaping such dead caches on vmpressure or periodically. Second, it substitutes per memcg slab_caches_mutex's with the global memcg_slab_mutex, which should be taken during the whole per memcg cache creation/destruction path before the slab_mutex (see patch 3). This greatly simplifies synchronization among various per memcg cache creation/destruction paths. I'm still not quite sure about the end picture, in particular I don't know whether we should reap dead memcgs' kmem caches periodically or try to merge them with their parents (see https://lkml.org/lkml/2014/4/20/38 for more details), but whichever way we choose, this set looks like a reasonable change to me, because it greatly simplifies kmemcg work-flows and eases further development. This patch (of 3): After a memcg is offlined, we mark its kmem caches that cannot be deleted right now due to pending objects as dead by setting the memcg_cache_params::dead flag, so that memcg_release_pages will schedule cache destruction (memcg_cache_params::destroy) as soon as the last slab of the cache is freed (memcg_cache_params::nr_pages drops to zero). I guess the idea was to destroy the caches as soon as possible, i.e. immediately after freeing the last object. However, it just doesn't work that way, because kmem caches always preserve some pages for the sake of performance, so that nr_pages never gets to zero unless the cache is shrunk explicitly using kmem_cache_shrink. Of course, we could account the total number of objects on the cache or check if all the slabs allocated for the cache are empty on kmem_cache_free and schedule destruction if so, but that would be too costly. Thus we have a piece of code that works only when we explicitly call kmem_cache_shrink, but complicates the whole picture a lot. Moreover, it's racy in fact. For instance, kmem_cache_shrink may free the last slab and thus schedule cache destruction before it finishes checking that the cache is empty, which can lead to use-after-free. So I propose to remove this async cache destruction from memcg_release_pages, and check if the cache is empty explicitly after calling kmem_cache_shrink instead. This will simplify things a lot w/o introducing any functional changes. And regarding dead memcg caches (i.e. those that are left hanging around after memcg offline for they have objects), I suppose we should reap them either periodically or on vmpressure as Glauber suggested initially. I'm going to implement this later. Signed-off-by: Vladimir Davydov Acked-by: Johannes Weiner Cc: Michal Hocko Cc: Glauber Costa Cc: Pekka Enberg Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/memcontrol.h | 1 - include/linux/slab.h | 2 -- mm/memcontrol.c | 63 ++-------------------------------------------- mm/slab.h | 7 ++---- 4 files changed, 4 insertions(+), 69 deletions(-) (limited to 'include/linux') diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h index 5155d09e749d..087a45314181 100644 --- a/include/linux/memcontrol.h +++ b/include/linux/memcontrol.h @@ -509,7 +509,6 @@ __memcg_kmem_get_cache(struct kmem_cache *cachep, gfp_t gfp); int memcg_charge_kmem(struct mem_cgroup *memcg, gfp_t gfp, u64 size); void memcg_uncharge_kmem(struct mem_cgroup *memcg, u64 size); -void mem_cgroup_destroy_cache(struct kmem_cache *cachep); int __kmem_cache_destroy_memcg_children(struct kmem_cache *s); /** diff --git a/include/linux/slab.h b/include/linux/slab.h index a6aab2c0dfc5..905541dd3778 100644 --- a/include/linux/slab.h +++ b/include/linux/slab.h @@ -524,7 +524,6 @@ static __always_inline void *kmalloc_node(size_t size, gfp_t flags, int node) * @memcg: pointer to the memcg this cache belongs to * @list: list_head for the list of all caches in this memcg * @root_cache: pointer to the global, root cache, this cache was derived from - * @dead: set to true after the memcg dies; the cache may still be around. * @nr_pages: number of pages that belongs to this cache. * @destroy: worker to be called whenever we are ready, or believe we may be * ready, to destroy this cache. @@ -540,7 +539,6 @@ struct memcg_cache_params { struct mem_cgroup *memcg; struct list_head list; struct kmem_cache *root_cache; - bool dead; atomic_t nr_pages; struct work_struct destroy; }; diff --git a/mm/memcontrol.c b/mm/memcontrol.c index 9f4ff49c6add..6b1c45ced733 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -3277,60 +3277,11 @@ static void kmem_cache_destroy_work_func(struct work_struct *w) cachep = memcg_params_to_cache(p); - /* - * If we get down to 0 after shrink, we could delete right away. - * However, memcg_release_pages() already puts us back in the workqueue - * in that case. If we proceed deleting, we'll get a dangling - * reference, and removing the object from the workqueue in that case - * is unnecessary complication. We are not a fast path. - * - * Note that this case is fundamentally different from racing with - * shrink_slab(): if memcg_cgroup_destroy_cache() is called in - * kmem_cache_shrink, not only we would be reinserting a dead cache - * into the queue, but doing so from inside the worker racing to - * destroy it. - * - * So if we aren't down to zero, we'll just schedule a worker and try - * again - */ - if (atomic_read(&cachep->memcg_params->nr_pages) != 0) - kmem_cache_shrink(cachep); - else + kmem_cache_shrink(cachep); + if (atomic_read(&cachep->memcg_params->nr_pages) == 0) kmem_cache_destroy(cachep); } -void mem_cgroup_destroy_cache(struct kmem_cache *cachep) -{ - if (!cachep->memcg_params->dead) - return; - - /* - * There are many ways in which we can get here. - * - * We can get to a memory-pressure situation while the delayed work is - * still pending to run. The vmscan shrinkers can then release all - * cache memory and get us to destruction. If this is the case, we'll - * be executed twice, which is a bug (the second time will execute over - * bogus data). In this case, cancelling the work should be fine. - * - * But we can also get here from the worker itself, if - * kmem_cache_shrink is enough to shake all the remaining objects and - * get the page count to 0. In this case, we'll deadlock if we try to - * cancel the work (the worker runs with an internal lock held, which - * is the same lock we would hold for cancel_work_sync().) - * - * Since we can't possibly know who got us here, just refrain from - * running if there is already work pending - */ - if (work_pending(&cachep->memcg_params->destroy)) - return; - /* - * We have to defer the actual destroying to a workqueue, because - * we might currently be in a context that cannot sleep. - */ - schedule_work(&cachep->memcg_params->destroy); -} - int __kmem_cache_destroy_memcg_children(struct kmem_cache *s) { struct kmem_cache *c; @@ -3356,16 +3307,7 @@ int __kmem_cache_destroy_memcg_children(struct kmem_cache *s) * We will now manually delete the caches, so to avoid races * we need to cancel all pending destruction workers and * proceed with destruction ourselves. - * - * kmem_cache_destroy() will call kmem_cache_shrink internally, - * and that could spawn the workers again: it is likely that - * the cache still have active pages until this very moment. - * This would lead us back to mem_cgroup_destroy_cache. - * - * But that will not execute at all if the "dead" flag is not - * set, so flip it down to guarantee we are in control. */ - c->memcg_params->dead = false; cancel_work_sync(&c->memcg_params->destroy); kmem_cache_destroy(c); @@ -3387,7 +3329,6 @@ static void mem_cgroup_destroy_all_caches(struct mem_cgroup *memcg) mutex_lock(&memcg->slab_caches_mutex); list_for_each_entry(params, &memcg->memcg_slab_caches, list) { cachep = memcg_params_to_cache(params); - cachep->memcg_params->dead = true; schedule_work(&cachep->memcg_params->destroy); } mutex_unlock(&memcg->slab_caches_mutex); diff --git a/mm/slab.h b/mm/slab.h index d85d59803d5f..b59447ac4533 100644 --- a/mm/slab.h +++ b/mm/slab.h @@ -129,11 +129,8 @@ static inline void memcg_bind_pages(struct kmem_cache *s, int order) static inline void memcg_release_pages(struct kmem_cache *s, int order) { - if (is_root_cache(s)) - return; - - if (atomic_sub_and_test((1 << order), &s->memcg_params->nr_pages)) - mem_cgroup_destroy_cache(s); + if (!is_root_cache(s)) + atomic_sub(1 << order, &s->memcg_params->nr_pages); } static inline bool slab_equal_or_root(struct kmem_cache *s, -- cgit v1.2.3-71-gd317 From c67a8a685a6e9abbaf0235e084168f15a721ae39 Mon Sep 17 00:00:00 2001 From: Vladimir Davydov Date: Wed, 4 Jun 2014 16:07:39 -0700 Subject: memcg, slab: merge memcg_{bind,release}_pages to memcg_{un}charge_slab Currently we have two pairs of kmemcg-related functions that are called on slab alloc/free. The first is memcg_{bind,release}_pages that count the total number of pages allocated on a kmem cache. The second is memcg_{un}charge_slab that {un}charge slab pages to kmemcg resource counter. Let's just merge them to keep the code clean. Signed-off-by: Vladimir Davydov Acked-by: Johannes Weiner Cc: Michal Hocko Cc: Glauber Costa Cc: Pekka Enberg Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/memcontrol.h | 4 ++-- mm/memcontrol.c | 22 ++++++++++++++++++++-- mm/slab.c | 2 -- mm/slab.h | 25 ++----------------------- mm/slub.c | 2 -- 5 files changed, 24 insertions(+), 31 deletions(-) (limited to 'include/linux') diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h index 087a45314181..d38d190f4cec 100644 --- a/include/linux/memcontrol.h +++ b/include/linux/memcontrol.h @@ -506,8 +506,8 @@ void memcg_update_array_size(int num_groups); struct kmem_cache * __memcg_kmem_get_cache(struct kmem_cache *cachep, gfp_t gfp); -int memcg_charge_kmem(struct mem_cgroup *memcg, gfp_t gfp, u64 size); -void memcg_uncharge_kmem(struct mem_cgroup *memcg, u64 size); +int __memcg_charge_slab(struct kmem_cache *cachep, gfp_t gfp, int order); +void __memcg_uncharge_slab(struct kmem_cache *cachep, int order); int __kmem_cache_destroy_memcg_children(struct kmem_cache *s); diff --git a/mm/memcontrol.c b/mm/memcontrol.c index 6b1c45ced733..86a2078805e5 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -2954,7 +2954,7 @@ static int mem_cgroup_slabinfo_read(struct seq_file *m, void *v) } #endif -int memcg_charge_kmem(struct mem_cgroup *memcg, gfp_t gfp, u64 size) +static int memcg_charge_kmem(struct mem_cgroup *memcg, gfp_t gfp, u64 size) { struct res_counter *fail_res; int ret = 0; @@ -2992,7 +2992,7 @@ int memcg_charge_kmem(struct mem_cgroup *memcg, gfp_t gfp, u64 size) return ret; } -void memcg_uncharge_kmem(struct mem_cgroup *memcg, u64 size) +static void memcg_uncharge_kmem(struct mem_cgroup *memcg, u64 size) { res_counter_uncharge(&memcg->res, size); if (do_swap_account) @@ -3390,6 +3390,24 @@ static void memcg_create_cache_enqueue(struct mem_cgroup *memcg, __memcg_create_cache_enqueue(memcg, cachep); memcg_resume_kmem_account(); } + +int __memcg_charge_slab(struct kmem_cache *cachep, gfp_t gfp, int order) +{ + int res; + + res = memcg_charge_kmem(cachep->memcg_params->memcg, gfp, + PAGE_SIZE << order); + if (!res) + atomic_add(1 << order, &cachep->memcg_params->nr_pages); + return res; +} + +void __memcg_uncharge_slab(struct kmem_cache *cachep, int order) +{ + memcg_uncharge_kmem(cachep->memcg_params->memcg, PAGE_SIZE << order); + atomic_sub(1 << order, &cachep->memcg_params->nr_pages); +} + /* * Return the kmem_cache we're supposed to use for a slab allocation. * We try to use the current memcg's version of the cache. diff --git a/mm/slab.c b/mm/slab.c index 7067ea7f3927..9ca3b87edabc 100644 --- a/mm/slab.c +++ b/mm/slab.c @@ -1712,7 +1712,6 @@ static struct page *kmem_getpages(struct kmem_cache *cachep, gfp_t flags, __SetPageSlab(page); if (page->pfmemalloc) SetPageSlabPfmemalloc(page); - memcg_bind_pages(cachep, cachep->gfporder); if (kmemcheck_enabled && !(cachep->flags & SLAB_NOTRACK)) { kmemcheck_alloc_shadow(page, cachep->gfporder, flags, nodeid); @@ -1748,7 +1747,6 @@ static void kmem_freepages(struct kmem_cache *cachep, struct page *page) page_mapcount_reset(page); page->mapping = NULL; - memcg_release_pages(cachep, cachep->gfporder); if (current->reclaim_state) current->reclaim_state->reclaimed_slab += nr_freed; __free_pages(page, cachep->gfporder); diff --git a/mm/slab.h b/mm/slab.h index b59447ac4533..961a3fb1f5a2 100644 --- a/mm/slab.h +++ b/mm/slab.h @@ -121,18 +121,6 @@ static inline bool is_root_cache(struct kmem_cache *s) return !s->memcg_params || s->memcg_params->is_root_cache; } -static inline void memcg_bind_pages(struct kmem_cache *s, int order) -{ - if (!is_root_cache(s)) - atomic_add(1 << order, &s->memcg_params->nr_pages); -} - -static inline void memcg_release_pages(struct kmem_cache *s, int order) -{ - if (!is_root_cache(s)) - atomic_sub(1 << order, &s->memcg_params->nr_pages); -} - static inline bool slab_equal_or_root(struct kmem_cache *s, struct kmem_cache *p) { @@ -198,8 +186,7 @@ static __always_inline int memcg_charge_slab(struct kmem_cache *s, return 0; if (is_root_cache(s)) return 0; - return memcg_charge_kmem(s->memcg_params->memcg, gfp, - PAGE_SIZE << order); + return __memcg_charge_slab(s, gfp, order); } static __always_inline void memcg_uncharge_slab(struct kmem_cache *s, int order) @@ -208,7 +195,7 @@ static __always_inline void memcg_uncharge_slab(struct kmem_cache *s, int order) return; if (is_root_cache(s)) return; - memcg_uncharge_kmem(s->memcg_params->memcg, PAGE_SIZE << order); + __memcg_uncharge_slab(s, order); } #else static inline bool is_root_cache(struct kmem_cache *s) @@ -216,14 +203,6 @@ static inline bool is_root_cache(struct kmem_cache *s) return true; } -static inline void memcg_bind_pages(struct kmem_cache *s, int order) -{ -} - -static inline void memcg_release_pages(struct kmem_cache *s, int order) -{ -} - static inline bool slab_equal_or_root(struct kmem_cache *s, struct kmem_cache *p) { diff --git a/mm/slub.c b/mm/slub.c index 5d1b653183ab..9e288d7c5e6a 100644 --- a/mm/slub.c +++ b/mm/slub.c @@ -1422,7 +1422,6 @@ static struct page *new_slab(struct kmem_cache *s, gfp_t flags, int node) order = compound_order(page); inc_slabs_node(s, page_to_nid(page), page->objects); - memcg_bind_pages(s, order); page->slab_cache = s; __SetPageSlab(page); if (page->pfmemalloc) @@ -1473,7 +1472,6 @@ static void __free_slab(struct kmem_cache *s, struct page *page) __ClearPageSlabPfmemalloc(page); __ClearPageSlab(page); - memcg_release_pages(s, order); page_mapcount_reset(page); if (current->reclaim_state) current->reclaim_state->reclaimed_slab += pages; -- cgit v1.2.3-71-gd317 From bd67314586a3d5725e60f2f6587b4cb0f659bb67 Mon Sep 17 00:00:00 2001 From: Vladimir Davydov Date: Wed, 4 Jun 2014 16:07:40 -0700 Subject: memcg, slab: simplify synchronization scheme At present, we have the following mutexes protecting data related to per memcg kmem caches: - slab_mutex. This one is held during the whole kmem cache creation and destruction paths. We also take it when updating per root cache memcg_caches arrays (see memcg_update_all_caches). As a result, taking it guarantees there will be no changes to any kmem cache (including per memcg). Why do we need something else then? The point is it is private to slab implementation and has some internal dependencies with other mutexes (get_online_cpus). So we just don't want to rely upon it and prefer to introduce additional mutexes instead. - activate_kmem_mutex. Initially it was added to synchronize initializing kmem limit (memcg_activate_kmem). However, since we can grow per root cache memcg_caches arrays only on kmem limit initialization (see memcg_update_all_caches), we also employ it to protect against memcg_caches arrays relocation (e.g. see __kmem_cache_destroy_memcg_children). - We have a convention not to take slab_mutex in memcontrol.c, but we want to walk over per memcg memcg_slab_caches lists there (e.g. for destroying all memcg caches on offline). So we have per memcg slab_caches_mutex's protecting those lists. The mutexes are taken in the following order: activate_kmem_mutex -> slab_mutex -> memcg::slab_caches_mutex Such a syncrhonization scheme has a number of flaws, for instance: - We can't call kmem_cache_{destroy,shrink} while walking over a memcg::memcg_slab_caches list due to locking order. As a result, in mem_cgroup_destroy_all_caches we schedule the memcg_cache_params::destroy work shrinking and destroying the cache. - We don't have a mutex to synchronize per memcg caches destruction between memcg offline (mem_cgroup_destroy_all_caches) and root cache destruction (__kmem_cache_destroy_memcg_children). Currently we just don't bother about it. This patch simplifies it by substituting per memcg slab_caches_mutex's with the global memcg_slab_mutex. It will be held whenever a new per memcg cache is created or destroyed, so it protects per root cache memcg_caches arrays and per memcg memcg_slab_caches lists. The locking order is following: activate_kmem_mutex -> memcg_slab_mutex -> slab_mutex This allows us to call kmem_cache_{create,shrink,destroy} under the memcg_slab_mutex. As a result, we don't need memcg_cache_params::destroy work any more - we can simply destroy caches while iterating over a per memcg slab caches list. Also using the global mutex simplifies synchronization between concurrent per memcg caches creation/destruction, e.g. mem_cgroup_destroy_all_caches vs __kmem_cache_destroy_memcg_children. The downside of this is that we substitute per-memcg slab_caches_mutex's with a hummer-like global mutex, but since we already take either the slab_mutex or the cgroup_mutex along with a memcg::slab_caches_mutex, it shouldn't hurt concurrency a lot. Signed-off-by: Vladimir Davydov Acked-by: Johannes Weiner Cc: Michal Hocko Cc: Glauber Costa Cc: Pekka Enberg Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/memcontrol.h | 10 --- include/linux/slab.h | 6 +- mm/memcontrol.c | 150 ++++++++++++++++++--------------------------- mm/slab_common.c | 23 +++---- 4 files changed, 69 insertions(+), 120 deletions(-) (limited to 'include/linux') diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h index d38d190f4cec..1fa23244fe37 100644 --- a/include/linux/memcontrol.h +++ b/include/linux/memcontrol.h @@ -497,8 +497,6 @@ char *memcg_create_cache_name(struct mem_cgroup *memcg, int memcg_alloc_cache_params(struct mem_cgroup *memcg, struct kmem_cache *s, struct kmem_cache *root_cache); void memcg_free_cache_params(struct kmem_cache *s); -void memcg_register_cache(struct kmem_cache *s); -void memcg_unregister_cache(struct kmem_cache *s); int memcg_update_cache_size(struct kmem_cache *s, int num_groups); void memcg_update_array_size(int num_groups); @@ -640,14 +638,6 @@ static inline void memcg_free_cache_params(struct kmem_cache *s) { } -static inline void memcg_register_cache(struct kmem_cache *s) -{ -} - -static inline void memcg_unregister_cache(struct kmem_cache *s) -{ -} - static inline struct kmem_cache * memcg_kmem_get_cache(struct kmem_cache *cachep, gfp_t gfp) { diff --git a/include/linux/slab.h b/include/linux/slab.h index 905541dd3778..ecbec9ccb80d 100644 --- a/include/linux/slab.h +++ b/include/linux/slab.h @@ -116,7 +116,8 @@ struct kmem_cache *kmem_cache_create(const char *, size_t, size_t, unsigned long, void (*)(void *)); #ifdef CONFIG_MEMCG_KMEM -void kmem_cache_create_memcg(struct mem_cgroup *, struct kmem_cache *); +struct kmem_cache *kmem_cache_create_memcg(struct mem_cgroup *, + struct kmem_cache *); #endif void kmem_cache_destroy(struct kmem_cache *); int kmem_cache_shrink(struct kmem_cache *); @@ -525,8 +526,6 @@ static __always_inline void *kmalloc_node(size_t size, gfp_t flags, int node) * @list: list_head for the list of all caches in this memcg * @root_cache: pointer to the global, root cache, this cache was derived from * @nr_pages: number of pages that belongs to this cache. - * @destroy: worker to be called whenever we are ready, or believe we may be - * ready, to destroy this cache. */ struct memcg_cache_params { bool is_root_cache; @@ -540,7 +539,6 @@ struct memcg_cache_params { struct list_head list; struct kmem_cache *root_cache; atomic_t nr_pages; - struct work_struct destroy; }; }; }; diff --git a/mm/memcontrol.c b/mm/memcontrol.c index 86a2078805e5..6b448881422b 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -357,10 +357,9 @@ struct mem_cgroup { struct cg_proto tcp_mem; #endif #if defined(CONFIG_MEMCG_KMEM) - /* analogous to slab_common's slab_caches list. per-memcg */ + /* analogous to slab_common's slab_caches list, but per-memcg; + * protected by memcg_slab_mutex */ struct list_head memcg_slab_caches; - /* Not a spinlock, we can take a lot of time walking the list */ - struct mutex slab_caches_mutex; /* Index in the kmem_cache->memcg_params->memcg_caches array */ int kmemcg_id; #endif @@ -2913,6 +2912,12 @@ static void __mem_cgroup_commit_charge(struct mem_cgroup *memcg, static DEFINE_MUTEX(set_limit_mutex); #ifdef CONFIG_MEMCG_KMEM +/* + * The memcg_slab_mutex is held whenever a per memcg kmem cache is created or + * destroyed. It protects memcg_caches arrays and memcg_slab_caches lists. + */ +static DEFINE_MUTEX(memcg_slab_mutex); + static DEFINE_MUTEX(activate_kmem_mutex); static inline bool memcg_can_account_kmem(struct mem_cgroup *memcg) @@ -2945,10 +2950,10 @@ static int mem_cgroup_slabinfo_read(struct seq_file *m, void *v) print_slabinfo_header(m); - mutex_lock(&memcg->slab_caches_mutex); + mutex_lock(&memcg_slab_mutex); list_for_each_entry(params, &memcg->memcg_slab_caches, list) cache_show(memcg_params_to_cache(params), m); - mutex_unlock(&memcg->slab_caches_mutex); + mutex_unlock(&memcg_slab_mutex); return 0; } @@ -3050,8 +3055,6 @@ void memcg_update_array_size(int num) memcg_limited_groups_array_size = memcg_caches_array_size(num); } -static void kmem_cache_destroy_work_func(struct work_struct *w); - int memcg_update_cache_size(struct kmem_cache *s, int num_groups) { struct memcg_cache_params *cur_params = s->memcg_params; @@ -3148,8 +3151,6 @@ int memcg_alloc_cache_params(struct mem_cgroup *memcg, struct kmem_cache *s, if (memcg) { s->memcg_params->memcg = memcg; s->memcg_params->root_cache = root_cache; - INIT_WORK(&s->memcg_params->destroy, - kmem_cache_destroy_work_func); css_get(&memcg->css); } else s->memcg_params->is_root_cache = true; @@ -3166,24 +3167,34 @@ void memcg_free_cache_params(struct kmem_cache *s) kfree(s->memcg_params); } -void memcg_register_cache(struct kmem_cache *s) +static void memcg_kmem_create_cache(struct mem_cgroup *memcg, + struct kmem_cache *root_cache) { - struct kmem_cache *root; - struct mem_cgroup *memcg; + struct kmem_cache *cachep; int id; - if (is_root_cache(s)) + lockdep_assert_held(&memcg_slab_mutex); + + id = memcg_cache_id(memcg); + + /* + * Since per-memcg caches are created asynchronously on first + * allocation (see memcg_kmem_get_cache()), several threads can try to + * create the same cache, but only one of them may succeed. + */ + if (cache_from_memcg_idx(root_cache, id)) return; + cachep = kmem_cache_create_memcg(memcg, root_cache); /* - * Holding the slab_mutex assures nobody will touch the memcg_caches - * array while we are modifying it. + * If we could not create a memcg cache, do not complain, because + * that's not critical at all as we can always proceed with the root + * cache. */ - lockdep_assert_held(&slab_mutex); + if (!cachep) + return; - root = s->memcg_params->root_cache; - memcg = s->memcg_params->memcg; - id = memcg_cache_id(memcg); + list_add(&cachep->memcg_params->list, &memcg->memcg_slab_caches); /* * Since readers won't lock (see cache_from_memcg_idx()), we need a @@ -3192,49 +3203,30 @@ void memcg_register_cache(struct kmem_cache *s) */ smp_wmb(); - /* - * Initialize the pointer to this cache in its parent's memcg_params - * before adding it to the memcg_slab_caches list, otherwise we can - * fail to convert memcg_params_to_cache() while traversing the list. - */ - VM_BUG_ON(root->memcg_params->memcg_caches[id]); - root->memcg_params->memcg_caches[id] = s; - - mutex_lock(&memcg->slab_caches_mutex); - list_add(&s->memcg_params->list, &memcg->memcg_slab_caches); - mutex_unlock(&memcg->slab_caches_mutex); + BUG_ON(root_cache->memcg_params->memcg_caches[id]); + root_cache->memcg_params->memcg_caches[id] = cachep; } -void memcg_unregister_cache(struct kmem_cache *s) +static void memcg_kmem_destroy_cache(struct kmem_cache *cachep) { - struct kmem_cache *root; + struct kmem_cache *root_cache; struct mem_cgroup *memcg; int id; - if (is_root_cache(s)) - return; + lockdep_assert_held(&memcg_slab_mutex); - /* - * Holding the slab_mutex assures nobody will touch the memcg_caches - * array while we are modifying it. - */ - lockdep_assert_held(&slab_mutex); + BUG_ON(is_root_cache(cachep)); - root = s->memcg_params->root_cache; - memcg = s->memcg_params->memcg; + root_cache = cachep->memcg_params->root_cache; + memcg = cachep->memcg_params->memcg; id = memcg_cache_id(memcg); - mutex_lock(&memcg->slab_caches_mutex); - list_del(&s->memcg_params->list); - mutex_unlock(&memcg->slab_caches_mutex); + BUG_ON(root_cache->memcg_params->memcg_caches[id] != cachep); + root_cache->memcg_params->memcg_caches[id] = NULL; - /* - * Clear the pointer to this cache in its parent's memcg_params only - * after removing it from the memcg_slab_caches list, otherwise we can - * fail to convert memcg_params_to_cache() while traversing the list. - */ - VM_BUG_ON(root->memcg_params->memcg_caches[id] != s); - root->memcg_params->memcg_caches[id] = NULL; + list_del(&cachep->memcg_params->list); + + kmem_cache_destroy(cachep); } /* @@ -3268,70 +3260,42 @@ static inline void memcg_resume_kmem_account(void) current->memcg_kmem_skip_account--; } -static void kmem_cache_destroy_work_func(struct work_struct *w) -{ - struct kmem_cache *cachep; - struct memcg_cache_params *p; - - p = container_of(w, struct memcg_cache_params, destroy); - - cachep = memcg_params_to_cache(p); - - kmem_cache_shrink(cachep); - if (atomic_read(&cachep->memcg_params->nr_pages) == 0) - kmem_cache_destroy(cachep); -} - int __kmem_cache_destroy_memcg_children(struct kmem_cache *s) { struct kmem_cache *c; int i, failed = 0; - /* - * If the cache is being destroyed, we trust that there is no one else - * requesting objects from it. Even if there are, the sanity checks in - * kmem_cache_destroy should caught this ill-case. - * - * Still, we don't want anyone else freeing memcg_caches under our - * noses, which can happen if a new memcg comes to life. As usual, - * we'll take the activate_kmem_mutex to protect ourselves against - * this. - */ - mutex_lock(&activate_kmem_mutex); + mutex_lock(&memcg_slab_mutex); for_each_memcg_cache_index(i) { c = cache_from_memcg_idx(s, i); if (!c) continue; - /* - * We will now manually delete the caches, so to avoid races - * we need to cancel all pending destruction workers and - * proceed with destruction ourselves. - */ - cancel_work_sync(&c->memcg_params->destroy); - kmem_cache_destroy(c); + memcg_kmem_destroy_cache(c); if (cache_from_memcg_idx(s, i)) failed++; } - mutex_unlock(&activate_kmem_mutex); + mutex_unlock(&memcg_slab_mutex); return failed; } static void mem_cgroup_destroy_all_caches(struct mem_cgroup *memcg) { struct kmem_cache *cachep; - struct memcg_cache_params *params; + struct memcg_cache_params *params, *tmp; if (!memcg_kmem_is_active(memcg)) return; - mutex_lock(&memcg->slab_caches_mutex); - list_for_each_entry(params, &memcg->memcg_slab_caches, list) { + mutex_lock(&memcg_slab_mutex); + list_for_each_entry_safe(params, tmp, &memcg->memcg_slab_caches, list) { cachep = memcg_params_to_cache(params); - schedule_work(&cachep->memcg_params->destroy); + kmem_cache_shrink(cachep); + if (atomic_read(&cachep->memcg_params->nr_pages) == 0) + memcg_kmem_destroy_cache(cachep); } - mutex_unlock(&memcg->slab_caches_mutex); + mutex_unlock(&memcg_slab_mutex); } struct create_work { @@ -3346,7 +3310,10 @@ static void memcg_create_cache_work_func(struct work_struct *w) struct mem_cgroup *memcg = cw->memcg; struct kmem_cache *cachep = cw->cachep; - kmem_cache_create_memcg(memcg, cachep); + mutex_lock(&memcg_slab_mutex); + memcg_kmem_create_cache(memcg, cachep); + mutex_unlock(&memcg_slab_mutex); + css_put(&memcg->css); kfree(cw); } @@ -5022,13 +4989,14 @@ static int __memcg_activate_kmem(struct mem_cgroup *memcg, * Make sure we have enough space for this cgroup in each root cache's * memcg_params. */ + mutex_lock(&memcg_slab_mutex); err = memcg_update_all_caches(memcg_id + 1); + mutex_unlock(&memcg_slab_mutex); if (err) goto out_rmid; memcg->kmemcg_id = memcg_id; INIT_LIST_HEAD(&memcg->memcg_slab_caches); - mutex_init(&memcg->slab_caches_mutex); /* * We couldn't have accounted to this cgroup, because it hasn't got the diff --git a/mm/slab_common.c b/mm/slab_common.c index 2dd920dc3776..7e348cff814d 100644 --- a/mm/slab_common.c +++ b/mm/slab_common.c @@ -160,7 +160,6 @@ do_kmem_cache_create(char *name, size_t object_size, size_t size, size_t align, s->refcount = 1; list_add(&s->list, &slab_caches); - memcg_register_cache(s); out: if (err) return ERR_PTR(err); @@ -270,9 +269,10 @@ EXPORT_SYMBOL(kmem_cache_create); * requests going from @memcg to @root_cache. The new cache inherits properties * from its parent. */ -void kmem_cache_create_memcg(struct mem_cgroup *memcg, struct kmem_cache *root_cache) +struct kmem_cache *kmem_cache_create_memcg(struct mem_cgroup *memcg, + struct kmem_cache *root_cache) { - struct kmem_cache *s; + struct kmem_cache *s = NULL; char *cache_name; get_online_cpus(); @@ -280,14 +280,6 @@ void kmem_cache_create_memcg(struct mem_cgroup *memcg, struct kmem_cache *root_c mutex_lock(&slab_mutex); - /* - * Since per-memcg caches are created asynchronously on first - * allocation (see memcg_kmem_get_cache()), several threads can try to - * create the same cache, but only one of them may succeed. - */ - if (cache_from_memcg_idx(root_cache, memcg_cache_id(memcg))) - goto out_unlock; - cache_name = memcg_create_cache_name(memcg, root_cache); if (!cache_name) goto out_unlock; @@ -296,14 +288,18 @@ void kmem_cache_create_memcg(struct mem_cgroup *memcg, struct kmem_cache *root_c root_cache->size, root_cache->align, root_cache->flags, root_cache->ctor, memcg, root_cache); - if (IS_ERR(s)) + if (IS_ERR(s)) { kfree(cache_name); + s = NULL; + } out_unlock: mutex_unlock(&slab_mutex); put_online_mems(); put_online_cpus(); + + return s; } static int kmem_cache_destroy_memcg_children(struct kmem_cache *s) @@ -348,11 +344,8 @@ void kmem_cache_destroy(struct kmem_cache *s) goto out_unlock; list_del(&s->list); - memcg_unregister_cache(s); - if (__kmem_cache_shutdown(s) != 0) { list_add(&s->list, &slab_caches); - memcg_register_cache(s); printk(KERN_ERR "kmem_cache_destroy %s: " "Slab cache still has objects\n", s->name); dump_stack(); -- cgit v1.2.3-71-gd317 From 1b938c0827478df268d2336469ec48d400a2eb3e Mon Sep 17 00:00:00 2001 From: Matthew Wilcox Date: Wed, 4 Jun 2014 16:07:43 -0700 Subject: fs/buffer.c: remove block_write_full_page_endio() The last in-tree caller of block_write_full_page_endio() was removed in January 2013. It's time to remove the EXPORT_SYMBOL, which leaves block_write_full_page() as the only caller of block_write_full_page_endio(), so inline block_write_full_page_endio() into block_write_full_page(). Signed-off-by: Matthew Wilcox Cc: Hugh Dickins Cc: Dave Chinner Cc: Dheeraj Reddy Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- fs/buffer.c | 21 +++++---------------- fs/ext4/page-io.c | 2 +- fs/ocfs2/file.c | 2 +- include/linux/buffer_head.h | 2 -- 4 files changed, 7 insertions(+), 20 deletions(-) (limited to 'include/linux') diff --git a/fs/buffer.c b/fs/buffer.c index 6a8110c03a47..e33f8d5452ad 100644 --- a/fs/buffer.c +++ b/fs/buffer.c @@ -2879,10 +2879,9 @@ EXPORT_SYMBOL(block_truncate_page); /* * The generic ->writepage function for buffer-backed address_spaces - * this form passes in the end_io handler used to finish the IO. */ -int block_write_full_page_endio(struct page *page, get_block_t *get_block, - struct writeback_control *wbc, bh_end_io_t *handler) +int block_write_full_page(struct page *page, get_block_t *get_block, + struct writeback_control *wbc) { struct inode * const inode = page->mapping->host; loff_t i_size = i_size_read(inode); @@ -2892,7 +2891,7 @@ int block_write_full_page_endio(struct page *page, get_block_t *get_block, /* Is the page fully inside i_size? */ if (page->index < end_index) return __block_write_full_page(inode, page, get_block, wbc, - handler); + end_buffer_async_write); /* Is the page fully outside i_size? (truncate in progress) */ offset = i_size & (PAGE_CACHE_SIZE-1); @@ -2915,18 +2914,8 @@ int block_write_full_page_endio(struct page *page, get_block_t *get_block, * writes to that region are not written out to the file." */ zero_user_segment(page, offset, PAGE_CACHE_SIZE); - return __block_write_full_page(inode, page, get_block, wbc, handler); -} -EXPORT_SYMBOL(block_write_full_page_endio); - -/* - * The generic ->writepage function for buffer-backed address_spaces - */ -int block_write_full_page(struct page *page, get_block_t *get_block, - struct writeback_control *wbc) -{ - return block_write_full_page_endio(page, get_block, wbc, - end_buffer_async_write); + return __block_write_full_page(inode, page, get_block, wbc, + end_buffer_async_write); } EXPORT_SYMBOL(block_write_full_page); diff --git a/fs/ext4/page-io.c b/fs/ext4/page-io.c index c18d95b50540..1a64e7a52b84 100644 --- a/fs/ext4/page-io.c +++ b/fs/ext4/page-io.c @@ -429,7 +429,7 @@ int ext4_bio_write_page(struct ext4_io_submit *io, block_start = bh_offset(bh); if (block_start >= len) { /* - * Comments copied from block_write_full_page_endio: + * Comments copied from block_write_full_page: * * The page straddles i_size. It must be zeroed out on * each and every writepage invocation because it may diff --git a/fs/ocfs2/file.c b/fs/ocfs2/file.c index 8970dcf74de5..8eb6e5732d3b 100644 --- a/fs/ocfs2/file.c +++ b/fs/ocfs2/file.c @@ -828,7 +828,7 @@ static int ocfs2_write_zero_page(struct inode *inode, u64 abs_from, /* * fs-writeback will release the dirty pages without page lock * whose offset are over inode size, the release happens at - * block_write_full_page_endio(). + * block_write_full_page(). */ i_size_write(inode, abs_to); inode->i_blocks = ocfs2_inode_sector_count(inode); diff --git a/include/linux/buffer_head.h b/include/linux/buffer_head.h index 7cbf837a279c..324329ceea1e 100644 --- a/include/linux/buffer_head.h +++ b/include/linux/buffer_head.h @@ -207,8 +207,6 @@ void block_invalidatepage(struct page *page, unsigned int offset, unsigned int length); int block_write_full_page(struct page *page, get_block_t *get_block, struct writeback_control *wbc); -int block_write_full_page_endio(struct page *page, get_block_t *get_block, - struct writeback_control *wbc, bh_end_io_t *handler); int block_read_full_page(struct page*, get_block_t*); int block_is_partially_uptodate(struct page *page, unsigned long from, unsigned long count); -- cgit v1.2.3-71-gd317 From 57d998456ae8680ed446aa1993f45f4d8a9a5973 Mon Sep 17 00:00:00 2001 From: Matthew Wilcox Date: Wed, 4 Jun 2014 16:07:45 -0700 Subject: fs/mpage.c: factor page_endio() out of mpage_end_io() page_endio() takes care of updating all the appropriate page flags once I/O has finished to a page. Switch to using mapping_set_error() instead of setting AS_EIO directly; this will handle thin-provisioned devices correctly. Signed-off-by: Matthew Wilcox Cc: Dave Chinner Cc: Dheeraj Reddy Cc: Hugh Dickins Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- fs/mpage.c | 18 +----------------- include/linux/pagemap.h | 2 ++ mm/filemap.c | 25 +++++++++++++++++++++++++ 3 files changed, 28 insertions(+), 17 deletions(-) (limited to 'include/linux') diff --git a/fs/mpage.c b/fs/mpage.c index 4cc9c5d079f7..10da0da73017 100644 --- a/fs/mpage.c +++ b/fs/mpage.c @@ -48,23 +48,7 @@ static void mpage_end_io(struct bio *bio, int err) bio_for_each_segment_all(bv, bio, i) { struct page *page = bv->bv_page; - - if (bio_data_dir(bio) == READ) { - if (!err) { - SetPageUptodate(page); - } else { - ClearPageUptodate(page); - SetPageError(page); - } - unlock_page(page); - } else { /* bio_data_dir(bio) == WRITE */ - if (err) { - SetPageError(page); - if (page->mapping) - set_bit(AS_EIO, &page->mapping->flags); - } - end_page_writeback(page); - } + page_endio(page, bio_data_dir(bio), err); } bio_put(bio); diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h index 45598f1e9aa3..718214c5584e 100644 --- a/include/linux/pagemap.h +++ b/include/linux/pagemap.h @@ -425,6 +425,8 @@ static inline void wait_on_page_writeback(struct page *page) extern void end_page_writeback(struct page *page); void wait_for_stable_page(struct page *page); +void page_endio(struct page *page, int rw, int err); + /* * Add an arbitrary waiter to a page's wait queue */ diff --git a/mm/filemap.c b/mm/filemap.c index 021056c324e6..47d235b357a7 100644 --- a/mm/filemap.c +++ b/mm/filemap.c @@ -764,6 +764,31 @@ void end_page_writeback(struct page *page) } EXPORT_SYMBOL(end_page_writeback); +/* + * After completing I/O on a page, call this routine to update the page + * flags appropriately + */ +void page_endio(struct page *page, int rw, int err) +{ + if (rw == READ) { + if (!err) { + SetPageUptodate(page); + } else { + ClearPageUptodate(page); + SetPageError(page); + } + unlock_page(page); + } else { /* rw == WRITE */ + if (err) { + SetPageError(page); + if (page->mapping) + mapping_set_error(page->mapping, err); + } + end_page_writeback(page); + } +} +EXPORT_SYMBOL_GPL(page_endio); + /** * __lock_page - get a lock on the page, assuming we need to sleep to get it * @page: the page to lock -- cgit v1.2.3-71-gd317 From 47a191fd38ebddb1bd1510ec2bc1085c578c8868 Mon Sep 17 00:00:00 2001 From: Matthew Wilcox Date: Wed, 4 Jun 2014 16:07:46 -0700 Subject: fs/block_dev.c: add bdev_read_page() and bdev_write_page() A block device driver may choose to provide a rw_page operation. These will be called when the filesystem is attempting to do page sized I/O to page cache pages (ie not for direct I/O). This does preclude I/Os that are larger than page size, so this may only be a performance gain for some devices. Signed-off-by: Matthew Wilcox Tested-by: Dheeraj Reddy Cc: Dave Chinner Cc: Hugh Dickins Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- fs/block_dev.c | 63 ++++++++++++++++++++++++++++++++++++++++++++++++++ fs/mpage.c | 12 ++++++++++ include/linux/blkdev.h | 4 ++++ 3 files changed, 79 insertions(+) (limited to 'include/linux') diff --git a/fs/block_dev.c b/fs/block_dev.c index 552a8d13bc32..83fba15cc394 100644 --- a/fs/block_dev.c +++ b/fs/block_dev.c @@ -363,6 +363,69 @@ int blkdev_fsync(struct file *filp, loff_t start, loff_t end, int datasync) } EXPORT_SYMBOL(blkdev_fsync); +/** + * bdev_read_page() - Start reading a page from a block device + * @bdev: The device to read the page from + * @sector: The offset on the device to read the page to (need not be aligned) + * @page: The page to read + * + * On entry, the page should be locked. It will be unlocked when the page + * has been read. If the block driver implements rw_page synchronously, + * that will be true on exit from this function, but it need not be. + * + * Errors returned by this function are usually "soft", eg out of memory, or + * queue full; callers should try a different route to read this page rather + * than propagate an error back up the stack. + * + * Return: negative errno if an error occurs, 0 if submission was successful. + */ +int bdev_read_page(struct block_device *bdev, sector_t sector, + struct page *page) +{ + const struct block_device_operations *ops = bdev->bd_disk->fops; + if (!ops->rw_page) + return -EOPNOTSUPP; + return ops->rw_page(bdev, sector + get_start_sect(bdev), page, READ); +} +EXPORT_SYMBOL_GPL(bdev_read_page); + +/** + * bdev_write_page() - Start writing a page to a block device + * @bdev: The device to write the page to + * @sector: The offset on the device to write the page to (need not be aligned) + * @page: The page to write + * @wbc: The writeback_control for the write + * + * On entry, the page should be locked and not currently under writeback. + * On exit, if the write started successfully, the page will be unlocked and + * under writeback. If the write failed already (eg the driver failed to + * queue the page to the device), the page will still be locked. If the + * caller is a ->writepage implementation, it will need to unlock the page. + * + * Errors returned by this function are usually "soft", eg out of memory, or + * queue full; callers should try a different route to write this page rather + * than propagate an error back up the stack. + * + * Return: negative errno if an error occurs, 0 if submission was successful. + */ +int bdev_write_page(struct block_device *bdev, sector_t sector, + struct page *page, struct writeback_control *wbc) +{ + int result; + int rw = (wbc->sync_mode == WB_SYNC_ALL) ? WRITE_SYNC : WRITE; + const struct block_device_operations *ops = bdev->bd_disk->fops; + if (!ops->rw_page) + return -EOPNOTSUPP; + set_page_writeback(page); + result = ops->rw_page(bdev, sector + get_start_sect(bdev), page, rw); + if (result) + end_page_writeback(page); + else + unlock_page(page); + return result; +} +EXPORT_SYMBOL_GPL(bdev_write_page); + /* * pseudo-fs */ diff --git a/fs/mpage.c b/fs/mpage.c index 10da0da73017..5f9ed622274f 100644 --- a/fs/mpage.c +++ b/fs/mpage.c @@ -269,6 +269,11 @@ do_mpage_readpage(struct bio *bio, struct page *page, unsigned nr_pages, alloc_new: if (bio == NULL) { + if (first_hole == blocks_per_page) { + if (!bdev_read_page(bdev, blocks[0] << (blkbits - 9), + page)) + goto out; + } bio = mpage_alloc(bdev, blocks[0] << (blkbits - 9), min_t(int, nr_pages, bio_get_nr_vecs(bdev)), GFP_KERNEL); @@ -587,6 +592,13 @@ page_is_mapped: alloc_new: if (bio == NULL) { + if (first_unmapped == blocks_per_page) { + if (!bdev_write_page(bdev, blocks[0] << (blkbits - 9), + page, wbc)) { + clean_buffers(page, first_unmapped); + goto out; + } + } bio = mpage_alloc(bdev, blocks[0] << (blkbits - 9), bio_get_nr_vecs(bdev), GFP_NOFS|__GFP_HIGH); if (bio == NULL) diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 45cf6e537c83..2f3886e6cc78 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -1588,6 +1588,7 @@ static inline bool blk_integrity_is_initialized(struct gendisk *g) struct block_device_operations { int (*open) (struct block_device *, fmode_t); void (*release) (struct gendisk *, fmode_t); + int (*rw_page)(struct block_device *, sector_t, struct page *, int rw); int (*ioctl) (struct block_device *, fmode_t, unsigned, unsigned long); int (*compat_ioctl) (struct block_device *, fmode_t, unsigned, unsigned long); int (*direct_access) (struct block_device *, sector_t, @@ -1606,6 +1607,9 @@ struct block_device_operations { extern int __blkdev_driver_ioctl(struct block_device *, fmode_t, unsigned int, unsigned long); +extern int bdev_read_page(struct block_device *, sector_t, struct page *); +extern int bdev_write_page(struct block_device *, sector_t, struct page *, + struct writeback_control *); #else /* CONFIG_BLOCK */ struct block_device; -- cgit v1.2.3-71-gd317 From f7f28ca98b9a7a99fc55df2dddcf49857ab004f0 Mon Sep 17 00:00:00 2001 From: Rasmus Villemoes Date: Wed, 4 Jun 2014 16:07:57 -0700 Subject: mm: constify nmask argument to mbind() The nmask argument to mbind() is const according to the userspace header numaif.h, and since the kernel does indeed not modify it, it might as well be declared const in the kernel. Signed-off-by: Rasmus Villemoes Acked-by: Rik van Riel Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/syscalls.h | 2 +- mm/mempolicy.c | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h index a4a0588c5397..bfef0be279dd 100644 --- a/include/linux/syscalls.h +++ b/include/linux/syscalls.h @@ -723,7 +723,7 @@ asmlinkage long sys_move_pages(pid_t pid, unsigned long nr_pages, int flags); asmlinkage long sys_mbind(unsigned long start, unsigned long len, unsigned long mode, - unsigned long __user *nmask, + const unsigned long __user *nmask, unsigned long maxnode, unsigned flags); asmlinkage long sys_get_mempolicy(int __user *policy, diff --git a/mm/mempolicy.c b/mm/mempolicy.c index 78e1472933ea..727187f1155b 100644 --- a/mm/mempolicy.c +++ b/mm/mempolicy.c @@ -1362,7 +1362,7 @@ static int copy_nodes_to_user(unsigned long __user *mask, unsigned long maxnode, } SYSCALL_DEFINE6(mbind, unsigned long, start, unsigned long, len, - unsigned long, mode, unsigned long __user *, nmask, + unsigned long, mode, const unsigned long __user *, nmask, unsigned long, maxnode, unsigned, flags) { nodemask_t nodes; -- cgit v1.2.3-71-gd317 From 23c8902d403ef9a04cdc367d0b76a3ed6d83f5c5 Mon Sep 17 00:00:00 2001 From: Rasmus Villemoes Date: Wed, 4 Jun 2014 16:07:58 -0700 Subject: mm: constify nmask argument to set_mempolicy() The nmask argument to set_mempolicy() is const according to the user-space header numaif.h, and since the kernel does indeed not modify it, it might as well be declared const in the kernel. Signed-off-by: Rasmus Villemoes Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/syscalls.h | 2 +- mm/mempolicy.c | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h index bfef0be279dd..b0881a0ed322 100644 --- a/include/linux/syscalls.h +++ b/include/linux/syscalls.h @@ -711,7 +711,7 @@ asmlinkage long sys_keyctl(int cmd, unsigned long arg2, unsigned long arg3, asmlinkage long sys_ioprio_set(int which, int who, int ioprio); asmlinkage long sys_ioprio_get(int which, int who); -asmlinkage long sys_set_mempolicy(int mode, unsigned long __user *nmask, +asmlinkage long sys_set_mempolicy(int mode, const unsigned long __user *nmask, unsigned long maxnode); asmlinkage long sys_migrate_pages(pid_t pid, unsigned long maxnode, const unsigned long __user *from, diff --git a/mm/mempolicy.c b/mm/mempolicy.c index 727187f1155b..b09586d8316b 100644 --- a/mm/mempolicy.c +++ b/mm/mempolicy.c @@ -1383,7 +1383,7 @@ SYSCALL_DEFINE6(mbind, unsigned long, start, unsigned long, len, } /* Set the process memory policy */ -SYSCALL_DEFINE3(set_mempolicy, int, mode, unsigned long __user *, nmask, +SYSCALL_DEFINE3(set_mempolicy, int, mode, const unsigned long __user *, nmask, unsigned long, maxnode) { int err; -- cgit v1.2.3-71-gd317 From d2ee40eae98d8a41ff27dcdd13b1b656c4c1ad00 Mon Sep 17 00:00:00 2001 From: Jianyu Zhan Date: Wed, 4 Jun 2014 16:08:02 -0700 Subject: mm: introdule compound_head_by_tail() MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Currently, in put_compound_page(), we have ====== if (likely(!PageTail(page))) { <------ (1) if (put_page_testzero(page)) { /* ¦* By the time all refcounts have been released ¦* split_huge_page cannot run anymore from under us. ¦*/ if (PageHead(page)) __put_compound_page(page); else __put_single_page(page); } return; } /* __split_huge_page_refcount can run under us */ page_head = compound_head(page); <------------ (2) ====== if at (1) , we fail the check, this means page is *likely* a tail page. Then at (2), as compoud_head(page) is inlined, it is : ====== static inline struct page *compound_head(struct page *page) { if (unlikely(PageTail(page))) { <----------- (3) struct page *head = page->first_page; smp_rmb(); if (likely(PageTail(page))) return head; } return page; } ====== here, the (3) unlikely in the case is a negative hint, because it is *likely* a tail page. So the check (3) in this case is not good, so I introduce a helper for this case. So this patch introduces compound_head_by_tail() which deals with a possible tail page(though it could be spilt by a racy thread), and make compound_head() a wrapper on it. This patch has no functional change, and it reduces the object size slightly: text data bss dec hex filename 11003 1328 16 12347 303b mm/swap.o.orig 10971 1328 16 12315 301b mm/swap.o.patched I've ran "perf top -e branch-miss" to observe branch-miss in this case. As Michael points out, it's a slow path, so only very few times this case happens. But I grep'ed the code base, and found there still are some other call sites could be benifited from this helper. And given that it only bloating up the source by only 5 lines, but with a reduced object size. I still believe this helper deserves to exsit. Signed-off-by: Jianyu Zhan Cc: Kirill A. Shutemov Cc: Rik van Riel Cc: Jiang Liu Cc: Peter Zijlstra Cc: Johannes Weiner Cc: Mel Gorman Cc: Andrea Arcangeli Cc: Sasha Levin Cc: Wanpeng Li Cc: Hugh Dickins Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mm.h | 29 +++++++++++++++++------------ mm/swap.c | 2 +- 2 files changed, 18 insertions(+), 13 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mm.h b/include/linux/mm.h index d6777060449f..368600628d14 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -407,20 +407,25 @@ static inline void compound_unlock_irqrestore(struct page *page, #endif } +static inline struct page *compound_head_by_tail(struct page *tail) +{ + struct page *head = tail->first_page; + + /* + * page->first_page may be a dangling pointer to an old + * compound page, so recheck that it is still a tail + * page before returning. + */ + smp_rmb(); + if (likely(PageTail(tail))) + return head; + return tail; +} + static inline struct page *compound_head(struct page *page) { - if (unlikely(PageTail(page))) { - struct page *head = page->first_page; - - /* - * page->first_page may be a dangling pointer to an old - * compound page, so recheck that it is still a tail - * page before returning. - */ - smp_rmb(); - if (likely(PageTail(page))) - return head; - } + if (unlikely(PageTail(page))) + return compound_head_by_tail(page); return page; } diff --git a/mm/swap.c b/mm/swap.c index d089c5a0cf98..c8d6df556ce6 100644 --- a/mm/swap.c +++ b/mm/swap.c @@ -253,7 +253,7 @@ static void put_compound_page(struct page *page) * Case 3 is possible, as we may race with * __split_huge_page_refcount tearing down a THP page. */ - page_head = compound_head(page); + page_head = compound_head_by_tail(page); if (!__compound_tail_refcounted(page_head)) put_unrefcounted_compound_page(page_head, page); else -- cgit v1.2.3-71-gd317 From 1754e44e8291c92b9d981a6eca59f28dd25f03ab Mon Sep 17 00:00:00 2001 From: Wang Sheng-Hui Date: Wed, 4 Jun 2014 16:08:04 -0700 Subject: include/linux/bootmem.h: cleanup the comment for BOOTMEM_ flags Use BOOTMEM_DEFAULT instead of 0 in the comment. Signed-off-by: Wang Sheng-Hui Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/bootmem.h | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/bootmem.h b/include/linux/bootmem.h index db51fe4fe317..4e2bd4c95b66 100644 --- a/include/linux/bootmem.h +++ b/include/linux/bootmem.h @@ -58,9 +58,9 @@ extern void free_bootmem_late(unsigned long physaddr, unsigned long size); * Flags for reserve_bootmem (also if CONFIG_HAVE_ARCH_BOOTMEM_NODE, * the architecture-specific code should honor this). * - * If flags is 0, then the return value is always 0 (success). If - * flags contains BOOTMEM_EXCLUSIVE, then -EBUSY is returned if the - * memory already was reserved. + * If flags is BOOTMEM_DEFAULT, then the return value is always 0 (success). + * If flags contains BOOTMEM_EXCLUSIVE, then -EBUSY is returned if the memory + * already was reserved. */ #define BOOTMEM_DEFAULT 0 #define BOOTMEM_EXCLUSIVE (1<<0) -- cgit v1.2.3-71-gd317 From ac7695012a6f3269acd80d6c2b2218a6769edbf3 Mon Sep 17 00:00:00 2001 From: "Kirill A. Shutemov" Date: Wed, 4 Jun 2014 16:08:17 -0700 Subject: mm/rmap.c: make page_referenced_one() and try_to_unmap_one() static KSM was converted to use rmap_walk() and now nobody uses these functions outside mm/rmap.c. Let's covert them back to static. Signed-off-by: Kirill A. Shutemov Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/rmap.h | 4 ---- mm/rmap.c | 4 ++-- 2 files changed, 2 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/rmap.h b/include/linux/rmap.h index b66c2110cb1f..9be55c7617da 100644 --- a/include/linux/rmap.h +++ b/include/linux/rmap.h @@ -183,14 +183,10 @@ static inline void page_dup_rmap(struct page *page) */ int page_referenced(struct page *, int is_locked, struct mem_cgroup *memcg, unsigned long *vm_flags); -int page_referenced_one(struct page *, struct vm_area_struct *, - unsigned long address, void *arg); #define TTU_ACTION(x) ((x) & TTU_ACTION_MASK) int try_to_unmap(struct page *, enum ttu_flags flags); -int try_to_unmap_one(struct page *, struct vm_area_struct *, - unsigned long address, void *arg); /* * Called from mm/filemap_xip.c to unmap empty zero page diff --git a/mm/rmap.c b/mm/rmap.c index 7da400d5d98e..8754e1fa83b6 100644 --- a/mm/rmap.c +++ b/mm/rmap.c @@ -671,7 +671,7 @@ struct page_referenced_arg { /* * arg: page_referenced_arg will be passed */ -int page_referenced_one(struct page *page, struct vm_area_struct *vma, +static int page_referenced_one(struct page *page, struct vm_area_struct *vma, unsigned long address, void *arg) { struct mm_struct *mm = vma->vm_mm; @@ -1114,7 +1114,7 @@ out: /* * @arg: enum ttu_flags will be passed to this argument */ -int try_to_unmap_one(struct page *page, struct vm_area_struct *vma, +static int try_to_unmap_one(struct page *page, struct vm_area_struct *vma, unsigned long address, void *arg) { struct mm_struct *mm = vma->vm_mm; -- cgit v1.2.3-71-gd317 From 3fb1c8dcfcda2f5bfb7d79d8b08bf2f04b1eed8f Mon Sep 17 00:00:00 2001 From: "Kirill A. Shutemov" Date: Wed, 4 Jun 2014 16:08:20 -0700 Subject: mm: update comment for DEFAULT_MAX_MAP_COUNT With ELF extended numbering 16-bit bound is not hard limit any more. [akpm@linux-foundation.org: fix typo] Signed-off-by: Kirill A. Shutemov Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/sched/sysctl.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/sched/sysctl.h b/include/linux/sched/sysctl.h index 8045a554cafb..596a0e007c62 100644 --- a/include/linux/sched/sysctl.h +++ b/include/linux/sched/sysctl.h @@ -25,6 +25,10 @@ enum { sysctl_hung_task_timeout_secs = 0 }; * Because the kernel adds some informative sections to a image of program at * generating coredump, we need some margin. The number of extra sections is * 1-3 now and depends on arch. We use "5" as safe margin, here. + * + * ELF extended numbering allows more than 65535 sections, so 16-bit bound is + * not a hard limit any more. Although some userspace tools can be surprised by + * that. */ #define MAPCOUNT_ELF_CORE_MARGIN (5) #define DEFAULT_MAX_MAP_COUNT (USHRT_MAX - MAPCOUNT_ELF_CORE_MARGIN) -- cgit v1.2.3-71-gd317 From 073ee1c6cd11cd190f4d0da84d9b4ba79d7b9e70 Mon Sep 17 00:00:00 2001 From: Vladimir Davydov Date: Wed, 4 Jun 2014 16:08:23 -0700 Subject: memcg: get rid of memcg_create_cache_name Instead of calling back to memcontrol.c from kmem_cache_create_memcg in order to just create the name of a per memcg cache, let's allocate it in place. We only need to pass the memcg name to kmem_cache_create_memcg for that - everything else can be done in slab_common.c. Signed-off-by: Vladimir Davydov Acked-by: Michal Hocko Cc: Johannes Weiner Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/memcontrol.h | 2 -- include/linux/slab.h | 3 ++- mm/memcontrol.c | 33 +++++++++------------------------ mm/slab_common.c | 7 +++++-- 4 files changed, 16 insertions(+), 29 deletions(-) (limited to 'include/linux') diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h index 1fa23244fe37..dfc2929a3877 100644 --- a/include/linux/memcontrol.h +++ b/include/linux/memcontrol.h @@ -492,8 +492,6 @@ void __memcg_kmem_uncharge_pages(struct page *page, int order); int memcg_cache_id(struct mem_cgroup *memcg); -char *memcg_create_cache_name(struct mem_cgroup *memcg, - struct kmem_cache *root_cache); int memcg_alloc_cache_params(struct mem_cgroup *memcg, struct kmem_cache *s, struct kmem_cache *root_cache); void memcg_free_cache_params(struct kmem_cache *s); diff --git a/include/linux/slab.h b/include/linux/slab.h index ecbec9ccb80d..86e5b26fbdab 100644 --- a/include/linux/slab.h +++ b/include/linux/slab.h @@ -117,7 +117,8 @@ struct kmem_cache *kmem_cache_create(const char *, size_t, size_t, void (*)(void *)); #ifdef CONFIG_MEMCG_KMEM struct kmem_cache *kmem_cache_create_memcg(struct mem_cgroup *, - struct kmem_cache *); + struct kmem_cache *, + const char *); #endif void kmem_cache_destroy(struct kmem_cache *); int kmem_cache_shrink(struct kmem_cache *); diff --git a/mm/memcontrol.c b/mm/memcontrol.c index 971d7b643f6e..7df7f599e3df 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -3095,29 +3095,6 @@ int memcg_update_cache_size(struct kmem_cache *s, int num_groups) return 0; } -char *memcg_create_cache_name(struct mem_cgroup *memcg, - struct kmem_cache *root_cache) -{ - static char *buf; - - /* - * We need a mutex here to protect the shared buffer. Since this is - * expected to be called only on cache creation, we can employ the - * slab_mutex for that purpose. - */ - lockdep_assert_held(&slab_mutex); - - if (!buf) { - buf = kmalloc(NAME_MAX + 1, GFP_KERNEL); - if (!buf) - return NULL; - } - - cgroup_name(memcg->css.cgroup, buf, NAME_MAX + 1); - return kasprintf(GFP_KERNEL, "%s(%d:%s)", root_cache->name, - memcg_cache_id(memcg), buf); -} - int memcg_alloc_cache_params(struct mem_cgroup *memcg, struct kmem_cache *s, struct kmem_cache *root_cache) { @@ -3158,6 +3135,7 @@ void memcg_free_cache_params(struct kmem_cache *s) static void memcg_kmem_create_cache(struct mem_cgroup *memcg, struct kmem_cache *root_cache) { + static char *memcg_name_buf; /* protected by memcg_slab_mutex */ struct kmem_cache *cachep; int id; @@ -3173,7 +3151,14 @@ static void memcg_kmem_create_cache(struct mem_cgroup *memcg, if (cache_from_memcg_idx(root_cache, id)) return; - cachep = kmem_cache_create_memcg(memcg, root_cache); + if (!memcg_name_buf) { + memcg_name_buf = kmalloc(NAME_MAX + 1, GFP_KERNEL); + if (!memcg_name_buf) + return; + } + + cgroup_name(memcg->css.cgroup, memcg_name_buf, NAME_MAX + 1); + cachep = kmem_cache_create_memcg(memcg, root_cache, memcg_name_buf); /* * If we could not create a memcg cache, do not complain, because * that's not critical at all as we can always proceed with the root diff --git a/mm/slab_common.c b/mm/slab_common.c index 7e348cff814d..32175617cb75 100644 --- a/mm/slab_common.c +++ b/mm/slab_common.c @@ -264,13 +264,15 @@ EXPORT_SYMBOL(kmem_cache_create); * kmem_cache_create_memcg - Create a cache for a memory cgroup. * @memcg: The memory cgroup the new cache is for. * @root_cache: The parent of the new cache. + * @memcg_name: The name of the memory cgroup (used for naming the new cache). * * This function attempts to create a kmem cache that will serve allocation * requests going from @memcg to @root_cache. The new cache inherits properties * from its parent. */ struct kmem_cache *kmem_cache_create_memcg(struct mem_cgroup *memcg, - struct kmem_cache *root_cache) + struct kmem_cache *root_cache, + const char *memcg_name) { struct kmem_cache *s = NULL; char *cache_name; @@ -280,7 +282,8 @@ struct kmem_cache *kmem_cache_create_memcg(struct mem_cgroup *memcg, mutex_lock(&slab_mutex); - cache_name = memcg_create_cache_name(memcg, root_cache); + cache_name = kasprintf(GFP_KERNEL, "%s(%d:%s)", root_cache->name, + memcg_cache_id(memcg), memcg_name); if (!cache_name) goto out_unlock; -- cgit v1.2.3-71-gd317 From 68711a746345c44ae00c64d8dbac6a9ce13ac54a Mon Sep 17 00:00:00 2001 From: David Rientjes Date: Wed, 4 Jun 2014 16:08:25 -0700 Subject: mm, migration: add destination page freeing callback Memory migration uses a callback defined by the caller to determine how to allocate destination pages. When migration fails for a source page, however, it frees the destination page back to the system. This patch adds a memory migration callback defined by the caller to determine how to free destination pages. If a caller, such as memory compaction, builds its own freelist for migration targets, this can reuse already freed memory instead of scanning additional memory. If the caller provides a function to handle freeing of destination pages, it is called when page migration fails. If the caller passes NULL then freeing back to the system will be handled as usual. This patch introduces no functional change. Signed-off-by: David Rientjes Reviewed-by: Naoya Horiguchi Acked-by: Mel Gorman Acked-by: Vlastimil Babka Cc: Greg Thelen Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/migrate.h | 11 ++++++---- mm/compaction.c | 2 +- mm/memory-failure.c | 4 ++-- mm/memory_hotplug.c | 2 +- mm/mempolicy.c | 4 ++-- mm/migrate.c | 55 +++++++++++++++++++++++++++++++++++-------------- mm/page_alloc.c | 2 +- 7 files changed, 53 insertions(+), 27 deletions(-) (limited to 'include/linux') diff --git a/include/linux/migrate.h b/include/linux/migrate.h index 84a31ad0b791..a2901c414664 100644 --- a/include/linux/migrate.h +++ b/include/linux/migrate.h @@ -5,7 +5,9 @@ #include #include -typedef struct page *new_page_t(struct page *, unsigned long private, int **); +typedef struct page *new_page_t(struct page *page, unsigned long private, + int **reason); +typedef void free_page_t(struct page *page, unsigned long private); /* * Return values from addresss_space_operations.migratepage(): @@ -38,7 +40,7 @@ enum migrate_reason { extern void putback_movable_pages(struct list_head *l); extern int migrate_page(struct address_space *, struct page *, struct page *, enum migrate_mode); -extern int migrate_pages(struct list_head *l, new_page_t x, +extern int migrate_pages(struct list_head *l, new_page_t new, free_page_t free, unsigned long private, enum migrate_mode mode, int reason); extern int migrate_prep(void); @@ -56,8 +58,9 @@ extern int migrate_page_move_mapping(struct address_space *mapping, #else static inline void putback_movable_pages(struct list_head *l) {} -static inline int migrate_pages(struct list_head *l, new_page_t x, - unsigned long private, enum migrate_mode mode, int reason) +static inline int migrate_pages(struct list_head *l, new_page_t new, + free_page_t free, unsigned long private, enum migrate_mode mode, + int reason) { return -ENOSYS; } static inline int migrate_prep(void) { return -ENOSYS; } diff --git a/mm/compaction.c b/mm/compaction.c index 6010aabde28c..f74a362d2e28 100644 --- a/mm/compaction.c +++ b/mm/compaction.c @@ -1016,7 +1016,7 @@ static int compact_zone(struct zone *zone, struct compact_control *cc) } nr_migrate = cc->nr_migratepages; - err = migrate_pages(&cc->migratepages, compaction_alloc, + err = migrate_pages(&cc->migratepages, compaction_alloc, NULL, (unsigned long)cc, cc->sync ? MIGRATE_SYNC_LIGHT : MIGRATE_ASYNC, MR_COMPACTION); diff --git a/mm/memory-failure.c b/mm/memory-failure.c index d50f17fb9be2..3cd1b652821c 100644 --- a/mm/memory-failure.c +++ b/mm/memory-failure.c @@ -1503,7 +1503,7 @@ static int soft_offline_huge_page(struct page *page, int flags) /* Keep page count to indicate a given hugepage is isolated. */ list_move(&hpage->lru, &pagelist); - ret = migrate_pages(&pagelist, new_page, MPOL_MF_MOVE_ALL, + ret = migrate_pages(&pagelist, new_page, NULL, MPOL_MF_MOVE_ALL, MIGRATE_SYNC, MR_MEMORY_FAILURE); if (ret) { pr_info("soft offline: %#lx: migration failed %d, type %lx\n", @@ -1584,7 +1584,7 @@ static int __soft_offline_page(struct page *page, int flags) inc_zone_page_state(page, NR_ISOLATED_ANON + page_is_file_cache(page)); list_add(&page->lru, &pagelist); - ret = migrate_pages(&pagelist, new_page, MPOL_MF_MOVE_ALL, + ret = migrate_pages(&pagelist, new_page, NULL, MPOL_MF_MOVE_ALL, MIGRATE_SYNC, MR_MEMORY_FAILURE); if (ret) { if (!list_empty(&pagelist)) { diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c index cbb7ca0ac44b..469bbf505f85 100644 --- a/mm/memory_hotplug.c +++ b/mm/memory_hotplug.c @@ -1394,7 +1394,7 @@ do_migrate_range(unsigned long start_pfn, unsigned long end_pfn) * alloc_migrate_target should be improooooved!! * migrate_pages returns # of failed pages. */ - ret = migrate_pages(&source, alloc_migrate_target, 0, + ret = migrate_pages(&source, alloc_migrate_target, NULL, 0, MIGRATE_SYNC, MR_MEMORY_HOTPLUG); if (ret) putback_movable_pages(&source); diff --git a/mm/mempolicy.c b/mm/mempolicy.c index 7f7864b95e8e..16bc9fa42998 100644 --- a/mm/mempolicy.c +++ b/mm/mempolicy.c @@ -1028,7 +1028,7 @@ static int migrate_to_node(struct mm_struct *mm, int source, int dest, flags | MPOL_MF_DISCONTIG_OK, &pagelist); if (!list_empty(&pagelist)) { - err = migrate_pages(&pagelist, new_node_page, dest, + err = migrate_pages(&pagelist, new_node_page, NULL, dest, MIGRATE_SYNC, MR_SYSCALL); if (err) putback_movable_pages(&pagelist); @@ -1277,7 +1277,7 @@ static long do_mbind(unsigned long start, unsigned long len, if (!list_empty(&pagelist)) { WARN_ON_ONCE(flags & MPOL_MF_LAZY); nr_failed = migrate_pages(&pagelist, new_vma_page, - (unsigned long)vma, + NULL, (unsigned long)vma, MIGRATE_SYNC, MR_MEMPOLICY_MBIND); if (nr_failed) putback_movable_pages(&pagelist); diff --git a/mm/migrate.c b/mm/migrate.c index 6247be7fa30e..2a459675eeab 100644 --- a/mm/migrate.c +++ b/mm/migrate.c @@ -938,8 +938,9 @@ out: * Obtain the lock on page, remove all ptes and migrate the page * to the newly allocated page in newpage. */ -static int unmap_and_move(new_page_t get_new_page, unsigned long private, - struct page *page, int force, enum migrate_mode mode) +static int unmap_and_move(new_page_t get_new_page, free_page_t put_new_page, + unsigned long private, struct page *page, int force, + enum migrate_mode mode) { int rc = 0; int *result = NULL; @@ -983,11 +984,17 @@ out: page_is_file_cache(page)); putback_lru_page(page); } + /* - * Move the new page to the LRU. If migration was not successful - * then this will free the page. + * If migration was not successful and there's a freeing callback, use + * it. Otherwise, putback_lru_page() will drop the reference grabbed + * during isolation. */ - putback_lru_page(newpage); + if (rc != MIGRATEPAGE_SUCCESS && put_new_page) + put_new_page(newpage, private); + else + putback_lru_page(newpage); + if (result) { if (rc) *result = rc; @@ -1016,8 +1023,9 @@ out: * will wait in the page fault for migration to complete. */ static int unmap_and_move_huge_page(new_page_t get_new_page, - unsigned long private, struct page *hpage, - int force, enum migrate_mode mode) + free_page_t put_new_page, unsigned long private, + struct page *hpage, int force, + enum migrate_mode mode) { int rc = 0; int *result = NULL; @@ -1056,20 +1064,30 @@ static int unmap_and_move_huge_page(new_page_t get_new_page, if (!page_mapped(hpage)) rc = move_to_new_page(new_hpage, hpage, 1, mode); - if (rc) + if (rc != MIGRATEPAGE_SUCCESS) remove_migration_ptes(hpage, hpage); if (anon_vma) put_anon_vma(anon_vma); - if (!rc) + if (rc == MIGRATEPAGE_SUCCESS) hugetlb_cgroup_migrate(hpage, new_hpage); unlock_page(hpage); out: if (rc != -EAGAIN) putback_active_hugepage(hpage); - put_page(new_hpage); + + /* + * If migration was not successful and there's a freeing callback, use + * it. Otherwise, put_page() will drop the reference grabbed during + * isolation. + */ + if (rc != MIGRATEPAGE_SUCCESS && put_new_page) + put_new_page(new_hpage, private); + else + put_page(new_hpage); + if (result) { if (rc) *result = rc; @@ -1086,6 +1104,8 @@ out: * @from: The list of pages to be migrated. * @get_new_page: The function used to allocate free pages to be used * as the target of the page migration. + * @put_new_page: The function used to free target pages if migration + * fails, or NULL if no special handling is necessary. * @private: Private data to be passed on to get_new_page() * @mode: The migration mode that specifies the constraints for * page migration, if any. @@ -1099,7 +1119,8 @@ out: * Returns the number of pages that were not migrated, or an error code. */ int migrate_pages(struct list_head *from, new_page_t get_new_page, - unsigned long private, enum migrate_mode mode, int reason) + free_page_t put_new_page, unsigned long private, + enum migrate_mode mode, int reason) { int retry = 1; int nr_failed = 0; @@ -1121,10 +1142,11 @@ int migrate_pages(struct list_head *from, new_page_t get_new_page, if (PageHuge(page)) rc = unmap_and_move_huge_page(get_new_page, - private, page, pass > 2, mode); + put_new_page, private, page, + pass > 2, mode); else - rc = unmap_and_move(get_new_page, private, - page, pass > 2, mode); + rc = unmap_and_move(get_new_page, put_new_page, + private, page, pass > 2, mode); switch(rc) { case -ENOMEM: @@ -1273,7 +1295,7 @@ set_status: err = 0; if (!list_empty(&pagelist)) { - err = migrate_pages(&pagelist, new_page_node, + err = migrate_pages(&pagelist, new_page_node, NULL, (unsigned long)pm, MIGRATE_SYNC, MR_SYSCALL); if (err) putback_movable_pages(&pagelist); @@ -1729,7 +1751,8 @@ int migrate_misplaced_page(struct page *page, struct vm_area_struct *vma, list_add(&page->lru, &migratepages); nr_remaining = migrate_pages(&migratepages, alloc_misplaced_dst_page, - node, MIGRATE_ASYNC, MR_NUMA_MISPLACED); + NULL, node, MIGRATE_ASYNC, + MR_NUMA_MISPLACED); if (nr_remaining) { if (!list_empty(&migratepages)) { list_del(&page->lru); diff --git a/mm/page_alloc.c b/mm/page_alloc.c index 132c337dbe55..027d0294413a 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -6218,7 +6218,7 @@ static int __alloc_contig_migrate_range(struct compact_control *cc, cc->nr_migratepages -= nr_reclaimed; ret = migrate_pages(&cc->migratepages, alloc_migrate_target, - 0, MIGRATE_SYNC, MR_CMA); + NULL, 0, MIGRATE_SYNC, MR_CMA); } if (ret < 0) { putback_movable_pages(&cc->migratepages); -- cgit v1.2.3-71-gd317 From 35979ef3393110ff3c12c6b94552208d3bdf1a36 Mon Sep 17 00:00:00 2001 From: David Rientjes Date: Wed, 4 Jun 2014 16:08:27 -0700 Subject: mm, compaction: add per-zone migration pfn cache for async compaction Each zone has a cached migration scanner pfn for memory compaction so that subsequent calls to memory compaction can start where the previous call left off. Currently, the compaction migration scanner only updates the per-zone cached pfn when pageblocks were not skipped for async compaction. This creates a dependency on calling sync compaction to avoid having subsequent calls to async compaction from scanning an enormous amount of non-MOVABLE pageblocks each time it is called. On large machines, this could be potentially very expensive. This patch adds a per-zone cached migration scanner pfn only for async compaction. It is updated everytime a pageblock has been scanned in its entirety and when no pages from it were successfully isolated. The cached migration scanner pfn for sync compaction is updated only when called for sync compaction. Signed-off-by: David Rientjes Acked-by: Vlastimil Babka Reviewed-by: Naoya Horiguchi Cc: Greg Thelen Cc: Mel Gorman Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mmzone.h | 5 ++-- mm/compaction.c | 66 ++++++++++++++++++++++++++++++-------------------- 2 files changed, 43 insertions(+), 28 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h index ae693e1ad0f9..10a96ee68311 100644 --- a/include/linux/mmzone.h +++ b/include/linux/mmzone.h @@ -360,9 +360,10 @@ struct zone { /* Set to true when the PG_migrate_skip bits should be cleared */ bool compact_blockskip_flush; - /* pfns where compaction scanners should start */ + /* pfn where compaction free scanner should start */ unsigned long compact_cached_free_pfn; - unsigned long compact_cached_migrate_pfn; + /* pfn where async and sync compaction migration scanner should start */ + unsigned long compact_cached_migrate_pfn[2]; #endif #ifdef CONFIG_MEMORY_HOTPLUG /* see spanned/present_pages for more description */ diff --git a/mm/compaction.c b/mm/compaction.c index d0c7c994e11b..70c0f8cda33f 100644 --- a/mm/compaction.c +++ b/mm/compaction.c @@ -89,7 +89,8 @@ static void __reset_isolation_suitable(struct zone *zone) unsigned long end_pfn = zone_end_pfn(zone); unsigned long pfn; - zone->compact_cached_migrate_pfn = start_pfn; + zone->compact_cached_migrate_pfn[0] = start_pfn; + zone->compact_cached_migrate_pfn[1] = start_pfn; zone->compact_cached_free_pfn = end_pfn; zone->compact_blockskip_flush = false; @@ -131,9 +132,10 @@ void reset_isolation_suitable(pg_data_t *pgdat) */ static void update_pageblock_skip(struct compact_control *cc, struct page *page, unsigned long nr_isolated, - bool migrate_scanner) + bool set_unsuitable, bool migrate_scanner) { struct zone *zone = cc->zone; + unsigned long pfn; if (cc->ignore_skip_hint) return; @@ -141,20 +143,31 @@ static void update_pageblock_skip(struct compact_control *cc, if (!page) return; - if (!nr_isolated) { - unsigned long pfn = page_to_pfn(page); + if (nr_isolated) + return; + + /* + * Only skip pageblocks when all forms of compaction will be known to + * fail in the near future. + */ + if (set_unsuitable) set_pageblock_skip(page); - /* Update where compaction should restart */ - if (migrate_scanner) { - if (!cc->finished_update_migrate && - pfn > zone->compact_cached_migrate_pfn) - zone->compact_cached_migrate_pfn = pfn; - } else { - if (!cc->finished_update_free && - pfn < zone->compact_cached_free_pfn) - zone->compact_cached_free_pfn = pfn; - } + pfn = page_to_pfn(page); + + /* Update where async and sync compaction should restart */ + if (migrate_scanner) { + if (cc->finished_update_migrate) + return; + if (pfn > zone->compact_cached_migrate_pfn[0]) + zone->compact_cached_migrate_pfn[0] = pfn; + if (cc->sync && pfn > zone->compact_cached_migrate_pfn[1]) + zone->compact_cached_migrate_pfn[1] = pfn; + } else { + if (cc->finished_update_free) + return; + if (pfn < zone->compact_cached_free_pfn) + zone->compact_cached_free_pfn = pfn; } } #else @@ -166,7 +179,7 @@ static inline bool isolation_suitable(struct compact_control *cc, static void update_pageblock_skip(struct compact_control *cc, struct page *page, unsigned long nr_isolated, - bool migrate_scanner) + bool set_unsuitable, bool migrate_scanner) { } #endif /* CONFIG_COMPACTION */ @@ -323,7 +336,8 @@ isolate_fail: /* Update the pageblock-skip if the whole pageblock was scanned */ if (blockpfn == end_pfn) - update_pageblock_skip(cc, valid_page, total_isolated, false); + update_pageblock_skip(cc, valid_page, total_isolated, true, + false); count_compact_events(COMPACTFREE_SCANNED, nr_scanned); if (total_isolated) @@ -458,7 +472,7 @@ isolate_migratepages_range(struct zone *zone, struct compact_control *cc, unsigned long flags; bool locked = false; struct page *page = NULL, *valid_page = NULL; - bool skipped_async_unsuitable = false; + bool set_unsuitable = true; const isolate_mode_t mode = (!cc->sync ? ISOLATE_ASYNC_MIGRATE : 0) | (unevictable ? ISOLATE_UNEVICTABLE : 0); @@ -535,8 +549,7 @@ isolate_migratepages_range(struct zone *zone, struct compact_control *cc, */ mt = get_pageblock_migratetype(page); if (!cc->sync && !migrate_async_suitable(mt)) { - cc->finished_update_migrate = true; - skipped_async_unsuitable = true; + set_unsuitable = false; goto next_pageblock; } } @@ -640,11 +653,10 @@ next_pageblock: /* * Update the pageblock-skip information and cached scanner pfn, * if the whole pageblock was scanned without isolating any page. - * This is not done when pageblock was skipped due to being unsuitable - * for async compaction, so that eventual sync compaction can try. */ - if (low_pfn == end_pfn && !skipped_async_unsuitable) - update_pageblock_skip(cc, valid_page, nr_isolated, true); + if (low_pfn == end_pfn) + update_pageblock_skip(cc, valid_page, nr_isolated, + set_unsuitable, true); trace_mm_compaction_isolate_migratepages(nr_scanned, nr_isolated); @@ -868,7 +880,8 @@ static int compact_finished(struct zone *zone, /* Compaction run completes if the migrate and free scanner meet */ if (cc->free_pfn <= cc->migrate_pfn) { /* Let the next compaction start anew. */ - zone->compact_cached_migrate_pfn = zone->zone_start_pfn; + zone->compact_cached_migrate_pfn[0] = zone->zone_start_pfn; + zone->compact_cached_migrate_pfn[1] = zone->zone_start_pfn; zone->compact_cached_free_pfn = zone_end_pfn(zone); /* @@ -993,7 +1006,7 @@ static int compact_zone(struct zone *zone, struct compact_control *cc) * information on where the scanners should start but check that it * is initialised by ensuring the values are within zone boundaries. */ - cc->migrate_pfn = zone->compact_cached_migrate_pfn; + cc->migrate_pfn = zone->compact_cached_migrate_pfn[cc->sync]; cc->free_pfn = zone->compact_cached_free_pfn; if (cc->free_pfn < start_pfn || cc->free_pfn > end_pfn) { cc->free_pfn = end_pfn & ~(pageblock_nr_pages-1); @@ -1001,7 +1014,8 @@ static int compact_zone(struct zone *zone, struct compact_control *cc) } if (cc->migrate_pfn < start_pfn || cc->migrate_pfn > end_pfn) { cc->migrate_pfn = start_pfn; - zone->compact_cached_migrate_pfn = cc->migrate_pfn; + zone->compact_cached_migrate_pfn[0] = cc->migrate_pfn; + zone->compact_cached_migrate_pfn[1] = cc->migrate_pfn; } trace_mm_compaction_begin(start_pfn, cc->migrate_pfn, cc->free_pfn, end_pfn); -- cgit v1.2.3-71-gd317 From e0b9daeb453e602a95ea43853dc12d385558ce1f Mon Sep 17 00:00:00 2001 From: David Rientjes Date: Wed, 4 Jun 2014 16:08:28 -0700 Subject: mm, compaction: embed migration mode in compact_control We're going to want to manipulate the migration mode for compaction in the page allocator, and currently compact_control's sync field is only a bool. Currently, we only do MIGRATE_ASYNC or MIGRATE_SYNC_LIGHT compaction depending on the value of this bool. Convert the bool to enum migrate_mode and pass the migration mode in directly. Later, we'll want to avoid MIGRATE_SYNC_LIGHT for thp allocations in the pagefault patch to avoid unnecessary latency. This also alters compaction triggered from sysfs, either for the entire system or for a node, to force MIGRATE_SYNC. [akpm@linux-foundation.org: fix build] [iamjoonsoo.kim@lge.com: use MIGRATE_SYNC in alloc_contig_range()] Signed-off-by: David Rientjes Suggested-by: Mel Gorman Acked-by: Vlastimil Babka Cc: Greg Thelen Cc: Naoya Horiguchi Signed-off-by: Joonsoo Kim Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/compaction.h | 4 ++-- mm/compaction.c | 36 +++++++++++++++++++----------------- mm/internal.h | 2 +- mm/page_alloc.c | 39 +++++++++++++++++---------------------- 4 files changed, 39 insertions(+), 42 deletions(-) (limited to 'include/linux') diff --git a/include/linux/compaction.h b/include/linux/compaction.h index 7e1c76e3cd68..01e3132820da 100644 --- a/include/linux/compaction.h +++ b/include/linux/compaction.h @@ -22,7 +22,7 @@ extern int sysctl_extfrag_handler(struct ctl_table *table, int write, extern int fragmentation_index(struct zone *zone, unsigned int order); extern unsigned long try_to_compact_pages(struct zonelist *zonelist, int order, gfp_t gfp_mask, nodemask_t *mask, - bool sync, bool *contended); + enum migrate_mode mode, bool *contended); extern void compact_pgdat(pg_data_t *pgdat, int order); extern void reset_isolation_suitable(pg_data_t *pgdat); extern unsigned long compaction_suitable(struct zone *zone, int order); @@ -91,7 +91,7 @@ static inline bool compaction_restarting(struct zone *zone, int order) #else static inline unsigned long try_to_compact_pages(struct zonelist *zonelist, int order, gfp_t gfp_mask, nodemask_t *nodemask, - bool sync, bool *contended) + enum migrate_mode mode, bool *contended) { return COMPACT_CONTINUE; } diff --git a/mm/compaction.c b/mm/compaction.c index 70c0f8cda33f..217a6ad9a20e 100644 --- a/mm/compaction.c +++ b/mm/compaction.c @@ -161,7 +161,8 @@ static void update_pageblock_skip(struct compact_control *cc, return; if (pfn > zone->compact_cached_migrate_pfn[0]) zone->compact_cached_migrate_pfn[0] = pfn; - if (cc->sync && pfn > zone->compact_cached_migrate_pfn[1]) + if (cc->mode != MIGRATE_ASYNC && + pfn > zone->compact_cached_migrate_pfn[1]) zone->compact_cached_migrate_pfn[1] = pfn; } else { if (cc->finished_update_free) @@ -208,7 +209,7 @@ static bool compact_checklock_irqsave(spinlock_t *lock, unsigned long *flags, } /* async aborts if taking too long or contended */ - if (!cc->sync) { + if (cc->mode == MIGRATE_ASYNC) { cc->contended = true; return false; } @@ -473,7 +474,8 @@ isolate_migratepages_range(struct zone *zone, struct compact_control *cc, bool locked = false; struct page *page = NULL, *valid_page = NULL; bool set_unsuitable = true; - const isolate_mode_t mode = (!cc->sync ? ISOLATE_ASYNC_MIGRATE : 0) | + const isolate_mode_t mode = (cc->mode == MIGRATE_ASYNC ? + ISOLATE_ASYNC_MIGRATE : 0) | (unevictable ? ISOLATE_UNEVICTABLE : 0); /* @@ -483,7 +485,7 @@ isolate_migratepages_range(struct zone *zone, struct compact_control *cc, */ while (unlikely(too_many_isolated(zone))) { /* async migration should just abort */ - if (!cc->sync) + if (cc->mode == MIGRATE_ASYNC) return 0; congestion_wait(BLK_RW_ASYNC, HZ/10); @@ -548,7 +550,8 @@ isolate_migratepages_range(struct zone *zone, struct compact_control *cc, * the minimum amount of work satisfies the allocation */ mt = get_pageblock_migratetype(page); - if (!cc->sync && !migrate_async_suitable(mt)) { + if (cc->mode == MIGRATE_ASYNC && + !migrate_async_suitable(mt)) { set_unsuitable = false; goto next_pageblock; } @@ -981,6 +984,7 @@ static int compact_zone(struct zone *zone, struct compact_control *cc) int ret; unsigned long start_pfn = zone->zone_start_pfn; unsigned long end_pfn = zone_end_pfn(zone); + const bool sync = cc->mode != MIGRATE_ASYNC; ret = compaction_suitable(zone, cc->order); switch (ret) { @@ -1006,7 +1010,7 @@ static int compact_zone(struct zone *zone, struct compact_control *cc) * information on where the scanners should start but check that it * is initialised by ensuring the values are within zone boundaries. */ - cc->migrate_pfn = zone->compact_cached_migrate_pfn[cc->sync]; + cc->migrate_pfn = zone->compact_cached_migrate_pfn[sync]; cc->free_pfn = zone->compact_cached_free_pfn; if (cc->free_pfn < start_pfn || cc->free_pfn > end_pfn) { cc->free_pfn = end_pfn & ~(pageblock_nr_pages-1); @@ -1040,8 +1044,7 @@ static int compact_zone(struct zone *zone, struct compact_control *cc) nr_migrate = cc->nr_migratepages; err = migrate_pages(&cc->migratepages, compaction_alloc, - compaction_free, (unsigned long)cc, - cc->sync ? MIGRATE_SYNC_LIGHT : MIGRATE_ASYNC, + compaction_free, (unsigned long)cc, cc->mode, MR_COMPACTION); update_nr_listpages(cc); nr_remaining = cc->nr_migratepages; @@ -1074,9 +1077,8 @@ out: return ret; } -static unsigned long compact_zone_order(struct zone *zone, - int order, gfp_t gfp_mask, - bool sync, bool *contended) +static unsigned long compact_zone_order(struct zone *zone, int order, + gfp_t gfp_mask, enum migrate_mode mode, bool *contended) { unsigned long ret; struct compact_control cc = { @@ -1085,7 +1087,7 @@ static unsigned long compact_zone_order(struct zone *zone, .order = order, .migratetype = allocflags_to_migratetype(gfp_mask), .zone = zone, - .sync = sync, + .mode = mode, }; INIT_LIST_HEAD(&cc.freepages); INIT_LIST_HEAD(&cc.migratepages); @@ -1107,7 +1109,7 @@ int sysctl_extfrag_threshold = 500; * @order: The order of the current allocation * @gfp_mask: The GFP mask of the current allocation * @nodemask: The allowed nodes to allocate from - * @sync: Whether migration is synchronous or not + * @mode: The migration mode for async, sync light, or sync migration * @contended: Return value that is true if compaction was aborted due to lock contention * @page: Optionally capture a free page of the requested order during compaction * @@ -1115,7 +1117,7 @@ int sysctl_extfrag_threshold = 500; */ unsigned long try_to_compact_pages(struct zonelist *zonelist, int order, gfp_t gfp_mask, nodemask_t *nodemask, - bool sync, bool *contended) + enum migrate_mode mode, bool *contended) { enum zone_type high_zoneidx = gfp_zone(gfp_mask); int may_enter_fs = gfp_mask & __GFP_FS; @@ -1140,7 +1142,7 @@ unsigned long try_to_compact_pages(struct zonelist *zonelist, nodemask) { int status; - status = compact_zone_order(zone, order, gfp_mask, sync, + status = compact_zone_order(zone, order, gfp_mask, mode, contended); rc = max(status, rc); @@ -1190,7 +1192,7 @@ void compact_pgdat(pg_data_t *pgdat, int order) { struct compact_control cc = { .order = order, - .sync = false, + .mode = MIGRATE_ASYNC, }; if (!order) @@ -1203,7 +1205,7 @@ static void compact_node(int nid) { struct compact_control cc = { .order = -1, - .sync = true, + .mode = MIGRATE_SYNC, .ignore_skip_hint = true, }; diff --git a/mm/internal.h b/mm/internal.h index 6ee580d69ddd..a25424a24e0c 100644 --- a/mm/internal.h +++ b/mm/internal.h @@ -134,7 +134,7 @@ struct compact_control { unsigned long nr_migratepages; /* Number of pages to migrate */ unsigned long free_pfn; /* isolate_freepages search base */ unsigned long migrate_pfn; /* isolate_migratepages search base */ - bool sync; /* Synchronous migration */ + enum migrate_mode mode; /* Async or sync migration mode */ bool ignore_skip_hint; /* Scan blocks even if marked skip */ bool finished_update_free; /* True when the zone cached pfns are * no longer being updated diff --git a/mm/page_alloc.c b/mm/page_alloc.c index 027d0294413a..afb29da0576c 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -2217,7 +2217,7 @@ static struct page * __alloc_pages_direct_compact(gfp_t gfp_mask, unsigned int order, struct zonelist *zonelist, enum zone_type high_zoneidx, nodemask_t *nodemask, int alloc_flags, struct zone *preferred_zone, - int migratetype, bool sync_migration, + int migratetype, enum migrate_mode mode, bool *contended_compaction, bool *deferred_compaction, unsigned long *did_some_progress) { @@ -2231,7 +2231,7 @@ __alloc_pages_direct_compact(gfp_t gfp_mask, unsigned int order, current->flags |= PF_MEMALLOC; *did_some_progress = try_to_compact_pages(zonelist, order, gfp_mask, - nodemask, sync_migration, + nodemask, mode, contended_compaction); current->flags &= ~PF_MEMALLOC; @@ -2264,7 +2264,7 @@ __alloc_pages_direct_compact(gfp_t gfp_mask, unsigned int order, * As async compaction considers a subset of pageblocks, only * defer if the failure was a sync compaction failure. */ - if (sync_migration) + if (mode != MIGRATE_ASYNC) defer_compaction(preferred_zone, order); cond_resched(); @@ -2277,9 +2277,8 @@ static inline struct page * __alloc_pages_direct_compact(gfp_t gfp_mask, unsigned int order, struct zonelist *zonelist, enum zone_type high_zoneidx, nodemask_t *nodemask, int alloc_flags, struct zone *preferred_zone, - int migratetype, bool sync_migration, - bool *contended_compaction, bool *deferred_compaction, - unsigned long *did_some_progress) + int migratetype, enum migrate_mode mode, bool *contended_compaction, + bool *deferred_compaction, unsigned long *did_some_progress) { return NULL; } @@ -2474,7 +2473,7 @@ __alloc_pages_slowpath(gfp_t gfp_mask, unsigned int order, int alloc_flags; unsigned long pages_reclaimed = 0; unsigned long did_some_progress; - bool sync_migration = false; + enum migrate_mode migration_mode = MIGRATE_ASYNC; bool deferred_compaction = false; bool contended_compaction = false; @@ -2568,17 +2567,15 @@ rebalance: * Try direct compaction. The first pass is asynchronous. Subsequent * attempts after direct reclaim are synchronous */ - page = __alloc_pages_direct_compact(gfp_mask, order, - zonelist, high_zoneidx, - nodemask, - alloc_flags, preferred_zone, - migratetype, sync_migration, - &contended_compaction, + page = __alloc_pages_direct_compact(gfp_mask, order, zonelist, + high_zoneidx, nodemask, alloc_flags, + preferred_zone, migratetype, + migration_mode, &contended_compaction, &deferred_compaction, &did_some_progress); if (page) goto got_pg; - sync_migration = true; + migration_mode = MIGRATE_SYNC_LIGHT; /* * If compaction is deferred for high-order allocations, it is because @@ -2653,12 +2650,10 @@ rebalance: * direct reclaim and reclaim/compaction depends on compaction * being called after reclaim so call directly if necessary */ - page = __alloc_pages_direct_compact(gfp_mask, order, - zonelist, high_zoneidx, - nodemask, - alloc_flags, preferred_zone, - migratetype, sync_migration, - &contended_compaction, + page = __alloc_pages_direct_compact(gfp_mask, order, zonelist, + high_zoneidx, nodemask, alloc_flags, + preferred_zone, migratetype, + migration_mode, &contended_compaction, &deferred_compaction, &did_some_progress); if (page) @@ -6218,7 +6213,7 @@ static int __alloc_contig_migrate_range(struct compact_control *cc, cc->nr_migratepages -= nr_reclaimed; ret = migrate_pages(&cc->migratepages, alloc_migrate_target, - NULL, 0, MIGRATE_SYNC, MR_CMA); + NULL, 0, cc->mode, MR_CMA); } if (ret < 0) { putback_movable_pages(&cc->migratepages); @@ -6257,7 +6252,7 @@ int alloc_contig_range(unsigned long start, unsigned long end, .nr_migratepages = 0, .order = -1, .zone = page_zone(pfn_to_page(start)), - .sync = true, + .mode = MIGRATE_SYNC, .ignore_skip_hint = true, }; INIT_LIST_HEAD(&cc.migratepages); -- cgit v1.2.3-71-gd317 From adfab836f4908deb049a5128082719e689eed964 Mon Sep 17 00:00:00 2001 From: Dan Streetman Date: Wed, 4 Jun 2014 16:09:53 -0700 Subject: swap: change swap_info singly-linked list to list_head The logic controlling the singly-linked list of swap_info_struct entries for all active, i.e. swapon'ed, swap targets is rather complex, because: - it stores the entries in priority order - there is a pointer to the highest priority entry - there is a pointer to the highest priority not-full entry - there is a highest_priority_index variable set outside the swap_lock - swap entries of equal priority should be used equally this complexity leads to bugs such as: https://lkml.org/lkml/2014/2/13/181 where different priority swap targets are incorrectly used equally. That bug probably could be solved with the existing singly-linked lists, but I think it would only add more complexity to the already difficult to understand get_swap_page() swap_list iteration logic. The first patch changes from a singly-linked list to a doubly-linked list using list_heads; the highest_priority_index and related code are removed and get_swap_page() starts each iteration at the highest priority swap_info entry, even if it's full. While this does introduce unnecessary list iteration (i.e. Schlemiel the painter's algorithm) in the case where one or more of the highest priority entries are full, the iteration and manipulation code is much simpler and behaves correctly re: the above bug; and the fourth patch removes the unnecessary iteration. The second patch adds some minor plist helper functions; nothing new really, just functions to match existing regular list functions. These are used by the next two patches. The third patch adds plist_requeue(), which is used by get_swap_page() in the next patch - it performs the requeueing of same-priority entries (which moves the entry to the end of its priority in the plist), so that all equal-priority swap_info_structs get used equally. The fourth patch converts the main list into a plist, and adds a new plist that contains only swap_info entries that are both active and not full. As Mel suggested using plists allows removing all the ordering code from swap - plists handle ordering automatically. The list naming is also clarified now that there are two lists, with the original list changed from swap_list_head to swap_active_head and the new list named swap_avail_head. A new spinlock is also added for the new list, so swap_info entries can be added or removed from the new list immediately as they become full or not full. This patch (of 4): Replace the singly-linked list tracking active, i.e. swapon'ed, swap_info_struct entries with a doubly-linked list using struct list_heads. Simplify the logic iterating and manipulating the list of entries, especially get_swap_page(), by using standard list_head functions, and removing the highest priority iteration logic. The change fixes the bug: https://lkml.org/lkml/2014/2/13/181 in which different priority swap entries after the highest priority entry are incorrectly used equally in pairs. The swap behavior is now as advertised, i.e. different priority swap entries are used in order, and equal priority swap targets are used concurrently. Signed-off-by: Dan Streetman Acked-by: Mel Gorman Cc: Shaohua Li Cc: Hugh Dickins Cc: Dan Streetman Cc: Michal Hocko Cc: Christian Ehrhardt Cc: Weijie Yang Cc: Rik van Riel Cc: Johannes Weiner Cc: Bob Liu Cc: Steven Rostedt Cc: Peter Zijlstra Cc: Paul Gortmaker Cc: Thomas Gleixner Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/swap.h | 7 +- include/linux/swapfile.h | 2 +- mm/frontswap.c | 13 ++-- mm/swapfile.c | 171 ++++++++++++++++++++--------------------------- 4 files changed, 78 insertions(+), 115 deletions(-) (limited to 'include/linux') diff --git a/include/linux/swap.h b/include/linux/swap.h index 5a14b928164e..8bb85d6d65f0 100644 --- a/include/linux/swap.h +++ b/include/linux/swap.h @@ -214,8 +214,8 @@ struct percpu_cluster { struct swap_info_struct { unsigned long flags; /* SWP_USED etc: see above */ signed short prio; /* swap priority of this type */ + struct list_head list; /* entry in swap list */ signed char type; /* strange name for an index */ - signed char next; /* next type on the swap list */ unsigned int max; /* extent of the swap_map */ unsigned char *swap_map; /* vmalloc'ed array of usage counts */ struct swap_cluster_info *cluster_info; /* cluster info. Only for SSD */ @@ -255,11 +255,6 @@ struct swap_info_struct { struct swap_cluster_info discard_cluster_tail; /* list tail of discard clusters */ }; -struct swap_list_t { - int head; /* head of priority-ordered swapfile list */ - int next; /* swapfile to be used next */ -}; - /* linux/mm/workingset.c */ void *workingset_eviction(struct address_space *mapping, struct page *page); bool workingset_refault(void *shadow); diff --git a/include/linux/swapfile.h b/include/linux/swapfile.h index e282624e8c10..2eab382d593d 100644 --- a/include/linux/swapfile.h +++ b/include/linux/swapfile.h @@ -6,7 +6,7 @@ * want to expose them to the dozens of source files that include swap.h */ extern spinlock_t swap_lock; -extern struct swap_list_t swap_list; +extern struct list_head swap_list_head; extern struct swap_info_struct *swap_info[]; extern int try_to_unuse(unsigned int, bool, unsigned long); diff --git a/mm/frontswap.c b/mm/frontswap.c index 1b24bdcb3197..fae11602e8a9 100644 --- a/mm/frontswap.c +++ b/mm/frontswap.c @@ -327,15 +327,12 @@ EXPORT_SYMBOL(__frontswap_invalidate_area); static unsigned long __frontswap_curr_pages(void) { - int type; unsigned long totalpages = 0; struct swap_info_struct *si = NULL; assert_spin_locked(&swap_lock); - for (type = swap_list.head; type >= 0; type = si->next) { - si = swap_info[type]; + list_for_each_entry(si, &swap_list_head, list) totalpages += atomic_read(&si->frontswap_pages); - } return totalpages; } @@ -347,11 +344,9 @@ static int __frontswap_unuse_pages(unsigned long total, unsigned long *unused, int si_frontswap_pages; unsigned long total_pages_to_unuse = total; unsigned long pages = 0, pages_to_unuse = 0; - int type; assert_spin_locked(&swap_lock); - for (type = swap_list.head; type >= 0; type = si->next) { - si = swap_info[type]; + list_for_each_entry(si, &swap_list_head, list) { si_frontswap_pages = atomic_read(&si->frontswap_pages); if (total_pages_to_unuse < si_frontswap_pages) { pages = pages_to_unuse = total_pages_to_unuse; @@ -366,7 +361,7 @@ static int __frontswap_unuse_pages(unsigned long total, unsigned long *unused, } vm_unacct_memory(pages); *unused = pages_to_unuse; - *swapid = type; + *swapid = si->type; ret = 0; break; } @@ -413,7 +408,7 @@ void frontswap_shrink(unsigned long target_pages) /* * we don't want to hold swap_lock while doing a very * lengthy try_to_unuse, but swap_list may change - * so restart scan from swap_list.head each time + * so restart scan from swap_list_head each time */ spin_lock(&swap_lock); ret = __frontswap_shrink(target_pages, &pages_to_unuse, &type); diff --git a/mm/swapfile.c b/mm/swapfile.c index 4a7f7e6992b6..6c95a8c63b1a 100644 --- a/mm/swapfile.c +++ b/mm/swapfile.c @@ -51,14 +51,17 @@ atomic_long_t nr_swap_pages; /* protected with swap_lock. reading in vm_swap_full() doesn't need lock */ long total_swap_pages; static int least_priority; -static atomic_t highest_priority_index = ATOMIC_INIT(-1); static const char Bad_file[] = "Bad swap file entry "; static const char Unused_file[] = "Unused swap file entry "; static const char Bad_offset[] = "Bad swap offset entry "; static const char Unused_offset[] = "Unused swap offset entry "; -struct swap_list_t swap_list = {-1, -1}; +/* + * all active swap_info_structs + * protected with swap_lock, and ordered by priority. + */ +LIST_HEAD(swap_list_head); struct swap_info_struct *swap_info[MAX_SWAPFILES]; @@ -640,66 +643,54 @@ no_page: swp_entry_t get_swap_page(void) { - struct swap_info_struct *si; + struct swap_info_struct *si, *next; pgoff_t offset; - int type, next; - int wrapped = 0; - int hp_index; + struct list_head *tmp; spin_lock(&swap_lock); if (atomic_long_read(&nr_swap_pages) <= 0) goto noswap; atomic_long_dec(&nr_swap_pages); - for (type = swap_list.next; type >= 0 && wrapped < 2; type = next) { - hp_index = atomic_xchg(&highest_priority_index, -1); - /* - * highest_priority_index records current highest priority swap - * type which just frees swap entries. If its priority is - * higher than that of swap_list.next swap type, we use it. It - * isn't protected by swap_lock, so it can be an invalid value - * if the corresponding swap type is swapoff. We double check - * the flags here. It's even possible the swap type is swapoff - * and swapon again and its priority is changed. In such rare - * case, low prority swap type might be used, but eventually - * high priority swap will be used after several rounds of - * swap. - */ - if (hp_index != -1 && hp_index != type && - swap_info[type]->prio < swap_info[hp_index]->prio && - (swap_info[hp_index]->flags & SWP_WRITEOK)) { - type = hp_index; - swap_list.next = type; - } - - si = swap_info[type]; - next = si->next; - if (next < 0 || - (!wrapped && si->prio != swap_info[next]->prio)) { - next = swap_list.head; - wrapped++; - } - + list_for_each(tmp, &swap_list_head) { + si = list_entry(tmp, typeof(*si), list); spin_lock(&si->lock); - if (!si->highest_bit) { - spin_unlock(&si->lock); - continue; - } - if (!(si->flags & SWP_WRITEOK)) { + if (!si->highest_bit || !(si->flags & SWP_WRITEOK)) { spin_unlock(&si->lock); continue; } - swap_list.next = next; + /* + * rotate the current swap_info that we're going to use + * to after any other swap_info that have the same prio, + * so that all equal-priority swap_info get used equally + */ + next = si; + list_for_each_entry_continue(next, &swap_list_head, list) { + if (si->prio != next->prio) + break; + list_rotate_left(&si->list); + next = si; + } spin_unlock(&swap_lock); /* This is called for allocating swap entry for cache */ offset = scan_swap_map(si, SWAP_HAS_CACHE); spin_unlock(&si->lock); if (offset) - return swp_entry(type, offset); + return swp_entry(si->type, offset); spin_lock(&swap_lock); - next = swap_list.next; + /* + * if we got here, it's likely that si was almost full before, + * and since scan_swap_map() can drop the si->lock, multiple + * callers probably all tried to get a page from the same si + * and it filled up before we could get one. So we need to + * try again. Since we dropped the swap_lock, there may now + * be non-full higher priority swap_infos, and this si may have + * even been removed from the list (although very unlikely). + * Let's start over. + */ + tmp = &swap_list_head; } atomic_long_inc(&nr_swap_pages); @@ -766,27 +757,6 @@ out: return NULL; } -/* - * This swap type frees swap entry, check if it is the highest priority swap - * type which just frees swap entry. get_swap_page() uses - * highest_priority_index to search highest priority swap type. The - * swap_info_struct.lock can't protect us if there are multiple swap types - * active, so we use atomic_cmpxchg. - */ -static void set_highest_priority_index(int type) -{ - int old_hp_index, new_hp_index; - - do { - old_hp_index = atomic_read(&highest_priority_index); - if (old_hp_index != -1 && - swap_info[old_hp_index]->prio >= swap_info[type]->prio) - break; - new_hp_index = type; - } while (atomic_cmpxchg(&highest_priority_index, - old_hp_index, new_hp_index) != old_hp_index); -} - static unsigned char swap_entry_free(struct swap_info_struct *p, swp_entry_t entry, unsigned char usage) { @@ -830,7 +800,6 @@ static unsigned char swap_entry_free(struct swap_info_struct *p, p->lowest_bit = offset; if (offset > p->highest_bit) p->highest_bit = offset; - set_highest_priority_index(p->type); atomic_long_inc(&nr_swap_pages); p->inuse_pages--; frontswap_invalidate_page(p->type, offset); @@ -1765,7 +1734,7 @@ static void _enable_swap_info(struct swap_info_struct *p, int prio, unsigned char *swap_map, struct swap_cluster_info *cluster_info) { - int i, prev; + struct swap_info_struct *si; if (prio >= 0) p->prio = prio; @@ -1777,18 +1746,28 @@ static void _enable_swap_info(struct swap_info_struct *p, int prio, atomic_long_add(p->pages, &nr_swap_pages); total_swap_pages += p->pages; - /* insert swap space into swap_list: */ - prev = -1; - for (i = swap_list.head; i >= 0; i = swap_info[i]->next) { - if (p->prio >= swap_info[i]->prio) - break; - prev = i; + assert_spin_locked(&swap_lock); + BUG_ON(!list_empty(&p->list)); + /* + * insert into swap list; the list is in priority order, + * so that get_swap_page() can get a page from the highest + * priority swap_info_struct with available page(s), and + * swapoff can adjust the auto-assigned (i.e. negative) prio + * values for any lower-priority swap_info_structs when + * removing a negative-prio swap_info_struct + */ + list_for_each_entry(si, &swap_list_head, list) { + if (p->prio >= si->prio) { + list_add_tail(&p->list, &si->list); + return; + } } - p->next = i; - if (prev < 0) - swap_list.head = swap_list.next = p->type; - else - swap_info[prev]->next = p->type; + /* + * this covers two cases: + * 1) p->prio is less than all existing prio + * 2) the swap list is empty + */ + list_add_tail(&p->list, &swap_list_head); } static void enable_swap_info(struct swap_info_struct *p, int prio, @@ -1823,8 +1802,7 @@ SYSCALL_DEFINE1(swapoff, const char __user *, specialfile) struct address_space *mapping; struct inode *inode; struct filename *pathname; - int i, type, prev; - int err; + int err, found = 0; unsigned int old_block_size; if (!capable(CAP_SYS_ADMIN)) @@ -1842,17 +1820,16 @@ SYSCALL_DEFINE1(swapoff, const char __user *, specialfile) goto out; mapping = victim->f_mapping; - prev = -1; spin_lock(&swap_lock); - for (type = swap_list.head; type >= 0; type = swap_info[type]->next) { - p = swap_info[type]; + list_for_each_entry(p, &swap_list_head, list) { if (p->flags & SWP_WRITEOK) { - if (p->swap_file->f_mapping == mapping) + if (p->swap_file->f_mapping == mapping) { + found = 1; break; + } } - prev = type; } - if (type < 0) { + if (!found) { err = -EINVAL; spin_unlock(&swap_lock); goto out_dput; @@ -1864,20 +1841,16 @@ SYSCALL_DEFINE1(swapoff, const char __user *, specialfile) spin_unlock(&swap_lock); goto out_dput; } - if (prev < 0) - swap_list.head = p->next; - else - swap_info[prev]->next = p->next; - if (type == swap_list.next) { - /* just pick something that's safe... */ - swap_list.next = swap_list.head; - } spin_lock(&p->lock); if (p->prio < 0) { - for (i = p->next; i >= 0; i = swap_info[i]->next) - swap_info[i]->prio = p->prio--; + struct swap_info_struct *si = p; + + list_for_each_entry_continue(si, &swap_list_head, list) { + si->prio++; + } least_priority++; } + list_del_init(&p->list); atomic_long_sub(p->pages, &nr_swap_pages); total_swap_pages -= p->pages; p->flags &= ~SWP_WRITEOK; @@ -1885,7 +1858,7 @@ SYSCALL_DEFINE1(swapoff, const char __user *, specialfile) spin_unlock(&swap_lock); set_current_oom_origin(); - err = try_to_unuse(type, false, 0); /* force all pages to be unused */ + err = try_to_unuse(p->type, false, 0); /* force unuse all pages */ clear_current_oom_origin(); if (err) { @@ -1926,7 +1899,7 @@ SYSCALL_DEFINE1(swapoff, const char __user *, specialfile) frontswap_map = frontswap_map_get(p); spin_unlock(&p->lock); spin_unlock(&swap_lock); - frontswap_invalidate_area(type); + frontswap_invalidate_area(p->type); frontswap_map_set(p, NULL); mutex_unlock(&swapon_mutex); free_percpu(p->percpu_cluster); @@ -1935,7 +1908,7 @@ SYSCALL_DEFINE1(swapoff, const char __user *, specialfile) vfree(cluster_info); vfree(frontswap_map); /* Destroy swap account information */ - swap_cgroup_swapoff(type); + swap_cgroup_swapoff(p->type); inode = mapping->host; if (S_ISBLK(inode->i_mode)) { @@ -2142,8 +2115,8 @@ static struct swap_info_struct *alloc_swap_info(void) */ } INIT_LIST_HEAD(&p->first_swap_extent.list); + INIT_LIST_HEAD(&p->list); p->flags = SWP_USED; - p->next = -1; spin_unlock(&swap_lock); spin_lock_init(&p->lock); -- cgit v1.2.3-71-gd317 From fd16618e12a05df79a3439d72d5ffdac5d34f3da Mon Sep 17 00:00:00 2001 From: Dan Streetman Date: Wed, 4 Jun 2014 16:09:55 -0700 Subject: lib/plist: add helper functions Add PLIST_HEAD() to plist.h, equivalent to LIST_HEAD() from list.h, to define and initialize a struct plist_head. Add plist_for_each_continue() and plist_for_each_entry_continue(), equivalent to list_for_each_continue() and list_for_each_entry_continue(), to iterate over a plist continuing after the current position. Add plist_prev() and plist_next(), equivalent to (struct list_head*)->prev and ->next, implemented by list_prev_entry() and list_next_entry(), to access the prev/next struct plist_node entry. These are needed because unlike struct list_head, direct access of the prev/next struct plist_node isn't possible; the list must be navigated via the contained struct list_head. e.g. instead of accessing the prev by list_prev_entry(node, node_list) it can be accessed by plist_prev(node). Signed-off-by: Dan Streetman Acked-by: Mel Gorman Cc: Paul Gortmaker Cc: Steven Rostedt Cc: Thomas Gleixner Cc: Shaohua Li Cc: Hugh Dickins Cc: Dan Streetman Cc: Michal Hocko Cc: Christian Ehrhardt Cc: Weijie Yang Cc: Rik van Riel Cc: Johannes Weiner Cc: Bob Liu Cc: Peter Zijlstra Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/plist.h | 43 +++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 43 insertions(+) (limited to 'include/linux') diff --git a/include/linux/plist.h b/include/linux/plist.h index aa0fb390bd29..c81549119bd4 100644 --- a/include/linux/plist.h +++ b/include/linux/plist.h @@ -97,6 +97,13 @@ struct plist_node { .node_list = LIST_HEAD_INIT((head).node_list) \ } +/** + * PLIST_HEAD - declare and init plist_head + * @head: name for struct plist_head variable + */ +#define PLIST_HEAD(head) \ + struct plist_head head = PLIST_HEAD_INIT(head) + /** * PLIST_NODE_INIT - static struct plist_node initializer * @node: struct plist_node variable name @@ -142,6 +149,16 @@ extern void plist_del(struct plist_node *node, struct plist_head *head); #define plist_for_each(pos, head) \ list_for_each_entry(pos, &(head)->node_list, node_list) +/** + * plist_for_each_continue - continue iteration over the plist + * @pos: the type * to use as a loop cursor + * @head: the head for your list + * + * Continue to iterate over plist, continuing after the current position. + */ +#define plist_for_each_continue(pos, head) \ + list_for_each_entry_continue(pos, &(head)->node_list, node_list) + /** * plist_for_each_safe - iterate safely over a plist of given type * @pos: the type * to use as a loop counter @@ -162,6 +179,18 @@ extern void plist_del(struct plist_node *node, struct plist_head *head); #define plist_for_each_entry(pos, head, mem) \ list_for_each_entry(pos, &(head)->node_list, mem.node_list) +/** + * plist_for_each_entry_continue - continue iteration over list of given type + * @pos: the type * to use as a loop cursor + * @head: the head for your list + * @m: the name of the list_struct within the struct + * + * Continue to iterate over list of given type, continuing after + * the current position. + */ +#define plist_for_each_entry_continue(pos, head, m) \ + list_for_each_entry_continue(pos, &(head)->node_list, m.node_list) + /** * plist_for_each_entry_safe - iterate safely over list of given type * @pos: the type * to use as a loop counter @@ -228,6 +257,20 @@ static inline int plist_node_empty(const struct plist_node *node) container_of(plist_last(head), type, member) #endif +/** + * plist_next - get the next entry in list + * @pos: the type * to cursor + */ +#define plist_next(pos) \ + list_next_entry(pos, node_list) + +/** + * plist_prev - get the prev entry in list + * @pos: the type * to cursor + */ +#define plist_prev(pos) \ + list_prev_entry(pos, node_list) + /** * plist_first - return the first node (and thus, highest priority) * @head: the &struct plist_head pointer -- cgit v1.2.3-71-gd317 From a75f232ce0fe38bd01301899ecd97ffd0254316a Mon Sep 17 00:00:00 2001 From: Dan Streetman Date: Wed, 4 Jun 2014 16:09:57 -0700 Subject: lib/plist: add plist_requeue Add plist_requeue(), which moves the specified plist_node after all other same-priority plist_nodes in the list. This is essentially an optimized plist_del() followed by plist_add(). This is needed by swap, which (with the next patch in this set) uses a plist of available swap devices. When a swap device (either a swap partition or swap file) are added to the system with swapon(), the device is added to a plist, ordered by the swap device's priority. When swap needs to allocate a page from one of the swap devices, it takes the page from the first swap device on the plist, which is the highest priority swap device. The swap device is left in the plist until all its pages are used, and then removed from the plist when it becomes full. However, as described in man 2 swapon, swap must allocate pages from swap devices with the same priority in round-robin order; to do this, on each swap page allocation, swap uses a page from the first swap device in the plist, and then calls plist_requeue() to move that swap device entry to after any other same-priority swap devices. The next swap page allocation will again use a page from the first swap device in the plist and requeue it, and so on, resulting in round-robin usage of equal-priority swap devices. Also add plist_test_requeue() test function, for use by plist_test() to test plist_requeue() function. Signed-off-by: Dan Streetman Cc: Steven Rostedt Cc: Peter Zijlstra Acked-by: Mel Gorman Cc: Paul Gortmaker Cc: Thomas Gleixner Cc: Shaohua Li Cc: Hugh Dickins Cc: Dan Streetman Cc: Michal Hocko Cc: Christian Ehrhardt Cc: Weijie Yang Cc: Rik van Riel Cc: Johannes Weiner Cc: Bob Liu Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/plist.h | 2 ++ lib/plist.c | 52 +++++++++++++++++++++++++++++++++++++++++++++++++++ 2 files changed, 54 insertions(+) (limited to 'include/linux') diff --git a/include/linux/plist.h b/include/linux/plist.h index c81549119bd4..8b6c970cff6c 100644 --- a/include/linux/plist.h +++ b/include/linux/plist.h @@ -141,6 +141,8 @@ static inline void plist_node_init(struct plist_node *node, int prio) extern void plist_add(struct plist_node *node, struct plist_head *head); extern void plist_del(struct plist_node *node, struct plist_head *head); +extern void plist_requeue(struct plist_node *node, struct plist_head *head); + /** * plist_for_each - iterate over the plist * @pos: the type * to use as a loop counter diff --git a/lib/plist.c b/lib/plist.c index 1ebc95f7a46f..0f2084d30798 100644 --- a/lib/plist.c +++ b/lib/plist.c @@ -134,6 +134,46 @@ void plist_del(struct plist_node *node, struct plist_head *head) plist_check_head(head); } +/** + * plist_requeue - Requeue @node at end of same-prio entries. + * + * This is essentially an optimized plist_del() followed by + * plist_add(). It moves an entry already in the plist to + * after any other same-priority entries. + * + * @node: &struct plist_node pointer - entry to be moved + * @head: &struct plist_head pointer - list head + */ +void plist_requeue(struct plist_node *node, struct plist_head *head) +{ + struct plist_node *iter; + struct list_head *node_next = &head->node_list; + + plist_check_head(head); + BUG_ON(plist_head_empty(head)); + BUG_ON(plist_node_empty(node)); + + if (node == plist_last(head)) + return; + + iter = plist_next(node); + + if (node->prio != iter->prio) + return; + + plist_del(node, head); + + plist_for_each_continue(iter, head) { + if (node->prio != iter->prio) { + node_next = &iter->node_list; + break; + } + } + list_add_tail(&node->node_list, node_next); + + plist_check_head(head); +} + #ifdef CONFIG_DEBUG_PI_LIST #include #include @@ -170,6 +210,14 @@ static void __init plist_test_check(int nr_expect) BUG_ON(prio_pos->prio_list.next != &first->prio_list); } +static void __init plist_test_requeue(struct plist_node *node) +{ + plist_requeue(node, &test_head); + + if (node != plist_last(&test_head)) + BUG_ON(node->prio == plist_next(node)->prio); +} + static int __init plist_test(void) { int nr_expect = 0, i, loop; @@ -193,6 +241,10 @@ static int __init plist_test(void) nr_expect--; } plist_test_check(nr_expect); + if (!plist_node_empty(test_node + i)) { + plist_test_requeue(test_node + i); + plist_test_check(nr_expect); + } } for (i = 0; i < ARRAY_SIZE(test_node); i++) { -- cgit v1.2.3-71-gd317 From 18ab4d4ced0817421e6db6940374cc39d28d65da Mon Sep 17 00:00:00 2001 From: Dan Streetman Date: Wed, 4 Jun 2014 16:09:59 -0700 Subject: swap: change swap_list_head to plist, add swap_avail_head Originally get_swap_page() started iterating through the singly-linked list of swap_info_structs using swap_list.next or highest_priority_index, which both were intended to point to the highest priority active swap target that was not full. The first patch in this series changed the singly-linked list to a doubly-linked list, and removed the logic to start at the highest priority non-full entry; it starts scanning at the highest priority entry each time, even if the entry is full. Replace the manually ordered swap_list_head with a plist, swap_active_head. Add a new plist, swap_avail_head. The original swap_active_head plist contains all active swap_info_structs, as before, while the new swap_avail_head plist contains only swap_info_structs that are active and available, i.e. not full. Add a new spinlock, swap_avail_lock, to protect the swap_avail_head list. Mel Gorman suggested using plists since they internally handle ordering the list entries based on priority, which is exactly what swap was doing manually. All the ordering code is now removed, and swap_info_struct entries and simply added to their corresponding plist and automatically ordered correctly. Using a new plist for available swap_info_structs simplifies and optimizes get_swap_page(), which no longer has to iterate over full swap_info_structs. Using a new spinlock for swap_avail_head plist allows each swap_info_struct to add or remove themselves from the plist when they become full or not-full; previously they could not do so because the swap_info_struct->lock is held when they change from full<->not-full, and the swap_lock protecting the main swap_active_head must be ordered before any swap_info_struct->lock. Signed-off-by: Dan Streetman Acked-by: Mel Gorman Cc: Shaohua Li Cc: Steven Rostedt Cc: Peter Zijlstra Cc: Hugh Dickins Cc: Dan Streetman Cc: Michal Hocko Cc: Christian Ehrhardt Cc: Weijie Yang Cc: Rik van Riel Cc: Johannes Weiner Cc: Bob Liu Cc: Paul Gortmaker Cc: Thomas Gleixner Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/swap.h | 3 +- include/linux/swapfile.h | 2 +- mm/frontswap.c | 6 +- mm/swapfile.c | 145 +++++++++++++++++++++++++++++------------------ 4 files changed, 97 insertions(+), 59 deletions(-) (limited to 'include/linux') diff --git a/include/linux/swap.h b/include/linux/swap.h index 8bb85d6d65f0..9155bcdcce12 100644 --- a/include/linux/swap.h +++ b/include/linux/swap.h @@ -214,7 +214,8 @@ struct percpu_cluster { struct swap_info_struct { unsigned long flags; /* SWP_USED etc: see above */ signed short prio; /* swap priority of this type */ - struct list_head list; /* entry in swap list */ + struct plist_node list; /* entry in swap_active_head */ + struct plist_node avail_list; /* entry in swap_avail_head */ signed char type; /* strange name for an index */ unsigned int max; /* extent of the swap_map */ unsigned char *swap_map; /* vmalloc'ed array of usage counts */ diff --git a/include/linux/swapfile.h b/include/linux/swapfile.h index 2eab382d593d..388293a91e8c 100644 --- a/include/linux/swapfile.h +++ b/include/linux/swapfile.h @@ -6,7 +6,7 @@ * want to expose them to the dozens of source files that include swap.h */ extern spinlock_t swap_lock; -extern struct list_head swap_list_head; +extern struct plist_head swap_active_head; extern struct swap_info_struct *swap_info[]; extern int try_to_unuse(unsigned int, bool, unsigned long); diff --git a/mm/frontswap.c b/mm/frontswap.c index fae11602e8a9..c30eec536f03 100644 --- a/mm/frontswap.c +++ b/mm/frontswap.c @@ -331,7 +331,7 @@ static unsigned long __frontswap_curr_pages(void) struct swap_info_struct *si = NULL; assert_spin_locked(&swap_lock); - list_for_each_entry(si, &swap_list_head, list) + plist_for_each_entry(si, &swap_active_head, list) totalpages += atomic_read(&si->frontswap_pages); return totalpages; } @@ -346,7 +346,7 @@ static int __frontswap_unuse_pages(unsigned long total, unsigned long *unused, unsigned long pages = 0, pages_to_unuse = 0; assert_spin_locked(&swap_lock); - list_for_each_entry(si, &swap_list_head, list) { + plist_for_each_entry(si, &swap_active_head, list) { si_frontswap_pages = atomic_read(&si->frontswap_pages); if (total_pages_to_unuse < si_frontswap_pages) { pages = pages_to_unuse = total_pages_to_unuse; @@ -408,7 +408,7 @@ void frontswap_shrink(unsigned long target_pages) /* * we don't want to hold swap_lock while doing a very * lengthy try_to_unuse, but swap_list may change - * so restart scan from swap_list_head each time + * so restart scan from swap_active_head each time */ spin_lock(&swap_lock); ret = __frontswap_shrink(target_pages, &pages_to_unuse, &type); diff --git a/mm/swapfile.c b/mm/swapfile.c index 6c95a8c63b1a..beeeef8a1b2d 100644 --- a/mm/swapfile.c +++ b/mm/swapfile.c @@ -61,7 +61,22 @@ static const char Unused_offset[] = "Unused swap offset entry "; * all active swap_info_structs * protected with swap_lock, and ordered by priority. */ -LIST_HEAD(swap_list_head); +PLIST_HEAD(swap_active_head); + +/* + * all available (active, not full) swap_info_structs + * protected with swap_avail_lock, ordered by priority. + * This is used by get_swap_page() instead of swap_active_head + * because swap_active_head includes all swap_info_structs, + * but get_swap_page() doesn't need to look at full ones. + * This uses its own lock instead of swap_lock because when a + * swap_info_struct changes between not-full/full, it needs to + * add/remove itself to/from this list, but the swap_info_struct->lock + * is held and the locking order requires swap_lock to be taken + * before any swap_info_struct->lock. + */ +static PLIST_HEAD(swap_avail_head); +static DEFINE_SPINLOCK(swap_avail_lock); struct swap_info_struct *swap_info[MAX_SWAPFILES]; @@ -594,6 +609,9 @@ checks: if (si->inuse_pages == si->pages) { si->lowest_bit = si->max; si->highest_bit = 0; + spin_lock(&swap_avail_lock); + plist_del(&si->avail_list, &swap_avail_head); + spin_unlock(&swap_avail_lock); } si->swap_map[offset] = usage; inc_cluster_info_page(si, si->cluster_info, offset); @@ -645,57 +663,63 @@ swp_entry_t get_swap_page(void) { struct swap_info_struct *si, *next; pgoff_t offset; - struct list_head *tmp; - spin_lock(&swap_lock); if (atomic_long_read(&nr_swap_pages) <= 0) goto noswap; atomic_long_dec(&nr_swap_pages); - list_for_each(tmp, &swap_list_head) { - si = list_entry(tmp, typeof(*si), list); + spin_lock(&swap_avail_lock); + +start_over: + plist_for_each_entry_safe(si, next, &swap_avail_head, avail_list) { + /* requeue si to after same-priority siblings */ + plist_requeue(&si->avail_list, &swap_avail_head); + spin_unlock(&swap_avail_lock); spin_lock(&si->lock); if (!si->highest_bit || !(si->flags & SWP_WRITEOK)) { + spin_lock(&swap_avail_lock); + if (plist_node_empty(&si->avail_list)) { + spin_unlock(&si->lock); + goto nextsi; + } + WARN(!si->highest_bit, + "swap_info %d in list but !highest_bit\n", + si->type); + WARN(!(si->flags & SWP_WRITEOK), + "swap_info %d in list but !SWP_WRITEOK\n", + si->type); + plist_del(&si->avail_list, &swap_avail_head); spin_unlock(&si->lock); - continue; + goto nextsi; } - /* - * rotate the current swap_info that we're going to use - * to after any other swap_info that have the same prio, - * so that all equal-priority swap_info get used equally - */ - next = si; - list_for_each_entry_continue(next, &swap_list_head, list) { - if (si->prio != next->prio) - break; - list_rotate_left(&si->list); - next = si; - } - - spin_unlock(&swap_lock); /* This is called for allocating swap entry for cache */ offset = scan_swap_map(si, SWAP_HAS_CACHE); spin_unlock(&si->lock); if (offset) return swp_entry(si->type, offset); - spin_lock(&swap_lock); + pr_debug("scan_swap_map of si %d failed to find offset\n", + si->type); + spin_lock(&swap_avail_lock); +nextsi: /* * if we got here, it's likely that si was almost full before, * and since scan_swap_map() can drop the si->lock, multiple * callers probably all tried to get a page from the same si - * and it filled up before we could get one. So we need to - * try again. Since we dropped the swap_lock, there may now - * be non-full higher priority swap_infos, and this si may have - * even been removed from the list (although very unlikely). - * Let's start over. + * and it filled up before we could get one; or, the si filled + * up between us dropping swap_avail_lock and taking si->lock. + * Since we dropped the swap_avail_lock, the swap_avail_head + * list may have been modified; so if next is still in the + * swap_avail_head list then try it, otherwise start over. */ - tmp = &swap_list_head; + if (plist_node_empty(&next->avail_list)) + goto start_over; } + spin_unlock(&swap_avail_lock); + atomic_long_inc(&nr_swap_pages); noswap: - spin_unlock(&swap_lock); return (swp_entry_t) {0}; } @@ -798,8 +822,18 @@ static unsigned char swap_entry_free(struct swap_info_struct *p, dec_cluster_info_page(p, p->cluster_info, offset); if (offset < p->lowest_bit) p->lowest_bit = offset; - if (offset > p->highest_bit) + if (offset > p->highest_bit) { + bool was_full = !p->highest_bit; p->highest_bit = offset; + if (was_full && (p->flags & SWP_WRITEOK)) { + spin_lock(&swap_avail_lock); + WARN_ON(!plist_node_empty(&p->avail_list)); + if (plist_node_empty(&p->avail_list)) + plist_add(&p->avail_list, + &swap_avail_head); + spin_unlock(&swap_avail_lock); + } + } atomic_long_inc(&nr_swap_pages); p->inuse_pages--; frontswap_invalidate_page(p->type, offset); @@ -1734,12 +1768,16 @@ static void _enable_swap_info(struct swap_info_struct *p, int prio, unsigned char *swap_map, struct swap_cluster_info *cluster_info) { - struct swap_info_struct *si; - if (prio >= 0) p->prio = prio; else p->prio = --least_priority; + /* + * the plist prio is negated because plist ordering is + * low-to-high, while swap ordering is high-to-low + */ + p->list.prio = -p->prio; + p->avail_list.prio = -p->prio; p->swap_map = swap_map; p->cluster_info = cluster_info; p->flags |= SWP_WRITEOK; @@ -1747,27 +1785,20 @@ static void _enable_swap_info(struct swap_info_struct *p, int prio, total_swap_pages += p->pages; assert_spin_locked(&swap_lock); - BUG_ON(!list_empty(&p->list)); - /* - * insert into swap list; the list is in priority order, - * so that get_swap_page() can get a page from the highest - * priority swap_info_struct with available page(s), and - * swapoff can adjust the auto-assigned (i.e. negative) prio - * values for any lower-priority swap_info_structs when - * removing a negative-prio swap_info_struct - */ - list_for_each_entry(si, &swap_list_head, list) { - if (p->prio >= si->prio) { - list_add_tail(&p->list, &si->list); - return; - } - } /* - * this covers two cases: - * 1) p->prio is less than all existing prio - * 2) the swap list is empty + * both lists are plists, and thus priority ordered. + * swap_active_head needs to be priority ordered for swapoff(), + * which on removal of any swap_info_struct with an auto-assigned + * (i.e. negative) priority increments the auto-assigned priority + * of any lower-priority swap_info_structs. + * swap_avail_head needs to be priority ordered for get_swap_page(), + * which allocates swap pages from the highest available priority + * swap_info_struct. */ - list_add_tail(&p->list, &swap_list_head); + plist_add(&p->list, &swap_active_head); + spin_lock(&swap_avail_lock); + plist_add(&p->avail_list, &swap_avail_head); + spin_unlock(&swap_avail_lock); } static void enable_swap_info(struct swap_info_struct *p, int prio, @@ -1821,7 +1852,7 @@ SYSCALL_DEFINE1(swapoff, const char __user *, specialfile) mapping = victim->f_mapping; spin_lock(&swap_lock); - list_for_each_entry(p, &swap_list_head, list) { + plist_for_each_entry(p, &swap_active_head, list) { if (p->flags & SWP_WRITEOK) { if (p->swap_file->f_mapping == mapping) { found = 1; @@ -1841,16 +1872,21 @@ SYSCALL_DEFINE1(swapoff, const char __user *, specialfile) spin_unlock(&swap_lock); goto out_dput; } + spin_lock(&swap_avail_lock); + plist_del(&p->avail_list, &swap_avail_head); + spin_unlock(&swap_avail_lock); spin_lock(&p->lock); if (p->prio < 0) { struct swap_info_struct *si = p; - list_for_each_entry_continue(si, &swap_list_head, list) { + plist_for_each_entry_continue(si, &swap_active_head, list) { si->prio++; + si->list.prio--; + si->avail_list.prio--; } least_priority++; } - list_del_init(&p->list); + plist_del(&p->list, &swap_active_head); atomic_long_sub(p->pages, &nr_swap_pages); total_swap_pages -= p->pages; p->flags &= ~SWP_WRITEOK; @@ -2115,7 +2151,8 @@ static struct swap_info_struct *alloc_swap_info(void) */ } INIT_LIST_HEAD(&p->first_swap_extent.list); - INIT_LIST_HEAD(&p->list); + plist_node_init(&p->list, 0); + plist_node_init(&p->avail_list, 0); p->flags = SWP_USED; spin_unlock(&swap_lock); spin_lock_init(&p->lock); -- cgit v1.2.3-71-gd317 From 776ed0f0377914d1e65fed903c052e9eef3f4cc3 Mon Sep 17 00:00:00 2001 From: Vladimir Davydov Date: Wed, 4 Jun 2014 16:10:02 -0700 Subject: memcg: cleanup kmem cache creation/destruction functions naming Current names are rather inconsistent. Let's try to improve them. Brief change log: ** old name ** ** new name ** kmem_cache_create_memcg memcg_create_kmem_cache memcg_kmem_create_cache memcg_regsiter_cache memcg_kmem_destroy_cache memcg_unregister_cache kmem_cache_destroy_memcg_children memcg_cleanup_cache_params mem_cgroup_destroy_all_caches memcg_unregister_all_caches create_work memcg_register_cache_work memcg_create_cache_work_func memcg_register_cache_func memcg_create_cache_enqueue memcg_schedule_register_cache Signed-off-by: Vladimir Davydov Acked-by: Michal Hocko Cc: Johannes Weiner Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/memcontrol.h | 2 +- include/linux/slab.h | 2 +- mm/memcontrol.c | 60 ++++++++++++++++++++++------------------------ mm/slab_common.c | 12 +++++----- 4 files changed, 36 insertions(+), 40 deletions(-) (limited to 'include/linux') diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h index dfc2929a3877..eb65d29516ca 100644 --- a/include/linux/memcontrol.h +++ b/include/linux/memcontrol.h @@ -505,7 +505,7 @@ __memcg_kmem_get_cache(struct kmem_cache *cachep, gfp_t gfp); int __memcg_charge_slab(struct kmem_cache *cachep, gfp_t gfp, int order); void __memcg_uncharge_slab(struct kmem_cache *cachep, int order); -int __kmem_cache_destroy_memcg_children(struct kmem_cache *s); +int __memcg_cleanup_cache_params(struct kmem_cache *s); /** * memcg_kmem_newpage_charge: verify if a new kmem allocation is allowed. diff --git a/include/linux/slab.h b/include/linux/slab.h index 86e5b26fbdab..1d9abb7d22a0 100644 --- a/include/linux/slab.h +++ b/include/linux/slab.h @@ -116,7 +116,7 @@ struct kmem_cache *kmem_cache_create(const char *, size_t, size_t, unsigned long, void (*)(void *)); #ifdef CONFIG_MEMCG_KMEM -struct kmem_cache *kmem_cache_create_memcg(struct mem_cgroup *, +struct kmem_cache *memcg_create_kmem_cache(struct mem_cgroup *, struct kmem_cache *, const char *); #endif diff --git a/mm/memcontrol.c b/mm/memcontrol.c index 5e2bfcc96da9..d176edb1d5e8 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -3132,8 +3132,8 @@ void memcg_free_cache_params(struct kmem_cache *s) kfree(s->memcg_params); } -static void memcg_kmem_create_cache(struct mem_cgroup *memcg, - struct kmem_cache *root_cache) +static void memcg_register_cache(struct mem_cgroup *memcg, + struct kmem_cache *root_cache) { static char memcg_name_buf[NAME_MAX + 1]; /* protected by memcg_slab_mutex */ @@ -3153,7 +3153,7 @@ static void memcg_kmem_create_cache(struct mem_cgroup *memcg, return; cgroup_name(memcg->css.cgroup, memcg_name_buf, NAME_MAX + 1); - cachep = kmem_cache_create_memcg(memcg, root_cache, memcg_name_buf); + cachep = memcg_create_kmem_cache(memcg, root_cache, memcg_name_buf); /* * If we could not create a memcg cache, do not complain, because * that's not critical at all as we can always proceed with the root @@ -3175,7 +3175,7 @@ static void memcg_kmem_create_cache(struct mem_cgroup *memcg, root_cache->memcg_params->memcg_caches[id] = cachep; } -static void memcg_kmem_destroy_cache(struct kmem_cache *cachep) +static void memcg_unregister_cache(struct kmem_cache *cachep) { struct kmem_cache *root_cache; struct mem_cgroup *memcg; @@ -3228,7 +3228,7 @@ static inline void memcg_resume_kmem_account(void) current->memcg_kmem_skip_account--; } -int __kmem_cache_destroy_memcg_children(struct kmem_cache *s) +int __memcg_cleanup_cache_params(struct kmem_cache *s) { struct kmem_cache *c; int i, failed = 0; @@ -3239,7 +3239,7 @@ int __kmem_cache_destroy_memcg_children(struct kmem_cache *s) if (!c) continue; - memcg_kmem_destroy_cache(c); + memcg_unregister_cache(c); if (cache_from_memcg_idx(s, i)) failed++; @@ -3248,7 +3248,7 @@ int __kmem_cache_destroy_memcg_children(struct kmem_cache *s) return failed; } -static void mem_cgroup_destroy_all_caches(struct mem_cgroup *memcg) +static void memcg_unregister_all_caches(struct mem_cgroup *memcg) { struct kmem_cache *cachep; struct memcg_cache_params *params, *tmp; @@ -3261,25 +3261,26 @@ static void mem_cgroup_destroy_all_caches(struct mem_cgroup *memcg) cachep = memcg_params_to_cache(params); kmem_cache_shrink(cachep); if (atomic_read(&cachep->memcg_params->nr_pages) == 0) - memcg_kmem_destroy_cache(cachep); + memcg_unregister_cache(cachep); } mutex_unlock(&memcg_slab_mutex); } -struct create_work { +struct memcg_register_cache_work { struct mem_cgroup *memcg; struct kmem_cache *cachep; struct work_struct work; }; -static void memcg_create_cache_work_func(struct work_struct *w) +static void memcg_register_cache_func(struct work_struct *w) { - struct create_work *cw = container_of(w, struct create_work, work); + struct memcg_register_cache_work *cw = + container_of(w, struct memcg_register_cache_work, work); struct mem_cgroup *memcg = cw->memcg; struct kmem_cache *cachep = cw->cachep; mutex_lock(&memcg_slab_mutex); - memcg_kmem_create_cache(memcg, cachep); + memcg_register_cache(memcg, cachep); mutex_unlock(&memcg_slab_mutex); css_put(&memcg->css); @@ -3289,12 +3290,12 @@ static void memcg_create_cache_work_func(struct work_struct *w) /* * Enqueue the creation of a per-memcg kmem_cache. */ -static void __memcg_create_cache_enqueue(struct mem_cgroup *memcg, - struct kmem_cache *cachep) +static void __memcg_schedule_register_cache(struct mem_cgroup *memcg, + struct kmem_cache *cachep) { - struct create_work *cw; + struct memcg_register_cache_work *cw; - cw = kmalloc(sizeof(struct create_work), GFP_NOWAIT); + cw = kmalloc(sizeof(*cw), GFP_NOWAIT); if (cw == NULL) { css_put(&memcg->css); return; @@ -3303,17 +3304,17 @@ static void __memcg_create_cache_enqueue(struct mem_cgroup *memcg, cw->memcg = memcg; cw->cachep = cachep; - INIT_WORK(&cw->work, memcg_create_cache_work_func); + INIT_WORK(&cw->work, memcg_register_cache_func); schedule_work(&cw->work); } -static void memcg_create_cache_enqueue(struct mem_cgroup *memcg, - struct kmem_cache *cachep) +static void memcg_schedule_register_cache(struct mem_cgroup *memcg, + struct kmem_cache *cachep) { /* * We need to stop accounting when we kmalloc, because if the * corresponding kmalloc cache is not yet created, the first allocation - * in __memcg_create_cache_enqueue will recurse. + * in __memcg_schedule_register_cache will recurse. * * However, it is better to enclose the whole function. Depending on * the debugging options enabled, INIT_WORK(), for instance, can @@ -3322,7 +3323,7 @@ static void memcg_create_cache_enqueue(struct mem_cgroup *memcg, * the safest choice is to do it like this, wrapping the whole function. */ memcg_stop_kmem_account(); - __memcg_create_cache_enqueue(memcg, cachep); + __memcg_schedule_register_cache(memcg, cachep); memcg_resume_kmem_account(); } @@ -3393,16 +3394,11 @@ struct kmem_cache *__memcg_kmem_get_cache(struct kmem_cache *cachep, * * However, there are some clashes that can arrive from locking. * For instance, because we acquire the slab_mutex while doing - * kmem_cache_dup, this means no further allocation could happen - * with the slab_mutex held. - * - * Also, because cache creation issue get_online_cpus(), this - * creates a lock chain: memcg_slab_mutex -> cpu_hotplug_mutex, - * that ends up reversed during cpu hotplug. (cpuset allocates - * a bunch of GFP_KERNEL memory during cpuup). Due to all that, - * better to defer everything. + * memcg_create_kmem_cache, this means no further allocation + * could happen with the slab_mutex held. So it's better to + * defer everything. */ - memcg_create_cache_enqueue(memcg, cachep); + memcg_schedule_register_cache(memcg, cachep); return cachep; out: rcu_read_unlock(); @@ -3526,7 +3522,7 @@ void __memcg_kmem_uncharge_pages(struct page *page, int order) memcg_uncharge_kmem(memcg, PAGE_SIZE << order); } #else -static inline void mem_cgroup_destroy_all_caches(struct mem_cgroup *memcg) +static inline void memcg_unregister_all_caches(struct mem_cgroup *memcg) { } #endif /* CONFIG_MEMCG_KMEM */ @@ -6372,7 +6368,7 @@ static void mem_cgroup_css_offline(struct cgroup_subsys_state *css) css_for_each_descendant_post(iter, css) mem_cgroup_reparent_charges(mem_cgroup_from_css(iter)); - mem_cgroup_destroy_all_caches(memcg); + memcg_unregister_all_caches(memcg); vmpressure_cleanup(&memcg->vmpressure); } diff --git a/mm/slab_common.c b/mm/slab_common.c index 32175617cb75..48fafb61f35e 100644 --- a/mm/slab_common.c +++ b/mm/slab_common.c @@ -261,7 +261,7 @@ EXPORT_SYMBOL(kmem_cache_create); #ifdef CONFIG_MEMCG_KMEM /* - * kmem_cache_create_memcg - Create a cache for a memory cgroup. + * memcg_create_kmem_cache - Create a cache for a memory cgroup. * @memcg: The memory cgroup the new cache is for. * @root_cache: The parent of the new cache. * @memcg_name: The name of the memory cgroup (used for naming the new cache). @@ -270,7 +270,7 @@ EXPORT_SYMBOL(kmem_cache_create); * requests going from @memcg to @root_cache. The new cache inherits properties * from its parent. */ -struct kmem_cache *kmem_cache_create_memcg(struct mem_cgroup *memcg, +struct kmem_cache *memcg_create_kmem_cache(struct mem_cgroup *memcg, struct kmem_cache *root_cache, const char *memcg_name) { @@ -305,7 +305,7 @@ out_unlock: return s; } -static int kmem_cache_destroy_memcg_children(struct kmem_cache *s) +static int memcg_cleanup_cache_params(struct kmem_cache *s) { int rc; @@ -314,13 +314,13 @@ static int kmem_cache_destroy_memcg_children(struct kmem_cache *s) return 0; mutex_unlock(&slab_mutex); - rc = __kmem_cache_destroy_memcg_children(s); + rc = __memcg_cleanup_cache_params(s); mutex_lock(&slab_mutex); return rc; } #else -static int kmem_cache_destroy_memcg_children(struct kmem_cache *s) +static int memcg_cleanup_cache_params(struct kmem_cache *s) { return 0; } @@ -343,7 +343,7 @@ void kmem_cache_destroy(struct kmem_cache *s) if (s->refcount) goto out_unlock; - if (kmem_cache_destroy_memcg_children(s) != 0) + if (memcg_cleanup_cache_params(s) != 0) goto out_unlock; list_del(&s->list); -- cgit v1.2.3-71-gd317 From ea5e9539abf1258f23e725cb9cb25aa74efa29eb Mon Sep 17 00:00:00 2001 From: Mel Gorman Date: Wed, 4 Jun 2014 16:10:07 -0700 Subject: include/linux/jump_label.h: expose the reference count This patch exposes the jump_label reference count in preparation for the next patch. cpusets cares about both the jump_label being enabled and how many users of the cpusets there currently are. Signed-off-by: Peter Zijlstra Signed-off-by: Mel Gorman Cc: Johannes Weiner Cc: Vlastimil Babka Cc: Jan Kara Cc: Michal Hocko Cc: Hugh Dickins Cc: Dave Hansen Cc: Theodore Ts'o Cc: "Paul E. McKenney" Cc: Oleg Nesterov Cc: Rik van Riel Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/jump_label.h | 20 +++++++++++++------- 1 file changed, 13 insertions(+), 7 deletions(-) (limited to 'include/linux') diff --git a/include/linux/jump_label.h b/include/linux/jump_label.h index 5c1dfb2a9e73..784304b222b3 100644 --- a/include/linux/jump_label.h +++ b/include/linux/jump_label.h @@ -69,6 +69,10 @@ struct static_key { # include # define HAVE_JUMP_LABEL +#else +struct static_key { + atomic_t enabled; +}; #endif /* CC_HAVE_ASM_GOTO && CONFIG_JUMP_LABEL */ enum jump_label_type { @@ -79,6 +83,12 @@ enum jump_label_type { struct module; #include + +static inline int static_key_count(struct static_key *key) +{ + return atomic_read(&key->enabled); +} + #ifdef HAVE_JUMP_LABEL #define JUMP_LABEL_TYPE_FALSE_BRANCH 0UL @@ -134,10 +144,6 @@ extern void jump_label_apply_nops(struct module *mod); #else /* !HAVE_JUMP_LABEL */ -struct static_key { - atomic_t enabled; -}; - static __always_inline void jump_label_init(void) { static_key_initialized = true; @@ -145,14 +151,14 @@ static __always_inline void jump_label_init(void) static __always_inline bool static_key_false(struct static_key *key) { - if (unlikely(atomic_read(&key->enabled) > 0)) + if (unlikely(static_key_count(key) > 0)) return true; return false; } static __always_inline bool static_key_true(struct static_key *key) { - if (likely(atomic_read(&key->enabled) > 0)) + if (likely(static_key_count(key) > 0)) return true; return false; } @@ -194,7 +200,7 @@ static inline int jump_label_apply_nops(struct module *mod) static inline bool static_key_enabled(struct static_key *key) { - return (atomic_read(&key->enabled) > 0); + return static_key_count(key) > 0; } #endif /* _LINUX_JUMP_LABEL_H */ -- cgit v1.2.3-71-gd317 From 664eeddeef6539247691197c1ac124d4aa872ab6 Mon Sep 17 00:00:00 2001 From: Mel Gorman Date: Wed, 4 Jun 2014 16:10:08 -0700 Subject: mm: page_alloc: use jump labels to avoid checking number_of_cpusets If cpusets are not in use then we still check a global variable on every page allocation. Use jump labels to avoid the overhead. Signed-off-by: Mel Gorman Reviewed-by: Rik van Riel Cc: Johannes Weiner Cc: Vlastimil Babka Cc: Jan Kara Cc: Michal Hocko Cc: Hugh Dickins Cc: Dave Hansen Cc: Theodore Ts'o Cc: "Paul E. McKenney" Cc: Oleg Nesterov Cc: Peter Zijlstra Cc: Stephen Rothwell Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/cpuset.h | 29 ++++++++++++++++++++++++++--- kernel/cpuset.c | 14 ++++---------- mm/page_alloc.c | 3 ++- 3 files changed, 32 insertions(+), 14 deletions(-) (limited to 'include/linux') diff --git a/include/linux/cpuset.h b/include/linux/cpuset.h index b19d3dc2e651..ade2390ffe92 100644 --- a/include/linux/cpuset.h +++ b/include/linux/cpuset.h @@ -12,10 +12,31 @@ #include #include #include +#include #ifdef CONFIG_CPUSETS -extern int number_of_cpusets; /* How many cpusets are defined in system? */ +extern struct static_key cpusets_enabled_key; +static inline bool cpusets_enabled(void) +{ + return static_key_false(&cpusets_enabled_key); +} + +static inline int nr_cpusets(void) +{ + /* jump label reference count + the top-level cpuset */ + return static_key_count(&cpusets_enabled_key) + 1; +} + +static inline void cpuset_inc(void) +{ + static_key_slow_inc(&cpusets_enabled_key); +} + +static inline void cpuset_dec(void) +{ + static_key_slow_dec(&cpusets_enabled_key); +} extern int cpuset_init(void); extern void cpuset_init_smp(void); @@ -32,13 +53,13 @@ extern int __cpuset_node_allowed_hardwall(int node, gfp_t gfp_mask); static inline int cpuset_node_allowed_softwall(int node, gfp_t gfp_mask) { - return number_of_cpusets <= 1 || + return nr_cpusets() <= 1 || __cpuset_node_allowed_softwall(node, gfp_mask); } static inline int cpuset_node_allowed_hardwall(int node, gfp_t gfp_mask) { - return number_of_cpusets <= 1 || + return nr_cpusets() <= 1 || __cpuset_node_allowed_hardwall(node, gfp_mask); } @@ -124,6 +145,8 @@ static inline void set_mems_allowed(nodemask_t nodemask) #else /* !CONFIG_CPUSETS */ +static inline bool cpusets_enabled(void) { return false; } + static inline int cpuset_init(void) { return 0; } static inline void cpuset_init_smp(void) {} diff --git a/kernel/cpuset.c b/kernel/cpuset.c index 3d54c418bd06..130017843899 100644 --- a/kernel/cpuset.c +++ b/kernel/cpuset.c @@ -61,12 +61,7 @@ #include #include -/* - * Tracks how many cpusets are currently defined in system. - * When there is only one cpuset (the root cpuset) we can - * short circuit some hooks. - */ -int number_of_cpusets __read_mostly; +struct static_key cpusets_enabled_key __read_mostly = STATIC_KEY_INIT_FALSE; /* See "Frequency meter" comments, below. */ @@ -611,7 +606,7 @@ static int generate_sched_domains(cpumask_var_t **domains, goto done; } - csa = kmalloc(number_of_cpusets * sizeof(cp), GFP_KERNEL); + csa = kmalloc(nr_cpusets() * sizeof(cp), GFP_KERNEL); if (!csa) goto done; csn = 0; @@ -1888,7 +1883,7 @@ static int cpuset_css_online(struct cgroup_subsys_state *css) if (is_spread_slab(parent)) set_bit(CS_SPREAD_SLAB, &cs->flags); - number_of_cpusets++; + cpuset_inc(); if (!test_bit(CGRP_CPUSET_CLONE_CHILDREN, &css->cgroup->flags)) goto out_unlock; @@ -1939,7 +1934,7 @@ static void cpuset_css_offline(struct cgroup_subsys_state *css) if (is_sched_load_balance(cs)) update_flag(CS_SCHED_LOAD_BALANCE, cs, 0); - number_of_cpusets--; + cpuset_dec(); clear_bit(CS_ONLINE, &cs->flags); mutex_unlock(&cpuset_mutex); @@ -1992,7 +1987,6 @@ int __init cpuset_init(void) if (!alloc_cpumask_var(&cpus_attach, GFP_KERNEL)) BUG(); - number_of_cpusets = 1; return 0; } diff --git a/mm/page_alloc.c b/mm/page_alloc.c index b4381eaee715..a2955e101715 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -1921,7 +1921,8 @@ zonelist_scan: if (IS_ENABLED(CONFIG_NUMA) && zlc_active && !zlc_zone_worth_trying(zonelist, z, allowednodes)) continue; - if ((alloc_flags & ALLOC_CPUSET) && + if (cpusets_enabled() && + (alloc_flags & ALLOC_CPUSET) && !cpuset_zone_allowed_softwall(zone, gfp_mask)) continue; BUILD_BUG_ON(ALLOC_NO_WATERMARKS < NR_WMARK); -- cgit v1.2.3-71-gd317 From e58469bafd0524e848c3733bc3918d854595e20f Mon Sep 17 00:00:00 2001 From: Mel Gorman Date: Wed, 4 Jun 2014 16:10:16 -0700 Subject: mm: page_alloc: use word-based accesses for get/set pageblock bitmaps The test_bit operations in get/set pageblock flags are expensive. This patch reads the bitmap on a word basis and use shifts and masks to isolate the bits of interest. Similarly masks are used to set a local copy of the bitmap and then use cmpxchg to update the bitmap if there have been no other changes made in parallel. In a test running dd onto tmpfs the overhead of the pageblock-related functions went from 1.27% in profiles to 0.5%. In addition to the performance benefits, this patch closes races that are possible between: a) get_ and set_pageblock_migratetype(), where get_pageblock_migratetype() reads part of the bits before and other part of the bits after set_pageblock_migratetype() has updated them. b) set_pageblock_migratetype() and set_pageblock_skip(), where the non-atomic read-modify-update set bit operation in set_pageblock_skip() will cause lost updates to some bits changed in the set_pageblock_migratetype(). Joonsoo Kim first reported the case a) via code inspection. Vlastimil Babka's testing with a debug patch showed that either a) or b) occurs roughly once per mmtests' stress-highalloc benchmark (although not necessarily in the same pageblock). Furthermore during development of unrelated compaction patches, it was observed that frequent calls to {start,undo}_isolate_page_range() the race occurs several thousands of times and has resulted in NULL pointer dereferences in move_freepages() and free_one_page() in places where free_list[migratetype] is manipulated by e.g. list_move(). Further debugging confirmed that migratetype had invalid value of 6, causing out of bounds access to the free_list array. That confirmed that the race exist, although it may be extremely rare, and currently only fatal where page isolation is performed due to memory hot remove. Races on pageblocks being updated by set_pageblock_migratetype(), where both old and new migratetype are lower MIGRATE_RESERVE, currently cannot result in an invalid value being observed, although theoretically they may still lead to unexpected creation or destruction of MIGRATE_RESERVE pageblocks. Furthermore, things could get suddenly worse when memory isolation is used more, or when new migratetypes are added. After this patch, the race has no longer been observed in testing. Signed-off-by: Mel Gorman Acked-by: Vlastimil Babka Reported-by: Joonsoo Kim Reported-and-tested-by: Vlastimil Babka Cc: Johannes Weiner Cc: Jan Kara Cc: Michal Hocko Cc: Hugh Dickins Cc: Dave Hansen Cc: Theodore Ts'o Cc: "Paul E. McKenney" Cc: Oleg Nesterov Cc: Rik van Riel Cc: Peter Zijlstra Cc: Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mmzone.h | 6 ++++- include/linux/pageblock-flags.h | 37 ++++++++++++++++++++++++----- mm/page_alloc.c | 52 +++++++++++++++++++++++++---------------- 3 files changed, 68 insertions(+), 27 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h index 10a96ee68311..8ef1e3f71e0f 100644 --- a/include/linux/mmzone.h +++ b/include/linux/mmzone.h @@ -75,9 +75,13 @@ enum { extern int page_group_by_mobility_disabled; +#define NR_MIGRATETYPE_BITS (PB_migrate_end - PB_migrate + 1) +#define MIGRATETYPE_MASK ((1UL << NR_MIGRATETYPE_BITS) - 1) + static inline int get_pageblock_migratetype(struct page *page) { - return get_pageblock_flags_group(page, PB_migrate, PB_migrate_end); + BUILD_BUG_ON(PB_migrate_end - PB_migrate != 2); + return get_pageblock_flags_mask(page, PB_migrate_end, MIGRATETYPE_MASK); } struct free_area { diff --git a/include/linux/pageblock-flags.h b/include/linux/pageblock-flags.h index 2ee8cd2466b5..c08730c10c7a 100644 --- a/include/linux/pageblock-flags.h +++ b/include/linux/pageblock-flags.h @@ -30,9 +30,12 @@ enum pageblock_bits { PB_migrate, PB_migrate_end = PB_migrate + 3 - 1, /* 3 bits required for migrate types */ -#ifdef CONFIG_COMPACTION PB_migrate_skip,/* If set the block is skipped by compaction */ -#endif /* CONFIG_COMPACTION */ + + /* + * Assume the bits will always align on a word. If this assumption + * changes then get/set pageblock needs updating. + */ NR_PAGEBLOCK_BITS }; @@ -62,11 +65,33 @@ extern int pageblock_order; /* Forward declaration */ struct page; +unsigned long get_pageblock_flags_mask(struct page *page, + unsigned long end_bitidx, + unsigned long mask); +void set_pageblock_flags_mask(struct page *page, + unsigned long flags, + unsigned long end_bitidx, + unsigned long mask); + /* Declarations for getting and setting flags. See mm/page_alloc.c */ -unsigned long get_pageblock_flags_group(struct page *page, - int start_bitidx, int end_bitidx); -void set_pageblock_flags_group(struct page *page, unsigned long flags, - int start_bitidx, int end_bitidx); +static inline unsigned long get_pageblock_flags_group(struct page *page, + int start_bitidx, int end_bitidx) +{ + unsigned long nr_flag_bits = end_bitidx - start_bitidx + 1; + unsigned long mask = (1 << nr_flag_bits) - 1; + + return get_pageblock_flags_mask(page, end_bitidx, mask); +} + +static inline void set_pageblock_flags_group(struct page *page, + unsigned long flags, + int start_bitidx, int end_bitidx) +{ + unsigned long nr_flag_bits = end_bitidx - start_bitidx + 1; + unsigned long mask = (1 << nr_flag_bits) - 1; + + set_pageblock_flags_mask(page, flags, end_bitidx, mask); +} #ifdef CONFIG_COMPACTION #define get_pageblock_skip(page) \ diff --git a/mm/page_alloc.c b/mm/page_alloc.c index 485932c577e7..6e937809c87a 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -6028,53 +6028,65 @@ static inline int pfn_to_bitidx(struct zone *zone, unsigned long pfn) * @end_bitidx: The last bit of interest * returns pageblock_bits flags */ -unsigned long get_pageblock_flags_group(struct page *page, - int start_bitidx, int end_bitidx) +unsigned long get_pageblock_flags_mask(struct page *page, + unsigned long end_bitidx, + unsigned long mask) { struct zone *zone; unsigned long *bitmap; - unsigned long pfn, bitidx; - unsigned long flags = 0; - unsigned long value = 1; + unsigned long pfn, bitidx, word_bitidx; + unsigned long word; zone = page_zone(page); pfn = page_to_pfn(page); bitmap = get_pageblock_bitmap(zone, pfn); bitidx = pfn_to_bitidx(zone, pfn); + word_bitidx = bitidx / BITS_PER_LONG; + bitidx &= (BITS_PER_LONG-1); - for (; start_bitidx <= end_bitidx; start_bitidx++, value <<= 1) - if (test_bit(bitidx + start_bitidx, bitmap)) - flags |= value; - - return flags; + word = bitmap[word_bitidx]; + bitidx += end_bitidx; + return (word >> (BITS_PER_LONG - bitidx - 1)) & mask; } /** - * set_pageblock_flags_group - Set the requested group of flags for a pageblock_nr_pages block of pages + * set_pageblock_flags_mask - Set the requested group of flags for a pageblock_nr_pages block of pages * @page: The page within the block of interest * @start_bitidx: The first bit of interest * @end_bitidx: The last bit of interest * @flags: The flags to set */ -void set_pageblock_flags_group(struct page *page, unsigned long flags, - int start_bitidx, int end_bitidx) +void set_pageblock_flags_mask(struct page *page, unsigned long flags, + unsigned long end_bitidx, + unsigned long mask) { struct zone *zone; unsigned long *bitmap; - unsigned long pfn, bitidx; - unsigned long value = 1; + unsigned long pfn, bitidx, word_bitidx; + unsigned long old_word, word; + + BUILD_BUG_ON(NR_PAGEBLOCK_BITS != 4); zone = page_zone(page); pfn = page_to_pfn(page); bitmap = get_pageblock_bitmap(zone, pfn); bitidx = pfn_to_bitidx(zone, pfn); + word_bitidx = bitidx / BITS_PER_LONG; + bitidx &= (BITS_PER_LONG-1); + VM_BUG_ON_PAGE(!zone_spans_pfn(zone, pfn), page); - for (; start_bitidx <= end_bitidx; start_bitidx++, value <<= 1) - if (flags & value) - __set_bit(bitidx + start_bitidx, bitmap); - else - __clear_bit(bitidx + start_bitidx, bitmap); + bitidx += end_bitidx; + mask <<= (BITS_PER_LONG - bitidx - 1); + flags <<= (BITS_PER_LONG - bitidx - 1); + + word = ACCESS_ONCE(bitmap[word_bitidx]); + for (;;) { + old_word = cmpxchg(&bitmap[word_bitidx], word, (word & ~mask) | flags); + if (word == old_word) + break; + word = old_word; + } } /* -- cgit v1.2.3-71-gd317 From dc4b0caff24d9b2918e9f27bc65499ee63187eba Mon Sep 17 00:00:00 2001 From: Mel Gorman Date: Wed, 4 Jun 2014 16:10:17 -0700 Subject: mm: page_alloc: reduce number of times page_to_pfn is called In the free path we calculate page_to_pfn multiple times. Reduce that. Signed-off-by: Mel Gorman Acked-by: Rik van Riel Cc: Johannes Weiner Acked-by: Vlastimil Babka Cc: Jan Kara Cc: Michal Hocko Cc: Hugh Dickins Cc: Dave Hansen Cc: Theodore Ts'o Cc: "Paul E. McKenney" Cc: Oleg Nesterov Cc: Peter Zijlstra Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mmzone.h | 9 +++++++-- include/linux/pageblock-flags.h | 33 +++++++++++++-------------------- mm/page_alloc.c | 34 +++++++++++++++++++--------------- 3 files changed, 39 insertions(+), 37 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h index 8ef1e3f71e0f..472426ac96ae 100644 --- a/include/linux/mmzone.h +++ b/include/linux/mmzone.h @@ -78,10 +78,15 @@ extern int page_group_by_mobility_disabled; #define NR_MIGRATETYPE_BITS (PB_migrate_end - PB_migrate + 1) #define MIGRATETYPE_MASK ((1UL << NR_MIGRATETYPE_BITS) - 1) -static inline int get_pageblock_migratetype(struct page *page) +#define get_pageblock_migratetype(page) \ + get_pfnblock_flags_mask(page, page_to_pfn(page), \ + PB_migrate_end, MIGRATETYPE_MASK) + +static inline int get_pfnblock_migratetype(struct page *page, unsigned long pfn) { BUILD_BUG_ON(PB_migrate_end - PB_migrate != 2); - return get_pageblock_flags_mask(page, PB_migrate_end, MIGRATETYPE_MASK); + return get_pfnblock_flags_mask(page, pfn, PB_migrate_end, + MIGRATETYPE_MASK); } struct free_area { diff --git a/include/linux/pageblock-flags.h b/include/linux/pageblock-flags.h index c08730c10c7a..2baeee12f48e 100644 --- a/include/linux/pageblock-flags.h +++ b/include/linux/pageblock-flags.h @@ -65,33 +65,26 @@ extern int pageblock_order; /* Forward declaration */ struct page; -unsigned long get_pageblock_flags_mask(struct page *page, +unsigned long get_pfnblock_flags_mask(struct page *page, + unsigned long pfn, unsigned long end_bitidx, unsigned long mask); -void set_pageblock_flags_mask(struct page *page, + +void set_pfnblock_flags_mask(struct page *page, unsigned long flags, + unsigned long pfn, unsigned long end_bitidx, unsigned long mask); /* Declarations for getting and setting flags. See mm/page_alloc.c */ -static inline unsigned long get_pageblock_flags_group(struct page *page, - int start_bitidx, int end_bitidx) -{ - unsigned long nr_flag_bits = end_bitidx - start_bitidx + 1; - unsigned long mask = (1 << nr_flag_bits) - 1; - - return get_pageblock_flags_mask(page, end_bitidx, mask); -} - -static inline void set_pageblock_flags_group(struct page *page, - unsigned long flags, - int start_bitidx, int end_bitidx) -{ - unsigned long nr_flag_bits = end_bitidx - start_bitidx + 1; - unsigned long mask = (1 << nr_flag_bits) - 1; - - set_pageblock_flags_mask(page, flags, end_bitidx, mask); -} +#define get_pageblock_flags_group(page, start_bitidx, end_bitidx) \ + get_pfnblock_flags_mask(page, page_to_pfn(page), \ + end_bitidx, \ + (1 << (end_bitidx - start_bitidx + 1)) - 1) +#define set_pageblock_flags_group(page, flags, start_bitidx, end_bitidx) \ + set_pfnblock_flags_mask(page, flags, page_to_pfn(page), \ + end_bitidx, \ + (1 << (end_bitidx - start_bitidx + 1)) - 1) #ifdef CONFIG_COMPACTION #define get_pageblock_skip(page) \ diff --git a/mm/page_alloc.c b/mm/page_alloc.c index 6e937809c87a..6cadc8678e28 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -560,6 +560,7 @@ static inline int page_is_buddy(struct page *page, struct page *buddy, */ static inline void __free_one_page(struct page *page, + unsigned long pfn, struct zone *zone, unsigned int order, int migratetype) { @@ -576,7 +577,7 @@ static inline void __free_one_page(struct page *page, VM_BUG_ON(migratetype == -1); - page_idx = page_to_pfn(page) & ((1 << MAX_ORDER) - 1); + page_idx = pfn & ((1 << MAX_ORDER) - 1); VM_BUG_ON_PAGE(page_idx & ((1 << order) - 1), page); VM_BUG_ON_PAGE(bad_range(zone, page), page); @@ -711,7 +712,7 @@ static void free_pcppages_bulk(struct zone *zone, int count, list_del(&page->lru); mt = get_freepage_migratetype(page); /* MIGRATE_MOVABLE list may include MIGRATE_RESERVEs */ - __free_one_page(page, zone, 0, mt); + __free_one_page(page, page_to_pfn(page), zone, 0, mt); trace_mm_page_pcpu_drain(page, 0, mt); if (likely(!is_migrate_isolate_page(page))) { __mod_zone_page_state(zone, NR_FREE_PAGES, 1); @@ -723,13 +724,15 @@ static void free_pcppages_bulk(struct zone *zone, int count, spin_unlock(&zone->lock); } -static void free_one_page(struct zone *zone, struct page *page, int order, +static void free_one_page(struct zone *zone, + struct page *page, unsigned long pfn, + int order, int migratetype) { spin_lock(&zone->lock); zone->pages_scanned = 0; - __free_one_page(page, zone, order, migratetype); + __free_one_page(page, pfn, zone, order, migratetype); if (unlikely(!is_migrate_isolate(migratetype))) __mod_zone_freepage_state(zone, 1 << order, migratetype); spin_unlock(&zone->lock); @@ -766,15 +769,16 @@ static void __free_pages_ok(struct page *page, unsigned int order) { unsigned long flags; int migratetype; + unsigned long pfn = page_to_pfn(page); if (!free_pages_prepare(page, order)) return; local_irq_save(flags); __count_vm_events(PGFREE, 1 << order); - migratetype = get_pageblock_migratetype(page); + migratetype = get_pfnblock_migratetype(page, pfn); set_freepage_migratetype(page, migratetype); - free_one_page(page_zone(page), page, order, migratetype); + free_one_page(page_zone(page), page, pfn, order, migratetype); local_irq_restore(flags); } @@ -1380,12 +1384,13 @@ void free_hot_cold_page(struct page *page, int cold) struct zone *zone = page_zone(page); struct per_cpu_pages *pcp; unsigned long flags; + unsigned long pfn = page_to_pfn(page); int migratetype; if (!free_pages_prepare(page, 0)) return; - migratetype = get_pageblock_migratetype(page); + migratetype = get_pfnblock_migratetype(page, pfn); set_freepage_migratetype(page, migratetype); local_irq_save(flags); __count_vm_event(PGFREE); @@ -1399,7 +1404,7 @@ void free_hot_cold_page(struct page *page, int cold) */ if (migratetype >= MIGRATE_PCPTYPES) { if (unlikely(is_migrate_isolate(migratetype))) { - free_one_page(zone, page, 0, migratetype); + free_one_page(zone, page, pfn, 0, migratetype); goto out; } migratetype = MIGRATE_MOVABLE; @@ -6028,17 +6033,16 @@ static inline int pfn_to_bitidx(struct zone *zone, unsigned long pfn) * @end_bitidx: The last bit of interest * returns pageblock_bits flags */ -unsigned long get_pageblock_flags_mask(struct page *page, +unsigned long get_pfnblock_flags_mask(struct page *page, unsigned long pfn, unsigned long end_bitidx, unsigned long mask) { struct zone *zone; unsigned long *bitmap; - unsigned long pfn, bitidx, word_bitidx; + unsigned long bitidx, word_bitidx; unsigned long word; zone = page_zone(page); - pfn = page_to_pfn(page); bitmap = get_pageblock_bitmap(zone, pfn); bitidx = pfn_to_bitidx(zone, pfn); word_bitidx = bitidx / BITS_PER_LONG; @@ -6050,25 +6054,25 @@ unsigned long get_pageblock_flags_mask(struct page *page, } /** - * set_pageblock_flags_mask - Set the requested group of flags for a pageblock_nr_pages block of pages + * set_pfnblock_flags_mask - Set the requested group of flags for a pageblock_nr_pages block of pages * @page: The page within the block of interest * @start_bitidx: The first bit of interest * @end_bitidx: The last bit of interest * @flags: The flags to set */ -void set_pageblock_flags_mask(struct page *page, unsigned long flags, +void set_pfnblock_flags_mask(struct page *page, unsigned long flags, + unsigned long pfn, unsigned long end_bitidx, unsigned long mask) { struct zone *zone; unsigned long *bitmap; - unsigned long pfn, bitidx, word_bitidx; + unsigned long bitidx, word_bitidx; unsigned long old_word, word; BUILD_BUG_ON(NR_PAGEBLOCK_BITS != 4); zone = page_zone(page); - pfn = page_to_pfn(page); bitmap = get_pageblock_bitmap(zone, pfn); bitidx = pfn_to_bitidx(zone, pfn); word_bitidx = bitidx / BITS_PER_LONG; -- cgit v1.2.3-71-gd317 From 7aeb09f9104b760fc53c98cb7d20d06640baf9e6 Mon Sep 17 00:00:00 2001 From: Mel Gorman Date: Wed, 4 Jun 2014 16:10:21 -0700 Subject: mm: page_alloc: use unsigned int for order in more places X86 prefers the use of unsigned types for iterators and there is a tendency to mix whether a signed or unsigned type if used for page order. This converts a number of sites in mm/page_alloc.c to use unsigned int for order where possible. Signed-off-by: Mel Gorman Acked-by: Rik van Riel Cc: Johannes Weiner Cc: Vlastimil Babka Cc: Jan Kara Cc: Michal Hocko Cc: Hugh Dickins Cc: Dave Hansen Cc: Theodore Ts'o Cc: "Paul E. McKenney" Cc: Oleg Nesterov Cc: Peter Zijlstra Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mmzone.h | 8 ++++---- mm/page_alloc.c | 43 +++++++++++++++++++++++-------------------- 2 files changed, 27 insertions(+), 24 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h index 472426ac96ae..6cbd1b6c3d20 100644 --- a/include/linux/mmzone.h +++ b/include/linux/mmzone.h @@ -817,10 +817,10 @@ static inline bool pgdat_is_empty(pg_data_t *pgdat) extern struct mutex zonelists_mutex; void build_all_zonelists(pg_data_t *pgdat, struct zone *zone); void wakeup_kswapd(struct zone *zone, int order, enum zone_type classzone_idx); -bool zone_watermark_ok(struct zone *z, int order, unsigned long mark, - int classzone_idx, int alloc_flags); -bool zone_watermark_ok_safe(struct zone *z, int order, unsigned long mark, - int classzone_idx, int alloc_flags); +bool zone_watermark_ok(struct zone *z, unsigned int order, + unsigned long mark, int classzone_idx, int alloc_flags); +bool zone_watermark_ok_safe(struct zone *z, unsigned int order, + unsigned long mark, int classzone_idx, int alloc_flags); enum memmap_context { MEMMAP_EARLY, MEMMAP_HOTPLUG, diff --git a/mm/page_alloc.c b/mm/page_alloc.c index ce4d3716214c..37ef1b87f1f3 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -409,7 +409,8 @@ static int destroy_compound_page(struct page *page, unsigned long order) return bad; } -static inline void prep_zero_page(struct page *page, int order, gfp_t gfp_flags) +static inline void prep_zero_page(struct page *page, unsigned int order, + gfp_t gfp_flags) { int i; @@ -453,7 +454,7 @@ static inline void set_page_guard_flag(struct page *page) { } static inline void clear_page_guard_flag(struct page *page) { } #endif -static inline void set_page_order(struct page *page, int order) +static inline void set_page_order(struct page *page, unsigned int order) { set_page_private(page, order); __SetPageBuddy(page); @@ -504,7 +505,7 @@ __find_buddy_index(unsigned long page_idx, unsigned int order) * For recording page's order, we use page_private(page). */ static inline int page_is_buddy(struct page *page, struct page *buddy, - int order) + unsigned int order) { if (!pfn_valid_within(page_to_pfn(buddy))) return 0; @@ -726,7 +727,7 @@ static void free_pcppages_bulk(struct zone *zone, int count, static void free_one_page(struct zone *zone, struct page *page, unsigned long pfn, - int order, + unsigned int order, int migratetype) { spin_lock(&zone->lock); @@ -897,7 +898,7 @@ static inline int check_new_page(struct page *page) return 0; } -static int prep_new_page(struct page *page, int order, gfp_t gfp_flags) +static int prep_new_page(struct page *page, unsigned int order, gfp_t gfp_flags) { int i; @@ -1108,16 +1109,17 @@ static int try_to_steal_freepages(struct zone *zone, struct page *page, /* Remove an element from the buddy allocator from the fallback list */ static inline struct page * -__rmqueue_fallback(struct zone *zone, int order, int start_migratetype) +__rmqueue_fallback(struct zone *zone, unsigned int order, int start_migratetype) { struct free_area *area; - int current_order; + unsigned int current_order; struct page *page; int migratetype, new_type, i; /* Find the largest possible block of pages in the other list */ - for (current_order = MAX_ORDER-1; current_order >= order; - --current_order) { + for (current_order = MAX_ORDER-1; + current_order >= order && current_order <= MAX_ORDER-1; + --current_order) { for (i = 0;; i++) { migratetype = fallbacks[start_migratetype][i]; @@ -1345,7 +1347,7 @@ void mark_free_pages(struct zone *zone) { unsigned long pfn, max_zone_pfn; unsigned long flags; - int order, t; + unsigned int order, t; struct list_head *curr; if (zone_is_empty(zone)) @@ -1541,8 +1543,8 @@ int split_free_page(struct page *page) */ static inline struct page *buffered_rmqueue(struct zone *preferred_zone, - struct zone *zone, int order, gfp_t gfp_flags, - int migratetype) + struct zone *zone, unsigned int order, + gfp_t gfp_flags, int migratetype) { unsigned long flags; struct page *page; @@ -1691,8 +1693,9 @@ static inline bool should_fail_alloc_page(gfp_t gfp_mask, unsigned int order) * Return true if free pages are above 'mark'. This takes into account the order * of the allocation. */ -static bool __zone_watermark_ok(struct zone *z, int order, unsigned long mark, - int classzone_idx, int alloc_flags, long free_pages) +static bool __zone_watermark_ok(struct zone *z, unsigned int order, + unsigned long mark, int classzone_idx, int alloc_flags, + long free_pages) { /* free_pages my go negative - that's OK */ long min = mark; @@ -1726,15 +1729,15 @@ static bool __zone_watermark_ok(struct zone *z, int order, unsigned long mark, return true; } -bool zone_watermark_ok(struct zone *z, int order, unsigned long mark, +bool zone_watermark_ok(struct zone *z, unsigned int order, unsigned long mark, int classzone_idx, int alloc_flags) { return __zone_watermark_ok(z, order, mark, classzone_idx, alloc_flags, zone_page_state(z, NR_FREE_PAGES)); } -bool zone_watermark_ok_safe(struct zone *z, int order, unsigned long mark, - int classzone_idx, int alloc_flags) +bool zone_watermark_ok_safe(struct zone *z, unsigned int order, + unsigned long mark, int classzone_idx, int alloc_flags) { long free_pages = zone_page_state(z, NR_FREE_PAGES); @@ -4121,7 +4124,7 @@ void __meminit memmap_init_zone(unsigned long size, int nid, unsigned long zone, static void __meminit zone_init_free_lists(struct zone *zone) { - int order, t; + unsigned int order, t; for_each_migratetype_order(order, t) { INIT_LIST_HEAD(&zone->free_area[order].free_list[t]); zone->free_area[order].nr_free = 0; @@ -6444,7 +6447,7 @@ __offline_isolated_pages(unsigned long start_pfn, unsigned long end_pfn) { struct page *page; struct zone *zone; - int order, i; + unsigned int order, i; unsigned long pfn; unsigned long flags; /* find the first valid pfn */ @@ -6496,7 +6499,7 @@ bool is_free_buddy_page(struct page *page) struct zone *zone = page_zone(page); unsigned long pfn = page_to_pfn(page); unsigned long flags; - int order; + unsigned int order; spin_lock_irqsave(&zone->lock, flags); for (order = 0; order < MAX_ORDER; order++) { -- cgit v1.2.3-71-gd317 From b745bc85f21ea707e4ea1a91948055fa3e72c77b Mon Sep 17 00:00:00 2001 From: Mel Gorman Date: Wed, 4 Jun 2014 16:10:22 -0700 Subject: mm: page_alloc: convert hot/cold parameter and immediate callers to bool cold is a bool, make it one. Make the likely case the "if" part of the block instead of the else as according to the optimisation manual this is preferred. Signed-off-by: Mel Gorman Acked-by: Rik van Riel Cc: Johannes Weiner Cc: Vlastimil Babka Cc: Jan Kara Cc: Michal Hocko Cc: Hugh Dickins Cc: Dave Hansen Cc: Theodore Ts'o Cc: "Paul E. McKenney" Cc: Oleg Nesterov Cc: Peter Zijlstra Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- arch/tile/mm/homecache.c | 2 +- fs/fuse/dev.c | 2 +- include/linux/gfp.h | 4 ++-- include/linux/pagemap.h | 2 +- include/linux/swap.h | 2 +- mm/page_alloc.c | 20 ++++++++++---------- mm/swap.c | 4 ++-- mm/swap_state.c | 2 +- mm/vmscan.c | 6 +++--- 9 files changed, 22 insertions(+), 22 deletions(-) (limited to 'include/linux') diff --git a/arch/tile/mm/homecache.c b/arch/tile/mm/homecache.c index 004ba568d93f..33294fdc402e 100644 --- a/arch/tile/mm/homecache.c +++ b/arch/tile/mm/homecache.c @@ -417,7 +417,7 @@ void __homecache_free_pages(struct page *page, unsigned int order) if (put_page_testzero(page)) { homecache_change_page_home(page, order, PAGE_HOME_HASH); if (order == 0) { - free_hot_cold_page(page, 0); + free_hot_cold_page(page, false); } else { init_page_count(page); __free_pages(page, order); diff --git a/fs/fuse/dev.c b/fs/fuse/dev.c index aac71ce373e4..098f97bdcf1b 100644 --- a/fs/fuse/dev.c +++ b/fs/fuse/dev.c @@ -1614,7 +1614,7 @@ out_finish: static void fuse_retrieve_end(struct fuse_conn *fc, struct fuse_req *req) { - release_pages(req->pages, req->num_pages, 0); + release_pages(req->pages, req->num_pages, false); } static int fuse_retrieve(struct fuse_conn *fc, struct inode *inode, diff --git a/include/linux/gfp.h b/include/linux/gfp.h index d382db71e300..454c99fdb79d 100644 --- a/include/linux/gfp.h +++ b/include/linux/gfp.h @@ -371,8 +371,8 @@ void *alloc_pages_exact_nid(int nid, size_t size, gfp_t gfp_mask); extern void __free_pages(struct page *page, unsigned int order); extern void free_pages(unsigned long addr, unsigned int order); -extern void free_hot_cold_page(struct page *page, int cold); -extern void free_hot_cold_page_list(struct list_head *list, int cold); +extern void free_hot_cold_page(struct page *page, bool cold); +extern void free_hot_cold_page_list(struct list_head *list, bool cold); extern void __free_kmem_pages(struct page *page, unsigned int order); extern void free_kmem_pages(unsigned long addr, unsigned int order); diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h index 718214c5584e..c16fb6d06e36 100644 --- a/include/linux/pagemap.h +++ b/include/linux/pagemap.h @@ -110,7 +110,7 @@ static inline void mapping_set_gfp_mask(struct address_space *m, gfp_t mask) #define page_cache_get(page) get_page(page) #define page_cache_release(page) put_page(page) -void release_pages(struct page **pages, int nr, int cold); +void release_pages(struct page **pages, int nr, bool cold); /* * speculatively take a reference to a page. diff --git a/include/linux/swap.h b/include/linux/swap.h index 9155bcdcce12..97cf16164c46 100644 --- a/include/linux/swap.h +++ b/include/linux/swap.h @@ -477,7 +477,7 @@ mem_cgroup_uncharge_swapcache(struct page *page, swp_entry_t ent, bool swapout) #define free_page_and_swap_cache(page) \ page_cache_release(page) #define free_pages_and_swap_cache(pages, nr) \ - release_pages((pages), (nr), 0); + release_pages((pages), (nr), false); static inline void show_swap_cache_info(void) { diff --git a/mm/page_alloc.c b/mm/page_alloc.c index 37ef1b87f1f3..09345ab7fb63 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -1199,7 +1199,7 @@ retry_reserve: */ static int rmqueue_bulk(struct zone *zone, unsigned int order, unsigned long count, struct list_head *list, - int migratetype, int cold) + int migratetype, bool cold) { int i; @@ -1218,7 +1218,7 @@ static int rmqueue_bulk(struct zone *zone, unsigned int order, * merge IO requests if the physical pages are ordered * properly. */ - if (likely(cold == 0)) + if (likely(!cold)) list_add(&page->lru, list); else list_add_tail(&page->lru, list); @@ -1379,9 +1379,9 @@ void mark_free_pages(struct zone *zone) /* * Free a 0-order page - * cold == 1 ? free a cold page : free a hot page + * cold == true ? free a cold page : free a hot page */ -void free_hot_cold_page(struct page *page, int cold) +void free_hot_cold_page(struct page *page, bool cold) { struct zone *zone = page_zone(page); struct per_cpu_pages *pcp; @@ -1413,10 +1413,10 @@ void free_hot_cold_page(struct page *page, int cold) } pcp = &this_cpu_ptr(zone->pageset)->pcp; - if (cold) - list_add_tail(&page->lru, &pcp->lists[migratetype]); - else + if (!cold) list_add(&page->lru, &pcp->lists[migratetype]); + else + list_add_tail(&page->lru, &pcp->lists[migratetype]); pcp->count++; if (pcp->count >= pcp->high) { unsigned long batch = ACCESS_ONCE(pcp->batch); @@ -1431,7 +1431,7 @@ out: /* * Free a list of 0-order pages */ -void free_hot_cold_page_list(struct list_head *list, int cold) +void free_hot_cold_page_list(struct list_head *list, bool cold) { struct page *page, *next; @@ -1548,7 +1548,7 @@ struct page *buffered_rmqueue(struct zone *preferred_zone, { unsigned long flags; struct page *page; - int cold = !!(gfp_flags & __GFP_COLD); + bool cold = ((gfp_flags & __GFP_COLD) != 0); again: if (likely(order == 0)) { @@ -2823,7 +2823,7 @@ void __free_pages(struct page *page, unsigned int order) { if (put_page_testzero(page)) { if (order == 0) - free_hot_cold_page(page, 0); + free_hot_cold_page(page, false); else __free_pages_ok(page, order); } diff --git a/mm/swap.c b/mm/swap.c index c8d6df556ce6..11ebb9714f49 100644 --- a/mm/swap.c +++ b/mm/swap.c @@ -67,7 +67,7 @@ static void __page_cache_release(struct page *page) static void __put_single_page(struct page *page) { __page_cache_release(page); - free_hot_cold_page(page, 0); + free_hot_cold_page(page, false); } static void __put_compound_page(struct page *page) @@ -860,7 +860,7 @@ void lru_add_drain_all(void) * grabbed the page via the LRU. If it did, give up: shrink_inactive_list() * will free it. */ -void release_pages(struct page **pages, int nr, int cold) +void release_pages(struct page **pages, int nr, bool cold) { int i; LIST_HEAD(pages_to_free); diff --git a/mm/swap_state.c b/mm/swap_state.c index e76ace30d436..2972eee184a4 100644 --- a/mm/swap_state.c +++ b/mm/swap_state.c @@ -270,7 +270,7 @@ void free_pages_and_swap_cache(struct page **pages, int nr) for (i = 0; i < todo; i++) free_swap_cache(pagep[i]); - release_pages(pagep, todo, 0); + release_pages(pagep, todo, false); pagep += todo; nr -= todo; } diff --git a/mm/vmscan.c b/mm/vmscan.c index 9253e188000f..494cd632178c 100644 --- a/mm/vmscan.c +++ b/mm/vmscan.c @@ -1121,7 +1121,7 @@ keep: VM_BUG_ON_PAGE(PageLRU(page) || PageUnevictable(page), page); } - free_hot_cold_page_list(&free_pages, 1); + free_hot_cold_page_list(&free_pages, true); list_splice(&ret_pages, page_list); count_vm_events(PGACTIVATE, pgactivate); @@ -1532,7 +1532,7 @@ shrink_inactive_list(unsigned long nr_to_scan, struct lruvec *lruvec, spin_unlock_irq(&zone->lru_lock); - free_hot_cold_page_list(&page_list, 1); + free_hot_cold_page_list(&page_list, true); /* * If reclaim is isolating dirty pages under writeback, it implies @@ -1755,7 +1755,7 @@ static void shrink_active_list(unsigned long nr_to_scan, __mod_zone_page_state(zone, NR_ISOLATED_ANON + file, -nr_taken); spin_unlock_irq(&zone->lru_lock); - free_hot_cold_page_list(&l_hold, 1); + free_hot_cold_page_list(&l_hold, true); } #ifdef CONFIG_SWAP -- cgit v1.2.3-71-gd317 From 07a427884348d38a6fd56fa4d78249c407196650 Mon Sep 17 00:00:00 2001 From: Mel Gorman Date: Wed, 4 Jun 2014 16:10:24 -0700 Subject: mm: shmem: avoid atomic operation during shmem_getpage_gfp shmem_getpage_gfp uses an atomic operation to set the SwapBacked field before it's even added to the LRU or visible. This is unnecessary as what could it possible race against? Use an unlocked variant. Signed-off-by: Mel Gorman Acked-by: Johannes Weiner Acked-by: Rik van Riel Cc: Vlastimil Babka Cc: Jan Kara Cc: Michal Hocko Cc: Hugh Dickins Cc: Dave Hansen Cc: Theodore Ts'o Cc: "Paul E. McKenney" Cc: Oleg Nesterov Cc: Peter Zijlstra Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/page-flags.h | 1 + mm/shmem.c | 2 +- 2 files changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/page-flags.h b/include/linux/page-flags.h index d1fe1a761047..4d4b39ab2341 100644 --- a/include/linux/page-flags.h +++ b/include/linux/page-flags.h @@ -208,6 +208,7 @@ PAGEFLAG(Pinned, pinned) TESTSCFLAG(Pinned, pinned) /* Xen */ PAGEFLAG(SavePinned, savepinned); /* Xen */ PAGEFLAG(Reserved, reserved) __CLEARPAGEFLAG(Reserved, reserved) PAGEFLAG(SwapBacked, swapbacked) __CLEARPAGEFLAG(SwapBacked, swapbacked) + __SETPAGEFLAG(SwapBacked, swapbacked) __PAGEFLAG(SlobFree, slob_free) diff --git a/mm/shmem.c b/mm/shmem.c index 9f70e02111c6..f47fb38c4889 100644 --- a/mm/shmem.c +++ b/mm/shmem.c @@ -1132,7 +1132,7 @@ repeat: goto decused; } - SetPageSwapBacked(page); + __SetPageSwapBacked(page); __set_page_locked(page); error = mem_cgroup_charge_file(page, current->mm, gfp & GFP_RECLAIM_MASK); -- cgit v1.2.3-71-gd317 From 2457aec63745e235bcafb7ef312b182d8682f0fc Mon Sep 17 00:00:00 2001 From: Mel Gorman Date: Wed, 4 Jun 2014 16:10:31 -0700 Subject: mm: non-atomically mark page accessed during page cache allocation where possible aops->write_begin may allocate a new page and make it visible only to have mark_page_accessed called almost immediately after. Once the page is visible the atomic operations are necessary which is noticable overhead when writing to an in-memory filesystem like tmpfs but should also be noticable with fast storage. The objective of the patch is to initialse the accessed information with non-atomic operations before the page is visible. The bulk of filesystems directly or indirectly use grab_cache_page_write_begin or find_or_create_page for the initial allocation of a page cache page. This patch adds an init_page_accessed() helper which behaves like the first call to mark_page_accessed() but may called before the page is visible and can be done non-atomically. The primary APIs of concern in this care are the following and are used by most filesystems. find_get_page find_lock_page find_or_create_page grab_cache_page_nowait grab_cache_page_write_begin All of them are very similar in detail to the patch creates a core helper pagecache_get_page() which takes a flags parameter that affects its behavior such as whether the page should be marked accessed or not. Then old API is preserved but is basically a thin wrapper around this core function. Each of the filesystems are then updated to avoid calling mark_page_accessed when it is known that the VM interfaces have already done the job. There is a slight snag in that the timing of the mark_page_accessed() has now changed so in rare cases it's possible a page gets to the end of the LRU as PageReferenced where as previously it might have been repromoted. This is expected to be rare but it's worth the filesystem people thinking about it in case they see a problem with the timing change. It is also the case that some filesystems may be marking pages accessed that previously did not but it makes sense that filesystems have consistent behaviour in this regard. The test case used to evaulate this is a simple dd of a large file done multiple times with the file deleted on each iterations. The size of the file is 1/10th physical memory to avoid dirty page balancing. In the async case it will be possible that the workload completes without even hitting the disk and will have variable results but highlight the impact of mark_page_accessed for async IO. The sync results are expected to be more stable. The exception is tmpfs where the normal case is for the "IO" to not hit the disk. The test machine was single socket and UMA to avoid any scheduling or NUMA artifacts. Throughput and wall times are presented for sync IO, only wall times are shown for async as the granularity reported by dd and the variability is unsuitable for comparison. As async results were variable do to writback timings, I'm only reporting the maximum figures. The sync results were stable enough to make the mean and stddev uninteresting. The performance results are reported based on a run with no profiling. Profile data is based on a separate run with oprofile running. async dd 3.15.0-rc3 3.15.0-rc3 vanilla accessed-v2 ext3 Max elapsed 13.9900 ( 0.00%) 11.5900 ( 17.16%) tmpfs Max elapsed 0.5100 ( 0.00%) 0.4900 ( 3.92%) btrfs Max elapsed 12.8100 ( 0.00%) 12.7800 ( 0.23%) ext4 Max elapsed 18.6000 ( 0.00%) 13.3400 ( 28.28%) xfs Max elapsed 12.5600 ( 0.00%) 2.0900 ( 83.36%) The XFS figure is a bit strange as it managed to avoid a worst case by sheer luck but the average figures looked reasonable. samples percentage ext3 86107 0.9783 vmlinux-3.15.0-rc4-vanilla mark_page_accessed ext3 23833 0.2710 vmlinux-3.15.0-rc4-accessed-v3r25 mark_page_accessed ext3 5036 0.0573 vmlinux-3.15.0-rc4-accessed-v3r25 init_page_accessed ext4 64566 0.8961 vmlinux-3.15.0-rc4-vanilla mark_page_accessed ext4 5322 0.0713 vmlinux-3.15.0-rc4-accessed-v3r25 mark_page_accessed ext4 2869 0.0384 vmlinux-3.15.0-rc4-accessed-v3r25 init_page_accessed xfs 62126 1.7675 vmlinux-3.15.0-rc4-vanilla mark_page_accessed xfs 1904 0.0554 vmlinux-3.15.0-rc4-accessed-v3r25 init_page_accessed xfs 103 0.0030 vmlinux-3.15.0-rc4-accessed-v3r25 mark_page_accessed btrfs 10655 0.1338 vmlinux-3.15.0-rc4-vanilla mark_page_accessed btrfs 2020 0.0273 vmlinux-3.15.0-rc4-accessed-v3r25 init_page_accessed btrfs 587 0.0079 vmlinux-3.15.0-rc4-accessed-v3r25 mark_page_accessed tmpfs 59562 3.2628 vmlinux-3.15.0-rc4-vanilla mark_page_accessed tmpfs 1210 0.0696 vmlinux-3.15.0-rc4-accessed-v3r25 init_page_accessed tmpfs 94 0.0054 vmlinux-3.15.0-rc4-accessed-v3r25 mark_page_accessed [akpm@linux-foundation.org: don't run init_page_accessed() against an uninitialised pointer] Signed-off-by: Mel Gorman Cc: Johannes Weiner Cc: Vlastimil Babka Cc: Jan Kara Cc: Michal Hocko Cc: Hugh Dickins Cc: Dave Hansen Cc: Theodore Ts'o Cc: "Paul E. McKenney" Cc: Oleg Nesterov Cc: Rik van Riel Cc: Peter Zijlstra Tested-by: Prabhakar Lad Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- fs/btrfs/extent_io.c | 11 +-- fs/btrfs/file.c | 5 +- fs/buffer.c | 7 +- fs/ext4/mballoc.c | 14 ++-- fs/f2fs/checkpoint.c | 3 - fs/f2fs/node.c | 2 - fs/fuse/file.c | 2 - fs/gfs2/aops.c | 1 - fs/gfs2/meta_io.c | 4 +- fs/ntfs/attrib.c | 1 - fs/ntfs/file.c | 1 - include/linux/page-flags.h | 1 + include/linux/pagemap.h | 107 ++++++++++++++++++++++-- include/linux/swap.h | 1 + mm/filemap.c | 202 +++++++++++++++++---------------------------- mm/shmem.c | 6 +- mm/swap.c | 11 +++ 17 files changed, 217 insertions(+), 162 deletions(-) (limited to 'include/linux') diff --git a/fs/btrfs/extent_io.c b/fs/btrfs/extent_io.c index f29a54e454d4..4cd0ac983f91 100644 --- a/fs/btrfs/extent_io.c +++ b/fs/btrfs/extent_io.c @@ -4510,7 +4510,8 @@ static void check_buffer_tree_ref(struct extent_buffer *eb) spin_unlock(&eb->refs_lock); } -static void mark_extent_buffer_accessed(struct extent_buffer *eb) +static void mark_extent_buffer_accessed(struct extent_buffer *eb, + struct page *accessed) { unsigned long num_pages, i; @@ -4519,7 +4520,8 @@ static void mark_extent_buffer_accessed(struct extent_buffer *eb) num_pages = num_extent_pages(eb->start, eb->len); for (i = 0; i < num_pages; i++) { struct page *p = extent_buffer_page(eb, i); - mark_page_accessed(p); + if (p != accessed) + mark_page_accessed(p); } } @@ -4533,7 +4535,7 @@ struct extent_buffer *find_extent_buffer(struct btrfs_fs_info *fs_info, start >> PAGE_CACHE_SHIFT); if (eb && atomic_inc_not_zero(&eb->refs)) { rcu_read_unlock(); - mark_extent_buffer_accessed(eb); + mark_extent_buffer_accessed(eb, NULL); return eb; } rcu_read_unlock(); @@ -4581,7 +4583,7 @@ struct extent_buffer *alloc_extent_buffer(struct btrfs_fs_info *fs_info, spin_unlock(&mapping->private_lock); unlock_page(p); page_cache_release(p); - mark_extent_buffer_accessed(exists); + mark_extent_buffer_accessed(exists, p); goto free_eb; } @@ -4596,7 +4598,6 @@ struct extent_buffer *alloc_extent_buffer(struct btrfs_fs_info *fs_info, attach_extent_buffer_page(eb, p); spin_unlock(&mapping->private_lock); WARN_ON(PageDirty(p)); - mark_page_accessed(p); eb->pages[i] = p; if (!PageUptodate(p)) uptodate = 0; diff --git a/fs/btrfs/file.c b/fs/btrfs/file.c index ae6af072b635..74272a3f9d9b 100644 --- a/fs/btrfs/file.c +++ b/fs/btrfs/file.c @@ -470,11 +470,12 @@ static void btrfs_drop_pages(struct page **pages, size_t num_pages) for (i = 0; i < num_pages; i++) { /* page checked is some magic around finding pages that * have been modified without going through btrfs_set_page_dirty - * clear it here + * clear it here. There should be no need to mark the pages + * accessed as prepare_pages should have marked them accessed + * in prepare_pages via find_or_create_page() */ ClearPageChecked(pages[i]); unlock_page(pages[i]); - mark_page_accessed(pages[i]); page_cache_release(pages[i]); } } diff --git a/fs/buffer.c b/fs/buffer.c index 0d3e8d5a2299..eba6e4f621ce 100644 --- a/fs/buffer.c +++ b/fs/buffer.c @@ -227,7 +227,7 @@ __find_get_block_slow(struct block_device *bdev, sector_t block) int all_mapped = 1; index = block >> (PAGE_CACHE_SHIFT - bd_inode->i_blkbits); - page = find_get_page(bd_mapping, index); + page = find_get_page_flags(bd_mapping, index, FGP_ACCESSED); if (!page) goto out; @@ -1366,12 +1366,13 @@ __find_get_block(struct block_device *bdev, sector_t block, unsigned size) struct buffer_head *bh = lookup_bh_lru(bdev, block, size); if (bh == NULL) { + /* __find_get_block_slow will mark the page accessed */ bh = __find_get_block_slow(bdev, block); if (bh) bh_lru_install(bh); - } - if (bh) + } else touch_buffer(bh); + return bh; } EXPORT_SYMBOL(__find_get_block); diff --git a/fs/ext4/mballoc.c b/fs/ext4/mballoc.c index c8238a26818c..afe8a133e3d1 100644 --- a/fs/ext4/mballoc.c +++ b/fs/ext4/mballoc.c @@ -1044,6 +1044,8 @@ int ext4_mb_init_group(struct super_block *sb, ext4_group_t group) * allocating. If we are looking at the buddy cache we would * have taken a reference using ext4_mb_load_buddy and that * would have pinned buddy page to page cache. + * The call to ext4_mb_get_buddy_page_lock will mark the + * page accessed. */ ret = ext4_mb_get_buddy_page_lock(sb, group, &e4b); if (ret || !EXT4_MB_GRP_NEED_INIT(this_grp)) { @@ -1062,7 +1064,6 @@ int ext4_mb_init_group(struct super_block *sb, ext4_group_t group) ret = -EIO; goto err; } - mark_page_accessed(page); if (e4b.bd_buddy_page == NULL) { /* @@ -1082,7 +1083,6 @@ int ext4_mb_init_group(struct super_block *sb, ext4_group_t group) ret = -EIO; goto err; } - mark_page_accessed(page); err: ext4_mb_put_buddy_page_lock(&e4b); return ret; @@ -1141,7 +1141,7 @@ ext4_mb_load_buddy(struct super_block *sb, ext4_group_t group, /* we could use find_or_create_page(), but it locks page * what we'd like to avoid in fast path ... */ - page = find_get_page(inode->i_mapping, pnum); + page = find_get_page_flags(inode->i_mapping, pnum, FGP_ACCESSED); if (page == NULL || !PageUptodate(page)) { if (page) /* @@ -1176,15 +1176,16 @@ ext4_mb_load_buddy(struct super_block *sb, ext4_group_t group, ret = -EIO; goto err; } + + /* Pages marked accessed already */ e4b->bd_bitmap_page = page; e4b->bd_bitmap = page_address(page) + (poff * sb->s_blocksize); - mark_page_accessed(page); block++; pnum = block / blocks_per_page; poff = block % blocks_per_page; - page = find_get_page(inode->i_mapping, pnum); + page = find_get_page_flags(inode->i_mapping, pnum, FGP_ACCESSED); if (page == NULL || !PageUptodate(page)) { if (page) page_cache_release(page); @@ -1209,9 +1210,10 @@ ext4_mb_load_buddy(struct super_block *sb, ext4_group_t group, ret = -EIO; goto err; } + + /* Pages marked accessed already */ e4b->bd_buddy_page = page; e4b->bd_buddy = page_address(page) + (poff * sb->s_blocksize); - mark_page_accessed(page); BUG_ON(e4b->bd_bitmap_page == NULL); BUG_ON(e4b->bd_buddy_page == NULL); diff --git a/fs/f2fs/checkpoint.c b/fs/f2fs/checkpoint.c index 4aa521aa9bc3..c405b8f17054 100644 --- a/fs/f2fs/checkpoint.c +++ b/fs/f2fs/checkpoint.c @@ -69,7 +69,6 @@ repeat: goto repeat; } out: - mark_page_accessed(page); return page; } @@ -137,13 +136,11 @@ int ra_meta_pages(struct f2fs_sb_info *sbi, int start, int nrpages, int type) if (!page) continue; if (PageUptodate(page)) { - mark_page_accessed(page); f2fs_put_page(page, 1); continue; } f2fs_submit_page_mbio(sbi, page, blk_addr, &fio); - mark_page_accessed(page); f2fs_put_page(page, 0); } out: diff --git a/fs/f2fs/node.c b/fs/f2fs/node.c index a161e955c4c8..57caa6eaf47b 100644 --- a/fs/f2fs/node.c +++ b/fs/f2fs/node.c @@ -967,7 +967,6 @@ repeat: goto repeat; } got_it: - mark_page_accessed(page); return page; } @@ -1022,7 +1021,6 @@ page_hit: f2fs_put_page(page, 1); return ERR_PTR(-EIO); } - mark_page_accessed(page); return page; } diff --git a/fs/fuse/file.c b/fs/fuse/file.c index f680d2c44e97..903cbc9cd6bd 100644 --- a/fs/fuse/file.c +++ b/fs/fuse/file.c @@ -1089,8 +1089,6 @@ static ssize_t fuse_fill_write_pages(struct fuse_req *req, tmp = iov_iter_copy_from_user_atomic(page, ii, offset, bytes); flush_dcache_page(page); - mark_page_accessed(page); - if (!tmp) { unlock_page(page); page_cache_release(page); diff --git a/fs/gfs2/aops.c b/fs/gfs2/aops.c index 5a49b037da81..492123cda64a 100644 --- a/fs/gfs2/aops.c +++ b/fs/gfs2/aops.c @@ -577,7 +577,6 @@ int gfs2_internal_read(struct gfs2_inode *ip, char *buf, loff_t *pos, p = kmap_atomic(page); memcpy(buf + copied, p + offset, amt); kunmap_atomic(p); - mark_page_accessed(page); page_cache_release(page); copied += amt; index++; diff --git a/fs/gfs2/meta_io.c b/fs/gfs2/meta_io.c index 2cf09b63a6b4..b984a6e190bc 100644 --- a/fs/gfs2/meta_io.c +++ b/fs/gfs2/meta_io.c @@ -136,7 +136,8 @@ struct buffer_head *gfs2_getbuf(struct gfs2_glock *gl, u64 blkno, int create) yield(); } } else { - page = find_lock_page(mapping, index); + page = find_get_page_flags(mapping, index, + FGP_LOCK|FGP_ACCESSED); if (!page) return NULL; } @@ -153,7 +154,6 @@ struct buffer_head *gfs2_getbuf(struct gfs2_glock *gl, u64 blkno, int create) map_bh(bh, sdp->sd_vfs, blkno); unlock_page(page); - mark_page_accessed(page); page_cache_release(page); return bh; diff --git a/fs/ntfs/attrib.c b/fs/ntfs/attrib.c index a27e3fecefaf..250ed5b20c8f 100644 --- a/fs/ntfs/attrib.c +++ b/fs/ntfs/attrib.c @@ -1748,7 +1748,6 @@ int ntfs_attr_make_non_resident(ntfs_inode *ni, const u32 data_size) if (page) { set_page_dirty(page); unlock_page(page); - mark_page_accessed(page); page_cache_release(page); } ntfs_debug("Done."); diff --git a/fs/ntfs/file.c b/fs/ntfs/file.c index db9bd8a31725..86ddab916b66 100644 --- a/fs/ntfs/file.c +++ b/fs/ntfs/file.c @@ -2060,7 +2060,6 @@ static ssize_t ntfs_file_buffered_write(struct kiocb *iocb, } do { unlock_page(pages[--do_pages]); - mark_page_accessed(pages[do_pages]); page_cache_release(pages[do_pages]); } while (do_pages); if (unlikely(status)) diff --git a/include/linux/page-flags.h b/include/linux/page-flags.h index 4d4b39ab2341..2093eb72785e 100644 --- a/include/linux/page-flags.h +++ b/include/linux/page-flags.h @@ -198,6 +198,7 @@ struct page; /* forward declaration */ TESTPAGEFLAG(Locked, locked) PAGEFLAG(Error, error) TESTCLEARFLAG(Error, error) PAGEFLAG(Referenced, referenced) TESTCLEARFLAG(Referenced, referenced) + __SETPAGEFLAG(Referenced, referenced) PAGEFLAG(Dirty, dirty) TESTSCFLAG(Dirty, dirty) __CLEARPAGEFLAG(Dirty, dirty) PAGEFLAG(LRU, lru) __CLEARPAGEFLAG(LRU, lru) PAGEFLAG(Active, active) __CLEARPAGEFLAG(Active, active) diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h index c16fb6d06e36..0a97b583ee8d 100644 --- a/include/linux/pagemap.h +++ b/include/linux/pagemap.h @@ -259,12 +259,109 @@ pgoff_t page_cache_next_hole(struct address_space *mapping, pgoff_t page_cache_prev_hole(struct address_space *mapping, pgoff_t index, unsigned long max_scan); +#define FGP_ACCESSED 0x00000001 +#define FGP_LOCK 0x00000002 +#define FGP_CREAT 0x00000004 +#define FGP_WRITE 0x00000008 +#define FGP_NOFS 0x00000010 +#define FGP_NOWAIT 0x00000020 + +struct page *pagecache_get_page(struct address_space *mapping, pgoff_t offset, + int fgp_flags, gfp_t cache_gfp_mask, gfp_t radix_gfp_mask); + +/** + * find_get_page - find and get a page reference + * @mapping: the address_space to search + * @offset: the page index + * + * Looks up the page cache slot at @mapping & @offset. If there is a + * page cache page, it is returned with an increased refcount. + * + * Otherwise, %NULL is returned. + */ +static inline struct page *find_get_page(struct address_space *mapping, + pgoff_t offset) +{ + return pagecache_get_page(mapping, offset, 0, 0, 0); +} + +static inline struct page *find_get_page_flags(struct address_space *mapping, + pgoff_t offset, int fgp_flags) +{ + return pagecache_get_page(mapping, offset, fgp_flags, 0, 0); +} + +/** + * find_lock_page - locate, pin and lock a pagecache page + * pagecache_get_page - find and get a page reference + * @mapping: the address_space to search + * @offset: the page index + * + * Looks up the page cache slot at @mapping & @offset. If there is a + * page cache page, it is returned locked and with an increased + * refcount. + * + * Otherwise, %NULL is returned. + * + * find_lock_page() may sleep. + */ +static inline struct page *find_lock_page(struct address_space *mapping, + pgoff_t offset) +{ + return pagecache_get_page(mapping, offset, FGP_LOCK, 0, 0); +} + +/** + * find_or_create_page - locate or add a pagecache page + * @mapping: the page's address_space + * @index: the page's index into the mapping + * @gfp_mask: page allocation mode + * + * Looks up the page cache slot at @mapping & @offset. If there is a + * page cache page, it is returned locked and with an increased + * refcount. + * + * If the page is not present, a new page is allocated using @gfp_mask + * and added to the page cache and the VM's LRU list. The page is + * returned locked and with an increased refcount. + * + * On memory exhaustion, %NULL is returned. + * + * find_or_create_page() may sleep, even if @gfp_flags specifies an + * atomic allocation! + */ +static inline struct page *find_or_create_page(struct address_space *mapping, + pgoff_t offset, gfp_t gfp_mask) +{ + return pagecache_get_page(mapping, offset, + FGP_LOCK|FGP_ACCESSED|FGP_CREAT, + gfp_mask, gfp_mask & GFP_RECLAIM_MASK); +} + +/** + * grab_cache_page_nowait - returns locked page at given index in given cache + * @mapping: target address_space + * @index: the page index + * + * Same as grab_cache_page(), but do not wait if the page is unavailable. + * This is intended for speculative data generators, where the data can + * be regenerated if the page couldn't be grabbed. This routine should + * be safe to call while holding the lock for another page. + * + * Clear __GFP_FS when allocating the page to avoid recursion into the fs + * and deadlock against the caller's locked page. + */ +static inline struct page *grab_cache_page_nowait(struct address_space *mapping, + pgoff_t index) +{ + return pagecache_get_page(mapping, index, + FGP_LOCK|FGP_CREAT|FGP_NOFS|FGP_NOWAIT, + mapping_gfp_mask(mapping), + GFP_NOFS); +} + struct page *find_get_entry(struct address_space *mapping, pgoff_t offset); -struct page *find_get_page(struct address_space *mapping, pgoff_t offset); struct page *find_lock_entry(struct address_space *mapping, pgoff_t offset); -struct page *find_lock_page(struct address_space *mapping, pgoff_t offset); -struct page *find_or_create_page(struct address_space *mapping, pgoff_t index, - gfp_t gfp_mask); unsigned find_get_entries(struct address_space *mapping, pgoff_t start, unsigned int nr_entries, struct page **entries, pgoff_t *indices); @@ -287,8 +384,6 @@ static inline struct page *grab_cache_page(struct address_space *mapping, return find_or_create_page(mapping, index, mapping_gfp_mask(mapping)); } -extern struct page * grab_cache_page_nowait(struct address_space *mapping, - pgoff_t index); extern struct page * read_cache_page(struct address_space *mapping, pgoff_t index, filler_t *filler, void *data); extern struct page * read_cache_page_gfp(struct address_space *mapping, diff --git a/include/linux/swap.h b/include/linux/swap.h index 97cf16164c46..4348d95e571f 100644 --- a/include/linux/swap.h +++ b/include/linux/swap.h @@ -311,6 +311,7 @@ extern void lru_add_page_tail(struct page *page, struct page *page_tail, struct lruvec *lruvec, struct list_head *head); extern void activate_page(struct page *); extern void mark_page_accessed(struct page *); +extern void init_page_accessed(struct page *page); extern void lru_add_drain(void); extern void lru_add_drain_cpu(int cpu); extern void lru_add_drain_all(void); diff --git a/mm/filemap.c b/mm/filemap.c index 47d235b357a7..0fcd792103f3 100644 --- a/mm/filemap.c +++ b/mm/filemap.c @@ -981,26 +981,6 @@ out: } EXPORT_SYMBOL(find_get_entry); -/** - * find_get_page - find and get a page reference - * @mapping: the address_space to search - * @offset: the page index - * - * Looks up the page cache slot at @mapping & @offset. If there is a - * page cache page, it is returned with an increased refcount. - * - * Otherwise, %NULL is returned. - */ -struct page *find_get_page(struct address_space *mapping, pgoff_t offset) -{ - struct page *page = find_get_entry(mapping, offset); - - if (radix_tree_exceptional_entry(page)) - page = NULL; - return page; -} -EXPORT_SYMBOL(find_get_page); - /** * find_lock_entry - locate, pin and lock a page cache entry * @mapping: the address_space to search @@ -1038,66 +1018,84 @@ repeat: EXPORT_SYMBOL(find_lock_entry); /** - * find_lock_page - locate, pin and lock a pagecache page + * pagecache_get_page - find and get a page reference * @mapping: the address_space to search * @offset: the page index + * @fgp_flags: PCG flags + * @gfp_mask: gfp mask to use if a page is to be allocated * - * Looks up the page cache slot at @mapping & @offset. If there is a - * page cache page, it is returned locked and with an increased - * refcount. - * - * Otherwise, %NULL is returned. - * - * find_lock_page() may sleep. - */ -struct page *find_lock_page(struct address_space *mapping, pgoff_t offset) -{ - struct page *page = find_lock_entry(mapping, offset); - - if (radix_tree_exceptional_entry(page)) - page = NULL; - return page; -} -EXPORT_SYMBOL(find_lock_page); - -/** - * find_or_create_page - locate or add a pagecache page - * @mapping: the page's address_space - * @index: the page's index into the mapping - * @gfp_mask: page allocation mode + * Looks up the page cache slot at @mapping & @offset. * - * Looks up the page cache slot at @mapping & @offset. If there is a - * page cache page, it is returned locked and with an increased - * refcount. + * PCG flags modify how the page is returned * - * If the page is not present, a new page is allocated using @gfp_mask - * and added to the page cache and the VM's LRU list. The page is - * returned locked and with an increased refcount. + * FGP_ACCESSED: the page will be marked accessed + * FGP_LOCK: Page is return locked + * FGP_CREAT: If page is not present then a new page is allocated using + * @gfp_mask and added to the page cache and the VM's LRU + * list. The page is returned locked and with an increased + * refcount. Otherwise, %NULL is returned. * - * On memory exhaustion, %NULL is returned. + * If FGP_LOCK or FGP_CREAT are specified then the function may sleep even + * if the GFP flags specified for FGP_CREAT are atomic. * - * find_or_create_page() may sleep, even if @gfp_flags specifies an - * atomic allocation! + * If there is a page cache page, it is returned with an increased refcount. */ -struct page *find_or_create_page(struct address_space *mapping, - pgoff_t index, gfp_t gfp_mask) +struct page *pagecache_get_page(struct address_space *mapping, pgoff_t offset, + int fgp_flags, gfp_t cache_gfp_mask, gfp_t radix_gfp_mask) { struct page *page; - int err; + repeat: - page = find_lock_page(mapping, index); - if (!page) { - page = __page_cache_alloc(gfp_mask); + page = find_get_entry(mapping, offset); + if (radix_tree_exceptional_entry(page)) + page = NULL; + if (!page) + goto no_page; + + if (fgp_flags & FGP_LOCK) { + if (fgp_flags & FGP_NOWAIT) { + if (!trylock_page(page)) { + page_cache_release(page); + return NULL; + } + } else { + lock_page(page); + } + + /* Has the page been truncated? */ + if (unlikely(page->mapping != mapping)) { + unlock_page(page); + page_cache_release(page); + goto repeat; + } + VM_BUG_ON_PAGE(page->index != offset, page); + } + + if (page && (fgp_flags & FGP_ACCESSED)) + mark_page_accessed(page); + +no_page: + if (!page && (fgp_flags & FGP_CREAT)) { + int err; + if ((fgp_flags & FGP_WRITE) && mapping_cap_account_dirty(mapping)) + cache_gfp_mask |= __GFP_WRITE; + if (fgp_flags & FGP_NOFS) { + cache_gfp_mask &= ~__GFP_FS; + radix_gfp_mask &= ~__GFP_FS; + } + + page = __page_cache_alloc(cache_gfp_mask); if (!page) return NULL; - /* - * We want a regular kernel memory (not highmem or DMA etc) - * allocation for the radix tree nodes, but we need to honour - * the context-specific requirements the caller has asked for. - * GFP_RECLAIM_MASK collects those requirements. - */ - err = add_to_page_cache_lru(page, mapping, index, - (gfp_mask & GFP_RECLAIM_MASK)); + + if (WARN_ON_ONCE(!(fgp_flags & FGP_LOCK))) + fgp_flags |= FGP_LOCK; + + /* Init accessed so avoit atomic mark_page_accessed later */ + if (fgp_flags & FGP_ACCESSED) + init_page_accessed(page); + + err = add_to_page_cache_lru(page, mapping, offset, radix_gfp_mask); if (unlikely(err)) { page_cache_release(page); page = NULL; @@ -1105,9 +1103,10 @@ repeat: goto repeat; } } + return page; } -EXPORT_SYMBOL(find_or_create_page); +EXPORT_SYMBOL(pagecache_get_page); /** * find_get_entries - gang pagecache lookup @@ -1404,39 +1403,6 @@ repeat: } EXPORT_SYMBOL(find_get_pages_tag); -/** - * grab_cache_page_nowait - returns locked page at given index in given cache - * @mapping: target address_space - * @index: the page index - * - * Same as grab_cache_page(), but do not wait if the page is unavailable. - * This is intended for speculative data generators, where the data can - * be regenerated if the page couldn't be grabbed. This routine should - * be safe to call while holding the lock for another page. - * - * Clear __GFP_FS when allocating the page to avoid recursion into the fs - * and deadlock against the caller's locked page. - */ -struct page * -grab_cache_page_nowait(struct address_space *mapping, pgoff_t index) -{ - struct page *page = find_get_page(mapping, index); - - if (page) { - if (trylock_page(page)) - return page; - page_cache_release(page); - return NULL; - } - page = __page_cache_alloc(mapping_gfp_mask(mapping) & ~__GFP_FS); - if (page && add_to_page_cache_lru(page, mapping, index, GFP_NOFS)) { - page_cache_release(page); - page = NULL; - } - return page; -} -EXPORT_SYMBOL(grab_cache_page_nowait); - /* * CD/DVDs are error prone. When a medium error occurs, the driver may fail * a _large_ part of the i/o request. Imagine the worst scenario: @@ -2406,7 +2372,6 @@ int pagecache_write_end(struct file *file, struct address_space *mapping, { const struct address_space_operations *aops = mapping->a_ops; - mark_page_accessed(page); return aops->write_end(file, mapping, pos, len, copied, page, fsdata); } EXPORT_SYMBOL(pagecache_write_end); @@ -2488,34 +2453,18 @@ EXPORT_SYMBOL(generic_file_direct_write); struct page *grab_cache_page_write_begin(struct address_space *mapping, pgoff_t index, unsigned flags) { - int status; - gfp_t gfp_mask; struct page *page; - gfp_t gfp_notmask = 0; + int fgp_flags = FGP_LOCK|FGP_ACCESSED|FGP_WRITE|FGP_CREAT; - gfp_mask = mapping_gfp_mask(mapping); - if (mapping_cap_account_dirty(mapping)) - gfp_mask |= __GFP_WRITE; if (flags & AOP_FLAG_NOFS) - gfp_notmask = __GFP_FS; -repeat: - page = find_lock_page(mapping, index); + fgp_flags |= FGP_NOFS; + + page = pagecache_get_page(mapping, index, fgp_flags, + mapping_gfp_mask(mapping), + GFP_KERNEL); if (page) - goto found; + wait_for_stable_page(page); - page = __page_cache_alloc(gfp_mask & ~gfp_notmask); - if (!page) - return NULL; - status = add_to_page_cache_lru(page, mapping, index, - GFP_KERNEL & ~gfp_notmask); - if (unlikely(status)) { - page_cache_release(page); - if (status == -EEXIST) - goto repeat; - return NULL; - } -found: - wait_for_stable_page(page); return page; } EXPORT_SYMBOL(grab_cache_page_write_begin); @@ -2564,7 +2513,7 @@ again: status = a_ops->write_begin(file, mapping, pos, bytes, flags, &page, &fsdata); - if (unlikely(status)) + if (unlikely(status < 0)) break; if (mapping_writably_mapped(mapping)) @@ -2573,7 +2522,6 @@ again: copied = iov_iter_copy_from_user_atomic(page, i, offset, bytes); flush_dcache_page(page); - mark_page_accessed(page); status = a_ops->write_end(file, mapping, pos, bytes, copied, page, fsdata); if (unlikely(status < 0)) diff --git a/mm/shmem.c b/mm/shmem.c index f47fb38c4889..5402481c28d1 100644 --- a/mm/shmem.c +++ b/mm/shmem.c @@ -1372,9 +1372,13 @@ shmem_write_begin(struct file *file, struct address_space *mapping, loff_t pos, unsigned len, unsigned flags, struct page **pagep, void **fsdata) { + int ret; struct inode *inode = mapping->host; pgoff_t index = pos >> PAGE_CACHE_SHIFT; - return shmem_getpage(inode, index, pagep, SGP_WRITE, NULL); + ret = shmem_getpage(inode, index, pagep, SGP_WRITE, NULL); + if (ret == 0 && *pagep) + init_page_accessed(*pagep); + return ret; } static int diff --git a/mm/swap.c b/mm/swap.c index 1fb25f8bb155..9e8e3472248b 100644 --- a/mm/swap.c +++ b/mm/swap.c @@ -614,6 +614,17 @@ void mark_page_accessed(struct page *page) } EXPORT_SYMBOL(mark_page_accessed); +/* + * Used to mark_page_accessed(page) that is not visible yet and when it is + * still safe to use non-atomic ops + */ +void init_page_accessed(struct page *page) +{ + if (!PageReferenced(page)) + __SetPageReferenced(page); +} +EXPORT_SYMBOL(init_page_accessed); + static void __lru_cache_add(struct page *page) { struct pagevec *pvec = &get_cpu_var(lru_add_pvec); -- cgit v1.2.3-71-gd317 From b7596fb43aa786fb3ee5015a73034fbb9e80feaa Mon Sep 17 00:00:00 2001 From: Andy Shevchenko Date: Wed, 4 Jun 2014 16:10:37 -0700 Subject: include/linux/gfp.h: exclude duplicate header mmdebug.h is included twice. Signed-off-by: Andy Shevchenko Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/gfp.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/gfp.h b/include/linux/gfp.h index 454c99fdb79d..6eb1fb37de9a 100644 --- a/include/linux/gfp.h +++ b/include/linux/gfp.h @@ -6,7 +6,6 @@ #include #include #include -#include struct vm_area_struct; -- cgit v1.2.3-71-gd317 From 4be89a34609659042ef0bf883ad76388fb5251bb Mon Sep 17 00:00:00 2001 From: Jianyu Zhan Date: Wed, 4 Jun 2014 16:10:38 -0700 Subject: mm/vmscan.c: use DIV_ROUND_UP for calculation of zone's balance_gap and correct comments. Currently, we use (zone->managed_pages + KSWAPD_ZONE_BALANCE_GAP_RATIO-1) / KSWAPD_ZONE_BALANCE_GAP_RATIO to avoid a zero gap value. It's better to use DIV_ROUND_UP macro for neater code and clear meaning. Besides, the gap value is calculated against the per-zone "managed pages", not "present pages". This patch also corrects the comment and do some rephrasing. Signed-off-by: Jianyu Zhan Acked-by: Rik van Riel Acked-by: Rafael Aquini Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/swap.h | 8 ++++---- mm/vmscan.c | 10 ++++------ 2 files changed, 8 insertions(+), 10 deletions(-) (limited to 'include/linux') diff --git a/include/linux/swap.h b/include/linux/swap.h index 4348d95e571f..4bdbee80eede 100644 --- a/include/linux/swap.h +++ b/include/linux/swap.h @@ -166,10 +166,10 @@ enum { #define COMPACT_CLUSTER_MAX SWAP_CLUSTER_MAX /* - * Ratio between the present memory in the zone and the "gap" that - * we're allowing kswapd to shrink in addition to the per-zone high - * wmark, even for zones that already have the high wmark satisfied, - * in order to provide better per-zone lru behavior. We are ok to + * Ratio between zone->managed_pages and the "gap" that above the per-zone + * "high_wmark". While balancing nodes, We allow kswapd to shrink zones that + * do not meet the (high_wmark + gap) watermark, even which already met the + * high_wmark, in order to provide better per-zone lru behavior. We are ok to * spend not more than 1% of the memory for this zone balancing "gap". */ #define KSWAPD_ZONE_BALANCE_GAP_RATIO 100 diff --git a/mm/vmscan.c b/mm/vmscan.c index 494cd632178c..cc29fca8d989 100644 --- a/mm/vmscan.c +++ b/mm/vmscan.c @@ -2295,9 +2295,8 @@ static inline bool compaction_ready(struct zone *zone, struct scan_control *sc) * there is a buffer of free pages available to give compaction * a reasonable chance of completing and allocating the page */ - balance_gap = min(low_wmark_pages(zone), - (zone->managed_pages + KSWAPD_ZONE_BALANCE_GAP_RATIO-1) / - KSWAPD_ZONE_BALANCE_GAP_RATIO); + balance_gap = min(low_wmark_pages(zone), DIV_ROUND_UP( + zone->managed_pages, KSWAPD_ZONE_BALANCE_GAP_RATIO)); watermark = high_wmark_pages(zone) + balance_gap + (2UL << sc->order); watermark_ok = zone_watermark_ok_safe(zone, 0, watermark, 0, 0); @@ -2949,9 +2948,8 @@ static bool kswapd_shrink_zone(struct zone *zone, * high wmark plus a "gap" where the gap is either the low * watermark or 1% of the zone, whichever is smaller. */ - balance_gap = min(low_wmark_pages(zone), - (zone->managed_pages + KSWAPD_ZONE_BALANCE_GAP_RATIO-1) / - KSWAPD_ZONE_BALANCE_GAP_RATIO); + balance_gap = min(low_wmark_pages(zone), DIV_ROUND_UP( + zone->managed_pages, KSWAPD_ZONE_BALANCE_GAP_RATIO)); /* * If there is no low memory pressure or the zone is balanced then no -- cgit v1.2.3-71-gd317 From daa5ba768b9e15da8867824d2f1e8d455f1acac2 Mon Sep 17 00:00:00 2001 From: Konstantin Khlebnikov Date: Wed, 4 Jun 2014 16:10:52 -0700 Subject: mm/rmap.c: cleanup ttu_flags Transform action part of ttu_flags into individiual bits. These flags aren't part of any uses-space visible api or even trace events. Signed-off-by: Konstantin Khlebnikov Cc: Rik van Riel Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/rmap.h | 7 +++---- mm/rmap.c | 10 +++++----- 2 files changed, 8 insertions(+), 9 deletions(-) (limited to 'include/linux') diff --git a/include/linux/rmap.h b/include/linux/rmap.h index 9be55c7617da..be574506e6a9 100644 --- a/include/linux/rmap.h +++ b/include/linux/rmap.h @@ -72,10 +72,9 @@ struct anon_vma_chain { }; enum ttu_flags { - TTU_UNMAP = 0, /* unmap mode */ - TTU_MIGRATION = 1, /* migration mode */ - TTU_MUNLOCK = 2, /* munlock mode */ - TTU_ACTION_MASK = 0xff, + TTU_UNMAP = 1, /* unmap mode */ + TTU_MIGRATION = 2, /* migration mode */ + TTU_MUNLOCK = 4, /* munlock mode */ TTU_IGNORE_MLOCK = (1 << 8), /* ignore mlock */ TTU_IGNORE_ACCESS = (1 << 9), /* don't age */ diff --git a/mm/rmap.c b/mm/rmap.c index ab74290d185d..ea8e20d75b29 100644 --- a/mm/rmap.c +++ b/mm/rmap.c @@ -1162,7 +1162,7 @@ static int try_to_unmap_one(struct page *page, struct vm_area_struct *vma, if (vma->vm_flags & VM_LOCKED) goto out_mlock; - if (TTU_ACTION(flags) == TTU_MUNLOCK) + if (flags & TTU_MUNLOCK) goto out_unmap; } if (!(flags & TTU_IGNORE_ACCESS)) { @@ -1230,7 +1230,7 @@ static int try_to_unmap_one(struct page *page, struct vm_area_struct *vma, * pte. do_swap_page() will wait until the migration * pte is removed and then restart fault handling. */ - BUG_ON(TTU_ACTION(flags) != TTU_MIGRATION); + BUG_ON(!(flags & TTU_MIGRATION)); entry = make_migration_entry(page, pte_write(pteval)); } swp_pte = swp_entry_to_pte(entry); @@ -1239,7 +1239,7 @@ static int try_to_unmap_one(struct page *page, struct vm_area_struct *vma, set_pte_at(mm, address, pte, swp_pte); BUG_ON(pte_file(*pte)); } else if (IS_ENABLED(CONFIG_MIGRATION) && - (TTU_ACTION(flags) == TTU_MIGRATION)) { + (flags & TTU_MIGRATION)) { /* Establish migration entry for a file page */ swp_entry_t entry; entry = make_migration_entry(page, pte_write(pteval)); @@ -1252,7 +1252,7 @@ static int try_to_unmap_one(struct page *page, struct vm_area_struct *vma, out_unmap: pte_unmap_unlock(pte, ptl); - if (ret != SWAP_FAIL && TTU_ACTION(flags) != TTU_MUNLOCK) + if (ret != SWAP_FAIL && !(flags & TTU_MUNLOCK)) mmu_notifier_invalidate_page(mm, address); out: return ret; @@ -1539,7 +1539,7 @@ int try_to_unmap(struct page *page, enum ttu_flags flags) * locking requirements of exec(), migration skips * temporary VMAs until after exec() completes. */ - if (flags & TTU_MIGRATION && !PageKsm(page) && PageAnon(page)) + if ((flags & TTU_MIGRATION) && !PageKsm(page) && PageAnon(page)) rwc.invalid_vma = invalid_migration_vma; ret = rmap_walk(page, &rwc); -- cgit v1.2.3-71-gd317 From 100873d7a777b67ad35197c5a998b5e778f8bf3f Mon Sep 17 00:00:00 2001 From: Naoya Horiguchi Date: Wed, 4 Jun 2014 16:10:56 -0700 Subject: hugetlb: rename hugepage_migration_support() to ..._supported() We already have a function named hugepages_supported(), and the similar name hugepage_migration_support() is a bit unconfortable, so let's rename it hugepage_migration_supported(). Signed-off-by: Naoya Horiguchi Acked-by: Hugh Dickins Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/hugetlb.h | 4 ++-- mm/hugetlb.c | 2 +- mm/migrate.c | 2 +- 3 files changed, 4 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h index 35786ee36f06..255cd5cc0754 100644 --- a/include/linux/hugetlb.h +++ b/include/linux/hugetlb.h @@ -397,7 +397,7 @@ static inline pgoff_t basepage_index(struct page *page) extern void dissolve_free_huge_pages(unsigned long start_pfn, unsigned long end_pfn); -static inline int hugepage_migration_support(struct hstate *h) +static inline int hugepage_migration_supported(struct hstate *h) { #ifdef CONFIG_ARCH_ENABLE_HUGEPAGE_MIGRATION return huge_page_shift(h) == PMD_SHIFT; @@ -453,7 +453,7 @@ static inline pgoff_t basepage_index(struct page *page) return page->index; } #define dissolve_free_huge_pages(s, e) do {} while (0) -#define hugepage_migration_support(h) 0 +#define hugepage_migration_supported(h) 0 static inline spinlock_t *huge_pte_lockptr(struct hstate *h, struct mm_struct *mm, pte_t *pte) diff --git a/mm/hugetlb.c b/mm/hugetlb.c index 244194217e39..226910cb7c9b 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -544,7 +544,7 @@ static struct page *dequeue_huge_page_node(struct hstate *h, int nid) /* Movability of hugepages depends on migration support. */ static inline gfp_t htlb_alloc_mask(struct hstate *h) { - if (hugepages_treat_as_movable || hugepage_migration_support(h)) + if (hugepages_treat_as_movable || hugepage_migration_supported(h)) return GFP_HIGHUSER_MOVABLE; else return GFP_HIGHUSER; diff --git a/mm/migrate.c b/mm/migrate.c index 2a459675eeab..63f0cd559999 100644 --- a/mm/migrate.c +++ b/mm/migrate.c @@ -1039,7 +1039,7 @@ static int unmap_and_move_huge_page(new_page_t get_new_page, * tables or check whether the hugepage is pmd-based or not before * kicking migration. */ - if (!hugepage_migration_support(page_hstate(hpage))) { + if (!hugepage_migration_supported(page_hstate(hpage))) { putback_active_hugepage(hpage); return -ENOSYS; } -- cgit v1.2.3-71-gd317 From 50417c55562c03e6746b13aee650c2bbb048fea3 Mon Sep 17 00:00:00 2001 From: Fabian Frederick Date: Wed, 4 Jun 2014 16:11:07 -0700 Subject: mm/zbud.c: make size unsigned like unique callsite zbud_alloc is only called by zswap_frontswap_store with unsigned int len. Change function parameter + update >= 0 check. Signed-off-by: Fabian Frederick Acked-by: Seth Jennings Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/zbud.h | 2 +- mm/zbud.c | 4 ++-- 2 files changed, 3 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/zbud.h b/include/linux/zbud.h index 2571a5cfa5fc..13af0d450bf6 100644 --- a/include/linux/zbud.h +++ b/include/linux/zbud.h @@ -11,7 +11,7 @@ struct zbud_ops { struct zbud_pool *zbud_create_pool(gfp_t gfp, struct zbud_ops *ops); void zbud_destroy_pool(struct zbud_pool *pool); -int zbud_alloc(struct zbud_pool *pool, int size, gfp_t gfp, +int zbud_alloc(struct zbud_pool *pool, unsigned int size, gfp_t gfp, unsigned long *handle); void zbud_free(struct zbud_pool *pool, unsigned long handle); int zbud_reclaim_page(struct zbud_pool *pool, unsigned int retries); diff --git a/mm/zbud.c b/mm/zbud.c index 9451361e6aa7..01df13a7e2e1 100644 --- a/mm/zbud.c +++ b/mm/zbud.c @@ -247,7 +247,7 @@ void zbud_destroy_pool(struct zbud_pool *pool) * gfp arguments are invalid or -ENOMEM if the pool was unable to allocate * a new page. */ -int zbud_alloc(struct zbud_pool *pool, int size, gfp_t gfp, +int zbud_alloc(struct zbud_pool *pool, unsigned int size, gfp_t gfp, unsigned long *handle) { int chunks, i, freechunks; @@ -255,7 +255,7 @@ int zbud_alloc(struct zbud_pool *pool, int size, gfp_t gfp, enum buddy bud; struct page *page; - if (size <= 0 || gfp & __GFP_HIGHMEM) + if (!size || (gfp & __GFP_HIGHMEM)) return -EINVAL; if (size > PAGE_SIZE - ZHDR_SIZE_ALIGNED - CHUNK_SIZE) return -ENOSPC; -- cgit v1.2.3-71-gd317 From 2c0d259e0e580dd95dd5d2d5aa4926169228d4a0 Mon Sep 17 00:00:00 2001 From: James Hogan Date: Wed, 4 Jun 2014 16:11:16 -0700 Subject: compiler.h: avoid sparse errors in __compiletime_error_fallback() Usually, BUG_ON and friends aren't even evaluated in sparse, but recently compiletime_assert_atomic_type() was added, and that now results in a sparse warning every time it is used. The reason turns out to be the temporary variable, after it sparse no longer considers the value to be a constant, and results in a warning and an error. The error is the more annoying part of this as it suppresses any further warnings in the same file, hiding other problems. Unfortunately the condition cannot be simply expanded out to avoid the temporary variable since it breaks compiletime_assert on old versions of GCC such as GCC 4.2.4 which the latest metag compiler is based on. Therefore #ifndef __CHECKER__ out the __compiletime_error_fallback which uses the potentially negative size array to trigger a conditional compiler error, so that sparse doesn't see it. Signed-off-by: James Hogan Cc: Johannes Berg Cc: Daniel Santos Cc: Luciano Coelho Cc: Peter Zijlstra Cc: Paul E. McKenney Acked-by: Johannes Berg Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/compiler.h | 13 +++++++++++-- 1 file changed, 11 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/compiler.h b/include/linux/compiler.h index ee7239ea1583..64fdfe1cfcf0 100644 --- a/include/linux/compiler.h +++ b/include/linux/compiler.h @@ -323,9 +323,18 @@ void ftrace_likely_update(struct ftrace_branch_data *f, int val, int expect); #endif #ifndef __compiletime_error # define __compiletime_error(message) -# define __compiletime_error_fallback(condition) \ +/* + * Sparse complains of variable sized arrays due to the temporary variable in + * __compiletime_assert. Unfortunately we can't just expand it out to make + * sparse see a constant array size without breaking compiletime_assert on old + * versions of GCC (e.g. 4.2.4), so hide the array from sparse altogether. + */ +# ifndef __CHECKER__ +# define __compiletime_error_fallback(condition) \ do { ((void)sizeof(char[1 - 2 * condition])); } while (0) -#else +# endif +#endif +#ifndef __compiletime_error_fallback # define __compiletime_error_fallback(condition) do { } while (0) #endif -- cgit v1.2.3-71-gd317 From b300a4ea665f7fa44f015616ac1874deca891c5e Mon Sep 17 00:00:00 2001 From: "Kirill A. Shutemov" Date: Wed, 4 Jun 2014 16:11:27 -0700 Subject: kernel/user.c: drop unused field 'files' from user_struct Nobody seems uses it for a long time. Let's drop it. Signed-off-by: Kirill A. Shutemov Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/sched.h | 1 - kernel/user.c | 1 - 2 files changed, 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sched.h b/include/linux/sched.h index 2f2dd7d932a2..611676fd4c2c 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -745,7 +745,6 @@ static inline int signal_group_exit(const struct signal_struct *sig) struct user_struct { atomic_t __count; /* reference count */ atomic_t processes; /* How many processes does this user have? */ - atomic_t files; /* How many open files does this user have? */ atomic_t sigpending; /* How many pending signals does this user have? */ #ifdef CONFIG_INOTIFY_USER atomic_t inotify_watches; /* How many inotify watches does this user have? */ diff --git a/kernel/user.c b/kernel/user.c index 294fc6a94168..4efa39350e44 100644 --- a/kernel/user.c +++ b/kernel/user.c @@ -87,7 +87,6 @@ static DEFINE_SPINLOCK(uidhash_lock); struct user_struct root_user = { .__count = ATOMIC_INIT(1), .processes = ATOMIC_INIT(1), - .files = ATOMIC_INIT(0), .sigpending = ATOMIC_INIT(0), .locked_shm = 0, .uid = GLOBAL_ROOT_UID, -- cgit v1.2.3-71-gd317 From aac74dc495456412c4130a1167ce4beb6c1f0b38 Mon Sep 17 00:00:00 2001 From: John Stultz Date: Wed, 4 Jun 2014 16:11:40 -0700 Subject: printk: rename printk_sched to printk_deferred After learning we'll need some sort of deferred printk functionality in the timekeeping core, Peter suggested we rename the printk_sched function so it can be reused by needed subsystems. This only changes the function name. No logic changes. Signed-off-by: John Stultz Reviewed-by: Steven Rostedt Cc: Jan Kara Cc: Peter Zijlstra Cc: Jiri Bohac Cc: Thomas Gleixner Cc: Ingo Molnar Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/printk.h | 6 +++--- kernel/printk/printk.c | 2 +- kernel/sched/core.c | 2 +- kernel/sched/deadline.c | 2 +- kernel/sched/rt.c | 2 +- 5 files changed, 7 insertions(+), 7 deletions(-) (limited to 'include/linux') diff --git a/include/linux/printk.h b/include/linux/printk.h index 8752f7595b27..7847301e2837 100644 --- a/include/linux/printk.h +++ b/include/linux/printk.h @@ -128,9 +128,9 @@ asmlinkage __printf(1, 2) __cold int printk(const char *fmt, ...); /* - * Special printk facility for scheduler use only, _DO_NOT_USE_ ! + * Special printk facility for scheduler/timekeeping use only, _DO_NOT_USE_ ! */ -__printf(1, 2) __cold int printk_sched(const char *fmt, ...); +__printf(1, 2) __cold int printk_deferred(const char *fmt, ...); /* * Please don't use printk_ratelimit(), because it shares ratelimiting state @@ -165,7 +165,7 @@ int printk(const char *s, ...) return 0; } static inline __printf(1, 2) __cold -int printk_sched(const char *s, ...) +int printk_deferred(const char *s, ...) { return 0; } diff --git a/kernel/printk/printk.c b/kernel/printk/printk.c index dc2b8bd9bc1e..35d9db251903 100644 --- a/kernel/printk/printk.c +++ b/kernel/printk/printk.c @@ -2585,7 +2585,7 @@ void wake_up_klogd(void) preempt_enable(); } -int printk_sched(const char *fmt, ...) +int printk_deferred(const char *fmt, ...) { va_list args; int r; diff --git a/kernel/sched/core.c b/kernel/sched/core.c index 913c6d6cc2c1..caf03e89a068 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -1367,7 +1367,7 @@ out: * leave kernel. */ if (p->mm && printk_ratelimit()) { - printk_sched("process %d (%s) no longer affine to cpu%d\n", + printk_deferred("process %d (%s) no longer affine to cpu%d\n", task_pid_nr(p), p->comm, cpu); } } diff --git a/kernel/sched/deadline.c b/kernel/sched/deadline.c index f9ca7d19781a..d17e1c48a79d 100644 --- a/kernel/sched/deadline.c +++ b/kernel/sched/deadline.c @@ -352,7 +352,7 @@ static void replenish_dl_entity(struct sched_dl_entity *dl_se, if (!lag_once) { lag_once = true; - printk_sched("sched: DL replenish lagged to much\n"); + printk_deferred("sched: DL replenish lagged to much\n"); } dl_se->deadline = rq_clock(rq) + pi_se->dl_deadline; dl_se->runtime = pi_se->dl_runtime; diff --git a/kernel/sched/rt.c b/kernel/sched/rt.c index 0ebfd7a29472..5d7667b37c21 100644 --- a/kernel/sched/rt.c +++ b/kernel/sched/rt.c @@ -896,7 +896,7 @@ static int sched_rt_runtime_exceeded(struct rt_rq *rt_rq) if (!once) { once = true; - printk_sched("sched: RT throttling activated\n"); + printk_deferred("sched: RT throttling activated\n"); } } else { /* -- cgit v1.2.3-71-gd317 From c224815dac9c739b79050d3cc67443ff500bc478 Mon Sep 17 00:00:00 2001 From: John Stultz Date: Wed, 4 Jun 2014 16:11:41 -0700 Subject: printk: Add printk_deferred_once Two of the three prink_deferred uses are really printk_once style uses, so add a printk_deferred_once macro to simplify those call sites. Signed-off-by: John Stultz Reviewed-by: Steven Rostedt Reviewed-by: Jan Kara Cc: Peter Zijlstra Cc: Jiri Bohac Cc: Thomas Gleixner Cc: Ingo Molnar Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/printk.h | 11 +++++++++++ kernel/sched/deadline.c | 7 +------ kernel/sched/rt.c | 8 +------- 3 files changed, 13 insertions(+), 13 deletions(-) (limited to 'include/linux') diff --git a/include/linux/printk.h b/include/linux/printk.h index 7847301e2837..f086d6c99dbc 100644 --- a/include/linux/printk.h +++ b/include/linux/printk.h @@ -266,9 +266,20 @@ extern asmlinkage void dump_stack(void) __cold; printk(fmt, ##__VA_ARGS__); \ } \ }) +#define printk_deferred_once(fmt, ...) \ +({ \ + static bool __print_once __read_mostly; \ + \ + if (!__print_once) { \ + __print_once = true; \ + printk_deferred(fmt, ##__VA_ARGS__); \ + } \ +}) #else #define printk_once(fmt, ...) \ no_printk(fmt, ##__VA_ARGS__) +#define printk_deferred_once(fmt, ...) \ + no_printk(fmt, ##__VA_ARGS__) #endif #define pr_emerg_once(fmt, ...) \ diff --git a/kernel/sched/deadline.c b/kernel/sched/deadline.c index d17e1c48a79d..e1574fca03b5 100644 --- a/kernel/sched/deadline.c +++ b/kernel/sched/deadline.c @@ -348,12 +348,7 @@ static void replenish_dl_entity(struct sched_dl_entity *dl_se, * entity. */ if (dl_time_before(dl_se->deadline, rq_clock(rq))) { - static bool lag_once = false; - - if (!lag_once) { - lag_once = true; - printk_deferred("sched: DL replenish lagged to much\n"); - } + printk_deferred_once("sched: DL replenish lagged to much\n"); dl_se->deadline = rq_clock(rq) + pi_se->dl_deadline; dl_se->runtime = pi_se->dl_runtime; } diff --git a/kernel/sched/rt.c b/kernel/sched/rt.c index 5d7667b37c21..b3512f1afce9 100644 --- a/kernel/sched/rt.c +++ b/kernel/sched/rt.c @@ -890,14 +890,8 @@ static int sched_rt_runtime_exceeded(struct rt_rq *rt_rq) * but accrue some time due to boosting. */ if (likely(rt_b->rt_runtime)) { - static bool once = false; - rt_rq->rt_throttled = 1; - - if (!once) { - once = true; - printk_deferred("sched: RT throttling activated\n"); - } + printk_deferred_once("sched: RT throttling activated\n"); } else { /* * In case we did anyway, make it go away, -- cgit v1.2.3-71-gd317 From 6e099f557d9c6797c3ee3ee7b5c8cebe543ec1cc Mon Sep 17 00:00:00 2001 From: Dan Streetman Date: Wed, 4 Jun 2014 16:11:44 -0700 Subject: Documentation: expand/clarify debug documentation The pr_debug() and related debug print macros all differ from the normal pr_XXX() macros, in that the normal ones print unconditionally, while the debug macros are compiled out unless DEBUG is defined or CONFIG_DYNAMIC_DEBUG is set. This isn't obvious, and the only way to find this out is either to review the actual printk.h code or to read CodingStyle, and the message there doesn't highlight the fact. Change Documentation/CodingStyle to clearly indicate that pr_debug() and related debug printing macros behave differently than all other pr_XXX() macros, and attempt to clarify when and where the different debug printing methods might be used. Add short comment to printk.h above the pr_XXX() macros indicating that while these macros print unconditionally, pr_debug() does not. Signed-off-by: Dan Streetman Cc: Joe Perches Cc: Fabian Frederick Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- Documentation/CodingStyle | 22 +++++++++++++++------- include/linux/printk.h | 6 ++++++ 2 files changed, 21 insertions(+), 7 deletions(-) (limited to 'include/linux') diff --git a/Documentation/CodingStyle b/Documentation/CodingStyle index 7fe0546c504a..6b6bef31e956 100644 --- a/Documentation/CodingStyle +++ b/Documentation/CodingStyle @@ -660,15 +660,23 @@ There are a number of driver model diagnostic macros in which you should use to make sure messages are matched to the right device and driver, and are tagged with the right level: dev_err(), dev_warn(), dev_info(), and so forth. For messages that aren't associated with a -particular device, defines pr_debug() and pr_info(). +particular device, defines pr_notice(), pr_info(), +pr_warn(), pr_err(), etc. Coming up with good debugging messages can be quite a challenge; and once -you have them, they can be a huge help for remote troubleshooting. Such -messages should be compiled out when the DEBUG symbol is not defined (that -is, by default they are not included). When you use dev_dbg() or pr_debug(), -that's automatic. Many subsystems have Kconfig options to turn on -DDEBUG. -A related convention uses VERBOSE_DEBUG to add dev_vdbg() messages to the -ones already enabled by DEBUG. +you have them, they can be a huge help for remote troubleshooting. However +debug message printing is handled differently than printing other non-debug +messages. While the other pr_XXX() functions print unconditionally, +pr_debug() does not; it is compiled out by default, unless either DEBUG is +defined or CONFIG_DYNAMIC_DEBUG is set. That is true for dev_dbg() also, +and a related convention uses VERBOSE_DEBUG to add dev_vdbg() messages to +the ones already enabled by DEBUG. + +Many subsystems have Kconfig debug options to turn on -DDEBUG in the +corresponding Makefile; in other cases specific files #define DEBUG. And +when a debug message should be unconditionally printed, such as if it is +already inside a debug-related #ifdef secton, printk(KERN_DEBUG ...) can be +used. Chapter 14: Allocating memory diff --git a/include/linux/printk.h b/include/linux/printk.h index f086d6c99dbc..37f3a6589c1c 100644 --- a/include/linux/printk.h +++ b/include/linux/printk.h @@ -210,6 +210,12 @@ extern asmlinkage void dump_stack(void) __cold; #define pr_fmt(fmt) fmt #endif +/* + * These can be used to print at the various log levels. + * All of these will print unconditionally, although note that pr_debug() + * and other debug macros are compiled out unless either DEBUG is defined + * or CONFIG_DYNAMIC_DEBUG is set. + */ #define pr_emerg(fmt, ...) \ printk(KERN_EMERG pr_fmt(fmt), ##__VA_ARGS__) #define pr_alert(fmt, ...) \ -- cgit v1.2.3-71-gd317 From a8fe19ebfbfd90ec17c02284717238b02efb9580 Mon Sep 17 00:00:00 2001 From: Borislav Petkov Date: Wed, 4 Jun 2014 16:11:46 -0700 Subject: kernel/printk: use symbolic defines for console loglevels ... instead of naked numbers. Stuff in sysrq.c used to set it to 8 which is supposed to mean above default level so set it to DEBUG instead as we're terminating/killing all tasks and we want to be verbose there. Also, correct the check in x86_64_start_kernel which should be >= as we're clearly issuing the string there for all debug levels, not only the magical 10. Signed-off-by: Borislav Petkov Acked-by: Kees Cook Acked-by: Randy Dunlap Cc: Joe Perches Cc: Valdis Kletnieks Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- arch/x86/kernel/head64.c | 2 +- arch/x86/platform/uv/uv_nmi.c | 2 +- drivers/nubus/nubus.c | 18 +++++++++--------- drivers/tty/sysrq.c | 8 ++++---- include/linux/printk.h | 15 +++++++++++++-- init/main.c | 4 ++-- kernel/debug/kdb/kdb_bt.c | 2 +- kernel/debug/kdb/kdb_io.c | 2 +- kernel/debug/kdb/kdb_main.c | 2 +- kernel/printk/printk.c | 13 +++---------- 10 files changed, 36 insertions(+), 32 deletions(-) (limited to 'include/linux') diff --git a/arch/x86/kernel/head64.c b/arch/x86/kernel/head64.c index 068054f4bf20..eda1a865641e 100644 --- a/arch/x86/kernel/head64.c +++ b/arch/x86/kernel/head64.c @@ -172,7 +172,7 @@ asmlinkage __visible void __init x86_64_start_kernel(char * real_mode_data) */ load_ucode_bsp(); - if (console_loglevel == 10) + if (console_loglevel >= CONSOLE_LOGLEVEL_DEBUG) early_printk("Kernel alive\n"); clear_page(init_level4_pgt); diff --git a/arch/x86/platform/uv/uv_nmi.c b/arch/x86/platform/uv/uv_nmi.c index be27da60dc8f..c89c93320c12 100644 --- a/arch/x86/platform/uv/uv_nmi.c +++ b/arch/x86/platform/uv/uv_nmi.c @@ -85,7 +85,7 @@ static cpumask_var_t uv_nmi_cpu_mask; * Default is all stack dumps go to the console and buffer. * Lower level to send to log buffer only. */ -static int uv_nmi_loglevel = 7; +static int uv_nmi_loglevel = CONSOLE_LOGLEVEL_DEFAULT; module_param_named(dump_loglevel, uv_nmi_loglevel, int, 0644); /* diff --git a/drivers/nubus/nubus.c b/drivers/nubus/nubus.c index 43926cd25ae8..5066a7ef7b6c 100644 --- a/drivers/nubus/nubus.c +++ b/drivers/nubus/nubus.c @@ -473,7 +473,7 @@ static struct nubus_dev* __init if (slot == 0 && (unsigned long)dir.base % 2) dir.base += 1; - if (console_loglevel >= 10) + if (console_loglevel >= CONSOLE_LOGLEVEL_DEBUG) printk(KERN_DEBUG "nubus_get_functional_resource: parent is 0x%p, dir is 0x%p\n", parent->base, dir.base); @@ -568,7 +568,7 @@ static int __init nubus_get_vidnames(struct nubus_board* board, printk(KERN_INFO " video modes supported:\n"); nubus_get_subdir(parent, &dir); - if (console_loglevel >= 10) + if (console_loglevel >= CONSOLE_LOGLEVEL_DEBUG) printk(KERN_DEBUG "nubus_get_vidnames: parent is 0x%p, dir is 0x%p\n", parent->base, dir.base); @@ -629,7 +629,7 @@ static int __init nubus_get_vendorinfo(struct nubus_board* board, printk(KERN_INFO " vendor info:\n"); nubus_get_subdir(parent, &dir); - if (console_loglevel >= 10) + if (console_loglevel >= CONSOLE_LOGLEVEL_DEBUG) printk(KERN_DEBUG "nubus_get_vendorinfo: parent is 0x%p, dir is 0x%p\n", parent->base, dir.base); @@ -654,7 +654,7 @@ static int __init nubus_get_board_resource(struct nubus_board* board, int slot, struct nubus_dirent ent; nubus_get_subdir(parent, &dir); - if (console_loglevel >= 10) + if (console_loglevel >= CONSOLE_LOGLEVEL_DEBUG) printk(KERN_DEBUG "nubus_get_board_resource: parent is 0x%p, dir is 0x%p\n", parent->base, dir.base); @@ -753,19 +753,19 @@ static void __init nubus_find_rom_dir(struct nubus_board* board) if (nubus_readdir(&dir, &ent) == -1) goto badrom; - if (console_loglevel >= 10) + if (console_loglevel >= CONSOLE_LOGLEVEL_DEBUG) printk(KERN_INFO "nubus_get_rom_dir: entry %02x %06x\n", ent.type, ent.data); /* This one takes us to where we want to go. */ if (nubus_readdir(&dir, &ent) == -1) goto badrom; - if (console_loglevel >= 10) + if (console_loglevel >= CONSOLE_LOGLEVEL_DEBUG) printk(KERN_DEBUG "nubus_get_rom_dir: entry %02x %06x\n", ent.type, ent.data); nubus_get_subdir(&ent, &dir); /* Resource ID 01, also an "Unknown Macintosh" */ if (nubus_readdir(&dir, &ent) == -1) goto badrom; - if (console_loglevel >= 10) + if (console_loglevel >= CONSOLE_LOGLEVEL_DEBUG) printk(KERN_DEBUG "nubus_get_rom_dir: entry %02x %06x\n", ent.type, ent.data); /* FIXME: the first one is *not* always the right one. We @@ -780,7 +780,7 @@ static void __init nubus_find_rom_dir(struct nubus_board* board) path to that address... */ if (nubus_readdir(&dir, &ent) == -1) goto badrom; - if (console_loglevel >= 10) + if (console_loglevel >= CONSOLE_LOGLEVEL_DEBUG) printk(KERN_DEBUG "nubus_get_rom_dir: entry %02x %06x\n", ent.type, ent.data); /* Bwahahahaha... */ @@ -816,7 +816,7 @@ static struct nubus_board* __init nubus_add_board(int slot, int bytelanes) board->fblock = rp; /* Dump the format block for debugging purposes */ - if (console_loglevel >= 10) { + if (console_loglevel >= CONSOLE_LOGLEVEL_DEBUG) { int i; printk(KERN_DEBUG "Slot %X, format block at 0x%p\n", slot, rp); diff --git a/drivers/tty/sysrq.c b/drivers/tty/sysrq.c index ce396ecdf412..b767a64e49d9 100644 --- a/drivers/tty/sysrq.c +++ b/drivers/tty/sysrq.c @@ -88,7 +88,7 @@ static void sysrq_handle_loglevel(int key) int i; i = key - '0'; - console_loglevel = 7; + console_loglevel = CONSOLE_LOGLEVEL_DEFAULT; printk("Loglevel set to %d\n", i); console_loglevel = i; } @@ -343,7 +343,7 @@ static void send_sig_all(int sig) static void sysrq_handle_term(int key) { send_sig_all(SIGTERM); - console_loglevel = 8; + console_loglevel = CONSOLE_LOGLEVEL_DEBUG; } static struct sysrq_key_op sysrq_term_op = { .handler = sysrq_handle_term, @@ -387,7 +387,7 @@ static struct sysrq_key_op sysrq_thaw_op = { static void sysrq_handle_kill(int key) { send_sig_all(SIGKILL); - console_loglevel = 8; + console_loglevel = CONSOLE_LOGLEVEL_DEBUG; } static struct sysrq_key_op sysrq_kill_op = { .handler = sysrq_handle_kill, @@ -520,7 +520,7 @@ void __handle_sysrq(int key, bool check_mask) * routing in the consumers of /proc/kmsg. */ orig_log_level = console_loglevel; - console_loglevel = 7; + console_loglevel = CONSOLE_LOGLEVEL_DEFAULT; printk(KERN_INFO "SysRq : "); op_p = __sysrq_get_key_op(key); diff --git a/include/linux/printk.h b/include/linux/printk.h index 37f3a6589c1c..319ff7e53efb 100644 --- a/include/linux/printk.h +++ b/include/linux/printk.h @@ -30,6 +30,17 @@ static inline const char *printk_skip_level(const char *buffer) return buffer; } +/* printk's without a loglevel use this.. */ +#define DEFAULT_MESSAGE_LOGLEVEL CONFIG_DEFAULT_MESSAGE_LOGLEVEL + +/* We show everything that is MORE important than this.. */ +#define CONSOLE_LOGLEVEL_SILENT 0 /* Mum's the word */ +#define CONSOLE_LOGLEVEL_MIN 1 /* Minimum loglevel we let people use */ +#define CONSOLE_LOGLEVEL_QUIET 4 /* Shhh ..., when booted with "quiet" */ +#define CONSOLE_LOGLEVEL_DEFAULT 7 /* anything MORE serious than KERN_DEBUG */ +#define CONSOLE_LOGLEVEL_DEBUG 10 /* issue debug messages */ +#define CONSOLE_LOGLEVEL_MOTORMOUTH 15 /* You can't shut this one up */ + extern int console_printk[]; #define console_loglevel (console_printk[0]) @@ -39,13 +50,13 @@ extern int console_printk[]; static inline void console_silent(void) { - console_loglevel = 0; + console_loglevel = CONSOLE_LOGLEVEL_SILENT; } static inline void console_verbose(void) { if (console_loglevel) - console_loglevel = 15; + console_loglevel = CONSOLE_LOGLEVEL_MOTORMOUTH; } struct va_format { diff --git a/init/main.c b/init/main.c index e08c0b2065a1..04fab8d74c89 100644 --- a/init/main.c +++ b/init/main.c @@ -203,13 +203,13 @@ EXPORT_SYMBOL(loops_per_jiffy); static int __init debug_kernel(char *str) { - console_loglevel = 10; + console_loglevel = CONSOLE_LOGLEVEL_DEBUG; return 0; } static int __init quiet_kernel(char *str) { - console_loglevel = 4; + console_loglevel = CONSOLE_LOGLEVEL_QUIET; return 0; } diff --git a/kernel/debug/kdb/kdb_bt.c b/kernel/debug/kdb/kdb_bt.c index b03e0e814e43..fe15fff5df53 100644 --- a/kernel/debug/kdb/kdb_bt.c +++ b/kernel/debug/kdb/kdb_bt.c @@ -21,7 +21,7 @@ static void kdb_show_stack(struct task_struct *p, void *addr) { int old_lvl = console_loglevel; - console_loglevel = 15; + console_loglevel = CONSOLE_LOGLEVEL_MOTORMOUTH; kdb_trap_printk++; kdb_set_current_task(p); if (addr) { diff --git a/kernel/debug/kdb/kdb_io.c b/kernel/debug/kdb/kdb_io.c index 14ff4849262c..7c70812caea5 100644 --- a/kernel/debug/kdb/kdb_io.c +++ b/kernel/debug/kdb/kdb_io.c @@ -710,7 +710,7 @@ kdb_printit: } if (logging) { saved_loglevel = console_loglevel; - console_loglevel = 0; + console_loglevel = CONSOLE_LOGLEVEL_SILENT; printk(KERN_INFO "%s", kdb_buffer); } diff --git a/kernel/debug/kdb/kdb_main.c b/kernel/debug/kdb/kdb_main.c index 0b097c8a1e50..2f7c760305ca 100644 --- a/kernel/debug/kdb/kdb_main.c +++ b/kernel/debug/kdb/kdb_main.c @@ -1091,7 +1091,7 @@ static int kdb_reboot(int argc, const char **argv) static void kdb_dumpregs(struct pt_regs *regs) { int old_lvl = console_loglevel; - console_loglevel = 15; + console_loglevel = CONSOLE_LOGLEVEL_MOTORMOUTH; kdb_trap_printk++; show_regs(regs); kdb_trap_printk--; diff --git a/kernel/printk/printk.c b/kernel/printk/printk.c index 923c5d4e4202..ea2d5f6962ed 100644 --- a/kernel/printk/printk.c +++ b/kernel/printk/printk.c @@ -54,18 +54,11 @@ #include "console_cmdline.h" #include "braille.h" -/* printk's without a loglevel use this.. */ -#define DEFAULT_MESSAGE_LOGLEVEL CONFIG_DEFAULT_MESSAGE_LOGLEVEL - -/* We show everything that is MORE important than this.. */ -#define MINIMUM_CONSOLE_LOGLEVEL 1 /* Minimum loglevel we let people use */ -#define DEFAULT_CONSOLE_LOGLEVEL 7 /* anything MORE serious than KERN_DEBUG */ - int console_printk[4] = { - DEFAULT_CONSOLE_LOGLEVEL, /* console_loglevel */ + CONSOLE_LOGLEVEL_DEFAULT, /* console_loglevel */ DEFAULT_MESSAGE_LOGLEVEL, /* default_message_loglevel */ - MINIMUM_CONSOLE_LOGLEVEL, /* minimum_console_loglevel */ - DEFAULT_CONSOLE_LOGLEVEL, /* default_console_loglevel */ + CONSOLE_LOGLEVEL_MIN, /* minimum_console_loglevel */ + CONSOLE_LOGLEVEL_DEFAULT, /* default_console_loglevel */ }; /* Deferred messaged from sched code are marked by this special level */ -- cgit v1.2.3-71-gd317 From 34a1b7236ad6113883f6c448d1da854cad60265e Mon Sep 17 00:00:00 2001 From: Oleg Nesterov Date: Wed, 4 Jun 2014 16:12:19 -0700 Subject: kthreads: kill CLONE_KERNEL, change kernel_thread(kernel_init) to avoid CLONE_SIGHAND 1. Remove CLONE_KERNEL, it has no users and it is dangerous. The (old) comment says "List of flags we want to share for kernel threads" but this is not true, we do not want to share ->sighand by default. This flag can only be used if the caller is sure that both parent/child will never play with signals (say, allow_signal/etc). 2. Change rest_init() to clone kernel_init() without CLONE_SIGHAND. In this case CLONE_SIGHAND does not really hurt, and it looks like optimization because copy_sighand() can avoid kmem_cache_alloc(). But in fact this only adds the minor pessimization. kernel_init() is going to exec the init process, and de_thread() will need to unshare ->sighand and do kmem_cache_alloc(sighand_cachep) anyway, but it needs to do more work and take tasklist_lock and siglock. Signed-off-by: Oleg Nesterov Acked-by: Peter Zijlstra Acked-by: Steven Rostedt Cc: Frederic Weisbecker Cc: Ingo Molnar Cc: Mathieu Desnoyers Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/sched.h | 6 ------ init/main.c | 2 +- 2 files changed, 1 insertion(+), 7 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sched.h b/include/linux/sched.h index 611676fd4c2c..8fcd0e6098d9 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -136,12 +136,6 @@ struct filename; #define VMACACHE_SIZE (1U << VMACACHE_BITS) #define VMACACHE_MASK (VMACACHE_SIZE - 1) -/* - * List of flags we want to share for kernel threads, - * if only because they are not used by them anyway. - */ -#define CLONE_KERNEL (CLONE_FS | CLONE_FILES | CLONE_SIGHAND) - /* * These are the constant used to fake the fixed-point load-average * counting. Some notes: diff --git a/init/main.c b/init/main.c index 8ac3833f2bdf..4de815c0309a 100644 --- a/init/main.c +++ b/init/main.c @@ -380,7 +380,7 @@ static noinline void __init_refok rest_init(void) * the init task will end up wanting to create kthreads, which, if * we schedule it before we create kthreadd, will OOPS. */ - kernel_thread(kernel_init, NULL, CLONE_FS | CLONE_SIGHAND); + kernel_thread(kernel_init, NULL, CLONE_FS); numa_default_policy(); pid = kernel_thread(kthreadd, NULL, CLONE_FS | CLONE_FILES); rcu_read_lock(); -- cgit v1.2.3-71-gd317 From 647f010bff6795b3e85c2b5a7768c0594a049ab0 Mon Sep 17 00:00:00 2001 From: Andrew Morton Date: Wed, 4 Jun 2014 16:12:20 -0700 Subject: init/main.c: remove an ifdef Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/proc_fs.h | 4 ++++ init/main.c | 2 -- 2 files changed, 4 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/proc_fs.h b/include/linux/proc_fs.h index 608e60a74c3c..9d117f61d976 100644 --- a/include/linux/proc_fs.h +++ b/include/linux/proc_fs.h @@ -44,6 +44,10 @@ extern int remove_proc_subtree(const char *, struct proc_dir_entry *); #else /* CONFIG_PROC_FS */ +static inline void proc_root_init(void) +{ +} + static inline void proc_flush_task(struct task_struct *task) { } diff --git a/init/main.c b/init/main.c index 4de815c0309a..17d47bcdf573 100644 --- a/init/main.c +++ b/init/main.c @@ -629,9 +629,7 @@ asmlinkage __visible void __init start_kernel(void) signals_init(); /* rootfs populating might need page-writeback */ page_writeback_init(); -#ifdef CONFIG_PROC_FS proc_root_init(); -#endif cgroup_init(); cpuset_init(); taskstats_init_early(); -- cgit v1.2.3-71-gd317