diff options
author | Linus Torvalds <torvalds@linux-foundation.org> | 2016-01-17 12:58:52 -0800 |
---|---|---|
committer | Linus Torvalds <torvalds@linux-foundation.org> | 2016-01-17 12:58:52 -0800 |
commit | 0cbeafb245ca568bc0765645aa64f0451b716657 (patch) | |
tree | 663c09ff5a62a1b2b66a17c4dfe0413603530a36 /include | |
parent | 58cf279acac3080ce03eeea5ca268210b3165fe1 (diff) | |
parent | 06b031de22d28ae76b2e5bfaf22c56a265a1e106 (diff) |
Merge branch 'akpm' (patches from Andrew)
Merge second patch-bomb from Andrew Morton:
- more MM stuff:
- Kirill's page-flags rework
- Kirill's now-allegedly-fixed THP rework
- MADV_FREE implementation
- DAX feature work (msync/fsync). This isn't quite complete but DAX
is new and it's good enough and the guys have a handle on what
needs to be done - I expect this to be wrapped in the next week or
two.
- some vsprintf maintenance work
- various other misc bits
* emailed patches from Andrew Morton <akpm@linux-foundation.org>: (145 commits)
printk: change recursion_bug type to bool
lib/vsprintf: factor out %pN[F] handler as netdev_bits()
lib/vsprintf: refactor duplicate code to special_hex_number()
printk-formats.txt: remove unimplemented %pT
printk: help pr_debug and pr_devel to optimize out arguments
lib/test_printf.c: test dentry printing
lib/test_printf.c: add test for large bitmaps
lib/test_printf.c: account for kvasprintf tests
lib/test_printf.c: add a few number() tests
lib/test_printf.c: test precision quirks
lib/test_printf.c: check for out-of-bound writes
lib/test_printf.c: don't BUG
lib/kasprintf.c: add sanity check to kvasprintf
lib/vsprintf.c: warn about too large precisions and field widths
lib/vsprintf.c: help gcc make number() smaller
lib/vsprintf.c: expand field_width to 24 bits
lib/vsprintf.c: eliminate potential race in string()
lib/vsprintf.c: move string() below widen_string()
lib/vsprintf.c: pull out padding code from dentry_name()
printk: do cond_resched() between lines while outputting to consoles
...
Diffstat (limited to 'include')
31 files changed, 798 insertions, 373 deletions
diff --git a/include/asm-generic/pgtable.h b/include/asm-generic/pgtable.h index 3a6803cb0ec9..0b3c0d39ef75 100644 --- a/include/asm-generic/pgtable.h +++ b/include/asm-generic/pgtable.h @@ -1,6 +1,8 @@ #ifndef _ASM_GENERIC_PGTABLE_H #define _ASM_GENERIC_PGTABLE_H +#include <linux/pfn.h> + #ifndef __ASSEMBLY__ #ifdef CONFIG_MMU @@ -207,11 +209,6 @@ static inline void pmdp_set_wrprotect(struct mm_struct *mm, #endif /* CONFIG_TRANSPARENT_HUGEPAGE */ #endif -#ifndef __HAVE_ARCH_PMDP_SPLITTING_FLUSH -extern void pmdp_splitting_flush(struct vm_area_struct *vma, - unsigned long address, pmd_t *pmdp); -#endif - #ifndef pmdp_collapse_flush #ifdef CONFIG_TRANSPARENT_HUGEPAGE extern pmd_t pmdp_collapse_flush(struct vm_area_struct *vma, @@ -554,7 +551,7 @@ static inline int track_pfn_remap(struct vm_area_struct *vma, pgprot_t *prot, * by vm_insert_pfn(). */ static inline int track_pfn_insert(struct vm_area_struct *vma, pgprot_t *prot, - unsigned long pfn) + pfn_t pfn) { return 0; } @@ -589,7 +586,7 @@ extern int track_pfn_remap(struct vm_area_struct *vma, pgprot_t *prot, unsigned long pfn, unsigned long addr, unsigned long size); extern int track_pfn_insert(struct vm_area_struct *vma, pgprot_t *prot, - unsigned long pfn); + pfn_t pfn); extern int track_pfn_copy(struct vm_area_struct *vma); extern void untrack_pfn(struct vm_area_struct *vma, unsigned long pfn, unsigned long size); @@ -627,10 +624,6 @@ static inline int pmd_trans_huge(pmd_t pmd) { return 0; } -static inline int pmd_trans_splitting(pmd_t pmd) -{ - return 0; -} #ifndef __HAVE_ARCH_PMD_WRITE static inline int pmd_write(pmd_t pmd) { diff --git a/include/asm-generic/sections.h b/include/asm-generic/sections.h index b58fd667f87b..af0254c09424 100644 --- a/include/asm-generic/sections.h +++ b/include/asm-generic/sections.h @@ -4,6 +4,7 @@ /* References to section boundaries */ #include <linux/compiler.h> +#include <linux/types.h> /* * Usage guidelines: @@ -63,4 +64,68 @@ static inline int arch_is_kernel_data(unsigned long addr) } #endif +/** + * memory_contains - checks if an object is contained within a memory region + * @begin: virtual address of the beginning of the memory region + * @end: virtual address of the end of the memory region + * @virt: virtual address of the memory object + * @size: size of the memory object + * + * Returns: true if the object specified by @virt and @size is entirely + * contained within the memory region defined by @begin and @end, false + * otherwise. + */ +static inline bool memory_contains(void *begin, void *end, void *virt, + size_t size) +{ + return virt >= begin && virt + size <= end; +} + +/** + * memory_intersects - checks if the region occupied by an object intersects + * with another memory region + * @begin: virtual address of the beginning of the memory regien + * @end: virtual address of the end of the memory region + * @virt: virtual address of the memory object + * @size: size of the memory object + * + * Returns: true if an object's memory region, specified by @virt and @size, + * intersects with the region specified by @begin and @end, false otherwise. + */ +static inline bool memory_intersects(void *begin, void *end, void *virt, + size_t size) +{ + void *vend = virt + size; + + return (virt >= begin && virt < end) || (vend >= begin && vend < end); +} + +/** + * init_section_contains - checks if an object is contained within the init + * section + * @virt: virtual address of the memory object + * @size: size of the memory object + * + * Returns: true if the object specified by @virt and @size is entirely + * contained within the init section, false otherwise. + */ +static inline bool init_section_contains(void *virt, size_t size) +{ + return memory_contains(__init_begin, __init_end, virt, size); +} + +/** + * init_section_intersects - checks if the region occupied by an object + * intersects with the init section + * @virt: virtual address of the memory object + * @size: size of the memory object + * + * Returns: true if an object's memory region, specified by @virt and @size, + * intersects with the init section, false otherwise. + */ +static inline bool init_section_intersects(void *virt, size_t size) +{ + return memory_intersects(__init_begin, __init_end, virt, size); +} + #endif /* _ASM_GENERIC_SECTIONS_H_ */ diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index c70e3588a48c..bfb64d672e19 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -15,6 +15,7 @@ #include <linux/backing-dev-defs.h> #include <linux/wait.h> #include <linux/mempool.h> +#include <linux/pfn.h> #include <linux/bio.h> #include <linux/stringify.h> #include <linux/gfp.h> @@ -1617,6 +1618,20 @@ static inline bool integrity_req_gap_front_merge(struct request *req, #endif /* CONFIG_BLK_DEV_INTEGRITY */ +/** + * struct blk_dax_ctl - control and output parameters for ->direct_access + * @sector: (input) offset relative to a block_device + * @addr: (output) kernel virtual address for @sector populated by driver + * @pfn: (output) page frame number for @addr populated by driver + * @size: (input) number of bytes requested + */ +struct blk_dax_ctl { + sector_t sector; + void __pmem *addr; + long size; + pfn_t pfn; +}; + struct block_device_operations { int (*open) (struct block_device *, fmode_t); void (*release) (struct gendisk *, fmode_t); @@ -1624,7 +1639,7 @@ struct block_device_operations { int (*ioctl) (struct block_device *, fmode_t, unsigned, unsigned long); int (*compat_ioctl) (struct block_device *, fmode_t, unsigned, unsigned long); long (*direct_access)(struct block_device *, sector_t, void __pmem **, - unsigned long *pfn); + pfn_t *); unsigned int (*check_events) (struct gendisk *disk, unsigned int clearing); /* ->media_changed() is DEPRECATED, use ->check_events() instead */ @@ -1643,8 +1658,7 @@ extern int __blkdev_driver_ioctl(struct block_device *, fmode_t, unsigned int, 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 *); -extern long bdev_direct_access(struct block_device *, sector_t, - void __pmem **addr, unsigned long *pfn, long size); +extern long bdev_direct_access(struct block_device *, struct blk_dax_ctl *); #else /* CONFIG_BLOCK */ struct block_device; diff --git a/include/linux/console.h b/include/linux/console.h index bd194343c346..ea731af2451e 100644 --- a/include/linux/console.h +++ b/include/linux/console.h @@ -150,6 +150,7 @@ extern int console_trylock(void); extern void console_unlock(void); extern void console_conditional_schedule(void); extern void console_unblank(void); +extern void console_flush_on_panic(void); extern struct tty_driver *console_device(int *); extern void console_stop(struct console *); extern void console_start(struct console *); diff --git a/include/linux/err.h b/include/linux/err.h index a729120644d5..56762ab41713 100644 --- a/include/linux/err.h +++ b/include/linux/err.h @@ -37,7 +37,7 @@ static inline bool __must_check IS_ERR(__force const void *ptr) static inline bool __must_check IS_ERR_OR_NULL(__force const void *ptr) { - return !ptr || IS_ERR_VALUE((unsigned long)ptr); + return unlikely(!ptr) || IS_ERR_VALUE((unsigned long)ptr); } /** diff --git a/include/linux/huge_mm.h b/include/linux/huge_mm.h index ecb080d6ff42..cfe81e10bd54 100644 --- a/include/linux/huge_mm.h +++ b/include/linux/huge_mm.h @@ -19,13 +19,16 @@ extern struct page *follow_trans_huge_pmd(struct vm_area_struct *vma, unsigned long addr, pmd_t *pmd, unsigned int flags); +extern int madvise_free_huge_pmd(struct mmu_gather *tlb, + struct vm_area_struct *vma, + pmd_t *pmd, unsigned long addr, unsigned long next); extern int zap_huge_pmd(struct mmu_gather *tlb, struct vm_area_struct *vma, pmd_t *pmd, unsigned long addr); extern int mincore_huge_pmd(struct vm_area_struct *vma, pmd_t *pmd, unsigned long addr, unsigned long end, unsigned char *vec); -extern int move_huge_pmd(struct vm_area_struct *vma, +extern bool move_huge_pmd(struct vm_area_struct *vma, struct vm_area_struct *new_vma, unsigned long old_addr, unsigned long new_addr, unsigned long old_end, @@ -34,8 +37,7 @@ extern int change_huge_pmd(struct vm_area_struct *vma, pmd_t *pmd, unsigned long addr, pgprot_t newprot, int prot_numa); int vmf_insert_pfn_pmd(struct vm_area_struct *, unsigned long addr, pmd_t *, - unsigned long pfn, bool write); - + pfn_t pfn, bool write); enum transparent_hugepage_flag { TRANSPARENT_HUGEPAGE_FLAG, TRANSPARENT_HUGEPAGE_REQ_MADV_FLAG, @@ -48,21 +50,13 @@ enum transparent_hugepage_flag { #endif }; -enum page_check_address_pmd_flag { - PAGE_CHECK_ADDRESS_PMD_FLAG, - PAGE_CHECK_ADDRESS_PMD_NOTSPLITTING_FLAG, - PAGE_CHECK_ADDRESS_PMD_SPLITTING_FLAG, -}; -extern pmd_t *page_check_address_pmd(struct page *page, - struct mm_struct *mm, - unsigned long address, - enum page_check_address_pmd_flag flag, - spinlock_t **ptl); - #define HPAGE_PMD_ORDER (HPAGE_PMD_SHIFT-PAGE_SHIFT) #define HPAGE_PMD_NR (1<<HPAGE_PMD_ORDER) #ifdef CONFIG_TRANSPARENT_HUGEPAGE +struct page *follow_devmap_pmd(struct vm_area_struct *vma, unsigned long addr, + pmd_t *pmd, int flags); + #define HPAGE_PMD_SHIFT PMD_SHIFT #define HPAGE_PMD_SIZE ((1UL) << HPAGE_PMD_SHIFT) #define HPAGE_PMD_MASK (~(HPAGE_PMD_SIZE - 1)) @@ -95,30 +89,28 @@ extern bool is_vma_temporary_stack(struct vm_area_struct *vma); #endif /* CONFIG_DEBUG_VM */ extern unsigned long transparent_hugepage_flags; -extern int split_huge_page_to_list(struct page *page, struct list_head *list); + +extern void prep_transhuge_page(struct page *page); +extern void free_transhuge_page(struct page *page); + +int split_huge_page_to_list(struct page *page, struct list_head *list); static inline int split_huge_page(struct page *page) { return split_huge_page_to_list(page, NULL); } -extern void __split_huge_page_pmd(struct vm_area_struct *vma, - unsigned long address, pmd_t *pmd); -#define split_huge_page_pmd(__vma, __address, __pmd) \ +void deferred_split_huge_page(struct page *page); + +void __split_huge_pmd(struct vm_area_struct *vma, pmd_t *pmd, + unsigned long address); + +#define split_huge_pmd(__vma, __pmd, __address) \ do { \ pmd_t *____pmd = (__pmd); \ - if (unlikely(pmd_trans_huge(*____pmd))) \ - __split_huge_page_pmd(__vma, __address, \ - ____pmd); \ + if (pmd_trans_huge(*____pmd) \ + || pmd_devmap(*____pmd)) \ + __split_huge_pmd(__vma, __pmd, __address); \ } while (0) -#define wait_split_huge_page(__anon_vma, __pmd) \ - do { \ - pmd_t *____pmd = (__pmd); \ - anon_vma_lock_write(__anon_vma); \ - anon_vma_unlock_write(__anon_vma); \ - BUG_ON(pmd_trans_splitting(*____pmd) || \ - pmd_trans_huge(*____pmd)); \ - } while (0) -extern void split_huge_page_pmd_mm(struct mm_struct *mm, unsigned long address, - pmd_t *pmd); + #if HPAGE_PMD_ORDER >= MAX_ORDER #error "hugepages can't be allocated by the buddy allocator" #endif @@ -128,17 +120,17 @@ extern void vma_adjust_trans_huge(struct vm_area_struct *vma, unsigned long start, unsigned long end, long adjust_next); -extern int __pmd_trans_huge_lock(pmd_t *pmd, struct vm_area_struct *vma, +extern bool __pmd_trans_huge_lock(pmd_t *pmd, struct vm_area_struct *vma, spinlock_t **ptl); /* mmap_sem must be held on entry */ -static inline int pmd_trans_huge_lock(pmd_t *pmd, struct vm_area_struct *vma, +static inline bool pmd_trans_huge_lock(pmd_t *pmd, struct vm_area_struct *vma, spinlock_t **ptl) { VM_BUG_ON_VMA(!rwsem_is_locked(&vma->vm_mm->mmap_sem), vma); - if (pmd_trans_huge(*pmd)) + if (pmd_trans_huge(*pmd) || pmd_devmap(*pmd)) return __pmd_trans_huge_lock(pmd, vma, ptl); else - return 0; + return false; } static inline int hpage_nr_pages(struct page *page) { @@ -183,11 +175,8 @@ static inline int split_huge_page(struct page *page) { return 0; } -#define split_huge_page_pmd(__vma, __address, __pmd) \ - do { } while (0) -#define wait_split_huge_page(__anon_vma, __pmd) \ - do { } while (0) -#define split_huge_page_pmd_mm(__mm, __address, __pmd) \ +static inline void deferred_split_huge_page(struct page *page) {} +#define split_huge_pmd(__vma, __pmd, __address) \ do { } while (0) static inline int hugepage_madvise(struct vm_area_struct *vma, unsigned long *vm_flags, int advice) @@ -201,10 +190,10 @@ static inline void vma_adjust_trans_huge(struct vm_area_struct *vma, long adjust_next) { } -static inline int pmd_trans_huge_lock(pmd_t *pmd, struct vm_area_struct *vma, +static inline bool pmd_trans_huge_lock(pmd_t *pmd, struct vm_area_struct *vma, spinlock_t **ptl) { - return 0; + return false; } static inline int do_huge_pmd_numa_page(struct mm_struct *mm, struct vm_area_struct *vma, @@ -218,6 +207,12 @@ static inline bool is_huge_zero_page(struct page *page) return false; } + +static inline struct page *follow_devmap_pmd(struct vm_area_struct *vma, + unsigned long addr, pmd_t *pmd, int flags) +{ + return NULL; +} #endif /* CONFIG_TRANSPARENT_HUGEPAGE */ #endif /* _LINUX_HUGE_MM_H */ diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h index e76574d8f9b5..7d953c2542a8 100644 --- a/include/linux/hugetlb.h +++ b/include/linux/hugetlb.h @@ -8,6 +8,7 @@ #include <linux/cgroup.h> #include <linux/list.h> #include <linux/kref.h> +#include <asm/pgtable.h> struct ctl_table; struct user_struct; diff --git a/include/linux/io.h b/include/linux/io.h index de64c1e53612..fffd88d7f426 100644 --- a/include/linux/io.h +++ b/include/linux/io.h @@ -89,21 +89,6 @@ void devm_memunmap(struct device *dev, void *addr); void *__devm_memremap_pages(struct device *dev, struct resource *res); -#ifdef CONFIG_ZONE_DEVICE -void *devm_memremap_pages(struct device *dev, struct resource *res); -#else -static inline void *devm_memremap_pages(struct device *dev, struct resource *res) -{ - /* - * Fail attempts to call devm_memremap_pages() without - * ZONE_DEVICE support enabled, this requires callers to fall - * back to plain devm_memremap() based on config - */ - WARN_ON_ONCE(1); - return ERR_PTR(-ENXIO); -} -#endif - /* * Some systems do not have legacy ISA devices. * /dev/port is not a valid interface on these systems. diff --git a/include/linux/kdev_t.h b/include/linux/kdev_t.h index 052c7b32cc91..8e9e288b08c1 100644 --- a/include/linux/kdev_t.h +++ b/include/linux/kdev_t.h @@ -35,11 +35,6 @@ static inline dev_t old_decode_dev(u16 val) return MKDEV((val >> 8) & 255, val & 255); } -static inline bool new_valid_dev(dev_t dev) -{ - return 1; -} - static inline u32 new_encode_dev(dev_t dev) { unsigned major = MAJOR(dev); diff --git a/include/linux/kernel.h b/include/linux/kernel.h index 7311c3294e25..f31638c6e873 100644 --- a/include/linux/kernel.h +++ b/include/linux/kernel.h @@ -202,26 +202,26 @@ extern int _cond_resched(void); /** * abs - return absolute value of an argument - * @x: the value. If it is unsigned type, it is converted to signed type first - * (s64, long or int depending on its size). + * @x: the value. If it is unsigned type, it is converted to signed type first. + * char is treated as if it was signed (regardless of whether it really is) + * but the macro's return type is preserved as char. * - * Return: an absolute value of x. If x is 64-bit, macro's return type is s64, - * otherwise it is signed long. + * Return: an absolute value of x. */ -#define abs(x) __builtin_choose_expr(sizeof(x) == sizeof(s64), ({ \ - s64 __x = (x); \ - (__x < 0) ? -__x : __x; \ - }), ({ \ - long ret; \ - if (sizeof(x) == sizeof(long)) { \ - long __x = (x); \ - ret = (__x < 0) ? -__x : __x; \ - } else { \ - int __x = (x); \ - ret = (__x < 0) ? -__x : __x; \ - } \ - ret; \ - })) +#define abs(x) __abs_choose_expr(x, long long, \ + __abs_choose_expr(x, long, \ + __abs_choose_expr(x, int, \ + __abs_choose_expr(x, short, \ + __abs_choose_expr(x, char, \ + __builtin_choose_expr( \ + __builtin_types_compatible_p(typeof(x), char), \ + (char)({ signed char __x = (x); __x<0?-__x:__x; }), \ + ((void)0))))))) + +#define __abs_choose_expr(x, type, other) __builtin_choose_expr( \ + __builtin_types_compatible_p(typeof(x), signed type) || \ + __builtin_types_compatible_p(typeof(x), unsigned type), \ + ({ signed type __x = (x); __x < 0 ? -__x : __x; }), other) /** * reciprocal_scale - "scale" a value into range [0, ep_ro) diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index f707f74055c3..861f690aa791 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -66,7 +66,7 @@ * error pfns indicate that the gfn is in slot but faild to * translate it to pfn on host. */ -static inline bool is_error_pfn(pfn_t pfn) +static inline bool is_error_pfn(kvm_pfn_t pfn) { return !!(pfn & KVM_PFN_ERR_MASK); } @@ -76,13 +76,13 @@ static inline bool is_error_pfn(pfn_t pfn) * translated to pfn - it is not in slot or failed to * translate it to pfn. */ -static inline bool is_error_noslot_pfn(pfn_t pfn) +static inline bool is_error_noslot_pfn(kvm_pfn_t pfn) { return !!(pfn & KVM_PFN_ERR_NOSLOT_MASK); } /* noslot pfn indicates that the gfn is not in slot. */ -static inline bool is_noslot_pfn(pfn_t pfn) +static inline bool is_noslot_pfn(kvm_pfn_t pfn) { return pfn == KVM_PFN_NOSLOT; } @@ -591,19 +591,20 @@ void kvm_release_page_clean(struct page *page); void kvm_release_page_dirty(struct page *page); void kvm_set_page_accessed(struct page *page); -pfn_t gfn_to_pfn_atomic(struct kvm *kvm, gfn_t gfn); -pfn_t gfn_to_pfn(struct kvm *kvm, gfn_t gfn); -pfn_t gfn_to_pfn_prot(struct kvm *kvm, gfn_t gfn, bool write_fault, +kvm_pfn_t gfn_to_pfn_atomic(struct kvm *kvm, gfn_t gfn); +kvm_pfn_t gfn_to_pfn(struct kvm *kvm, gfn_t gfn); +kvm_pfn_t gfn_to_pfn_prot(struct kvm *kvm, gfn_t gfn, bool write_fault, bool *writable); -pfn_t gfn_to_pfn_memslot(struct kvm_memory_slot *slot, gfn_t gfn); -pfn_t gfn_to_pfn_memslot_atomic(struct kvm_memory_slot *slot, gfn_t gfn); -pfn_t __gfn_to_pfn_memslot(struct kvm_memory_slot *slot, gfn_t gfn, bool atomic, - bool *async, bool write_fault, bool *writable); +kvm_pfn_t gfn_to_pfn_memslot(struct kvm_memory_slot *slot, gfn_t gfn); +kvm_pfn_t gfn_to_pfn_memslot_atomic(struct kvm_memory_slot *slot, gfn_t gfn); +kvm_pfn_t __gfn_to_pfn_memslot(struct kvm_memory_slot *slot, gfn_t gfn, + bool atomic, bool *async, bool write_fault, + bool *writable); -void kvm_release_pfn_clean(pfn_t pfn); -void kvm_set_pfn_dirty(pfn_t pfn); -void kvm_set_pfn_accessed(pfn_t pfn); -void kvm_get_pfn(pfn_t pfn); +void kvm_release_pfn_clean(kvm_pfn_t pfn); +void kvm_set_pfn_dirty(kvm_pfn_t pfn); +void kvm_set_pfn_accessed(kvm_pfn_t pfn); +void kvm_get_pfn(kvm_pfn_t pfn); int kvm_read_guest_page(struct kvm *kvm, gfn_t gfn, void *data, int offset, int len); @@ -629,8 +630,8 @@ void mark_page_dirty(struct kvm *kvm, gfn_t gfn); struct kvm_memslots *kvm_vcpu_memslots(struct kvm_vcpu *vcpu); struct kvm_memory_slot *kvm_vcpu_gfn_to_memslot(struct kvm_vcpu *vcpu, gfn_t gfn); -pfn_t kvm_vcpu_gfn_to_pfn_atomic(struct kvm_vcpu *vcpu, gfn_t gfn); -pfn_t kvm_vcpu_gfn_to_pfn(struct kvm_vcpu *vcpu, gfn_t gfn); +kvm_pfn_t kvm_vcpu_gfn_to_pfn_atomic(struct kvm_vcpu *vcpu, gfn_t gfn); +kvm_pfn_t kvm_vcpu_gfn_to_pfn(struct kvm_vcpu *vcpu, gfn_t gfn); struct page *kvm_vcpu_gfn_to_page(struct kvm_vcpu *vcpu, gfn_t gfn); unsigned long kvm_vcpu_gfn_to_hva(struct kvm_vcpu *vcpu, gfn_t gfn); unsigned long kvm_vcpu_gfn_to_hva_prot(struct kvm_vcpu *vcpu, gfn_t gfn, bool *writable); @@ -811,7 +812,7 @@ void kvm_arch_sync_events(struct kvm *kvm); int kvm_cpu_has_pending_timer(struct kvm_vcpu *vcpu); void kvm_vcpu_kick(struct kvm_vcpu *vcpu); -bool kvm_is_reserved_pfn(pfn_t pfn); +bool kvm_is_reserved_pfn(kvm_pfn_t pfn); struct kvm_irq_ack_notifier { struct hlist_node link; @@ -965,7 +966,7 @@ static inline gfn_t gpa_to_gfn(gpa_t gpa) return (gfn_t)(gpa >> PAGE_SHIFT); } -static inline hpa_t pfn_to_hpa(pfn_t pfn) +static inline hpa_t pfn_to_hpa(kvm_pfn_t pfn) { return (hpa_t)pfn << PAGE_SHIFT; } diff --git a/include/linux/kvm_types.h b/include/linux/kvm_types.h index 1b47a185c2f0..8bf259dae9f6 100644 --- a/include/linux/kvm_types.h +++ b/include/linux/kvm_types.h @@ -53,7 +53,7 @@ typedef unsigned long hva_t; typedef u64 hpa_t; typedef u64 hfn_t; -typedef hfn_t pfn_t; +typedef hfn_t kvm_pfn_t; struct gfn_to_hva_cache { u64 generation; diff --git a/include/linux/list.h b/include/linux/list.h index 5356f4d661a7..30cf4200ab40 100644 --- a/include/linux/list.h +++ b/include/linux/list.h @@ -113,6 +113,17 @@ extern void __list_del_entry(struct list_head *entry); extern void list_del(struct list_head *entry); #endif +#ifdef CONFIG_DEBUG_LIST +/* + * See devm_memremap_pages() which wants DEBUG_LIST=y to assert if one + * of the pages it allocates is ever passed to list_add() + */ +extern void list_force_poison(struct list_head *entry); +#else +/* fallback to the less strict LIST_POISON* definitions */ +#define list_force_poison list_del +#endif + /** * list_replace - replace old entry by new one * @old : the element to be replaced diff --git a/include/linux/memblock.h b/include/linux/memblock.h index 173fb44e22f1..3106ac1c895e 100644 --- a/include/linux/memblock.h +++ b/include/linux/memblock.h @@ -61,6 +61,14 @@ extern int memblock_debug; extern bool movable_node_enabled; #endif /* CONFIG_MOVABLE_NODE */ +#ifdef CONFIG_ARCH_DISCARD_MEMBLOCK +#define __init_memblock __meminit +#define __initdata_memblock __meminitdata +#else +#define __init_memblock +#define __initdata_memblock +#endif + #define memblock_dbg(fmt, ...) \ if (memblock_debug) printk(KERN_INFO pr_fmt(fmt), ##__VA_ARGS__) @@ -166,7 +174,7 @@ static inline bool memblock_is_hotpluggable(struct memblock_region *m) return m->flags & MEMBLOCK_HOTPLUG; } -static inline bool movable_node_is_enabled(void) +static inline bool __init_memblock movable_node_is_enabled(void) { return movable_node_enabled; } @@ -405,14 +413,6 @@ static inline unsigned long memblock_region_reserved_end_pfn(const struct memblo for (idx = 0; idx < memblock_type->cnt; \ idx++,rgn = &memblock_type->regions[idx]) -#ifdef CONFIG_ARCH_DISCARD_MEMBLOCK -#define __init_memblock __meminit -#define __initdata_memblock __meminitdata -#else -#define __init_memblock -#define __initdata_memblock -#endif - #ifdef CONFIG_MEMTEST extern void early_memtest(phys_addr_t start, phys_addr_t end); #else diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h index 2292468f2a30..189f04d4d2ec 100644 --- a/include/linux/memcontrol.h +++ b/include/linux/memcontrol.h @@ -280,10 +280,12 @@ static inline void mem_cgroup_events(struct mem_cgroup *memcg, bool mem_cgroup_low(struct mem_cgroup *root, struct mem_cgroup *memcg); int mem_cgroup_try_charge(struct page *page, struct mm_struct *mm, - gfp_t gfp_mask, struct mem_cgroup **memcgp); + gfp_t gfp_mask, struct mem_cgroup **memcgp, + bool compound); void mem_cgroup_commit_charge(struct page *page, struct mem_cgroup *memcg, - bool lrucare); -void mem_cgroup_cancel_charge(struct page *page, struct mem_cgroup *memcg); + bool lrucare, bool compound); +void mem_cgroup_cancel_charge(struct page *page, struct mem_cgroup *memcg, + bool compound); void mem_cgroup_uncharge(struct page *page); void mem_cgroup_uncharge_list(struct list_head *page_list); @@ -515,7 +517,8 @@ static inline bool mem_cgroup_low(struct mem_cgroup *root, static inline int mem_cgroup_try_charge(struct page *page, struct mm_struct *mm, gfp_t gfp_mask, - struct mem_cgroup **memcgp) + struct mem_cgroup **memcgp, + bool compound) { *memcgp = NULL; return 0; @@ -523,12 +526,13 @@ static inline int mem_cgroup_try_charge(struct page *page, struct mm_struct *mm, static inline void mem_cgroup_commit_charge(struct page *page, struct mem_cgroup *memcg, - bool lrucare) + bool lrucare, bool compound) { } static inline void mem_cgroup_cancel_charge(struct page *page, - struct mem_cgroup *memcg) + struct mem_cgroup *memcg, + bool compound) { } diff --git a/include/linux/memory_hotplug.h b/include/linux/memory_hotplug.h index 2ea574ff9714..43405992d027 100644 --- a/include/linux/memory_hotplug.h +++ b/include/linux/memory_hotplug.h @@ -275,7 +275,8 @@ extern int offline_pages(unsigned long start_pfn, unsigned long nr_pages); extern bool is_memblock_offlined(struct memory_block *mem); extern void remove_memory(int nid, u64 start, u64 size); extern int sparse_add_one_section(struct zone *zone, unsigned long start_pfn); -extern void sparse_remove_one_section(struct zone *zone, struct mem_section *ms); +extern void sparse_remove_one_section(struct zone *zone, struct mem_section *ms, + unsigned long map_offset); extern struct page *sparse_decode_mem_map(unsigned long coded_mem_map, unsigned long pnum); diff --git a/include/linux/memremap.h b/include/linux/memremap.h new file mode 100644 index 000000000000..bcaa634139a9 --- /dev/null +++ b/include/linux/memremap.h @@ -0,0 +1,114 @@ +#ifndef _LINUX_MEMREMAP_H_ +#define _LINUX_MEMREMAP_H_ +#include <linux/mm.h> +#include <linux/ioport.h> +#include <linux/percpu-refcount.h> + +struct resource; +struct device; + +/** + * struct vmem_altmap - pre-allocated storage for vmemmap_populate + * @base_pfn: base of the entire dev_pagemap mapping + * @reserve: pages mapped, but reserved for driver use (relative to @base) + * @free: free pages set aside in the mapping for memmap storage + * @align: pages reserved to meet allocation alignments + * @alloc: track pages consumed, private to vmemmap_populate() + */ +struct vmem_altmap { + const unsigned long base_pfn; + const unsigned long reserve; + unsigned long free; + unsigned long align; + unsigned long alloc; +}; + +unsigned long vmem_altmap_offset(struct vmem_altmap *altmap); +void vmem_altmap_free(struct vmem_altmap *altmap, unsigned long nr_pfns); + +#if defined(CONFIG_SPARSEMEM_VMEMMAP) && defined(CONFIG_ZONE_DEVICE) +struct vmem_altmap *to_vmem_altmap(unsigned long memmap_start); +#else +static inline struct vmem_altmap *to_vmem_altmap(unsigned long memmap_start) +{ + return NULL; +} +#endif + +/** + * struct dev_pagemap - metadata for ZONE_DEVICE mappings + * @altmap: pre-allocated/reserved memory for vmemmap allocations + * @res: physical address range covered by @ref + * @ref: reference count that pins the devm_memremap_pages() mapping + * @dev: host device of the mapping for debug + */ +struct dev_pagemap { + struct vmem_altmap *altmap; + const struct resource *res; + struct percpu_ref *ref; + struct device *dev; +}; + +#ifdef CONFIG_ZONE_DEVICE +void *devm_memremap_pages(struct device *dev, struct resource *res, + struct percpu_ref *ref, struct vmem_altmap *altmap); +struct dev_pagemap *find_dev_pagemap(resource_size_t phys); +#else +static inline void *devm_memremap_pages(struct device *dev, + struct resource *res, struct percpu_ref *ref, + struct vmem_altmap *altmap) +{ + /* + * Fail attempts to call devm_memremap_pages() without + * ZONE_DEVICE support enabled, this requires callers to fall + * back to plain devm_memremap() based on config + */ + WARN_ON_ONCE(1); + return ERR_PTR(-ENXIO); +} + +static inline struct dev_pagemap *find_dev_pagemap(resource_size_t phys) +{ + return NULL; +} +#endif + +/** + * get_dev_pagemap() - take a new live reference on the dev_pagemap for @pfn + * @pfn: page frame number to lookup page_map + * @pgmap: optional known pgmap that already has a reference + * + * @pgmap allows the overhead of a lookup to be bypassed when @pfn lands in the + * same mapping. + */ +static inline struct dev_pagemap *get_dev_pagemap(unsigned long pfn, + struct dev_pagemap *pgmap) +{ + const struct resource *res = pgmap ? pgmap->res : NULL; + resource_size_t phys = PFN_PHYS(pfn); + + /* + * In the cached case we're already holding a live reference so + * we can simply do a blind increment + */ + if (res && phys >= res->start && phys <= res->end) { + percpu_ref_get(pgmap->ref); + return pgmap; + } + + /* fall back to slow path lookup */ + rcu_read_lock(); + pgmap = find_dev_pagemap(phys); + if (pgmap && !percpu_ref_tryget_live(pgmap->ref)) + pgmap = NULL; + rcu_read_unlock(); + + return pgmap; +} + +static inline void put_dev_pagemap(struct dev_pagemap *pgmap) +{ + if (pgmap) + percpu_ref_put(pgmap->ref); +} +#endif /* _LINUX_MEMREMAP_H_ */ diff --git a/include/linux/mm.h b/include/linux/mm.h index 839d9e9a1c38..f1cd22f2df1a 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -16,6 +16,7 @@ #include <linux/mm_types.h> #include <linux/range.h> #include <linux/pfn.h> +#include <linux/percpu-refcount.h> #include <linux/bit_spinlock.h> #include <linux/shrinker.h> #include <linux/resource.h> @@ -329,6 +330,13 @@ struct inode; #define page_private(page) ((page)->private) #define set_page_private(page, v) ((page)->private = (v)) +#if !defined(__HAVE_ARCH_PTE_DEVMAP) || !defined(CONFIG_TRANSPARENT_HUGEPAGE) +static inline int pmd_devmap(pmd_t pmd) +{ + return 0; +} +#endif + /* * FIXME: take this include out, include page-flags.h in * files which need it (119 of them) @@ -410,39 +418,17 @@ static inline int is_vmalloc_or_module_addr(const void *x) extern void kvfree(const void *addr); -static inline void compound_lock(struct page *page) +static inline atomic_t *compound_mapcount_ptr(struct page *page) { -#ifdef CONFIG_TRANSPARENT_HUGEPAGE - VM_BUG_ON_PAGE(PageSlab(page), page); - bit_spin_lock(PG_compound_lock, &page->flags); -#endif + return &page[1].compound_mapcount; } -static inline void compound_unlock(struct page *page) +static inline int compound_mapcount(struct page *page) { -#ifdef CONFIG_TRANSPARENT_HUGEPAGE - VM_BUG_ON_PAGE(PageSlab(page), page); - bit_spin_unlock(PG_compound_lock, &page->flags); -#endif -} - -static inline unsigned long compound_lock_irqsave(struct page *page) -{ - unsigned long uninitialized_var(flags); -#ifdef CONFIG_TRANSPARENT_HUGEPAGE - local_irq_save(flags); - compound_lock(page); -#endif - return flags; -} - -static inline void compound_unlock_irqrestore(struct page *page, - unsigned long flags) -{ -#ifdef CONFIG_TRANSPARENT_HUGEPAGE - compound_unlock(page); - local_irq_restore(flags); -#endif + if (!PageCompound(page)) + return 0; + page = compound_head(page); + return atomic_read(compound_mapcount_ptr(page)) + 1; } /* @@ -455,61 +441,29 @@ static inline void page_mapcount_reset(struct page *page) atomic_set(&(page)->_mapcount, -1); } +int __page_mapcount(struct page *page); + static inline int page_mapcount(struct page *page) { VM_BUG_ON_PAGE(PageSlab(page), page); - return atomic_read(&page->_mapcount) + 1; -} -static inline int page_count(struct page *page) -{ - return atomic_read(&compound_head(page)->_count); -} - -static inline bool __compound_tail_refcounted(struct page *page) -{ - return PageAnon(page) && !PageSlab(page) && !PageHeadHuge(page); -} - -/* - * This takes a head page as parameter and tells if the - * tail page reference counting can be skipped. - * - * For this to be safe, PageSlab and PageHeadHuge must remain true on - * any given page where they return true here, until all tail pins - * have been released. - */ -static inline bool compound_tail_refcounted(struct page *page) -{ - VM_BUG_ON_PAGE(!PageHead(page), page); - return __compound_tail_refcounted(page); + if (unlikely(PageCompound(page))) + return __page_mapcount(page); + return atomic_read(&page->_mapcount) + 1; } -static inline void get_huge_page_tail(struct page *page) +#ifdef CONFIG_TRANSPARENT_HUGEPAGE +int total_mapcount(struct page *page); +#else +static inline int total_mapcount(struct page *page) { - /* - * __split_huge_page_refcount() cannot run from under us. - */ - VM_BUG_ON_PAGE(!PageTail(page), page); - VM_BUG_ON_PAGE(page_mapcount(page) < 0, page); - VM_BUG_ON_PAGE(atomic_read(&page->_count) != 0, page); - if (compound_tail_refcounted(compound_head(page))) - atomic_inc(&page->_mapcount); + return page_mapcount(page); } +#endif -extern bool __get_page_tail(struct page *page); - -static inline void get_page(struct page *page) +static inline int page_count(struct page *page) { - if (unlikely(PageTail(page))) - if (likely(__get_page_tail(page))) - return; - /* - * Getting a normal page or the head of a compound page - * requires to already have an elevated page->_count. - */ - VM_BUG_ON_PAGE(atomic_read(&page->_count) <= 0, page); - atomic_inc(&page->_count); + return atomic_read(&compound_head(page)->_count); } static inline struct page *virt_to_head_page(const void *x) @@ -528,7 +482,8 @@ static inline void init_page_count(struct page *page) atomic_set(&page->_count, 1); } -void put_page(struct page *page); +void __put_page(struct page *page); + void put_pages_list(struct list_head *pages); void split_page(struct page *page, unsigned int order); @@ -548,6 +503,9 @@ enum compound_dtor_id { #ifdef CONFIG_HUGETLB_PAGE HUGETLB_PAGE_DTOR, #endif +#ifdef CONFIG_TRANSPARENT_HUGEPAGE + TRANSHUGE_PAGE_DTOR, +#endif NR_COMPOUND_DTORS, }; extern compound_page_dtor * const compound_page_dtors[]; @@ -577,6 +535,8 @@ static inline void set_compound_order(struct page *page, unsigned int order) page[1].compound_order = order; } +void free_compound_page(struct page *page); + #ifdef CONFIG_MMU /* * Do pte_mkwrite, but only if the vma says VM_WRITE. We do this when @@ -704,6 +664,51 @@ static inline enum zone_type page_zonenum(const struct page *page) return (page->flags >> ZONES_PGSHIFT) & ZONES_MASK; } +#ifdef CONFIG_ZONE_DEVICE +void get_zone_device_page(struct page *page); +void put_zone_device_page(struct page *page); +static inline bool is_zone_device_page(const struct page *page) +{ + return page_zonenum(page) == ZONE_DEVICE; +} +#else +static inline void get_zone_device_page(struct page *page) +{ +} +static inline void put_zone_device_page(struct page *page) +{ +} +static inline bool is_zone_device_page(const struct page *page) +{ + return false; +} +#endif + +static inline void get_page(struct page *page) +{ + page = compound_head(page); + /* + * Getting a normal page or the head of a compound page + * requires to already have an elevated page->_count. + */ + VM_BUG_ON_PAGE(atomic_read(&page->_count) <= 0, page); + atomic_inc(&page->_count); + + if (unlikely(is_zone_device_page(page))) + get_zone_device_page(page); +} + +static inline void put_page(struct page *page) +{ + page = compound_head(page); + + if (put_page_testzero(page)) + __put_page(page); + + if (unlikely(is_zone_device_page(page))) + put_zone_device_page(page); +} + #if defined(CONFIG_SPARSEMEM) && !defined(CONFIG_SPARSEMEM_VMEMMAP) #define SECTION_IN_PAGE_FLAGS #endif @@ -993,10 +998,21 @@ static inline pgoff_t page_file_index(struct page *page) /* * Return true if this page is mapped into pagetables. + * For compound page it returns true if any subpage of compound page is mapped. */ -static inline int page_mapped(struct page *page) -{ - return atomic_read(&(page)->_mapcount) >= 0; +static inline bool page_mapped(struct page *page) +{ + int i; + if (likely(!PageCompound(page))) + return atomic_read(&page->_mapcount) >= 0; + page = compound_head(page); + if (atomic_read(compound_mapcount_ptr(page)) >= 0) + return true; + for (i = 0; i < hpage_nr_pages(page); i++) { + if (atomic_read(&page[i]._mapcount) >= 0) + return true; + } + return false; } /* @@ -1084,7 +1100,7 @@ static inline bool shmem_mapping(struct address_space *mapping) } #endif -extern int can_do_mlock(void); +extern bool can_do_mlock(void); extern int user_shm_lock(size_t, struct user_struct *); extern void user_shm_unlock(size_t, struct user_struct *); @@ -1178,7 +1194,8 @@ int invalidate_inode_page(struct page *page); extern int handle_mm_fault(struct mm_struct *mm, struct vm_area_struct *vma, unsigned long address, unsigned int flags); extern int fixup_user_fault(struct task_struct *tsk, struct mm_struct *mm, - unsigned long address, unsigned int fault_flags); + unsigned long address, unsigned int fault_flags, + bool *unlocked); #else static inline int handle_mm_fault(struct mm_struct *mm, struct vm_area_struct *vma, unsigned long address, @@ -1190,7 +1207,7 @@ static inline int handle_mm_fault(struct mm_struct *mm, } static inline int fixup_user_fault(struct task_struct *tsk, struct mm_struct *mm, unsigned long address, - unsigned int fault_flags) + unsigned int fault_flags, bool *unlocked) { /* should never happen if there's no MMU */ BUG(); @@ -1444,6 +1461,13 @@ static inline void sync_mm_rss(struct mm_struct *mm) } #endif +#ifndef __HAVE_ARCH_PTE_DEVMAP +static inline int pte_devmap(pte_t pte) +{ + return 0; +} +#endif + int vma_wants_writenotify(struct vm_area_struct *vma); extern pte_t *__get_locked_pte(struct mm_struct *mm, unsigned long addr, @@ -2114,7 +2138,7 @@ int vm_insert_page(struct vm_area_struct *, unsigned long addr, struct page *); int vm_insert_pfn(struct vm_area_struct *vma, unsigned long addr, unsigned long pfn); int vm_insert_mixed(struct vm_area_struct *vma, unsigned long addr, - unsigned long pfn); + pfn_t pfn); int vm_iomap_memory(struct vm_area_struct *vma, phys_addr_t start, unsigned long len); @@ -2224,7 +2248,14 @@ pud_t *vmemmap_pud_populate(pgd_t *pgd, unsigned long addr, int node); pmd_t *vmemmap_pmd_populate(pud_t *pud, unsigned long addr, int node); pte_t *vmemmap_pte_populate(pmd_t *pmd, unsigned long addr, int node); void *vmemmap_alloc_block(unsigned long size, int node); -void *vmemmap_alloc_block_buf(unsigned long size, int node); +struct vmem_altmap; +void *__vmemmap_alloc_block_buf(unsigned long size, int node, + struct vmem_altmap *altmap); +static inline void *vmemmap_alloc_block_buf(unsigned long size, int node) +{ + return __vmemmap_alloc_block_buf(size, node, NULL); +} + void vmemmap_verify(pte_t *, int, unsigned long, unsigned long); int vmemmap_populate_basepages(unsigned long start, unsigned long end, int node); @@ -2246,7 +2277,7 @@ extern int memory_failure(unsigned long pfn, int trapno, int flags); extern void memory_failure_queue(unsigned long pfn, int trapno, int flags); extern int unpoison_memory(unsigned long pfn); extern int get_hwpoison_page(struct page *page); -extern void put_hwpoison_page(struct page *page); +#define put_hwpoison_page(page) put_page(page) extern int sysctl_memory_failure_early_kill; extern int sysctl_memory_failure_recovery; extern void shake_page(struct page *p, int access); diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h index 6bc9a0ce2253..d3ebb9d21a53 100644 --- a/include/linux/mm_types.h +++ b/include/linux/mm_types.h @@ -54,6 +54,8 @@ struct page { * see PAGE_MAPPING_ANON below. */ void *s_mem; /* slab first object */ + atomic_t compound_mapcount; /* first tail page */ + /* page_deferred_list().next -- second tail page */ }; /* Second double word */ @@ -61,6 +63,7 @@ struct page { union { pgoff_t index; /* Our offset within mapping. */ void *freelist; /* sl[aou]b first free object */ + /* page_deferred_list().prev -- second tail page */ }; union { @@ -81,20 +84,9 @@ struct page { union { /* - * Count of ptes mapped in - * mms, to show when page is - * mapped & limit reverse map - * searches. - * - * Used also for tail pages - * refcounting instead of - * _count. Tail pages cannot - * be mapped and keeping the - * tail page _count zero at - * all times guarantees - * get_page_unless_zero() will - * never succeed on tail - * pages. + * Count of ptes mapped in mms, to show + * when page is mapped & limit reverse + * map searches. */ atomic_t _mapcount; @@ -124,6 +116,11 @@ struct page { * Can be used as a generic list * by the page owner. */ + struct dev_pagemap *pgmap; /* ZONE_DEVICE pages are never on an + * lru or handled by a slab + * allocator, this points to the + * hosting device page map. + */ struct { /* slub per cpu partial pages */ struct page *next; /* Next partial slab */ #ifdef CONFIG_64BIT diff --git a/include/linux/mmdebug.h b/include/linux/mmdebug.h index 772362adf471..053824b0a412 100644 --- a/include/linux/mmdebug.h +++ b/include/linux/mmdebug.h @@ -56,4 +56,10 @@ void dump_mm(const struct mm_struct *mm); #define VIRTUAL_BUG_ON(cond) do { } while (0) #endif +#ifdef CONFIG_DEBUG_VM_PGFLAGS +#define VM_BUG_ON_PGFLAGS(cond, page) VM_BUG_ON_PAGE(cond, page) +#else +#define VM_BUG_ON_PGFLAGS(cond, page) BUILD_BUG_ON_INVALID(cond) +#endif + #endif diff --git a/include/linux/page-flags.h b/include/linux/page-flags.h index bb53c7b86315..19724e6ebd26 100644 --- a/include/linux/page-flags.h +++ b/include/linux/page-flags.h @@ -101,9 +101,6 @@ enum pageflags { #ifdef CONFIG_MEMORY_FAILURE PG_hwpoison, /* hardware poisoned page. Don't touch */ #endif -#ifdef CONFIG_TRANSPARENT_HUGEPAGE - PG_compound_lock, -#endif #if defined(CONFIG_IDLE_PAGE_TRACKING) && defined(CONFIG_64BIT) PG_young, PG_idle, @@ -129,53 +126,104 @@ enum pageflags { /* SLOB */ PG_slob_free = PG_private, + + /* Compound pages. Stored in first tail page's flags */ + PG_double_map = PG_private_2, }; #ifndef __GENERATING_BOUNDS_H +struct page; /* forward declaration */ + +static inline struct page *compound_head(struct page *page) +{ + unsigned long head = READ_ONCE(page->compound_head); + + if (unlikely(head & 1)) + return (struct page *) (head - 1); + return page; +} + +static inline int PageTail(struct page *page) +{ + return READ_ONCE(page->compound_head) & 1; +} + +static inline int PageCompound(struct page *page) +{ + return test_bit(PG_head, &page->flags) || PageTail(page); +} + +/* + * Page flags policies wrt compound pages + * + * PF_ANY: + * the page flag is relevant for small, head and tail pages. + * + * PF_HEAD: + * for compound page all operations related to the page flag applied to + * head page. + * + * PF_NO_TAIL: + * modifications of the page flag must be done on small or head pages, + * checks can be done on tail pages too. + * + * PF_NO_COMPOUND: + * the page flag is not relevant for compound pages. + */ +#define PF_ANY(page, enforce) page +#define PF_HEAD(page, enforce) compound_head(page) +#define PF_NO_TAIL(page, enforce) ({ \ + VM_BUG_ON_PGFLAGS(enforce && PageTail(page), page); \ + compound_head(page);}) +#define PF_NO_COMPOUND(page, enforce) ({ \ + VM_BUG_ON_PGFLAGS(enforce && PageCompound(page), page); \ + page;}) + /* * Macros to create function definitions for page flags */ -#define TESTPAGEFLAG(uname, lname) \ -static inline int Page##uname(const struct page *page) \ - { return test_bit(PG_##lname, &page->flags); } +#define TESTPAGEFLAG(uname, lname, policy) \ +static inline int Page##uname(struct page *page) \ + { return test_bit(PG_##lname, &policy(page, 0)->flags); } -#define SETPAGEFLAG(uname, lname) \ +#define SETPAGEFLAG(uname, lname, policy) \ static inline void SetPage##uname(struct page *page) \ - { set_bit(PG_##lname, &page->flags); } + { set_bit(PG_##lname, &policy(page, 1)->flags); } -#define CLEARPAGEFLAG(uname, lname) \ +#define CLEARPAGEFLAG(uname, lname, policy) \ static inline void ClearPage##uname(struct page *page) \ - { clear_bit(PG_##lname, &page->flags); } + { clear_bit(PG_##lname, &policy(page, 1)->flags); } -#define __SETPAGEFLAG(uname, lname) \ +#define __SETPAGEFLAG(uname, lname, policy) \ static inline void __SetPage##uname(struct page *page) \ - { __set_bit(PG_##lname, &page->flags); } + { __set_bit(PG_##lname, &policy(page, 1)->flags); } -#define __CLEARPAGEFLAG(uname, lname) \ +#define __CLEARPAGEFLAG(uname, lname, policy) \ static inline void __ClearPage##uname(struct page *page) \ - { __clear_bit(PG_##lname, &page->flags); } + { __clear_bit(PG_##lname, &policy(page, 1)->flags); } -#define TESTSETFLAG(uname, lname) \ +#define TESTSETFLAG(uname, lname, policy) \ static inline int TestSetPage##uname(struct page *page) \ - { return test_and_set_bit(PG_##lname, &page->flags); } + { return test_and_set_bit(PG_##lname, &policy(page, 1)->flags); } -#define TESTCLEARFLAG(uname, lname) \ +#define TESTCLEARFLAG(uname, lname, policy) \ static inline int TestClearPage##uname(struct page *page) \ - { return test_and_clear_bit(PG_##lname, &page->flags); } - -#define __TESTCLEARFLAG(uname, lname) \ -static inline int __TestClearPage##uname(struct page *page) \ - { return __test_and_clear_bit(PG_##lname, &page->flags); } + { return test_and_clear_bit(PG_##lname, &policy(page, 1)->flags); } -#define PAGEFLAG(uname, lname) TESTPAGEFLAG(uname, lname) \ - SETPAGEFLAG(uname, lname) CLEARPAGEFLAG(uname, lname) +#define PAGEFLAG(uname, lname, policy) \ + TESTPAGEFLAG(uname, lname, policy) \ + SETPAGEFLAG(uname, lname, policy) \ + CLEARPAGEFLAG(uname, lname, policy) -#define __PAGEFLAG(uname, lname) TESTPAGEFLAG(uname, lname) \ - __SETPAGEFLAG(uname, lname) __CLEARPAGEFLAG(uname, lname) +#define __PAGEFLAG(uname, lname, policy) \ + TESTPAGEFLAG(uname, lname, policy) \ + __SETPAGEFLAG(uname, lname, policy) \ + __CLEARPAGEFLAG(uname, lname, policy) -#define TESTSCFLAG(uname, lname) \ - TESTSETFLAG(uname, lname) TESTCLEARFLAG(uname, lname) +#define TESTSCFLAG(uname, lname, policy) \ + TESTSETFLAG(uname, lname, policy) \ + TESTCLEARFLAG(uname, lname, policy) #define TESTPAGEFLAG_FALSE(uname) \ static inline int Page##uname(const struct page *page) { return 0; } @@ -195,56 +243,62 @@ static inline int TestSetPage##uname(struct page *page) { return 0; } #define TESTCLEARFLAG_FALSE(uname) \ static inline int TestClearPage##uname(struct page *page) { return 0; } -#define __TESTCLEARFLAG_FALSE(uname) \ -static inline int __TestClearPage##uname(struct page *page) { return 0; } - #define PAGEFLAG_FALSE(uname) TESTPAGEFLAG_FALSE(uname) \ SETPAGEFLAG_NOOP(uname) CLEARPAGEFLAG_NOOP(uname) #define TESTSCFLAG_FALSE(uname) \ TESTSETFLAG_FALSE(uname) TESTCLEARFLAG_FALSE(uname) -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) - TESTCLEARFLAG(Active, active) -__PAGEFLAG(Slab, slab) -PAGEFLAG(Checked, checked) /* Used by some filesystems */ -PAGEFLAG(Pinned, pinned) TESTSCFLAG(Pinned, pinned) /* Xen */ -PAGEFLAG(SavePinned, savepinned); /* Xen */ -PAGEFLAG(Foreign, foreign); /* Xen */ -PAGEFLAG(Reserved, reserved) __CLEARPAGEFLAG(Reserved, reserved) -PAGEFLAG(SwapBacked, swapbacked) __CLEARPAGEFLAG(SwapBacked, swapbacked) - __SETPAGEFLAG(SwapBacked, swapbacked) - -__PAGEFLAG(SlobFree, slob_free) +__PAGEFLAG(Locked, locked, PF_NO_TAIL) +PAGEFLAG(Error, error, PF_NO_COMPOUND) TESTCLEARFLAG(Error, error, PF_NO_COMPOUND) +PAGEFLAG(Referenced, referenced, PF_HEAD) + TESTCLEARFLAG(Referenced, referenced, PF_HEAD) + __SETPAGEFLAG(Referenced, referenced, PF_HEAD) +PAGEFLAG(Dirty, dirty, PF_HEAD) TESTSCFLAG(Dirty, dirty, PF_HEAD) + __CLEARPAGEFLAG(Dirty, dirty, PF_HEAD) +PAGEFLAG(LRU, lru, PF_HEAD) __CLEARPAGEFLAG(LRU, lru, PF_HEAD) +PAGEFLAG(Active, active, PF_HEAD) __CLEARPAGEFLAG(Active, active, PF_HEAD) + TESTCLEARFLAG(Active, active, PF_HEAD) +__PAGEFLAG(Slab, slab, PF_NO_TAIL) +__PAGEFLAG(SlobFree, slob_free, PF_NO_TAIL) +PAGEFLAG(Checked, checked, PF_NO_COMPOUND) /* Used by some filesystems */ + +/* Xen */ +PAGEFLAG(Pinned, pinned, PF_NO_COMPOUND) + TESTSCFLAG(Pinned, pinned, PF_NO_COMPOUND) +PAGEFLAG(SavePinned, savepinned, PF_NO_COMPOUND); +PAGEFLAG(Foreign, foreign, PF_NO_COMPOUND); + +PAGEFLAG(Reserved, reserved, PF_NO_COMPOUND) + __CLEARPAGEFLAG(Reserved, reserved, PF_NO_COMPOUND) +PAGEFLAG(SwapBacked, swapbacked, PF_NO_TAIL) + __CLEARPAGEFLAG(SwapBacked, swapbacked, PF_NO_TAIL) + __SETPAGEFLAG(SwapBacked, swapbacked, PF_NO_TAIL) /* * Private page markings that may be used by the filesystem that owns the page * for its own purposes. * - PG_private and PG_private_2 cause releasepage() and co to be invoked */ -PAGEFLAG(Private, private) __SETPAGEFLAG(Private, private) - __CLEARPAGEFLAG(Private, private) -PAGEFLAG(Private2, private_2) TESTSCFLAG(Private2, private_2) -PAGEFLAG(OwnerPriv1, owner_priv_1) TESTCLEARFLAG(OwnerPriv1, owner_priv_1) +PAGEFLAG(Private, private, PF_ANY) __SETPAGEFLAG(Private, private, PF_ANY) + __CLEARPAGEFLAG(Private, private, PF_ANY) +PAGEFLAG(Private2, private_2, PF_ANY) TESTSCFLAG(Private2, private_2, PF_ANY) +PAGEFLAG(OwnerPriv1, owner_priv_1, PF_ANY) + TESTCLEARFLAG(OwnerPriv1, owner_priv_1, PF_ANY) /* * Only test-and-set exist for PG_writeback. The unconditional operators are * risky: they bypass page accounting. */ -TESTPAGEFLAG(Writeback, writeback) TESTSCFLAG(Writeback, writeback) -PAGEFLAG(MappedToDisk, mappedtodisk) +TESTPAGEFLAG(Writeback, writeback, PF_NO_COMPOUND) + TESTSCFLAG(Writeback, writeback, PF_NO_COMPOUND) +PAGEFLAG(MappedToDisk, mappedtodisk, PF_NO_COMPOUND) /* PG_readahead is only used for reads; PG_reclaim is only for writes */ -PAGEFLAG(Reclaim, reclaim) TESTCLEARFLAG(Reclaim, reclaim) -PAGEFLAG(Readahead, reclaim) TESTCLEARFLAG(Readahead, reclaim) +PAGEFLAG(Reclaim, reclaim, PF_NO_COMPOUND) + TESTCLEARFLAG(Reclaim, reclaim, PF_NO_COMPOUND) +PAGEFLAG(Readahead, reclaim, PF_NO_COMPOUND) + TESTCLEARFLAG(Readahead, reclaim, PF_NO_COMPOUND) #ifdef CONFIG_HIGHMEM /* @@ -257,31 +311,33 @@ PAGEFLAG_FALSE(HighMem) #endif #ifdef CONFIG_SWAP -PAGEFLAG(SwapCache, swapcache) +PAGEFLAG(SwapCache, swapcache, PF_NO_COMPOUND) #else PAGEFLAG_FALSE(SwapCache) #endif -PAGEFLAG(Unevictable, unevictable) __CLEARPAGEFLAG(Unevictable, unevictable) - TESTCLEARFLAG(Unevictable, unevictable) +PAGEFLAG(Unevictable, unevictable, PF_HEAD) + __CLEARPAGEFLAG(Unevictable, unevictable, PF_HEAD) + TESTCLEARFLAG(Unevictable, unevictable, PF_HEAD) #ifdef CONFIG_MMU -PAGEFLAG(Mlocked, mlocked) __CLEARPAGEFLAG(Mlocked, mlocked) - TESTSCFLAG(Mlocked, mlocked) __TESTCLEARFLAG(Mlocked, mlocked) +PAGEFLAG(Mlocked, mlocked, PF_NO_TAIL) + __CLEARPAGEFLAG(Mlocked, mlocked, PF_NO_TAIL) + TESTSCFLAG(Mlocked, mlocked, PF_NO_TAIL) #else PAGEFLAG_FALSE(Mlocked) __CLEARPAGEFLAG_NOOP(Mlocked) - TESTSCFLAG_FALSE(Mlocked) __TESTCLEARFLAG_FALSE(Mlocked) + TESTSCFLAG_FALSE(Mlocked) #endif #ifdef CONFIG_ARCH_USES_PG_UNCACHED -PAGEFLAG(Uncached, uncached) +PAGEFLAG(Uncached, uncached, PF_NO_COMPOUND) #else PAGEFLAG_FALSE(Uncached) #endif #ifdef CONFIG_MEMORY_FAILURE -PAGEFLAG(HWPoison, hwpoison) -TESTSCFLAG(HWPoison, hwpoison) +PAGEFLAG(HWPoison, hwpoison, PF_ANY) +TESTSCFLAG(HWPoison, hwpoison, PF_ANY) #define __PG_HWPOISON (1UL << PG_hwpoison) #else PAGEFLAG_FALSE(HWPoison) @@ -289,10 +345,10 @@ PAGEFLAG_FALSE(HWPoison) #endif #if defined(CONFIG_IDLE_PAGE_TRACKING) && defined(CONFIG_64BIT) -TESTPAGEFLAG(Young, young) -SETPAGEFLAG(Young, young) -TESTCLEARFLAG(Young, young) -PAGEFLAG(Idle, idle) +TESTPAGEFLAG(Young, young, PF_ANY) +SETPAGEFLAG(Young, young, PF_ANY) +TESTCLEARFLAG(Young, young, PF_ANY) +PAGEFLAG(Idle, idle, PF_ANY) #endif /* @@ -317,6 +373,7 @@ PAGEFLAG(Idle, idle) static inline int PageAnon(struct page *page) { + page = compound_head(page); return ((unsigned long)page->mapping & PAGE_MAPPING_ANON) != 0; } @@ -329,6 +386,7 @@ static inline int PageAnon(struct page *page) */ static inline int PageKsm(struct page *page) { + page = compound_head(page); return ((unsigned long)page->mapping & PAGE_MAPPING_FLAGS) == (PAGE_MAPPING_ANON | PAGE_MAPPING_KSM); } @@ -340,8 +398,9 @@ u64 stable_page_flags(struct page *page); static inline int PageUptodate(struct page *page) { - int ret = test_bit(PG_uptodate, &(page)->flags); - + int ret; + page = compound_head(page); + ret = test_bit(PG_uptodate, &(page)->flags); /* * Must ensure that the data we read out of the page is loaded * _after_ we've loaded page->flags to check for PageUptodate. @@ -358,22 +417,24 @@ static inline int PageUptodate(struct page *page) static inline void __SetPageUptodate(struct page *page) { + VM_BUG_ON_PAGE(PageTail(page), page); smp_wmb(); - __set_bit(PG_uptodate, &(page)->flags); + __set_bit(PG_uptodate, &page->flags); } static inline void SetPageUptodate(struct page *page) { + VM_BUG_ON_PAGE(PageTail(page), page); /* * Memory barrier must be issued before setting the PG_uptodate bit, * so that all previous stores issued in order to bring the page * uptodate are actually visible before PageUptodate becomes true. */ smp_wmb(); - set_bit(PG_uptodate, &(page)->flags); + set_bit(PG_uptodate, &page->flags); } -CLEARPAGEFLAG(Uptodate, uptodate) +CLEARPAGEFLAG(Uptodate, uptodate, PF_NO_TAIL) int test_clear_page_writeback(struct page *page); int __test_set_page_writeback(struct page *page, bool keep_write); @@ -393,12 +454,7 @@ static inline void set_page_writeback_keepwrite(struct page *page) test_set_page_writeback_keepwrite(page); } -__PAGEFLAG(Head, head) CLEARPAGEFLAG(Head, head) - -static inline int PageTail(struct page *page) -{ - return READ_ONCE(page->compound_head) & 1; -} +__PAGEFLAG(Head, head, PF_ANY) CLEARPAGEFLAG(Head, head, PF_ANY) static inline void set_compound_head(struct page *page, struct page *head) { @@ -410,20 +466,6 @@ static inline void clear_compound_head(struct page *page) WRITE_ONCE(page->compound_head, 0); } -static inline struct page *compound_head(struct page *page) -{ - unsigned long head = READ_ONCE(page->compound_head); - - if (unlikely(head & 1)) - return (struct page *) (head - 1); - return page; -} - -static inline int PageCompound(struct page *page) -{ - return PageHead(page) || PageTail(page); - -} #ifdef CONFIG_TRANSPARENT_HUGEPAGE static inline void ClearPageCompound(struct page *page) { @@ -484,22 +526,43 @@ static inline int PageTransTail(struct page *page) return PageTail(page); } -#else - -static inline int PageTransHuge(struct page *page) +/* + * PageDoubleMap indicates that the compound page is mapped with PTEs as well + * as PMDs. + * + * This is required for optimization of rmap operations for THP: we can postpone + * per small page mapcount accounting (and its overhead from atomic operations) + * until the first PMD split. + * + * For the page PageDoubleMap means ->_mapcount in all sub-pages is offset up + * by one. This reference will go away with last compound_mapcount. + * + * See also __split_huge_pmd_locked() and page_remove_anon_compound_rmap(). + */ +static inline int PageDoubleMap(struct page *page) { - return 0; + return PageHead(page) && test_bit(PG_double_map, &page[1].flags); } -static inline int PageTransCompound(struct page *page) +static inline int TestSetPageDoubleMap(struct page *page) { - return 0; + VM_BUG_ON_PAGE(!PageHead(page), page); + return test_and_set_bit(PG_double_map, &page[1].flags); } -static inline int PageTransTail(struct page *page) +static inline int TestClearPageDoubleMap(struct page *page) { - return 0; + VM_BUG_ON_PAGE(!PageHead(page), page); + return test_and_clear_bit(PG_double_map, &page[1].flags); } + +#else +TESTPAGEFLAG_FALSE(TransHuge) +TESTPAGEFLAG_FALSE(TransCompound) +TESTPAGEFLAG_FALSE(TransTail) +TESTPAGEFLAG_FALSE(DoubleMap) + TESTSETFLAG_FALSE(DoubleMap) + TESTCLEARFLAG_FALSE(DoubleMap) #endif /* @@ -583,12 +646,6 @@ static inline void ClearPageSlabPfmemalloc(struct page *page) #define __PG_MLOCKED 0 #endif -#ifdef CONFIG_TRANSPARENT_HUGEPAGE -#define __PG_COMPOUND_LOCK (1 << PG_compound_lock) -#else -#define __PG_COMPOUND_LOCK 0 -#endif - /* * Flags checked when a page is freed. Pages being freed should not have * these flags set. It they are, there is a problem. @@ -598,8 +655,7 @@ static inline void ClearPageSlabPfmemalloc(struct page *page) 1 << PG_private | 1 << PG_private_2 | \ 1 << PG_writeback | 1 << PG_reserved | \ 1 << PG_slab | 1 << PG_swapcache | 1 << PG_active | \ - 1 << PG_unevictable | __PG_MLOCKED | \ - __PG_COMPOUND_LOCK) + 1 << PG_unevictable | __PG_MLOCKED) /* * Flags checked when a page is prepped for return by the page allocator. @@ -626,6 +682,10 @@ static inline int page_has_private(struct page *page) return !!(page->flags & PAGE_FLAGS_PRIVATE); } +#undef PF_ANY +#undef PF_HEAD +#undef PF_NO_TAIL +#undef PF_NO_COMPOUND #endif /* !__GENERATING_BOUNDS_H */ #endif /* PAGE_FLAGS_H */ diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h index 26eabf5ec718..4d08b6c33557 100644 --- a/include/linux/pagemap.h +++ b/include/linux/pagemap.h @@ -394,10 +394,21 @@ static inline struct page *read_mapping_page(struct address_space *mapping, */ static inline pgoff_t page_to_pgoff(struct page *page) { + pgoff_t pgoff; + if (unlikely(PageHeadHuge(page))) return page->index << compound_order(page); - else + + if (likely(!PageTransTail(page))) return page->index << (PAGE_CACHE_SHIFT - PAGE_SHIFT); + + /* + * We don't initialize ->index for tail pages: calculate based on + * head page + */ + pgoff = compound_head(page)->index << (PAGE_CACHE_SHIFT - PAGE_SHIFT); + pgoff += page - compound_head(page); + return pgoff; } /* @@ -433,18 +444,9 @@ extern int __lock_page_or_retry(struct page *page, struct mm_struct *mm, unsigned int flags); extern void unlock_page(struct page *page); -static inline void __set_page_locked(struct page *page) -{ - __set_bit(PG_locked, &page->flags); -} - -static inline void __clear_page_locked(struct page *page) -{ - __clear_bit(PG_locked, &page->flags); -} - static inline int trylock_page(struct page *page) { + page = compound_head(page); return (likely(!test_and_set_bit_lock(PG_locked, &page->flags))); } @@ -497,9 +499,9 @@ extern int wait_on_page_bit_killable_timeout(struct page *page, static inline int wait_on_page_locked_killable(struct page *page) { - if (PageLocked(page)) - return wait_on_page_bit_killable(page, PG_locked); - return 0; + if (!PageLocked(page)) + return 0; + return wait_on_page_bit_killable(compound_head(page), PG_locked); } extern wait_queue_head_t *page_waitqueue(struct page *page); @@ -518,7 +520,7 @@ static inline void wake_up_page(struct page *page, int bit) static inline void wait_on_page_locked(struct page *page) { if (PageLocked(page)) - wait_on_page_bit(page, PG_locked); + wait_on_page_bit(compound_head(page), PG_locked); } /* @@ -664,17 +666,17 @@ int replace_page_cache_page(struct page *old, struct page *new, gfp_t gfp_mask); /* * Like add_to_page_cache_locked, but used to add newly allocated pages: - * the page is new, so we can just run __set_page_locked() against it. + * the page is new, so we can just run __SetPageLocked() against it. */ static inline int add_to_page_cache(struct page *page, struct address_space *mapping, pgoff_t offset, gfp_t gfp_mask) { int error; - __set_page_locked(page); + __SetPageLocked(page); error = add_to_page_cache_locked(page, mapping, offset, gfp_mask); if (unlikely(error)) - __clear_page_locked(page); + __ClearPageLocked(page); return error; } diff --git a/include/linux/pfn.h b/include/linux/pfn.h index 97f3e88aead4..2d8e49711b63 100644 --- a/include/linux/pfn.h +++ b/include/linux/pfn.h @@ -3,6 +3,15 @@ #ifndef __ASSEMBLY__ #include <linux/types.h> + +/* + * pfn_t: encapsulates a page-frame number that is optionally backed + * by memmap (struct page). Whether a pfn_t has a 'struct page' + * backing is indicated by flags in the high bits of the value. + */ +typedef struct { + unsigned long val; +} pfn_t; #endif #define PFN_ALIGN(x) (((unsigned long)(x) + (PAGE_SIZE - 1)) & PAGE_MASK) diff --git a/include/linux/pfn_t.h b/include/linux/pfn_t.h new file mode 100644 index 000000000000..0703b5360d31 --- /dev/null +++ b/include/linux/pfn_t.h @@ -0,0 +1,102 @@ +#ifndef _LINUX_PFN_T_H_ +#define _LINUX_PFN_T_H_ +#include <linux/mm.h> + +/* + * PFN_FLAGS_MASK - mask of all the possible valid pfn_t flags + * PFN_SG_CHAIN - pfn is a pointer to the next scatterlist entry + * PFN_SG_LAST - pfn references a page and is the last scatterlist entry + * PFN_DEV - pfn is not covered by system memmap by default + * PFN_MAP - pfn has a dynamic page mapping established by a device driver + */ +#define PFN_FLAGS_MASK (((unsigned long) ~PAGE_MASK) \ + << (BITS_PER_LONG - PAGE_SHIFT)) +#define PFN_SG_CHAIN (1UL << (BITS_PER_LONG - 1)) +#define PFN_SG_LAST (1UL << (BITS_PER_LONG - 2)) +#define PFN_DEV (1UL << (BITS_PER_LONG - 3)) +#define PFN_MAP (1UL << (BITS_PER_LONG - 4)) + +static inline pfn_t __pfn_to_pfn_t(unsigned long pfn, unsigned long flags) +{ + pfn_t pfn_t = { .val = pfn | (flags & PFN_FLAGS_MASK), }; + + return pfn_t; +} + +/* a default pfn to pfn_t conversion assumes that @pfn is pfn_valid() */ +static inline pfn_t pfn_to_pfn_t(unsigned long pfn) +{ + return __pfn_to_pfn_t(pfn, 0); +} + +extern pfn_t phys_to_pfn_t(dma_addr_t addr, unsigned long flags); + +static inline bool pfn_t_has_page(pfn_t pfn) +{ + return (pfn.val & PFN_MAP) == PFN_MAP || (pfn.val & PFN_DEV) == 0; +} + +static inline unsigned long pfn_t_to_pfn(pfn_t pfn) +{ + return pfn.val & ~PFN_FLAGS_MASK; +} + +static inline struct page *pfn_t_to_page(pfn_t pfn) +{ + if (pfn_t_has_page(pfn)) + return pfn_to_page(pfn_t_to_pfn(pfn)); + return NULL; +} + +static inline dma_addr_t pfn_t_to_phys(pfn_t pfn) +{ + return PFN_PHYS(pfn_t_to_pfn(pfn)); +} + +static inline void *pfn_t_to_virt(pfn_t pfn) +{ + if (pfn_t_has_page(pfn)) + return __va(pfn_t_to_phys(pfn)); + return NULL; +} + +static inline pfn_t page_to_pfn_t(struct page *page) +{ + return pfn_to_pfn_t(page_to_pfn(page)); +} + +static inline int pfn_t_valid(pfn_t pfn) +{ + return pfn_valid(pfn_t_to_pfn(pfn)); +} + +#ifdef CONFIG_MMU +static inline pte_t pfn_t_pte(pfn_t pfn, pgprot_t pgprot) +{ + return pfn_pte(pfn_t_to_pfn(pfn), pgprot); +} +#endif + +#ifdef CONFIG_TRANSPARENT_HUGEPAGE +static inline pmd_t pfn_t_pmd(pfn_t pfn, pgprot_t pgprot) +{ + return pfn_pmd(pfn_t_to_pfn(pfn), pgprot); +} +#endif + +#ifdef __HAVE_ARCH_PTE_DEVMAP +static inline bool pfn_t_devmap(pfn_t pfn) +{ + const unsigned long flags = PFN_DEV|PFN_MAP; + + return (pfn.val & flags) == flags; +} +#else +static inline bool pfn_t_devmap(pfn_t pfn) +{ + return false; +} +pte_t pte_mkdevmap(pte_t pte); +pmd_t pmd_mkdevmap(pmd_t pmd); +#endif +#endif /* _LINUX_PFN_T_H_ */ diff --git a/include/linux/poison.h b/include/linux/poison.h index 317e16de09e5..4a27153574e2 100644 --- a/include/linux/poison.h +++ b/include/linux/poison.h @@ -27,11 +27,15 @@ * Magic number "tsta" to indicate a static timer initializer * for the object debugging code. */ -#define TIMER_ENTRY_STATIC ((void *) 0x74737461) +#define TIMER_ENTRY_STATIC ((void *) 0x300 + POISON_POINTER_DELTA) /********** mm/debug-pagealloc.c **********/ #define PAGE_POISON 0xaa +/********** mm/page_alloc.c ************/ + +#define TAIL_MAPPING ((void *) 0x400 + POISON_POINTER_DELTA) + /********** mm/slab.c **********/ /* * Magic nums for obj red zoning. diff --git a/include/linux/printk.h b/include/linux/printk.h index 9729565c25ff..9ccbdf2c1453 100644 --- a/include/linux/printk.h +++ b/include/linux/printk.h @@ -106,13 +106,13 @@ struct va_format { /* * Dummy printk for disabled debugging statements to use whilst maintaining - * gcc's format and side-effect checking. + * gcc's format checking. */ -static inline __printf(1, 2) -int no_printk(const char *fmt, ...) -{ - return 0; -} +#define no_printk(fmt, ...) \ +do { \ + if (0) \ + printk(fmt, ##__VA_ARGS__); \ +} while (0) #ifdef CONFIG_EARLY_PRINTK extern asmlinkage __printf(1, 2) diff --git a/include/linux/rmap.h b/include/linux/rmap.h index 29446aeef36e..bdf597c4f0be 100644 --- a/include/linux/rmap.h +++ b/include/linux/rmap.h @@ -85,6 +85,7 @@ enum ttu_flags { TTU_UNMAP = 1, /* unmap mode */ TTU_MIGRATION = 2, /* migration mode */ TTU_MUNLOCK = 4, /* munlock mode */ + TTU_LZFREE = 8, /* lazy free mode */ TTU_IGNORE_MLOCK = (1 << 8), /* ignore mlock */ TTU_IGNORE_ACCESS = (1 << 9), /* don't age */ @@ -161,25 +162,31 @@ static inline void anon_vma_merge(struct vm_area_struct *vma, struct anon_vma *page_get_anon_vma(struct page *page); +/* bitflags for do_page_add_anon_rmap() */ +#define RMAP_EXCLUSIVE 0x01 +#define RMAP_COMPOUND 0x02 + /* * rmap interfaces called when adding or removing pte of page */ void page_move_anon_rmap(struct page *, struct vm_area_struct *, unsigned long); -void page_add_anon_rmap(struct page *, struct vm_area_struct *, unsigned long); +void page_add_anon_rmap(struct page *, struct vm_area_struct *, + unsigned long, bool); void do_page_add_anon_rmap(struct page *, struct vm_area_struct *, unsigned long, int); -void page_add_new_anon_rmap(struct page *, struct vm_area_struct *, unsigned long); +void page_add_new_anon_rmap(struct page *, struct vm_area_struct *, + unsigned long, bool); void page_add_file_rmap(struct page *); -void page_remove_rmap(struct page *); +void page_remove_rmap(struct page *, bool); void hugepage_add_anon_rmap(struct page *, struct vm_area_struct *, unsigned long); void hugepage_add_new_anon_rmap(struct page *, struct vm_area_struct *, unsigned long); -static inline void page_dup_rmap(struct page *page) +static inline void page_dup_rmap(struct page *page, bool compound) { - atomic_inc(&page->_mapcount); + atomic_inc(compound ? compound_mapcount_ptr(page) : &page->_mapcount); } /* @@ -210,6 +217,25 @@ static inline pte_t *page_check_address(struct page *page, struct mm_struct *mm, } /* + * Used by idle page tracking to check if a page was referenced via page + * tables. + */ +#ifdef CONFIG_TRANSPARENT_HUGEPAGE +bool page_check_address_transhuge(struct page *page, struct mm_struct *mm, + unsigned long address, pmd_t **pmdp, + pte_t **ptep, spinlock_t **ptlp); +#else +static inline bool page_check_address_transhuge(struct page *page, + struct mm_struct *mm, unsigned long address, + pmd_t **pmdp, pte_t **ptep, spinlock_t **ptlp) +{ + *ptep = page_check_address(page, mm, address, ptlp, 0); + *pmdp = NULL; + return !!*ptep; +} +#endif + +/* * Used by swapoff to help locate where page is expected in vma. */ unsigned long page_address_in_vma(struct page *, struct vm_area_struct *); @@ -286,5 +312,6 @@ static inline int page_mkclean(struct page *page) #define SWAP_AGAIN 1 #define SWAP_FAIL 2 #define SWAP_MLOCK 3 +#define SWAP_LZFREE 4 #endif /* _LINUX_RMAP_H */ diff --git a/include/linux/swap.h b/include/linux/swap.h index 066bd21765ad..414e101cd061 100644 --- a/include/linux/swap.h +++ b/include/linux/swap.h @@ -307,6 +307,7 @@ extern void lru_add_drain_cpu(int cpu); extern void lru_add_drain_all(void); extern void rotate_reclaimable_page(struct page *page); extern void deactivate_file_page(struct page *page); +extern void deactivate_page(struct page *page); extern void swap_setup(void); extern void add_page_to_unevictable_list(struct page *page); @@ -538,7 +539,8 @@ static inline int swp_swapcount(swp_entry_t entry) return 0; } -#define reuse_swap_page(page) (page_mapcount(page) == 1) +#define reuse_swap_page(page) \ + (!PageTransCompound(page) && page_mapcount(page) == 1) static inline int try_to_free_swap(struct page *page) { diff --git a/include/linux/vm_event_item.h b/include/linux/vm_event_item.h index e623d392db0c..67c1dbd19c6d 100644 --- a/include/linux/vm_event_item.h +++ b/include/linux/vm_event_item.h @@ -25,6 +25,7 @@ enum vm_event_item { PGPGIN, PGPGOUT, PSWPIN, PSWPOUT, FOR_ALL_ZONES(PGALLOC), PGFREE, PGACTIVATE, PGDEACTIVATE, PGFAULT, PGMAJFAULT, + PGLAZYFREED, FOR_ALL_ZONES(PGREFILL), FOR_ALL_ZONES(PGSTEAL_KSWAPD), FOR_ALL_ZONES(PGSTEAL_DIRECT), @@ -68,7 +69,9 @@ enum vm_event_item { PGPGIN, PGPGOUT, PSWPIN, PSWPOUT, THP_FAULT_FALLBACK, THP_COLLAPSE_ALLOC, THP_COLLAPSE_ALLOC_FAILED, - THP_SPLIT, + THP_SPLIT_PAGE, + THP_SPLIT_PAGE_FAILED, + THP_SPLIT_PMD, THP_ZERO_PAGE_ALLOC, THP_ZERO_PAGE_ALLOC_FAILED, #endif diff --git a/include/trace/events/huge_memory.h b/include/trace/events/huge_memory.h index 97d635cabac8..0f803d2783e3 100644 --- a/include/trace/events/huge_memory.h +++ b/include/trace/events/huge_memory.h @@ -22,6 +22,7 @@ EM( SCAN_PAGE_LRU, "page_not_in_lru") \ EM( SCAN_PAGE_LOCK, "page_locked") \ EM( SCAN_PAGE_ANON, "page_not_anon") \ + EM( SCAN_PAGE_COMPOUND, "page_compound") \ EM( SCAN_ANY_PROCESS, "no_process_for_page") \ EM( SCAN_VMA_NULL, "vma_null") \ EM( SCAN_VMA_CHECK, "vma_check_failed") \ diff --git a/include/uapi/asm-generic/mman-common.h b/include/uapi/asm-generic/mman-common.h index a74dd84bbb6d..58274382a616 100644 --- a/include/uapi/asm-generic/mman-common.h +++ b/include/uapi/asm-generic/mman-common.h @@ -41,6 +41,7 @@ #define MADV_DONTNEED 4 /* don't need these pages */ /* common parameters: try to keep these consistent across architectures */ +#define MADV_FREE 8 /* free pages only if memory pressure */ #define MADV_REMOVE 9 /* remove these pages & resources */ #define MADV_DONTFORK 10 /* don't inherit across fork */ #define MADV_DOFORK 11 /* do inherit across fork */ |