diff options
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 |