diff options
author | Linus Torvalds <torvalds@linux-foundation.org> | 2019-05-14 20:10:55 +0300 |
---|---|---|
committer | Linus Torvalds <torvalds@linux-foundation.org> | 2019-05-14 20:10:55 +0300 |
commit | 318222a35bfb0ae9b5ff3e359a583463e6cfcd94 (patch) | |
tree | 6a8d921f7ac9915f3f12dd3fcd7efaaf6f16bb09 /include/linux | |
parent | 7e9890a3500d95c01511a4c45b7e7192dfa47ae2 (diff) | |
parent | 640be2d1ffbc1946f1547eb89b5005ed7542de99 (diff) | |
download | linux-318222a35bfb0ae9b5ff3e359a583463e6cfcd94.tar.xz |
Merge branch 'akpm' (patches from Andrew)
Merge misc updates from Andrew Morton:
- a few misc things and hotfixes
- ocfs2
- almost all of MM
* emailed patches from Andrew Morton <akpm@linux-foundation.org>: (139 commits)
kernel/memremap.c: remove the unused device_private_entry_fault() export
mm: delete find_get_entries_tag
mm/huge_memory.c: make __thp_get_unmapped_area static
mm/mprotect.c: fix compilation warning because of unused 'mm' variable
mm/page-writeback: introduce tracepoint for wait_on_page_writeback()
mm/vmscan: simplify trace_reclaim_flags and trace_shrink_flags
mm/Kconfig: update "Memory Model" help text
mm/vmscan.c: don't disable irq again when count pgrefill for memcg
mm: memblock: make keeping memblock memory opt-in rather than opt-out
hugetlbfs: always use address space in inode for resv_map pointer
mm/z3fold.c: support page migration
mm/z3fold.c: add structure for buddy handles
mm/z3fold.c: improve compression by extending search
mm/z3fold.c: introduce helper functions
mm/page_alloc.c: remove unnecessary parameter in rmqueue_pcplist
mm/hmm: add ARCH_HAS_HMM_MIRROR ARCH_HAS_HMM_DEVICE Kconfig
mm/vmscan.c: simplify shrink_inactive_list()
fs/sync.c: sync_file_range(2) may use WB_SYNC_ALL writeback
xen/privcmd-buf.c: convert to use vm_map_pages_zero()
xen/gntdev.c: convert to use vm_map_pages()
...
Diffstat (limited to 'include/linux')
-rw-r--r-- | include/linux/balloon_compaction.h | 15 | ||||
-rw-r--r-- | include/linux/gfp.h | 4 | ||||
-rw-r--r-- | include/linux/hmm.h | 310 | ||||
-rw-r--r-- | include/linux/huge_mm.h | 6 | ||||
-rw-r--r-- | include/linux/hugetlb.h | 4 | ||||
-rw-r--r-- | include/linux/list.h | 18 | ||||
-rw-r--r-- | include/linux/memblock.h | 44 | ||||
-rw-r--r-- | include/linux/memcontrol.h | 34 | ||||
-rw-r--r-- | include/linux/memory.h | 2 | ||||
-rw-r--r-- | include/linux/memory_hotplug.h | 42 | ||||
-rw-r--r-- | include/linux/mm.h | 114 | ||||
-rw-r--r-- | include/linux/mm_inline.h | 2 | ||||
-rw-r--r-- | include/linux/mm_types.h | 2 | ||||
-rw-r--r-- | include/linux/mmu_notifier.h | 63 | ||||
-rw-r--r-- | include/linux/mmzone.h | 5 | ||||
-rw-r--r-- | include/linux/pagemap.h | 26 | ||||
-rw-r--r-- | include/linux/userfaultfd_k.h | 2 | ||||
-rw-r--r-- | include/linux/vmstat.h | 2 |
18 files changed, 527 insertions, 168 deletions
diff --git a/include/linux/balloon_compaction.h b/include/linux/balloon_compaction.h index f111c780ef1d..f31521dcb09a 100644 --- a/include/linux/balloon_compaction.h +++ b/include/linux/balloon_compaction.h @@ -151,21 +151,6 @@ static inline void balloon_page_delete(struct page *page) list_del(&page->lru); } -static inline bool __is_movable_balloon_page(struct page *page) -{ - return false; -} - -static inline bool balloon_page_movable(struct page *page) -{ - return false; -} - -static inline bool isolated_balloon_page(struct page *page) -{ - return false; -} - static inline bool balloon_page_isolate(struct page *page) { return false; diff --git a/include/linux/gfp.h b/include/linux/gfp.h index fdab7de7490d..fb07b503dc45 100644 --- a/include/linux/gfp.h +++ b/include/linux/gfp.h @@ -585,12 +585,12 @@ static inline bool pm_suspended_storage(void) } #endif /* CONFIG_PM_SLEEP */ -#if (defined(CONFIG_MEMORY_ISOLATION) && defined(CONFIG_COMPACTION)) || defined(CONFIG_CMA) +#ifdef CONFIG_CONTIG_ALLOC /* The below functions must be run on a range from a single zone. */ extern int alloc_contig_range(unsigned long start, unsigned long end, unsigned migratetype, gfp_t gfp_mask); -extern void free_contig_range(unsigned long pfn, unsigned nr_pages); #endif +void free_contig_range(unsigned long pfn, unsigned int nr_pages); #ifdef CONFIG_CMA /* CMA stuff */ diff --git a/include/linux/hmm.h b/include/linux/hmm.h index ad50b7b4f141..51ec27a84668 100644 --- a/include/linux/hmm.h +++ b/include/linux/hmm.h @@ -77,8 +77,34 @@ #include <linux/migrate.h> #include <linux/memremap.h> #include <linux/completion.h> +#include <linux/mmu_notifier.h> -struct hmm; + +/* + * struct hmm - HMM per mm struct + * + * @mm: mm struct this HMM struct is bound to + * @lock: lock protecting ranges list + * @ranges: list of range being snapshotted + * @mirrors: list of mirrors for this mm + * @mmu_notifier: mmu notifier to track updates to CPU page table + * @mirrors_sem: read/write semaphore protecting the mirrors list + * @wq: wait queue for user waiting on a range invalidation + * @notifiers: count of active mmu notifiers + * @dead: is the mm dead ? + */ +struct hmm { + struct mm_struct *mm; + struct kref kref; + struct mutex lock; + struct list_head ranges; + struct list_head mirrors; + struct mmu_notifier mmu_notifier; + struct rw_semaphore mirrors_sem; + wait_queue_head_t wq; + long notifiers; + bool dead; +}; /* * hmm_pfn_flag_e - HMM flag enums @@ -131,6 +157,7 @@ enum hmm_pfn_value_e { /* * struct hmm_range - track invalidation lock on virtual address range * + * @hmm: the core HMM structure this range is active against * @vma: the vm area struct for the range * @list: all range lock are on a list * @start: range virtual start address (inclusive) @@ -138,10 +165,13 @@ enum hmm_pfn_value_e { * @pfns: array of pfns (big enough for the range) * @flags: pfn flags to match device driver page table * @values: pfn value for some special case (none, special, error, ...) + * @default_flags: default flags for the range (write, read, ... see hmm doc) + * @pfn_flags_mask: allows to mask pfn flags so that only default_flags matter * @pfn_shifts: pfn shift value (should be <= PAGE_SHIFT) * @valid: pfns array did not change since it has been fill by an HMM function */ struct hmm_range { + struct hmm *hmm; struct vm_area_struct *vma; struct list_head list; unsigned long start; @@ -149,41 +179,96 @@ struct hmm_range { uint64_t *pfns; const uint64_t *flags; const uint64_t *values; + uint64_t default_flags; + uint64_t pfn_flags_mask; + uint8_t page_shift; uint8_t pfn_shift; bool valid; }; /* - * hmm_pfn_to_page() - return struct page pointed to by a valid HMM pfn - * @range: range use to decode HMM pfn value - * @pfn: HMM pfn value to get corresponding struct page from - * Returns: struct page pointer if pfn is a valid HMM pfn, NULL otherwise + * hmm_range_page_shift() - return the page shift for the range + * @range: range being queried + * Returns: page shift (page size = 1 << page shift) for the range + */ +static inline unsigned hmm_range_page_shift(const struct hmm_range *range) +{ + return range->page_shift; +} + +/* + * hmm_range_page_size() - return the page size for the range + * @range: range being queried + * Returns: page size for the range in bytes + */ +static inline unsigned long hmm_range_page_size(const struct hmm_range *range) +{ + return 1UL << hmm_range_page_shift(range); +} + +/* + * hmm_range_wait_until_valid() - wait for range to be valid + * @range: range affected by invalidation to wait on + * @timeout: time out for wait in ms (ie abort wait after that period of time) + * Returns: true if the range is valid, false otherwise. + */ +static inline bool hmm_range_wait_until_valid(struct hmm_range *range, + unsigned long timeout) +{ + /* Check if mm is dead ? */ + if (range->hmm == NULL || range->hmm->dead || range->hmm->mm == NULL) { + range->valid = false; + return false; + } + if (range->valid) + return true; + wait_event_timeout(range->hmm->wq, range->valid || range->hmm->dead, + msecs_to_jiffies(timeout)); + /* Return current valid status just in case we get lucky */ + return range->valid; +} + +/* + * hmm_range_valid() - test if a range is valid or not + * @range: range + * Returns: true if the range is valid, false otherwise. + */ +static inline bool hmm_range_valid(struct hmm_range *range) +{ + return range->valid; +} + +/* + * hmm_device_entry_to_page() - return struct page pointed to by a device entry + * @range: range use to decode device entry value + * @entry: device entry value to get corresponding struct page from + * Returns: struct page pointer if entry is a valid, NULL otherwise * - * If the HMM pfn is valid (ie valid flag set) then return the struct page - * matching the pfn value stored in the HMM pfn. Otherwise return NULL. + * If the device entry is valid (ie valid flag set) then return the struct page + * matching the entry value. Otherwise return NULL. */ -static inline struct page *hmm_pfn_to_page(const struct hmm_range *range, - uint64_t pfn) +static inline struct page *hmm_device_entry_to_page(const struct hmm_range *range, + uint64_t entry) { - if (pfn == range->values[HMM_PFN_NONE]) + if (entry == range->values[HMM_PFN_NONE]) return NULL; - if (pfn == range->values[HMM_PFN_ERROR]) + if (entry == range->values[HMM_PFN_ERROR]) return NULL; - if (pfn == range->values[HMM_PFN_SPECIAL]) + if (entry == range->values[HMM_PFN_SPECIAL]) return NULL; - if (!(pfn & range->flags[HMM_PFN_VALID])) + if (!(entry & range->flags[HMM_PFN_VALID])) return NULL; - return pfn_to_page(pfn >> range->pfn_shift); + return pfn_to_page(entry >> range->pfn_shift); } /* - * hmm_pfn_to_pfn() - return pfn value store in a HMM pfn - * @range: range use to decode HMM pfn value - * @pfn: HMM pfn value to extract pfn from - * Returns: pfn value if HMM pfn is valid, -1UL otherwise + * hmm_device_entry_to_pfn() - return pfn value store in a device entry + * @range: range use to decode device entry value + * @entry: device entry to extract pfn from + * Returns: pfn value if device entry is valid, -1UL otherwise */ -static inline unsigned long hmm_pfn_to_pfn(const struct hmm_range *range, - uint64_t pfn) +static inline unsigned long +hmm_device_entry_to_pfn(const struct hmm_range *range, uint64_t pfn) { if (pfn == range->values[HMM_PFN_NONE]) return -1UL; @@ -197,31 +282,66 @@ static inline unsigned long hmm_pfn_to_pfn(const struct hmm_range *range, } /* - * hmm_pfn_from_page() - create a valid HMM pfn value from struct page + * hmm_device_entry_from_page() - create a valid device entry for a page * @range: range use to encode HMM pfn value - * @page: struct page pointer for which to create the HMM pfn - * Returns: valid HMM pfn for the page + * @page: page for which to create the device entry + * Returns: valid device entry for the page */ -static inline uint64_t hmm_pfn_from_page(const struct hmm_range *range, - struct page *page) +static inline uint64_t hmm_device_entry_from_page(const struct hmm_range *range, + struct page *page) { return (page_to_pfn(page) << range->pfn_shift) | range->flags[HMM_PFN_VALID]; } /* - * hmm_pfn_from_pfn() - create a valid HMM pfn value from pfn + * hmm_device_entry_from_pfn() - create a valid device entry value from pfn * @range: range use to encode HMM pfn value - * @pfn: pfn value for which to create the HMM pfn - * Returns: valid HMM pfn for the pfn + * @pfn: pfn value for which to create the device entry + * Returns: valid device entry for the pfn */ -static inline uint64_t hmm_pfn_from_pfn(const struct hmm_range *range, - unsigned long pfn) +static inline uint64_t hmm_device_entry_from_pfn(const struct hmm_range *range, + unsigned long pfn) { return (pfn << range->pfn_shift) | range->flags[HMM_PFN_VALID]; } +/* + * Old API: + * hmm_pfn_to_page() + * hmm_pfn_to_pfn() + * hmm_pfn_from_page() + * hmm_pfn_from_pfn() + * + * This are the OLD API please use new API, it is here to avoid cross-tree + * merge painfullness ie we convert things to new API in stages. + */ +static inline struct page *hmm_pfn_to_page(const struct hmm_range *range, + uint64_t pfn) +{ + return hmm_device_entry_to_page(range, pfn); +} + +static inline unsigned long hmm_pfn_to_pfn(const struct hmm_range *range, + uint64_t pfn) +{ + return hmm_device_entry_to_pfn(range, pfn); +} + +static inline uint64_t hmm_pfn_from_page(const struct hmm_range *range, + struct page *page) +{ + return hmm_device_entry_from_page(range, page); +} + +static inline uint64_t hmm_pfn_from_pfn(const struct hmm_range *range, + unsigned long pfn) +{ + return hmm_device_entry_from_pfn(range, pfn); +} + + #if IS_ENABLED(CONFIG_HMM_MIRROR) /* @@ -353,43 +473,113 @@ struct hmm_mirror { int hmm_mirror_register(struct hmm_mirror *mirror, struct mm_struct *mm); void hmm_mirror_unregister(struct hmm_mirror *mirror); - /* - * To snapshot the CPU page table, call hmm_vma_get_pfns(), then take a device - * driver lock that serializes device page table updates, then call - * hmm_vma_range_done(), to check if the snapshot is still valid. The same - * device driver page table update lock must also be used in the - * hmm_mirror_ops.sync_cpu_device_pagetables() callback, so that CPU page - * table invalidation serializes on it. - * - * YOU MUST CALL hmm_vma_range_done() ONCE AND ONLY ONCE EACH TIME YOU CALL - * hmm_vma_get_pfns() WITHOUT ERROR ! - * - * IF YOU DO NOT FOLLOW THE ABOVE RULE THE SNAPSHOT CONTENT MIGHT BE INVALID ! + * hmm_mirror_mm_is_alive() - test if mm is still alive + * @mirror: the HMM mm mirror for which we want to lock the mmap_sem + * Returns: false if the mm is dead, true otherwise + * + * This is an optimization it will not accurately always return -EINVAL if the + * mm is dead ie there can be false negative (process is being kill but HMM is + * not yet inform of that). It is only intented to be use to optimize out case + * where driver is about to do something time consuming and it would be better + * to skip it if the mm is dead. */ -int hmm_vma_get_pfns(struct hmm_range *range); -bool hmm_vma_range_done(struct hmm_range *range); +static inline bool hmm_mirror_mm_is_alive(struct hmm_mirror *mirror) +{ + struct mm_struct *mm; + + if (!mirror || !mirror->hmm) + return false; + mm = READ_ONCE(mirror->hmm->mm); + if (mirror->hmm->dead || !mm) + return false; + + return true; +} /* - * Fault memory on behalf of device driver. Unlike handle_mm_fault(), this will - * not migrate any device memory back to system memory. The HMM pfn array will - * be updated with the fault result and current snapshot of the CPU page table - * for the range. - * - * The mmap_sem must be taken in read mode before entering and it might be - * dropped by the function if the block argument is false. In that case, the - * function returns -EAGAIN. - * - * Return value does not reflect if the fault was successful for every single - * address or not. Therefore, the caller must to inspect the HMM pfn array to - * determine fault status for each address. - * - * Trying to fault inside an invalid vma will result in -EINVAL. + * Please see Documentation/vm/hmm.rst for how to use the range API. + */ +int hmm_range_register(struct hmm_range *range, + struct mm_struct *mm, + unsigned long start, + unsigned long end, + unsigned page_shift); +void hmm_range_unregister(struct hmm_range *range); +long hmm_range_snapshot(struct hmm_range *range); +long hmm_range_fault(struct hmm_range *range, bool block); +long hmm_range_dma_map(struct hmm_range *range, + struct device *device, + dma_addr_t *daddrs, + bool block); +long hmm_range_dma_unmap(struct hmm_range *range, + struct vm_area_struct *vma, + struct device *device, + dma_addr_t *daddrs, + bool dirty); + +/* + * HMM_RANGE_DEFAULT_TIMEOUT - default timeout (ms) when waiting for a range * - * See the function description in mm/hmm.c for further documentation. + * When waiting for mmu notifiers we need some kind of time out otherwise we + * could potentialy wait for ever, 1000ms ie 1s sounds like a long time to + * wait already. */ -int hmm_vma_fault(struct hmm_range *range, bool block); +#define HMM_RANGE_DEFAULT_TIMEOUT 1000 + +/* This is a temporary helper to avoid merge conflict between trees. */ +static inline bool hmm_vma_range_done(struct hmm_range *range) +{ + bool ret = hmm_range_valid(range); + + hmm_range_unregister(range); + return ret; +} + +/* This is a temporary helper to avoid merge conflict between trees. */ +static inline int hmm_vma_fault(struct hmm_range *range, bool block) +{ + long ret; + + /* + * With the old API the driver must set each individual entries with + * the requested flags (valid, write, ...). So here we set the mask to + * keep intact the entries provided by the driver and zero out the + * default_flags. + */ + range->default_flags = 0; + range->pfn_flags_mask = -1UL; + + ret = hmm_range_register(range, range->vma->vm_mm, + range->start, range->end, + PAGE_SHIFT); + if (ret) + return (int)ret; + + if (!hmm_range_wait_until_valid(range, HMM_RANGE_DEFAULT_TIMEOUT)) { + /* + * The mmap_sem was taken by driver we release it here and + * returns -EAGAIN which correspond to mmap_sem have been + * drop in the old API. + */ + up_read(&range->vma->vm_mm->mmap_sem); + return -EAGAIN; + } + + ret = hmm_range_fault(range, block); + if (ret <= 0) { + if (ret == -EBUSY || !ret) { + /* Same as above drop mmap_sem to match old API. */ + up_read(&range->vma->vm_mm->mmap_sem); + ret = -EBUSY; + } else if (ret == -EAGAIN) + ret = -EBUSY; + hmm_range_unregister(range); + return ret; + } + return 0; +} /* Below are for HMM internal use only! Not to be used by device driver! */ void hmm_mm_destroy(struct mm_struct *mm); diff --git a/include/linux/huge_mm.h b/include/linux/huge_mm.h index 381e872bfde0..7cd5c150c21d 100644 --- a/include/linux/huge_mm.h +++ b/include/linux/huge_mm.h @@ -47,10 +47,8 @@ extern bool move_huge_pmd(struct vm_area_struct *vma, unsigned long old_addr, extern int change_huge_pmd(struct vm_area_struct *vma, pmd_t *pmd, unsigned long addr, pgprot_t newprot, int prot_numa); -vm_fault_t vmf_insert_pfn_pmd(struct vm_area_struct *vma, unsigned long addr, - pmd_t *pmd, pfn_t pfn, bool write); -vm_fault_t vmf_insert_pfn_pud(struct vm_area_struct *vma, unsigned long addr, - pud_t *pud, pfn_t pfn, bool write); +vm_fault_t vmf_insert_pfn_pmd(struct vm_fault *vmf, pfn_t pfn, bool write); +vm_fault_t vmf_insert_pfn_pud(struct vm_fault *vmf, pfn_t pfn, bool write); enum transparent_hugepage_flag { TRANSPARENT_HUGEPAGE_FLAG, TRANSPARENT_HUGEPAGE_REQ_MADV_FLAG, diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h index 11943b60f208..edf476c8cfb9 100644 --- a/include/linux/hugetlb.h +++ b/include/linux/hugetlb.h @@ -123,9 +123,7 @@ void move_hugetlb_state(struct page *oldpage, struct page *newpage, int reason); void free_huge_page(struct page *page); void hugetlb_fix_reserve_counts(struct inode *inode); extern struct mutex *hugetlb_fault_mutex_table; -u32 hugetlb_fault_mutex_hash(struct hstate *h, struct mm_struct *mm, - struct vm_area_struct *vma, - struct address_space *mapping, +u32 hugetlb_fault_mutex_hash(struct hstate *h, struct address_space *mapping, pgoff_t idx, unsigned long address); pte_t *huge_pmd_share(struct mm_struct *mm, unsigned long addr, pud_t *pud); diff --git a/include/linux/list.h b/include/linux/list.h index 58aa3adf94e6..9e9a6403dbe4 100644 --- a/include/linux/list.h +++ b/include/linux/list.h @@ -271,6 +271,24 @@ static inline void list_rotate_left(struct list_head *head) } /** + * list_rotate_to_front() - Rotate list to specific item. + * @list: The desired new front of the list. + * @head: The head of the list. + * + * Rotates list so that @list becomes the new front of the list. + */ +static inline void list_rotate_to_front(struct list_head *list, + struct list_head *head) +{ + /* + * Deletes the list head from the list denoted by @head and + * places it as the tail of @list, this effectively rotates the + * list so that @list is at the front. + */ + list_move_tail(head, list); +} + +/** * list_is_singular - tests whether a list has just one entry. * @head: the list to test. */ diff --git a/include/linux/memblock.h b/include/linux/memblock.h index 294d5d80e150..676d3900e1bd 100644 --- a/include/linux/memblock.h +++ b/include/linux/memblock.h @@ -96,13 +96,14 @@ struct memblock { extern struct memblock memblock; extern int memblock_debug; -#ifdef CONFIG_ARCH_DISCARD_MEMBLOCK +#ifndef CONFIG_ARCH_KEEP_MEMBLOCK #define __init_memblock __meminit #define __initdata_memblock __meminitdata void memblock_discard(void); #else #define __init_memblock #define __initdata_memblock +static inline void memblock_discard(void) {} #endif #define memblock_dbg(fmt, ...) \ @@ -240,6 +241,47 @@ void __next_mem_pfn_range(int *idx, int nid, unsigned long *out_start_pfn, i >= 0; __next_mem_pfn_range(&i, nid, p_start, p_end, p_nid)) #endif /* CONFIG_HAVE_MEMBLOCK_NODE_MAP */ +#ifdef CONFIG_DEFERRED_STRUCT_PAGE_INIT +void __next_mem_pfn_range_in_zone(u64 *idx, struct zone *zone, + unsigned long *out_spfn, + unsigned long *out_epfn); +/** + * for_each_free_mem_range_in_zone - iterate through zone specific free + * memblock areas + * @i: u64 used as loop variable + * @zone: zone in which all of the memory blocks reside + * @p_start: ptr to phys_addr_t for start address of the range, can be %NULL + * @p_end: ptr to phys_addr_t for end address of the range, can be %NULL + * + * Walks over free (memory && !reserved) areas of memblock in a specific + * zone. Available once memblock and an empty zone is initialized. The main + * assumption is that the zone start, end, and pgdat have been associated. + * This way we can use the zone to determine NUMA node, and if a given part + * of the memblock is valid for the zone. + */ +#define for_each_free_mem_pfn_range_in_zone(i, zone, p_start, p_end) \ + for (i = 0, \ + __next_mem_pfn_range_in_zone(&i, zone, p_start, p_end); \ + i != U64_MAX; \ + __next_mem_pfn_range_in_zone(&i, zone, p_start, p_end)) + +/** + * for_each_free_mem_range_in_zone_from - iterate through zone specific + * free memblock areas from a given point + * @i: u64 used as loop variable + * @zone: zone in which all of the memory blocks reside + * @p_start: ptr to phys_addr_t for start address of the range, can be %NULL + * @p_end: ptr to phys_addr_t for end address of the range, can be %NULL + * + * Walks over free (memory && !reserved) areas of memblock in a specific + * zone, continuing from current position. Available as soon as memblock is + * initialized. + */ +#define for_each_free_mem_pfn_range_in_zone_from(i, zone, p_start, p_end) \ + for (; i != U64_MAX; \ + __next_mem_pfn_range_in_zone(&i, zone, p_start, p_end)) +#endif /* CONFIG_DEFERRED_STRUCT_PAGE_INIT */ + /** * for_each_free_mem_range - iterate through free memblock areas * @i: u64 used as loop variable diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h index dbb6118370c1..30561a954ee0 100644 --- a/include/linux/memcontrol.h +++ b/include/linux/memcontrol.h @@ -501,22 +501,6 @@ int mem_cgroup_select_victim_node(struct mem_cgroup *memcg); void mem_cgroup_update_lru_size(struct lruvec *lruvec, enum lru_list lru, int zid, int nr_pages); -unsigned long mem_cgroup_node_nr_lru_pages(struct mem_cgroup *memcg, - int nid, unsigned int lru_mask); - -static inline -unsigned long mem_cgroup_get_lru_size(struct lruvec *lruvec, enum lru_list lru) -{ - struct mem_cgroup_per_node *mz; - unsigned long nr_pages = 0; - int zid; - - mz = container_of(lruvec, struct mem_cgroup_per_node, lruvec); - for (zid = 0; zid < MAX_NR_ZONES; zid++) - nr_pages += mz->lru_zone_size[zid][lru]; - return nr_pages; -} - static inline unsigned long mem_cgroup_get_zone_lru_size(struct lruvec *lruvec, enum lru_list lru, int zone_idx) @@ -960,11 +944,6 @@ static inline bool mem_cgroup_online(struct mem_cgroup *memcg) return true; } -static inline unsigned long -mem_cgroup_get_lru_size(struct lruvec *lruvec, enum lru_list lru) -{ - return 0; -} static inline unsigned long mem_cgroup_get_zone_lru_size(struct lruvec *lruvec, enum lru_list lru, int zone_idx) @@ -972,13 +951,6 @@ unsigned long mem_cgroup_get_zone_lru_size(struct lruvec *lruvec, return 0; } -static inline unsigned long -mem_cgroup_node_nr_lru_pages(struct mem_cgroup *memcg, - int nid, unsigned int lru_mask) -{ - return 0; -} - static inline unsigned long mem_cgroup_get_max(struct mem_cgroup *memcg) { return 0; @@ -1117,6 +1089,12 @@ static inline void count_memcg_events(struct mem_cgroup *memcg, { } +static inline void __count_memcg_events(struct mem_cgroup *memcg, + enum vm_event_item idx, + unsigned long count) +{ +} + static inline void count_memcg_page_event(struct page *page, int idx) { diff --git a/include/linux/memory.h b/include/linux/memory.h index a6ddefc60517..e1dc1bb2b787 100644 --- a/include/linux/memory.h +++ b/include/linux/memory.h @@ -113,7 +113,7 @@ extern int register_memory_isolate_notifier(struct notifier_block *nb); extern void unregister_memory_isolate_notifier(struct notifier_block *nb); int hotplug_memory_register(int nid, struct mem_section *section); #ifdef CONFIG_MEMORY_HOTREMOVE -extern int unregister_memory_section(struct mem_section *); +extern void unregister_memory_section(struct mem_section *); #endif extern int memory_dev_init(void); extern int memory_notify(unsigned long val, void *v); diff --git a/include/linux/memory_hotplug.h b/include/linux/memory_hotplug.h index 8ade08c50d26..ae892eef8b82 100644 --- a/include/linux/memory_hotplug.h +++ b/include/linux/memory_hotplug.h @@ -54,6 +54,16 @@ enum { }; /* + * Restrictions for the memory hotplug: + * flags: MHP_ flags + * altmap: alternative allocator for memmap array + */ +struct mhp_restrictions { + unsigned long flags; + struct vmem_altmap *altmap; +}; + +/* * Zone resizing functions * * Note: any attempt to resize a zone should has pgdat_resize_lock() @@ -87,7 +97,8 @@ extern int add_one_highpage(struct page *page, int pfn, int bad_ppro); extern int online_pages(unsigned long, unsigned long, int); extern int test_pages_in_a_zone(unsigned long start_pfn, unsigned long end_pfn, unsigned long *valid_start, unsigned long *valid_end); -extern void __offline_isolated_pages(unsigned long, unsigned long); +extern unsigned long __offline_isolated_pages(unsigned long start_pfn, + unsigned long end_pfn); typedef void (*online_page_callback_t)(struct page *page, unsigned int order); @@ -100,6 +111,8 @@ extern void __online_page_free(struct page *page); extern int try_online_node(int nid); +extern int arch_add_memory(int nid, u64 start, u64 size, + struct mhp_restrictions *restrictions); extern u64 max_mem_size; extern bool memhp_auto_online; @@ -111,26 +124,33 @@ static inline bool movable_node_is_enabled(void) } #ifdef CONFIG_MEMORY_HOTREMOVE -extern int arch_remove_memory(int nid, u64 start, u64 size, - struct vmem_altmap *altmap); -extern int __remove_pages(struct zone *zone, unsigned long start_pfn, - unsigned long nr_pages, struct vmem_altmap *altmap); +extern void arch_remove_memory(int nid, u64 start, u64 size, + struct vmem_altmap *altmap); +extern void __remove_pages(struct zone *zone, unsigned long start_pfn, + unsigned long nr_pages, struct vmem_altmap *altmap); #endif /* CONFIG_MEMORY_HOTREMOVE */ +/* + * Do we want sysfs memblock files created. This will allow userspace to online + * and offline memory explicitly. Lack of this bit means that the caller has to + * call move_pfn_range_to_zone to finish the initialization. + */ + +#define MHP_MEMBLOCK_API (1<<0) + /* reasonably generic interface to expand the physical pages */ extern int __add_pages(int nid, unsigned long start_pfn, unsigned long nr_pages, - struct vmem_altmap *altmap, bool want_memblock); + struct mhp_restrictions *restrictions); #ifndef CONFIG_ARCH_HAS_ADD_PAGES static inline int add_pages(int nid, unsigned long start_pfn, - unsigned long nr_pages, struct vmem_altmap *altmap, - bool want_memblock) + unsigned long nr_pages, struct mhp_restrictions *restrictions) { - return __add_pages(nid, start_pfn, nr_pages, altmap, want_memblock); + return __add_pages(nid, start_pfn, nr_pages, restrictions); } #else /* ARCH_HAS_ADD_PAGES */ int add_pages(int nid, unsigned long start_pfn, unsigned long nr_pages, - struct vmem_altmap *altmap, bool want_memblock); + struct mhp_restrictions *restrictions); #endif /* ARCH_HAS_ADD_PAGES */ #ifdef CONFIG_NUMA @@ -331,8 +351,6 @@ extern int walk_memory_range(unsigned long start_pfn, unsigned long end_pfn, extern int __add_memory(int nid, u64 start, u64 size); extern int add_memory(int nid, u64 start, u64 size); extern int add_memory_resource(int nid, struct resource *resource); -extern int arch_add_memory(int nid, u64 start, u64 size, - struct vmem_altmap *altmap, bool want_memblock); extern void move_pfn_range_to_zone(struct zone *zone, unsigned long start_pfn, unsigned long nr_pages, struct vmem_altmap *altmap); extern bool is_memblock_offlined(struct memory_block *mem); diff --git a/include/linux/mm.h b/include/linux/mm.h index 083d7b4863ed..912614fbbef3 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -124,10 +124,45 @@ extern int mmap_rnd_compat_bits __read_mostly; /* * On some architectures it is expensive to call memset() for small sizes. - * Those architectures should provide their own implementation of "struct page" - * zeroing by defining this macro in <asm/pgtable.h>. + * If an architecture decides to implement their own version of + * mm_zero_struct_page they should wrap the defines below in a #ifndef and + * define their own version of this macro in <asm/pgtable.h> */ -#ifndef mm_zero_struct_page +#if BITS_PER_LONG == 64 +/* This function must be updated when the size of struct page grows above 80 + * or reduces below 56. The idea that compiler optimizes out switch() + * statement, and only leaves move/store instructions. Also the compiler can + * combine write statments if they are both assignments and can be reordered, + * this can result in several of the writes here being dropped. + */ +#define mm_zero_struct_page(pp) __mm_zero_struct_page(pp) +static inline void __mm_zero_struct_page(struct page *page) +{ + unsigned long *_pp = (void *)page; + + /* Check that struct page is either 56, 64, 72, or 80 bytes */ + BUILD_BUG_ON(sizeof(struct page) & 7); + BUILD_BUG_ON(sizeof(struct page) < 56); + BUILD_BUG_ON(sizeof(struct page) > 80); + + switch (sizeof(struct page)) { + case 80: + _pp[9] = 0; /* fallthrough */ + case 72: + _pp[8] = 0; /* fallthrough */ + case 64: + _pp[7] = 0; /* fallthrough */ + case 56: + _pp[6] = 0; + _pp[5] = 0; + _pp[4] = 0; + _pp[3] = 0; + _pp[2] = 0; + _pp[1] = 0; + _pp[0] = 0; + } +} +#else #define mm_zero_struct_page(pp) ((void)memset((pp), 0, sizeof(struct page))) #endif @@ -1007,6 +1042,30 @@ static inline void put_page(struct page *page) __put_page(page); } +/** + * put_user_page() - release a gup-pinned page + * @page: pointer to page to be released + * + * Pages that were pinned via get_user_pages*() must be released via + * either put_user_page(), or one of the put_user_pages*() routines + * below. This is so that eventually, pages that are pinned via + * get_user_pages*() can be separately tracked and uniquely handled. In + * particular, interactions with RDMA and filesystems need special + * handling. + * + * put_user_page() and put_page() are not interchangeable, despite this early + * implementation that makes them look the same. put_user_page() calls must + * be perfectly matched up with get_user_page() calls. + */ +static inline void put_user_page(struct page *page) +{ + put_page(page); +} + +void put_user_pages_dirty(struct page **pages, unsigned long npages); +void put_user_pages_dirty_lock(struct page **pages, unsigned long npages); +void put_user_pages(struct page **pages, unsigned long npages); + #if defined(CONFIG_SPARSEMEM) && !defined(CONFIG_SPARSEMEM_VMEMMAP) #define SECTION_IN_PAGE_FLAGS #endif @@ -1505,21 +1564,8 @@ long get_user_pages_locked(unsigned long start, unsigned long nr_pages, long get_user_pages_unlocked(unsigned long start, unsigned long nr_pages, struct page **pages, unsigned int gup_flags); -#if defined(CONFIG_FS_DAX) || defined(CONFIG_CMA) -long get_user_pages_longterm(unsigned long start, unsigned long nr_pages, - unsigned int gup_flags, struct page **pages, - struct vm_area_struct **vmas); -#else -static inline long get_user_pages_longterm(unsigned long start, - unsigned long nr_pages, unsigned int gup_flags, - struct page **pages, struct vm_area_struct **vmas) -{ - return get_user_pages(start, nr_pages, gup_flags, pages, vmas); -} -#endif /* CONFIG_FS_DAX */ - -int get_user_pages_fast(unsigned long start, int nr_pages, int write, - struct page **pages); +int get_user_pages_fast(unsigned long start, int nr_pages, + unsigned int gup_flags, struct page **pages); /* Container for pinned pfns / pages */ struct frame_vector { @@ -2533,6 +2579,10 @@ struct vm_area_struct *find_extend_vma(struct mm_struct *, unsigned long addr); int remap_pfn_range(struct vm_area_struct *, unsigned long addr, unsigned long pfn, unsigned long size, pgprot_t); int vm_insert_page(struct vm_area_struct *, unsigned long addr, struct page *); +int vm_map_pages(struct vm_area_struct *vma, struct page **pages, + unsigned long num); +int vm_map_pages_zero(struct vm_area_struct *vma, struct page **pages, + unsigned long num); vm_fault_t vmf_insert_pfn(struct vm_area_struct *vma, unsigned long addr, unsigned long pfn); vm_fault_t vmf_insert_pfn_prot(struct vm_area_struct *vma, unsigned long addr, @@ -2583,6 +2633,34 @@ struct page *follow_page(struct vm_area_struct *vma, unsigned long address, #define FOLL_REMOTE 0x2000 /* we are working on non-current tsk/mm */ #define FOLL_COW 0x4000 /* internal GUP flag */ #define FOLL_ANON 0x8000 /* don't do file mappings */ +#define FOLL_LONGTERM 0x10000 /* mapping lifetime is indefinite: see below */ + +/* + * NOTE on FOLL_LONGTERM: + * + * FOLL_LONGTERM indicates that the page will be held for an indefinite time + * period _often_ under userspace control. This is contrasted with + * iov_iter_get_pages() where usages which are transient. + * + * FIXME: For pages which are part of a filesystem, mappings are subject to the + * lifetime enforced by the filesystem and we need guarantees that longterm + * users like RDMA and V4L2 only establish mappings which coordinate usage with + * the filesystem. Ideas for this coordination include revoking the longterm + * pin, delaying writeback, bounce buffer page writeback, etc. As FS DAX was + * added after the problem with filesystems was found FS DAX VMAs are + * specifically failed. Filesystem pages are still subject to bugs and use of + * FOLL_LONGTERM should be avoided on those pages. + * + * FIXME: Also NOTE that FOLL_LONGTERM is not supported in every GUP call. + * Currently only get_user_pages() and get_user_pages_fast() support this flag + * and calls to get_user_pages_[un]locked are specifically not allowed. This + * is due to an incompatibility with the FS DAX check and + * FAULT_FLAG_ALLOW_RETRY + * + * In the CMA case: longterm pins in a CMA region would unnecessarily fragment + * that region. And so CMA attempts to migrate the page before pinning when + * FOLL_LONGTERM is specified. + */ static inline int vm_fault_to_errno(vm_fault_t vm_fault, int foll_flags) { diff --git a/include/linux/mm_inline.h b/include/linux/mm_inline.h index 04ec454d44ce..6f2fef7b0784 100644 --- a/include/linux/mm_inline.h +++ b/include/linux/mm_inline.h @@ -29,7 +29,7 @@ static __always_inline void __update_lru_size(struct lruvec *lruvec, { struct pglist_data *pgdat = lruvec_pgdat(lruvec); - __mod_node_page_state(pgdat, NR_LRU_BASE + lru, nr_pages); + __mod_lruvec_state(lruvec, NR_LRU_BASE + lru, nr_pages); __mod_zone_page_state(&pgdat->node_zones[zid], NR_ZONE_LRU_BASE + lru, nr_pages); } diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h index 4ef4bbe78a1d..e1f42a07d8f0 100644 --- a/include/linux/mm_types.h +++ b/include/linux/mm_types.h @@ -103,7 +103,7 @@ struct page { }; struct { /* slab, slob and slub */ union { - struct list_head slab_list; /* uses lru */ + struct list_head slab_list; struct { /* Partial pages */ struct page *next; #ifdef CONFIG_64BIT diff --git a/include/linux/mmu_notifier.h b/include/linux/mmu_notifier.h index 4050ec1c3b45..b6c004bd9f6a 100644 --- a/include/linux/mmu_notifier.h +++ b/include/linux/mmu_notifier.h @@ -10,6 +10,36 @@ struct mmu_notifier; struct mmu_notifier_ops; +/** + * enum mmu_notifier_event - reason for the mmu notifier callback + * @MMU_NOTIFY_UNMAP: either munmap() that unmap the range or a mremap() that + * move the range + * + * @MMU_NOTIFY_CLEAR: clear page table entry (many reasons for this like + * madvise() or replacing a page by another one, ...). + * + * @MMU_NOTIFY_PROTECTION_VMA: update is due to protection change for the range + * ie using the vma access permission (vm_page_prot) to update the whole range + * is enough no need to inspect changes to the CPU page table (mprotect() + * syscall) + * + * @MMU_NOTIFY_PROTECTION_PAGE: update is due to change in read/write flag for + * pages in the range so to mirror those changes the user must inspect the CPU + * page table (from the end callback). + * + * @MMU_NOTIFY_SOFT_DIRTY: soft dirty accounting (still same page and same + * access flags). User should soft dirty the page in the end callback to make + * sure that anyone relying on soft dirtyness catch pages that might be written + * through non CPU mappings. + */ +enum mmu_notifier_event { + MMU_NOTIFY_UNMAP = 0, + MMU_NOTIFY_CLEAR, + MMU_NOTIFY_PROTECTION_VMA, + MMU_NOTIFY_PROTECTION_PAGE, + MMU_NOTIFY_SOFT_DIRTY, +}; + #ifdef CONFIG_MMU_NOTIFIER /* @@ -25,11 +55,15 @@ struct mmu_notifier_mm { spinlock_t lock; }; +#define MMU_NOTIFIER_RANGE_BLOCKABLE (1 << 0) + struct mmu_notifier_range { + struct vm_area_struct *vma; struct mm_struct *mm; unsigned long start; unsigned long end; - bool blockable; + unsigned flags; + enum mmu_notifier_event event; }; struct mmu_notifier_ops { @@ -225,6 +259,14 @@ extern void __mmu_notifier_invalidate_range_end(struct mmu_notifier_range *r, bool only_end); extern void __mmu_notifier_invalidate_range(struct mm_struct *mm, unsigned long start, unsigned long end); +extern bool +mmu_notifier_range_update_to_read_only(const struct mmu_notifier_range *range); + +static inline bool +mmu_notifier_range_blockable(const struct mmu_notifier_range *range) +{ + return (range->flags & MMU_NOTIFIER_RANGE_BLOCKABLE); +} static inline void mmu_notifier_release(struct mm_struct *mm) { @@ -269,7 +311,7 @@ static inline void mmu_notifier_invalidate_range_start(struct mmu_notifier_range *range) { if (mm_has_notifiers(range->mm)) { - range->blockable = true; + range->flags |= MMU_NOTIFIER_RANGE_BLOCKABLE; __mmu_notifier_invalidate_range_start(range); } } @@ -278,7 +320,7 @@ static inline int mmu_notifier_invalidate_range_start_nonblock(struct mmu_notifier_range *range) { if (mm_has_notifiers(range->mm)) { - range->blockable = false; + range->flags &= ~MMU_NOTIFIER_RANGE_BLOCKABLE; return __mmu_notifier_invalidate_range_start(range); } return 0; @@ -318,13 +360,19 @@ static inline void mmu_notifier_mm_destroy(struct mm_struct *mm) static inline void mmu_notifier_range_init(struct mmu_notifier_range *range, + enum mmu_notifier_event event, + unsigned flags, + struct vm_area_struct *vma, struct mm_struct *mm, unsigned long start, unsigned long end) { + range->vma = vma; + range->event = event; range->mm = mm; range->start = start; range->end = end; + range->flags = flags; } #define ptep_clear_flush_young_notify(__vma, __address, __ptep) \ @@ -452,9 +500,14 @@ static inline void _mmu_notifier_range_init(struct mmu_notifier_range *range, range->end = end; } -#define mmu_notifier_range_init(range, mm, start, end) \ +#define mmu_notifier_range_init(range,event,flags,vma,mm,start,end) \ _mmu_notifier_range_init(range, start, end) +static inline bool +mmu_notifier_range_blockable(const struct mmu_notifier_range *range) +{ + return true; +} static inline int mm_has_notifiers(struct mm_struct *mm) { @@ -517,6 +570,8 @@ static inline void mmu_notifier_mm_destroy(struct mm_struct *mm) { } +#define mmu_notifier_range_update_to_read_only(r) false + #define ptep_clear_flush_young_notify ptep_clear_flush_young #define pmdp_clear_flush_young_notify pmdp_clear_flush_young #define ptep_clear_young_notify ptep_test_and_clear_young diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h index fba7741533be..5a4aedc160bd 100644 --- a/include/linux/mmzone.h +++ b/include/linux/mmzone.h @@ -247,11 +247,6 @@ struct lruvec { #endif }; -/* Mask used at gathering information at once (see memcontrol.c) */ -#define LRU_ALL_FILE (BIT(LRU_INACTIVE_FILE) | BIT(LRU_ACTIVE_FILE)) -#define LRU_ALL_ANON (BIT(LRU_INACTIVE_ANON) | BIT(LRU_ACTIVE_ANON)) -#define LRU_ALL ((1 << NR_LRU_LISTS) - 1) - /* Isolate unmapped file */ #define ISOLATE_UNMAPPED ((__force isolate_mode_t)0x2) /* Isolate for asynchronous migration */ diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h index bcf909d0de5f..9ec3544baee2 100644 --- a/include/linux/pagemap.h +++ b/include/linux/pagemap.h @@ -333,6 +333,19 @@ static inline struct page *grab_cache_page_nowait(struct address_space *mapping, mapping_gfp_mask(mapping)); } +static inline struct page *find_subpage(struct page *page, pgoff_t offset) +{ + unsigned long mask; + + if (PageHuge(page)) + return page; + + VM_BUG_ON_PAGE(PageTail(page), page); + + mask = (1UL << compound_order(page)) - 1; + return page + (offset & mask); +} + struct page *find_get_entry(struct address_space *mapping, pgoff_t offset); struct page *find_lock_entry(struct address_space *mapping, pgoff_t offset); unsigned find_get_entries(struct address_space *mapping, pgoff_t start, @@ -360,9 +373,6 @@ static inline unsigned find_get_pages_tag(struct address_space *mapping, return find_get_pages_range_tag(mapping, index, (pgoff_t)-1, tag, nr_pages, pages); } -unsigned find_get_entries_tag(struct address_space *mapping, pgoff_t start, - xa_mark_t tag, unsigned int nr_entries, - struct page **entries, pgoff_t *indices); struct page *grab_cache_page_write_begin(struct address_space *mapping, pgoff_t index, unsigned flags); @@ -527,15 +537,7 @@ static inline int wait_on_page_locked_killable(struct page *page) extern void put_and_wait_on_page_locked(struct page *page); -/* - * Wait for a page to complete writeback - */ -static inline void wait_on_page_writeback(struct page *page) -{ - if (PageWriteback(page)) - wait_on_page_bit(page, PG_writeback); -} - +void wait_on_page_writeback(struct page *page); extern void end_page_writeback(struct page *page); void wait_for_stable_page(struct page *page); diff --git a/include/linux/userfaultfd_k.h b/include/linux/userfaultfd_k.h index 37c9eba75c98..ac9d71e24b81 100644 --- a/include/linux/userfaultfd_k.h +++ b/include/linux/userfaultfd_k.h @@ -28,6 +28,8 @@ #define UFFD_SHARED_FCNTL_FLAGS (O_CLOEXEC | O_NONBLOCK) #define UFFD_FLAGS_SET (EFD_SHARED_FCNTL_FLAGS) +extern int sysctl_unprivileged_userfaultfd; + extern vm_fault_t handle_userfault(struct vm_fault *vmf, unsigned long reason); extern ssize_t mcopy_atomic(struct mm_struct *dst_mm, unsigned long dst_start, diff --git a/include/linux/vmstat.h b/include/linux/vmstat.h index 2db8d60981fe..bdeda4b079fe 100644 --- a/include/linux/vmstat.h +++ b/include/linux/vmstat.h @@ -26,7 +26,7 @@ struct reclaim_stat { unsigned nr_congested; unsigned nr_writeback; unsigned nr_immediate; - unsigned nr_activate; + unsigned nr_activate[2]; unsigned nr_ref_keep; unsigned nr_unmap_fail; }; |