diff options
Diffstat (limited to 'include/linux/hmm.h')
-rw-r--r-- | include/linux/hmm.h | 279 |
1 files changed, 16 insertions, 263 deletions
diff --git a/include/linux/hmm.h b/include/linux/hmm.h index 7ef56dc18050..ddf9f7144c43 100644 --- a/include/linux/hmm.h +++ b/include/linux/hmm.h @@ -62,40 +62,12 @@ #include <linux/kconfig.h> #include <asm/pgtable.h> -#ifdef CONFIG_HMM_MIRROR - #include <linux/device.h> #include <linux/migrate.h> #include <linux/memremap.h> #include <linux/completion.h> #include <linux/mmu_notifier.h> - -/* - * 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 - */ -struct hmm { - struct mm_struct *mm; - struct kref kref; - spinlock_t ranges_lock; - struct list_head ranges; - struct list_head mirrors; - struct mmu_notifier mmu_notifier; - struct rw_semaphore mirrors_sem; - wait_queue_head_t wq; - struct rcu_head rcu; - long notifiers; -}; - /* * hmm_pfn_flag_e - HMM flag enums * @@ -148,6 +120,8 @@ enum hmm_pfn_value_e { /* * struct hmm_range - track invalidation lock on virtual address range * + * @notifier: a mmu_interval_notifier that includes the start/end + * @notifier_seq: result of mmu_interval_read_begin() * @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 @@ -158,14 +132,12 @@ enum hmm_pfn_value_e { * @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 - * @page_shift: device virtual address shift value (should be >= PAGE_SHIFT) * @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; + struct mmu_interval_notifier *notifier; + unsigned long notifier_seq; unsigned long start; unsigned long end; uint64_t *pfns; @@ -173,55 +145,10 @@ struct hmm_range { const uint64_t *values; uint64_t default_flags; uint64_t pfn_flags_mask; - uint8_t page_shift; uint8_t pfn_shift; - bool valid; }; /* - * hmm_range_page_shift() - return the page shift for the range - * @range: range being queried - * Return: 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 - * Return: 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) - * Return: true if the range is valid, false otherwise. - */ -static inline bool hmm_range_wait_until_valid(struct hmm_range *range, - unsigned long timeout) -{ - return wait_event_timeout(range->hmm->wq, range->valid, - msecs_to_jiffies(timeout)) != 0; -} - -/* - * hmm_range_valid() - test if a range is valid or not - * @range: range - * Return: 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 @@ -291,189 +218,24 @@ static inline uint64_t hmm_device_entry_from_pfn(const struct hmm_range *range, } /* - * 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); -} - -/* - * Mirroring: how to synchronize device page table with CPU page table. - * - * A device driver that is participating in HMM mirroring must always - * synchronize with CPU page table updates. For this, device drivers can either - * directly use mmu_notifier APIs or they can use the hmm_mirror API. Device - * drivers can decide to register one mirror per device per process, or just - * one mirror per process for a group of devices. The pattern is: - * - * int device_bind_address_space(..., struct mm_struct *mm, ...) - * { - * struct device_address_space *das; - * - * // Device driver specific initialization, and allocation of das - * // which contains an hmm_mirror struct as one of its fields. - * ... - * - * ret = hmm_mirror_register(&das->mirror, mm, &device_mirror_ops); - * if (ret) { - * // Cleanup on error - * return ret; - * } - * - * // Other device driver specific initialization - * ... - * } - * - * Once an hmm_mirror is registered for an address space, the device driver - * will get callbacks through sync_cpu_device_pagetables() operation (see - * hmm_mirror_ops struct). - * - * Device driver must not free the struct containing the hmm_mirror struct - * before calling hmm_mirror_unregister(). The expected usage is to do that when - * the device driver is unbinding from an address space. - * - * - * void device_unbind_address_space(struct device_address_space *das) - * { - * // Device driver specific cleanup - * ... - * - * hmm_mirror_unregister(&das->mirror); - * - * // Other device driver specific cleanup, and now das can be freed - * ... - * } + * Retry fault if non-blocking, drop mmap_sem and return -EAGAIN in that case. */ +#define HMM_FAULT_ALLOW_RETRY (1 << 0) -struct hmm_mirror; - -/* - * enum hmm_update_event - type of update - * @HMM_UPDATE_INVALIDATE: invalidate range (no indication as to why) - */ -enum hmm_update_event { - HMM_UPDATE_INVALIDATE, -}; - -/* - * struct hmm_update - HMM update information for callback - * - * @start: virtual start address of the range to update - * @end: virtual end address of the range to update - * @event: event triggering the update (what is happening) - * @blockable: can the callback block/sleep ? - */ -struct hmm_update { - unsigned long start; - unsigned long end; - enum hmm_update_event event; - bool blockable; -}; - -/* - * struct hmm_mirror_ops - HMM mirror device operations callback - * - * @update: callback to update range on a device - */ -struct hmm_mirror_ops { - /* release() - release hmm_mirror - * - * @mirror: pointer to struct hmm_mirror - * - * This is called when the mm_struct is being released. The callback - * must ensure that all access to any pages obtained from this mirror - * is halted before the callback returns. All future access should - * fault. - */ - void (*release)(struct hmm_mirror *mirror); - - /* sync_cpu_device_pagetables() - synchronize page tables - * - * @mirror: pointer to struct hmm_mirror - * @update: update information (see struct hmm_update) - * Return: -EAGAIN if update.blockable false and callback need to - * block, 0 otherwise. - * - * This callback ultimately originates from mmu_notifiers when the CPU - * page table is updated. The device driver must update its page table - * in response to this callback. The update argument tells what action - * to perform. - * - * The device driver must not return from this callback until the device - * page tables are completely updated (TLBs flushed, etc); this is a - * synchronous call. - */ - int (*sync_cpu_device_pagetables)(struct hmm_mirror *mirror, - const struct hmm_update *update); -}; - -/* - * struct hmm_mirror - mirror struct for a device driver - * - * @hmm: pointer to struct hmm (which is unique per mm_struct) - * @ops: device driver callback for HMM mirror operations - * @list: for list of mirrors of a given mm - * - * Each address space (mm_struct) being mirrored by a device must register one - * instance of an hmm_mirror struct with HMM. HMM will track the list of all - * mirrors for each mm_struct. - */ -struct hmm_mirror { - struct hmm *hmm; - const struct hmm_mirror_ops *ops; - struct list_head list; -}; - -int hmm_mirror_register(struct hmm_mirror *mirror, struct mm_struct *mm); -void hmm_mirror_unregister(struct hmm_mirror *mirror); +/* Don't fault in missing PTEs, just snapshot the current state. */ +#define HMM_FAULT_SNAPSHOT (1 << 1) +#ifdef CONFIG_HMM_MIRROR /* * Please see Documentation/vm/hmm.rst for how to use the range API. */ -int hmm_range_register(struct hmm_range *range, - struct hmm_mirror *mirror, - 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); +long hmm_range_fault(struct hmm_range *range, unsigned int flags); +#else +static inline long hmm_range_fault(struct hmm_range *range, unsigned int flags) +{ + return -EOPNOTSUPP; +} +#endif /* * HMM_RANGE_DEFAULT_TIMEOUT - default timeout (ms) when waiting for a range @@ -484,13 +246,4 @@ long hmm_range_dma_unmap(struct hmm_range *range, */ #define HMM_RANGE_DEFAULT_TIMEOUT 1000 -/* Below are for HMM internal use only! Not to be used by device driver! */ -static inline void hmm_mm_init(struct mm_struct *mm) -{ - mm->hmm = NULL; -} -#else /* IS_ENABLED(CONFIG_HMM_MIRROR) */ -static inline void hmm_mm_init(struct mm_struct *mm) {} -#endif /* IS_ENABLED(CONFIG_HMM_MIRROR) */ - #endif /* LINUX_HMM_H */ |