diff options
Diffstat (limited to 'include/linux/hmm.h')
-rw-r--r-- | include/linux/hmm.h | 104 |
1 files changed, 35 insertions, 69 deletions
diff --git a/include/linux/hmm.h b/include/linux/hmm.h index b697496e85ba..b8a08b2a10ca 100644 --- a/include/linux/hmm.h +++ b/include/linux/hmm.h @@ -21,8 +21,8 @@ * * HMM address space mirroring API: * - * Use HMM address space mirroring if you want to mirror range of the CPU page - * table of a process into a device page table. Here, "mirror" means "keep + * Use HMM address space mirroring if you want to mirror a range of the CPU + * page tables of a process into a device page table. Here, "mirror" means "keep * synchronized". Prerequisites: the device must provide the ability to write- * protect its page tables (at PAGE_SIZE granularity), and must be able to * recover from the resulting potential page faults. @@ -82,19 +82,18 @@ * @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; + 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; - bool dead; }; /* @@ -105,10 +104,11 @@ struct hmm { * HMM_PFN_WRITE: CPU page table has write permission set * HMM_PFN_DEVICE_PRIVATE: private device memory (ZONE_DEVICE) * - * The driver provide a flags array, if driver valid bit for an entry is bit - * 3 ie (entry & (1 << 3)) is true if entry is valid then driver must provide + * The driver provides a flags array for mapping page protections to device + * PTE bits. If the driver valid bit for an entry is bit 3, + * i.e., (entry & (1 << 3)), then the driver must provide * an array in hmm_range.flags with hmm_range.flags[HMM_PFN_VALID] == 1 << 3. - * Same logic apply to all flags. This is same idea as vm_page_prot in vma + * Same logic apply to all flags. This is the same idea as vm_page_prot in vma * except that this is per device driver rather than per architecture. */ enum hmm_pfn_flag_e { @@ -129,13 +129,13 @@ enum hmm_pfn_flag_e { * be mirrored by a device, because the entry will never have HMM_PFN_VALID * set and the pfn value is undefined. * - * Driver provide entry value for none entry, error entry and special entry, - * driver can alias (ie use same value for error and special for instance). It - * should not alias none and error or special. + * Driver provides values for none entry, error entry, and special entry. + * Driver can alias (i.e., use same value) error and special, but + * it should not alias none with error or special. * * HMM pfn value returned by hmm_vma_get_pfns() or hmm_vma_fault() will be: * hmm_range.values[HMM_PFN_ERROR] if CPU page table entry is poisonous, - * hmm_range.values[HMM_PFN_NONE] if there is no CPU page table + * hmm_range.values[HMM_PFN_NONE] if there is no CPU page table entry, * hmm_range.values[HMM_PFN_SPECIAL] if CPU page table entry is a special one */ enum hmm_pfn_value_e { @@ -158,6 +158,7 @@ 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 */ @@ -180,7 +181,7 @@ struct hmm_range { /* * 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 + * Return: page shift (page size = 1 << page shift) for the range */ static inline unsigned hmm_range_page_shift(const struct hmm_range *range) { @@ -190,7 +191,7 @@ static inline unsigned hmm_range_page_shift(const struct hmm_range *range) /* * hmm_range_page_size() - return the page size for the range * @range: range being queried - * Returns: page size for the range in bytes + * Return: page size for the range in bytes */ static inline unsigned long hmm_range_page_size(const struct hmm_range *range) { @@ -201,28 +202,19 @@ static inline unsigned long hmm_range_page_size(const struct hmm_range *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. + * Return: 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; + 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 - * Returns: true if the range is valid, false otherwise. + * Return: true if the range is valid, false otherwise. */ static inline bool hmm_range_valid(struct hmm_range *range) { @@ -233,7 +225,7 @@ static inline bool hmm_range_valid(struct hmm_range *range) * 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 + * Return: struct page pointer if entry is a valid, NULL otherwise * * If the device entry is valid (ie valid flag set) then return the struct page * matching the entry value. Otherwise return NULL. @@ -256,7 +248,7 @@ static inline struct page *hmm_device_entry_to_page(const struct hmm_range *rang * 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 + * Return: pfn value if device entry is valid, -1UL otherwise */ static inline unsigned long hmm_device_entry_to_pfn(const struct hmm_range *range, uint64_t pfn) @@ -276,7 +268,7 @@ hmm_device_entry_to_pfn(const struct hmm_range *range, uint64_t pfn) * hmm_device_entry_from_page() - create a valid device entry for a page * @range: range use to encode HMM pfn value * @page: page for which to create the device entry - * Returns: valid device entry for the page + * Return: valid device entry for the page */ static inline uint64_t hmm_device_entry_from_page(const struct hmm_range *range, struct page *page) @@ -289,7 +281,7 @@ static inline uint64_t hmm_device_entry_from_page(const struct hmm_range *range, * 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 device entry - * Returns: valid device entry for the pfn + * Return: valid device entry for the pfn */ static inline uint64_t hmm_device_entry_from_pfn(const struct hmm_range *range, unsigned long pfn) @@ -391,7 +383,7 @@ enum hmm_update_event { }; /* - * struct hmm_update - HMM update informations for callback + * 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 @@ -415,17 +407,18 @@ struct hmm_mirror_ops { * * @mirror: pointer to struct hmm_mirror * - * This is called when the mm_struct is being released. - * The callback should make sure no references to the mirror occur - * after the callback returns. + * 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 informations (see struct hmm_update) - * Returns: -EAGAIN if update.blockable false and callback need to + * @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 @@ -462,35 +455,10 @@ int hmm_mirror_register(struct hmm_mirror *mirror, struct mm_struct *mm); void hmm_mirror_unregister(struct hmm_mirror *mirror); /* - * 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. - */ -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; -} - - -/* * 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, + struct hmm_mirror *mirror, unsigned long start, unsigned long end, unsigned page_shift); @@ -526,7 +494,8 @@ static inline bool hmm_vma_range_done(struct hmm_range *range) } /* This is a temporary helper to avoid merge conflict between trees. */ -static inline int hmm_vma_fault(struct hmm_range *range, bool block) +static inline int hmm_vma_fault(struct hmm_mirror *mirror, + struct hmm_range *range, bool block) { long ret; @@ -539,7 +508,7 @@ static inline int hmm_vma_fault(struct hmm_range *range, bool block) range->default_flags = 0; range->pfn_flags_mask = -1UL; - ret = hmm_range_register(range, range->vma->vm_mm, + ret = hmm_range_register(range, mirror, range->start, range->end, PAGE_SHIFT); if (ret) @@ -558,7 +527,7 @@ static inline int hmm_vma_fault(struct hmm_range *range, bool block) ret = hmm_range_fault(range, block); if (ret <= 0) { if (ret == -EBUSY || !ret) { - /* Same as above drop mmap_sem to match old API. */ + /* Same as above, drop mmap_sem to match old API. */ up_read(&range->vma->vm_mm->mmap_sem); ret = -EBUSY; } else if (ret == -EAGAIN) @@ -570,14 +539,11 @@ static inline int hmm_vma_fault(struct hmm_range *range, bool block) } /* Below are for HMM internal use only! Not to be used by device driver! */ -void hmm_mm_destroy(struct mm_struct *mm); - static inline void hmm_mm_init(struct mm_struct *mm) { mm->hmm = NULL; } #else /* IS_ENABLED(CONFIG_HMM_MIRROR) */ -static inline void hmm_mm_destroy(struct mm_struct *mm) {} static inline void hmm_mm_init(struct mm_struct *mm) {} #endif /* IS_ENABLED(CONFIG_HMM_MIRROR) */ |