diff options
| -rw-r--r-- | include/linux/hmm.h | 104 | ||||
| -rw-r--r-- | mm/hmm.c | 24 |
2 files changed, 19 insertions, 109 deletions
diff --git a/include/linux/hmm.h b/include/linux/hmm.h index bb6be4428633..daee6508a3f6 100644 --- a/include/linux/hmm.h +++ b/include/linux/hmm.h @@ -3,58 +3,8 @@ * Copyright 2013 Red Hat Inc. * * Authors: Jérôme Glisse <jglisse@redhat.com> - */ -/* - * Heterogeneous Memory Management (HMM) - * - * See Documentation/vm/hmm.rst for reasons and overview of what HMM is and it - * is for. Here we focus on the HMM API description, with some explanation of - * the underlying implementation. - * - * Short description: HMM provides a set of helpers to share a virtual address - * space between CPU and a device, so that the device can access any valid - * address of the process (while still obeying memory protection). HMM also - * provides helpers to migrate process memory to device memory, and back. Each - * set of functionality (address space mirroring, and migration to and from - * device memory) can be used independently of the other. - * - * - * HMM address space mirroring API: - * - * 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. * - * HMM guarantees that at any point in time, a given virtual address points to - * either the same memory in both CPU and device page tables (that is: CPU and - * device page tables each point to the same pages), or that one page table (CPU - * or device) points to no entry, while the other still points to the old page - * for the address. The latter case happens when the CPU page table update - * happens first, and then the update is mirrored over to the device page table. - * This does not cause any issue, because the CPU page table cannot start - * pointing to a new page until the device page table is invalidated. - * - * HMM uses mmu_notifiers to monitor the CPU page tables, and forwards any - * updates to each device driver that has registered a mirror. It also provides - * some API calls to help with taking a snapshot of the CPU page table, and to - * synchronize with any updates that might happen concurrently. - * - * - * HMM migration to and from device memory: - * - * HMM provides a set of helpers to hotplug device memory as ZONE_DEVICE, with - * a new MEMORY_DEVICE_PRIVATE type. This provides a struct page for each page - * of the device memory, and allows the device driver to manage its memory - * using those struct pages. Having struct pages for device memory makes - * migration easier. Because that memory is not addressable by the CPU it must - * never be pinned to the device; in other words, any CPU page fault can always - * cause the device memory to be migrated (copied/moved) back to regular memory. - * - * A new migrate helper (migrate_vma()) has been added (see mm/migrate.c) that - * allows use of a device DMA engine to perform the copy operation between - * regular system memory and device memory. + * See Documentation/vm/hmm.rst for reasons and overview of what HMM is. */ #ifndef LINUX_HMM_H #define LINUX_HMM_H @@ -120,9 +70,6 @@ enum hmm_pfn_value_e { * * @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 * @start: range virtual start address (inclusive) * @end: range virtual end address (exclusive) * @pfns: array of pfns (big enough for the range) @@ -130,8 +77,7 @@ 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 - * @pfn_shifts: pfn shift value (should be <= PAGE_SHIFT) - * @valid: pfns array did not change since it has been fill by an HMM function + * @pfn_shift: pfn shift value (should be <= PAGE_SHIFT) * @dev_private_owner: owner of device private pages */ struct hmm_range { @@ -171,52 +117,6 @@ static inline struct page *hmm_device_entry_to_page(const struct hmm_range *rang return pfn_to_page(entry >> range->pfn_shift); } -/* - * 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 - * 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) -{ - if (pfn == range->values[HMM_PFN_NONE]) - return -1UL; - if (pfn == range->values[HMM_PFN_ERROR]) - return -1UL; - if (pfn == range->values[HMM_PFN_SPECIAL]) - return -1UL; - if (!(pfn & range->flags[HMM_PFN_VALID])) - return -1UL; - return (pfn >> range->pfn_shift); -} - -/* - * 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 - * Return: valid device entry for the 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_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 - * Return: valid device entry for the 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]; -} - /* Don't fault in missing PTEs, just snapshot the current state. */ #define HMM_FAULT_SNAPSHOT (1 << 1) @@ -38,6 +38,18 @@ enum { HMM_NEED_ALL_BITS = HMM_NEED_FAULT | HMM_NEED_WRITE_FAULT, }; +/* + * 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 + * Return: valid device entry for the pfn + */ +static 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]; +} + static int hmm_pfns_fill(unsigned long addr, unsigned long end, struct hmm_range *range, enum hmm_pfn_value_e value) { @@ -544,7 +556,7 @@ static const struct mm_walk_ops hmm_walk_ops = { /** * hmm_range_fault - try to fault some address in a virtual address range - * @range: range being faulted + * @range: argument structure * @flags: HMM_FAULT_* flags * * Return: the number of valid pages in range->pfns[] (from range start @@ -558,13 +570,11 @@ static const struct mm_walk_ops hmm_walk_ops = { * only). * -EBUSY: The range has been invalidated and the caller needs to wait for * the invalidation to finish. - * -EFAULT: Invalid (i.e., either no valid vma or it is illegal to access - * that range) number of valid pages in range->pfns[] (from - * range start address). + * -EFAULT: A page was requested to be valid and could not be made valid + * ie it has no backing VMA or it is illegal to access * - * This is similar to a regular CPU page fault except that it will not trigger - * any memory migration if the memory being faulted is not accessible by CPUs - * and caller does not ask for migration. + * This is similar to get_user_pages(), except that it can read the page tables + * without mutating them (ie causing faults). * * On error, for one virtual address in the range, the function will mark the * corresponding HMM pfn entry with an error flag. |