diff --git a/fs/proc/task_mmu.c b/fs/proc/task_mmu.c index 4b21c4e51ce490830cf5553bbfb174bcd9f568eb..90ab657f8e5653ca2b284015a537e51e455afdb3 100644 --- a/fs/proc/task_mmu.c +++ b/fs/proc/task_mmu.c @@ -549,6 +549,8 @@ static void smaps_pte_entry(pte_t *pte, unsigned long addr, } } else if (is_migration_entry(swpent)) page = migration_entry_to_page(swpent); + else if (is_device_private_entry(swpent)) + page = device_private_entry_to_page(swpent); } else if (unlikely(IS_ENABLED(CONFIG_SHMEM) && mss->check_shmem_swap && pte_none(*pte))) { page = find_get_entry(vma->vm_file->f_mapping, @@ -713,6 +715,8 @@ static int smaps_hugetlb_range(pte_t *pte, unsigned long hmask, if (is_migration_entry(swpent)) page = migration_entry_to_page(swpent); + else if (is_device_private_entry(swpent)) + page = device_private_entry_to_page(swpent); } if (page) { int mapcount = page_mapcount(page); @@ -1276,6 +1280,9 @@ static pagemap_entry_t pte_to_pagemap_entry(struct pagemapread *pm, flags |= PM_SWAP; if (is_migration_entry(entry)) page = migration_entry_to_page(entry); + + if (is_device_private_entry(entry)) + page = device_private_entry_to_page(entry); } if (page && !PageAnon(page)) diff --git a/include/linux/ioport.h b/include/linux/ioport.h index 6230064d7f95d072d61e2bc0eedd341463880d32..3a4f69137bc2fa732dca27167573a9cec506dd2a 100644 --- a/include/linux/ioport.h +++ b/include/linux/ioport.h @@ -130,6 +130,7 @@ enum { IORES_DESC_ACPI_NV_STORAGE = 3, IORES_DESC_PERSISTENT_MEMORY = 4, IORES_DESC_PERSISTENT_MEMORY_LEGACY = 5, + IORES_DESC_DEVICE_PRIVATE_MEMORY = 6, }; /* helpers to define resources */ diff --git a/include/linux/memremap.h b/include/linux/memremap.h index 93416196ba64f6b4747ad9f37aaf5a913ff3ac29..8e164ec9eed0e34e8e1d6654fced5f9b64f97d5c 100644 --- a/include/linux/memremap.h +++ b/include/linux/memremap.h @@ -4,6 +4,8 @@ #include #include +#include + struct resource; struct device; @@ -35,18 +37,89 @@ static inline struct vmem_altmap *to_vmem_altmap(unsigned long memmap_start) } #endif +/* + * Specialize ZONE_DEVICE memory into multiple types each having differents + * usage. + * + * MEMORY_DEVICE_HOST: + * Persistent device memory (pmem): struct page might be allocated in different + * memory and architecture might want to perform special actions. It is similar + * to regular memory, in that the CPU can access it transparently. However, + * it is likely to have different bandwidth and latency than regular memory. + * See Documentation/nvdimm/nvdimm.txt for more information. + * + * MEMORY_DEVICE_PRIVATE: + * Device memory that is not directly addressable by the CPU: CPU can neither + * read nor write private memory. In this case, we do still have struct pages + * backing the device memory. Doing so simplifies the implementation, but it is + * important to remember that there are certain points at which the struct page + * must be treated as an opaque object, rather than a "normal" struct page. + * + * A more complete discussion of unaddressable memory may be found in + * include/linux/hmm.h and Documentation/vm/hmm.txt. + */ +enum memory_type { + MEMORY_DEVICE_HOST = 0, + MEMORY_DEVICE_PRIVATE, +}; + +/* + * For MEMORY_DEVICE_PRIVATE we use ZONE_DEVICE and extend it with two + * callbacks: + * page_fault() + * page_free() + * + * Additional notes about MEMORY_DEVICE_PRIVATE may be found in + * include/linux/hmm.h and Documentation/vm/hmm.txt. There is also a brief + * explanation in include/linux/memory_hotplug.h. + * + * The page_fault() callback must migrate page back, from device memory to + * system memory, so that the CPU can access it. This might fail for various + * reasons (device issues, device have been unplugged, ...). When such error + * conditions happen, the page_fault() callback must return VM_FAULT_SIGBUS and + * set the CPU page table entry to "poisoned". + * + * Note that because memory cgroup charges are transferred to the device memory, + * this should never fail due to memory restrictions. However, allocation + * of a regular system page might still fail because we are out of memory. If + * that happens, the page_fault() callback must return VM_FAULT_OOM. + * + * The page_fault() callback can also try to migrate back multiple pages in one + * chunk, as an optimization. It must, however, prioritize the faulting address + * over all the others. + * + * + * The page_free() callback is called once the page refcount reaches 1 + * (ZONE_DEVICE pages never reach 0 refcount unless there is a refcount bug. + * This allows the device driver to implement its own memory management.) + */ +typedef int (*dev_page_fault_t)(struct vm_area_struct *vma, + unsigned long addr, + const struct page *page, + unsigned int flags, + pmd_t *pmdp); +typedef void (*dev_page_free_t)(struct page *page, void *data); + /** * struct dev_pagemap - metadata for ZONE_DEVICE mappings + * @page_fault: callback when CPU fault on an unaddressable device page + * @page_free: free page callback when page refcount reaches 1 * @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 + * @data: private data pointer for page_free() + * @type: memory type: see MEMORY_* in memory_hotplug.h */ struct dev_pagemap { + dev_page_fault_t page_fault; + dev_page_free_t page_free; struct vmem_altmap *altmap; const struct resource *res; struct percpu_ref *ref; struct device *dev; + void *data; + enum memory_type type; }; #ifdef CONFIG_ZONE_DEVICE diff --git a/include/linux/mm.h b/include/linux/mm.h index 39db8e54c5d50a98ee9cf49eb5cf16e5271095a4..a74c4e95435223e835510d80764ff33e52b06dfd 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -792,11 +792,23 @@ static inline bool is_zone_device_page(const struct page *page) { return page_zonenum(page) == ZONE_DEVICE; } + +static inline bool is_device_private_page(const struct page *page) +{ + /* See MEMORY_DEVICE_PRIVATE in include/linux/memory_hotplug.h */ + return ((page_zonenum(page) == ZONE_DEVICE) && + (page->pgmap->type == MEMORY_DEVICE_PRIVATE)); +} #else static inline bool is_zone_device_page(const struct page *page) { return false; } + +static inline bool is_device_private_page(const struct page *page) +{ + return false; +} #endif static inline void get_page(struct page *page) diff --git a/include/linux/swap.h b/include/linux/swap.h index 8bf3487fb2046b1a03e4d28fca762c35281cc219..8a807292037f9ff956980260ba61c0c4c22dd07f 100644 --- a/include/linux/swap.h +++ b/include/linux/swap.h @@ -50,6 +50,23 @@ static inline int current_is_kswapd(void) * actions on faults. */ +/* + * Unaddressable device memory support. See include/linux/hmm.h and + * Documentation/vm/hmm.txt. Short description is we need struct pages for + * device memory that is unaddressable (inaccessible) by CPU, so that we can + * migrate part of a process memory to device memory. + * + * When a page is migrated from CPU to device, we set the CPU page table entry + * to a special SWP_DEVICE_* entry. + */ +#ifdef CONFIG_DEVICE_PRIVATE +#define SWP_DEVICE_NUM 2 +#define SWP_DEVICE_WRITE (MAX_SWAPFILES+SWP_HWPOISON_NUM+SWP_MIGRATION_NUM) +#define SWP_DEVICE_READ (MAX_SWAPFILES+SWP_HWPOISON_NUM+SWP_MIGRATION_NUM+1) +#else +#define SWP_DEVICE_NUM 0 +#endif + /* * NUMA node memory migration support */ @@ -72,7 +89,8 @@ static inline int current_is_kswapd(void) #endif #define MAX_SWAPFILES \ - ((1 << MAX_SWAPFILES_SHIFT) - SWP_MIGRATION_NUM - SWP_HWPOISON_NUM) + ((1 << MAX_SWAPFILES_SHIFT) - SWP_DEVICE_NUM - \ + SWP_MIGRATION_NUM - SWP_HWPOISON_NUM) /* * Magic header for a swap area. The first part of the union is @@ -469,8 +487,8 @@ static inline void show_swap_cache_info(void) { } -#define free_swap_and_cache(swp) is_migration_entry(swp) -#define swapcache_prepare(swp) is_migration_entry(swp) +#define free_swap_and_cache(e) ({(is_migration_entry(e) || is_device_private_entry(e));}) +#define swapcache_prepare(e) ({(is_migration_entry(e) || is_device_private_entry(e));}) static inline int add_swap_count_continuation(swp_entry_t swp, gfp_t gfp_mask) { diff --git a/include/linux/swapops.h b/include/linux/swapops.h index 45b092aa6419959c37ce0f7d57d64ba751a43c01..291c4b53465819293aaa9c25bbed1b932f449f1f 100644 --- a/include/linux/swapops.h +++ b/include/linux/swapops.h @@ -100,6 +100,74 @@ static inline void *swp_to_radix_entry(swp_entry_t entry) return (void *)(value | RADIX_TREE_EXCEPTIONAL_ENTRY); } +#if IS_ENABLED(CONFIG_DEVICE_PRIVATE) +static inline swp_entry_t make_device_private_entry(struct page *page, bool write) +{ + return swp_entry(write ? SWP_DEVICE_WRITE : SWP_DEVICE_READ, + page_to_pfn(page)); +} + +static inline bool is_device_private_entry(swp_entry_t entry) +{ + int type = swp_type(entry); + return type == SWP_DEVICE_READ || type == SWP_DEVICE_WRITE; +} + +static inline void make_device_private_entry_read(swp_entry_t *entry) +{ + *entry = swp_entry(SWP_DEVICE_READ, swp_offset(*entry)); +} + +static inline bool is_write_device_private_entry(swp_entry_t entry) +{ + return unlikely(swp_type(entry) == SWP_DEVICE_WRITE); +} + +static inline struct page *device_private_entry_to_page(swp_entry_t entry) +{ + return pfn_to_page(swp_offset(entry)); +} + +int device_private_entry_fault(struct vm_area_struct *vma, + unsigned long addr, + swp_entry_t entry, + unsigned int flags, + pmd_t *pmdp); +#else /* CONFIG_DEVICE_PRIVATE */ +static inline swp_entry_t make_device_private_entry(struct page *page, bool write) +{ + return swp_entry(0, 0); +} + +static inline void make_device_private_entry_read(swp_entry_t *entry) +{ +} + +static inline bool is_device_private_entry(swp_entry_t entry) +{ + return false; +} + +static inline bool is_write_device_private_entry(swp_entry_t entry) +{ + return false; +} + +static inline struct page *device_private_entry_to_page(swp_entry_t entry) +{ + return NULL; +} + +static inline int device_private_entry_fault(struct vm_area_struct *vma, + unsigned long addr, + swp_entry_t entry, + unsigned int flags, + pmd_t *pmdp) +{ + return VM_FAULT_SIGBUS; +} +#endif /* CONFIG_DEVICE_PRIVATE */ + #ifdef CONFIG_MIGRATION static inline swp_entry_t make_migration_entry(struct page *page, int write) { diff --git a/kernel/memremap.c b/kernel/memremap.c index 066e73c2fcc9dbbd89c13923e203ed47aaff7d58..f1d1e0dfe8b4f693db64668c46873a56ab8995d7 100644 --- a/kernel/memremap.c +++ b/kernel/memremap.c @@ -18,6 +18,8 @@ #include #include #include +#include +#include #ifndef ioremap_cache /* temporary while we convert existing ioremap_cache users to memremap */ @@ -219,6 +221,34 @@ static unsigned long order_at(struct resource *res, unsigned long pgoff) for (pgoff = 0, order = order_at((res), pgoff); order < ULONG_MAX; \ pgoff += 1UL << order, order = order_at((res), pgoff)) +#if IS_ENABLED(CONFIG_DEVICE_PRIVATE) +int device_private_entry_fault(struct vm_area_struct *vma, + unsigned long addr, + swp_entry_t entry, + unsigned int flags, + pmd_t *pmdp) +{ + struct page *page = device_private_entry_to_page(entry); + + /* + * The page_fault() callback must migrate page back to system memory + * so that CPU can access it. This might fail for various reasons + * (device issue, device was unsafely unplugged, ...). When such + * error conditions happen, the callback must return VM_FAULT_SIGBUS. + * + * Note that because memory cgroup charges are accounted to the device + * memory, this should never fail because of memory restrictions (but + * allocation of regular system page might still fail because we are + * out of memory). + * + * There is a more in-depth description of what that callback can and + * cannot do, in include/linux/memremap.h + */ + return page->pgmap->page_fault(vma, addr, page, flags, pmdp); +} +EXPORT_SYMBOL(device_private_entry_fault); +#endif /* CONFIG_DEVICE_PRIVATE */ + static void pgmap_radix_release(struct resource *res) { unsigned long pgoff, order; @@ -356,6 +386,10 @@ void *devm_memremap_pages(struct device *dev, struct resource *res, } pgmap->ref = ref; pgmap->res = &page_map->res; + pgmap->type = MEMORY_DEVICE_HOST; + pgmap->page_fault = NULL; + pgmap->page_free = NULL; + pgmap->data = NULL; mutex_lock(&pgmap_lock); error = 0; diff --git a/mm/Kconfig b/mm/Kconfig index 254db99f263dc929f6edc3848258a35794854934..ec27855db1339da1f24c616ee1d6750d0bc33d1e 100644 --- a/mm/Kconfig +++ b/mm/Kconfig @@ -676,7 +676,7 @@ config ARCH_HAS_ZONE_DEVICE bool config ZONE_DEVICE - bool "Device memory (pmem, etc...) hotplug support" + bool "Device memory (pmem, HMM, etc...) hotplug support" depends on MEMORY_HOTPLUG depends on MEMORY_HOTREMOVE depends on SPARSEMEM_VMEMMAP @@ -717,6 +717,15 @@ config HMM_MIRROR page tables (at PAGE_SIZE granularity), and must be able to recover from the resulting potential page faults. +config DEVICE_PRIVATE + bool "Unaddressable device memory (GPU memory, ...)" + depends on ARCH_HAS_HMM + + help + Allows creation of struct pages to represent unaddressable device + memory; i.e., memory that is only accessible from the device (or + group of devices). You likely also want to select HMM_MIRROR. + config FRAME_VECTOR bool diff --git a/mm/memory.c b/mm/memory.c index 886033b95fd2754f8d34a8e12c627bfd88d9839c..079eeac0b009790ac6c707eb65f05562f9ddcb86 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -49,6 +49,7 @@ #include #include #include +#include #include #include #include @@ -956,6 +957,35 @@ copy_one_pte(struct mm_struct *dst_mm, struct mm_struct *src_mm, pte = pte_swp_mksoft_dirty(pte); set_pte_at(src_mm, addr, src_pte, pte); } + } else if (is_device_private_entry(entry)) { + page = device_private_entry_to_page(entry); + + /* + * Update rss count even for unaddressable pages, as + * they should treated just like normal pages in this + * respect. + * + * We will likely want to have some new rss counters + * for unaddressable pages, at some point. But for now + * keep things as they are. + */ + get_page(page); + rss[mm_counter(page)]++; + page_dup_rmap(page, false); + + /* + * We do not preserve soft-dirty information, because so + * far, checkpoint/restore is the only feature that + * requires that. And checkpoint/restore does not work + * when a device driver is involved (you cannot easily + * save and restore device driver state). + */ + if (is_write_device_private_entry(entry) && + is_cow_mapping(vm_flags)) { + make_device_private_entry_read(&entry); + pte = swp_entry_to_pte(entry); + set_pte_at(src_mm, addr, src_pte, pte); + } } goto out_set_pte; } @@ -1274,6 +1304,29 @@ static unsigned long zap_pte_range(struct mmu_gather *tlb, } continue; } + + entry = pte_to_swp_entry(ptent); + if (non_swap_entry(entry) && is_device_private_entry(entry)) { + struct page *page = device_private_entry_to_page(entry); + + if (unlikely(details && details->check_mapping)) { + /* + * unmap_shared_mapping_pages() wants to + * invalidate cache without truncating: + * unmap shared but keep private pages. + */ + if (details->check_mapping != + page_rmapping(page)) + continue; + } + + pte_clear_not_present_full(mm, addr, pte, tlb->fullmm); + rss[mm_counter(page)]--; + page_remove_rmap(page, false); + put_page(page); + continue; + } + /* If details->check_mapping, we leave swap entries. */ if (unlikely(details)) continue; @@ -2776,6 +2829,14 @@ int do_swap_page(struct vm_fault *vmf) if (is_migration_entry(entry)) { migration_entry_wait(vma->vm_mm, vmf->pmd, vmf->address); + } else if (is_device_private_entry(entry)) { + /* + * For un-addressable device memory we call the pgmap + * fault handler callback. The callback must migrate + * the page back to some CPU accessible page. + */ + ret = device_private_entry_fault(vma, vmf->address, entry, + vmf->flags, vmf->pmd); } else if (is_hwpoison_entry(entry)) { ret = VM_FAULT_HWPOISON; } else { diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c index 1f92fb84770d27d9adf4b3516db7f01f7fdf9c0a..e882cb6da99425bad30e4017c5feeadacba2e8ce 100644 --- a/mm/memory_hotplug.c +++ b/mm/memory_hotplug.c @@ -99,7 +99,7 @@ void mem_hotplug_done(void) /* add this memory to iomem resource */ static struct resource *register_memory_resource(u64 start, u64 size) { - struct resource *res; + struct resource *res, *conflict; res = kzalloc(sizeof(struct resource), GFP_KERNEL); if (!res) return ERR_PTR(-ENOMEM); @@ -108,7 +108,13 @@ static struct resource *register_memory_resource(u64 start, u64 size) res->start = start; res->end = start + size - 1; res->flags = IORESOURCE_SYSTEM_RAM | IORESOURCE_BUSY; - if (request_resource(&iomem_resource, res) < 0) { + conflict = request_resource_conflict(&iomem_resource, res); + if (conflict) { + if (conflict->desc == IORES_DESC_DEVICE_PRIVATE_MEMORY) { + pr_debug("Device unaddressable memory block " + "memory hotplug at %#010llx !\n", + (unsigned long long)start); + } pr_debug("System RAM resource %pR cannot be added\n", res); kfree(res); return ERR_PTR(-EEXIST); diff --git a/mm/mprotect.c b/mm/mprotect.c index a1bfe954577064149468e06e74191a1eeeeae6d0..6d3e2f0822901605aa3554234e3e96838997b0ba 100644 --- a/mm/mprotect.c +++ b/mm/mprotect.c @@ -125,6 +125,20 @@ static unsigned long change_pte_range(struct vm_area_struct *vma, pmd_t *pmd, pages++; } + + if (is_write_device_private_entry(entry)) { + pte_t newpte; + + /* + * We do not preserve soft-dirtiness. See + * copy_one_pte() for explanation. + */ + make_device_private_entry_read(&entry); + newpte = swp_entry_to_pte(entry); + set_pte_at(mm, addr, pte, newpte); + + pages++; + } } } while (pte++, addr += PAGE_SIZE, addr != end); arch_leave_lazy_mmu_mode();