7d3bf613e9
* DAX broke a fundamental assumption of truncate of file mapped pages. The truncate path assumed that it is safe to disconnect a pinned page from a file and let the filesystem reclaim the physical block. With DAX the page is equivalent to the filesystem block. Introduce dax_layout_busy_page() to enable filesystems to wait for pinned DAX pages to be released. Without this wait a filesystem could allocate blocks under active device-DMA to a new file. * DAX arranges for the block layer to be bypassed and uses dax_direct_access() + copy_to_iter() to satisfy read(2) calls. However, the memcpy_mcsafe() facility is available through the pmem block driver. In order to safely handle media errors, via the DAX block-layer bypass, introduce copy_to_iter_mcsafe(). * Fix cache management policy relative to the ACPI NFIT Platform Capabilities Structure to properly elide cache flushes when they are not necessary. The table indicates whether CPU caches are power-fail protected. Clarify that a deep flush is always performed on REQ_{FUA,PREFLUSH} requests. -----BEGIN PGP SIGNATURE----- iQIcBAABAgAGBQJbGxI7AAoJEB7SkWpmfYgCDjsP/2Lcibu9Kf4tKIzuInsle6iE 6qP29qlkpHVTpDKbhvIxTYTYL9sMU0DNUrpPCJR/EYdeyztLWDFC5EAT1wF240vf maV37s/uP331jSC/2VJnKWzBs2ztQxmKLEIQCxh6aT0qs9cbaOvJgB/WlVu+qtsl aGJFLmb6vdQacp31noU5plKrMgMA1pADyF5qx9I9K2HwowHE7T368ZEFS/3S//c3 LXmpx/Nfq52sGu/qbRbu6B1CTJhIGhmarObyQnvBYoKntK1Ov4e8DS95wD3EhNDe FuRkOCUKhjl6cFy7QVWh1ct1bFm84ny+b4/AtbpOmv9l/+0mveJ7e+5mu8HQTifT wYiEe2xzXJ+OG/xntv8SvlZKMpjP3BqI0jYsTutsjT4oHrciiXdXM186cyS+BiGp KtFmWyncQJgfiTq6+Hj5XpP9BapNS+OYdYgUagw9ZwzdzptuGFYUMSVOBrYrn6c/ fwqtxjubykJoW0P3pkIoT91arFSea7nxOKnGwft06imQ7TwR4ARsI308feQ9itJq 2P2e7/20nYMsw2aRaUDDA70Yu+Lagn1m8WL87IybUGeUDLb1BAkjphAlWa6COJ+u PhvAD2tvyM9m0c7O5Mytvz7iWKG6SVgatoAyOPkaeplQK8khZ+wEpuK58sO6C1w8 4GBvt9ri9i/Ww/A+ppWs =4bfw -----END PGP SIGNATURE----- Merge tag 'libnvdimm-for-4.18' of git://git.kernel.org/pub/scm/linux/kernel/git/nvdimm/nvdimm Pull libnvdimm updates from Dan Williams: "This adds a user for the new 'bytes-remaining' updates to memcpy_mcsafe() that you already received through Ingo via the x86-dax- for-linus pull. Not included here, but still targeting this cycle, is support for handling memory media errors (poison) consumed via userspace dax mappings. Summary: - DAX broke a fundamental assumption of truncate of file mapped pages. The truncate path assumed that it is safe to disconnect a pinned page from a file and let the filesystem reclaim the physical block. With DAX the page is equivalent to the filesystem block. Introduce dax_layout_busy_page() to enable filesystems to wait for pinned DAX pages to be released. Without this wait a filesystem could allocate blocks under active device-DMA to a new file. - DAX arranges for the block layer to be bypassed and uses dax_direct_access() + copy_to_iter() to satisfy read(2) calls. However, the memcpy_mcsafe() facility is available through the pmem block driver. In order to safely handle media errors, via the DAX block-layer bypass, introduce copy_to_iter_mcsafe(). - Fix cache management policy relative to the ACPI NFIT Platform Capabilities Structure to properly elide cache flushes when they are not necessary. The table indicates whether CPU caches are power-fail protected. Clarify that a deep flush is always performed on REQ_{FUA,PREFLUSH} requests" * tag 'libnvdimm-for-4.18' of git://git.kernel.org/pub/scm/linux/kernel/git/nvdimm/nvdimm: (21 commits) dax: Use dax_write_cache* helpers libnvdimm, pmem: Do not flush power-fail protected CPU caches libnvdimm, pmem: Unconditionally deep flush on *sync libnvdimm, pmem: Complete REQ_FLUSH => REQ_PREFLUSH acpi, nfit: Remove ecc_unit_size dax: dax_insert_mapping_entry always succeeds libnvdimm, e820: Register all pmem resources libnvdimm: Debug probe times linvdimm, pmem: Preserve read-only setting for pmem devices x86, nfit_test: Add unit test for memcpy_mcsafe() pmem: Switch to copy_to_iter_mcsafe() dax: Report bytes remaining in dax_iomap_actor() dax: Introduce a ->copy_to_iter dax operation uio, lib: Fix CONFIG_ARCH_HAS_UACCESS_MCSAFE compilation xfs, dax: introduce xfs_break_dax_layouts() xfs: prepare xfs_break_layouts() for another layout type xfs: prepare xfs_break_layouts() to be called with XFS_MMAPLOCK_EXCL mm, fs, dax: handle layout changes to pinned dax mappings mm: fix __gup_device_huge vs unmap mm: introduce MEMORY_DEVICE_FS_DAX and CONFIG_DEV_PAGEMAP_OPS ...
167 lines
5.8 KiB
C
167 lines
5.8 KiB
C
/* SPDX-License-Identifier: GPL-2.0 */
|
|
#ifndef _LINUX_MEMREMAP_H_
|
|
#define _LINUX_MEMREMAP_H_
|
|
#include <linux/ioport.h>
|
|
#include <linux/percpu-refcount.h>
|
|
|
|
#include <asm/pgtable.h>
|
|
|
|
struct resource;
|
|
struct device;
|
|
|
|
/**
|
|
* struct vmem_altmap - pre-allocated storage for vmemmap_populate
|
|
* @base_pfn: base of the entire dev_pagemap mapping
|
|
* @reserve: pages mapped, but reserved for driver use (relative to @base)
|
|
* @free: free pages set aside in the mapping for memmap storage
|
|
* @align: pages reserved to meet allocation alignments
|
|
* @alloc: track pages consumed, private to vmemmap_populate()
|
|
*/
|
|
struct vmem_altmap {
|
|
const unsigned long base_pfn;
|
|
const unsigned long reserve;
|
|
unsigned long free;
|
|
unsigned long align;
|
|
unsigned long alloc;
|
|
};
|
|
|
|
/*
|
|
* Specialize ZONE_DEVICE memory into multiple types each having differents
|
|
* usage.
|
|
*
|
|
* 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.rst.
|
|
*
|
|
* MEMORY_DEVICE_PUBLIC:
|
|
* Device memory that is cache coherent from device and CPU point of view. This
|
|
* is use on platform that have an advance system bus (like CAPI or CCIX). A
|
|
* driver can hotplug the device memory using ZONE_DEVICE and with that memory
|
|
* type. Any page of a process can be migrated to such memory. However no one
|
|
* should be allow to pin such memory so that it can always be evicted.
|
|
*
|
|
* MEMORY_DEVICE_FS_DAX:
|
|
* Host memory that has similar access semantics as System RAM i.e. DMA
|
|
* coherent and supports page pinning. In support of coordinating page
|
|
* pinning vs other operations MEMORY_DEVICE_FS_DAX arranges for a
|
|
* wakeup event whenever a page is unpinned and becomes idle. This
|
|
* wakeup is used to coordinate physical address space management (ex:
|
|
* fs truncate/hole punch) vs pinned pages (ex: device dma).
|
|
*/
|
|
enum memory_type {
|
|
MEMORY_DEVICE_PRIVATE = 1,
|
|
MEMORY_DEVICE_PUBLIC,
|
|
MEMORY_DEVICE_FS_DAX,
|
|
};
|
|
|
|
/*
|
|
* 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.rst. 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.)
|
|
*
|
|
* For MEMORY_DEVICE_PUBLIC only the page_free() callback matter.
|
|
*/
|
|
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;
|
|
bool altmap_valid;
|
|
struct resource res;
|
|
struct percpu_ref *ref;
|
|
struct device *dev;
|
|
void *data;
|
|
enum memory_type type;
|
|
};
|
|
|
|
#ifdef CONFIG_ZONE_DEVICE
|
|
void *devm_memremap_pages(struct device *dev, struct dev_pagemap *pgmap);
|
|
struct dev_pagemap *get_dev_pagemap(unsigned long pfn,
|
|
struct dev_pagemap *pgmap);
|
|
|
|
unsigned long vmem_altmap_offset(struct vmem_altmap *altmap);
|
|
void vmem_altmap_free(struct vmem_altmap *altmap, unsigned long nr_pfns);
|
|
#else
|
|
static inline void *devm_memremap_pages(struct device *dev,
|
|
struct dev_pagemap *pgmap)
|
|
{
|
|
/*
|
|
* Fail attempts to call devm_memremap_pages() without
|
|
* ZONE_DEVICE support enabled, this requires callers to fall
|
|
* back to plain devm_memremap() based on config
|
|
*/
|
|
WARN_ON_ONCE(1);
|
|
return ERR_PTR(-ENXIO);
|
|
}
|
|
|
|
static inline struct dev_pagemap *get_dev_pagemap(unsigned long pfn,
|
|
struct dev_pagemap *pgmap)
|
|
{
|
|
return NULL;
|
|
}
|
|
|
|
static inline unsigned long vmem_altmap_offset(struct vmem_altmap *altmap)
|
|
{
|
|
return 0;
|
|
}
|
|
|
|
static inline void vmem_altmap_free(struct vmem_altmap *altmap,
|
|
unsigned long nr_pfns)
|
|
{
|
|
}
|
|
#endif /* CONFIG_ZONE_DEVICE */
|
|
|
|
static inline void put_dev_pagemap(struct dev_pagemap *pgmap)
|
|
{
|
|
if (pgmap)
|
|
percpu_ref_put(pgmap->ref);
|
|
}
|
|
#endif /* _LINUX_MEMREMAP_H_ */
|