![Linus Torvalds](/assets/img/avatar_default.png)
* 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 ...
165 lines
4.7 KiB
C
165 lines
4.7 KiB
C
/* SPDX-License-Identifier: GPL-2.0 */
|
|
#ifndef _LINUX_DAX_H
|
|
#define _LINUX_DAX_H
|
|
|
|
#include <linux/fs.h>
|
|
#include <linux/mm.h>
|
|
#include <linux/radix-tree.h>
|
|
#include <asm/pgtable.h>
|
|
|
|
struct iomap_ops;
|
|
struct dax_device;
|
|
struct dax_operations {
|
|
/*
|
|
* direct_access: translate a device-relative
|
|
* logical-page-offset into an absolute physical pfn. Return the
|
|
* number of pages available for DAX at that pfn.
|
|
*/
|
|
long (*direct_access)(struct dax_device *, pgoff_t, long,
|
|
void **, pfn_t *);
|
|
/* copy_from_iter: required operation for fs-dax direct-i/o */
|
|
size_t (*copy_from_iter)(struct dax_device *, pgoff_t, void *, size_t,
|
|
struct iov_iter *);
|
|
/* copy_to_iter: required operation for fs-dax direct-i/o */
|
|
size_t (*copy_to_iter)(struct dax_device *, pgoff_t, void *, size_t,
|
|
struct iov_iter *);
|
|
};
|
|
|
|
extern struct attribute_group dax_attribute_group;
|
|
|
|
#if IS_ENABLED(CONFIG_DAX)
|
|
struct dax_device *dax_get_by_host(const char *host);
|
|
struct dax_device *alloc_dax(void *private, const char *host,
|
|
const struct dax_operations *ops);
|
|
void put_dax(struct dax_device *dax_dev);
|
|
void kill_dax(struct dax_device *dax_dev);
|
|
void dax_write_cache(struct dax_device *dax_dev, bool wc);
|
|
bool dax_write_cache_enabled(struct dax_device *dax_dev);
|
|
#else
|
|
static inline struct dax_device *dax_get_by_host(const char *host)
|
|
{
|
|
return NULL;
|
|
}
|
|
static inline struct dax_device *alloc_dax(void *private, const char *host,
|
|
const struct dax_operations *ops)
|
|
{
|
|
/*
|
|
* Callers should check IS_ENABLED(CONFIG_DAX) to know if this
|
|
* NULL is an error or expected.
|
|
*/
|
|
return NULL;
|
|
}
|
|
static inline void put_dax(struct dax_device *dax_dev)
|
|
{
|
|
}
|
|
static inline void kill_dax(struct dax_device *dax_dev)
|
|
{
|
|
}
|
|
static inline void dax_write_cache(struct dax_device *dax_dev, bool wc)
|
|
{
|
|
}
|
|
static inline bool dax_write_cache_enabled(struct dax_device *dax_dev)
|
|
{
|
|
return false;
|
|
}
|
|
#endif
|
|
|
|
struct writeback_control;
|
|
int bdev_dax_pgoff(struct block_device *, sector_t, size_t, pgoff_t *pgoff);
|
|
#if IS_ENABLED(CONFIG_FS_DAX)
|
|
bool __bdev_dax_supported(struct block_device *bdev, int blocksize);
|
|
static inline bool bdev_dax_supported(struct block_device *bdev, int blocksize)
|
|
{
|
|
return __bdev_dax_supported(bdev, blocksize);
|
|
}
|
|
|
|
static inline struct dax_device *fs_dax_get_by_host(const char *host)
|
|
{
|
|
return dax_get_by_host(host);
|
|
}
|
|
|
|
static inline void fs_put_dax(struct dax_device *dax_dev)
|
|
{
|
|
put_dax(dax_dev);
|
|
}
|
|
|
|
struct dax_device *fs_dax_get_by_bdev(struct block_device *bdev);
|
|
int dax_writeback_mapping_range(struct address_space *mapping,
|
|
struct block_device *bdev, struct writeback_control *wbc);
|
|
|
|
struct page *dax_layout_busy_page(struct address_space *mapping);
|
|
#else
|
|
static inline bool bdev_dax_supported(struct block_device *bdev,
|
|
int blocksize)
|
|
{
|
|
return false;
|
|
}
|
|
|
|
static inline struct dax_device *fs_dax_get_by_host(const char *host)
|
|
{
|
|
return NULL;
|
|
}
|
|
|
|
static inline void fs_put_dax(struct dax_device *dax_dev)
|
|
{
|
|
}
|
|
|
|
static inline struct dax_device *fs_dax_get_by_bdev(struct block_device *bdev)
|
|
{
|
|
return NULL;
|
|
}
|
|
|
|
static inline struct page *dax_layout_busy_page(struct address_space *mapping)
|
|
{
|
|
return NULL;
|
|
}
|
|
|
|
static inline int dax_writeback_mapping_range(struct address_space *mapping,
|
|
struct block_device *bdev, struct writeback_control *wbc)
|
|
{
|
|
return -EOPNOTSUPP;
|
|
}
|
|
#endif
|
|
|
|
int dax_read_lock(void);
|
|
void dax_read_unlock(int id);
|
|
bool dax_alive(struct dax_device *dax_dev);
|
|
void *dax_get_private(struct dax_device *dax_dev);
|
|
long dax_direct_access(struct dax_device *dax_dev, pgoff_t pgoff, long nr_pages,
|
|
void **kaddr, pfn_t *pfn);
|
|
size_t dax_copy_from_iter(struct dax_device *dax_dev, pgoff_t pgoff, void *addr,
|
|
size_t bytes, struct iov_iter *i);
|
|
size_t dax_copy_to_iter(struct dax_device *dax_dev, pgoff_t pgoff, void *addr,
|
|
size_t bytes, struct iov_iter *i);
|
|
void dax_flush(struct dax_device *dax_dev, void *addr, size_t size);
|
|
|
|
ssize_t dax_iomap_rw(struct kiocb *iocb, struct iov_iter *iter,
|
|
const struct iomap_ops *ops);
|
|
int dax_iomap_fault(struct vm_fault *vmf, enum page_entry_size pe_size,
|
|
pfn_t *pfnp, int *errp, const struct iomap_ops *ops);
|
|
vm_fault_t dax_finish_sync_fault(struct vm_fault *vmf,
|
|
enum page_entry_size pe_size, pfn_t pfn);
|
|
int dax_delete_mapping_entry(struct address_space *mapping, pgoff_t index);
|
|
int dax_invalidate_mapping_entry_sync(struct address_space *mapping,
|
|
pgoff_t index);
|
|
|
|
#ifdef CONFIG_FS_DAX
|
|
int __dax_zero_page_range(struct block_device *bdev,
|
|
struct dax_device *dax_dev, sector_t sector,
|
|
unsigned int offset, unsigned int length);
|
|
#else
|
|
static inline int __dax_zero_page_range(struct block_device *bdev,
|
|
struct dax_device *dax_dev, sector_t sector,
|
|
unsigned int offset, unsigned int length)
|
|
{
|
|
return -ENXIO;
|
|
}
|
|
#endif
|
|
|
|
static inline bool dax_mapping(struct address_space *mapping)
|
|
{
|
|
return mapping->host && IS_DAX(mapping->host);
|
|
}
|
|
|
|
#endif
|