OpenCloudOS-Kernel/include/linux/dax.h

168 lines
4.9 KiB
C
Raw Normal View History

#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 *);
x86, uaccess: introduce copy_from_iter_flushcache for pmem / cache-bypass operations The pmem driver has a need to transfer data with a persistent memory destination and be able to rely on the fact that the destination writes are not cached. It is sufficient for the writes to be flushed to a cpu-store-buffer (non-temporal / "movnt" in x86 terms), as we expect userspace to call fsync() to ensure data-writes have reached a power-fail-safe zone in the platform. The fsync() triggers a REQ_FUA or REQ_FLUSH to the pmem driver which will turn around and fence previous writes with an "sfence". Implement a __copy_from_user_inatomic_flushcache, memcpy_page_flushcache, and memcpy_flushcache, that guarantee that the destination buffer is not dirty in the cpu cache on completion. The new copy_from_iter_flushcache and sub-routines will be used to replace the "pmem api" (include/linux/pmem.h + arch/x86/include/asm/pmem.h). The availability of copy_from_iter_flushcache() and memcpy_flushcache() are gated by the CONFIG_ARCH_HAS_UACCESS_FLUSHCACHE config symbol, and fallback to copy_from_iter_nocache() and plain memcpy() otherwise. This is meant to satisfy the concern from Linus that if a driver wants to do something beyond the normal nocache semantics it should be something private to that driver [1], and Al's concern that anything uaccess related belongs with the rest of the uaccess code [2]. The first consumer of this interface is a new 'copy_from_iter' dax operation so that pmem can inject cache maintenance operations without imposing this overhead on other dax-capable drivers. [1]: https://lists.01.org/pipermail/linux-nvdimm/2017-January/008364.html [2]: https://lists.01.org/pipermail/linux-nvdimm/2017-April/009942.html Cc: <x86@kernel.org> Cc: Jan Kara <jack@suse.cz> Cc: Jeff Moyer <jmoyer@redhat.com> Cc: Ingo Molnar <mingo@redhat.com> Cc: Christoph Hellwig <hch@lst.de> Cc: Toshi Kani <toshi.kani@hpe.com> Cc: "H. Peter Anvin" <hpa@zytor.com> Cc: Al Viro <viro@zeniv.linux.org.uk> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Matthew Wilcox <mawilcox@microsoft.com> Reviewed-by: Ross Zwisler <ross.zwisler@linux.intel.com> Signed-off-by: Dan Williams <dan.j.williams@intel.com>
2017-05-30 03:22:50 +08:00
/* copy_from_iter: dax-driver override for default copy_from_iter */
size_t (*copy_from_iter)(struct dax_device *, pgoff_t, void *, size_t,
struct iov_iter *);
/* flush: optional driver-specific cache management after writes */
void (*flush)(struct dax_device *, pgoff_t, void *, size_t);
};
#if IS_ENABLED(CONFIG_DAX)
struct dax_device *dax_get_by_host(const char *host);
void put_dax(struct dax_device *dax_dev);
#else
static inline struct dax_device *dax_get_by_host(const char *host)
{
return NULL;
}
static inline void put_dax(struct dax_device *dax_dev)
{
}
#endif
int bdev_dax_pgoff(struct block_device *, sector_t, size_t, pgoff_t *pgoff);
#if IS_ENABLED(CONFIG_FS_DAX)
int __bdev_dax_supported(struct super_block *sb, int blocksize);
static inline int bdev_dax_supported(struct super_block *sb, int blocksize)
{
return __bdev_dax_supported(sb, 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);
}
#else
static inline int bdev_dax_supported(struct super_block *sb, int blocksize)
{
return -EOPNOTSUPP;
}
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)
{
}
#endif
int dax_read_lock(void);
void dax_read_unlock(int id);
struct dax_device *alloc_dax(void *private, const char *host,
const struct dax_operations *ops);
bool dax_alive(struct dax_device *dax_dev);
void kill_dax(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);
void dax_flush(struct dax_device *dax_dev, pgoff_t pgoff, void *addr,
size_t size);
/*
dax: add struct iomap based DAX PMD support DAX PMDs have been disabled since Jan Kara introduced DAX radix tree based locking. This patch allows DAX PMDs to participate in the DAX radix tree based locking scheme so that they can be re-enabled using the new struct iomap based fault handlers. There are currently three types of DAX 4k entries: 4k zero pages, 4k DAX mappings that have an associated block allocation, and 4k DAX empty entries. The empty entries exist to provide locking for the duration of a given page fault. This patch adds three equivalent 2MiB DAX entries: Huge Zero Page (HZP) entries, PMD DAX entries that have associated block allocations, and 2 MiB DAX empty entries. Unlike the 4k case where we insert a struct page* into the radix tree for 4k zero pages, for HZP we insert a DAX exceptional entry with the new RADIX_DAX_HZP flag set. This is because we use a single 2 MiB zero page in every 2MiB hole mapping, and it doesn't make sense to have that same struct page* with multiple entries in multiple trees. This would cause contention on the single page lock for the one Huge Zero Page, and it would break the page->index and page->mapping associations that are assumed to be valid in many other places in the kernel. One difficult use case is when one thread is trying to use 4k entries in radix tree for a given offset, and another thread is using 2 MiB entries for that same offset. The current code handles this by making the 2 MiB user fall back to 4k entries for most cases. This was done because it is the simplest solution, and because the use of 2MiB pages is already opportunistic. If we were to try to upgrade from 4k pages to 2MiB pages for a given range, we run into the problem of how we lock out 4k page faults for the entire 2MiB range while we clean out the radix tree so we can insert the 2MiB entry. We can solve this problem if we need to, but I think that the cases where both 2MiB entries and 4K entries are being used for the same range will be rare enough and the gain small enough that it probably won't be worth the complexity. Signed-off-by: Ross Zwisler <ross.zwisler@linux.intel.com> Reviewed-by: Jan Kara <jack@suse.cz> Signed-off-by: Dave Chinner <david@fromorbit.com>
2016-11-08 08:34:45 +08:00
* We use lowest available bit in exceptional entry for locking, one bit for
* the entry size (PMD) and two more to tell us if the entry is a huge zero
* page (HZP) or an empty entry that is just used for locking. In total four
* special bits.
*
* If the PMD bit isn't set the entry has size PAGE_SIZE, and if the HZP and
* EMPTY bits aren't set the entry is a normal DAX entry with a filesystem
* block allocation.
*/
dax: add struct iomap based DAX PMD support DAX PMDs have been disabled since Jan Kara introduced DAX radix tree based locking. This patch allows DAX PMDs to participate in the DAX radix tree based locking scheme so that they can be re-enabled using the new struct iomap based fault handlers. There are currently three types of DAX 4k entries: 4k zero pages, 4k DAX mappings that have an associated block allocation, and 4k DAX empty entries. The empty entries exist to provide locking for the duration of a given page fault. This patch adds three equivalent 2MiB DAX entries: Huge Zero Page (HZP) entries, PMD DAX entries that have associated block allocations, and 2 MiB DAX empty entries. Unlike the 4k case where we insert a struct page* into the radix tree for 4k zero pages, for HZP we insert a DAX exceptional entry with the new RADIX_DAX_HZP flag set. This is because we use a single 2 MiB zero page in every 2MiB hole mapping, and it doesn't make sense to have that same struct page* with multiple entries in multiple trees. This would cause contention on the single page lock for the one Huge Zero Page, and it would break the page->index and page->mapping associations that are assumed to be valid in many other places in the kernel. One difficult use case is when one thread is trying to use 4k entries in radix tree for a given offset, and another thread is using 2 MiB entries for that same offset. The current code handles this by making the 2 MiB user fall back to 4k entries for most cases. This was done because it is the simplest solution, and because the use of 2MiB pages is already opportunistic. If we were to try to upgrade from 4k pages to 2MiB pages for a given range, we run into the problem of how we lock out 4k page faults for the entire 2MiB range while we clean out the radix tree so we can insert the 2MiB entry. We can solve this problem if we need to, but I think that the cases where both 2MiB entries and 4K entries are being used for the same range will be rare enough and the gain small enough that it probably won't be worth the complexity. Signed-off-by: Ross Zwisler <ross.zwisler@linux.intel.com> Reviewed-by: Jan Kara <jack@suse.cz> Signed-off-by: Dave Chinner <david@fromorbit.com>
2016-11-08 08:34:45 +08:00
#define RADIX_DAX_SHIFT (RADIX_TREE_EXCEPTIONAL_SHIFT + 4)
#define RADIX_DAX_ENTRY_LOCK (1 << RADIX_TREE_EXCEPTIONAL_SHIFT)
dax: add struct iomap based DAX PMD support DAX PMDs have been disabled since Jan Kara introduced DAX radix tree based locking. This patch allows DAX PMDs to participate in the DAX radix tree based locking scheme so that they can be re-enabled using the new struct iomap based fault handlers. There are currently three types of DAX 4k entries: 4k zero pages, 4k DAX mappings that have an associated block allocation, and 4k DAX empty entries. The empty entries exist to provide locking for the duration of a given page fault. This patch adds three equivalent 2MiB DAX entries: Huge Zero Page (HZP) entries, PMD DAX entries that have associated block allocations, and 2 MiB DAX empty entries. Unlike the 4k case where we insert a struct page* into the radix tree for 4k zero pages, for HZP we insert a DAX exceptional entry with the new RADIX_DAX_HZP flag set. This is because we use a single 2 MiB zero page in every 2MiB hole mapping, and it doesn't make sense to have that same struct page* with multiple entries in multiple trees. This would cause contention on the single page lock for the one Huge Zero Page, and it would break the page->index and page->mapping associations that are assumed to be valid in many other places in the kernel. One difficult use case is when one thread is trying to use 4k entries in radix tree for a given offset, and another thread is using 2 MiB entries for that same offset. The current code handles this by making the 2 MiB user fall back to 4k entries for most cases. This was done because it is the simplest solution, and because the use of 2MiB pages is already opportunistic. If we were to try to upgrade from 4k pages to 2MiB pages for a given range, we run into the problem of how we lock out 4k page faults for the entire 2MiB range while we clean out the radix tree so we can insert the 2MiB entry. We can solve this problem if we need to, but I think that the cases where both 2MiB entries and 4K entries are being used for the same range will be rare enough and the gain small enough that it probably won't be worth the complexity. Signed-off-by: Ross Zwisler <ross.zwisler@linux.intel.com> Reviewed-by: Jan Kara <jack@suse.cz> Signed-off-by: Dave Chinner <david@fromorbit.com>
2016-11-08 08:34:45 +08:00
#define RADIX_DAX_PMD (1 << (RADIX_TREE_EXCEPTIONAL_SHIFT + 1))
#define RADIX_DAX_HZP (1 << (RADIX_TREE_EXCEPTIONAL_SHIFT + 2))
#define RADIX_DAX_EMPTY (1 << (RADIX_TREE_EXCEPTIONAL_SHIFT + 3))
dax: add struct iomap based DAX PMD support DAX PMDs have been disabled since Jan Kara introduced DAX radix tree based locking. This patch allows DAX PMDs to participate in the DAX radix tree based locking scheme so that they can be re-enabled using the new struct iomap based fault handlers. There are currently three types of DAX 4k entries: 4k zero pages, 4k DAX mappings that have an associated block allocation, and 4k DAX empty entries. The empty entries exist to provide locking for the duration of a given page fault. This patch adds three equivalent 2MiB DAX entries: Huge Zero Page (HZP) entries, PMD DAX entries that have associated block allocations, and 2 MiB DAX empty entries. Unlike the 4k case where we insert a struct page* into the radix tree for 4k zero pages, for HZP we insert a DAX exceptional entry with the new RADIX_DAX_HZP flag set. This is because we use a single 2 MiB zero page in every 2MiB hole mapping, and it doesn't make sense to have that same struct page* with multiple entries in multiple trees. This would cause contention on the single page lock for the one Huge Zero Page, and it would break the page->index and page->mapping associations that are assumed to be valid in many other places in the kernel. One difficult use case is when one thread is trying to use 4k entries in radix tree for a given offset, and another thread is using 2 MiB entries for that same offset. The current code handles this by making the 2 MiB user fall back to 4k entries for most cases. This was done because it is the simplest solution, and because the use of 2MiB pages is already opportunistic. If we were to try to upgrade from 4k pages to 2MiB pages for a given range, we run into the problem of how we lock out 4k page faults for the entire 2MiB range while we clean out the radix tree so we can insert the 2MiB entry. We can solve this problem if we need to, but I think that the cases where both 2MiB entries and 4K entries are being used for the same range will be rare enough and the gain small enough that it probably won't be worth the complexity. Signed-off-by: Ross Zwisler <ross.zwisler@linux.intel.com> Reviewed-by: Jan Kara <jack@suse.cz> Signed-off-by: Dave Chinner <david@fromorbit.com>
2016-11-08 08:34:45 +08:00
static inline unsigned long dax_radix_sector(void *entry)
{
return (unsigned long)entry >> RADIX_DAX_SHIFT;
}
static inline void *dax_radix_locked_entry(sector_t sector, unsigned long flags)
{
return (void *)(RADIX_TREE_EXCEPTIONAL_ENTRY | flags |
((unsigned long)sector << RADIX_DAX_SHIFT) |
RADIX_DAX_ENTRY_LOCK);
}
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,
const struct iomap_ops *ops);
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);
void dax_wake_mapping_entry_waiter(struct address_space *mapping,
pgoff_t index, void *entry, bool wake_all);
#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
dax: add struct iomap based DAX PMD support DAX PMDs have been disabled since Jan Kara introduced DAX radix tree based locking. This patch allows DAX PMDs to participate in the DAX radix tree based locking scheme so that they can be re-enabled using the new struct iomap based fault handlers. There are currently three types of DAX 4k entries: 4k zero pages, 4k DAX mappings that have an associated block allocation, and 4k DAX empty entries. The empty entries exist to provide locking for the duration of a given page fault. This patch adds three equivalent 2MiB DAX entries: Huge Zero Page (HZP) entries, PMD DAX entries that have associated block allocations, and 2 MiB DAX empty entries. Unlike the 4k case where we insert a struct page* into the radix tree for 4k zero pages, for HZP we insert a DAX exceptional entry with the new RADIX_DAX_HZP flag set. This is because we use a single 2 MiB zero page in every 2MiB hole mapping, and it doesn't make sense to have that same struct page* with multiple entries in multiple trees. This would cause contention on the single page lock for the one Huge Zero Page, and it would break the page->index and page->mapping associations that are assumed to be valid in many other places in the kernel. One difficult use case is when one thread is trying to use 4k entries in radix tree for a given offset, and another thread is using 2 MiB entries for that same offset. The current code handles this by making the 2 MiB user fall back to 4k entries for most cases. This was done because it is the simplest solution, and because the use of 2MiB pages is already opportunistic. If we were to try to upgrade from 4k pages to 2MiB pages for a given range, we run into the problem of how we lock out 4k page faults for the entire 2MiB range while we clean out the radix tree so we can insert the 2MiB entry. We can solve this problem if we need to, but I think that the cases where both 2MiB entries and 4K entries are being used for the same range will be rare enough and the gain small enough that it probably won't be worth the complexity. Signed-off-by: Ross Zwisler <ross.zwisler@linux.intel.com> Reviewed-by: Jan Kara <jack@suse.cz> Signed-off-by: Dave Chinner <david@fromorbit.com>
2016-11-08 08:34:45 +08:00
#ifdef CONFIG_FS_DAX_PMD
static inline unsigned int dax_radix_order(void *entry)
{
if ((unsigned long)entry & RADIX_DAX_PMD)
return PMD_SHIFT - PAGE_SHIFT;
return 0;
}
#else
static inline unsigned int dax_radix_order(void *entry)
{
return 0;
}
#endif
int dax_pfn_mkwrite(struct vm_fault *vmf);
static inline bool vma_is_dax(struct vm_area_struct *vma)
{
return vma->vm_file && IS_DAX(vma->vm_file->f_mapping->host);
}
dax: support dirty DAX entries in radix tree Add support for tracking dirty DAX entries in the struct address_space radix tree. This tree is already used for dirty page writeback, and it already supports the use of exceptional (non struct page*) entries. In order to properly track dirty DAX pages we will insert new exceptional entries into the radix tree that represent dirty DAX PTE or PMD pages. These exceptional entries will also contain the writeback addresses for the PTE or PMD faults that we can use at fsync/msync time. There are currently two types of exceptional entries (shmem and shadow) that can be placed into the radix tree, and this adds a third. We rely on the fact that only one type of exceptional entry can be found in a given radix tree based on its usage. This happens for free with DAX vs shmem but we explicitly prevent shadow entries from being added to radix trees for DAX mappings. The only shadow entries that would be generated for DAX radix trees would be to track zero page mappings that were created for holes. These pages would receive minimal benefit from having shadow entries, and the choice to have only one type of exceptional entry in a given radix tree makes the logic simpler both in clear_exceptional_entry() and in the rest of DAX. Signed-off-by: Ross Zwisler <ross.zwisler@linux.intel.com> Cc: "H. Peter Anvin" <hpa@zytor.com> Cc: "J. Bruce Fields" <bfields@fieldses.org> Cc: "Theodore Ts'o" <tytso@mit.edu> Cc: Alexander Viro <viro@zeniv.linux.org.uk> Cc: Andreas Dilger <adilger.kernel@dilger.ca> Cc: Dave Chinner <david@fromorbit.com> Cc: Ingo Molnar <mingo@redhat.com> Cc: Jan Kara <jack@suse.com> Cc: Jeff Layton <jlayton@poochiereds.net> Cc: Matthew Wilcox <willy@linux.intel.com> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Dan Williams <dan.j.williams@intel.com> Cc: Matthew Wilcox <matthew.r.wilcox@intel.com> Cc: Dave Hansen <dave.hansen@linux.intel.com> Cc: Hugh Dickins <hughd@google.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2016-01-23 07:10:40 +08:00
static inline bool dax_mapping(struct address_space *mapping)
{
return mapping->host && IS_DAX(mapping->host);
}
struct writeback_control;
int dax_writeback_mapping_range(struct address_space *mapping,
struct block_device *bdev, struct writeback_control *wbc);
#endif