b29ea3c0af
commit 2bb6d2837083de722bfdc369cb0d76ce188dd9b4 upstream.
Patch series "introduce get_user_pages_longterm()", v2.
Here is a new get_user_pages api for cases where a driver intends to
keep an elevated page count indefinitely. This is distinct from usages
like iov_iter_get_pages where the elevated page counts are transient.
The iov_iter_get_pages cases immediately turn around and submit the
pages to a device driver which will put_page when the i/o operation
completes (under kernel control).
In the longterm case userspace is responsible for dropping the page
reference at some undefined point in the future. This is untenable for
filesystem-dax case where the filesystem is in control of the lifetime
of the block / page and needs reasonable limits on how long it can wait
for pages in a mapping to become idle.
Fixing filesystems to actually wait for dax pages to be idle before
blocks from a truncate/hole-punch operation are repurposed is saved for
a later patch series.
Also, allowing longterm registration of dax mappings is a future patch
series that introduces a "map with lease" semantic where the kernel can
revoke a lease and force userspace to drop its page references.
I have also tagged these for -stable to purposely break cases that might
assume that longterm memory registrations for filesystem-dax mappings
were supported by the kernel. The behavior regression this policy
change implies is one of the reasons we maintain the "dax enabled.
Warning: EXPERIMENTAL, use at your own risk" notification when mounting
a filesystem in dax mode.
It is worth noting the device-dax interface does not suffer the same
constraints since it does not support file space management operations
like hole-punch.
This patch (of 4):
Until there is a solution to the dma-to-dax vs truncate problem it is
not safe to allow long standing memory registrations against
filesytem-dax vmas. Device-dax vmas do not have this problem and are
explicitly allowed.
This is temporary until a "memory registration with layout-lease"
mechanism can be implemented for the affected sub-systems (RDMA and
V4L2).
[akpm@linux-foundation.org: use kcalloc()]
Link: http://lkml.kernel.org/r/151068939435.7446.13560129395419350737.stgit@dwillia2-desk3.amr.corp.intel.com
Fixes: 3565fce3a6 ("mm, x86: get_user_pages() for dax mappings")
Signed-off-by: Dan Williams <dan.j.williams@intel.com>
Suggested-by: Christoph Hellwig <hch@lst.de>
Cc: Doug Ledford <dledford@redhat.com>
Cc: Hal Rosenstock <hal.rosenstock@gmail.com>
Cc: Inki Dae <inki.dae@samsung.com>
Cc: Jan Kara <jack@suse.cz>
Cc: Jason Gunthorpe <jgg@mellanox.com>
Cc: Jeff Moyer <jmoyer@redhat.com>
Cc: Joonyoung Shim <jy0922.shim@samsung.com>
Cc: Kyungmin Park <kyungmin.park@samsung.com>
Cc: Mauro Carvalho Chehab <mchehab@kernel.org>
Cc: Mel Gorman <mgorman@suse.de>
Cc: Ross Zwisler <ross.zwisler@linux.intel.com>
Cc: Sean Hefty <sean.hefty@intel.com>
Cc: Seung-Woo Kim <sw0312.kim@samsung.com>
Cc: Vlastimil Babka <vbabka@suse.cz>
Cc: <stable@vger.kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
72 lines
2.4 KiB
C
72 lines
2.4 KiB
C
#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;
|
|
|
|
/* We use lowest available exceptional entry bit for locking */
|
|
#define RADIX_DAX_ENTRY_LOCK (1 << RADIX_TREE_EXCEPTIONAL_SHIFT)
|
|
|
|
ssize_t iomap_dax_rw(struct kiocb *iocb, struct iov_iter *iter,
|
|
struct iomap_ops *ops);
|
|
ssize_t dax_do_io(struct kiocb *, struct inode *, struct iov_iter *,
|
|
get_block_t, dio_iodone_t, int flags);
|
|
int dax_zero_page_range(struct inode *, loff_t from, unsigned len, get_block_t);
|
|
int dax_truncate_page(struct inode *, loff_t from, get_block_t);
|
|
int iomap_dax_fault(struct vm_area_struct *vma, struct vm_fault *vmf,
|
|
struct iomap_ops *ops);
|
|
int dax_fault(struct vm_area_struct *, struct vm_fault *, get_block_t);
|
|
int dax_delete_mapping_entry(struct address_space *mapping, pgoff_t index);
|
|
void dax_wake_mapping_entry_waiter(struct address_space *mapping,
|
|
pgoff_t index, bool wake_all);
|
|
|
|
#ifdef CONFIG_FS_DAX
|
|
struct page *read_dax_sector(struct block_device *bdev, sector_t n);
|
|
void dax_unlock_mapping_entry(struct address_space *mapping, pgoff_t index);
|
|
int __dax_zero_page_range(struct block_device *bdev, sector_t sector,
|
|
unsigned int offset, unsigned int length);
|
|
#else
|
|
static inline struct page *read_dax_sector(struct block_device *bdev,
|
|
sector_t n)
|
|
{
|
|
return ERR_PTR(-ENXIO);
|
|
}
|
|
/* Shouldn't ever be called when dax is disabled. */
|
|
static inline void dax_unlock_mapping_entry(struct address_space *mapping,
|
|
pgoff_t index)
|
|
{
|
|
BUG();
|
|
}
|
|
static inline int __dax_zero_page_range(struct block_device *bdev,
|
|
sector_t sector, unsigned int offset, unsigned int length)
|
|
{
|
|
return -ENXIO;
|
|
}
|
|
#endif
|
|
|
|
#if defined(CONFIG_TRANSPARENT_HUGEPAGE)
|
|
int dax_pmd_fault(struct vm_area_struct *, unsigned long addr, pmd_t *,
|
|
unsigned int flags, get_block_t);
|
|
#else
|
|
static inline int dax_pmd_fault(struct vm_area_struct *vma, unsigned long addr,
|
|
pmd_t *pmd, unsigned int flags, get_block_t gb)
|
|
{
|
|
return VM_FAULT_FALLBACK;
|
|
}
|
|
#endif
|
|
int dax_pfn_mkwrite(struct vm_area_struct *, struct vm_fault *);
|
|
#define dax_mkwrite(vma, vmf, gb) dax_fault(vma, vmf, gb)
|
|
|
|
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
|