a2d581675d
Patch series "1G transparent hugepage support for device dax", v2. The following series implements support for 1G trasparent hugepage on x86 for device dax. The bulk of the code was written by Mathew Wilcox a while back supporting transparent 1G hugepage for fs DAX. I have forward ported the relevant bits to 4.10-rc. The current submission has only the necessary code to support device DAX. Comments from Dan Williams: So the motivation and intended user of this functionality mirrors the motivation and users of 1GB page support in hugetlbfs. Given expected capacities of persistent memory devices an in-memory database may want to reduce tlb pressure beyond what they can already achieve with 2MB mappings of a device-dax file. We have customer feedback to that effect as Willy mentioned in his previous version of these patches [1]. [1]: https://lkml.org/lkml/2016/1/31/52 Comments from Nilesh @ Oracle: There are applications which have a process model; and if you assume 10,000 processes attempting to mmap all the 6TB memory available on a server; we are looking at the following: processes : 10,000 memory : 6TB pte @ 4k page size: 8 bytes / 4K of memory * #processes = 6TB / 4k * 8 * 10000 = 1.5GB * 80000 = 120,000GB pmd @ 2M page size: 120,000 / 512 = ~240GB pud @ 1G page size: 240GB / 512 = ~480MB As you can see with 2M pages, this system will use up an exorbitant amount of DRAM to hold the page tables; but the 1G pages finally brings it down to a reasonable level. Memory sizes will keep increasing; so this number will keep increasing. An argument can be made to convert the applications from process model to thread model, but in the real world that may not be always practical. Hopefully this helps explain the use case where this is valuable. This patch (of 3): In preparation for adding the ability to handle PUD pages, convert vm_operations_struct.pmd_fault to vm_operations_struct.huge_fault. The vm_fault structure is extended to include a union of the different page table pointers that may be needed, and three flag bits are reserved to indicate which type of pointer is in the union. [ross.zwisler@linux.intel.com: remove unused function ext4_dax_huge_fault()] Link: http://lkml.kernel.org/r/1485813172-7284-1-git-send-email-ross.zwisler@linux.intel.com [dave.jiang@intel.com: clear PMD or PUD size flags when in fall through path] Link: http://lkml.kernel.org/r/148589842696.5820.16078080610311444794.stgit@djiang5-desk3.ch.intel.com Link: http://lkml.kernel.org/r/148545058784.17912.6353162518188733642.stgit@djiang5-desk3.ch.intel.com Signed-off-by: Matthew Wilcox <mawilcox@microsoft.com> Signed-off-by: Dave Jiang <dave.jiang@intel.com> Signed-off-by: Ross Zwisler <ross.zwisler@linux.intel.com> Cc: Dave Hansen <dave.hansen@linux.intel.com> Cc: Vlastimil Babka <vbabka@suse.cz> Cc: Jan Kara <jack@suse.com> Cc: Dan Williams <dan.j.williams@intel.com> Cc: Kirill A. Shutemov <kirill.shutemov@linux.intel.com> Cc: Nilesh Choudhury <nilesh.choudhury@oracle.com> Cc: Ingo Molnar <mingo@elte.hu> Cc: "H. Peter Anvin" <hpa@zytor.com> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Dave Jiang <dave.jiang@intel.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
95 lines
2.9 KiB
C
95 lines
2.9 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 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.
|
|
*/
|
|
#define RADIX_DAX_SHIFT (RADIX_TREE_EXCEPTIONAL_SHIFT + 4)
|
|
#define RADIX_DAX_ENTRY_LOCK (1 << RADIX_TREE_EXCEPTIONAL_SHIFT)
|
|
#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))
|
|
|
|
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, const struct iomap_ops *ops);
|
|
int dax_delete_mapping_entry(struct address_space *mapping, pgoff_t index);
|
|
int dax_invalidate_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
|
|
struct page *read_dax_sector(struct block_device *bdev, sector_t n);
|
|
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);
|
|
}
|
|
static inline int __dax_zero_page_range(struct block_device *bdev,
|
|
sector_t sector, unsigned int offset, unsigned int length)
|
|
{
|
|
return -ENXIO;
|
|
}
|
|
#endif
|
|
|
|
#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);
|
|
}
|
|
|
|
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
|