fs\dax.c –> copy_cow_page_dax()

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
static int copy_cow_page_dax(struct vm_fault *vmf, const struct iomap_iter *iter)
{
	pgoff_t pgoff = dax_iomap_pgoff(&iter->iomap, iter->pos);/* dax_iomap_pgoff -> PHYS_PFN ：获得物理页框号*/
	void *vto, *kaddr;
	long rc;
	int id;

	id = dax_read_lock();
	rc = dax_direct_access(iter->iomap.dax_dev, pgoff, 1, DAX_ACCESS,
				&kaddr, NULL);
	if (rc < 0) {
		dax_read_unlock(id);
		return rc;
	}
	vto = kmap_atomic(vmf->cow_page);
	copy_user_page(vto, kaddr, vmf->address, vmf->cow_page);
	kunmap_atomic(vto);
	dax_read_unlock(id);
	return 0;
}

include/linux/iomap.h –> struct iomap_iter

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
/**
 * struct iomap_iter - Iterate through a range of a file(遍历文件的某一范围)
 * @inode: Set at the start of the iteration and should not change.
 * @pos: The current file position we are operating on.  It is updated by
 *	calls to iomap_iter().  Treat as read-only in the body.
 * @len: The remaining length of the file segment we're operating on.
 *	It is updated at the same time as @pos.
 * @processed: The number of bytes processed by the body in the most recent
 *	iteration, or a negative errno. 0 causes the iteration to stop.
 * @flags: Zero or more of the iomap_begin flags above.
 * @iomap: Map describing the I/O iteration
 * @srcmap: Source map for COW operations
 */
struct iomap_iter {
	struct inode *inode;
	loff_t pos;
	u64 len;
	s64 processed;
	unsigned flags;
	struct iomap iomap;
	struct iomap srcmap;
	void *private;
};

/drivers/dax/super.c –> dax_direct_access()

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
/**
 * dax_direct_access() - translate a device pgoff to an absolute pfn
 * @dax_dev: a dax_device instance representing the logical memory range
 * @pgoff: offset in pages from the start of the device to translate
 			从设备开始翻译，以页为单位的偏移量
 * @nr_pages: number of consecutive pages caller can handle relative to @pfn
 * @mode: indicator on normal access or recovery write
 * @kaddr: output parameter that returns a virtual address mapping of pfn
 * @pfn: output parameter that returns an absolute pfn translation of @pgoff
 *
 * Return: negative errno if an error occurs, otherwise the number of
 * pages accessible at the device relative @pgoff.
 */
long dax_direct_access(struct dax_device *dax_dev, pgoff_t pgoff, long nr_pages,
		enum dax_access_mode mode, void **kaddr, pfn_t *pfn)
{
	long avail;

	if (!dax_dev)
		return -EOPNOTSUPP;

	if (!dax_alive(dax_dev))
		return -ENXIO;

	if (nr_pages < 0)
		return -EINVAL;

	avail = dax_dev->ops->direct_access(dax_dev, pgoff, nr_pages,
			mode, kaddr, pfn);
	if (!avail)
		return -ERANGE;
	return min(avail, nr_pages);
}
EXPORT_SYMBOL_GPL(dax_direct_access);

/include/linux/dax.h –> dax_operrations->direct_access()

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
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,
			enum dax_access_mode, void **, pfn_t *);
	/*
	 * Validate whether this device is usable as an fsdax backing
	 * device.
	 */
	bool (*dax_supported)(struct dax_device *, struct block_device *, int,
			sector_t, sector_t);
	/* zero_page_range: required operation. Zero page range   */
	int (*zero_page_range)(struct dax_device *, pgoff_t, size_t);
	/*
	 * recovery_write: recover a poisoned range by DAX device driver
	 * capable of clearing poison.
	 */
	size_t (*recovery_write)(struct dax_device *dax_dev, pgoff_t pgoff,
			void *addr, size_t bytes, struct iov_iter *iter);
};

/drivers/nvdimm/pmem.c 中 :

  • .direct_access = pmem_dax_direct_access
1
2
3
4
5
static const struct dax_operations pmem_dax_ops = {
	.direct_access = pmem_dax_direct_access,
	.zero_page_range = pmem_dax_zero_page_range,
	.recovery_write = pmem_recovery_write,
};

/drivers/nvdimm/pmem.c

1
2
3
4
5
6
7
8
static long pmem_dax_direct_access(struct dax_device *dax_dev,
		pgoff_t pgoff, long nr_pages, enum dax_access_mode mode,
		void **kaddr, pfn_t *pfn)
{
	struct pmem_device *pmem = dax_get_private(dax_dev);

	return __pmem_direct_access(pmem, pgoff, nr_pages, mode, kaddr, pfn);
}

/drivers/nvdimm/pmem.c

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
/* see "strong" declaration in tools/testing/nvdimm/pmem-dax.c */
__weak long __pmem_direct_access(struct pmem_device *pmem, pgoff_t pgoff,
		long nr_pages, enum dax_access_mode mode, void **kaddr,
		pfn_t *pfn)
{
    /* pgoff 是在设备起始地址开始的页偏移量 */ 
	resource_size_t offset = PFN_PHYS(pgoff) + pmem->data_offset;
	sector_t sector = PFN_PHYS(pgoff) >> SECTOR_SHIFT;
	unsigned int num = PFN_PHYS(nr_pages) >> SECTOR_SHIFT;
	struct badblocks *bb = &pmem->bb;
	sector_t first_bad;
	int num_bad;

	if (kaddr)
		*kaddr = pmem->virt_addr + offset; //填充 pmem 对应的虚拟地址
	if (pfn)
		*pfn = phys_to_pfn_t(pmem->phys_addr + offset, pmem->pfn_flags);

	if (bb->count &&
	    badblocks_check(bb, sector, num, &first_bad, &num_bad)) {
		long actual_nr;

		if (mode != DAX_RECOVERY_WRITE)
			return -EIO;

		/*
		 * Set the recovery stride is set to kernel page size because
		 * the underlying driver and firmware clear poison functions
		 * don't appear to handle large chunk(such as 2MiB) reliably.
		 */
		actual_nr = PHYS_PFN(
			PAGE_ALIGN((first_bad - sector) << SECTOR_SHIFT));
		dev_dbg(pmem->bb.dev, "start sector(%llu), nr_pages(%ld), first_bad(%llu), actual_nr(%ld)\n",
				sector, nr_pages, first_bad, actual_nr);
		if (actual_nr)
			return actual_nr;
		return 1;
	}

	/*
	 * If badblocks are present but not in the range, limit known good range
	 * to the requested range.
	 */
	if (bb->count)
		return nr_pages;
	return PHYS_PFN(pmem->size - pmem->pfn_pad - offset);
}

/include/linux/highmem.h –> kmap_atomic()

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
/**
 * kmap_atomic - Atomically map a page for temporary usage - Deprecated!
 * @page:	Pointer to the page to be mapped
 *
 * Returns: The virtual address of the mapping
 *
 * In fact a wrapper around kmap_local_page() which also disables pagefaults
 * and, depending on PREEMPT_RT configuration, also CPU migration and
 * preemption. Therefore users should not count on the latter two side effects.
 *
 * Mappings should always be released by kunmap_atomic().
 *
 * Do not use in new code. Use kmap_local_page() instead.
 *
 * It is used in atomic context when code wants to access the contents of a
 * page that might be allocated from high memory (see __GFP_HIGHMEM), for
 * example a page in the pagecache.  The API has two functions, and they
 * can be used in a manner similar to the following::
 *
 *   // Find the page of interest.
 *   struct page *page = find_get_page(mapping, offset);
 *
 *   // Gain access to the contents of that page.
 *   void *vaddr = kmap_atomic(page);
 *
 *   // Do something to the contents of that page.
 *   memset(vaddr, 0, PAGE_SIZE);
 *
 *   // Unmap that page.
 *   kunmap_atomic(vaddr);
 *
 * Note that the kunmap_atomic() call takes the result of the kmap_atomic()
 * call, not the argument.
 *
 * If you need to map two pages because you want to copy from one page to
 * another you need to keep the kmap_atomic calls strictly nested, like:
 *
 * vaddr1 = kmap_atomic(page1);
 * vaddr2 = kmap_atomic(page2);
 *
 * memcpy(vaddr1, vaddr2, PAGE_SIZE);
 *
 * kunmap_atomic(vaddr2);
 * kunmap_atomic(vaddr1);
 */
static inline void *kmap_atomic(struct page *page);