Commit dd22f551 authored by Matthew Wilcox's avatar Matthew Wilcox Committed by Jens Axboe

block: Change direct_access calling convention

In order to support accesses to larger chunks of memory, pass in a
'size' parameter (counted in bytes), and return the amount available at
that address.

Add a new helper function, bdev_direct_access(), to handle common
functionality including partition handling, checking the length requested
is positive, checking for the sector being page-aligned, and checking
the length of the request does not pass the end of the partition.
Signed-off-by: default avatarMatthew Wilcox <matthew.r.wilcox@intel.com>
Reviewed-by: default avatarJan Kara <jack@suse.cz>
Reviewed-by: default avatarBoaz Harrosh <boaz@plexistor.com>
Signed-off-by: default avatarJens Axboe <axboe@fb.com>
parent c761d96b
...@@ -28,12 +28,15 @@ Implementation ...@@ -28,12 +28,15 @@ Implementation
Execute-in-place is implemented in three steps: block device operation, Execute-in-place is implemented in three steps: block device operation,
address space operation, and file operations. address space operation, and file operations.
A block device operation named direct_access is used to retrieve a A block device operation named direct_access is used to translate the
reference (pointer) to a block on-disk. The reference is supposed to be block device sector number to a page frame number (pfn) that identifies
cpu-addressable, physical address and remain valid until the release operation the physical page for the memory. It also returns a kernel virtual
is performed. A struct block_device reference is used to address the device, address that can be used to access the memory.
and a sector_t argument is used to identify the individual block. As an
alternative, memory technology devices can be used for this. The direct_access method takes a 'size' parameter that indicates the
number of bytes being requested. The function should return the number
of bytes that can be contiguously accessed at that offset. It may also
return a negative errno if an error occurs.
The block device operation is optional, these block devices support it as of The block device operation is optional, these block devices support it as of
today: today:
......
...@@ -139,26 +139,17 @@ axon_ram_make_request(struct request_queue *queue, struct bio *bio) ...@@ -139,26 +139,17 @@ axon_ram_make_request(struct request_queue *queue, struct bio *bio)
* axon_ram_direct_access - direct_access() method for block device * axon_ram_direct_access - direct_access() method for block device
* @device, @sector, @data: see block_device_operations method * @device, @sector, @data: see block_device_operations method
*/ */
static int static long
axon_ram_direct_access(struct block_device *device, sector_t sector, axon_ram_direct_access(struct block_device *device, sector_t sector,
void **kaddr, unsigned long *pfn) void **kaddr, unsigned long *pfn, long size)
{ {
struct axon_ram_bank *bank = device->bd_disk->private_data; struct axon_ram_bank *bank = device->bd_disk->private_data;
loff_t offset; loff_t offset = (loff_t)sector << AXON_RAM_SECTOR_SHIFT;
offset = sector;
if (device->bd_part != NULL)
offset += device->bd_part->start_sect;
offset <<= AXON_RAM_SECTOR_SHIFT;
if (offset >= bank->size) {
dev_err(&bank->device->dev, "Access outside of address space\n");
return -ERANGE;
}
*kaddr = (void *)(bank->ph_addr + offset); *kaddr = (void *)(bank->ph_addr + offset);
*pfn = virt_to_phys(kaddr) >> PAGE_SHIFT; *pfn = virt_to_phys(kaddr) >> PAGE_SHIFT;
return 0; return bank->size - offset;
} }
static const struct block_device_operations axon_ram_devops = { static const struct block_device_operations axon_ram_devops = {
......
...@@ -370,25 +370,25 @@ static int brd_rw_page(struct block_device *bdev, sector_t sector, ...@@ -370,25 +370,25 @@ static int brd_rw_page(struct block_device *bdev, sector_t sector,
} }
#ifdef CONFIG_BLK_DEV_XIP #ifdef CONFIG_BLK_DEV_XIP
static int brd_direct_access(struct block_device *bdev, sector_t sector, static long brd_direct_access(struct block_device *bdev, sector_t sector,
void **kaddr, unsigned long *pfn) void **kaddr, unsigned long *pfn, long size)
{ {
struct brd_device *brd = bdev->bd_disk->private_data; struct brd_device *brd = bdev->bd_disk->private_data;
struct page *page; struct page *page;
if (!brd) if (!brd)
return -ENODEV; return -ENODEV;
if (sector & (PAGE_SECTORS-1))
return -EINVAL;
if (sector + PAGE_SECTORS > get_capacity(bdev->bd_disk))
return -ERANGE;
page = brd_insert_page(brd, sector); page = brd_insert_page(brd, sector);
if (!page) if (!page)
return -ENOSPC; return -ENOSPC;
*kaddr = page_address(page); *kaddr = page_address(page);
*pfn = page_to_pfn(page); *pfn = page_to_pfn(page);
return 0; /*
* TODO: If size > PAGE_SIZE, we could look to see if the next page in
* the file happens to be mapped to the next page of physical RAM.
*/
return PAGE_SIZE;
} }
#endif #endif
......
...@@ -28,8 +28,8 @@ ...@@ -28,8 +28,8 @@
static int dcssblk_open(struct block_device *bdev, fmode_t mode); static int dcssblk_open(struct block_device *bdev, fmode_t mode);
static void dcssblk_release(struct gendisk *disk, fmode_t mode); static void dcssblk_release(struct gendisk *disk, fmode_t mode);
static void dcssblk_make_request(struct request_queue *q, struct bio *bio); static void dcssblk_make_request(struct request_queue *q, struct bio *bio);
static int dcssblk_direct_access(struct block_device *bdev, sector_t secnum, static long dcssblk_direct_access(struct block_device *bdev, sector_t secnum,
void **kaddr, unsigned long *pfn); void **kaddr, unsigned long *pfn, long size);
static char dcssblk_segments[DCSSBLK_PARM_LEN] = "\0"; static char dcssblk_segments[DCSSBLK_PARM_LEN] = "\0";
...@@ -866,25 +866,22 @@ dcssblk_make_request(struct request_queue *q, struct bio *bio) ...@@ -866,25 +866,22 @@ dcssblk_make_request(struct request_queue *q, struct bio *bio)
bio_io_error(bio); bio_io_error(bio);
} }
static int static long
dcssblk_direct_access (struct block_device *bdev, sector_t secnum, dcssblk_direct_access (struct block_device *bdev, sector_t secnum,
void **kaddr, unsigned long *pfn) void **kaddr, unsigned long *pfn, long size)
{ {
struct dcssblk_dev_info *dev_info; struct dcssblk_dev_info *dev_info;
unsigned long pgoff; unsigned long offset, dev_sz;
dev_info = bdev->bd_disk->private_data; dev_info = bdev->bd_disk->private_data;
if (!dev_info) if (!dev_info)
return -ENODEV; return -ENODEV;
if (secnum % (PAGE_SIZE/512)) dev_sz = dev_info->end - dev_info->start;
return -EINVAL; offset = secnum * 512;
pgoff = secnum / (PAGE_SIZE / 512); *kaddr = (void *) (dev_info->start + offset);
if ((pgoff+1)*PAGE_SIZE-1 > dev_info->end - dev_info->start)
return -ERANGE;
*kaddr = (void *) (dev_info->start+pgoff*PAGE_SIZE);
*pfn = virt_to_phys(*kaddr) >> PAGE_SHIFT; *pfn = virt_to_phys(*kaddr) >> PAGE_SHIFT;
return 0; return dev_sz - offset;
} }
static void static void
......
...@@ -429,6 +429,46 @@ int bdev_write_page(struct block_device *bdev, sector_t sector, ...@@ -429,6 +429,46 @@ int bdev_write_page(struct block_device *bdev, sector_t sector,
} }
EXPORT_SYMBOL_GPL(bdev_write_page); EXPORT_SYMBOL_GPL(bdev_write_page);
/**
* bdev_direct_access() - Get the address for directly-accessibly memory
* @bdev: The device containing the memory
* @sector: The offset within the device
* @addr: Where to put the address of the memory
* @pfn: The Page Frame Number for the memory
* @size: The number of bytes requested
*
* If a block device is made up of directly addressable memory, this function
* will tell the caller the PFN and the address of the memory. The address
* may be directly dereferenced within the kernel without the need to call
* ioremap(), kmap() or similar. The PFN is suitable for inserting into
* page tables.
*
* Return: negative errno if an error occurs, otherwise the number of bytes
* accessible at this address.
*/
long bdev_direct_access(struct block_device *bdev, sector_t sector,
void **addr, unsigned long *pfn, long size)
{
long avail;
const struct block_device_operations *ops = bdev->bd_disk->fops;
if (size < 0)
return size;
if (!ops->direct_access)
return -EOPNOTSUPP;
if ((sector + DIV_ROUND_UP(size, 512)) >
part_nr_sects_read(bdev->bd_part))
return -ERANGE;
sector += get_start_sect(bdev);
if (sector % (PAGE_SIZE / 512))
return -EINVAL;
avail = ops->direct_access(bdev, sector, addr, pfn, size);
if (!avail)
return -ERANGE;
return min(avail, size);
}
EXPORT_SYMBOL_GPL(bdev_direct_access);
/* /*
* pseudo-fs * pseudo-fs
*/ */
......
...@@ -13,18 +13,12 @@ ...@@ -13,18 +13,12 @@
#include "ext2.h" #include "ext2.h"
#include "xip.h" #include "xip.h"
static inline int static inline long __inode_direct_access(struct inode *inode, sector_t block,
__inode_direct_access(struct inode *inode, sector_t block, void **kaddr, unsigned long *pfn, long size)
void **kaddr, unsigned long *pfn)
{ {
struct block_device *bdev = inode->i_sb->s_bdev; struct block_device *bdev = inode->i_sb->s_bdev;
const struct block_device_operations *ops = bdev->bd_disk->fops; sector_t sector = block * (PAGE_SIZE / 512);
sector_t sector; return bdev_direct_access(bdev, sector, kaddr, pfn, size);
sector = block * (PAGE_SIZE / 512); /* ext2 block to bdev sector */
BUG_ON(!ops->direct_access);
return ops->direct_access(bdev, sector, kaddr, pfn);
} }
static inline int static inline int
...@@ -53,12 +47,13 @@ ext2_clear_xip_target(struct inode *inode, sector_t block) ...@@ -53,12 +47,13 @@ ext2_clear_xip_target(struct inode *inode, sector_t block)
{ {
void *kaddr; void *kaddr;
unsigned long pfn; unsigned long pfn;
int rc; long size;
rc = __inode_direct_access(inode, block, &kaddr, &pfn); size = __inode_direct_access(inode, block, &kaddr, &pfn, PAGE_SIZE);
if (!rc) if (size < 0)
return size;
clear_page(kaddr); clear_page(kaddr);
return rc; return 0;
} }
void ext2_xip_verify_sb(struct super_block *sb) void ext2_xip_verify_sb(struct super_block *sb)
...@@ -77,7 +72,7 @@ void ext2_xip_verify_sb(struct super_block *sb) ...@@ -77,7 +72,7 @@ void ext2_xip_verify_sb(struct super_block *sb)
int ext2_get_xip_mem(struct address_space *mapping, pgoff_t pgoff, int create, int ext2_get_xip_mem(struct address_space *mapping, pgoff_t pgoff, int create,
void **kmem, unsigned long *pfn) void **kmem, unsigned long *pfn)
{ {
int rc; long rc;
sector_t block; sector_t block;
/* first, retrieve the sector number */ /* first, retrieve the sector number */
...@@ -86,6 +81,6 @@ int ext2_get_xip_mem(struct address_space *mapping, pgoff_t pgoff, int create, ...@@ -86,6 +81,6 @@ int ext2_get_xip_mem(struct address_space *mapping, pgoff_t pgoff, int create,
return rc; return rc;
/* retrieve address of the target data */ /* retrieve address of the target data */
rc = __inode_direct_access(mapping->host, block, kmem, pfn); rc = __inode_direct_access(mapping->host, block, kmem, pfn, PAGE_SIZE);
return rc; return (rc < 0) ? rc : 0;
} }
...@@ -1601,8 +1601,8 @@ struct block_device_operations { ...@@ -1601,8 +1601,8 @@ struct block_device_operations {
int (*rw_page)(struct block_device *, sector_t, struct page *, int rw); int (*rw_page)(struct block_device *, sector_t, struct page *, int rw);
int (*ioctl) (struct block_device *, fmode_t, unsigned, unsigned long); int (*ioctl) (struct block_device *, fmode_t, unsigned, unsigned long);
int (*compat_ioctl) (struct block_device *, fmode_t, unsigned, unsigned long); int (*compat_ioctl) (struct block_device *, fmode_t, unsigned, unsigned long);
int (*direct_access) (struct block_device *, sector_t, long (*direct_access)(struct block_device *, sector_t,
void **, unsigned long *); void **, unsigned long *pfn, long size);
unsigned int (*check_events) (struct gendisk *disk, unsigned int (*check_events) (struct gendisk *disk,
unsigned int clearing); unsigned int clearing);
/* ->media_changed() is DEPRECATED, use ->check_events() instead */ /* ->media_changed() is DEPRECATED, use ->check_events() instead */
...@@ -1620,6 +1620,8 @@ extern int __blkdev_driver_ioctl(struct block_device *, fmode_t, unsigned int, ...@@ -1620,6 +1620,8 @@ extern int __blkdev_driver_ioctl(struct block_device *, fmode_t, unsigned int,
extern int bdev_read_page(struct block_device *, sector_t, struct page *); extern int bdev_read_page(struct block_device *, sector_t, struct page *);
extern int bdev_write_page(struct block_device *, sector_t, struct page *, extern int bdev_write_page(struct block_device *, sector_t, struct page *,
struct writeback_control *); struct writeback_control *);
extern long bdev_direct_access(struct block_device *, sector_t, void **addr,
unsigned long *pfn, long size);
#else /* CONFIG_BLOCK */ #else /* CONFIG_BLOCK */
struct block_device; struct block_device;
......
Markdown is supported
0%
or
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment