Commit 0a70bd43 authored by Dan Williams's avatar Dan Williams Committed by Vishal Verma

dax: enable dax in the presence of known media errors (badblocks)

1/ If a mapping overlaps a bad sector fail the request.

2/ Do not opportunistically report more dax-capable capacity than is
   requested when errors present.
Reviewed-by: default avatarJeff Moyer <jmoyer@redhat.com>
Reviewed-by: default avatarChristoph Hellwig <hch@lst.de>
Signed-off-by: default avatarDan Williams <dan.j.williams@intel.com>
[vishal: fix a conflict with system RAM collision patches]
[vishal: add a 'size' parameter to ->direct_access]
[vishal: fix a conflict with DAX alignment check patches]
Signed-off-by: default avatarVishal Verma <vishal.l.verma@intel.com>
parent 8b3db979
...@@ -143,7 +143,7 @@ axon_ram_make_request(struct request_queue *queue, struct bio *bio) ...@@ -143,7 +143,7 @@ axon_ram_make_request(struct request_queue *queue, struct bio *bio)
*/ */
static long 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 __pmem **kaddr, pfn_t *pfn) void __pmem **kaddr, pfn_t *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)sector << AXON_RAM_SECTOR_SHIFT; loff_t offset = (loff_t)sector << AXON_RAM_SECTOR_SHIFT;
......
...@@ -381,7 +381,7 @@ static int brd_rw_page(struct block_device *bdev, sector_t sector, ...@@ -381,7 +381,7 @@ static int brd_rw_page(struct block_device *bdev, sector_t sector,
#ifdef CONFIG_BLK_DEV_RAM_DAX #ifdef CONFIG_BLK_DEV_RAM_DAX
static long brd_direct_access(struct block_device *bdev, sector_t sector, static long brd_direct_access(struct block_device *bdev, sector_t sector,
void __pmem **kaddr, pfn_t *pfn) void __pmem **kaddr, pfn_t *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;
......
...@@ -182,14 +182,22 @@ static int pmem_rw_page(struct block_device *bdev, sector_t sector, ...@@ -182,14 +182,22 @@ static int pmem_rw_page(struct block_device *bdev, sector_t sector,
} }
static long pmem_direct_access(struct block_device *bdev, sector_t sector, static long pmem_direct_access(struct block_device *bdev, sector_t sector,
void __pmem **kaddr, pfn_t *pfn) void __pmem **kaddr, pfn_t *pfn, long size)
{ {
struct pmem_device *pmem = bdev->bd_disk->private_data; struct pmem_device *pmem = bdev->bd_disk->private_data;
resource_size_t offset = sector * 512 + pmem->data_offset; resource_size_t offset = sector * 512 + pmem->data_offset;
if (unlikely(is_bad_pmem(&pmem->bb, sector, size)))
return -EIO;
*kaddr = pmem->virt_addr + offset; *kaddr = pmem->virt_addr + offset;
*pfn = phys_to_pfn_t(pmem->phys_addr + offset, pmem->pfn_flags); *pfn = phys_to_pfn_t(pmem->phys_addr + offset, pmem->pfn_flags);
/*
* If badblocks are present, limit known good range to the
* requested range.
*/
if (unlikely(pmem->bb.count))
return size;
return pmem->size - pmem->pfn_pad - offset; return pmem->size - pmem->pfn_pad - offset;
} }
......
...@@ -31,7 +31,7 @@ static void dcssblk_release(struct gendisk *disk, fmode_t mode); ...@@ -31,7 +31,7 @@ static void dcssblk_release(struct gendisk *disk, fmode_t mode);
static blk_qc_t dcssblk_make_request(struct request_queue *q, static blk_qc_t dcssblk_make_request(struct request_queue *q,
struct bio *bio); struct bio *bio);
static long dcssblk_direct_access(struct block_device *bdev, sector_t secnum, static long dcssblk_direct_access(struct block_device *bdev, sector_t secnum,
void __pmem **kaddr, pfn_t *pfn); void __pmem **kaddr, pfn_t *pfn, long size);
static char dcssblk_segments[DCSSBLK_PARM_LEN] = "\0"; static char dcssblk_segments[DCSSBLK_PARM_LEN] = "\0";
...@@ -883,7 +883,7 @@ dcssblk_make_request(struct request_queue *q, struct bio *bio) ...@@ -883,7 +883,7 @@ dcssblk_make_request(struct request_queue *q, struct bio *bio)
static long static long
dcssblk_direct_access (struct block_device *bdev, sector_t secnum, dcssblk_direct_access (struct block_device *bdev, sector_t secnum,
void __pmem **kaddr, pfn_t *pfn) void __pmem **kaddr, pfn_t *pfn, long size)
{ {
struct dcssblk_dev_info *dev_info; struct dcssblk_dev_info *dev_info;
unsigned long offset, dev_sz; unsigned long offset, dev_sz;
......
...@@ -29,7 +29,6 @@ ...@@ -29,7 +29,6 @@
#include <linux/log2.h> #include <linux/log2.h>
#include <linux/cleancache.h> #include <linux/cleancache.h>
#include <linux/dax.h> #include <linux/dax.h>
#include <linux/badblocks.h>
#include <asm/uaccess.h> #include <asm/uaccess.h>
#include "internal.h" #include "internal.h"
...@@ -501,7 +500,7 @@ long bdev_direct_access(struct block_device *bdev, struct blk_dax_ctl *dax) ...@@ -501,7 +500,7 @@ long bdev_direct_access(struct block_device *bdev, struct blk_dax_ctl *dax)
sector += get_start_sect(bdev); sector += get_start_sect(bdev);
if (sector % (PAGE_SIZE / 512)) if (sector % (PAGE_SIZE / 512))
return -EINVAL; return -EINVAL;
avail = ops->direct_access(bdev, sector, &dax->addr, &dax->pfn); avail = ops->direct_access(bdev, sector, &dax->addr, &dax->pfn, size);
if (!avail) if (!avail)
return -ERANGE; return -ERANGE;
if (avail > 0 && avail & ~PAGE_MASK) if (avail > 0 && avail & ~PAGE_MASK)
...@@ -561,7 +560,6 @@ EXPORT_SYMBOL_GPL(bdev_dax_supported); ...@@ -561,7 +560,6 @@ EXPORT_SYMBOL_GPL(bdev_dax_supported);
*/ */
bool bdev_dax_capable(struct block_device *bdev) bool bdev_dax_capable(struct block_device *bdev)
{ {
struct gendisk *disk = bdev->bd_disk;
struct blk_dax_ctl dax = { struct blk_dax_ctl dax = {
.size = PAGE_SIZE, .size = PAGE_SIZE,
}; };
...@@ -577,15 +575,6 @@ bool bdev_dax_capable(struct block_device *bdev) ...@@ -577,15 +575,6 @@ bool bdev_dax_capable(struct block_device *bdev)
if (bdev_direct_access(bdev, &dax) < 0) if (bdev_direct_access(bdev, &dax) < 0)
return false; return false;
/*
* If the device has known bad blocks, force all I/O through the
* driver / page cache.
*
* TODO: support finer grained dax error handling
*/
if (disk->bb && disk->bb->count)
return false;
return true; return true;
} }
......
...@@ -1668,7 +1668,7 @@ struct block_device_operations { ...@@ -1668,7 +1668,7 @@ struct block_device_operations {
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);
long (*direct_access)(struct block_device *, sector_t, void __pmem **, long (*direct_access)(struct block_device *, sector_t, void __pmem **,
pfn_t *); pfn_t *, long);
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 */
......
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