summaryrefslogtreecommitdiff
path: root/fs/block_dev.c
diff options
context:
space:
mode:
authorLinus Torvalds <torvalds@linux-foundation.org>2017-05-06 04:49:20 +0300
committerLinus Torvalds <torvalds@linux-foundation.org>2017-05-06 04:49:20 +0300
commit53ef7d0e208fa38c3f63d287e0c3ab174f1e1235 (patch)
tree7d437edf73ef6deb0d77ce291aa25f041837d056 /fs/block_dev.c
parentc6a677c6f37bb7abc85ba7e3465e82b9f7eb1d91 (diff)
parent736163671bcb163fc82600b46c83dfa89d532d95 (diff)
downloadlinux-53ef7d0e208fa38c3f63d287e0c3ab174f1e1235.tar.xz
Merge tag 'libnvdimm-for-4.12' of git://git.kernel.org/pub/scm/linux/kernel/git/nvdimm/nvdimm
Pull libnvdimm updates from Dan Williams: "The bulk of this has been in multiple -next releases. There were a few late breaking fixes and small features that got added in the last couple days, but the whole set has received a build success notification from the kbuild robot. Change summary: - Region media error reporting: A libnvdimm region device is the parent to one or more namespaces. To date, media errors have been reported via the "badblocks" attribute attached to pmem block devices for namespaces in "raw" or "memory" mode. Given that namespaces can be in "device-dax" or "btt-sector" mode this new interface reports media errors generically, i.e. independent of namespace modes or state. This subsequently allows userspace tooling to craft "ACPI 6.1 Section 9.20.7.6 Function Index 4 - Clear Uncorrectable Error" requests and submit them via the ioctl path for NVDIMM root bus devices. - Introduce 'struct dax_device' and 'struct dax_operations': Prompted by a request from Linus and feedback from Christoph this allows for dax capable drivers to publish their own custom dax operations. This fixes the broken assumption that all dax operations are related to a persistent memory device, and makes it easier for other architectures and platforms to add customized persistent memory support. - 'libnvdimm' core updates: A new "deep_flush" sysfs attribute is available for storage appliance applications to manually trigger memory controllers to drain write-pending buffers that would otherwise be flushed automatically by the platform ADR (asynchronous-DRAM-refresh) mechanism at a power loss event. Support for "locked" DIMMs is included to prevent namespaces from surfacing when the namespace label data area is locked. Finally, fixes for various reported deadlocks and crashes, also tagged for -stable. - ACPI / nfit driver updates: General updates of the nfit driver to add DSM command overrides, ACPI 6.1 health state flags support, DSM payload debug available by default, and various fixes. Acknowledgements that came after the branch was pushed: - commmit 565851c972b5 "device-dax: fix sysfs attribute deadlock": Tested-by: Yi Zhang <yizhan@redhat.com> - commit 23f498448362 "libnvdimm: rework region badblocks clearing" Tested-by: Toshi Kani <toshi.kani@hpe.com>" * tag 'libnvdimm-for-4.12' of git://git.kernel.org/pub/scm/linux/kernel/git/nvdimm/nvdimm: (52 commits) libnvdimm, pfn: fix 'npfns' vs section alignment libnvdimm: handle locked label storage areas libnvdimm: convert NDD_ flags to use bitops, introduce NDD_LOCKED brd: fix uninitialized use of brd->dax_dev block, dax: use correct format string in bdev_dax_supported device-dax: fix sysfs attribute deadlock libnvdimm: restore "libnvdimm: band aid btt vs clear poison locking" libnvdimm: fix nvdimm_bus_lock() vs device_lock() ordering libnvdimm: rework region badblocks clearing acpi, nfit: kill ACPI_NFIT_DEBUG libnvdimm: fix clear length of nvdimm_forget_poison() libnvdimm, pmem: fix a NULL pointer BUG in nd_pmem_notify libnvdimm, region: sysfs trigger for nvdimm_flush() libnvdimm: fix phys_addr for nvdimm_clear_poison x86, dax, pmem: remove indirection around memcpy_from_pmem() block: remove block_device_operations ->direct_access() block, dax: convert bdev_dax_supported() to dax_direct_access() filesystem-dax: convert to dax_direct_access() Revert "block: use DAX for partition table reads" ext2, ext4, xfs: retrieve dax_device for iomap operations ...
Diffstat (limited to 'fs/block_dev.c')
-rw-r--r--fs/block_dev.c117
1 files changed, 35 insertions, 82 deletions
diff --git a/fs/block_dev.c b/fs/block_dev.c
index 0d435c794d76..2a305c1a2d88 100644
--- a/fs/block_dev.c
+++ b/fs/block_dev.c
@@ -18,6 +18,7 @@
#include <linux/module.h>
#include <linux/blkpg.h>
#include <linux/magic.h>
+#include <linux/dax.h>
#include <linux/buffer_head.h>
#include <linux/swap.h>
#include <linux/pagevec.h>
@@ -716,50 +717,18 @@ int bdev_write_page(struct block_device *bdev, sector_t sector,
}
EXPORT_SYMBOL_GPL(bdev_write_page);
-/**
- * bdev_direct_access() - Get the address for directly-accessibly memory
- * @bdev: The device containing the memory
- * @dax: control and output parameters for ->direct_access
- *
- * 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, struct blk_dax_ctl *dax)
+int bdev_dax_pgoff(struct block_device *bdev, sector_t sector, size_t size,
+ pgoff_t *pgoff)
{
- sector_t sector = dax->sector;
- long avail, size = dax->size;
- const struct block_device_operations *ops = bdev->bd_disk->fops;
+ phys_addr_t phys_off = (get_start_sect(bdev) + sector) * 512;
- /*
- * The device driver is allowed to sleep, in order to make the
- * memory directly accessible.
- */
- might_sleep();
-
- if (size < 0)
- return size;
- if (!blk_queue_dax(bdev_get_queue(bdev)) || !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))
+ if (pgoff)
+ *pgoff = PHYS_PFN(phys_off);
+ if (phys_off % PAGE_SIZE || size % PAGE_SIZE)
return -EINVAL;
- avail = ops->direct_access(bdev, sector, &dax->addr, &dax->pfn, size);
- if (!avail)
- return -ERANGE;
- if (avail > 0 && avail & ~PAGE_MASK)
- return -ENXIO;
- return min(avail, size);
+ return 0;
}
-EXPORT_SYMBOL_GPL(bdev_direct_access);
+EXPORT_SYMBOL(bdev_dax_pgoff);
/**
* bdev_dax_supported() - Check if the device supports dax for filesystem
@@ -773,62 +742,46 @@ EXPORT_SYMBOL_GPL(bdev_direct_access);
*/
int bdev_dax_supported(struct super_block *sb, int blocksize)
{
- struct blk_dax_ctl dax = {
- .sector = 0,
- .size = PAGE_SIZE,
- };
- int err;
+ struct block_device *bdev = sb->s_bdev;
+ struct dax_device *dax_dev;
+ pgoff_t pgoff;
+ int err, id;
+ void *kaddr;
+ pfn_t pfn;
+ long len;
if (blocksize != PAGE_SIZE) {
vfs_msg(sb, KERN_ERR, "error: unsupported blocksize for dax");
return -EINVAL;
}
- err = bdev_direct_access(sb->s_bdev, &dax);
- if (err < 0) {
- switch (err) {
- case -EOPNOTSUPP:
- vfs_msg(sb, KERN_ERR,
- "error: device does not support dax");
- break;
- case -EINVAL:
- vfs_msg(sb, KERN_ERR,
- "error: unaligned partition for dax");
- break;
- default:
- vfs_msg(sb, KERN_ERR,
- "error: dax access failed (%d)", err);
- }
+ err = bdev_dax_pgoff(bdev, 0, PAGE_SIZE, &pgoff);
+ if (err) {
+ vfs_msg(sb, KERN_ERR, "error: unaligned partition for dax");
return err;
}
- return 0;
-}
-EXPORT_SYMBOL_GPL(bdev_dax_supported);
-
-/**
- * bdev_dax_capable() - Return if the raw device is capable for dax
- * @bdev: The device for raw block device access
- */
-bool bdev_dax_capable(struct block_device *bdev)
-{
- struct blk_dax_ctl dax = {
- .size = PAGE_SIZE,
- };
+ dax_dev = dax_get_by_host(bdev->bd_disk->disk_name);
+ if (!dax_dev) {
+ vfs_msg(sb, KERN_ERR, "error: device does not support dax");
+ return -EOPNOTSUPP;
+ }
- if (!IS_ENABLED(CONFIG_FS_DAX))
- return false;
+ id = dax_read_lock();
+ len = dax_direct_access(dax_dev, pgoff, 1, &kaddr, &pfn);
+ dax_read_unlock(id);
- dax.sector = 0;
- if (bdev_direct_access(bdev, &dax) < 0)
- return false;
+ put_dax(dax_dev);
- dax.sector = bdev->bd_part->nr_sects - (PAGE_SIZE / 512);
- if (bdev_direct_access(bdev, &dax) < 0)
- return false;
+ if (len < 1) {
+ vfs_msg(sb, KERN_ERR,
+ "error: dax access failed (%ld)", len);
+ return len < 0 ? len : -EIO;
+ }
- return true;
+ return 0;
}
+EXPORT_SYMBOL_GPL(bdev_dax_supported);
/*
* pseudo-fs