summaryrefslogtreecommitdiff
path: root/fs/block_dev.c
diff options
context:
space:
mode:
authorLinus Torvalds <torvalds@linux-foundation.org>2016-01-14 06:15:14 +0300
committerLinus Torvalds <torvalds@linux-foundation.org>2016-01-14 06:15:14 +0300
commitd080827f850ba4df5b955d5ca8c8c0fc92fe18c0 (patch)
tree37262315200bbbe50bdd64ce3011951a92855159 /fs/block_dev.c
parentcbd88cd4c07f9361914ab7fd7e21c9227986fe68 (diff)
parent8b63b6bfc1a551acf154061699028c7032d7890c (diff)
downloadlinux-d080827f850ba4df5b955d5ca8c8c0fc92fe18c0.tar.xz
Merge tag 'libnvdimm-for-4.5' of git://git.kernel.org/pub/scm/linux/kernel/git/nvdimm/nvdimm
Pull libnvdimm updates from Dan Williams: "The bulk of this has appeared in -next and independently received a build success notification from the kbuild robot. The 'for-4.5/block- dax' topic branch was rebased over the weekend to drop the "block device end-of-life" rework that Al would like to see re-implemented with a notifier, and to address bug reports against the badblocks integration. There is pending feedback against "libnvdimm: Add a poison list and export badblocks" received last week. Linda identified some localized fixups that we will handle incrementally. Summary: - Media error handling: The 'badblocks' implementation that originated in md-raid is up-levelled to a generic capability of a block device. This initial implementation is limited to being consulted in the pmem block-i/o path. Later, 'badblocks' will be consulted when creating dax mappings. - Raw block device dax: For virtualization and other cases that want large contiguous mappings of persistent memory, add the capability to dax-mmap a block device directly. - Increased /dev/mem restrictions: Add an option to treat all io-memory as IORESOURCE_EXCLUSIVE, i.e. disable /dev/mem access while a driver is actively using an address range. This behavior is controlled via the new CONFIG_IO_STRICT_DEVMEM option and can be overridden by the existing "iomem=relaxed" kernel command line option. - Miscellaneous fixes include a 'pfn'-device huge page alignment fix, block device shutdown crash fix, and other small libnvdimm fixes" * tag 'libnvdimm-for-4.5' of git://git.kernel.org/pub/scm/linux/kernel/git/nvdimm/nvdimm: (32 commits) block: kill disk_{check|set|clear|alloc}_badblocks libnvdimm, pmem: nvdimm_read_bytes() badblocks support pmem, dax: disable dax in the presence of bad blocks pmem: fail io-requests to known bad blocks libnvdimm: convert to statically allocated badblocks libnvdimm: don't fail init for full badblocks list block, badblocks: introduce devm_init_badblocks block: clarify badblocks lifetime badblocks: rename badblocks_free to badblocks_exit libnvdimm, pmem: move definition of nvdimm_namespace_add_poison to nd.h libnvdimm: Add a poison list and export badblocks nfit_test: Enable DSMs for all test NFITs md: convert to use the generic badblocks code block: Add badblock management for gendisks badblocks: Add core badblock management code block: fix del_gendisk() vs blkdev_ioctl crash block: enable dax for raw block devices block: introduce bdev_file_inode() restrict /dev/mem to idle io memory ranges arch: consolidate CONFIG_STRICT_DEVM in lib/Kconfig.debug ...
Diffstat (limited to 'fs/block_dev.c')
-rw-r--r--fs/block_dev.c122
1 files changed, 107 insertions, 15 deletions
diff --git a/fs/block_dev.c b/fs/block_dev.c
index 01b8e0d4b4ff..d878e4860fb7 100644
--- a/fs/block_dev.c
+++ b/fs/block_dev.c
@@ -156,11 +156,16 @@ blkdev_get_block(struct inode *inode, sector_t iblock,
return 0;
}
+static struct inode *bdev_file_inode(struct file *file)
+{
+ return file->f_mapping->host;
+}
+
static ssize_t
blkdev_direct_IO(struct kiocb *iocb, struct iov_iter *iter, loff_t offset)
{
struct file *file = iocb->ki_filp;
- struct inode *inode = file->f_mapping->host;
+ struct inode *inode = bdev_file_inode(file);
if (IS_DAX(inode))
return dax_do_io(iocb, inode, iter, offset, blkdev_get_block,
@@ -338,7 +343,7 @@ static int blkdev_write_end(struct file *file, struct address_space *mapping,
*/
static loff_t block_llseek(struct file *file, loff_t offset, int whence)
{
- struct inode *bd_inode = file->f_mapping->host;
+ struct inode *bd_inode = bdev_file_inode(file);
loff_t retval;
mutex_lock(&bd_inode->i_mutex);
@@ -349,7 +354,7 @@ static loff_t block_llseek(struct file *file, loff_t offset, int whence)
int blkdev_fsync(struct file *filp, loff_t start, loff_t end, int datasync)
{
- struct inode *bd_inode = filp->f_mapping->host;
+ struct inode *bd_inode = bdev_file_inode(filp);
struct block_device *bdev = I_BDEV(bd_inode);
int error;
@@ -1224,8 +1229,11 @@ static int __blkdev_get(struct block_device *bdev, fmode_t mode, int for_part)
}
}
- if (!ret)
+ if (!ret) {
bd_set_size(bdev,(loff_t)get_capacity(disk)<<9);
+ if (!blkdev_dax_capable(bdev))
+ bdev->bd_inode->i_flags &= ~S_DAX;
+ }
/*
* If the device is invalidated, rescan partition
@@ -1239,6 +1247,7 @@ static int __blkdev_get(struct block_device *bdev, fmode_t mode, int for_part)
else if (ret == -ENOMEDIUM)
invalidate_partitions(disk, bdev);
}
+
if (ret)
goto out_clear;
} else {
@@ -1259,12 +1268,7 @@ static int __blkdev_get(struct block_device *bdev, fmode_t mode, int for_part)
goto out_clear;
}
bd_set_size(bdev, (loff_t)bdev->bd_part->nr_sects << 9);
- /*
- * If the partition is not aligned on a page
- * boundary, we can't do dax I/O to it.
- */
- if ((bdev->bd_part->start_sect % (PAGE_SIZE / 512)) ||
- (bdev->bd_part->nr_sects % (PAGE_SIZE / 512)))
+ if (!blkdev_dax_capable(bdev))
bdev->bd_inode->i_flags &= ~S_DAX;
}
} else {
@@ -1599,14 +1603,14 @@ EXPORT_SYMBOL(blkdev_put);
static int blkdev_close(struct inode * inode, struct file * filp)
{
- struct block_device *bdev = I_BDEV(filp->f_mapping->host);
+ struct block_device *bdev = I_BDEV(bdev_file_inode(filp));
blkdev_put(bdev, filp->f_mode);
return 0;
}
static long block_ioctl(struct file *file, unsigned cmd, unsigned long arg)
{
- struct block_device *bdev = I_BDEV(file->f_mapping->host);
+ struct block_device *bdev = I_BDEV(bdev_file_inode(file));
fmode_t mode = file->f_mode;
/*
@@ -1631,7 +1635,7 @@ static long block_ioctl(struct file *file, unsigned cmd, unsigned long arg)
ssize_t blkdev_write_iter(struct kiocb *iocb, struct iov_iter *from)
{
struct file *file = iocb->ki_filp;
- struct inode *bd_inode = file->f_mapping->host;
+ struct inode *bd_inode = bdev_file_inode(file);
loff_t size = i_size_read(bd_inode);
struct blk_plug plug;
ssize_t ret;
@@ -1663,7 +1667,7 @@ EXPORT_SYMBOL_GPL(blkdev_write_iter);
ssize_t blkdev_read_iter(struct kiocb *iocb, struct iov_iter *to)
{
struct file *file = iocb->ki_filp;
- struct inode *bd_inode = file->f_mapping->host;
+ struct inode *bd_inode = bdev_file_inode(file);
loff_t size = i_size_read(bd_inode);
loff_t pos = iocb->ki_pos;
@@ -1702,13 +1706,101 @@ static const struct address_space_operations def_blk_aops = {
.is_dirty_writeback = buffer_check_dirty_writeback,
};
+#ifdef CONFIG_FS_DAX
+/*
+ * In the raw block case we do not need to contend with truncation nor
+ * unwritten file extents. Without those concerns there is no need for
+ * additional locking beyond the mmap_sem context that these routines
+ * are already executing under.
+ *
+ * Note, there is no protection if the block device is dynamically
+ * resized (partition grow/shrink) during a fault. A stable block device
+ * size is already not enforced in the blkdev_direct_IO path.
+ *
+ * For DAX, it is the responsibility of the block device driver to
+ * ensure the whole-disk device size is stable while requests are in
+ * flight.
+ *
+ * Finally, unlike the filemap_page_mkwrite() case there is no
+ * filesystem superblock to sync against freezing. We still include a
+ * pfn_mkwrite callback for dax drivers to receive write fault
+ * notifications.
+ */
+static int blkdev_dax_fault(struct vm_area_struct *vma, struct vm_fault *vmf)
+{
+ return __dax_fault(vma, vmf, blkdev_get_block, NULL);
+}
+
+static int blkdev_dax_pmd_fault(struct vm_area_struct *vma, unsigned long addr,
+ pmd_t *pmd, unsigned int flags)
+{
+ return __dax_pmd_fault(vma, addr, pmd, flags, blkdev_get_block, NULL);
+}
+
+static void blkdev_vm_open(struct vm_area_struct *vma)
+{
+ struct inode *bd_inode = bdev_file_inode(vma->vm_file);
+ struct block_device *bdev = I_BDEV(bd_inode);
+
+ mutex_lock(&bd_inode->i_mutex);
+ bdev->bd_map_count++;
+ mutex_unlock(&bd_inode->i_mutex);
+}
+
+static void blkdev_vm_close(struct vm_area_struct *vma)
+{
+ struct inode *bd_inode = bdev_file_inode(vma->vm_file);
+ struct block_device *bdev = I_BDEV(bd_inode);
+
+ mutex_lock(&bd_inode->i_mutex);
+ bdev->bd_map_count--;
+ mutex_unlock(&bd_inode->i_mutex);
+}
+
+static const struct vm_operations_struct blkdev_dax_vm_ops = {
+ .open = blkdev_vm_open,
+ .close = blkdev_vm_close,
+ .fault = blkdev_dax_fault,
+ .pmd_fault = blkdev_dax_pmd_fault,
+ .pfn_mkwrite = blkdev_dax_fault,
+};
+
+static const struct vm_operations_struct blkdev_default_vm_ops = {
+ .open = blkdev_vm_open,
+ .close = blkdev_vm_close,
+ .fault = filemap_fault,
+ .map_pages = filemap_map_pages,
+};
+
+static int blkdev_mmap(struct file *file, struct vm_area_struct *vma)
+{
+ struct inode *bd_inode = bdev_file_inode(file);
+ struct block_device *bdev = I_BDEV(bd_inode);
+
+ file_accessed(file);
+ mutex_lock(&bd_inode->i_mutex);
+ bdev->bd_map_count++;
+ if (IS_DAX(bd_inode)) {
+ vma->vm_ops = &blkdev_dax_vm_ops;
+ vma->vm_flags |= VM_MIXEDMAP | VM_HUGEPAGE;
+ } else {
+ vma->vm_ops = &blkdev_default_vm_ops;
+ }
+ mutex_unlock(&bd_inode->i_mutex);
+
+ return 0;
+}
+#else
+#define blkdev_mmap generic_file_mmap
+#endif
+
const struct file_operations def_blk_fops = {
.open = blkdev_open,
.release = blkdev_close,
.llseek = block_llseek,
.read_iter = blkdev_read_iter,
.write_iter = blkdev_write_iter,
- .mmap = generic_file_mmap,
+ .mmap = blkdev_mmap,
.fsync = blkdev_fsync,
.unlocked_ioctl = block_ioctl,
#ifdef CONFIG_COMPAT