aboutsummaryrefslogtreecommitdiffstats
path: root/fs/block_dev.c
diff options
context:
space:
mode:
Diffstat (limited to 'fs/block_dev.c')
-rw-r--r--fs/block_dev.c156
1 files changed, 48 insertions, 108 deletions
diff --git a/fs/block_dev.c b/fs/block_dev.c
index 2eca00ec4370..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>
@@ -103,12 +104,11 @@ void invalidate_bdev(struct block_device *bdev)
{
struct address_space *mapping = bdev->bd_inode->i_mapping;
- if (mapping->nrpages == 0)
- return;
-
- invalidate_bh_lrus();
- lru_add_drain_all(); /* make sure all lru add caches are flushed */
- invalidate_mapping_pages(mapping, 0, -1);
+ if (mapping->nrpages) {
+ invalidate_bh_lrus();
+ lru_add_drain_all(); /* make sure all lru add caches are flushed */
+ invalidate_mapping_pages(mapping, 0, -1);
+ }
/* 99% of the time, we don't need to flush the cleancache on the bdev.
* But, for the strange corners, lets be cautious
*/
@@ -717,50 +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
@@ -774,62 +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
@@ -885,6 +837,8 @@ static void bdev_evict_inode(struct inode *inode)
spin_lock(&bdev_lock);
list_del_init(&bdev->bd_list);
spin_unlock(&bdev_lock);
+ /* Detach inode from wb early as bdi_put() may free bdi->wb */
+ inode_detach_wb(inode);
if (bdev->bd_bdi != &noop_backing_dev_info) {
bdi_put(bdev->bd_bdi);
bdev->bd_bdi = &noop_backing_dev_info;
@@ -1451,7 +1405,6 @@ int revalidate_disk(struct gendisk *disk)
if (disk->fops->revalidate_disk)
ret = disk->fops->revalidate_disk(disk);
- blk_integrity_revalidate(disk);
bdev = bdget_disk(disk, 0);
if (!bdev)
return ret;
@@ -1556,8 +1509,6 @@ static int __blkdev_get(struct block_device *bdev, fmode_t mode, int for_part)
bdev->bd_disk = disk;
bdev->bd_queue = disk->queue;
bdev->bd_contains = bdev;
- if (bdev->bd_bdi == &noop_backing_dev_info)
- bdev->bd_bdi = bdi_get(disk->queue->backing_dev_info);
if (!partno) {
ret = -ENXIO;
@@ -1622,6 +1573,9 @@ static int __blkdev_get(struct block_device *bdev, fmode_t mode, int for_part)
}
bd_set_size(bdev, (loff_t)bdev->bd_part->nr_sects << 9);
}
+
+ if (bdev->bd_bdi == &noop_backing_dev_info)
+ bdev->bd_bdi = bdi_get(disk->queue->backing_dev_info);
} else {
if (bdev->bd_contains == bdev) {
ret = 0;
@@ -1653,8 +1607,6 @@ static int __blkdev_get(struct block_device *bdev, fmode_t mode, int for_part)
bdev->bd_disk = NULL;
bdev->bd_part = NULL;
bdev->bd_queue = NULL;
- bdi_put(bdev->bd_bdi);
- bdev->bd_bdi = &noop_backing_dev_info;
if (bdev != bdev->bd_contains)
__blkdev_put(bdev->bd_contains, mode, 1);
bdev->bd_contains = NULL;
@@ -1876,12 +1828,6 @@ static void __blkdev_put(struct block_device *bdev, fmode_t mode, int for_part)
kill_bdev(bdev);
bdev_write_inode(bdev);
- /*
- * Detaching bdev inode from its wb in __destroy_inode()
- * is too late: the queue which embeds its bdi (along with
- * root wb) can be gone as soon as we put_disk() below.
- */
- inode_detach_wb(bdev->bd_inode);
}
if (bdev->bd_contains == bdev) {
if (disk->fops->release)
@@ -2074,7 +2020,6 @@ static long blkdev_fallocate(struct file *file, int mode, loff_t start,
loff_t len)
{
struct block_device *bdev = I_BDEV(bdev_file_inode(file));
- struct request_queue *q = bdev_get_queue(bdev);
struct address_space *mapping;
loff_t end = start + len - 1;
loff_t isize;
@@ -2110,18 +2055,13 @@ static long blkdev_fallocate(struct file *file, int mode, loff_t start,
case FALLOC_FL_ZERO_RANGE:
case FALLOC_FL_ZERO_RANGE | FALLOC_FL_KEEP_SIZE:
error = blkdev_issue_zeroout(bdev, start >> 9, len >> 9,
- GFP_KERNEL, false);
+ GFP_KERNEL, BLKDEV_ZERO_NOUNMAP);
break;
case FALLOC_FL_PUNCH_HOLE | FALLOC_FL_KEEP_SIZE:
- /* Only punch if the device can do zeroing discard. */
- if (!blk_queue_discard(q) || !q->limits.discard_zeroes_data)
- return -EOPNOTSUPP;
- error = blkdev_issue_discard(bdev, start >> 9, len >> 9,
- GFP_KERNEL, 0);
+ error = blkdev_issue_zeroout(bdev, start >> 9, len >> 9,
+ GFP_KERNEL, BLKDEV_ZERO_NOFALLBACK);
break;
case FALLOC_FL_PUNCH_HOLE | FALLOC_FL_KEEP_SIZE | FALLOC_FL_NO_HIDE_STALE:
- if (!blk_queue_discard(q))
- return -EOPNOTSUPP;
error = blkdev_issue_discard(bdev, start >> 9, len >> 9,
GFP_KERNEL, 0);
break;
Copyright © 1996 – 2023 Jason A. Donenfeld. All Rights Reverse Engineered.