xiaomi-sm8450/android_kernel_xiaomi_sm8450
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

dax: rip out get_block based IO support

Browse Source 
No one uses functions using the get_block callback anymore. Rip them
out and update documentation.

Reviewed-by: Ross Zwisler <ross.zwisler@linux.intel.com>
Signed-off-by: Jan Kara <jack@suse.cz>
Signed-off-by: Theodore Ts'o <tytso@mit.edu>
This commit is contained in:
Jan Kara
2016-11-20 20:48:36 -05:00
committed by Theodore Ts'o
parent 00697eed38
commit dd936e4313
3 changed files with 11 additions and 338 deletions
Download Patch File Download Diff File Expand all files Collapse all files

315
fs/dax.c
View File

@@ -116,168 +116,6 @@ struct page *read_dax_sector(struct block_device *bdev, sector_t n)
return page;
}
static bool buffer_written(struct buffer_head *bh)
{
return buffer_mapped(bh) && !buffer_unwritten(bh);
}
static sector_t to_sector(const struct buffer_head *bh,
const struct inode *inode)
{
sector_t sector = bh->b_blocknr << (inode->i_blkbits - 9);
return sector;
}
static ssize_t dax_io(struct inode *inode, struct iov_iter *iter,
loff_t start, loff_t end, get_block_t get_block,
struct buffer_head *bh)
{
loff_t pos = start, max = start, bh_max = start;
bool hole = false;
struct block_device *bdev = NULL;
int rw = iov_iter_rw(iter), rc;
long map_len = 0;
struct blk_dax_ctl dax = {
.addr = ERR_PTR(-EIO),
};
unsigned blkbits = inode->i_blkbits;
sector_t file_blks = (i_size_read(inode) + (1 << blkbits) - 1)
>> blkbits;
if (rw == READ)
end = min(end, i_size_read(inode));
while (pos < end) {
size_t len;
if (pos == max) {
long page = pos >> PAGE_SHIFT;
sector_t block = page << (PAGE_SHIFT - blkbits);
unsigned first = pos - (block << blkbits);
long size;
if (pos == bh_max) {
bh->b_size = PAGE_ALIGN(end - pos);
bh->b_state = 0;
rc = get_block(inode, block, bh, rw == WRITE);
if (rc)
break;
bh_max = pos - first + bh->b_size;
bdev = bh->b_bdev;
/*
* We allow uninitialized buffers for writes
* beyond EOF as those cannot race with faults
*/
WARN_ON_ONCE(
(buffer_new(bh) && block < file_blks) ||
(rw == WRITE && buffer_unwritten(bh)));
} else {
unsigned done = bh->b_size -
(bh_max - (pos - first));
bh->b_blocknr += done >> blkbits;
bh->b_size -= done;
}
hole = rw == READ && !buffer_written(bh);
if (hole) {
size = bh->b_size - first;
} else {
dax_unmap_atomic(bdev, &dax);
dax.sector = to_sector(bh, inode);
dax.size = bh->b_size;
map_len = dax_map_atomic(bdev, &dax);
if (map_len < 0) {
rc = map_len;
break;
}
dax.addr += first;
size = map_len - first;
}
/*
* pos + size is one past the last offset for IO,
* so pos + size can overflow loff_t at extreme offsets.
* Cast to u64 to catch this and get the true minimum.
*/
max = min_t(u64, pos + size, end);
}
if (iov_iter_rw(iter) == WRITE) {
len = copy_from_iter_pmem(dax.addr, max - pos, iter);
} else if (!hole)
len = copy_to_iter((void __force *) dax.addr, max - pos,
iter);
else
len = iov_iter_zero(max - pos, iter);
if (!len) {
rc = -EFAULT;
break;
}
pos += len;
if (!IS_ERR(dax.addr))
dax.addr += len;
}
dax_unmap_atomic(bdev, &dax);
return (pos == start) ? rc : pos - start;
}
/**
* dax_do_io - Perform I/O to a DAX file
* @iocb: The control block for this I/O
* @inode: The file which the I/O is directed at
* @iter: The addresses to do I/O from or to
* @get_block: The filesystem method used to translate file offsets to blocks
* @end_io: A filesystem callback for I/O completion
* @flags: See below
*
* This function uses the same locking scheme as do_blockdev_direct_IO:
* If @flags has DIO_LOCKING set, we assume that the i_mutex is held by the
* caller for writes. For reads, we take and release the i_mutex ourselves.
* If DIO_LOCKING is not set, the filesystem takes care of its own locking.
* As with do_blockdev_direct_IO(), we increment i_dio_count while the I/O
* is in progress.
*/
ssize_t dax_do_io(struct kiocb *iocb, struct inode *inode,
struct iov_iter *iter, get_block_t get_block,
dio_iodone_t end_io, int flags)
{
struct buffer_head bh;
ssize_t retval = -EINVAL;
loff_t pos = iocb->ki_pos;
loff_t end = pos + iov_iter_count(iter);
memset(&bh, 0, sizeof(bh));
bh.b_bdev = inode->i_sb->s_bdev;
if ((flags & DIO_LOCKING) && iov_iter_rw(iter) == READ)
inode_lock(inode);
/* Protects against truncate */
if (!(flags & DIO_SKIP_DIO_COUNT))
inode_dio_begin(inode);
retval = dax_io(inode, iter, pos, end, get_block, &bh);
if ((flags & DIO_LOCKING) && iov_iter_rw(iter) == READ)
inode_unlock(inode);
if (end_io) {
int err;
err = end_io(iocb, pos, retval, bh.b_private);
if (err)
retval = err;
}
if (!(flags & DIO_SKIP_DIO_COUNT))
inode_dio_end(inode);
return retval;
}
EXPORT_SYMBOL_GPL(dax_do_io);
/*
* DAX radix tree locking
*/
@@ -919,105 +757,6 @@ static int dax_insert_mapping(struct address_space *mapping,
return vm_insert_mixed(vma, vaddr, dax.pfn);
}
/**
* dax_fault - handle a page fault on a DAX file
* @vma: The virtual memory area where the fault occurred
* @vmf: The description of the fault
* @get_block: The filesystem method used to translate file offsets to blocks
*
* When a page fault occurs, filesystems may call this helper in their
* fault handler for DAX files. dax_fault() assumes the caller has done all
* the necessary locking for the page fault to proceed successfully.
*/
int dax_fault(struct vm_area_struct *vma, struct vm_fault *vmf,
get_block_t get_block)
{
struct file *file = vma->vm_file;
struct address_space *mapping = file->f_mapping;
struct inode *inode = mapping->host;
void *entry;
struct buffer_head bh;
unsigned long vaddr = (unsigned long)vmf->virtual_address;
unsigned blkbits = inode->i_blkbits;
sector_t block;
pgoff_t size;
int error;
int major = 0;
/*
* Check whether offset isn't beyond end of file now. Caller is supposed
* to hold locks serializing us with truncate / punch hole so this is
* a reliable test.
*/
size = (i_size_read(inode) + PAGE_SIZE - 1) >> PAGE_SHIFT;
if (vmf->pgoff >= size)
return VM_FAULT_SIGBUS;
memset(&bh, 0, sizeof(bh));
block = (sector_t)vmf->pgoff << (PAGE_SHIFT - blkbits);
bh.b_bdev = inode->i_sb->s_bdev;
bh.b_size = PAGE_SIZE;
entry = grab_mapping_entry(mapping, vmf->pgoff, 0);
if (IS_ERR(entry)) {
error = PTR_ERR(entry);
goto out;
}
error = get_block(inode, block, &bh, 0);
if (!error && (bh.b_size < PAGE_SIZE))
error = -EIO; /* fs corruption? */
if (error)
goto unlock_entry;
if (vmf->cow_page) {
struct page *new_page = vmf->cow_page;
if (buffer_written(&bh))
error = copy_user_dax(bh.b_bdev, to_sector(&bh, inode),
bh.b_size, new_page, vaddr);
else
clear_user_highpage(new_page, vaddr);
if (error)
goto unlock_entry;
if (!radix_tree_exceptional_entry(entry)) {
vmf->page = entry;
return VM_FAULT_LOCKED;
}
vmf->entry = entry;
return VM_FAULT_DAX_LOCKED;
}
if (!buffer_mapped(&bh)) {
if (vmf->flags & FAULT_FLAG_WRITE) {
error = get_block(inode, block, &bh, 1);
count_vm_event(PGMAJFAULT);
mem_cgroup_count_vm_event(vma->vm_mm, PGMAJFAULT);
major = VM_FAULT_MAJOR;
if (!error && (bh.b_size < PAGE_SIZE))
error = -EIO;
if (error)
goto unlock_entry;
} else {
return dax_load_hole(mapping, entry, vmf);
}
}
/* Filesystem should not return unwritten buffers to us! */
WARN_ON_ONCE(buffer_unwritten(&bh) || buffer_new(&bh));
error = dax_insert_mapping(mapping, bh.b_bdev, to_sector(&bh, inode),
bh.b_size, &entry, vma, vmf);
unlock_entry:
put_locked_mapping_entry(mapping, vmf->pgoff, entry);
out:
if (error == -ENOMEM)
return VM_FAULT_OOM | major;
/* -EBUSY is fine, somebody else faulted on the same PTE */
if ((error < 0) && (error != -EBUSY))
return VM_FAULT_SIGBUS | major;
return VM_FAULT_NOPAGE | major;
}
EXPORT_SYMBOL_GPL(dax_fault);
/**
* dax_pfn_mkwrite - handle first write to DAX page
* @vma: The virtual memory area where the fault occurred
@@ -1078,60 +817,6 @@ int __dax_zero_page_range(struct block_device *bdev, sector_t sector,
}
EXPORT_SYMBOL_GPL(__dax_zero_page_range);
/**
* dax_zero_page_range - zero a range within a page of a DAX file
* @inode: The file being truncated
* @from: The file offset that is being truncated to
* @length: The number of bytes to zero
* @get_block: The filesystem method used to translate file offsets to blocks
*
* This function can be called by a filesystem when it is zeroing part of a
* page in a DAX file. This is intended for hole-punch operations. If
* you are truncating a file, the helper function dax_truncate_page() may be
* more convenient.
*/
int dax_zero_page_range(struct inode *inode, loff_t from, unsigned length,
get_block_t get_block)
{
struct buffer_head bh;
pgoff_t index = from >> PAGE_SHIFT;
unsigned offset = from & (PAGE_SIZE-1);
int err;
/* Block boundary? Nothing to do */
if (!length)
return 0;
if (WARN_ON_ONCE((offset + length) > PAGE_SIZE))
return -EINVAL;
memset(&bh, 0, sizeof(bh));
bh.b_bdev = inode->i_sb->s_bdev;
bh.b_size = PAGE_SIZE;
err = get_block(inode, index, &bh, 0);
if (err < 0 || !buffer_written(&bh))
return err;
return __dax_zero_page_range(bh.b_bdev, to_sector(&bh, inode),
offset, length);
}
EXPORT_SYMBOL_GPL(dax_zero_page_range);
/**
* dax_truncate_page - handle a partial page being truncated in a DAX file
* @inode: The file being truncated
* @from: The file offset that is being truncated to
* @get_block: The filesystem method used to translate file offsets to blocks
*
* Similar to block_truncate_page(), this function can be called by a
* filesystem when it is truncating a DAX file to handle the partial page.
*/
int dax_truncate_page(struct inode *inode, loff_t from, get_block_t get_block)
{
unsigned length = PAGE_ALIGN(from) - from;
return dax_zero_page_range(inode, from, length, get_block);
}
EXPORT_SYMBOL_GPL(dax_truncate_page);
#ifdef CONFIG_FS_IOMAP
static sector_t dax_iomap_sector(struct iomap *iomap, loff_t pos)
{