/*
* Load the given bvec with the next few pages.
*/
static void afs_load_bvec(struct afs_call *call, struct msghdr *msg,
struct bio_vec *bv, pgoff_t first, pgoff_t last,
unsigned offset)
{
struct page *pages[AFS_BVEC_MAX];
unsigned int nr, n, i, to, bytes = 0;
nr = min_t(pgoff_t, last - first + 1, AFS_BVEC_MAX);
n = find_get_pages_contig(call->mapping, first, nr, pages);
ASSERTCMP(n, ==, nr);
msg->msg_flags |= MSG_MORE;
for (i = 0; i < nr; i++) {
to = PAGE_SIZE;
if (first + i >= last) {
to = call->last_to;
msg->msg_flags &= ~MSG_MORE;
}
bv[i].bv_page = pages[i];
bv[i].bv_len = to - offset;
bv[i].bv_offset = offset;
bytes += to - offset;
offset = 0;
}
iov_iter_bvec(&msg->msg_iter, WRITE | ITER_BVEC, bv, nr, bytes);
}
/*
* kill all the pages in the given range
*/
static void afs_kill_pages(struct address_space *mapping,
pgoff_t first, pgoff_t last)
{
struct afs_vnode *vnode = AFS_FS_I(mapping->host);
struct pagevec pv;
unsigned count, loop;
_enter("{%x:%u},%lx-%lx",
vnode->fid.vid, vnode->fid.vnode, first, last);
pagevec_init(&pv);
do {
_debug("kill %lx-%lx", first, last);
count = last - first + 1;
if (count > PAGEVEC_SIZE)
count = PAGEVEC_SIZE;
pv.nr = find_get_pages_contig(mapping, first, count, pv.pages);
ASSERTCMP(pv.nr, ==, count);
for (loop = 0; loop < count; loop++) {
struct page *page = pv.pages[loop];
ClearPageUptodate(page);
SetPageError(page);
end_page_writeback(page);
if (page->index >= first)
first = page->index + 1;
lock_page(page);
generic_error_remove_page(mapping, page);
}
__pagevec_release(&pv);
} while (first <= last);
_leave("");
}
/*
* Redirty all the pages in a given range.
*/
static void afs_redirty_pages(struct writeback_control *wbc,
struct address_space *mapping,
pgoff_t first, pgoff_t last)
{
struct afs_vnode *vnode = AFS_FS_I(mapping->host);
struct pagevec pv;
unsigned count, loop;
_enter("{%x:%u},%lx-%lx",
vnode->fid.vid, vnode->fid.vnode, first, last);
pagevec_init(&pv);
do {
_debug("redirty %lx-%lx", first, last);
count = last - first + 1;
if (count > PAGEVEC_SIZE)
count = PAGEVEC_SIZE;
pv.nr = find_get_pages_contig(mapping, first, count, pv.pages);
ASSERTCMP(pv.nr, ==, count);
for (loop = 0; loop < count; loop++) {
struct page *page = pv.pages[loop];
redirty_page_for_writepage(wbc, page);
end_page_writeback(page);
if (page->index >= first)
first = page->index + 1;
}
__pagevec_release(&pv);
} while (first <= last);
_leave("");
}
/**
* nilfs_find_uncommitted_extent - find extent of uncommitted data
* @inode: inode
* @start_blk: start block offset (in)
* @blkoff: start offset of the found extent (out)
*
* This function searches an extent of buffers marked "delayed" which
* starts from a block offset equal to or larger than @start_blk. If
* such an extent was found, this will store the start offset in
* @blkoff and return its length in blocks. Otherwise, zero is
* returned.
*/
unsigned long nilfs_find_uncommitted_extent(struct inode *inode,
sector_t start_blk,
sector_t *blkoff)
{
unsigned int i;
pgoff_t index;
unsigned int nblocks_in_page;
unsigned long length = 0;
sector_t b;
struct pagevec pvec;
struct page *page;
if (inode->i_mapping->nrpages == 0)
return 0;
index = start_blk >> (PAGE_SHIFT - inode->i_blkbits);
nblocks_in_page = 1U << (PAGE_SHIFT - inode->i_blkbits);
pagevec_init(&pvec);
repeat:
pvec.nr = find_get_pages_contig(inode->i_mapping, index, PAGEVEC_SIZE,
pvec.pages);
if (pvec.nr == 0)
return length;
if (length > 0 && pvec.pages[0]->index > index)
goto out;
b = pvec.pages[0]->index << (PAGE_SHIFT - inode->i_blkbits);
i = 0;
do {
page = pvec.pages[i];
lock_page(page);
if (page_has_buffers(page)) {
struct buffer_head *bh, *head;
bh = head = page_buffers(page);
do {
if (b < start_blk)
continue;
if (buffer_delay(bh)) {
if (length == 0)
*blkoff = b;
length++;
} else if (length > 0) {
goto out_locked;
}
} while (++b, bh = bh->b_this_page, bh != head);
} else {
if (length > 0)
goto out_locked;
b += nblocks_in_page;
}
unlock_page(page);
} while (++i < pagevec_count(&pvec));
index = page->index + 1;
pagevec_release(&pvec);
cond_resched();
goto repeat;
out_locked:
unlock_page(page);
out:
pagevec_release(&pvec);
return length;
}
static int
__generic_file_splice_read(struct file *in, loff_t *ppos,
struct pipe_inode_info *pipe, size_t len,
unsigned int flags)
{
struct address_space *mapping = in->f_mapping;
unsigned int loff, nr_pages;
struct page *pages[PIPE_BUFFERS];
struct partial_page partial[PIPE_BUFFERS];
struct page *page;
pgoff_t index, end_index;
loff_t isize;
size_t total_len;
int error, page_nr;
struct splice_pipe_desc spd = {
.pages = pages,
.partial = partial,
.flags = flags,
.ops = &page_cache_pipe_buf_ops,
};
index = *ppos >> PAGE_CACHE_SHIFT;
loff = *ppos & ~PAGE_CACHE_MASK;
nr_pages = (len + loff + PAGE_CACHE_SIZE - 1) >> PAGE_CACHE_SHIFT;
if (nr_pages > PIPE_BUFFERS)
nr_pages = PIPE_BUFFERS;
/*
* Initiate read-ahead on this page range. however, don't call into
* read-ahead if this is a non-zero offset (we are likely doing small
* chunk splice and the page is already there) for a single page.
*/
if (!loff || nr_pages > 1)
page_cache_readahead(mapping, &in->f_ra, in, index, nr_pages);
/*
* Now fill in the holes:
*/
error = 0;
total_len = 0;
/*
* Lookup the (hopefully) full range of pages we need.
*/
spd.nr_pages = find_get_pages_contig(mapping, index, nr_pages, pages);
/*
* If find_get_pages_contig() returned fewer pages than we needed,
* allocate the rest.
*/
index += spd.nr_pages;
while (spd.nr_pages < nr_pages) {
/*
* Page could be there, find_get_pages_contig() breaks on
* the first hole.
*/
page = find_get_page(mapping, index);
if (!page) {
/*
* Make sure the read-ahead engine is notified
* about this failure.
*/
handle_ra_miss(mapping, &in->f_ra, index);
/*
* page didn't exist, allocate one.
*/
page = page_cache_alloc_cold(mapping);
if (!page)
break;
error = add_to_page_cache_lru(page, mapping, index,
GFP_KERNEL);
if (unlikely(error)) {
page_cache_release(page);
if (error == -EEXIST)
continue;
break;
}
/*
* add_to_page_cache() locks the page, unlock it
* to avoid convoluting the logic below even more.
*/
unlock_page(page);
}
pages[spd.nr_pages++] = page;
index++;
}
/*
* Now loop over the map and see if we need to start IO on any
* pages, fill in the partial map, etc.
*/
index = *ppos >> PAGE_CACHE_SHIFT;
nr_pages = spd.nr_pages;
spd.nr_pages = 0;
for (page_nr = 0; page_nr < nr_pages; page_nr++) {
unsigned int this_len;
if (!len)
break;
/*
* this_len is the max we'll use from this page
*/
this_len = min_t(unsigned long, len, PAGE_CACHE_SIZE - loff);
page = pages[page_nr];
/*
* If the page isn't uptodate, we may need to start io on it
*/
if (!PageUptodate(page)) {
/*
* If in nonblock mode then dont block on waiting
* for an in-flight io page
*/
if (flags & SPLICE_F_NONBLOCK)
break;
lock_page(page);
/*
* page was truncated, stop here. if this isn't the
* first page, we'll just complete what we already
* added
*/
if (!page->mapping) {
unlock_page(page);
break;
}
/*
* page was already under io and is now done, great
*/
if (PageUptodate(page)) {
unlock_page(page);
goto fill_it;
}
/*
* need to read in the page
*/
error = mapping->a_ops->readpage(in, page);
if (unlikely(error)) {
/*
* We really should re-lookup the page here,
* but it complicates things a lot. Instead
* lets just do what we already stored, and
* we'll get it the next time we are called.
*/
if (error == AOP_TRUNCATED_PAGE)
error = 0;
break;
}
/*
* i_size must be checked after ->readpage().
*/
isize = i_size_read(mapping->host);
end_index = (isize - 1) >> PAGE_CACHE_SHIFT;
if (unlikely(!isize || index > end_index))
break;
/*
* if this is the last page, see if we need to shrink
* the length and stop
*/
if (end_index == index) {
loff = PAGE_CACHE_SIZE - (isize & ~PAGE_CACHE_MASK);
if (total_len + loff > isize)
break;
/*
* force quit after adding this page
*/
len = this_len;
this_len = min(this_len, loff);
loff = 0;
}
}
fill_it:
partial[page_nr].offset = loff;
partial[page_nr].len = this_len;
len -= this_len;
total_len += this_len;
loff = 0;
spd.nr_pages++;
index++;
}
/*
* Release any pages at the end, if we quit early. 'i' is how far
* we got, 'nr_pages' is how many pages are in the map.
*/
while (page_nr < nr_pages)
page_cache_release(pages[page_nr++]);
if (spd.nr_pages)
return splice_to_pipe(pipe, &spd);
return error;
}
/*
* attach the data from a bunch of pages on an inode to a call
*/
static int afs_send_pages(struct afs_call *call, struct msghdr *msg,
struct kvec *iov)
{
struct page *pages[8];
unsigned count, n, loop, offset, to;
pgoff_t first = call->first, last = call->last;
int ret;
_enter("");
offset = call->first_offset;
call->first_offset = 0;
do {
_debug("attach %lx-%lx", first, last);
count = last - first + 1;
if (count > ARRAY_SIZE(pages))
count = ARRAY_SIZE(pages);
n = find_get_pages_contig(call->mapping, first, count, pages);
ASSERTCMP(n, ==, count);
loop = 0;
do {
msg->msg_flags = 0;
to = PAGE_SIZE;
if (first + loop >= last)
to = call->last_to;
else
msg->msg_flags = MSG_MORE;
iov->iov_base = kmap(pages[loop]) + offset;
iov->iov_len = to - offset;
offset = 0;
_debug("- range %u-%u%s",
offset, to, msg->msg_flags ? " [more]" : "");
msg->msg_iov = (struct iovec *) iov;
msg->msg_iovlen = 1;
/* have to change the state *before* sending the last
* packet as RxRPC might give us the reply before it
* returns from sending the request */
if (first + loop >= last)
call->state = AFS_CALL_AWAIT_REPLY;
ret = rxrpc_kernel_send_data(call->rxcall, msg,
to - offset);
kunmap(pages[loop]);
if (ret < 0)
break;
} while (++loop < count);
first += count;
for (loop = 0; loop < count; loop++)
put_page(pages[loop]);
if (ret < 0)
break;
} while (first <= last);
_leave(" = %d", ret);
return ret;
}
/*
* Synchronously write back the locked page and any subsequent non-locked dirty
* pages.
*/
static int afs_write_back_from_locked_page(struct address_space *mapping,
struct writeback_control *wbc,
struct page *primary_page,
pgoff_t final_page)
{
struct afs_vnode *vnode = AFS_FS_I(mapping->host);
struct page *pages[8], *page;
unsigned long count, priv;
unsigned n, offset, to, f, t;
pgoff_t start, first, last;
int loop, ret;
_enter(",%lx", primary_page->index);
count = 1;
if (test_set_page_writeback(primary_page))
BUG();
/* Find all consecutive lockable dirty pages that have contiguous
* written regions, stopping when we find a page that is not
* immediately lockable, is not dirty or is missing, or we reach the
* end of the range.
*/
start = primary_page->index;
priv = page_private(primary_page);
offset = priv & AFS_PRIV_MAX;
to = priv >> AFS_PRIV_SHIFT;
trace_afs_page_dirty(vnode, tracepoint_string("store"),
primary_page->index, priv);
WARN_ON(offset == to);
if (offset == to)
trace_afs_page_dirty(vnode, tracepoint_string("WARN"),
primary_page->index, priv);
if (start >= final_page ||
(to < PAGE_SIZE && !test_bit(AFS_VNODE_NEW_CONTENT, &vnode->flags)))
goto no_more;
start++;
do {
_debug("more %lx [%lx]", start, count);
n = final_page - start + 1;
if (n > ARRAY_SIZE(pages))
n = ARRAY_SIZE(pages);
n = find_get_pages_contig(mapping, start, ARRAY_SIZE(pages), pages);
_debug("fgpc %u", n);
if (n == 0)
goto no_more;
if (pages[0]->index != start) {
do {
put_page(pages[--n]);
} while (n > 0);
goto no_more;
}
for (loop = 0; loop < n; loop++) {
page = pages[loop];
if (to != PAGE_SIZE &&
!test_bit(AFS_VNODE_NEW_CONTENT, &vnode->flags))
break;
if (page->index > final_page)
break;
if (!trylock_page(page))
break;
if (!PageDirty(page) || PageWriteback(page)) {
unlock_page(page);
break;
}
priv = page_private(page);
f = priv & AFS_PRIV_MAX;
t = priv >> AFS_PRIV_SHIFT;
if (f != 0 &&
!test_bit(AFS_VNODE_NEW_CONTENT, &vnode->flags)) {
unlock_page(page);
break;
}
to = t;
trace_afs_page_dirty(vnode, tracepoint_string("store+"),
page->index, priv);
if (!clear_page_dirty_for_io(page))
BUG();
if (test_set_page_writeback(page))
BUG();
unlock_page(page);
put_page(page);
}
count += loop;
if (loop < n) {
for (; loop < n; loop++)
put_page(pages[loop]);
goto no_more;
}
start += loop;
} while (start <= final_page && count < 65536);
no_more:
/* We now have a contiguous set of dirty pages, each with writeback
* set; the first page is still locked at this point, but all the rest
* have been unlocked.
*/
unlock_page(primary_page);
first = primary_page->index;
last = first + count - 1;
_debug("write back %lx[%u..] to %lx[..%u]", first, offset, last, to);
ret = afs_store_data(mapping, first, last, offset, to);
switch (ret) {
case 0:
ret = count;
break;
default:
pr_notice("kAFS: Unexpected error from FS.StoreData %d\n", ret);
/* Fall through */
case -EACCES:
case -EPERM:
case -ENOKEY:
case -EKEYEXPIRED:
case -EKEYREJECTED:
case -EKEYREVOKED:
afs_redirty_pages(wbc, mapping, first, last);
mapping_set_error(mapping, ret);
break;
case -EDQUOT:
case -ENOSPC:
afs_redirty_pages(wbc, mapping, first, last);
mapping_set_error(mapping, -ENOSPC);
break;
case -EROFS:
case -EIO:
case -EREMOTEIO:
case -EFBIG:
case -ENOENT:
case -ENOMEDIUM:
case -ENXIO:
afs_kill_pages(mapping, first, last);
mapping_set_error(mapping, ret);
break;
}
_leave(" = %d", ret);
return ret;
}
