linux-stable/fs/netfs/iterator.c

201 lines
5.3 KiB
C
Raw Normal View History

// SPDX-License-Identifier: GPL-2.0-or-later
/* Iterator helpers.
*
* Copyright (C) 2022 Red Hat, Inc. All Rights Reserved.
* Written by David Howells (dhowells@redhat.com)
*/
#include <linux/export.h>
#include <linux/slab.h>
#include <linux/mm.h>
#include <linux/uio.h>
#include <linux/scatterlist.h>
#include <linux/netfs.h>
#include "internal.h"
/**
* netfs_extract_user_iter - Extract the pages from a user iterator into a bvec
* @orig: The original iterator
* @orig_len: The amount of iterator to copy
* @new: The iterator to be set up
* @extraction_flags: Flags to qualify the request
*
* Extract the page fragments from the given amount of the source iterator and
* build up a second iterator that refers to all of those bits. This allows
* the original iterator to disposed of.
*
* @extraction_flags can have ITER_ALLOW_P2PDMA set to request peer-to-peer DMA be
* allowed on the pages extracted.
*
* On success, the number of elements in the bvec is returned, the original
* iterator will have been advanced by the amount extracted.
*
* The iov_iter_extract_mode() function should be used to query how cleanup
* should be performed.
*/
ssize_t netfs_extract_user_iter(struct iov_iter *orig, size_t orig_len,
struct iov_iter *new,
iov_iter_extraction_t extraction_flags)
{
struct bio_vec *bv = NULL;
struct page **pages;
unsigned int cur_npages;
unsigned int max_pages;
unsigned int npages = 0;
unsigned int i;
ssize_t ret;
size_t count = orig_len, offset, len;
size_t bv_size, pg_size;
if (WARN_ON_ONCE(!iter_is_ubuf(orig) && !iter_is_iovec(orig)))
return -EIO;
max_pages = iov_iter_npages(orig, INT_MAX);
bv_size = array_size(max_pages, sizeof(*bv));
bv = kvmalloc(bv_size, GFP_KERNEL);
if (!bv)
return -ENOMEM;
/* Put the page list at the end of the bvec list storage. bvec
* elements are larger than page pointers, so as long as we work
* 0->last, we should be fine.
*/
pg_size = array_size(max_pages, sizeof(*pages));
pages = (void *)bv + bv_size - pg_size;
while (count && npages < max_pages) {
ret = iov_iter_extract_pages(orig, &pages, count,
max_pages - npages, extraction_flags,
&offset);
if (ret < 0) {
pr_err("Couldn't get user pages (rc=%zd)\n", ret);
break;
}
if (ret > count) {
pr_err("get_pages rc=%zd more than %zu\n", ret, count);
break;
}
count -= ret;
ret += offset;
cur_npages = DIV_ROUND_UP(ret, PAGE_SIZE);
if (npages + cur_npages > max_pages) {
pr_err("Out of bvec array capacity (%u vs %u)\n",
npages + cur_npages, max_pages);
break;
}
for (i = 0; i < cur_npages; i++) {
len = ret > PAGE_SIZE ? PAGE_SIZE : ret;
46 fs/cifs (smb3 client) changesets, 37 in fs/cifs and 9 for related helper functions and cleanup outside from Dave Howells and Willy -----BEGIN PGP SIGNATURE----- iQGzBAABCgAdFiEE6fsu8pdIjtWE/DpLiiy9cAdyT1EFAmP2kaAACgkQiiy9cAdy T1Eergv9FHVs7hS0anJF0xgRghR4+g0m5UUo08iJazgJdDgcS5JY+ZasIpYpEsG3 QmsIT33XVYZypXoOzjMSsPlwo6esTCJQScVLz85e4ebedCbCBDks+wVQcbfTzD5/ KrwmUoTBLU0L/ppFhqRk9k53nrSf1SXCWPthjdfWa3mTHdIVM4kQJruTWwUDiJXp mdYwTx6FnTNer3QWetNzYOwdUgLu3rk0zLcBwQNCo6g5LOpA44iFfEAO4zeiOuZT LMDPbDj0nWQyWPLLdcbtsn2laYyEBDBLZevLirSaqPQ/KCtGcw0mBt6dCAzg8/CM ONqHHxdEpvPON8Sxujcn4CxpXhl0nCLwwtKtWU4rt7IevI9U+PynNl57TtJJ16/s b3XD2QVbFjlcdAMTmArvqnogdzoC3mZu1R1IRs+jukhLAOqZiLN6o/E2HAllt47i krzXeXIzQr10w9fnJ7LtIc/7IUFgtUfrOkg4TKyNcnRVHQaSSxv+JLRgqMPOr/M0 I7zt0G0j =4hIT -----END PGP SIGNATURE----- Merge tag '6.3-rc-smb3-client-fixes' of git://git.samba.org/sfrench/cifs-2.6 Pull cifs client updates from Steve French: "The largest subset of this is from David Howells et al: making the cifs/smb3 driver pass iov_iters down to the lowest layers, directly to the network transport rather than passing lists of pages around, helping multiple areas: - Pin user pages, thereby fixing the race between concurrent DIO read and fork, where the pages containing the DIO read buffer may end up belonging to the child process and not the parent - with the result that the parent might not see the retrieved data. - cifs shouldn't take refs on pages extracted from non-user-backed iterators (eg. KVEC). With these changes, cifs will apply the appropriate cleanup. - Making it easier to transition to using folios in cifs rather than pages by dealing with them through BVEC and XARRAY iterators. - Allowing cifs to use the new splice function The remainder are: - fixes for stable, including various fixes for uninitialized memory, wrong length field causing mount issue to very old servers, important directory lease fixes and reconnect fixes - cleanups (unused code removal, change one element array usage, and a change form strtobool to kstrtobool, and Kconfig cleanups) - SMBDIRECT (RDMA) fixes including iov_iter integration and UAF fixes - reconnect fixes - multichannel fixes, including improving channel allocation (to least used channel) - remove the last use of lock_page_killable by moving to folio_lock_killable" * tag '6.3-rc-smb3-client-fixes' of git://git.samba.org/sfrench/cifs-2.6: (46 commits) update internal module version number for cifs.ko cifs: update ip_addr for ses only for primary chan setup cifs: use tcon allocation functions even for dummy tcon cifs: use the least loaded channel for sending requests cifs: DIO to/from KVEC-type iterators should now work cifs: Remove unused code cifs: Build the RDMA SGE list directly from an iterator cifs: Change the I/O paths to use an iterator rather than a page list cifs: Add a function to read into an iter from a socket cifs: Add some helper functions cifs: Add a function to Hash the contents of an iterator cifs: Add a function to build an RDMA SGE list from an iterator netfs: Add a function to extract an iterator into a scatterlist netfs: Add a function to extract a UBUF or IOVEC into a BVEC iterator cifs: Implement splice_read to pass down ITER_BVEC not ITER_PIPE splice: Export filemap/direct_splice_read() iov_iter: Add a function to extract a page list from an iterator iov_iter: Define flags to qualify page extraction. splice: Add a func to do a splice from an O_DIRECT file without ITER_PIPE splice: Add a func to do a splice from a buffered file without ITER_PIPE ...
2023-02-23 01:12:44 +00:00
bvec_set_page(bv + npages + i, *pages++, len - offset, offset);
ret -= len;
offset = 0;
}
npages += cur_npages;
}
iov_iter_bvec(new, orig->data_source, bv, npages, orig_len - count);
return npages;
}
EXPORT_SYMBOL_GPL(netfs_extract_user_iter);
/*
* Select the span of a bvec iterator we're going to use. Limit it by both maximum
* size and maximum number of segments. Returns the size of the span in bytes.
*/
static size_t netfs_limit_bvec(const struct iov_iter *iter, size_t start_offset,
size_t max_size, size_t max_segs)
{
const struct bio_vec *bvecs = iter->bvec;
unsigned int nbv = iter->nr_segs, ix = 0, nsegs = 0;
size_t len, span = 0, n = iter->count;
size_t skip = iter->iov_offset + start_offset;
if (WARN_ON(!iov_iter_is_bvec(iter)) ||
WARN_ON(start_offset > n) ||
n == 0)
return 0;
while (n && ix < nbv && skip) {
len = bvecs[ix].bv_len;
if (skip < len)
break;
skip -= len;
n -= len;
ix++;
}
while (n && ix < nbv) {
len = min3(n, bvecs[ix].bv_len - skip, max_size);
span += len;
nsegs++;
ix++;
if (span >= max_size || nsegs >= max_segs)
break;
skip = 0;
n -= len;
}
return min(span, max_size);
}
/*
* Select the span of an xarray iterator we're going to use. Limit it by both
* maximum size and maximum number of segments. It is assumed that segments
* can be larger than a page in size, provided they're physically contiguous.
* Returns the size of the span in bytes.
*/
static size_t netfs_limit_xarray(const struct iov_iter *iter, size_t start_offset,
size_t max_size, size_t max_segs)
{
struct folio *folio;
unsigned int nsegs = 0;
loff_t pos = iter->xarray_start + iter->iov_offset;
pgoff_t index = pos / PAGE_SIZE;
size_t span = 0, n = iter->count;
XA_STATE(xas, iter->xarray, index);
if (WARN_ON(!iov_iter_is_xarray(iter)) ||
WARN_ON(start_offset > n) ||
n == 0)
return 0;
max_size = min(max_size, n - start_offset);
rcu_read_lock();
xas_for_each(&xas, folio, ULONG_MAX) {
size_t offset, flen, len;
if (xas_retry(&xas, folio))
continue;
if (WARN_ON(xa_is_value(folio)))
break;
if (WARN_ON(folio_test_hugetlb(folio)))
break;
flen = folio_size(folio);
offset = offset_in_folio(folio, pos);
len = min(max_size, flen - offset);
span += len;
nsegs++;
if (span >= max_size || nsegs >= max_segs)
break;
}
rcu_read_unlock();
return min(span, max_size);
}
size_t netfs_limit_iter(const struct iov_iter *iter, size_t start_offset,
size_t max_size, size_t max_segs)
{
if (iov_iter_is_bvec(iter))
return netfs_limit_bvec(iter, start_offset, max_size, max_segs);
if (iov_iter_is_xarray(iter))
return netfs_limit_xarray(iter, start_offset, max_size, max_segs);
BUG();
}
EXPORT_SYMBOL(netfs_limit_iter);